From a94fd40a18ae76ba76dbaa8eca0e3c46aa1142c1 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 6 Jun 2023 13:23:06 +0300
Subject: [PATCH 0001/1806] xfrm: delete not-needed clear to zero of encap_oa

After commit 2f4796518315 ("af_key: Fix heap information leak"), there is
no need to clear encap_oa again as it is already initialized to zero.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/key/af_key.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c
index a815f5ab4c49a..1cb4560afd44f 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1281,7 +1281,6 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 				ext_hdrs[SADB_X_EXT_NAT_T_DPORT-1];
 			natt->encap_dport = n_port->sadb_x_nat_t_port_port;
 		}
-		memset(&natt->encap_oa, 0, sizeof(natt->encap_oa));
 	}
 
 	err = xfrm_init_state(x);
-- 
GitLab


From da1a055d01ed0c18402dd1f1934096ac4bb36ada Mon Sep 17 00:00:00 2001
From: Sumitra Sharma <sumitraartsy@gmail.com>
Date: Fri, 23 Jun 2023 08:16:44 -0700
Subject: [PATCH 0002/1806] lib/test_bpf: Call page_address() on page acquired
 with GFP_KERNEL flag

generate_test_data() acquires a page with alloc_page(GFP_KERNEL).
The GFP_KERNEL is typical for kernel-internal allocations. The
caller requires ZONE_NORMAL or a lower zone for direct access.

Therefore the page cannot come from ZONE_HIGHMEM. Thus there's no
need to map it with kmap().

Also, the kmap() is being deprecated in favor of kmap_local_page() [1].

Hence, use a plain page_address() directly.

Since the page passed to the page_address() is not from the highmem
zone, the page_address() function will always return a valid kernel
virtual address and will not return NULL. Hence, remove the check
'if (!ptr)'.

Remove the unused variable 'ptr' and label 'err_free_page'.

  [1] https://lore.kernel.org/all/20220813220034.806698-1-ira.weiny@intel.com/

Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Fabio M. De Francesco <fmdefrancesco@gmail.com>
Signed-off-by: Sumitra Sharma <sumitraartsy@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Fabio M. De Francesco <fmdefrancesco@gmail.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/bpf/20230623151644.GA434468@sumitra.com
---
 lib/test_bpf.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index fa0833410ac18..913a7a079239e 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -14381,25 +14381,15 @@ static void *generate_test_data(struct bpf_test *test, int sub)
 		 * single fragment to the skb, filled with
 		 * test->frag_data.
 		 */
-		void *ptr;
-
 		page = alloc_page(GFP_KERNEL);
-
 		if (!page)
 			goto err_kfree_skb;
 
-		ptr = kmap(page);
-		if (!ptr)
-			goto err_free_page;
-		memcpy(ptr, test->frag_data, MAX_DATA);
-		kunmap(page);
+		memcpy(page_address(page), test->frag_data, MAX_DATA);
 		skb_add_rx_frag(skb, 0, page, 0, MAX_DATA, MAX_DATA);
 	}
 
 	return skb;
-
-err_free_page:
-	__free_page(page);
 err_kfree_skb:
 	kfree_skb(skb);
 	return NULL;
-- 
GitLab


From bbaf1ff06af49e856501024abbe161d96c1f0d66 Mon Sep 17 00:00:00 2001
From: Fangrui Song <maskray@google.com>
Date: Sat, 24 Jun 2023 00:18:56 +0000
Subject: [PATCH 0003/1806] bpf: Replace deprecated -target with --target= for
 Clang

The -target option has been deprecated since clang 3.4 in 2013. Therefore, use
the preferred --target=bpf form instead. This also matches how we use --target=
in scripts/Makefile.clang.

Signed-off-by: Fangrui Song <maskray@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Link: https://github.com/llvm/llvm-project/commit/274b6f0c87a6a1798de0a68135afc7f95def6277
Link: https://lore.kernel.org/bpf/20230624001856.1903733-1-maskray@google.com
---
 Documentation/bpf/bpf_devel_QA.rst              | 10 +++++-----
 Documentation/bpf/btf.rst                       |  4 ++--
 Documentation/bpf/llvm_reloc.rst                |  6 +++---
 drivers/hid/bpf/entrypoints/Makefile            |  2 +-
 kernel/bpf/preload/iterators/Makefile           |  2 +-
 samples/bpf/Makefile                            |  6 +++---
 samples/bpf/gnu/stubs.h                         |  2 +-
 samples/bpf/test_lwt_bpf.sh                     |  2 +-
 samples/hid/Makefile                            |  6 +++---
 tools/bpf/bpftool/Documentation/bpftool-gen.rst |  4 ++--
 tools/bpf/bpftool/Makefile                      |  2 +-
 tools/bpf/runqslower/Makefile                   |  2 +-
 tools/build/feature/Makefile                    |  2 +-
 tools/testing/selftests/bpf/Makefile            |  6 +++---
 tools/testing/selftests/bpf/gnu/stubs.h         |  2 +-
 tools/testing/selftests/hid/Makefile            |  6 +++---
 tools/testing/selftests/net/Makefile            |  4 ++--
 tools/testing/selftests/tc-testing/Makefile     |  2 +-
 18 files changed, 35 insertions(+), 35 deletions(-)

diff --git a/Documentation/bpf/bpf_devel_QA.rst b/Documentation/bpf/bpf_devel_QA.rst
index 609b71f5747d7..de27e1620821c 100644
--- a/Documentation/bpf/bpf_devel_QA.rst
+++ b/Documentation/bpf/bpf_devel_QA.rst
@@ -635,12 +635,12 @@ test coverage.
 
 Q: clang flag for target bpf?
 -----------------------------
-Q: In some cases clang flag ``-target bpf`` is used but in other cases the
+Q: In some cases clang flag ``--target=bpf`` is used but in other cases the
 default clang target, which matches the underlying architecture, is used.
 What is the difference and when I should use which?
 
 A: Although LLVM IR generation and optimization try to stay architecture
-independent, ``-target <arch>`` still has some impact on generated code:
+independent, ``--target=<arch>`` still has some impact on generated code:
 
 - BPF program may recursively include header file(s) with file scope
   inline assembly codes. The default target can handle this well,
@@ -658,7 +658,7 @@ independent, ``-target <arch>`` still has some impact on generated code:
   The clang option ``-fno-jump-tables`` can be used to disable
   switch table generation.
 
-- For clang ``-target bpf``, it is guaranteed that pointer or long /
+- For clang ``--target=bpf``, it is guaranteed that pointer or long /
   unsigned long types will always have a width of 64 bit, no matter
   whether underlying clang binary or default target (or kernel) is
   32 bit. However, when native clang target is used, then it will
@@ -668,7 +668,7 @@ independent, ``-target <arch>`` still has some impact on generated code:
   while the BPF LLVM back end still operates in 64 bit. The native
   target is mostly needed in tracing for the case of walking ``pt_regs``
   or other kernel structures where CPU's register width matters.
-  Otherwise, ``clang -target bpf`` is generally recommended.
+  Otherwise, ``clang --target=bpf`` is generally recommended.
 
 You should use default target when:
 
@@ -685,7 +685,7 @@ when:
   into these structures is verified by the BPF verifier and may result
   in verification failures if the native architecture is not aligned with
   the BPF architecture, e.g. 64-bit. An example of this is
-  BPF_PROG_TYPE_SK_MSG require ``-target bpf``
+  BPF_PROG_TYPE_SK_MSG require ``--target=bpf``
 
 
 .. Links
diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst
index 7cd7c5415a992..f32db1f44ae90 100644
--- a/Documentation/bpf/btf.rst
+++ b/Documentation/bpf/btf.rst
@@ -990,7 +990,7 @@ format.::
     } g2;
     int main() { return 0; }
     int test() { return 0; }
-    -bash-4.4$ clang -c -g -O2 -target bpf t2.c
+    -bash-4.4$ clang -c -g -O2 --target=bpf t2.c
     -bash-4.4$ readelf -S t2.o
       ......
       [ 8] .BTF              PROGBITS         0000000000000000  00000247
@@ -1000,7 +1000,7 @@ format.::
       [10] .rel.BTF.ext      REL              0000000000000000  000007e0
            0000000000000040  0000000000000010          16     9     8
       ......
-    -bash-4.4$ clang -S -g -O2 -target bpf t2.c
+    -bash-4.4$ clang -S -g -O2 --target=bpf t2.c
     -bash-4.4$ cat t2.s
       ......
             .section        .BTF,"",@progbits
diff --git a/Documentation/bpf/llvm_reloc.rst b/Documentation/bpf/llvm_reloc.rst
index e4a777a6a3a24..450e6403fe3de 100644
--- a/Documentation/bpf/llvm_reloc.rst
+++ b/Documentation/bpf/llvm_reloc.rst
@@ -28,7 +28,7 @@ For example, for the following code::
     return g1 + g2 + l1 + l2;
   }
 
-Compiled with ``clang -target bpf -O2 -c test.c``, the following is
+Compiled with ``clang --target=bpf -O2 -c test.c``, the following is
 the code with ``llvm-objdump -dr test.o``::
 
        0:       18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll
@@ -157,7 +157,7 @@ and ``call`` instructions. For example::
     return gfunc(a, b) +  lfunc(a, b) + global;
   }
 
-Compiled with ``clang -target bpf -O2 -c test.c``, we will have
+Compiled with ``clang --target=bpf -O2 -c test.c``, we will have
 following code with `llvm-objdump -dr test.o``::
 
   Disassembly of section .text:
@@ -203,7 +203,7 @@ The following is an example to show how R_BPF_64_ABS64 could be generated::
   int global() { return 0; }
   struct t { void *g; } gbl = { global };
 
-Compiled with ``clang -target bpf -O2 -g -c test.c``, we will see a
+Compiled with ``clang --target=bpf -O2 -g -c test.c``, we will see a
 relocation below in ``.data`` section with command
 ``llvm-readelf -r test.o``::
 
diff --git a/drivers/hid/bpf/entrypoints/Makefile b/drivers/hid/bpf/entrypoints/Makefile
index a12edcfa4fe3d..43b99b5575cfe 100644
--- a/drivers/hid/bpf/entrypoints/Makefile
+++ b/drivers/hid/bpf/entrypoints/Makefile
@@ -58,7 +58,7 @@ entrypoints.lskel.h: $(OUTPUT)/entrypoints.bpf.o | $(BPFTOOL)
 
 $(OUTPUT)/entrypoints.bpf.o: entrypoints.bpf.c $(OUTPUT)/vmlinux.h $(BPFOBJ) | $(OUTPUT)
 	$(call msg,BPF,$@)
-	$(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES)			      \
+	$(Q)$(CLANG) -g -O2 --target=bpf $(INCLUDES)			      \
 		 -c $(filter %.c,$^) -o $@ &&				      \
 	$(LLVM_STRIP) -g $@
 
diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile
index 8937dc6bc8d0c..b83c2f5e9be14 100644
--- a/kernel/bpf/preload/iterators/Makefile
+++ b/kernel/bpf/preload/iterators/Makefile
@@ -50,7 +50,7 @@ iterators.lskel-%.h: $(OUTPUT)/%/iterators.bpf.o | $(BPFTOOL)
 $(OUTPUT)/%/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT)
 	$(call msg,BPF,$@)
 	$(Q)mkdir -p $(@D)
-	$(Q)$(CLANG) -g -O2 -target bpf -m$* $(INCLUDES)		      \
+	$(Q)$(CLANG) -g -O2 --target=bpf -m$* $(INCLUDES)		      \
 		 -c $(filter %.c,$^) -o $@ &&				      \
 	$(LLVM_STRIP) -g $@
 
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 615f24ebc49cc..595b98d825cee 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -248,7 +248,7 @@ BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
 BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
 BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
-			  $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
+			  $(CLANG) --target=bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
 			  $(LLVM_READELF) -S ./llvm_btf_verify.o | grep BTF; \
 			  /bin/rm -f ./llvm_btf_verify.o)
 
@@ -370,7 +370,7 @@ endif
 clean-files += vmlinux.h
 
 # Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
 #
 # Use '-idirafter': Don't interfere with include mechanics except where the
@@ -392,7 +392,7 @@ $(obj)/xdp_router_ipv4.bpf.o: $(obj)/xdp_sample.bpf.o
 
 $(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/xdp_sample_shared.h
 	@echo "  CLANG-BPF " $@
-	$(Q)$(CLANG) -g -O2 -target bpf -D__TARGET_ARCH_$(SRCARCH) \
+	$(Q)$(CLANG) -g -O2 --target=bpf -D__TARGET_ARCH_$(SRCARCH) \
 		-Wno-compare-distinct-pointer-types -I$(srctree)/include \
 		-I$(srctree)/samples/bpf -I$(srctree)/tools/include \
 		-I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \
diff --git a/samples/bpf/gnu/stubs.h b/samples/bpf/gnu/stubs.h
index 719225b166269..1c638d9dce1a4 100644
--- a/samples/bpf/gnu/stubs.h
+++ b/samples/bpf/gnu/stubs.h
@@ -1 +1 @@
-/* dummy .h to trick /usr/include/features.h to work with 'clang -target bpf' */
+/* dummy .h to trick /usr/include/features.h to work with 'clang --target=bpf' */
diff --git a/samples/bpf/test_lwt_bpf.sh b/samples/bpf/test_lwt_bpf.sh
index 0bf2d0f6bf4ba..148e2df6cdcec 100755
--- a/samples/bpf/test_lwt_bpf.sh
+++ b/samples/bpf/test_lwt_bpf.sh
@@ -376,7 +376,7 @@ DST_MAC=$(lookup_mac $VETH1 $NS1)
 SRC_MAC=$(lookup_mac $VETH0)
 DST_IFINDEX=$(cat /sys/class/net/$VETH0/ifindex)
 
-CLANG_OPTS="-O2 -target bpf -I ../include/"
+CLANG_OPTS="-O2 --target=bpf -I ../include/"
 CLANG_OPTS+=" -DSRC_MAC=$SRC_MAC -DDST_MAC=$DST_MAC -DDST_IFINDEX=$DST_IFINDEX"
 clang $CLANG_OPTS -c $PROG_SRC -o $BPF_PROG
 
diff --git a/samples/hid/Makefile b/samples/hid/Makefile
index 026288280a035..9f7fe29dd7497 100644
--- a/samples/hid/Makefile
+++ b/samples/hid/Makefile
@@ -86,7 +86,7 @@ BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
 BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
 BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
-			  $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
+			  $(CLANG) --target=bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
 			  $(LLVM_READELF) -S ./llvm_btf_verify.o | grep BTF; \
 			  /bin/rm -f ./llvm_btf_verify.o)
 
@@ -181,7 +181,7 @@ endif
 clean-files += vmlinux.h
 
 # Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
 #
 # Use '-idirafter': Don't interfere with include mechanics except where the
@@ -198,7 +198,7 @@ EXTRA_BPF_HEADERS_SRC := $(addprefix $(src)/,$(EXTRA_BPF_HEADERS))
 
 $(obj)/%.bpf.o: $(src)/%.bpf.c $(EXTRA_BPF_HEADERS_SRC) $(obj)/vmlinux.h
 	@echo "  CLANG-BPF " $@
-	$(Q)$(CLANG) -g -O2 -target bpf -D__TARGET_ARCH_$(SRCARCH) \
+	$(Q)$(CLANG) -g -O2 --target=bpf -D__TARGET_ARCH_$(SRCARCH) \
 		-Wno-compare-distinct-pointer-types -I$(srctree)/include \
 		-I$(srctree)/samples/bpf -I$(srctree)/tools/include \
 		-I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \
diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
index 68454ef28f58e..5006e724d1bc0 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
@@ -260,9 +260,9 @@ EXAMPLES
 This is example BPF application with two BPF programs and a mix of BPF maps
 and global variables. Source code is split across two source code files.
 
-**$ clang -target bpf -g example1.bpf.c -o example1.bpf.o**
+**$ clang --target=bpf -g example1.bpf.c -o example1.bpf.o**
 
-**$ clang -target bpf -g example2.bpf.c -o example2.bpf.o**
+**$ clang --target=bpf -g example2.bpf.c -o example2.bpf.o**
 
 **$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o**
 
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 681fbcc5ed504..e9154ace80fff 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -216,7 +216,7 @@ $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP)
 		-I$(srctree)/tools/include/uapi/ \
 		-I$(LIBBPF_BOOTSTRAP_INCLUDE) \
 		-g -O2 -Wall -fno-stack-protector \
-		-target bpf -c $< -o $@
+		--target=bpf -c $< -o $@
 	$(Q)$(LLVM_STRIP) -g $@
 
 $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP)
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
index 47acf6936516f..d8288936c9120 100644
--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -62,7 +62,7 @@ $(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL)
 	$(QUIET_GEN)$(BPFTOOL) gen skeleton $< > $@
 
 $(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT)
-	$(QUIET_GEN)$(CLANG) -g -O2 -target bpf $(INCLUDES)		      \
+	$(QUIET_GEN)$(CLANG) -g -O2 --target=bpf $(INCLUDES)		      \
 		 -c $(filter %.c,$^) -o $@ &&				      \
 	$(LLVM_STRIP) -g $@
 
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 0f0aa9b7d7b5e..6654b1a35ab32 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -372,7 +372,7 @@ $(OUTPUT)test-libzstd.bin:
 	$(BUILD) -lzstd
 
 $(OUTPUT)test-clang-bpf-co-re.bin:
-	$(CLANG) -S -g -target bpf -o - $(patsubst %.bin,%.c,$(@F)) |	\
+	$(CLANG) -S -g --target=bpf -o - $(patsubst %.bin,%.c,$(@F)) |	\
 		grep BTF_KIND_VAR
 
 $(OUTPUT)test-file-handle.bin:
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 538df8fb8c42b..ad6b585e0d7c1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -331,7 +331,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
 #
 # Use '-idirafter': Don't interfere with include mechanics except where the
@@ -372,12 +372,12 @@ $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h
 # $3 - CFLAGS
 define CLANG_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v3 -o $2
+	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v3 -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
 define CLANG_NOALU32_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v2 -o $2
+	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2
 endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
diff --git a/tools/testing/selftests/bpf/gnu/stubs.h b/tools/testing/selftests/bpf/gnu/stubs.h
index 719225b166269..1c638d9dce1a4 100644
--- a/tools/testing/selftests/bpf/gnu/stubs.h
+++ b/tools/testing/selftests/bpf/gnu/stubs.h
@@ -1 +1 @@
-/* dummy .h to trick /usr/include/features.h to work with 'clang -target bpf' */
+/* dummy .h to trick /usr/include/features.h to work with 'clang --target=bpf' */
diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile
index 01c0491d64dab..2e986cbf1a463 100644
--- a/tools/testing/selftests/hid/Makefile
+++ b/tools/testing/selftests/hid/Makefile
@@ -167,7 +167,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
 #
 # Use '-idirafter': Don't interfere with include mechanics except where the
@@ -196,12 +196,12 @@ CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
 # $3 - CFLAGS
 define CLANG_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v3 -o $2
+	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v3 -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
 define CLANG_NOALU32_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v2 -o $2
+	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2
 endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 7f3ab2a93ed61..2f69f7274e3d8 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -113,7 +113,7 @@ $(MAKE_DIRS):
 	mkdir -p $@
 
 # Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
 #
 # Use '-idirafter': Don't interfere with include mechanics except where the
@@ -131,7 +131,7 @@ endif
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 
 $(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS)
-	$(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@
+	$(CLANG) -O2 --target=bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@
 
 $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	   $(APIDIR)/linux/bpf.h					       \
diff --git a/tools/testing/selftests/tc-testing/Makefile b/tools/testing/selftests/tc-testing/Makefile
index cb553eac9f419..3c4b7fa05075c 100644
--- a/tools/testing/selftests/tc-testing/Makefile
+++ b/tools/testing/selftests/tc-testing/Makefile
@@ -24,7 +24,7 @@ CLANG_FLAGS = -I. -I$(APIDIR) \
 
 $(OUTPUT)/%.o: %.c
 	$(CLANG) $(CLANG_FLAGS) \
-		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+		 -O2 --target=bpf -emit-llvm -c $< -o - |      \
 	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
 
 TEST_PROGS += ./tdc.sh
-- 
GitLab


From 85b0c6d4905ec21cd22cb18da701aa02278ccc4c Mon Sep 17 00:00:00 2001
From: Dave Thaler <dthaler@microsoft.com>
Date: Tue, 27 Jun 2023 21:39:12 +0000
Subject: [PATCH 0004/1806] bpf, docs: Fix definition of BPF_NEG operation

Instruction is an arithmetic negative, not a bitwise inverse.

Signed-off-by: Dave Thaler <dthaler@microsoft.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/bpf/20230627213912.951-1-dthaler1968@googlemail.com
---
 Documentation/bpf/instruction-set.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/bpf/instruction-set.rst b/Documentation/bpf/instruction-set.rst
index 6644842cd3ea1..751e657973f0b 100644
--- a/Documentation/bpf/instruction-set.rst
+++ b/Documentation/bpf/instruction-set.rst
@@ -165,7 +165,7 @@ BPF_OR    0x40   dst \|= src
 BPF_AND   0x50   dst &= src
 BPF_LSH   0x60   dst <<= (src & mask)
 BPF_RSH   0x70   dst >>= (src & mask)
-BPF_NEG   0x80   dst = ~src
+BPF_NEG   0x80   dst = -src
 BPF_MOD   0x90   dst = (src != 0) ? (dst % src) : dst
 BPF_XOR   0xa0   dst ^= src
 BPF_MOV   0xb0   dst = src
-- 
GitLab


From 17e8e5d6e09adb4b4f4fb5c89b3ec3fcae2c64a6 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 26 Jun 2023 15:19:42 +0200
Subject: [PATCH 0005/1806] selftests/bpf: Fix bpf_nf failure upon test rerun

Alexei reported:

  After fast forwarding bpf-next today bpf_nf test started to fail when
  run twice:

  $ ./test_progs -t bpf_nf
  #17      bpf_nf:OK
  Summary: 1/10 PASSED, 0 SKIPPED, 0 FAILED

  $ ./test_progs -t bpf_nf
  All error logs:
  test_bpf_nf_ct:PASS:test_bpf_nf__open_and_load 0 nsec
  test_bpf_nf_ct:PASS:iptables-legacy -t raw -A PREROUTING -j CONNMARK
  --set-mark 42/0 0 nsec
  (network_helpers.c:102: errno: Address already in use) Failed to bind socket
  test_bpf_nf_ct:FAIL:start_server unexpected start_server: actual -1 < expected 0
  #17/1    bpf_nf/xdp-ct:FAIL
  test_bpf_nf_ct:PASS:test_bpf_nf__open_and_load 0 nsec
  test_bpf_nf_ct:PASS:iptables-legacy -t raw -A PREROUTING -j CONNMARK
  --set-mark 42/0 0 nsec
  (network_helpers.c:102: errno: Address already in use) Failed to bind socket
  test_bpf_nf_ct:FAIL:start_server unexpected start_server: actual -1 < expected 0
  #17/2    bpf_nf/tc-bpf-ct:FAIL
  #17      bpf_nf:FAIL
  Summary: 0/8 PASSED, 0 SKIPPED, 1 FAILED

I was able to locally reproduce as well. Rearrange the connection teardown
so that the client closes its connection first so that we don't need to
linger in TCP time-wait.

Fixes: e81fbd4c1ba7 ("selftests/bpf: Add existing connection bpf_*_ct_lookup() test")
Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/CAADnVQ+0dnDq_v_vH1EfkacbfGnHANaon7zsw10pMb-D9FS0Pw@mail.gmail.com
Link: https://lore.kernel.org/bpf/20230626131942.5100-1-daniel@iogearbox.net
---
 tools/testing/selftests/bpf/prog_tests/bpf_nf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
index c8ba4009e4ab9..b30ff6b3b81ae 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
@@ -123,12 +123,13 @@ static void test_bpf_nf_ct(int mode)
 	ASSERT_EQ(skel->data->test_snat_addr, 0, "Test for source natting");
 	ASSERT_EQ(skel->data->test_dnat_addr, 0, "Test for destination natting");
 end:
-	if (srv_client_fd != -1)
-		close(srv_client_fd);
 	if (client_fd != -1)
 		close(client_fd);
+	if (srv_client_fd != -1)
+		close(srv_client_fd);
 	if (srv_fd != -1)
 		close(srv_fd);
+
 	snprintf(cmd, sizeof(cmd), iptables, "-D");
 	system(cmd);
 	test_bpf_nf__destroy(skel);
-- 
GitLab


From 819d43428a8661abccf8b9ecad94c7e6f23a0024 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 26 Jun 2023 14:25:21 -0700
Subject: [PATCH 0006/1806] bpf: Resolve modifiers when walking structs

It is impossible to use skb_frag_t in the tracing program. Resolve typedefs
when walking structs.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20230626212522.2414485-1-sdf@google.com
---
 kernel/bpf/btf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 29fe210992985..3dd47451f097a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6135,6 +6135,8 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf,
 
 	*flag = 0;
 again:
+	if (btf_type_is_modifier(t))
+		t = btf_type_skip_modifiers(btf, t->type, NULL);
 	tname = __btf_name_by_offset(btf, t->name_off);
 	if (!btf_type_is_struct(t)) {
 		bpf_log(log, "Type '%s' is not a struct\n", tname);
-- 
GitLab


From 2597a25cb865b17c1c9c2a0dcf4925e9d1a696bb Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 26 Jun 2023 14:25:22 -0700
Subject: [PATCH 0007/1806] selftests/bpf: Add test to exercise typedef walking

Add new bpf_fentry_test_sinfo with skb_shared_info argument and try to
access frags.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20230626212522.2414485-2-sdf@google.com
---
 net/bpf/test_run.c                            |  4 ++++
 .../selftests/bpf/prog_tests/verifier.c       |  2 ++
 .../selftests/bpf/progs/verifier_typedef.c    | 23 +++++++++++++++++++
 3 files changed, 29 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_typedef.c

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 2321bd2f9964f..63b11f7a5392b 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -555,6 +555,10 @@ __bpf_kfunc u32 bpf_fentry_test9(u32 *a)
 	return *a;
 }
 
+void noinline bpf_fentry_test_sinfo(struct skb_shared_info *sinfo)
+{
+}
+
 __bpf_kfunc int bpf_modify_return_test(int a, int *b)
 {
 	*b += 1;
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 070a13833c3f0..c375e59ff28da 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -58,6 +58,7 @@
 #include "verifier_stack_ptr.skel.h"
 #include "verifier_subprog_precision.skel.h"
 #include "verifier_subreg.skel.h"
+#include "verifier_typedef.skel.h"
 #include "verifier_uninit.skel.h"
 #include "verifier_unpriv.skel.h"
 #include "verifier_unpriv_perf.skel.h"
@@ -159,6 +160,7 @@ void test_verifier_spin_lock(void)            { RUN(verifier_spin_lock); }
 void test_verifier_stack_ptr(void)            { RUN(verifier_stack_ptr); }
 void test_verifier_subprog_precision(void)    { RUN(verifier_subprog_precision); }
 void test_verifier_subreg(void)               { RUN(verifier_subreg); }
+void test_verifier_typedef(void)              { RUN(verifier_typedef); }
 void test_verifier_uninit(void)               { RUN(verifier_uninit); }
 void test_verifier_unpriv(void)               { RUN(verifier_unpriv); }
 void test_verifier_unpriv_perf(void)          { RUN(verifier_unpriv_perf); }
diff --git a/tools/testing/selftests/bpf/progs/verifier_typedef.c b/tools/testing/selftests/bpf/progs/verifier_typedef.c
new file mode 100644
index 0000000000000..08481cfaac4b5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_typedef.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("fentry/bpf_fentry_test_sinfo")
+__description("typedef: resolve")
+__success __retval(0)
+__naked void resolve_typedef(void)
+{
+	asm volatile ("					\
+	r1 = *(u64 *)(r1 +0);				\
+	r2 = *(u64 *)(r1 +%[frags_offs]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(frags_offs,
+		      offsetof(struct skb_shared_info, frags))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From 223f5f79f2ce8facd9d77dd44e9f403343630bfc Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Fri, 23 Jun 2023 18:45:59 -0700
Subject: [PATCH 0008/1806] bpf, net: Check skb ownership against full socket.

Check skb ownership of an skb against full sockets instead of request_sock.

The filters were called only if an skb is owned by the sock that the skb is
sent out through. In another words, skb->sk should point to the sock that
it is sending through its egress. However, the filters would miss SYN/ACK
skbs that they are owned by a request_sock but sent through the listener
sock, that is the socket listening incoming connections.

However, the listener socket is also the full socket of the request socket.
We should use the full socket as the owner socket of an skb instead.

What is the ownership check for?
================================

BPF_CGROUP_RUN_PROG_INET_EGRESS() checked sk == skb->sk to ensure the
ownership of an skb. Alexei referred to a mailing list conversation [0]
that took place a few years ago. In that conversation, Daniel Borkmann
stated that:

    Wouldn't that mean however, when you go through stacked devices that
    you'd run the same eBPF cgroup program for skb->sk multiple times?

According to what Daniel said, the ownership check mentioned earlier
presumably prevents multiple calls of egress filters caused by an skb.

A test that reproduce this scenario shows that the BPF cgroup egress
programs can be called multiple times for one skb if this ownership
check is not there. So, we can not just remove this check.

Test Stacked Devices
====================

We use L2TP to build an environment of stacked devices. L2TP (Layer 2
Tunneling Protocol) is a tunneling protocol used to support virtual private
networks (VPNs). It relays encapsulated packets; for example in UDP, to its
peer by using a socket.

Using L2TP, packets are first sent through the IP stack and should then
arrive at an L2TP device. The device will expand its skb header to
encapsulate the packet. The skb will be sent back to the IP stack using
the socket that was made for the L2TP session. After that, the routing
process will occur once more, but this time for a new destination.

We changed tools/testing/selftests/net/l2tp.sh to set up a test environment
using L2TP. The run_ping() function in l2tp.sh is where the main change
occurred.

    run_ping()
    {
        local desc="$1"

        sleep 10
        run_cmd host-1 ${ping6} -s 227 -c 4 -i 10 -I fc00:101::1
        fc00:101::2
        log_test $? 0 "IPv6 route through L2TP tunnel ${desc}"
        sleep 10
    }

The test will use L2TP devices to send PING messages. These messages will
have a message size of 227 bytes as a special label to distinguish them.
This is not an ideal solution, but works.

During the execution of the test script, bpftrace was attached to
ip6_finish_output() and l2tp_xmit_skb():

    bpftrace -e '
      kfunc:ip6_finish_output {
        time("%H:%M:%S: ");
        printf("ip6_finish_output skb=%p skb->len=%d cgroup=%p sk=%p
                skb->sk=%p\n", args->skb, args->skb->len,
               args->sk->sk_cgrp_data.cgroup, args->sk, args->skb->sk); }
      kfunc:l2tp_xmit_skb {
        time("%H:%M:%S: ");
        printf("l2tp_xmit_skb skb=%p sk=%p\n", args->skb,
	       args->session->tunnel->sock); }'

The following is part of the output messages printed by bpftrace:

    16:35:20: ip6_finish_output skb=0xffff888103d8e600 skb->len=275
              cgroup=0xffff88810741f800 sk=0xffff888105f3b900
              skb->sk=0xffff888105f3b900

    16:35:20: l2tp_xmit_skb skb=0xffff888103d8e600 sk=0xffff888103dd6300

    16:35:20: ip6_finish_output skb=0xffff888103d8e600 skb->len=337
              cgroup=0xffff88810741f800 sk=0xffff888103dd6300
              skb->sk=0xffff888105f3b900

    16:35:20: ip6_finish_output skb=0xffff888103d8e600 skb->len=337
              cgroup=(nil) sk=(nil) skb->sk=(nil)

    16:35:20: ip6_finish_output skb=0xffff888103d8e000 skb->len=275
              cgroup=0xffffffff837741d0 sk=0xffff888101fe0000
              skb->sk=0xffff888101fe0000

    16:35:20: l2tp_xmit_skb skb=0xffff888103d8e000 sk=0xffff888103483180

    16:35:20: ip6_finish_output skb=0xffff888103d8e000 skb->len=337
              cgroup=0xffff88810741f800 sk=0xffff888103483180
              skb->sk=0xffff888101fe0000

    16:35:20: ip6_finish_output skb=0xffff888103d8e000 skb->len=337
              cgroup=(nil) sk=(nil) skb->sk=(nil)

The first four entries describe a PING message that was sent using the ping
command, whereas the following four entries describe the response received.
Multiple sockets are used to send one skb, including the socket used by the
L2TP session. This can be observed.

Based on this information, it seems that the ownership check is designed to
avoid multiple calls of egress filters caused by a single skb.

  [0] https://lore.kernel.org/all/58193E9D.7040201@iogearbox.net/

Signed-off-by: Kui-Feng Lee <kuifeng@meta.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230624014600.576756-2-kuifeng@meta.com
---
 include/linux/bpf-cgroup.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 57e9e109257e5..8506690dbb9ca 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -199,9 +199,9 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb)			       \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \
+	if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk) {		       \
 		typeof(sk) __sk = sk_to_full_sk(sk);			       \
-		if (sk_fullsock(__sk) &&				       \
+		if (sk_fullsock(__sk) && __sk == skb_to_full_sk(skb) &&	       \
 		    cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS))	       \
 			__ret = __cgroup_bpf_run_filter_skb(__sk, skb,	       \
 						      CGROUP_INET_EGRESS); \
-- 
GitLab


From 539c7e67aa4a170eea9a401464ec72a18a795a30 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Fri, 23 Jun 2023 18:46:00 -0700
Subject: [PATCH 0009/1806] selftests/bpf: Verify that the cgroup_skb filters
 receive expected packets.

This test case includes four scenarios:

1. Connect to the server from outside the cgroup and close the connection
   from outside the cgroup.
2. Connect to the server from outside the cgroup and close the connection
   from inside the cgroup.
3. Connect to the server from inside the cgroup and close the connection
   from outside the cgroup.
4. Connect to the server from inside the cgroup and close the connection
   from inside the cgroup.

The test case is to verify that cgroup_skb/{egress, ingress} filters
receive expected packets including SYN, SYN/ACK, ACK, FIN, and FIN/ACK.

Signed-off-by: Kui-Feng Lee <kuifeng@meta.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230624014600.576756-3-kuifeng@meta.com
---
 tools/testing/selftests/bpf/cgroup_helpers.c  |  12 +
 tools/testing/selftests/bpf/cgroup_helpers.h  |   1 +
 tools/testing/selftests/bpf/cgroup_tcp_skb.h  |  35 ++
 .../selftests/bpf/prog_tests/cgroup_tcp_skb.c | 402 ++++++++++++++++++
 .../selftests/bpf/progs/cgroup_tcp_skb.c      | 382 +++++++++++++++++
 5 files changed, 832 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/cgroup_tcp_skb.h
 create mode 100644 tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
 create mode 100644 tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c

diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 9e95b37a7dff2..2caee8423ee02 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -277,6 +277,18 @@ int join_cgroup(const char *relative_path)
 	return join_cgroup_from_top(cgroup_path);
 }
 
+/**
+ * join_root_cgroup() - Join the root cgroup
+ *
+ * This function joins the root cgroup.
+ *
+ * On success, it returns 0, otherwise on failure it returns 1.
+ */
+int join_root_cgroup(void)
+{
+	return join_cgroup_from_top(CGROUP_MOUNT_PATH);
+}
+
 /**
  * join_parent_cgroup() - Join a cgroup in the parent process workdir
  * @relative_path: The cgroup path, relative to parent process workdir, to join
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index f099a166c94d4..5c2cb9c8b5463 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -22,6 +22,7 @@ void remove_cgroup(const char *relative_path);
 unsigned long long get_cgroup_id(const char *relative_path);
 
 int join_cgroup(const char *relative_path);
+int join_root_cgroup(void);
 int join_parent_cgroup(const char *relative_path);
 
 int setup_cgroup_environment(void);
diff --git a/tools/testing/selftests/bpf/cgroup_tcp_skb.h b/tools/testing/selftests/bpf/cgroup_tcp_skb.h
new file mode 100644
index 0000000000000..7f6b24f102fbe
--- /dev/null
+++ b/tools/testing/selftests/bpf/cgroup_tcp_skb.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+/* Define states of a socket to tracking messages sending to and from the
+ * socket.
+ *
+ * These states are based on rfc9293 with some modifications to support
+ * tracking of messages sent out from a socket. For example, when a SYN is
+ * received, a new socket is transiting to the SYN_RECV state defined in
+ * rfc9293. But, we put it in SYN_RECV_SENDING_SYN_ACK state and when
+ * SYN-ACK is sent out, it moves to SYN_RECV state. With this modification,
+ * we can track the message sent out from a socket.
+ */
+
+#ifndef __CGROUP_TCP_SKB_H__
+#define __CGROUP_TCP_SKB_H__
+
+enum {
+	INIT,
+	CLOSED,
+	SYN_SENT,
+	SYN_RECV_SENDING_SYN_ACK,
+	SYN_RECV,
+	ESTABLISHED,
+	FIN_WAIT1,
+	FIN_WAIT2,
+	CLOSE_WAIT_SENDING_ACK,
+	CLOSE_WAIT,
+	CLOSING,
+	LAST_ACK,
+	TIME_WAIT_SENDING_ACK,
+	TIME_WAIT,
+};
+
+#endif /* __CGROUP_TCP_SKB_H__ */
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
new file mode 100644
index 0000000000000..95bab61a1e57b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
@@ -0,0 +1,402 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Facebook */
+#include <test_progs.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+#include <sched.h>
+#include <unistd.h>
+#include "cgroup_helpers.h"
+#include "testing_helpers.h"
+#include "cgroup_tcp_skb.skel.h"
+#include "cgroup_tcp_skb.h"
+
+#define CGROUP_TCP_SKB_PATH "/test_cgroup_tcp_skb"
+
+static int install_filters(int cgroup_fd,
+			   struct bpf_link **egress_link,
+			   struct bpf_link **ingress_link,
+			   struct bpf_program *egress_prog,
+			   struct bpf_program *ingress_prog,
+			   struct cgroup_tcp_skb *skel)
+{
+	/* Prepare filters */
+	skel->bss->g_sock_state = 0;
+	skel->bss->g_unexpected = 0;
+	*egress_link =
+		bpf_program__attach_cgroup(egress_prog,
+					   cgroup_fd);
+	if (!ASSERT_OK_PTR(egress_link, "egress_link"))
+		return -1;
+	*ingress_link =
+		bpf_program__attach_cgroup(ingress_prog,
+					   cgroup_fd);
+	if (!ASSERT_OK_PTR(ingress_link, "ingress_link"))
+		return -1;
+
+	return 0;
+}
+
+static void uninstall_filters(struct bpf_link **egress_link,
+			      struct bpf_link **ingress_link)
+{
+	bpf_link__destroy(*egress_link);
+	*egress_link = NULL;
+	bpf_link__destroy(*ingress_link);
+	*ingress_link = NULL;
+}
+
+static int create_client_sock_v6(void)
+{
+	int fd;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd < 0) {
+		perror("socket");
+		return -1;
+	}
+
+	return fd;
+}
+
+static int create_server_sock_v6(void)
+{
+	struct sockaddr_in6 addr = {
+		.sin6_family = AF_INET6,
+		.sin6_port = htons(0),
+		.sin6_addr = IN6ADDR_LOOPBACK_INIT,
+	};
+	int fd, err;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd < 0) {
+		perror("socket");
+		return -1;
+	}
+
+	err = bind(fd, (struct sockaddr *)&addr, sizeof(addr));
+	if (err < 0) {
+		perror("bind");
+		return -1;
+	}
+
+	err = listen(fd, 1);
+	if (err < 0) {
+		perror("listen");
+		return -1;
+	}
+
+	return fd;
+}
+
+static int get_sock_port_v6(int fd)
+{
+	struct sockaddr_in6 addr;
+	socklen_t len;
+	int err;
+
+	len = sizeof(addr);
+	err = getsockname(fd, (struct sockaddr *)&addr, &len);
+	if (err < 0) {
+		perror("getsockname");
+		return -1;
+	}
+
+	return ntohs(addr.sin6_port);
+}
+
+static int connect_client_server_v6(int client_fd, int listen_fd)
+{
+	struct sockaddr_in6 addr = {
+		.sin6_family = AF_INET6,
+		.sin6_addr = IN6ADDR_LOOPBACK_INIT,
+	};
+	int err;
+
+	addr.sin6_port = htons(get_sock_port_v6(listen_fd));
+	if (addr.sin6_port < 0)
+		return -1;
+
+	err = connect(client_fd, (struct sockaddr *)&addr, sizeof(addr));
+	if (err < 0) {
+		perror("connect");
+		return -1;
+	}
+
+	return 0;
+}
+
+/* Connect to the server in a cgroup from the outside of the cgroup. */
+static int talk_to_cgroup(int *client_fd, int *listen_fd, int *service_fd,
+			  struct cgroup_tcp_skb *skel)
+{
+	int err, cp;
+	char buf[5];
+
+	/* Create client & server socket */
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	*client_fd = create_client_sock_v6();
+	if (!ASSERT_GE(*client_fd, 0, "client_fd"))
+		return -1;
+	err = join_cgroup(CGROUP_TCP_SKB_PATH);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		return -1;
+	*listen_fd = create_server_sock_v6();
+	if (!ASSERT_GE(*listen_fd, 0, "listen_fd"))
+		return -1;
+	skel->bss->g_sock_port = get_sock_port_v6(*listen_fd);
+
+	/* Connect client to server */
+	err = connect_client_server_v6(*client_fd, *listen_fd);
+	if (!ASSERT_OK(err, "connect_client_server_v6"))
+		return -1;
+	*service_fd = accept(*listen_fd, NULL, NULL);
+	if (!ASSERT_GE(*service_fd, 0, "service_fd"))
+		return -1;
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	cp = write(*client_fd, "hello", 5);
+	if (!ASSERT_EQ(cp, 5, "write"))
+		return -1;
+	cp = read(*service_fd, buf, 5);
+	if (!ASSERT_EQ(cp, 5, "read"))
+		return -1;
+
+	return 0;
+}
+
+/* Connect to the server out of a cgroup from inside the cgroup. */
+static int talk_to_outside(int *client_fd, int *listen_fd, int *service_fd,
+			   struct cgroup_tcp_skb *skel)
+
+{
+	int err, cp;
+	char buf[5];
+
+	/* Create client & server socket */
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	*listen_fd = create_server_sock_v6();
+	if (!ASSERT_GE(*listen_fd, 0, "listen_fd"))
+		return -1;
+	err = join_cgroup(CGROUP_TCP_SKB_PATH);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		return -1;
+	*client_fd = create_client_sock_v6();
+	if (!ASSERT_GE(*client_fd, 0, "client_fd"))
+		return -1;
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	skel->bss->g_sock_port = get_sock_port_v6(*listen_fd);
+
+	/* Connect client to server */
+	err = connect_client_server_v6(*client_fd, *listen_fd);
+	if (!ASSERT_OK(err, "connect_client_server_v6"))
+		return -1;
+	*service_fd = accept(*listen_fd, NULL, NULL);
+	if (!ASSERT_GE(*service_fd, 0, "service_fd"))
+		return -1;
+	cp = write(*client_fd, "hello", 5);
+	if (!ASSERT_EQ(cp, 5, "write"))
+		return -1;
+	cp = read(*service_fd, buf, 5);
+	if (!ASSERT_EQ(cp, 5, "read"))
+		return -1;
+
+	return 0;
+}
+
+static int close_connection(int *closing_fd, int *peer_fd, int *listen_fd,
+			    struct cgroup_tcp_skb *skel)
+{
+	__u32 saved_packet_count = 0;
+	int err;
+	int i;
+
+	/* Wait for ACKs to be sent */
+	saved_packet_count = skel->bss->g_packet_count;
+	usleep(100000);		/* 0.1s */
+	for (i = 0;
+	     skel->bss->g_packet_count != saved_packet_count && i < 10;
+	     i++) {
+		saved_packet_count = skel->bss->g_packet_count;
+		usleep(100000);	/* 0.1s */
+	}
+	if (!ASSERT_EQ(skel->bss->g_packet_count, saved_packet_count,
+		       "packet_count"))
+		return -1;
+
+	skel->bss->g_packet_count = 0;
+	saved_packet_count = 0;
+
+	/* Half shutdown to make sure the closing socket having a chance to
+	 * receive a FIN from the peer.
+	 */
+	err = shutdown(*closing_fd, SHUT_WR);
+	if (!ASSERT_OK(err, "shutdown closing_fd"))
+		return -1;
+
+	/* Wait for FIN and the ACK of the FIN to be observed */
+	for (i = 0;
+	     skel->bss->g_packet_count < saved_packet_count + 2 && i < 10;
+	     i++)
+		usleep(100000);	/* 0.1s */
+	if (!ASSERT_GE(skel->bss->g_packet_count, saved_packet_count + 2,
+		       "packet_count"))
+		return -1;
+
+	saved_packet_count = skel->bss->g_packet_count;
+
+	/* Fully shutdown the connection */
+	err = close(*peer_fd);
+	if (!ASSERT_OK(err, "close peer_fd"))
+		return -1;
+	*peer_fd = -1;
+
+	/* Wait for FIN and the ACK of the FIN to be observed */
+	for (i = 0;
+	     skel->bss->g_packet_count < saved_packet_count + 2 && i < 10;
+	     i++)
+		usleep(100000);	/* 0.1s */
+	if (!ASSERT_GE(skel->bss->g_packet_count, saved_packet_count + 2,
+		       "packet_count"))
+		return -1;
+
+	err = close(*closing_fd);
+	if (!ASSERT_OK(err, "close closing_fd"))
+		return -1;
+	*closing_fd = -1;
+
+	close(*listen_fd);
+	*listen_fd = -1;
+
+	return 0;
+}
+
+/* This test case includes four scenarios:
+ * 1. Connect to the server from outside the cgroup and close the connection
+ *    from outside the cgroup.
+ * 2. Connect to the server from outside the cgroup and close the connection
+ *    from inside the cgroup.
+ * 3. Connect to the server from inside the cgroup and close the connection
+ *    from outside the cgroup.
+ * 4. Connect to the server from inside the cgroup and close the connection
+ *    from inside the cgroup.
+ *
+ * The test case is to verify that cgroup_skb/{egress,ingress} filters
+ * receive expected packets including SYN, SYN/ACK, ACK, FIN, and FIN/ACK.
+ */
+void test_cgroup_tcp_skb(void)
+{
+	struct bpf_link *ingress_link = NULL;
+	struct bpf_link *egress_link = NULL;
+	int client_fd = -1, listen_fd = -1;
+	struct cgroup_tcp_skb *skel;
+	int service_fd = -1;
+	int cgroup_fd = -1;
+	int err;
+
+	skel = cgroup_tcp_skb__open_and_load();
+	if (!ASSERT_OK(!skel, "skel_open_load"))
+		return;
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto cleanup;
+
+	cgroup_fd = create_and_get_cgroup(CGROUP_TCP_SKB_PATH);
+	if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd"))
+		goto cleanup;
+
+	/* Scenario 1 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.server_egress,
+			      skel->progs.server_ingress,
+			      skel);
+	if (!ASSERT_OK(err, "install_filters"))
+		goto cleanup;
+
+	err = talk_to_cgroup(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_cgroup"))
+		goto cleanup;
+
+	err = close_connection(&client_fd, &service_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, CLOSED, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+	/* Scenario 2 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.server_egress_srv,
+			      skel->progs.server_ingress_srv,
+			      skel);
+
+	err = talk_to_cgroup(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_cgroup"))
+		goto cleanup;
+
+	err = close_connection(&service_fd, &client_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, TIME_WAIT, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+	/* Scenario 3 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.client_egress_srv,
+			      skel->progs.client_ingress_srv,
+			      skel);
+
+	err = talk_to_outside(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_outside"))
+		goto cleanup;
+
+	err = close_connection(&service_fd, &client_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, CLOSED, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+	/* Scenario 4 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.client_egress,
+			      skel->progs.client_ingress,
+			      skel);
+
+	err = talk_to_outside(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_outside"))
+		goto cleanup;
+
+	err = close_connection(&client_fd, &service_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, TIME_WAIT, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+cleanup:
+	close(client_fd);
+	close(listen_fd);
+	close(service_fd);
+	close(cgroup_fd);
+	bpf_link__destroy(egress_link);
+	bpf_link__destroy(ingress_link);
+	cleanup_cgroup_environment();
+	cgroup_tcp_skb__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c
new file mode 100644
index 0000000000000..1e2e73f3b7493
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include "cgroup_tcp_skb.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u16 g_sock_port = 0;
+__u32 g_sock_state = 0;
+int g_unexpected = 0;
+__u32 g_packet_count = 0;
+
+int needed_tcp_pkt(struct __sk_buff *skb, struct tcphdr *tcph)
+{
+	struct ipv6hdr ip6h;
+
+	if (skb->protocol != bpf_htons(ETH_P_IPV6))
+		return 0;
+	if (bpf_skb_load_bytes(skb, 0, &ip6h, sizeof(ip6h)))
+		return 0;
+
+	if (ip6h.nexthdr != IPPROTO_TCP)
+		return 0;
+
+	if (bpf_skb_load_bytes(skb, sizeof(ip6h), tcph, sizeof(*tcph)))
+		return 0;
+
+	if (tcph->source != bpf_htons(g_sock_port) &&
+	    tcph->dest != bpf_htons(g_sock_port))
+		return 0;
+
+	return 1;
+}
+
+/* Run accept() on a socket in the cgroup to receive a new connection. */
+static int egress_accept(struct tcphdr *tcph)
+{
+	if (g_sock_state ==  SYN_RECV_SENDING_SYN_ACK) {
+		if (tcph->fin || !tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = SYN_RECV;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int ingress_accept(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case INIT:
+		if (!tcph->syn || tcph->fin || tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = SYN_RECV_SENDING_SYN_ACK;
+		break;
+	case SYN_RECV:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = ESTABLISHED;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+/* Run connect() on a socket in the cgroup to start a new connection. */
+static int egress_connect(struct tcphdr *tcph)
+{
+	if (g_sock_state == INIT) {
+		if (!tcph->syn || tcph->fin || tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = SYN_SENT;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int ingress_connect(struct tcphdr *tcph)
+{
+	if (g_sock_state == SYN_SENT) {
+		if (tcph->fin || !tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = ESTABLISHED;
+		return 1;
+	}
+
+	return 0;
+}
+
+/* The connection is closed by the peer outside the cgroup. */
+static int egress_close_remote(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		break;
+	case CLOSE_WAIT_SENDING_ACK:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = CLOSE_WAIT;
+		break;
+	case CLOSE_WAIT:
+		if (!tcph->fin)
+			g_unexpected++;
+		else
+			g_sock_state = LAST_ACK;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+static int ingress_close_remote(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		if (tcph->fin)
+			g_sock_state = CLOSE_WAIT_SENDING_ACK;
+		break;
+	case LAST_ACK:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = CLOSED;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+/* The connection is closed by the endpoint inside the cgroup. */
+static int egress_close_local(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		if (tcph->fin)
+			g_sock_state = FIN_WAIT1;
+		break;
+	case TIME_WAIT_SENDING_ACK:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = TIME_WAIT;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+static int ingress_close_local(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		break;
+	case FIN_WAIT1:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = FIN_WAIT2;
+		break;
+	case FIN_WAIT2:
+		if (!tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = TIME_WAIT_SENDING_ACK;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+/* Check the types of outgoing packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/egress")
+int server_egress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_accept(&tcph) || egress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/ingress")
+int server_ingress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_accept(&tcph) || ingress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of outgoing packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/egress")
+int server_egress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_accept(&tcph) || egress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/ingress")
+int server_ingress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_accept(&tcph) || ingress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of outgoing packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/egress")
+int client_egress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_connect(&tcph) || egress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/ingress")
+int client_ingress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_connect(&tcph) || ingress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of outgoing packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/egress")
+int client_egress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_connect(&tcph) || egress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/ingress")
+int client_ingress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_connect(&tcph) || ingress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
-- 
GitLab


From 2d2c95162de8fc6875c9c3d39f83527ae28e2e8a Mon Sep 17 00:00:00 2001
From: Andrea Terzolo <andreaterzolo3@gmail.com>
Date: Mon, 26 Jun 2023 11:36:14 +0200
Subject: [PATCH 0010/1806] libbpf: Skip modules BTF loading when CAP_SYS_ADMIN
 is missing

If during CO-RE relocations libbpf is not able to find the target type
in the running kernel BTF, it searches for it in modules' BTF.
The downside of this approach is that loading modules' BTF requires
CAP_SYS_ADMIN and this prevents BPF applications from running with more
granular capabilities (e.g. CAP_BPF) when they don't need to search
types into modules' BTF.

This patch skips by default modules' BTF loading phase when
CAP_SYS_ADMIN is missing.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Co-developed-by: Federico Di Pierro <nierro92@gmail.com>
Signed-off-by: Federico Di Pierro <nierro92@gmail.com>
Signed-off-by: Andrea Terzolo <andreaterzolo3@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/CAGQdkDvYU_e=_NX+6DRkL_-TeH3p+QtsdZwHkmH0w3Fuzw0C4w@mail.gmail.com
Link: https://lore.kernel.org/bpf/20230626093614.21270-1-andreaterzolo3@gmail.com
---
 tools/lib/bpf/libbpf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 214f828ece6bf..d793a1bfb70c0 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -5471,6 +5471,10 @@ static int load_module_btfs(struct bpf_object *obj)
 		err = bpf_btf_get_next_id(id, &id);
 		if (err && errno == ENOENT)
 			return 0;
+		if (err && errno == EPERM) {
+			pr_debug("skipping module BTFs loading, missing privileges\n");
+			return 0;
+		}
 		if (err) {
 			err = -errno;
 			pr_warn("failed to iterate BTF objects: %d\n", err);
-- 
GitLab


From 52364abb10b57074bf724ee2032e688180ed8bde Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 28 Jun 2023 17:27:37 +0200
Subject: [PATCH 0011/1806] libbpf: Add netfilter link attach helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add new api function: bpf_program__attach_netfilter.

It takes a bpf program (netfilter type), and a pointer to a option struct
that contains the desired attachment (protocol family, priority, hook
location, ...).

It returns a pointer to a 'bpf_link' structure or NULL on error.

Next patch adds new netfilter_basic test that uses this function to
attach a program to a few pf/hook/priority combinations.

v2: change name and use bpf_link_create.

Suggested-by: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/bpf/CAEf4BzZrmUv27AJp0dDxBDMY_B8e55-wLs8DUKK69vCWsCG_pQ@mail.gmail.com/
Link: https://lore.kernel.org/bpf/CAEf4BzZ69YgrQW7DHCJUT_X+GqMq_ZQQPBwopaJJVGFD5=d5Vg@mail.gmail.com/
Link: https://lore.kernel.org/bpf/20230628152738.22765-2-fw@strlen.de
---
 tools/lib/bpf/bpf.c      |  8 ++++++++
 tools/lib/bpf/bpf.h      |  6 ++++++
 tools/lib/bpf/libbpf.c   | 42 ++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.h   | 15 ++++++++++++++
 tools/lib/bpf/libbpf.map |  1 +
 5 files changed, 72 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index ed86b37d80243..3b0da19715e1d 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -741,6 +741,14 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, tracing))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_NETFILTER:
+		attr.link_create.netfilter.pf = OPTS_GET(opts, netfilter.pf, 0);
+		attr.link_create.netfilter.hooknum = OPTS_GET(opts, netfilter.hooknum, 0);
+		attr.link_create.netfilter.priority = OPTS_GET(opts, netfilter.priority, 0);
+		attr.link_create.netfilter.flags = OPTS_GET(opts, netfilter.flags, 0);
+		if (!OPTS_ZEROED(opts, netfilter))
+			return libbpf_err(-EINVAL);
+		break;
 	default:
 		if (!OPTS_ZEROED(opts, flags))
 			return libbpf_err(-EINVAL);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9aa0ee4737546..c676295ab9bfe 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -349,6 +349,12 @@ struct bpf_link_create_opts {
 		struct {
 			__u64 cookie;
 		} tracing;
+		struct {
+			__u32 pf;
+			__u32 hooknum;
+			__s32 priority;
+			__u32 flags;
+		} netfilter;
 	};
 	size_t :0;
 };
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d793a1bfb70c0..1c6588ad3e753 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -11815,6 +11815,48 @@ static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_l
 	return libbpf_get_error(*link);
 }
 
+struct bpf_link *bpf_program__attach_netfilter(const struct bpf_program *prog,
+					       const struct bpf_netfilter_opts *opts)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, lopts);
+	struct bpf_link *link;
+	int prog_fd, link_fd;
+
+	if (!OPTS_VALID(opts, bpf_netfilter_opts))
+		return libbpf_err_ptr(-EINVAL);
+
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
+	link = calloc(1, sizeof(*link));
+	if (!link)
+		return libbpf_err_ptr(-ENOMEM);
+
+	link->detach = &bpf_link__detach_fd;
+
+	lopts.netfilter.pf = OPTS_GET(opts, pf, 0);
+	lopts.netfilter.hooknum = OPTS_GET(opts, hooknum, 0);
+	lopts.netfilter.priority = OPTS_GET(opts, priority, 0);
+	lopts.netfilter.flags = OPTS_GET(opts, flags, 0);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_NETFILTER, &lopts);
+	if (link_fd < 0) {
+		char errmsg[STRERR_BUFSIZE];
+
+		link_fd = -errno;
+		free(link);
+		pr_warn("prog '%s': failed to attach to netfilter: %s\n",
+			prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
+		return libbpf_err_ptr(link_fd);
+	}
+	link->fd = link_fd;
+
+	return link;
+}
+
 struct bpf_link *bpf_program__attach(const struct bpf_program *prog)
 {
 	struct bpf_link *link = NULL;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 754da73c643b2..10642ad69d763 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -718,6 +718,21 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_freplace(const struct bpf_program *prog,
 			     int target_fd, const char *attach_func_name);
 
+struct bpf_netfilter_opts {
+	/* size of this struct, for forward/backward compatibility */
+	size_t sz;
+
+	__u32 pf;
+	__u32 hooknum;
+	__s32 priority;
+	__u32 flags;
+};
+#define bpf_netfilter_opts__last_field flags
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_netfilter(const struct bpf_program *prog,
+			      const struct bpf_netfilter_opts *opts);
+
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 7521a2fb76264..d9ec4407befa6 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -395,4 +395,5 @@ LIBBPF_1.2.0 {
 LIBBPF_1.3.0 {
 	global:
 		bpf_obj_pin_opts;
+		bpf_program__attach_netfilter;
 } LIBBPF_1.2.0;
-- 
GitLab


From a94098d490e17d652770f2309fcb9b46bc4cf864 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 28 Jun 2023 17:27:38 +0200
Subject: [PATCH 0012/1806] selftests/bpf: Add bpf_program__attach_netfilter
 helper test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Call bpf_program__attach_netfilter() with different
protocol/hook/priority combinations.

Test fails if supposedly-illegal attachments work
(e.g., bogus protocol family, illegal priority and so on) or if a
should-work attachment fails.  Expected output:

 ./test_progs -t netfilter_link_attach
 #145/1   netfilter_link_attach/allzero:OK
 #145/2   netfilter_link_attach/invalid-pf:OK
 #145/3   netfilter_link_attach/invalid-hooknum:OK
 #145/4   netfilter_link_attach/invalid-priority-min:OK
 #145/5   netfilter_link_attach/invalid-priority-max:OK
 #145/6   netfilter_link_attach/invalid-flags:OK
 #145/7   netfilter_link_attach/invalid-inet-not-supported:OK
 #145/8   netfilter_link_attach/attach ipv4:OK
 #145/9   netfilter_link_attach/attach ipv6:OK

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/bpf/20230628152738.22765-3-fw@strlen.de
---
 .../bpf/prog_tests/netfilter_link_attach.c    | 86 +++++++++++++++++++
 .../bpf/progs/test_netfilter_link_attach.c    | 14 +++
 2 files changed, 100 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c

diff --git a/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c
new file mode 100644
index 0000000000000..4297a2a4cb11b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <netinet/in.h>
+#include <linux/netfilter.h>
+
+#include "test_progs.h"
+#include "test_netfilter_link_attach.skel.h"
+
+struct nf_link_test {
+	__u32 pf;
+	__u32 hooknum;
+	__s32 priority;
+	__u32 flags;
+
+	bool expect_success;
+	const char * const name;
+};
+
+static const struct nf_link_test nf_hook_link_tests[] = {
+	{ .name = "allzero", },
+	{ .pf = NFPROTO_NUMPROTO, .name = "invalid-pf", },
+	{ .pf = NFPROTO_IPV4, .hooknum = 42, .name = "invalid-hooknum", },
+	{ .pf = NFPROTO_IPV4, .priority = INT_MIN, .name = "invalid-priority-min", },
+	{ .pf = NFPROTO_IPV4, .priority = INT_MAX, .name = "invalid-priority-max", },
+	{ .pf = NFPROTO_IPV4, .flags = UINT_MAX, .name = "invalid-flags", },
+
+	{ .pf = NFPROTO_INET, .priority = 1, .name = "invalid-inet-not-supported", },
+
+	{ .pf = NFPROTO_IPV4, .priority = -10000, .expect_success = true, .name = "attach ipv4", },
+	{ .pf = NFPROTO_IPV6, .priority =  10001, .expect_success = true, .name = "attach ipv6", },
+};
+
+void test_netfilter_link_attach(void)
+{
+	struct test_netfilter_link_attach *skel;
+	struct bpf_program *prog;
+	LIBBPF_OPTS(bpf_netfilter_opts, opts);
+	int i;
+
+	skel = test_netfilter_link_attach__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_netfilter_link_attach__open_and_load"))
+		goto out;
+
+	prog = skel->progs.nf_link_attach_test;
+	if (!ASSERT_OK_PTR(prog, "attach program"))
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(nf_hook_link_tests); i++) {
+		struct bpf_link *link;
+
+		if (!test__start_subtest(nf_hook_link_tests[i].name))
+			continue;
+
+#define X(opts, m, i)	opts.m = nf_hook_link_tests[(i)].m
+		X(opts, pf, i);
+		X(opts, hooknum, i);
+		X(opts, priority, i);
+		X(opts, flags, i);
+#undef X
+		link = bpf_program__attach_netfilter(prog, &opts);
+		if (nf_hook_link_tests[i].expect_success) {
+			struct bpf_link *link2;
+
+			if (!ASSERT_OK_PTR(link, "program attach successful"))
+				continue;
+
+			link2 = bpf_program__attach_netfilter(prog, &opts);
+			ASSERT_ERR_PTR(link2, "attach program with same pf/hook/priority");
+
+			if (!ASSERT_OK(bpf_link__destroy(link), "link destroy"))
+				break;
+
+			link2 = bpf_program__attach_netfilter(prog, &opts);
+			if (!ASSERT_OK_PTR(link2, "program reattach successful"))
+				continue;
+			if (!ASSERT_OK(bpf_link__destroy(link2), "link destroy"))
+				break;
+		} else {
+			ASSERT_ERR_PTR(link, "program load failure");
+		}
+	}
+
+out:
+	test_netfilter_link_attach__destroy(skel);
+}
+
diff --git a/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c b/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c
new file mode 100644
index 0000000000000..03a475160abe7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+#define NF_ACCEPT 1
+
+SEC("netfilter")
+int nf_link_attach_test(struct bpf_nf_ctx *ctx)
+{
+	return NF_ACCEPT;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From cf6eeb8f9dace014f63a3b2e959d0922bf737233 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Tue, 4 Jul 2023 15:40:14 +0800
Subject: [PATCH 0013/1806] bpf: Remove unnecessary ring buffer size check

The theoretical maximum size of ring buffer is about 64GB, but now the
size of ring buffer is specified by max_entries in bpf_attr and its
maximum value is (4GB - 1), and it won't be possible for overflow.

So just remove the unnecessary size check in ringbuf_map_alloc() but
keep the comments for possible extension in future.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Closes: https://lore.kernel.org/bpf/9c636a63-1f3d-442d-9223-96c2dccb9469@moroto.mountain
Link: https://lore.kernel.org/bpf/20230704074014.216616-1-houtao@huaweicloud.com
---
 kernel/bpf/ringbuf.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 875ac9b698d96..f045fde632e5f 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -23,15 +23,6 @@
 
 #define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4)
 
-/* Maximum size of ring buffer area is limited by 32-bit page offset within
- * record header, counted in pages. Reserve 8 bits for extensibility, and take
- * into account few extra pages for consumer/producer pages and
- * non-mmap()'able parts. This gives 64GB limit, which seems plenty for single
- * ring buffer.
- */
-#define RINGBUF_MAX_DATA_SZ \
-	(((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE)
-
 struct bpf_ringbuf {
 	wait_queue_head_t waitq;
 	struct irq_work work;
@@ -161,6 +152,17 @@ static void bpf_ringbuf_notify(struct irq_work *work)
 	wake_up_all(&rb->waitq);
 }
 
+/* Maximum size of ring buffer area is limited by 32-bit page offset within
+ * record header, counted in pages. Reserve 8 bits for extensibility, and
+ * take into account few extra pages for consumer/producer pages and
+ * non-mmap()'able parts, the current maximum size would be:
+ *
+ *     (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE)
+ *
+ * This gives 64GB limit, which seems plenty for single ring buffer. Now
+ * considering that the maximum value of data_sz is (4GB - 1), there
+ * will be no overflow, so just note the size limit in the comments.
+ */
 static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
 {
 	struct bpf_ringbuf *rb;
@@ -193,12 +195,6 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr)
 	    !PAGE_ALIGNED(attr->max_entries))
 		return ERR_PTR(-EINVAL);
 
-#ifdef CONFIG_64BIT
-	/* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */
-	if (attr->max_entries > RINGBUF_MAX_DATA_SZ)
-		return ERR_PTR(-E2BIG);
-#endif
-
 	rb_map = bpf_map_area_alloc(sizeof(*rb_map), NUMA_NO_NODE);
 	if (!rb_map)
 		return ERR_PTR(-ENOMEM);
-- 
GitLab


From ce1f289f541e34f5ae235cb66a5c130436f327f1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@rivosinc.com>
Date: Wed, 5 Jul 2023 13:39:25 +0200
Subject: [PATCH 0014/1806] selftests/bpf: Add
 F_NEEDS_EFFICIENT_UNALIGNED_ACCESS to some tests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some verifier tests were missing F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
which made the test fail. Add the flag where needed.

Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230705113926.751791-2-bjorn@kernel.org
---
 tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c | 1 +
 tools/testing/selftests/bpf/verifier/ctx_skb.c        | 2 ++
 tools/testing/selftests/bpf/verifier/jmp32.c          | 8 ++++++++
 tools/testing/selftests/bpf/verifier/map_kptr.c       | 2 ++
 tools/testing/selftests/bpf/verifier/precise.c        | 2 +-
 5 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
index b39665f33524f..319337bdcfc85 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
@@ -242,4 +242,5 @@
 	.result = REJECT,
 	.errstr = "R0 invalid mem access",
 	.errstr_unpriv = "R10 partial copy of pointer",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index 83cecfbd67394..0b394a7f7a2d5 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -1169,6 +1169,7 @@
        },
        .result = ACCEPT,
        .prog_type = BPF_PROG_TYPE_SK_SKB,
+       .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
        "pkt_end < pkt taken check",
@@ -1190,4 +1191,5 @@
        },
        .result = ACCEPT,
        .prog_type = BPF_PROG_TYPE_SK_SKB,
+       .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c
index 1a27a62105543..43776f6f92f47 100644
--- a/tools/testing/selftests/bpf/verifier/jmp32.c
+++ b/tools/testing/selftests/bpf/verifier/jmp32.c
@@ -290,6 +290,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jgt32: BPF_K",
@@ -360,6 +361,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jle32: BPF_K",
@@ -430,6 +432,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jlt32: BPF_K",
@@ -500,6 +503,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsge32: BPF_K",
@@ -570,6 +574,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsgt32: BPF_K",
@@ -640,6 +645,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsle32: BPF_K",
@@ -710,6 +716,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jslt32: BPF_K",
@@ -780,6 +787,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jgt32: range bound deduction, reg op imm",
diff --git a/tools/testing/selftests/bpf/verifier/map_kptr.c b/tools/testing/selftests/bpf/verifier/map_kptr.c
index a0cfc06d75bc8..d25c3e9605f13 100644
--- a/tools/testing/selftests/bpf/verifier/map_kptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_kptr.c
@@ -68,6 +68,7 @@
 	.fixup_map_kptr = { 1 },
 	.result = REJECT,
 	.errstr = "kptr access cannot have variable offset",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map_kptr: bpf_kptr_xchg non-const var_off",
@@ -121,6 +122,7 @@
 	.fixup_map_kptr = { 1 },
 	.result = REJECT,
 	.errstr = "kptr access misaligned expected=0 off=7",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map_kptr: reject var_off != 0",
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 99272bb890da8..0d84dd1f38b6b 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -216,7 +216,7 @@
 	},
 	.fixup_map_ringbuf = { 1 },
 	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = BPF_F_TEST_STATE_FREQ,
+	.flags = BPF_F_TEST_STATE_FREQ | F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	.errstr = "invalid access to memory, mem_size=1 off=42 size=8",
 	.result = REJECT,
 },
-- 
GitLab


From 21be9e477fd2e0b39b5180db6793a1ffeb84d504 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@rivosinc.com>
Date: Wed, 5 Jul 2023 13:39:26 +0200
Subject: [PATCH 0015/1806] selftests/bpf: Honor $(O) when figuring out paths
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When building the kselftests out-of-tree, e.g. ...

  | make ARCH=riscv CROSS_COMPILE=riscv64-linux-gnu- \
  |   O=/tmp/kselftest headers
  | make ARCH=riscv CROSS_COMPILE=riscv64-linux-gnu- \
  |  O=/tmp/kselftest HOSTCC=gcc FORMAT= \
  |  SKIP_TARGETS="arm64 ia64 powerpc sparc64 x86 sgx" \
  |  -C tools/testing/selftests gen_tar

... the kselftest build would not pick up the correct GENDIR path, and
therefore not including autoconf.h.

Correct that by taking $(O) into consideration when figuring out the
GENDIR path.

Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230705113926.751791-3-bjorn@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index ad6b585e0d7c1..daccc1b8573a6 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -12,7 +12,11 @@ BPFDIR := $(LIBDIR)/bpf
 TOOLSINCDIR := $(TOOLSDIR)/include
 BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
 APIDIR := $(TOOLSINCDIR)/uapi
+ifneq ($(O),)
+GENDIR := $(O)/include/generated
+else
 GENDIR := $(abspath ../../../../include/generated)
+endif
 GENHDR := $(GENDIR)/autoconf.h
 HOSTPKG_CONFIG := pkg-config
 
-- 
GitLab


From fd283ab196a867f8f65f36913e0fadd031fcb823 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Tue, 4 Jul 2023 10:50:39 +0800
Subject: [PATCH 0016/1806] selftests/bpf: Add benchmark for bpf memory
 allocator
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The benchmark could be used to compare the performance of hash map
operations and the memory usage between different flavors of bpf memory
allocator (e.g., no bpf ma vs bpf ma vs reuse-after-gp bpf ma). It also
could be used to check the performance improvement or the memory saving
provided by optimization.

The benchmark creates a non-preallocated hash map which uses bpf memory
allocator and shows the operation performance and the memory usage of
the hash map under different use cases:
(1) overwrite
Each CPU overwrites nonoverlapping part of hash map. When each CPU
completes overwriting of 64 elements in hash map, it increases the
op_count.
(2) batch_add_batch_del
Each CPU adds then deletes nonoverlapping part of hash map in batch.
When each CPU adds and deletes 64 elements in hash map, it increases
the op_count twice.
(3) add_del_on_diff_cpu
Each two-CPUs pair adds and deletes nonoverlapping part of map
cooperatively. When each CPU adds or deletes 64 elements in hash map,
it will increase the op_count.

The following is the benchmark results when comparing between different
flavors of bpf memory allocator. These tests are conducted on a KVM guest
with 8 CPUs and 16 GB memory. The command line below is used to do all
the following benchmarks:

  ./bench htab-mem --use-case $name ${OPTS} -w3 -d10 -a -p8

These results show that preallocated hash map has both better performance
and smaller memory footprint.

(1) non-preallocated + no bpf memory allocator (v6.0.19)
use kmalloc() + call_rcu

overwrite            per-prod-op: 11.24 ± 0.07k/s, avg mem: 82.64 ± 26.32MiB, peak mem: 119.18MiB
batch_add_batch_del  per-prod-op: 18.45 ± 0.10k/s, avg mem: 50.47 ± 14.51MiB, peak mem: 94.96MiB
add_del_on_diff_cpu  per-prod-op: 14.50 ± 0.03k/s, avg mem: 4.64 ± 0.73MiB, peak mem: 7.20MiB

(2) preallocated
OPTS=--preallocated

overwrite            per-prod-op: 191.42 ± 0.09k/s, avg mem: 1.24 ± 0.00MiB, peak mem: 1.49MiB
batch_add_batch_del  per-prod-op: 221.83 ± 0.17k/s, avg mem: 1.23 ± 0.00MiB, peak mem: 1.49MiB
add_del_on_diff_cpu  per-prod-op: 39.66 ± 0.31k/s, avg mem: 1.47 ± 0.13MiB, peak mem: 1.75MiB

(3) normal bpf memory allocator

overwrite            per-prod-op: 126.59 ± 0.02k/s, avg mem: 2.26 ± 0.00MiB, peak mem: 2.74MiB
batch_add_batch_del  per-prod-op: 83.37 ± 0.20k/s, avg mem: 2.14 ± 0.17MiB, peak mem: 2.74MiB
add_del_on_diff_cpu  per-prod-op: 21.25 ± 0.24k/s, avg mem: 17.50 ± 3.32MiB, peak mem: 28.87MiB

Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20230704025039.938914-1-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/Makefile          |   3 +
 tools/testing/selftests/bpf/bench.c           |   4 +
 .../selftests/bpf/benchs/bench_htab_mem.c     | 350 ++++++++++++++++++
 .../bpf/benchs/run_bench_htab_mem.sh          |  40 ++
 .../selftests/bpf/progs/htab_mem_bench.c      | 105 ++++++
 5 files changed, 502 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/benchs/bench_htab_mem.c
 create mode 100755 tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh
 create mode 100644 tools/testing/selftests/bpf/progs/htab_mem_bench.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index daccc1b8573a6..882be03b179fa 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -648,11 +648,13 @@ $(OUTPUT)/bench_local_storage.o: $(OUTPUT)/local_storage_bench.skel.h
 $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o: $(OUTPUT)/local_storage_rcu_tasks_trace_bench.skel.h
 $(OUTPUT)/bench_local_storage_create.o: $(OUTPUT)/bench_local_storage_create.skel.h
 $(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h
+$(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(TESTING_HELPERS) \
 		 $(TRACE_HELPERS) \
+		 $(CGROUP_HELPERS) \
 		 $(OUTPUT)/bench_count.o \
 		 $(OUTPUT)/bench_rename.o \
 		 $(OUTPUT)/bench_trigger.o \
@@ -665,6 +667,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o \
 		 $(OUTPUT)/bench_bpf_hashmap_lookup.o \
 		 $(OUTPUT)/bench_local_storage_create.o \
+		 $(OUTPUT)/bench_htab_mem.o \
 		 #
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 41fe5a82b88bc..73ce11b0547da 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -279,6 +279,7 @@ extern struct argp bench_local_storage_rcu_tasks_trace_argp;
 extern struct argp bench_strncmp_argp;
 extern struct argp bench_hashmap_lookup_argp;
 extern struct argp bench_local_storage_create_argp;
+extern struct argp bench_htab_mem_argp;
 
 static const struct argp_child bench_parsers[] = {
 	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
@@ -290,6 +291,7 @@ static const struct argp_child bench_parsers[] = {
 		"local_storage RCU Tasks Trace slowdown benchmark", 0 },
 	{ &bench_hashmap_lookup_argp, 0, "Hashmap lookup benchmark", 0 },
 	{ &bench_local_storage_create_argp, 0, "local-storage-create benchmark", 0 },
+	{ &bench_htab_mem_argp, 0, "hash map memory benchmark", 0 },
 	{},
 };
 
@@ -520,6 +522,7 @@ extern const struct bench bench_local_storage_cache_hashmap_control;
 extern const struct bench bench_local_storage_tasks_trace;
 extern const struct bench bench_bpf_hashmap_lookup;
 extern const struct bench bench_local_storage_create;
+extern const struct bench bench_htab_mem;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -561,6 +564,7 @@ static const struct bench *benchs[] = {
 	&bench_local_storage_tasks_trace,
 	&bench_bpf_hashmap_lookup,
 	&bench_local_storage_create,
+	&bench_htab_mem,
 };
 
 static void find_benchmark(void)
diff --git a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
new file mode 100644
index 0000000000000..9146d3f414d2e
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
@@ -0,0 +1,350 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <argp.h>
+#include <stdbool.h>
+#include <pthread.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/param.h>
+#include <fcntl.h>
+
+#include "bench.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+#include "htab_mem_bench.skel.h"
+
+struct htab_mem_use_case {
+	const char *name;
+	const char **progs;
+	/* Do synchronization between addition thread and deletion thread */
+	bool need_sync;
+};
+
+static struct htab_mem_ctx {
+	const struct htab_mem_use_case *uc;
+	struct htab_mem_bench *skel;
+	pthread_barrier_t *notify;
+	int fd;
+} ctx;
+
+const char *ow_progs[] = {"overwrite", NULL};
+const char *batch_progs[] = {"batch_add_batch_del", NULL};
+const char *add_del_progs[] = {"add_only", "del_only", NULL};
+const static struct htab_mem_use_case use_cases[] = {
+	{ .name = "overwrite", .progs = ow_progs },
+	{ .name = "batch_add_batch_del", .progs = batch_progs },
+	{ .name = "add_del_on_diff_cpu", .progs = add_del_progs, .need_sync = true },
+};
+
+static struct htab_mem_args {
+	u32 value_size;
+	const char *use_case;
+	bool preallocated;
+} args = {
+	.value_size = 8,
+	.use_case = "overwrite",
+	.preallocated = false,
+};
+
+enum {
+	ARG_VALUE_SIZE = 10000,
+	ARG_USE_CASE = 10001,
+	ARG_PREALLOCATED = 10002,
+};
+
+static const struct argp_option opts[] = {
+	{ "value-size", ARG_VALUE_SIZE, "VALUE_SIZE", 0,
+	  "Set the value size of hash map (default 8)" },
+	{ "use-case", ARG_USE_CASE, "USE_CASE", 0,
+	  "Set the use case of hash map: overwrite|batch_add_batch_del|add_del_on_diff_cpu" },
+	{ "preallocated", ARG_PREALLOCATED, NULL, 0, "use preallocated hash map" },
+	{},
+};
+
+static error_t htab_mem_parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_VALUE_SIZE:
+		args.value_size = strtoul(arg, NULL, 10);
+		if (args.value_size > 4096) {
+			fprintf(stderr, "too big value size %u\n", args.value_size);
+			argp_usage(state);
+		}
+		break;
+	case ARG_USE_CASE:
+		args.use_case = strdup(arg);
+		if (!args.use_case) {
+			fprintf(stderr, "no mem for use-case\n");
+			argp_usage(state);
+		}
+		break;
+	case ARG_PREALLOCATED:
+		args.preallocated = true;
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+const struct argp bench_htab_mem_argp = {
+	.options = opts,
+	.parser = htab_mem_parse_arg,
+};
+
+static void htab_mem_validate(void)
+{
+	if (!strcmp(use_cases[2].name, args.use_case) && env.producer_cnt % 2) {
+		fprintf(stderr, "%s needs an even number of producers\n", args.use_case);
+		exit(1);
+	}
+}
+
+static int htab_mem_bench_init_barriers(void)
+{
+	pthread_barrier_t *barriers;
+	unsigned int i, nr;
+
+	if (!ctx.uc->need_sync)
+		return 0;
+
+	nr = (env.producer_cnt + 1) / 2;
+	barriers = calloc(nr, sizeof(*barriers));
+	if (!barriers)
+		return -1;
+
+	/* Used for synchronization between two threads */
+	for (i = 0; i < nr; i++)
+		pthread_barrier_init(&barriers[i], NULL, 2);
+
+	ctx.notify = barriers;
+	return 0;
+}
+
+static void htab_mem_bench_exit_barriers(void)
+{
+	unsigned int i, nr;
+
+	if (!ctx.notify)
+		return;
+
+	nr = (env.producer_cnt + 1) / 2;
+	for (i = 0; i < nr; i++)
+		pthread_barrier_destroy(&ctx.notify[i]);
+	free(ctx.notify);
+}
+
+static const struct htab_mem_use_case *htab_mem_find_use_case_or_exit(const char *name)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(use_cases); i++) {
+		if (!strcmp(name, use_cases[i].name))
+			return &use_cases[i];
+	}
+
+	fprintf(stderr, "no such use-case: %s\n", name);
+	fprintf(stderr, "available use case:");
+	for (i = 0; i < ARRAY_SIZE(use_cases); i++)
+		fprintf(stderr, " %s", use_cases[i].name);
+	fprintf(stderr, "\n");
+	exit(1);
+}
+
+static void htab_mem_setup(void)
+{
+	struct bpf_map *map;
+	const char **names;
+	int err;
+
+	setup_libbpf();
+
+	ctx.uc = htab_mem_find_use_case_or_exit(args.use_case);
+	err = htab_mem_bench_init_barriers();
+	if (err) {
+		fprintf(stderr, "failed to init barrier\n");
+		exit(1);
+	}
+
+	ctx.fd = cgroup_setup_and_join("/htab_mem");
+	if (ctx.fd < 0)
+		goto cleanup;
+
+	ctx.skel = htab_mem_bench__open();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		goto cleanup;
+	}
+
+	map = ctx.skel->maps.htab;
+	bpf_map__set_value_size(map, args.value_size);
+	/* Ensure that different CPUs can operate on different subset */
+	bpf_map__set_max_entries(map, MAX(8192, 64 * env.nr_cpus));
+	if (args.preallocated)
+		bpf_map__set_map_flags(map, bpf_map__map_flags(map) & ~BPF_F_NO_PREALLOC);
+
+	names = ctx.uc->progs;
+	while (*names) {
+		struct bpf_program *prog;
+
+		prog = bpf_object__find_program_by_name(ctx.skel->obj, *names);
+		if (!prog) {
+			fprintf(stderr, "no such program %s\n", *names);
+			goto cleanup;
+		}
+		bpf_program__set_autoload(prog, true);
+		names++;
+	}
+	ctx.skel->bss->nr_thread = env.producer_cnt;
+
+	err = htab_mem_bench__load(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to load skeleton\n");
+		goto cleanup;
+	}
+	err = htab_mem_bench__attach(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to attach skeleton\n");
+		goto cleanup;
+	}
+	return;
+
+cleanup:
+	htab_mem_bench__destroy(ctx.skel);
+	htab_mem_bench_exit_barriers();
+	if (ctx.fd >= 0) {
+		close(ctx.fd);
+		cleanup_cgroup_environment();
+	}
+	exit(1);
+}
+
+static void htab_mem_add_fn(pthread_barrier_t *notify)
+{
+	while (true) {
+		/* Do addition */
+		(void)syscall(__NR_getpgid, 0);
+		/* Notify deletion thread to do deletion */
+		pthread_barrier_wait(notify);
+		/* Wait for deletion to complete */
+		pthread_barrier_wait(notify);
+	}
+}
+
+static void htab_mem_delete_fn(pthread_barrier_t *notify)
+{
+	while (true) {
+		/* Wait for addition to complete */
+		pthread_barrier_wait(notify);
+		/* Do deletion */
+		(void)syscall(__NR_getppid);
+		/* Notify addition thread to do addition */
+		pthread_barrier_wait(notify);
+	}
+}
+
+static void *htab_mem_producer(void *arg)
+{
+	pthread_barrier_t *notify;
+	int seq;
+
+	if (!ctx.uc->need_sync) {
+		while (true)
+			(void)syscall(__NR_getpgid, 0);
+		return NULL;
+	}
+
+	seq = (long)arg;
+	notify = &ctx.notify[seq / 2];
+	if (seq & 1)
+		htab_mem_delete_fn(notify);
+	else
+		htab_mem_add_fn(notify);
+	return NULL;
+}
+
+static void htab_mem_read_mem_cgrp_file(const char *name, unsigned long *value)
+{
+	char buf[32];
+	ssize_t got;
+	int fd;
+
+	fd = openat(ctx.fd, name, O_RDONLY);
+	if (fd < 0) {
+		/* cgroup v1 ? */
+		fprintf(stderr, "no %s\n", name);
+		*value = 0;
+		return;
+	}
+
+	got = read(fd, buf, sizeof(buf) - 1);
+	if (got <= 0) {
+		*value = 0;
+		return;
+	}
+	buf[got] = 0;
+
+	*value = strtoull(buf, NULL, 0);
+
+	close(fd);
+}
+
+static void htab_mem_measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.skel->bss->op_cnt, 0) / env.producer_cnt;
+	htab_mem_read_mem_cgrp_file("memory.current", &res->gp_ct);
+}
+
+static void htab_mem_report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	double loop, mem;
+
+	loop = res->hits / 1000.0 / (delta_ns / 1000000000.0);
+	mem = res->gp_ct / 1048576.0;
+	printf("Iter %3d (%7.3lfus): ", iter, (delta_ns - 1000000000) / 1000.0);
+	printf("per-prod-op %7.2lfk/s, memory usage %7.2lfMiB\n", loop, mem);
+}
+
+static void htab_mem_report_final(struct bench_res res[], int res_cnt)
+{
+	double mem_mean = 0.0, mem_stddev = 0.0;
+	double loop_mean = 0.0, loop_stddev = 0.0;
+	unsigned long peak_mem;
+	int i;
+
+	for (i = 0; i < res_cnt; i++) {
+		loop_mean += res[i].hits / 1000.0 / (0.0 + res_cnt);
+		mem_mean += res[i].gp_ct / 1048576.0 / (0.0 + res_cnt);
+	}
+	if (res_cnt > 1)  {
+		for (i = 0; i < res_cnt; i++) {
+			loop_stddev += (loop_mean - res[i].hits / 1000.0) *
+				       (loop_mean - res[i].hits / 1000.0) /
+				       (res_cnt - 1.0);
+			mem_stddev += (mem_mean - res[i].gp_ct / 1048576.0) *
+				      (mem_mean - res[i].gp_ct / 1048576.0) /
+				      (res_cnt - 1.0);
+		}
+		loop_stddev = sqrt(loop_stddev);
+		mem_stddev = sqrt(mem_stddev);
+	}
+
+	htab_mem_read_mem_cgrp_file("memory.peak", &peak_mem);
+	printf("Summary: per-prod-op %7.2lf \u00B1 %7.2lfk/s, memory usage %7.2lf \u00B1 %7.2lfMiB,"
+	       " peak memory usage %7.2lfMiB\n",
+	       loop_mean, loop_stddev, mem_mean, mem_stddev, peak_mem / 1048576.0);
+
+	cleanup_cgroup_environment();
+}
+
+const struct bench bench_htab_mem = {
+	.name = "htab-mem",
+	.argp = &bench_htab_mem_argp,
+	.validate = htab_mem_validate,
+	.setup = htab_mem_setup,
+	.producer_thread = htab_mem_producer,
+	.measure = htab_mem_measure,
+	.report_progress = htab_mem_report_progress,
+	.report_final = htab_mem_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh b/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh
new file mode 100755
index 0000000000000..9ff5832463a2b
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh
@@ -0,0 +1,40 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+htab_mem()
+{
+	echo -n "per-prod-op: "
+	echo -n "$*" | sed -E "s/.* per-prod-op\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+k\/s).*/\1/"
+	echo -n -e ", avg mem: "
+	echo -n "$*" | sed -E "s/.* memory usage\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+MiB).*/\1/"
+	echo -n ", peak mem: "
+	echo "$*" | sed -E "s/.* peak memory usage\s+([0-9]+\.[0-9]+MiB).*/\1/"
+}
+
+summarize_htab_mem()
+{
+	local bench="$1"
+	local summary=$(echo $2 | tail -n1)
+
+	printf "%-20s %s\n" "$bench" "$(htab_mem $summary)"
+}
+
+htab_mem_bench()
+{
+	local name
+
+	for name in overwrite batch_add_batch_del add_del_on_diff_cpu
+	do
+		summarize_htab_mem "$name" "$($RUN_BENCH htab-mem --use-case $name -p8 "$@")"
+	done
+}
+
+header "preallocated"
+htab_mem_bench "--preallocated"
+
+header "normal bpf ma"
+htab_mem_bench
diff --git a/tools/testing/selftests/bpf/progs/htab_mem_bench.c b/tools/testing/selftests/bpf/progs/htab_mem_bench.c
new file mode 100644
index 0000000000000..b1b721b14d678
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/htab_mem_bench.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <stdbool.h>
+#include <errno.h>
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define OP_BATCH 64
+
+struct update_ctx {
+	unsigned int from;
+	unsigned int step;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, 4);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} htab SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+unsigned char zeroed_value[4096];
+unsigned int nr_thread = 0;
+long op_cnt = 0;
+
+static int write_htab(unsigned int i, struct update_ctx *ctx, unsigned int flags)
+{
+	bpf_map_update_elem(&htab, &ctx->from, zeroed_value, flags);
+	ctx->from += ctx->step;
+
+	return 0;
+}
+
+static int overwrite_htab(unsigned int i, struct update_ctx *ctx)
+{
+	return write_htab(i, ctx, 0);
+}
+
+static int newwrite_htab(unsigned int i, struct update_ctx *ctx)
+{
+	return write_htab(i, ctx, BPF_NOEXIST);
+}
+
+static int del_htab(unsigned int i, struct update_ctx *ctx)
+{
+	bpf_map_delete_elem(&htab, &ctx->from);
+	ctx->from += ctx->step;
+
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getpgid")
+int overwrite(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id();
+	update.step = nr_thread;
+	bpf_loop(OP_BATCH, overwrite_htab, &update, 0);
+	__sync_fetch_and_add(&op_cnt, 1);
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getpgid")
+int batch_add_batch_del(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id();
+	update.step = nr_thread;
+	bpf_loop(OP_BATCH, overwrite_htab, &update, 0);
+
+	update.from = bpf_get_smp_processor_id();
+	bpf_loop(OP_BATCH, del_htab, &update, 0);
+
+	__sync_fetch_and_add(&op_cnt, 2);
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getpgid")
+int add_only(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id() / 2;
+	update.step = nr_thread / 2;
+	bpf_loop(OP_BATCH, newwrite_htab, &update, 0);
+	__sync_fetch_and_add(&op_cnt, 1);
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getppid")
+int del_only(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id() / 2;
+	update.step = nr_thread / 2;
+	bpf_loop(OP_BATCH, del_htab, &update, 0);
+	__sync_fetch_and_add(&op_cnt, 1);
+	return 0;
+}
-- 
GitLab


From 25954730461af01f66afa9e17036b051986b007e Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Thu, 6 Jul 2023 13:39:28 +0000
Subject: [PATCH 0017/1806] bpf: add percpu stats for bpf_map elements
 insertions/deletions

Add a generic percpu stats for bpf_map elements insertions/deletions in order
to keep track of both, the current (approximate) number of elements in a map
and per-cpu statistics on update/delete operations.

To expose these stats a particular map implementation should initialize the
counter and adjust it as needed using the 'bpf_map_*_elem_count' helpers
provided by this commit.

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230706133932.45883-2-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f58895830adae..360433f14496a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -275,6 +275,7 @@ struct bpf_map {
 	} owner;
 	bool bypass_spec_v1;
 	bool frozen; /* write-once; write-protected by freeze_mutex */
+	s64 __percpu *elem_count;
 };
 
 static inline const char *btf_field_type_name(enum btf_field_type type)
@@ -2040,6 +2041,35 @@ bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align,
 }
 #endif
 
+static inline int
+bpf_map_init_elem_count(struct bpf_map *map)
+{
+	size_t size = sizeof(*map->elem_count), align = size;
+	gfp_t flags = GFP_USER | __GFP_NOWARN;
+
+	map->elem_count = bpf_map_alloc_percpu(map, size, align, flags);
+	if (!map->elem_count)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline void
+bpf_map_free_elem_count(struct bpf_map *map)
+{
+	free_percpu(map->elem_count);
+}
+
+static inline void bpf_map_inc_elem_count(struct bpf_map *map)
+{
+	this_cpu_inc(*map->elem_count);
+}
+
+static inline void bpf_map_dec_elem_count(struct bpf_map *map)
+{
+	this_cpu_dec(*map->elem_count);
+}
+
 extern int sysctl_unprivileged_bpf_disabled;
 
 static inline bool bpf_allow_ptr_leaks(void)
-- 
GitLab


From 803370d3d37579e080e8c59f2360a072d0e45aff Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Thu, 6 Jul 2023 13:39:29 +0000
Subject: [PATCH 0018/1806] bpf: add a new kfunc to return current bpf_map
 elements count

A bpf_map_sum_elem_count kfunc was added to simplify getting the sum of the map
per-cpu element counters. If a map doesn't implement the counter, then the
function will always return 0.

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230706133932.45883-3-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/map_iter.c | 39 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index b0fa190b09790..d06d3b7150e57 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -93,7 +93,7 @@ static struct bpf_iter_reg bpf_map_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map, map),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.seq_info		= &bpf_map_seq_info,
 };
@@ -193,3 +193,40 @@ static int __init bpf_map_iter_init(void)
 }
 
 late_initcall(bpf_map_iter_init);
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in vmlinux BTF");
+
+__bpf_kfunc s64 bpf_map_sum_elem_count(struct bpf_map *map)
+{
+	s64 *pcount;
+	s64 ret = 0;
+	int cpu;
+
+	if (!map || !map->elem_count)
+		return 0;
+
+	for_each_possible_cpu(cpu) {
+		pcount = per_cpu_ptr(map->elem_count, cpu);
+		ret += READ_ONCE(*pcount);
+	}
+	return ret;
+}
+
+__diag_pop();
+
+BTF_SET8_START(bpf_map_iter_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS)
+BTF_SET8_END(bpf_map_iter_kfunc_ids)
+
+static const struct btf_kfunc_id_set bpf_map_iter_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &bpf_map_iter_kfunc_ids,
+};
+
+static int init_subsystem(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_map_iter_kfunc_set);
+}
+late_initcall(init_subsystem);
-- 
GitLab


From 9bc421b6be955c0960356210960d82707aa009e8 Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Thu, 6 Jul 2023 13:39:30 +0000
Subject: [PATCH 0019/1806] bpf: populate the per-cpu insertions/deletions
 counters for hashmaps

Initialize and utilize the per-cpu insertions/deletions counters for hash-based
maps. Non-trivial changes only apply to the preallocated maps for which the
{inc,dec}_elem_count functions are not called, as there's no need in counting
elements to sustain proper map operations.

To increase/decrease percpu counters for preallocated maps we add raw calls to
the bpf_map_{inc,dec}_elem_count functions so that the impact is minimal. For
dynamically allocated maps we add corresponding calls to the existing
{inc,dec}_elem_count functions.

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230706133932.45883-4-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/hashtab.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 56d3da7d0bc66..a8c7e1c5abfac 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -302,6 +302,7 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
 	struct htab_elem *l;
 
 	if (node) {
+		bpf_map_inc_elem_count(&htab->map);
 		l = container_of(node, struct htab_elem, lru_node);
 		memcpy(l->key, key, htab->map.key_size);
 		return l;
@@ -510,12 +511,16 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	    htab->n_buckets > U32_MAX / sizeof(struct bucket))
 		goto free_htab;
 
+	err = bpf_map_init_elem_count(&htab->map);
+	if (err)
+		goto free_htab;
+
 	err = -ENOMEM;
 	htab->buckets = bpf_map_area_alloc(htab->n_buckets *
 					   sizeof(struct bucket),
 					   htab->map.numa_node);
 	if (!htab->buckets)
-		goto free_htab;
+		goto free_elem_count;
 
 	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) {
 		htab->map_locked[i] = bpf_map_alloc_percpu(&htab->map,
@@ -593,6 +598,8 @@ free_map_locked:
 	bpf_map_area_free(htab->buckets);
 	bpf_mem_alloc_destroy(&htab->pcpu_ma);
 	bpf_mem_alloc_destroy(&htab->ma);
+free_elem_count:
+	bpf_map_free_elem_count(&htab->map);
 free_htab:
 	lockdep_unregister_key(&htab->lockdep_key);
 	bpf_map_area_free(htab);
@@ -804,6 +811,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 		if (l == tgt_l) {
 			hlist_nulls_del_rcu(&l->hash_node);
 			check_and_free_fields(htab, l);
+			bpf_map_dec_elem_count(&htab->map);
 			break;
 		}
 
@@ -900,6 +908,8 @@ static bool is_map_full(struct bpf_htab *htab)
 
 static void inc_elem_count(struct bpf_htab *htab)
 {
+	bpf_map_inc_elem_count(&htab->map);
+
 	if (htab->use_percpu_counter)
 		percpu_counter_add_batch(&htab->pcount, 1, PERCPU_COUNTER_BATCH);
 	else
@@ -908,6 +918,8 @@ static void inc_elem_count(struct bpf_htab *htab)
 
 static void dec_elem_count(struct bpf_htab *htab)
 {
+	bpf_map_dec_elem_count(&htab->map);
+
 	if (htab->use_percpu_counter)
 		percpu_counter_add_batch(&htab->pcount, -1, PERCPU_COUNTER_BATCH);
 	else
@@ -920,6 +932,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 	htab_put_fd_value(htab, l);
 
 	if (htab_is_prealloc(htab)) {
+		bpf_map_dec_elem_count(&htab->map);
 		check_and_free_fields(htab, l);
 		__pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
@@ -1000,6 +1013,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			if (!l)
 				return ERR_PTR(-E2BIG);
 			l_new = container_of(l, struct htab_elem, fnode);
+			bpf_map_inc_elem_count(&htab->map);
 		}
 	} else {
 		if (is_map_full(htab))
@@ -1168,6 +1182,7 @@ err:
 static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem)
 {
 	check_and_free_fields(htab, elem);
+	bpf_map_dec_elem_count(&htab->map);
 	bpf_lru_push_free(&htab->lru, &elem->lru_node);
 }
 
@@ -1357,8 +1372,10 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 err:
 	htab_unlock_bucket(htab, b, hash, flags);
 err_lock_bucket:
-	if (l_new)
+	if (l_new) {
+		bpf_map_dec_elem_count(&htab->map);
 		bpf_lru_push_free(&htab->lru, &l_new->lru_node);
+	}
 	return ret;
 }
 
@@ -1523,6 +1540,7 @@ static void htab_map_free(struct bpf_map *map)
 		prealloc_destroy(htab);
 	}
 
+	bpf_map_free_elem_count(map);
 	free_percpu(htab->extra_elems);
 	bpf_map_area_free(htab->buckets);
 	bpf_mem_alloc_destroy(&htab->pcpu_ma);
-- 
GitLab


From 515ee52b2224f73f63ac031cbf400cd513d2f45b Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Thu, 6 Jul 2023 13:39:31 +0000
Subject: [PATCH 0020/1806] bpf: make preloaded map iterators to display map
 elements count

Add another column to the /sys/fs/bpf/maps.debug iterator to display
cur_entries, the current number of entries in the map as is returned
by the bpf_map_sum_elem_count kfunc. Also fix formatting.

Example:

    # cat /sys/fs/bpf/maps.debug
      id name             max_entries  cur_entries
       2 iterator.rodata            1            0
     125 cilium_auth_map       524288          666
     126 cilium_runtime_          256            0
     127 cilium_signals            32            0
     128 cilium_node_map        16384         1344
     129 cilium_events             32            0
     ...

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230706133932.45883-5-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/preload/iterators/iterators.bpf.c  |   9 +-
 .../iterators/iterators.lskel-little-endian.h | 526 +++++++++---------
 2 files changed, 275 insertions(+), 260 deletions(-)

diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c
index 03af863314ea7..b78968b63fab7 100644
--- a/kernel/bpf/preload/iterators/iterators.bpf.c
+++ b/kernel/bpf/preload/iterators/iterators.bpf.c
@@ -73,6 +73,8 @@ static const char *get_name(struct btf *btf, long btf_id, const char *fallback)
 	return str + name_off;
 }
 
+__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym;
+
 SEC("iter/bpf_map")
 int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 {
@@ -84,9 +86,12 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 		return 0;
 
 	if (seq_num == 0)
-		BPF_SEQ_PRINTF(seq, "  id name             max_entries\n");
+		BPF_SEQ_PRINTF(seq, "  id name             max_entries  cur_entries\n");
+
+	BPF_SEQ_PRINTF(seq, "%4u %-16s  %10d   %10lld\n",
+		       map->id, map->name, map->max_entries,
+		       bpf_map_sum_elem_count(map));
 
-	BPF_SEQ_PRINTF(seq, "%4u %-16s%6d\n", map->id, map->name, map->max_entries);
 	return 0;
 }
 
diff --git a/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h
index 70f236a82fe19..5b98ab02025eb 100644
--- a/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h
+++ b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-/* THIS FILE IS AUTOGENERATED! */
+/* THIS FILE IS AUTOGENERATED BY BPFTOOL! */
 #ifndef __ITERATORS_BPF_SKEL_H__
 #define __ITERATORS_BPF_SKEL_H__
 
@@ -18,8 +18,6 @@ struct iterators_bpf {
 		int dump_bpf_map_fd;
 		int dump_bpf_prog_fd;
 	} links;
-	struct iterators_bpf__rodata {
-	} *rodata;
 };
 
 static inline int
@@ -68,7 +66,6 @@ iterators_bpf__destroy(struct iterators_bpf *skel)
 	iterators_bpf__detach(skel);
 	skel_closenz(skel->progs.dump_bpf_map.prog_fd);
 	skel_closenz(skel->progs.dump_bpf_prog.prog_fd);
-	skel_free_map_data(skel->rodata, skel->maps.rodata.initial_value, 4096);
 	skel_closenz(skel->maps.rodata.map_fd);
 	skel_free(skel);
 }
@@ -81,15 +78,6 @@ iterators_bpf__open(void)
 	if (!skel)
 		goto cleanup;
 	skel->ctx.sz = (void *)&skel->links - (void *)skel;
-	skel->rodata = skel_prep_map_data((void *)"\
-\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
-\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\
-\x25\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\
-\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\
-\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0", 4096, 98);
-	if (!skel->rodata)
-		goto cleanup;
-	skel->maps.rodata.initial_value = (__u64) (long) skel->rodata;
 	return skel;
 cleanup:
 	iterators_bpf__destroy(skel);
@@ -103,7 +91,7 @@ iterators_bpf__load(struct iterators_bpf *skel)
 	int err;
 
 	opts.ctx = (struct bpf_loader_ctx *)skel;
-	opts.data_sz = 6056;
+	opts.data_sz = 6208;
 	opts.data = (void *)"\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
@@ -138,190 +126,197 @@ iterators_bpf__load(struct iterators_bpf *skel)
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x9f\xeb\x01\0\
-\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\xf9\x04\0\0\0\0\0\0\0\0\0\x02\x02\0\
+\x18\0\0\0\0\0\0\0\x80\x04\0\0\x80\x04\0\0\x31\x05\0\0\0\0\0\0\0\0\0\x02\x02\0\
 \0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\0\0\0\x04\
 \0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\0\0\0\0\0\
 \0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\0\0\0\x20\
-\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xa3\0\0\0\x03\0\0\x04\x18\0\0\0\xb1\0\
-\0\0\x09\0\0\0\0\0\0\0\xb5\0\0\0\x0b\0\0\0\x40\0\0\0\xc0\0\0\0\x0b\0\0\0\x80\0\
-\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xc8\0\0\0\0\0\0\x07\0\0\0\0\xd1\0\0\0\0\0\0\
-\x08\x0c\0\0\0\xd7\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\x94\x01\0\0\x03\0\0\x04\
-\x18\0\0\0\x9c\x01\0\0\x0e\0\0\0\0\0\0\0\x9f\x01\0\0\x11\0\0\0\x20\0\0\0\xa4\
-\x01\0\0\x0e\0\0\0\xa0\0\0\0\xb0\x01\0\0\0\0\0\x08\x0f\0\0\0\xb6\x01\0\0\0\0\0\
-\x01\x04\0\0\0\x20\0\0\0\xc3\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\0\0\0\
-\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xc8\x01\0\0\0\0\0\x01\x04\0\0\0\
-\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x2c\x02\0\0\x02\0\0\x04\x10\0\0\0\x13\0\
-\0\0\x03\0\0\0\0\0\0\0\x3f\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x18\0\
-\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x44\x02\0\0\x01\0\0\x0c\
-\x16\0\0\0\x90\x02\0\0\x01\0\0\x04\x08\0\0\0\x99\x02\0\0\x19\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\x02\x1a\0\0\0\xea\x02\0\0\x06\0\0\x04\x38\0\0\0\x9c\x01\0\0\x0e\0\0\
-\0\0\0\0\0\x9f\x01\0\0\x11\0\0\0\x20\0\0\0\xf7\x02\0\0\x1b\0\0\0\xc0\0\0\0\x08\
-\x03\0\0\x15\0\0\0\0\x01\0\0\x11\x03\0\0\x1d\0\0\0\x40\x01\0\0\x1b\x03\0\0\x1e\
-\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x1c\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\0\0\0\0\
-\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x65\x03\0\0\x02\0\0\x04\
-\x08\0\0\0\x73\x03\0\0\x0e\0\0\0\0\0\0\0\x7c\x03\0\0\x0e\0\0\0\x20\0\0\0\x1b\
-\x03\0\0\x03\0\0\x04\x18\0\0\0\x86\x03\0\0\x1b\0\0\0\0\0\0\0\x8e\x03\0\0\x21\0\
-\0\0\x40\0\0\0\x94\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\0\0\0\
-\0\0\0\0\0\x02\x24\0\0\0\x98\x03\0\0\x01\0\0\x04\x04\0\0\0\xa3\x03\0\0\x0e\0\0\
-\0\0\0\0\0\x0c\x04\0\0\x01\0\0\x04\x04\0\0\0\x15\x04\0\0\x0e\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x8b\x04\0\0\0\0\0\x0e\x25\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\0\x9f\x04\
-\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\
-\x20\0\0\0\xb5\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\
-\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xca\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xe1\x04\0\0\0\0\0\x0e\x2d\0\0\
-\0\x01\0\0\0\xe9\x04\0\0\x04\0\0\x0f\x62\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\0\x28\
-\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\0\0\
-\x11\0\0\0\xf1\x04\0\0\x01\0\0\x0f\x04\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\x62\
-\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\
-\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\x70\
-\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x30\
-\x3a\x30\0\x2f\x77\x2f\x6e\x65\x74\x2d\x6e\x65\x78\x74\x2f\x6b\x65\x72\x6e\x65\
-\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\
-\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\
-\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\
-\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\
-\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\
-\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\
-\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x75\x6e\x73\x69\x67\x6e\
-\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\0\x30\x3a\x31\0\x09\x73\x74\
-\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\
-\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\
-\x29\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x20\x63\
-\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\x3b\0\x30\
-\x3a\x32\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\
-\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\
-\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\
-\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\
-\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\
-\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\
-\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\
-\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\
-\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\
-\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\
-\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\
-\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\
-\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\
-\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\
-\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\
-\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\
-\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\
-\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\
-\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\
-\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\
-\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\
-\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\
-\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\
-\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\
-\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\
-\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\
-\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\
-\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\
-\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\
-\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\
-\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\
-\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\
-\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\
-\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\
-\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\
-\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\
-\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\
-\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\
-\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\
-\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\
-\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\
-\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\
-\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\
-\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\
-\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\
-\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x2d\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\
-\0\x04\0\0\0\x62\0\0\0\x01\0\0\0\x80\x04\0\0\0\0\0\0\0\0\0\0\x69\x74\x65\x72\
-\x61\x74\x6f\x72\x2e\x72\x6f\x64\x61\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\x2f\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\
-\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\
-\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\
-\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
-\x61\x74\x74\x61\x63\x68\x65\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\
-\x25\x73\x20\x25\x73\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\
-\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\x1b\0\0\
-\0\0\0\x79\x11\0\0\0\0\0\0\x79\x11\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\
-\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\x23\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\
-\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\
-\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\x7b\x2a\xf0\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\
-\x7b\x1a\xf8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\
-\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x23\0\0\0\xb7\x03\0\0\x0e\0\0\0\
-\xb7\x05\0\0\x18\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\
-\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x3c\x01\0\x01\0\0\0\x42\0\0\
-\0\x7b\0\0\0\x24\x3c\x01\0\x02\0\0\0\x42\0\0\0\xee\0\0\0\x1d\x44\x01\0\x03\0\0\
-\0\x42\0\0\0\x0f\x01\0\0\x06\x4c\x01\0\x04\0\0\0\x42\0\0\0\x1a\x01\0\0\x17\x40\
-\x01\0\x05\0\0\0\x42\0\0\0\x1a\x01\0\0\x1d\x40\x01\0\x06\0\0\0\x42\0\0\0\x43\
-\x01\0\0\x06\x58\x01\0\x08\0\0\0\x42\0\0\0\x56\x01\0\0\x03\x5c\x01\0\x0f\0\0\0\
-\x42\0\0\0\xdc\x01\0\0\x02\x64\x01\0\x1f\0\0\0\x42\0\0\0\x2a\x02\0\0\x01\x6c\
-\x01\0\0\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\
-\0\x10\0\0\0\x02\0\0\0\xea\0\0\0\0\0\0\0\x20\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\
-\x28\0\0\0\x08\0\0\0\x3f\x01\0\0\0\0\0\0\x78\0\0\0\x0d\0\0\0\x3e\0\0\0\0\0\0\0\
-\x88\0\0\0\x0d\0\0\0\xea\0\0\0\0\0\0\0\xa8\0\0\0\x0d\0\0\0\x3f\x01\0\0\0\0\0\0\
-\x1a\0\0\0\x21\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\
-\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\
-\0\0\0\0\0\x0a\0\0\0\x01\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\
-\0\0\0\0\x79\x12\x08\0\0\0\0\0\x15\x02\x3c\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x79\
-\x27\0\0\0\0\0\0\x79\x11\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\
-\0\x07\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\
-\x31\0\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x7b\
-\x6a\xc8\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xb7\x03\0\0\
-\x04\0\0\0\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\x71\x28\0\0\0\0\0\x79\
-\x78\x30\0\0\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\0\0\x0f\x21\0\0\0\0\0\
-\0\x61\x11\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\0\x03\0\0\0\x0f\x13\0\
-\0\0\0\0\0\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf8\xff\xff\xff\
-\xb7\x02\0\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\0\0\0\0\x79\xa3\xf8\xff\
-\0\0\0\0\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf4\xff\xff\xff\
-\xb7\x02\0\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\
-\xff\0\0\0\0\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\x0f\x16\0\0\0\0\0\0\
-\xbf\x69\0\0\0\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\0\0\0\0\x7b\x1a\xe0\
-\xff\0\0\0\0\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x31\0\0\0\0\0\0\x7b\
-\x1a\xe8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\x79\xa1\
-\xc8\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x51\0\0\0\xb7\x03\0\0\x11\0\0\0\
-\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\
-\0\0\0\0\x17\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x80\x01\0\x01\0\0\0\x42\0\0\
-\0\x7b\0\0\0\x24\x80\x01\0\x02\0\0\0\x42\0\0\0\x60\x02\0\0\x1f\x88\x01\0\x03\0\
-\0\0\x42\0\0\0\x84\x02\0\0\x06\x94\x01\0\x04\0\0\0\x42\0\0\0\x1a\x01\0\0\x17\
-\x84\x01\0\x05\0\0\0\x42\0\0\0\x9d\x02\0\0\x0e\xa0\x01\0\x06\0\0\0\x42\0\0\0\
-\x1a\x01\0\0\x1d\x84\x01\0\x07\0\0\0\x42\0\0\0\x43\x01\0\0\x06\xa4\x01\0\x09\0\
-\0\0\x42\0\0\0\xaf\x02\0\0\x03\xa8\x01\0\x11\0\0\0\x42\0\0\0\x1f\x03\0\0\x02\
-\xb0\x01\0\x18\0\0\0\x42\0\0\0\x5a\x03\0\0\x06\x04\x01\0\x1b\0\0\0\x42\0\0\0\0\
-\0\0\0\0\0\0\0\x1c\0\0\0\x42\0\0\0\xab\x03\0\0\x0f\x10\x01\0\x1d\0\0\0\x42\0\0\
-\0\xc0\x03\0\0\x2d\x14\x01\0\x1f\0\0\0\x42\0\0\0\xf7\x03\0\0\x0d\x0c\x01\0\x21\
-\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x22\0\0\0\x42\0\0\0\xc0\x03\0\0\x02\x14\x01\0\
-\x25\0\0\0\x42\0\0\0\x1e\x04\0\0\x0d\x18\x01\0\x28\0\0\0\x42\0\0\0\0\0\0\0\0\0\
-\0\0\x29\0\0\0\x42\0\0\0\x1e\x04\0\0\x0d\x18\x01\0\x2c\0\0\0\x42\0\0\0\x1e\x04\
-\0\0\x0d\x18\x01\0\x2d\0\0\0\x42\0\0\0\x4c\x04\0\0\x1b\x1c\x01\0\x2e\0\0\0\x42\
-\0\0\0\x4c\x04\0\0\x06\x1c\x01\0\x2f\0\0\0\x42\0\0\0\x6f\x04\0\0\x0d\x24\x01\0\
-\x31\0\0\0\x42\0\0\0\x1f\x03\0\0\x02\xb0\x01\0\x40\0\0\0\x42\0\0\0\x2a\x02\0\0\
-\x01\xc0\x01\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\
-\0\0\0\0\0\x10\0\0\0\x14\0\0\0\xea\0\0\0\0\0\0\0\x20\0\0\0\x14\0\0\0\x3e\0\0\0\
-\0\0\0\0\x28\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x30\0\0\0\x08\0\0\0\x3f\x01\0\0\
-\0\0\0\0\x88\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x98\0\0\0\x1a\0\0\0\xea\0\0\0\0\
-\0\0\0\xb0\0\0\0\x1a\0\0\0\x52\x03\0\0\0\0\0\0\xb8\0\0\0\x1a\0\0\0\x56\x03\0\0\
-\0\0\0\0\xc8\0\0\0\x1f\0\0\0\x84\x03\0\0\0\0\0\0\xe0\0\0\0\x20\0\0\0\xea\0\0\0\
-\0\0\0\0\xf8\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x20\x01\0\0\x24\0\0\0\x3e\0\0\0\
-\0\0\0\0\x58\x01\0\0\x1a\0\0\0\xea\0\0\0\0\0\0\0\x68\x01\0\0\x20\0\0\0\x46\x04\
-\0\0\0\0\0\0\x90\x01\0\0\x1a\0\0\0\x3f\x01\0\0\0\0\0\0\xa0\x01\0\0\x1a\0\0\0\
-\x87\x04\0\0\0\0\0\0\xa8\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x42\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0\x1c\0\0\
-\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x1a\0\
-\0\0\x01\0\0\0\0\0\0\0\x13\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\
-\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\
-\0\0\0\0";
-	opts.insns_sz = 2216;
+\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xb0\0\0\0\x03\0\0\x04\x18\0\0\0\xbe\0\
+\0\0\x09\0\0\0\0\0\0\0\xc2\0\0\0\x0b\0\0\0\x40\0\0\0\xcd\0\0\0\x0b\0\0\0\x80\0\
+\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xd5\0\0\0\0\0\0\x07\0\0\0\0\xde\0\0\0\0\0\0\
+\x08\x0c\0\0\0\xe4\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\xae\x01\0\0\x03\0\0\x04\
+\x18\0\0\0\xb6\x01\0\0\x0e\0\0\0\0\0\0\0\xb9\x01\0\0\x11\0\0\0\x20\0\0\0\xbe\
+\x01\0\0\x0e\0\0\0\xa0\0\0\0\xca\x01\0\0\0\0\0\x08\x0f\0\0\0\xd0\x01\0\0\0\0\0\
+\x01\x04\0\0\0\x20\0\0\0\xdd\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\0\0\0\
+\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xe2\x01\0\0\0\0\0\x01\x04\0\0\0\
+\x20\0\0\0\0\0\0\0\x01\0\0\x0d\x14\0\0\0\x26\x05\0\0\x04\0\0\0\x2b\x02\0\0\0\0\
+\0\x08\x15\0\0\0\x31\x02\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\x01\x3b\x02\0\0\x01\0\
+\0\x0c\x13\0\0\0\0\0\0\0\0\0\0\x02\x18\0\0\0\x52\x02\0\0\x02\0\0\x04\x10\0\0\0\
+\x13\0\0\0\x03\0\0\0\0\0\0\0\x65\x02\0\0\x19\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\
+\x1c\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x17\0\0\0\x6a\x02\0\0\x01\0\
+\0\x0c\x1a\0\0\0\xb6\x02\0\0\x01\0\0\x04\x08\0\0\0\xbf\x02\0\0\x1d\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x02\x1e\0\0\0\x10\x03\0\0\x06\0\0\x04\x38\0\0\0\xb6\x01\0\0\
+\x0e\0\0\0\0\0\0\0\xb9\x01\0\0\x11\0\0\0\x20\0\0\0\x1d\x03\0\0\x1f\0\0\0\xc0\0\
+\0\0\x2e\x03\0\0\x19\0\0\0\0\x01\0\0\x37\x03\0\0\x21\0\0\0\x40\x01\0\0\x41\x03\
+\0\0\x22\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\
+\0\0\0\0\0\0\0\0\0\x02\x23\0\0\0\0\0\0\0\0\0\0\x02\x24\0\0\0\x8b\x03\0\0\x02\0\
+\0\x04\x08\0\0\0\x99\x03\0\0\x0e\0\0\0\0\0\0\0\xa2\x03\0\0\x0e\0\0\0\x20\0\0\0\
+\x41\x03\0\0\x03\0\0\x04\x18\0\0\0\xac\x03\0\0\x1f\0\0\0\0\0\0\0\xb4\x03\0\0\
+\x25\0\0\0\x40\0\0\0\xba\x03\0\0\x27\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x26\0\0\
+\0\0\0\0\0\0\0\0\x02\x28\0\0\0\xbe\x03\0\0\x01\0\0\x04\x04\0\0\0\xc9\x03\0\0\
+\x0e\0\0\0\0\0\0\0\x32\x04\0\0\x01\0\0\x04\x04\0\0\0\x3b\x04\0\0\x0e\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\x12\0\0\0\x30\0\0\0\xb1\x04\0\0\0\0\0\
+\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\x12\0\0\0\x1a\0\0\0\
+\xc5\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\
+\x12\0\0\0\x20\0\0\0\xdb\x04\0\0\0\0\0\x0e\x2d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\
+\0\0\0\0\x20\0\0\0\x12\0\0\0\x11\0\0\0\xf0\x04\0\0\0\0\0\x0e\x2f\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\x07\x05\0\0\0\0\0\x0e\
+\x31\0\0\0\x01\0\0\0\x0f\x05\0\0\x01\0\0\x0f\x04\0\0\0\x36\0\0\0\0\0\0\0\x04\0\
+\0\0\x16\x05\0\0\x04\0\0\x0f\x7b\0\0\0\x2a\0\0\0\0\0\0\0\x30\0\0\0\x2c\0\0\0\
+\x30\0\0\0\x1a\0\0\0\x2e\0\0\0\x4a\0\0\0\x20\0\0\0\x30\0\0\0\x6a\0\0\0\x11\0\0\
+\0\x1e\x05\0\0\x01\0\0\x0f\x04\0\0\0\x32\0\0\0\0\0\0\0\x04\0\0\0\x26\x05\0\0\0\
+\0\0\x0e\x06\0\0\0\x01\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\
+\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\
+\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\
+\x62\x70\x66\x5f\x6d\x61\x70\0\x30\x3a\x30\0\x2f\x68\x6f\x6d\x65\x2f\x61\x73\
+\x70\x73\x6b\x2f\x73\x72\x63\x2f\x62\x70\x66\x2d\x6e\x65\x78\x74\x2f\x6b\x65\
+\x72\x6e\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\
+\x65\x72\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\
+\x70\x66\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\
+\x65\x20\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\
+\x3e\x73\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\
+\x73\x65\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\
+\x75\x6d\0\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x75\x6e\x73\
+\x69\x67\x6e\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\0\x30\x3a\x31\0\
+\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\
+\x70\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\
+\x6d\x61\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\
+\x6e\x75\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\
+\x71\x5f\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\
+\x3d\x3d\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\
+\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\
+\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\
+\x72\x69\x65\x73\x20\x20\x63\x75\x72\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\x6e\
+\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\x6d\
+\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\x73\
+\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\x52\
+\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\x5f\
+\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\
+\x75\x20\x25\x2d\x31\x36\x73\x20\x20\x25\x31\x30\x64\x20\x20\x20\x25\x31\x30\
+\x6c\x6c\x64\x5c\x6e\x22\x2c\0\x7d\0\x5f\x5f\x73\x36\x34\0\x6c\x6f\x6e\x67\x20\
+\x6c\x6f\x6e\x67\0\x62\x70\x66\x5f\x6d\x61\x70\x5f\x73\x75\x6d\x5f\x65\x6c\x65\
+\x6d\x5f\x63\x6f\x75\x6e\x74\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\
+\x66\x5f\x70\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\
+\x5f\x70\x72\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\
+\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\
+\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\
+\x20\x28\x21\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\
+\x78\0\x09\x61\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\
+\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\
+\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\
+\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\
+\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\
+\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\
+\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\
+\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\
+\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\
+\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\
+\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\
+\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\
+\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\
+\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\
+\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\
+\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\
+\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\x20\
+\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\x74\
+\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\
+\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\
+\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\
+\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\x66\
+\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\x3e\
+\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\x6e\
+\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\
+\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\
+\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\
+\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\
+\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\
+\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x6b\x73\x79\x6d\
+\x73\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x64\x75\x6d\
+\x6d\x79\x5f\x6b\x73\x79\x6d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\xc9\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\0\x04\0\0\0\x7b\0\0\0\x01\0\0\0\
+\x80\0\0\0\0\0\0\0\0\0\0\0\x69\x74\x65\x72\x61\x74\x6f\x72\x2e\x72\x6f\x64\x61\
+\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\x34\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x20\
+\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
+\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x20\x20\x63\x75\x72\x5f\x65\
+\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x20\x25\
+\x31\x30\x64\x20\x20\x20\x25\x31\x30\x6c\x6c\x64\x0a\0\x20\x20\x69\x64\x20\x6e\
+\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\
+\x61\x63\x68\x65\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\
+\x25\x73\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\
+\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\x1d\0\0\0\0\0\x79\x21\
+\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe0\xff\
+\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\
+\x30\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\
+\xe0\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\
+\x7b\x2a\xe8\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\x7b\x1a\xf0\xff\0\0\0\0\xbf\x71\
+\0\0\0\0\0\0\x85\x20\0\0\0\0\0\0\x7b\x0a\xf8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\
+\x07\x04\0\0\xe0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\
+\x30\0\0\0\xb7\x03\0\0\x1a\0\0\0\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\
+\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x88\0\0\0\
+\x1e\x44\x01\0\x01\0\0\0\x42\0\0\0\x88\0\0\0\x24\x44\x01\0\x02\0\0\0\x42\0\0\0\
+\xfb\0\0\0\x1d\x4c\x01\0\x03\0\0\0\x42\0\0\0\x1c\x01\0\0\x06\x54\x01\0\x04\0\0\
+\0\x42\0\0\0\x2b\x01\0\0\x1d\x48\x01\0\x05\0\0\0\x42\0\0\0\x50\x01\0\0\x06\x60\
+\x01\0\x07\0\0\0\x42\0\0\0\x63\x01\0\0\x03\x64\x01\0\x0e\0\0\0\x42\0\0\0\xf6\
+\x01\0\0\x02\x6c\x01\0\x21\0\0\0\x42\0\0\0\x29\x02\0\0\x01\x80\x01\0\0\0\0\0\
+\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\
+\x02\0\0\0\xf7\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x27\x01\0\0\0\0\0\0\x70\0\0\0\
+\x0d\0\0\0\x3e\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xf7\0\0\0\0\0\0\0\xa0\0\0\0\
+\x0d\0\0\0\x27\x01\0\0\0\0\0\0\x1a\0\0\0\x23\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\
+\x70\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\
+\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x09\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\x69\x74\
+\x65\x72\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x62\x70\x66\x5f\x6d\
+\x61\x70\x5f\x73\x75\x6d\x5f\x65\x6c\x65\x6d\x5f\x63\x6f\x75\x6e\x74\0\0\x47\
+\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x11\x08\0\0\0\0\
+\0\x15\x01\x3b\0\0\0\0\0\x79\x17\0\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\
+\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\
+\x18\x62\0\0\0\0\0\0\0\0\0\0\x4a\0\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x7e\0\0\0\x7b\x6a\xc8\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\
+\xff\0\0\0\0\xb7\x03\0\0\x04\0\0\0\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\
+\x71\x28\0\0\0\0\0\x79\x78\x30\0\0\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\
+\0\0\x0f\x21\0\0\0\0\0\0\x61\x11\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\
+\0\x03\0\0\0\x0f\x13\0\0\0\0\0\0\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\
+\x01\0\0\xf8\xff\xff\xff\xb7\x02\0\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\
+\0\0\0\0\x79\xa3\xf8\xff\0\0\0\0\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\
+\x01\0\0\xf4\xff\xff\xff\xb7\x02\0\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\
+\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\
+\x0f\x16\0\0\0\0\0\0\xbf\x69\0\0\0\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\
+\0\0\0\0\x7b\x1a\xe0\xff\0\0\0\0\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\
+\x31\0\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\
+\xff\xff\xff\x79\xa1\xc8\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x6a\0\0\0\xb7\
+\x03\0\0\x11\0\0\0\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\
+\x95\0\0\0\0\0\0\0\0\0\0\0\x1b\0\0\0\0\0\0\0\x42\0\0\0\x88\0\0\0\x1e\x94\x01\0\
+\x01\0\0\0\x42\0\0\0\x88\0\0\0\x24\x94\x01\0\x02\0\0\0\x42\0\0\0\x86\x02\0\0\
+\x1f\x9c\x01\0\x03\0\0\0\x42\0\0\0\xaa\x02\0\0\x06\xa8\x01\0\x04\0\0\0\x42\0\0\
+\0\xc3\x02\0\0\x0e\xb4\x01\0\x05\0\0\0\x42\0\0\0\x2b\x01\0\0\x1d\x98\x01\0\x06\
+\0\0\0\x42\0\0\0\x50\x01\0\0\x06\xb8\x01\0\x08\0\0\0\x42\0\0\0\xd5\x02\0\0\x03\
+\xbc\x01\0\x10\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x17\0\0\0\x42\0\0\0\
+\x80\x03\0\0\x06\x04\x01\0\x1a\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x1b\0\
+\0\0\x42\0\0\0\xd1\x03\0\0\x0f\x10\x01\0\x1c\0\0\0\x42\0\0\0\xe6\x03\0\0\x2d\
+\x14\x01\0\x1e\0\0\0\x42\0\0\0\x1d\x04\0\0\x0d\x0c\x01\0\x20\0\0\0\x42\0\0\0\
+\x45\x03\0\0\x02\xc4\x01\0\x21\0\0\0\x42\0\0\0\xe6\x03\0\0\x02\x14\x01\0\x24\0\
+\0\0\x42\0\0\0\x44\x04\0\0\x0d\x18\x01\0\x27\0\0\0\x42\0\0\0\x45\x03\0\0\x02\
+\xc4\x01\0\x28\0\0\0\x42\0\0\0\x44\x04\0\0\x0d\x18\x01\0\x2b\0\0\0\x42\0\0\0\
+\x44\x04\0\0\x0d\x18\x01\0\x2c\0\0\0\x42\0\0\0\x72\x04\0\0\x1b\x1c\x01\0\x2d\0\
+\0\0\x42\0\0\0\x72\x04\0\0\x06\x1c\x01\0\x2e\0\0\0\x42\0\0\0\x95\x04\0\0\x0d\
+\x24\x01\0\x30\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x3f\0\0\0\x42\0\0\0\
+\x29\x02\0\0\x01\xd4\x01\0\0\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\
+\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x18\0\0\0\xf7\0\0\0\0\0\0\0\x20\0\0\0\x1c\0\0\
+\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\0\x27\x01\0\0\0\0\0\0\x80\0\0\0\x1e\0\0\
+\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1e\0\0\0\xf7\0\0\0\0\0\0\0\xa8\0\0\0\x1e\0\0\0\
+\x78\x03\0\0\0\0\0\0\xb0\0\0\0\x1e\0\0\0\x7c\x03\0\0\0\0\0\0\xc0\0\0\0\x23\0\0\
+\0\xaa\x03\0\0\0\0\0\0\xd8\0\0\0\x24\0\0\0\xf7\0\0\0\0\0\0\0\xf0\0\0\0\x24\0\0\
+\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x28\0\0\0\x3e\0\0\0\0\0\0\0\x50\x01\0\0\x1e\0\
+\0\0\xf7\0\0\0\0\0\0\0\x60\x01\0\0\x24\0\0\0\x6c\x04\0\0\0\0\0\0\x88\x01\0\0\
+\x1e\0\0\0\x27\x01\0\0\0\0\0\0\x98\x01\0\0\x1e\0\0\0\xad\x04\0\0\0\0\0\0\xa0\
+\x01\0\0\x1c\0\0\0\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x41\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\
+\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\
+\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x19\0\0\0\x01\0\0\0\0\0\0\0\
+\x12\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\
+\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0";
+	opts.insns_sz = 2456;
 	opts.insns = (void *)"\
 \xbf\x16\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\x78\xff\xff\xff\xb7\x02\0\
 \0\x88\0\0\0\xb7\x03\0\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x05\0\x14\0\0\0\0\0\x61\
@@ -331,79 +326,83 @@ iterators_bpf__load(struct iterators_bpf *skel)
 \0\0\0\x85\0\0\0\xa8\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x01\0\0\0\0\
 \0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xbf\x70\0\0\
 \0\0\0\0\x95\0\0\0\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
-\x48\x0e\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\
-\0\0\x44\x0e\0\0\x63\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\
-\0\0\0\0\x38\x0e\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x05\0\0\
-\x18\x61\0\0\0\0\0\0\0\0\0\0\x30\x0e\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x12\0\
-\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x30\x0e\0\0\xb7\x03\0\0\x1c\0\0\0\x85\0\0\0\
+\xe8\x0e\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\
+\0\0\xe4\x0e\0\0\x63\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\
+\0\0\0\0\xd8\x0e\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x05\0\0\
+\x18\x61\0\0\0\0\0\0\0\0\0\0\xd0\x0e\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x12\0\
+\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xd0\x0e\0\0\xb7\x03\0\0\x1c\0\0\0\x85\0\0\0\
 \xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\xd4\xff\0\0\0\0\x63\x7a\x78\xff\0\0\0\0\
-\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x0e\0\0\x63\x01\0\0\0\
+\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x20\x0f\0\0\x63\x01\0\0\0\
 \0\0\0\x61\x60\x1c\0\0\0\0\0\x15\0\x03\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
-\x5c\x0e\0\0\x63\x01\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\
-\0\x50\x0e\0\0\xb7\x03\0\0\x48\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\
+\xfc\x0e\0\0\x63\x01\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\
+\0\xf0\x0e\0\0\xb7\x03\0\0\x48\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\
 \xc5\x07\xc3\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x63\x71\0\0\0\0\0\
-\0\x79\x63\x20\0\0\0\0\0\x15\x03\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x98\
-\x0e\0\0\xb7\x02\0\0\x62\0\0\0\x61\x60\x04\0\0\0\0\0\x45\0\x02\0\x01\0\0\0\x85\
+\0\x79\x63\x20\0\0\0\0\0\x15\x03\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x38\
+\x0f\0\0\xb7\x02\0\0\x7b\0\0\0\x61\x60\x04\0\0\0\0\0\x45\0\x02\0\x01\0\0\0\x85\
 \0\0\0\x94\0\0\0\x05\0\x01\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x18\x62\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x08\x0f\0\0\x63\
-\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\
-\0\0\x10\x0f\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x98\x0e\0\0\
-\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x0f\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x02\0\
-\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x08\x0f\0\0\xb7\x03\0\0\x20\0\0\0\x85\0\0\0\
+\0\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xc0\x0f\0\0\x63\
+\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xb8\x0f\0\0\x18\x61\0\0\0\0\0\0\0\
+\0\0\0\xc8\x0f\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x38\x0f\0\0\
+\x18\x61\0\0\0\0\0\0\0\0\0\0\xd0\x0f\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x02\0\
+\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xc0\x0f\0\0\xb7\x03\0\0\x20\0\0\0\x85\0\0\0\
 \xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x9f\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x0f\0\0\x63\
-\x01\0\0\0\0\0\0\xb7\x01\0\0\x16\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x28\x0f\0\0\
+\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\x0f\0\0\x63\
+\x01\0\0\0\0\0\0\xb7\x01\0\0\x16\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xe0\x0f\0\0\
 \xb7\x03\0\0\x04\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x92\xff\
-\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x30\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
-\x78\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x38\x0f\0\0\x18\
-\x61\0\0\0\0\0\0\0\0\0\0\x70\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\
-\0\0\0\x40\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x11\0\0\x7b\x01\0\0\0\0\0\0\
-\x18\x60\0\0\0\0\0\0\0\0\0\0\x48\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xc8\x11\0\
-\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x10\0\0\x18\x61\0\0\0\0\
-\0\0\0\0\0\0\xe8\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\x11\0\0\x7b\x01\0\0\0\0\0\0\x61\x60\x08\0\0\
-\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x11\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\
-\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x84\x11\0\0\x63\x01\0\0\0\0\0\0\x79\x60\
-\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x88\x11\0\0\x7b\x01\0\0\0\0\0\0\x61\
-\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb0\x11\0\0\x63\x01\0\0\0\0\0\
-\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xf8\x11\0\0\xb7\x02\0\0\x11\0\0\0\xb7\x03\0\0\
+\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
+\x20\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xf0\x0f\0\0\x18\
+\x61\0\0\0\0\0\0\0\0\0\0\x18\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\
+\0\0\0\x08\x11\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x60\x12\0\0\x7b\x01\0\0\0\0\0\0\
+\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x11\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x70\x12\0\
+\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xa0\x11\0\0\x18\x61\0\0\0\0\
+\0\0\0\0\0\0\x90\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x88\x12\0\0\x7b\x01\0\0\0\0\0\0\x61\x60\x08\0\0\
+\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x12\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\
+\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x2c\x12\0\0\x63\x01\0\0\0\0\0\0\x79\x60\
+\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x30\x12\0\0\x7b\x01\0\0\0\0\0\0\x61\
+\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x58\x12\0\0\x63\x01\0\0\0\0\0\
+\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xa0\x12\0\0\xb7\x02\0\0\x11\0\0\0\xb7\x03\0\0\
 \x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\
-\x5c\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x68\x11\0\0\x63\x70\x6c\0\0\0\0\0\
-\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\0\x05\0\0\0\x18\x62\0\0\
-\0\0\0\0\0\0\0\0\x68\x11\0\0\xb7\x03\0\0\x8c\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\
-\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd8\x11\0\0\x61\x01\0\0\0\0\0\0\xd5\
-\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\x07\x4a\xff\0\0\
-\0\0\x63\x7a\x80\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\x18\x61\0\
-\0\0\0\0\0\0\0\0\0\x10\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\
-\x18\x12\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x08\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\
-\x60\0\0\0\0\0\0\0\0\0\0\x28\x14\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x50\x17\0\0\
-\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x30\x14\0\0\x18\x61\0\0\0\0\0\
-\0\0\0\0\0\x60\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd0\x15\
-\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x78\x17\0\0\x7b\x01\0\0\0\0\
-\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x17\0\0\x63\x01\0\0\
-\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x1c\x17\0\0\x63\x01\
-\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x20\x17\0\0\x7b\
-\x01\0\0\0\0\0\0\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x48\x17\0\
-\0\x63\x01\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x90\x17\0\0\xb7\x02\0\0\x12\
-\0\0\0\xb7\x03\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\
-\0\0\0\0\0\xc5\x07\x13\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\x63\
-\x70\x6c\0\0\0\0\0\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\0\x05\
-\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\xb7\x03\0\0\x8c\0\0\0\x85\0\0\0\
-\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x70\x17\0\0\x61\x01\
-\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\
-\x07\x01\xff\0\0\0\0\x63\x7a\x84\xff\0\0\0\0\x61\xa1\x78\xff\0\0\0\0\xd5\x01\
-\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa0\x80\xff\0\0\0\0\
-\x63\x06\x28\0\0\0\0\0\x61\xa0\x84\xff\0\0\0\0\x63\x06\x2c\0\0\0\0\0\x18\x61\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\0\0\x63\x06\x18\0\0\0\0\0\xb7\0\0\0\
-\0\0\0\0\x95\0\0\0\0\0\0\0";
+\x5c\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\x63\x70\x6c\0\0\0\0\0\
+\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\x18\x68\0\0\0\0\0\0\0\0\0\0\xa8\
+\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x12\0\0\xb7\x02\0\0\x17\0\0\0\xb7\x03\
+\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\
+\x07\x4d\xff\0\0\0\0\x75\x07\x03\0\0\0\0\0\x62\x08\x04\0\0\0\0\0\x6a\x08\x02\0\
+\0\0\0\0\x05\0\x0a\0\0\0\0\0\x63\x78\x04\0\0\0\0\0\xbf\x79\0\0\0\0\0\0\x77\x09\
+\0\0\x20\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\x63\x90\0\0\0\0\0\0\x55\
+\x09\x02\0\0\0\0\0\x6a\x08\x02\0\0\0\0\0\x05\0\x01\0\0\0\0\0\x6a\x08\x02\0\x40\
+\0\0\0\xb7\x01\0\0\x05\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\xb7\x03\0\
+\0\x8c\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\
+\0\0\x01\0\0\x61\x01\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\
+\0\0\0\xa8\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x80\x12\0\0\x61\x01\0\0\0\0\0\0\
+\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\x07\x2c\xff\
+\0\0\0\0\x63\x7a\x80\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd0\x12\0\0\x18\
+\x61\0\0\0\0\0\0\0\0\0\0\xa8\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\
+\0\0\0\xd8\x12\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xa0\x17\0\0\x7b\x01\0\0\0\0\0\0\
+\x18\x60\0\0\0\0\0\0\0\0\0\0\xe0\x14\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe8\x17\0\
+\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x14\0\0\x18\x61\0\0\0\0\
+\0\0\0\0\0\0\xf8\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x78\
+\x16\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x18\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x10\x18\0\0\x7b\x01\0\0\
+\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb0\x17\0\0\x63\x01\
+\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb4\x17\0\0\x63\
+\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x17\0\0\
+\x7b\x01\0\0\0\0\0\0\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\
+\x17\0\0\x63\x01\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x18\0\0\xb7\x02\0\
+\0\x12\0\0\0\xb7\x03\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\
+\x07\0\0\0\0\0\0\xc5\x07\xf5\xfe\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x98\x17\0\
+\0\x63\x70\x6c\0\0\0\0\0\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\
+\0\x05\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x98\x17\0\0\xb7\x03\0\0\x8c\0\0\0\x85\
+\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x08\x18\0\0\
+\x61\x01\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\
+\0\0\xc5\x07\xe3\xfe\0\0\0\0\x63\x7a\x84\xff\0\0\0\0\x61\xa1\x78\xff\0\0\0\0\
+\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa0\x80\xff\
+\0\0\0\0\x63\x06\x28\0\0\0\0\0\x61\xa0\x84\xff\0\0\0\0\x63\x06\x2c\0\0\0\0\0\
+\x18\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\0\0\x63\x06\x18\0\0\0\0\0\
+\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0";
 	err = bpf_load_and_run(&opts);
 	if (err < 0)
 		return err;
-	skel->rodata = skel_finalize_map_data(&skel->maps.rodata.initial_value,
-					4096, PROT_READ, skel->maps.rodata.map_fd);
-	if (!skel->rodata)
-		return -ENOMEM;
 	return 0;
 }
 
@@ -422,4 +421,15 @@ iterators_bpf__open_and_load(void)
 	return skel;
 }
 
+__attribute__((unused)) static void
+iterators_bpf__assert(struct iterators_bpf *s __attribute__((unused)))
+{
+#ifdef __cplusplus
+#define _Static_assert static_assert
+#endif
+#ifdef __cplusplus
+#undef _Static_assert
+#endif
+}
+
 #endif /* __ITERATORS_BPF_SKEL_H__ */
-- 
GitLab


From 6c1b8cb6a70ad4b357fbc92fc9c5d6bc67593351 Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Thu, 6 Jul 2023 13:39:32 +0000
Subject: [PATCH 0021/1806] selftests/bpf: test map percpu stats

Add a new map test, map_percpu_stats.c, which is checking the correctness of
map's percpu elements counters.  For supported maps the test upserts a number
of elements, checks the correctness of the counters, then deletes all the
elements and checks again that the counters sum drops down to zero.

The following map types are tested:

    * BPF_MAP_TYPE_HASH, BPF_F_NO_PREALLOC
    * BPF_MAP_TYPE_PERCPU_HASH, BPF_F_NO_PREALLOC
    * BPF_MAP_TYPE_HASH,
    * BPF_MAP_TYPE_PERCPU_HASH,
    * BPF_MAP_TYPE_LRU_HASH
    * BPF_MAP_TYPE_LRU_PERCPU_HASH
    * BPF_MAP_TYPE_LRU_HASH, BPF_F_NO_COMMON_LRU
    * BPF_MAP_TYPE_LRU_PERCPU_HASH, BPF_F_NO_COMMON_LRU
    * BPF_MAP_TYPE_HASH_OF_MAPS

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20230706133932.45883-6-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/map_tests/map_percpu_stats.c          | 447 ++++++++++++++++++
 .../selftests/bpf/progs/map_percpu_stats.c    |  24 +
 2 files changed, 471 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
 create mode 100644 tools/testing/selftests/bpf/progs/map_percpu_stats.c

diff --git a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
new file mode 100644
index 0000000000000..1a9eeefda9a87
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
@@ -0,0 +1,447 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <errno.h>
+#include <unistd.h>
+#include <pthread.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <bpf_util.h>
+#include <test_maps.h>
+
+#include "map_percpu_stats.skel.h"
+
+#define MAX_ENTRIES			16384
+#define MAX_ENTRIES_HASH_OF_MAPS	64
+#define N_THREADS			8
+#define MAX_MAP_KEY_SIZE		4
+
+static void map_info(int map_fd, struct bpf_map_info *info)
+{
+	__u32 len = sizeof(*info);
+	int ret;
+
+	memset(info, 0, sizeof(*info));
+
+	ret = bpf_obj_get_info_by_fd(map_fd, info, &len);
+	CHECK(ret < 0, "bpf_obj_get_info_by_fd", "error: %s\n", strerror(errno));
+}
+
+static const char *map_type_to_s(__u32 type)
+{
+	switch (type) {
+	case BPF_MAP_TYPE_HASH:
+		return "HASH";
+	case BPF_MAP_TYPE_PERCPU_HASH:
+		return "PERCPU_HASH";
+	case BPF_MAP_TYPE_LRU_HASH:
+		return "LRU_HASH";
+	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
+		return "LRU_PERCPU_HASH";
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+		return "BPF_MAP_TYPE_HASH_OF_MAPS";
+	default:
+		return "<define-me>";
+	}
+}
+
+static __u32 map_count_elements(__u32 type, int map_fd)
+{
+	__u32 key = -1;
+	int n = 0;
+
+	while (!bpf_map_get_next_key(map_fd, &key, &key))
+		n++;
+	return n;
+}
+
+#define BATCH	true
+
+static void delete_and_lookup_batch(int map_fd, void *keys, __u32 count)
+{
+	static __u8 values[(8 << 10) * MAX_ENTRIES];
+	void *in_batch = NULL, *out_batch;
+	__u32 save_count = count;
+	int ret;
+
+	ret = bpf_map_lookup_and_delete_batch(map_fd,
+					      &in_batch, &out_batch,
+					      keys, values, &count,
+					      NULL);
+
+	/*
+	 * Despite what uapi header says, lookup_and_delete_batch will return
+	 * -ENOENT in case we successfully have deleted all elements, so check
+	 * this separately
+	 */
+	CHECK(ret < 0 && (errno != ENOENT || !count), "bpf_map_lookup_and_delete_batch",
+		       "error: %s\n", strerror(errno));
+
+	CHECK(count != save_count,
+			"bpf_map_lookup_and_delete_batch",
+			"deleted not all elements: removed=%u expected=%u\n",
+			count, save_count);
+}
+
+static void delete_all_elements(__u32 type, int map_fd, bool batch)
+{
+	static __u8 val[8 << 10]; /* enough for 1024 CPUs */
+	__u32 key = -1;
+	void *keys;
+	__u32 i, n;
+	int ret;
+
+	keys = calloc(MAX_MAP_KEY_SIZE, MAX_ENTRIES);
+	CHECK(!keys, "calloc", "error: %s\n", strerror(errno));
+
+	for (n = 0; !bpf_map_get_next_key(map_fd, &key, &key); n++)
+		memcpy(keys + n*MAX_MAP_KEY_SIZE, &key, MAX_MAP_KEY_SIZE);
+
+	if (batch) {
+		/* Can't mix delete_batch and delete_and_lookup_batch because
+		 * they have different semantics in relation to the keys
+		 * argument. However, delete_batch utilize map_delete_elem,
+		 * so we actually test it in non-batch scenario */
+		delete_and_lookup_batch(map_fd, keys, n);
+	} else {
+		/* Intentionally mix delete and lookup_and_delete so we can test both */
+		for (i = 0; i < n; i++) {
+			void *keyp = keys + i*MAX_MAP_KEY_SIZE;
+
+			if (i % 2 || type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+				ret = bpf_map_delete_elem(map_fd, keyp);
+				CHECK(ret < 0, "bpf_map_delete_elem",
+					       "error: key %u: %s\n", i, strerror(errno));
+			} else {
+				ret = bpf_map_lookup_and_delete_elem(map_fd, keyp, val);
+				CHECK(ret < 0, "bpf_map_lookup_and_delete_elem",
+					       "error: key %u: %s\n", i, strerror(errno));
+			}
+		}
+	}
+
+	free(keys);
+}
+
+static bool is_lru(__u32 map_type)
+{
+	return map_type == BPF_MAP_TYPE_LRU_HASH ||
+	       map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
+struct upsert_opts {
+	__u32 map_type;
+	int map_fd;
+	__u32 n;
+};
+
+static int create_small_hash(void)
+{
+	int map_fd;
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, "small", 4, 4, 4, NULL);
+	CHECK(map_fd < 0, "bpf_map_create()", "error:%s (name=%s)\n",
+			strerror(errno), "small");
+
+	return map_fd;
+}
+
+static void *patch_map_thread(void *arg)
+{
+	struct upsert_opts *opts = arg;
+	int val;
+	int ret;
+	int i;
+
+	for (i = 0; i < opts->n; i++) {
+		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
+			val = create_small_hash();
+		else
+			val = rand();
+		ret = bpf_map_update_elem(opts->map_fd, &i, &val, 0);
+		CHECK(ret < 0, "bpf_map_update_elem", "key=%d error: %s\n", i, strerror(errno));
+
+		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
+			close(val);
+	}
+	return NULL;
+}
+
+static void upsert_elements(struct upsert_opts *opts)
+{
+	pthread_t threads[N_THREADS];
+	int ret;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(threads); i++) {
+		ret = pthread_create(&i[threads], NULL, patch_map_thread, opts);
+		CHECK(ret != 0, "pthread_create", "error: %s\n", strerror(ret));
+	}
+
+	for (i = 0; i < ARRAY_SIZE(threads); i++) {
+		ret = pthread_join(i[threads], NULL);
+		CHECK(ret != 0, "pthread_join", "error: %s\n", strerror(ret));
+	}
+}
+
+static __u32 read_cur_elements(int iter_fd)
+{
+	char buf[64];
+	ssize_t n;
+	__u32 ret;
+
+	n = read(iter_fd, buf, sizeof(buf)-1);
+	CHECK(n <= 0, "read", "error: %s\n", strerror(errno));
+	buf[n] = '\0';
+
+	errno = 0;
+	ret = (__u32)strtol(buf, NULL, 10);
+	CHECK(errno != 0, "strtol", "error: %s\n", strerror(errno));
+
+	return ret;
+}
+
+static __u32 get_cur_elements(int map_id)
+{
+	struct map_percpu_stats *skel;
+	struct bpf_link *link;
+	__u32 n_elements;
+	int iter_fd;
+	int ret;
+
+	skel = map_percpu_stats__open();
+	CHECK(skel == NULL, "map_percpu_stats__open", "error: %s", strerror(errno));
+
+	skel->bss->target_id = map_id;
+
+	ret = map_percpu_stats__load(skel);
+	CHECK(ret != 0, "map_percpu_stats__load", "error: %s", strerror(errno));
+
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_map, NULL);
+	CHECK(!link, "bpf_program__attach_iter", "error: %s\n", strerror(errno));
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	CHECK(iter_fd < 0, "bpf_iter_create", "error: %s\n", strerror(errno));
+
+	n_elements = read_cur_elements(iter_fd);
+
+	close(iter_fd);
+	bpf_link__destroy(link);
+	map_percpu_stats__destroy(skel);
+
+	return n_elements;
+}
+
+static void check_expected_number_elements(__u32 n_inserted, int map_fd,
+					   struct bpf_map_info *info)
+{
+	__u32 n_real;
+	__u32 n_iter;
+
+	/* Count the current number of elements in the map by iterating through
+	 * all the map keys via bpf_get_next_key
+	 */
+	n_real = map_count_elements(info->type, map_fd);
+
+	/* The "real" number of elements should be the same as the inserted
+	 * number of elements in all cases except LRU maps, where some elements
+	 * may have been evicted
+	 */
+	if (n_inserted == 0 || !is_lru(info->type))
+		CHECK(n_inserted != n_real, "map_count_elements",
+		      "n_real(%u) != n_inserted(%u)\n", n_real, n_inserted);
+
+	/* Count the current number of elements in the map using an iterator */
+	n_iter = get_cur_elements(info->id);
+
+	/* Both counts should be the same, as all updates are over */
+	CHECK(n_iter != n_real, "get_cur_elements",
+	      "n_iter=%u, expected %u (map_type=%s,map_flags=%08x)\n",
+	      n_iter, n_real, map_type_to_s(info->type), info->map_flags);
+}
+
+static void __test(int map_fd)
+{
+	struct upsert_opts opts = {
+		.map_fd = map_fd,
+	};
+	struct bpf_map_info info;
+
+	map_info(map_fd, &info);
+	opts.map_type = info.type;
+	opts.n = info.max_entries;
+
+	/* Reduce the number of elements we are updating such that we don't
+	 * bump into -E2BIG from non-preallocated hash maps, but still will
+	 * have some evictions for LRU maps  */
+	if (opts.map_type != BPF_MAP_TYPE_HASH_OF_MAPS)
+		opts.n -= 512;
+	else
+		opts.n /= 2;
+
+	/*
+	 * Upsert keys [0, n) under some competition: with random values from
+	 * N_THREADS threads. Check values, then delete all elements and check
+	 * values again.
+	 */
+	upsert_elements(&opts);
+	check_expected_number_elements(opts.n, map_fd, &info);
+	delete_all_elements(info.type, map_fd, !BATCH);
+	check_expected_number_elements(0, map_fd, &info);
+
+	/* Now do the same, but using batch delete operations */
+	upsert_elements(&opts);
+	check_expected_number_elements(opts.n, map_fd, &info);
+	delete_all_elements(info.type, map_fd, BATCH);
+	check_expected_number_elements(0, map_fd, &info);
+
+	close(map_fd);
+}
+
+static int map_create_opts(__u32 type, const char *name,
+			   struct bpf_map_create_opts *map_opts,
+			   __u32 key_size, __u32 val_size)
+{
+	int max_entries;
+	int map_fd;
+
+	if (type == BPF_MAP_TYPE_HASH_OF_MAPS)
+		max_entries = MAX_ENTRIES_HASH_OF_MAPS;
+	else
+		max_entries = MAX_ENTRIES;
+
+	map_fd = bpf_map_create(type, name, key_size, val_size, max_entries, map_opts);
+	CHECK(map_fd < 0, "bpf_map_create()", "error:%s (name=%s)\n",
+			strerror(errno), name);
+
+	return map_fd;
+}
+
+static int map_create(__u32 type, const char *name, struct bpf_map_create_opts *map_opts)
+{
+	return map_create_opts(type, name, map_opts, sizeof(int), sizeof(int));
+}
+
+static int create_hash(void)
+{
+	struct bpf_map_create_opts map_opts = {
+		.sz = sizeof(map_opts),
+		.map_flags = BPF_F_NO_PREALLOC,
+	};
+
+	return map_create(BPF_MAP_TYPE_HASH, "hash", &map_opts);
+}
+
+static int create_percpu_hash(void)
+{
+	struct bpf_map_create_opts map_opts = {
+		.sz = sizeof(map_opts),
+		.map_flags = BPF_F_NO_PREALLOC,
+	};
+
+	return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash", &map_opts);
+}
+
+static int create_hash_prealloc(void)
+{
+	return map_create(BPF_MAP_TYPE_HASH, "hash", NULL);
+}
+
+static int create_percpu_hash_prealloc(void)
+{
+	return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash_prealloc", NULL);
+}
+
+static int create_lru_hash(__u32 type, __u32 map_flags)
+{
+	struct bpf_map_create_opts map_opts = {
+		.sz = sizeof(map_opts),
+		.map_flags = map_flags,
+	};
+
+	return map_create(type, "lru_hash", &map_opts);
+}
+
+static int create_hash_of_maps(void)
+{
+	struct bpf_map_create_opts map_opts = {
+		.sz = sizeof(map_opts),
+		.map_flags = BPF_F_NO_PREALLOC,
+		.inner_map_fd = create_small_hash(),
+	};
+	int ret;
+
+	ret = map_create_opts(BPF_MAP_TYPE_HASH_OF_MAPS, "hash_of_maps",
+			      &map_opts, sizeof(int), sizeof(int));
+	close(map_opts.inner_map_fd);
+	return ret;
+}
+
+static void map_percpu_stats_hash(void)
+{
+	__test(create_hash());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_hash(void)
+{
+	__test(create_percpu_hash());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_hash_prealloc(void)
+{
+	__test(create_hash_prealloc());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_hash_prealloc(void)
+{
+	__test(create_percpu_hash_prealloc());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_lru_hash(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_HASH, 0));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_lru_hash_no_common(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_HASH, BPF_F_NO_COMMON_LRU));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_lru_hash(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_PERCPU_HASH, 0));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_lru_hash_no_common(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_PERCPU_HASH, BPF_F_NO_COMMON_LRU));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_hash_of_maps(void)
+{
+	__test(create_hash_of_maps());
+	printf("test_%s:PASS\n", __func__);
+}
+
+void test_map_percpu_stats(void)
+{
+	map_percpu_stats_hash();
+	map_percpu_stats_percpu_hash();
+	map_percpu_stats_hash_prealloc();
+	map_percpu_stats_percpu_hash_prealloc();
+	map_percpu_stats_lru_hash();
+	map_percpu_stats_lru_hash_no_common();
+	map_percpu_stats_percpu_lru_hash();
+	map_percpu_stats_percpu_lru_hash_no_common();
+	map_percpu_stats_hash_of_maps();
+}
diff --git a/tools/testing/selftests/bpf/progs/map_percpu_stats.c b/tools/testing/selftests/bpf/progs/map_percpu_stats.c
new file mode 100644
index 0000000000000..10b2325c17207
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_percpu_stats.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+__u32 target_id;
+
+__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym;
+
+SEC("iter/bpf_map")
+int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct bpf_map *map = ctx->map;
+
+	if (map && map->id == target_id)
+		BPF_SEQ_PRINTF(seq, "%lld", bpf_map_sum_elem_count(map));
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From e76a014334a6d46a9c21356afa25aa5b81566540 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@rivosinc.com>
Date: Thu, 6 Jul 2023 16:22:28 +0200
Subject: [PATCH 0022/1806] selftests/bpf: Bump and validate MAX_SYMS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BPF tests that load /proc/kallsyms, e.g. bpf_cookie, will perform a
buffer overrun if the number of syms on the system is larger than
MAX_SYMS.

Bump the MAX_SYMS to 400000, and add a runtime check that bails out if
the maximum is reached.

Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20230706142228.1128452-1-bjorn@kernel.org
---
 tools/testing/selftests/bpf/trace_helpers.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 9b070cdf44ace..f83d9f65c65b5 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -18,7 +18,7 @@
 #define TRACEFS_PIPE	"/sys/kernel/tracing/trace_pipe"
 #define DEBUGFS_PIPE	"/sys/kernel/debug/tracing/trace_pipe"
 
-#define MAX_SYMS 300000
+#define MAX_SYMS 400000
 static struct ksym syms[MAX_SYMS];
 static int sym_cnt;
 
@@ -46,6 +46,9 @@ int load_kallsyms_refresh(void)
 			break;
 		if (!addr)
 			continue;
+		if (i >= MAX_SYMS)
+			return -EFBIG;
+
 		syms[i].addr = (long) addr;
 		syms[i].name = strdup(func);
 		i++;
-- 
GitLab


From 8a3fe76f8718bad4056d665bee1a0c43d128af72 Mon Sep 17 00:00:00 2001
From: Jackie Liu <liuyun01@kylinos.cn>
Date: Wed, 5 Jul 2023 17:12:08 +0800
Subject: [PATCH 0023/1806] libbpf: Cross-join available_filter_functions and
 kallsyms for multi-kprobes

When using regular expression matching with "kprobe multi", it scans all
the functions under "/proc/kallsyms" that can be matched. However, not all
of them can be traced by kprobe.multi. If any one of the functions fails
to be traced, it will result in the failure of all functions. The best
approach is to filter out the functions that cannot be traced to ensure
proper tracking of the functions.

Closes: https://lore.kernel.org/oe-kbuild-all/202307030355.TdXOHklM-lkp@intel.com/
Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Jiri Olsa <jolsa@kernel.org>
Suggested-by: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230705091209.3803873-1-liu.yun@linux.dev
---
 tools/lib/bpf/libbpf.c | 110 ++++++++++++++++++++++++++++++++++++-----
 1 file changed, 97 insertions(+), 13 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 1c6588ad3e753..924bf52f06e43 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10228,6 +10228,12 @@ static const char *tracefs_uprobe_events(void)
 	return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events";
 }
 
+static const char *tracefs_available_filter_functions(void)
+{
+	return use_debugfs() ? DEBUGFS"/available_filter_functions"
+			     : TRACEFS"/available_filter_functions";
+}
+
 static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
 					 const char *kfunc_name, size_t offset)
 {
@@ -10543,25 +10549,107 @@ struct kprobe_multi_resolve {
 	size_t cnt;
 };
 
-static int
-resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type,
-			const char *sym_name, void *ctx)
+struct avail_kallsyms_data {
+	char **syms;
+	size_t cnt;
+	struct kprobe_multi_resolve *res;
+};
+
+static int avail_func_cmp(const void *a, const void *b)
 {
-	struct kprobe_multi_resolve *res = ctx;
+	return strcmp(*(const char **)a, *(const char **)b);
+}
+
+static int avail_kallsyms_cb(unsigned long long sym_addr, char sym_type,
+			     const char *sym_name, void *ctx)
+{
+	struct avail_kallsyms_data *data = ctx;
+	struct kprobe_multi_resolve *res = data->res;
 	int err;
 
-	if (!glob_match(sym_name, res->pattern))
+	if (!bsearch(&sym_name, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp))
 		return 0;
 
-	err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long),
-				res->cnt + 1);
+	err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, sizeof(*res->addrs), res->cnt + 1);
 	if (err)
 		return err;
 
-	res->addrs[res->cnt++] = (unsigned long) sym_addr;
+	res->addrs[res->cnt++] = (unsigned long)sym_addr;
 	return 0;
 }
 
+static int libbpf_available_kallsyms_parse(struct kprobe_multi_resolve *res)
+{
+	const char *available_functions_file = tracefs_available_filter_functions();
+	struct avail_kallsyms_data data;
+	char sym_name[500];
+	FILE *f;
+	int err = 0, ret, i;
+	char **syms = NULL;
+	size_t cap = 0, cnt = 0;
+
+	f = fopen(available_functions_file, "re");
+	if (!f) {
+		err = -errno;
+		pr_warn("failed to open %s: %d\n", available_functions_file, err);
+		return err;
+	}
+
+	while (true) {
+		char *name;
+
+		ret = fscanf(f, "%499s%*[^\n]\n", sym_name);
+		if (ret == EOF && feof(f))
+			break;
+
+		if (ret != 1) {
+			pr_warn("failed to parse available_filter_functions entry: %d\n", ret);
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		if (!glob_match(sym_name, res->pattern))
+			continue;
+
+		err = libbpf_ensure_mem((void **)&syms, &cap, sizeof(*syms), cnt + 1);
+		if (err)
+			goto cleanup;
+
+		name = strdup(sym_name);
+		if (!name) {
+			err = -errno;
+			goto cleanup;
+		}
+
+		syms[cnt++] = name;
+	}
+
+	/* no entries found, bail out */
+	if (cnt == 0) {
+		err = -ENOENT;
+		goto cleanup;
+	}
+
+	/* sort available functions */
+	qsort(syms, cnt, sizeof(*syms), avail_func_cmp);
+
+	data.syms = syms;
+	data.res = res;
+	data.cnt = cnt;
+	libbpf_kallsyms_parse(avail_kallsyms_cb, &data);
+
+	if (res->cnt == 0)
+		err = -ENOENT;
+
+cleanup:
+	for (i = 0; i < cnt; i++)
+		free((char *)syms[i]);
+	free(syms);
+
+	fclose(f);
+	return err;
+}
+
 struct bpf_link *
 bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 				      const char *pattern,
@@ -10598,13 +10686,9 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 		return libbpf_err_ptr(-EINVAL);
 
 	if (pattern) {
-		err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res);
+		err = libbpf_available_kallsyms_parse(&res);
 		if (err)
 			goto error;
-		if (!res.cnt) {
-			err = -ENOENT;
-			goto error;
-		}
 		addrs = res.addrs;
 		cnt = res.cnt;
 	}
-- 
GitLab


From 56baeeba0a355ecf4d0c71bfbb1d5ba09501dbfc Mon Sep 17 00:00:00 2001
From: Jackie Liu <liuyun01@kylinos.cn>
Date: Wed, 5 Jul 2023 17:12:09 +0800
Subject: [PATCH 0024/1806] libbpf: Use available_filter_functions_addrs with
 multi-kprobes

Now that kernel provides a new available_filter_functions_addrs file
which can help us avoid the need to cross-validate
available_filter_functions and kallsyms, we can improve efficiency of
multi-attach kprobes. For example, on my device, the sample program [1]
of start time:

$ sudo ./funccount "tcp_*"

before   after
1.2s     1.0s

  [1]: https://github.com/JackieLiu1/ketones/tree/master/src/funccount

Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230705091209.3803873-2-liu.yun@linux.dev
---
 tools/lib/bpf/libbpf.c | 62 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 61 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 924bf52f06e43..fd4f1875df653 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10234,6 +10234,12 @@ static const char *tracefs_available_filter_functions(void)
 			     : TRACEFS"/available_filter_functions";
 }
 
+static const char *tracefs_available_filter_functions_addrs(void)
+{
+	return use_debugfs() ? DEBUGFS"/available_filter_functions_addrs"
+			     : TRACEFS"/available_filter_functions_addrs";
+}
+
 static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
 					 const char *kfunc_name, size_t offset)
 {
@@ -10650,6 +10656,57 @@ cleanup:
 	return err;
 }
 
+static bool has_available_filter_functions_addrs(void)
+{
+	return access(tracefs_available_filter_functions_addrs(), R_OK) != -1;
+}
+
+static int libbpf_available_kprobes_parse(struct kprobe_multi_resolve *res)
+{
+	const char *available_path = tracefs_available_filter_functions_addrs();
+	char sym_name[500];
+	FILE *f;
+	int ret, err = 0;
+	unsigned long long sym_addr;
+
+	f = fopen(available_path, "re");
+	if (!f) {
+		err = -errno;
+		pr_warn("failed to open %s: %d\n", available_path, err);
+		return err;
+	}
+
+	while (true) {
+		ret = fscanf(f, "%llx %499s%*[^\n]\n", &sym_addr, sym_name);
+		if (ret == EOF && feof(f))
+			break;
+
+		if (ret != 2) {
+			pr_warn("failed to parse available_filter_functions_addrs entry: %d\n",
+				ret);
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		if (!glob_match(sym_name, res->pattern))
+			continue;
+
+		err = libbpf_ensure_mem((void **)&res->addrs, &res->cap,
+					sizeof(*res->addrs), res->cnt + 1);
+		if (err)
+			goto cleanup;
+
+		res->addrs[res->cnt++] = (unsigned long)sym_addr;
+	}
+
+	if (res->cnt == 0)
+		err = -ENOENT;
+
+cleanup:
+	fclose(f);
+	return err;
+}
+
 struct bpf_link *
 bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 				      const char *pattern,
@@ -10686,7 +10743,10 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 		return libbpf_err_ptr(-EINVAL);
 
 	if (pattern) {
-		err = libbpf_available_kallsyms_parse(&res);
+		if (has_available_filter_functions_addrs())
+			err = libbpf_available_kprobes_parse(&res);
+		else
+			err = libbpf_available_kallsyms_parse(&res);
 		if (err)
 			goto error;
 		addrs = res.addrs;
-- 
GitLab


From 856fe03d929205b4c8c8fa51296342cd85592e3f Mon Sep 17 00:00:00 2001
From: Lu Hongfei <luhongfei@vivo.com>
Date: Fri, 7 Jul 2023 16:12:50 +0800
Subject: [PATCH 0025/1806] selftests/bpf: Correct two typos

When wrapping code, use ';' better than using ',' which is more in line with
the coding habits of most engineers.

Signed-off-by: Lu Hongfei <luhongfei@vivo.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20230707081253.34638-1-luhongfei@vivo.com
---
 tools/testing/selftests/bpf/benchs/bench_ringbufs.c      | 2 +-
 tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
index 3ca14ad366071..e1ee979e6acc6 100644
--- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -399,7 +399,7 @@ static void perfbuf_libbpf_setup(void)
 	ctx->skel = perfbuf_setup_skeleton();
 
 	memset(&attr, 0, sizeof(attr));
-	attr.config = PERF_COUNT_SW_BPF_OUTPUT,
+	attr.config = PERF_COUNT_SW_BPF_OUTPUT;
 	attr.type = PERF_TYPE_SOFTWARE;
 	attr.sample_type = PERF_SAMPLE_RAW;
 	/* notify only every Nth sample */
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
index 13bcaeb028b84..56685fc03c7e9 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
@@ -347,7 +347,7 @@ static void syncookie_estab(void)
 	exp_active_estab_in.max_delack_ms = 22;
 
 	exp_passive_hdr_stg.syncookie = true;
-	exp_active_hdr_stg.resend_syn = true,
+	exp_active_hdr_stg.resend_syn = true;
 
 	prepare_out();
 
-- 
GitLab


From c628747cc8800cf6d33d09f7f42c8b6f91e64dc7 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 7 Jul 2023 16:11:56 -0700
Subject: [PATCH 0026/1806] libbpf: only reset sec_def handler when necessary

Don't reset recorded sec_def handler unconditionally on
bpf_program__set_type(). There are two situations where this is wrong.

First, if the program type didn't actually change. In that case original
SEC handler should work just fine.

Second, catch-all custom SEC handler is supposed to work with any BPF
program type and SEC() annotation, so it also doesn't make sense to
reset that.

This patch fixes both issues. This was reported recently in the context
of breaking perf tool, which uses custom catch-all handler for fancy BPF
prologue generation logic. This patch should fix the issue.

  [0] https://lore.kernel.org/linux-perf-users/ab865e6d-06c5-078e-e404-7f90686db50d@amd.com/

Fixes: d6e6286a12e7 ("libbpf: disassociate section handler on explicit bpf_program__set_type() call")
Reported-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20230707231156.1711948-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index fd4f1875df653..78635feb19466 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8562,13 +8562,31 @@ enum bpf_prog_type bpf_program__type(const struct bpf_program *prog)
 	return prog->type;
 }
 
+static size_t custom_sec_def_cnt;
+static struct bpf_sec_def *custom_sec_defs;
+static struct bpf_sec_def custom_fallback_def;
+static bool has_custom_fallback_def;
+static int last_custom_sec_def_handler_id;
+
 int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
 {
 	if (prog->obj->loaded)
 		return libbpf_err(-EBUSY);
 
+	/* if type is not changed, do nothing */
+	if (prog->type == type)
+		return 0;
+
 	prog->type = type;
-	prog->sec_def = NULL;
+
+	/* If a program type was changed, we need to reset associated SEC()
+	 * handler, as it will be invalid now. The only exception is a generic
+	 * fallback handler, which by definition is program type-agnostic and
+	 * is a catch-all custom handler, optionally set by the application,
+	 * so should be able to handle any type of BPF program.
+	 */
+	if (prog->sec_def != &custom_fallback_def)
+		prog->sec_def = NULL;
 	return 0;
 }
 
@@ -8744,13 +8762,6 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("netfilter",		NETFILTER, BPF_NETFILTER, SEC_NONE),
 };
 
-static size_t custom_sec_def_cnt;
-static struct bpf_sec_def *custom_sec_defs;
-static struct bpf_sec_def custom_fallback_def;
-static bool has_custom_fallback_def;
-
-static int last_custom_sec_def_handler_id;
-
 int libbpf_register_prog_handler(const char *sec,
 				 enum bpf_prog_type prog_type,
 				 enum bpf_attach_type exp_attach_type,
-- 
GitLab


From 4cbeeb0dc02f8ac7b975b2ab0080ace53d43d62a Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@pm.me>
Date: Fri, 7 Jul 2023 10:54:22 +0100
Subject: [PATCH 0027/1806] bpftool: use a local copy of perf_event to fix
 accessing :: Bpf_cookie

When CONFIG_PERF_EVENTS is not set, struct perf_event remains empty.
However, the structure is being used by bpftool indirectly via BTF.
This leads to:

skeleton/pid_iter.bpf.c:49:30: error: no member named 'bpf_cookie' in 'struct perf_event'
        return BPF_CORE_READ(event, bpf_cookie);
               ~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~

...

skeleton/pid_iter.bpf.c:49:9: error: returning 'void' from a function with incompatible result type '__u64' (aka 'unsigned long long')
        return BPF_CORE_READ(event, bpf_cookie);
               ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Tools and samples can't use any CONFIG_ definitions, so the fields
used there should always be present.
Define struct perf_event___local with the `preserve_access_index`
attribute inside the pid_iter BPF prog to allow compiling on any
configs. CO-RE will substitute it with the real struct perf_event
accesses later on.

Fixes: cbdaf71f7e65 ("bpftool: Add bpf_cookie to link output")
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230707095425.168126-2-quentin@isovalent.com
---
 tools/bpf/bpftool/skeleton/pid_iter.bpf.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
index eb05ea53afb12..e2af8e5fb29ec 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -15,6 +15,10 @@ enum bpf_obj_type {
 	BPF_OBJ_BTF,
 };
 
+struct perf_event___local {
+	u64 bpf_cookie;
+} __attribute__((preserve_access_index));
+
 extern const void bpf_link_fops __ksym;
 extern const void bpf_map_fops __ksym;
 extern const void bpf_prog_fops __ksym;
@@ -41,8 +45,8 @@ static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type)
 /* could be used only with BPF_LINK_TYPE_PERF_EVENT links */
 static __u64 get_bpf_cookie(struct bpf_link *link)
 {
+	struct perf_event___local *event;
 	struct bpf_perf_link *perf_link;
-	struct perf_event *event;
 
 	perf_link = container_of(link, struct bpf_perf_link, link);
 	event = BPF_CORE_READ(perf_link, perf_file, private_data);
-- 
GitLab


From 67a43462ee2405c94e985a747bdcb8e3a0d66203 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@pm.me>
Date: Fri, 7 Jul 2023 10:54:23 +0100
Subject: [PATCH 0028/1806] bpftool: Define a local bpf_perf_link to fix
 accessing its fields

When building bpftool with !CONFIG_PERF_EVENTS:

skeleton/pid_iter.bpf.c:47:14: error: incomplete definition of type 'struct bpf_perf_link'
        perf_link = container_of(link, struct bpf_perf_link, link);
                    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tools/bpf/bpftool/bootstrap/libbpf/include/bpf/bpf_helpers.h:74:22: note: expanded from macro 'container_of'
                ((type *)(__mptr - offsetof(type, member)));    \
                                   ^~~~~~~~~~~~~~~~~~~~~~
tools/bpf/bpftool/bootstrap/libbpf/include/bpf/bpf_helpers.h:68:60: note: expanded from macro 'offsetof'
 #define offsetof(TYPE, MEMBER)  ((unsigned long)&((TYPE *)0)->MEMBER)
                                                  ~~~~~~~~~~~^
skeleton/pid_iter.bpf.c:44:9: note: forward declaration of 'struct bpf_perf_link'
        struct bpf_perf_link *perf_link;
               ^

&bpf_perf_link is being defined and used only under the ifdef.
Define struct bpf_perf_link___local with the `preserve_access_index`
attribute inside the pid_iter BPF prog to allow compiling on any
configs. CO-RE will substitute it with the real struct bpf_perf_link
accesses later on.
container_of() uses offsetof(), which does the necessary CO-RE
relocation if the field is specified with `preserve_access_index` - as
is the case for struct bpf_perf_link___local.

Fixes: cbdaf71f7e65 ("bpftool: Add bpf_cookie to link output")
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230707095425.168126-3-quentin@isovalent.com
---
 tools/bpf/bpftool/skeleton/pid_iter.bpf.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
index e2af8e5fb29ec..3a4c4f7d83d86 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -15,6 +15,11 @@ enum bpf_obj_type {
 	BPF_OBJ_BTF,
 };
 
+struct bpf_perf_link___local {
+	struct bpf_link link;
+	struct file *perf_file;
+} __attribute__((preserve_access_index));
+
 struct perf_event___local {
 	u64 bpf_cookie;
 } __attribute__((preserve_access_index));
@@ -45,10 +50,10 @@ static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type)
 /* could be used only with BPF_LINK_TYPE_PERF_EVENT links */
 static __u64 get_bpf_cookie(struct bpf_link *link)
 {
+	struct bpf_perf_link___local *perf_link;
 	struct perf_event___local *event;
-	struct bpf_perf_link *perf_link;
 
-	perf_link = container_of(link, struct bpf_perf_link, link);
+	perf_link = container_of(link, struct bpf_perf_link___local, link);
 	event = BPF_CORE_READ(perf_link, perf_file, private_data);
 	return BPF_CORE_READ(event, bpf_cookie);
 }
-- 
GitLab


From 44ba7b30e84fb40da2295e85a6d209e199fdc977 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Fri, 7 Jul 2023 10:54:24 +0100
Subject: [PATCH 0029/1806] bpftool: Use a local copy of
 BPF_LINK_TYPE_PERF_EVENT in pid_iter.bpf.c

In order to allow the BPF program in bpftool's pid_iter.bpf.c to compile
correctly on hosts where vmlinux.h does not define
BPF_LINK_TYPE_PERF_EVENT (running kernel versions lower than 5.15, for
example), define and use a local copy of the enum value. This requires
LLVM 12 or newer to build the BPF program.

Fixes: cbdaf71f7e65 ("bpftool: Add bpf_cookie to link output")
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230707095425.168126-4-quentin@isovalent.com
---
 tools/bpf/bpftool/skeleton/pid_iter.bpf.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
index 3a4c4f7d83d86..26004f0c5a6ae 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -24,6 +24,10 @@ struct perf_event___local {
 	u64 bpf_cookie;
 } __attribute__((preserve_access_index));
 
+enum bpf_link_type___local {
+	BPF_LINK_TYPE_PERF_EVENT___local = 7,
+};
+
 extern const void bpf_link_fops __ksym;
 extern const void bpf_map_fops __ksym;
 extern const void bpf_prog_fops __ksym;
@@ -93,10 +97,13 @@ int iter(struct bpf_iter__task_file *ctx)
 	e.pid = task->tgid;
 	e.id = get_obj_id(file->private_data, obj_type);
 
-	if (obj_type == BPF_OBJ_LINK) {
+	if (obj_type == BPF_OBJ_LINK &&
+	    bpf_core_enum_value_exists(enum bpf_link_type___local,
+				       BPF_LINK_TYPE_PERF_EVENT___local)) {
 		struct bpf_link *link = (struct bpf_link *) file->private_data;
 
-		if (BPF_CORE_READ(link, type) == BPF_LINK_TYPE_PERF_EVENT) {
+		if (link->type == bpf_core_enum_value(enum bpf_link_type___local,
+						      BPF_LINK_TYPE_PERF_EVENT___local)) {
 			e.has_bpf_cookie = true;
 			e.bpf_cookie = get_bpf_cookie(link);
 		}
-- 
GitLab


From 658ac06801315b739774a15796ff06913ef5cad5 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@pm.me>
Date: Fri, 7 Jul 2023 10:54:25 +0100
Subject: [PATCH 0030/1806] bpftool: Use a local bpf_perf_event_value to fix
 accessing its fields

Fix the following error when building bpftool:

  CLANG   profiler.bpf.o
  CLANG   pid_iter.bpf.o
skeleton/profiler.bpf.c:18:21: error: invalid application of 'sizeof' to an incomplete type 'struct bpf_perf_event_value'
        __uint(value_size, sizeof(struct bpf_perf_event_value));
                           ^     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tools/bpf/bpftool/bootstrap/libbpf/include/bpf/bpf_helpers.h:13:39: note: expanded from macro '__uint'
tools/bpf/bpftool/bootstrap/libbpf/include/bpf/bpf_helper_defs.h:7:8: note: forward declaration of 'struct bpf_perf_event_value'
struct bpf_perf_event_value;
       ^

struct bpf_perf_event_value is being used in the kernel only when
CONFIG_BPF_EVENTS is enabled, so it misses a BTF entry then.
Define struct bpf_perf_event_value___local with the
`preserve_access_index` attribute inside the pid_iter BPF prog to
allow compiling on any configs. It is a full mirror of a UAPI
structure, so is compatible both with and w/o CO-RE.
bpf_perf_event_read_value() requires a pointer of the original type,
so a cast is needed.

Fixes: 47c09d6a9f67 ("bpftool: Introduce "prog profile" command")
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230707095425.168126-5-quentin@isovalent.com
---
 tools/bpf/bpftool/skeleton/profiler.bpf.c | 27 ++++++++++++++---------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c
index ce5b65e07ab10..2f80edc682f11 100644
--- a/tools/bpf/bpftool/skeleton/profiler.bpf.c
+++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c
@@ -4,6 +4,12 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+struct bpf_perf_event_value___local {
+	__u64 counter;
+	__u64 enabled;
+	__u64 running;
+} __attribute__((preserve_access_index));
+
 /* map of perf event fds, num_cpu * num_metric entries */
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
@@ -15,14 +21,14 @@ struct {
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(key_size, sizeof(u32));
-	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(value_size, sizeof(struct bpf_perf_event_value___local));
 } fentry_readings SEC(".maps");
 
 /* accumulated readings */
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(key_size, sizeof(u32));
-	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(value_size, sizeof(struct bpf_perf_event_value___local));
 } accum_readings SEC(".maps");
 
 /* sample counts, one per cpu */
@@ -39,7 +45,7 @@ const volatile __u32 num_metric = 1;
 SEC("fentry/XXX")
 int BPF_PROG(fentry_XXX)
 {
-	struct bpf_perf_event_value *ptrs[MAX_NUM_MATRICS];
+	struct bpf_perf_event_value___local *ptrs[MAX_NUM_MATRICS];
 	u32 key = bpf_get_smp_processor_id();
 	u32 i;
 
@@ -53,10 +59,10 @@ int BPF_PROG(fentry_XXX)
 	}
 
 	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
-		struct bpf_perf_event_value reading;
+		struct bpf_perf_event_value___local reading;
 		int err;
 
-		err = bpf_perf_event_read_value(&events, key, &reading,
+		err = bpf_perf_event_read_value(&events, key, (void *)&reading,
 						sizeof(reading));
 		if (err)
 			return 0;
@@ -68,14 +74,14 @@ int BPF_PROG(fentry_XXX)
 }
 
 static inline void
-fexit_update_maps(u32 id, struct bpf_perf_event_value *after)
+fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after)
 {
-	struct bpf_perf_event_value *before, diff;
+	struct bpf_perf_event_value___local *before, diff;
 
 	before = bpf_map_lookup_elem(&fentry_readings, &id);
 	/* only account samples with a valid fentry_reading */
 	if (before && before->counter) {
-		struct bpf_perf_event_value *accum;
+		struct bpf_perf_event_value___local *accum;
 
 		diff.counter = after->counter - before->counter;
 		diff.enabled = after->enabled - before->enabled;
@@ -93,7 +99,7 @@ fexit_update_maps(u32 id, struct bpf_perf_event_value *after)
 SEC("fexit/XXX")
 int BPF_PROG(fexit_XXX)
 {
-	struct bpf_perf_event_value readings[MAX_NUM_MATRICS];
+	struct bpf_perf_event_value___local readings[MAX_NUM_MATRICS];
 	u32 cpu = bpf_get_smp_processor_id();
 	u32 i, zero = 0;
 	int err;
@@ -102,7 +108,8 @@ int BPF_PROG(fexit_XXX)
 	/* read all events before updating the maps, to reduce error */
 	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
 		err = bpf_perf_event_read_value(&events, cpu + i * num_cpu,
-						readings + i, sizeof(*readings));
+						(void *)(readings + i),
+						sizeof(*readings));
 		if (err)
 			return 0;
 	}
-- 
GitLab


From 4d496be9ca05d22dbbbba78368ac4bb05bcc67f2 Mon Sep 17 00:00:00 2001
From: David Vernet <void@manifault.com>
Date: Mon, 10 Jul 2023 13:30:27 -0500
Subject: [PATCH 0031/1806] bpf,docs: Create new standardization subdirectory

The BPF standardization effort is actively underway with the IETF. As
described in the BPF Working Group (WG) charter in [0], there are a
number of proposed documents, some informational and some proposed
standards, that will be drafted as part of the standardization effort.

[0]: https://datatracker.ietf.org/wg/bpf/about/

Though the specific documents that will formally be standardized will
exist as Internet Drafts (I-D) and WG documents in the BPF WG
datatracker page, the source of truth from where those documents will be
generated will reside in the kernel documentation tree (originating in
the bpf-next tree).

Because these documents will be used to generate the I-D and WG
documents which will be standardized with the IETF, they are a bit
special as far as kernel-tree documentation goes:

- They will be dual licensed with LGPL-2.1 OR BSD-2-Clause
- IETF I-D and WG documents (the documents which will actually be
  standardized) will be auto-generated from these documents.

In order to keep things clearly organized in the BPF documentation tree,
and to make it abundantly clear where standards-related documentation
needs to go, we should move standards-relevant documents into a separate
standardization/ subdirectory.

Signed-off-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/r/20230710183027.15132-1-void@manifault.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/bpf/index.rst                    |  3 +--
 Documentation/bpf/standardization/index.rst    | 18 ++++++++++++++++++
 .../{ => standardization}/instruction-set.rst  |  0
 .../bpf/{ => standardization}/linux-notes.rst  |  3 ++-
 MAINTAINERS                                    |  2 +-
 5 files changed, 22 insertions(+), 4 deletions(-)
 create mode 100644 Documentation/bpf/standardization/index.rst
 rename Documentation/bpf/{ => standardization}/instruction-set.rst (100%)
 rename Documentation/bpf/{ => standardization}/linux-notes.rst (96%)

diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index dbb39e8f98898..1ff177b89d66b 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -12,9 +12,9 @@ that goes into great technical depth about the BPF Architecture.
 .. toctree::
    :maxdepth: 1
 
-   instruction-set
    verifier
    libbpf/index
+   standardization/index
    btf
    faq
    syscall_api
@@ -29,7 +29,6 @@ that goes into great technical depth about the BPF Architecture.
    bpf_licensing
    test_debug
    clang-notes
-   linux-notes
    other
    redirect
 
diff --git a/Documentation/bpf/standardization/index.rst b/Documentation/bpf/standardization/index.rst
new file mode 100644
index 0000000000000..09c6ba055fd70
--- /dev/null
+++ b/Documentation/bpf/standardization/index.rst
@@ -0,0 +1,18 @@
+.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+===================
+BPF Standardization
+===================
+
+This directory contains documents that are being iterated on as part of the BPF
+standardization effort with the IETF. See the `IETF BPF Working Group`_ page
+for the working group charter, documents, and more.
+
+.. toctree::
+   :maxdepth: 1
+
+   instruction-set
+   linux-notes
+
+.. Links:
+.. _IETF BPF Working Group: https://datatracker.ietf.org/wg/bpf/about/
diff --git a/Documentation/bpf/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
similarity index 100%
rename from Documentation/bpf/instruction-set.rst
rename to Documentation/bpf/standardization/instruction-set.rst
diff --git a/Documentation/bpf/linux-notes.rst b/Documentation/bpf/standardization/linux-notes.rst
similarity index 96%
rename from Documentation/bpf/linux-notes.rst
rename to Documentation/bpf/standardization/linux-notes.rst
index 508d009d3bede..00d2693de025a 100644
--- a/Documentation/bpf/linux-notes.rst
+++ b/Documentation/bpf/standardization/linux-notes.rst
@@ -45,7 +45,8 @@ On Linux, this integer is a BTF ID.
 Legacy BPF Packet access instructions
 =====================================
 
-As mentioned in the `ISA standard documentation <instruction-set.rst#legacy-bpf-packet-access-instructions>`_,
+As mentioned in the `ISA standard documentation
+<instruction-set.html#legacy-bpf-packet-access-instructions>`_,
 Linux has special eBPF instructions for access to packet data that have been
 carried over from classic BPF to retain the performance of legacy socket
 filters running in the eBPF interpreter.
diff --git a/MAINTAINERS b/MAINTAINERS
index acbe54087d1ce..99d8dc9b28500 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3746,7 +3746,7 @@ R:	David Vernet <void@manifault.com>
 L:	bpf@vger.kernel.org
 L:	bpf@ietf.org
 S:	Maintained
-F:	Documentation/bpf/instruction-set.rst
+F:	Documentation/bpf/standardization/
 
 BPF [GENERAL] (Safe Dynamic Programs and Tools)
 M:	Alexei Starovoitov <ast@kernel.org>
-- 
GitLab


From 8a0260dbf6553c969248b6530cafadac46562f47 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 10 Jul 2023 19:41:50 -0700
Subject: [PATCH 0032/1806] libbpf: Fix realloc API handling in zero-sized edge
 cases

realloc() and reallocarray() can either return NULL or a special
non-NULL pointer, if their size argument is zero. This requires a bit
more care to handle NULL-as-valid-result situation differently from
NULL-as-error case. This has caused real issues before ([0]), and just
recently bit again in production when performing bpf_program__attach_usdt().

This patch fixes 4 places that do or potentially could suffer from this
mishandling of NULL, including the reported USDT-related one.

There are many other places where realloc()/reallocarray() is used and
NULL is always treated as an error value, but all those have guarantees
that their size is always non-zero, so those spot don't need any extra
handling.

  [0] d08ab82f59d5 ("libbpf: Fix double-free when linker processes empty sections")

Fixes: 999783c8bbda ("libbpf: Wire up spec management and other arch-independent USDT logic")
Fixes: b63b3c490eee ("libbpf: Add bpf_program__set_insns function")
Fixes: 697f104db8a6 ("libbpf: Support custom SEC() handlers")
Fixes: b12688267280 ("libbpf: Change the order of data and text relocations.")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230711024150.1566433-1-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 15 ++++++++++++---
 tools/lib/bpf/usdt.c   |  5 ++++-
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 78635feb19466..63311a73c16d4 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6161,7 +6161,11 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra
 	if (main_prog == subprog)
 		return 0;
 	relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos));
-	if (!relos)
+	/* if new count is zero, reallocarray can return a valid NULL result;
+	 * in this case the previous pointer will be freed, so we *have to*
+	 * reassign old pointer to the new value (even if it's NULL)
+	 */
+	if (!relos && new_cnt)
 		return -ENOMEM;
 	if (subprog->nr_reloc)
 		memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc,
@@ -8532,7 +8536,8 @@ int bpf_program__set_insns(struct bpf_program *prog,
 		return -EBUSY;
 
 	insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns));
-	if (!insns) {
+	/* NULL is a valid return from reallocarray if the new count is zero */
+	if (!insns && new_insn_cnt) {
 		pr_warn("prog '%s': failed to realloc prog code\n", prog->name);
 		return -ENOMEM;
 	}
@@ -8841,7 +8846,11 @@ int libbpf_unregister_prog_handler(int handler_id)
 
 	/* try to shrink the array, but it's ok if we couldn't */
 	sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs));
-	if (sec_defs)
+	/* if new count is zero, reallocarray can return a valid NULL result;
+	 * in this case the previous pointer will be freed, so we *have to*
+	 * reassign old pointer to the new value (even if it's NULL)
+	 */
+	if (sec_defs || custom_sec_def_cnt == 0)
 		custom_sec_defs = sec_defs;
 
 	return 0;
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index f1a141555f084..37455d00b239c 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -852,8 +852,11 @@ static int bpf_link_usdt_detach(struct bpf_link *link)
 		 * system is so exhausted on memory, it's the least of user's
 		 * concerns, probably.
 		 * So just do our best here to return those IDs to usdt_manager.
+		 * Another edge case when we can legitimately get NULL is when
+		 * new_cnt is zero, which can happen in some edge cases, so we
+		 * need to be careful about that.
 		 */
-		if (new_free_ids) {
+		if (new_free_ids || new_cnt == 0) {
 			memcpy(new_free_ids + man->free_spec_cnt, usdt_link->spec_ids,
 			       usdt_link->spec_cnt * sizeof(*usdt_link->spec_ids));
 			man->free_spec_ids = new_free_ids;
-- 
GitLab


From 274c4a6d529cff48b241b15627b46b0f65987ade Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 10 Jul 2023 13:08:29 +0300
Subject: [PATCH 0033/1806] net/core: Make use of assign_bit() API

We have for some time the assign_bit() API to replace open coded

	if (foo)
		set_bit(n, bar);
	else
		clear_bit(n, bar);

Use this API in the code. No functional change intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Message-ID: <20230710100830.89936-1-andriy.shevchenko@linux.intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/dev.c  |  8 ++------
 net/core/sock.c | 15 +++------------
 2 files changed, 5 insertions(+), 18 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 69a3e544676c4..d6e1b786c5c52 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6316,12 +6316,8 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 	 * softirq mode will happen in the next round of napi_schedule().
 	 * This should not cause hiccups/stalls to the live traffic.
 	 */
-	list_for_each_entry(napi, &dev->napi_list, dev_list) {
-		if (threaded)
-			set_bit(NAPI_STATE_THREADED, &napi->state);
-		else
-			clear_bit(NAPI_STATE_THREADED, &napi->state);
-	}
+	list_for_each_entry(napi, &dev->napi_list, dev_list)
+		assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
 
 	return err;
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 9370fd50aa2c9..ab1e8d1bd5a1f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1244,17 +1244,11 @@ set_sndbuf:
 		break;
 
 	case SO_PASSCRED:
-		if (valbool)
-			set_bit(SOCK_PASSCRED, &sock->flags);
-		else
-			clear_bit(SOCK_PASSCRED, &sock->flags);
+		assign_bit(SOCK_PASSCRED, &sock->flags, valbool);
 		break;
 
 	case SO_PASSPIDFD:
-		if (valbool)
-			set_bit(SOCK_PASSPIDFD, &sock->flags);
-		else
-			clear_bit(SOCK_PASSPIDFD, &sock->flags);
+		assign_bit(SOCK_PASSPIDFD, &sock->flags, valbool);
 		break;
 
 	case SO_TIMESTAMP_OLD:
@@ -1358,10 +1352,7 @@ set_sndbuf:
 		break;
 
 	case SO_PASSSEC:
-		if (valbool)
-			set_bit(SOCK_PASSSEC, &sock->flags);
-		else
-			clear_bit(SOCK_PASSSEC, &sock->flags);
+		assign_bit(SOCK_PASSSEC, &sock->flags, valbool);
 		break;
 	case SO_MARK:
 		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-- 
GitLab


From b8e39b38487e68c6503419db6e4a851a0ef56de7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 10 Jul 2023 13:08:30 +0300
Subject: [PATCH 0034/1806] netlink: Make use of __assign_bit() API

We have for some time the __assign_bit() API to replace open coded

	if (foo)
		__set_bit(n, bar);
	else
		__clear_bit(n, bar);

Use this API in the code. No functional change intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Message-ID: <20230710100830.89936-2-andriy.shevchenko@linux.intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/netlink/af_netlink.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 3836318737483..9c9df143a2ec0 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1629,10 +1629,7 @@ static void netlink_update_socket_mc(struct netlink_sock *nlk,
 
 	old = test_bit(group - 1, nlk->groups);
 	subscriptions = nlk->subscriptions - old + new;
-	if (new)
-		__set_bit(group - 1, nlk->groups);
-	else
-		__clear_bit(group - 1, nlk->groups);
+	__assign_bit(group - 1, nlk->groups, new);
 	netlink_update_subscriptions(&nlk->sk, subscriptions);
 	netlink_update_listeners(&nlk->sk);
 }
-- 
GitLab


From a3e7e6b17946f48badce98d7ac360678a0ea7393 Mon Sep 17 00:00:00 2001
From: John Sanpe <sanpeqf@gmail.com>
Date: Tue, 11 Jul 2023 15:07:12 +0800
Subject: [PATCH 0035/1806] libbpf: Remove HASHMAP_INIT static initialization
 helper

Remove the wrong HASHMAP_INIT. It's not used anywhere in libbpf.

Signed-off-by: John Sanpe <sanpeqf@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230711070712.2064144-1-sanpeqf@gmail.com
---
 tools/lib/bpf/hashmap.h | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index 0a5bf1937a7c5..c12f8320e6682 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -80,16 +80,6 @@ struct hashmap {
 	size_t sz;
 };
 
-#define HASHMAP_INIT(hash_fn, equal_fn, ctx) {	\
-	.hash_fn = (hash_fn),			\
-	.equal_fn = (equal_fn),			\
-	.ctx = (ctx),				\
-	.buckets = NULL,			\
-	.cap = 0,				\
-	.cap_bits = 0,				\
-	.sz = 0,				\
-}
-
 void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
 		   hashmap_equal_fn equal_fn, void *ctx);
 struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
-- 
GitLab


From 07018b57066e0009c0b9945723f30e532d347ed3 Mon Sep 17 00:00:00 2001
From: Rong Tao <rongtao@cestc.cn>
Date: Tue, 11 Jul 2023 19:14:59 +0800
Subject: [PATCH 0036/1806] samples/bpf: syscall_tp: Aarch64 no open syscall

__NR_open never exist on AArch64.

Signed-off-by: Rong Tao <rongtao@cestc.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/tencent_C6AD4AD72BEFE813228FC188905F96C6A506@qq.com
---
 samples/bpf/syscall_tp_kern.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c
index e7121dd1ee377..090fecfe641a9 100644
--- a/samples/bpf/syscall_tp_kern.c
+++ b/samples/bpf/syscall_tp_kern.c
@@ -44,12 +44,14 @@ static __always_inline void count(void *map)
 		bpf_map_update_elem(map, &key, &init_val, BPF_NOEXIST);
 }
 
+#if !defined(__aarch64__)
 SEC("tracepoint/syscalls/sys_enter_open")
 int trace_enter_open(struct syscalls_enter_open_args *ctx)
 {
 	count(&enter_open_map);
 	return 0;
 }
+#endif
 
 SEC("tracepoint/syscalls/sys_enter_openat")
 int trace_enter_open_at(struct syscalls_enter_open_args *ctx)
@@ -65,12 +67,14 @@ int trace_enter_open_at2(struct syscalls_enter_open_args *ctx)
 	return 0;
 }
 
+#if !defined(__aarch64__)
 SEC("tracepoint/syscalls/sys_exit_open")
 int trace_enter_exit(struct syscalls_exit_open_args *ctx)
 {
 	count(&exit_open_map);
 	return 0;
 }
+#endif
 
 SEC("tracepoint/syscalls/sys_exit_openat")
 int trace_enter_exit_at(struct syscalls_exit_open_args *ctx)
-- 
GitLab


From 7ac8d0d2619256cc13eaf4a889b3177a1607b02d Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:21 +0000
Subject: [PATCH 0037/1806] bpf: Support ->fill_link_info for kprobe_multi

With the addition of support for fill_link_info to the kprobe_multi link,
users will gain the ability to inspect it conveniently using the
`bpftool link show`. This enhancement provides valuable information to the
user, including the count of probed functions and their respective
addresses. It's important to note that if the kptr_restrict setting is not
permitted, the probed address will not be exposed, ensuring security.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-2-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       |  5 +++++
 kernel/trace/bpf_trace.c       | 37 ++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  5 +++++
 3 files changed, 47 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 60a9d59beeabb..a4e881c64e0fe 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6439,6 +6439,11 @@ struct bpf_link_info {
 			__s32 priority;
 			__u32 flags;
 		} netfilter;
+		struct {
+			__aligned_u64 addrs;
+			__u32 count; /* in/out: kprobe_multi function count */
+			__u32 flags;
+		} kprobe_multi;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 03b7f6b8e4f0c..acb3d6dd7a772 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2469,6 +2469,7 @@ struct bpf_kprobe_multi_link {
 	u32 cnt;
 	u32 mods_cnt;
 	struct module **mods;
+	u32 flags;
 };
 
 struct bpf_kprobe_multi_run_ctx {
@@ -2558,9 +2559,44 @@ static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
 	kfree(kmulti_link);
 }
 
+static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
+						struct bpf_link_info *info)
+{
+	u64 __user *uaddrs = u64_to_user_ptr(info->kprobe_multi.addrs);
+	struct bpf_kprobe_multi_link *kmulti_link;
+	u32 ucount = info->kprobe_multi.count;
+	int err = 0, i;
+
+	if (!uaddrs ^ !ucount)
+		return -EINVAL;
+
+	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	info->kprobe_multi.count = kmulti_link->cnt;
+	info->kprobe_multi.flags = kmulti_link->flags;
+
+	if (!uaddrs)
+		return 0;
+	if (ucount < kmulti_link->cnt)
+		err = -ENOSPC;
+	else
+		ucount = kmulti_link->cnt;
+
+	if (kallsyms_show_value(current_cred())) {
+		if (copy_to_user(uaddrs, kmulti_link->addrs, ucount * sizeof(u64)))
+			return -EFAULT;
+	} else {
+		for (i = 0; i < ucount; i++) {
+			if (put_user(0, uaddrs + i))
+				return -EFAULT;
+		}
+	}
+	return err;
+}
+
 static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
 	.release = bpf_kprobe_multi_link_release,
 	.dealloc = bpf_kprobe_multi_link_dealloc,
+	.fill_link_info = bpf_kprobe_multi_link_fill_link_info,
 };
 
 static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv)
@@ -2872,6 +2908,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	link->addrs = addrs;
 	link->cookies = cookies;
 	link->cnt = cnt;
+	link->flags = flags;
 
 	if (cookies) {
 		/*
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 60a9d59beeabb..a4e881c64e0fe 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6439,6 +6439,11 @@ struct bpf_link_info {
 			__s32 priority;
 			__u32 flags;
 		} netfilter;
+		struct {
+			__aligned_u64 addrs;
+			__u32 count; /* in/out: kprobe_multi function count */
+			__u32 flags;
+		} kprobe_multi;
 	};
 } __attribute__((aligned(8)));
 
-- 
GitLab


From dc6519445b33bcd9c0ce69c914979a3c0c6e80ce Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:22 +0000
Subject: [PATCH 0038/1806] bpftool: Dump the kernel symbol's module name

If the kernel symbol is in a module, we will dump the module name as
well. The square brackets around the module name are trimmed.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-3-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/xlated_dumper.c | 6 +++++-
 tools/bpf/bpftool/xlated_dumper.h | 2 ++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index da608e10c843a..567f56dfd9f1e 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -46,7 +46,11 @@ out:
 		}
 		dd->sym_mapping = tmp;
 		sym = &dd->sym_mapping[dd->sym_count];
-		if (sscanf(buff, "%p %*c %s", &address, sym->name) != 2)
+
+		/* module is optional */
+		sym->module[0] = '\0';
+		/* trim the square brackets around the module name */
+		if (sscanf(buff, "%p %*c %s [%[^]]s", &address, sym->name, sym->module) < 2)
 			continue;
 		sym->address = (unsigned long)address;
 		if (!strcmp(sym->name, "__bpf_call_base")) {
diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h
index 9a946377b0e63..db3ba0671501b 100644
--- a/tools/bpf/bpftool/xlated_dumper.h
+++ b/tools/bpf/bpftool/xlated_dumper.h
@@ -5,12 +5,14 @@
 #define __BPF_TOOL_XLATED_DUMPER_H
 
 #define SYM_MAX_NAME	256
+#define MODULE_MAX_NAME	64
 
 struct bpf_prog_linfo;
 
 struct kernel_sym {
 	unsigned long address;
 	char name[SYM_MAX_NAME];
+	char module[MODULE_MAX_NAME];
 };
 
 struct dump_data {
-- 
GitLab


From edd7f49bb884139af9069dcf59d9f89f1f4ddf3f Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:23 +0000
Subject: [PATCH 0039/1806] bpftool: Show kprobe_multi link info

Show the already expose kprobe_multi link info in bpftool. The result as
follows,

$ tools/bpf/bpftool/bpftool link show
91: kprobe_multi  prog 244
        kprobe.multi  func_cnt 7
        addr             func [module]
        ffffffff98c44f20 schedule_timeout_interruptible
        ffffffff98c44f60 schedule_timeout_killable
        ffffffff98c44fa0 schedule_timeout_uninterruptible
        ffffffff98c44fe0 schedule_timeout_idle
        ffffffffc075b8d0 xfs_trans_get_efd [xfs]
        ffffffffc0768a10 xfs_trans_get_buf_map [xfs]
        ffffffffc076c320 xfs_trans_get_dqtrx [xfs]
        pids kprobe_multi(188367)
92: kprobe_multi  prog 244
        kretprobe.multi  func_cnt 7
        addr             func [module]
        ffffffff98c44f20 schedule_timeout_interruptible
        ffffffff98c44f60 schedule_timeout_killable
        ffffffff98c44fa0 schedule_timeout_uninterruptible
        ffffffff98c44fe0 schedule_timeout_idle
        ffffffffc075b8d0 xfs_trans_get_efd [xfs]
        ffffffffc0768a10 xfs_trans_get_buf_map [xfs]
        ffffffffc076c320 xfs_trans_get_dqtrx [xfs]
        pids kprobe_multi(188367)

$ tools/bpf/bpftool/bpftool link show -j
[{"id":91,"type":"kprobe_multi","prog_id":244,"retprobe":false,"func_cnt":7,"funcs":[{"addr":18446744071977586464,"func":"schedule_timeout_interruptible","module":null},{"addr":18446744071977586528,"func":"schedule_timeout_killable","module":null},{"addr":18446744071977586592,"func":"schedule_timeout_uninterruptible","module":null},{"addr":18446744071977586656,"func":"schedule_timeout_idle","module":null},{"addr":18446744072643524816,"func":"xfs_trans_get_efd","module":"xfs"},{"addr":18446744072643578384,"func":"xfs_trans_get_buf_map","module":"xfs"},{"addr":18446744072643592992,"func":"xfs_trans_get_dqtrx","module":"xfs"}],"pids":[{"pid":188367,"comm":"kprobe_multi"}]},{"id":92,"type":"kprobe_multi","prog_id":244,"retprobe":true,"func_cnt":7,"funcs":[{"addr":18446744071977586464,"func":"schedule_timeout_interruptible","module":null},{"addr":18446744071977586528,"func":"schedule_timeout_killable","module":null},{"addr":18446744071977586592,"func":"schedule_timeout_uninterruptible","module":null},{"addr":18446744071977586656,"func":"schedule_timeout_idle","module":null},{"addr":18446744072643524816,"func":"xfs_trans_get_efd","module":"xfs"},{"addr":18446744072643578384,"func":"xfs_trans_get_buf_map","module":"xfs"},{"addr":18446744072643592992,"func":"xfs_trans_get_dqtrx","module":"xfs"}],"pids":[{"pid":188367,"comm":"kprobe_multi"}]}]

When kptr_restrict is 2, the result is,

$ tools/bpf/bpftool/bpftool link show
91: kprobe_multi  prog 244
        kprobe.multi  func_cnt 7
92: kprobe_multi  prog 244
        kretprobe.multi  func_cnt 7

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-4-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/link.c | 118 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 115 insertions(+), 3 deletions(-)

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 2d786072ed0d0..a4f5a436777f0 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -14,8 +14,10 @@
 
 #include "json_writer.h"
 #include "main.h"
+#include "xlated_dumper.h"
 
 static struct hashmap *link_table;
+static struct dump_data dd;
 
 static int link_parse_fd(int *argc, char ***argv)
 {
@@ -166,6 +168,50 @@ static int get_prog_info(int prog_id, struct bpf_prog_info *info)
 	return err;
 }
 
+static int cmp_u64(const void *A, const void *B)
+{
+	const __u64 *a = A, *b = B;
+
+	return *a - *b;
+}
+
+static void
+show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	__u32 i, j = 0;
+	__u64 *addrs;
+
+	jsonw_bool_field(json_wtr, "retprobe",
+			 info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN);
+	jsonw_uint_field(json_wtr, "func_cnt", info->kprobe_multi.count);
+	jsonw_name(json_wtr, "funcs");
+	jsonw_start_array(json_wtr);
+	addrs = u64_to_ptr(info->kprobe_multi.addrs);
+	qsort(addrs, info->kprobe_multi.count, sizeof(addrs[0]), cmp_u64);
+
+	/* Load it once for all. */
+	if (!dd.sym_count)
+		kernel_syms_load(&dd);
+	for (i = 0; i < dd.sym_count; i++) {
+		if (dd.sym_mapping[i].address != addrs[j])
+			continue;
+		jsonw_start_object(json_wtr);
+		jsonw_uint_field(json_wtr, "addr", dd.sym_mapping[i].address);
+		jsonw_string_field(json_wtr, "func", dd.sym_mapping[i].name);
+		/* Print null if it is vmlinux */
+		if (dd.sym_mapping[i].module[0] == '\0') {
+			jsonw_name(json_wtr, "module");
+			jsonw_null(json_wtr);
+		} else {
+			jsonw_string_field(json_wtr, "module", dd.sym_mapping[i].module);
+		}
+		jsonw_end_object(json_wtr);
+		if (j++ == info->kprobe_multi.count)
+			break;
+	}
+	jsonw_end_array(json_wtr);
+}
+
 static int show_link_close_json(int fd, struct bpf_link_info *info)
 {
 	struct bpf_prog_info prog_info;
@@ -218,6 +264,9 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 		jsonw_uint_field(json_wtr, "map_id",
 				 info->struct_ops.map_id);
 		break;
+	case BPF_LINK_TYPE_KPROBE_MULTI:
+		show_kprobe_multi_json(info, json_wtr);
+		break;
 	default:
 		break;
 	}
@@ -351,6 +400,44 @@ void netfilter_dump_plain(const struct bpf_link_info *info)
 		printf(" flags 0x%x", info->netfilter.flags);
 }
 
+static void show_kprobe_multi_plain(struct bpf_link_info *info)
+{
+	__u32 i, j = 0;
+	__u64 *addrs;
+
+	if (!info->kprobe_multi.count)
+		return;
+
+	if (info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN)
+		printf("\n\tkretprobe.multi  ");
+	else
+		printf("\n\tkprobe.multi  ");
+	printf("func_cnt %u  ", info->kprobe_multi.count);
+	addrs = (__u64 *)u64_to_ptr(info->kprobe_multi.addrs);
+	qsort(addrs, info->kprobe_multi.count, sizeof(__u64), cmp_u64);
+
+	/* Load it once for all. */
+	if (!dd.sym_count)
+		kernel_syms_load(&dd);
+	if (!dd.sym_count)
+		return;
+
+	printf("\n\t%-16s %s", "addr", "func [module]");
+	for (i = 0; i < dd.sym_count; i++) {
+		if (dd.sym_mapping[i].address != addrs[j])
+			continue;
+		printf("\n\t%016lx %s",
+		       dd.sym_mapping[i].address, dd.sym_mapping[i].name);
+		if (dd.sym_mapping[i].module[0] != '\0')
+			printf(" [%s]  ", dd.sym_mapping[i].module);
+		else
+			printf("  ");
+
+		if (j++ == info->kprobe_multi.count)
+			break;
+	}
+}
+
 static int show_link_close_plain(int fd, struct bpf_link_info *info)
 {
 	struct bpf_prog_info prog_info;
@@ -396,6 +483,9 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_NETFILTER:
 		netfilter_dump_plain(info);
 		break;
+	case BPF_LINK_TYPE_KPROBE_MULTI:
+		show_kprobe_multi_plain(info);
+		break;
 	default:
 		break;
 	}
@@ -417,7 +507,9 @@ static int do_show_link(int fd)
 {
 	struct bpf_link_info info;
 	__u32 len = sizeof(info);
+	__u64 *addrs = NULL;
 	char buf[256];
+	int count;
 	int err;
 
 	memset(&info, 0, sizeof(info));
@@ -431,22 +523,38 @@ again:
 	}
 	if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT &&
 	    !info.raw_tracepoint.tp_name) {
-		info.raw_tracepoint.tp_name = (unsigned long)&buf;
+		info.raw_tracepoint.tp_name = ptr_to_u64(&buf);
 		info.raw_tracepoint.tp_name_len = sizeof(buf);
 		goto again;
 	}
 	if (info.type == BPF_LINK_TYPE_ITER &&
 	    !info.iter.target_name) {
-		info.iter.target_name = (unsigned long)&buf;
+		info.iter.target_name = ptr_to_u64(&buf);
 		info.iter.target_name_len = sizeof(buf);
 		goto again;
 	}
+	if (info.type == BPF_LINK_TYPE_KPROBE_MULTI &&
+	    !info.kprobe_multi.addrs) {
+		count = info.kprobe_multi.count;
+		if (count) {
+			addrs = calloc(count, sizeof(__u64));
+			if (!addrs) {
+				p_err("mem alloc failed");
+				close(fd);
+				return -ENOMEM;
+			}
+			info.kprobe_multi.addrs = ptr_to_u64(addrs);
+			goto again;
+		}
+	}
 
 	if (json_output)
 		show_link_close_json(fd, &info);
 	else
 		show_link_close_plain(fd, &info);
 
+	if (addrs)
+		free(addrs);
 	close(fd);
 	return 0;
 }
@@ -471,7 +579,8 @@ static int do_show(int argc, char **argv)
 		fd = link_parse_fd(&argc, &argv);
 		if (fd < 0)
 			return fd;
-		return do_show_link(fd);
+		do_show_link(fd);
+		goto out;
 	}
 
 	if (argc)
@@ -510,6 +619,9 @@ static int do_show(int argc, char **argv)
 	if (show_pinned)
 		delete_pinned_obj_table(link_table);
 
+out:
+	if (dd.sym_count)
+		kernel_syms_destroy(&dd);
 	return errno == ENOENT ? 0 : -1;
 }
 
-- 
GitLab


From f1a414537ecc18b5882a57045ce3e4a11e528290 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:24 +0000
Subject: [PATCH 0040/1806] bpf: Protect probed address based on kptr_restrict
 setting

The probed address can be accessed by userspace through querying the task
file descriptor (fd). However, it is crucial to adhere to the kptr_restrict
setting and refrain from exposing the address if it is not permitted.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-5-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/trace_kprobe.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 1b3fa7b854aa7..249eb14d0f7ab 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1551,7 +1551,10 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
 	} else {
 		*symbol = NULL;
 		*probe_offset = 0;
-		*probe_addr = (unsigned long)tk->rp.kp.addr;
+		if (kallsyms_show_value(current_cred()))
+			*probe_addr = (unsigned long)tk->rp.kp.addr;
+		else
+			*probe_addr = 0;
 	}
 	return 0;
 }
-- 
GitLab


From 5125e757e62f6c1d5478db4c2b61a744060ddf3f Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:25 +0000
Subject: [PATCH 0041/1806] bpf: Clear the probe_addr for uprobe

To avoid returning uninitialized or random values when querying the file
descriptor (fd) and accessing probe_addr, it is necessary to clear the
variable prior to its use.

Fixes: 41bdc4b40ed6 ("bpf: introduce bpf subcommand BPF_TASK_FD_QUERY")
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-6-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/trace_events.h | 3 ++-
 kernel/trace/bpf_trace.c     | 2 +-
 kernel/trace/trace_uprobe.c  | 3 ++-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 7c4a0b72334eb..36de9ebec4409 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -864,7 +864,8 @@ extern int  perf_uprobe_init(struct perf_event *event,
 extern void perf_uprobe_destroy(struct perf_event *event);
 extern int bpf_get_uprobe_info(const struct perf_event *event,
 			       u32 *fd_type, const char **filename,
-			       u64 *probe_offset, bool perf_type_tracepoint);
+			       u64 *probe_offset, u64 *probe_addr,
+			       bool perf_type_tracepoint);
 #endif
 extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index acb3d6dd7a772..31ec0e2853ec4 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2384,7 +2384,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 #ifdef CONFIG_UPROBE_EVENTS
 		if (flags & TRACE_EVENT_FL_UPROBE)
 			err = bpf_get_uprobe_info(event, fd_type, buf,
-						  probe_offset,
+						  probe_offset, probe_addr,
 						  event->attr.type == PERF_TYPE_TRACEPOINT);
 #endif
 	}
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 8b92e34ff0c83..fd6c71450ba74 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1415,7 +1415,7 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
 
 int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
 			const char **filename, u64 *probe_offset,
-			bool perf_type_tracepoint)
+			u64 *probe_addr, bool perf_type_tracepoint)
 {
 	const char *pevent = trace_event_name(event->tp_event);
 	const char *group = event->tp_event->class->system;
@@ -1432,6 +1432,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
 				    : BPF_FD_TYPE_UPROBE;
 	*filename = tu->filename;
 	*probe_offset = tu->offset;
+	*probe_addr = 0;
 	return 0;
 }
 #endif	/* CONFIG_PERF_EVENTS */
-- 
GitLab


From cd3910d005052382901fe3d0a3aeed48b1b64906 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:26 +0000
Subject: [PATCH 0042/1806] bpf: Expose symbol's respective address

Since different symbols can share the same name, it is insufficient to only
expose the symbol name. It is essential to also expose the symbol address
so that users can accurately identify which one is being probed.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-7-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/trace_kprobe.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 249eb14d0f7ab..bf2872ca5aaf6 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1544,18 +1544,10 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
 
 	*fd_type = trace_kprobe_is_return(tk) ? BPF_FD_TYPE_KRETPROBE
 					      : BPF_FD_TYPE_KPROBE;
-	if (tk->symbol) {
-		*symbol = tk->symbol;
-		*probe_offset = tk->rp.kp.offset;
-		*probe_addr = 0;
-	} else {
-		*symbol = NULL;
-		*probe_offset = 0;
-		if (kallsyms_show_value(current_cred()))
-			*probe_addr = (unsigned long)tk->rp.kp.addr;
-		else
-			*probe_addr = 0;
-	}
+	*probe_offset = tk->rp.kp.offset;
+	*probe_addr = kallsyms_show_value(current_cred()) ?
+		      (unsigned long)tk->rp.kp.addr : 0;
+	*symbol = tk->symbol;
 	return 0;
 }
 #endif	/* CONFIG_PERF_EVENTS */
-- 
GitLab


From 57d485376552480602ab83bf7499b451bae5a1b9 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:27 +0000
Subject: [PATCH 0043/1806] bpf: Add a common helper bpf_copy_to_user()

Add a common helper bpf_copy_to_user(), which will be used at multiple
places.
No functional change.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-8-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/syscall.c | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a2aef900519c2..4aa6e5776a04b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3295,6 +3295,25 @@ static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link,
 		   raw_tp_link->btp->tp->name);
 }
 
+static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen,
+			    u32 len)
+{
+	if (ulen >= len + 1) {
+		if (copy_to_user(ubuf, buf, len + 1))
+			return -EFAULT;
+	} else {
+		char zero = '\0';
+
+		if (copy_to_user(ubuf, buf, ulen - 1))
+			return -EFAULT;
+		if (put_user(zero, ubuf + ulen - 1))
+			return -EFAULT;
+		return -ENOSPC;
+	}
+
+	return 0;
+}
+
 static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
 					  struct bpf_link_info *info)
 {
@@ -3313,20 +3332,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
 	if (!ubuf)
 		return 0;
 
-	if (ulen >= tp_len + 1) {
-		if (copy_to_user(ubuf, tp_name, tp_len + 1))
-			return -EFAULT;
-	} else {
-		char zero = '\0';
-
-		if (copy_to_user(ubuf, tp_name, ulen - 1))
-			return -EFAULT;
-		if (put_user(zero, ubuf + ulen - 1))
-			return -EFAULT;
-		return -ENOSPC;
-	}
-
-	return 0;
+	return bpf_copy_to_user(ubuf, tp_name, ulen, tp_len);
 }
 
 static const struct bpf_link_ops bpf_raw_tp_link_lops = {
-- 
GitLab


From 1b715e1b0ec531fae72cd6698fe1c98affa436f8 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:28 +0000
Subject: [PATCH 0044/1806] bpf: Support ->fill_link_info for perf_event

By introducing support for ->fill_link_info to the perf_event link, users
gain the ability to inspect it using `bpftool link show`. While the current
approach involves accessing this information via `bpftool perf show`,
consolidating link information for all link types in one place offers
greater convenience. Additionally, this patch extends support to the
generic perf event, which is not currently accommodated by
`bpftool perf show`. While only the perf type and config are exposed to
userspace, other attributes such as sample_period and sample_freq are
ignored. It's important to note that if kptr_restrict is not permitted, the
probed address will not be exposed, maintaining security measures.

A new enum bpf_perf_event_type is introduced to help the user understand
which struct is relevant.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-9-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       |  35 ++++++++
 kernel/bpf/syscall.c           | 146 +++++++++++++++++++++++++++++++++
 kernel/trace/bpf_trace.c       |  10 ++-
 tools/include/uapi/linux/bpf.h |  35 ++++++++
 4 files changed, 223 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a4e881c64e0fe..600d0caebbd8a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1057,6 +1057,16 @@ enum bpf_link_type {
 	MAX_BPF_LINK_TYPE,
 };
 
+enum bpf_perf_event_type {
+	BPF_PERF_EVENT_UNSPEC = 0,
+	BPF_PERF_EVENT_UPROBE = 1,
+	BPF_PERF_EVENT_URETPROBE = 2,
+	BPF_PERF_EVENT_KPROBE = 3,
+	BPF_PERF_EVENT_KRETPROBE = 4,
+	BPF_PERF_EVENT_TRACEPOINT = 5,
+	BPF_PERF_EVENT_EVENT = 6,
+};
+
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
  *
  * NONE(default): No further bpf programs allowed in the subtree.
@@ -6444,6 +6454,31 @@ struct bpf_link_info {
 			__u32 count; /* in/out: kprobe_multi function count */
 			__u32 flags;
 		} kprobe_multi;
+		struct {
+			__u32 type; /* enum bpf_perf_event_type */
+			__u32 :32;
+			union {
+				struct {
+					__aligned_u64 file_name; /* in/out */
+					__u32 name_len;
+					__u32 offset; /* offset from file_name */
+				} uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */
+				struct {
+					__aligned_u64 func_name; /* in/out */
+					__u32 name_len;
+					__u32 offset; /* offset from func_name */
+					__u64 addr;
+				} kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
+				struct {
+					__aligned_u64 tp_name;   /* in/out */
+					__u32 name_len;
+				} tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */
+				struct {
+					__u64 config;
+					__u32 type;
+				} event; /* BPF_PERF_EVENT_EVENT */
+			};
+		} perf_event;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4aa6e5776a04b..ee8cb1a174aa1 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3364,9 +3364,155 @@ static void bpf_perf_link_dealloc(struct bpf_link *link)
 	kfree(perf_link);
 }
 
+static int bpf_perf_link_fill_common(const struct perf_event *event,
+				     char __user *uname, u32 ulen,
+				     u64 *probe_offset, u64 *probe_addr,
+				     u32 *fd_type)
+{
+	const char *buf;
+	u32 prog_id;
+	size_t len;
+	int err;
+
+	if (!ulen ^ !uname)
+		return -EINVAL;
+	if (!uname)
+		return 0;
+
+	err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf,
+				      probe_offset, probe_addr);
+	if (err)
+		return err;
+
+	if (buf) {
+		len = strlen(buf);
+		err = bpf_copy_to_user(uname, buf, ulen, len);
+		if (err)
+			return err;
+	} else {
+		char zero = '\0';
+
+		if (put_user(zero, uname))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+#ifdef CONFIG_KPROBE_EVENTS
+static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
+				     struct bpf_link_info *info)
+{
+	char __user *uname;
+	u64 addr, offset;
+	u32 ulen, type;
+	int err;
+
+	uname = u64_to_user_ptr(info->perf_event.kprobe.func_name);
+	ulen = info->perf_event.kprobe.name_len;
+	err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
+					&type);
+	if (err)
+		return err;
+	if (type == BPF_FD_TYPE_KRETPROBE)
+		info->perf_event.type = BPF_PERF_EVENT_KRETPROBE;
+	else
+		info->perf_event.type = BPF_PERF_EVENT_KPROBE;
+
+	info->perf_event.kprobe.offset = offset;
+	if (!kallsyms_show_value(current_cred()))
+		addr = 0;
+	info->perf_event.kprobe.addr = addr;
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_UPROBE_EVENTS
+static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
+				     struct bpf_link_info *info)
+{
+	char __user *uname;
+	u64 addr, offset;
+	u32 ulen, type;
+	int err;
+
+	uname = u64_to_user_ptr(info->perf_event.uprobe.file_name);
+	ulen = info->perf_event.uprobe.name_len;
+	err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
+					&type);
+	if (err)
+		return err;
+
+	if (type == BPF_FD_TYPE_URETPROBE)
+		info->perf_event.type = BPF_PERF_EVENT_URETPROBE;
+	else
+		info->perf_event.type = BPF_PERF_EVENT_UPROBE;
+	info->perf_event.uprobe.offset = offset;
+	return 0;
+}
+#endif
+
+static int bpf_perf_link_fill_probe(const struct perf_event *event,
+				    struct bpf_link_info *info)
+{
+#ifdef CONFIG_KPROBE_EVENTS
+	if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE)
+		return bpf_perf_link_fill_kprobe(event, info);
+#endif
+#ifdef CONFIG_UPROBE_EVENTS
+	if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE)
+		return bpf_perf_link_fill_uprobe(event, info);
+#endif
+	return -EOPNOTSUPP;
+}
+
+static int bpf_perf_link_fill_tracepoint(const struct perf_event *event,
+					 struct bpf_link_info *info)
+{
+	char __user *uname;
+	u32 ulen;
+
+	uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name);
+	ulen = info->perf_event.tracepoint.name_len;
+	info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT;
+	return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL);
+}
+
+static int bpf_perf_link_fill_perf_event(const struct perf_event *event,
+					 struct bpf_link_info *info)
+{
+	info->perf_event.event.type = event->attr.type;
+	info->perf_event.event.config = event->attr.config;
+	info->perf_event.type = BPF_PERF_EVENT_EVENT;
+	return 0;
+}
+
+static int bpf_perf_link_fill_link_info(const struct bpf_link *link,
+					struct bpf_link_info *info)
+{
+	struct bpf_perf_link *perf_link;
+	const struct perf_event *event;
+
+	perf_link = container_of(link, struct bpf_perf_link, link);
+	event = perf_get_event(perf_link->perf_file);
+	if (IS_ERR(event))
+		return PTR_ERR(event);
+
+	switch (event->prog->type) {
+	case BPF_PROG_TYPE_PERF_EVENT:
+		return bpf_perf_link_fill_perf_event(event, info);
+	case BPF_PROG_TYPE_TRACEPOINT:
+		return bpf_perf_link_fill_tracepoint(event, info);
+	case BPF_PROG_TYPE_KPROBE:
+		return bpf_perf_link_fill_probe(event, info);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct bpf_link_ops bpf_perf_link_lops = {
 	.release = bpf_perf_link_release,
 	.dealloc = bpf_perf_link_dealloc,
+	.fill_link_info = bpf_perf_link_fill_link_info,
 };
 
 static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 31ec0e2853ec4..897edfc9ca129 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2369,9 +2369,13 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 	if (is_tracepoint || is_syscall_tp) {
 		*buf = is_tracepoint ? event->tp_event->tp->name
 				     : event->tp_event->name;
-		*fd_type = BPF_FD_TYPE_TRACEPOINT;
-		*probe_offset = 0x0;
-		*probe_addr = 0x0;
+		/* We allow NULL pointer for tracepoint */
+		if (fd_type)
+			*fd_type = BPF_FD_TYPE_TRACEPOINT;
+		if (probe_offset)
+			*probe_offset = 0x0;
+		if (probe_addr)
+			*probe_addr = 0x0;
 	} else {
 		/* kprobe/uprobe */
 		err = -EOPNOTSUPP;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a4e881c64e0fe..600d0caebbd8a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1057,6 +1057,16 @@ enum bpf_link_type {
 	MAX_BPF_LINK_TYPE,
 };
 
+enum bpf_perf_event_type {
+	BPF_PERF_EVENT_UNSPEC = 0,
+	BPF_PERF_EVENT_UPROBE = 1,
+	BPF_PERF_EVENT_URETPROBE = 2,
+	BPF_PERF_EVENT_KPROBE = 3,
+	BPF_PERF_EVENT_KRETPROBE = 4,
+	BPF_PERF_EVENT_TRACEPOINT = 5,
+	BPF_PERF_EVENT_EVENT = 6,
+};
+
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
  *
  * NONE(default): No further bpf programs allowed in the subtree.
@@ -6444,6 +6454,31 @@ struct bpf_link_info {
 			__u32 count; /* in/out: kprobe_multi function count */
 			__u32 flags;
 		} kprobe_multi;
+		struct {
+			__u32 type; /* enum bpf_perf_event_type */
+			__u32 :32;
+			union {
+				struct {
+					__aligned_u64 file_name; /* in/out */
+					__u32 name_len;
+					__u32 offset; /* offset from file_name */
+				} uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */
+				struct {
+					__aligned_u64 func_name; /* in/out */
+					__u32 name_len;
+					__u32 offset; /* offset from func_name */
+					__u64 addr;
+				} kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
+				struct {
+					__aligned_u64 tp_name;   /* in/out */
+					__u32 name_len;
+				} tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */
+				struct {
+					__u64 config;
+					__u32 type;
+				} event; /* BPF_PERF_EVENT_EVENT */
+			};
+		} perf_event;
 	};
 } __attribute__((aligned(8)));
 
-- 
GitLab


From 62b57e3ddd64002f5b3f6fb2ea50b79a2994cfec Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:29 +0000
Subject: [PATCH 0045/1806] bpftool: Add perf event names

Add new functions and macros to get perf event names. These names except
the perf_type_name are all copied from
tool/perf/util/{parse-events,evsel}.c, so that in the future we will
have a good chance to use the same code.

Suggested-by: Jiri Olsa <olsajiri@gmail.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-10-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/link.c | 67 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index a4f5a436777f0..8e4d9176a6e85 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -5,6 +5,7 @@
 #include <linux/err.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter_arp.h>
+#include <linux/perf_event.h>
 #include <net/if.h>
 #include <stdio.h>
 #include <unistd.h>
@@ -19,6 +20,72 @@
 static struct hashmap *link_table;
 static struct dump_data dd;
 
+static const char *perf_type_name[PERF_TYPE_MAX] = {
+	[PERF_TYPE_HARDWARE]			= "hardware",
+	[PERF_TYPE_SOFTWARE]			= "software",
+	[PERF_TYPE_TRACEPOINT]			= "tracepoint",
+	[PERF_TYPE_HW_CACHE]			= "hw-cache",
+	[PERF_TYPE_RAW]				= "raw",
+	[PERF_TYPE_BREAKPOINT]			= "breakpoint",
+};
+
+const char *event_symbols_hw[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= "cpu-cycles",
+	[PERF_COUNT_HW_INSTRUCTIONS]		= "instructions",
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= "cache-references",
+	[PERF_COUNT_HW_CACHE_MISSES]		= "cache-misses",
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= "branch-instructions",
+	[PERF_COUNT_HW_BRANCH_MISSES]		= "branch-misses",
+	[PERF_COUNT_HW_BUS_CYCLES]		= "bus-cycles",
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= "stalled-cycles-frontend",
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= "stalled-cycles-backend",
+	[PERF_COUNT_HW_REF_CPU_CYCLES]		= "ref-cycles",
+};
+
+const char *event_symbols_sw[PERF_COUNT_SW_MAX] = {
+	[PERF_COUNT_SW_CPU_CLOCK]		= "cpu-clock",
+	[PERF_COUNT_SW_TASK_CLOCK]		= "task-clock",
+	[PERF_COUNT_SW_PAGE_FAULTS]		= "page-faults",
+	[PERF_COUNT_SW_CONTEXT_SWITCHES]	= "context-switches",
+	[PERF_COUNT_SW_CPU_MIGRATIONS]		= "cpu-migrations",
+	[PERF_COUNT_SW_PAGE_FAULTS_MIN]		= "minor-faults",
+	[PERF_COUNT_SW_PAGE_FAULTS_MAJ]		= "major-faults",
+	[PERF_COUNT_SW_ALIGNMENT_FAULTS]	= "alignment-faults",
+	[PERF_COUNT_SW_EMULATION_FAULTS]	= "emulation-faults",
+	[PERF_COUNT_SW_DUMMY]			= "dummy",
+	[PERF_COUNT_SW_BPF_OUTPUT]		= "bpf-output",
+	[PERF_COUNT_SW_CGROUP_SWITCHES]		= "cgroup-switches",
+};
+
+const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] = {
+	[PERF_COUNT_HW_CACHE_L1D]		= "L1-dcache",
+	[PERF_COUNT_HW_CACHE_L1I]		= "L1-icache",
+	[PERF_COUNT_HW_CACHE_LL]		= "LLC",
+	[PERF_COUNT_HW_CACHE_DTLB]		= "dTLB",
+	[PERF_COUNT_HW_CACHE_ITLB]		= "iTLB",
+	[PERF_COUNT_HW_CACHE_BPU]		= "branch",
+	[PERF_COUNT_HW_CACHE_NODE]		= "node",
+};
+
+const char *evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] = {
+	[PERF_COUNT_HW_CACHE_OP_READ]		= "load",
+	[PERF_COUNT_HW_CACHE_OP_WRITE]		= "store",
+	[PERF_COUNT_HW_CACHE_OP_PREFETCH]	= "prefetch",
+};
+
+const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[PERF_COUNT_HW_CACHE_RESULT_ACCESS]	= "refs",
+	[PERF_COUNT_HW_CACHE_RESULT_MISS]	= "misses",
+};
+
+#define perf_event_name(array, id) ({			\
+	const char *event_str = NULL;			\
+							\
+	if ((id) >= 0 && (id) < ARRAY_SIZE(array))	\
+		event_str = array[id];			\
+	event_str;					\
+})
+
 static int link_parse_fd(int *argc, char ***argv)
 {
 	int fd;
-- 
GitLab


From 88d6160737fa7bec9addb9c479b8166e88bc5ff5 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:30 +0000
Subject: [PATCH 0046/1806] bpftool: Show perf link info

Enhance bpftool to display comprehensive information about exposed
perf_event links, covering uprobe, kprobe, tracepoint, and generic perf
event. The resulting output will include the following details:

$ tools/bpf/bpftool/bpftool link show
3: perf_event  prog 14
        event software:cpu-clock
        bpf_cookie 0
        pids perf_event(19483)
4: perf_event  prog 14
        event hw-cache:LLC-load-misses
        bpf_cookie 0
        pids perf_event(19483)
5: perf_event  prog 14
        event hardware:cpu-cycles
        bpf_cookie 0
        pids perf_event(19483)
6: perf_event  prog 19
        tracepoint sched_switch
        bpf_cookie 0
        pids tracepoint(20947)
7: perf_event  prog 26
        uprobe /home/dev/waken/bpf/uprobe/a.out+0x1338
        bpf_cookie 0
        pids uprobe(21973)
8: perf_event  prog 27
        uretprobe /home/dev/waken/bpf/uprobe/a.out+0x1338
        bpf_cookie 0
        pids uprobe(21973)
10: perf_event  prog 43
        kprobe ffffffffb70a9660 kernel_clone
        bpf_cookie 0
        pids kprobe(35275)
11: perf_event  prog 41
        kretprobe ffffffffb70a9660 kernel_clone
        bpf_cookie 0
        pids kprobe(35275)

$ tools/bpf/bpftool/bpftool link show -j
[{"id":3,"type":"perf_event","prog_id":14,"event_type":"software","event_config":"cpu-clock","bpf_cookie":0,"pids":[{"pid":19483,"comm":"perf_event"}]},{"id":4,"type":"perf_event","prog_id":14,"event_type":"hw-cache","event_config":"LLC-load-misses","bpf_cookie":0,"pids":[{"pid":19483,"comm":"perf_event"}]},{"id":5,"type":"perf_event","prog_id":14,"event_type":"hardware","event_config":"cpu-cycles","bpf_cookie":0,"pids":[{"pid":19483,"comm":"perf_event"}]},{"id":6,"type":"perf_event","prog_id":19,"tracepoint":"sched_switch","bpf_cookie":0,"pids":[{"pid":20947,"comm":"tracepoint"}]},{"id":7,"type":"perf_event","prog_id":26,"retprobe":false,"file":"/home/dev/waken/bpf/uprobe/a.out","offset":4920,"bpf_cookie":0,"pids":[{"pid":21973,"comm":"uprobe"}]},{"id":8,"type":"perf_event","prog_id":27,"retprobe":true,"file":"/home/dev/waken/bpf/uprobe/a.out","offset":4920,"bpf_cookie":0,"pids":[{"pid":21973,"comm":"uprobe"}]},{"id":10,"type":"perf_event","prog_id":43,"retprobe":false,"addr":18446744072485508704,"func":"kernel_clone","offset":0,"bpf_cookie":0,"pids":[{"pid":35275,"comm":"kprobe"}]},{"id":11,"type":"perf_event","prog_id":41,"retprobe":true,"addr":18446744072485508704,"func":"kernel_clone","offset":0,"bpf_cookie":0,"pids":[{"pid":35275,"comm":"kprobe"}]}]

For generic perf events, the displayed information in bpftool is limited to
the type and configuration, while other attributes such as sample_period,
sample_freq, etc., are not included.

The kernel function address won't be exposed if it is not permitted by
kptr_restrict. The result as follows when kptr_restrict is 2.

$ tools/bpf/bpftool/bpftool link show
3: perf_event  prog 14
        event software:cpu-clock
4: perf_event  prog 14
        event hw-cache:LLC-load-misses
5: perf_event  prog 14
        event hardware:cpu-cycles
6: perf_event  prog 19
        tracepoint sched_switch
7: perf_event  prog 26
        uprobe /home/dev/waken/bpf/uprobe/a.out+0x1338
8: perf_event  prog 27
        uretprobe /home/dev/waken/bpf/uprobe/a.out+0x1338
10: perf_event  prog 43
        kprobe kernel_clone
11: perf_event  prog 41
        kretprobe kernel_clone

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-11-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/link.c | 247 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 246 insertions(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 8e4d9176a6e85..65a168df63bc1 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -17,6 +17,8 @@
 #include "main.h"
 #include "xlated_dumper.h"
 
+#define PERF_HW_CACHE_LEN 128
+
 static struct hashmap *link_table;
 static struct dump_data dd;
 
@@ -279,6 +281,110 @@ show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
 	jsonw_end_array(json_wtr);
 }
 
+static void
+show_perf_event_kprobe_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	jsonw_bool_field(wtr, "retprobe", info->perf_event.type == BPF_PERF_EVENT_KRETPROBE);
+	jsonw_uint_field(wtr, "addr", info->perf_event.kprobe.addr);
+	jsonw_string_field(wtr, "func",
+			   u64_to_ptr(info->perf_event.kprobe.func_name));
+	jsonw_uint_field(wtr, "offset", info->perf_event.kprobe.offset);
+}
+
+static void
+show_perf_event_uprobe_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	jsonw_bool_field(wtr, "retprobe", info->perf_event.type == BPF_PERF_EVENT_URETPROBE);
+	jsonw_string_field(wtr, "file",
+			   u64_to_ptr(info->perf_event.uprobe.file_name));
+	jsonw_uint_field(wtr, "offset", info->perf_event.uprobe.offset);
+}
+
+static void
+show_perf_event_tracepoint_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	jsonw_string_field(wtr, "tracepoint",
+			   u64_to_ptr(info->perf_event.tracepoint.tp_name));
+}
+
+static char *perf_config_hw_cache_str(__u64 config)
+{
+	const char *hw_cache, *result, *op;
+	char *str = malloc(PERF_HW_CACHE_LEN);
+
+	if (!str) {
+		p_err("mem alloc failed");
+		return NULL;
+	}
+
+	hw_cache = perf_event_name(evsel__hw_cache, config & 0xff);
+	if (hw_cache)
+		snprintf(str, PERF_HW_CACHE_LEN, "%s-", hw_cache);
+	else
+		snprintf(str, PERF_HW_CACHE_LEN, "%lld-", config & 0xff);
+
+	op = perf_event_name(evsel__hw_cache_op, (config >> 8) & 0xff);
+	if (op)
+		snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str),
+			 "%s-", op);
+	else
+		snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str),
+			 "%lld-", (config >> 8) & 0xff);
+
+	result = perf_event_name(evsel__hw_cache_result, config >> 16);
+	if (result)
+		snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str),
+			 "%s", result);
+	else
+		snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str),
+			 "%lld", config >> 16);
+	return str;
+}
+
+static const char *perf_config_str(__u32 type, __u64 config)
+{
+	const char *perf_config;
+
+	switch (type) {
+	case PERF_TYPE_HARDWARE:
+		perf_config = perf_event_name(event_symbols_hw, config);
+		break;
+	case PERF_TYPE_SOFTWARE:
+		perf_config = perf_event_name(event_symbols_sw, config);
+		break;
+	case PERF_TYPE_HW_CACHE:
+		perf_config = perf_config_hw_cache_str(config);
+		break;
+	default:
+		perf_config = NULL;
+		break;
+	}
+	return perf_config;
+}
+
+static void
+show_perf_event_event_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	__u64 config = info->perf_event.event.config;
+	__u32 type = info->perf_event.event.type;
+	const char *perf_type, *perf_config;
+
+	perf_type = perf_event_name(perf_type_name, type);
+	if (perf_type)
+		jsonw_string_field(wtr, "event_type", perf_type);
+	else
+		jsonw_uint_field(wtr, "event_type", type);
+
+	perf_config = perf_config_str(type, config);
+	if (perf_config)
+		jsonw_string_field(wtr, "event_config", perf_config);
+	else
+		jsonw_uint_field(wtr, "event_config", config);
+
+	if (type == PERF_TYPE_HW_CACHE && perf_config)
+		free((void *)perf_config);
+}
+
 static int show_link_close_json(int fd, struct bpf_link_info *info)
 {
 	struct bpf_prog_info prog_info;
@@ -334,6 +440,26 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_KPROBE_MULTI:
 		show_kprobe_multi_json(info, json_wtr);
 		break;
+	case BPF_LINK_TYPE_PERF_EVENT:
+		switch (info->perf_event.type) {
+		case BPF_PERF_EVENT_EVENT:
+			show_perf_event_event_json(info, json_wtr);
+			break;
+		case BPF_PERF_EVENT_TRACEPOINT:
+			show_perf_event_tracepoint_json(info, json_wtr);
+			break;
+		case BPF_PERF_EVENT_KPROBE:
+		case BPF_PERF_EVENT_KRETPROBE:
+			show_perf_event_kprobe_json(info, json_wtr);
+			break;
+		case BPF_PERF_EVENT_UPROBE:
+		case BPF_PERF_EVENT_URETPROBE:
+			show_perf_event_uprobe_json(info, json_wtr);
+			break;
+		default:
+			break;
+		}
+		break;
 	default:
 		break;
 	}
@@ -505,6 +631,75 @@ static void show_kprobe_multi_plain(struct bpf_link_info *info)
 	}
 }
 
+static void show_perf_event_kprobe_plain(struct bpf_link_info *info)
+{
+	const char *buf;
+
+	buf = u64_to_ptr(info->perf_event.kprobe.func_name);
+	if (buf[0] == '\0' && !info->perf_event.kprobe.addr)
+		return;
+
+	if (info->perf_event.type == BPF_PERF_EVENT_KRETPROBE)
+		printf("\n\tkretprobe ");
+	else
+		printf("\n\tkprobe ");
+	if (info->perf_event.kprobe.addr)
+		printf("%llx ", info->perf_event.kprobe.addr);
+	printf("%s", buf);
+	if (info->perf_event.kprobe.offset)
+		printf("+%#x", info->perf_event.kprobe.offset);
+	printf("  ");
+}
+
+static void show_perf_event_uprobe_plain(struct bpf_link_info *info)
+{
+	const char *buf;
+
+	buf = u64_to_ptr(info->perf_event.uprobe.file_name);
+	if (buf[0] == '\0')
+		return;
+
+	if (info->perf_event.type == BPF_PERF_EVENT_URETPROBE)
+		printf("\n\turetprobe ");
+	else
+		printf("\n\tuprobe ");
+	printf("%s+%#x  ", buf, info->perf_event.uprobe.offset);
+}
+
+static void show_perf_event_tracepoint_plain(struct bpf_link_info *info)
+{
+	const char *buf;
+
+	buf = u64_to_ptr(info->perf_event.tracepoint.tp_name);
+	if (buf[0] == '\0')
+		return;
+
+	printf("\n\ttracepoint %s  ", buf);
+}
+
+static void show_perf_event_event_plain(struct bpf_link_info *info)
+{
+	__u64 config = info->perf_event.event.config;
+	__u32 type = info->perf_event.event.type;
+	const char *perf_type, *perf_config;
+
+	printf("\n\tevent ");
+	perf_type = perf_event_name(perf_type_name, type);
+	if (perf_type)
+		printf("%s:", perf_type);
+	else
+		printf("%u :", type);
+
+	perf_config = perf_config_str(type, config);
+	if (perf_config)
+		printf("%s  ", perf_config);
+	else
+		printf("%llu  ", config);
+
+	if (type == PERF_TYPE_HW_CACHE && perf_config)
+		free((void *)perf_config);
+}
+
 static int show_link_close_plain(int fd, struct bpf_link_info *info)
 {
 	struct bpf_prog_info prog_info;
@@ -553,6 +748,26 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_KPROBE_MULTI:
 		show_kprobe_multi_plain(info);
 		break;
+	case BPF_LINK_TYPE_PERF_EVENT:
+		switch (info->perf_event.type) {
+		case BPF_PERF_EVENT_EVENT:
+			show_perf_event_event_plain(info);
+			break;
+		case BPF_PERF_EVENT_TRACEPOINT:
+			show_perf_event_tracepoint_plain(info);
+			break;
+		case BPF_PERF_EVENT_KPROBE:
+		case BPF_PERF_EVENT_KRETPROBE:
+			show_perf_event_kprobe_plain(info);
+			break;
+		case BPF_PERF_EVENT_UPROBE:
+		case BPF_PERF_EVENT_URETPROBE:
+			show_perf_event_uprobe_plain(info);
+			break;
+		default:
+			break;
+		}
+		break;
 	default:
 		break;
 	}
@@ -575,11 +790,12 @@ static int do_show_link(int fd)
 	struct bpf_link_info info;
 	__u32 len = sizeof(info);
 	__u64 *addrs = NULL;
-	char buf[256];
+	char buf[PATH_MAX];
 	int count;
 	int err;
 
 	memset(&info, 0, sizeof(info));
+	buf[0] = '\0';
 again:
 	err = bpf_link_get_info_by_fd(fd, &info, &len);
 	if (err) {
@@ -614,6 +830,35 @@ again:
 			goto again;
 		}
 	}
+	if (info.type == BPF_LINK_TYPE_PERF_EVENT) {
+		switch (info.perf_event.type) {
+		case BPF_PERF_EVENT_TRACEPOINT:
+			if (!info.perf_event.tracepoint.tp_name) {
+				info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf);
+				info.perf_event.tracepoint.name_len = sizeof(buf);
+				goto again;
+			}
+			break;
+		case BPF_PERF_EVENT_KPROBE:
+		case BPF_PERF_EVENT_KRETPROBE:
+			if (!info.perf_event.kprobe.func_name) {
+				info.perf_event.kprobe.func_name = ptr_to_u64(&buf);
+				info.perf_event.kprobe.name_len = sizeof(buf);
+				goto again;
+			}
+			break;
+		case BPF_PERF_EVENT_UPROBE:
+		case BPF_PERF_EVENT_URETPROBE:
+			if (!info.perf_event.uprobe.file_name) {
+				info.perf_event.uprobe.file_name = ptr_to_u64(&buf);
+				info.perf_event.uprobe.name_len = sizeof(buf);
+				goto again;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
 	if (json_output)
 		show_link_close_json(fd, &info);
-- 
GitLab


From 1e679b957ae244cd839b8792b589ea5a671482e8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 10 Jul 2023 09:19:39 +0200
Subject: [PATCH 0047/1806] net: dpaa: Improve error reporting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of the generic error message emitted by the driver core when a
remove callback returns an error code ("remove callback returned a
non-zero value. This will be ignored."), emit a message describing the
actual problem and return zero to suppress the generic message.

Note that apart from suppressing the generic error message there are no
side effects by changing the return value to zero. This prepares
changing the remove callback to return void.

Acked-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230710071946.3470249-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 431f8917dc392..e0e5bf0587fc7 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -3516,6 +3516,9 @@ static int dpaa_remove(struct platform_device *pdev)
 	phylink_destroy(priv->mac_dev->phylink);
 
 	err = dpaa_fq_free(dev, &priv->dpaa_fq_list);
+	if (err)
+		dev_err(dev, "Failed to free FQs on remove (%pE)\n",
+			ERR_PTR(err));
 
 	qman_delete_cgr_safe(&priv->ingress_cgr);
 	qman_release_cgrid(priv->ingress_cgr.cgrid);
@@ -3528,7 +3531,7 @@ static int dpaa_remove(struct platform_device *pdev)
 
 	free_netdev(net_dev);
 
-	return err;
+	return 0;
 }
 
 static const struct platform_device_id dpaa_devtype[] = {
-- 
GitLab


From 9c3ddc44d0c005ac3138efd53d6037dd99e43ccb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 10 Jul 2023 09:19:40 +0200
Subject: [PATCH 0048/1806] net: dpaa: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Acked-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230710071946.3470249-3-u.kleine-koenig@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index e0e5bf0587fc7..85e38a1ec22a4 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -3497,7 +3497,7 @@ free_netdev:
 	return err;
 }
 
-static int dpaa_remove(struct platform_device *pdev)
+static void dpaa_remove(struct platform_device *pdev)
 {
 	struct net_device *net_dev;
 	struct dpaa_priv *priv;
@@ -3530,8 +3530,6 @@ static int dpaa_remove(struct platform_device *pdev)
 	dpaa_bps_free(priv);
 
 	free_netdev(net_dev);
-
-	return 0;
 }
 
 static const struct platform_device_id dpaa_devtype[] = {
@@ -3549,7 +3547,7 @@ static struct platform_driver dpaa_driver = {
 	},
 	.id_table = dpaa_devtype,
 	.probe = dpaa_eth_probe,
-	.remove = dpaa_remove
+	.remove_new = dpaa_remove
 };
 
 static int __init dpaa_load(void)
-- 
GitLab


From 12d6cc19f29b86982d16e15486f8bc5f520e84a0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 10 Jul 2023 09:19:41 +0200
Subject: [PATCH 0049/1806] net: fec: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230710071946.3470249-4-u.kleine-koenig@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c        | 5 ++---
 drivers/net/ethernet/freescale/fec_mpc52xx.c     | 6 ++----
 drivers/net/ethernet/freescale/fec_mpc52xx_phy.c | 6 ++----
 3 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8fbe47703d475..1280da699fa3b 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -4458,7 +4458,7 @@ failed_ioremap:
 	return ret;
 }
 
-static int
+static void
 fec_drv_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
@@ -4494,7 +4494,6 @@ fec_drv_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 
 	free_netdev(ndev);
-	return 0;
 }
 
 static int __maybe_unused fec_suspend(struct device *dev)
@@ -4650,7 +4649,7 @@ static struct platform_driver fec_driver = {
 	},
 	.id_table = fec_devtype,
 	.probe	= fec_probe,
-	.remove	= fec_drv_remove,
+	.remove_new = fec_drv_remove,
 };
 
 module_platform_driver(fec_driver);
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c
index b88816b71ddff..984ece5cd64f6 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c
@@ -974,7 +974,7 @@ err_netdev:
 	return rv;
 }
 
-static int
+static void
 mpc52xx_fec_remove(struct platform_device *op)
 {
 	struct net_device *ndev;
@@ -998,8 +998,6 @@ mpc52xx_fec_remove(struct platform_device *op)
 	release_mem_region(ndev->base_addr, sizeof(struct mpc52xx_fec));
 
 	free_netdev(ndev);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -1042,7 +1040,7 @@ static struct platform_driver mpc52xx_fec_driver = {
 		.of_match_table = mpc52xx_fec_match,
 	},
 	.probe		= mpc52xx_fec_probe,
-	.remove		= mpc52xx_fec_remove,
+	.remove_new	= mpc52xx_fec_remove,
 #ifdef CONFIG_PM
 	.suspend	= mpc52xx_fec_of_suspend,
 	.resume		= mpc52xx_fec_of_resume,
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c b/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c
index 95f778cce98cb..61d3776d67509 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c
@@ -117,7 +117,7 @@ static int mpc52xx_fec_mdio_probe(struct platform_device *of)
 	return err;
 }
 
-static int mpc52xx_fec_mdio_remove(struct platform_device *of)
+static void mpc52xx_fec_mdio_remove(struct platform_device *of)
 {
 	struct mii_bus *bus = platform_get_drvdata(of);
 	struct mpc52xx_fec_mdio_priv *priv = bus->priv;
@@ -126,8 +126,6 @@ static int mpc52xx_fec_mdio_remove(struct platform_device *of)
 	iounmap(priv->regs);
 	kfree(priv);
 	mdiobus_free(bus);
-
-	return 0;
 }
 
 static const struct of_device_id mpc52xx_fec_mdio_match[] = {
@@ -145,7 +143,7 @@ struct platform_driver mpc52xx_fec_mdio_driver = {
 		.of_match_table = mpc52xx_fec_mdio_match,
 	},
 	.probe = mpc52xx_fec_mdio_probe,
-	.remove = mpc52xx_fec_mdio_remove,
+	.remove_new = mpc52xx_fec_mdio_remove,
 };
 
 /* let fec driver call it, since this has to be registered before it */
-- 
GitLab


From 4875b2a362e97a25d5f0ec905bb5b8672f951aeb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 10 Jul 2023 09:19:42 +0200
Subject: [PATCH 0050/1806] net: fman: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Acked-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230710071946.3470249-5-u.kleine-koenig@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fman/mac.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 43665806c5902..c5045891d694b 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -331,12 +331,11 @@ _return_of_node_put:
 	return err;
 }
 
-static int mac_remove(struct platform_device *pdev)
+static void mac_remove(struct platform_device *pdev)
 {
 	struct mac_device *mac_dev = platform_get_drvdata(pdev);
 
 	platform_device_unregister(mac_dev->priv->eth_dev);
-	return 0;
 }
 
 static struct platform_driver mac_driver = {
@@ -345,7 +344,7 @@ static struct platform_driver mac_driver = {
 		.of_match_table	= mac_match,
 	},
 	.probe		= mac_probe,
-	.remove		= mac_remove,
+	.remove_new	= mac_remove,
 };
 
 builtin_platform_driver(mac_driver);
-- 
GitLab


From ead29c5e0888ddf25300962bd18f8776b89390a0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 10 Jul 2023 09:19:43 +0200
Subject: [PATCH 0051/1806] net: fs_enet: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230710071946.3470249-6-u.kleine-koenig@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 5 ++---
 drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c  | 6 ++----
 drivers/net/ethernet/freescale/fs_enet/mii-fec.c      | 6 ++----
 3 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 8844a9a04fcf9..f9f5b28cc72e8 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -1051,7 +1051,7 @@ out_free_fpi:
 	return ret;
 }
 
-static int fs_enet_remove(struct platform_device *ofdev)
+static void fs_enet_remove(struct platform_device *ofdev)
 {
 	struct net_device *ndev = platform_get_drvdata(ofdev);
 	struct fs_enet_private *fep = netdev_priv(ndev);
@@ -1066,7 +1066,6 @@ static int fs_enet_remove(struct platform_device *ofdev)
 	if (of_phy_is_fixed_link(ofdev->dev.of_node))
 		of_phy_deregister_fixed_link(ofdev->dev.of_node);
 	free_netdev(ndev);
-	return 0;
 }
 
 static const struct of_device_id fs_enet_match[] = {
@@ -1113,7 +1112,7 @@ static struct platform_driver fs_enet_driver = {
 		.of_match_table = fs_enet_match,
 	},
 	.probe = fs_enet_probe,
-	.remove = fs_enet_remove,
+	.remove_new = fs_enet_remove,
 };
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
index 21de56345503f..91a69fc2f7c2d 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
@@ -192,7 +192,7 @@ out:
 	return ret;
 }
 
-static int fs_enet_mdio_remove(struct platform_device *ofdev)
+static void fs_enet_mdio_remove(struct platform_device *ofdev)
 {
 	struct mii_bus *bus = platform_get_drvdata(ofdev);
 	struct bb_info *bitbang = bus->priv;
@@ -201,8 +201,6 @@ static int fs_enet_mdio_remove(struct platform_device *ofdev)
 	free_mdio_bitbang(bus);
 	iounmap(bitbang->dir);
 	kfree(bitbang);
-
-	return 0;
 }
 
 static const struct of_device_id fs_enet_mdio_bb_match[] = {
@@ -219,7 +217,7 @@ static struct platform_driver fs_enet_bb_mdio_driver = {
 		.of_match_table = fs_enet_mdio_bb_match,
 	},
 	.probe = fs_enet_mdio_probe,
-	.remove = fs_enet_mdio_remove,
+	.remove_new = fs_enet_mdio_remove,
 };
 
 module_platform_driver(fs_enet_bb_mdio_driver);
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
index 59a8f0bd0f5c0..1910df250c33e 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
@@ -187,7 +187,7 @@ out:
 	return ret;
 }
 
-static int fs_enet_mdio_remove(struct platform_device *ofdev)
+static void fs_enet_mdio_remove(struct platform_device *ofdev)
 {
 	struct mii_bus *bus = platform_get_drvdata(ofdev);
 	struct fec_info *fec = bus->priv;
@@ -196,8 +196,6 @@ static int fs_enet_mdio_remove(struct platform_device *ofdev)
 	iounmap(fec->fecp);
 	kfree(fec);
 	mdiobus_free(bus);
-
-	return 0;
 }
 
 static const struct of_device_id fs_enet_mdio_fec_match[] = {
@@ -220,7 +218,7 @@ static struct platform_driver fs_enet_fec_mdio_driver = {
 		.of_match_table = fs_enet_mdio_fec_match,
 	},
 	.probe = fs_enet_mdio_probe,
-	.remove = fs_enet_mdio_remove,
+	.remove_new = fs_enet_mdio_remove,
 };
 
 module_platform_driver(fs_enet_fec_mdio_driver);
-- 
GitLab


From f833635589aefc713582ae763aed8ef997b39f91 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 10 Jul 2023 09:19:44 +0200
Subject: [PATCH 0052/1806] net: fsl_pq_mdio: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230710071946.3470249-7-u.kleine-koenig@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fsl_pq_mdio.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 9d58d83344670..01d594886f52b 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -511,7 +511,7 @@ error:
 }
 
 
-static int fsl_pq_mdio_remove(struct platform_device *pdev)
+static void fsl_pq_mdio_remove(struct platform_device *pdev)
 {
 	struct device *device = &pdev->dev;
 	struct mii_bus *bus = dev_get_drvdata(device);
@@ -521,8 +521,6 @@ static int fsl_pq_mdio_remove(struct platform_device *pdev)
 
 	iounmap(priv->map);
 	mdiobus_free(bus);
-
-	return 0;
 }
 
 static struct platform_driver fsl_pq_mdio_driver = {
@@ -531,7 +529,7 @@ static struct platform_driver fsl_pq_mdio_driver = {
 		.of_match_table = fsl_pq_mdio_match,
 	},
 	.probe = fsl_pq_mdio_probe,
-	.remove = fsl_pq_mdio_remove,
+	.remove_new = fsl_pq_mdio_remove,
 };
 
 module_platform_driver(fsl_pq_mdio_driver);
-- 
GitLab


From 4be0ebc33f39f22f5568eac9d23715d79f1d110f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 10 Jul 2023 09:19:45 +0200
Subject: [PATCH 0053/1806] net: gianfar: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230710071946.3470249-8-u.kleine-koenig@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/gianfar.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 38d5013c6fedf..0c898f9ee3581 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -3364,7 +3364,7 @@ register_fail:
 	return err;
 }
 
-static int gfar_remove(struct platform_device *ofdev)
+static void gfar_remove(struct platform_device *ofdev)
 {
 	struct gfar_private *priv = platform_get_drvdata(ofdev);
 	struct device_node *np = ofdev->dev.of_node;
@@ -3381,8 +3381,6 @@ static int gfar_remove(struct platform_device *ofdev)
 	gfar_free_rx_queues(priv);
 	gfar_free_tx_queues(priv);
 	free_gfar_dev(priv);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -3642,7 +3640,7 @@ static struct platform_driver gfar_driver = {
 		.of_match_table = gfar_match,
 	},
 	.probe = gfar_probe,
-	.remove = gfar_remove,
+	.remove_new = gfar_remove,
 };
 
 module_platform_driver(gfar_driver);
-- 
GitLab


From ae18facf566c94ba78b2acbe26feae5b5596cbea Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 10 Jul 2023 09:19:46 +0200
Subject: [PATCH 0054/1806] net: ucc_geth: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230710071946.3470249-9-u.kleine-koenig@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/ucc_geth.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 7a4cb4f07c32d..2b3a15f24e7c3 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3753,7 +3753,7 @@ err_free_info:
 	return err;
 }
 
-static int ucc_geth_remove(struct platform_device* ofdev)
+static void ucc_geth_remove(struct platform_device* ofdev)
 {
 	struct net_device *dev = platform_get_drvdata(ofdev);
 	struct ucc_geth_private *ugeth = netdev_priv(dev);
@@ -3767,8 +3767,6 @@ static int ucc_geth_remove(struct platform_device* ofdev)
 	of_node_put(ugeth->ug_info->phy_node);
 	kfree(ugeth->ug_info);
 	free_netdev(dev);
-
-	return 0;
 }
 
 static const struct of_device_id ucc_geth_match[] = {
@@ -3787,7 +3785,7 @@ static struct platform_driver ucc_geth_driver = {
 		.of_match_table = ucc_geth_match,
 	},
 	.probe		= ucc_geth_probe,
-	.remove		= ucc_geth_remove,
+	.remove_new	= ucc_geth_remove,
 	.suspend	= ucc_geth_suspend,
 	.resume		= ucc_geth_resume,
 };
-- 
GitLab


From 47b7acfb016b9fdc950cb501c351faf5723b1868 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Mon, 10 Jul 2023 17:47:47 +0800
Subject: [PATCH 0055/1806] bnxt_en: use dev_consume_skb_any() in bnxt_tx_int

Replace dev_kfree_skb_any() with dev_consume_skb_any() in bnxt_tx_int()
to clear the unnecessary noise of "kfree_skb" event.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230710094747.943782-1-imagedong@tencent.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e5b54e6025bec..d84ded8db93d8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -685,7 +685,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 next_tx_int:
 		cons = NEXT_TX(cons);
 
-		dev_kfree_skb_any(skb);
+		dev_consume_skb_any(skb);
 	}
 
 	WRITE_ONCE(txr->tx_cons, cons);
-- 
GitLab


From a8aa20a64ef2bdbad7421acf9c7217c2c0e4ac75 Mon Sep 17 00:00:00 2001
From: Andrew Halaney <ahalaney@redhat.com>
Date: Mon, 10 Jul 2023 15:06:37 -0500
Subject: [PATCH 0056/1806] net: stmmac: dwmac-qcom-ethqos: Use
 of_get_phy_mode() over device_get_phy_mode()

Since this driver only uses devicetree, let's move over to
of_get_phy_mode(). That API has an explicit error return and produces a
phy_interface_t directly instead of an int when representing the phy
mode.

Signed-off-by: Andrew Halaney <ahalaney@redhat.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c    | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index e62940414e54b..ebafdadb28d52 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -4,10 +4,10 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/of_net.h>
 #include <linux/platform_device.h>
 #include <linux/phy.h>
 #include <linux/phy/phy.h>
-#include <linux/property.h>
 
 #include "stmmac.h"
 #include "stmmac_platform.h"
@@ -104,7 +104,7 @@ struct qcom_ethqos {
 	struct clk *link_clk;
 	struct phy *serdes_phy;
 	unsigned int speed;
-	int phy_mode;
+	phy_interface_t phy_mode;
 
 	const struct ethqos_emac_por *por;
 	unsigned int num_por;
@@ -720,7 +720,9 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	if (!ethqos)
 		return -ENOMEM;
 
-	ethqos->phy_mode = device_get_phy_mode(dev);
+	ret = of_get_phy_mode(np, &ethqos->phy_mode);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to get phy mode\n");
 	switch (ethqos->phy_mode) {
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
@@ -731,8 +733,6 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	case PHY_INTERFACE_MODE_SGMII:
 		ethqos->configure_func = ethqos_configure_sgmii;
 		break;
-	case -ENODEV:
-		return -ENODEV;
 	default:
 		return -EINVAL;
 	}
-- 
GitLab


From b2f3d915b4fe203b725da8b5a88bc9d42a1ffc50 Mon Sep 17 00:00:00 2001
From: Andrew Halaney <ahalaney@redhat.com>
Date: Mon, 10 Jul 2023 15:06:38 -0500
Subject: [PATCH 0057/1806] net: stmmac: dwmac-qcom-ethqos: Use dev_err_probe()

Using dev_err_probe() logs to devices_deferred which is helpful
when debugging.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Andrew Halaney <ahalaney@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index ebafdadb28d52..1e103fd356b7c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -710,8 +710,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 
 	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
 	if (IS_ERR(plat_dat)) {
-		dev_err(dev, "dt configuration failed\n");
-		return PTR_ERR(plat_dat);
+		return dev_err_probe(dev, PTR_ERR(plat_dat),
+				     "dt configuration failed\n");
 	}
 
 	plat_dat->clks_config = ethqos_clks_config;
-- 
GitLab


From 27381e72a2db75a8d82b4baed705b9cc4e5d278d Mon Sep 17 00:00:00 2001
From: Andrew Halaney <ahalaney@redhat.com>
Date: Mon, 10 Jul 2023 15:06:39 -0500
Subject: [PATCH 0058/1806] net: stmmac: dwmac-qcom-ethqos: Log more errors in
 probe

These are useful to see when debugging a probe failure.

Signed-off-by: Andrew Halaney <ahalaney@redhat.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c    | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 1e103fd356b7c..757504ebb676a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -706,7 +706,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 
 	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
 	if (ret)
-		return ret;
+		return dev_err_probe(dev, ret,
+				     "Failed to get platform resources\n");
 
 	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
 	if (IS_ERR(plat_dat)) {
@@ -734,13 +735,16 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 		ethqos->configure_func = ethqos_configure_sgmii;
 		break;
 	default:
+		dev_err(dev, "Unsupported phy mode %s\n",
+			phy_modes(ethqos->phy_mode));
 		return -EINVAL;
 	}
 
 	ethqos->pdev = pdev;
 	ethqos->rgmii_base = devm_platform_ioremap_resource_byname(pdev, "rgmii");
 	if (IS_ERR(ethqos->rgmii_base))
-		return PTR_ERR(ethqos->rgmii_base);
+		return dev_err_probe(dev, PTR_ERR(ethqos->rgmii_base),
+				     "Failed to map rgmii resource\n");
 
 	ethqos->mac_base = stmmac_res.addr;
 
@@ -752,7 +756,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 
 	ethqos->link_clk = devm_clk_get(dev, data->link_clk_name ?: "rgmii");
 	if (IS_ERR(ethqos->link_clk))
-		return PTR_ERR(ethqos->link_clk);
+		return dev_err_probe(dev, PTR_ERR(ethqos->link_clk),
+				     "Failed to get link_clk\n");
 
 	ret = ethqos_clks_config(ethqos, true);
 	if (ret)
@@ -764,7 +769,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 
 	ethqos->serdes_phy = devm_phy_optional_get(dev, "serdes");
 	if (IS_ERR(ethqos->serdes_phy))
-		return PTR_ERR(ethqos->serdes_phy);
+		return dev_err_probe(dev, PTR_ERR(ethqos->serdes_phy),
+				     "Failed to get serdes phy\n");
 
 	ethqos->speed = SPEED_1000;
 	ethqos_update_link_clk(ethqos, SPEED_1000);
-- 
GitLab


From f42bcd168d034aa8abd9178c430b407be8c98827 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 11 Jul 2023 16:23:59 -0700
Subject: [PATCH 0059/1806] bpf: teach verifier actual bounds of
 bpf_get_smp_processor_id() result

bpf_get_smp_processor_id() helper returns current CPU on which BPF
program runs. It can't return value that is bigger than maximum allowed
number of CPUs (minus one, due to zero indexing). Teach BPF verifier to
recognize that. This makes it possible to use bpf_get_smp_processor_id()
result to index into arrays without extra checks, as demonstrated in
subsequent selftests/bpf patch.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230711232400.1658562-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 37 ++++++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 11 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 11e54dd8b6ddc..81a93eeac7a0a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -25,6 +25,7 @@
 #include <linux/btf_ids.h>
 #include <linux/poison.h>
 #include <linux/module.h>
+#include <linux/cpumask.h>
 
 #include "disasm.h"
 
@@ -9116,19 +9117,33 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
 {
 	struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
 
-	if (ret_type != RET_INTEGER ||
-	    (func_id != BPF_FUNC_get_stack &&
-	     func_id != BPF_FUNC_get_task_stack &&
-	     func_id != BPF_FUNC_probe_read_str &&
-	     func_id != BPF_FUNC_probe_read_kernel_str &&
-	     func_id != BPF_FUNC_probe_read_user_str))
+	if (ret_type != RET_INTEGER)
 		return;
 
-	ret_reg->smax_value = meta->msize_max_value;
-	ret_reg->s32_max_value = meta->msize_max_value;
-	ret_reg->smin_value = -MAX_ERRNO;
-	ret_reg->s32_min_value = -MAX_ERRNO;
-	reg_bounds_sync(ret_reg);
+	switch (func_id) {
+	case BPF_FUNC_get_stack:
+	case BPF_FUNC_get_task_stack:
+	case BPF_FUNC_probe_read_str:
+	case BPF_FUNC_probe_read_kernel_str:
+	case BPF_FUNC_probe_read_user_str:
+		ret_reg->smax_value = meta->msize_max_value;
+		ret_reg->s32_max_value = meta->msize_max_value;
+		ret_reg->smin_value = -MAX_ERRNO;
+		ret_reg->s32_min_value = -MAX_ERRNO;
+		reg_bounds_sync(ret_reg);
+		break;
+	case BPF_FUNC_get_smp_processor_id:
+		ret_reg->umax_value = nr_cpu_ids - 1;
+		ret_reg->u32_max_value = nr_cpu_ids - 1;
+		ret_reg->smax_value = nr_cpu_ids - 1;
+		ret_reg->s32_max_value = nr_cpu_ids - 1;
+		ret_reg->umin_value = 0;
+		ret_reg->u32_min_value = 0;
+		ret_reg->smin_value = 0;
+		ret_reg->s32_min_value = 0;
+		reg_bounds_sync(ret_reg);
+		break;
+	}
 }
 
 static int
-- 
GitLab


From c21de5fc5ffde70b21e4f370aebad79a7d7bdc0d Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 11 Jul 2023 16:24:00 -0700
Subject: [PATCH 0060/1806] selftests/bpf: extend existing map resize tests for
 per-cpu use case

Add a per-cpu array resizing use case and demonstrate how
bpf_get_smp_processor_id() can be used to directly access proper data
with no extra checks.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230711232400.1658562-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/global_map_resize.c   | 14 +++++++++++---
 .../selftests/bpf/progs/test_global_map_resize.c   |  8 ++++++--
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c
index fd41425d2e5c3..56b5baef35c8c 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c
@@ -22,7 +22,7 @@ static void global_map_resize_bss_subtest(void)
 	struct test_global_map_resize *skel;
 	struct bpf_map *map;
 	const __u32 desired_sz = sizeof(skel->bss->sum) + sysconf(_SC_PAGE_SIZE) * 2;
-	size_t array_len, actual_sz;
+	size_t array_len, actual_sz, new_sz;
 
 	skel = test_global_map_resize__open();
 	if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open"))
@@ -42,6 +42,10 @@ static void global_map_resize_bss_subtest(void)
 	if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize"))
 		goto teardown;
 
+	new_sz = sizeof(skel->data_percpu_arr->percpu_arr[0]) * libbpf_num_possible_cpus();
+	err = bpf_map__set_value_size(skel->maps.data_percpu_arr, new_sz);
+	ASSERT_OK(err, "percpu_arr_resize");
+
 	/* set the expected number of elements based on the resized array */
 	array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->bss->array[0]);
 	if (!ASSERT_GT(array_len, 1, "array_len"))
@@ -84,11 +88,11 @@ teardown:
 
 static void global_map_resize_data_subtest(void)
 {
-	int err;
 	struct test_global_map_resize *skel;
 	struct bpf_map *map;
 	const __u32 desired_sz = sysconf(_SC_PAGE_SIZE) * 2;
-	size_t array_len, actual_sz;
+	size_t array_len, actual_sz, new_sz;
+	int err;
 
 	skel = test_global_map_resize__open();
 	if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open"))
@@ -108,6 +112,10 @@ static void global_map_resize_data_subtest(void)
 	if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize"))
 		goto teardown;
 
+	new_sz = sizeof(skel->data_percpu_arr->percpu_arr[0]) * libbpf_num_possible_cpus();
+	err = bpf_map__set_value_size(skel->maps.data_percpu_arr, new_sz);
+	ASSERT_OK(err, "percpu_arr_resize");
+
 	/* set the expected number of elements based on the resized array */
 	array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->data_custom->my_array[0]);
 	if (!ASSERT_GT(array_len, 1, "array_len"))
diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
index 2588f23842462..1fbb73d3e5d5a 100644
--- a/tools/testing/selftests/bpf/progs/test_global_map_resize.c
+++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
@@ -29,13 +29,16 @@ int my_int SEC(".data.non_array");
 int my_array_first[1] SEC(".data.array_not_last");
 int my_int_last SEC(".data.array_not_last");
 
+int percpu_arr[1] SEC(".data.percpu_arr");
+
 SEC("tp/syscalls/sys_enter_getpid")
 int bss_array_sum(void *ctx)
 {
 	if (pid != (bpf_get_current_pid_tgid() >> 32))
 		return 0;
 
-	sum = 0;
+	/* this will be zero, we just rely on verifier not rejecting this */
+	sum = percpu_arr[bpf_get_smp_processor_id()];
 
 	for (size_t i = 0; i < bss_array_len; ++i)
 		sum += array[i];
@@ -49,7 +52,8 @@ int data_array_sum(void *ctx)
 	if (pid != (bpf_get_current_pid_tgid() >> 32))
 		return 0;
 
-	sum = 0;
+	/* this will be zero, we just rely on verifier not rejecting this */
+	sum = percpu_arr[bpf_get_smp_processor_id()];
 
 	for (size_t i = 0; i < data_array_len; ++i)
 		sum += my_array[i];
-- 
GitLab


From 12c8d0f4c8702f88a74973fb7ced85b59043b0ab Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:34 -0700
Subject: [PATCH 0061/1806] bpf: Rename few bpf_mem_alloc fields.

Rename:
-       struct rcu_head rcu;
-       struct llist_head free_by_rcu;
-       struct llist_head waiting_for_gp;
-       atomic_t call_rcu_in_progress;
+       struct llist_head free_by_rcu_ttrace;
+       struct llist_head waiting_for_gp_ttrace;
+       struct rcu_head rcu_ttrace;
+       atomic_t call_rcu_ttrace_in_progress;
...
-	static void do_call_rcu(struct bpf_mem_cache *c)
+	static void do_call_rcu_ttrace(struct bpf_mem_cache *c)

to better indicate intended use.

The 'tasks trace' is shortened to 'ttrace' to reduce verbosity.
No functional changes.

Later patches will add free_by_rcu/waiting_for_gp fields to be used with normal RCU.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-2-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 57 ++++++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 28 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 0668bcd7c926f..cc5b8adb4c83c 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -99,10 +99,11 @@ struct bpf_mem_cache {
 	int low_watermark, high_watermark, batch;
 	int percpu_size;
 
-	struct rcu_head rcu;
-	struct llist_head free_by_rcu;
-	struct llist_head waiting_for_gp;
-	atomic_t call_rcu_in_progress;
+	/* list of objects to be freed after RCU tasks trace GP */
+	struct llist_head free_by_rcu_ttrace;
+	struct llist_head waiting_for_gp_ttrace;
+	struct rcu_head rcu_ttrace;
+	atomic_t call_rcu_ttrace_in_progress;
 };
 
 struct bpf_mem_caches {
@@ -165,18 +166,18 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 	old_memcg = set_active_memcg(memcg);
 	for (i = 0; i < cnt; i++) {
 		/*
-		 * free_by_rcu is only manipulated by irq work refill_work().
+		 * free_by_rcu_ttrace is only manipulated by irq work refill_work().
 		 * IRQ works on the same CPU are called sequentially, so it is
 		 * safe to use __llist_del_first() here. If alloc_bulk() is
 		 * invoked by the initial prefill, there will be no running
 		 * refill_work(), so __llist_del_first() is fine as well.
 		 *
-		 * In most cases, objects on free_by_rcu are from the same CPU.
+		 * In most cases, objects on free_by_rcu_ttrace are from the same CPU.
 		 * If some objects come from other CPUs, it doesn't incur any
 		 * harm because NUMA_NO_NODE means the preference for current
 		 * numa node and it is not a guarantee.
 		 */
-		obj = __llist_del_first(&c->free_by_rcu);
+		obj = __llist_del_first(&c->free_by_rcu_ttrace);
 		if (!obj) {
 			/* Allocate, but don't deplete atomic reserves that typical
 			 * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
@@ -232,10 +233,10 @@ static void free_all(struct llist_node *llnode, bool percpu)
 
 static void __free_rcu(struct rcu_head *head)
 {
-	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
+	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace);
 
-	free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
-	atomic_set(&c->call_rcu_in_progress, 0);
+	free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size);
+	atomic_set(&c->call_rcu_ttrace_in_progress, 0);
 }
 
 static void __free_rcu_tasks_trace(struct rcu_head *head)
@@ -254,32 +255,32 @@ static void enque_to_free(struct bpf_mem_cache *c, void *obj)
 	struct llist_node *llnode = obj;
 
 	/* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work.
-	 * Nothing races to add to free_by_rcu list.
+	 * Nothing races to add to free_by_rcu_ttrace list.
 	 */
-	__llist_add(llnode, &c->free_by_rcu);
+	__llist_add(llnode, &c->free_by_rcu_ttrace);
 }
 
-static void do_call_rcu(struct bpf_mem_cache *c)
+static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 {
 	struct llist_node *llnode, *t;
 
-	if (atomic_xchg(&c->call_rcu_in_progress, 1))
+	if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1))
 		return;
 
-	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
-	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
-		/* There is no concurrent __llist_add(waiting_for_gp) access.
+	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
+	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu_ttrace))
+		/* There is no concurrent __llist_add(waiting_for_gp_ttrace) access.
 		 * It doesn't race with llist_del_all either.
-		 * But there could be two concurrent llist_del_all(waiting_for_gp):
+		 * But there could be two concurrent llist_del_all(waiting_for_gp_ttrace):
 		 * from __free_rcu() and from drain_mem_cache().
 		 */
-		__llist_add(llnode, &c->waiting_for_gp);
+		__llist_add(llnode, &c->waiting_for_gp_ttrace);
 	/* Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
 	 * If RCU Tasks Trace grace period implies RCU grace period, free
 	 * these elements directly, else use call_rcu() to wait for normal
 	 * progs to finish and finally do free_one() on each element.
 	 */
-	call_rcu_tasks_trace(&c->rcu, __free_rcu_tasks_trace);
+	call_rcu_tasks_trace(&c->rcu_ttrace, __free_rcu_tasks_trace);
 }
 
 static void free_bulk(struct bpf_mem_cache *c)
@@ -307,7 +308,7 @@ static void free_bulk(struct bpf_mem_cache *c)
 	/* and drain free_llist_extra */
 	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
 		enque_to_free(c, llnode);
-	do_call_rcu(c);
+	do_call_rcu_ttrace(c);
 }
 
 static void bpf_mem_refill(struct irq_work *work)
@@ -441,13 +442,13 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 
 	/* No progs are using this bpf_mem_cache, but htab_map_free() called
 	 * bpf_mem_cache_free() for all remaining elements and they can be in
-	 * free_by_rcu or in waiting_for_gp lists, so drain those lists now.
+	 * free_by_rcu_ttrace or in waiting_for_gp_ttrace lists, so drain those lists now.
 	 *
-	 * Except for waiting_for_gp list, there are no concurrent operations
+	 * Except for waiting_for_gp_ttrace list, there are no concurrent operations
 	 * on these lists, so it is safe to use __llist_del_all().
 	 */
-	free_all(__llist_del_all(&c->free_by_rcu), percpu);
-	free_all(llist_del_all(&c->waiting_for_gp), percpu);
+	free_all(__llist_del_all(&c->free_by_rcu_ttrace), percpu);
+	free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu);
 	free_all(__llist_del_all(&c->free_llist), percpu);
 	free_all(__llist_del_all(&c->free_llist_extra), percpu);
 }
@@ -462,7 +463,7 @@ static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
 
 static void free_mem_alloc(struct bpf_mem_alloc *ma)
 {
-	/* waiting_for_gp lists was drained, but __free_rcu might
+	/* waiting_for_gp_ttrace lists was drained, but __free_rcu might
 	 * still execute. Wait for it now before we freeing percpu caches.
 	 *
 	 * rcu_barrier_tasks_trace() doesn't imply synchronize_rcu_tasks_trace(),
@@ -535,7 +536,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			 */
 			irq_work_sync(&c->refill_work);
 			drain_mem_cache(c);
-			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
+			rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
 		}
 		/* objcg is the same across cpus */
 		if (c->objcg)
@@ -550,7 +551,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 				c = &cc->cache[i];
 				irq_work_sync(&c->refill_work);
 				drain_mem_cache(c);
-				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
+				rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
 			}
 		}
 		if (c->objcg)
-- 
GitLab


From a80672d7e10edab757e771a1864ea2e1b9a31ac9 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:35 -0700
Subject: [PATCH 0062/1806] bpf: Simplify code of destroy_mem_alloc() with
 kmemdup().

Use kmemdup() to simplify the code.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-3-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index cc5b8adb4c83c..b0011217be6c9 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -499,7 +499,7 @@ static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress)
 		return;
 	}
 
-	copy = kmalloc(sizeof(*ma), GFP_KERNEL);
+	copy = kmemdup(ma, sizeof(*ma), GFP_KERNEL);
 	if (!copy) {
 		/* Slow path with inline barrier-s */
 		free_mem_alloc(ma);
@@ -507,10 +507,7 @@ static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress)
 	}
 
 	/* Defer barriers into worker to let the rest of map memory to be freed */
-	copy->cache = ma->cache;
-	ma->cache = NULL;
-	copy->caches = ma->caches;
-	ma->caches = NULL;
+	memset(ma, 0, sizeof(*ma));
 	INIT_WORK(&copy->work, free_mem_alloc_deferred);
 	queue_work(system_unbound_wq, &copy->work);
 }
-- 
GitLab


From 9de3e81521b4d943c9ec27ae2c871292c12f1409 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:36 -0700
Subject: [PATCH 0063/1806] bpf: Let free_all() return the number of freed
 elements.

Let free_all() helper return the number of freed elements.
It's not used in this patch, but helps in debug/development of bpf_mem_alloc.

For example this diff for __free_rcu():
-       free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size);
+       printk("cpu %d freed %d objs after tasks trace\n", raw_smp_processor_id(),
+       	free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size));

would show how busy RCU tasks trace is.
In artificial benchmark where one cpu is allocating and different cpu is freeing
the RCU tasks trace won't be able to keep up and the list of objects
would keep growing from thousands to millions and eventually OOMing.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-4-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index b0011217be6c9..693651d2648b7 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -223,12 +223,16 @@ static void free_one(void *obj, bool percpu)
 	kfree(obj);
 }
 
-static void free_all(struct llist_node *llnode, bool percpu)
+static int free_all(struct llist_node *llnode, bool percpu)
 {
 	struct llist_node *pos, *t;
+	int cnt = 0;
 
-	llist_for_each_safe(pos, t, llnode)
+	llist_for_each_safe(pos, t, llnode) {
 		free_one(pos, percpu);
+		cnt++;
+	}
+	return cnt;
 }
 
 static void __free_rcu(struct rcu_head *head)
-- 
GitLab


From 05ae68656a8e9d9386ce4243fe992122fd29bb51 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:37 -0700
Subject: [PATCH 0064/1806] bpf: Refactor alloc_bulk().

Factor out inner body of alloc_bulk into separate helper.
No functional changes.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-5-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 46 ++++++++++++++++++++++++-------------------
 1 file changed, 26 insertions(+), 20 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 693651d2648b7..9693b1f8cbda5 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -154,11 +154,35 @@ static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)
 #endif
 }
 
+static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
+{
+	unsigned long flags;
+
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		/* In RT irq_work runs in per-cpu kthread, so disable
+		 * interrupts to avoid preemption and interrupts and
+		 * reduce the chance of bpf prog executing on this cpu
+		 * when active counter is busy.
+		 */
+		local_irq_save(flags);
+	/* alloc_bulk runs from irq_work which will not preempt a bpf
+	 * program that does unit_alloc/unit_free since IRQs are
+	 * disabled there. There is no race to increment 'active'
+	 * counter. It protects free_llist from corruption in case NMI
+	 * bpf prog preempted this loop.
+	 */
+	WARN_ON_ONCE(local_inc_return(&c->active) != 1);
+	__llist_add(obj, &c->free_llist);
+	c->free_cnt++;
+	local_dec(&c->active);
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_restore(flags);
+}
+
 /* Mostly runs from irq_work except __init phase. */
 static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 {
 	struct mem_cgroup *memcg = NULL, *old_memcg;
-	unsigned long flags;
 	void *obj;
 	int i;
 
@@ -188,25 +212,7 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 			if (!obj)
 				break;
 		}
-		if (IS_ENABLED(CONFIG_PREEMPT_RT))
-			/* In RT irq_work runs in per-cpu kthread, so disable
-			 * interrupts to avoid preemption and interrupts and
-			 * reduce the chance of bpf prog executing on this cpu
-			 * when active counter is busy.
-			 */
-			local_irq_save(flags);
-		/* alloc_bulk runs from irq_work which will not preempt a bpf
-		 * program that does unit_alloc/unit_free since IRQs are
-		 * disabled there. There is no race to increment 'active'
-		 * counter. It protects free_llist from corruption in case NMI
-		 * bpf prog preempted this loop.
-		 */
-		WARN_ON_ONCE(local_inc_return(&c->active) != 1);
-		__llist_add(obj, &c->free_llist);
-		c->free_cnt++;
-		local_dec(&c->active);
-		if (IS_ENABLED(CONFIG_PREEMPT_RT))
-			local_irq_restore(flags);
+		add_obj_to_free_list(c, obj);
 	}
 	set_active_memcg(old_memcg);
 	mem_cgroup_put(memcg);
-- 
GitLab


From 18e027b1c7c6dd858b36305468251a5e4a6bcdf7 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:38 -0700
Subject: [PATCH 0065/1806] bpf: Factor out inc/dec of active flag into
 helpers.

Factor out local_inc/dec_return(&c->active) into helpers.
No functional changes.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-6-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 9693b1f8cbda5..052fc801fb9f4 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -154,17 +154,15 @@ static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)
 #endif
 }
 
-static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
+static void inc_active(struct bpf_mem_cache *c, unsigned long *flags)
 {
-	unsigned long flags;
-
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		/* In RT irq_work runs in per-cpu kthread, so disable
 		 * interrupts to avoid preemption and interrupts and
 		 * reduce the chance of bpf prog executing on this cpu
 		 * when active counter is busy.
 		 */
-		local_irq_save(flags);
+		local_irq_save(*flags);
 	/* alloc_bulk runs from irq_work which will not preempt a bpf
 	 * program that does unit_alloc/unit_free since IRQs are
 	 * disabled there. There is no race to increment 'active'
@@ -172,13 +170,25 @@ static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
 	 * bpf prog preempted this loop.
 	 */
 	WARN_ON_ONCE(local_inc_return(&c->active) != 1);
-	__llist_add(obj, &c->free_llist);
-	c->free_cnt++;
+}
+
+static void dec_active(struct bpf_mem_cache *c, unsigned long flags)
+{
 	local_dec(&c->active);
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		local_irq_restore(flags);
 }
 
+static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
+{
+	unsigned long flags;
+
+	inc_active(c, &flags);
+	__llist_add(obj, &c->free_llist);
+	c->free_cnt++;
+	dec_active(c, flags);
+}
+
 /* Mostly runs from irq_work except __init phase. */
 static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 {
@@ -300,17 +310,13 @@ static void free_bulk(struct bpf_mem_cache *c)
 	int cnt;
 
 	do {
-		if (IS_ENABLED(CONFIG_PREEMPT_RT))
-			local_irq_save(flags);
-		WARN_ON_ONCE(local_inc_return(&c->active) != 1);
+		inc_active(c, &flags);
 		llnode = __llist_del_first(&c->free_llist);
 		if (llnode)
 			cnt = --c->free_cnt;
 		else
 			cnt = 0;
-		local_dec(&c->active);
-		if (IS_ENABLED(CONFIG_PREEMPT_RT))
-			local_irq_restore(flags);
+		dec_active(c, flags);
 		if (llnode)
 			enque_to_free(c, llnode);
 	} while (cnt > (c->high_watermark + c->low_watermark) / 2);
-- 
GitLab


From 7468048237b8a99c03e1325b11373f9b29ef4139 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:39 -0700
Subject: [PATCH 0066/1806] bpf: Further refactor alloc_bulk().

In certain scenarios alloc_bulk() might be taking free objects mainly from
free_by_rcu_ttrace list. In such case get_memcg() and set_active_memcg() are
redundant, but they show up in perf profile. Split the loop and only set memcg
when allocating from slab. No performance difference in this patch alone, but
it helps in combination with further patches.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-7-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 052fc801fb9f4..0ee566a7719a9 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -196,8 +196,6 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 	void *obj;
 	int i;
 
-	memcg = get_memcg(c);
-	old_memcg = set_active_memcg(memcg);
 	for (i = 0; i < cnt; i++) {
 		/*
 		 * free_by_rcu_ttrace is only manipulated by irq work refill_work().
@@ -212,16 +210,24 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 		 * numa node and it is not a guarantee.
 		 */
 		obj = __llist_del_first(&c->free_by_rcu_ttrace);
-		if (!obj) {
-			/* Allocate, but don't deplete atomic reserves that typical
-			 * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
-			 * will allocate from the current numa node which is what we
-			 * want here.
-			 */
-			obj = __alloc(c, node, GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT);
-			if (!obj)
-				break;
-		}
+		if (!obj)
+			break;
+		add_obj_to_free_list(c, obj);
+	}
+	if (i >= cnt)
+		return;
+
+	memcg = get_memcg(c);
+	old_memcg = set_active_memcg(memcg);
+	for (; i < cnt; i++) {
+		/* Allocate, but don't deplete atomic reserves that typical
+		 * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
+		 * will allocate from the current numa node which is what we
+		 * want here.
+		 */
+		obj = __alloc(c, node, GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT);
+		if (!obj)
+			break;
 		add_obj_to_free_list(c, obj);
 	}
 	set_active_memcg(old_memcg);
-- 
GitLab


From d114dde245f9115b73756203b03a633a6fc1b36a Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:40 -0700
Subject: [PATCH 0067/1806] bpf: Change bpf_mem_cache draining process.

The next patch will introduce cross-cpu llist access and existing
irq_work_sync() + drain_mem_cache() + rcu_barrier_tasks_trace() mechanism will
not be enough, since irq_work_sync() + drain_mem_cache() on cpu A won't
guarantee that llist on cpu A are empty. The free_bulk() on cpu B might add
objects back to llist of cpu A. Add 'bool draining' flag.
The modified sequence looks like:
for_each_cpu:
  WRITE_ONCE(c->draining, true); // do_call_rcu_ttrace() won't be doing call_rcu() any more
  irq_work_sync(); // wait for irq_work callback (free_bulk) to finish
  drain_mem_cache(); // free all objects
rcu_barrier_tasks_trace(); // wait for RCU callbacks to execute

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-8-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 0ee566a7719a9..2615f296f052d 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -98,6 +98,7 @@ struct bpf_mem_cache {
 	int free_cnt;
 	int low_watermark, high_watermark, batch;
 	int percpu_size;
+	bool draining;
 
 	/* list of objects to be freed after RCU tasks trace GP */
 	struct llist_head free_by_rcu_ttrace;
@@ -301,6 +302,12 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 		 * from __free_rcu() and from drain_mem_cache().
 		 */
 		__llist_add(llnode, &c->waiting_for_gp_ttrace);
+
+	if (unlikely(READ_ONCE(c->draining))) {
+		__free_rcu(&c->rcu_ttrace);
+		return;
+	}
+
 	/* Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
 	 * If RCU Tasks Trace grace period implies RCU grace period, free
 	 * these elements directly, else use call_rcu() to wait for normal
@@ -544,15 +551,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 		rcu_in_progress = 0;
 		for_each_possible_cpu(cpu) {
 			c = per_cpu_ptr(ma->cache, cpu);
-			/*
-			 * refill_work may be unfinished for PREEMPT_RT kernel
-			 * in which irq work is invoked in a per-CPU RT thread.
-			 * It is also possible for kernel with
-			 * arch_irq_work_has_interrupt() being false and irq
-			 * work is invoked in timer interrupt. So waiting for
-			 * the completion of irq work to ease the handling of
-			 * concurrency.
-			 */
+			WRITE_ONCE(c->draining, true);
 			irq_work_sync(&c->refill_work);
 			drain_mem_cache(c);
 			rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
@@ -568,6 +567,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			cc = per_cpu_ptr(ma->caches, cpu);
 			for (i = 0; i < NUM_CACHES; i++) {
 				c = &cc->cache[i];
+				WRITE_ONCE(c->draining, true);
 				irq_work_sync(&c->refill_work);
 				drain_mem_cache(c);
 				rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
-- 
GitLab


From 822fb26bdb55932d0635f43cc418d2004b19e358 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:41 -0700
Subject: [PATCH 0068/1806] bpf: Add a hint to allocated objects.

To address OOM issue when one cpu is allocating and another cpu is freeing add
a target bpf_mem_cache hint to allocated objects and when local cpu free_llist
overflows free to that bpf_mem_cache. The hint addresses the OOM while
maintaining the same performance for common case when alloc/free are done on the
same cpu.

Note that do_call_rcu_ttrace() now has to check 'draining' flag in one more case,
since do_call_rcu_ttrace() is called not only for current cpu.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-9-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 50 +++++++++++++++++++++++++++----------------
 1 file changed, 31 insertions(+), 19 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 2615f296f052d..9986c6b7df4d3 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -99,6 +99,7 @@ struct bpf_mem_cache {
 	int low_watermark, high_watermark, batch;
 	int percpu_size;
 	bool draining;
+	struct bpf_mem_cache *tgt;
 
 	/* list of objects to be freed after RCU tasks trace GP */
 	struct llist_head free_by_rcu_ttrace;
@@ -199,18 +200,11 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 
 	for (i = 0; i < cnt; i++) {
 		/*
-		 * free_by_rcu_ttrace is only manipulated by irq work refill_work().
-		 * IRQ works on the same CPU are called sequentially, so it is
-		 * safe to use __llist_del_first() here. If alloc_bulk() is
-		 * invoked by the initial prefill, there will be no running
-		 * refill_work(), so __llist_del_first() is fine as well.
-		 *
-		 * In most cases, objects on free_by_rcu_ttrace are from the same CPU.
-		 * If some objects come from other CPUs, it doesn't incur any
-		 * harm because NUMA_NO_NODE means the preference for current
-		 * numa node and it is not a guarantee.
+		 * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is
+		 * done only by one CPU == current CPU. Other CPUs might
+		 * llist_add() and llist_del_all() in parallel.
 		 */
-		obj = __llist_del_first(&c->free_by_rcu_ttrace);
+		obj = llist_del_first(&c->free_by_rcu_ttrace);
 		if (!obj)
 			break;
 		add_obj_to_free_list(c, obj);
@@ -284,18 +278,23 @@ static void enque_to_free(struct bpf_mem_cache *c, void *obj)
 	/* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work.
 	 * Nothing races to add to free_by_rcu_ttrace list.
 	 */
-	__llist_add(llnode, &c->free_by_rcu_ttrace);
+	llist_add(llnode, &c->free_by_rcu_ttrace);
 }
 
 static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 {
 	struct llist_node *llnode, *t;
 
-	if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1))
+	if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) {
+		if (unlikely(READ_ONCE(c->draining))) {
+			llnode = llist_del_all(&c->free_by_rcu_ttrace);
+			free_all(llnode, !!c->percpu_size);
+		}
 		return;
+	}
 
 	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
-	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu_ttrace))
+	llist_for_each_safe(llnode, t, llist_del_all(&c->free_by_rcu_ttrace))
 		/* There is no concurrent __llist_add(waiting_for_gp_ttrace) access.
 		 * It doesn't race with llist_del_all either.
 		 * But there could be two concurrent llist_del_all(waiting_for_gp_ttrace):
@@ -318,10 +317,13 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 
 static void free_bulk(struct bpf_mem_cache *c)
 {
+	struct bpf_mem_cache *tgt = c->tgt;
 	struct llist_node *llnode, *t;
 	unsigned long flags;
 	int cnt;
 
+	WARN_ON_ONCE(tgt->unit_size != c->unit_size);
+
 	do {
 		inc_active(c, &flags);
 		llnode = __llist_del_first(&c->free_llist);
@@ -331,13 +333,13 @@ static void free_bulk(struct bpf_mem_cache *c)
 			cnt = 0;
 		dec_active(c, flags);
 		if (llnode)
-			enque_to_free(c, llnode);
+			enque_to_free(tgt, llnode);
 	} while (cnt > (c->high_watermark + c->low_watermark) / 2);
 
 	/* and drain free_llist_extra */
 	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
-		enque_to_free(c, llnode);
-	do_call_rcu_ttrace(c);
+		enque_to_free(tgt, llnode);
+	do_call_rcu_ttrace(tgt);
 }
 
 static void bpf_mem_refill(struct irq_work *work)
@@ -436,6 +438,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->unit_size = unit_size;
 			c->objcg = objcg;
 			c->percpu_size = percpu_size;
+			c->tgt = c;
 			prefill_mem_cache(c, cpu);
 		}
 		ma->cache = pc;
@@ -458,6 +461,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c = &cc->cache[i];
 			c->unit_size = sizes[i];
 			c->objcg = objcg;
+			c->tgt = c;
 			prefill_mem_cache(c, cpu);
 		}
 	}
@@ -476,7 +480,7 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 	 * Except for waiting_for_gp_ttrace list, there are no concurrent operations
 	 * on these lists, so it is safe to use __llist_del_all().
 	 */
-	free_all(__llist_del_all(&c->free_by_rcu_ttrace), percpu);
+	free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu);
 	free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu);
 	free_all(__llist_del_all(&c->free_llist), percpu);
 	free_all(__llist_del_all(&c->free_llist_extra), percpu);
@@ -601,8 +605,10 @@ static void notrace *unit_alloc(struct bpf_mem_cache *c)
 	local_irq_save(flags);
 	if (local_inc_return(&c->active) == 1) {
 		llnode = __llist_del_first(&c->free_llist);
-		if (llnode)
+		if (llnode) {
 			cnt = --c->free_cnt;
+			*(struct bpf_mem_cache **)llnode = c;
+		}
 	}
 	local_dec(&c->active);
 	local_irq_restore(flags);
@@ -626,6 +632,12 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
 
 	BUILD_BUG_ON(LLIST_NODE_SZ > 8);
 
+	/*
+	 * Remember bpf_mem_cache that allocated this object.
+	 * The hint is not accurate.
+	 */
+	c->tgt = *(struct bpf_mem_cache **)llnode;
+
 	local_irq_save(flags);
 	if (local_inc_return(&c->active) == 1) {
 		__llist_add(llnode, &c->free_llist);
-- 
GitLab


From 04fabf00b4d3aff5d010ecb617001814e409e24a Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:42 -0700
Subject: [PATCH 0069/1806] bpf: Allow reuse from waiting_for_gp_ttrace list.

alloc_bulk() can reuse elements from free_by_rcu_ttrace.
Let it reuse from waiting_for_gp_ttrace as well to avoid unnecessary kmalloc().

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230706033447.54696-10-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 9986c6b7df4d3..e5a87f6cf2ccd 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -212,6 +212,15 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 	if (i >= cnt)
 		return;
 
+	for (; i < cnt; i++) {
+		obj = llist_del_first(&c->waiting_for_gp_ttrace);
+		if (!obj)
+			break;
+		add_obj_to_free_list(c, obj);
+	}
+	if (i >= cnt)
+		return;
+
 	memcg = get_memcg(c);
 	old_memcg = set_active_memcg(memcg);
 	for (; i < cnt; i++) {
@@ -295,12 +304,7 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 
 	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
 	llist_for_each_safe(llnode, t, llist_del_all(&c->free_by_rcu_ttrace))
-		/* There is no concurrent __llist_add(waiting_for_gp_ttrace) access.
-		 * It doesn't race with llist_del_all either.
-		 * But there could be two concurrent llist_del_all(waiting_for_gp_ttrace):
-		 * from __free_rcu() and from drain_mem_cache().
-		 */
-		__llist_add(llnode, &c->waiting_for_gp_ttrace);
+		llist_add(llnode, &c->waiting_for_gp_ttrace);
 
 	if (unlikely(READ_ONCE(c->draining))) {
 		__free_rcu(&c->rcu_ttrace);
-- 
GitLab


From 43a89baecfe200cb4530f42b9fcf904925d6d14a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 5 Jul 2023 20:34:43 -0700
Subject: [PATCH 0070/1806] rcu: Export rcu_request_urgent_qs_task()

If a CPU is executing a long series of non-sleeping system calls,
RCU grace periods can be delayed for on the order of a couple hundred
milliseconds.  This is normally not a problem, but if each system call
does a call_rcu(), those callbacks can stack up.  RCU will eventually
notice this callback storm, but use of rcu_request_urgent_qs_task()
allows the code invoking call_rcu() to give RCU a heads up.

This function is not for general use, not yet, anyway.

Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230706033447.54696-11-alexei.starovoitov@gmail.com
---
 include/linux/rcutiny.h | 2 ++
 include/linux/rcutree.h | 1 +
 kernel/rcu/rcu.h        | 2 --
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 7f17acf29dda7..7b949292908a9 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -138,6 +138,8 @@ static inline int rcu_needs_cpu(void)
 	return 0;
 }
 
+static inline void rcu_request_urgent_qs_task(struct task_struct *t) { }
+
 /*
  * Take advantage of the fact that there is only one CPU, which
  * allows us to ignore virtualization-based context switches.
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 56bccb5a8fdea..126f6b418f6af 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -21,6 +21,7 @@ void rcu_softirq_qs(void);
 void rcu_note_context_switch(bool preempt);
 int rcu_needs_cpu(void);
 void rcu_cpu_stall_reset(void);
+void rcu_request_urgent_qs_task(struct task_struct *t);
 
 /*
  * Note a virtualization-based context switch.  This is simply a
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 98c1544cf572b..f95cfb5bf2eeb 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -493,7 +493,6 @@ static inline void rcu_expedite_gp(void) { }
 static inline void rcu_unexpedite_gp(void) { }
 static inline void rcu_async_hurry(void) { }
 static inline void rcu_async_relax(void) { }
-static inline void rcu_request_urgent_qs_task(struct task_struct *t) { }
 #else /* #ifdef CONFIG_TINY_RCU */
 bool rcu_gp_is_normal(void);     /* Internal RCU use. */
 bool rcu_gp_is_expedited(void);  /* Internal RCU use. */
@@ -508,7 +507,6 @@ void show_rcu_tasks_gp_kthreads(void);
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
 static inline void show_rcu_tasks_gp_kthreads(void) {}
 #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
-void rcu_request_urgent_qs_task(struct task_struct *t);
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
 #define RCU_SCHEDULER_INACTIVE	0
-- 
GitLab


From f76faa65c9717304b5abb9d77a19b3c09d4086f3 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:44 -0700
Subject: [PATCH 0071/1806] selftests/bpf: Improve test coverage of
 bpf_mem_alloc.

bpf_obj_new() calls bpf_mem_alloc(), but doing alloc/free of 8 elements
is not triggering watermark conditions in bpf_mem_alloc.
Increase to 200 elements to make sure alloc_bulk/free_bulk is exercised.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-12-alexei.starovoitov@gmail.com
---
 tools/testing/selftests/bpf/progs/linked_list.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c
index 57440a554304d..84d1777a9e6c9 100644
--- a/tools/testing/selftests/bpf/progs/linked_list.c
+++ b/tools/testing/selftests/bpf/progs/linked_list.c
@@ -96,7 +96,7 @@ static __always_inline
 int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map)
 {
 	struct bpf_list_node *n;
-	struct foo *f[8], *pf;
+	struct foo *f[200], *pf;
 	int i;
 
 	/* Loop following this check adds nodes 2-at-a-time in order to
-- 
GitLab


From 5af6807bdb10d1af9d412d7d6c177ba8440adffb Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:45 -0700
Subject: [PATCH 0072/1806] bpf: Introduce bpf_mem_free_rcu() similar to
 kfree_rcu().

Introduce bpf_mem_[cache_]free_rcu() similar to kfree_rcu().
Unlike bpf_mem_[cache_]free() that links objects for immediate reuse into
per-cpu free list the _rcu() flavor waits for RCU grace period and then moves
objects into free_by_rcu_ttrace list where they are waiting for RCU
task trace grace period to be freed into slab.

The life cycle of objects:
alloc: dequeue free_llist
free: enqeueu free_llist
free_rcu: enqueue free_by_rcu -> waiting_for_gp
free_llist above high watermark -> free_by_rcu_ttrace
after RCU GP waiting_for_gp -> free_by_rcu_ttrace
free_by_rcu_ttrace -> waiting_for_gp_ttrace -> slab

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-13-alexei.starovoitov@gmail.com
---
 include/linux/bpf_mem_alloc.h |   2 +
 kernel/bpf/memalloc.c         | 129 +++++++++++++++++++++++++++++++++-
 2 files changed, 128 insertions(+), 3 deletions(-)

diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index 3929be5743f49..d644bbb298af4 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -27,10 +27,12 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
 /* kmalloc/kfree equivalent: */
 void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size);
 void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr);
+void bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr);
 
 /* kmem_cache_alloc/free equivalent: */
 void *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma);
 void bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr);
+void bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr);
 void bpf_mem_cache_raw_free(void *ptr);
 void *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags);
 
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index e5a87f6cf2ccd..17ef2e9b278a3 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -101,6 +101,15 @@ struct bpf_mem_cache {
 	bool draining;
 	struct bpf_mem_cache *tgt;
 
+	/* list of objects to be freed after RCU GP */
+	struct llist_head free_by_rcu;
+	struct llist_node *free_by_rcu_tail;
+	struct llist_head waiting_for_gp;
+	struct llist_node *waiting_for_gp_tail;
+	struct rcu_head rcu;
+	atomic_t call_rcu_in_progress;
+	struct llist_head free_llist_extra_rcu;
+
 	/* list of objects to be freed after RCU tasks trace GP */
 	struct llist_head free_by_rcu_ttrace;
 	struct llist_head waiting_for_gp_ttrace;
@@ -346,6 +355,69 @@ static void free_bulk(struct bpf_mem_cache *c)
 	do_call_rcu_ttrace(tgt);
 }
 
+static void __free_by_rcu(struct rcu_head *head)
+{
+	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
+	struct bpf_mem_cache *tgt = c->tgt;
+	struct llist_node *llnode;
+
+	llnode = llist_del_all(&c->waiting_for_gp);
+	if (!llnode)
+		goto out;
+
+	llist_add_batch(llnode, c->waiting_for_gp_tail, &tgt->free_by_rcu_ttrace);
+
+	/* Objects went through regular RCU GP. Send them to RCU tasks trace */
+	do_call_rcu_ttrace(tgt);
+out:
+	atomic_set(&c->call_rcu_in_progress, 0);
+}
+
+static void check_free_by_rcu(struct bpf_mem_cache *c)
+{
+	struct llist_node *llnode, *t;
+	unsigned long flags;
+
+	/* drain free_llist_extra_rcu */
+	if (unlikely(!llist_empty(&c->free_llist_extra_rcu))) {
+		inc_active(c, &flags);
+		llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra_rcu))
+			if (__llist_add(llnode, &c->free_by_rcu))
+				c->free_by_rcu_tail = llnode;
+		dec_active(c, flags);
+	}
+
+	if (llist_empty(&c->free_by_rcu))
+		return;
+
+	if (atomic_xchg(&c->call_rcu_in_progress, 1)) {
+		/*
+		 * Instead of kmalloc-ing new rcu_head and triggering 10k
+		 * call_rcu() to hit rcutree.qhimark and force RCU to notice
+		 * the overload just ask RCU to hurry up. There could be many
+		 * objects in free_by_rcu list.
+		 * This hint reduces memory consumption for an artificial
+		 * benchmark from 2 Gbyte to 150 Mbyte.
+		 */
+		rcu_request_urgent_qs_task(current);
+		return;
+	}
+
+	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
+
+	inc_active(c, &flags);
+	WRITE_ONCE(c->waiting_for_gp.first, __llist_del_all(&c->free_by_rcu));
+	c->waiting_for_gp_tail = c->free_by_rcu_tail;
+	dec_active(c, flags);
+
+	if (unlikely(READ_ONCE(c->draining))) {
+		free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
+		atomic_set(&c->call_rcu_in_progress, 0);
+	} else {
+		call_rcu_hurry(&c->rcu, __free_by_rcu);
+	}
+}
+
 static void bpf_mem_refill(struct irq_work *work)
 {
 	struct bpf_mem_cache *c = container_of(work, struct bpf_mem_cache, refill_work);
@@ -360,6 +432,8 @@ static void bpf_mem_refill(struct irq_work *work)
 		alloc_bulk(c, c->batch, NUMA_NO_NODE);
 	else if (cnt > c->high_watermark)
 		free_bulk(c);
+
+	check_free_by_rcu(c);
 }
 
 static void notrace irq_work_raise(struct bpf_mem_cache *c)
@@ -488,6 +562,9 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 	free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu);
 	free_all(__llist_del_all(&c->free_llist), percpu);
 	free_all(__llist_del_all(&c->free_llist_extra), percpu);
+	free_all(__llist_del_all(&c->free_by_rcu), percpu);
+	free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu);
+	free_all(llist_del_all(&c->waiting_for_gp), percpu);
 }
 
 static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
@@ -500,8 +577,8 @@ static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
 
 static void free_mem_alloc(struct bpf_mem_alloc *ma)
 {
-	/* waiting_for_gp_ttrace lists was drained, but __free_rcu might
-	 * still execute. Wait for it now before we freeing percpu caches.
+	/* waiting_for_gp[_ttrace] lists were drained, but RCU callbacks
+	 * might still execute. Wait for them.
 	 *
 	 * rcu_barrier_tasks_trace() doesn't imply synchronize_rcu_tasks_trace(),
 	 * but rcu_barrier_tasks_trace() and rcu_barrier() below are only used
@@ -510,7 +587,8 @@ static void free_mem_alloc(struct bpf_mem_alloc *ma)
 	 * rcu_trace_implies_rcu_gp(), it will be OK to skip rcu_barrier() by
 	 * using rcu_trace_implies_rcu_gp() as well.
 	 */
-	rcu_barrier_tasks_trace();
+	rcu_barrier(); /* wait for __free_by_rcu */
+	rcu_barrier_tasks_trace(); /* wait for __free_rcu */
 	if (!rcu_trace_implies_rcu_gp())
 		rcu_barrier();
 	free_mem_alloc_no_barrier(ma);
@@ -563,6 +641,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			irq_work_sync(&c->refill_work);
 			drain_mem_cache(c);
 			rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
+			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 		}
 		/* objcg is the same across cpus */
 		if (c->objcg)
@@ -579,6 +658,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 				irq_work_sync(&c->refill_work);
 				drain_mem_cache(c);
 				rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
+				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 			}
 		}
 		if (c->objcg)
@@ -663,6 +743,27 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
 		irq_work_raise(c);
 }
 
+static void notrace unit_free_rcu(struct bpf_mem_cache *c, void *ptr)
+{
+	struct llist_node *llnode = ptr - LLIST_NODE_SZ;
+	unsigned long flags;
+
+	c->tgt = *(struct bpf_mem_cache **)llnode;
+
+	local_irq_save(flags);
+	if (local_inc_return(&c->active) == 1) {
+		if (__llist_add(llnode, &c->free_by_rcu))
+			c->free_by_rcu_tail = llnode;
+	} else {
+		llist_add(llnode, &c->free_llist_extra_rcu);
+	}
+	local_dec(&c->active);
+	local_irq_restore(flags);
+
+	if (!atomic_read(&c->call_rcu_in_progress))
+		irq_work_raise(c);
+}
+
 /* Called from BPF program or from sys_bpf syscall.
  * In both cases migration is disabled.
  */
@@ -696,6 +797,20 @@ void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
 	unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr);
 }
 
+void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr)
+{
+	int idx;
+
+	if (!ptr)
+		return;
+
+	idx = bpf_mem_cache_idx(ksize(ptr - LLIST_NODE_SZ));
+	if (idx < 0)
+		return;
+
+	unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr);
+}
+
 void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma)
 {
 	void *ret;
@@ -712,6 +827,14 @@ void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr)
 	unit_free(this_cpu_ptr(ma->cache), ptr);
 }
 
+void notrace bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr)
+{
+	if (!ptr)
+		return;
+
+	unit_free_rcu(this_cpu_ptr(ma->cache), ptr);
+}
+
 /* Directly does a kfree() without putting 'ptr' back to the free_llist
  * for reuse and without waiting for a rcu_tasks_trace gp.
  * The caller must first go through the rcu_tasks_trace gp for 'ptr'
-- 
GitLab


From 8e07bb9ebcd9b9ddf58337253ee5522d86b99370 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:46 -0700
Subject: [PATCH 0073/1806] bpf: Convert bpf_cpumask to bpf_mem_cache_free_rcu.

Convert bpf_cpumask to bpf_mem_cache_free_rcu.
Note that migrate_disable() in bpf_cpumask_release() is still necessary, since
bpf_cpumask_release() is a dtor. bpf_obj_free_fields() can be converted to do
migrate_disable() there in a follow up.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-14-alexei.starovoitov@gmail.com
---
 kernel/bpf/cpumask.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index 938a60ff4295f..6983af8e093c4 100644
--- a/kernel/bpf/cpumask.c
+++ b/kernel/bpf/cpumask.c
@@ -9,7 +9,6 @@
 /**
  * struct bpf_cpumask - refcounted BPF cpumask wrapper structure
  * @cpumask:	The actual cpumask embedded in the struct.
- * @rcu:	The RCU head used to free the cpumask with RCU safety.
  * @usage:	Object reference counter. When the refcount goes to 0, the
  *		memory is released back to the BPF allocator, which provides
  *		RCU safety.
@@ -25,7 +24,6 @@
  */
 struct bpf_cpumask {
 	cpumask_t cpumask;
-	struct rcu_head rcu;
 	refcount_t usage;
 };
 
@@ -82,16 +80,6 @@ __bpf_kfunc struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask)
 	return cpumask;
 }
 
-static void cpumask_free_cb(struct rcu_head *head)
-{
-	struct bpf_cpumask *cpumask;
-
-	cpumask = container_of(head, struct bpf_cpumask, rcu);
-	migrate_disable();
-	bpf_mem_cache_free(&bpf_cpumask_ma, cpumask);
-	migrate_enable();
-}
-
 /**
  * bpf_cpumask_release() - Release a previously acquired BPF cpumask.
  * @cpumask: The cpumask being released.
@@ -102,8 +90,12 @@ static void cpumask_free_cb(struct rcu_head *head)
  */
 __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask)
 {
-	if (refcount_dec_and_test(&cpumask->usage))
-		call_rcu(&cpumask->rcu, cpumask_free_cb);
+	if (!refcount_dec_and_test(&cpumask->usage))
+		return;
+
+	migrate_disable();
+	bpf_mem_cache_free_rcu(&bpf_cpumask_ma, cpumask);
+	migrate_enable();
 }
 
 /**
-- 
GitLab


From 4ed8b5bcfada6687baa478bf8febe891d9107118 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Wed, 5 Jul 2023 20:34:47 -0700
Subject: [PATCH 0074/1806] bpf: Add object leak check.

The object leak check is cheap. Do it unconditionally to spot difficult races
in bpf_mem_alloc.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230706033447.54696-15-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 17ef2e9b278a3..51d6389e5152e 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -567,8 +567,43 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 	free_all(llist_del_all(&c->waiting_for_gp), percpu);
 }
 
+static void check_mem_cache(struct bpf_mem_cache *c)
+{
+	WARN_ON_ONCE(!llist_empty(&c->free_by_rcu_ttrace));
+	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
+	WARN_ON_ONCE(!llist_empty(&c->free_llist));
+	WARN_ON_ONCE(!llist_empty(&c->free_llist_extra));
+	WARN_ON_ONCE(!llist_empty(&c->free_by_rcu));
+	WARN_ON_ONCE(!llist_empty(&c->free_llist_extra_rcu));
+	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
+}
+
+static void check_leaked_objs(struct bpf_mem_alloc *ma)
+{
+	struct bpf_mem_caches *cc;
+	struct bpf_mem_cache *c;
+	int cpu, i;
+
+	if (ma->cache) {
+		for_each_possible_cpu(cpu) {
+			c = per_cpu_ptr(ma->cache, cpu);
+			check_mem_cache(c);
+		}
+	}
+	if (ma->caches) {
+		for_each_possible_cpu(cpu) {
+			cc = per_cpu_ptr(ma->caches, cpu);
+			for (i = 0; i < NUM_CACHES; i++) {
+				c = &cc->cache[i];
+				check_mem_cache(c);
+			}
+		}
+	}
+}
+
 static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
 {
+	check_leaked_objs(ma);
 	free_percpu(ma->cache);
 	free_percpu(ma->caches);
 	ma->cache = NULL;
-- 
GitLab


From 9f4a7c930284bf2b5b84d3636a8e88857149328f Mon Sep 17 00:00:00 2001
From: Jian Wen <wenjianhn@gmail.com>
Date: Tue, 11 Jul 2023 11:24:05 +0800
Subject: [PATCH 0075/1806] tcp: add a scheduling point in
 established_get_first()

Kubernetes[1] is going to stick with /proc/net/tcp for a while.

This commit reduces the scheduling latency introduced by
established_get_first(), similar to commit acffb584cda7 ("net: diag:
add a scheduling point in inet_diag_dump_icsk()").

In our environment, the scheduling latency affects the performance of
latency-sensitive services like Redis.

Changes in V2 :
 - call cond_resched() before checking if a bucket is empty as
   suggested by Eric Dumazet
 - removed the delay of synchronize_net() from the commit message

[1] https://github.com/google/cadvisor/blob/v0.47.2/container/libcontainer/handler.go#L130

Signed-off-by: Jian Wen <wenjian1@xiaomi.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230711032405.3253025-1-wenjian1@xiaomi.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_ipv4.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fd365de4d5ffc..cecd5a135e649 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -57,6 +57,7 @@
 #include <linux/init.h>
 #include <linux/times.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 
 #include <net/net_namespace.h>
 #include <net/icmp.h>
@@ -2446,6 +2447,8 @@ static void *established_get_first(struct seq_file *seq)
 		struct hlist_nulls_node *node;
 		spinlock_t *lock = inet_ehash_lockp(hinfo, st->bucket);
 
+		cond_resched();
+
 		/* Lockless fast path for the common case of empty buckets */
 		if (empty_bucket(hinfo, st))
 			continue;
-- 
GitLab


From 0a5550b1165cd60ad6972791eda4a3eb7e347280 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Wed, 12 Jul 2023 16:23:22 +0100
Subject: [PATCH 0076/1806] bpftool: Use "fallthrough;" keyword instead of
 comments

After using "__fallthrough;" in a switch/case block in bpftool's
btf_dumper.c [0], and then turning it into a comment [1] to prevent a
merge conflict in linux-next when the keyword was changed into just
"fallthrough;" [2], we can now drop the comment and use the new keyword,
no underscores.

Also update the other occurrence of "/* fallthrough */" in bpftool.

[0] commit 9fd496848b1c ("bpftool: Support inline annotations when dumping the CFG of a program")
[1] commit 4b7ef71ac977 ("bpftool: Replace "__fallthrough" by a comment to address merge conflict")
[2] commit f7a858bffcdd ("tools: Rename __fallthrough to fallthrough")

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230712152322.81758-1-quentin@isovalent.com
---
 tools/bpf/bpftool/btf_dumper.c | 2 +-
 tools/bpf/bpftool/feature.c    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 294de231db99c..1b7f697146041 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -835,7 +835,7 @@ static void dotlabel_puts(const char *s)
 		case '|':
 		case ' ':
 			putchar('\\');
-			/* fallthrough */
+			fallthrough;
 		default:
 			putchar(*s);
 		}
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index 0675d6a464138..edda4fc2c4d03 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -757,7 +757,7 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type,
 		case BPF_FUNC_probe_write_user:
 			if (!full_mode)
 				continue;
-			/* fallthrough */
+			fallthrough;
 		default:
 			probe_res |= probe_helper_for_progtype(prog_type, supported_type,
 						  define_prefix, id, prog_type_str,
-- 
GitLab


From f3b8bec7d29e1f330287b4df9f58b01e8b8ca010 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 11 Jul 2023 18:43:54 +0200
Subject: [PATCH 0077/1806] mlxsw: reg: Add Policy-Engine Port Range Register

Add the Policy-Engine Port Range Register that is used for configuring
port range identification.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/d1a1f53d758f7452cf5abfe006b23496076ec3e6.1689092769.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 73 +++++++++++++++++++++++
 1 file changed, 73 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 8165bf31a99ae..df63f39233724 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2799,6 +2799,78 @@ static inline void mlxsw_reg_ptar_unpack(char *payload, char *tcam_region_info)
 	mlxsw_reg_ptar_tcam_region_info_memcpy_from(payload, tcam_region_info);
 }
 
+/* PPRR - Policy-Engine Port Range Register
+ * ----------------------------------------
+ * This register is used for configuring port range identification.
+ */
+#define MLXSW_REG_PPRR_ID 0x3008
+#define MLXSW_REG_PPRR_LEN 0x14
+
+MLXSW_REG_DEFINE(pprr, MLXSW_REG_PPRR_ID, MLXSW_REG_PPRR_LEN);
+
+/* reg_pprr_ipv4
+ * Apply port range register to IPv4 packets.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pprr, ipv4, 0x00, 31, 1);
+
+/* reg_pprr_ipv6
+ * Apply port range register to IPv6 packets.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pprr, ipv6, 0x00, 30, 1);
+
+/* reg_pprr_src
+ * Apply port range register to source L4 ports.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pprr, src, 0x00, 29, 1);
+
+/* reg_pprr_dst
+ * Apply port range register to destination L4 ports.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pprr, dst, 0x00, 28, 1);
+
+/* reg_pprr_tcp
+ * Apply port range register to TCP packets.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pprr, tcp, 0x00, 27, 1);
+
+/* reg_pprr_udp
+ * Apply port range register to UDP packets.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pprr, udp, 0x00, 26, 1);
+
+/* reg_pprr_register_index
+ * Index of Port Range Register being accessed.
+ * Range is 0..cap_max_acl_l4_port_range-1.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pprr, register_index, 0x00, 0, 8);
+
+/* reg_prrr_port_range_min
+ * Minimum port range for comparison.
+ * Match is defined as:
+ * port_range_min <= packet_port <= port_range_max.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pprr, port_range_min, 0x04, 16, 16);
+
+/* reg_prrr_port_range_max
+ * Maximum port range for comparison.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pprr, port_range_max, 0x04, 0, 16);
+
+static inline void mlxsw_reg_pprr_pack(char *payload, u8 register_index)
+{
+	MLXSW_REG_ZERO(pprr, payload);
+	mlxsw_reg_pprr_register_index_set(payload, register_index);
+}
+
 /* PPBS - Policy-Engine Policy Based Switching Register
  * ----------------------------------------------------
  * This register retrieves and sets Policy Based Switching Table entries.
@@ -12819,6 +12891,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(pacl),
 	MLXSW_REG(pagt),
 	MLXSW_REG(ptar),
+	MLXSW_REG(pprr),
 	MLXSW_REG(ppbs),
 	MLXSW_REG(prcr),
 	MLXSW_REG(pefa),
-- 
GitLab


From 9f53a7602ac6970cadeeead0e4352818ad000dcc Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 11 Jul 2023 18:43:55 +0200
Subject: [PATCH 0078/1806] mlxsw: resource: Add resource identifier for port
 range registers

Add a resource identifier for maximum number of layer 4 port range
register so that it could be later used to query the information from
firmware.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/59a8fec353d5ad9fbfb7612e4a7ff61eaedad445.1689092769.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/resources.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index 19ae0d1c74a8d..89dd2777ec4da 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -39,6 +39,7 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_ACL_FLEX_KEYS,
 	MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE,
 	MLXSW_RES_ID_ACL_ACTIONS_PER_SET,
+	MLXSW_RES_ID_ACL_MAX_L4_PORT_RANGE,
 	MLXSW_RES_ID_ACL_MAX_ERPT_BANKS,
 	MLXSW_RES_ID_ACL_MAX_ERPT_BANK_SIZE,
 	MLXSW_RES_ID_ACL_MAX_LARGE_KEY_ID,
@@ -99,6 +100,7 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_ACL_FLEX_KEYS] = 0x2910,
 	[MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE] = 0x2911,
 	[MLXSW_RES_ID_ACL_ACTIONS_PER_SET] = 0x2912,
+	[MLXSW_RES_ID_ACL_MAX_L4_PORT_RANGE] = 0x2920,
 	[MLXSW_RES_ID_ACL_MAX_ERPT_BANKS] = 0x2940,
 	[MLXSW_RES_ID_ACL_MAX_ERPT_BANK_SIZE] = 0x2941,
 	[MLXSW_RES_ID_ACL_MAX_LARGE_KEY_ID] = 0x2942,
-- 
GitLab


From b3eb04be729982ae7e311afcc9c031eca4718a46 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 11 Jul 2023 18:43:56 +0200
Subject: [PATCH 0079/1806] mlxsw: spectrum_port_range: Add port range core

The Spectrum ASICs have a fixed number of port range registers, each of
which maintains the following parameters:

* Minimum and maximum port.
* Apply port range for source port, destination port or both.
* Apply port range for TCP, UDP or both.
* Apply port range for IPv4, IPv6 or both.

Implement a port range core which takes care of the allocation and
configuration of these registers and exposes an API that allows
in-driver consumers (e.g., the ACL code) to request matching on a range
of either source or destination port.

These registers are going to be used for port range matching in the
flower classifier that already matches on EtherType being IPv4 / IPv6 and
IP protocol being TCP / UDP. As such, there is no need to limit these
registers to a specific EtherType or IP protocol, which will increase
the likelihood of a register being shared by multiple flower filters.

It is unlikely that a filter will match on the same range of both source
and destination ports, which is why each register is only configured to
match on either source or destination port. If a filter requires
matching on a range of both source and destination ports, it will
utilize two port range registers and match on the output of both.

For efficient lookup and traversal, use XArray to store the allocated
port range registers. The XArray uses RCU and an internal spinlock to
synchronise access, so there is no need for a dedicate lock.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/674f00539a0072d455847663b5feb504db51a259.1689092769.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile  |   2 +-
 .../net/ethernet/mellanox/mlxsw/spectrum.c    |   9 +
 .../net/ethernet/mellanox/mlxsw/spectrum.h    |  15 ++
 .../mellanox/mlxsw/spectrum_port_range.c      | 181 ++++++++++++++++++
 4 files changed, 206 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_port_range.c

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 3ca9fce759eac..71cad6bb6e626 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -29,7 +29,7 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_nve.o spectrum_nve_vxlan.o \
 				   spectrum_dpipe.o spectrum_trap.o \
 				   spectrum_ethtool.o spectrum_policer.o \
-				   spectrum_pgt.o
+				   spectrum_pgt.o spectrum_port_range.o
 mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
 mlxsw_spectrum-$(CONFIG_PTP_1588_CLOCK)		+= spectrum_ptp.o
 obj-$(CONFIG_MLXSW_MINIMAL)	+= mlxsw_minimal.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 25a01dafde1ba..c0edcc91f178c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3188,6 +3188,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_nve_init;
 	}
 
+	err = mlxsw_sp_port_range_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize port ranges\n");
+		goto err_port_range_init;
+	}
+
 	err = mlxsw_sp_acl_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize ACL\n");
@@ -3280,6 +3286,8 @@ err_ptp_clock_init:
 err_router_init:
 	mlxsw_sp_acl_fini(mlxsw_sp);
 err_acl_init:
+	mlxsw_sp_port_range_fini(mlxsw_sp);
+err_port_range_init:
 	mlxsw_sp_nve_fini(mlxsw_sp);
 err_nve_init:
 	mlxsw_sp_ipv6_addr_ht_fini(mlxsw_sp);
@@ -3462,6 +3470,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	}
 	mlxsw_sp_router_fini(mlxsw_sp);
 	mlxsw_sp_acl_fini(mlxsw_sp);
+	mlxsw_sp_port_range_fini(mlxsw_sp);
 	mlxsw_sp_nve_fini(mlxsw_sp);
 	mlxsw_sp_ipv6_addr_ht_fini(mlxsw_sp);
 	mlxsw_sp_afa_fini(mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 231e364cbb7c3..fe6c6e02a484f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -175,6 +175,7 @@ struct mlxsw_sp {
 	struct mlxsw_sp_acl *acl;
 	struct mlxsw_sp_fid_core *fid_core;
 	struct mlxsw_sp_policer_core *policer_core;
+	struct mlxsw_sp_port_range_core *pr_core;
 	struct mlxsw_sp_kvdl *kvdl;
 	struct mlxsw_sp_nve *nve;
 	struct notifier_block netdevice_nb;
@@ -1484,4 +1485,18 @@ int mlxsw_sp_pgt_entry_port_set(struct mlxsw_sp *mlxsw_sp, u16 mid,
 int mlxsw_sp_pgt_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_pgt_fini(struct mlxsw_sp *mlxsw_sp);
 
+/* spectrum_port_range.c */
+struct mlxsw_sp_port_range {
+	u16 min;
+	u16 max;
+	u8 source:1;	/* Source or destination */
+};
+
+int mlxsw_sp_port_range_reg_get(struct mlxsw_sp *mlxsw_sp,
+				const struct mlxsw_sp_port_range *range,
+				struct netlink_ext_ack *extack,
+				u8 *p_prr_index);
+void mlxsw_sp_port_range_reg_put(struct mlxsw_sp *mlxsw_sp, u8 prr_index);
+int mlxsw_sp_port_range_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_port_range_fini(struct mlxsw_sp *mlxsw_sp);
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_port_range.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_port_range.c
new file mode 100644
index 0000000000000..a12a62632721c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_port_range.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include <linux/bits.h>
+#include <linux/netlink.h>
+#include <linux/refcount.h>
+#include <linux/xarray.h>
+
+#include "spectrum.h"
+
+struct mlxsw_sp_port_range_reg {
+	struct mlxsw_sp_port_range range;
+	refcount_t refcount;
+	u32 index;
+};
+
+struct mlxsw_sp_port_range_core {
+	struct xarray prr_xa;
+	struct xa_limit prr_ids;
+};
+
+static int
+mlxsw_sp_port_range_reg_configure(struct mlxsw_sp *mlxsw_sp,
+				  const struct mlxsw_sp_port_range_reg *prr)
+{
+	char pprr_pl[MLXSW_REG_PPRR_LEN];
+
+	/* We do not care if packet is IPv4/IPv6 and TCP/UDP, so set all four
+	 * fields.
+	 */
+	mlxsw_reg_pprr_pack(pprr_pl, prr->index);
+	mlxsw_reg_pprr_ipv4_set(pprr_pl, true);
+	mlxsw_reg_pprr_ipv6_set(pprr_pl, true);
+	mlxsw_reg_pprr_src_set(pprr_pl, prr->range.source);
+	mlxsw_reg_pprr_dst_set(pprr_pl, !prr->range.source);
+	mlxsw_reg_pprr_tcp_set(pprr_pl, true);
+	mlxsw_reg_pprr_udp_set(pprr_pl, true);
+	mlxsw_reg_pprr_port_range_min_set(pprr_pl, prr->range.min);
+	mlxsw_reg_pprr_port_range_max_set(pprr_pl, prr->range.max);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pprr), pprr_pl);
+}
+
+static struct mlxsw_sp_port_range_reg *
+mlxsw_sp_port_range_reg_create(struct mlxsw_sp *mlxsw_sp,
+			       const struct mlxsw_sp_port_range *range,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_port_range_core *pr_core = mlxsw_sp->pr_core;
+	struct mlxsw_sp_port_range_reg *prr;
+	int err;
+
+	prr = kzalloc(sizeof(*prr), GFP_KERNEL);
+	if (!prr)
+		return ERR_PTR(-ENOMEM);
+
+	prr->range = *range;
+	refcount_set(&prr->refcount, 1);
+
+	err = xa_alloc(&pr_core->prr_xa, &prr->index, prr, pr_core->prr_ids,
+		       GFP_KERNEL);
+	if (err) {
+		if (err == -EBUSY)
+			NL_SET_ERR_MSG_MOD(extack, "Exceeded number of port range registers");
+		goto err_xa_alloc;
+	}
+
+	err = mlxsw_sp_port_range_reg_configure(mlxsw_sp, prr);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to configure port range register");
+		goto err_reg_configure;
+	}
+
+	return prr;
+
+err_reg_configure:
+	xa_erase(&pr_core->prr_xa, prr->index);
+err_xa_alloc:
+	kfree(prr);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_port_range_reg_destroy(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_port_range_reg *prr)
+{
+	struct mlxsw_sp_port_range_core *pr_core = mlxsw_sp->pr_core;
+
+	xa_erase(&pr_core->prr_xa, prr->index);
+	kfree(prr);
+}
+
+static struct mlxsw_sp_port_range_reg *
+mlxsw_sp_port_range_reg_find(struct mlxsw_sp *mlxsw_sp,
+			     const struct mlxsw_sp_port_range *range)
+{
+	struct mlxsw_sp_port_range_core *pr_core = mlxsw_sp->pr_core;
+	struct mlxsw_sp_port_range_reg *prr;
+	unsigned long index;
+
+	xa_for_each(&pr_core->prr_xa, index, prr) {
+		if (prr->range.min == range->min &&
+		    prr->range.max == range->max &&
+		    prr->range.source == range->source)
+			return prr;
+	}
+
+	return NULL;
+}
+
+int mlxsw_sp_port_range_reg_get(struct mlxsw_sp *mlxsw_sp,
+				const struct mlxsw_sp_port_range *range,
+				struct netlink_ext_ack *extack,
+				u8 *p_prr_index)
+{
+	struct mlxsw_sp_port_range_reg *prr;
+
+	prr = mlxsw_sp_port_range_reg_find(mlxsw_sp, range);
+	if (prr) {
+		refcount_inc(&prr->refcount);
+		*p_prr_index = prr->index;
+		return 0;
+	}
+
+	prr = mlxsw_sp_port_range_reg_create(mlxsw_sp, range, extack);
+	if (IS_ERR(prr))
+		return PTR_ERR(prr);
+
+	*p_prr_index = prr->index;
+
+	return 0;
+}
+
+void mlxsw_sp_port_range_reg_put(struct mlxsw_sp *mlxsw_sp, u8 prr_index)
+{
+	struct mlxsw_sp_port_range_core *pr_core = mlxsw_sp->pr_core;
+	struct mlxsw_sp_port_range_reg *prr;
+
+	prr = xa_load(&pr_core->prr_xa, prr_index);
+	if (WARN_ON(!prr))
+		return;
+
+	if (!refcount_dec_and_test(&prr->refcount))
+		return;
+
+	mlxsw_sp_port_range_reg_destroy(mlxsw_sp, prr);
+}
+
+int mlxsw_sp_port_range_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_port_range_core *pr_core;
+	struct mlxsw_core *core = mlxsw_sp->core;
+	u64 max;
+
+	if (!MLXSW_CORE_RES_VALID(core, ACL_MAX_L4_PORT_RANGE))
+		return -EIO;
+	max = MLXSW_CORE_RES_GET(core, ACL_MAX_L4_PORT_RANGE);
+
+	/* Each port range register is represented using a single bit in the
+	 * two bytes "l4_port_range" ACL key element.
+	 */
+	WARN_ON(max > BITS_PER_BYTE * sizeof(u16));
+
+	pr_core = kzalloc(sizeof(*mlxsw_sp->pr_core), GFP_KERNEL);
+	if (!pr_core)
+		return -ENOMEM;
+	mlxsw_sp->pr_core = pr_core;
+
+	pr_core->prr_ids.max = max - 1;
+	xa_init_flags(&pr_core->prr_xa, XA_FLAGS_ALLOC);
+
+	return 0;
+}
+
+void mlxsw_sp_port_range_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_port_range_core *pr_core = mlxsw_sp->pr_core;
+
+	WARN_ON(!xa_empty(&pr_core->prr_xa));
+	xa_destroy(&pr_core->prr_xa);
+	kfree(pr_core);
+}
-- 
GitLab


From 74d6786cf2dc563bebd3bceb4fd48aadee7856b2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 11 Jul 2023 18:43:57 +0200
Subject: [PATCH 0080/1806] mlxsw: spectrum_port_range: Add devlink resource
 support

Expose via devlink-resource the maximum number of port range registers
and their current occupancy. Besides the observability benefits, this
resource will be used by subsequent patches for scale and occupancy
tests.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/7945e0c715dc5efb1617f45f7560c1f1bd0bcf8a.1689092769.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    | 30 +++++++++++++++++++
 .../net/ethernet/mellanox/mlxsw/spectrum.h    |  1 +
 .../mellanox/mlxsw/spectrum_port_range.c      | 19 ++++++++++++
 3 files changed, 50 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index c0edcc91f178c..86e2f0ed64d3d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3739,6 +3739,26 @@ static int mlxsw_sp_resources_rifs_register(struct mlxsw_core *mlxsw_core)
 				      &size_params);
 }
 
+static int
+mlxsw_sp_resources_port_range_register(struct mlxsw_core *mlxsw_core)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_core);
+	struct devlink_resource_size_params size_params;
+	u64 max;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_core, ACL_MAX_L4_PORT_RANGE))
+		return -EIO;
+
+	max = MLXSW_CORE_RES_GET(mlxsw_core, ACL_MAX_L4_PORT_RANGE);
+	devlink_resource_size_params_init(&size_params, max, max, 1,
+					  DEVLINK_RESOURCE_UNIT_ENTRY);
+
+	return devl_resource_register(devlink, "port_range_registers", max,
+				      MLXSW_SP_RESOURCE_PORT_RANGE_REGISTERS,
+				      DEVLINK_RESOURCE_ID_PARENT_TOP,
+				      &size_params);
+}
+
 static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core)
 {
 	int err;
@@ -3767,8 +3787,13 @@ static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core)
 	if (err)
 		goto err_resources_rifs_register;
 
+	err = mlxsw_sp_resources_port_range_register(mlxsw_core);
+	if (err)
+		goto err_resources_port_range_register;
+
 	return 0;
 
+err_resources_port_range_register:
 err_resources_rifs_register:
 err_resources_rif_mac_profile_register:
 err_policer_resources_register:
@@ -3806,8 +3831,13 @@ static int mlxsw_sp2_resources_register(struct mlxsw_core *mlxsw_core)
 	if (err)
 		goto err_resources_rifs_register;
 
+	err = mlxsw_sp_resources_port_range_register(mlxsw_core);
+	if (err)
+		goto err_resources_port_range_register;
+
 	return 0;
 
+err_resources_port_range_register:
 err_resources_rifs_register:
 err_resources_rif_mac_profile_register:
 err_policer_resources_register:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index fe6c6e02a484f..a74652ea4d7cf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -69,6 +69,7 @@ enum mlxsw_sp_resource_id {
 	MLXSW_SP_RESOURCE_SINGLE_RATE_POLICERS,
 	MLXSW_SP_RESOURCE_RIF_MAC_PROFILES,
 	MLXSW_SP_RESOURCE_RIFS,
+	MLXSW_SP_RESOURCE_PORT_RANGE_REGISTERS,
 };
 
 struct mlxsw_sp_port;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_port_range.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_port_range.c
index a12a62632721c..2d193de12be69 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_port_range.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_port_range.c
@@ -5,6 +5,7 @@
 #include <linux/netlink.h>
 #include <linux/refcount.h>
 #include <linux/xarray.h>
+#include <net/devlink.h>
 
 #include "spectrum.h"
 
@@ -17,6 +18,7 @@ struct mlxsw_sp_port_range_reg {
 struct mlxsw_sp_port_range_core {
 	struct xarray prr_xa;
 	struct xa_limit prr_ids;
+	atomic_t prr_count;
 };
 
 static int
@@ -71,6 +73,8 @@ mlxsw_sp_port_range_reg_create(struct mlxsw_sp *mlxsw_sp,
 		goto err_reg_configure;
 	}
 
+	atomic_inc(&pr_core->prr_count);
+
 	return prr;
 
 err_reg_configure:
@@ -85,6 +89,7 @@ static void mlxsw_sp_port_range_reg_destroy(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_port_range_core *pr_core = mlxsw_sp->pr_core;
 
+	atomic_dec(&pr_core->prr_count);
 	xa_erase(&pr_core->prr_xa, prr->index);
 	kfree(prr);
 }
@@ -145,6 +150,13 @@ void mlxsw_sp_port_range_reg_put(struct mlxsw_sp *mlxsw_sp, u8 prr_index)
 	mlxsw_sp_port_range_reg_destroy(mlxsw_sp, prr);
 }
 
+static u64 mlxsw_sp_port_range_reg_occ_get(void *priv)
+{
+	struct mlxsw_sp_port_range_core *pr_core = priv;
+
+	return atomic_read(&pr_core->prr_count);
+}
+
 int mlxsw_sp_port_range_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_port_range_core *pr_core;
@@ -168,6 +180,11 @@ int mlxsw_sp_port_range_init(struct mlxsw_sp *mlxsw_sp)
 	pr_core->prr_ids.max = max - 1;
 	xa_init_flags(&pr_core->prr_xa, XA_FLAGS_ALLOC);
 
+	devl_resource_occ_get_register(priv_to_devlink(core),
+				       MLXSW_SP_RESOURCE_PORT_RANGE_REGISTERS,
+				       mlxsw_sp_port_range_reg_occ_get,
+				       pr_core);
+
 	return 0;
 }
 
@@ -175,6 +192,8 @@ void mlxsw_sp_port_range_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_port_range_core *pr_core = mlxsw_sp->pr_core;
 
+	devl_resource_occ_get_unregister(priv_to_devlink(mlxsw_sp->core),
+					 MLXSW_SP_RESOURCE_PORT_RANGE_REGISTERS);
 	WARN_ON(!xa_empty(&pr_core->prr_xa));
 	xa_destroy(&pr_core->prr_xa);
 	kfree(pr_core);
-- 
GitLab


From d65f24c9fa6917f1c32c52cc920f478485a0c6d6 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 11 Jul 2023 18:43:58 +0200
Subject: [PATCH 0081/1806] mlxsw: spectrum_acl: Add port range key element

Add the port range key element to supported key blocks so that it could
be used to match on the output of the port range registers. Each bit in
the element can be used to match on the output of the port range
register with the corresponding index.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/f0423f6ee9e36c6b0a426bc9995f42223c48f2db.1689092769.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c     | 1 +
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h     | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c | 3 +++
 3 files changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index f0b2963ebac32..7870327d921b2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -43,6 +43,7 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
 	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_32_63, 0x38, 4),
 	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_0_31, 0x3C, 4),
 	MLXSW_AFK_ELEMENT_INFO_U32(FDB_MISS, 0x40, 0, 1),
+	MLXSW_AFK_ELEMENT_INFO_U32(L4_PORT_RANGE, 0x40, 1, 16),
 };
 
 struct mlxsw_afk {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 65a4abadc7dbb..2eac7582c31a8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -36,6 +36,7 @@ enum mlxsw_afk_element {
 	MLXSW_AFK_ELEMENT_VIRT_ROUTER_MSB,
 	MLXSW_AFK_ELEMENT_VIRT_ROUTER_LSB,
 	MLXSW_AFK_ELEMENT_FDB_MISS,
+	MLXSW_AFK_ELEMENT_L4_PORT_RANGE,
 	MLXSW_AFK_ELEMENT_MAX,
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index 4dea39f2b304b..b7f58605b6c73 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -31,12 +31,14 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_sip[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(L4_PORT_RANGE, 0x04, 16, 16),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(L4_PORT_RANGE, 0x04, 16, 16),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
@@ -205,6 +207,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l4_0[] = {
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l4_2[] = {
 	MLXSW_AFK_ELEMENT_INST_U32(TCP_FLAGS, 0x04, 16, 9), /* TCP_CONTROL + TCP_ECN */
+	MLXSW_AFK_ELEMENT_INST_U32(L4_PORT_RANGE, 0x04, 0, 16),
 };
 
 static const struct mlxsw_afk_block mlxsw_sp2_afk_blocks[] = {
-- 
GitLab


From 898979c7238a5b465b55c7027129fb51fab908c5 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 11 Jul 2023 18:43:59 +0200
Subject: [PATCH 0082/1806] mlxsw: spectrum_acl: Pass main driver structure to
 mlxsw_sp_acl_rulei_destroy()

The main driver structure will be needed in this function by a
subsequent patch, so pass it. No functional changes intended.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/24d96a4e21310e5de2951ace58263db35e44a0df.1689092769.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           | 3 ++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c | 4 ++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c       | 5 +++--
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index a74652ea4d7cf..4a1bf2d39fa05 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -994,7 +994,8 @@ void mlxsw_sp_acl_ruleset_prio_get(struct mlxsw_sp_acl_ruleset *ruleset,
 struct mlxsw_sp_acl_rule_info *
 mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
 			  struct mlxsw_afa_block *afa_block);
-void mlxsw_sp_acl_rulei_destroy(struct mlxsw_sp_acl_rule_info *rulei);
+void mlxsw_sp_acl_rulei_destroy(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_rulei_commit(struct mlxsw_sp_acl_rule_info *rulei);
 void mlxsw_sp_acl_rulei_priority(struct mlxsw_sp_acl_rule_info *rulei,
 				 unsigned int priority);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index 3a636f753607b..dfcdd37e797b1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -90,7 +90,7 @@ mlxsw_sp1_acl_ctcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
 err_entry_add:
 err_rulei_commit:
 err_rulei_act_continue:
-	mlxsw_sp_acl_rulei_destroy(rulei);
+	mlxsw_sp_acl_rulei_destroy(mlxsw_sp, rulei);
 err_rulei_create:
 	mlxsw_sp_acl_ctcam_chunk_fini(&region->catchall.cchunk);
 	return err;
@@ -105,7 +105,7 @@ mlxsw_sp1_acl_ctcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &region->cregion,
 				     &region->catchall.cchunk,
 				     &region->catchall.centry);
-	mlxsw_sp_acl_rulei_destroy(rulei);
+	mlxsw_sp_acl_rulei_destroy(mlxsw_sp, rulei);
 	mlxsw_sp_acl_ctcam_chunk_fini(&region->catchall.cchunk);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 0423ac262d89f..7240b74b48836 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -339,7 +339,8 @@ err_afa_block_create:
 	return ERR_PTR(err);
 }
 
-void mlxsw_sp_acl_rulei_destroy(struct mlxsw_sp_acl_rule_info *rulei)
+void mlxsw_sp_acl_rulei_destroy(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule_info *rulei)
 {
 	if (rulei->action_created)
 		mlxsw_afa_block_destroy(rulei->act_block);
@@ -834,7 +835,7 @@ void mlxsw_sp_acl_rule_destroy(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
 
-	mlxsw_sp_acl_rulei_destroy(rule->rulei);
+	mlxsw_sp_acl_rulei_destroy(mlxsw_sp, rule->rulei);
 	kfree(rule);
 	mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset);
 }
-- 
GitLab


From fe22f7410527c2077223b5fd0fc0458db912f0db Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 11 Jul 2023 18:44:00 +0200
Subject: [PATCH 0083/1806] mlxsw: spectrum_flower: Add ability to match on
 port ranges

Add the ability to match on port ranges by utilizing the previously
added port range registers and the port range key element. Up to two
port range registers can be used for each filter, one for source port
and another for destination port.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/df4385a9592917e9a22ebff339e0463e4a8dfa82.1689092769.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.h    |  6 +-
 .../ethernet/mellanox/mlxsw/spectrum_acl.c    |  6 ++
 .../ethernet/mellanox/mlxsw/spectrum_flower.c | 68 +++++++++++++++++++
 3 files changed, 79 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 4a1bf2d39fa05..c6231e62a371e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -867,9 +867,13 @@ struct mlxsw_sp_acl_rule_info {
 	   egress_bind_blocker:1,
 	   counter_valid:1,
 	   policer_index_valid:1,
-	   ipv6_valid:1;
+	   ipv6_valid:1,
+	   src_port_range_reg_valid:1,
+	   dst_port_range_reg_valid:1;
 	unsigned int counter_index;
 	u16 policer_index;
+	u8 src_port_range_reg_index;
+	u8 dst_port_range_reg_index;
 	struct {
 		u32 prev_val;
 		enum mlxsw_sp_acl_mangle_field prev_field;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 7240b74b48836..186161a3459dd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -344,6 +344,12 @@ void mlxsw_sp_acl_rulei_destroy(struct mlxsw_sp *mlxsw_sp,
 {
 	if (rulei->action_created)
 		mlxsw_afa_block_destroy(rulei->act_block);
+	if (rulei->src_port_range_reg_valid)
+		mlxsw_sp_port_range_reg_put(mlxsw_sp,
+					    rulei->src_port_range_reg_index);
+	if (rulei->dst_port_range_reg_valid)
+		mlxsw_sp_port_range_reg_put(mlxsw_sp,
+					    rulei->dst_port_range_reg_index);
 	kfree(rulei);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 72917f09e806e..8329100479b3c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -418,6 +418,68 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
+static int
+mlxsw_sp_flower_parse_ports_range(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_rule_info *rulei,
+				  struct flow_cls_offload *f, u8 ip_proto)
+{
+	const struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_match_ports_range match;
+	u32 key_mask_value = 0;
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS_RANGE))
+		return 0;
+
+	if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "Only UDP and TCP keys are supported");
+		return -EINVAL;
+	}
+
+	flow_rule_match_ports_range(rule, &match);
+
+	if (match.mask->tp_min.src) {
+		struct mlxsw_sp_port_range range = {
+			.min = ntohs(match.key->tp_min.src),
+			.max = ntohs(match.key->tp_max.src),
+			.source = true,
+		};
+		u8 prr_index;
+		int err;
+
+		err = mlxsw_sp_port_range_reg_get(mlxsw_sp, &range,
+						  f->common.extack, &prr_index);
+		if (err)
+			return err;
+
+		rulei->src_port_range_reg_index = prr_index;
+		rulei->src_port_range_reg_valid = true;
+		key_mask_value |= BIT(prr_index);
+	}
+
+	if (match.mask->tp_min.dst) {
+		struct mlxsw_sp_port_range range = {
+			.min = ntohs(match.key->tp_min.dst),
+			.max = ntohs(match.key->tp_max.dst),
+		};
+		u8 prr_index;
+		int err;
+
+		err = mlxsw_sp_port_range_reg_get(mlxsw_sp, &range,
+						  f->common.extack, &prr_index);
+		if (err)
+			return err;
+
+		rulei->dst_port_range_reg_index = prr_index;
+		rulei->dst_port_range_reg_valid = true;
+		key_mask_value |= BIT(prr_index);
+	}
+
+	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_L4_PORT_RANGE,
+				       key_mask_value, key_mask_value);
+
+	return 0;
+}
+
 static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_acl_rule_info *rulei,
 				     struct flow_cls_offload *f,
@@ -503,6 +565,7 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT(FLOW_DISSECTOR_KEY_PORTS_RANGE) |
 	      BIT(FLOW_DISSECTOR_KEY_TCP) |
 	      BIT(FLOW_DISSECTOR_KEY_IP) |
 	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
@@ -604,6 +667,11 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	err = mlxsw_sp_flower_parse_ports(mlxsw_sp, rulei, f, ip_proto);
 	if (err)
 		return err;
+
+	err = mlxsw_sp_flower_parse_ports_range(mlxsw_sp, rulei, f, ip_proto);
+	if (err)
+		return err;
+
 	err = mlxsw_sp_flower_parse_tcp(mlxsw_sp, rulei, f, ip_proto);
 	if (err)
 		return err;
-- 
GitLab


From 45c5a384765bb879f8a07e0056c0885771124271 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 11 Jul 2023 18:44:01 +0200
Subject: [PATCH 0084/1806] selftests: mlxsw: Add scale test for port ranges

Query the maximum number of supported port range registers using
devlink-resource and test that this number can be reached by configuring
tc filters with different port ranges. Test that an error is returned in
case the maximum number is exceeded.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/48eee181270d9f291e09d1858c7b26a3f7fcc164.1689092769.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../drivers/net/mlxsw/port_range_scale.sh     | 95 +++++++++++++++++++
 .../net/mlxsw/spectrum-2/port_range_scale.sh  |  1 +
 .../net/mlxsw/spectrum-2/resource_scale.sh    |  1 +
 .../net/mlxsw/spectrum/port_range_scale.sh    | 16 ++++
 .../net/mlxsw/spectrum/resource_scale.sh      |  1 +
 5 files changed, 114 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/port_range_scale.sh
 create mode 120000 tools/testing/selftests/drivers/net/mlxsw/spectrum-2/port_range_scale.sh
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/spectrum/port_range_scale.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/port_range_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/port_range_scale.sh
new file mode 100644
index 0000000000000..2a70840ff14b7
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/port_range_scale.sh
@@ -0,0 +1,95 @@
+# SPDX-License-Identifier: GPL-2.0
+
+PORT_RANGE_NUM_NETIFS=2
+
+port_range_h1_create()
+{
+	simple_if_init $h1
+}
+
+port_range_h1_destroy()
+{
+	simple_if_fini $h1
+}
+
+port_range_switch_create()
+{
+	simple_if_init $swp1
+	tc qdisc add dev $swp1 clsact
+}
+
+port_range_switch_destroy()
+{
+	tc qdisc del dev $swp1 clsact
+	simple_if_fini $swp1
+}
+
+port_range_rules_create()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+	local batch_file="$(mktemp)"
+
+	for ((i = 0; i < count; ++i)); do
+		cat >> $batch_file <<-EOF
+			filter add dev $swp1 ingress \
+				prot ipv4 \
+				pref 1000 \
+				flower skip_sw \
+				ip_proto udp dst_port 1-$((100 + i)) \
+				action pass
+		EOF
+	done
+
+	tc -b $batch_file
+	check_err_fail $should_fail $? "Rule insertion"
+
+	rm -f $batch_file
+}
+
+__port_range_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	port_range_rules_create $count $should_fail
+
+	offload_count=$(tc -j filter show dev $swp1 ingress |
+			jq "[.[] | select(.options.in_hw == true)] | length")
+	((offload_count == count))
+	check_err_fail $should_fail $? "port range offload count"
+}
+
+port_range_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	if ! tc_offload_check $PORT_RANGE_NUM_NETIFS; then
+		check_err 1 "Could not test offloaded functionality"
+		return
+	fi
+
+	__port_range_test $count $should_fail
+}
+
+port_range_setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	vrf_prepare
+
+	port_range_h1_create
+	port_range_switch_create
+}
+
+port_range_cleanup()
+{
+	pre_cleanup
+
+	port_range_switch_destroy
+	port_range_h1_destroy
+
+	vrf_cleanup
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/port_range_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/port_range_scale.sh
new file mode 120000
index 0000000000000..bd670d9dc4e5c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/port_range_scale.sh
@@ -0,0 +1 @@
+../spectrum/port_range_scale.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
index 688338bbeb971..a88d8a8c85f2e 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
@@ -33,6 +33,7 @@ ALL_TESTS="
 	port
 	rif_mac_profile
 	rif_counter
+	port_range
 "
 
 for current_test in ${TESTS:-$ALL_TESTS}; do
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/port_range_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/port_range_scale.sh
new file mode 100644
index 0000000000000..d0847e8ea2705
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/port_range_scale.sh
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../port_range_scale.sh
+
+port_range_get_target()
+{
+	local should_fail=$1; shift
+	local target
+
+	target=$(devlink_resource_size_get port_range_registers)
+
+	if ((! should_fail)); then
+		echo $target
+	else
+		echo $((target + 1))
+	fi
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index 95d9f710a6308..f981c957f0975 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -30,6 +30,7 @@ ALL_TESTS="
 	port
 	rif_mac_profile
 	rif_counter
+	port_range
 "
 
 for current_test in ${TESTS:-$ALL_TESTS}; do
-- 
GitLab


From 0a1a818d8a1c13375219d358de7e0e28e308d6a5 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 11 Jul 2023 18:44:02 +0200
Subject: [PATCH 0085/1806] selftests: mlxsw: Test port range registers'
 occupancy

Test that filters that match on the same port range, but with different
combination of IPv4/IPv6 and TCP/UDP all use the same port range
register by observing port range registers' occupancy via
devlink-resource.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/0a2eb63b234fb062ff011e80231868cc80000c81.1689092769.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../drivers/net/mlxsw/port_range_occ.sh       | 111 ++++++++++++++++++
 1 file changed, 111 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/port_range_occ.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/port_range_occ.sh b/tools/testing/selftests/drivers/net/mlxsw/port_range_occ.sh
new file mode 100755
index 0000000000000..b1f0781f6b25f
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/port_range_occ.sh
@@ -0,0 +1,111 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that filters that match on the same port range, but with different
+# combination of IPv4/IPv6 and TCP/UDP all use the same port range register by
+# observing port range registers' occupancy via devlink-resource.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	port_range_occ_test
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1
+}
+
+switch_create()
+{
+	simple_if_init $swp1
+	tc qdisc add dev $swp1 clsact
+}
+
+switch_destroy()
+{
+	tc qdisc del dev $swp1 clsact
+	simple_if_fini $swp1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	vrf_prepare
+
+	h1_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+port_range_occ_get()
+{
+	devlink_resource_occ_get port_range_registers
+}
+
+port_range_occ_test()
+{
+	RET=0
+
+	local occ=$(port_range_occ_get)
+
+	# Two port range registers are used, for source and destination port
+	# ranges.
+	tc filter add dev $swp1 ingress pref 1 handle 101 proto ip \
+		flower skip_sw ip_proto udp src_port 1-100 dst_port 1-100 \
+		action pass
+	(( occ + 2 == $(port_range_occ_get) ))
+	check_err $? "Got occupancy $(port_range_occ_get), expected $((occ + 2))"
+
+	tc filter add dev $swp1 ingress pref 1 handle 102 proto ip \
+		flower skip_sw ip_proto tcp src_port 1-100 dst_port 1-100 \
+		action pass
+	tc filter add dev $swp1 ingress pref 2 handle 103 proto ipv6 \
+		flower skip_sw ip_proto udp src_port 1-100 dst_port 1-100 \
+		action pass
+	tc filter add dev $swp1 ingress pref 2 handle 104 proto ipv6 \
+		flower skip_sw ip_proto tcp src_port 1-100 dst_port 1-100 \
+		action pass
+	(( occ + 2 == $(port_range_occ_get) ))
+	check_err $? "Got occupancy $(port_range_occ_get), expected $((occ + 2))"
+
+	tc filter del dev $swp1 ingress pref 2 handle 104 flower
+	tc filter del dev $swp1 ingress pref 2 handle 103 flower
+	tc filter del dev $swp1 ingress pref 1 handle 102 flower
+	(( occ + 2 == $(port_range_occ_get) ))
+	check_err $? "Got occupancy $(port_range_occ_get), expected $((occ + 2))"
+
+	tc filter del dev $swp1 ingress pref 1 handle 101 flower
+	(( occ == $(port_range_occ_get) ))
+	check_err $? "Got occupancy $(port_range_occ_get), expected $occ"
+
+	log_test "port range occupancy"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From 209218e4799bf1bac0296f749b824b4e0da1575e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 11 Jul 2023 18:44:03 +0200
Subject: [PATCH 0086/1806] selftests: forwarding: Add test cases for flower
 port range matching

Add test cases to verify that flower port range matching works
correctly. Test both source and destination port ranges, with different
combinations of IPv4/IPv6 and TCP/UDP, on both ingress and egress.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/9d47c9cd4522b2d335b13ce8f6c9b33199298cee.1689092769.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/forwarding/Makefile |   1 +
 .../net/forwarding/tc_flower_port_range.sh    | 228 ++++++++++++++++++
 2 files changed, 229 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/tc_flower_port_range.sh

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 770efbe24f0d0..f49c6c3f6520a 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -85,6 +85,7 @@ TEST_PROGS = bridge_igmp.sh \
 	tc_flower.sh \
 	tc_flower_l2_miss.sh \
 	tc_flower_cfm.sh \
+	tc_flower_port_range.sh \
 	tc_mpls_l2vpn.sh \
 	tc_police.sh \
 	tc_shblocks.sh \
diff --git a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh
new file mode 100755
index 0000000000000..3885a2a91f7d8
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh
@@ -0,0 +1,228 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +-----------------------+                             +----------------------+
+# | H1 (vrf)              |                             | H2 (vrf)             |
+# |    + $h1              |                             |              $h2 +   |
+# |    | 192.0.2.1/28     |                             |     192.0.2.2/28 |   |
+# |    | 2001:db8:1::1/64 |                             | 2001:db8:1::2/64 |   |
+# +----|------------------+                             +------------------|---+
+#      |                                                                   |
+# +----|-------------------------------------------------------------------|---+
+# | SW |                                                                   |   |
+# |  +-|-------------------------------------------------------------------|-+ |
+# |  | + $swp1                       BR                              $swp2 + | |
+# |  +-----------------------------------------------------------------------+ |
+# +----------------------------------------------------------------------------+
+
+ALL_TESTS="
+	test_port_range_ipv4_udp
+	test_port_range_ipv4_tcp
+	test_port_range_ipv6_udp
+	test_port_range_ipv6_tcp
+"
+
+NUM_NETIFS=4
+source lib.sh
+source tc_common.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64
+}
+
+h2_destroy()
+{
+	simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64
+}
+
+switch_create()
+{
+	ip link add name br1 type bridge
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+	ip link set dev $swp2 master br1
+	ip link set dev $swp2 up
+	ip link set dev br1 up
+
+	tc qdisc add dev $swp1 clsact
+	tc qdisc add dev $swp2 clsact
+}
+
+switch_destroy()
+{
+	tc qdisc del dev $swp2 clsact
+	tc qdisc del dev $swp1 clsact
+
+	ip link set dev br1 down
+	ip link set dev $swp2 down
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+	ip link del dev br1
+}
+
+__test_port_range()
+{
+	local proto=$1; shift
+	local ip_proto=$1; shift
+	local sip=$1; shift
+	local dip=$1; shift
+	local mode=$1; shift
+	local name=$1; shift
+	local dmac=$(mac_get $h2)
+	local smac=$(mac_get $h1)
+	local sport_min=100
+	local sport_max=200
+	local sport_mid=$((sport_min + (sport_max - sport_min) / 2))
+	local dport_min=300
+	local dport_max=400
+	local dport_mid=$((dport_min + (dport_max - dport_min) / 2))
+
+	RET=0
+
+	tc filter add dev $swp1 ingress protocol $proto handle 101 pref 1 \
+		flower src_ip $sip dst_ip $dip ip_proto $ip_proto \
+		src_port $sport_min-$sport_max \
+		dst_port $dport_min-$dport_max \
+		action pass
+	tc filter add dev $swp2 egress protocol $proto handle 101 pref 1 \
+		flower src_ip $sip dst_ip $dip ip_proto $ip_proto \
+		src_port $sport_min-$sport_max \
+		dst_port $dport_min-$dport_max \
+		action drop
+
+	$MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \
+		-t $ip_proto "sp=$sport_min,dp=$dport_min"
+	tc_check_packets "dev $swp1 ingress" 101 1
+	check_err $? "Ingress filter not hit with minimum ports"
+	tc_check_packets "dev $swp2 egress" 101 1
+	check_err $? "Egress filter not hit with minimum ports"
+
+	$MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \
+		-t $ip_proto "sp=$sport_mid,dp=$dport_mid"
+	tc_check_packets "dev $swp1 ingress" 101 2
+	check_err $? "Ingress filter not hit with middle ports"
+	tc_check_packets "dev $swp2 egress" 101 2
+	check_err $? "Egress filter not hit with middle ports"
+
+	$MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \
+		-t $ip_proto "sp=$sport_max,dp=$dport_max"
+	tc_check_packets "dev $swp1 ingress" 101 3
+	check_err $? "Ingress filter not hit with maximum ports"
+	tc_check_packets "dev $swp2 egress" 101 3
+	check_err $? "Egress filter not hit with maximum ports"
+
+	# Send traffic when both ports are out of range and when only one port
+	# is out of range.
+	$MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \
+		-t $ip_proto "sp=$((sport_min - 1)),dp=$dport_min"
+	$MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \
+		-t $ip_proto "sp=$((sport_max + 1)),dp=$dport_min"
+	$MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \
+		-t $ip_proto "sp=$sport_min,dp=$((dport_min - 1))"
+	$MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \
+		-t $ip_proto "sp=$sport_min,dp=$((dport_max + 1))"
+	$MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \
+		-t $ip_proto "sp=$((sport_max + 1)),dp=$((dport_max + 1))"
+	tc_check_packets "dev $swp1 ingress" 101 3
+	check_err $? "Ingress filter was hit when should not"
+	tc_check_packets "dev $swp2 egress" 101 3
+	check_err $? "Egress filter was hit when should not"
+
+	tc filter del dev $swp2 egress protocol $proto pref 1 handle 101 flower
+	tc filter del dev $swp1 ingress protocol $proto pref 1 handle 101 flower
+
+	log_test "Port range matching - $name"
+}
+
+test_port_range_ipv4_udp()
+{
+	local proto=ipv4
+	local ip_proto=udp
+	local sip=192.0.2.1
+	local dip=192.0.2.2
+	local mode="-4"
+	local name="IPv4 UDP"
+
+	__test_port_range $proto $ip_proto $sip $dip $mode "$name"
+}
+
+test_port_range_ipv4_tcp()
+{
+	local proto=ipv4
+	local ip_proto=tcp
+	local sip=192.0.2.1
+	local dip=192.0.2.2
+	local mode="-4"
+	local name="IPv4 TCP"
+
+	__test_port_range $proto $ip_proto $sip $dip $mode "$name"
+}
+
+test_port_range_ipv6_udp()
+{
+	local proto=ipv6
+	local ip_proto=udp
+	local sip=2001:db8:1::1
+	local dip=2001:db8:1::2
+	local mode="-6"
+	local name="IPv6 UDP"
+
+	__test_port_range $proto $ip_proto $sip $dip $mode "$name"
+}
+
+test_port_range_ipv6_tcp()
+{
+	local proto=ipv6
+	local ip_proto=tcp
+	local sip=2001:db8:1::1
+	local dip=2001:db8:1::2
+	local mode="-6"
+	local name="IPv6 TCP"
+
+	__test_port_range $proto $ip_proto $sip $dip $mode "$name"
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+	h1_create
+	h2_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From c5ec13e38af5527f69f647c46ce15ebaa6b35e6c Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Mon, 10 Jul 2023 14:35:11 -0700
Subject: [PATCH 0087/1806] ipv6: rpl: Remove redundant skb_dst_drop().

RPL code has a pattern where skb_dst_drop() is called before
ip6_route_input().

However, ip6_route_input() calls skb_dst_drop() internally,
so we need not call skb_dst_drop() before ip6_route_input().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230710213511.5364-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/exthdrs.c      | 2 --
 net/ipv6/rpl_iptunnel.c | 3 +--
 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 202fc3aaa83cc..f4bfccae003cc 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -612,8 +612,6 @@ looped_back:
 
 	kfree(buf);
 
-	skb_dst_drop(skb);
-
 	ip6_route_input(skb);
 
 	if (skb_dst(skb)->error) {
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index b1c028df686ed..a013b92cbb860 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -272,8 +272,6 @@ static int rpl_input(struct sk_buff *skb)
 	dst = dst_cache_get(&rlwt->cache);
 	preempt_enable();
 
-	skb_dst_drop(skb);
-
 	if (!dst) {
 		ip6_route_input(skb);
 		dst = skb_dst(skb);
@@ -284,6 +282,7 @@ static int rpl_input(struct sk_buff *skb)
 			preempt_enable();
 		}
 	} else {
+		skb_dst_drop(skb);
 		skb_dst_set(skb, dst);
 	}
 
-- 
GitLab


From ba2274dcfda859b8a27193e68ad37bfe4da28ddc Mon Sep 17 00:00:00 2001
From: Jose Ignacio Tornos Martinez <jtornosm@redhat.com>
Date: Tue, 11 Jul 2023 08:28:13 +0200
Subject: [PATCH 0088/1806] net: wwan: t7xx: Add AP CLDMA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

At this moment with the current status, t7xx is not functional due to
problems like this after connection, if there is no activity:
[   57.370534] mtk_t7xx 0000:72:00.0: [PM] SAP suspend error: -110
[   57.370581] mtk_t7xx 0000:72:00.0: can't suspend
    (t7xx_pci_pm_runtime_suspend [mtk_t7xx] returned -110)
because after this, the traffic no longer works.

The complete series 'net: wwan: t7xx: fw flashing & coredump support'
was reverted because of issues with the pci implementation.
In order to have at least the modem working, it would be enough if just
the first commit of the series is re-applied:
d20ef656f994 net: wwan: t7xx: Add AP CLDMA
With that, the Application Processor would be controlled, correctly
suspended and the commented problems would be fixed (I am testing here
like this with no related issue).

This commit is independent of the others and not related to the
commented pci implementation for the new features: fw flashing and
coredump collection.

Use v2 patch version of d20ef656f994 as JinJian Song suggests
(https://patchwork.kernel.org/project/netdevbpf/patch/20230105154215.198828-1-m.chetan.kumar@linux.intel.com/).

Original text from the commit that would be re-applied:

    d20ef656f994 net: wwan: t7xx: Add AP CLDMA
    Author: Haijun Liu <haijun.liu@mediatek.com>
    Date:   Tue Aug 16 09:53:28 2022 +0530

    The t7xx device contains two Cross Layer DMA (CLDMA) interfaces to
    communicate with AP and Modem processors respectively. So far only
    MD-CLDMA was being used, this patch enables AP-CLDMA.

    Rename small Application Processor (sAP) to AP.

    Signed-off-by: Haijun Liu <haijun.liu@mediatek.com>
    Co-developed-by: Madhusmita Sahu <madhusmita.sahu@intel.com>
    Signed-off-by: Madhusmita Sahu <madhusmita.sahu@intel.com>
    Signed-off-by: Moises Veleta <moises.veleta@linux.intel.com>
    Signed-off-by: Devegowda Chandrashekar <chandrashekar.devegowda@intel.com>
    Signed-off-by: M Chetan Kumar <m.chetan.kumar@linux.intel.com>
    Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
    Reviewed-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
    Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>

Signed-off-by: Jose Ignacio Tornos Martinez <jtornosm@redhat.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230711062817.6108-1-jtornosm@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/wwan/t7xx/t7xx_hif_cldma.c     | 17 +++--
 drivers/net/wwan/t7xx/t7xx_hif_cldma.h     |  2 +-
 drivers/net/wwan/t7xx/t7xx_mhccif.h        |  1 +
 drivers/net/wwan/t7xx/t7xx_modem_ops.c     | 76 +++++++++++++++++-----
 drivers/net/wwan/t7xx/t7xx_modem_ops.h     |  2 +
 drivers/net/wwan/t7xx/t7xx_port.h          |  6 +-
 drivers/net/wwan/t7xx/t7xx_port_ctrl_msg.c |  8 ++-
 drivers/net/wwan/t7xx/t7xx_port_proxy.c    | 18 ++++-
 drivers/net/wwan/t7xx/t7xx_reg.h           |  2 +-
 drivers/net/wwan/t7xx/t7xx_state_monitor.c | 13 +++-
 drivers/net/wwan/t7xx/t7xx_state_monitor.h |  2 +
 11 files changed, 116 insertions(+), 31 deletions(-)

diff --git a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c
index 7162bf38a8c90..cc70360364b7d 100644
--- a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c
+++ b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c
@@ -1066,13 +1066,18 @@ static void t7xx_hw_info_init(struct cldma_ctrl *md_ctrl)
 	struct t7xx_cldma_hw *hw_info = &md_ctrl->hw_info;
 	u32 phy_ao_base, phy_pd_base;
 
-	if (md_ctrl->hif_id != CLDMA_ID_MD)
-		return;
-
-	phy_ao_base = CLDMA1_AO_BASE;
-	phy_pd_base = CLDMA1_PD_BASE;
-	hw_info->phy_interrupt_id = CLDMA1_INT;
 	hw_info->hw_mode = MODE_BIT_64;
+
+	if (md_ctrl->hif_id == CLDMA_ID_MD) {
+		phy_ao_base = CLDMA1_AO_BASE;
+		phy_pd_base = CLDMA1_PD_BASE;
+		hw_info->phy_interrupt_id = CLDMA1_INT;
+	} else {
+		phy_ao_base = CLDMA0_AO_BASE;
+		phy_pd_base = CLDMA0_PD_BASE;
+		hw_info->phy_interrupt_id = CLDMA0_INT;
+	}
+
 	hw_info->ap_ao_base = t7xx_pcie_addr_transfer(pbase->pcie_ext_reg_base,
 						      pbase->pcie_dev_reg_trsl_addr, phy_ao_base);
 	hw_info->ap_pdn_base = t7xx_pcie_addr_transfer(pbase->pcie_ext_reg_base,
diff --git a/drivers/net/wwan/t7xx/t7xx_hif_cldma.h b/drivers/net/wwan/t7xx/t7xx_hif_cldma.h
index 47a35e552da78..4410bac6993ae 100644
--- a/drivers/net/wwan/t7xx/t7xx_hif_cldma.h
+++ b/drivers/net/wwan/t7xx/t7xx_hif_cldma.h
@@ -34,7 +34,7 @@
 /**
  * enum cldma_id - Identifiers for CLDMA HW units.
  * @CLDMA_ID_MD: Modem control channel.
- * @CLDMA_ID_AP: Application Processor control channel (not used at the moment).
+ * @CLDMA_ID_AP: Application Processor control channel.
  * @CLDMA_NUM:   Number of CLDMA HW units available.
  */
 enum cldma_id {
diff --git a/drivers/net/wwan/t7xx/t7xx_mhccif.h b/drivers/net/wwan/t7xx/t7xx_mhccif.h
index 209b386bc0886..20c50dce9fc31 100644
--- a/drivers/net/wwan/t7xx/t7xx_mhccif.h
+++ b/drivers/net/wwan/t7xx/t7xx_mhccif.h
@@ -25,6 +25,7 @@
 			 D2H_INT_EXCEPTION_CLEARQ_DONE |	\
 			 D2H_INT_EXCEPTION_ALLQ_RESET |		\
 			 D2H_INT_PORT_ENUM |			\
+			 D2H_INT_ASYNC_AP_HK |			\
 			 D2H_INT_ASYNC_MD_HK)
 
 void t7xx_mhccif_mask_set(struct t7xx_pci_dev *t7xx_dev, u32 val);
diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.c b/drivers/net/wwan/t7xx/t7xx_modem_ops.c
index 7d0f5e4f0a781..24e7d491468e0 100644
--- a/drivers/net/wwan/t7xx/t7xx_modem_ops.c
+++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.c
@@ -44,6 +44,7 @@
 #include "t7xx_state_monitor.h"
 
 #define RT_ID_MD_PORT_ENUM	0
+#define RT_ID_AP_PORT_ENUM	1
 /* Modem feature query identification code - "ICCC" */
 #define MD_FEATURE_QUERY_ID	0x49434343
 
@@ -298,6 +299,7 @@ static void t7xx_md_exception(struct t7xx_modem *md, enum hif_ex_stage stage)
 	}
 
 	t7xx_cldma_exception(md->md_ctrl[CLDMA_ID_MD], stage);
+	t7xx_cldma_exception(md->md_ctrl[CLDMA_ID_AP], stage);
 
 	if (stage == HIF_EX_INIT)
 		t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_EXCEPTION_ACK);
@@ -426,7 +428,7 @@ static int t7xx_parse_host_rt_data(struct t7xx_fsm_ctl *ctl, struct t7xx_sys_inf
 		if (ft_spt_st != MTK_FEATURE_MUST_BE_SUPPORTED)
 			return -EINVAL;
 
-		if (i == RT_ID_MD_PORT_ENUM)
+		if (i == RT_ID_MD_PORT_ENUM || i == RT_ID_AP_PORT_ENUM)
 			t7xx_port_enum_msg_handler(ctl->md, rt_feature->data);
 	}
 
@@ -456,12 +458,12 @@ static int t7xx_core_reset(struct t7xx_modem *md)
 	return 0;
 }
 
-static void t7xx_core_hk_handler(struct t7xx_modem *md, struct t7xx_fsm_ctl *ctl,
+static void t7xx_core_hk_handler(struct t7xx_modem *md, struct t7xx_sys_info *core_info,
+				 struct t7xx_fsm_ctl *ctl,
 				 enum t7xx_fsm_event_state event_id,
 				 enum t7xx_fsm_event_state err_detect)
 {
 	struct t7xx_fsm_event *event = NULL, *event_next;
-	struct t7xx_sys_info *core_info = &md->core_md;
 	struct device *dev = &md->t7xx_dev->pdev->dev;
 	unsigned long flags;
 	int ret;
@@ -531,19 +533,33 @@ static void t7xx_md_hk_wq(struct work_struct *work)
 	t7xx_cldma_start(md->md_ctrl[CLDMA_ID_MD]);
 	t7xx_fsm_broadcast_state(ctl, MD_STATE_WAITING_FOR_HS2);
 	md->core_md.handshake_ongoing = true;
-	t7xx_core_hk_handler(md, ctl, FSM_EVENT_MD_HS2, FSM_EVENT_MD_HS2_EXIT);
+	t7xx_core_hk_handler(md, &md->core_md, ctl, FSM_EVENT_MD_HS2, FSM_EVENT_MD_HS2_EXIT);
+}
+
+static void t7xx_ap_hk_wq(struct work_struct *work)
+{
+	struct t7xx_modem *md = container_of(work, struct t7xx_modem, ap_handshake_work);
+	struct t7xx_fsm_ctl *ctl = md->fsm_ctl;
+
+	 /* Clear the HS2 EXIT event appended in t7xx_core_reset(). */
+	t7xx_fsm_clr_event(ctl, FSM_EVENT_AP_HS2_EXIT);
+	t7xx_cldma_stop(md->md_ctrl[CLDMA_ID_AP]);
+	t7xx_cldma_switch_cfg(md->md_ctrl[CLDMA_ID_AP]);
+	t7xx_cldma_start(md->md_ctrl[CLDMA_ID_AP]);
+	md->core_ap.handshake_ongoing = true;
+	t7xx_core_hk_handler(md, &md->core_ap, ctl, FSM_EVENT_AP_HS2, FSM_EVENT_AP_HS2_EXIT);
 }
 
 void t7xx_md_event_notify(struct t7xx_modem *md, enum md_event_id evt_id)
 {
 	struct t7xx_fsm_ctl *ctl = md->fsm_ctl;
-	void __iomem *mhccif_base;
 	unsigned int int_sta;
 	unsigned long flags;
 
 	switch (evt_id) {
 	case FSM_PRE_START:
-		t7xx_mhccif_mask_clr(md->t7xx_dev, D2H_INT_PORT_ENUM);
+		t7xx_mhccif_mask_clr(md->t7xx_dev, D2H_INT_PORT_ENUM | D2H_INT_ASYNC_MD_HK |
+						   D2H_INT_ASYNC_AP_HK);
 		break;
 
 	case FSM_START:
@@ -556,16 +572,26 @@ void t7xx_md_event_notify(struct t7xx_modem *md, enum md_event_id evt_id)
 			ctl->exp_flg = true;
 			md->exp_id &= ~D2H_INT_EXCEPTION_INIT;
 			md->exp_id &= ~D2H_INT_ASYNC_MD_HK;
+			md->exp_id &= ~D2H_INT_ASYNC_AP_HK;
 		} else if (ctl->exp_flg) {
 			md->exp_id &= ~D2H_INT_ASYNC_MD_HK;
-		} else if (md->exp_id & D2H_INT_ASYNC_MD_HK) {
-			queue_work(md->handshake_wq, &md->handshake_work);
-			md->exp_id &= ~D2H_INT_ASYNC_MD_HK;
-			mhccif_base = md->t7xx_dev->base_addr.mhccif_rc_base;
-			iowrite32(D2H_INT_ASYNC_MD_HK, mhccif_base + REG_EP2RC_SW_INT_ACK);
-			t7xx_mhccif_mask_set(md->t7xx_dev, D2H_INT_ASYNC_MD_HK);
+			md->exp_id &= ~D2H_INT_ASYNC_AP_HK;
 		} else {
-			t7xx_mhccif_mask_clr(md->t7xx_dev, D2H_INT_ASYNC_MD_HK);
+			void __iomem *mhccif_base = md->t7xx_dev->base_addr.mhccif_rc_base;
+
+			if (md->exp_id & D2H_INT_ASYNC_MD_HK) {
+				queue_work(md->handshake_wq, &md->handshake_work);
+				md->exp_id &= ~D2H_INT_ASYNC_MD_HK;
+				iowrite32(D2H_INT_ASYNC_MD_HK, mhccif_base + REG_EP2RC_SW_INT_ACK);
+				t7xx_mhccif_mask_set(md->t7xx_dev, D2H_INT_ASYNC_MD_HK);
+			}
+
+			if (md->exp_id & D2H_INT_ASYNC_AP_HK) {
+				queue_work(md->handshake_wq, &md->ap_handshake_work);
+				md->exp_id &= ~D2H_INT_ASYNC_AP_HK;
+				iowrite32(D2H_INT_ASYNC_AP_HK, mhccif_base + REG_EP2RC_SW_INT_ACK);
+				t7xx_mhccif_mask_set(md->t7xx_dev, D2H_INT_ASYNC_AP_HK);
+			}
 		}
 		spin_unlock_irqrestore(&md->exp_lock, flags);
 
@@ -578,6 +604,7 @@ void t7xx_md_event_notify(struct t7xx_modem *md, enum md_event_id evt_id)
 
 	case FSM_READY:
 		t7xx_mhccif_mask_set(md->t7xx_dev, D2H_INT_ASYNC_MD_HK);
+		t7xx_mhccif_mask_set(md->t7xx_dev, D2H_INT_ASYNC_AP_HK);
 		break;
 
 	default:
@@ -629,6 +656,12 @@ static struct t7xx_modem *t7xx_md_alloc(struct t7xx_pci_dev *t7xx_dev)
 	md->core_md.feature_set[RT_ID_MD_PORT_ENUM] &= ~FEATURE_MSK;
 	md->core_md.feature_set[RT_ID_MD_PORT_ENUM] |=
 		FIELD_PREP(FEATURE_MSK, MTK_FEATURE_MUST_BE_SUPPORTED);
+
+	INIT_WORK(&md->ap_handshake_work, t7xx_ap_hk_wq);
+	md->core_ap.feature_set[RT_ID_AP_PORT_ENUM] &= ~FEATURE_MSK;
+	md->core_ap.feature_set[RT_ID_AP_PORT_ENUM] |=
+		FIELD_PREP(FEATURE_MSK, MTK_FEATURE_MUST_BE_SUPPORTED);
+
 	return md;
 }
 
@@ -640,6 +673,7 @@ int t7xx_md_reset(struct t7xx_pci_dev *t7xx_dev)
 	md->exp_id = 0;
 	t7xx_fsm_reset(md);
 	t7xx_cldma_reset(md->md_ctrl[CLDMA_ID_MD]);
+	t7xx_cldma_reset(md->md_ctrl[CLDMA_ID_AP]);
 	t7xx_port_proxy_reset(md->port_prox);
 	md->md_init_finish = true;
 	return t7xx_core_reset(md);
@@ -669,6 +703,10 @@ int t7xx_md_init(struct t7xx_pci_dev *t7xx_dev)
 	if (ret)
 		goto err_destroy_hswq;
 
+	ret = t7xx_cldma_alloc(CLDMA_ID_AP, t7xx_dev);
+	if (ret)
+		goto err_destroy_hswq;
+
 	ret = t7xx_fsm_init(md);
 	if (ret)
 		goto err_destroy_hswq;
@@ -681,12 +719,16 @@ int t7xx_md_init(struct t7xx_pci_dev *t7xx_dev)
 	if (ret)
 		goto err_uninit_ccmni;
 
-	ret = t7xx_port_proxy_init(md);
+	ret = t7xx_cldma_init(md->md_ctrl[CLDMA_ID_AP]);
 	if (ret)
 		goto err_uninit_md_cldma;
 
+	ret = t7xx_port_proxy_init(md);
+	if (ret)
+		goto err_uninit_ap_cldma;
+
 	ret = t7xx_fsm_append_cmd(md->fsm_ctl, FSM_CMD_START, 0);
-	if (ret) /* fsm_uninit flushes cmd queue */
+	if (ret) /* t7xx_fsm_uninit() flushes cmd queue */
 		goto err_uninit_proxy;
 
 	t7xx_md_sys_sw_init(t7xx_dev);
@@ -696,6 +738,9 @@ int t7xx_md_init(struct t7xx_pci_dev *t7xx_dev)
 err_uninit_proxy:
 	t7xx_port_proxy_uninit(md->port_prox);
 
+err_uninit_ap_cldma:
+	t7xx_cldma_exit(md->md_ctrl[CLDMA_ID_AP]);
+
 err_uninit_md_cldma:
 	t7xx_cldma_exit(md->md_ctrl[CLDMA_ID_MD]);
 
@@ -722,6 +767,7 @@ void t7xx_md_exit(struct t7xx_pci_dev *t7xx_dev)
 
 	t7xx_fsm_append_cmd(md->fsm_ctl, FSM_CMD_PRE_STOP, FSM_CMD_FLAG_WAIT_FOR_COMPLETION);
 	t7xx_port_proxy_uninit(md->port_prox);
+	t7xx_cldma_exit(md->md_ctrl[CLDMA_ID_AP]);
 	t7xx_cldma_exit(md->md_ctrl[CLDMA_ID_MD]);
 	t7xx_ccmni_exit(t7xx_dev);
 	t7xx_fsm_uninit(md);
diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.h b/drivers/net/wwan/t7xx/t7xx_modem_ops.h
index 7469ed636ae81..abe633cf7adc0 100644
--- a/drivers/net/wwan/t7xx/t7xx_modem_ops.h
+++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.h
@@ -66,10 +66,12 @@ struct t7xx_modem {
 	struct cldma_ctrl		*md_ctrl[CLDMA_NUM];
 	struct t7xx_pci_dev		*t7xx_dev;
 	struct t7xx_sys_info		core_md;
+	struct t7xx_sys_info		core_ap;
 	bool				md_init_finish;
 	bool				rgu_irq_asserted;
 	struct workqueue_struct		*handshake_wq;
 	struct work_struct		handshake_work;
+	struct work_struct		ap_handshake_work;
 	struct t7xx_fsm_ctl		*fsm_ctl;
 	struct port_proxy		*port_prox;
 	unsigned int			exp_id;
diff --git a/drivers/net/wwan/t7xx/t7xx_port.h b/drivers/net/wwan/t7xx/t7xx_port.h
index 8ea9079af997b..4ae8a00a85322 100644
--- a/drivers/net/wwan/t7xx/t7xx_port.h
+++ b/drivers/net/wwan/t7xx/t7xx_port.h
@@ -36,9 +36,13 @@
 /* Channel ID and Message ID definitions.
  * The channel number consists of peer_id(15:12) , channel_id(11:0)
  * peer_id:
- * 0:reserved, 1: to sAP, 2: to MD
+ * 0:reserved, 1: to AP, 2: to MD
  */
 enum port_ch {
+	/* to AP */
+	PORT_CH_AP_CONTROL_RX = 0x1000,
+	PORT_CH_AP_CONTROL_TX = 0x1001,
+
 	/* to MD */
 	PORT_CH_CONTROL_RX = 0x2000,
 	PORT_CH_CONTROL_TX = 0x2001,
diff --git a/drivers/net/wwan/t7xx/t7xx_port_ctrl_msg.c b/drivers/net/wwan/t7xx/t7xx_port_ctrl_msg.c
index 68430b130a678..ae632ef966983 100644
--- a/drivers/net/wwan/t7xx/t7xx_port_ctrl_msg.c
+++ b/drivers/net/wwan/t7xx/t7xx_port_ctrl_msg.c
@@ -167,8 +167,12 @@ static int control_msg_handler(struct t7xx_port *port, struct sk_buff *skb)
 	case CTL_ID_HS2_MSG:
 		skb_pull(skb, sizeof(*ctrl_msg_h));
 
-		if (port_conf->rx_ch == PORT_CH_CONTROL_RX) {
-			ret = t7xx_fsm_append_event(ctl, FSM_EVENT_MD_HS2, skb->data,
+		if (port_conf->rx_ch == PORT_CH_CONTROL_RX ||
+		    port_conf->rx_ch == PORT_CH_AP_CONTROL_RX) {
+			int event = port_conf->rx_ch == PORT_CH_CONTROL_RX ?
+				    FSM_EVENT_MD_HS2 : FSM_EVENT_AP_HS2;
+
+			ret = t7xx_fsm_append_event(ctl, event, skb->data,
 						    le32_to_cpu(ctrl_msg_h->data_length));
 			if (ret)
 				dev_err(port->dev, "Failed to append Handshake 2 event");
diff --git a/drivers/net/wwan/t7xx/t7xx_port_proxy.c b/drivers/net/wwan/t7xx/t7xx_port_proxy.c
index 894b1d11b2c9c..274846d39fbf3 100644
--- a/drivers/net/wwan/t7xx/t7xx_port_proxy.c
+++ b/drivers/net/wwan/t7xx/t7xx_port_proxy.c
@@ -48,7 +48,7 @@
 	     i < (proxy)->port_count;		\
 	     i++, (p) = &(proxy)->ports[i])
 
-static const struct t7xx_port_conf t7xx_md_port_conf[] = {
+static const struct t7xx_port_conf t7xx_port_conf[] = {
 	{
 		.tx_ch = PORT_CH_UART2_TX,
 		.rx_ch = PORT_CH_UART2_RX,
@@ -89,6 +89,14 @@ static const struct t7xx_port_conf t7xx_md_port_conf[] = {
 		.path_id = CLDMA_ID_MD,
 		.ops = &ctl_port_ops,
 		.name = "t7xx_ctrl",
+	}, {
+		.tx_ch = PORT_CH_AP_CONTROL_TX,
+		.rx_ch = PORT_CH_AP_CONTROL_RX,
+		.txq_index = Q_IDX_CTRL,
+		.rxq_index = Q_IDX_CTRL,
+		.path_id = CLDMA_ID_AP,
+		.ops = &ctl_port_ops,
+		.name = "t7xx_ap_ctrl",
 	},
 };
 
@@ -428,6 +436,9 @@ static void t7xx_proxy_init_all_ports(struct t7xx_modem *md)
 		if (port_conf->tx_ch == PORT_CH_CONTROL_TX)
 			md->core_md.ctl_port = port;
 
+		if (port_conf->tx_ch == PORT_CH_AP_CONTROL_TX)
+			md->core_ap.ctl_port = port;
+
 		port->t7xx_dev = md->t7xx_dev;
 		port->dev = &md->t7xx_dev->pdev->dev;
 		spin_lock_init(&port->port_update_lock);
@@ -442,7 +453,7 @@ static void t7xx_proxy_init_all_ports(struct t7xx_modem *md)
 
 static int t7xx_proxy_alloc(struct t7xx_modem *md)
 {
-	unsigned int port_count = ARRAY_SIZE(t7xx_md_port_conf);
+	unsigned int port_count = ARRAY_SIZE(t7xx_port_conf);
 	struct device *dev = &md->t7xx_dev->pdev->dev;
 	struct port_proxy *port_prox;
 	int i;
@@ -456,7 +467,7 @@ static int t7xx_proxy_alloc(struct t7xx_modem *md)
 	port_prox->dev = dev;
 
 	for (i = 0; i < port_count; i++)
-		port_prox->ports[i].port_conf = &t7xx_md_port_conf[i];
+		port_prox->ports[i].port_conf = &t7xx_port_conf[i];
 
 	port_prox->port_count = port_count;
 	t7xx_proxy_init_all_ports(md);
@@ -481,6 +492,7 @@ int t7xx_port_proxy_init(struct t7xx_modem *md)
 	if (ret)
 		return ret;
 
+	t7xx_cldma_set_recv_skb(md->md_ctrl[CLDMA_ID_AP], t7xx_port_proxy_recv_skb);
 	t7xx_cldma_set_recv_skb(md->md_ctrl[CLDMA_ID_MD], t7xx_port_proxy_recv_skb);
 	return 0;
 }
diff --git a/drivers/net/wwan/t7xx/t7xx_reg.h b/drivers/net/wwan/t7xx/t7xx_reg.h
index 7c1b81091a0f3..c41d7d094c085 100644
--- a/drivers/net/wwan/t7xx/t7xx_reg.h
+++ b/drivers/net/wwan/t7xx/t7xx_reg.h
@@ -56,7 +56,7 @@
 #define D2H_INT_RESUME_ACK			BIT(12)
 #define D2H_INT_SUSPEND_ACK_AP			BIT(13)
 #define D2H_INT_RESUME_ACK_AP			BIT(14)
-#define D2H_INT_ASYNC_SAP_HK			BIT(15)
+#define D2H_INT_ASYNC_AP_HK			BIT(15)
 #define D2H_INT_ASYNC_MD_HK			BIT(16)
 
 /* Register base */
diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.c b/drivers/net/wwan/t7xx/t7xx_state_monitor.c
index 0bcca08ff2bd0..80edb8e75a6ad 100644
--- a/drivers/net/wwan/t7xx/t7xx_state_monitor.c
+++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.c
@@ -285,8 +285,9 @@ static int fsm_routine_starting(struct t7xx_fsm_ctl *ctl)
 	t7xx_fsm_broadcast_state(ctl, MD_STATE_WAITING_FOR_HS1);
 	t7xx_md_event_notify(md, FSM_START);
 
-	wait_event_interruptible_timeout(ctl->async_hk_wq, md->core_md.ready || ctl->exp_flg,
-					 HZ * 60);
+	wait_event_interruptible_timeout(ctl->async_hk_wq,
+					 (md->core_md.ready && md->core_ap.ready) ||
+					  ctl->exp_flg, HZ * 60);
 	dev = &md->t7xx_dev->pdev->dev;
 
 	if (ctl->exp_flg)
@@ -297,6 +298,13 @@ static int fsm_routine_starting(struct t7xx_fsm_ctl *ctl)
 		if (md->core_md.handshake_ongoing)
 			t7xx_fsm_append_event(ctl, FSM_EVENT_MD_HS2_EXIT, NULL, 0);
 
+		fsm_routine_exception(ctl, NULL, EXCEPTION_HS_TIMEOUT);
+		return -ETIMEDOUT;
+	} else if (!md->core_ap.ready) {
+		dev_err(dev, "AP handshake timeout\n");
+		if (md->core_ap.handshake_ongoing)
+			t7xx_fsm_append_event(ctl, FSM_EVENT_AP_HS2_EXIT, NULL, 0);
+
 		fsm_routine_exception(ctl, NULL, EXCEPTION_HS_TIMEOUT);
 		return -ETIMEDOUT;
 	}
@@ -335,6 +343,7 @@ static void fsm_routine_start(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command
 		return;
 	}
 
+	t7xx_cldma_hif_hw_init(md->md_ctrl[CLDMA_ID_AP]);
 	t7xx_cldma_hif_hw_init(md->md_ctrl[CLDMA_ID_MD]);
 	fsm_finish_command(ctl, cmd, fsm_routine_starting(ctl));
 }
diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.h b/drivers/net/wwan/t7xx/t7xx_state_monitor.h
index b1af0259d4c55..b6e76f3903c89 100644
--- a/drivers/net/wwan/t7xx/t7xx_state_monitor.h
+++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.h
@@ -38,10 +38,12 @@ enum t7xx_fsm_state {
 enum t7xx_fsm_event_state {
 	FSM_EVENT_INVALID,
 	FSM_EVENT_MD_HS2,
+	FSM_EVENT_AP_HS2,
 	FSM_EVENT_MD_EX,
 	FSM_EVENT_MD_EX_REC_OK,
 	FSM_EVENT_MD_EX_PASS,
 	FSM_EVENT_MD_HS2_EXIT,
+	FSM_EVENT_AP_HS2_EXIT,
 	FSM_EVENT_MAX
 };
 
-- 
GitLab


From 02a6dfa8ff43efb1c989f87a4d862aedf436088a Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Thu, 13 Jul 2023 12:07:36 +0800
Subject: [PATCH 0089/1806] bpf, x86: save/restore regs with BPF_DW size

As we already reserve 8 byte in the stack for each reg, it is ok to
store/restore the regs in BPF_DW size. This will make the code in
save_regs()/restore_regs() simpler.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20230713040738.1789742-2-imagedong@tencent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 35 ++++++-----------------------------
 1 file changed, 6 insertions(+), 29 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 438adb695daab..fcbd3b7123a47 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1860,57 +1860,34 @@ emit_jmp:
 static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_regs,
 		      int stack_size)
 {
-	int i, j, arg_size;
-	bool next_same_struct = false;
+	int i;
 
 	/* Store function arguments to stack.
 	 * For a function that accepts two pointers the sequence will be:
 	 * mov QWORD PTR [rbp-0x10],rdi
 	 * mov QWORD PTR [rbp-0x8],rsi
 	 */
-	for (i = 0, j = 0; i < min(nr_regs, 6); i++) {
-		/* The arg_size is at most 16 bytes, enforced by the verifier. */
-		arg_size = m->arg_size[j];
-		if (arg_size > 8) {
-			arg_size = 8;
-			next_same_struct = !next_same_struct;
-		}
-
-		emit_stx(prog, bytes_to_bpf_size(arg_size),
-			 BPF_REG_FP,
+	for (i = 0; i < min(nr_regs, 6); i++)
+		emit_stx(prog, BPF_DW, BPF_REG_FP,
 			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
 			 -(stack_size - i * 8));
-
-		j = next_same_struct ? j : j + 1;
-	}
 }
 
 static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_regs,
 			 int stack_size)
 {
-	int i, j, arg_size;
-	bool next_same_struct = false;
+	int i;
 
 	/* Restore function arguments from stack.
 	 * For a function that accepts two pointers the sequence will be:
 	 * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10]
 	 * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8]
 	 */
-	for (i = 0, j = 0; i < min(nr_regs, 6); i++) {
-		/* The arg_size is at most 16 bytes, enforced by the verifier. */
-		arg_size = m->arg_size[j];
-		if (arg_size > 8) {
-			arg_size = 8;
-			next_same_struct = !next_same_struct;
-		}
-
-		emit_ldx(prog, bytes_to_bpf_size(arg_size),
+	for (i = 0; i < min(nr_regs, 6); i++)
+		emit_ldx(prog, BPF_DW,
 			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
 			 BPF_REG_FP,
 			 -(stack_size - i * 8));
-
-		j = next_same_struct ? j : j + 1;
-	}
 }
 
 static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
-- 
GitLab


From 473e3150e30a2db4199e6bad68c0be11279d1c34 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Thu, 13 Jul 2023 12:07:37 +0800
Subject: [PATCH 0090/1806] bpf, x86: allow function arguments up to 12 for
 TRACING

For now, the BPF program of type BPF_PROG_TYPE_TRACING can only be used
on the kernel functions whose arguments count less than or equal to 6, if
not considering '> 8 bytes' struct argument. This is not friendly at all,
as too many functions have arguments count more than 6.

According to the current kernel version, below is a statistics of the
function arguments count:

argument count | function count
7              | 704
8              | 270
9              | 84
10             | 47
11             | 47
12             | 27
13             | 22
14             | 5
15             | 0
16             | 1

Therefore, let's enhance it by increasing the function arguments count
allowed in arch_prepare_bpf_trampoline(), for now, only x86_64.

For the case that we don't need to call origin function, which means
without BPF_TRAMP_F_CALL_ORIG, we need only copy the function arguments
that stored in the frame of the caller to current frame. The 7th and later
arguments are stored in "$rbp + 0x18", and they will be copied to the
stack area following where register values are saved.

For the case with BPF_TRAMP_F_CALL_ORIG, we need prepare the arguments
in stack before call origin function, which means we need alloc extra
"8 * (arg_count - 6)" memory in the top of the stack. Note, there should
not be any data be pushed to the stack before calling the origin function.
So 'rbx' value will be stored on a stack position higher than where stack
arguments are stored for BPF_TRAMP_F_CALL_ORIG.

According to the research of Yonghong, struct members should be all in
register or all on the stack. Meanwhile, the compiler will pass the
argument on regs if the remaining regs can hold the argument. Therefore,
we need save the arguments in order. Otherwise, disorder of the args can
happen. For example:

  struct foo_struct {
      long a;
      int b;
  };
  int foo(char, char, char, char, char, struct foo_struct,
          char);

the arg1-5,arg7 will be passed by regs, and arg6 will by stack. Therefore,
we should save/restore the arguments in the same order with the
declaration of foo(). And the args used as ctx in stack will be like this:

  reg_arg6   -- copy from regs
  stack_arg2 -- copy from stack
  stack_arg1
  reg_arg5   -- copy from regs
  reg_arg4
  reg_arg3
  reg_arg2
  reg_arg1

We use EMIT3_off32() or EMIT4() for "lea" and "sub". The range of the
imm in "lea" and "sub" is [-128, 127] if EMIT4() is used. Therefore,
we use EMIT3_off32() instead if the imm out of the range.

It works well for the FENTRY/FEXIT/MODIFY_RETURN.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20230713040738.1789742-3-imagedong@tencent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 235 ++++++++++++++++++++++++++++++++----
 1 file changed, 209 insertions(+), 26 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index fcbd3b7123a47..5ab531be56acf 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1857,37 +1857,178 @@ emit_jmp:
 	return proglen;
 }
 
-static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_regs,
-		      int stack_size)
+static void clean_stack_garbage(const struct btf_func_model *m,
+				u8 **pprog, int nr_stack_slots,
+				int stack_size)
 {
-	int i;
+	int arg_size, off;
+	u8 *prog;
+
+	/* Generally speaking, the compiler will pass the arguments
+	 * on-stack with "push" instruction, which will take 8-byte
+	 * on the stack. In this case, there won't be garbage values
+	 * while we copy the arguments from origin stack frame to current
+	 * in BPF_DW.
+	 *
+	 * However, sometimes the compiler will only allocate 4-byte on
+	 * the stack for the arguments. For now, this case will only
+	 * happen if there is only one argument on-stack and its size
+	 * not more than 4 byte. In this case, there will be garbage
+	 * values on the upper 4-byte where we store the argument on
+	 * current stack frame.
+	 *
+	 * arguments on origin stack:
+	 *
+	 * stack_arg_1(4-byte) xxx(4-byte)
+	 *
+	 * what we copy:
+	 *
+	 * stack_arg_1(8-byte): stack_arg_1(origin) xxx
+	 *
+	 * and the xxx is the garbage values which we should clean here.
+	 */
+	if (nr_stack_slots != 1)
+		return;
+
+	/* the size of the last argument */
+	arg_size = m->arg_size[m->nr_args - 1];
+	if (arg_size <= 4) {
+		off = -(stack_size - 4);
+		prog = *pprog;
+		/* mov DWORD PTR [rbp + off], 0 */
+		if (!is_imm8(off))
+			EMIT2_off32(0xC7, 0x85, off);
+		else
+			EMIT3(0xC7, 0x45, off);
+		EMIT(0, 4);
+		*pprog = prog;
+	}
+}
+
+/* get the count of the regs that are used to pass arguments */
+static int get_nr_used_regs(const struct btf_func_model *m)
+{
+	int i, arg_regs, nr_used_regs = 0;
+
+	for (i = 0; i < min_t(int, m->nr_args, MAX_BPF_FUNC_ARGS); i++) {
+		arg_regs = (m->arg_size[i] + 7) / 8;
+		if (nr_used_regs + arg_regs <= 6)
+			nr_used_regs += arg_regs;
+
+		if (nr_used_regs >= 6)
+			break;
+	}
+
+	return nr_used_regs;
+}
+
+static void save_args(const struct btf_func_model *m, u8 **prog,
+		      int stack_size, bool for_call_origin)
+{
+	int arg_regs, first_off, nr_regs = 0, nr_stack_slots = 0;
+	int i, j;
 
 	/* Store function arguments to stack.
 	 * For a function that accepts two pointers the sequence will be:
 	 * mov QWORD PTR [rbp-0x10],rdi
 	 * mov QWORD PTR [rbp-0x8],rsi
 	 */
-	for (i = 0; i < min(nr_regs, 6); i++)
-		emit_stx(prog, BPF_DW, BPF_REG_FP,
-			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
-			 -(stack_size - i * 8));
+	for (i = 0; i < min_t(int, m->nr_args, MAX_BPF_FUNC_ARGS); i++) {
+		arg_regs = (m->arg_size[i] + 7) / 8;
+
+		/* According to the research of Yonghong, struct members
+		 * should be all in register or all on the stack.
+		 * Meanwhile, the compiler will pass the argument on regs
+		 * if the remaining regs can hold the argument.
+		 *
+		 * Disorder of the args can happen. For example:
+		 *
+		 * struct foo_struct {
+		 *     long a;
+		 *     int b;
+		 * };
+		 * int foo(char, char, char, char, char, struct foo_struct,
+		 *         char);
+		 *
+		 * the arg1-5,arg7 will be passed by regs, and arg6 will
+		 * by stack.
+		 */
+		if (nr_regs + arg_regs > 6) {
+			/* copy function arguments from origin stack frame
+			 * into current stack frame.
+			 *
+			 * The starting address of the arguments on-stack
+			 * is:
+			 *   rbp + 8(push rbp) +
+			 *   8(return addr of origin call) +
+			 *   8(return addr of the caller)
+			 * which means: rbp + 24
+			 */
+			for (j = 0; j < arg_regs; j++) {
+				emit_ldx(prog, BPF_DW, BPF_REG_0, BPF_REG_FP,
+					 nr_stack_slots * 8 + 0x18);
+				emit_stx(prog, BPF_DW, BPF_REG_FP, BPF_REG_0,
+					 -stack_size);
+
+				if (!nr_stack_slots)
+					first_off = stack_size;
+				stack_size -= 8;
+				nr_stack_slots++;
+			}
+		} else {
+			/* Only copy the arguments on-stack to current
+			 * 'stack_size' and ignore the regs, used to
+			 * prepare the arguments on-stack for orign call.
+			 */
+			if (for_call_origin) {
+				nr_regs += arg_regs;
+				continue;
+			}
+
+			/* copy the arguments from regs into stack */
+			for (j = 0; j < arg_regs; j++) {
+				emit_stx(prog, BPF_DW, BPF_REG_FP,
+					 nr_regs == 5 ? X86_REG_R9 : BPF_REG_1 + nr_regs,
+					 -stack_size);
+				stack_size -= 8;
+				nr_regs++;
+			}
+		}
+	}
+
+	clean_stack_garbage(m, prog, nr_stack_slots, first_off);
 }
 
-static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_regs,
+static void restore_regs(const struct btf_func_model *m, u8 **prog,
 			 int stack_size)
 {
-	int i;
+	int i, j, arg_regs, nr_regs = 0;
 
 	/* Restore function arguments from stack.
 	 * For a function that accepts two pointers the sequence will be:
 	 * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10]
 	 * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8]
+	 *
+	 * The logic here is similar to what we do in save_args()
 	 */
-	for (i = 0; i < min(nr_regs, 6); i++)
-		emit_ldx(prog, BPF_DW,
-			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
-			 BPF_REG_FP,
-			 -(stack_size - i * 8));
+	for (i = 0; i < min_t(int, m->nr_args, MAX_BPF_FUNC_ARGS); i++) {
+		arg_regs = (m->arg_size[i] + 7) / 8;
+		if (nr_regs + arg_regs <= 6) {
+			for (j = 0; j < arg_regs; j++) {
+				emit_ldx(prog, BPF_DW,
+					 nr_regs == 5 ? X86_REG_R9 : BPF_REG_1 + nr_regs,
+					 BPF_REG_FP,
+					 -stack_size);
+				stack_size -= 8;
+				nr_regs++;
+			}
+		} else {
+			stack_size -= 8 * arg_regs;
+		}
+
+		if (nr_regs >= 6)
+			break;
+	}
 }
 
 static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
@@ -1915,7 +2056,10 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	/* arg1: mov rdi, progs[i] */
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
 	/* arg2: lea rsi, [rbp - ctx_cookie_off] */
-	EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
+	if (!is_imm8(-run_ctx_off))
+		EMIT3_off32(0x48, 0x8D, 0xB5, -run_ctx_off);
+	else
+		EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
 
 	if (emit_rsb_call(&prog, bpf_trampoline_enter(p), prog))
 		return -EINVAL;
@@ -1931,7 +2075,10 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	emit_nops(&prog, 2);
 
 	/* arg1: lea rdi, [rbp - stack_size] */
-	EMIT4(0x48, 0x8D, 0x7D, -stack_size);
+	if (!is_imm8(-stack_size))
+		EMIT3_off32(0x48, 0x8D, 0xBD, -stack_size);
+	else
+		EMIT4(0x48, 0x8D, 0x7D, -stack_size);
 	/* arg2: progs[i]->insnsi for interpreter */
 	if (!p->jited)
 		emit_mov_imm64(&prog, BPF_REG_2,
@@ -1961,7 +2108,10 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	/* arg2: mov rsi, rbx <- start time in nsec */
 	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
 	/* arg3: lea rdx, [rbp - run_ctx_off] */
-	EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
+	if (!is_imm8(-run_ctx_off))
+		EMIT3_off32(0x48, 0x8D, 0x95, -run_ctx_off);
+	else
+		EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
 	if (emit_rsb_call(&prog, bpf_trampoline_exit(p), prog))
 		return -EINVAL;
 
@@ -2113,7 +2263,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 				void *func_addr)
 {
 	int i, ret, nr_regs = m->nr_args, stack_size = 0;
-	int regs_off, nregs_off, ip_off, run_ctx_off;
+	int regs_off, nregs_off, ip_off, run_ctx_off, arg_stack_off, rbx_off;
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
@@ -2127,8 +2277,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
 			nr_regs += (m->arg_size[i] + 7) / 8 - 1;
 
-	/* x86-64 supports up to 6 arguments. 7+ can be added in the future */
-	if (nr_regs > 6)
+	/* x86-64 supports up to MAX_BPF_FUNC_ARGS arguments. 1-6
+	 * are passed through regs, the remains are through stack.
+	 */
+	if (nr_regs > MAX_BPF_FUNC_ARGS)
 		return -ENOTSUPP;
 
 	/* Generated trampoline stack layout:
@@ -2147,7 +2299,14 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	 *
 	 * RBP - ip_off    [ traced function ]  BPF_TRAMP_F_IP_ARG flag
 	 *
+	 * RBP - rbx_off   [ rbx value       ]  always
+	 *
 	 * RBP - run_ctx_off [ bpf_tramp_run_ctx ]
+	 *
+	 *                     [ stack_argN ]  BPF_TRAMP_F_CALL_ORIG
+	 *                     [ ...        ]
+	 *                     [ stack_arg2 ]
+	 * RBP - arg_stack_off [ stack_arg1 ]
 	 */
 
 	/* room for return value of orig_call or fentry prog */
@@ -2167,9 +2326,26 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 
 	ip_off = stack_size;
 
+	stack_size += 8;
+	rbx_off = stack_size;
+
 	stack_size += (sizeof(struct bpf_tramp_run_ctx) + 7) & ~0x7;
 	run_ctx_off = stack_size;
 
+	if (nr_regs > 6 && (flags & BPF_TRAMP_F_CALL_ORIG)) {
+		/* the space that used to pass arguments on-stack */
+		stack_size += (nr_regs - get_nr_used_regs(m)) * 8;
+		/* make sure the stack pointer is 16-byte aligned if we
+		 * need pass arguments on stack, which means
+		 *  [stack_size + 8(rbp) + 8(rip) + 8(origin rip)]
+		 * should be 16-byte aligned. Following code depend on
+		 * that stack_size is already 8-byte aligned.
+		 */
+		stack_size += (stack_size % 16) ? 0 : 8;
+	}
+
+	arg_stack_off = stack_size;
+
 	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
@@ -2189,8 +2365,14 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	x86_call_depth_emit_accounting(&prog, NULL);
 	EMIT1(0x55);		 /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
-	EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */
-	EMIT1(0x53);		 /* push rbx */
+	if (!is_imm8(stack_size))
+		/* sub rsp, stack_size */
+		EMIT3_off32(0x48, 0x81, 0xEC, stack_size);
+	else
+		/* sub rsp, stack_size */
+		EMIT4(0x48, 0x83, 0xEC, stack_size);
+	/* mov QWORD PTR [rbp - rbx_off], rbx */
+	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_6, -rbx_off);
 
 	/* Store number of argument registers of the traced function:
 	 *   mov rax, nr_regs
@@ -2208,7 +2390,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off);
 	}
 
-	save_regs(m, &prog, nr_regs, regs_off);
+	save_args(m, &prog, regs_off, false);
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		/* arg1: mov rdi, im */
@@ -2238,7 +2420,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	}
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		restore_regs(m, &prog, nr_regs, regs_off);
+		restore_regs(m, &prog, regs_off);
+		save_args(m, &prog, arg_stack_off, true);
 
 		if (flags & BPF_TRAMP_F_ORIG_STACK) {
 			emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8);
@@ -2279,7 +2462,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		}
 
 	if (flags & BPF_TRAMP_F_RESTORE_REGS)
-		restore_regs(m, &prog, nr_regs, regs_off);
+		restore_regs(m, &prog, regs_off);
 
 	/* This needs to be done regardless. If there were fmod_ret programs,
 	 * the return value is only updated on the stack and still needs to be
@@ -2298,7 +2481,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (save_ret)
 		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
 
-	EMIT1(0x5B); /* pop rbx */
+	emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, -rbx_off);
 	EMIT1(0xC9); /* leave */
 	if (flags & BPF_TRAMP_F_SKIP_FRAME)
 		/* skip our return address and return to parent */
-- 
GitLab


From 5e9cf77d81f9ba51019157dc55a3b73dc89a7cf4 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Thu, 13 Jul 2023 12:07:38 +0800
Subject: [PATCH 0091/1806] selftests/bpf: add testcase for TRACING with 6+
 arguments

Add fentry_many_args.c and fexit_many_args.c to test the fentry/fexit
with 7/11 arguments. As this feature is not supported by arm64 yet, we
disable these testcases for arm64 in DENYLIST.aarch64. We can combine
them with fentry_test.c/fexit_test.c when arm64 is supported too.

Correspondingly, add bpf_testmod_fentry_test7() and
bpf_testmod_fentry_test11() to bpf_testmod.c

Meanwhile, add bpf_modify_return_test2() to test_run.c to test the
MODIFY_RETURN with 7 arguments.

Add bpf_testmod_test_struct_arg_7/bpf_testmod_test_struct_arg_7 in
bpf_testmod.c to test the struct in the arguments.

And the testcases passed on x86_64:

./test_progs -t fexit
Summary: 5/14 PASSED, 0 SKIPPED, 0 FAILED

./test_progs -t fentry
Summary: 3/2 PASSED, 0 SKIPPED, 0 FAILED

./test_progs -t modify_return
Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED

./test_progs -t tracing_struct
Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20230713040738.1789742-4-imagedong@tencent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/bpf/test_run.c                            | 14 ++++-
 tools/testing/selftests/bpf/DENYLIST.aarch64  |  2 +
 .../selftests/bpf/bpf_testmod/bpf_testmod.c   | 49 ++++++++++++++++-
 .../selftests/bpf/prog_tests/fentry_test.c    | 43 +++++++++++++--
 .../selftests/bpf/prog_tests/fexit_test.c     | 43 +++++++++++++--
 .../bpf/prog_tests/get_func_args_test.c       |  4 +-
 .../selftests/bpf/prog_tests/modify_return.c  | 10 ++--
 .../selftests/bpf/prog_tests/tracing_struct.c | 19 +++++++
 .../bpf/prog_tests/trampoline_count.c         |  4 +-
 .../selftests/bpf/progs/fentry_many_args.c    | 39 ++++++++++++++
 .../selftests/bpf/progs/fexit_many_args.c     | 40 ++++++++++++++
 .../selftests/bpf/progs/modify_return.c       | 40 ++++++++++++++
 .../selftests/bpf/progs/tracing_struct.c      | 54 +++++++++++++++++++
 13 files changed, 345 insertions(+), 16 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/fentry_many_args.c
 create mode 100644 tools/testing/selftests/bpf/progs/fexit_many_args.c

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 63b11f7a5392b..7d47f53f20c10 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -565,6 +565,13 @@ __bpf_kfunc int bpf_modify_return_test(int a, int *b)
 	return a + *b;
 }
 
+__bpf_kfunc int bpf_modify_return_test2(int a, int *b, short c, int d,
+					void *e, char f, int g)
+{
+	*b += 1;
+	return a + *b + c + d + (long)e + f + g;
+}
+
 int noinline bpf_fentry_shadow_test(int a)
 {
 	return a + 1;
@@ -600,6 +607,7 @@ __diag_pop();
 
 BTF_SET8_START(bpf_test_modify_return_ids)
 BTF_ID_FLAGS(func, bpf_modify_return_test)
+BTF_ID_FLAGS(func, bpf_modify_return_test2)
 BTF_ID_FLAGS(func, bpf_fentry_test1, KF_SLEEPABLE)
 BTF_SET8_END(bpf_test_modify_return_ids)
 
@@ -667,7 +675,11 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
 	case BPF_MODIFY_RETURN:
 		ret = bpf_modify_return_test(1, &b);
 		if (b != 2)
-			side_effect = 1;
+			side_effect++;
+		b = 2;
+		ret += bpf_modify_return_test2(1, &b, 3, 4, (void *)5, 6, 7);
+		if (b != 2)
+			side_effect++;
 		break;
 	default:
 		goto out;
diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64
index 08adc805878bb..3b61e8b35d620 100644
--- a/tools/testing/selftests/bpf/DENYLIST.aarch64
+++ b/tools/testing/selftests/bpf/DENYLIST.aarch64
@@ -10,3 +10,5 @@ kprobe_multi_test/link_api_addrs                 # link_fd unexpected link_fd: a
 kprobe_multi_test/link_api_syms                  # link_fd unexpected link_fd: actual -95 < expected 0
 kprobe_multi_test/skel_api                       # libbpf: failed to load BPF skeleton 'kprobe_multi': -3
 module_attach                                    # prog 'kprobe_multi': failed to auto-attach: -95
+fentry_test/fentry_many_args                     # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524
+fexit_test/fexit_many_args                       # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index aaf6ef1201c7b..a6f991b56345d 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -34,6 +34,11 @@ struct bpf_testmod_struct_arg_3 {
 	int b[];
 };
 
+struct bpf_testmod_struct_arg_4 {
+	u64 a;
+	int b;
+};
+
 __diag_push();
 __diag_ignore_all("-Wmissing-prototypes",
 		  "Global functions as their definitions will be in bpf_testmod.ko BTF");
@@ -75,6 +80,24 @@ bpf_testmod_test_struct_arg_6(struct bpf_testmod_struct_arg_3 *a) {
 	return bpf_testmod_test_struct_arg_result;
 }
 
+noinline int
+bpf_testmod_test_struct_arg_7(u64 a, void *b, short c, int d, void *e,
+			      struct bpf_testmod_struct_arg_4 f)
+{
+	bpf_testmod_test_struct_arg_result = a + (long)b + c + d +
+		(long)e + f.a + f.b;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_struct_arg_8(u64 a, void *b, short c, int d, void *e,
+			      struct bpf_testmod_struct_arg_4 f, int g)
+{
+	bpf_testmod_test_struct_arg_result = a + (long)b + c + d +
+		(long)e + f.a + f.b + g;
+	return bpf_testmod_test_struct_arg_result;
+}
+
 __bpf_kfunc void
 bpf_testmod_test_mod_kfunc(int i)
 {
@@ -191,6 +214,20 @@ noinline int bpf_testmod_fentry_test3(char a, int b, u64 c)
 	return a + b + c;
 }
 
+noinline int bpf_testmod_fentry_test7(u64 a, void *b, short c, int d,
+				      void *e, char f, int g)
+{
+	return a + (long)b + c + d + (long)e + f + g;
+}
+
+noinline int bpf_testmod_fentry_test11(u64 a, void *b, short c, int d,
+				       void *e, char f, int g,
+				       unsigned int h, long i, __u64 j,
+				       unsigned long k)
+{
+	return a + (long)b + c + d + (long)e + f + g + h + i + j + k;
+}
+
 int bpf_testmod_fentry_ok;
 
 noinline ssize_t
@@ -206,6 +243,7 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 	struct bpf_testmod_struct_arg_1 struct_arg1 = {10};
 	struct bpf_testmod_struct_arg_2 struct_arg2 = {2, 3};
 	struct bpf_testmod_struct_arg_3 *struct_arg3;
+	struct bpf_testmod_struct_arg_4 struct_arg4 = {21, 22};
 	int i = 1;
 
 	while (bpf_testmod_return_ptr(i))
@@ -216,6 +254,11 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 	(void)bpf_testmod_test_struct_arg_3(1, 4, struct_arg2);
 	(void)bpf_testmod_test_struct_arg_4(struct_arg1, 1, 2, 3, struct_arg2);
 	(void)bpf_testmod_test_struct_arg_5();
+	(void)bpf_testmod_test_struct_arg_7(16, (void *)17, 18, 19,
+					    (void *)20, struct_arg4);
+	(void)bpf_testmod_test_struct_arg_8(16, (void *)17, 18, 19,
+					    (void *)20, struct_arg4, 23);
+
 
 	struct_arg3 = kmalloc((sizeof(struct bpf_testmod_struct_arg_3) +
 				sizeof(int)), GFP_KERNEL);
@@ -243,7 +286,11 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 
 	if (bpf_testmod_fentry_test1(1) != 2 ||
 	    bpf_testmod_fentry_test2(2, 3) != 5 ||
-	    bpf_testmod_fentry_test3(4, 5, 6) != 15)
+	    bpf_testmod_fentry_test3(4, 5, 6) != 15 ||
+	    bpf_testmod_fentry_test7(16, (void *)17, 18, 19, (void *)20,
+			21, 22) != 133 ||
+	    bpf_testmod_fentry_test11(16, (void *)17, 18, 19, (void *)20,
+			21, 22, 23, 24, 25, 26) != 231)
 		goto out;
 
 	bpf_testmod_fentry_ok = 1;
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index c0d1d61d5f666..aee1bc77a17f7 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -2,8 +2,9 @@
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
 #include "fentry_test.lskel.h"
+#include "fentry_many_args.skel.h"
 
-static int fentry_test(struct fentry_test_lskel *fentry_skel)
+static int fentry_test_common(struct fentry_test_lskel *fentry_skel)
 {
 	int err, prog_fd, i;
 	int link_fd;
@@ -37,7 +38,7 @@ static int fentry_test(struct fentry_test_lskel *fentry_skel)
 	return 0;
 }
 
-void test_fentry_test(void)
+static void fentry_test(void)
 {
 	struct fentry_test_lskel *fentry_skel = NULL;
 	int err;
@@ -46,13 +47,47 @@ void test_fentry_test(void)
 	if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
 		goto cleanup;
 
-	err = fentry_test(fentry_skel);
+	err = fentry_test_common(fentry_skel);
 	if (!ASSERT_OK(err, "fentry_first_attach"))
 		goto cleanup;
 
-	err = fentry_test(fentry_skel);
+	err = fentry_test_common(fentry_skel);
 	ASSERT_OK(err, "fentry_second_attach");
 
 cleanup:
 	fentry_test_lskel__destroy(fentry_skel);
 }
+
+static void fentry_many_args(void)
+{
+	struct fentry_many_args *fentry_skel = NULL;
+	int err;
+
+	fentry_skel = fentry_many_args__open_and_load();
+	if (!ASSERT_OK_PTR(fentry_skel, "fentry_many_args_skel_load"))
+		goto cleanup;
+
+	err = fentry_many_args__attach(fentry_skel);
+	if (!ASSERT_OK(err, "fentry_many_args_attach"))
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(1), "trigger_read");
+
+	ASSERT_EQ(fentry_skel->bss->test1_result, 1,
+		  "fentry_many_args_result1");
+	ASSERT_EQ(fentry_skel->bss->test2_result, 1,
+		  "fentry_many_args_result2");
+	ASSERT_EQ(fentry_skel->bss->test3_result, 1,
+		  "fentry_many_args_result3");
+
+cleanup:
+	fentry_many_args__destroy(fentry_skel);
+}
+
+void test_fentry_test(void)
+{
+	if (test__start_subtest("fentry"))
+		fentry_test();
+	if (test__start_subtest("fentry_many_args"))
+		fentry_many_args();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index 101b7343036b2..1c13007e37dd2 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -2,8 +2,9 @@
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
 #include "fexit_test.lskel.h"
+#include "fexit_many_args.skel.h"
 
-static int fexit_test(struct fexit_test_lskel *fexit_skel)
+static int fexit_test_common(struct fexit_test_lskel *fexit_skel)
 {
 	int err, prog_fd, i;
 	int link_fd;
@@ -37,7 +38,7 @@ static int fexit_test(struct fexit_test_lskel *fexit_skel)
 	return 0;
 }
 
-void test_fexit_test(void)
+static void fexit_test(void)
 {
 	struct fexit_test_lskel *fexit_skel = NULL;
 	int err;
@@ -46,13 +47,47 @@ void test_fexit_test(void)
 	if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
 		goto cleanup;
 
-	err = fexit_test(fexit_skel);
+	err = fexit_test_common(fexit_skel);
 	if (!ASSERT_OK(err, "fexit_first_attach"))
 		goto cleanup;
 
-	err = fexit_test(fexit_skel);
+	err = fexit_test_common(fexit_skel);
 	ASSERT_OK(err, "fexit_second_attach");
 
 cleanup:
 	fexit_test_lskel__destroy(fexit_skel);
 }
+
+static void fexit_many_args(void)
+{
+	struct fexit_many_args *fexit_skel = NULL;
+	int err;
+
+	fexit_skel = fexit_many_args__open_and_load();
+	if (!ASSERT_OK_PTR(fexit_skel, "fexit_many_args_skel_load"))
+		goto cleanup;
+
+	err = fexit_many_args__attach(fexit_skel);
+	if (!ASSERT_OK(err, "fexit_many_args_attach"))
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(1), "trigger_read");
+
+	ASSERT_EQ(fexit_skel->bss->test1_result, 1,
+		  "fexit_many_args_result1");
+	ASSERT_EQ(fexit_skel->bss->test2_result, 1,
+		  "fexit_many_args_result2");
+	ASSERT_EQ(fexit_skel->bss->test3_result, 1,
+		  "fexit_many_args_result3");
+
+cleanup:
+	fexit_many_args__destroy(fexit_skel);
+}
+
+void test_fexit_test(void)
+{
+	if (test__start_subtest("fexit"))
+		fexit_test();
+	if (test__start_subtest("fexit_many_args"))
+		fexit_many_args();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
index 28cf63963cb79..64a9c95d4acf6 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
@@ -30,7 +30,9 @@ void test_get_func_args_test(void)
 	prog_fd = bpf_program__fd(skel->progs.fmod_ret_test);
 	err = bpf_prog_test_run_opts(prog_fd, &topts);
 	ASSERT_OK(err, "test_run");
-	ASSERT_EQ(topts.retval, 1234, "test_run");
+
+	ASSERT_EQ(topts.retval >> 16, 1, "test_run");
+	ASSERT_EQ(topts.retval & 0xffff, 1234 + 29, "test_run");
 
 	ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
 	ASSERT_EQ(skel->bss->test2_result, 1, "test2_result");
diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c
index 5d9955af62475..a70c99c2f8c83 100644
--- a/tools/testing/selftests/bpf/prog_tests/modify_return.c
+++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c
@@ -41,6 +41,10 @@ static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret)
 	ASSERT_EQ(skel->bss->fexit_result, 1, "modify_return fexit_result");
 	ASSERT_EQ(skel->bss->fmod_ret_result, 1, "modify_return fmod_ret_result");
 
+	ASSERT_EQ(skel->bss->fentry_result2, 1, "modify_return fentry_result2");
+	ASSERT_EQ(skel->bss->fexit_result2, 1, "modify_return fexit_result2");
+	ASSERT_EQ(skel->bss->fmod_ret_result2, 1, "modify_return fmod_ret_result2");
+
 cleanup:
 	modify_return__destroy(skel);
 }
@@ -49,9 +53,9 @@ cleanup:
 void serial_test_modify_return(void)
 {
 	run_test(0 /* input_retval */,
-		 1 /* want_side_effect */,
-		 4 /* want_ret */);
+		 2 /* want_side_effect */,
+		 33 /* want_ret */);
 	run_test(-EINVAL /* input_retval */,
 		 0 /* want_side_effect */,
-		 -EINVAL /* want_ret */);
+		 -EINVAL * 2 /* want_ret */);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
index 1c75a32186d68..fe0fb0c9849ad 100644
--- a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
@@ -55,6 +55,25 @@ static void test_fentry(void)
 
 	ASSERT_EQ(skel->bss->t6, 1, "t6 ret");
 
+	ASSERT_EQ(skel->bss->t7_a, 16, "t7:a");
+	ASSERT_EQ(skel->bss->t7_b, 17, "t7:b");
+	ASSERT_EQ(skel->bss->t7_c, 18, "t7:c");
+	ASSERT_EQ(skel->bss->t7_d, 19, "t7:d");
+	ASSERT_EQ(skel->bss->t7_e, 20, "t7:e");
+	ASSERT_EQ(skel->bss->t7_f_a, 21, "t7:f.a");
+	ASSERT_EQ(skel->bss->t7_f_b, 22, "t7:f.b");
+	ASSERT_EQ(skel->bss->t7_ret, 133, "t7 ret");
+
+	ASSERT_EQ(skel->bss->t8_a, 16, "t8:a");
+	ASSERT_EQ(skel->bss->t8_b, 17, "t8:b");
+	ASSERT_EQ(skel->bss->t8_c, 18, "t8:c");
+	ASSERT_EQ(skel->bss->t8_d, 19, "t8:d");
+	ASSERT_EQ(skel->bss->t8_e, 20, "t8:e");
+	ASSERT_EQ(skel->bss->t8_f_a, 21, "t8:f.a");
+	ASSERT_EQ(skel->bss->t8_f_b, 22, "t8:f.b");
+	ASSERT_EQ(skel->bss->t8_g, 23, "t8:g");
+	ASSERT_EQ(skel->bss->t8_ret, 156, "t8 ret");
+
 	tracing_struct__detach(skel);
 destroy_skel:
 	tracing_struct__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
index e91d0d1769f1e..6cd7349d4a2ba 100644
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -88,8 +88,8 @@ void serial_test_trampoline_count(void)
 	if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
 		goto cleanup;
 
-	ASSERT_EQ(opts.retval & 0xffff, 4, "bpf_modify_return_test.result");
-	ASSERT_EQ(opts.retval >> 16, 1, "bpf_modify_return_test.side_effect");
+	ASSERT_EQ(opts.retval & 0xffff, 33, "bpf_modify_return_test.result");
+	ASSERT_EQ(opts.retval >> 16, 2, "bpf_modify_return_test.side_effect");
 
 cleanup:
 	for (; i >= 0; i--) {
diff --git a/tools/testing/selftests/bpf/progs/fentry_many_args.c b/tools/testing/selftests/bpf/progs/fentry_many_args.c
new file mode 100644
index 0000000000000..b61bb92fee2c5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_many_args.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Tencent */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_result = 0;
+SEC("fentry/bpf_testmod_fentry_test7")
+int BPF_PROG(test1, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g)
+{
+	test1_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22;
+	return 0;
+}
+
+__u64 test2_result = 0;
+SEC("fentry/bpf_testmod_fentry_test11")
+int BPF_PROG(test2, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g, unsigned int h, long i, __u64 j, unsigned long k)
+{
+	test2_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26;
+	return 0;
+}
+
+__u64 test3_result = 0;
+SEC("fentry/bpf_testmod_fentry_test11")
+int BPF_PROG(test3, __u64 a, __u64 b, __u64 c, __u64 d, __u64 e, __u64 f,
+	     __u64 g, __u64 h, __u64 i, __u64 j, __u64 k)
+{
+	test3_result = a == 16 && b == 17 && c == 18 && d == 19 &&
+		e == 20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/fexit_many_args.c b/tools/testing/selftests/bpf/progs/fexit_many_args.c
new file mode 100644
index 0000000000000..53b335c2dafb2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fexit_many_args.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Tencent */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_result = 0;
+SEC("fexit/bpf_testmod_fentry_test7")
+int BPF_PROG(test1, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g, int ret)
+{
+	test1_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22 && ret == 133;
+	return 0;
+}
+
+__u64 test2_result = 0;
+SEC("fexit/bpf_testmod_fentry_test11")
+int BPF_PROG(test2, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g, unsigned int h, long i, __u64 j, unsigned long k,
+	     int ret)
+{
+	test2_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26 && ret == 231;
+	return 0;
+}
+
+__u64 test3_result = 0;
+SEC("fexit/bpf_testmod_fentry_test11")
+int BPF_PROG(test3, __u64 a, __u64 b, __u64 c, __u64 d, __u64 e, __u64 f,
+	     __u64 g, __u64 h, __u64 i, __u64 j, __u64 k, __u64 ret)
+{
+	test3_result = a == 16 && b == 17 && c == 18 && d == 19 &&
+		e == 20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26 && ret == 231;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/modify_return.c b/tools/testing/selftests/bpf/progs/modify_return.c
index 8b7466a15c6b1..3376d4849f585 100644
--- a/tools/testing/selftests/bpf/progs/modify_return.c
+++ b/tools/testing/selftests/bpf/progs/modify_return.c
@@ -47,3 +47,43 @@ int BPF_PROG(fexit_test, int a, __u64 b, int ret)
 
 	return 0;
 }
+
+static int sequence2;
+
+__u64 fentry_result2 = 0;
+SEC("fentry/bpf_modify_return_test2")
+int BPF_PROG(fentry_test2, int a, int *b, short c, int d, void *e, char f,
+	     int g)
+{
+	sequence2++;
+	fentry_result2 = (sequence2 == 1);
+	return 0;
+}
+
+__u64 fmod_ret_result2 = 0;
+SEC("fmod_ret/bpf_modify_return_test2")
+int BPF_PROG(fmod_ret_test2, int a, int *b, short c, int d, void *e, char f,
+	     int g, int ret)
+{
+	sequence2++;
+	/* This is the first fmod_ret program, the ret passed should be 0 */
+	fmod_ret_result2 = (sequence2 == 2 && ret == 0);
+	return input_retval;
+}
+
+__u64 fexit_result2 = 0;
+SEC("fexit/bpf_modify_return_test2")
+int BPF_PROG(fexit_test2, int a, int *b, short c, int d, void *e, char f,
+	     int g, int ret)
+{
+	sequence2++;
+	/* If the input_reval is non-zero a successful modification should have
+	 * occurred.
+	 */
+	if (input_retval)
+		fexit_result2 = (sequence2 == 3 && ret == input_retval);
+	else
+		fexit_result2 = (sequence2 == 3 && ret == 29);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/tracing_struct.c b/tools/testing/selftests/bpf/progs/tracing_struct.c
index c435a3a8328ab..515daef3c84ba 100644
--- a/tools/testing/selftests/bpf/progs/tracing_struct.c
+++ b/tools/testing/selftests/bpf/progs/tracing_struct.c
@@ -18,6 +18,11 @@ struct bpf_testmod_struct_arg_3 {
 	int b[];
 };
 
+struct bpf_testmod_struct_arg_4 {
+	u64 a;
+	int b;
+};
+
 long t1_a_a, t1_a_b, t1_b, t1_c, t1_ret, t1_nregs;
 __u64 t1_reg0, t1_reg1, t1_reg2, t1_reg3;
 long t2_a, t2_b_a, t2_b_b, t2_c, t2_ret;
@@ -25,6 +30,9 @@ long t3_a, t3_b, t3_c_a, t3_c_b, t3_ret;
 long t4_a_a, t4_b, t4_c, t4_d, t4_e_a, t4_e_b, t4_ret;
 long t5_ret;
 int t6;
+long t7_a, t7_b, t7_c, t7_d, t7_e, t7_f_a, t7_f_b, t7_ret;
+long t8_a, t8_b, t8_c, t8_d, t8_e, t8_f_a, t8_f_b, t8_g, t8_ret;
+
 
 SEC("fentry/bpf_testmod_test_struct_arg_1")
 int BPF_PROG2(test_struct_arg_1, struct bpf_testmod_struct_arg_2, a, int, b, int, c)
@@ -130,4 +138,50 @@ int BPF_PROG2(test_struct_arg_11, struct bpf_testmod_struct_arg_3 *, a)
 	return 0;
 }
 
+SEC("fentry/bpf_testmod_test_struct_arg_7")
+int BPF_PROG2(test_struct_arg_12, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f)
+{
+	t7_a = a;
+	t7_b = (long)b;
+	t7_c = c;
+	t7_d = d;
+	t7_e = (long)e;
+	t7_f_a = f.a;
+	t7_f_b = f.b;
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_test_struct_arg_7")
+int BPF_PROG2(test_struct_arg_13, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f, int, ret)
+{
+	t7_ret = ret;
+	return 0;
+}
+
+SEC("fentry/bpf_testmod_test_struct_arg_8")
+int BPF_PROG2(test_struct_arg_14, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f, int, g)
+{
+	t8_a = a;
+	t8_b = (long)b;
+	t8_c = c;
+	t8_d = d;
+	t8_e = (long)e;
+	t8_f_a = f.a;
+	t8_f_b = f.b;
+	t8_g = g;
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_test_struct_arg_8")
+int BPF_PROG2(test_struct_arg_15, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f, int, g,
+	      int, ret)
+{
+	t8_ret = ret;
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
GitLab


From 7ce4dc3e4a9d954c8a1fb483c7a527e9b060b860 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Thu, 13 Jul 2023 02:56:39 +0000
Subject: [PATCH 0092/1806] bpf: Fix an error around PTR_UNTRUSTED

Per discussion with Alexei, the PTR_UNTRUSTED flag should not been
cleared when we start to walk a new struct, because the struct in
question may be a struct nested in a union. We should also check and set
this flag before we walk its each member, in case itself is a union.
We will clear this flag if the field is BTF_TYPE_SAFE_RCU_OR_NULL.

Fixes: 6fcd486b3a0a ("bpf: Refactor RCU enforcement in the verifier.")
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Link: https://lore.kernel.org/r/20230713025642.27477-2-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c      | 20 +++++++++-----------
 kernel/bpf/verifier.c |  5 +++++
 2 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 3dd47451f097a..fae6fc24a8453 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6133,7 +6133,6 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf,
 	const char *tname, *mname, *tag_value;
 	u32 vlen, elem_id, mid;
 
-	*flag = 0;
 again:
 	if (btf_type_is_modifier(t))
 		t = btf_type_skip_modifiers(btf, t->type, NULL);
@@ -6144,6 +6143,14 @@ again:
 	}
 
 	vlen = btf_type_vlen(t);
+	if (BTF_INFO_KIND(t->info) == BTF_KIND_UNION && vlen != 1 && !(*flag & PTR_UNTRUSTED))
+		/*
+		 * walking unions yields untrusted pointers
+		 * with exception of __bpf_md_ptr and other
+		 * unions with a single member
+		 */
+		*flag |= PTR_UNTRUSTED;
+
 	if (off + size > t->size) {
 		/* If the last element is a variable size array, we may
 		 * need to relax the rule.
@@ -6304,15 +6311,6 @@ error:
 		 * of this field or inside of this struct
 		 */
 		if (btf_type_is_struct(mtype)) {
-			if (BTF_INFO_KIND(mtype->info) == BTF_KIND_UNION &&
-			    btf_type_vlen(mtype) != 1)
-				/*
-				 * walking unions yields untrusted pointers
-				 * with exception of __bpf_md_ptr and other
-				 * unions with a single member
-				 */
-				*flag |= PTR_UNTRUSTED;
-
 			/* our field must be inside that union or struct */
 			t = mtype;
 
@@ -6478,7 +6476,7 @@ bool btf_struct_ids_match(struct bpf_verifier_log *log,
 			  bool strict)
 {
 	const struct btf_type *type;
-	enum bpf_type_flag flag;
+	enum bpf_type_flag flag = 0;
 	int err;
 
 	/* Are we already done? */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 81a93eeac7a0a..584eb34dce8a8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6067,6 +6067,11 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 				   type_is_rcu_or_null(env, reg, field_name, btf_id)) {
 				/* __rcu tagged pointers can be NULL */
 				flag |= MEM_RCU | PTR_MAYBE_NULL;
+
+				/* We always trust them */
+				if (type_is_rcu_or_null(env, reg, field_name, btf_id) &&
+				    flag & PTR_UNTRUSTED)
+					flag &= ~PTR_UNTRUSTED;
 			} else if (flag & (MEM_PERCPU | MEM_USER)) {
 				/* keep as-is */
 			} else {
-- 
GitLab


From d2284d68259c8816fc0dbcb89a0e56849e1f24c2 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Thu, 13 Jul 2023 02:56:40 +0000
Subject: [PATCH 0093/1806] selftests/bpf: Add selftests for nested_trust

Add selftests for nested_strust to check whehter PTR_UNTRUSTED is cleared
as expected, the result as follows:

 #141/1   nested_trust/test_read_cpumask:OK
 #141/2   nested_trust/test_skb_field:OK                    <<<<
 #141/3   nested_trust/test_invalid_nested_user_cpus:OK
 #141/4   nested_trust/test_invalid_nested_offset:OK
 #141/5   nested_trust/test_invalid_skb_field:OK            <<<<
 #141     nested_trust:OK

The #141/2 and #141/5 are newly added.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Link: https://lore.kernel.org/r/20230713025642.27477-3-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/progs/nested_trust_failure.c   | 16 ++++++++++++++++
 .../selftests/bpf/progs/nested_trust_success.c   | 15 +++++++++++++++
 2 files changed, 31 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/nested_trust_failure.c b/tools/testing/selftests/bpf/progs/nested_trust_failure.c
index 0d1aa6bbace4b..ea39497f11ed7 100644
--- a/tools/testing/selftests/bpf/progs/nested_trust_failure.c
+++ b/tools/testing/selftests/bpf/progs/nested_trust_failure.c
@@ -10,6 +10,13 @@
 
 char _license[] SEC("license") = "GPL";
 
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, u64);
+} sk_storage_map SEC(".maps");
+
 /* Prototype for all of the program trace events below:
  *
  * TRACE_EVENT(task_newtask,
@@ -31,3 +38,12 @@ int BPF_PROG(test_invalid_nested_offset, struct task_struct *task, u64 clone_fla
 	bpf_cpumask_first_zero(&task->cpus_mask);
 	return 0;
 }
+
+/* Although R2 is of type sk_buff but sock_common is expected, we will hit untrusted ptr first. */
+SEC("tp_btf/tcp_probe")
+__failure __msg("R2 type=untrusted_ptr_ expected=ptr_, trusted_ptr_, rcu_ptr_")
+int BPF_PROG(test_invalid_skb_field, struct sock *sk, struct sk_buff *skb)
+{
+	bpf_sk_storage_get(&sk_storage_map, skb->next, 0, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/nested_trust_success.c b/tools/testing/selftests/bpf/progs/nested_trust_success.c
index 886ade4aa99d9..833840bffd3b0 100644
--- a/tools/testing/selftests/bpf/progs/nested_trust_success.c
+++ b/tools/testing/selftests/bpf/progs/nested_trust_success.c
@@ -10,6 +10,13 @@
 
 char _license[] SEC("license") = "GPL";
 
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, u64);
+} sk_storage_map SEC(".maps");
+
 SEC("tp_btf/task_newtask")
 __success
 int BPF_PROG(test_read_cpumask, struct task_struct *task, u64 clone_flags)
@@ -17,3 +24,11 @@ int BPF_PROG(test_read_cpumask, struct task_struct *task, u64 clone_flags)
 	bpf_cpumask_test_cpu(0, task->cpus_ptr);
 	return 0;
 }
+
+SEC("tp_btf/tcp_probe")
+__success
+int BPF_PROG(test_skb_field, struct sock *sk, struct sk_buff *skb)
+{
+	bpf_sk_storage_get(&sk_storage_map, skb->sk, 0, 0);
+	return 0;
+}
-- 
GitLab


From 33937607efa050d9e237e0c4ac4ada02d961c466 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Thu, 13 Jul 2023 02:56:41 +0000
Subject: [PATCH 0094/1806] bpf: Fix an error in verifying a field in a union

We are utilizing BPF LSM to monitor BPF operations within our container
environment. When we add support for raw_tracepoint, it hits below
error.

; (const void *)attr->raw_tracepoint.name);
27: (79) r3 = *(u64 *)(r2 +0)
access beyond the end of member map_type (mend:4) in struct (anon) with off 0 size 8

It can be reproduced with below BPF prog.

SEC("lsm/bpf")
int BPF_PROG(bpf_audit, int cmd, union bpf_attr *attr, unsigned int size)
{
	switch (cmd) {
	case BPF_RAW_TRACEPOINT_OPEN:
		bpf_printk("raw_tracepoint is %s", attr->raw_tracepoint.name);
		break;
	default:
		break;
	}
	return 0;
}

The reason is that when accessing a field in a union, such as bpf_attr,
if the field is located within a nested struct that is not the first
member of the union, it can result in incorrect field verification.

  union bpf_attr {
      struct {
          __u32 map_type; <<<< Actually it will find that field.
          __u32 key_size;
          __u32 value_size;
         ...
      };
      ...
      struct {
          __u64 name;    <<<< We want to verify this field.
          __u32 prog_fd;
      } raw_tracepoint;
  };

Considering the potential deep nesting levels, finding a perfect
solution to address this issue has proven challenging. Therefore, I
propose a solution where we simply skip the verification process if the
field in question is located within a union.

Fixes: 7e3617a72df3 ("bpf: Add array support to btf_struct_access")
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Link: https://lore.kernel.org/r/20230713025642.27477-4-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index fae6fc24a8453..a542760c807a9 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6368,7 +6368,7 @@ error:
 		 * that also allows using an array of int as a scratch
 		 * space. e.g. skb->cb[].
 		 */
-		if (off + size > mtrue_end) {
+		if (off + size > mtrue_end && !(*flag & PTR_UNTRUSTED)) {
 			bpf_log(log,
 				"access beyond the end of member %s (mend:%u) in struct %s with off %u size %u\n",
 				mname, mtrue_end, tname, off, size);
-- 
GitLab


From 1cd0e7715cad848017e48033772791e8b9ee2932 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Thu, 13 Jul 2023 02:56:42 +0000
Subject: [PATCH 0095/1806] selftests/bpf: Add selftest for PTR_UNTRUSTED

Add a new selftest to check the PTR_UNTRUSTED condition. Below is the
result,

 #160     ptr_untrusted:OK

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Link: https://lore.kernel.org/r/20230713025642.27477-5-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/ptr_untrusted.c  | 36 +++++++++++++++++++
 .../selftests/bpf/progs/test_ptr_untrusted.c  | 29 +++++++++++++++
 2 files changed, 65 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_ptr_untrusted.c

diff --git a/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c b/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c
new file mode 100644
index 0000000000000..8d077d150c568
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include <string.h>
+#include <linux/bpf.h>
+#include <test_progs.h>
+#include "test_ptr_untrusted.skel.h"
+
+#define TP_NAME "sched_switch"
+
+void serial_test_ptr_untrusted(void)
+{
+	struct test_ptr_untrusted *skel;
+	int err;
+
+	skel = test_ptr_untrusted__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	/* First, attach lsm prog */
+	skel->links.lsm_run = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(skel->links.lsm_run, "lsm_attach"))
+		goto cleanup;
+
+	/* Second, attach raw_tp prog. The lsm prog will be triggered. */
+	skel->links.raw_tp_run = bpf_program__attach_raw_tracepoint(skel->progs.raw_tp_run,
+								    TP_NAME);
+	if (!ASSERT_OK_PTR(skel->links.raw_tp_run, "raw_tp_attach"))
+		goto cleanup;
+
+	err = strncmp(skel->bss->tp_name, TP_NAME, strlen(TP_NAME));
+	ASSERT_EQ(err, 0, "cmp_tp_name");
+
+cleanup:
+	test_ptr_untrusted__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
new file mode 100644
index 0000000000000..4bdd65b5aa2d1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+
+char tp_name[128];
+
+SEC("lsm/bpf")
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
+{
+	switch (cmd) {
+	case BPF_RAW_TRACEPOINT_OPEN:
+		bpf_probe_read_user_str(tp_name, sizeof(tp_name) - 1,
+					(void *)attr->raw_tracepoint.name);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+SEC("raw_tracepoint")
+int BPF_PROG(raw_tp_run)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From 662aa22d7dcdc4806a44038c8f0015e559d46c6d Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 12 Jul 2023 18:03:16 +0200
Subject: [PATCH 0096/1806] selftests: mptcp: set all env vars as local ones

It would be better to move the declaration of all the env variables to
do_transfer(), run_tests(), or pm_nl_set_endpoint() as local variables,
instead of exporting them globally at the beginning of the file.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Link: https://lore.kernel.org/r/20230712-upstream-net-next-20230712-selftests-mptcp-use-local-env-v1-1-f1c8b62fbf95@tessares.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh  | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index e6c9d5451c5b5..b0aaeead56c42 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -49,11 +49,12 @@ TEST_COUNT=0
 TEST_NAME=""
 nr_blank=40
 
-export FAILING_LINKS=""
-export test_linkfail=0
-export addr_nr_ns1=0
-export addr_nr_ns2=0
-export sflags=""
+# These var are used only in some tests, make sure they are not already set
+unset FAILING_LINKS
+unset test_linkfail
+unset addr_nr_ns1
+unset addr_nr_ns2
+unset sflags
 
 # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
 #				  (ip6 && (ip6[74] & 0xf0) == 0x30)'"
@@ -100,7 +101,6 @@ init_partial()
 	stats_dumped=0
 	check_invert=0
 	validate_checksum=$checksum
-	FAILING_LINKS=""
 
 	#  ns1         ns2
 	# ns1eth1    ns2eth1
@@ -828,6 +828,10 @@ pm_nl_set_endpoint()
 	local connector_ns="$2"
 	local connect_addr="$3"
 
+	local addr_nr_ns1=${addr_nr_ns1:-0}
+	local addr_nr_ns2=${addr_nr_ns2:-0}
+	local sflags=${sflags:-""}
+
 	# let the mptcp subflow be established in background before
 	# do endpoint manipulation
 	if [ $addr_nr_ns1 != "0" ] || [ $addr_nr_ns2 != "0" ]; then
@@ -979,6 +983,7 @@ do_transfer()
 
 	local port=$((10000 + TEST_COUNT - 1))
 	local cappid
+	local FAILING_LINKS=${FAILING_LINKS:-""}
 
 	:> "$cout"
 	:> "$sout"
@@ -1158,6 +1163,7 @@ run_tests()
 	local speed="${4:-fast}"
 
 	local size
+	local test_linkfail=${test_linkfail:-0}
 
 	# The values above 2 are reused to make test files
 	# with the given sizes (KB)
-- 
GitLab


From 080b7f5733fd1283509e667bb49d19cc1b245083 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 12 Jul 2023 18:03:17 +0200
Subject: [PATCH 0097/1806] selftests: mptcp: add fastclose env var

Use a new env var fastclose instead of passing fastclose to addr_nr_ns2.
It can be set with 'server' or 'client':

  addr_nr_ns2=fastclose_client \
          run_tests $ns1 $ns2 10.0.1.1

  ->

  fastclose=client \
          run_tests $ns1 $ns2 10.0.1.1.

With this change, the fullmesh flag setting code can be moved into
pm_nl_set_endpoint() from do_transfer().

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Link: https://lore.kernel.org/r/20230712-upstream-net-next-20230712-selftests-mptcp-use-local-env-v1-2-f1c8b62fbf95@tessares.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 21 +++++++++++--------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index b0aaeead56c42..3e8c560938f28 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -55,6 +55,7 @@ unset test_linkfail
 unset addr_nr_ns1
 unset addr_nr_ns2
 unset sflags
+unset fastclose
 
 # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
 #				  (ip6 && (ip6[74] & 0xf0) == 0x30)'"
@@ -832,6 +833,12 @@ pm_nl_set_endpoint()
 	local addr_nr_ns2=${addr_nr_ns2:-0}
 	local sflags=${sflags:-""}
 
+	local flags="subflow"
+	if [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then
+		flags="${flags},fullmesh"
+		addr_nr_ns2=${addr_nr_ns2:9}
+	fi
+
 	# let the mptcp subflow be established in background before
 	# do endpoint manipulation
 	if [ $addr_nr_ns1 != "0" ] || [ $addr_nr_ns2 != "0" ]; then
@@ -984,6 +991,7 @@ do_transfer()
 	local port=$((10000 + TEST_COUNT - 1))
 	local cappid
 	local FAILING_LINKS=${FAILING_LINKS:-""}
+	local fastclose=${fastclose:-""}
 
 	:> "$cout"
 	:> "$sout"
@@ -1020,11 +1028,10 @@ do_transfer()
 		extra_args="-r ${speed:6}"
 	fi
 
-	local flags="subflow"
 	local extra_cl_args=""
 	local extra_srv_args=""
 	local trunc_size=""
-	if [[ "${addr_nr_ns2}" = "fastclose_"* ]]; then
+	if [ -n "${fastclose}" ]; then
 		if [ ${test_linkfail} -le 1 ]; then
 			echo "fastclose tests need test_linkfail argument"
 			fail_test
@@ -1033,7 +1040,7 @@ do_transfer()
 
 		# disconnect
 		trunc_size=${test_linkfail}
-		local side=${addr_nr_ns2:10}
+		local side=${fastclose}
 
 		if [ ${side} = "client" ]; then
 			extra_cl_args="-f ${test_linkfail}"
@@ -1046,10 +1053,6 @@ do_transfer()
 			fail_test
 			return 1
 		fi
-		addr_nr_ns2=0
-	elif [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then
-		flags="${flags},fullmesh"
-		addr_nr_ns2=${addr_nr_ns2:9}
 	fi
 
 	extra_srv_args="$extra_args $extra_srv_args"
@@ -3186,7 +3189,7 @@ fullmesh_tests()
 fastclose_tests()
 {
 	if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then
-		test_linkfail=1024 addr_nr_ns2=fastclose_client \
+		test_linkfail=1024 fastclose=client \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
 		chk_fclose_nr 1 1
@@ -3194,7 +3197,7 @@ fastclose_tests()
 	fi
 
 	if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then
-		test_linkfail=1024 addr_nr_ns2=fastclose_server \
+		test_linkfail=1024 fastclose=server \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
 		chk_fclose_nr 1 1 invert
-- 
GitLab


From 4aadde088a58e40bc14e6cefa285aa600a0942c4 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 12 Jul 2023 18:03:18 +0200
Subject: [PATCH 0098/1806] selftests: mptcp: add fullmesh env var

Use a new env var fullmesh instead of passing 'fullmesh_*' to addr_nr_ns2.
It can be set with the actual value of addr_nr_ns2 now:

  addr_nr_ns2=fullmesh_1 \
          run_tests $ns1 $ns2 10.0.1.1

  ->

  fullmesh=1 \
          run_tests $ns1 $ns2 10.0.1.1.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Link: https://lore.kernel.org/r/20230712-upstream-net-next-20230712-selftests-mptcp-use-local-env-v1-3-f1c8b62fbf95@tessares.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 3e8c560938f28..5ad95cc382e6f 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -56,6 +56,7 @@ unset addr_nr_ns1
 unset addr_nr_ns2
 unset sflags
 unset fastclose
+unset fullmesh
 
 # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
 #				  (ip6 && (ip6[74] & 0xf0) == 0x30)'"
@@ -832,11 +833,12 @@ pm_nl_set_endpoint()
 	local addr_nr_ns1=${addr_nr_ns1:-0}
 	local addr_nr_ns2=${addr_nr_ns2:-0}
 	local sflags=${sflags:-""}
+	local fullmesh=${fullmesh:-""}
 
 	local flags="subflow"
-	if [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then
+	if [ -n "${fullmesh}" ]; then
 		flags="${flags},fullmesh"
-		addr_nr_ns2=${addr_nr_ns2:9}
+		addr_nr_ns2=${fullmesh}
 	fi
 
 	# let the mptcp subflow be established in background before
@@ -2689,7 +2691,7 @@ mixed_tests()
 		pm_nl_set_limits $ns2 2 4
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal
-		addr_nr_ns2=fullmesh_1 \
+		fullmesh=1 \
 			run_tests $ns1 $ns2 dead:beef:1::1 slow
 		chk_join_nr 4 4 4
 	fi
@@ -3102,7 +3104,7 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 1 3
 		pm_nl_set_limits $ns2 1 3
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		addr_nr_ns2=fullmesh_1 \
+		fullmesh=1 \
 			run_tests $ns1 $ns2 10.0.1.1 slow
 		chk_join_nr 3 3 3
 		chk_add_nr 1 1
@@ -3115,7 +3117,7 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 2 5
 		pm_nl_set_limits $ns2 1 5
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		addr_nr_ns2=fullmesh_2 \
+		fullmesh=2 \
 			run_tests $ns1 $ns2 10.0.1.1 slow
 		chk_join_nr 5 5 5
 		chk_add_nr 1 1
@@ -3129,7 +3131,7 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 2 4
 		pm_nl_set_limits $ns2 1 4
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		addr_nr_ns2=fullmesh_2 \
+		fullmesh=2 \
 			run_tests $ns1 $ns2 10.0.1.1 slow
 		chk_join_nr 4 4 4
 		chk_add_nr 1 1
@@ -3153,7 +3155,7 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 4 4
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh
 		pm_nl_set_limits $ns2 4 4
-		addr_nr_ns2=fullmesh_1 sflags=nofullmesh \
+		fullmesh=1 sflags=nofullmesh \
 			run_tests $ns1 $ns2 10.0.1.1 slow
 		chk_join_nr 2 2 2
 		chk_rm_nr 0 1
-- 
GitLab


From e571fb09c893ee9cf6cfb7d926ef321771a5c51b Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 12 Jul 2023 18:03:19 +0200
Subject: [PATCH 0099/1806] selftests: mptcp: add speed env var

Use a new env var speed instead of using 'speed' argument of run_tests()
and do_transfer(). It can be set with 'fast', 'slow', or the actual speed
number:

  run_tests $ns1 $ns2 10.0.1.1 slow

  ->

  speed=slow \
          run_tests $ns1 $ns2 10.0.1.1.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Link: https://lore.kernel.org/r/20230712-upstream-net-next-20230712-selftests-mptcp-use-local-env-v1-4-f1c8b62fbf95@tessares.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 230 ++++++++++--------
 1 file changed, 125 insertions(+), 105 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 5ad95cc382e6f..b5eeea4c3efaf 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -57,6 +57,7 @@ unset addr_nr_ns2
 unset sflags
 unset fastclose
 unset fullmesh
+unset speed
 
 # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
 #				  (ip6 && (ip6[74] & 0xf0) == 0x30)'"
@@ -988,12 +989,12 @@ do_transfer()
 	local cl_proto="$3"
 	local srv_proto="$4"
 	local connect_addr="$5"
-	local speed="$6"
 
 	local port=$((10000 + TEST_COUNT - 1))
 	local cappid
 	local FAILING_LINKS=${FAILING_LINKS:-""}
 	local fastclose=${fastclose:-""}
+	local speed=${speed:-"fast"}
 
 	:> "$cout"
 	:> "$sout"
@@ -1026,8 +1027,8 @@ do_transfer()
 		extra_args="-j"
 	elif [ $speed = "slow" ]; then
 		extra_args="-r 50"
-	elif [[ $speed = "speed_"* ]]; then
-		extra_args="-r ${speed:6}"
+	elif [ $speed -gt 0 ]; then
+		extra_args="-r ${speed}"
 	fi
 
 	local extra_cl_args=""
@@ -1165,7 +1166,6 @@ run_tests()
 	local listener_ns="$1"
 	local connector_ns="$2"
 	local connect_addr="$3"
-	local speed="${4:-fast}"
 
 	local size
 	local test_linkfail=${test_linkfail:-0}
@@ -1210,7 +1210,7 @@ run_tests()
 		make_file "$sinfail" "server" $size
 	fi
 
-	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${speed}
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr}
 }
 
 dump_stats()
@@ -1999,7 +1999,8 @@ subflows_error_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow
-		run_tests $ns1 $ns2 10.0.1.1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
 	fi
 
@@ -2010,7 +2011,8 @@ subflows_error_tests()
 		pm_nl_set_limits $ns2 0 2
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
-		run_tests $ns1 $ns2 10.0.1.1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 	fi
 
@@ -2021,7 +2023,8 @@ subflows_error_tests()
 		pm_nl_set_limits $ns2 0 2
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
-		run_tests $ns1 $ns2 10.0.1.1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 	fi
 
@@ -2033,7 +2036,8 @@ subflows_error_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
-		run_tests $ns1 $ns2 10.0.1.1 slow &
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1 &
 
 		# mpj subflow will be in TW after the reset
 		wait_attempt_fail $ns2
@@ -2132,7 +2136,8 @@ signal_address_tests()
 
 		# the peer could possibly miss some addr notification, allow retransmission
 		ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1
-		run_tests $ns1 $ns2 10.0.1.1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 
 		# It is not directly linked to the commit introducing this
 		# symbol but for the parent one which is linked anyway.
@@ -2242,7 +2247,8 @@ add_addr_timeout_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		run_tests $ns1 $ns2 10.0.1.1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_tx_nr 4 4
 		chk_add_nr 4 0
@@ -2253,7 +2259,8 @@ add_addr_timeout_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal
-		run_tests $ns1 $ns2 dead:beef:1::1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 1 1 1
 		chk_add_nr 4 0
 	fi
@@ -2264,7 +2271,8 @@ add_addr_timeout_tests()
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
 		pm_nl_set_limits $ns2 2 2
-		run_tests $ns1 $ns2 10.0.1.1 speed_10
+		speed=10 \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
 		chk_add_nr 8 0
 	fi
@@ -2275,7 +2283,8 @@ add_addr_timeout_tests()
 		pm_nl_add_endpoint $ns1 10.0.12.1 flags signal
 		pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
 		pm_nl_set_limits $ns2 2 2
-		run_tests $ns1 $ns2 10.0.1.1 speed_10
+		speed=10 \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 8 0
 	fi
@@ -2288,8 +2297,8 @@ remove_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
-		addr_nr_ns2=-1 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns2=-1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_rm_tx_nr 1
 		chk_rm_nr 1 1
@@ -2301,8 +2310,8 @@ remove_tests()
 		pm_nl_set_limits $ns2 0 2
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
-		addr_nr_ns2=-2 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns2=-2 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
 		chk_rm_nr 2 2
 	fi
@@ -2312,8 +2321,8 @@ remove_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		pm_nl_set_limits $ns2 1 1
-		addr_nr_ns1=-1 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=-1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
 		chk_rm_nr 1 1 invert
@@ -2325,8 +2334,8 @@ remove_tests()
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		pm_nl_set_limits $ns2 1 2
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
-		addr_nr_ns1=-1 addr_nr_ns2=-1 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=-1 addr_nr_ns2=-1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
 		chk_add_nr 1 1
 		chk_rm_nr 1 1
@@ -2339,8 +2348,8 @@ remove_tests()
 		pm_nl_set_limits $ns2 1 3
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow
-		addr_nr_ns1=-1 addr_nr_ns2=-2 \
-			run_tests $ns1 $ns2 10.0.1.1 speed_10
+		addr_nr_ns1=-1 addr_nr_ns2=-2 speed=10 \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 3 3 3
 		chk_add_nr 1 1
 		chk_rm_nr 2 2
@@ -2353,8 +2362,8 @@ remove_tests()
 		pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
 		pm_nl_add_endpoint $ns1 10.0.4.1 flags signal
 		pm_nl_set_limits $ns2 3 3
-		addr_nr_ns1=-3 \
-			run_tests $ns1 $ns2 10.0.1.1 speed_10
+		addr_nr_ns1=-3 speed=10 \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 3 3 3
 		chk_add_nr 3 3
 		chk_rm_nr 3 3 invert
@@ -2367,8 +2376,8 @@ remove_tests()
 		pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
 		pm_nl_add_endpoint $ns1 10.0.14.1 flags signal
 		pm_nl_set_limits $ns2 3 3
-		addr_nr_ns1=-3 \
-			run_tests $ns1 $ns2 10.0.1.1 speed_10
+		addr_nr_ns1=-3 speed=10 \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 3 3
 		chk_rm_nr 3 1 invert
@@ -2381,8 +2390,8 @@ remove_tests()
 		pm_nl_set_limits $ns2 1 3
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow
-		addr_nr_ns1=-8 addr_nr_ns2=-8 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=-8 addr_nr_ns2=-8 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 3 3 3
 		chk_add_nr 1 1
 		chk_rm_nr 1 3 invert simult
@@ -2395,8 +2404,8 @@ remove_tests()
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow
-		addr_nr_ns1=-8 addr_nr_ns2=-8 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=-8 addr_nr_ns2=-8 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 3 3 3
 
 		if mptcp_lib_kversion_ge 5.18; then
@@ -2414,8 +2423,8 @@ remove_tests()
 		pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
 		pm_nl_add_endpoint $ns1 10.0.4.1 flags signal
 		pm_nl_set_limits $ns2 3 3
-		addr_nr_ns1=-8 addr_nr_ns2=-8 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=-8 addr_nr_ns2=-8 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 3 3 3
 		chk_add_nr 3 3
 		chk_rm_nr 3 3 invert simult
@@ -2428,8 +2437,8 @@ remove_tests()
 		pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
 		pm_nl_add_endpoint $ns1 10.0.14.1 flags signal
 		pm_nl_set_limits $ns2 3 3
-		addr_nr_ns1=-8 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=-8 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 3 3
 		chk_rm_nr 3 1 invert
@@ -2440,8 +2449,8 @@ remove_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
-		addr_nr_ns2=-9 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns2=-9 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_rm_nr 1 1
 	fi
@@ -2451,8 +2460,8 @@ remove_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		pm_nl_set_limits $ns2 1 1
-		addr_nr_ns1=-9 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=-9 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
 		chk_rm_nr 1 1 invert
@@ -2465,8 +2474,8 @@ add_tests()
 	if reset "add single subflow"; then
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
-		addr_nr_ns2=1 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns2=1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 	fi
 
@@ -2474,8 +2483,8 @@ add_tests()
 	if reset "add signal address"; then
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 1 1
-		addr_nr_ns1=1 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
 	fi
@@ -2484,8 +2493,8 @@ add_tests()
 	if reset "add multiple subflows"; then
 		pm_nl_set_limits $ns1 0 2
 		pm_nl_set_limits $ns2 0 2
-		addr_nr_ns2=2 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns2=2 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
 	fi
 
@@ -2493,8 +2502,8 @@ add_tests()
 	if reset "add multiple subflows IPv6"; then
 		pm_nl_set_limits $ns1 0 2
 		pm_nl_set_limits $ns2 0 2
-		addr_nr_ns2=2 \
-			run_tests $ns1 $ns2 dead:beef:1::1 slow
+		addr_nr_ns2=2 speed=slow \
+			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 2 2 2
 	fi
 
@@ -2502,8 +2511,8 @@ add_tests()
 	if reset "add multiple addresses IPv6"; then
 		pm_nl_set_limits $ns1 0 2
 		pm_nl_set_limits $ns2 2 2
-		addr_nr_ns1=2 \
-			run_tests $ns1 $ns2 dead:beef:1::1 slow
+		addr_nr_ns1=2 speed=slow \
+			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 2 2 2
 		chk_add_nr 2 2
 	fi
@@ -2516,14 +2525,16 @@ ipv6_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow
-		run_tests $ns1 $ns2 dead:beef:1::1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 1 1 1
 	fi
 
 	# add_address, unused IPv6
 	if reset "unused signal address IPv6"; then
 		pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal
-		run_tests $ns1 $ns2 dead:beef:1::1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 0 0 0
 		chk_add_nr 1 1
 	fi
@@ -2533,7 +2544,8 @@ ipv6_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal
 		pm_nl_set_limits $ns2 1 1
-		run_tests $ns1 $ns2 dead:beef:1::1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
 	fi
@@ -2543,8 +2555,8 @@ ipv6_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal
 		pm_nl_set_limits $ns2 1 1
-		addr_nr_ns1=-1 \
-			run_tests $ns1 $ns2 dead:beef:1::1 slow
+		addr_nr_ns1=-1 speed=slow \
+			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
 		chk_rm_nr 1 1 invert
@@ -2556,8 +2568,8 @@ ipv6_tests()
 		pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal
 		pm_nl_set_limits $ns2 1 2
 		pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow
-		addr_nr_ns1=-1 addr_nr_ns2=-1 \
-			run_tests $ns1 $ns2 dead:beef:1::1 slow
+		addr_nr_ns1=-1 addr_nr_ns2=-1 speed=slow \
+			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 2 2 2
 		chk_add_nr 1 1
 		chk_rm_nr 1 1
@@ -2658,7 +2670,8 @@ mixed_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal
-		run_tests $ns1 $ns2 10.0.1.1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
 	fi
 
@@ -2668,7 +2681,8 @@ mixed_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns1 10.0.1.1 flags signal
-		run_tests $ns1 $ns2 dead:beef:2::1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 dead:beef:2::1
 		chk_join_nr 1 1 1
 	fi
 
@@ -2679,7 +2693,8 @@ mixed_tests()
 		pm_nl_set_limits $ns2 1 4
 		pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow,fullmesh
 		pm_nl_add_endpoint $ns1 10.0.1.1 flags signal
-		run_tests $ns1 $ns2 dead:beef:2::1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 dead:beef:2::1
 		chk_join_nr 1 1 1
 	fi
 
@@ -2691,8 +2706,8 @@ mixed_tests()
 		pm_nl_set_limits $ns2 2 4
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal
-		fullmesh=1 \
-			run_tests $ns1 $ns2 dead:beef:1::1 slow
+		fullmesh=1 speed=slow \
+			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 4 4 4
 	fi
 }
@@ -2705,8 +2720,8 @@ backup_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup
-		sflags=nobackup \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		sflags=nobackup speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_prio_nr 0 1
 	fi
@@ -2717,8 +2732,8 @@ backup_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		pm_nl_set_limits $ns2 1 1
-		sflags=backup \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		sflags=backup speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
 		chk_prio_nr 1 1
@@ -2730,8 +2745,8 @@ backup_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100
 		pm_nl_set_limits $ns2 1 1
-		sflags=backup \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		sflags=backup speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
 		chk_prio_nr 1 1
@@ -2740,7 +2755,8 @@ backup_tests()
 	if reset "mpc backup" &&
 	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
-		run_tests $ns1 $ns2 10.0.1.1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
 		chk_prio_nr 0 1
 	fi
@@ -2749,7 +2765,8 @@ backup_tests()
 	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
-		run_tests $ns1 $ns2 10.0.1.1 slow
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
 		chk_prio_nr 1 1
 	fi
@@ -2757,8 +2774,8 @@ backup_tests()
 	if reset "mpc switch to backup" &&
 	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow
-		sflags=backup \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		sflags=backup speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
 		chk_prio_nr 0 1
 	fi
@@ -2767,8 +2784,8 @@ backup_tests()
 	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow
-		sflags=backup \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		sflags=backup speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
 		chk_prio_nr 1 1
 	fi
@@ -2857,8 +2874,8 @@ add_addr_ports_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100
 		pm_nl_set_limits $ns2 1 1
-		addr_nr_ns1=-1 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=-1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1 1
 		chk_rm_nr 1 1 invert
@@ -2874,8 +2891,8 @@ add_addr_ports_tests()
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100
 		pm_nl_set_limits $ns2 1 2
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
-		addr_nr_ns1=-1 addr_nr_ns2=-1 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=-1 addr_nr_ns2=-1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
 		chk_add_nr 1 1 1
 		chk_rm_nr 1 1
@@ -2888,8 +2905,8 @@ add_addr_ports_tests()
 		pm_nl_set_limits $ns2 1 3
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow
-		addr_nr_ns1=-8 addr_nr_ns2=-2 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=-8 addr_nr_ns2=-2 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 3 3 3
 		chk_add_nr 1 1
 		chk_rm_nr 1 3 invert simult
@@ -3091,8 +3108,8 @@ fullmesh_tests()
 		pm_nl_set_limits $ns2 1 4
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh
-		addr_nr_ns1=1 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns1=1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 4 4 4
 		chk_add_nr 1 1
 	fi
@@ -3104,8 +3121,8 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 1 3
 		pm_nl_set_limits $ns2 1 3
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		fullmesh=1 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		fullmesh=1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 3 3 3
 		chk_add_nr 1 1
 	fi
@@ -3117,8 +3134,8 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 2 5
 		pm_nl_set_limits $ns2 1 5
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		fullmesh=2 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		fullmesh=2 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 5 5 5
 		chk_add_nr 1 1
 	fi
@@ -3131,8 +3148,8 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 2 4
 		pm_nl_set_limits $ns2 1 4
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		fullmesh=2 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		fullmesh=2 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 4 4 4
 		chk_add_nr 1 1
 	fi
@@ -3143,8 +3160,8 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 4 4
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow
 		pm_nl_set_limits $ns2 4 4
-		addr_nr_ns2=1 sflags=fullmesh \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns2=1 sflags=fullmesh speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
 		chk_rm_nr 0 1
 	fi
@@ -3155,8 +3172,8 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 4 4
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh
 		pm_nl_set_limits $ns2 4 4
-		fullmesh=1 sflags=nofullmesh \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		fullmesh=1 sflags=nofullmesh speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
 		chk_rm_nr 0 1
 	fi
@@ -3167,8 +3184,8 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 4 4
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow
 		pm_nl_set_limits $ns2 4 4
-		addr_nr_ns2=1 sflags=backup,fullmesh \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns2=1 sflags=backup,fullmesh speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
 		chk_prio_nr 0 1
 		chk_rm_nr 0 1
@@ -3180,8 +3197,8 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 4 4
 		pm_nl_set_limits $ns2 4 4
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh
-		sflags=nobackup,nofullmesh \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		sflags=nobackup,nofullmesh speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
 		chk_prio_nr 0 1
 		chk_rm_nr 0 1
@@ -3356,8 +3373,8 @@ userspace_tests()
 		pm_nl_set_limits $ns1 1 1
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
-		sflags=backup \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		sflags=backup speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 0
 		chk_prio_nr 0 0
 	fi
@@ -3370,8 +3387,8 @@ userspace_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
-		addr_nr_ns2=-1 \
-			run_tests $ns1 $ns2 10.0.1.1 slow
+		addr_nr_ns2=-1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
 		chk_rm_nr 0 0
 	fi
@@ -3381,7 +3398,8 @@ userspace_tests()
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns1
 		pm_nl_set_limits $ns2 1 1
-		run_tests $ns1 $ns2 10.0.1.1 speed_10 &
+		speed=10 \
+			run_tests $ns1 $ns2 10.0.1.1 &
 		local tests_pid=$!
 		wait_mpj $ns1
 		userspace_pm_add_addr 10.0.2.1 10
@@ -3401,7 +3419,8 @@ userspace_tests()
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns2
 		pm_nl_set_limits $ns1 0 1
-		run_tests $ns1 $ns2 10.0.1.1 speed_10 &
+		speed=10 \
+			run_tests $ns1 $ns2 10.0.1.1 &
 		local tests_pid=$!
 		wait_mpj $ns2
 		userspace_pm_add_sf 10.0.3.2 20
@@ -3424,7 +3443,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns1 2 2
 		pm_nl_set_limits $ns2 2 2
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		run_tests $ns1 $ns2 10.0.1.1 slow 2>/dev/null &
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
 
 		wait_mpj $ns1
 		pm_nl_check_endpoint 1 "creation" \
@@ -3447,8 +3467,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns1 1 1
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
-		test_linkfail=4 \
-			run_tests $ns1 $ns2 10.0.1.1 speed_20 2>/dev/null &
+		test_linkfail=4 speed=20 \
+			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
 
 		wait_mpj $ns2
 		chk_subflow_nr needtitle "before delete" 2
-- 
GitLab


From bec9ce34075e4b1c4a36d9eb7a40e84929d12aa8 Mon Sep 17 00:00:00 2001
From: Ziyang Chen <ziyang.chen@corigine.com>
Date: Wed, 12 Jul 2023 14:35:51 +0200
Subject: [PATCH 0100/1806] nfp: prevent dropped counter increment during probe

The dev_rx_discards counter will increment by one when an interface is
toggled up and down. The main reason is that the driver first sends a
`NFP_NET_CFG_CTRL_ENABLE` configuration packet to the NIC to perform port
initialisation when an interface is set up. But there is a race between
physical link up and free list queue initialization which may lead to the
configuration packet being discarded.

To address this problem a new bit NFP_NET_CFG_CTRL_FREELIST_EN is added to
perform free list initialisation on the NIC. The FREELIST_EN should be sent
in advance to initialize free list queue. When a port is set to down,
FREELIST_EN should be sent after CTRL_ENABLE to avoid packet discards.

Signed-off-by: Ziyang Chen <ziyang.chen@corigine.com>
Acked-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Link: https://lore.kernel.org/r/20230712123551.13858-1-louis.peens@corigine.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/netronome/nfp/nfp_net_common.c   | 54 ++++++++++++++++---
 .../net/ethernet/netronome/nfp/nfp_net_ctrl.h |  1 +
 2 files changed, 48 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 6b1fb57084347..f18c791cf698f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -924,7 +924,7 @@ static void nfp_net_write_mac_addr(struct nfp_net *nn, const u8 *addr)
  */
 static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 {
-	u32 new_ctrl, update;
+	u32 new_ctrl, new_ctrl_w1, update;
 	unsigned int r;
 	int err;
 
@@ -937,14 +937,29 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 	if (nn->cap & NFP_NET_CFG_CTRL_RINGCFG)
 		new_ctrl &= ~NFP_NET_CFG_CTRL_RINGCFG;
 
-	nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, 0);
-	nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, 0);
+	if (!(nn->cap_w1 & NFP_NET_CFG_CTRL_FREELIST_EN)) {
+		nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, 0);
+		nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, 0);
+	}
 
 	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
 	err = nfp_net_reconfig(nn, update);
 	if (err)
 		nn_err(nn, "Could not disable device: %d\n", err);
 
+	if (nn->cap_w1 & NFP_NET_CFG_CTRL_FREELIST_EN) {
+		new_ctrl_w1 = nn->dp.ctrl_w1;
+		new_ctrl_w1 &= ~NFP_NET_CFG_CTRL_FREELIST_EN;
+		nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, 0);
+		nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, 0);
+
+		nn_writel(nn, NFP_NET_CFG_CTRL_WORD1, new_ctrl_w1);
+		err = nfp_net_reconfig(nn, update);
+		if (err)
+			nn_err(nn, "Could not disable FREELIST_EN: %d\n", err);
+		nn->dp.ctrl_w1 = new_ctrl_w1;
+	}
+
 	for (r = 0; r < nn->dp.num_rx_rings; r++) {
 		nfp_net_rx_ring_reset(&nn->dp.rx_rings[r]);
 		if (nfp_net_has_xsk_pool_slow(&nn->dp, nn->dp.rx_rings[r].idx))
@@ -964,11 +979,12 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
  */
 static int nfp_net_set_config_and_enable(struct nfp_net *nn)
 {
-	u32 bufsz, new_ctrl, update = 0;
+	u32 bufsz, new_ctrl, new_ctrl_w1, update = 0;
 	unsigned int r;
 	int err;
 
 	new_ctrl = nn->dp.ctrl;
+	new_ctrl_w1 = nn->dp.ctrl_w1;
 
 	if (nn->dp.ctrl & NFP_NET_CFG_CTRL_RSS_ANY) {
 		nfp_net_rss_write_key(nn);
@@ -1001,16 +1017,25 @@ static int nfp_net_set_config_and_enable(struct nfp_net *nn)
 	bufsz = nn->dp.fl_bufsz - nn->dp.rx_dma_off - NFP_NET_RX_BUF_NON_DATA;
 	nn_writel(nn, NFP_NET_CFG_FLBUFSZ, bufsz);
 
-	/* Enable device */
-	new_ctrl |= NFP_NET_CFG_CTRL_ENABLE;
+	/* Enable device
+	 * Step 1: Replace the CTRL_ENABLE by NFP_NET_CFG_CTRL_FREELIST_EN if
+	 * FREELIST_EN exits.
+	 */
+	if (nn->cap_w1 & NFP_NET_CFG_CTRL_FREELIST_EN)
+		new_ctrl_w1 |= NFP_NET_CFG_CTRL_FREELIST_EN;
+	else
+		new_ctrl |= NFP_NET_CFG_CTRL_ENABLE;
 	update |= NFP_NET_CFG_UPDATE_GEN;
 	update |= NFP_NET_CFG_UPDATE_MSIX;
 	update |= NFP_NET_CFG_UPDATE_RING;
 	if (nn->cap & NFP_NET_CFG_CTRL_RINGCFG)
 		new_ctrl |= NFP_NET_CFG_CTRL_RINGCFG;
 
+	/* Step 2: Send the configuration and write the freelist.
+	 * - The freelist only need to be written once.
+	 */
 	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
-	nn_writel(nn, NFP_NET_CFG_CTRL_WORD1, nn->dp.ctrl_w1);
+	nn_writel(nn, NFP_NET_CFG_CTRL_WORD1, new_ctrl_w1);
 	err = nfp_net_reconfig(nn, update);
 	if (err) {
 		nfp_net_clear_config_and_disable(nn);
@@ -1018,10 +1043,25 @@ static int nfp_net_set_config_and_enable(struct nfp_net *nn)
 	}
 
 	nn->dp.ctrl = new_ctrl;
+	nn->dp.ctrl_w1 = new_ctrl_w1;
 
 	for (r = 0; r < nn->dp.num_rx_rings; r++)
 		nfp_net_rx_ring_fill_freelist(&nn->dp, &nn->dp.rx_rings[r]);
 
+	/* Step 3: Do the NFP_NET_CFG_CTRL_ENABLE. Send the configuration.
+	 */
+	if (nn->cap_w1 & NFP_NET_CFG_CTRL_FREELIST_EN) {
+		new_ctrl |= NFP_NET_CFG_CTRL_ENABLE;
+		nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
+
+		err = nfp_net_reconfig(nn, update);
+		if (err) {
+			nfp_net_clear_config_and_disable(nn);
+			return err;
+		}
+		nn->dp.ctrl = new_ctrl;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index 669b9dccb6a93..3e63f6d6a563d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -268,6 +268,7 @@
 #define   NFP_NET_CFG_CTRL_PKT_TYPE	  (0x1 << 0) /* Pkttype offload */
 #define   NFP_NET_CFG_CTRL_IPSEC	  (0x1 << 1) /* IPsec offload */
 #define   NFP_NET_CFG_CTRL_MCAST_FILTER	  (0x1 << 2) /* Multicast Filter */
+#define   NFP_NET_CFG_CTRL_FREELIST_EN	  (0x1 << 6) /* Freelist enable flag bit */
 
 #define NFP_NET_CFG_CAP_WORD1		0x00a4
 
-- 
GitLab


From d26979f1cef71d6fa036f6cedfa0059715092503 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 10:59:50 +0200
Subject: [PATCH 0101/1806] net: stmmac: replace the has_integrated_pcs field
 with a flag

struct plat_stmmacenet_data contains several boolean fields that could be
easily replaced with a common integer 'flags' bitfield and bit defines.

Start the process with the has_integrated_pcs field.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-2-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 3 ++-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c       | 3 ++-
 include/linux/stmmac.h                                  | 4 +++-
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 757504ebb676a..3cfa4d2e1929a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -786,7 +786,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	plat_dat->tso_en = of_property_read_bool(np, "snps,tso");
 	if (of_device_is_compatible(np, "qcom,qcs404-ethqos"))
 		plat_dat->rx_clk_runs_in_lpi = 1;
-	plat_dat->has_integrated_pcs = data->has_integrated_pcs;
+	if (data->has_integrated_pcs)
+		plat_dat->flags |= STMMAC_FLAG_HAS_INTEGRATED_PCS;
 
 	if (ethqos->serdes_phy) {
 		plat_dat->serdes_powerup = qcom_ethqos_serdes_powerup;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4727f7be4f86e..38b6cbd8a1331 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -5798,7 +5798,8 @@ static void stmmac_common_interrupt(struct stmmac_priv *priv)
 		}
 
 		/* PCS link status */
-		if (priv->hw->pcs && !priv->plat->has_integrated_pcs) {
+		if (priv->hw->pcs &&
+		    !(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS)) {
 			if (priv->xstats.pcs_link)
 				netif_carrier_on(priv->dev);
 			else
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 06090538fe2d7..8e7511071ef12 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -204,6 +204,8 @@ struct dwmac4_addrs {
 	u32 mtl_low_cred_offset;
 };
 
+#define STMMAC_FLAG_HAS_INTEGRATED_PCS		BIT(0)
+
 struct plat_stmmacenet_data {
 	int bus_id;
 	int phy_addr;
@@ -293,6 +295,6 @@ struct plat_stmmacenet_data {
 	bool sph_disable;
 	bool serdes_up_after_phy_linkup;
 	const struct dwmac4_addrs *dwmac4_addrs;
-	bool has_integrated_pcs;
+	unsigned int flags;
 };
 #endif
-- 
GitLab


From 309efe6eb499d04b7c09e57298c453b602efe3fd Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 10:59:51 +0200
Subject: [PATCH 0102/1806] net: stmmac: replace the sph_disable field with a
 flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-3-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c       | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c       | 3 ++-
 include/linux/stmmac.h                                  | 2 +-
 4 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 9f88530c5e8c8..0c12ab67c27bc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -359,7 +359,7 @@ bypass_clk_reset_gpio:
 	data->fix_mac_speed = tegra_eqos_fix_speed;
 	data->init = tegra_eqos_init;
 	data->bsp_priv = eqos;
-	data->sph_disable = 1;
+	data->flags |= STMMAC_FLAG_SPH_DISABLE;
 
 	err = tegra_eqos_init(pdev, eqos);
 	if (err < 0)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index ab9f876b6df7e..ae5db39a3f1b0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -459,7 +459,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->has_gmac4 = 1;
 	plat->force_sf_dma_mode = 0;
 	plat->tso_en = 1;
-	plat->sph_disable = 1;
+	plat->flags |= STMMAC_FLAG_SPH_DISABLE;
 
 	/* Multiplying factor to the clk_eee_i clock time
 	 * period to make it closer to 100 ns. This value
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 38b6cbd8a1331..18e56299363db 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7258,7 +7258,8 @@ int stmmac_dvr_probe(struct device *device,
 		dev_info(priv->device, "TSO feature enabled\n");
 	}
 
-	if (priv->dma_cap.sphen && !priv->plat->sph_disable) {
+	if (priv->dma_cap.sphen &&
+	    !(priv->plat->flags & STMMAC_FLAG_SPH_DISABLE)) {
 		ndev->hw_features |= NETIF_F_GRO;
 		priv->sph_cap = true;
 		priv->sph = priv->sph_cap;
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 8e7511071ef12..1b02f866316c4 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -205,6 +205,7 @@ struct dwmac4_addrs {
 };
 
 #define STMMAC_FLAG_HAS_INTEGRATED_PCS		BIT(0)
+#define STMMAC_FLAG_SPH_DISABLE			BIT(1)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -292,7 +293,6 @@ struct plat_stmmacenet_data {
 	int msi_rx_base_vec;
 	int msi_tx_base_vec;
 	bool use_phy_wol;
-	bool sph_disable;
 	bool serdes_up_after_phy_linkup;
 	const struct dwmac4_addrs *dwmac4_addrs;
 	unsigned int flags;
-- 
GitLab


From fd1d62d80ebc1a68ba700e92c9da9d443c08f371 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 10:59:52 +0200
Subject: [PATCH 0103/1806] net: stmmac: replace the use_phy_wol field with a
 flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-4-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c    | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c | 5 ++++-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c    | 2 +-
 include/linux/stmmac.h                               | 2 +-
 4 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index ae5db39a3f1b0..c690ec1b9bab4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -628,7 +628,7 @@ static int ehl_common_data(struct pci_dev *pdev,
 {
 	plat->rx_queues_to_use = 8;
 	plat->tx_queues_to_use = 8;
-	plat->use_phy_wol = 1;
+	plat->flags |= STMMAC_FLAG_USE_PHY_WOL;
 
 	plat->safety_feat_cfg->tsoee = 1;
 	plat->safety_feat_cfg->mrxpee = 1;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index 73c1dfa7ecb1d..4d877d75642d9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -588,7 +588,10 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev,
 	int i;
 
 	plat->interface = priv_plat->phy_mode;
-	plat->use_phy_wol = priv_plat->mac_wol ? 0 : 1;
+	if (priv_plat->mac_wol)
+		plat->flags |= STMMAC_FLAG_USE_PHY_WOL;
+	else
+		plat->flags &= ~STMMAC_FLAG_USE_PHY_WOL;
 	plat->riwt_off = 1;
 	plat->maxmtu = ETH_DATA_LEN;
 	plat->host_dma_width = priv_plat->variant->dma_bit_mask;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 18e56299363db..a1a59af3961dc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6877,7 +6877,7 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 		 */
 		priv->plat->enh_desc = priv->dma_cap.enh_desc;
 		priv->plat->pmt = priv->dma_cap.pmt_remote_wake_up &&
-				!priv->plat->use_phy_wol;
+				!(priv->plat->flags & STMMAC_FLAG_USE_PHY_WOL);
 		priv->hw->pmt = priv->plat->pmt;
 		if (priv->dma_cap.hash_tb_sz) {
 			priv->hw->multicast_filter_bins =
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 1b02f866316c4..15fb07cc89c83 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -206,6 +206,7 @@ struct dwmac4_addrs {
 
 #define STMMAC_FLAG_HAS_INTEGRATED_PCS		BIT(0)
 #define STMMAC_FLAG_SPH_DISABLE			BIT(1)
+#define STMMAC_FLAG_USE_PHY_WOL			BIT(2)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -292,7 +293,6 @@ struct plat_stmmacenet_data {
 	int msi_sfty_ue_vec;
 	int msi_rx_base_vec;
 	int msi_tx_base_vec;
-	bool use_phy_wol;
 	bool serdes_up_after_phy_linkup;
 	const struct dwmac4_addrs *dwmac4_addrs;
 	unsigned int flags;
-- 
GitLab


From d8daff284e305409fd640feda7345d0221d782ce Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 10:59:53 +0200
Subject: [PATCH 0104/1806] net: stmmac: replace the has_sun8i field with a
 flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-5-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++--
 include/linux/stmmac.h                            | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 1e714380d1250..2b5ebb15bfda8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -1227,7 +1227,7 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	plat_dat->interface = interface;
 	plat_dat->rx_coe = STMMAC_RX_COE_TYPE2;
 	plat_dat->tx_coe = 1;
-	plat_dat->has_sun8i = true;
+	plat_dat->flags |= STMMAC_FLAG_HAS_SUN8I;
 	plat_dat->bsp_priv = gmac;
 	plat_dat->init = sun8i_dwmac_init;
 	plat_dat->exit = sun8i_dwmac_exit;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a1a59af3961dc..3df32658b5bb4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -325,7 +325,7 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv)
 			priv->clk_csr = STMMAC_CSR_250_300M;
 	}
 
-	if (priv->plat->has_sun8i) {
+	if (priv->plat->flags & STMMAC_FLAG_HAS_SUN8I) {
 		if (clk_rate > 160000000)
 			priv->clk_csr = 0x03;
 		else if (clk_rate > 80000000)
@@ -6856,7 +6856,7 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 	int ret;
 
 	/* dwmac-sun8i only work in chain mode */
-	if (priv->plat->has_sun8i)
+	if (priv->plat->flags & STMMAC_FLAG_HAS_SUN8I)
 		chain_mode = 1;
 	priv->chain_mode = chain_mode;
 
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 15fb07cc89c83..66dcf84d024aa 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -207,6 +207,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_HAS_INTEGRATED_PCS		BIT(0)
 #define STMMAC_FLAG_SPH_DISABLE			BIT(1)
 #define STMMAC_FLAG_USE_PHY_WOL			BIT(2)
+#define STMMAC_FLAG_HAS_SUN8I			BIT(3)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -270,7 +271,6 @@ struct plat_stmmacenet_data {
 	struct reset_control *stmmac_ahb_rst;
 	struct stmmac_axi *axi;
 	int has_gmac4;
-	bool has_sun8i;
 	bool tso_en;
 	int rss_en;
 	int mac_port_sel_speed;
-- 
GitLab


From 68861a3bcc1caf5c15a56e02090310271fd085e1 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 10:59:54 +0200
Subject: [PATCH 0105/1806] net: stmmac: replace the tso_en field with a flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-6-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c       | 3 +--
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 3 ++-
 drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c       | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c       | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c        | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c   | 6 ++++--
 include/linux/stmmac.h                                  | 2 +-
 8 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 0c12ab67c27bc..b5efd9c2eac78 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -113,7 +113,7 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
 	/* dwc-qos needs GMAC4, AAL, TSO and PMT */
 	plat_dat->has_gmac4 = 1;
 	plat_dat->dma_cfg->aal = 1;
-	plat_dat->tso_en = 1;
+	plat_dat->flags |= STMMAC_FLAG_TSO_EN;
 	plat_dat->pmt = 1;
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index c690ec1b9bab4..faa6f4ec68389 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -458,8 +458,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->has_gmac = 0;
 	plat->has_gmac4 = 1;
 	plat->force_sf_dma_mode = 0;
-	plat->tso_en = 1;
-	plat->flags |= STMMAC_FLAG_SPH_DISABLE;
+	plat->flags |= (STMMAC_FLAG_TSO_EN | STMMAC_FLAG_SPH_DISABLE);
 
 	/* Multiplying factor to the clk_eee_i clock time
 	 * period to make it closer to 100 ns. This value
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 3cfa4d2e1929a..4b58904ee132b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -783,7 +783,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	if (ethqos->has_emac_ge_3)
 		plat_dat->dwmac4_addrs = &data->dwmac4_addrs;
 	plat_dat->pmt = 1;
-	plat_dat->tso_en = of_property_read_bool(np, "snps,tso");
+	if (of_property_read_bool(np, "snps,tso"))
+		plat_dat->flags |= STMMAC_FLAG_TSO_EN;
 	if (of_device_is_compatible(np, "qcom,qcs404-ethqos"))
 		plat_dat->rx_clk_runs_in_lpi = 1;
 	if (data->has_integrated_pcs)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
index f8367c5b490ba..5e8aa03cffaee 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
@@ -290,7 +290,7 @@ static int tegra_mgbe_probe(struct platform_device *pdev)
 	}
 
 	plat->has_xgmac = 1;
-	plat->tso_en = 1;
+	plat->flags |= STMMAC_FLAG_TSO_EN;
 	plat->pmt = 1;
 	plat->bsp_priv = mgbe;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3df32658b5bb4..73002ed923aaa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -5677,7 +5677,7 @@ static netdev_features_t stmmac_fix_features(struct net_device *dev,
 		features &= ~NETIF_F_CSUM_MASK;
 
 	/* Disable tso if asked by ethtool */
-	if ((priv->plat->tso_en) && (priv->dma_cap.tsoen)) {
+	if ((priv->plat->flags & STMMAC_FLAG_TSO_EN) && (priv->dma_cap.tsoen)) {
 		if (features & NETIF_F_TSO)
 			priv->tso = true;
 		else
@@ -7250,7 +7250,7 @@ int stmmac_dvr_probe(struct device *device,
 		ndev->hw_features |= NETIF_F_HW_TC;
 	}
 
-	if ((priv->plat->tso_en) && (priv->dma_cap.tsoen)) {
+	if ((priv->plat->flags & STMMAC_FLAG_TSO_EN) && (priv->dma_cap.tsoen)) {
 		ndev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
 		if (priv->plat->has_gmac4)
 			ndev->hw_features |= NETIF_F_GSO_UDP_L4;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 644bb54f5f020..352b01678c223 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -77,7 +77,7 @@ static int snps_gmac5_default_data(struct pci_dev *pdev,
 	plat->clk_csr = 5;
 	plat->has_gmac4 = 1;
 	plat->force_sf_dma_mode = 1;
-	plat->tso_en = 1;
+	plat->flags |= STMMAC_FLAG_TSO_EN;
 	plat->pmt = 1;
 
 	/* Set default value for multicast hash bins */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 231152ee5a323..f51522cb00611 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -525,7 +525,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 		plat->has_gmac4 = 1;
 		plat->has_gmac = 0;
 		plat->pmt = 1;
-		plat->tso_en = of_property_read_bool(np, "snps,tso");
+		if (of_property_read_bool(np, "snps,tso"))
+			plat->flags |= STMMAC_FLAG_TSO_EN;
 	}
 
 	if (of_device_is_compatible(np, "snps,dwmac-3.610") ||
@@ -538,7 +539,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	if (of_device_is_compatible(np, "snps,dwxgmac")) {
 		plat->has_xgmac = 1;
 		plat->pmt = 1;
-		plat->tso_en = of_property_read_bool(np, "snps,tso");
+		if (of_property_read_bool(np, "snps,tso"))
+			plat->flags |= STMMAC_FLAG_TSO_EN;
 	}
 
 	dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg),
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 66dcf84d024aa..47ae29a988357 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -208,6 +208,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_SPH_DISABLE			BIT(1)
 #define STMMAC_FLAG_USE_PHY_WOL			BIT(2)
 #define STMMAC_FLAG_HAS_SUN8I			BIT(3)
+#define STMMAC_FLAG_TSO_EN			BIT(4)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -271,7 +272,6 @@ struct plat_stmmacenet_data {
 	struct reset_control *stmmac_ahb_rst;
 	struct stmmac_axi *axi;
 	int has_gmac4;
-	bool tso_en;
 	int rss_en;
 	int mac_port_sel_speed;
 	bool en_tx_lpi_clockgating;
-- 
GitLab


From efe92571bfc30f251f6f2fa7828aa5f239736abf Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 10:59:55 +0200
Subject: [PATCH 0106/1806] net: stmmac: replace the serdes_up_after_phy_linkup
 field with a flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-7-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 9 ++++++---
 include/linux/stmmac.h                            | 2 +-
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
index 5e8aa03cffaee..99e2e5a5cd60e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
@@ -337,7 +337,7 @@ static int tegra_mgbe_probe(struct platform_device *pdev)
 	/* Program SID */
 	writel(MGBE_SID, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL);
 
-	plat->serdes_up_after_phy_linkup = 1;
+	plat->flags |= STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP;
 
 	err = stmmac_dvr_probe(&pdev->dev, plat, &res);
 	if (err < 0)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 73002ed923aaa..d444514db07e9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -991,7 +991,8 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
 	u32 old_ctrl, ctrl;
 
-	if (priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup)
+	if ((priv->plat->flags & STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP) &&
+	    priv->plat->serdes_powerup)
 		priv->plat->serdes_powerup(priv->dev, priv->plat->bsp_priv);
 
 	old_ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
@@ -3838,7 +3839,8 @@ static int __stmmac_open(struct net_device *dev,
 
 	stmmac_reset_queues_param(priv);
 
-	if (!priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) {
+	if (!(priv->plat->flags & STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP) &&
+	    priv->plat->serdes_powerup) {
 		ret = priv->plat->serdes_powerup(dev, priv->plat->bsp_priv);
 		if (ret < 0) {
 			netdev_err(priv->dev, "%s: Serdes powerup failed\n",
@@ -7623,7 +7625,8 @@ int stmmac_resume(struct device *dev)
 			stmmac_mdio_reset(priv->mii);
 	}
 
-	if (!priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) {
+	if (!(priv->plat->flags & STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP) &&
+	    priv->plat->serdes_powerup) {
 		ret = priv->plat->serdes_powerup(ndev,
 						 priv->plat->bsp_priv);
 
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 47ae29a988357..aeb3e75dc748c 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -209,6 +209,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_USE_PHY_WOL			BIT(2)
 #define STMMAC_FLAG_HAS_SUN8I			BIT(3)
 #define STMMAC_FLAG_TSO_EN			BIT(4)
+#define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP	BIT(5)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -293,7 +294,6 @@ struct plat_stmmacenet_data {
 	int msi_sfty_ue_vec;
 	int msi_rx_base_vec;
 	int msi_tx_base_vec;
-	bool serdes_up_after_phy_linkup;
 	const struct dwmac4_addrs *dwmac4_addrs;
 	unsigned int flags;
 };
-- 
GitLab


From fc02152bdbb28bd46df66ddcf4f469760c1b8df8 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 10:59:56 +0200
Subject: [PATCH 0107/1806] net: stmmac: replace the vlan_fail_q_en field with
 a flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-8-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++-
 include/linux/stmmac.h                            | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index faa6f4ec68389..1f1bc99571a5a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -560,7 +560,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	/* Set the maxmtu to a default of JUMBO_LEN */
 	plat->maxmtu = JUMBO_LEN;
 
-	plat->vlan_fail_q_en = true;
+	plat->flags |= STMMAC_FLAG_VLAN_FAIL_Q_EN;
 
 	/* Use the last Rx queue */
 	plat->vlan_fail_q = plat->rx_queues_to_use - 1;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d444514db07e9..c5763f60c6eff 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6923,7 +6923,8 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 	if (priv->dma_cap.tsoen)
 		dev_info(priv->device, "TSO supported\n");
 
-	priv->hw->vlan_fail_q_en = priv->plat->vlan_fail_q_en;
+	priv->hw->vlan_fail_q_en =
+		(priv->plat->flags & STMMAC_FLAG_VLAN_FAIL_Q_EN);
 	priv->hw->vlan_fail_q = priv->plat->vlan_fail_q;
 
 	/* Run HW quirks, if any */
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index aeb3e75dc748c..155cb11b1c8a3 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -210,6 +210,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_HAS_SUN8I			BIT(3)
 #define STMMAC_FLAG_TSO_EN			BIT(4)
 #define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP	BIT(5)
+#define STMMAC_FLAG_VLAN_FAIL_Q_EN		BIT(6)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -278,7 +279,6 @@ struct plat_stmmacenet_data {
 	bool en_tx_lpi_clockgating;
 	bool rx_clk_runs_in_lpi;
 	int has_xgmac;
-	bool vlan_fail_q_en;
 	u8 vlan_fail_q;
 	unsigned int eee_usecs_rate;
 	struct pci_dev *pdev;
-- 
GitLab


From 956c3f09b9c4cc9567ca11c84007545b939e61aa Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 10:59:57 +0200
Subject: [PATCH 0108/1806] net: stmmac: replace the multi_msi_en field with a
 flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-9-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 ++++---
 include/linux/stmmac.h                            | 2 +-
 3 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 1f1bc99571a5a..d8bcf94521974 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -953,7 +953,7 @@ static int stmmac_config_single_msi(struct pci_dev *pdev,
 
 	res->irq = pci_irq_vector(pdev, 0);
 	res->wol_irq = res->irq;
-	plat->multi_msi_en = 0;
+	plat->flags &= ~STMMAC_FLAG_MULTI_MSI_EN;
 	dev_info(&pdev->dev, "%s: Single IRQ enablement successful\n",
 		 __func__);
 
@@ -1005,7 +1005,7 @@ static int stmmac_config_multi_msi(struct pci_dev *pdev,
 	if (plat->msi_sfty_ue_vec < STMMAC_MSI_VEC_MAX)
 		res->sfty_ue_irq = pci_irq_vector(pdev, plat->msi_sfty_ue_vec);
 
-	plat->multi_msi_en = 1;
+	plat->flags |= STMMAC_FLAG_MULTI_MSI_EN;
 	dev_info(&pdev->dev, "%s: multi MSI enablement successful\n", __func__);
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c5763f60c6eff..ebe82e7b50fc6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3711,7 +3711,7 @@ static int stmmac_request_irq(struct net_device *dev)
 	int ret;
 
 	/* Request the IRQ lines */
-	if (priv->plat->multi_msi_en)
+	if (priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN)
 		ret = stmmac_request_irq_multi_msi(dev);
 	else
 		ret = stmmac_request_irq_single(dev);
@@ -5954,7 +5954,7 @@ static void stmmac_poll_controller(struct net_device *dev)
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return;
 
-	if (priv->plat->multi_msi_en) {
+	if (priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN) {
 		for (i = 0; i < priv->plat->rx_queues_to_use; i++)
 			stmmac_msi_intr_rx(0, &priv->dma_conf.rx_queue[i]);
 
@@ -7169,7 +7169,8 @@ int stmmac_dvr_probe(struct device *device,
 	priv->plat = plat_dat;
 	priv->ioaddr = res->addr;
 	priv->dev->base_addr = (unsigned long)res->addr;
-	priv->plat->dma_cfg->multi_msi_en = priv->plat->multi_msi_en;
+	priv->plat->dma_cfg->multi_msi_en =
+		(priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN);
 
 	priv->dev->irq = res->irq;
 	priv->wol_irq = res->wol_irq;
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 155cb11b1c8a3..3365b8071686f 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -211,6 +211,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_TSO_EN			BIT(4)
 #define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP	BIT(5)
 #define STMMAC_FLAG_VLAN_FAIL_Q_EN		BIT(6)
+#define STMMAC_FLAG_MULTI_MSI_EN		BIT(7)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -286,7 +287,6 @@ struct plat_stmmacenet_data {
 	int ext_snapshot_num;
 	bool int_snapshot_en;
 	bool ext_snapshot_en;
-	bool multi_msi_en;
 	int msi_mac_vec;
 	int msi_wol_vec;
 	int msi_lpi_vec;
-- 
GitLab


From aa5513f5d95f6b5311de859f8f466a09863bedf6 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 10:59:58 +0200
Subject: [PATCH 0109/1806] net: stmmac: replace the ext_snapshot_en field with
 a flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-10-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c     | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c      | 5 ++++-
 include/linux/stmmac.h                                | 2 +-
 4 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index d8bcf94521974..a3d0da4e9e916 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -326,7 +326,7 @@ static int intel_crosststamp(ktime_t *device,
 	/* Both internal crosstimestamping and external triggered event
 	 * timestamping cannot be run concurrently.
 	 */
-	if (priv->plat->ext_snapshot_en)
+	if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN)
 		return -EBUSY;
 
 	priv->plat->int_snapshot_en = 1;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 8b50f03056b7b..afd81aac66444 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -195,7 +195,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv)
 	 */
 	ts_status = readl(priv->ioaddr + GMAC_TIMESTAMP_STATUS);
 
-	if (!priv->plat->ext_snapshot_en)
+	if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN)
 		return;
 
 	num_snapshot = (ts_status & GMAC_TIMESTAMP_ATSNS_MASK) >>
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index b4388ca8d2116..3d7825cb30bb1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -192,7 +192,10 @@ static int stmmac_enable(struct ptp_clock_info *ptp,
 		write_unlock_irqrestore(&priv->ptp_lock, flags);
 		break;
 	case PTP_CLK_REQ_EXTTS:
-		priv->plat->ext_snapshot_en = on;
+		if (on)
+			priv->plat->flags |= STMMAC_FLAG_EXT_SNAPSHOT_EN;
+		else
+			priv->plat->flags &= ~STMMAC_FLAG_EXT_SNAPSHOT_EN;
 		mutex_lock(&priv->aux_ts_lock);
 		acr_value = readl(ptpaddr + PTP_ACR);
 		acr_value &= ~PTP_ACR_MASK;
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 3365b8071686f..0a77e8b05d3a9 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -212,6 +212,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP	BIT(5)
 #define STMMAC_FLAG_VLAN_FAIL_Q_EN		BIT(6)
 #define STMMAC_FLAG_MULTI_MSI_EN		BIT(7)
+#define STMMAC_FLAG_EXT_SNAPSHOT_EN		BIT(8)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -286,7 +287,6 @@ struct plat_stmmacenet_data {
 	int int_snapshot_num;
 	int ext_snapshot_num;
 	bool int_snapshot_en;
-	bool ext_snapshot_en;
 	int msi_mac_vec;
 	int msi_wol_vec;
 	int msi_lpi_vec;
-- 
GitLab


From 621ba7ad7891b381baf9ebf3da4ec4e95c86ea4e Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 10:59:59 +0200
Subject: [PATCH 0110/1806] net: stmmac: replace the int_snapshot_en field with
 a flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-11-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c     | 10 +++++-----
 drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c |  2 +-
 include/linux/stmmac.h                                |  2 +-
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index a3d0da4e9e916..0ffae785d8bd9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -329,7 +329,7 @@ static int intel_crosststamp(ktime_t *device,
 	if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN)
 		return -EBUSY;
 
-	priv->plat->int_snapshot_en = 1;
+	priv->plat->flags |= STMMAC_FLAG_INT_SNAPSHOT_EN;
 
 	mutex_lock(&priv->aux_ts_lock);
 	/* Enable Internal snapshot trigger */
@@ -350,7 +350,7 @@ static int intel_crosststamp(ktime_t *device,
 		break;
 	default:
 		mutex_unlock(&priv->aux_ts_lock);
-		priv->plat->int_snapshot_en = 0;
+		priv->plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN;
 		return -EINVAL;
 	}
 	writel(acr_value, ptpaddr + PTP_ACR);
@@ -376,7 +376,7 @@ static int intel_crosststamp(ktime_t *device,
 	if (!wait_event_interruptible_timeout(priv->tstamp_busy_wait,
 					      stmmac_cross_ts_isr(priv),
 					      HZ / 100)) {
-		priv->plat->int_snapshot_en = 0;
+		priv->plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN;
 		return -ETIMEDOUT;
 	}
 
@@ -395,7 +395,7 @@ static int intel_crosststamp(ktime_t *device,
 	}
 
 	system->cycles *= intel_priv->crossts_adj;
-	priv->plat->int_snapshot_en = 0;
+	priv->plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN;
 
 	return 0;
 }
@@ -609,7 +609,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->ext_snapshot_num = AUX_SNAPSHOT0;
 
 	plat->crosststamp = intel_crosststamp;
-	plat->int_snapshot_en = 0;
+	plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN;
 
 	/* Setup MSI vector offset specific to Intel mGbE controller */
 	plat->msi_mac_vec = 29;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index afd81aac66444..fa2c3ba7e9fe7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -180,7 +180,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv)
 	u64 ptp_time;
 	int i;
 
-	if (priv->plat->int_snapshot_en) {
+	if (priv->plat->flags & STMMAC_FLAG_INT_SNAPSHOT_EN) {
 		wake_up(&priv->tstamp_busy_wait);
 		return;
 	}
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 0a77e8b05d3a9..47708ddd57fd3 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -213,6 +213,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_VLAN_FAIL_Q_EN		BIT(6)
 #define STMMAC_FLAG_MULTI_MSI_EN		BIT(7)
 #define STMMAC_FLAG_EXT_SNAPSHOT_EN		BIT(8)
+#define STMMAC_FLAG_INT_SNAPSHOT_EN		BIT(9)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -286,7 +287,6 @@ struct plat_stmmacenet_data {
 	struct pci_dev *pdev;
 	int int_snapshot_num;
 	int ext_snapshot_num;
-	bool int_snapshot_en;
 	int msi_mac_vec;
 	int msi_wol_vec;
 	int msi_lpi_vec;
-- 
GitLab


From 743dd1db85f40be1e2c7416c83f0289aaa260ceb Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 11:00:00 +0200
Subject: [PATCH 0111/1806] net: stmmac: replace the rx_clk_runs_in_lpi field
 with a flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-12-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c       | 3 ++-
 include/linux/stmmac.h                                  | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 4b58904ee132b..735525ba8b931 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -786,7 +786,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	if (of_property_read_bool(np, "snps,tso"))
 		plat_dat->flags |= STMMAC_FLAG_TSO_EN;
 	if (of_device_is_compatible(np, "qcom,qcs404-ethqos"))
-		plat_dat->rx_clk_runs_in_lpi = 1;
+		plat_dat->flags |= STMMAC_FLAG_RX_CLK_RUNS_IN_LPI;
 	if (data->has_integrated_pcs)
 		plat_dat->flags |= STMMAC_FLAG_HAS_INTEGRATED_PCS;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ebe82e7b50fc6..2d68a6e84b0e4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1085,7 +1085,8 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 	stmmac_mac_set(priv, priv->ioaddr, true);
 	if (phy && priv->dma_cap.eee) {
 		priv->eee_active =
-			phy_init_eee(phy, !priv->plat->rx_clk_runs_in_lpi) >= 0;
+			phy_init_eee(phy, !(priv->plat->flags &
+				STMMAC_FLAG_RX_CLK_RUNS_IN_LPI)) >= 0;
 		priv->eee_enabled = stmmac_eee_init(priv);
 		priv->tx_lpi_enabled = priv->eee_enabled;
 		stmmac_set_eee_pls(priv, priv->hw, true);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 47708ddd57fd3..c3769dad82381 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -214,6 +214,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_MULTI_MSI_EN		BIT(7)
 #define STMMAC_FLAG_EXT_SNAPSHOT_EN		BIT(8)
 #define STMMAC_FLAG_INT_SNAPSHOT_EN		BIT(9)
+#define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI		BIT(10)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -280,7 +281,6 @@ struct plat_stmmacenet_data {
 	int rss_en;
 	int mac_port_sel_speed;
 	bool en_tx_lpi_clockgating;
-	bool rx_clk_runs_in_lpi;
 	int has_xgmac;
 	u8 vlan_fail_q;
 	unsigned int eee_usecs_rate;
-- 
GitLab


From 9d0c0d5ebd635f914ab2ab691b68e8754fbe0a57 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Jul 2023 11:00:01 +0200
Subject: [PATCH 0112/1806] net: stmmac: replace the en_tx_lpi_clockgating
 field with a flag

Drop the boolean field of the plat_stmmacenet_data structure in favor of a
simple bitfield flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230710090001.303225-13-brgl@bgdev.pl
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c     | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 4 ++--
 include/linux/stmmac.h                                | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 2d68a6e84b0e4..efe85b086abec 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -421,7 +421,7 @@ static int stmmac_enable_eee_mode(struct stmmac_priv *priv)
 	/* Check and enter in LPI mode */
 	if (!priv->tx_path_in_lpi_mode)
 		stmmac_set_eee_mode(priv, priv->hw,
-				priv->plat->en_tx_lpi_clockgating);
+			priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLOCKGATING);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index f51522cb00611..23d53ea04b24d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -466,8 +466,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	plat->force_sf_dma_mode =
 		of_property_read_bool(np, "snps,force_sf_dma_mode");
 
-	plat->en_tx_lpi_clockgating =
-		of_property_read_bool(np, "snps,en-tx-lpi-clockgating");
+	if (of_property_read_bool(np, "snps,en-tx-lpi-clockgating"))
+		plat->flags |= STMMAC_FLAG_EN_TX_LPI_CLOCKGATING;
 
 	/* Set the maxmtu to a default of JUMBO_LEN in case the
 	 * parameter is not present in the device tree.
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index c3769dad82381..ef67dba775d04 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -215,6 +215,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_EXT_SNAPSHOT_EN		BIT(8)
 #define STMMAC_FLAG_INT_SNAPSHOT_EN		BIT(9)
 #define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI		BIT(10)
+#define STMMAC_FLAG_EN_TX_LPI_CLOCKGATING	BIT(11)
 
 struct plat_stmmacenet_data {
 	int bus_id;
@@ -280,7 +281,6 @@ struct plat_stmmacenet_data {
 	int has_gmac4;
 	int rss_en;
 	int mac_port_sel_speed;
-	bool en_tx_lpi_clockgating;
 	int has_xgmac;
 	u8 vlan_fail_q;
 	unsigned int eee_usecs_rate;
-- 
GitLab


From 5b52ad34f9487b2c2d1e60fe37e5bd5656b4dac8 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Tue, 11 Jul 2023 15:06:08 +0200
Subject: [PATCH 0113/1806] security: Constify sk in the sk_getsecid hook.

The sk_getsecid hook shouldn't need to modify its socket argument.
Make it const so that callers of security_sk_classify_flow() can use a
const struct sock *.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/lsm_hook_defs.h | 2 +-
 include/linux/security.h      | 5 +++--
 security/security.c           | 2 +-
 security/selinux/hooks.c      | 4 ++--
 4 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 7308a1a7599b4..4f2621e876340 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -316,7 +316,7 @@ LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority)
 LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk)
 LSM_HOOK(void, LSM_RET_VOID, sk_clone_security, const struct sock *sk,
 	 struct sock *newsk)
-LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, struct sock *sk, u32 *secid)
+LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, const struct sock *sk, u32 *secid)
 LSM_HOOK(void, LSM_RET_VOID, sock_graft, struct sock *sk, struct socket *parent)
 LSM_HOOK(int, 0, inet_conn_request, const struct sock *sk, struct sk_buff *skb,
 	 struct request_sock *req)
diff --git a/include/linux/security.h b/include/linux/security.h
index 32828502f09ea..994cf099d9ac9 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1439,7 +1439,8 @@ int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u
 int security_sk_alloc(struct sock *sk, int family, gfp_t priority);
 void security_sk_free(struct sock *sk);
 void security_sk_clone(const struct sock *sk, struct sock *newsk);
-void security_sk_classify_flow(struct sock *sk, struct flowi_common *flic);
+void security_sk_classify_flow(const struct sock *sk,
+			       struct flowi_common *flic);
 void security_req_classify_flow(const struct request_sock *req,
 				struct flowi_common *flic);
 void security_sock_graft(struct sock*sk, struct socket *parent);
@@ -1597,7 +1598,7 @@ static inline void security_sk_clone(const struct sock *sk, struct sock *newsk)
 {
 }
 
-static inline void security_sk_classify_flow(struct sock *sk,
+static inline void security_sk_classify_flow(const struct sock *sk,
 					     struct flowi_common *flic)
 {
 }
diff --git a/security/security.c b/security/security.c
index b720424ca37d9..2dfc7b9f6ed99 100644
--- a/security/security.c
+++ b/security/security.c
@@ -4396,7 +4396,7 @@ void security_sk_clone(const struct sock *sk, struct sock *newsk)
 }
 EXPORT_SYMBOL(security_sk_clone);
 
-void security_sk_classify_flow(struct sock *sk, struct flowi_common *flic)
+void security_sk_classify_flow(const struct sock *sk, struct flowi_common *flic)
 {
 	call_void_hook(sk_getsecid, sk, &flic->flowic_secid);
 }
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index d06e350fedee5..2bdc48dd86709 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5167,12 +5167,12 @@ static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk)
 	selinux_netlbl_sk_security_reset(newsksec);
 }
 
-static void selinux_sk_getsecid(struct sock *sk, u32 *secid)
+static void selinux_sk_getsecid(const struct sock *sk, u32 *secid)
 {
 	if (!sk)
 		*secid = SECINITSID_ANY_SOCKET;
 	else {
-		struct sk_security_struct *sksec = sk->sk_security;
+		const struct sk_security_struct *sksec = sk->sk_security;
 
 		*secid = sksec->sid;
 	}
-- 
GitLab


From 8d6eba33a2726e463eeab5c42b8eb373d7462127 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Tue, 11 Jul 2023 15:06:14 +0200
Subject: [PATCH 0114/1806] ipv4: Constify the sk parameter of
 ip_route_output_*().

These functions don't need to modify the socket, so let's allow the
callers to pass a const struct sock *.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/route.h b/include/net/route.h
index 5a5c726472bd6..d8d1501551953 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -163,7 +163,7 @@ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr,
 }
 
 static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi4 *fl4,
-						   struct sock *sk,
+						   const struct sock *sk,
 						   __be32 daddr, __be32 saddr,
 						   __be16 dport, __be16 sport,
 						   __u8 proto, __u8 tos, int oif)
@@ -309,7 +309,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
 static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst,
 					      __be32 src, int oif, u8 protocol,
 					      __be16 sport, __be16 dport,
-					      struct sock *sk)
+					      const struct sock *sk)
 {
 	struct net *net = sock_net(sk);
 	struct rtable *rt;
@@ -330,7 +330,7 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst,
 static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable *rt,
 					       __be16 orig_sport, __be16 orig_dport,
 					       __be16 sport, __be16 dport,
-					       struct sock *sk)
+					       const struct sock *sk)
 {
 	if (sport != orig_sport || dport != orig_dport) {
 		fl4->fl4_dport = dport;
-- 
GitLab


From 5bc67a854cb4982aa7746e8d2206a00b46a9cc0f Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Tue, 11 Jul 2023 15:06:21 +0200
Subject: [PATCH 0115/1806] ipv6: Constify the sk parameter of several helper
 functions.

icmpv6_flow_init(), ip6_datagram_flow_key_init() and ip6_mc_hdr() don't
need to modify their sk argument. Make that explicit using const.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/icmpv6.h | 10 ++++------
 net/ipv6/datagram.c    |  7 ++++---
 net/ipv6/icmp.c        |  6 ++----
 net/ipv6/mcast.c       |  8 +++-----
 4 files changed, 13 insertions(+), 18 deletions(-)

diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index db0f4fcfdaf4f..e3b3b0fa2a8f8 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -85,12 +85,10 @@ extern void				icmpv6_param_prob_reason(struct sk_buff *skb,
 
 struct flowi6;
 struct in6_addr;
-extern void				icmpv6_flow_init(struct sock *sk,
-							 struct flowi6 *fl6,
-							 u8 type,
-							 const struct in6_addr *saddr,
-							 const struct in6_addr *daddr,
-							 int oif);
+
+void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type,
+		      const struct in6_addr *saddr,
+		      const struct in6_addr *daddr, int oif);
 
 static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
 {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 9b6818453afea..d80d6024cafa9 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -38,10 +38,11 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
 	return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
 }
 
-static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
+static void ip6_datagram_flow_key_init(struct flowi6 *fl6,
+				       const struct sock *sk)
 {
-	struct inet_sock *inet = inet_sk(sk);
-	struct ipv6_pinfo *np = inet6_sk(sk);
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct ipv6_pinfo *np = inet6_sk(sk);
 	int oif = sk->sk_bound_dev_if;
 
 	memset(fl6, 0, sizeof(*fl6));
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 65fa5014bc85e..6d88f5248c1f3 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -1034,11 +1034,9 @@ drop_no_count:
 	return 0;
 }
 
-void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
-		      u8 type,
+void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type,
 		      const struct in6_addr *saddr,
-		      const struct in6_addr *daddr,
-		      int oif)
+		      const struct in6_addr *daddr, int oif)
 {
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->saddr = *saddr;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 714cdc9e2b8ed..5ce25bcb9974d 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1699,11 +1699,9 @@ mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted)
 	return scount;
 }
 
-static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb,
-		       struct net_device *dev,
-		       const struct in6_addr *saddr,
-		       const struct in6_addr *daddr,
-		       int proto, int len)
+static void ip6_mc_hdr(const struct sock *sk, struct sk_buff *skb,
+		       struct net_device *dev, const struct in6_addr *saddr,
+		       const struct in6_addr *daddr, int proto, int len)
 {
 	struct ipv6hdr *hdr;
 
-- 
GitLab


From dc4c399d215d76689ebadec7ed3184bcf213e2ee Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Tue, 11 Jul 2023 15:06:26 +0200
Subject: [PATCH 0116/1806] pptp: Constify the po parameter of
 pptp_route_output().

Make it explicit that this function doesn't modify the socket passed as
parameter.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 32183f24e63ff..57d38b27812d5 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -129,10 +129,10 @@ static void del_chan(struct pppox_sock *sock)
 	spin_unlock(&chan_lock);
 }
 
-static struct rtable *pptp_route_output(struct pppox_sock *po,
+static struct rtable *pptp_route_output(const struct pppox_sock *po,
 					struct flowi4 *fl4)
 {
-	struct sock *sk = &po->sk;
+	const struct sock *sk = &po->sk;
 	struct net *net;
 
 	net = sock_net(sk);
-- 
GitLab


From 88085b3b83f55eab1be57f4eb0f69446717f23fb Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Thu, 13 Jul 2023 00:45:58 +0100
Subject: [PATCH 0117/1806] net: dsa: ar9331: Use maple tree register cache

We now have a regmap cache which uses a maple tree to store the register
state, this is a more modern data structure and the regmap level code
using it makes a number of assumptions better tuned for modern hardware
than those made by the rbtree cache type that the at9331 driver uses.
Switch the ar9331 driver to use the more modern data structure.

This should have minimal practical impact, it's mainly code
modernisation.

Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/qca/ar9331.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c
index b2bf78ac485eb..72730dcc9ca97 100644
--- a/drivers/net/dsa/qca/ar9331.c
+++ b/drivers/net/dsa/qca/ar9331.c
@@ -1010,7 +1010,7 @@ static const struct regmap_config ar9331_mdio_regmap_config = {
 	.wr_table = &ar9331_register_set,
 	.rd_table = &ar9331_register_set,
 
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_MAPLE,
 };
 
 static struct regmap_bus ar9331_sw_bus = {
-- 
GitLab


From 6963e463256e4a5fa1635b3636aa38b058668122 Mon Sep 17 00:00:00 2001
From: Mengyuan Lou <mengyuanlou@net-swift.com>
Date: Thu, 13 Jul 2023 14:09:11 +0800
Subject: [PATCH 0118/1806] net: ngbe: add Wake on Lan support

Implement ethtool_ops get_wol and set_wol.
Implement Wake-on-LAN support.

Wol requires hardware board support which use sub id
to identify.
Magic packets are checked by fw, for now just support
WAKE_MAGIC.

Signed-off-by: Mengyuan Lou <mengyuanlou@net-swift.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/wangxun/libwx/wx_hw.c    |  3 +-
 drivers/net/ethernet/wangxun/libwx/wx_hw.h    |  1 +
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |  6 +-
 .../net/ethernet/wangxun/ngbe/ngbe_ethtool.c  | 35 ++++++++++
 drivers/net/ethernet/wangxun/ngbe/ngbe_main.c | 64 +++++++++++++++++--
 drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c |  1 +
 6 files changed, 102 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index 39a9aeee7aab2..ad09ab1d12095 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -1501,7 +1501,7 @@ static void wx_restore_vlan(struct wx *wx)
  *
  * Configure the Rx unit of the MAC after a reset.
  **/
-static void wx_configure_rx(struct wx *wx)
+void wx_configure_rx(struct wx *wx)
 {
 	u32 psrtype, i;
 	int ret;
@@ -1545,6 +1545,7 @@ static void wx_configure_rx(struct wx *wx)
 	wx_enable_rx(wx);
 	wx_enable_sec_rx_path(wx);
 }
+EXPORT_SYMBOL(wx_configure_rx);
 
 static void wx_configure_isb(struct wx *wx)
 {
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
index 1f93ca32c9212..b95090e973aeb 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
@@ -25,6 +25,7 @@ void wx_disable_rx(struct wx *wx);
 void wx_set_rx_mode(struct net_device *netdev);
 int wx_change_mtu(struct net_device *netdev, int new_mtu);
 void wx_disable_rx_queue(struct wx *wx, struct wx_ring *ring);
+void wx_configure_rx(struct wx *wx);
 void wx_configure(struct wx *wx);
 void wx_start_hw(struct wx *wx);
 int wx_disable_pcie_master(struct wx *wx);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 29dfb561887d3..1de88a33a698a 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -160,6 +160,10 @@
 #define WX_PSR_LAN_FLEX_DW_H(_i)     (0x15C04 + ((_i) * 16))
 #define WX_PSR_LAN_FLEX_MSK(_i)      (0x15C08 + ((_i) * 16))
 
+#define WX_PSR_WKUP_CTL              0x15B80
+/* Wake Up Filter Control Bit */
+#define WX_PSR_WKUP_CTL_MAG          BIT(1) /* Magic Packet Wakeup Enable */
+
 /* vlan tbl */
 #define WX_PSR_VLAN_TBL(_i)          (0x16000 + ((_i) * 4))
 
@@ -846,7 +850,7 @@ struct wx {
 	int duplex;
 	struct phy_device *phydev;
 
-	bool wol_enabled;
+	bool wol_hw_supported;
 	bool ncsi_enabled;
 	bool gpio_ctrl;
 	raw_spinlock_t gpio_lock;
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
index 5b25834baf386..ec0e869e9aacf 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
@@ -6,14 +6,49 @@
 #include <linux/netdevice.h>
 
 #include "../libwx/wx_ethtool.h"
+#include "../libwx/wx_type.h"
 #include "ngbe_ethtool.h"
 
+static void ngbe_get_wol(struct net_device *netdev,
+			 struct ethtool_wolinfo *wol)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	if (!wx->wol_hw_supported)
+		return;
+	wol->supported = WAKE_MAGIC;
+	wol->wolopts = 0;
+	if (wx->wol & WX_PSR_WKUP_CTL_MAG)
+		wol->wolopts |= WAKE_MAGIC;
+}
+
+static int ngbe_set_wol(struct net_device *netdev,
+			struct ethtool_wolinfo *wol)
+{
+	struct wx *wx = netdev_priv(netdev);
+	struct pci_dev *pdev = wx->pdev;
+
+	if (!wx->wol_hw_supported)
+		return -EOPNOTSUPP;
+
+	wx->wol = 0;
+	if (wol->wolopts & WAKE_MAGIC)
+		wx->wol = WX_PSR_WKUP_CTL_MAG;
+	netdev->wol_enabled = !!(wx->wol);
+	wr32(wx, WX_PSR_WKUP_CTL, wx->wol);
+	device_set_wakeup_enable(&pdev->dev, netdev->wol_enabled);
+
+	return 0;
+}
+
 static const struct ethtool_ops ngbe_ethtool_ops = {
 	.get_drvinfo		= wx_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 	.nway_reset		= phy_ethtool_nway_reset,
+	.get_wol		= ngbe_get_wol,
+	.set_wol		= ngbe_set_wol,
 };
 
 void ngbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index c99a5d3de72e6..2b431db6085a6 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -62,7 +62,7 @@ static void ngbe_init_type_code(struct wx *wx)
 		       em_mac_type_rgmii :
 		       em_mac_type_mdi;
 
-	wx->wol_enabled = (wol_mask == NGBE_WOL_SUP) ? 1 : 0;
+	wx->wol_hw_supported = (wol_mask == NGBE_WOL_SUP) ? 1 : 0;
 	wx->ncsi_enabled = (ncsi_mask == NGBE_NCSI_MASK ||
 			   type_mask == NGBE_SUBID_OCP_CARD) ? 1 : 0;
 
@@ -440,14 +440,26 @@ static void ngbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake)
 {
 	struct wx *wx = pci_get_drvdata(pdev);
 	struct net_device *netdev;
+	u32 wufc = wx->wol;
 
 	netdev = wx->netdev;
+	rtnl_lock();
 	netif_device_detach(netdev);
 
-	rtnl_lock();
 	if (netif_running(netdev))
-		ngbe_down(wx);
+		ngbe_close(netdev);
+	wx_clear_interrupt_scheme(wx);
 	rtnl_unlock();
+
+	if (wufc) {
+		wx_set_rx_mode(netdev);
+		wx_configure_rx(wx);
+		wr32(wx, NGBE_PSR_WKUP_CTL, wufc);
+	} else {
+		wr32(wx, NGBE_PSR_WKUP_CTL, 0);
+	}
+	pci_wake_from_d3(pdev, !!wufc);
+	*enable_wake = !!wufc;
 	wx_control_hw(wx, false);
 
 	pci_disable_device(pdev);
@@ -621,12 +633,11 @@ static int ngbe_probe(struct pci_dev *pdev,
 	}
 
 	wx->wol = 0;
-	if (wx->wol_enabled)
+	if (wx->wol_hw_supported)
 		wx->wol = NGBE_PSR_WKUP_CTL_MAG;
 
-	wx->wol_enabled = !!(wx->wol);
+	netdev->wol_enabled = !!(wx->wol);
 	wr32(wx, NGBE_PSR_WKUP_CTL, wx->wol);
-
 	device_set_wakeup_enable(&pdev->dev, wx->wol);
 
 	/* Save off EEPROM version number and Option Rom version which
@@ -712,11 +723,52 @@ static void ngbe_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
+static int ngbe_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	bool wake;
+
+	ngbe_dev_shutdown(pdev, &wake);
+	device_set_wakeup_enable(&pdev->dev, wake);
+
+	return 0;
+}
+
+static int ngbe_resume(struct pci_dev *pdev)
+{
+	struct net_device *netdev;
+	struct wx *wx;
+	u32 err;
+
+	wx = pci_get_drvdata(pdev);
+	netdev = wx->netdev;
+
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		wx_err(wx, "Cannot enable PCI device from suspend\n");
+		return err;
+	}
+	pci_set_master(pdev);
+	device_wakeup_disable(&pdev->dev);
+
+	ngbe_reset_hw(wx);
+	rtnl_lock();
+	err = wx_init_interrupt_scheme(wx);
+	if (!err && netif_running(netdev))
+		err = ngbe_open(netdev);
+	if (!err)
+		netif_device_attach(netdev);
+	rtnl_unlock();
+
+	return 0;
+}
+
 static struct pci_driver ngbe_driver = {
 	.name     = ngbe_driver_name,
 	.id_table = ngbe_pci_tbl,
 	.probe    = ngbe_probe,
 	.remove   = ngbe_remove,
+	.suspend  = ngbe_suspend,
+	.resume   = ngbe_resume,
 	.shutdown = ngbe_shutdown,
 };
 
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
index c9ddbbc3fa4f7..cc2f325a52f78 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
@@ -236,6 +236,7 @@ static void ngbe_phy_fixup(struct wx *wx)
 	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
 	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
 
+	phydev->mac_managed_pm = true;
 	if (wx->mac_type != em_mac_type_mdi)
 		return;
 	/* disable EEE, internal phy does not support eee */
-- 
GitLab


From 90ef0a7b0622c62758b2638604927867775479ea Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:07 +0100
Subject: [PATCH 0119/1806] net: phylink: add pcs_enable()/pcs_disable()
 methods

Add phylink PCS enable/disable callbacks that will allow us to place
IEEE 802.3 register compliant PCS in power-down mode while not being
used.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 48 +++++++++++++++++++++++++++++++--------
 include/linux/phylink.h   | 16 +++++++++++++
 2 files changed, 55 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index d0aaa5cad8533..748c62efceb83 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -34,6 +34,10 @@ enum {
 	PHYLINK_DISABLE_STOPPED,
 	PHYLINK_DISABLE_LINK,
 	PHYLINK_DISABLE_MAC_WOL,
+
+	PCS_STATE_DOWN = 0,
+	PCS_STATE_STARTING,
+	PCS_STATE_STARTED,
 };
 
 /**
@@ -72,6 +76,7 @@ struct phylink {
 	struct phylink_link_state phy_state;
 	struct work_struct resolve;
 	unsigned int pcs_neg_mode;
+	unsigned int pcs_state;
 
 	bool mac_link_dropped;
 	bool using_mac_select_pcs;
@@ -993,6 +998,22 @@ static void phylink_resolve_an_pause(struct phylink_link_state *state)
 	}
 }
 
+static void phylink_pcs_disable(struct phylink_pcs *pcs)
+{
+	if (pcs && pcs->ops->pcs_disable)
+		pcs->ops->pcs_disable(pcs);
+}
+
+static int phylink_pcs_enable(struct phylink_pcs *pcs)
+{
+	int err = 0;
+
+	if (pcs && pcs->ops->pcs_enable)
+		err = pcs->ops->pcs_enable(pcs);
+
+	return err;
+}
+
 static int phylink_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
 			      const struct phylink_link_state *state,
 			      bool permit_pause_to_mac)
@@ -1095,11 +1116,17 @@ static void phylink_major_config(struct phylink *pl, bool restart,
 	/* If we have a new PCS, switch to the new PCS after preparing the MAC
 	 * for the change.
 	 */
-	if (pcs_changed)
+	if (pcs_changed) {
+		phylink_pcs_disable(pl->pcs);
+
 		pl->pcs = pcs;
+	}
 
 	phylink_mac_config(pl, state);
 
+	if (pl->pcs_state == PCS_STATE_STARTING || pcs_changed)
+		phylink_pcs_enable(pl->pcs);
+
 	neg_mode = pl->cur_link_an_mode;
 	if (pl->pcs && pl->pcs->neg_mode)
 		neg_mode = pl->pcs_neg_mode;
@@ -1586,6 +1613,7 @@ struct phylink *phylink_create(struct phylink_config *config,
 	pl->link_config.pause = MLO_PAUSE_AN;
 	pl->link_config.speed = SPEED_UNKNOWN;
 	pl->link_config.duplex = DUPLEX_UNKNOWN;
+	pl->pcs_state = PCS_STATE_DOWN;
 	pl->mac_ops = mac_ops;
 	__set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);
 	timer_setup(&pl->link_poll, phylink_fixed_poll, 0);
@@ -1987,6 +2015,8 @@ void phylink_start(struct phylink *pl)
 	if (pl->netdev)
 		netif_carrier_off(pl->netdev);
 
+	pl->pcs_state = PCS_STATE_STARTING;
+
 	/* Apply the link configuration to the MAC when starting. This allows
 	 * a fixed-link to start with the correct parameters, and also
 	 * ensures that we set the appropriate advertisement for Serdes links.
@@ -1997,6 +2027,8 @@ void phylink_start(struct phylink *pl)
 	 */
 	phylink_mac_initial_config(pl, true);
 
+	pl->pcs_state = PCS_STATE_STARTED;
+
 	phylink_enable_and_run_resolve(pl, PHYLINK_DISABLE_STOPPED);
 
 	if (pl->cfg_link_an_mode == MLO_AN_FIXED && pl->link_gpio) {
@@ -2015,15 +2047,9 @@ void phylink_start(struct phylink *pl)
 			poll = true;
 	}
 
-	switch (pl->cfg_link_an_mode) {
-	case MLO_AN_FIXED:
+	if (pl->cfg_link_an_mode == MLO_AN_FIXED)
 		poll |= pl->config->poll_fixed_state;
-		break;
-	case MLO_AN_INBAND:
-		if (pl->pcs)
-			poll |= pl->pcs->poll;
-		break;
-	}
+
 	if (poll)
 		mod_timer(&pl->link_poll, jiffies + HZ);
 	if (pl->phydev)
@@ -2060,6 +2086,10 @@ void phylink_stop(struct phylink *pl)
 	}
 
 	phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_STOPPED);
+
+	pl->pcs_state = PCS_STATE_DOWN;
+
+	phylink_pcs_disable(pl->pcs);
 }
 EXPORT_SYMBOL_GPL(phylink_stop);
 
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 1817940a3418e..8e2fdd48a935f 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -535,6 +535,8 @@ struct phylink_pcs {
 /**
  * struct phylink_pcs_ops - MAC PCS operations structure.
  * @pcs_validate: validate the link configuration.
+ * @pcs_enable: enable the PCS.
+ * @pcs_disable: disable the PCS.
  * @pcs_get_state: read the current MAC PCS link state from the hardware.
  * @pcs_config: configure the MAC PCS for the selected mode and state.
  * @pcs_an_restart: restart 802.3z BaseX autonegotiation.
@@ -544,6 +546,8 @@ struct phylink_pcs {
 struct phylink_pcs_ops {
 	int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported,
 			    const struct phylink_link_state *state);
+	int (*pcs_enable)(struct phylink_pcs *pcs);
+	void (*pcs_disable)(struct phylink_pcs *pcs);
 	void (*pcs_get_state)(struct phylink_pcs *pcs,
 			      struct phylink_link_state *state);
 	int (*pcs_config)(struct phylink_pcs *pcs, unsigned int neg_mode,
@@ -573,6 +577,18 @@ struct phylink_pcs_ops {
 int pcs_validate(struct phylink_pcs *pcs, unsigned long *supported,
 		 const struct phylink_link_state *state);
 
+/**
+ * pcs_enable() - enable the PCS.
+ * @pcs: a pointer to a &struct phylink_pcs.
+ */
+int pcs_enable(struct phylink_pcs *pcs);
+
+/**
+ * pcs_disable() - disable the PCS.
+ * @pcs: a pointer to a &struct phylink_pcs.
+ */
+void pcs_disable(struct phylink_pcs *pcs);
+
 /**
  * pcs_get_state() - Read the current inband link state from the hardware
  * @pcs: a pointer to a &struct phylink_pcs.
-- 
GitLab


From aee6098822ed8a298ad817da8339ba4c7ea381fe Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:12 +0100
Subject: [PATCH 0120/1806] net: phylink: add
 pcs_pre_config()/pcs_post_config() methods

Add hooks that are called before and after the mac_config() call,
which will be needed to deal with errata workarounds for the
Marvell 88e639x DSA switches.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 24 ++++++++++++++++++++++++
 include/linux/phylink.h   |  6 ++++++
 2 files changed, 30 insertions(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 748c62efceb83..9840a2952309a 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -998,6 +998,24 @@ static void phylink_resolve_an_pause(struct phylink_link_state *state)
 	}
 }
 
+static void phylink_pcs_pre_config(struct phylink_pcs *pcs,
+				   phy_interface_t interface)
+{
+	if (pcs && pcs->ops->pcs_pre_config)
+		pcs->ops->pcs_pre_config(pcs, interface);
+}
+
+static int phylink_pcs_post_config(struct phylink_pcs *pcs,
+				   phy_interface_t interface)
+{
+	int err = 0;
+
+	if (pcs && pcs->ops->pcs_post_config)
+		err = pcs->ops->pcs_post_config(pcs, interface);
+
+	return err;
+}
+
 static void phylink_pcs_disable(struct phylink_pcs *pcs)
 {
 	if (pcs && pcs->ops->pcs_disable)
@@ -1122,8 +1140,14 @@ static void phylink_major_config(struct phylink *pl, bool restart,
 		pl->pcs = pcs;
 	}
 
+	if (pl->pcs)
+		phylink_pcs_pre_config(pl->pcs, state->interface);
+
 	phylink_mac_config(pl, state);
 
+	if (pl->pcs)
+		phylink_pcs_post_config(pl->pcs, state->interface);
+
 	if (pl->pcs_state == PCS_STATE_STARTING || pcs_changed)
 		phylink_pcs_enable(pl->pcs);
 
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 8e2fdd48a935f..99fc2fa606955 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -537,6 +537,8 @@ struct phylink_pcs {
  * @pcs_validate: validate the link configuration.
  * @pcs_enable: enable the PCS.
  * @pcs_disable: disable the PCS.
+ * @pcs_pre_config: pre-mac_config method (for errata)
+ * @pcs_post_config: post-mac_config method (for arrata)
  * @pcs_get_state: read the current MAC PCS link state from the hardware.
  * @pcs_config: configure the MAC PCS for the selected mode and state.
  * @pcs_an_restart: restart 802.3z BaseX autonegotiation.
@@ -548,6 +550,10 @@ struct phylink_pcs_ops {
 			    const struct phylink_link_state *state);
 	int (*pcs_enable)(struct phylink_pcs *pcs);
 	void (*pcs_disable)(struct phylink_pcs *pcs);
+	void (*pcs_pre_config)(struct phylink_pcs *pcs,
+			       phy_interface_t interface);
+	int (*pcs_post_config)(struct phylink_pcs *pcs,
+			       phy_interface_t interface);
 	void (*pcs_get_state)(struct phylink_pcs *pcs,
 			      struct phylink_link_state *state);
 	int (*pcs_config)(struct phylink_pcs *pcs, unsigned int neg_mode,
-- 
GitLab


From 24699cc1ff3e633d7c3a0d3ef394243db11757ec Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:17 +0100
Subject: [PATCH 0121/1806] net: phylink: add support for PCS link change
 notifications

Add a function, phylink_pcs_change() which can be used by PCs drivers
to notify phylink about changes to the PCS link state.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 38 ++++++++++++++++++++++++++++++++++----
 include/linux/phylink.h   |  7 +++++++
 2 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 9840a2952309a..71b1012ef3be8 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1137,6 +1137,11 @@ static void phylink_major_config(struct phylink *pl, bool restart,
 	if (pcs_changed) {
 		phylink_pcs_disable(pl->pcs);
 
+		if (pl->pcs)
+			pl->pcs->phylink = NULL;
+
+		pcs->phylink = pl;
+
 		pl->pcs = pcs;
 	}
 
@@ -1991,6 +1996,14 @@ void phylink_disconnect_phy(struct phylink *pl)
 }
 EXPORT_SYMBOL_GPL(phylink_disconnect_phy);
 
+static void phylink_link_changed(struct phylink *pl, bool up, const char *what)
+{
+	if (!up)
+		pl->mac_link_dropped = true;
+	phylink_run_resolve(pl);
+	phylink_dbg(pl, "%s link %s\n", what, up ? "up" : "down");
+}
+
 /**
  * phylink_mac_change() - notify phylink of a change in MAC state
  * @pl: a pointer to a &struct phylink returned from phylink_create()
@@ -2001,13 +2014,30 @@ EXPORT_SYMBOL_GPL(phylink_disconnect_phy);
  */
 void phylink_mac_change(struct phylink *pl, bool up)
 {
-	if (!up)
-		pl->mac_link_dropped = true;
-	phylink_run_resolve(pl);
-	phylink_dbg(pl, "mac link %s\n", up ? "up" : "down");
+	phylink_link_changed(pl, up, "mac");
 }
 EXPORT_SYMBOL_GPL(phylink_mac_change);
 
+/**
+ * phylink_pcs_change() - notify phylink of a change to PCS link state
+ * @pcs: pointer to &struct phylink_pcs
+ * @up: indicates whether the link is currently up.
+ *
+ * The PCS driver should call this when the state of its link changes
+ * (e.g. link failure, new negotiation results, etc.) Note: it should
+ * not determine "up" by reading the BMSR. If in doubt about the link
+ * state at interrupt time, then pass true if pcs_get_state() returns
+ * the latched link-down state, otherwise pass false.
+ */
+void phylink_pcs_change(struct phylink_pcs *pcs, bool up)
+{
+	struct phylink *pl = pcs->phylink;
+
+	if (pl)
+		phylink_link_changed(pl, up, "pcs");
+}
+EXPORT_SYMBOL_GPL(phylink_pcs_change);
+
 static irqreturn_t phylink_link_handler(int irq, void *data)
 {
 	struct phylink *pl = data;
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 99fc2fa606955..b28aa3eef7d56 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -9,6 +9,7 @@ struct device_node;
 struct ethtool_cmd;
 struct fwnode_handle;
 struct net_device;
+struct phylink;
 
 enum {
 	MLO_PAUSE_NONE,
@@ -520,14 +521,19 @@ struct phylink_pcs_ops;
 /**
  * struct phylink_pcs - PHYLINK PCS instance
  * @ops: a pointer to the &struct phylink_pcs_ops structure
+ * @phylink: pointer to &struct phylink_config
  * @neg_mode: provide PCS neg mode via "mode" argument
  * @poll: poll the PCS for link changes
  *
  * This structure is designed to be embedded within the PCS private data,
  * and will be passed between phylink and the PCS.
+ *
+ * The @phylink member is private to phylink and must not be touched by
+ * the PCS driver.
  */
 struct phylink_pcs {
 	const struct phylink_pcs_ops *ops;
+	struct phylink *phylink;
 	bool neg_mode;
 	bool poll;
 };
@@ -699,6 +705,7 @@ int phylink_fwnode_phy_connect(struct phylink *pl,
 void phylink_disconnect_phy(struct phylink *);
 
 void phylink_mac_change(struct phylink *, bool up);
+void phylink_pcs_change(struct phylink_pcs *, bool up);
 
 void phylink_start(struct phylink *);
 void phylink_stop(struct phylink *);
-- 
GitLab


From e6a45700e7e19b1c945ee56feab429ff8489370b Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:22 +0100
Subject: [PATCH 0122/1806] net: mdio: add unlocked mdiobus and mdiodev bus
 accessors

Add the following unlocked accessors to complete the set:
__mdiobus_modify()
__mdiodev_read()
__mdiodev_write()
__mdiodev_modify()
__mdiodev_modify_changed()
which we will need for Marvell DSA PCS conversion.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 24 ++++++++++++++++++++++--
 include/linux/mdio.h       | 26 ++++++++++++++++++++++++++
 2 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 8b3618d3da4aa..bc04048de2faf 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -1210,6 +1210,26 @@ int mdiobus_c45_write_nested(struct mii_bus *bus, int addr, int devad,
 }
 EXPORT_SYMBOL(mdiobus_c45_write_nested);
 
+/*
+ * __mdiobus_modify - Convenience function for modifying a given mdio device
+ *	register
+ * @bus: the mii_bus struct
+ * @addr: the phy address
+ * @regnum: register number to write
+ * @mask: bit mask of bits to clear
+ * @set: bit mask of bits to set
+ */
+int __mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask,
+		     u16 set)
+{
+	int err;
+
+	err = __mdiobus_modify_changed(bus, addr, regnum, mask, set);
+
+	return err < 0 ? err : 0;
+}
+EXPORT_SYMBOL_GPL(__mdiobus_modify);
+
 /**
  * mdiobus_modify - Convenience function for modifying a given mdio device
  *	register
@@ -1224,10 +1244,10 @@ int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set)
 	int err;
 
 	mutex_lock(&bus->mdio_lock);
-	err = __mdiobus_modify_changed(bus, addr, regnum, mask, set);
+	err = __mdiobus_modify(bus, addr, regnum, mask, set);
 	mutex_unlock(&bus->mdio_lock);
 
-	return err < 0 ? err : 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(mdiobus_modify);
 
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index c1b7008826e5b..8fa23bdcedbf9 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -537,6 +537,8 @@ static inline void mii_c73_mod_linkmode(unsigned long *adv, u16 *lpa)
 
 int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum);
 int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val);
+int __mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask,
+		     u16 set);
 int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum,
 			     u16 mask, u16 set);
 
@@ -564,6 +566,30 @@ int mdiobus_c45_modify(struct mii_bus *bus, int addr, int devad, u32 regnum,
 int mdiobus_c45_modify_changed(struct mii_bus *bus, int addr, int devad,
 			       u32 regnum, u16 mask, u16 set);
 
+static inline int __mdiodev_read(struct mdio_device *mdiodev, u32 regnum)
+{
+	return __mdiobus_read(mdiodev->bus, mdiodev->addr, regnum);
+}
+
+static inline int __mdiodev_write(struct mdio_device *mdiodev, u32 regnum,
+				  u16 val)
+{
+	return __mdiobus_write(mdiodev->bus, mdiodev->addr, regnum, val);
+}
+
+static inline int __mdiodev_modify(struct mdio_device *mdiodev, u32 regnum,
+				   u16 mask, u16 set)
+{
+	return __mdiobus_modify(mdiodev->bus, mdiodev->addr, regnum, mask, set);
+}
+
+static inline int __mdiodev_modify_changed(struct mdio_device *mdiodev,
+					   u32 regnum, u16 mask, u16 set)
+{
+	return __mdiobus_modify_changed(mdiodev->bus, mdiodev->addr, regnum,
+					mask, set);
+}
+
 static inline int mdiodev_read(struct mdio_device *mdiodev, u32 regnum)
 {
 	return mdiobus_read(mdiodev->bus, mdiodev->addr, regnum);
-- 
GitLab


From 40da0c32c3fcb5bcb79068574ae60baaea78f3c4 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:28 +0100
Subject: [PATCH 0123/1806] net: dsa: mv88e6xxx: remove handling for DSA and
 CPU ports

As we now always use a fixed-link for DSA and CPU ports, we no longer
need the hack in the Marvell code to make this work. Remove it.

This is especially important with the conversion of DSA drivers to
phylink_pcs, as the PCS code only gets called if we are using
phylink for the port.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 48 ++++----------------------------
 1 file changed, 5 insertions(+), 43 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 8b51756bd8054..42c325409ac48 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3315,56 +3315,17 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 {
 	struct device_node *phy_handle = NULL;
 	struct dsa_switch *ds = chip->ds;
-	phy_interface_t mode;
 	struct dsa_port *dp;
-	int tx_amp, speed;
+	int tx_amp;
 	int err;
 	u16 reg;
 
 	chip->ports[port].chip = chip;
 	chip->ports[port].port = port;
 
-	dp = dsa_to_port(ds, port);
-
-	/* MAC Forcing register: don't force link, speed, duplex or flow control
-	 * state to any particular values on physical ports, but force the CPU
-	 * port and all DSA ports to their maximum bandwidth and full duplex.
-	 */
-	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
-		struct phylink_config pl_config = {};
-		unsigned long caps;
-
-		chip->info->ops->phylink_get_caps(chip, port, &pl_config);
-
-		caps = pl_config.mac_capabilities;
-
-		if (chip->info->ops->port_max_speed_mode)
-			mode = chip->info->ops->port_max_speed_mode(chip, port);
-		else
-			mode = PHY_INTERFACE_MODE_NA;
-
-		if (caps & MAC_10000FD)
-			speed = SPEED_10000;
-		else if (caps & MAC_5000FD)
-			speed = SPEED_5000;
-		else if (caps & MAC_2500FD)
-			speed = SPEED_2500;
-		else if (caps & MAC_1000)
-			speed = SPEED_1000;
-		else if (caps & MAC_100)
-			speed = SPEED_100;
-		else
-			speed = SPEED_10;
-
-		err = mv88e6xxx_port_setup_mac(chip, port, LINK_FORCED_UP,
-					       speed, DUPLEX_FULL,
-					       PAUSE_OFF, mode);
-	} else {
-		err = mv88e6xxx_port_setup_mac(chip, port, LINK_UNFORCED,
-					       SPEED_UNFORCED, DUPLEX_UNFORCED,
-					       PAUSE_ON,
-					       PHY_INTERFACE_MODE_NA);
-	}
+	err = mv88e6xxx_port_setup_mac(chip, port, LINK_UNFORCED,
+				       SPEED_UNFORCED, DUPLEX_UNFORCED,
+				       PAUSE_ON, PHY_INTERFACE_MODE_NA);
 	if (err)
 		return err;
 
@@ -3541,6 +3502,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 	}
 
 	if (chip->info->ops->serdes_set_tx_amplitude) {
+		dp = dsa_to_port(ds, port);
 		if (dp)
 			phy_handle = of_parse_phandle(dp->dn, "phy-handle", 0);
 
-- 
GitLab


From b92143d4420fde0e7f2ca1637362120177e03458 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:33 +0100
Subject: [PATCH 0124/1806] net: dsa: mv88e6xxx: add infrastructure for
 phylink_pcs

Add infrastructure for phylink_pcs to the mv88e6xxx driver. This
involves adding a mac_select_pcs() hook so we can pass the PCS to
phylink at the appropriate time, and a PCS initialisation function.

As the various chip implementations are converted to use phylink_pcs,
they are no longer reliant on the legacy phylink behaviour. We detect
this by the use of this infrastructure, or the lack of any serdes.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 48 ++++++++++++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/chip.h | 12 ++++++++
 2 files changed, 60 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 42c325409ac48..acbe55762f5ef 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -844,6 +844,31 @@ static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port,
 		__set_bit(PHY_INTERFACE_MODE_GMII,
 			  config->supported_interfaces);
 	}
+
+	/* If we have a .pcs_ops, or don't have a .serdes_pcs_get_state,
+	 * serdes_pcs_config, serdes_pcs_an_restart, or serdes_pcs_link_up,
+	 * we are not legacy.
+	 */
+	if (chip->info->ops->pcs_ops ||
+	    (!chip->info->ops->serdes_pcs_get_state &&
+	     !chip->info->ops->serdes_pcs_config &&
+	     !chip->info->ops->serdes_pcs_an_restart &&
+	     !chip->info->ops->serdes_pcs_link_up))
+		config->legacy_pre_march2020 = false;
+}
+
+static struct phylink_pcs *mv88e6xxx_mac_select_pcs(struct dsa_switch *ds,
+						    int port,
+						    phy_interface_t interface)
+{
+	struct mv88e6xxx_chip *chip = ds->priv;
+	struct phylink_pcs *pcs = ERR_PTR(-EOPNOTSUPP);
+
+	if (chip->info->ops->pcs_ops)
+		pcs = chip->info->ops->pcs_ops->pcs_select(chip, port,
+							   interface);
+
+	return pcs;
 }
 
 static int mv88e6xxx_mac_prepare(struct dsa_switch *ds, int port,
@@ -3582,6 +3607,10 @@ static int mv88e6xxx_port_enable(struct dsa_switch *ds, int port,
 	struct mv88e6xxx_chip *chip = ds->priv;
 	int err;
 
+	/* Do not control power or request irqs if using PCS */
+	if (chip->info->ops->pcs_ops)
+		return 0;
+
 	mv88e6xxx_reg_lock(chip);
 	err = mv88e6xxx_serdes_power(chip, port, true);
 	mv88e6xxx_reg_unlock(chip);
@@ -3593,6 +3622,10 @@ static void mv88e6xxx_port_disable(struct dsa_switch *ds, int port)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
 
+	/* Do not control power or request irqs if using PCS */
+	if (chip->info->ops->pcs_ops)
+		return;
+
 	mv88e6xxx_reg_lock(chip);
 	if (mv88e6xxx_serdes_power(chip, port, false))
 		dev_err(chip->dev, "failed to power off SERDES\n");
@@ -4061,12 +4094,26 @@ out_mdios:
 
 static int mv88e6xxx_port_setup(struct dsa_switch *ds, int port)
 {
+	struct mv88e6xxx_chip *chip = ds->priv;
+	int err;
+
+	if (chip->info->ops->pcs_ops->pcs_init) {
+		err = chip->info->ops->pcs_ops->pcs_init(chip, port);
+		if (err)
+			return err;
+	}
+
 	return mv88e6xxx_setup_devlink_regions_port(ds, port);
 }
 
 static void mv88e6xxx_port_teardown(struct dsa_switch *ds, int port)
 {
+	struct mv88e6xxx_chip *chip = ds->priv;
+
 	mv88e6xxx_teardown_devlink_regions_port(ds, port);
+
+	if (chip->info->ops->pcs_ops->pcs_teardown)
+		chip->info->ops->pcs_ops->pcs_teardown(chip, port);
 }
 
 static int mv88e6xxx_get_eeprom_len(struct dsa_switch *ds)
@@ -7061,6 +7108,7 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
 	.port_setup		= mv88e6xxx_port_setup,
 	.port_teardown		= mv88e6xxx_port_teardown,
 	.phylink_get_caps	= mv88e6xxx_get_caps,
+	.phylink_mac_select_pcs	= mv88e6xxx_mac_select_pcs,
 	.phylink_mac_link_state	= mv88e6xxx_serdes_pcs_get_state,
 	.phylink_mac_prepare	= mv88e6xxx_mac_prepare,
 	.phylink_mac_config	= mv88e6xxx_mac_config,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 0ad34b2d89137..1dd310a3c41f3 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -205,6 +205,7 @@ struct mv88e6xxx_irq_ops;
 struct mv88e6xxx_gpio_ops;
 struct mv88e6xxx_avb_ops;
 struct mv88e6xxx_ptp_ops;
+struct mv88e6xxx_pcs_ops;
 
 struct mv88e6xxx_irq {
 	u16 masked;
@@ -288,6 +289,7 @@ struct mv88e6xxx_port {
 	unsigned int serdes_irq;
 	char serdes_irq_name[64];
 	struct devlink_region *region;
+	void *pcs_private;
 
 	/* MacAuth Bypass control flag */
 	bool mab;
@@ -664,6 +666,8 @@ struct mv88e6xxx_ops {
 	void (*phylink_get_caps)(struct mv88e6xxx_chip *chip, int port,
 				 struct phylink_config *config);
 
+	const struct mv88e6xxx_pcs_ops *pcs_ops;
+
 	/* Max Frame Size */
 	int (*set_max_frame_size)(struct mv88e6xxx_chip *chip, int mtu);
 };
@@ -736,6 +740,14 @@ struct mv88e6xxx_ptp_ops {
 	u32 cc_mult_dem;
 };
 
+struct mv88e6xxx_pcs_ops {
+	int (*pcs_init)(struct mv88e6xxx_chip *chip, int port);
+	void (*pcs_teardown)(struct mv88e6xxx_chip *chip, int port);
+	struct phylink_pcs *(*pcs_select)(struct mv88e6xxx_chip *chip, int port,
+					  phy_interface_t mode);
+
+};
+
 #define STATS_TYPE_PORT		BIT(0)
 #define STATS_TYPE_BANK0	BIT(1)
 #define STATS_TYPE_BANK1	BIT(2)
-- 
GitLab


From 05407b0ebc3932cf9a6010eb81168ba0b6c5e8ab Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:38 +0100
Subject: [PATCH 0125/1806] net: dsa: mv88e6xxx: export
 mv88e6xxx_pcs_decode_state()

Rename and export the PCS state decoding function so our PCS can
make use of the functionality provided by this.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/serdes.c | 11 +++++------
 drivers/net/dsa/mv88e6xxx/serdes.h |  5 +++++
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 80167d53212f8..7ea36d04d9fab 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -45,9 +45,8 @@ static int mv88e6390_serdes_write(struct mv88e6xxx_chip *chip,
 	return mv88e6xxx_phy_write_c45(chip, lane, device, reg, val);
 }
 
-static int mv88e6xxx_serdes_pcs_get_state(struct mv88e6xxx_chip *chip,
-					  u16 bmsr, u16 lpa, u16 status,
-					  struct phylink_link_state *state)
+int mv88e6xxx_pcs_decode_state(struct device *dev, u16 bmsr, u16 lpa,
+			       u16 status, struct phylink_link_state *state)
 {
 	state->link = false;
 
@@ -88,7 +87,7 @@ static int mv88e6xxx_serdes_pcs_get_state(struct mv88e6xxx_chip *chip,
 			state->speed = SPEED_10;
 			break;
 		default:
-			dev_err(chip->dev, "invalid PHY speed\n");
+			dev_err(dev, "invalid PHY speed\n");
 			return -EINVAL;
 		}
 	} else if (state->link &&
@@ -211,7 +210,7 @@ int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
 		return err;
 	}
 
-	return mv88e6xxx_serdes_pcs_get_state(chip, bmsr, lpa, status, state);
+	return mv88e6xxx_pcs_decode_state(chip->dev, bmsr, lpa, status, state);
 }
 
 int mv88e6352_serdes_pcs_an_restart(struct mv88e6xxx_chip *chip, int port,
@@ -942,7 +941,7 @@ static int mv88e6390_serdes_pcs_get_state_sgmii(struct mv88e6xxx_chip *chip,
 		return err;
 	}
 
-	return mv88e6xxx_serdes_pcs_get_state(chip, bmsr, lpa, status, state);
+	return mv88e6xxx_pcs_decode_state(chip->dev, bmsr, lpa, status, state);
 }
 
 static int mv88e6390_serdes_pcs_get_state_10g(struct mv88e6xxx_chip *chip,
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index e245687ddb1d0..93d40d66d7c50 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -12,6 +12,8 @@
 
 #include "chip.h"
 
+struct phylink_link_state;
+
 #define MV88E6352_ADDR_SERDES		0x0f
 #define MV88E6352_SERDES_PAGE_FIBER	0x01
 #define MV88E6352_SERDES_IRQ		0x0b
@@ -107,6 +109,9 @@
 #define MV88E6393X_ERRATA_4_8_REG		0xF074
 #define MV88E6393X_ERRATA_4_8_BIT		BIT(14)
 
+int mv88e6xxx_pcs_decode_state(struct device *dev, u16 bmsr, u16 lpa,
+			       u16 status, struct phylink_link_state *state);
+
 int mv88e6185_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6341_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
-- 
GitLab


From 4aabe35c385ce6c28613ab56b334b4a9521d62b7 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:43 +0100
Subject: [PATCH 0126/1806] net: dsa: mv88e6xxx: convert 88e6185 to phylink_pcs

Convert the 88E6185 SERDES code to use the phylink_pcs infrastructure.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/Makefile   |   1 +
 drivers/net/dsa/mv88e6xxx/chip.c     |  14 +-
 drivers/net/dsa/mv88e6xxx/pcs-6185.c | 190 +++++++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/serdes.c   | 109 ---------------
 drivers/net/dsa/mv88e6xxx/serdes.h   |  11 +-
 5 files changed, 196 insertions(+), 129 deletions(-)
 create mode 100644 drivers/net/dsa/mv88e6xxx/pcs-6185.c

diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile
index 1409e691ab77d..9becf56fdec1d 100644
--- a/drivers/net/dsa/mv88e6xxx/Makefile
+++ b/drivers/net/dsa/mv88e6xxx/Makefile
@@ -9,6 +9,7 @@ mv88e6xxx-objs += global2.o
 mv88e6xxx-objs += global2_avb.o
 mv88e6xxx-objs += global2_scratch.o
 mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_PTP) += hwtstamp.o
+mv88e6xxx-objs += pcs-6185.o
 mv88e6xxx-objs += phy.o
 mv88e6xxx-objs += port.o
 mv88e6xxx-objs += port_hidden.o
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index acbe55762f5ef..fd876cf5577f3 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4230,15 +4230,13 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
 	.stats_get_strings = mv88e6095_stats_get_strings,
 	.stats_get_stats = mv88e6095_stats_get_stats,
 	.mgmt_rsvd2cpu = mv88e6185_g2_mgmt_rsvd2cpu,
-	.serdes_power = mv88e6185_serdes_power,
-	.serdes_get_lane = mv88e6185_serdes_get_lane,
-	.serdes_pcs_get_state = mv88e6185_serdes_pcs_get_state,
 	.ppu_enable = mv88e6185_g1_ppu_enable,
 	.ppu_disable = mv88e6185_g1_ppu_disable,
 	.reset = mv88e6185_g1_reset,
 	.vtu_getnext = mv88e6185_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
 	.phylink_get_caps = mv88e6095_phylink_get_caps,
+	.pcs_ops = &mv88e6185_pcs_ops,
 	.set_max_frame_size = mv88e6185_g1_set_max_frame_size,
 };
 
@@ -4276,18 +4274,14 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu,
-	.serdes_power = mv88e6185_serdes_power,
-	.serdes_get_lane = mv88e6185_serdes_get_lane,
-	.serdes_pcs_get_state = mv88e6185_serdes_pcs_get_state,
 	.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6097_serdes_irq_enable,
-	.serdes_irq_status = mv88e6097_serdes_irq_status,
 	.pot_clear = mv88e6xxx_g2_pot_clear,
 	.reset = mv88e6352_g1_reset,
 	.rmu_disable = mv88e6085_g1_rmu_disable,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.phylink_get_caps = mv88e6095_phylink_get_caps,
+	.pcs_ops = &mv88e6185_pcs_ops,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
 	.set_max_frame_size = mv88e6185_g1_set_max_frame_size,
@@ -4768,9 +4762,6 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6185_g2_mgmt_rsvd2cpu,
-	.serdes_power = mv88e6185_serdes_power,
-	.serdes_get_lane = mv88e6185_serdes_get_lane,
-	.serdes_pcs_get_state = mv88e6185_serdes_pcs_get_state,
 	.set_cascade_port = mv88e6185_g1_set_cascade_port,
 	.ppu_enable = mv88e6185_g1_ppu_enable,
 	.ppu_disable = mv88e6185_g1_ppu_disable,
@@ -4778,6 +4769,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.vtu_getnext = mv88e6185_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
 	.phylink_get_caps = mv88e6185_phylink_get_caps,
+	.pcs_ops = &mv88e6185_pcs_ops,
 	.set_max_frame_size = mv88e6185_g1_set_max_frame_size,
 };
 
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6185.c b/drivers/net/dsa/mv88e6xxx/pcs-6185.c
new file mode 100644
index 0000000000000..4d677f8368078
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/pcs-6185.c
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Marvell 88E6185 family SERDES PCS support
+ *
+ * Copyright (c) 2008 Marvell Semiconductor
+ *
+ * Copyright (c) 2017 Andrew Lunn <andrew@lunn.ch>
+ */
+#include <linux/phylink.h>
+
+#include "global2.h"
+#include "port.h"
+#include "serdes.h"
+
+struct mv88e6185_pcs {
+	struct phylink_pcs phylink_pcs;
+	unsigned int irq;
+	char name[64];
+
+	struct mv88e6xxx_chip *chip;
+	int port;
+};
+
+static struct mv88e6185_pcs *pcs_to_mv88e6185_pcs(struct phylink_pcs *pcs)
+{
+	return container_of(pcs, struct mv88e6185_pcs, phylink_pcs);
+}
+
+static irqreturn_t mv88e6185_pcs_handle_irq(int irq, void *dev_id)
+{
+	struct mv88e6185_pcs *mpcs = dev_id;
+	struct mv88e6xxx_chip *chip;
+	irqreturn_t ret = IRQ_NONE;
+	bool link_up;
+	u16 status;
+	int port;
+	int err;
+
+	chip = mpcs->chip;
+	port = mpcs->port;
+
+	mv88e6xxx_reg_lock(chip);
+	err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &status);
+	mv88e6xxx_reg_unlock(chip);
+
+	if (!err) {
+		link_up = !!(status & MV88E6XXX_PORT_STS_LINK);
+
+		phylink_pcs_change(&mpcs->phylink_pcs, link_up);
+
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+static void mv88e6185_pcs_get_state(struct phylink_pcs *pcs,
+				    struct phylink_link_state *state)
+{
+	struct mv88e6185_pcs *mpcs = pcs_to_mv88e6185_pcs(pcs);
+	struct mv88e6xxx_chip *chip = mpcs->chip;
+	int port = mpcs->port;
+	u16 status;
+	int err;
+
+	mv88e6xxx_reg_lock(chip);
+	err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &status);
+	mv88e6xxx_reg_unlock(chip);
+
+	if (err)
+		status = 0;
+
+	state->link = !!(status & MV88E6XXX_PORT_STS_LINK);
+	if (state->link) {
+		state->duplex = status & MV88E6XXX_PORT_STS_DUPLEX ?
+			DUPLEX_FULL : DUPLEX_HALF;
+
+		switch (status & MV88E6XXX_PORT_STS_SPEED_MASK) {
+		case MV88E6XXX_PORT_STS_SPEED_1000:
+			state->speed = SPEED_1000;
+			break;
+
+		case MV88E6XXX_PORT_STS_SPEED_100:
+			state->speed = SPEED_100;
+			break;
+
+		case MV88E6XXX_PORT_STS_SPEED_10:
+			state->speed = SPEED_10;
+			break;
+
+		default:
+			state->link = false;
+			break;
+		}
+	}
+}
+
+static int mv88e6185_pcs_config(struct phylink_pcs *pcs, unsigned int mode,
+				phy_interface_t interface,
+				const unsigned long *advertising,
+				bool permit_pause_to_mac)
+{
+	return 0;
+}
+
+static void mv88e6185_pcs_an_restart(struct phylink_pcs *pcs)
+{
+}
+
+static const struct phylink_pcs_ops mv88e6185_phylink_pcs_ops = {
+	.pcs_get_state = mv88e6185_pcs_get_state,
+	.pcs_config = mv88e6185_pcs_config,
+	.pcs_an_restart = mv88e6185_pcs_an_restart,
+};
+
+static int mv88e6185_pcs_init(struct mv88e6xxx_chip *chip, int port)
+{
+	struct mv88e6185_pcs *mpcs;
+	struct device *dev;
+	unsigned int irq;
+	int err;
+
+	/* There are no configurable serdes lanes on this switch chip, so
+	 * we use the static cmode configuration to determine whether we
+	 * have a PCS or not.
+	 */
+	if (chip->ports[port].cmode != MV88E6185_PORT_STS_CMODE_SERDES &&
+	    chip->ports[port].cmode != MV88E6185_PORT_STS_CMODE_1000BASE_X)
+		return 0;
+
+	dev = chip->dev;
+
+	mpcs = kzalloc(sizeof(*mpcs), GFP_KERNEL);
+	if (!mpcs)
+		return -ENOMEM;
+
+	mpcs->chip = chip;
+	mpcs->port = port;
+	mpcs->phylink_pcs.ops = &mv88e6185_phylink_pcs_ops;
+
+	irq = mv88e6xxx_serdes_irq_mapping(chip, port);
+	if (irq) {
+		snprintf(mpcs->name, sizeof(mpcs->name),
+			 "mv88e6xxx-%s-serdes-%d", dev_name(dev), port);
+
+		err = request_threaded_irq(irq, NULL, mv88e6185_pcs_handle_irq,
+					   IRQF_ONESHOT, mpcs->name, mpcs);
+		if (err) {
+			kfree(mpcs);
+			return err;
+		}
+
+		mpcs->irq = irq;
+	} else {
+		mpcs->phylink_pcs.poll = true;
+	}
+
+	chip->ports[port].pcs_private = &mpcs->phylink_pcs;
+
+	return 0;
+}
+
+static void mv88e6185_pcs_teardown(struct mv88e6xxx_chip *chip, int port)
+{
+	struct mv88e6185_pcs *mpcs;
+
+	mpcs = chip->ports[port].pcs_private;
+	if (!mpcs)
+		return;
+
+	if (mpcs->irq)
+		free_irq(mpcs->irq, mpcs);
+
+	kfree(mpcs);
+
+	chip->ports[port].pcs_private = NULL;
+}
+
+static struct phylink_pcs *mv88e6185_pcs_select(struct mv88e6xxx_chip *chip,
+						int port,
+						phy_interface_t interface)
+{
+	return chip->ports[port].pcs_private;
+}
+
+const struct mv88e6xxx_pcs_ops mv88e6185_pcs_ops = {
+	.pcs_init = mv88e6185_pcs_init,
+	.pcs_teardown = mv88e6185_pcs_teardown,
+	.pcs_select = mv88e6185_pcs_select,
+};
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 7ea36d04d9fab..5ac5687e76a94 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -460,115 +460,6 @@ int mv88e6341_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
 	return lane;
 }
 
-int mv88e6185_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
-			   bool up)
-{
-	/* The serdes power can't be controlled on this switch chip but we need
-	 * to supply this function to avoid returning -EOPNOTSUPP in
-	 * mv88e6xxx_serdes_power_up/mv88e6xxx_serdes_power_down
-	 */
-	return 0;
-}
-
-int mv88e6185_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
-{
-	/* There are no configurable serdes lanes on this switch chip but we
-	 * need to return a non-negative lane number so that callers of
-	 * mv88e6xxx_serdes_get_lane() know this is a serdes port.
-	 */
-	switch (chip->ports[port].cmode) {
-	case MV88E6185_PORT_STS_CMODE_SERDES:
-	case MV88E6185_PORT_STS_CMODE_1000BASE_X:
-		return 0;
-	default:
-		return -ENODEV;
-	}
-}
-
-int mv88e6185_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
-				   int lane, struct phylink_link_state *state)
-{
-	int err;
-	u16 status;
-
-	err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &status);
-	if (err)
-		return err;
-
-	state->link = !!(status & MV88E6XXX_PORT_STS_LINK);
-
-	if (state->link) {
-		state->duplex = status & MV88E6XXX_PORT_STS_DUPLEX ? DUPLEX_FULL : DUPLEX_HALF;
-
-		switch (status &  MV88E6XXX_PORT_STS_SPEED_MASK) {
-		case MV88E6XXX_PORT_STS_SPEED_1000:
-			state->speed = SPEED_1000;
-			break;
-		case MV88E6XXX_PORT_STS_SPEED_100:
-			state->speed = SPEED_100;
-			break;
-		case MV88E6XXX_PORT_STS_SPEED_10:
-			state->speed = SPEED_10;
-			break;
-		default:
-			dev_err(chip->dev, "invalid PHY speed\n");
-			return -EINVAL;
-		}
-	} else {
-		state->duplex = DUPLEX_UNKNOWN;
-		state->speed = SPEED_UNKNOWN;
-	}
-
-	return 0;
-}
-
-int mv88e6097_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, int lane,
-				bool enable)
-{
-	u8 cmode = chip->ports[port].cmode;
-
-	/* The serdes interrupts are enabled in the G2_INT_MASK register. We
-	 * need to return 0 to avoid returning -EOPNOTSUPP in
-	 * mv88e6xxx_serdes_irq_enable/mv88e6xxx_serdes_irq_disable
-	 */
-	switch (cmode) {
-	case MV88E6185_PORT_STS_CMODE_SERDES:
-	case MV88E6185_PORT_STS_CMODE_1000BASE_X:
-		return 0;
-	}
-
-	return -EOPNOTSUPP;
-}
-
-static void mv88e6097_serdes_irq_link(struct mv88e6xxx_chip *chip, int port)
-{
-	u16 status;
-	int err;
-
-	err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &status);
-	if (err) {
-		dev_err(chip->dev, "can't read port status: %d\n", err);
-		return;
-	}
-
-	dsa_port_phylink_mac_change(chip->ds, port, !!(status & MV88E6XXX_PORT_STS_LINK));
-}
-
-irqreturn_t mv88e6097_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
-					int lane)
-{
-	u8 cmode = chip->ports[port].cmode;
-
-	switch (cmode) {
-	case MV88E6185_PORT_STS_CMODE_SERDES:
-	case MV88E6185_PORT_STS_CMODE_1000BASE_X:
-		mv88e6097_serdes_irq_link(chip, port);
-		return IRQ_HANDLED;
-	}
-
-	return IRQ_NONE;
-}
-
 int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
 {
 	u8 cmode = chip->ports[port].cmode;
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index 93d40d66d7c50..93d363eb61ea8 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -112,7 +112,6 @@ struct phylink_link_state;
 int mv88e6xxx_pcs_decode_state(struct device *dev, u16 bmsr, u16 lpa,
 			       u16 status, struct phylink_link_state *state);
 
-int mv88e6185_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6341_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
@@ -126,8 +125,6 @@ int mv88e6390_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
 				int lane, unsigned int mode,
 				phy_interface_t interface,
 				const unsigned long *advertise);
-int mv88e6185_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
-				   int lane, struct phylink_link_state *state);
 int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
 				   int lane, struct phylink_link_state *state);
 int mv88e6390_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
@@ -146,8 +143,6 @@ unsigned int mv88e6352_serdes_irq_mapping(struct mv88e6xxx_chip *chip,
 					  int port);
 unsigned int mv88e6390_serdes_irq_mapping(struct mv88e6xxx_chip *chip,
 					  int port);
-int mv88e6185_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
-			   bool up);
 int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
 			   bool on);
 int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
@@ -155,16 +150,12 @@ int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
 int mv88e6393x_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
 			    bool on);
 int mv88e6393x_serdes_setup_errata(struct mv88e6xxx_chip *chip);
-int mv88e6097_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, int lane,
-				bool enable);
 int mv88e6352_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, int lane,
 				bool enable);
 int mv88e6390_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, int lane,
 				bool enable);
 int mv88e6393x_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port,
 				 int lane, bool enable);
-irqreturn_t mv88e6097_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
-					int lane);
 irqreturn_t mv88e6352_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
 					int lane);
 irqreturn_t mv88e6390_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
@@ -254,4 +245,6 @@ mv88e6xxx_serdes_irq_status(struct mv88e6xxx_chip *chip, int port, int lane)
 	return chip->info->ops->serdes_irq_status(chip, port, lane);
 }
 
+extern const struct mv88e6xxx_pcs_ops mv88e6185_pcs_ops;
+
 #endif
-- 
GitLab


From 85764555442fad03b67ee91c066a49586cceef5d Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:48 +0100
Subject: [PATCH 0127/1806] net: dsa: mv88e6xxx: convert 88e6352 to phylink_pcs

Convert the 88E6352 SERDES code to use the phylink_pcs infrastructure.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/Makefile   |   1 +
 drivers/net/dsa/mv88e6xxx/chip.c     |  34 +--
 drivers/net/dsa/mv88e6xxx/pcs-6352.c | 390 +++++++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/serdes.c   | 205 --------------
 drivers/net/dsa/mv88e6xxx/serdes.h   |  18 +-
 5 files changed, 396 insertions(+), 252 deletions(-)
 create mode 100644 drivers/net/dsa/mv88e6xxx/pcs-6352.c

diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile
index 9becf56fdec1d..05976e1f93f66 100644
--- a/drivers/net/dsa/mv88e6xxx/Makefile
+++ b/drivers/net/dsa/mv88e6xxx/Makefile
@@ -10,6 +10,7 @@ mv88e6xxx-objs += global2_avb.o
 mv88e6xxx-objs += global2_scratch.o
 mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_PTP) += hwtstamp.o
 mv88e6xxx-objs += pcs-6185.o
+mv88e6xxx-objs += pcs-6352.o
 mv88e6xxx-objs += phy.o
 mv88e6xxx-objs += port.o
 mv88e6xxx-objs += port_hidden.o
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index fd876cf5577f3..90573407d4048 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4614,16 +4614,11 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.serdes_get_lane = mv88e6352_serdes_get_lane,
-	.serdes_pcs_get_state = mv88e6352_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6352_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6352_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6352_serdes_pcs_link_up,
-	.serdes_power = mv88e6352_serdes_power,
 	.serdes_get_regs_len = mv88e6352_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6352_serdes_get_regs,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.phylink_get_caps = mv88e6352_phylink_get_caps,
+	.pcs_ops = &mv88e6352_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6175_ops = {
@@ -4719,20 +4714,13 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.serdes_get_lane = mv88e6352_serdes_get_lane,
-	.serdes_pcs_get_state = mv88e6352_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6352_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6352_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6352_serdes_pcs_link_up,
-	.serdes_power = mv88e6352_serdes_power,
 	.serdes_irq_mapping = mv88e6352_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6352_serdes_irq_enable,
-	.serdes_irq_status = mv88e6352_serdes_irq_status,
 	.serdes_get_regs_len = mv88e6352_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6352_serdes_get_regs,
 	.serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.phylink_get_caps = mv88e6352_phylink_get_caps,
+	.pcs_ops = &mv88e6352_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6185_ops = {
@@ -5014,15 +5002,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.serdes_get_lane = mv88e6352_serdes_get_lane,
-	.serdes_pcs_get_state = mv88e6352_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6352_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6352_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6352_serdes_pcs_link_up,
-	.serdes_power = mv88e6352_serdes_power,
 	.serdes_irq_mapping = mv88e6352_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6352_serdes_irq_enable,
-	.serdes_irq_status = mv88e6352_serdes_irq_status,
 	.serdes_get_regs_len = mv88e6352_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6352_serdes_get_regs,
 	.serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude,
@@ -5030,6 +5010,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
 	.phylink_get_caps = mv88e6352_phylink_get_caps,
+	.pcs_ops = &mv88e6352_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6250_ops = {
@@ -5445,15 +5426,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.serdes_get_lane = mv88e6352_serdes_get_lane,
-	.serdes_pcs_get_state = mv88e6352_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6352_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6352_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6352_serdes_pcs_link_up,
-	.serdes_power = mv88e6352_serdes_power,
 	.serdes_irq_mapping = mv88e6352_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6352_serdes_irq_enable,
-	.serdes_irq_status = mv88e6352_serdes_irq_status,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -5464,6 +5437,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.serdes_get_regs = mv88e6352_serdes_get_regs,
 	.serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude,
 	.phylink_get_caps = mv88e6352_phylink_get_caps,
+	.pcs_ops = &mv88e6352_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6390_ops = {
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6352.c b/drivers/net/dsa/mv88e6xxx/pcs-6352.c
new file mode 100644
index 0000000000000..88f624b654702
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/pcs-6352.c
@@ -0,0 +1,390 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Marvell 88E6352 family SERDES PCS support
+ *
+ * Copyright (c) 2008 Marvell Semiconductor
+ *
+ * Copyright (c) 2017 Andrew Lunn <andrew@lunn.ch>
+ */
+#include <linux/phylink.h>
+
+#include "global2.h"
+#include "port.h"
+#include "serdes.h"
+
+/* Definitions from drivers/net/phy/marvell.c, which would be good to reuse. */
+#define MII_M1011_PHY_STATUS		17
+#define MII_M1011_IMASK			18
+#define MII_M1011_IMASK_LINK_CHANGE	BIT(10)
+#define MII_M1011_IEVENT		19
+#define MII_M1011_IEVENT_LINK_CHANGE	BIT(10)
+#define MII_MARVELL_PHY_PAGE		22
+#define MII_MARVELL_FIBER_PAGE		1
+
+struct marvell_c22_pcs {
+	struct mdio_device mdio;
+	struct phylink_pcs phylink_pcs;
+	unsigned int irq;
+	char name[64];
+	bool (*link_check)(struct marvell_c22_pcs *mpcs);
+	struct mv88e6xxx_port *port;
+};
+
+static struct marvell_c22_pcs *pcs_to_marvell_c22_pcs(struct phylink_pcs *pcs)
+{
+	return container_of(pcs, struct marvell_c22_pcs, phylink_pcs);
+}
+
+static int marvell_c22_pcs_set_fiber_page(struct marvell_c22_pcs *mpcs)
+{
+	u16 page;
+	int err;
+
+	mutex_lock(&mpcs->mdio.bus->mdio_lock);
+
+	err = __mdiodev_read(&mpcs->mdio, MII_MARVELL_PHY_PAGE);
+	if (err < 0) {
+		dev_err(mpcs->mdio.dev.parent,
+			"%s: can't read Serdes page register: %pe\n",
+			mpcs->name, ERR_PTR(err));
+		return err;
+	}
+
+	page = err;
+
+	err = __mdiodev_write(&mpcs->mdio, MII_MARVELL_PHY_PAGE,
+			      MII_MARVELL_FIBER_PAGE);
+	if (err) {
+		dev_err(mpcs->mdio.dev.parent,
+			"%s: can't set Serdes page register: %pe\n",
+			mpcs->name, ERR_PTR(err));
+		return err;
+	}
+
+	return page;
+}
+
+static int marvell_c22_pcs_restore_page(struct marvell_c22_pcs *mpcs,
+					int oldpage, int ret)
+{
+	int err;
+
+	if (oldpage >= 0) {
+		err = __mdiodev_write(&mpcs->mdio, MII_MARVELL_PHY_PAGE,
+				      oldpage);
+		if (err)
+			dev_err(mpcs->mdio.dev.parent,
+				"%s: can't restore Serdes page register: %pe\n",
+				mpcs->name, ERR_PTR(err));
+		if (!err || ret < 0)
+			err = ret;
+	} else {
+		err = oldpage;
+	}
+	mutex_unlock(&mpcs->mdio.bus->mdio_lock);
+
+	return err;
+}
+
+static irqreturn_t marvell_c22_pcs_handle_irq(int irq, void *dev_id)
+{
+	struct marvell_c22_pcs *mpcs = dev_id;
+	irqreturn_t status = IRQ_NONE;
+	int err, oldpage;
+
+	oldpage = marvell_c22_pcs_set_fiber_page(mpcs);
+	if (oldpage < 0)
+		goto fail;
+
+	err = __mdiodev_read(&mpcs->mdio, MII_M1011_IEVENT);
+	if (err >= 0 && err & MII_M1011_IEVENT_LINK_CHANGE) {
+		phylink_pcs_change(&mpcs->phylink_pcs, true);
+		status = IRQ_HANDLED;
+	}
+
+fail:
+	marvell_c22_pcs_restore_page(mpcs, oldpage, 0);
+
+	return status;
+}
+
+static int marvell_c22_pcs_modify(struct marvell_c22_pcs *mpcs, u8 reg,
+				  u16 mask, u16 val)
+{
+	int oldpage, err = 0;
+
+	oldpage = marvell_c22_pcs_set_fiber_page(mpcs);
+	if (oldpage >= 0)
+		err = __mdiodev_modify(&mpcs->mdio, reg, mask, val);
+
+	return marvell_c22_pcs_restore_page(mpcs, oldpage, err);
+}
+
+static int marvell_c22_pcs_power(struct marvell_c22_pcs *mpcs,
+				 bool on)
+{
+	u16 val = on ? 0 : BMCR_PDOWN;
+
+	return marvell_c22_pcs_modify(mpcs, MII_BMCR, BMCR_PDOWN, val);
+}
+
+static int marvell_c22_pcs_control_irq(struct marvell_c22_pcs *mpcs,
+				       bool enable)
+{
+	u16 val = enable ? MII_M1011_IMASK_LINK_CHANGE : 0;
+
+	return marvell_c22_pcs_modify(mpcs, MII_M1011_IMASK,
+				      MII_M1011_IMASK_LINK_CHANGE, val);
+}
+
+static int marvell_c22_pcs_enable(struct phylink_pcs *pcs)
+{
+	struct marvell_c22_pcs *mpcs = pcs_to_marvell_c22_pcs(pcs);
+	int err;
+
+	err = marvell_c22_pcs_power(mpcs, true);
+	if (err)
+		return err;
+
+	return marvell_c22_pcs_control_irq(mpcs, !!mpcs->irq);
+}
+
+static void marvell_c22_pcs_disable(struct phylink_pcs *pcs)
+{
+	struct marvell_c22_pcs *mpcs = pcs_to_marvell_c22_pcs(pcs);
+
+	marvell_c22_pcs_control_irq(mpcs, false);
+	marvell_c22_pcs_power(mpcs, false);
+}
+
+static void marvell_c22_pcs_get_state(struct phylink_pcs *pcs,
+				      struct phylink_link_state *state)
+{
+	struct marvell_c22_pcs *mpcs = pcs_to_marvell_c22_pcs(pcs);
+	int oldpage, bmsr, lpa, status;
+
+	state->link = false;
+
+	if (mpcs->link_check && !mpcs->link_check(mpcs))
+		return;
+
+	oldpage = marvell_c22_pcs_set_fiber_page(mpcs);
+	if (oldpage >= 0) {
+		bmsr = __mdiodev_read(&mpcs->mdio, MII_BMSR);
+		lpa = __mdiodev_read(&mpcs->mdio, MII_LPA);
+		status = __mdiodev_read(&mpcs->mdio, MII_M1011_PHY_STATUS);
+	}
+
+	if (marvell_c22_pcs_restore_page(mpcs, oldpage, 0) >= 0 &&
+	    bmsr >= 0 && lpa >= 0 && status >= 0)
+		mv88e6xxx_pcs_decode_state(mpcs->mdio.dev.parent, bmsr, lpa,
+					   status, state);
+}
+
+static int marvell_c22_pcs_config(struct phylink_pcs *pcs,
+				  unsigned int neg_mode,
+				  phy_interface_t interface,
+				  const unsigned long *advertising,
+				  bool permit_pause_to_mac)
+{
+	struct marvell_c22_pcs *mpcs = pcs_to_marvell_c22_pcs(pcs);
+	int oldpage, adv, err, ret = 0;
+	u16 bmcr;
+
+	adv = phylink_mii_c22_pcs_encode_advertisement(interface, advertising);
+	if (adv < 0)
+		return 0;
+
+	bmcr = neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED ? BMCR_ANENABLE : 0;
+
+	oldpage = marvell_c22_pcs_set_fiber_page(mpcs);
+	if (oldpage < 0)
+		goto restore;
+
+	err = __mdiodev_modify_changed(&mpcs->mdio, MII_ADVERTISE, 0xffff, adv);
+	ret = err;
+	if (err < 0)
+		goto restore;
+
+	err = __mdiodev_modify_changed(&mpcs->mdio, MII_BMCR, BMCR_ANENABLE,
+				       bmcr);
+	if (err < 0) {
+		ret = err;
+		goto restore;
+	}
+
+	/* If the ANENABLE bit was changed, the PHY will restart negotiation,
+	 * so we don't need to flag a change to trigger its own restart.
+	 */
+	if (err)
+		ret = 0;
+
+restore:
+	return marvell_c22_pcs_restore_page(mpcs, oldpage, ret);
+}
+
+static void marvell_c22_pcs_an_restart(struct phylink_pcs *pcs)
+{
+	struct marvell_c22_pcs *mpcs = pcs_to_marvell_c22_pcs(pcs);
+
+	marvell_c22_pcs_modify(mpcs, MII_BMCR, BMCR_ANRESTART, BMCR_ANRESTART);
+}
+
+static void marvell_c22_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode,
+				    phy_interface_t interface, int speed,
+				    int duplex)
+{
+	struct marvell_c22_pcs *mpcs = pcs_to_marvell_c22_pcs(pcs);
+	u16 bmcr;
+	int err;
+
+	if (phylink_autoneg_inband(mode))
+		return;
+
+	bmcr = mii_bmcr_encode_fixed(speed, duplex);
+
+	err = marvell_c22_pcs_modify(mpcs, MII_BMCR, BMCR_SPEED100 |
+				     BMCR_FULLDPLX | BMCR_SPEED1000, bmcr);
+	if (err)
+		dev_err(mpcs->mdio.dev.parent,
+			"%s: failed to configure mpcs: %pe\n", mpcs->name,
+			ERR_PTR(err));
+}
+
+static const struct phylink_pcs_ops marvell_c22_pcs_ops = {
+	.pcs_enable = marvell_c22_pcs_enable,
+	.pcs_disable = marvell_c22_pcs_disable,
+	.pcs_get_state = marvell_c22_pcs_get_state,
+	.pcs_config = marvell_c22_pcs_config,
+	.pcs_an_restart = marvell_c22_pcs_an_restart,
+	.pcs_link_up = marvell_c22_pcs_link_up,
+};
+
+static struct marvell_c22_pcs *marvell_c22_pcs_alloc(struct device *dev,
+						     struct mii_bus *bus,
+						     unsigned int addr)
+{
+	struct marvell_c22_pcs *mpcs;
+
+	mpcs = kzalloc(sizeof(*mpcs), GFP_KERNEL);
+	if (!mpcs)
+		return NULL;
+
+	mpcs->mdio.dev.parent = dev;
+	mpcs->mdio.bus = bus;
+	mpcs->mdio.addr = addr;
+	mpcs->phylink_pcs.ops = &marvell_c22_pcs_ops;
+	mpcs->phylink_pcs.neg_mode = true;
+
+	return mpcs;
+}
+
+static int marvell_c22_pcs_setup_irq(struct marvell_c22_pcs *mpcs,
+				     unsigned int irq)
+{
+	int err;
+
+	mpcs->phylink_pcs.poll = !irq;
+	mpcs->irq = irq;
+
+	if (irq) {
+		err = request_threaded_irq(irq, NULL,
+					   marvell_c22_pcs_handle_irq,
+					   IRQF_ONESHOT, mpcs->name, mpcs);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/* mv88e6352 specifics */
+
+static bool mv88e6352_pcs_link_check(struct marvell_c22_pcs *mpcs)
+{
+	struct mv88e6xxx_port *port = mpcs->port;
+	struct mv88e6xxx_chip *chip = port->chip;
+	u8 cmode;
+
+	/* Port 4 can be in auto-media mode. Check that the port is
+	 * associated with the mpcs.
+	 */
+	mv88e6xxx_reg_lock(chip);
+	chip->info->ops->port_get_cmode(chip, port->port, &cmode);
+	mv88e6xxx_reg_unlock(chip);
+
+	return cmode == MV88E6XXX_PORT_STS_CMODE_100BASEX ||
+	       cmode == MV88E6XXX_PORT_STS_CMODE_1000BASEX ||
+	       cmode == MV88E6XXX_PORT_STS_CMODE_SGMII;
+}
+
+static int mv88e6352_pcs_init(struct mv88e6xxx_chip *chip, int port)
+{
+	struct marvell_c22_pcs *mpcs;
+	struct mii_bus *bus;
+	struct device *dev;
+	unsigned int irq;
+	int err;
+
+	mv88e6xxx_reg_lock(chip);
+	err = mv88e6352_g2_scratch_port_has_serdes(chip, port);
+	mv88e6xxx_reg_unlock(chip);
+	if (err <= 0)
+		return err;
+
+	irq = mv88e6xxx_serdes_irq_mapping(chip, port);
+	bus = mv88e6xxx_default_mdio_bus(chip);
+	dev = chip->dev;
+
+	mpcs = marvell_c22_pcs_alloc(dev, bus, MV88E6352_ADDR_SERDES);
+	if (!mpcs)
+		return -ENOMEM;
+
+	snprintf(mpcs->name, sizeof(mpcs->name),
+		 "mv88e6xxx-%s-serdes-%d", dev_name(dev), port);
+
+	mpcs->link_check = mv88e6352_pcs_link_check;
+	mpcs->port = &chip->ports[port];
+
+	err = marvell_c22_pcs_setup_irq(mpcs, irq);
+	if (err) {
+		kfree(mpcs);
+		return err;
+	}
+
+	chip->ports[port].pcs_private = &mpcs->phylink_pcs;
+
+	return 0;
+}
+
+static void mv88e6352_pcs_teardown(struct mv88e6xxx_chip *chip, int port)
+{
+	struct marvell_c22_pcs *mpcs;
+	struct phylink_pcs *pcs;
+
+	pcs = chip->ports[port].pcs_private;
+	if (!pcs)
+		return;
+
+	mpcs = pcs_to_marvell_c22_pcs(pcs);
+
+	if (mpcs->irq)
+		free_irq(mpcs->irq, mpcs);
+
+	kfree(mpcs);
+
+	chip->ports[port].pcs_private = NULL;
+}
+
+static struct phylink_pcs *mv88e6352_pcs_select(struct mv88e6xxx_chip *chip,
+						int port,
+						phy_interface_t interface)
+{
+	return chip->ports[port].pcs_private;
+}
+
+const struct mv88e6xxx_pcs_ops mv88e6352_pcs_ops = {
+	.pcs_init = mv88e6352_pcs_init,
+	.pcs_teardown = mv88e6352_pcs_teardown,
+	.pcs_select = mv88e6352_pcs_select,
+};
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 5ac5687e76a94..5eea0cba3ee0b 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -39,12 +39,6 @@ static int mv88e6390_serdes_read(struct mv88e6xxx_chip *chip,
 	return mv88e6xxx_phy_read_c45(chip, lane, device, reg, val);
 }
 
-static int mv88e6390_serdes_write(struct mv88e6xxx_chip *chip,
-				  int lane, int device, int reg, u16 val)
-{
-	return mv88e6xxx_phy_write_c45(chip, lane, device, reg, val);
-}
-
 int mv88e6xxx_pcs_decode_state(struct device *dev, u16 bmsr, u16 lpa,
 			       u16 status, struct phylink_link_state *state)
 {
@@ -116,160 +110,6 @@ int mv88e6xxx_pcs_decode_state(struct device *dev, u16 bmsr, u16 lpa,
 	return 0;
 }
 
-int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
-			   bool up)
-{
-	u16 val, new_val;
-	int err;
-
-	err = mv88e6352_serdes_read(chip, MII_BMCR, &val);
-	if (err)
-		return err;
-
-	if (up)
-		new_val = val & ~BMCR_PDOWN;
-	else
-		new_val = val | BMCR_PDOWN;
-
-	if (val != new_val)
-		err = mv88e6352_serdes_write(chip, MII_BMCR, new_val);
-
-	return err;
-}
-
-int mv88e6352_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
-				int lane, unsigned int mode,
-				phy_interface_t interface,
-				const unsigned long *advertise)
-{
-	u16 adv, bmcr, val;
-	bool changed;
-	int err;
-
-	switch (interface) {
-	case PHY_INTERFACE_MODE_SGMII:
-		adv = 0x0001;
-		break;
-
-	case PHY_INTERFACE_MODE_1000BASEX:
-		adv = linkmode_adv_to_mii_adv_x(advertise,
-					ETHTOOL_LINK_MODE_1000baseX_Full_BIT);
-		break;
-
-	default:
-		return 0;
-	}
-
-	err = mv88e6352_serdes_read(chip, MII_ADVERTISE, &val);
-	if (err)
-		return err;
-
-	changed = val != adv;
-	if (changed) {
-		err = mv88e6352_serdes_write(chip, MII_ADVERTISE, adv);
-		if (err)
-			return err;
-	}
-
-	err = mv88e6352_serdes_read(chip, MII_BMCR, &val);
-	if (err)
-		return err;
-
-	if (phylink_autoneg_inband(mode))
-		bmcr = val | BMCR_ANENABLE;
-	else
-		bmcr = val & ~BMCR_ANENABLE;
-
-	if (bmcr == val)
-		return changed;
-
-	return mv88e6352_serdes_write(chip, MII_BMCR, bmcr);
-}
-
-int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
-				   int lane, struct phylink_link_state *state)
-{
-	u16 bmsr, lpa, status;
-	int err;
-
-	err = mv88e6352_serdes_read(chip, MII_BMSR, &bmsr);
-	if (err) {
-		dev_err(chip->dev, "can't read Serdes PHY BMSR: %d\n", err);
-		return err;
-	}
-
-	err = mv88e6352_serdes_read(chip, 0x11, &status);
-	if (err) {
-		dev_err(chip->dev, "can't read Serdes PHY status: %d\n", err);
-		return err;
-	}
-
-	err = mv88e6352_serdes_read(chip, MII_LPA, &lpa);
-	if (err) {
-		dev_err(chip->dev, "can't read Serdes PHY LPA: %d\n", err);
-		return err;
-	}
-
-	return mv88e6xxx_pcs_decode_state(chip->dev, bmsr, lpa, status, state);
-}
-
-int mv88e6352_serdes_pcs_an_restart(struct mv88e6xxx_chip *chip, int port,
-				    int lane)
-{
-	u16 bmcr;
-	int err;
-
-	err = mv88e6352_serdes_read(chip, MII_BMCR, &bmcr);
-	if (err)
-		return err;
-
-	return mv88e6352_serdes_write(chip, MII_BMCR, bmcr | BMCR_ANRESTART);
-}
-
-int mv88e6352_serdes_pcs_link_up(struct mv88e6xxx_chip *chip, int port,
-				 int lane, int speed, int duplex)
-{
-	u16 val, bmcr;
-	int err;
-
-	err = mv88e6352_serdes_read(chip, MII_BMCR, &val);
-	if (err)
-		return err;
-
-	bmcr = val & ~(BMCR_SPEED100 | BMCR_FULLDPLX | BMCR_SPEED1000);
-	switch (speed) {
-	case SPEED_1000:
-		bmcr |= BMCR_SPEED1000;
-		break;
-	case SPEED_100:
-		bmcr |= BMCR_SPEED100;
-		break;
-	case SPEED_10:
-		break;
-	}
-
-	if (duplex == DUPLEX_FULL)
-		bmcr |= BMCR_FULLDPLX;
-
-	if (bmcr == val)
-		return 0;
-
-	return mv88e6352_serdes_write(chip, MII_BMCR, bmcr);
-}
-
-int mv88e6352_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
-{
-	u8 cmode = chip->ports[port].cmode;
-	int lane = -ENODEV;
-
-	if ((cmode == MV88E6XXX_PORT_STS_CMODE_100BASEX) ||
-	    (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASEX) ||
-	    (cmode == MV88E6XXX_PORT_STS_CMODE_SGMII))
-		lane = 0xff; /* Unused */
-
-	return lane;
-}
-
 struct mv88e6352_serdes_hw_stat {
 	char string[ETH_GSTRING_LEN];
 	int sizeof_stat;
@@ -362,51 +202,6 @@ int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
 	return ARRAY_SIZE(mv88e6352_serdes_hw_stats);
 }
 
-static void mv88e6352_serdes_irq_link(struct mv88e6xxx_chip *chip, int port)
-{
-	u16 bmsr;
-	int err;
-
-	/* If the link has dropped, we want to know about it. */
-	err = mv88e6352_serdes_read(chip, MII_BMSR, &bmsr);
-	if (err) {
-		dev_err(chip->dev, "can't read Serdes BMSR: %d\n", err);
-		return;
-	}
-
-	dsa_port_phylink_mac_change(chip->ds, port, !!(bmsr & BMSR_LSTATUS));
-}
-
-irqreturn_t mv88e6352_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
-					int lane)
-{
-	irqreturn_t ret = IRQ_NONE;
-	u16 status;
-	int err;
-
-	err = mv88e6352_serdes_read(chip, MV88E6352_SERDES_INT_STATUS, &status);
-	if (err)
-		return ret;
-
-	if (status & MV88E6352_SERDES_INT_LINK_CHANGE) {
-		ret = IRQ_HANDLED;
-		mv88e6352_serdes_irq_link(chip, port);
-	}
-
-	return ret;
-}
-
-int mv88e6352_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, int lane,
-				bool enable)
-{
-	u16 val = 0;
-
-	if (enable)
-		val |= MV88E6352_SERDES_INT_LINK_CHANGE;
-
-	return mv88e6352_serdes_write(chip, MV88E6352_SERDES_INT_ENABLE, val);
-}
-
 unsigned int mv88e6352_serdes_irq_mapping(struct mv88e6xxx_chip *chip, int port)
 {
 	return irq_find_mapping(chip->g2_irq.domain, MV88E6352_SERDES_IRQ);
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index 93d363eb61ea8..73cf2d0b8bb3c 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -113,51 +113,34 @@ int mv88e6xxx_pcs_decode_state(struct device *dev, u16 bmsr, u16 lpa,
 			       u16 status, struct phylink_link_state *state);
 
 int mv88e6341_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
-int mv88e6352_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6393x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
-int mv88e6352_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
-				int lane, unsigned int mode,
-				phy_interface_t interface,
-				const unsigned long *advertise);
 int mv88e6390_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
 				int lane, unsigned int mode,
 				phy_interface_t interface,
 				const unsigned long *advertise);
-int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
-				   int lane, struct phylink_link_state *state);
 int mv88e6390_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
 				   int lane, struct phylink_link_state *state);
 int mv88e6393x_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
 				    int lane, struct phylink_link_state *state);
-int mv88e6352_serdes_pcs_an_restart(struct mv88e6xxx_chip *chip, int port,
-				    int lane);
 int mv88e6390_serdes_pcs_an_restart(struct mv88e6xxx_chip *chip, int port,
 				    int lane);
-int mv88e6352_serdes_pcs_link_up(struct mv88e6xxx_chip *chip, int port,
-				 int lane, int speed, int duplex);
 int mv88e6390_serdes_pcs_link_up(struct mv88e6xxx_chip *chip, int port,
 				 int lane, int speed, int duplex);
 unsigned int mv88e6352_serdes_irq_mapping(struct mv88e6xxx_chip *chip,
 					  int port);
 unsigned int mv88e6390_serdes_irq_mapping(struct mv88e6xxx_chip *chip,
 					  int port);
-int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
-			   bool on);
 int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
 			   bool on);
 int mv88e6393x_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
 			    bool on);
 int mv88e6393x_serdes_setup_errata(struct mv88e6xxx_chip *chip);
-int mv88e6352_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, int lane,
-				bool enable);
 int mv88e6390_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, int lane,
 				bool enable);
 int mv88e6393x_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port,
 				 int lane, bool enable);
-irqreturn_t mv88e6352_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
-					int lane);
 irqreturn_t mv88e6390_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
 					int lane);
 irqreturn_t mv88e6393x_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
@@ -246,5 +229,6 @@ mv88e6xxx_serdes_irq_status(struct mv88e6xxx_chip *chip, int port, int lane)
 }
 
 extern const struct mv88e6xxx_pcs_ops mv88e6185_pcs_ops;
+extern const struct mv88e6xxx_pcs_ops mv88e6352_pcs_ops;
 
 #endif
-- 
GitLab


From e5b732a275f5fae0f1342fb8cf76de654cd51e50 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:53 +0100
Subject: [PATCH 0128/1806] net: dsa: mv88e6xxx: convert 88e639x to phylink_pcs

Convert the 88E6390, 88E6390X, and 88E6393X family of switches to use
the phylink_pcs infrastructure.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/Makefile   |   1 +
 drivers/net/dsa/mv88e6xxx/chip.c     |  80 +--
 drivers/net/dsa/mv88e6xxx/pcs-639x.c | 898 +++++++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/serdes.c   | 785 -----------------------
 drivers/net/dsa/mv88e6xxx/serdes.h   |  31 +-
 5 files changed, 914 insertions(+), 881 deletions(-)
 create mode 100644 drivers/net/dsa/mv88e6xxx/pcs-639x.c

diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile
index 05976e1f93f66..a9a9651187db7 100644
--- a/drivers/net/dsa/mv88e6xxx/Makefile
+++ b/drivers/net/dsa/mv88e6xxx/Makefile
@@ -11,6 +11,7 @@ mv88e6xxx-objs += global2_scratch.o
 mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_PTP) += hwtstamp.o
 mv88e6xxx-objs += pcs-6185.o
 mv88e6xxx-objs += pcs-6352.o
+mv88e6xxx-objs += pcs-639x.o
 mv88e6xxx-objs += phy.o
 mv88e6xxx-objs += port.o
 mv88e6xxx-objs += port_hidden.o
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 90573407d4048..a1ca827157141 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4417,16 +4417,8 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
 	.serdes_get_lane = mv88e6341_serdes_get_lane,
-	/* Check status register pause & lpa register */
-	.serdes_pcs_get_state = mv88e6390_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6390_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6390_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6390_serdes_pcs_link_up,
 	.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6390_serdes_irq_enable,
-	.serdes_irq_status = mv88e6390_serdes_irq_status,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.serdes_get_sset_count = mv88e6390_serdes_get_sset_count,
 	.serdes_get_strings = mv88e6390_serdes_get_strings,
@@ -4434,6 +4426,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6390_serdes_get_regs,
 	.phylink_get_caps = mv88e6341_phylink_get_caps,
+	.pcs_ops = &mv88e6390_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6161_ops = {
@@ -4808,22 +4801,15 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6390_g1_stu_getnext,
 	.stu_loadpurge = mv88e6390_g1_stu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
 	.serdes_get_lane = mv88e6390_serdes_get_lane,
-	/* Check status register pause & lpa register */
-	.serdes_pcs_get_state = mv88e6390_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6390_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6390_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6390_serdes_pcs_link_up,
 	.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6390_serdes_irq_enable,
-	.serdes_irq_status = mv88e6390_serdes_irq_status,
 	.serdes_get_strings = mv88e6390_serdes_get_strings,
 	.serdes_get_stats = mv88e6390_serdes_get_stats,
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6390_serdes_get_regs,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.phylink_get_caps = mv88e6390_phylink_get_caps,
+	.pcs_ops = &mv88e6390_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6190x_ops = {
@@ -4873,22 +4859,15 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6390_g1_stu_getnext,
 	.stu_loadpurge = mv88e6390_g1_stu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
 	.serdes_get_lane = mv88e6390x_serdes_get_lane,
-	/* Check status register pause & lpa register */
-	.serdes_pcs_get_state = mv88e6390_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6390_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6390_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6390_serdes_pcs_link_up,
 	.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6390_serdes_irq_enable,
-	.serdes_irq_status = mv88e6390_serdes_irq_status,
 	.serdes_get_strings = mv88e6390_serdes_get_strings,
 	.serdes_get_stats = mv88e6390_serdes_get_stats,
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6390_serdes_get_regs,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.phylink_get_caps = mv88e6390x_phylink_get_caps,
+	.pcs_ops = &mv88e6390_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6191_ops = {
@@ -4936,16 +4915,8 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6390_g1_stu_getnext,
 	.stu_loadpurge = mv88e6390_g1_stu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
 	.serdes_get_lane = mv88e6390_serdes_get_lane,
-	/* Check status register pause & lpa register */
-	.serdes_pcs_get_state = mv88e6390_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6390_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6390_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6390_serdes_pcs_link_up,
 	.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6390_serdes_irq_enable,
-	.serdes_irq_status = mv88e6390_serdes_irq_status,
 	.serdes_get_strings = mv88e6390_serdes_get_strings,
 	.serdes_get_stats = mv88e6390_serdes_get_stats,
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
@@ -4953,6 +4924,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
 	.phylink_get_caps = mv88e6390_phylink_get_caps,
+	.pcs_ops = &mv88e6390_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6240_ops = {
@@ -5102,16 +5074,8 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6390_g1_stu_getnext,
 	.stu_loadpurge = mv88e6390_g1_stu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
 	.serdes_get_lane = mv88e6390_serdes_get_lane,
-	/* Check status register pause & lpa register */
-	.serdes_pcs_get_state = mv88e6390_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6390_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6390_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6390_serdes_pcs_link_up,
 	.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6390_serdes_irq_enable,
-	.serdes_irq_status = mv88e6390_serdes_irq_status,
 	.serdes_get_strings = mv88e6390_serdes_get_strings,
 	.serdes_get_stats = mv88e6390_serdes_get_stats,
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
@@ -5120,6 +5084,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6390_ptp_ops,
 	.phylink_get_caps = mv88e6390_phylink_get_caps,
+	.pcs_ops = &mv88e6390_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6320_ops = {
@@ -5264,16 +5229,8 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
 	.serdes_get_lane = mv88e6341_serdes_get_lane,
-	/* Check status register pause & lpa register */
-	.serdes_pcs_get_state = mv88e6390_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6390_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6390_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6390_serdes_pcs_link_up,
 	.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6390_serdes_irq_enable,
-	.serdes_irq_status = mv88e6390_serdes_irq_status,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -5283,6 +5240,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6390_serdes_get_regs,
 	.phylink_get_caps = mv88e6341_phylink_get_caps,
+	.pcs_ops = &mv88e6390_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6350_ops = {
@@ -5488,16 +5446,8 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6390_g1_stu_getnext,
 	.stu_loadpurge = mv88e6390_g1_stu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
 	.serdes_get_lane = mv88e6390_serdes_get_lane,
-	/* Check status register pause & lpa register */
-	.serdes_pcs_get_state = mv88e6390_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6390_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6390_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6390_serdes_pcs_link_up,
 	.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6390_serdes_irq_enable,
-	.serdes_irq_status = mv88e6390_serdes_irq_status,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6390_ptp_ops,
@@ -5507,6 +5457,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6390_serdes_get_regs,
 	.phylink_get_caps = mv88e6390_phylink_get_caps,
+	.pcs_ops = &mv88e6390_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6390x_ops = {
@@ -5557,15 +5508,8 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6390_g1_stu_getnext,
 	.stu_loadpurge = mv88e6390_g1_stu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
 	.serdes_get_lane = mv88e6390x_serdes_get_lane,
-	.serdes_pcs_get_state = mv88e6390_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6390_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6390_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6390_serdes_pcs_link_up,
 	.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6390_serdes_irq_enable,
-	.serdes_irq_status = mv88e6390_serdes_irq_status,
 	.serdes_get_sset_count = mv88e6390_serdes_get_sset_count,
 	.serdes_get_strings = mv88e6390_serdes_get_strings,
 	.serdes_get_stats = mv88e6390_serdes_get_stats,
@@ -5575,11 +5519,11 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6390_ptp_ops,
 	.phylink_get_caps = mv88e6390x_phylink_get_caps,
+	.pcs_ops = &mv88e6390_pcs_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6393x_ops = {
 	/* MV88E6XXX_FAMILY_6393 */
-	.setup_errata = mv88e6393x_serdes_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -5629,20 +5573,14 @@ static const struct mv88e6xxx_ops mv88e6393x_ops = {
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6390_g1_stu_getnext,
 	.stu_loadpurge = mv88e6390_g1_stu_loadpurge,
-	.serdes_power = mv88e6393x_serdes_power,
 	.serdes_get_lane = mv88e6393x_serdes_get_lane,
-	.serdes_pcs_get_state = mv88e6393x_serdes_pcs_get_state,
-	.serdes_pcs_config = mv88e6390_serdes_pcs_config,
-	.serdes_pcs_an_restart = mv88e6390_serdes_pcs_an_restart,
-	.serdes_pcs_link_up = mv88e6390_serdes_pcs_link_up,
 	.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
-	.serdes_irq_enable = mv88e6393x_serdes_irq_enable,
-	.serdes_irq_status = mv88e6393x_serdes_irq_status,
 	/* TODO: serdes stats */
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
 	.phylink_get_caps = mv88e6393x_phylink_get_caps,
+	.pcs_ops = &mv88e6393x_pcs_ops,
 };
 
 static const struct mv88e6xxx_info mv88e6xxx_table[] = {
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
new file mode 100644
index 0000000000000..98dd49dac4215
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
@@ -0,0 +1,898 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Marvell 88E6352 family SERDES PCS support
+ *
+ * Copyright (c) 2008 Marvell Semiconductor
+ *
+ * Copyright (c) 2017 Andrew Lunn <andrew@lunn.ch>
+ */
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/mii.h>
+
+#include "chip.h"
+#include "global2.h"
+#include "phy.h"
+#include "port.h"
+#include "serdes.h"
+
+struct mv88e639x_pcs {
+	struct mdio_device mdio;
+	struct phylink_pcs sgmii_pcs;
+	struct phylink_pcs xg_pcs;
+	bool supports_5g;
+	phy_interface_t interface;
+	unsigned int irq;
+	char name[64];
+	irqreturn_t (*handle_irq)(struct mv88e639x_pcs *mpcs);
+};
+
+static int mv88e639x_read(struct mv88e639x_pcs *mpcs, u16 regnum, u16 *val)
+{
+	int err;
+
+	err = mdiodev_c45_read(&mpcs->mdio, MDIO_MMD_PHYXS, regnum);
+	if (err < 0)
+		return err;
+
+	*val = err;
+
+	return 0;
+}
+
+static int mv88e639x_write(struct mv88e639x_pcs *mpcs, u16 regnum, u16 val)
+{
+	return mdiodev_c45_write(&mpcs->mdio, MDIO_MMD_PHYXS, regnum, val);
+}
+
+static int mv88e639x_modify(struct mv88e639x_pcs *mpcs, u16 regnum, u16 mask,
+			    u16 val)
+{
+	return mdiodev_c45_modify(&mpcs->mdio, MDIO_MMD_PHYXS, regnum, mask,
+				  val);
+}
+
+static int mv88e639x_modify_changed(struct mv88e639x_pcs *mpcs, u16 regnum,
+				    u16 mask, u16 set)
+{
+	return mdiodev_c45_modify_changed(&mpcs->mdio, MDIO_MMD_PHYXS, regnum,
+					  mask, set);
+}
+
+static struct mv88e639x_pcs *
+mv88e639x_pcs_alloc(struct device *dev, struct mii_bus *bus, unsigned int addr,
+		    int port)
+{
+	struct mv88e639x_pcs *mpcs;
+
+	mpcs = kzalloc(sizeof(*mpcs), GFP_KERNEL);
+	if (!mpcs)
+		return NULL;
+
+	mpcs->mdio.dev.parent = dev;
+	mpcs->mdio.bus = bus;
+	mpcs->mdio.addr = addr;
+
+	snprintf(mpcs->name, sizeof(mpcs->name),
+		 "mv88e6xxx-%s-serdes-%d", dev_name(dev), port);
+
+	return mpcs;
+}
+
+static irqreturn_t mv88e639x_pcs_handle_irq(int irq, void *dev_id)
+{
+	struct mv88e639x_pcs *mpcs = dev_id;
+	irqreturn_t (*handler)(struct mv88e639x_pcs *);
+
+	handler = READ_ONCE(mpcs->handle_irq);
+	if (!handler)
+		return IRQ_NONE;
+
+	return handler(mpcs);
+}
+
+static int mv88e639x_pcs_setup_irq(struct mv88e639x_pcs *mpcs,
+				   struct mv88e6xxx_chip *chip, int port)
+{
+	unsigned int irq;
+
+	irq = mv88e6xxx_serdes_irq_mapping(chip, port);
+	if (!irq) {
+		/* Use polling mode */
+		mpcs->sgmii_pcs.poll = true;
+		mpcs->xg_pcs.poll = true;
+		return 0;
+	}
+
+	mpcs->irq = irq;
+
+	return request_threaded_irq(irq, NULL, mv88e639x_pcs_handle_irq,
+				    IRQF_ONESHOT, mpcs->name, mpcs);
+}
+
+static void mv88e639x_pcs_teardown(struct mv88e6xxx_chip *chip, int port)
+{
+	struct mv88e639x_pcs *mpcs = chip->ports[port].pcs_private;
+
+	if (!mpcs)
+		return;
+
+	if (mpcs->irq)
+		free_irq(mpcs->irq, mpcs);
+
+	kfree(mpcs);
+
+	chip->ports[port].pcs_private = NULL;
+}
+
+static struct mv88e639x_pcs *sgmii_pcs_to_mv88e639x_pcs(struct phylink_pcs *pcs)
+{
+	return container_of(pcs, struct mv88e639x_pcs, sgmii_pcs);
+}
+
+static irqreturn_t mv88e639x_sgmii_handle_irq(struct mv88e639x_pcs *mpcs)
+{
+	u16 int_status;
+	int err;
+
+	err = mv88e639x_read(mpcs, MV88E6390_SGMII_INT_STATUS, &int_status);
+	if (err)
+		return IRQ_NONE;
+
+	if (int_status & (MV88E6390_SGMII_INT_LINK_DOWN |
+			  MV88E6390_SGMII_INT_LINK_UP)) {
+		phylink_pcs_change(&mpcs->sgmii_pcs,
+				   int_status & MV88E6390_SGMII_INT_LINK_UP);
+
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static int mv88e639x_sgmii_pcs_control_irq(struct mv88e639x_pcs *mpcs,
+					   bool enable)
+{
+	u16 val = 0;
+
+	if (enable)
+		val |= MV88E6390_SGMII_INT_LINK_DOWN |
+		       MV88E6390_SGMII_INT_LINK_UP;
+
+	return mv88e639x_modify(mpcs, MV88E6390_SGMII_INT_ENABLE,
+				MV88E6390_SGMII_INT_LINK_DOWN |
+				MV88E6390_SGMII_INT_LINK_UP, val);
+}
+
+static int mv88e639x_sgmii_pcs_control_pwr(struct mv88e639x_pcs *mpcs,
+					   bool enable)
+{
+	u16 mask, val;
+
+	if (enable) {
+		mask = BMCR_RESET | BMCR_LOOPBACK | BMCR_PDOWN;
+		val = 0;
+	} else {
+		mask = val = BMCR_PDOWN;
+	}
+
+	return mv88e639x_modify(mpcs, MV88E6390_SGMII_BMCR, mask, val);
+}
+
+static int mv88e639x_sgmii_pcs_enable(struct phylink_pcs *pcs)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+
+	/* power enable done in post_config */
+	mpcs->handle_irq = mv88e639x_sgmii_handle_irq;
+
+	return mv88e639x_sgmii_pcs_control_irq(mpcs, !!mpcs->irq);
+}
+
+static void mv88e639x_sgmii_pcs_disable(struct phylink_pcs *pcs)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+
+	mv88e639x_sgmii_pcs_control_irq(mpcs, false);
+	mv88e639x_sgmii_pcs_control_pwr(mpcs, false);
+}
+
+static void mv88e639x_sgmii_pcs_pre_config(struct phylink_pcs *pcs,
+					   phy_interface_t interface)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+
+	mv88e639x_sgmii_pcs_control_pwr(mpcs, false);
+}
+
+static int mv88e639x_sgmii_pcs_post_config(struct phylink_pcs *pcs,
+					   phy_interface_t interface)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+
+	mv88e639x_sgmii_pcs_control_pwr(mpcs, true);
+
+	return 0;
+}
+
+static void mv88e639x_sgmii_pcs_get_state(struct phylink_pcs *pcs,
+					  struct phylink_link_state *state)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+	u16 bmsr, lpa, status;
+	int err;
+
+	err = mv88e639x_read(mpcs, MV88E6390_SGMII_BMSR, &bmsr);
+	if (err) {
+		dev_err(mpcs->mdio.dev.parent,
+			"can't read Serdes PHY %s: %pe\n",
+			"BMSR", ERR_PTR(err));
+		state->link = false;
+		return;
+	}
+
+	err = mv88e639x_read(mpcs, MV88E6390_SGMII_LPA, &lpa);
+	if (err) {
+		dev_err(mpcs->mdio.dev.parent,
+			"can't read Serdes PHY %s: %pe\n",
+			"LPA", ERR_PTR(err));
+		state->link = false;
+		return;
+	}
+
+	err = mv88e639x_read(mpcs, MV88E6390_SGMII_PHY_STATUS, &status);
+	if (err) {
+		dev_err(mpcs->mdio.dev.parent,
+			"can't read Serdes PHY %s: %pe\n",
+			"status", ERR_PTR(err));
+		state->link = false;
+		return;
+	}
+
+	mv88e6xxx_pcs_decode_state(mpcs->mdio.dev.parent, bmsr, lpa, status,
+				   state);
+}
+
+static int mv88e639x_sgmii_pcs_config(struct phylink_pcs *pcs,
+				      unsigned int neg_mode,
+				      phy_interface_t interface,
+				      const unsigned long *advertising,
+				      bool permit_pause_to_mac)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+	u16 val, bmcr;
+	bool changed;
+	int adv, err;
+
+	adv = phylink_mii_c22_pcs_encode_advertisement(interface, advertising);
+	if (adv < 0)
+		return 0;
+
+	mpcs->interface = interface;
+
+	err = mv88e639x_modify_changed(mpcs, MV88E6390_SGMII_ADVERTISE,
+				       0xffff, adv);
+	if (err < 0)
+		return err;
+
+	changed = err > 0;
+
+	err = mv88e639x_read(mpcs, MV88E6390_SGMII_BMCR, &val);
+	if (err)
+		return err;
+
+	if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED)
+		bmcr = val | BMCR_ANENABLE;
+	else
+		bmcr = val & ~BMCR_ANENABLE;
+
+	/* setting ANENABLE triggers a restart of negotiation */
+	if (bmcr == val)
+		return changed;
+
+	return mv88e639x_write(mpcs, MV88E6390_SGMII_BMCR, bmcr);
+}
+
+static void mv88e639x_sgmii_pcs_an_restart(struct phylink_pcs *pcs)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+
+	mv88e639x_modify(mpcs, MV88E6390_SGMII_BMCR,
+			 BMCR_ANRESTART, BMCR_ANRESTART);
+}
+
+static void mv88e639x_sgmii_pcs_link_up(struct phylink_pcs *pcs,
+					unsigned int mode,
+					phy_interface_t interface,
+					int speed, int duplex)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+	u16 bmcr;
+	int err;
+
+	if (phylink_autoneg_inband(mode))
+		return;
+
+	bmcr = mii_bmcr_encode_fixed(speed, duplex);
+
+	err = mv88e639x_modify(mpcs, MV88E6390_SGMII_BMCR,
+			       BMCR_SPEED1000 | BMCR_SPEED100 | BMCR_FULLDPLX,
+			       bmcr);
+	if (err)
+		dev_err(mpcs->mdio.dev.parent,
+			"can't access Serdes PHY %s: %pe\n",
+			"BMCR", ERR_PTR(err));
+}
+
+static const struct phylink_pcs_ops mv88e639x_sgmii_pcs_ops = {
+	.pcs_enable = mv88e639x_sgmii_pcs_enable,
+	.pcs_disable = mv88e639x_sgmii_pcs_disable,
+	.pcs_pre_config = mv88e639x_sgmii_pcs_pre_config,
+	.pcs_post_config = mv88e639x_sgmii_pcs_post_config,
+	.pcs_get_state = mv88e639x_sgmii_pcs_get_state,
+	.pcs_an_restart = mv88e639x_sgmii_pcs_an_restart,
+	.pcs_config = mv88e639x_sgmii_pcs_config,
+	.pcs_link_up = mv88e639x_sgmii_pcs_link_up,
+};
+
+static struct mv88e639x_pcs *xg_pcs_to_mv88e639x_pcs(struct phylink_pcs *pcs)
+{
+	return container_of(pcs, struct mv88e639x_pcs, xg_pcs);
+}
+
+static int mv88e639x_xg_pcs_enable(struct mv88e639x_pcs *mpcs)
+{
+	return mv88e639x_modify(mpcs, MV88E6390_10G_CTRL1,
+				MDIO_CTRL1_RESET | MDIO_PCS_CTRL1_LOOPBACK |
+				MDIO_CTRL1_LPOWER, 0);
+}
+
+static void mv88e639x_xg_pcs_disable(struct mv88e639x_pcs *mpcs)
+{
+	mv88e639x_modify(mpcs, MV88E6390_10G_CTRL1, MDIO_CTRL1_LPOWER,
+			 MDIO_CTRL1_LPOWER);
+}
+
+static void mv88e639x_xg_pcs_get_state(struct phylink_pcs *pcs,
+				       struct phylink_link_state *state)
+{
+	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
+	u16 status;
+	int err;
+
+	state->link = false;
+
+	err = mv88e639x_read(mpcs, MV88E6390_10G_STAT1, &status);
+	if (err) {
+		dev_err(mpcs->mdio.dev.parent,
+			"can't read Serdes PHY %s: %pe\n",
+			"STAT1", ERR_PTR(err));
+		return;
+	}
+
+	state->link = !!(status & MDIO_STAT1_LSTATUS);
+	if (state->link) {
+		switch (state->interface) {
+		case PHY_INTERFACE_MODE_5GBASER:
+			state->speed = SPEED_5000;
+			break;
+
+		case PHY_INTERFACE_MODE_10GBASER:
+		case PHY_INTERFACE_MODE_RXAUI:
+		case PHY_INTERFACE_MODE_XAUI:
+			state->speed = SPEED_10000;
+			break;
+
+		default:
+			state->link = false;
+			return;
+		}
+
+		state->duplex = DUPLEX_FULL;
+	}
+}
+
+static int mv88e639x_xg_pcs_config(struct phylink_pcs *pcs,
+				   unsigned int neg_mode,
+				   phy_interface_t interface,
+				   const unsigned long *advertising,
+				   bool permit_pause_to_mac)
+{
+	return 0;
+}
+
+static struct phylink_pcs *
+mv88e639x_pcs_select(struct mv88e6xxx_chip *chip, int port,
+		     phy_interface_t mode)
+{
+	struct mv88e639x_pcs *mpcs;
+
+	mpcs = chip->ports[port].pcs_private;
+	if (!mpcs)
+		return NULL;
+
+	switch (mode) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
+		return &mpcs->sgmii_pcs;
+
+	case PHY_INTERFACE_MODE_5GBASER:
+		if (!mpcs->supports_5g)
+			return NULL;
+		fallthrough;
+	case PHY_INTERFACE_MODE_10GBASER:
+	case PHY_INTERFACE_MODE_XAUI:
+	case PHY_INTERFACE_MODE_RXAUI:
+		return &mpcs->xg_pcs;
+
+	default:
+		return NULL;
+	}
+}
+
+/* Marvell 88E6390 Specific support */
+
+static irqreturn_t mv88e6390_xg_handle_irq(struct mv88e639x_pcs *mpcs)
+{
+	u16 int_status;
+	int err;
+
+	err = mv88e639x_read(mpcs, MV88E6390_10G_INT_STATUS, &int_status);
+	if (err)
+		return IRQ_NONE;
+
+	if (int_status & (MV88E6390_10G_INT_LINK_DOWN |
+			  MV88E6390_10G_INT_LINK_UP)) {
+		phylink_pcs_change(&mpcs->xg_pcs,
+				   int_status & MV88E6390_10G_INT_LINK_UP);
+
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static int mv88e6390_xg_control_irq(struct mv88e639x_pcs *mpcs, bool enable)
+{
+	u16 val = 0;
+
+	if (enable)
+		val = MV88E6390_10G_INT_LINK_DOWN | MV88E6390_10G_INT_LINK_UP;
+
+	return mv88e639x_modify(mpcs, MV88E6390_10G_INT_ENABLE,
+				MV88E6390_10G_INT_LINK_DOWN |
+				MV88E6390_10G_INT_LINK_UP, val);
+}
+
+static int mv88e6390_xg_pcs_enable(struct phylink_pcs *pcs)
+{
+	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
+	int err;
+
+	err = mv88e639x_xg_pcs_enable(mpcs);
+	if (err)
+		return err;
+
+	mpcs->handle_irq = mv88e6390_xg_handle_irq;
+
+	return mv88e6390_xg_control_irq(mpcs, !!mpcs->irq);
+}
+
+static void mv88e6390_xg_pcs_disable(struct phylink_pcs *pcs)
+{
+	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
+
+	mv88e6390_xg_control_irq(mpcs, false);
+	mv88e639x_xg_pcs_disable(mpcs);
+}
+
+static const struct phylink_pcs_ops mv88e6390_xg_pcs_ops = {
+	.pcs_enable = mv88e6390_xg_pcs_enable,
+	.pcs_disable = mv88e6390_xg_pcs_disable,
+	.pcs_get_state = mv88e639x_xg_pcs_get_state,
+	.pcs_config = mv88e639x_xg_pcs_config,
+};
+
+static int mv88e6390_pcs_enable_checker(struct mv88e639x_pcs *mpcs)
+{
+	return mv88e639x_modify(mpcs, MV88E6390_PG_CONTROL,
+				MV88E6390_PG_CONTROL_ENABLE_PC,
+				MV88E6390_PG_CONTROL_ENABLE_PC);
+}
+
+static int mv88e6390_pcs_init(struct mv88e6xxx_chip *chip, int port)
+{
+	struct mv88e639x_pcs *mpcs;
+	struct mii_bus *bus;
+	struct device *dev;
+	int lane, err;
+
+	lane = mv88e6xxx_serdes_get_lane(chip, port);
+	if (lane < 0)
+		return 0;
+
+	bus = mv88e6xxx_default_mdio_bus(chip);
+	dev = chip->dev;
+
+	mpcs = mv88e639x_pcs_alloc(dev, bus, lane, port);
+	if (!mpcs)
+		return -ENOMEM;
+
+	mpcs->sgmii_pcs.ops = &mv88e639x_sgmii_pcs_ops;
+	mpcs->sgmii_pcs.neg_mode = true;
+	mpcs->xg_pcs.ops = &mv88e6390_xg_pcs_ops;
+	mpcs->xg_pcs.neg_mode = true;
+
+	err = mv88e639x_pcs_setup_irq(mpcs, chip, port);
+	if (err)
+		goto err_free;
+
+	/* 6390 and 6390x has the checker, 6393x doesn't appear to? */
+	/* This is to enable gathering the statistics. Maybe this
+	 * should call out to a helper? Or we could do this at init time.
+	 */
+	err = mv88e6390_pcs_enable_checker(mpcs);
+	if (err)
+		goto err_free;
+
+	chip->ports[port].pcs_private = mpcs;
+
+	return 0;
+
+err_free:
+	kfree(mpcs);
+	return err;
+}
+
+const struct mv88e6xxx_pcs_ops mv88e6390_pcs_ops = {
+	.pcs_init = mv88e6390_pcs_init,
+	.pcs_teardown = mv88e639x_pcs_teardown,
+	.pcs_select = mv88e639x_pcs_select,
+};
+
+/* Marvell 88E6393X Specific support */
+
+static int mv88e6393x_power_lane(struct mv88e639x_pcs *mpcs, bool enable)
+{
+	u16 val = MV88E6393X_SERDES_CTRL1_TX_PDOWN |
+		  MV88E6393X_SERDES_CTRL1_RX_PDOWN;
+
+	return mv88e639x_modify(mpcs, MV88E6393X_SERDES_CTRL1, val,
+				enable ? 0 : val);
+}
+
+/* mv88e6393x family errata 4.6:
+ * Cannot clear PwrDn bit on SERDES if device is configured CPU_MGD mode or
+ * P0_mode is configured for [x]MII.
+ * Workaround: Set SERDES register 4.F002 bit 5=0 and bit 15=1.
+ *
+ * It seems that after this workaround the SERDES is automatically powered up
+ * (the bit is cleared), so power it down.
+ */
+static int mv88e6393x_erratum_4_6(struct mv88e639x_pcs *mpcs)
+{
+	int err;
+
+	err = mv88e639x_modify(mpcs, MV88E6393X_SERDES_POC,
+			       MV88E6393X_SERDES_POC_PDOWN |
+			       MV88E6393X_SERDES_POC_RESET,
+			       MV88E6393X_SERDES_POC_RESET);
+	if (err)
+		return err;
+
+	err = mv88e639x_modify(mpcs, MV88E6390_SGMII_BMCR,
+			       BMCR_PDOWN, BMCR_PDOWN);
+	if (err)
+		return err;
+
+	err = mv88e639x_sgmii_pcs_control_pwr(mpcs, false);
+	if (err)
+		return err;
+
+	return mv88e6393x_power_lane(mpcs, false);
+}
+
+/* mv88e6393x family errata 4.8:
+ * When a SERDES port is operating in 1000BASE-X or SGMII mode link may not
+ * come up after hardware reset or software reset of SERDES core. Workaround
+ * is to write SERDES register 4.F074.14=1 for only those modes and 0 in all
+ * other modes.
+ */
+static int mv88e6393x_erratum_4_8(struct mv88e639x_pcs *mpcs)
+{
+	u16 reg, poc;
+	int err;
+
+	err = mv88e639x_read(mpcs, MV88E6393X_SERDES_POC, &poc);
+	if (err)
+		return err;
+
+	poc &= MV88E6393X_SERDES_POC_PCS_MASK;
+	if (poc == MV88E6393X_SERDES_POC_PCS_1000BASEX ||
+	    poc == MV88E6393X_SERDES_POC_PCS_SGMII_PHY ||
+	    poc == MV88E6393X_SERDES_POC_PCS_SGMII_MAC)
+		reg = MV88E6393X_ERRATA_4_8_BIT;
+	else
+		reg = 0;
+
+	return mv88e639x_modify(mpcs, MV88E6393X_ERRATA_4_8_REG,
+				MV88E6393X_ERRATA_4_8_BIT, reg);
+}
+
+/* mv88e6393x family errata 5.2:
+ * For optimal signal integrity the following sequence should be applied to
+ * SERDES operating in 10G mode. These registers only apply to 10G operation
+ * and have no effect on other speeds.
+ */
+static int mv88e6393x_erratum_5_2(struct mv88e639x_pcs *mpcs)
+{
+	static const struct {
+		u16 dev, reg, val, mask;
+	} fixes[] = {
+		{ MDIO_MMD_VEND1, 0x8093, 0xcb5a, 0xffff },
+		{ MDIO_MMD_VEND1, 0x8171, 0x7088, 0xffff },
+		{ MDIO_MMD_VEND1, 0x80c9, 0x311a, 0xffff },
+		{ MDIO_MMD_VEND1, 0x80a2, 0x8000, 0xff7f },
+		{ MDIO_MMD_VEND1, 0x80a9, 0x0000, 0xfff0 },
+		{ MDIO_MMD_VEND1, 0x80a3, 0x0000, 0xf8ff },
+		{ MDIO_MMD_PHYXS, MV88E6393X_SERDES_POC,
+		  MV88E6393X_SERDES_POC_RESET, MV88E6393X_SERDES_POC_RESET },
+	};
+	int err, i;
+
+	for (i = 0; i < ARRAY_SIZE(fixes); ++i) {
+		err = mdiodev_c45_modify(&mpcs->mdio, fixes[i].dev,
+					 fixes[i].reg, fixes[i].mask,
+					 fixes[i].val);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/* Inband AN is broken on Amethyst in 2500base-x mode when set by standard
+ * mechanism (via cmode).
+ * We can get around this by configuring the PCS mode to 1000base-x and then
+ * writing value 0x58 to register 1e.8000. (This must be done while SerDes
+ * receiver and transmitter are disabled, which is, when this function is
+ * called.)
+ * It seem that when we do this configuration to 2500base-x mode (by changing
+ * PCS mode to 1000base-x and frequency to 3.125 GHz from 1.25 GHz) and then
+ * configure to sgmii or 1000base-x, the device thinks that it already has
+ * SerDes at 1.25 GHz and does not change the 1e.8000 register, leaving SerDes
+ * at 3.125 GHz.
+ * To avoid this, change PCS mode back to 2500base-x when disabling SerDes from
+ * 2500base-x mode.
+ */
+static int mv88e6393x_fix_2500basex_an(struct mv88e639x_pcs *mpcs, bool on)
+{
+	u16 reg;
+	int err;
+
+	if (on)
+		reg = MV88E6393X_SERDES_POC_PCS_1000BASEX |
+		      MV88E6393X_SERDES_POC_AN;
+	else
+		reg = MV88E6393X_SERDES_POC_PCS_2500BASEX;
+
+	reg |= MV88E6393X_SERDES_POC_RESET;
+
+	err = mv88e639x_modify(mpcs, MV88E6393X_SERDES_POC,
+			       MV88E6393X_SERDES_POC_PCS_MASK |
+			       MV88E6393X_SERDES_POC_AN |
+			       MV88E6393X_SERDES_POC_RESET, reg);
+	if (err)
+		return err;
+
+	return mdiodev_c45_write(&mpcs->mdio, MDIO_MMD_VEND1, 0x8000, 0x58);
+}
+
+static int mv88e6393x_sgmii_apply_2500basex_an(struct mv88e639x_pcs *mpcs,
+					       phy_interface_t interface,
+					       bool enable)
+{
+	int err;
+
+	if (interface != PHY_INTERFACE_MODE_2500BASEX)
+		return 0;
+
+	err = mv88e6393x_fix_2500basex_an(mpcs, enable);
+	if (err)
+		dev_err(mpcs->mdio.dev.parent,
+			"failed to %s 2500basex fix: %pe\n",
+			enable ? "enable" : "disable", ERR_PTR(err));
+
+	return err;
+}
+
+static void mv88e6393x_sgmii_pcs_disable(struct phylink_pcs *pcs)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+
+	mv88e639x_sgmii_pcs_disable(pcs);
+	mv88e6393x_power_lane(mpcs, false);
+	mv88e6393x_sgmii_apply_2500basex_an(mpcs, mpcs->interface, false);
+}
+
+static void mv88e6393x_sgmii_pcs_pre_config(struct phylink_pcs *pcs,
+					    phy_interface_t interface)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+
+	mv88e639x_sgmii_pcs_pre_config(pcs, interface);
+	mv88e6393x_power_lane(mpcs, false);
+	mv88e6393x_sgmii_apply_2500basex_an(mpcs, mpcs->interface, false);
+}
+
+static int mv88e6393x_sgmii_pcs_post_config(struct phylink_pcs *pcs,
+					    phy_interface_t interface)
+{
+	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+	int err;
+
+	err = mv88e6393x_erratum_4_8(mpcs);
+	if (err)
+		return err;
+
+	err = mv88e6393x_sgmii_apply_2500basex_an(mpcs, interface, true);
+	if (err)
+		return err;
+
+	err = mv88e6393x_power_lane(mpcs, true);
+	if (err)
+		return err;
+
+	return mv88e639x_sgmii_pcs_post_config(pcs, interface);
+}
+
+static const struct phylink_pcs_ops mv88e6393x_sgmii_pcs_ops = {
+	.pcs_enable = mv88e639x_sgmii_pcs_enable,
+	.pcs_disable = mv88e6393x_sgmii_pcs_disable,
+	.pcs_pre_config = mv88e6393x_sgmii_pcs_pre_config,
+	.pcs_post_config = mv88e6393x_sgmii_pcs_post_config,
+	.pcs_get_state = mv88e639x_sgmii_pcs_get_state,
+	.pcs_an_restart = mv88e639x_sgmii_pcs_an_restart,
+	.pcs_config = mv88e639x_sgmii_pcs_config,
+	.pcs_link_up = mv88e639x_sgmii_pcs_link_up,
+};
+
+static irqreturn_t mv88e6393x_xg_handle_irq(struct mv88e639x_pcs *mpcs)
+{
+	u16 int_status, stat1;
+	bool link_down;
+	int err;
+
+	err = mv88e639x_read(mpcs, MV88E6393X_10G_INT_STATUS, &int_status);
+	if (err)
+		return IRQ_NONE;
+
+	if (int_status & MV88E6393X_10G_INT_LINK_CHANGE) {
+		err = mv88e639x_read(mpcs, MV88E6390_10G_STAT1, &stat1);
+		if (err)
+			return IRQ_NONE;
+
+		link_down = !(stat1 & MDIO_STAT1_LSTATUS);
+
+		phylink_pcs_change(&mpcs->xg_pcs, !link_down);
+
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static int mv88e6393x_xg_control_irq(struct mv88e639x_pcs *mpcs, bool enable)
+{
+	u16 val = 0;
+
+	if (enable)
+		val = MV88E6393X_10G_INT_LINK_CHANGE;
+
+	return mv88e639x_modify(mpcs, MV88E6393X_10G_INT_ENABLE,
+				MV88E6393X_10G_INT_LINK_CHANGE, val);
+}
+
+static int mv88e6393x_xg_pcs_enable(struct phylink_pcs *pcs)
+{
+	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
+
+	mpcs->handle_irq = mv88e6393x_xg_handle_irq;
+
+	return mv88e6393x_xg_control_irq(mpcs, !!mpcs->irq);
+}
+
+static void mv88e6393x_xg_pcs_disable(struct phylink_pcs *pcs)
+{
+	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
+
+	mv88e6393x_xg_control_irq(mpcs, false);
+	mv88e639x_xg_pcs_disable(mpcs);
+	mv88e6393x_power_lane(mpcs, false);
+}
+
+/* The PCS has to be powered down while CMODE is changed */
+static void mv88e6393x_xg_pcs_pre_config(struct phylink_pcs *pcs,
+					 phy_interface_t interface)
+{
+	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
+
+	mv88e639x_xg_pcs_disable(mpcs);
+	mv88e6393x_power_lane(mpcs, false);
+}
+
+static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs,
+					 phy_interface_t interface)
+{
+	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
+	int err;
+
+	if (interface == PHY_INTERFACE_MODE_10GBASER) {
+		err = mv88e6393x_erratum_5_2(mpcs);
+		if (err)
+			return err;
+	}
+
+	err = mv88e6393x_power_lane(mpcs, true);
+	if (err)
+		return err;
+
+	return mv88e639x_xg_pcs_enable(mpcs);
+}
+
+static const struct phylink_pcs_ops mv88e6393x_xg_pcs_ops = {
+	.pcs_enable = mv88e6393x_xg_pcs_enable,
+	.pcs_disable = mv88e6393x_xg_pcs_disable,
+	.pcs_pre_config = mv88e6393x_xg_pcs_pre_config,
+	.pcs_post_config = mv88e6393x_xg_pcs_post_config,
+	.pcs_get_state = mv88e639x_xg_pcs_get_state,
+	.pcs_config = mv88e639x_xg_pcs_config,
+};
+
+static int mv88e6393x_pcs_init(struct mv88e6xxx_chip *chip, int port)
+{
+	struct mv88e639x_pcs *mpcs;
+	struct mii_bus *bus;
+	struct device *dev;
+	int lane, err;
+
+	lane = mv88e6xxx_serdes_get_lane(chip, port);
+	if (lane < 0)
+		return 0;
+
+	bus = mv88e6xxx_default_mdio_bus(chip);
+	dev = chip->dev;
+
+	mpcs = mv88e639x_pcs_alloc(dev, bus, lane, port);
+	if (!mpcs)
+		return -ENOMEM;
+
+	mpcs->sgmii_pcs.ops = &mv88e6393x_sgmii_pcs_ops;
+	mpcs->sgmii_pcs.neg_mode = true;
+	mpcs->xg_pcs.ops = &mv88e6393x_xg_pcs_ops;
+	mpcs->xg_pcs.neg_mode = true;
+	mpcs->supports_5g = true;
+
+	err = mv88e6393x_erratum_4_6(mpcs);
+	if (err)
+		goto err_free;
+
+	err = mv88e639x_pcs_setup_irq(mpcs, chip, port);
+	if (err)
+		goto err_free;
+
+	chip->ports[port].pcs_private = mpcs;
+
+	return 0;
+
+err_free:
+	kfree(mpcs);
+	return err;
+}
+
+const struct mv88e6xxx_pcs_ops mv88e6393x_pcs_ops = {
+	.pcs_init = mv88e6393x_pcs_init,
+	.pcs_teardown = mv88e639x_pcs_teardown,
+	.pcs_select = mv88e639x_pcs_select,
+};
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 5eea0cba3ee0b..3b4b42651fa3d 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -375,57 +375,6 @@ int mv88e6393x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
 	return lane;
 }
 
-/* Set power up/down for 10GBASE-R and 10GBASE-X4/X2 */
-static int mv88e6390_serdes_power_10g(struct mv88e6xxx_chip *chip, int lane,
-				      bool up)
-{
-	u16 val, new_val;
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_10G_CTRL1, &val);
-
-	if (err)
-		return err;
-
-	if (up)
-		new_val = val & ~(MDIO_CTRL1_RESET |
-				  MDIO_PCS_CTRL1_LOOPBACK |
-				  MDIO_CTRL1_LPOWER);
-	else
-		new_val = val | MDIO_CTRL1_LPOWER;
-
-	if (val != new_val)
-		err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-					     MV88E6390_10G_CTRL1, new_val);
-
-	return err;
-}
-
-/* Set power up/down for SGMII and 1000Base-X */
-static int mv88e6390_serdes_power_sgmii(struct mv88e6xxx_chip *chip, int lane,
-					bool up)
-{
-	u16 val, new_val;
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_SGMII_BMCR, &val);
-	if (err)
-		return err;
-
-	if (up)
-		new_val = val & ~(BMCR_RESET | BMCR_LOOPBACK | BMCR_PDOWN);
-	else
-		new_val = val | BMCR_PDOWN;
-
-	if (val != new_val)
-		err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-					     MV88E6390_SGMII_BMCR, new_val);
-
-	return err;
-}
-
 struct mv88e6390_serdes_hw_stat {
 	char string[ETH_GSTRING_LEN];
 	int reg;
@@ -499,484 +448,6 @@ int mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
 	return ARRAY_SIZE(mv88e6390_serdes_hw_stats);
 }
 
-static int mv88e6390_serdes_enable_checker(struct mv88e6xxx_chip *chip, int lane)
-{
-	u16 reg;
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_PG_CONTROL, &reg);
-	if (err)
-		return err;
-
-	reg |= MV88E6390_PG_CONTROL_ENABLE_PC;
-	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-				      MV88E6390_PG_CONTROL, reg);
-}
-
-int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
-			   bool up)
-{
-	u8 cmode = chip->ports[port].cmode;
-	int err;
-
-	switch (cmode) {
-	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-	case MV88E6XXX_PORT_STS_CMODE_1000BASEX:
-	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		err = mv88e6390_serdes_power_sgmii(chip, lane, up);
-		break;
-	case MV88E6XXX_PORT_STS_CMODE_XAUI:
-	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
-		err = mv88e6390_serdes_power_10g(chip, lane, up);
-		break;
-	default:
-		err = -EINVAL;
-		break;
-	}
-
-	if (!err && up)
-		err = mv88e6390_serdes_enable_checker(chip, lane);
-
-	return err;
-}
-
-int mv88e6390_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
-				int lane, unsigned int mode,
-				phy_interface_t interface,
-				const unsigned long *advertise)
-{
-	u16 val, bmcr, adv;
-	bool changed;
-	int err;
-
-	switch (interface) {
-	case PHY_INTERFACE_MODE_SGMII:
-		adv = 0x0001;
-		break;
-
-	case PHY_INTERFACE_MODE_1000BASEX:
-		adv = linkmode_adv_to_mii_adv_x(advertise,
-					ETHTOOL_LINK_MODE_1000baseX_Full_BIT);
-		break;
-
-	case PHY_INTERFACE_MODE_2500BASEX:
-		adv = linkmode_adv_to_mii_adv_x(advertise,
-					ETHTOOL_LINK_MODE_2500baseX_Full_BIT);
-		break;
-
-	default:
-		return 0;
-	}
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_SGMII_ADVERTISE, &val);
-	if (err)
-		return err;
-
-	changed = val != adv;
-	if (changed) {
-		err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-					     MV88E6390_SGMII_ADVERTISE, adv);
-		if (err)
-			return err;
-	}
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_SGMII_BMCR, &val);
-	if (err)
-		return err;
-
-	if (phylink_autoneg_inband(mode))
-		bmcr = val | BMCR_ANENABLE;
-	else
-		bmcr = val & ~BMCR_ANENABLE;
-
-	/* setting ANENABLE triggers a restart of negotiation */
-	if (bmcr == val)
-		return changed;
-
-	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-				      MV88E6390_SGMII_BMCR, bmcr);
-}
-
-static int mv88e6390_serdes_pcs_get_state_sgmii(struct mv88e6xxx_chip *chip,
-	int port, int lane, struct phylink_link_state *state)
-{
-	u16 bmsr, lpa, status;
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_SGMII_BMSR, &bmsr);
-	if (err) {
-		dev_err(chip->dev, "can't read Serdes PHY BMSR: %d\n", err);
-		return err;
-	}
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_SGMII_PHY_STATUS, &status);
-	if (err) {
-		dev_err(chip->dev, "can't read Serdes PHY status: %d\n", err);
-		return err;
-	}
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_SGMII_LPA, &lpa);
-	if (err) {
-		dev_err(chip->dev, "can't read Serdes PHY LPA: %d\n", err);
-		return err;
-	}
-
-	return mv88e6xxx_pcs_decode_state(chip->dev, bmsr, lpa, status, state);
-}
-
-static int mv88e6390_serdes_pcs_get_state_10g(struct mv88e6xxx_chip *chip,
-	int port, int lane, struct phylink_link_state *state)
-{
-	u16 status;
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_10G_STAT1, &status);
-	if (err)
-		return err;
-
-	state->link = !!(status & MDIO_STAT1_LSTATUS);
-	if (state->link) {
-		state->speed = SPEED_10000;
-		state->duplex = DUPLEX_FULL;
-	}
-
-	return 0;
-}
-
-static int mv88e6393x_serdes_pcs_get_state_10g(struct mv88e6xxx_chip *chip,
-					       int port, int lane,
-					       struct phylink_link_state *state)
-{
-	u16 status;
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_10G_STAT1, &status);
-	if (err)
-		return err;
-
-	state->link = !!(status & MDIO_STAT1_LSTATUS);
-	if (state->link) {
-		if (state->interface == PHY_INTERFACE_MODE_5GBASER)
-			state->speed = SPEED_5000;
-		else
-			state->speed = SPEED_10000;
-		state->duplex = DUPLEX_FULL;
-	}
-	return 0;
-}
-
-/* USXGMII registers for Marvell switch 88e639x are undocumented and this function is based
- * on some educated guesses. It appears that there are no status bits related to
- * autonegotiation complete or flow control.
- */
-static int mv88e639x_serdes_pcs_get_state_usxgmii(struct mv88e6xxx_chip *chip,
-						  int port, int lane,
-						  struct phylink_link_state *state)
-{
-	u16 status, lp_status;
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_USXGMII_PHY_STATUS, &status);
-	if (err) {
-		dev_err(chip->dev, "can't read Serdes USXGMII PHY status: %d\n", err);
-		return err;
-	}
-	dev_dbg(chip->dev, "USXGMII PHY status: 0x%x\n", status);
-
-	state->link = !!(status & MDIO_USXGMII_LINK);
-	state->an_complete = state->link;
-
-	if (state->link) {
-		err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-					    MV88E6390_USXGMII_LP_STATUS, &lp_status);
-		if (err) {
-			dev_err(chip->dev, "can't read Serdes USXGMII LP status: %d\n", err);
-			return err;
-		}
-		dev_dbg(chip->dev, "USXGMII LP status: 0x%x\n", lp_status);
-		/* lp_status appears to include the "link" bit as per USXGMII spec. */
-		phylink_decode_usxgmii_word(state, lp_status);
-	}
-	return 0;
-}
-
-int mv88e6390_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
-				   int lane, struct phylink_link_state *state)
-{
-	switch (state->interface) {
-	case PHY_INTERFACE_MODE_SGMII:
-	case PHY_INTERFACE_MODE_1000BASEX:
-	case PHY_INTERFACE_MODE_2500BASEX:
-		return mv88e6390_serdes_pcs_get_state_sgmii(chip, port, lane,
-							    state);
-	case PHY_INTERFACE_MODE_XAUI:
-	case PHY_INTERFACE_MODE_RXAUI:
-		return mv88e6390_serdes_pcs_get_state_10g(chip, port, lane,
-							  state);
-
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-int mv88e6393x_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
-				    int lane, struct phylink_link_state *state)
-{
-	switch (state->interface) {
-	case PHY_INTERFACE_MODE_SGMII:
-	case PHY_INTERFACE_MODE_1000BASEX:
-	case PHY_INTERFACE_MODE_2500BASEX:
-		return mv88e6390_serdes_pcs_get_state_sgmii(chip, port, lane,
-							    state);
-	case PHY_INTERFACE_MODE_5GBASER:
-	case PHY_INTERFACE_MODE_10GBASER:
-		return mv88e6393x_serdes_pcs_get_state_10g(chip, port, lane,
-							   state);
-	case PHY_INTERFACE_MODE_USXGMII:
-		return mv88e639x_serdes_pcs_get_state_usxgmii(chip, port, lane,
-							   state);
-
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-int mv88e6390_serdes_pcs_an_restart(struct mv88e6xxx_chip *chip, int port,
-				    int lane)
-{
-	u16 bmcr;
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_SGMII_BMCR, &bmcr);
-	if (err)
-		return err;
-
-	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-				      MV88E6390_SGMII_BMCR,
-				      bmcr | BMCR_ANRESTART);
-}
-
-int mv88e6390_serdes_pcs_link_up(struct mv88e6xxx_chip *chip, int port,
-				 int lane, int speed, int duplex)
-{
-	u16 val, bmcr;
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_SGMII_BMCR, &val);
-	if (err)
-		return err;
-
-	bmcr = val & ~(BMCR_SPEED100 | BMCR_FULLDPLX | BMCR_SPEED1000);
-	switch (speed) {
-	case SPEED_2500:
-	case SPEED_1000:
-		bmcr |= BMCR_SPEED1000;
-		break;
-	case SPEED_100:
-		bmcr |= BMCR_SPEED100;
-		break;
-	case SPEED_10:
-		break;
-	}
-
-	if (duplex == DUPLEX_FULL)
-		bmcr |= BMCR_FULLDPLX;
-
-	if (bmcr == val)
-		return 0;
-
-	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-				      MV88E6390_SGMII_BMCR, bmcr);
-}
-
-static void mv88e6390_serdes_irq_link_sgmii(struct mv88e6xxx_chip *chip,
-					    int port, int lane)
-{
-	u16 bmsr;
-	int err;
-
-	/* If the link has dropped, we want to know about it. */
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_SGMII_BMSR, &bmsr);
-	if (err) {
-		dev_err(chip->dev, "can't read Serdes BMSR: %d\n", err);
-		return;
-	}
-
-	dsa_port_phylink_mac_change(chip->ds, port, !!(bmsr & BMSR_LSTATUS));
-}
-
-static void mv88e6393x_serdes_irq_link_10g(struct mv88e6xxx_chip *chip,
-					   int port, u8 lane)
-{
-	u16 status;
-	int err;
-
-	/* If the link has dropped, we want to know about it. */
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_10G_STAT1, &status);
-	if (err) {
-		dev_err(chip->dev, "can't read Serdes STAT1: %d\n", err);
-		return;
-	}
-
-	dsa_port_phylink_mac_change(chip->ds, port, !!(status & MDIO_STAT1_LSTATUS));
-}
-
-static int mv88e6390_serdes_irq_enable_sgmii(struct mv88e6xxx_chip *chip,
-					     int lane, bool enable)
-{
-	u16 val = 0;
-
-	if (enable)
-		val |= MV88E6390_SGMII_INT_LINK_DOWN |
-			MV88E6390_SGMII_INT_LINK_UP;
-
-	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-				      MV88E6390_SGMII_INT_ENABLE, val);
-}
-
-int mv88e6390_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, int lane,
-				bool enable)
-{
-	u8 cmode = chip->ports[port].cmode;
-
-	switch (cmode) {
-	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-	case MV88E6XXX_PORT_STS_CMODE_1000BASEX:
-	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		return mv88e6390_serdes_irq_enable_sgmii(chip, lane, enable);
-	}
-
-	return 0;
-}
-
-static int mv88e6390_serdes_irq_status_sgmii(struct mv88e6xxx_chip *chip,
-					     int lane, u16 *status)
-{
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6390_SGMII_INT_STATUS, status);
-
-	return err;
-}
-
-static int mv88e6393x_serdes_irq_enable_10g(struct mv88e6xxx_chip *chip,
-					    u8 lane, bool enable)
-{
-	u16 val = 0;
-
-	if (enable)
-		val |= MV88E6393X_10G_INT_LINK_CHANGE;
-
-	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-				      MV88E6393X_10G_INT_ENABLE, val);
-}
-
-int mv88e6393x_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port,
-				 int lane, bool enable)
-{
-	u8 cmode = chip->ports[port].cmode;
-
-	switch (cmode) {
-	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-	case MV88E6XXX_PORT_STS_CMODE_1000BASEX:
-	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		return mv88e6390_serdes_irq_enable_sgmii(chip, lane, enable);
-	case MV88E6393X_PORT_STS_CMODE_5GBASER:
-	case MV88E6393X_PORT_STS_CMODE_10GBASER:
-	case MV88E6393X_PORT_STS_CMODE_USXGMII:
-		return mv88e6393x_serdes_irq_enable_10g(chip, lane, enable);
-	}
-
-	return 0;
-}
-
-static int mv88e6393x_serdes_irq_status_10g(struct mv88e6xxx_chip *chip,
-					    u8 lane, u16 *status)
-{
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6393X_10G_INT_STATUS, status);
-
-	return err;
-}
-
-irqreturn_t mv88e6393x_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
-					 int lane)
-{
-	u8 cmode = chip->ports[port].cmode;
-	irqreturn_t ret = IRQ_NONE;
-	u16 status;
-	int err;
-
-	switch (cmode) {
-	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-	case MV88E6XXX_PORT_STS_CMODE_1000BASEX:
-	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		err = mv88e6390_serdes_irq_status_sgmii(chip, lane, &status);
-		if (err)
-			return ret;
-		if (status & (MV88E6390_SGMII_INT_LINK_DOWN |
-			      MV88E6390_SGMII_INT_LINK_UP)) {
-			ret = IRQ_HANDLED;
-			mv88e6390_serdes_irq_link_sgmii(chip, port, lane);
-		}
-		break;
-	case MV88E6393X_PORT_STS_CMODE_5GBASER:
-	case MV88E6393X_PORT_STS_CMODE_10GBASER:
-	case MV88E6393X_PORT_STS_CMODE_USXGMII:
-		err = mv88e6393x_serdes_irq_status_10g(chip, lane, &status);
-		if (err)
-			return err;
-		if (status & MV88E6393X_10G_INT_LINK_CHANGE) {
-			ret = IRQ_HANDLED;
-			mv88e6393x_serdes_irq_link_10g(chip, port, lane);
-		}
-		break;
-	}
-
-	return ret;
-}
-
-irqreturn_t mv88e6390_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
-					int lane)
-{
-	u8 cmode = chip->ports[port].cmode;
-	irqreturn_t ret = IRQ_NONE;
-	u16 status;
-	int err;
-
-	switch (cmode) {
-	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-	case MV88E6XXX_PORT_STS_CMODE_1000BASEX:
-	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		err = mv88e6390_serdes_irq_status_sgmii(chip, lane, &status);
-		if (err)
-			return ret;
-		if (status & (MV88E6390_SGMII_INT_LINK_DOWN |
-			      MV88E6390_SGMII_INT_LINK_UP)) {
-			ret = IRQ_HANDLED;
-			mv88e6390_serdes_irq_link_sgmii(chip, port, lane);
-		}
-	}
-
-	return ret;
-}
-
 unsigned int mv88e6390_serdes_irq_mapping(struct mv88e6xxx_chip *chip, int port)
 {
 	return irq_find_mapping(chip->g2_irq.domain, port);
@@ -1075,259 +546,3 @@ int mv88e6352_serdes_set_tx_amplitude(struct mv88e6xxx_chip *chip, int port,
 
 	return mv88e6352_serdes_write(chip, MV88E6352_SERDES_SPEC_CTRL2, ctrl);
 }
-
-static int mv88e6393x_serdes_power_lane(struct mv88e6xxx_chip *chip, int lane,
-					bool on)
-{
-	u16 reg;
-	int err;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6393X_SERDES_CTRL1, &reg);
-	if (err)
-		return err;
-
-	if (on)
-		reg &= ~(MV88E6393X_SERDES_CTRL1_TX_PDOWN |
-			 MV88E6393X_SERDES_CTRL1_RX_PDOWN);
-	else
-		reg |= MV88E6393X_SERDES_CTRL1_TX_PDOWN |
-		       MV88E6393X_SERDES_CTRL1_RX_PDOWN;
-
-	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-				      MV88E6393X_SERDES_CTRL1, reg);
-}
-
-static int mv88e6393x_serdes_erratum_4_6(struct mv88e6xxx_chip *chip, int lane)
-{
-	u16 reg;
-	int err;
-
-	/* mv88e6393x family errata 4.6:
-	 * Cannot clear PwrDn bit on SERDES if device is configured CPU_MGD
-	 * mode or P0_mode is configured for [x]MII.
-	 * Workaround: Set SERDES register 4.F002 bit 5=0 and bit 15=1.
-	 *
-	 * It seems that after this workaround the SERDES is automatically
-	 * powered up (the bit is cleared), so power it down.
-	 */
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6393X_SERDES_POC, &reg);
-	if (err)
-		return err;
-
-	reg &= ~MV88E6393X_SERDES_POC_PDOWN;
-	reg |= MV88E6393X_SERDES_POC_RESET;
-
-	err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-				     MV88E6393X_SERDES_POC, reg);
-	if (err)
-		return err;
-
-	err = mv88e6390_serdes_power_sgmii(chip, lane, false);
-	if (err)
-		return err;
-
-	return mv88e6393x_serdes_power_lane(chip, lane, false);
-}
-
-int mv88e6393x_serdes_setup_errata(struct mv88e6xxx_chip *chip)
-{
-	int err;
-
-	err = mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT0_LANE);
-	if (err)
-		return err;
-
-	err = mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT9_LANE);
-	if (err)
-		return err;
-
-	return mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT10_LANE);
-}
-
-static int mv88e6393x_serdes_erratum_4_8(struct mv88e6xxx_chip *chip, int lane)
-{
-	u16 reg, pcs;
-	int err;
-
-	/* mv88e6393x family errata 4.8:
-	 * When a SERDES port is operating in 1000BASE-X or SGMII mode link may
-	 * not come up after hardware reset or software reset of SERDES core.
-	 * Workaround is to write SERDES register 4.F074.14=1 for only those
-	 * modes and 0 in all other modes.
-	 */
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6393X_SERDES_POC, &pcs);
-	if (err)
-		return err;
-
-	pcs &= MV88E6393X_SERDES_POC_PCS_MASK;
-
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6393X_ERRATA_4_8_REG, &reg);
-	if (err)
-		return err;
-
-	if (pcs == MV88E6393X_SERDES_POC_PCS_1000BASEX ||
-	    pcs == MV88E6393X_SERDES_POC_PCS_SGMII_PHY ||
-	    pcs == MV88E6393X_SERDES_POC_PCS_SGMII_MAC)
-		reg |= MV88E6393X_ERRATA_4_8_BIT;
-	else
-		reg &= ~MV88E6393X_ERRATA_4_8_BIT;
-
-	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-				      MV88E6393X_ERRATA_4_8_REG, reg);
-}
-
-static int mv88e6393x_serdes_erratum_5_2(struct mv88e6xxx_chip *chip, int lane,
-					 u8 cmode)
-{
-	static const struct {
-		u16 dev, reg, val, mask;
-	} fixes[] = {
-		{ MDIO_MMD_VEND1, 0x8093, 0xcb5a, 0xffff },
-		{ MDIO_MMD_VEND1, 0x8171, 0x7088, 0xffff },
-		{ MDIO_MMD_VEND1, 0x80c9, 0x311a, 0xffff },
-		{ MDIO_MMD_VEND1, 0x80a2, 0x8000, 0xff7f },
-		{ MDIO_MMD_VEND1, 0x80a9, 0x0000, 0xfff0 },
-		{ MDIO_MMD_VEND1, 0x80a3, 0x0000, 0xf8ff },
-		{ MDIO_MMD_PHYXS, MV88E6393X_SERDES_POC,
-		  MV88E6393X_SERDES_POC_RESET, MV88E6393X_SERDES_POC_RESET },
-	};
-	int err, i;
-	u16 reg;
-
-	/* mv88e6393x family errata 5.2:
-	 * For optimal signal integrity the following sequence should be applied
-	 * to SERDES operating in 10G mode. These registers only apply to 10G
-	 * operation and have no effect on other speeds.
-	 */
-	if (cmode != MV88E6393X_PORT_STS_CMODE_10GBASER &&
-	    cmode != MV88E6393X_PORT_STS_CMODE_USXGMII)
-		return 0;
-
-	for (i = 0; i < ARRAY_SIZE(fixes); ++i) {
-		err = mv88e6390_serdes_read(chip, lane, fixes[i].dev,
-					    fixes[i].reg, &reg);
-		if (err)
-			return err;
-
-		reg &= ~fixes[i].mask;
-		reg |= fixes[i].val;
-
-		err = mv88e6390_serdes_write(chip, lane, fixes[i].dev,
-					     fixes[i].reg, reg);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int mv88e6393x_serdes_fix_2500basex_an(struct mv88e6xxx_chip *chip,
-					      int lane, u8 cmode, bool on)
-{
-	u16 reg;
-	int err;
-
-	if (cmode != MV88E6XXX_PORT_STS_CMODE_2500BASEX)
-		return 0;
-
-	/* Inband AN is broken on Amethyst in 2500base-x mode when set by
-	 * standard mechanism (via cmode).
-	 * We can get around this by configuring the PCS mode to 1000base-x
-	 * and then writing value 0x58 to register 1e.8000. (This must be done
-	 * while SerDes receiver and transmitter are disabled, which is, when
-	 * this function is called.)
-	 * It seem that when we do this configuration to 2500base-x mode (by
-	 * changing PCS mode to 1000base-x and frequency to 3.125 GHz from
-	 * 1.25 GHz) and then configure to sgmii or 1000base-x, the device
-	 * thinks that it already has SerDes at 1.25 GHz and does not change
-	 * the 1e.8000 register, leaving SerDes at 3.125 GHz.
-	 * To avoid this, change PCS mode back to 2500base-x when disabling
-	 * SerDes from 2500base-x mode.
-	 */
-	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
-				    MV88E6393X_SERDES_POC, &reg);
-	if (err)
-		return err;
-
-	reg &= ~(MV88E6393X_SERDES_POC_PCS_MASK | MV88E6393X_SERDES_POC_AN);
-	if (on)
-		reg |= MV88E6393X_SERDES_POC_PCS_1000BASEX |
-		       MV88E6393X_SERDES_POC_AN;
-	else
-		reg |= MV88E6393X_SERDES_POC_PCS_2500BASEX;
-	reg |= MV88E6393X_SERDES_POC_RESET;
-
-	err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-				     MV88E6393X_SERDES_POC, reg);
-	if (err)
-		return err;
-
-	err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_VEND1, 0x8000, 0x58);
-	if (err)
-		return err;
-
-	return 0;
-}
-
-int mv88e6393x_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
-			    bool on)
-{
-	u8 cmode = chip->ports[port].cmode;
-	int err;
-
-	if (port != 0 && port != 9 && port != 10)
-		return -EOPNOTSUPP;
-
-	if (on) {
-		err = mv88e6393x_serdes_erratum_4_8(chip, lane);
-		if (err)
-			return err;
-
-		err = mv88e6393x_serdes_erratum_5_2(chip, lane, cmode);
-		if (err)
-			return err;
-
-		err = mv88e6393x_serdes_fix_2500basex_an(chip, lane, cmode,
-							 true);
-		if (err)
-			return err;
-
-		err = mv88e6393x_serdes_power_lane(chip, lane, true);
-		if (err)
-			return err;
-	}
-
-	switch (cmode) {
-	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-	case MV88E6XXX_PORT_STS_CMODE_1000BASEX:
-	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		err = mv88e6390_serdes_power_sgmii(chip, lane, on);
-		break;
-	case MV88E6393X_PORT_STS_CMODE_5GBASER:
-	case MV88E6393X_PORT_STS_CMODE_10GBASER:
-	case MV88E6393X_PORT_STS_CMODE_USXGMII:
-		err = mv88e6390_serdes_power_10g(chip, lane, on);
-		break;
-	default:
-		err = -EINVAL;
-		break;
-	}
-
-	if (err)
-		return err;
-
-	if (!on) {
-		err = mv88e6393x_serdes_power_lane(chip, lane, false);
-		if (err)
-			return err;
-
-		err = mv88e6393x_serdes_fix_2500basex_an(chip, lane, cmode,
-							 false);
-	}
-
-	return err;
-}
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index 73cf2d0b8bb3c..67584cb1fdb95 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -46,6 +46,10 @@ struct phylink_link_state;
 /* 10GBASE-R and 10GBASE-X4/X2 */
 #define MV88E6390_10G_CTRL1		(0x1000 + MDIO_CTRL1)
 #define MV88E6390_10G_STAT1		(0x1000 + MDIO_STAT1)
+#define MV88E6390_10G_INT_ENABLE	0x9001
+#define MV88E6390_10G_INT_LINK_DOWN	BIT(3)
+#define MV88E6390_10G_INT_LINK_UP	BIT(2)
+#define MV88E6390_10G_INT_STATUS	0x9003
 #define MV88E6393X_10G_INT_ENABLE	0x9000
 #define MV88E6393X_10G_INT_LINK_CHANGE	BIT(2)
 #define MV88E6393X_10G_INT_STATUS	0x9001
@@ -116,35 +120,10 @@ int mv88e6341_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6393x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
-int mv88e6390_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
-				int lane, unsigned int mode,
-				phy_interface_t interface,
-				const unsigned long *advertise);
-int mv88e6390_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
-				   int lane, struct phylink_link_state *state);
-int mv88e6393x_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
-				    int lane, struct phylink_link_state *state);
-int mv88e6390_serdes_pcs_an_restart(struct mv88e6xxx_chip *chip, int port,
-				    int lane);
-int mv88e6390_serdes_pcs_link_up(struct mv88e6xxx_chip *chip, int port,
-				 int lane, int speed, int duplex);
 unsigned int mv88e6352_serdes_irq_mapping(struct mv88e6xxx_chip *chip,
 					  int port);
 unsigned int mv88e6390_serdes_irq_mapping(struct mv88e6xxx_chip *chip,
 					  int port);
-int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
-			   bool on);
-int mv88e6393x_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
-			    bool on);
-int mv88e6393x_serdes_setup_errata(struct mv88e6xxx_chip *chip);
-int mv88e6390_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, int lane,
-				bool enable);
-int mv88e6393x_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port,
-				 int lane, bool enable);
-irqreturn_t mv88e6390_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
-					int lane);
-irqreturn_t mv88e6393x_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
-					 int lane);
 int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip,
 				 int port, uint8_t *data);
@@ -230,5 +209,7 @@ mv88e6xxx_serdes_irq_status(struct mv88e6xxx_chip *chip, int port, int lane)
 
 extern const struct mv88e6xxx_pcs_ops mv88e6185_pcs_ops;
 extern const struct mv88e6xxx_pcs_ops mv88e6352_pcs_ops;
+extern const struct mv88e6xxx_pcs_ops mv88e6390_pcs_ops;
+extern const struct mv88e6xxx_pcs_ops mv88e6393x_pcs_ops;
 
 #endif
-- 
GitLab


From d20acfdd3f88fc2a68897c202310194654988276 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Jul 2023 09:42:59 +0100
Subject: [PATCH 0129/1806] net: dsa: mv88e6xxx: cleanup after phylink_pcs
 conversion

Now that mv88e6xxx is completely converted to using phylink_pcs
support, we have no need for the serdes methods. Remove all this
infrastructure. Also remove the __maybe_unused from
mv88e6xxx_pcs_select().

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c   | 238 +----------------------------
 drivers/net/dsa/mv88e6xxx/chip.h   |  21 ---
 drivers/net/dsa/mv88e6xxx/port.c   |  30 ----
 drivers/net/dsa/mv88e6xxx/serdes.h |  45 ------
 4 files changed, 2 insertions(+), 332 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index a1ca827157141..6174855188d90 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -492,81 +492,6 @@ static int mv88e6xxx_port_ppu_updates(struct mv88e6xxx_chip *chip, int port)
 	return !!(reg & MV88E6XXX_PORT_STS_PHY_DETECT);
 }
 
-static int mv88e6xxx_serdes_pcs_get_state(struct dsa_switch *ds, int port,
-					  struct phylink_link_state *state)
-{
-	struct mv88e6xxx_chip *chip = ds->priv;
-	int lane;
-	int err;
-
-	mv88e6xxx_reg_lock(chip);
-	lane = mv88e6xxx_serdes_get_lane(chip, port);
-	if (lane >= 0 && chip->info->ops->serdes_pcs_get_state)
-		err = chip->info->ops->serdes_pcs_get_state(chip, port, lane,
-							    state);
-	else
-		err = -EOPNOTSUPP;
-	mv88e6xxx_reg_unlock(chip);
-
-	return err;
-}
-
-static int mv88e6xxx_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
-				       unsigned int mode,
-				       phy_interface_t interface,
-				       const unsigned long *advertise)
-{
-	const struct mv88e6xxx_ops *ops = chip->info->ops;
-	int lane;
-
-	if (ops->serdes_pcs_config) {
-		lane = mv88e6xxx_serdes_get_lane(chip, port);
-		if (lane >= 0)
-			return ops->serdes_pcs_config(chip, port, lane, mode,
-						      interface, advertise);
-	}
-
-	return 0;
-}
-
-static void mv88e6xxx_serdes_pcs_an_restart(struct dsa_switch *ds, int port)
-{
-	struct mv88e6xxx_chip *chip = ds->priv;
-	const struct mv88e6xxx_ops *ops;
-	int err = 0;
-	int lane;
-
-	ops = chip->info->ops;
-
-	if (ops->serdes_pcs_an_restart) {
-		mv88e6xxx_reg_lock(chip);
-		lane = mv88e6xxx_serdes_get_lane(chip, port);
-		if (lane >= 0)
-			err = ops->serdes_pcs_an_restart(chip, port, lane);
-		mv88e6xxx_reg_unlock(chip);
-
-		if (err)
-			dev_err(ds->dev, "p%d: failed to restart AN\n", port);
-	}
-}
-
-static int mv88e6xxx_serdes_pcs_link_up(struct mv88e6xxx_chip *chip, int port,
-					unsigned int mode,
-					int speed, int duplex)
-{
-	const struct mv88e6xxx_ops *ops = chip->info->ops;
-	int lane;
-
-	if (!phylink_autoneg_inband(mode) && ops->serdes_pcs_link_up) {
-		lane = mv88e6xxx_serdes_get_lane(chip, port);
-		if (lane >= 0)
-			return ops->serdes_pcs_link_up(chip, port, lane,
-						       speed, duplex);
-	}
-
-	return 0;
-}
-
 static const u8 mv88e6185_phy_interface_modes[] = {
 	[MV88E6185_PORT_STS_CMODE_GMII_FD]	 = PHY_INTERFACE_MODE_GMII,
 	[MV88E6185_PORT_STS_CMODE_MII_100_FD_PS] = PHY_INTERFACE_MODE_MII,
@@ -845,15 +770,8 @@ static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port,
 			  config->supported_interfaces);
 	}
 
-	/* If we have a .pcs_ops, or don't have a .serdes_pcs_get_state,
-	 * serdes_pcs_config, serdes_pcs_an_restart, or serdes_pcs_link_up,
-	 * we are not legacy.
-	 */
-	if (chip->info->ops->pcs_ops ||
-	    (!chip->info->ops->serdes_pcs_get_state &&
-	     !chip->info->ops->serdes_pcs_config &&
-	     !chip->info->ops->serdes_pcs_an_restart &&
-	     !chip->info->ops->serdes_pcs_link_up))
+	/* If we have a .pcs_init, we are not legacy. */
+	if (chip->info->ops->pcs_ops)
 		config->legacy_pre_march2020 = false;
 }
 
@@ -907,16 +825,6 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
 						      state->interface);
 		if (err && err != -EOPNOTSUPP)
 			goto err_unlock;
-
-		err = mv88e6xxx_serdes_pcs_config(chip, port, mode,
-						  state->interface,
-						  state->advertising);
-		/* FIXME: we should restart negotiation if something changed -
-		 * which is something we get if we convert to using phylinks
-		 * PCS operations.
-		 */
-		if (err > 0)
-			err = 0;
 	}
 
 err_unlock:
@@ -1000,17 +908,6 @@ static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port,
 	 */
 	if (!mv88e6xxx_port_ppu_updates(chip, port) ||
 	    mode == MLO_AN_FIXED) {
-		/* FIXME: for an automedia port, should we force the link
-		 * down here - what if the link comes up due to "other" media
-		 * while we're bringing the port up, how is the exclusivity
-		 * handled in the Marvell hardware? E.g. port 2 on 88E6390
-		 * shared between internal PHY and Serdes.
-		 */
-		err = mv88e6xxx_serdes_pcs_link_up(chip, port, mode, speed,
-						   duplex);
-		if (err)
-			goto error;
-
 		if (ops->port_set_speed_duplex) {
 			err = ops->port_set_speed_duplex(chip, port,
 							 speed, duplex);
@@ -3181,102 +3078,6 @@ static int mv88e6xxx_setup_egress_floods(struct mv88e6xxx_chip *chip, int port)
 	return 0;
 }
 
-static irqreturn_t mv88e6xxx_serdes_irq_thread_fn(int irq, void *dev_id)
-{
-	struct mv88e6xxx_port *mvp = dev_id;
-	struct mv88e6xxx_chip *chip = mvp->chip;
-	irqreturn_t ret = IRQ_NONE;
-	int port = mvp->port;
-	int lane;
-
-	mv88e6xxx_reg_lock(chip);
-	lane = mv88e6xxx_serdes_get_lane(chip, port);
-	if (lane >= 0)
-		ret = mv88e6xxx_serdes_irq_status(chip, port, lane);
-	mv88e6xxx_reg_unlock(chip);
-
-	return ret;
-}
-
-static int mv88e6xxx_serdes_irq_request(struct mv88e6xxx_chip *chip, int port,
-					int lane)
-{
-	struct mv88e6xxx_port *dev_id = &chip->ports[port];
-	unsigned int irq;
-	int err;
-
-	/* Nothing to request if this SERDES port has no IRQ */
-	irq = mv88e6xxx_serdes_irq_mapping(chip, port);
-	if (!irq)
-		return 0;
-
-	snprintf(dev_id->serdes_irq_name, sizeof(dev_id->serdes_irq_name),
-		 "mv88e6xxx-%s-serdes-%d", dev_name(chip->dev), port);
-
-	/* Requesting the IRQ will trigger IRQ callbacks, so release the lock */
-	mv88e6xxx_reg_unlock(chip);
-	err = request_threaded_irq(irq, NULL, mv88e6xxx_serdes_irq_thread_fn,
-				   IRQF_ONESHOT, dev_id->serdes_irq_name,
-				   dev_id);
-	mv88e6xxx_reg_lock(chip);
-	if (err)
-		return err;
-
-	dev_id->serdes_irq = irq;
-
-	return mv88e6xxx_serdes_irq_enable(chip, port, lane);
-}
-
-static int mv88e6xxx_serdes_irq_free(struct mv88e6xxx_chip *chip, int port,
-				     int lane)
-{
-	struct mv88e6xxx_port *dev_id = &chip->ports[port];
-	unsigned int irq = dev_id->serdes_irq;
-	int err;
-
-	/* Nothing to free if no IRQ has been requested */
-	if (!irq)
-		return 0;
-
-	err = mv88e6xxx_serdes_irq_disable(chip, port, lane);
-
-	/* Freeing the IRQ will trigger IRQ callbacks, so release the lock */
-	mv88e6xxx_reg_unlock(chip);
-	free_irq(irq, dev_id);
-	mv88e6xxx_reg_lock(chip);
-
-	dev_id->serdes_irq = 0;
-
-	return err;
-}
-
-static int mv88e6xxx_serdes_power(struct mv88e6xxx_chip *chip, int port,
-				  bool on)
-{
-	int lane;
-	int err;
-
-	lane = mv88e6xxx_serdes_get_lane(chip, port);
-	if (lane < 0)
-		return 0;
-
-	if (on) {
-		err = mv88e6xxx_serdes_power_up(chip, port, lane);
-		if (err)
-			return err;
-
-		err = mv88e6xxx_serdes_irq_request(chip, port, lane);
-	} else {
-		err = mv88e6xxx_serdes_irq_free(chip, port, lane);
-		if (err)
-			return err;
-
-		err = mv88e6xxx_serdes_power_down(chip, port, lane);
-	}
-
-	return err;
-}
-
 static int mv88e6xxx_set_egress_port(struct mv88e6xxx_chip *chip,
 				     enum mv88e6xxx_egress_direction direction,
 				     int port)
@@ -3601,37 +3402,6 @@ static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 	return ret;
 }
 
-static int mv88e6xxx_port_enable(struct dsa_switch *ds, int port,
-				 struct phy_device *phydev)
-{
-	struct mv88e6xxx_chip *chip = ds->priv;
-	int err;
-
-	/* Do not control power or request irqs if using PCS */
-	if (chip->info->ops->pcs_ops)
-		return 0;
-
-	mv88e6xxx_reg_lock(chip);
-	err = mv88e6xxx_serdes_power(chip, port, true);
-	mv88e6xxx_reg_unlock(chip);
-
-	return err;
-}
-
-static void mv88e6xxx_port_disable(struct dsa_switch *ds, int port)
-{
-	struct mv88e6xxx_chip *chip = ds->priv;
-
-	/* Do not control power or request irqs if using PCS */
-	if (chip->info->ops->pcs_ops)
-		return;
-
-	mv88e6xxx_reg_lock(chip);
-	if (mv88e6xxx_serdes_power(chip, port, false))
-		dev_err(chip->dev, "failed to power off SERDES\n");
-	mv88e6xxx_reg_unlock(chip);
-}
-
 static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds,
 				     unsigned int ageing_time)
 {
@@ -7013,18 +6783,14 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
 	.port_teardown		= mv88e6xxx_port_teardown,
 	.phylink_get_caps	= mv88e6xxx_get_caps,
 	.phylink_mac_select_pcs	= mv88e6xxx_mac_select_pcs,
-	.phylink_mac_link_state	= mv88e6xxx_serdes_pcs_get_state,
 	.phylink_mac_prepare	= mv88e6xxx_mac_prepare,
 	.phylink_mac_config	= mv88e6xxx_mac_config,
 	.phylink_mac_finish	= mv88e6xxx_mac_finish,
-	.phylink_mac_an_restart	= mv88e6xxx_serdes_pcs_an_restart,
 	.phylink_mac_link_down	= mv88e6xxx_mac_link_down,
 	.phylink_mac_link_up	= mv88e6xxx_mac_link_up,
 	.get_strings		= mv88e6xxx_get_strings,
 	.get_ethtool_stats	= mv88e6xxx_get_ethtool_stats,
 	.get_sset_count		= mv88e6xxx_get_sset_count,
-	.port_enable		= mv88e6xxx_port_enable,
-	.port_disable		= mv88e6xxx_port_disable,
 	.port_max_mtu		= mv88e6xxx_get_max_mtu,
 	.port_change_mtu	= mv88e6xxx_change_mtu,
 	.get_mac_eee		= mv88e6xxx_get_mac_eee,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 1dd310a3c41f3..44383a03ef2ff 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -286,8 +286,6 @@ struct mv88e6xxx_port {
 	u8 cmode;
 	bool mirror_ingress;
 	bool mirror_egress;
-	unsigned int serdes_irq;
-	char serdes_irq_name[64];
 	struct devlink_region *region;
 	void *pcs_private;
 
@@ -592,31 +590,12 @@ struct mv88e6xxx_ops {
 
 	int (*mgmt_rsvd2cpu)(struct mv88e6xxx_chip *chip);
 
-	/* Power on/off a SERDES interface */
-	int (*serdes_power)(struct mv88e6xxx_chip *chip, int port, int lane,
-			    bool up);
-
 	/* SERDES lane mapping */
 	int (*serdes_get_lane)(struct mv88e6xxx_chip *chip, int port);
 
-	int (*serdes_pcs_get_state)(struct mv88e6xxx_chip *chip, int port,
-				    int lane, struct phylink_link_state *state);
-	int (*serdes_pcs_config)(struct mv88e6xxx_chip *chip, int port,
-				 int lane, unsigned int mode,
-				 phy_interface_t interface,
-				 const unsigned long *advertise);
-	int (*serdes_pcs_an_restart)(struct mv88e6xxx_chip *chip, int port,
-				     int lane);
-	int (*serdes_pcs_link_up)(struct mv88e6xxx_chip *chip, int port,
-				  int lane, int speed, int duplex);
-
 	/* SERDES interrupt handling */
 	unsigned int (*serdes_irq_mapping)(struct mv88e6xxx_chip *chip,
 					   int port);
-	int (*serdes_irq_enable)(struct mv88e6xxx_chip *chip, int port, int lane,
-				 bool enable);
-	irqreturn_t (*serdes_irq_status)(struct mv88e6xxx_chip *chip, int port,
-					 int lane);
 
 	/* Statistics from the SERDES interface */
 	int (*serdes_get_sset_count)(struct mv88e6xxx_chip *chip, int port);
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index dd66ec902d4cb..5394a8cf7bf1d 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -524,7 +524,6 @@ static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 				    phy_interface_t mode, bool force)
 {
 	u16 cmode;
-	int lane;
 	u16 reg;
 	int err;
 
@@ -577,19 +576,6 @@ static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 	if (cmode == chip->ports[port].cmode && !force)
 		return 0;
 
-	lane = mv88e6xxx_serdes_get_lane(chip, port);
-	if (lane >= 0) {
-		if (chip->ports[port].serdes_irq) {
-			err = mv88e6xxx_serdes_irq_disable(chip, port, lane);
-			if (err)
-				return err;
-		}
-
-		err = mv88e6xxx_serdes_power_down(chip, port, lane);
-		if (err)
-			return err;
-	}
-
 	chip->ports[port].cmode = 0;
 
 	if (cmode) {
@@ -605,22 +591,6 @@ static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 			return err;
 
 		chip->ports[port].cmode = cmode;
-
-		lane = mv88e6xxx_serdes_get_lane(chip, port);
-		if (lane == -ENODEV)
-			return 0;
-		if (lane < 0)
-			return lane;
-
-		err = mv88e6xxx_serdes_power_up(chip, port, lane);
-		if (err)
-			return err;
-
-		if (chip->ports[port].serdes_irq) {
-			err = mv88e6xxx_serdes_irq_enable(chip, port, lane);
-			if (err)
-				return err;
-		}
 	}
 
 	return 0;
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index 67584cb1fdb95..aac95cab46e3d 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -153,24 +153,6 @@ static inline int mv88e6xxx_serdes_get_lane(struct mv88e6xxx_chip *chip,
 	return chip->info->ops->serdes_get_lane(chip, port);
 }
 
-static inline int mv88e6xxx_serdes_power_up(struct mv88e6xxx_chip *chip,
-					    int port, int lane)
-{
-	if (!chip->info->ops->serdes_power)
-		return -EOPNOTSUPP;
-
-	return chip->info->ops->serdes_power(chip, port, lane, true);
-}
-
-static inline int mv88e6xxx_serdes_power_down(struct mv88e6xxx_chip *chip,
-					      int port, int lane)
-{
-	if (!chip->info->ops->serdes_power)
-		return -EOPNOTSUPP;
-
-	return chip->info->ops->serdes_power(chip, port, lane, false);
-}
-
 static inline unsigned int
 mv88e6xxx_serdes_irq_mapping(struct mv88e6xxx_chip *chip, int port)
 {
@@ -180,33 +162,6 @@ mv88e6xxx_serdes_irq_mapping(struct mv88e6xxx_chip *chip, int port)
 	return chip->info->ops->serdes_irq_mapping(chip, port);
 }
 
-static inline int mv88e6xxx_serdes_irq_enable(struct mv88e6xxx_chip *chip,
-					      int port, int lane)
-{
-	if (!chip->info->ops->serdes_irq_enable)
-		return -EOPNOTSUPP;
-
-	return chip->info->ops->serdes_irq_enable(chip, port, lane, true);
-}
-
-static inline int mv88e6xxx_serdes_irq_disable(struct mv88e6xxx_chip *chip,
-					       int port, int lane)
-{
-	if (!chip->info->ops->serdes_irq_enable)
-		return -EOPNOTSUPP;
-
-	return chip->info->ops->serdes_irq_enable(chip, port, lane, false);
-}
-
-static inline irqreturn_t
-mv88e6xxx_serdes_irq_status(struct mv88e6xxx_chip *chip, int port, int lane)
-{
-	if (!chip->info->ops->serdes_irq_status)
-		return IRQ_NONE;
-
-	return chip->info->ops->serdes_irq_status(chip, port, lane);
-}
-
 extern const struct mv88e6xxx_pcs_ops mv88e6185_pcs_ops;
 extern const struct mv88e6xxx_pcs_ops mv88e6352_pcs_ops;
 extern const struct mv88e6xxx_pcs_ops mv88e6390_pcs_ops;
-- 
GitLab


From 633d76ad01ad0321a1ace3e5cc4fed06753d7ac4 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 13 Jul 2023 11:44:19 +0200
Subject: [PATCH 0130/1806] devlink: remove reload failed checks in params
 get/set callbacks

The checks in question were introduced by:
commit 6b4db2e528f6 ("devlink: Fix use-after-free after a failed reload").
That fixed an issue of reload with mlxsw driver.

Back then, that was a valid fix, because there was a limitation
in place that prevented drivers from registering/unregistering params
when devlink instance was registered.

It was possible to do the fix differently by changing drivers to
register/unregister params in appropriate places making sure the ops
operate only on memory which is allocated and initialized. But that,
as a dependency, would require to remove the limitation mentioned above.

Eventually, this limitation was lifted by:
commit 1d18bb1a4ddd ("devlink: allow registering parameters after the instance")

Also, the alternative fix (which also fixed another issue) was done by:
commit 74cbc3c03c82 ("mlxsw: spectrum_acl_tcam: Move devlink param to TCAM code").

Therefore, the checks are no longer relevant. Each driver should make
sure to have the params registered only when the memory the ops
are working with is allocated and initialized.

So remove the checks.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/devlink/leftover.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 1f00f874471fa..5128b9c7eea81 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -3946,7 +3946,7 @@ static int devlink_param_get(struct devlink *devlink,
 			     const struct devlink_param *param,
 			     struct devlink_param_gset_ctx *ctx)
 {
-	if (!param->get || devlink->reload_failed)
+	if (!param->get)
 		return -EOPNOTSUPP;
 	return param->get(devlink, param->id, ctx);
 }
@@ -3955,7 +3955,7 @@ static int devlink_param_set(struct devlink *devlink,
 			     const struct devlink_param *param,
 			     struct devlink_param_gset_ctx *ctx)
 {
-	if (!param->set || devlink->reload_failed)
+	if (!param->set)
 		return -EOPNOTSUPP;
 	return param->set(devlink, param->id, ctx);
 }
-- 
GitLab


From 02b34d03a24b18970925cf57434be28ba4a29d3a Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 13 Jul 2023 15:20:23 +0200
Subject: [PATCH 0131/1806] netdevsim: add dummy macsec offload

When the kernel is compiled with MACsec support, add the
NETIF_F_HW_MACSEC feature to netdevsim devices and implement
macsec_ops.

To allow easy testing of failure from the device, support is limited
to 3 SecY's per netdevsim device, and 1 RXSC per SecY.

v2:
 - nsim_macsec_add_secy, return -ENOSPC if secy_count isn't full but
   we can't find an empty slot (Simon Horman)
 - add sci_to_cpu to make sparse happy (Simon Horman)
 - remove set but not used secy variable (kernel test robot and
   Simon Horman)

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/Makefile    |   4 +
 drivers/net/netdevsim/macsec.c    | 356 ++++++++++++++++++++++++++++++
 drivers/net/netdevsim/netdev.c    |   3 +
 drivers/net/netdevsim/netdevsim.h |  34 +++
 4 files changed, 397 insertions(+)
 create mode 100644 drivers/net/netdevsim/macsec.c

diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile
index 5735e5b1a2cb7..f8de93bc5f5be 100644
--- a/drivers/net/netdevsim/Makefile
+++ b/drivers/net/netdevsim/Makefile
@@ -17,3 +17,7 @@ endif
 ifneq ($(CONFIG_PSAMPLE),)
 netdevsim-objs += psample.o
 endif
+
+ifneq ($(CONFIG_MACSEC),)
+netdevsim-objs += macsec.o
+endif
diff --git a/drivers/net/netdevsim/macsec.c b/drivers/net/netdevsim/macsec.c
new file mode 100644
index 0000000000000..0d5f50430dd38
--- /dev/null
+++ b/drivers/net/netdevsim/macsec.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <net/macsec.h>
+#include "netdevsim.h"
+
+static inline u64 sci_to_cpu(sci_t sci)
+{
+	return be64_to_cpu((__force __be64)sci);
+}
+
+static int nsim_macsec_find_secy(struct netdevsim *ns, sci_t sci)
+{
+	int i;
+
+	for (i = 0; i < NSIM_MACSEC_MAX_SECY_COUNT; i++) {
+		if (ns->macsec.nsim_secy[i].sci == sci)
+			return i;
+	}
+
+	return -1;
+}
+
+static int nsim_macsec_find_rxsc(struct nsim_secy *ns_secy, sci_t sci)
+{
+	int i;
+
+	for (i = 0; i < NSIM_MACSEC_MAX_RXSC_COUNT; i++) {
+		if (ns_secy->nsim_rxsc[i].sci == sci)
+			return i;
+	}
+
+	return -1;
+}
+
+static int nsim_macsec_add_secy(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	if (ns->macsec.nsim_secy_count == NSIM_MACSEC_MAX_SECY_COUNT)
+		return -ENOSPC;
+
+	for (idx = 0; idx < NSIM_MACSEC_MAX_SECY_COUNT; idx++) {
+		if (!ns->macsec.nsim_secy[idx].used)
+			break;
+	}
+
+	if (idx == NSIM_MACSEC_MAX_SECY_COUNT) {
+		netdev_err(ctx->netdev, "%s: nsim_secy_count not full but all SecYs used\n",
+			   __func__);
+		return -ENOSPC;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: adding new secy with sci %08llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), idx);
+	ns->macsec.nsim_secy[idx].used = true;
+	ns->macsec.nsim_secy[idx].nsim_rxsc_count = 0;
+	ns->macsec.nsim_secy[idx].sci = ctx->secy->sci;
+	ns->macsec.nsim_secy_count++;
+
+	return 0;
+}
+
+static int nsim_macsec_upd_secy(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: updating secy with sci %08llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), idx);
+
+	return 0;
+}
+
+static int nsim_macsec_del_secy(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: removing SecY with SCI %08llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), idx);
+
+	ns->macsec.nsim_secy[idx].used = false;
+	memset(&ns->macsec.nsim_secy[idx], 0, sizeof(ns->macsec.nsim_secy[idx]));
+	ns->macsec.nsim_secy_count--;
+
+	return 0;
+}
+
+static int nsim_macsec_add_rxsc(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	if (secy->nsim_rxsc_count == NSIM_MACSEC_MAX_RXSC_COUNT)
+		return -ENOSPC;
+
+	for (idx = 0; idx < NSIM_MACSEC_MAX_RXSC_COUNT; idx++) {
+		if (!secy->nsim_rxsc[idx].used)
+			break;
+	}
+
+	if (idx == NSIM_MACSEC_MAX_RXSC_COUNT)
+		netdev_err(ctx->netdev, "%s: nsim_rxsc_count not full but all RXSCs used\n",
+			   __func__);
+
+	netdev_dbg(ctx->netdev, "%s: adding new rxsc with sci %08llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->rx_sc->sci), idx);
+	secy->nsim_rxsc[idx].used = true;
+	secy->nsim_rxsc[idx].sci = ctx->rx_sc->sci;
+	secy->nsim_rxsc_count++;
+
+	return 0;
+}
+
+static int nsim_macsec_upd_rxsc(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	idx = nsim_macsec_find_rxsc(secy, ctx->rx_sc->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in RXSC table\n",
+			   __func__, sci_to_cpu(ctx->rx_sc->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: updating RXSC with sci %08llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->rx_sc->sci), idx);
+
+	return 0;
+}
+
+static int nsim_macsec_del_rxsc(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	idx = nsim_macsec_find_rxsc(secy, ctx->rx_sc->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in RXSC table\n",
+			   __func__, sci_to_cpu(ctx->rx_sc->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: removing RXSC with sci %08llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->rx_sc->sci), idx);
+
+	secy->nsim_rxsc[idx].used = false;
+	memset(&secy->nsim_rxsc[idx], 0, sizeof(secy->nsim_rxsc[idx]));
+	secy->nsim_rxsc_count--;
+
+	return 0;
+}
+
+static int nsim_macsec_add_rxsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in RXSC table\n",
+			   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: RXSC with sci %08llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static int nsim_macsec_upd_rxsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in RXSC table\n",
+			   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: RXSC with sci %08llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static int nsim_macsec_del_rxsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in RXSC table\n",
+			   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: RXSC with sci %08llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static int nsim_macsec_add_txsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: SECY with sci %08llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static int nsim_macsec_upd_txsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: SECY with sci %08llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static int nsim_macsec_del_txsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %08llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: SECY with sci %08llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static const struct macsec_ops nsim_macsec_ops = {
+	.mdo_add_secy = nsim_macsec_add_secy,
+	.mdo_upd_secy = nsim_macsec_upd_secy,
+	.mdo_del_secy = nsim_macsec_del_secy,
+	.mdo_add_rxsc = nsim_macsec_add_rxsc,
+	.mdo_upd_rxsc = nsim_macsec_upd_rxsc,
+	.mdo_del_rxsc = nsim_macsec_del_rxsc,
+	.mdo_add_rxsa = nsim_macsec_add_rxsa,
+	.mdo_upd_rxsa = nsim_macsec_upd_rxsa,
+	.mdo_del_rxsa = nsim_macsec_del_rxsa,
+	.mdo_add_txsa = nsim_macsec_add_txsa,
+	.mdo_upd_txsa = nsim_macsec_upd_txsa,
+	.mdo_del_txsa = nsim_macsec_del_txsa,
+};
+
+void nsim_macsec_init(struct netdevsim *ns)
+{
+	ns->netdev->macsec_ops = &nsim_macsec_ops;
+	ns->netdev->features |= NETIF_F_HW_MACSEC;
+	memset(&ns->macsec, 0, sizeof(ns->macsec));
+}
+
+void nsim_macsec_teardown(struct netdevsim *ns)
+{
+}
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 35fa1ca986715..0c8daeb0d62b9 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -304,6 +304,7 @@ static int nsim_init_netdevsim(struct netdevsim *ns)
 	if (err)
 		goto err_utn_destroy;
 
+	nsim_macsec_init(ns);
 	nsim_ipsec_init(ns);
 
 	err = register_netdevice(ns->netdev);
@@ -314,6 +315,7 @@ static int nsim_init_netdevsim(struct netdevsim *ns)
 
 err_ipsec_teardown:
 	nsim_ipsec_teardown(ns);
+	nsim_macsec_teardown(ns);
 	nsim_bpf_uninit(ns);
 err_utn_destroy:
 	rtnl_unlock();
@@ -374,6 +376,7 @@ void nsim_destroy(struct netdevsim *ns)
 	rtnl_lock();
 	unregister_netdevice(dev);
 	if (nsim_dev_port_is_pf(ns->nsim_dev_port)) {
+		nsim_macsec_teardown(ns);
 		nsim_ipsec_teardown(ns);
 		nsim_bpf_uninit(ns);
 	}
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 7d8ed8d8df5c9..7be98b7dcca96 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -23,6 +23,7 @@
 #include <net/devlink.h>
 #include <net/udp_tunnel.h>
 #include <net/xdp.h>
+#include <net/macsec.h>
 
 #define DRV_NAME	"netdevsim"
 
@@ -52,6 +53,25 @@ struct nsim_ipsec {
 	u32 ok;
 };
 
+#define NSIM_MACSEC_MAX_SECY_COUNT 3
+#define NSIM_MACSEC_MAX_RXSC_COUNT 1
+struct nsim_rxsc {
+	sci_t sci;
+	bool used;
+};
+
+struct nsim_secy {
+	sci_t sci;
+	struct nsim_rxsc nsim_rxsc[NSIM_MACSEC_MAX_RXSC_COUNT];
+	u8 nsim_rxsc_count;
+	bool used;
+};
+
+struct nsim_macsec {
+	struct nsim_secy nsim_secy[NSIM_MACSEC_MAX_SECY_COUNT];
+	u8 nsim_secy_count;
+};
+
 struct nsim_ethtool_pauseparam {
 	bool rx;
 	bool tx;
@@ -93,6 +113,7 @@ struct netdevsim {
 
 	bool bpf_map_accept;
 	struct nsim_ipsec ipsec;
+	struct nsim_macsec macsec;
 	struct {
 		u32 inject_error;
 		u32 sleep;
@@ -366,6 +387,19 @@ static inline bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_MACSEC)
+void nsim_macsec_init(struct netdevsim *ns);
+void nsim_macsec_teardown(struct netdevsim *ns);
+#else
+static inline void nsim_macsec_init(struct netdevsim *ns)
+{
+}
+
+static inline void nsim_macsec_teardown(struct netdevsim *ns)
+{
+}
+#endif
+
 struct nsim_bus_dev {
 	struct device dev;
 	struct list_head list;
-- 
GitLab


From 3b5222e2ac57982586d1bb33167e381a8167afe6 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 13 Jul 2023 15:20:24 +0200
Subject: [PATCH 0132/1806] selftests: rtnetlink: add MACsec offload tests

Like the IPsec offload test, this requires netdevsim.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 83 ++++++++++++++++++++++++
 1 file changed, 83 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index ba286d680fd9a..488f4964365e7 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -21,6 +21,7 @@ ALL_TESTS="
 	kci_test_vrf
 	kci_test_encap
 	kci_test_macsec
+	kci_test_macsec_offload
 	kci_test_ipsec
 	kci_test_ipsec_offload
 	kci_test_fdb_get
@@ -643,6 +644,88 @@ kci_test_macsec()
 	echo "PASS: macsec"
 }
 
+kci_test_macsec_offload()
+{
+	sysfsd=/sys/kernel/debug/netdevsim/netdevsim0/ports/0/
+	sysfsnet=/sys/bus/netdevsim/devices/netdevsim0/net/
+	probed=false
+	local ret=0
+
+	ip macsec help 2>&1 | grep -q "^Usage: ip macsec"
+	if [ $? -ne 0 ]; then
+		echo "SKIP: macsec: iproute2 too old"
+		return $ksft_skip
+	fi
+
+	# setup netdevsim since dummydev doesn't have offload support
+	if [ ! -w /sys/bus/netdevsim/new_device ] ; then
+		modprobe -q netdevsim
+		check_err $?
+		if [ $ret -ne 0 ]; then
+			echo "SKIP: macsec_offload can't load netdevsim"
+			return $ksft_skip
+		fi
+		probed=true
+	fi
+
+	echo "0" > /sys/bus/netdevsim/new_device
+	while [ ! -d $sysfsnet ] ; do :; done
+	udevadm settle
+	dev=`ls $sysfsnet`
+
+	ip link set $dev up
+	if [ ! -d $sysfsd ] ; then
+		echo "FAIL: macsec_offload can't create device $dev"
+		return 1
+	fi
+
+	ethtool -k $dev | grep -q 'macsec-hw-offload: on'
+	if [ $? -eq 1 ] ; then
+		echo "FAIL: macsec_offload netdevsim doesn't support MACsec offload"
+		return 1
+	fi
+
+	ip link add link $dev kci_macsec1 type macsec port 4 offload mac
+	check_err $?
+
+	ip link add link $dev kci_macsec2 type macsec address "aa:bb:cc:dd:ee:ff" port 5 offload mac
+	check_err $?
+
+	ip link add link $dev kci_macsec3 type macsec sci abbacdde01020304 offload mac
+	check_err $?
+
+	ip link add link $dev kci_macsec4 type macsec port 8 offload mac 2> /dev/null
+	check_fail $?
+
+	msname=kci_macsec1
+
+	ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
+	check_err $?
+
+	ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef"
+	check_err $?
+
+	ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on \
+		key 00 0123456789abcdef0123456789abcdef
+	check_err $?
+
+	ip macsec add "$msname" rx port 1235 address "1c:ed:de:ad:be:ef" 2> /dev/null
+	check_fail $?
+
+	# clean up any leftovers
+	for msdev in kci_macsec{1,2,3,4} ; do
+	    ip link del $msdev 2> /dev/null
+	done
+	echo 0 > /sys/bus/netdevsim/del_device
+	$probed && rmmod netdevsim
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: macsec_offload"
+		return 1
+	fi
+	echo "PASS: macsec_offload"
+}
+
 #-------------------------------------------------------------------
 # Example commands
 #   ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \
-- 
GitLab


From 352be882deda87d30b5f6249994e2ab2749e5106 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:24 +0200
Subject: [PATCH 0133/1806] mlxsw: spectrum_switchdev: Pass extack to
 mlxsw_sp_br_ban_rif_pvid_change()

Currently the reason for rejection of PVID manipulation is dumped to
syslog, and a generic -EBUSY is returned to the userspace. But
switchdev_handle_port_obj_add(), through which we get to
mlxsw_sp_port_vlans_add(), handles extack just fine, and we can pass the
message this way.

This improves visibility into reasons why the request to change PVID
was rejected. Before the change:

 # bridge vlan add dev br vid 2 self pvid untagged
 RTNETLINK answers: Device or resource busy
 (plus a syslog line)

After the change:

 # bridge vlan add dev br vid 2 self pvid untagged
 Error: mlxsw_spectrum: Can't change PVID, it's used by router interface.

Note that this particular error message is going away in the following
patches. However the ability to pass error messages through extack will be
useful more broadly for communicating in particular reasons why a RIF
failed to be created.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index d88e62bc759fb..a3365f7437d66 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1481,7 +1481,8 @@ err_port_vlan_set:
 static int
 mlxsw_sp_br_ban_rif_pvid_change(struct mlxsw_sp *mlxsw_sp,
 				const struct net_device *br_dev,
-				const struct switchdev_obj_port_vlan *vlan)
+				const struct switchdev_obj_port_vlan *vlan,
+				struct netlink_ext_ack *extack)
 {
 	u16 pvid;
 
@@ -1491,12 +1492,12 @@ mlxsw_sp_br_ban_rif_pvid_change(struct mlxsw_sp *mlxsw_sp,
 
 	if (vlan->flags & BRIDGE_VLAN_INFO_PVID) {
 		if (vlan->vid != pvid) {
-			netdev_err(br_dev, "Can't change PVID, it's used by router interface\n");
+			NL_SET_ERR_MSG_MOD(extack, "Can't change PVID, it's used by router interface");
 			return -EBUSY;
 		}
 	} else {
 		if (vlan->vid == pvid) {
-			netdev_err(br_dev, "Can't remove PVID, it's used by router interface\n");
+			NL_SET_ERR_MSG_MOD(extack, "Can't remove PVID, it's used by router interface");
 			return -EBUSY;
 		}
 	}
@@ -1519,7 +1520,8 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 
 		if (br_vlan_enabled(orig_dev))
 			err = mlxsw_sp_br_ban_rif_pvid_change(mlxsw_sp,
-							      orig_dev, vlan);
+							      orig_dev, vlan,
+							      extack);
 		if (!err)
 			err = -EOPNOTSUPP;
 		return err;
-- 
GitLab


From 5ca9f42caf8103a5b51cbe78777f7df972cc6263 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:25 +0200
Subject: [PATCH 0134/1806] mlxsw: spectrum_router: Pass struct
 mlxsw_sp_rif_params to fid_get

The fid_get callback is called to allocate a FID for the newly-created RIF.
In a following patch, the fid_get implementation for VLANs will be modified
to take the VLAN ID from the parameters instead of deducing it from the
netdevice. To that end, propagate the RIF parameters to the fid_get
callback.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index b32adf277a227..adfb1ef2a6646 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -139,6 +139,7 @@ struct mlxsw_sp_rif_ops {
 			 struct netlink_ext_ack *extack);
 	void (*deconfigure)(struct mlxsw_sp_rif *rif);
 	struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif,
+					 const struct mlxsw_sp_rif_params *params,
 					 struct netlink_ext_ack *extack);
 	void (*fdb_del)(struct mlxsw_sp_rif *rif, const char *mac);
 };
@@ -8300,7 +8301,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	rif->rif_entries = rif_entries;
 
 	if (ops->fid_get) {
-		fid = ops->fid_get(rif, extack);
+		fid = ops->fid_get(rif, params, extack);
 		if (IS_ERR(fid)) {
 			err = PTR_ERR(fid);
 			goto err_fid_get;
@@ -8678,7 +8679,7 @@ __mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 		return PTR_ERR(rif);
 
 	/* FID was already created, just take a reference */
-	fid = rif->ops->fid_get(rif, extack);
+	fid = rif->ops->fid_get(rif, &params, extack);
 	err = mlxsw_sp_fid_port_vid_map(fid, mlxsw_sp_port, vid);
 	if (err)
 		goto err_fid_port_vid_map;
@@ -9724,6 +9725,7 @@ static void mlxsw_sp_rif_subport_deconfigure(struct mlxsw_sp_rif *rif)
 
 static struct mlxsw_sp_fid *
 mlxsw_sp_rif_subport_fid_get(struct mlxsw_sp_rif *rif,
+			     const struct mlxsw_sp_rif_params *params,
 			     struct netlink_ext_ack *extack)
 {
 	return mlxsw_sp_fid_rfid_get(rif->mlxsw_sp, rif->rif_index);
@@ -9836,6 +9838,7 @@ static void mlxsw_sp_rif_fid_deconfigure(struct mlxsw_sp_rif *rif)
 
 static struct mlxsw_sp_fid *
 mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif,
+			 const struct mlxsw_sp_rif_params *params,
 			 struct netlink_ext_ack *extack)
 {
 	int rif_ifindex = mlxsw_sp_rif_dev_ifindex(rif);
@@ -9869,6 +9872,7 @@ static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = {
 
 static struct mlxsw_sp_fid *
 mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
+			  const struct mlxsw_sp_rif_params *params,
 			  struct netlink_ext_ack *extack)
 {
 	struct net_device *dev = mlxsw_sp_rif_dev(rif);
-- 
GitLab


From a0944b24d278b2657ffd5dcbaaf8c24d43e39e0c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:26 +0200
Subject: [PATCH 0135/1806] mlxsw: spectrum_router: Take VID for VLAN FIDs from
 RIF params

Currently, when an IP address is added to a bridge that has no PVID, the
operation is rejected. An IP address addition is interpreted as a request
to create a RIF for the bridge device, but without a PVID there is no VLAN
for which the RIF should be created. Thus the correct way to create a RIF
for a bridge as a user is to first add a PVID, and then add the IP address.

Ideally this ordering requirement would not exist. RIF would be created
either because an IP address is added, or because a PVID is added,
depending on which comes last.

For that, the switchdev code (which notices the PVID change request) must
be able to request that a RIF is created with a given VLAN ID, because at
the time that the PVID notification is distributed, the PVID setting is not
yet visible for querying.

Therefore when creating a VLAN-based RIF, use mlxsw_sp_rif_params.vid to
communicate the VID, and do not determine it ad-hoc in the fid_get
callback.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 31 +++++++++++--------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index adfb1ef2a6646..e840ca9a96738 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8665,14 +8665,17 @@ __mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	struct mlxsw_sp_rif_params params = {
-		.dev = l3_dev,
-	};
+	struct mlxsw_sp_rif_params params;
 	u16 vid = mlxsw_sp_port_vlan->vid;
 	struct mlxsw_sp_rif *rif;
 	struct mlxsw_sp_fid *fid;
 	int err;
 
+	params = (struct mlxsw_sp_rif_params) {
+		.dev = l3_dev,
+		.vid = vid,
+	};
+
 	mlxsw_sp_rif_subport_params_init(&params, mlxsw_sp_port_vlan);
 	rif = mlxsw_sp_rif_subport_get(mlxsw_sp, &params, extack);
 	if (IS_ERR(rif))
@@ -8830,6 +8833,7 @@ static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp,
 		.dev = l3_dev,
 	};
 	struct mlxsw_sp_rif *rif;
+	int err;
 
 	switch (event) {
 	case NETDEV_UP:
@@ -8841,6 +8845,13 @@ static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp,
 				NL_SET_ERR_MSG_MOD(extack, "Adding an IP address to 802.1ad bridge is not supported");
 				return -EOPNOTSUPP;
 			}
+			err = br_vlan_get_pvid(l3_dev, &params.vid);
+			if (err < 0 || !params.vid) {
+				NL_SET_ERR_MSG_MOD(extack, "Couldn't determine bridge PVID");
+				return -EINVAL;
+			}
+		} else if (is_vlan_dev(l3_dev)) {
+			params.vid = vlan_dev_vlan_id(l3_dev);
 		}
 		rif = mlxsw_sp_rif_create(mlxsw_sp, &params, extack);
 		if (IS_ERR(rif))
@@ -9877,23 +9888,17 @@ mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
 {
 	struct net_device *dev = mlxsw_sp_rif_dev(rif);
 	struct net_device *br_dev;
-	u16 vid;
-	int err;
+
+	if (WARN_ON(!params->vid))
+		return ERR_PTR(-EINVAL);
 
 	if (is_vlan_dev(dev)) {
-		vid = vlan_dev_vlan_id(dev);
 		br_dev = vlan_dev_real_dev(dev);
 		if (WARN_ON(!netif_is_bridge_master(br_dev)))
 			return ERR_PTR(-EINVAL);
-	} else {
-		err = br_vlan_get_pvid(dev, &vid);
-		if (err < 0 || !vid) {
-			NL_SET_ERR_MSG_MOD(extack, "Couldn't determine bridge PVID");
-			return ERR_PTR(-EINVAL);
-		}
 	}
 
-	return mlxsw_sp_fid_8021q_get(rif->mlxsw_sp, vid);
+	return mlxsw_sp_fid_8021q_get(rif->mlxsw_sp, params->vid);
 }
 
 static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
-- 
GitLab


From a24a4d29ff0a4a425913e3f538ba429f2bbd2bbd Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:27 +0200
Subject: [PATCH 0136/1806] mlxsw: spectrum_router: Adjust
 mlxsw_sp_inetaddr_vlan_event() coding style

The bridge branch of the dispatch in this function is going to get more
code and will need curly braces. Per the doctrine, that means the whole
if-else chain should get them.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index e840ca9a96738..3a51032698309 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8877,15 +8877,17 @@ static int mlxsw_sp_inetaddr_vlan_event(struct mlxsw_sp *mlxsw_sp,
 	if (netif_is_bridge_port(vlan_dev))
 		return 0;
 
-	if (mlxsw_sp_port_dev_check(real_dev))
+	if (mlxsw_sp_port_dev_check(real_dev)) {
 		return mlxsw_sp_inetaddr_port_vlan_event(vlan_dev, real_dev,
 							 event, vid, extack);
-	else if (netif_is_lag_master(real_dev))
+	} else if (netif_is_lag_master(real_dev)) {
 		return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
 						     vid, extack);
-	else if (netif_is_bridge_master(real_dev) && br_vlan_enabled(real_dev))
+	} else if (netif_is_bridge_master(real_dev) &&
+		   br_vlan_enabled(real_dev)) {
 		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, vlan_dev, event,
 						      extack);
+	}
 
 	return 0;
 }
-- 
GitLab


From 3430f2cf91a4b0ee4d639644c75f7c7b4b0bf1cf Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:28 +0200
Subject: [PATCH 0137/1806] mlxsw: spectrum_router:
 mlxsw_sp_inetaddr_bridge_event: Add an argument

For purposes of replay, mlxsw_sp_inetaddr_bridge_event() will need to make
decisions based on the proposed value of PVID. Querying PVID reveals the
current settings, not the in-flight values that the user requested and that
the notifiers are acting upon. Add a parameter, lower_pvid, which carries
the proposed PVID of the lower bridge, or -1 if the lower is not a bridge.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 3a51032698309..63f40d16be3bf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8826,6 +8826,7 @@ static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
 
 static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp,
 					  struct net_device *l3_dev,
+					  int lower_pvid,
 					  unsigned long event,
 					  struct netlink_ext_ack *extack)
 {
@@ -8873,6 +8874,8 @@ static int mlxsw_sp_inetaddr_vlan_event(struct mlxsw_sp *mlxsw_sp,
 {
 	struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
 	u16 vid = vlan_dev_vlan_id(vlan_dev);
+	u16 lower_pvid;
+	int err;
 
 	if (netif_is_bridge_port(vlan_dev))
 		return 0;
@@ -8885,7 +8888,11 @@ static int mlxsw_sp_inetaddr_vlan_event(struct mlxsw_sp *mlxsw_sp,
 						     vid, extack);
 	} else if (netif_is_bridge_master(real_dev) &&
 		   br_vlan_enabled(real_dev)) {
-		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, vlan_dev, event,
+		err = br_vlan_get_pvid(real_dev, &lower_pvid);
+		if (err)
+			return err;
+		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, vlan_dev,
+						      lower_pvid, event,
 						      extack);
 	}
 
@@ -9022,7 +9029,7 @@ static int __mlxsw_sp_inetaddr_event(struct mlxsw_sp *mlxsw_sp,
 	else if (netif_is_lag_master(dev))
 		return mlxsw_sp_inetaddr_lag_event(dev, event, extack);
 	else if (netif_is_bridge_master(dev))
-		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, dev, event,
+		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, dev, -1, event,
 						      extack);
 	else if (is_vlan_dev(dev))
 		return mlxsw_sp_inetaddr_vlan_event(mlxsw_sp, dev, event,
-- 
GitLab


From a5b52692e69338e4fc6abe0609679db3bade0d22 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:29 +0200
Subject: [PATCH 0138/1806] mlxsw: spectrum_switchdev: Manage RIFs on PVID
 change

Currently, mlxsw has several shortcomings with regards to RIF handling due
to PVID changes:

- In order to cause RIF for a bridge device to be created, the user is
  expected first to set PVID, then to add an IP address. The reverse
  ordering is disallowed, which is not very user-friendly.

- When such bridge gets a VLAN upper whose VID was the same as the existing
  PVID, and this VLAN netdevice gets an IP address, a RIF is created for
  this netdevice. The new RIF is then assigned to the 802.1Q FID for the
  given VID. This results in a working configuration. However, then, when
  the VLAN netdevice is removed again, the RIF for the bridge itself is
  never reassociated to the VLAN.

- PVID cannot be changed once the bridge has uppers. Presumably this is
  because the driver does not manage RIFs properly in face of PVID changes.
  However, as the previous point shows, it is still possible to get into
  invalid configurations.

In this patch, add the logic necessary for creation of a RIF as a result of
PVID change. Moreover, when a VLAN upper is created whose VID matches lower
PVID, do not create RIF for this netdevice.

These changes obviate the need for ordering of IP address additions and
PVID configuration, so stop forbidding addition of an IP address to a
PVID-less bridge. Instead, bail out quietly. Also stop preventing PVID
changes when the bridge has uppers.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 119 +++++++++++++++++-
 .../ethernet/mellanox/mlxsw/spectrum_router.h |   4 +
 .../mellanox/mlxsw/spectrum_switchdev.c       |  34 ++---
 3 files changed, 128 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 63f40d16be3bf..109ac2db0d654 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8411,6 +8411,110 @@ out:
 	mutex_unlock(&mlxsw_sp->router->lock);
 }
 
+static void mlxsw_sp_rif_destroy_vlan_upper(struct mlxsw_sp *mlxsw_sp,
+					    struct net_device *br_dev,
+					    u16 vid)
+{
+	struct net_device *upper_dev;
+	struct mlxsw_sp_crif *crif;
+
+	rcu_read_lock();
+	upper_dev = __vlan_find_dev_deep_rcu(br_dev, htons(ETH_P_8021Q), vid);
+	rcu_read_unlock();
+
+	if (!upper_dev)
+		return;
+
+	crif = mlxsw_sp_crif_lookup(mlxsw_sp->router, upper_dev);
+	if (!crif || !crif->rif)
+		return;
+
+	mlxsw_sp_rif_destroy(crif->rif);
+}
+
+static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp,
+					  struct net_device *l3_dev,
+					  int lower_pvid,
+					  unsigned long event,
+					  struct netlink_ext_ack *extack);
+
+int mlxsw_sp_router_bridge_vlan_add(struct mlxsw_sp *mlxsw_sp,
+				    struct net_device *br_dev,
+				    u16 new_vid, bool is_pvid,
+				    struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_rif *old_rif;
+	struct mlxsw_sp_rif *new_rif;
+	struct net_device *upper_dev;
+	u16 old_pvid = 0;
+	u16 new_pvid;
+	int err = 0;
+
+	mutex_lock(&mlxsw_sp->router->lock);
+	old_rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, br_dev);
+	if (old_rif) {
+		/* If the RIF on the bridge is not a VLAN RIF, we shouldn't have
+		 * gotten a PVID notification.
+		 */
+		if (WARN_ON(old_rif->ops->type != MLXSW_SP_RIF_TYPE_VLAN))
+			old_rif = NULL;
+		else
+			old_pvid = mlxsw_sp_fid_8021q_vid(old_rif->fid);
+	}
+
+	if (is_pvid)
+		new_pvid = new_vid;
+	else if (old_pvid == new_vid)
+		new_pvid = 0;
+	else
+		goto out;
+
+	if (old_pvid == new_pvid)
+		goto out;
+
+	if (new_pvid) {
+		struct mlxsw_sp_rif_params params = {
+			.dev = br_dev,
+			.vid = new_pvid,
+		};
+
+		/* If there is a VLAN upper with the same VID as the new PVID,
+		 * kill its RIF, if there is one.
+		 */
+		mlxsw_sp_rif_destroy_vlan_upper(mlxsw_sp, br_dev, new_pvid);
+
+		if (mlxsw_sp_dev_addr_list_empty(br_dev))
+			goto out;
+		new_rif = mlxsw_sp_rif_create(mlxsw_sp, &params, extack);
+		if (IS_ERR(new_rif)) {
+			err = PTR_ERR(new_rif);
+			goto out;
+		}
+
+		if (old_pvid)
+			mlxsw_sp_rif_migrate_destroy(mlxsw_sp, old_rif, new_rif,
+						     true);
+	} else {
+		mlxsw_sp_rif_destroy(old_rif);
+	}
+
+	if (old_pvid) {
+		rcu_read_lock();
+		upper_dev = __vlan_find_dev_deep_rcu(br_dev, htons(ETH_P_8021Q),
+						     old_pvid);
+		rcu_read_unlock();
+		if (upper_dev)
+			err = mlxsw_sp_inetaddr_bridge_event(mlxsw_sp,
+							     upper_dev,
+							     new_pvid,
+							     NETDEV_UP, extack);
+	}
+
+out:
+	mutex_unlock(&mlxsw_sp->router->lock);
+	return err;
+}
+
 static void
 mlxsw_sp_rif_subport_params_init(struct mlxsw_sp_rif_params *params,
 				 struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
@@ -8847,13 +8951,20 @@ static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp,
 				return -EOPNOTSUPP;
 			}
 			err = br_vlan_get_pvid(l3_dev, &params.vid);
-			if (err < 0 || !params.vid) {
-				NL_SET_ERR_MSG_MOD(extack, "Couldn't determine bridge PVID");
-				return -EINVAL;
-			}
+			if (err)
+				return err;
+			if (!params.vid)
+				return 0;
 		} else if (is_vlan_dev(l3_dev)) {
 			params.vid = vlan_dev_vlan_id(l3_dev);
+
+			/* If the VID matches PVID of the bridge below, the
+			 * bridge owns the RIF for this VLAN. Don't do anything.
+			 */
+			if ((int)params.vid == lower_pvid)
+				return 0;
 		}
+
 		rif = mlxsw_sp_rif_create(mlxsw_sp, &params, extack);
 		if (IS_ERR(rif))
 			return PTR_ERR(rif);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 9a2669a084800..74242220a0cf0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -171,6 +171,10 @@ int mlxsw_sp_ipip_ecn_encap_init(struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_ipip_ecn_decap_init(struct mlxsw_sp *mlxsw_sp);
 struct net_device *
 mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev);
+int mlxsw_sp_router_bridge_vlan_add(struct mlxsw_sp *mlxsw_sp,
+				    struct net_device *dev,
+				    u16 new_vid, bool is_pvid,
+				    struct netlink_ext_ack *extack);
 int mlxsw_sp_router_port_join_lag(struct mlxsw_sp_port *mlxsw_sp_port,
 				  struct net_device *lag_dev,
 				  struct netlink_ext_ack *extack);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index a3365f7437d66..79d45c6c6edf6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1479,30 +1479,15 @@ err_port_vlan_set:
 }
 
 static int
-mlxsw_sp_br_ban_rif_pvid_change(struct mlxsw_sp *mlxsw_sp,
-				const struct net_device *br_dev,
-				const struct switchdev_obj_port_vlan *vlan,
-				struct netlink_ext_ack *extack)
+mlxsw_sp_br_rif_pvid_change(struct mlxsw_sp *mlxsw_sp,
+			    struct net_device *br_dev,
+			    const struct switchdev_obj_port_vlan *vlan,
+			    struct netlink_ext_ack *extack)
 {
-	u16 pvid;
-
-	pvid = mlxsw_sp_rif_vid(mlxsw_sp, br_dev);
-	if (!pvid)
-		return 0;
-
-	if (vlan->flags & BRIDGE_VLAN_INFO_PVID) {
-		if (vlan->vid != pvid) {
-			NL_SET_ERR_MSG_MOD(extack, "Can't change PVID, it's used by router interface");
-			return -EBUSY;
-		}
-	} else {
-		if (vlan->vid == pvid) {
-			NL_SET_ERR_MSG_MOD(extack, "Can't remove PVID, it's used by router interface");
-			return -EBUSY;
-		}
-	}
+	bool flag_pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
 
-	return 0;
+	return mlxsw_sp_router_bridge_vlan_add(mlxsw_sp, br_dev, vlan->vid,
+					       flag_pvid, extack);
 }
 
 static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -1519,9 +1504,8 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 		int err = 0;
 
 		if (br_vlan_enabled(orig_dev))
-			err = mlxsw_sp_br_ban_rif_pvid_change(mlxsw_sp,
-							      orig_dev, vlan,
-							      extack);
+			err = mlxsw_sp_br_rif_pvid_change(mlxsw_sp, orig_dev,
+							  vlan, extack);
 		if (!err)
 			err = -EOPNOTSUPP;
 		return err;
-- 
GitLab


From 5f44a7144cc59e18454a74e0ed1d0bc33e9cf398 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:30 +0200
Subject: [PATCH 0139/1806] selftests: forwarding: lib: Add ping6_,
 ping_test_fails()

Add two helpers to run a ping test that succeeds when the pings themselves
fail.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 9ddb68dd6a089..71f7c0c496776 100755
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -1215,6 +1215,15 @@ ping_test()
 	log_test "ping$3"
 }
 
+ping_test_fails()
+{
+	RET=0
+
+	ping_do $1 $2
+	check_fail $?
+	log_test "ping fails$3"
+}
+
 ping6_do()
 {
 	local if_name=$1
@@ -1237,6 +1246,15 @@ ping6_test()
 	log_test "ping6$3"
 }
 
+ping6_test_fails()
+{
+	RET=0
+
+	ping6_do $1 $2
+	check_fail $?
+	log_test "ping6 fails$3"
+}
+
 learning_test()
 {
 	local bridge=$1
-- 
GitLab


From c7203a2981dcd0aa738312a458317d86037a69e7 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:31 +0200
Subject: [PATCH 0140/1806] selftests: router_bridge: Add tests to remove and
 add PVID

This test relies on PVID being configured on the bridge itself. Thus when
it is deconfigured, the system should lose the ability to forward traffic.
Later when it is added again, the ability to forward traffic should be
regained. Add tests to exercise these configuration changes and verify
results.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/router_bridge.sh | 50 +++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/router_bridge.sh b/tools/testing/selftests/net/forwarding/router_bridge.sh
index 8ce0aed54ece3..4f33db04699d0 100755
--- a/tools/testing/selftests/net/forwarding/router_bridge.sh
+++ b/tools/testing/selftests/net/forwarding/router_bridge.sh
@@ -1,9 +1,33 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+# +------------------------+                           +----------------------+
+# | H1 (vrf)               |                           |             H2 (vrf) |
+# |    + $h1               |                           |  + $h2               |
+# |    | 192.0.2.1/28      |                           |  | 192.0.2.130/28    |
+# |    | 2001:db8:1::1/64  |                           |  | 2001:db8:2::2/64  |
+# |    |                   |                           |  |                   |
+# +----|-------------------+                           +--|-------------------+
+#      |                                                  |
+# +----|--------------------------------------------------|-------------------+
+# | SW |                                                  |                   |
+# | +--|-----------------------------+                    + $swp2             |
+# | |  + $swp1      BR1 (802.1q)     |                      192.0.2.129/28    |
+# | |               192.0.2.2/28     |                      2001:db8:2::1/64  |
+# | |               2001:db8:1::1/64 |                                        |
+# | |                                |                                        |
+# | +--------------------------------+                                        |
+# +---------------------------------------------------------------------------+
+
 ALL_TESTS="
 	ping_ipv4
 	ping_ipv6
+	config_remove_pvid
+	ping_ipv4_fails
+	ping_ipv6_fails
+	config_add_pvid
+	ping_ipv4
+	ping_ipv6
 "
 NUM_NETIFS=4
 source lib.sh
@@ -62,6 +86,22 @@ router_destroy()
 	ip link del dev br1
 }
 
+config_remove_pvid()
+{
+	log_info "Remove PVID from the bridge"
+
+	bridge vlan add dev br1 vid 1 self
+	sleep 2
+}
+
+config_add_pvid()
+{
+	log_info "Add PVID to the bridge"
+
+	bridge vlan add dev br1 vid 1 self pvid untagged
+	sleep 2
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
@@ -104,6 +144,16 @@ ping_ipv6()
 	ping6_test $h1 2001:db8:2::2
 }
 
+ping_ipv4_fails()
+{
+	ping_test_fails $h1 192.0.2.130
+}
+
+ping_ipv6_fails()
+{
+	ping6_test_fails $h1 2001:db8:2::2
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
GitLab


From d4172a93b2792387970148541336aad6d2c8bed8 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:32 +0200
Subject: [PATCH 0141/1806] selftests: router_bridge_vlan: Add PVID change test

Add an alternative path involving VLAN 777 instead of the current 555. Then
add tests that verify that marking 777 as PVID makes the 555 path not work,
and the 777 path work.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/router_bridge_vlan.sh      | 100 +++++++++++++++---
 1 file changed, 85 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
index de2b2d5480dd2..b76a4a707a5b3 100755
--- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
+++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
@@ -1,25 +1,28 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-# +------------------------+                           +----------------------+
-# | H1 (vrf)               |                           |             H2 (vrf) |
-# |    + $h1.555           |                           |  + $h2               |
-# |    | 192.0.2.1/28      |                           |  | 192.0.2.130/28    |
-# |    | 2001:db8:1::1/64  |                           |  | 2001:db8:2::2/64  |
-# |    |                   |                           |  |                   |
-# |    + $h1               |                           |  |                   |
-# +----|-------------------+                           +--|-------------------+
+# +------------------------------------------------+   +----------------------+
+# | H1 (vrf)                                       |   |             H2 (vrf) |
+# |    + $h1.555           + $h1.777               |   |  + $h2               |
+# |    | 192.0.2.1/28      | 192.0.2.17/28         |   |  | 192.0.2.130/28    |
+# |    | 2001:db8:1::1/64  | 2001:db8:3::1/64      |   |  | 192.0.2.146/28    |
+# |    | .-----------------'                       |   |  | 2001:db8:2::2/64  |
+# |    |/                                          |   |  | 2001:db8:4::2/64  |
+# |    + $h1                                       |   |  |                   |
+# +----|-------------------------------------------+   +--|-------------------+
 #      |                                                  |
 # +----|--------------------------------------------------|-------------------+
 # | SW |                                                  |                   |
 # | +--|-------------------------------+                  + $swp2             |
 # | |  + $swp1                         |                    192.0.2.129/28    |
-# | |    vid 555                       |                    2001:db8:2::1/64  |
-# | |                                  |                                      |
-# | |  + BR1 (802.1q)                  |                                      |
+# | |    vid 555 777                   |                    192.0.2.145/28    |
+# | |                                  |                    2001:db8:2::1/64  |
+# | |  + BR1 (802.1q)                  |                    2001:db8:4::1/64  |
 # | |    vid 555 pvid untagged         |                                      |
 # | |    192.0.2.2/28                  |                                      |
+# | |    192.0.2.18/28                 |                                      |
 # | |    2001:db8:1::2/64              |                                      |
+# | |    2001:db8:3::2/64              |                                      |
 # | +----------------------------------+                                      |
 # +---------------------------------------------------------------------------+
 
@@ -27,6 +30,14 @@ ALL_TESTS="
 	ping_ipv4
 	ping_ipv6
 	vlan
+	config_777
+	ping_ipv4_fails
+	ping_ipv6_fails
+	ping_ipv4_777
+	ping_ipv6_777
+	config_555
+	ping_ipv4
+	ping_ipv6
 "
 NUM_NETIFS=4
 source lib.sh
@@ -34,31 +45,47 @@ source lib.sh
 h1_create()
 {
 	simple_if_init $h1
+
 	vlan_create $h1 555 v$h1 192.0.2.1/28 2001:db8:1::1/64
 	ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2
 	ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+
+	vlan_create $h1 777 v$h1 192.0.2.17/28 2001:db8:3::1/64
+	ip -4 route add 192.0.2.144/28 vrf v$h1 nexthop via 192.0.2.18
+	ip -6 route add 2001:db8:4::/64 vrf v$h1 nexthop via 2001:db8:3::2
 }
 
 h1_destroy()
 {
+	ip -6 route del 2001:db8:4::/64 vrf v$h1
+	ip -4 route del 192.0.2.144/28 vrf v$h1
+	vlan_destroy $h1 777
+
 	ip -6 route del 2001:db8:2::/64 vrf v$h1
 	ip -4 route del 192.0.2.128/28 vrf v$h1
 	vlan_destroy $h1 555
+
 	simple_if_fini $h1
 }
 
 h2_create()
 {
-	simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64
+	simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 \
+			   192.0.2.146/28 2001:db8:4::2/64
 	ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129
+	ip -4 route add 192.0.2.16/28 vrf v$h2 nexthop via 192.0.2.145
 	ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+	ip -6 route add 2001:db8:3::/64 vrf v$h2 nexthop via 2001:db8:4::1
 }
 
 h2_destroy()
 {
+	ip -6 route del 2001:db8:3::/64 vrf v$h2
 	ip -6 route del 2001:db8:1::/64 vrf v$h2
+	ip -4 route del 192.0.2.16/28 vrf v$h2
 	ip -4 route del 192.0.2.0/28 vrf v$h2
-	simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64
+	simple_if_fini $h2 192.0.2.146/28 2001:db8:4::2/64 \
+			   192.0.2.130/28 2001:db8:2::2/64
 }
 
 router_create()
@@ -71,18 +98,23 @@ router_create()
 
 	bridge vlan add dev br1 vid 555 self pvid untagged
 	bridge vlan add dev $swp1 vid 555
+	bridge vlan add dev $swp1 vid 777
 
 	__addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+	__addr_add_del br1 add 192.0.2.18/28 2001:db8:3::2/64
 
 	ip link set dev $swp2 up
 	__addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64
+	__addr_add_del $swp2 add 192.0.2.145/28 2001:db8:4::1/64
 }
 
 router_destroy()
 {
+	__addr_add_del $swp2 del 192.0.2.145/28 2001:db8:4::1/64
 	__addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64
 	ip link set dev $swp2 down
 
+	__addr_add_del br1 del 192.0.2.18/28 2001:db8:3::2/64
 	__addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
 	ip link set dev $swp1 down
 	ip link set dev $swp1 nomaster
@@ -108,6 +140,24 @@ setup_prepare()
 	forwarding_enable
 }
 
+config_555()
+{
+	log_info "Configure VLAN 555 as PVID"
+
+	bridge vlan add dev br1 vid 555 self pvid untagged
+	bridge vlan del dev br1 vid 777 self
+	sleep 2
+}
+
+config_777()
+{
+	log_info "Configure VLAN 777 as PVID"
+
+	bridge vlan add dev br1 vid 777 self pvid untagged
+	bridge vlan del dev br1 vid 555 self
+	sleep 2
+}
+
 cleanup()
 {
 	pre_cleanup
@@ -136,12 +186,32 @@ vlan()
 
 ping_ipv4()
 {
-	ping_test $h1 192.0.2.130
+	ping_test $h1.555 192.0.2.130
 }
 
 ping_ipv6()
 {
-	ping6_test $h1 2001:db8:2::2
+	ping6_test $h1.555 2001:db8:2::2
+}
+
+ping_ipv4_fails()
+{
+	ping_test_fails $h1.555 192.0.2.130 ": via 555"
+}
+
+ping_ipv6_fails()
+{
+	ping6_test_fails $h1.555 2001:db8:2::2 ": via 555"
+}
+
+ping_ipv4_777()
+{
+	ping_test $h1.777 192.0.2.146 ": via 777"
+}
+
+ping_ipv6_777()
+{
+	ping6_test $h1.777 2001:db8:4::2 ": via 777"
 }
 
 trap cleanup EXIT
-- 
GitLab


From b0307b77265bc8e2f4d2ecea3225ed2de8565a70 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:33 +0200
Subject: [PATCH 0142/1806] selftests: router_bridge_vlan_upper_pvid: Add a new
 selftest

This tests whether changes to PVID that coincide with an existing VLAN
upper throw off forwarding. This selftests is specifically geared towards
offloading drivers, but since there's nothing HW-specific in the test
itself (it absolutely is supposed to pass on SW datapath), it is put into
the generic forwarding directory.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/forwarding/Makefile |   1 +
 .../router_bridge_vlan_upper_pvid.sh          | 171 ++++++++++++++++++
 2 files changed, 172 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_bridge_vlan_upper_pvid.sh

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index f49c6c3f6520a..1a21990d0864e 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -65,6 +65,7 @@ TEST_PROGS = bridge_igmp.sh \
 	q_in_vni.sh \
 	router_bridge.sh \
 	router_bridge_vlan.sh \
+	router_bridge_vlan_upper_pvid.sh \
 	router_broadcast.sh \
 	router_mpath_nh_res.sh \
 	router_mpath_nh.sh \
diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper_pvid.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper_pvid.sh
new file mode 100755
index 0000000000000..1385584524022
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper_pvid.sh
@@ -0,0 +1,171 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +----------------------------+
+# |                   H1 (vrf) |
+# |   + $h1.10                 |                      +----------------------+
+# |   | 192.0.2.1/28           |                      |             H2 (vrf) |
+# |   | 2001:db8:1::1/64       |                      |  + $h2               |
+# |   |                        |                      |  | 192.0.2.130/28    |
+# |   + $h1                    |                      |  | 2001:db8:2::2/64  |
+# +---|------------------------+                      +--|-------------------+
+#     |                                                  |
+# +---|--------------------------------------------------|-------------------+
+# |   |                            router (main VRF)     |                   |
+# | +-|--------------------------+                       + $swp2             |
+# | | + $swp1      BR1 (802.1q)  |                         192.0.2.129/28    |
+# | +-----+----------------------+                         2001:db8:2::1/64  |
+# |       |                                                                  |
+# |       + br1.10                                                           |
+# |         192.0.2.2/28                                                     |
+# |         2001:db8:1::2/64                                                 |
+# +--------------------------------------------------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	pvid_set_unset
+	ping_ipv4
+	ping_ipv6
+	pvid_set_move
+	ping_ipv4
+	ping_ipv6
+"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+	vlan_create $h1 10 v$h1 192.0.2.1/28 2001:db8:1::1/64
+	ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2
+	ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip -6 route del 2001:db8:2::/64 vrf v$h1
+	ip -4 route del 192.0.2.128/28 vrf v$h1
+	vlan_destroy $h1 10
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64
+	ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129
+	ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip -6 route del 2001:db8:1::/64 vrf v$h2
+	ip -4 route del 192.0.2.0/28 vrf v$h2
+	simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64
+}
+
+router_create()
+{
+	ip link add name br1 address $(mac_get $swp1) \
+		type bridge vlan_filtering 1 vlan_default_pvid 0
+	ip link set dev br1 up
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 up
+	__addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64
+
+	bridge vlan add dev br1 vid 10 self
+	bridge vlan add dev $swp1 vid 10
+	vlan_create br1 10 "" 192.0.2.2/28 2001:db8:1::2/64
+}
+
+router_destroy()
+{
+	vlan_destroy br1 10
+	bridge vlan del dev $swp1 vid 10
+	bridge vlan del dev br1 vid 10 self
+
+	__addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64
+	ip link set dev $swp2 down
+
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+
+	ip link del dev br1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+pvid_set_unset()
+{
+	log_info "Set and unset PVID on VLAN 10"
+
+	bridge vlan add dev br1 vid 10 pvid self
+	sleep 1
+	bridge vlan add dev br1 vid 10 self
+}
+
+pvid_set_move()
+{
+	log_info "Set PVID on VLAN 10, then move it to VLAN 20"
+
+	bridge vlan add dev br1 vid 10 pvid self
+	sleep 1
+	bridge vlan add dev br1 vid 20 pvid self
+}
+
+shuffle_vlan()
+{
+	log_info ""
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.130
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From 9cbb3da4f4f7c2851df2ed3548263718e99c281a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 13 Jul 2023 18:15:34 +0200
Subject: [PATCH 0143/1806] selftests: router_bridge_pvid_vlan_upper: Add a new
 selftest

This tests whether addition and deletion of a VLAN upper that coincides
with the current PVID setting throws off forwarding.

This selftests is specifically geared towards offloading drivers. In
particular, mlxsw used to fail this selftest, and an earlier patch in this
patchset fixes the issue. However, there's nothing HW-specific in the test
itself (it absolutely is supposed to pass on SW datapath), and therefore it
is put into the generic forwarding directory.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/forwarding/Makefile |   1 +
 .../router_bridge_pvid_vlan_upper.sh          | 155 ++++++++++++++++++
 2 files changed, 156 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_bridge_pvid_vlan_upper.sh

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 1a21990d0864e..2d8bb72762a47 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -65,6 +65,7 @@ TEST_PROGS = bridge_igmp.sh \
 	q_in_vni.sh \
 	router_bridge.sh \
 	router_bridge_vlan.sh \
+	router_bridge_pvid_vlan_upper.sh \
 	router_bridge_vlan_upper_pvid.sh \
 	router_broadcast.sh \
 	router_mpath_nh_res.sh \
diff --git a/tools/testing/selftests/net/forwarding/router_bridge_pvid_vlan_upper.sh b/tools/testing/selftests/net/forwarding/router_bridge_pvid_vlan_upper.sh
new file mode 100755
index 0000000000000..76e4941fef736
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_bridge_pvid_vlan_upper.sh
@@ -0,0 +1,155 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +----------------------------+
+# |                   H1 (vrf) |
+# |   + $h1.10                 |                      +----------------------+
+# |   | 192.0.2.1/28           |                      |             H2 (vrf) |
+# |   | 2001:db8:1::1/64       |                      |  + $h2               |
+# |   |                        |                      |  | 192.0.2.130/28    |
+# |   + $h1                    |                      |  | 2001:db8:2::2/64  |
+# +---|------------------------+                      +--|-------------------+
+#     |                                                  |
+# +---|--------------------------------------------------|-------------------+
+# |   |                            router (main VRF)     |                   |
+# | +-|----------------------------------+               + $swp2             |
+# | | + $swp1      BR1 (802.1q, pvid=10) |                 192.0.2.129/28    |
+# | |              192.0.2.2/28          |                 2001:db8:2::1/64  |
+# | |              2001:db8:1::2/64      |                                   |
+# | +------------------------------------+                                   |
+# +--------------------------------------------------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	shuffle_pvid
+	ping_ipv4
+	ping_ipv6
+"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+	vlan_create $h1 10 v$h1 192.0.2.1/28 2001:db8:1::1/64
+	ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2
+	ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip -6 route del 2001:db8:2::/64 vrf v$h1
+	ip -4 route del 192.0.2.128/28 vrf v$h1
+	vlan_destroy $h1 10
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64
+	ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129
+	ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip -6 route del 2001:db8:1::/64 vrf v$h2
+	ip -4 route del 192.0.2.0/28 vrf v$h2
+	simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64
+}
+
+router_create()
+{
+	ip link add name br1 address $(mac_get $swp1) \
+		type bridge vlan_filtering 1 vlan_default_pvid 0
+	ip link set dev br1 up
+	__addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 up
+	__addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64
+
+	bridge vlan add dev br1 vid 10 pvid untagged self
+	bridge vlan add dev $swp1 vid 10
+}
+
+router_destroy()
+{
+	bridge vlan del dev $swp1 vid 10
+	bridge vlan del dev br1 vid 10 self
+
+	__addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64
+	ip link set dev $swp2 down
+
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+
+	__addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
+	ip link del dev br1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+shuffle_pvid()
+{
+	log_info "Add and remove VLAN upper for PVID VLAN"
+
+	# Adding and removing a VLAN upper for the PVID VLAN shouldn't change
+	# anything. The address is arbitrary, just to make sure it will be an L3
+	# netdevice.
+	vlan_create br1 10 "" 192.0.2.33/28
+	sleep 1
+	vlan_destroy br1 10
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.130
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From 68af900072c157c0cdce0256968edd15067e1e5a Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 13 Jul 2023 17:54:37 +0200
Subject: [PATCH 0144/1806] gve: trivial spell fix Recive to Receive

Spotted this trivial spell mistake while casually reading
the google GVE driver code.

Signed-off-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/google/gve/gve_desc.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve_desc.h b/drivers/net/ethernet/google/gve/gve_desc.h
index f4ae9e19b8443..c2874cdcf40cb 100644
--- a/drivers/net/ethernet/google/gve/gve_desc.h
+++ b/drivers/net/ethernet/google/gve/gve_desc.h
@@ -105,10 +105,10 @@ union gve_rx_data_slot {
 	__be64 addr;
 };
 
-/* GVE Recive Packet Descriptor Seq No */
+/* GVE Receive Packet Descriptor Seq No */
 #define GVE_SEQNO(x) (be16_to_cpu(x) & 0x7)
 
-/* GVE Recive Packet Descriptor Flags */
+/* GVE Receive Packet Descriptor Flags */
 #define GVE_RXFLG(x)	cpu_to_be16(1 << (3 + (x)))
 #define	GVE_RXF_FRAG		GVE_RXFLG(3)	/* IP Fragment			*/
 #define	GVE_RXF_IPV4		GVE_RXFLG(4)	/* IPv4				*/
-- 
GitLab


From df84f0ce569dbec8cb4895a9aafab53fc9306320 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 13 Jul 2023 16:57:54 +0200
Subject: [PATCH 0145/1806] i40e: Add helper for VF inited state check with
 timeout

Move the check for VF inited state (with optional up-to 300ms
timeout to separate helper i40e_check_vf_init_timeout() that
will be used in the following commit.

Tested-by: Ma Yuying <yuma@redhat.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../ethernet/intel/i40e/i40e_virtchnl_pf.c    | 49 +++++++++++++------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index be59ba3774e15..b203465357afb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -4304,6 +4304,38 @@ err_out:
 	return ret;
 }
 
+/**
+ * i40e_check_vf_init_timeout
+ * @vf: the virtual function
+ *
+ * Check that the VF's initialization was successfully done and if not
+ * wait up to 300ms for its finish.
+ *
+ * Returns true when VF is initialized, false on timeout
+ **/
+static bool i40e_check_vf_init_timeout(struct i40e_vf *vf)
+{
+	int i;
+
+	/* When the VF is resetting wait until it is done.
+	 * It can take up to 200 milliseconds, but wait for
+	 * up to 300 milliseconds to be safe.
+	 */
+	for (i = 0; i < 15; i++) {
+		if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states))
+			return true;
+		msleep(20);
+	}
+
+	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
+		dev_err(&vf->pf->pdev->dev,
+			"VF %d still in reset. Try again.\n", vf->vf_id);
+		return false;
+	}
+
+	return true;
+}
+
 /**
  * i40e_ndo_set_vf_mac
  * @netdev: network interface device structure
@@ -4322,7 +4354,6 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	int ret = 0;
 	struct hlist_node *h;
 	int bkt;
-	u8 i;
 
 	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
 		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
@@ -4335,21 +4366,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 		goto error_param;
 
 	vf = &pf->vf[vf_id];
-
-	/* When the VF is resetting wait until it is done.
-	 * It can take up to 200 milliseconds,
-	 * but wait for up to 300 milliseconds to be safe.
-	 * Acquire the VSI pointer only after the VF has been
-	 * properly initialized.
-	 */
-	for (i = 0; i < 15; i++) {
-		if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states))
-			break;
-		msleep(20);
-	}
-	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
-		dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
-			vf_id);
+	if (!i40e_check_vf_init_timeout(vf)) {
 		ret = -EAGAIN;
 		goto error_param;
 	}
-- 
GitLab


From efb6f4a35954de375a74daf9770fe6b634f6ca56 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 13 Jul 2023 16:57:55 +0200
Subject: [PATCH 0146/1806] i40e: Wait for pending VF reset in VF set callbacks

Commit 028daf80117376 ("i40e: Fix attach VF to VM issue") fixed
a race between i40e_ndo_set_vf_mac() and i40e_reset_vf() during
an attachment of VF device to VM. This issue is not related to
setting MAC address only but also VLAN assignment to particular
VF because the newer libvirt sets configured MAC address as well
as an optional VLAN. The same behavior is also for i40e's
.ndo_set_vf_rate and .ndo_set_vf_spoofchk where the callbacks
just check if the VF was initialized but not wait for the finish
of pending reset.

Reproducer:
[root@host ~]# virsh attach-interface guest hostdev --managed 0000:02:02.0 --mac 52:54:00:b4:aa:bb
error: Failed to attach interface
error: Cannot set interface MAC/vlanid to 52:54:00:b4:aa:bb/0 for ifname enp2s0f0 vf 0: Resource temporarily unavailable

Fix this issue by using i40e_check_vf_init_timeout() helper to check
whether a reset of particular VF was finished in i40e's
.ndo_set_vf_vlan, .ndo_set_vf_rate and .ndo_set_vf_spoofchk callbacks.

Tested-by: Ma Yuying <yuma@redhat.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/i40e/i40e_virtchnl_pf.c   | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index b203465357afb..398fb4854cbe0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -4468,13 +4468,11 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 	}
 
 	vf = &pf->vf[vf_id];
-	vsi = pf->vsi[vf->lan_vsi_idx];
-	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
-		dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
-			vf_id);
+	if (!i40e_check_vf_init_timeout(vf)) {
 		ret = -EAGAIN;
 		goto error_pvid;
 	}
+	vsi = pf->vsi[vf->lan_vsi_idx];
 
 	if (le16_to_cpu(vsi->info.pvid) == vlanprio)
 		/* duplicate request, so just return success */
@@ -4618,13 +4616,11 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
 	}
 
 	vf = &pf->vf[vf_id];
-	vsi = pf->vsi[vf->lan_vsi_idx];
-	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
-		dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
-			vf_id);
+	if (!i40e_check_vf_init_timeout(vf)) {
 		ret = -EAGAIN;
 		goto error;
 	}
+	vsi = pf->vsi[vf->lan_vsi_idx];
 
 	ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate);
 	if (ret)
@@ -4791,9 +4787,7 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable)
 	}
 
 	vf = &(pf->vf[vf_id]);
-	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
-		dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
-			vf_id);
+	if (!i40e_check_vf_init_timeout(vf)) {
 		ret = -EAGAIN;
 		goto out;
 	}
-- 
GitLab


From f08469d0f664ff7b22f91871fa77bc59f8f7cec8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cs=C3=B3k=C3=A1s=20Bence?= <Csokas.Bence@prolan.hu>
Date: Thu, 13 Jul 2023 11:09:33 +0000
Subject: [PATCH 0147/1806] net: fec: Refactor: rename `adapter` to `fep`
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename local `struct fec_enet_private *adapter` to `fep` in `fec_ptp_gettime()` to match the rest of the driver

Signed-off-by: Csókás Bence <csokas.bence@prolan.hu>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_ptp.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index ab86bb8562ef0..afc658d2c2711 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -443,21 +443,21 @@ static int fec_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
  */
 static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 {
-	struct fec_enet_private *adapter =
+	struct fec_enet_private *fep =
 	    container_of(ptp, struct fec_enet_private, ptp_caps);
 	u64 ns;
 	unsigned long flags;
 
-	mutex_lock(&adapter->ptp_clk_mutex);
+	mutex_lock(&fep->ptp_clk_mutex);
 	/* Check the ptp clock */
-	if (!adapter->ptp_clk_on) {
-		mutex_unlock(&adapter->ptp_clk_mutex);
+	if (!fep->ptp_clk_on) {
+		mutex_unlock(&fep->ptp_clk_mutex);
 		return -EINVAL;
 	}
-	spin_lock_irqsave(&adapter->tmreg_lock, flags);
-	ns = timecounter_read(&adapter->tc);
-	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
-	mutex_unlock(&adapter->ptp_clk_mutex);
+	spin_lock_irqsave(&fep->tmreg_lock, flags);
+	ns = timecounter_read(&fep->tc);
+	spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+	mutex_unlock(&fep->ptp_clk_mutex);
 
 	*ts = ns_to_timespec64(ns);
 
-- 
GitLab


From 27312c43472bf367aad476ed0b48894063eeb845 Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 13 Jul 2023 15:18:56 -0700
Subject: [PATCH 0148/1806] dt-bindings: net: brcm,unimac-mdio: Add asp-v2.0

The ASP 2.0 Ethernet controller uses a brcm unimac.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml
index 0be426ee1e44f..6684810fcbf01 100644
--- a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml
+++ b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml
@@ -22,6 +22,8 @@ properties:
       - brcm,genet-mdio-v3
       - brcm,genet-mdio-v4
       - brcm,genet-mdio-v5
+      - brcm,asp-v2.0-mdio
+      - brcm,asp-v2.1-mdio
       - brcm,unimac-mdio
 
   reg:
-- 
GitLab


From a29401be8c697c0366a2e1ba50c629193bf25d71 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <florian.fainelli@broadcom.com>
Date: Thu, 13 Jul 2023 15:18:57 -0700
Subject: [PATCH 0149/1806] dt-bindings: net: Brcm ASP 2.0 Ethernet controller

Add a binding document for the Broadcom ASP 2.0 Ethernet
controller.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../bindings/net/brcm,asp-v2.0.yaml           | 155 ++++++++++++++++++
 1 file changed, 155 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml

diff --git a/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml b/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml
new file mode 100644
index 0000000000000..aa3162c74833b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml
@@ -0,0 +1,155 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/brcm,asp-v2.0.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Broadcom ASP 2.0 Ethernet controller
+
+maintainers:
+  - Justin Chen <justin.chen@broadcom.com>
+  - Florian Fainelli <florian.fainelli@broadcom.com>
+
+description: Broadcom Ethernet controller first introduced with 72165
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - brcm,bcm74165-asp
+          - const: brcm,asp-v2.1
+      - items:
+          - enum:
+              - brcm,bcm72165-asp
+          - const: brcm,asp-v2.0
+
+  "#address-cells":
+    const: 1
+  "#size-cells":
+    const: 1
+
+  reg:
+    maxItems: 1
+
+  ranges: true
+
+  interrupts:
+    minItems: 1
+    items:
+      - description: RX/TX interrupt
+      - description: Port 0 Wake-on-LAN
+      - description: Port 1 Wake-on-LAN
+
+  clocks:
+    maxItems: 1
+
+  ethernet-ports:
+    type: object
+    properties:
+      "#address-cells":
+        const: 1
+      "#size-cells":
+        const: 0
+
+    patternProperties:
+      "^port@[0-9]+$":
+        type: object
+
+        $ref: ethernet-controller.yaml#
+
+        unevaluatedProperties: false
+
+        properties:
+          reg:
+            maxItems: 1
+            description: Port number
+
+          brcm,channel:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            description: |
+              ASP Channel Number
+
+              The depacketizer channel that consumes packets from
+              the unimac/port.
+
+        required:
+          - reg
+          - brcm,channel
+
+    additionalProperties: false
+
+patternProperties:
+  "^mdio@[0-9a-f]+$":
+    type: object
+    $ref: brcm,unimac-mdio.yaml
+
+    description:
+      ASP internal UniMAC MDIO bus
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - ranges
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    ethernet@9c00000 {
+        compatible = "brcm,bcm72165-asp", "brcm,asp-v2.0";
+        reg = <0x9c00000 0x1fff14>;
+        interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
+        ranges = <0x0 0x9c00000 0x1fff14>;
+        clocks = <&scmi 14>;
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        mdio@c614 {
+            compatible = "brcm,asp-v2.0-mdio";
+            reg = <0xc614 0x8>;
+            reg-names = "mdio";
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            phy0: ethernet-phy@1 {
+                reg = <1>;
+            };
+       };
+
+        mdio@ce14 {
+            compatible = "brcm,asp-v2.0-mdio";
+            reg = <0xce14 0x8>;
+            reg-names = "mdio";
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            phy1: ethernet-phy@1 {
+                reg = <1>;
+            };
+        };
+
+        ethernet-ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                reg = <0>;
+                brcm,channel = <8>;
+                phy-mode = "rgmii";
+                phy-handle = <&phy0>;
+            };
+
+            port@1 {
+                reg = <1>;
+                brcm,channel = <9>;
+                phy-mode = "rgmii";
+                phy-handle = <&phy1>;
+            };
+        };
+    };
-- 
GitLab


From 490cb412007de593e07c1d3e2b1ec4233886707c Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 13 Jul 2023 15:18:58 -0700
Subject: [PATCH 0150/1806] net: bcmasp: Add support for ASP2.0 Ethernet
 controller

Add support for the Broadcom ASP 2.0 Ethernet controller which is first
introduced with 72165. This controller features two distinct Ethernet
ports that can be independently operated.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/Kconfig         |   11 +
 drivers/net/ethernet/broadcom/Makefile        |    1 +
 drivers/net/ethernet/broadcom/asp2/Makefile   |    2 +
 drivers/net/ethernet/broadcom/asp2/bcmasp.c   |  696 +++++++++
 drivers/net/ethernet/broadcom/asp2/bcmasp.h   |  503 ++++++
 .../ethernet/broadcom/asp2/bcmasp_ethtool.c   |   40 +
 .../net/ethernet/broadcom/asp2/bcmasp_intf.c  | 1342 +++++++++++++++++
 .../ethernet/broadcom/asp2/bcmasp_intf_defs.h |  196 +++
 8 files changed, 2791 insertions(+)
 create mode 100644 drivers/net/ethernet/broadcom/asp2/Makefile
 create mode 100644 drivers/net/ethernet/broadcom/asp2/bcmasp.c
 create mode 100644 drivers/net/ethernet/broadcom/asp2/bcmasp.h
 create mode 100644 drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
 create mode 100644 drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
 create mode 100644 drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 948586bf1b5b2..d4166141145d6 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -255,4 +255,15 @@ config BNXT_HWMON
 	  Say Y if you want to expose the thermal sensor data on NetXtreme-C/E
 	  devices, via the hwmon sysfs interface.
 
+config BCMASP
+	tristate "Broadcom ASP 2.0 Ethernet support"
+	default ARCH_BRCMSTB
+	depends on OF
+	select MII
+	select PHYLIB
+	select MDIO_BCM_UNIMAC
+	help
+	  This configuration enables the Broadcom ASP 2.0 Ethernet controller
+	  driver which is present in Broadcom STB SoCs such as 72165.
+
 endif # NET_VENDOR_BROADCOM
diff --git a/drivers/net/ethernet/broadcom/Makefile b/drivers/net/ethernet/broadcom/Makefile
index 0ddfb5b5d53ca..bac5cb6ad0cd2 100644
--- a/drivers/net/ethernet/broadcom/Makefile
+++ b/drivers/net/ethernet/broadcom/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_BGMAC_BCMA) += bgmac-bcma.o bgmac-bcma-mdio.o
 obj-$(CONFIG_BGMAC_PLATFORM) += bgmac-platform.o
 obj-$(CONFIG_SYSTEMPORT) += bcmsysport.o
 obj-$(CONFIG_BNXT) += bnxt/
+obj-$(CONFIG_BCMASP) += asp2/
diff --git a/drivers/net/ethernet/broadcom/asp2/Makefile b/drivers/net/ethernet/broadcom/asp2/Makefile
new file mode 100644
index 0000000000000..e07550315f83e
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/asp2/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_BCMASP) += bcm-asp.o
+bcm-asp-objs := bcmasp.o bcmasp_intf.o bcmasp_ethtool.o
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
new file mode 100644
index 0000000000000..83494641b545c
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -0,0 +1,696 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Broadcom STB ASP 2.0 Driver
+ *
+ * Copyright (c) 2023 Broadcom
+ */
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/clk.h>
+
+#include "bcmasp.h"
+#include "bcmasp_intf_defs.h"
+
+static void _intr2_mask_clear(struct bcmasp_priv *priv, u32 mask)
+{
+	intr2_core_wl(priv, mask, ASP_INTR2_MASK_CLEAR);
+	priv->irq_mask &= ~mask;
+}
+
+static void _intr2_mask_set(struct bcmasp_priv *priv, u32 mask)
+{
+	intr2_core_wl(priv, mask, ASP_INTR2_MASK_SET);
+	priv->irq_mask |= mask;
+}
+
+void bcmasp_enable_tx_irq(struct bcmasp_intf *intf, int en)
+{
+	struct bcmasp_priv *priv = intf->parent;
+
+	if (en)
+		_intr2_mask_clear(priv, ASP_INTR2_TX_DESC(intf->channel));
+	else
+		_intr2_mask_set(priv, ASP_INTR2_TX_DESC(intf->channel));
+}
+EXPORT_SYMBOL_GPL(bcmasp_enable_tx_irq);
+
+void bcmasp_enable_rx_irq(struct bcmasp_intf *intf, int en)
+{
+	struct bcmasp_priv *priv = intf->parent;
+
+	if (en)
+		_intr2_mask_clear(priv, ASP_INTR2_RX_ECH(intf->channel));
+	else
+		_intr2_mask_set(priv, ASP_INTR2_RX_ECH(intf->channel));
+}
+EXPORT_SYMBOL_GPL(bcmasp_enable_rx_irq);
+
+static void bcmasp_intr2_mask_set_all(struct bcmasp_priv *priv)
+{
+	_intr2_mask_set(priv, 0xffffffff);
+	priv->irq_mask = 0xffffffff;
+}
+
+static void bcmasp_intr2_clear_all(struct bcmasp_priv *priv)
+{
+	intr2_core_wl(priv, 0xffffffff, ASP_INTR2_CLEAR);
+}
+
+static void bcmasp_intr2_handling(struct bcmasp_intf *intf, u32 status)
+{
+	if (status & ASP_INTR2_RX_ECH(intf->channel)) {
+		if (likely(napi_schedule_prep(&intf->rx_napi))) {
+			bcmasp_enable_rx_irq(intf, 0);
+			__napi_schedule_irqoff(&intf->rx_napi);
+		}
+	}
+
+	if (status & ASP_INTR2_TX_DESC(intf->channel)) {
+		if (likely(napi_schedule_prep(&intf->tx_napi))) {
+			bcmasp_enable_tx_irq(intf, 0);
+			__napi_schedule_irqoff(&intf->tx_napi);
+		}
+	}
+}
+
+static irqreturn_t bcmasp_isr(int irq, void *data)
+{
+	struct bcmasp_priv *priv = data;
+	struct bcmasp_intf *intf;
+	u32 status;
+
+	status = intr2_core_rl(priv, ASP_INTR2_STATUS) &
+		~intr2_core_rl(priv, ASP_INTR2_MASK_STATUS);
+
+	intr2_core_wl(priv, status, ASP_INTR2_CLEAR);
+
+	if (unlikely(status == 0)) {
+		dev_warn(&priv->pdev->dev, "l2 spurious interrupt\n");
+		return IRQ_NONE;
+	}
+
+	/* Handle intferfaces */
+	list_for_each_entry(intf, &priv->intfs, list)
+		bcmasp_intr2_handling(intf, status);
+
+	return IRQ_HANDLED;
+}
+
+void bcmasp_flush_rx_port(struct bcmasp_intf *intf)
+{
+	struct bcmasp_priv *priv = intf->parent;
+	u32 mask;
+
+	switch (intf->port) {
+	case 0:
+		mask = ASP_CTRL_UMAC0_FLUSH_MASK;
+		break;
+	case 1:
+		mask = ASP_CTRL_UMAC1_FLUSH_MASK;
+		break;
+	case 2:
+		mask = ASP_CTRL_SPB_FLUSH_MASK;
+		break;
+	default:
+		/* Not valid port */
+		return;
+	}
+
+	rx_ctrl_core_wl(priv, mask, priv->hw_info->rx_ctrl_flush);
+}
+
+static void bcmasp_addr_to_uint(unsigned char *addr, u32 *high, u32 *low)
+{
+	*high = (u32)(addr[0] << 8 | addr[1]);
+	*low = (u32)(addr[2] << 24 | addr[3] << 16 | addr[4] << 8 |
+		     addr[5]);
+}
+
+static void bcmasp_set_mda_filter(struct bcmasp_intf *intf,
+				  const unsigned char *addr,
+				  unsigned char *mask,
+				  unsigned int i)
+{
+	struct bcmasp_priv *priv = intf->parent;
+	u32 addr_h, addr_l, mask_h, mask_l;
+
+	/* Set local copy */
+	ether_addr_copy(priv->mda_filters[i].mask, mask);
+	ether_addr_copy(priv->mda_filters[i].addr, addr);
+
+	/* Write to HW */
+	bcmasp_addr_to_uint(priv->mda_filters[i].mask, &mask_h, &mask_l);
+	bcmasp_addr_to_uint(priv->mda_filters[i].addr, &addr_h, &addr_l);
+	rx_filter_core_wl(priv, addr_h, ASP_RX_FILTER_MDA_PAT_H(i));
+	rx_filter_core_wl(priv, addr_l, ASP_RX_FILTER_MDA_PAT_L(i));
+	rx_filter_core_wl(priv, mask_h, ASP_RX_FILTER_MDA_MSK_H(i));
+	rx_filter_core_wl(priv, mask_l, ASP_RX_FILTER_MDA_MSK_L(i));
+}
+
+static void bcmasp_en_mda_filter(struct bcmasp_intf *intf, bool en,
+				 unsigned int i)
+{
+	struct bcmasp_priv *priv = intf->parent;
+
+	if (priv->mda_filters[i].en == en)
+		return;
+
+	priv->mda_filters[i].en = en;
+	priv->mda_filters[i].port = intf->port;
+
+	rx_filter_core_wl(priv, ((intf->channel + 8) |
+			  (en << ASP_RX_FILTER_MDA_CFG_EN_SHIFT) |
+			  ASP_RX_FILTER_MDA_CFG_UMC_SEL(intf->port)),
+			  ASP_RX_FILTER_MDA_CFG(i));
+}
+
+/* There are 32 MDA filters shared between all ports, we reserve 4 filters per
+ * port for the following.
+ * - Promisc: Filter to allow all packets when promisc is enabled
+ * - All Multicast
+ * - Broadcast
+ * - Own address
+ *
+ * The reserved filters are identified as so.
+ * - Promisc: (index * 4) + 0
+ * - All Multicast: (index * 4) + 1
+ * - Broadcast: (index * 4) + 2
+ * - Own address: (index * 4) + 3
+ */
+enum asp_rx_filter_id {
+	ASP_RX_FILTER_MDA_PROMISC = 0,
+	ASP_RX_FILTER_MDA_ALLMULTI,
+	ASP_RX_FILTER_MDA_BROADCAST,
+	ASP_RX_FILTER_MDA_OWN_ADDR,
+	ASP_RX_FILTER_MDA_RES_MAX,
+};
+
+#define ASP_RX_FILT_MDA(intf, name)	(((intf)->index * \
+					  ASP_RX_FILTER_MDA_RES_MAX) \
+					 + ASP_RX_FILTER_MDA_##name)
+
+static int bcmasp_total_res_mda_cnt(struct bcmasp_priv *priv)
+{
+	return list_count_nodes(&priv->intfs) * ASP_RX_FILTER_MDA_RES_MAX;
+}
+
+void bcmasp_set_promisc(struct bcmasp_intf *intf, bool en)
+{
+	unsigned int i = ASP_RX_FILT_MDA(intf, PROMISC);
+	unsigned char promisc[ETH_ALEN];
+
+	eth_zero_addr(promisc);
+	/* Set mask to 00:00:00:00:00:00 to match all packets */
+	bcmasp_set_mda_filter(intf, promisc, promisc, i);
+	bcmasp_en_mda_filter(intf, en, i);
+}
+
+void bcmasp_set_allmulti(struct bcmasp_intf *intf, bool en)
+{
+	unsigned char allmulti[] = {0x01, 0x00, 0x00, 0x00, 0x00, 0x00};
+	unsigned int i = ASP_RX_FILT_MDA(intf, ALLMULTI);
+
+	/* Set mask to 01:00:00:00:00:00 to match all multicast */
+	bcmasp_set_mda_filter(intf, allmulti, allmulti, i);
+	bcmasp_en_mda_filter(intf, en, i);
+}
+
+void bcmasp_set_broad(struct bcmasp_intf *intf, bool en)
+{
+	unsigned int i = ASP_RX_FILT_MDA(intf, BROADCAST);
+	unsigned char addr[ETH_ALEN];
+
+	eth_broadcast_addr(addr);
+	bcmasp_set_mda_filter(intf, addr, addr, i);
+	bcmasp_en_mda_filter(intf, en, i);
+}
+
+void bcmasp_set_oaddr(struct bcmasp_intf *intf, const unsigned char *addr,
+		      bool en)
+{
+	unsigned char mask[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+	unsigned int i = ASP_RX_FILT_MDA(intf, OWN_ADDR);
+
+	bcmasp_set_mda_filter(intf, addr, mask, i);
+	bcmasp_en_mda_filter(intf, en, i);
+}
+
+void bcmasp_disable_all_filters(struct bcmasp_intf *intf)
+{
+	struct bcmasp_priv *priv = intf->parent;
+	unsigned int i;
+	int res_count;
+
+	res_count = bcmasp_total_res_mda_cnt(intf->parent);
+
+	/* Disable all filters held by this port */
+	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+		if (priv->mda_filters[i].en &&
+		    priv->mda_filters[i].port == intf->port)
+			bcmasp_en_mda_filter(intf, 0, i);
+	}
+}
+
+static int bcmasp_combine_set_filter(struct bcmasp_intf *intf,
+				     unsigned char *addr, unsigned char *mask,
+				     int i)
+{
+	struct bcmasp_priv *priv = intf->parent;
+	u64 addr1, addr2, mask1, mask2, mask3;
+
+	/* Switch to u64 to help with the calculations */
+	addr1 = ether_addr_to_u64(priv->mda_filters[i].addr);
+	mask1 = ether_addr_to_u64(priv->mda_filters[i].mask);
+	addr2 = ether_addr_to_u64(addr);
+	mask2 = ether_addr_to_u64(mask);
+
+	/* Check if one filter resides within the other */
+	mask3 = mask1 & mask2;
+	if (mask3 == mask1 && ((addr1 & mask1) == (addr2 & mask1))) {
+		/* Filter 2 resides within filter 1, so everything is good */
+		return 0;
+	} else if (mask3 == mask2 && ((addr1 & mask2) == (addr2 & mask2))) {
+		/* Filter 1 resides within filter 2, so swap filters */
+		bcmasp_set_mda_filter(intf, addr, mask, i);
+		return 0;
+	}
+
+	/* Unable to combine */
+	return -EINVAL;
+}
+
+int bcmasp_set_en_mda_filter(struct bcmasp_intf *intf, unsigned char *addr,
+			     unsigned char *mask)
+{
+	struct bcmasp_priv *priv = intf->parent;
+	int ret, res_count;
+	unsigned int i;
+
+	res_count = bcmasp_total_res_mda_cnt(intf->parent);
+
+	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+		/* If filter not enabled or belongs to another port skip */
+		if (!priv->mda_filters[i].en ||
+		    priv->mda_filters[i].port != intf->port)
+			continue;
+
+		/* Attempt to combine filters */
+		ret = bcmasp_combine_set_filter(intf, addr, mask, i);
+		if (!ret)
+			return 0;
+	}
+
+	/* Create new filter if possible */
+	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+		if (priv->mda_filters[i].en)
+			continue;
+
+		bcmasp_set_mda_filter(intf, addr, mask, i);
+		bcmasp_en_mda_filter(intf, 1, i);
+		return 0;
+	}
+
+	/* No room for new filter */
+	return -EINVAL;
+}
+
+static void bcmasp_core_init_filters(struct bcmasp_priv *priv)
+{
+	unsigned int i;
+
+	/* Disable all filters and reset software view since the HW
+	 * can lose context while in deep sleep suspend states
+	 */
+	for (i = 0; i < NUM_MDA_FILTERS; i++) {
+		rx_filter_core_wl(priv, 0x0, ASP_RX_FILTER_MDA_CFG(i));
+		priv->mda_filters[i].en = 0;
+	}
+
+	/* Top level filter enable bit should be enabled at all times, set
+	 * GEN_WAKE_CLEAR to clear the network filter wake-up which would
+	 * otherwise be sticky
+	 */
+	rx_filter_core_wl(priv, (ASP_RX_FILTER_OPUT_EN |
+			  ASP_RX_FILTER_MDA_EN |
+			  ASP_RX_FILTER_GEN_WK_CLR |
+			  ASP_RX_FILTER_NT_FLT_EN),
+			  ASP_RX_FILTER_BLK_CTRL);
+}
+
+/* ASP core initialization */
+static void bcmasp_core_init(struct bcmasp_priv *priv)
+{
+	tx_analytics_core_wl(priv, 0x0, ASP_TX_ANALYTICS_CTRL);
+	rx_analytics_core_wl(priv, 0x4, ASP_RX_ANALYTICS_CTRL);
+
+	rx_edpkt_core_wl(priv, (ASP_EDPKT_HDR_SZ_128 << ASP_EDPKT_HDR_SZ_SHIFT),
+			 ASP_EDPKT_HDR_CFG);
+	rx_edpkt_core_wl(priv,
+			 (ASP_EDPKT_ENDI_BT_SWP_WD << ASP_EDPKT_ENDI_DESC_SHIFT),
+			 ASP_EDPKT_ENDI);
+
+	rx_edpkt_core_wl(priv, 0x1b, ASP_EDPKT_BURST_BUF_PSCAL_TOUT);
+	rx_edpkt_core_wl(priv, 0x3e8, ASP_EDPKT_BURST_BUF_WRITE_TOUT);
+	rx_edpkt_core_wl(priv, 0x3e8, ASP_EDPKT_BURST_BUF_READ_TOUT);
+
+	rx_edpkt_core_wl(priv, ASP_EDPKT_ENABLE_EN, ASP_EDPKT_ENABLE);
+
+	/* Disable and clear both UniMAC's wake-up interrupts to avoid
+	 * sticky interrupts.
+	 */
+	_intr2_mask_set(priv, ASP_INTR2_UMC0_WAKE | ASP_INTR2_UMC1_WAKE);
+	intr2_core_wl(priv, ASP_INTR2_UMC0_WAKE | ASP_INTR2_UMC1_WAKE,
+		      ASP_INTR2_CLEAR);
+}
+
+static void bcmasp_core_clock_select(struct bcmasp_priv *priv, bool slow)
+{
+	u32 reg;
+
+	reg = ctrl_core_rl(priv, ASP_CTRL_CORE_CLOCK_SELECT);
+	if (slow)
+		reg &= ~ASP_CTRL_CORE_CLOCK_SELECT_MAIN;
+	else
+		reg |= ASP_CTRL_CORE_CLOCK_SELECT_MAIN;
+	ctrl_core_wl(priv, reg, ASP_CTRL_CORE_CLOCK_SELECT);
+}
+
+static void bcmasp_core_clock_set_ll(struct bcmasp_priv *priv, u32 clr, u32 set)
+{
+	u32 reg;
+
+	reg = ctrl_core_rl(priv, ASP_CTRL_CLOCK_CTRL);
+	reg &= ~clr;
+	reg |= set;
+	ctrl_core_wl(priv, reg, ASP_CTRL_CLOCK_CTRL);
+
+	reg = ctrl_core_rl(priv, ASP_CTRL_SCRATCH_0);
+	reg &= ~clr;
+	reg |= set;
+	ctrl_core_wl(priv, reg, ASP_CTRL_SCRATCH_0);
+}
+
+static void bcmasp_core_clock_set(struct bcmasp_priv *priv, u32 clr, u32 set)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->clk_lock, flags);
+	bcmasp_core_clock_set_ll(priv, clr, set);
+	spin_unlock_irqrestore(&priv->clk_lock, flags);
+}
+
+void bcmasp_core_clock_set_intf(struct bcmasp_intf *intf, bool en)
+{
+	u32 intf_mask = ASP_CTRL_CLOCK_CTRL_ASP_RGMII_DIS(intf->port);
+	struct bcmasp_priv *priv = intf->parent;
+	unsigned long flags;
+	u32 reg;
+
+	/* When enabling an interface, if the RX or TX clocks were not enabled,
+	 * enable them. Conversely, while disabling an interface, if this is
+	 * the last one enabled, we can turn off the shared RX and TX clocks as
+	 * well. We control enable bits which is why we test for equality on
+	 * the RGMII clock bit mask.
+	 */
+	spin_lock_irqsave(&priv->clk_lock, flags);
+	if (en) {
+		intf_mask |= ASP_CTRL_CLOCK_CTRL_ASP_TX_DISABLE |
+			     ASP_CTRL_CLOCK_CTRL_ASP_RX_DISABLE;
+		bcmasp_core_clock_set_ll(priv, intf_mask, 0);
+	} else {
+		reg = ctrl_core_rl(priv, ASP_CTRL_SCRATCH_0) | intf_mask;
+		if ((reg & ASP_CTRL_CLOCK_CTRL_ASP_RGMII_MASK) ==
+		    ASP_CTRL_CLOCK_CTRL_ASP_RGMII_MASK)
+			intf_mask |= ASP_CTRL_CLOCK_CTRL_ASP_TX_DISABLE |
+				     ASP_CTRL_CLOCK_CTRL_ASP_RX_DISABLE;
+		bcmasp_core_clock_set_ll(priv, 0, intf_mask);
+	}
+	spin_unlock_irqrestore(&priv->clk_lock, flags);
+}
+
+static struct bcmasp_hw_info v20_hw_info = {
+	.rx_ctrl_flush = ASP_RX_CTRL_FLUSH,
+	.umac2fb = UMAC2FB_OFFSET,
+	.rx_ctrl_fb_out_frame_count = ASP_RX_CTRL_FB_OUT_FRAME_COUNT,
+	.rx_ctrl_fb_filt_out_frame_count = ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT,
+	.rx_ctrl_fb_rx_fifo_depth = ASP_RX_CTRL_FB_RX_FIFO_DEPTH,
+};
+
+static const struct bcmasp_plat_data v20_plat_data = {
+	.hw_info = &v20_hw_info,
+};
+
+static struct bcmasp_hw_info v21_hw_info = {
+	.rx_ctrl_flush = ASP_RX_CTRL_FLUSH_2_1,
+	.umac2fb = UMAC2FB_OFFSET_2_1,
+	.rx_ctrl_fb_out_frame_count = ASP_RX_CTRL_FB_OUT_FRAME_COUNT_2_1,
+	.rx_ctrl_fb_filt_out_frame_count =
+		ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT_2_1,
+	.rx_ctrl_fb_rx_fifo_depth = ASP_RX_CTRL_FB_RX_FIFO_DEPTH_2_1,
+};
+
+static const struct bcmasp_plat_data v21_plat_data = {
+	.hw_info = &v21_hw_info,
+};
+
+static const struct of_device_id bcmasp_of_match[] = {
+	{ .compatible = "brcm,asp-v2.0", .data = &v20_plat_data },
+	{ .compatible = "brcm,asp-v2.1", .data = &v21_plat_data },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, bcmasp_of_match);
+
+static const struct of_device_id bcmasp_mdio_of_match[] = {
+	{ .compatible = "brcm,asp-v2.1-mdio", },
+	{ .compatible = "brcm,asp-v2.0-mdio", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, bcmasp_mdio_of_match);
+
+static void bcmasp_remove_intfs(struct bcmasp_priv *priv)
+{
+	struct bcmasp_intf *intf, *n;
+
+	list_for_each_entry_safe(intf, n, &priv->intfs, list) {
+		list_del(&intf->list);
+		bcmasp_interface_destroy(intf);
+	}
+}
+
+static int bcmasp_probe(struct platform_device *pdev)
+{
+	struct device_node *ports_node, *intf_node;
+	const struct bcmasp_plat_data *pdata;
+	struct device *dev = &pdev->dev;
+	struct bcmasp_priv *priv;
+	struct bcmasp_intf *intf;
+	int ret = 0, count = 0;
+	unsigned int i;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->irq = platform_get_irq(pdev, 0);
+	if (priv->irq <= 0)
+		return dev_err_probe(dev, -EINVAL, "invalid interrupt\n");
+
+	priv->clk = devm_clk_get_optional_enabled(dev, "sw_asp");
+	if (IS_ERR(priv->clk))
+		return dev_err_probe(dev, PTR_ERR(priv->clk),
+				     "failed to request clock\n");
+
+	/* Base from parent node */
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->base))
+		return dev_err_probe(dev, PTR_ERR(priv->base), "failed to iomap\n");
+
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
+	if (ret)
+		return dev_err_probe(dev, ret, "unable to set DMA mask: %d\n", ret);
+
+	dev_set_drvdata(&pdev->dev, priv);
+	priv->pdev = pdev;
+	spin_lock_init(&priv->mda_lock);
+	spin_lock_init(&priv->clk_lock);
+	INIT_LIST_HEAD(&priv->intfs);
+
+	pdata = device_get_match_data(&pdev->dev);
+	if (!pdata)
+		return dev_err_probe(dev, -EINVAL, "unable to find platform data\n");
+
+	priv->hw_info = pdata->hw_info;
+
+	/* Enable all clocks to ensure successful probing */
+	bcmasp_core_clock_set(priv, ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE, 0);
+
+	/* Switch to the main clock */
+	bcmasp_core_clock_select(priv, false);
+
+	bcmasp_intr2_mask_set_all(priv);
+	bcmasp_intr2_clear_all(priv);
+
+	ret = devm_request_irq(&pdev->dev, priv->irq, bcmasp_isr, 0,
+			       pdev->name, priv);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to request ASP interrupt: %d", ret);
+
+	/* Register mdio child nodes */
+	of_platform_populate(dev->of_node, bcmasp_mdio_of_match, NULL, dev);
+
+	/* ASP specific initialization, Needs to be done regardless of
+	 * how many interfaces come up.
+	 */
+	bcmasp_core_init(priv);
+	bcmasp_core_init_filters(priv);
+
+	ports_node = of_find_node_by_name(dev->of_node, "ethernet-ports");
+	if (!ports_node) {
+		dev_warn(dev, "No ports found\n");
+		return -EINVAL;
+	}
+
+	i = 0;
+	for_each_available_child_of_node(ports_node, intf_node) {
+		intf = bcmasp_interface_create(priv, intf_node, i);
+		if (!intf) {
+			dev_err(dev, "Cannot create eth interface %d\n", i);
+			bcmasp_remove_intfs(priv);
+			goto of_put_exit;
+		}
+		list_add_tail(&intf->list, &priv->intfs);
+		i++;
+	}
+
+	/* Drop the clock reference count now and let ndo_open()/ndo_close()
+	 * manage it for us from now on.
+	 */
+	bcmasp_core_clock_set(priv, 0, ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE);
+
+	clk_disable_unprepare(priv->clk);
+
+	/* Now do the registration of the network ports which will take care
+	 * of managing the clock properly.
+	 */
+	list_for_each_entry(intf, &priv->intfs, list) {
+		ret = register_netdev(intf->ndev);
+		if (ret) {
+			netdev_err(intf->ndev,
+				   "failed to register net_device: %d\n", ret);
+			bcmasp_remove_intfs(priv);
+			goto of_put_exit;
+		}
+		count++;
+	}
+
+	dev_info(dev, "Initialized %d port(s)\n", count);
+
+of_put_exit:
+	of_node_put(ports_node);
+	return ret;
+}
+
+static int bcmasp_remove(struct platform_device *pdev)
+{
+	struct bcmasp_priv *priv = dev_get_drvdata(&pdev->dev);
+
+	if (!priv)
+		return 0;
+
+	bcmasp_remove_intfs(priv);
+
+	return 0;
+}
+
+static void bcmasp_shutdown(struct platform_device *pdev)
+{
+	bcmasp_remove(pdev);
+}
+
+static int __maybe_unused bcmasp_suspend(struct device *d)
+{
+	struct bcmasp_priv *priv = dev_get_drvdata(d);
+	struct bcmasp_intf *intf;
+	int ret;
+
+	list_for_each_entry(intf, &priv->intfs, list) {
+		ret = bcmasp_interface_suspend(intf);
+		if (ret)
+			break;
+	}
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return ret;
+
+	/* Whether Wake-on-LAN is enabled or not, we can always disable
+	 * the shared TX clock
+	 */
+	bcmasp_core_clock_set(priv, 0, ASP_CTRL_CLOCK_CTRL_ASP_TX_DISABLE);
+
+	bcmasp_core_clock_select(priv, true);
+
+	clk_disable_unprepare(priv->clk);
+
+	return ret;
+}
+
+static int __maybe_unused bcmasp_resume(struct device *d)
+{
+	struct bcmasp_priv *priv = dev_get_drvdata(d);
+	struct bcmasp_intf *intf;
+	int ret;
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return ret;
+
+	/* Switch to the main clock domain */
+	bcmasp_core_clock_select(priv, false);
+
+	/* Re-enable all clocks for re-initialization */
+	bcmasp_core_clock_set(priv, ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE, 0);
+
+	bcmasp_core_init(priv);
+	bcmasp_core_init_filters(priv);
+
+	/* And disable them to let the network devices take care of them */
+	bcmasp_core_clock_set(priv, 0, ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE);
+
+	clk_disable_unprepare(priv->clk);
+
+	list_for_each_entry(intf, &priv->intfs, list) {
+		ret = bcmasp_interface_resume(intf);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static SIMPLE_DEV_PM_OPS(bcmasp_pm_ops,
+			 bcmasp_suspend, bcmasp_resume);
+
+static struct platform_driver bcmasp_driver = {
+	.probe = bcmasp_probe,
+	.remove = bcmasp_remove,
+	.shutdown = bcmasp_shutdown,
+	.driver = {
+		.name = "brcm,asp-v2",
+		.of_match_table = bcmasp_of_match,
+		.pm = &bcmasp_pm_ops,
+	},
+};
+module_platform_driver(bcmasp_driver);
+
+MODULE_DESCRIPTION("Broadcom ASP 2.0 Ethernet controller driver");
+MODULE_ALIAS("platform:brcm,asp-v2");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
new file mode 100644
index 0000000000000..4fe84d26251df
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
@@ -0,0 +1,503 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BCMASP_H
+#define __BCMASP_H
+
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/io-64-nonatomic-hi-lo.h>
+#include <uapi/linux/ethtool.h>
+
+#define ASP_INTR2_OFFSET			0x1000
+#define  ASP_INTR2_STATUS			0x0
+#define  ASP_INTR2_SET				0x4
+#define  ASP_INTR2_CLEAR			0x8
+#define  ASP_INTR2_MASK_STATUS			0xc
+#define  ASP_INTR2_MASK_SET			0x10
+#define  ASP_INTR2_MASK_CLEAR			0x14
+
+#define ASP_INTR2_RX_ECH(intr)			BIT(intr)
+#define ASP_INTR2_TX_DESC(intr)			BIT((intr) + 14)
+#define ASP_INTR2_UMC0_WAKE			BIT(22)
+#define ASP_INTR2_UMC1_WAKE			BIT(28)
+
+#define ASP_WAKEUP_INTR2_OFFSET			0x1200
+#define  ASP_WAKEUP_INTR2_STATUS		0x0
+#define  ASP_WAKEUP_INTR2_SET			0x4
+#define  ASP_WAKEUP_INTR2_CLEAR			0x8
+#define  ASP_WAKEUP_INTR2_MASK_STATUS		0xc
+#define  ASP_WAKEUP_INTR2_MASK_SET		0x10
+#define  ASP_WAKEUP_INTR2_MASK_CLEAR		0x14
+#define ASP_WAKEUP_INTR2_MPD_0			BIT(0)
+#define ASP_WAKEUP_INTR2_MPD_1			BIT(1)
+#define ASP_WAKEUP_INTR2_FILT_0			BIT(2)
+#define ASP_WAKEUP_INTR2_FILT_1			BIT(3)
+#define ASP_WAKEUP_INTR2_FW			BIT(4)
+
+#define ASP_TX_ANALYTICS_OFFSET			0x4c000
+#define  ASP_TX_ANALYTICS_CTRL			0x0
+
+#define ASP_RX_ANALYTICS_OFFSET			0x98000
+#define  ASP_RX_ANALYTICS_CTRL			0x0
+
+#define ASP_RX_CTRL_OFFSET			0x9f000
+#define ASP_RX_CTRL_UMAC_0_FRAME_COUNT		0x8
+#define ASP_RX_CTRL_UMAC_1_FRAME_COUNT		0xc
+#define ASP_RX_CTRL_FB_0_FRAME_COUNT		0x14
+#define ASP_RX_CTRL_FB_1_FRAME_COUNT		0x18
+#define ASP_RX_CTRL_FB_8_FRAME_COUNT		0x1c
+/* asp2.1 diverges offsets here */
+/* ASP2.0 */
+#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT		0x20
+#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT	0x24
+#define ASP_RX_CTRL_FLUSH			0x28
+#define  ASP_CTRL_UMAC0_FLUSH_MASK		(BIT(0) | BIT(12))
+#define  ASP_CTRL_UMAC1_FLUSH_MASK		(BIT(1) | BIT(13))
+#define  ASP_CTRL_SPB_FLUSH_MASK		(BIT(8) | BIT(20))
+#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH		0x30
+/* ASP2.1 */
+#define ASP_RX_CTRL_FB_9_FRAME_COUNT_2_1	0x20
+#define ASP_RX_CTRL_FB_10_FRAME_COUNT_2_1	0x24
+#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT_2_1	0x28
+#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT_2_1	0x2c
+#define ASP_RX_CTRL_FLUSH_2_1			0x30
+#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH_2_1	0x38
+
+#define ASP_RX_FILTER_OFFSET			0x80000
+#define  ASP_RX_FILTER_BLK_CTRL			0x0
+#define   ASP_RX_FILTER_OPUT_EN			BIT(0)
+#define   ASP_RX_FILTER_MDA_EN			BIT(1)
+#define   ASP_RX_FILTER_LNR_MD			BIT(2)
+#define   ASP_RX_FILTER_GEN_WK_EN		BIT(3)
+#define   ASP_RX_FILTER_GEN_WK_CLR		BIT(4)
+#define   ASP_RX_FILTER_NT_FLT_EN		BIT(5)
+#define  ASP_RX_FILTER_MDA_CFG(sel)		(((sel) * 0x14) + 0x100)
+#define   ASP_RX_FILTER_MDA_CFG_EN_SHIFT	8
+#define   ASP_RX_FILTER_MDA_CFG_UMC_SEL(sel)	((sel) > 1 ? BIT(17) : \
+						 BIT((sel) + 9))
+#define  ASP_RX_FILTER_MDA_PAT_H(sel)		(((sel) * 0x14) + 0x104)
+#define  ASP_RX_FILTER_MDA_PAT_L(sel)		(((sel) * 0x14) + 0x108)
+#define  ASP_RX_FILTER_MDA_MSK_H(sel)		(((sel) * 0x14) + 0x10c)
+#define  ASP_RX_FILTER_MDA_MSK_L(sel)		(((sel) * 0x14) + 0x110)
+#define  ASP_RX_FILTER_MDA_CFG(sel)		(((sel) * 0x14) + 0x100)
+#define  ASP_RX_FILTER_MDA_PAT_H(sel)		(((sel) * 0x14) + 0x104)
+#define  ASP_RX_FILTER_MDA_PAT_L(sel)		(((sel) * 0x14) + 0x108)
+#define  ASP_RX_FILTER_MDA_MSK_H(sel)		(((sel) * 0x14) + 0x10c)
+#define  ASP_RX_FILTER_MDA_MSK_L(sel)		(((sel) * 0x14) + 0x110)
+#define  ASP_RX_FILTER_NET_CFG(sel)		(((sel) * 0xa04) + 0x400)
+#define   ASP_RX_FILTER_NET_CFG_CH(sel)		((sel) << 0)
+#define   ASP_RX_FILTER_NET_CFG_EN		BIT(9)
+#define   ASP_RX_FILTER_NET_CFG_L2_EN		BIT(10)
+#define   ASP_RX_FILTER_NET_CFG_L3_EN		BIT(11)
+#define   ASP_RX_FILTER_NET_CFG_L4_EN		BIT(12)
+#define   ASP_RX_FILTER_NET_CFG_L3_FRM(sel)	((sel) << 13)
+#define   ASP_RX_FILTER_NET_CFG_L4_FRM(sel)	((sel) << 15)
+#define   ASP_RX_FILTER_NET_CFG_UMC(sel)	BIT((sel) + 19)
+#define   ASP_RX_FILTER_NET_CFG_DMA_EN		BIT(27)
+
+#define  ASP_RX_FILTER_NET_OFFSET_MAX		32
+#define  ASP_RX_FILTER_NET_PAT(sel, block, off) \
+		(((sel) * 0xa04) + ((block) * 0x200) + (off) + 0x600)
+#define  ASP_RX_FILTER_NET_MASK(sel, block, off) \
+		(((sel) * 0xa04) + ((block) * 0x200) + (off) + 0x700)
+
+#define  ASP_RX_FILTER_NET_OFFSET(sel)		(((sel) * 0xa04) + 0xe00)
+#define   ASP_RX_FILTER_NET_OFFSET_L2(val)	((val) << 0)
+#define   ASP_RX_FILTER_NET_OFFSET_L3_0(val)	((val) << 8)
+#define   ASP_RX_FILTER_NET_OFFSET_L3_1(val)	((val) << 16)
+#define   ASP_RX_FILTER_NET_OFFSET_L4(val)	((val) << 24)
+
+#define ASP_EDPKT_OFFSET			0x9c000
+#define  ASP_EDPKT_ENABLE			0x4
+#define   ASP_EDPKT_ENABLE_EN			BIT(0)
+#define  ASP_EDPKT_HDR_CFG			0xc
+#define   ASP_EDPKT_HDR_SZ_SHIFT		2
+#define   ASP_EDPKT_HDR_SZ_32			0
+#define   ASP_EDPKT_HDR_SZ_64			1
+#define   ASP_EDPKT_HDR_SZ_96			2
+#define   ASP_EDPKT_HDR_SZ_128			3
+#define ASP_EDPKT_BURST_BUF_PSCAL_TOUT		0x10
+#define ASP_EDPKT_BURST_BUF_WRITE_TOUT		0x14
+#define ASP_EDPKT_BURST_BUF_READ_TOUT		0x18
+#define ASP_EDPKT_RX_TS_COUNTER			0x38
+#define  ASP_EDPKT_ENDI				0x48
+#define   ASP_EDPKT_ENDI_DESC_SHIFT		8
+#define   ASP_EDPKT_ENDI_NO_BT_SWP		0
+#define   ASP_EDPKT_ENDI_BT_SWP_WD		1
+#define ASP_EDPKT_RX_PKT_CNT			0x138
+#define ASP_EDPKT_HDR_EXTR_CNT			0x13c
+#define ASP_EDPKT_HDR_OUT_CNT			0x140
+
+#define ASP_CTRL				0x101000
+#define  ASP_CTRL_ASP_SW_INIT			0x04
+#define   ASP_CTRL_ASP_SW_INIT_ACPUSS_CORE	BIT(0)
+#define   ASP_CTRL_ASP_SW_INIT_ASP_TX		BIT(1)
+#define   ASP_CTRL_ASP_SW_INIT_AS_RX		BIT(2)
+#define   ASP_CTRL_ASP_SW_INIT_ASP_RGMII_UMAC0	BIT(3)
+#define   ASP_CTRL_ASP_SW_INIT_ASP_RGMII_UMAC1	BIT(4)
+#define   ASP_CTRL_ASP_SW_INIT_ASP_XMEMIF	BIT(5)
+#define  ASP_CTRL_CLOCK_CTRL			0x04
+#define   ASP_CTRL_CLOCK_CTRL_ASP_TX_DISABLE	BIT(0)
+#define   ASP_CTRL_CLOCK_CTRL_ASP_RX_DISABLE	BIT(1)
+#define   ASP_CTRL_CLOCK_CTRL_ASP_RGMII_SHIFT	2
+#define   ASP_CTRL_CLOCK_CTRL_ASP_RGMII_MASK	(0x7 << ASP_CTRL_CLOCK_CTRL_ASP_RGMII_SHIFT)
+#define   ASP_CTRL_CLOCK_CTRL_ASP_RGMII_DIS(x)	BIT(ASP_CTRL_CLOCK_CTRL_ASP_RGMII_SHIFT + (x))
+#define   ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE	GENMASK(4, 0)
+#define  ASP_CTRL_CORE_CLOCK_SELECT		0x08
+#define   ASP_CTRL_CORE_CLOCK_SELECT_MAIN	BIT(0)
+#define  ASP_CTRL_SCRATCH_0			0x0c
+
+struct bcmasp_tx_cb {
+	struct sk_buff		*skb;
+	unsigned int		bytes_sent;
+	bool			last;
+
+	DEFINE_DMA_UNMAP_ADDR(dma_addr);
+	DEFINE_DMA_UNMAP_LEN(dma_len);
+};
+
+struct bcmasp_res {
+	/* Per interface resources */
+	/* Port */
+	void __iomem		*umac;
+	void __iomem		*umac2fb;
+	void __iomem		*rgmii;
+
+	/* TX slowpath/configuration */
+	void __iomem		*tx_spb_ctrl;
+	void __iomem		*tx_spb_top;
+	void __iomem		*tx_epkt_core;
+	void __iomem		*tx_pause_ctrl;
+};
+
+#define DESC_ADDR(x)		((x) & GENMASK_ULL(39, 0))
+#define DESC_FLAGS(x)		((x) & GENMASK_ULL(63, 40))
+
+struct bcmasp_desc {
+	u64		buf;
+	#define DESC_CHKSUM	BIT_ULL(40)
+	#define DESC_CRC_ERR	BIT_ULL(41)
+	#define DESC_RX_SYM_ERR	BIT_ULL(42)
+	#define DESC_NO_OCT_ALN BIT_ULL(43)
+	#define DESC_PKT_TRUC	BIT_ULL(44)
+	/*  39:0 (TX/RX) bits 0-39 of buf addr
+	 *    40 (RX) checksum
+	 *    41 (RX) crc_error
+	 *    42 (RX) rx_symbol_error
+	 *    43 (RX) non_octet_aligned
+	 *    44 (RX) pkt_truncated
+	 *    45 Reserved
+	 * 56:46 (RX) mac_filter_id
+	 * 60:57 (RX) rx_port_num (0-unicmac0, 1-unimac1)
+	 *    61 Reserved
+	 * 63:62 (TX) forward CRC, overwrite CRC
+	 */
+	u32		size;
+	u32		flags;
+	#define DESC_INT_EN     BIT(0)
+	#define DESC_SOF	BIT(1)
+	#define DESC_EOF	BIT(2)
+	#define DESC_EPKT_CMD   BIT(3)
+	#define DESC_SCRAM_ST   BIT(8)
+	#define DESC_SCRAM_END  BIT(9)
+	#define DESC_PCPP       BIT(10)
+	#define DESC_PPPP       BIT(11)
+	/*     0 (TX) tx_int_en
+	 *     1 (TX/RX) SOF
+	 *     2 (TX/RX) EOF
+	 *     3 (TX) epkt_command
+	 *   6:4 (TX) PA
+	 *     7 (TX) pause at desc end
+	 *     8 (TX) scram_start
+	 *     9 (TX) scram_end
+	 *    10 (TX) PCPP
+	 *    11 (TX) PPPP
+	 * 14:12 Reserved
+	 *    15 (TX) pid ch Valid
+	 * 19:16 (TX) data_pkt_type
+	 * 32:20 (TX) pid_channel (RX) nw_filter_id
+	 */
+};
+
+struct bcmasp_intf;
+
+struct bcmasp_intf_stats64 {
+	/* Rx Stats */
+	u64_stats_t	rx_packets;
+	u64_stats_t	rx_bytes;
+	u64_stats_t	rx_errors;
+	u64_stats_t	rx_dropped;
+	u64_stats_t	rx_crc_errs;
+	u64_stats_t	rx_sym_errs;
+
+	/* Tx Stats*/
+	u64_stats_t	tx_packets;
+	u64_stats_t	tx_bytes;
+
+	struct u64_stats_sync		syncp;
+};
+
+struct bcmasp_intf_ops {
+	unsigned long (*rx_desc_read)(struct bcmasp_intf *intf);
+	void (*rx_buffer_write)(struct bcmasp_intf *intf, dma_addr_t addr);
+	void (*rx_desc_write)(struct bcmasp_intf *intf, dma_addr_t addr);
+	unsigned long (*tx_read)(struct bcmasp_intf *intf);
+	void (*tx_write)(struct bcmasp_intf *intf, dma_addr_t addr);
+};
+
+struct bcmasp_priv;
+
+struct bcmasp_intf {
+	struct list_head		list;
+	struct net_device		*ndev;
+	struct bcmasp_priv		*parent;
+
+	/* ASP Ch */
+	int				channel;
+	int				port;
+	const struct bcmasp_intf_ops	*ops;
+
+	/* Used for splitting shared resources */
+	int				index;
+
+	struct napi_struct		tx_napi;
+	/* TX ring, starts on a new cacheline boundary */
+	void __iomem			*tx_spb_dma;
+	int				tx_spb_index;
+	int				tx_spb_clean_index;
+	struct bcmasp_desc		*tx_spb_cpu;
+	dma_addr_t			tx_spb_dma_addr;
+	dma_addr_t			tx_spb_dma_valid;
+	dma_addr_t			tx_spb_dma_read;
+	struct bcmasp_tx_cb		*tx_cbs;
+
+	/* RX ring, starts on a new cacheline boundary */
+	void __iomem			*rx_edpkt_cfg;
+	void __iomem			*rx_edpkt_dma;
+	int				rx_edpkt_index;
+	int				rx_buf_order;
+	struct bcmasp_desc		*rx_edpkt_cpu;
+	dma_addr_t			rx_edpkt_dma_addr;
+	dma_addr_t			rx_edpkt_dma_read;
+
+	/* RX buffer prefetcher ring*/
+	void				*rx_ring_cpu;
+	dma_addr_t			rx_ring_dma;
+	dma_addr_t			rx_ring_dma_valid;
+	struct napi_struct		rx_napi;
+
+	struct bcmasp_res		res;
+	unsigned int			crc_fwd;
+
+	/* PHY device */
+	struct device_node		*phy_dn;
+	struct device_node		*ndev_dn;
+	phy_interface_t			phy_interface;
+	bool				internal_phy;
+	int				old_pause;
+	int				old_link;
+	int				old_duplex;
+
+	u32				msg_enable;
+
+	/* Statistics */
+	struct bcmasp_intf_stats64	stats64;
+};
+
+#define NUM_MDA_FILTERS				32
+struct bcmasp_mda_filter {
+	/* Current owner of this filter */
+	int		port;
+	bool		en;
+	u8		addr[ETH_ALEN];
+	u8		mask[ETH_ALEN];
+};
+
+struct bcmasp_hw_info {
+	u32		rx_ctrl_flush;
+	u32		umac2fb;
+	u32		rx_ctrl_fb_out_frame_count;
+	u32		rx_ctrl_fb_filt_out_frame_count;
+	u32		rx_ctrl_fb_rx_fifo_depth;
+};
+
+struct bcmasp_plat_data {
+	struct bcmasp_hw_info		*hw_info;
+};
+
+struct bcmasp_priv {
+	struct platform_device		*pdev;
+	struct clk			*clk;
+
+	int				irq;
+	u32				irq_mask;
+
+	void __iomem			*base;
+	struct	bcmasp_hw_info		*hw_info;
+
+	struct list_head		intfs;
+
+	struct bcmasp_mda_filter	mda_filters[NUM_MDA_FILTERS];
+
+	/* MAC destination address filters lock */
+	spinlock_t			mda_lock;
+
+	/* Protects accesses to ASP_CTRL_CLOCK_CTRL */
+	spinlock_t			clk_lock;
+};
+
+static inline unsigned long bcmasp_intf_rx_desc_read(struct bcmasp_intf *intf)
+{
+	return intf->ops->rx_desc_read(intf);
+}
+
+static inline void bcmasp_intf_rx_buffer_write(struct bcmasp_intf *intf,
+					       dma_addr_t addr)
+{
+	intf->ops->rx_buffer_write(intf, addr);
+}
+
+static inline void bcmasp_intf_rx_desc_write(struct bcmasp_intf *intf,
+					     dma_addr_t addr)
+{
+	intf->ops->rx_desc_write(intf, addr);
+}
+
+static inline unsigned long bcmasp_intf_tx_read(struct bcmasp_intf *intf)
+{
+	return intf->ops->tx_read(intf);
+}
+
+static inline void bcmasp_intf_tx_write(struct bcmasp_intf *intf,
+					dma_addr_t addr)
+{
+	intf->ops->tx_write(intf, addr);
+}
+
+#define __BCMASP_IO_MACRO(name, m)					\
+static inline u32 name##_rl(struct bcmasp_intf *intf, u32 off)		\
+{									\
+	u32 reg = readl_relaxed(intf->m + off);				\
+	return reg;							\
+}									\
+static inline void name##_wl(struct bcmasp_intf *intf, u32 val, u32 off)\
+{									\
+	writel_relaxed(val, intf->m + off);				\
+}
+
+#define BCMASP_IO_MACRO(name)		__BCMASP_IO_MACRO(name, res.name)
+#define BCMASP_FP_IO_MACRO(name)	__BCMASP_IO_MACRO(name, name)
+
+BCMASP_IO_MACRO(umac);
+BCMASP_IO_MACRO(umac2fb);
+BCMASP_IO_MACRO(rgmii);
+BCMASP_FP_IO_MACRO(tx_spb_dma);
+BCMASP_IO_MACRO(tx_spb_ctrl);
+BCMASP_IO_MACRO(tx_spb_top);
+BCMASP_IO_MACRO(tx_epkt_core);
+BCMASP_IO_MACRO(tx_pause_ctrl);
+BCMASP_FP_IO_MACRO(rx_edpkt_dma);
+BCMASP_FP_IO_MACRO(rx_edpkt_cfg);
+
+#define __BCMASP_FP_IO_MACRO_Q(name, m)					\
+static inline u64 name##_rq(struct bcmasp_intf *intf, u32 off)		\
+{									\
+	u64 reg = readq_relaxed(intf->m + off);				\
+	return reg;							\
+}									\
+static inline void name##_wq(struct bcmasp_intf *intf, u64 val, u32 off)\
+{									\
+	writeq_relaxed(val, intf->m + off);				\
+}
+
+#define BCMASP_FP_IO_MACRO_Q(name)	__BCMASP_FP_IO_MACRO_Q(name, name)
+
+BCMASP_FP_IO_MACRO_Q(tx_spb_dma);
+BCMASP_FP_IO_MACRO_Q(rx_edpkt_dma);
+BCMASP_FP_IO_MACRO_Q(rx_edpkt_cfg);
+
+#define PKT_OFFLOAD_NOP			(0 << 28)
+#define PKT_OFFLOAD_HDR_OP		(1 << 28)
+#define  PKT_OFFLOAD_HDR_WRBACK		BIT(19)
+#define  PKT_OFFLOAD_HDR_COUNT(x)	((x) << 16)
+#define  PKT_OFFLOAD_HDR_SIZE_1(x)	((x) << 4)
+#define  PKT_OFFLOAD_HDR_SIZE_2(x)	(x)
+#define  PKT_OFFLOAD_HDR2_SIZE_2(x)	((x) << 24)
+#define  PKT_OFFLOAD_HDR2_SIZE_3(x)	((x) << 12)
+#define  PKT_OFFLOAD_HDR2_SIZE_4(x)	(x)
+#define PKT_OFFLOAD_EPKT_OP		(2 << 28)
+#define  PKT_OFFLOAD_EPKT_WRBACK	BIT(23)
+#define  PKT_OFFLOAD_EPKT_IP(x)		((x) << 21)
+#define  PKT_OFFLOAD_EPKT_TP(x)		((x) << 19)
+#define  PKT_OFFLOAD_EPKT_LEN(x)	((x) << 16)
+#define  PKT_OFFLOAD_EPKT_CSUM_L3	BIT(15)
+#define  PKT_OFFLOAD_EPKT_CSUM_L2	BIT(14)
+#define  PKT_OFFLOAD_EPKT_ID(x)		((x) << 12)
+#define  PKT_OFFLOAD_EPKT_SEQ(x)	((x) << 10)
+#define  PKT_OFFLOAD_EPKT_TS(x)		((x) << 8)
+#define  PKT_OFFLOAD_EPKT_BLOC(x)	(x)
+#define PKT_OFFLOAD_END_OP		(7 << 28)
+
+struct bcmasp_pkt_offload {
+	__be32		nop;
+	__be32		header;
+	__be32		header2;
+	__be32		epkt;
+	__be32		end;
+};
+
+#define BCMASP_CORE_IO_MACRO(name, offset)				\
+static inline u32 name##_core_rl(struct bcmasp_priv *priv,		\
+				 u32 off)				\
+{									\
+	u32 reg = readl_relaxed(priv->base + (offset) + off);		\
+	return reg;							\
+}									\
+static inline void name##_core_wl(struct bcmasp_priv *priv,		\
+				  u32 val, u32 off)			\
+{									\
+	writel_relaxed(val, priv->base + (offset) + off);		\
+}
+
+BCMASP_CORE_IO_MACRO(intr2, ASP_INTR2_OFFSET);
+BCMASP_CORE_IO_MACRO(wakeup_intr2, ASP_WAKEUP_INTR2_OFFSET);
+BCMASP_CORE_IO_MACRO(tx_analytics, ASP_TX_ANALYTICS_OFFSET);
+BCMASP_CORE_IO_MACRO(rx_analytics, ASP_RX_ANALYTICS_OFFSET);
+BCMASP_CORE_IO_MACRO(rx_ctrl, ASP_RX_CTRL_OFFSET);
+BCMASP_CORE_IO_MACRO(rx_filter, ASP_RX_FILTER_OFFSET);
+BCMASP_CORE_IO_MACRO(rx_edpkt, ASP_EDPKT_OFFSET);
+BCMASP_CORE_IO_MACRO(ctrl, ASP_CTRL);
+
+struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv,
+					    struct device_node *ndev_dn, int i);
+
+void bcmasp_interface_destroy(struct bcmasp_intf *intf);
+
+void bcmasp_enable_tx_irq(struct bcmasp_intf *intf, int en);
+
+void bcmasp_enable_rx_irq(struct bcmasp_intf *intf, int en);
+
+void bcmasp_flush_rx_port(struct bcmasp_intf *intf);
+
+extern const struct ethtool_ops bcmasp_ethtool_ops;
+
+int bcmasp_interface_suspend(struct bcmasp_intf *intf);
+
+int bcmasp_interface_resume(struct bcmasp_intf *intf);
+
+void bcmasp_set_promisc(struct bcmasp_intf *intf, bool en);
+
+void bcmasp_set_allmulti(struct bcmasp_intf *intf, bool en);
+
+void bcmasp_set_broad(struct bcmasp_intf *intf, bool en);
+
+void bcmasp_set_oaddr(struct bcmasp_intf *intf, const unsigned char *addr,
+		      bool en);
+
+int bcmasp_set_en_mda_filter(struct bcmasp_intf *intf, unsigned char *addr,
+			     unsigned char *mask);
+
+void bcmasp_disable_all_filters(struct bcmasp_intf *intf);
+
+void bcmasp_core_clock_set_intf(struct bcmasp_intf *intf, bool en);
+
+#endif
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
new file mode 100644
index 0000000000000..394c0e1cb026a
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+#define pr_fmt(fmt)				"bcmasp_ethtool: " fmt
+
+#include <linux/ethtool.h>
+#include <linux/netdevice.h>
+#include <linux/platform_device.h>
+
+#include "bcmasp.h"
+#include "bcmasp_intf_defs.h"
+
+static void bcmasp_get_drvinfo(struct net_device *dev,
+			       struct ethtool_drvinfo *info)
+{
+	strscpy(info->driver, "bcmasp", sizeof(info->driver));
+	strscpy(info->bus_info, dev_name(dev->dev.parent),
+		sizeof(info->bus_info));
+}
+
+static u32 bcmasp_get_msglevel(struct net_device *dev)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+
+	return intf->msg_enable;
+}
+
+static void bcmasp_set_msglevel(struct net_device *dev, u32 level)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+
+	intf->msg_enable = level;
+}
+
+const struct ethtool_ops bcmasp_ethtool_ops = {
+	.get_drvinfo		= bcmasp_get_drvinfo,
+	.get_link		= ethtool_op_get_link,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
+	.get_msglevel		= bcmasp_get_msglevel,
+	.set_msglevel		= bcmasp_set_msglevel,
+};
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
new file mode 100644
index 0000000000000..0232f5cf8909c
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -0,0 +1,1342 @@
+// SPDX-License-Identifier: GPL-2.0
+#define pr_fmt(fmt)			"bcmasp_intf: " fmt
+
+#include <asm/byteorder.h>
+#include <linux/brcmphy.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
+#include <linux/phy.h>
+#include <linux/phy_fixed.h>
+#include <linux/ptp_classify.h>
+#include <linux/platform_device.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+
+#include "bcmasp.h"
+#include "bcmasp_intf_defs.h"
+
+static int incr_ring(int index, int ring_count)
+{
+	index++;
+	if (index == ring_count)
+		return 0;
+
+	return index;
+}
+
+/* Points to last byte of descriptor */
+static dma_addr_t incr_last_byte(dma_addr_t addr, dma_addr_t beg,
+				 int ring_count)
+{
+	dma_addr_t end = beg + (ring_count * DESC_SIZE);
+
+	addr += DESC_SIZE;
+	if (addr > end)
+		return beg + DESC_SIZE - 1;
+
+	return addr;
+}
+
+/* Points to first byte of descriptor */
+static dma_addr_t incr_first_byte(dma_addr_t addr, dma_addr_t beg,
+				  int ring_count)
+{
+	dma_addr_t end = beg + (ring_count * DESC_SIZE);
+
+	addr += DESC_SIZE;
+	if (addr >= end)
+		return beg;
+
+	return addr;
+}
+
+static void bcmasp_enable_tx(struct bcmasp_intf *intf, int en)
+{
+	if (en) {
+		tx_spb_ctrl_wl(intf, TX_SPB_CTRL_ENABLE_EN, TX_SPB_CTRL_ENABLE);
+		tx_epkt_core_wl(intf, (TX_EPKT_C_CFG_MISC_EN |
+				TX_EPKT_C_CFG_MISC_PT |
+				(intf->port << TX_EPKT_C_CFG_MISC_PS_SHIFT)),
+				TX_EPKT_C_CFG_MISC);
+	} else {
+		tx_spb_ctrl_wl(intf, 0x0, TX_SPB_CTRL_ENABLE);
+		tx_epkt_core_wl(intf, 0x0, TX_EPKT_C_CFG_MISC);
+	}
+}
+
+static void bcmasp_enable_rx(struct bcmasp_intf *intf, int en)
+{
+	if (en)
+		rx_edpkt_cfg_wl(intf, RX_EDPKT_CFG_ENABLE_EN,
+				RX_EDPKT_CFG_ENABLE);
+	else
+		rx_edpkt_cfg_wl(intf, 0x0, RX_EDPKT_CFG_ENABLE);
+}
+
+static void bcmasp_set_rx_mode(struct net_device *dev)
+{
+	unsigned char mask[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	struct netdev_hw_addr *ha;
+	int ret;
+
+	spin_lock_bh(&intf->parent->mda_lock);
+
+	bcmasp_disable_all_filters(intf);
+
+	if (dev->flags & IFF_PROMISC)
+		goto set_promisc;
+
+	bcmasp_set_promisc(intf, 0);
+
+	bcmasp_set_broad(intf, 1);
+
+	bcmasp_set_oaddr(intf, dev->dev_addr, 1);
+
+	if (dev->flags & IFF_ALLMULTI) {
+		bcmasp_set_allmulti(intf, 1);
+	} else {
+		bcmasp_set_allmulti(intf, 0);
+
+		netdev_for_each_mc_addr(ha, dev) {
+			ret = bcmasp_set_en_mda_filter(intf, ha->addr, mask);
+			if (ret)
+				goto set_promisc;
+		}
+	}
+
+	netdev_for_each_uc_addr(ha, dev) {
+		ret = bcmasp_set_en_mda_filter(intf, ha->addr, mask);
+		if (ret)
+			goto set_promisc;
+	}
+
+	spin_unlock_bh(&intf->parent->mda_lock);
+	return;
+
+set_promisc:
+	bcmasp_set_promisc(intf, 1);
+
+	/* disable all filters used by this port */
+	bcmasp_disable_all_filters(intf);
+
+	spin_unlock_bh(&intf->parent->mda_lock);
+}
+
+static void bcmasp_clean_txcb(struct bcmasp_intf *intf, int index)
+{
+	struct bcmasp_tx_cb *txcb = &intf->tx_cbs[index];
+
+	txcb->skb = NULL;
+	dma_unmap_addr_set(txcb, dma_addr, 0);
+	dma_unmap_len_set(txcb, dma_len, 0);
+	txcb->last = false;
+}
+
+static int tx_spb_ring_full(struct bcmasp_intf *intf, int cnt)
+{
+	int next_index, i;
+
+	/* Check if we have enough room for cnt descriptors */
+	for (i = 0; i < cnt; i++) {
+		next_index = incr_ring(intf->tx_spb_index, DESC_RING_COUNT);
+		if (next_index == intf->tx_spb_clean_index)
+			return 1;
+	}
+
+	return 0;
+}
+
+static struct sk_buff *bcmasp_csum_offload(struct net_device *dev,
+					   struct sk_buff *skb,
+					   bool *csum_hw)
+{
+	u32 header = 0, header2 = 0, epkt = 0;
+	struct bcmasp_pkt_offload *offload;
+	unsigned int header_cnt = 0;
+	u8 ip_proto;
+	int ret;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return skb;
+
+	ret = skb_cow_head(skb, sizeof(*offload));
+	if (ret < 0)
+		goto help;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		header |= PKT_OFFLOAD_HDR_SIZE_2((ip_hdrlen(skb) >> 8) & 0xf);
+		header2 |= PKT_OFFLOAD_HDR2_SIZE_2(ip_hdrlen(skb) & 0xff);
+		epkt |= PKT_OFFLOAD_EPKT_IP(0) | PKT_OFFLOAD_EPKT_CSUM_L2;
+		ip_proto = ip_hdr(skb)->protocol;
+		header_cnt += 2;
+		break;
+	case htons(ETH_P_IPV6):
+		header |= PKT_OFFLOAD_HDR_SIZE_2((IP6_HLEN >> 8) & 0xf);
+		header2 |= PKT_OFFLOAD_HDR2_SIZE_2(IP6_HLEN & 0xff);
+		epkt |= PKT_OFFLOAD_EPKT_IP(1) | PKT_OFFLOAD_EPKT_CSUM_L2;
+		ip_proto = ipv6_hdr(skb)->nexthdr;
+		header_cnt += 2;
+		break;
+	default:
+		goto help;
+	}
+
+	switch (ip_proto) {
+	case IPPROTO_TCP:
+		header2 |= PKT_OFFLOAD_HDR2_SIZE_3(tcp_hdrlen(skb));
+		epkt |= PKT_OFFLOAD_EPKT_TP(0) | PKT_OFFLOAD_EPKT_CSUM_L3;
+		header_cnt++;
+		break;
+	case IPPROTO_UDP:
+		header2 |= PKT_OFFLOAD_HDR2_SIZE_3(UDP_HLEN);
+		epkt |= PKT_OFFLOAD_EPKT_TP(1) | PKT_OFFLOAD_EPKT_CSUM_L3;
+		header_cnt++;
+		break;
+	default:
+		goto help;
+	}
+
+	offload = (struct bcmasp_pkt_offload *)skb_push(skb, sizeof(*offload));
+
+	header |= PKT_OFFLOAD_HDR_OP | PKT_OFFLOAD_HDR_COUNT(header_cnt) |
+		  PKT_OFFLOAD_HDR_SIZE_1(ETH_HLEN);
+	epkt |= PKT_OFFLOAD_EPKT_OP;
+
+	offload->nop = htonl(PKT_OFFLOAD_NOP);
+	offload->header = htonl(header);
+	offload->header2 = htonl(header2);
+	offload->epkt = htonl(epkt);
+	offload->end = htonl(PKT_OFFLOAD_END_OP);
+	*csum_hw = true;
+
+	return skb;
+
+help:
+	skb_checksum_help(skb);
+
+	return skb;
+}
+
+static unsigned long bcmasp_rx_edpkt_dma_rq(struct bcmasp_intf *intf)
+{
+	return rx_edpkt_dma_rq(intf, RX_EDPKT_DMA_VALID);
+}
+
+static void bcmasp_rx_edpkt_cfg_wq(struct bcmasp_intf *intf, dma_addr_t addr)
+{
+	rx_edpkt_cfg_wq(intf, addr, RX_EDPKT_RING_BUFFER_READ);
+}
+
+static void bcmasp_rx_edpkt_dma_wq(struct bcmasp_intf *intf, dma_addr_t addr)
+{
+	rx_edpkt_dma_wq(intf, addr, RX_EDPKT_DMA_READ);
+}
+
+static unsigned long bcmasp_tx_spb_dma_rq(struct bcmasp_intf *intf)
+{
+	return tx_spb_dma_rq(intf, TX_SPB_DMA_READ);
+}
+
+static void bcmasp_tx_spb_dma_wq(struct bcmasp_intf *intf, dma_addr_t addr)
+{
+	tx_spb_dma_wq(intf, addr, TX_SPB_DMA_VALID);
+}
+
+static const struct bcmasp_intf_ops bcmasp_intf_ops = {
+	.rx_desc_read = bcmasp_rx_edpkt_dma_rq,
+	.rx_buffer_write = bcmasp_rx_edpkt_cfg_wq,
+	.rx_desc_write = bcmasp_rx_edpkt_dma_wq,
+	.tx_read = bcmasp_tx_spb_dma_rq,
+	.tx_write = bcmasp_tx_spb_dma_wq,
+};
+
+static netdev_tx_t bcmasp_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	unsigned int total_bytes, size;
+	int spb_index, nr_frags, i, j;
+	struct bcmasp_tx_cb *txcb;
+	dma_addr_t mapping, valid;
+	struct bcmasp_desc *desc;
+	bool csum_hw = false;
+	struct device *kdev;
+	skb_frag_t *frag;
+
+	kdev = &intf->parent->pdev->dev;
+
+	nr_frags = skb_shinfo(skb)->nr_frags;
+
+	if (tx_spb_ring_full(intf, nr_frags + 1)) {
+		netif_stop_queue(dev);
+		if (net_ratelimit())
+			netdev_err(dev, "Tx Ring Full!\n");
+		return NETDEV_TX_BUSY;
+	}
+
+	/* Save skb len before adding csum offload header */
+	total_bytes = skb->len;
+	skb = bcmasp_csum_offload(dev, skb, &csum_hw);
+	if (!skb)
+		return NETDEV_TX_OK;
+
+	spb_index = intf->tx_spb_index;
+	valid = intf->tx_spb_dma_valid;
+	for (i = 0; i <= nr_frags; i++) {
+		if (!i) {
+			size = skb_headlen(skb);
+			if (!nr_frags && size < (ETH_ZLEN + ETH_FCS_LEN)) {
+				if (skb_put_padto(skb, ETH_ZLEN + ETH_FCS_LEN))
+					return NETDEV_TX_OK;
+				size = skb->len;
+			}
+			mapping = dma_map_single(kdev, skb->data, size,
+						 DMA_TO_DEVICE);
+		} else {
+			frag = &skb_shinfo(skb)->frags[i - 1];
+			size = skb_frag_size(frag);
+			mapping = skb_frag_dma_map(kdev, frag, 0, size,
+						   DMA_TO_DEVICE);
+		}
+
+		if (dma_mapping_error(kdev, mapping)) {
+			spb_index = intf->tx_spb_index;
+			for (j = 0; j < i; j++) {
+				bcmasp_clean_txcb(intf, spb_index);
+				spb_index = incr_ring(spb_index,
+						      DESC_RING_COUNT);
+			}
+			/* Rewind so we do not have a hole */
+			spb_index = intf->tx_spb_index;
+			return NETDEV_TX_OK;
+		}
+
+		txcb = &intf->tx_cbs[spb_index];
+		desc = &intf->tx_spb_cpu[spb_index];
+		memset(desc, 0, sizeof(*desc));
+		txcb->skb = skb;
+		txcb->bytes_sent = total_bytes;
+		dma_unmap_addr_set(txcb, dma_addr, mapping);
+		dma_unmap_len_set(txcb, dma_len, size);
+		if (!i) {
+			desc->flags |= DESC_SOF;
+			if (csum_hw)
+				desc->flags |= DESC_EPKT_CMD;
+		}
+
+		if (i == nr_frags) {
+			desc->flags |= DESC_EOF;
+			txcb->last = true;
+		}
+
+		desc->buf = mapping;
+		desc->size = size;
+		desc->flags |= DESC_INT_EN;
+
+		netif_dbg(intf, tx_queued, dev,
+			  "%s dma_buf=%pad dma_len=0x%x flags=0x%x index=0x%x\n",
+			  __func__, &mapping, desc->size, desc->flags,
+			  spb_index);
+
+		spb_index = incr_ring(spb_index, DESC_RING_COUNT);
+		valid = incr_last_byte(valid, intf->tx_spb_dma_addr,
+				       DESC_RING_COUNT);
+	}
+
+	/* Ensure all descriptors have been written to DRAM for the
+	 * hardware to see up-to-date contents.
+	 */
+	wmb();
+
+	intf->tx_spb_index = spb_index;
+	intf->tx_spb_dma_valid = valid;
+	bcmasp_intf_tx_write(intf, intf->tx_spb_dma_valid);
+
+	if (tx_spb_ring_full(intf, MAX_SKB_FRAGS + 1))
+		netif_stop_queue(dev);
+
+	return NETDEV_TX_OK;
+}
+
+static void bcmasp_netif_start(struct net_device *dev)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+
+	bcmasp_set_rx_mode(dev);
+	napi_enable(&intf->tx_napi);
+	napi_enable(&intf->rx_napi);
+
+	bcmasp_enable_rx_irq(intf, 1);
+	bcmasp_enable_tx_irq(intf, 1);
+
+	phy_start(dev->phydev);
+}
+
+static void umac_reset(struct bcmasp_intf *intf)
+{
+	umac_wl(intf, 0x0, UMC_CMD);
+	umac_wl(intf, UMC_CMD_SW_RESET, UMC_CMD);
+	usleep_range(10, 100);
+	umac_wl(intf, 0x0, UMC_CMD);
+}
+
+static void umac_set_hw_addr(struct bcmasp_intf *intf,
+			     const unsigned char *addr)
+{
+	u32 mac0 = (addr[0] << 24) | (addr[1] << 16) | (addr[2] << 8) |
+		    addr[3];
+	u32 mac1 = (addr[4] << 8) | addr[5];
+
+	umac_wl(intf, mac0, UMC_MAC0);
+	umac_wl(intf, mac1, UMC_MAC1);
+}
+
+static void umac_enable_set(struct bcmasp_intf *intf, u32 mask,
+			    unsigned int enable)
+{
+	u32 reg;
+
+	reg = umac_rl(intf, UMC_CMD);
+	if (enable)
+		reg |= mask;
+	else
+		reg &= ~mask;
+	umac_wl(intf, reg, UMC_CMD);
+
+	/* UniMAC stops on a packet boundary, wait for a full-sized packet
+	 * to be processed (1 msec).
+	 */
+	if (enable == 0)
+		usleep_range(1000, 2000);
+}
+
+static void umac_init(struct bcmasp_intf *intf)
+{
+	umac_wl(intf, 0x800, UMC_FRM_LEN);
+	umac_wl(intf, 0xffff, UMC_PAUSE_CNTRL);
+	umac_wl(intf, 0x800, UMC_RX_MAX_PKT_SZ);
+	umac_enable_set(intf, UMC_CMD_PROMISC, 1);
+}
+
+static int bcmasp_tx_poll(struct napi_struct *napi, int budget)
+{
+	struct bcmasp_intf *intf =
+		container_of(napi, struct bcmasp_intf, tx_napi);
+	struct bcmasp_intf_stats64 *stats = &intf->stats64;
+	struct device *kdev = &intf->parent->pdev->dev;
+	unsigned long read, released = 0;
+	struct bcmasp_tx_cb *txcb;
+	struct bcmasp_desc *desc;
+	dma_addr_t mapping;
+
+	read = bcmasp_intf_tx_read(intf);
+	while (intf->tx_spb_dma_read != read) {
+		txcb = &intf->tx_cbs[intf->tx_spb_clean_index];
+		mapping = dma_unmap_addr(txcb, dma_addr);
+
+		dma_unmap_single(kdev, mapping,
+				 dma_unmap_len(txcb, dma_len),
+				 DMA_TO_DEVICE);
+
+		if (txcb->last) {
+			dev_consume_skb_any(txcb->skb);
+
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->tx_packets);
+			u64_stats_add(&stats->tx_bytes, txcb->bytes_sent);
+			u64_stats_update_end(&stats->syncp);
+		}
+
+		desc = &intf->tx_spb_cpu[intf->tx_spb_clean_index];
+
+		netif_dbg(intf, tx_done, intf->ndev,
+			  "%s dma_buf=%pad dma_len=0x%x flags=0x%x c_index=0x%x\n",
+			  __func__, &mapping, desc->size, desc->flags,
+			  intf->tx_spb_clean_index);
+
+		bcmasp_clean_txcb(intf, intf->tx_spb_clean_index);
+		released++;
+
+		intf->tx_spb_clean_index = incr_ring(intf->tx_spb_clean_index,
+						     DESC_RING_COUNT);
+		intf->tx_spb_dma_read = incr_first_byte(intf->tx_spb_dma_read,
+							intf->tx_spb_dma_addr,
+							DESC_RING_COUNT);
+	}
+
+	/* Ensure all descriptors have been written to DRAM for the hardware
+	 * to see updated contents.
+	 */
+	wmb();
+
+	napi_complete(&intf->tx_napi);
+
+	bcmasp_enable_tx_irq(intf, 1);
+
+	if (released)
+		netif_wake_queue(intf->ndev);
+
+	return 0;
+}
+
+static int bcmasp_rx_poll(struct napi_struct *napi, int budget)
+{
+	struct bcmasp_intf *intf =
+		container_of(napi, struct bcmasp_intf, rx_napi);
+	struct bcmasp_intf_stats64 *stats = &intf->stats64;
+	struct device *kdev = &intf->parent->pdev->dev;
+	unsigned long processed = 0;
+	struct bcmasp_desc *desc;
+	struct sk_buff *skb;
+	dma_addr_t valid;
+	void *data;
+	u64 flags;
+	u32 len;
+
+	valid = bcmasp_intf_rx_desc_read(intf) + 1;
+	if (valid == intf->rx_edpkt_dma_addr + DESC_RING_SIZE)
+		valid = intf->rx_edpkt_dma_addr;
+
+	while ((processed < budget) && (valid != intf->rx_edpkt_dma_read)) {
+		desc = &intf->rx_edpkt_cpu[intf->rx_edpkt_index];
+
+		/* Ensure that descriptor has been fully written to DRAM by
+		 * hardware before reading by the CPU
+		 */
+		rmb();
+
+		/* Calculate virt addr by offsetting from physical addr */
+		data = intf->rx_ring_cpu +
+			(DESC_ADDR(desc->buf) - intf->rx_ring_dma);
+
+		flags = DESC_FLAGS(desc->buf);
+		if (unlikely(flags & (DESC_CRC_ERR | DESC_RX_SYM_ERR))) {
+			if (net_ratelimit()) {
+				netif_err(intf, rx_status, intf->ndev,
+					  "flags=0x%llx\n", flags);
+			}
+
+			u64_stats_update_begin(&stats->syncp);
+			if (flags & DESC_CRC_ERR)
+				u64_stats_inc(&stats->rx_crc_errs);
+			if (flags & DESC_RX_SYM_ERR)
+				u64_stats_inc(&stats->rx_sym_errs);
+			u64_stats_update_end(&stats->syncp);
+
+			goto next;
+		}
+
+		dma_sync_single_for_cpu(kdev, DESC_ADDR(desc->buf), desc->size,
+					DMA_FROM_DEVICE);
+
+		len = desc->size;
+
+		skb = napi_alloc_skb(napi, len);
+		if (!skb) {
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->rx_dropped);
+			u64_stats_update_end(&stats->syncp);
+			goto next;
+		}
+
+		skb_put(skb, len);
+		memcpy(skb->data, data, len);
+
+		skb_pull(skb, 2);
+		len -= 2;
+		if (likely(intf->crc_fwd)) {
+			skb_trim(skb, len - ETH_FCS_LEN);
+			len -= ETH_FCS_LEN;
+		}
+
+		if ((intf->ndev->features & NETIF_F_RXCSUM) &&
+		    (desc->buf & DESC_CHKSUM))
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		skb->protocol = eth_type_trans(skb, intf->ndev);
+
+		napi_gro_receive(napi, skb);
+
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->rx_packets);
+		u64_stats_add(&stats->rx_bytes, len);
+		u64_stats_update_end(&stats->syncp);
+
+next:
+		bcmasp_intf_rx_buffer_write(intf, (DESC_ADDR(desc->buf) +
+					    desc->size));
+
+		processed++;
+		intf->rx_edpkt_dma_read =
+			incr_first_byte(intf->rx_edpkt_dma_read,
+					intf->rx_edpkt_dma_addr,
+					DESC_RING_COUNT);
+		intf->rx_edpkt_index = incr_ring(intf->rx_edpkt_index,
+						 DESC_RING_COUNT);
+	}
+
+	bcmasp_intf_rx_desc_write(intf, intf->rx_edpkt_dma_read);
+
+	if (processed < budget) {
+		napi_complete_done(&intf->rx_napi, processed);
+		bcmasp_enable_rx_irq(intf, 1);
+	}
+
+	return processed;
+}
+
+static void bcmasp_adj_link(struct net_device *dev)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	struct phy_device *phydev = dev->phydev;
+	u32 cmd_bits = 0, reg;
+	int changed = 0;
+
+	if (intf->old_link != phydev->link) {
+		changed = 1;
+		intf->old_link = phydev->link;
+	}
+
+	if (intf->old_duplex != phydev->duplex) {
+		changed = 1;
+		intf->old_duplex = phydev->duplex;
+	}
+
+	switch (phydev->speed) {
+	case SPEED_2500:
+		cmd_bits = UMC_CMD_SPEED_2500;
+		break;
+	case SPEED_1000:
+		cmd_bits = UMC_CMD_SPEED_1000;
+		break;
+	case SPEED_100:
+		cmd_bits = UMC_CMD_SPEED_100;
+		break;
+	case SPEED_10:
+		cmd_bits = UMC_CMD_SPEED_10;
+		break;
+	default:
+		break;
+	}
+	cmd_bits <<= UMC_CMD_SPEED_SHIFT;
+
+	if (phydev->duplex == DUPLEX_HALF)
+		cmd_bits |= UMC_CMD_HD_EN;
+
+	if (intf->old_pause != phydev->pause) {
+		changed = 1;
+		intf->old_pause = phydev->pause;
+	}
+
+	if (!phydev->pause)
+		cmd_bits |= UMC_CMD_RX_PAUSE_IGNORE | UMC_CMD_TX_PAUSE_IGNORE;
+
+	if (!changed)
+		return;
+
+	if (phydev->link) {
+		reg = umac_rl(intf, UMC_CMD);
+		reg &= ~((UMC_CMD_SPEED_MASK << UMC_CMD_SPEED_SHIFT) |
+			UMC_CMD_HD_EN | UMC_CMD_RX_PAUSE_IGNORE |
+			UMC_CMD_TX_PAUSE_IGNORE);
+		reg |= cmd_bits;
+		umac_wl(intf, reg, UMC_CMD);
+	}
+
+	reg = rgmii_rl(intf, RGMII_OOB_CNTRL);
+	if (phydev->link)
+		reg |= RGMII_LINK;
+	else
+		reg &= ~RGMII_LINK;
+	rgmii_wl(intf, reg, RGMII_OOB_CNTRL);
+
+	if (changed)
+		phy_print_status(phydev);
+}
+
+static int bcmasp_init_rx(struct bcmasp_intf *intf)
+{
+	struct device *kdev = &intf->parent->pdev->dev;
+	struct page *buffer_pg;
+	dma_addr_t dma;
+	void *p;
+	u32 reg;
+	int ret;
+
+	intf->rx_buf_order = get_order(RING_BUFFER_SIZE);
+	buffer_pg = alloc_pages(GFP_KERNEL, intf->rx_buf_order);
+
+	dma = dma_map_page(kdev, buffer_pg, 0, RING_BUFFER_SIZE,
+			   DMA_FROM_DEVICE);
+	if (dma_mapping_error(kdev, dma)) {
+		__free_pages(buffer_pg, intf->rx_buf_order);
+		return -ENOMEM;
+	}
+	intf->rx_ring_cpu = page_to_virt(buffer_pg);
+	intf->rx_ring_dma = dma;
+	intf->rx_ring_dma_valid = intf->rx_ring_dma + RING_BUFFER_SIZE - 1;
+
+	p = dma_alloc_coherent(kdev, DESC_RING_SIZE, &intf->rx_edpkt_dma_addr,
+			       GFP_KERNEL);
+	if (!p) {
+		ret = -ENOMEM;
+		goto free_rx_ring;
+	}
+	intf->rx_edpkt_cpu = p;
+
+	netif_napi_add(intf->ndev, &intf->rx_napi, bcmasp_rx_poll);
+
+	intf->rx_edpkt_dma_read = intf->rx_edpkt_dma_addr;
+	intf->rx_edpkt_index = 0;
+
+	/* Make sure channels are disabled */
+	rx_edpkt_cfg_wl(intf, 0x0, RX_EDPKT_CFG_ENABLE);
+
+	/* Rx SPB */
+	rx_edpkt_cfg_wq(intf, intf->rx_ring_dma, RX_EDPKT_RING_BUFFER_READ);
+	rx_edpkt_cfg_wq(intf, intf->rx_ring_dma, RX_EDPKT_RING_BUFFER_WRITE);
+	rx_edpkt_cfg_wq(intf, intf->rx_ring_dma, RX_EDPKT_RING_BUFFER_BASE);
+	rx_edpkt_cfg_wq(intf, intf->rx_ring_dma_valid,
+			RX_EDPKT_RING_BUFFER_END);
+	rx_edpkt_cfg_wq(intf, intf->rx_ring_dma_valid,
+			RX_EDPKT_RING_BUFFER_VALID);
+
+	/* EDPKT */
+	rx_edpkt_cfg_wl(intf, (RX_EDPKT_CFG_CFG0_RBUF_4K <<
+			RX_EDPKT_CFG_CFG0_DBUF_SHIFT) |
+		       (RX_EDPKT_CFG_CFG0_64_ALN <<
+			RX_EDPKT_CFG_CFG0_BALN_SHIFT) |
+		       (RX_EDPKT_CFG_CFG0_EFRM_STUF),
+			RX_EDPKT_CFG_CFG0);
+	rx_edpkt_dma_wq(intf, intf->rx_edpkt_dma_addr, RX_EDPKT_DMA_WRITE);
+	rx_edpkt_dma_wq(intf, intf->rx_edpkt_dma_addr, RX_EDPKT_DMA_READ);
+	rx_edpkt_dma_wq(intf, intf->rx_edpkt_dma_addr, RX_EDPKT_DMA_BASE);
+	rx_edpkt_dma_wq(intf, intf->rx_edpkt_dma_addr + (DESC_RING_SIZE - 1),
+			RX_EDPKT_DMA_END);
+	rx_edpkt_dma_wq(intf, intf->rx_edpkt_dma_addr + (DESC_RING_SIZE - 1),
+			RX_EDPKT_DMA_VALID);
+
+	reg = UMAC2FB_CFG_DEFAULT_EN |
+	      ((intf->channel + 11) << UMAC2FB_CFG_CHID_SHIFT);
+	reg |= (0xd << UMAC2FB_CFG_OK_SEND_SHIFT);
+	umac2fb_wl(intf, reg, UMAC2FB_CFG);
+
+	return 0;
+
+free_rx_ring:
+	dma_unmap_page(kdev, intf->rx_ring_dma, RING_BUFFER_SIZE,
+		       DMA_FROM_DEVICE);
+	__free_pages(virt_to_page(intf->rx_ring_cpu), intf->rx_buf_order);
+
+	return ret;
+}
+
+static void bcmasp_reclaim_free_all_rx(struct bcmasp_intf *intf)
+{
+	struct device *kdev = &intf->parent->pdev->dev;
+
+	dma_free_coherent(kdev, DESC_RING_SIZE, intf->rx_edpkt_cpu,
+			  intf->rx_edpkt_dma_addr);
+	dma_unmap_page(kdev, intf->rx_ring_dma, RING_BUFFER_SIZE,
+		       DMA_FROM_DEVICE);
+	__free_pages(virt_to_page(intf->rx_ring_cpu), intf->rx_buf_order);
+}
+
+static int bcmasp_init_tx(struct bcmasp_intf *intf)
+{
+	struct device *kdev = &intf->parent->pdev->dev;
+	void *p;
+	int ret;
+
+	p = dma_alloc_coherent(kdev, DESC_RING_SIZE, &intf->tx_spb_dma_addr,
+			       GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	intf->tx_spb_cpu = p;
+	intf->tx_spb_dma_valid = intf->tx_spb_dma_addr + DESC_RING_SIZE - 1;
+	intf->tx_spb_dma_read = intf->tx_spb_dma_addr;
+
+	intf->tx_cbs = kcalloc(DESC_RING_COUNT, sizeof(struct bcmasp_tx_cb),
+			       GFP_KERNEL);
+	if (!intf->tx_cbs) {
+		ret = -ENOMEM;
+		goto free_tx_spb;
+	}
+
+	intf->tx_spb_index = 0;
+	intf->tx_spb_clean_index = 0;
+
+	netif_napi_add_tx(intf->ndev, &intf->tx_napi, bcmasp_tx_poll);
+
+	/* Make sure channels are disabled */
+	tx_spb_ctrl_wl(intf, 0x0, TX_SPB_CTRL_ENABLE);
+	tx_epkt_core_wl(intf, 0x0, TX_EPKT_C_CFG_MISC);
+
+	/* Tx SPB */
+	tx_spb_ctrl_wl(intf, ((intf->channel + 8) << TX_SPB_CTRL_XF_BID_SHIFT),
+		       TX_SPB_CTRL_XF_CTRL2);
+	tx_pause_ctrl_wl(intf, (1 << (intf->channel + 8)), TX_PAUSE_MAP_VECTOR);
+	tx_spb_top_wl(intf, 0x1e, TX_SPB_TOP_BLKOUT);
+	tx_spb_top_wl(intf, 0x0, TX_SPB_TOP_SPRE_BW_CTRL);
+
+	tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_READ);
+	tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_BASE);
+	tx_spb_dma_wq(intf, intf->tx_spb_dma_valid, TX_SPB_DMA_END);
+	tx_spb_dma_wq(intf, intf->tx_spb_dma_valid, TX_SPB_DMA_VALID);
+
+	return 0;
+
+free_tx_spb:
+	dma_free_coherent(kdev, DESC_RING_SIZE, intf->tx_spb_cpu,
+			  intf->tx_spb_dma_addr);
+
+	return ret;
+}
+
+static void bcmasp_reclaim_free_all_tx(struct bcmasp_intf *intf)
+{
+	struct device *kdev = &intf->parent->pdev->dev;
+
+	/* Free descriptors */
+	dma_free_coherent(kdev, DESC_RING_SIZE, intf->tx_spb_cpu,
+			  intf->tx_spb_dma_addr);
+
+	/* Free cbs */
+	kfree(intf->tx_cbs);
+}
+
+static void bcmasp_ephy_enable_set(struct bcmasp_intf *intf, bool enable)
+{
+	u32 mask = RGMII_EPHY_CFG_IDDQ_BIAS | RGMII_EPHY_CFG_EXT_PWRDOWN |
+		   RGMII_EPHY_CFG_IDDQ_GLOBAL;
+	u32 reg;
+
+	reg = rgmii_rl(intf, RGMII_EPHY_CNTRL);
+	if (enable) {
+		reg &= ~RGMII_EPHY_CK25_DIS;
+		rgmii_wl(intf, reg, RGMII_EPHY_CNTRL);
+		mdelay(1);
+
+		reg &= ~mask;
+		reg |= RGMII_EPHY_RESET;
+		rgmii_wl(intf, reg, RGMII_EPHY_CNTRL);
+		mdelay(1);
+
+		reg &= ~RGMII_EPHY_RESET;
+	} else {
+		reg |= mask | RGMII_EPHY_RESET;
+		rgmii_wl(intf, reg, RGMII_EPHY_CNTRL);
+		mdelay(1);
+		reg |= RGMII_EPHY_CK25_DIS;
+	}
+	rgmii_wl(intf, reg, RGMII_EPHY_CNTRL);
+	mdelay(1);
+
+	/* Set or clear the LED control override to avoid lighting up LEDs
+	 * while the EPHY is powered off and drawing unnecessary current.
+	 */
+	reg = rgmii_rl(intf, RGMII_SYS_LED_CNTRL);
+	if (enable)
+		reg &= ~RGMII_SYS_LED_CNTRL_LINK_OVRD;
+	else
+		reg |= RGMII_SYS_LED_CNTRL_LINK_OVRD;
+	rgmii_wl(intf, reg, RGMII_SYS_LED_CNTRL);
+}
+
+static void bcmasp_rgmii_mode_en_set(struct bcmasp_intf *intf, bool enable)
+{
+	u32 reg;
+
+	reg = rgmii_rl(intf, RGMII_OOB_CNTRL);
+	reg &= ~RGMII_OOB_DIS;
+	if (enable)
+		reg |= RGMII_MODE_EN;
+	else
+		reg &= ~RGMII_MODE_EN;
+	rgmii_wl(intf, reg, RGMII_OOB_CNTRL);
+}
+
+static void bcmasp_netif_deinit(struct net_device *dev)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	u32 reg, timeout = 1000;
+
+	napi_disable(&intf->tx_napi);
+
+	bcmasp_enable_tx(intf, 0);
+
+	/* Flush any TX packets in the pipe */
+	tx_spb_dma_wl(intf, TX_SPB_DMA_FIFO_FLUSH, TX_SPB_DMA_FIFO_CTRL);
+	do {
+		reg = tx_spb_dma_rl(intf, TX_SPB_DMA_FIFO_STATUS);
+		if (!(reg & TX_SPB_DMA_FIFO_FLUSH))
+			break;
+		usleep_range(1000, 2000);
+	} while (timeout-- > 0);
+	tx_spb_dma_wl(intf, 0x0, TX_SPB_DMA_FIFO_CTRL);
+
+	umac_enable_set(intf, UMC_CMD_TX_EN, 0);
+
+	phy_stop(dev->phydev);
+
+	umac_enable_set(intf, UMC_CMD_RX_EN, 0);
+
+	bcmasp_flush_rx_port(intf);
+	usleep_range(1000, 2000);
+	bcmasp_enable_rx(intf, 0);
+
+	napi_disable(&intf->rx_napi);
+
+	/* Disable interrupts */
+	bcmasp_enable_tx_irq(intf, 0);
+	bcmasp_enable_rx_irq(intf, 0);
+
+	netif_napi_del(&intf->tx_napi);
+	bcmasp_reclaim_free_all_tx(intf);
+
+	netif_napi_del(&intf->rx_napi);
+	bcmasp_reclaim_free_all_rx(intf);
+}
+
+static int bcmasp_stop(struct net_device *dev)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+
+	netif_dbg(intf, ifdown, dev, "bcmasp stop\n");
+
+	/* Stop tx from updating HW */
+	netif_tx_disable(dev);
+
+	bcmasp_netif_deinit(dev);
+
+	phy_disconnect(dev->phydev);
+
+	/* Disable internal EPHY or external PHY */
+	if (intf->internal_phy)
+		bcmasp_ephy_enable_set(intf, false);
+	else
+		bcmasp_rgmii_mode_en_set(intf, false);
+
+	/* Disable the interface clocks */
+	bcmasp_core_clock_set_intf(intf, false);
+
+	clk_disable_unprepare(intf->parent->clk);
+
+	return 0;
+}
+
+static void bcmasp_configure_port(struct bcmasp_intf *intf)
+{
+	u32 reg, id_mode_dis = 0;
+
+	reg = rgmii_rl(intf, RGMII_PORT_CNTRL);
+	reg &= ~RGMII_PORT_MODE_MASK;
+
+	switch (intf->phy_interface) {
+	case PHY_INTERFACE_MODE_RGMII:
+		/* RGMII_NO_ID: TXC transitions at the same time as TXD
+		 *		(requires PCB or receiver-side delay)
+		 * RGMII:	Add 2ns delay on TXC (90 degree shift)
+		 *
+		 * ID is implicitly disabled for 100Mbps (RG)MII operation.
+		 */
+		id_mode_dis = RGMII_ID_MODE_DIS;
+		fallthrough;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		reg |= RGMII_PORT_MODE_EXT_GPHY;
+		break;
+	case PHY_INTERFACE_MODE_MII:
+		reg |= RGMII_PORT_MODE_EXT_EPHY;
+		break;
+	default:
+		break;
+	}
+
+	if (intf->internal_phy)
+		reg |= RGMII_PORT_MODE_EPHY;
+
+	rgmii_wl(intf, reg, RGMII_PORT_CNTRL);
+
+	reg = rgmii_rl(intf, RGMII_OOB_CNTRL);
+	reg &= ~RGMII_ID_MODE_DIS;
+	reg |= id_mode_dis;
+	rgmii_wl(intf, reg, RGMII_OOB_CNTRL);
+}
+
+static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	phy_interface_t phy_iface = intf->phy_interface;
+	u32 phy_flags = PHY_BRCM_AUTO_PWRDWN_ENABLE |
+			PHY_BRCM_DIS_TXCRXC_NOENRGY |
+			PHY_BRCM_IDDQ_SUSPEND;
+	struct phy_device *phydev = NULL;
+	int ret;
+
+	/* Always enable interface clocks */
+	bcmasp_core_clock_set_intf(intf, true);
+
+	/* Enable internal PHY or external PHY before any MAC activity */
+	if (intf->internal_phy)
+		bcmasp_ephy_enable_set(intf, true);
+	else
+		bcmasp_rgmii_mode_en_set(intf, true);
+	bcmasp_configure_port(intf);
+
+	/* This is an ugly quirk but we have not been correctly
+	 * interpreting the phy_interface values and we have done that
+	 * across different drivers, so at least we are consistent in
+	 * our mistakes.
+	 *
+	 * When the Generic PHY driver is in use either the PHY has
+	 * been strapped or programmed correctly by the boot loader so
+	 * we should stick to our incorrect interpretation since we
+	 * have validated it.
+	 *
+	 * Now when a dedicated PHY driver is in use, we need to
+	 * reverse the meaning of the phy_interface_mode values to
+	 * something that the PHY driver will interpret and act on such
+	 * that we have two mistakes canceling themselves so to speak.
+	 * We only do this for the two modes that GENET driver
+	 * officially supports on Broadcom STB chips:
+	 * PHY_INTERFACE_MODE_RGMII and PHY_INTERFACE_MODE_RGMII_TXID.
+	 * Other modes are not *officially* supported with the boot
+	 * loader and the scripted environment generating Device Tree
+	 * blobs for those platforms.
+	 *
+	 * Note that internal PHY and fixed-link configurations are not
+	 * affected because they use different phy_interface_t values
+	 * or the Generic PHY driver.
+	 */
+	switch (phy_iface) {
+	case PHY_INTERFACE_MODE_RGMII:
+		phy_iface = PHY_INTERFACE_MODE_RGMII_ID;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		phy_iface = PHY_INTERFACE_MODE_RGMII_RXID;
+		break;
+	default:
+		break;
+	}
+
+	if (phy_connect) {
+		phydev = of_phy_connect(dev, intf->phy_dn,
+					bcmasp_adj_link, phy_flags,
+					phy_iface);
+		if (!phydev) {
+			ret = -ENODEV;
+			netdev_err(dev, "could not attach to PHY\n");
+			goto err_phy_disable;
+		}
+	} else {
+		ret = phy_resume(dev->phydev);
+		if (ret)
+			goto err_phy_disable;
+	}
+
+	umac_reset(intf);
+
+	umac_init(intf);
+
+	/* Disable the UniMAC RX/TX */
+	umac_enable_set(intf, (UMC_CMD_RX_EN | UMC_CMD_TX_EN), 0);
+
+	umac_set_hw_addr(intf, dev->dev_addr);
+
+	intf->old_duplex = -1;
+	intf->old_link = -1;
+	intf->old_pause = -1;
+
+	ret = bcmasp_init_tx(intf);
+	if (ret)
+		goto err_phy_disconnect;
+
+	/* Turn on asp */
+	bcmasp_enable_tx(intf, 1);
+
+	ret = bcmasp_init_rx(intf);
+	if (ret)
+		goto err_reclaim_tx;
+
+	bcmasp_enable_rx(intf, 1);
+
+	/* Turn on UniMAC TX/RX */
+	umac_enable_set(intf, (UMC_CMD_RX_EN | UMC_CMD_TX_EN), 1);
+
+	intf->crc_fwd = !!(umac_rl(intf, UMC_CMD) & UMC_CMD_CRC_FWD);
+
+	bcmasp_netif_start(dev);
+
+	netif_start_queue(dev);
+
+	return 0;
+
+err_reclaim_tx:
+	bcmasp_reclaim_free_all_tx(intf);
+err_phy_disconnect:
+	if (phydev)
+		phy_disconnect(phydev);
+err_phy_disable:
+	if (intf->internal_phy)
+		bcmasp_ephy_enable_set(intf, false);
+	else
+		bcmasp_rgmii_mode_en_set(intf, false);
+	return ret;
+}
+
+static int bcmasp_open(struct net_device *dev)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	int ret;
+
+	netif_dbg(intf, ifup, dev, "bcmasp open\n");
+
+	ret = clk_prepare_enable(intf->parent->clk);
+	if (ret)
+		return ret;
+
+	ret = bcmasp_netif_init(dev, true);
+	if (ret)
+		clk_disable_unprepare(intf->parent->clk);
+
+	return ret;
+}
+
+static void bcmasp_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+
+	netif_dbg(intf, tx_err, dev, "transmit timeout!\n");
+}
+
+static int bcmasp_get_phys_port_name(struct net_device *dev,
+				     char *name, size_t len)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+
+	if (snprintf(name, len, "p%d", intf->port) >= len)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void bcmasp_get_stats64(struct net_device *dev,
+			       struct rtnl_link_stats64 *stats)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	struct bcmasp_intf_stats64 *lstats;
+	unsigned int start;
+
+	lstats = &intf->stats64;
+
+	do {
+		start = u64_stats_fetch_begin(&lstats->syncp);
+		stats->rx_packets = u64_stats_read(&lstats->rx_packets);
+		stats->rx_bytes = u64_stats_read(&lstats->rx_bytes);
+		stats->rx_dropped = u64_stats_read(&lstats->rx_dropped);
+		stats->rx_crc_errors = u64_stats_read(&lstats->rx_crc_errs);
+		stats->rx_frame_errors = u64_stats_read(&lstats->rx_sym_errs);
+		stats->rx_errors = stats->rx_crc_errors + stats->rx_frame_errors;
+
+		stats->tx_packets = u64_stats_read(&lstats->tx_packets);
+		stats->tx_bytes = u64_stats_read(&lstats->tx_bytes);
+	} while (u64_stats_fetch_retry(&lstats->syncp, start));
+}
+
+static const struct net_device_ops bcmasp_netdev_ops = {
+	.ndo_open		= bcmasp_open,
+	.ndo_stop		= bcmasp_stop,
+	.ndo_start_xmit		= bcmasp_xmit,
+	.ndo_tx_timeout		= bcmasp_tx_timeout,
+	.ndo_set_rx_mode	= bcmasp_set_rx_mode,
+	.ndo_get_phys_port_name	= bcmasp_get_phys_port_name,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
+	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_get_stats64	= bcmasp_get_stats64,
+};
+
+static void bcmasp_map_res(struct bcmasp_priv *priv, struct bcmasp_intf *intf)
+{
+	/* Per port */
+	intf->res.umac = priv->base + UMC_OFFSET(intf);
+	intf->res.umac2fb = priv->base + (priv->hw_info->umac2fb +
+					  (intf->port * 0x4));
+	intf->res.rgmii = priv->base + RGMII_OFFSET(intf);
+
+	/* Per ch */
+	intf->tx_spb_dma = priv->base + TX_SPB_DMA_OFFSET(intf);
+	intf->res.tx_spb_ctrl = priv->base + TX_SPB_CTRL_OFFSET(intf);
+	intf->res.tx_spb_top = priv->base + TX_SPB_TOP_OFFSET(intf);
+	intf->res.tx_epkt_core = priv->base + TX_EPKT_C_OFFSET(intf);
+	intf->res.tx_pause_ctrl = priv->base + TX_PAUSE_CTRL_OFFSET(intf);
+
+	intf->rx_edpkt_dma = priv->base + RX_EDPKT_DMA_OFFSET(intf);
+	intf->rx_edpkt_cfg = priv->base + RX_EDPKT_CFG_OFFSET(intf);
+}
+
+#define MAX_IRQ_STR_LEN		64
+struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv,
+					    struct device_node *ndev_dn, int i)
+{
+	struct device *dev = &priv->pdev->dev;
+	struct bcmasp_intf *intf;
+	struct net_device *ndev;
+	int ch, port, ret;
+
+	if (of_property_read_u32(ndev_dn, "reg", &port)) {
+		dev_warn(dev, "%s: invalid port number\n", ndev_dn->name);
+		goto err;
+	}
+
+	if (of_property_read_u32(ndev_dn, "brcm,channel", &ch)) {
+		dev_warn(dev, "%s: invalid ch number\n", ndev_dn->name);
+		goto err;
+	}
+
+	ndev = alloc_etherdev(sizeof(struct bcmasp_intf));
+	if (!ndev) {
+		dev_warn(dev, "%s: unable to alloc ndev\n", ndev_dn->name);
+		goto err;
+	}
+	intf = netdev_priv(ndev);
+
+	intf->parent = priv;
+	intf->ndev = ndev;
+	intf->channel = ch;
+	intf->port = port;
+	intf->ndev_dn = ndev_dn;
+	intf->index = i;
+
+	ret = of_get_phy_mode(ndev_dn, &intf->phy_interface);
+	if (ret < 0) {
+		dev_err(dev, "invalid PHY mode property\n");
+		goto err_free_netdev;
+	}
+
+	if (intf->phy_interface == PHY_INTERFACE_MODE_INTERNAL)
+		intf->internal_phy = true;
+
+	intf->phy_dn = of_parse_phandle(ndev_dn, "phy-handle", 0);
+	if (!intf->phy_dn && of_phy_is_fixed_link(ndev_dn)) {
+		ret = of_phy_register_fixed_link(ndev_dn);
+		if (ret) {
+			dev_warn(dev, "%s: failed to register fixed PHY\n",
+				 ndev_dn->name);
+			goto err_free_netdev;
+		}
+		intf->phy_dn = ndev_dn;
+	}
+
+	/* Map resource */
+	bcmasp_map_res(priv, intf);
+
+	if ((!phy_interface_mode_is_rgmii(intf->phy_interface) &&
+	     intf->phy_interface != PHY_INTERFACE_MODE_MII &&
+	     intf->phy_interface != PHY_INTERFACE_MODE_INTERNAL) ||
+	    (intf->port != 1 && intf->internal_phy)) {
+		netdev_err(intf->ndev, "invalid PHY mode: %s for port %d\n",
+			   phy_modes(intf->phy_interface), intf->port);
+		ret = -EINVAL;
+		goto err_free_netdev;
+	}
+
+	ret = of_get_ethdev_address(ndev_dn, ndev);
+	if (ret) {
+		netdev_warn(ndev, "using random Ethernet MAC\n");
+		eth_hw_addr_random(ndev);
+	}
+
+	SET_NETDEV_DEV(ndev, dev);
+	intf->ops = &bcmasp_intf_ops;
+	ndev->netdev_ops = &bcmasp_netdev_ops;
+	ndev->ethtool_ops = &bcmasp_ethtool_ops;
+	intf->msg_enable = netif_msg_init(-1, NETIF_MSG_DRV |
+					  NETIF_MSG_PROBE |
+					  NETIF_MSG_LINK);
+	ndev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
+			  NETIF_F_RXCSUM;
+	ndev->hw_features |= ndev->features;
+	ndev->needed_headroom += sizeof(struct bcmasp_pkt_offload);
+
+	return intf;
+
+err_free_netdev:
+	free_netdev(ndev);
+err:
+	return NULL;
+}
+
+void bcmasp_interface_destroy(struct bcmasp_intf *intf)
+{
+	if (intf->ndev->reg_state == NETREG_REGISTERED)
+		unregister_netdev(intf->ndev);
+	if (of_phy_is_fixed_link(intf->ndev_dn))
+		of_phy_deregister_fixed_link(intf->ndev_dn);
+	free_netdev(intf->ndev);
+}
+
+int bcmasp_interface_suspend(struct bcmasp_intf *intf)
+{
+	struct net_device *dev = intf->ndev;
+	int ret = 0;
+
+	if (!netif_running(dev))
+		return 0;
+
+	netif_device_detach(dev);
+
+	bcmasp_netif_deinit(dev);
+
+	ret = phy_suspend(dev->phydev);
+	if (ret)
+		goto out;
+
+	if (intf->internal_phy)
+		bcmasp_ephy_enable_set(intf, false);
+	else
+		bcmasp_rgmii_mode_en_set(intf, false);
+
+	/* If Wake-on-LAN is disabled, we can safely
+	 * disable the network interface clocks.
+	 */
+	bcmasp_core_clock_set_intf(intf, false);
+
+	clk_disable_unprepare(intf->parent->clk);
+
+	return ret;
+
+out:
+	bcmasp_netif_init(dev, false);
+	return ret;
+}
+
+int bcmasp_interface_resume(struct bcmasp_intf *intf)
+{
+	struct net_device *dev = intf->ndev;
+	int ret;
+
+	if (!netif_running(dev))
+		return 0;
+
+	ret = clk_prepare_enable(intf->parent->clk);
+	if (ret)
+		return ret;
+
+	ret = bcmasp_netif_init(dev, false);
+	if (ret)
+		goto out;
+
+	netif_device_attach(dev);
+
+	return 0;
+
+out:
+	clk_disable_unprepare(intf->parent->clk);
+	return ret;
+}
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
new file mode 100644
index 0000000000000..b259a475207fc
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
@@ -0,0 +1,196 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BCMASP_INTF_DEFS_H
+#define __BCMASP_INTF_DEFS_H
+
+#define UMC_OFFSET(intf)		\
+	((((intf)->port) * 0x800) + 0xc000)
+#define  UMC_CMD			0x008
+#define   UMC_CMD_TX_EN			BIT(0)
+#define   UMC_CMD_RX_EN			BIT(1)
+#define   UMC_CMD_SPEED_SHIFT		0x2
+#define    UMC_CMD_SPEED_MASK		0x3
+#define    UMC_CMD_SPEED_10		0x0
+#define    UMC_CMD_SPEED_100		0x1
+#define    UMC_CMD_SPEED_1000		0x2
+#define    UMC_CMD_SPEED_2500		0x3
+#define   UMC_CMD_PROMISC		BIT(4)
+#define   UMC_CMD_PAD_EN		BIT(5)
+#define   UMC_CMD_CRC_FWD		BIT(6)
+#define   UMC_CMD_PAUSE_FWD		BIT(7)
+#define   UMC_CMD_RX_PAUSE_IGNORE	BIT(8)
+#define   UMC_CMD_TX_ADDR_INS		BIT(9)
+#define   UMC_CMD_HD_EN			BIT(10)
+#define   UMC_CMD_SW_RESET		BIT(13)
+#define   UMC_CMD_LCL_LOOP_EN		BIT(15)
+#define   UMC_CMD_AUTO_CONFIG		BIT(22)
+#define   UMC_CMD_CNTL_FRM_EN		BIT(23)
+#define   UMC_CMD_NO_LEN_CHK		BIT(24)
+#define   UMC_CMD_RMT_LOOP_EN		BIT(25)
+#define   UMC_CMD_PRBL_EN		BIT(27)
+#define   UMC_CMD_TX_PAUSE_IGNORE	BIT(28)
+#define   UMC_CMD_TX_RX_EN		BIT(29)
+#define   UMC_CMD_RUNT_FILTER_DIS	BIT(30)
+#define  UMC_MAC0			0x0c
+#define  UMC_MAC1			0x10
+#define  UMC_FRM_LEN			0x14
+#define  UMC_EEE_CTRL			0x64
+#define   EN_LPI_RX_PAUSE		BIT(0)
+#define   EN_LPI_TX_PFC			BIT(1)
+#define   EN_LPI_TX_PAUSE		BIT(2)
+#define   EEE_EN			BIT(3)
+#define   RX_FIFO_CHECK			BIT(4)
+#define   EEE_TX_CLK_DIS		BIT(5)
+#define   DIS_EEE_10M			BIT(6)
+#define   LP_IDLE_PREDICTION_MODE	BIT(7)
+#define  UMC_EEE_LPI_TIMER		0x68
+#define  UMC_PAUSE_CNTRL		0x330
+#define  UMC_TX_FLUSH			0x334
+#define  UMC_MIB_START			0x400
+#define  UMC_MIB_CNTRL			0x580
+#define   UMC_MIB_CNTRL_RX_CNT_RST	BIT(0)
+#define   UMC_MIB_CNTRL_RUNT_CNT_RST	BIT(1)
+#define   UMC_MIB_CNTRL_TX_CNT_RST	BIT(2)
+#define  UMC_RX_MAX_PKT_SZ		0x608
+#define  UMC_MPD_CTRL			0x620
+#define   UMC_MPD_CTRL_MPD_EN		BIT(0)
+#define   UMC_MPD_CTRL_PSW_EN		BIT(27)
+#define  UMC_PSW_MS			0x624
+#define  UMC_PSW_LS			0x628
+
+#define UMAC2FB_OFFSET_2_1		0x9f044
+#define UMAC2FB_OFFSET			0x9f03c
+#define  UMAC2FB_CFG			0x0
+#define   UMAC2FB_CFG_OPUT_EN		BIT(0)
+#define   UMAC2FB_CFG_VLAN_EN		BIT(1)
+#define   UMAC2FB_CFG_SNAP_EN		BIT(2)
+#define   UMAC2FB_CFG_BCM_TG_EN		BIT(3)
+#define   UMAC2FB_CFG_IPUT_EN		BIT(4)
+#define   UMAC2FB_CFG_CHID_SHIFT	8
+#define   UMAC2FB_CFG_OK_SEND_SHIFT	24
+#define   UMAC2FB_CFG_DEFAULT_EN	\
+		(UMAC2FB_CFG_OPUT_EN | UMAC2FB_CFG_VLAN_EN \
+		| UMAC2FB_CFG_SNAP_EN | UMAC2FB_CFG_IPUT_EN)
+
+#define RGMII_OFFSET(intf)	\
+	((((intf)->port) * 0x100) + 0xd000)
+#define  RGMII_EPHY_CNTRL		0x00
+#define    RGMII_EPHY_CFG_IDDQ_BIAS	BIT(0)
+#define    RGMII_EPHY_CFG_EXT_PWRDOWN	BIT(1)
+#define    RGMII_EPHY_CFG_FORCE_DLL_EN	BIT(2)
+#define    RGMII_EPHY_CFG_IDDQ_GLOBAL	BIT(3)
+#define    RGMII_EPHY_CK25_DIS		BIT(4)
+#define    RGMII_EPHY_RESET		BIT(7)
+#define  RGMII_OOB_CNTRL		0x0c
+#define   RGMII_LINK			BIT(4)
+#define   RGMII_OOB_DIS			BIT(5)
+#define   RGMII_MODE_EN			BIT(6)
+#define   RGMII_ID_MODE_DIS		BIT(16)
+
+#define RGMII_PORT_CNTRL		0x60
+#define   RGMII_PORT_MODE_EPHY		0
+#define   RGMII_PORT_MODE_GPHY		1
+#define   RGMII_PORT_MODE_EXT_EPHY	2
+#define   RGMII_PORT_MODE_EXT_GPHY	3
+#define   RGMII_PORT_MODE_EXT_RVMII	4
+#define   RGMII_PORT_MODE_MASK		GENMASK(2, 0)
+
+#define RGMII_SYS_LED_CNTRL		0x74
+#define  RGMII_SYS_LED_CNTRL_LINK_OVRD	BIT(15)
+
+#define TX_SPB_DMA_OFFSET(intf) \
+	((((intf)->channel) * 0x30) + 0x48180)
+#define  TX_SPB_DMA_READ		0x00
+#define  TX_SPB_DMA_BASE		0x08
+#define  TX_SPB_DMA_END			0x10
+#define  TX_SPB_DMA_VALID		0x18
+#define  TX_SPB_DMA_FIFO_CTRL		0x20
+#define   TX_SPB_DMA_FIFO_FLUSH		BIT(0)
+#define  TX_SPB_DMA_FIFO_STATUS		0x24
+
+#define TX_SPB_CTRL_OFFSET(intf) \
+	((((intf)->channel) * 0x68) + 0x49340)
+#define  TX_SPB_CTRL_ENABLE		0x0
+#define   TX_SPB_CTRL_ENABLE_EN		BIT(0)
+#define  TX_SPB_CTRL_XF_CTRL2		0x20
+#define   TX_SPB_CTRL_XF_BID_SHIFT	16
+
+#define TX_SPB_TOP_OFFSET(intf) \
+	((((intf)->channel) * 0x1c) + 0x4a0e0)
+#define TX_SPB_TOP_BLKOUT		0x0
+#define TX_SPB_TOP_SPRE_BW_CTRL		0x4
+
+#define TX_EPKT_C_OFFSET(intf) \
+	((((intf)->channel) * 0x120) + 0x40900)
+#define  TX_EPKT_C_CFG_MISC		0x0
+#define   TX_EPKT_C_CFG_MISC_EN		BIT(0)
+#define   TX_EPKT_C_CFG_MISC_PT		BIT(1)
+#define   TX_EPKT_C_CFG_MISC_PS_SHIFT	14
+#define   TX_EPKT_C_CFG_MISC_FD_SHIFT	20
+
+#define TX_PAUSE_CTRL_OFFSET(intf) \
+	((((intf)->channel * 0xc) + 0x49a20))
+#define  TX_PAUSE_MAP_VECTOR		0x8
+
+#define RX_EDPKT_DMA_OFFSET(intf) \
+	((((intf)->channel) * 0x38) + 0x9ca00)
+#define  RX_EDPKT_DMA_WRITE		0x00
+#define  RX_EDPKT_DMA_READ		0x08
+#define  RX_EDPKT_DMA_BASE		0x10
+#define  RX_EDPKT_DMA_END		0x18
+#define  RX_EDPKT_DMA_VALID		0x20
+#define  RX_EDPKT_DMA_FULLNESS		0x28
+#define  RX_EDPKT_DMA_MIN_THRES		0x2c
+#define  RX_EDPKT_DMA_CH_XONOFF		0x30
+
+#define RX_EDPKT_CFG_OFFSET(intf) \
+	((((intf)->channel) * 0x70) + 0x9c600)
+#define  RX_EDPKT_CFG_CFG0		0x0
+#define   RX_EDPKT_CFG_CFG0_DBUF_SHIFT	9
+#define    RX_EDPKT_CFG_CFG0_RBUF	0x0
+#define    RX_EDPKT_CFG_CFG0_RBUF_4K	0x1
+#define    RX_EDPKT_CFG_CFG0_BUF_4K	0x2
+/* EFRM STUFF, 0 = no byte stuff, 1 = two byte stuff */
+#define   RX_EDPKT_CFG_CFG0_EFRM_STUF	BIT(11)
+#define   RX_EDPKT_CFG_CFG0_BALN_SHIFT	12
+#define    RX_EDPKT_CFG_CFG0_NO_ALN	0
+#define    RX_EDPKT_CFG_CFG0_4_ALN	2
+#define    RX_EDPKT_CFG_CFG0_64_ALN	6
+#define  RX_EDPKT_RING_BUFFER_WRITE	0x38
+#define  RX_EDPKT_RING_BUFFER_READ	0x40
+#define  RX_EDPKT_RING_BUFFER_BASE	0x48
+#define  RX_EDPKT_RING_BUFFER_END	0x50
+#define  RX_EDPKT_RING_BUFFER_VALID	0x58
+#define  RX_EDPKT_CFG_ENABLE		0x6c
+#define   RX_EDPKT_CFG_ENABLE_EN	BIT(0)
+
+#define RX_SPB_DMA_OFFSET(intf) \
+	((((intf)->channel) * 0x30) + 0xa0000)
+#define  RX_SPB_DMA_READ		0x00
+#define  RX_SPB_DMA_BASE		0x08
+#define  RX_SPB_DMA_END			0x10
+#define  RX_SPB_DMA_VALID		0x18
+#define  RX_SPB_DMA_FIFO_CTRL		0x20
+#define   RX_SPB_DMA_FIFO_FLUSH		BIT(0)
+#define  RX_SPB_DMA_FIFO_STATUS		0x24
+
+#define RX_SPB_CTRL_OFFSET(intf) \
+	((((intf)->channel - 6) * 0x68) + 0xa1000)
+#define  RX_SPB_CTRL_ENABLE		0x00
+#define   RX_SPB_CTRL_ENABLE_EN		BIT(0)
+
+#define RX_PAUSE_CTRL_OFFSET(intf) \
+	((((intf)->channel - 6) * 0x4) + 0xa1138)
+#define  RX_PAUSE_MAP_VECTOR		0x00
+
+#define RX_SPB_TOP_CTRL_OFFSET(intf) \
+	((((intf)->channel - 6) * 0x14) + 0xa2000)
+#define  RX_SPB_TOP_BLKOUT		0x00
+
+#define NUM_4K_BUFFERS			32
+#define RING_BUFFER_SIZE		(PAGE_SIZE * NUM_4K_BUFFERS)
+
+#define DESC_RING_COUNT			(64 * NUM_4K_BUFFERS)
+#define DESC_SIZE			16
+#define DESC_RING_SIZE			(DESC_RING_COUNT * DESC_SIZE)
+
+#endif
-- 
GitLab


From a2f0751206b03374f6d02f89c18a60f1bb238fea Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 13 Jul 2023 15:18:59 -0700
Subject: [PATCH 0151/1806] net: bcmasp: Add support for WoL magic packet

Add support for Wake-On-Lan magic packet and magic packet with password.

Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.c   | 144 ++++++++++++++++++
 drivers/net/ethernet/broadcom/asp2/bcmasp.h   |  18 +++
 .../ethernet/broadcom/asp2/bcmasp_ethtool.c   |  36 +++++
 .../net/ethernet/broadcom/asp2/bcmasp_intf.c  |  76 +++++++--
 4 files changed, 262 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index 83494641b545c..894c14dca9116 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -436,6 +436,135 @@ void bcmasp_core_clock_set_intf(struct bcmasp_intf *intf, bool en)
 	spin_unlock_irqrestore(&priv->clk_lock, flags);
 }
 
+static irqreturn_t bcmasp_isr_wol(int irq, void *data)
+{
+	struct bcmasp_priv *priv = data;
+	u32 status;
+
+	/* No L3 IRQ, so we good */
+	if (priv->wol_irq <= 0)
+		goto irq_handled;
+
+	status = wakeup_intr2_core_rl(priv, ASP_WAKEUP_INTR2_STATUS) &
+		~wakeup_intr2_core_rl(priv, ASP_WAKEUP_INTR2_MASK_STATUS);
+	wakeup_intr2_core_wl(priv, status, ASP_WAKEUP_INTR2_CLEAR);
+
+irq_handled:
+	pm_wakeup_event(&priv->pdev->dev, 0);
+	return IRQ_HANDLED;
+}
+
+static int bcmasp_get_and_request_irq(struct bcmasp_priv *priv, int i)
+{
+	struct platform_device *pdev = priv->pdev;
+	int irq, ret;
+
+	irq = platform_get_irq_optional(pdev, i);
+	if (irq < 0)
+		return irq;
+
+	ret = devm_request_irq(&pdev->dev, irq, bcmasp_isr_wol, 0,
+			       pdev->name, priv);
+	if (ret)
+		return ret;
+
+	return irq;
+}
+
+static void bcmasp_init_wol_shared(struct bcmasp_priv *priv)
+{
+	struct platform_device *pdev = priv->pdev;
+	struct device *dev = &pdev->dev;
+	int irq;
+
+	irq = bcmasp_get_and_request_irq(priv, 1);
+	if (irq < 0) {
+		dev_warn(dev, "Failed to init WoL irq: %d\n", irq);
+		return;
+	}
+
+	priv->wol_irq = irq;
+	priv->wol_irq_enabled_mask = 0;
+	device_set_wakeup_capable(&pdev->dev, 1);
+}
+
+static void bcmasp_enable_wol_shared(struct bcmasp_intf *intf, bool en)
+{
+	struct bcmasp_priv *priv = intf->parent;
+	struct device *dev = &priv->pdev->dev;
+
+	if (en) {
+		if (priv->wol_irq_enabled_mask) {
+			set_bit(intf->port, &priv->wol_irq_enabled_mask);
+			return;
+		}
+
+		/* First enable */
+		set_bit(intf->port, &priv->wol_irq_enabled_mask);
+		enable_irq_wake(priv->wol_irq);
+		device_set_wakeup_enable(dev, 1);
+	} else {
+		if (!priv->wol_irq_enabled_mask)
+			return;
+
+		clear_bit(intf->port, &priv->wol_irq_enabled_mask);
+		if (priv->wol_irq_enabled_mask)
+			return;
+
+		/* Last disable */
+		disable_irq_wake(priv->wol_irq);
+		device_set_wakeup_enable(dev, 0);
+	}
+}
+
+static void bcmasp_wol_irq_destroy_shared(struct bcmasp_priv *priv)
+{
+	if (priv->wol_irq > 0)
+		free_irq(priv->wol_irq, priv);
+}
+
+static void bcmasp_init_wol_per_intf(struct bcmasp_priv *priv)
+{
+	struct platform_device *pdev = priv->pdev;
+	struct device *dev = &pdev->dev;
+	struct bcmasp_intf *intf;
+	int irq;
+
+	list_for_each_entry(intf, &priv->intfs, list) {
+		irq = bcmasp_get_and_request_irq(priv, intf->port + 1);
+		if (irq < 0) {
+			dev_warn(dev, "Failed to init WoL irq(port %d): %d\n",
+				 intf->port, irq);
+			continue;
+		}
+
+		intf->wol_irq = irq;
+		intf->wol_irq_enabled = false;
+		device_set_wakeup_capable(&pdev->dev, 1);
+	}
+}
+
+static void bcmasp_enable_wol_per_intf(struct bcmasp_intf *intf, bool en)
+{
+	struct device *dev = &intf->parent->pdev->dev;
+
+	if (en ^ intf->wol_irq_enabled)
+		irq_set_irq_wake(intf->wol_irq, en);
+
+	intf->wol_irq_enabled = en;
+	device_set_wakeup_enable(dev, en);
+}
+
+static void bcmasp_wol_irq_destroy_per_intf(struct bcmasp_priv *priv)
+{
+	struct bcmasp_intf *intf;
+
+	list_for_each_entry(intf, &priv->intfs, list) {
+		if (intf->wol_irq > 0)
+			free_irq(intf->wol_irq, priv);
+	}
+}
+
 static struct bcmasp_hw_info v20_hw_info = {
 	.rx_ctrl_flush = ASP_RX_CTRL_FLUSH,
 	.umac2fb = UMAC2FB_OFFSET,
@@ -445,6 +574,9 @@ static struct bcmasp_hw_info v20_hw_info = {
 };
 
 static const struct bcmasp_plat_data v20_plat_data = {
+	.init_wol = bcmasp_init_wol_per_intf,
+	.enable_wol = bcmasp_enable_wol_per_intf,
+	.destroy_wol = bcmasp_wol_irq_destroy_per_intf,
 	.hw_info = &v20_hw_info,
 };
 
@@ -458,6 +590,9 @@ static struct bcmasp_hw_info v21_hw_info = {
 };
 
 static const struct bcmasp_plat_data v21_plat_data = {
+	.init_wol = bcmasp_init_wol_shared,
+	.enable_wol = bcmasp_enable_wol_shared,
+	.destroy_wol = bcmasp_wol_irq_destroy_shared,
 	.hw_info = &v21_hw_info,
 };
 
@@ -521,12 +656,16 @@ static int bcmasp_probe(struct platform_device *pdev)
 	priv->pdev = pdev;
 	spin_lock_init(&priv->mda_lock);
 	spin_lock_init(&priv->clk_lock);
+	mutex_init(&priv->wol_lock);
 	INIT_LIST_HEAD(&priv->intfs);
 
 	pdata = device_get_match_data(&pdev->dev);
 	if (!pdata)
 		return dev_err_probe(dev, -EINVAL, "unable to find platform data\n");
 
+	priv->init_wol = pdata->init_wol;
+	priv->enable_wol = pdata->enable_wol;
+	priv->destroy_wol = pdata->destroy_wol;
 	priv->hw_info = pdata->hw_info;
 
 	/* Enable all clocks to ensure successful probing */
@@ -570,6 +709,9 @@ static int bcmasp_probe(struct platform_device *pdev)
 		i++;
 	}
 
+	/* Check and enable WoL */
+	priv->init_wol(priv);
+
 	/* Drop the clock reference count now and let ndo_open()/ndo_close()
 	 * manage it for us from now on.
 	 */
@@ -585,6 +727,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 		if (ret) {
 			netdev_err(intf->ndev,
 				   "failed to register net_device: %d\n", ret);
+			priv->destroy_wol(priv);
 			bcmasp_remove_intfs(priv);
 			goto of_put_exit;
 		}
@@ -605,6 +748,7 @@ static int bcmasp_remove(struct platform_device *pdev)
 	if (!priv)
 		return 0;
 
+	priv->destroy_wol(priv);
 	bcmasp_remove_intfs(priv);
 
 	return 0;
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
index 4fe84d26251df..2cdf22732f4ca 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
@@ -301,6 +301,12 @@ struct bcmasp_intf {
 
 	/* Statistics */
 	struct bcmasp_intf_stats64	stats64;
+
+	u32				wolopts;
+	u8				sopass[SOPASS_MAX];
+	/* Used if per intf wol irq */
+	int				wol_irq;
+	unsigned int			wol_irq_enabled:1;
 };
 
 #define NUM_MDA_FILTERS				32
@@ -321,6 +327,9 @@ struct bcmasp_hw_info {
 };
 
 struct bcmasp_plat_data {
+	void (*init_wol)(struct bcmasp_priv *priv);
+	void (*enable_wol)(struct bcmasp_intf *intf, bool en);
+	void (*destroy_wol)(struct bcmasp_priv *priv);
 	struct bcmasp_hw_info		*hw_info;
 };
 
@@ -331,6 +340,15 @@ struct bcmasp_priv {
 	int				irq;
 	u32				irq_mask;
 
+	/* Used if shared wol irq */
+	struct mutex			wol_lock;
+	int				wol_irq;
+	unsigned long			wol_irq_enabled_mask;
+
+	void (*init_wol)(struct bcmasp_priv *priv);
+	void (*enable_wol)(struct bcmasp_intf *intf, bool en);
+	void (*destroy_wol)(struct bcmasp_priv *priv);
+
 	void __iomem			*base;
 	struct	bcmasp_hw_info		*hw_info;
 
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
index 394c0e1cb026a..ae24a1f74d49d 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
@@ -30,6 +30,40 @@ static void bcmasp_set_msglevel(struct net_device *dev, u32 level)
 	intf->msg_enable = level;
 }
 
+#define BCMASP_SUPPORTED_WAKE   (WAKE_MAGIC | WAKE_MAGICSECURE)
+static void bcmasp_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+
+	wol->supported = BCMASP_SUPPORTED_WAKE;
+	wol->wolopts = intf->wolopts;
+	memset(wol->sopass, 0, sizeof(wol->sopass));
+
+	if (wol->wolopts & WAKE_MAGICSECURE)
+		memcpy(wol->sopass, intf->sopass, sizeof(intf->sopass));
+}
+
+static int bcmasp_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	struct bcmasp_priv *priv = intf->parent;
+	struct device *kdev = &priv->pdev->dev;
+
+	if (!device_can_wakeup(kdev))
+		return -EOPNOTSUPP;
+
+	/* Interface Specific */
+	intf->wolopts = wol->wolopts;
+	if (intf->wolopts & WAKE_MAGICSECURE)
+		memcpy(intf->sopass, wol->sopass, sizeof(wol->sopass));
+
+	mutex_lock(&priv->wol_lock);
+	priv->enable_wol(intf, !!intf->wolopts);
+	mutex_unlock(&priv->wol_lock);
+
+	return 0;
+}
+
 const struct ethtool_ops bcmasp_ethtool_ops = {
 	.get_drvinfo		= bcmasp_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
@@ -37,4 +71,6 @@ const struct ethtool_ops bcmasp_ethtool_ops = {
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 	.get_msglevel		= bcmasp_get_msglevel,
 	.set_msglevel		= bcmasp_set_msglevel,
+	.get_wol		= bcmasp_get_wol,
+	.set_wol		= bcmasp_set_wol,
 };
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index 0232f5cf8909c..21a8d15a47d82 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -1034,7 +1034,7 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
 			netdev_err(dev, "could not attach to PHY\n");
 			goto err_phy_disable;
 		}
-	} else {
+	} else if (!intf->wolopts) {
 		ret = phy_resume(dev->phydev);
 		if (ret)
 			goto err_phy_disable;
@@ -1281,8 +1281,39 @@ void bcmasp_interface_destroy(struct bcmasp_intf *intf)
 	free_netdev(intf->ndev);
 }
 
+static void bcmasp_suspend_to_wol(struct bcmasp_intf *intf)
+{
+	struct net_device *ndev = intf->ndev;
+	u32 reg;
+
+	reg = umac_rl(intf, UMC_MPD_CTRL);
+	if (intf->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE))
+		reg |= UMC_MPD_CTRL_MPD_EN;
+	reg &= ~UMC_MPD_CTRL_PSW_EN;
+	if (intf->wolopts & WAKE_MAGICSECURE) {
+		/* Program the SecureOn password */
+		umac_wl(intf, get_unaligned_be16(&intf->sopass[0]),
+			UMC_PSW_MS);
+		umac_wl(intf, get_unaligned_be32(&intf->sopass[2]),
+			UMC_PSW_LS);
+		reg |= UMC_MPD_CTRL_PSW_EN;
+	}
+	umac_wl(intf, reg, UMC_MPD_CTRL);
+
+	/* UniMAC receive needs to be turned on */
+	umac_enable_set(intf, UMC_CMD_RX_EN, 1);
+
+	if (intf->parent->wol_irq > 0) {
+		wakeup_intr2_core_wl(intf->parent, 0xffffffff,
+				     ASP_WAKEUP_INTR2_MASK_CLEAR);
+	}
+
+	netif_dbg(intf, wol, ndev, "entered WOL mode\n");
+}
+
 int bcmasp_interface_suspend(struct bcmasp_intf *intf)
 {
+	struct device *kdev = &intf->parent->pdev->dev;
 	struct net_device *dev = intf->ndev;
 	int ret = 0;
 
@@ -1293,19 +1324,24 @@ int bcmasp_interface_suspend(struct bcmasp_intf *intf)
 
 	bcmasp_netif_deinit(dev);
 
-	ret = phy_suspend(dev->phydev);
-	if (ret)
-		goto out;
+	if (!intf->wolopts) {
+		ret = phy_suspend(dev->phydev);
+		if (ret)
+			goto out;
 
-	if (intf->internal_phy)
-		bcmasp_ephy_enable_set(intf, false);
-	else
-		bcmasp_rgmii_mode_en_set(intf, false);
+		if (intf->internal_phy)
+			bcmasp_ephy_enable_set(intf, false);
+		else
+			bcmasp_rgmii_mode_en_set(intf, false);
 
-	/* If Wake-on-LAN is disabled, we can safely
-	 * disable the network interface clocks.
-	 */
-	bcmasp_core_clock_set_intf(intf, false);
+		/* If Wake-on-LAN is disabled, we can safely
+		 * disable the network interface clocks.
+		 */
+		bcmasp_core_clock_set_intf(intf, false);
+	}
+
+	if (device_may_wakeup(kdev) && intf->wolopts)
+		bcmasp_suspend_to_wol(intf);
 
 	clk_disable_unprepare(intf->parent->clk);
 
@@ -1316,6 +1352,20 @@ out:
 	return ret;
 }
 
+static void bcmasp_resume_from_wol(struct bcmasp_intf *intf)
+{
+	u32 reg;
+
+	reg = umac_rl(intf, UMC_MPD_CTRL);
+	reg &= ~UMC_MPD_CTRL_MPD_EN;
+	umac_wl(intf, reg, UMC_MPD_CTRL);
+
+	if (intf->parent->wol_irq > 0) {
+		wakeup_intr2_core_wl(intf->parent, 0xffffffff,
+				     ASP_WAKEUP_INTR2_MASK_SET);
+	}
+}
+
 int bcmasp_interface_resume(struct bcmasp_intf *intf)
 {
 	struct net_device *dev = intf->ndev;
@@ -1332,6 +1382,8 @@ int bcmasp_interface_resume(struct bcmasp_intf *intf)
 	if (ret)
 		goto out;
 
+	bcmasp_resume_from_wol(intf);
+
 	netif_device_attach(dev);
 
 	return 0;
-- 
GitLab


From c5d511c4958780338ac93f3e728012d5e17de710 Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 13 Jul 2023 15:19:00 -0700
Subject: [PATCH 0152/1806] net: bcmasp: Add support for wake on net filters

Add support for wake on network filters. The max match is 256 bytes.

Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.c   | 595 ++++++++++++++++++
 drivers/net/ethernet/broadcom/asp2/bcmasp.h   |  40 ++
 .../ethernet/broadcom/asp2/bcmasp_ethtool.c   | 131 +++-
 .../net/ethernet/broadcom/asp2/bcmasp_intf.c  |   3 +
 4 files changed, 768 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index 894c14dca9116..92dfea961add4 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -127,6 +127,597 @@ void bcmasp_flush_rx_port(struct bcmasp_intf *intf)
 	rx_ctrl_core_wl(priv, mask, priv->hw_info->rx_ctrl_flush);
 }
 
+static void bcmasp_netfilt_hw_en_wake(struct bcmasp_priv *priv,
+				      struct bcmasp_net_filter *nfilt)
+{
+	rx_filter_core_wl(priv, ASP_RX_FILTER_NET_OFFSET_L3_1(64),
+			  ASP_RX_FILTER_NET_OFFSET(nfilt->hw_index));
+
+	rx_filter_core_wl(priv, ASP_RX_FILTER_NET_OFFSET_L2(32) |
+			  ASP_RX_FILTER_NET_OFFSET_L3_0(32) |
+			  ASP_RX_FILTER_NET_OFFSET_L3_1(96) |
+			  ASP_RX_FILTER_NET_OFFSET_L4(32),
+			  ASP_RX_FILTER_NET_OFFSET(nfilt->hw_index + 1));
+
+	rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->port + 8) |
+			  ASP_RX_FILTER_NET_CFG_EN |
+			  ASP_RX_FILTER_NET_CFG_L2_EN |
+			  ASP_RX_FILTER_NET_CFG_L3_EN |
+			  ASP_RX_FILTER_NET_CFG_L4_EN |
+			  ASP_RX_FILTER_NET_CFG_L3_FRM(2) |
+			  ASP_RX_FILTER_NET_CFG_L4_FRM(2) |
+			  ASP_RX_FILTER_NET_CFG_UMC(nfilt->port),
+			  ASP_RX_FILTER_NET_CFG(nfilt->hw_index));
+
+	rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->port + 8) |
+			  ASP_RX_FILTER_NET_CFG_EN |
+			  ASP_RX_FILTER_NET_CFG_L2_EN |
+			  ASP_RX_FILTER_NET_CFG_L3_EN |
+			  ASP_RX_FILTER_NET_CFG_L4_EN |
+			  ASP_RX_FILTER_NET_CFG_L3_FRM(2) |
+			  ASP_RX_FILTER_NET_CFG_L4_FRM(2) |
+			  ASP_RX_FILTER_NET_CFG_UMC(nfilt->port),
+			  ASP_RX_FILTER_NET_CFG(nfilt->hw_index + 1));
+}
+
+#define MAX_WAKE_FILTER_SIZE		256
+enum asp_netfilt_reg_type {
+	ASP_NETFILT_MATCH = 0,
+	ASP_NETFILT_MASK,
+	ASP_NETFILT_MAX
+};
+
+static int bcmasp_netfilt_get_reg_offset(struct bcmasp_priv *priv,
+					 struct bcmasp_net_filter *nfilt,
+					 enum asp_netfilt_reg_type reg_type,
+					 u32 offset)
+{
+	u32 block_index, filter_sel;
+
+	if (offset < 32) {
+		block_index = ASP_RX_FILTER_NET_L2;
+		filter_sel = nfilt->hw_index;
+	} else if (offset < 64) {
+		block_index = ASP_RX_FILTER_NET_L2;
+		filter_sel = nfilt->hw_index + 1;
+	} else if (offset < 96) {
+		block_index = ASP_RX_FILTER_NET_L3_0;
+		filter_sel = nfilt->hw_index;
+	} else if (offset < 128) {
+		block_index = ASP_RX_FILTER_NET_L3_0;
+		filter_sel = nfilt->hw_index + 1;
+	} else if (offset < 160) {
+		block_index = ASP_RX_FILTER_NET_L3_1;
+		filter_sel = nfilt->hw_index;
+	} else if (offset < 192) {
+		block_index = ASP_RX_FILTER_NET_L3_1;
+		filter_sel = nfilt->hw_index + 1;
+	} else if (offset < 224) {
+		block_index = ASP_RX_FILTER_NET_L4;
+		filter_sel = nfilt->hw_index;
+	} else if (offset < 256) {
+		block_index = ASP_RX_FILTER_NET_L4;
+		filter_sel = nfilt->hw_index + 1;
+	} else {
+		return -EINVAL;
+	}
+
+	switch (reg_type) {
+	case ASP_NETFILT_MATCH:
+		return ASP_RX_FILTER_NET_PAT(filter_sel, block_index,
+					     (offset % 32));
+	case ASP_NETFILT_MASK:
+		return ASP_RX_FILTER_NET_MASK(filter_sel, block_index,
+					      (offset % 32));
+	default:
+		return -EINVAL;
+	}
+}
+
+static void bcmasp_netfilt_wr(struct bcmasp_priv *priv,
+			      struct bcmasp_net_filter *nfilt,
+			      enum asp_netfilt_reg_type reg_type,
+			      u32 val, u32 offset)
+{
+	int reg_offset;
+
+	/* HW only accepts 4 byte aligned writes */
+	if (!IS_ALIGNED(offset, 4) || offset > MAX_WAKE_FILTER_SIZE)
+		return;
+
+	reg_offset = bcmasp_netfilt_get_reg_offset(priv, nfilt, reg_type,
+						   offset);
+
+	rx_filter_core_wl(priv, val, reg_offset);
+}
+
+static u32 bcmasp_netfilt_rd(struct bcmasp_priv *priv,
+			     struct bcmasp_net_filter *nfilt,
+			     enum asp_netfilt_reg_type reg_type,
+			     u32 offset)
+{
+	int reg_offset;
+
+	/* HW only accepts 4 byte aligned writes */
+	if (!IS_ALIGNED(offset, 4) || offset > MAX_WAKE_FILTER_SIZE)
+		return 0;
+
+	reg_offset = bcmasp_netfilt_get_reg_offset(priv, nfilt, reg_type,
+						   offset);
+
+	return rx_filter_core_rl(priv, reg_offset);
+}
+
+static int bcmasp_netfilt_wr_m_wake(struct bcmasp_priv *priv,
+				    struct bcmasp_net_filter *nfilt,
+				    u32 offset, void *match, void *mask,
+				    size_t size)
+{
+	u32 shift, mask_val = 0, match_val = 0;
+	bool first_byte = true;
+
+	if ((offset + size) > MAX_WAKE_FILTER_SIZE)
+		return -EINVAL;
+
+	while (size--) {
+		/* The HW only accepts 4 byte aligned writes, so if we
+		 * begin unaligned or if remaining bytes less than 4,
+		 * we need to read then write to avoid losing current
+		 * register state
+		 */
+		if (first_byte && (!IS_ALIGNED(offset, 4) || size < 3)) {
+			match_val = bcmasp_netfilt_rd(priv, nfilt,
+						      ASP_NETFILT_MATCH,
+						      ALIGN_DOWN(offset, 4));
+			mask_val = bcmasp_netfilt_rd(priv, nfilt,
+						     ASP_NETFILT_MASK,
+						     ALIGN_DOWN(offset, 4));
+		}
+
+		shift = (3 - (offset % 4)) * 8;
+		match_val &= ~GENMASK(shift + 7, shift);
+		mask_val &= ~GENMASK(shift + 7, shift);
+		match_val |= (u32)(*((u8 *)match) << shift);
+		mask_val |= (u32)(*((u8 *)mask) << shift);
+
+		/* If last byte or last byte of word, write to reg */
+		if (!size || ((offset % 4) == 3)) {
+			bcmasp_netfilt_wr(priv, nfilt, ASP_NETFILT_MATCH,
+					  match_val, ALIGN_DOWN(offset, 4));
+			bcmasp_netfilt_wr(priv, nfilt, ASP_NETFILT_MASK,
+					  mask_val, ALIGN_DOWN(offset, 4));
+			first_byte = true;
+		} else {
+			first_byte = false;
+		}
+
+		offset++;
+		match++;
+		mask++;
+	}
+
+	return 0;
+}
+
+static void bcmasp_netfilt_reset_hw(struct bcmasp_priv *priv,
+				    struct bcmasp_net_filter *nfilt)
+{
+	int i;
+
+	for (i = 0; i < MAX_WAKE_FILTER_SIZE; i += 4) {
+		bcmasp_netfilt_wr(priv, nfilt, ASP_NETFILT_MATCH, 0, i);
+		bcmasp_netfilt_wr(priv, nfilt, ASP_NETFILT_MASK, 0, i);
+	}
+}
+
+static void bcmasp_netfilt_tcpip4_wr(struct bcmasp_priv *priv,
+				     struct bcmasp_net_filter *nfilt,
+				     struct ethtool_tcpip4_spec *match,
+				     struct ethtool_tcpip4_spec *mask,
+				     u32 offset)
+{
+	__be16 val_16, mask_16;
+
+	val_16 = htons(ETH_P_IP);
+	mask_16 = htons(0xFFFF);
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, (ETH_ALEN * 2) + offset,
+				 &val_16, &mask_16, sizeof(val_16));
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 1,
+				 &match->tos, &mask->tos,
+				 sizeof(match->tos));
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 12,
+				 &match->ip4src, &mask->ip4src,
+				 sizeof(match->ip4src));
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 16,
+				 &match->ip4dst, &mask->ip4dst,
+				 sizeof(match->ip4dst));
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 20,
+				 &match->psrc, &mask->psrc,
+				 sizeof(match->psrc));
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 22,
+				 &match->pdst, &mask->pdst,
+				 sizeof(match->pdst));
+}
+
+static void bcmasp_netfilt_tcpip6_wr(struct bcmasp_priv *priv,
+				     struct bcmasp_net_filter *nfilt,
+				     struct ethtool_tcpip6_spec *match,
+				     struct ethtool_tcpip6_spec *mask,
+				     u32 offset)
+{
+	__be16 val_16, mask_16;
+
+	val_16 = htons(ETH_P_IPV6);
+	mask_16 = htons(0xFFFF);
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, (ETH_ALEN * 2) + offset,
+				 &val_16, &mask_16, sizeof(val_16));
+	val_16 = htons(match->tclass << 4);
+	mask_16 = htons(mask->tclass << 4);
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset,
+				 &val_16, &mask_16, sizeof(val_16));
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 8,
+				 &match->ip6src, &mask->ip6src,
+				 sizeof(match->ip6src));
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 24,
+				 &match->ip6dst, &mask->ip6dst,
+				 sizeof(match->ip6dst));
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 40,
+				 &match->psrc, &mask->psrc,
+				 sizeof(match->psrc));
+	bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 42,
+				 &match->pdst, &mask->pdst,
+				 sizeof(match->pdst));
+}
+
+static int bcmasp_netfilt_wr_to_hw(struct bcmasp_priv *priv,
+				   struct bcmasp_net_filter *nfilt)
+{
+	struct ethtool_rx_flow_spec *fs = &nfilt->fs;
+	unsigned int offset = 0;
+	__be16 val_16, mask_16;
+	u8 val_8, mask_8;
+
+	/* Currently only supports wake filters */
+	if (!nfilt->wake_filter)
+		return -EINVAL;
+
+	bcmasp_netfilt_reset_hw(priv, nfilt);
+
+	if (fs->flow_type & FLOW_MAC_EXT) {
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, 0, &fs->h_ext.h_dest,
+					 &fs->m_ext.h_dest,
+					 sizeof(fs->h_ext.h_dest));
+	}
+
+	if ((fs->flow_type & FLOW_EXT) &&
+	    (fs->m_ext.vlan_etype || fs->m_ext.vlan_tci)) {
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, (ETH_ALEN * 2),
+					 &fs->h_ext.vlan_etype,
+					 &fs->m_ext.vlan_etype,
+					 sizeof(fs->h_ext.vlan_etype));
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ((ETH_ALEN * 2) + 2),
+					 &fs->h_ext.vlan_tci,
+					 &fs->m_ext.vlan_tci,
+					 sizeof(fs->h_ext.vlan_tci));
+		offset += VLAN_HLEN;
+	}
+
+	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+	case ETHER_FLOW:
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, 0,
+					 &fs->h_u.ether_spec.h_dest,
+					 &fs->m_u.ether_spec.h_dest,
+					 sizeof(fs->h_u.ether_spec.h_dest));
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_ALEN,
+					 &fs->h_u.ether_spec.h_source,
+					 &fs->m_u.ether_spec.h_source,
+					 sizeof(fs->h_u.ether_spec.h_source));
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, (ETH_ALEN * 2) + offset,
+					 &fs->h_u.ether_spec.h_proto,
+					 &fs->m_u.ether_spec.h_proto,
+					 sizeof(fs->h_u.ether_spec.h_proto));
+
+		break;
+	case IP_USER_FLOW:
+		val_16 = htons(ETH_P_IP);
+		mask_16 = htons(0xFFFF);
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, (ETH_ALEN * 2) + offset,
+					 &val_16, &mask_16, sizeof(val_16));
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 1,
+					 &fs->h_u.usr_ip4_spec.tos,
+					 &fs->m_u.usr_ip4_spec.tos,
+					 sizeof(fs->h_u.usr_ip4_spec.tos));
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 9,
+					 &fs->h_u.usr_ip4_spec.proto,
+					 &fs->m_u.usr_ip4_spec.proto,
+					 sizeof(fs->h_u.usr_ip4_spec.proto));
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 12,
+					 &fs->h_u.usr_ip4_spec.ip4src,
+					 &fs->m_u.usr_ip4_spec.ip4src,
+					 sizeof(fs->h_u.usr_ip4_spec.ip4src));
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 16,
+					 &fs->h_u.usr_ip4_spec.ip4dst,
+					 &fs->m_u.usr_ip4_spec.ip4dst,
+					 sizeof(fs->h_u.usr_ip4_spec.ip4dst));
+		if (!fs->m_u.usr_ip4_spec.l4_4_bytes)
+			break;
+
+		/* Only supports 20 byte IPv4 header */
+		val_8 = 0x45;
+		mask_8 = 0xFF;
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset,
+					 &val_8, &mask_8, sizeof(val_8));
+		bcmasp_netfilt_wr_m_wake(priv, nfilt,
+					 ETH_HLEN + 20 + offset,
+					 &fs->h_u.usr_ip4_spec.l4_4_bytes,
+					 &fs->m_u.usr_ip4_spec.l4_4_bytes,
+					 sizeof(fs->h_u.usr_ip4_spec.l4_4_bytes)
+					 );
+		break;
+	case TCP_V4_FLOW:
+		val_8 = IPPROTO_TCP;
+		mask_8 = 0xFF;
+		bcmasp_netfilt_tcpip4_wr(priv, nfilt, &fs->h_u.tcp_ip4_spec,
+					 &fs->m_u.tcp_ip4_spec, offset);
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 9,
+					 &val_8, &mask_8, sizeof(val_8));
+		break;
+	case UDP_V4_FLOW:
+		val_8 = IPPROTO_UDP;
+		mask_8 = 0xFF;
+		bcmasp_netfilt_tcpip4_wr(priv, nfilt, &fs->h_u.udp_ip4_spec,
+					 &fs->m_u.udp_ip4_spec, offset);
+
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 9,
+					 &val_8, &mask_8, sizeof(val_8));
+		break;
+	case TCP_V6_FLOW:
+		val_8 = IPPROTO_TCP;
+		mask_8 = 0xFF;
+		bcmasp_netfilt_tcpip6_wr(priv, nfilt, &fs->h_u.tcp_ip6_spec,
+					 &fs->m_u.tcp_ip6_spec, offset);
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 6,
+					 &val_8, &mask_8, sizeof(val_8));
+		break;
+	case UDP_V6_FLOW:
+		val_8 = IPPROTO_UDP;
+		mask_8 = 0xFF;
+		bcmasp_netfilt_tcpip6_wr(priv, nfilt, &fs->h_u.udp_ip6_spec,
+					 &fs->m_u.udp_ip6_spec, offset);
+		bcmasp_netfilt_wr_m_wake(priv, nfilt, ETH_HLEN + offset + 6,
+					 &val_8, &mask_8, sizeof(val_8));
+		break;
+	}
+
+	bcmasp_netfilt_hw_en_wake(priv, nfilt);
+
+	return 0;
+}
+
+void bcmasp_netfilt_suspend(struct bcmasp_intf *intf)
+{
+	struct bcmasp_priv *priv = intf->parent;
+	bool write = false;
+	int ret, i;
+
+	/* Write all filters to HW */
+	for (i = 0; i < NUM_NET_FILTERS; i++) {
+		/* If the filter does not match the port, skip programming. */
+		if (!priv->net_filters[i].claimed ||
+		    priv->net_filters[i].port != intf->port)
+			continue;
+
+		if (i > 0 && (i % 2) &&
+		    priv->net_filters[i].wake_filter &&
+		    priv->net_filters[i - 1].wake_filter)
+			continue;
+
+		ret = bcmasp_netfilt_wr_to_hw(priv, &priv->net_filters[i]);
+		if (!ret)
+			write = true;
+	}
+
+	/* Successfully programmed at least one wake filter
+	 * so enable top level wake config
+	 */
+	if (write)
+		rx_filter_core_wl(priv, (ASP_RX_FILTER_OPUT_EN |
+				  ASP_RX_FILTER_LNR_MD |
+				  ASP_RX_FILTER_GEN_WK_EN |
+				  ASP_RX_FILTER_NT_FLT_EN),
+				  ASP_RX_FILTER_BLK_CTRL);
+}
+
+void bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
+				   u32 *rule_cnt)
+{
+	struct bcmasp_priv *priv = intf->parent;
+	int j = 0, i;
+
+	for (i = 0; i < NUM_NET_FILTERS; i++) {
+		if (!priv->net_filters[i].claimed ||
+		    priv->net_filters[i].port != intf->port)
+			continue;
+
+		if (i > 0 && (i % 2) &&
+		    priv->net_filters[i].wake_filter &&
+		    priv->net_filters[i - 1].wake_filter)
+			continue;
+
+		rule_locs[j++] = priv->net_filters[i].fs.location;
+	}
+
+	*rule_cnt = j;
+}
+
+int bcmasp_netfilt_get_active(struct bcmasp_intf *intf)
+{
+	struct bcmasp_priv *priv = intf->parent;
+	int cnt = 0, i;
+
+	for (i = 0; i < NUM_NET_FILTERS; i++) {
+		if (!priv->net_filters[i].claimed ||
+		    priv->net_filters[i].port != intf->port)
+			continue;
+
+		/* Skip over a wake filter pair */
+		if (i > 0 && (i % 2) &&
+		    priv->net_filters[i].wake_filter &&
+		    priv->net_filters[i - 1].wake_filter)
+			continue;
+
+		cnt++;
+	}
+
+	return cnt;
+}
+
+bool bcmasp_netfilt_check_dup(struct bcmasp_intf *intf,
+			      struct ethtool_rx_flow_spec *fs)
+{
+	struct bcmasp_priv *priv = intf->parent;
+	struct ethtool_rx_flow_spec *cur;
+	size_t fs_size = 0;
+	int i;
+
+	for (i = 0; i < NUM_NET_FILTERS; i++) {
+		if (!priv->net_filters[i].claimed ||
+		    priv->net_filters[i].port != intf->port)
+			continue;
+
+		cur = &priv->net_filters[i].fs;
+
+		if (cur->flow_type != fs->flow_type ||
+		    cur->ring_cookie != fs->ring_cookie)
+			continue;
+
+		switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+		case ETHER_FLOW:
+			fs_size = sizeof(struct ethhdr);
+			break;
+		case IP_USER_FLOW:
+			fs_size = sizeof(struct ethtool_usrip4_spec);
+			break;
+		case TCP_V6_FLOW:
+		case UDP_V6_FLOW:
+			fs_size = sizeof(struct ethtool_tcpip6_spec);
+			break;
+		case TCP_V4_FLOW:
+		case UDP_V4_FLOW:
+			fs_size = sizeof(struct ethtool_tcpip4_spec);
+			break;
+		default:
+			continue;
+		}
+
+		if (memcmp(&cur->h_u, &fs->h_u, fs_size) ||
+		    memcmp(&cur->m_u, &fs->m_u, fs_size))
+			continue;
+
+		if (cur->flow_type & FLOW_EXT) {
+			if (cur->h_ext.vlan_etype != fs->h_ext.vlan_etype ||
+			    cur->m_ext.vlan_etype != fs->m_ext.vlan_etype ||
+			    cur->h_ext.vlan_tci != fs->h_ext.vlan_tci ||
+			    cur->m_ext.vlan_tci != fs->m_ext.vlan_tci ||
+			    cur->h_ext.data[0] != fs->h_ext.data[0])
+				continue;
+		}
+		if (cur->flow_type & FLOW_MAC_EXT) {
+			if (memcmp(&cur->h_ext.h_dest,
+				   &fs->h_ext.h_dest, ETH_ALEN) ||
+			    memcmp(&cur->m_ext.h_dest,
+				   &fs->m_ext.h_dest, ETH_ALEN))
+				continue;
+		}
+
+		return true;
+	}
+
+	return false;
+}
+
+/* If no network filter found, return open filter.
+ * If no more open filters return NULL
+ */
+struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf,
+						  int loc, bool wake_filter,
+						  bool init)
+{
+	struct bcmasp_net_filter *nfilter = NULL;
+	struct bcmasp_priv *priv = intf->parent;
+	int i, open_index = -1;
+
+	/* Check whether we exceed the filter table capacity */
+	if (loc != RX_CLS_LOC_ANY && loc >= NUM_NET_FILTERS)
+		return ERR_PTR(-EINVAL);
+
+	/* If the filter location is busy (already claimed) and we are initializing
+	 * the filter (insertion), return a busy error code.
+	 */
+	if (loc != RX_CLS_LOC_ANY && init && priv->net_filters[loc].claimed)
+		return ERR_PTR(-EBUSY);
+
+	/* We need two filters for wake-up, so we cannot use an odd filter */
+	if (wake_filter && loc != RX_CLS_LOC_ANY && (loc % 2))
+		return ERR_PTR(-EINVAL);
+
+	/* Initialize the loop index based on the desired location or from 0 */
+	i = loc == RX_CLS_LOC_ANY ? 0 : loc;
+
+	for ( ; i < NUM_NET_FILTERS; i++) {
+		/* Found matching network filter */
+		if (!init &&
+		    priv->net_filters[i].claimed &&
+		    priv->net_filters[i].hw_index == i &&
+		    priv->net_filters[i].port == intf->port)
+			return &priv->net_filters[i];
+
+		/* If we don't need a new filter or new filter already found */
+		if (!init || open_index >= 0)
+			continue;
+
+		/* Wake filter conslidates two filters to cover more bytes
+		 * Wake filter is open if...
+		 * 1. It is an even filter
+		 * 2. The current and next filter is not claimed
+		 */
+		if (wake_filter && !(i % 2) && !priv->net_filters[i].claimed &&
+		    !priv->net_filters[i + 1].claimed)
+			open_index = i;
+		else if (!priv->net_filters[i].claimed)
+			open_index = i;
+	}
+
+	if (open_index >= 0) {
+		nfilter = &priv->net_filters[open_index];
+		nfilter->claimed = true;
+		nfilter->port = intf->port;
+		nfilter->hw_index = open_index;
+	}
+
+	if (wake_filter && open_index >= 0) {
+		/* Claim next filter */
+		priv->net_filters[open_index + 1].claimed = true;
+		priv->net_filters[open_index + 1].wake_filter = true;
+		nfilter->wake_filter = true;
+	}
+
+	return nfilter ? nfilter : ERR_PTR(-EINVAL);
+}
+
+void bcmasp_netfilt_release(struct bcmasp_intf *intf,
+			    struct bcmasp_net_filter *nfilt)
+{
+	struct bcmasp_priv *priv = intf->parent;
+
+	if (nfilt->wake_filter) {
+		memset(&priv->net_filters[nfilt->hw_index + 1], 0,
+		       sizeof(struct bcmasp_net_filter));
+	}
+
+	memset(nfilt, 0, sizeof(struct bcmasp_net_filter));
+}
+
 static void bcmasp_addr_to_uint(unsigned char *addr, u32 *high, u32 *low)
 {
 	*high = (u32)(addr[0] << 8 | addr[1]);
@@ -334,6 +925,9 @@ static void bcmasp_core_init_filters(struct bcmasp_priv *priv)
 		priv->mda_filters[i].en = 0;
 	}
 
+	for (i = 0; i < NUM_NET_FILTERS; i++)
+		rx_filter_core_wl(priv, 0x0, ASP_RX_FILTER_NET_CFG(i));
+
 	/* Top level filter enable bit should be enabled at all times, set
 	 * GEN_WAKE_CLEAR to clear the network filter wake-up which would
 	 * otherwise be sticky
@@ -657,6 +1251,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 	spin_lock_init(&priv->mda_lock);
 	spin_lock_init(&priv->clk_lock);
 	mutex_init(&priv->wol_lock);
+	mutex_init(&priv->net_lock);
 	INIT_LIST_HEAD(&priv->intfs);
 
 	pdata = device_get_match_data(&pdev->dev);
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
index 2cdf22732f4ca..fbbde04a0eab3 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
@@ -106,6 +106,14 @@
 #define   ASP_RX_FILTER_NET_OFFSET_L3_1(val)	((val) << 16)
 #define   ASP_RX_FILTER_NET_OFFSET_L4(val)	((val) << 24)
 
+enum asp_rx_net_filter_block {
+	ASP_RX_FILTER_NET_L2 = 0,
+	ASP_RX_FILTER_NET_L3_0,
+	ASP_RX_FILTER_NET_L3_1,
+	ASP_RX_FILTER_NET_L4,
+	ASP_RX_FILTER_NET_BLOCK_MAX
+};
+
 #define ASP_EDPKT_OFFSET			0x9c000
 #define  ASP_EDPKT_ENABLE			0x4
 #define   ASP_EDPKT_ENABLE_EN			BIT(0)
@@ -309,6 +317,17 @@ struct bcmasp_intf {
 	unsigned int			wol_irq_enabled:1;
 };
 
+#define NUM_NET_FILTERS				32
+struct bcmasp_net_filter {
+	struct ethtool_rx_flow_spec	fs;
+
+	bool				claimed;
+	bool				wake_filter;
+
+	int				port;
+	unsigned int			hw_index;
+};
+
 #define NUM_MDA_FILTERS				32
 struct bcmasp_mda_filter {
 	/* Current owner of this filter */
@@ -361,6 +380,11 @@ struct bcmasp_priv {
 
 	/* Protects accesses to ASP_CTRL_CLOCK_CTRL */
 	spinlock_t			clk_lock;
+
+	struct bcmasp_net_filter	net_filters[NUM_NET_FILTERS];
+
+	/* Network filter lock */
+	struct mutex			net_lock;
 };
 
 static inline unsigned long bcmasp_intf_rx_desc_read(struct bcmasp_intf *intf)
@@ -518,4 +542,20 @@ void bcmasp_disable_all_filters(struct bcmasp_intf *intf);
 
 void bcmasp_core_clock_set_intf(struct bcmasp_intf *intf, bool en);
 
+struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf,
+						  int loc, bool wake_filter,
+						  bool init);
+
+bool bcmasp_netfilt_check_dup(struct bcmasp_intf *intf,
+			      struct ethtool_rx_flow_spec *fs);
+
+void bcmasp_netfilt_release(struct bcmasp_intf *intf,
+			    struct bcmasp_net_filter *nfilt);
+
+int bcmasp_netfilt_get_active(struct bcmasp_intf *intf);
+
+void bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
+				   u32 *rule_cnt);
+
+void bcmasp_netfilt_suspend(struct bcmasp_intf *intf);
 #endif
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
index ae24a1f74d49d..eddd1c43f00e6 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
@@ -30,7 +30,7 @@ static void bcmasp_set_msglevel(struct net_device *dev, u32 level)
 	intf->msg_enable = level;
 }
 
-#define BCMASP_SUPPORTED_WAKE   (WAKE_MAGIC | WAKE_MAGICSECURE)
+#define BCMASP_SUPPORTED_WAKE   (WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER)
 static void bcmasp_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmasp_intf *intf = netdev_priv(dev);
@@ -64,6 +64,133 @@ static int bcmasp_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	return 0;
 }
 
+static int bcmasp_flow_insert(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	struct bcmasp_net_filter *nfilter;
+	u32 loc = cmd->fs.location;
+	bool wake = false;
+
+	if (cmd->fs.ring_cookie == RX_CLS_FLOW_WAKE)
+		wake = true;
+
+	/* Currently only supports WAKE filters */
+	if (!wake)
+		return -EOPNOTSUPP;
+
+	switch (cmd->fs.flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+	case ETHER_FLOW:
+	case IP_USER_FLOW:
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* Check if filter already exists */
+	if (bcmasp_netfilt_check_dup(intf, &cmd->fs))
+		return -EINVAL;
+
+	nfilter = bcmasp_netfilt_get_init(intf, loc, wake, true);
+	if (IS_ERR(nfilter))
+		return PTR_ERR(nfilter);
+
+	/* Return the location where we did insert the filter */
+	cmd->fs.location = nfilter->hw_index;
+	memcpy(&nfilter->fs, &cmd->fs, sizeof(struct ethtool_rx_flow_spec));
+
+	/* Since we only support wake filters, defer register programming till
+	 * suspend time.
+	 */
+	return 0;
+}
+
+static int bcmasp_flow_delete(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	struct bcmasp_net_filter *nfilter;
+
+	nfilter = bcmasp_netfilt_get_init(intf, cmd->fs.location, false, false);
+	if (IS_ERR(nfilter))
+		return PTR_ERR(nfilter);
+
+	bcmasp_netfilt_release(intf, nfilter);
+
+	return 0;
+}
+
+static int bcmasp_flow_get(struct bcmasp_intf *intf, struct ethtool_rxnfc *cmd)
+{
+	struct bcmasp_net_filter *nfilter;
+
+	nfilter = bcmasp_netfilt_get_init(intf, cmd->fs.location, false, false);
+	if (IS_ERR(nfilter))
+		return PTR_ERR(nfilter);
+
+	memcpy(&cmd->fs, &nfilter->fs, sizeof(nfilter->fs));
+
+	cmd->data = NUM_NET_FILTERS;
+
+	return 0;
+}
+
+static int bcmasp_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	mutex_lock(&intf->parent->net_lock);
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		ret = bcmasp_flow_insert(dev, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		ret = bcmasp_flow_delete(dev, cmd);
+		break;
+	default:
+		break;
+	}
+
+	mutex_unlock(&intf->parent->net_lock);
+
+	return ret;
+}
+
+static int bcmasp_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
+			    u32 *rule_locs)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	int err = 0;
+
+	mutex_lock(&intf->parent->net_lock);
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXCLSRLCNT:
+		cmd->rule_cnt = bcmasp_netfilt_get_active(intf);
+		/* We support specifying rule locations */
+		cmd->data |= RX_CLS_LOC_SPECIAL;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		err = bcmasp_flow_get(intf, cmd);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		bcmasp_netfilt_get_all_active(intf, rule_locs, &cmd->rule_cnt);
+		cmd->data = NUM_NET_FILTERS;
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	mutex_unlock(&intf->parent->net_lock);
+
+	return err;
+}
+
 const struct ethtool_ops bcmasp_ethtool_ops = {
 	.get_drvinfo		= bcmasp_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
@@ -73,4 +200,6 @@ const struct ethtool_ops bcmasp_ethtool_ops = {
 	.set_msglevel		= bcmasp_set_msglevel,
 	.get_wol		= bcmasp_get_wol,
 	.set_wol		= bcmasp_set_wol,
+	.get_rxnfc		= bcmasp_get_rxnfc,
+	.set_rxnfc		= bcmasp_set_rxnfc,
 };
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index 21a8d15a47d82..ad8422334f38a 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -1300,6 +1300,9 @@ static void bcmasp_suspend_to_wol(struct bcmasp_intf *intf)
 	}
 	umac_wl(intf, reg, UMC_MPD_CTRL);
 
+	if (intf->wolopts & WAKE_FILTER)
+		bcmasp_netfilt_suspend(intf);
+
 	/* UniMAC receive needs to be turned on */
 	umac_enable_set(intf, UMC_CMD_RX_EN, 1);
 
-- 
GitLab


From 550e6f345687253083b289b167651deb42869032 Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 13 Jul 2023 15:19:01 -0700
Subject: [PATCH 0153/1806] net: bcmasp: Add support for eee mode

Add support for eee mode.

Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.h   |  4 ++
 .../ethernet/broadcom/asp2/bcmasp_ethtool.c   | 61 +++++++++++++++++++
 .../net/ethernet/broadcom/asp2/bcmasp_intf.c  |  6 ++
 3 files changed, 71 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
index fbbde04a0eab3..18a44044ad935 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
@@ -315,6 +315,8 @@ struct bcmasp_intf {
 	/* Used if per intf wol irq */
 	int				wol_irq;
 	unsigned int			wol_irq_enabled:1;
+
+	struct ethtool_eee		eee;
 };
 
 #define NUM_NET_FILTERS				32
@@ -558,4 +560,6 @@ void bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 				   u32 *rule_cnt);
 
 void bcmasp_netfilt_suspend(struct bcmasp_intf *intf);
+
+void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable);
 #endif
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
index eddd1c43f00e6..1e96a69043f3d 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
@@ -191,6 +191,65 @@ static int bcmasp_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	return err;
 }
 
+void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable)
+{
+	u32 reg;
+
+	reg = umac_rl(intf, UMC_EEE_CTRL);
+	if (enable)
+		reg |= EEE_EN;
+	else
+		reg &= ~EEE_EN;
+	umac_wl(intf, reg, UMC_EEE_CTRL);
+
+	intf->eee.eee_enabled = enable;
+	intf->eee.eee_active = enable;
+}
+
+static int bcmasp_get_eee(struct net_device *dev, struct ethtool_eee *e)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	struct ethtool_eee *p = &intf->eee;
+
+	if (!dev->phydev)
+		return -ENODEV;
+
+	e->eee_enabled = p->eee_enabled;
+	e->eee_active = p->eee_active;
+	e->tx_lpi_enabled = p->tx_lpi_enabled;
+	e->tx_lpi_timer = umac_rl(intf, UMC_EEE_LPI_TIMER);
+
+	return phy_ethtool_get_eee(dev->phydev, e);
+}
+
+static int bcmasp_set_eee(struct net_device *dev, struct ethtool_eee *e)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	struct ethtool_eee *p = &intf->eee;
+	int ret;
+
+	if (!dev->phydev)
+		return -ENODEV;
+
+	if (!p->eee_enabled) {
+		bcmasp_eee_enable_set(intf, false);
+	} else {
+		ret = phy_init_eee(dev->phydev, 0);
+		if (ret) {
+			netif_err(intf, hw, dev,
+				  "EEE initialization failed: %d\n", ret);
+			return ret;
+		}
+
+		umac_wl(intf, e->tx_lpi_timer, UMC_EEE_LPI_TIMER);
+		intf->eee.eee_active = ret >= 0;
+		intf->eee.tx_lpi_enabled = e->tx_lpi_enabled;
+		bcmasp_eee_enable_set(intf, true);
+	}
+
+	return phy_ethtool_set_eee(dev->phydev, e);
+}
+
 const struct ethtool_ops bcmasp_ethtool_ops = {
 	.get_drvinfo		= bcmasp_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
@@ -202,4 +261,6 @@ const struct ethtool_ops bcmasp_ethtool_ops = {
 	.set_wol		= bcmasp_set_wol,
 	.get_rxnfc		= bcmasp_get_rxnfc,
 	.set_rxnfc		= bcmasp_set_rxnfc,
+	.set_eee		= bcmasp_set_eee,
+	.get_eee		= bcmasp_get_eee,
 };
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index ad8422334f38a..051f882b2766f 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -646,6 +646,9 @@ static void bcmasp_adj_link(struct net_device *dev)
 			UMC_CMD_TX_PAUSE_IGNORE);
 		reg |= cmd_bits;
 		umac_wl(intf, reg, UMC_CMD);
+
+		intf->eee.eee_active = phy_init_eee(phydev, 0) >= 0;
+		bcmasp_eee_enable_set(intf, intf->eee.eee_active);
 	}
 
 	reg = rgmii_rl(intf, RGMII_OOB_CNTRL);
@@ -1387,6 +1390,9 @@ int bcmasp_interface_resume(struct bcmasp_intf *intf)
 
 	bcmasp_resume_from_wol(intf);
 
+	if (intf->eee.eee_enabled)
+		bcmasp_eee_enable_set(intf, true);
+
 	netif_device_attach(dev);
 
 	return 0;
-- 
GitLab


From 6493153467298877e05fe8faa1602588d0ef25b8 Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 13 Jul 2023 15:19:02 -0700
Subject: [PATCH 0154/1806] net: bcmasp: Add support for ethtool standard stats

Add support for eth_mac_stats, rmon_stats, and eth_ctrl_stats.

Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/broadcom/asp2/bcmasp_ethtool.c   | 77 +++++++++++++++++++
 .../ethernet/broadcom/asp2/bcmasp_intf_defs.h | 63 ++++++++++++++-
 2 files changed, 139 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
index 1e96a69043f3d..59d853c2293c5 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
@@ -250,6 +250,80 @@ static int bcmasp_set_eee(struct net_device *dev, struct ethtool_eee *e)
 	return phy_ethtool_set_eee(dev->phydev, e);
 }
 
+static void bcmasp_get_eth_mac_stats(struct net_device *dev,
+				     struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+
+	mac_stats->FramesTransmittedOK = umac_rl(intf, UMC_GTPOK);
+	mac_stats->SingleCollisionFrames = umac_rl(intf, UMC_GTSCL);
+	mac_stats->MultipleCollisionFrames = umac_rl(intf, UMC_GTMCL);
+	mac_stats->FramesReceivedOK = umac_rl(intf, UMC_GRPOK);
+	mac_stats->FrameCheckSequenceErrors = umac_rl(intf, UMC_GRFCS);
+	mac_stats->AlignmentErrors = umac_rl(intf, UMC_GRALN);
+	mac_stats->OctetsTransmittedOK = umac_rl(intf, UMC_GTBYT);
+	mac_stats->FramesWithDeferredXmissions = umac_rl(intf, UMC_GTDRF);
+	mac_stats->LateCollisions = umac_rl(intf, UMC_GTLCL);
+	mac_stats->FramesAbortedDueToXSColls = umac_rl(intf, UMC_GTXCL);
+	mac_stats->OctetsReceivedOK = umac_rl(intf, UMC_GRBYT);
+	mac_stats->MulticastFramesXmittedOK = umac_rl(intf, UMC_GTMCA);
+	mac_stats->BroadcastFramesXmittedOK = umac_rl(intf, UMC_GTBCA);
+	mac_stats->FramesWithExcessiveDeferral = umac_rl(intf, UMC_GTEDF);
+	mac_stats->MulticastFramesReceivedOK = umac_rl(intf, UMC_GRMCA);
+	mac_stats->BroadcastFramesReceivedOK = umac_rl(intf, UMC_GRBCA);
+}
+
+static const struct ethtool_rmon_hist_range bcmasp_rmon_ranges[] = {
+	{    0,   64},
+	{   65,  127},
+	{  128,  255},
+	{  256,  511},
+	{  512, 1023},
+	{ 1024, 1518},
+	{ 1519, 1522},
+	{}
+};
+
+static void bcmasp_get_rmon_stats(struct net_device *dev,
+				  struct ethtool_rmon_stats *rmon_stats,
+				  const struct ethtool_rmon_hist_range **ranges)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+
+	*ranges = bcmasp_rmon_ranges;
+
+	rmon_stats->undersize_pkts = umac_rl(intf, UMC_RRUND);
+	rmon_stats->oversize_pkts = umac_rl(intf, UMC_GROVR);
+	rmon_stats->fragments = umac_rl(intf, UMC_RRFRG);
+	rmon_stats->jabbers = umac_rl(intf, UMC_GRJBR);
+
+	rmon_stats->hist[0] = umac_rl(intf, UMC_GR64);
+	rmon_stats->hist[1] = umac_rl(intf, UMC_GR127);
+	rmon_stats->hist[2] = umac_rl(intf, UMC_GR255);
+	rmon_stats->hist[3] = umac_rl(intf, UMC_GR511);
+	rmon_stats->hist[4] = umac_rl(intf, UMC_GR1023);
+	rmon_stats->hist[5] = umac_rl(intf, UMC_GR1518);
+	rmon_stats->hist[6] = umac_rl(intf, UMC_GRMGV);
+
+	rmon_stats->hist_tx[0] = umac_rl(intf, UMC_TR64);
+	rmon_stats->hist_tx[1] = umac_rl(intf, UMC_TR127);
+	rmon_stats->hist_tx[2] = umac_rl(intf, UMC_TR255);
+	rmon_stats->hist_tx[3] = umac_rl(intf, UMC_TR511);
+	rmon_stats->hist_tx[4] = umac_rl(intf, UMC_TR1023);
+	rmon_stats->hist_tx[5] = umac_rl(intf, UMC_TR1518);
+	rmon_stats->hist_tx[6] = umac_rl(intf, UMC_TRMGV);
+}
+
+static void bcmasp_get_eth_ctrl_stats(struct net_device *dev,
+				      struct ethtool_eth_ctrl_stats *ctrl_stats)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+
+	ctrl_stats->MACControlFramesTransmitted = umac_rl(intf, UMC_GTXCF);
+	ctrl_stats->MACControlFramesReceived = umac_rl(intf, UMC_GRXCF);
+	ctrl_stats->UnsupportedOpcodesReceived = umac_rl(intf, UMC_GRXUO);
+}
+
 const struct ethtool_ops bcmasp_ethtool_ops = {
 	.get_drvinfo		= bcmasp_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
@@ -263,4 +337,7 @@ const struct ethtool_ops bcmasp_ethtool_ops = {
 	.set_rxnfc		= bcmasp_set_rxnfc,
 	.set_eee		= bcmasp_set_eee,
 	.get_eee		= bcmasp_get_eee,
+	.get_eth_mac_stats	= bcmasp_get_eth_mac_stats,
+	.get_rmon_stats		= bcmasp_get_rmon_stats,
+	.get_eth_ctrl_stats	= bcmasp_get_eth_ctrl_stats,
 };
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
index b259a475207fc..ad742612895fc 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
@@ -45,7 +45,68 @@
 #define  UMC_EEE_LPI_TIMER		0x68
 #define  UMC_PAUSE_CNTRL		0x330
 #define  UMC_TX_FLUSH			0x334
-#define  UMC_MIB_START			0x400
+#define  UMC_GR64			0x400
+#define  UMC_GR127			0x404
+#define  UMC_GR255			0x408
+#define  UMC_GR511			0x40c
+#define  UMC_GR1023			0x410
+#define  UMC_GR1518			0x414
+#define  UMC_GRMGV			0x418
+#define  UMC_GR2047			0x41c
+#define  UMC_GR4095			0x420
+#define  UMC_GR9216			0x424
+#define  UMC_GRPKT			0x428
+#define  UMC_GRBYT			0x42c
+#define  UMC_GRMCA			0x430
+#define  UMC_GRBCA			0x434
+#define  UMC_GRFCS			0x438
+#define  UMC_GRXCF			0x43c
+#define  UMC_GRXPF			0x440
+#define  UMC_GRXUO			0x444
+#define  UMC_GRALN			0x448
+#define  UMC_GRFLR			0x44c
+#define  UMC_GRCDE			0x450
+#define  UMC_GRFCR			0x454
+#define  UMC_GROVR			0x458
+#define  UMC_GRJBR			0x45c
+#define  UMC_GRMTUE			0x460
+#define  UMC_GRPOK			0x464
+#define  UMC_GRUC			0x468
+#define  UMC_GRPPP			0x46c
+#define  UMC_GRMCRC			0x470
+#define  UMC_TR64			0x480
+#define  UMC_TR127			0x484
+#define  UMC_TR255			0x488
+#define  UMC_TR511			0x48c
+#define  UMC_TR1023			0x490
+#define  UMC_TR1518			0x494
+#define  UMC_TRMGV			0x498
+#define  UMC_TR2047			0x49c
+#define  UMC_TR4095			0x4a0
+#define  UMC_TR9216			0x4a4
+#define  UMC_GTPKT			0x4a8
+#define  UMC_GTMCA			0x4ac
+#define  UMC_GTBCA			0x4b0
+#define  UMC_GTXPF			0x4b4
+#define  UMC_GTXCF			0x4b8
+#define  UMC_GTFCS			0x4bc
+#define  UMC_GTOVR			0x4c0
+#define  UMC_GTDRF			0x4c4
+#define  UMC_GTEDF			0x4c8
+#define  UMC_GTSCL			0x4cc
+#define  UMC_GTMCL			0x4d0
+#define  UMC_GTLCL			0x4d4
+#define  UMC_GTXCL			0x4d8
+#define  UMC_GTFRG			0x4dc
+#define  UMC_GTNCL			0x4e0
+#define  UMC_GTJBR			0x4e4
+#define  UMC_GTBYT			0x4e8
+#define  UMC_GTPOK			0x4ec
+#define  UMC_GTUC			0x4f0
+#define  UMC_RRPKT			0x500
+#define  UMC_RRUND			0x504
+#define  UMC_RRFRG			0x508
+#define  UMC_RRBYT			0x50c
 #define  UMC_MIB_CNTRL			0x580
 #define   UMC_MIB_CNTRL_RX_CNT_RST	BIT(0)
 #define   UMC_MIB_CNTRL_RUNT_CNT_RST	BIT(1)
-- 
GitLab


From 7c10691e1f5e2c2b358340aaed5eefccc1df17c5 Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 13 Jul 2023 15:19:03 -0700
Subject: [PATCH 0155/1806] net: bcmasp: Add support for ethtool driver stats

Add support for ethernet driver specific stats.

Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.c   |   4 +-
 drivers/net/ethernet/broadcom/asp2/bcmasp.h   |  21 +++
 .../ethernet/broadcom/asp2/bcmasp_ethtool.c   | 160 ++++++++++++++++++
 .../net/ethernet/broadcom/asp2/bcmasp_intf.c  |  18 +-
 4 files changed, 199 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index 92dfea961add4..a9984efff6d18 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -895,8 +895,10 @@ int bcmasp_set_en_mda_filter(struct bcmasp_intf *intf, unsigned char *addr,
 
 		/* Attempt to combine filters */
 		ret = bcmasp_combine_set_filter(intf, addr, mask, i);
-		if (!ret)
+		if (!ret) {
+			intf->mib.filters_combine_cnt++;
 			return 0;
+		}
 	}
 
 	/* Create new filter if possible */
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
index 18a44044ad935..6bfcaa7f95a83 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
@@ -244,6 +244,26 @@ struct bcmasp_intf_stats64 {
 	struct u64_stats_sync		syncp;
 };
 
+struct bcmasp_mib_counters {
+	u32	edpkt_ts;
+	u32	edpkt_rx_pkt_cnt;
+	u32	edpkt_hdr_ext_cnt;
+	u32	edpkt_hdr_out_cnt;
+	u32	umac_frm_cnt;
+	u32	fb_frm_cnt;
+	u32	fb_rx_fifo_depth;
+	u32	fb_out_frm_cnt;
+	u32	fb_filt_out_frm_cnt;
+	u32	alloc_rx_skb_failed;
+	u32	tx_dma_failed;
+	u32	mc_filters_full_cnt;
+	u32	uc_filters_full_cnt;
+	u32	filters_combine_cnt;
+	u32	promisc_filters_cnt;
+	u32	tx_realloc_offload_failed;
+	u32	tx_timeout_cnt;
+};
+
 struct bcmasp_intf_ops {
 	unsigned long (*rx_desc_read)(struct bcmasp_intf *intf);
 	void (*rx_buffer_write)(struct bcmasp_intf *intf, dma_addr_t addr);
@@ -309,6 +329,7 @@ struct bcmasp_intf {
 
 	/* Statistics */
 	struct bcmasp_intf_stats64	stats64;
+	struct bcmasp_mib_counters	mib;
 
 	u32				wolopts;
 	u8				sopass[SOPASS_MAX];
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
index 59d853c2293c5..c4f1604d5ab39 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #define pr_fmt(fmt)				"bcmasp_ethtool: " fmt
 
+#include <asm-generic/unaligned.h>
 #include <linux/ethtool.h>
 #include <linux/netdevice.h>
 #include <linux/platform_device.h>
@@ -8,6 +9,162 @@
 #include "bcmasp.h"
 #include "bcmasp_intf_defs.h"
 
+enum bcmasp_stat_type {
+	BCMASP_STAT_RX_EDPKT,
+	BCMASP_STAT_RX_CTRL,
+	BCMASP_STAT_RX_CTRL_PER_INTF,
+	BCMASP_STAT_SOFT,
+};
+
+struct bcmasp_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	enum bcmasp_stat_type type;
+	u32 reg_offset;
+};
+
+#define STAT_BCMASP_SOFT_MIB(str) { \
+	.stat_string = str, \
+	.type = BCMASP_STAT_SOFT, \
+}
+
+#define STAT_BCMASP_OFFSET(str, _type, offset) { \
+	.stat_string = str, \
+	.type = _type, \
+	.reg_offset = offset, \
+}
+
+#define STAT_BCMASP_RX_EDPKT(str, offset) \
+	STAT_BCMASP_OFFSET(str, BCMASP_STAT_RX_EDPKT, offset)
+#define STAT_BCMASP_RX_CTRL(str, offset) \
+	STAT_BCMASP_OFFSET(str, BCMASP_STAT_RX_CTRL, offset)
+#define STAT_BCMASP_RX_CTRL_PER_INTF(str, offset) \
+	STAT_BCMASP_OFFSET(str, BCMASP_STAT_RX_CTRL_PER_INTF, offset)
+
+/* Must match the order of struct bcmasp_mib_counters */
+static const struct bcmasp_stats bcmasp_gstrings_stats[] = {
+	/* EDPKT counters */
+	STAT_BCMASP_RX_EDPKT("RX Time Stamp", ASP_EDPKT_RX_TS_COUNTER),
+	STAT_BCMASP_RX_EDPKT("RX PKT Count", ASP_EDPKT_RX_PKT_CNT),
+	STAT_BCMASP_RX_EDPKT("RX PKT Buffered", ASP_EDPKT_HDR_EXTR_CNT),
+	STAT_BCMASP_RX_EDPKT("RX PKT Pushed to DRAM", ASP_EDPKT_HDR_OUT_CNT),
+	/* ASP RX control */
+	STAT_BCMASP_RX_CTRL_PER_INTF("Frames From Unimac",
+				     ASP_RX_CTRL_UMAC_0_FRAME_COUNT),
+	STAT_BCMASP_RX_CTRL_PER_INTF("Frames From Port",
+				     ASP_RX_CTRL_FB_0_FRAME_COUNT),
+	STAT_BCMASP_RX_CTRL_PER_INTF("RX Buffer FIFO Depth",
+				     ASP_RX_CTRL_FB_RX_FIFO_DEPTH),
+	STAT_BCMASP_RX_CTRL("Frames Out(Buffer)",
+			    ASP_RX_CTRL_FB_OUT_FRAME_COUNT),
+	STAT_BCMASP_RX_CTRL("Frames Out(Filters)",
+			    ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT),
+	/* Software maintained statistics */
+	STAT_BCMASP_SOFT_MIB("RX SKB Alloc Failed"),
+	STAT_BCMASP_SOFT_MIB("TX DMA Failed"),
+	STAT_BCMASP_SOFT_MIB("Multicast Filters Full"),
+	STAT_BCMASP_SOFT_MIB("Unicast Filters Full"),
+	STAT_BCMASP_SOFT_MIB("MDA Filters Combined"),
+	STAT_BCMASP_SOFT_MIB("Promisc Filter Set"),
+	STAT_BCMASP_SOFT_MIB("TX Realloc For Offload Failed"),
+	STAT_BCMASP_SOFT_MIB("Tx Timeout Count"),
+};
+
+#define BCMASP_STATS_LEN	ARRAY_SIZE(bcmasp_gstrings_stats)
+
+static u16 bcmasp_stat_fixup_offset(struct bcmasp_intf *intf,
+				    const struct bcmasp_stats *s)
+{
+	struct bcmasp_priv *priv = intf->parent;
+
+	if (!strcmp("Frames Out(Buffer)", s->stat_string))
+		return priv->hw_info->rx_ctrl_fb_out_frame_count;
+
+	if (!strcmp("Frames Out(Filters)", s->stat_string))
+		return priv->hw_info->rx_ctrl_fb_filt_out_frame_count;
+
+	if (!strcmp("RX Buffer FIFO Depth", s->stat_string))
+		return priv->hw_info->rx_ctrl_fb_rx_fifo_depth;
+
+	return s->reg_offset;
+}
+
+static int bcmasp_get_sset_count(struct net_device *dev, int string_set)
+{
+	switch (string_set) {
+	case ETH_SS_STATS:
+		return BCMASP_STATS_LEN;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void bcmasp_get_strings(struct net_device *dev, u32 stringset,
+			       u8 *data)
+{
+	unsigned int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < BCMASP_STATS_LEN; i++) {
+			memcpy(data + i * ETH_GSTRING_LEN,
+			       bcmasp_gstrings_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+		}
+		break;
+	default:
+		return;
+	}
+}
+
+static void bcmasp_update_mib_counters(struct bcmasp_intf *intf)
+{
+	unsigned int i;
+
+	for (i = 0; i < BCMASP_STATS_LEN; i++) {
+		const struct bcmasp_stats *s;
+		u32 offset, val;
+		char *p;
+
+		s = &bcmasp_gstrings_stats[i];
+		offset = bcmasp_stat_fixup_offset(intf, s);
+		switch (s->type) {
+		case BCMASP_STAT_SOFT:
+			continue;
+		case BCMASP_STAT_RX_EDPKT:
+			val = rx_edpkt_core_rl(intf->parent, offset);
+			break;
+		case BCMASP_STAT_RX_CTRL:
+			val = rx_ctrl_core_rl(intf->parent, offset);
+			break;
+		case BCMASP_STAT_RX_CTRL_PER_INTF:
+			offset += sizeof(u32) * intf->port;
+			val = rx_ctrl_core_rl(intf->parent, offset);
+			break;
+		default:
+			continue;
+		}
+		p = (char *)(&intf->mib) + (i * sizeof(u32));
+		put_unaligned(val, (u32 *)p);
+	}
+}
+
+static void bcmasp_get_ethtool_stats(struct net_device *dev,
+				     struct ethtool_stats *stats,
+				     u64 *data)
+{
+	struct bcmasp_intf *intf = netdev_priv(dev);
+	unsigned int i;
+	char *p;
+
+	if (netif_running(dev))
+		bcmasp_update_mib_counters(intf);
+
+	for (i = 0; i < BCMASP_STATS_LEN; i++) {
+		p = (char *)(&intf->mib) + (i * sizeof(u32));
+		data[i] = *(u32 *)p;
+	}
+}
+
 static void bcmasp_get_drvinfo(struct net_device *dev,
 			       struct ethtool_drvinfo *info)
 {
@@ -340,4 +497,7 @@ const struct ethtool_ops bcmasp_ethtool_ops = {
 	.get_eth_mac_stats	= bcmasp_get_eth_mac_stats,
 	.get_rmon_stats		= bcmasp_get_rmon_stats,
 	.get_eth_ctrl_stats	= bcmasp_get_eth_ctrl_stats,
+	.get_strings		= bcmasp_get_strings,
+	.get_ethtool_stats	= bcmasp_get_ethtool_stats,
+	.get_sset_count		= bcmasp_get_sset_count,
 };
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index 051f882b2766f..53e5428812552 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -104,15 +104,19 @@ static void bcmasp_set_rx_mode(struct net_device *dev)
 
 		netdev_for_each_mc_addr(ha, dev) {
 			ret = bcmasp_set_en_mda_filter(intf, ha->addr, mask);
-			if (ret)
+			if (ret) {
+				intf->mib.mc_filters_full_cnt++;
 				goto set_promisc;
+			}
 		}
 	}
 
 	netdev_for_each_uc_addr(ha, dev) {
 		ret = bcmasp_set_en_mda_filter(intf, ha->addr, mask);
-		if (ret)
+		if (ret) {
+			intf->mib.uc_filters_full_cnt++;
 			goto set_promisc;
+		}
 	}
 
 	spin_unlock_bh(&intf->parent->mda_lock);
@@ -120,6 +124,7 @@ static void bcmasp_set_rx_mode(struct net_device *dev)
 
 set_promisc:
 	bcmasp_set_promisc(intf, 1);
+	intf->mib.promisc_filters_cnt++;
 
 	/* disable all filters used by this port */
 	bcmasp_disable_all_filters(intf);
@@ -155,6 +160,7 @@ static struct sk_buff *bcmasp_csum_offload(struct net_device *dev,
 					   struct sk_buff *skb,
 					   bool *csum_hw)
 {
+	struct bcmasp_intf *intf = netdev_priv(dev);
 	u32 header = 0, header2 = 0, epkt = 0;
 	struct bcmasp_pkt_offload *offload;
 	unsigned int header_cnt = 0;
@@ -165,8 +171,10 @@ static struct sk_buff *bcmasp_csum_offload(struct net_device *dev,
 		return skb;
 
 	ret = skb_cow_head(skb, sizeof(*offload));
-	if (ret < 0)
+	if (ret < 0) {
+		intf->mib.tx_realloc_offload_failed++;
 		goto help;
+	}
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
@@ -305,6 +313,7 @@ static netdev_tx_t bcmasp_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 
 		if (dma_mapping_error(kdev, mapping)) {
+			intf->mib.tx_dma_failed++;
 			spb_index = intf->tx_spb_index;
 			for (j = 0; j < i; j++) {
 				bcmasp_clean_txcb(intf, spb_index);
@@ -541,6 +550,8 @@ static int bcmasp_rx_poll(struct napi_struct *napi, int budget)
 			u64_stats_update_begin(&stats->syncp);
 			u64_stats_inc(&stats->rx_dropped);
 			u64_stats_update_end(&stats->syncp);
+			intf->mib.alloc_rx_skb_failed++;
+
 			goto next;
 		}
 
@@ -1116,6 +1127,7 @@ static void bcmasp_tx_timeout(struct net_device *dev, unsigned int txqueue)
 	struct bcmasp_intf *intf = netdev_priv(dev);
 
 	netif_dbg(intf, tx_err, dev, "transmit timeout!\n");
+	intf->mib.tx_timeout_cnt++;
 }
 
 static int bcmasp_get_phys_port_name(struct net_device *dev,
-- 
GitLab


From 9de2b402d818fcb257e61308b190661f30d36c33 Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 13 Jul 2023 15:19:04 -0700
Subject: [PATCH 0156/1806] net: phy: mdio-bcm-unimac: Add asp v2.0 support

Add mdio compat string for ASP 2.0 ethernet driver.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/mdio/mdio-bcm-unimac.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/mdio/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c
index bfc9be23c9731..6b26a0803696d 100644
--- a/drivers/net/mdio/mdio-bcm-unimac.c
+++ b/drivers/net/mdio/mdio-bcm-unimac.c
@@ -334,6 +334,8 @@ static SIMPLE_DEV_PM_OPS(unimac_mdio_pm_ops,
 			 unimac_mdio_suspend, unimac_mdio_resume);
 
 static const struct of_device_id unimac_mdio_ids[] = {
+	{ .compatible = "brcm,asp-v2.1-mdio", },
+	{ .compatible = "brcm,asp-v2.0-mdio", },
 	{ .compatible = "brcm,genet-mdio-v5", },
 	{ .compatible = "brcm,genet-mdio-v4", },
 	{ .compatible = "brcm,genet-mdio-v3", },
-- 
GitLab


From 9fa0bba012c2dd6d2b0db893314a4cc252a91b5f Mon Sep 17 00:00:00 2001
From: Florian Fainelli <florian.fainelli@broadcom.com>
Date: Thu, 13 Jul 2023 15:19:05 -0700
Subject: [PATCH 0157/1806] net: phy: bcm7xxx: Add EPHY entry for 74165

74165 is a 16nm process SoC with a 10/100 integrated Ethernet PHY,
utilize the recently defined 16nm EPHY macro to configure that PHY.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm7xxx.c | 1 +
 include/linux/brcmphy.h   | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index f8c17a253f8b3..8478b081c058d 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -913,6 +913,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7278, "Broadcom BCM7278"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7364, "Broadcom BCM7364"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7366, "Broadcom BCM7366"),
+	BCM7XXX_16NM_EPHY(PHY_ID_BCM74165, "Broadcom BCM74165"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM74371, "Broadcom BCM74371"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7439, "Broadcom BCM7439"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7439_2, "Broadcom BCM7439 (2)"),
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 5d732f48f7876..c55810a43541a 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -44,6 +44,7 @@
 #define PHY_ID_BCM7366			0x600d8490
 #define PHY_ID_BCM7346			0x600d8650
 #define PHY_ID_BCM7362			0x600d84b0
+#define PHY_ID_BCM74165			0x359052c0
 #define PHY_ID_BCM7425			0x600d86b0
 #define PHY_ID_BCM7429			0x600d8730
 #define PHY_ID_BCM7435			0x600d8750
-- 
GitLab


From 3abf3d15ffff62f906e6c7626efb69d136141556 Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 13 Jul 2023 15:19:06 -0700
Subject: [PATCH 0158/1806] MAINTAINERS: ASP 2.0 Ethernet driver maintainers

Add maintainers entry for ASP 2.0 Ethernet driver.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index d1fc5d26c6999..9a5863f1b0165 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4145,6 +4145,15 @@ F:	drivers/net/mdio/mdio-bcm-unimac.c
 F:	include/linux/platform_data/bcmgenet.h
 F:	include/linux/platform_data/mdio-bcm-unimac.h
 
+BROADCOM ASP 2.0 ETHERNET DRIVER
+M:	Justin Chen <justin.chen@broadcom.com>
+M:	Florian Fainelli <florian.fainelli@broadcom.com>
+L:	bcm-kernel-feedback-list@broadcom.com
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml
+F:	drivers/net/ethernet/broadcom/asp2/
+
 BROADCOM IPROC ARM ARCHITECTURE
 M:	Ray Jui <rjui@broadcom.com>
 M:	Scott Branden <sbranden@broadcom.com>
-- 
GitLab


From 608a147a88728f84bbd2efdde3d4984339f1d872 Mon Sep 17 00:00:00 2001
From: Vignesh Viswanathan <quic_viswanat@quicinc.com>
Date: Fri, 14 Jul 2023 11:28:44 +0530
Subject: [PATCH 0159/1806] net: qrtr: ns: Change servers radix tree to xarray

There is a use after free scenario while iterating through the servers
radix tree despite the ns being a single threaded process. This can
happen when the radix tree APIs are not synchronized with the
rcu_read_lock() APIs.

Convert the radix tree for servers to xarray to take advantage of the
built in rcu lock usage provided by xarray.

Signed-off-by: Chris Lew <quic_clew@quicinc.com>
Signed-off-by: Vignesh Viswanathan <quic_viswanat@quicinc.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/ns.c | 133 +++++++++-----------------------------------------
 1 file changed, 24 insertions(+), 109 deletions(-)

diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index 0f7a729f1a1fa..af28d9e6b53f5 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -66,7 +66,7 @@ struct qrtr_server {
 
 struct qrtr_node {
 	unsigned int id;
-	struct radix_tree_root servers;
+	struct xarray servers;
 };
 
 static struct qrtr_node *node_get(unsigned int node_id)
@@ -83,6 +83,7 @@ static struct qrtr_node *node_get(unsigned int node_id)
 		return NULL;
 
 	node->id = node_id;
+	xa_init(&node->servers);
 
 	if (radix_tree_insert(&nodes, node_id, node)) {
 		kfree(node);
@@ -193,40 +194,23 @@ static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv,
 
 static int announce_servers(struct sockaddr_qrtr *sq)
 {
-	struct radix_tree_iter iter;
 	struct qrtr_server *srv;
 	struct qrtr_node *node;
-	void __rcu **slot;
+	unsigned long index;
 	int ret;
 
 	node = node_get(qrtr_ns.local_node);
 	if (!node)
 		return 0;
 
-	rcu_read_lock();
 	/* Announce the list of servers registered in this node */
-	radix_tree_for_each_slot(slot, &node->servers, &iter, 0) {
-		srv = radix_tree_deref_slot(slot);
-		if (!srv)
-			continue;
-		if (radix_tree_deref_retry(srv)) {
-			slot = radix_tree_iter_retry(&iter);
-			continue;
-		}
-		slot = radix_tree_iter_resume(slot, &iter);
-		rcu_read_unlock();
-
+	xa_for_each(&node->servers, index, srv) {
 		ret = service_announce_new(sq, srv);
 		if (ret < 0) {
 			pr_err("failed to announce new service\n");
 			return ret;
 		}
-
-		rcu_read_lock();
 	}
-
-	rcu_read_unlock();
-
 	return 0;
 }
 
@@ -256,14 +240,17 @@ static struct qrtr_server *server_add(unsigned int service,
 		goto err;
 
 	/* Delete the old server on the same port */
-	old = radix_tree_lookup(&node->servers, port);
+	old = xa_store(&node->servers, port, srv, GFP_KERNEL);
 	if (old) {
-		radix_tree_delete(&node->servers, port);
-		kfree(old);
+		if (xa_is_err(old)) {
+			pr_err("failed to add server [0x%x:0x%x] ret:%d\n",
+			       srv->service, srv->instance, xa_err(old));
+			goto err;
+		} else {
+			kfree(old);
+		}
 	}
 
-	radix_tree_insert(&node->servers, port, srv);
-
 	trace_qrtr_ns_server_add(srv->service, srv->instance,
 				 srv->node, srv->port);
 
@@ -280,11 +267,11 @@ static int server_del(struct qrtr_node *node, unsigned int port, bool bcast)
 	struct qrtr_server *srv;
 	struct list_head *li;
 
-	srv = radix_tree_lookup(&node->servers, port);
+	srv = xa_load(&node->servers, port);
 	if (!srv)
 		return -ENOENT;
 
-	radix_tree_delete(&node->servers, port);
+	xa_erase(&node->servers, port);
 
 	/* Broadcast the removal of local servers */
 	if (srv->node == qrtr_ns.local_node && bcast)
@@ -344,13 +331,12 @@ static int ctrl_cmd_hello(struct sockaddr_qrtr *sq)
 static int ctrl_cmd_bye(struct sockaddr_qrtr *from)
 {
 	struct qrtr_node *local_node;
-	struct radix_tree_iter iter;
 	struct qrtr_ctrl_pkt pkt;
 	struct qrtr_server *srv;
 	struct sockaddr_qrtr sq;
 	struct msghdr msg = { };
 	struct qrtr_node *node;
-	void __rcu **slot;
+	unsigned long index;
 	struct kvec iv;
 	int ret;
 
@@ -361,22 +347,9 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from)
 	if (!node)
 		return 0;
 
-	rcu_read_lock();
 	/* Advertise removal of this client to all servers of remote node */
-	radix_tree_for_each_slot(slot, &node->servers, &iter, 0) {
-		srv = radix_tree_deref_slot(slot);
-		if (!srv)
-			continue;
-		if (radix_tree_deref_retry(srv)) {
-			slot = radix_tree_iter_retry(&iter);
-			continue;
-		}
-		slot = radix_tree_iter_resume(slot, &iter);
-		rcu_read_unlock();
+	xa_for_each(&node->servers, index, srv)
 		server_del(node, srv->port, true);
-		rcu_read_lock();
-	}
-	rcu_read_unlock();
 
 	/* Advertise the removal of this client to all local servers */
 	local_node = node_get(qrtr_ns.local_node);
@@ -387,18 +360,7 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from)
 	pkt.cmd = cpu_to_le32(QRTR_TYPE_BYE);
 	pkt.client.node = cpu_to_le32(from->sq_node);
 
-	rcu_read_lock();
-	radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) {
-		srv = radix_tree_deref_slot(slot);
-		if (!srv)
-			continue;
-		if (radix_tree_deref_retry(srv)) {
-			slot = radix_tree_iter_retry(&iter);
-			continue;
-		}
-		slot = radix_tree_iter_resume(slot, &iter);
-		rcu_read_unlock();
-
+	xa_for_each(&local_node->servers, index, srv) {
 		sq.sq_family = AF_QIPCRTR;
 		sq.sq_node = srv->node;
 		sq.sq_port = srv->port;
@@ -411,11 +373,7 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from)
 			pr_err("failed to send bye cmd\n");
 			return ret;
 		}
-		rcu_read_lock();
 	}
-
-	rcu_read_unlock();
-
 	return 0;
 }
 
@@ -423,7 +381,6 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from,
 			       unsigned int node_id, unsigned int port)
 {
 	struct qrtr_node *local_node;
-	struct radix_tree_iter iter;
 	struct qrtr_lookup *lookup;
 	struct qrtr_ctrl_pkt pkt;
 	struct msghdr msg = { };
@@ -432,7 +389,7 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from,
 	struct qrtr_node *node;
 	struct list_head *tmp;
 	struct list_head *li;
-	void __rcu **slot;
+	unsigned long index;
 	struct kvec iv;
 	int ret;
 
@@ -477,18 +434,7 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from,
 	pkt.client.node = cpu_to_le32(node_id);
 	pkt.client.port = cpu_to_le32(port);
 
-	rcu_read_lock();
-	radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) {
-		srv = radix_tree_deref_slot(slot);
-		if (!srv)
-			continue;
-		if (radix_tree_deref_retry(srv)) {
-			slot = radix_tree_iter_retry(&iter);
-			continue;
-		}
-		slot = radix_tree_iter_resume(slot, &iter);
-		rcu_read_unlock();
-
+	xa_for_each(&local_node->servers, index, srv) {
 		sq.sq_family = AF_QIPCRTR;
 		sq.sq_node = srv->node;
 		sq.sq_port = srv->port;
@@ -501,11 +447,7 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from,
 			pr_err("failed to send del client cmd\n");
 			return ret;
 		}
-		rcu_read_lock();
 	}
-
-	rcu_read_unlock();
-
 	return 0;
 }
 
@@ -576,13 +518,12 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from,
 static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from,
 			       unsigned int service, unsigned int instance)
 {
-	struct radix_tree_iter node_iter;
 	struct qrtr_server_filter filter;
-	struct radix_tree_iter srv_iter;
 	struct qrtr_lookup *lookup;
+	struct qrtr_server *srv;
 	struct qrtr_node *node;
-	void __rcu **node_slot;
-	void __rcu **srv_slot;
+	unsigned long node_idx;
+	unsigned long srv_idx;
 
 	/* Accept only local observers */
 	if (from->sq_node != qrtr_ns.local_node)
@@ -601,40 +542,14 @@ static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from,
 	filter.service = service;
 	filter.instance = instance;
 
-	rcu_read_lock();
-	radix_tree_for_each_slot(node_slot, &nodes, &node_iter, 0) {
-		node = radix_tree_deref_slot(node_slot);
-		if (!node)
-			continue;
-		if (radix_tree_deref_retry(node)) {
-			node_slot = radix_tree_iter_retry(&node_iter);
-			continue;
-		}
-		node_slot = radix_tree_iter_resume(node_slot, &node_iter);
-
-		radix_tree_for_each_slot(srv_slot, &node->servers,
-					 &srv_iter, 0) {
-			struct qrtr_server *srv;
-
-			srv = radix_tree_deref_slot(srv_slot);
-			if (!srv)
-				continue;
-			if (radix_tree_deref_retry(srv)) {
-				srv_slot = radix_tree_iter_retry(&srv_iter);
-				continue;
-			}
-
+	xa_for_each(&nodes, node_idx, node) {
+		xa_for_each(&node->servers, srv_idx, srv) {
 			if (!server_match(srv, &filter))
 				continue;
 
-			srv_slot = radix_tree_iter_resume(srv_slot, &srv_iter);
-
-			rcu_read_unlock();
 			lookup_notify(from, srv, true);
-			rcu_read_lock();
 		}
 	}
-	rcu_read_unlock();
 
 	/* Empty notification, to indicate end of listing */
 	lookup_notify(from, NULL, true);
-- 
GitLab


From f26b32ef2fe6f7ae0ba56854e666339e105610ad Mon Sep 17 00:00:00 2001
From: Vignesh Viswanathan <quic_viswanat@quicinc.com>
Date: Fri, 14 Jul 2023 11:28:45 +0530
Subject: [PATCH 0160/1806] net: qrtr: ns: Change nodes radix tree to xarray

There is a use after free scenario while iterating through the nodes
radix tree despite the ns being a single threaded process. This can
happen when the radix tree APIs are not synchronized with the
rcu_read_lock() APIs.

Convert the radix tree for nodes to xarray to take advantage of the
built in rcu lock usage provided by xarray.

Signed-off-by: Chris Lew <quic_clew@quicinc.com>
Signed-off-by: Vignesh Viswanathan <quic_viswanat@quicinc.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/ns.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index af28d9e6b53f5..b1db0b519179b 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -16,7 +16,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/qrtr.h>
 
-static RADIX_TREE(nodes, GFP_KERNEL);
+static DEFINE_XARRAY(nodes);
 
 static struct {
 	struct socket *sock;
@@ -73,7 +73,7 @@ static struct qrtr_node *node_get(unsigned int node_id)
 {
 	struct qrtr_node *node;
 
-	node = radix_tree_lookup(&nodes, node_id);
+	node = xa_load(&nodes, node_id);
 	if (node)
 		return node;
 
@@ -85,7 +85,7 @@ static struct qrtr_node *node_get(unsigned int node_id)
 	node->id = node_id;
 	xa_init(&node->servers);
 
-	if (radix_tree_insert(&nodes, node_id, node)) {
+	if (xa_store(&nodes, node_id, node, GFP_KERNEL)) {
 		kfree(node);
 		return NULL;
 	}
-- 
GitLab


From 69940b888e3502868efd1acf3719fd1af810c123 Mon Sep 17 00:00:00 2001
From: Vignesh Viswanathan <quic_viswanat@quicinc.com>
Date: Fri, 14 Jul 2023 11:28:46 +0530
Subject: [PATCH 0161/1806] net: qrtr: Handle IPCR control port format of older
 targets

The destination port value in the IPCR control buffer on older
targets is 0xFFFF. Handle the same by updating the dst_port to
QRTR_PORT_CTRL.

Signed-off-by: Vignesh Viswanathan <quic_viswanat@quicinc.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/af_qrtr.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c
index 78beb74146e74..41ece61eb57ab 100644
--- a/net/qrtr/af_qrtr.c
+++ b/net/qrtr/af_qrtr.c
@@ -23,6 +23,8 @@
 #define QRTR_EPH_PORT_RANGE \
 		XA_LIMIT(QRTR_MIN_EPH_SOCKET, QRTR_MAX_EPH_SOCKET)
 
+#define QRTR_PORT_CTRL_LEGACY 0xffff
+
 /**
  * struct qrtr_hdr_v1 - (I|R)PCrouter packet header version 1
  * @version: protocol version
@@ -495,6 +497,9 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 		goto err;
 	}
 
+	if (cb->dst_port == QRTR_PORT_CTRL_LEGACY)
+		cb->dst_port = QRTR_PORT_CTRL;
+
 	if (!size || len != ALIGN(size, 4) + hdrlen)
 		goto err;
 
-- 
GitLab


From 8b8bc13d89a7d23d14b0e041c73f037c9db997b1 Mon Sep 17 00:00:00 2001
From: Luo Jie <quic_luoj@quicinc.com>
Date: Sun, 16 Jul 2023 16:49:19 +0800
Subject: [PATCH 0162/1806] net: phy: at803x: support qca8081
 genphy_c45_pma_read_abilities

qca8081 PHY supports to use genphy_c45_pma_read_abilities for
getting the PHY features supported except for the autoneg ability

but autoneg ability exists in MDIO_STAT1 instead of MMD7.1, add it
manually after calling genphy_c45_pma_read_abilities.

Signed-off-by: Luo Jie <quic_luoj@quicinc.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index c1f307d90518b..11388ef3f7ef6 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -897,15 +897,6 @@ static int at803x_get_features(struct phy_device *phydev)
 	if (err)
 		return err;
 
-	if (phydev->drv->phy_id == QCA8081_PHY_ID) {
-		err = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_NG_EXTABLE);
-		if (err < 0)
-			return err;
-
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, phydev->supported,
-				err & MDIO_PMA_NG_EXTABLE_2_5GBT);
-	}
-
 	if (phydev->drv->phy_id != ATH8031_PHY_ID)
 		return 0;
 
@@ -1991,6 +1982,23 @@ static int qca808x_cable_test_get_status(struct phy_device *phydev, bool *finish
 	return 0;
 }
 
+static int qca808x_get_features(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_c45_pma_read_abilities(phydev);
+	if (ret)
+		return ret;
+
+	/* The autoneg ability is not existed in bit3 of MMD7.1,
+	 * but it is supported by qca808x PHY, so we add it here
+	 * manually.
+	 */
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported);
+
+	return 0;
+}
+
 static struct phy_driver at803x_driver[] = {
 {
 	/* Qualcomm Atheros AR8035 */
@@ -2160,7 +2168,7 @@ static struct phy_driver at803x_driver[] = {
 	.set_tunable		= at803x_set_tunable,
 	.set_wol		= at803x_set_wol,
 	.get_wol		= at803x_get_wol,
-	.get_features		= at803x_get_features,
+	.get_features		= qca808x_get_features,
 	.config_aneg		= at803x_config_aneg,
 	.suspend		= genphy_suspend,
 	.resume			= genphy_resume,
-- 
GitLab


From f3db55ae860a82e1224a909072783ef850e5d228 Mon Sep 17 00:00:00 2001
From: Luo Jie <quic_luoj@quicinc.com>
Date: Sun, 16 Jul 2023 16:49:20 +0800
Subject: [PATCH 0163/1806] net: phy: at803x: merge qca8081 slave seed function

merge the seed enablement and seed value configuration into
one function, since the random seed value is needed to be
configured when the seed is enabled.

Signed-off-by: Luo Jie <quic_luoj@quicinc.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c | 29 +++++++++--------------------
 1 file changed, 9 insertions(+), 20 deletions(-)

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 11388ef3f7ef6..1d4aef60d51a9 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -1725,24 +1725,19 @@ static int qca808x_phy_fast_retrain_config(struct phy_device *phydev)
 	return 0;
 }
 
-static int qca808x_phy_ms_random_seed_set(struct phy_device *phydev)
-{
-	u16 seed_value = get_random_u32_below(QCA808X_MASTER_SLAVE_SEED_RANGE);
-
-	return at803x_debug_reg_mask(phydev, QCA808X_PHY_DEBUG_LOCAL_SEED,
-			QCA808X_MASTER_SLAVE_SEED_CFG,
-			FIELD_PREP(QCA808X_MASTER_SLAVE_SEED_CFG, seed_value));
-}
-
 static int qca808x_phy_ms_seed_enable(struct phy_device *phydev, bool enable)
 {
-	u16 seed_enable = 0;
+	u16 seed_value;
 
-	if (enable)
-		seed_enable = QCA808X_MASTER_SLAVE_SEED_ENABLE;
+	if (!enable)
+		return at803x_debug_reg_mask(phydev, QCA808X_PHY_DEBUG_LOCAL_SEED,
+				QCA808X_MASTER_SLAVE_SEED_ENABLE, 0);
 
+	seed_value = get_random_u32_below(QCA808X_MASTER_SLAVE_SEED_RANGE);
 	return at803x_debug_reg_mask(phydev, QCA808X_PHY_DEBUG_LOCAL_SEED,
-			QCA808X_MASTER_SLAVE_SEED_ENABLE, seed_enable);
+			QCA808X_MASTER_SLAVE_SEED_CFG | QCA808X_MASTER_SLAVE_SEED_ENABLE,
+			FIELD_PREP(QCA808X_MASTER_SLAVE_SEED_CFG, seed_value) |
+			QCA808X_MASTER_SLAVE_SEED_ENABLE);
 }
 
 static int qca808x_config_init(struct phy_device *phydev)
@@ -1766,12 +1761,7 @@ static int qca808x_config_init(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
-	/* Configure lower ramdom seed to make phy linked as slave mode */
-	ret = qca808x_phy_ms_random_seed_set(phydev);
-	if (ret)
-		return ret;
-
-	/* Enable seed */
+	/* Enable seed and configure lower ramdom seed to make phy linked as slave mode */
 	ret = qca808x_phy_ms_seed_enable(phydev, true);
 	if (ret)
 		return ret;
@@ -1816,7 +1806,6 @@ static int qca808x_read_status(struct phy_device *phydev)
 		if (phydev->master_slave_state == MASTER_SLAVE_STATE_ERR) {
 			qca808x_phy_ms_seed_enable(phydev, false);
 		} else {
-			qca808x_phy_ms_random_seed_set(phydev);
 			qca808x_phy_ms_seed_enable(phydev, true);
 		}
 	}
-- 
GitLab


From 7cc3209558002d95c0d45a1276ba4f5f741eec42 Mon Sep 17 00:00:00 2001
From: Luo Jie <quic_luoj@quicinc.com>
Date: Sun, 16 Jul 2023 16:49:21 +0800
Subject: [PATCH 0164/1806] net: phy: at803x: enable qca8081 slave seed
 conditionally

qca8081 is the single port PHY, the slave prefer mode is used
by default.

if the phy master perfer mode is configured, the slave seed
configuration should not be enabled, since the slave seed
enablement is for making PHY linked as slave mode easily.

disable slave seed if the master mode is preferred.

Signed-off-by: Luo Jie <quic_luoj@quicinc.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 1d4aef60d51a9..6cdc1b8f8c4d8 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -1740,6 +1740,12 @@ static int qca808x_phy_ms_seed_enable(struct phy_device *phydev, bool enable)
 			QCA808X_MASTER_SLAVE_SEED_ENABLE);
 }
 
+static bool qca808x_is_prefer_master(struct phy_device *phydev)
+{
+	return (phydev->master_slave_get == MASTER_SLAVE_CFG_MASTER_FORCE) ||
+		(phydev->master_slave_get == MASTER_SLAVE_CFG_MASTER_PREFERRED);
+}
+
 static int qca808x_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -1761,11 +1767,17 @@ static int qca808x_config_init(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
-	/* Enable seed and configure lower ramdom seed to make phy linked as slave mode */
-	ret = qca808x_phy_ms_seed_enable(phydev, true);
-	if (ret)
+	ret = genphy_read_master_slave(phydev);
+	if (ret < 0)
 		return ret;
 
+	if (!qca808x_is_prefer_master(phydev)) {
+		/* Enable seed and configure lower ramdom seed to make phy linked as slave mode */
+		ret = qca808x_phy_ms_seed_enable(phydev, true);
+		if (ret)
+			return ret;
+	}
+
 	/* Configure adc threshold as 100mv for the link 10M */
 	return at803x_debug_reg_mask(phydev, QCA808X_PHY_DEBUG_ADC_THRESHOLD,
 			QCA808X_ADC_THRESHOLD_MASK, QCA808X_ADC_THRESHOLD_100MV);
@@ -1797,13 +1809,16 @@ static int qca808x_read_status(struct phy_device *phydev)
 			phydev->interface = PHY_INTERFACE_MODE_SGMII;
 	} else {
 		/* generate seed as a lower random value to make PHY linked as SLAVE easily,
-		 * except for master/slave configuration fault detected.
+		 * except for master/slave configuration fault detected or the master mode
+		 * preferred.
+		 *
 		 * the reason for not putting this code into the function link_change_notify is
 		 * the corner case where the link partner is also the qca8081 PHY and the seed
 		 * value is configured as the same value, the link can't be up and no link change
 		 * occurs.
 		 */
-		if (phydev->master_slave_state == MASTER_SLAVE_STATE_ERR) {
+		if (phydev->master_slave_state == MASTER_SLAVE_STATE_ERR ||
+				qca808x_is_prefer_master(phydev)) {
 			qca808x_phy_ms_seed_enable(phydev, false);
 		} else {
 			qca808x_phy_ms_seed_enable(phydev, true);
-- 
GitLab


From fea7cfb83d1a2782e39cd101dd44ed2548539de5 Mon Sep 17 00:00:00 2001
From: Luo Jie <quic_luoj@quicinc.com>
Date: Sun, 16 Jul 2023 16:49:22 +0800
Subject: [PATCH 0165/1806] net: phy: at803x: support qca8081 1G chip type

The qca8081 1G chip version does not support 2.5 capability, which
is distinguished from qca8081 2.5G chip according to the bit0 of
register mmd7.0x901d, the 1G version chip also has the same PHY ID
as the normal qca8081 2.5G chip.

Signed-off-by: Luo Jie <quic_luoj@quicinc.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 6cdc1b8f8c4d8..cb4c45c81a853 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -272,6 +272,10 @@
 #define QCA808X_CDT_STATUS_STAT_OPEN		2
 #define QCA808X_CDT_STATUS_STAT_SHORT		3
 
+/* QCA808X 1G chip type */
+#define QCA808X_PHY_MMD7_CHIP_TYPE		0x901d
+#define QCA808X_PHY_CHIP_TYPE_1G		BIT(0)
+
 MODULE_DESCRIPTION("Qualcomm Atheros AR803x and QCA808X PHY driver");
 MODULE_AUTHOR("Matus Ujhelyi");
 MODULE_LICENSE("GPL");
@@ -2000,6 +2004,17 @@ static int qca808x_get_features(struct phy_device *phydev)
 	 */
 	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported);
 
+	/* As for the qca8081 1G version chip, the 2500baseT ability is also
+	 * existed in the bit0 of MMD1.21, we need to remove it manually if
+	 * it is the qca8081 1G chip according to the bit0 of MMD7.0x901d.
+	 */
+	ret = phy_read_mmd(phydev, MDIO_MMD_AN, QCA808X_PHY_MMD7_CHIP_TYPE);
+	if (ret < 0)
+		return ret;
+
+	if (QCA808X_PHY_CHIP_TYPE_1G & ret)
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, phydev->supported);
+
 	return 0;
 }
 
-- 
GitLab


From df9401ff3e6eeaa42bfb06761967f1b71f5afce7 Mon Sep 17 00:00:00 2001
From: Luo Jie <quic_luoj@quicinc.com>
Date: Sun, 16 Jul 2023 16:49:23 +0800
Subject: [PATCH 0166/1806] net: phy: at803x: remove qca8081 1G fast retrain
 and slave seed config

The fast retrain and slave seed configs are only applicable when the 2.5G
ability is supported.

Signed-off-by: Luo Jie <quic_luoj@quicinc.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c | 50 +++++++++++++++++++++++++---------------
 1 file changed, 32 insertions(+), 18 deletions(-)

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index cb4c45c81a853..a141f133b8aa1 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -1750,6 +1750,11 @@ static bool qca808x_is_prefer_master(struct phy_device *phydev)
 		(phydev->master_slave_get == MASTER_SLAVE_CFG_MASTER_PREFERRED);
 }
 
+static bool qca808x_has_fast_retrain_or_slave_seed(struct phy_device *phydev)
+{
+	return linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, phydev->supported);
+}
+
 static int qca808x_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -1766,20 +1771,24 @@ static int qca808x_config_init(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
-	/* Config the fast retrain for the link 2500M */
-	ret = qca808x_phy_fast_retrain_config(phydev);
-	if (ret)
-		return ret;
-
-	ret = genphy_read_master_slave(phydev);
-	if (ret < 0)
-		return ret;
-
-	if (!qca808x_is_prefer_master(phydev)) {
-		/* Enable seed and configure lower ramdom seed to make phy linked as slave mode */
-		ret = qca808x_phy_ms_seed_enable(phydev, true);
+	if (qca808x_has_fast_retrain_or_slave_seed(phydev)) {
+		/* Config the fast retrain for the link 2500M */
+		ret = qca808x_phy_fast_retrain_config(phydev);
 		if (ret)
 			return ret;
+
+		ret = genphy_read_master_slave(phydev);
+		if (ret < 0)
+			return ret;
+
+		if (!qca808x_is_prefer_master(phydev)) {
+			/* Enable seed and configure lower ramdom seed to make phy
+			 * linked as slave mode.
+			 */
+			ret = qca808x_phy_ms_seed_enable(phydev, true);
+			if (ret)
+				return ret;
+		}
 	}
 
 	/* Configure adc threshold as 100mv for the link 10M */
@@ -1821,11 +1830,13 @@ static int qca808x_read_status(struct phy_device *phydev)
 		 * value is configured as the same value, the link can't be up and no link change
 		 * occurs.
 		 */
-		if (phydev->master_slave_state == MASTER_SLAVE_STATE_ERR ||
-				qca808x_is_prefer_master(phydev)) {
-			qca808x_phy_ms_seed_enable(phydev, false);
-		} else {
-			qca808x_phy_ms_seed_enable(phydev, true);
+		if (qca808x_has_fast_retrain_or_slave_seed(phydev)) {
+			if (phydev->master_slave_state == MASTER_SLAVE_STATE_ERR ||
+					qca808x_is_prefer_master(phydev)) {
+				qca808x_phy_ms_seed_enable(phydev, false);
+			} else {
+				qca808x_phy_ms_seed_enable(phydev, true);
+			}
 		}
 	}
 
@@ -1840,7 +1851,10 @@ static int qca808x_soft_reset(struct phy_device *phydev)
 	if (ret < 0)
 		return ret;
 
-	return qca808x_phy_ms_seed_enable(phydev, true);
+	if (qca808x_has_fast_retrain_or_slave_seed(phydev))
+		ret = qca808x_phy_ms_seed_enable(phydev, true);
+
+	return ret;
 }
 
 static bool qca808x_cdt_fault_length_valid(int cdt_code)
-- 
GitLab


From 723970affdd8766fa0d91cd34bf2ffc861538b5f Mon Sep 17 00:00:00 2001
From: Luo Jie <quic_luoj@quicinc.com>
Date: Sun, 16 Jul 2023 16:49:24 +0800
Subject: [PATCH 0167/1806] net: phy: at803x: add qca8081 fifo reset on the
 link changed

The qca8081 sgmii fifo needs to be reset on link down and
released on the link up in case of any abnormal issue
such as the packet blocked on the PHY.

Signed-off-by: Luo Jie <quic_luoj@quicinc.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index a141f133b8aa1..13c4121fa3092 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -276,6 +276,9 @@
 #define QCA808X_PHY_MMD7_CHIP_TYPE		0x901d
 #define QCA808X_PHY_CHIP_TYPE_1G		BIT(0)
 
+#define QCA8081_PHY_SERDES_MMD1_FIFO_CTRL	0x9072
+#define QCA8081_PHY_FIFO_RSTN			BIT(11)
+
 MODULE_DESCRIPTION("Qualcomm Atheros AR803x and QCA808X PHY driver");
 MODULE_AUTHOR("Matus Ujhelyi");
 MODULE_LICENSE("GPL");
@@ -2032,6 +2035,16 @@ static int qca808x_get_features(struct phy_device *phydev)
 	return 0;
 }
 
+static void qca808x_link_change_notify(struct phy_device *phydev)
+{
+	/* Assert interface sgmii fifo on link down, deassert it on link up,
+	 * the interface device address is always phy address added by 1.
+	 */
+	mdiobus_c45_modify_changed(phydev->mdio.bus, phydev->mdio.addr + 1,
+			MDIO_MMD_PMAPMD, QCA8081_PHY_SERDES_MMD1_FIFO_CTRL,
+			QCA8081_PHY_FIFO_RSTN, phydev->link ? QCA8081_PHY_FIFO_RSTN : 0);
+}
+
 static struct phy_driver at803x_driver[] = {
 {
 	/* Qualcomm Atheros AR8035 */
@@ -2210,6 +2223,7 @@ static struct phy_driver at803x_driver[] = {
 	.soft_reset		= qca808x_soft_reset,
 	.cable_test_start	= qca808x_cable_test_start,
 	.cable_test_get_status	= qca808x_cable_test_get_status,
+	.link_change_notify	= qca808x_link_change_notify,
 }, };
 
 module_phy_driver(at803x_driver);
-- 
GitLab


From bb410c03b999a361ab4e11e103d88707b4155bf9 Mon Sep 17 00:00:00 2001
From: Judith Mendez <jm@ti.com>
Date: Fri, 7 Jul 2023 15:47:13 -0500
Subject: [PATCH 0168/1806] dt-bindings: net: can: Remove interrupt properties
 for MCAN

On AM62x SoC, MCANs on MCU domain do not have hardware interrupt
routed to A53 Linux, instead they will use software interrupt by
timer polling.

To enable timer polling method, interrupts should be
optional so remove interrupts property from required section and
add an example for MCAN node with timer polling enabled.

Reviewed-by: Tony Lindgren <tony@atomide.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Judith Mendez <jm@ti.com>
Link: https://lore.kernel.org/all/20230707204714.62964-2-jm@ti.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../bindings/net/can/bosch,m_can.yaml         | 20 +++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml b/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml
index 67879aab623b5..bb518c831f7b1 100644
--- a/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml
+++ b/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml
@@ -122,8 +122,6 @@ required:
   - compatible
   - reg
   - reg-names
-  - interrupts
-  - interrupt-names
   - clocks
   - clock-names
   - bosch,mram-cfg
@@ -132,6 +130,7 @@ additionalProperties: false
 
 examples:
   - |
+    // Example with interrupts
     #include <dt-bindings/clock/imx6sx-clock.h>
     can@20e8000 {
       compatible = "bosch,m_can";
@@ -149,4 +148,21 @@ examples:
       };
     };
 
+  - |
+    // Example with timer polling
+    #include <dt-bindings/clock/imx6sx-clock.h>
+    can@20e8000 {
+      compatible = "bosch,m_can";
+      reg = <0x020e8000 0x4000>, <0x02298000 0x4000>;
+      reg-names = "m_can", "message_ram";
+      clocks = <&clks IMX6SX_CLK_CANFD>,
+               <&clks IMX6SX_CLK_CANFD>;
+      clock-names = "hclk", "cclk";
+      bosch,mram-cfg = <0x0 0 0 32 0 0 0 1>;
+
+      can-transceiver {
+        max-bitrate = <5000000>;
+      };
+    };
+
 ...
-- 
GitLab


From b382380c0d2da427aaffca931e4a3b831048cace Mon Sep 17 00:00:00 2001
From: Judith Mendez <jm@ti.com>
Date: Fri, 7 Jul 2023 15:47:14 -0500
Subject: [PATCH 0169/1806] can: m_can: Add hrtimer to generate software
 interrupt

Introduce timer polling method to MCAN since some SoCs may not
have M_CAN interrupt routed to A53 Linux and do not have
interrupt property in device tree M_CAN node.

On AM62x SoC, MCANs on MCU domain do not have hardware interrupt
routed to A53 Linux, instead they will use timer polling method.

Add an hrtimer to MCAN class device. Each MCAN will have its own
hrtimer instantiated if there is no hardware interrupt found in
device tree M_CAN node. The timer will generate a software
interrupt every 1 ms. In hrtimer callback, we check if there is
a transaction pending by reading a register, then process by
calling the isr if there is.

Tested-by: Hiago De Franco <hiago.franco@toradex.com> # Toradex Verdin AM62
Reviewed-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Judith Mendez <jm@ti.com>
Link: https://lore.kernel.org/all/20230707204714.62964-3-jm@ti.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c          | 32 +++++++++++++++++++++++++-
 drivers/net/can/m_can/m_can.h          |  3 +++
 drivers/net/can/m_can/m_can_platform.c | 21 +++++++++++++----
 3 files changed, 51 insertions(+), 5 deletions(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index c5af92bcc9c98..13fd84b2e2dde 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -11,6 +11,7 @@
 #include <linux/bitfield.h>
 #include <linux/can/dev.h>
 #include <linux/ethtool.h>
+#include <linux/hrtimer.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
@@ -308,6 +309,9 @@ enum m_can_reg {
 #define TX_EVENT_MM_MASK	GENMASK(31, 24)
 #define TX_EVENT_TXTS_MASK	GENMASK(15, 0)
 
+/* Hrtimer polling interval */
+#define HRTIMER_POLL_INTERVAL_MS		1
+
 /* The ID and DLC registers are adjacent in M_CAN FIFO memory,
  * and we can save a (potentially slow) bus round trip by combining
  * reads and writes to them.
@@ -1414,6 +1418,12 @@ static int m_can_start(struct net_device *dev)
 
 	m_can_enable_all_interrupts(cdev);
 
+	if (!dev->irq) {
+		dev_dbg(cdev->dev, "Start hrtimer\n");
+		hrtimer_start(&cdev->hrtimer, ms_to_ktime(HRTIMER_POLL_INTERVAL_MS),
+			      HRTIMER_MODE_REL_PINNED);
+	}
+
 	return 0;
 }
 
@@ -1568,6 +1578,11 @@ static void m_can_stop(struct net_device *dev)
 {
 	struct m_can_classdev *cdev = netdev_priv(dev);
 
+	if (!dev->irq) {
+		dev_dbg(cdev->dev, "Stop hrtimer\n");
+		hrtimer_cancel(&cdev->hrtimer);
+	}
+
 	/* disable all interrupts */
 	m_can_disable_all_interrupts(cdev);
 
@@ -1793,6 +1808,18 @@ static netdev_tx_t m_can_start_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
+static enum hrtimer_restart hrtimer_callback(struct hrtimer *timer)
+{
+	struct m_can_classdev *cdev = container_of(timer, struct
+						   m_can_classdev, hrtimer);
+
+	m_can_isr(0, cdev->net);
+
+	hrtimer_forward_now(timer, ms_to_ktime(HRTIMER_POLL_INTERVAL_MS));
+
+	return HRTIMER_RESTART;
+}
+
 static int m_can_open(struct net_device *dev)
 {
 	struct m_can_classdev *cdev = netdev_priv(dev);
@@ -1831,7 +1858,7 @@ static int m_can_open(struct net_device *dev)
 		err = request_threaded_irq(dev->irq, NULL, m_can_isr,
 					   IRQF_ONESHOT,
 					   dev->name, dev);
-	} else {
+	} else if (dev->irq) {
 		err = request_irq(dev->irq, m_can_isr, IRQF_SHARED, dev->name,
 				  dev);
 	}
@@ -2027,6 +2054,9 @@ int m_can_class_register(struct m_can_classdev *cdev)
 			goto clk_disable;
 	}
 
+	if (!cdev->net->irq)
+		cdev->hrtimer.function = &hrtimer_callback;
+
 	ret = m_can_dev_setup(cdev);
 	if (ret)
 		goto rx_offload_del;
diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h
index a839dc71dc9ba..2ac18ac867a45 100644
--- a/drivers/net/can/m_can/m_can.h
+++ b/drivers/net/can/m_can/m_can.h
@@ -15,6 +15,7 @@
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/freezer.h>
+#include <linux/hrtimer.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
@@ -93,6 +94,8 @@ struct m_can_classdev {
 	int is_peripheral;
 
 	struct mram_cfg mcfg[MRAM_CFG_NUM];
+
+	struct hrtimer hrtimer;
 };
 
 struct m_can_classdev *m_can_class_allocate_dev(struct device *dev, int sizeof_priv);
diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c
index 94dc826441136..cdb28d6a092c6 100644
--- a/drivers/net/can/m_can/m_can_platform.c
+++ b/drivers/net/can/m_can/m_can_platform.c
@@ -5,6 +5,7 @@
 //
 // Copyright (C) 2018-19 Texas Instruments Incorporated - http://www.ti.com/
 
+#include <linux/hrtimer.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 
@@ -82,7 +83,7 @@ static int m_can_plat_probe(struct platform_device *pdev)
 	void __iomem *addr;
 	void __iomem *mram_addr;
 	struct phy *transceiver;
-	int irq, ret = 0;
+	int irq = 0, ret = 0;
 
 	mcan_class = m_can_class_allocate_dev(&pdev->dev,
 					      sizeof(struct m_can_plat_priv));
@@ -96,12 +97,24 @@ static int m_can_plat_probe(struct platform_device *pdev)
 		goto probe_fail;
 
 	addr = devm_platform_ioremap_resource_byname(pdev, "m_can");
-	irq = platform_get_irq_byname(pdev, "int0");
-	if (IS_ERR(addr) || irq < 0) {
-		ret = -EINVAL;
+	if (IS_ERR(addr)) {
+		ret = PTR_ERR(addr);
 		goto probe_fail;
 	}
 
+	if (device_property_present(mcan_class->dev, "interrupts") ||
+	    device_property_present(mcan_class->dev, "interrupt-names")) {
+		irq = platform_get_irq_byname(pdev, "int0");
+		if (irq < 0) {
+			ret = irq;
+			goto probe_fail;
+		}
+	} else {
+		dev_dbg(mcan_class->dev, "Polling enabled, initialize hrtimer");
+		hrtimer_init(&mcan_class->hrtimer, CLOCK_MONOTONIC,
+			     HRTIMER_MODE_REL_PINNED);
+	}
+
 	/* message ram could be shared */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "message_ram");
 	if (!res) {
-- 
GitLab


From 2cee73cef253a333c7d48a0f8edda53e3cca990c Mon Sep 17 00:00:00 2001
From: Paul Fertser <fercerpav@gmail.com>
Date: Thu, 13 Jul 2023 12:57:43 +0300
Subject: [PATCH 0170/1806] net: ftgmac100: support getting MAC address from
 NVMEM

Make use of of_get_ethdev_address() to support reading MAC address not
only from the usual DT nodes but also from an NVMEM provider (e.g. using
a dedicated area in an FRU EEPROM).

Signed-off-by: Paul Fertser <fercerpav@gmail.com>
Link: https://lore.kernel.org/r/20230713095743.30517-1-fercerpav@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/faraday/ftgmac100.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index a03879a27b041..9135b918dd490 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -177,16 +177,20 @@ static void ftgmac100_write_mac_addr(struct ftgmac100 *priv, const u8 *mac)
 	iowrite32(laddr, priv->base + FTGMAC100_OFFSET_MAC_LADR);
 }
 
-static void ftgmac100_initial_mac(struct ftgmac100 *priv)
+static int ftgmac100_initial_mac(struct ftgmac100 *priv)
 {
 	u8 mac[ETH_ALEN];
 	unsigned int m;
 	unsigned int l;
+	int err;
 
-	if (!device_get_ethdev_address(priv->dev, priv->netdev)) {
+	err = of_get_ethdev_address(priv->dev->of_node, priv->netdev);
+	if (err == -EPROBE_DEFER)
+		return err;
+	if (!err) {
 		dev_info(priv->dev, "Read MAC address %pM from device tree\n",
 			 priv->netdev->dev_addr);
-		return;
+		return 0;
 	}
 
 	m = ioread32(priv->base + FTGMAC100_OFFSET_MAC_MADR);
@@ -207,6 +211,8 @@ static void ftgmac100_initial_mac(struct ftgmac100 *priv)
 		dev_info(priv->dev, "Generated random MAC address %pM\n",
 			 priv->netdev->dev_addr);
 	}
+
+	return 0;
 }
 
 static int ftgmac100_set_mac_addr(struct net_device *dev, void *p)
@@ -1843,7 +1849,9 @@ static int ftgmac100_probe(struct platform_device *pdev)
 	priv->aneg_pause = true;
 
 	/* MAC address from chip or random one */
-	ftgmac100_initial_mac(priv);
+	err = ftgmac100_initial_mac(priv);
+	if (err)
+		goto err_phy_connect;
 
 	np = pdev->dev.of_node;
 	if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac") ||
-- 
GitLab


From a88dd7538461b2daf6883e5392957b21270638ed Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Fri, 14 Jul 2023 10:12:07 +0100
Subject: [PATCH 0171/1806] net: dsa: remove legacy_pre_march2020 detection

All drivers are now updated for the March 2020 changes, and no longer
make use of the mac_pcs_get_state() or mac_an_restart() operations,
which are now NULL across all DSA drivers. All DSA drivers don't look
at speed, duplex, pause or advertisement in their phylink_mac_config()
method either.

Remove support for these operations from DSA, and stop marking DSA as
a legacy driver by default.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/dsa.h |  3 ---
 net/dsa/port.c    | 41 -----------------------------------------
 2 files changed, 44 deletions(-)

diff --git a/include/net/dsa.h b/include/net/dsa.h
index d309ee7ed04bb..0b9c6aa270474 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -873,8 +873,6 @@ struct dsa_switch_ops {
 	struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds,
 						      int port,
 						      phy_interface_t iface);
-	int	(*phylink_mac_link_state)(struct dsa_switch *ds, int port,
-					  struct phylink_link_state *state);
 	int	(*phylink_mac_prepare)(struct dsa_switch *ds, int port,
 				       unsigned int mode,
 				       phy_interface_t interface);
@@ -884,7 +882,6 @@ struct dsa_switch_ops {
 	int	(*phylink_mac_finish)(struct dsa_switch *ds, int port,
 				      unsigned int mode,
 				      phy_interface_t interface);
-	void	(*phylink_mac_an_restart)(struct dsa_switch *ds, int port);
 	void	(*phylink_mac_link_down)(struct dsa_switch *ds, int port,
 					 unsigned int mode,
 					 phy_interface_t interface);
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 0ce8fd311c787..c63cbfbe6489a 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -1568,27 +1568,6 @@ static void dsa_port_phylink_validate(struct phylink_config *config,
 		phylink_generic_validate(config, supported, state);
 }
 
-static void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config,
-					       struct phylink_link_state *state)
-{
-	struct dsa_port *dp = container_of(config, struct dsa_port, pl_config);
-	struct dsa_switch *ds = dp->ds;
-	int err;
-
-	/* Only called for inband modes */
-	if (!ds->ops->phylink_mac_link_state) {
-		state->link = 0;
-		return;
-	}
-
-	err = ds->ops->phylink_mac_link_state(ds, dp->index, state);
-	if (err < 0) {
-		dev_err(ds->dev, "p%d: phylink_mac_link_state() failed: %d\n",
-			dp->index, err);
-		state->link = 0;
-	}
-}
-
 static struct phylink_pcs *
 dsa_port_phylink_mac_select_pcs(struct phylink_config *config,
 				phy_interface_t interface)
@@ -1646,17 +1625,6 @@ static int dsa_port_phylink_mac_finish(struct phylink_config *config,
 	return err;
 }
 
-static void dsa_port_phylink_mac_an_restart(struct phylink_config *config)
-{
-	struct dsa_port *dp = container_of(config, struct dsa_port, pl_config);
-	struct dsa_switch *ds = dp->ds;
-
-	if (!ds->ops->phylink_mac_an_restart)
-		return;
-
-	ds->ops->phylink_mac_an_restart(ds, dp->index);
-}
-
 static void dsa_port_phylink_mac_link_down(struct phylink_config *config,
 					   unsigned int mode,
 					   phy_interface_t interface)
@@ -1700,11 +1668,9 @@ static void dsa_port_phylink_mac_link_up(struct phylink_config *config,
 static const struct phylink_mac_ops dsa_port_phylink_mac_ops = {
 	.validate = dsa_port_phylink_validate,
 	.mac_select_pcs = dsa_port_phylink_mac_select_pcs,
-	.mac_pcs_get_state = dsa_port_phylink_mac_pcs_get_state,
 	.mac_prepare = dsa_port_phylink_mac_prepare,
 	.mac_config = dsa_port_phylink_mac_config,
 	.mac_finish = dsa_port_phylink_mac_finish,
-	.mac_an_restart = dsa_port_phylink_mac_an_restart,
 	.mac_link_down = dsa_port_phylink_mac_link_down,
 	.mac_link_up = dsa_port_phylink_mac_link_up,
 };
@@ -1720,13 +1686,6 @@ int dsa_port_phylink_create(struct dsa_port *dp)
 	if (err)
 		mode = PHY_INTERFACE_MODE_NA;
 
-	/* Presence of phylink_mac_link_state or phylink_mac_an_restart is
-	 * an indicator of a legacy phylink driver.
-	 */
-	if (ds->ops->phylink_mac_link_state ||
-	    ds->ops->phylink_mac_an_restart)
-		dp->pl_config.legacy_pre_march2020 = true;
-
 	if (ds->ops->phylink_get_caps)
 		ds->ops->phylink_get_caps(ds, dp->index, &dp->pl_config);
 
-- 
GitLab


From 8f42c07fb0f208150676e2e7b6b0482522b304c9 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Fri, 14 Jul 2023 10:12:12 +0100
Subject: [PATCH 0172/1806] net: dsa: remove legacy_pre_march2020 from drivers

Since DSA no longer marks anything as phylink-legacy, there is now no
need for DSA drivers to set this member to false. Remove all instances
of this.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/b53/b53_common.c       | 6 ------
 drivers/net/dsa/lan9303-core.c         | 6 ------
 drivers/net/dsa/microchip/ksz_common.c | 2 --
 drivers/net/dsa/mt7530.c               | 6 ------
 drivers/net/dsa/mv88e6xxx/chip.c       | 4 ----
 drivers/net/dsa/ocelot/felix.c         | 6 ------
 drivers/net/dsa/qca/qca8k-8xxx.c       | 2 --
 drivers/net/dsa/sja1105/sja1105_main.c | 6 ------
 8 files changed, 38 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 3464ce5e74705..4e27dc913cf71 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1393,12 +1393,6 @@ static void b53_phylink_get_caps(struct dsa_switch *ds, int port,
 	/* Get the implementation specific capabilities */
 	if (dev->ops->phylink_get_caps)
 		dev->ops->phylink_get_caps(dev, port, config);
-
-	/* This driver does not make use of the speed, duplex, pause or the
-	 * advertisement in its mac_config, so it is safe to mark this driver
-	 * as non-legacy.
-	 */
-	config->legacy_pre_march2020 = false;
 }
 
 static struct phylink_pcs *b53_phylink_mac_select_pcs(struct dsa_switch *ds,
diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c
index ff76444057d24..b0da1e4de63c3 100644
--- a/drivers/net/dsa/lan9303-core.c
+++ b/drivers/net/dsa/lan9303-core.c
@@ -1290,12 +1290,6 @@ static void lan9303_phylink_get_caps(struct dsa_switch *ds, int port,
 		__set_bit(PHY_INTERFACE_MODE_GMII,
 			  config->supported_interfaces);
 	}
-
-	/* This driver does not make use of the speed, duplex, pause or the
-	 * advertisement in its mac_config, so it is safe to mark this driver
-	 * as non-legacy.
-	 */
-	config->legacy_pre_march2020 = false;
 }
 
 static void lan9303_phylink_mac_link_up(struct dsa_switch *ds, int port,
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 813b91a816bbe..07ba2b54ab994 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -1624,8 +1624,6 @@ static void ksz_phylink_get_caps(struct dsa_switch *ds, int port,
 {
 	struct ksz_device *dev = ds->priv;
 
-	config->legacy_pre_march2020 = false;
-
 	if (dev->info->supports_mii[port])
 		__set_bit(PHY_INTERFACE_MODE_MII, config->supported_interfaces);
 
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 38b3c6dda386a..8fbda739c1b35 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2949,12 +2949,6 @@ static void mt753x_phylink_get_caps(struct dsa_switch *ds, int port,
 	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 				   MAC_10 | MAC_100 | MAC_1000FD;
 
-	/* This driver does not make use of the speed, duplex, pause or the
-	 * advertisement in its mac_config, so it is safe to mark this driver
-	 * as non-legacy.
-	 */
-	config->legacy_pre_march2020 = false;
-
 	priv->info->mac_port_get_caps(ds, port, config);
 }
 
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 6174855188d90..8dd82fd87fc69 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -769,10 +769,6 @@ static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port,
 		__set_bit(PHY_INTERFACE_MODE_GMII,
 			  config->supported_interfaces);
 	}
-
-	/* If we have a .pcs_init, we are not legacy. */
-	if (chip->info->ops->pcs_ops)
-		config->legacy_pre_march2020 = false;
 }
 
 static struct phylink_pcs *mv88e6xxx_mac_select_pcs(struct dsa_switch *ds,
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 8da46d284e356..fd7eb4a529183 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -1042,12 +1042,6 @@ static void felix_phylink_get_caps(struct dsa_switch *ds, int port,
 {
 	struct ocelot *ocelot = ds->priv;
 
-	/* This driver does not make use of the speed, duplex, pause or the
-	 * advertisement in its mac_config, so it is safe to mark this driver
-	 * as non-legacy.
-	 */
-	config->legacy_pre_march2020 = false;
-
 	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 				   MAC_10 | MAC_100 | MAC_1000FD |
 				   MAC_2500FD;
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index 09b80644c11bd..27bf58e40be6a 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -1397,8 +1397,6 @@ static void qca8k_phylink_get_caps(struct dsa_switch *ds, int port,
 
 	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100 | MAC_1000FD;
-
-	config->legacy_pre_march2020 = false;
 }
 
 static void
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 3529a565b4aaf..52dd52d6c43d0 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1396,12 +1396,6 @@ static void sja1105_phylink_get_caps(struct dsa_switch *ds, int port,
 	struct sja1105_xmii_params_entry *mii;
 	phy_interface_t phy_mode;
 
-	/* This driver does not make use of the speed, duplex, pause or the
-	 * advertisement in its mac_config, so it is safe to mark this driver
-	 * as non-legacy.
-	 */
-	config->legacy_pre_march2020 = false;
-
 	phy_mode = priv->phy_mode[port];
 	if (phy_mode == PHY_INTERFACE_MODE_SGMII ||
 	    phy_mode == PHY_INTERFACE_MODE_2500BASEX) {
-- 
GitLab


From 76226787e137962750241bb29a9572dfc10d9eb1 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Fri, 14 Jul 2023 10:12:17 +0100
Subject: [PATCH 0173/1806] net: phylink: remove legacy mac_an_restart() method

The mac_an_restart() method is now completely unused, and has been
superseded by phylink_pcs support. Remove this method.

Since phylink_pcs_mac_an_restart() now only deals with the PCS, rename
the function to remove the _mac infix.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phylink.c | 22 +++++++++-------------
 include/linux/phylink.h   | 12 ------------
 2 files changed, 9 insertions(+), 25 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 71b1012ef3be8..f07e496319b4a 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1079,17 +1079,13 @@ static void phylink_mac_config(struct phylink *pl,
 	pl->mac_ops->mac_config(pl->config, pl->cur_link_an_mode, state);
 }
 
-static void phylink_mac_pcs_an_restart(struct phylink *pl)
+static void phylink_pcs_an_restart(struct phylink *pl)
 {
-	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
-			      pl->link_config.advertising) &&
+	if (pl->pcs && linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+					 pl->link_config.advertising) &&
 	    phy_interface_mode_is_8023z(pl->link_config.interface) &&
-	    phylink_autoneg_inband(pl->cur_link_an_mode)) {
-		if (pl->pcs)
-			pl->pcs->ops->pcs_an_restart(pl->pcs);
-		else if (pl->config->legacy_pre_march2020)
-			pl->mac_ops->mac_an_restart(pl->config);
-	}
+	    phylink_autoneg_inband(pl->cur_link_an_mode))
+		pl->pcs->ops->pcs_an_restart(pl->pcs);
 }
 
 static void phylink_major_config(struct phylink *pl, bool restart,
@@ -1169,7 +1165,7 @@ static void phylink_major_config(struct phylink *pl, bool restart,
 		restart = true;
 
 	if (restart)
-		phylink_mac_pcs_an_restart(pl);
+		phylink_pcs_an_restart(pl);
 
 	if (pl->mac_ops->mac_finish) {
 		err = pl->mac_ops->mac_finish(pl->config, pl->cur_link_an_mode,
@@ -1205,7 +1201,7 @@ static int phylink_change_inband_advert(struct phylink *pl)
 	if (!pl->pcs && pl->config->legacy_pre_march2020) {
 		/* Legacy method */
 		phylink_mac_config(pl, &pl->link_config);
-		phylink_mac_pcs_an_restart(pl);
+		phylink_pcs_an_restart(pl);
 		return 0;
 	}
 
@@ -1234,7 +1230,7 @@ static int phylink_change_inband_advert(struct phylink *pl)
 		return ret;
 
 	if (ret > 0)
-		phylink_mac_pcs_an_restart(pl);
+		phylink_pcs_an_restart(pl);
 
 	return 0;
 }
@@ -2533,7 +2529,7 @@ int phylink_ethtool_nway_reset(struct phylink *pl)
 
 	if (pl->phydev)
 		ret = phy_restart_aneg(pl->phydev);
-	phylink_mac_pcs_an_restart(pl);
+	phylink_pcs_an_restart(pl);
 
 	return ret;
 }
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index b28aa3eef7d56..9e861c8316d0c 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -234,7 +234,6 @@ struct phylink_config {
  * @mac_prepare: prepare for a major reconfiguration of the interface.
  * @mac_config: configure the MAC for the selected mode and state.
  * @mac_finish: finish a major reconfiguration of the interface.
- * @mac_an_restart: restart 802.3z BaseX autonegotiation.
  * @mac_link_down: take the link down.
  * @mac_link_up: allow the link to come up.
  *
@@ -254,7 +253,6 @@ struct phylink_mac_ops {
 			   const struct phylink_link_state *state);
 	int (*mac_finish)(struct phylink_config *config, unsigned int mode,
 			  phy_interface_t iface);
-	void (*mac_an_restart)(struct phylink_config *config);
 	void (*mac_link_down)(struct phylink_config *config, unsigned int mode,
 			      phy_interface_t interface);
 	void (*mac_link_up)(struct phylink_config *config,
@@ -459,16 +457,6 @@ void mac_config(struct phylink_config *config, unsigned int mode,
 int mac_finish(struct phylink_config *config, unsigned int mode,
 		phy_interface_t iface);
 
-/**
- * mac_an_restart() - restart 802.3z BaseX autonegotiation
- * @config: a pointer to a &struct phylink_config.
- *
- * Note: This is a legacy method. This function will not be called unless
- * legacy_pre_march2020 is set in &struct phylink_config and there is no
- * PCS attached.
- */
-void mac_an_restart(struct phylink_config *config);
-
 /**
  * mac_link_down() - take the link down
  * @config: a pointer to a &struct phylink_config.
-- 
GitLab


From c62c0a17f9b7398022f9eebe547878033264f81f Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 14 Jul 2023 04:13:29 -0700
Subject: [PATCH 0174/1806] netconsole: Append kernel version to message

Create a new netconsole runtime option that prepends the kernel version in
the netconsole message. This is useful to map kernel messages to kernel
version in a simple way, i.e., without checking somewhere which kernel
version the host that sent the message is using.

If this option is selected, then the "<release>," is prepended before the
netconsole message. This is an example of a netconsole output, with
release feature enabled:

	6.4.0-01762-ga1ba2ffe946e;12,426,112883998,-;this is a test

Cc: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20230714111330.3069605-1-leitao@debian.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/netconsole.rst | 11 +++-
 drivers/net/netconsole.c                | 81 ++++++++++++++++++++++++-
 2 files changed, 88 insertions(+), 4 deletions(-)

diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst
index dd0518e002f62..7a9de0568e847 100644
--- a/Documentation/networking/netconsole.rst
+++ b/Documentation/networking/netconsole.rst
@@ -13,6 +13,8 @@ IPv6 support by Cong Wang <xiyou.wangcong@gmail.com>, Jan 1 2013
 
 Extended console support by Tejun Heo <tj@kernel.org>, May 1 2015
 
+Release prepend support by Breno Leitao <leitao@debian.org>, Jul 7 2023
+
 Please send bug reports to Matt Mackall <mpm@selenic.com>
 Satyam Sharma <satyam.sharma@gmail.com>, and Cong Wang <xiyou.wangcong@gmail.com>
 
@@ -34,10 +36,11 @@ Sender and receiver configuration:
 It takes a string configuration parameter "netconsole" in the
 following format::
 
- netconsole=[+][src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr]
+ netconsole=[+][r][src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr]
 
    where
 	+             if present, enable extended console support
+	r             if present, prepend kernel version (release) to the message
 	src-port      source for UDP packets (defaults to 6665)
 	src-ip        source IP to use (interface address)
 	dev           network interface (eth0)
@@ -125,6 +128,7 @@ The interface exposes these parameters of a netconsole target to userspace:
 	==============  =================================       ============
 	enabled		Is this target currently enabled?	(read-write)
 	extended	Extended mode enabled			(read-write)
+	release		Prepend kernel release to message	(read-write)
 	dev_name	Local network interface name		(read-write)
 	local_port	Source UDP port to use			(read-write)
 	remote_port	Remote agent's UDP port			(read-write)
@@ -165,6 +169,11 @@ following format which is the same as /dev/kmsg::
 
  <level>,<sequnum>,<timestamp>,<contflag>;<message text>
 
+If 'r' (release) feature is enabled, the kernel release version is
+prepended to the start of the message. Example::
+
+ 6.4.0,6,444,501151268,-;netconsole: network logging started
+
 Non printable characters in <message text> are escaped using "\xff"
 notation. If the message contains optional dictionary, verbatim
 newline is used as the delimiter.
diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 4f4f79532c6cf..31cbe02eda495 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -36,6 +36,7 @@
 #include <linux/inet.h>
 #include <linux/configfs.h>
 #include <linux/etherdevice.h>
+#include <linux/utsname.h>
 
 MODULE_AUTHOR("Maintainer: Matt Mackall <mpm@selenic.com>");
 MODULE_DESCRIPTION("Console driver for network interfaces");
@@ -84,6 +85,8 @@ static struct console netconsole_ext;
  *		Also, other parameters of a target may be modified at
  *		runtime only when it is disabled (enabled == 0).
  * @extended:	Denotes whether console is extended or not.
+ * @release:	Denotes whether kernel release version should be prepended
+ *		to the message. Depends on extended console.
  * @np:		The netpoll structure for this target.
  *		Contains the other userspace visible parameters:
  *		dev_name	(read-write)
@@ -101,6 +104,7 @@ struct netconsole_target {
 #endif
 	bool			enabled;
 	bool			extended;
+	bool			release;
 	struct netpoll		np;
 };
 
@@ -188,6 +192,15 @@ static struct netconsole_target *alloc_param_target(char *target_config)
 		target_config++;
 	}
 
+	if (*target_config == 'r') {
+		if (!nt->extended) {
+			pr_err("Netconsole configuration error. Release feature requires extended log message");
+			goto fail;
+		}
+		nt->release = true;
+		target_config++;
+	}
+
 	/* Parse parameters and setup netpoll */
 	err = netpoll_parse_options(&nt->np, target_config);
 	if (err)
@@ -222,6 +235,7 @@ static void free_param_target(struct netconsole_target *nt)
  *				|
  *				<target>/
  *				|	enabled
+ *				|	release
  *				|	dev_name
  *				|	local_port
  *				|	remote_port
@@ -254,6 +268,11 @@ static ssize_t extended_show(struct config_item *item, char *buf)
 	return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->extended);
 }
 
+static ssize_t release_show(struct config_item *item, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->release);
+}
+
 static ssize_t dev_name_show(struct config_item *item, char *buf)
 {
 	return snprintf(buf, PAGE_SIZE, "%s\n", to_target(item)->np.dev_name);
@@ -332,6 +351,11 @@ static ssize_t enabled_store(struct config_item *item,
 	}
 
 	if (enabled) {	/* true */
+		if (nt->release && !nt->extended) {
+			pr_err("Not enabling netconsole. Release feature requires extended log message");
+			goto out_unlock;
+		}
+
 		if (nt->extended && !console_is_registered(&netconsole_ext))
 			register_console(&netconsole_ext);
 
@@ -366,6 +390,38 @@ out_unlock:
 	return err;
 }
 
+static ssize_t release_store(struct config_item *item, const char *buf,
+			     size_t count)
+{
+	struct netconsole_target *nt = to_target(item);
+	int release;
+	int err;
+
+	mutex_lock(&dynamic_netconsole_mutex);
+	if (nt->enabled) {
+		pr_err("target (%s) is enabled, disable to update parameters\n",
+		       config_item_name(&nt->item));
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
+	err = kstrtoint(buf, 10, &release);
+	if (err < 0)
+		goto out_unlock;
+	if (release < 0 || release > 1) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
+	nt->release = release;
+
+	mutex_unlock(&dynamic_netconsole_mutex);
+	return strnlen(buf, count);
+out_unlock:
+	mutex_unlock(&dynamic_netconsole_mutex);
+	return err;
+}
+
 static ssize_t extended_store(struct config_item *item, const char *buf,
 		size_t count)
 {
@@ -576,10 +632,12 @@ CONFIGFS_ATTR(, local_ip);
 CONFIGFS_ATTR(, remote_ip);
 CONFIGFS_ATTR_RO(, local_mac);
 CONFIGFS_ATTR(, remote_mac);
+CONFIGFS_ATTR(, release);
 
 static struct configfs_attribute *netconsole_target_attrs[] = {
 	&attr_enabled,
 	&attr_extended,
+	&attr_release,
 	&attr_dev_name,
 	&attr_local_port,
 	&attr_remote_port,
@@ -772,9 +830,23 @@ static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg,
 	const char *header, *body;
 	int offset = 0;
 	int header_len, body_len;
+	const char *msg_ready = msg;
+	const char *release;
+	int release_len = 0;
+
+	if (nt->release) {
+		release = init_utsname()->release;
+		release_len = strlen(release) + 1;
+	}
 
-	if (msg_len <= MAX_PRINT_CHUNK) {
-		netpoll_send_udp(&nt->np, msg, msg_len);
+	if (msg_len + release_len <= MAX_PRINT_CHUNK) {
+		/* No fragmentation needed */
+		if (nt->release) {
+			scnprintf(buf, MAX_PRINT_CHUNK, "%s,%s", release, msg);
+			msg_len += release_len;
+			msg_ready = buf;
+		}
+		netpoll_send_udp(&nt->np, msg_ready, msg_len);
 		return;
 	}
 
@@ -792,7 +864,10 @@ static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg,
 	 * Transfer multiple chunks with the following extra header.
 	 * "ncfrag=<byte-offset>/<total-bytes>"
 	 */
-	memcpy(buf, header, header_len);
+	if (nt->release)
+		scnprintf(buf, MAX_PRINT_CHUNK, "%s,", release);
+	memcpy(buf + release_len, header, header_len);
+	header_len += release_len;
 
 	while (offset < body_len) {
 		int this_header = header_len;
-- 
GitLab


From 9ffc4de5c695df237644502a87d10165cd455501 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 14 Jul 2023 11:49:22 -0600
Subject: [PATCH 0175/1806] ptp: Explicitly include correct DT includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Link: https://lore.kernel.org/r/20230714174922.4063153-1-robh@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/ptp/ptp_qoriq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index 350154e4c2b54..a52859d024f0d 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -12,7 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/timex.h>
 #include <linux/slab.h>
 #include <linux/clk.h>
-- 
GitLab


From d3750076d4641b697da990b6aee5b096a10c4d12 Mon Sep 17 00:00:00 2001
From: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Date: Fri, 14 Jul 2023 13:14:28 -0700
Subject: [PATCH 0176/1806] igc: Add TransmissionOverrun counter

Add TransmissionOverrun as per defined by IEEE 802.1Q Bridges.
TransmissionOverrun counter shall be incremented if the implementation
detects that a frame from a given queue is still being transmitted by
the MAC when that gate-close event for that queue occurs.

This counter is utilised by the Certification conformance test to
inform the user application whether any packets are currently being
transmitted on a particular queue during a gate-close event.

Intel Discrete I225/I226 have a mechanism to not transmit a packets if
the gate open time is insufficient for the packet transmission by setting
the Strict_End bit. Thus, it is expected for this counter to be always
zero at this moment.

Inspired from enetc_taprio_stats() and enetc_taprio_queue_stats(), now
driver also report the tx_overruns counter per traffic class.

User can get this counter by using below command:
1) tc -s qdisc show dev <interface> root
2) tc -s class show dev <interface>

Test Result (Before):
class mq :1 root
 Sent 1289 bytes 20 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
class mq :2 root
 Sent 124 bytes 2 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
class mq :3 root
 Sent 46028 bytes 86 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
class mq :4 root
 Sent 2596 bytes 14 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0

Test Result (After):
class taprio 100:1 root
 Sent 8491 bytes 38 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 Transmit overruns: 0
class taprio 100:2 root
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 Transmit overruns: 0
class taprio 100:3 root
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 Transmit overruns: 0
class taprio 100:4 root
 Sent 994 bytes 11 pkt (dropped 0, overlimits 0 requeues 1)
 backlog 0b 0p requeues 1
 Transmit overruns: 0

Signed-off-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20230714201428.1718097-1-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 35 +++++++++++++++++++++--
 1 file changed, 32 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 9f93f0f4f7520..ddb4386c00ccf 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6115,6 +6115,26 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter)
 	return 0;
 }
 
+static void igc_taprio_stats(struct net_device *dev,
+			     struct tc_taprio_qopt_stats *stats)
+{
+	/* When Strict_End is enabled, the tx_overruns counter
+	 * will always be zero.
+	 */
+	stats->tx_overruns = 0;
+}
+
+static void igc_taprio_queue_stats(struct net_device *dev,
+				   struct tc_taprio_qopt_queue_stats *queue_stats)
+{
+	struct tc_taprio_qopt_stats *stats = &queue_stats->stats;
+
+	/* When Strict_End is enabled, the tx_overruns counter
+	 * will always be zero.
+	 */
+	stats->tx_overruns = 0;
+}
+
 static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 				 struct tc_taprio_qopt_offload *qopt)
 {
@@ -6125,11 +6145,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	size_t n;
 	int i;
 
-	if (qopt->cmd == TAPRIO_CMD_DESTROY)
+	switch (qopt->cmd) {
+	case TAPRIO_CMD_REPLACE:
+		break;
+	case TAPRIO_CMD_DESTROY:
 		return igc_tsn_clear_schedule(adapter);
-
-	if (qopt->cmd != TAPRIO_CMD_REPLACE)
+	case TAPRIO_CMD_STATS:
+		igc_taprio_stats(adapter->netdev, &qopt->stats);
+		return 0;
+	case TAPRIO_CMD_QUEUE_STATS:
+		igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats);
+		return 0;
+	default:
 		return -EOPNOTSUPP;
+	}
 
 	if (qopt->base_time < 0)
 		return -ERANGE;
-- 
GitLab


From 4a59cdfd66998259061b86437b9439d186f89d5a Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 16 Jul 2023 10:24:40 +0300
Subject: [PATCH 0177/1806] rtnetlink: Move nesting cancellation rollback to
 proper function

Make rtnl_fill_vf() cancel the vfinfo attribute on error instead of the
inner rtnl_fill_vfinfo(), as it is the function that starts it.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://lore.kernel.org/r/20230716072440.2372567-1-gal@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/rtnetlink.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 3ad4e030846d8..70838d7e5b325 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1273,7 +1273,6 @@ static noinline_for_stack int rtnl_fill_stats(struct sk_buff *skb,
 static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 					       struct net_device *dev,
 					       int vfs_num,
-					       struct nlattr *vfinfo,
 					       u32 ext_filter_mask)
 {
 	struct ifla_vf_rss_query_en vf_rss_query_en;
@@ -1343,7 +1342,7 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	vf_trust.setting = ivi.trusted;
 	vf = nla_nest_start_noflag(skb, IFLA_VF_INFO);
 	if (!vf)
-		goto nla_put_vfinfo_failure;
+		return -EMSGSIZE;
 	if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) ||
 	    nla_put(skb, IFLA_VF_BROADCAST, sizeof(vf_broadcast), &vf_broadcast) ||
 	    nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) ||
@@ -1414,8 +1413,6 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 
 nla_put_vf_failure:
 	nla_nest_cancel(skb, vf);
-nla_put_vfinfo_failure:
-	nla_nest_cancel(skb, vfinfo);
 	return -EMSGSIZE;
 }
 
@@ -1441,8 +1438,10 @@ static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb,
 		return -EMSGSIZE;
 
 	for (i = 0; i < num_vfs; i++) {
-		if (rtnl_fill_vfinfo(skb, dev, i, vfinfo, ext_filter_mask))
+		if (rtnl_fill_vfinfo(skb, dev, i, ext_filter_mask)) {
+			nla_nest_cancel(skb, vfinfo);
 			return -EMSGSIZE;
+		}
 	}
 
 	nla_nest_end(skb, vfinfo);
-- 
GitLab


From 0a1f7bfe35a3e1302529fa900bf0574a5dfc8ea6 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Tue, 18 Jul 2023 01:38:09 -0700
Subject: [PATCH 0178/1806] bpf: Introduce internal definitions for UAPI-opaque
 bpf_{rb,list}_node

Structs bpf_rb_node and bpf_list_node are opaquely defined in
uapi/linux/bpf.h, as BPF program writers are not expected to touch their
fields - nor does the verifier allow them to do so.

Currently these structs are simple wrappers around structs rb_node and
list_head and linked_list / rbtree implementation just casts and passes
to library functions for those data structures. Later patches in this
series, though, will add an "owner" field to bpf_{rb,list}_node, such
that they're not just wrapping an underlying node type. Moreover, the
bpf linked_list and rbtree implementations will deal with these owner
pointers directly in a few different places.

To avoid having to do

  void *owner = (void*)bpf_list_node + sizeof(struct list_head)

with opaque UAPI node types, add bpf_{list,rb}_node_kern struct
definitions to internal headers and modify linked_list and rbtree to use
the internal types where appropriate.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/r/20230718083813.3416104-3-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h  | 10 ++++++++++
 kernel/bpf/helpers.c | 23 +++++++++++++----------
 2 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 360433f14496a..511ed49c3fe9c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -228,6 +228,16 @@ struct btf_record {
 	struct btf_field fields[];
 };
 
+/* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */
+struct bpf_rb_node_kern {
+	struct rb_node rb_node;
+} __attribute__((aligned(8)));
+
+/* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */
+struct bpf_list_node_kern {
+	struct list_head list_head;
+} __attribute__((aligned(8)));
+
 struct bpf_map {
 	/* The first two cachelines with read-mostly members of which some
 	 * are also accessed in fast-path (e.g. ops, max_entries).
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9e80efa59a5d6..d564ff97de0b5 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1942,10 +1942,11 @@ __bpf_kfunc void *bpf_refcount_acquire_impl(void *p__refcounted_kptr, void *meta
 	return (void *)p__refcounted_kptr;
 }
 
-static int __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *head,
+static int __bpf_list_add(struct bpf_list_node_kern *node,
+			  struct bpf_list_head *head,
 			  bool tail, struct btf_record *rec, u64 off)
 {
-	struct list_head *n = (void *)node, *h = (void *)head;
+	struct list_head *n = &node->list_head, *h = (void *)head;
 
 	/* If list_head was 0-initialized by map, bpf_obj_init_field wasn't
 	 * called on its fields, so init here
@@ -1967,20 +1968,20 @@ __bpf_kfunc int bpf_list_push_front_impl(struct bpf_list_head *head,
 					 struct bpf_list_node *node,
 					 void *meta__ign, u64 off)
 {
+	struct bpf_list_node_kern *n = (void *)node;
 	struct btf_struct_meta *meta = meta__ign;
 
-	return __bpf_list_add(node, head, false,
-			      meta ? meta->record : NULL, off);
+	return __bpf_list_add(n, head, false, meta ? meta->record : NULL, off);
 }
 
 __bpf_kfunc int bpf_list_push_back_impl(struct bpf_list_head *head,
 					struct bpf_list_node *node,
 					void *meta__ign, u64 off)
 {
+	struct bpf_list_node_kern *n = (void *)node;
 	struct btf_struct_meta *meta = meta__ign;
 
-	return __bpf_list_add(node, head, true,
-			      meta ? meta->record : NULL, off);
+	return __bpf_list_add(n, head, true, meta ? meta->record : NULL, off);
 }
 
 static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tail)
@@ -2013,7 +2014,7 @@ __bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
 						  struct bpf_rb_node *node)
 {
 	struct rb_root_cached *r = (struct rb_root_cached *)root;
-	struct rb_node *n = (struct rb_node *)node;
+	struct rb_node *n = &((struct bpf_rb_node_kern *)node)->rb_node;
 
 	if (RB_EMPTY_NODE(n))
 		return NULL;
@@ -2026,11 +2027,12 @@ __bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
 /* Need to copy rbtree_add_cached's logic here because our 'less' is a BPF
  * program
  */
-static int __bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node,
+static int __bpf_rbtree_add(struct bpf_rb_root *root,
+			    struct bpf_rb_node_kern *node,
 			    void *less, struct btf_record *rec, u64 off)
 {
 	struct rb_node **link = &((struct rb_root_cached *)root)->rb_root.rb_node;
-	struct rb_node *parent = NULL, *n = (struct rb_node *)node;
+	struct rb_node *parent = NULL, *n = &node->rb_node;
 	bpf_callback_t cb = (bpf_callback_t)less;
 	bool leftmost = true;
 
@@ -2060,8 +2062,9 @@ __bpf_kfunc int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node
 				    void *meta__ign, u64 off)
 {
 	struct btf_struct_meta *meta = meta__ign;
+	struct bpf_rb_node_kern *n = (void *)node;
 
-	return __bpf_rbtree_add(root, node, (void *)less, meta ? meta->record : NULL, off);
+	return __bpf_rbtree_add(root, n, (void *)less, meta ? meta->record : NULL, off);
 }
 
 __bpf_kfunc struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root)
-- 
GitLab


From c3c510ce431cd99fa10dcd50d995c8e89330ee5b Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Tue, 18 Jul 2023 01:38:10 -0700
Subject: [PATCH 0179/1806] bpf: Add 'owner' field to bpf_{list,rb}_node

As described by Kumar in [0], in shared ownership scenarios it is
necessary to do runtime tracking of {rb,list} node ownership - and
synchronize updates using this ownership information - in order to
prevent races. This patch adds an 'owner' field to struct bpf_list_node
and bpf_rb_node to implement such runtime tracking.

The owner field is a void * that describes the ownership state of a
node. It can have the following values:

  NULL           - the node is not owned by any data structure
  BPF_PTR_POISON - the node is in the process of being added to a data
                   structure
  ptr_to_root    - the pointee is a data structure 'root'
                   (bpf_rb_root / bpf_list_head) which owns this node

The field is initially NULL (set by bpf_obj_init_field default behavior)
and transitions states in the following sequence:

  Insertion: NULL -> BPF_PTR_POISON -> ptr_to_root
  Removal:   ptr_to_root -> NULL

Before a node has been successfully inserted, it is not protected by any
root's lock, and therefore two programs can attempt to add the same node
to different roots simultaneously. For this reason the intermediate
BPF_PTR_POISON state is necessary. For removal, the node is protected
by some root's lock so this intermediate hop isn't necessary.

Note that bpf_list_pop_{front,back} helpers don't need to check owner
before removing as the node-to-be-removed is not passed in as input and
is instead taken directly from the list. Do the check anyways and
WARN_ON_ONCE in this unexpected scenario.

Selftest changes in this patch are entirely mechanical: some BTF
tests have hardcoded struct sizes for structs that contain
bpf_{list,rb}_node fields, those were adjusted to account for the new
sizes. Selftest additions to validate the owner field are added in a
further patch in the series.

  [0]: https://lore.kernel.org/bpf/d7hyspcow5wtjcmw4fugdgyp3fwhljwuscp3xyut5qnwivyeru@ysdq543otzv2

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Suggested-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230718083813.3416104-4-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h                           |  2 +
 include/uapi/linux/bpf.h                      |  2 +
 kernel/bpf/helpers.c                          | 29 ++++++-
 .../selftests/bpf/prog_tests/linked_list.c    | 78 +++++++++----------
 4 files changed, 68 insertions(+), 43 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 511ed49c3fe9c..ceaa8c23287fc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -231,11 +231,13 @@ struct btf_record {
 /* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */
 struct bpf_rb_node_kern {
 	struct rb_node rb_node;
+	void *owner;
 } __attribute__((aligned(8)));
 
 /* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */
 struct bpf_list_node_kern {
 	struct list_head list_head;
+	void *owner;
 } __attribute__((aligned(8)));
 
 struct bpf_map {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 600d0caebbd8a..9ed59896ebc5a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7052,6 +7052,7 @@ struct bpf_list_head {
 struct bpf_list_node {
 	__u64 :64;
 	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_rb_root {
@@ -7063,6 +7064,7 @@ struct bpf_rb_node {
 	__u64 :64;
 	__u64 :64;
 	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_refcount {
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index d564ff97de0b5..bcff584985e7d 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1953,13 +1953,18 @@ static int __bpf_list_add(struct bpf_list_node_kern *node,
 	 */
 	if (unlikely(!h->next))
 		INIT_LIST_HEAD(h);
-	if (!list_empty(n)) {
+
+	/* node->owner != NULL implies !list_empty(n), no need to separately
+	 * check the latter
+	 */
+	if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) {
 		/* Only called from BPF prog, no need to migrate_disable */
 		__bpf_obj_drop_impl((void *)n - off, rec);
 		return -EINVAL;
 	}
 
 	tail ? list_add_tail(n, h) : list_add(n, h);
+	WRITE_ONCE(node->owner, head);
 
 	return 0;
 }
@@ -1987,6 +1992,7 @@ __bpf_kfunc int bpf_list_push_back_impl(struct bpf_list_head *head,
 static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tail)
 {
 	struct list_head *n, *h = (void *)head;
+	struct bpf_list_node_kern *node;
 
 	/* If list_head was 0-initialized by map, bpf_obj_init_field wasn't
 	 * called on its fields, so init here
@@ -1995,8 +2001,14 @@ static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tai
 		INIT_LIST_HEAD(h);
 	if (list_empty(h))
 		return NULL;
+
 	n = tail ? h->prev : h->next;
+	node = container_of(n, struct bpf_list_node_kern, list_head);
+	if (WARN_ON_ONCE(READ_ONCE(node->owner) != head))
+		return NULL;
+
 	list_del_init(n);
+	WRITE_ONCE(node->owner, NULL);
 	return (struct bpf_list_node *)n;
 }
 
@@ -2013,14 +2025,19 @@ __bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head)
 __bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
 						  struct bpf_rb_node *node)
 {
+	struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node;
 	struct rb_root_cached *r = (struct rb_root_cached *)root;
-	struct rb_node *n = &((struct bpf_rb_node_kern *)node)->rb_node;
+	struct rb_node *n = &node_internal->rb_node;
 
-	if (RB_EMPTY_NODE(n))
+	/* node_internal->owner != root implies either RB_EMPTY_NODE(n) or
+	 * n is owned by some other tree. No need to check RB_EMPTY_NODE(n)
+	 */
+	if (READ_ONCE(node_internal->owner) != root)
 		return NULL;
 
 	rb_erase_cached(n, r);
 	RB_CLEAR_NODE(n);
+	WRITE_ONCE(node_internal->owner, NULL);
 	return (struct bpf_rb_node *)n;
 }
 
@@ -2036,7 +2053,10 @@ static int __bpf_rbtree_add(struct bpf_rb_root *root,
 	bpf_callback_t cb = (bpf_callback_t)less;
 	bool leftmost = true;
 
-	if (!RB_EMPTY_NODE(n)) {
+	/* node->owner != NULL implies !RB_EMPTY_NODE(n), no need to separately
+	 * check the latter
+	 */
+	if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) {
 		/* Only called from BPF prog, no need to migrate_disable */
 		__bpf_obj_drop_impl((void *)n - off, rec);
 		return -EINVAL;
@@ -2054,6 +2074,7 @@ static int __bpf_rbtree_add(struct bpf_rb_root *root,
 
 	rb_link_node(n, parent, link);
 	rb_insert_color_cached(n, (struct rb_root_cached *)root, leftmost);
+	WRITE_ONCE(node->owner, root);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c
index f63309fd0e28e..18cf7b17463d9 100644
--- a/tools/testing/selftests/bpf/prog_tests/linked_list.c
+++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c
@@ -23,7 +23,7 @@ static struct {
 	  "bpf_spin_lock at off=" #off " must be held for bpf_list_head" }, \
 	{ #test "_missing_lock_pop_back", \
 	  "bpf_spin_lock at off=" #off " must be held for bpf_list_head" },
-	TEST(kptr, 32)
+	TEST(kptr, 40)
 	TEST(global, 16)
 	TEST(map, 0)
 	TEST(inner_map, 0)
@@ -31,7 +31,7 @@ static struct {
 #define TEST(test, op) \
 	{ #test "_kptr_incorrect_lock_" #op, \
 	  "held lock and object are not in the same allocation\n" \
-	  "bpf_spin_lock at off=32 must be held for bpf_list_head" }, \
+	  "bpf_spin_lock at off=40 must be held for bpf_list_head" }, \
 	{ #test "_global_incorrect_lock_" #op, \
 	  "held lock and object are not in the same allocation\n" \
 	  "bpf_spin_lock at off=16 must be held for bpf_list_head" }, \
@@ -84,23 +84,23 @@ static struct {
 	{ "double_push_back", "arg#1 expected pointer to allocated object" },
 	{ "no_node_value_type", "bpf_list_node not found at offset=0" },
 	{ "incorrect_value_type",
-	  "operation on bpf_list_head expects arg#1 bpf_list_node at offset=40 in struct foo, "
+	  "operation on bpf_list_head expects arg#1 bpf_list_node at offset=48 in struct foo, "
 	  "but arg is at offset=0 in struct bar" },
 	{ "incorrect_node_var_off", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" },
-	{ "incorrect_node_off1", "bpf_list_node not found at offset=41" },
-	{ "incorrect_node_off2", "arg#1 offset=0, but expected bpf_list_node at offset=40 in struct foo" },
+	{ "incorrect_node_off1", "bpf_list_node not found at offset=49" },
+	{ "incorrect_node_off2", "arg#1 offset=0, but expected bpf_list_node at offset=48 in struct foo" },
 	{ "no_head_type", "bpf_list_head not found at offset=0" },
 	{ "incorrect_head_var_off1", "R1 doesn't have constant offset" },
 	{ "incorrect_head_var_off2", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" },
-	{ "incorrect_head_off1", "bpf_list_head not found at offset=17" },
+	{ "incorrect_head_off1", "bpf_list_head not found at offset=25" },
 	{ "incorrect_head_off2", "bpf_list_head not found at offset=1" },
 	{ "pop_front_off",
-	  "15: (bf) r1 = r6                      ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) "
-	  "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) refs=2,4\n"
+	  "15: (bf) r1 = r6                      ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) "
+	  "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n"
 	  "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" },
 	{ "pop_back_off",
-	  "15: (bf) r1 = r6                      ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) "
-	  "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) refs=2,4\n"
+	  "15: (bf) r1 = r6                      ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) "
+	  "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n"
 	  "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" },
 };
 
@@ -257,7 +257,7 @@ static struct btf *init_btf(void)
 	hid = btf__add_struct(btf, "bpf_list_head", 16);
 	if (!ASSERT_EQ(hid, LIST_HEAD, "btf__add_struct bpf_list_head"))
 		goto end;
-	nid = btf__add_struct(btf, "bpf_list_node", 16);
+	nid = btf__add_struct(btf, "bpf_list_node", 24);
 	if (!ASSERT_EQ(nid, LIST_NODE, "btf__add_struct bpf_list_node"))
 		goto end;
 	return btf;
@@ -276,7 +276,7 @@ static void list_and_rb_node_same_struct(bool refcount_field)
 	if (!ASSERT_OK_PTR(btf, "init_btf"))
 		return;
 
-	bpf_rb_node_btf_id = btf__add_struct(btf, "bpf_rb_node", 24);
+	bpf_rb_node_btf_id = btf__add_struct(btf, "bpf_rb_node", 32);
 	if (!ASSERT_GT(bpf_rb_node_btf_id, 0, "btf__add_struct bpf_rb_node"))
 		return;
 
@@ -286,17 +286,17 @@ static void list_and_rb_node_same_struct(bool refcount_field)
 			return;
 	}
 
-	id = btf__add_struct(btf, "bar", refcount_field ? 44 : 40);
+	id = btf__add_struct(btf, "bar", refcount_field ? 60 : 56);
 	if (!ASSERT_GT(id, 0, "btf__add_struct bar"))
 		return;
 	err = btf__add_field(btf, "a", LIST_NODE, 0, 0);
 	if (!ASSERT_OK(err, "btf__add_field bar::a"))
 		return;
-	err = btf__add_field(btf, "c", bpf_rb_node_btf_id, 128, 0);
+	err = btf__add_field(btf, "c", bpf_rb_node_btf_id, 192, 0);
 	if (!ASSERT_OK(err, "btf__add_field bar::c"))
 		return;
 	if (refcount_field) {
-		err = btf__add_field(btf, "ref", bpf_refcount_btf_id, 320, 0);
+		err = btf__add_field(btf, "ref", bpf_refcount_btf_id, 448, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::ref"))
 			return;
 	}
@@ -527,7 +527,7 @@ static void test_btf(void)
 		btf = init_btf();
 		if (!ASSERT_OK_PTR(btf, "init_btf"))
 			break;
-		id = btf__add_struct(btf, "foo", 36);
+		id = btf__add_struct(btf, "foo", 44);
 		if (!ASSERT_EQ(id, 5, "btf__add_struct foo"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -536,7 +536,7 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:foo:b", 5, 0);
@@ -553,7 +553,7 @@ static void test_btf(void)
 		btf = init_btf();
 		if (!ASSERT_OK_PTR(btf, "init_btf"))
 			break;
-		id = btf__add_struct(btf, "foo", 36);
+		id = btf__add_struct(btf, "foo", 44);
 		if (!ASSERT_EQ(id, 5, "btf__add_struct foo"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -562,13 +562,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0);
 		if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b"))
 			break;
-		id = btf__add_struct(btf, "bar", 36);
+		id = btf__add_struct(btf, "bar", 44);
 		if (!ASSERT_EQ(id, 7, "btf__add_struct bar"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -577,7 +577,7 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:foo:b", 7, 0);
@@ -594,19 +594,19 @@ static void test_btf(void)
 		btf = init_btf();
 		if (!ASSERT_OK_PTR(btf, "init_btf"))
 			break;
-		id = btf__add_struct(btf, "foo", 20);
+		id = btf__add_struct(btf, "foo", 28);
 		if (!ASSERT_EQ(id, 5, "btf__add_struct foo"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::a"))
 			break;
-		err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0);
+		err = btf__add_field(btf, "b", SPIN_LOCK, 192, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::b"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:bar:a", 5, 0);
 		if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:a"))
 			break;
-		id = btf__add_struct(btf, "bar", 16);
+		id = btf__add_struct(btf, "bar", 24);
 		if (!ASSERT_EQ(id, 7, "btf__add_struct bar"))
 			break;
 		err = btf__add_field(btf, "a", LIST_NODE, 0, 0);
@@ -623,19 +623,19 @@ static void test_btf(void)
 		btf = init_btf();
 		if (!ASSERT_OK_PTR(btf, "init_btf"))
 			break;
-		id = btf__add_struct(btf, "foo", 20);
+		id = btf__add_struct(btf, "foo", 28);
 		if (!ASSERT_EQ(id, 5, "btf__add_struct foo"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::a"))
 			break;
-		err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0);
+		err = btf__add_field(btf, "b", SPIN_LOCK, 192, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::b"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0);
 		if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b"))
 			break;
-		id = btf__add_struct(btf, "bar", 36);
+		id = btf__add_struct(btf, "bar", 44);
 		if (!ASSERT_EQ(id, 7, "btf__add_struct bar"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -644,13 +644,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:baz:a", 7, 0);
 		if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:baz:a"))
 			break;
-		id = btf__add_struct(btf, "baz", 16);
+		id = btf__add_struct(btf, "baz", 24);
 		if (!ASSERT_EQ(id, 9, "btf__add_struct baz"))
 			break;
 		err = btf__add_field(btf, "a", LIST_NODE, 0, 0);
@@ -667,7 +667,7 @@ static void test_btf(void)
 		btf = init_btf();
 		if (!ASSERT_OK_PTR(btf, "init_btf"))
 			break;
-		id = btf__add_struct(btf, "foo", 36);
+		id = btf__add_struct(btf, "foo", 44);
 		if (!ASSERT_EQ(id, 5, "btf__add_struct foo"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -676,13 +676,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0);
 		if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b"))
 			break;
-		id = btf__add_struct(btf, "bar", 36);
+		id = btf__add_struct(btf, "bar", 44);
 		if (!ASSERT_EQ(id, 7, "btf__add_struct bar"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -691,13 +691,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar:b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar:c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:baz:a", 7, 0);
 		if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:baz:a"))
 			break;
-		id = btf__add_struct(btf, "baz", 16);
+		id = btf__add_struct(btf, "baz", 24);
 		if (!ASSERT_EQ(id, 9, "btf__add_struct baz"))
 			break;
 		err = btf__add_field(btf, "a", LIST_NODE, 0, 0);
@@ -726,7 +726,7 @@ static void test_btf(void)
 		id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0);
 		if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b"))
 			break;
-		id = btf__add_struct(btf, "bar", 36);
+		id = btf__add_struct(btf, "bar", 44);
 		if (!ASSERT_EQ(id, 7, "btf__add_struct bar"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -735,13 +735,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:baz:b", 7, 0);
 		if (!ASSERT_EQ(id, 8, "btf__add_decl_tag"))
 			break;
-		id = btf__add_struct(btf, "baz", 36);
+		id = btf__add_struct(btf, "baz", 44);
 		if (!ASSERT_EQ(id, 9, "btf__add_struct baz"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -750,13 +750,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:bam:a", 9, 0);
 		if (!ASSERT_EQ(id, 10, "btf__add_decl_tag contains:bam:a"))
 			break;
-		id = btf__add_struct(btf, "bam", 16);
+		id = btf__add_struct(btf, "bam", 24);
 		if (!ASSERT_EQ(id, 11, "btf__add_struct bam"))
 			break;
 		err = btf__add_field(btf, "a", LIST_NODE, 0, 0);
-- 
GitLab


From fdf48dc2d054b73453f6e11ae39e96a559fc7144 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Tue, 18 Jul 2023 01:38:11 -0700
Subject: [PATCH 0180/1806] selftests/bpf: Add rbtree test exercising race
 which 'owner' field prevents

This patch adds a runnable version of one of the races described by
Kumar in [0]. Specifically, this interleaving:

(rbtree1 and list head protected by lock1, rbtree2 protected by lock2)

Prog A                          Prog B
======================================
n = bpf_obj_new(...)
m = bpf_refcount_acquire(n)
kptr_xchg(map, m)

                                m = kptr_xchg(map, NULL)
                                lock(lock2)
				bpf_rbtree_add(rbtree2, m->r, less)
				unlock(lock2)

lock(lock1)
bpf_list_push_back(head, n->l)
/* make n non-owning ref */
bpf_rbtree_remove(rbtree1, n->r)
unlock(lock1)

The above interleaving, the node's struct bpf_rb_node *r can be used to
add it to either rbtree1 or rbtree2, which are protected by different
locks. If the node has been added to rbtree2, we should not be allowed
to remove it while holding rbtree1's lock.

Before changes in the previous patch in this series, the rbtree_remove
in the second part of Prog A would succeed as the verifier has no way of
knowing which tree owns a particular node at verification time. The
addition of 'owner' field results in bpf_rbtree_remove correctly
failing.

The test added in this patch splits "Prog A" above into two separate BPF
programs - A1 and A2 - and uses a second mapval + kptr_xchg to pass n
from A1 to A2 similarly to the pass from A1 to B. If the test is run
without the fix applied, the remove will succeed.

Kumar's example had the two programs running on separate CPUs. This
patch doesn't do this as it's not necessary to exercise the broken
behavior / validate fixed behavior.

  [0]: https://lore.kernel.org/bpf/d7hyspcow5wtjcmw4fugdgyp3fwhljwuscp3xyut5qnwivyeru@ysdq543otzv2

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Suggested-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230718083813.3416104-5-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/refcounted_kptr.c          | 28 ++++++
 .../selftests/bpf/progs/refcounted_kptr.c     | 94 ++++++++++++++++++-
 2 files changed, 121 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
index 595cbf92bff5f..1cb5c657dc38e 100644
--- a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
@@ -14,3 +14,31 @@ void test_refcounted_kptr(void)
 void test_refcounted_kptr_fail(void)
 {
 }
+
+void test_refcounted_kptr_wrong_owner(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct refcounted_kptr *skel;
+	int ret;
+
+	skel = refcounted_kptr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "refcounted_kptr__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_a1), &opts);
+	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_a1");
+	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a1 retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_b), &opts);
+	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_b");
+	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_b retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_a2), &opts);
+	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_a2");
+	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a2 retval");
+	refcounted_kptr__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c
index a3da610b1e6b0..c55652fdc63ab 100644
--- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c
@@ -24,7 +24,7 @@ struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__type(key, int);
 	__type(value, struct map_value);
-	__uint(max_entries, 1);
+	__uint(max_entries, 2);
 } stashed_nodes SEC(".maps");
 
 struct node_acquire {
@@ -42,6 +42,9 @@ private(A) struct bpf_list_head head __contains(node_data, l);
 private(B) struct bpf_spin_lock alock;
 private(B) struct bpf_rb_root aroot __contains(node_acquire, node);
 
+private(C) struct bpf_spin_lock block;
+private(C) struct bpf_rb_root broot __contains(node_data, r);
+
 static bool less(struct bpf_rb_node *node_a, const struct bpf_rb_node *node_b)
 {
 	struct node_data *a;
@@ -405,4 +408,93 @@ long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)
 	return 0;
 }
 
+static long __stash_map_empty_xchg(struct node_data *n, int idx)
+{
+	struct map_value *mapval = bpf_map_lookup_elem(&stashed_nodes, &idx);
+
+	if (!mapval) {
+		bpf_obj_drop(n);
+		return 1;
+	}
+	n = bpf_kptr_xchg(&mapval->node, n);
+	if (n) {
+		bpf_obj_drop(n);
+		return 2;
+	}
+	return 0;
+}
+
+SEC("tc")
+long rbtree_wrong_owner_remove_fail_a1(void *ctx)
+{
+	struct node_data *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+	m = bpf_refcount_acquire(n);
+
+	if (__stash_map_empty_xchg(n, 0)) {
+		bpf_obj_drop(m);
+		return 2;
+	}
+
+	if (__stash_map_empty_xchg(m, 1))
+		return 3;
+
+	return 0;
+}
+
+SEC("tc")
+long rbtree_wrong_owner_remove_fail_b(void *ctx)
+{
+	struct map_value *mapval;
+	struct node_data *n;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&stashed_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	n = bpf_kptr_xchg(&mapval->node, NULL);
+	if (!n)
+		return 2;
+
+	bpf_spin_lock(&block);
+
+	bpf_rbtree_add(&broot, &n->r, less);
+
+	bpf_spin_unlock(&block);
+	return 0;
+}
+
+SEC("tc")
+long rbtree_wrong_owner_remove_fail_a2(void *ctx)
+{
+	struct map_value *mapval;
+	struct bpf_rb_node *res;
+	struct node_data *m;
+	int idx = 1;
+
+	mapval = bpf_map_lookup_elem(&stashed_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	m = bpf_kptr_xchg(&mapval->node, NULL);
+	if (!m)
+		return 2;
+	bpf_spin_lock(&lock);
+
+	/* make m non-owning ref */
+	bpf_list_push_back(&head, &m->l);
+	res = bpf_rbtree_remove(&root, &m->r);
+
+	bpf_spin_unlock(&lock);
+	if (res) {
+		bpf_obj_drop(container_of(res, struct node_data, r));
+		return 3;
+	}
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
GitLab


From f3514a5d67403f803eadd39cf61986638101e755 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Tue, 18 Jul 2023 01:38:12 -0700
Subject: [PATCH 0181/1806] selftests/bpf: Disable newly-added 'owner' field
 test until refcount re-enabled

The test added in previous patch will fail with bpf_refcount_acquire
disabled. Until all races are fixed and bpf_refcount_acquire is
re-enabled on bpf-next, disable the test so CI doesn't complain.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/r/20230718083813.3416104-6-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/refcounted_kptr.c          | 24 -------------------
 1 file changed, 24 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
index 1cb5c657dc38e..7423983472c7c 100644
--- a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
@@ -17,28 +17,4 @@ void test_refcounted_kptr_fail(void)
 
 void test_refcounted_kptr_wrong_owner(void)
 {
-	LIBBPF_OPTS(bpf_test_run_opts, opts,
-		    .data_in = &pkt_v4,
-		    .data_size_in = sizeof(pkt_v4),
-		    .repeat = 1,
-	);
-	struct refcounted_kptr *skel;
-	int ret;
-
-	skel = refcounted_kptr__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "refcounted_kptr__open_and_load"))
-		return;
-
-	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_a1), &opts);
-	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_a1");
-	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a1 retval");
-
-	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_b), &opts);
-	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_b");
-	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_b retval");
-
-	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_a2), &opts);
-	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_a2");
-	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a2 retval");
-	refcounted_kptr__destroy(skel);
 }
-- 
GitLab


From 89dc4037dda1219a3f5e3f367c2fe5e69c44a0d0 Mon Sep 17 00:00:00 2001
From: Anh Tuan Phan <tuananhlfc@gmail.com>
Date: Sun, 16 Jul 2023 23:13:51 +0700
Subject: [PATCH 0182/1806] samples/bpf: README: Update build dependencies
 required

Update samples/bpf/README.rst to add pahole to the build dependencies
list. Add the reference to "Documentation/process/changes.rst" for
minimum version required so that the version required will not be
outdated in the future.

Signed-off-by: Anh Tuan Phan <tuananhlfc@gmail.com>
Link: https://lore.kernel.org/r/aecaf7a2-9100-cd5b-5cf4-91e5dbb2c90d@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/README.rst | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst
index 57f93edd1957d..f16fc48e55a5d 100644
--- a/samples/bpf/README.rst
+++ b/samples/bpf/README.rst
@@ -8,11 +8,14 @@ Build dependencies
 ==================
 
 Compiling requires having installed:
- * clang >= version 3.4.0
- * llvm >= version 3.7.1
+ * clang
+ * llvm
+ * pahole
 
-Note that LLVM's tool 'llc' must support target 'bpf', list version
-and supported targets with command: ``llc --version``
+Consult :ref:`Documentation/process/changes.rst <changes>` for the minimum
+version numbers required and how to update them. Note that LLVM's tool
+'llc' must support target 'bpf', list version and supported targets with
+command: ``llc --version``
 
 Clean and configuration
 -----------------------
@@ -24,7 +27,8 @@ after some changes (on demand)::
  make -C samples/bpf clean
  make clean
 
-Configure kernel, defconfig for instance::
+Configure kernel, defconfig for instance
+(see "tools/testing/selftests/bpf/config" for a reference config)::
 
  make defconfig
 
-- 
GitLab


From 8daf847714ec55fe590d1135e26c531658b2ac1c Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 17 Jul 2023 16:32:52 +0800
Subject: [PATCH 0183/1806] bpf: Drop useless btf_vmlinux in bpf_tcp_ca

The code using btf_vmlinux in bpf_tcp_ca is removed by the
commit 9f0265e921de ("bpf: Require only one of cong_avoid() and cong_control() from a TCP CC")
so drop this useless btf_vmlinux declaration.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Link: https://lore.kernel.org/r/4d38da4eadaba476bd92ffcd7a5a03a5e28745c0.1689582557.git.geliang.tang@suse.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/ipv4/bpf_tcp_ca.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 4406d796cc2f1..39dcccf0f174b 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -51,8 +51,6 @@ static bool is_unsupported(u32 member_offset)
 	return false;
 }
 
-extern struct btf *btf_vmlinux;
-
 static bool bpf_tcp_ca_is_valid_access(int off, int size,
 				       enum bpf_access_type type,
 				       const struct bpf_prog *prog,
-- 
GitLab


From 3645c71b582b29e288598bc8e08c284ba5d2c94b Mon Sep 17 00:00:00 2001
From: Mahmoud Maatuq <mahmoudmatook.mm@gmail.com>
Date: Sun, 16 Jul 2023 22:43:49 +0400
Subject: [PATCH 0184/1806] selftests/net: replace manual array size calc with
 ARRAYSIZE macro.

fixes coccinelle WARNING: Use ARRAY_SIZE

Signed-off-by: Mahmoud Maatuq <mahmoudmatook.mm@gmail.com>
Link: https://lore.kernel.org/r/20230716184349.2124858-1-mahmoudmatook.mm@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile          | 2 ++
 tools/testing/selftests/net/csum.c            | 6 ++++--
 tools/testing/selftests/net/hwtstamp_config.c | 6 ++++--
 tools/testing/selftests/net/psock_lib.h       | 4 +++-
 4 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 2f69f7274e3d8..fbf579f469927 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -3,6 +3,8 @@
 
 CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
 CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES)
+# Additional include paths needed by kselftest.h
+CFLAGS += -I../
 
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \
 	      rtnetlink.sh xfrm_policy.sh test_blackhole_dev.sh
diff --git a/tools/testing/selftests/net/csum.c b/tools/testing/selftests/net/csum.c
index 82a1c1839da68..90eb06fefa59e 100644
--- a/tools/testing/selftests/net/csum.c
+++ b/tools/testing/selftests/net/csum.c
@@ -91,6 +91,8 @@
 #include <sys/types.h>
 #include <unistd.h>
 
+#include "kselftest.h"
+
 static bool cfg_bad_csum;
 static int cfg_family = PF_INET6;
 static int cfg_num_pkt = 4;
@@ -450,7 +452,7 @@ static void send_packet(int fd, const char *buf, int len)
 	iov[2].iov_len = len;
 
 	msg.msg_iov = iov;
-	msg.msg_iovlen = sizeof(iov) / sizeof(iov[0]);
+	msg.msg_iovlen = ARRAY_SIZE(iov);
 
 	msg.msg_name = &addr;
 	msg.msg_namelen = sizeof(addr);
@@ -505,7 +507,7 @@ static void __recv_prepare_packet_filter(int fd, int off_nexthdr, int off_dport)
 	struct sock_fprog prog = {};
 
 	prog.filter = filter;
-	prog.len = sizeof(filter) / sizeof(struct sock_filter);
+	prog.len = ARRAY_SIZE(filter);
 	if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prog, sizeof(prog)))
 		error(1, errno, "setsockopt filter");
 }
diff --git a/tools/testing/selftests/net/hwtstamp_config.c b/tools/testing/selftests/net/hwtstamp_config.c
index e1fdee8410211..170728c96c464 100644
--- a/tools/testing/selftests/net/hwtstamp_config.c
+++ b/tools/testing/selftests/net/hwtstamp_config.c
@@ -16,6 +16,8 @@
 #include <linux/net_tstamp.h>
 #include <linux/sockios.h>
 
+#include "kselftest.h"
+
 static int
 lookup_value(const char **names, int size, const char *name)
 {
@@ -50,7 +52,7 @@ static const char *tx_types[] = {
 	TX_TYPE(ONESTEP_SYNC)
 #undef TX_TYPE
 };
-#define N_TX_TYPES ((int)(sizeof(tx_types) / sizeof(tx_types[0])))
+#define N_TX_TYPES ((int)(ARRAY_SIZE(tx_types)))
 
 static const char *rx_filters[] = {
 #define RX_FILTER(name) [HWTSTAMP_FILTER_ ## name] = #name
@@ -71,7 +73,7 @@ static const char *rx_filters[] = {
 	RX_FILTER(PTP_V2_DELAY_REQ),
 #undef RX_FILTER
 };
-#define N_RX_FILTERS ((int)(sizeof(rx_filters) / sizeof(rx_filters[0])))
+#define N_RX_FILTERS ((int)(ARRAY_SIZE(rx_filters)))
 
 static void usage(void)
 {
diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h
index faa884385c45c..6e4fef560873b 100644
--- a/tools/testing/selftests/net/psock_lib.h
+++ b/tools/testing/selftests/net/psock_lib.h
@@ -14,6 +14,8 @@
 #include <arpa/inet.h>
 #include <unistd.h>
 
+#include "kselftest.h"
+
 #define DATA_LEN			100
 #define DATA_CHAR			'a'
 #define DATA_CHAR_1			'b'
@@ -63,7 +65,7 @@ static __maybe_unused void pair_udp_setfilter(int fd)
 	struct sock_fprog bpf_prog;
 
 	bpf_prog.filter = bpf_filter;
-	bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter);
+	bpf_prog.len = ARRAY_SIZE(bpf_filter);
 
 	if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf_prog,
 		       sizeof(bpf_prog))) {
-- 
GitLab


From 9843814fc651d590cc5a82488c644ccf70975f16 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Mon, 17 Jul 2023 10:13:33 +0800
Subject: [PATCH 0185/1806] net: txgbe: change LAN reset mode

The old way to do LAN reset is sending reset command to firmware. Once
firmware performs reset, it reconfigures what it needs.

In the new firmware versions, veto bit is introduced for NCSI/LLDP to
block PHY domain in LAN reset. At this point, writing register of LAN
reset directly makes the same effect as the old way. And it does not
reset MNG domain, so that veto bit does not change.

Since veto bit was never used, the old firmware is compatible with the
driver before and after this change. The new firmware needs to use with
the driver after this change if it wants to implement the new feature,
otherwise it is the same as the old firmware.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230717021333.94181-1-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/libwx/wx_hw.c    | 65 -------------------
 drivers/net/ethernet/wangxun/libwx/wx_hw.h    |  1 -
 drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c |  8 +--
 3 files changed, 4 insertions(+), 70 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index ad09ab1d12095..f833c84a78768 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -431,71 +431,6 @@ out:
 }
 EXPORT_SYMBOL(wx_read_ee_hostif_buffer);
 
-/**
- *  wx_calculate_checksum - Calculate checksum for buffer
- *  @buffer: pointer to EEPROM
- *  @length: size of EEPROM to calculate a checksum for
- *  Calculates the checksum for some buffer on a specified length.  The
- *  checksum calculated is returned.
- **/
-static u8 wx_calculate_checksum(u8 *buffer, u32 length)
-{
-	u8 sum = 0;
-	u32 i;
-
-	if (!buffer)
-		return 0;
-
-	for (i = 0; i < length; i++)
-		sum += buffer[i];
-
-	return (u8)(0 - sum);
-}
-
-/**
- *  wx_reset_hostif - send reset cmd to fw
- *  @wx: pointer to hardware structure
- *
- *  Sends reset cmd to firmware through the manageability
- *  block.
- **/
-int wx_reset_hostif(struct wx *wx)
-{
-	struct wx_hic_reset reset_cmd;
-	int ret_val = 0;
-	int i;
-
-	reset_cmd.hdr.cmd = FW_RESET_CMD;
-	reset_cmd.hdr.buf_len = FW_RESET_LEN;
-	reset_cmd.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED;
-	reset_cmd.lan_id = wx->bus.func;
-	reset_cmd.reset_type = (u16)wx->reset_type;
-	reset_cmd.hdr.checksum = 0;
-	reset_cmd.hdr.checksum = wx_calculate_checksum((u8 *)&reset_cmd,
-						       (FW_CEM_HDR_LEN +
-							reset_cmd.hdr.buf_len));
-
-	for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) {
-		ret_val = wx_host_interface_command(wx, (u32 *)&reset_cmd,
-						    sizeof(reset_cmd),
-						    WX_HI_COMMAND_TIMEOUT,
-						    true);
-		if (ret_val != 0)
-			continue;
-
-		if (reset_cmd.hdr.cmd_or_resp.ret_status ==
-		    FW_CEM_RESP_STATUS_SUCCESS)
-			ret_val = 0;
-		else
-			ret_val = -EFAULT;
-
-		break;
-	}
-
-	return ret_val;
-}
-EXPORT_SYMBOL(wx_reset_hostif);
-
 /**
  *  wx_init_eeprom_params - Initialize EEPROM params
  *  @wx: pointer to hardware structure
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
index b95090e973aeb..0b3447bc6f2fe 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
@@ -14,7 +14,6 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer,
 int wx_read_ee_hostif(struct wx *wx, u16 offset, u16 *data);
 int wx_read_ee_hostif_buffer(struct wx *wx,
 			     u16 offset, u16 words, u16 *data);
-int wx_reset_hostif(struct wx *wx);
 void wx_init_eeprom_params(struct wx *wx);
 void wx_get_mac_addr(struct wx *wx, u8 *mac_addr);
 void wx_init_rx_addrs(struct wx *wx);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
index 0772eb14eabf6..6e130d1f7a7bb 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
@@ -257,16 +257,16 @@ static void txgbe_reset_misc(struct wx *wx)
 int txgbe_reset_hw(struct wx *wx)
 {
 	int status;
+	u32 val;
 
 	/* Call adapter stop to disable tx/rx and clear interrupts */
 	status = wx_stop_adapter(wx);
 	if (status != 0)
 		return status;
 
-	if (!(((wx->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) ||
-	      ((wx->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP)))
-		wx_reset_hostif(wx);
-
+	val = WX_MIS_RST_LAN_RST(wx->bus.func);
+	wr32(wx, WX_MIS_RST, val | rd32(wx, WX_MIS_RST));
+	WX_WRITE_FLUSH(wx);
 	usleep_range(10, 100);
 
 	status = wx_check_flash_load(wx, TXGBE_SPI_ILDR_STATUS_LAN_SW_RST(wx->bus.func));
-- 
GitLab


From f8e343326c1d267e2144586a72663540f651c6a7 Mon Sep 17 00:00:00 2001
From: Minjie Du <duminjie@vivo.com>
Date: Mon, 17 Jul 2023 10:55:37 +0800
Subject: [PATCH 0186/1806] net: mvpp2: debugfs: remove redundant parameter
 check in three functions

As per the comment above debugfs_create_dir(), it is not expected to
return an error, so an extra error check is not needed.
Drop the return check of debugfs_create_dir() in
mvpp2_dbgfs_c2_entry_init(), mvpp2_dbgfs_flow_tbl_entry_init()
and mvpp2_dbgfs_cls_init().

Signed-off-by: Minjie Du <duminjie@vivo.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/20230717025538.2848-1-duminjie@vivo.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
index 75e83ea2a926e..0f9bc4f8ec3b9 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
@@ -593,8 +593,6 @@ static int mvpp2_dbgfs_c2_entry_init(struct dentry *parent,
 	sprintf(c2_entry_name, "%03d", id);
 
 	c2_entry_dir = debugfs_create_dir(c2_entry_name, parent);
-	if (!c2_entry_dir)
-		return -ENOMEM;
 
 	entry = &priv->dbgfs_entries->c2_entries[id];
 
@@ -626,8 +624,6 @@ static int mvpp2_dbgfs_flow_tbl_entry_init(struct dentry *parent,
 	sprintf(flow_tbl_entry_name, "%03d", id);
 
 	flow_tbl_entry_dir = debugfs_create_dir(flow_tbl_entry_name, parent);
-	if (!flow_tbl_entry_dir)
-		return -ENOMEM;
 
 	entry = &priv->dbgfs_entries->flt_entries[id];
 
@@ -646,12 +642,8 @@ static int mvpp2_dbgfs_cls_init(struct dentry *parent, struct mvpp2 *priv)
 	int i, ret;
 
 	cls_dir = debugfs_create_dir("classifier", parent);
-	if (!cls_dir)
-		return -ENOMEM;
 
 	c2_dir = debugfs_create_dir("c2", cls_dir);
-	if (!c2_dir)
-		return -ENOMEM;
 
 	for (i = 0; i < MVPP22_CLS_C2_N_ENTRIES; i++) {
 		ret = mvpp2_dbgfs_c2_entry_init(c2_dir, priv, i);
@@ -660,8 +652,6 @@ static int mvpp2_dbgfs_cls_init(struct dentry *parent, struct mvpp2 *priv)
 	}
 
 	flow_tbl_dir = debugfs_create_dir("flow_table", cls_dir);
-	if (!flow_tbl_dir)
-		return -ENOMEM;
 
 	for (i = 0; i < MVPP2_CLS_FLOWS_TBL_SIZE; i++) {
 		ret = mvpp2_dbgfs_flow_tbl_entry_init(flow_tbl_dir, priv, i);
-- 
GitLab


From da4e8648079eb6f26f3a88d8c34270a057e2bfe6 Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Mon, 17 Jul 2023 12:35:38 -0700
Subject: [PATCH 0187/1806] net: mana: Batch ringing RX queue doorbell on
 receiving packets

It's inefficient to ring the doorbell page every time a WQE is posted to
the received queue. Excessive MMIO writes result in CPU spending more
time waiting on LOCK instructions (atomic operations), resulting in
poor scaling performance.

Move the code for ringing doorbell page to where after we have posted all
WQEs to the receive queue during a callback from napi_poll().

With this change, tests showed an improvement from 120G/s to 160G/s on a
200G physical link, with 16 or 32 hardware queues.

Tests showed no regression in network latency benchmarks on single
connection.

Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Long Li <longli@microsoft.com>
Link: https://lore.kernel.org/r/1689622539-5334-2-git-send-email-longli@linuxonhyperv.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index a499e460594b6..ac2acc9aca9d0 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1386,8 +1386,8 @@ static void mana_post_pkt_rxq(struct mana_rxq *rxq)
 
 	recv_buf_oob = &rxq->rx_oobs[curr_index];
 
-	err = mana_gd_post_and_ring(rxq->gdma_rq, &recv_buf_oob->wqe_req,
-				    &recv_buf_oob->wqe_inf);
+	err = mana_gd_post_work_request(rxq->gdma_rq, &recv_buf_oob->wqe_req,
+					&recv_buf_oob->wqe_inf);
 	if (WARN_ON_ONCE(err))
 		return;
 
@@ -1657,6 +1657,12 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
 		mana_process_rx_cqe(rxq, cq, &comp[i]);
 	}
 
+	if (comp_read > 0) {
+		struct gdma_context *gc = rxq->gdma_rq->gdma_dev->gdma_context;
+
+		mana_gd_wq_ring_doorbell(gc, rxq->gdma_rq);
+	}
+
 	if (rxq->xdp_flush)
 		xdp_do_flush();
 }
-- 
GitLab


From f5e39b57124fd4715d7f0e2f841b8609b38f3e40 Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Mon, 17 Jul 2023 12:35:39 -0700
Subject: [PATCH 0188/1806] net: mana: Use the correct WQE count for ringing RQ
 doorbell

The hardware specification specifies that WQE_COUNT should set to 0 for
the Receive Queue. Although currently the hardware doesn't enforce the
check, in the future releases it may check on this value.

Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Long Li <longli@microsoft.com>
Link: https://lore.kernel.org/r/1689622539-5334-3-git-send-email-longli@linuxonhyperv.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/gdma_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 8f3f78b685922..3765d3389a9a0 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -300,8 +300,11 @@ static void mana_gd_ring_doorbell(struct gdma_context *gc, u32 db_index,
 
 void mana_gd_wq_ring_doorbell(struct gdma_context *gc, struct gdma_queue *queue)
 {
+	/* Hardware Spec specifies that software client should set 0 for
+	 * wqe_cnt for Receive Queues. This value is not used in Send Queues.
+	 */
 	mana_gd_ring_doorbell(gc, queue->gdma_dev->doorbell, queue->type,
-			      queue->id, queue->head * GDMA_WQE_BU_SIZE, 1);
+			      queue->id, queue->head * GDMA_WQE_BU_SIZE, 0);
 }
 
 void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
-- 
GitLab


From dfa2f0483360d4d6f2324405464c9f281156bd87 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 17 Jul 2023 15:29:17 +0000
Subject: [PATCH 0189/1806] tcp: get rid of sysctl_tcp_adv_win_scale

With modern NIC drivers shifting to full page allocations per
received frame, we face the following issue:

TCP has one per-netns sysctl used to tweak how to translate
a memory use into an expected payload (RWIN), in RX path.

tcp_win_from_space() implementation is limited to few cases.

For hosts dealing with various MSS, we either under estimate
or over estimate the RWIN we send to the remote peers.

For instance with the default sysctl_tcp_adv_win_scale value,
we expect to store 50% of payload per allocated chunk of memory.

For the typical use of MTU=1500 traffic, and order-0 pages allocations
by NIC drivers, we are sending too big RWIN, leading to potential
tcp collapse operations, which are extremely expensive and source
of latency spikes.

This patch makes sysctl_tcp_adv_win_scale obsolete, and instead
uses a per socket scaling factor, so that we can precisely
adjust the RWIN based on effective skb->len/skb->truesize ratio.

This patch alone can double TCP receive performance when receivers
are too slow to drain their receive queue, or by allowing
a bigger RWIN when MSS is close to PAGE_SIZE.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Link: https://lore.kernel.org/r/20230717152917.751987-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/ip-sysctl.rst |  1 +
 include/linux/tcp.h                    |  4 +++-
 include/net/netns/ipv4.h               |  2 +-
 include/net/tcp.h                      | 24 ++++++++++++++++++++----
 net/ipv4/tcp.c                         | 11 ++++++-----
 net/ipv4/tcp_input.c                   | 19 ++++++++++++-------
 6 files changed, 43 insertions(+), 18 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 4a010a7cde7f8..82f2117cf2b36 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -321,6 +321,7 @@ tcp_abort_on_overflow - BOOLEAN
 	option can harm clients of your server.
 
 tcp_adv_win_scale - INTEGER
+	Obsolete since linux-6.6
 	Count buffering overhead as bytes/2^tcp_adv_win_scale
 	(if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale),
 	if it is <= 0.
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index b4c08ac869835..fbcb0ce13171d 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -172,6 +172,8 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
 	return (struct tcp_request_sock *)req;
 }
 
+#define TCP_RMEM_TO_WIN_SCALE 8
+
 struct tcp_sock {
 	/* inet_connection_sock has to be the first member of tcp_sock */
 	struct inet_connection_sock	inet_conn;
@@ -238,7 +240,7 @@ struct tcp_sock {
 
 	u32	window_clamp;	/* Maximal window to advertise		*/
 	u32	rcv_ssthresh;	/* Current window clamp			*/
-
+	u8	scaling_ratio;	/* see tcp_win_from_space() */
 	/* Information of the most recently (s)acked skb */
 	struct tcp_rack {
 		u64 mstamp; /* (Re)sent time of the skb */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index f003747181593..7a41c47915367 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -152,7 +152,7 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_abort_on_overflow;
 	u8 sysctl_tcp_fack; /* obsolete */
 	int sysctl_tcp_max_reordering;
-	int sysctl_tcp_adv_win_scale;
+	int sysctl_tcp_adv_win_scale; /* obsolete */
 	u8 sysctl_tcp_dsack;
 	u8 sysctl_tcp_app_win;
 	u8 sysctl_tcp_frto;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 226bce6d1e8c3..2104a71c75ba7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1434,11 +1434,27 @@ void tcp_select_initial_window(const struct sock *sk, int __space,
 
 static inline int tcp_win_from_space(const struct sock *sk, int space)
 {
-	int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale);
+	s64 scaled_space = (s64)space * tcp_sk(sk)->scaling_ratio;
 
-	return tcp_adv_win_scale <= 0 ?
-		(space>>(-tcp_adv_win_scale)) :
-		space - (space>>tcp_adv_win_scale);
+	return scaled_space >> TCP_RMEM_TO_WIN_SCALE;
+}
+
+/* inverse of tcp_win_from_space() */
+static inline int tcp_space_from_win(const struct sock *sk, int win)
+{
+	u64 val = (u64)win << TCP_RMEM_TO_WIN_SCALE;
+
+	do_div(val, tcp_sk(sk)->scaling_ratio);
+	return val;
+}
+
+static inline void tcp_scaling_ratio_init(struct sock *sk)
+{
+	/* Assume a conservative default of 1200 bytes of payload per 4K page.
+	 * This may be adjusted later in tcp_measure_rcv_mss().
+	 */
+	tcp_sk(sk)->scaling_ratio = (1200 << TCP_RMEM_TO_WIN_SCALE) /
+				    SKB_TRUESIZE(4096);
 }
 
 /* Note: caller must be prepared to deal with negative returns */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e03e087453081..88f4ebab12acc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -457,6 +457,7 @@ void tcp_init_sock(struct sock *sk)
 
 	WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
 	WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
+	tcp_scaling_ratio_init(sk);
 
 	set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
 	sk_sockets_allocated_inc(sk);
@@ -1700,7 +1701,7 @@ EXPORT_SYMBOL(tcp_peek_len);
 /* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */
 int tcp_set_rcvlowat(struct sock *sk, int val)
 {
-	int cap;
+	int space, cap;
 
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		cap = sk->sk_rcvbuf >> 1;
@@ -1715,10 +1716,10 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		return 0;
 
-	val <<= 1;
-	if (val > sk->sk_rcvbuf) {
-		WRITE_ONCE(sk->sk_rcvbuf, val);
-		tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val);
+	space = tcp_space_from_win(sk, val);
+	if (space > sk->sk_rcvbuf) {
+		WRITE_ONCE(sk->sk_rcvbuf, space);
+		tcp_sk(sk)->window_clamp = val;
 	}
 	return 0;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 57c8af1859c16..3cd92035e0902 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -237,6 +237,16 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 	 */
 	len = skb_shinfo(skb)->gso_size ? : skb->len;
 	if (len >= icsk->icsk_ack.rcv_mss) {
+		/* Note: divides are still a bit expensive.
+		 * For the moment, only adjust scaling_ratio
+		 * when we update icsk_ack.rcv_mss.
+		 */
+		if (unlikely(len != icsk->icsk_ack.rcv_mss)) {
+			u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE;
+
+			do_div(val, skb->truesize);
+			tcp_sk(sk)->scaling_ratio = val ? val : 1;
+		}
 		icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
 					       tcp_sk(sk)->advmss);
 		/* Account for possibly-removed options */
@@ -727,8 +737,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
-		int rcvmem, rcvbuf;
 		u64 rcvwin, grow;
+		int rcvbuf;
 
 		/* minimal window to cope with packet losses, assuming
 		 * steady state. Add some cushion because of small variations.
@@ -740,12 +750,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 		do_div(grow, tp->rcvq_space.space);
 		rcvwin += (grow << 1);
 
-		rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
-		while (tcp_win_from_space(sk, rcvmem) < tp->advmss)
-			rcvmem += 128;
-
-		do_div(rcvwin, tp->advmss);
-		rcvbuf = min_t(u64, rcvwin * rcvmem,
+		rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
 			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 		if (rcvbuf > sk->sk_rcvbuf) {
 			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
-- 
GitLab


From f15fbe46f5ed473f547944ebafdff35372588fb5 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Mon, 17 Jul 2023 11:10:55 +0800
Subject: [PATCH 0190/1806] net: atlantic: Remove unnecessary (void*)
 conversions

No need cast (void*) to (struct hw_atl2_priv *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Link: https://lore.kernel.org/r/20230717031055.54266-1-yunchuan@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c | 12 ++++++------
 .../aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c     |  2 +-
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index 5dfc751572edc..220400a633f5e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -93,7 +93,7 @@ static u32 hw_atl2_sem_act_rslvr_get(struct aq_hw_s *self)
 
 static int hw_atl2_hw_reset(struct aq_hw_s *self)
 {
-	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	struct hw_atl2_priv *priv = self->priv;
 	int err;
 
 	err = hw_atl2_utils_soft_reset(self);
@@ -378,8 +378,8 @@ static int hw_atl2_hw_init_tx_path(struct aq_hw_s *self)
 
 static void hw_atl2_hw_init_new_rx_filters(struct aq_hw_s *self)
 {
-	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
 	u8 *prio_tc_map = self->aq_nic_cfg->prio_tc_map;
+	struct hw_atl2_priv *priv = self->priv;
 	u16 action;
 	u8 index;
 	int i;
@@ -433,7 +433,7 @@ static void hw_atl2_hw_new_rx_filter_vlan_promisc(struct aq_hw_s *self,
 	u16 off_action = (!promisc &&
 			  !hw_atl_rpfl2promiscuous_mode_en_get(self)) ?
 				HW_ATL2_ACTION_DROP : HW_ATL2_ACTION_DISABLE;
-	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	struct hw_atl2_priv *priv = self->priv;
 	u8 index;
 
 	index = priv->art_base_index + HW_ATL2_RPF_VLAN_PROMISC_OFF_INDEX;
@@ -445,7 +445,7 @@ static void hw_atl2_hw_new_rx_filter_vlan_promisc(struct aq_hw_s *self,
 static void hw_atl2_hw_new_rx_filter_promisc(struct aq_hw_s *self, bool promisc)
 {
 	u16 off_action = promisc ? HW_ATL2_ACTION_DISABLE : HW_ATL2_ACTION_DROP;
-	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	struct hw_atl2_priv *priv = self->priv;
 	bool vlan_promisc_enable;
 	u8 index;
 
@@ -539,8 +539,8 @@ static int hw_atl2_hw_init(struct aq_hw_s *self, const u8 *mac_addr)
 		[AQ_HW_IRQ_MSIX]    = { 0x20000022U, 0x20000026U },
 	};
 
-	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
 	struct aq_nic_cfg_s *aq_nic_cfg = self->aq_nic_cfg;
+	struct hw_atl2_priv *priv = self->priv;
 	u8 base_index, count;
 	int err;
 
@@ -770,7 +770,7 @@ static struct aq_stats_s *hw_atl2_utils_get_hw_stats(struct aq_hw_s *self)
 static int hw_atl2_hw_vlan_set(struct aq_hw_s *self,
 			       struct aq_rx_filter_vlan *aq_vlans)
 {
-	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	struct hw_atl2_priv *priv = self->priv;
 	u32 queue;
 	u8 index;
 	int i;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
index 674683b543044..52e2070a4a2f0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
@@ -413,8 +413,8 @@ do { \
 
 static int aq_a2_fw_update_stats(struct aq_hw_s *self)
 {
-	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
 	struct aq_stats_s *cs = &self->curr_stats;
+	struct hw_atl2_priv *priv = self->priv;
 	struct statistics_s stats;
 	struct version_s version;
 	int err;
-- 
GitLab


From 89c04d6c49c36f7bb6e5d2f7c90dd0634d7a1642 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Mon, 17 Jul 2023 11:11:15 +0800
Subject: [PATCH 0191/1806] net: ppp: Remove unnecessary (void*) conversions

No need cast (void*) to (struct sock *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://lore.kernel.org/r/20230717031115.54432-1-yunchuan@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ppp/pppoe.c | 4 ++--
 drivers/net/ppp/pptp.c  | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 3b79c603b9363..ba8b6bd8233ca 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -968,7 +968,7 @@ abort:
  ***********************************************************************/
 static int pppoe_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 {
-	struct sock *sk = (struct sock *)chan->private;
+	struct sock *sk = chan->private;
 	return __pppoe_xmit(sk, skb);
 }
 
@@ -976,7 +976,7 @@ static int pppoe_fill_forward_path(struct net_device_path_ctx *ctx,
 				   struct net_device_path *path,
 				   const struct ppp_channel *chan)
 {
-	struct sock *sk = (struct sock *)chan->private;
+	struct sock *sk = chan->private;
 	struct pppox_sock *po = pppox_sk(sk);
 	struct net_device *dev = po->pppoe_dev;
 
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 57d38b27812d5..6833ef0c79305 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -148,7 +148,7 @@ static struct rtable *pptp_route_output(const struct pppox_sock *po,
 
 static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 {
-	struct sock *sk = (struct sock *) chan->private;
+	struct sock *sk = chan->private;
 	struct pppox_sock *po = pppox_sk(sk);
 	struct net *net = sock_net(sk);
 	struct pptp_opt *opt = &po->proto.pptp;
@@ -575,7 +575,7 @@ out:
 static int pptp_ppp_ioctl(struct ppp_channel *chan, unsigned int cmd,
 	unsigned long arg)
 {
-	struct sock *sk = (struct sock *) chan->private;
+	struct sock *sk = chan->private;
 	struct pppox_sock *po = pppox_sk(sk);
 	struct pptp_opt *opt = &po->proto.pptp;
 	void __user *argp = (void __user *)arg;
-- 
GitLab


From 14fbcad00fe51be25ff4c545836fdc518b69045a Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Mon, 17 Jul 2023 11:11:28 +0800
Subject: [PATCH 0192/1806] net: hns3: remove unnecessary (void*) conversions.

No need cast (void*) to (struct hns3_nic_priv *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Reviewed-by: Hao Lan <lanhao@huawei.com>
Link: https://lore.kernel.org/r/20230717031128.54557-1-yunchuan@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 407d30ee55d2e..36858a72d771e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -569,8 +569,8 @@ static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 
 static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data)
 {
-	struct hns3_nic_priv *nic_priv = (struct hns3_nic_priv *)handle->priv;
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct hns3_nic_priv *nic_priv = handle->priv;
 	struct hns3_enet_ring *ring;
 	u8 *stat;
 	int i, j;
-- 
GitLab


From 406eb9cf6f6fc248bd898bef26ea34987c84f8cd Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Mon, 17 Jul 2023 11:11:37 +0800
Subject: [PATCH 0193/1806] net: hns: Remove unnecessary (void*) conversions

No need cast (void*) to (struct hns_mdio_device *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Reviewed-by: Hao Lan <lanhao@huawei.com>
Link: https://lore.kernel.org/r/20230717031137.54639-1-yunchuan@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns_mdio.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 9232caaf0bdc1..409a89d802208 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -217,7 +217,7 @@ static void hns_mdio_cmd_write(struct hns_mdio_device *mdio_dev,
 static int hns_mdio_write_c22(struct mii_bus *bus,
 			      int phy_id, int regnum, u16 data)
 {
-	struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv;
+	struct hns_mdio_device *mdio_dev = bus->priv;
 	u16 reg = (u16)(regnum & 0xffff);
 	u16 cmd_reg_cfg;
 	int ret;
@@ -259,7 +259,7 @@ static int hns_mdio_write_c22(struct mii_bus *bus,
 static int hns_mdio_write_c45(struct mii_bus *bus, int phy_id, int devad,
 			      int regnum, u16 data)
 {
-	struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv;
+	struct hns_mdio_device *mdio_dev = bus->priv;
 	u16 reg = (u16)(regnum & 0xffff);
 	u16 cmd_reg_cfg;
 	int ret;
@@ -312,7 +312,7 @@ static int hns_mdio_write_c45(struct mii_bus *bus, int phy_id, int devad,
  */
 static int hns_mdio_read_c22(struct mii_bus *bus, int phy_id, int regnum)
 {
-	struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv;
+	struct hns_mdio_device *mdio_dev = bus->priv;
 	u16 reg = (u16)(regnum & 0xffff);
 	u16 reg_val;
 	int ret;
@@ -363,7 +363,7 @@ static int hns_mdio_read_c22(struct mii_bus *bus, int phy_id, int regnum)
 static int hns_mdio_read_c45(struct mii_bus *bus, int phy_id, int devad,
 			     int regnum)
 {
-	struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv;
+	struct hns_mdio_device *mdio_dev = bus->priv;
 	u16 reg = (u16)(regnum & 0xffff);
 	u16 reg_val;
 	int ret;
@@ -424,7 +424,7 @@ static int hns_mdio_read_c45(struct mii_bus *bus, int phy_id, int devad,
  */
 static int hns_mdio_reset(struct mii_bus *bus)
 {
-	struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv;
+	struct hns_mdio_device *mdio_dev = bus->priv;
 	const struct hns_mdio_sc_reg *sc_reg;
 	int ret;
 
-- 
GitLab


From c59cc2679accb9b6b2b50190cf484e036d9662c3 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Mon, 17 Jul 2023 11:11:54 +0800
Subject: [PATCH 0194/1806] ice: remove unnecessary (void*) conversions

No need cast (void*) to (struct ice_ring_container *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Link: https://lore.kernel.org/r/20230717031154.54740-1-yunchuan@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 19a5e7f3a075e..6d021597506f7 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -6249,7 +6249,7 @@ static void ice_tx_dim_work(struct work_struct *work)
 	u16 itr;
 
 	dim = container_of(work, struct dim, work);
-	rc = (struct ice_ring_container *)dim->priv;
+	rc = dim->priv;
 
 	WARN_ON(dim->profile_ix >= ARRAY_SIZE(tx_profile));
 
@@ -6269,7 +6269,7 @@ static void ice_rx_dim_work(struct work_struct *work)
 	u16 itr;
 
 	dim = container_of(work, struct dim, work);
-	rc = (struct ice_ring_container *)dim->priv;
+	rc = dim->priv;
 
 	WARN_ON(dim->profile_ix >= ARRAY_SIZE(rx_profile));
 
-- 
GitLab


From 099090c6effc6b28b30c680b33903559bcaff6d0 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Mon, 17 Jul 2023 11:12:04 +0800
Subject: [PATCH 0195/1806] ethernet: smsc: remove unnecessary (void*)
 conversions

No need cast (voidd*) to (struct smsc911x_data *) or
(struct smsc9420_pdata *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Link: https://lore.kernel.org/r/20230717031204.54912-1-yunchuan@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/smsc/smsc911x.c | 4 ++--
 drivers/net/ethernet/smsc/smsc9420.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 174dc8908b72f..c362bff3cb835 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -552,7 +552,7 @@ static void smsc911x_mac_write(struct smsc911x_data *pdata,
 /* Get a phy register */
 static int smsc911x_mii_read(struct mii_bus *bus, int phyaddr, int regidx)
 {
-	struct smsc911x_data *pdata = (struct smsc911x_data *)bus->priv;
+	struct smsc911x_data *pdata = bus->priv;
 	unsigned long flags;
 	unsigned int addr;
 	int i, reg;
@@ -591,7 +591,7 @@ out:
 static int smsc911x_mii_write(struct mii_bus *bus, int phyaddr, int regidx,
 			   u16 val)
 {
-	struct smsc911x_data *pdata = (struct smsc911x_data *)bus->priv;
+	struct smsc911x_data *pdata = bus->priv;
 	unsigned long flags;
 	unsigned int addr;
 	int i, reg;
diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c
index 71fbb358bb7d2..3b26f1d86beba 100644
--- a/drivers/net/ethernet/smsc/smsc9420.c
+++ b/drivers/net/ethernet/smsc/smsc9420.c
@@ -102,7 +102,7 @@ static inline void smsc9420_pci_flush_write(struct smsc9420_pdata *pd)
 
 static int smsc9420_mii_read(struct mii_bus *bus, int phyaddr, int regidx)
 {
-	struct smsc9420_pdata *pd = (struct smsc9420_pdata *)bus->priv;
+	struct smsc9420_pdata *pd = bus->priv;
 	unsigned long flags;
 	u32 addr;
 	int i, reg = -EIO;
@@ -140,7 +140,7 @@ out:
 static int smsc9420_mii_write(struct mii_bus *bus, int phyaddr, int regidx,
 			   u16 val)
 {
-	struct smsc9420_pdata *pd = (struct smsc9420_pdata *)bus->priv;
+	struct smsc9420_pdata *pd = bus->priv;
 	unsigned long flags;
 	u32 addr;
 	int i, reg = -EIO;
-- 
GitLab


From 04115debedce8a14f4e293b5493ed7379a0d3cf8 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Mon, 17 Jul 2023 11:12:12 +0800
Subject: [PATCH 0196/1806] net: mdio: Remove unnecessary (void*) conversions

No need cast (void*) to (struct xgene_mdio_pdata *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230717031212.54991-1-yunchuan@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mdio/mdio-xgene.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/mdio/mdio-xgene.c b/drivers/net/mdio/mdio-xgene.c
index 7aafc221b5cf0..683e8f8319abe 100644
--- a/drivers/net/mdio/mdio-xgene.c
+++ b/drivers/net/mdio/mdio-xgene.c
@@ -79,7 +79,7 @@ EXPORT_SYMBOL(xgene_mdio_wr_mac);
 
 int xgene_mdio_rgmii_read(struct mii_bus *bus, int phy_id, int reg)
 {
-	struct xgene_mdio_pdata *pdata = (struct xgene_mdio_pdata *)bus->priv;
+	struct xgene_mdio_pdata *pdata = bus->priv;
 	u32 data, done;
 	u8 wait = 10;
 
@@ -105,7 +105,7 @@ EXPORT_SYMBOL(xgene_mdio_rgmii_read);
 
 int xgene_mdio_rgmii_write(struct mii_bus *bus, int phy_id, int reg, u16 data)
 {
-	struct xgene_mdio_pdata *pdata = (struct xgene_mdio_pdata *)bus->priv;
+	struct xgene_mdio_pdata *pdata = bus->priv;
 	u32 val, done;
 	u8 wait = 10;
 
-- 
GitLab


From 9235e3bcc613e3c549fb4e5948b7d75294f9e2c9 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Mon, 17 Jul 2023 11:12:21 +0800
Subject: [PATCH 0197/1806] can: ems_pci: Remove unnecessary (void*)
 conversions

No need cast (void*) to (struct ems_pci_card *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Acked-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://lore.kernel.org/r/20230717031221.55073-1-yunchuan@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/can/sja1000/ems_pci.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/sja1000/ems_pci.c b/drivers/net/can/sja1000/ems_pci.c
index c56e27223e5fe..ac86640998a8f 100644
--- a/drivers/net/can/sja1000/ems_pci.c
+++ b/drivers/net/can/sja1000/ems_pci.c
@@ -148,7 +148,7 @@ static void ems_pci_v1_write_reg(const struct sja1000_priv *priv,
 
 static void ems_pci_v1_post_irq(const struct sja1000_priv *priv)
 {
-	struct ems_pci_card *card = (struct ems_pci_card *)priv->priv;
+	struct ems_pci_card *card = priv->priv;
 
 	/* reset int flag of pita */
 	writel(PITA2_ICR_INT0_EN | PITA2_ICR_INT0,
@@ -168,7 +168,7 @@ static void ems_pci_v2_write_reg(const struct sja1000_priv *priv,
 
 static void ems_pci_v2_post_irq(const struct sja1000_priv *priv)
 {
-	struct ems_pci_card *card = (struct ems_pci_card *)priv->priv;
+	struct ems_pci_card *card = priv->priv;
 
 	writel(PLX_ICSR_ENA_CLR, card->conf_addr + PLX_ICSR);
 }
@@ -186,7 +186,7 @@ static void ems_pci_v3_write_reg(const struct sja1000_priv *priv,
 
 static void ems_pci_v3_post_irq(const struct sja1000_priv *priv)
 {
-	struct ems_pci_card *card = (struct ems_pci_card *)priv->priv;
+	struct ems_pci_card *card = priv->priv;
 
 	writel(ASIX_LINTSR_INT0AC, card->conf_addr + ASIX_LINTSR);
 }
-- 
GitLab


From 1d5123efdb917f102e30dba1cdd6c6912b85cdb9 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Mon, 17 Jul 2023 11:12:29 +0800
Subject: [PATCH 0198/1806] net: bna: Remove unnecessary (void*) conversions

No need cast (void*) to (struct bnad_tx_info *) or
(struct bnad_rx_info *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Link: https://lore.kernel.org/r/20230717031229.55169-1-yunchuan@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/brocade/bna/bnad.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index d6d90f9722a7e..31191b520b587 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -1037,8 +1037,7 @@ bnad_cb_ccb_destroy(struct bnad *bnad, struct bna_ccb *ccb)
 static void
 bnad_cb_tx_stall(struct bnad *bnad, struct bna_tx *tx)
 {
-	struct bnad_tx_info *tx_info =
-			(struct bnad_tx_info *)tx->priv;
+	struct bnad_tx_info *tx_info = tx->priv;
 	struct bna_tcb *tcb;
 	u32 txq_id;
 	int i;
@@ -1056,7 +1055,7 @@ bnad_cb_tx_stall(struct bnad *bnad, struct bna_tx *tx)
 static void
 bnad_cb_tx_resume(struct bnad *bnad, struct bna_tx *tx)
 {
-	struct bnad_tx_info *tx_info = (struct bnad_tx_info *)tx->priv;
+	struct bnad_tx_info *tx_info = tx->priv;
 	struct bna_tcb *tcb;
 	u32 txq_id;
 	int i;
@@ -1133,7 +1132,7 @@ bnad_tx_cleanup(struct delayed_work *work)
 static void
 bnad_cb_tx_cleanup(struct bnad *bnad, struct bna_tx *tx)
 {
-	struct bnad_tx_info *tx_info = (struct bnad_tx_info *)tx->priv;
+	struct bnad_tx_info *tx_info = tx->priv;
 	struct bna_tcb *tcb;
 	int i;
 
@@ -1149,7 +1148,7 @@ bnad_cb_tx_cleanup(struct bnad *bnad, struct bna_tx *tx)
 static void
 bnad_cb_rx_stall(struct bnad *bnad, struct bna_rx *rx)
 {
-	struct bnad_rx_info *rx_info = (struct bnad_rx_info *)rx->priv;
+	struct bnad_rx_info *rx_info = rx->priv;
 	struct bna_ccb *ccb;
 	struct bnad_rx_ctrl *rx_ctrl;
 	int i;
@@ -1208,7 +1207,7 @@ bnad_rx_cleanup(void *work)
 static void
 bnad_cb_rx_cleanup(struct bnad *bnad, struct bna_rx *rx)
 {
-	struct bnad_rx_info *rx_info = (struct bnad_rx_info *)rx->priv;
+	struct bnad_rx_info *rx_info = rx->priv;
 	struct bna_ccb *ccb;
 	struct bnad_rx_ctrl *rx_ctrl;
 	int i;
@@ -1231,7 +1230,7 @@ bnad_cb_rx_cleanup(struct bnad *bnad, struct bna_rx *rx)
 static void
 bnad_cb_rx_post(struct bnad *bnad, struct bna_rx *rx)
 {
-	struct bnad_rx_info *rx_info = (struct bnad_rx_info *)rx->priv;
+	struct bnad_rx_info *rx_info = rx->priv;
 	struct bna_ccb *ccb;
 	struct bna_rcb *rcb;
 	struct bnad_rx_ctrl *rx_ctrl;
-- 
GitLab


From 62bd0232d7456d074b7923be21aca18f96f11f7b Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Wed, 12 Jul 2023 14:20:45 +0200
Subject: [PATCH 0199/1806] dt-bindings: can: xilinx_can: Add reset description

IP core has input for reset signal which can be connected that's why
describe optional reset property.

Signed-off-by: Michal Simek <michal.simek@amd.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/all/bfaed896cc51af02fe5f290675313ab4dcab0d33.1689164442.git.michal.simek@amd.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/devicetree/bindings/net/can/xilinx,can.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/can/xilinx,can.yaml b/Documentation/devicetree/bindings/net/can/xilinx,can.yaml
index 897d2cbda45b1..64d57c343e6f0 100644
--- a/Documentation/devicetree/bindings/net/can/xilinx,can.yaml
+++ b/Documentation/devicetree/bindings/net/can/xilinx,can.yaml
@@ -46,6 +46,9 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     description: CAN Tx mailbox buffer count (CAN FD)
 
+  resets:
+    maxItems: 1
+
 required:
   - compatible
   - reg
-- 
GitLab


From 25000fc785b4cf034466ff547eabf2adcf1845bc Mon Sep 17 00:00:00 2001
From: Srinivas Neeli <srinivas.neeli@amd.com>
Date: Wed, 12 Jul 2023 14:20:46 +0200
Subject: [PATCH 0200/1806] can: xilinx_can: Add support for controller reset

Add support for an optional reset for the CAN controller using the reset
driver. If the CAN node contains the "resets" property, then this logic
will perform CAN controller reset.

Signed-off-by: Srinivas Neeli <srinivas.neeli@amd.com>
Signed-off-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/all/ab7e6503aa3343e39ead03c1797e765be6c50de2.1689164442.git.michal.simek@amd.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/xilinx_can.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 4d3283db3a131..abe58f1030433 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -30,6 +30,7 @@
 #include <linux/can/error.h>
 #include <linux/phy/phy.h>
 #include <linux/pm_runtime.h>
+#include <linux/reset.h>
 
 #define DRIVER_NAME	"xilinx_can"
 
@@ -200,6 +201,7 @@ struct xcan_devtype_data {
  * @can_clk:			Pointer to struct clk
  * @devtype:			Device type specific constants
  * @transceiver:		Optional pointer to associated CAN transceiver
+ * @rstc:			Pointer to reset control
  */
 struct xcan_priv {
 	struct can_priv can;
@@ -218,6 +220,7 @@ struct xcan_priv {
 	struct clk *can_clk;
 	struct xcan_devtype_data devtype;
 	struct phy *transceiver;
+	struct reset_control *rstc;
 };
 
 /* CAN Bittiming constants as per Xilinx CAN specs */
@@ -1799,6 +1802,16 @@ static int xcan_probe(struct platform_device *pdev)
 	priv->can.do_get_berr_counter = xcan_get_berr_counter;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 					CAN_CTRLMODE_BERR_REPORTING;
+	priv->rstc = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL);
+	if (IS_ERR(priv->rstc)) {
+		dev_err(&pdev->dev, "Cannot get CAN reset.\n");
+		ret = PTR_ERR(priv->rstc);
+		goto err_free;
+	}
+
+	ret = reset_control_reset(priv->rstc);
+	if (ret)
+		goto err_free;
 
 	if (devtype->cantype == XAXI_CANFD) {
 		priv->can.data_bittiming_const =
@@ -1827,7 +1840,7 @@ static int xcan_probe(struct platform_device *pdev)
 	/* Get IRQ for the device */
 	ret = platform_get_irq(pdev, 0);
 	if (ret < 0)
-		goto err_free;
+		goto err_reset;
 
 	ndev->irq = ret;
 
@@ -1843,21 +1856,21 @@ static int xcan_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->can_clk)) {
 		ret = dev_err_probe(&pdev->dev, PTR_ERR(priv->can_clk),
 				    "device clock not found\n");
-		goto err_free;
+		goto err_reset;
 	}
 
 	priv->bus_clk = devm_clk_get(&pdev->dev, devtype->bus_clk_name);
 	if (IS_ERR(priv->bus_clk)) {
 		ret = dev_err_probe(&pdev->dev, PTR_ERR(priv->bus_clk),
 				    "bus clock not found\n");
-		goto err_free;
+		goto err_reset;
 	}
 
 	transceiver = devm_phy_optional_get(&pdev->dev, NULL);
 	if (IS_ERR(transceiver)) {
 		ret = PTR_ERR(transceiver);
 		dev_err_probe(&pdev->dev, ret, "failed to get phy\n");
-		goto err_free;
+		goto err_reset;
 	}
 	priv->transceiver = transceiver;
 
@@ -1904,6 +1917,8 @@ static int xcan_probe(struct platform_device *pdev)
 err_disableclks:
 	pm_runtime_put(priv->dev);
 	pm_runtime_disable(&pdev->dev);
+err_reset:
+	reset_control_assert(priv->rstc);
 err_free:
 	free_candev(ndev);
 err:
@@ -1920,9 +1935,11 @@ err:
 static void xcan_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct xcan_priv *priv = netdev_priv(ndev);
 
 	unregister_candev(ndev);
 	pm_runtime_disable(&pdev->dev);
+	reset_control_assert(priv->rstc);
 	free_candev(ndev);
 }
 
-- 
GitLab


From 22d8e8d6338d17bc192559dad24d1e45be0f9795 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 14 Jul 2023 11:47:57 -0600
Subject: [PATCH 0201/1806] can: Explicitly include correct DT includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/all/20230714174757.4060748-1-robh@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/grcan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index 3174efdae271a..6d3ba71a6a733 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -30,8 +30,9 @@
 #include <linux/ethtool.h>
 #include <linux/io.h>
 #include <linux/can/dev.h>
+#include <linux/platform_device.h>
 #include <linux/spinlock.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
 
 #include <linux/dma-mapping.h>
-- 
GitLab


From c2ad812956aeb3068f4e24cacdbe9d0847de2bc5 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Thu, 22 Jun 2023 17:11:52 +0200
Subject: [PATCH 0202/1806] can: kvaser_pciefd: Move hardware specific
 constants and functions into a driver_data struct

Move hardware specific address offsets, interrupt masks and DMA mapping
function, into struct kvaser_pciefd_driver_data, as a step towards adding
new devices based on different hardware.

Co-developed-by: Martin Jocic <majoc@kvaser.com>
Signed-off-by: Martin Jocic <majoc@kvaser.com>
Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Link: https://lore.kernel.org/all/20230622151153.294844-2-extja@kvaser.com
[mkl: mark structs as static]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/kvaser_pciefd.c | 230 +++++++++++++++++++++-----------
 1 file changed, 154 insertions(+), 76 deletions(-)

diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index db6256f2b1b36..3d478e6fb73b9 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -33,37 +33,17 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices");
 #define KVASER_PCIEFD_DMA_SIZE (4U * 1024U)
 
 #define KVASER_PCIEFD_VENDOR 0x1a07
+/* Altera based devices */
 #define KVASER_PCIEFD_4HS_DEVICE_ID 0x000d
 #define KVASER_PCIEFD_2HS_V2_DEVICE_ID 0x000e
 #define KVASER_PCIEFD_HS_V2_DEVICE_ID 0x000f
 #define KVASER_PCIEFD_MINIPCIE_HS_V2_DEVICE_ID 0x0010
 #define KVASER_PCIEFD_MINIPCIE_2HS_V2_DEVICE_ID 0x0011
 
-/* PCIe IRQ registers */
-#define KVASER_PCIEFD_IRQ_REG 0x40
-#define KVASER_PCIEFD_IEN_REG 0x50
-/* DMA address translation map register base */
-#define KVASER_PCIEFD_DMA_MAP_BASE 0x1000
-/* Loopback control register */
-#define KVASER_PCIEFD_LOOP_REG 0x1f000
-/* System identification and information registers */
-#define KVASER_PCIEFD_SYSID_BASE 0x1f020
-#define KVASER_PCIEFD_SYSID_VERSION_REG (KVASER_PCIEFD_SYSID_BASE + 0x8)
-#define KVASER_PCIEFD_SYSID_CANFREQ_REG (KVASER_PCIEFD_SYSID_BASE + 0xc)
-#define KVASER_PCIEFD_SYSID_BUSFREQ_REG (KVASER_PCIEFD_SYSID_BASE + 0x10)
-#define KVASER_PCIEFD_SYSID_BUILD_REG (KVASER_PCIEFD_SYSID_BASE + 0x14)
-/* Shared receive buffer registers */
-#define KVASER_PCIEFD_SRB_BASE 0x1f200
-#define KVASER_PCIEFD_SRB_FIFO_LAST_REG (KVASER_PCIEFD_SRB_BASE + 0x1f4)
-#define KVASER_PCIEFD_SRB_CMD_REG (KVASER_PCIEFD_SRB_BASE + 0x200)
-#define KVASER_PCIEFD_SRB_IEN_REG (KVASER_PCIEFD_SRB_BASE + 0x204)
-#define KVASER_PCIEFD_SRB_IRQ_REG (KVASER_PCIEFD_SRB_BASE + 0x20c)
-#define KVASER_PCIEFD_SRB_STAT_REG (KVASER_PCIEFD_SRB_BASE + 0x210)
-#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG (KVASER_PCIEFD_SRB_BASE + 0x214)
-#define KVASER_PCIEFD_SRB_CTRL_REG (KVASER_PCIEFD_SRB_BASE + 0x218)
+/* Altera SerDes Enable 64-bit DMA address translation */
+#define KVASER_PCIEFD_ALTERA_DMA_64BIT BIT(0)
+
 /* Kvaser KCAN CAN controller registers */
-#define KVASER_PCIEFD_KCAN0_BASE 0x10000
-#define KVASER_PCIEFD_KCAN_BASE_OFFSET 0x1000
 #define KVASER_PCIEFD_KCAN_FIFO_REG 0x100
 #define KVASER_PCIEFD_KCAN_FIFO_LAST_REG 0x180
 #define KVASER_PCIEFD_KCAN_CTRL_REG 0x2c0
@@ -77,13 +57,20 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices");
 #define KVASER_PCIEFD_KCAN_BUS_LOAD_REG 0x424
 #define KVASER_PCIEFD_KCAN_BTRD_REG 0x428
 #define KVASER_PCIEFD_KCAN_PWM_REG 0x430
-
-/* PCI interrupt fields */
-#define KVASER_PCIEFD_IRQ_SRB BIT(4)
-#define KVASER_PCIEFD_IRQ_ALL_MASK GENMASK(4, 0)
-
-/* Enable 64-bit DMA address translation */
-#define KVASER_PCIEFD_64BIT_DMA_BIT BIT(0)
+/* System identification and information registers */
+#define KVASER_PCIEFD_SYSID_VERSION_REG 0x8
+#define KVASER_PCIEFD_SYSID_CANFREQ_REG 0xc
+#define KVASER_PCIEFD_SYSID_BUSFREQ_REG 0x10
+#define KVASER_PCIEFD_SYSID_BUILD_REG 0x14
+/* Shared receive buffer FIFO registers */
+#define KVASER_PCIEFD_SRB_FIFO_LAST_REG 0x1f4
+/* Shared receive buffer registers */
+#define KVASER_PCIEFD_SRB_CMD_REG 0x0
+#define KVASER_PCIEFD_SRB_IEN_REG 0x04
+#define KVASER_PCIEFD_SRB_IRQ_REG 0x0c
+#define KVASER_PCIEFD_SRB_STAT_REG 0x10
+#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG 0x14
+#define KVASER_PCIEFD_SRB_CTRL_REG 0x18
 
 /* System build information fields */
 #define KVASER_PCIEFD_SYSID_VERSION_NR_CHAN_MASK GENMASK(31, 24)
@@ -253,7 +240,92 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices");
 /* KCAN Error detected packet, second word */
 #define KVASER_PCIEFD_EPACK_DIR_TX BIT(0)
 
+/* Macros for calculating addresses of registers */
+#define KVASER_PCIEFD_GET_BLOCK_ADDR(pcie, block) \
+	((pcie)->reg_base + (pcie)->driver_data->address_offset->block)
+#define KVASER_PCIEFD_PCI_IEN_ADDR(pcie) \
+	(KVASER_PCIEFD_GET_BLOCK_ADDR((pcie), pci_ien))
+#define KVASER_PCIEFD_PCI_IRQ_ADDR(pcie) \
+	(KVASER_PCIEFD_GET_BLOCK_ADDR((pcie), pci_irq))
+#define KVASER_PCIEFD_SERDES_ADDR(pcie) \
+	(KVASER_PCIEFD_GET_BLOCK_ADDR((pcie), serdes))
+#define KVASER_PCIEFD_SYSID_ADDR(pcie) \
+	(KVASER_PCIEFD_GET_BLOCK_ADDR((pcie), sysid))
+#define KVASER_PCIEFD_LOOPBACK_ADDR(pcie) \
+	(KVASER_PCIEFD_GET_BLOCK_ADDR((pcie), loopback))
+#define KVASER_PCIEFD_SRB_FIFO_ADDR(pcie) \
+	(KVASER_PCIEFD_GET_BLOCK_ADDR((pcie), kcan_srb_fifo))
+#define KVASER_PCIEFD_SRB_ADDR(pcie) \
+	(KVASER_PCIEFD_GET_BLOCK_ADDR((pcie), kcan_srb))
+#define KVASER_PCIEFD_KCAN_CH0_ADDR(pcie) \
+	(KVASER_PCIEFD_GET_BLOCK_ADDR((pcie), kcan_ch0))
+#define KVASER_PCIEFD_KCAN_CH1_ADDR(pcie) \
+	(KVASER_PCIEFD_GET_BLOCK_ADDR((pcie), kcan_ch1))
+#define KVASER_PCIEFD_KCAN_CHANNEL_SPAN(pcie) \
+	(KVASER_PCIEFD_KCAN_CH1_ADDR((pcie)) - KVASER_PCIEFD_KCAN_CH0_ADDR((pcie)))
+#define KVASER_PCIEFD_KCAN_CHX_ADDR(pcie, i) \
+	(KVASER_PCIEFD_KCAN_CH0_ADDR((pcie)) + (i) * KVASER_PCIEFD_KCAN_CHANNEL_SPAN((pcie)))
+
 struct kvaser_pciefd;
+static void kvaser_pciefd_write_dma_map_altera(struct kvaser_pciefd *pcie,
+					       dma_addr_t addr, int index);
+
+struct kvaser_pciefd_address_offset {
+	u32 serdes;
+	u32 pci_ien;
+	u32 pci_irq;
+	u32 sysid;
+	u32 loopback;
+	u32 kcan_srb_fifo;
+	u32 kcan_srb;
+	u32 kcan_ch0;
+	u32 kcan_ch1;
+};
+
+struct kvaser_pciefd_dev_ops {
+	void (*kvaser_pciefd_write_dma_map)(struct kvaser_pciefd *pcie,
+					    dma_addr_t addr, int index);
+};
+
+struct kvaser_pciefd_irq_mask {
+	u32 kcan_rx0;
+	u32 kcan_tx[KVASER_PCIEFD_MAX_CAN_CHANNELS];
+	u32 all;
+};
+
+struct kvaser_pciefd_driver_data {
+	const struct kvaser_pciefd_address_offset *address_offset;
+	const struct kvaser_pciefd_irq_mask *irq_mask;
+	const struct kvaser_pciefd_dev_ops *ops;
+};
+
+static const struct kvaser_pciefd_address_offset kvaser_pciefd_altera_address_offset = {
+	.serdes = 0x1000,
+	.pci_ien = 0x50,
+	.pci_irq = 0x40,
+	.sysid = 0x1f020,
+	.loopback = 0x1f000,
+	.kcan_srb_fifo = 0x1f200,
+	.kcan_srb = 0x1f400,
+	.kcan_ch0 = 0x10000,
+	.kcan_ch1 = 0x11000,
+};
+
+static const struct kvaser_pciefd_irq_mask kvaser_pciefd_altera_irq_mask = {
+	.kcan_rx0 = BIT(4),
+	.kcan_tx = { BIT(0), BIT(1), BIT(2), BIT(3) },
+	.all = GENMASK(4, 0),
+};
+
+static const struct kvaser_pciefd_dev_ops kvaser_pciefd_altera_dev_ops = {
+	.kvaser_pciefd_write_dma_map = kvaser_pciefd_write_dma_map_altera,
+};
+
+static const struct kvaser_pciefd_driver_data kvaser_pciefd_altera_driver_data = {
+	.address_offset = &kvaser_pciefd_altera_address_offset,
+	.irq_mask = &kvaser_pciefd_altera_irq_mask,
+	.ops = &kvaser_pciefd_altera_dev_ops,
+};
 
 struct kvaser_pciefd_can {
 	struct can_priv can;
@@ -273,6 +345,7 @@ struct kvaser_pciefd {
 	struct pci_dev *pci;
 	void __iomem *reg_base;
 	struct kvaser_pciefd_can *can[KVASER_PCIEFD_MAX_CAN_CHANNELS];
+	const struct kvaser_pciefd_driver_data *driver_data;
 	void *dma_data[KVASER_PCIEFD_DMA_COUNT];
 	u8 nr_channels;
 	u32 bus_freq;
@@ -305,18 +378,23 @@ static const struct can_bittiming_const kvaser_pciefd_bittiming_const = {
 static struct pci_device_id kvaser_pciefd_id_table[] = {
 	{
 		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_4HS_DEVICE_ID),
+		.driver_data = (kernel_ulong_t)&kvaser_pciefd_altera_driver_data,
 	},
 	{
 		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_2HS_V2_DEVICE_ID),
+		.driver_data = (kernel_ulong_t)&kvaser_pciefd_altera_driver_data,
 	},
 	{
 		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_HS_V2_DEVICE_ID),
+		.driver_data = (kernel_ulong_t)&kvaser_pciefd_altera_driver_data,
 	},
 	{
 		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_MINIPCIE_HS_V2_DEVICE_ID),
+		.driver_data = (kernel_ulong_t)&kvaser_pciefd_altera_driver_data,
 	},
 	{
 		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_MINIPCIE_2HS_V2_DEVICE_ID),
+		.driver_data = (kernel_ulong_t)&kvaser_pciefd_altera_driver_data,
 	},
 	{
 		0,
@@ -783,8 +861,7 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		can = netdev_priv(netdev);
 		netdev->netdev_ops = &kvaser_pciefd_netdev_ops;
 		netdev->ethtool_ops = &kvaser_pciefd_ethtool_ops;
-		can->reg_base = pcie->reg_base + KVASER_PCIEFD_KCAN0_BASE +
-				i * KVASER_PCIEFD_KCAN_BASE_OFFSET;
+		can->reg_base = KVASER_PCIEFD_KCAN_CHX_ADDR(pcie, i);
 		can->kv_pcie = pcie;
 		can->cmd_seq = 0;
 		can->err_rep_cnt = 0;
@@ -865,20 +942,22 @@ static int kvaser_pciefd_reg_candev(struct kvaser_pciefd *pcie)
 	return 0;
 }
 
-static void kvaser_pciefd_write_dma_map(struct kvaser_pciefd *pcie,
-					dma_addr_t addr, int offset)
+static void kvaser_pciefd_write_dma_map_altera(struct kvaser_pciefd *pcie,
+					       dma_addr_t addr, int index)
 {
+	void __iomem *serdes_base;
 	u32 word1, word2;
 
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	word1 = addr | KVASER_PCIEFD_64BIT_DMA_BIT;
+	word1 = addr | KVASER_PCIEFD_ALTERA_DMA_64BIT;
 	word2 = addr >> 32;
 #else
 	word1 = addr;
 	word2 = 0;
 #endif
-	iowrite32(word1, pcie->reg_base + offset);
-	iowrite32(word2, pcie->reg_base + offset + 4);
+	serdes_base = KVASER_PCIEFD_SERDES_ADDR(pcie) + 0x8 * index;
+	iowrite32(word1, serdes_base);
+	iowrite32(word2, serdes_base + 0x4);
 }
 
 static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie)
@@ -889,10 +968,8 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie)
 	dma_addr_t dma_addr[KVASER_PCIEFD_DMA_COUNT];
 
 	/* Disable the DMA */
-	iowrite32(0, pcie->reg_base + KVASER_PCIEFD_SRB_CTRL_REG);
+	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG);
 	for (i = 0; i < KVASER_PCIEFD_DMA_COUNT; i++) {
-		unsigned int offset = KVASER_PCIEFD_DMA_MAP_BASE + 8 * i;
-
 		pcie->dma_data[i] = dmam_alloc_coherent(&pcie->pci->dev,
 							KVASER_PCIEFD_DMA_SIZE,
 							&dma_addr[i],
@@ -903,24 +980,25 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie)
 				KVASER_PCIEFD_DMA_SIZE);
 			return -ENOMEM;
 		}
-		kvaser_pciefd_write_dma_map(pcie, dma_addr[i], offset);
+		pcie->driver_data->ops->kvaser_pciefd_write_dma_map(pcie, dma_addr[i], i);
 	}
 
 	/* Reset Rx FIFO, and both DMA buffers */
 	iowrite32(KVASER_PCIEFD_SRB_CMD_FOR | KVASER_PCIEFD_SRB_CMD_RDB0 |
 		  KVASER_PCIEFD_SRB_CMD_RDB1,
-		  pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG);
+		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
 	/* Empty Rx FIFO */
 	srb_packet_count =
 		FIELD_GET(KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK,
-			  ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG));
+			  ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) +
+				   KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG));
 	while (srb_packet_count) {
 		/* Drop current packet in FIFO */
-		ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_FIFO_LAST_REG);
+		ioread32(KVASER_PCIEFD_SRB_FIFO_ADDR(pcie) + KVASER_PCIEFD_SRB_FIFO_LAST_REG);
 		srb_packet_count--;
 	}
 
-	srb_status = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_STAT_REG);
+	srb_status = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_STAT_REG);
 	if (!(srb_status & KVASER_PCIEFD_SRB_STAT_DI)) {
 		dev_err(&pcie->pci->dev, "DMA not idle before enabling\n");
 		return -EIO;
@@ -928,7 +1006,7 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie)
 
 	/* Enable the DMA */
 	iowrite32(KVASER_PCIEFD_SRB_CTRL_DMA_ENABLE,
-		  pcie->reg_base + KVASER_PCIEFD_SRB_CTRL_REG);
+		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG);
 
 	return 0;
 }
@@ -937,30 +1015,29 @@ static int kvaser_pciefd_setup_board(struct kvaser_pciefd *pcie)
 {
 	u32 version, srb_status, build;
 
-	version = ioread32(pcie->reg_base + KVASER_PCIEFD_SYSID_VERSION_REG);
+	version = ioread32(KVASER_PCIEFD_SYSID_ADDR(pcie) + KVASER_PCIEFD_SYSID_VERSION_REG);
 	pcie->nr_channels = min(KVASER_PCIEFD_MAX_CAN_CHANNELS,
 				FIELD_GET(KVASER_PCIEFD_SYSID_VERSION_NR_CHAN_MASK, version));
 
-	build = ioread32(pcie->reg_base + KVASER_PCIEFD_SYSID_BUILD_REG);
+	build = ioread32(KVASER_PCIEFD_SYSID_ADDR(pcie) + KVASER_PCIEFD_SYSID_BUILD_REG);
 	dev_dbg(&pcie->pci->dev, "Version %lu.%lu.%lu\n",
 		FIELD_GET(KVASER_PCIEFD_SYSID_VERSION_MAJOR_MASK, version),
 		FIELD_GET(KVASER_PCIEFD_SYSID_VERSION_MINOR_MASK, version),
 		FIELD_GET(KVASER_PCIEFD_SYSID_BUILD_SEQ_MASK, build));
 
-	srb_status = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_STAT_REG);
+	srb_status = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_STAT_REG);
 	if (!(srb_status & KVASER_PCIEFD_SRB_STAT_DMA)) {
 		dev_err(&pcie->pci->dev, "Hardware without DMA is not supported\n");
 		return -ENODEV;
 	}
 
-	pcie->bus_freq = ioread32(pcie->reg_base +
-				  KVASER_PCIEFD_SYSID_BUSFREQ_REG);
-	pcie->freq = ioread32(pcie->reg_base + KVASER_PCIEFD_SYSID_CANFREQ_REG);
+	pcie->bus_freq = ioread32(KVASER_PCIEFD_SYSID_ADDR(pcie) + KVASER_PCIEFD_SYSID_BUSFREQ_REG);
+	pcie->freq = ioread32(KVASER_PCIEFD_SYSID_ADDR(pcie) + KVASER_PCIEFD_SYSID_CANFREQ_REG);
 	pcie->freq_to_ticks_div = pcie->freq / 1000000;
 	if (pcie->freq_to_ticks_div == 0)
 		pcie->freq_to_ticks_div = 1;
 	/* Turn off all loopback functionality */
-	iowrite32(0, pcie->reg_base + KVASER_PCIEFD_LOOP_REG);
+	iowrite32(0, KVASER_PCIEFD_LOOPBACK_ADDR(pcie));
 
 	return 0;
 }
@@ -1430,21 +1507,20 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf)
 
 static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
 {
-	u32 irq;
+	u32 irq = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
 
-	irq = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG);
 	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) {
 		kvaser_pciefd_read_buffer(pcie, 0);
 		/* Reset DMA buffer 0 */
 		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0,
-			  pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG);
+			  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
 	}
 
 	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) {
 		kvaser_pciefd_read_buffer(pcie, 1);
 		/* Reset DMA buffer 1 */
 		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1,
-			  pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG);
+			  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
 	}
 
 	if (irq & KVASER_PCIEFD_SRB_IRQ_DOF0 ||
@@ -1453,7 +1529,7 @@ static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
 	    irq & KVASER_PCIEFD_SRB_IRQ_DUF1)
 		dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq);
 
-	iowrite32(irq, pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG);
+	iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
 }
 
 static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can)
@@ -1479,15 +1555,14 @@ static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can)
 static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev)
 {
 	struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev;
-	u32 board_irq;
+	const struct kvaser_pciefd_irq_mask *irq_mask = pcie->driver_data->irq_mask;
+	u32 board_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie));
 	int i;
 
-	board_irq = ioread32(pcie->reg_base + KVASER_PCIEFD_IRQ_REG);
-
-	if (!(board_irq & KVASER_PCIEFD_IRQ_ALL_MASK))
+	if (!(board_irq & irq_mask->all))
 		return IRQ_NONE;
 
-	if (board_irq & KVASER_PCIEFD_IRQ_SRB)
+	if (board_irq & irq_mask->kcan_rx0)
 		kvaser_pciefd_receive_irq(pcie);
 
 	for (i = 0; i < pcie->nr_channels; i++) {
@@ -1498,7 +1573,7 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev)
 		}
 
 		/* Check that mask matches channel (i) IRQ mask */
-		if (board_irq & (1 << i))
+		if (board_irq & irq_mask->kcan_tx[i])
 			kvaser_pciefd_transmit_irq(pcie->can[i]);
 	}
 
@@ -1525,6 +1600,8 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 {
 	int err;
 	struct kvaser_pciefd *pcie;
+	const struct kvaser_pciefd_irq_mask *irq_mask;
+	void __iomem *irq_en_base;
 
 	pcie = devm_kzalloc(&pdev->dev, sizeof(*pcie), GFP_KERNEL);
 	if (!pcie)
@@ -1532,6 +1609,8 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 
 	pci_set_drvdata(pdev, pcie);
 	pcie->pci = pdev;
+	pcie->driver_data = (const struct kvaser_pciefd_driver_data *)id->driver_data;
+	irq_mask = pcie->driver_data->irq_mask;
 
 	err = pci_enable_device(pdev);
 	if (err)
@@ -1567,22 +1646,21 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 		goto err_teardown_can_ctrls;
 
 	iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1,
-		  pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG);
+		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
 
 	iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1 |
 		  KVASER_PCIEFD_SRB_IRQ_DOF0 | KVASER_PCIEFD_SRB_IRQ_DOF1 |
 		  KVASER_PCIEFD_SRB_IRQ_DUF0 | KVASER_PCIEFD_SRB_IRQ_DUF1,
-		  pcie->reg_base + KVASER_PCIEFD_SRB_IEN_REG);
+		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
 
 	/* Enable PCI interrupts */
-	iowrite32(KVASER_PCIEFD_IRQ_ALL_MASK,
-		  pcie->reg_base + KVASER_PCIEFD_IEN_REG);
-
+	irq_en_base = KVASER_PCIEFD_PCI_IEN_ADDR(pcie);
+	iowrite32(irq_mask->all, irq_en_base);
 	/* Ready the DMA buffers */
 	iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0,
-		  pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG);
+		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
 	iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1,
-		  pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG);
+		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
 
 	err = kvaser_pciefd_reg_candev(pcie);
 	if (err)
@@ -1592,12 +1670,12 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 
 err_free_irq:
 	/* Disable PCI interrupts */
-	iowrite32(0, pcie->reg_base + KVASER_PCIEFD_IEN_REG);
+	iowrite32(0, irq_en_base);
 	free_irq(pcie->pci->irq, pcie);
 
 err_teardown_can_ctrls:
 	kvaser_pciefd_teardown_can_ctrls(pcie);
-	iowrite32(0, pcie->reg_base + KVASER_PCIEFD_SRB_CTRL_REG);
+	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG);
 	pci_clear_master(pdev);
 
 err_pci_iounmap:
@@ -1636,8 +1714,8 @@ static void kvaser_pciefd_remove(struct pci_dev *pdev)
 	kvaser_pciefd_remove_all_ctrls(pcie);
 
 	/* Disable interrupts */
-	iowrite32(0, pcie->reg_base + KVASER_PCIEFD_SRB_CTRL_REG);
-	iowrite32(0, pcie->reg_base + KVASER_PCIEFD_IEN_REG);
+	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG);
+	iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
 
 	free_irq(pcie->pci->irq, pcie);
 
-- 
GitLab


From f33ad6776b2fb8005c954fa1f8b88125260c190f Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Thu, 22 Jun 2023 17:11:53 +0200
Subject: [PATCH 0203/1806] can: kvaser_pciefd: Add support for new Kvaser
 pciefd devices

Add support for new Kvaser pciefd devices, based on SmartFusion2 SoC.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Link: https://lore.kernel.org/all/20230622151153.294844-3-extja@kvaser.com
[mkl: mark structs as static]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/Kconfig         |  5 +++
 drivers/net/can/kvaser_pciefd.c | 77 ++++++++++++++++++++++++++++++++-
 2 files changed, 81 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index a5c5036dfb943..18e4a6e94ba93 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -160,8 +160,13 @@ config CAN_KVASER_PCIEFD
 	    Kvaser PCIEcan 4xHS
 	    Kvaser PCIEcan 2xHS v2
 	    Kvaser PCIEcan HS v2
+	    Kvaser PCIEcan 1xCAN v3
+	    Kvaser PCIEcan 2xCAN v3
+	    Kvaser PCIEcan 4xCAN v2
 	    Kvaser Mini PCI Express HS v2
 	    Kvaser Mini PCI Express 2xHS v2
+	    Kvaser Mini PCI Express 1xCAN v3
+	    Kvaser Mini PCI Express 2xCAN v3
 
 config CAN_SLCAN
 	tristate "Serial / USB serial CAN Adaptors (slcan)"
diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index 3d478e6fb73b9..a57005faa04f5 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
 /* Copyright (C) 2018 KVASER AB, Sweden. All rights reserved.
  * Parts of this driver are based on the following:
- *  - Kvaser linux pciefd driver (version 5.25)
+ *  - Kvaser linux pciefd driver (version 5.42)
  *  - PEAK linux canfd driver
  */
 
@@ -40,9 +40,19 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices");
 #define KVASER_PCIEFD_MINIPCIE_HS_V2_DEVICE_ID 0x0010
 #define KVASER_PCIEFD_MINIPCIE_2HS_V2_DEVICE_ID 0x0011
 
+/* SmartFusion2 based devices */
+#define KVASER_PCIEFD_2CAN_V3_DEVICE_ID 0x0012
+#define KVASER_PCIEFD_1CAN_V3_DEVICE_ID 0x0013
+#define KVASER_PCIEFD_4CAN_V2_DEVICE_ID 0x0014
+#define KVASER_PCIEFD_MINIPCIE_2CAN_V3_DEVICE_ID 0x0015
+#define KVASER_PCIEFD_MINIPCIE_1CAN_V3_DEVICE_ID 0x0016
+
 /* Altera SerDes Enable 64-bit DMA address translation */
 #define KVASER_PCIEFD_ALTERA_DMA_64BIT BIT(0)
 
+/* SmartFusion2 SerDes LSB address translation mask */
+#define KVASER_PCIEFD_SF2_DMA_LSB_MASK GENMASK(31, 12)
+
 /* Kvaser KCAN CAN controller registers */
 #define KVASER_PCIEFD_KCAN_FIFO_REG 0x100
 #define KVASER_PCIEFD_KCAN_FIFO_LAST_REG 0x180
@@ -269,6 +279,8 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices");
 struct kvaser_pciefd;
 static void kvaser_pciefd_write_dma_map_altera(struct kvaser_pciefd *pcie,
 					       dma_addr_t addr, int index);
+static void kvaser_pciefd_write_dma_map_sf2(struct kvaser_pciefd *pcie,
+					    dma_addr_t addr, int index);
 
 struct kvaser_pciefd_address_offset {
 	u32 serdes;
@@ -311,22 +323,50 @@ static const struct kvaser_pciefd_address_offset kvaser_pciefd_altera_address_of
 	.kcan_ch1 = 0x11000,
 };
 
+static const struct kvaser_pciefd_address_offset kvaser_pciefd_sf2_address_offset = {
+	.serdes = 0x280c8,
+	.pci_ien = 0x102004,
+	.pci_irq = 0x102008,
+	.sysid = 0x100000,
+	.loopback = 0x103000,
+	.kcan_srb_fifo = 0x120000,
+	.kcan_srb = 0x121000,
+	.kcan_ch0 = 0x140000,
+	.kcan_ch1 = 0x142000,
+};
+
 static const struct kvaser_pciefd_irq_mask kvaser_pciefd_altera_irq_mask = {
 	.kcan_rx0 = BIT(4),
 	.kcan_tx = { BIT(0), BIT(1), BIT(2), BIT(3) },
 	.all = GENMASK(4, 0),
 };
 
+static const struct kvaser_pciefd_irq_mask kvaser_pciefd_sf2_irq_mask = {
+	.kcan_rx0 = BIT(4),
+	.kcan_tx = { BIT(16), BIT(17), BIT(18), BIT(19) },
+	.all = GENMASK(19, 16) | BIT(4),
+};
+
 static const struct kvaser_pciefd_dev_ops kvaser_pciefd_altera_dev_ops = {
 	.kvaser_pciefd_write_dma_map = kvaser_pciefd_write_dma_map_altera,
 };
 
+static const struct kvaser_pciefd_dev_ops kvaser_pciefd_sf2_dev_ops = {
+	.kvaser_pciefd_write_dma_map = kvaser_pciefd_write_dma_map_sf2,
+};
+
 static const struct kvaser_pciefd_driver_data kvaser_pciefd_altera_driver_data = {
 	.address_offset = &kvaser_pciefd_altera_address_offset,
 	.irq_mask = &kvaser_pciefd_altera_irq_mask,
 	.ops = &kvaser_pciefd_altera_dev_ops,
 };
 
+static const struct kvaser_pciefd_driver_data kvaser_pciefd_sf2_driver_data = {
+	.address_offset = &kvaser_pciefd_sf2_address_offset,
+	.irq_mask = &kvaser_pciefd_sf2_irq_mask,
+	.ops = &kvaser_pciefd_sf2_dev_ops,
+};
+
 struct kvaser_pciefd_can {
 	struct can_priv can;
 	struct kvaser_pciefd *kv_pcie;
@@ -396,6 +436,26 @@ static struct pci_device_id kvaser_pciefd_id_table[] = {
 		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_MINIPCIE_2HS_V2_DEVICE_ID),
 		.driver_data = (kernel_ulong_t)&kvaser_pciefd_altera_driver_data,
 	},
+	{
+		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_2CAN_V3_DEVICE_ID),
+		.driver_data = (kernel_ulong_t)&kvaser_pciefd_sf2_driver_data,
+	},
+	{
+		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_1CAN_V3_DEVICE_ID),
+		.driver_data = (kernel_ulong_t)&kvaser_pciefd_sf2_driver_data,
+	},
+	{
+		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_4CAN_V2_DEVICE_ID),
+		.driver_data = (kernel_ulong_t)&kvaser_pciefd_sf2_driver_data,
+	},
+	{
+		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_MINIPCIE_2CAN_V3_DEVICE_ID),
+		.driver_data = (kernel_ulong_t)&kvaser_pciefd_sf2_driver_data,
+	},
+	{
+		PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_MINIPCIE_1CAN_V3_DEVICE_ID),
+		.driver_data = (kernel_ulong_t)&kvaser_pciefd_sf2_driver_data,
+	},
 	{
 		0,
 	},
@@ -960,6 +1020,21 @@ static void kvaser_pciefd_write_dma_map_altera(struct kvaser_pciefd *pcie,
 	iowrite32(word2, serdes_base + 0x4);
 }
 
+static void kvaser_pciefd_write_dma_map_sf2(struct kvaser_pciefd *pcie,
+					    dma_addr_t addr, int index)
+{
+	void __iomem *serdes_base;
+	u32 lsb = addr & KVASER_PCIEFD_SF2_DMA_LSB_MASK;
+	u32 msb = 0x0;
+
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	msb = addr >> 32;
+#endif
+	serdes_base = KVASER_PCIEFD_SERDES_ADDR(pcie) + 0x10 * index;
+	iowrite32(lsb, serdes_base);
+	iowrite32(msb, serdes_base + 0x4);
+}
+
 static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie)
 {
 	int i;
-- 
GitLab


From 03df47c1bb392b795bcecb6953dcc49199d33b2a Mon Sep 17 00:00:00 2001
From: Mao Zhu <zhumao001@208suo.com>
Date: Wed, 19 Jul 2023 00:25:23 +0800
Subject: [PATCH 0204/1806] can: ucan: Remove repeated word

Delete one of repeated word 'information' in comment.

Signed-off-by: Mao Zhu <zhumao001@208suo.com>
Link: https://lore.kernel.org/all/20230718163718.461137-1-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/ucan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index a0f7bcec719c2..39a63b7313a46 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -284,7 +284,7 @@ struct ucan_priv {
 	 */
 	spinlock_t echo_skb_lock;
 
-	/* usb device information information */
+	/* usb device information */
 	u8 intf_index;
 	u8 in_ep_addr;
 	u8 out_ep_addr;
-- 
GitLab


From 8bb5e82589f0141a990d3fd21d5b79a73a8c6c7b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Jul 2023 11:12:26 +0300
Subject: [PATCH 0205/1806] ip_tunnels: Add nexthop ID field to ip_tunnel_key

Extend the ip_tunnel_key structure with a field indicating the ID of the
nexthop object via which the skb should be routed.

The field is going to be populated in subsequent patches by the bridge
driver in order to indicate to the VXLAN driver which FDB nexthop object
to use in order to reach the target host.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_tunnels.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index ed4b6ad3fcac8..e8750b4ef7e17 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -52,6 +52,7 @@ struct ip_tunnel_key {
 	u8			tos;		/* TOS for IPv4, TC for IPv6 */
 	u8			ttl;		/* TTL for IPv4, HL for IPv6 */
 	__be32			label;		/* Flow Label for IPv6 */
+	u32			nhid;
 	__be16			tp_src;
 	__be16			tp_dst;
 	__u8			flow_flags;
-- 
GitLab


From d977e1c8e3a143bceb63a0042890f4a0268a9990 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Jul 2023 11:12:27 +0300
Subject: [PATCH 0206/1806] vxlan: Add support for nexthop ID metadata

VXLAN FDB entries can point to FDB nexthop objects. Each such object
includes the IP address(es) of remote VTEP(s) via which the target host
is accessible. Example:

 # ip nexthop add id 1 via 192.0.2.1 fdb
 # ip nexthop add id 2 via 192.0.2.17 fdb
 # ip nexthop add id 1000 group 1/2 fdb
 # bridge fdb add 00:11:22:33:44:55 dev vx0 self static nhid 1000 src_vni 10020

This is useful for EVPN multihoming where a single host can be connected
to multiple VTEPs. The source VTEP will calculate the flow hash of the
skb and forward it towards the IP address of one of the VTEPs member in
the nexthop group.

There are cases where an external entity (e.g., the bridge driver) can
provide not only the tunnel ID (i.e., VNI) of the skb, but also the ID
of the nexthop object via which the skb should be forwarded.

Therefore, in order to support such cases, when the VXLAN device is in
external / collect metadata mode and the tunnel info attached to the skb
is of bridge type, extract the nexthop ID from the tunnel info. If the
ID is valid (i.e., non-zero), forward the skb via the nexthop object
associated with the ID, as if the skb hit an FDB entry associated with
this ID.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan/vxlan_core.c | 44 ++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 78744549c1b30..10a4dbd50710c 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2672,6 +2672,45 @@ drop:
 	dev_kfree_skb(skb);
 }
 
+static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev,
+				   u32 nhid, __be32 vni)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_rdst nh_rdst;
+	struct nexthop *nh;
+	bool do_xmit;
+	u32 hash;
+
+	memset(&nh_rdst, 0, sizeof(struct vxlan_rdst));
+	hash = skb_get_hash(skb);
+
+	rcu_read_lock();
+	nh = nexthop_find_by_id(dev_net(dev), nhid);
+	if (unlikely(!nh || !nexthop_is_fdb(nh) || !nexthop_is_multipath(nh))) {
+		rcu_read_unlock();
+		goto drop;
+	}
+	do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst);
+	rcu_read_unlock();
+
+	if (vxlan->cfg.saddr.sa.sa_family != nh_rdst.remote_ip.sa.sa_family)
+		goto drop;
+
+	if (likely(do_xmit))
+		vxlan_xmit_one(skb, dev, vni, &nh_rdst, false);
+	else
+		goto drop;
+
+	return NETDEV_TX_OK;
+
+drop:
+	dev->stats.tx_dropped++;
+	vxlan_vnifilter_count(netdev_priv(dev), vni, NULL,
+			      VXLAN_VNI_STATS_TX_DROPS, 0);
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
 /* Transmit local packets over Vxlan
  *
  * Outer IP header inherits ECN and DF from inner header.
@@ -2687,6 +2726,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct vxlan_fdb *f;
 	struct ethhdr *eth;
 	__be32 vni = 0;
+	u32 nhid = 0;
 
 	info = skb_tunnel_info(skb);
 
@@ -2696,6 +2736,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (info && info->mode & IP_TUNNEL_INFO_BRIDGE &&
 		    info->mode & IP_TUNNEL_INFO_TX) {
 			vni = tunnel_id_to_key32(info->key.tun_id);
+			nhid = info->key.nhid;
 		} else {
 			if (info && info->mode & IP_TUNNEL_INFO_TX)
 				vxlan_xmit_one(skb, dev, vni, NULL, false);
@@ -2723,6 +2764,9 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 #endif
 	}
 
+	if (nhid)
+		return vxlan_xmit_nhid(skb, dev, nhid, vni);
+
 	if (vxlan->cfg.flags & VXLAN_F_MDB) {
 		struct vxlan_mdb_entry *mdb_entry;
 
-- 
GitLab


From 29cfb2aaa4425a608651a05b9b875bc445394443 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Jul 2023 11:12:28 +0300
Subject: [PATCH 0207/1806] bridge: Add backup nexthop ID support

Add a new bridge port attribute that allows attaching a nexthop object
ID to an skb that is redirected to a backup bridge port with VLAN
tunneling enabled.

Specifically, when redirecting a known unicast packet, read the backup
nexthop ID from the bridge port that lost its carrier and set it in the
bridge control block of the skb before forwarding it via the backup
port. Note that reading the ID from the bridge port should not result in
a cache miss as the ID is added next to the 'backup_port' field that was
already accessed. After this change, the 'state' field still stays on
the first cache line, together with other data path related fields such
as 'flags and 'vlgrp':

struct net_bridge_port {
        struct net_bridge *        br;                   /*     0     8 */
        struct net_device *        dev;                  /*     8     8 */
        netdevice_tracker          dev_tracker;          /*    16     0 */
        struct list_head           list;                 /*    16    16 */
        long unsigned int          flags;                /*    32     8 */
        struct net_bridge_vlan_group * vlgrp;            /*    40     8 */
        struct net_bridge_port *   backup_port;          /*    48     8 */
        u32                        backup_nhid;          /*    56     4 */
        u8                         priority;             /*    60     1 */
        u8                         state;                /*    61     1 */
        u16                        port_no;              /*    62     2 */
        /* --- cacheline 1 boundary (64 bytes) --- */
[...]
} __attribute__((__aligned__(8)));

When forwarding an skb via a bridge port that has VLAN tunneling
enabled, check if the backup nexthop ID stored in the bridge control
block is valid (i.e., not zero). If so, instead of attaching the
pre-allocated metadata (that only has the tunnel key set), allocate a
new metadata, set both the tunnel key and the nexthop object ID and
attach it to the skb.

By default, do not dump the new attribute to user space as a value of
zero is an invalid nexthop object ID.

The above is useful for EVPN multihoming. When one of the links
composing an Ethernet Segment (ES) fails, traffic needs to be redirected
towards the host via one of the other ES peers. For example, if a host
is multihomed to three different VTEPs, the backup port of each ES link
needs to be set to the VXLAN device and the backup nexthop ID needs to
point to an FDB nexthop group that includes the IP addresses of the
other two VTEPs. The VXLAN driver will extract the ID from the metadata
of the redirected skb, calculate its flow hash and forward it towards
one of the other VTEPs. If the ID does not exist, or represents an
invalid nexthop object, the VXLAN driver will drop the skb. This
relieves the bridge driver from the need to validate the ID.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h |  1 +
 net/bridge/br_forward.c      |  1 +
 net/bridge/br_netlink.c      | 12 ++++++++++++
 net/bridge/br_private.h      |  3 +++
 net/bridge/br_vlan_tunnel.c  | 15 +++++++++++++++
 net/core/rtnetlink.c         |  2 +-
 6 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 0f6a0fe09bdbd..ce3117df9cec2 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -570,6 +570,7 @@ enum {
 	IFLA_BRPORT_MCAST_N_GROUPS,
 	IFLA_BRPORT_MCAST_MAX_GROUPS,
 	IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
+	IFLA_BRPORT_BACKUP_NHID,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 6116eba1bd891..9d7bc8b96b53a 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -154,6 +154,7 @@ void br_forward(const struct net_bridge_port *to,
 		backup_port = rcu_dereference(to->backup_port);
 		if (unlikely(!backup_port))
 			goto out;
+		BR_INPUT_SKB_CB(skb)->backup_nhid = READ_ONCE(to->backup_nhid);
 		to = backup_port;
 	}
 
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 05c5863d2e20f..10f0d33d8ccf2 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -211,6 +211,7 @@ static inline size_t br_port_info_size(void)
 		+ nla_total_size(sizeof(u8))	/* IFLA_BRPORT_MRP_IN_OPEN */
 		+ nla_total_size(sizeof(u32))	/* IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT */
 		+ nla_total_size(sizeof(u32))	/* IFLA_BRPORT_MCAST_EHT_HOSTS_CNT */
+		+ nla_total_size(sizeof(u32))	/* IFLA_BRPORT_BACKUP_NHID */
 		+ 0;
 }
 
@@ -319,6 +320,10 @@ static int br_port_fill_attrs(struct sk_buff *skb,
 			    backup_p->dev->ifindex);
 	rcu_read_unlock();
 
+	if (p->backup_nhid &&
+	    nla_put_u32(skb, IFLA_BRPORT_BACKUP_NHID, p->backup_nhid))
+		return -EMSGSIZE;
+
 	return 0;
 }
 
@@ -895,6 +900,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
 	[IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT },
 	[IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 },
 	[IFLA_BRPORT_NEIGH_VLAN_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1),
+	[IFLA_BRPORT_BACKUP_NHID] = { .type = NLA_U32 },
 };
 
 /* Change the state of the port and notify spanning tree */
@@ -1065,6 +1071,12 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[],
 			return err;
 	}
 
+	if (tb[IFLA_BRPORT_BACKUP_NHID]) {
+		u32 backup_nhid = nla_get_u32(tb[IFLA_BRPORT_BACKUP_NHID]);
+
+		WRITE_ONCE(p->backup_nhid, backup_nhid);
+	}
+
 	return 0;
 }
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index a63b32c1638ea..05a965ef76f1a 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -387,6 +387,7 @@ struct net_bridge_port {
 	struct net_bridge_vlan_group	__rcu *vlgrp;
 #endif
 	struct net_bridge_port		__rcu *backup_port;
+	u32				backup_nhid;
 
 	/* STP */
 	u8				priority;
@@ -605,6 +606,8 @@ struct br_input_skb_cb {
 	 */
 	unsigned long fwd_hwdoms;
 #endif
+
+	u32 backup_nhid;
 };
 
 #define BR_INPUT_SKB_CB(__skb)	((struct br_input_skb_cb *)(__skb)->cb)
diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c
index 6399a8a69d076..81833ca7a2c77 100644
--- a/net/bridge/br_vlan_tunnel.c
+++ b/net/bridge/br_vlan_tunnel.c
@@ -201,6 +201,21 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb,
 	if (err)
 		return err;
 
+	if (BR_INPUT_SKB_CB(skb)->backup_nhid) {
+		tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY,
+					      tunnel_id, 0);
+		if (!tunnel_dst)
+			return -ENOMEM;
+
+		tunnel_dst->u.tun_info.mode |= IP_TUNNEL_INFO_TX |
+					       IP_TUNNEL_INFO_BRIDGE;
+		tunnel_dst->u.tun_info.key.nhid =
+			BR_INPUT_SKB_CB(skb)->backup_nhid;
+		skb_dst_set(skb, &tunnel_dst->dst);
+
+		return 0;
+	}
+
 	tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst);
 	if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst))
 		skb_dst_set(skb, &tunnel_dst->dst);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 70838d7e5b325..1777a5e1830b7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -61,7 +61,7 @@
 #include "dev.h"
 
 #define RTNL_MAX_TYPE		50
-#define RTNL_SLAVE_MAX_TYPE	43
+#define RTNL_SLAVE_MAX_TYPE	44
 
 struct rtnl_link {
 	rtnl_doit_func		doit;
-- 
GitLab


From b408453053fbd1409cc98ce420d64448f58cfd09 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Jul 2023 11:12:29 +0300
Subject: [PATCH 0208/1806] selftests: net: Add bridge backup port and backup
 nexthop ID test

Add test cases for bridge backup port and backup nexthop ID, testing
both good and bad flows.

Example truncated output:

 # ./test_bridge_backup_port.sh
 [...]
 Tests passed:  83
 Tests failed:   0

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile          |   1 +
 .../selftests/net/test_bridge_backup_port.sh  | 759 ++++++++++++++++++
 2 files changed, 760 insertions(+)
 create mode 100755 tools/testing/selftests/net/test_bridge_backup_port.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index fbf579f469927..04341e1b38f04 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -87,6 +87,7 @@ TEST_GEN_FILES += bind_wildcard
 TEST_PROGS += test_vxlan_mdb.sh
 TEST_PROGS += test_bridge_neigh_suppress.sh
 TEST_PROGS += test_vxlan_nolocalbypass.sh
+TEST_PROGS += test_bridge_backup_port.sh
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/net/test_bridge_backup_port.sh b/tools/testing/selftests/net/test_bridge_backup_port.sh
new file mode 100755
index 0000000000000..112cfd8a10ad9
--- /dev/null
+++ b/tools/testing/selftests/net/test_bridge_backup_port.sh
@@ -0,0 +1,759 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking bridge backup port and backup nexthop ID
+# functionality. The topology consists of two bridge (VTEPs) connected using
+# VXLAN. The test checks that when the switch port (swp1) is down, traffic is
+# redirected to the VXLAN port (vx0). When a backup nexthop ID is configured,
+# the test checks that traffic is redirected with the correct nexthop
+# information.
+#
+# +------------------------------------+ +------------------------------------+
+# |    + swp1                   + vx0  | |    + swp1                   + vx0  |
+# |    |                        |      | |    |                        |      |
+# |    |           br0          |      | |    |                        |      |
+# |    +------------+-----------+      | |    +------------+-----------+      |
+# |                 |                  | |                 |                  |
+# |                 |                  | |                 |                  |
+# |                 +                  | |                 +                  |
+# |                br0                 | |                br0                 |
+# |                 +                  | |                 +                  |
+# |                 |                  | |                 |                  |
+# |                 |                  | |                 |                  |
+# |                 +                  | |                 +                  |
+# |              br0.10                | |              br0.10                |
+# |           192.0.2.65/28            | |            192.0.2.66/28           |
+# |                                    | |                                    |
+# |                                    | |                                    |
+# |                 192.0.2.33         | |                 192.0.2.34         |
+# |                 + lo               | |                 + lo               |
+# |                                    | |                                    |
+# |                                    | |                                    |
+# |                   192.0.2.49/28    | |    192.0.2.50/28                   |
+# |                           veth0 +-------+ veth0                           |
+# |                                    | |                                    |
+# | sw1                                | | sw2                                |
+# +------------------------------------+ +------------------------------------+
+
+ret=0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# All tests in this script. Can be overridden with -t option.
+TESTS="
+	backup_port
+	backup_nhid
+	backup_nhid_invalid
+	backup_nhid_ping
+	backup_nhid_torture
+"
+VERBOSE=0
+PAUSE_ON_FAIL=no
+PAUSE=no
+PING_TIMEOUT=5
+
+################################################################################
+# Utilities
+
+log_test()
+{
+	local rc=$1
+	local expected=$2
+	local msg="$3"
+
+	if [ ${rc} -eq ${expected} ]; then
+		printf "TEST: %-60s  [ OK ]\n" "${msg}"
+		nsuccess=$((nsuccess+1))
+	else
+		ret=1
+		nfail=$((nfail+1))
+		printf "TEST: %-60s  [FAIL]\n" "${msg}"
+		if [ "$VERBOSE" = "1" ]; then
+			echo "    rc=$rc, expected $expected"
+		fi
+
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+		echo
+			echo "hit enter to continue, 'q' to quit"
+			read a
+			[ "$a" = "q" ] && exit 1
+		fi
+	fi
+
+	if [ "${PAUSE}" = "yes" ]; then
+		echo
+		echo "hit enter to continue, 'q' to quit"
+		read a
+		[ "$a" = "q" ] && exit 1
+	fi
+
+	[ "$VERBOSE" = "1" ] && echo
+}
+
+run_cmd()
+{
+	local cmd="$1"
+	local out
+	local stderr="2>/dev/null"
+
+	if [ "$VERBOSE" = "1" ]; then
+		printf "COMMAND: $cmd\n"
+		stderr=
+	fi
+
+	out=$(eval $cmd $stderr)
+	rc=$?
+	if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+		echo "    $out"
+	fi
+
+	return $rc
+}
+
+tc_check_packets()
+{
+	local ns=$1; shift
+	local id=$1; shift
+	local handle=$1; shift
+	local count=$1; shift
+	local pkts
+
+	sleep 0.1
+	pkts=$(tc -n $ns -j -s filter show $id \
+		| jq ".[] | select(.options.handle == $handle) | \
+		.options.actions[0].stats.packets")
+	[[ $pkts == $count ]]
+}
+
+################################################################################
+# Setup
+
+setup_topo_ns()
+{
+	local ns=$1; shift
+
+	ip netns add $ns
+	ip -n $ns link set dev lo up
+
+	ip netns exec $ns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1
+	ip netns exec $ns sysctl -qw net.ipv6.conf.default.ignore_routes_with_linkdown=1
+	ip netns exec $ns sysctl -qw net.ipv6.conf.all.accept_dad=0
+	ip netns exec $ns sysctl -qw net.ipv6.conf.default.accept_dad=0
+}
+
+setup_topo()
+{
+	local ns
+
+	for ns in sw1 sw2; do
+		setup_topo_ns $ns
+	done
+
+	ip link add name veth0 type veth peer name veth1
+	ip link set dev veth0 netns sw1 name veth0
+	ip link set dev veth1 netns sw2 name veth0
+}
+
+setup_sw_common()
+{
+	local ns=$1; shift
+	local local_addr=$1; shift
+	local remote_addr=$1; shift
+	local veth_addr=$1; shift
+	local gw_addr=$1; shift
+	local br_addr=$1; shift
+
+	ip -n $ns address add $local_addr/32 dev lo
+
+	ip -n $ns link set dev veth0 up
+	ip -n $ns address add $veth_addr/28 dev veth0
+	ip -n $ns route add default via $gw_addr
+
+	ip -n $ns link add name br0 up type bridge vlan_filtering 1 \
+		vlan_default_pvid 0 mcast_snooping 0
+
+	ip -n $ns link add link br0 name br0.10 up type vlan id 10
+	bridge -n $ns vlan add vid 10 dev br0 self
+	ip -n $ns address add $br_addr/28 dev br0.10
+
+	ip -n $ns link add name swp1 up type dummy
+	ip -n $ns link set dev swp1 master br0
+	bridge -n $ns vlan add vid 10 dev swp1 untagged
+
+	ip -n $ns link add name vx0 up master br0 type vxlan \
+		local $local_addr dstport 4789 nolearning external
+	bridge -n $ns link set dev vx0 vlan_tunnel on learning off
+
+	bridge -n $ns vlan add vid 10 dev vx0
+	bridge -n $ns vlan add vid 10 dev vx0 tunnel_info id 10010
+}
+
+setup_sw1()
+{
+	local ns=sw1
+	local local_addr=192.0.2.33
+	local remote_addr=192.0.2.34
+	local veth_addr=192.0.2.49
+	local gw_addr=192.0.2.50
+	local br_addr=192.0.2.65
+
+	setup_sw_common $ns $local_addr $remote_addr $veth_addr $gw_addr \
+		$br_addr
+}
+
+setup_sw2()
+{
+	local ns=sw2
+	local local_addr=192.0.2.34
+	local remote_addr=192.0.2.33
+	local veth_addr=192.0.2.50
+	local gw_addr=192.0.2.49
+	local br_addr=192.0.2.66
+
+	setup_sw_common $ns $local_addr $remote_addr $veth_addr $gw_addr \
+		$br_addr
+}
+
+setup()
+{
+	set -e
+
+	setup_topo
+	setup_sw1
+	setup_sw2
+
+	sleep 5
+
+	set +e
+}
+
+cleanup()
+{
+	local ns
+
+	for ns in h1 h2 sw1 sw2; do
+		ip netns del $ns &> /dev/null
+	done
+}
+
+################################################################################
+# Tests
+
+backup_port()
+{
+	local dmac=00:11:22:33:44:55
+	local smac=00:aa:bb:cc:dd:ee
+
+	echo
+	echo "Backup port"
+	echo "-----------"
+
+	run_cmd "tc -n sw1 qdisc replace dev swp1 clsact"
+	run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+
+	run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+
+	run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10"
+
+	# Initial state - check that packets are forwarded out of swp1 when it
+	# has a carrier and not forwarded out of any port when it does not have
+	# a carrier.
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 1
+	log_test $? 0 "Forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 0
+	log_test $? 0 "No forwarding out of vx0"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	log_test $? 0 "swp1 carrier off"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 1
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 0
+	log_test $? 0 "No forwarding out of vx0"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier on"
+	log_test $? 0 "swp1 carrier on"
+
+	# Configure vx0 as the backup port of swp1 and check that packets are
+	# forwarded out of swp1 when it has a carrier and out of vx0 when swp1
+	# does not have a carrier.
+	run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\""
+	log_test $? 0 "vx0 configured as backup port of swp1"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 2
+	log_test $? 0 "Forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 0
+	log_test $? 0 "No forwarding out of vx0"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	log_test $? 0 "swp1 carrier off"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 2
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 1
+	log_test $? 0 "Forwarding out of vx0"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier on"
+	log_test $? 0 "swp1 carrier on"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 3
+	log_test $? 0 "Forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 1
+	log_test $? 0 "No forwarding out of vx0"
+
+	# Remove vx0 as the backup port of swp1 and check that packets are no
+	# longer forwarded out of vx0 when swp1 does not have a carrier.
+	run_cmd "bridge -n sw1 link set dev swp1 nobackup_port"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\""
+	log_test $? 1 "vx0 not configured as backup port of swp1"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 4
+	log_test $? 0 "Forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 1
+	log_test $? 0 "No forwarding out of vx0"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	log_test $? 0 "swp1 carrier off"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 4
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 1
+	log_test $? 0 "No forwarding out of vx0"
+}
+
+backup_nhid()
+{
+	local dmac=00:11:22:33:44:55
+	local smac=00:aa:bb:cc:dd:ee
+
+	echo
+	echo "Backup nexthop ID"
+	echo "-----------------"
+
+	run_cmd "tc -n sw1 qdisc replace dev swp1 clsact"
+	run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+
+	run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+
+	run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb"
+	run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb"
+	run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb"
+
+	run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10"
+	run_cmd "bridge -n sw1 fdb replace $dmac dev vx0 self static dst 192.0.2.36 src_vni 10010"
+
+	run_cmd "ip -n sw2 address replace 192.0.2.36/32 dev lo"
+
+	# The first filter matches on packets forwarded using the backup
+	# nexthop ID and the second filter matches on packets forwarded using a
+	# regular VXLAN FDB entry.
+	run_cmd "tc -n sw2 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass"
+	run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 102 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.36 action pass"
+
+	# Configure vx0 as the backup port of swp1 and check that packets are
+	# forwarded out of swp1 when it has a carrier and out of vx0 when swp1
+	# does not have a carrier. When packets are forwarded out of vx0, check
+	# that they are forwarded by the VXLAN FDB entry.
+	run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\""
+	log_test $? 0 "vx0 configured as backup port of swp1"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 1
+	log_test $? 0 "Forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 0
+	log_test $? 0 "No forwarding out of vx0"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	log_test $? 0 "swp1 carrier off"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 1
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 1
+	log_test $? 0 "Forwarding out of vx0"
+	tc_check_packets sw2 "dev vx0 ingress" 101 0
+	log_test $? 0 "No forwarding using backup nexthop ID"
+	tc_check_packets sw2 "dev vx0 ingress" 102 1
+	log_test $? 0 "Forwarding using VXLAN FDB entry"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier on"
+	log_test $? 0 "swp1 carrier on"
+
+	# Configure nexthop ID 10 as the backup nexthop ID of swp1 and check
+	# that when packets are forwarded out of vx0, they are forwarded using
+	# the backup nexthop ID.
+	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 10\""
+	log_test $? 0 "nexthop ID 10 configured as backup nexthop ID of swp1"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 2
+	log_test $? 0 "Forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 1
+	log_test $? 0 "No forwarding out of vx0"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	log_test $? 0 "swp1 carrier off"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 2
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 2
+	log_test $? 0 "Forwarding out of vx0"
+	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	log_test $? 0 "Forwarding using backup nexthop ID"
+	tc_check_packets sw2 "dev vx0 ingress" 102 1
+	log_test $? 0 "No forwarding using VXLAN FDB entry"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier on"
+	log_test $? 0 "swp1 carrier on"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 3
+	log_test $? 0 "Forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 2
+	log_test $? 0 "No forwarding out of vx0"
+	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	log_test $? 0 "No forwarding using backup nexthop ID"
+	tc_check_packets sw2 "dev vx0 ingress" 102 1
+	log_test $? 0 "No forwarding using VXLAN FDB entry"
+
+	# Reset the backup nexthop ID to 0 and check that packets are no longer
+	# forwarded using the backup nexthop ID when swp1 does not have a
+	# carrier and are instead forwarded by the VXLAN FDB.
+	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 0"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid\""
+	log_test $? 1 "No backup nexthop ID configured for swp1"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 4
+	log_test $? 0 "Forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 2
+	log_test $? 0 "No forwarding out of vx0"
+	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	log_test $? 0 "No forwarding using backup nexthop ID"
+	tc_check_packets sw2 "dev vx0 ingress" 102 1
+	log_test $? 0 "No forwarding using VXLAN FDB entry"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	log_test $? 0 "swp1 carrier off"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 4
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 3
+	log_test $? 0 "Forwarding out of vx0"
+	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	log_test $? 0 "No forwarding using backup nexthop ID"
+	tc_check_packets sw2 "dev vx0 ingress" 102 2
+	log_test $? 0 "Forwarding using VXLAN FDB entry"
+}
+
+backup_nhid_invalid()
+{
+	local dmac=00:11:22:33:44:55
+	local smac=00:aa:bb:cc:dd:ee
+	local tx_drop
+
+	echo
+	echo "Backup nexthop ID - invalid IDs"
+	echo "-------------------------------"
+
+	# Check that when traffic is redirected with an invalid nexthop ID, it
+	# is forwarded out of the VXLAN port, but dropped by the VXLAN driver
+	# and does not crash the host.
+
+	run_cmd "tc -n sw1 qdisc replace dev swp1 clsact"
+	run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+
+	run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+	# Drop all other Tx traffic to avoid changes to Tx drop counter.
+	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 2 handle 102 proto all matchall action drop"
+
+	tx_drop=$(ip -n sw1 -s -j link show dev vx0 | jq '.[]["stats64"]["tx"]["dropped"]')
+
+	run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb"
+	run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb"
+	run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb"
+
+	run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10"
+
+	run_cmd "tc -n sw2 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass"
+
+	# First, check that redirection works.
+	run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\""
+	log_test $? 0 "vx0 configured as backup port of swp1"
+
+	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 10\""
+	log_test $? 0 "Valid nexthop as backup nexthop"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	log_test $? 0 "swp1 carrier off"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 0
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 1
+	log_test $? 0 "Forwarding out of vx0"
+	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	log_test $? 0 "Forwarding using backup nexthop ID"
+	run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $tx_drop'"
+	log_test $? 0 "No Tx drop increase"
+
+	# Use a non-existent nexthop ID.
+	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 20"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 20\""
+	log_test $? 0 "Non-existent nexthop as backup nexthop"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 0
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 2
+	log_test $? 0 "Forwarding out of vx0"
+	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	log_test $? 0 "No forwarding using backup nexthop ID"
+	run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 1))'"
+	log_test $? 0 "Tx drop increased"
+
+	# Use a blckhole nexthop.
+	run_cmd "ip -n sw1 nexthop replace id 30 blackhole"
+	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 30"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 30\""
+	log_test $? 0 "Blackhole nexthop as backup nexthop"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 0
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 3
+	log_test $? 0 "Forwarding out of vx0"
+	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	log_test $? 0 "No forwarding using backup nexthop ID"
+	run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 2))'"
+	log_test $? 0 "Tx drop increased"
+
+	# Non-group FDB nexthop.
+	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 1"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 1\""
+	log_test $? 0 "Non-group FDB nexthop as backup nexthop"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 0
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 4
+	log_test $? 0 "Forwarding out of vx0"
+	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	log_test $? 0 "No forwarding using backup nexthop ID"
+	run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 3))'"
+	log_test $? 0 "Tx drop increased"
+
+	# IPv6 address family nexthop.
+	run_cmd "ip -n sw1 nexthop replace id 100 via 2001:db8:100::1 fdb"
+	run_cmd "ip -n sw1 nexthop replace id 200 via 2001:db8:100::1 fdb"
+	run_cmd "ip -n sw1 nexthop replace id 300 group 100/200 fdb"
+	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 300"
+	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 300\""
+	log_test $? 0 "IPv6 address family nexthop as backup nexthop"
+
+	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets sw1 "dev swp1 egress" 101 0
+	log_test $? 0 "No forwarding out of swp1"
+	tc_check_packets sw1 "dev vx0 egress" 101 5
+	log_test $? 0 "Forwarding out of vx0"
+	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	log_test $? 0 "No forwarding using backup nexthop ID"
+	run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 4))'"
+	log_test $? 0 "Tx drop increased"
+}
+
+backup_nhid_ping()
+{
+	local sw1_mac
+	local sw2_mac
+
+	echo
+	echo "Backup nexthop ID - ping"
+	echo "------------------------"
+
+	# Test bidirectional traffic when traffic is redirected in both VTEPs.
+	sw1_mac=$(ip -n sw1 -j -p link show br0.10 | jq -r '.[]["address"]')
+	sw2_mac=$(ip -n sw2 -j -p link show br0.10 | jq -r '.[]["address"]')
+
+	run_cmd "bridge -n sw1 fdb replace $sw2_mac dev swp1 master static vlan 10"
+	run_cmd "bridge -n sw2 fdb replace $sw1_mac dev swp1 master static vlan 10"
+
+	run_cmd "ip -n sw1 neigh replace 192.0.2.66 lladdr $sw2_mac nud perm dev br0.10"
+	run_cmd "ip -n sw2 neigh replace 192.0.2.65 lladdr $sw1_mac nud perm dev br0.10"
+
+	run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb"
+	run_cmd "ip -n sw2 nexthop replace id 1 via 192.0.2.33 fdb"
+	run_cmd "ip -n sw1 nexthop replace id 10 group 1 fdb"
+	run_cmd "ip -n sw2 nexthop replace id 10 group 1 fdb"
+
+	run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n sw2 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10"
+	run_cmd "bridge -n sw2 link set dev swp1 backup_nhid 10"
+
+	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	run_cmd "ip -n sw2 link set dev swp1 carrier off"
+
+	run_cmd "ip netns exec sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66"
+	log_test $? 0 "Ping with backup nexthop ID"
+
+	# Reset the backup nexthop ID to 0 and check that ping fails.
+	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 0"
+	run_cmd "bridge -n sw2 link set dev swp1 backup_nhid 0"
+
+	run_cmd "ip netns exec sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66"
+	log_test $? 1 "Ping after disabling backup nexthop ID"
+}
+
+backup_nhid_add_del_loop()
+{
+	while true; do
+		ip -n sw1 nexthop del id 10
+		ip -n sw1 nexthop replace id 10 group 1/2 fdb
+	done >/dev/null 2>&1
+}
+
+backup_nhid_torture()
+{
+	local dmac=00:11:22:33:44:55
+	local smac=00:aa:bb:cc:dd:ee
+	local pid1
+	local pid2
+	local pid3
+
+	echo
+	echo "Backup nexthop ID - torture test"
+	echo "--------------------------------"
+
+	# Continuously send traffic through the backup nexthop while adding and
+	# deleting the group. The test is considered successful if nothing
+	# crashed.
+
+	run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb"
+	run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb"
+	run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb"
+
+	run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10"
+
+	run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10"
+	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+
+	backup_nhid_add_del_loop &
+	pid1=$!
+	ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 0 &
+	pid2=$!
+
+	sleep 30
+	kill -9 $pid1 $pid2
+	wait $pid1 $pid2 2>/dev/null
+
+	log_test 0 0 "Torture test"
+}
+
+################################################################################
+# Usage
+
+usage()
+{
+	cat <<EOF
+usage: ${0##*/} OPTS
+
+        -t <test>   Test(s) to run (default: all)
+                    (options: $TESTS)
+        -p          Pause on fail
+        -P          Pause after each test before cleanup
+        -v          Verbose mode (show commands and output)
+        -w          Timeout for ping
+EOF
+}
+
+################################################################################
+# Main
+
+trap cleanup EXIT
+
+while getopts ":t:pPvhw:" opt; do
+	case $opt in
+		t) TESTS=$OPTARG;;
+		p) PAUSE_ON_FAIL=yes;;
+		P) PAUSE=yes;;
+		v) VERBOSE=$(($VERBOSE + 1));;
+		w) PING_TIMEOUT=$OPTARG;;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
+# Make sure we don't pause twice.
+[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no
+
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit $ksft_skip;
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v bridge)" ]; then
+	echo "SKIP: Could not run test without bridge tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v tc)" ]; then
+	echo "SKIP: Could not run test without tc tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v mausezahn)" ]; then
+	echo "SKIP: Could not run test without mausezahn tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v jq)" ]; then
+	echo "SKIP: Could not run test without jq tool"
+	exit $ksft_skip
+fi
+
+bridge link help 2>&1 | grep -q "backup_nhid"
+if [ $? -ne 0 ]; then
+   echo "SKIP: iproute2 bridge too old, missing backup nexthop ID support"
+   exit $ksft_skip
+fi
+
+# Start clean.
+cleanup
+
+for t in $TESTS
+do
+	setup; $t; cleanup;
+done
+
+if [ "$TESTS" != "none" ]; then
+	printf "\nTests passed: %3d\n" ${nsuccess}
+	printf "Tests failed: %3d\n"   ${nfail}
+fi
+
+exit $ret
-- 
GitLab


From 47448ff2d5c7715d9c06a27aa6d1b1f5ad1ff3db Mon Sep 17 00:00:00 2001
From: Rohan G Thomas <rohan.g.thomas@intel.com>
Date: Mon, 17 Jul 2023 20:06:03 +0800
Subject: [PATCH 0209/1806] net: stmmac: xgmac: Fix L3L4 filter count

Get the exact count of L3L4 filters when the L3L4FNUM field of
HW_FEATURE1 register is >= 8. If L3L4FNUM < 8, then the number of L3L4
filters supported by XGMAC is equal to L3L4FNUM. From L3L4FNUM >= 8
the number of L3L4 filters goes on like 8, 16, 32, ... Current
maximum of L3L4FNUM = 10.

Also, fix the XGMAC_IDDR bitmask of L3L4_ADDR_CTRL register. IDDR
field starts from the 8th bit of the L3L4_ADDR_CTRL register. IDDR[3:0]
indicates the type of L3L4 filter register while IDDR[8:4] indicates
the filter number (0 to 31). So overall 9 bits are used for IDDR
(i.e. L3L4_ADDR_CTRL[16:8]) to address the registers of all the
filters. Currently, XGMAC_IDDR is GENMASK(15,8), causing issues
accessing L3L4 filters above 15 for those XGMACs configured with more
than 16 L3L4 filters.

Signed-off-by: Rohan G Thomas <rohan.g.thomas@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h     |  2 +-
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 10 ++++++++++
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 1913385df6856..153321fe42c31 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -165,7 +165,7 @@
 #define XGMAC_DCS_SHIFT			16
 #define XGMAC_ADDRx_LOW(x)		(0x00000304 + (x) * 0x8)
 #define XGMAC_L3L4_ADDR_CTRL		0x00000c00
-#define XGMAC_IDDR			GENMASK(15, 8)
+#define XGMAC_IDDR			GENMASK(16, 8)
 #define XGMAC_IDDR_SHIFT		8
 #define XGMAC_IDDR_FNUM			4
 #define XGMAC_TT			BIT(1)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 070bd912580b7..df5af52fd1a17 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -408,6 +408,16 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 	/* MAC HW feature 1 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1);
 	dma_cap->l3l4fnum = (hw_cap & XGMAC_HWFEAT_L3L4FNUM) >> 27;
+	/* If L3L4FNUM < 8, then the number of L3L4 filters supported by
+	 * XGMAC is equal to L3L4FNUM. From L3L4FNUM >= 8 the number of
+	 * L3L4 filters goes on like 8, 16, 32, ... Current maximum of
+	 * L3L4FNUM = 10.
+	 */
+	if (dma_cap->l3l4fnum >= 8 && dma_cap->l3l4fnum <= 10)
+		dma_cap->l3l4fnum = 8 << (dma_cap->l3l4fnum - 8);
+	else if (dma_cap->l3l4fnum > 10)
+		dma_cap->l3l4fnum = 32;
+
 	dma_cap->hash_tb_sz = (hw_cap & XGMAC_HWFEAT_HASHTBLSZ) >> 24;
 	dma_cap->rssen = (hw_cap & XGMAC_HWFEAT_RSSEN) >> 20;
 	dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18;
-- 
GitLab


From edbc16c43b271e2c07cb922c60af5110cd0cc2b9 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:21 +0200
Subject: [PATCH 0210/1806] selftests: mptcp: connect: don't stop if error

No more tests were executed after a failure but it is still interesting
to get results for all the tests to better understand what's still OK
and what's not after a modification.

Now we only exit earlier if the basic tests are failing: no ping going
through namespaces or unable to transfer data on the loopback interface.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/mptcp/mptcp_connect.sh      | 27 ++++++++++++++-----
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index bbae40882bfaf..0f060af01a847 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -7,6 +7,7 @@ time_start=$(date +%s)
 
 optstring="S:R:d:e:l:r:h4cm:f:tC"
 ret=0
+final_ret=0
 sin=""
 sout=""
 cin_disconnect=""
@@ -837,14 +838,25 @@ display_time()
 	echo "Time: ${time_run} seconds"
 }
 
-stop_if_error()
+log_if_error()
 {
 	local msg="$1"
 
 	if [ ${ret} -ne 0 ]; then
 		echo "FAIL: ${msg}" 1>&2
+
+		final_ret=${ret}
+		ret=0
+
+		return ${final_ret}
+	fi
+}
+
+stop_if_error()
+{
+	if ! log_if_error "${@}"; then
 		display_time
-		exit ${ret}
+		exit ${final_ret}
 	fi
 }
 
@@ -934,23 +946,24 @@ for sender in $ns1 $ns2 $ns3 $ns4;do
 	run_tests "$ns4" $sender 10.0.3.1
 	run_tests "$ns4" $sender dead:beef:3::1
 
-	stop_if_error "Tests with $sender as a sender have failed"
+	log_if_error "Tests with $sender as a sender have failed"
 done
 
 run_tests_peekmode "saveWithPeek"
 run_tests_peekmode "saveAfterPeek"
-stop_if_error "Tests with peek mode have failed"
+log_if_error "Tests with peek mode have failed"
 
 # MPTFO (MultiPath TCP Fatopen tests)
 run_tests_mptfo
-stop_if_error "Tests with MPTFO have failed"
+log_if_error "Tests with MPTFO have failed"
 
 # connect to ns4 ip address, ns2 should intercept/proxy
 run_test_transparent 10.0.3.1 "tproxy ipv4"
 run_test_transparent dead:beef:3::1 "tproxy ipv6"
-stop_if_error "Tests with tproxy have failed"
+log_if_error "Tests with tproxy have failed"
 
 run_tests_disconnect
+log_if_error "Tests of the full disconnection have failed"
 
 display_time
-exit $ret
+exit ${final_ret}
-- 
GitLab


From e141c1e8e4c17ba4b75e362f8da85285f906a7a1 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:22 +0200
Subject: [PATCH 0211/1806] selftests: mptcp: userspace pm: don't stop if error

No more tests were executed after a failure but it is still interesting
to get results for all the tests to better understand what's still OK
and what's not after a modification.

Now we only exit earlier if the two connections cannot be established.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/mptcp/userspace_pm.sh       | 21 ++++++++++---------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index b180133a30af7..c57ce4df4973d 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -52,6 +52,7 @@ sec=$(date +%s)
 rndh=$(printf %x "$sec")-$(mktemp -u XXXXXX)
 ns1="ns1-$rndh"
 ns2="ns2-$rndh"
+ret=0
 
 print_title()
 {
@@ -257,21 +258,21 @@ check_expected_one()
 # $@: all var names to check
 check_expected()
 {
-	local ret=0
+	local rc=0
 	local var
 
 	for var in "${@}"
 	do
-		check_expected_one "${var}" "${ret}" || ret=1
+		check_expected_one "${var}" "${rc}" || rc=1
 	done
 
-	if [ ${ret} -eq 0 ]
+	if [ ${rc} -eq 0 ]
 	then
 		stdbuf -o0 -e0 printf "[OK]\n"
 		return 0
 	fi
 
-	exit 1
+	ret=1
 }
 
 verify_announce_event()
@@ -323,7 +324,7 @@ test_announce()
 		stdbuf -o0 -e0 printf "[OK]\n"
 	else
 		stdbuf -o0 -e0 printf "[FAIL]\n\ttype defined: %s\n" "${type}"
-		exit 1
+		ret=1
 	fi
 
 	# ADD_ADDR from the client to server machine reusing the subflow port
@@ -423,7 +424,7 @@ test_remove()
 		stdbuf -o0 -e0 printf "[OK]\n"
 	else
 		stdbuf -o0 -e0 printf "[FAIL]\n"
-		exit 1
+		ret=1
 	fi
 
 	# RM_ADDR using an invalid addr id should result in no action
@@ -438,7 +439,7 @@ test_remove()
 		stdbuf -o0 -e0 printf "[OK]\n"
 	else
 		stdbuf -o0 -e0 printf "[FAIL]\n"
-		exit 1
+		ret=1
 	fi
 
 	# RM_ADDR from the client to server machine
@@ -859,7 +860,7 @@ test_prio()
 	[ -z "$count" ] && count=0
 	if [ $count != 1 ]; then
 		stdbuf -o0 -e0 printf "[FAIL]\n\tCount != 1: %d\n" "${count}"
-		exit 1
+		ret=1
 	else
 		stdbuf -o0 -e0 printf "[OK]\n"
 	fi
@@ -870,7 +871,7 @@ test_prio()
 	[ -z "$count" ] && count=0
 	if [ $count != 1 ]; then
 		stdbuf -o0 -e0 printf "[FAIL]\n\tCount != 1: %d\n" "${count}"
-		exit 1
+		ret=1
 	else
 		stdbuf -o0 -e0 printf "[OK]\n"
 	fi
@@ -961,4 +962,4 @@ test_subflows_v4_v6_mix
 test_prio
 test_listener
 
-exit 0
+exit ${ret}
-- 
GitLab


From 8320b1387a157d3eb065b1f2c1c629577a8ba8e8 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:23 +0200
Subject: [PATCH 0212/1806] selftests: mptcp: userspace_pm: fix shellcheck
 warnings

shellcheck recently helped to find an issue where a wrong variable name
was used. It is then good to fix the other harmless issues in order to
spot "real" ones later.

Here, three categories of warnings are ignored:

- SC2317: Command appears to be unreachable. The cleanup() function is
  invoke indirectly via the EXIT trap.

- SC2034: Variable appears unused. The check_expected_one() function
  takes the name of the variable in argument but it ends up reading the
  content: indirect usage.

- SC2086: Double quote to prevent globbing and word splitting. This is
  recommended but the current usage is correct and there is no need to
  do all these modifications to be compliant with this rule.

One error has been fixed with SC2181: Check exit code directly with e.g.
'if ! mycmd;', not indirectly with $?.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/userspace_pm.sh | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index c57ce4df4973d..63d348693e98c 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -1,6 +1,13 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+# Double quotes to prevent globbing and word splitting is recommended in new
+# code but we accept it.
+#shellcheck disable=SC2086
+
+# Some variables are used below but indirectly, see check_expected_one()
+#shellcheck disable=SC2034
+
 . "$(dirname "${0}")/mptcp_lib.sh"
 
 mptcp_lib_check_mptcp
@@ -11,8 +18,7 @@ if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 	exit ${KSFT_SKIP}
 fi
 
-ip -Version > /dev/null 2>&1
-if [ $? -ne 0 ];then
+if ! ip -Version &> /dev/null; then
 	echo "SKIP: Cannot not run test without ip tool"
 	exit ${KSFT_SKIP}
 fi
@@ -68,6 +74,8 @@ kill_wait()
 	wait $1 2>/dev/null
 }
 
+# This function is used in the cleanup trap
+#shellcheck disable=SC2317
 cleanup()
 {
 	print_title "Cleanup"
-- 
GitLab


From e198ad75927342cb0dead1b5c41331c73388ce7d Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:24 +0200
Subject: [PATCH 0213/1806] selftests: mptcp: userspace_pm: uniform results
 printing

There are a few reasons to do that:

- When the tabs are not printed as 8 spaces, some results were not
  properly aligned

- Some lines printing the test name were very long due to the use of a
  lot of spaces/tabs at the end and stdbuf at the beginning.

- To reduce duplicated code, e.g. to print what has failed and set the
  status

But by centralising how the test results are printed, this also prepares
future commits to avoid more duplicated code and ease the tracking of
the different subtests.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/mptcp/userspace_pm.sh       | 141 ++++++++++--------
 1 file changed, 79 insertions(+), 62 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 63d348693e98c..6b733b97d3585 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -65,6 +65,38 @@ print_title()
 	stdbuf -o0 -e0 printf "INFO: %s\n" "${1}"
 }
 
+# $1: test name
+print_test()
+{
+	stdbuf -o0 -e0 printf "%-63s" "${1}"
+}
+
+print_results()
+{
+	stdbuf -o0 -e0 printf "[%s]\n" "${1}"
+}
+
+test_pass()
+{
+	print_results " OK "
+}
+
+test_skip()
+{
+	print_results "SKIP"
+}
+
+# $1: msg
+test_fail()
+{
+	print_results "FAIL"
+	ret=1
+
+	if [ -n "${1}" ]; then
+		stdbuf -o0 -e0 printf "\t%s\n" "${1}"
+	fi
+}
+
 kill_wait()
 {
 	[ $1 -eq 0 ] && return 0
@@ -127,7 +159,8 @@ ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth1 nodad
 ip -net "$ns2" link set ns2eth1 up
 
 print_title "Init"
-stdbuf -o0 -e0 printf "Created network namespaces ns1, ns2         \t\t\t[OK]\n"
+print_test "Created network namespaces ns1, ns2"
+test_pass
 
 make_file()
 {
@@ -212,16 +245,13 @@ make_connection()
 	server_serverside=$(grep "type:1," "$server_evts" |
 			    sed --unbuffered -n 's/.*\(server_side:\)\([[:digit:]]*\).*$/\2/p;q')
 
-	stdbuf -o0 -e0 printf "Established IP%s MPTCP Connection ns2 => ns1    \t\t" $is_v6
+	print_test "Established IP${is_v6} MPTCP Connection ns2 => ns1"
 	if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] &&
 		   [ "$server_serverside" = 1 ]
 	then
-		stdbuf -o0 -e0 printf "[OK]\n"
+		test_pass
 	else
-		stdbuf -o0 -e0 printf "[FAIL]\n"
-		stdbuf -o0 -e0 printf "\tExpected tokens (c:%s - s:%s) and server (c:%d - s:%d)\n" \
-			"${client_token}" "${server_token}" \
-			"${client_serverside}" "${server_serverside}"
+		test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})"
 		exit 1
 	fi
 
@@ -255,7 +285,7 @@ check_expected_one()
 
 	if [ "${prev_ret}" = "0" ]
 	then
-		stdbuf -o0 -e0 printf "[FAIL]\n"
+		test_fail
 	fi
 
 	stdbuf -o0 -e0 printf "\tExpected value for '%s': '%s', got '%s'.\n" \
@@ -276,11 +306,11 @@ check_expected()
 
 	if [ ${rc} -eq 0 ]
 	then
-		stdbuf -o0 -e0 printf "[OK]\n"
+		test_pass
 		return 0
 	fi
 
-	ret=1
+	return 1
 }
 
 verify_announce_event()
@@ -326,13 +356,12 @@ test_announce()
 
 	local type
 	type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts")
-	stdbuf -o0 -e0 printf "ADD_ADDR 10.0.2.2 (ns2) => ns1, invalid token    \t\t"
+	print_test "ADD_ADDR 10.0.2.2 (ns2) => ns1, invalid token"
 	if [ "$type" = "" ]
 	then
-		stdbuf -o0 -e0 printf "[OK]\n"
+		test_pass
 	else
-		stdbuf -o0 -e0 printf "[FAIL]\n\ttype defined: %s\n" "${type}"
-		ret=1
+		test_fail "type defined: ${type}"
 	fi
 
 	# ADD_ADDR from the client to server machine reusing the subflow port
@@ -340,7 +369,7 @@ test_announce()
 	ip netns exec "$ns2"\
 	   ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id $client_addr_id dev\
 	   ns2eth1 > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.2 (ns2) => ns1, reuse port \t\t" $client_addr_id
+	print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, reuse port"
 	sleep 0.5
 	verify_announce_event $server_evts $ANNOUNCED $server4_token "10.0.2.2" $client_addr_id \
 			      "$client4_port"
@@ -349,7 +378,7 @@ test_announce()
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl ann\
 	   dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1 > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "ADD_ADDR6 id:%d dead:beef:2::2 (ns2) => ns1, reuse port\t\t" $client_addr_id
+	print_test "ADD_ADDR6 id:${client_addr_id} dead:beef:2::2 (ns2) => ns1, reuse port"
 	sleep 0.5
 	verify_announce_event "$server_evts" "$ANNOUNCED" "$server6_token" "dead:beef:2::2"\
 			      "$client_addr_id" "$client6_port" "v6"
@@ -359,7 +388,7 @@ test_announce()
 	client_addr_id=$((client_addr_id+1))
 	ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\
 	   $client_addr_id dev ns2eth1 port $new4_port > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.2 (ns2) => ns1, new port \t\t\t" $client_addr_id
+	print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, new port"
 	sleep 0.5
 	verify_announce_event "$server_evts" "$ANNOUNCED" "$server4_token" "10.0.2.2"\
 			      "$client_addr_id" "$new4_port"
@@ -370,7 +399,7 @@ test_announce()
 	# ADD_ADDR from the server to client machine reusing the subflow port
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
 	   $server_addr_id dev ns1eth2 > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.1 (ns1) => ns2, reuse port \t\t" $server_addr_id
+	print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\
 			      "$server_addr_id" "$app4_port"
@@ -379,7 +408,7 @@ test_announce()
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\
 	   $server_addr_id dev ns1eth2 > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "ADD_ADDR6 id:%d dead:beef:2::1 (ns1) => ns2, reuse port\t\t" $server_addr_id
+	print_test "ADD_ADDR6 id:${server_addr_id} dead:beef:2::1 (ns1) => ns2, reuse port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "dead:beef:2::1"\
 			      "$server_addr_id" "$app6_port" "v6"
@@ -389,7 +418,7 @@ test_announce()
 	server_addr_id=$((server_addr_id+1))
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
 	   $server_addr_id dev ns1eth2 port $new4_port > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.1 (ns1) => ns2, new port \t\t\t" $server_addr_id
+	print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, new port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\
 			      "$server_addr_id" "$new4_port"
@@ -423,39 +452,34 @@ test_remove()
 	local invalid_token=$(( client4_token - 1 ))
 	ip netns exec "$ns2" ./pm_nl_ctl rem token $invalid_token id\
 	   $client_addr_id > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1, invalid token                    \t"\
-	       $client_addr_id
+	print_test "RM_ADDR id:${client_addr_id} ns2 => ns1, invalid token"
 	local type
 	type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts")
 	if [ "$type" = "" ]
 	then
-		stdbuf -o0 -e0 printf "[OK]\n"
+		test_pass
 	else
-		stdbuf -o0 -e0 printf "[FAIL]\n"
-		ret=1
+		test_fail
 	fi
 
 	# RM_ADDR using an invalid addr id should result in no action
 	local invalid_id=$(( client_addr_id + 1 ))
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
 	   $invalid_id > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1, invalid id                    \t"\
-	       $invalid_id
+	print_test "RM_ADDR id:${invalid_id} ns2 => ns1, invalid id"
 	type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts")
 	if [ "$type" = "" ]
 	then
-		stdbuf -o0 -e0 printf "[OK]\n"
+		test_pass
 	else
-		stdbuf -o0 -e0 printf "[FAIL]\n"
-		ret=1
+		test_fail
 	fi
 
 	# RM_ADDR from the client to server machine
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
 	   $client_addr_id > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1                                \t"\
-	       $client_addr_id
+	print_test "RM_ADDR id:${client_addr_id} ns2 => ns1"
 	sleep 0.5
 	verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id"
 
@@ -464,8 +488,7 @@ test_remove()
 	client_addr_id=$(( client_addr_id - 1 ))
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
 	   $client_addr_id > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1                                \t"\
-	       $client_addr_id
+	print_test "RM_ADDR id:${client_addr_id} ns2 => ns1"
 	sleep 0.5
 	verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id"
 
@@ -473,8 +496,7 @@ test_remove()
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client6_token" id\
 	   $client_addr_id > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "RM_ADDR6 id:%d ns2 => ns1                               \t"\
-	       $client_addr_id
+	print_test "RM_ADDR6 id:${client_addr_id} ns2 => ns1"
 	sleep 0.5
 	verify_remove_event "$server_evts" "$REMOVED" "$server6_token" "$client_addr_id"
 
@@ -484,8 +506,7 @@ test_remove()
 	# RM_ADDR from the server to client machine
 	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\
 	   $server_addr_id > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "RM_ADDR id:%d ns1 => ns2                                \t"\
-	       $server_addr_id
+	print_test "RM_ADDR id:${server_addr_id} ns1 => ns2"
 	sleep 0.5
 	verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id"
 
@@ -494,7 +515,7 @@ test_remove()
 	server_addr_id=$(( server_addr_id - 1 ))
 	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\
 	   $server_addr_id > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "RM_ADDR id:%d ns1 => ns2                                \t" $server_addr_id
+	print_test "RM_ADDR id:${server_addr_id} ns1 => ns2"
 	sleep 0.5
 	verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id"
 
@@ -502,7 +523,7 @@ test_remove()
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server6_token" id\
 	   $server_addr_id > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "RM_ADDR6 id:%d ns1 => ns2                               \t" $server_addr_id
+	print_test "RM_ADDR6 id:${server_addr_id} ns1 => ns2"
 	sleep 0.5
 	verify_remove_event "$client_evts" "$REMOVED" "$client6_token" "$server_addr_id"
 }
@@ -529,25 +550,24 @@ verify_subflow_events()
 	local dport
 	local locid
 	local remid
+	local info
+
+	info="${e_saddr} (${e_from}) => ${e_daddr} (${e_to})"
 
 	if [ "$e_type" = "$SUB_ESTABLISHED" ]
 	then
 		if [ "$e_family" = "$AF_INET6" ]
 		then
-			stdbuf -o0 -e0 printf "CREATE_SUBFLOW6 %s (%s) => %s (%s)    "\
-			       "$e_saddr" "$e_from" "$e_daddr" "$e_to"
+			print_test "CREATE_SUBFLOW6 ${info}"
 		else
-			stdbuf -o0 -e0 printf "CREATE_SUBFLOW %s (%s) => %s (%s)         \t"\
-			       "$e_saddr" "$e_from" "$e_daddr" "$e_to"
+			print_test "CREATE_SUBFLOW ${info}"
 		fi
 	else
 		if [ "$e_family" = "$AF_INET6" ]
 		then
-			stdbuf -o0 -e0 printf "DESTROY_SUBFLOW6 %s (%s) => %s (%s)   "\
-			       "$e_saddr" "$e_from" "$e_daddr" "$e_to"
+			print_test "DESTROY_SUBFLOW6 ${info}"
 		else
-			stdbuf -o0 -e0 printf "DESTROY_SUBFLOW %s (%s) => %s (%s)         \t"\
-			       "$e_saddr" "$e_from" "$e_daddr" "$e_to"
+			print_test "DESTROY_SUBFLOW ${info}"
 		fi
 	fi
 
@@ -818,7 +838,7 @@ test_subflows_v4_v6_mix()
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\
 	   $server_addr_id dev ns1eth2 > /dev/null 2>&1
-	stdbuf -o0 -e0 printf "ADD_ADDR4 id:%d 10.0.2.1 (ns1) => ns2, reuse port\t\t" $server_addr_id
+	print_test "ADD_ADDR4 id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\
 			      "$server_addr_id" "$app6_port"
@@ -863,25 +883,23 @@ test_prio()
 	sleep 0.5
 
 	# Check TX
-	stdbuf -o0 -e0 printf "MP_PRIO TX                                                 \t"
+	print_test "MP_PRIO TX"
 	count=$(ip netns exec "$ns2" nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}')
 	[ -z "$count" ] && count=0
 	if [ $count != 1 ]; then
-		stdbuf -o0 -e0 printf "[FAIL]\n\tCount != 1: %d\n" "${count}"
-		ret=1
+		test_fail "Count != 1: ${count}"
 	else
-		stdbuf -o0 -e0 printf "[OK]\n"
+		test_pass
 	fi
 
 	# Check RX
-	stdbuf -o0 -e0 printf "MP_PRIO RX                                                 \t"
+	print_test "MP_PRIO RX"
 	count=$(ip netns exec "$ns1" nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}')
 	[ -z "$count" ] && count=0
 	if [ $count != 1 ]; then
-		stdbuf -o0 -e0 printf "[FAIL]\n\tCount != 1: %d\n" "${count}"
-		ret=1
+		test_fail "Count != 1: ${count}"
 	else
-		stdbuf -o0 -e0 printf "[OK]\n"
+		test_pass
 	fi
 }
 
@@ -898,11 +916,9 @@ verify_listener_events()
 	local sport
 
 	if [ $e_type = $LISTENER_CREATED ]; then
-		stdbuf -o0 -e0 printf "CREATE_LISTENER %s:%s\t\t\t\t\t"\
-			$e_saddr $e_sport
+		print_test "CREATE_LISTENER $e_saddr:$e_sport"
 	elif [ $e_type = $LISTENER_CLOSED ]; then
-		stdbuf -o0 -e0 printf "CLOSE_LISTENER %s:%s\t\t\t\t\t"\
-			$e_saddr $e_sport
+		print_test "CLOSE_LISTENER $e_saddr:$e_sport"
 	fi
 
 	type=$(grep "type:$e_type," $evt |
@@ -927,7 +943,8 @@ test_listener()
 	print_title "Listener tests"
 
 	if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then
-		stdbuf -o0 -e0 printf "LISTENER events                                            \t[SKIP] Not supported\n"
+		print_test "LISTENER events"
+		test_skip
 		return
 	fi
 
-- 
GitLab


From d8463d81652de31fa8878b89629954be7a715c05 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:25 +0200
Subject: [PATCH 0214/1806] selftests: mptcp: userspace_pm: reduce dup code
 around printf

In this selftest, "printf" is always used with "stdbuf".

With a new helper, it is possible to call "stdbuf" only from one place.
This makes the code a bit clearer to read.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/userspace_pm.sh | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 6b733b97d3585..568ddee1d1027 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -59,21 +59,24 @@ rndh=$(printf %x "$sec")-$(mktemp -u XXXXXX)
 ns1="ns1-$rndh"
 ns2="ns2-$rndh"
 ret=0
+_printf() {
+	stdbuf -o0 -e0 printf "${@}"
+}
 
 print_title()
 {
-	stdbuf -o0 -e0 printf "INFO: %s\n" "${1}"
+	_printf "INFO: %s\n" "${1}"
 }
 
 # $1: test name
 print_test()
 {
-	stdbuf -o0 -e0 printf "%-63s" "${1}"
+	_printf "%-63s" "${1}"
 }
 
 print_results()
 {
-	stdbuf -o0 -e0 printf "[%s]\n" "${1}"
+	_printf "[%s]\n" "${1}"
 }
 
 test_pass()
@@ -93,7 +96,7 @@ test_fail()
 	ret=1
 
 	if [ -n "${1}" ]; then
-		stdbuf -o0 -e0 printf "\t%s\n" "${1}"
+		_printf "\t%s\n" "${1}"
 	fi
 }
 
@@ -127,7 +130,7 @@ cleanup()
 
 	rm -rf $file $client_evts $server_evts
 
-	stdbuf -o0 -e0 printf "Done\n"
+	_printf "Done\n"
 }
 
 trap cleanup EXIT
@@ -288,7 +291,7 @@ check_expected_one()
 		test_fail
 	fi
 
-	stdbuf -o0 -e0 printf "\tExpected value for '%s': '%s', got '%s'.\n" \
+	_printf "\tExpected value for '%s': '%s', got '%s'.\n" \
 		"${var}" "${!exp}" "${!var}"
 	return 1
 }
-- 
GitLab


From c4192967e62f91d26f54f9e8d80282ea469647e7 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:26 +0200
Subject: [PATCH 0215/1806] selftests: mptcp: lib: format subtests results in
 TAP

The current selftests infrastructure formats the results in TAP 13. This
version doesn't support subtests and only the end result of each
selftest is taken into account. It means that a single issue in a
subtest of a selftest containing multiple subtests forces the whole
selftest to be marked as failed. It also means that subtests results are
not tracked by CIs executing selftests.

MPTCP selftests run hundreds of various subtests. It is then important
to track each of them and not one result per selftest.

It is particularly interesting to do that when validating stable kernels
with the last version of the test suite: tests might fail because a
feature is not supported but the test didn't skip that part. In this
case, if subtests are not tracked, the whole selftest will be marked as
failed making the other subtests useless because their results are
ignored.

This patch adds some helpers in mptcp_lib.sh to be able to easily format
subtests results in TAP in the different MPTCP selftests.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/368
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/mptcp/mptcp_lib.sh  | 66 +++++++++++++++++++
 1 file changed, 66 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index f32045b23b893..b1a0fdd0408b5 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -1,8 +1,12 @@
 #! /bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+readonly KSFT_PASS=0
 readonly KSFT_FAIL=1
 readonly KSFT_SKIP=4
+readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g')
+
+MPTCP_LIB_SUBTESTS=()
 
 # SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all
 # features using the last version of the kernel and the selftests to make sure
@@ -102,3 +106,65 @@ mptcp_lib_kversion_ge() {
 
 	mptcp_lib_fail_if_expected_feature "kernel version ${1} lower than ${v}"
 }
+
+__mptcp_lib_result_add() {
+	local result="${1}"
+	shift
+
+	local id=$((${#MPTCP_LIB_SUBTESTS[@]} + 1))
+
+	MPTCP_LIB_SUBTESTS+=("${result} ${id} - ${KSFT_TEST}: ${*}")
+}
+
+# $1: test name
+mptcp_lib_result_pass() {
+	__mptcp_lib_result_add "ok" "${1}"
+}
+
+# $1: test name
+mptcp_lib_result_fail() {
+	__mptcp_lib_result_add "not ok" "${1}"
+}
+
+# $1: test name
+mptcp_lib_result_skip() {
+	__mptcp_lib_result_add "ok" "${1} # SKIP"
+}
+
+# $1: result code ; $2: test name
+mptcp_lib_result_code() {
+	local ret="${1}"
+	local name="${2}"
+
+	case "${ret}" in
+		"${KSFT_PASS}")
+			mptcp_lib_result_pass "${name}"
+			;;
+		"${KSFT_FAIL}")
+			mptcp_lib_result_fail "${name}"
+			;;
+		"${KSFT_SKIP}")
+			mptcp_lib_result_skip "${name}"
+			;;
+		*)
+			echo "ERROR: wrong result code: ${ret}"
+			exit ${KSFT_FAIL}
+			;;
+	esac
+}
+
+mptcp_lib_result_print_all_tap() {
+	local subtest
+
+	if [ ${#MPTCP_LIB_SUBTESTS[@]} -eq 0 ] ||
+	   [ "${SELFTESTS_MPTCP_LIB_NO_TAP:-}" = "1" ]; then
+		return
+	fi
+
+	printf "\nTAP version 13\n"
+	printf "1..%d\n" "${#MPTCP_LIB_SUBTESTS[@]}"
+
+	for subtest in "${MPTCP_LIB_SUBTESTS[@]}"; do
+		printf "%s\n" "${subtest}"
+	done
+}
-- 
GitLab


From dd350f46e35e8c6bbdc6c1818b7591864ced467a Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:27 +0200
Subject: [PATCH 0216/1806] selftests: mptcp: connect: format subtests results
 in TAP

The current selftests infrastructure formats the results in TAP 13. This
version doesn't support subtests and only the end result of each
selftest is taken into account. It means that a single issue in a
subtest of a selftest containing multiple subtests forces the whole
selftest to be marked as failed. It also means that subtests results are
not tracked by CIs executing selftests.

MPTCP selftests run hundreds of various subtests. It is then important
to track each of them and not one result per selftest.

It is particularly interesting to do that when validating stable kernels
with the last version of the test suite: tests might fail because a
feature is not supported but the test didn't skip that part. In this
case, if subtests are not tracked, the whole selftest will be marked as
failed making the other subtests useless because their results are
ignored.

This patch formats subtests results in TAP in mptcp_connect.sh selftest.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/mptcp/mptcp_connect.sh      | 39 +++++++++++++++++--
 1 file changed, 36 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 0f060af01a847..b1fc8afd072dc 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -129,6 +129,7 @@ ns3="ns3-$rndh"
 ns4="ns4-$rndh"
 
 TEST_COUNT=0
+TEST_GROUP=""
 
 cleanup()
 {
@@ -286,6 +287,7 @@ check_mptcp_disabled()
 	# net.mptcp.enabled should be enabled by default
 	if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then
 		echo -e "net.mptcp.enabled sysctl is not 1 by default\t\t[ FAIL ]"
+		mptcp_lib_result_fail "net.mptcp.enabled sysctl is not 1 by default"
 		ret=1
 		return 1
 	fi
@@ -298,11 +300,13 @@ check_mptcp_disabled()
 
 	if [ ${err} -eq 0 ]; then
 		echo -e "New MPTCP socket cannot be blocked via sysctl\t\t[ FAIL ]"
+		mptcp_lib_result_fail "New MPTCP socket cannot be blocked via sysctl"
 		ret=1
 		return 1
 	fi
 
 	echo -e "New MPTCP socket can be blocked via sysctl\t\t[ OK ]"
+	mptcp_lib_result_pass "New MPTCP socket can be blocked via sysctl"
 	return 0
 }
 
@@ -318,14 +322,16 @@ do_ping()
 	local connector_ns="$2"
 	local connect_addr="$3"
 	local ping_args="-q -c 1"
+	local rc=0
 
 	if is_v6 "${connect_addr}"; then
 		$ipv6 || return 0
 		ping_args="${ping_args} -6"
 	fi
 
-	ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null
-	if [ $? -ne 0 ] ; then
+	ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null || rc=1
+
+	if [ $rc -ne 0 ] ; then
 		echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2
 		ret=1
 
@@ -404,7 +410,9 @@ do_transfer()
 
 	local addr_port
 	addr_port=$(printf "%s:%d" ${connect_addr} ${port})
-	printf "%.3s %-5s -> %.3s (%-20s) %-5s\t" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto}
+	local result_msg
+	result_msg="$(printf "%.3s %-5s -> %.3s (%-20s) %-5s" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto})"
+	printf "%s\t" "${result_msg}"
 
 	if $capture; then
 		local capuser
@@ -479,6 +487,7 @@ do_transfer()
 
 	local duration
 	duration=$((stop-start))
+	result_msg+=" # time=${duration}ms"
 	printf "(duration %05sms) " "${duration}"
 	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
 		echo "[ FAIL ] client exit code $retc, server $rets" 1>&2
@@ -491,6 +500,7 @@ do_transfer()
 
 		echo
 		cat "$capout"
+		mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}"
 		return 1
 	fi
 
@@ -550,6 +560,9 @@ do_transfer()
 
 	if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then
 		printf "[ OK ]"
+		mptcp_lib_result_pass "${TEST_GROUP}: ${result_msg}"
+	else
+		mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}"
 	fi
 
 	if [ $cookies -eq 2 ];then
@@ -692,6 +705,8 @@ run_test_transparent()
 	local lret=0
 	local r6flag=""
 
+	TEST_GROUP="${msg}"
+
 	# skip if we don't want v6
 	if ! $ipv6 && is_v6 "${connect_addr}"; then
 		return 0
@@ -703,6 +718,7 @@ run_test_transparent()
 	# checking for a specific kernel version.
 	if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then
 		echo "INFO: ${msg} not supported by the kernel: SKIP"
+		mptcp_lib_result_skip "${TEST_GROUP}"
 		return
 	fi
 
@@ -720,6 +736,7 @@ EOF
 	if [ $? -ne 0 ]; then
 		echo "SKIP: $msg, could not load nft ruleset"
 		mptcp_lib_fail_if_expected_feature "nft rules"
+		mptcp_lib_result_skip "${TEST_GROUP}"
 		return
 	fi
 
@@ -736,6 +753,7 @@ EOF
 		ip netns exec "$listener_ns" nft flush ruleset
 		echo "SKIP: $msg, ip $r6flag rule failed"
 		mptcp_lib_fail_if_expected_feature "ip rule"
+		mptcp_lib_result_skip "${TEST_GROUP}"
 		return
 	fi
 
@@ -745,6 +763,7 @@ EOF
 		ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100
 		echo "SKIP: $msg, ip route add local $local_addr failed"
 		mptcp_lib_fail_if_expected_feature "ip route"
+		mptcp_lib_result_skip "${TEST_GROUP}"
 		return
 	fi
 
@@ -774,6 +793,7 @@ run_tests_peekmode()
 {
 	local peekmode="$1"
 
+	TEST_GROUP="peek mode: ${peekmode}"
 	echo "INFO: with peek mode: ${peekmode}"
 	run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 "-P ${peekmode}"
 	run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-P ${peekmode}"
@@ -781,8 +801,11 @@ run_tests_peekmode()
 
 run_tests_mptfo()
 {
+	TEST_GROUP="MPTFO"
+
 	if ! mptcp_lib_kallsyms_has "mptcp_fastopen_"; then
 		echo "INFO: TFO not supported by the kernel: SKIP"
+		mptcp_lib_result_skip "${TEST_GROUP}"
 		return
 	fi
 
@@ -806,8 +829,11 @@ run_tests_disconnect()
 	local old_cin=$cin
 	local old_sin=$sin
 
+	TEST_GROUP="full disconnect"
+
 	if ! mptcp_lib_kallsyms_has "mptcp_pm_data_reset$"; then
 		echo "INFO: Full disconnect not supported: SKIP"
+		mptcp_lib_result_skip "${TEST_GROUP}"
 		return
 	fi
 
@@ -856,6 +882,7 @@ stop_if_error()
 {
 	if ! log_if_error "${@}"; then
 		display_time
+		mptcp_lib_result_print_all_tap
 		exit ${final_ret}
 	fi
 }
@@ -886,6 +913,8 @@ for sender in "$ns1" "$ns2" "$ns3" "$ns4";do
 	do_ping "$ns4" $sender dead:beef:3::1
 done
 
+mptcp_lib_result_code "${ret}" "ping tests"
+
 stop_if_error "Could not even run ping tests"
 
 [ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss delay ${tc_delay}ms
@@ -915,12 +944,15 @@ echo "on ns3eth4"
 
 tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${reorder_delay}ms $tc_reorder
 
+TEST_GROUP="loopback v4"
 run_tests_lo "$ns1" "$ns1" 10.0.1.1 1
 stop_if_error "Could not even run loopback test"
 
+TEST_GROUP="loopback v6"
 run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1
 stop_if_error "Could not even run loopback v6 test"
 
+TEST_GROUP="multihosts"
 for sender in $ns1 $ns2 $ns3 $ns4;do
 	# ns1<->ns2 is not subject to reordering/tc delays. Use it to test
 	# mptcp syncookie support.
@@ -966,4 +998,5 @@ run_tests_disconnect
 log_if_error "Tests of the full disconnection have failed"
 
 display_time
+mptcp_lib_result_print_all_tap
 exit ${final_ret}
-- 
GitLab


From d85555ac11f90ed719062ca0d51b8103ce0e4277 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:28 +0200
Subject: [PATCH 0217/1806] selftests: mptcp: pm_netlink: format subtests
 results in TAP

The current selftests infrastructure formats the results in TAP 13. This
version doesn't support subtests and only the end result of each
selftest is taken into account. It means that a single issue in a
subtest of a selftest containing multiple subtests forces the whole
selftest to be marked as failed. It also means that subtests results are
not tracked by CIs executing selftests.

MPTCP selftests run hundreds of various subtests. It is then important
to track each of them and not one result per selftest.

It is particularly interesting to do that when validating stable kernels
with the last version of the test suite: tests might fail because a
feature is not supported but the test didn't skip that part. In this
case, if subtests are not tracked, the whole selftest will be marked as
failed making the other subtests useless because their results are
ignored.

This patch formats subtests results in TAP in pm_netlink.sh selftest.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/pm_netlink.sh | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index d02e0d63a8f91..f32038fe1ee5b 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -58,16 +58,19 @@ check()
 	local out=`$cmd 2>$err`
 	local cmd_ret=$?
 
-	printf "%-50s %s" "$msg"
+	printf "%-50s" "$msg"
 	if [ $cmd_ret -ne 0 ]; then
 		echo "[FAIL] command execution '$cmd' stderr "
 		cat $err
+		mptcp_lib_result_fail "${msg} # error ${cmd_ret}"
 		ret=1
 	elif [ "$out" = "$expected" ]; then
 		echo "[ OK ]"
+		mptcp_lib_result_pass "${msg}"
 	else
 		echo -n "[FAIL] "
 		echo "expected '$expected' got '$out'"
+		mptcp_lib_result_fail "${msg} # different output"
 		ret=1
 	fi
 }
@@ -193,4 +196,5 @@ subflow 10.0.1.1" "          (nofullmesh)"
 subflow,backup,fullmesh 10.0.1.1" "          (backup,fullmesh)"
 fi
 
+mptcp_lib_result_print_all_tap
 exit $ret
-- 
GitLab


From 7f117cd37c61d39837efb19f9f1074a8526e2fee Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:29 +0200
Subject: [PATCH 0218/1806] selftests: mptcp: join: format subtests results in
 TAP

The current selftests infrastructure formats the results in TAP 13. This
version doesn't support subtests and only the end result of each
selftest is taken into account. It means that a single issue in a
subtest of a selftest containing multiple subtests forces the whole
selftest to be marked as failed. It also means that subtests results are
not tracked by CIs executing selftests.

MPTCP selftests run hundreds of various subtests. It is then important
to track each of them and not one result per selftest.

It is particularly interesting to do that when validating stable kernels
with the last version of the test suite: tests might fail because a
feature is not supported but the test didn't skip that part. In this
case, if subtests are not tracked, the whole selftest will be marked as
failed making the other subtests useless because their results are
ignored.

This patch formats subtests results in TAP in mptcp_join.sh selftest.

In this selftest and before starting each subtest, the 'reset' function
is called. We can then check if the previous test has passed, failed or
has been skipped from there.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 37 ++++++++++++++++---
 1 file changed, 32 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index b5eeea4c3efaf..f336f86d652e5 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -39,7 +39,9 @@ evts_ns1=""
 evts_ns2=""
 evts_ns1_pid=0
 evts_ns2_pid=0
-stats_dumped=0
+last_test_failed=0
+last_test_skipped=0
+last_test_ignored=1
 
 declare -A all_tests
 declare -a only_tests_ids
@@ -101,7 +103,6 @@ init_partial()
 		fi
 	done
 
-	stats_dumped=0
 	check_invert=0
 	validate_checksum=$checksum
 
@@ -216,6 +217,8 @@ mark_as_skipped()
 
 	print_title "[ skip ] ${msg}"
 	printf "\n"
+
+	last_test_skipped=1
 }
 
 # $@: condition
@@ -248,14 +251,32 @@ skip_test()
 	return 0
 }
 
+append_prev_results()
+{
+	if [ ${last_test_failed} -eq 1 ]; then
+		mptcp_lib_result_fail "${TEST_NAME}"
+	elif [ ${last_test_skipped} -eq 1 ]; then
+		mptcp_lib_result_skip "${TEST_NAME}"
+	elif [ ${last_test_ignored} -ne 1 ]; then
+		mptcp_lib_result_pass "${TEST_NAME}"
+	fi
+
+	last_test_failed=0
+	last_test_skipped=0
+	last_test_ignored=0
+}
+
 # $1: test name
 reset()
 {
+	append_prev_results
+
 	TEST_NAME="${1}"
 
 	TEST_COUNT=$((TEST_COUNT+1))
 
 	if skip_test; then
+		last_test_ignored=1
 		return 1
 	fi
 
@@ -442,10 +463,13 @@ reset_with_tcp_filter()
 fail_test()
 {
 	ret=1
-	failed_tests[${TEST_COUNT}]="${TEST_NAME}"
 
-	[ "${stats_dumped}" = 0 ] && dump_stats
-	stats_dumped=1
+	# just in case a test is marked twice as failed
+	if [ ${last_test_failed} -eq 0 ]; then
+		failed_tests[${TEST_COUNT}]="${TEST_NAME}"
+		dump_stats
+		last_test_failed=1
+	fi
 }
 
 get_failed_tests_ids()
@@ -3599,4 +3623,7 @@ if [ ${ret} -ne 0 ]; then
 	echo
 fi
 
+append_prev_results
+mptcp_lib_result_print_all_tap
+
 exit $ret
-- 
GitLab


From ce99025736525e5ba1a639fd5c1e78936decea57 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:30 +0200
Subject: [PATCH 0219/1806] selftests: mptcp: diag: format subtests results in
 TAP

The current selftests infrastructure formats the results in TAP 13. This
version doesn't support subtests and only the end result of each
selftest is taken into account. It means that a single issue in a
subtest of a selftest containing multiple subtests forces the whole
selftest to be marked as failed. It also means that subtests results are
not tracked by CIs executing selftests.

MPTCP selftests run hundreds of various subtests. It is then important
to track each of them and not one result per selftest.

It is particularly interesting to do that when validating stable kernels
with the last version of the test suite: tests might fail because a
feature is not supported but the test didn't skip that part. In this
case, if subtests are not tracked, the whole selftest will be marked as
failed making the other subtests useless because their results are
ignored.

This patch formats subtests results in TAP in diag.sh selftest.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/diag.sh | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index fa9e09ad97d99..85a8ee9395b39 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -65,12 +65,15 @@ __chk_nr()
 	if [ $nr != $expected ]; then
 		if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then
 			echo "[ skip ] Feature probably not supported"
+			mptcp_lib_result_skip "${msg}"
 		else
 			echo "[ fail ] expected $expected found $nr"
+			mptcp_lib_result_fail "${msg}"
 			ret=$test_cnt
 		fi
 	else
 		echo "[  ok  ]"
+		mptcp_lib_result_pass "${msg}"
 	fi
 	test_cnt=$((test_cnt+1))
 }
@@ -111,12 +114,15 @@ wait_msk_nr()
 	printf "%-50s" "$msg"
 	if [ $i -ge $timeout ]; then
 		echo "[ fail ] timeout while expecting $expected max $max last $nr"
+		mptcp_lib_result_fail "${msg} # timeout"
 		ret=$test_cnt
 	elif [ $nr != $expected ]; then
 		echo "[ fail ] expected $expected found $nr"
+		mptcp_lib_result_fail "${msg} # unexpected result"
 		ret=$test_cnt
 	else
 		echo "[  ok  ]"
+		mptcp_lib_result_pass "${msg}"
 	fi
 	test_cnt=$((test_cnt+1))
 }
@@ -276,4 +282,5 @@ flush_pids
 
 chk_msk_inuse 0 "....chk 0 msk in use after flush"
 
+mptcp_lib_result_print_all_tap
 exit $ret
-- 
GitLab


From 675d99338e7a6cd925d61d7dbf8c26612f7f08a9 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:31 +0200
Subject: [PATCH 0220/1806] selftests: mptcp: simult flows: format subtests
 results in TAP

The current selftests infrastructure formats the results in TAP 13. This
version doesn't support subtests and only the end result of each
selftest is taken into account. It means that a single issue in a
subtest of a selftest containing multiple subtests forces the whole
selftest to be marked as failed. It also means that subtests results are
not tracked by CIs executing selftests.

MPTCP selftests run hundreds of various subtests. It is then important
to track each of them and not one result per selftest.

It is particularly interesting to do that when validating stable kernels
with the last version of the test suite: tests might fail because a
feature is not supported but the test didn't skip that part. In this
case, if subtests are not tracked, the whole selftest will be marked as
failed making the other subtests useless because their results are
ignored.

This patch formats subtests results in TAP in simult_flows.sh selftest.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/simult_flows.sh | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 36a3c9d92e205..ce9203b817f88 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -261,6 +261,7 @@ run_test()
 	printf "%-60s" "$msg"
 	do_transfer $small $large $time
 	lret=$?
+	mptcp_lib_result_code "${lret}" "${msg}"
 	if [ $lret -ne 0 ]; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
@@ -269,6 +270,7 @@ run_test()
 	printf "%-60s" "$msg - reverse direction"
 	do_transfer $large $small $time
 	lret=$?
+	mptcp_lib_result_code "${lret}" "${msg}"
 	if [ $lret -ne 0 ]; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
@@ -305,4 +307,6 @@ run_test 10 10 1 50 "balanced bwidth with unbalanced delay"
 run_test 30 10 0 0 "unbalanced bwidth"
 run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay"
 run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay"
+
+mptcp_lib_result_print_all_tap
 exit $ret
-- 
GitLab


From 9e86a297796bc35a8d2a63f8c6d16bd7262dc948 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:32 +0200
Subject: [PATCH 0221/1806] selftests: mptcp: sockopt: format subtests results
 in TAP

The current selftests infrastructure formats the results in TAP 13. This
version doesn't support subtests and only the end result of each
selftest is taken into account. It means that a single issue in a
subtest of a selftest containing multiple subtests forces the whole
selftest to be marked as failed. It also means that subtests results are
not tracked by CIs executing selftests.

MPTCP selftests run hundreds of various subtests. It is then important
to track each of them and not one result per selftest.

It is particularly interesting to do that when validating stable kernels
with the last version of the test suite: tests might fail because a
feature is not supported but the test didn't skip that part. In this
case, if subtests are not tracked, the whole selftest will be marked as
failed making the other subtests useless because their results are
ignored.

This patch formats subtests results in TAP in mptcp_sockopt.sh selftest.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/mptcp/mptcp_sockopt.sh      | 20 +++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index dc8d473fc82c8..8c8694f21e7df 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -183,11 +183,13 @@ do_transfer()
 
 	local mptcp_connect="./mptcp_connect -r 20"
 
-	local local_addr
+	local local_addr ip
 	if is_v6 "${connect_addr}"; then
 		local_addr="::"
+		ip=ipv6
 	else
 		local_addr="0.0.0.0"
+		ip=ipv4
 	fi
 
 	cmsg="TIMESTAMPNS"
@@ -223,6 +225,8 @@ do_transfer()
 		echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2
 		ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port"
 
+		mptcp_lib_result_fail "transfer ${ip}"
+
 		ret=1
 		return 1
 	fi
@@ -236,9 +240,11 @@ do_transfer()
 	fi
 
 	check_transfer $cin $sout "file received by server"
-
 	rets=$?
 
+	mptcp_lib_result_code "${retc}" "mark ${ip}"
+	mptcp_lib_result_code "${rets}" "transfer ${ip}"
+
 	if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
 		return 0
 	fi
@@ -264,6 +270,7 @@ do_mptcp_sockopt_tests()
 
 	if ! mptcp_lib_kallsyms_has "mptcp_diag_fill_info$"; then
 		echo "INFO: MPTCP sockopt not supported: SKIP"
+		mptcp_lib_result_skip "sockopt"
 		return
 	fi
 
@@ -272,18 +279,22 @@ do_mptcp_sockopt_tests()
 
 	if [ $lret -ne 0 ]; then
 		echo "FAIL: SOL_MPTCP getsockopt" 1>&2
+		mptcp_lib_result_fail "sockopt v4"
 		ret=$lret
 		return
 	fi
+	mptcp_lib_result_pass "sockopt v4"
 
 	ip netns exec "$ns_sbox" ./mptcp_sockopt -6
 	lret=$?
 
 	if [ $lret -ne 0 ]; then
 		echo "FAIL: SOL_MPTCP getsockopt (ipv6)" 1>&2
+		mptcp_lib_result_fail "sockopt v6"
 		ret=$lret
 		return
 	fi
+	mptcp_lib_result_pass "sockopt v6"
 }
 
 run_tests()
@@ -310,10 +321,12 @@ do_tcpinq_test()
 	if [ $lret -ne 0 ];then
 		ret=$lret
 		echo "FAIL: mptcp_inq $@" 1>&2
+		mptcp_lib_result_fail "TCP_INQ: $*"
 		return $lret
 	fi
 
 	echo "PASS: TCP_INQ cmsg/ioctl $@"
+	mptcp_lib_result_pass "TCP_INQ: $*"
 	return $lret
 }
 
@@ -323,6 +336,7 @@ do_tcpinq_tests()
 
 	if ! mptcp_lib_kallsyms_has "mptcp_ioctl$"; then
 		echo "INFO: TCP_INQ not supported: SKIP"
+		mptcp_lib_result_skip "TCP_INQ"
 		return
 	fi
 
@@ -367,4 +381,6 @@ if [ $ret -eq 0 ];then
 fi
 
 do_tcpinq_tests
+
+mptcp_lib_result_print_all_tap
 exit $ret
-- 
GitLab


From f589234e1af05bb96771378384ace72cfa54c1bf Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Mon, 17 Jul 2023 15:21:33 +0200
Subject: [PATCH 0222/1806] selftests: mptcp: userspace_pm: format subtests
 results in TAP

The current selftests infrastructure formats the results in TAP 13. This
version doesn't support subtests and only the end result of each
selftest is taken into account. It means that a single issue in a
subtest of a selftest containing multiple subtests forces the whole
selftest to be marked as failed. It also means that subtests results are
not tracked by CIs executing selftests.

MPTCP selftests run hundreds of various subtests. It is then important
to track each of them and not one result per selftest.

It is particularly interesting to do that when validating stable kernels
with the last version of the test suite: tests might fail because a
feature is not supported but the test didn't skip that part. In this
case, if subtests are not tracked, the whole selftest will be marked as
failed making the other subtests useless because their results are
ignored.

This patch formats subtests results in TAP in userspace_pm.sh selftest.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/userspace_pm.sh | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 568ddee1d1027..23f8959a8ea8e 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -59,6 +59,8 @@ rndh=$(printf %x "$sec")-$(mktemp -u XXXXXX)
 ns1="ns1-$rndh"
 ns2="ns2-$rndh"
 ret=0
+test_name=""
+
 _printf() {
 	stdbuf -o0 -e0 printf "${@}"
 }
@@ -71,7 +73,9 @@ print_title()
 # $1: test name
 print_test()
 {
-	_printf "%-63s" "${1}"
+	test_name="${1}"
+
+	_printf "%-63s" "${test_name}"
 }
 
 print_results()
@@ -82,11 +86,13 @@ print_results()
 test_pass()
 {
 	print_results " OK "
+	mptcp_lib_result_pass "${test_name}"
 }
 
 test_skip()
 {
 	print_results "SKIP"
+	mptcp_lib_result_skip "${test_name}"
 }
 
 # $1: msg
@@ -98,6 +104,8 @@ test_fail()
 	if [ -n "${1}" ]; then
 		_printf "\t%s\n" "${1}"
 	fi
+
+	mptcp_lib_result_fail "${test_name}"
 }
 
 kill_wait()
@@ -255,6 +263,7 @@ make_connection()
 		test_pass
 	else
 		test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})"
+		mptcp_lib_result_print_all_tap
 		exit 1
 	fi
 
@@ -990,4 +999,5 @@ test_subflows_v4_v6_mix
 test_prio
 test_listener
 
+mptcp_lib_result_print_all_tap
 exit ${ret}
-- 
GitLab


From b16b50476714c75ff99dba23b8ee96179197e31e Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Mon, 17 Jul 2023 15:53:30 +0200
Subject: [PATCH 0223/1806] gtp: Set TOS and routing scope independently for
 fib lookups.

There's no reason for setting the RTO_ONLINK flag in ->flowi4_tos as
RT_CONN_FLAGS() does. We can easily set ->flowi4_scope properly
instead. This makes the code more explicit and will allow to convert
->flowi4_tos to dscp_t in the future.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index acb20ad4e37eb..144ec626230d6 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -243,7 +243,8 @@ static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4,
 	fl4->flowi4_oif		= sk->sk_bound_dev_if;
 	fl4->daddr		= daddr;
 	fl4->saddr		= saddr;
-	fl4->flowi4_tos		= RT_CONN_FLAGS(sk);
+	fl4->flowi4_tos		= ip_sock_rt_tos(sk);
+	fl4->flowi4_scope	= ip_sock_rt_scope(sk);
 	fl4->flowi4_proto	= sk->sk_protocol;
 
 	return ip_route_output_key(sock_net(sk), fl4);
-- 
GitLab


From 2d6c85ca3eb8e175e4b5b508b1203b909af5189c Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Mon, 17 Jul 2023 15:53:35 +0200
Subject: [PATCH 0224/1806] dccp: Set TOS and routing scope independently for
 fib lookups.

There's no reason for setting the RTO_ONLINK flag in ->flowi4_tos as
RT_CONN_FLAGS() does. We can easily set ->flowi4_scope properly
instead. This makes the code more explicit and will allow to convert
->flowi4_tos to dscp_t in the future.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index fa8079303cb06..8e919cfe6e233 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -474,7 +474,8 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 		.flowi4_oif = inet_iif(skb),
 		.daddr = iph->saddr,
 		.saddr = iph->daddr,
-		.flowi4_tos = RT_CONN_FLAGS(sk),
+		.flowi4_tos = ip_sock_rt_tos(sk),
+		.flowi4_scope = ip_sock_rt_scope(sk),
 		.flowi4_proto = sk->sk_protocol,
 		.fl4_sport = dccp_hdr(skb)->dccph_dport,
 		.fl4_dport = dccp_hdr(skb)->dccph_sport,
-- 
GitLab


From ba80e20d7f3f87dab3f9f0c0ca66e4b1fcc7be9f Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Mon, 17 Jul 2023 15:53:40 +0200
Subject: [PATCH 0225/1806] sctp: Set TOS and routing scope independently for
 fib lookups.

There's no reason for setting the RTO_ONLINK flag in ->flowi4_tos as
RT_CONN_FLAGS() does. We can easily set ->flowi4_scope properly
instead. This makes the code more explicit and will allow to convert
->flowi4_tos to dscp_t in the future.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 274d07bd774f0..33c0895e101c0 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -435,7 +435,8 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	fl4->fl4_dport = daddr->v4.sin_port;
 	fl4->flowi4_proto = IPPROTO_SCTP;
 	if (asoc) {
-		fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos);
+		fl4->flowi4_tos = RT_TOS(tos);
+		fl4->flowi4_scope = ip_sock_rt_scope(asoc->base.sk);
 		fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
 		fl4->fl4_sport = htons(asoc->base.bind_addr.port);
 	}
-- 
GitLab


From 831deb2976de4458adae4daee56aa6f740ed4acc Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Wed, 19 Jul 2023 09:29:49 +0000
Subject: [PATCH 0226/1806] bpf: consider types listed in reg2btf_ids as
 trusted

The reg2btf_ids array contains a list of types for which we can (and need)
to find a corresponding static BTF id. All the types in the list can be
considered as trusted for purposes of kfuncs.

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230719092952.41202-2-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0b9da95331d79..05123feab3786 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5413,12 +5413,24 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
 	return reg->type == PTR_TO_FLOW_KEYS;
 }
 
+static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
+#ifdef CONFIG_NET
+	[PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
+	[PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	[PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
+#endif
+};
+
 static bool is_trusted_reg(const struct bpf_reg_state *reg)
 {
 	/* A referenced register is always trusted. */
 	if (reg->ref_obj_id)
 		return true;
 
+	/* Types listed in the reg2btf_ids are always trusted */
+	if (reg2btf_ids[base_type(reg->type)])
+		return true;
+
 	/* If a register is not referenced, it is trusted if it has the
 	 * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the
 	 * other type modifiers may be safe, but we elect to take an opt-in
@@ -10052,15 +10064,6 @@ static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env,
 	return true;
 }
 
-
-static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
-#ifdef CONFIG_NET
-	[PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
-	[PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
-	[PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
-#endif
-};
-
 enum kfunc_ptr_arg_type {
 	KF_ARG_PTR_TO_CTX,
 	KF_ARG_PTR_TO_ALLOC_BTF_ID,    /* Allocated object */
-- 
GitLab


From 5ba190c29cf92f157bd63c9909c7050d6dc43df7 Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Wed, 19 Jul 2023 09:29:50 +0000
Subject: [PATCH 0227/1806] bpf: consider CONST_PTR_TO_MAP as trusted pointer
 to struct bpf_map

Add the BTF id of struct bpf_map to the reg2btf_ids array. This makes the
values of the CONST_PTR_TO_MAP type to be considered as trusted by kfuncs.
This, in turn, allows users to execute trusted kfuncs which accept `struct
bpf_map *` arguments from non-tracing programs.

While exporting the btf_bpf_map_id variable, save some bytes by defining
it as BTF_ID_LIST_GLOBAL_SINGLE (which is u32[1]) and not as BTF_ID_LIST
(which is u32[64]).

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230719092952.41202-3-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf_ids.h | 1 +
 kernel/bpf/map_iter.c   | 3 +--
 kernel/bpf/verifier.c   | 1 +
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 00950cc03bff2..a3462a9b8e185 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -267,5 +267,6 @@ MAX_BTF_TRACING_TYPE,
 extern u32 btf_tracing_ids[];
 extern u32 bpf_cgroup_btf_id[];
 extern u32 bpf_local_storage_map_btf_id[];
+extern u32 btf_bpf_map_id[];
 
 #endif
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index d06d3b7150e57..b67996147895a 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -78,8 +78,7 @@ static const struct seq_operations bpf_map_seq_ops = {
 	.show	= bpf_map_seq_show,
 };
 
-BTF_ID_LIST(btf_bpf_map_id)
-BTF_ID(struct, bpf_map)
+BTF_ID_LIST_GLOBAL_SINGLE(btf_bpf_map_id, struct, bpf_map)
 
 static const struct bpf_iter_seq_info bpf_map_seq_info = {
 	.seq_ops		= &bpf_map_seq_ops,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 05123feab3786..803b91135ca04 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5419,6 +5419,7 @@ static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
 	[PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	[PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
 #endif
+	[CONST_PTR_TO_MAP] = btf_bpf_map_id,
 };
 
 static bool is_trusted_reg(const struct bpf_reg_state *reg)
-- 
GitLab


From 9c29804961c1bbf5c879a1879fe5fcac6364736f Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Wed, 19 Jul 2023 09:29:51 +0000
Subject: [PATCH 0228/1806] bpf: make an argument const in the
 bpf_map_sum_elem_count kfunc

We use the map pointer only to read the counter values, no locking
involved, so mark the argument as const.

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230719092952.41202-4-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/map_iter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index b67996147895a..011adb41858e6 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -197,7 +197,7 @@ __diag_push();
 __diag_ignore_all("-Wmissing-prototypes",
 		  "Global functions as their definitions will be in vmlinux BTF");
 
-__bpf_kfunc s64 bpf_map_sum_elem_count(struct bpf_map *map)
+__bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
 {
 	s64 *pcount;
 	s64 ret = 0;
-- 
GitLab


From 72829b1c1f1601015cd7332b968befcf5e636c24 Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Wed, 19 Jul 2023 09:29:52 +0000
Subject: [PATCH 0229/1806] bpf: allow any program to use the
 bpf_map_sum_elem_count kfunc

Register the bpf_map_sum_elem_count func for all programs, and update the
map_ptr subtest of the test_progs test to test the new functionality.

The usage is allowed as long as the pointer to the map is trusted (when
using tracing programs) or is a const pointer to map, as in the following
example:

    struct {
            __uint(type, BPF_MAP_TYPE_HASH);
            ...
    } hash SEC(".maps");

    ...

    static inline int some_bpf_prog(void)
    {
            struct bpf_map *map = (struct bpf_map *)&hash;
            __s64 count;

            count = bpf_map_sum_elem_count(map);

            ...
    }

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230719092952.41202-5-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/map_iter.c                            | 2 +-
 tools/testing/selftests/bpf/progs/map_ptr_kern.c | 5 +++++
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index 011adb41858e6..6fc9dae9edc81 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -226,6 +226,6 @@ static const struct btf_kfunc_id_set bpf_map_iter_kfunc_set = {
 
 static int init_subsystem(void)
 {
-	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_map_iter_kfunc_set);
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_map_iter_kfunc_set);
 }
 late_initcall(init_subsystem);
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index db388f593d0a2..3325da17ec81a 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -103,6 +103,8 @@ struct {
 	__type(value, __u32);
 } m_hash SEC(".maps");
 
+__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym;
+
 static inline int check_hash(void)
 {
 	struct bpf_htab *hash = (struct bpf_htab *)&m_hash;
@@ -115,6 +117,8 @@ static inline int check_hash(void)
 	VERIFY(hash->elem_size == 64);
 
 	VERIFY(hash->count.counter == 0);
+	VERIFY(bpf_map_sum_elem_count(map) == 0);
+
 	for (i = 0; i < HALF_ENTRIES; ++i) {
 		const __u32 key = i;
 		const __u32 val = 1;
@@ -123,6 +127,7 @@ static inline int check_hash(void)
 			return 0;
 	}
 	VERIFY(hash->count.counter == HALF_ENTRIES);
+	VERIFY(bpf_map_sum_elem_count(map) == HALF_ENTRIES);
 
 	return 1;
 }
-- 
GitLab


From 492e797fdab25f2d8eb1b6bb3236f4aac474f878 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Wed, 19 Jul 2023 19:03:30 +0800
Subject: [PATCH 0230/1806] bpf, x86: initialize the variable "first_off" in
 save_args()

As Dan Carpenter reported, the variable "first_off" which is passed to
clean_stack_garbage() in save_args() can be uninitialized, which can
cause runtime warnings with KMEMsan. Therefore, init it with 0.

Fixes: 473e3150e30a ("bpf, x86: allow function arguments up to 12 for TRACING")
Cc: Hao Peng <flyingpeng@tencent.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/bpf/09784025-a812-493f-9829-5e26c8691e07@moroto.mountain/
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Link: https://lore.kernel.org/r/20230719110330.2007949-1-imagedong@tencent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5ab531be56acf..83c4b45dc65f9 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1925,7 +1925,7 @@ static int get_nr_used_regs(const struct btf_func_model *m)
 static void save_args(const struct btf_func_model *m, u8 **prog,
 		      int stack_size, bool for_call_origin)
 {
-	int arg_regs, first_off, nr_regs = 0, nr_stack_slots = 0;
+	int arg_regs, first_off = 0, nr_regs = 0, nr_stack_slots = 0;
 	int i, j;
 
 	/* Store function arguments to stack.
-- 
GitLab


From 63a64a56bc3f77c74085047ee45356ac850da3e8 Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 19 Jul 2023 15:23:58 +0200
Subject: [PATCH 0231/1806] xsk: prepare 'options' in xdp_desc for multi-buffer
 use

Use the 'options' field in xdp_desc as a packet continuity marker. Since
'options' field was unused till now and was expected to be set to 0, the
'eop' descriptor will have it set to 0, while the non-eop descriptors
will have to set it to 1. This ensures legacy applications continue to
work without needing any change for single-buffer packets.

Add helper functions and extend xskq_prod_reserve_desc() to use the
'options' field.

Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-2-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/if_xdp.h |  7 +++++++
 net/xdp/xsk.c               |  8 ++++----
 net/xdp/xsk_queue.h         | 12 +++++++++---
 3 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index a78a8096f4ce6..434f313dc26c7 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -108,4 +108,11 @@ struct xdp_desc {
 
 /* UMEM descriptor is __u64 */
 
+/* Flag indicating that the packet continues with the buffer pointed out by the
+ * next frame in the ring. The end of the packet is signalled by setting this
+ * bit to zero. For single buffer packets, every descriptor has 'options' set
+ * to 0 and this maintains backward compatibility.
+ */
+#define XDP_PKT_CONTD (1 << 0)
+
 #endif /* _LINUX_IF_XDP_H */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 31dca4ecb2c53..914a80cd55d34 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -135,14 +135,14 @@ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
 	return 0;
 }
 
-static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
+static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, u32 flags)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 	u64 addr;
 	int err;
 
 	addr = xp_get_handle(xskb);
-	err = xskq_prod_reserve_desc(xs->rx, addr, len);
+	err = xskq_prod_reserve_desc(xs->rx, addr, len, flags);
 	if (err) {
 		xs->rx_queue_full++;
 		return err;
@@ -189,7 +189,7 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	}
 
 	xsk_copy_xdp(xsk_xdp, xdp, len);
-	err = __xsk_rcv_zc(xs, xsk_xdp, len);
+	err = __xsk_rcv_zc(xs, xsk_xdp, len, 0);
 	if (err) {
 		xsk_buff_free(xsk_xdp);
 		return err;
@@ -259,7 +259,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 
 	if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) {
 		len = xdp->data_end - xdp->data;
-		return __xsk_rcv_zc(xs, xdp, len);
+		return __xsk_rcv_zc(xs, xdp, len, 0);
 	}
 
 	err = __xsk_rcv(xs, xdp);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 6d40a77fccbe9..2f1aacae81af6 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -130,6 +130,11 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
 	return false;
 }
 
+static inline bool xp_unused_options_set(u32 options)
+{
+	return options & ~XDP_PKT_CONTD;
+}
+
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 					    struct xdp_desc *desc)
 {
@@ -141,7 +146,7 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 	if (desc->addr >= pool->addrs_cnt)
 		return false;
 
-	if (desc->options)
+	if (xp_unused_options_set(desc->options))
 		return false;
 	return true;
 }
@@ -158,7 +163,7 @@ static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 	    xp_desc_crosses_non_contig_pg(pool, addr, desc->len))
 		return false;
 
-	if (desc->options)
+	if (xp_unused_options_set(desc->options))
 		return false;
 	return true;
 }
@@ -360,7 +365,7 @@ static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_de
 }
 
 static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
-					 u64 addr, u32 len)
+					 u64 addr, u32 len, u32 flags)
 {
 	struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 	u32 idx;
@@ -372,6 +377,7 @@ static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
 	idx = q->cached_prod++ & q->ring_mask;
 	ring->desc[idx].addr = addr;
 	ring->desc[idx].len = len;
+	ring->desc[idx].options = flags;
 
 	return 0;
 }
-- 
GitLab


From 81470b5c3c6649eef8e5f282cd06793f788ae165 Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 19 Jul 2023 15:23:59 +0200
Subject: [PATCH 0232/1806] xsk: introduce XSK_USE_SG bind flag for xsk socket

As of now xsk core drops any xdp_buff with data size greater than the
xsk frame_size as set by the af_xdp application. With multi-buffer
support introduced in the next patch xsk core can now split those
buffers into multiple descriptors provided the af_xdp application can
handle them. Such capability of the application needs to be independent
of the xdp_prog's frag support capability since there are cases where
even a single xdp_buffer may need to be split into multiple descriptors
owing to a smaller xsk frame size.

For e.g., with NIC rx_buffer size set to 4kB, a 3kB packet will
constitute of a single buffer and so will be sent as such to AF_XDP layer
irrespective of 'xdp.frags' capability of the XDP program. Now if the xsk
frame size is set to 2kB by the AF_XDP application, then the packet will
need to be split into 2 descriptors if AF_XDP application can handle
multi-buffer, else it needs to be dropped.

Applications can now advertise their frag handling capability to xsk core
so that xsk core can decide if it should drop or split xdp_buffs that
exceed xsk frame size. This is done using a new 'XSK_USE_SG' bind flag
for the xdp socket.

Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-3-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xdp_sock.h      | 1 +
 include/uapi/linux/if_xdp.h | 6 ++++++
 net/xdp/xsk.c               | 5 +++--
 3 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index e96a1151ec759..36b0411a0d1b3 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -52,6 +52,7 @@ struct xdp_sock {
 	struct xsk_buff_pool *pool;
 	u16 queue_id;
 	bool zc;
+	bool sg;
 	enum {
 		XSK_READY = 0,
 		XSK_BOUND,
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index 434f313dc26c7..8d48863472b92 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -25,6 +25,12 @@
  * application.
  */
 #define XDP_USE_NEED_WAKEUP (1 << 3)
+/* By setting this option, userspace application indicates that it can
+ * handle multiple descriptors per packet thus enabling AF_XDP to split
+ * multi-buffer XDP frames into multiple Rx descriptors. Without this set
+ * such frames will be dropped.
+ */
+#define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
 #define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 914a80cd55d34..7b709e4e7ec46 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -897,7 +897,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 
 	flags = sxdp->sxdp_flags;
 	if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY |
-		      XDP_USE_NEED_WAKEUP))
+		      XDP_USE_NEED_WAKEUP | XDP_USE_SG))
 		return -EINVAL;
 
 	bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
@@ -929,7 +929,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		struct socket *sock;
 
 		if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY) ||
-		    (flags & XDP_USE_NEED_WAKEUP)) {
+		    (flags & XDP_USE_NEED_WAKEUP) || (flags & XDP_USE_SG)) {
 			/* Cannot specify flags for shared sockets. */
 			err = -EINVAL;
 			goto out_unlock;
@@ -1028,6 +1028,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 
 	xs->dev = dev;
 	xs->zc = xs->umem->zc;
+	xs->sg = !!(flags & XDP_USE_SG);
 	xs->queue_id = qid;
 	xp_add_xsk(xs->pool, xs);
 
-- 
GitLab


From 556444c4e683e73531766d4a577b8b94c42ac160 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 19 Jul 2023 15:24:00 +0200
Subject: [PATCH 0233/1806] xsk: prepare both copy and zero-copy modes to
 co-exist

Currently, __xsk_rcv_zc() is a function that is responsible for
producing AF_XDP Rx descriptors. It is used by both copy and zero-copy
mode. Both of these modes are going to differ when multi-buffer support
is going to be added. ZC will work on a chain of xdp_buff_xsk structs
whereas copy-mode is going to utilize skb_shared_info contents. This
means that ZC-specific changes would affect the copy mode.

Let's modify __xsk_rcv_zc() to work directly on xdp_buff_xsk so the
callsites have to retrieve this from xdp_buff. Also, introduce
xsk_rcv_zc() which will carry all the needed later changes for
supporting multi-buffer on ZC side that do not apply to copy mode.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-4-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/xdp/xsk.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 7b709e4e7ec46..029a092582da4 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -135,9 +135,9 @@ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
 	return 0;
 }
 
-static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, u32 flags)
+static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff_xsk *xskb, u32 len,
+			u32 flags)
 {
-	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 	u64 addr;
 	int err;
 
@@ -152,6 +152,13 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, u32
 	return 0;
 }
 
+static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
+{
+	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+
+	return __xsk_rcv_zc(xs, xskb, len, 0);
+}
+
 static void xsk_copy_xdp(struct xdp_buff *to, struct xdp_buff *from, u32 len)
 {
 	void *from_buf, *to_buf;
@@ -172,6 +179,7 @@ static void xsk_copy_xdp(struct xdp_buff *to, struct xdp_buff *from, u32 len)
 
 static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
+	struct xdp_buff_xsk *xskb;
 	struct xdp_buff *xsk_xdp;
 	int err;
 	u32 len;
@@ -189,7 +197,8 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	}
 
 	xsk_copy_xdp(xsk_xdp, xdp, len);
-	err = __xsk_rcv_zc(xs, xsk_xdp, len, 0);
+	xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp);
+	err = __xsk_rcv_zc(xs, xskb, len, 0);
 	if (err) {
 		xsk_buff_free(xsk_xdp);
 		return err;
@@ -259,7 +268,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 
 	if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) {
 		len = xdp->data_end - xdp->data;
-		return __xsk_rcv_zc(xs, xdp, len, 0);
+		return xsk_rcv_zc(xs, xdp, len);
 	}
 
 	err = __xsk_rcv(xs, xdp);
-- 
GitLab


From faa91b839b09b15d6f9655fc866fa433bb65454c Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 19 Jul 2023 15:24:01 +0200
Subject: [PATCH 0234/1806] xsk: move xdp_buff's data length check to
 xsk_rcv_check

If the data in xdp_buff exceeds the xsk frame length, the packet needs
to be dropped. This check is currently being done in __xsk_rcv(). Move
the described logic to xsk_rcv_check() so that such a xdp_buff will
only be dropped if the application does not support multi-buffer
(absence of XDP_USE_SG bind flag). This is applicable for all cases:
copy mode, zero copy mode as well as skb mode.

Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-5-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/xdp/xsk.c | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 029a092582da4..a968ac506f4a1 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -177,18 +177,11 @@ static void xsk_copy_xdp(struct xdp_buff *to, struct xdp_buff *from, u32 len)
 	memcpy(to_buf, from_buf, len + metalen);
 }
 
-static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
 	struct xdp_buff_xsk *xskb;
 	struct xdp_buff *xsk_xdp;
 	int err;
-	u32 len;
-
-	len = xdp->data_end - xdp->data;
-	if (len > xsk_pool_get_rx_frame_size(xs->pool)) {
-		xs->rx_dropped++;
-		return -ENOSPC;
-	}
 
 	xsk_xdp = xsk_buff_alloc(xs->pool);
 	if (!xsk_xdp) {
@@ -224,7 +217,7 @@ static bool xsk_is_bound(struct xdp_sock *xs)
 	return false;
 }
 
-static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp)
+static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
 	if (!xsk_is_bound(xs))
 		return -ENXIO;
@@ -232,6 +225,11 @@ static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp)
 	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
 		return -EINVAL;
 
+	if (len > xsk_pool_get_rx_frame_size(xs->pool)) {
+		xs->rx_dropped++;
+		return -ENOSPC;
+	}
+
 	sk_mark_napi_id_once_xdp(&xs->sk, xdp);
 	return 0;
 }
@@ -245,12 +243,13 @@ static void xsk_flush(struct xdp_sock *xs)
 
 int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
+	u32 len = xdp_get_buff_len(xdp);
 	int err;
 
 	spin_lock_bh(&xs->rx_lock);
-	err = xsk_rcv_check(xs, xdp);
+	err = xsk_rcv_check(xs, xdp, len);
 	if (!err) {
-		err = __xsk_rcv(xs, xdp);
+		err = __xsk_rcv(xs, xdp, len);
 		xsk_flush(xs);
 	}
 	spin_unlock_bh(&xs->rx_lock);
@@ -259,10 +258,10 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 
 static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
+	u32 len = xdp_get_buff_len(xdp);
 	int err;
-	u32 len;
 
-	err = xsk_rcv_check(xs, xdp);
+	err = xsk_rcv_check(xs, xdp, len);
 	if (err)
 		return err;
 
@@ -271,7 +270,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 		return xsk_rcv_zc(xs, xdp, len);
 	}
 
-	err = __xsk_rcv(xs, xdp);
+	err = __xsk_rcv(xs, xdp, len);
 	if (!err)
 		xdp_return_buff(xdp);
 	return err;
-- 
GitLab


From 804627751b4281dd95148e7564759145da67855e Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 19 Jul 2023 15:24:02 +0200
Subject: [PATCH 0235/1806] xsk: add support for AF_XDP multi-buffer on Rx path

Add multi-buffer support for AF_XDP by extending the XDP multi-buffer
support to be reflected in user-space when a packet is redirected to
an AF_XDP socket.

In the XDP implementation, the NIC driver builds the xdp_buff from the
first frag of the packet and adds any subsequent frags in the skb_shinfo
area of the xdp_buff. In AF_XDP core, XDP buffers are allocated from
xdp_sock's pool and data is copied from the driver's xdp_buff and frags.

Once an allocated XDP buffer is full and there is still data to be
copied, the 'XDP_PKT_CONTD' flag in'options' field of the corresponding
xdp ring descriptor is set and passed to the application. When application
sees the aforementioned flag set it knows there is pending data for this
packet that will be carried in the following descriptors. If there is no
more data to be copied, the flag in 'options' field is cleared for that
descriptor signalling EOP to the application.

If application reads a batch of descriptors using for example the libxdp
interfaces, it is not guaranteed that the batch will end with a full
packet. It might end in the middle of a packet and the rest of the frames
of that packet will arrive at the beginning of the next batch.

AF_XDP ensures that only a complete packet (along with all its frags) is
sent to application.

Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-6-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/core/filter.c |   7 +--
 net/xdp/xsk.c     | 110 ++++++++++++++++++++++++++++++++++++----------
 2 files changed, 88 insertions(+), 29 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 06ba0e56e3693..b4410dc841a0e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4345,13 +4345,8 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	enum bpf_map_type map_type = ri->map_type;
 
-	if (map_type == BPF_MAP_TYPE_XSKMAP) {
-		/* XDP_REDIRECT is not supported AF_XDP yet. */
-		if (unlikely(xdp_buff_has_frags(xdp)))
-			return -EOPNOTSUPP;
-
+	if (map_type == BPF_MAP_TYPE_XSKMAP)
 		return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog);
-	}
 
 	return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp),
 				       xdp_prog);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index a968ac506f4a1..01c134b1186e5 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -159,43 +159,107 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	return __xsk_rcv_zc(xs, xskb, len, 0);
 }
 
-static void xsk_copy_xdp(struct xdp_buff *to, struct xdp_buff *from, u32 len)
+static void *xsk_copy_xdp_start(struct xdp_buff *from)
 {
-	void *from_buf, *to_buf;
-	u32 metalen;
+	if (unlikely(xdp_data_meta_unsupported(from)))
+		return from->data;
+	else
+		return from->data_meta;
+}
 
-	if (unlikely(xdp_data_meta_unsupported(from))) {
-		from_buf = from->data;
-		to_buf = to->data;
-		metalen = 0;
-	} else {
-		from_buf = from->data_meta;
-		metalen = from->data - from->data_meta;
-		to_buf = to->data - metalen;
-	}
+static u32 xsk_copy_xdp(void *to, void **from, u32 to_len,
+			u32 *from_len, skb_frag_t **frag, u32 rem)
+{
+	u32 copied = 0;
+
+	while (1) {
+		u32 copy_len = min_t(u32, *from_len, to_len);
+
+		memcpy(to, *from, copy_len);
+		copied += copy_len;
+		if (rem == copied)
+			return copied;
+
+		if (*from_len == copy_len) {
+			*from = skb_frag_address(*frag);
+			*from_len = skb_frag_size((*frag)++);
+		} else {
+			*from += copy_len;
+			*from_len -= copy_len;
+		}
+		if (to_len == copy_len)
+			return copied;
 
-	memcpy(to_buf, from_buf, len + metalen);
+		to_len -= copy_len;
+		to += copy_len;
+	}
 }
 
 static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
+	u32 frame_size = xsk_pool_get_rx_frame_size(xs->pool);
+	void *copy_from = xsk_copy_xdp_start(xdp), *copy_to;
+	u32 from_len, meta_len, rem, num_desc;
 	struct xdp_buff_xsk *xskb;
 	struct xdp_buff *xsk_xdp;
-	int err;
+	skb_frag_t *frag;
+
+	from_len = xdp->data_end - copy_from;
+	meta_len = xdp->data - copy_from;
+	rem = len + meta_len;
+
+	if (len <= frame_size && !xdp_buff_has_frags(xdp)) {
+		int err;
 
-	xsk_xdp = xsk_buff_alloc(xs->pool);
-	if (!xsk_xdp) {
+		xsk_xdp = xsk_buff_alloc(xs->pool);
+		if (!xsk_xdp) {
+			xs->rx_dropped++;
+			return -ENOMEM;
+		}
+		memcpy(xsk_xdp->data - meta_len, copy_from, rem);
+		xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp);
+		err = __xsk_rcv_zc(xs, xskb, len, 0);
+		if (err) {
+			xsk_buff_free(xsk_xdp);
+			return err;
+		}
+
+		return 0;
+	}
+
+	num_desc = (len - 1) / frame_size + 1;
+
+	if (!xsk_buff_can_alloc(xs->pool, num_desc)) {
 		xs->rx_dropped++;
 		return -ENOMEM;
 	}
+	if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) {
+		xs->rx_queue_full++;
+		return -ENOBUFS;
+	}
 
-	xsk_copy_xdp(xsk_xdp, xdp, len);
-	xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp);
-	err = __xsk_rcv_zc(xs, xskb, len, 0);
-	if (err) {
-		xsk_buff_free(xsk_xdp);
-		return err;
+	if (xdp_buff_has_frags(xdp)) {
+		struct skb_shared_info *sinfo;
+
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		frag =  &sinfo->frags[0];
 	}
+
+	do {
+		u32 to_len = frame_size + meta_len;
+		u32 copied;
+
+		xsk_xdp = xsk_buff_alloc(xs->pool);
+		copy_to = xsk_xdp->data - meta_len;
+
+		copied = xsk_copy_xdp(copy_to, &copy_from, to_len, &from_len, &frag, rem);
+		rem -= copied;
+
+		xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp);
+		__xsk_rcv_zc(xs, xskb, copied - meta_len, rem ? XDP_PKT_CONTD : 0);
+		meta_len = 0;
+	} while (rem);
+
 	return 0;
 }
 
@@ -225,7 +289,7 @@ static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
 		return -EINVAL;
 
-	if (len > xsk_pool_get_rx_frame_size(xs->pool)) {
+	if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) {
 		xs->rx_dropped++;
 		return -ENOSPC;
 	}
-- 
GitLab


From b7f72a30e9ac2555b05afc6cfddc9dbc98e1eb8d Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 19 Jul 2023 15:24:03 +0200
Subject: [PATCH 0236/1806] xsk: introduce wrappers and helpers for supporting
 multi-buffer in Tx path

In Tx path, xsk core reserves space for each desc to be transmitted in
the completion queue and it's address contained in it is stored in the
skb destructor arg. After successful transmission the skb destructor
submits the addr marking completion.

To handle multiple descriptors per packet, now along with reserving
space for each descriptor, the corresponding address is also stored in
completion queue. The number of pending descriptors are stored in skb
destructor arg and is used by the skb destructor to update completions.

Introduce 'skb' in xdp_sock to store a partially built packet when
__xsk_generic_xmit() must return before it sees the EOP descriptor for
the current packet so that packet building can resume in next call of
__xsk_generic_xmit().

Helper functions are introduced to set and get the pending descriptors
in the skb destructor arg. Also, wrappers are introduced for storing
descriptor addresses, submitting and cancelling (for unsuccessful
transmissions) the number of completions.

Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-7-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xdp_sock.h |  6 ++++
 net/xdp/xsk.c          | 74 ++++++++++++++++++++++++++++++------------
 net/xdp/xsk_queue.h    | 19 ++++-------
 3 files changed, 67 insertions(+), 32 deletions(-)

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 36b0411a0d1b3..1617af3801620 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -68,6 +68,12 @@ struct xdp_sock {
 	u64 rx_dropped;
 	u64 rx_queue_full;
 
+	/* When __xsk_generic_xmit() must return before it sees the EOP descriptor for the current
+	 * packet, the partially built skb is saved here so that packet building can resume in next
+	 * call of __xsk_generic_xmit().
+	 */
+	struct sk_buff *skb;
+
 	struct list_head map_list;
 	/* Protects map_list */
 	spinlock_t map_list_lock;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 01c134b1186e5..ed7f863000876 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -480,19 +480,65 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 	return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
 }
 
-static void xsk_destruct_skb(struct sk_buff *skb)
+static int xsk_cq_reserve_addr_locked(struct xdp_sock *xs, u64 addr)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&xs->pool->cq_lock, flags);
+	ret = xskq_prod_reserve_addr(xs->pool->cq, addr);
+	spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+
+	return ret;
+}
+
+static void xsk_cq_submit_locked(struct xdp_sock *xs, u32 n)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&xs->pool->cq_lock, flags);
+	xskq_prod_submit_n(xs->pool->cq, n);
+	spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+}
+
+static void xsk_cq_cancel_locked(struct xdp_sock *xs, u32 n)
 {
-	u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg;
-	struct xdp_sock *xs = xdp_sk(skb->sk);
 	unsigned long flags;
 
 	spin_lock_irqsave(&xs->pool->cq_lock, flags);
-	xskq_prod_submit_addr(xs->pool->cq, addr);
+	xskq_prod_cancel_n(xs->pool->cq, n);
 	spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+}
+
+static u32 xsk_get_num_desc(struct sk_buff *skb)
+{
+	return skb ? (long)skb_shinfo(skb)->destructor_arg : 0;
+}
 
+static void xsk_destruct_skb(struct sk_buff *skb)
+{
+	xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb));
 	sock_wfree(skb);
 }
 
+static void xsk_set_destructor_arg(struct sk_buff *skb)
+{
+	long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1;
+
+	skb_shinfo(skb)->destructor_arg = (void *)num;
+}
+
+static void xsk_consume_skb(struct sk_buff *skb)
+{
+	struct xdp_sock *xs = xdp_sk(skb->sk);
+
+	skb->destructor = sock_wfree;
+	xsk_cq_cancel_locked(xs, xsk_get_num_desc(skb));
+	/* Free skb without triggering the perf drop trace */
+	consume_skb(skb);
+	xs->skb = NULL;
+}
+
 static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 					      struct xdp_desc *desc)
 {
@@ -578,8 +624,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 	skb->dev = dev;
 	skb->priority = xs->sk.sk_priority;
 	skb->mark = xs->sk.sk_mark;
-	skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr;
 	skb->destructor = xsk_destruct_skb;
+	xsk_set_destructor_arg(skb);
 
 	return skb;
 }
@@ -591,7 +637,6 @@ static int __xsk_generic_xmit(struct sock *sk)
 	bool sent_frame = false;
 	struct xdp_desc desc;
 	struct sk_buff *skb;
-	unsigned long flags;
 	int err = 0;
 
 	mutex_lock(&xs->mutex);
@@ -616,31 +661,20 @@ static int __xsk_generic_xmit(struct sock *sk)
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
-		spin_lock_irqsave(&xs->pool->cq_lock, flags);
-		if (xskq_prod_reserve(xs->pool->cq)) {
-			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+		if (xsk_cq_reserve_addr_locked(xs, desc.addr))
 			goto out;
-		}
-		spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 
 		skb = xsk_build_skb(xs, &desc);
 		if (IS_ERR(skb)) {
 			err = PTR_ERR(skb);
-			spin_lock_irqsave(&xs->pool->cq_lock, flags);
-			xskq_prod_cancel(xs->pool->cq);
-			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+			xsk_cq_cancel_locked(xs, 1);
 			goto out;
 		}
 
 		err = __dev_direct_xmit(skb, xs->queue_id);
 		if  (err == NETDEV_TX_BUSY) {
 			/* Tell user-space to retry the send */
-			skb->destructor = sock_wfree;
-			spin_lock_irqsave(&xs->pool->cq_lock, flags);
-			xskq_prod_cancel(xs->pool->cq);
-			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
-			/* Free skb without triggering the perf drop trace */
-			consume_skb(skb);
+			xsk_consume_skb(skb);
 			err = -EAGAIN;
 			goto out;
 		}
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 2f1aacae81af6..423ad7368fa29 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -297,6 +297,11 @@ static inline void xskq_cons_release(struct xsk_queue *q)
 	q->cached_cons++;
 }
 
+static inline void xskq_cons_cancel_n(struct xsk_queue *q, u32 cnt)
+{
+	q->cached_cons -= cnt;
+}
+
 static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
 {
 	/* No barriers needed since data is not accessed */
@@ -324,9 +329,9 @@ static inline bool xskq_prod_is_full(struct xsk_queue *q)
 	return xskq_prod_nb_free(q, 1) ? false : true;
 }
 
-static inline void xskq_prod_cancel(struct xsk_queue *q)
+static inline void xskq_prod_cancel_n(struct xsk_queue *q, u32 cnt)
 {
-	q->cached_prod--;
+	q->cached_prod -= cnt;
 }
 
 static inline int xskq_prod_reserve(struct xsk_queue *q)
@@ -392,16 +397,6 @@ static inline void xskq_prod_submit(struct xsk_queue *q)
 	__xskq_prod_submit(q, q->cached_prod);
 }
 
-static inline void xskq_prod_submit_addr(struct xsk_queue *q, u64 addr)
-{
-	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
-	u32 idx = q->ring->producer;
-
-	ring->desc[idx++ & q->ring_mask] = addr;
-
-	__xskq_prod_submit(q, idx);
-}
-
 static inline void xskq_prod_submit_n(struct xsk_queue *q, u32 nb_entries)
 {
 	__xskq_prod_submit(q, q->ring->producer + nb_entries);
-- 
GitLab


From 1b725b0c8163cfd2d9ab22057df46b487981cfea Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 19 Jul 2023 15:24:04 +0200
Subject: [PATCH 0237/1806] xsk: allow core/drivers to test EOP bit

Drivers are used to check for EOP bit whereas AF_XDP operates on
inverted logic - user space indicates that current frag is not the last
one and packet continues. For AF_XDP core needs, add xp_mb_desc() that
will simply test XDP_PKT_CONTD from xdp_desc::options, but in order to
preserve drivers default behavior, introduce an interface for ZC drivers
that will negate xp_mb_desc() result and therefore make it easier to
test EOP bit from during production of HW Tx descriptors.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-8-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xdp_sock_drv.h  | 10 ++++++++++
 include/net/xsk_buff_pool.h |  5 +++++
 2 files changed, 15 insertions(+)

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index c243f906ebed4..0d34cdb5567d4 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -89,6 +89,11 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 	return xp_alloc(pool);
 }
 
+static inline bool xsk_is_eop_desc(struct xdp_desc *desc)
+{
+	return !xp_mb_desc(desc);
+}
+
 /* Returns as many entries as possible up to max. 0 <= N <= max. */
 static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
 {
@@ -241,6 +246,11 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 	return NULL;
 }
 
+static inline bool xsk_is_eop_desc(struct xdp_desc *desc)
+{
+	return false;
+}
+
 static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
 {
 	return 0;
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index a8d7b8a3688a6..4dcca163e076e 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -184,6 +184,11 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool,
 	       !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK);
 }
 
+static inline bool xp_mb_desc(struct xdp_desc *desc)
+{
+	return desc->options & XDP_PKT_CONTD;
+}
+
 static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr)
 {
 	return addr & pool->chunk_mask;
-- 
GitLab


From cf24f5a5feeaae34c1a34d1e04f8ac697290427a Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 19 Jul 2023 15:24:05 +0200
Subject: [PATCH 0238/1806] xsk: add support for AF_XDP multi-buffer on Tx path

For transmitting an AF_XDP packet, allocate skb while processing the
first desc and copy data to it. The 'XDP_PKT_CONTD' flag in 'options'
field of the desc indicates the EOP status of the packet. If the current
desc is not EOP, store the skb, release the current desc and go
on to read the next descs.

Allocate a page for each subsequent desc, copy data to it and add it as
a frag in the skb stored in xsk. On processing EOP, transmit the skb
with frags. Addresses contained in descs have been already queued in
consumer queue and skb destructor updated the completion count.

On transmit failure cancel the releases, clear the descs from the
completion queue and consume the skb for retrying packet transmission.

For any invalid descriptor (invalid length/address/options) in the middle
of a packet, all pending descriptors will be dropped by xsk core along
with the invalid one and the next descriptor is treated as the start of
a new packet.

Maximum supported frames for a packet is MAX_SKB_FRAGS + 1. If it is
exceeded, all descriptors accumulated so far are dropped.

Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-9-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/xdp/xsk.c       | 120 +++++++++++++++++++++++++++++++++-----------
 net/xdp/xsk_queue.h |  13 +++--
 2 files changed, 100 insertions(+), 33 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index ed7f863000876..ba755fed37507 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -393,7 +393,8 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
 	rcu_read_lock();
 	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		if (!xskq_cons_peek_desc(xs->tx, desc, pool)) {
-			xs->tx->queue_empty_descs++;
+			if (xskq_has_descs(xs->tx))
+				xskq_cons_release(xs->tx);
 			continue;
 		}
 
@@ -539,24 +540,32 @@ static void xsk_consume_skb(struct sk_buff *skb)
 	xs->skb = NULL;
 }
 
+static void xsk_drop_skb(struct sk_buff *skb)
+{
+	xdp_sk(skb->sk)->tx->invalid_descs += xsk_get_num_desc(skb);
+	xsk_consume_skb(skb);
+}
+
 static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 					      struct xdp_desc *desc)
 {
 	struct xsk_buff_pool *pool = xs->pool;
 	u32 hr, len, ts, offset, copy, copied;
-	struct sk_buff *skb;
+	struct sk_buff *skb = xs->skb;
 	struct page *page;
 	void *buffer;
 	int err, i;
 	u64 addr;
 
-	hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
+	if (!skb) {
+		hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
 
-	skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err);
-	if (unlikely(!skb))
-		return ERR_PTR(err);
+		skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err);
+		if (unlikely(!skb))
+			return ERR_PTR(err);
 
-	skb_reserve(skb, hr);
+		skb_reserve(skb, hr);
+	}
 
 	addr = desc->addr;
 	len = desc->len;
@@ -566,7 +575,10 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 	offset = offset_in_page(buffer);
 	addr = buffer - pool->addrs;
 
-	for (copied = 0, i = 0; copied < len; i++) {
+	for (copied = 0, i = skb_shinfo(skb)->nr_frags; copied < len; i++) {
+		if (unlikely(i >= MAX_SKB_FRAGS))
+			return ERR_PTR(-EFAULT);
+
 		page = pool->umem->pgs[addr >> PAGE_SHIFT];
 		get_page(page);
 
@@ -591,33 +603,56 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				     struct xdp_desc *desc)
 {
 	struct net_device *dev = xs->dev;
-	struct sk_buff *skb;
+	struct sk_buff *skb = xs->skb;
+	int err;
 
 	if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
 		skb = xsk_build_skb_zerocopy(xs, desc);
-		if (IS_ERR(skb))
-			return skb;
+		if (IS_ERR(skb)) {
+			err = PTR_ERR(skb);
+			goto free_err;
+		}
 	} else {
 		u32 hr, tr, len;
 		void *buffer;
-		int err;
 
-		hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
-		tr = dev->needed_tailroom;
+		buffer = xsk_buff_raw_get_data(xs->pool, desc->addr);
 		len = desc->len;
 
-		skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
-		if (unlikely(!skb))
-			return ERR_PTR(err);
+		if (!skb) {
+			hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
+			tr = dev->needed_tailroom;
+			skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
+			if (unlikely(!skb))
+				goto free_err;
 
-		skb_reserve(skb, hr);
-		skb_put(skb, len);
+			skb_reserve(skb, hr);
+			skb_put(skb, len);
 
-		buffer = xsk_buff_raw_get_data(xs->pool, desc->addr);
-		err = skb_store_bits(skb, 0, buffer, len);
-		if (unlikely(err)) {
-			kfree_skb(skb);
-			return ERR_PTR(err);
+			err = skb_store_bits(skb, 0, buffer, len);
+			if (unlikely(err))
+				goto free_err;
+		} else {
+			int nr_frags = skb_shinfo(skb)->nr_frags;
+			struct page *page;
+			u8 *vaddr;
+
+			if (unlikely(nr_frags == (MAX_SKB_FRAGS - 1) && xp_mb_desc(desc))) {
+				err = -EFAULT;
+				goto free_err;
+			}
+
+			page = alloc_page(xs->sk.sk_allocation);
+			if (unlikely(!page)) {
+				err = -EAGAIN;
+				goto free_err;
+			}
+
+			vaddr = kmap_local_page(page);
+			memcpy(vaddr, buffer, len);
+			kunmap_local(vaddr);
+
+			skb_add_rx_frag(skb, nr_frags, page, 0, len, 0);
 		}
 	}
 
@@ -628,6 +663,17 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 	xsk_set_destructor_arg(skb);
 
 	return skb;
+
+free_err:
+	if (err == -EAGAIN) {
+		xsk_cq_cancel_locked(xs, 1);
+	} else {
+		xsk_set_destructor_arg(skb);
+		xsk_drop_skb(skb);
+		xskq_cons_release(xs->tx);
+	}
+
+	return ERR_PTR(err);
 }
 
 static int __xsk_generic_xmit(struct sock *sk)
@@ -667,30 +713,45 @@ static int __xsk_generic_xmit(struct sock *sk)
 		skb = xsk_build_skb(xs, &desc);
 		if (IS_ERR(skb)) {
 			err = PTR_ERR(skb);
-			xsk_cq_cancel_locked(xs, 1);
-			goto out;
+			if (err == -EAGAIN)
+				goto out;
+			err = 0;
+			continue;
+		}
+
+		xskq_cons_release(xs->tx);
+
+		if (xp_mb_desc(&desc)) {
+			xs->skb = skb;
+			continue;
 		}
 
 		err = __dev_direct_xmit(skb, xs->queue_id);
 		if  (err == NETDEV_TX_BUSY) {
 			/* Tell user-space to retry the send */
+			xskq_cons_cancel_n(xs->tx, xsk_get_num_desc(skb));
 			xsk_consume_skb(skb);
 			err = -EAGAIN;
 			goto out;
 		}
 
-		xskq_cons_release(xs->tx);
 		/* Ignore NET_XMIT_CN as packet might have been sent */
 		if (err == NET_XMIT_DROP) {
 			/* SKB completed but not sent */
 			err = -EBUSY;
+			xs->skb = NULL;
 			goto out;
 		}
 
 		sent_frame = true;
+		xs->skb = NULL;
 	}
 
-	xs->tx->queue_empty_descs++;
+	if (xskq_has_descs(xs->tx)) {
+		if (xs->skb)
+			xsk_drop_skb(xs->skb);
+		xskq_cons_release(xs->tx);
+	}
 
 out:
 	if (sent_frame)
@@ -940,6 +1001,9 @@ static int xsk_release(struct socket *sock)
 
 	net = sock_net(sk);
 
+	if (xs->skb)
+		xsk_drop_skb(xs->skb);
+
 	mutex_lock(&net->xdp.lock);
 	sk_del_node_init_rcu(sk);
 	mutex_unlock(&net->xdp.lock);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 423ad7368fa29..5752c9fd8ce77 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -175,6 +175,11 @@ static inline bool xp_validate_desc(struct xsk_buff_pool *pool,
 		xp_aligned_validate_desc(pool, desc);
 }
 
+static inline bool xskq_has_descs(struct xsk_queue *q)
+{
+	return q->cached_cons != q->cached_prod;
+}
+
 static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
 					   struct xdp_desc *d,
 					   struct xsk_buff_pool *pool)
@@ -190,17 +195,15 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q,
 				       struct xdp_desc *desc,
 				       struct xsk_buff_pool *pool)
 {
-	while (q->cached_cons != q->cached_prod) {
+	if (q->cached_cons != q->cached_prod) {
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 		u32 idx = q->cached_cons & q->ring_mask;
 
 		*desc = ring->desc[idx];
-		if (xskq_cons_is_valid_desc(q, desc, pool))
-			return true;
-
-		q->cached_cons++;
+		return xskq_cons_is_valid_desc(q, desc, pool);
 	}
 
+	q->queue_empty_descs++;
 	return false;
 }
 
-- 
GitLab


From 07428da9e25a5dfae7252cd554c90557f9086a73 Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 19 Jul 2023 15:24:06 +0200
Subject: [PATCH 0239/1806] xsk: discard zero length descriptors in Tx path

Descriptors with zero length are not supported by many NICs. To preserve
uniform behavior discard any zero length desc as invvalid desc.

Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-10-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/xdp/xsk_queue.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 5752c9fd8ce77..bac32027f8654 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -140,6 +140,9 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 {
 	u64 offset = desc->addr & (pool->chunk_size - 1);
 
+	if (!desc->len)
+		return false;
+
 	if (offset + desc->len > pool->chunk_size)
 		return false;
 
@@ -156,6 +159,9 @@ static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 {
 	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr);
 
+	if (!desc->len)
+		return false;
+
 	if (desc->len > pool->chunk_size)
 		return false;
 
-- 
GitLab


From 13ce2daa259a3bfbc9a5aeeee8b9a87058703731 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 19 Jul 2023 15:24:07 +0200
Subject: [PATCH 0240/1806] xsk: add new netlink attribute dedicated for ZC max
 frags

Introduce new netlink attribute NETDEV_A_DEV_XDP_ZC_MAX_SEGS that will
carry maximum fragments that underlying ZC driver is able to handle on
TX side. It is going to be included in netlink response only when driver
supports ZC. Any value higher than 1 implies multi-buffer ZC support on
underlying device.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-11-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 6 ++++++
 include/linux/netdevice.h               | 1 +
 include/uapi/linux/netdev.h             | 1 +
 net/core/dev.c                          | 1 +
 net/core/netdev-genl.c                  | 8 ++++++++
 tools/include/uapi/linux/netdev.h       | 1 +
 tools/lib/bpf/libbpf.h                  | 3 ++-
 tools/lib/bpf/netlink.c                 | 5 +++++
 8 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index b99e7ffef7a15..e41015310a6e3 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -62,6 +62,12 @@ attribute-sets:
         type: u64
         enum: xdp-act
         enum-as-flags: true
+      -
+        name: xdp_zc_max_segs
+        doc: max fragment count supported by ZC driver
+        type: u32
+        checks:
+          min: 1
 
 operations:
   list:
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b828c7a75be20..b12477ea4032b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2250,6 +2250,7 @@ struct net_device {
 #define GRO_MAX_SIZE		(8 * 65535u)
 	unsigned int		gro_max_size;
 	unsigned int		gro_ipv4_max_size;
+	unsigned int		xdp_zc_max_segs;
 	rx_handler_func_t __rcu	*rx_handler;
 	void __rcu		*rx_handler_data;
 
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 639524b59930b..bf71698a1e82a 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -41,6 +41,7 @@ enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
+	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
diff --git a/net/core/dev.c b/net/core/dev.c
index d6e1b786c5c52..dd4f114a7cbfe 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10613,6 +10613,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev_net_set(dev, &init_net);
 
 	dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
+	dev->xdp_zc_max_segs = 1;
 	dev->gso_max_segs = GSO_MAX_SEGS;
 	dev->gro_max_size = GRO_LEGACY_MAX_SIZE;
 	dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE;
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index a4270fafdf119..65ef4867fc495 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -25,6 +25,14 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
 		return -EINVAL;
 	}
 
+	if (netdev->xdp_features & NETDEV_XDP_ACT_XSK_ZEROCOPY) {
+		if (nla_put_u32(rsp, NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
+				netdev->xdp_zc_max_segs)) {
+			genlmsg_cancel(rsp, hdr);
+			return -EINVAL;
+		}
+	}
+
 	genlmsg_end(rsp, hdr);
 
 	return 0;
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 639524b59930b..bf71698a1e82a 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -41,6 +41,7 @@ enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
+	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 10642ad69d763..674e5788eb108 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1105,9 +1105,10 @@ struct bpf_xdp_query_opts {
 	__u32 skb_prog_id;	/* output */
 	__u8 attach_mode;	/* output */
 	__u64 feature_flags;	/* output */
+	__u32 xdp_zc_max_segs;	/* output */
 	size_t :0;
 };
-#define bpf_xdp_query_opts__last_field feature_flags
+#define bpf_xdp_query_opts__last_field xdp_zc_max_segs
 
 LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags,
 			      const struct bpf_xdp_attach_opts *opts);
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 84dd5fa149058..090bcf6e3b3d5 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -45,6 +45,7 @@ struct xdp_id_md {
 
 struct xdp_features_md {
 	int ifindex;
+	__u32 xdp_zc_max_segs;
 	__u64 flags;
 };
 
@@ -421,6 +422,9 @@ static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
 		return NL_CONT;
 
 	md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]);
+	if (tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS])
+		md->xdp_zc_max_segs =
+			libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS]);
 	return NL_DONE;
 }
 
@@ -493,6 +497,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
 		return libbpf_err(err);
 
 	opts->feature_flags = md.flags;
+	opts->xdp_zc_max_segs = md.xdp_zc_max_segs;
 
 skip_feature_flags:
 	return 0;
-- 
GitLab


From 24ea50127ecf0efe819c1f6230add27abc6ca9d9 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 19 Jul 2023 15:24:08 +0200
Subject: [PATCH 0241/1806] xsk: support mbuf on ZC RX

Given that skb_shared_info relies on skb_frag_t, in order to support
xskb chaining, introduce xdp_buff_xsk::xskb_list_node and
xsk_buff_pool::xskb_list.

This is needed so ZC drivers can add frags as xskb nodes which will make
it possible to handle it both when producing AF_XDP Rx descriptors as
well as freeing/recycling all the frags that a single frame carries.

Speaking of latter, update xsk_buff_free() to take care of list nodes.
For the former (adding as frags), introduce xsk_buff_add_frag() for ZC
drivers usage that is going to be used to add a frag to xskb list from
pool.

xsk_buff_get_frag() will be utilized by XDP_TX and, on contrary, will
return xdp_buff.

One of the previous patches added a wrapper for ZC Rx so implement xskb
list walk and production of Rx descriptors there.

On bind() path, bail out if socket wants to use ZC multi-buffer but
underlying netdev does not support it.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-12-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xdp_sock_drv.h  | 44 +++++++++++++++++++++++++++++++++++++
 include/net/xsk_buff_pool.h |  2 ++
 net/xdp/xsk.c               | 26 +++++++++++++++++++++-
 net/xdp/xsk_buff_pool.c     |  7 ++++++
 4 files changed, 78 insertions(+), 1 deletion(-)

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 0d34cdb5567d4..1f6fc8c7a84c6 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -108,10 +108,45 @@ static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
 static inline void xsk_buff_free(struct xdp_buff *xdp)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+	struct list_head *xskb_list = &xskb->pool->xskb_list;
+	struct xdp_buff_xsk *pos, *tmp;
 
+	if (likely(!xdp_buff_has_frags(xdp)))
+		goto out;
+
+	list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
+		list_del(&pos->xskb_list_node);
+		xp_free(pos);
+	}
+
+	xdp_get_shared_info_from_buff(xdp)->nr_frags = 0;
+out:
 	xp_free(xskb);
 }
 
+static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
+{
+	struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp);
+
+	list_add_tail(&frag->xskb_list_node, &frag->pool->xskb_list);
+}
+
+static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
+{
+	struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
+	struct xdp_buff *ret = NULL;
+	struct xdp_buff_xsk *frag;
+
+	frag = list_first_entry_or_null(&xskb->pool->xskb_list,
+					struct xdp_buff_xsk, xskb_list_node);
+	if (frag) {
+		list_del(&frag->xskb_list_node);
+		ret = &frag->xdp;
+	}
+
+	return ret;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
 	xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
@@ -265,6 +300,15 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 {
 }
 
+static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
+{
+}
+
+static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
+{
+	return NULL;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
 }
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 4dcca163e076e..b0bdff26fc882 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -29,6 +29,7 @@ struct xdp_buff_xsk {
 	struct xsk_buff_pool *pool;
 	u64 orig_addr;
 	struct list_head free_list_node;
+	struct list_head xskb_list_node;
 };
 
 #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
@@ -54,6 +55,7 @@ struct xsk_buff_pool {
 	struct xdp_umem *umem;
 	struct work_struct work;
 	struct list_head free_list;
+	struct list_head xskb_list;
 	u32 heads_cnt;
 	u16 queue_id;
 
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index ba755fed37507..4f1e0599146e2 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -155,8 +155,32 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff_xsk *xskb, u32 len,
 static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+	u32 frags = xdp_buff_has_frags(xdp);
+	struct xdp_buff_xsk *pos, *tmp;
+	struct list_head *xskb_list;
+	u32 contd = 0;
+	int err;
+
+	if (frags)
+		contd = XDP_PKT_CONTD;
 
-	return __xsk_rcv_zc(xs, xskb, len, 0);
+	err = __xsk_rcv_zc(xs, xskb, len, contd);
+	if (err || likely(!frags))
+		goto out;
+
+	xskb_list = &xskb->pool->xskb_list;
+	list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
+		if (list_is_singular(xskb_list))
+			contd = 0;
+		len = pos->xdp.data_end - pos->xdp.data;
+		err = __xsk_rcv_zc(xs, pos, len, contd);
+		if (err)
+			return err;
+		list_del(&pos->xskb_list_node);
+	}
+
+out:
+	return err;
 }
 
 static void *xsk_copy_xdp_start(struct xdp_buff *from)
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 26f6d304451e9..b3f7b310811ed 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -86,6 +86,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	pool->umem = umem;
 	pool->addrs = umem->addrs;
 	INIT_LIST_HEAD(&pool->free_list);
+	INIT_LIST_HEAD(&pool->xskb_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
 	spin_lock_init(&pool->xsk_tx_list_lock);
 	spin_lock_init(&pool->cq_lock);
@@ -99,6 +100,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		xskb->pool = pool;
 		xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
 		INIT_LIST_HEAD(&xskb->free_list_node);
+		INIT_LIST_HEAD(&xskb->xskb_list_node);
 		if (pool->unaligned)
 			pool->free_heads[i] = xskb;
 		else
@@ -187,6 +189,11 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
 		goto err_unreg_pool;
 	}
 
+	if (netdev->xdp_zc_max_segs == 1 && (flags & XDP_USE_SG)) {
+		err = -EOPNOTSUPP;
+		goto err_unreg_pool;
+	}
+
 	bpf.command = XDP_SETUP_XSK_POOL;
 	bpf.xsk.pool = pool;
 	bpf.xsk.queue_id = queue_id;
-- 
GitLab


From 1bbc04de607babfca7374d374960e20ebb20813f Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 19 Jul 2023 15:24:09 +0200
Subject: [PATCH 0242/1806] ice: xsk: add RX multi-buffer support

This support is strongly inspired by work that introduced multi-buffer
support to regular Rx data path in ice. There are some differences,
though. When adding a frag, besides adding it to skb_shared_info, use
also fresh xsk_buff_add_frag() helper. Reason for doing both things is
that we can not rule out the fact that AF_XDP pipeline could use XDP
program that needs to access frame fragments. Without them being in
skb_shared_info it will not be possible. Another difference is that
XDP_PASS has to allocate a new pages for each frags and copy contents
from memory backed by xsk_buff_pool.

chain_len that is used for programming HW Rx descriptors no longer has
to be limited to 1 when xsk_pool is present - remove this restriction.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-13-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_base.c |   9 +-
 drivers/net/ethernet/intel/ice/ice_xsk.c  | 136 ++++++++++++++++------
 2 files changed, 102 insertions(+), 43 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 4a12316f7b464..3367b8ba98518 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -408,7 +408,6 @@ static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring)
  */
 static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 {
-	int chain_len = ICE_MAX_CHAINED_RX_BUFS;
 	struct ice_vsi *vsi = ring->vsi;
 	u32 rxdid = ICE_RXDID_FLEX_NIC;
 	struct ice_rlan_ctx rlan_ctx;
@@ -472,17 +471,11 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	 */
 	rlan_ctx.showiv = 0;
 
-	/* For AF_XDP ZC, we disallow packets to span on
-	 * multiple buffers, thus letting us skip that
-	 * handling in the fast-path.
-	 */
-	if (ring->xsk_pool)
-		chain_len = 1;
 	/* Max packet size for this queue - must not be set to a larger value
 	 * than 5 x DBUF
 	 */
 	rlan_ctx.rxmax = min_t(u32, vsi->max_frame,
-			       chain_len * ring->rx_buf_len);
+			       ICE_MAX_CHAINED_RX_BUFS * ring->rx_buf_len);
 
 	/* Rx queue threshold in units of 64 */
 	rlan_ctx.lrxqthresh = 1;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index a7fe2b4ce6552..91cdd5e4790dd 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -545,19 +545,6 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	return __ice_alloc_rx_bufs_zc(rx_ring, leftover);
 }
 
-/**
- * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring
- * @rx_ring: Rx ring
- */
-static void ice_bump_ntc(struct ice_rx_ring *rx_ring)
-{
-	int ntc = rx_ring->next_to_clean + 1;
-
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
-	rx_ring->next_to_clean = ntc;
-	prefetch(ICE_RX_DESC(rx_ring, ntc));
-}
-
 /**
  * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer
  * @rx_ring: Rx ring
@@ -572,8 +559,14 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 {
 	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
+	struct skb_shared_info *sinfo = NULL;
 	struct sk_buff *skb;
+	u32 nr_frags = 0;
 
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
 	net_prefetch(xdp->data_meta);
 
 	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
@@ -589,6 +582,29 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 		__skb_pull(skb, metasize);
 	}
 
+	if (likely(!xdp_buff_has_frags(xdp)))
+		goto out;
+
+	for (int i = 0; i < nr_frags; i++) {
+		struct skb_shared_info *skinfo = skb_shinfo(skb);
+		skb_frag_t *frag = &sinfo->frags[i];
+		struct page *page;
+		void *addr;
+
+		page = dev_alloc_page();
+		if (!page) {
+			dev_kfree_skb(skb);
+			return NULL;
+		}
+		addr = page_to_virt(page);
+
+		memcpy(addr, skb_frag_page(frag), skb_frag_size(frag));
+
+		__skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++,
+					   addr, 0, skb_frag_size(frag));
+	}
+
+out:
 	xsk_buff_free(xdp);
 	return skb;
 }
@@ -752,6 +768,34 @@ out_failure:
 	return result;
 }
 
+static int
+ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
+		 struct xdp_buff *xdp, const unsigned int size)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first);
+
+	if (!size)
+		return 0;
+
+	if (!xdp_buff_has_frags(first)) {
+		sinfo->nr_frags = 0;
+		sinfo->xdp_frags_size = 0;
+		xdp_buff_set_frags_flag(first);
+	}
+
+	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
+		xsk_buff_free(first);
+		return -ENOMEM;
+	}
+
+	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
+				   virt_to_page(xdp->data_hard_start), 0, size);
+	sinfo->xdp_frags_size += size;
+	xsk_buff_add_frag(xdp);
+
+	return 0;
+}
+
 /**
  * ice_clean_rx_irq_zc - consumes packets from the hardware ring
  * @rx_ring: AF_XDP Rx ring
@@ -762,9 +806,14 @@ out_failure:
 int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+	struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool;
+	u32 ntc = rx_ring->next_to_clean;
+	u32 ntu = rx_ring->next_to_use;
+	struct xdp_buff *first = NULL;
 	struct ice_tx_ring *xdp_ring;
 	unsigned int xdp_xmit = 0;
 	struct bpf_prog *xdp_prog;
+	u32 cnt = rx_ring->count;
 	bool failure = false;
 	int entries_to_alloc;
 
@@ -774,6 +823,9 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	xdp_ring = rx_ring->xdp_ring;
 
+	if (ntc != rx_ring->first_desc)
+		first = *ice_xdp_buf(rx_ring, rx_ring->first_desc);
+
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
 		unsigned int size, xdp_res = 0;
@@ -783,7 +835,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		u16 vlan_tag = 0;
 		u16 rx_ptype;
 
-		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);
+		rx_desc = ICE_RX_DESC(rx_ring, ntc);
 
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S);
 		if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits))
@@ -795,51 +847,61 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
-		if (unlikely(rx_ring->next_to_clean == rx_ring->next_to_use))
+		if (unlikely(ntc == ntu))
 			break;
 
-		xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean);
+		xdp = *ice_xdp_buf(rx_ring, ntc);
 
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
 				   ICE_RX_FLX_DESC_PKT_LEN_M;
-		if (!size) {
-			xdp->data = NULL;
-			xdp->data_end = NULL;
-			xdp->data_hard_start = NULL;
-			xdp->data_meta = NULL;
-			goto construct_skb;
-		}
 
 		xsk_buff_set_size(xdp, size);
-		xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool);
+		xsk_buff_dma_sync_for_cpu(xdp, xsk_pool);
+
+		if (!first) {
+			first = xdp;
+			xdp_buff_clear_frags_flag(first);
+		} else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) {
+			break;
+		}
+
+		if (++ntc == cnt)
+			ntc = 0;
+
+		if (ice_is_non_eop(rx_ring, rx_desc))
+			continue;
 
-		xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring);
+		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring);
 		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
 			xdp_xmit |= xdp_res;
 		} else if (xdp_res == ICE_XDP_EXIT) {
 			failure = true;
+			first = NULL;
+			rx_ring->first_desc = ntc;
 			break;
 		} else if (xdp_res == ICE_XDP_CONSUMED) {
-			xsk_buff_free(xdp);
+			xsk_buff_free(first);
 		} else if (xdp_res == ICE_XDP_PASS) {
 			goto construct_skb;
 		}
 
-		total_rx_bytes += size;
+		total_rx_bytes += xdp_get_buff_len(first);
 		total_rx_packets++;
 
-		ice_bump_ntc(rx_ring);
+		first = NULL;
+		rx_ring->first_desc = ntc;
 		continue;
 
 construct_skb:
 		/* XDP_PASS path */
-		skb = ice_construct_skb_zc(rx_ring, xdp);
+		skb = ice_construct_skb_zc(rx_ring, first);
 		if (!skb) {
 			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
 			break;
 		}
 
-		ice_bump_ntc(rx_ring);
+		first = NULL;
+		rx_ring->first_desc = ntc;
 
 		if (eth_skb_pad(skb)) {
 			skb = NULL;
@@ -858,18 +920,22 @@ construct_skb:
 		ice_receive_skb(rx_ring, skb, vlan_tag);
 	}
 
-	entries_to_alloc = ICE_DESC_UNUSED(rx_ring);
+	rx_ring->next_to_clean = ntc;
+	entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring);
 	if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
 		failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
 
-	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
-		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
-			xsk_set_rx_need_wakeup(rx_ring->xsk_pool);
+	if (xsk_uses_need_wakeup(xsk_pool)) {
+		/* ntu could have changed when allocating entries above, so
+		 * use rx_ring value instead of stack based one
+		 */
+		if (failure || ntc == rx_ring->next_to_use)
+			xsk_set_rx_need_wakeup(xsk_pool);
 		else
-			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool);
+			xsk_clear_rx_need_wakeup(xsk_pool);
 
 		return (int)total_rx_packets;
 	}
-- 
GitLab


From 1c9ba9c146589ff3d679b21e5e56b2d25ef43edd Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 19 Jul 2023 15:24:10 +0200
Subject: [PATCH 0243/1806] i40e: xsk: add RX multi-buffer support

This patch is inspired from the multi-buffer support in non-zc path for
i40e as well as from the patch to support zc on ice. Each subsequent
frag is added to skb_shared_info of the first frag for possible xdp_prog
use as well to xsk buffer list for accessing the buffers in af_xdp.

For XDP_PASS, new pages are allocated for frags and contents are copied
from memory backed by xsk_buff_pool.

Replace next_to_clean with next_to_process as done in non-zc path and
advance it for every buffer and change the semantics of next_to_clean to
point to the first buffer of a packet. Driver will use next_to_process
in the same way next_to_clean was used previously.

For the non multi-buffer case, next_to_process and next_to_clean will
always be the same since each packet consists of a single buffer.

Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-14-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c |  5 --
 drivers/net/ethernet/intel/i40e/i40e_txrx.c |  4 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.h |  2 +
 drivers/net/ethernet/intel/i40e/i40e_xsk.c  | 91 ++++++++++++++++++---
 4 files changed, 84 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 29ad1797adcea..1bd72cdedc8ac 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3585,11 +3585,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	if (ring->xsk_pool) {
 		ring->rx_buf_len =
 		  xsk_pool_get_rx_frame_size(ring->xsk_pool);
-		/* For AF_XDP ZC, we disallow packets to span on
-		 * multiple buffers, thus letting us skip that
-		 * handling in the fast-path.
-		 */
-		chain_len = 1;
 		ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						 MEM_TYPE_XSK_BUFF_POOL,
 						 NULL);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 8b8bf4880faa6..0b3a27f118fb9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2284,8 +2284,8 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
  * If the buffer is an EOP buffer, this function exits returning false,
  * otherwise return true indicating that this is in fact a non-EOP buffer.
  */
-static bool i40e_is_non_eop(struct i40e_ring *rx_ring,
-			    union i40e_rx_desc *rx_desc)
+bool i40e_is_non_eop(struct i40e_ring *rx_ring,
+		     union i40e_rx_desc *rx_desc)
 {
 	/* if we are the last buffer then there is nothing else to do */
 #define I40E_RXD_EOF BIT(I40E_RX_DESC_STATUS_EOF_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 8c3d24012c54c..900b0d9ede9f5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -473,6 +473,8 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
 bool __i40e_chk_linearize(struct sk_buff *skb);
 int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		  u32 flags);
+bool i40e_is_non_eop(struct i40e_ring *rx_ring,
+		     union i40e_rx_desc *rx_desc);
 
 /**
  * i40e_get_head - Retrieve head from head writeback
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 05ec1181471ea..89a8aca1153e6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -294,8 +294,14 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
 {
 	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
+	struct skb_shared_info *sinfo = NULL;
 	struct sk_buff *skb;
+	u32 nr_frags = 0;
 
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
 	net_prefetch(xdp->data_meta);
 
 	/* allocate a skb to store the frags */
@@ -312,6 +318,28 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
 		__skb_pull(skb, metasize);
 	}
 
+	if (likely(!xdp_buff_has_frags(xdp)))
+		goto out;
+
+	for (int i = 0; i < nr_frags; i++) {
+		struct skb_shared_info *skinfo = skb_shinfo(skb);
+		skb_frag_t *frag = &sinfo->frags[i];
+		struct page *page;
+		void *addr;
+
+		page = dev_alloc_page();
+		if (!page) {
+			dev_kfree_skb(skb);
+			return NULL;
+		}
+		addr = page_to_virt(page);
+
+		memcpy(addr, skb_frag_page(frag), skb_frag_size(frag));
+
+		__skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++,
+					   addr, 0, skb_frag_size(frag));
+	}
+
 out:
 	xsk_buff_free(xdp);
 	return skb;
@@ -322,14 +350,13 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
 				      union i40e_rx_desc *rx_desc,
 				      unsigned int *rx_packets,
 				      unsigned int *rx_bytes,
-				      unsigned int size,
 				      unsigned int xdp_res,
 				      bool *failure)
 {
 	struct sk_buff *skb;
 
 	*rx_packets = 1;
-	*rx_bytes = size;
+	*rx_bytes = xdp_get_buff_len(xdp_buff);
 
 	if (likely(xdp_res == I40E_XDP_REDIR) || xdp_res == I40E_XDP_TX)
 		return;
@@ -363,7 +390,6 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
 			return;
 		}
 
-		*rx_bytes = skb->len;
 		i40e_process_skb_fields(rx_ring, rx_desc, skb);
 		napi_gro_receive(&rx_ring->q_vector->napi, skb);
 		return;
@@ -374,6 +400,31 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
 	WARN_ON_ONCE(1);
 }
 
+static int
+i40e_add_xsk_frag(struct i40e_ring *rx_ring, struct xdp_buff *first,
+		  struct xdp_buff *xdp, const unsigned int size)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first);
+
+	if (!xdp_buff_has_frags(first)) {
+		sinfo->nr_frags = 0;
+		sinfo->xdp_frags_size = 0;
+		xdp_buff_set_frags_flag(first);
+	}
+
+	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
+		xsk_buff_free(first);
+		return -ENOMEM;
+	}
+
+	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
+				   virt_to_page(xdp->data_hard_start), 0, size);
+	sinfo->xdp_frags_size += size;
+	xsk_buff_add_frag(xdp);
+
+	return 0;
+}
+
 /**
  * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring
  * @rx_ring: Rx ring
@@ -384,13 +435,18 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
 int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+	u16 next_to_process = rx_ring->next_to_process;
 	u16 next_to_clean = rx_ring->next_to_clean;
 	u16 count_mask = rx_ring->count - 1;
 	unsigned int xdp_res, xdp_xmit = 0;
+	struct xdp_buff *first = NULL;
 	struct bpf_prog *xdp_prog;
 	bool failure = false;
 	u16 cleaned_count;
 
+	if (next_to_process != next_to_clean)
+		first = *i40e_rx_bi(rx_ring, next_to_clean);
+
 	/* NB! xdp_prog will always be !NULL, due to the fact that
 	 * this path is enabled by setting an XDP program.
 	 */
@@ -404,7 +460,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		unsigned int size;
 		u64 qword;
 
-		rx_desc = I40E_RX_DESC(rx_ring, next_to_clean);
+		rx_desc = I40E_RX_DESC(rx_ring, next_to_process);
 		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
 
 		/* This memory barrier is needed to keep us from reading
@@ -417,9 +473,9 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 			i40e_clean_programming_status(rx_ring,
 						      rx_desc->raw.qword[0],
 						      qword);
-			bi = *i40e_rx_bi(rx_ring, next_to_clean);
+			bi = *i40e_rx_bi(rx_ring, next_to_process);
 			xsk_buff_free(bi);
-			next_to_clean = (next_to_clean + 1) & count_mask;
+			next_to_process = (next_to_process + 1) & count_mask;
 			continue;
 		}
 
@@ -428,22 +484,35 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		if (!size)
 			break;
 
-		bi = *i40e_rx_bi(rx_ring, next_to_clean);
+		bi = *i40e_rx_bi(rx_ring, next_to_process);
 		xsk_buff_set_size(bi, size);
 		xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool);
 
-		xdp_res = i40e_run_xdp_zc(rx_ring, bi, xdp_prog);
-		i40e_handle_xdp_result_zc(rx_ring, bi, rx_desc, &rx_packets,
-					  &rx_bytes, size, xdp_res, &failure);
+		if (!first)
+			first = bi;
+		else if (i40e_add_xsk_frag(rx_ring, first, bi, size))
+			break;
+
+		next_to_process = (next_to_process + 1) & count_mask;
+
+		if (i40e_is_non_eop(rx_ring, rx_desc))
+			continue;
+
+		xdp_res = i40e_run_xdp_zc(rx_ring, first, xdp_prog);
+		i40e_handle_xdp_result_zc(rx_ring, first, rx_desc, &rx_packets,
+					  &rx_bytes, xdp_res, &failure);
+		first->flags = 0;
+		next_to_clean = next_to_process;
 		if (failure)
 			break;
 		total_rx_packets += rx_packets;
 		total_rx_bytes += rx_bytes;
 		xdp_xmit |= xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR);
-		next_to_clean = (next_to_clean + 1) & count_mask;
+		first = NULL;
 	}
 
 	rx_ring->next_to_clean = next_to_clean;
+	rx_ring->next_to_process = next_to_process;
 	cleaned_count = (next_to_clean - rx_ring->next_to_use - 1) & count_mask;
 
 	if (cleaned_count >= I40E_RX_BUFFER_WRITE)
-- 
GitLab


From d5581966040f313c76b0f54ad76b3fb4095fddcd Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 19 Jul 2023 15:24:11 +0200
Subject: [PATCH 0244/1806] xsk: support ZC Tx multi-buffer in batch API

Modify xskq_cons_read_desc_batch() in a way that each processed
descriptor will be checked if it is an EOP one or not and act
accordingly to that.

Change the behavior of mentioned function to break the processing when
stumbling upon invalid descriptor instead of skipping it. Furthermore,
let us give only full packets down to ZC driver.
With these two assumptions ZC drivers will not have to take care of an
intermediate state of incomplete frames, which will simplify its
implementations a lot.

Last but not least, stop processing when count of frags would exceed
max supported segments on underlying device.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-15-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/xdp/xsk_queue.h | 45 ++++++++++++++++++++++++++++++++++++---------
 1 file changed, 36 insertions(+), 9 deletions(-)

diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index bac32027f8654..13354a1e42801 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -48,6 +48,11 @@ struct xsk_queue {
 	size_t ring_vmalloc_size;
 };
 
+struct parsed_desc {
+	u32 mb;
+	u32 valid;
+};
+
 /* The structure of the shared state of the rings are a simple
  * circular buffer, as outlined in
  * Documentation/core-api/circular-buffers.rst. For the Rx and
@@ -218,30 +223,52 @@ static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
 	q->cached_cons += cnt;
 }
 
-static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool,
-					    u32 max)
+static inline void parse_desc(struct xsk_queue *q, struct xsk_buff_pool *pool,
+			      struct xdp_desc *desc, struct parsed_desc *parsed)
+{
+	parsed->valid = xskq_cons_is_valid_desc(q, desc, pool);
+	parsed->mb = xp_mb_desc(desc);
+}
+
+static inline
+u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool,
+			      u32 max)
 {
 	u32 cached_cons = q->cached_cons, nb_entries = 0;
 	struct xdp_desc *descs = pool->tx_descs;
+	u32 total_descs = 0, nr_frags = 0;
 
+	/* track first entry, if stumble upon *any* invalid descriptor, rewind
+	 * current packet that consists of frags and stop the processing
+	 */
 	while (cached_cons != q->cached_prod && nb_entries < max) {
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 		u32 idx = cached_cons & q->ring_mask;
+		struct parsed_desc parsed;
 
 		descs[nb_entries] = ring->desc[idx];
-		if (unlikely(!xskq_cons_is_valid_desc(q, &descs[nb_entries], pool))) {
-			/* Skip the entry */
-			cached_cons++;
-			continue;
+		cached_cons++;
+		parse_desc(q, pool, &descs[nb_entries], &parsed);
+		if (unlikely(!parsed.valid))
+			break;
+
+		if (likely(!parsed.mb)) {
+			total_descs += (nr_frags + 1);
+			nr_frags = 0;
+		} else {
+			nr_frags++;
+			if (nr_frags == pool->netdev->xdp_zc_max_segs) {
+				nr_frags = 0;
+				break;
+			}
 		}
-
 		nb_entries++;
-		cached_cons++;
 	}
 
+	cached_cons -= nr_frags;
 	/* Release valid plus any invalid entries */
 	xskq_cons_release_n(q, cached_cons - q->cached_cons);
-	return nb_entries;
+	return total_descs;
 }
 
 /* Functions for consumers */
-- 
GitLab


From eeb2b5381038201133b52829634d2f95a4a8ac5e Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 19 Jul 2023 15:24:12 +0200
Subject: [PATCH 0245/1806] ice: xsk: Tx multi-buffer support

Most of this patch is about actually supporting XDP_TX action. Pure Tx
ZC support is only about looking at XDP_PKT_CONTD presence at options
field and based on that generating EOP bit on Tx HW descriptor. This is
that simple due to the implementation on
xsk_tx_peek_release_desc_batch() where we are making sure that last
produced descriptor is an EOP one.

Overwrite xdp_zc_max_segs with a value that defines max scatter-gatter
count on Tx side that HW can handle.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-16-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_main.c |  1 +
 drivers/net/ethernet/intel/ice/ice_xsk.c  | 83 ++++++++++++++++-------
 2 files changed, 61 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 19a5e7f3a075e..ca83379b2de12 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3392,6 +3392,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
 	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			       NETDEV_XDP_ACT_XSK_ZEROCOPY |
 			       NETDEV_XDP_ACT_RX_SG;
+	netdev->xdp_zc_max_segs = ICE_MAX_BUF_TXD;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 91cdd5e4790dd..2a3f0834e1391 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -613,7 +613,7 @@ out:
  * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
  * @xdp_ring: XDP Tx ring
  */
-static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
 {
 	u16 ntc = xdp_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
@@ -635,7 +635,7 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
 	}
 
 	if (!completed_frames)
-		return;
+		return 0;
 
 	if (likely(!xdp_ring->xdp_tx_active)) {
 		xsk_frames = completed_frames;
@@ -665,6 +665,8 @@ skip:
 		xdp_ring->next_to_clean -= cnt;
 	if (xsk_frames)
 		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+
+	return completed_frames;
 }
 
 /**
@@ -682,37 +684,72 @@ skip:
 static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 			      struct ice_tx_ring *xdp_ring)
 {
+	struct skb_shared_info *sinfo = NULL;
 	u32 size = xdp->data_end - xdp->data;
 	u32 ntu = xdp_ring->next_to_use;
 	struct ice_tx_desc *tx_desc;
 	struct ice_tx_buf *tx_buf;
-	dma_addr_t dma;
+	struct xdp_buff *head;
+	u32 nr_frags = 0;
+	u32 free_space;
+	u32 frag = 0;
 
-	if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring)) {
-		ice_clean_xdp_irq_zc(xdp_ring);
-		if (!ICE_DESC_UNUSED(xdp_ring)) {
-			xdp_ring->ring_stats->tx_stats.tx_busy++;
-			return ICE_XDP_CONSUMED;
-		}
-	}
+	free_space = ICE_DESC_UNUSED(xdp_ring);
+	if (free_space < ICE_RING_QUARTER(xdp_ring))
+		free_space += ice_clean_xdp_irq_zc(xdp_ring);
 
-	dma = xsk_buff_xdp_get_dma(xdp);
-	xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+	if (unlikely(!free_space))
+		goto busy;
+
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+		if (free_space < nr_frags + 1)
+			goto busy;
+	}
 
-	tx_buf = &xdp_ring->tx_buf[ntu];
-	tx_buf->xdp = xdp;
-	tx_buf->type = ICE_TX_BUF_XSK_TX;
 	tx_desc = ICE_TX_DESC(xdp_ring, ntu);
-	tx_desc->buf_addr = cpu_to_le64(dma);
-	tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP,
-						      0, size, 0);
-	xdp_ring->xdp_tx_active++;
+	tx_buf = &xdp_ring->tx_buf[ntu];
+	head = xdp;
+
+	for (;;) {
+		dma_addr_t dma;
+
+		dma = xsk_buff_xdp_get_dma(xdp);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+
+		tx_buf->xdp = xdp;
+		tx_buf->type = ICE_TX_BUF_XSK_TX;
+		tx_desc->buf_addr = cpu_to_le64(dma);
+		tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0);
+		/* account for each xdp_buff from xsk_buff_pool */
+		xdp_ring->xdp_tx_active++;
+
+		if (++ntu == xdp_ring->count)
+			ntu = 0;
+
+		if (frag == nr_frags)
+			break;
+
+		tx_desc = ICE_TX_DESC(xdp_ring, ntu);
+		tx_buf = &xdp_ring->tx_buf[ntu];
+
+		xdp = xsk_buff_get_frag(head);
+		size = skb_frag_size(&sinfo->frags[frag]);
+		frag++;
+	}
 
-	if (++ntu == xdp_ring->count)
-		ntu = 0;
 	xdp_ring->next_to_use = ntu;
+	/* update last descriptor from a frame with EOP */
+	tx_desc->cmd_type_offset_bsz |=
+		cpu_to_le64(ICE_TX_DESC_CMD_EOP << ICE_TXD_QW1_CMD_S);
 
 	return ICE_XDP_TX;
+
+busy:
+	xdp_ring->ring_stats->tx_stats.tx_busy++;
+
+	return ICE_XDP_CONSUMED;
 }
 
 /**
@@ -960,7 +997,7 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
 
 	tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
 	tx_desc->buf_addr = cpu_to_le64(dma);
-	tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP,
+	tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(desc),
 						      0, desc->len, 0);
 
 	*total_bytes += desc->len;
@@ -987,7 +1024,7 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 
 		tx_desc = ICE_TX_DESC(xdp_ring, ntu++);
 		tx_desc->buf_addr = cpu_to_le64(dma);
-		tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP,
+		tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(&descs[i]),
 							      0, descs[i].len, 0);
 
 		*total_bytes += descs[i].len;
-- 
GitLab


From a92b96c4ae10950d8b904ae443d588c0e7f8344b Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 19 Jul 2023 15:24:13 +0200
Subject: [PATCH 0246/1806] i40e: xsk: add TX multi-buffer support

Set eop bit in TX desc command only for the last descriptor of the
packet and do not set for all preceding descriptors.

Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-17-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c |  1 +
 drivers/net/ethernet/intel/i40e/i40e_xsk.c  | 10 +++++-----
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 1bd72cdedc8ac..982ae70c51e8c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -13817,6 +13817,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 				       NETDEV_XDP_ACT_REDIRECT |
 				       NETDEV_XDP_ACT_XSK_ZEROCOPY |
 				       NETDEV_XDP_ACT_RX_SG;
+		netdev->xdp_zc_max_segs = I40E_MAX_BUFFER_TXD;
 	} else {
 		/* Relate the VSI_VMDQ name to the VSI_MAIN name. Note that we
 		 * are still limited by IFNAMSIZ, but we're adding 'v%d\0' to
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 89a8aca1153e6..37f41c8a682fb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -535,6 +535,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 static void i40e_xmit_pkt(struct i40e_ring *xdp_ring, struct xdp_desc *desc,
 			  unsigned int *total_bytes)
 {
+	u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(desc);
 	struct i40e_tx_desc *tx_desc;
 	dma_addr_t dma;
 
@@ -543,8 +544,7 @@ static void i40e_xmit_pkt(struct i40e_ring *xdp_ring, struct xdp_desc *desc,
 
 	tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
 	tx_desc->buffer_addr = cpu_to_le64(dma);
-	tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC | I40E_TX_DESC_CMD_EOP,
-						  0, desc->len, 0);
+	tx_desc->cmd_type_offset_bsz = build_ctob(cmd, 0, desc->len, 0);
 
 	*total_bytes += desc->len;
 }
@@ -558,14 +558,14 @@ static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *des
 	u32 i;
 
 	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+		u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(&desc[i]);
+
 		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr);
 		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc[i].len);
 
 		tx_desc = I40E_TX_DESC(xdp_ring, ntu++);
 		tx_desc->buffer_addr = cpu_to_le64(dma);
-		tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC |
-							  I40E_TX_DESC_CMD_EOP,
-							  0, desc[i].len, 0);
+		tx_desc->cmd_type_offset_bsz = build_ctob(cmd, 0, desc[i].len, 0);
 
 		*total_bytes += desc[i].len;
 	}
-- 
GitLab


From 49ca37d0d825d175bc6ae624f584a7502e848ebc Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 19 Jul 2023 15:24:14 +0200
Subject: [PATCH 0247/1806] xsk: add multi-buffer documentation

Add AF_XDP multi-buffer support documentation including two
pseudo-code samples.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-18-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/networking/af_xdp.rst | 211 +++++++++++++++++++++++++++-
 1 file changed, 210 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst
index 1cc35de336a41..dceeb0d763aa2 100644
--- a/Documentation/networking/af_xdp.rst
+++ b/Documentation/networking/af_xdp.rst
@@ -462,8 +462,92 @@ XDP_OPTIONS getsockopt
 Gets options from an XDP socket. The only one supported so far is
 XDP_OPTIONS_ZEROCOPY which tells you if zero-copy is on or not.
 
+Multi-Buffer Support
+====================
+
+With multi-buffer support, programs using AF_XDP sockets can receive
+and transmit packets consisting of multiple buffers both in copy and
+zero-copy mode. For example, a packet can consist of two
+frames/buffers, one with the header and the other one with the data,
+or a 9K Ethernet jumbo frame can be constructed by chaining together
+three 4K frames.
+
+Some definitions:
+
+* A packet consists of one or more frames
+
+* A descriptor in one of the AF_XDP rings always refers to a single
+  frame. In the case the packet consists of a single frame, the
+  descriptor refers to the whole packet.
+
+To enable multi-buffer support for an AF_XDP socket, use the new bind
+flag XDP_USE_SG. If this is not provided, all multi-buffer packets
+will be dropped just as before. Note that the XDP program loaded also
+needs to be in multi-buffer mode. This can be accomplished by using
+"xdp.frags" as the section name of the XDP program used.
+
+To represent a packet consisting of multiple frames, a new flag called
+XDP_PKT_CONTD is introduced in the options field of the Rx and Tx
+descriptors. If it is true (1) the packet continues with the next
+descriptor and if it is false (0) it means this is the last descriptor
+of the packet. Why the reverse logic of end-of-packet (eop) flag found
+in many NICs? Just to preserve compatibility with non-multi-buffer
+applications that have this bit set to false for all packets on Rx,
+and the apps set the options field to zero for Tx, as anything else
+will be treated as an invalid descriptor.
+
+These are the semantics for producing packets onto AF_XDP Tx ring
+consisting of multiple frames:
+
+* When an invalid descriptor is found, all the other
+  descriptors/frames of this packet are marked as invalid and not
+  completed. The next descriptor is treated as the start of a new
+  packet, even if this was not the intent (because we cannot guess
+  the intent). As before, if your program is producing invalid
+  descriptors you have a bug that must be fixed.
+
+* Zero length descriptors are treated as invalid descriptors.
+
+* For copy mode, the maximum supported number of frames in a packet is
+  equal to CONFIG_MAX_SKB_FRAGS + 1. If it is exceeded, all
+  descriptors accumulated so far are dropped and treated as
+  invalid. To produce an application that will work on any system
+  regardless of this config setting, limit the number of frags to 18,
+  as the minimum value of the config is 17.
+
+* For zero-copy mode, the limit is up to what the NIC HW
+  supports. Usually at least five on the NICs we have checked. We
+  consciously chose to not enforce a rigid limit (such as
+  CONFIG_MAX_SKB_FRAGS + 1) for zero-copy mode, as it would have
+  resulted in copy actions under the hood to fit into what limit the
+  NIC supports. Kind of defeats the purpose of zero-copy mode. How to
+  probe for this limit is explained in the "probe for multi-buffer
+  support" section.
+
+On the Rx path in copy-mode, the xsk core copies the XDP data into
+multiple descriptors, if needed, and sets the XDP_PKT_CONTD flag as
+detailed before. Zero-copy mode works the same, though the data is not
+copied. When the application gets a descriptor with the XDP_PKT_CONTD
+flag set to one, it means that the packet consists of multiple buffers
+and it continues with the next buffer in the following
+descriptor. When a descriptor with XDP_PKT_CONTD == 0 is received, it
+means that this is the last buffer of the packet. AF_XDP guarantees
+that only a complete packet (all frames in the packet) is sent to the
+application. If there is not enough space in the AF_XDP Rx ring, all
+frames of the packet will be dropped.
+
+If application reads a batch of descriptors, using for example the libxdp
+interfaces, it is not guaranteed that the batch will end with a full
+packet. It might end in the middle of a packet and the rest of the
+buffers of that packet will arrive at the beginning of the next batch,
+since the libxdp interface does not read the whole ring (unless you
+have an enormous batch size or a very small ring size).
+
+An example program each for Rx and Tx multi-buffer support can be found
+later in this document.
+
 Usage
-=====
+-----
 
 In order to use AF_XDP sockets two parts are needed. The
 user-space application and the XDP program. For a complete setup and
@@ -541,6 +625,131 @@ like this:
 But please use the libbpf functions as they are optimized and ready to
 use. Will make your life easier.
 
+Usage Multi-Buffer Rx
+---------------------
+
+Here is a simple Rx path pseudo-code example (using libxdp interfaces
+for simplicity). Error paths have been excluded to keep it short:
+
+.. code-block:: c
+
+    void rx_packets(struct xsk_socket_info *xsk)
+    {
+        static bool new_packet = true;
+        u32 idx_rx = 0, idx_fq = 0;
+        static char *pkt;
+
+        int rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx);
+
+        xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+
+        for (int i = 0; i < rcvd; i++) {
+            struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++);
+            char *frag = xsk_umem__get_data(xsk->umem->buffer, desc->addr);
+            bool eop = !(desc->options & XDP_PKT_CONTD);
+
+            if (new_packet)
+                pkt = frag;
+            else
+                add_frag_to_pkt(pkt, frag);
+
+            if (eop)
+                process_pkt(pkt);
+
+            new_packet = eop;
+
+            *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = desc->addr;
+        }
+
+        xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
+        xsk_ring_cons__release(&xsk->rx, rcvd);
+    }
+
+Usage Multi-Buffer Tx
+---------------------
+
+Here is an example Tx path pseudo-code (using libxdp interfaces for
+simplicity) ignoring that the umem is finite in size, and that we
+eventually will run out of packets to send. Also assumes pkts.addr
+points to a valid location in the umem.
+
+.. code-block:: c
+
+    void tx_packets(struct xsk_socket_info *xsk, struct pkt *pkts,
+                    int batch_size)
+    {
+        u32 idx, i, pkt_nb = 0;
+
+        xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx);
+
+        for (i = 0; i < batch_size;) {
+            u64 addr = pkts[pkt_nb].addr;
+            u32 len = pkts[pkt_nb].size;
+
+            do {
+                struct xdp_desc *tx_desc;
+
+                tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i++);
+                tx_desc->addr = addr;
+
+                if (len > xsk_frame_size) {
+                    tx_desc->len = xsk_frame_size;
+                    tx_desc->options = XDP_PKT_CONTD;
+                } else {
+                    tx_desc->len = len;
+                    tx_desc->options = 0;
+                    pkt_nb++;
+                }
+                len -= tx_desc->len;
+                addr += xsk_frame_size;
+
+                if (i == batch_size) {
+                    /* Remember len, addr, pkt_nb for next iteration.
+                     * Skipped for simplicity.
+                     */
+                    break;
+                }
+            } while (len);
+        }
+
+        xsk_ring_prod__submit(&xsk->tx, i);
+    }
+
+Probing for Multi-Buffer Support
+--------------------------------
+
+To discover if a driver supports multi-buffer AF_XDP in SKB or DRV
+mode, use the XDP_FEATURES feature of netlink in linux/netdev.h to
+query for NETDEV_XDP_ACT_RX_SG support. This is the same flag as for
+querying for XDP multi-buffer support. If XDP supports multi-buffer in
+a driver, then AF_XDP will also support that in SKB and DRV mode.
+
+To discover if a driver supports multi-buffer AF_XDP in zero-copy
+mode, use XDP_FEATURES and first check the NETDEV_XDP_ACT_XSK_ZEROCOPY
+flag. If it is set, it means that at least zero-copy is supported and
+you should go and check the netlink attribute
+NETDEV_A_DEV_XDP_ZC_MAX_SEGS in linux/netdev.h. An unsigned integer
+value will be returned stating the max number of frags that are
+supported by this device in zero-copy mode. These are the possible
+return values:
+
+1: Multi-buffer for zero-copy is not supported by this device, as max
+   one fragment supported means that multi-buffer is not possible.
+
+>=2: Multi-buffer is supported in zero-copy mode for this device. The
+     returned number signifies the max number of frags supported.
+
+For an example on how these are used through libbpf, please take a
+look at tools/testing/selftests/bpf/xskxceiver.c.
+
+Multi-Buffer Support for Zero-Copy Drivers
+------------------------------------------
+
+Zero-copy drivers usually use the batched APIs for Rx and Tx
+processing. Note that the Tx batch API guarantees that it will provide
+a batch of Tx descriptors that ends with full packet at the end. This
+to facilitate extending a zero-copy driver with multi-buffer support.
+
 Sample application
 ==================
 
-- 
GitLab


From 17f1034dd76d7465d4c0948c5280c6fc64ee0542 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 19 Jul 2023 15:24:15 +0200
Subject: [PATCH 0248/1806] selftests/xsk: transmit and receive multi-buffer
 packets

Add the ability to send and receive packets that are larger than the
size of a umem frame, using the AF_XDP /XDP multi-buffer
support. There are three pieces of code that need to be changed to
achieve this: the Rx path, the Tx path, and the validation logic.

Both the Rx path and Tx could only deal with a single fragment per
packet. The Tx path is extended with a new function called
pkt_nb_frags() that can be used to retrieve the number of fragments a
packet will consume. We then create these many fragments in a loop and
fill the N-1 first ones to the max size limit to use the buffer space
efficiently, and the Nth one with whatever data that is left. This
goes on until we have filled in at the most BATCH_SIZE worth of
descriptors and fragments. If we detect that the next packet would
lead to BATCH_SIZE number of fragments sent being exceeded, we do not
send this packet and finish the batch. This packet is instead sent in
the next iteration of BATCH_SIZE fragments.

For Rx, we loop over all fragments we receive as usual, but for every
descriptor that we receive we call a new validation function called
is_frag_valid() to validate the consistency of this fragment. The code
then checks if the packet continues in the next frame. If so, it loops
over the next packet and performs the same validation. once we have
received the last fragment of the packet we also call the function
is_pkt_valid() to validate the packet as a whole. If we get to the end
of the batch and we are not at the end of the current packet, we back
out the partial packet and end the loop. Once we get into the receive
loop next time, we start over from the beginning of that packet. This
so the code becomes simpler at the cost of some performance.

The validation function is_frag_valid() checks that the sequence and
packet numbers are correct at the start and end of each fragment.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-19-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/if_xdp.h        |   3 +
 tools/testing/selftests/bpf/xskxceiver.c | 167 ++++++++++++++++++-----
 tools/testing/selftests/bpf/xskxceiver.h |   3 +-
 3 files changed, 139 insertions(+), 34 deletions(-)

diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index a78a8096f4ce6..80245f5b4dd78 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -106,6 +106,9 @@ struct xdp_desc {
 	__u32 options;
 };
 
+/* Flag indicating packet constitutes of multiple buffers*/
+#define XDP_PKT_CONTD (1 << 0)
+
 /* UMEM descriptor is __u64 */
 
 #endif /* _LINUX_IF_XDP_H */
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 218d7f694e5cf..5e29e88504884 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -533,6 +533,11 @@ static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts)
 	return pkt_stream;
 }
 
+static bool pkt_continues(const struct xdp_desc *desc)
+{
+	return desc->options & XDP_PKT_CONTD;
+}
+
 static u32 ceil_u32(u32 a, u32 b)
 {
 	return (a + b - 1) / b;
@@ -549,7 +554,7 @@ static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, int offset, u32
 {
 	pkt->offset = offset;
 	pkt->len = len;
-	if (len > umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 2 - umem->frame_headroom)
+	if (len > MAX_ETH_JUMBO_SIZE)
 		pkt->valid = false;
 	else
 		pkt->valid = true;
@@ -637,6 +642,11 @@ static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem)
 	return pkt->offset + umem_alloc_buffer(umem);
 }
 
+static void pkt_stream_cancel(struct pkt_stream *pkt_stream)
+{
+	pkt_stream->current_pkt_nb--;
+}
+
 static void pkt_generate(struct ifobject *ifobject, u64 addr, u32 len, u32 pkt_nb,
 			 u32 bytes_written)
 {
@@ -765,43 +775,81 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr)
 	return true;
 }
 
-static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
+static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb,
+			  u32 bytes_processed)
 {
-	void *data = xsk_umem__get_data(buffer, addr);
-	u32 seqnum, pkt_data;
+	u32 seqnum, pkt_nb, *pkt_data, words_to_end, expected_seqnum;
+	void *data = xsk_umem__get_data(umem->buffer, addr);
 
-	if (!pkt) {
-		ksft_print_msg("[%s] too many packets received\n", __func__);
-		goto error;
+	addr -= umem->base_addr;
+
+	if (addr >= umem->num_frames * umem->frame_size ||
+	    addr + len > umem->num_frames * umem->frame_size) {
+		ksft_print_msg("Frag invalid addr: %llx len: %u\n", addr, len);
+		return false;
+	}
+	if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) {
+		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", addr, len);
+		return false;
 	}
 
-	if (len < MIN_PKT_SIZE || pkt->len < MIN_PKT_SIZE) {
-		/* Do not try to verify packets that are smaller than minimum size. */
-		return true;
+	pkt_data = data;
+	if (!bytes_processed) {
+		pkt_data += PKT_HDR_SIZE / sizeof(*pkt_data);
+		len -= PKT_HDR_SIZE;
+	} else {
+		bytes_processed -= PKT_HDR_SIZE;
 	}
 
-	if (pkt->len != len) {
-		ksft_print_msg("[%s] expected length [%d], got length [%d]\n",
-			       __func__, pkt->len, len);
+	expected_seqnum = bytes_processed / sizeof(*pkt_data);
+	seqnum = ntohl(*pkt_data) & 0xffff;
+	pkt_nb = ntohl(*pkt_data) >> 16;
+
+	if (expected_pkt_nb != pkt_nb) {
+		ksft_print_msg("[%s] expected pkt_nb [%u], got pkt_nb [%u]\n",
+			       __func__, expected_pkt_nb, pkt_nb);
+		goto error;
+	}
+	if (expected_seqnum != seqnum) {
+		ksft_print_msg("[%s] expected seqnum at start [%u], got seqnum [%u]\n",
+			       __func__, expected_seqnum, seqnum);
 		goto error;
 	}
 
-	pkt_data = ntohl(*((u32 *)(data + PKT_HDR_SIZE)));
-	seqnum = pkt_data >> 16;
-
-	if (pkt->pkt_nb != seqnum) {
-		ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n",
-			       __func__, pkt->pkt_nb, seqnum);
+	words_to_end = len / sizeof(*pkt_data) - 1;
+	pkt_data += words_to_end;
+	seqnum = ntohl(*pkt_data) & 0xffff;
+	expected_seqnum += words_to_end;
+	if (expected_seqnum != seqnum) {
+		ksft_print_msg("[%s] expected seqnum at end [%u], got seqnum [%u]\n",
+			       __func__, expected_seqnum, seqnum);
 		goto error;
 	}
 
 	return true;
 
 error:
-	pkt_dump(data, len, true);
+	pkt_dump(data, len, !bytes_processed);
 	return false;
 }
 
+static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
+{
+	if (!pkt) {
+		ksft_print_msg("[%s] too many packets received\n", __func__);
+		return false;
+	}
+
+	if (pkt->len != len) {
+		ksft_print_msg("[%s] expected packet length [%d], got length [%d]\n",
+			       __func__, pkt->len, len);
+		pkt_dump(xsk_umem__get_data(buffer, addr), len, true);
+		return false;
+	}
+
+	return true;
+}
+
 static void kick_tx(struct xsk_socket_info *xsk)
 {
 	int ret;
@@ -854,8 +902,8 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 {
 	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
 	struct pkt_stream *pkt_stream = test->ifobj_rx->pkt_stream;
-	u32 idx_rx = 0, idx_fq = 0, rcvd, i, pkts_sent = 0;
 	struct xsk_socket_info *xsk = test->ifobj_rx->xsk;
+	u32 idx_rx = 0, idx_fq = 0, rcvd, pkts_sent = 0;
 	struct ifobject *ifobj = test->ifobj_rx;
 	struct xsk_umem_info *umem = xsk->umem;
 	struct pkt *pkt;
@@ -868,6 +916,9 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 
 	pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent);
 	while (pkt) {
+		u32 frags_processed = 0, nb_frags = 0, pkt_len = 0;
+		u64 first_addr;
+
 		ret = gettimeofday(&tv_now, NULL);
 		if (ret)
 			exit_with_error(errno);
@@ -913,27 +964,53 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 			}
 		}
 
-		for (i = 0; i < rcvd; i++) {
+		while (frags_processed < rcvd) {
 			const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++);
 			u64 addr = desc->addr, orig;
 
 			orig = xsk_umem__extract_addr(addr);
 			addr = xsk_umem__add_offset_to_addr(addr);
 
-			if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len) ||
+			if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) ||
 			    !is_offset_correct(umem, pkt, addr) ||
 			    (ifobj->use_metadata && !is_metadata_correct(pkt, umem->buffer, addr)))
 				return TEST_FAILURE;
 
+			if (!nb_frags++)
+				first_addr = addr;
+			frags_processed++;
+			pkt_len += desc->len;
 			if (ifobj->use_fill_ring)
 				*xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig;
+
+			if (pkt_continues(desc))
+				continue;
+
+			/* The complete packet has been received */
+			if (!is_pkt_valid(pkt, umem->buffer, first_addr, pkt_len) ||
+			    !is_offset_correct(umem, pkt, addr))
+				return TEST_FAILURE;
+
 			pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent);
+			nb_frags = 0;
+			pkt_len = 0;
+		}
+
+		if (nb_frags) {
+			/* In the middle of a packet. Start over from beginning of packet. */
+			idx_rx -= nb_frags;
+			xsk_ring_cons__cancel(&xsk->rx, nb_frags);
+			if (ifobj->use_fill_ring) {
+				idx_fq -= nb_frags;
+				xsk_ring_prod__cancel(&umem->fq, nb_frags);
+			}
+			frags_processed -= nb_frags;
 		}
 
 		if (ifobj->use_fill_ring)
-			xsk_ring_prod__submit(&umem->fq, rcvd);
+			xsk_ring_prod__submit(&umem->fq, frags_processed);
 		if (ifobj->release_rx)
-			xsk_ring_cons__release(&xsk->rx, rcvd);
+			xsk_ring_cons__release(&xsk->rx, frags_processed);
 
 		pthread_mutex_lock(&pacing_mutex);
 		pkts_in_flight -= pkts_sent;
@@ -946,13 +1023,14 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 
 static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeout)
 {
+	u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len;
+	struct pkt_stream *pkt_stream = ifobject->pkt_stream;
 	struct xsk_socket_info *xsk = ifobject->xsk;
 	struct xsk_umem_info *umem = ifobject->umem;
-	u32 i, idx = 0, valid_pkts = 0, buffer_len;
 	bool use_poll = ifobject->use_poll;
 	int ret;
 
-	buffer_len = pkt_get_buffer_len(umem, ifobject->pkt_stream->max_pkt_len);
+	buffer_len = pkt_get_buffer_len(umem, pkt_stream->max_pkt_len);
 	/* pkts_in_flight might be negative if many invalid packets are sent */
 	if (pkts_in_flight >= (int)((umem_size(umem) - BATCH_SIZE * buffer_len) / buffer_len)) {
 		kick_tx(xsk);
@@ -983,17 +1061,40 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo
 	}
 
 	for (i = 0; i < BATCH_SIZE; i++) {
-		struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
-		struct pkt *pkt = pkt_stream_get_next_tx_pkt(ifobject->pkt_stream);
+		struct pkt *pkt = pkt_stream_get_next_tx_pkt(pkt_stream);
+		u32 nb_frags, bytes_written = 0;
 
 		if (!pkt)
 			break;
 
-		tx_desc->addr = pkt_get_addr(pkt, umem);
-		tx_desc->len = pkt->len;
+		nb_frags = pkt_nb_frags(umem->frame_size, pkt);
+		if (nb_frags > BATCH_SIZE - i) {
+			pkt_stream_cancel(pkt_stream);
+			xsk_ring_prod__cancel(&xsk->tx, BATCH_SIZE - i);
+			break;
+		}
+
 		if (pkt->valid) {
 			valid_pkts++;
-			pkt_generate(ifobject, tx_desc->addr, tx_desc->len, pkt->pkt_nb, 0);
+			valid_frags += nb_frags;
+		}
+
+		while (nb_frags--) {
+			struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
+
+			tx_desc->addr = pkt_get_addr(pkt, ifobject->umem);
+			if (nb_frags) {
+				tx_desc->len = umem->frame_size;
+				tx_desc->options = XDP_PKT_CONTD;
+				i++;
+			} else {
+				tx_desc->len = pkt->len - bytes_written;
+				tx_desc->options = 0;
+			}
+			if (pkt->valid)
+				pkt_generate(ifobject, tx_desc->addr, tx_desc->len, pkt->pkt_nb,
+					     bytes_written);
+			bytes_written += tx_desc->len;
 		}
 	}
 
@@ -1002,7 +1103,7 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo
 	pthread_mutex_unlock(&pacing_mutex);
 
 	xsk_ring_prod__submit(&xsk->tx, i);
-	xsk->outstanding_tx += valid_pkts;
+	xsk->outstanding_tx += valid_frags;
 
 	if (use_poll) {
 		ret = poll(fds, 1, POLL_TMOUT);
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index aaf27e0676406..310b48ad8a3a5 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -38,6 +38,7 @@
 #define MAX_TEARDOWN_ITER 10
 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */
 #define MIN_PKT_SIZE 64
+#define MAX_ETH_JUMBO_SIZE 9000
 #define USLEEP_MAX 10000
 #define SOCK_RECONF_CTR 10
 #define BATCH_SIZE 64
@@ -47,7 +48,7 @@
 #define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4)
 #define RX_FULL_RXQSIZE 32
 #define UMEM_HEADROOM_TEST_SIZE 128
-#define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1)
+#define XSK_UMEM__INVALID_FRAME_SIZE (MAX_ETH_JUMBO_SIZE + 1)
 #define HUGEPAGE_SIZE (2 * 1024 * 1024)
 #define PKT_DUMP_NB_TO_PRINT 16
 
-- 
GitLab


From f540d44e05cf2f324697ba375235da2d7c92743c Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 19 Jul 2023 15:24:16 +0200
Subject: [PATCH 0249/1806] selftests/xsk: add basic multi-buffer test

Add the first basic multi-buffer test that sends a stream of 9K
packets and validates that they are received at the other end. In
order to enable sending and receiving multi-buffer packets, code that
sets the MTU is introduced as well as modifications to the XDP
programs so that they signal that they are multi-buffer enabled.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-20-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/if_xdp.h             |   6 +
 .../selftests/bpf/progs/xsk_xdp_progs.c       |   4 +-
 tools/testing/selftests/bpf/xsk.c             | 136 +++++++++++++++++-
 tools/testing/selftests/bpf/xsk.h             |   2 +
 tools/testing/selftests/bpf/xskxceiver.c      |  68 +++++++++
 tools/testing/selftests/bpf/xskxceiver.h      |   6 +
 6 files changed, 219 insertions(+), 3 deletions(-)

diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 80245f5b4dd78..73a47da885dc1 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -25,6 +25,12 @@
  * application.
  */
 #define XDP_USE_NEED_WAKEUP (1 << 3)
+/* By setting this option, userspace application indicates that it can
+ * handle multiple descriptors per packet thus enabling xsk core to split
+ * multi-buffer XDP frames into multiple Rx descriptors. Without this set
+ * such frames will be dropped by xsk.
+ */
+#define XDP_USE_SG     (1 << 4)
 
 /* Flags for xsk_umem_config flags */
 #define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
index a630c95c74716..ac76e73637768 100644
--- a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
+++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
@@ -15,12 +15,12 @@ struct {
 static unsigned int idx;
 int count = 0;
 
-SEC("xdp") int xsk_def_prog(struct xdp_md *xdp)
+SEC("xdp.frags") int xsk_def_prog(struct xdp_md *xdp)
 {
 	return bpf_redirect_map(&xsk, 0, XDP_DROP);
 }
 
-SEC("xdp") int xsk_xdp_drop(struct xdp_md *xdp)
+SEC("xdp.frags") int xsk_xdp_drop(struct xdp_md *xdp)
 {
 	/* Drop every other packet */
 	if (idx++ % 2)
diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c
index 687d83e707f83..d9fb2b730a2cd 100644
--- a/tools/testing/selftests/bpf/xsk.c
+++ b/tools/testing/selftests/bpf/xsk.c
@@ -18,17 +18,19 @@
 #include <linux/ethtool.h>
 #include <linux/filter.h>
 #include <linux/if_ether.h>
+#include <linux/if_link.h>
 #include <linux/if_packet.h>
 #include <linux/if_xdp.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
 #include <linux/sockios.h>
 #include <net/if.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
 #include <sys/socket.h>
 #include <sys/types.h>
-#include <linux/if_link.h>
 
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
@@ -81,6 +83,12 @@ struct xsk_socket {
 	int fd;
 };
 
+struct nl_mtu_req {
+	struct nlmsghdr nh;
+	struct ifinfomsg msg;
+	char             buf[512];
+};
+
 int xsk_umem__fd(const struct xsk_umem *umem)
 {
 	return umem ? umem->fd : -EINVAL;
@@ -286,6 +294,132 @@ bool xsk_is_in_mode(u32 ifindex, int mode)
 	return false;
 }
 
+/* Lifted from netlink.c in tools/lib/bpf */
+static int netlink_recvmsg(int sock, struct msghdr *mhdr, int flags)
+{
+	int len;
+
+	do {
+		len = recvmsg(sock, mhdr, flags);
+	} while (len < 0 && (errno == EINTR || errno == EAGAIN));
+
+	if (len < 0)
+		return -errno;
+	return len;
+}
+
+/* Lifted from netlink.c in tools/lib/bpf */
+static int alloc_iov(struct iovec *iov, int len)
+{
+	void *nbuf;
+
+	nbuf = realloc(iov->iov_base, len);
+	if (!nbuf)
+		return -ENOMEM;
+
+	iov->iov_base = nbuf;
+	iov->iov_len = len;
+	return 0;
+}
+
+/* Original version lifted from netlink.c in tools/lib/bpf */
+static int netlink_recv(int sock)
+{
+	struct iovec iov = {};
+	struct msghdr mhdr = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+	bool multipart = true;
+	struct nlmsgerr *err;
+	struct nlmsghdr *nh;
+	int len, ret;
+
+	ret = alloc_iov(&iov, 4096);
+	if (ret)
+		goto done;
+
+	while (multipart) {
+		multipart = false;
+		len = netlink_recvmsg(sock, &mhdr, MSG_PEEK | MSG_TRUNC);
+		if (len < 0) {
+			ret = len;
+			goto done;
+		}
+
+		if (len > iov.iov_len) {
+			ret = alloc_iov(&iov, len);
+			if (ret)
+				goto done;
+		}
+
+		len = netlink_recvmsg(sock, &mhdr, 0);
+		if (len < 0) {
+			ret = len;
+			goto done;
+		}
+
+		if (len == 0)
+			break;
+
+		for (nh = (struct nlmsghdr *)iov.iov_base; NLMSG_OK(nh, len);
+		     nh = NLMSG_NEXT(nh, len)) {
+			if (nh->nlmsg_flags & NLM_F_MULTI)
+				multipart = true;
+			switch (nh->nlmsg_type) {
+			case NLMSG_ERROR:
+				err = (struct nlmsgerr *)NLMSG_DATA(nh);
+				if (!err->error)
+					continue;
+				ret = err->error;
+				goto done;
+			case NLMSG_DONE:
+				ret = 0;
+				goto done;
+			default:
+				break;
+			}
+		}
+	}
+	ret = 0;
+done:
+	free(iov.iov_base);
+	return ret;
+}
+
+int xsk_set_mtu(int ifindex, int mtu)
+{
+	struct nl_mtu_req req;
+	struct rtattr *rta;
+	int fd, ret;
+
+	fd = socket(AF_NETLINK, SOCK_DGRAM, NETLINK_ROUTE);
+	if (fd < 0)
+		return fd;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type = RTM_NEWLINK;
+	req.msg.ifi_family = AF_UNSPEC;
+	req.msg.ifi_index = ifindex;
+	rta = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nh.nlmsg_len));
+	rta->rta_type = IFLA_MTU;
+	rta->rta_len = RTA_LENGTH(sizeof(unsigned int));
+	req.nh.nlmsg_len = NLMSG_ALIGN(req.nh.nlmsg_len) + RTA_LENGTH(sizeof(mtu));
+	memcpy(RTA_DATA(rta), &mtu, sizeof(mtu));
+
+	ret = send(fd, &req, req.nh.nlmsg_len, 0);
+	if (ret < 0) {
+		close(fd);
+		return errno;
+	}
+
+	ret = netlink_recv(fd);
+	close(fd);
+	return ret;
+}
+
 int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags)
 {
 	int prog_fd;
diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h
index 8da8d557768b4..d93200fdaa8d8 100644
--- a/tools/testing/selftests/bpf/xsk.h
+++ b/tools/testing/selftests/bpf/xsk.h
@@ -239,6 +239,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 int xsk_umem__delete(struct xsk_umem *umem);
 void xsk_socket__delete(struct xsk_socket *xsk);
 
+int xsk_set_mtu(int ifindex, int mtu);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 5e29e88504884..6fb682facce59 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -49,6 +49,7 @@
  *    h. tests for invalid and corner case Tx descriptors so that the correct ones
  *       are discarded and let through, respectively.
  *    i. 2K frame size tests
+ *    j. If multi-buffer is supported, send 9k packets divided into 3 frames
  *
  * Total tests: 12
  *
@@ -77,6 +78,7 @@
 #include <linux/if_link.h>
 #include <linux/if_ether.h>
 #include <linux/mman.h>
+#include <linux/netdev.h>
 #include <arpa/inet.h>
 #include <net/if.h>
 #include <locale.h>
@@ -253,6 +255,8 @@ static int __xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_i
 	cfg.bind_flags = ifobject->bind_flags;
 	if (shared)
 		cfg.bind_flags |= XDP_SHARED_UMEM;
+	if (ifobject->pkt_stream && ifobject->mtu > MAX_ETH_PKT_SIZE)
+		cfg.bind_flags |= XDP_USE_SG;
 
 	txr = ifobject->tx_on ? &xsk->tx : NULL;
 	rxr = ifobject->rx_on ? &xsk->rx : NULL;
@@ -415,6 +419,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 	test->total_steps = 1;
 	test->nb_sockets = 1;
 	test->fail = false;
+	test->mtu = MAX_ETH_PKT_SIZE;
 	test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog;
 	test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk;
 	test->xdp_prog_tx = ifobj_tx->xdp_progs->progs.xsk_def_prog;
@@ -468,6 +473,26 @@ static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *x
 	test->xskmap_tx = xskmap_tx;
 }
 
+static int test_spec_set_mtu(struct test_spec *test, int mtu)
+{
+	int err;
+
+	if (test->ifobj_rx->mtu != mtu) {
+		err = xsk_set_mtu(test->ifobj_rx->ifindex, mtu);
+		if (err)
+			return err;
+		test->ifobj_rx->mtu = mtu;
+	}
+	if (test->ifobj_tx->mtu != mtu) {
+		err = xsk_set_mtu(test->ifobj_tx->ifindex, mtu);
+		if (err)
+			return err;
+		test->ifobj_tx->mtu = mtu;
+	}
+
+	return 0;
+}
+
 static void pkt_stream_reset(struct pkt_stream *pkt_stream)
 {
 	if (pkt_stream)
@@ -1516,6 +1541,25 @@ static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *i
 				      struct ifobject *ifobj2)
 {
 	pthread_t t0, t1;
+	int err;
+
+	if (test->mtu > MAX_ETH_PKT_SIZE) {
+		if (test->mode == TEST_MODE_ZC && (!ifobj1->multi_buff_zc_supp ||
+						   (ifobj2 && !ifobj2->multi_buff_zc_supp))) {
+			ksft_test_result_skip("Multi buffer for zero-copy not supported.\n");
+			return TEST_SKIP;
+		}
+		if (test->mode != TEST_MODE_ZC && (!ifobj1->multi_buff_supp ||
+						   (ifobj2 && !ifobj2->multi_buff_supp))) {
+			ksft_test_result_skip("Multi buffer not supported.\n");
+			return TEST_SKIP;
+		}
+	}
+	err = test_spec_set_mtu(test, test->mtu);
+	if (err) {
+		ksft_print_msg("Error, could not set mtu.\n");
+		exit_with_error(err);
+	}
 
 	if (ifobj2) {
 		if (pthread_barrier_init(&barr, NULL, 2))
@@ -1725,6 +1769,15 @@ static int testapp_single_pkt(struct test_spec *test)
 	return testapp_validate_traffic(test);
 }
 
+static int testapp_multi_buffer(struct test_spec *test)
+{
+	test_spec_set_name(test, "RUN_TO_COMPLETION_9K_PACKETS");
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE);
+
+	return testapp_validate_traffic(test);
+}
+
 static int testapp_invalid_desc(struct test_spec *test)
 {
 	struct xsk_umem_info *umem = test->ifobj_tx->umem;
@@ -1858,6 +1911,7 @@ static bool hugepages_present(void)
 static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac,
 		       thread_func_t func_ptr)
 {
+	LIBBPF_OPTS(bpf_xdp_query_opts, query_opts);
 	int err;
 
 	memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN);
@@ -1873,6 +1927,17 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 
 	if (hugepages_present())
 		ifobj->unaligned_supp = true;
+
+	err = bpf_xdp_query(ifobj->ifindex, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (err) {
+		ksft_print_msg("Error querrying XDP capabilities\n");
+		exit_with_error(-err);
+	}
+	if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG)
+		ifobj->multi_buff_supp = true;
+	if (query_opts.feature_flags & NETDEV_XDP_ACT_XSK_ZEROCOPY)
+		if (query_opts.xdp_zc_max_segs > 1)
+			ifobj->multi_buff_zc_supp = true;
 }
 
 static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type)
@@ -1905,6 +1970,9 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		test_spec_set_name(test, "RUN_TO_COMPLETION");
 		ret = testapp_validate_traffic(test);
 		break;
+	case TEST_TYPE_RUN_TO_COMPLETION_MB:
+		ret = testapp_multi_buffer(test);
+		break;
 	case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT:
 		test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT");
 		ret = testapp_single_pkt(test);
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 310b48ad8a3a5..cfc7c572fd2cb 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -38,6 +38,7 @@
 #define MAX_TEARDOWN_ITER 10
 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */
 #define MIN_PKT_SIZE 64
+#define MAX_ETH_PKT_SIZE 1518
 #define MAX_ETH_JUMBO_SIZE 9000
 #define USLEEP_MAX 10000
 #define SOCK_RECONF_CTR 10
@@ -84,6 +85,7 @@ enum test_type {
 	TEST_TYPE_BPF_RES,
 	TEST_TYPE_XDP_DROP_HALF,
 	TEST_TYPE_XDP_METADATA_COUNT,
+	TEST_TYPE_RUN_TO_COMPLETION_MB,
 	TEST_TYPE_MAX
 };
 
@@ -142,6 +144,7 @@ struct ifobject {
 	struct bpf_program *xdp_prog;
 	enum test_mode mode;
 	int ifindex;
+	int mtu;
 	u32 bind_flags;
 	bool tx_on;
 	bool rx_on;
@@ -152,6 +155,8 @@ struct ifobject {
 	bool shared_umem;
 	bool use_metadata;
 	bool unaligned_supp;
+	bool multi_buff_supp;
+	bool multi_buff_zc_supp;
 	u8 dst_mac[ETH_ALEN];
 	u8 src_mac[ETH_ALEN];
 };
@@ -165,6 +170,7 @@ struct test_spec {
 	struct bpf_program *xdp_prog_tx;
 	struct bpf_map *xskmap_rx;
 	struct bpf_map *xskmap_tx;
+	int mtu;
 	u16 total_steps;
 	u16 current_step;
 	u16 nb_sockets;
-- 
GitLab


From 1005a226da9ab458c3421cfd3730d6534e2f38b1 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 19 Jul 2023 15:24:17 +0200
Subject: [PATCH 0250/1806] selftests/xsk: add unaligned mode test for
 multi-buffer

Add a test for multi-buffer AF_XDP when using unaligned mode. The test
sends 4096 9K-buffers.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-21-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/xskxceiver.c | 15 +++++++++++++++
 tools/testing/selftests/bpf/xskxceiver.h |  1 +
 2 files changed, 16 insertions(+)

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 6fb682facce59..0a1e693e5713b 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -50,6 +50,8 @@
  *       are discarded and let through, respectively.
  *    i. 2K frame size tests
  *    j. If multi-buffer is supported, send 9k packets divided into 3 frames
+ *    k. If multi-buffer and huge pages are supported, send 9k packets in a single frame
+ *       using unaligned mode
  *
  * Total tests: 12
  *
@@ -1761,6 +1763,16 @@ static int testapp_unaligned(struct test_spec *test)
 	return testapp_validate_traffic(test);
 }
 
+static int testapp_unaligned_mb(struct test_spec *test)
+{
+	test_spec_set_name(test, "UNALIGNED_MODE_9K");
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE);
+	return testapp_validate_traffic(test);
+}
+
 static int testapp_single_pkt(struct test_spec *test)
 {
 	struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}};
@@ -2038,6 +2050,9 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 	case TEST_TYPE_UNALIGNED:
 		ret = testapp_unaligned(test);
 		break;
+	case TEST_TYPE_UNALIGNED_MB:
+		ret = testapp_unaligned_mb(test);
+		break;
 	case TEST_TYPE_HEADROOM:
 		ret = testapp_headroom(test);
 		break;
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index cfc7c572fd2cb..48cb48f1c5e66 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -86,6 +86,7 @@ enum test_type {
 	TEST_TYPE_XDP_DROP_HALF,
 	TEST_TYPE_XDP_METADATA_COUNT,
 	TEST_TYPE_RUN_TO_COMPLETION_MB,
+	TEST_TYPE_UNALIGNED_MB,
 	TEST_TYPE_MAX
 };
 
-- 
GitLab


From 697604492b642e4057c6a350dfe33351c770c7af Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 19 Jul 2023 15:24:18 +0200
Subject: [PATCH 0251/1806] selftests/xsk: add invalid descriptor test for
 multi-buffer

Add a test that produces lots of nasty descriptors testing the corner
cases of the descriptor validation. Some of these descriptors are
valid and some are not as indicated by the valid flag. For a
description of all the test combinations, please see the code.

To stress the API, we need to be able to generate combinations of
descriptors that make little sense. A new verbatim mode is introduced
for the packet_stream to accomplish this. In this mode, all packets in
the packet_stream are sent as is. We do not try to chop them up into
frames that are of the right size that we know are going to work as we
would normally do. The packets are just written into the Tx ring even
if we know they make no sense.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> # adjusted valid flags for frags
Link: https://lore.kernel.org/r/20230719132421.584801-22-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/xskxceiver.c | 185 ++++++++++++++++++-----
 tools/testing/selftests/bpf/xskxceiver.h |   7 +
 2 files changed, 151 insertions(+), 41 deletions(-)

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 0a1e693e5713b..59210cb33beba 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -52,8 +52,8 @@
  *    j. If multi-buffer is supported, send 9k packets divided into 3 frames
  *    k. If multi-buffer and huge pages are supported, send 9k packets in a single frame
  *       using unaligned mode
- *
- * Total tests: 12
+ *    l. If multi-buffer is supported, try various nasty combinations of descriptors to
+ *       check if they pass the validation or not
  *
  * Flow:
  * -----
@@ -76,7 +76,6 @@
 #include <fcntl.h>
 #include <errno.h>
 #include <getopt.h>
-#include <asm/barrier.h>
 #include <linux/if_link.h>
 #include <linux/if_ether.h>
 #include <linux/mman.h>
@@ -95,7 +94,6 @@
 #include <sys/socket.h>
 #include <sys/time.h>
 #include <sys/types.h>
-#include <time.h>
 #include <unistd.h>
 
 #include "xsk_xdp_progs.skel.h"
@@ -560,9 +558,9 @@ static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts)
 	return pkt_stream;
 }
 
-static bool pkt_continues(const struct xdp_desc *desc)
+static bool pkt_continues(u32 options)
 {
-	return desc->options & XDP_PKT_CONTD;
+	return options & XDP_PKT_CONTD;
 }
 
 static u32 ceil_u32(u32 a, u32 b)
@@ -570,11 +568,32 @@ static u32 ceil_u32(u32 a, u32 b)
 	return (a + b - 1) / b;
 }
 
-static u32 pkt_nb_frags(u32 frame_size, struct pkt *pkt)
+static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pkt *pkt)
 {
-	if (!pkt || !pkt->valid)
+	u32 nb_frags = 1, next_frag;
+
+	if (!pkt)
 		return 1;
-	return ceil_u32(pkt->len, frame_size);
+
+	if (!pkt_stream->verbatim) {
+		if (!pkt->valid || !pkt->len)
+			return 1;
+		return ceil_u32(pkt->len, frame_size);
+	}
+
+	/* Search for the end of the packet in verbatim mode */
+	if (!pkt_continues(pkt->options))
+		return nb_frags;
+
+	next_frag = pkt_stream->current_pkt_nb;
+	pkt++;
+	while (next_frag++ < pkt_stream->nb_pkts) {
+		nb_frags++;
+		if (!pkt_continues(pkt->options) || !pkt->valid)
+			break;
+		pkt++;
+	}
+	return nb_frags;
 }
 
 static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, int offset, u32 len)
@@ -694,34 +713,59 @@ static void pkt_generate(struct ifobject *ifobject, u64 addr, u32 len, u32 pkt_n
 	write_payload(data, pkt_nb, bytes_written, len);
 }
 
-static void __pkt_stream_generate_custom(struct ifobject *ifobj,
-					 struct pkt *pkts, u32 nb_pkts)
+static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, struct pkt *frames,
+						       u32 nb_frames, bool verbatim)
 {
+	u32 i, len = 0, pkt_nb = 0, payload = 0;
 	struct pkt_stream *pkt_stream;
-	u32 i;
 
-	pkt_stream = __pkt_stream_alloc(nb_pkts);
+	pkt_stream = __pkt_stream_alloc(nb_frames);
 	if (!pkt_stream)
 		exit_with_error(ENOMEM);
 
-	for (i = 0; i < nb_pkts; i++) {
-		struct pkt *pkt = &pkt_stream->pkts[i];
+	for (i = 0; i < nb_frames; i++) {
+		struct pkt *pkt = &pkt_stream->pkts[pkt_nb];
+		struct pkt *frame = &frames[i];
 
-		pkt->offset = pkts[i].offset;
-		pkt->len = pkts[i].len;
-		pkt->pkt_nb = i;
-		pkt->valid = pkts[i].valid;
-		if (pkt->len > pkt_stream->max_pkt_len)
+		pkt->offset = frame->offset;
+		if (verbatim) {
+			*pkt = *frame;
+			pkt->pkt_nb = payload;
+			if (!frame->valid || !pkt_continues(frame->options))
+				payload++;
+		} else {
+			if (frame->valid)
+				len += frame->len;
+			if (frame->valid && pkt_continues(frame->options))
+				continue;
+
+			pkt->pkt_nb = pkt_nb;
+			pkt->len = len;
+			pkt->valid = frame->valid;
+			pkt->options = 0;
+
+			len = 0;
+		}
+
+		if (pkt->valid && pkt->len > pkt_stream->max_pkt_len)
 			pkt_stream->max_pkt_len = pkt->len;
+		pkt_nb++;
 	}
 
-	ifobj->pkt_stream = pkt_stream;
+	pkt_stream->nb_pkts = pkt_nb;
+	pkt_stream->verbatim = verbatim;
+	return pkt_stream;
 }
 
 static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts)
 {
-	__pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts);
-	__pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts);
+	struct pkt_stream *pkt_stream;
+
+	pkt_stream = __pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts, true);
+	test->ifobj_tx->pkt_stream = pkt_stream;
+
+	pkt_stream = __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts, false);
+	test->ifobj_rx->pkt_stream = pkt_stream;
 }
 
 static void pkt_print_data(u32 *data, u32 cnt)
@@ -862,11 +906,6 @@ error:
 
 static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
 {
-	if (!pkt) {
-		ksft_print_msg("[%s] too many packets received\n", __func__);
-		return false;
-	}
-
 	if (pkt->len != len) {
 		ksft_print_msg("[%s] expected packet length [%d], got length [%d]\n",
 			       __func__, pkt->len, len);
@@ -966,7 +1005,6 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 
 				ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__);
 				return TEST_FAILURE;
-
 			}
 
 			if (!(fds->revents & POLLIN))
@@ -998,6 +1036,12 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 			orig = xsk_umem__extract_addr(addr);
 			addr = xsk_umem__add_offset_to_addr(addr);
 
+			if (!pkt) {
+				ksft_print_msg("[%s] received too many packets addr: %lx len %u\n",
+					       __func__, addr, desc->len);
+				return TEST_FAILURE;
+			}
+
 			if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) ||
 			    !is_offset_correct(umem, pkt, addr) ||
 			    (ifobj->use_metadata && !is_metadata_correct(pkt, umem->buffer, addr)))
@@ -1010,7 +1054,7 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 			if (ifobj->use_fill_ring)
 				*xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig;
 
-			if (pkt_continues(desc))
+			if (pkt_continues(desc->options))
 				continue;
 
 			/* The complete packet has been received */
@@ -1089,31 +1133,29 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo
 
 	for (i = 0; i < BATCH_SIZE; i++) {
 		struct pkt *pkt = pkt_stream_get_next_tx_pkt(pkt_stream);
-		u32 nb_frags, bytes_written = 0;
+		u32 nb_frags_left, nb_frags, bytes_written = 0;
 
 		if (!pkt)
 			break;
 
-		nb_frags = pkt_nb_frags(umem->frame_size, pkt);
+		nb_frags = pkt_nb_frags(umem->frame_size, pkt_stream, pkt);
 		if (nb_frags > BATCH_SIZE - i) {
 			pkt_stream_cancel(pkt_stream);
 			xsk_ring_prod__cancel(&xsk->tx, BATCH_SIZE - i);
 			break;
 		}
+		nb_frags_left = nb_frags;
 
-		if (pkt->valid) {
-			valid_pkts++;
-			valid_frags += nb_frags;
-		}
-
-		while (nb_frags--) {
+		while (nb_frags_left--) {
 			struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
 
 			tx_desc->addr = pkt_get_addr(pkt, ifobject->umem);
-			if (nb_frags) {
+			if (pkt_stream->verbatim) {
+				tx_desc->len = pkt->len;
+				tx_desc->options = pkt->options;
+			} else if (nb_frags_left) {
 				tx_desc->len = umem->frame_size;
 				tx_desc->options = XDP_PKT_CONTD;
-				i++;
 			} else {
 				tx_desc->len = pkt->len - bytes_written;
 				tx_desc->options = 0;
@@ -1122,6 +1164,17 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo
 				pkt_generate(ifobject, tx_desc->addr, tx_desc->len, pkt->pkt_nb,
 					     bytes_written);
 			bytes_written += tx_desc->len;
+
+			if (nb_frags_left) {
+				i++;
+				if (pkt_stream->verbatim)
+					pkt = pkt_stream_get_next_tx_pkt(pkt_stream);
+			}
+		}
+
+		if (pkt && pkt->valid) {
+			valid_pkts++;
+			valid_frags += nb_frags;
 		}
 	}
 
@@ -1350,7 +1403,7 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream
 		u64 addr;
 		u32 i;
 
-		for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt); i++) {
+		for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt_stream, pkt); i++) {
 			if (!pkt) {
 				if (!fill_up)
 					break;
@@ -1790,6 +1843,46 @@ static int testapp_multi_buffer(struct test_spec *test)
 	return testapp_validate_traffic(test);
 }
 
+static int testapp_invalid_desc_mb(struct test_spec *test)
+{
+	struct xsk_umem_info *umem = test->ifobj_tx->umem;
+	u64 umem_size = umem->num_frames * umem->frame_size;
+	struct pkt pkts[] = {
+		/* Valid packet for synch to start with */
+		{0, MIN_PKT_SIZE, 0, true, 0},
+		/* Zero frame len is not legal */
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{0, 0, 0, false, 0},
+		/* Invalid address in the second frame */
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{umem_size, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		/* Invalid len in the middle */
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		/* Invalid options in the middle */
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XSK_DESC__INVALID_OPTION},
+		/* Transmit 2 frags, receive 3 */
+		{0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, XDP_PKT_CONTD},
+		{0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, 0},
+		/* Middle frame crosses chunk boundary with small length */
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{-MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false, 0},
+		/* Valid packet for synch so that something is received */
+		{0, MIN_PKT_SIZE, 0, true, 0}};
+
+	if (umem->unaligned_mode) {
+		/* Crossing a chunk boundary allowed */
+		pkts[12].valid = true;
+		pkts[13].valid = true;
+	}
+
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts));
+	return testapp_validate_traffic(test);
+}
+
 static int testapp_invalid_desc(struct test_spec *test)
 {
 	struct xsk_umem_info *umem = test->ifobj_tx->umem;
@@ -2047,6 +2140,16 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		ret = testapp_invalid_desc(test);
 		break;
 	}
+	case TEST_TYPE_ALIGNED_INV_DESC_MB:
+		test_spec_set_name(test, "ALIGNED_INV_DESC_MULTI_BUFF");
+		ret = testapp_invalid_desc_mb(test);
+		break;
+	case TEST_TYPE_UNALIGNED_INV_DESC_MB:
+		test_spec_set_name(test, "UNALIGNED_INV_DESC_MULTI_BUFF");
+		test->ifobj_tx->umem->unaligned_mode = true;
+		test->ifobj_rx->umem->unaligned_mode = true;
+		ret = testapp_invalid_desc_mb(test);
+		break;
 	case TEST_TYPE_UNALIGNED:
 		ret = testapp_unaligned(test);
 		break;
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 48cb48f1c5e66..7140943410dec 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -50,6 +50,9 @@
 #define RX_FULL_RXQSIZE 32
 #define UMEM_HEADROOM_TEST_SIZE 128
 #define XSK_UMEM__INVALID_FRAME_SIZE (MAX_ETH_JUMBO_SIZE + 1)
+#define XSK_UMEM__LARGE_FRAME_SIZE (3 * 1024)
+#define XSK_UMEM__MAX_FRAME_SIZE (4 * 1024)
+#define XSK_DESC__INVALID_OPTION (0xffff)
 #define HUGEPAGE_SIZE (2 * 1024 * 1024)
 #define PKT_DUMP_NB_TO_PRINT 16
 
@@ -87,6 +90,8 @@ enum test_type {
 	TEST_TYPE_XDP_METADATA_COUNT,
 	TEST_TYPE_RUN_TO_COMPLETION_MB,
 	TEST_TYPE_UNALIGNED_MB,
+	TEST_TYPE_ALIGNED_INV_DESC_MB,
+	TEST_TYPE_UNALIGNED_INV_DESC_MB,
 	TEST_TYPE_MAX
 };
 
@@ -119,6 +124,7 @@ struct pkt {
 	u32 len;
 	u32 pkt_nb;
 	bool valid;
+	u16 options;
 };
 
 struct pkt_stream {
@@ -126,6 +132,7 @@ struct pkt_stream {
 	u32 current_pkt_nb;
 	struct pkt *pkts;
 	u32 max_pkt_len;
+	bool verbatim;
 };
 
 struct ifobject;
-- 
GitLab


From f80ddbec476257a064ee0f57aa018bfc0f4d54d7 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 19 Jul 2023 15:24:19 +0200
Subject: [PATCH 0252/1806] selftests/xsk: add metadata copy test for
 multi-buff

Enable the already existing metadata copy test to also run in
multi-buffer mode with 9K packets.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-23-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/xsk_xdp_progs.c | 2 +-
 tools/testing/selftests/bpf/xskxceiver.c          | 7 ++++++-
 tools/testing/selftests/bpf/xskxceiver.h          | 1 +
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
index ac76e73637768..24369f2428537 100644
--- a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
+++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
@@ -29,7 +29,7 @@ SEC("xdp.frags") int xsk_xdp_drop(struct xdp_md *xdp)
 	return bpf_redirect_map(&xsk, 0, XDP_DROP);
 }
 
-SEC("xdp") int xsk_xdp_populate_metadata(struct xdp_md *xdp)
+SEC("xdp.frags") int xsk_xdp_populate_metadata(struct xdp_md *xdp)
 {
 	void *data, *data_meta;
 	struct xdp_info *meta;
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 59210cb33beba..4767d09d68934 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -1949,7 +1949,6 @@ static int testapp_xdp_metadata_count(struct test_spec *test)
 	int count = 0;
 	int key = 0;
 
-	test_spec_set_name(test, "XDP_METADATA_COUNT");
 	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_populate_metadata,
 			       skel_tx->progs.xsk_xdp_populate_metadata,
 			       skel_rx->maps.xsk, skel_tx->maps.xsk);
@@ -2163,6 +2162,12 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		ret = testapp_xdp_drop(test);
 		break;
 	case TEST_TYPE_XDP_METADATA_COUNT:
+		test_spec_set_name(test, "XDP_METADATA_COUNT");
+		ret = testapp_xdp_metadata_count(test);
+		break;
+	case TEST_TYPE_XDP_METADATA_COUNT_MB:
+		test_spec_set_name(test, "XDP_METADATA_COUNT_MULTI_BUFF");
+		test->mtu = MAX_ETH_JUMBO_SIZE;
 		ret = testapp_xdp_metadata_count(test);
 		break;
 	default:
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 7140943410dec..9e1f66e0a3b66 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -88,6 +88,7 @@ enum test_type {
 	TEST_TYPE_BPF_RES,
 	TEST_TYPE_XDP_DROP_HALF,
 	TEST_TYPE_XDP_METADATA_COUNT,
+	TEST_TYPE_XDP_METADATA_COUNT_MB,
 	TEST_TYPE_RUN_TO_COMPLETION_MB,
 	TEST_TYPE_UNALIGNED_MB,
 	TEST_TYPE_ALIGNED_INV_DESC_MB,
-- 
GitLab


From 807bf4da204938f01ad2e994ba92e82ac486ea2b Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 19 Jul 2023 15:24:20 +0200
Subject: [PATCH 0253/1806] selftests/xsk: add test for too many frags

Add a test that will exercise maximum number of supported fragments.
This number depends on mode of the test - for SKB and DRV it will be 18
whereas for ZC this is defined by a value from NETDEV_A_DEV_XDP_ZC_MAX_SEGS
netlink attribute.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> # made use of new netlink attribute
Link: https://lore.kernel.org/r/20230719132421.584801-24-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/xskxceiver.c | 54 +++++++++++++++++++++++-
 tools/testing/selftests/bpf/xskxceiver.h |  3 ++
 2 files changed, 55 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 4767d09d68934..3ff4367066401 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -1982,6 +1982,48 @@ static int testapp_poll_rxq_tmout(struct test_spec *test)
 	return testapp_validate_traffic_single_thread(test, test->ifobj_rx);
 }
 
+static int testapp_too_many_frags(struct test_spec *test)
+{
+	struct pkt pkts[2 * XSK_DESC__MAX_SKB_FRAGS + 2] = {};
+	u32 max_frags, i;
+
+	test_spec_set_name(test, "TOO_MANY_FRAGS");
+	if (test->mode == TEST_MODE_ZC)
+		max_frags = test->ifobj_tx->xdp_zc_max_segs;
+	else
+		max_frags = XSK_DESC__MAX_SKB_FRAGS;
+
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+
+	/* Valid packet for synch */
+	pkts[0].len = MIN_PKT_SIZE;
+	pkts[0].valid = true;
+
+	/* One valid packet with the max amount of frags */
+	for (i = 1; i < max_frags + 1; i++) {
+		pkts[i].len = MIN_PKT_SIZE;
+		pkts[i].options = XDP_PKT_CONTD;
+		pkts[i].valid = true;
+	}
+	pkts[max_frags].options = 0;
+
+	/* An invalid packet with the max amount of frags but signals packet
+	 * continues on the last frag
+	 */
+	for (i = max_frags + 1; i < 2 * max_frags + 1; i++) {
+		pkts[i].len = MIN_PKT_SIZE;
+		pkts[i].options = XDP_PKT_CONTD;
+		pkts[i].valid = false;
+	}
+
+	/* Valid packet for synch */
+	pkts[2 * max_frags + 1].len = MIN_PKT_SIZE;
+	pkts[2 * max_frags + 1].valid = true;
+
+	pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2);
+	return testapp_validate_traffic(test);
+}
+
 static int xsk_load_xdp_programs(struct ifobject *ifobj)
 {
 	ifobj->xdp_progs = xsk_xdp_progs__open_and_load();
@@ -2039,9 +2081,14 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 	}
 	if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG)
 		ifobj->multi_buff_supp = true;
-	if (query_opts.feature_flags & NETDEV_XDP_ACT_XSK_ZEROCOPY)
-		if (query_opts.xdp_zc_max_segs > 1)
+	if (query_opts.feature_flags & NETDEV_XDP_ACT_XSK_ZEROCOPY) {
+		if (query_opts.xdp_zc_max_segs > 1) {
 			ifobj->multi_buff_zc_supp = true;
+			ifobj->xdp_zc_max_segs = query_opts.xdp_zc_max_segs;
+		} else {
+			ifobj->xdp_zc_max_segs = 0;
+		}
+	}
 }
 
 static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type)
@@ -2170,6 +2217,9 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		test->mtu = MAX_ETH_JUMBO_SIZE;
 		ret = testapp_xdp_metadata_count(test);
 		break;
+	case TEST_TYPE_TOO_MANY_FRAGS:
+		ret = testapp_too_many_frags(test);
+		break;
 	default:
 		break;
 	}
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 9e1f66e0a3b66..233b66cef64a5 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -53,6 +53,7 @@
 #define XSK_UMEM__LARGE_FRAME_SIZE (3 * 1024)
 #define XSK_UMEM__MAX_FRAME_SIZE (4 * 1024)
 #define XSK_DESC__INVALID_OPTION (0xffff)
+#define XSK_DESC__MAX_SKB_FRAGS 18
 #define HUGEPAGE_SIZE (2 * 1024 * 1024)
 #define PKT_DUMP_NB_TO_PRINT 16
 
@@ -93,6 +94,7 @@ enum test_type {
 	TEST_TYPE_UNALIGNED_MB,
 	TEST_TYPE_ALIGNED_INV_DESC_MB,
 	TEST_TYPE_UNALIGNED_INV_DESC_MB,
+	TEST_TYPE_TOO_MANY_FRAGS,
 	TEST_TYPE_MAX
 };
 
@@ -155,6 +157,7 @@ struct ifobject {
 	int ifindex;
 	int mtu;
 	u32 bind_flags;
+	u32 xdp_zc_max_segs;
 	bool tx_on;
 	bool rx_on;
 	bool use_poll;
-- 
GitLab


From 3666bccab43a33904372eaa26936dabef3232497 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 19 Jul 2023 15:24:21 +0200
Subject: [PATCH 0254/1806] selftests/xsk: reset NIC settings to default after
 running test suite

Currently, when running ZC test suite, after finishing first run of test
suite and then switching to busy-poll tests within xskxceiver, such
errors are observed:

libbpf: Kernel error message: ice: MTU is too large for linear frames and XDP prog does not support frags
1..26
libbpf: Kernel error message: Native and generic XDP can't be active at the same time
Error attaching XDP program
not ok 1 [xskxceiver.c:xsk_reattach_xdp:1568]: ERROR: 17/"File exists"

this is because test suite ends with 9k MTU and native xdp program being
loaded. Busy-poll tests start non-multi-buffer tests for generic mode.
To fix this, let us introduce bash function that will reset NIC settings
to default (e.g. 1500 MTU and no xdp progs loaded) so that test suite
can continue without interrupts. It also means that after busy-poll
tests NIC will have those default settings, whereas right now it is left
with 9k MTU and xdp prog loaded in native mode.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-25-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_xsk.sh    | 5 +++++
 tools/testing/selftests/bpf/xsk_prereqs.sh | 7 +++++++
 2 files changed, 12 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index c2ad50f26b636..2aa5a3445056a 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -171,7 +171,10 @@ exec_xskxceiver
 
 if [ -z $ETH ]; then
 	cleanup_exit ${VETH0} ${VETH1}
+else
+	cleanup_iface ${ETH} ${MTU}
 fi
+
 TEST_NAME="XSK_SELFTESTS_${VETH0}_BUSY_POLL"
 busy_poll=1
 
@@ -184,6 +187,8 @@ exec_xskxceiver
 
 if [ -z $ETH ]; then
 	cleanup_exit ${VETH0} ${VETH1}
+else
+	cleanup_iface ${ETH} ${MTU}
 fi
 
 failures=0
diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh
index ae697a10a0569..29175682c44d6 100755
--- a/tools/testing/selftests/bpf/xsk_prereqs.sh
+++ b/tools/testing/selftests/bpf/xsk_prereqs.sh
@@ -53,6 +53,13 @@ test_exit()
 	exit 1
 }
 
+cleanup_iface()
+{
+	ip link set $1 mtu $2
+	ip link set $1 xdp off
+	ip link set $1 xdpgeneric off
+}
+
 clear_configs()
 {
 	[ $(ip link show $1 &>/dev/null; echo $?;) == 0 ] &&
-- 
GitLab


From 053c8e1f235dc3f69d13375b32f4209228e1cb96 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 19 Jul 2023 16:08:51 +0200
Subject: [PATCH 0255/1806] bpf: Add generic attach/detach/query API for
 multi-progs

This adds a generic layer called bpf_mprog which can be reused by different
attachment layers to enable multi-program attachment and dependency resolution.
In-kernel users of the bpf_mprog don't need to care about the dependency
resolution internals, they can just consume it with few API calls.

The initial idea of having a generic API sparked out of discussion [0] from an
earlier revision of this work where tc's priority was reused and exposed via
BPF uapi as a way to coordinate dependencies among tc BPF programs, similar
as-is for classic tc BPF. The feedback was that priority provides a bad user
experience and is hard to use [1], e.g.:

  I cannot help but feel that priority logic copy-paste from old tc, netfilter
  and friends is done because "that's how things were done in the past". [...]
  Priority gets exposed everywhere in uapi all the way to bpftool when it's
  right there for users to understand. And that's the main problem with it.

  The user don't want to and don't need to be aware of it, but uapi forces them
  to pick the priority. [...] Your cover letter [0] example proves that in
  real life different service pick the same priority. They simply don't know
  any better. Priority is an unnecessary magic that apps _have_ to pick, so
  they just copy-paste and everyone ends up using the same.

The course of the discussion showed more and more the need for a generic,
reusable API where the "same look and feel" can be applied for various other
program types beyond just tc BPF, for example XDP today does not have multi-
program support in kernel, but also there was interest around this API for
improving management of cgroup program types. Such common multi-program
management concept is useful for BPF management daemons or user space BPF
applications coordinating internally about their attachments.

Both from Cilium and Meta side [2], we've collected the following requirements
for a generic attach/detach/query API for multi-progs which has been implemented
as part of this work:

  - Support prog-based attach/detach and link API
  - Dependency directives (can also be combined):
    - BPF_F_{BEFORE,AFTER} with relative_{fd,id} which can be {prog,link,none}
      - BPF_F_ID flag as {fd,id} toggle; the rationale for id is so that user
        space application does not need CAP_SYS_ADMIN to retrieve foreign fds
        via bpf_*_get_fd_by_id()
      - BPF_F_LINK flag as {prog,link} toggle
      - If relative_{fd,id} is none, then BPF_F_BEFORE will just prepend, and
        BPF_F_AFTER will just append for attaching
      - Enforced only at attach time
    - BPF_F_REPLACE with replace_bpf_fd which can be prog, links have their
      own infra for replacing their internal prog
    - If no flags are set, then it's default append behavior for attaching
  - Internal revision counter and optionally being able to pass expected_revision
  - User space application can query current state with revision, and pass it
    along for attachment to assert current state before doing updates
  - Query also gets extension for link_ids array and link_attach_flags:
    - prog_ids are always filled with program IDs
    - link_ids are filled with link IDs when link was used, otherwise 0
    - {prog,link}_attach_flags for holding {prog,link}-specific flags
  - Must be easy to integrate/reuse for in-kernel users

The uapi-side changes needed for supporting bpf_mprog are rather minimal,
consisting of the additions of the attachment flags, revision counter, and
expanding existing union with relative_{fd,id} member.

The bpf_mprog framework consists of an bpf_mprog_entry object which holds
an array of bpf_mprog_fp (fast-path structure). The bpf_mprog_cp (control-path
structure) is part of bpf_mprog_bundle. Both have been separated, so that
fast-path gets efficient packing of bpf_prog pointers for maximum cache
efficiency. Also, array has been chosen instead of linked list or other
structures to remove unnecessary indirections for a fast point-to-entry in
tc for BPF.

The bpf_mprog_entry comes as a pair via bpf_mprog_bundle so that in case of
updates the peer bpf_mprog_entry is populated and then just swapped which
avoids additional allocations that could otherwise fail, for example, in
detach case. bpf_mprog_{fp,cp} arrays are currently static, but they could
be converted to dynamic allocation if necessary at a point in future.
Locking is deferred to the in-kernel user of bpf_mprog, for example, in case
of tcx which uses this API in the next patch, it piggybacks on rtnl.

An extensive test suite for checking all aspects of this API for prog-based
attach/detach and link API comes as BPF selftests in this series.

Thanks also to Andrii Nakryiko for early API discussions wrt Meta's BPF prog
management.

  [0] https://lore.kernel.org/bpf/20221004231143.19190-1-daniel@iogearbox.net
  [1] https://lore.kernel.org/bpf/CAADnVQ+gEY3FjCR=+DmjDR4gp5bOYZUFJQXj4agKFHT9CQPZBw@mail.gmail.com
  [2] http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20230719140858.13224-2-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 MAINTAINERS                    |   1 +
 include/linux/bpf_mprog.h      | 318 +++++++++++++++++++++++
 include/uapi/linux/bpf.h       |  36 ++-
 kernel/bpf/Makefile            |   2 +-
 kernel/bpf/mprog.c             | 445 +++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  36 ++-
 6 files changed, 821 insertions(+), 17 deletions(-)
 create mode 100644 include/linux/bpf_mprog.h
 create mode 100644 kernel/bpf/mprog.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 9a5863f1b0165..678bef9f60b40 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3684,6 +3684,7 @@ F:	include/linux/filter.h
 F:	include/linux/tnum.h
 F:	kernel/bpf/core.c
 F:	kernel/bpf/dispatcher.c
+F:	kernel/bpf/mprog.c
 F:	kernel/bpf/syscall.c
 F:	kernel/bpf/tnum.c
 F:	kernel/bpf/trampoline.c
diff --git a/include/linux/bpf_mprog.h b/include/linux/bpf_mprog.h
new file mode 100644
index 0000000000000..6feefec434224
--- /dev/null
+++ b/include/linux/bpf_mprog.h
@@ -0,0 +1,318 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Isovalent */
+#ifndef __BPF_MPROG_H
+#define __BPF_MPROG_H
+
+#include <linux/bpf.h>
+
+/* bpf_mprog framework:
+ *
+ * bpf_mprog is a generic layer for multi-program attachment. In-kernel users
+ * of the bpf_mprog don't need to care about the dependency resolution
+ * internals, they can just consume it with few API calls. Currently available
+ * dependency directives are BPF_F_{BEFORE,AFTER} which enable insertion of
+ * a BPF program or BPF link relative to an existing BPF program or BPF link
+ * inside the multi-program array as well as prepend and append behavior if
+ * no relative object was specified, see corresponding selftests for concrete
+ * examples (e.g. tc_links and tc_opts test cases of test_progs).
+ *
+ * Usage of bpf_mprog_{attach,detach,query}() core APIs with pseudo code:
+ *
+ *  Attach case:
+ *
+ *   struct bpf_mprog_entry *entry, *entry_new;
+ *   int ret;
+ *
+ *   // bpf_mprog user-side lock
+ *   // fetch active @entry from attach location
+ *   [...]
+ *   ret = bpf_mprog_attach(entry, &entry_new, [...]);
+ *   if (!ret) {
+ *       if (entry != entry_new) {
+ *           // swap @entry to @entry_new at attach location
+ *           // ensure there are no inflight users of @entry:
+ *           synchronize_rcu();
+ *       }
+ *       bpf_mprog_commit(entry);
+ *   } else {
+ *       // error path, bail out, propagate @ret
+ *   }
+ *   // bpf_mprog user-side unlock
+ *
+ *  Detach case:
+ *
+ *   struct bpf_mprog_entry *entry, *entry_new;
+ *   int ret;
+ *
+ *   // bpf_mprog user-side lock
+ *   // fetch active @entry from attach location
+ *   [...]
+ *   ret = bpf_mprog_detach(entry, &entry_new, [...]);
+ *   if (!ret) {
+ *       // all (*) marked is optional and depends on the use-case
+ *       // whether bpf_mprog_bundle should be freed or not
+ *       if (!bpf_mprog_total(entry_new))     (*)
+ *           entry_new = NULL                 (*)
+ *       // swap @entry to @entry_new at attach location
+ *       // ensure there are no inflight users of @entry:
+ *       synchronize_rcu();
+ *       bpf_mprog_commit(entry);
+ *       if (!entry_new)                      (*)
+ *           // free bpf_mprog_bundle         (*)
+ *   } else {
+ *       // error path, bail out, propagate @ret
+ *   }
+ *   // bpf_mprog user-side unlock
+ *
+ *  Query case:
+ *
+ *   struct bpf_mprog_entry *entry;
+ *   int ret;
+ *
+ *   // bpf_mprog user-side lock
+ *   // fetch active @entry from attach location
+ *   [...]
+ *   ret = bpf_mprog_query(attr, uattr, entry);
+ *   // bpf_mprog user-side unlock
+ *
+ *  Data/fast path:
+ *
+ *   struct bpf_mprog_entry *entry;
+ *   struct bpf_mprog_fp *fp;
+ *   struct bpf_prog *prog;
+ *   int ret = [...];
+ *
+ *   rcu_read_lock();
+ *   // fetch active @entry from attach location
+ *   [...]
+ *   bpf_mprog_foreach_prog(entry, fp, prog) {
+ *       ret = bpf_prog_run(prog, [...]);
+ *       // process @ret from program
+ *   }
+ *   [...]
+ *   rcu_read_unlock();
+ *
+ * bpf_mprog locking considerations:
+ *
+ * bpf_mprog_{attach,detach,query}() must be protected by an external lock
+ * (like RTNL in case of tcx).
+ *
+ * bpf_mprog_entry pointer can be an __rcu annotated pointer (in case of tcx
+ * the netdevice has tcx_ingress and tcx_egress __rcu pointer) which gets
+ * updated via rcu_assign_pointer() pointing to the active bpf_mprog_entry of
+ * the bpf_mprog_bundle.
+ *
+ * Fast path accesses the active bpf_mprog_entry within RCU critical section
+ * (in case of tcx it runs in NAPI which provides RCU protection there,
+ * other users might need explicit rcu_read_lock()). The bpf_mprog_commit()
+ * assumes that for the old bpf_mprog_entry there are no inflight users
+ * anymore.
+ *
+ * The READ_ONCE()/WRITE_ONCE() pairing for bpf_mprog_fp's prog access is for
+ * the replacement case where we don't swap the bpf_mprog_entry.
+ */
+
+#define bpf_mprog_foreach_tuple(entry, fp, cp, t)			\
+	for (fp = &entry->fp_items[0], cp = &entry->parent->cp_items[0];\
+	     ({								\
+		t.prog = READ_ONCE(fp->prog);				\
+		t.link = cp->link;					\
+		t.prog;							\
+	      });							\
+	     fp++, cp++)
+
+#define bpf_mprog_foreach_prog(entry, fp, p)				\
+	for (fp = &entry->fp_items[0];					\
+	     (p = READ_ONCE(fp->prog));					\
+	     fp++)
+
+#define BPF_MPROG_MAX 64
+
+struct bpf_mprog_fp {
+	struct bpf_prog *prog;
+};
+
+struct bpf_mprog_cp {
+	struct bpf_link *link;
+};
+
+struct bpf_mprog_entry {
+	struct bpf_mprog_fp fp_items[BPF_MPROG_MAX];
+	struct bpf_mprog_bundle *parent;
+};
+
+struct bpf_mprog_bundle {
+	struct bpf_mprog_entry a;
+	struct bpf_mprog_entry b;
+	struct bpf_mprog_cp cp_items[BPF_MPROG_MAX];
+	struct bpf_prog *ref;
+	atomic64_t revision;
+	u32 count;
+};
+
+struct bpf_tuple {
+	struct bpf_prog *prog;
+	struct bpf_link *link;
+};
+
+static inline struct bpf_mprog_entry *
+bpf_mprog_peer(const struct bpf_mprog_entry *entry)
+{
+	if (entry == &entry->parent->a)
+		return &entry->parent->b;
+	else
+		return &entry->parent->a;
+}
+
+static inline void bpf_mprog_bundle_init(struct bpf_mprog_bundle *bundle)
+{
+	BUILD_BUG_ON(sizeof(bundle->a.fp_items[0]) > sizeof(u64));
+	BUILD_BUG_ON(ARRAY_SIZE(bundle->a.fp_items) !=
+		     ARRAY_SIZE(bundle->cp_items));
+
+	memset(bundle, 0, sizeof(*bundle));
+	atomic64_set(&bundle->revision, 1);
+	bundle->a.parent = bundle;
+	bundle->b.parent = bundle;
+}
+
+static inline void bpf_mprog_inc(struct bpf_mprog_entry *entry)
+{
+	entry->parent->count++;
+}
+
+static inline void bpf_mprog_dec(struct bpf_mprog_entry *entry)
+{
+	entry->parent->count--;
+}
+
+static inline int bpf_mprog_max(void)
+{
+	return ARRAY_SIZE(((struct bpf_mprog_entry *)NULL)->fp_items) - 1;
+}
+
+static inline int bpf_mprog_total(struct bpf_mprog_entry *entry)
+{
+	int total = entry->parent->count;
+
+	WARN_ON_ONCE(total > bpf_mprog_max());
+	return total;
+}
+
+static inline bool bpf_mprog_exists(struct bpf_mprog_entry *entry,
+				    struct bpf_prog *prog)
+{
+	const struct bpf_mprog_fp *fp;
+	const struct bpf_prog *tmp;
+
+	bpf_mprog_foreach_prog(entry, fp, tmp) {
+		if (tmp == prog)
+			return true;
+	}
+	return false;
+}
+
+static inline void bpf_mprog_mark_for_release(struct bpf_mprog_entry *entry,
+					      struct bpf_tuple *tuple)
+{
+	WARN_ON_ONCE(entry->parent->ref);
+	if (!tuple->link)
+		entry->parent->ref = tuple->prog;
+}
+
+static inline void bpf_mprog_complete_release(struct bpf_mprog_entry *entry)
+{
+	/* In the non-link case prog deletions can only drop the reference
+	 * to the prog after the bpf_mprog_entry got swapped and the
+	 * bpf_mprog ensured that there are no inflight users anymore.
+	 *
+	 * Paired with bpf_mprog_mark_for_release().
+	 */
+	if (entry->parent->ref) {
+		bpf_prog_put(entry->parent->ref);
+		entry->parent->ref = NULL;
+	}
+}
+
+static inline void bpf_mprog_revision_new(struct bpf_mprog_entry *entry)
+{
+	atomic64_inc(&entry->parent->revision);
+}
+
+static inline void bpf_mprog_commit(struct bpf_mprog_entry *entry)
+{
+	bpf_mprog_complete_release(entry);
+	bpf_mprog_revision_new(entry);
+}
+
+static inline u64 bpf_mprog_revision(struct bpf_mprog_entry *entry)
+{
+	return atomic64_read(&entry->parent->revision);
+}
+
+static inline void bpf_mprog_entry_copy(struct bpf_mprog_entry *dst,
+					struct bpf_mprog_entry *src)
+{
+	memcpy(dst->fp_items, src->fp_items, sizeof(src->fp_items));
+}
+
+static inline void bpf_mprog_entry_grow(struct bpf_mprog_entry *entry, int idx)
+{
+	int total = bpf_mprog_total(entry);
+
+	memmove(entry->fp_items + idx + 1,
+		entry->fp_items + idx,
+		(total - idx) * sizeof(struct bpf_mprog_fp));
+
+	memmove(entry->parent->cp_items + idx + 1,
+		entry->parent->cp_items + idx,
+		(total - idx) * sizeof(struct bpf_mprog_cp));
+}
+
+static inline void bpf_mprog_entry_shrink(struct bpf_mprog_entry *entry, int idx)
+{
+	/* Total array size is needed in this case to enure the NULL
+	 * entry is copied at the end.
+	 */
+	int total = ARRAY_SIZE(entry->fp_items);
+
+	memmove(entry->fp_items + idx,
+		entry->fp_items + idx + 1,
+		(total - idx - 1) * sizeof(struct bpf_mprog_fp));
+
+	memmove(entry->parent->cp_items + idx,
+		entry->parent->cp_items + idx + 1,
+		(total - idx - 1) * sizeof(struct bpf_mprog_cp));
+}
+
+static inline void bpf_mprog_read(struct bpf_mprog_entry *entry, u32 idx,
+				  struct bpf_mprog_fp **fp,
+				  struct bpf_mprog_cp **cp)
+{
+	*fp = &entry->fp_items[idx];
+	*cp = &entry->parent->cp_items[idx];
+}
+
+static inline void bpf_mprog_write(struct bpf_mprog_fp *fp,
+				   struct bpf_mprog_cp *cp,
+				   struct bpf_tuple *tuple)
+{
+	WRITE_ONCE(fp->prog, tuple->prog);
+	cp->link = tuple->link;
+}
+
+int bpf_mprog_attach(struct bpf_mprog_entry *entry,
+		     struct bpf_mprog_entry **entry_new,
+		     struct bpf_prog *prog_new, struct bpf_link *link,
+		     struct bpf_prog *prog_old,
+		     u32 flags, u32 id_or_fd, u64 revision);
+
+int bpf_mprog_detach(struct bpf_mprog_entry *entry,
+		     struct bpf_mprog_entry **entry_new,
+		     struct bpf_prog *prog, struct bpf_link *link,
+		     u32 flags, u32 id_or_fd, u64 revision);
+
+int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr,
+		    struct bpf_mprog_entry *entry);
+
+#endif /* __BPF_MPROG_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9ed59896ebc5a..d4c07e4353362 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1113,7 +1113,12 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 #define BPF_F_ALLOW_MULTI	(1U << 1)
+/* Generic attachment flags. */
 #define BPF_F_REPLACE		(1U << 2)
+#define BPF_F_BEFORE		(1U << 3)
+#define BPF_F_AFTER		(1U << 4)
+#define BPF_F_ID		(1U << 5)
+#define BPF_F_LINK		BPF_F_LINK /* 1 << 13 */
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -1444,14 +1449,19 @@ union bpf_attr {
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
-		__u32		target_fd;	/* container object to attach to */
-		__u32		attach_bpf_fd;	/* eBPF program to attach */
+		union {
+			__u32	target_fd;	/* target object to attach to or ... */
+			__u32	target_ifindex;	/* target ifindex */
+		};
+		__u32		attach_bpf_fd;
 		__u32		attach_type;
 		__u32		attach_flags;
-		__u32		replace_bpf_fd;	/* previously attached eBPF
-						 * program to replace if
-						 * BPF_F_REPLACE is used
-						 */
+		__u32		replace_bpf_fd;
+		union {
+			__u32	relative_fd;
+			__u32	relative_id;
+		};
+		__u64		expected_revision;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
@@ -1497,16 +1507,26 @@ union bpf_attr {
 	} info;
 
 	struct { /* anonymous struct used by BPF_PROG_QUERY command */
-		__u32		target_fd;	/* container object to query */
+		union {
+			__u32	target_fd;	/* target object to query or ... */
+			__u32	target_ifindex;	/* target ifindex */
+		};
 		__u32		attach_type;
 		__u32		query_flags;
 		__u32		attach_flags;
 		__aligned_u64	prog_ids;
-		__u32		prog_cnt;
+		union {
+			__u32	prog_cnt;
+			__u32	count;
+		};
+		__u32		:32;
 		/* output: per-program attach_flags.
 		 * not allowed to be set during effective query.
 		 */
 		__aligned_u64	prog_attach_flags;
+		__aligned_u64	link_ids;
+		__aligned_u64	link_attach_flags;
+		__u64		revision;
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 1d3892168d329..1bea2eb912cdb 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
 obj-${CONFIG_BPF_LSM}	  += bpf_inode_storage.o
-obj-$(CONFIG_BPF_SYSCALL) += disasm.o
+obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o
 obj-$(CONFIG_BPF_JIT) += trampoline.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o
 obj-$(CONFIG_BPF_JIT) += dispatcher.o
diff --git a/kernel/bpf/mprog.c b/kernel/bpf/mprog.c
new file mode 100644
index 0000000000000..f7816d2bc3e4a
--- /dev/null
+++ b/kernel/bpf/mprog.c
@@ -0,0 +1,445 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <linux/bpf.h>
+#include <linux/bpf_mprog.h>
+
+static int bpf_mprog_link(struct bpf_tuple *tuple,
+			  u32 id_or_fd, u32 flags,
+			  enum bpf_prog_type type)
+{
+	struct bpf_link *link = ERR_PTR(-EINVAL);
+	bool id = flags & BPF_F_ID;
+
+	if (id)
+		link = bpf_link_by_id(id_or_fd);
+	else if (id_or_fd)
+		link = bpf_link_get_from_fd(id_or_fd);
+	if (IS_ERR(link))
+		return PTR_ERR(link);
+	if (type && link->prog->type != type) {
+		bpf_link_put(link);
+		return -EINVAL;
+	}
+
+	tuple->link = link;
+	tuple->prog = link->prog;
+	return 0;
+}
+
+static int bpf_mprog_prog(struct bpf_tuple *tuple,
+			  u32 id_or_fd, u32 flags,
+			  enum bpf_prog_type type)
+{
+	struct bpf_prog *prog = ERR_PTR(-EINVAL);
+	bool id = flags & BPF_F_ID;
+
+	if (id)
+		prog = bpf_prog_by_id(id_or_fd);
+	else if (id_or_fd)
+		prog = bpf_prog_get(id_or_fd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+	if (type && prog->type != type) {
+		bpf_prog_put(prog);
+		return -EINVAL;
+	}
+
+	tuple->link = NULL;
+	tuple->prog = prog;
+	return 0;
+}
+
+static int bpf_mprog_tuple_relative(struct bpf_tuple *tuple,
+				    u32 id_or_fd, u32 flags,
+				    enum bpf_prog_type type)
+{
+	bool link = flags & BPF_F_LINK;
+	bool id = flags & BPF_F_ID;
+
+	memset(tuple, 0, sizeof(*tuple));
+	if (link)
+		return bpf_mprog_link(tuple, id_or_fd, flags, type);
+	/* If no relevant flag is set and no id_or_fd was passed, then
+	 * tuple link/prog is just NULLed. This is the case when before/
+	 * after selects first/last position without passing fd.
+	 */
+	if (!id && !id_or_fd)
+		return 0;
+	return bpf_mprog_prog(tuple, id_or_fd, flags, type);
+}
+
+static void bpf_mprog_tuple_put(struct bpf_tuple *tuple)
+{
+	if (tuple->link)
+		bpf_link_put(tuple->link);
+	else if (tuple->prog)
+		bpf_prog_put(tuple->prog);
+}
+
+/* The bpf_mprog_{replace,delete}() operate on exact idx position with the
+ * one exception that for deletion we support delete from front/back. In
+ * case of front idx is -1, in case of back idx is bpf_mprog_total(entry).
+ * Adjustment to first and last entry is trivial. The bpf_mprog_insert()
+ * we have to deal with the following cases:
+ *
+ * idx + before:
+ *
+ * Insert P4 before P3: idx for old array is 1, idx for new array is 2,
+ * hence we adjust target idx for the new array, so that memmove copies
+ * P1 and P2 to the new entry, and we insert P4 into idx 2. Inserting
+ * before P1 would have old idx -1 and new idx 0.
+ *
+ * +--+--+--+     +--+--+--+--+     +--+--+--+--+
+ * |P1|P2|P3| ==> |P1|P2|  |P3| ==> |P1|P2|P4|P3|
+ * +--+--+--+     +--+--+--+--+     +--+--+--+--+
+ *
+ * idx + after:
+ *
+ * Insert P4 after P2: idx for old array is 2, idx for new array is 2.
+ * Again, memmove copies P1 and P2 to the new entry, and we insert P4
+ * into idx 2. Inserting after P3 would have both old/new idx at 4 aka
+ * bpf_mprog_total(entry).
+ *
+ * +--+--+--+     +--+--+--+--+     +--+--+--+--+
+ * |P1|P2|P3| ==> |P1|P2|  |P3| ==> |P1|P2|P4|P3|
+ * +--+--+--+     +--+--+--+--+     +--+--+--+--+
+ */
+static int bpf_mprog_replace(struct bpf_mprog_entry *entry,
+			     struct bpf_mprog_entry **entry_new,
+			     struct bpf_tuple *ntuple, int idx)
+{
+	struct bpf_mprog_fp *fp;
+	struct bpf_mprog_cp *cp;
+	struct bpf_prog *oprog;
+
+	bpf_mprog_read(entry, idx, &fp, &cp);
+	oprog = READ_ONCE(fp->prog);
+	bpf_mprog_write(fp, cp, ntuple);
+	if (!ntuple->link) {
+		WARN_ON_ONCE(cp->link);
+		bpf_prog_put(oprog);
+	}
+	*entry_new = entry;
+	return 0;
+}
+
+static int bpf_mprog_insert(struct bpf_mprog_entry *entry,
+			    struct bpf_mprog_entry **entry_new,
+			    struct bpf_tuple *ntuple, int idx, u32 flags)
+{
+	int total = bpf_mprog_total(entry);
+	struct bpf_mprog_entry *peer;
+	struct bpf_mprog_fp *fp;
+	struct bpf_mprog_cp *cp;
+
+	peer = bpf_mprog_peer(entry);
+	bpf_mprog_entry_copy(peer, entry);
+	if (idx == total)
+		goto insert;
+	else if (flags & BPF_F_BEFORE)
+		idx += 1;
+	bpf_mprog_entry_grow(peer, idx);
+insert:
+	bpf_mprog_read(peer, idx, &fp, &cp);
+	bpf_mprog_write(fp, cp, ntuple);
+	bpf_mprog_inc(peer);
+	*entry_new = peer;
+	return 0;
+}
+
+static int bpf_mprog_delete(struct bpf_mprog_entry *entry,
+			    struct bpf_mprog_entry **entry_new,
+			    struct bpf_tuple *dtuple, int idx)
+{
+	int total = bpf_mprog_total(entry);
+	struct bpf_mprog_entry *peer;
+
+	peer = bpf_mprog_peer(entry);
+	bpf_mprog_entry_copy(peer, entry);
+	if (idx == -1)
+		idx = 0;
+	else if (idx == total)
+		idx = total - 1;
+	bpf_mprog_entry_shrink(peer, idx);
+	bpf_mprog_dec(peer);
+	bpf_mprog_mark_for_release(peer, dtuple);
+	*entry_new = peer;
+	return 0;
+}
+
+/* In bpf_mprog_pos_*() we evaluate the target position for the BPF
+ * program/link that needs to be replaced, inserted or deleted for
+ * each "rule" independently. If all rules agree on that position
+ * or existing element, then enact replacement, addition or deletion.
+ * If this is not the case, then the request cannot be satisfied and
+ * we bail out with an error.
+ */
+static int bpf_mprog_pos_exact(struct bpf_mprog_entry *entry,
+			       struct bpf_tuple *tuple)
+{
+	struct bpf_mprog_fp *fp;
+	struct bpf_mprog_cp *cp;
+	int i;
+
+	for (i = 0; i < bpf_mprog_total(entry); i++) {
+		bpf_mprog_read(entry, i, &fp, &cp);
+		if (tuple->prog == READ_ONCE(fp->prog))
+			return tuple->link == cp->link ? i : -EBUSY;
+	}
+	return -ENOENT;
+}
+
+static int bpf_mprog_pos_before(struct bpf_mprog_entry *entry,
+				struct bpf_tuple *tuple)
+{
+	struct bpf_mprog_fp *fp;
+	struct bpf_mprog_cp *cp;
+	int i;
+
+	for (i = 0; i < bpf_mprog_total(entry); i++) {
+		bpf_mprog_read(entry, i, &fp, &cp);
+		if (tuple->prog == READ_ONCE(fp->prog) &&
+		    (!tuple->link || tuple->link == cp->link))
+			return i - 1;
+	}
+	return tuple->prog ? -ENOENT : -1;
+}
+
+static int bpf_mprog_pos_after(struct bpf_mprog_entry *entry,
+			       struct bpf_tuple *tuple)
+{
+	struct bpf_mprog_fp *fp;
+	struct bpf_mprog_cp *cp;
+	int i;
+
+	for (i = 0; i < bpf_mprog_total(entry); i++) {
+		bpf_mprog_read(entry, i, &fp, &cp);
+		if (tuple->prog == READ_ONCE(fp->prog) &&
+		    (!tuple->link || tuple->link == cp->link))
+			return i + 1;
+	}
+	return tuple->prog ? -ENOENT : bpf_mprog_total(entry);
+}
+
+int bpf_mprog_attach(struct bpf_mprog_entry *entry,
+		     struct bpf_mprog_entry **entry_new,
+		     struct bpf_prog *prog_new, struct bpf_link *link,
+		     struct bpf_prog *prog_old,
+		     u32 flags, u32 id_or_fd, u64 revision)
+{
+	struct bpf_tuple rtuple, ntuple = {
+		.prog = prog_new,
+		.link = link,
+	}, otuple = {
+		.prog = prog_old,
+		.link = link,
+	};
+	int ret, idx = -ERANGE, tidx;
+
+	if (revision && revision != bpf_mprog_revision(entry))
+		return -ESTALE;
+	if (bpf_mprog_exists(entry, prog_new))
+		return -EEXIST;
+	ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd,
+				       flags & ~BPF_F_REPLACE,
+				       prog_new->type);
+	if (ret)
+		return ret;
+	if (flags & BPF_F_REPLACE) {
+		tidx = bpf_mprog_pos_exact(entry, &otuple);
+		if (tidx < 0) {
+			ret = tidx;
+			goto out;
+		}
+		idx = tidx;
+	}
+	if (flags & BPF_F_BEFORE) {
+		tidx = bpf_mprog_pos_before(entry, &rtuple);
+		if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+			ret = tidx < -1 ? tidx : -ERANGE;
+			goto out;
+		}
+		idx = tidx;
+	}
+	if (flags & BPF_F_AFTER) {
+		tidx = bpf_mprog_pos_after(entry, &rtuple);
+		if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+			ret = tidx < 0 ? tidx : -ERANGE;
+			goto out;
+		}
+		idx = tidx;
+	}
+	if (idx < -1) {
+		if (rtuple.prog || flags) {
+			ret = -EINVAL;
+			goto out;
+		}
+		idx = bpf_mprog_total(entry);
+		flags = BPF_F_AFTER;
+	}
+	if (idx >= bpf_mprog_max()) {
+		ret = -ERANGE;
+		goto out;
+	}
+	if (flags & BPF_F_REPLACE)
+		ret = bpf_mprog_replace(entry, entry_new, &ntuple, idx);
+	else
+		ret = bpf_mprog_insert(entry, entry_new, &ntuple, idx, flags);
+out:
+	bpf_mprog_tuple_put(&rtuple);
+	return ret;
+}
+
+static int bpf_mprog_fetch(struct bpf_mprog_entry *entry,
+			   struct bpf_tuple *tuple, int idx)
+{
+	int total = bpf_mprog_total(entry);
+	struct bpf_mprog_cp *cp;
+	struct bpf_mprog_fp *fp;
+	struct bpf_prog *prog;
+	struct bpf_link *link;
+
+	if (idx == -1)
+		idx = 0;
+	else if (idx == total)
+		idx = total - 1;
+	bpf_mprog_read(entry, idx, &fp, &cp);
+	prog = READ_ONCE(fp->prog);
+	link = cp->link;
+	/* The deletion request can either be without filled tuple in which
+	 * case it gets populated here based on idx, or with filled tuple
+	 * where the only thing we end up doing is the WARN_ON_ONCE() assert.
+	 * If we hit a BPF link at the given index, it must not be removed
+	 * from opts path.
+	 */
+	if (link && !tuple->link)
+		return -EBUSY;
+	WARN_ON_ONCE(tuple->prog && tuple->prog != prog);
+	WARN_ON_ONCE(tuple->link && tuple->link != link);
+	tuple->prog = prog;
+	tuple->link = link;
+	return 0;
+}
+
+int bpf_mprog_detach(struct bpf_mprog_entry *entry,
+		     struct bpf_mprog_entry **entry_new,
+		     struct bpf_prog *prog, struct bpf_link *link,
+		     u32 flags, u32 id_or_fd, u64 revision)
+{
+	struct bpf_tuple rtuple, dtuple = {
+		.prog = prog,
+		.link = link,
+	};
+	int ret, idx = -ERANGE, tidx;
+
+	if (flags & BPF_F_REPLACE)
+		return -EINVAL;
+	if (revision && revision != bpf_mprog_revision(entry))
+		return -ESTALE;
+	ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, flags,
+				       prog ? prog->type :
+				       BPF_PROG_TYPE_UNSPEC);
+	if (ret)
+		return ret;
+	if (dtuple.prog) {
+		tidx = bpf_mprog_pos_exact(entry, &dtuple);
+		if (tidx < 0) {
+			ret = tidx;
+			goto out;
+		}
+		idx = tidx;
+	}
+	if (flags & BPF_F_BEFORE) {
+		tidx = bpf_mprog_pos_before(entry, &rtuple);
+		if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+			ret = tidx < -1 ? tidx : -ERANGE;
+			goto out;
+		}
+		idx = tidx;
+	}
+	if (flags & BPF_F_AFTER) {
+		tidx = bpf_mprog_pos_after(entry, &rtuple);
+		if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+			ret = tidx < 0 ? tidx : -ERANGE;
+			goto out;
+		}
+		idx = tidx;
+	}
+	if (idx < -1) {
+		if (rtuple.prog || flags) {
+			ret = -EINVAL;
+			goto out;
+		}
+		idx = bpf_mprog_total(entry);
+		flags = BPF_F_AFTER;
+	}
+	if (idx >= bpf_mprog_max()) {
+		ret = -ERANGE;
+		goto out;
+	}
+	ret = bpf_mprog_fetch(entry, &dtuple, idx);
+	if (ret)
+		goto out;
+	ret = bpf_mprog_delete(entry, entry_new, &dtuple, idx);
+out:
+	bpf_mprog_tuple_put(&rtuple);
+	return ret;
+}
+
+int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr,
+		    struct bpf_mprog_entry *entry)
+{
+	u32 __user *uprog_flags, *ulink_flags;
+	u32 __user *uprog_id, *ulink_id;
+	struct bpf_mprog_fp *fp;
+	struct bpf_mprog_cp *cp;
+	struct bpf_prog *prog;
+	const u32 flags = 0;
+	int i, ret = 0;
+	u32 id, count;
+	u64 revision;
+
+	if (attr->query.query_flags || attr->query.attach_flags)
+		return -EINVAL;
+	revision = bpf_mprog_revision(entry);
+	count = bpf_mprog_total(entry);
+	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+		return -EFAULT;
+	if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision)))
+		return -EFAULT;
+	if (copy_to_user(&uattr->query.count, &count, sizeof(count)))
+		return -EFAULT;
+	uprog_id = u64_to_user_ptr(attr->query.prog_ids);
+	uprog_flags = u64_to_user_ptr(attr->query.prog_attach_flags);
+	ulink_id = u64_to_user_ptr(attr->query.link_ids);
+	ulink_flags = u64_to_user_ptr(attr->query.link_attach_flags);
+	if (attr->query.count == 0 || !uprog_id || !count)
+		return 0;
+	if (attr->query.count < count) {
+		count = attr->query.count;
+		ret = -ENOSPC;
+	}
+	for (i = 0; i < bpf_mprog_max(); i++) {
+		bpf_mprog_read(entry, i, &fp, &cp);
+		prog = READ_ONCE(fp->prog);
+		if (!prog)
+			break;
+		id = prog->aux->id;
+		if (copy_to_user(uprog_id + i, &id, sizeof(id)))
+			return -EFAULT;
+		if (uprog_flags &&
+		    copy_to_user(uprog_flags + i, &flags, sizeof(flags)))
+			return -EFAULT;
+		id = cp->link ? cp->link->id : 0;
+		if (ulink_id &&
+		    copy_to_user(ulink_id + i, &id, sizeof(id)))
+			return -EFAULT;
+		if (ulink_flags &&
+		    copy_to_user(ulink_flags + i, &flags, sizeof(flags)))
+			return -EFAULT;
+		if (i + 1 == count)
+			break;
+	}
+	return ret;
+}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 600d0caebbd8a..1c166870cdf3d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1113,7 +1113,12 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 #define BPF_F_ALLOW_MULTI	(1U << 1)
+/* Generic attachment flags. */
 #define BPF_F_REPLACE		(1U << 2)
+#define BPF_F_BEFORE		(1U << 3)
+#define BPF_F_AFTER		(1U << 4)
+#define BPF_F_ID		(1U << 5)
+#define BPF_F_LINK		BPF_F_LINK /* 1 << 13 */
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -1444,14 +1449,19 @@ union bpf_attr {
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
-		__u32		target_fd;	/* container object to attach to */
-		__u32		attach_bpf_fd;	/* eBPF program to attach */
+		union {
+			__u32	target_fd;	/* target object to attach to or ... */
+			__u32	target_ifindex;	/* target ifindex */
+		};
+		__u32		attach_bpf_fd;
 		__u32		attach_type;
 		__u32		attach_flags;
-		__u32		replace_bpf_fd;	/* previously attached eBPF
-						 * program to replace if
-						 * BPF_F_REPLACE is used
-						 */
+		__u32		replace_bpf_fd;
+		union {
+			__u32	relative_fd;
+			__u32	relative_id;
+		};
+		__u64		expected_revision;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
@@ -1497,16 +1507,26 @@ union bpf_attr {
 	} info;
 
 	struct { /* anonymous struct used by BPF_PROG_QUERY command */
-		__u32		target_fd;	/* container object to query */
+		union {
+			__u32	target_fd;	/* target object to query or ... */
+			__u32	target_ifindex;	/* target ifindex */
+		};
 		__u32		attach_type;
 		__u32		query_flags;
 		__u32		attach_flags;
 		__aligned_u64	prog_ids;
-		__u32		prog_cnt;
+		union {
+			__u32	prog_cnt;
+			__u32	count;
+		};
+		__u32		:32;
 		/* output: per-program attach_flags.
 		 * not allowed to be set during effective query.
 		 */
 		__aligned_u64	prog_attach_flags;
+		__aligned_u64	link_ids;
+		__aligned_u64	link_attach_flags;
+		__u64		revision;
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
-- 
GitLab


From e420bed025071a623d2720a92bc2245c84757ecb Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 19 Jul 2023 16:08:52 +0200
Subject: [PATCH 0256/1806] bpf: Add fd-based tcx multi-prog infra with link
 support

This work refactors and adds a lightweight extension ("tcx") to the tc BPF
ingress and egress data path side for allowing BPF program management based
on fds via bpf() syscall through the newly added generic multi-prog API.
The main goal behind this work which we also presented at LPC [0] last year
and a recent update at LSF/MM/BPF this year [3] is to support long-awaited
BPF link functionality for tc BPF programs, which allows for a model of safe
ownership and program detachment.

Given the rise in tc BPF users in cloud native environments, this becomes
necessary to avoid hard to debug incidents either through stale leftover
programs or 3rd party applications accidentally stepping on each others toes.
As a recap, a BPF link represents the attachment of a BPF program to a BPF
hook point. The BPF link holds a single reference to keep BPF program alive.
Moreover, hook points do not reference a BPF link, only the application's
fd or pinning does. A BPF link holds meta-data specific to attachment and
implements operations for link creation, (atomic) BPF program update,
detachment and introspection. The motivation for BPF links for tc BPF programs
is multi-fold, for example:

  - From Meta: "It's especially important for applications that are deployed
    fleet-wide and that don't "control" hosts they are deployed to. If such
    application crashes and no one notices and does anything about that, BPF
    program will keep running draining resources or even just, say, dropping
    packets. We at FB had outages due to such permanent BPF attachment
    semantics. With fd-based BPF link we are getting a framework, which allows
    safe, auto-detachable behavior by default, unless application explicitly
    opts in by pinning the BPF link." [1]

  - From Cilium-side the tc BPF programs we attach to host-facing veth devices
    and phys devices build the core datapath for Kubernetes Pods, and they
    implement forwarding, load-balancing, policy, EDT-management, etc, within
    BPF. Currently there is no concept of 'safe' ownership, e.g. we've recently
    experienced hard-to-debug issues in a user's staging environment where
    another Kubernetes application using tc BPF attached to the same prio/handle
    of cls_bpf, accidentally wiping all Cilium-based BPF programs from underneath
    it. The goal is to establish a clear/safe ownership model via links which
    cannot accidentally be overridden. [0,2]

BPF links for tc can co-exist with non-link attachments, and the semantics are
in line also with XDP links: BPF links cannot replace other BPF links, BPF
links cannot replace non-BPF links, non-BPF links cannot replace BPF links and
lastly only non-BPF links can replace non-BPF links. In case of Cilium, this
would solve mentioned issue of safe ownership model as 3rd party applications
would not be able to accidentally wipe Cilium programs, even if they are not
BPF link aware.

Earlier attempts [4] have tried to integrate BPF links into core tc machinery
to solve cls_bpf, which has been intrusive to the generic tc kernel API with
extensions only specific to cls_bpf and suboptimal/complex since cls_bpf could
be wiped from the qdisc also. Locking a tc BPF program in place this way, is
getting into layering hacks given the two object models are vastly different.

We instead implemented the tcx (tc 'express') layer which is an fd-based tc BPF
attach API, so that the BPF link implementation blends in naturally similar to
other link types which are fd-based and without the need for changing core tc
internal APIs. BPF programs for tc can then be successively migrated from classic
cls_bpf to the new tc BPF link without needing to change the program's source
code, just the BPF loader mechanics for attaching is sufficient.

For the current tc framework, there is no change in behavior with this change
and neither does this change touch on tc core kernel APIs. The gist of this
patch is that the ingress and egress hook have a lightweight, qdisc-less
extension for BPF to attach its tc BPF programs, in other words, a minimal
entry point for tc BPF. The name tcx has been suggested from discussion of
earlier revisions of this work as a good fit, and to more easily differ between
the classic cls_bpf attachment and the fd-based one.

For the ingress and egress tcx points, the device holds a cache-friendly array
with program pointers which is separated from control plane (slow-path) data.
Earlier versions of this work used priority to determine ordering and expression
of dependencies similar as with classic tc, but it was challenged that for
something more future-proof a better user experience is required. Hence this
resulted in the design and development of the generic attach/detach/query API
for multi-progs. See prior patch with its discussion on the API design. tcx is
the first user and later we plan to integrate also others, for example, one
candidate is multi-prog support for XDP which would benefit and have the same
'look and feel' from API perspective.

The goal with tcx is to have maximum compatibility to existing tc BPF programs,
so they don't need to be rewritten specifically. Compatibility to call into
classic tcf_classify() is also provided in order to allow successive migration
or both to cleanly co-exist where needed given its all one logical tc layer and
the tcx plus classic tc cls/act build one logical overall processing pipeline.

tcx supports the simplified return codes TCX_NEXT which is non-terminating (go
to next program) and terminating ones with TCX_PASS, TCX_DROP, TCX_REDIRECT.
The fd-based API is behind a static key, so that when unused the code is also
not entered. The struct tcx_entry's program array is currently static, but
could be made dynamic if necessary at a point in future. The a/b pair swap
design has been chosen so that for detachment there are no allocations which
otherwise could fail.

The work has been tested with tc-testing selftest suite which all passes, as
well as the tc BPF tests from the BPF CI, and also with Cilium's L4LB.

Thanks also to Nikolay Aleksandrov and Martin Lau for in-depth early reviews
of this work.

  [0] https://lpc.events/event/16/contributions/1353/
  [1] https://lore.kernel.org/bpf/CAEf4BzbokCJN33Nw_kg82sO=xppXnKWEncGTWCTB9vGCmLB6pw@mail.gmail.com
  [2] https://colocatedeventseu2023.sched.com/event/1Jo6O/tales-from-an-ebpf-programs-murder-mystery-hemanth-malla-guillaume-fournier-datadog
  [3] http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf
  [4] https://lore.kernel.org/bpf/20210604063116.234316-1-memxor@gmail.com

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230719140858.13224-3-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 MAINTAINERS                    |   4 +-
 include/linux/bpf_mprog.h      |   9 +
 include/linux/netdevice.h      |  15 +-
 include/linux/skbuff.h         |   4 +-
 include/net/sch_generic.h      |   2 +-
 include/net/tcx.h              | 206 +++++++++++++++++++
 include/uapi/linux/bpf.h       |  34 +++-
 kernel/bpf/Kconfig             |   1 +
 kernel/bpf/Makefile            |   1 +
 kernel/bpf/syscall.c           |  82 ++++++--
 kernel/bpf/tcx.c               | 348 +++++++++++++++++++++++++++++++++
 net/Kconfig                    |   5 +
 net/core/dev.c                 | 265 +++++++++++++++----------
 net/core/filter.c              |   4 +-
 net/sched/Kconfig              |   4 +-
 net/sched/sch_ingress.c        |  61 +++++-
 tools/include/uapi/linux/bpf.h |  34 +++-
 17 files changed, 935 insertions(+), 144 deletions(-)
 create mode 100644 include/net/tcx.h
 create mode 100644 kernel/bpf/tcx.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 678bef9f60b40..990e3fce753ce 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3778,13 +3778,15 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	kernel/bpf/bpf_struct*
 
-BPF [NETWORKING] (tc BPF, sock_addr)
+BPF [NETWORKING] (tcx & tc BPF, sock_addr)
 M:	Martin KaFai Lau <martin.lau@linux.dev>
 M:	Daniel Borkmann <daniel@iogearbox.net>
 R:	John Fastabend <john.fastabend@gmail.com>
 L:	bpf@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Maintained
+F:	include/net/tcx.h
+F:	kernel/bpf/tcx.c
 F:	net/core/filter.c
 F:	net/sched/act_bpf.c
 F:	net/sched/cls_bpf.c
diff --git a/include/linux/bpf_mprog.h b/include/linux/bpf_mprog.h
index 6feefec434224..2b429488f8402 100644
--- a/include/linux/bpf_mprog.h
+++ b/include/linux/bpf_mprog.h
@@ -315,4 +315,13 @@ int bpf_mprog_detach(struct bpf_mprog_entry *entry,
 int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr,
 		    struct bpf_mprog_entry *entry);
 
+static inline bool bpf_mprog_supported(enum bpf_prog_type type)
+{
+	switch (type) {
+	case BPF_PROG_TYPE_SCHED_CLS:
+		return true;
+	default:
+		return false;
+	}
+}
 #endif /* __BPF_MPROG_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b12477ea4032b..3800d04796984 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1930,8 +1930,7 @@ enum netdev_ml_priv_type {
  *
  *	@rx_handler:		handler for received packets
  *	@rx_handler_data: 	XXX: need comments on this one
- *	@miniq_ingress:		ingress/clsact qdisc specific data for
- *				ingress processing
+ *	@tcx_ingress:		BPF & clsact qdisc specific data for ingress processing
  *	@ingress_queue:		XXX: need comments on this one
  *	@nf_hooks_ingress:	netfilter hooks executed for ingress packets
  *	@broadcast:		hw bcast address
@@ -1952,8 +1951,7 @@ enum netdev_ml_priv_type {
  *	@xps_maps:		all CPUs/RXQs maps for XPS device
  *
  *	@xps_maps:	XXX: need comments on this one
- *	@miniq_egress:		clsact qdisc specific data for
- *				egress processing
+ *	@tcx_egress:		BPF & clsact qdisc specific data for egress processing
  *	@nf_hooks_egress:	netfilter hooks executed for egress packets
  *	@qdisc_hash:		qdisc hash table
  *	@watchdog_timeo:	Represents the timeout that is used by
@@ -2253,9 +2251,8 @@ struct net_device {
 	unsigned int		xdp_zc_max_segs;
 	rx_handler_func_t __rcu	*rx_handler;
 	void __rcu		*rx_handler_data;
-
-#ifdef CONFIG_NET_CLS_ACT
-	struct mini_Qdisc __rcu	*miniq_ingress;
+#ifdef CONFIG_NET_XGRESS
+	struct bpf_mprog_entry __rcu *tcx_ingress;
 #endif
 	struct netdev_queue __rcu *ingress_queue;
 #ifdef CONFIG_NETFILTER_INGRESS
@@ -2283,8 +2280,8 @@ struct net_device {
 #ifdef CONFIG_XPS
 	struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
 #endif
-#ifdef CONFIG_NET_CLS_ACT
-	struct mini_Qdisc __rcu	*miniq_egress;
+#ifdef CONFIG_NET_XGRESS
+	struct bpf_mprog_entry __rcu *tcx_egress;
 #endif
 #ifdef CONFIG_NETFILTER_EGRESS
 	struct nf_hook_entries __rcu *nf_hooks_egress;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 91ed66952580a..ed83f1c5fc1f6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -944,7 +944,7 @@ struct sk_buff {
 	__u8			__mono_tc_offset[0];
 	/* public: */
 	__u8			mono_delivery_time:1;	/* See SKB_MONO_DELIVERY_TIME_MASK */
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_XGRESS
 	__u8			tc_at_ingress:1;	/* See TC_AT_INGRESS_MASK */
 	__u8			tc_skip_classify:1;
 #endif
@@ -993,7 +993,7 @@ struct sk_buff {
 	__u8			csum_not_inet:1;
 #endif
 
-#ifdef CONFIG_NET_SCHED
+#if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS)
 	__u16			tc_index;	/* traffic control index */
 #endif
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e92f73bb31984..15be2d96b06de 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -703,7 +703,7 @@ int skb_do_redirect(struct sk_buff *);
 
 static inline bool skb_at_tc_ingress(const struct sk_buff *skb)
 {
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_XGRESS
 	return skb->tc_at_ingress;
 #else
 	return false;
diff --git a/include/net/tcx.h b/include/net/tcx.h
new file mode 100644
index 0000000000000..264f147953bae
--- /dev/null
+++ b/include/net/tcx.h
@@ -0,0 +1,206 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Isovalent */
+#ifndef __NET_TCX_H
+#define __NET_TCX_H
+
+#include <linux/bpf.h>
+#include <linux/bpf_mprog.h>
+
+#include <net/sch_generic.h>
+
+struct mini_Qdisc;
+
+struct tcx_entry {
+	struct mini_Qdisc __rcu *miniq;
+	struct bpf_mprog_bundle bundle;
+	bool miniq_active;
+	struct rcu_head rcu;
+};
+
+struct tcx_link {
+	struct bpf_link link;
+	struct net_device *dev;
+	u32 location;
+};
+
+static inline void tcx_set_ingress(struct sk_buff *skb, bool ingress)
+{
+#ifdef CONFIG_NET_XGRESS
+	skb->tc_at_ingress = ingress;
+#endif
+}
+
+#ifdef CONFIG_NET_XGRESS
+static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry)
+{
+	struct bpf_mprog_bundle *bundle = entry->parent;
+
+	return container_of(bundle, struct tcx_entry, bundle);
+}
+
+static inline struct tcx_link *tcx_link(struct bpf_link *link)
+{
+	return container_of(link, struct tcx_link, link);
+}
+
+static inline const struct tcx_link *tcx_link_const(const struct bpf_link *link)
+{
+	return tcx_link((struct bpf_link *)link);
+}
+
+void tcx_inc(void);
+void tcx_dec(void);
+
+static inline void tcx_entry_sync(void)
+{
+	/* bpf_mprog_entry got a/b swapped, therefore ensure that
+	 * there are no inflight users on the old one anymore.
+	 */
+	synchronize_rcu();
+}
+
+static inline void
+tcx_entry_update(struct net_device *dev, struct bpf_mprog_entry *entry,
+		 bool ingress)
+{
+	ASSERT_RTNL();
+	if (ingress)
+		rcu_assign_pointer(dev->tcx_ingress, entry);
+	else
+		rcu_assign_pointer(dev->tcx_egress, entry);
+}
+
+static inline struct bpf_mprog_entry *
+tcx_entry_fetch(struct net_device *dev, bool ingress)
+{
+	ASSERT_RTNL();
+	if (ingress)
+		return rcu_dereference_rtnl(dev->tcx_ingress);
+	else
+		return rcu_dereference_rtnl(dev->tcx_egress);
+}
+
+static inline struct bpf_mprog_entry *tcx_entry_create(void)
+{
+	struct tcx_entry *tcx = kzalloc(sizeof(*tcx), GFP_KERNEL);
+
+	if (tcx) {
+		bpf_mprog_bundle_init(&tcx->bundle);
+		return &tcx->bundle.a;
+	}
+	return NULL;
+}
+
+static inline void tcx_entry_free(struct bpf_mprog_entry *entry)
+{
+	kfree_rcu(tcx_entry(entry), rcu);
+}
+
+static inline struct bpf_mprog_entry *
+tcx_entry_fetch_or_create(struct net_device *dev, bool ingress, bool *created)
+{
+	struct bpf_mprog_entry *entry = tcx_entry_fetch(dev, ingress);
+
+	*created = false;
+	if (!entry) {
+		entry = tcx_entry_create();
+		if (!entry)
+			return NULL;
+		*created = true;
+	}
+	return entry;
+}
+
+static inline void tcx_skeys_inc(bool ingress)
+{
+	tcx_inc();
+	if (ingress)
+		net_inc_ingress_queue();
+	else
+		net_inc_egress_queue();
+}
+
+static inline void tcx_skeys_dec(bool ingress)
+{
+	if (ingress)
+		net_dec_ingress_queue();
+	else
+		net_dec_egress_queue();
+	tcx_dec();
+}
+
+static inline void tcx_miniq_set_active(struct bpf_mprog_entry *entry,
+					const bool active)
+{
+	ASSERT_RTNL();
+	tcx_entry(entry)->miniq_active = active;
+}
+
+static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry)
+{
+	ASSERT_RTNL();
+	return bpf_mprog_total(entry) || tcx_entry(entry)->miniq_active;
+}
+
+static inline enum tcx_action_base tcx_action_code(struct sk_buff *skb,
+						   int code)
+{
+	switch (code) {
+	case TCX_PASS:
+		skb->tc_index = qdisc_skb_cb(skb)->tc_classid;
+		fallthrough;
+	case TCX_DROP:
+	case TCX_REDIRECT:
+		return code;
+	case TCX_NEXT:
+	default:
+		return TCX_NEXT;
+	}
+}
+#endif /* CONFIG_NET_XGRESS */
+
+#if defined(CONFIG_NET_XGRESS) && defined(CONFIG_BPF_SYSCALL)
+int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog);
+void tcx_uninstall(struct net_device *dev, bool ingress);
+
+int tcx_prog_query(const union bpf_attr *attr,
+		   union bpf_attr __user *uattr);
+
+static inline void dev_tcx_uninstall(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	tcx_uninstall(dev, true);
+	tcx_uninstall(dev, false);
+}
+#else
+static inline int tcx_prog_attach(const union bpf_attr *attr,
+				  struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int tcx_link_attach(const union bpf_attr *attr,
+				  struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int tcx_prog_detach(const union bpf_attr *attr,
+				  struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int tcx_prog_query(const union bpf_attr *attr,
+				 union bpf_attr __user *uattr)
+{
+	return -EINVAL;
+}
+
+static inline void dev_tcx_uninstall(struct net_device *dev)
+{
+}
+#endif /* CONFIG_NET_XGRESS && CONFIG_BPF_SYSCALL */
+#endif /* __NET_TCX_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d4c07e4353362..739c15906a65d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1036,6 +1036,8 @@ enum bpf_attach_type {
 	BPF_LSM_CGROUP,
 	BPF_STRUCT_OPS,
 	BPF_NETFILTER,
+	BPF_TCX_INGRESS,
+	BPF_TCX_EGRESS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1053,7 +1055,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_KPROBE_MULTI = 8,
 	BPF_LINK_TYPE_STRUCT_OPS = 9,
 	BPF_LINK_TYPE_NETFILTER = 10,
-
+	BPF_LINK_TYPE_TCX = 11,
 	MAX_BPF_LINK_TYPE,
 };
 
@@ -1569,13 +1571,13 @@ union bpf_attr {
 			__u32		map_fd;		/* struct_ops to attach */
 		};
 		union {
-			__u32		target_fd;	/* object to attach to */
-			__u32		target_ifindex; /* target ifindex */
+			__u32	target_fd;	/* target object to attach to or ... */
+			__u32	target_ifindex; /* target ifindex */
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
 		union {
-			__u32		target_btf_id;	/* btf_id of target to attach to */
+			__u32	target_btf_id;	/* btf_id of target to attach to */
 			struct {
 				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
 				__u32		iter_info_len;	/* iter_info length */
@@ -1609,6 +1611,13 @@ union bpf_attr {
 				__s32		priority;
 				__u32		flags;
 			} netfilter;
+			struct {
+				union {
+					__u32	relative_fd;
+					__u32	relative_id;
+				};
+				__u64		expected_revision;
+			} tcx;
 		};
 	} link_create;
 
@@ -6217,6 +6226,19 @@ struct bpf_sock_tuple {
 	};
 };
 
+/* (Simplified) user return codes for tcx prog type.
+ * A valid tcx program must return one of these defined values. All other
+ * return codes are reserved for future use. Must remain compatible with
+ * their TC_ACT_* counter-parts. For compatibility in behavior, unknown
+ * return codes are mapped to TCX_NEXT.
+ */
+enum tcx_action_base {
+	TCX_NEXT	= -1,
+	TCX_PASS	= 0,
+	TCX_DROP	= 2,
+	TCX_REDIRECT	= 7,
+};
+
 struct bpf_xdp_sock {
 	__u32 queue_id;
 };
@@ -6499,6 +6521,10 @@ struct bpf_link_info {
 				} event; /* BPF_PERF_EVENT_EVENT */
 			};
 		} perf_event;
+		struct {
+			__u32 ifindex;
+			__u32 attach_type;
+		} tcx;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig
index 2dfe1079f7727..6a906ff930065 100644
--- a/kernel/bpf/Kconfig
+++ b/kernel/bpf/Kconfig
@@ -31,6 +31,7 @@ config BPF_SYSCALL
 	select TASKS_TRACE_RCU
 	select BINARY_PRINTF
 	select NET_SOCK_MSG if NET
+	select NET_XGRESS if NET
 	select PAGE_POOL if NET
 	default n
 	help
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 1bea2eb912cdb..f526b7573e97c 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
 obj-$(CONFIG_BPF_SYSCALL) += offload.o
 obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o
+obj-$(CONFIG_BPF_SYSCALL) += tcx.o
 endif
 ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ee8cb1a174aa1..7f4e8c357a6af 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -37,6 +37,8 @@
 #include <linux/trace_events.h>
 #include <net/netfilter/nf_bpf_link.h>
 
+#include <net/tcx.h>
+
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
@@ -3740,31 +3742,45 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 		return BPF_PROG_TYPE_XDP;
 	case BPF_LSM_CGROUP:
 		return BPF_PROG_TYPE_LSM;
+	case BPF_TCX_INGRESS:
+	case BPF_TCX_EGRESS:
+		return BPF_PROG_TYPE_SCHED_CLS;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
 }
 
-#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd
+#define BPF_PROG_ATTACH_LAST_FIELD expected_revision
+
+#define BPF_F_ATTACH_MASK_BASE	\
+	(BPF_F_ALLOW_OVERRIDE |	\
+	 BPF_F_ALLOW_MULTI |	\
+	 BPF_F_REPLACE)
 
-#define BPF_F_ATTACH_MASK \
-	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE)
+#define BPF_F_ATTACH_MASK_MPROG	\
+	(BPF_F_REPLACE |	\
+	 BPF_F_BEFORE |		\
+	 BPF_F_AFTER |		\
+	 BPF_F_ID |		\
+	 BPF_F_LINK)
 
 static int bpf_prog_attach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
+	u32 mask;
 	int ret;
 
 	if (CHECK_ATTR(BPF_PROG_ATTACH))
 		return -EINVAL;
 
-	if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
-		return -EINVAL;
-
 	ptype = attach_type_to_prog_type(attr->attach_type);
 	if (ptype == BPF_PROG_TYPE_UNSPEC)
 		return -EINVAL;
+	mask = bpf_mprog_supported(ptype) ?
+	       BPF_F_ATTACH_MASK_MPROG : BPF_F_ATTACH_MASK_BASE;
+	if (attr->attach_flags & ~mask)
+		return -EINVAL;
 
 	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
 	if (IS_ERR(prog))
@@ -3800,6 +3816,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		else
 			ret = cgroup_bpf_prog_attach(attr, ptype, prog);
 		break;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		ret = tcx_prog_attach(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -3809,25 +3828,41 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	return ret;
 }
 
-#define BPF_PROG_DETACH_LAST_FIELD attach_type
+#define BPF_PROG_DETACH_LAST_FIELD expected_revision
 
 static int bpf_prog_detach(const union bpf_attr *attr)
 {
+	struct bpf_prog *prog = NULL;
 	enum bpf_prog_type ptype;
+	int ret;
 
 	if (CHECK_ATTR(BPF_PROG_DETACH))
 		return -EINVAL;
 
 	ptype = attach_type_to_prog_type(attr->attach_type);
+	if (bpf_mprog_supported(ptype)) {
+		if (ptype == BPF_PROG_TYPE_UNSPEC)
+			return -EINVAL;
+		if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
+			return -EINVAL;
+		if (attr->attach_bpf_fd) {
+			prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+			if (IS_ERR(prog))
+				return PTR_ERR(prog);
+		}
+	}
 
 	switch (ptype) {
 	case BPF_PROG_TYPE_SK_MSG:
 	case BPF_PROG_TYPE_SK_SKB:
-		return sock_map_prog_detach(attr, ptype);
+		ret = sock_map_prog_detach(attr, ptype);
+		break;
 	case BPF_PROG_TYPE_LIRC_MODE2:
-		return lirc_prog_detach(attr);
+		ret = lirc_prog_detach(attr);
+		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		return netns_bpf_prog_detach(attr, ptype);
+		ret = netns_bpf_prog_detach(attr, ptype);
+		break;
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
@@ -3836,13 +3871,21 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 	case BPF_PROG_TYPE_SOCK_OPS:
 	case BPF_PROG_TYPE_LSM:
-		return cgroup_bpf_prog_detach(attr, ptype);
+		ret = cgroup_bpf_prog_detach(attr, ptype);
+		break;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		ret = tcx_prog_detach(attr, prog);
+		break;
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
 	}
+
+	if (prog)
+		bpf_prog_put(prog);
+	return ret;
 }
 
-#define BPF_PROG_QUERY_LAST_FIELD query.prog_attach_flags
+#define BPF_PROG_QUERY_LAST_FIELD query.link_attach_flags
 
 static int bpf_prog_query(const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
@@ -3890,6 +3933,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_SK_MSG_VERDICT:
 	case BPF_SK_SKB_VERDICT:
 		return sock_map_bpf_prog_query(attr, uattr);
+	case BPF_TCX_INGRESS:
+	case BPF_TCX_EGRESS:
+		return tcx_prog_query(attr, uattr);
 	default:
 		return -EINVAL;
 	}
@@ -4852,6 +4898,13 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 			goto out;
 		}
 		break;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		if (attr->link_create.attach_type != BPF_TCX_INGRESS &&
+		    attr->link_create.attach_type != BPF_TCX_EGRESS) {
+			ret = -EINVAL;
+			goto out;
+		}
+		break;
 	default:
 		ptype = attach_type_to_prog_type(attr->link_create.attach_type);
 		if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
@@ -4903,6 +4956,9 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	case BPF_PROG_TYPE_XDP:
 		ret = bpf_xdp_link_attach(attr, prog);
 		break;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		ret = tcx_link_attach(attr, prog);
+		break;
 	case BPF_PROG_TYPE_NETFILTER:
 		ret = bpf_nf_link_attach(attr, prog);
 		break;
diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c
new file mode 100644
index 0000000000000..69a272712b29f
--- /dev/null
+++ b/kernel/bpf/tcx.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <linux/bpf.h>
+#include <linux/bpf_mprog.h>
+#include <linux/netdevice.h>
+
+#include <net/tcx.h>
+
+int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	bool created, ingress = attr->attach_type == BPF_TCX_INGRESS;
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_mprog_entry *entry, *entry_new;
+	struct bpf_prog *replace_prog = NULL;
+	struct net_device *dev;
+	int ret;
+
+	rtnl_lock();
+	dev = __dev_get_by_index(net, attr->target_ifindex);
+	if (!dev) {
+		ret = -ENODEV;
+		goto out;
+	}
+	if (attr->attach_flags & BPF_F_REPLACE) {
+		replace_prog = bpf_prog_get_type(attr->replace_bpf_fd,
+						 prog->type);
+		if (IS_ERR(replace_prog)) {
+			ret = PTR_ERR(replace_prog);
+			replace_prog = NULL;
+			goto out;
+		}
+	}
+	entry = tcx_entry_fetch_or_create(dev, ingress, &created);
+	if (!entry) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog,
+			       attr->attach_flags, attr->relative_fd,
+			       attr->expected_revision);
+	if (!ret) {
+		if (entry != entry_new) {
+			tcx_entry_update(dev, entry_new, ingress);
+			tcx_entry_sync();
+			tcx_skeys_inc(ingress);
+		}
+		bpf_mprog_commit(entry);
+	} else if (created) {
+		tcx_entry_free(entry);
+	}
+out:
+	if (replace_prog)
+		bpf_prog_put(replace_prog);
+	rtnl_unlock();
+	return ret;
+}
+
+int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	bool ingress = attr->attach_type == BPF_TCX_INGRESS;
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_mprog_entry *entry, *entry_new;
+	struct net_device *dev;
+	int ret;
+
+	rtnl_lock();
+	dev = __dev_get_by_index(net, attr->target_ifindex);
+	if (!dev) {
+		ret = -ENODEV;
+		goto out;
+	}
+	entry = tcx_entry_fetch(dev, ingress);
+	if (!entry) {
+		ret = -ENOENT;
+		goto out;
+	}
+	ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags,
+			       attr->relative_fd, attr->expected_revision);
+	if (!ret) {
+		if (!tcx_entry_is_active(entry_new))
+			entry_new = NULL;
+		tcx_entry_update(dev, entry_new, ingress);
+		tcx_entry_sync();
+		tcx_skeys_dec(ingress);
+		bpf_mprog_commit(entry);
+		if (!entry_new)
+			tcx_entry_free(entry);
+	}
+out:
+	rtnl_unlock();
+	return ret;
+}
+
+void tcx_uninstall(struct net_device *dev, bool ingress)
+{
+	struct bpf_tuple tuple = {};
+	struct bpf_mprog_entry *entry;
+	struct bpf_mprog_fp *fp;
+	struct bpf_mprog_cp *cp;
+
+	entry = tcx_entry_fetch(dev, ingress);
+	if (!entry)
+		return;
+	tcx_entry_update(dev, NULL, ingress);
+	tcx_entry_sync();
+	bpf_mprog_foreach_tuple(entry, fp, cp, tuple) {
+		if (tuple.link)
+			tcx_link(tuple.link)->dev = NULL;
+		else
+			bpf_prog_put(tuple.prog);
+		tcx_skeys_dec(ingress);
+	}
+	WARN_ON_ONCE(tcx_entry(entry)->miniq_active);
+	tcx_entry_free(entry);
+}
+
+int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
+{
+	bool ingress = attr->query.attach_type == BPF_TCX_INGRESS;
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_mprog_entry *entry;
+	struct net_device *dev;
+	int ret;
+
+	rtnl_lock();
+	dev = __dev_get_by_index(net, attr->query.target_ifindex);
+	if (!dev) {
+		ret = -ENODEV;
+		goto out;
+	}
+	entry = tcx_entry_fetch(dev, ingress);
+	if (!entry) {
+		ret = -ENOENT;
+		goto out;
+	}
+	ret = bpf_mprog_query(attr, uattr, entry);
+out:
+	rtnl_unlock();
+	return ret;
+}
+
+static int tcx_link_prog_attach(struct bpf_link *link, u32 flags, u32 id_or_fd,
+				u64 revision)
+{
+	struct tcx_link *tcx = tcx_link(link);
+	bool created, ingress = tcx->location == BPF_TCX_INGRESS;
+	struct bpf_mprog_entry *entry, *entry_new;
+	struct net_device *dev = tcx->dev;
+	int ret;
+
+	ASSERT_RTNL();
+	entry = tcx_entry_fetch_or_create(dev, ingress, &created);
+	if (!entry)
+		return -ENOMEM;
+	ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags,
+			       id_or_fd, revision);
+	if (!ret) {
+		if (entry != entry_new) {
+			tcx_entry_update(dev, entry_new, ingress);
+			tcx_entry_sync();
+			tcx_skeys_inc(ingress);
+		}
+		bpf_mprog_commit(entry);
+	} else if (created) {
+		tcx_entry_free(entry);
+	}
+	return ret;
+}
+
+static void tcx_link_release(struct bpf_link *link)
+{
+	struct tcx_link *tcx = tcx_link(link);
+	bool ingress = tcx->location == BPF_TCX_INGRESS;
+	struct bpf_mprog_entry *entry, *entry_new;
+	struct net_device *dev;
+	int ret = 0;
+
+	rtnl_lock();
+	dev = tcx->dev;
+	if (!dev)
+		goto out;
+	entry = tcx_entry_fetch(dev, ingress);
+	if (!entry) {
+		ret = -ENOENT;
+		goto out;
+	}
+	ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0);
+	if (!ret) {
+		if (!tcx_entry_is_active(entry_new))
+			entry_new = NULL;
+		tcx_entry_update(dev, entry_new, ingress);
+		tcx_entry_sync();
+		tcx_skeys_dec(ingress);
+		bpf_mprog_commit(entry);
+		if (!entry_new)
+			tcx_entry_free(entry);
+		tcx->dev = NULL;
+	}
+out:
+	WARN_ON_ONCE(ret);
+	rtnl_unlock();
+}
+
+static int tcx_link_update(struct bpf_link *link, struct bpf_prog *nprog,
+			   struct bpf_prog *oprog)
+{
+	struct tcx_link *tcx = tcx_link(link);
+	bool ingress = tcx->location == BPF_TCX_INGRESS;
+	struct bpf_mprog_entry *entry, *entry_new;
+	struct net_device *dev;
+	int ret = 0;
+
+	rtnl_lock();
+	dev = tcx->dev;
+	if (!dev) {
+		ret = -ENOLINK;
+		goto out;
+	}
+	if (oprog && link->prog != oprog) {
+		ret = -EPERM;
+		goto out;
+	}
+	oprog = link->prog;
+	if (oprog == nprog) {
+		bpf_prog_put(nprog);
+		goto out;
+	}
+	entry = tcx_entry_fetch(dev, ingress);
+	if (!entry) {
+		ret = -ENOENT;
+		goto out;
+	}
+	ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog,
+			       BPF_F_REPLACE | BPF_F_ID,
+			       link->prog->aux->id, 0);
+	if (!ret) {
+		WARN_ON_ONCE(entry != entry_new);
+		oprog = xchg(&link->prog, nprog);
+		bpf_prog_put(oprog);
+		bpf_mprog_commit(entry);
+	}
+out:
+	rtnl_unlock();
+	return ret;
+}
+
+static void tcx_link_dealloc(struct bpf_link *link)
+{
+	kfree(tcx_link(link));
+}
+
+static void tcx_link_fdinfo(const struct bpf_link *link, struct seq_file *seq)
+{
+	const struct tcx_link *tcx = tcx_link_const(link);
+	u32 ifindex = 0;
+
+	rtnl_lock();
+	if (tcx->dev)
+		ifindex = tcx->dev->ifindex;
+	rtnl_unlock();
+
+	seq_printf(seq, "ifindex:\t%u\n", ifindex);
+	seq_printf(seq, "attach_type:\t%u (%s)\n",
+		   tcx->location,
+		   tcx->location == BPF_TCX_INGRESS ? "ingress" : "egress");
+}
+
+static int tcx_link_fill_info(const struct bpf_link *link,
+			      struct bpf_link_info *info)
+{
+	const struct tcx_link *tcx = tcx_link_const(link);
+	u32 ifindex = 0;
+
+	rtnl_lock();
+	if (tcx->dev)
+		ifindex = tcx->dev->ifindex;
+	rtnl_unlock();
+
+	info->tcx.ifindex = ifindex;
+	info->tcx.attach_type = tcx->location;
+	return 0;
+}
+
+static int tcx_link_detach(struct bpf_link *link)
+{
+	tcx_link_release(link);
+	return 0;
+}
+
+static const struct bpf_link_ops tcx_link_lops = {
+	.release	= tcx_link_release,
+	.detach		= tcx_link_detach,
+	.dealloc	= tcx_link_dealloc,
+	.update_prog	= tcx_link_update,
+	.show_fdinfo	= tcx_link_fdinfo,
+	.fill_link_info	= tcx_link_fill_info,
+};
+
+static int tcx_link_init(struct tcx_link *tcx,
+			 struct bpf_link_primer *link_primer,
+			 const union bpf_attr *attr,
+			 struct net_device *dev,
+			 struct bpf_prog *prog)
+{
+	bpf_link_init(&tcx->link, BPF_LINK_TYPE_TCX, &tcx_link_lops, prog);
+	tcx->location = attr->link_create.attach_type;
+	tcx->dev = dev;
+	return bpf_link_prime(&tcx->link, link_primer);
+}
+
+int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_link_primer link_primer;
+	struct net_device *dev;
+	struct tcx_link *tcx;
+	int ret;
+
+	rtnl_lock();
+	dev = __dev_get_by_index(net, attr->link_create.target_ifindex);
+	if (!dev) {
+		ret = -ENODEV;
+		goto out;
+	}
+	tcx = kzalloc(sizeof(*tcx), GFP_USER);
+	if (!tcx) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	ret = tcx_link_init(tcx, &link_primer, attr, dev, prog);
+	if (ret) {
+		kfree(tcx);
+		goto out;
+	}
+	ret = tcx_link_prog_attach(&tcx->link, attr->link_create.flags,
+				   attr->link_create.tcx.relative_fd,
+				   attr->link_create.tcx.expected_revision);
+	if (ret) {
+		tcx->dev = NULL;
+		bpf_link_cleanup(&link_primer);
+		goto out;
+	}
+	ret = bpf_link_settle(&link_primer);
+out:
+	rtnl_unlock();
+	return ret;
+}
diff --git a/net/Kconfig b/net/Kconfig
index 2fb25b534df57..d532ec33f1fed 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -52,6 +52,11 @@ config NET_INGRESS
 config NET_EGRESS
 	bool
 
+config NET_XGRESS
+	select NET_INGRESS
+	select NET_EGRESS
+	bool
+
 config NET_REDIRECT
 	bool
 
diff --git a/net/core/dev.c b/net/core/dev.c
index dd4f114a7cbfe..8e7d0cb540cdb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -107,6 +107,7 @@
 #include <net/pkt_cls.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
+#include <net/tcx.h>
 #include <linux/highmem.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -154,7 +155,6 @@
 #include "dev.h"
 #include "net-sysfs.h"
 
-
 static DEFINE_SPINLOCK(ptype_lock);
 struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
 struct list_head ptype_all __read_mostly;	/* Taps */
@@ -3882,69 +3882,198 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
 EXPORT_SYMBOL(dev_loopback_xmit);
 
 #ifdef CONFIG_NET_EGRESS
-static struct sk_buff *
-sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
+static struct netdev_queue *
+netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
+{
+	int qm = skb_get_queue_mapping(skb);
+
+	return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
+}
+
+static bool netdev_xmit_txqueue_skipped(void)
 {
+	return __this_cpu_read(softnet_data.xmit.skip_txqueue);
+}
+
+void netdev_xmit_skip_txqueue(bool skip)
+{
+	__this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
+}
+EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
+#endif /* CONFIG_NET_EGRESS */
+
+#ifdef CONFIG_NET_XGRESS
+static int tc_run(struct tcx_entry *entry, struct sk_buff *skb)
+{
+	int ret = TC_ACT_UNSPEC;
 #ifdef CONFIG_NET_CLS_ACT
-	struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress);
-	struct tcf_result cl_res;
+	struct mini_Qdisc *miniq = rcu_dereference_bh(entry->miniq);
+	struct tcf_result res;
 
 	if (!miniq)
-		return skb;
+		return ret;
 
-	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
 	tc_skb_cb(skb)->mru = 0;
 	tc_skb_cb(skb)->post_ct = false;
-	mini_qdisc_bstats_cpu_update(miniq, skb);
 
-	switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) {
+	mini_qdisc_bstats_cpu_update(miniq, skb);
+	ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false);
+	/* Only tcf related quirks below. */
+	switch (ret) {
+	case TC_ACT_SHOT:
+		mini_qdisc_qstats_cpu_drop(miniq);
+		break;
 	case TC_ACT_OK:
 	case TC_ACT_RECLASSIFY:
-		skb->tc_index = TC_H_MIN(cl_res.classid);
+		skb->tc_index = TC_H_MIN(res.classid);
 		break;
+	}
+#endif /* CONFIG_NET_CLS_ACT */
+	return ret;
+}
+
+static DEFINE_STATIC_KEY_FALSE(tcx_needed_key);
+
+void tcx_inc(void)
+{
+	static_branch_inc(&tcx_needed_key);
+}
+
+void tcx_dec(void)
+{
+	static_branch_dec(&tcx_needed_key);
+}
+
+static __always_inline enum tcx_action_base
+tcx_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb,
+	const bool needs_mac)
+{
+	const struct bpf_mprog_fp *fp;
+	const struct bpf_prog *prog;
+	int ret = TCX_NEXT;
+
+	if (needs_mac)
+		__skb_push(skb, skb->mac_len);
+	bpf_mprog_foreach_prog(entry, fp, prog) {
+		bpf_compute_data_pointers(skb);
+		ret = bpf_prog_run(prog, skb);
+		if (ret != TCX_NEXT)
+			break;
+	}
+	if (needs_mac)
+		__skb_pull(skb, skb->mac_len);
+	return tcx_action_code(skb, ret);
+}
+
+static __always_inline struct sk_buff *
+sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
+		   struct net_device *orig_dev, bool *another)
+{
+	struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress);
+	int sch_ret;
+
+	if (!entry)
+		return skb;
+	if (*pt_prev) {
+		*ret = deliver_skb(skb, *pt_prev, orig_dev);
+		*pt_prev = NULL;
+	}
+
+	qdisc_skb_cb(skb)->pkt_len = skb->len;
+	tcx_set_ingress(skb, true);
+
+	if (static_branch_unlikely(&tcx_needed_key)) {
+		sch_ret = tcx_run(entry, skb, true);
+		if (sch_ret != TC_ACT_UNSPEC)
+			goto ingress_verdict;
+	}
+	sch_ret = tc_run(tcx_entry(entry), skb);
+ingress_verdict:
+	switch (sch_ret) {
+	case TC_ACT_REDIRECT:
+		/* skb_mac_header check was done by BPF, so we can safely
+		 * push the L2 header back before redirecting to another
+		 * netdev.
+		 */
+		__skb_push(skb, skb->mac_len);
+		if (skb_do_redirect(skb) == -EAGAIN) {
+			__skb_pull(skb, skb->mac_len);
+			*another = true;
+			break;
+		}
+		*ret = NET_RX_SUCCESS;
+		return NULL;
 	case TC_ACT_SHOT:
-		mini_qdisc_qstats_cpu_drop(miniq);
-		*ret = NET_XMIT_DROP;
-		kfree_skb_reason(skb, SKB_DROP_REASON_TC_EGRESS);
+		kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS);
+		*ret = NET_RX_DROP;
 		return NULL;
+	/* used by tc_run */
 	case TC_ACT_STOLEN:
 	case TC_ACT_QUEUED:
 	case TC_ACT_TRAP:
-		*ret = NET_XMIT_SUCCESS;
 		consume_skb(skb);
+		fallthrough;
+	case TC_ACT_CONSUMED:
+		*ret = NET_RX_SUCCESS;
 		return NULL;
+	}
+
+	return skb;
+}
+
+static __always_inline struct sk_buff *
+sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
+{
+	struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress);
+	int sch_ret;
+
+	if (!entry)
+		return skb;
+
+	/* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was
+	 * already set by the caller.
+	 */
+	if (static_branch_unlikely(&tcx_needed_key)) {
+		sch_ret = tcx_run(entry, skb, false);
+		if (sch_ret != TC_ACT_UNSPEC)
+			goto egress_verdict;
+	}
+	sch_ret = tc_run(tcx_entry(entry), skb);
+egress_verdict:
+	switch (sch_ret) {
 	case TC_ACT_REDIRECT:
 		/* No need to push/pop skb's mac_header here on egress! */
 		skb_do_redirect(skb);
 		*ret = NET_XMIT_SUCCESS;
 		return NULL;
-	default:
-		break;
+	case TC_ACT_SHOT:
+		kfree_skb_reason(skb, SKB_DROP_REASON_TC_EGRESS);
+		*ret = NET_XMIT_DROP;
+		return NULL;
+	/* used by tc_run */
+	case TC_ACT_STOLEN:
+	case TC_ACT_QUEUED:
+	case TC_ACT_TRAP:
+		*ret = NET_XMIT_SUCCESS;
+		return NULL;
 	}
-#endif /* CONFIG_NET_CLS_ACT */
 
 	return skb;
 }
-
-static struct netdev_queue *
-netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
-{
-	int qm = skb_get_queue_mapping(skb);
-
-	return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
-}
-
-static bool netdev_xmit_txqueue_skipped(void)
+#else
+static __always_inline struct sk_buff *
+sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
+		   struct net_device *orig_dev, bool *another)
 {
-	return __this_cpu_read(softnet_data.xmit.skip_txqueue);
+	return skb;
 }
 
-void netdev_xmit_skip_txqueue(bool skip)
+static __always_inline struct sk_buff *
+sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 {
-	__this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
+	return skb;
 }
-EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
-#endif /* CONFIG_NET_EGRESS */
+#endif /* CONFIG_NET_XGRESS */
 
 #ifdef CONFIG_XPS
 static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb,
@@ -4128,9 +4257,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	skb_update_prio(skb);
 
 	qdisc_pkt_len_init(skb);
-#ifdef CONFIG_NET_CLS_ACT
-	skb->tc_at_ingress = 0;
-#endif
+	tcx_set_ingress(skb, false);
 #ifdef CONFIG_NET_EGRESS
 	if (static_branch_unlikely(&egress_needed_key)) {
 		if (nf_hook_egress_active()) {
@@ -5064,72 +5191,6 @@ int (*br_fdb_test_addr_hook)(struct net_device *dev,
 EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
 #endif
 
-static inline struct sk_buff *
-sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
-		   struct net_device *orig_dev, bool *another)
-{
-#ifdef CONFIG_NET_CLS_ACT
-	struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
-	struct tcf_result cl_res;
-
-	/* If there's at least one ingress present somewhere (so
-	 * we get here via enabled static key), remaining devices
-	 * that are not configured with an ingress qdisc will bail
-	 * out here.
-	 */
-	if (!miniq)
-		return skb;
-
-	if (*pt_prev) {
-		*ret = deliver_skb(skb, *pt_prev, orig_dev);
-		*pt_prev = NULL;
-	}
-
-	qdisc_skb_cb(skb)->pkt_len = skb->len;
-	tc_skb_cb(skb)->mru = 0;
-	tc_skb_cb(skb)->post_ct = false;
-	skb->tc_at_ingress = 1;
-	mini_qdisc_bstats_cpu_update(miniq, skb);
-
-	switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) {
-	case TC_ACT_OK:
-	case TC_ACT_RECLASSIFY:
-		skb->tc_index = TC_H_MIN(cl_res.classid);
-		break;
-	case TC_ACT_SHOT:
-		mini_qdisc_qstats_cpu_drop(miniq);
-		kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS);
-		*ret = NET_RX_DROP;
-		return NULL;
-	case TC_ACT_STOLEN:
-	case TC_ACT_QUEUED:
-	case TC_ACT_TRAP:
-		consume_skb(skb);
-		*ret = NET_RX_SUCCESS;
-		return NULL;
-	case TC_ACT_REDIRECT:
-		/* skb_mac_header check was done by cls/act_bpf, so
-		 * we can safely push the L2 header back before
-		 * redirecting to another netdev
-		 */
-		__skb_push(skb, skb->mac_len);
-		if (skb_do_redirect(skb) == -EAGAIN) {
-			__skb_pull(skb, skb->mac_len);
-			*another = true;
-			break;
-		}
-		*ret = NET_RX_SUCCESS;
-		return NULL;
-	case TC_ACT_CONSUMED:
-		*ret = NET_RX_SUCCESS;
-		return NULL;
-	default:
-		break;
-	}
-#endif /* CONFIG_NET_CLS_ACT */
-	return skb;
-}
-
 /**
  *	netdev_is_rx_handler_busy - check if receive handler is registered
  *	@dev: device to check
@@ -10835,7 +10896,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 
 		/* Shutdown queueing discipline. */
 		dev_shutdown(dev);
-
+		dev_tcx_uninstall(dev);
 		dev_xdp_uninstall(dev);
 		bpf_dev_bound_netdev_unregister(dev);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index b4410dc841a0e..797e8f0396964 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9307,7 +9307,7 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog,
 	__u8 value_reg = si->dst_reg;
 	__u8 skb_reg = si->src_reg;
 
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_XGRESS
 	/* If the tstamp_type is read,
 	 * the bpf prog is aware the tstamp could have delivery time.
 	 * Thus, read skb->tstamp as is if tstamp_type_access is true.
@@ -9341,7 +9341,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog,
 	__u8 value_reg = si->src_reg;
 	__u8 skb_reg = si->dst_reg;
 
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_XGRESS
 	/* If the tstamp_type is read,
 	 * the bpf prog is aware the tstamp could have delivery time.
 	 * Thus, write skb->tstamp as is if tstamp_type_access is true.
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 4b95cb1ac4356..470c70deffe2d 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -347,8 +347,7 @@ config NET_SCH_FQ_PIE
 config NET_SCH_INGRESS
 	tristate "Ingress/classifier-action Qdisc"
 	depends on NET_CLS_ACT
-	select NET_INGRESS
-	select NET_EGRESS
+	select NET_XGRESS
 	help
 	  Say Y here if you want to use classifiers for incoming and/or outgoing
 	  packets. This qdisc doesn't do anything else besides running classifiers,
@@ -679,6 +678,7 @@ config NET_EMATCH_IPT
 config NET_CLS_ACT
 	bool "Actions"
 	select NET_CLS
+	select NET_XGRESS
 	help
 	  Say Y here if you want to use traffic control actions. Actions
 	  get attached to classifiers and are invoked after a successful
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index e43a454993723..04e886f6cee43 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -13,6 +13,7 @@
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
+#include <net/tcx.h>
 
 struct ingress_sched_data {
 	struct tcf_block *block;
@@ -78,6 +79,8 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct ingress_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
+	struct bpf_mprog_entry *entry;
+	bool created;
 	int err;
 
 	if (sch->parent != TC_H_INGRESS)
@@ -85,7 +88,13 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 
 	net_inc_ingress_queue();
 
-	mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress);
+	entry = tcx_entry_fetch_or_create(dev, true, &created);
+	if (!entry)
+		return -ENOMEM;
+	tcx_miniq_set_active(entry, true);
+	mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq);
+	if (created)
+		tcx_entry_update(dev, entry, true);
 
 	q->block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	q->block_info.chain_head_change = clsact_chain_head_change;
@@ -103,11 +112,22 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 static void ingress_destroy(struct Qdisc *sch)
 {
 	struct ingress_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct bpf_mprog_entry *entry = rtnl_dereference(dev->tcx_ingress);
 
 	if (sch->parent != TC_H_INGRESS)
 		return;
 
 	tcf_block_put_ext(q->block, sch, &q->block_info);
+
+	if (entry) {
+		tcx_miniq_set_active(entry, false);
+		if (!tcx_entry_is_active(entry)) {
+			tcx_entry_update(dev, NULL, false);
+			tcx_entry_free(entry);
+		}
+	}
+
 	net_dec_ingress_queue();
 }
 
@@ -223,6 +243,8 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct clsact_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
+	struct bpf_mprog_entry *entry;
+	bool created;
 	int err;
 
 	if (sch->parent != TC_H_CLSACT)
@@ -231,7 +253,13 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 	net_inc_ingress_queue();
 	net_inc_egress_queue();
 
-	mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress);
+	entry = tcx_entry_fetch_or_create(dev, true, &created);
+	if (!entry)
+		return -ENOMEM;
+	tcx_miniq_set_active(entry, true);
+	mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq);
+	if (created)
+		tcx_entry_update(dev, entry, true);
 
 	q->ingress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	q->ingress_block_info.chain_head_change = clsact_chain_head_change;
@@ -244,7 +272,13 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 
 	mini_qdisc_pair_block_init(&q->miniqp_ingress, q->ingress_block);
 
-	mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress);
+	entry = tcx_entry_fetch_or_create(dev, false, &created);
+	if (!entry)
+		return -ENOMEM;
+	tcx_miniq_set_active(entry, true);
+	mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq);
+	if (created)
+		tcx_entry_update(dev, entry, false);
 
 	q->egress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS;
 	q->egress_block_info.chain_head_change = clsact_chain_head_change;
@@ -256,12 +290,31 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 static void clsact_destroy(struct Qdisc *sch)
 {
 	struct clsact_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct bpf_mprog_entry *ingress_entry = rtnl_dereference(dev->tcx_ingress);
+	struct bpf_mprog_entry *egress_entry = rtnl_dereference(dev->tcx_egress);
 
 	if (sch->parent != TC_H_CLSACT)
 		return;
 
-	tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
 	tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info);
+	tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
+
+	if (ingress_entry) {
+		tcx_miniq_set_active(ingress_entry, false);
+		if (!tcx_entry_is_active(ingress_entry)) {
+			tcx_entry_update(dev, NULL, true);
+			tcx_entry_free(ingress_entry);
+		}
+	}
+
+	if (egress_entry) {
+		tcx_miniq_set_active(egress_entry, false);
+		if (!tcx_entry_is_active(egress_entry)) {
+			tcx_entry_update(dev, NULL, false);
+			tcx_entry_free(egress_entry);
+		}
+	}
 
 	net_dec_ingress_queue();
 	net_dec_egress_queue();
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1c166870cdf3d..47b76925189f4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1036,6 +1036,8 @@ enum bpf_attach_type {
 	BPF_LSM_CGROUP,
 	BPF_STRUCT_OPS,
 	BPF_NETFILTER,
+	BPF_TCX_INGRESS,
+	BPF_TCX_EGRESS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1053,7 +1055,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_KPROBE_MULTI = 8,
 	BPF_LINK_TYPE_STRUCT_OPS = 9,
 	BPF_LINK_TYPE_NETFILTER = 10,
-
+	BPF_LINK_TYPE_TCX = 11,
 	MAX_BPF_LINK_TYPE,
 };
 
@@ -1569,13 +1571,13 @@ union bpf_attr {
 			__u32		map_fd;		/* struct_ops to attach */
 		};
 		union {
-			__u32		target_fd;	/* object to attach to */
-			__u32		target_ifindex; /* target ifindex */
+			__u32	target_fd;	/* target object to attach to or ... */
+			__u32	target_ifindex; /* target ifindex */
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
 		union {
-			__u32		target_btf_id;	/* btf_id of target to attach to */
+			__u32	target_btf_id;	/* btf_id of target to attach to */
 			struct {
 				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
 				__u32		iter_info_len;	/* iter_info length */
@@ -1609,6 +1611,13 @@ union bpf_attr {
 				__s32		priority;
 				__u32		flags;
 			} netfilter;
+			struct {
+				union {
+					__u32	relative_fd;
+					__u32	relative_id;
+				};
+				__u64		expected_revision;
+			} tcx;
 		};
 	} link_create;
 
@@ -6217,6 +6226,19 @@ struct bpf_sock_tuple {
 	};
 };
 
+/* (Simplified) user return codes for tcx prog type.
+ * A valid tcx program must return one of these defined values. All other
+ * return codes are reserved for future use. Must remain compatible with
+ * their TC_ACT_* counter-parts. For compatibility in behavior, unknown
+ * return codes are mapped to TCX_NEXT.
+ */
+enum tcx_action_base {
+	TCX_NEXT	= -1,
+	TCX_PASS	= 0,
+	TCX_DROP	= 2,
+	TCX_REDIRECT	= 7,
+};
+
 struct bpf_xdp_sock {
 	__u32 queue_id;
 };
@@ -6499,6 +6521,10 @@ struct bpf_link_info {
 				} event; /* BPF_PERF_EVENT_EVENT */
 			};
 		} perf_event;
+		struct {
+			__u32 ifindex;
+			__u32 attach_type;
+		} tcx;
 	};
 } __attribute__((aligned(8)));
 
-- 
GitLab


From fe20ce3a512649b7f883e15dfc01eb29bfcf2168 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 19 Jul 2023 16:08:53 +0200
Subject: [PATCH 0257/1806] libbpf: Add opts-based attach/detach/query API for
 tcx

Extend libbpf attach opts and add a new detach opts API so this can be used
to add/remove fd-based tcx BPF programs. The old-style bpf_prog_detach() and
bpf_prog_detach2() APIs are refactored to reuse the new bpf_prog_detach_opts()
internally.

The bpf_prog_query_opts() API got extended to be able to handle the new
link_ids, link_attach_flags and revision fields.

For concrete usage examples, see the extensive selftests that have been
developed as part of this series.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230719140858.13224-4-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c      | 107 ++++++++++++++++++++++++++-------------
 tools/lib/bpf/bpf.h      |  92 ++++++++++++++++++++++++++++-----
 tools/lib/bpf/libbpf.c   |  12 +++--
 tools/lib/bpf/libbpf.map |   1 +
 4 files changed, 159 insertions(+), 53 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 3b0da19715e1d..4131d3a1484b6 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -629,55 +629,89 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
 	return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts);
 }
 
-int bpf_prog_attach_opts(int prog_fd, int target_fd,
-			  enum bpf_attach_type type,
-			  const struct bpf_prog_attach_opts *opts)
+int bpf_prog_attach_opts(int prog_fd, int target, enum bpf_attach_type type,
+			 const struct bpf_prog_attach_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, expected_revision);
+	__u32 relative_id, flags;
+	int ret, relative_fd;
 	union bpf_attr attr;
-	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_attach_opts))
 		return libbpf_err(-EINVAL);
 
+	relative_id = OPTS_GET(opts, relative_id, 0);
+	relative_fd = OPTS_GET(opts, relative_fd, 0);
+	flags = OPTS_GET(opts, flags, 0);
+
+	/* validate we don't have unexpected combinations of non-zero fields */
+	if (relative_fd && relative_id)
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
-	attr.target_fd	   = target_fd;
-	attr.attach_bpf_fd = prog_fd;
-	attr.attach_type   = type;
-	attr.attach_flags  = OPTS_GET(opts, flags, 0);
-	attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0);
+	attr.target_fd		= target;
+	attr.attach_bpf_fd	= prog_fd;
+	attr.attach_type	= type;
+	attr.replace_bpf_fd	= OPTS_GET(opts, replace_fd, 0);
+	attr.expected_revision	= OPTS_GET(opts, expected_revision, 0);
+
+	if (relative_id) {
+		attr.attach_flags = flags | BPF_F_ID;
+		attr.relative_id  = relative_id;
+	} else {
+		attr.attach_flags = flags;
+		attr.relative_fd  = relative_fd;
+	}
 
 	ret = sys_bpf(BPF_PROG_ATTACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
-int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
+int bpf_prog_detach_opts(int prog_fd, int target, enum bpf_attach_type type,
+			 const struct bpf_prog_detach_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, expected_revision);
+	__u32 relative_id, flags;
+	int ret, relative_fd;
 	union bpf_attr attr;
-	int ret;
+
+	if (!OPTS_VALID(opts, bpf_prog_detach_opts))
+		return libbpf_err(-EINVAL);
+
+	relative_id = OPTS_GET(opts, relative_id, 0);
+	relative_fd = OPTS_GET(opts, relative_fd, 0);
+	flags = OPTS_GET(opts, flags, 0);
+
+	/* validate we don't have unexpected combinations of non-zero fields */
+	if (relative_fd && relative_id)
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, attr_sz);
-	attr.target_fd	 = target_fd;
-	attr.attach_type = type;
+	attr.target_fd		= target;
+	attr.attach_bpf_fd	= prog_fd;
+	attr.attach_type	= type;
+	attr.expected_revision	= OPTS_GET(opts, expected_revision, 0);
+
+	if (relative_id) {
+		attr.attach_flags = flags | BPF_F_ID;
+		attr.relative_id  = relative_id;
+	} else {
+		attr.attach_flags = flags;
+		attr.relative_fd  = relative_fd;
+	}
 
 	ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
-int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
+int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
-	union bpf_attr attr;
-	int ret;
-
-	memset(&attr, 0, attr_sz);
-	attr.target_fd	 = target_fd;
-	attr.attach_bpf_fd = prog_fd;
-	attr.attach_type = type;
+	return bpf_prog_detach_opts(0, target_fd, type, NULL);
+}
 
-	ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz);
-	return libbpf_err_errno(ret);
+int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
+{
+	return bpf_prog_detach_opts(prog_fd, target_fd, type, NULL);
 }
 
 int bpf_link_create(int prog_fd, int target_fd,
@@ -841,8 +875,7 @@ int bpf_iter_create(int link_fd)
 	return libbpf_err_errno(fd);
 }
 
-int bpf_prog_query_opts(int target_fd,
-			enum bpf_attach_type type,
+int bpf_prog_query_opts(int target, enum bpf_attach_type type,
 			struct bpf_prog_query_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, query);
@@ -853,18 +886,20 @@ int bpf_prog_query_opts(int target_fd,
 		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, attr_sz);
-
-	attr.query.target_fd	= target_fd;
-	attr.query.attach_type	= type;
-	attr.query.query_flags	= OPTS_GET(opts, query_flags, 0);
-	attr.query.prog_cnt	= OPTS_GET(opts, prog_cnt, 0);
-	attr.query.prog_ids	= ptr_to_u64(OPTS_GET(opts, prog_ids, NULL));
-	attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL));
+	attr.query.target_fd		= target;
+	attr.query.attach_type		= type;
+	attr.query.query_flags		= OPTS_GET(opts, query_flags, 0);
+	attr.query.count		= OPTS_GET(opts, count, 0);
+	attr.query.prog_ids		= ptr_to_u64(OPTS_GET(opts, prog_ids, NULL));
+	attr.query.link_ids		= ptr_to_u64(OPTS_GET(opts, link_ids, NULL));
+	attr.query.prog_attach_flags	= ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL));
+	attr.query.link_attach_flags	= ptr_to_u64(OPTS_GET(opts, link_attach_flags, NULL));
 
 	ret = sys_bpf(BPF_PROG_QUERY, &attr, attr_sz);
 
 	OPTS_SET(opts, attach_flags, attr.query.attach_flags);
-	OPTS_SET(opts, prog_cnt, attr.query.prog_cnt);
+	OPTS_SET(opts, revision, attr.query.revision);
+	OPTS_SET(opts, count, attr.query.count);
 
 	return libbpf_err_errno(ret);
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index c676295ab9bfe..49e9d88fd9cf1 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -312,22 +312,68 @@ LIBBPF_API int bpf_obj_get(const char *pathname);
 LIBBPF_API int bpf_obj_get_opts(const char *pathname,
 				const struct bpf_obj_get_opts *opts);
 
-struct bpf_prog_attach_opts {
-	size_t sz; /* size of this struct for forward/backward compatibility */
-	unsigned int flags;
-	int replace_prog_fd;
-};
-#define bpf_prog_attach_opts__last_field replace_prog_fd
-
 LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
 			       enum bpf_attach_type type, unsigned int flags);
-LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd,
-				     enum bpf_attach_type type,
-				     const struct bpf_prog_attach_opts *opts);
 LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
 				enum bpf_attach_type type);
 
+struct bpf_prog_attach_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;
+	union {
+		int replace_prog_fd;
+		int replace_fd;
+	};
+	int relative_fd;
+	__u32 relative_id;
+	__u64 expected_revision;
+	size_t :0;
+};
+#define bpf_prog_attach_opts__last_field expected_revision
+
+struct bpf_prog_detach_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;
+	int relative_fd;
+	__u32 relative_id;
+	__u64 expected_revision;
+	size_t :0;
+};
+#define bpf_prog_detach_opts__last_field expected_revision
+
+/**
+ * @brief **bpf_prog_attach_opts()** attaches the BPF program corresponding to
+ * *prog_fd* to a *target* which can represent a file descriptor or netdevice
+ * ifindex.
+ *
+ * @param prog_fd BPF program file descriptor
+ * @param target attach location file descriptor or ifindex
+ * @param type attach type for the BPF program
+ * @param opts options for configuring the attachment
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int target,
+				    enum bpf_attach_type type,
+				    const struct bpf_prog_attach_opts *opts);
+
+/**
+ * @brief **bpf_prog_detach_opts()** detaches the BPF program corresponding to
+ * *prog_fd* from a *target* which can represent a file descriptor or netdevice
+ * ifindex.
+ *
+ * @param prog_fd BPF program file descriptor
+ * @param target detach location file descriptor or ifindex
+ * @param type detach type for the BPF program
+ * @param opts options for configuring the detachment
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_prog_detach_opts(int prog_fd, int target,
+				    enum bpf_attach_type type,
+				    const struct bpf_prog_detach_opts *opts);
+
 union bpf_iter_link_info; /* defined in up-to-date linux/bpf.h */
 struct bpf_link_create_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
@@ -495,13 +541,31 @@ struct bpf_prog_query_opts {
 	__u32 query_flags;
 	__u32 attach_flags; /* output argument */
 	__u32 *prog_ids;
-	__u32 prog_cnt; /* input+output argument */
+	union {
+		/* input+output argument */
+		__u32 prog_cnt;
+		__u32 count;
+	};
 	__u32 *prog_attach_flags;
+	__u32 *link_ids;
+	__u32 *link_attach_flags;
+	__u64 revision;
+	size_t :0;
 };
-#define bpf_prog_query_opts__last_field prog_attach_flags
+#define bpf_prog_query_opts__last_field revision
 
-LIBBPF_API int bpf_prog_query_opts(int target_fd,
-				   enum bpf_attach_type type,
+/**
+ * @brief **bpf_prog_query_opts()** queries the BPF programs and BPF links
+ * which are attached to *target* which can represent a file descriptor or
+ * netdevice ifindex.
+ *
+ * @param target query location file descriptor or ifindex
+ * @param type attach type for the BPF program
+ * @param opts options for configuring the query
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_prog_query_opts(int target, enum bpf_attach_type type,
 				   struct bpf_prog_query_opts *opts);
 LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 63311a73c16d4..0f6913e1059bb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -118,6 +118,8 @@ static const char * const attach_type_name[] = {
 	[BPF_TRACE_KPROBE_MULTI]	= "trace_kprobe_multi",
 	[BPF_STRUCT_OPS]		= "struct_ops",
 	[BPF_NETFILTER]			= "netfilter",
+	[BPF_TCX_INGRESS]		= "tcx_ingress",
+	[BPF_TCX_EGRESS]		= "tcx_egress",
 };
 
 static const char * const link_type_name[] = {
@@ -8696,9 +8698,13 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("ksyscall+",		KPROBE,	0, SEC_NONE, attach_ksyscall),
 	SEC_DEF("kretsyscall+",		KPROBE, 0, SEC_NONE, attach_ksyscall),
 	SEC_DEF("usdt+",		KPROBE,	0, SEC_NONE, attach_usdt),
-	SEC_DEF("tc",			SCHED_CLS, 0, SEC_NONE),
-	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_NONE),
-	SEC_DEF("action",		SCHED_ACT, 0, SEC_NONE),
+	SEC_DEF("tc/ingress",		SCHED_CLS, BPF_TCX_INGRESS, SEC_NONE), /* alias for tcx */
+	SEC_DEF("tc/egress",		SCHED_CLS, BPF_TCX_EGRESS, SEC_NONE),  /* alias for tcx */
+	SEC_DEF("tcx/ingress",		SCHED_CLS, BPF_TCX_INGRESS, SEC_NONE),
+	SEC_DEF("tcx/egress",		SCHED_CLS, BPF_TCX_EGRESS, SEC_NONE),
+	SEC_DEF("tc",			SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */
+	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */
+	SEC_DEF("action",		SCHED_ACT, 0, SEC_NONE), /* deprecated / legacy, use tcx */
 	SEC_DEF("tracepoint+",		TRACEPOINT, 0, SEC_NONE, attach_tp),
 	SEC_DEF("tp+",			TRACEPOINT, 0, SEC_NONE, attach_tp),
 	SEC_DEF("raw_tracepoint+",	RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index d9ec4407befa6..8d1608643c33b 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -395,5 +395,6 @@ LIBBPF_1.2.0 {
 LIBBPF_1.3.0 {
 	global:
 		bpf_obj_pin_opts;
+		bpf_prog_detach_opts;
 		bpf_program__attach_netfilter;
 } LIBBPF_1.2.0;
-- 
GitLab


From 55cc3768473e139483be8f17796b50d21788953f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 19 Jul 2023 16:08:54 +0200
Subject: [PATCH 0258/1806] libbpf: Add link-based API for tcx

Implement tcx BPF link support for libbpf.

The bpf_program__attach_fd() API has been refactored slightly in order to pass
bpf_link_create_opts pointer as input.

A new bpf_program__attach_tcx() has been added on top of this which allows for
passing all relevant data via extensible struct bpf_tcx_opts.

The program sections tcx/ingress and tcx/egress correspond to the hook locations
for tc ingress and egress, respectively.

For concrete usage examples, see the extensive selftests that have been
developed as part of this series.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230719140858.13224-5-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c      | 20 ++++++++++++--
 tools/lib/bpf/bpf.h      |  5 ++++
 tools/lib/bpf/libbpf.c   | 58 +++++++++++++++++++++++++++++++++-------
 tools/lib/bpf/libbpf.h   | 15 +++++++++++
 tools/lib/bpf/libbpf.map |  1 +
 5 files changed, 88 insertions(+), 11 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 4131d3a1484b6..c9b6b311a441f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -719,9 +719,9 @@ int bpf_link_create(int prog_fd, int target_fd,
 		    const struct bpf_link_create_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, link_create);
-	__u32 target_btf_id, iter_info_len;
+	__u32 target_btf_id, iter_info_len, relative_id;
+	int fd, err, relative_fd;
 	union bpf_attr attr;
-	int fd, err;
 
 	if (!OPTS_VALID(opts, bpf_link_create_opts))
 		return libbpf_err(-EINVAL);
@@ -783,6 +783,22 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, netfilter))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_TCX_INGRESS:
+	case BPF_TCX_EGRESS:
+		relative_fd = OPTS_GET(opts, tcx.relative_fd, 0);
+		relative_id = OPTS_GET(opts, tcx.relative_id, 0);
+		if (relative_fd && relative_id)
+			return libbpf_err(-EINVAL);
+		if (relative_id) {
+			attr.link_create.tcx.relative_id = relative_id;
+			attr.link_create.flags |= BPF_F_ID;
+		} else {
+			attr.link_create.tcx.relative_fd = relative_fd;
+		}
+		attr.link_create.tcx.expected_revision = OPTS_GET(opts, tcx.expected_revision, 0);
+		if (!OPTS_ZEROED(opts, tcx))
+			return libbpf_err(-EINVAL);
+		break;
 	default:
 		if (!OPTS_ZEROED(opts, flags))
 			return libbpf_err(-EINVAL);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 49e9d88fd9cf1..044a74ffc38aa 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -401,6 +401,11 @@ struct bpf_link_create_opts {
 			__s32 priority;
 			__u32 flags;
 		} netfilter;
+		struct {
+			__u32 relative_fd;
+			__u32 relative_id;
+			__u64 expected_revision;
+		} tcx;
 	};
 	size_t :0;
 };
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 0f6913e1059bb..17883f5a44b97 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -134,6 +134,7 @@ static const char * const link_type_name[] = {
 	[BPF_LINK_TYPE_KPROBE_MULTI]		= "kprobe_multi",
 	[BPF_LINK_TYPE_STRUCT_OPS]		= "struct_ops",
 	[BPF_LINK_TYPE_NETFILTER]		= "netfilter",
+	[BPF_LINK_TYPE_TCX]			= "tcx",
 };
 
 static const char * const map_type_name[] = {
@@ -11854,11 +11855,10 @@ static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_li
 }
 
 static struct bpf_link *
-bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id,
-		       const char *target_name)
+bpf_program_attach_fd(const struct bpf_program *prog,
+		      int target_fd, const char *target_name,
+		      const struct bpf_link_create_opts *opts)
 {
-	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts,
-			    .target_btf_id = btf_id);
 	enum bpf_attach_type attach_type;
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
@@ -11876,7 +11876,7 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id
 	link->detach = &bpf_link__detach_fd;
 
 	attach_type = bpf_program__expected_attach_type(prog);
-	link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts);
+	link_fd = bpf_link_create(prog_fd, target_fd, attach_type, opts);
 	if (link_fd < 0) {
 		link_fd = -errno;
 		free(link);
@@ -11892,19 +11892,54 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id
 struct bpf_link *
 bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd)
 {
-	return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup");
+	return bpf_program_attach_fd(prog, cgroup_fd, "cgroup", NULL);
 }
 
 struct bpf_link *
 bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd)
 {
-	return bpf_program__attach_fd(prog, netns_fd, 0, "netns");
+	return bpf_program_attach_fd(prog, netns_fd, "netns", NULL);
 }
 
 struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex)
 {
 	/* target_fd/target_ifindex use the same field in LINK_CREATE */
-	return bpf_program__attach_fd(prog, ifindex, 0, "xdp");
+	return bpf_program_attach_fd(prog, ifindex, "xdp", NULL);
+}
+
+struct bpf_link *
+bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
+			const struct bpf_tcx_opts *opts)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, link_create_opts);
+	__u32 relative_id;
+	int relative_fd;
+
+	if (!OPTS_VALID(opts, bpf_tcx_opts))
+		return libbpf_err_ptr(-EINVAL);
+
+	relative_id = OPTS_GET(opts, relative_id, 0);
+	relative_fd = OPTS_GET(opts, relative_fd, 0);
+
+	/* validate we don't have unexpected combinations of non-zero fields */
+	if (!ifindex) {
+		pr_warn("prog '%s': target netdevice ifindex cannot be zero\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+	if (relative_fd && relative_id) {
+		pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
+	link_create_opts.tcx.expected_revision = OPTS_GET(opts, expected_revision, 0);
+	link_create_opts.tcx.relative_fd = relative_fd;
+	link_create_opts.tcx.relative_id = relative_id;
+	link_create_opts.flags = OPTS_GET(opts, flags, 0);
+
+	/* target_fd/target_ifindex use the same field in LINK_CREATE */
+	return bpf_program_attach_fd(prog, ifindex, "tcx", &link_create_opts);
 }
 
 struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog,
@@ -11926,11 +11961,16 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog,
 	}
 
 	if (target_fd) {
+		LIBBPF_OPTS(bpf_link_create_opts, target_opts);
+
 		btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd);
 		if (btf_id < 0)
 			return libbpf_err_ptr(btf_id);
 
-		return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace");
+		target_opts.target_btf_id = btf_id;
+
+		return bpf_program_attach_fd(prog, target_fd, "freplace",
+					     &target_opts);
 	} else {
 		/* no target, so use raw_tracepoint_open for compatibility
 		 * with old kernels
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 674e5788eb108..55b97b2087540 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -733,6 +733,21 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_netfilter(const struct bpf_program *prog,
 			      const struct bpf_netfilter_opts *opts);
 
+struct bpf_tcx_opts {
+	/* size of this struct, for forward/backward compatibility */
+	size_t sz;
+	__u32 flags;
+	__u32 relative_fd;
+	__u32 relative_id;
+	__u64 expected_revision;
+	size_t :0;
+};
+#define bpf_tcx_opts__last_field expected_revision
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
+			const struct bpf_tcx_opts *opts);
+
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 8d1608643c33b..9c7538dd5835e 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -397,4 +397,5 @@ LIBBPF_1.3.0 {
 		bpf_obj_pin_opts;
 		bpf_prog_detach_opts;
 		bpf_program__attach_netfilter;
+		bpf_program__attach_tcx;
 } LIBBPF_1.2.0;
-- 
GitLab


From 4e9c2d9af5612a6992260b3c7d3047c40265861e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 19 Jul 2023 16:08:55 +0200
Subject: [PATCH 0259/1806] libbpf: Add helper macro to clear opts structs

Add a small and generic LIBBPF_OPTS_RESET() helper macros which clears an
opts structure and reinitializes its .sz member to place the structure
size. Additionally, the user can pass option-specific data to reinitialize
via varargs.

I found this very useful when developing selftests, but it is also generic
enough as a macro next to the existing LIBBPF_OPTS() which hides the .sz
initialization, too.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20230719140858.13224-6-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf_common.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h
index 9a7937f339dfa..b7060f2544861 100644
--- a/tools/lib/bpf/libbpf_common.h
+++ b/tools/lib/bpf/libbpf_common.h
@@ -70,4 +70,20 @@
 		};							    \
 	})
 
+/* Helper macro to clear and optionally reinitialize libbpf options struct
+ *
+ * Small helper macro to reset all fields and to reinitialize the common
+ * structure size member. Values provided by users in struct initializer-
+ * syntax as varargs can be provided as well to reinitialize options struct
+ * specific members.
+ */
+#define LIBBPF_OPTS_RESET(NAME, ...)					    \
+	do {								    \
+		memset(&NAME, 0, sizeof(NAME));				    \
+		NAME = (typeof(NAME)) {					    \
+			.sz = sizeof(NAME),				    \
+			__VA_ARGS__					    \
+		};							    \
+	} while (0)
+
 #endif /* __LIBBPF_LIBBPF_COMMON_H */
-- 
GitLab


From 57c61da8bff4a5cf5fd15a26517c3960e04d8d61 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 19 Jul 2023 16:08:56 +0200
Subject: [PATCH 0260/1806] bpftool: Extend net dump with tcx progs

Add support to dump fd-based attach types via bpftool. This includes both
the tc BPF link and attach ops programs. Dumped information contain the
attach location, function entry name, program ID and link ID when applicable.

Example with tc BPF link:

  # ./bpftool net
  xdp:

  tc:
  bond0(4) tcx/ingress cil_from_netdev prog_id 784 link_id 10
  bond0(4) tcx/egress cil_to_netdev prog_id 804 link_id 11

  flow_dissector:

  netfilter:

Example with tc BPF attach ops:

  # ./bpftool net
  xdp:

  tc:
  bond0(4) tcx/ingress cil_from_netdev prog_id 654
  bond0(4) tcx/egress cil_to_netdev prog_id 672

  flow_dissector:

  netfilter:

Currently, permanent flags are not yet supported, so 'unknown' ones are dumped
via NET_DUMP_UINT_ONLY() and once we do have permanent ones, we dump them as
human readable string.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/r/20230719140858.13224-7-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/bpftool/Documentation/bpftool-net.rst | 26 ++---
 tools/bpf/bpftool/net.c                       | 98 ++++++++++++++++++-
 tools/bpf/bpftool/netlink_dumper.h            |  8 ++
 3 files changed, 116 insertions(+), 16 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
index f4e0a516335ac..5e2abd3de5ab8 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-net.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -4,7 +4,7 @@
 bpftool-net
 ================
 -------------------------------------------------------------------------------
-tool for inspection of netdev/tc related bpf prog attachments
+tool for inspection of networking related bpf prog attachments
 -------------------------------------------------------------------------------
 
 :Manual section: 8
@@ -37,10 +37,13 @@ DESCRIPTION
 	**bpftool net { show | list }** [ **dev** *NAME* ]
 		  List bpf program attachments in the kernel networking subsystem.
 
-		  Currently, only device driver xdp attachments and tc filter
-		  classification/action attachments are implemented, i.e., for
-		  program types **BPF_PROG_TYPE_SCHED_CLS**,
-		  **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**.
+		  Currently, device driver xdp attachments, tcx and old-style tc
+		  classifier/action attachments, flow_dissector as well as netfilter
+		  attachments are implemented, i.e., for
+		  program types **BPF_PROG_TYPE_XDP**, **BPF_PROG_TYPE_SCHED_CLS**,
+		  **BPF_PROG_TYPE_SCHED_ACT**, **BPF_PROG_TYPE_FLOW_DISSECTOR**,
+		  **BPF_PROG_TYPE_NETFILTER**.
+
 		  For programs attached to a particular cgroup, e.g.,
 		  **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**,
 		  **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
@@ -49,12 +52,13 @@ DESCRIPTION
 		  bpf programs, users should consult other tools, e.g., iproute2.
 
 		  The current output will start with all xdp program attachments, followed by
-		  all tc class/qdisc bpf program attachments. Both xdp programs and
-		  tc programs are ordered based on ifindex number. If multiple bpf
-		  programs attached to the same networking device through **tc filter**,
-		  the order will be first all bpf programs attached to tc classes, then
-		  all bpf programs attached to non clsact qdiscs, and finally all
-		  bpf programs attached to root and clsact qdisc.
+		  all tcx, then tc class/qdisc bpf program attachments, then flow_dissector
+		  and finally netfilter programs. Both xdp programs and tcx/tc programs are
+		  ordered based on ifindex number. If multiple bpf programs attached
+		  to the same networking device through **tc**, the order will be first
+		  all bpf programs attached to tcx, then tc classes, then all bpf programs
+		  attached to non clsact qdiscs, and finally all bpf programs attached
+		  to root and clsact qdisc.
 
 	**bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ]
 		  Attach bpf program *PROG* to network interface *NAME* with
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 26a49965bf710..66a8ce8ae0127 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -76,6 +76,11 @@ static const char * const attach_type_strings[] = {
 	[NET_ATTACH_TYPE_XDP_OFFLOAD]	= "xdpoffload",
 };
 
+static const char * const attach_loc_strings[] = {
+	[BPF_TCX_INGRESS]		= "tcx/ingress",
+	[BPF_TCX_EGRESS]		= "tcx/egress",
+};
+
 const size_t net_attach_type_size = ARRAY_SIZE(attach_type_strings);
 
 static enum net_attach_type parse_attach_type(const char *str)
@@ -422,8 +427,89 @@ static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 			      filter_info->devname, filter_info->ifindex);
 }
 
-static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
-			   struct ip_devname_ifindex *dev)
+static int __show_dev_tc_bpf_name(__u32 id, char *name, size_t len)
+{
+	struct bpf_prog_info info = {};
+	__u32 ilen = sizeof(info);
+	int fd, ret;
+
+	fd = bpf_prog_get_fd_by_id(id);
+	if (fd < 0)
+		return fd;
+	ret = bpf_obj_get_info_by_fd(fd, &info, &ilen);
+	if (ret < 0)
+		goto out;
+	ret = -ENOENT;
+	if (info.name[0]) {
+		get_prog_full_name(&info, fd, name, len);
+		ret = 0;
+	}
+out:
+	close(fd);
+	return ret;
+}
+
+static void __show_dev_tc_bpf(const struct ip_devname_ifindex *dev,
+			      const enum bpf_attach_type loc)
+{
+	__u32 prog_flags[64] = {}, link_flags[64] = {}, i, j;
+	__u32 prog_ids[64] = {}, link_ids[64] = {};
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	char prog_name[MAX_PROG_FULL_NAME];
+	int ret;
+
+	optq.prog_ids = prog_ids;
+	optq.prog_attach_flags = prog_flags;
+	optq.link_ids = link_ids;
+	optq.link_attach_flags = link_flags;
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	ret = bpf_prog_query_opts(dev->ifindex, loc, &optq);
+	if (ret)
+		return;
+	for (i = 0; i < optq.count; i++) {
+		NET_START_OBJECT;
+		NET_DUMP_STR("devname", "%s", dev->devname);
+		NET_DUMP_UINT("ifindex", "(%u)", dev->ifindex);
+		NET_DUMP_STR("kind", " %s", attach_loc_strings[loc]);
+		ret = __show_dev_tc_bpf_name(prog_ids[i], prog_name,
+					     sizeof(prog_name));
+		if (!ret)
+			NET_DUMP_STR("name", " %s", prog_name);
+		NET_DUMP_UINT("prog_id", " prog_id %u ", prog_ids[i]);
+		if (prog_flags[i] || json_output) {
+			NET_START_ARRAY("prog_flags", "%s ");
+			for (j = 0; prog_flags[i] && j < 32; j++) {
+				if (!(prog_flags[i] & (1 << j)))
+					continue;
+				NET_DUMP_UINT_ONLY(1 << j);
+			}
+			NET_END_ARRAY("");
+		}
+		if (link_ids[i] || json_output) {
+			NET_DUMP_UINT("link_id", "link_id %u ", link_ids[i]);
+			if (link_flags[i] || json_output) {
+				NET_START_ARRAY("link_flags", "%s ");
+				for (j = 0; link_flags[i] && j < 32; j++) {
+					if (!(link_flags[i] & (1 << j)))
+						continue;
+					NET_DUMP_UINT_ONLY(1 << j);
+				}
+				NET_END_ARRAY("");
+			}
+		}
+		NET_END_OBJECT_FINAL;
+	}
+}
+
+static void show_dev_tc_bpf(struct ip_devname_ifindex *dev)
+{
+	__show_dev_tc_bpf(dev, BPF_TCX_INGRESS);
+	__show_dev_tc_bpf(dev, BPF_TCX_EGRESS);
+}
+
+static int show_dev_tc_bpf_classic(int sock, unsigned int nl_pid,
+				   struct ip_devname_ifindex *dev)
 {
 	struct bpf_filter_t filter_info;
 	struct bpf_tcinfo_t tcinfo;
@@ -790,8 +876,9 @@ static int do_show(int argc, char **argv)
 	if (!ret) {
 		NET_START_ARRAY("tc", "%s:\n");
 		for (i = 0; i < dev_array.used_len; i++) {
-			ret = show_dev_tc_bpf(sock, nl_pid,
-					      &dev_array.devices[i]);
+			show_dev_tc_bpf(&dev_array.devices[i]);
+			ret = show_dev_tc_bpf_classic(sock, nl_pid,
+						      &dev_array.devices[i]);
 			if (ret)
 				break;
 		}
@@ -839,7 +926,8 @@ static int do_help(int argc, char **argv)
 		"       ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n"
 		"       " HELP_SPEC_OPTIONS " }\n"
 		"\n"
-		"Note: Only xdp and tc attachments are supported now.\n"
+		"Note: Only xdp, tcx, tc, flow_dissector and netfilter attachments\n"
+		"      are currently supported.\n"
 		"      For progs attached to cgroups, use \"bpftool cgroup\"\n"
 		"      to dump program attachments. For program types\n"
 		"      sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n"
diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
index 774af6c62ef5f..96318106fb497 100644
--- a/tools/bpf/bpftool/netlink_dumper.h
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -76,6 +76,14 @@
 		fprintf(stdout, fmt_str, val);		\
 }
 
+#define NET_DUMP_UINT_ONLY(str)				\
+{							\
+	if (json_output)				\
+		jsonw_uint(json_wtr, str);		\
+	else						\
+		fprintf(stdout, "%u ", str);		\
+}
+
 #define NET_DUMP_STR(name, fmt_str, str)		\
 {							\
 	if (json_output)				\
-- 
GitLab


From cd13c91d929053baec94e278b28c7f3b974d02ed Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 19 Jul 2023 16:08:57 +0200
Subject: [PATCH 0261/1806] selftests/bpf: Add mprog API tests for BPF tcx opts

Add a big batch of test coverage to assert all aspects of the tcx opts
attach, detach and query API:

  # ./vmtest.sh -- ./test_progs -t tc_opts
  [...]
  #238     tc_opts_after:OK
  #239     tc_opts_append:OK
  #240     tc_opts_basic:OK
  #241     tc_opts_before:OK
  #242     tc_opts_chain_classic:OK
  #243     tc_opts_demixed:OK
  #244     tc_opts_detach:OK
  #245     tc_opts_detach_after:OK
  #246     tc_opts_detach_before:OK
  #247     tc_opts_dev_cleanup:OK
  #248     tc_opts_invalid:OK
  #249     tc_opts_mixed:OK
  #250     tc_opts_prepend:OK
  #251     tc_opts_replace:OK
  #252     tc_opts_revision:OK
  Summary: 15/0 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20230719140858.13224-8-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/tc_helpers.h     |   72 +
 .../selftests/bpf/prog_tests/tc_opts.c        | 2239 +++++++++++++++++
 .../selftests/bpf/progs/test_tc_link.c        |   40 +
 3 files changed, 2351 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/tc_helpers.h
 create mode 100644 tools/testing/selftests/bpf/prog_tests/tc_opts.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_tc_link.c

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
new file mode 100644
index 0000000000000..6c93215be8a3a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Isovalent */
+#ifndef TC_HELPERS
+#define TC_HELPERS
+#include <test_progs.h>
+
+static inline __u32 id_from_prog_fd(int fd)
+{
+	struct bpf_prog_info prog_info = {};
+	__u32 prog_info_len = sizeof(prog_info);
+	int err;
+
+	err = bpf_obj_get_info_by_fd(fd, &prog_info, &prog_info_len);
+	if (!ASSERT_OK(err, "id_from_prog_fd"))
+		return 0;
+
+	ASSERT_NEQ(prog_info.id, 0, "prog_info.id");
+	return prog_info.id;
+}
+
+static inline __u32 id_from_link_fd(int fd)
+{
+	struct bpf_link_info link_info = {};
+	__u32 link_info_len = sizeof(link_info);
+	int err;
+
+	err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len);
+	if (!ASSERT_OK(err, "id_from_link_fd"))
+		return 0;
+
+	ASSERT_NEQ(link_info.id, 0, "link_info.id");
+	return link_info.id;
+}
+
+static inline __u32 ifindex_from_link_fd(int fd)
+{
+	struct bpf_link_info link_info = {};
+	__u32 link_info_len = sizeof(link_info);
+	int err;
+
+	err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len);
+	if (!ASSERT_OK(err, "id_from_link_fd"))
+		return 0;
+
+	return link_info.tcx.ifindex;
+}
+
+static inline void __assert_mprog_count(int target, int expected, bool miniq, int ifindex)
+{
+	__u32 count = 0, attach_flags = 0;
+	int err;
+
+	err = bpf_prog_query(ifindex, target, 0, &attach_flags,
+			     NULL, &count);
+	ASSERT_EQ(count, expected, "count");
+	if (!expected && !miniq)
+		ASSERT_EQ(err, -ENOENT, "prog_query");
+	else
+		ASSERT_EQ(err, 0, "prog_query");
+}
+
+static inline void assert_mprog_count(int target, int expected)
+{
+	__assert_mprog_count(target, expected, false, loopback);
+}
+
+static inline void assert_mprog_count_ifindex(int ifindex, int target, int expected)
+{
+	__assert_mprog_count(target, expected, false, ifindex);
+}
+
+#endif /* TC_HELPERS */
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
new file mode 100644
index 0000000000000..7914100f9b469
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
@@ -0,0 +1,2239 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <uapi/linux/if_link.h>
+#include <net/if.h>
+#include <test_progs.h>
+
+#define loopback 1
+#define ping_cmd "ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+#include "test_tc_link.skel.h"
+#include "tc_helpers.h"
+
+void serial_test_tc_opts_basic(void)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, id1, id2;
+	struct test_tc_link *skel;
+	__u32 prog_ids[2];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+
+	assert_mprog_count(BPF_TCX_INGRESS, 0);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	err = bpf_prog_attach_opts(fd1, loopback, BPF_TCX_INGRESS, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(BPF_TCX_INGRESS, 1);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, BPF_TCX_INGRESS, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_in;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	err = bpf_prog_attach_opts(fd2, loopback, BPF_TCX_EGRESS, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_in;
+
+	assert_mprog_count(BPF_TCX_INGRESS, 1);
+	assert_mprog_count(BPF_TCX_EGRESS, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, BPF_TCX_EGRESS, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_eg;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+
+cleanup_eg:
+	err = bpf_prog_detach_opts(fd2, loopback, BPF_TCX_EGRESS, &optd);
+	ASSERT_OK(err, "prog_detach_eg");
+
+	assert_mprog_count(BPF_TCX_INGRESS, 1);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+cleanup_in:
+	err = bpf_prog_detach_opts(fd1, loopback, BPF_TCX_INGRESS, &optd);
+	ASSERT_OK(err, "prog_detach_in");
+
+	assert_mprog_count(BPF_TCX_INGRESS, 0);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+static void test_tc_opts_before_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd2,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target3;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 4, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_id = id1,
+	);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target3;
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id4, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id2, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+
+cleanup_target4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup_target3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup_target2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup_target:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_before(void)
+{
+	test_tc_opts_before_target(BPF_TCX_INGRESS);
+	test_tc_opts_before_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_after_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target3;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 4, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+		.relative_id = id2,
+	);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target3;
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+
+cleanup_target4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target3;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 6, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+cleanup_target3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 7, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+cleanup_target2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 8, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+cleanup_target:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_after(void)
+{
+	test_tc_opts_after_target(BPF_TCX_INGRESS);
+	test_tc_opts_after_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_revision_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, id1, id2;
+	struct test_tc_link *skel;
+	__u32 prog_ids[3];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 1,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, -ESTALE, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 2,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+
+	LIBBPF_OPTS_RESET(optd,
+		.expected_revision = 2,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_EQ(err, -ESTALE, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup_target2:
+	LIBBPF_OPTS_RESET(optd,
+		.expected_revision = 3,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup_target:
+	LIBBPF_OPTS_RESET(optd);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_revision(void)
+{
+	test_tc_opts_revision_target(BPF_TCX_INGRESS);
+	test_tc_opts_revision_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_chain_classic(int target, bool chain_tc_old)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	bool hook_created = false, tc_attached = false;
+	__u32 fd1, fd2, fd3, id1, id2, id3;
+	struct test_tc_link *skel;
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	if (chain_tc_old) {
+		tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+				       BPF_TC_INGRESS : BPF_TC_EGRESS;
+		err = bpf_tc_hook_create(&tc_hook);
+		if (err == 0)
+			hook_created = true;
+		err = err == -EEXIST ? 0 : err;
+		if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+			goto cleanup;
+
+		tc_opts.prog_fd = fd3;
+		err = bpf_tc_attach(&tc_hook, &tc_opts);
+		if (!ASSERT_OK(err, "bpf_tc_attach"))
+			goto cleanup;
+		tc_attached = true;
+	}
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_detach;
+
+	assert_mprog_count(target, 2);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+	skel->bss->seen_tc3 = false;
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	if (!ASSERT_OK(err, "prog_detach"))
+		goto cleanup_detach;
+
+	assert_mprog_count(target, 1);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+
+cleanup_detach:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	if (!ASSERT_OK(err, "prog_detach"))
+		goto cleanup;
+
+	__assert_mprog_count(target, 0, chain_tc_old, loopback);
+cleanup:
+	if (tc_attached) {
+		tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+		err = bpf_tc_detach(&tc_hook, &tc_opts);
+		ASSERT_OK(err, "bpf_tc_detach");
+	}
+	if (hook_created) {
+		tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+		bpf_tc_hook_destroy(&tc_hook);
+	}
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_opts_chain_classic(void)
+{
+	test_tc_chain_classic(BPF_TCX_INGRESS, false);
+	test_tc_chain_classic(BPF_TCX_EGRESS, false);
+	test_tc_chain_classic(BPF_TCX_INGRESS, true);
+	test_tc_chain_classic(BPF_TCX_EGRESS, true);
+}
+
+static void test_tc_opts_replace_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, id1, id2, id3, detach_fd;
+	__u32 prog_ids[4], prog_flags[4];
+	struct test_tc_link *skel;
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_id = id1,
+		.expected_revision = 2,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	detach_fd = fd2;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_attach_flags = prog_flags;
+	optq.prog_ids = prog_ids;
+
+	memset(prog_flags, 0, sizeof(prog_flags));
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	ASSERT_EQ(optq.prog_attach_flags[0], 0, "prog_flags[0]");
+	ASSERT_EQ(optq.prog_attach_flags[1], 0, "prog_flags[1]");
+	ASSERT_EQ(optq.prog_attach_flags[2], 0, "prog_flags[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+	skel->bss->seen_tc3 = false;
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = fd2,
+		.expected_revision = 3,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	detach_fd = fd3;
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 4, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id3, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+	skel->bss->seen_tc3 = false;
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE | BPF_F_BEFORE,
+		.replace_prog_fd = fd3,
+		.relative_fd = fd1,
+		.expected_revision = 4,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	detach_fd = fd2;
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = fd2,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE | BPF_F_AFTER,
+		.replace_prog_fd = fd2,
+		.relative_fd = fd1,
+		.expected_revision = 5,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	ASSERT_EQ(err, -ERANGE, "prog_attach");
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE | BPF_F_AFTER | BPF_F_REPLACE,
+		.replace_prog_fd = fd2,
+		.relative_fd = fd1,
+		.expected_revision = 5,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	ASSERT_EQ(err, -ERANGE, "prog_attach");
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_id = id1,
+		.expected_revision = 5,
+	);
+
+cleanup_target2:
+	err = bpf_prog_detach_opts(detach_fd, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup_target:
+	LIBBPF_OPTS_RESET(optd);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_replace(void)
+{
+	test_tc_opts_replace_target(BPF_TCX_INGRESS);
+	test_tc_opts_replace_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_invalid_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	__u32 fd1, fd2, id1, id2;
+	struct test_tc_link *skel;
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE | BPF_F_AFTER,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ERANGE, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE | BPF_F_ID,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER | BPF_F_ID,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.relative_fd = fd2,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE | BPF_F_AFTER,
+		.relative_fd = fd2,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ID,
+		.relative_id = id2,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach_x1");
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_invalid(void)
+{
+	test_tc_opts_invalid_target(BPF_TCX_INGRESS);
+	test_tc_opts_invalid_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_prepend_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target3;
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id4, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id1, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+
+cleanup_target4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup_target3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup_target2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup_target:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_prepend(void)
+{
+	test_tc_opts_prepend_target(BPF_TCX_INGRESS);
+	test_tc_opts_prepend_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_append_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target3;
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+
+cleanup_target4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup_target3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup_target2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup_target:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_append(void)
+{
+	test_tc_opts_append_target(BPF_TCX_INGRESS);
+	test_tc_opts_append_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_dev_cleanup_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	int err, ifindex;
+
+	ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth");
+	ifindex = if_nametoindex("tcx_opts1");
+	ASSERT_NEQ(ifindex, 0, "non_zero_ifindex");
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+
+	err = bpf_prog_attach_opts(fd1, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	err = bpf_prog_attach_opts(fd2, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+
+	err = bpf_prog_attach_opts(fd3, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count_ifindex(ifindex, target, 3);
+
+	err = bpf_prog_attach_opts(fd4, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count_ifindex(ifindex, target, 4);
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+	return;
+cleanup3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+cleanup:
+	test_tc_link__destroy(skel);
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+}
+
+void serial_test_tc_opts_dev_cleanup(void)
+{
+	test_tc_opts_dev_cleanup_target(BPF_TCX_INGRESS);
+	test_tc_opts_dev_cleanup_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_mixed_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, pid3, pid4, lid2, lid4;
+	__u32 prog_flags[4], link_flags[4];
+	__u32 prog_ids[4], link_ids[4];
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, detach_fd;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc1),
+				   loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	detach_fd = bpf_program__fd(skel->progs.tc1);
+
+	assert_mprog_count(target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup1;
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc2),
+				   loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc1),
+				   loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc3),
+				   loopback, target, &opta);
+	ASSERT_EQ(err, -EBUSY, "prog_attach");
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc3),
+				   loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	detach_fd = bpf_program__fd(skel->progs.tc3);
+
+	assert_mprog_count(target, 2);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup1;
+	skel->links.tc4 = link;
+
+	lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4));
+
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = bpf_program__fd(skel->progs.tc4),
+	);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc2),
+				   loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+
+	optq.prog_ids = prog_ids;
+	optq.prog_attach_flags = prog_flags;
+	optq.link_ids = link_ids;
+	optq.link_attach_flags = link_flags;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(prog_flags, 0, sizeof(prog_flags));
+	memset(link_ids, 0, sizeof(link_ids));
+	memset(link_flags, 0, sizeof(link_flags));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup1;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid3, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_attach_flags[0], 0, "prog_flags[0]");
+	ASSERT_EQ(optq.link_ids[0], 0, "link_ids[0]");
+	ASSERT_EQ(optq.link_attach_flags[0], 0, "link_flags[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_attach_flags[1], 0, "prog_flags[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.link_attach_flags[1], 0, "link_flags[1]");
+	ASSERT_EQ(optq.prog_ids[2], pid4, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_attach_flags[2], 0, "prog_flags[2]");
+	ASSERT_EQ(optq.link_ids[2], lid4, "link_ids[2]");
+	ASSERT_EQ(optq.link_attach_flags[2], 0, "link_flags[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_attach_flags[3], 0, "prog_flags[3]");
+	ASSERT_EQ(optq.link_ids[3], 0, "link_ids[3]");
+	ASSERT_EQ(optq.link_attach_flags[3], 0, "link_flags[3]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+cleanup1:
+	err = bpf_prog_detach_opts(detach_fd, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_opts_mixed(void)
+{
+	test_tc_opts_mixed_target(BPF_TCX_INGRESS);
+	test_tc_opts_mixed_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_demixed_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	__u32 pid1, pid2;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc1),
+				   loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup1;
+	skel->links.tc2 = link;
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_EQ(err, -EBUSY, "prog_detach");
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 1);
+	goto cleanup;
+
+cleanup1:
+	err = bpf_prog_detach_opts(bpf_program__fd(skel->progs.tc1),
+				   loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_opts_demixed(void)
+{
+	test_tc_opts_demixed_target(BPF_TCX_INGRESS);
+	test_tc_opts_demixed_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_detach_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(target, 2);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(target, 3);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(target, 4);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 3);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 6, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id4, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 7, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	LIBBPF_OPTS_RESET(optd);
+
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+	goto cleanup;
+
+cleanup4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_detach(void)
+{
+	test_tc_opts_detach_target(BPF_TCX_INGRESS);
+	test_tc_opts_detach_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_detach_before_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(target, 2);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(target, 3);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(target, 4);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd2,
+	);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 3);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 6, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id4, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd2,
+	);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd4,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_EQ(err, -ERANGE, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd3,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 7, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id3, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id4, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd4,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 8, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id4, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 0);
+	goto cleanup;
+
+cleanup4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_detach_before(void)
+{
+	test_tc_opts_detach_before_target(BPF_TCX_INGRESS);
+	test_tc_opts_detach_before_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_detach_after_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(target, 2);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(target, 3);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(target, 4);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 3);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 6, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id4, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd4,
+	);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_EQ(err, -ERANGE, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd3,
+	);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_EQ(err, -ERANGE, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_EQ(err, -ERANGE, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 7, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id4, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 8, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 0);
+	goto cleanup;
+
+cleanup4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_detach_after(void)
+{
+	test_tc_opts_detach_after_target(BPF_TCX_INGRESS);
+	test_tc_opts_detach_after_target(BPF_TCX_EGRESS);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c
new file mode 100644
index 0000000000000..ed1fd0e9cee9c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tc_link.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+bool seen_tc1;
+bool seen_tc2;
+bool seen_tc3;
+bool seen_tc4;
+
+SEC("tc/ingress")
+int tc1(struct __sk_buff *skb)
+{
+	seen_tc1 = true;
+	return TCX_NEXT;
+}
+
+SEC("tc/egress")
+int tc2(struct __sk_buff *skb)
+{
+	seen_tc2 = true;
+	return TCX_NEXT;
+}
+
+SEC("tc/egress")
+int tc3(struct __sk_buff *skb)
+{
+	seen_tc3 = true;
+	return TCX_NEXT;
+}
+
+SEC("tc/egress")
+int tc4(struct __sk_buff *skb)
+{
+	seen_tc4 = true;
+	return TCX_NEXT;
+}
-- 
GitLab


From c6d479b3346c7430b911a891f3246043c61f054d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 19 Jul 2023 16:08:58 +0200
Subject: [PATCH 0262/1806] selftests/bpf: Add mprog API tests for BPF tcx
 links

Add a big batch of test coverage to assert all aspects of the tcx link API:

  # ./vmtest.sh -- ./test_progs -t tc_links
  [...]
  #225     tc_links_after:OK
  #226     tc_links_append:OK
  #227     tc_links_basic:OK
  #228     tc_links_before:OK
  #229     tc_links_chain_classic:OK
  #230     tc_links_dev_cleanup:OK
  #231     tc_links_invalid:OK
  #232     tc_links_prepend:OK
  #233     tc_links_replace:OK
  #234     tc_links_revision:OK
  Summary: 10/0 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20230719140858.13224-9-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/tc_links.c       | 1583 +++++++++++++++++
 1 file changed, 1583 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/tc_links.c

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_links.c b/tools/testing/selftests/bpf/prog_tests/tc_links.c
new file mode 100644
index 0000000000000..81eea5f10742e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_links.c
@@ -0,0 +1,1583 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <uapi/linux/if_link.h>
+#include <net/if.h>
+#include <test_progs.h>
+
+#define loopback 1
+#define ping_cmd "ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+#include "test_tc_link.skel.h"
+#include "tc_helpers.h"
+
+void serial_test_tc_links_basic(void)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[2], link_ids[2];
+	__u32 pid1, pid2, lid1, lid2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count(BPF_TCX_INGRESS, 0);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(BPF_TCX_INGRESS, 1);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, BPF_TCX_INGRESS, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+	ASSERT_NEQ(lid1, lid2, "link_ids_1_2");
+
+	assert_mprog_count(BPF_TCX_INGRESS, 1);
+	assert_mprog_count(BPF_TCX_EGRESS, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, BPF_TCX_EGRESS, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count(BPF_TCX_INGRESS, 0);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+}
+
+static void test_tc_links_before_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[5], link_ids[5];
+	__u32 pid1, pid2, pid3, pid4;
+	__u32 lid1, lid2, lid3, lid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3));
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_LINK,
+		.relative_id = lid1,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4));
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid4, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid4, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], pid3, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], lid3, "link_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], pid2, "prog_ids[3]");
+	ASSERT_EQ(optq.link_ids[3], lid2, "link_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_links_before(void)
+{
+	test_tc_links_before_target(BPF_TCX_INGRESS);
+	test_tc_links_before_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_after_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[5], link_ids[5];
+	__u32 pid1, pid2, pid3, pid4;
+	__u32 lid1, lid2, lid3, lid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3));
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER | BPF_F_LINK,
+		.relative_fd = bpf_link__fd(skel->links.tc2),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4));
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid3, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid3, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], pid2, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], lid2, "link_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], pid4, "prog_ids[3]");
+	ASSERT_EQ(optq.link_ids[3], lid4, "link_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_links_after(void)
+{
+	test_tc_links_after_target(BPF_TCX_INGRESS);
+	test_tc_links_after_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_revision_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[3], link_ids[3];
+	__u32 pid1, pid2, lid1, lid2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count(target, 0);
+
+	optl.expected_revision = 1;
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	optl.expected_revision = 1;
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 1);
+
+	optl.expected_revision = 2;
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "prog_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_links_revision(void)
+{
+	test_tc_links_revision_target(BPF_TCX_INGRESS);
+	test_tc_links_revision_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_chain_classic(int target, bool chain_tc_old)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+	bool hook_created = false, tc_attached = false;
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, pid3;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	if (chain_tc_old) {
+		tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+				       BPF_TC_INGRESS : BPF_TC_EGRESS;
+		err = bpf_tc_hook_create(&tc_hook);
+		if (err == 0)
+			hook_created = true;
+		err = err == -EEXIST ? 0 : err;
+		if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+			goto cleanup;
+
+		tc_opts.prog_fd = bpf_program__fd(skel->progs.tc3);
+		err = bpf_tc_attach(&tc_hook, &tc_opts);
+		if (!ASSERT_OK(err, "bpf_tc_attach"))
+			goto cleanup;
+		tc_attached = true;
+	}
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	assert_mprog_count(target, 2);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+	skel->bss->seen_tc3 = false;
+
+	err = bpf_link__detach(skel->links.tc2);
+	if (!ASSERT_OK(err, "prog_detach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+cleanup:
+	if (tc_attached) {
+		tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+		err = bpf_tc_detach(&tc_hook, &tc_opts);
+		ASSERT_OK(err, "bpf_tc_detach");
+	}
+	if (hook_created) {
+		tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+		bpf_tc_hook_destroy(&tc_hook);
+	}
+	assert_mprog_count(target, 1);
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_links_chain_classic(void)
+{
+	test_tc_chain_classic(BPF_TCX_INGRESS, false);
+	test_tc_chain_classic(BPF_TCX_EGRESS, false);
+	test_tc_chain_classic(BPF_TCX_INGRESS, true);
+	test_tc_chain_classic(BPF_TCX_EGRESS, true);
+}
+
+static void test_tc_links_replace_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, pid3, lid1, lid2;
+	__u32 prog_ids[4], link_ids[4];
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	optl.expected_revision = 1;
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+		.relative_id = pid1,
+		.expected_revision = 2,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+	skel->bss->seen_tc3 = false;
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_REPLACE,
+		.relative_fd = bpf_program__fd(skel->progs.tc2),
+		.expected_revision = 3,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_REPLACE | BPF_F_LINK,
+		.relative_fd = bpf_link__fd(skel->links.tc2),
+		.expected_revision = 3,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_REPLACE | BPF_F_LINK | BPF_F_AFTER,
+		.relative_id = lid2,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 2);
+
+	err = bpf_link__update_program(skel->links.tc2, skel->progs.tc3);
+	if (!ASSERT_OK(err, "link_update"))
+		goto cleanup;
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 4, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid3, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+	skel->bss->seen_tc3 = false;
+
+	err = bpf_link__detach(skel->links.tc2);
+	if (!ASSERT_OK(err, "link_detach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+	skel->bss->seen_tc3 = false;
+
+	err = bpf_link__update_program(skel->links.tc1, skel->progs.tc1);
+	if (!ASSERT_OK(err, "link_update_self"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_links_replace(void)
+{
+	test_tc_links_replace_target(BPF_TCX_INGRESS);
+	test_tc_links_replace_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_invalid_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, lid1;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count(target, 0);
+
+	optl.flags = BPF_F_BEFORE | BPF_F_AFTER;
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_ID,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER | BPF_F_ID,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_ID,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_LINK,
+		.relative_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_LINK,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.relative_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_AFTER,
+		.relative_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_ID,
+		.relative_id = pid2,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_ID,
+		.relative_id = 42,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_LINK,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, 0, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER | BPF_F_LINK,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER | BPF_F_LINK,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_LINK | BPF_F_ID,
+		.relative_id = ~0,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_LINK | BPF_F_ID,
+		.relative_id = lid1,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_ID,
+		.relative_id = pid1,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_LINK | BPF_F_ID,
+		.relative_id = lid1,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	assert_mprog_count(target, 2);
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_links_invalid(void)
+{
+	test_tc_links_invalid_target(BPF_TCX_INGRESS);
+	test_tc_links_invalid_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_prepend_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[5], link_ids[5];
+	__u32 pid1, pid2, pid3, pid4;
+	__u32 lid1, lid2, lid3, lid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3));
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4));
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid4, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid4, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid3, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid3, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], pid2, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], lid2, "link_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], pid1, "prog_ids[3]");
+	ASSERT_EQ(optq.link_ids[3], lid1, "link_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_links_prepend(void)
+{
+	test_tc_links_prepend_target(BPF_TCX_INGRESS);
+	test_tc_links_prepend_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_append_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[5], link_ids[5];
+	__u32 pid1, pid2, pid3, pid4;
+	__u32 lid1, lid2, lid3, lid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3));
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4));
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], pid3, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], lid3, "link_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], pid4, "prog_ids[3]");
+	ASSERT_EQ(optq.link_ids[3], lid4, "link_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_links_append(void)
+{
+	test_tc_links_append_target(BPF_TCX_INGRESS);
+	test_tc_links_append_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_dev_cleanup_target(int target)
+{
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 pid1, pid2, pid3, pid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth");
+	ifindex = if_nametoindex("tcx_opts1");
+	ASSERT_NEQ(ifindex, 0, "non_zero_ifindex");
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 3);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 4);
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc1)), 0, "tc1_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc2)), 0, "tc2_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc3)), 0, "tc3_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc4)), 0, "tc4_ifindex");
+
+	test_tc_link__destroy(skel);
+	return;
+cleanup:
+	test_tc_link__destroy(skel);
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+}
+
+void serial_test_tc_links_dev_cleanup(void)
+{
+	test_tc_links_dev_cleanup_target(BPF_TCX_INGRESS);
+	test_tc_links_dev_cleanup_target(BPF_TCX_EGRESS);
+}
-- 
GitLab


From 41ee0145a4ea7f6971c02a6dddef20d6cd806270 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Wed, 19 Jul 2023 17:22:57 +0100
Subject: [PATCH 0263/1806] bpf: sync tools/ uapi header with

Seeing the following:

Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'

...so sync tools version missing some list_node/rb_tree fields.

Fixes: c3c510ce431c ("bpf: Add 'owner' field to bpf_{list,rb}_node")
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Link: https://lore.kernel.org/r/20230719162257.20818-1-alan.maguire@oracle.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 47b76925189f4..739c15906a65d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7098,6 +7098,7 @@ struct bpf_list_head {
 struct bpf_list_node {
 	__u64 :64;
 	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_rb_root {
@@ -7109,6 +7110,7 @@ struct bpf_rb_node {
 	__u64 :64;
 	__u64 :64;
 	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_refcount {
-- 
GitLab


From 6f5a630d7c57cd79b1f526a95e757311e32d41e5 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 18 Jul 2023 16:40:21 -0700
Subject: [PATCH 0264/1806] bpf, net: Introduce skb_pointer_if_linear().

Network drivers always call skb_header_pointer() with non-null buffer.
Remove !buffer check to prevent accidental misuse of skb_header_pointer().
Introduce skb_pointer_if_linear() instead.

Reported-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230718234021.43640-1-alexei.starovoitov@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/skbuff.h | 10 +++++++++-
 kernel/bpf/helpers.c   |  5 ++++-
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ed83f1c5fc1f6..faaba050f843d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4023,7 +4023,7 @@ __skb_header_pointer(const struct sk_buff *skb, int offset, int len,
 	if (likely(hlen - offset >= len))
 		return (void *)data + offset;
 
-	if (!skb || !buffer || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0))
+	if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0))
 		return NULL;
 
 	return buffer;
@@ -4036,6 +4036,14 @@ skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer)
 				    skb_headlen(skb), buffer);
 }
 
+static inline void * __must_check
+skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len)
+{
+	if (likely(skb_headlen(skb) - offset >= len))
+		return skb->data + offset;
+	return NULL;
+}
+
 /**
  *	skb_needs_linearize - check if we need to linearize a given skb
  *			      depending on the given device features.
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index bcff584985e7d..56ce5008aedda 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2263,7 +2263,10 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
 	case BPF_DYNPTR_TYPE_RINGBUF:
 		return ptr->data + ptr->offset + offset;
 	case BPF_DYNPTR_TYPE_SKB:
-		return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt);
+		if (buffer__opt)
+			return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt);
+		else
+			return skb_pointer_if_linear(ptr->data, ptr->offset + offset, len);
 	case BPF_DYNPTR_TYPE_XDP:
 	{
 		void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len);
-- 
GitLab


From 2eb85b750512cc5dc5a93d5ff00e1f83b99651db Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Tue, 18 Jul 2023 00:06:29 +0800
Subject: [PATCH 0265/1806] net: stmmac: don't clear network statistics in
 .ndo_open()

FWICT, the common style in other network drivers: the network
statistics are not cleared since initialization, follow the common
style for stmmac.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Link: https://lore.kernel.org/r/20230717160630.1892-2-jszhang@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index efe85b086abec..a29a9619b48ec 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3829,10 +3829,6 @@ static int __stmmac_open(struct net_device *dev,
 		}
 	}
 
-	/* Extra statistics */
-	memset(&priv->xstats, 0, sizeof(struct stmmac_extra_stats));
-	priv->xstats.threshold = tc;
-
 	priv->rx_copybreak = STMMAC_RX_COPYBREAK;
 
 	buf_sz = dma_conf->dma_buf_sz;
@@ -7322,6 +7318,8 @@ int stmmac_dvr_probe(struct device *device,
 #endif
 	priv->msg_enable = netif_msg_init(debug, default_msg_level);
 
+	priv->xstats.threshold = tc;
+
 	/* Initialize RSS */
 	rxq = priv->plat->rx_queues_to_use;
 	netdev_rss_key_fill(priv->rss.key, sizeof(priv->rss.key));
-- 
GitLab


From 133466c3bbe171f826294161db203f7670bb30c8 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Tue, 18 Jul 2023 00:06:30 +0800
Subject: [PATCH 0266/1806] net: stmmac: use per-queue 64 bit statistics where
 necessary

Currently, there are two major issues with stmmac driver statistics
First of all, statistics in stmmac_extra_stats, stmmac_rxq_stats
and stmmac_txq_stats are 32 bit variables on 32 bit platforms. This
can cause some stats to overflow after several minutes of
high traffic, for example rx_pkt_n, tx_pkt_n and so on.

Secondly, if HW supports multiqueues, there are frequent cacheline
ping pongs on some driver statistic vars, for example, normal_irq_n,
tx_pkt_n and so on. What's more, frequent cacheline ping pongs on
normal_irq_n happens in ISR, this makes the situation worse.

To improve the driver, we convert those statistics to 64 bit, implement
ndo_get_stats64 and update .get_ethtool_stats implementation
accordingly. We also use per-queue statistics where necessary to remove
the cacheline ping pongs as much as possible to make multiqueue
operations faster. Those statistics which are not possible to overflow
and not frequently updated are kept as is.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Link: https://lore.kernel.org/r/20230717160630.1892-3-jszhang@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/common.h  |  39 ++--
 .../net/ethernet/stmicro/stmmac/dwmac-sun8i.c |  12 +-
 .../ethernet/stmicro/stmmac/dwmac100_dma.c    |   7 +-
 .../ethernet/stmicro/stmmac/dwmac4_descs.c    |  16 +-
 .../net/ethernet/stmicro/stmmac/dwmac4_lib.c  |  15 +-
 .../net/ethernet/stmicro/stmmac/dwmac_lib.c   |  12 +-
 .../ethernet/stmicro/stmmac/dwxgmac2_descs.c  |   6 +-
 .../ethernet/stmicro/stmmac/dwxgmac2_dma.c    |  14 +-
 .../net/ethernet/stmicro/stmmac/enh_desc.c    |  20 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h    |  12 +-
 .../net/ethernet/stmicro/stmmac/norm_desc.c   |  15 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac.h  |   2 +
 .../ethernet/stmicro/stmmac/stmmac_ethtool.c  | 123 ++++++++---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 200 ++++++++++++++----
 14 files changed, 335 insertions(+), 158 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 16e67c18b6f71..57f2137bbe9d9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -59,13 +59,25 @@
 /* #define FRAME_FILTER_DEBUG */
 
 struct stmmac_txq_stats {
-	unsigned long tx_pkt_n;
-	unsigned long tx_normal_irq_n;
+	u64 tx_bytes;
+	u64 tx_packets;
+	u64 tx_pkt_n;
+	u64 tx_normal_irq_n;
+	u64 napi_poll;
+	u64 tx_clean;
+	u64 tx_set_ic_bit;
+	u64 tx_tso_frames;
+	u64 tx_tso_nfrags;
+	struct u64_stats_sync syncp;
 };
 
 struct stmmac_rxq_stats {
-	unsigned long rx_pkt_n;
-	unsigned long rx_normal_irq_n;
+	u64 rx_bytes;
+	u64 rx_packets;
+	u64 rx_pkt_n;
+	u64 rx_normal_irq_n;
+	u64 napi_poll;
+	struct u64_stats_sync syncp;
 };
 
 /* Extra statistic and debug information exposed by ethtool */
@@ -81,6 +93,7 @@ struct stmmac_extra_stats {
 	unsigned long tx_frame_flushed;
 	unsigned long tx_payload_error;
 	unsigned long tx_ip_header_error;
+	unsigned long tx_collision;
 	/* Receive errors */
 	unsigned long rx_desc;
 	unsigned long sa_filter_fail;
@@ -113,14 +126,6 @@ struct stmmac_extra_stats {
 	/* Tx/Rx IRQ Events */
 	unsigned long rx_early_irq;
 	unsigned long threshold;
-	unsigned long tx_pkt_n;
-	unsigned long rx_pkt_n;
-	unsigned long normal_irq_n;
-	unsigned long rx_normal_irq_n;
-	unsigned long napi_poll;
-	unsigned long tx_normal_irq_n;
-	unsigned long tx_clean;
-	unsigned long tx_set_ic_bit;
 	unsigned long irq_receive_pmt_irq_n;
 	/* MMC info */
 	unsigned long mmc_tx_irq_n;
@@ -190,18 +195,16 @@ struct stmmac_extra_stats {
 	unsigned long mtl_rx_fifo_ctrl_active;
 	unsigned long mac_rx_frame_ctrl_fifo;
 	unsigned long mac_gmii_rx_proto_engine;
-	/* TSO */
-	unsigned long tx_tso_frames;
-	unsigned long tx_tso_nfrags;
 	/* EST */
 	unsigned long mtl_est_cgce;
 	unsigned long mtl_est_hlbs;
 	unsigned long mtl_est_hlbf;
 	unsigned long mtl_est_btre;
 	unsigned long mtl_est_btrlm;
-	/* per queue statistics */
-	struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES];
-	struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES];
+	unsigned long rx_dropped;
+	unsigned long rx_errors;
+	unsigned long tx_dropped;
+	unsigned long tx_errors;
 };
 
 /* Safety Feature statistics exposed by ethtool */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 2b5ebb15bfda8..b607279e8cbd7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -440,8 +440,10 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 				     struct stmmac_extra_stats *x, u32 chan,
 				     u32 dir)
 {
-	u32 v;
+	struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[chan];
+	struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[chan];
 	int ret = 0;
+	u32 v;
 
 	v = readl(ioaddr + EMAC_INT_STA);
 
@@ -452,7 +454,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 
 	if (v & EMAC_TX_INT) {
 		ret |= handle_tx;
-		x->tx_normal_irq_n++;
+		u64_stats_update_begin(&tx_q->txq_stats.syncp);
+		tx_q->txq_stats.tx_normal_irq_n++;
+		u64_stats_update_end(&tx_q->txq_stats.syncp);
 	}
 
 	if (v & EMAC_TX_DMA_STOP_INT)
@@ -474,7 +478,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 
 	if (v & EMAC_RX_INT) {
 		ret |= handle_rx;
-		x->rx_normal_irq_n++;
+		u64_stats_update_begin(&rx_q->rxq_stats.syncp);
+		rx_q->rxq_stats.rx_normal_irq_n++;
+		u64_stats_update_end(&rx_q->rxq_stats.syncp);
 	}
 
 	if (v & EMAC_RX_BUF_UA_INT)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
index 1c32b1788f02e..dea270f60cc3e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
@@ -82,29 +82,24 @@ static void dwmac100_dump_dma_regs(struct stmmac_priv *priv,
 }
 
 /* DMA controller has two counters to track the number of the missed frames. */
-static void dwmac100_dma_diagnostic_fr(struct net_device_stats *stats,
-				       struct stmmac_extra_stats *x,
+static void dwmac100_dma_diagnostic_fr(struct stmmac_extra_stats *x,
 				       void __iomem *ioaddr)
 {
 	u32 csr8 = readl(ioaddr + DMA_MISSED_FRAME_CTR);
 
 	if (unlikely(csr8)) {
 		if (csr8 & DMA_MISSED_FRAME_OVE) {
-			stats->rx_over_errors += 0x800;
 			x->rx_overflow_cntr += 0x800;
 		} else {
 			unsigned int ove_cntr;
 			ove_cntr = ((csr8 & DMA_MISSED_FRAME_OVE_CNTR) >> 17);
-			stats->rx_over_errors += ove_cntr;
 			x->rx_overflow_cntr += ove_cntr;
 		}
 
 		if (csr8 & DMA_MISSED_FRAME_OVE_M) {
-			stats->rx_missed_errors += 0xffff;
 			x->rx_missed_cntr += 0xffff;
 		} else {
 			unsigned int miss_f = (csr8 & DMA_MISSED_FRAME_M_CNTR);
-			stats->rx_missed_errors += miss_f;
 			x->rx_missed_cntr += miss_f;
 		}
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 6a011d8633e8e..89a14084c6117 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -13,8 +13,7 @@
 #include "dwmac4.h"
 #include "dwmac4_descs.h"
 
-static int dwmac4_wrback_get_tx_status(struct net_device_stats *stats,
-				       struct stmmac_extra_stats *x,
+static int dwmac4_wrback_get_tx_status(struct stmmac_extra_stats *x,
 				       struct dma_desc *p,
 				       void __iomem *ioaddr)
 {
@@ -40,15 +39,13 @@ static int dwmac4_wrback_get_tx_status(struct net_device_stats *stats,
 			x->tx_frame_flushed++;
 		if (unlikely(tdes3 & TDES3_LOSS_CARRIER)) {
 			x->tx_losscarrier++;
-			stats->tx_carrier_errors++;
 		}
 		if (unlikely(tdes3 & TDES3_NO_CARRIER)) {
 			x->tx_carrier++;
-			stats->tx_carrier_errors++;
 		}
 		if (unlikely((tdes3 & TDES3_LATE_COLLISION) ||
 			     (tdes3 & TDES3_EXCESSIVE_COLLISION)))
-			stats->collisions +=
+			x->tx_collision +=
 			    (tdes3 & TDES3_COLLISION_COUNT_MASK)
 			    >> TDES3_COLLISION_COUNT_SHIFT;
 
@@ -73,8 +70,7 @@ static int dwmac4_wrback_get_tx_status(struct net_device_stats *stats,
 	return ret;
 }
 
-static int dwmac4_wrback_get_rx_status(struct net_device_stats *stats,
-				       struct stmmac_extra_stats *x,
+static int dwmac4_wrback_get_rx_status(struct stmmac_extra_stats *x,
 				       struct dma_desc *p)
 {
 	unsigned int rdes1 = le32_to_cpu(p->des1);
@@ -93,7 +89,7 @@ static int dwmac4_wrback_get_rx_status(struct net_device_stats *stats,
 
 	if (unlikely(rdes3 & RDES3_ERROR_SUMMARY)) {
 		if (unlikely(rdes3 & RDES3_GIANT_PACKET))
-			stats->rx_length_errors++;
+			x->rx_length++;
 		if (unlikely(rdes3 & RDES3_OVERFLOW_ERROR))
 			x->rx_gmac_overflow++;
 
@@ -103,10 +99,8 @@ static int dwmac4_wrback_get_rx_status(struct net_device_stats *stats,
 		if (unlikely(rdes3 & RDES3_RECEIVE_ERROR))
 			x->rx_mii++;
 
-		if (unlikely(rdes3 & RDES3_CRC_ERROR)) {
+		if (unlikely(rdes3 & RDES3_CRC_ERROR))
 			x->rx_crc_errors++;
-			stats->rx_crc_errors++;
-		}
 
 		if (unlikely(rdes3 & RDES3_DRIBBLE_ERROR))
 			x->dribbling_bit++;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index df41eac54058f..8dc8c2d91fa5b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -171,6 +171,8 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 	const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs;
 	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(dwmac4_addrs, chan));
 	u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan));
+	struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[chan];
+	struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[chan];
 	int ret = 0;
 
 	if (dir == DMA_DIR_RX)
@@ -198,18 +200,19 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 		}
 	}
 	/* TX/RX NORMAL interrupts */
-	if (likely(intr_status & DMA_CHAN_STATUS_NIS))
-		x->normal_irq_n++;
 	if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
-		x->rx_normal_irq_n++;
-		x->rxq_stats[chan].rx_normal_irq_n++;
+		u64_stats_update_begin(&rx_q->rxq_stats.syncp);
+		rx_q->rxq_stats.rx_normal_irq_n++;
+		u64_stats_update_end(&rx_q->rxq_stats.syncp);
 		ret |= handle_rx;
 	}
 	if (likely(intr_status & DMA_CHAN_STATUS_TI)) {
-		x->tx_normal_irq_n++;
-		x->txq_stats[chan].tx_normal_irq_n++;
+		u64_stats_update_begin(&tx_q->txq_stats.syncp);
+		tx_q->txq_stats.tx_normal_irq_n++;
+		u64_stats_update_end(&tx_q->txq_stats.syncp);
 		ret |= handle_tx;
 	}
+
 	if (unlikely(intr_status & DMA_CHAN_STATUS_TBU))
 		ret |= handle_tx;
 	if (unlikely(intr_status & DMA_CHAN_STATUS_ERI))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index 0b6f999a83052..aaa09b16b016f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -10,6 +10,7 @@
 #include <linux/iopoll.h>
 #include "common.h"
 #include "dwmac_dma.h"
+#include "stmmac.h"
 
 #define GMAC_HI_REG_AE		0x80000000
 
@@ -161,6 +162,8 @@ static void show_rx_process_state(unsigned int status)
 int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 			struct stmmac_extra_stats *x, u32 chan, u32 dir)
 {
+	struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[chan];
+	struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[chan];
 	int ret = 0;
 	/* read the status register (CSR5) */
 	u32 intr_status = readl(ioaddr + DMA_STATUS);
@@ -208,17 +211,20 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 	}
 	/* TX/RX NORMAL interrupts */
 	if (likely(intr_status & DMA_STATUS_NIS)) {
-		x->normal_irq_n++;
 		if (likely(intr_status & DMA_STATUS_RI)) {
 			u32 value = readl(ioaddr + DMA_INTR_ENA);
 			/* to schedule NAPI on real RIE event. */
 			if (likely(value & DMA_INTR_ENA_RIE)) {
-				x->rx_normal_irq_n++;
+				u64_stats_update_begin(&rx_q->rxq_stats.syncp);
+				rx_q->rxq_stats.rx_normal_irq_n++;
+				u64_stats_update_end(&rx_q->rxq_stats.syncp);
 				ret |= handle_rx;
 			}
 		}
 		if (likely(intr_status & DMA_STATUS_TI)) {
-			x->tx_normal_irq_n++;
+			u64_stats_update_begin(&tx_q->txq_stats.syncp);
+			tx_q->txq_stats.tx_normal_irq_n++;
+			u64_stats_update_end(&tx_q->txq_stats.syncp);
 			ret |= handle_tx;
 		}
 		if (unlikely(intr_status & DMA_STATUS_ERI))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
index 13c347ee8be9c..fc82862a612c7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -8,8 +8,7 @@
 #include "common.h"
 #include "dwxgmac2.h"
 
-static int dwxgmac2_get_tx_status(struct net_device_stats *stats,
-				  struct stmmac_extra_stats *x,
+static int dwxgmac2_get_tx_status(struct stmmac_extra_stats *x,
 				  struct dma_desc *p, void __iomem *ioaddr)
 {
 	unsigned int tdes3 = le32_to_cpu(p->des3);
@@ -23,8 +22,7 @@ static int dwxgmac2_get_tx_status(struct net_device_stats *stats,
 	return ret;
 }
 
-static int dwxgmac2_get_rx_status(struct net_device_stats *stats,
-				  struct stmmac_extra_stats *x,
+static int dwxgmac2_get_rx_status(struct stmmac_extra_stats *x,
 				  struct dma_desc *p)
 {
 	unsigned int rdes3 = le32_to_cpu(p->des3);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index df5af52fd1a17..b09395f5edcb1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -337,6 +337,8 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 				  struct stmmac_extra_stats *x, u32 chan,
 				  u32 dir)
 {
+	struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[chan];
+	struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[chan];
 	u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan));
 	u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
 	int ret = 0;
@@ -364,16 +366,16 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 
 	/* TX/RX NORMAL interrupts */
 	if (likely(intr_status & XGMAC_NIS)) {
-		x->normal_irq_n++;
-
 		if (likely(intr_status & XGMAC_RI)) {
-			x->rx_normal_irq_n++;
-			x->rxq_stats[chan].rx_normal_irq_n++;
+			u64_stats_update_begin(&rx_q->rxq_stats.syncp);
+			rx_q->rxq_stats.rx_normal_irq_n++;
+			u64_stats_update_end(&rx_q->rxq_stats.syncp);
 			ret |= handle_rx;
 		}
 		if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
-			x->tx_normal_irq_n++;
-			x->txq_stats[chan].tx_normal_irq_n++;
+			u64_stats_update_begin(&tx_q->txq_stats.syncp);
+			tx_q->txq_stats.tx_normal_irq_n++;
+			u64_stats_update_end(&tx_q->txq_stats.syncp);
 			ret |= handle_tx;
 		}
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index a91d8f13a931d..937b7a0466fca 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -12,8 +12,7 @@
 #include "common.h"
 #include "descs_com.h"
 
-static int enh_desc_get_tx_status(struct net_device_stats *stats,
-				  struct stmmac_extra_stats *x,
+static int enh_desc_get_tx_status(struct stmmac_extra_stats *x,
 				  struct dma_desc *p, void __iomem *ioaddr)
 {
 	unsigned int tdes0 = le32_to_cpu(p->des0);
@@ -38,15 +37,13 @@ static int enh_desc_get_tx_status(struct net_device_stats *stats,
 
 		if (unlikely(tdes0 & ETDES0_LOSS_CARRIER)) {
 			x->tx_losscarrier++;
-			stats->tx_carrier_errors++;
 		}
 		if (unlikely(tdes0 & ETDES0_NO_CARRIER)) {
 			x->tx_carrier++;
-			stats->tx_carrier_errors++;
 		}
 		if (unlikely((tdes0 & ETDES0_LATE_COLLISION) ||
 			     (tdes0 & ETDES0_EXCESSIVE_COLLISIONS)))
-			stats->collisions +=
+			x->tx_collision +=
 				(tdes0 & ETDES0_COLLISION_COUNT_MASK) >> 3;
 
 		if (unlikely(tdes0 & ETDES0_EXCESSIVE_DEFERRAL))
@@ -117,8 +114,7 @@ static int enh_desc_coe_rdes0(int ipc_err, int type, int payload_err)
 	return ret;
 }
 
-static void enh_desc_get_ext_status(struct net_device_stats *stats,
-				    struct stmmac_extra_stats *x,
+static void enh_desc_get_ext_status(struct stmmac_extra_stats *x,
 				    struct dma_extended_desc *p)
 {
 	unsigned int rdes0 = le32_to_cpu(p->basic.des0);
@@ -182,8 +178,7 @@ static void enh_desc_get_ext_status(struct net_device_stats *stats,
 	}
 }
 
-static int enh_desc_get_rx_status(struct net_device_stats *stats,
-				  struct stmmac_extra_stats *x,
+static int enh_desc_get_rx_status(struct stmmac_extra_stats *x,
 				  struct dma_desc *p)
 {
 	unsigned int rdes0 = le32_to_cpu(p->des0);
@@ -193,14 +188,14 @@ static int enh_desc_get_rx_status(struct net_device_stats *stats,
 		return dma_own;
 
 	if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
-		stats->rx_length_errors++;
+		x->rx_length++;
 		return discard_frame;
 	}
 
 	if (unlikely(rdes0 & RDES0_ERROR_SUMMARY)) {
 		if (unlikely(rdes0 & RDES0_DESCRIPTOR_ERROR)) {
 			x->rx_desc++;
-			stats->rx_length_errors++;
+			x->rx_length++;
 		}
 		if (unlikely(rdes0 & RDES0_OVERFLOW_ERROR))
 			x->rx_gmac_overflow++;
@@ -209,7 +204,7 @@ static int enh_desc_get_rx_status(struct net_device_stats *stats,
 			pr_err("\tIPC Csum Error/Giant frame\n");
 
 		if (unlikely(rdes0 & RDES0_COLLISION))
-			stats->collisions++;
+			x->rx_collision++;
 		if (unlikely(rdes0 & RDES0_RECEIVE_WATCHDOG))
 			x->rx_watchdog++;
 
@@ -218,7 +213,6 @@ static int enh_desc_get_rx_status(struct net_device_stats *stats,
 
 		if (unlikely(rdes0 & RDES0_CRC_ERROR)) {
 			x->rx_crc_errors++;
-			stats->rx_crc_errors++;
 		}
 		ret = discard_frame;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 6ee7cf07cfd76..652af8f6e75ff 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -57,8 +57,7 @@ struct stmmac_desc_ops {
 	/* Last tx segment reports the transmit status */
 	int (*get_tx_ls)(struct dma_desc *p);
 	/* Return the transmit status looking at the TDES1 */
-	int (*tx_status)(struct net_device_stats *stats,
-			 struct stmmac_extra_stats *x,
+	int (*tx_status)(struct stmmac_extra_stats *x,
 			 struct dma_desc *p, void __iomem *ioaddr);
 	/* Get the buffer size from the descriptor */
 	int (*get_tx_len)(struct dma_desc *p);
@@ -67,11 +66,9 @@ struct stmmac_desc_ops {
 	/* Get the receive frame size */
 	int (*get_rx_frame_len)(struct dma_desc *p, int rx_coe_type);
 	/* Return the reception status looking at the RDES1 */
-	int (*rx_status)(struct net_device_stats *stats,
-			 struct stmmac_extra_stats *x,
+	int (*rx_status)(struct stmmac_extra_stats *x,
 			 struct dma_desc *p);
-	void (*rx_extended_status)(struct net_device_stats *stats,
-				   struct stmmac_extra_stats *x,
+	void (*rx_extended_status)(struct stmmac_extra_stats *x,
 				   struct dma_extended_desc *p);
 	/* Set tx timestamp enable bit */
 	void (*enable_tx_timestamp) (struct dma_desc *p);
@@ -191,8 +188,7 @@ struct stmmac_dma_ops {
 	void (*dma_tx_mode)(struct stmmac_priv *priv, void __iomem *ioaddr,
 			    int mode, u32 channel, int fifosz, u8 qmode);
 	/* To track extra statistic (if supported) */
-	void (*dma_diagnostic_fr)(struct net_device_stats *stats,
-				  struct stmmac_extra_stats *x,
+	void (*dma_diagnostic_fr)(struct stmmac_extra_stats *x,
 				  void __iomem *ioaddr);
 	void (*enable_dma_transmission) (void __iomem *ioaddr);
 	void (*enable_dma_irq)(struct stmmac_priv *priv, void __iomem *ioaddr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index 350e6670a5766..68a7cfcb1d8f3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -12,8 +12,7 @@
 #include "common.h"
 #include "descs_com.h"
 
-static int ndesc_get_tx_status(struct net_device_stats *stats,
-			       struct stmmac_extra_stats *x,
+static int ndesc_get_tx_status(struct stmmac_extra_stats *x,
 			       struct dma_desc *p, void __iomem *ioaddr)
 {
 	unsigned int tdes0 = le32_to_cpu(p->des0);
@@ -31,15 +30,12 @@ static int ndesc_get_tx_status(struct net_device_stats *stats,
 	if (unlikely(tdes0 & TDES0_ERROR_SUMMARY)) {
 		if (unlikely(tdes0 & TDES0_UNDERFLOW_ERROR)) {
 			x->tx_underflow++;
-			stats->tx_fifo_errors++;
 		}
 		if (unlikely(tdes0 & TDES0_NO_CARRIER)) {
 			x->tx_carrier++;
-			stats->tx_carrier_errors++;
 		}
 		if (unlikely(tdes0 & TDES0_LOSS_CARRIER)) {
 			x->tx_losscarrier++;
-			stats->tx_carrier_errors++;
 		}
 		if (unlikely((tdes0 & TDES0_EXCESSIVE_DEFERRAL) ||
 			     (tdes0 & TDES0_EXCESSIVE_COLLISIONS) ||
@@ -47,7 +43,7 @@ static int ndesc_get_tx_status(struct net_device_stats *stats,
 			unsigned int collisions;
 
 			collisions = (tdes0 & TDES0_COLLISION_COUNT_MASK) >> 3;
-			stats->collisions += collisions;
+			x->tx_collision += collisions;
 		}
 		ret = tx_err;
 	}
@@ -70,8 +66,7 @@ static int ndesc_get_tx_len(struct dma_desc *p)
  * and, if required, updates the multicast statistics.
  * In case of success, it returns good_frame because the GMAC device
  * is supposed to be able to compute the csum in HW. */
-static int ndesc_get_rx_status(struct net_device_stats *stats,
-			       struct stmmac_extra_stats *x,
+static int ndesc_get_rx_status(struct stmmac_extra_stats *x,
 			       struct dma_desc *p)
 {
 	int ret = good_frame;
@@ -81,7 +76,7 @@ static int ndesc_get_rx_status(struct net_device_stats *stats,
 		return dma_own;
 
 	if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
-		stats->rx_length_errors++;
+		x->rx_length++;
 		return discard_frame;
 	}
 
@@ -96,11 +91,9 @@ static int ndesc_get_rx_status(struct net_device_stats *stats,
 			x->ipc_csum_error++;
 		if (unlikely(rdes0 & RDES0_COLLISION)) {
 			x->rx_collision++;
-			stats->collisions++;
 		}
 		if (unlikely(rdes0 & RDES0_CRC_ERROR)) {
 			x->rx_crc_errors++;
-			stats->rx_crc_errors++;
 		}
 		ret = discard_frame;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 07ea5ab0a60ba..4ce5eaaae5135 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -77,6 +77,7 @@ struct stmmac_tx_queue {
 	dma_addr_t dma_tx_phy;
 	dma_addr_t tx_tail_addr;
 	u32 mss;
+	struct stmmac_txq_stats txq_stats;
 };
 
 struct stmmac_rx_buffer {
@@ -121,6 +122,7 @@ struct stmmac_rx_queue {
 		unsigned int len;
 		unsigned int error;
 	} state;
+	struct stmmac_rxq_stats rxq_stats;
 };
 
 struct stmmac_channel {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 2ae73ab842d45..b7ac7abecdd35 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -89,14 +89,6 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
 	/* Tx/Rx IRQ Events */
 	STMMAC_STAT(rx_early_irq),
 	STMMAC_STAT(threshold),
-	STMMAC_STAT(tx_pkt_n),
-	STMMAC_STAT(rx_pkt_n),
-	STMMAC_STAT(normal_irq_n),
-	STMMAC_STAT(rx_normal_irq_n),
-	STMMAC_STAT(napi_poll),
-	STMMAC_STAT(tx_normal_irq_n),
-	STMMAC_STAT(tx_clean),
-	STMMAC_STAT(tx_set_ic_bit),
 	STMMAC_STAT(irq_receive_pmt_irq_n),
 	/* MMC info */
 	STMMAC_STAT(mmc_tx_irq_n),
@@ -163,9 +155,6 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
 	STMMAC_STAT(mtl_rx_fifo_ctrl_active),
 	STMMAC_STAT(mac_rx_frame_ctrl_fifo),
 	STMMAC_STAT(mac_gmii_rx_proto_engine),
-	/* TSO */
-	STMMAC_STAT(tx_tso_frames),
-	STMMAC_STAT(tx_tso_nfrags),
 	/* EST */
 	STMMAC_STAT(mtl_est_cgce),
 	STMMAC_STAT(mtl_est_hlbs),
@@ -175,6 +164,23 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
 };
 #define STMMAC_STATS_LEN ARRAY_SIZE(stmmac_gstrings_stats)
 
+/* statistics collected in queue which will be summed up for all TX or RX
+ * queues, or summed up for both TX and RX queues(napi_poll, normal_irq_n).
+ */
+static const char stmmac_qstats_string[][ETH_GSTRING_LEN] = {
+	"rx_pkt_n",
+	"rx_normal_irq_n",
+	"tx_pkt_n",
+	"tx_normal_irq_n",
+	"tx_clean",
+	"tx_set_ic_bit",
+	"tx_tso_frames",
+	"tx_tso_nfrags",
+	"normal_irq_n",
+	"napi_poll",
+};
+#define STMMAC_QSTATS ARRAY_SIZE(stmmac_qstats_string)
+
 /* HW MAC Management counters (if supported) */
 #define STMMAC_MMC_STAT(m)	\
 	{ #m, sizeof_field(struct stmmac_counters, m),	\
@@ -535,23 +541,44 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
 {
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	unsigned int start;
 	int q, stat;
+	u64 *pos;
 	char *p;
 
+	pos = data;
 	for (q = 0; q < tx_cnt; q++) {
-		p = (char *)priv + offsetof(struct stmmac_priv,
-					    xstats.txq_stats[q].tx_pkt_n);
+		struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[q];
+		struct stmmac_txq_stats snapshot;
+
+		data = pos;
+		do {
+			start = u64_stats_fetch_begin(&tx_q->txq_stats.syncp);
+			snapshot = tx_q->txq_stats;
+		} while (u64_stats_fetch_retry(&tx_q->txq_stats.syncp, start));
+
+		p = (char *)&snapshot + offsetof(struct stmmac_txq_stats, tx_pkt_n);
 		for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
-			*data++ = (*(unsigned long *)p);
-			p += sizeof(unsigned long);
+			*data++ += (*(u64 *)p);
+			p += sizeof(u64);
 		}
 	}
+
+	pos = data;
 	for (q = 0; q < rx_cnt; q++) {
-		p = (char *)priv + offsetof(struct stmmac_priv,
-					    xstats.rxq_stats[q].rx_pkt_n);
+		struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[q];
+		struct stmmac_rxq_stats snapshot;
+
+		data = pos;
+		do {
+			start = u64_stats_fetch_begin(&rx_q->rxq_stats.syncp);
+			snapshot = rx_q->rxq_stats;
+		} while (u64_stats_fetch_retry(&rx_q->rxq_stats.syncp, start));
+
+		p = (char *)&snapshot + offsetof(struct stmmac_rxq_stats, rx_pkt_n);
 		for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
-			*data++ = (*(unsigned long *)p);
-			p += sizeof(unsigned long);
+			*data++ += (*(u64 *)p);
+			p += sizeof(u64);
 		}
 	}
 }
@@ -562,8 +589,10 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 	struct stmmac_priv *priv = netdev_priv(dev);
 	u32 rx_queues_count = priv->plat->rx_queues_to_use;
 	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u64 napi_poll = 0, normal_irq_n = 0;
+	int i, j = 0, pos, ret;
 	unsigned long count;
-	int i, j = 0, ret;
+	unsigned int start;
 
 	if (priv->dma_cap.asp) {
 		for (i = 0; i < STMMAC_SAFETY_FEAT_SIZE; i++) {
@@ -574,8 +603,7 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 	}
 
 	/* Update the DMA HW counters for dwmac10/100 */
-	ret = stmmac_dma_diagnostic_fr(priv, &dev->stats, (void *) &priv->xstats,
-			priv->ioaddr);
+	ret = stmmac_dma_diagnostic_fr(priv, &priv->xstats, priv->ioaddr);
 	if (ret) {
 		/* If supported, for new GMAC chips expose the MMC counters */
 		if (priv->dma_cap.rmon) {
@@ -606,6 +634,48 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 		data[j++] = (stmmac_gstrings_stats[i].sizeof_stat ==
 			     sizeof(u64)) ? (*(u64 *)p) : (*(u32 *)p);
 	}
+
+	pos = j;
+	for (i = 0; i < rx_queues_count; i++) {
+		struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[i];
+		struct stmmac_rxq_stats snapshot;
+
+		j = pos;
+		do {
+			start = u64_stats_fetch_begin(&rx_q->rxq_stats.syncp);
+			snapshot = rx_q->rxq_stats;
+		} while (u64_stats_fetch_retry(&rx_q->rxq_stats.syncp, start));
+
+		data[j++] += snapshot.rx_pkt_n;
+		data[j++] += snapshot.rx_normal_irq_n;
+		normal_irq_n += snapshot.rx_normal_irq_n;
+		napi_poll += snapshot.napi_poll;
+	}
+
+	pos = j;
+	for (i = 0; i < tx_queues_count; i++) {
+		struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[i];
+		struct stmmac_txq_stats snapshot;
+
+		j = pos;
+		do {
+			start = u64_stats_fetch_begin(&tx_q->txq_stats.syncp);
+			snapshot = tx_q->txq_stats;
+		} while (u64_stats_fetch_retry(&tx_q->txq_stats.syncp, start));
+
+		data[j++] += snapshot.tx_pkt_n;
+		data[j++] += snapshot.tx_normal_irq_n;
+		normal_irq_n += snapshot.tx_normal_irq_n;
+		data[j++] += snapshot.tx_clean;
+		data[j++] += snapshot.tx_set_ic_bit;
+		data[j++] += snapshot.tx_tso_frames;
+		data[j++] += snapshot.tx_tso_nfrags;
+		napi_poll += snapshot.napi_poll;
+	}
+	normal_irq_n += priv->xstats.rx_early_irq;
+	data[j++] = normal_irq_n;
+	data[j++] = napi_poll;
+
 	stmmac_get_per_qstats(priv, &data[j]);
 }
 
@@ -618,7 +688,7 @@ static int stmmac_get_sset_count(struct net_device *netdev, int sset)
 
 	switch (sset) {
 	case ETH_SS_STATS:
-		len = STMMAC_STATS_LEN +
+		len = STMMAC_STATS_LEN + STMMAC_QSTATS +
 		      STMMAC_TXQ_STATS * tx_cnt +
 		      STMMAC_RXQ_STATS * rx_cnt;
 
@@ -691,8 +761,11 @@ static void stmmac_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 				p += ETH_GSTRING_LEN;
 			}
 		for (i = 0; i < STMMAC_STATS_LEN; i++) {
-			memcpy(p, stmmac_gstrings_stats[i].stat_string,
-				ETH_GSTRING_LEN);
+			memcpy(p, stmmac_gstrings_stats[i].stat_string, ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < STMMAC_QSTATS; i++) {
+			memcpy(p, stmmac_qstats_string[i], ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
 		stmmac_get_qstats_string(priv, p);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a29a9619b48ec..e7ca52f0d2f2d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2434,6 +2434,8 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 	struct dma_desc *tx_desc = NULL;
 	struct xdp_desc xdp_desc;
 	bool work_done = true;
+	u32 tx_set_ic_bit = 0;
+	unsigned long flags;
 
 	/* Avoids TX time-out as we are sharing with slow path */
 	txq_trans_cond_update(nq);
@@ -2494,7 +2496,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		if (set_ic) {
 			tx_q->tx_count_frames = 0;
 			stmmac_set_tx_ic(priv, tx_desc);
-			priv->xstats.tx_set_ic_bit++;
+			tx_set_ic_bit++;
 		}
 
 		stmmac_prepare_tx_desc(priv, tx_desc, 1, xdp_desc.len,
@@ -2506,6 +2508,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size);
 		entry = tx_q->cur_tx;
 	}
+	flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp);
+	tx_q->txq_stats.tx_set_ic_bit += tx_set_ic_bit;
+	u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags);
 
 	if (tx_desc) {
 		stmmac_flush_tx_descriptors(priv, queue);
@@ -2547,11 +2552,11 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
 	struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
 	unsigned int bytes_compl = 0, pkts_compl = 0;
 	unsigned int entry, xmits = 0, count = 0;
+	u32 tx_packets = 0, tx_errors = 0;
+	unsigned long flags;
 
 	__netif_tx_lock_bh(netdev_get_tx_queue(priv->dev, queue));
 
-	priv->xstats.tx_clean++;
-
 	tx_q->xsk_frames_done = 0;
 
 	entry = tx_q->dirty_tx;
@@ -2582,8 +2587,7 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
 		else
 			p = tx_q->dma_tx + entry;
 
-		status = stmmac_tx_status(priv, &priv->dev->stats,
-				&priv->xstats, p, priv->ioaddr);
+		status = stmmac_tx_status(priv,	&priv->xstats, p, priv->ioaddr);
 		/* Check if the descriptor is owned by the DMA */
 		if (unlikely(status & tx_dma_own))
 			break;
@@ -2599,13 +2603,11 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
 		if (likely(!(status & tx_not_ls))) {
 			/* ... verify the status error condition */
 			if (unlikely(status & tx_err)) {
-				priv->dev->stats.tx_errors++;
+				tx_errors++;
 				if (unlikely(status & tx_err_bump_tc))
 					stmmac_bump_dma_threshold(priv, queue);
 			} else {
-				priv->dev->stats.tx_packets++;
-				priv->xstats.tx_pkt_n++;
-				priv->xstats.txq_stats[queue].tx_pkt_n++;
+				tx_packets++;
 			}
 			if (skb)
 				stmmac_get_tx_hwtstamp(priv, p, skb);
@@ -2709,6 +2711,14 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
 			      STMMAC_COAL_TIMER(priv->tx_coal_timer[queue]),
 			      HRTIMER_MODE_REL);
 
+	flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp);
+	tx_q->txq_stats.tx_packets += tx_packets;
+	tx_q->txq_stats.tx_pkt_n += tx_packets;
+	tx_q->txq_stats.tx_clean++;
+	u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags);
+
+	priv->xstats.tx_errors += tx_errors;
+
 	__netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue));
 
 	/* Combine decisions from TX clean and XSK TX */
@@ -2736,7 +2746,7 @@ static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan)
 			    tx_q->dma_tx_phy, chan);
 	stmmac_start_tx_dma(priv, chan);
 
-	priv->dev->stats.tx_errors++;
+	priv->xstats.tx_errors++;
 	netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, chan));
 }
 
@@ -4109,6 +4119,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct stmmac_tx_queue *tx_q;
 	bool has_vlan, set_ic;
 	u8 proto_hdr_len, hdr;
+	unsigned long flags;
 	u32 pay_len, mss;
 	dma_addr_t des;
 	int i;
@@ -4257,7 +4268,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
-		priv->xstats.tx_set_ic_bit++;
 	}
 
 	/* We've used all descriptors we need for this skb, however,
@@ -4273,9 +4283,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
-	dev->stats.tx_bytes += skb->len;
-	priv->xstats.tx_tso_frames++;
-	priv->xstats.tx_tso_nfrags += nfrags;
+	flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp);
+	tx_q->txq_stats.tx_bytes += skb->len;
+	tx_q->txq_stats.tx_tso_frames++;
+	tx_q->txq_stats.tx_tso_nfrags += nfrags;
+	if (set_ic)
+		tx_q->txq_stats.tx_set_ic_bit++;
+	u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags);
 
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4325,7 +4339,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 dma_map_err:
 	dev_err(priv->device, "Tx dma map failed\n");
 	dev_kfree_skb(skb);
-	priv->dev->stats.tx_dropped++;
+	priv->xstats.tx_dropped++;
 	return NETDEV_TX_OK;
 }
 
@@ -4351,6 +4365,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct stmmac_tx_queue *tx_q;
 	bool has_vlan, set_ic;
 	int entry, first_tx;
+	unsigned long flags;
 	dma_addr_t des;
 
 	tx_q = &priv->dma_conf.tx_queue[queue];
@@ -4479,7 +4494,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
-		priv->xstats.tx_set_ic_bit++;
 	}
 
 	/* We've used all descriptors we need for this skb, however,
@@ -4506,7 +4520,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
-	dev->stats.tx_bytes += skb->len;
+	flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp);
+	tx_q->txq_stats.tx_bytes += skb->len;
+	if (set_ic)
+		tx_q->txq_stats.tx_set_ic_bit++;
+	u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags);
 
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4568,7 +4586,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 dma_map_err:
 	netdev_err(priv->dev, "Tx DMA map failed\n");
 	dev_kfree_skb(skb);
-	priv->dev->stats.tx_dropped++;
+	priv->xstats.tx_dropped++;
 	return NETDEV_TX_OK;
 }
 
@@ -4769,9 +4787,12 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
 		set_ic = false;
 
 	if (set_ic) {
+		unsigned long flags;
 		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, tx_desc);
-		priv->xstats.tx_set_ic_bit++;
+		flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp);
+		tx_q->txq_stats.tx_set_ic_bit++;
+		u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags);
 	}
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr);
@@ -4916,16 +4937,18 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 				   struct dma_desc *p, struct dma_desc *np,
 				   struct xdp_buff *xdp)
 {
+	struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[queue];
 	struct stmmac_channel *ch = &priv->channel[queue];
 	unsigned int len = xdp->data_end - xdp->data;
 	enum pkt_hash_types hash_type;
 	int coe = priv->hw->rx_csum;
+	unsigned long flags;
 	struct sk_buff *skb;
 	u32 hash;
 
 	skb = stmmac_construct_skb_zc(ch, xdp);
 	if (!skb) {
-		priv->dev->stats.rx_dropped++;
+		priv->xstats.rx_dropped++;
 		return;
 	}
 
@@ -4944,8 +4967,10 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 	skb_record_rx_queue(skb, queue);
 	napi_gro_receive(&ch->rxtx_napi, skb);
 
-	priv->dev->stats.rx_packets++;
-	priv->dev->stats.rx_bytes += len;
+	flags = u64_stats_update_begin_irqsave(&rx_q->rxq_stats.syncp);
+	rx_q->rxq_stats.rx_pkt_n++;
+	rx_q->rxq_stats.rx_bytes += len;
+	u64_stats_update_end_irqrestore(&rx_q->rxq_stats.syncp, flags);
 }
 
 static bool stmmac_rx_refill_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
@@ -5022,9 +5047,11 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
 	unsigned int count = 0, error = 0, len = 0;
 	int dirty = stmmac_rx_dirty(priv, queue);
 	unsigned int next_entry = rx_q->cur_rx;
+	u32 rx_errors = 0, rx_dropped = 0;
 	unsigned int desc_size;
 	struct bpf_prog *prog;
 	bool failure = false;
+	unsigned long flags;
 	int xdp_status = 0;
 	int status = 0;
 
@@ -5080,8 +5107,7 @@ read_again:
 			p = rx_q->dma_rx + entry;
 
 		/* read the status of the incoming frame */
-		status = stmmac_rx_status(priv, &priv->dev->stats,
-					  &priv->xstats, p);
+		status = stmmac_rx_status(priv, &priv->xstats, p);
 		/* check if managed by the DMA otherwise go ahead */
 		if (unlikely(status & dma_own))
 			break;
@@ -5103,8 +5129,7 @@ read_again:
 			break;
 
 		if (priv->extend_desc)
-			stmmac_rx_extended_status(priv, &priv->dev->stats,
-						  &priv->xstats,
+			stmmac_rx_extended_status(priv, &priv->xstats,
 						  rx_q->dma_erx + entry);
 		if (unlikely(status == discard_frame)) {
 			xsk_buff_free(buf->xdp);
@@ -5112,7 +5137,7 @@ read_again:
 			dirty++;
 			error = 1;
 			if (!priv->hwts_rx_en)
-				priv->dev->stats.rx_errors++;
+				rx_errors++;
 		}
 
 		if (unlikely(error && (status & rx_not_ls)))
@@ -5160,7 +5185,7 @@ read_again:
 			break;
 		case STMMAC_XDP_CONSUMED:
 			xsk_buff_free(buf->xdp);
-			priv->dev->stats.rx_dropped++;
+			rx_dropped++;
 			break;
 		case STMMAC_XDP_TX:
 		case STMMAC_XDP_REDIRECT:
@@ -5181,8 +5206,12 @@ read_again:
 
 	stmmac_finalize_xdp_rx(priv, xdp_status);
 
-	priv->xstats.rx_pkt_n += count;
-	priv->xstats.rxq_stats[queue].rx_pkt_n += count;
+	flags = u64_stats_update_begin_irqsave(&rx_q->rxq_stats.syncp);
+	rx_q->rxq_stats.rx_pkt_n += count;
+	u64_stats_update_end_irqrestore(&rx_q->rxq_stats.syncp, flags);
+
+	priv->xstats.rx_dropped += rx_dropped;
+	priv->xstats.rx_errors += rx_errors;
 
 	if (xsk_uses_need_wakeup(rx_q->xsk_pool)) {
 		if (failure || stmmac_rx_dirty(priv, queue) > 0)
@@ -5206,6 +5235,7 @@ read_again:
  */
 static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 {
+	u32 rx_errors = 0, rx_dropped = 0, rx_bytes = 0, rx_packets = 0;
 	struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[queue];
 	struct stmmac_channel *ch = &priv->channel[queue];
 	unsigned int count = 0, error = 0, len = 0;
@@ -5215,6 +5245,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	unsigned int desc_size;
 	struct sk_buff *skb = NULL;
 	struct stmmac_xdp_buff ctx;
+	unsigned long flags;
 	int xdp_status = 0;
 	int buf_sz;
 
@@ -5270,8 +5301,7 @@ read_again:
 			p = rx_q->dma_rx + entry;
 
 		/* read the status of the incoming frame */
-		status = stmmac_rx_status(priv, &priv->dev->stats,
-				&priv->xstats, p);
+		status = stmmac_rx_status(priv, &priv->xstats, p);
 		/* check if managed by the DMA otherwise go ahead */
 		if (unlikely(status & dma_own))
 			break;
@@ -5288,14 +5318,13 @@ read_again:
 		prefetch(np);
 
 		if (priv->extend_desc)
-			stmmac_rx_extended_status(priv, &priv->dev->stats,
-					&priv->xstats, rx_q->dma_erx + entry);
+			stmmac_rx_extended_status(priv, &priv->xstats, rx_q->dma_erx + entry);
 		if (unlikely(status == discard_frame)) {
 			page_pool_recycle_direct(rx_q->page_pool, buf->page);
 			buf->page = NULL;
 			error = 1;
 			if (!priv->hwts_rx_en)
-				priv->dev->stats.rx_errors++;
+				rx_errors++;
 		}
 
 		if (unlikely(error && (status & rx_not_ls)))
@@ -5363,7 +5392,7 @@ read_again:
 							   virt_to_head_page(ctx.xdp.data),
 							   sync_len, true);
 					buf->page = NULL;
-					priv->dev->stats.rx_dropped++;
+					rx_dropped++;
 
 					/* Clear skb as it was set as
 					 * status by XDP program.
@@ -5392,7 +5421,7 @@ read_again:
 
 			skb = napi_alloc_skb(&ch->rx_napi, buf1_len);
 			if (!skb) {
-				priv->dev->stats.rx_dropped++;
+				rx_dropped++;
 				count++;
 				goto drain_data;
 			}
@@ -5452,8 +5481,8 @@ drain_data:
 		napi_gro_receive(&ch->rx_napi, skb);
 		skb = NULL;
 
-		priv->dev->stats.rx_packets++;
-		priv->dev->stats.rx_bytes += len;
+		rx_packets++;
+		rx_bytes += len;
 		count++;
 	}
 
@@ -5468,8 +5497,14 @@ drain_data:
 
 	stmmac_rx_refill(priv, queue);
 
-	priv->xstats.rx_pkt_n += count;
-	priv->xstats.rxq_stats[queue].rx_pkt_n += count;
+	flags = u64_stats_update_begin_irqsave(&rx_q->rxq_stats.syncp);
+	rx_q->rxq_stats.rx_packets += rx_packets;
+	rx_q->rxq_stats.rx_bytes += rx_bytes;
+	rx_q->rxq_stats.rx_pkt_n += count;
+	u64_stats_update_end_irqrestore(&rx_q->rxq_stats.syncp, flags);
+
+	priv->xstats.rx_dropped += rx_dropped;
+	priv->xstats.rx_errors += rx_errors;
 
 	return count;
 }
@@ -5479,10 +5514,15 @@ static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget)
 	struct stmmac_channel *ch =
 		container_of(napi, struct stmmac_channel, rx_napi);
 	struct stmmac_priv *priv = ch->priv_data;
+	struct stmmac_rx_queue *rx_q;
 	u32 chan = ch->index;
+	unsigned long flags;
 	int work_done;
 
-	priv->xstats.napi_poll++;
+	rx_q = &priv->dma_conf.rx_queue[chan];
+	flags = u64_stats_update_begin_irqsave(&rx_q->rxq_stats.syncp);
+	rx_q->rxq_stats.napi_poll++;
+	u64_stats_update_end_irqrestore(&rx_q->rxq_stats.syncp, flags);
 
 	work_done = stmmac_rx(priv, budget, chan);
 	if (work_done < budget && napi_complete_done(napi, work_done)) {
@@ -5501,10 +5541,15 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget)
 	struct stmmac_channel *ch =
 		container_of(napi, struct stmmac_channel, tx_napi);
 	struct stmmac_priv *priv = ch->priv_data;
+	struct stmmac_tx_queue *tx_q;
 	u32 chan = ch->index;
+	unsigned long flags;
 	int work_done;
 
-	priv->xstats.napi_poll++;
+	tx_q = &priv->dma_conf.tx_queue[chan];
+	flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp);
+	tx_q->txq_stats.napi_poll++;
+	u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags);
 
 	work_done = stmmac_tx_clean(priv, budget, chan);
 	work_done = min(work_done, budget);
@@ -5526,9 +5571,20 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget)
 		container_of(napi, struct stmmac_channel, rxtx_napi);
 	struct stmmac_priv *priv = ch->priv_data;
 	int rx_done, tx_done, rxtx_done;
+	struct stmmac_rx_queue *rx_q;
+	struct stmmac_tx_queue *tx_q;
 	u32 chan = ch->index;
+	unsigned long flags;
+
+	rx_q = &priv->dma_conf.rx_queue[chan];
+	flags = u64_stats_update_begin_irqsave(&rx_q->rxq_stats.syncp);
+	rx_q->rxq_stats.napi_poll++;
+	u64_stats_update_end_irqrestore(&rx_q->rxq_stats.syncp, flags);
 
-	priv->xstats.napi_poll++;
+	tx_q = &priv->dma_conf.tx_queue[chan];
+	flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp);
+	tx_q->txq_stats.napi_poll++;
+	u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags);
 
 	tx_done = stmmac_tx_clean(priv, budget, chan);
 	tx_done = min(tx_done, budget);
@@ -6788,6 +6844,56 @@ int stmmac_xsk_wakeup(struct net_device *dev, u32 queue, u32 flags)
 	return 0;
 }
 
+static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	unsigned int start;
+	int q;
+
+	for (q = 0; q < tx_cnt; q++) {
+		struct stmmac_txq_stats *txq_stats = &priv->dma_conf.tx_queue[q].txq_stats;
+		u64 tx_packets;
+		u64 tx_bytes;
+
+		do {
+			start = u64_stats_fetch_begin(&txq_stats->syncp);
+			tx_packets = txq_stats->tx_packets;
+			tx_bytes   = txq_stats->tx_bytes;
+		} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+
+		stats->tx_packets += tx_packets;
+		stats->tx_bytes += tx_bytes;
+	}
+
+	for (q = 0; q < rx_cnt; q++) {
+		struct stmmac_rxq_stats *rxq_stats = &priv->dma_conf.rx_queue[q].rxq_stats;
+		u64 rx_packets;
+		u64 rx_bytes;
+
+		do {
+			start = u64_stats_fetch_begin(&rxq_stats->syncp);
+			rx_packets = rxq_stats->rx_packets;
+			rx_bytes   = rxq_stats->rx_bytes;
+		} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+
+		stats->rx_packets += rx_packets;
+		stats->rx_bytes += rx_bytes;
+	}
+
+	stats->rx_dropped = priv->xstats.rx_dropped;
+	stats->rx_errors = priv->xstats.rx_errors;
+	stats->tx_dropped = priv->xstats.tx_dropped;
+	stats->tx_errors = priv->xstats.tx_errors;
+	stats->tx_carrier_errors = priv->xstats.tx_losscarrier + priv->xstats.tx_carrier;
+	stats->collisions = priv->xstats.tx_collision + priv->xstats.rx_collision;
+	stats->rx_length_errors = priv->xstats.rx_length;
+	stats->rx_crc_errors = priv->xstats.rx_crc_errors;
+	stats->rx_over_errors = priv->xstats.rx_overflow_cntr;
+	stats->rx_missed_errors = priv->xstats.rx_missed_cntr;
+}
+
 static const struct net_device_ops stmmac_netdev_ops = {
 	.ndo_open = stmmac_open,
 	.ndo_start_xmit = stmmac_xmit,
@@ -6798,6 +6904,7 @@ static const struct net_device_ops stmmac_netdev_ops = {
 	.ndo_set_rx_mode = stmmac_set_rx_mode,
 	.ndo_tx_timeout = stmmac_tx_timeout,
 	.ndo_eth_ioctl = stmmac_ioctl,
+	.ndo_get_stats64 = stmmac_get_stats64,
 	.ndo_setup_tc = stmmac_setup_tc,
 	.ndo_select_queue = stmmac_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -7161,6 +7268,11 @@ int stmmac_dvr_probe(struct device *device,
 	priv->device = device;
 	priv->dev = ndev;
 
+	for (i = 0; i < MTL_MAX_RX_QUEUES; i++)
+		u64_stats_init(&priv->dma_conf.rx_queue[i].rxq_stats.syncp);
+	for (i = 0; i < MTL_MAX_TX_QUEUES; i++)
+		u64_stats_init(&priv->dma_conf.tx_queue[i].txq_stats.syncp);
+
 	stmmac_set_ethtool_ops(ndev);
 	priv->pause = pause;
 	priv->plat = plat_dat;
-- 
GitLab


From 51318bf443955b083d12ab7d7a168e18ea6e14da Mon Sep 17 00:00:00 2001
From: Eugen Hristev <eugen.hristev@collabora.com>
Date: Tue, 18 Jul 2023 12:09:14 +0300
Subject: [PATCH 0267/1806] dt-bindings: net: rockchip-dwmac: add default
 'input' for clock_in_out

'clock_in_out' property is optional, and it can be one of two enums.
The binding does not specify what is the behavior when the property is
missing altogether.
Hence, add a default value that the driver can use.

Signed-off-by: Eugen Hristev <eugen.hristev@collabora.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230718090914.282293-1-eugen.hristev@collabora.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/rockchip-dwmac.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
index 176ea5f90251a..bb943c96c1963 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
@@ -80,6 +80,7 @@ properties:
       "output" means GMAC provides the reference clock.
     $ref: /schemas/types.yaml#/definitions/string
     enum: [input, output]
+    default: input
 
   rockchip,grf:
     description: The phandle of the syscon node for the general register file.
-- 
GitLab


From 3b23ecd53ab5cc46965bc49dece460c0e85ddaac Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 18 Jul 2023 17:09:26 +0800
Subject: [PATCH 0268/1806] net: fec: remove the remaining code of rx copybreak

Since the commit 95698ff6177b ("net: fec: using page pool to manage
RX buffers") has been applied, all the rx packets, no matter small
packets or large packets are put directly into the kernel networking
buffers. That is to say, the rx copybreak function has been removed
since then, but the related code has not been completely cleaned up.
So the purpose of this patch is to clean up the remaining related
code of rx copybreak.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Link: https://lore.kernel.org/r/20230718090928.2654347-2-wei.fang@nxp.com
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec.h      |  2 --
 drivers/net/ethernet/freescale/fec_main.c | 43 -----------------------
 2 files changed, 45 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 63a053dea819d..81c9a07387c4b 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -679,8 +679,6 @@ struct fec_enet_private {
 	struct ethtool_eee eee;
 	unsigned int clk_ref_rate;
 
-	u32 rx_copybreak;
-
 	/* ptp clock period in ns*/
 	unsigned int ptp_inc;
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 1b990a486059b..fef313d3380eb 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -325,8 +325,6 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #define FEC_WOL_FLAG_ENABLE		(0x1 << 1)
 #define FEC_WOL_FLAG_SLEEP_ON		(0x1 << 2)
 
-#define COPYBREAK_DEFAULT	256
-
 /* Max number of allowed TCP segments for software TSO */
 #define FEC_MAX_TSO_SEGS	100
 #define FEC_MAX_SKB_DESCS	(FEC_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
@@ -3051,44 +3049,6 @@ static int fec_enet_set_coalesce(struct net_device *ndev,
 	return 0;
 }
 
-static int fec_enet_get_tunable(struct net_device *netdev,
-				const struct ethtool_tunable *tuna,
-				void *data)
-{
-	struct fec_enet_private *fep = netdev_priv(netdev);
-	int ret = 0;
-
-	switch (tuna->id) {
-	case ETHTOOL_RX_COPYBREAK:
-		*(u32 *)data = fep->rx_copybreak;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
-static int fec_enet_set_tunable(struct net_device *netdev,
-				const struct ethtool_tunable *tuna,
-				const void *data)
-{
-	struct fec_enet_private *fep = netdev_priv(netdev);
-	int ret = 0;
-
-	switch (tuna->id) {
-	case ETHTOOL_RX_COPYBREAK:
-		fep->rx_copybreak = *(u32 *)data;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
 /* LPI Sleep Ts count base on tx clk (clk_ref).
  * The lpi sleep cnt value = X us / (cycle_ns).
  */
@@ -3226,8 +3186,6 @@ static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.get_sset_count		= fec_enet_get_sset_count,
 #endif
 	.get_ts_info		= fec_enet_get_ts_info,
-	.get_tunable		= fec_enet_get_tunable,
-	.set_tunable		= fec_enet_set_tunable,
 	.get_wol		= fec_enet_get_wol,
 	.set_wol		= fec_enet_set_wol,
 	.get_eee		= fec_enet_get_eee,
@@ -4476,7 +4434,6 @@ fec_probe(struct platform_device *pdev)
 	if (fep->bufdesc_ex && fep->ptp_clock)
 		netdev_info(ndev, "registered PHC device %d\n", fep->dev_id);
 
-	fep->rx_copybreak = COPYBREAK_DEFAULT;
 	INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
 
 	pm_runtime_mark_last_busy(&pdev->dev);
-- 
GitLab


From 36bde9c1accb8f7aa908b9c04c0769251629e6fd Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 18 Jul 2023 17:09:27 +0800
Subject: [PATCH 0269/1806] net: fec: remove fec_set_mac_address() from
 fec_enet_init()

The fec_enet_init() is only invoked when the FEC driver probes, and
the network device of FEC is not been brought up at this moment. So
the fec_set_mac_address() does nothing and just returns zero when it
is invoked in the fec_enet_init(). Actually, the MAC address is set
into the hardware through fec_restart() which is also called in the
fec_enet_init().

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Link: https://lore.kernel.org/r/20230718090928.2654347-3-wei.fang@nxp.com
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index fef313d3380eb..03ac7690b5c4a 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3966,9 +3966,6 @@ static int fec_enet_init(struct net_device *ndev)
 	if (ret)
 		goto free_queue_mem;
 
-	/* make sure MAC we just acquired is programmed into the hw */
-	fec_set_mac_address(ndev, NULL);
-
 	/* Set receive and transmit descriptor base. */
 	for (i = 0; i < fep->num_rx_queues; i++) {
 		struct fec_enet_priv_rx_q *rxq = fep->rx_queue[i];
-- 
GitLab


From 636a5e88233a1a95dcb368d340fd04658d548d5f Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 18 Jul 2023 17:09:28 +0800
Subject: [PATCH 0270/1806] net: fec: remove unused members from struct
 fec_enet_private

Three members of struct fec_enet_private have not been used since
they were first introduced into the FEC driver (commit 6605b730c061
("FEC: Add time stamping code and a PTP hardware clock")). Namely,
last_overflow_check, rx_hwtstamp_filter and base_incval. These
unused members make the struct fec_enet_private a bit messy and
might confuse the readers. There is no reason to keep them in the
FEC driver any longer.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Link: https://lore.kernel.org/r/20230718090928.2654347-4-wei.fang@nxp.com
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 81c9a07387c4b..8f1edcca96c49 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -651,12 +651,9 @@ struct fec_enet_private {
 
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_caps;
-	unsigned long last_overflow_check;
 	spinlock_t tmreg_lock;
 	struct cyclecounter cc;
 	struct timecounter tc;
-	int rx_hwtstamp_filter;
-	u32 base_incval;
 	u32 cycle_speed;
 	int hwts_rx_en;
 	int hwts_tx_en;
-- 
GitLab


From 0558e1674598ec9029c1d3bceb787c8340272b51 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 18 Jul 2023 16:38:09 +0200
Subject: [PATCH 0271/1806] udp: use indirect call wrapper for data ready()

In most cases UDP sockets use the default data ready callback.
Leverage the indirect call wrapper for such callback to avoid an
indirect call in fastpath.

The above gives small but measurable performance gain under UDP flood.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/d47d53e6f8ee7a11228ca2f025d6243cc04b77f3.1689691004.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 42a96b3547c9f..8c3ebd95f5b98 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1553,7 +1553,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	spin_unlock(&list->lock);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk);
+		INDIRECT_CALL_1(sk->sk_data_ready, sock_def_readable, sk);
 
 	busylock_release(busy);
 	return 0;
-- 
GitLab


From 730b9051b8bce5eabd1f5b67dfd090c37d5dabea Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 18 Jul 2023 16:16:20 +0000
Subject: [PATCH 0272/1806] tcp: remove tcp_send_partial()

This function does not exist.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230718161620.1391951-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2104a71c75ba7..8d1f1af5e02a8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -606,7 +606,6 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 		 unsigned int mss_now, gfp_t gfp);
 
 void tcp_send_probe0(struct sock *);
-void tcp_send_partial(struct sock *);
 int tcp_write_wakeup(struct sock *, int mib);
 void tcp_send_fin(struct sock *sk);
 void tcp_send_active_reset(struct sock *sk, gfp_t priority);
-- 
GitLab


From 03b123debcbc8db987bda17ed8412cc011064c22 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 18 Jul 2023 16:20:49 +0000
Subject: [PATCH 0273/1806] tcp: tcp_enter_quickack_mode() should be static

After commit d2ccd7bc8acd ("tcp: avoid resetting ACK timer in DCTCP"),
tcp_enter_quickack_mode() is only used from net/ipv4/tcp_input.c.

Fixes: d2ccd7bc8acd ("tcp: avoid resetting ACK timer in DCTCP")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20230718162049.1444938-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h    | 1 -
 net/ipv4/tcp_input.c | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 8d1f1af5e02a8..c5fb900799200 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -350,7 +350,6 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
 struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp,
 				     bool force_schedule);
 
-void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks);
 static inline void tcp_dec_quickack_mode(struct sock *sk,
 					 const unsigned int pkts)
 {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3cd92035e0902..e2affdd147daa 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -297,7 +297,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
 		icsk->icsk_ack.quick = quickacks;
 }
 
-void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -305,7 +305,6 @@ void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 	inet_csk_exit_pingpong_mode(sk);
 	icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
-EXPORT_SYMBOL(tcp_enter_quickack_mode);
 
 /* Send ACKs quickly, if "quick" count is not exhausted
  * and the session is not interactive.
-- 
GitLab


From 4914109a8e1e494c6aa9852f9e84ec77a5fc643f Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 16 Jul 2023 17:09:17 -0400
Subject: [PATCH 0274/1806] netfilter: allow exp not to be removed in
 nf_ct_find_expectation

Currently nf_conntrack_in() calling nf_ct_find_expectation() will
remove the exp from the hash table. However, in some scenario, we
expect the exp not to be removed when the created ct will not be
confirmed, like in OVS and TC conntrack in the following patches.

This patch allows exp not to be removed by setting IPS_CONFIRMED
in the status of the tmpl.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Aaron Conole <aconole@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/netfilter/nf_conntrack_expect.h | 2 +-
 net/netfilter/nf_conntrack_core.c           | 2 +-
 net/netfilter/nf_conntrack_expect.c         | 4 ++--
 net/netfilter/nft_ct.c                      | 2 ++
 4 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index cf0d81be5a96e..165e7a03b8e9d 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -100,7 +100,7 @@ nf_ct_expect_find_get(struct net *net,
 struct nf_conntrack_expect *
 nf_ct_find_expectation(struct net *net,
 		       const struct nf_conntrack_zone *zone,
-		       const struct nf_conntrack_tuple *tuple);
+		       const struct nf_conntrack_tuple *tuple, bool unlink);
 
 void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 				u32 portid, int report);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 992393102d5f5..9f6f2e6435758 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1756,7 +1756,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	cnet = nf_ct_pernet(net);
 	if (cnet->expect_count) {
 		spin_lock_bh(&nf_conntrack_expect_lock);
-		exp = nf_ct_find_expectation(net, zone, tuple);
+		exp = nf_ct_find_expectation(net, zone, tuple, !tmpl || nf_ct_is_confirmed(tmpl));
 		if (exp) {
 			/* Welcome, Mr. Bond.  We've been expecting you... */
 			__set_bit(IPS_EXPECTED_BIT, &ct->status);
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 96948e98ec53d..81ca348915c98 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -171,7 +171,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_find_get);
 struct nf_conntrack_expect *
 nf_ct_find_expectation(struct net *net,
 		       const struct nf_conntrack_zone *zone,
-		       const struct nf_conntrack_tuple *tuple)
+		       const struct nf_conntrack_tuple *tuple, bool unlink)
 {
 	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct nf_conntrack_expect *i, *exp = NULL;
@@ -211,7 +211,7 @@ nf_ct_find_expectation(struct net *net,
 		     !refcount_inc_not_zero(&exp->master->ct_general.use)))
 		return NULL;
 
-	if (exp->flags & NF_CT_EXPECT_PERMANENT) {
+	if (exp->flags & NF_CT_EXPECT_PERMANENT || !unlink) {
 		refcount_inc(&exp->use);
 		return exp;
 	} else if (del_timer(&exp->timeout)) {
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 38958e067aa8a..e87fd4314c686 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -262,6 +262,7 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
 			regs->verdict.code = NF_DROP;
 			return;
 		}
+		__set_bit(IPS_CONFIRMED_BIT, &ct->status);
 	}
 
 	nf_ct_set(skb, ct, IP_CT_NEW);
@@ -368,6 +369,7 @@ static bool nft_ct_tmpl_alloc_pcpu(void)
 			return false;
 		}
 
+		__set_bit(IPS_CONFIRMED_BIT, &tmp->status);
 		per_cpu(nft_ct_pcpu_template, cpu) = tmp;
 	}
 
-- 
GitLab


From 76622ced50a103e278ad560566b5e43d82f718c6 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 16 Jul 2023 17:09:18 -0400
Subject: [PATCH 0275/1806] net: sched: set IPS_CONFIRMED in tmpl status only
 when commit is set in act_ct

With the following flows, the packets will be dropped if OVS TC offload is
enabled.

  'ip,ct_state=-trk,in_port=1 actions=ct(zone=1)'
  'ip,ct_state=+trk+new+rel,in_port=1 actions=ct(commit,zone=1)'
  'ip,ct_state=+trk+new+rel,in_port=1 actions=ct(commit,zone=2),normal'

In the 1st flow, it finds the exp from the hashtable and removes it then
creates the ct with this exp in act_ct. However, in the 2nd flow it goes
to the OVS upcall at the 1st time. When the skb comes back from userspace,
it has to create the ct again without exp(the exp was removed last time).
With no 'rel' set in the ct, the 3rd flow can never get matched.

In OVS conntrack, it works around it by adding its own exp lookup function
ovs_ct_expect_find() where it doesn't remove the exp. Instead of creating
a real ct, it only updates its keys with the exp and its master info. So
when the skb comes back, the exp is still in the hashtable.

However, we can't do this trick in act_ct, as tc flower match is using a
real ct, and passing the exp and its master info to flower parsing via
tc_skb_cb is also not possible (tc_skb_cb size is not big enough).

The simple and clear fix is to not remove the exp at the 1st flow, namely,
not set IPS_CONFIRMED in tmpl when commit is not set in act_ct.

Reported-by: Shuang Li <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Aaron Conole <aconole@redhat.com>
Reviewed-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/act_ct.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index abc71a06d634a..7c652d14528be 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1238,7 +1238,8 @@ static int tcf_ct_fill_params(struct net *net,
 		}
 	}
 
-	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+	if (p->ct_action & TCA_CT_ACT_COMMIT)
+		__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
 	return 0;
 err:
 	nf_ct_put(p->tmpl);
-- 
GitLab


From 8c8b733208058702da451b7d60a12c0ff90b6879 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 16 Jul 2023 17:09:19 -0400
Subject: [PATCH 0276/1806] openvswitch: set IPS_CONFIRMED in tmpl status only
 when commit is set in conntrack

By not setting IPS_CONFIRMED in tmpl that allows the exp not to be removed
from the hashtable when lookup, we can simplify the exp processing code a
lot in openvswitch conntrack.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Aaron Conole <aconole@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/openvswitch/conntrack.c | 78 +++++--------------------------------
 1 file changed, 10 insertions(+), 68 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 331730fd35803..fa955e892210f 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -455,45 +455,6 @@ static int ovs_ct_handle_fragments(struct net *net, struct sw_flow_key *key,
 	return 0;
 }
 
-static struct nf_conntrack_expect *
-ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone,
-		   u16 proto, const struct sk_buff *skb)
-{
-	struct nf_conntrack_tuple tuple;
-	struct nf_conntrack_expect *exp;
-
-	if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, net, &tuple))
-		return NULL;
-
-	exp = __nf_ct_expect_find(net, zone, &tuple);
-	if (exp) {
-		struct nf_conntrack_tuple_hash *h;
-
-		/* Delete existing conntrack entry, if it clashes with the
-		 * expectation.  This can happen since conntrack ALGs do not
-		 * check for clashes between (new) expectations and existing
-		 * conntrack entries.  nf_conntrack_in() will check the
-		 * expectations only if a conntrack entry can not be found,
-		 * which can lead to OVS finding the expectation (here) in the
-		 * init direction, but which will not be removed by the
-		 * nf_conntrack_in() call, if a matching conntrack entry is
-		 * found instead.  In this case all init direction packets
-		 * would be reported as new related packets, while reply
-		 * direction packets would be reported as un-related
-		 * established packets.
-		 */
-		h = nf_conntrack_find_get(net, zone, &tuple);
-		if (h) {
-			struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
-
-			nf_ct_delete(ct, 0, 0);
-			nf_ct_put(ct);
-		}
-	}
-
-	return exp;
-}
-
 /* This replicates logic from nf_conntrack_core.c that is not exported. */
 static enum ip_conntrack_info
 ovs_ct_get_info(const struct nf_conntrack_tuple_hash *h)
@@ -852,36 +813,16 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
 			 const struct ovs_conntrack_info *info,
 			 struct sk_buff *skb)
 {
-	struct nf_conntrack_expect *exp;
-
-	/* If we pass an expected packet through nf_conntrack_in() the
-	 * expectation is typically removed, but the packet could still be
-	 * lost in upcall processing.  To prevent this from happening we
-	 * perform an explicit expectation lookup.  Expected connections are
-	 * always new, and will be passed through conntrack only when they are
-	 * committed, as it is OK to remove the expectation at that time.
-	 */
-	exp = ovs_ct_expect_find(net, &info->zone, info->family, skb);
-	if (exp) {
-		u8 state;
-
-		/* NOTE: New connections are NATted and Helped only when
-		 * committed, so we are not calling into NAT here.
-		 */
-		state = OVS_CS_F_TRACKED | OVS_CS_F_NEW | OVS_CS_F_RELATED;
-		__ovs_ct_update_key(key, state, &info->zone, exp->master);
-	} else {
-		struct nf_conn *ct;
-		int err;
+	struct nf_conn *ct;
+	int err;
 
-		err = __ovs_ct_lookup(net, key, info, skb);
-		if (err)
-			return err;
+	err = __ovs_ct_lookup(net, key, info, skb);
+	if (err)
+		return err;
 
-		ct = (struct nf_conn *)skb_nfct(skb);
-		if (ct)
-			nf_ct_deliver_cached_events(ct);
-	}
+	ct = (struct nf_conn *)skb_nfct(skb);
+	if (ct)
+		nf_ct_deliver_cached_events(ct);
 
 	return 0;
 }
@@ -1460,7 +1401,8 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
 	if (err)
 		goto err_free_ct;
 
-	__set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status);
+	if (ct_info.commit)
+		__set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status);
 	return 0;
 err_free_ct:
 	__ovs_ct_free_action(&ct_info);
-- 
GitLab


From cf3e913bf41d4aa4b89d8f1323ee8371be912261 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 18 Jul 2023 14:32:03 -0600
Subject: [PATCH 0277/1806] dt-bindings: net: dsa: Fix JSON pointer references

A JSON pointer reference to the entire document must not have a trailing
"/" and should be just a "#". The existing jsonschema package allows
these, but changes in 4.18 make allowed "$ref" URIs stricter and throw
errors on these references.

Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230718203202.1761304-1-robh@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/devicetree/bindings/net/dsa/dsa.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.yaml b/Documentation/devicetree/bindings/net/dsa/dsa.yaml
index 8d971813bab6b..ec74a660bedae 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.yaml
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.yaml
@@ -36,7 +36,7 @@ additionalProperties: true
 $defs:
   ethernet-ports:
     description: A DSA switch without any extra port properties
-    $ref: '#/'
+    $ref: '#'
 
     patternProperties:
       "^(ethernet-)?ports$":
-- 
GitLab


From 6f1c646d88c591a8139997c5591c1385cbc3d4e1 Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <eichest@gmail.com>
Date: Wed, 19 Jul 2023 08:42:54 +0200
Subject: [PATCH 0278/1806] net: phy: add registers to support 1000BASE-T1

Add registers and definitions to support 1000BASE-T1. This includes the
PCS Control and Status registers (3.2304 and 3.2305) as well as some
missing bits on the PMA/PMD extended ability register (1.18) and PMA/PMD
CTRL (1.2100) register.

Signed-off-by: Stefan Eichenberger <eichest@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/uapi/linux/mdio.h | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h
index b826598d1e94c..d03863da180e7 100644
--- a/include/uapi/linux/mdio.h
+++ b/include/uapi/linux/mdio.h
@@ -82,6 +82,8 @@
 #define MDIO_AN_10BT1_AN_CTRL	526	/* 10BASE-T1 AN control register */
 #define MDIO_AN_10BT1_AN_STAT	527	/* 10BASE-T1 AN status register */
 #define MDIO_PMA_PMD_BT1_CTRL	2100	/* BASE-T1 PMA/PMD control register */
+#define MDIO_PCS_1000BT1_CTRL	2304	/* 1000BASE-T1 PCS control register */
+#define MDIO_PCS_1000BT1_STAT	2305	/* 1000BASE-T1 PCS status register */
 
 /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */
 #define MDIO_PMA_LASI_RXCTRL	0x9000	/* RX_ALARM control */
@@ -332,6 +334,8 @@
 #define MDIO_PCS_10T1L_CTRL_RESET	0x8000	/* PCS reset */
 
 /* BASE-T1 PMA/PMD extended ability register. */
+#define MDIO_PMA_PMD_BT1_B100_ABLE	0x0001	/* 100BASE-T1 Ability */
+#define MDIO_PMA_PMD_BT1_B1000_ABLE	0x0002	/* 1000BASE-T1 Ability */
 #define MDIO_PMA_PMD_BT1_B10L_ABLE	0x0004	/* 10BASE-T1L Ability */
 
 /* BASE-T1 auto-negotiation advertisement register [15:0] */
@@ -373,7 +377,19 @@
 #define MDIO_AN_10BT1_AN_STAT_LPA_EEE_T1L	0x4000 /* 10BASE-T1L LP EEE ability advertisement */
 
 /* BASE-T1 PMA/PMD control register */
-#define MDIO_PMA_PMD_BT1_CTRL_CFG_MST	0x4000 /* MASTER-SLAVE config value */
+#define MDIO_PMA_PMD_BT1_CTRL_STRAP		0x000F /* Type selection (Strap) */
+#define MDIO_PMA_PMD_BT1_CTRL_STRAP_B1000	0x0001 /* Select 1000BASE-T1 */
+#define MDIO_PMA_PMD_BT1_CTRL_CFG_MST		0x4000 /* MASTER-SLAVE config value */
+
+/* 1000BASE-T1 PCS control register */
+#define MDIO_PCS_1000BT1_CTRL_LOW_POWER		0x0800 /* Low power mode */
+#define MDIO_PCS_1000BT1_CTRL_DISABLE_TX	0x4000 /* Global PMA transmit disable */
+#define MDIO_PCS_1000BT1_CTRL_RESET		0x8000 /* Software reset value */
+
+/* 1000BASE-T1 PCS status register */
+#define MDIO_PCS_1000BT1_STAT_LINK	0x0004 /* PCS Link is up */
+#define MDIO_PCS_1000BT1_STAT_FAULT	0x0080 /* There is a fault condition */
+
 
 /* EEE Supported/Advertisement/LP Advertisement registers.
  *
-- 
GitLab


From 25108a834e145a274024d174083089f8a83fe5bb Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <eichest@gmail.com>
Date: Wed, 19 Jul 2023 08:42:55 +0200
Subject: [PATCH 0279/1806] net: phy: c45: add support for 1000BASE-T1 forced
 setup

Add support to force 1000BASE-T1 by setting the correct control bit in
the MDIO_MMD_PMA_PMD_BT1_CTRL register.

Signed-off-by: Stefan Eichenberger <eichest@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-c45.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 93ed072233779..b73c428a15663 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -108,7 +108,7 @@ EXPORT_SYMBOL_GPL(genphy_c45_pma_baset1_setup_master_slave);
  */
 int genphy_c45_pma_setup_forced(struct phy_device *phydev)
 {
-	int ctrl1, ctrl2, ret;
+	int bt1_ctrl, ctrl1, ctrl2, ret;
 
 	/* Half duplex is not supported */
 	if (phydev->duplex != DUPLEX_FULL)
@@ -176,6 +176,15 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev)
 		ret = genphy_c45_pma_baset1_setup_master_slave(phydev);
 		if (ret < 0)
 			return ret;
+
+		bt1_ctrl = 0;
+		if (phydev->speed == SPEED_1000)
+			bt1_ctrl = MDIO_PMA_PMD_BT1_CTRL_STRAP_B1000;
+
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1_CTRL,
+				     MDIO_PMA_PMD_BT1_CTRL_STRAP, bt1_ctrl);
+		if (ret < 0)
+			return ret;
 	}
 
 	return genphy_c45_an_disable_aneg(phydev);
-- 
GitLab


From eba2e4c2faef618b6e33dfdba918c76727f891b5 Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <eichest@gmail.com>
Date: Wed, 19 Jul 2023 08:42:56 +0200
Subject: [PATCH 0280/1806] net: phy: c45: add a separate function to read
 BASE-T1 abilities

Add a separate function to read the BASE-T1 abilities. Some PHYs do not
indicate the availability of the extended BASE-T1 ability register, so
this function must be called separately.

Signed-off-by: Stefan Eichenberger <eichest@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-c45.c | 44 +++++++++++++++++++++++++++------------
 include/linux/phy.h       |  1 +
 2 files changed, 32 insertions(+), 13 deletions(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index b73c428a15663..58a6bbbe8a70c 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -881,6 +881,36 @@ int genphy_c45_an_config_eee_aneg(struct phy_device *phydev)
 	return genphy_c45_write_eee_adv(phydev, phydev->advertising_eee);
 }
 
+/**
+ * genphy_c45_pma_baset1_read_abilities - read supported baset1 link modes from PMA
+ * @phydev: target phy_device struct
+ *
+ * Read the supported link modes from the extended BASE-T1 ability register
+ */
+int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev)
+{
+	int val;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1);
+	if (val < 0)
+		return val;
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_PMD_BT1_B10L_ABLE);
+
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_STAT);
+	if (val < 0)
+		return val;
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+			 phydev->supported,
+			 val & MDIO_AN_STAT1_ABLE);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(genphy_c45_pma_baset1_read_abilities);
+
 /**
  * genphy_c45_pma_read_abilities - read supported link modes from PMA
  * @phydev: target phy_device struct
@@ -977,21 +1007,9 @@ int genphy_c45_pma_read_abilities(struct phy_device *phydev)
 		}
 
 		if (val & MDIO_PMA_EXTABLE_BT1) {
-			val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1);
+			val = genphy_c45_pma_baset1_read_abilities(phydev);
 			if (val < 0)
 				return val;
-
-			linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT,
-					 phydev->supported,
-					 val & MDIO_PMA_PMD_BT1_B10L_ABLE);
-
-			val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_STAT);
-			if (val < 0)
-				return val;
-
-			linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
-					 phydev->supported,
-					 val & MDIO_AN_STAT1_ABLE);
 		}
 	}
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 11c1e91563d47..b254848a9c99a 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1826,6 +1826,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev);
 int genphy_c45_an_disable_aneg(struct phy_device *phydev);
 int genphy_c45_read_mdix(struct phy_device *phydev);
 int genphy_c45_pma_read_abilities(struct phy_device *phydev);
+int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev);
 int genphy_c45_read_eee_abilities(struct phy_device *phydev);
 int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev);
 int genphy_c45_read_status(struct phy_device *phydev);
-- 
GitLab


From a60eb72066af272c2891c6685b9a082dde69198c Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <eichest@gmail.com>
Date: Wed, 19 Jul 2023 08:42:57 +0200
Subject: [PATCH 0281/1806] net: phy: c45: detect the BASE-T1 speed from the
 ability register

Read the ability to do 100BASE-T1 and 1000BASE-T1 from the extended
BASE-T1 ability register of the PHY.

Signed-off-by: Stefan Eichenberger <eichest@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-c45.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 58a6bbbe8a70c..8e6fd4962c486 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -899,6 +899,14 @@ int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev)
 			 phydev->supported,
 			 val & MDIO_PMA_PMD_BT1_B10L_ABLE);
 
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT1_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_PMD_BT1_B100_ABLE);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT1_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_PMD_BT1_B1000_ABLE);
+
 	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_STAT);
 	if (val < 0)
 		return val;
-- 
GitLab


From 00f11ac71708d2e5e434aa2ef9249f95b5e7e313 Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <eichest@gmail.com>
Date: Wed, 19 Jul 2023 08:42:58 +0200
Subject: [PATCH 0282/1806] net: phy: marvell-88q2xxx: add driver for the
 Marvell 88Q2110 PHY

Add a driver for the Marvell 88Q2110. This driver allows to detect the
link, switch between 100BASE-T1 and 1000BASE-T1 and switch between
master and slave mode. Autonegotiation supported by the PHY does not yet
work.

Signed-off-by: Stefan Eichenberger <eichest@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/Kconfig           |   6 +
 drivers/net/phy/Makefile          |   1 +
 drivers/net/phy/marvell-88q2xxx.c | 263 ++++++++++++++++++++++++++++++
 include/linux/marvell_phy.h       |   1 +
 4 files changed, 271 insertions(+)
 create mode 100644 drivers/net/phy/marvell-88q2xxx.c

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 78e6981650d94..87b8238587173 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -217,6 +217,12 @@ config MARVELL_10G_PHY
 	help
 	  Support for the Marvell Alaska MV88X3310 and compatible PHYs.
 
+config MARVELL_88Q2XXX_PHY
+	tristate "Marvell 88Q2XXX PHY"
+	help
+	  Support for the Marvell 88Q2XXX 100/1000BASE-T1 Automotive Ethernet
+	  PHYs.
+
 config MARVELL_88X2222_PHY
 	tristate "Marvell 88X2222 PHY"
 	help
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 2fe51ea83babe..35142780fc9da 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -66,6 +66,7 @@ obj-$(CONFIG_LSI_ET1011C_PHY)	+= et1011c.o
 obj-$(CONFIG_LXT_PHY)		+= lxt.o
 obj-$(CONFIG_MARVELL_10G_PHY)	+= marvell10g.o
 obj-$(CONFIG_MARVELL_PHY)	+= marvell.o
+obj-$(CONFIG_MARVELL_88Q2XXX_PHY)	+= marvell-88q2xxx.o
 obj-$(CONFIG_MARVELL_88X2222_PHY)	+= marvell-88x2222.o
 obj-$(CONFIG_MAXLINEAR_GPHY)	+= mxl-gpy.o
 obj-$(CONFIG_MEDIATEK_GE_PHY)	+= mediatek-ge.o
diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
new file mode 100644
index 0000000000000..1c3ff77de56b4
--- /dev/null
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -0,0 +1,263 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Marvell 88Q2XXX automotive 100BASE-T1/1000BASE-T1 PHY driver
+ */
+#include <linux/ethtool_netlink.h>
+#include <linux/marvell_phy.h>
+#include <linux/phy.h>
+
+#define MDIO_MMD_AN_MV_STAT			32769
+#define MDIO_MMD_AN_MV_STAT_ANEG		0x0100
+#define MDIO_MMD_AN_MV_STAT_LOCAL_RX		0x1000
+#define MDIO_MMD_AN_MV_STAT_REMOTE_RX		0x2000
+#define MDIO_MMD_AN_MV_STAT_LOCAL_MASTER	0x4000
+#define MDIO_MMD_AN_MV_STAT_MS_CONF_FAULT	0x8000
+
+#define MDIO_MMD_PCS_MV_100BT1_STAT1			33032
+#define MDIO_MMD_PCS_MV_100BT1_STAT1_IDLE_ERROR	0x00FF
+#define MDIO_MMD_PCS_MV_100BT1_STAT1_JABBER		0x0100
+#define MDIO_MMD_PCS_MV_100BT1_STAT1_LINK		0x0200
+#define MDIO_MMD_PCS_MV_100BT1_STAT1_LOCAL_RX		0x1000
+#define MDIO_MMD_PCS_MV_100BT1_STAT1_REMOTE_RX		0x2000
+#define MDIO_MMD_PCS_MV_100BT1_STAT1_LOCAL_MASTER	0x4000
+
+#define MDIO_MMD_PCS_MV_100BT1_STAT2		33033
+#define MDIO_MMD_PCS_MV_100BT1_STAT2_JABBER	0x0001
+#define MDIO_MMD_PCS_MV_100BT1_STAT2_POL	0x0002
+#define MDIO_MMD_PCS_MV_100BT1_STAT2_LINK	0x0004
+#define MDIO_MMD_PCS_MV_100BT1_STAT2_ANGE	0x0008
+
+static int mv88q2xxx_soft_reset(struct phy_device *phydev)
+{
+	int ret;
+	int val;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_PCS,
+			    MDIO_PCS_1000BT1_CTRL, MDIO_PCS_1000BT1_CTRL_RESET);
+	if (ret < 0)
+		return ret;
+
+	return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_PCS,
+					 MDIO_PCS_1000BT1_CTRL, val,
+					 !(val & MDIO_PCS_1000BT1_CTRL_RESET),
+					 50000, 600000, true);
+}
+
+static int mv88q2xxx_read_link_gbit(struct phy_device *phydev)
+{
+	int ret;
+	bool link = false;
+
+	/* Read vendor specific Auto-Negotiation status register to get local
+	 * and remote receiver status according to software initialization
+	 * guide.
+	 */
+	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_MMD_AN_MV_STAT);
+	if (ret < 0) {
+		return ret;
+	} else if ((ret & MDIO_MMD_AN_MV_STAT_LOCAL_RX) &&
+		   (ret & MDIO_MMD_AN_MV_STAT_REMOTE_RX)) {
+		/* The link state is latched low so that momentary link
+		 * drops can be detected. Do not double-read the status
+		 * in polling mode to detect such short link drops except
+		 * the link was already down.
+		 */
+		if (!phy_polling_mode(phydev) || !phydev->link) {
+			ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_1000BT1_STAT);
+			if (ret < 0)
+				return ret;
+			else if (ret & MDIO_PCS_1000BT1_STAT_LINK)
+				link = true;
+		}
+
+		if (!link) {
+			ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_1000BT1_STAT);
+			if (ret < 0)
+				return ret;
+			else if (ret & MDIO_PCS_1000BT1_STAT_LINK)
+				link = true;
+		}
+	}
+
+	phydev->link = link;
+
+	return 0;
+}
+
+static int mv88q2xxx_read_link_100m(struct phy_device *phydev)
+{
+	int ret;
+
+	/* The link state is latched low so that momentary link
+	 * drops can be detected. Do not double-read the status
+	 * in polling mode to detect such short link drops except
+	 * the link was already down. In case we are not polling,
+	 * we always read the realtime status.
+	 */
+	if (!phy_polling_mode(phydev) || !phydev->link) {
+		ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_MMD_PCS_MV_100BT1_STAT1);
+		if (ret < 0)
+			return ret;
+		else if (ret & MDIO_MMD_PCS_MV_100BT1_STAT1_LINK)
+			goto out;
+	}
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_MMD_PCS_MV_100BT1_STAT1);
+	if (ret < 0)
+		return ret;
+
+out:
+	/* Check if we have link and if the remote and local receiver are ok */
+	if ((ret & MDIO_MMD_PCS_MV_100BT1_STAT1_LINK) &&
+	    (ret & MDIO_MMD_PCS_MV_100BT1_STAT1_LOCAL_RX) &&
+	    (ret & MDIO_MMD_PCS_MV_100BT1_STAT1_REMOTE_RX))
+		phydev->link = true;
+	else
+		phydev->link = false;
+
+	return 0;
+}
+
+static int mv88q2xxx_read_link(struct phy_device *phydev)
+{
+	int ret;
+
+	/* The 88Q2XXX PHYs do not have the PMA/PMD status register available,
+	 * therefore we need to read the link status from the vendor specific
+	 * registers depending on the speed.
+	 */
+	if (phydev->speed == SPEED_1000)
+		ret = mv88q2xxx_read_link_gbit(phydev);
+	else
+		ret = mv88q2xxx_read_link_100m(phydev);
+
+	return ret;
+}
+
+static int mv88q2xxx_read_status(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = mv88q2xxx_read_link(phydev);
+	if (ret < 0)
+		return ret;
+
+	return genphy_c45_read_pma(phydev);
+}
+
+static int mv88q2xxx_get_features(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_c45_pma_read_abilities(phydev);
+	if (ret)
+		return ret;
+
+	/* We need to read the baset1 extended abilities manually because the
+	 * PHY does not signalize it has the extended abilities register
+	 * available.
+	 */
+	ret = genphy_c45_pma_baset1_read_abilities(phydev);
+	if (ret)
+		return ret;
+
+	/* The PHY signalizes it supports autonegotiation. Unfortunately, so
+	 * far it was not possible to get a link even when following the init
+	 * sequence provided by Marvell. Disable it for now until a proper
+	 * workaround is found or a new PHY revision is released.
+	 */
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported);
+
+	return 0;
+}
+
+static int mv88q2xxx_config_aneg(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_c45_config_aneg(phydev);
+	if (ret)
+		return ret;
+
+	return mv88q2xxx_soft_reset(phydev);
+}
+
+static int mv88q2xxx_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	/* The 88Q2XXX PHYs do have the extended ability register available, but
+	 * register MDIO_PMA_EXTABLE where they should signalize it does not
+	 * work according to specification. Therefore, we force it here.
+	 */
+	phydev->pma_extable = MDIO_PMA_EXTABLE_BT1;
+
+	/* Read the current PHY configuration */
+	ret = genphy_c45_read_pma(phydev);
+	if (ret)
+		return ret;
+
+	return mv88q2xxx_config_aneg(phydev);
+}
+
+static int mv88q2xxxx_get_sqi(struct phy_device *phydev)
+{
+	int ret;
+
+	if (phydev->speed == SPEED_100) {
+		/* Read the SQI from the vendor specific receiver status
+		 * register
+		 */
+		ret = phy_read_mmd(phydev, MDIO_MMD_PCS, 0x8230);
+		if (ret < 0)
+			return ret;
+
+		ret = ret >> 12;
+	} else {
+		/* Read from vendor specific registers, they are not documented
+		 * but can be found in the Software Initialization Guide. Only
+		 * revisions >= A0 are supported.
+		 */
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, 0xFC5D, 0x00FF, 0x00AC);
+		if (ret < 0)
+			return ret;
+
+		ret = phy_read_mmd(phydev, MDIO_MMD_PCS, 0xfc88);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret & 0x0F;
+}
+
+static int mv88q2xxxx_get_sqi_max(struct phy_device *phydev)
+{
+	return 15;
+}
+
+static struct phy_driver mv88q2xxx_driver[] = {
+	{
+		.phy_id			= MARVELL_PHY_ID_88Q2110,
+		.phy_id_mask		= MARVELL_PHY_ID_MASK,
+		.name			= "mv88q2110",
+		.get_features		= mv88q2xxx_get_features,
+		.config_aneg		= mv88q2xxx_config_aneg,
+		.config_init		= mv88q2xxx_config_init,
+		.read_status		= mv88q2xxx_read_status,
+		.soft_reset		= mv88q2xxx_soft_reset,
+		.set_loopback		= genphy_c45_loopback,
+		.get_sqi		= mv88q2xxxx_get_sqi,
+		.get_sqi_max		= mv88q2xxxx_get_sqi_max,
+	},
+};
+
+module_phy_driver(mv88q2xxx_driver);
+
+static struct mdio_device_id __maybe_unused mv88q2xxx_tbl[] = {
+	{ MARVELL_PHY_ID_88Q2110, MARVELL_PHY_ID_MASK },
+	{ /*sentinel*/ }
+};
+MODULE_DEVICE_TABLE(mdio, mv88q2xxx_tbl);
+
+MODULE_DESCRIPTION("Marvell 88Q2XXX 100/1000BASE-T1 Automotive Ethernet PHY driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index 0f06c2287b527..9b54c4f0677f8 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -25,6 +25,7 @@
 #define MARVELL_PHY_ID_88X3310		0x002b09a0
 #define MARVELL_PHY_ID_88E2110		0x002b09b0
 #define MARVELL_PHY_ID_88X2222		0x01410f10
+#define MARVELL_PHY_ID_88Q2110		0x002b0980
 
 /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */
 #define MARVELL_PHY_ID_88E1111_FINISAR	0x01ff0cc0
-- 
GitLab


From b44693495af8f309b8ddec4b30833085d1c2d0c4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 19 Jul 2023 06:47:54 +0000
Subject: [PATCH 0283/1806] tcp: add TCP_OLD_SEQUENCE drop reason

tcp_sequence() uses two conditions to decide to drop a packet,
and we currently report generic TCP_INVALID_SEQUENCE drop reason.

Duplicates are common, we need to distinguish them from
the other case.

I chose to not reuse TCP_OLD_DATA, and instead added
TCP_OLD_SEQUENCE drop reason.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230719064754.2794106-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/dropreason-core.h |  3 +++
 net/ipv4/tcp_input.c          | 16 +++++++++++-----
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index a2b953b57689b..f291a3b0f9e51 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -30,6 +30,7 @@
 	FN(TCP_OVERWINDOW)		\
 	FN(TCP_OFOMERGE)		\
 	FN(TCP_RFC7323_PAWS)		\
+	FN(TCP_OLD_SEQUENCE)		\
 	FN(TCP_INVALID_SEQUENCE)	\
 	FN(TCP_RESET)			\
 	FN(TCP_INVALID_SYN)		\
@@ -188,6 +189,8 @@ enum skb_drop_reason {
 	 * LINUX_MIB_PAWSESTABREJECTED
 	 */
 	SKB_DROP_REASON_TCP_RFC7323_PAWS,
+	/** @SKB_DROP_REASON_TCP_OLD_SEQUENCE: Old SEQ field (duplicate packet) */
+	SKB_DROP_REASON_TCP_OLD_SEQUENCE,
 	/** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */
 	SKB_DROP_REASON_TCP_INVALID_SEQUENCE,
 	/** @SKB_DROP_REASON_TCP_RESET: Invalid RST packet */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e2affdd147daa..670c3dab24f2b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4312,10 +4312,16 @@ static inline bool tcp_paws_discard(const struct sock *sk,
  * (borrowed from freebsd)
  */
 
-static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq)
+static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp,
+					 u32 seq, u32 end_seq)
 {
-	return	!before(end_seq, tp->rcv_wup) &&
-		!after(seq, tp->rcv_nxt + tcp_receive_window(tp));
+	if (before(end_seq, tp->rcv_wup))
+		return SKB_DROP_REASON_TCP_OLD_SEQUENCE;
+
+	if (after(seq, tp->rcv_nxt + tcp_receive_window(tp)))
+		return SKB_DROP_REASON_TCP_INVALID_SEQUENCE;
+
+	return SKB_NOT_DROPPED_YET;
 }
 
 /* When we get a reset we do this. */
@@ -5738,7 +5744,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	}
 
 	/* Step 1: check sequence number */
-	if (!tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq)) {
+	reason = tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
+	if (reason) {
 		/* RFC793, page 37: "In all states except SYN-SENT, all reset
 		 * (RST) segments are validated by checking their SEQ-fields."
 		 * And page 69: "If an incoming segment is not acceptable,
@@ -5755,7 +5762,6 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		} else if (tcp_reset_check(sk, skb)) {
 			goto reset;
 		}
-		SKB_DR_SET(reason, TCP_INVALID_SEQUENCE);
 		goto discard;
 	}
 
-- 
GitLab


From fea2993aecd74d5d11ede1ebbd60e478ebfed996 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Jul 2023 18:04:38 -0700
Subject: [PATCH 0284/1806] eth: bnxt: move and rename reset helpers

Move the reset helpers, subsequent patches will need some
of them on the Tx path.

While at it rename bnxt_sched_reset(), on more recent chips
it schedules a queue reset, instead of a fuller reset.

Link: https://lore.kernel.org/r/20230720010440.1967136-2-kuba@kernel.org
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 72 +++++++++++------------
 1 file changed, 36 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d84ded8db93d8..417554a4c8372 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -293,6 +293,38 @@ static void bnxt_db_cq(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 		BNXT_DB_CQ(db, idx);
 }
 
+static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay)
+{
+	if (!(test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)))
+		return;
+
+	if (BNXT_PF(bp))
+		queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay);
+	else
+		schedule_delayed_work(&bp->fw_reset_task, delay);
+}
+
+static void bnxt_queue_sp_work(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		queue_work(bnxt_pf_wq, &bp->sp_task);
+	else
+		schedule_work(&bp->sp_task);
+}
+
+static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
+{
+	if (!rxr->bnapi->in_reset) {
+		rxr->bnapi->in_reset = true;
+		if (bp->flags & BNXT_FLAG_CHIP_P5)
+			set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
+		else
+			set_bit(BNXT_RST_RING_SP_EVENT, &bp->sp_event);
+		bnxt_queue_sp_work(bp);
+	}
+	rxr->rx_next_cons = 0xffff;
+}
+
 const u16 bnxt_lhint_arr[] = {
 	TX_BD_FLAGS_LHINT_512_AND_SMALLER,
 	TX_BD_FLAGS_LHINT_512_TO_1023,
@@ -1234,38 +1266,6 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	return 0;
 }
 
-static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay)
-{
-	if (!(test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)))
-		return;
-
-	if (BNXT_PF(bp))
-		queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay);
-	else
-		schedule_delayed_work(&bp->fw_reset_task, delay);
-}
-
-static void bnxt_queue_sp_work(struct bnxt *bp)
-{
-	if (BNXT_PF(bp))
-		queue_work(bnxt_pf_wq, &bp->sp_task);
-	else
-		schedule_work(&bp->sp_task);
-}
-
-static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
-{
-	if (!rxr->bnapi->in_reset) {
-		rxr->bnapi->in_reset = true;
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
-			set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
-		else
-			set_bit(BNXT_RST_RING_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
-	rxr->rx_next_cons = 0xffff;
-}
-
 static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id)
 {
 	struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map;
@@ -1320,7 +1320,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		netdev_warn(bp->dev, "TPA cons %x, expected cons %x, error code %x\n",
 			    cons, rxr->rx_next_cons,
 			    TPA_START_ERROR_CODE(tpa_start1));
-		bnxt_sched_reset(bp, rxr);
+		bnxt_sched_reset_rxr(bp, rxr);
 		return;
 	}
 	/* Store cfa_code in tpa_info to use in tpa_end
@@ -1844,7 +1844,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		if (rxr->rx_next_cons != 0xffff)
 			netdev_warn(bp->dev, "RX cons %x != expected cons %x\n",
 				    cons, rxr->rx_next_cons);
-		bnxt_sched_reset(bp, rxr);
+		bnxt_sched_reset_rxr(bp, rxr);
 		if (rc1)
 			return rc1;
 		goto next_rx_no_prod_no_len;
@@ -1882,7 +1882,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			    !(bp->fw_cap & BNXT_FW_CAP_RING_MONITOR)) {
 				netdev_warn_once(bp->dev, "RX buffer error %x\n",
 						 rx_err);
-				bnxt_sched_reset(bp, rxr);
+				bnxt_sched_reset_rxr(bp, rxr);
 			}
 		}
 		goto next_rx_no_len;
@@ -2329,7 +2329,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 			goto async_event_process_exit;
 		}
 		rxr = bp->bnapi[grp_idx]->rx_ring;
-		bnxt_sched_reset(bp, rxr);
+		bnxt_sched_reset_rxr(bp, rxr);
 		goto async_event_process_exit;
 	}
 	case ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST: {
-- 
GitLab


From 9b1a00fda61ee9874e11c24c6be7ddc36e8a4598 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Jul 2023 18:04:39 -0700
Subject: [PATCH 0285/1806] eth: bnxt: take the bit to set as argument of
 bnxt_queue_sp_work()

Most callers of bnxt_queue_sp_work() set a bit to indicate what work
to perform right before calling it. Pass it to the function instead.

Link: https://lore.kernel.org/r/20230720010440.1967136-3-kuba@kernel.org
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 61 ++++++++++-------------
 1 file changed, 26 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 417554a4c8372..7b545d2a98b46 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -304,7 +304,7 @@ static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay)
 		schedule_delayed_work(&bp->fw_reset_task, delay);
 }
 
-static void bnxt_queue_sp_work(struct bnxt *bp)
+static void __bnxt_queue_sp_work(struct bnxt *bp)
 {
 	if (BNXT_PF(bp))
 		queue_work(bnxt_pf_wq, &bp->sp_task);
@@ -312,6 +312,12 @@ static void bnxt_queue_sp_work(struct bnxt *bp)
 		schedule_work(&bp->sp_task);
 }
 
+static void bnxt_queue_sp_work(struct bnxt *bp, unsigned int event)
+{
+	set_bit(event, &bp->sp_event);
+	__bnxt_queue_sp_work(bp);
+}
+
 static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
 	if (!rxr->bnapi->in_reset) {
@@ -320,7 +326,7 @@ static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 			set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
 		else
 			set_bit(BNXT_RST_RING_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
+		__bnxt_queue_sp_work(bp);
 	}
 	rxr->rx_next_cons = 0xffff;
 }
@@ -2384,7 +2390,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 	default:
 		goto async_event_process_exit;
 	}
-	bnxt_queue_sp_work(bp);
+	__bnxt_queue_sp_work(bp);
 async_event_process_exit:
 	return 0;
 }
@@ -2413,8 +2419,7 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp)
 		}
 
 		set_bit(vf_id - bp->pf.first_vf_id, bp->pf.vf_event_bmap);
-		set_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
+		bnxt_queue_sp_work(bp, BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT);
 		break;
 
 	case CMPL_BASE_TYPE_HWRM_ASYNC_EVENT:
@@ -11031,8 +11036,7 @@ static void bnxt_set_rx_mode(struct net_device *dev)
 	if (mask != vnic->rx_mask || uc_update || mc_update) {
 		vnic->rx_mask = mask;
 
-		set_bit(BNXT_RX_MASK_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
+		bnxt_queue_sp_work(bp, BNXT_RX_MASK_SP_EVENT);
 	}
 }
 
@@ -11597,8 +11601,7 @@ static void bnxt_tx_timeout(struct net_device *dev, unsigned int txqueue)
 	struct bnxt *bp = netdev_priv(dev);
 
 	netdev_err(bp->dev,  "TX timeout detected, starting reset task!\n");
-	set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
-	bnxt_queue_sp_work(bp);
+	bnxt_queue_sp_work(bp, BNXT_RESET_TASK_SP_EVENT);
 }
 
 static void bnxt_fw_health_check(struct bnxt *bp)
@@ -11635,8 +11638,7 @@ static void bnxt_fw_health_check(struct bnxt *bp)
 	return;
 
 fw_reset:
-	set_bit(BNXT_FW_EXCEPTION_SP_EVENT, &bp->sp_event);
-	bnxt_queue_sp_work(bp);
+	bnxt_queue_sp_work(bp, BNXT_FW_EXCEPTION_SP_EVENT);
 }
 
 static void bnxt_timer(struct timer_list *t)
@@ -11653,21 +11655,15 @@ static void bnxt_timer(struct timer_list *t)
 	if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)
 		bnxt_fw_health_check(bp);
 
-	if (BNXT_LINK_IS_UP(bp) && bp->stats_coal_ticks) {
-		set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
+	if (BNXT_LINK_IS_UP(bp) && bp->stats_coal_ticks)
+		bnxt_queue_sp_work(bp, BNXT_PERIODIC_STATS_SP_EVENT);
 
-	if (bnxt_tc_flower_enabled(bp)) {
-		set_bit(BNXT_FLOW_STATS_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
+	if (bnxt_tc_flower_enabled(bp))
+		bnxt_queue_sp_work(bp, BNXT_FLOW_STATS_SP_EVENT);
 
 #ifdef CONFIG_RFS_ACCEL
-	if ((bp->flags & BNXT_FLAG_RFS) && bp->ntp_fltr_count) {
-		set_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
+	if ((bp->flags & BNXT_FLAG_RFS) && bp->ntp_fltr_count)
+		bnxt_queue_sp_work(bp, BNXT_RX_NTP_FLTR_SP_EVENT);
 #endif /*CONFIG_RFS_ACCEL*/
 
 	if (bp->link_info.phy_retry) {
@@ -11675,21 +11671,17 @@ static void bnxt_timer(struct timer_list *t)
 			bp->link_info.phy_retry = false;
 			netdev_warn(bp->dev, "failed to update phy settings after maximum retries.\n");
 		} else {
-			set_bit(BNXT_UPDATE_PHY_SP_EVENT, &bp->sp_event);
-			bnxt_queue_sp_work(bp);
+			bnxt_queue_sp_work(bp, BNXT_UPDATE_PHY_SP_EVENT);
 		}
 	}
 
-	if (test_bit(BNXT_STATE_L2_FILTER_RETRY, &bp->state)) {
-		set_bit(BNXT_RX_MASK_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
+	if (test_bit(BNXT_STATE_L2_FILTER_RETRY, &bp->state))
+		bnxt_queue_sp_work(bp, BNXT_RX_MASK_SP_EVENT);
 
 	if ((bp->flags & BNXT_FLAG_CHIP_P5) && !bp->chip_rev &&
-	    netif_carrier_ok(dev)) {
-		set_bit(BNXT_RING_COAL_NOW_SP_EVENT, &bp->sp_event);
-		bnxt_queue_sp_work(bp);
-	}
+	    netif_carrier_ok(dev))
+		bnxt_queue_sp_work(bp, BNXT_RING_COAL_NOW_SP_EVENT);
+
 bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
@@ -12968,8 +12960,7 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	bp->ntp_fltr_count++;
 	spin_unlock_bh(&bp->ntp_fltr_lock);
 
-	set_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event);
-	bnxt_queue_sp_work(bp);
+	bnxt_queue_sp_work(bp, BNXT_RX_NTP_FLTR_SP_EVENT);
 
 	return new_fltr->sw_id;
 
-- 
GitLab


From 2b56b3d9924160d84c37d085628525666e3b1cea Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Jul 2023 18:04:40 -0700
Subject: [PATCH 0286/1806] eth: bnxt: handle invalid Tx completions more
 gracefully

Invalid Tx completions should never happen (tm) but when they do
they crash the host, because driver blindly trusts that there is
a valid skb pointer on the ring.

The completions I've seen appear to be some form of FW / HW
miscalculation or staleness, they have typical (small) values
(<100), but they are most often higher than number of queued
descriptors. They usually happen after boot.

Instead of crashing, print a warning and schedule a reset.

Link: https://lore.kernel.org/r/20230720010440.1967136-4-kuba@kernel.org
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 25 ++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  3 +++
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c |  4 +++
 3 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7b545d2a98b46..a3bbd13c070fc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -331,6 +331,22 @@ static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 	rxr->rx_next_cons = 0xffff;
 }
 
+void bnxt_sched_reset_txr(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			  int idx)
+{
+	struct bnxt_napi *bnapi = txr->bnapi;
+
+	if (bnapi->tx_fault)
+		return;
+
+	netdev_err(bp->dev, "Invalid Tx completion (ring:%d tx_pkts:%d cons:%u prod:%u i:%d)",
+		   txr->txq_index, bnapi->tx_pkts,
+		   txr->tx_cons, txr->tx_prod, idx);
+	WARN_ON_ONCE(1);
+	bnapi->tx_fault = 1;
+	bnxt_queue_sp_work(bp, BNXT_RESET_TASK_SP_EVENT);
+}
+
 const u16 bnxt_lhint_arr[] = {
 	TX_BD_FLAGS_LHINT_512_AND_SMALLER,
 	TX_BD_FLAGS_LHINT_512_TO_1023,
@@ -690,6 +706,11 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 		skb = tx_buf->skb;
 		tx_buf->skb = NULL;
 
+		if (unlikely(!skb)) {
+			bnxt_sched_reset_txr(bp, txr, i);
+			return;
+		}
+
 		tx_bytes += skb->len;
 
 		if (tx_buf->is_push) {
@@ -2576,7 +2597,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi)
 {
-	if (bnapi->tx_pkts) {
+	if (bnapi->tx_pkts && !bnapi->tx_fault) {
 		bnapi->tx_int(bp, bnapi, bnapi->tx_pkts);
 		bnapi->tx_pkts = 0;
 	}
@@ -9429,6 +9450,8 @@ static void bnxt_enable_napi(struct bnxt *bp)
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr;
 
+		bnapi->tx_fault = 0;
+
 		cpr = &bnapi->cp_ring;
 		if (bnapi->in_reset)
 			cpr->sw_stats.rx.rx_resets++;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 080e73496066b..9d16757e27fe4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1008,6 +1008,7 @@ struct bnxt_napi {
 					  int);
 	int			tx_pkts;
 	u8			events;
+	u8			tx_fault:1;
 
 	u32			flags;
 #define BNXT_NAPI_FLAG_XDP	0x1
@@ -2329,6 +2330,8 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init);
 void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
+void bnxt_sched_reset_txr(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			  int idx);
 void bnxt_report_link(struct bnxt *bp);
 int bnxt_update_link(struct bnxt *bp, bool chng_link_state);
 int bnxt_hwrm_set_pause(struct bnxt *);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 4efa5fe6972b2..5b6fbdc4dc406 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -149,6 +149,7 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 			tx_buf->action = 0;
 			tx_buf->xdpf = NULL;
 		} else if (tx_buf->action == XDP_TX) {
+			tx_buf->action = 0;
 			rx_doorbell_needed = true;
 			last_tx_cons = tx_cons;
 
@@ -158,6 +159,9 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 				tx_buf = &txr->tx_buf_ring[tx_cons];
 				page_pool_recycle_direct(rxr->page_pool, tx_buf->page);
 			}
+		} else {
+			bnxt_sched_reset_txr(bp, txr, i);
+			return;
 		}
 		tx_cons = NEXT_TX(tx_cons);
 	}
-- 
GitLab


From eedd47a6ec9f683f0b8d931aacca81985be55eec Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 19 Jul 2023 13:57:11 +0000
Subject: [PATCH 0287/1806] nexthop: Factor out hash threshold fdb nexthop
 selection

The loop in nexthop_select_path_hthr() includes code to check for neighbor
validity. Since this does not apply to fdb nexthops, simplify the loop by
moving the fdb nexthop selection to its own function.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230719-nh_select-v2-1-04383e89f868@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/nexthop.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index f95142e56da05..27089dea0ed04 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1152,11 +1152,31 @@ static bool ipv4_good_nh(const struct fib_nh *nh)
 	return !!(state & NUD_VALID);
 }
 
+static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash)
+{
+	int i;
+
+	for (i = 0; i < nhg->num_nh; i++) {
+		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+
+		if (hash > atomic_read(&nhge->hthr.upper_bound))
+			continue;
+
+		return nhge->nh;
+	}
+
+	WARN_ON_ONCE(1);
+	return NULL;
+}
+
 static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash)
 {
 	struct nexthop *rc = NULL;
 	int i;
 
+	if (nhg->fdb_nh)
+		return nexthop_select_path_fdb(nhg, hash);
+
 	for (i = 0; i < nhg->num_nh; ++i) {
 		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
 		struct nh_info *nhi;
@@ -1165,8 +1185,6 @@ static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash)
 			continue;
 
 		nhi = rcu_dereference(nhge->nh->nh_info);
-		if (nhi->fdb_nh)
-			return nhge->nh;
 
 		/* nexthops always check if it is good and does
 		 * not rely on a sysctl for this behavior
-- 
GitLab


From 4bb5239b43348f4a1cd73f44be3dc57ac653ae9c Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 19 Jul 2023 13:57:16 +0000
Subject: [PATCH 0288/1806] nexthop: Factor out neighbor validity check

For legacy nexthops, there is fib_good_nh() to check the neighbor validity.
In order to make the nexthop object code more similar to the legacy nexthop
code, factor out the nexthop object neighbor validity check into its own
function.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230719-nh_select-v2-2-04383e89f868@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/nexthop.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 27089dea0ed04..c12acbf39659b 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1152,6 +1152,20 @@ static bool ipv4_good_nh(const struct fib_nh *nh)
 	return !!(state & NUD_VALID);
 }
 
+static bool nexthop_is_good_nh(const struct nexthop *nh)
+{
+	struct nh_info *nhi = rcu_dereference(nh->nh_info);
+
+	switch (nhi->family) {
+	case AF_INET:
+		return ipv4_good_nh(&nhi->fib_nh);
+	case AF_INET6:
+		return ipv6_good_nh(&nhi->fib6_nh);
+	}
+
+	return false;
+}
+
 static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash)
 {
 	int i;
@@ -1179,26 +1193,15 @@ static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash)
 
 	for (i = 0; i < nhg->num_nh; ++i) {
 		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
-		struct nh_info *nhi;
 
 		if (hash > atomic_read(&nhge->hthr.upper_bound))
 			continue;
 
-		nhi = rcu_dereference(nhge->nh->nh_info);
-
 		/* nexthops always check if it is good and does
 		 * not rely on a sysctl for this behavior
 		 */
-		switch (nhi->family) {
-		case AF_INET:
-			if (ipv4_good_nh(&nhi->fib_nh))
-				return nhge->nh;
-			break;
-		case AF_INET6:
-			if (ipv6_good_nh(&nhi->fib6_nh))
-				return nhge->nh;
-			break;
-		}
+		if (nexthop_is_good_nh(nhge->nh))
+			return nhge->nh;
 
 		if (!rc)
 			rc = nhge->nh;
-- 
GitLab


From 75f5f04c7bd2163044f80d5f7bea6b79edc288fa Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 19 Jul 2023 13:57:22 +0000
Subject: [PATCH 0289/1806] nexthop: Do not return invalid nexthop object
 during multipath selection

With legacy nexthops, when net.ipv4.fib_multipath_use_neigh is set,
fib_select_multipath() will never set res->nhc to a nexthop that is not
good (as per fib_good_nh()). OTOH, with nexthop objects,
nexthop_select_path_hthr() may return a nexthop that failed the
nexthop_is_good_nh() test even if there was one that passed. Refactor
nexthop_select_path_hthr() to follow a selection logic more similar to
fib_select_multipath().

The issue can be demonstrated with the following sequence of commands. The
first block shows that things work as expected with legacy nexthops. The
last sequence of `ip rou get` in the second block shows the problem case -
some routes still use the .2 nexthop.

sysctl net.ipv4.fib_multipath_use_neigh=1
ip link add dummy1 up type dummy
ip rou add 198.51.100.0/24 nexthop via 192.0.2.1 dev dummy1 onlink nexthop via 192.0.2.2 dev dummy1 onlink
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip neigh add 192.0.2.1 dev dummy1 nud failed
echo ".1 failed:"  # results should not use .1
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip neigh del 192.0.2.1 dev dummy1
ip neigh add 192.0.2.2 dev dummy1 nud failed
echo ".2 failed:"  # results should not use .2
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip link del dummy1

ip link add dummy1 up type dummy
ip nexthop add id 1 via 192.0.2.1 dev dummy1 onlink
ip nexthop add id 2 via 192.0.2.2 dev dummy1 onlink
ip nexthop add id 1001 group 1/2
ip rou add 198.51.100.0/24 nhid 1001
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip neigh add 192.0.2.1 dev dummy1 nud failed
echo ".1 failed:"  # results should not use .1
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip neigh del 192.0.2.1 dev dummy1
ip neigh add 192.0.2.2 dev dummy1 nud failed
echo ".2 failed:"  # results should not use .2
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip link del dummy1

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230719-nh_select-v2-3-04383e89f868@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/nexthop.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index c12acbf39659b..93f14d39fef68 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1194,20 +1194,22 @@ static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash)
 	for (i = 0; i < nhg->num_nh; ++i) {
 		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
 
-		if (hash > atomic_read(&nhge->hthr.upper_bound))
-			continue;
-
 		/* nexthops always check if it is good and does
 		 * not rely on a sysctl for this behavior
 		 */
-		if (nexthop_is_good_nh(nhge->nh))
-			return nhge->nh;
+		if (!nexthop_is_good_nh(nhge->nh))
+			continue;
 
 		if (!rc)
 			rc = nhge->nh;
+
+		if (hash > atomic_read(&nhge->hthr.upper_bound))
+			continue;
+
+		return nhge->nh;
 	}
 
-	return rc;
+	return rc ? : nhg->nh_entries[0].nh;
 }
 
 static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash)
-- 
GitLab


From c7e95bbda82207ae81095dfa8d09ef1d6519a63d Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 19 Jul 2023 13:57:27 +0000
Subject: [PATCH 0290/1806] selftests: net: Add test cases for nexthop groups
 with invalid neighbors

Add test cases for hash threshold (multipath) nexthop groups with invalid
neighbors. Check that a nexthop with invalid neighbor is not selected when
there is another nexthop with a valid neighbor. Check that there is no
crash when there is no nexthop with a valid neighbor.

The first test fails before the previous commit in this series.

Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230719-nh_select-v2-4-04383e89f868@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_nexthops.sh | 129 ++++++++++++++++++++
 1 file changed, 129 insertions(+)

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 0f5e88c8f4ffe..54ec2b7b7b8c8 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -29,6 +29,7 @@ IPV4_TESTS="
 	ipv4_large_res_grp
 	ipv4_compat_mode
 	ipv4_fdb_grp_fcnal
+	ipv4_mpath_select
 	ipv4_torture
 	ipv4_res_torture
 "
@@ -42,6 +43,7 @@ IPV6_TESTS="
 	ipv6_large_res_grp
 	ipv6_compat_mode
 	ipv6_fdb_grp_fcnal
+	ipv6_mpath_select
 	ipv6_torture
 	ipv6_res_torture
 "
@@ -370,6 +372,27 @@ check_large_res_grp()
 	log_test $? 0 "Dump large (x$buckets) nexthop buckets"
 }
 
+get_route_dev()
+{
+	local pfx="$1"
+	local out
+
+	if out=$($IP -j route get "$pfx" | jq -re ".[0].dev"); then
+		echo "$out"
+	fi
+}
+
+check_route_dev()
+{
+	local pfx="$1"
+	local expected="$2"
+	local out
+
+	out=$(get_route_dev "$pfx")
+
+	check_output "$out" "$expected"
+}
+
 start_ip_monitor()
 {
 	local mtype=$1
@@ -575,6 +598,112 @@ ipv4_fdb_grp_fcnal()
 	$IP link del dev vx10
 }
 
+ipv4_mpath_select()
+{
+	local rc dev match h addr
+
+	echo
+	echo "IPv4 multipath selection"
+	echo "------------------------"
+	if [ ! -x "$(command -v jq)" ]; then
+		echo "SKIP: Could not run test; need jq tool"
+		return $ksft_skip
+	fi
+
+	# Use status of existing neighbor entry when determining nexthop for
+	# multipath routes.
+	local -A gws
+	gws=([veth1]=172.16.1.2 [veth3]=172.16.2.2)
+	local -A other_dev
+	other_dev=([veth1]=veth3 [veth3]=veth1)
+
+	run_cmd "$IP nexthop add id 1 via ${gws["veth1"]} dev veth1"
+	run_cmd "$IP nexthop add id 2 via ${gws["veth3"]} dev veth3"
+	run_cmd "$IP nexthop add id 1001 group 1/2"
+	run_cmd "$IP ro add 172.16.101.0/24 nhid 1001"
+	rc=0
+	for dev in veth1 veth3; do
+		match=0
+		for h in {1..254}; do
+			addr="172.16.101.$h"
+			if [ "$(get_route_dev "$addr")" = "$dev" ]; then
+				match=1
+				break
+			fi
+		done
+		if (( match == 0 )); then
+			echo "SKIP: Did not find a route using device $dev"
+			return $ksft_skip
+		fi
+		run_cmd "$IP neigh add ${gws[$dev]} dev $dev nud failed"
+		if ! check_route_dev "$addr" "${other_dev[$dev]}"; then
+			rc=1
+			break
+		fi
+		run_cmd "$IP neigh del ${gws[$dev]} dev $dev"
+	done
+	log_test $rc 0 "Use valid neighbor during multipath selection"
+
+	run_cmd "$IP neigh add 172.16.1.2 dev veth1 nud incomplete"
+	run_cmd "$IP neigh add 172.16.2.2 dev veth3 nud incomplete"
+	run_cmd "$IP route get 172.16.101.1"
+	# if we did not crash, success
+	log_test $rc 0 "Multipath selection with no valid neighbor"
+}
+
+ipv6_mpath_select()
+{
+	local rc dev match h addr
+
+	echo
+	echo "IPv6 multipath selection"
+	echo "------------------------"
+	if [ ! -x "$(command -v jq)" ]; then
+		echo "SKIP: Could not run test; need jq tool"
+		return $ksft_skip
+	fi
+
+	# Use status of existing neighbor entry when determining nexthop for
+	# multipath routes.
+	local -A gws
+	gws=([veth1]=2001:db8:91::2 [veth3]=2001:db8:92::2)
+	local -A other_dev
+	other_dev=([veth1]=veth3 [veth3]=veth1)
+
+	run_cmd "$IP nexthop add id 1 via ${gws["veth1"]} dev veth1"
+	run_cmd "$IP nexthop add id 2 via ${gws["veth3"]} dev veth3"
+	run_cmd "$IP nexthop add id 1001 group 1/2"
+	run_cmd "$IP ro add 2001:db8:101::/64 nhid 1001"
+	rc=0
+	for dev in veth1 veth3; do
+		match=0
+		for h in {1..65535}; do
+			addr=$(printf "2001:db8:101::%x" $h)
+			if [ "$(get_route_dev "$addr")" = "$dev" ]; then
+				match=1
+				break
+			fi
+		done
+		if (( match == 0 )); then
+			echo "SKIP: Did not find a route using device $dev"
+			return $ksft_skip
+		fi
+		run_cmd "$IP neigh add ${gws[$dev]} dev $dev nud failed"
+		if ! check_route_dev "$addr" "${other_dev[$dev]}"; then
+			rc=1
+			break
+		fi
+		run_cmd "$IP neigh del ${gws[$dev]} dev $dev"
+	done
+	log_test $rc 0 "Use valid neighbor during multipath selection"
+
+	run_cmd "$IP neigh add 2001:db8:91::2 dev veth1 nud incomplete"
+	run_cmd "$IP neigh add 2001:db8:92::2 dev veth3 nud incomplete"
+	run_cmd "$IP route get 2001:db8:101::1"
+	# if we did not crash, success
+	log_test $rc 0 "Multipath selection with no valid neighbor"
+}
+
 ################################################################################
 # basic operations (add, delete, replace) on nexthops and nexthop groups
 #
-- 
GitLab


From a5dc694e16d31fbf85596de1239ebf4ca8426042 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 19 Jul 2023 12:29:49 +0200
Subject: [PATCH 0291/1806] net: ethernet: mtk_ppe: add
 MTK_FOE_ENTRY_V{1,2}_SIZE macros

Introduce MTK_FOE_ENTRY_V{1,2}_SIZE macros in order to make more
explicit foe_entry size for different chipset revisions.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 10 +++++-----
 drivers/net/ethernet/mediatek/mtk_ppe.h     |  3 +++
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 2d15342c260ae..18a8aca7944db 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -4804,7 +4804,7 @@ static const struct mtk_soc_data mt7621_data = {
 	.required_pctl = false,
 	.offload_version = 1,
 	.hash_offset = 2,
-	.foe_entry_size = sizeof(struct mtk_foe_entry) - 16,
+	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma),
 		.rxd_size = sizeof(struct mtk_rx_dma),
@@ -4825,7 +4825,7 @@ static const struct mtk_soc_data mt7622_data = {
 	.offload_version = 2,
 	.hash_offset = 2,
 	.has_accounting = true,
-	.foe_entry_size = sizeof(struct mtk_foe_entry) - 16,
+	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma),
 		.rxd_size = sizeof(struct mtk_rx_dma),
@@ -4844,7 +4844,7 @@ static const struct mtk_soc_data mt7623_data = {
 	.required_pctl = true,
 	.offload_version = 1,
 	.hash_offset = 2,
-	.foe_entry_size = sizeof(struct mtk_foe_entry) - 16,
+	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma),
 		.rxd_size = sizeof(struct mtk_rx_dma),
@@ -4882,8 +4882,8 @@ static const struct mtk_soc_data mt7981_data = {
 	.required_pctl = false,
 	.offload_version = 2,
 	.hash_offset = 4,
-	.foe_entry_size = sizeof(struct mtk_foe_entry),
 	.has_accounting = true,
+	.foe_entry_size = MTK_FOE_ENTRY_V2_SIZE,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma_v2),
 		.rxd_size = sizeof(struct mtk_rx_dma_v2),
@@ -4903,8 +4903,8 @@ static const struct mtk_soc_data mt7986_data = {
 	.required_pctl = false,
 	.offload_version = 2,
 	.hash_offset = 4,
-	.foe_entry_size = sizeof(struct mtk_foe_entry),
 	.has_accounting = true,
+	.foe_entry_size = MTK_FOE_ENTRY_V2_SIZE,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma_v2),
 		.rxd_size = sizeof(struct mtk_rx_dma_v2),
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h
index e51de31a52ec6..fb6bf58172d98 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.h
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.h
@@ -216,6 +216,9 @@ struct mtk_foe_ipv6_6rd {
 	struct mtk_foe_mac_info l2;
 };
 
+#define MTK_FOE_ENTRY_V1_SIZE	80
+#define MTK_FOE_ENTRY_V2_SIZE	96
+
 struct mtk_foe_entry {
 	u32 ib1;
 
-- 
GitLab


From 989280d6ea70b2d91b8b0e20ac11a6529a37ac08 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:16 +0200
Subject: [PATCH 0292/1806] net: bridge: br_switchdev: Tolerate -EOPNOTSUPP
 when replaying MDB

There are two kinds of MDB entries to be replayed: port MDB entries, and
host MDB entries. They are both replayed by br_switchdev_mdb_replay(). If
the driver supports one kind, but lacks the other, the first -EOPNOTSUPP
returned terminates the whole replay, including any further still-supported
objects in the list.

For this to cause issues, there must be MDB entries for both the host and
the port being replayed. In that case, if the driver bails out from
handling the host entry, the port entries are never replayed. However, the
replay is currently only done when a switchdev port joins a bridge. There
would be no port memberships at that point. Thus despite being erroneous,
the code does not cause observable bugs.

This is not an issue with other object kinds either, because there, each
function replays one object kind. If a driver does not support that kind,
it makes sense to bail out early. -EOPNOTSUPP is then ignored in
nbp_switchdev_sync_objs().

For MDB, suppress the -EOPNOTSUPP error code in br_switchdev_mdb_replay()
already, so that the whole list gets replayed.

The reason we need this patch is that a future patch will introduce a
replay that should be used when a front-panel port netdevice is enslaved to
a bridge lower, in particular a LAG. The LAG netdevice can already have
both host and port MDB entries. The port entries need to be replayed so
that they are offloaded on the port that joins the LAG.

Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Ivan Vecera <ivecera@redhat.com>
Cc: Roopa Prabhu <roopa@nvidia.com>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Cc: bridge@lists.linux-foundation.org
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_switchdev.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index ba95c4d74a601..e92e0338afee3 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -727,6 +727,8 @@ br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev,
 		err = br_switchdev_mdb_replay_one(nb, dev,
 						  SWITCHDEV_OBJ_PORT_MDB(obj),
 						  action, ctx, extack);
+		if (err == -EOPNOTSUPP)
+			err = 0;
 		if (err)
 			goto out_free_mdb;
 	}
@@ -759,8 +761,10 @@ static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx,
 
 	err = br_switchdev_mdb_replay(br_dev, dev, ctx, true, blocking_nb,
 				      extack);
-	if (err && err != -EOPNOTSUPP)
+	if (err) {
+		/* -EOPNOTSUPP not propagated from MDB replay. */
 		return err;
+	}
 
 	err = br_switchdev_fdb_replay(br_dev, ctx, true, atomic_nb);
 	if (err && err != -EOPNOTSUPP)
-- 
GitLab


From f2e2857b352277a451e2f91409e461fa7ebf2d15 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:17 +0200
Subject: [PATCH 0293/1806] net: switchdev: Add a helper to replay objects on a
 bridge port

When a front panel joins a bridge via another netdevice (typically a LAG),
the driver needs to learn about the objects configured on the bridge port.
When the bridge port is offloaded by the driver for the first time, this
can be achieved by passing a notifier to switchdev_bridge_port_offload().
The notifier is then invoked for the individual objects (such as VLANs)
configured on the bridge, and can look for the interesting ones.

Calling switchdev_bridge_port_offload() when the second port joins the
bridge lower is unnecessary, but the replay is still needed. To that end,
add a new function, switchdev_bridge_port_replay(), which does only the
replay part of the _offload() function in exactly the same way as that
function.

Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Ivan Vecera <ivecera@redhat.com>
Cc: Roopa Prabhu <roopa@nvidia.com>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Cc: bridge@lists.linux-foundation.org
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h   |  6 ++++++
 net/bridge/br.c           |  8 ++++++++
 net/bridge/br_private.h   | 16 ++++++++++++++++
 net/bridge/br_switchdev.c |  9 +++++++++
 net/switchdev/switchdev.c | 25 +++++++++++++++++++++++++
 5 files changed, 64 insertions(+)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index ca0312b78294e..4d324e2a2eef0 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -231,6 +231,7 @@ enum switchdev_notifier_type {
 
 	SWITCHDEV_BRPORT_OFFLOADED,
 	SWITCHDEV_BRPORT_UNOFFLOADED,
+	SWITCHDEV_BRPORT_REPLAY,
 };
 
 struct switchdev_notifier_info {
@@ -299,6 +300,11 @@ void switchdev_bridge_port_unoffload(struct net_device *brport_dev,
 				     const void *ctx,
 				     struct notifier_block *atomic_nb,
 				     struct notifier_block *blocking_nb);
+int switchdev_bridge_port_replay(struct net_device *brport_dev,
+				 struct net_device *dev, const void *ctx,
+				 struct notifier_block *atomic_nb,
+				 struct notifier_block *blocking_nb,
+				 struct netlink_ext_ack *extack);
 
 void switchdev_deferred_process(void);
 int switchdev_port_attr_set(struct net_device *dev,
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 4f5098d33a46b..a6e94ceb7c9a0 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -234,6 +234,14 @@ static int br_switchdev_blocking_event(struct notifier_block *nb,
 		br_switchdev_port_unoffload(p, b->ctx, b->atomic_nb,
 					    b->blocking_nb);
 		break;
+	case SWITCHDEV_BRPORT_REPLAY:
+		brport_info = ptr;
+		b = &brport_info->brport;
+
+		err = br_switchdev_port_replay(p, b->dev, b->ctx, b->atomic_nb,
+					       b->blocking_nb, extack);
+		err = notifier_from_errno(err);
+		break;
 	}
 
 out:
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 05a965ef76f1a..51e4ca54b5377 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -2118,6 +2118,12 @@ void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx,
 				 struct notifier_block *atomic_nb,
 				 struct notifier_block *blocking_nb);
 
+int br_switchdev_port_replay(struct net_bridge_port *p,
+			     struct net_device *dev, const void *ctx,
+			     struct notifier_block *atomic_nb,
+			     struct notifier_block *blocking_nb,
+			     struct netlink_ext_ack *extack);
+
 bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb);
 
 void br_switchdev_frame_set_offload_fwd_mark(struct sk_buff *skb);
@@ -2168,6 +2174,16 @@ br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx,
 {
 }
 
+static inline int
+br_switchdev_port_replay(struct net_bridge_port *p,
+			 struct net_device *dev, const void *ctx,
+			 struct notifier_block *atomic_nb,
+			 struct notifier_block *blocking_nb,
+			 struct netlink_ext_ack *extack)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb)
 {
 	return false;
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index e92e0338afee3..ee84e783e1dff 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -829,3 +829,12 @@ void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx,
 
 	nbp_switchdev_del(p);
 }
+
+int br_switchdev_port_replay(struct net_bridge_port *p,
+			     struct net_device *dev, const void *ctx,
+			     struct notifier_block *atomic_nb,
+			     struct notifier_block *blocking_nb,
+			     struct netlink_ext_ack *extack)
+{
+	return nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack);
+}
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 8cc42aea19c7e..5b045284849e0 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -862,3 +862,28 @@ void switchdev_bridge_port_unoffload(struct net_device *brport_dev,
 					  NULL);
 }
 EXPORT_SYMBOL_GPL(switchdev_bridge_port_unoffload);
+
+int switchdev_bridge_port_replay(struct net_device *brport_dev,
+				 struct net_device *dev, const void *ctx,
+				 struct notifier_block *atomic_nb,
+				 struct notifier_block *blocking_nb,
+				 struct netlink_ext_ack *extack)
+{
+	struct switchdev_notifier_brport_info brport_info = {
+		.brport = {
+			.dev = dev,
+			.ctx = ctx,
+			.atomic_nb = atomic_nb,
+			.blocking_nb = blocking_nb,
+		},
+	};
+	int err;
+
+	ASSERT_RTNL();
+
+	err = call_switchdev_blocking_notifiers(SWITCHDEV_BRPORT_REPLAY,
+						brport_dev, &brport_info.info,
+						extack);
+	return notifier_to_errno(err);
+}
+EXPORT_SYMBOL_GPL(switchdev_bridge_port_replay);
-- 
GitLab


From d7eb1f17515300d313f4eecf63a2f95704805382 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:18 +0200
Subject: [PATCH 0294/1806] selftests: mlxsw: rtnetlink: Drop obsolete tests

Support for enslaving ports to LAGs with uppers will be added in the
following patches. Selftests to make sure it actually does the right thing
are ready and will be sent as a follow-up.

Similarly, ordering of MACVLAN creation and RIF creation will be relaxed
and it will be permitted to create a MACVLAN first.

Thus these two tests are obsolete. Drop them.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/rtnetlink.sh  | 31 -------------------
 1 file changed, 31 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index 5e89657857c75..893a693ad8057 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -16,7 +16,6 @@ ALL_TESTS="
 	bridge_deletion_test
 	bridge_vlan_flags_test
 	vlan_1_test
-	lag_bridge_upper_test
 	duplicate_vlans_test
 	vlan_rif_refcount_test
 	subport_rif_refcount_test
@@ -211,33 +210,6 @@ vlan_1_test()
 	ip link del dev $swp1.1
 }
 
-lag_bridge_upper_test()
-{
-	# Test that ports cannot be enslaved to LAG devices that have uppers
-	# and that failure is handled gracefully. See commit b3529af6bb0d
-	# ("spectrum: Reference count VLAN entries") for more details
-	RET=0
-
-	ip link add name bond1 type bond mode 802.3ad
-
-	ip link add name br0 type bridge vlan_filtering 1
-	ip link set dev bond1 master br0
-
-	ip link set dev $swp1 down
-	ip link set dev $swp1 master bond1 &> /dev/null
-	check_fail $? "managed to enslave port to lag when should not"
-
-	# This might generate a trace, if we did not handle the failure
-	# correctly
-	ip -6 address add 2001:db8:1::1/64 dev $swp1
-	ip -6 address del 2001:db8:1::1/64 dev $swp1
-
-	log_test "lag with bridge upper"
-
-	ip link del dev br0
-	ip link del dev bond1
-}
-
 duplicate_vlans_test()
 {
 	# Test that on a given port a VLAN is only used once. Either as VLAN
@@ -510,9 +482,6 @@ vlan_interface_uppers_test()
 	ip link set dev $swp1 master br0
 
 	ip link add link br0 name br0.10 type vlan id 10
-	ip link add link br0.10 name macvlan0 \
-		type macvlan mode private &> /dev/null
-	check_fail $? "managed to create a macvlan when should not"
 
 	ip -6 address add 2001:db8:1::1/64 dev br0.10
 	ip link add link br0.10 name macvlan0 type macvlan mode private
-- 
GitLab


From 6bbc9ca6a3a7eacff0363770c2bc3e7640c2996c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:19 +0200
Subject: [PATCH 0295/1806] mlxsw: spectrum_router: Allow address handlers to
 run on bridge ports

Currently the IP address event handlers bail out when the event is related
to a netdevice that is a bridge port or a member of a LAG. In order to
create a RIF when a bridged or LAG'd port is unenslaved, these event
handlers will be replayed. However, at the point in time when the
NETDEV_CHANGEUPPER event is delivered, informing of the loss of
enslavement, the port is still formally enslaved.

In order for the operation to have any effect, these handlers need an extra
parameter to indicate that the check for bridge or LAG membership should
not be done. In this patch, add an argument "nomaster" to several event
handlers.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 41 +++++++++++--------
 1 file changed, 24 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 109ac2db0d654..6b1b142c95db3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8884,10 +8884,11 @@ static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev,
 }
 
 static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
-					unsigned long event,
+					unsigned long event, bool nomaster,
 					struct netlink_ext_ack *extack)
 {
-	if (netif_is_any_bridge_port(port_dev) || netif_is_lag_port(port_dev))
+	if (!nomaster && (netif_is_any_bridge_port(port_dev) ||
+			  netif_is_lag_port(port_dev)))
 		return 0;
 
 	return mlxsw_sp_inetaddr_port_vlan_event(port_dev, port_dev, event,
@@ -8918,10 +8919,10 @@ static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
 }
 
 static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
-				       unsigned long event,
+				       unsigned long event, bool nomaster,
 				       struct netlink_ext_ack *extack)
 {
-	if (netif_is_bridge_port(lag_dev))
+	if (!nomaster && netif_is_bridge_port(lag_dev))
 		return 0;
 
 	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event,
@@ -8980,7 +8981,7 @@ static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp,
 
 static int mlxsw_sp_inetaddr_vlan_event(struct mlxsw_sp *mlxsw_sp,
 					struct net_device *vlan_dev,
-					unsigned long event,
+					unsigned long event, bool nomaster,
 					struct netlink_ext_ack *extack)
 {
 	struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
@@ -8988,7 +8989,7 @@ static int mlxsw_sp_inetaddr_vlan_event(struct mlxsw_sp *mlxsw_sp,
 	u16 lower_pvid;
 	int err;
 
-	if (netif_is_bridge_port(vlan_dev))
+	if (!nomaster && netif_is_bridge_port(vlan_dev))
 		return 0;
 
 	if (mlxsw_sp_port_dev_check(real_dev)) {
@@ -9132,19 +9133,21 @@ static int mlxsw_sp_inetaddr_macvlan_event(struct mlxsw_sp *mlxsw_sp,
 
 static int __mlxsw_sp_inetaddr_event(struct mlxsw_sp *mlxsw_sp,
 				     struct net_device *dev,
-				     unsigned long event,
+				     unsigned long event, bool nomaster,
 				     struct netlink_ext_ack *extack)
 {
 	if (mlxsw_sp_port_dev_check(dev))
-		return mlxsw_sp_inetaddr_port_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_port_event(dev, event, nomaster,
+						    extack);
 	else if (netif_is_lag_master(dev))
-		return mlxsw_sp_inetaddr_lag_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_lag_event(dev, event, nomaster,
+						   extack);
 	else if (netif_is_bridge_master(dev))
 		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, dev, -1, event,
 						      extack);
 	else if (is_vlan_dev(dev))
 		return mlxsw_sp_inetaddr_vlan_event(mlxsw_sp, dev, event,
-						    extack);
+						    nomaster, extack);
 	else if (netif_is_macvlan(dev))
 		return mlxsw_sp_inetaddr_macvlan_event(mlxsw_sp, dev, event,
 						       extack);
@@ -9171,7 +9174,8 @@ static int mlxsw_sp_inetaddr_event(struct notifier_block *nb,
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(router->mlxsw_sp, dev, event, NULL);
+	err = __mlxsw_sp_inetaddr_event(router->mlxsw_sp, dev, event, false,
+					NULL);
 out:
 	mutex_unlock(&router->lock);
 	return notifier_from_errno(err);
@@ -9195,7 +9199,8 @@ static int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, ivi->extack);
+	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, false,
+					ivi->extack);
 out:
 	mutex_unlock(&mlxsw_sp->router->lock);
 	return notifier_from_errno(err);
@@ -9224,7 +9229,7 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work)
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	__mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, NULL);
+	__mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, false, NULL);
 out:
 	mutex_unlock(&mlxsw_sp->router->lock);
 	rtnl_unlock();
@@ -9278,7 +9283,8 @@ static int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused,
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, i6vi->extack);
+	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, false,
+					i6vi->extack);
 out:
 	mutex_unlock(&mlxsw_sp->router->lock);
 	return notifier_from_errno(err);
@@ -9598,10 +9604,11 @@ static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp,
 	 */
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
 	if (rif)
-		__mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_DOWN,
+		__mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_DOWN, false,
 					  extack);
 
-	return __mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_UP, extack);
+	return __mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_UP, false,
+					 extack);
 }
 
 static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
@@ -9612,7 +9619,7 @@ static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
 	if (!rif)
 		return;
-	__mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_DOWN, NULL);
+	__mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_DOWN, false, NULL);
 }
 
 static bool mlxsw_sp_is_vrf_event(unsigned long event, void *ptr)
-- 
GitLab


From 96c3e45c0130205136a13dab129c207e958a5637 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:20 +0200
Subject: [PATCH 0296/1806] mlxsw: spectrum_router: Extract a helper to
 schedule neighbour work

This will come in handy for neighbour replay.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 25 ++++++++++++-------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 6b1b142c95db3..18e059e94079e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2872,6 +2872,21 @@ static bool mlxsw_sp_dev_lower_is_port(struct net_device *dev)
 	return !!mlxsw_sp_port;
 }
 
+static int mlxsw_sp_router_schedule_neigh_work(struct mlxsw_sp_router *router,
+					       struct neighbour *n)
+{
+	struct net *net;
+
+	net = neigh_parms_net(n->parms);
+
+	/* Take a reference to ensure the neighbour won't be destructed until we
+	 * drop the reference in delayed work.
+	 */
+	neigh_clone(n);
+	return mlxsw_sp_router_schedule_work(net, router, n,
+					     mlxsw_sp_router_neigh_event_work);
+}
+
 static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 					  unsigned long event, void *ptr)
 {
@@ -2879,7 +2894,6 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 	unsigned long interval;
 	struct neigh_parms *p;
 	struct neighbour *n;
-	struct net *net;
 
 	router = container_of(nb, struct mlxsw_sp_router, netevent_nb);
 
@@ -2903,7 +2917,6 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 		break;
 	case NETEVENT_NEIGH_UPDATE:
 		n = ptr;
-		net = neigh_parms_net(n->parms);
 
 		if (n->tbl->family != AF_INET && n->tbl->family != AF_INET6)
 			return NOTIFY_DONE;
@@ -2911,13 +2924,7 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 		if (!mlxsw_sp_dev_lower_is_port(n->dev))
 			return NOTIFY_DONE;
 
-		/* Take a reference to ensure the neighbour won't be
-		 * destructed until we drop the reference in delayed
-		 * work.
-		 */
-		neigh_clone(n);
-		return mlxsw_sp_router_schedule_work(net, router, n,
-				mlxsw_sp_router_neigh_event_work);
+		return mlxsw_sp_router_schedule_neigh_work(router, n);
 
 	case NETEVENT_IPV4_MPATH_HASH_UPDATE:
 	case NETEVENT_IPV6_MPATH_HASH_UPDATE:
-- 
GitLab


From 721717fafdc416c66ed66f10ce9ac01e1f52d145 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:21 +0200
Subject: [PATCH 0297/1806] mlxsw: spectrum: Split a helper out of
 mlxsw_sp_netdevice_event()

Move the meat of mlxsw_sp_netdevice_event() to a separate function that
does just the validation. This separate helper will be possible to call
later for recursive ascent when validating attachment of a front panel port
to a bridge with uppers.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    | 20 ++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 86e2f0ed64d3d..0488fe5695bda 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5146,21 +5146,18 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-static int mlxsw_sp_netdevice_event(struct notifier_block *nb,
-				    unsigned long event, void *ptr)
+static int __mlxsw_sp_netdevice_event(struct mlxsw_sp *mlxsw_sp,
+				      unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct mlxsw_sp_span_entry *span_entry;
-	struct mlxsw_sp *mlxsw_sp;
 	int err = 0;
 
-	mlxsw_sp = container_of(nb, struct mlxsw_sp, netdevice_nb);
 	if (event == NETDEV_UNREGISTER) {
 		span_entry = mlxsw_sp_span_entry_find_by_port(mlxsw_sp, dev);
 		if (span_entry)
 			mlxsw_sp_span_entry_invalidate(mlxsw_sp, span_entry);
 	}
-	mlxsw_sp_span_respin(mlxsw_sp);
 
 	if (netif_is_vxlan(dev))
 		err = mlxsw_sp_netdevice_vxlan_event(mlxsw_sp, dev, event, ptr);
@@ -5175,6 +5172,19 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb,
 	else if (netif_is_macvlan(dev))
 		err = mlxsw_sp_netdevice_macvlan_event(dev, event, ptr);
 
+	return err;
+}
+
+static int mlxsw_sp_netdevice_event(struct notifier_block *nb,
+				    unsigned long event, void *ptr)
+{
+	struct mlxsw_sp *mlxsw_sp;
+	int err;
+
+	mlxsw_sp = container_of(nb, struct mlxsw_sp, netdevice_nb);
+	mlxsw_sp_span_respin(mlxsw_sp);
+	err = __mlxsw_sp_netdevice_event(mlxsw_sp, event, ptr);
+
 	return notifier_from_errno(err);
 }
 
-- 
GitLab


From 40b7b4236c1f8e31d7608ecdae07d3889d5e95a0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:22 +0200
Subject: [PATCH 0298/1806] mlxsw: spectrum: Allow event handlers to check
 unowned bridges

Currently the bridge-related handlers bail out when the event is related to
a netdevice that is not an upper of one of the front-panel ports. In order
to allow enslavement of front-panel ports to bridges that already have
uppers, it will be necessary to replay CHANGEUPPER events to validate that
the configuration is offloadable. In order for the replay to be effective,
it must be possible to ignore unsupported configuration in the context of
an actual notifier event, but to still "veto" these configurations when the
validation is performed.

To that end, introduce two parameters to a number of handlers: mlxsw_sp,
because it will not be possible to deduce that from the netdevice lowers;
and process_foreign to indicate whether netdevices that are not front panel
uppers should be validated.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    | 40 +++++++++++--------
 1 file changed, 24 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 0488fe5695bda..3d1a045ff4704 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4936,17 +4936,17 @@ static int mlxsw_sp_netdevice_lag_port_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
-static int mlxsw_sp_netdevice_bridge_vlan_event(struct net_device *vlan_dev,
+static int mlxsw_sp_netdevice_bridge_vlan_event(struct mlxsw_sp *mlxsw_sp,
+						struct net_device *vlan_dev,
 						struct net_device *br_dev,
 						unsigned long event, void *ptr,
-						u16 vid)
+						u16 vid, bool process_foreign)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
 	struct netdev_notifier_changeupper_info *info = ptr;
 	struct netlink_ext_ack *extack;
 	struct net_device *upper_dev;
 
-	if (!mlxsw_sp)
+	if (!process_foreign && !mlxsw_sp_lower_get(vlan_dev))
 		return 0;
 
 	extack = netdev_notifier_info_to_extack(&info->info);
@@ -4979,8 +4979,10 @@ static int mlxsw_sp_netdevice_bridge_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
-static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
-					 unsigned long event, void *ptr)
+static int mlxsw_sp_netdevice_vlan_event(struct mlxsw_sp *mlxsw_sp,
+					 struct net_device *vlan_dev,
+					 unsigned long event, void *ptr,
+					 bool process_foreign)
 {
 	struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
 	u16 vid = vlan_dev_vlan_id(vlan_dev);
@@ -4993,22 +4995,25 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 							      real_dev, event,
 							      ptr, vid);
 	else if (netif_is_bridge_master(real_dev))
-		return mlxsw_sp_netdevice_bridge_vlan_event(vlan_dev, real_dev,
-							    event, ptr, vid);
+		return mlxsw_sp_netdevice_bridge_vlan_event(mlxsw_sp, vlan_dev,
+							    real_dev, event,
+							    ptr, vid,
+							    process_foreign);
 
 	return 0;
 }
 
-static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev,
-					   unsigned long event, void *ptr)
+static int mlxsw_sp_netdevice_bridge_event(struct mlxsw_sp *mlxsw_sp,
+					   struct net_device *br_dev,
+					   unsigned long event, void *ptr,
+					   bool process_foreign)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(br_dev);
 	struct netdev_notifier_changeupper_info *info = ptr;
 	struct netlink_ext_ack *extack;
 	struct net_device *upper_dev;
 	u16 proto;
 
-	if (!mlxsw_sp)
+	if (!process_foreign && !mlxsw_sp_lower_get(br_dev))
 		return 0;
 
 	extack = netdev_notifier_info_to_extack(&info->info);
@@ -5147,7 +5152,8 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int __mlxsw_sp_netdevice_event(struct mlxsw_sp *mlxsw_sp,
-				      unsigned long event, void *ptr)
+				      unsigned long event, void *ptr,
+				      bool process_foreign)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct mlxsw_sp_span_entry *span_entry;
@@ -5166,9 +5172,11 @@ static int __mlxsw_sp_netdevice_event(struct mlxsw_sp *mlxsw_sp,
 	else if (netif_is_lag_master(dev))
 		err = mlxsw_sp_netdevice_lag_event(dev, event, ptr);
 	else if (is_vlan_dev(dev))
-		err = mlxsw_sp_netdevice_vlan_event(dev, event, ptr);
+		err = mlxsw_sp_netdevice_vlan_event(mlxsw_sp, dev, event, ptr,
+						    process_foreign);
 	else if (netif_is_bridge_master(dev))
-		err = mlxsw_sp_netdevice_bridge_event(dev, event, ptr);
+		err = mlxsw_sp_netdevice_bridge_event(mlxsw_sp, dev, event, ptr,
+						      process_foreign);
 	else if (netif_is_macvlan(dev))
 		err = mlxsw_sp_netdevice_macvlan_event(dev, event, ptr);
 
@@ -5183,7 +5191,7 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb,
 
 	mlxsw_sp = container_of(nb, struct mlxsw_sp, netdevice_nb);
 	mlxsw_sp_span_respin(mlxsw_sp);
-	err = __mlxsw_sp_netdevice_event(mlxsw_sp, event, ptr);
+	err = __mlxsw_sp_netdevice_event(mlxsw_sp, event, ptr, false);
 
 	return notifier_from_errno(err);
 }
-- 
GitLab


From 1c47e65b8c0ba018152beb13f28afe50017438e4 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:23 +0200
Subject: [PATCH 0299/1806] mlxsw: spectrum: Add a replay_deslavement argument
 to event handlers

When handling deslavement of LAG or its upper from a bridge device, when
the deslaved netdevice has an IP address, it should join the router. This
should be done after all the lowers of the LAG have left the bridge. The
replay intended to cause the device to join the router therefore cannot be
invoked unconditionally in the event handlers themselves. It can be done
right away if the handler is invoked for a sole device, but when it is
invoked repeated for each LAG lower, the replay needs to be postponed
until after this processing is done.

To that end, add a boolean parameter, replay_deslavement, to
mlxsw_sp_netdevice_port_upper_event(), mlxsw_sp_netdevice_port_vlan_event()
and one helper on the call path. Have the invocations that are done for
sole netdevices pass true, and those done for LAG lowers pass false.

Nothing depends on this flag at this point, but it removes some noise from
the patch that introduces the replay itself.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    | 20 +++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3d1a045ff4704..b9ceffe258bf9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4641,7 +4641,8 @@ static bool mlxsw_sp_bridge_vxlan_is_valid(struct net_device *br_dev,
 
 static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 					       struct net_device *dev,
-					       unsigned long event, void *ptr)
+					       unsigned long event, void *ptr,
+					       bool replay_deslavement)
 {
 	struct netdev_notifier_changeupper_info *info;
 	struct mlxsw_sp_port *mlxsw_sp_port;
@@ -4815,13 +4816,15 @@ static int mlxsw_sp_netdevice_port_lower_event(struct net_device *dev,
 
 static int mlxsw_sp_netdevice_port_event(struct net_device *lower_dev,
 					 struct net_device *port_dev,
-					 unsigned long event, void *ptr)
+					 unsigned long event, void *ptr,
+					 bool replay_deslavement)
 {
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
 	case NETDEV_CHANGEUPPER:
 		return mlxsw_sp_netdevice_port_upper_event(lower_dev, port_dev,
-							   event, ptr);
+							   event, ptr,
+							   replay_deslavement);
 	case NETDEV_CHANGELOWERSTATE:
 		return mlxsw_sp_netdevice_port_lower_event(port_dev, event,
 							   ptr);
@@ -4840,7 +4843,7 @@ static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev,
 	netdev_for_each_lower_dev(lag_dev, dev, iter) {
 		if (mlxsw_sp_port_dev_check(dev)) {
 			ret = mlxsw_sp_netdevice_port_event(lag_dev, dev, event,
-							    ptr);
+							    ptr, false);
 			if (ret)
 				return ret;
 		}
@@ -4852,7 +4855,7 @@ static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev,
 static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 					      struct net_device *dev,
 					      unsigned long event, void *ptr,
-					      u16 vid)
+					      u16 vid, bool replay_deslavement)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
@@ -4927,7 +4930,7 @@ static int mlxsw_sp_netdevice_lag_port_vlan_event(struct net_device *vlan_dev,
 		if (mlxsw_sp_port_dev_check(dev)) {
 			ret = mlxsw_sp_netdevice_port_vlan_event(vlan_dev, dev,
 								 event, ptr,
-								 vid);
+								 vid, false);
 			if (ret)
 				return ret;
 		}
@@ -4989,7 +4992,8 @@ static int mlxsw_sp_netdevice_vlan_event(struct mlxsw_sp *mlxsw_sp,
 
 	if (mlxsw_sp_port_dev_check(real_dev))
 		return mlxsw_sp_netdevice_port_vlan_event(vlan_dev, real_dev,
-							  event, ptr, vid);
+							  event, ptr, vid,
+							  true);
 	else if (netif_is_lag_master(real_dev))
 		return mlxsw_sp_netdevice_lag_port_vlan_event(vlan_dev,
 							      real_dev, event,
@@ -5168,7 +5172,7 @@ static int __mlxsw_sp_netdevice_event(struct mlxsw_sp *mlxsw_sp,
 	if (netif_is_vxlan(dev))
 		err = mlxsw_sp_netdevice_vxlan_event(mlxsw_sp, dev, event, ptr);
 	else if (mlxsw_sp_port_dev_check(dev))
-		err = mlxsw_sp_netdevice_port_event(dev, dev, event, ptr);
+		err = mlxsw_sp_netdevice_port_event(dev, dev, event, ptr, true);
 	else if (netif_is_lag_master(dev))
 		err = mlxsw_sp_netdevice_lag_event(dev, event, ptr);
 	else if (is_vlan_dev(dev))
-- 
GitLab


From 987c7782f0627e1c87617458806a7e6c1995678a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:24 +0200
Subject: [PATCH 0300/1806] mlxsw: spectrum: On port enslavement to a LAG, join
 upper's bridges

Currently it never happens that a netdevice that is already a bridge slave
would suddenly become mlxsw upper. The only case where this might be
possible as far as mlxsw is concerned, is with LAG netdevices. But if a LAG
already has an upper, enslaving mlxsw port to that LAG is forbidden. Thus
the only way to install a LAG between a bridge and a mlxsw port is by first
enslaving the port to the LAG, and then enslaving that LAG to a bridge.

However in the following patches, the requirement that ports be only
enslaved to masters without uppers, is going to be relaxed. It will
therefore be necessary to join bridges of LAG uppers. Without this replay,
the mlxsw bridge_port objects are not instantiated, which causes issues
later, as a lot of code relies on their presence.

Therefore in this patch, when the first mlxsw physical netdevice is
enslaved to a LAG, consider bridges upper to the LAG (both the direct
master, if any, and any bridge masters of VLAN uppers), and have the
relevant netdevices join their bridges.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    | 90 +++++++++++++++++++
 1 file changed, 90 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index b9ceffe258bf9..9a6e1ce4e7861 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4337,6 +4337,88 @@ static int mlxsw_sp_port_lag_index_get(struct mlxsw_sp *mlxsw_sp,
 	return -EBUSY;
 }
 
+static int mlxsw_sp_lag_uppers_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port,
+					   struct net_device *lag_dev,
+					   struct netlink_ext_ack *extack)
+{
+	struct net_device *upper_dev;
+	struct net_device *master;
+	struct list_head *iter;
+	int done = 0;
+	int err;
+
+	master = netdev_master_upper_dev_get(lag_dev);
+	if (master && netif_is_bridge_master(master)) {
+		err = mlxsw_sp_port_bridge_join(mlxsw_sp_port, lag_dev, master,
+						extack);
+		if (err)
+			return err;
+	}
+
+	netdev_for_each_upper_dev_rcu(lag_dev, upper_dev, iter) {
+		if (!is_vlan_dev(upper_dev))
+			continue;
+
+		master = netdev_master_upper_dev_get(upper_dev);
+		if (master && netif_is_bridge_master(master)) {
+			err = mlxsw_sp_port_bridge_join(mlxsw_sp_port,
+							upper_dev, master,
+							extack);
+			if (err)
+				goto err_port_bridge_join;
+		}
+
+		++done;
+	}
+
+	return 0;
+
+err_port_bridge_join:
+	netdev_for_each_upper_dev_rcu(lag_dev, upper_dev, iter) {
+		if (!is_vlan_dev(upper_dev))
+			continue;
+
+		master = netdev_master_upper_dev_get(upper_dev);
+		if (!master || !netif_is_bridge_master(master))
+			continue;
+
+		if (!done--)
+			break;
+
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, upper_dev, master);
+	}
+
+	master = netdev_master_upper_dev_get(lag_dev);
+	if (master && netif_is_bridge_master(master))
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, lag_dev, master);
+
+	return err;
+}
+
+static void
+mlxsw_sp_lag_uppers_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
+				 struct net_device *lag_dev)
+{
+	struct net_device *upper_dev;
+	struct net_device *master;
+	struct list_head *iter;
+
+	netdev_for_each_upper_dev_rcu(lag_dev, upper_dev, iter) {
+		if (!is_vlan_dev(upper_dev))
+			continue;
+
+		master = netdev_master_upper_dev_get(upper_dev);
+		if (!master)
+			continue;
+
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, upper_dev, master);
+	}
+
+	master = netdev_master_upper_dev_get(lag_dev);
+	if (master)
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, lag_dev, master);
+}
+
 static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 				  struct net_device *lag_dev,
 				  struct netlink_ext_ack *extack)
@@ -4361,6 +4443,12 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	err = mlxsw_sp_port_lag_index_get(mlxsw_sp, lag_id, &port_index);
 	if (err)
 		return err;
+
+	err = mlxsw_sp_lag_uppers_bridge_join(mlxsw_sp_port, lag_dev,
+					      extack);
+	if (err)
+		goto err_lag_uppers_bridge_join;
+
 	err = mlxsw_sp_lag_col_port_add(mlxsw_sp_port, lag_id, port_index);
 	if (err)
 		goto err_col_port_add;
@@ -4390,6 +4478,8 @@ err_router_join:
 				     mlxsw_sp_port->local_port);
 	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
 err_col_port_add:
+	mlxsw_sp_lag_uppers_bridge_leave(mlxsw_sp_port, lag_dev);
+err_lag_uppers_bridge_join:
 	if (!lag->ref_count)
 		mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
 	return err;
-- 
GitLab


From ec4643ca3d98c4a7a421f11b76c8a46223a1aa19 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:25 +0200
Subject: [PATCH 0301/1806] mlxsw: spectrum_switchdev: Replay switchdev objects
 on port join

Currently it never happens that a netdevice that is already a bridge slave
would suddenly become mlxsw upper. The only case where this might be
possible as far as mlxsw is concerned, is with LAG netdevices. But if a LAG
has any upper (e.g. is enslaved), enlaving mlxsw port to that LAG is
forbidden. Thus the only way to install a LAG between a bridge and a mlxsw
port is by first enslaving the port to the LAG, and then enslaving that LAG
to a bridge. At that point there are no bridge objects (such as port VLANs)
to replay. Those are added afterwards, and notified as they are created.
This holds even for the PVID.

However in the following patches, the requirement that ports be only
enslaved to masters without uppers, is going to be relaxed. It will
therefore be necessary to replay the existing bridge objects. Without this
replay, e.g. the mlxsw bridge_port_vlan objects are not instantiated, which
causes issues later, as a lot of code relies on their presence.

To that end, add a new notifier block whose sole role is to filter out
events related to the one relevant upper, and forward those to the existing
switchdev notifier block. Pass the new notifier block to
switchdev_bridge_port_offload() when the bridge port is created.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    |   4 +-
 .../net/ethernet/mellanox/mlxsw/spectrum.h    |   2 +
 .../mellanox/mlxsw/spectrum_switchdev.c       | 131 +++++++++++++++++-
 3 files changed, 132 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 9a6e1ce4e7861..8087da00f38fe 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1132,8 +1132,8 @@ static int mlxsw_sp_port_add_vid(struct net_device *dev,
 	return PTR_ERR_OR_ZERO(mlxsw_sp_port_vlan_create(mlxsw_sp_port, vid));
 }
 
-static int mlxsw_sp_port_kill_vid(struct net_device *dev,
-				  __be16 __always_unused proto, u16 vid)
+int mlxsw_sp_port_kill_vid(struct net_device *dev,
+			   __be16 __always_unused proto, u16 vid)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index c6231e62a371e..65eaa181e0aa6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -700,6 +700,8 @@ int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
 struct mlxsw_sp_port_vlan *
 mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
 void mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
+int mlxsw_sp_port_kill_vid(struct net_device *dev,
+			   __be16 __always_unused proto, u16 vid);
 int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
 			   u16 vid_end, bool is_member, bool untagged);
 int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 79d45c6c6edf6..982eae6bd63ec 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -384,6 +384,91 @@ mlxsw_sp_bridge_port_find(struct mlxsw_sp_bridge *bridge,
 	return __mlxsw_sp_bridge_port_find(bridge_device, brport_dev);
 }
 
+static int mlxsw_sp_port_obj_add(struct net_device *dev, const void *ctx,
+				 const struct switchdev_obj *obj,
+				 struct netlink_ext_ack *extack);
+static int mlxsw_sp_port_obj_del(struct net_device *dev, const void *ctx,
+				 const struct switchdev_obj *obj);
+
+struct mlxsw_sp_bridge_port_replay_switchdev_objs {
+	struct net_device *brport_dev;
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	int done;
+};
+
+static int
+mlxsw_sp_bridge_port_replay_switchdev_objs(struct notifier_block *nb,
+					   unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	struct switchdev_notifier_port_obj_info *port_obj_info = ptr;
+	struct netlink_ext_ack *extack = port_obj_info->info.extack;
+	struct mlxsw_sp_bridge_port_replay_switchdev_objs *rso;
+	int err = 0;
+
+	rso = (void *)port_obj_info->info.ctx;
+
+	if (event != SWITCHDEV_PORT_OBJ_ADD ||
+	    dev != rso->brport_dev)
+		goto out;
+
+	/* When a port is joining the bridge through a LAG, there likely are
+	 * VLANs configured on that LAG already. The replay will thus attempt to
+	 * have the given port-vlans join the corresponding FIDs. But the LAG
+	 * netdevice has already called the ndo_vlan_rx_add_vid NDO for its VLAN
+	 * memberships, back before CHANGEUPPER was distributed and netdevice
+	 * master set. So now before propagating the VLAN events further, we
+	 * first need to kill the corresponding VID at the mlxsw_sp_port.
+	 *
+	 * Note that this doesn't need to be rolled back on failure -- if the
+	 * replay fails, the enslavement is off, and the VIDs would be killed by
+	 * LAG anyway as part of its rollback.
+	 */
+	if (port_obj_info->obj->id == SWITCHDEV_OBJ_ID_PORT_VLAN) {
+		u16 vid = SWITCHDEV_OBJ_PORT_VLAN(port_obj_info->obj)->vid;
+
+		err = mlxsw_sp_port_kill_vid(rso->mlxsw_sp_port->dev, 0, vid);
+		if (err)
+			goto out;
+	}
+
+	++rso->done;
+	err = mlxsw_sp_port_obj_add(rso->mlxsw_sp_port->dev, NULL,
+				    port_obj_info->obj, extack);
+
+out:
+	return notifier_from_errno(err);
+}
+
+static struct notifier_block mlxsw_sp_bridge_port_replay_switchdev_objs_nb = {
+	.notifier_call = mlxsw_sp_bridge_port_replay_switchdev_objs,
+};
+
+static int
+mlxsw_sp_bridge_port_unreplay_switchdev_objs(struct notifier_block *nb,
+					     unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	struct switchdev_notifier_port_obj_info *port_obj_info = ptr;
+	struct mlxsw_sp_bridge_port_replay_switchdev_objs *rso;
+
+	rso = (void *)port_obj_info->info.ctx;
+
+	if (event != SWITCHDEV_PORT_OBJ_ADD ||
+	    dev != rso->brport_dev)
+		return NOTIFY_DONE;
+	if (!rso->done--)
+		return NOTIFY_STOP;
+
+	mlxsw_sp_port_obj_del(rso->mlxsw_sp_port->dev, NULL,
+			      port_obj_info->obj);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block mlxsw_sp_bridge_port_unreplay_switchdev_objs_nb = {
+	.notifier_call = mlxsw_sp_bridge_port_unreplay_switchdev_objs,
+};
+
 static struct mlxsw_sp_bridge_port *
 mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device,
 			    struct net_device *brport_dev,
@@ -2350,6 +2435,33 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
+static int
+mlxsw_sp_bridge_port_replay(struct mlxsw_sp_bridge_port *bridge_port,
+			    struct mlxsw_sp_port *mlxsw_sp_port,
+			    struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_bridge_port_replay_switchdev_objs rso = {
+		.brport_dev = bridge_port->dev,
+		.mlxsw_sp_port = mlxsw_sp_port,
+	};
+	struct notifier_block *nb;
+	int err;
+
+	nb = &mlxsw_sp_bridge_port_replay_switchdev_objs_nb;
+	err = switchdev_bridge_port_replay(bridge_port->dev, mlxsw_sp_port->dev,
+					   &rso, NULL, nb, extack);
+	if (err)
+		goto err_replay;
+
+	return 0;
+
+err_replay:
+	nb = &mlxsw_sp_bridge_port_unreplay_switchdev_objs_nb;
+	switchdev_bridge_port_replay(bridge_port->dev, mlxsw_sp_port->dev,
+				     &rso, NULL, nb, extack);
+	return err;
+}
+
 static int
 mlxsw_sp_bridge_vlan_aware_port_join(struct mlxsw_sp_bridge_port *bridge_port,
 				     struct mlxsw_sp_port *mlxsw_sp_port,
@@ -2364,7 +2476,7 @@ mlxsw_sp_bridge_vlan_aware_port_join(struct mlxsw_sp_bridge_port *bridge_port,
 	if (mlxsw_sp_port->default_vlan->fid)
 		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port->default_vlan);
 
-	return 0;
+	return mlxsw_sp_bridge_port_replay(bridge_port, mlxsw_sp_port, extack);
 }
 
 static int
@@ -2536,6 +2648,7 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 	struct net_device *dev = bridge_port->dev;
 	u16 vid;
+	int err;
 
 	vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : MLXSW_SP_DEFAULT_VID;
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
@@ -2551,8 +2664,20 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 	if (mlxsw_sp_port_vlan->fid)
 		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
 
-	return mlxsw_sp_port_vlan_bridge_join(mlxsw_sp_port_vlan, bridge_port,
-					      extack);
+	err = mlxsw_sp_port_vlan_bridge_join(mlxsw_sp_port_vlan, bridge_port,
+					     extack);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_bridge_port_replay(bridge_port, mlxsw_sp_port, extack);
+	if (err)
+		goto err_replay;
+
+	return 0;
+
+err_replay:
+	mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
+	return err;
 }
 
 static void
-- 
GitLab


From ef59713c26b1c2a9b0b3a8c481b23335ce6d7183 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:26 +0200
Subject: [PATCH 0302/1806] mlxsw: spectrum_router: Join RIFs of LAG upper
 VLANs

In the following patches, the requirement that ports be only enslaved to
masters without uppers, is going to be relaxed. It will therefore be
necessary to join not only RIF for the immediate LAG, as is currently the
case, but also RIFs for VLAN netdevices upper to the LAG.

In this patch, extend mlxsw_sp_netdevice_router_join_lag() to walk the
uppers of a LAG being joined, and also join any VLAN ones.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 55 ++++++++++++++++++-
 1 file changed, 52 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 18e059e94079e..ae2d5e760f1b5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -9685,15 +9685,64 @@ mlxsw_sp_port_vid_router_join_existing(struct mlxsw_sp_port *mlxsw_sp_port,
 						       dev, extack);
 }
 
+static void
+mlxsw_sp_port_vid_router_leave(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
+			       struct net_device *dev)
+{
+	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
+
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port,
+							    vid);
+	if (WARN_ON(!mlxsw_sp_port_vlan))
+		return;
+
+	__mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
+}
+
 static int __mlxsw_sp_router_port_join_lag(struct mlxsw_sp_port *mlxsw_sp_port,
 					   struct net_device *lag_dev,
 					   struct netlink_ext_ack *extack)
 {
 	u16 default_vid = MLXSW_SP_DEFAULT_VID;
+	struct net_device *upper_dev;
+	struct list_head *iter;
+	int done = 0;
+	u16 vid;
+	int err;
 
-	return mlxsw_sp_port_vid_router_join_existing(mlxsw_sp_port,
-						      default_vid, lag_dev,
-						      extack);
+	err = mlxsw_sp_port_vid_router_join_existing(mlxsw_sp_port, default_vid,
+						     lag_dev, extack);
+	if (err)
+		return err;
+
+	netdev_for_each_upper_dev_rcu(lag_dev, upper_dev, iter) {
+		if (!is_vlan_dev(upper_dev))
+			continue;
+
+		vid = vlan_dev_vlan_id(upper_dev);
+		err = mlxsw_sp_port_vid_router_join_existing(mlxsw_sp_port, vid,
+							     upper_dev, extack);
+		if (err)
+			goto err_router_join_dev;
+
+		++done;
+	}
+
+	return 0;
+
+err_router_join_dev:
+	netdev_for_each_upper_dev_rcu(lag_dev, upper_dev, iter) {
+		if (!is_vlan_dev(upper_dev))
+			continue;
+		if (!done--)
+			break;
+
+		vid = vlan_dev_vlan_id(upper_dev);
+		mlxsw_sp_port_vid_router_leave(mlxsw_sp_port, vid, upper_dev);
+	}
+
+	mlxsw_sp_port_vid_router_leave(mlxsw_sp_port, default_vid, lag_dev);
+	return err;
 }
 
 int mlxsw_sp_router_port_join_lag(struct mlxsw_sp_port *mlxsw_sp_port,
-- 
GitLab


From cfc01a92eaffdb9ac635f3aedc00ad5a6a2f437a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:27 +0200
Subject: [PATCH 0303/1806] mlxsw: spectrum_router: Offload ethernet nexthops
 when RIF is made

As RIF is created, refresh each netxhop group tracked at the CRIF for which
the RIF was created.

Note that nothing needs to be done for IPIP nexthops. The RIF for these is
either available from the get-go, or will never be available, so no after
the fact offloading needs to be done.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 54 +++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index ae2d5e760f1b5..fe1855cc2c76a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4404,6 +4404,19 @@ err_neigh_init:
 	return err;
 }
 
+static int mlxsw_sp_nexthop_type_rif_made(struct mlxsw_sp *mlxsw_sp,
+					  struct mlxsw_sp_nexthop *nh)
+{
+	switch (nh->type) {
+	case MLXSW_SP_NEXTHOP_TYPE_ETH:
+		return mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
+	case MLXSW_SP_NEXTHOP_TYPE_IPIP:
+		break;
+	}
+
+	return 0;
+}
+
 static void mlxsw_sp_nexthop_type_rif_gone(struct mlxsw_sp *mlxsw_sp,
 					   struct mlxsw_sp_nexthop *nh)
 {
@@ -4532,6 +4545,35 @@ static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp,
 	}
 }
 
+static int mlxsw_sp_nexthop_rif_made_sync(struct mlxsw_sp *mlxsw_sp,
+					  struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_nexthop *nh, *tmp;
+	unsigned int n = 0;
+	int err;
+
+	list_for_each_entry_safe(nh, tmp, &rif->crif->nexthop_list,
+				 crif_list_node) {
+		err = mlxsw_sp_nexthop_type_rif_made(mlxsw_sp, nh);
+		if (err)
+			goto err_nexthop_type_rif;
+		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp);
+		n++;
+	}
+
+	return 0;
+
+err_nexthop_type_rif:
+	list_for_each_entry_safe(nh, tmp, &rif->crif->nexthop_list,
+				 crif_list_node) {
+		if (!n--)
+			break;
+		mlxsw_sp_nexthop_type_rif_gone(mlxsw_sp, nh);
+		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp);
+	}
+	return err;
+}
+
 static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
 					   struct mlxsw_sp_rif *rif)
 {
@@ -7892,6 +7934,12 @@ static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
 }
 
+static int mlxsw_sp_router_rif_made_sync(struct mlxsw_sp *mlxsw_sp,
+					 struct mlxsw_sp_rif *rif)
+{
+	return mlxsw_sp_nexthop_rif_made_sync(mlxsw_sp, rif);
+}
+
 static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
 					  struct mlxsw_sp_rif *rif)
 {
@@ -8329,6 +8377,10 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 			goto err_mr_rif_add;
 	}
 
+	err = mlxsw_sp_router_rif_made_sync(mlxsw_sp, rif);
+	if (err)
+		goto err_rif_made_sync;
+
 	if (netdev_offload_xstats_enabled(params->dev,
 					  NETDEV_OFFLOAD_XSTATS_TYPE_L3)) {
 		err = mlxsw_sp_router_port_l3_stats_enable(rif);
@@ -8343,6 +8395,8 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	return rif;
 
 err_stats_enable:
+	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
+err_rif_made_sync:
 err_mr_rif_add:
 	for (i--; i >= 0; i--)
 		mlxsw_sp_mr_rif_del(vr->mr_table[i], rif);
-- 
GitLab


From 49c3a615d382c984a373690b8c4aa783f58e8089 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:28 +0200
Subject: [PATCH 0304/1806] mlxsw: spectrum_router: Replay MACVLANs when RIF is
 made

If IP address is added to a MACVLAN netdevice, the effect is of configuring
VRRP on the RIF for the netdevice linked to the MACVLAN. Because the
MACVLAN offload is tied to existence of a RIF at the linked netdevice,
adding a MACVLAN is currently not allowed until a RIF is present.

If this requirement stays, it will never be possible to attach a first port
into a topology that involves a MACVLAN. Thus topologies would need to be
built in a certain order, which is impractical.

Additionally, IP address removal, which leads to disappearance of the RIF
that the MACVLAN depends on, cannot be vetoed. Thus even as things stand
now it is possible to get to a state where a MACVLAN netdevice exists
without a RIF, despite having mlxsw lowers. And once the MACVLAN is
un-offloaded due to RIF getting destroyed, recreating the RIF does not
bring it back.

In this patch, accept that MACVLAN can be created out of order and support
that use case.

One option would seem to be to simply recognize MACVLAN netdevices as
"interesting", and let the existing replay mechanisms take care of the
offload. However, that does not address the necessity to reoffload MACVLAN
once a RIF is created.

Thus add a new replay hook, symmetrical to mlxsw_sp_rif_macvlan_flush(),
called mlxsw_sp_rif_macvlan_replay(), which instead of unwinding the
existing offloads, applies the configuration as if the netdevice were
created just now.

Additionally, remove all vetoes and warning messages that checked for
presence of a RIF at the linked device.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    | 22 -------
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 59 +++++++++++++++++--
 2 files changed, 54 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 8087da00f38fe..4346cc7365795 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4786,11 +4786,6 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 			NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on a LAG port");
 			return -EINVAL;
 		}
-		if (netif_is_macvlan(upper_dev) &&
-		    !mlxsw_sp_rif_exists(mlxsw_sp, lower_dev)) {
-			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
-			return -EOPNOTSUPP;
-		}
 		if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) {
 			NL_SET_ERR_MSG_MOD(extack, "Master device is an OVS master and this device has a VLAN");
 			return -EINVAL;
@@ -4979,11 +4974,6 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 			NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a device that already has an upper device is not supported");
 			return -EINVAL;
 		}
-		if (netif_is_macvlan(upper_dev) &&
-		    !mlxsw_sp_rif_exists(mlxsw_sp, vlan_dev)) {
-			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
-			return -EOPNOTSUPP;
-		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
@@ -5052,13 +5042,6 @@ static int mlxsw_sp_netdevice_bridge_vlan_event(struct mlxsw_sp *mlxsw_sp,
 			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
 			return -EOPNOTSUPP;
 		}
-		if (!info->linking)
-			break;
-		if (netif_is_macvlan(upper_dev) &&
-		    !mlxsw_sp_rif_exists(mlxsw_sp, vlan_dev)) {
-			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
-			return -EOPNOTSUPP;
-		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
@@ -5135,11 +5118,6 @@ static int mlxsw_sp_netdevice_bridge_event(struct mlxsw_sp *mlxsw_sp,
 			NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are only supported with 802.1q VLAN protocol");
 			return -EOPNOTSUPP;
 		}
-		if (netif_is_macvlan(upper_dev) &&
-		    !mlxsw_sp_rif_exists(mlxsw_sp, br_dev)) {
-			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
-			return -EOPNOTSUPP;
-		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index fe1855cc2c76a..2322429cdb72c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -9121,10 +9121,8 @@ static int mlxsw_sp_rif_macvlan_add(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan->lowerdev);
-	if (!rif) {
-		NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
-		return -EOPNOTSUPP;
-	}
+	if (!rif)
+		return 0;
 
 	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
 				  mlxsw_sp_fid_index(rif->fid), true);
@@ -9857,6 +9855,40 @@ out:
 	return notifier_from_errno(err);
 }
 
+struct mlxsw_sp_macvlan_replay {
+	struct mlxsw_sp *mlxsw_sp;
+	struct netlink_ext_ack *extack;
+};
+
+static int mlxsw_sp_macvlan_replay_upper(struct net_device *dev,
+					 struct netdev_nested_priv *priv)
+{
+	const struct mlxsw_sp_macvlan_replay *rms = priv->data;
+	struct netlink_ext_ack *extack = rms->extack;
+	struct mlxsw_sp *mlxsw_sp = rms->mlxsw_sp;
+
+	if (!netif_is_macvlan(dev))
+		return 0;
+
+	return mlxsw_sp_rif_macvlan_add(mlxsw_sp, dev, extack);
+}
+
+static int mlxsw_sp_macvlan_replay(struct mlxsw_sp_rif *rif,
+				   struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_macvlan_replay rms = {
+		.mlxsw_sp = rif->mlxsw_sp,
+		.extack = extack,
+	};
+	struct netdev_nested_priv priv = {
+		.data = &rms,
+	};
+
+	return netdev_walk_all_upper_dev_rcu(mlxsw_sp_rif_dev(rif),
+					     mlxsw_sp_macvlan_replay_upper,
+					     &priv);
+}
+
 static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev,
 					struct netdev_nested_priv *priv)
 {
@@ -9879,7 +9911,6 @@ static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif)
 	if (!netif_is_macvlan_port(dev))
 		return 0;
 
-	netdev_warn(dev, "Router interface is deleted. Upper macvlans will not work\n");
 	return netdev_walk_all_upper_dev_rcu(dev,
 					     __mlxsw_sp_rif_macvlan_flush, &priv);
 }
@@ -9937,6 +9968,10 @@ static int mlxsw_sp_rif_subport_configure(struct mlxsw_sp_rif *rif,
 	if (err)
 		goto err_rif_subport_op;
 
+	err = mlxsw_sp_macvlan_replay(rif, extack);
+	if (err)
+		goto err_macvlan_replay;
+
 	err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr,
 				  mlxsw_sp_fid_index(rif->fid), true);
 	if (err)
@@ -9952,6 +9987,8 @@ err_fid_rif_set:
 	mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr,
 			    mlxsw_sp_fid_index(rif->fid), false);
 err_rif_fdb_op:
+	mlxsw_sp_rif_macvlan_flush(rif);
+err_macvlan_replay:
 	mlxsw_sp_rif_subport_op(rif, false);
 err_rif_subport_op:
 	mlxsw_sp_rif_mac_profile_put(rif->mlxsw_sp, mac_profile);
@@ -10038,6 +10075,10 @@ static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif,
 	if (err)
 		goto err_fid_bc_flood_set;
 
+	err = mlxsw_sp_macvlan_replay(rif, extack);
+	if (err)
+		goto err_macvlan_replay;
+
 	err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr,
 				  mlxsw_sp_fid_index(rif->fid), true);
 	if (err)
@@ -10053,6 +10094,8 @@ err_fid_rif_set:
 	mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr,
 			    mlxsw_sp_fid_index(rif->fid), false);
 err_rif_fdb_op:
+	mlxsw_sp_rif_macvlan_flush(rif);
+err_macvlan_replay:
 	mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
 			       mlxsw_sp_router_port(mlxsw_sp), false);
 err_fid_bc_flood_set:
@@ -10200,6 +10243,10 @@ static int mlxsw_sp_rif_vlan_configure(struct mlxsw_sp_rif *rif, u16 efid,
 	if (err)
 		goto err_fid_bc_flood_set;
 
+	err = mlxsw_sp_macvlan_replay(rif, extack);
+	if (err)
+		goto err_macvlan_replay;
+
 	err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr,
 				  mlxsw_sp_fid_index(rif->fid), true);
 	if (err)
@@ -10215,6 +10262,8 @@ err_fid_rif_set:
 	mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr,
 			    mlxsw_sp_fid_index(rif->fid), false);
 err_rif_fdb_op:
+	mlxsw_sp_rif_macvlan_flush(rif);
+err_macvlan_replay:
 	mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
 			       mlxsw_sp_router_port(mlxsw_sp), false);
 err_fid_bc_flood_set:
-- 
GitLab


From 8fdb09a7674c61c4f0e5faf0d63b3ce500a341b0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:29 +0200
Subject: [PATCH 0305/1806] mlxsw: spectrum_router: Replay neighbours when RIF
 is made

As neighbours are created, mlxsw is involved through the netevent
notifications. When at the time there is no RIF for a given neighbour, the
notification is not acted upon. When the RIF is later created, these
outstanding neighbours are left unoffloaded and cause traffic to go through
the SW datapath.

In order to fix this issue, as a RIF is created, walk the ARP and ND tables
and find neighbours for the netdevice that represents the RIF. Then
schedule neighbour work for them, allowing them to be offloaded.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 62 ++++++++++++++++++-
 1 file changed, 61 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 2322429cdb72c..9263a914bcc7b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2983,6 +2983,52 @@ static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
 	}
 }
 
+struct mlxsw_sp_neigh_rif_made_sync {
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+	int err;
+};
+
+static void mlxsw_sp_neigh_rif_made_sync_each(struct neighbour *n, void *data)
+{
+	struct mlxsw_sp_neigh_rif_made_sync *rms = data;
+	int rc;
+
+	if (rms->err)
+		return;
+	if (n->dev != mlxsw_sp_rif_dev(rms->rif))
+		return;
+	rc = mlxsw_sp_router_schedule_neigh_work(rms->mlxsw_sp->router, n);
+	if (rc != NOTIFY_DONE)
+		rms->err = -ENOMEM;
+}
+
+static int mlxsw_sp_neigh_rif_made_sync(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_neigh_rif_made_sync rms = {
+		.mlxsw_sp = mlxsw_sp,
+		.rif = rif,
+	};
+
+	neigh_for_each(&arp_tbl, mlxsw_sp_neigh_rif_made_sync_each, &rms);
+	if (rms.err)
+		goto err_arp;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	neigh_for_each(&nd_tbl, mlxsw_sp_neigh_rif_made_sync_each, &rms);
+#endif
+	if (rms.err)
+		goto err_nd;
+
+	return 0;
+
+err_nd:
+err_arp:
+	mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, rif);
+	return rms.err;
+}
+
 enum mlxsw_sp_nexthop_type {
 	MLXSW_SP_NEXTHOP_TYPE_ETH,
 	MLXSW_SP_NEXTHOP_TYPE_IPIP,
@@ -7937,7 +7983,21 @@ static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
 static int mlxsw_sp_router_rif_made_sync(struct mlxsw_sp *mlxsw_sp,
 					 struct mlxsw_sp_rif *rif)
 {
-	return mlxsw_sp_nexthop_rif_made_sync(mlxsw_sp, rif);
+	int err;
+
+	err = mlxsw_sp_neigh_rif_made_sync(mlxsw_sp, rif);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_nexthop_rif_made_sync(mlxsw_sp, rif);
+	if (err)
+		goto err_nexthop;
+
+	return 0;
+
+err_nexthop:
+	mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, rif);
+	return err;
 }
 
 static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
-- 
GitLab


From 31618b22f2c4c0a4491554a2d879141efdffe88f Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:30 +0200
Subject: [PATCH 0306/1806] mlxsw: spectrum_router: Replay IP NETDEV_UP on
 device enslavement

Enslaving of front panel ports (and their uppers) to netdevices that
already have uppers is currently forbidden. When this is permitted, any
uppers with IP addresses need to have the NETDEV_UP inetaddr event
replayed, so that any RIFs are created.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    |   6 +
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 119 ++++++++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_router.h |   5 +
 .../mellanox/mlxsw/spectrum_switchdev.c       |   7 ++
 4 files changed, 137 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 4346cc7365795..0dcd988ffce1d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4469,8 +4469,14 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (err)
 		goto err_router_join;
 
+	err = mlxsw_sp_netdevice_enslavement_replay(mlxsw_sp, lag_dev, extack);
+	if (err)
+		goto err_replay;
+
 	return 0;
 
+err_replay:
+	mlxsw_sp_router_port_leave_lag(mlxsw_sp_port, lag_dev);
 err_router_join:
 	lag->ref_count--;
 	mlxsw_sp_port->lagged = 0;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 9263a914bcc7b..18d1bcbb3fdfc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -9781,6 +9781,97 @@ mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
 	return err;
 }
 
+struct mlxsw_sp_router_replay_inetaddr_up {
+	struct mlxsw_sp *mlxsw_sp;
+	struct netlink_ext_ack *extack;
+	unsigned int done;
+};
+
+static int mlxsw_sp_router_replay_inetaddr_up(struct net_device *dev,
+					      struct netdev_nested_priv *priv)
+{
+	struct mlxsw_sp_router_replay_inetaddr_up *ctx = priv->data;
+	struct mlxsw_sp_crif *crif;
+	int err;
+
+	if (mlxsw_sp_dev_addr_list_empty(dev))
+		return 0;
+
+	crif = mlxsw_sp_crif_lookup(ctx->mlxsw_sp->router, dev);
+	if (!crif || crif->rif)
+		return 0;
+
+	if (!mlxsw_sp_rif_should_config(crif->rif, dev, NETDEV_UP))
+		return 0;
+
+	err = __mlxsw_sp_inetaddr_event(ctx->mlxsw_sp, dev, NETDEV_UP,
+					false, ctx->extack);
+	if (err)
+		return err;
+
+	ctx->done++;
+	return 0;
+}
+
+static int mlxsw_sp_router_unreplay_inetaddr_up(struct net_device *dev,
+						struct netdev_nested_priv *priv)
+{
+	struct mlxsw_sp_router_replay_inetaddr_up *ctx = priv->data;
+	struct mlxsw_sp_crif *crif;
+
+	if (!ctx->done)
+		return 0;
+
+	if (mlxsw_sp_dev_addr_list_empty(dev))
+		return 0;
+
+	crif = mlxsw_sp_crif_lookup(ctx->mlxsw_sp->router, dev);
+	if (!crif || !crif->rif)
+		return 0;
+
+	/* We are rolling back NETDEV_UP, so ask for that. */
+	if (!mlxsw_sp_rif_should_config(crif->rif, dev, NETDEV_UP))
+		return 0;
+
+	__mlxsw_sp_inetaddr_event(ctx->mlxsw_sp, dev, NETDEV_DOWN, false, NULL);
+
+	ctx->done--;
+	return 0;
+}
+
+int mlxsw_sp_netdevice_enslavement_replay(struct mlxsw_sp *mlxsw_sp,
+					  struct net_device *upper_dev,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_router_replay_inetaddr_up ctx = {
+		.mlxsw_sp = mlxsw_sp,
+		.extack = extack,
+	};
+	struct netdev_nested_priv priv = {
+		.data = &ctx,
+	};
+	int err;
+
+	err = mlxsw_sp_router_replay_inetaddr_up(upper_dev, &priv);
+	if (err)
+		return err;
+
+	err = netdev_walk_all_upper_dev_rcu(upper_dev,
+					    mlxsw_sp_router_replay_inetaddr_up,
+					    &priv);
+	if (err)
+		goto err_replay_up;
+
+	return 0;
+
+err_replay_up:
+	netdev_walk_all_upper_dev_rcu(upper_dev,
+				      mlxsw_sp_router_unreplay_inetaddr_up,
+				      &priv);
+	mlxsw_sp_router_unreplay_inetaddr_up(upper_dev, &priv);
+	return err;
+}
+
 static int
 mlxsw_sp_port_vid_router_join_existing(struct mlxsw_sp_port *mlxsw_sp_port,
 				       u16 vid, struct net_device *dev,
@@ -9857,6 +9948,26 @@ err_router_join_dev:
 	return err;
 }
 
+static void
+__mlxsw_sp_router_port_leave_lag(struct mlxsw_sp_port *mlxsw_sp_port,
+				 struct net_device *lag_dev)
+{
+	u16 default_vid = MLXSW_SP_DEFAULT_VID;
+	struct net_device *upper_dev;
+	struct list_head *iter;
+	u16 vid;
+
+	netdev_for_each_upper_dev_rcu(lag_dev, upper_dev, iter) {
+		if (!is_vlan_dev(upper_dev))
+			continue;
+
+		vid = vlan_dev_vlan_id(upper_dev);
+		mlxsw_sp_port_vid_router_leave(mlxsw_sp_port, vid, upper_dev);
+	}
+
+	mlxsw_sp_port_vid_router_leave(mlxsw_sp_port, default_vid, lag_dev);
+}
+
 int mlxsw_sp_router_port_join_lag(struct mlxsw_sp_port *mlxsw_sp_port,
 				  struct net_device *lag_dev,
 				  struct netlink_ext_ack *extack)
@@ -9870,6 +9981,14 @@ int mlxsw_sp_router_port_join_lag(struct mlxsw_sp_port *mlxsw_sp_port,
 	return err;
 }
 
+void mlxsw_sp_router_port_leave_lag(struct mlxsw_sp_port *mlxsw_sp_port,
+				    struct net_device *lag_dev)
+{
+	mutex_lock(&mlxsw_sp_port->mlxsw_sp->router->lock);
+	__mlxsw_sp_router_port_leave_lag(mlxsw_sp_port, lag_dev);
+	mutex_unlock(&mlxsw_sp_port->mlxsw_sp->router->lock);
+}
+
 static int mlxsw_sp_router_netdevice_event(struct notifier_block *nb,
 					   unsigned long event, void *ptr)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 74242220a0cf0..eed04fbf719f9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -178,5 +178,10 @@ int mlxsw_sp_router_bridge_vlan_add(struct mlxsw_sp *mlxsw_sp,
 int mlxsw_sp_router_port_join_lag(struct mlxsw_sp_port *mlxsw_sp_port,
 				  struct net_device *lag_dev,
 				  struct netlink_ext_ack *extack);
+void mlxsw_sp_router_port_leave_lag(struct mlxsw_sp_port *mlxsw_sp_port,
+				    struct net_device *lag_dev);
+int mlxsw_sp_netdevice_enslavement_replay(struct mlxsw_sp *mlxsw_sp,
+					  struct net_device *upper_dev,
+					  struct netlink_ext_ack *extack);
 
 #endif /* _MLXSW_ROUTER_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 982eae6bd63ec..dffb67c1038e2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2894,8 +2894,15 @@ int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (err)
 		goto err_port_join;
 
+	err = mlxsw_sp_netdevice_enslavement_replay(mlxsw_sp, br_dev, extack);
+	if (err)
+		goto err_replay;
+
 	return 0;
 
+err_replay:
+	bridge_device->ops->port_leave(bridge_device, bridge_port,
+				       mlxsw_sp_port);
 err_port_join:
 	mlxsw_sp_bridge_port_put(mlxsw_sp->bridge, bridge_port);
 	return err;
-- 
GitLab


From 4560cf408ecae4824a2bbdcef83cf91b2db5d268 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:31 +0200
Subject: [PATCH 0307/1806] mlxsw: spectrum_router: Replay IP NETDEV_UP on
 device deslavement

When a netdevice is removed from a bridge or a LAG, and it has an IP
address, it should join the router and gain a RIF. Do that by replaying
address addition event on the netdevice.

When handling deslavement of LAG or its upper from a bridge device, the
replay should be done after all the lowers of the LAG have left the bridge.
Thus these scenarios are handled by passing replay_deslavement of false,
and by invoking, after the lowers have been processed, a new helper,
mlxsw_sp_netdevice_post_lag_event(), which does the per-LAG / -upper
handling, and in particular invokes the replay.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    | 48 ++++++++++++++++---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 23 ++++++++-
 .../ethernet/mellanox/mlxsw/spectrum_router.h |  2 +
 3 files changed, 65 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 0dcd988ffce1d..b955511fe5a2b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4838,15 +4838,20 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
 		if (netif_is_bridge_master(upper_dev)) {
-			if (info->linking)
+			if (info->linking) {
 				err = mlxsw_sp_port_bridge_join(mlxsw_sp_port,
 								lower_dev,
 								upper_dev,
 								extack);
-			else
+			} else {
 				mlxsw_sp_port_bridge_leave(mlxsw_sp_port,
 							   lower_dev,
 							   upper_dev);
+				if (!replay_deslavement)
+					break;
+				mlxsw_sp_netdevice_deslavement_replay(mlxsw_sp,
+								      lower_dev);
+			}
 		} else if (netif_is_lag_master(upper_dev)) {
 			if (info->linking) {
 				err = mlxsw_sp_port_lag_join(mlxsw_sp_port,
@@ -4855,6 +4860,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 				mlxsw_sp_port_lag_col_dist_disable(mlxsw_sp_port);
 				mlxsw_sp_port_lag_leave(mlxsw_sp_port,
 							upper_dev);
+				mlxsw_sp_netdevice_deslavement_replay(mlxsw_sp,
+								      dev);
 			}
 		} else if (netif_is_ovs_master(upper_dev)) {
 			if (info->linking)
@@ -4924,6 +4931,30 @@ static int mlxsw_sp_netdevice_port_event(struct net_device *lower_dev,
 	return 0;
 }
 
+/* Called for LAG or its upper VLAN after the per-LAG-lower processing was done,
+ * to do any per-LAG / per-LAG-upper processing.
+ */
+static int mlxsw_sp_netdevice_post_lag_event(struct net_device *dev,
+					     unsigned long event,
+					     void *ptr)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(dev);
+	struct netdev_notifier_changeupper_info *info = ptr;
+
+	if (!mlxsw_sp)
+		return 0;
+
+	switch (event) {
+	case NETDEV_CHANGEUPPER:
+		if (info->linking)
+			break;
+		if (netif_is_bridge_master(info->upper_dev))
+			mlxsw_sp_netdevice_deslavement_replay(mlxsw_sp, dev);
+		break;
+	}
+	return 0;
+}
+
 static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev,
 					unsigned long event, void *ptr)
 {
@@ -4940,7 +4971,7 @@ static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev,
 		}
 	}
 
-	return 0;
+	return mlxsw_sp_netdevice_post_lag_event(lag_dev, event, ptr);
 }
 
 static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
@@ -4984,15 +5015,20 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
 		if (netif_is_bridge_master(upper_dev)) {
-			if (info->linking)
+			if (info->linking) {
 				err = mlxsw_sp_port_bridge_join(mlxsw_sp_port,
 								vlan_dev,
 								upper_dev,
 								extack);
-			else
+			} else {
 				mlxsw_sp_port_bridge_leave(mlxsw_sp_port,
 							   vlan_dev,
 							   upper_dev);
+				if (!replay_deslavement)
+					break;
+				mlxsw_sp_netdevice_deslavement_replay(mlxsw_sp,
+								      vlan_dev);
+			}
 		} else if (netif_is_macvlan(upper_dev)) {
 			if (!info->linking)
 				mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
@@ -5022,7 +5058,7 @@ static int mlxsw_sp_netdevice_lag_port_vlan_event(struct net_device *vlan_dev,
 		}
 	}
 
-	return 0;
+	return mlxsw_sp_netdevice_post_lag_event(vlan_dev, event, ptr);
 }
 
 static int mlxsw_sp_netdevice_bridge_vlan_event(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 18d1bcbb3fdfc..57f0faac836c9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -9785,12 +9785,14 @@ struct mlxsw_sp_router_replay_inetaddr_up {
 	struct mlxsw_sp *mlxsw_sp;
 	struct netlink_ext_ack *extack;
 	unsigned int done;
+	bool deslavement;
 };
 
 static int mlxsw_sp_router_replay_inetaddr_up(struct net_device *dev,
 					      struct netdev_nested_priv *priv)
 {
 	struct mlxsw_sp_router_replay_inetaddr_up *ctx = priv->data;
+	bool nomaster = ctx->deslavement;
 	struct mlxsw_sp_crif *crif;
 	int err;
 
@@ -9805,7 +9807,7 @@ static int mlxsw_sp_router_replay_inetaddr_up(struct net_device *dev,
 		return 0;
 
 	err = __mlxsw_sp_inetaddr_event(ctx->mlxsw_sp, dev, NETDEV_UP,
-					false, ctx->extack);
+					nomaster, ctx->extack);
 	if (err)
 		return err;
 
@@ -9817,6 +9819,7 @@ static int mlxsw_sp_router_unreplay_inetaddr_up(struct net_device *dev,
 						struct netdev_nested_priv *priv)
 {
 	struct mlxsw_sp_router_replay_inetaddr_up *ctx = priv->data;
+	bool nomaster = ctx->deslavement;
 	struct mlxsw_sp_crif *crif;
 
 	if (!ctx->done)
@@ -9833,7 +9836,8 @@ static int mlxsw_sp_router_unreplay_inetaddr_up(struct net_device *dev,
 	if (!mlxsw_sp_rif_should_config(crif->rif, dev, NETDEV_UP))
 		return 0;
 
-	__mlxsw_sp_inetaddr_event(ctx->mlxsw_sp, dev, NETDEV_DOWN, false, NULL);
+	__mlxsw_sp_inetaddr_event(ctx->mlxsw_sp, dev, NETDEV_DOWN, nomaster,
+				  NULL);
 
 	ctx->done--;
 	return 0;
@@ -9846,6 +9850,7 @@ int mlxsw_sp_netdevice_enslavement_replay(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_router_replay_inetaddr_up ctx = {
 		.mlxsw_sp = mlxsw_sp,
 		.extack = extack,
+		.deslavement = false,
 	};
 	struct netdev_nested_priv priv = {
 		.data = &ctx,
@@ -9872,6 +9877,20 @@ err_replay_up:
 	return err;
 }
 
+void mlxsw_sp_netdevice_deslavement_replay(struct mlxsw_sp *mlxsw_sp,
+					   struct net_device *dev)
+{
+	struct mlxsw_sp_router_replay_inetaddr_up ctx = {
+		.mlxsw_sp = mlxsw_sp,
+		.deslavement = true,
+	};
+	struct netdev_nested_priv priv = {
+		.data = &ctx,
+	};
+
+	mlxsw_sp_router_replay_inetaddr_up(dev, &priv);
+}
+
 static int
 mlxsw_sp_port_vid_router_join_existing(struct mlxsw_sp_port *mlxsw_sp_port,
 				       u16 vid, struct net_device *dev,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index eed04fbf719f9..ed3b628caafe5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -183,5 +183,7 @@ void mlxsw_sp_router_port_leave_lag(struct mlxsw_sp_port *mlxsw_sp_port,
 int mlxsw_sp_netdevice_enslavement_replay(struct mlxsw_sp *mlxsw_sp,
 					  struct net_device *upper_dev,
 					  struct netlink_ext_ack *extack);
+void mlxsw_sp_netdevice_deslavement_replay(struct mlxsw_sp *mlxsw_sp,
+					   struct net_device *dev);
 
 #endif /* _MLXSW_ROUTER_H_*/
-- 
GitLab


From 2c5ffe8d7226283856e258c1531c957edb45226c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 19 Jul 2023 13:01:32 +0200
Subject: [PATCH 0308/1806] mlxsw: spectrum: Permit enslavement to netdevices
 with uppers

Enslaving of front panel ports (and their uppers) to netdevices that
already have uppers is currently forbidden. In the previous patches, a
number of replays have been added. Those ensure that various bits of state,
such as next hops or switchdev objects, are offloaded when they become
relevant due to a mlxsw lower being introduced into the topology.

However the act of actually, for example, enslaving a front-panel port to
a bridge with uppers, has been vetoed so far. In this patch, remove the
vetoes and permit the operation.

mlxsw currently validates creation of "interesting" uppers. Thus creating
VLAN netdevices on top of 802.1ad bridges is forbidden if the bridge has an
mlxsw lower, but permitted in general. This validation code never gets run
when a port is introduced as a lower of an existing netdevice structure.

Thus when enslaving an mlxsw netdevice to netdevices with uppers, invoke
the PRECHANGEUPPER event handler for each netdevice above the one that the
front panel port is being enslaved to. This way the tower of netdevices
above the attachment point is validated.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    | 66 +++++++++++++++++--
 1 file changed, 62 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index b955511fe5a2b..f0f6af3ec7c57 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4735,6 +4735,58 @@ static bool mlxsw_sp_bridge_vxlan_is_valid(struct net_device *br_dev,
 	return true;
 }
 
+static bool mlxsw_sp_netdev_is_master(struct net_device *upper_dev,
+				      struct net_device *dev)
+{
+	return upper_dev == netdev_master_upper_dev_get(dev);
+}
+
+static int __mlxsw_sp_netdevice_event(struct mlxsw_sp *mlxsw_sp,
+				      unsigned long event, void *ptr,
+				      bool process_foreign);
+
+static int mlxsw_sp_netdevice_validate_uppers(struct mlxsw_sp *mlxsw_sp,
+					      struct net_device *dev,
+					      struct netlink_ext_ack *extack)
+{
+	struct net_device *upper_dev;
+	struct list_head *iter;
+	int err;
+
+	netdev_for_each_upper_dev_rcu(dev, upper_dev, iter) {
+		struct netdev_notifier_changeupper_info info = {
+			.info = {
+				.dev = dev,
+				.extack = extack,
+			},
+			.master = mlxsw_sp_netdev_is_master(upper_dev, dev),
+			.upper_dev = upper_dev,
+			.linking = true,
+
+			/* upper_info is relevant for LAG devices. But we would
+			 * only need this if LAG were a valid upper above
+			 * another upper (e.g. a bridge that is a member of a
+			 * LAG), and that is never a valid configuration. So we
+			 * can keep this as NULL.
+			 */
+			.upper_info = NULL,
+		};
+
+		err = __mlxsw_sp_netdevice_event(mlxsw_sp,
+						 NETDEV_PRECHANGEUPPER,
+						 &info, true);
+		if (err)
+			return err;
+
+		err = mlxsw_sp_netdevice_validate_uppers(mlxsw_sp, upper_dev,
+							 extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 					       struct net_device *dev,
 					       unsigned long event, void *ptr,
@@ -4776,8 +4828,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 		    (!netif_is_bridge_master(upper_dev) ||
 		     !mlxsw_sp_bridge_device_is_offloaded(mlxsw_sp,
 							  upper_dev))) {
-			NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a device that already has an upper device is not supported");
-			return -EINVAL;
+			err = mlxsw_sp_netdevice_validate_uppers(mlxsw_sp,
+								 upper_dev,
+								 extack);
+			if (err)
+				return err;
 		}
 		if (netif_is_lag_master(upper_dev) &&
 		    !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev,
@@ -5008,8 +5063,11 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 		    (!netif_is_bridge_master(upper_dev) ||
 		     !mlxsw_sp_bridge_device_is_offloaded(mlxsw_sp,
 							  upper_dev))) {
-			NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a device that already has an upper device is not supported");
-			return -EINVAL;
+			err = mlxsw_sp_netdevice_validate_uppers(mlxsw_sp,
+								 upper_dev,
+								 extack);
+			if (err)
+				return err;
 		}
 		break;
 	case NETDEV_CHANGEUPPER:
-- 
GitLab


From f78dca691287813b6f101b207272786f0cb39c65 Mon Sep 17 00:00:00 2001
From: Naveen Mamindlapalli <naveenm@marvell.com>
Date: Wed, 19 Jul 2023 16:34:40 +0530
Subject: [PATCH 0309/1806] octeontx2-pf: implement transmit schedular
 allocation algorithm

unlike strict priority, where number of classes are limited to max
8, there is no restriction on the number of dwrr child nodes unless
the count increases the max number of child nodes supported.

Hardware expects strict priority transmit schedular indexes mapped
to their priority. This patch adds defines transmit schedular allocation
algorithm such that the above requirement is honored.

Signed-off-by: Naveen Mamindlapalli <naveenm@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/octeontx2/nic/qos.c  | 136 +++++++++++++++++-
 .../net/ethernet/marvell/octeontx2/nic/qos.h  |   6 +
 2 files changed, 136 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index d3a76c5ccda8b..919cd01b7f025 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -19,6 +19,7 @@
 #define OTX2_QOS_CLASS_NONE		0
 #define OTX2_QOS_DEFAULT_PRIO		0xF
 #define OTX2_QOS_INVALID_SQ		0xFFFF
+#define OTX2_QOS_INVALID_TXSCHQ_IDX	0xFFFF
 
 static void otx2_qos_update_tx_netdev_queues(struct otx2_nic *pfvf)
 {
@@ -315,9 +316,14 @@ static void otx2_qos_fill_cfg_tl(struct otx2_qos_node *parent,
 
 	list_for_each_entry(node, &parent->child_list, list) {
 		otx2_qos_fill_cfg_tl(node, cfg);
-		cfg->schq_contig[node->level]++;
 		otx2_qos_fill_cfg_schq(node, cfg);
 	}
+
+	/* Assign the required number of transmit schedular queues under the
+	 * given class
+	 */
+	cfg->schq_contig[parent->level - 1] += parent->child_dwrr_cnt +
+					       parent->max_static_prio + 1;
 }
 
 static void otx2_qos_prepare_txschq_cfg(struct otx2_nic *pfvf,
@@ -401,9 +407,13 @@ static int otx2_qos_add_child_node(struct otx2_qos_node *parent,
 	struct otx2_qos_node *tmp_node;
 	struct list_head *tmp;
 
+	if (node->prio > parent->max_static_prio)
+		parent->max_static_prio = node->prio;
+
 	for (tmp = head->next; tmp != head; tmp = tmp->next) {
 		tmp_node = list_entry(tmp, struct otx2_qos_node, list);
-		if (tmp_node->prio == node->prio)
+		if (tmp_node->prio == node->prio &&
+		    tmp_node->is_static)
 			return -EEXIST;
 		if (tmp_node->prio > node->prio) {
 			list_add_tail(&node->list, tmp);
@@ -476,6 +486,7 @@ otx2_qos_sw_create_leaf_node(struct otx2_nic *pfvf,
 	node->rate = otx2_convert_rate(rate);
 	node->ceil = otx2_convert_rate(ceil);
 	node->prio = prio;
+	node->is_static = true;
 
 	__set_bit(qid, pfvf->qos.qos_sq_bmap);
 
@@ -628,6 +639,21 @@ out:
 	return rc;
 }
 
+static void otx2_qos_free_unused_txschq(struct otx2_nic *pfvf,
+					struct otx2_qos_cfg *cfg)
+{
+	int lvl, idx, schq;
+
+	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
+		for (idx = 0; idx < cfg->schq_contig[lvl]; idx++) {
+			if (!cfg->schq_index_used[lvl][idx]) {
+				schq = cfg->schq_contig_list[lvl][idx];
+				otx2_txschq_free_one(pfvf, lvl, schq);
+			}
+		}
+	}
+}
+
 static void otx2_qos_txschq_fill_cfg_schq(struct otx2_nic *pfvf,
 					  struct otx2_qos_node *node,
 					  struct otx2_qos_cfg *cfg)
@@ -652,9 +678,11 @@ static void otx2_qos_txschq_fill_cfg_tl(struct otx2_nic *pfvf,
 	list_for_each_entry(tmp, &node->child_list, list) {
 		otx2_qos_txschq_fill_cfg_tl(pfvf, tmp, cfg);
 		cnt = cfg->static_node_pos[tmp->level];
-		tmp->schq = cfg->schq_contig_list[tmp->level][cnt];
+		tmp->schq = cfg->schq_contig_list[tmp->level][tmp->txschq_idx];
+		cfg->schq_index_used[tmp->level][tmp->txschq_idx] = true;
 		if (cnt == 0)
-			node->prio_anchor = tmp->schq;
+			node->prio_anchor =
+				cfg->schq_contig_list[tmp->level][0];
 		cfg->static_node_pos[tmp->level]++;
 		otx2_qos_txschq_fill_cfg_schq(pfvf, tmp, cfg);
 	}
@@ -667,9 +695,87 @@ static void otx2_qos_txschq_fill_cfg(struct otx2_nic *pfvf,
 	mutex_lock(&pfvf->qos.qos_lock);
 	otx2_qos_txschq_fill_cfg_tl(pfvf, node, cfg);
 	otx2_qos_txschq_fill_cfg_schq(pfvf, node, cfg);
+	otx2_qos_free_unused_txschq(pfvf, cfg);
 	mutex_unlock(&pfvf->qos.qos_lock);
 }
 
+static void __otx2_qos_assign_base_idx_tl(struct otx2_nic *pfvf,
+					  struct otx2_qos_node *tmp,
+					  unsigned long *child_idx_bmap,
+					  int child_cnt)
+{
+	int idx;
+
+	if (tmp->txschq_idx != OTX2_QOS_INVALID_TXSCHQ_IDX)
+		return;
+
+	/* assign static nodes 1:1 prio mapping first, then remaining nodes */
+	for (idx = 0; idx < child_cnt; idx++) {
+		if (tmp->is_static && tmp->prio == idx &&
+		    !test_bit(idx, child_idx_bmap)) {
+			tmp->txschq_idx = idx;
+			set_bit(idx, child_idx_bmap);
+			return;
+		} else if (!tmp->is_static && idx >= tmp->prio &&
+			   !test_bit(idx, child_idx_bmap)) {
+			tmp->txschq_idx = idx;
+			set_bit(idx, child_idx_bmap);
+			return;
+		}
+	}
+}
+
+static int otx2_qos_assign_base_idx_tl(struct otx2_nic *pfvf,
+				       struct otx2_qos_node *node)
+{
+	unsigned long *child_idx_bmap;
+	struct otx2_qos_node *tmp;
+	int child_cnt;
+
+	list_for_each_entry(tmp, &node->child_list, list)
+		tmp->txschq_idx = OTX2_QOS_INVALID_TXSCHQ_IDX;
+
+	/* allocate child index array */
+	child_cnt = node->child_dwrr_cnt + node->max_static_prio + 1;
+	child_idx_bmap = kcalloc(BITS_TO_LONGS(child_cnt),
+				 sizeof(unsigned long),
+				 GFP_KERNEL);
+	if (!child_idx_bmap)
+		return -ENOMEM;
+
+	list_for_each_entry(tmp, &node->child_list, list)
+		otx2_qos_assign_base_idx_tl(pfvf, tmp);
+
+	/* assign base index of static priority children first */
+	list_for_each_entry(tmp, &node->child_list, list) {
+		if (!tmp->is_static)
+			continue;
+		__otx2_qos_assign_base_idx_tl(pfvf, tmp, child_idx_bmap,
+					      child_cnt);
+	}
+
+	/* assign base index of dwrr priority children */
+	list_for_each_entry(tmp, &node->child_list, list)
+		__otx2_qos_assign_base_idx_tl(pfvf, tmp, child_idx_bmap,
+					      child_cnt);
+
+	kfree(child_idx_bmap);
+
+	return 0;
+}
+
+static int otx2_qos_assign_base_idx(struct otx2_nic *pfvf,
+				    struct otx2_qos_node *node)
+{
+	int ret = 0;
+
+	mutex_lock(&pfvf->qos.qos_lock);
+	ret = otx2_qos_assign_base_idx_tl(pfvf, node);
+	mutex_unlock(&pfvf->qos.qos_lock);
+
+	return ret;
+}
+
 static int otx2_qos_txschq_push_cfg_schq(struct otx2_nic *pfvf,
 					 struct otx2_qos_node *node,
 					 struct otx2_qos_cfg *cfg)
@@ -761,8 +867,10 @@ static void otx2_qos_free_cfg(struct otx2_nic *pfvf, struct otx2_qos_cfg *cfg)
 
 	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
 		for (idx = 0; idx < cfg->schq_contig[lvl]; idx++) {
-			schq = cfg->schq_contig_list[lvl][idx];
-			otx2_txschq_free_one(pfvf, lvl, schq);
+			if (cfg->schq_index_used[lvl][idx]) {
+				schq = cfg->schq_contig_list[lvl][idx];
+				otx2_txschq_free_one(pfvf, lvl, schq);
+			}
 		}
 	}
 }
@@ -838,6 +946,10 @@ static int otx2_qos_push_txschq_cfg(struct otx2_nic *pfvf,
 	if (ret)
 		return -ENOSPC;
 
+	ret = otx2_qos_assign_base_idx(pfvf, node);
+	if (ret)
+		return -ENOMEM;
+
 	if (!(pfvf->netdev->flags & IFF_UP)) {
 		otx2_qos_txschq_fill_cfg(pfvf, node, cfg);
 		return 0;
@@ -995,6 +1107,7 @@ static int otx2_qos_leaf_alloc_queue(struct otx2_nic *pfvf, u16 classid,
 	if (ret)
 		goto out;
 
+	parent->child_static_cnt++;
 	set_bit(prio, parent->prio_bmap);
 
 	/* read current txschq configuration */
@@ -1067,6 +1180,7 @@ free_node:
 free_old_cfg:
 	kfree(old_cfg);
 reset_prio:
+	parent->child_static_cnt--;
 	clear_bit(prio, parent->prio_bmap);
 out:
 	return ret;
@@ -1105,6 +1219,7 @@ static int otx2_qos_leaf_to_inner(struct otx2_nic *pfvf, u16 classid,
 		goto out;
 	}
 
+	node->child_static_cnt++;
 	set_bit(prio, node->prio_bmap);
 
 	/* store the qid to assign to leaf node */
@@ -1178,6 +1293,7 @@ free_node:
 free_old_cfg:
 	kfree(old_cfg);
 reset_prio:
+	node->child_static_cnt--;
 	clear_bit(prio, node->prio_bmap);
 out:
 	return ret;
@@ -1207,6 +1323,10 @@ static int otx2_qos_leaf_del(struct otx2_nic *pfvf, u16 *classid,
 	otx2_qos_destroy_node(pfvf, node);
 	pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ;
 
+	parent->child_static_cnt--;
+	if (!parent->child_static_cnt)
+		parent->max_static_prio = 0;
+
 	clear_bit(prio, parent->prio_bmap);
 
 	return 0;
@@ -1245,6 +1365,10 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force
 	otx2_qos_destroy_node(pfvf, node);
 	pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ;
 
+	parent->child_static_cnt--;
+	if (!parent->child_static_cnt)
+		parent->max_static_prio = 0;
+
 	clear_bit(prio, parent->prio_bmap);
 
 	/* create downstream txschq entries to parent */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.h b/drivers/net/ethernet/marvell/octeontx2/nic/qos.h
index 19773284be27a..faa7c24675d1b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.h
@@ -35,6 +35,7 @@ struct otx2_qos_cfg {
 	int dwrr_node_pos[NIX_TXSCH_LVL_CNT];
 	u16 schq_contig_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
 	u16 schq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
+	bool schq_index_used[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
 };
 
 struct otx2_qos {
@@ -62,7 +63,12 @@ struct otx2_qos_node {
 	u16 schq; /* hw txschq */
 	u16 qid;
 	u16 prio_anchor;
+	u16 max_static_prio;
+	u16 child_dwrr_cnt;
+	u16 child_static_cnt;
+	u16 txschq_idx;			/* txschq allocation index */
 	u8 level;
+	bool is_static;
 };
 
 
-- 
GitLab


From 9fe63d5f1da939855bdfaebfd9e95c96938b6411 Mon Sep 17 00:00:00 2001
From: Naveen Mamindlapalli <naveenm@marvell.com>
Date: Wed, 19 Jul 2023 16:34:41 +0530
Subject: [PATCH 0310/1806] sch_htb: Allow HTB quantum parameter in offload
 mode

The current implementation of HTB offload returns the EINVAL error for
quantum parameter. This patch removes the error returning checks for
'quantum' parameter and populates its value to tc_htb_qopt_offload
structure such that driver can use the same.

Add quantum parameter check in mlx5 driver, as mlx5 devices are not capable
of supporting the quantum parameter when htb offload is used. Report error
if quantum parameter is set to a non-default value.

Signed-off-by: Naveen Mamindlapalli <naveenm@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/qos.c | 4 ++--
 include/net/pkt_cls.h                            | 1 +
 net/sched/sch_htb.c                              | 7 +++----
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index 1874c2f0587f4..244bc15a42abf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -379,9 +379,9 @@ int mlx5e_htb_setup_tc(struct mlx5e_priv *priv, struct tc_htb_qopt_offload *htb_
 	if (!htb && htb_qopt->command != TC_HTB_CREATE)
 		return -EINVAL;
 
-	if (htb_qopt->prio) {
+	if (htb_qopt->prio || htb_qopt->quantum) {
 		NL_SET_ERR_MSG_MOD(htb_qopt->extack,
-				   "prio parameter is not supported by device with HTB offload enabled.");
+				   "prio and quantum parameters are not supported by device with HTB offload enabled.");
 		return -EOPNOTSUPP;
 	}
 
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a2ea45c7b53eb..139cd09828af2 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -866,6 +866,7 @@ struct tc_htb_qopt_offload {
 	u32 parent_classid;
 	u16 classid;
 	u16 qid;
+	u32 quantum;
 	u64 rate;
 	u64 ceil;
 	u8 prio;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 325c29041c7d6..333800a7d4ebe 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1810,10 +1810,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			NL_SET_ERR_MSG(extack, "HTB offload doesn't support the mpu parameter");
 			goto failure;
 		}
-		if (hopt->quantum) {
-			NL_SET_ERR_MSG(extack, "HTB offload doesn't support the quantum parameter");
-			goto failure;
-		}
 	}
 
 	/* Keeping backward compatible with rate_table based iproute2 tc */
@@ -1910,6 +1906,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 				.rate = max_t(u64, hopt->rate.rate, rate64),
 				.ceil = max_t(u64, hopt->ceil.rate, ceil64),
 				.prio = hopt->prio,
+				.quantum = hopt->quantum,
 				.extack = extack,
 			};
 			err = htb_offload(dev, &offload_opt);
@@ -1931,6 +1928,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 				.rate = max_t(u64, hopt->rate.rate, rate64),
 				.ceil = max_t(u64, hopt->ceil.rate, ceil64),
 				.prio = hopt->prio,
+				.quantum = hopt->quantum,
 				.extack = extack,
 			};
 			err = htb_offload(dev, &offload_opt);
@@ -2017,6 +2015,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 				.rate = max_t(u64, hopt->rate.rate, rate64),
 				.ceil = max_t(u64, hopt->ceil.rate, ceil64),
 				.prio = hopt->prio,
+				.quantum = hopt->quantum,
 				.extack = extack,
 			};
 			err = htb_offload(dev, &offload_opt);
-- 
GitLab


From 47a9656f168a4b76a1e069ed8a67924ea8c1ac43 Mon Sep 17 00:00:00 2001
From: Naveen Mamindlapalli <naveenm@marvell.com>
Date: Wed, 19 Jul 2023 16:34:42 +0530
Subject: [PATCH 0311/1806] octeontx2-pf: htb offload support for Round Robin
 scheduling

When multiple traffic flows reach Transmit level with the same
priority, with Round robin scheduling traffic flow with the highest
quantum value is picked. With this support, the user can add multiple
classes with the same priority and different quantum. This patch
does necessary changes to support the same.

Signed-off-by: Naveen Mamindlapalli <naveenm@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../marvell/octeontx2/nic/otx2_common.c       |   1 +
 .../marvell/octeontx2/nic/otx2_common.h       |   1 +
 .../net/ethernet/marvell/octeontx2/nic/qos.c  | 280 +++++++++++++++---
 .../net/ethernet/marvell/octeontx2/nic/qos.h  |   5 +-
 4 files changed, 247 insertions(+), 40 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 77c8f650f7ac1..8cdd92dd97628 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -774,6 +774,7 @@ int otx2_txsch_alloc(struct otx2_nic *pfvf)
 				rsp->schq_list[lvl][schq];
 
 	pfvf->hw.txschq_link_cfg_lvl = rsp->link_cfg_lvl;
+	pfvf->hw.txschq_aggr_lvl_rr_prio = rsp->aggr_lvl_rr_prio;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index ba8091131ec08..37d792f188093 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -224,6 +224,7 @@ struct otx2_hw {
 
 	/* NIX */
 	u8			txschq_link_cfg_lvl;
+	u8			txschq_aggr_lvl_rr_prio;
 	u16			txschq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
 	u16			matchall_ipolicer;
 	u32			dwrr_mtu;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index 919cd01b7f025..1e77bbf5d22a1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -20,6 +20,8 @@
 #define OTX2_QOS_DEFAULT_PRIO		0xF
 #define OTX2_QOS_INVALID_SQ		0xFFFF
 #define OTX2_QOS_INVALID_TXSCHQ_IDX	0xFFFF
+#define CN10K_MAX_RR_WEIGHT		GENMASK_ULL(13, 0)
+#define OTX2_MAX_RR_QUANTUM		GENMASK_ULL(23, 0)
 
 static void otx2_qos_update_tx_netdev_queues(struct otx2_nic *pfvf)
 {
@@ -66,11 +68,24 @@ static void otx2_qos_get_regaddr(struct otx2_qos_node *node,
 	}
 }
 
+static int otx2_qos_quantum_to_dwrr_weight(struct otx2_nic *pfvf, u32 quantum)
+{
+	u32 weight;
+
+	weight = quantum / pfvf->hw.dwrr_mtu;
+	if (quantum % pfvf->hw.dwrr_mtu)
+		weight += 1;
+
+	return weight;
+}
+
 static void otx2_config_sched_shaping(struct otx2_nic *pfvf,
 				      struct otx2_qos_node *node,
 				      struct nix_txschq_config *cfg,
 				      int *num_regs)
 {
+	u32 rr_weight;
+	u32 quantum;
 	u64 maxrate;
 
 	otx2_qos_get_regaddr(node, cfg, *num_regs);
@@ -87,8 +102,17 @@ static void otx2_config_sched_shaping(struct otx2_nic *pfvf,
 		return;
 	}
 
-	/* configure priority  */
-	cfg->regval[*num_regs] = (node->schq - node->parent->prio_anchor) << 24;
+	/* configure priority/quantum  */
+	if (node->is_static) {
+		cfg->regval[*num_regs] =
+			(node->schq - node->parent->prio_anchor) << 24;
+	} else {
+		quantum = node->quantum ?
+			  node->quantum : pfvf->tx_max_pktlen;
+		rr_weight = otx2_qos_quantum_to_dwrr_weight(pfvf, quantum);
+		cfg->regval[*num_regs] = node->parent->child_dwrr_prio << 24 |
+					 rr_weight;
+	}
 	(*num_regs)++;
 
 	/* configure PIR */
@@ -196,9 +220,8 @@ static int otx2_qos_txschq_set_parent_topology(struct otx2_nic *pfvf,
 		cfg->reg[0] = NIX_AF_TL1X_TOPOLOGY(parent->schq);
 
 	cfg->regval[0] = (u64)parent->prio_anchor << 32;
-	if (parent->level == NIX_TXSCH_LVL_TL1)
-		cfg->regval[0] |= (u64)TXSCH_TL1_DFLT_RR_PRIO << 1;
-
+	cfg->regval[0] |= ((parent->child_dwrr_prio != OTX2_QOS_DEFAULT_PRIO) ?
+			    parent->child_dwrr_prio : 0)  << 1;
 	cfg->num_regs++;
 
 	rc = otx2_sync_mbox_msg(&pfvf->mbox);
@@ -384,10 +407,12 @@ otx2_qos_alloc_root(struct otx2_nic *pfvf)
 		return ERR_PTR(-ENOMEM);
 
 	node->parent = NULL;
-	if (!is_otx2_vf(pfvf->pcifunc))
+	if (!is_otx2_vf(pfvf->pcifunc)) {
 		node->level = NIX_TXSCH_LVL_TL1;
-	else
+	} else {
 		node->level = NIX_TXSCH_LVL_TL2;
+		node->child_dwrr_prio = OTX2_QOS_DEFAULT_PRIO;
+	}
 
 	WRITE_ONCE(node->qid, OTX2_QOS_QID_INNER);
 	node->classid = OTX2_QOS_ROOT_CLASSID;
@@ -444,6 +469,10 @@ static int otx2_qos_alloc_txschq_node(struct otx2_nic *pfvf,
 		txschq_node->rate = 0;
 		txschq_node->ceil = 0;
 		txschq_node->prio = 0;
+		txschq_node->quantum = 0;
+		txschq_node->is_static = true;
+		txschq_node->child_dwrr_prio = OTX2_QOS_DEFAULT_PRIO;
+		txschq_node->txschq_idx = OTX2_QOS_INVALID_TXSCHQ_IDX;
 
 		mutex_lock(&pfvf->qos.qos_lock);
 		list_add_tail(&txschq_node->list, &node->child_schq_list);
@@ -469,7 +498,7 @@ static struct otx2_qos_node *
 otx2_qos_sw_create_leaf_node(struct otx2_nic *pfvf,
 			     struct otx2_qos_node *parent,
 			     u16 classid, u32 prio, u64 rate, u64 ceil,
-			     u16 qid)
+			     u32 quantum, u16 qid, bool static_cfg)
 {
 	struct otx2_qos_node *node;
 	int err;
@@ -486,7 +515,10 @@ otx2_qos_sw_create_leaf_node(struct otx2_nic *pfvf,
 	node->rate = otx2_convert_rate(rate);
 	node->ceil = otx2_convert_rate(ceil);
 	node->prio = prio;
-	node->is_static = true;
+	node->quantum = quantum;
+	node->is_static = static_cfg;
+	node->child_dwrr_prio = OTX2_QOS_DEFAULT_PRIO;
+	node->txschq_idx = OTX2_QOS_INVALID_TXSCHQ_IDX;
 
 	__set_bit(qid, pfvf->qos.qos_sq_bmap);
 
@@ -633,6 +665,7 @@ static int otx2_qos_txschq_alloc(struct otx2_nic *pfvf,
 	}
 
 	pfvf->qos.link_cfg_lvl = rsp->link_cfg_lvl;
+	pfvf->hw.txschq_aggr_lvl_rr_prio = rsp->aggr_lvl_rr_prio;
 
 out:
 	mutex_unlock(&mbox->lock);
@@ -1006,6 +1039,13 @@ static int otx2_qos_root_add(struct otx2_nic *pfvf, u16 htb_maj_id, u16 htb_defc
 		goto free_root_node;
 	}
 
+	/* Update TL1 RR PRIO */
+	if (root->level == NIX_TXSCH_LVL_TL1) {
+		root->child_dwrr_prio = pfvf->hw.txschq_aggr_lvl_rr_prio;
+		netdev_dbg(pfvf->netdev,
+			   "TL1 DWRR Priority %d\n", root->child_dwrr_prio);
+	}
+
 	if (!(pfvf->netdev->flags & IFF_UP) ||
 	    root->level == NIX_TXSCH_LVL_TL1) {
 		root->schq = new_cfg->schq_list[root->level][0];
@@ -1052,37 +1092,126 @@ static int otx2_qos_root_destroy(struct otx2_nic *pfvf)
 	return 0;
 }
 
+static int otx2_qos_validate_quantum(struct otx2_nic *pfvf, u32 quantum)
+{
+	u32 rr_weight = otx2_qos_quantum_to_dwrr_weight(pfvf, quantum);
+	int err = 0;
+
+	/* Max Round robin weight supported by octeontx2 and CN10K
+	 * is different. Validate accordingly
+	 */
+	if (is_dev_otx2(pfvf->pdev))
+		err = (rr_weight > OTX2_MAX_RR_QUANTUM) ? -EINVAL : 0;
+	else if	(rr_weight > CN10K_MAX_RR_WEIGHT)
+		err = -EINVAL;
+
+	return err;
+}
+
+static int otx2_qos_validate_dwrr_cfg(struct otx2_qos_node *parent,
+				      struct netlink_ext_ack *extack,
+				      struct otx2_nic *pfvf,
+				      u64 prio, u64 quantum)
+{
+	int err;
+
+	err = otx2_qos_validate_quantum(pfvf, quantum);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported quantum value");
+		return err;
+	}
+
+	if (parent->child_dwrr_prio == OTX2_QOS_DEFAULT_PRIO) {
+		parent->child_dwrr_prio = prio;
+	} else if (prio != parent->child_dwrr_prio) {
+		NL_SET_ERR_MSG_MOD(extack, "Only one DWRR group is allowed");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static int otx2_qos_validate_configuration(struct otx2_qos_node *parent,
 					   struct netlink_ext_ack *extack,
 					   struct otx2_nic *pfvf,
-					   u64 prio)
+					   u64 prio, bool static_cfg)
 {
-	if (test_bit(prio, parent->prio_bmap)) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Static priority child with same priority exists");
+	if (prio == parent->child_dwrr_prio && static_cfg) {
+		NL_SET_ERR_MSG_MOD(extack, "DWRR child group with same priority exists");
 		return -EEXIST;
 	}
 
-	if (prio == TXSCH_TL1_DFLT_RR_PRIO) {
+	if (static_cfg && test_bit(prio, parent->prio_bmap)) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Priority is reserved for Round Robin");
-		return -EINVAL;
+				   "Static priority child with same priority exists");
+		return -EEXIST;
 	}
 
 	return 0;
 }
 
+static void otx2_reset_dwrr_prio(struct otx2_qos_node *parent, u64 prio)
+{
+	/* For PF, root node dwrr priority is static */
+	if (parent->level == NIX_TXSCH_LVL_TL1)
+		return;
+
+	if (parent->child_dwrr_prio != OTX2_QOS_DEFAULT_PRIO) {
+		parent->child_dwrr_prio = OTX2_QOS_DEFAULT_PRIO;
+		clear_bit(prio, parent->prio_bmap);
+	}
+}
+
+static bool is_qos_node_dwrr(struct otx2_qos_node *parent,
+			     struct otx2_nic *pfvf,
+			     u64 prio)
+{
+	struct otx2_qos_node *node;
+	bool ret = false;
+
+	if (parent->child_dwrr_prio == prio)
+		return true;
+
+	mutex_lock(&pfvf->qos.qos_lock);
+	list_for_each_entry(node, &parent->child_list, list) {
+		if (prio == node->prio) {
+			if (parent->child_dwrr_prio != OTX2_QOS_DEFAULT_PRIO &&
+			    parent->child_dwrr_prio != prio)
+				continue;
+
+			if (otx2_qos_validate_quantum(pfvf, node->quantum)) {
+				netdev_err(pfvf->netdev,
+					   "Unsupported quantum value for existing classid=0x%x quantum=%d prio=%d",
+					    node->classid, node->quantum,
+					    node->prio);
+				break;
+			}
+			/* mark old node as dwrr */
+			node->is_static = false;
+			parent->child_dwrr_cnt++;
+			parent->child_static_cnt--;
+			ret = true;
+			break;
+		}
+	}
+	mutex_unlock(&pfvf->qos.qos_lock);
+
+	return ret;
+}
+
 static int otx2_qos_leaf_alloc_queue(struct otx2_nic *pfvf, u16 classid,
 				     u32 parent_classid, u64 rate, u64 ceil,
-				     u64 prio, struct netlink_ext_ack *extack)
+				     u64 prio, u32 quantum,
+				     struct netlink_ext_ack *extack)
 {
 	struct otx2_qos_cfg *old_cfg, *new_cfg;
 	struct otx2_qos_node *node, *parent;
 	int qid, ret, err;
+	bool static_cfg;
 
 	netdev_dbg(pfvf->netdev,
-		   "TC_HTB_LEAF_ALLOC_QUEUE: classid=0x%x parent_classid=0x%x rate=%lld ceil=%lld prio=%lld\n",
-		   classid, parent_classid, rate, ceil, prio);
+		   "TC_HTB_LEAF_ALLOC_QUEUE: classid=0x%x parent_classid=0x%x rate=%lld ceil=%lld prio=%lld quantum=%d\n",
+		   classid, parent_classid, rate, ceil, prio, quantum);
 
 	if (prio > OTX2_QOS_MAX_PRIO) {
 		NL_SET_ERR_MSG_MOD(extack, "Valid priority range 0 to 7");
@@ -1090,6 +1219,12 @@ static int otx2_qos_leaf_alloc_queue(struct otx2_nic *pfvf, u16 classid,
 		goto out;
 	}
 
+	if (!quantum || quantum > INT_MAX) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid quantum, range 1 - 2147483647 bytes");
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
 	/* get parent node */
 	parent = otx2_sw_node_find(pfvf, parent_classid);
 	if (!parent) {
@@ -1103,11 +1238,24 @@ static int otx2_qos_leaf_alloc_queue(struct otx2_nic *pfvf, u16 classid,
 		goto out;
 	}
 
-	ret = otx2_qos_validate_configuration(parent, extack, pfvf, prio);
+	static_cfg = !is_qos_node_dwrr(parent, pfvf, prio);
+	ret = otx2_qos_validate_configuration(parent, extack, pfvf, prio,
+					      static_cfg);
 	if (ret)
 		goto out;
 
-	parent->child_static_cnt++;
+	if (!static_cfg) {
+		ret = otx2_qos_validate_dwrr_cfg(parent, extack, pfvf, prio,
+						 quantum);
+		if (ret)
+			goto out;
+	}
+
+	if (static_cfg)
+		parent->child_static_cnt++;
+	else
+		parent->child_dwrr_cnt++;
+
 	set_bit(prio, parent->prio_bmap);
 
 	/* read current txschq configuration */
@@ -1132,7 +1280,7 @@ static int otx2_qos_leaf_alloc_queue(struct otx2_nic *pfvf, u16 classid,
 
 	/* allocate and initialize a new child node */
 	node = otx2_qos_sw_create_leaf_node(pfvf, parent, classid, prio, rate,
-					    ceil, qid);
+					    ceil, quantum, qid, static_cfg);
 	if (IS_ERR(node)) {
 		NL_SET_ERR_MSG_MOD(extack, "Unable to allocate leaf node");
 		ret = PTR_ERR(node);
@@ -1180,7 +1328,11 @@ free_node:
 free_old_cfg:
 	kfree(old_cfg);
 reset_prio:
-	parent->child_static_cnt--;
+	if (static_cfg)
+		parent->child_static_cnt--;
+	else
+		parent->child_dwrr_cnt--;
+
 	clear_bit(prio, parent->prio_bmap);
 out:
 	return ret;
@@ -1188,10 +1340,11 @@ out:
 
 static int otx2_qos_leaf_to_inner(struct otx2_nic *pfvf, u16 classid,
 				  u16 child_classid, u64 rate, u64 ceil, u64 prio,
-				  struct netlink_ext_ack *extack)
+				  u32 quantum, struct netlink_ext_ack *extack)
 {
 	struct otx2_qos_cfg *old_cfg, *new_cfg;
 	struct otx2_qos_node *node, *child;
+	bool static_cfg;
 	int ret, err;
 	u16 qid;
 
@@ -1205,6 +1358,12 @@ static int otx2_qos_leaf_to_inner(struct otx2_nic *pfvf, u16 classid,
 		goto out;
 	}
 
+	if (!quantum || quantum > INT_MAX) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid quantum, range 1 - 2147483647 bytes");
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
 	/* find node related to classid */
 	node = otx2_sw_node_find(pfvf, classid);
 	if (!node) {
@@ -1219,7 +1378,19 @@ static int otx2_qos_leaf_to_inner(struct otx2_nic *pfvf, u16 classid,
 		goto out;
 	}
 
-	node->child_static_cnt++;
+	static_cfg = !is_qos_node_dwrr(node, pfvf, prio);
+	if (!static_cfg) {
+		ret = otx2_qos_validate_dwrr_cfg(node, extack, pfvf, prio,
+						 quantum);
+		if (ret)
+			goto out;
+	}
+
+	if (static_cfg)
+		node->child_static_cnt++;
+	else
+		node->child_dwrr_cnt++;
+
 	set_bit(prio, node->prio_bmap);
 
 	/* store the qid to assign to leaf node */
@@ -1242,7 +1413,8 @@ static int otx2_qos_leaf_to_inner(struct otx2_nic *pfvf, u16 classid,
 
 	/* allocate and initialize a new child node */
 	child = otx2_qos_sw_create_leaf_node(pfvf, node, child_classid,
-					     prio, rate, ceil, qid);
+					     prio, rate, ceil, quantum,
+					     qid, static_cfg);
 	if (IS_ERR(child)) {
 		NL_SET_ERR_MSG_MOD(extack, "Unable to allocate leaf node");
 		ret = PTR_ERR(child);
@@ -1293,7 +1465,10 @@ free_node:
 free_old_cfg:
 	kfree(old_cfg);
 reset_prio:
-	node->child_static_cnt--;
+	if (static_cfg)
+		node->child_static_cnt--;
+	else
+		node->child_dwrr_cnt--;
 	clear_bit(prio, node->prio_bmap);
 out:
 	return ret;
@@ -1303,6 +1478,7 @@ static int otx2_qos_leaf_del(struct otx2_nic *pfvf, u16 *classid,
 			     struct netlink_ext_ack *extack)
 {
 	struct otx2_qos_node *node, *parent;
+	int dwrr_del_node = false;
 	u64 prio;
 	u16 qid;
 
@@ -1318,17 +1494,28 @@ static int otx2_qos_leaf_del(struct otx2_nic *pfvf, u16 *classid,
 	prio   = node->prio;
 	qid    = node->qid;
 
+	if (!node->is_static)
+		dwrr_del_node = true;
+
 	otx2_qos_disable_sq(pfvf, node->qid);
 
 	otx2_qos_destroy_node(pfvf, node);
 	pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ;
 
-	parent->child_static_cnt--;
+	if (dwrr_del_node) {
+		parent->child_dwrr_cnt--;
+	} else {
+		parent->child_static_cnt--;
+		clear_bit(prio, parent->prio_bmap);
+	}
+
+	/* Reset DWRR priority if all dwrr nodes are deleted */
+	if (!parent->child_dwrr_cnt)
+		otx2_reset_dwrr_prio(parent, prio);
+
 	if (!parent->child_static_cnt)
 		parent->max_static_prio = 0;
 
-	clear_bit(prio, parent->prio_bmap);
-
 	return 0;
 }
 
@@ -1337,6 +1524,7 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force
 {
 	struct otx2_qos_node *node, *parent;
 	struct otx2_qos_cfg *new_cfg;
+	int dwrr_del_node = false;
 	u64 prio;
 	int err;
 	u16 qid;
@@ -1361,16 +1549,27 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force
 		return -ENOENT;
 	}
 
+	if (!node->is_static)
+		dwrr_del_node = true;
+
 	/* destroy the leaf node */
 	otx2_qos_destroy_node(pfvf, node);
 	pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ;
 
-	parent->child_static_cnt--;
+	if (dwrr_del_node) {
+		parent->child_dwrr_cnt--;
+	} else {
+		parent->child_static_cnt--;
+		clear_bit(prio, parent->prio_bmap);
+	}
+
+	/* Reset DWRR priority if all dwrr nodes are deleted */
+	if (!parent->child_dwrr_cnt)
+		otx2_reset_dwrr_prio(parent, prio);
+
 	if (!parent->child_static_cnt)
 		parent->max_static_prio = 0;
 
-	clear_bit(prio, parent->prio_bmap);
-
 	/* create downstream txschq entries to parent */
 	err = otx2_qos_alloc_txschq_node(pfvf, parent);
 	if (err) {
@@ -1422,10 +1621,12 @@ void otx2_qos_config_txschq(struct otx2_nic *pfvf)
 	if (!root)
 		return;
 
-	err = otx2_qos_txschq_config(pfvf, root);
-	if (err) {
-		netdev_err(pfvf->netdev, "Error update txschq configuration\n");
-		goto root_destroy;
+	if (root->level != NIX_TXSCH_LVL_TL1) {
+		err = otx2_qos_txschq_config(pfvf, root);
+		if (err) {
+			netdev_err(pfvf->netdev, "Error update txschq configuration\n");
+			goto root_destroy;
+		}
 	}
 
 	err = otx2_qos_txschq_push_cfg_tl(pfvf, root, NULL);
@@ -1458,7 +1659,8 @@ int otx2_setup_tc_htb(struct net_device *ndev, struct tc_htb_qopt_offload *htb)
 		res = otx2_qos_leaf_alloc_queue(pfvf, htb->classid,
 						htb->parent_classid,
 						htb->rate, htb->ceil,
-						htb->prio, htb->extack);
+						htb->prio, htb->quantum,
+						htb->extack);
 		if (res < 0)
 			return res;
 		htb->qid = res;
@@ -1467,7 +1669,7 @@ int otx2_setup_tc_htb(struct net_device *ndev, struct tc_htb_qopt_offload *htb)
 		return otx2_qos_leaf_to_inner(pfvf, htb->parent_classid,
 					      htb->classid, htb->rate,
 					      htb->ceil, htb->prio,
-					      htb->extack);
+					      htb->quantum, htb->extack);
 	case TC_HTB_LEAF_DEL:
 		return otx2_qos_leaf_del(pfvf, &htb->classid, htb->extack);
 	case TC_HTB_LEAF_DEL_LAST:
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.h b/drivers/net/ethernet/marvell/octeontx2/nic/qos.h
index faa7c24675d1b..221bd0438f603 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.h
@@ -60,12 +60,15 @@ struct otx2_qos_node {
 	u64 ceil;
 	u32 classid;
 	u32 prio;
-	u16 schq; /* hw txschq */
+	u32 quantum;
+	/* hw txschq */
+	u16 schq;
 	u16 qid;
 	u16 prio_anchor;
 	u16 max_static_prio;
 	u16 child_dwrr_cnt;
 	u16 child_static_cnt;
+	u16 child_dwrr_prio;
 	u16 txschq_idx;			/* txschq allocation index */
 	u8 level;
 	bool is_static;
-- 
GitLab


From 6f71051ffbdb914fc3688ba9b13baba4142630a5 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Wed, 19 Jul 2023 16:34:43 +0530
Subject: [PATCH 0312/1806] docs: octeontx2: extend documentation for Round
 Robin scheduling

Add example tc-htb commands for Round robin scheduling

Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../device_drivers/ethernet/marvell/octeontx2.rst         | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
index bfd233cfac352..1e196cb9ce254 100644
--- a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
+++ b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
@@ -332,3 +332,11 @@ Setup HTB offload
         # tc class add dev <interface> parent 1: classid 1:1 htb rate 10Gbit prio 1
 
         # tc class add dev <interface> parent 1: classid 1:2 htb rate 10Gbit prio 7
+
+4. Create tc classes with same priorities and different quantum::
+
+        # tc class add dev <interface> parent 1: classid 1:1 htb rate 10Gbit prio 2 quantum 409600
+
+        # tc class add dev <interface> parent 1: classid 1:2 htb rate 10Gbit prio 2 quantum 188416
+
+        # tc class add dev <interface> parent 1: classid 1:3 htb rate 10Gbit prio 2 quantum 32768
-- 
GitLab


From 070e8bd31b288c3aa3f965778417708c8bfedb06 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 20 Jul 2023 17:11:07 +0200
Subject: [PATCH 0313/1806] MAINTAINERS: net: fix sort order

Linus seems to like the MAINTAINERS file sorted, see
c192ac735768 ("MAINTAINERS 2: Electric Boogaloo").

Since this is currently not the case, restore the sort order.

Fixes: 3abf3d15ffff ("MAINTAINERS: ASP 2.0 Ethernet driver maintainers")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Acked-by: Justin Chen <justin.chen@broadcom.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20230720151107.679668-1-mkl@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 019b8017ab3c3..d0553ad37865e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3838,6 +3838,15 @@ S:	Maintained
 F:	kernel/bpf/stackmap.c
 F:	kernel/trace/bpf_trace.c
 
+BROADCOM ASP 2.0 ETHERNET DRIVER
+M:	Justin Chen <justin.chen@broadcom.com>
+M:	Florian Fainelli <florian.fainelli@broadcom.com>
+L:	bcm-kernel-feedback-list@broadcom.com
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml
+F:	drivers/net/ethernet/broadcom/asp2/
+
 BROADCOM B44 10/100 ETHERNET DRIVER
 M:	Michael Chan <michael.chan@broadcom.com>
 L:	netdev@vger.kernel.org
@@ -4155,15 +4164,6 @@ F:	drivers/net/mdio/mdio-bcm-unimac.c
 F:	include/linux/platform_data/bcmgenet.h
 F:	include/linux/platform_data/mdio-bcm-unimac.h
 
-BROADCOM ASP 2.0 ETHERNET DRIVER
-M:	Justin Chen <justin.chen@broadcom.com>
-M:	Florian Fainelli <florian.fainelli@broadcom.com>
-L:	bcm-kernel-feedback-list@broadcom.com
-L:	netdev@vger.kernel.org
-S:	Supported
-F:	Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml
-F:	drivers/net/ethernet/broadcom/asp2/
-
 BROADCOM IPROC ARM ARCHITECTURE
 M:	Ray Jui <rjui@broadcom.com>
 M:	Scott Branden <sbranden@broadcom.com>
-- 
GitLab


From 5766946ea5117e4edeb78c80cac367fb06854cc1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 20 Jul 2023 13:13:54 +0200
Subject: [PATCH 0314/1806] genetlink: add explicit ordering break check for
 split ops

Currently, if cmd in the split ops array is of lower value than the
previous one, genl_validate_ops() continues to do the checks as if
the values are equal. This may result in non-obvious WARN_ON() hit in
these check.

Instead, check the incorrect ordering explicitly and put a WARN_ON()
in case it is broken.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230720111354.562242-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netlink/genetlink.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index a157247a1e452..6bd2ce51271f3 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -593,8 +593,12 @@ static int genl_validate_ops(const struct genl_family *family)
 			return -EINVAL;
 
 		/* Check sort order */
-		if (a->cmd < b->cmd)
+		if (a->cmd < b->cmd) {
 			continue;
+		} else if (a->cmd > b->cmd) {
+			WARN_ON(1);
+			return -EINVAL;
+		}
 
 		if (a->internal_flags != b->internal_flags ||
 		    ((a->flags ^ b->flags) & ~(GENL_CMD_CAP_DO |
-- 
GitLab


From b03f68ba26c85671c6734b14ea37a5955b0fb8d3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Jul 2023 18:04:06 -0700
Subject: [PATCH 0315/1806] eth: tsnep: let page recycling happen with skbs

tsnep builds an skb with napi_build_skb() and then calls
page_pool_release_page() for the page in which that skb's
head sits. Use recycling instead, recycling of heads works
just fine.

Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Link: https://lore.kernel.org/r/20230720010409.1967072-2-kuba@kernel.org
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/engleder/tsnep_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 84751bb303a68..079f9f6ae21ae 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -1333,7 +1333,7 @@ static void tsnep_rx_page(struct tsnep_rx *rx, struct napi_struct *napi,
 
 	skb = tsnep_build_skb(rx, page, length);
 	if (skb) {
-		page_pool_release_page(rx->page_pool, page);
+		skb_mark_for_recycle(skb);
 
 		rx->packets++;
 		rx->bytes += length;
-- 
GitLab


From 98e2727c79d007d99a026eb66f481908e66af263 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Jul 2023 18:04:07 -0700
Subject: [PATCH 0316/1806] eth: stmmac: let page recycling happen with skbs

stmmac removes pages from the page pool after attaching them
to skbs. Use page recycling instead.

skb heads are always copied, and pages are always from page
pool in this driver. We could as well mark all allocated skbs
for recycling.

Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Link: https://lore.kernel.org/r/20230720010409.1967072-3-kuba@kernel.org
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index e7ca52f0d2f2d..e1f1c034d3259 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -5441,7 +5441,7 @@ read_again:
 					priv->dma_conf.dma_buf_sz);
 
 			/* Data payload appended into SKB */
-			page_pool_release_page(rx_q->page_pool, buf->page);
+			skb_mark_for_recycle(skb);
 			buf->page = NULL;
 		}
 
@@ -5453,7 +5453,7 @@ read_again:
 					priv->dma_conf.dma_buf_sz);
 
 			/* Data payload appended into SKB */
-			page_pool_release_page(rx_q->page_pool, buf->sec_page);
+			skb_mark_for_recycle(skb);
 			buf->sec_page = NULL;
 		}
 
-- 
GitLab


From 535b9c61bdef6017228c708128b7849a476f8da5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Jul 2023 18:04:08 -0700
Subject: [PATCH 0317/1806] net: page_pool: hide page_pool_release_page()

There seems to be no user calling page_pool_release_page()
for legit reasons, all the users simply haven't been converted
to skb-based recycling, yet. Previous changes converted them.
Update the docs, and unexport the function.

Link: https://lore.kernel.org/r/20230720010409.1967072-4-kuba@kernel.org
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/page_pool.rst | 11 ++++-------
 include/net/page_pool.h                | 10 ++--------
 net/core/page_pool.c                   |  3 +--
 3 files changed, 7 insertions(+), 17 deletions(-)

diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst
index 873efd97f8228..0aa850cf4447c 100644
--- a/Documentation/networking/page_pool.rst
+++ b/Documentation/networking/page_pool.rst
@@ -13,9 +13,9 @@ replacing dev_alloc_pages().
 
 API keeps track of in-flight pages, in order to let API user know
 when it is safe to free a page_pool object.  Thus, API users
-must run page_pool_release_page() when a page is leaving the page_pool or
-call page_pool_put_page() where appropriate in order to maintain correct
-accounting.
+must call page_pool_put_page() to free the page, or attach
+the page to a page_pool-aware objects like skbs marked with
+skb_mark_for_recycle().
 
 API user must call page_pool_put_page() once on a page, as it
 will either recycle the page, or in case of refcnt > 1, it will
@@ -87,9 +87,6 @@ a page will cause no race conditions is enough.
   must guarantee safe context (e.g NAPI), since it will recycle the page
   directly into the pool fast cache.
 
-* page_pool_release_page(): Unmap the page (if mapped) and account for it on
-  in-flight counters.
-
 * page_pool_dev_alloc_pages(): Get a page from the page allocator or page_pool
   caches.
 
@@ -194,7 +191,7 @@ NAPI poller
             if XDP_DROP:
                 page_pool_recycle_direct(page_pool, page);
         } else (packet_is_skb) {
-            page_pool_release_page(page_pool, page);
+            skb_mark_for_recycle(skb);
             new_page = page_pool_dev_alloc_pages(page_pool);
         }
     }
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 126f9e294389a..f1d5cc1fa13b1 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -18,9 +18,8 @@
  *
  * API keeps track of in-flight pages, in-order to let API user know
  * when it is safe to dealloactor page_pool object.  Thus, API users
- * must make sure to call page_pool_release_page() when a page is
- * "leaving" the page_pool.  Or call page_pool_put_page() where
- * appropiate.  For maintaining correct accounting.
+ * must call page_pool_put_page() where appropriate and only attach
+ * the page to a page_pool-aware objects, like skbs marked for recycling.
  *
  * API user must only call page_pool_put_page() once on a page, as it
  * will either recycle the page, or in case of elevated refcnt, it
@@ -251,7 +250,6 @@ void page_pool_unlink_napi(struct page_pool *pool);
 void page_pool_destroy(struct page_pool *pool);
 void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
 			   struct xdp_mem_info *mem);
-void page_pool_release_page(struct page_pool *pool, struct page *page);
 void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 			     int count);
 #else
@@ -268,10 +266,6 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool,
 					 struct xdp_mem_info *mem)
 {
 }
-static inline void page_pool_release_page(struct page_pool *pool,
-					  struct page *page)
-{
-}
 
 static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 					   int count)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index a3e12a61d456c..2c7cf5f2bcb80 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -492,7 +492,7 @@ static s32 page_pool_inflight(struct page_pool *pool)
  * a regular page (that will eventually be returned to the normal
  * page-allocator via put_page).
  */
-void page_pool_release_page(struct page_pool *pool, struct page *page)
+static void page_pool_release_page(struct page_pool *pool, struct page *page)
 {
 	dma_addr_t dma;
 	int count;
@@ -519,7 +519,6 @@ skip_dma_unmap:
 	count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt);
 	trace_page_pool_state_release(pool, page, count);
 }
-EXPORT_SYMBOL(page_pool_release_page);
 
 /* Return a page to the page allocator, cleaning up our state */
 static void page_pool_return_page(struct page_pool *pool, struct page *page)
-- 
GitLab


From 07e0c7d3179da5d06132f3d71b740aa91bde52aa Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Jul 2023 18:04:09 -0700
Subject: [PATCH 0318/1806] net: page_pool: merge page_pool_release_page() with
 page_pool_return_page()

Now that page_pool_release_page() is not exported we can
merge it with page_pool_return_page(). I believe that
the "Do not replace this with page_pool_return_page()"
comment was there in case page_pool_return_page() was
not inlined, to avoid two function calls.

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Link: https://lore.kernel.org/r/20230720010409.1967072-5-kuba@kernel.org
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/page_pool.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 2c7cf5f2bcb80..7ca456bfab71c 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -492,7 +492,7 @@ static s32 page_pool_inflight(struct page_pool *pool)
  * a regular page (that will eventually be returned to the normal
  * page-allocator via put_page).
  */
-static void page_pool_release_page(struct page_pool *pool, struct page *page)
+static void page_pool_return_page(struct page_pool *pool, struct page *page)
 {
 	dma_addr_t dma;
 	int count;
@@ -518,12 +518,6 @@ skip_dma_unmap:
 	 */
 	count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt);
 	trace_page_pool_state_release(pool, page, count);
-}
-
-/* Return a page to the page allocator, cleaning up our state */
-static void page_pool_return_page(struct page_pool *pool, struct page *page)
-{
-	page_pool_release_page(pool, page);
 
 	put_page(page);
 	/* An optimization would be to call __free_pages(page, pool->p.order)
@@ -615,9 +609,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
 	 * will be invoking put_page.
 	 */
 	recycle_stat_inc(pool, released_refcnt);
-	/* Do not replace this with page_pool_return_page() */
-	page_pool_release_page(pool, page);
-	put_page(page);
+	page_pool_return_page(pool, page);
 
 	return NULL;
 }
-- 
GitLab


From a3377386b56420d78a4c0a931a40f9a25c3ca2bd Mon Sep 17 00:00:00 2001
From: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Date: Wed, 19 Jul 2023 13:18:16 -0700
Subject: [PATCH 0319/1806] netlink: Reverse the patch which removed filtering

To use filtering at the connector & cn_proc layers, we need to enable
filtering in the netlink layer. This reverses the patch which removed
netlink filtering - commit ID for that patch:
549017aa1bb7 (netlink: remove netlink_broadcast_filtered).

Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netlink.h  |  5 +++++
 net/netlink/af_netlink.c | 27 +++++++++++++++++++++++++--
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 9eec3f4f5351e..3a6563681b500 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -227,6 +227,11 @@ bool netlink_strict_get_check(struct sk_buff *skb);
 int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
 int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
 		      __u32 group, gfp_t allocation);
+int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
+			       __u32 portid, __u32 group, gfp_t allocation,
+			       int (*filter)(struct sock *dsk,
+					     struct sk_buff *skb, void *data),
+			       void *filter_data);
 int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code);
 int netlink_register_notifier(struct notifier_block *nb);
 int netlink_unregister_notifier(struct notifier_block *nb);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 9c9df143a2ec0..6c0bcde620e84 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1432,6 +1432,8 @@ struct netlink_broadcast_data {
 	int delivered;
 	gfp_t allocation;
 	struct sk_buff *skb, *skb2;
+	int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data);
+	void *tx_data;
 };
 
 static void do_one_broadcast(struct sock *sk,
@@ -1485,6 +1487,13 @@ static void do_one_broadcast(struct sock *sk,
 			p->delivery_failure = 1;
 		goto out;
 	}
+
+	if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) {
+		kfree_skb(p->skb2);
+		p->skb2 = NULL;
+		goto out;
+	}
+
 	if (sk_filter(sk, p->skb2)) {
 		kfree_skb(p->skb2);
 		p->skb2 = NULL;
@@ -1507,8 +1516,12 @@ out:
 	sock_put(sk);
 }
 
-int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid,
-		      u32 group, gfp_t allocation)
+int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
+			       u32 portid,
+			       u32 group, gfp_t allocation,
+			       int (*filter)(struct sock *dsk,
+					     struct sk_buff *skb, void *data),
+			       void *filter_data)
 {
 	struct net *net = sock_net(ssk);
 	struct netlink_broadcast_data info;
@@ -1527,6 +1540,8 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid,
 	info.allocation = allocation;
 	info.skb = skb;
 	info.skb2 = NULL;
+	info.tx_filter = filter;
+	info.tx_data = filter_data;
 
 	/* While we sleep in clone, do not allow to change socket list */
 
@@ -1552,6 +1567,14 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid,
 	}
 	return -ESRCH;
 }
+EXPORT_SYMBOL(netlink_broadcast_filtered);
+
+int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid,
+		      u32 group, gfp_t allocation)
+{
+	return netlink_broadcast_filtered(ssk, skb, portid, group, allocation,
+					  NULL, NULL);
+}
 EXPORT_SYMBOL(netlink_broadcast);
 
 struct netlink_set_err_data {
-- 
GitLab


From a4c9a56e6a2cdeeab7caef1f496b7bfefd95b50e Mon Sep 17 00:00:00 2001
From: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Date: Wed, 19 Jul 2023 13:18:17 -0700
Subject: [PATCH 0320/1806] netlink: Add new netlink_release function

A new function netlink_release is added in netlink_sock to store the
protocol's release function. This is called when the socket is deleted.
This can be supplied by the protocol via the release function in
netlink_kernel_cfg. This is being added for the NETLINK_CONNECTOR
protocol, so it can free it's data when socket is deleted.

Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netlink.h  | 1 +
 net/netlink/af_netlink.c | 6 ++++++
 net/netlink/af_netlink.h | 4 ++++
 3 files changed, 11 insertions(+)

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 3a6563681b500..75d7de34c9087 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -50,6 +50,7 @@ struct netlink_kernel_cfg {
 	struct mutex	*cb_mutex;
 	int		(*bind)(struct net *net, int group);
 	void		(*unbind)(struct net *net, int group);
+	void            (*release) (struct sock *sk, unsigned long *groups);
 };
 
 struct sock *__netlink_kernel_create(struct net *net, int unit,
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 6c0bcde620e84..96c605e452358 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -677,6 +677,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	struct netlink_sock *nlk;
 	int (*bind)(struct net *net, int group);
 	void (*unbind)(struct net *net, int group);
+	void (*release)(struct sock *sock, unsigned long *groups);
 	int err = 0;
 
 	sock->state = SS_UNCONNECTED;
@@ -704,6 +705,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	cb_mutex = nl_table[protocol].cb_mutex;
 	bind = nl_table[protocol].bind;
 	unbind = nl_table[protocol].unbind;
+	release = nl_table[protocol].release;
 	netlink_unlock_table();
 
 	if (err < 0)
@@ -719,6 +721,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	nlk->module = module;
 	nlk->netlink_bind = bind;
 	nlk->netlink_unbind = unbind;
+	nlk->netlink_release = release;
 out:
 	return err;
 
@@ -763,6 +766,8 @@ static int netlink_release(struct socket *sock)
 	 * OK. Socket is unlinked, any packets that arrive now
 	 * will be purged.
 	 */
+	if (nlk->netlink_release)
+		nlk->netlink_release(sk, nlk->groups);
 
 	/* must not acquire netlink_table_lock in any way again before unbind
 	 * and notifying genetlink is done as otherwise it might deadlock
@@ -2089,6 +2094,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 		if (cfg) {
 			nl_table[unit].bind = cfg->bind;
 			nl_table[unit].unbind = cfg->unbind;
+			nl_table[unit].release = cfg->release;
 			nl_table[unit].flags = cfg->flags;
 		}
 		nl_table[unit].registered = 1;
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 90a3198a9b7f7..fd424cd63f31c 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -42,6 +42,8 @@ struct netlink_sock {
 	void			(*netlink_rcv)(struct sk_buff *skb);
 	int			(*netlink_bind)(struct net *net, int group);
 	void			(*netlink_unbind)(struct net *net, int group);
+	void			(*netlink_release)(struct sock *sk,
+						   unsigned long *groups);
 	struct module		*module;
 
 	struct rhash_head	node;
@@ -64,6 +66,8 @@ struct netlink_table {
 	struct module		*module;
 	int			(*bind)(struct net *net, int group);
 	void			(*unbind)(struct net *net, int group);
+	void                    (*release)(struct sock *sk,
+					   unsigned long *groups);
 	int			registered;
 };
 
-- 
GitLab


From 2aa1f7a1f47ce8dac7593af605aaa859b3cf3bb1 Mon Sep 17 00:00:00 2001
From: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Date: Wed, 19 Jul 2023 13:18:18 -0700
Subject: [PATCH 0321/1806] connector/cn_proc: Add filtering to fix some bugs

The current proc connector code has the foll. bugs - if there are more
than one listeners for the proc connector messages, and one of them
deregisters for listening using PROC_CN_MCAST_IGNORE, they will still get
all proc connector messages, as long as there is another listener.

Another issue is if one client calls PROC_CN_MCAST_LISTEN, and another one
calls PROC_CN_MCAST_IGNORE, then both will end up not getting any messages.

This patch adds filtering and drops packet if client has sent
PROC_CN_MCAST_IGNORE. This data is stored in the client socket's
sk_user_data. In addition, we only increment or decrement
proc_event_num_listeners once per client. This fixes the above issues.

cn_release is the release function added for NETLINK_CONNECTOR. It uses
the newly added netlink_release function added to netlink_sock. It will
free sk_user_data.

Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/connector/cn_proc.c   | 57 +++++++++++++++++++++++++++++------
 drivers/connector/connector.c | 21 ++++++++++---
 drivers/w1/w1_netlink.c       |  6 ++--
 include/linux/connector.h     |  8 ++++-
 include/uapi/linux/cn_proc.h  | 43 +++++++++++++++-----------
 5 files changed, 100 insertions(+), 35 deletions(-)

diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index ccac1c453080b..1ba288ed2bf7c 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -48,6 +48,21 @@ static DEFINE_PER_CPU(struct local_event, local_event) = {
 	.lock = INIT_LOCAL_LOCK(lock),
 };
 
+static int cn_filter(struct sock *dsk, struct sk_buff *skb, void *data)
+{
+	enum proc_cn_mcast_op mc_op;
+
+	if (!dsk)
+		return 0;
+
+	mc_op = ((struct proc_input *)(dsk->sk_user_data))->mcast_op;
+
+	if (mc_op == PROC_CN_MCAST_IGNORE)
+		return 1;
+
+	return 0;
+}
+
 static inline void send_msg(struct cn_msg *msg)
 {
 	local_lock(&local_event.lock);
@@ -61,7 +76,8 @@ static inline void send_msg(struct cn_msg *msg)
 	 *
 	 * If cn_netlink_send() fails, the data is not sent.
 	 */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT);
+	cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
+			     cn_filter, NULL);
 
 	local_unlock(&local_event.lock);
 }
@@ -346,11 +362,9 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack)
 static void cn_proc_mcast_ctl(struct cn_msg *msg,
 			      struct netlink_skb_parms *nsp)
 {
-	enum proc_cn_mcast_op *mc_op = NULL;
-	int err = 0;
-
-	if (msg->len != sizeof(*mc_op))
-		return;
+	enum proc_cn_mcast_op mc_op = 0, prev_mc_op = 0;
+	int err = 0, initial = 0;
+	struct sock *sk = NULL;
 
 	/* 
 	 * Events are reported with respect to the initial pid
@@ -367,13 +381,36 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 		goto out;
 	}
 
-	mc_op = (enum proc_cn_mcast_op *)msg->data;
-	switch (*mc_op) {
+	if (msg->len == sizeof(mc_op))
+		mc_op = *((enum proc_cn_mcast_op *)msg->data);
+	else
+		return;
+
+	if (nsp->sk) {
+		sk = nsp->sk;
+		if (sk->sk_user_data == NULL) {
+			sk->sk_user_data = kzalloc(sizeof(struct proc_input),
+						   GFP_KERNEL);
+			if (sk->sk_user_data == NULL) {
+				err = ENOMEM;
+				goto out;
+			}
+			initial = 1;
+		} else {
+			prev_mc_op =
+			((struct proc_input *)(sk->sk_user_data))->mcast_op;
+		}
+		((struct proc_input *)(sk->sk_user_data))->mcast_op = mc_op;
+	}
+
+	switch (mc_op) {
 	case PROC_CN_MCAST_LISTEN:
-		atomic_inc(&proc_event_num_listeners);
+		if (initial || (prev_mc_op != PROC_CN_MCAST_LISTEN))
+			atomic_inc(&proc_event_num_listeners);
 		break;
 	case PROC_CN_MCAST_IGNORE:
-		atomic_dec(&proc_event_num_listeners);
+		if (!initial && (prev_mc_op != PROC_CN_MCAST_IGNORE))
+			atomic_dec(&proc_event_num_listeners);
 		break;
 	default:
 		err = EINVAL;
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 48ec7ce6ecace..d1179df2b0ba2 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -59,7 +59,9 @@ static int cn_already_initialized;
  * both, or if both are zero then the group is looked up and sent there.
  */
 int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group,
-	gfp_t gfp_mask)
+	gfp_t gfp_mask,
+	int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data),
+	void *filter_data)
 {
 	struct cn_callback_entry *__cbq;
 	unsigned int size;
@@ -110,8 +112,9 @@ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group,
 	NETLINK_CB(skb).dst_group = group;
 
 	if (group)
-		return netlink_broadcast(dev->nls, skb, portid, group,
-					 gfp_mask);
+		return netlink_broadcast_filtered(dev->nls, skb, portid, group,
+						  gfp_mask, filter,
+						  (void *)filter_data);
 	return netlink_unicast(dev->nls, skb, portid,
 			!gfpflags_allow_blocking(gfp_mask));
 }
@@ -121,7 +124,8 @@ EXPORT_SYMBOL_GPL(cn_netlink_send_mult);
 int cn_netlink_send(struct cn_msg *msg, u32 portid, u32 __group,
 	gfp_t gfp_mask)
 {
-	return cn_netlink_send_mult(msg, msg->len, portid, __group, gfp_mask);
+	return cn_netlink_send_mult(msg, msg->len, portid, __group, gfp_mask,
+				    NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(cn_netlink_send);
 
@@ -162,6 +166,14 @@ static int cn_call_callback(struct sk_buff *skb)
 	return err;
 }
 
+static void cn_release(struct sock *sk, unsigned long *groups)
+{
+	if (groups && test_bit(CN_IDX_PROC - 1, groups)) {
+		kfree(sk->sk_user_data);
+		sk->sk_user_data = NULL;
+	}
+}
+
 /*
  * Main netlink receiving function.
  *
@@ -249,6 +261,7 @@ static int cn_init(void)
 	struct netlink_kernel_cfg cfg = {
 		.groups	= CN_NETLINK_USERS + 0xf,
 		.input	= cn_rx_skb,
+		.release = cn_release,
 	};
 
 	dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, &cfg);
diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c
index db110cc442b13..691978cddab7c 100644
--- a/drivers/w1/w1_netlink.c
+++ b/drivers/w1/w1_netlink.c
@@ -65,7 +65,8 @@ static void w1_unref_block(struct w1_cb_block *block)
 		u16 len = w1_reply_len(block);
 		if (len) {
 			cn_netlink_send_mult(block->first_cn, len,
-				block->portid, 0, GFP_KERNEL);
+					     block->portid, 0,
+					     GFP_KERNEL, NULL, NULL);
 		}
 		kfree(block);
 	}
@@ -83,7 +84,8 @@ static void w1_reply_make_space(struct w1_cb_block *block, u16 space)
 {
 	u16 len = w1_reply_len(block);
 	if (len + space >= block->maxlen) {
-		cn_netlink_send_mult(block->first_cn, len, block->portid, 0, GFP_KERNEL);
+		cn_netlink_send_mult(block->first_cn, len, block->portid,
+				     0, GFP_KERNEL, NULL, NULL);
 		block->first_cn->len = 0;
 		block->cn = NULL;
 		block->msg = NULL;
diff --git a/include/linux/connector.h b/include/linux/connector.h
index 487350bb19c34..cec2d99ae9021 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -90,13 +90,19 @@ void cn_del_callback(const struct cb_id *id);
  *		If @group is not zero, then message will be delivered
  *		to the specified group.
  * @gfp_mask:	GFP mask.
+ * @filter:     Filter function to be used at netlink layer.
+ * @filter_data:Filter data to be supplied to the filter function
  *
  * It can be safely called from softirq context, but may silently
  * fail under strong memory pressure.
  *
  * If there are no listeners for given group %-ESRCH can be returned.
  */
-int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 group, gfp_t gfp_mask);
+int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid,
+			 u32 group, gfp_t gfp_mask,
+			 int (*filter)(struct sock *dsk, struct sk_buff *skb,
+				       void *data),
+			 void *filter_data);
 
 /**
  * cn_netlink_send - Sends message to the specified groups.
diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h
index db210625cee8c..6a06fb424313c 100644
--- a/include/uapi/linux/cn_proc.h
+++ b/include/uapi/linux/cn_proc.h
@@ -30,6 +30,30 @@ enum proc_cn_mcast_op {
 	PROC_CN_MCAST_IGNORE = 2
 };
 
+enum proc_cn_event {
+	/* Use successive bits so the enums can be used to record
+	 * sets of events as well
+	 */
+	PROC_EVENT_NONE = 0x00000000,
+	PROC_EVENT_FORK = 0x00000001,
+	PROC_EVENT_EXEC = 0x00000002,
+	PROC_EVENT_UID  = 0x00000004,
+	PROC_EVENT_GID  = 0x00000040,
+	PROC_EVENT_SID  = 0x00000080,
+	PROC_EVENT_PTRACE = 0x00000100,
+	PROC_EVENT_COMM = 0x00000200,
+	/* "next" should be 0x00000400 */
+	/* "last" is the last process event: exit,
+	 * while "next to last" is coredumping event
+	 */
+	PROC_EVENT_COREDUMP = 0x40000000,
+	PROC_EVENT_EXIT = 0x80000000
+};
+
+struct proc_input {
+	enum proc_cn_mcast_op mcast_op;
+};
+
 /*
  * From the user's point of view, the process
  * ID is the thread group ID and thread ID is the internal
@@ -44,24 +68,7 @@ enum proc_cn_mcast_op {
  */
 
 struct proc_event {
-	enum what {
-		/* Use successive bits so the enums can be used to record
-		 * sets of events as well
-		 */
-		PROC_EVENT_NONE = 0x00000000,
-		PROC_EVENT_FORK = 0x00000001,
-		PROC_EVENT_EXEC = 0x00000002,
-		PROC_EVENT_UID  = 0x00000004,
-		PROC_EVENT_GID  = 0x00000040,
-		PROC_EVENT_SID  = 0x00000080,
-		PROC_EVENT_PTRACE = 0x00000100,
-		PROC_EVENT_COMM = 0x00000200,
-		/* "next" should be 0x00000400 */
-		/* "last" is the last process event: exit,
-		 * while "next to last" is coredumping event */
-		PROC_EVENT_COREDUMP = 0x40000000,
-		PROC_EVENT_EXIT = 0x80000000
-	} what;
+	enum proc_cn_event what;
 	__u32 cpu;
 	__u64 __attribute__((aligned(8))) timestamp_ns;
 		/* Number of nano seconds since system boot */
-- 
GitLab


From 743acf351bae1ff7ff4aaadd6a406d4d6091d90b Mon Sep 17 00:00:00 2001
From: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Date: Wed, 19 Jul 2023 13:18:19 -0700
Subject: [PATCH 0322/1806] connector/cn_proc: Performance improvements

This patch adds the capability to filter messages sent by the proc
connector on the event type supplied in the message from the client
to the connector. The client can register to listen for an event type
given in struct proc_input.

This event based filteting will greatly enhance performance - handling
8K exits takes about 70ms, whereas 8K-forks + 8K-exits takes about 150ms
& handling 8K-forks + 8K-exits + 8K-execs takes 200ms. There are currently
9 different types of events, and we need to listen to all of them. Also,
measuring the time using pidfds for monitoring 8K process exits took
much longer - 200ms, as compared to 70ms using only exit notifications of
proc connector.

We also add a new event type - PROC_EVENT_NONZERO_EXIT, which is
only sent by kernel to a listening application when any process exiting,
has a non-zero exit status. This will help the clients like Oracle DB,
where a monitoring process wants notfications for non-zero process exits
so it can cleanup after them.

This kind of a new event could also be useful to other applications like
Google's lmkd daemon, which needs a killed process's exit notification.

The patch takes care that existing clients using old mechanism of not
sending the event type work without any changes.

cn_filter function checks to see if the event type being notified via
proc connector matches the event type requested by client, before
sending(matches) or dropping(does not match) a packet.

Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/connector/cn_proc.c  | 62 ++++++++++++++++++++++++++++++++----
 include/uapi/linux/cn_proc.h | 19 +++++++++++
 2 files changed, 75 insertions(+), 6 deletions(-)

diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 1ba288ed2bf7c..dfc84d44f8043 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -50,21 +50,45 @@ static DEFINE_PER_CPU(struct local_event, local_event) = {
 
 static int cn_filter(struct sock *dsk, struct sk_buff *skb, void *data)
 {
+	__u32 what, exit_code, *ptr;
 	enum proc_cn_mcast_op mc_op;
+	uintptr_t val;
 
-	if (!dsk)
+	if (!dsk || !data)
 		return 0;
 
+	ptr = (__u32 *)data;
+	what = *ptr++;
+	exit_code = *ptr;
+	val = ((struct proc_input *)(dsk->sk_user_data))->event_type;
 	mc_op = ((struct proc_input *)(dsk->sk_user_data))->mcast_op;
 
 	if (mc_op == PROC_CN_MCAST_IGNORE)
 		return 1;
 
-	return 0;
+	if ((__u32)val == PROC_EVENT_ALL)
+		return 0;
+
+	/*
+	 * Drop packet if we have to report only non-zero exit status
+	 * (PROC_EVENT_NONZERO_EXIT) and exit status is 0
+	 */
+	if (((__u32)val & PROC_EVENT_NONZERO_EXIT) &&
+	    (what == PROC_EVENT_EXIT)) {
+		if (exit_code)
+			return 0;
+	}
+
+	if ((__u32)val & what)
+		return 0;
+
+	return 1;
 }
 
 static inline void send_msg(struct cn_msg *msg)
 {
+	__u32 filter_data[2];
+
 	local_lock(&local_event.lock);
 
 	msg->seq = __this_cpu_inc_return(local_event.count) - 1;
@@ -76,8 +100,16 @@ static inline void send_msg(struct cn_msg *msg)
 	 *
 	 * If cn_netlink_send() fails, the data is not sent.
 	 */
+	filter_data[0] = ((struct proc_event *)msg->data)->what;
+	if (filter_data[0] == PROC_EVENT_EXIT) {
+		filter_data[1] =
+		((struct proc_event *)msg->data)->event_data.exit.exit_code;
+	} else {
+		filter_data[1] = 0;
+	}
+
 	cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
-			     cn_filter, NULL);
+			     cn_filter, (void *)filter_data);
 
 	local_unlock(&local_event.lock);
 }
@@ -357,12 +389,15 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack)
 
 /**
  * cn_proc_mcast_ctl
- * @data: message sent from userspace via the connector
+ * @msg: message sent from userspace via the connector
+ * @nsp: NETLINK_CB of the client's socket buffer
  */
 static void cn_proc_mcast_ctl(struct cn_msg *msg,
 			      struct netlink_skb_parms *nsp)
 {
 	enum proc_cn_mcast_op mc_op = 0, prev_mc_op = 0;
+	struct proc_input *pinput = NULL;
+	enum proc_cn_event ev_type = 0;
 	int err = 0, initial = 0;
 	struct sock *sk = NULL;
 
@@ -381,10 +416,21 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 		goto out;
 	}
 
-	if (msg->len == sizeof(mc_op))
+	if (msg->len == sizeof(*pinput)) {
+		pinput = (struct proc_input *)msg->data;
+		mc_op = pinput->mcast_op;
+		ev_type = pinput->event_type;
+	} else if (msg->len == sizeof(mc_op)) {
 		mc_op = *((enum proc_cn_mcast_op *)msg->data);
-	else
+		ev_type = PROC_EVENT_ALL;
+	} else {
 		return;
+	}
+
+	ev_type = valid_event((enum proc_cn_event)ev_type);
+
+	if (ev_type == PROC_EVENT_NONE)
+		ev_type = PROC_EVENT_ALL;
 
 	if (nsp->sk) {
 		sk = nsp->sk;
@@ -400,6 +446,8 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 			prev_mc_op =
 			((struct proc_input *)(sk->sk_user_data))->mcast_op;
 		}
+		((struct proc_input *)(sk->sk_user_data))->event_type =
+			ev_type;
 		((struct proc_input *)(sk->sk_user_data))->mcast_op = mc_op;
 	}
 
@@ -411,6 +459,8 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 	case PROC_CN_MCAST_IGNORE:
 		if (!initial && (prev_mc_op != PROC_CN_MCAST_IGNORE))
 			atomic_dec(&proc_event_num_listeners);
+		((struct proc_input *)(sk->sk_user_data))->event_type =
+			PROC_EVENT_NONE;
 		break;
 	default:
 		err = EINVAL;
diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h
index 6a06fb424313c..f2afb7cc4926c 100644
--- a/include/uapi/linux/cn_proc.h
+++ b/include/uapi/linux/cn_proc.h
@@ -30,6 +30,15 @@ enum proc_cn_mcast_op {
 	PROC_CN_MCAST_IGNORE = 2
 };
 
+#define PROC_EVENT_ALL (PROC_EVENT_FORK | PROC_EVENT_EXEC | PROC_EVENT_UID |  \
+			PROC_EVENT_GID | PROC_EVENT_SID | PROC_EVENT_PTRACE | \
+			PROC_EVENT_COMM | PROC_EVENT_NONZERO_EXIT |           \
+			PROC_EVENT_COREDUMP | PROC_EVENT_EXIT)
+
+/*
+ * If you add an entry in proc_cn_event, make sure you add it in
+ * PROC_EVENT_ALL above as well.
+ */
 enum proc_cn_event {
 	/* Use successive bits so the enums can be used to record
 	 * sets of events as well
@@ -45,15 +54,25 @@ enum proc_cn_event {
 	/* "next" should be 0x00000400 */
 	/* "last" is the last process event: exit,
 	 * while "next to last" is coredumping event
+	 * before that is report only if process dies
+	 * with non-zero exit status
 	 */
+	PROC_EVENT_NONZERO_EXIT = 0x20000000,
 	PROC_EVENT_COREDUMP = 0x40000000,
 	PROC_EVENT_EXIT = 0x80000000
 };
 
 struct proc_input {
 	enum proc_cn_mcast_op mcast_op;
+	enum proc_cn_event event_type;
 };
 
+static inline enum proc_cn_event valid_event(enum proc_cn_event ev_type)
+{
+	ev_type &= PROC_EVENT_ALL;
+	return ev_type;
+}
+
 /*
  * From the user's point of view, the process
  * ID is the thread group ID and thread ID is the internal
-- 
GitLab


From bfdfdc2f3b7073571ce40b6d19193002b0126b6a Mon Sep 17 00:00:00 2001
From: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Date: Wed, 19 Jul 2023 13:18:20 -0700
Subject: [PATCH 0323/1806] connector/cn_proc: Allow non-root users access

There were a couple of reasons for not allowing non-root users access
initially  - one is there was some point no proper receive buffer
management in place for netlink multicast. But that should be long
fixed. See link below for more context.

Second is that some of the messages may contain data that is root only. But
this should be handled with a finer granularity, which is being done at the
protocol layer.  The only problematic protocols are nf_queue and the
firewall netlink. Hence, this restriction for non-root access was relaxed
for NETLINK_ROUTE initially:
https://lore.kernel.org/all/20020612013101.A22399@wotan.suse.de/

This restriction has also been removed for following protocols:
NETLINK_KOBJECT_UEVENT, NETLINK_AUDIT, NETLINK_SOCK_DIAG,
NETLINK_GENERIC, NETLINK_SELINUX.

Since process connector messages are not sensitive (process fork, exit
notifications etc.), and anyone can read /proc data, we can allow non-root
access here. However, since process event notification is not the only
consumer of NETLINK_CONNECTOR, we can make this change even more
fine grained than the protocol level, by checking for multicast group
within the protocol.

Allow non-root access for NETLINK_CONNECTOR via NL_CFG_F_NONROOT_RECV
but add new bind function cn_bind(), which allows non-root access only
for CN_IDX_PROC multicast group.

Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/connector/cn_proc.c   |  6 ------
 drivers/connector/connector.c | 19 +++++++++++++++++++
 2 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index dfc84d44f8043..05d562e9c8b18 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -410,12 +410,6 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 	    !task_is_in_init_pid_ns(current))
 		return;
 
-	/* Can only change if privileged. */
-	if (!__netlink_ns_capable(nsp, &init_user_ns, CAP_NET_ADMIN)) {
-		err = EPERM;
-		goto out;
-	}
-
 	if (msg->len == sizeof(*pinput)) {
 		pinput = (struct proc_input *)msg->data;
 		mc_op = pinput->mcast_op;
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index d1179df2b0ba2..7f7b94f616a66 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -166,6 +166,23 @@ static int cn_call_callback(struct sk_buff *skb)
 	return err;
 }
 
+/*
+ * Allow non-root access for NETLINK_CONNECTOR family having CN_IDX_PROC
+ * multicast group.
+ */
+static int cn_bind(struct net *net, int group)
+{
+	unsigned long groups = (unsigned long) group;
+
+	if (ns_capable(net->user_ns, CAP_NET_ADMIN))
+		return 0;
+
+	if (test_bit(CN_IDX_PROC - 1, &groups))
+		return 0;
+
+	return -EPERM;
+}
+
 static void cn_release(struct sock *sk, unsigned long *groups)
 {
 	if (groups && test_bit(CN_IDX_PROC - 1, groups)) {
@@ -261,6 +278,8 @@ static int cn_init(void)
 	struct netlink_kernel_cfg cfg = {
 		.groups	= CN_NETLINK_USERS + 0xf,
 		.input	= cn_rx_skb,
+		.flags  = NL_CFG_F_NONROOT_RECV,
+		.bind   = cn_bind,
 		.release = cn_release,
 	};
 
-- 
GitLab


From 73a29531f45fed6423144057d7a844aae46dad9d Mon Sep 17 00:00:00 2001
From: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Date: Wed, 19 Jul 2023 13:18:21 -0700
Subject: [PATCH 0324/1806] connector/cn_proc: Selftest for proc connector

Run as ./proc_filter -f to run new filter code. Run without "-f" to run
usual proc connector code without the new filtering code.

Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/Makefile              |   1 +
 tools/testing/selftests/connector/Makefile    |   6 +
 .../testing/selftests/connector/proc_filter.c | 310 ++++++++++++++++++
 3 files changed, 317 insertions(+)
 create mode 100644 tools/testing/selftests/connector/Makefile
 create mode 100644 tools/testing/selftests/connector/proc_filter.c

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 666b56f22a417..5c60a7cea7321 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -8,6 +8,7 @@ TARGETS += cachestat
 TARGETS += capabilities
 TARGETS += cgroup
 TARGETS += clone3
+TARGETS += connector
 TARGETS += core
 TARGETS += cpufreq
 TARGETS += cpu-hotplug
diff --git a/tools/testing/selftests/connector/Makefile b/tools/testing/selftests/connector/Makefile
new file mode 100644
index 0000000000000..21c9f3a973a0e
--- /dev/null
+++ b/tools/testing/selftests/connector/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wall
+
+TEST_GEN_PROGS = proc_filter
+
+include ../lib.mk
diff --git a/tools/testing/selftests/connector/proc_filter.c b/tools/testing/selftests/connector/proc_filter.c
new file mode 100644
index 0000000000000..4fe8c6763fd8e
--- /dev/null
+++ b/tools/testing/selftests/connector/proc_filter.c
@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <sys/types.h>
+#include <sys/epoll.h>
+#include <sys/socket.h>
+#include <linux/netlink.h>
+#include <linux/connector.h>
+#include <linux/cn_proc.h>
+
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <strings.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+
+#include "../kselftest.h"
+
+#define NL_MESSAGE_SIZE (sizeof(struct nlmsghdr) + sizeof(struct cn_msg) + \
+			 sizeof(struct proc_input))
+#define NL_MESSAGE_SIZE_NF (sizeof(struct nlmsghdr) + sizeof(struct cn_msg) + \
+			 sizeof(int))
+
+#define MAX_EVENTS 1
+
+volatile static int interrupted;
+static int nl_sock, ret_errno, tcount;
+static struct epoll_event evn;
+
+static int filter;
+
+#ifdef ENABLE_PRINTS
+#define Printf printf
+#else
+#define Printf ksft_print_msg
+#endif
+
+int send_message(void *pinp)
+{
+	char buff[NL_MESSAGE_SIZE];
+	struct nlmsghdr *hdr;
+	struct cn_msg *msg;
+
+	hdr = (struct nlmsghdr *)buff;
+	if (filter)
+		hdr->nlmsg_len = NL_MESSAGE_SIZE;
+	else
+		hdr->nlmsg_len = NL_MESSAGE_SIZE_NF;
+	hdr->nlmsg_type = NLMSG_DONE;
+	hdr->nlmsg_flags = 0;
+	hdr->nlmsg_seq = 0;
+	hdr->nlmsg_pid = getpid();
+
+	msg = (struct cn_msg *)NLMSG_DATA(hdr);
+	msg->id.idx = CN_IDX_PROC;
+	msg->id.val = CN_VAL_PROC;
+	msg->seq = 0;
+	msg->ack = 0;
+	msg->flags = 0;
+
+	if (filter) {
+		msg->len = sizeof(struct proc_input);
+		((struct proc_input *)msg->data)->mcast_op =
+			((struct proc_input *)pinp)->mcast_op;
+		((struct proc_input *)msg->data)->event_type =
+			((struct proc_input *)pinp)->event_type;
+	} else {
+		msg->len = sizeof(int);
+		*(int *)msg->data = *(enum proc_cn_mcast_op *)pinp;
+	}
+
+	if (send(nl_sock, hdr, hdr->nlmsg_len, 0) == -1) {
+		ret_errno = errno;
+		perror("send failed");
+		return -3;
+	}
+	return 0;
+}
+
+int register_proc_netlink(int *efd, void *input)
+{
+	struct sockaddr_nl sa_nl;
+	int err = 0, epoll_fd;
+
+	nl_sock = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR);
+
+	if (nl_sock == -1) {
+		ret_errno = errno;
+		perror("socket failed");
+		return -1;
+	}
+
+	bzero(&sa_nl, sizeof(sa_nl));
+	sa_nl.nl_family = AF_NETLINK;
+	sa_nl.nl_groups = CN_IDX_PROC;
+	sa_nl.nl_pid    = getpid();
+
+	if (bind(nl_sock, (struct sockaddr *)&sa_nl, sizeof(sa_nl)) == -1) {
+		ret_errno = errno;
+		perror("bind failed");
+		return -2;
+	}
+
+	epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (epoll_fd < 0) {
+		ret_errno = errno;
+		perror("epoll_create1 failed");
+		return -2;
+	}
+
+	err = send_message(input);
+
+	if (err < 0)
+		return err;
+
+	evn.events = EPOLLIN;
+	evn.data.fd = nl_sock;
+	if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, nl_sock, &evn) < 0) {
+		ret_errno = errno;
+		perror("epoll_ctl failed");
+		return -3;
+	}
+	*efd = epoll_fd;
+	return 0;
+}
+
+static void sigint(int sig)
+{
+	interrupted = 1;
+}
+
+int handle_packet(char *buff, int fd, struct proc_event *event)
+{
+	struct nlmsghdr *hdr;
+
+	hdr = (struct nlmsghdr *)buff;
+
+	if (hdr->nlmsg_type == NLMSG_ERROR) {
+		perror("NLMSG_ERROR error\n");
+		return -3;
+	} else if (hdr->nlmsg_type == NLMSG_DONE) {
+		event = (struct proc_event *)
+			((struct cn_msg *)NLMSG_DATA(hdr))->data;
+		tcount++;
+		switch (event->what) {
+		case PROC_EVENT_EXIT:
+			Printf("Exit process %d (tgid %d) with code %d, signal %d\n",
+			       event->event_data.exit.process_pid,
+			       event->event_data.exit.process_tgid,
+			       event->event_data.exit.exit_code,
+			       event->event_data.exit.exit_signal);
+			break;
+		case PROC_EVENT_FORK:
+			Printf("Fork process %d (tgid %d), parent %d (tgid %d)\n",
+			       event->event_data.fork.child_pid,
+			       event->event_data.fork.child_tgid,
+			       event->event_data.fork.parent_pid,
+			       event->event_data.fork.parent_tgid);
+			break;
+		case PROC_EVENT_EXEC:
+			Printf("Exec process %d (tgid %d)\n",
+			       event->event_data.exec.process_pid,
+			       event->event_data.exec.process_tgid);
+			break;
+		case PROC_EVENT_UID:
+			Printf("UID process %d (tgid %d) uid %d euid %d\n",
+			       event->event_data.id.process_pid,
+			       event->event_data.id.process_tgid,
+			       event->event_data.id.r.ruid,
+			       event->event_data.id.e.euid);
+			break;
+		case PROC_EVENT_GID:
+			Printf("GID process %d (tgid %d) gid %d egid %d\n",
+			       event->event_data.id.process_pid,
+			       event->event_data.id.process_tgid,
+			       event->event_data.id.r.rgid,
+			       event->event_data.id.e.egid);
+			break;
+		case PROC_EVENT_SID:
+			Printf("SID process %d (tgid %d)\n",
+			       event->event_data.sid.process_pid,
+			       event->event_data.sid.process_tgid);
+			break;
+		case PROC_EVENT_PTRACE:
+			Printf("Ptrace process %d (tgid %d), Tracer %d (tgid %d)\n",
+			       event->event_data.ptrace.process_pid,
+			       event->event_data.ptrace.process_tgid,
+			       event->event_data.ptrace.tracer_pid,
+			       event->event_data.ptrace.tracer_tgid);
+			break;
+		case PROC_EVENT_COMM:
+			Printf("Comm process %d (tgid %d) comm %s\n",
+			       event->event_data.comm.process_pid,
+			       event->event_data.comm.process_tgid,
+			       event->event_data.comm.comm);
+			break;
+		case PROC_EVENT_COREDUMP:
+			Printf("Coredump process %d (tgid %d) parent %d, (tgid %d)\n",
+			       event->event_data.coredump.process_pid,
+			       event->event_data.coredump.process_tgid,
+			       event->event_data.coredump.parent_pid,
+			       event->event_data.coredump.parent_tgid);
+			break;
+		default:
+			break;
+		}
+	}
+	return 0;
+}
+
+int handle_events(int epoll_fd, struct proc_event *pev)
+{
+	char buff[CONNECTOR_MAX_MSG_SIZE];
+	struct epoll_event ev[MAX_EVENTS];
+	int i, event_count = 0, err = 0;
+
+	event_count = epoll_wait(epoll_fd, ev, MAX_EVENTS, -1);
+	if (event_count < 0) {
+		ret_errno = errno;
+		if (ret_errno != EINTR)
+			perror("epoll_wait failed");
+		return -3;
+	}
+	for (i = 0; i < event_count; i++) {
+		if (!(ev[i].events & EPOLLIN))
+			continue;
+		if (recv(ev[i].data.fd, buff, sizeof(buff), 0) == -1) {
+			ret_errno = errno;
+			perror("recv failed");
+			return -3;
+		}
+		err = handle_packet(buff, ev[i].data.fd, pev);
+		if (err < 0)
+			return err;
+	}
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	int epoll_fd, err;
+	struct proc_event proc_ev;
+	struct proc_input input;
+
+	signal(SIGINT, sigint);
+
+	if (argc > 2) {
+		printf("Expected 0(assume no-filter) or 1 argument(-f)\n");
+		exit(1);
+	}
+
+	if (argc == 2) {
+		if (strcmp(argv[1], "-f") == 0) {
+			filter = 1;
+		} else {
+			printf("Valid option : -f (for filter feature)\n");
+			exit(1);
+		}
+	}
+
+	if (filter) {
+		input.event_type = PROC_EVENT_NONZERO_EXIT;
+		input.mcast_op = PROC_CN_MCAST_LISTEN;
+		err = register_proc_netlink(&epoll_fd, (void*)&input);
+	} else {
+		enum proc_cn_mcast_op op = PROC_CN_MCAST_LISTEN;
+		err = register_proc_netlink(&epoll_fd, (void*)&op);
+	}
+
+	if (err < 0) {
+		if (err == -2)
+			close(nl_sock);
+		if (err == -3) {
+			close(nl_sock);
+			close(epoll_fd);
+		}
+		exit(1);
+	}
+
+	while (!interrupted) {
+		err = handle_events(epoll_fd, &proc_ev);
+		if (err < 0) {
+			if (ret_errno == EINTR)
+				continue;
+			if (err == -2)
+				close(nl_sock);
+			if (err == -3) {
+				close(nl_sock);
+				close(epoll_fd);
+			}
+			exit(1);
+		}
+	}
+
+	if (filter) {
+		input.mcast_op = PROC_CN_MCAST_IGNORE;
+		send_message((void*)&input);
+	} else {
+		enum proc_cn_mcast_op op = PROC_CN_MCAST_IGNORE;
+		send_message((void*)&op);
+	}
+
+	close(epoll_fd);
+	close(nl_sock);
+
+	printf("Done total count: %d\n", tcount);
+	exit(0);
+}
-- 
GitLab


From 5c9f7b04aadf79f783542d096dfbb8184e7c91f5 Mon Sep 17 00:00:00 2001
From: "justinstitt@google.com" <justinstitt@google.com>
Date: Tue, 18 Jul 2023 22:56:38 +0000
Subject: [PATCH 0325/1806] net: dsa: remove deprecated strncpy

`strncpy` is deprecated for use on NUL-terminated destination strings [1].

Even call sites utilizing length-bounded destination buffers should
switch over to using `strtomem` or `strtomem_pad`. In this case,
however, the compiler is unable to determine the size of the `data`
buffer which renders `strtomem` unusable. Due to this, `strscpy`
should be used.

It should be noted that most call sites already zero-initialize the
destination buffer. However, I've opted to use `strscpy_pad` to maintain
the same exact behavior that `strncpy` produced (zero-padded tail up to
`len`).

Also see [3].

[1]: www.kernel.org/doc/html/latest/process/deprecated.html#strncpy-on-nul-terminated-strings
[2]: elixir.bootlin.com/linux/v6.3/source/net/ethtool/ioctl.c#L1944
[3]: manpages.debian.org/testing/linux-manual-4.8/strscpy.9.en.html

Link: https://github.com/KSPP/linux/issues/90
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 527b1d576460f..48db91b33390b 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -21,6 +21,7 @@
 #include <linux/if_hsr.h>
 #include <net/dcbnl.h>
 #include <linux/netpoll.h>
+#include <linux/string.h>
 
 #include "dsa.h"
 #include "port.h"
@@ -1056,10 +1057,10 @@ static void dsa_slave_get_strings(struct net_device *dev,
 	if (stringset == ETH_SS_STATS) {
 		int len = ETH_GSTRING_LEN;
 
-		strncpy(data, "tx_packets", len);
-		strncpy(data + len, "tx_bytes", len);
-		strncpy(data + 2 * len, "rx_packets", len);
-		strncpy(data + 3 * len, "rx_bytes", len);
+		strscpy_pad(data, "tx_packets", len);
+		strscpy_pad(data + len, "tx_bytes", len);
+		strscpy_pad(data + 2 * len, "rx_packets", len);
+		strscpy_pad(data + 3 * len, "rx_bytes", len);
 		if (ds->ops->get_strings)
 			ds->ops->get_strings(ds, dp->index, stringset,
 					     data + 4 * len);
-- 
GitLab


From 1671bcfd76fdc0b9e65153cf759153083755fe4c Mon Sep 17 00:00:00 2001
From: Patrick Rohr <prohr@google.com>
Date: Wed, 19 Jul 2023 07:52:13 -0700
Subject: [PATCH 0326/1806] net: add sysctl accept_ra_min_rtr_lft
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This change adds a new sysctl accept_ra_min_rtr_lft to specify the
minimum acceptable router lifetime in an RA. If the received RA router
lifetime is less than the configured value (and not 0), the RA is
ignored.
This is useful for mobile devices, whose battery life can be impacted
by networks that configure RAs with a short lifetime. On such networks,
the device should never gain IPv6 provisioning and should attempt to
drop RAs via hardware offload, if available.

Signed-off-by: Patrick Rohr <prohr@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.rst |  8 ++++++++
 include/linux/ipv6.h                   |  1 +
 include/uapi/linux/ipv6.h              |  1 +
 net/ipv6/addrconf.c                    | 10 ++++++++++
 net/ipv6/ndisc.c                       | 18 ++++++++++++++++--
 5 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 82f2117cf2b36..37603ad6126b3 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -2288,6 +2288,14 @@ accept_ra_min_hop_limit - INTEGER
 
 	Default: 1
 
+accept_ra_min_rtr_lft - INTEGER
+	Minimum acceptable router lifetime in Router Advertisement.
+
+	RAs with a router lifetime less than this value shall be
+	ignored. RAs with a router lifetime of 0 are unaffected.
+
+	Default: 0
+
 accept_ra_pinfo - BOOLEAN
 	Learn Prefix Information in Router Advertisement.
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 839247a4f48ea..ed3d110c2eb59 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -33,6 +33,7 @@ struct ipv6_devconf {
 	__s32		accept_ra_defrtr;
 	__u32		ra_defrtr_metric;
 	__s32		accept_ra_min_hop_limit;
+	__s32		accept_ra_min_rtr_lft;
 	__s32		accept_ra_pinfo;
 	__s32		ignore_routes_with_linkdown;
 #ifdef CONFIG_IPV6_ROUTER_PREF
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index ac56605fe9bca..8b6bcbf6ed4a8 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -198,6 +198,7 @@ enum {
 	DEVCONF_IOAM6_ID_WIDE,
 	DEVCONF_NDISC_EVICT_NOCARRIER,
 	DEVCONF_ACCEPT_UNTRACKED_NA,
+	DEVCONF_ACCEPT_RA_MIN_RTR_LFT,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index e5213e598a040..19eb4b3d26ea7 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -202,6 +202,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.ra_defrtr_metric	= IP6_RT_PRIO_USER,
 	.accept_ra_from_local	= 0,
 	.accept_ra_min_hop_limit= 1,
+	.accept_ra_min_rtr_lft	= 0,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -262,6 +263,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.ra_defrtr_metric	= IP6_RT_PRIO_USER,
 	.accept_ra_from_local	= 0,
 	.accept_ra_min_hop_limit= 1,
+	.accept_ra_min_rtr_lft	= 0,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -5596,6 +5598,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide;
 	array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier;
 	array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na;
+	array[DEVCONF_ACCEPT_RA_MIN_RTR_LFT] = cnf->accept_ra_min_rtr_lft;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -6789,6 +6792,13 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "accept_ra_min_rtr_lft",
+		.data		= &ipv6_devconf.accept_ra_min_rtr_lft,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "accept_ra_pinfo",
 		.data		= &ipv6_devconf.accept_ra_pinfo,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 18634ebd20a47..29ddad1c1a2f3 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1280,6 +1280,8 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
 	if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts))
 		return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
 
+	lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
+
 	if (!ipv6_accept_ra(in6_dev)) {
 		ND_PRINTK(2, info,
 			  "RA: %s, did not accept ra for dev: %s\n",
@@ -1287,6 +1289,13 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
 		goto skip_linkparms;
 	}
 
+	if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) {
+		ND_PRINTK(2, info,
+			  "RA: router lifetime (%ds) is too short: %s\n",
+			  lifetime, skb->dev->name);
+		goto skip_linkparms;
+	}
+
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	/* skip link-specific parameters from interior routers */
 	if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) {
@@ -1339,8 +1348,6 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
 		goto skip_defrtr;
 	}
 
-	lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
-
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	pref = ra_msg->icmph.icmp6_router_pref;
 	/* 10b is handled as if it were 00b (medium) */
@@ -1492,6 +1499,13 @@ skip_linkparms:
 		goto out;
 	}
 
+	if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) {
+		ND_PRINTK(2, info,
+			  "RA: router lifetime (%ds) is too short: %s\n",
+			  lifetime, skb->dev->name);
+		goto out;
+	}
+
 #ifdef CONFIG_IPV6_ROUTE_INFO
 	if (!in6_dev->cnf.accept_ra_from_local &&
 	    ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr,
-- 
GitLab


From f5f80e32de12fad2813d37270e8364a03e6d3ef0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 20 Jul 2023 11:09:01 +0000
Subject: [PATCH 0327/1806] ipv6: remove hard coded limitation on ipv6_pinfo

IPv6 inet sockets are supposed to have a "struct ipv6_pinfo"
field at the end of their definition, so that inet6_sk_generic()
can derive from socket size the offset of the "struct ipv6_pinfo".

This is very fragile, and prevents adding bigger alignment
in sockets, because inet6_sk_generic() does not work
if the compiler adds padding after the ipv6_pinfo component.

We are currently working on a patch series to reorganize
TCP structures for better data locality and found issues
similar to the one fixed in commit f5d547676ca0
("tcp: fix tcp_inet6_sk() for 32bit kernels")

Alternative would be to force an alignment on "struct ipv6_pinfo",
greater or equal to __alignof__(any ipv6 sock) to ensure there is
no padding. This does not look great.

v2: fix typo in mptcp_proto_v6_init() (Paolo)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Chao Wu <wwchao@google.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: YiFei Zhu <zhuyifei@google.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h | 15 ++++-----------
 include/net/sock.h   |  1 +
 net/dccp/ipv6.c      |  1 +
 net/dccp/ipv6.h      |  4 ----
 net/ipv6/af_inet6.c  |  4 ++--
 net/ipv6/ping.c      |  1 +
 net/ipv6/raw.c       |  1 +
 net/ipv6/tcp_ipv6.c  |  1 +
 net/ipv6/udp.c       |  1 +
 net/ipv6/udplite.c   |  1 +
 net/l2tp/l2tp_ip6.c  |  4 +---
 net/mptcp/protocol.c |  1 +
 net/sctp/socket.c    |  1 +
 13 files changed, 16 insertions(+), 20 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ed3d110c2eb59..0295b47c10a32 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -200,14 +200,7 @@ struct inet6_cork {
 	u8 tclass;
 };
 
-/**
- * struct ipv6_pinfo - ipv6 private area
- *
- * In the struct sock hierarchy (tcp6_sock, upd6_sock, etc)
- * this _must_ be the last member, so that inet6_sk_generic
- * is able to calculate its offset from the base struct sock
- * by using the struct proto->slab_obj_size member. -acme
- */
+/* struct ipv6_pinfo - ipv6 private area */
 struct ipv6_pinfo {
 	struct in6_addr 	saddr;
 	struct in6_pktinfo	sticky_pktinfo;
@@ -307,19 +300,19 @@ struct raw6_sock {
 	__u32			offset;		/* checksum offset  */
 	struct icmp6_filter	filter;
 	__u32			ip6mr_table;
-	/* ipv6_pinfo has to be the last member of raw6_sock, see inet6_sk_generic */
+
 	struct ipv6_pinfo	inet6;
 };
 
 struct udp6_sock {
 	struct udp_sock	  udp;
-	/* ipv6_pinfo has to be the last member of udp6_sock, see inet6_sk_generic */
+
 	struct ipv6_pinfo inet6;
 };
 
 struct tcp6_sock {
 	struct tcp_sock	  tcp;
-	/* ipv6_pinfo has to be the last member of tcp6_sock, see inet6_sk_generic */
+
 	struct ipv6_pinfo inet6;
 };
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 2eb916d1ff648..7ae44bf866af5 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1339,6 +1339,7 @@ struct proto {
 
 	struct kmem_cache	*slab;
 	unsigned int		obj_size;
+	unsigned int		ipv6_pinfo_offset;
 	slab_flags_t		slab_flags;
 	unsigned int		useroffset;	/* Usercopy region offset */
 	unsigned int		usersize;	/* Usercopy region size */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 7249ef2181787..e03b5331df6d7 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1056,6 +1056,7 @@ static struct proto dccp_v6_prot = {
 	.orphan_count	   = &dccp_orphan_count,
 	.max_header	   = MAX_DCCP_HEADER,
 	.obj_size	   = sizeof(struct dccp6_sock),
+	.ipv6_pinfo_offset = offsetof(struct dccp6_sock, inet6),
 	.slab_flags	   = SLAB_TYPESAFE_BY_RCU,
 	.rsk_prot	   = &dccp6_request_sock_ops,
 	.twsk_prot	   = &dccp6_timewait_sock_ops,
diff --git a/net/dccp/ipv6.h b/net/dccp/ipv6.h
index 7e4c2a3b322b5..c5d14c48def17 100644
--- a/net/dccp/ipv6.h
+++ b/net/dccp/ipv6.h
@@ -13,10 +13,6 @@
 
 struct dccp6_sock {
 	struct dccp_sock  dccp;
-	/*
-	 * ipv6_pinfo has to be the last member of dccp6_sock,
-	 * see inet6_sk_generic.
-	 */
 	struct ipv6_pinfo inet6;
 };
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 5d593ddc0347e..9f9c4b838664a 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -102,9 +102,9 @@ bool ipv6_mod_enabled(void)
 }
 EXPORT_SYMBOL_GPL(ipv6_mod_enabled);
 
-static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
+static struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
 {
-	const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
+	const int offset = sk->sk_prot->ipv6_pinfo_offset;
 
 	return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
 }
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index f804c11e2146c..2a0e8bc073983 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -215,6 +215,7 @@ struct proto pingv6_prot = {
 	.get_port =	ping_get_port,
 	.put_port =	ping_unhash,
 	.obj_size =	sizeof(struct raw6_sock),
+	.ipv6_pinfo_offset = offsetof(struct raw6_sock, inet6),
 };
 EXPORT_SYMBOL_GPL(pingv6_prot);
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ac1cef094c5f2..0fcf1b8908079 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1216,6 +1216,7 @@ struct proto rawv6_prot = {
 	.hash		   = raw_hash_sk,
 	.unhash		   = raw_unhash_sk,
 	.obj_size	   = sizeof(struct raw6_sock),
+	.ipv6_pinfo_offset = offsetof(struct raw6_sock, inet6),
 	.useroffset	   = offsetof(struct raw6_sock, filter),
 	.usersize	   = sizeof_field(struct raw6_sock, filter),
 	.h.raw_hash	   = &raw_v6_hashinfo,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4714eb695913d..1b4529e833a19 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2175,6 +2175,7 @@ struct proto tcpv6_prot = {
 	.sysctl_rmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_rmem),
 	.max_header		= MAX_TCP_HEADER,
 	.obj_size		= sizeof(struct tcp6_sock),
+	.ipv6_pinfo_offset = offsetof(struct tcp6_sock, inet6),
 	.slab_flags		= SLAB_TYPESAFE_BY_RCU,
 	.twsk_prot		= &tcp6_timewait_sock_ops,
 	.rsk_prot		= &tcp6_request_sock_ops,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index b7c972aa09a75..95c75d8f73d51 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1798,6 +1798,7 @@ struct proto udpv6_prot = {
 	.sysctl_wmem_offset     = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
 	.sysctl_rmem_offset     = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
 	.obj_size		= sizeof(struct udp6_sock),
+	.ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6),
 	.h.udp_table		= NULL,
 	.diag_destroy		= udp_abort,
 };
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 8e010d07917a7..267d491e97075 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -67,6 +67,7 @@ struct proto udplitev6_prot = {
 	.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
 	.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
 	.obj_size	   = sizeof(struct udp6_sock),
+	.ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6),
 	.h.udp_table	   = &udplite_table,
 };
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index b1623f9c4f921..2eee95a00c053 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -36,9 +36,6 @@ struct l2tp_ip6_sock {
 	u32			conn_id;
 	u32			peer_conn_id;
 
-	/* ipv6_pinfo has to be the last member of l2tp_ip6_sock, see
-	 * inet6_sk_generic
-	 */
 	struct ipv6_pinfo	inet6;
 };
 
@@ -730,6 +727,7 @@ static struct proto l2tp_ip6_prot = {
 	.hash		   = l2tp_ip6_hash,
 	.unhash		   = l2tp_ip6_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip6_sock),
+	.ipv6_pinfo_offset = offsetof(struct l2tp_ip6_sock, inet6),
 };
 
 static const struct proto_ops l2tp_ip6_ops = {
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3613489eb6e3b..22323b1fa1842 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3988,6 +3988,7 @@ int __init mptcp_proto_v6_init(void)
 	strcpy(mptcp_v6_prot.name, "MPTCPv6");
 	mptcp_v6_prot.slab = NULL;
 	mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock);
+	mptcp_v6_prot.ipv6_pinfo_offset = offsetof(struct mptcp6_sock, np);
 
 	err = proto_register(&mptcp_v6_prot, 1);
 	if (err)
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9388d98aebc03..6e3d28aa587cd 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -9732,6 +9732,7 @@ struct proto sctpv6_prot = {
 	.unhash		= sctp_unhash,
 	.no_autobind	= true,
 	.obj_size	= sizeof(struct sctp6_sock),
+	.ipv6_pinfo_offset = offsetof(struct sctp6_sock, inet6),
 	.useroffset	= offsetof(struct sctp6_sock, sctp.subscribe),
 	.usersize	= offsetof(struct sctp6_sock, sctp.initmsg) -
 				offsetof(struct sctp6_sock, sctp.subscribe) +
-- 
GitLab


From 79e71d9569959b15ec7b150d0c43f993c2f6e32e Mon Sep 17 00:00:00 2001
From: Samin Guo <samin.guo@starfivetech.com>
Date: Thu, 20 Jul 2023 19:15:08 +0800
Subject: [PATCH 0328/1806] dt-bindings: net: motorcomm: Add pad driver
 strength cfg

The motorcomm phy (YT8531) supports the ability to adjust the drive
strength of the rx_clk/rx_data.

The YT8531 RGMII LDO voltage supports 1.8V/3.3V, and the
LDO voltage can be configured with hardware pull-up resistors to match
the SOC voltage (usually 1.8V). The software can read the registers
0xA001 obtain the current LDO voltage value.

Reviewed-by: Hal Feng <hal.feng@starfivetech.com>
Signed-off-by: Samin Guo <samin.guo@starfivetech.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../bindings/net/motorcomm,yt8xxx.yaml        | 34 +++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/motorcomm,yt8xxx.yaml b/Documentation/devicetree/bindings/net/motorcomm,yt8xxx.yaml
index 157e3bbcaf6f7..26688e2302eaa 100644
--- a/Documentation/devicetree/bindings/net/motorcomm,yt8xxx.yaml
+++ b/Documentation/devicetree/bindings/net/motorcomm,yt8xxx.yaml
@@ -52,6 +52,40 @@ properties:
       for a timer.
     type: boolean
 
+  motorcomm,rx-clk-drv-microamp:
+    description: |
+      drive strength of rx_clk rgmii pad.
+      The YT8531 RGMII LDO voltage supports 1.8V/3.3V, and the LDO voltage can
+      be configured with hardware pull-up resistors to match the SOC voltage
+      (usually 1.8V).
+      The software can read the registers to obtain the LDO voltage and configure
+      the legal drive strength(curren).
+      =====================================================
+      | voltage |        current Available (uA)           |
+      |   1.8v  | 1200 2100 2700 2910 3110 3600 3970 4350 |
+      |   3.3v  | 3070 4080 4370 4680 5020 5450 5740 6140 |
+      =====================================================
+    enum: [ 1200, 2100, 2700, 2910, 3070, 3110, 3600, 3970,
+            4080, 4350, 4370, 4680, 5020, 5450, 5740, 6140 ]
+    default: 2910
+
+  motorcomm,rx-data-drv-microamp:
+    description: |
+      drive strength of rx_data/rx_ctl rgmii pad.
+      The YT8531 RGMII LDO voltage supports 1.8V/3.3V, and the LDO voltage can
+      be configured with hardware pull-up resistors to match the SOC voltage
+      (usually 1.8V).
+      The software can read the registers to obtain the LDO voltage and configure
+      the legal drive strength(curren).
+      =====================================================
+      | voltage |        current Available (uA)           |
+      |   1.8v  | 1200 2100 2700 2910 3110 3600 3970 4350 |
+      |   3.3v  | 3070 4080 4370 4680 5020 5450 5740 6140 |
+      =====================================================
+    enum: [ 1200, 2100, 2700, 2910, 3070, 3110, 3600, 3970,
+            4080, 4350, 4370, 4680, 5020, 5450, 5740, 6140 ]
+    default: 2910
+
   motorcomm,tx-clk-adj-enabled:
     description: |
       This configuration is mainly to adapt to VF2 with JH7110 SoC.
-- 
GitLab


From 7a561e9351ae7e3fb1f08584d40b49c1e55dde60 Mon Sep 17 00:00:00 2001
From: Samin Guo <samin.guo@starfivetech.com>
Date: Thu, 20 Jul 2023 19:15:09 +0800
Subject: [PATCH 0329/1806] net: phy: motorcomm: Add pad drive strength cfg
 support

The motorcomm phy (YT8531) supports the ability to adjust the drive
strength of the rx_clk/rx_data, and the default strength may not be
suitable for all boards. So add configurable options to better match
the boards.(e.g. StarFive VisionFive 2)

When we configure the drive strength, we need to read the current
LDO voltage value to ensure that it is a legal value at that LDO
voltage.

Reviewed-by: Hal Feng <hal.feng@starfivetech.com>
Signed-off-by: Samin Guo <samin.guo@starfivetech.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/motorcomm.c | 118 ++++++++++++++++++++++++++++++++++++
 1 file changed, 118 insertions(+)

diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c
index 2fa5a90e073bd..7a11fdb687cc4 100644
--- a/drivers/net/phy/motorcomm.c
+++ b/drivers/net/phy/motorcomm.c
@@ -163,6 +163,10 @@
 
 #define YT8521_CHIP_CONFIG_REG			0xA001
 #define YT8521_CCR_SW_RST			BIT(15)
+#define YT8531_RGMII_LDO_VOL_MASK		GENMASK(5, 4)
+#define YT8531_LDO_VOL_3V3			0x0
+#define YT8531_LDO_VOL_1V8			0x2
+
 /* 1b0 disable 1.9ns rxc clock delay  *default*
  * 1b1 enable 1.9ns rxc clock delay
  */
@@ -236,6 +240,12 @@
  */
 #define YTPHY_WCR_TYPE_PULSE			BIT(0)
 
+#define YTPHY_PAD_DRIVE_STRENGTH_REG		0xA010
+#define YT8531_RGMII_RXC_DS_MASK		GENMASK(15, 13)
+#define YT8531_RGMII_RXD_DS_HI_MASK		BIT(12)		/* Bit 2 of rxd_ds */
+#define YT8531_RGMII_RXD_DS_LOW_MASK		GENMASK(5, 4)	/* Bit 1/0 of rxd_ds */
+#define YT8531_RGMII_RX_DS_DEFAULT		0x3
+
 #define YTPHY_SYNCE_CFG_REG			0xA012
 #define YT8521_SCR_SYNCE_ENABLE			BIT(5)
 /* 1b0 output 25m clock
@@ -834,6 +844,110 @@ static int ytphy_rgmii_clk_delay_config_with_lock(struct phy_device *phydev)
 	return ret;
 }
 
+/**
+ * struct ytphy_ldo_vol_map - map a current value to a register value
+ * @vol: ldo voltage
+ * @ds:  value in the register
+ * @cur: value in device configuration
+ */
+struct ytphy_ldo_vol_map {
+	u32 vol;
+	u32 ds;
+	u32 cur;
+};
+
+static const struct ytphy_ldo_vol_map yt8531_ldo_vol[] = {
+	{.vol = YT8531_LDO_VOL_1V8, .ds = 0, .cur = 1200},
+	{.vol = YT8531_LDO_VOL_1V8, .ds = 1, .cur = 2100},
+	{.vol = YT8531_LDO_VOL_1V8, .ds = 2, .cur = 2700},
+	{.vol = YT8531_LDO_VOL_1V8, .ds = 3, .cur = 2910},
+	{.vol = YT8531_LDO_VOL_1V8, .ds = 4, .cur = 3110},
+	{.vol = YT8531_LDO_VOL_1V8, .ds = 5, .cur = 3600},
+	{.vol = YT8531_LDO_VOL_1V8, .ds = 6, .cur = 3970},
+	{.vol = YT8531_LDO_VOL_1V8, .ds = 7, .cur = 4350},
+	{.vol = YT8531_LDO_VOL_3V3, .ds = 0, .cur = 3070},
+	{.vol = YT8531_LDO_VOL_3V3, .ds = 1, .cur = 4080},
+	{.vol = YT8531_LDO_VOL_3V3, .ds = 2, .cur = 4370},
+	{.vol = YT8531_LDO_VOL_3V3, .ds = 3, .cur = 4680},
+	{.vol = YT8531_LDO_VOL_3V3, .ds = 4, .cur = 5020},
+	{.vol = YT8531_LDO_VOL_3V3, .ds = 5, .cur = 5450},
+	{.vol = YT8531_LDO_VOL_3V3, .ds = 6, .cur = 5740},
+	{.vol = YT8531_LDO_VOL_3V3, .ds = 7, .cur = 6140},
+};
+
+static u32 yt8531_get_ldo_vol(struct phy_device *phydev)
+{
+	u32 val;
+
+	val = ytphy_read_ext_with_lock(phydev, YT8521_CHIP_CONFIG_REG);
+	val = FIELD_GET(YT8531_RGMII_LDO_VOL_MASK, val);
+
+	return val <= YT8531_LDO_VOL_1V8 ? val : YT8531_LDO_VOL_1V8;
+}
+
+static int yt8531_get_ds_map(struct phy_device *phydev, u32 cur)
+{
+	u32 vol;
+	int i;
+
+	vol = yt8531_get_ldo_vol(phydev);
+	for (i = 0; i < ARRAY_SIZE(yt8531_ldo_vol); i++) {
+		if (yt8531_ldo_vol[i].vol == vol && yt8531_ldo_vol[i].cur == cur)
+			return yt8531_ldo_vol[i].ds;
+	}
+
+	return -EINVAL;
+}
+
+static int yt8531_set_ds(struct phy_device *phydev)
+{
+	struct device_node *node = phydev->mdio.dev.of_node;
+	u32 ds_field_low, ds_field_hi, val;
+	int ret, ds;
+
+	/* set rgmii rx clk driver strength */
+	if (!of_property_read_u32(node, "motorcomm,rx-clk-drv-microamp", &val)) {
+		ds = yt8531_get_ds_map(phydev, val);
+		if (ds < 0)
+			return dev_err_probe(&phydev->mdio.dev, ds,
+					     "No matching current value was found.\n");
+	} else {
+		ds = YT8531_RGMII_RX_DS_DEFAULT;
+	}
+
+	ret = ytphy_modify_ext_with_lock(phydev,
+					 YTPHY_PAD_DRIVE_STRENGTH_REG,
+					 YT8531_RGMII_RXC_DS_MASK,
+					 FIELD_PREP(YT8531_RGMII_RXC_DS_MASK, ds));
+	if (ret < 0)
+		return ret;
+
+	/* set rgmii rx data driver strength */
+	if (!of_property_read_u32(node, "motorcomm,rx-data-drv-microamp", &val)) {
+		ds = yt8531_get_ds_map(phydev, val);
+		if (ds < 0)
+			return dev_err_probe(&phydev->mdio.dev, ds,
+					     "No matching current value was found.\n");
+	} else {
+		ds = YT8531_RGMII_RX_DS_DEFAULT;
+	}
+
+	ds_field_hi = FIELD_GET(BIT(2), ds);
+	ds_field_hi = FIELD_PREP(YT8531_RGMII_RXD_DS_HI_MASK, ds_field_hi);
+
+	ds_field_low = FIELD_GET(GENMASK(1, 0), ds);
+	ds_field_low = FIELD_PREP(YT8531_RGMII_RXD_DS_LOW_MASK, ds_field_low);
+
+	ret = ytphy_modify_ext_with_lock(phydev,
+					 YTPHY_PAD_DRIVE_STRENGTH_REG,
+					 YT8531_RGMII_RXD_DS_LOW_MASK | YT8531_RGMII_RXD_DS_HI_MASK,
+					 ds_field_low | ds_field_hi);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 /**
  * yt8521_probe() - read chip config then set suitable polling_mode
  * @phydev: a pointer to a &struct phy_device
@@ -1518,6 +1632,10 @@ static int yt8531_config_init(struct phy_device *phydev)
 			return ret;
 	}
 
+	ret = yt8531_set_ds(phydev);
+	if (ret < 0)
+		return ret;
+
 	return 0;
 }
 
-- 
GitLab


From 87d7a9f3734fb314a15b579137cd9d69892b36aa Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Thu, 20 Jul 2023 12:08:13 -0700
Subject: [PATCH 0330/1806] ionic: extract common bits from ionic_remove

Pull out a chunk of code from ionic_remove() that will
be common in teardown paths.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/pensando/ionic/ionic_bus_pci.c   | 25 ++++++++++---------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index ab7d217b98b37..2bc3cab3967d4 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -213,6 +213,13 @@ out:
 	return ret;
 }
 
+static void ionic_clear_pci(struct ionic *ionic)
+{
+	ionic_unmap_bars(ionic);
+	pci_release_regions(ionic->pdev);
+	pci_disable_device(ionic->pdev);
+}
+
 static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct device *dev = &pdev->dev;
@@ -249,20 +256,20 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	err = pci_request_regions(pdev, IONIC_DRV_NAME);
 	if (err) {
 		dev_err(dev, "Cannot request PCI regions: %d, aborting\n", err);
-		goto err_out_pci_disable_device;
+		goto err_out_clear_pci;
 	}
 
 	pcie_print_link_status(pdev);
 
 	err = ionic_map_bars(ionic);
 	if (err)
-		goto err_out_pci_release_regions;
+		goto err_out_clear_pci;
 
 	/* Configure the device */
 	err = ionic_setup(ionic);
 	if (err) {
 		dev_err(dev, "Cannot setup device: %d, aborting\n", err);
-		goto err_out_unmap_bars;
+		goto err_out_clear_pci;
 	}
 	pci_set_master(pdev);
 
@@ -353,12 +360,8 @@ err_out_reset:
 	ionic_reset(ionic);
 err_out_teardown:
 	ionic_dev_teardown(ionic);
-err_out_unmap_bars:
-	ionic_unmap_bars(ionic);
-err_out_pci_release_regions:
-	pci_release_regions(pdev);
-err_out_pci_disable_device:
-	pci_disable_device(pdev);
+err_out_clear_pci:
+	ionic_clear_pci(ionic);
 err_out_debugfs_del_dev:
 	ionic_debugfs_del_dev(ionic);
 err_out_clear_drvdata:
@@ -386,9 +389,7 @@ static void ionic_remove(struct pci_dev *pdev)
 	ionic_port_reset(ionic);
 	ionic_reset(ionic);
 	ionic_dev_teardown(ionic);
-	ionic_unmap_bars(ionic);
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
+	ionic_clear_pci(ionic);
 	ionic_debugfs_del_dev(ionic);
 	mutex_destroy(&ionic->dev_cmd_lock);
 	ionic_devlink_free(ionic);
-- 
GitLab


From 0de38d9f1dba2336f84799824af08263fc407dd1 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Thu, 20 Jul 2023 12:08:14 -0700
Subject: [PATCH 0331/1806] ionic: extract common bits from ionic_probe

Pull out some chunks of code from ionic_probe() that will
be common in rebuild paths.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/pensando/ionic/ionic_bus_pci.c   | 84 +++++++++++--------
 1 file changed, 49 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index 2bc3cab3967d4..bcce613449c2a 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -220,30 +220,12 @@ static void ionic_clear_pci(struct ionic *ionic)
 	pci_disable_device(ionic->pdev);
 }
 
-static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+static int ionic_setup_one(struct ionic *ionic)
 {
-	struct device *dev = &pdev->dev;
-	struct ionic *ionic;
-	int num_vfs;
+	struct pci_dev *pdev = ionic->pdev;
+	struct device *dev = ionic->dev;
 	int err;
 
-	ionic = ionic_devlink_alloc(dev);
-	if (!ionic)
-		return -ENOMEM;
-
-	ionic->pdev = pdev;
-	ionic->dev = dev;
-	pci_set_drvdata(pdev, ionic);
-	mutex_init(&ionic->dev_cmd_lock);
-
-	/* Query system for DMA addressing limitation for the device. */
-	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(IONIC_ADDR_LEN));
-	if (err) {
-		dev_err(dev, "Unable to obtain 64-bit DMA for consistent allocations, aborting.  err=%d\n",
-			err);
-		goto err_out_clear_drvdata;
-	}
-
 	ionic_debugfs_add_dev(ionic);
 
 	/* Setup PCI device */
@@ -258,7 +240,6 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_err(dev, "Cannot request PCI regions: %d, aborting\n", err);
 		goto err_out_clear_pci;
 	}
-
 	pcie_print_link_status(pdev);
 
 	err = ionic_map_bars(ionic);
@@ -286,24 +267,64 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_teardown;
 	}
 
-	/* Configure the ports */
+	/* Configure the port */
 	err = ionic_port_identify(ionic);
 	if (err) {
 		dev_err(dev, "Cannot identify port: %d, aborting\n", err);
-		goto err_out_reset;
+		goto err_out_teardown;
 	}
 
 	err = ionic_port_init(ionic);
 	if (err) {
 		dev_err(dev, "Cannot init port: %d, aborting\n", err);
-		goto err_out_reset;
+		goto err_out_teardown;
+	}
+
+	return 0;
+
+err_out_teardown:
+	ionic_dev_teardown(ionic);
+err_out_clear_pci:
+	ionic_clear_pci(ionic);
+err_out_debugfs_del_dev:
+	ionic_debugfs_del_dev(ionic);
+
+	return err;
+}
+
+static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct device *dev = &pdev->dev;
+	struct ionic *ionic;
+	int num_vfs;
+	int err;
+
+	ionic = ionic_devlink_alloc(dev);
+	if (!ionic)
+		return -ENOMEM;
+
+	ionic->pdev = pdev;
+	ionic->dev = dev;
+	pci_set_drvdata(pdev, ionic);
+	mutex_init(&ionic->dev_cmd_lock);
+
+	/* Query system for DMA addressing limitation for the device. */
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(IONIC_ADDR_LEN));
+	if (err) {
+		dev_err(dev, "Unable to obtain 64-bit DMA for consistent allocations, aborting.  err=%d\n",
+			err);
+		goto err_out;
 	}
 
+	err = ionic_setup_one(ionic);
+	if (err)
+		goto err_out;
+
 	/* Allocate and init the LIF */
 	err = ionic_lif_size(ionic);
 	if (err) {
 		dev_err(dev, "Cannot size LIF: %d, aborting\n", err);
-		goto err_out_port_reset;
+		goto err_out_pci;
 	}
 
 	err = ionic_lif_alloc(ionic);
@@ -354,17 +375,10 @@ err_out_free_lifs:
 	ionic->lif = NULL;
 err_out_free_irqs:
 	ionic_bus_free_irq_vectors(ionic);
-err_out_port_reset:
-	ionic_port_reset(ionic);
-err_out_reset:
-	ionic_reset(ionic);
-err_out_teardown:
+err_out_pci:
 	ionic_dev_teardown(ionic);
-err_out_clear_pci:
 	ionic_clear_pci(ionic);
-err_out_debugfs_del_dev:
-	ionic_debugfs_del_dev(ionic);
-err_out_clear_drvdata:
+err_out:
 	mutex_destroy(&ionic->dev_cmd_lock);
 	ionic_devlink_free(ionic);
 
-- 
GitLab


From 30d2e073964dbc7b7e1e8ded12924a8f0cc5cedf Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Thu, 20 Jul 2023 12:08:15 -0700
Subject: [PATCH 0332/1806] ionic: pull out common bits from fw_up

Pull out some code from ionic_lif_handle_fw_up() that can be
used in the coming FLR recovery patch.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/pensando/ionic/ionic_lif.c   | 64 ++++++++++++-------
 1 file changed, 42 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 612b0015dc43e..2d03c1b995bc0 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3266,27 +3266,11 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif)
 	dev_info(ionic->dev, "FW Down: LIFs stopped\n");
 }
 
-static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
+static int ionic_restart_lif(struct ionic_lif *lif)
 {
 	struct ionic *ionic = lif->ionic;
 	int err;
 
-	if (!test_bit(IONIC_LIF_F_FW_RESET, lif->state))
-		return;
-
-	dev_info(ionic->dev, "FW Up: restarting LIFs\n");
-
-	ionic_init_devinfo(ionic);
-	err = ionic_identify(ionic);
-	if (err)
-		goto err_out;
-	err = ionic_port_identify(ionic);
-	if (err)
-		goto err_out;
-	err = ionic_port_init(ionic);
-	if (err)
-		goto err_out;
-
 	mutex_lock(&lif->queue_lock);
 
 	if (test_and_clear_bit(IONIC_LIF_F_BROKEN, lif->state))
@@ -3322,12 +3306,8 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 	clear_bit(IONIC_LIF_F_FW_RESET, lif->state);
 	ionic_link_status_check_request(lif, CAN_SLEEP);
 	netif_device_attach(lif->netdev);
-	dev_info(ionic->dev, "FW Up: LIFs restarted\n");
-
-	/* restore the hardware timestamping queues */
-	ionic_lif_hwstamp_replay(lif);
 
-	return;
+	return 0;
 
 err_txrx_free:
 	ionic_txrx_free(lif);
@@ -3337,6 +3317,46 @@ err_qcqs_free:
 	ionic_qcqs_free(lif);
 err_unlock:
 	mutex_unlock(&lif->queue_lock);
+
+	return err;
+}
+
+static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
+{
+	struct ionic *ionic = lif->ionic;
+	int err;
+
+	if (!test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		return;
+
+	dev_info(ionic->dev, "FW Up: restarting LIFs\n");
+
+	/* This is a little different from what happens at
+	 * probe time because the LIF already exists so we
+	 * just need to reanimate it.
+	 */
+	ionic_init_devinfo(ionic);
+	err = ionic_identify(ionic);
+	if (err)
+		goto err_out;
+	err = ionic_port_identify(ionic);
+	if (err)
+		goto err_out;
+	err = ionic_port_init(ionic);
+	if (err)
+		goto err_out;
+
+	err = ionic_restart_lif(lif);
+	if (err)
+		goto err_out;
+
+	dev_info(ionic->dev, "FW Up: LIFs restarted\n");
+
+	/* restore the hardware timestamping queues */
+	ionic_lif_hwstamp_replay(lif);
+
+	return;
+
 err_out:
 	dev_err(ionic->dev, "FW Up: LIFs restart failed - err %d\n", err);
 }
-- 
GitLab


From a79b559e99bea6e3284366265d1c63b28ff0ca2e Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Thu, 20 Jul 2023 12:08:16 -0700
Subject: [PATCH 0333/1806] ionic: add FLR recovery support

Add support for the PCI reset handlers in order to manage an FLR event.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/pensando/ionic/ionic_bus_pci.c   | 53 +++++++++++++++++++
 .../net/ethernet/pensando/ionic/ionic_lif.c   |  8 +--
 .../net/ethernet/pensando/ionic/ionic_lif.h   |  5 ++
 3 files changed, 62 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index bcce613449c2a..d6ce113a4210b 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -409,12 +409,65 @@ static void ionic_remove(struct pci_dev *pdev)
 	ionic_devlink_free(ionic);
 }
 
+static void ionic_reset_prepare(struct pci_dev *pdev)
+{
+	struct ionic *ionic = pci_get_drvdata(pdev);
+	struct ionic_lif *lif = ionic->lif;
+
+	dev_dbg(ionic->dev, "%s: device stopping\n", __func__);
+
+	del_timer_sync(&ionic->watchdog_timer);
+	cancel_work_sync(&lif->deferred.work);
+
+	mutex_lock(&lif->queue_lock);
+	ionic_stop_queues_reconfig(lif);
+	ionic_txrx_free(lif);
+	ionic_lif_deinit(lif);
+	ionic_qcqs_free(lif);
+	mutex_unlock(&lif->queue_lock);
+
+	ionic_dev_teardown(ionic);
+	ionic_clear_pci(ionic);
+	ionic_debugfs_del_dev(ionic);
+}
+
+static void ionic_reset_done(struct pci_dev *pdev)
+{
+	struct ionic *ionic = pci_get_drvdata(pdev);
+	struct ionic_lif *lif = ionic->lif;
+	int err;
+
+	err = ionic_setup_one(ionic);
+	if (err)
+		goto err_out;
+
+	ionic_debugfs_add_sizes(ionic);
+	ionic_debugfs_add_lif(ionic->lif);
+
+	err = ionic_restart_lif(lif);
+	if (err)
+		goto err_out;
+
+	mod_timer(&ionic->watchdog_timer, jiffies + 1);
+
+err_out:
+	dev_dbg(ionic->dev, "%s: device recovery %s\n",
+		__func__, err ? "failed" : "done");
+}
+
+static const struct pci_error_handlers ionic_err_handler = {
+	/* FLR handling */
+	.reset_prepare      = ionic_reset_prepare,
+	.reset_done         = ionic_reset_done,
+};
+
 static struct pci_driver ionic_driver = {
 	.name = IONIC_DRV_NAME,
 	.id_table = ionic_id_table,
 	.probe = ionic_probe,
 	.remove = ionic_remove,
 	.sriov_configure = ionic_sriov_configure,
+	.err_handler = &ionic_err_handler
 };
 
 int ionic_bus_register_driver(void)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 2d03c1b995bc0..adc05f944c140 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -434,7 +434,7 @@ static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq)
 	}
 }
 
-static void ionic_qcqs_free(struct ionic_lif *lif)
+void ionic_qcqs_free(struct ionic_lif *lif)
 {
 	struct device *dev = lif->ionic->dev;
 	struct ionic_qcq *adminqcq;
@@ -1754,7 +1754,7 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa)
 	return ionic_lif_addr_add(netdev_priv(netdev), mac);
 }
 
-static void ionic_stop_queues_reconfig(struct ionic_lif *lif)
+void ionic_stop_queues_reconfig(struct ionic_lif *lif)
 {
 	/* Stop and clean the queues before reconfiguration */
 	netif_device_detach(lif->netdev);
@@ -2009,7 +2009,7 @@ static void ionic_txrx_deinit(struct ionic_lif *lif)
 	}
 }
 
-static void ionic_txrx_free(struct ionic_lif *lif)
+void ionic_txrx_free(struct ionic_lif *lif)
 {
 	unsigned int i;
 
@@ -3266,7 +3266,7 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif)
 	dev_info(ionic->dev, "FW Down: LIFs stopped\n");
 }
 
-static int ionic_restart_lif(struct ionic_lif *lif)
+int ionic_restart_lif(struct ionic_lif *lif)
 {
 	struct ionic *ionic = lif->ionic;
 	int err;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index fd2ea670e7d84..457c24195ca61 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -325,6 +325,11 @@ void ionic_lif_deinit(struct ionic_lif *lif);
 int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr);
 int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr);
 
+void ionic_stop_queues_reconfig(struct ionic_lif *lif);
+void ionic_txrx_free(struct ionic_lif *lif);
+void ionic_qcqs_free(struct ionic_lif *lif);
+int ionic_restart_lif(struct ionic_lif *lif);
+
 int ionic_lif_register(struct ionic_lif *lif);
 void ionic_lif_unregister(struct ionic_lif *lif);
 int ionic_lif_identify(struct ionic *ionic, u8 lif_type,
-- 
GitLab


From ee95d4420a2f4f02a2bf2b9ff0086ddc31965187 Mon Sep 17 00:00:00 2001
From: Wojciech Drewek <wojciech.drewek@intel.com>
Date: Wed, 12 Jul 2023 13:03:26 +0200
Subject: [PATCH 0334/1806] ice: Skip adv rules removal upon switchdev release

Advanced rules for ctrl VSI will be removed anyway when the
VSI will cleaned up, no need to do it explicitly.

Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_eswitch.c |  1 -
 drivers/net/ethernet/intel/ice/ice_switch.c  | 53 --------------------
 drivers/net/ethernet/intel/ice/ice_switch.h  |  1 -
 3 files changed, 55 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index ad0a007b73988..be5b22691f7cb 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -503,7 +503,6 @@ static void ice_eswitch_disable_switchdev(struct ice_pf *pf)
 
 	ice_eswitch_napi_disable(pf);
 	ice_eswitch_release_env(pf);
-	ice_rem_adv_rule_for_vsi(&pf->hw, ctrl_vsi->idx);
 	ice_eswitch_release_reprs(pf, ctrl_vsi);
 	ice_vsi_release(ctrl_vsi);
 	ice_repr_rem_from_all_vfs(pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 6db4ca7978cbb..81f45d7e76dea 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -6532,59 +6532,6 @@ ice_rem_adv_rule_by_id(struct ice_hw *hw,
 	return -ENOENT;
 }
 
-/**
- * ice_rem_adv_rule_for_vsi - removes existing advanced switch rules for a
- *                            given VSI handle
- * @hw: pointer to the hardware structure
- * @vsi_handle: VSI handle for which we are supposed to remove all the rules.
- *
- * This function is used to remove all the rules for a given VSI and as soon
- * as removing a rule fails, it will return immediately with the error code,
- * else it will return success.
- */
-int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle)
-{
-	struct ice_adv_fltr_mgmt_list_entry *list_itr, *tmp_entry;
-	struct ice_vsi_list_map_info *map_info;
-	struct ice_adv_rule_info rinfo;
-	struct list_head *list_head;
-	struct ice_switch_info *sw;
-	int status;
-	u8 rid;
-
-	sw = hw->switch_info;
-	for (rid = 0; rid < ICE_MAX_NUM_RECIPES; rid++) {
-		if (!sw->recp_list[rid].recp_created)
-			continue;
-		if (!sw->recp_list[rid].adv_rule)
-			continue;
-
-		list_head = &sw->recp_list[rid].filt_rules;
-		list_for_each_entry_safe(list_itr, tmp_entry, list_head,
-					 list_entry) {
-			rinfo = list_itr->rule_info;
-
-			if (rinfo.sw_act.fltr_act == ICE_FWD_TO_VSI_LIST) {
-				map_info = list_itr->vsi_list_info;
-				if (!map_info)
-					continue;
-
-				if (!test_bit(vsi_handle, map_info->vsi_map))
-					continue;
-			} else if (rinfo.sw_act.vsi_handle != vsi_handle) {
-				continue;
-			}
-
-			rinfo.sw_act.vsi_handle = vsi_handle;
-			status = ice_rem_adv_rule(hw, list_itr->lkups,
-						  list_itr->lkups_cnt, &rinfo);
-			if (status)
-				return status;
-		}
-	}
-	return 0;
-}
-
 /**
  * ice_replay_vsi_adv_rule - Replay advanced rule for requested VSI
  * @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index c84b56fe84a5e..db08509805cec 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -379,7 +379,6 @@ int
 ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 			 bool rm_vlan_promisc);
 
-int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle);
 int
 ice_rem_adv_rule_by_id(struct ice_hw *hw,
 		       struct ice_rule_query_data *remove_entry);
-- 
GitLab


From 2571a3fa6251662e5201372f889bf93f234c8261 Mon Sep 17 00:00:00 2001
From: Wojciech Drewek <wojciech.drewek@intel.com>
Date: Wed, 12 Jul 2023 13:03:27 +0200
Subject: [PATCH 0335/1806] ice: Prohibit rx mode change in switchdev mode

Don't allow to change promisc mode in switchdev mode.
When switchdev is configured, PF netdev is set to be a
default VSI. This is needed for the slow-path to work correctly.
All the unmatched packets will be directed to PF netdev.

It is possible that this setting might be overwritten by
ndo_set_rx_mode. Prevent this by checking if switchdev is
enabled in ice_set_rx_mode.

Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 4f70f5553c803..d1f2077676e46 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5704,7 +5704,7 @@ static void ice_set_rx_mode(struct net_device *netdev)
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
 
-	if (!vsi)
+	if (!vsi || ice_is_switchdev_running(vsi->back))
 		return;
 
 	/* Set the flags to synchronize filters
-- 
GitLab


From 7aa529a69e92b9aff585e569d5003f7c15d8d60b Mon Sep 17 00:00:00 2001
From: Wojciech Drewek <wojciech.drewek@intel.com>
Date: Wed, 12 Jul 2023 13:03:28 +0200
Subject: [PATCH 0336/1806] ice: Don't tx before switchdev is fully configured

There is possibility that ice_eswitch_port_start_xmit might be
called while some resources are still not allocated which might
cause NULL pointer dereference. Fix this by checking if switchdev
configuration was finished.

Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_eswitch.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index be5b22691f7cb..15a4c148c28b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -331,6 +331,9 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	np = netdev_priv(netdev);
 	vsi = np->vsi;
 
+	if (!vsi || !ice_is_switchdev_running(vsi->back))
+		return NETDEV_TX_BUSY;
+
 	if (ice_is_reset_in_progress(vsi->back->state) ||
 	    test_bit(ICE_VF_DIS, vsi->back->state))
 		return NETDEV_TX_BUSY;
-- 
GitLab


From 6ab1155798c356630a7ad1e4baae44eb6414f5ba Mon Sep 17 00:00:00 2001
From: Wojciech Drewek <wojciech.drewek@intel.com>
Date: Wed, 12 Jul 2023 13:03:29 +0200
Subject: [PATCH 0337/1806] ice: Disable vlan pruning for uplink VSI

In switchdev mode, uplink VSI is configured to be default
VSI which means it will receive all unmatched packets.
In order to receive vlan packets we need to disable vlan pruning
as well. This is done by dis_rx_filtering vlan op.

Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_eswitch.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index 15a4c148c28b9..bfd003135fc8e 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -103,6 +103,10 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 		rule_added = true;
 	}
 
+	vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
+	if (vlan_ops->dis_rx_filtering(uplink_vsi))
+		goto err_dis_rx;
+
 	if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override))
 		goto err_override_uplink;
 
@@ -114,6 +118,8 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 err_override_control:
 	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
 err_override_uplink:
+	vlan_ops->ena_rx_filtering(uplink_vsi);
+err_dis_rx:
 	if (rule_added)
 		ice_clear_dflt_vsi(uplink_vsi);
 err_def_rx:
@@ -381,9 +387,13 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 {
 	struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi;
 	struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi;
+	struct ice_vsi_vlan_ops *vlan_ops;
+
+	vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
 
 	ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override);
 	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
+	vlan_ops->ena_rx_filtering(uplink_vsi);
 	ice_clear_dflt_vsi(uplink_vsi);
 	ice_fltr_add_mac_and_broadcast(uplink_vsi,
 				       uplink_vsi->port_info->mac.perm_addr,
-- 
GitLab


From 6c0f4441d83b1efd311acbab266246aee6e46bea Mon Sep 17 00:00:00 2001
From: Wojciech Drewek <wojciech.drewek@intel.com>
Date: Wed, 12 Jul 2023 13:03:30 +0200
Subject: [PATCH 0338/1806] ice: Unset src prune on uplink VSI

In switchdev mode uplink VSI is supposed to receive all packets that
were not matched by existing filters. If ICE_AQ_VSI_SW_FLAG_LOCAL_LB
bit is unset and we have a filter associated with uplink VSI
which matches on dst mac equal to MAC1, then packets with src mac equal
to MAC1 will be pruned from reaching uplink VSI.

Fix this by updating uplink VSI with ICE_AQ_VSI_SW_FLAG_LOCAL_LB bit
set when configuring switchdev mode.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_eswitch.c |  6 +++++
 drivers/net/ethernet/intel/ice/ice_lib.c     | 25 ++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_lib.h     |  1 +
 3 files changed, 32 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index bfd003135fc8e..4fe235da1182f 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -113,8 +113,13 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	if (ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_set_allow_override))
 		goto err_override_control;
 
+	if (ice_vsi_update_local_lb(uplink_vsi, true))
+		goto err_override_local_lb;
+
 	return 0;
 
+err_override_local_lb:
+	ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override);
 err_override_control:
 	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
 err_override_uplink:
@@ -391,6 +396,7 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 
 	vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
 
+	ice_vsi_update_local_lb(uplink_vsi, false);
 	ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override);
 	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
 	vlan_ops->ena_rx_filtering(uplink_vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 0054d7e64ec31..a43c23c80565b 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -4076,3 +4076,28 @@ void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx)
 {
 	ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
 }
+
+/**
+ * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit
+ * @vsi: pointer to VSI structure
+ * @set: set or unset the bit
+ */
+int
+ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set)
+{
+	struct ice_vsi_ctx ctx = {
+		.info	= vsi->info,
+	};
+
+	ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID);
+	if (set)
+		ctx.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_LOCAL_LB;
+	else
+		ctx.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_LOCAL_LB;
+
+	if (ice_update_vsi(&vsi->back->hw, vsi->idx, &ctx, NULL))
+		return -ENODEV;
+
+	vsi->info = ctx.info;
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index e985766e6bb5f..1628385a96726 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -157,6 +157,7 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx);
 void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx);
 
 void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx);
+int ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set);
 int ice_vsi_add_vlan_zero(struct ice_vsi *vsi);
 int ice_vsi_del_vlan_zero(struct ice_vsi *vsi);
 bool ice_vsi_has_non_zero_vlans(struct ice_vsi *vsi);
-- 
GitLab


From f6e8fb55e5af9a506d2e50d1079a231ce95ca215 Mon Sep 17 00:00:00 2001
From: Wojciech Drewek <wojciech.drewek@intel.com>
Date: Wed, 12 Jul 2023 13:03:31 +0200
Subject: [PATCH 0339/1806] ice: Implement basic eswitch bridge setup

With this patch, ice driver is able to track if the port
representors or uplink port were added to the linux bridge in
switchdev mode. Listen for NETDEV_CHANGEUPPER events in order to
detect this. ice_esw_br data structure reflects the linux bridge
and stores all the ports of the bridge (ice_esw_br_port) in
xarray, it's created when the first port is added to the bridge and
freed once the last port is removed. Note that only one bridge is
supported per eswitch.

Bridge port (ice_esw_br_port) can be either a VF port representor
port or uplink port (ice_esw_br_port_type). In both cases bridge port
holds a reference to the VSI, VF's VSI in case of the PR and uplink
VSI in case of the uplink. VSI's index is used as an index to the
xarray in which ports are stored.

Add a check which prevents configuring switchdev mode if uplink is
already added to any bridge. This is needed because we need to listen
for NETDEV_CHANGEUPPER events to record if the uplink was added to
the bridge. Netdevice notifier is registered after eswitch mode
is changed to switchdev.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/Makefile       |   2 +-
 drivers/net/ethernet/intel/ice/ice.h          |   4 +-
 drivers/net/ethernet/intel/ice/ice_eswitch.c  |  26 +-
 .../net/ethernet/intel/ice/ice_eswitch_br.c   | 384 ++++++++++++++++++
 .../net/ethernet/intel/ice/ice_eswitch_br.h   |  42 ++
 drivers/net/ethernet/intel/ice/ice_main.c     |   2 +-
 drivers/net/ethernet/intel/ice/ice_repr.c     |   2 +-
 drivers/net/ethernet/intel/ice/ice_repr.h     |   3 +-
 8 files changed, 456 insertions(+), 9 deletions(-)
 create mode 100644 drivers/net/ethernet/intel/ice/ice_eswitch_br.c
 create mode 100644 drivers/net/ethernet/intel/ice/ice_eswitch_br.h

diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 817977e3039d5..960277d78e091 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -47,5 +47,5 @@ ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o
 ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o
 ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o
 ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o
-ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o
+ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o ice_eswitch_br.o
 ice-$(CONFIG_GNSS) += ice_gnss.o
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 4ba3d99439a0a..8918a4b836a24 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -517,6 +517,7 @@ enum ice_misc_thread_tasks {
 struct ice_switchdev_info {
 	struct ice_vsi *control_vsi;
 	struct ice_vsi *uplink_vsi;
+	struct ice_esw_br_offloads *br_offloads;
 	bool is_running;
 };
 
@@ -626,6 +627,7 @@ struct ice_pf {
 	struct ice_lag *lag; /* Link Aggregation information */
 
 	struct ice_switchdev_info switchdev;
+	struct ice_esw_br_port *br_port;
 
 #define ICE_INVALID_AGG_NODE_ID		0
 #define ICE_PF_AGG_NODE_ID_START	1
@@ -853,7 +855,7 @@ static inline bool ice_is_adq_active(struct ice_pf *pf)
 	return false;
 }
 
-bool netif_is_ice(struct net_device *dev);
+bool netif_is_ice(const struct net_device *dev);
 int ice_vsi_setup_tx_rings(struct ice_vsi *vsi);
 int ice_vsi_setup_rx_rings(struct ice_vsi *vsi);
 int ice_vsi_open_ctrl(struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index 4fe235da1182f..9a53a5e5d73eb 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -4,6 +4,7 @@
 #include "ice.h"
 #include "ice_lib.h"
 #include "ice_eswitch.h"
+#include "ice_eswitch_br.h"
 #include "ice_fltr.h"
 #include "ice_repr.h"
 #include "ice_devlink.h"
@@ -317,6 +318,9 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi)
 	repr->src_vsi = vsi;
 	repr->dst->u.port_info.port_id = vsi->vsi_num;
 
+	if (repr->br_port)
+		repr->br_port->vsi = vsi;
+
 	ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof);
 	if (ret) {
 		ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI);
@@ -474,16 +478,24 @@ static void ice_eswitch_napi_disable(struct ice_pf *pf)
  */
 static int ice_eswitch_enable_switchdev(struct ice_pf *pf)
 {
-	struct ice_vsi *ctrl_vsi;
+	struct ice_vsi *ctrl_vsi, *uplink_vsi;
+
+	uplink_vsi = ice_get_main_vsi(pf);
+	if (!uplink_vsi)
+		return -ENODEV;
+
+	if (netif_is_any_bridge_port(uplink_vsi->netdev)) {
+		dev_err(ice_pf_to_dev(pf),
+			"Uplink port cannot be a bridge port\n");
+		return -EINVAL;
+	}
 
 	pf->switchdev.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info);
 	if (!pf->switchdev.control_vsi)
 		return -ENODEV;
 
 	ctrl_vsi = pf->switchdev.control_vsi;
-	pf->switchdev.uplink_vsi = ice_get_main_vsi(pf);
-	if (!pf->switchdev.uplink_vsi)
-		goto err_vsi;
+	pf->switchdev.uplink_vsi = uplink_vsi;
 
 	if (ice_eswitch_setup_env(pf))
 		goto err_vsi;
@@ -499,10 +511,15 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf)
 	if (ice_vsi_open(ctrl_vsi))
 		goto err_setup_reprs;
 
+	if (ice_eswitch_br_offloads_init(pf))
+		goto err_br_offloads;
+
 	ice_eswitch_napi_enable(pf);
 
 	return 0;
 
+err_br_offloads:
+	ice_vsi_close(ctrl_vsi);
 err_setup_reprs:
 	ice_repr_rem_from_all_vfs(pf);
 err_repr_add:
@@ -521,6 +538,7 @@ static void ice_eswitch_disable_switchdev(struct ice_pf *pf)
 	struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi;
 
 	ice_eswitch_napi_disable(pf);
+	ice_eswitch_br_offloads_deinit(pf);
 	ice_eswitch_release_env(pf);
 	ice_eswitch_release_reprs(pf, ctrl_vsi);
 	ice_vsi_release(ctrl_vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
new file mode 100644
index 0000000000000..dbc077447ea1c
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
@@ -0,0 +1,384 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023, Intel Corporation. */
+
+#include "ice.h"
+#include "ice_eswitch_br.h"
+#include "ice_repr.h"
+
+static bool ice_eswitch_br_is_dev_valid(const struct net_device *dev)
+{
+	/* Accept only PF netdev and PRs */
+	return ice_is_port_repr_netdev(dev) || netif_is_ice(dev);
+}
+
+static struct ice_esw_br_port *
+ice_eswitch_br_netdev_to_port(struct net_device *dev)
+{
+	if (ice_is_port_repr_netdev(dev)) {
+		struct ice_repr *repr = ice_netdev_to_repr(dev);
+
+		return repr->br_port;
+	} else if (netif_is_ice(dev)) {
+		struct ice_pf *pf = ice_netdev_to_pf(dev);
+
+		return pf->br_port;
+	}
+
+	return NULL;
+}
+
+static void
+ice_eswitch_br_port_deinit(struct ice_esw_br *bridge,
+			   struct ice_esw_br_port *br_port)
+{
+	struct ice_vsi *vsi = br_port->vsi;
+
+	if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back)
+		vsi->back->br_port = NULL;
+	else if (vsi->vf && vsi->vf->repr)
+		vsi->vf->repr->br_port = NULL;
+
+	xa_erase(&bridge->ports, br_port->vsi_idx);
+	kfree(br_port);
+}
+
+static struct ice_esw_br_port *
+ice_eswitch_br_port_init(struct ice_esw_br *bridge)
+{
+	struct ice_esw_br_port *br_port;
+
+	br_port = kzalloc(sizeof(*br_port), GFP_KERNEL);
+	if (!br_port)
+		return ERR_PTR(-ENOMEM);
+
+	br_port->bridge = bridge;
+
+	return br_port;
+}
+
+static int
+ice_eswitch_br_vf_repr_port_init(struct ice_esw_br *bridge,
+				 struct ice_repr *repr)
+{
+	struct ice_esw_br_port *br_port;
+	int err;
+
+	br_port = ice_eswitch_br_port_init(bridge);
+	if (IS_ERR(br_port))
+		return PTR_ERR(br_port);
+
+	br_port->vsi = repr->src_vsi;
+	br_port->vsi_idx = br_port->vsi->idx;
+	br_port->type = ICE_ESWITCH_BR_VF_REPR_PORT;
+	repr->br_port = br_port;
+
+	err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL);
+	if (err) {
+		ice_eswitch_br_port_deinit(bridge, br_port);
+		return err;
+	}
+
+	return 0;
+}
+
+static int
+ice_eswitch_br_uplink_port_init(struct ice_esw_br *bridge, struct ice_pf *pf)
+{
+	struct ice_vsi *vsi = pf->switchdev.uplink_vsi;
+	struct ice_esw_br_port *br_port;
+	int err;
+
+	br_port = ice_eswitch_br_port_init(bridge);
+	if (IS_ERR(br_port))
+		return PTR_ERR(br_port);
+
+	br_port->vsi = vsi;
+	br_port->vsi_idx = br_port->vsi->idx;
+	br_port->type = ICE_ESWITCH_BR_UPLINK_PORT;
+	pf->br_port = br_port;
+
+	err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL);
+	if (err) {
+		ice_eswitch_br_port_deinit(bridge, br_port);
+		return err;
+	}
+
+	return 0;
+}
+
+static void
+ice_eswitch_br_ports_flush(struct ice_esw_br *bridge)
+{
+	struct ice_esw_br_port *port;
+	unsigned long i;
+
+	xa_for_each(&bridge->ports, i, port)
+		ice_eswitch_br_port_deinit(bridge, port);
+}
+
+static void
+ice_eswitch_br_deinit(struct ice_esw_br_offloads *br_offloads,
+		      struct ice_esw_br *bridge)
+{
+	if (!bridge)
+		return;
+
+	/* Cleanup all the ports that were added asynchronously
+	 * through NETDEV_CHANGEUPPER event.
+	 */
+	ice_eswitch_br_ports_flush(bridge);
+	WARN_ON(!xa_empty(&bridge->ports));
+	xa_destroy(&bridge->ports);
+	br_offloads->bridge = NULL;
+	kfree(bridge);
+}
+
+static struct ice_esw_br *
+ice_eswitch_br_init(struct ice_esw_br_offloads *br_offloads, int ifindex)
+{
+	struct ice_esw_br *bridge;
+
+	bridge = kzalloc(sizeof(*bridge), GFP_KERNEL);
+	if (!bridge)
+		return ERR_PTR(-ENOMEM);
+
+	bridge->br_offloads = br_offloads;
+	bridge->ifindex = ifindex;
+	xa_init(&bridge->ports);
+	br_offloads->bridge = bridge;
+
+	return bridge;
+}
+
+static struct ice_esw_br *
+ice_eswitch_br_get(struct ice_esw_br_offloads *br_offloads, int ifindex,
+		   struct netlink_ext_ack *extack)
+{
+	struct ice_esw_br *bridge = br_offloads->bridge;
+
+	if (bridge) {
+		if (bridge->ifindex != ifindex) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only one bridge is supported per eswitch");
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+		return bridge;
+	}
+
+	/* Create the bridge if it doesn't exist yet */
+	bridge = ice_eswitch_br_init(br_offloads, ifindex);
+	if (IS_ERR(bridge))
+		NL_SET_ERR_MSG_MOD(extack, "Failed to init the bridge");
+
+	return bridge;
+}
+
+static void
+ice_eswitch_br_verify_deinit(struct ice_esw_br_offloads *br_offloads,
+			     struct ice_esw_br *bridge)
+{
+	/* Remove the bridge if it exists and there are no ports left */
+	if (!bridge || !xa_empty(&bridge->ports))
+		return;
+
+	ice_eswitch_br_deinit(br_offloads, bridge);
+}
+
+static int
+ice_eswitch_br_port_unlink(struct ice_esw_br_offloads *br_offloads,
+			   struct net_device *dev, int ifindex,
+			   struct netlink_ext_ack *extack)
+{
+	struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(dev);
+	struct ice_esw_br *bridge;
+
+	if (!br_port) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Port representor is not attached to any bridge");
+		return -EINVAL;
+	}
+
+	if (br_port->bridge->ifindex != ifindex) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Port representor is attached to another bridge");
+		return -EINVAL;
+	}
+
+	bridge = br_port->bridge;
+
+	ice_eswitch_br_port_deinit(br_port->bridge, br_port);
+	ice_eswitch_br_verify_deinit(br_offloads, bridge);
+
+	return 0;
+}
+
+static int
+ice_eswitch_br_port_link(struct ice_esw_br_offloads *br_offloads,
+			 struct net_device *dev, int ifindex,
+			 struct netlink_ext_ack *extack)
+{
+	struct ice_esw_br *bridge;
+	int err;
+
+	if (ice_eswitch_br_netdev_to_port(dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Port is already attached to the bridge");
+		return -EINVAL;
+	}
+
+	bridge = ice_eswitch_br_get(br_offloads, ifindex, extack);
+	if (IS_ERR(bridge))
+		return PTR_ERR(bridge);
+
+	if (ice_is_port_repr_netdev(dev)) {
+		struct ice_repr *repr = ice_netdev_to_repr(dev);
+
+		err = ice_eswitch_br_vf_repr_port_init(bridge, repr);
+	} else {
+		struct ice_pf *pf = ice_netdev_to_pf(dev);
+
+		err = ice_eswitch_br_uplink_port_init(bridge, pf);
+	}
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to init bridge port");
+		goto err_port_init;
+	}
+
+	return 0;
+
+err_port_init:
+	ice_eswitch_br_verify_deinit(br_offloads, bridge);
+	return err;
+}
+
+static int
+ice_eswitch_br_port_changeupper(struct notifier_block *nb, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct ice_esw_br_offloads *br_offloads;
+	struct netlink_ext_ack *extack;
+	struct net_device *upper;
+
+	br_offloads = ice_nb_to_br_offloads(nb, netdev_nb);
+
+	if (!ice_eswitch_br_is_dev_valid(dev))
+		return 0;
+
+	upper = info->upper_dev;
+	if (!netif_is_bridge_master(upper))
+		return 0;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	if (info->linking)
+		return ice_eswitch_br_port_link(br_offloads, dev,
+						upper->ifindex, extack);
+	else
+		return ice_eswitch_br_port_unlink(br_offloads, dev,
+						  upper->ifindex, extack);
+}
+
+static int
+ice_eswitch_br_port_event(struct notifier_block *nb,
+			  unsigned long event, void *ptr)
+{
+	int err = 0;
+
+	switch (event) {
+	case NETDEV_CHANGEUPPER:
+		err = ice_eswitch_br_port_changeupper(nb, ptr);
+		break;
+	}
+
+	return notifier_from_errno(err);
+}
+
+static void
+ice_eswitch_br_offloads_dealloc(struct ice_pf *pf)
+{
+	struct ice_esw_br_offloads *br_offloads = pf->switchdev.br_offloads;
+
+	ASSERT_RTNL();
+
+	if (!br_offloads)
+		return;
+
+	ice_eswitch_br_deinit(br_offloads, br_offloads->bridge);
+
+	pf->switchdev.br_offloads = NULL;
+	kfree(br_offloads);
+}
+
+static struct ice_esw_br_offloads *
+ice_eswitch_br_offloads_alloc(struct ice_pf *pf)
+{
+	struct ice_esw_br_offloads *br_offloads;
+
+	ASSERT_RTNL();
+
+	if (pf->switchdev.br_offloads)
+		return ERR_PTR(-EEXIST);
+
+	br_offloads = kzalloc(sizeof(*br_offloads), GFP_KERNEL);
+	if (!br_offloads)
+		return ERR_PTR(-ENOMEM);
+
+	pf->switchdev.br_offloads = br_offloads;
+	br_offloads->pf = pf;
+
+	return br_offloads;
+}
+
+void
+ice_eswitch_br_offloads_deinit(struct ice_pf *pf)
+{
+	struct ice_esw_br_offloads *br_offloads;
+
+	br_offloads = pf->switchdev.br_offloads;
+	if (!br_offloads)
+		return;
+
+	unregister_netdevice_notifier(&br_offloads->netdev_nb);
+	/* Although notifier block is unregistered just before,
+	 * so we don't get any new events, some events might be
+	 * already in progress. Hold the rtnl lock and wait for
+	 * them to finished.
+	 */
+	rtnl_lock();
+	ice_eswitch_br_offloads_dealloc(pf);
+	rtnl_unlock();
+}
+
+int
+ice_eswitch_br_offloads_init(struct ice_pf *pf)
+{
+	struct ice_esw_br_offloads *br_offloads;
+	struct device *dev = ice_pf_to_dev(pf);
+	int err;
+
+	rtnl_lock();
+	br_offloads = ice_eswitch_br_offloads_alloc(pf);
+	rtnl_unlock();
+	if (IS_ERR(br_offloads)) {
+		dev_err(dev, "Failed to init eswitch bridge\n");
+		return PTR_ERR(br_offloads);
+	}
+
+	br_offloads->netdev_nb.notifier_call = ice_eswitch_br_port_event;
+	err = register_netdevice_notifier(&br_offloads->netdev_nb);
+	if (err) {
+		dev_err(dev,
+			"Failed to register bridge port event notifier\n");
+		goto err_reg_netdev_nb;
+	}
+
+	return 0;
+
+err_reg_netdev_nb:
+	rtnl_lock();
+	ice_eswitch_br_offloads_dealloc(pf);
+	rtnl_unlock();
+
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
new file mode 100644
index 0000000000000..3ad28a17298f3
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2023, Intel Corporation. */
+
+#ifndef _ICE_ESWITCH_BR_H_
+#define _ICE_ESWITCH_BR_H_
+
+enum ice_esw_br_port_type {
+	ICE_ESWITCH_BR_UPLINK_PORT = 0,
+	ICE_ESWITCH_BR_VF_REPR_PORT = 1,
+};
+
+struct ice_esw_br_port {
+	struct ice_esw_br *bridge;
+	struct ice_vsi *vsi;
+	enum ice_esw_br_port_type type;
+	u16 vsi_idx;
+};
+
+struct ice_esw_br {
+	struct ice_esw_br_offloads *br_offloads;
+	struct xarray ports;
+
+	int ifindex;
+};
+
+struct ice_esw_br_offloads {
+	struct ice_pf *pf;
+	struct ice_esw_br *bridge;
+	struct notifier_block netdev_nb;
+};
+
+#define ice_nb_to_br_offloads(nb, nb_name) \
+	container_of(nb, \
+		     struct ice_esw_br_offloads, \
+		     nb_name)
+
+void
+ice_eswitch_br_offloads_deinit(struct ice_pf *pf);
+int
+ice_eswitch_br_offloads_init(struct ice_pf *pf);
+
+#endif /* _ICE_ESWITCH_BR_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index d1f2077676e46..9b36cce306b89 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -80,7 +80,7 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch,
 		     void *data,
 		     void (*cleanup)(struct flow_block_cb *block_cb));
 
-bool netif_is_ice(struct net_device *dev)
+bool netif_is_ice(const struct net_device *dev)
 {
 	return dev && (dev->netdev_ops == &ice_netdev_ops);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index e30e12321abd4..c686ac0935ebe 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -254,7 +254,7 @@ static const struct net_device_ops ice_repr_netdev_ops = {
  * ice_is_port_repr_netdev - Check if a given netdevice is a port representor netdev
  * @netdev: pointer to netdev
  */
-bool ice_is_port_repr_netdev(struct net_device *netdev)
+bool ice_is_port_repr_netdev(const struct net_device *netdev)
 {
 	return netdev && (netdev->netdev_ops == &ice_repr_netdev_ops);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h
index 9c2a6f496b3b9..e1ee2d2c1d2de 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.h
+++ b/drivers/net/ethernet/intel/ice/ice_repr.h
@@ -12,6 +12,7 @@ struct ice_repr {
 	struct ice_q_vector *q_vector;
 	struct net_device *netdev;
 	struct metadata_dst *dst;
+	struct ice_esw_br_port *br_port;
 #ifdef CONFIG_ICE_SWITCHDEV
 	/* info about slow path rule */
 	struct ice_rule_query_data sp_rule;
@@ -27,5 +28,5 @@ void ice_repr_stop_tx_queues(struct ice_repr *repr);
 void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi);
 
 struct ice_repr *ice_netdev_to_repr(struct net_device *netdev);
-bool ice_is_port_repr_netdev(struct net_device *netdev);
+bool ice_is_port_repr_netdev(const struct net_device *netdev);
 #endif
-- 
GitLab


From 7c945a1a8e5fb84195f74813b5d24c924b694932 Mon Sep 17 00:00:00 2001
From: Wojciech Drewek <wojciech.drewek@intel.com>
Date: Wed, 12 Jul 2023 13:03:32 +0200
Subject: [PATCH 0340/1806] ice: Switchdev FDB events support

Listen for SWITCHDEV_FDB_{ADD|DEL}_TO_DEVICE events while in switchdev
mode. Accept these events on both uplink and VF PR ports. Add HW
rules in newly created workqueue. FDB entries are stored in rhashtable
for lookup when removing the entry and in the list for cleanup
purpose. Direction of the HW rule depends on the type of the ports
on which the FDB event was received:

ICE_ESWITCH_BR_UPLINK_PORT:
TX rule that forwards the packet to the LAN (egress).

ICE_ESWITCH_BR_VF_REPR_PORT:
RX rule that forwards the packet to the VF associated
with the port representor.

In both cases the rule matches on the dst mac address.
All the FDB entries are stored in the bridge structure.
When the port is removed all the FDB entries associated with
this port are removed as well. This is achieved thanks to the reference
to the port that FDB entry holds.

In the fwd rule we use only one lookup type (MAC address)
but lkups_cnt variable is already introduced because
we will have more lookups in the subsequent patches.

Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_eswitch_br.c   | 433 ++++++++++++++++++
 .../net/ethernet/intel/ice/ice_eswitch_br.h   |  45 ++
 2 files changed, 478 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
index dbc077447ea1c..49b3ca5e956ed 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
@@ -4,6 +4,14 @@
 #include "ice.h"
 #include "ice_eswitch_br.h"
 #include "ice_repr.h"
+#include "ice_switch.h"
+
+static const struct rhashtable_params ice_fdb_ht_params = {
+	.key_offset = offsetof(struct ice_esw_br_fdb_entry, data),
+	.key_len = sizeof(struct ice_esw_br_fdb_data),
+	.head_offset = offsetof(struct ice_esw_br_fdb_entry, ht_node),
+	.automatic_shrinking = true,
+};
 
 static bool ice_eswitch_br_is_dev_valid(const struct net_device *dev)
 {
@@ -27,12 +35,405 @@ ice_eswitch_br_netdev_to_port(struct net_device *dev)
 	return NULL;
 }
 
+static void
+ice_eswitch_br_ingress_rule_setup(struct ice_adv_rule_info *rule_info,
+				  u8 pf_id, u16 vf_vsi_idx)
+{
+	rule_info->sw_act.vsi_handle = vf_vsi_idx;
+	rule_info->sw_act.flag |= ICE_FLTR_RX;
+	rule_info->sw_act.src = pf_id;
+	rule_info->priority = 5;
+}
+
+static void
+ice_eswitch_br_egress_rule_setup(struct ice_adv_rule_info *rule_info,
+				 u16 pf_vsi_idx)
+{
+	rule_info->sw_act.vsi_handle = pf_vsi_idx;
+	rule_info->sw_act.flag |= ICE_FLTR_TX;
+	rule_info->flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE;
+	rule_info->flags_info.act_valid = true;
+	rule_info->priority = 5;
+}
+
+static int
+ice_eswitch_br_rule_delete(struct ice_hw *hw, struct ice_rule_query_data *rule)
+{
+	int err;
+
+	if (!rule)
+		return -EINVAL;
+
+	err = ice_rem_adv_rule_by_id(hw, rule);
+	kfree(rule);
+
+	return err;
+}
+
+static struct ice_rule_query_data *
+ice_eswitch_br_fwd_rule_create(struct ice_hw *hw, int vsi_idx, int port_type,
+			       const unsigned char *mac)
+{
+	struct ice_adv_rule_info rule_info = { 0 };
+	struct ice_rule_query_data *rule;
+	struct ice_adv_lkup_elem *list;
+	u16 lkups_cnt = 1;
+	int err;
+
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
+		return ERR_PTR(-ENOMEM);
+
+	list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC);
+	if (!list) {
+		err = -ENOMEM;
+		goto err_list_alloc;
+	}
+
+	switch (port_type) {
+	case ICE_ESWITCH_BR_UPLINK_PORT:
+		ice_eswitch_br_egress_rule_setup(&rule_info, vsi_idx);
+		break;
+	case ICE_ESWITCH_BR_VF_REPR_PORT:
+		ice_eswitch_br_ingress_rule_setup(&rule_info, hw->pf_id,
+						  vsi_idx);
+		break;
+	default:
+		err = -EINVAL;
+		goto err_add_rule;
+	}
+
+	list[0].type = ICE_MAC_OFOS;
+	ether_addr_copy(list[0].h_u.eth_hdr.dst_addr, mac);
+	eth_broadcast_addr(list[0].m_u.eth_hdr.dst_addr);
+
+	rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI;
+
+	err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule);
+	if (err)
+		goto err_add_rule;
+
+	kfree(list);
+
+	return rule;
+
+err_add_rule:
+	kfree(list);
+err_list_alloc:
+	kfree(rule);
+
+	return ERR_PTR(err);
+}
+
+static struct ice_esw_br_flow *
+ice_eswitch_br_flow_create(struct device *dev, struct ice_hw *hw, int vsi_idx,
+			   int port_type, const unsigned char *mac)
+{
+	struct ice_rule_query_data *fwd_rule;
+	struct ice_esw_br_flow *flow;
+	int err;
+
+	flow = kzalloc(sizeof(*flow), GFP_KERNEL);
+	if (!flow)
+		return ERR_PTR(-ENOMEM);
+
+	fwd_rule = ice_eswitch_br_fwd_rule_create(hw, vsi_idx, port_type, mac);
+	err = PTR_ERR_OR_ZERO(fwd_rule);
+	if (err) {
+		dev_err(dev, "Failed to create eswitch bridge %sgress forward rule, err: %d\n",
+			port_type == ICE_ESWITCH_BR_UPLINK_PORT ? "e" : "in",
+			err);
+		goto err_fwd_rule;
+	}
+
+	flow->fwd_rule = fwd_rule;
+
+	return flow;
+
+err_fwd_rule:
+	kfree(flow);
+
+	return ERR_PTR(err);
+}
+
+static struct ice_esw_br_fdb_entry *
+ice_eswitch_br_fdb_find(struct ice_esw_br *bridge, const unsigned char *mac,
+			u16 vid)
+{
+	struct ice_esw_br_fdb_data data = {
+		.vid = vid,
+	};
+
+	ether_addr_copy(data.addr, mac);
+	return rhashtable_lookup_fast(&bridge->fdb_ht, &data,
+				      ice_fdb_ht_params);
+}
+
+static void
+ice_eswitch_br_flow_delete(struct ice_pf *pf, struct ice_esw_br_flow *flow)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	int err;
+
+	err = ice_eswitch_br_rule_delete(&pf->hw, flow->fwd_rule);
+	if (err)
+		dev_err(dev, "Failed to delete FDB forward rule, err: %d\n",
+			err);
+
+	kfree(flow);
+}
+
+static void
+ice_eswitch_br_fdb_entry_delete(struct ice_esw_br *bridge,
+				struct ice_esw_br_fdb_entry *fdb_entry)
+{
+	struct ice_pf *pf = bridge->br_offloads->pf;
+
+	rhashtable_remove_fast(&bridge->fdb_ht, &fdb_entry->ht_node,
+			       ice_fdb_ht_params);
+	list_del(&fdb_entry->list);
+
+	ice_eswitch_br_flow_delete(pf, fdb_entry->flow);
+
+	kfree(fdb_entry);
+}
+
+static void
+ice_eswitch_br_fdb_offload_notify(struct net_device *dev,
+				  const unsigned char *mac, u16 vid,
+				  unsigned long val)
+{
+	struct switchdev_notifier_fdb_info fdb_info = {
+		.addr = mac,
+		.vid = vid,
+		.offloaded = true,
+	};
+
+	call_switchdev_notifiers(val, dev, &fdb_info.info, NULL);
+}
+
+static void
+ice_eswitch_br_fdb_entry_notify_and_cleanup(struct ice_esw_br *bridge,
+					    struct ice_esw_br_fdb_entry *entry)
+{
+	if (!(entry->flags & ICE_ESWITCH_BR_FDB_ADDED_BY_USER))
+		ice_eswitch_br_fdb_offload_notify(entry->dev, entry->data.addr,
+						  entry->data.vid,
+						  SWITCHDEV_FDB_DEL_TO_BRIDGE);
+	ice_eswitch_br_fdb_entry_delete(bridge, entry);
+}
+
+static void
+ice_eswitch_br_fdb_entry_find_and_delete(struct ice_esw_br *bridge,
+					 const unsigned char *mac, u16 vid)
+{
+	struct ice_pf *pf = bridge->br_offloads->pf;
+	struct ice_esw_br_fdb_entry *fdb_entry;
+	struct device *dev = ice_pf_to_dev(pf);
+
+	fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid);
+	if (!fdb_entry) {
+		dev_err(dev, "FDB entry with mac: %pM and vid: %u not found\n",
+			mac, vid);
+		return;
+	}
+
+	ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry);
+}
+
+static void
+ice_eswitch_br_fdb_entry_create(struct net_device *netdev,
+				struct ice_esw_br_port *br_port,
+				bool added_by_user,
+				const unsigned char *mac, u16 vid)
+{
+	struct ice_esw_br *bridge = br_port->bridge;
+	struct ice_pf *pf = bridge->br_offloads->pf;
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_esw_br_fdb_entry *fdb_entry;
+	struct ice_esw_br_flow *flow;
+	struct ice_hw *hw = &pf->hw;
+	unsigned long event;
+	int err;
+
+	fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid);
+	if (fdb_entry)
+		ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry);
+
+	fdb_entry = kzalloc(sizeof(*fdb_entry), GFP_KERNEL);
+	if (!fdb_entry) {
+		err = -ENOMEM;
+		goto err_exit;
+	}
+
+	flow = ice_eswitch_br_flow_create(dev, hw, br_port->vsi_idx,
+					  br_port->type, mac);
+	if (IS_ERR(flow)) {
+		err = PTR_ERR(flow);
+		goto err_add_flow;
+	}
+
+	ether_addr_copy(fdb_entry->data.addr, mac);
+	fdb_entry->data.vid = vid;
+	fdb_entry->br_port = br_port;
+	fdb_entry->flow = flow;
+	fdb_entry->dev = netdev;
+	event = SWITCHDEV_FDB_ADD_TO_BRIDGE;
+
+	if (added_by_user) {
+		fdb_entry->flags |= ICE_ESWITCH_BR_FDB_ADDED_BY_USER;
+		event = SWITCHDEV_FDB_OFFLOADED;
+	}
+
+	err = rhashtable_insert_fast(&bridge->fdb_ht, &fdb_entry->ht_node,
+				     ice_fdb_ht_params);
+	if (err)
+		goto err_fdb_insert;
+
+	list_add(&fdb_entry->list, &bridge->fdb_list);
+
+	ice_eswitch_br_fdb_offload_notify(netdev, mac, vid, event);
+
+	return;
+
+err_fdb_insert:
+	ice_eswitch_br_flow_delete(pf, flow);
+err_add_flow:
+	kfree(fdb_entry);
+err_exit:
+	dev_err(dev, "Failed to create fdb entry, err: %d\n", err);
+}
+
+static void
+ice_eswitch_br_fdb_work_dealloc(struct ice_esw_br_fdb_work *fdb_work)
+{
+	kfree(fdb_work->fdb_info.addr);
+	kfree(fdb_work);
+}
+
+static void
+ice_eswitch_br_fdb_event_work(struct work_struct *work)
+{
+	struct ice_esw_br_fdb_work *fdb_work = ice_work_to_fdb_work(work);
+	bool added_by_user = fdb_work->fdb_info.added_by_user;
+	const unsigned char *mac = fdb_work->fdb_info.addr;
+	u16 vid = fdb_work->fdb_info.vid;
+	struct ice_esw_br_port *br_port;
+
+	rtnl_lock();
+
+	br_port = ice_eswitch_br_netdev_to_port(fdb_work->dev);
+	if (!br_port)
+		goto err_exit;
+
+	switch (fdb_work->event) {
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
+		ice_eswitch_br_fdb_entry_create(fdb_work->dev, br_port,
+						added_by_user, mac, vid);
+		break;
+	case SWITCHDEV_FDB_DEL_TO_DEVICE:
+		ice_eswitch_br_fdb_entry_find_and_delete(br_port->bridge,
+							 mac, vid);
+		break;
+	default:
+		goto err_exit;
+	}
+
+err_exit:
+	rtnl_unlock();
+	dev_put(fdb_work->dev);
+	ice_eswitch_br_fdb_work_dealloc(fdb_work);
+}
+
+static struct ice_esw_br_fdb_work *
+ice_eswitch_br_fdb_work_alloc(struct switchdev_notifier_fdb_info *fdb_info,
+			      struct net_device *dev,
+			      unsigned long event)
+{
+	struct ice_esw_br_fdb_work *work;
+	unsigned char *mac;
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_WORK(&work->work, ice_eswitch_br_fdb_event_work);
+	memcpy(&work->fdb_info, fdb_info, sizeof(work->fdb_info));
+
+	mac = kzalloc(ETH_ALEN, GFP_ATOMIC);
+	if (!mac) {
+		kfree(work);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	ether_addr_copy(mac, fdb_info->addr);
+	work->fdb_info.addr = mac;
+	work->event = event;
+	work->dev = dev;
+
+	return work;
+}
+
+static int
+ice_eswitch_br_switchdev_event(struct notifier_block *nb,
+			       unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	struct switchdev_notifier_fdb_info *fdb_info;
+	struct switchdev_notifier_info *info = ptr;
+	struct ice_esw_br_offloads *br_offloads;
+	struct ice_esw_br_fdb_work *work;
+	struct netlink_ext_ack *extack;
+	struct net_device *upper;
+
+	br_offloads = ice_nb_to_br_offloads(nb, switchdev_nb);
+	extack = switchdev_notifier_info_to_extack(ptr);
+
+	upper = netdev_master_upper_dev_get_rcu(dev);
+	if (!upper)
+		return NOTIFY_DONE;
+
+	if (!netif_is_bridge_master(upper))
+		return NOTIFY_DONE;
+
+	if (!ice_eswitch_br_is_dev_valid(dev))
+		return NOTIFY_DONE;
+
+	if (!ice_eswitch_br_netdev_to_port(dev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
+	case SWITCHDEV_FDB_DEL_TO_DEVICE:
+		fdb_info = container_of(info, typeof(*fdb_info), info);
+
+		work = ice_eswitch_br_fdb_work_alloc(fdb_info, dev, event);
+		if (IS_ERR(work)) {
+			NL_SET_ERR_MSG_MOD(extack, "Failed to init switchdev fdb work");
+			return notifier_from_errno(PTR_ERR(work));
+		}
+		dev_hold(dev);
+
+		queue_work(br_offloads->wq, &work->work);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
 static void
 ice_eswitch_br_port_deinit(struct ice_esw_br *bridge,
 			   struct ice_esw_br_port *br_port)
 {
+	struct ice_esw_br_fdb_entry *fdb_entry, *tmp;
 	struct ice_vsi *vsi = br_port->vsi;
 
+	list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) {
+		if (br_port == fdb_entry->br_port)
+			ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry);
+	}
+
 	if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back)
 		vsi->back->br_port = NULL;
 	else if (vsi->vf && vsi->vf->repr)
@@ -129,6 +530,8 @@ ice_eswitch_br_deinit(struct ice_esw_br_offloads *br_offloads,
 	ice_eswitch_br_ports_flush(bridge);
 	WARN_ON(!xa_empty(&bridge->ports));
 	xa_destroy(&bridge->ports);
+	rhashtable_destroy(&bridge->fdb_ht);
+
 	br_offloads->bridge = NULL;
 	kfree(bridge);
 }
@@ -137,11 +540,19 @@ static struct ice_esw_br *
 ice_eswitch_br_init(struct ice_esw_br_offloads *br_offloads, int ifindex)
 {
 	struct ice_esw_br *bridge;
+	int err;
 
 	bridge = kzalloc(sizeof(*bridge), GFP_KERNEL);
 	if (!bridge)
 		return ERR_PTR(-ENOMEM);
 
+	err = rhashtable_init(&bridge->fdb_ht, &ice_fdb_ht_params);
+	if (err) {
+		kfree(bridge);
+		return ERR_PTR(err);
+	}
+
+	INIT_LIST_HEAD(&bridge->fdb_list);
 	bridge->br_offloads = br_offloads;
 	bridge->ifindex = ifindex;
 	xa_init(&bridge->ports);
@@ -340,6 +751,8 @@ ice_eswitch_br_offloads_deinit(struct ice_pf *pf)
 		return;
 
 	unregister_netdevice_notifier(&br_offloads->netdev_nb);
+	unregister_switchdev_notifier(&br_offloads->switchdev_nb);
+	destroy_workqueue(br_offloads->wq);
 	/* Although notifier block is unregistered just before,
 	 * so we don't get any new events, some events might be
 	 * already in progress. Hold the rtnl lock and wait for
@@ -365,6 +778,22 @@ ice_eswitch_br_offloads_init(struct ice_pf *pf)
 		return PTR_ERR(br_offloads);
 	}
 
+	br_offloads->wq = alloc_ordered_workqueue("ice_bridge_wq", 0);
+	if (!br_offloads->wq) {
+		err = -ENOMEM;
+		dev_err(dev, "Failed to allocate bridge workqueue\n");
+		goto err_alloc_wq;
+	}
+
+	br_offloads->switchdev_nb.notifier_call =
+		ice_eswitch_br_switchdev_event;
+	err = register_switchdev_notifier(&br_offloads->switchdev_nb);
+	if (err) {
+		dev_err(dev,
+			"Failed to register switchdev notifier\n");
+		goto err_reg_switchdev_nb;
+	}
+
 	br_offloads->netdev_nb.notifier_call = ice_eswitch_br_port_event;
 	err = register_netdevice_notifier(&br_offloads->netdev_nb);
 	if (err) {
@@ -376,6 +805,10 @@ ice_eswitch_br_offloads_init(struct ice_pf *pf)
 	return 0;
 
 err_reg_netdev_nb:
+	unregister_switchdev_notifier(&br_offloads->switchdev_nb);
+err_reg_switchdev_nb:
+	destroy_workqueue(br_offloads->wq);
+err_alloc_wq:
 	rtnl_lock();
 	ice_eswitch_br_offloads_dealloc(pf);
 	rtnl_unlock();
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
index 3ad28a17298f3..e1b4eda7a8900 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
@@ -4,6 +4,33 @@
 #ifndef _ICE_ESWITCH_BR_H_
 #define _ICE_ESWITCH_BR_H_
 
+#include <linux/rhashtable.h>
+
+struct ice_esw_br_fdb_data {
+	unsigned char addr[ETH_ALEN];
+	u16 vid;
+};
+
+struct ice_esw_br_flow {
+	struct ice_rule_query_data *fwd_rule;
+};
+
+enum {
+	ICE_ESWITCH_BR_FDB_ADDED_BY_USER = BIT(0),
+};
+
+struct ice_esw_br_fdb_entry {
+	struct ice_esw_br_fdb_data data;
+	struct rhash_head ht_node;
+	struct list_head list;
+
+	int flags;
+
+	struct net_device *dev;
+	struct ice_esw_br_port *br_port;
+	struct ice_esw_br_flow *flow;
+};
+
 enum ice_esw_br_port_type {
 	ICE_ESWITCH_BR_UPLINK_PORT = 0,
 	ICE_ESWITCH_BR_VF_REPR_PORT = 1,
@@ -20,6 +47,9 @@ struct ice_esw_br {
 	struct ice_esw_br_offloads *br_offloads;
 	struct xarray ports;
 
+	struct rhashtable fdb_ht;
+	struct list_head fdb_list;
+
 	int ifindex;
 };
 
@@ -27,6 +57,16 @@ struct ice_esw_br_offloads {
 	struct ice_pf *pf;
 	struct ice_esw_br *bridge;
 	struct notifier_block netdev_nb;
+	struct notifier_block switchdev_nb;
+
+	struct workqueue_struct *wq;
+};
+
+struct ice_esw_br_fdb_work {
+	struct work_struct work;
+	struct switchdev_notifier_fdb_info fdb_info;
+	struct net_device *dev;
+	unsigned long event;
 };
 
 #define ice_nb_to_br_offloads(nb, nb_name) \
@@ -34,6 +74,11 @@ struct ice_esw_br_offloads {
 		     struct ice_esw_br_offloads, \
 		     nb_name)
 
+#define ice_work_to_fdb_work(w) \
+	container_of(w, \
+		     struct ice_esw_br_fdb_work, \
+		     work)
+
 void
 ice_eswitch_br_offloads_deinit(struct ice_pf *pf);
 int
-- 
GitLab


From bccd9bce29e0d0ac3d0705cc2e58fffe16179d12 Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@intel.com>
Date: Wed, 12 Jul 2023 13:03:33 +0200
Subject: [PATCH 0341/1806] ice: Add guard rule when creating FDB in switchdev

Introduce new "guard" rule upon FDB entry creation.

It matches on src_mac, has valid bit unset, allow_pass_l2 set
and has a nop action.

Previously introduced "forward" rule matches on dst_mac, has valid
bit set, need_pass_l2 set and has a forward action.

With these rules, a packet will be offloaded only if FDB exists in both
directions (RX and TX).

Let's assume link partner sends a packet to VF1: src_mac = LP_MAC,
dst_mac = is VF1_MAC. Bridge adds FDB, two rules are created:
1. Guard rule matching on src_mac == LP_MAC
2. Forward rule matching on dst_mac == LP_MAC
Now VF1 responds with src_mac = VF1_MAC, dst_mac = LP_MAC. Before this
change, only one rule with dst_mac == LP_MAC would have existed, and the
packet would have been offloaded, meaning the bridge wouldn't add FDB in
the opposite direction. Now, the forward rule matches (dst_mac == LP_MAC),
but it has need_pass_l2 set an there is no guard rule with
src_mac == VF1_MAC, so the packet goes through slow-path and the bridge
adds FDB. Two rules are created:
1. Guard rule matching on src_mac == VF1_MAC
2. Forward rule matching on dst_mac == VF1_MAC
Further packets in both directions will be offloaded.

The same example is true in opposite direction (i.e. VF1 is the first to
send a packet out).

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Marcin Szycik <marcin.szycik@intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_eswitch_br.c   | 64 +++++++++++-
 .../net/ethernet/intel/ice/ice_eswitch_br.h   |  1 +
 drivers/net/ethernet/intel/ice/ice_switch.c   | 97 ++++++++++++-------
 drivers/net/ethernet/intel/ice/ice_switch.h   |  5 +
 drivers/net/ethernet/intel/ice/ice_type.h     |  1 +
 5 files changed, 132 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
index 49b3ca5e956ed..297d0eb45dded 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
@@ -107,6 +107,8 @@ ice_eswitch_br_fwd_rule_create(struct ice_hw *hw, int vsi_idx, int port_type,
 	ether_addr_copy(list[0].h_u.eth_hdr.dst_addr, mac);
 	eth_broadcast_addr(list[0].m_u.eth_hdr.dst_addr);
 
+	rule_info.need_pass_l2 = true;
+
 	rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI;
 
 	err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule);
@@ -125,11 +127,54 @@ err_list_alloc:
 	return ERR_PTR(err);
 }
 
+static struct ice_rule_query_data *
+ice_eswitch_br_guard_rule_create(struct ice_hw *hw, u16 vsi_idx,
+				 const unsigned char *mac)
+{
+	struct ice_adv_rule_info rule_info = { 0 };
+	struct ice_rule_query_data *rule;
+	struct ice_adv_lkup_elem *list;
+	const u16 lkups_cnt = 1;
+	int err = -ENOMEM;
+
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
+		goto err_exit;
+
+	list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC);
+	if (!list)
+		goto err_list_alloc;
+
+	list[0].type = ICE_MAC_OFOS;
+	ether_addr_copy(list[0].h_u.eth_hdr.src_addr, mac);
+	eth_broadcast_addr(list[0].m_u.eth_hdr.src_addr);
+
+	rule_info.allow_pass_l2 = true;
+	rule_info.sw_act.vsi_handle = vsi_idx;
+	rule_info.sw_act.fltr_act = ICE_NOP;
+	rule_info.priority = 5;
+
+	err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule);
+	if (err)
+		goto err_add_rule;
+
+	kfree(list);
+
+	return rule;
+
+err_add_rule:
+	kfree(list);
+err_list_alloc:
+	kfree(rule);
+err_exit:
+	return ERR_PTR(err);
+}
+
 static struct ice_esw_br_flow *
 ice_eswitch_br_flow_create(struct device *dev, struct ice_hw *hw, int vsi_idx,
 			   int port_type, const unsigned char *mac)
 {
-	struct ice_rule_query_data *fwd_rule;
+	struct ice_rule_query_data *fwd_rule, *guard_rule;
 	struct ice_esw_br_flow *flow;
 	int err;
 
@@ -146,10 +191,22 @@ ice_eswitch_br_flow_create(struct device *dev, struct ice_hw *hw, int vsi_idx,
 		goto err_fwd_rule;
 	}
 
+	guard_rule = ice_eswitch_br_guard_rule_create(hw, vsi_idx, mac);
+	err = PTR_ERR_OR_ZERO(guard_rule);
+	if (err) {
+		dev_err(dev, "Failed to create eswitch bridge %sgress guard rule, err: %d\n",
+			port_type == ICE_ESWITCH_BR_UPLINK_PORT ? "e" : "in",
+			err);
+		goto err_guard_rule;
+	}
+
 	flow->fwd_rule = fwd_rule;
+	flow->guard_rule = guard_rule;
 
 	return flow;
 
+err_guard_rule:
+	ice_eswitch_br_rule_delete(hw, fwd_rule);
 err_fwd_rule:
 	kfree(flow);
 
@@ -180,6 +237,11 @@ ice_eswitch_br_flow_delete(struct ice_pf *pf, struct ice_esw_br_flow *flow)
 		dev_err(dev, "Failed to delete FDB forward rule, err: %d\n",
 			err);
 
+	err = ice_eswitch_br_rule_delete(&pf->hw, flow->guard_rule);
+	if (err)
+		dev_err(dev, "Failed to delete FDB guard rule, err: %d\n",
+			err);
+
 	kfree(flow);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
index e1b4eda7a8900..d0dcf66ff08b1 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
@@ -13,6 +13,7 @@ struct ice_esw_br_fdb_data {
 
 struct ice_esw_br_flow {
 	struct ice_rule_query_data *fwd_rule;
+	struct ice_rule_query_data *guard_rule;
 };
 
 enum {
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 81f45d7e76dea..813fef5fd7482 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -2272,6 +2272,10 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid,
 		/* Propagate some data to the recipe database */
 		recps[idx].is_root = !!is_root;
 		recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority;
+		recps[idx].need_pass_l2 = root_bufs.content.act_ctrl &
+					  ICE_AQ_RECIPE_ACT_NEED_PASS_L2;
+		recps[idx].allow_pass_l2 = root_bufs.content.act_ctrl &
+					   ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2;
 		bitmap_zero(recps[idx].res_idxs, ICE_MAX_FV_WORDS);
 		if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) {
 			recps[idx].chain_idx = root_bufs.content.result_indx &
@@ -4613,13 +4617,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = {
  * ice_find_recp - find a recipe
  * @hw: pointer to the hardware structure
  * @lkup_exts: extension sequence to match
- * @tun_type: type of recipe tunnel
+ * @rinfo: information regarding the rule e.g. priority and action info
  *
  * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found.
  */
 static u16
 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts,
-	      enum ice_sw_tunnel_type tun_type)
+	      const struct ice_adv_rule_info *rinfo)
 {
 	bool refresh_required = true;
 	struct ice_sw_recipe *recp;
@@ -4680,9 +4684,12 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts,
 			}
 			/* If for "i"th recipe the found was never set to false
 			 * then it means we found our match
-			 * Also tun type of recipe needs to be checked
+			 * Also tun type and *_pass_l2 of recipe needs to be
+			 * checked
 			 */
-			if (found && recp[i].tun_type == tun_type)
+			if (found && recp[i].tun_type == rinfo->tun_type &&
+			    recp[i].need_pass_l2 == rinfo->need_pass_l2 &&
+			    recp[i].allow_pass_l2 == rinfo->allow_pass_l2)
 				return i; /* Return the recipe ID */
 		}
 	}
@@ -4952,6 +4959,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 		  unsigned long *profiles)
 {
 	DECLARE_BITMAP(result_idx_bm, ICE_MAX_FV_WORDS);
+	struct ice_aqc_recipe_content *content;
 	struct ice_aqc_recipe_data_elem *tmp;
 	struct ice_aqc_recipe_data_elem *buf;
 	struct ice_recp_grp_entry *entry;
@@ -5012,6 +5020,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 		if (status)
 			goto err_unroll;
 
+		content = &buf[recps].content;
+
 		/* Clear the result index of the located recipe, as this will be
 		 * updated, if needed, later in the recipe creation process.
 		 */
@@ -5022,26 +5032,24 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 		/* if the recipe is a non-root recipe RID should be programmed
 		 * as 0 for the rules to be applied correctly.
 		 */
-		buf[recps].content.rid = 0;
-		memset(&buf[recps].content.lkup_indx, 0,
-		       sizeof(buf[recps].content.lkup_indx));
+		content->rid = 0;
+		memset(&content->lkup_indx, 0,
+		       sizeof(content->lkup_indx));
 
 		/* All recipes use look-up index 0 to match switch ID. */
-		buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX;
-		buf[recps].content.mask[0] =
-			cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK);
+		content->lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX;
+		content->mask[0] = cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK);
 		/* Setup lkup_indx 1..4 to INVALID/ignore and set the mask
 		 * to be 0
 		 */
 		for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) {
-			buf[recps].content.lkup_indx[i] = 0x80;
-			buf[recps].content.mask[i] = 0;
+			content->lkup_indx[i] = 0x80;
+			content->mask[i] = 0;
 		}
 
 		for (i = 0; i < entry->r_group.n_val_pairs; i++) {
-			buf[recps].content.lkup_indx[i + 1] = entry->fv_idx[i];
-			buf[recps].content.mask[i + 1] =
-				cpu_to_le16(entry->fv_mask[i]);
+			content->lkup_indx[i + 1] = entry->fv_idx[i];
+			content->mask[i + 1] = cpu_to_le16(entry->fv_mask[i]);
 		}
 
 		if (rm->n_grp_count > 1) {
@@ -5055,7 +5063,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 			}
 
 			entry->chain_idx = chain_idx;
-			buf[recps].content.result_indx =
+			content->result_indx =
 				ICE_AQ_RECIPE_RESULT_EN |
 				((chain_idx << ICE_AQ_RECIPE_RESULT_DATA_S) &
 				 ICE_AQ_RECIPE_RESULT_DATA_M);
@@ -5069,7 +5077,13 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 			    ICE_MAX_NUM_RECIPES);
 		set_bit(buf[recps].recipe_indx,
 			(unsigned long *)buf[recps].recipe_bitmap);
-		buf[recps].content.act_ctrl_fwd_priority = rm->priority;
+		content->act_ctrl_fwd_priority = rm->priority;
+
+		if (rm->need_pass_l2)
+			content->act_ctrl |= ICE_AQ_RECIPE_ACT_NEED_PASS_L2;
+
+		if (rm->allow_pass_l2)
+			content->act_ctrl |= ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2;
 		recps++;
 	}
 
@@ -5107,9 +5121,11 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 		if (status)
 			goto err_unroll;
 
+		content = &buf[recps].content;
+
 		buf[recps].recipe_indx = (u8)rid;
-		buf[recps].content.rid = (u8)rid;
-		buf[recps].content.rid |= ICE_AQ_RECIPE_ID_IS_ROOT;
+		content->rid = (u8)rid;
+		content->rid |= ICE_AQ_RECIPE_ID_IS_ROOT;
 		/* the new entry created should also be part of rg_list to
 		 * make sure we have complete recipe
 		 */
@@ -5121,16 +5137,13 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 			goto err_unroll;
 		}
 		last_chain_entry->rid = rid;
-		memset(&buf[recps].content.lkup_indx, 0,
-		       sizeof(buf[recps].content.lkup_indx));
+		memset(&content->lkup_indx, 0, sizeof(content->lkup_indx));
 		/* All recipes use look-up index 0 to match switch ID. */
-		buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX;
-		buf[recps].content.mask[0] =
-			cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK);
+		content->lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX;
+		content->mask[0] = cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK);
 		for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) {
-			buf[recps].content.lkup_indx[i] =
-				ICE_AQ_RECIPE_LKUP_IGNORE;
-			buf[recps].content.mask[i] = 0;
+			content->lkup_indx[i] = ICE_AQ_RECIPE_LKUP_IGNORE;
+			content->mask[i] = 0;
 		}
 
 		i = 1;
@@ -5142,8 +5155,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 		last_chain_entry->chain_idx = ICE_INVAL_CHAIN_IND;
 		list_for_each_entry(entry, &rm->rg_list, l_entry) {
 			last_chain_entry->fv_idx[i] = entry->chain_idx;
-			buf[recps].content.lkup_indx[i] = entry->chain_idx;
-			buf[recps].content.mask[i++] = cpu_to_le16(0xFFFF);
+			content->lkup_indx[i] = entry->chain_idx;
+			content->mask[i++] = cpu_to_le16(0xFFFF);
 			set_bit(entry->rid, rm->r_bitmap);
 		}
 		list_add(&last_chain_entry->l_entry, &rm->rg_list);
@@ -5155,7 +5168,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 			status = -EINVAL;
 			goto err_unroll;
 		}
-		buf[recps].content.act_ctrl_fwd_priority = rm->priority;
+		content->act_ctrl_fwd_priority = rm->priority;
 
 		recps++;
 		rm->root_rid = (u8)rid;
@@ -5220,6 +5233,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 		recp->priority = buf[buf_idx].content.act_ctrl_fwd_priority;
 		recp->n_grp_count = rm->n_grp_count;
 		recp->tun_type = rm->tun_type;
+		recp->need_pass_l2 = rm->need_pass_l2;
+		recp->allow_pass_l2 = rm->allow_pass_l2;
 		recp->recp_created = true;
 	}
 	rm->root_buf = buf;
@@ -5388,6 +5403,9 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 	/* set the recipe priority if specified */
 	rm->priority = (u8)rinfo->priority;
 
+	rm->need_pass_l2 = rinfo->need_pass_l2;
+	rm->allow_pass_l2 = rinfo->allow_pass_l2;
+
 	/* Find offsets from the field vector. Pick the first one for all the
 	 * recipes.
 	 */
@@ -5403,7 +5421,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 	}
 
 	/* Look for a recipe which matches our requested fv / mask list */
-	*rid = ice_find_recp(hw, lkup_exts, rinfo->tun_type);
+	*rid = ice_find_recp(hw, lkup_exts, rinfo);
 	if (*rid < ICE_MAX_NUM_RECIPES)
 		/* Success if found a recipe that match the existing criteria */
 		goto err_unroll;
@@ -5839,7 +5857,9 @@ static bool ice_rules_equal(const struct ice_adv_rule_info *first,
 	return first->sw_act.flag == second->sw_act.flag &&
 	       first->tun_type == second->tun_type &&
 	       first->vlan_type == second->vlan_type &&
-	       first->src_vsi == second->src_vsi;
+	       first->src_vsi == second->src_vsi &&
+	       first->need_pass_l2 == second->need_pass_l2 &&
+	       first->allow_pass_l2 == second->allow_pass_l2;
 }
 
 /**
@@ -6078,7 +6098,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 	if (!(rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI ||
 	      rinfo->sw_act.fltr_act == ICE_FWD_TO_Q ||
 	      rinfo->sw_act.fltr_act == ICE_FWD_TO_QGRP ||
-	      rinfo->sw_act.fltr_act == ICE_DROP_PACKET)) {
+	      rinfo->sw_act.fltr_act == ICE_DROP_PACKET ||
+	      rinfo->sw_act.fltr_act == ICE_NOP)) {
 		status = -EIO;
 		goto free_pkt_profile;
 	}
@@ -6089,7 +6110,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 		goto free_pkt_profile;
 	}
 
-	if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI)
+	if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI ||
+	    rinfo->sw_act.fltr_act == ICE_NOP)
 		rinfo->sw_act.fwd_id.hw_vsi_id =
 			ice_get_hw_vsi_num(hw, vsi_handle);
 
@@ -6159,6 +6181,11 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 		act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP |
 		       ICE_SINGLE_ACT_VALID_BIT;
 		break;
+	case ICE_NOP:
+		act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M,
+				  rinfo->sw_act.fwd_id.hw_vsi_id);
+		act &= ~ICE_SINGLE_ACT_VALID_BIT;
+		break;
 	default:
 		status = -EIO;
 		goto err_ice_add_adv_rule;
@@ -6439,7 +6466,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 			return -EIO;
 	}
 
-	rid = ice_find_recp(hw, &lkup_exts, rinfo->tun_type);
+	rid = ice_find_recp(hw, &lkup_exts, rinfo);
 	/* If did not find a recipe that match the existing criteria */
 	if (rid == ICE_MAX_NUM_RECIPES)
 		return -EINVAL;
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index db08509805cec..10f5a0ae199e8 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -191,6 +191,8 @@ struct ice_adv_rule_info {
 	u16 vlan_type;
 	u16 fltr_rule_id;
 	u32 priority;
+	u16 need_pass_l2:1;
+	u16 allow_pass_l2:1;
 	u16 src_vsi;
 	struct ice_sw_act_ctrl sw_act;
 	struct ice_adv_rule_flags_info flags_info;
@@ -254,6 +256,9 @@ struct ice_sw_recipe {
 	 */
 	u8 priority;
 
+	u8 need_pass_l2:1;
+	u8 allow_pass_l2:1;
+
 	struct list_head rg_list;
 
 	/* AQ buffer associated with this recipe */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index a09556e57803d..df9171a1a34f0 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -1033,6 +1033,7 @@ enum ice_sw_fwd_act_type {
 	ICE_FWD_TO_Q,
 	ICE_FWD_TO_QGRP,
 	ICE_DROP_PACKET,
+	ICE_NOP,
 	ICE_INVAL_ACT
 };
 
-- 
GitLab


From e9dda2cfab820f76c40932bda629aaeed71eec74 Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@intel.com>
Date: Wed, 12 Jul 2023 13:03:34 +0200
Subject: [PATCH 0342/1806] ice: Add VLAN FDB support in switchdev mode

Add support for matching on VLAN tag in bridge offloads.
Currently only trunk mode is supported.

To enable VLAN filtering (existing FDB entries will be deleted):
ip link set $BR type bridge vlan_filtering 1

To add VLANs to bridge in trunk mode:
bridge vlan add dev $PF1 vid 110-111
bridge vlan add dev $VF1_PR vid 110-111

Signed-off-by: Marcin Szycik <marcin.szycik@intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_eswitch_br.c   | 304 +++++++++++++++++-
 .../net/ethernet/intel/ice/ice_eswitch_br.h   |  21 ++
 2 files changed, 317 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
index 297d0eb45dded..151b40857515f 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
@@ -70,16 +70,34 @@ ice_eswitch_br_rule_delete(struct ice_hw *hw, struct ice_rule_query_data *rule)
 	return err;
 }
 
+static u16
+ice_eswitch_br_get_lkups_cnt(u16 vid)
+{
+	return ice_eswitch_br_is_vid_valid(vid) ? 2 : 1;
+}
+
+static void
+ice_eswitch_br_add_vlan_lkup(struct ice_adv_lkup_elem *list, u16 vid)
+{
+	if (ice_eswitch_br_is_vid_valid(vid)) {
+		list[1].type = ICE_VLAN_OFOS;
+		list[1].h_u.vlan_hdr.vlan = cpu_to_be16(vid & VLAN_VID_MASK);
+		list[1].m_u.vlan_hdr.vlan = cpu_to_be16(0xFFFF);
+	}
+}
+
 static struct ice_rule_query_data *
 ice_eswitch_br_fwd_rule_create(struct ice_hw *hw, int vsi_idx, int port_type,
-			       const unsigned char *mac)
+			       const unsigned char *mac, u16 vid)
 {
 	struct ice_adv_rule_info rule_info = { 0 };
 	struct ice_rule_query_data *rule;
 	struct ice_adv_lkup_elem *list;
-	u16 lkups_cnt = 1;
+	u16 lkups_cnt;
 	int err;
 
+	lkups_cnt = ice_eswitch_br_get_lkups_cnt(vid);
+
 	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
 	if (!rule)
 		return ERR_PTR(-ENOMEM);
@@ -107,6 +125,8 @@ ice_eswitch_br_fwd_rule_create(struct ice_hw *hw, int vsi_idx, int port_type,
 	ether_addr_copy(list[0].h_u.eth_hdr.dst_addr, mac);
 	eth_broadcast_addr(list[0].m_u.eth_hdr.dst_addr);
 
+	ice_eswitch_br_add_vlan_lkup(list, vid);
+
 	rule_info.need_pass_l2 = true;
 
 	rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI;
@@ -129,13 +149,15 @@ err_list_alloc:
 
 static struct ice_rule_query_data *
 ice_eswitch_br_guard_rule_create(struct ice_hw *hw, u16 vsi_idx,
-				 const unsigned char *mac)
+				 const unsigned char *mac, u16 vid)
 {
 	struct ice_adv_rule_info rule_info = { 0 };
 	struct ice_rule_query_data *rule;
 	struct ice_adv_lkup_elem *list;
-	const u16 lkups_cnt = 1;
 	int err = -ENOMEM;
+	u16 lkups_cnt;
+
+	lkups_cnt = ice_eswitch_br_get_lkups_cnt(vid);
 
 	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
 	if (!rule)
@@ -149,6 +171,8 @@ ice_eswitch_br_guard_rule_create(struct ice_hw *hw, u16 vsi_idx,
 	ether_addr_copy(list[0].h_u.eth_hdr.src_addr, mac);
 	eth_broadcast_addr(list[0].m_u.eth_hdr.src_addr);
 
+	ice_eswitch_br_add_vlan_lkup(list, vid);
+
 	rule_info.allow_pass_l2 = true;
 	rule_info.sw_act.vsi_handle = vsi_idx;
 	rule_info.sw_act.fltr_act = ICE_NOP;
@@ -172,7 +196,7 @@ err_exit:
 
 static struct ice_esw_br_flow *
 ice_eswitch_br_flow_create(struct device *dev, struct ice_hw *hw, int vsi_idx,
-			   int port_type, const unsigned char *mac)
+			   int port_type, const unsigned char *mac, u16 vid)
 {
 	struct ice_rule_query_data *fwd_rule, *guard_rule;
 	struct ice_esw_br_flow *flow;
@@ -182,7 +206,8 @@ ice_eswitch_br_flow_create(struct device *dev, struct ice_hw *hw, int vsi_idx,
 	if (!flow)
 		return ERR_PTR(-ENOMEM);
 
-	fwd_rule = ice_eswitch_br_fwd_rule_create(hw, vsi_idx, port_type, mac);
+	fwd_rule = ice_eswitch_br_fwd_rule_create(hw, vsi_idx, port_type, mac,
+						  vid);
 	err = PTR_ERR_OR_ZERO(fwd_rule);
 	if (err) {
 		dev_err(dev, "Failed to create eswitch bridge %sgress forward rule, err: %d\n",
@@ -191,7 +216,7 @@ ice_eswitch_br_flow_create(struct device *dev, struct ice_hw *hw, int vsi_idx,
 		goto err_fwd_rule;
 	}
 
-	guard_rule = ice_eswitch_br_guard_rule_create(hw, vsi_idx, mac);
+	guard_rule = ice_eswitch_br_guard_rule_create(hw, vsi_idx, mac, vid);
 	err = PTR_ERR_OR_ZERO(guard_rule);
 	if (err) {
 		dev_err(dev, "Failed to create eswitch bridge %sgress guard rule, err: %d\n",
@@ -245,6 +270,30 @@ ice_eswitch_br_flow_delete(struct ice_pf *pf, struct ice_esw_br_flow *flow)
 	kfree(flow);
 }
 
+static struct ice_esw_br_vlan *
+ice_esw_br_port_vlan_lookup(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid)
+{
+	struct ice_pf *pf = bridge->br_offloads->pf;
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_esw_br_port *port;
+	struct ice_esw_br_vlan *vlan;
+
+	port = xa_load(&bridge->ports, vsi_idx);
+	if (!port) {
+		dev_info(dev, "Bridge port lookup failed (vsi=%u)\n", vsi_idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	vlan = xa_load(&port->vlans, vid);
+	if (!vlan) {
+		dev_info(dev, "Bridge port vlan metadata lookup failed (vsi=%u)\n",
+			 vsi_idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return vlan;
+}
+
 static void
 ice_eswitch_br_fdb_entry_delete(struct ice_esw_br *bridge,
 				struct ice_esw_br_fdb_entry *fdb_entry)
@@ -314,10 +363,25 @@ ice_eswitch_br_fdb_entry_create(struct net_device *netdev,
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_esw_br_fdb_entry *fdb_entry;
 	struct ice_esw_br_flow *flow;
+	struct ice_esw_br_vlan *vlan;
 	struct ice_hw *hw = &pf->hw;
 	unsigned long event;
 	int err;
 
+	/* untagged filtering is not yet supported */
+	if (!(bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING) && vid)
+		return;
+
+	if ((bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING)) {
+		vlan = ice_esw_br_port_vlan_lookup(bridge, br_port->vsi_idx,
+						   vid);
+		if (IS_ERR(vlan)) {
+			dev_err(dev, "Failed to find vlan lookup, err: %ld\n",
+				PTR_ERR(vlan));
+			return;
+		}
+	}
+
 	fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid);
 	if (fdb_entry)
 		ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry);
@@ -329,7 +393,7 @@ ice_eswitch_br_fdb_entry_create(struct net_device *netdev,
 	}
 
 	flow = ice_eswitch_br_flow_create(dev, hw, br_port->vsi_idx,
-					  br_port->type, mac);
+					  br_port->type, mac, vid);
 	if (IS_ERR(flow)) {
 		err = PTR_ERR(flow);
 		goto err_add_flow;
@@ -484,6 +548,215 @@ ice_eswitch_br_switchdev_event(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
+static void ice_eswitch_br_fdb_flush(struct ice_esw_br *bridge)
+{
+	struct ice_esw_br_fdb_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list)
+		ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry);
+}
+
+static void
+ice_eswitch_br_vlan_filtering_set(struct ice_esw_br *bridge, bool enable)
+{
+	if (enable == !!(bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING))
+		return;
+
+	ice_eswitch_br_fdb_flush(bridge);
+	if (enable)
+		bridge->flags |= ICE_ESWITCH_BR_VLAN_FILTERING;
+	else
+		bridge->flags &= ~ICE_ESWITCH_BR_VLAN_FILTERING;
+}
+
+static void
+ice_eswitch_br_vlan_cleanup(struct ice_esw_br_port *port,
+			    struct ice_esw_br_vlan *vlan)
+{
+	struct ice_esw_br_fdb_entry *fdb_entry, *tmp;
+	struct ice_esw_br *bridge = port->bridge;
+
+	list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) {
+		if (vlan->vid == fdb_entry->data.vid)
+			ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry);
+	}
+
+	xa_erase(&port->vlans, vlan->vid);
+	kfree(vlan);
+}
+
+static void ice_eswitch_br_port_vlans_flush(struct ice_esw_br_port *port)
+{
+	struct ice_esw_br_vlan *vlan;
+	unsigned long index;
+
+	xa_for_each(&port->vlans, index, vlan)
+		ice_eswitch_br_vlan_cleanup(port, vlan);
+}
+
+static struct ice_esw_br_vlan *
+ice_eswitch_br_vlan_create(u16 vid, u16 flags, struct ice_esw_br_port *port)
+{
+	struct ice_esw_br_vlan *vlan;
+	int err;
+
+	vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
+	if (!vlan)
+		return ERR_PTR(-ENOMEM);
+
+	vlan->vid = vid;
+	vlan->flags = flags;
+
+	err = xa_insert(&port->vlans, vlan->vid, vlan, GFP_KERNEL);
+	if (err) {
+		kfree(vlan);
+		return ERR_PTR(err);
+	}
+
+	return vlan;
+}
+
+static int
+ice_eswitch_br_port_vlan_add(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid,
+			     u16 flags, struct netlink_ext_ack *extack)
+{
+	struct ice_esw_br_port *port;
+	struct ice_esw_br_vlan *vlan;
+
+	port = xa_load(&bridge->ports, vsi_idx);
+	if (!port)
+		return -EINVAL;
+
+	vlan = xa_load(&port->vlans, vid);
+	if (vlan) {
+		if (vlan->flags == flags)
+			return 0;
+
+		ice_eswitch_br_vlan_cleanup(port, vlan);
+	}
+
+	vlan = ice_eswitch_br_vlan_create(vid, flags, port);
+	if (IS_ERR(vlan)) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to create VLAN entry, vid: %u, vsi: %u",
+				       vid, vsi_idx);
+		return PTR_ERR(vlan);
+	}
+
+	return 0;
+}
+
+static void
+ice_eswitch_br_port_vlan_del(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid)
+{
+	struct ice_esw_br_port *port;
+	struct ice_esw_br_vlan *vlan;
+
+	port = xa_load(&bridge->ports, vsi_idx);
+	if (!port)
+		return;
+
+	vlan = xa_load(&port->vlans, vid);
+	if (!vlan)
+		return;
+
+	ice_eswitch_br_vlan_cleanup(port, vlan);
+}
+
+static int
+ice_eswitch_br_port_obj_add(struct net_device *netdev, const void *ctx,
+			    const struct switchdev_obj *obj,
+			    struct netlink_ext_ack *extack)
+{
+	struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev);
+	struct switchdev_obj_port_vlan *vlan;
+	int err;
+
+	if (!br_port)
+		return -EINVAL;
+
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
+		err = ice_eswitch_br_port_vlan_add(br_port->bridge,
+						   br_port->vsi_idx, vlan->vid,
+						   vlan->flags, extack);
+		return err;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+ice_eswitch_br_port_obj_del(struct net_device *netdev, const void *ctx,
+			    const struct switchdev_obj *obj)
+{
+	struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev);
+	struct switchdev_obj_port_vlan *vlan;
+
+	if (!br_port)
+		return -EINVAL;
+
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
+		ice_eswitch_br_port_vlan_del(br_port->bridge, br_port->vsi_idx,
+					     vlan->vid);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+ice_eswitch_br_port_obj_attr_set(struct net_device *netdev, const void *ctx,
+				 const struct switchdev_attr *attr,
+				 struct netlink_ext_ack *extack)
+{
+	struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev);
+
+	if (!br_port)
+		return -EINVAL;
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
+		ice_eswitch_br_vlan_filtering_set(br_port->bridge,
+						  attr->u.vlan_filtering);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+ice_eswitch_br_event_blocking(struct notifier_block *nb, unsigned long event,
+			      void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+		err = switchdev_handle_port_obj_add(dev, ptr,
+						    ice_eswitch_br_is_dev_valid,
+						    ice_eswitch_br_port_obj_add);
+		break;
+	case SWITCHDEV_PORT_OBJ_DEL:
+		err = switchdev_handle_port_obj_del(dev, ptr,
+						    ice_eswitch_br_is_dev_valid,
+						    ice_eswitch_br_port_obj_del);
+		break;
+	case SWITCHDEV_PORT_ATTR_SET:
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     ice_eswitch_br_is_dev_valid,
+						     ice_eswitch_br_port_obj_attr_set);
+		break;
+	default:
+		err = 0;
+	}
+
+	return notifier_from_errno(err);
+}
+
 static void
 ice_eswitch_br_port_deinit(struct ice_esw_br *bridge,
 			   struct ice_esw_br_port *br_port)
@@ -502,6 +775,7 @@ ice_eswitch_br_port_deinit(struct ice_esw_br *bridge,
 		vsi->vf->repr->br_port = NULL;
 
 	xa_erase(&bridge->ports, br_port->vsi_idx);
+	ice_eswitch_br_port_vlans_flush(br_port);
 	kfree(br_port);
 }
 
@@ -514,6 +788,8 @@ ice_eswitch_br_port_init(struct ice_esw_br *bridge)
 	if (!br_port)
 		return ERR_PTR(-ENOMEM);
 
+	xa_init(&br_port->vlans);
+
 	br_port->bridge = bridge;
 
 	return br_port;
@@ -813,6 +1089,7 @@ ice_eswitch_br_offloads_deinit(struct ice_pf *pf)
 		return;
 
 	unregister_netdevice_notifier(&br_offloads->netdev_nb);
+	unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk);
 	unregister_switchdev_notifier(&br_offloads->switchdev_nb);
 	destroy_workqueue(br_offloads->wq);
 	/* Although notifier block is unregistered just before,
@@ -856,6 +1133,15 @@ ice_eswitch_br_offloads_init(struct ice_pf *pf)
 		goto err_reg_switchdev_nb;
 	}
 
+	br_offloads->switchdev_blk.notifier_call =
+		ice_eswitch_br_event_blocking;
+	err = register_switchdev_blocking_notifier(&br_offloads->switchdev_blk);
+	if (err) {
+		dev_err(dev,
+			"Failed to register bridge blocking switchdev notifier\n");
+		goto err_reg_switchdev_blk;
+	}
+
 	br_offloads->netdev_nb.notifier_call = ice_eswitch_br_port_event;
 	err = register_netdevice_notifier(&br_offloads->netdev_nb);
 	if (err) {
@@ -867,6 +1153,8 @@ ice_eswitch_br_offloads_init(struct ice_pf *pf)
 	return 0;
 
 err_reg_netdev_nb:
+	unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk);
+err_reg_switchdev_blk:
 	unregister_switchdev_notifier(&br_offloads->switchdev_nb);
 err_reg_switchdev_nb:
 	destroy_workqueue(br_offloads->wq);
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
index d0dcf66ff08b1..fa1f77f76292c 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
@@ -42,6 +42,11 @@ struct ice_esw_br_port {
 	struct ice_vsi *vsi;
 	enum ice_esw_br_port_type type;
 	u16 vsi_idx;
+	struct xarray vlans;
+};
+
+enum {
+	ICE_ESWITCH_BR_VLAN_FILTERING = BIT(0),
 };
 
 struct ice_esw_br {
@@ -52,12 +57,14 @@ struct ice_esw_br {
 	struct list_head fdb_list;
 
 	int ifindex;
+	u32 flags;
 };
 
 struct ice_esw_br_offloads {
 	struct ice_pf *pf;
 	struct ice_esw_br *bridge;
 	struct notifier_block netdev_nb;
+	struct notifier_block switchdev_blk;
 	struct notifier_block switchdev_nb;
 
 	struct workqueue_struct *wq;
@@ -70,6 +77,11 @@ struct ice_esw_br_fdb_work {
 	unsigned long event;
 };
 
+struct ice_esw_br_vlan {
+	u16 vid;
+	u16 flags;
+};
+
 #define ice_nb_to_br_offloads(nb, nb_name) \
 	container_of(nb, \
 		     struct ice_esw_br_offloads, \
@@ -80,6 +92,15 @@ struct ice_esw_br_fdb_work {
 		     struct ice_esw_br_fdb_work, \
 		     work)
 
+static inline bool ice_eswitch_br_is_vid_valid(u16 vid)
+{
+	/* In trunk VLAN mode, for untagged traffic the bridge sends requests
+	 * to offload VLAN 1 with pvid and untagged flags set. Since these
+	 * flags are not supported, add a MAC filter instead.
+	 */
+	return vid > 1;
+}
+
 void
 ice_eswitch_br_offloads_deinit(struct ice_pf *pf);
 int
-- 
GitLab


From 2946204b3fa84fda9b3b3048451fb9ffc977f434 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Wed, 12 Jul 2023 13:03:35 +0200
Subject: [PATCH 0343/1806] ice: implement bridge port vlan

Port VLAN in this case means push and pop VLAN action on specific vid.
There are a few limitation in hardware:
- push and pop can't be used separately
- if port VLAN is used there can't be any trunk VLANs, because pop
  action is done on all traffic received by VSI in port VLAN mode
- port VLAN mode on uplink port isn't supported

Reflect these limitations in code using dev_info to inform the user
about unsupported configuration.

In bridge mode there is a need to configure port vlan without resetting
VFs. To do that implement ice_port_vlan_on/off() functions. They are
only configuring correct vlan_ops to allow setting port vlan.

We also need to clear port vlan without resetting the VF which is not
supported right now. Change it by implementing clear_port_vlan ops.
As previous VLAN configuration isn't always the same, store current
config while creating port vlan and restore it in clear function.

Configuration steps:
- configure switchdev with bridge
- #bridge vlan add dev eth0 vid 120 pvid untagged
- #bridge vlan add dev eth1 vid 120 pvid untagged
- ping from VF0 to VF1

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h          |   1 +
 .../net/ethernet/intel/ice/ice_eswitch_br.c   |  92 ++++++++-
 .../net/ethernet/intel/ice/ice_eswitch_br.h   |   1 +
 .../ethernet/intel/ice/ice_vf_vsi_vlan_ops.c  | 186 ++++++++++--------
 .../ethernet/intel/ice/ice_vf_vsi_vlan_ops.h  |   4 +
 .../net/ethernet/intel/ice/ice_vsi_vlan_lib.c |  84 +++++++-
 .../net/ethernet/intel/ice/ice_vsi_vlan_lib.h |   8 +
 .../net/ethernet/intel/ice/ice_vsi_vlan_ops.h |   1 +
 8 files changed, 287 insertions(+), 90 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 8918a4b836a24..9109006336f0d 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -370,6 +370,7 @@ struct ice_vsi {
 	u16 rx_buf_len;
 
 	struct ice_aqc_vsi_props info;	 /* VSI properties */
+	struct ice_vsi_vlan_info vlan_info;	/* vlan config to be restored */
 
 	/* VSI stats */
 	struct rtnl_link_stats64 net_stats;
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
index 151b40857515f..85143ad9eb1df 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
@@ -5,6 +5,8 @@
 #include "ice_eswitch_br.h"
 #include "ice_repr.h"
 #include "ice_switch.h"
+#include "ice_vlan.h"
+#include "ice_vf_vsi_vlan_ops.h"
 
 static const struct rhashtable_params ice_fdb_ht_params = {
 	.key_offset = offsetof(struct ice_esw_br_fdb_entry, data),
@@ -569,6 +571,22 @@ ice_eswitch_br_vlan_filtering_set(struct ice_esw_br *bridge, bool enable)
 		bridge->flags &= ~ICE_ESWITCH_BR_VLAN_FILTERING;
 }
 
+static void
+ice_eswitch_br_clear_pvid(struct ice_esw_br_port *port)
+{
+	struct ice_vlan port_vlan = ICE_VLAN(ETH_P_8021Q, port->pvid, 0);
+	struct ice_vsi_vlan_ops *vlan_ops;
+
+	vlan_ops = ice_get_compat_vsi_vlan_ops(port->vsi);
+
+	vlan_ops->del_vlan(port->vsi, &port_vlan);
+	vlan_ops->clear_port_vlan(port->vsi);
+
+	ice_vf_vsi_disable_port_vlan(port->vsi);
+
+	port->pvid = 0;
+}
+
 static void
 ice_eswitch_br_vlan_cleanup(struct ice_esw_br_port *port,
 			    struct ice_esw_br_vlan *vlan)
@@ -582,6 +600,8 @@ ice_eswitch_br_vlan_cleanup(struct ice_esw_br_port *port,
 	}
 
 	xa_erase(&port->vlans, vlan->vid);
+	if (port->pvid == vlan->vid)
+		ice_eswitch_br_clear_pvid(port);
 	kfree(vlan);
 }
 
@@ -594,9 +614,50 @@ static void ice_eswitch_br_port_vlans_flush(struct ice_esw_br_port *port)
 		ice_eswitch_br_vlan_cleanup(port, vlan);
 }
 
+static int
+ice_eswitch_br_set_pvid(struct ice_esw_br_port *port,
+			struct ice_esw_br_vlan *vlan)
+{
+	struct ice_vlan port_vlan = ICE_VLAN(ETH_P_8021Q, vlan->vid, 0);
+	struct device *dev = ice_pf_to_dev(port->vsi->back);
+	struct ice_vsi_vlan_ops *vlan_ops;
+	int err;
+
+	if (port->pvid == vlan->vid || vlan->vid == 1)
+		return 0;
+
+	/* Setting port vlan on uplink isn't supported by hw */
+	if (port->type == ICE_ESWITCH_BR_UPLINK_PORT)
+		return -EOPNOTSUPP;
+
+	if (port->pvid) {
+		dev_info(dev,
+			 "Port VLAN (vsi=%u, vid=%u) already exists on the port, remove it before adding new one\n",
+			 port->vsi_idx, port->pvid);
+		return -EEXIST;
+	}
+
+	ice_vf_vsi_enable_port_vlan(port->vsi);
+
+	vlan_ops = ice_get_compat_vsi_vlan_ops(port->vsi);
+	err = vlan_ops->set_port_vlan(port->vsi, &port_vlan);
+	if (err)
+		return err;
+
+	err = vlan_ops->add_vlan(port->vsi, &port_vlan);
+	if (err)
+		return err;
+
+	ice_eswitch_br_port_vlans_flush(port);
+	port->pvid = vlan->vid;
+
+	return 0;
+}
+
 static struct ice_esw_br_vlan *
 ice_eswitch_br_vlan_create(u16 vid, u16 flags, struct ice_esw_br_port *port)
 {
+	struct device *dev = ice_pf_to_dev(port->vsi->back);
 	struct ice_esw_br_vlan *vlan;
 	int err;
 
@@ -606,14 +667,30 @@ ice_eswitch_br_vlan_create(u16 vid, u16 flags, struct ice_esw_br_port *port)
 
 	vlan->vid = vid;
 	vlan->flags = flags;
+	if ((flags & BRIDGE_VLAN_INFO_PVID) &&
+	    (flags & BRIDGE_VLAN_INFO_UNTAGGED)) {
+		err = ice_eswitch_br_set_pvid(port, vlan);
+		if (err)
+			goto err_set_pvid;
+	} else if ((flags & BRIDGE_VLAN_INFO_PVID) ||
+		   (flags & BRIDGE_VLAN_INFO_UNTAGGED)) {
+		dev_info(dev, "VLAN push and pop are supported only simultaneously\n");
+		err = -EOPNOTSUPP;
+		goto err_set_pvid;
+	}
 
 	err = xa_insert(&port->vlans, vlan->vid, vlan, GFP_KERNEL);
-	if (err) {
-		kfree(vlan);
-		return ERR_PTR(err);
-	}
+	if (err)
+		goto err_insert;
 
 	return vlan;
+
+err_insert:
+	if (port->pvid)
+		ice_eswitch_br_clear_pvid(port);
+err_set_pvid:
+	kfree(vlan);
+	return ERR_PTR(err);
 }
 
 static int
@@ -627,6 +704,13 @@ ice_eswitch_br_port_vlan_add(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid,
 	if (!port)
 		return -EINVAL;
 
+	if (port->pvid) {
+		dev_info(ice_pf_to_dev(port->vsi->back),
+			 "Port VLAN (vsi=%u, vid=%d) exists on the port, remove it to add trunk VLANs\n",
+			 port->vsi_idx, port->pvid);
+		return -EEXIST;
+	}
+
 	vlan = xa_load(&port->vlans, vid);
 	if (vlan) {
 		if (vlan->flags == flags)
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
index fa1f77f76292c..978e9ce8e2772 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
@@ -42,6 +42,7 @@ struct ice_esw_br_port {
 	struct ice_vsi *vsi;
 	enum ice_esw_br_port_type type;
 	u16 vsi_idx;
+	u16 pvid;
 	struct xarray vlans;
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
index b1ffb81893d48..d7b10dc67f035 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
@@ -21,6 +21,99 @@ noop_vlan(struct ice_vsi __always_unused *vsi)
 	return 0;
 }
 
+static void ice_port_vlan_on(struct ice_vsi *vsi)
+{
+	struct ice_vsi_vlan_ops *vlan_ops;
+	struct ice_pf *pf = vsi->back;
+
+	if (ice_is_dvm_ena(&pf->hw)) {
+		vlan_ops = &vsi->outer_vlan_ops;
+
+		/* setup outer VLAN ops */
+		vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan;
+		vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan;
+		vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan;
+
+		/* setup inner VLAN ops */
+		vlan_ops = &vsi->inner_vlan_ops;
+		vlan_ops->add_vlan = noop_vlan_arg;
+		vlan_ops->del_vlan = noop_vlan_arg;
+		vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping;
+		vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping;
+		vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion;
+		vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion;
+	} else {
+		vlan_ops = &vsi->inner_vlan_ops;
+
+		vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan;
+		vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan;
+		vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan;
+	}
+	vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering;
+}
+
+static void ice_port_vlan_off(struct ice_vsi *vsi)
+{
+	struct ice_vsi_vlan_ops *vlan_ops;
+	struct ice_pf *pf = vsi->back;
+
+	/* setup inner VLAN ops */
+	vlan_ops = &vsi->inner_vlan_ops;
+
+	vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping;
+	vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping;
+	vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion;
+	vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion;
+
+	if (ice_is_dvm_ena(&pf->hw)) {
+		vlan_ops = &vsi->outer_vlan_ops;
+
+		vlan_ops->del_vlan = ice_vsi_del_vlan;
+		vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping;
+		vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping;
+		vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion;
+		vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion;
+	} else {
+		vlan_ops->del_vlan = ice_vsi_del_vlan;
+	}
+
+	if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags))
+		vlan_ops->ena_rx_filtering = noop_vlan;
+	else
+		vlan_ops->ena_rx_filtering =
+			ice_vsi_ena_rx_vlan_filtering;
+}
+
+/**
+ * ice_vf_vsi_enable_port_vlan - Set VSI VLAN ops to support port VLAN
+ * @vsi: VF's VSI being configured
+ *
+ * The function won't create port VLAN, it only allows to create port VLAN
+ * using VLAN ops on the VF VSI.
+ */
+void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi)
+{
+	if (WARN_ON_ONCE(!vsi->vf))
+		return;
+
+	ice_port_vlan_on(vsi);
+}
+
+/**
+ * ice_vf_vsi_disable_port_vlan - Clear VSI support for creating port VLAN
+ * @vsi: VF's VSI being configured
+ *
+ * The function should be called after removing port VLAN on VSI
+ * (using VLAN ops)
+ */
+void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi)
+{
+	if (WARN_ON_ONCE(!vsi->vf))
+		return;
+
+	ice_port_vlan_off(vsi);
+}
+
 /**
  * ice_vf_vsi_init_vlan_ops - Initialize default VSI VLAN ops for VF VSI
  * @vsi: VF's VSI being configured
@@ -39,91 +132,18 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi)
 	if (WARN_ON(!vf))
 		return;
 
-	if (ice_is_dvm_ena(&pf->hw)) {
-		vlan_ops = &vsi->outer_vlan_ops;
+	if (ice_vf_is_port_vlan_ena(vf))
+		ice_port_vlan_on(vsi);
+	else
+		ice_port_vlan_off(vsi);
 
-		/* outer VLAN ops regardless of port VLAN config */
-		vlan_ops->add_vlan = ice_vsi_add_vlan;
-		vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering;
-		vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering;
-
-		if (ice_vf_is_port_vlan_ena(vf)) {
-			/* setup outer VLAN ops */
-			vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan;
-			/* all Rx traffic should be in the domain of the
-			 * assigned port VLAN, so prevent disabling Rx VLAN
-			 * filtering
-			 */
-			vlan_ops->dis_rx_filtering = noop_vlan;
-			vlan_ops->ena_rx_filtering =
-				ice_vsi_ena_rx_vlan_filtering;
-
-			/* setup inner VLAN ops */
-			vlan_ops = &vsi->inner_vlan_ops;
-			vlan_ops->add_vlan = noop_vlan_arg;
-			vlan_ops->del_vlan = noop_vlan_arg;
-			vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping;
-			vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping;
-			vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion;
-			vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion;
-		} else {
-			vlan_ops->dis_rx_filtering =
-				ice_vsi_dis_rx_vlan_filtering;
-
-			if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags))
-				vlan_ops->ena_rx_filtering = noop_vlan;
-			else
-				vlan_ops->ena_rx_filtering =
-					ice_vsi_ena_rx_vlan_filtering;
-
-			vlan_ops->del_vlan = ice_vsi_del_vlan;
-			vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping;
-			vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping;
-			vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion;
-			vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion;
-
-			/* setup inner VLAN ops */
-			vlan_ops = &vsi->inner_vlan_ops;
-
-			vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping;
-			vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping;
-			vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion;
-			vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion;
-		}
-	} else {
-		vlan_ops = &vsi->inner_vlan_ops;
+	vlan_ops = ice_is_dvm_ena(&pf->hw) ?
+		&vsi->outer_vlan_ops : &vsi->inner_vlan_ops;
 
-		/* inner VLAN ops regardless of port VLAN config */
-		vlan_ops->add_vlan = ice_vsi_add_vlan;
-		vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering;
-		vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering;
-		vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering;
-
-		if (ice_vf_is_port_vlan_ena(vf)) {
-			vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan;
-			vlan_ops->ena_rx_filtering =
-				ice_vsi_ena_rx_vlan_filtering;
-			/* all Rx traffic should be in the domain of the
-			 * assigned port VLAN, so prevent disabling Rx VLAN
-			 * filtering
-			 */
-			vlan_ops->dis_rx_filtering = noop_vlan;
-		} else {
-			vlan_ops->dis_rx_filtering =
-				ice_vsi_dis_rx_vlan_filtering;
-			if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags))
-				vlan_ops->ena_rx_filtering = noop_vlan;
-			else
-				vlan_ops->ena_rx_filtering =
-					ice_vsi_ena_rx_vlan_filtering;
-
-			vlan_ops->del_vlan = ice_vsi_del_vlan;
-			vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping;
-			vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping;
-			vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion;
-			vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion;
-		}
-	}
+	vlan_ops->add_vlan = ice_vsi_add_vlan;
+	vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering;
+	vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering;
+	vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h
index 875a4e615f398..df8aa09df3e32 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h
@@ -13,7 +13,11 @@ void ice_vf_vsi_cfg_svm_legacy_vlan_mode(struct ice_vsi *vsi);
 
 #ifdef CONFIG_PCI_IOV
 void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi);
+void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi);
+void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi);
 #else
 static inline void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) { }
+static inline void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi) { }
+static inline void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi) { }
 #endif /* CONFIG_PCI_IOV */
 #endif /* _ICE_PF_VSI_VLAN_OPS_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
index 5b4a0abb46077..76266e709a392 100644
--- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
@@ -202,6 +202,24 @@ int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi)
 	return ice_vsi_manage_vlan_insertion(vsi);
 }
 
+static void
+ice_save_vlan_info(struct ice_aqc_vsi_props *info,
+		   struct ice_vsi_vlan_info *vlan)
+{
+	vlan->sw_flags2 = info->sw_flags2;
+	vlan->inner_vlan_flags = info->inner_vlan_flags;
+	vlan->outer_vlan_flags = info->outer_vlan_flags;
+}
+
+static void
+ice_restore_vlan_info(struct ice_aqc_vsi_props *info,
+		      struct ice_vsi_vlan_info *vlan)
+{
+	info->sw_flags2 = vlan->sw_flags2;
+	info->inner_vlan_flags = vlan->inner_vlan_flags;
+	info->outer_vlan_flags = vlan->outer_vlan_flags;
+}
+
 /**
  * __ice_vsi_set_inner_port_vlan - set port VLAN VSI context settings to enable a port VLAN
  * @vsi: the VSI to update
@@ -218,6 +236,7 @@ static int __ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, u16 pvid_info)
 	if (!ctxt)
 		return -ENOMEM;
 
+	ice_save_vlan_info(&vsi->info, &vsi->vlan_info);
 	ctxt->info = vsi->info;
 	info = &ctxt->info;
 	info->inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTUNTAGGED |
@@ -259,6 +278,33 @@ int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan)
 	return __ice_vsi_set_inner_port_vlan(vsi, port_vlan_info);
 }
 
+int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	struct ice_aqc_vsi_props *info;
+	struct ice_vsi_ctx *ctxt;
+	int ret;
+
+	ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
+
+	ice_restore_vlan_info(&vsi->info, &vsi->vlan_info);
+	vsi->info.port_based_inner_vlan = 0;
+	ctxt->info = vsi->info;
+	info = &ctxt->info;
+	info->valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID |
+					   ICE_AQ_VSI_PROP_SW_VALID);
+
+	ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
+	if (ret)
+		dev_err(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %s\n",
+			ret, ice_aq_str(hw->adminq.sq_last_status));
+
+	kfree(ctxt);
+	return ret;
+}
+
 /**
  * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI
  * @vsi: VSI to enable or disable VLAN pruning on
@@ -647,6 +693,7 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid)
 	if (!ctxt)
 		return -ENOMEM;
 
+	ice_save_vlan_info(&vsi->info, &vsi->vlan_info);
 	ctxt->info = vsi->info;
 
 	ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
@@ -689,9 +736,6 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid)
  * used if DVM is supported. Also, this function should never be called directly
  * as it should be part of ice_vsi_vlan_ops if it's needed.
  *
- * This function does not support clearing the port VLAN as there is currently
- * no use case for this.
- *
  * Use the ice_vlan structure passed in to set this VSI in a port VLAN.
  */
 int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan)
@@ -705,3 +749,37 @@ int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan)
 
 	return __ice_vsi_set_outer_port_vlan(vsi, port_vlan_info, vlan->tpid);
 }
+
+/**
+ * ice_vsi_clear_outer_port_vlan - clear outer port vlan
+ * @vsi: VSI to configure
+ *
+ * The function is restoring previously set vlan config (saved in
+ * vsi->vlan_info). Setting happens in port vlan configuration.
+ */
+int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	struct ice_vsi_ctx *ctxt;
+	int err;
+
+	ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
+
+	ice_restore_vlan_info(&vsi->info, &vsi->vlan_info);
+	vsi->info.port_based_outer_vlan = 0;
+	ctxt->info = vsi->info;
+
+	ctxt->info.valid_sections =
+		cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID |
+			    ICE_AQ_VSI_PROP_SW_VALID);
+
+	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
+	if (err)
+		dev_err(ice_pf_to_dev(vsi->back), "update VSI for clearing outer port based VLAN failed, err %d aq_err %s\n",
+			err, ice_aq_str(hw->adminq.sq_last_status));
+
+	kfree(ctxt);
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h
index f459909490ecb..f0d84d11bd5b1 100644
--- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h
@@ -7,6 +7,12 @@
 #include <linux/types.h>
 #include "ice_vlan.h"
 
+struct ice_vsi_vlan_info {
+	u8 sw_flags2;
+	u8 inner_vlan_flags;
+	u8 outer_vlan_flags;
+};
+
 struct ice_vsi;
 
 int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan);
@@ -17,6 +23,7 @@ int ice_vsi_dis_inner_stripping(struct ice_vsi *vsi);
 int ice_vsi_ena_inner_insertion(struct ice_vsi *vsi, u16 tpid);
 int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi);
 int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan);
+int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi);
 
 int ice_vsi_ena_rx_vlan_filtering(struct ice_vsi *vsi);
 int ice_vsi_dis_rx_vlan_filtering(struct ice_vsi *vsi);
@@ -28,5 +35,6 @@ int ice_vsi_dis_outer_stripping(struct ice_vsi *vsi);
 int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid);
 int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi);
 int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan);
+int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi);
 
 #endif /* _ICE_VSI_VLAN_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h
index 5b47568f6256f..b2d2330dedcba 100644
--- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h
+++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h
@@ -21,6 +21,7 @@ struct ice_vsi_vlan_ops {
 	int (*ena_tx_filtering)(struct ice_vsi *vsi);
 	int (*dis_tx_filtering)(struct ice_vsi *vsi);
 	int (*set_port_vlan)(struct ice_vsi *vsi, struct ice_vlan *vlan);
+	int (*clear_port_vlan)(struct ice_vsi *vsi);
 };
 
 void ice_vsi_init_vlan_ops(struct ice_vsi *vsi);
-- 
GitLab


From e42c6e0c902b34cdbf06a6d80009a0b3c32e3d37 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Wed, 12 Jul 2023 13:03:36 +0200
Subject: [PATCH 0344/1806] ice: implement static version of ageing

Remove fdb entries always when ageing time expired.

Allow user to set ageing time using port object attribute.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_eswitch_br.c   | 48 +++++++++++++++++++
 .../net/ethernet/intel/ice/ice_eswitch_br.h   | 10 ++++
 2 files changed, 58 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
index 85143ad9eb1df..157f0d01fdb1a 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
@@ -8,6 +8,8 @@
 #include "ice_vlan.h"
 #include "ice_vf_vsi_vlan_ops.h"
 
+#define ICE_ESW_BRIDGE_UPDATE_INTERVAL msecs_to_jiffies(1000)
+
 static const struct rhashtable_params ice_fdb_ht_params = {
 	.key_offset = offsetof(struct ice_esw_br_fdb_entry, data),
 	.key_len = sizeof(struct ice_esw_br_fdb_data),
@@ -406,6 +408,7 @@ ice_eswitch_br_fdb_entry_create(struct net_device *netdev,
 	fdb_entry->br_port = br_port;
 	fdb_entry->flow = flow;
 	fdb_entry->dev = netdev;
+	fdb_entry->last_use = jiffies;
 	event = SWITCHDEV_FDB_ADD_TO_BRIDGE;
 
 	if (added_by_user) {
@@ -806,6 +809,10 @@ ice_eswitch_br_port_obj_attr_set(struct net_device *netdev, const void *ctx,
 		ice_eswitch_br_vlan_filtering_set(br_port->bridge,
 						  attr->u.vlan_filtering);
 		return 0;
+	case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME:
+		br_port->bridge->ageing_time =
+			clock_t_to_jiffies(attr->u.ageing_time);
+		return 0;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -977,6 +984,7 @@ ice_eswitch_br_init(struct ice_esw_br_offloads *br_offloads, int ifindex)
 	INIT_LIST_HEAD(&bridge->fdb_list);
 	bridge->br_offloads = br_offloads;
 	bridge->ifindex = ifindex;
+	bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME);
 	xa_init(&bridge->ports);
 	br_offloads->bridge = bridge;
 
@@ -1172,6 +1180,7 @@ ice_eswitch_br_offloads_deinit(struct ice_pf *pf)
 	if (!br_offloads)
 		return;
 
+	cancel_delayed_work_sync(&br_offloads->update_work);
 	unregister_netdevice_notifier(&br_offloads->netdev_nb);
 	unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk);
 	unregister_switchdev_notifier(&br_offloads->switchdev_nb);
@@ -1186,6 +1195,40 @@ ice_eswitch_br_offloads_deinit(struct ice_pf *pf)
 	rtnl_unlock();
 }
 
+static void ice_eswitch_br_update(struct ice_esw_br_offloads *br_offloads)
+{
+	struct ice_esw_br *bridge = br_offloads->bridge;
+	struct ice_esw_br_fdb_entry *entry, *tmp;
+
+	if (!bridge)
+		return;
+
+	rtnl_lock();
+	list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) {
+		if (entry->flags & ICE_ESWITCH_BR_FDB_ADDED_BY_USER)
+			continue;
+
+		if (time_is_after_eq_jiffies(entry->last_use +
+					     bridge->ageing_time))
+			continue;
+
+		ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry);
+	}
+	rtnl_unlock();
+}
+
+static void ice_eswitch_br_update_work(struct work_struct *work)
+{
+	struct ice_esw_br_offloads *br_offloads;
+
+	br_offloads = ice_work_to_br_offloads(work);
+
+	ice_eswitch_br_update(br_offloads);
+
+	queue_delayed_work(br_offloads->wq, &br_offloads->update_work,
+			   ICE_ESW_BRIDGE_UPDATE_INTERVAL);
+}
+
 int
 ice_eswitch_br_offloads_init(struct ice_pf *pf)
 {
@@ -1234,6 +1277,11 @@ ice_eswitch_br_offloads_init(struct ice_pf *pf)
 		goto err_reg_netdev_nb;
 	}
 
+	INIT_DELAYED_WORK(&br_offloads->update_work,
+			  ice_eswitch_br_update_work);
+	queue_delayed_work(br_offloads->wq, &br_offloads->update_work,
+			   ICE_ESW_BRIDGE_UPDATE_INTERVAL);
+
 	return 0;
 
 err_reg_netdev_nb:
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
index 978e9ce8e2772..85a8fadb2928e 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h
@@ -5,6 +5,7 @@
 #define _ICE_ESWITCH_BR_H_
 
 #include <linux/rhashtable.h>
+#include <linux/workqueue.h>
 
 struct ice_esw_br_fdb_data {
 	unsigned char addr[ETH_ALEN];
@@ -30,6 +31,8 @@ struct ice_esw_br_fdb_entry {
 	struct net_device *dev;
 	struct ice_esw_br_port *br_port;
 	struct ice_esw_br_flow *flow;
+
+	unsigned long last_use;
 };
 
 enum ice_esw_br_port_type {
@@ -59,6 +62,7 @@ struct ice_esw_br {
 
 	int ifindex;
 	u32 flags;
+	unsigned long ageing_time;
 };
 
 struct ice_esw_br_offloads {
@@ -69,6 +73,7 @@ struct ice_esw_br_offloads {
 	struct notifier_block switchdev_nb;
 
 	struct workqueue_struct *wq;
+	struct delayed_work update_work;
 };
 
 struct ice_esw_br_fdb_work {
@@ -88,6 +93,11 @@ struct ice_esw_br_vlan {
 		     struct ice_esw_br_offloads, \
 		     nb_name)
 
+#define ice_work_to_br_offloads(w) \
+	container_of(w, \
+		     struct ice_esw_br_offloads, \
+		     update_work.work)
+
 #define ice_work_to_fdb_work(w) \
 	container_of(w, \
 		     struct ice_esw_br_fdb_work, \
-- 
GitLab


From d129c2a245bfd59035cc661364b056c38f2bf18e Mon Sep 17 00:00:00 2001
From: Pawel Chmielewski <pawel.chmielewski@intel.com>
Date: Wed, 12 Jul 2023 13:03:37 +0200
Subject: [PATCH 0345/1806] ice: add tracepoints for the switchdev bridge

Add tracepoints for the following events:
- Add FDB entry
- Delete FDB entry
- Create bridge VLAN
- Cleanup bridge VLAN
- Link port to the bridge
- Unlink port from the bridge

Signed-off-by: Pawel Chmielewski <pawel.chmielewski@intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_eswitch_br.c   | 10 +++
 drivers/net/ethernet/intel/ice/ice_trace.h    | 90 +++++++++++++++++++
 2 files changed, 100 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
index 157f0d01fdb1a..cc7357ed6e5fb 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
@@ -7,6 +7,7 @@
 #include "ice_switch.h"
 #include "ice_vlan.h"
 #include "ice_vf_vsi_vlan_ops.h"
+#include "ice_trace.h"
 
 #define ICE_ESW_BRIDGE_UPDATE_INTERVAL msecs_to_jiffies(1000)
 
@@ -353,6 +354,7 @@ ice_eswitch_br_fdb_entry_find_and_delete(struct ice_esw_br *bridge,
 		return;
 	}
 
+	trace_ice_eswitch_br_fdb_entry_find_and_delete(fdb_entry);
 	ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry);
 }
 
@@ -422,6 +424,7 @@ ice_eswitch_br_fdb_entry_create(struct net_device *netdev,
 		goto err_fdb_insert;
 
 	list_add(&fdb_entry->list, &bridge->fdb_list);
+	trace_ice_eswitch_br_fdb_entry_create(fdb_entry);
 
 	ice_eswitch_br_fdb_offload_notify(netdev, mac, vid, event);
 
@@ -597,6 +600,8 @@ ice_eswitch_br_vlan_cleanup(struct ice_esw_br_port *port,
 	struct ice_esw_br_fdb_entry *fdb_entry, *tmp;
 	struct ice_esw_br *bridge = port->bridge;
 
+	trace_ice_eswitch_br_vlan_cleanup(vlan);
+
 	list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) {
 		if (vlan->vid == fdb_entry->data.vid)
 			ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry);
@@ -686,6 +691,8 @@ ice_eswitch_br_vlan_create(u16 vid, u16 flags, struct ice_esw_br_port *port)
 	if (err)
 		goto err_insert;
 
+	trace_ice_eswitch_br_vlan_create(vlan);
+
 	return vlan;
 
 err_insert:
@@ -1047,6 +1054,7 @@ ice_eswitch_br_port_unlink(struct ice_esw_br_offloads *br_offloads,
 
 	bridge = br_port->bridge;
 
+	trace_ice_eswitch_br_port_unlink(br_port);
 	ice_eswitch_br_port_deinit(br_port->bridge, br_port);
 	ice_eswitch_br_verify_deinit(br_offloads, bridge);
 
@@ -1075,10 +1083,12 @@ ice_eswitch_br_port_link(struct ice_esw_br_offloads *br_offloads,
 		struct ice_repr *repr = ice_netdev_to_repr(dev);
 
 		err = ice_eswitch_br_vf_repr_port_init(bridge, repr);
+		trace_ice_eswitch_br_port_link(repr->br_port);
 	} else {
 		struct ice_pf *pf = ice_netdev_to_pf(dev);
 
 		err = ice_eswitch_br_uplink_port_init(bridge, pf);
+		trace_ice_eswitch_br_port_link(pf->br_port);
 	}
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed to init bridge port");
diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h
index ae98d5a8ff60e..b2f5c9fe01492 100644
--- a/drivers/net/ethernet/intel/ice/ice_trace.h
+++ b/drivers/net/ethernet/intel/ice/ice_trace.h
@@ -21,6 +21,7 @@
 #define _ICE_TRACE_H_
 
 #include <linux/tracepoint.h>
+#include "ice_eswitch_br.h"
 
 /* ice_trace() macro enables shared code to refer to trace points
  * like:
@@ -240,6 +241,95 @@ DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_fw_req);
 DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_fw_done);
 DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_complete);
 
+DECLARE_EVENT_CLASS(ice_esw_br_fdb_template,
+		    TP_PROTO(struct ice_esw_br_fdb_entry *fdb),
+		    TP_ARGS(fdb),
+		    TP_STRUCT__entry(__array(char, dev_name, IFNAMSIZ)
+				     __array(unsigned char, addr, ETH_ALEN)
+				     __field(u16, vid)
+				     __field(int, flags)),
+		    TP_fast_assign(strscpy(__entry->dev_name,
+					   netdev_name(fdb->dev),
+					   IFNAMSIZ);
+				   memcpy(__entry->addr, fdb->data.addr, ETH_ALEN);
+				   __entry->vid = fdb->data.vid;
+				   __entry->flags = fdb->flags;),
+		    TP_printk("net_device=%s addr=%pM vid=%u flags=%x",
+			      __entry->dev_name,
+			      __entry->addr,
+			      __entry->vid,
+			      __entry->flags)
+);
+
+DEFINE_EVENT(ice_esw_br_fdb_template,
+	     ice_eswitch_br_fdb_entry_create,
+	     TP_PROTO(struct ice_esw_br_fdb_entry *fdb),
+	     TP_ARGS(fdb)
+);
+
+DEFINE_EVENT(ice_esw_br_fdb_template,
+	     ice_eswitch_br_fdb_entry_find_and_delete,
+	     TP_PROTO(struct ice_esw_br_fdb_entry *fdb),
+	     TP_ARGS(fdb)
+);
+
+DECLARE_EVENT_CLASS(ice_esw_br_vlan_template,
+		    TP_PROTO(struct ice_esw_br_vlan *vlan),
+		    TP_ARGS(vlan),
+		    TP_STRUCT__entry(__field(u16, vid)
+				     __field(u16, flags)),
+		    TP_fast_assign(__entry->vid = vlan->vid;
+				   __entry->flags = vlan->flags;),
+		    TP_printk("vid=%u flags=%x",
+			      __entry->vid,
+			      __entry->flags)
+);
+
+DEFINE_EVENT(ice_esw_br_vlan_template,
+	     ice_eswitch_br_vlan_create,
+	     TP_PROTO(struct ice_esw_br_vlan *vlan),
+	     TP_ARGS(vlan)
+);
+
+DEFINE_EVENT(ice_esw_br_vlan_template,
+	     ice_eswitch_br_vlan_cleanup,
+	     TP_PROTO(struct ice_esw_br_vlan *vlan),
+	     TP_ARGS(vlan)
+);
+
+#define ICE_ESW_BR_PORT_NAME_L 16
+
+DECLARE_EVENT_CLASS(ice_esw_br_port_template,
+		    TP_PROTO(struct ice_esw_br_port *port),
+		    TP_ARGS(port),
+		    TP_STRUCT__entry(__field(u16, vport_num)
+				     __array(char, port_type, ICE_ESW_BR_PORT_NAME_L)),
+		    TP_fast_assign(__entry->vport_num = port->vsi_idx;
+					if (port->type == ICE_ESWITCH_BR_UPLINK_PORT)
+						strscpy(__entry->port_type,
+							"Uplink",
+							ICE_ESW_BR_PORT_NAME_L);
+					else
+						strscpy(__entry->port_type,
+							"VF Representor",
+							ICE_ESW_BR_PORT_NAME_L);),
+		    TP_printk("vport_num=%u port type=%s",
+			      __entry->vport_num,
+			      __entry->port_type)
+);
+
+DEFINE_EVENT(ice_esw_br_port_template,
+	     ice_eswitch_br_port_link,
+	     TP_PROTO(struct ice_esw_br_port *port),
+	     TP_ARGS(port)
+);
+
+DEFINE_EVENT(ice_esw_br_port_template,
+	     ice_eswitch_br_port_unlink,
+	     TP_PROTO(struct ice_esw_br_port *port),
+	     TP_ARGS(port)
+);
+
 /* End tracepoints */
 
 #endif /* _ICE_TRACE_H_ */
-- 
GitLab


From dc644b540a2d2874112706591234be3d3fbf9ef7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 22 Jul 2023 01:33:30 +0200
Subject: [PATCH 0346/1806] tcx: Fix splat in ingress_destroy upon
 tcx_entry_free

On qdisc destruction, the ingress_destroy() needs to update the correct
entry, that is, tcx_entry_update must NULL the dev->tcx_ingress pointer.
Therefore, fix the typo.

Fixes: e420bed02507 ("bpf: Add fd-based tcx multi-prog infra with link support")
Reported-by: syzbot+bdcf141f362ef83335cf@syzkaller.appspotmail.com
Reported-by: syzbot+b202b7208664142954fa@syzkaller.appspotmail.com
Reported-by: syzbot+14736e249bce46091c18@syzkaller.appspotmail.com
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: syzbot+bdcf141f362ef83335cf@syzkaller.appspotmail.com
Tested-by: syzbot+b202b7208664142954fa@syzkaller.appspotmail.com
Tested-by: syzbot+14736e249bce46091c18@syzkaller.appspotmail.com
Tested-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/20230721233330.5678-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_ingress.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 04e886f6cee43..a463a63192c3c 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -123,7 +123,7 @@ static void ingress_destroy(struct Qdisc *sch)
 	if (entry) {
 		tcx_miniq_set_active(entry, false);
 		if (!tcx_entry_is_active(entry)) {
-			tcx_entry_update(dev, NULL, false);
+			tcx_entry_update(dev, NULL, true);
 			tcx_entry_free(entry);
 		}
 	}
-- 
GitLab


From a097627dcaddb90f55c1780da348bf9b56f6b4bd Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Fri, 21 Jul 2023 16:58:08 +0200
Subject: [PATCH 0347/1806] net: add missing net_device::xdp_zc_max_segs
 description

Cited commit under 'Fixes' tag introduced new member to struct
net_device without providing description of it - fix it.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/all/20230720141613.61488b9e@canb.auug.org.au/
Fixes: 13ce2daa259a ("xsk: add new netlink attribute dedicated for ZC max frags")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Tested-by: Simon Horman <simon.horman@corigine.com> # build-tested
Link: https://lore.kernel.org/r/20230721145808.596298-1-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3800d04796984..11652e464f5df 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2043,6 +2043,8 @@ enum netdev_ml_priv_type {
  *			receive offload (GRO)
  * 	@gro_ipv4_max_size:	Maximum size of aggregated packet in generic
  * 				receive offload (GRO), for IPv4.
+ *	@xdp_zc_max_segs:	Maximum number of segments supported by AF_XDP
+ *				zero copy driver
  *
  *	@dev_addr_shadow:	Copy of @dev_addr to catch direct writes.
  *	@linkwatch_dev_tracker:	refcount tracker used by linkwatch.
-- 
GitLab


From 9f64b6e459d3eee73ca4ea6226653e008d1c1e61 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 21 Jul 2023 02:21:44 -0700
Subject: [PATCH 0348/1806] netconsole: Use sysfs_emit() instead of snprintf()

According to the sysfs.rst documentation, _show() functions should only
use sysfs_emit() instead of snprintf().

Since snprintf() shouldn't be used in the sysfs _show() path, replace it
by sysfs_emit().

Suggested-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230721092146.4036622-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 31cbe02eda495..a3c53b8c9efc4 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -260,32 +260,32 @@ static struct netconsole_target *to_target(struct config_item *item)
 
 static ssize_t enabled_show(struct config_item *item, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->enabled);
+	return sysfs_emit(buf, "%d\n", to_target(item)->enabled);
 }
 
 static ssize_t extended_show(struct config_item *item, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->extended);
+	return sysfs_emit(buf, "%d\n", to_target(item)->extended);
 }
 
 static ssize_t release_show(struct config_item *item, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->release);
+	return sysfs_emit(buf, "%d\n", to_target(item)->release);
 }
 
 static ssize_t dev_name_show(struct config_item *item, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%s\n", to_target(item)->np.dev_name);
+	return sysfs_emit(buf, "%s\n", to_target(item)->np.dev_name);
 }
 
 static ssize_t local_port_show(struct config_item *item, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->np.local_port);
+	return sysfs_emit(buf, "%d\n", to_target(item)->np.local_port);
 }
 
 static ssize_t remote_port_show(struct config_item *item, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->np.remote_port);
+	return sysfs_emit(buf, "%d\n", to_target(item)->np.remote_port);
 }
 
 static ssize_t local_ip_show(struct config_item *item, char *buf)
@@ -293,9 +293,9 @@ static ssize_t local_ip_show(struct config_item *item, char *buf)
 	struct netconsole_target *nt = to_target(item);
 
 	if (nt->np.ipv6)
-		return snprintf(buf, PAGE_SIZE, "%pI6c\n", &nt->np.local_ip.in6);
+		return sysfs_emit(buf, "%pI6c\n", &nt->np.local_ip.in6);
 	else
-		return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.local_ip);
+		return sysfs_emit(buf, "%pI4\n", &nt->np.local_ip);
 }
 
 static ssize_t remote_ip_show(struct config_item *item, char *buf)
@@ -303,9 +303,9 @@ static ssize_t remote_ip_show(struct config_item *item, char *buf)
 	struct netconsole_target *nt = to_target(item);
 
 	if (nt->np.ipv6)
-		return snprintf(buf, PAGE_SIZE, "%pI6c\n", &nt->np.remote_ip.in6);
+		return sysfs_emit(buf, "%pI6c\n", &nt->np.remote_ip.in6);
 	else
-		return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.remote_ip);
+		return sysfs_emit(buf, "%pI4\n", &nt->np.remote_ip);
 }
 
 static ssize_t local_mac_show(struct config_item *item, char *buf)
@@ -313,12 +313,12 @@ static ssize_t local_mac_show(struct config_item *item, char *buf)
 	struct net_device *dev = to_target(item)->np.dev;
 	static const u8 bcast[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
 
-	return snprintf(buf, PAGE_SIZE, "%pM\n", dev ? dev->dev_addr : bcast);
+	return sysfs_emit(buf, "%pM\n", dev ? dev->dev_addr : bcast);
 }
 
 static ssize_t remote_mac_show(struct config_item *item, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%pM\n", to_target(item)->np.remote_mac);
+	return sysfs_emit(buf, "%pM\n", to_target(item)->np.remote_mac);
 }
 
 /*
-- 
GitLab


From 004a04b97bbcbb630421e44aadfe675fe6b4c460 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 21 Jul 2023 02:21:45 -0700
Subject: [PATCH 0349/1806] netconsole: Use kstrtobool() instead of kstrtoint()

Replace kstrtoint() by kstrtobool() in the sysfs _store() functions.
This improves the user usability and simplify the code.

With this fix, it is now possible to use [YyNn] to set and unset a
feature. Old behaviour is still unchanged.

kstrtobool() is also safer and doesn't need the extra validation that
is required when converting a string to bool (end field in the struct),
which makes the code simpler.

Suggested-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230721092146.4036622-2-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 28 +++++++++-------------------
 1 file changed, 9 insertions(+), 19 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index a3c53b8c9efc4..87f18aedd3bd7 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -333,17 +333,15 @@ static ssize_t enabled_store(struct config_item *item,
 {
 	struct netconsole_target *nt = to_target(item);
 	unsigned long flags;
-	int enabled;
+	bool enabled;
 	int err;
 
 	mutex_lock(&dynamic_netconsole_mutex);
-	err = kstrtoint(buf, 10, &enabled);
-	if (err < 0)
+	err = kstrtobool(buf, &enabled);
+	if (err)
 		goto out_unlock;
 
 	err = -EINVAL;
-	if (enabled < 0 || enabled > 1)
-		goto out_unlock;
 	if ((bool)enabled == nt->enabled) {
 		pr_info("network logging has already %s\n",
 			nt->enabled ? "started" : "stopped");
@@ -394,7 +392,7 @@ static ssize_t release_store(struct config_item *item, const char *buf,
 			     size_t count)
 {
 	struct netconsole_target *nt = to_target(item);
-	int release;
+	bool release;
 	int err;
 
 	mutex_lock(&dynamic_netconsole_mutex);
@@ -405,13 +403,9 @@ static ssize_t release_store(struct config_item *item, const char *buf,
 		goto out_unlock;
 	}
 
-	err = kstrtoint(buf, 10, &release);
-	if (err < 0)
-		goto out_unlock;
-	if (release < 0 || release > 1) {
-		err = -EINVAL;
+	err = kstrtobool(buf, &release);
+	if (err)
 		goto out_unlock;
-	}
 
 	nt->release = release;
 
@@ -426,7 +420,7 @@ static ssize_t extended_store(struct config_item *item, const char *buf,
 		size_t count)
 {
 	struct netconsole_target *nt = to_target(item);
-	int extended;
+	bool extended;
 	int err;
 
 	mutex_lock(&dynamic_netconsole_mutex);
@@ -437,13 +431,9 @@ static ssize_t extended_store(struct config_item *item, const char *buf,
 		goto out_unlock;
 	}
 
-	err = kstrtoint(buf, 10, &extended);
-	if (err < 0)
-		goto out_unlock;
-	if (extended < 0 || extended > 1) {
-		err = -EINVAL;
+	err = kstrtobool(buf, &extended);
+	if (err)
 		goto out_unlock;
-	}
 
 	nt->extended = extended;
 
-- 
GitLab


From b8dc6d6ce93142ccd4c976003bb6c25d63aac2ce Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 20 Jul 2023 20:47:50 +0200
Subject: [PATCH 0350/1806] mptcp: fix rcv buffer auto-tuning

The MPTCP code uses the assumption that the tcp_win_from_space() helper
does not use any TCP-specific field, and thus works correctly operating
on an MPTCP socket.

The commit dfa2f0483360 ("tcp: get rid of sysctl_tcp_adv_win_scale")
broke such assumption, and as a consequence most MPTCP connections stall
on zero-window event due to auto-tuning changing the rcv buffer size
quite randomly.

Address the issue syncing again the MPTCP auto-tuning code with the TCP
one. To achieve that, factor out the windows size logic in socket
independent helpers, and reuse them in mptcp_rcv_space_adjust(). The
MPTCP level scaling_ratio is selected as the minimum one from the all
the subflows, as a worst-case estimate.

Fixes: dfa2f0483360 ("tcp: get rid of sysctl_tcp_adv_win_scale")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Link: https://lore.kernel.org/r/20230720-upstream-net-next-20230720-mptcp-fix-rcv-buffer-auto-tuning-v1-1-175ef12b8380@tessares.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h    | 20 +++++++++++++++-----
 net/mptcp/protocol.c | 15 +++++++--------
 net/mptcp/protocol.h |  8 +++++++-
 net/mptcp/subflow.c  |  2 +-
 4 files changed, 30 insertions(+), 15 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index d17cb8ab4c48c..6ebf54992ffee 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1430,22 +1430,32 @@ void tcp_select_initial_window(const struct sock *sk, int __space,
 			       __u32 *window_clamp, int wscale_ok,
 			       __u8 *rcv_wscale, __u32 init_rcv_wnd);
 
-static inline int tcp_win_from_space(const struct sock *sk, int space)
+static inline int __tcp_win_from_space(u8 scaling_ratio, int space)
 {
-	s64 scaled_space = (s64)space * tcp_sk(sk)->scaling_ratio;
+	s64 scaled_space = (s64)space * scaling_ratio;
 
 	return scaled_space >> TCP_RMEM_TO_WIN_SCALE;
 }
 
-/* inverse of tcp_win_from_space() */
-static inline int tcp_space_from_win(const struct sock *sk, int win)
+static inline int tcp_win_from_space(const struct sock *sk, int space)
+{
+	return __tcp_win_from_space(tcp_sk(sk)->scaling_ratio, space);
+}
+
+/* inverse of __tcp_win_from_space() */
+static inline int __tcp_space_from_win(u8 scaling_ratio, int win)
 {
 	u64 val = (u64)win << TCP_RMEM_TO_WIN_SCALE;
 
-	do_div(val, tcp_sk(sk)->scaling_ratio);
+	do_div(val, scaling_ratio);
 	return val;
 }
 
+static inline int tcp_space_from_win(const struct sock *sk, int win)
+{
+	return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win);
+}
+
 static inline void tcp_scaling_ratio_init(struct sock *sk)
 {
 	/* Assume a conservative default of 1200 bytes of payload per 4K page.
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 22323b1fa1842..68da265399704 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -90,6 +90,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	if (err)
 		return err;
 
+	msk->scaling_ratio = tcp_sk(ssock->sk)->scaling_ratio;
 	WRITE_ONCE(msk->first, ssock->sk);
 	WRITE_ONCE(msk->subflow, ssock);
 	subflow = mptcp_subflow_ctx(ssock->sk);
@@ -1881,6 +1882,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 {
 	struct mptcp_subflow_context *subflow;
 	struct sock *sk = (struct sock *)msk;
+	u8 scaling_ratio = U8_MAX;
 	u32 time, advmss = 1;
 	u64 rtt_us, mstamp;
 
@@ -1911,9 +1913,11 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 
 		rtt_us = max(sf_rtt_us, rtt_us);
 		advmss = max(sf_advmss, advmss);
+		scaling_ratio = min(tp->scaling_ratio, scaling_ratio);
 	}
 
 	msk->rcvq_space.rtt_us = rtt_us;
+	msk->scaling_ratio = scaling_ratio;
 	if (time < (rtt_us >> 3) || rtt_us == 0)
 		return;
 
@@ -1922,8 +1926,8 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 
 	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
-		int rcvmem, rcvbuf;
 		u64 rcvwin, grow;
+		int rcvbuf;
 
 		rcvwin = ((u64)msk->rcvq_space.copied << 1) + 16 * advmss;
 
@@ -1932,18 +1936,13 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 		do_div(grow, msk->rcvq_space.space);
 		rcvwin += (grow << 1);
 
-		rcvmem = SKB_TRUESIZE(advmss + MAX_TCP_HEADER);
-		while (tcp_win_from_space(sk, rcvmem) < advmss)
-			rcvmem += 128;
-
-		do_div(rcvwin, advmss);
-		rcvbuf = min_t(u64, rcvwin * rcvmem,
+		rcvbuf = min_t(u64, __tcp_space_from_win(scaling_ratio, rcvwin),
 			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 
 		if (rcvbuf > sk->sk_rcvbuf) {
 			u32 window_clamp;
 
-			window_clamp = tcp_win_from_space(sk, rcvbuf);
+			window_clamp = __tcp_win_from_space(scaling_ratio, rcvbuf);
 			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
 			/* Make subflows follow along.  If we do not do this, we
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 37fbe22e2433d..795f422e8597e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -321,6 +321,7 @@ struct mptcp_sock {
 		u64	time;	/* start time of measurement window */
 		u64	rtt_us; /* last maximum rtt of subflows */
 	} rcvq_space;
+	u8		scaling_ratio;
 
 	u32		subflow_id;
 	u32		setsockopt_seq;
@@ -351,9 +352,14 @@ static inline int __mptcp_rmem(const struct sock *sk)
 	return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released);
 }
 
+static inline int mptcp_win_from_space(const struct sock *sk, int space)
+{
+	return __tcp_win_from_space(mptcp_sk(sk)->scaling_ratio, space);
+}
+
 static inline int __mptcp_space(const struct sock *sk)
 {
-	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
+	return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
 }
 
 static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 9ee3b7abbaf6d..ad7080fabb2ff 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1359,7 +1359,7 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space)
 	const struct sock *sk = subflow->conn;
 
 	*space = __mptcp_space(sk);
-	*full_space = tcp_full_space(sk);
+	*full_space = mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
 void __mptcp_error_report(struct sock *sk)
-- 
GitLab


From ec87f05402f592d27507e1aa6b2fd21c486f2cc0 Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Fri, 21 Jul 2023 10:09:25 +0530
Subject: [PATCH 0351/1806] octeontx2-af: Install TC filter rules in hardware
 based on priority

As of today, hardware does not support installing tc filter
rules based on priority. This patch adds support to install
the hardware rules based on priority. The final hardware rules
will not be dependent on rule installation order, it will be strictly
priority based, same as software.

Signed-off-by: Suman Ghosh <sumang@marvell.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230721043925.2627806-1-sumang@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/marvell/octeontx2/af/mbox.h  |   9 +-
 .../marvell/octeontx2/af/rvu_npc_fs.c         |   9 +-
 .../marvell/octeontx2/af/rvu_switch.c         |   6 +-
 .../marvell/octeontx2/nic/otx2_common.h       |  11 +-
 .../marvell/octeontx2/nic/otx2_devlink.c      |   1 -
 .../marvell/octeontx2/nic/otx2_ethtool.c      |   1 +
 .../marvell/octeontx2/nic/otx2_flows.c        |   2 +
 .../ethernet/marvell/octeontx2/nic/otx2_tc.c  | 320 +++++++++++++-----
 8 files changed, 255 insertions(+), 104 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index eba307eee2b2b..ed66c59891028 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -235,7 +235,7 @@ M(NPC_GET_KEX_CFG,	  0x600c, npc_get_kex_cfg,			\
 M(NPC_INSTALL_FLOW,	  0x600d, npc_install_flow,			       \
 				  npc_install_flow_req, npc_install_flow_rsp)  \
 M(NPC_DELETE_FLOW,	  0x600e, npc_delete_flow,			\
-				  npc_delete_flow_req, msg_rsp)		\
+				  npc_delete_flow_req, npc_delete_flow_rsp)		\
 M(NPC_MCAM_READ_ENTRY,	  0x600f, npc_mcam_read_entry,			\
 				  npc_mcam_read_entry_req,		\
 				  npc_mcam_read_entry_rsp)		\
@@ -1491,6 +1491,8 @@ struct npc_install_flow_req {
 	u8  vtag0_op;
 	u16 vtag1_def;
 	u8  vtag1_op;
+	/* old counter value */
+	u16 cntr_val;
 };
 
 struct npc_install_flow_rsp {
@@ -1506,6 +1508,11 @@ struct npc_delete_flow_req {
 	u8 all; /* PF + VFs */
 };
 
+struct npc_delete_flow_rsp {
+	struct mbox_msghdr hdr;
+	u16 cntr_val;
+};
+
 struct npc_mcam_read_entry_req {
 	struct mbox_msghdr hdr;
 	u16 entry;	 /* MCAM entry to read */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index 952319453701b..9c365cc3e7364 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -1192,7 +1192,7 @@ find_rule:
 	write_req.enable_entry = (u8)enable;
 	/* if counter is available then clear and use it */
 	if (req->set_cntr && rule->has_cntr) {
-		rvu_write64(rvu, blkaddr, NPC_AF_MATCH_STATX(rule->cntr), 0x00);
+		rvu_write64(rvu, blkaddr, NPC_AF_MATCH_STATX(rule->cntr), req->cntr_val);
 		write_req.set_cntr = 1;
 		write_req.cntr = rule->cntr;
 	}
@@ -1407,12 +1407,13 @@ static int npc_delete_flow(struct rvu *rvu, struct rvu_npc_mcam_rule *rule,
 
 int rvu_mbox_handler_npc_delete_flow(struct rvu *rvu,
 				     struct npc_delete_flow_req *req,
-				     struct msg_rsp *rsp)
+				     struct npc_delete_flow_rsp *rsp)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct rvu_npc_mcam_rule *iter, *tmp;
 	u16 pcifunc = req->hdr.pcifunc;
 	struct list_head del_list;
+	int blkaddr;
 
 	INIT_LIST_HEAD(&del_list);
 
@@ -1428,6 +1429,10 @@ int rvu_mbox_handler_npc_delete_flow(struct rvu *rvu,
 				list_move_tail(&iter->list, &del_list);
 			/* single rule */
 			} else if (req->entry == iter->entry) {
+				blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+				if (blkaddr)
+					rsp->cntr_val = rvu_read64(rvu, blkaddr,
+								   NPC_AF_MATCH_STATX(iter->cntr));
 				list_move_tail(&iter->list, &del_list);
 				break;
 			}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
index 592b317f46376..854045ed3b068 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
@@ -158,6 +158,7 @@ void rvu_switch_enable(struct rvu *rvu)
 	struct npc_mcam_alloc_entry_req alloc_req = { 0 };
 	struct npc_mcam_alloc_entry_rsp alloc_rsp = { 0 };
 	struct npc_delete_flow_req uninstall_req = { 0 };
+	struct npc_delete_flow_rsp uninstall_rsp = { 0 };
 	struct npc_mcam_free_entry_req free_req = { 0 };
 	struct rvu_switch *rswitch = &rvu->rswitch;
 	struct msg_rsp rsp;
@@ -197,7 +198,7 @@ void rvu_switch_enable(struct rvu *rvu)
 uninstall_rules:
 	uninstall_req.start = rswitch->start_entry;
 	uninstall_req.end =  rswitch->start_entry + rswitch->used_entries - 1;
-	rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &rsp);
+	rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &uninstall_rsp);
 	kfree(rswitch->entry2pcifunc);
 free_entries:
 	free_req.all = 1;
@@ -209,6 +210,7 @@ exit:
 void rvu_switch_disable(struct rvu *rvu)
 {
 	struct npc_delete_flow_req uninstall_req = { 0 };
+	struct npc_delete_flow_rsp uninstall_rsp = { 0 };
 	struct npc_mcam_free_entry_req free_req = { 0 };
 	struct rvu_switch *rswitch = &rvu->rswitch;
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -250,7 +252,7 @@ void rvu_switch_disable(struct rvu *rvu)
 	uninstall_req.start = rswitch->start_entry;
 	uninstall_req.end =  rswitch->start_entry + rswitch->used_entries - 1;
 	free_req.all = 1;
-	rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &rsp);
+	rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &uninstall_rsp);
 	rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp);
 	rswitch->used_entries = 0;
 	kfree(rswitch->entry2pcifunc);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 37d792f188093..25e99fd2e3fd3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -361,13 +361,8 @@ struct otx2_flow_config {
 	struct list_head	flow_list;
 	u32			dmacflt_max_flows;
 	u16                     max_flows;
-};
-
-struct otx2_tc_info {
-	/* hash table to store TC offloaded flows */
-	struct rhashtable		flow_table;
-	struct rhashtable_params	flow_ht_params;
-	unsigned long			*tc_entries_bitmap;
+	struct list_head	flow_list_tc;
+	bool			ntuple;
 };
 
 struct dev_hw_ops {
@@ -492,7 +487,6 @@ struct otx2_nic {
 	/* NPC MCAM */
 	struct otx2_flow_config	*flow_cfg;
 	struct otx2_mac_table	*mac_table;
-	struct otx2_tc_info	tc_info;
 
 	u64			reset_count;
 	struct work_struct	reset_task;
@@ -1064,7 +1058,6 @@ int otx2_init_tc(struct otx2_nic *nic);
 void otx2_shutdown_tc(struct otx2_nic *nic);
 int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 		  void *type_data);
-int otx2_tc_alloc_ent_bitmap(struct otx2_nic *nic);
 /* CGX/RPM DMAC filters support */
 int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf);
 int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u32 bit_pos);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
index 63ef7c41d18d1..4e1130496573e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -41,7 +41,6 @@ static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id,
 		return 0;
 
 	otx2_alloc_mcam_entries(pfvf, ctx->val.vu16);
-	otx2_tc_alloc_ent_bitmap(pfvf);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index c47d91da32dc7..9efcec549834e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -764,6 +764,7 @@ static int otx2_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc)
 	struct otx2_nic *pfvf = netdev_priv(dev);
 	int ret = -EOPNOTSUPP;
 
+	pfvf->flow_cfg->ntuple = ntuple;
 	switch (nfc->cmd) {
 	case ETHTOOL_SRXFH:
 		ret = otx2_set_rss_hash_opts(pfvf, nfc);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 2d7713a1a1539..4762dbea64a12 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -276,6 +276,7 @@ int otx2vf_mcam_flow_init(struct otx2_nic *pfvf)
 
 	flow_cfg = pfvf->flow_cfg;
 	INIT_LIST_HEAD(&flow_cfg->flow_list);
+	INIT_LIST_HEAD(&flow_cfg->flow_list_tc);
 	flow_cfg->max_flows = 0;
 
 	return 0;
@@ -298,6 +299,7 @@ int otx2_mcam_flow_init(struct otx2_nic *pf)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&pf->flow_cfg->flow_list);
+	INIT_LIST_HEAD(&pf->flow_cfg->flow_list_tc);
 
 	/* Allocate bare minimum number of MCAM entries needed for
 	 * unicast and ntuple filters.
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 5e56b6c3e60ad..1e6fc23eca4fe 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -34,9 +34,8 @@ struct otx2_tc_flow_stats {
 };
 
 struct otx2_tc_flow {
-	struct rhash_head		node;
+	struct list_head		list;
 	unsigned long			cookie;
-	unsigned int			bitpos;
 	struct rcu_head			rcu;
 	struct otx2_tc_flow_stats	stats;
 	spinlock_t			lock; /* lock for stats */
@@ -44,31 +43,10 @@ struct otx2_tc_flow {
 	u16				entry;
 	u16				leaf_profile;
 	bool				is_act_police;
+	u32				prio;
+	struct npc_install_flow_req	req;
 };
 
-int otx2_tc_alloc_ent_bitmap(struct otx2_nic *nic)
-{
-	struct otx2_tc_info *tc = &nic->tc_info;
-
-	if (!nic->flow_cfg->max_flows)
-		return 0;
-
-	/* Max flows changed, free the existing bitmap */
-	kfree(tc->tc_entries_bitmap);
-
-	tc->tc_entries_bitmap =
-			kcalloc(BITS_TO_LONGS(nic->flow_cfg->max_flows),
-				sizeof(long), GFP_KERNEL);
-	if (!tc->tc_entries_bitmap) {
-		netdev_err(nic->netdev,
-			   "Unable to alloc TC flow entries bitmap\n");
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(otx2_tc_alloc_ent_bitmap);
-
 static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst,
 				      u32 *burst_exp, u32 *burst_mantissa)
 {
@@ -707,8 +685,117 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 	return otx2_tc_parse_actions(nic, &rule->action, req, f, node);
 }
 
-static int otx2_del_mcam_flow_entry(struct otx2_nic *nic, u16 entry)
+static void otx2_destroy_tc_flow_list(struct otx2_nic *pfvf)
+{
+	struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
+	struct otx2_tc_flow *iter, *tmp;
+
+	if (!(pfvf->flags & OTX2_FLAG_MCAM_ENTRIES_ALLOC))
+		return;
+
+	list_for_each_entry_safe(iter, tmp, &flow_cfg->flow_list_tc, list) {
+		list_del(&iter->list);
+		kfree(iter);
+		flow_cfg->nr_flows--;
+	}
+}
+
+static struct otx2_tc_flow *otx2_tc_get_entry_by_cookie(struct otx2_flow_config *flow_cfg,
+							unsigned long cookie)
+{
+	struct otx2_tc_flow *tmp;
+
+	list_for_each_entry(tmp, &flow_cfg->flow_list_tc, list) {
+		if (tmp->cookie == cookie)
+			return tmp;
+	}
+
+	return NULL;
+}
+
+static struct otx2_tc_flow *otx2_tc_get_entry_by_index(struct otx2_flow_config *flow_cfg,
+						       int index)
 {
+	struct otx2_tc_flow *tmp;
+	int i = 0;
+
+	list_for_each_entry(tmp, &flow_cfg->flow_list_tc, list) {
+		if (i == index)
+			return tmp;
+		i++;
+	}
+
+	return NULL;
+}
+
+static void otx2_tc_del_from_flow_list(struct otx2_flow_config *flow_cfg,
+				       struct otx2_tc_flow *node)
+{
+	struct list_head *pos, *n;
+	struct otx2_tc_flow *tmp;
+
+	list_for_each_safe(pos, n, &flow_cfg->flow_list_tc) {
+		tmp = list_entry(pos, struct otx2_tc_flow, list);
+		if (node == tmp) {
+			list_del(&node->list);
+			return;
+		}
+	}
+}
+
+static int otx2_tc_add_to_flow_list(struct otx2_flow_config *flow_cfg,
+				    struct otx2_tc_flow *node)
+{
+	struct list_head *pos, *n;
+	struct otx2_tc_flow *tmp;
+	int index = 0;
+
+	/* If the flow list is empty then add the new node */
+	if (list_empty(&flow_cfg->flow_list_tc)) {
+		list_add(&node->list, &flow_cfg->flow_list_tc);
+		return index;
+	}
+
+	list_for_each_safe(pos, n, &flow_cfg->flow_list_tc) {
+		tmp = list_entry(pos, struct otx2_tc_flow, list);
+		if (node->prio < tmp->prio)
+			break;
+		index++;
+	}
+
+	list_add(&node->list, pos->prev);
+	return index;
+}
+
+static int otx2_add_mcam_flow_entry(struct otx2_nic *nic, struct npc_install_flow_req *req)
+{
+	struct npc_install_flow_req *tmp_req;
+	int err;
+
+	mutex_lock(&nic->mbox.lock);
+	tmp_req = otx2_mbox_alloc_msg_npc_install_flow(&nic->mbox);
+	if (!tmp_req) {
+		mutex_unlock(&nic->mbox.lock);
+		return -ENOMEM;
+	}
+
+	memcpy(tmp_req, req, sizeof(struct npc_install_flow_req));
+	/* Send message to AF */
+	err = otx2_sync_mbox_msg(&nic->mbox);
+	if (err) {
+		netdev_err(nic->netdev, "Failed to install MCAM flow entry %d\n",
+			   req->entry);
+		mutex_unlock(&nic->mbox.lock);
+		return -EFAULT;
+	}
+
+	mutex_unlock(&nic->mbox.lock);
+	return 0;
+}
+
+static int otx2_del_mcam_flow_entry(struct otx2_nic *nic, u16 entry, u16 *cntr_val)
+{
+	struct npc_delete_flow_rsp *rsp;
 	struct npc_delete_flow_req *req;
 	int err;
 
@@ -729,22 +816,113 @@ static int otx2_del_mcam_flow_entry(struct otx2_nic *nic, u16 entry)
 		mutex_unlock(&nic->mbox.lock);
 		return -EFAULT;
 	}
+
+	if (cntr_val) {
+		rsp = (struct npc_delete_flow_rsp *)otx2_mbox_get_rsp(&nic->mbox.mbox,
+								      0, &req->hdr);
+		if (IS_ERR(rsp)) {
+			netdev_err(nic->netdev, "Failed to get MCAM delete response for entry %d\n",
+				   entry);
+			mutex_unlock(&nic->mbox.lock);
+			return -EFAULT;
+		}
+
+		*cntr_val = rsp->cntr_val;
+	}
+
 	mutex_unlock(&nic->mbox.lock);
+	return 0;
+}
+
+static int otx2_tc_update_mcam_table_del_req(struct otx2_nic *nic,
+					     struct otx2_flow_config *flow_cfg,
+					     struct otx2_tc_flow *node)
+{
+	struct list_head *pos, *n;
+	struct otx2_tc_flow *tmp;
+	int i = 0, index = 0;
+	u16 cntr_val;
+
+	/* Find and delete the entry from the list and re-install
+	 * all the entries from beginning to the index of the
+	 * deleted entry to higher mcam indexes.
+	 */
+	list_for_each_safe(pos, n, &flow_cfg->flow_list_tc) {
+		tmp = list_entry(pos, struct otx2_tc_flow, list);
+		if (node == tmp) {
+			list_del(&tmp->list);
+			break;
+		}
+
+		otx2_del_mcam_flow_entry(nic, tmp->entry, &cntr_val);
+		tmp->entry++;
+		tmp->req.entry = tmp->entry;
+		tmp->req.cntr_val = cntr_val;
+		index++;
+	}
+
+	list_for_each_safe(pos, n, &flow_cfg->flow_list_tc) {
+		if (i == index)
+			break;
+
+		tmp = list_entry(pos, struct otx2_tc_flow, list);
+		otx2_add_mcam_flow_entry(nic, &tmp->req);
+		i++;
+	}
 
 	return 0;
 }
 
+static int otx2_tc_update_mcam_table_add_req(struct otx2_nic *nic,
+					     struct otx2_flow_config *flow_cfg,
+					     struct otx2_tc_flow *node)
+{
+	int mcam_idx = flow_cfg->max_flows - flow_cfg->nr_flows - 1;
+	struct otx2_tc_flow *tmp;
+	int list_idx, i;
+	u16 cntr_val;
+
+	/* Find the index of the entry(list_idx) whose priority
+	 * is greater than the new entry and re-install all
+	 * the entries from beginning to list_idx to higher
+	 * mcam indexes.
+	 */
+	list_idx = otx2_tc_add_to_flow_list(flow_cfg, node);
+	for (i = 0; i < list_idx; i++) {
+		tmp = otx2_tc_get_entry_by_index(flow_cfg, i);
+		if (!tmp)
+			return -ENOMEM;
+
+		otx2_del_mcam_flow_entry(nic, tmp->entry, &cntr_val);
+		tmp->entry = flow_cfg->flow_ent[mcam_idx];
+		tmp->req.entry = tmp->entry;
+		tmp->req.cntr_val = cntr_val;
+		otx2_add_mcam_flow_entry(nic, &tmp->req);
+		mcam_idx++;
+	}
+
+	return mcam_idx;
+}
+
+static int otx2_tc_update_mcam_table(struct otx2_nic *nic,
+				     struct otx2_flow_config *flow_cfg,
+				     struct otx2_tc_flow *node,
+				     bool add_req)
+{
+	if (add_req)
+		return otx2_tc_update_mcam_table_add_req(nic, flow_cfg, node);
+
+	return otx2_tc_update_mcam_table_del_req(nic, flow_cfg, node);
+}
+
 static int otx2_tc_del_flow(struct otx2_nic *nic,
 			    struct flow_cls_offload *tc_flow_cmd)
 {
 	struct otx2_flow_config *flow_cfg = nic->flow_cfg;
-	struct otx2_tc_info *tc_info = &nic->tc_info;
 	struct otx2_tc_flow *flow_node;
 	int err;
 
-	flow_node = rhashtable_lookup_fast(&tc_info->flow_table,
-					   &tc_flow_cmd->cookie,
-					   tc_info->flow_ht_params);
+	flow_node = otx2_tc_get_entry_by_cookie(flow_cfg, tc_flow_cmd->cookie);
 	if (!flow_node) {
 		netdev_err(nic->netdev, "tc flow not found for cookie 0x%lx\n",
 			   tc_flow_cmd->cookie);
@@ -772,16 +950,10 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 		mutex_unlock(&nic->mbox.lock);
 	}
 
-	otx2_del_mcam_flow_entry(nic, flow_node->entry);
-
-	WARN_ON(rhashtable_remove_fast(&nic->tc_info.flow_table,
-				       &flow_node->node,
-				       nic->tc_info.flow_ht_params));
+	otx2_del_mcam_flow_entry(nic, flow_node->entry, NULL);
+	otx2_tc_update_mcam_table(nic, flow_cfg, flow_node, false);
 	kfree_rcu(flow_node, rcu);
-
-	clear_bit(flow_node->bitpos, tc_info->tc_entries_bitmap);
 	flow_cfg->nr_flows--;
-
 	return 0;
 }
 
@@ -790,15 +962,14 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 {
 	struct netlink_ext_ack *extack = tc_flow_cmd->common.extack;
 	struct otx2_flow_config *flow_cfg = nic->flow_cfg;
-	struct otx2_tc_info *tc_info = &nic->tc_info;
 	struct otx2_tc_flow *new_node, *old_node;
 	struct npc_install_flow_req *req, dummy;
-	int rc, err;
+	int rc, err, mcam_idx;
 
 	if (!(nic->flags & OTX2_FLAG_TC_FLOWER_SUPPORT))
 		return -ENOMEM;
 
-	if (bitmap_full(tc_info->tc_entries_bitmap, flow_cfg->max_flows)) {
+	if (flow_cfg->nr_flows == flow_cfg->max_flows) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Free MCAM entry not available to add the flow");
 		return -ENOMEM;
@@ -810,6 +981,7 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 		return -ENOMEM;
 	spin_lock_init(&new_node->lock);
 	new_node->cookie = tc_flow_cmd->cookie;
+	new_node->prio = tc_flow_cmd->common.prio;
 
 	memset(&dummy, 0, sizeof(struct npc_install_flow_req));
 
@@ -820,12 +992,11 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	}
 
 	/* If a flow exists with the same cookie, delete it */
-	old_node = rhashtable_lookup_fast(&tc_info->flow_table,
-					  &tc_flow_cmd->cookie,
-					  tc_info->flow_ht_params);
+	old_node = otx2_tc_get_entry_by_cookie(flow_cfg, tc_flow_cmd->cookie);
 	if (old_node)
 		otx2_tc_del_flow(nic, tc_flow_cmd);
 
+	mcam_idx = otx2_tc_update_mcam_table(nic, flow_cfg, new_node, true);
 	mutex_lock(&nic->mbox.lock);
 	req = otx2_mbox_alloc_msg_npc_install_flow(&nic->mbox);
 	if (!req) {
@@ -836,11 +1007,8 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 
 	memcpy(&dummy.hdr, &req->hdr, sizeof(struct mbox_msghdr));
 	memcpy(req, &dummy, sizeof(struct npc_install_flow_req));
-
-	new_node->bitpos = find_first_zero_bit(tc_info->tc_entries_bitmap,
-					       flow_cfg->max_flows);
 	req->channel = nic->hw.rx_chan_base;
-	req->entry = flow_cfg->flow_ent[flow_cfg->max_flows - new_node->bitpos - 1];
+	req->entry = flow_cfg->flow_ent[mcam_idx];
 	req->intf = NIX_INTF_RX;
 	req->set_cntr = 1;
 	new_node->entry = req->entry;
@@ -850,26 +1018,18 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	if (rc) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed to install MCAM flow entry");
 		mutex_unlock(&nic->mbox.lock);
-		kfree_rcu(new_node, rcu);
 		goto free_leaf;
 	}
-	mutex_unlock(&nic->mbox.lock);
 
-	/* add new flow to flow-table */
-	rc = rhashtable_insert_fast(&nic->tc_info.flow_table, &new_node->node,
-				    nic->tc_info.flow_ht_params);
-	if (rc) {
-		otx2_del_mcam_flow_entry(nic, req->entry);
-		kfree_rcu(new_node, rcu);
-		goto free_leaf;
-	}
+	mutex_unlock(&nic->mbox.lock);
+	memcpy(&new_node->req, req, sizeof(struct npc_install_flow_req));
 
-	set_bit(new_node->bitpos, tc_info->tc_entries_bitmap);
 	flow_cfg->nr_flows++;
-
 	return 0;
 
 free_leaf:
+	otx2_tc_del_from_flow_list(flow_cfg, new_node);
+	kfree_rcu(new_node, rcu);
 	if (new_node->is_act_police) {
 		mutex_lock(&nic->mbox.lock);
 
@@ -896,16 +1056,13 @@ free_leaf:
 static int otx2_tc_get_flow_stats(struct otx2_nic *nic,
 				  struct flow_cls_offload *tc_flow_cmd)
 {
-	struct otx2_tc_info *tc_info = &nic->tc_info;
 	struct npc_mcam_get_stats_req *req;
 	struct npc_mcam_get_stats_rsp *rsp;
 	struct otx2_tc_flow_stats *stats;
 	struct otx2_tc_flow *flow_node;
 	int err;
 
-	flow_node = rhashtable_lookup_fast(&tc_info->flow_table,
-					   &tc_flow_cmd->cookie,
-					   tc_info->flow_ht_params);
+	flow_node = otx2_tc_get_entry_by_cookie(nic->flow_cfg, tc_flow_cmd->cookie);
 	if (!flow_node) {
 		netdev_info(nic->netdev, "tc flow not found for cookie %lx",
 			    tc_flow_cmd->cookie);
@@ -1053,12 +1210,20 @@ static int otx2_setup_tc_block_ingress_cb(enum tc_setup_type type,
 					  void *type_data, void *cb_priv)
 {
 	struct otx2_nic *nic = cb_priv;
+	bool ntuple;
 
 	if (!tc_cls_can_offload_and_chain0(nic->netdev, type_data))
 		return -EOPNOTSUPP;
 
+	ntuple = nic->netdev->features & NETIF_F_NTUPLE;
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
+		if (ntuple) {
+			netdev_warn(nic->netdev,
+				    "Can't install TC flower offload rule when NTUPLE is active");
+			return -EOPNOTSUPP;
+		}
+
 		return otx2_setup_tc_cls_flower(nic, type_data);
 	case TC_SETUP_CLSMATCHALL:
 		return otx2_setup_tc_ingress_matchall(nic, type_data);
@@ -1143,18 +1308,8 @@ int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 }
 EXPORT_SYMBOL(otx2_setup_tc);
 
-static const struct rhashtable_params tc_flow_ht_params = {
-	.head_offset = offsetof(struct otx2_tc_flow, node),
-	.key_offset = offsetof(struct otx2_tc_flow, cookie),
-	.key_len = sizeof(((struct otx2_tc_flow *)0)->cookie),
-	.automatic_shrinking = true,
-};
-
 int otx2_init_tc(struct otx2_nic *nic)
 {
-	struct otx2_tc_info *tc = &nic->tc_info;
-	int err;
-
 	/* Exclude receive queue 0 being used for police action */
 	set_bit(0, &nic->rq_bmap);
 
@@ -1164,25 +1319,12 @@ int otx2_init_tc(struct otx2_nic *nic)
 		return -EINVAL;
 	}
 
-	err = otx2_tc_alloc_ent_bitmap(nic);
-	if (err)
-		return err;
-
-	tc->flow_ht_params = tc_flow_ht_params;
-	err = rhashtable_init(&tc->flow_table, &tc->flow_ht_params);
-	if (err) {
-		kfree(tc->tc_entries_bitmap);
-		tc->tc_entries_bitmap = NULL;
-	}
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL(otx2_init_tc);
 
 void otx2_shutdown_tc(struct otx2_nic *nic)
 {
-	struct otx2_tc_info *tc = &nic->tc_info;
-
-	kfree(tc->tc_entries_bitmap);
-	rhashtable_destroy(&tc->flow_table);
+	otx2_destroy_tc_flow_list(nic);
 }
 EXPORT_SYMBOL(otx2_shutdown_tc);
-- 
GitLab


From 76a4cb755cf911ad5acdb82f7228a9e22addf52b Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sat, 22 Jul 2023 21:32:49 +0100
Subject: [PATCH 0352/1806] net: ethernet: mtk_eth_soc: remove incorrect PLL
 configuration

MT7623 GMAC0 attempts to configure the system clocking according to the
required speed in the .mac_config callback for non-SGMII, non-baseX and
non-TRGMII modes.

state->speed setting has never been reliable in the .mac_config
callback - there are cases where this is not the link speed,
particularly via ethtool paths, so this has always been unreliable (as
detailed in phylink's documentation.)

There is the additional issue that mtk_gmac0_rgmii_adjust() will only
be called if state->interface changes, which means it only configures
the system clocking on the very first .mac_config call, which will be
made when the network device is first brought up before any link is
established.

Essentially, this code is incredibly buggy, and probably never worked.

Moreover, checking the in-kernel DT files, it seems no platform makes
use of this code path.

Therefore, let's remove it, and disable interface modes for port 0 that
are not SGMII, 1000base-X, 2500base-X or TRGMII on the MT7623.

Reviewed-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Frank Wunderlich <frank-w@public-files.de>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 59 ++++++---------------
 drivers/net/ethernet/mediatek/mtk_eth_soc.h |  1 +
 2 files changed, 17 insertions(+), 43 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 18a8aca7944db..fe8b7e38decc3 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -385,10 +385,8 @@ static int mt7621_gmac0_rgmii_adjust(struct mtk_eth *eth,
 }
 
 static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth,
-				   phy_interface_t interface, int speed)
+				   phy_interface_t interface)
 {
-	unsigned long rate;
-	u32 tck, rck, intf;
 	int ret;
 
 	if (interface == PHY_INTERFACE_MODE_TRGMII) {
@@ -399,30 +397,7 @@ static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth,
 		return;
 	}
 
-	if (speed == SPEED_1000) {
-		intf = INTF_MODE_RGMII_1000;
-		rate = 250000000;
-		rck = RCK_CTRL_RGMII_1000;
-		tck = TCK_CTRL_RGMII_1000;
-	} else {
-		intf = INTF_MODE_RGMII_10_100;
-		rate = 500000000;
-		rck = RCK_CTRL_RGMII_10_100;
-		tck = TCK_CTRL_RGMII_10_100;
-	}
-
-	mtk_w32(eth, intf, INTF_MODE);
-
-	regmap_update_bits(eth->ethsys, ETHSYS_CLKCFG0,
-			   ETHSYS_TRGMII_CLK_SEL362_5,
-			   ETHSYS_TRGMII_CLK_SEL362_5);
-
-	ret = clk_set_rate(eth->clks[MTK_CLK_TRGPLL], rate);
-	if (ret)
-		dev_err(eth->dev, "Failed to set trgmii pll: %d\n", ret);
-
-	mtk_w32(eth, rck, TRGMII_RCK_CTRL);
-	mtk_w32(eth, tck, TRGMII_TCK_CTRL);
+	dev_err(eth->dev, "Missing PLL configuration, ethernet may not work\n");
 }
 
 static struct phylink_pcs *mtk_mac_select_pcs(struct phylink_config *config,
@@ -498,17 +473,8 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 							      state->interface))
 					goto err_phy;
 			} else {
-				/* FIXME: this is incorrect. Not only does it
-				 * use state->speed (which is not guaranteed
-				 * to be correct) but it also makes use of it
-				 * in a code path that will only be reachable
-				 * when the PHY interface mode changes, not
-				 * when the speed changes. Consequently, RGMII
-				 * is probably broken.
-				 */
 				mtk_gmac0_rgmii_adjust(mac->hw,
-						       state->interface,
-						       state->speed);
+						       state->interface);
 
 				/* mt7623_pad_clk_setup */
 				for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
@@ -4366,13 +4332,19 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD;
 
-	__set_bit(PHY_INTERFACE_MODE_MII,
-		  mac->phylink_config.supported_interfaces);
-	__set_bit(PHY_INTERFACE_MODE_GMII,
-		  mac->phylink_config.supported_interfaces);
+	/* MT7623 gmac0 is now missing its speed-specific PLL configuration
+	 * in its .mac_config method (since state->speed is not valid there.
+	 * Disable support for MII, GMII and RGMII.
+	 */
+	if (!mac->hw->soc->disable_pll_modes || mac->id != 0) {
+		__set_bit(PHY_INTERFACE_MODE_MII,
+			  mac->phylink_config.supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_GMII,
+			  mac->phylink_config.supported_interfaces);
 
-	if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_RGMII))
-		phy_interface_set_rgmii(mac->phylink_config.supported_interfaces);
+		if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_RGMII))
+			phy_interface_set_rgmii(mac->phylink_config.supported_interfaces);
+	}
 
 	if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_TRGMII) && !mac->id)
 		__set_bit(PHY_INTERFACE_MODE_TRGMII,
@@ -4845,6 +4817,7 @@ static const struct mtk_soc_data mt7623_data = {
 	.offload_version = 1,
 	.hash_offset = 2,
 	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
+	.disable_pll_modes = true,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma),
 		.rxd_size = sizeof(struct mtk_rx_dma),
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 707445f6bcb1b..28adda0c90c0d 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -1030,6 +1030,7 @@ struct mtk_soc_data {
 	u16		foe_entry_size;
 	netdev_features_t hw_features;
 	bool		has_accounting;
+	bool		disable_pll_modes;
 	struct {
 		u32	txd_size;
 		u32	rxd_size;
-- 
GitLab


From 28e1737d2544536c23fc71d3a7f24ce8c9f08eb1 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sat, 22 Jul 2023 21:32:54 +0100
Subject: [PATCH 0353/1806] net: ethernet: mtk_eth_soc: remove
 mac_pcs_get_state and modernise

Remove the .mac_pcs_get_state function, since as far as I can tell is
never called - no DT appears to specify an in-band-status management
nor SFP support for this driver.

Removal of this, along with the previous patch to remove the incorrect
clocking configuration, means that the driver becomes non-legacy, so
we can remove the "legacy_pre_march2020" status from this driver.

Reviewed-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Frank Wunderlich <frank-w@public-files.de>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 35 ---------------------
 1 file changed, 35 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index fe8b7e38decc3..7490d48000c26 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -568,38 +568,6 @@ static int mtk_mac_finish(struct phylink_config *config, unsigned int mode,
 	return 0;
 }
 
-static void mtk_mac_pcs_get_state(struct phylink_config *config,
-				  struct phylink_link_state *state)
-{
-	struct mtk_mac *mac = container_of(config, struct mtk_mac,
-					   phylink_config);
-	u32 pmsr = mtk_r32(mac->hw, MTK_MAC_MSR(mac->id));
-
-	state->link = (pmsr & MAC_MSR_LINK);
-	state->duplex = (pmsr & MAC_MSR_DPX) >> 1;
-
-	switch (pmsr & (MAC_MSR_SPEED_1000 | MAC_MSR_SPEED_100)) {
-	case 0:
-		state->speed = SPEED_10;
-		break;
-	case MAC_MSR_SPEED_100:
-		state->speed = SPEED_100;
-		break;
-	case MAC_MSR_SPEED_1000:
-		state->speed = SPEED_1000;
-		break;
-	default:
-		state->speed = SPEED_UNKNOWN;
-		break;
-	}
-
-	state->pause &= (MLO_PAUSE_RX | MLO_PAUSE_TX);
-	if (pmsr & MAC_MSR_RX_FC)
-		state->pause |= MLO_PAUSE_RX;
-	if (pmsr & MAC_MSR_TX_FC)
-		state->pause |= MLO_PAUSE_TX;
-}
-
 static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode,
 			      phy_interface_t interface)
 {
@@ -722,7 +690,6 @@ static void mtk_mac_link_up(struct phylink_config *config,
 
 static const struct phylink_mac_ops mtk_phylink_ops = {
 	.mac_select_pcs = mtk_mac_select_pcs,
-	.mac_pcs_get_state = mtk_mac_pcs_get_state,
 	.mac_config = mtk_mac_config,
 	.mac_finish = mtk_mac_finish,
 	.mac_link_down = mtk_mac_link_down,
@@ -4327,8 +4294,6 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 
 	mac->phylink_config.dev = &eth->netdev[id]->dev;
 	mac->phylink_config.type = PHYLINK_NETDEV;
-	/* This driver makes use of state->speed in mac_config */
-	mac->phylink_config.legacy_pre_march2020 = true;
 	mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD;
 
-- 
GitLab


From 4d72c3bb60dd9d5ea180f157bac72b4458112282 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sat, 22 Jul 2023 21:32:59 +0100
Subject: [PATCH 0354/1806] net: phylink: strip out pre-March 2020 legacy code

Strip out all the pre-March 2020 legacy code from phylink now that the
last user of it is gone.

Reviewed-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Frank Wunderlich <frank-w@public-files.de>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phylink.c | 25 ++++------------------
 include/linux/phylink.h   | 45 ++++++---------------------------------
 2 files changed, 10 insertions(+), 60 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index f07e496319b4a..df413fb15088d 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1198,13 +1198,6 @@ static int phylink_change_inband_advert(struct phylink *pl)
 	if (test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state))
 		return 0;
 
-	if (!pl->pcs && pl->config->legacy_pre_march2020) {
-		/* Legacy method */
-		phylink_mac_config(pl, &pl->link_config);
-		phylink_pcs_an_restart(pl);
-		return 0;
-	}
-
 	phylink_dbg(pl, "%s: mode=%s/%s adv=%*pb pause=%02x\n", __func__,
 		    phylink_an_mode_str(pl->cur_link_an_mode),
 		    phy_modes(pl->link_config.interface),
@@ -1257,9 +1250,6 @@ static void phylink_mac_pcs_get_state(struct phylink *pl,
 
 	if (pl->pcs)
 		pl->pcs->ops->pcs_get_state(pl->pcs, state);
-	else if (pl->mac_ops->mac_pcs_get_state &&
-		 pl->config->legacy_pre_march2020)
-		pl->mac_ops->mac_pcs_get_state(pl->config, state);
 	else
 		state->link = 0;
 }
@@ -1492,13 +1482,6 @@ static void phylink_resolve(struct work_struct *w)
 			}
 			phylink_major_config(pl, false, &link_state);
 			pl->link_config.interface = link_state.interface;
-		} else if (!pl->pcs && pl->config->legacy_pre_march2020) {
-			/* The interface remains unchanged, only the speed,
-			 * duplex or pause settings have changed. Call the
-			 * old mac_config() method to configure the MAC/PCS
-			 * only if we do not have a legacy MAC driver.
-			 */
-			phylink_mac_config(pl, &link_state);
 		}
 	}
 
@@ -3513,7 +3496,7 @@ static void phylink_decode_usgmii_word(struct phylink_link_state *state,
  *
  * Parse the Clause 37 or Cisco SGMII link partner negotiation word into
  * the phylink @state structure. This is suitable to be used for implementing
- * the mac_pcs_get_state() member of the struct phylink_mac_ops structure if
+ * the pcs_get_state() member of the struct phylink_pcs_ops structure if
  * accessing @bmsr and @lpa cannot be done with MDIO directly.
  */
 void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state,
@@ -3563,7 +3546,7 @@ EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_decode_state);
  * Read the MAC PCS state from the MII device configured in @config and
  * parse the Clause 37 or Cisco SGMII link partner negotiation word into
  * the phylink @state structure. This is suitable to be directly plugged
- * into the mac_pcs_get_state() member of the struct phylink_mac_ops
+ * into the pcs_get_state() member of the struct phylink_pcs_ops
  * structure.
  */
 void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs,
@@ -3674,8 +3657,8 @@ EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_config);
  * clause 37 negotiation.
  *
  * Restart the clause 37 negotiation with the link partner. This is
- * suitable to be directly plugged into the mac_pcs_get_state() member
- * of the struct phylink_mac_ops structure.
+ * suitable to be directly plugged into the pcs_get_state() member
+ * of the struct phylink_pcs_ops structure.
  */
 void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs)
 {
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 9e861c8316d0c..789c516c6b4a8 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -201,8 +201,6 @@ enum phylink_op_type {
  * struct phylink_config - PHYLINK configuration structure
  * @dev: a pointer to a struct device associated with the MAC
  * @type: operation type of PHYLINK instance
- * @legacy_pre_march2020: driver has not been updated for March 2020 updates
- *	(See commit 7cceb599d15d ("net: phylink: avoid mac_config calls")
  * @poll_fixed_state: if true, starts link_poll,
  *		      if MAC link is at %MLO_AN_FIXED mode.
  * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM.
@@ -216,7 +214,6 @@ enum phylink_op_type {
 struct phylink_config {
 	struct device *dev;
 	enum phylink_op_type type;
-	bool legacy_pre_march2020;
 	bool poll_fixed_state;
 	bool mac_managed_pm;
 	bool ovr_an_inband;
@@ -230,7 +227,6 @@ struct phylink_config {
  * struct phylink_mac_ops - MAC operations structure.
  * @validate: Validate and update the link configuration.
  * @mac_select_pcs: Select a PCS for the interface mode.
- * @mac_pcs_get_state: Read the current link state from the hardware.
  * @mac_prepare: prepare for a major reconfiguration of the interface.
  * @mac_config: configure the MAC for the selected mode and state.
  * @mac_finish: finish a major reconfiguration of the interface.
@@ -245,8 +241,6 @@ struct phylink_mac_ops {
 			 struct phylink_link_state *state);
 	struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config,
 					      phy_interface_t interface);
-	void (*mac_pcs_get_state)(struct phylink_config *config,
-				  struct phylink_link_state *state);
 	int (*mac_prepare)(struct phylink_config *config, unsigned int mode,
 			   phy_interface_t iface);
 	void (*mac_config)(struct phylink_config *config, unsigned int mode,
@@ -312,25 +306,6 @@ void validate(struct phylink_config *config, unsigned long *supported,
 struct phylink_pcs *mac_select_pcs(struct phylink_config *config,
 				   phy_interface_t interface);
 
-/**
- * mac_pcs_get_state() - Read the current inband link state from the hardware
- * @config: a pointer to a &struct phylink_config.
- * @state: a pointer to a &struct phylink_link_state.
- *
- * Read the current inband link state from the MAC PCS, reporting the
- * current speed in @state->speed, duplex mode in @state->duplex, pause
- * mode in @state->pause using the %MLO_PAUSE_RX and %MLO_PAUSE_TX bits,
- * negotiation completion state in @state->an_complete, and link up state
- * in @state->link. If possible, @state->lp_advertising should also be
- * populated.
- *
- * Note: This is a legacy method. This function will not be called unless
- * legacy_pre_march2020 is set in &struct phylink_config and there is no
- * PCS attached.
- */
-void mac_pcs_get_state(struct phylink_config *config,
-		       struct phylink_link_state *state);
-
 /**
  * mac_prepare() - prepare to change the PHY interface mode
  * @config: a pointer to a &struct phylink_config.
@@ -367,17 +342,9 @@ int mac_prepare(struct phylink_config *config, unsigned int mode,
  * guaranteed to be correct, and so any mac_config() implementation must
  * never reference these fields.
  *
- * Note: For legacy March 2020 drivers (drivers with legacy_pre_march2020 set
- * in their &phylnk_config and which don't have a PCS), this function will be
- * called on each link up event, and to also change the in-band advert. For
- * non-legacy drivers, it will only be called to reconfigure the MAC for a
- * "major" change in e.g. interface mode. It will not be called for changes
- * in speed, duplex or pause modes or to change the in-band advertisement.
- * In any case, it is strongly preferred that speed, duplex and pause settings
- * are handled in the mac_link_up() method and not in this method.
- *
- * (this requires a rewrite - please refer to mac_link_up() for situations
- *  where the PCS and MAC are not tightly integrated.)
+ * This will only be called to reconfigure the MAC for a "major" change in
+ * e.g. interface mode. It will not be called for changes in speed, duplex
+ * or pause modes or to change the in-band advertisement.
  *
  * In all negotiation modes, as defined by @mode, @state->pause indicates the
  * pause settings which should be applied as follows. If %MLO_PAUSE_AN is not
@@ -409,7 +376,7 @@ int mac_prepare(struct phylink_config *config, unsigned int mode,
  *   1000base-X or Cisco SGMII mode depending on the @state->interface
  *   mode). In both cases, link state management (whether the link
  *   is up or not) is performed by the MAC, and reported via the
- *   mac_pcs_get_state() callback. Changes in link state must be made
+ *   pcs_get_state() callback. Changes in link state must be made
  *   by calling phylink_mac_change().
  *
  *   Interface mode specific details are mentioned below.
@@ -601,8 +568,8 @@ void pcs_disable(struct phylink_pcs *pcs);
  * in @state->link. If possible, @state->lp_advertising should also be
  * populated.
  *
- * When present, this overrides mac_pcs_get_state() in &struct
- * phylink_mac_ops.
+ * When present, this overrides pcs_get_state() in &struct
+ * phylink_pcs_ops.
  */
 void pcs_get_state(struct phylink_pcs *pcs,
 		   struct phylink_link_state *state);
-- 
GitLab


From c5714f68a76bcad3d2dbaafc5a7e98096f3b4c75 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sat, 22 Jul 2023 21:33:05 +0100
Subject: [PATCH 0355/1806] net: phylink: explicitly invalidate link_state
 members in mac_config

Explicitly invalidate the phylink_link_state structure members in
mac_config that do not contain reliable information for this function,
thereby preventing their future incorrect use.

Reviewed-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Frank Wunderlich <frank-w@public-files.de>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phylink.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index df413fb15088d..4f1c8bb199e9f 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1066,17 +1066,24 @@ static void phylink_pcs_poll_start(struct phylink *pl)
 static void phylink_mac_config(struct phylink *pl,
 			       const struct phylink_link_state *state)
 {
+	struct phylink_link_state st = *state;
+
+	/* Stop drivers incorrectly using these */
+	linkmode_zero(st.lp_advertising);
+	st.speed = SPEED_UNKNOWN;
+	st.duplex = DUPLEX_UNKNOWN;
+	st.an_complete = false;
+	st.link = false;
+
 	phylink_dbg(pl,
-		    "%s: mode=%s/%s/%s/%s/%s adv=%*pb pause=%02x link=%u\n",
+		    "%s: mode=%s/%s/%s adv=%*pb pause=%02x\n",
 		    __func__, phylink_an_mode_str(pl->cur_link_an_mode),
-		    phy_modes(state->interface),
-		    phy_speed_to_str(state->speed),
-		    phy_duplex_to_str(state->duplex),
-		    phy_rate_matching_to_str(state->rate_matching),
-		    __ETHTOOL_LINK_MODE_MASK_NBITS, state->advertising,
-		    state->pause, state->link);
-
-	pl->mac_ops->mac_config(pl->config, pl->cur_link_an_mode, state);
+		    phy_modes(st.interface),
+		    phy_rate_matching_to_str(st.rate_matching),
+		    __ETHTOOL_LINK_MODE_MASK_NBITS, st.advertising,
+		    st.pause);
+
+	pl->mac_ops->mac_config(pl->config, pl->cur_link_an_mode, &st);
 }
 
 static void phylink_pcs_an_restart(struct phylink *pl)
-- 
GitLab


From 57266281271add0132bea0b83ef0d6f32704c402 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 19 Jul 2023 12:26:53 +0300
Subject: [PATCH 0356/1806] net/mlx5: Add relevant capabilities bits to support
 NAT-T

Provide an ability to check if flow steering supports UDP
encapsulation and decapsulation of IPsec ESP packets.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/mlx5/mlx5_ifc.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 33344a71c3e36..b3ad6b9852ecb 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -464,10 +464,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 
 	u8         reformat_add_esp_trasport[0x1];
 	u8         reformat_l2_to_l3_esp_tunnel[0x1];
-	u8         reserved_at_42[0x1];
+	u8         reformat_add_esp_transport_over_udp[0x1];
 	u8         reformat_del_esp_trasport[0x1];
 	u8         reformat_l3_esp_tunnel_to_l2[0x1];
-	u8         reserved_at_45[0x1];
+	u8         reformat_del_esp_transport_over_udp[0x1];
 	u8         execute_aso[0x1];
 	u8         reserved_at_47[0x19];
 
@@ -6665,9 +6665,12 @@ enum mlx5_reformat_ctx_type {
 	MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4,
 	MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4 = 0x5,
 	MLX5_REFORMAT_TYPE_L2_TO_L3_ESP_TUNNEL = 0x6,
+	MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV4 = 0x7,
 	MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT = 0x8,
 	MLX5_REFORMAT_TYPE_L3_ESP_TUNNEL_TO_L2 = 0x9,
+	MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT_OVER_UDP = 0xa,
 	MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6 = 0xb,
+	MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV6 = 0xc,
 	MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf,
 	MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10,
 	MLX5_REFORMAT_TYPE_ADD_MACSEC = 0x11,
-- 
GitLab


From 4acea83a849a04c4b88bf2ee7bcecfcc2f502a24 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 19 Jul 2023 12:26:54 +0300
Subject: [PATCH 0357/1806] net/mlx5e: Check for IPsec NAT-T support

Set relevant IPsec capability to indicate if flow steering supports UDP
encapsulation and decapsulation of IPsec ESP packets.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h    | 1 +
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c    | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 4e98871715086..b382b0cad7f64 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -110,6 +110,7 @@ enum mlx5_ipsec_cap {
 	MLX5_IPSEC_CAP_ROCE             = 1 << 3,
 	MLX5_IPSEC_CAP_PRIO             = 1 << 4,
 	MLX5_IPSEC_CAP_TUNNEL           = 1 << 5,
+	MLX5_IPSEC_CAP_ESPINUDP         = 1 << 6,
 };
 
 struct mlx5e_priv;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index a3554bde3e075..5ff06263c5bd2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -54,6 +54,12 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
 					      reformat_l3_esp_tunnel_to_l2))
 			caps |= MLX5_IPSEC_CAP_TUNNEL;
+
+		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,
+					      reformat_add_esp_transport_over_udp) &&
+		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
+					      reformat_del_esp_transport_over_udp))
+			caps |= MLX5_IPSEC_CAP_ESPINUDP;
 	}
 
 	if (mlx5_get_roce_state(mdev) &&
-- 
GitLab


From d65954934937f1509501ffdd7e0201b37638d2e1 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 19 Jul 2023 12:26:55 +0300
Subject: [PATCH 0358/1806] net/mlx5e: Support IPsec NAT-T functionality

Extend mlx5 IPsec packet offload to support UDP encapsulation
of IPsec ESP packets.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec.c       | 27 +++++++-
 .../mellanox/mlx5/core/en_accel/ipsec.h       | 11 +++-
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 61 ++++++++++++++-----
 3 files changed, 81 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 891d39b4bfd4f..658b7d8d50c77 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -354,6 +354,12 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 
 	mlx5e_ipsec_init_limits(sa_entry, attrs);
 	mlx5e_ipsec_init_macs(sa_entry, attrs);
+
+	if (x->encap) {
+		attrs->encap = true;
+		attrs->sport = x->encap->encap_sport;
+		attrs->dport = x->encap->encap_dport;
+	}
 }
 
 static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev,
@@ -387,8 +393,25 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev,
 		return -EINVAL;
 	}
 	if (x->encap) {
-		NL_SET_ERR_MSG_MOD(extack, "Encapsulated xfrm state may not be offloaded");
-		return -EINVAL;
+		if (!(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ESPINUDP)) {
+			NL_SET_ERR_MSG_MOD(extack, "Encapsulation is not supported");
+			return -EINVAL;
+		}
+
+		if (x->encap->encap_type != UDP_ENCAP_ESPINUDP) {
+			NL_SET_ERR_MSG_MOD(extack, "Encapsulation other than UDP is not supported");
+			return -EINVAL;
+		}
+
+		if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) {
+			NL_SET_ERR_MSG_MOD(extack, "Encapsulation is supported in packet offload mode only");
+			return -EINVAL;
+		}
+
+		if (x->props.mode != XFRM_MODE_TRANSPORT) {
+			NL_SET_ERR_MSG_MOD(extack, "Encapsulation is supported in transport mode only");
+			return -EINVAL;
+		}
 	}
 	if (!x->aead) {
 		NL_SET_ERR_MSG_MOD(extack, "Cannot offload xfrm states without aead");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index b382b0cad7f64..7a70472636180 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -94,13 +94,20 @@ struct mlx5_accel_esp_xfrm_attrs {
 	u8 dir : 2;
 	u8 type : 2;
 	u8 drop : 1;
+	u8 encap : 1;
 	u8 family;
 	struct mlx5_replay_esn replay_esn;
 	u32 authsize;
 	u32 reqid;
 	struct mlx5_ipsec_lft lft;
-	u8 smac[ETH_ALEN];
-	u8 dmac[ETH_ALEN];
+	union {
+		u8 smac[ETH_ALEN];
+		__be16 sport;
+	};
+	union {
+		u8 dmac[ETH_ALEN];
+		__be16 dport;
+	};
 };
 
 enum mlx5_ipsec_cap {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index dbe87bf89c0dd..47baf983147f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -951,37 +951,70 @@ free_reformatbf:
 	return -EINVAL;
 }
 
+static int get_reformat_type(struct mlx5_accel_esp_xfrm_attrs *attrs)
+{
+	switch (attrs->dir) {
+	case XFRM_DEV_OFFLOAD_IN:
+		if (attrs->encap)
+			return MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT_OVER_UDP;
+		return MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT;
+	case XFRM_DEV_OFFLOAD_OUT:
+		if (attrs->family == AF_INET) {
+			if (attrs->encap)
+				return MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV4;
+			return MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4;
+		}
+
+		if (attrs->encap)
+			return MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV6;
+		return MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6;
+	default:
+		WARN_ON(true);
+	}
+
+	return -EINVAL;
+}
+
 static int
 setup_pkt_transport_reformat(struct mlx5_accel_esp_xfrm_attrs *attrs,
 			     struct mlx5_pkt_reformat_params *reformat_params)
 {
-	u8 *reformatbf;
+	struct udphdr *udphdr;
+	char *reformatbf;
+	size_t bfflen;
 	__be32 spi;
+	void *hdr;
+
+	reformat_params->type = get_reformat_type(attrs);
+	if (reformat_params->type < 0)
+		return reformat_params->type;
 
 	switch (attrs->dir) {
 	case XFRM_DEV_OFFLOAD_IN:
-		reformat_params->type = MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT;
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
-		if (attrs->family == AF_INET)
-			reformat_params->type =
-				MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4;
-		else
-			reformat_params->type =
-				MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6;
-
-		reformatbf = kzalloc(MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE,
-				     GFP_KERNEL);
+		bfflen = MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE;
+		if (attrs->encap)
+			bfflen += sizeof(*udphdr);
+
+		reformatbf = kzalloc(bfflen, GFP_KERNEL);
 		if (!reformatbf)
 			return -ENOMEM;
 
+		hdr = reformatbf;
+		if (attrs->encap) {
+			udphdr = (struct udphdr *)reformatbf;
+			udphdr->source = attrs->sport;
+			udphdr->dest = attrs->dport;
+			hdr += sizeof(*udphdr);
+		}
+
 		/* convert to network format */
 		spi = htonl(attrs->spi);
-		memcpy(reformatbf, &spi, sizeof(spi));
+		memcpy(hdr, &spi, sizeof(spi));
 
 		reformat_params->param_0 = attrs->authsize;
-		reformat_params->size =
-			MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE;
+		reformat_params->size = bfflen;
 		reformat_params->data = reformatbf;
 		break;
 	default:
-- 
GitLab


From 89edf40220be8e68922beb54a06fdfc66f743c39 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 19 Jul 2023 12:26:56 +0300
Subject: [PATCH 0359/1806] xfrm: Support UDP encapsulation in packet offload
 mode

Since mlx5 supports UDP encapsulation in packet offload, change the XFRM
core to allow users to configure it.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/xfrm/xfrm_device.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 533697e2488f2..3784534c91855 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -247,12 +247,6 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 		return -EINVAL;
 	}
 
-	/* We don't yet support UDP encapsulation and TFC padding. */
-	if (x->encap || x->tfcpad) {
-		NL_SET_ERR_MSG(extack, "Encapsulation and TFC padding can't be offloaded");
-		return -EINVAL;
-	}
-
 	if (xuo->flags &
 	    ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND | XFRM_OFFLOAD_PACKET)) {
 		NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request");
@@ -260,6 +254,13 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 	}
 
 	is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET;
+
+	/* We don't yet support UDP encapsulation and TFC padding. */
+	if ((!is_packet_offload && x->encap) || x->tfcpad) {
+		NL_SET_ERR_MSG(extack, "Encapsulation and TFC padding can't be offloaded");
+		return -EINVAL;
+	}
+
 	dev = dev_get_by_index(net, xuo->ifindex);
 	if (!dev) {
 		if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) {
-- 
GitLab


From 90f2ba4896e289ba7973a5349cbad4463c97e321 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Mon, 24 Jul 2023 13:11:07 +0300
Subject: [PATCH 0360/1806] wifi: ath9k: avoid using uninitialized array
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In 'ath_tx_count_frames()', 'ba' array may be used uninitialized, so
add 'memset()' call similar to one used in 'ath_tx_complete_aggr()'.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230620080855.396851-1-dmantipov@yandex.ru
---
 drivers/net/wireless/ath/ath9k/xmit.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index f6f2ab7a63ffc..8babaaacacf59 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -466,6 +466,8 @@ static void ath_tx_count_frames(struct ath_softc *sc, struct ath_buf *bf,
 	*nframes = 0;
 
 	isaggr = bf_isaggr(bf);
+	memset(ba, 0, WME_BA_BMP_SIZE >> 3);
+
 	if (isaggr) {
 		seq_st = ts->ts_seqnum;
 		memcpy(ba, &ts->ba_low, WME_BA_BMP_SIZE >> 3);
-- 
GitLab


From 810e41cebb6c6e394f2068f839e1a3fc745a5dcc Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Mon, 24 Jul 2023 13:11:07 +0300
Subject: [PATCH 0361/1806] wifi: ath9k: fix fortify warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When compiling with gcc 13.1 and CONFIG_FORTIFY_SOURCE=y,
I've noticed the following:

In function ‘fortify_memcpy_chk’,
    inlined from ‘ath_tx_complete_aggr’ at drivers/net/wireless/ath/ath9k/xmit.c:556:4,
    inlined from ‘ath_tx_process_buffer’ at drivers/net/wireless/ath/ath9k/xmit.c:773:3:
./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Wattribute-warning]
  529 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

In function ‘fortify_memcpy_chk’,
    inlined from ‘ath_tx_count_frames’ at drivers/net/wireless/ath/ath9k/xmit.c:473:3,
    inlined from ‘ath_tx_complete_aggr’ at drivers/net/wireless/ath/ath9k/xmit.c:572:2,
    inlined from ‘ath_tx_process_buffer’ at drivers/net/wireless/ath/ath9k/xmit.c:773:3:
./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Wattribute-warning]
  529 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

In both cases, the compiler complains on:

memcpy(ba, &ts->ba_low, WME_BA_BMP_SIZE >> 3);

which is the legal way to copy both 'ba_low' and following 'ba_high'
members of 'struct ath_tx_status' at once (that is, issue one 8-byte
'memcpy()' for two 4-byte fields). Since the fortification logic seems
interprets this trick as an attempt to overread 4-byte 'ba_low', silence
relevant warnings by using the convenient 'struct_group()' quirk.

Suggested-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230620080855.396851-2-dmantipov@yandex.ru
---
 drivers/net/wireless/ath/ath9k/mac.h  | 6 ++++--
 drivers/net/wireless/ath/ath9k/xmit.c | 4 ++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h
index af44b33814ddc..f03d792732da7 100644
--- a/drivers/net/wireless/ath/ath9k/mac.h
+++ b/drivers/net/wireless/ath/ath9k/mac.h
@@ -115,8 +115,10 @@ struct ath_tx_status {
 	u8 qid;
 	u16 desc_id;
 	u8 tid;
-	u32 ba_low;
-	u32 ba_high;
+	struct_group(ba,
+		u32 ba_low;
+		u32 ba_high;
+	);
 	u32 evm0;
 	u32 evm1;
 	u32 evm2;
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 8babaaacacf59..4e939dcac1c9d 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -470,7 +470,7 @@ static void ath_tx_count_frames(struct ath_softc *sc, struct ath_buf *bf,
 
 	if (isaggr) {
 		seq_st = ts->ts_seqnum;
-		memcpy(ba, &ts->ba_low, WME_BA_BMP_SIZE >> 3);
+		memcpy(ba, &ts->ba, WME_BA_BMP_SIZE >> 3);
 	}
 
 	while (bf) {
@@ -553,7 +553,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq,
 	if (isaggr && txok) {
 		if (ts->ts_flags & ATH9K_TX_BA) {
 			seq_st = ts->ts_seqnum;
-			memcpy(ba, &ts->ba_low, WME_BA_BMP_SIZE >> 3);
+			memcpy(ba, &ts->ba, WME_BA_BMP_SIZE >> 3);
 		} else {
 			/*
 			 * AR5416 can become deaf/mute when BA
-- 
GitLab


From f7eb8315b22a8f58365b8916446a11326e5a719b Mon Sep 17 00:00:00 2001
From: Minjie Du <duminjie@vivo.com>
Date: Mon, 24 Jul 2023 13:11:07 +0300
Subject: [PATCH 0362/1806] wifi: ath5k: remove phydir check from
 ath5k_debug_init_device()

'phydir' returned from debugfs_create_dir() is checked against NULL.
As the debugfs API returns an error pointer,
the returned value can never be NULL.

Therefore, as the documentation suggests that the check is unnecessary
and other debugfs calls have no operation in error cases,
it is advisable to completely eliminate the check.

Signed-off-by: Minjie Du <duminjie@vivo.com>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230714081619.2032-1-duminjie@vivo.com
---
 drivers/net/wireless/ath/ath5k/debug.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath5k/debug.c b/drivers/net/wireless/ath/ath5k/debug.c
index 4b41160e5d389..ec130510aeb2a 100644
--- a/drivers/net/wireless/ath/ath5k/debug.c
+++ b/drivers/net/wireless/ath/ath5k/debug.c
@@ -982,8 +982,6 @@ ath5k_debug_init_device(struct ath5k_hw *ah)
 	ah->debug.level = ath5k_debug;
 
 	phydir = debugfs_create_dir("ath5k", ah->hw->wiphy->debugfsdir);
-	if (!phydir)
-		return;
 
 	debugfs_create_file("debug", 0600, phydir, ah, &fops_debug);
 	debugfs_create_file("registers", 0400, phydir, ah, &registers_fops);
-- 
GitLab


From 1301783c8def21fb5e1658676f36d75fff15c571 Mon Sep 17 00:00:00 2001
From: Wang Ming <machel@vivo.com>
Date: Mon, 24 Jul 2023 13:11:08 +0300
Subject: [PATCH 0363/1806] wifi: ath6kl: Remove error checking for
 debugfs_create_dir()

It is expected that most callers should _ignore_ the errors
return by debugfs_create_dir() in ath6kl_debug_init_fs().

Signed-off-by: Wang Ming <machel@vivo.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230714014358.514-1-machel@vivo.com
---
 drivers/net/wireless/ath/ath6kl/debug.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath6kl/debug.c b/drivers/net/wireless/ath/ath6kl/debug.c
index 433a047f3747b..b837d31416dfe 100644
--- a/drivers/net/wireless/ath/ath6kl/debug.c
+++ b/drivers/net/wireless/ath/ath6kl/debug.c
@@ -1793,8 +1793,6 @@ int ath6kl_debug_init_fs(struct ath6kl *ar)
 {
 	ar->debugfs_phy = debugfs_create_dir("ath6kl",
 					     ar->wiphy->debugfsdir);
-	if (!ar->debugfs_phy)
-		return -ENOMEM;
 
 	debugfs_create_file("tgt_stats", 0400, ar->debugfs_phy, ar,
 			    &fops_tgt_stats);
-- 
GitLab


From 061115fbfb2ce5870c9a004d68dc63138c07c782 Mon Sep 17 00:00:00 2001
From: Dongliang Mu <dzm91@hust.edu.cn>
Date: Sun, 23 Jul 2023 12:04:02 +0800
Subject: [PATCH 0364/1806] wifi: ath9k: fix printk specifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Smatch reports:

ath_pci_probe() warn: argument 4 to %lx specifier is cast from pointer
ath_ahb_probe() warn: argument 4 to %lx specifier is cast from pointer

Fix it by modifying %lx to %p in the printk format string.

Note that with this change, the pointer address will be printed as a
hashed value by default. This is appropriate because the kernel
should not leak kernel pointers to user space in an informational
message. If someone wants to see the real address for debugging
purposes, this can be achieved with the no_hash_pointers kernel option.

Signed-off-by: Dongliang Mu <dzm91@hust.edu.cn>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230723040403.296723-1-dzm91@hust.edu.cn
---
 drivers/net/wireless/ath/ath9k/ahb.c | 4 ++--
 drivers/net/wireless/ath/ath9k/pci.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ahb.c b/drivers/net/wireless/ath/ath9k/ahb.c
index 9cd12b20b18d8..9bfaadfa6c009 100644
--- a/drivers/net/wireless/ath/ath9k/ahb.c
+++ b/drivers/net/wireless/ath/ath9k/ahb.c
@@ -132,8 +132,8 @@ static int ath_ahb_probe(struct platform_device *pdev)
 
 	ah = sc->sc_ah;
 	ath9k_hw_name(ah, hw_name, sizeof(hw_name));
-	wiphy_info(hw->wiphy, "%s mem=0x%lx, irq=%d\n",
-		   hw_name, (unsigned long)mem, irq);
+	wiphy_info(hw->wiphy, "%s mem=0x%p, irq=%d\n",
+		   hw_name, mem, irq);
 
 	return 0;
 
diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index a09f9d223f3de..0633589b85c23 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -988,8 +988,8 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	sc->sc_ah->msi_reg = 0;
 
 	ath9k_hw_name(sc->sc_ah, hw_name, sizeof(hw_name));
-	wiphy_info(hw->wiphy, "%s mem=0x%lx, irq=%d\n",
-		   hw_name, (unsigned long)sc->mem, pdev->irq);
+	wiphy_info(hw->wiphy, "%s mem=0x%p, irq=%d\n",
+		   hw_name, sc->mem, pdev->irq);
 
 	return 0;
 
-- 
GitLab


From 634fcbcaa4062db39aeb5ac6ed1bc1feb8dd5216 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 28 Jun 2023 10:23:15 +0300
Subject: [PATCH 0365/1806] wifi: rtw88: delete timer and free skb queue when
 unloading

Fix possible crash and memory leak on driver unload by deleting
TX purge timer and freeing C2H queue in 'rtw_core_deinit()',
shrink critical section in the latter by freeing COEX queue
out of TX report lock scope.

Reviewed-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230628072327.167196-1-dmantipov@yandex.ru
---
 drivers/net/wireless/realtek/rtw88/main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index c853e2f2d448f..c2ddb4d382af5 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -2183,10 +2183,12 @@ void rtw_core_deinit(struct rtw_dev *rtwdev)
 		release_firmware(wow_fw->firmware);
 
 	destroy_workqueue(rtwdev->tx_wq);
+	timer_delete_sync(&rtwdev->tx_report.purge_timer);
 	spin_lock_irqsave(&rtwdev->tx_report.q_lock, flags);
 	skb_queue_purge(&rtwdev->tx_report.queue);
-	skb_queue_purge(&rtwdev->coex.queue);
 	spin_unlock_irqrestore(&rtwdev->tx_report.q_lock, flags);
+	skb_queue_purge(&rtwdev->coex.queue);
+	skb_queue_purge(&rtwdev->c2h_queue);
 
 	list_for_each_entry_safe(rsvd_pkt, tmp, &rtwdev->rsvd_page_list,
 				 build_list) {
-- 
GitLab


From 6ca25a31e0a804be1675c0c0115fd6dbdfd7889e Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 28 Jun 2023 10:23:16 +0300
Subject: [PATCH 0366/1806] wifi: rtw88: remove unused and set but unused
 leftovers

Drop unused and set but unused 'last_push' of 'struct rtw_txq',
'wireless_set' of 'struct rtw_sta_info', 'usb_txagg_num' of
'struct rtw_usb' and 'n' of 'struct rx_usb_ctrl_block', unused
definition of 'struct rtw_timer_list', adjust related code.

Reviewed-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230628072327.167196-2-dmantipov@yandex.ru
---
 drivers/net/wireless/realtek/rtw88/main.c | 1 -
 drivers/net/wireless/realtek/rtw88/main.h | 9 ---------
 drivers/net/wireless/realtek/rtw88/tx.c   | 2 --
 drivers/net/wireless/realtek/rtw88/usb.c  | 1 -
 drivers/net/wireless/realtek/rtw88/usb.h  | 2 --
 5 files changed, 15 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index c2ddb4d382af5..935022246fd4b 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -1303,7 +1303,6 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si,
 	si->stbc_en = stbc_en;
 	si->ldpc_en = ldpc_en;
 	si->rf_type = rf_type;
-	si->wireless_set = wireless_set;
 	si->sgi_enable = is_support_sgi;
 	si->vht_enable = is_vht_enable;
 	si->ra_mask = ra_mask;
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index f9dd2ab941c8f..c42ef8294d59e 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -511,12 +511,6 @@ struct rtw_txpwr_idx {
 	struct rtw_5g_txpwr_idx pwr_idx_5g;
 };
 
-struct rtw_timer_list {
-	struct timer_list timer;
-	void (*function)(void *data);
-	void *args;
-};
-
 struct rtw_channel_params {
 	u8 center_chan;
 	u8 primary_chan;
@@ -734,9 +728,7 @@ struct rtw_ra_report {
 
 struct rtw_txq {
 	struct list_head list;
-
 	unsigned long flags;
-	unsigned long last_push;
 };
 
 #define RTW_BC_MC_MACID 1
@@ -754,7 +746,6 @@ struct rtw_sta_info {
 	u8 rate_id;
 	enum rtw_bandwidth bw_mode;
 	enum rtw_rf_type rf_type;
-	enum rtw_wireless_set wireless_set;
 	u8 stbc_en:2;
 	u8 ldpc_en:2;
 	bool sgi_enable;
diff --git a/drivers/net/wireless/realtek/rtw88/tx.c b/drivers/net/wireless/realtek/rtw88/tx.c
index 2821119dc9308..f63900b6621d9 100644
--- a/drivers/net/wireless/realtek/rtw88/tx.c
+++ b/drivers/net/wireless/realtek/rtw88/tx.c
@@ -606,8 +606,6 @@ static int rtw_txq_push_skb(struct rtw_dev *rtwdev,
 		rtw_err(rtwdev, "failed to write TX skb to HCI\n");
 		return ret;
 	}
-	rtwtxq->last_push = jiffies;
-
 	return 0;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 4a57efdba97bb..0458ab02a89ff 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -654,7 +654,6 @@ static int rtw_usb_alloc_rx_bufs(struct rtw_usb *rtwusb)
 	for (i = 0; i < RTW_USB_RXCB_NUM; i++) {
 		struct rx_usb_ctrl_block *rxcb = &rtwusb->rx_cb[i];
 
-		rxcb->n = i;
 		rxcb->rtwdev = rtwusb->rtwdev;
 		rxcb->rx_urb = usb_alloc_urb(0, GFP_KERNEL);
 		if (!rxcb->rx_urb)
diff --git a/drivers/net/wireless/realtek/rtw88/usb.h b/drivers/net/wireless/realtek/rtw88/usb.h
index ad1d7955c6a51..fad998005ec86 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.h
+++ b/drivers/net/wireless/realtek/rtw88/usb.h
@@ -58,7 +58,6 @@ struct rx_usb_ctrl_block {
 	struct rtw_dev *rtwdev;
 	struct urb *rx_urb;
 	struct sk_buff *rx_skb;
-	int n;
 };
 
 struct rtw_usb_tx_data {
@@ -79,7 +78,6 @@ struct rtw_usb {
 	u8 pipe_in;
 	u8 out_ep[RTW_USB_EP_MAX];
 	int qsel_to_ep[TX_DESC_QSEL_MAX];
-	u8 usb_txagg_num;
 
 	struct workqueue_struct *txwq, *rxwq;
 
-- 
GitLab


From e88c9558951f4209a29fcaae64def133a30e9917 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 28 Jun 2023 10:23:17 +0300
Subject: [PATCH 0367/1806] wifi: rtw88: remove unused USB bulkout size set

Drop no longer used 'bulkout_size' of 'struct rtw_usb' as well
as related macros from usb.h and leftovers in 'rtw_usb_parse()'.
This follows commit 462c8db6a011 ("wifi: rtw88: usb: drop
now unnecessary URB size check").

Reviewed-by: Ping-Ke Shih <pkshih@realtek.com>
Reviewed-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230628072327.167196-3-dmantipov@yandex.ru
---
 drivers/net/wireless/realtek/rtw88/usb.c | 17 -----------------
 drivers/net/wireless/realtek/rtw88/usb.h |  5 -----
 2 files changed, 22 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 0458ab02a89ff..91ed6d10ba8ac 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -142,7 +142,6 @@ static int rtw_usb_parse(struct rtw_dev *rtwdev,
 	struct usb_host_interface *host_interface = &interface->altsetting[0];
 	struct usb_interface_descriptor *interface_desc = &host_interface->desc;
 	struct usb_endpoint_descriptor *endpoint;
-	struct usb_device *usbd = interface_to_usbdev(interface);
 	int num_out_pipes = 0;
 	int i;
 	u8 num;
@@ -184,22 +183,6 @@ static int rtw_usb_parse(struct rtw_dev *rtwdev,
 		}
 	}
 
-	switch (usbd->speed) {
-	case USB_SPEED_LOW:
-	case USB_SPEED_FULL:
-		rtwusb->bulkout_size = RTW_USB_FULL_SPEED_BULK_SIZE;
-		break;
-	case USB_SPEED_HIGH:
-		rtwusb->bulkout_size = RTW_USB_HIGH_SPEED_BULK_SIZE;
-		break;
-	case USB_SPEED_SUPER:
-		rtwusb->bulkout_size = RTW_USB_SUPER_SPEED_BULK_SIZE;
-		break;
-	default:
-		rtw_err(rtwdev, "failed to detect usb speed\n");
-		return -EINVAL;
-	}
-
 	rtwdev->hci.bulkout_num = num_out_pipes;
 
 	if (num_out_pipes < 1 || num_out_pipes > 4) {
diff --git a/drivers/net/wireless/realtek/rtw88/usb.h b/drivers/net/wireless/realtek/rtw88/usb.h
index fad998005ec86..86697a5c0103a 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.h
+++ b/drivers/net/wireless/realtek/rtw88/usb.h
@@ -18,10 +18,6 @@
 
 #define RTW_USB_VENQT_CMD_IDX		0x00
 
-#define RTW_USB_SUPER_SPEED_BULK_SIZE	1024
-#define RTW_USB_HIGH_SPEED_BULK_SIZE	512
-#define RTW_USB_FULL_SPEED_BULK_SIZE	64
-
 #define RTW_USB_TX_SEL_HQ		BIT(0)
 #define RTW_USB_TX_SEL_LQ		BIT(1)
 #define RTW_USB_TX_SEL_NQ		BIT(2)
@@ -73,7 +69,6 @@ struct rtw_usb {
 	__le32 *usb_data;
 	unsigned int usb_data_index;
 
-	u32 bulkout_size;
 	u8 pipe_interrupt;
 	u8 pipe_in;
 	u8 out_ep[RTW_USB_EP_MAX];
-- 
GitLab


From 8986f0a9a3bb26bdaf17d5a1c8fadcc4c3edeae8 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 28 Jun 2023 10:23:18 +0300
Subject: [PATCH 0368/1806] wifi: rtw88: simplify vif iterators

Since all iterators called by 'rtw_iterate_vifs()' never uses
'mac' argument, it may be omitted, and 'struct rtw_vifs_entry'
may be simplified accordingly.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Reviewed-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230628072327.167196-4-dmantipov@yandex.ru
---
 drivers/net/wireless/realtek/rtw88/fw.c   | 2 +-
 drivers/net/wireless/realtek/rtw88/main.c | 8 +++-----
 drivers/net/wireless/realtek/rtw88/ps.c   | 6 ++----
 drivers/net/wireless/realtek/rtw88/util.c | 7 ++-----
 drivers/net/wireless/realtek/rtw88/util.h | 3 +--
 5 files changed, 9 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
index 567bbedd8ee09..a1b674e3caaa3 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.c
+++ b/drivers/net/wireless/realtek/rtw88/fw.c
@@ -140,7 +140,7 @@ struct rtw_beacon_filter_iter_data {
 	u8 *payload;
 };
 
-static void rtw_fw_bcn_filter_notify_vif_iter(void *data, u8 *mac,
+static void rtw_fw_bcn_filter_notify_vif_iter(void *data,
 					      struct ieee80211_vif *vif)
 {
 	struct rtw_beacon_filter_iter_data *iter_data = data;
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 935022246fd4b..4a33d2e47f33f 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -185,8 +185,7 @@ static void rtw_dynamic_csi_rate(struct rtw_dev *rtwdev, struct rtw_vif *rtwvif)
 		bf_info->cur_csi_rpt_rate = new_csi_rate_idx;
 }
 
-static void rtw_vif_watch_dog_iter(void *data, u8 *mac,
-				   struct ieee80211_vif *vif)
+static void rtw_vif_watch_dog_iter(void *data, struct ieee80211_vif *vif)
 {
 	struct rtw_watch_dog_iter_data *iter_data = data;
 	struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv;
@@ -2330,7 +2329,7 @@ struct rtw_iter_port_switch_data {
 	struct rtw_vif *rtwvif_ap;
 };
 
-static void rtw_port_switch_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
+static void rtw_port_switch_iter(void *data, struct ieee80211_vif *vif)
 {
 	struct rtw_iter_port_switch_data *iter_data = data;
 	struct rtw_dev *rtwdev = iter_data->rtwdev;
@@ -2382,8 +2381,7 @@ void rtw_core_port_switch(struct rtw_dev *rtwdev, struct ieee80211_vif *vif)
 	rtw_iterate_vifs(rtwdev, rtw_port_switch_iter, &iter_data);
 }
 
-static void rtw_check_sta_active_iter(void *data, u8 *mac,
-				      struct ieee80211_vif *vif)
+static void rtw_check_sta_active_iter(void *data, struct ieee80211_vif *vif)
 {
 	struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv;
 	bool *active = data;
diff --git a/drivers/net/wireless/realtek/rtw88/ps.c b/drivers/net/wireless/realtek/rtw88/ps.c
index 43e80a3a8136d..07e8cbd436cd8 100644
--- a/drivers/net/wireless/realtek/rtw88/ps.c
+++ b/drivers/net/wireless/realtek/rtw88/ps.c
@@ -37,8 +37,7 @@ int rtw_enter_ips(struct rtw_dev *rtwdev)
 	return 0;
 }
 
-static void rtw_restore_port_cfg_iter(void *data, u8 *mac,
-				      struct ieee80211_vif *vif)
+static void rtw_restore_port_cfg_iter(void *data, struct ieee80211_vif *vif)
 {
 	struct rtw_dev *rtwdev = data;
 	struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv;
@@ -320,8 +319,7 @@ static void __rtw_vif_recalc_lps(struct rtw_vif_recalc_lps_iter_data *data,
 	data->found_vif = vif;
 }
 
-static void rtw_vif_recalc_lps_iter(void *data, u8 *mac,
-				    struct ieee80211_vif *vif)
+static void rtw_vif_recalc_lps_iter(void *data, struct ieee80211_vif *vif)
 {
 	__rtw_vif_recalc_lps(data, vif);
 }
diff --git a/drivers/net/wireless/realtek/rtw88/util.c b/drivers/net/wireless/realtek/rtw88/util.c
index ff3c269fb1a72..e222d3c01a77e 100644
--- a/drivers/net/wireless/realtek/rtw88/util.c
+++ b/drivers/net/wireless/realtek/rtw88/util.c
@@ -159,7 +159,6 @@ void rtw_iterate_stas(struct rtw_dev *rtwdev,
 struct rtw_vifs_entry {
 	struct list_head list;
 	struct ieee80211_vif *vif;
-	u8 mac[ETH_ALEN];
 };
 
 struct rtw_iter_vifs_data {
@@ -177,13 +176,11 @@ static void rtw_collect_vif_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 		return;
 
 	vifs_entry->vif = vif;
-	ether_addr_copy(vifs_entry->mac, mac);
 	list_add_tail(&vifs_entry->list, &iter_stas->list);
 }
 
 void rtw_iterate_vifs(struct rtw_dev *rtwdev,
-		      void (*iterator)(void *data, u8 *mac,
-				       struct ieee80211_vif *vif),
+		      void (*iterator)(void *data, struct ieee80211_vif *vif),
 		      void *data)
 {
 	struct rtw_iter_vifs_data iter_data;
@@ -204,7 +201,7 @@ void rtw_iterate_vifs(struct rtw_dev *rtwdev,
 	list_for_each_entry_safe(vif_entry, tmp, &iter_data.list,
 				 list) {
 		list_del_init(&vif_entry->list);
-		iterator(data, vif_entry->mac, vif_entry->vif);
+		iterator(data, vif_entry->vif);
 		kfree(vif_entry);
 	}
 }
diff --git a/drivers/net/wireless/realtek/rtw88/util.h b/drivers/net/wireless/realtek/rtw88/util.h
index dc89655254002..f8399128a9a3a 100644
--- a/drivers/net/wireless/realtek/rtw88/util.h
+++ b/drivers/net/wireless/realtek/rtw88/util.h
@@ -18,8 +18,7 @@ struct rtw_dev;
 	ieee80211_iter_keys_rcu((rtwdev)->hw, vif, iterator, data)
 
 void rtw_iterate_vifs(struct rtw_dev *rtwdev,
-		      void (*iterator)(void *data, u8 *mac,
-				       struct ieee80211_vif *vif),
+		      void (*iterator)(void *data, struct ieee80211_vif *vif),
 		      void *data);
 void rtw_iterate_stas(struct rtw_dev *rtwdev,
 		      void (*iterator)(void *data,
-- 
GitLab


From 59b4cc439f184c5eaa34161ec67af1e16ffabed4 Mon Sep 17 00:00:00 2001
From: Zhang Shurong <zhang_shurong@foxmail.com>
Date: Sat, 15 Jul 2023 21:42:57 +0800
Subject: [PATCH 0369/1806] wifi: rtw89: debug: Fix error handling in
 rtw89_debug_priv_btc_manual_set()

If there is a failure during kstrtobool_from_user()
rtw89_debug_priv_btc_manual_set should return a negative error code
instead of returning the count directly.

Fix this bug by returning an error code instead of a count after
a failed call of the function "kstrtobool_from_user". Moreover
I omitted the label "out" with this source code correction.

Fixes: e3ec7017f6a2 ("rtw89: add Realtek 802.11ax driver")
Signed-off-by: Zhang Shurong <zhang_shurong@foxmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/tencent_1C09B99BD7DA9CAD18B00C8F0F050F540607@qq.com
---
 drivers/net/wireless/realtek/rtw89/debug.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index a4bbac916e22b..ce5a9ac081457 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -3193,12 +3193,14 @@ static ssize_t rtw89_debug_priv_btc_manual_set(struct file *filp,
 	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	struct rtw89_btc *btc = &rtwdev->btc;
 	bool btc_manual;
+	int ret;
 
-	if (kstrtobool_from_user(user_buf, count, &btc_manual))
-		goto out;
+	ret = kstrtobool_from_user(user_buf, count, &btc_manual);
+	if (ret)
+		return ret;
 
 	btc->ctrl.manual = btc_manual;
-out:
+
 	return count;
 }
 
-- 
GitLab


From 2d59478308685f95346e2289c2dc519d8d8ecc48 Mon Sep 17 00:00:00 2001
From: Yueh-Shun Li <shamrocklee@posteo.net>
Date: Thu, 22 Jun 2023 01:26:27 +0000
Subject: [PATCH 0370/1806] wifi: zd1211rw: fix typo "tranmits"

Spell "transmits" properly.

Found by searching for keyword "tranm".

Signed-off-by: Yueh-Shun Li <shamrocklee@posteo.net>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230622012627.15050-4-shamrocklee@posteo.net
---
 drivers/net/wireless/zydas/zd1211rw/zd_usb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
index 850c26bc95247..8505d84eeed60 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
@@ -1006,7 +1006,7 @@ resubmit:
  * @usb: the zd1211rw-private USB structure
  * @skb: a &struct sk_buff pointer
  *
- * This function tranmits a frame to the device. It doesn't wait for
+ * This function transmits a frame to the device. It doesn't wait for
  * completion. The frame must contain the control set and have all the
  * control set information available.
  *
-- 
GitLab


From efbc7e791a51b416555c6013cdf4943288d49261 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 11 Jul 2023 00:02:45 +0300
Subject: [PATCH 0371/1806] wifi: rtl8xxxu: Enable AP mode for RTL8192FU

Theoretically this chip can handle 127 clients.

Tested only very briefly but it should work as well as the RTL8188FU.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Reviewed-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/ffcabba5-7e9e-674c-ad03-73646b040b96@gmail.com
---
 drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192f.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192f.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192f.c
index 18dc5221a9c0c..28e93835e05a6 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192f.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192f.c
@@ -2079,6 +2079,8 @@ struct rtl8xxxu_fileops rtl8192fu_fops = {
 	.ampdu_max_time = 0x5e,
 	.ustime_tsf_edca = 0x50,
 	.max_aggr_num = 0x1f1f,
+	.supports_ap = 1,
+	.max_macid_num = 128,
 	.trxff_boundary = 0x3f3f,
 	.pbp_rx = PBP_PAGE_SIZE_256,
 	.pbp_tx = PBP_PAGE_SIZE_256,
-- 
GitLab


From dd71aca9a58bedb7bbba1c5c7cca2059a9cb2430 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 11 Jul 2023 00:04:05 +0300
Subject: [PATCH 0372/1806] wifi: rtl8xxxu: Enable AP mode for RTL8710BU
 (RTL8188GU)

Theoretically this chip can handle 15 clients.

Tested only very briefly but it should work as well as the RTL8188FU.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/ce04a0a1-df72-ea30-f742-8834e01457f5@gmail.com
---
 drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8710b.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8710b.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8710b.c
index f0d17b75c5f10..871b8cca8a188 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8710b.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8710b.c
@@ -1875,6 +1875,8 @@ struct rtl8xxxu_fileops rtl8710bu_fops = {
 	 */
 	.ustime_tsf_edca = 0x28,
 	.max_aggr_num = 0x0c14,
+	.supports_ap = 1,
+	.max_macid_num = 16,
 	.adda_1t_init = 0x03c00016,
 	.adda_1t_path_on = 0x03c00016,
 	.trxff_boundary = 0x3f7f,
-- 
GitLab


From 8c34b62167b449d16d6737a132996acad312a398 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 11 Jul 2023 00:04:39 +0300
Subject: [PATCH 0373/1806] wifi: rtl8xxxu: Enable AP mode for RTL8192EU

Theoretically this chip can handle 127 clients.

Tested only very briefly but it should work as well as the RTL8188FU.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/56c9b186-ba9a-8469-652d-ce1709813e9e@gmail.com
---
 drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
index f673aa9ba15a5..47bcaec6f2db4 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
@@ -1767,6 +1767,8 @@ struct rtl8xxxu_fileops rtl8192eu_fops = {
 	.has_s0s1 = 0,
 	.gen2_thermal_meter = 1,
 	.needs_full_init = 1,
+	.supports_ap = 1,
+	.max_macid_num = 128,
 	.adda_1t_init = 0x0fc01616,
 	.adda_1t_path_on = 0x0fc01616,
 	.adda_2t_path_on_a = 0x0fc01616,
-- 
GitLab


From 4831a80908f1562685ed29f7ec63ef5bec6b0fc3 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 11 Jul 2023 00:05:14 +0300
Subject: [PATCH 0374/1806] wifi: rtl8xxxu: Enable AP mode for RTL8723BU

Theoretically this chip can handle 127 clients.

Only compile tested but it should work as well as the RTL8188FU.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/b2876c56-0ea7-c398-5c9b-635f9f894f2c@gmail.com
---
 drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c
index 13ad5d5b73f4e..954369ed6226c 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c
@@ -1742,6 +1742,8 @@ struct rtl8xxxu_fileops rtl8723bu_fops = {
 	.ampdu_max_time = 0x5e,
 	.ustime_tsf_edca = 0x50,
 	.max_aggr_num = 0x0c14,
+	.supports_ap = 1,
+	.max_macid_num = 128,
 	.adda_1t_init = 0x01c00014,
 	.adda_1t_path_on = 0x01c00014,
 	.adda_2t_path_on_a = 0x01c00014,
-- 
GitLab


From caf9ead2c7d06fd7aa4cb48bd569ad61db9a0b4a Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 29 Jun 2023 11:51:00 +0300
Subject: [PATCH 0375/1806] wifi: mwifiex: prefer strscpy() over strlcpy()

Prefer 'strscpy()' over 'strlcpy()' in 'mwifiex_init_hw_fw()'.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230629085115.180499-1-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/main.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 1cd9d20cca16e..d99127dc466ec 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -724,14 +724,9 @@ static int mwifiex_init_hw_fw(struct mwifiex_adapter *adapter,
 	/* Override default firmware with manufacturing one if
 	 * manufacturing mode is enabled
 	 */
-	if (mfg_mode) {
-		if (strlcpy(adapter->fw_name, MFG_FIRMWARE,
-			    sizeof(adapter->fw_name)) >=
-			    sizeof(adapter->fw_name)) {
-			pr_err("%s: fw_name too long!\n", __func__);
-			return -1;
-		}
-	}
+	if (mfg_mode)
+		strscpy(adapter->fw_name, MFG_FIRMWARE,
+			sizeof(adapter->fw_name));
 
 	if (req_fw_nowait) {
 		ret = request_firmware_nowait(THIS_MODULE, 1, adapter->fw_name,
-- 
GitLab


From dcce94b80a954a8968ff29fafcfb066d6197fa9a Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 29 Jun 2023 11:51:01 +0300
Subject: [PATCH 0376/1806] wifi: mwifiex: fix fortify warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When compiling with gcc 13.1 and CONFIG_FORTIFY_SOURCE=y,
I've noticed the following:

In function ‘fortify_memcpy_chk’,
    inlined from ‘mwifiex_construct_tdls_action_frame’ at drivers/net/wireless/marvell/mwifiex/tdls.c:765:3,
    inlined from ‘mwifiex_send_tdls_action_frame’ at drivers/net/wireless/marvell/mwifiex/tdls.c:856:6:
./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Wattribute-warning]
  529 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The compiler actually complains on:

memmove(pos + ETH_ALEN, &mgmt->u.action.category,
	sizeof(mgmt->u.action.u.tdls_discover_resp));

and it happens because the fortification logic interprets this
as an attempt to overread 1-byte 'u.action.category' member of
'struct ieee80211_mgmt'. To silence this warning, it's enough
to pass an address of 'u.action' itself instead of an address
of its first member.

This also fixes an improper usage of 'sizeof()'. Since 'skb' is
extended with 'sizeof(mgmt->u.action.u.tdls_discover_resp) + 1'
bytes (where 1 is actually 'sizeof(mgmt->u.action.category)'),
I assume that the same number of bytes should be copied.

Suggested-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230629085115.180499-2-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/tdls.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c
index 97bb87c3676bb..6c60621b6cccb 100644
--- a/drivers/net/wireless/marvell/mwifiex/tdls.c
+++ b/drivers/net/wireless/marvell/mwifiex/tdls.c
@@ -735,6 +735,7 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv,
 	int ret;
 	u16 capab;
 	struct ieee80211_ht_cap *ht_cap;
+	unsigned int extra;
 	u8 radio, *pos;
 
 	capab = priv->curr_bss_params.bss_descriptor.cap_info_bitmap;
@@ -753,7 +754,10 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv,
 
 	switch (action_code) {
 	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
-		skb_put(skb, sizeof(mgmt->u.action.u.tdls_discover_resp) + 1);
+		/* See the layout of 'struct ieee80211_mgmt'. */
+		extra = sizeof(mgmt->u.action.u.tdls_discover_resp) +
+			sizeof(mgmt->u.action.category);
+		skb_put(skb, extra);
 		mgmt->u.action.category = WLAN_CATEGORY_PUBLIC;
 		mgmt->u.action.u.tdls_discover_resp.action_code =
 					      WLAN_PUB_ACTION_TDLS_DISCOVER_RES;
@@ -762,8 +766,7 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv,
 		mgmt->u.action.u.tdls_discover_resp.capability =
 							     cpu_to_le16(capab);
 		/* move back for addr4 */
-		memmove(pos + ETH_ALEN, &mgmt->u.action.category,
-			sizeof(mgmt->u.action.u.tdls_discover_resp));
+		memmove(pos + ETH_ALEN, &mgmt->u.action, extra);
 		/* init address 4 */
 		eth_broadcast_addr(pos);
 
-- 
GitLab


From 7ee92f6b41606202de66f7629a7d3c597d92da02 Mon Sep 17 00:00:00 2001
From: Johannes Wiesboeck <johannes.wiesboeck@aisec.fraunhofer.de>
Date: Thu, 6 Jul 2023 11:34:36 +0200
Subject: [PATCH 0377/1806] wifi: mwifiex: Set WIPHY_FLAG_NETNS_OK flag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allow moving the wiphy device for mwififex to a non-inital network
namespace. Many wireless drivers enable this flag implicitly by
initializing through the generic ieee80211_alloc_hw_nm function. As
mwifiex does not utilize this function WIPHY_FLAG_NETNS_OK must be set
explicitly.

Moving to network namespace and working connection tested using
wpa_supplicant from a network namespace as well as from a container on
GyroidOS. The hardware was the Toradex Apalis i.MX8QM Board using the
Azurewave AW-CM276NF wireless module.

Signed-off-by: Johannes Wiesboeck <johannes.wiesboeck@aisec.fraunhofer.de>
Reviewed-by: Michael Weiß <michael.weiss@aisec.fraunhofer.de>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230706093437.3380526-1-johannes.wiesboeck@aisec.fraunhofer.de
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 813d1cbebe19b..ba4e29713a8c9 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -4395,6 +4395,7 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 			WIPHY_FLAG_AP_UAPSD |
 			WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL |
 			WIPHY_FLAG_HAS_CHANNEL_SWITCH |
+			WIPHY_FLAG_NETNS_OK |
 			WIPHY_FLAG_PS_ON_BY_DEFAULT;
 
 	if (ISSUPP_TDLS_ENABLED(adapter->fw_cap_info))
-- 
GitLab


From b2090d93d4b6f1c72a9793d5a171806b8468b7cb Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 19 Jul 2023 11:31:55 +0300
Subject: [PATCH 0378/1806] wifi: brcmsmac: remove unused data type

Remove unused 'struct gpioh_item'. It seems it was so since
commit 5b435de0d786 ("net: wireless: add brcm80211 drivers").

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230719083232.158177-1-dmantipov@yandex.ru
---
 .../net/wireless/broadcom/brcm80211/brcmsmac/aiutils.h    | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.h
index 2d08c155c23bc..90b6e3982d2c3 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.h
@@ -145,14 +145,6 @@ struct si_pub {
 
 struct pci_dev;
 
-struct gpioh_item {
-	void *arg;
-	bool level;
-	void (*handler) (u32 stat, void *arg);
-	u32 event;
-	struct gpioh_item *next;
-};
-
 /* misc si info needed by some of the routines */
 struct si_info {
 	struct si_pub pub;	/* back plane public state (must be first) */
-- 
GitLab


From 7b2b20125f1e9ec49e3d13c41264afef70e70463 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Mon, 24 Jul 2023 22:41:00 -0700
Subject: [PATCH 0379/1806] MAINTAINERS: Replace my email address

Switch from corporate email address to linux.dev address.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230725054100.1013421-1-yonghong.song@linux.dev
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d0553ad37865e..cfd7c06a4b2da 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3703,7 +3703,7 @@ M:	Daniel Borkmann <daniel@iogearbox.net>
 M:	Andrii Nakryiko <andrii@kernel.org>
 R:	Martin KaFai Lau <martin.lau@linux.dev>
 R:	Song Liu <song@kernel.org>
-R:	Yonghong Song <yhs@fb.com>
+R:	Yonghong Song <yonghong.song@linux.dev>
 R:	John Fastabend <john.fastabend@gmail.com>
 R:	KP Singh <kpsingh@kernel.org>
 R:	Stanislav Fomichev <sdf@google.com>
@@ -3742,7 +3742,7 @@ F:	tools/lib/bpf/
 F:	tools/testing/selftests/bpf/
 
 BPF [ITERATOR]
-M:	Yonghong Song <yhs@fb.com>
+M:	Yonghong Song <yonghong.song@linux.dev>
 L:	bpf@vger.kernel.org
 S:	Maintained
 F:	kernel/bpf/*iter.c
-- 
GitLab


From 98c4d0abf5c478db1ad126ff0c187dbb84c0803c Mon Sep 17 00:00:00 2001
From: Matt Whitlock <kernel@mattwhitlock.name>
Date: Thu, 20 Apr 2023 15:24:51 -0400
Subject: [PATCH 0380/1806] mt76: mt7921: don't assume adequate headroom for
 SDIO headers

mt7921_usb_sdio_tx_prepare_skb() calls mt7921_usb_sdio_write_txwi() and
mt7921_skb_add_usb_sdio_hdr(), both of which blindly assume that
adequate headroom will be available in the passed skb. This assumption
typically is satisfied when the skb was allocated in the net core for
transmission via the mt7921 netdev (although even that is only an
optimization and is not strictly guaranteed), but the assumption is
sometimes not satisfied when the skb originated in the receive path of
another netdev and was passed through to the mt7921, such as by the
bridge layer. Blindly prepending bytes to an skb is always wrong.

This commit introduces a call to skb_cow_head() before the call to
mt7921_usb_sdio_write_txwi() in mt7921_usb_sdio_tx_prepare_skb() to
ensure that at least MT_SDIO_TXD_SIZE + MT_SDIO_HDR_SIZE bytes can be
pushed onto the skb.

Without this fix, I can trivially cause kernel panics by bridging an
MT7921AU-based USB 802.11ax interface with an Ethernet interface on an
Intel Atom-based x86 system using its onboard RTL8169 PCI Ethernet
adapter and also on an ARM-based Raspberry Pi 1 using its onboard
SMSC9512 USB Ethernet adapter. Note that the panics do not occur in
every system configuration, as they occur only if the receiving netdev
leaves less headroom in its received skbs than the mt7921 needs for its
SDIO headers.

Here is an example stack trace of this panic on Raspberry Pi OS Lite
2023-02-21 running kernel 6.1.24+ [1]:

 skb_panic from skb_push+0x44/0x48
 skb_push from mt7921_usb_sdio_tx_prepare_skb+0xd4/0x190 [mt7921_common]
 mt7921_usb_sdio_tx_prepare_skb [mt7921_common] from mt76u_tx_queue_skb+0x94/0x1d0 [mt76_usb]
 mt76u_tx_queue_skb [mt76_usb] from __mt76_tx_queue_skb+0x4c/0xc8 [mt76]
 __mt76_tx_queue_skb [mt76] from mt76_txq_schedule.part.0+0x13c/0x398 [mt76]
 mt76_txq_schedule.part.0 [mt76] from mt76_txq_schedule_all+0x24/0x30 [mt76]
 mt76_txq_schedule_all [mt76] from mt7921_tx_worker+0x58/0xf4 [mt7921_common]
 mt7921_tx_worker [mt7921_common] from __mt76_worker_fn+0x9c/0xec [mt76]
 __mt76_worker_fn [mt76] from kthread+0xbc/0xe0
 kthread from ret_from_fork+0x14/0x34

After this fix, bridging the mt7921 interface works fine on both of my
previously problematic systems.

[1] https://github.com/raspberrypi/firmware/tree/5c276f55a4b21345cd4d6200a504ee991851ff7a

Link: https://github.com/openwrt/openwrt/issues/11796
Signed-off-by: Matt Whitlock <kernel@mattwhitlock.name>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/mac.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 1675bf5204812..a671c601c5836 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -1180,6 +1180,10 @@ int mt7921_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	if (unlikely(tx_info->skb->len <= ETH_HLEN))
 		return -EINVAL;
 
+	err = skb_cow_head(skb, MT_SDIO_TXD_SIZE + MT_SDIO_HDR_SIZE);
+	if (err)
+		return err;
+
 	if (!wcid)
 		wcid = &dev->mt76.global_wcid;
 
-- 
GitLab


From c55b4e788f1dd6ca89cc97cf291d2a03b0b96de1 Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Thu, 27 Apr 2023 07:05:15 +0800
Subject: [PATCH 0381/1806] wifi: mt76: mt7996: fix header translation logic

When header translation failure is indicated, the hardware will insert
an extra 2-byte field containing the data length after the protocol
type field. This happens either when the LLC-SNAP pattern did not match,
or if a VLAN header was detected.

The previous commit accidentally breaks the logic, so reverts back.

Fixes: 27db47ab1f47 (wifi: mt76: mt7996: enable mesh HW amsdu/de-amsdu support)
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 9b0f6053e0fa6..25c5deb15d213 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -836,14 +836,19 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, struct sk_buff *skb)
 		skb_pull(skb, hdr_gap);
 		if (!hdr_trans && status->amsdu && !(ieee80211_has_a4(fc) && is_mesh)) {
 			pad_start = ieee80211_get_hdrlen_from_skb(skb);
-		} else if (hdr_trans && (rxd2 & MT_RXD2_NORMAL_HDR_TRANS_ERROR) &&
-			   get_unaligned_be16(skb->data + pad_start) == ETH_P_8021Q) {
+		} else if (hdr_trans && (rxd2 & MT_RXD2_NORMAL_HDR_TRANS_ERROR)) {
 			/* When header translation failure is indicated,
 			 * the hardware will insert an extra 2-byte field
 			 * containing the data length after the protocol
-			 * type field.
+			 * type field. This happens either when the LLC-SNAP
+			 * pattern did not match, or if a VLAN header was
+			 * detected.
 			 */
-			pad_start = 16;
+			pad_start = 12;
+			if (get_unaligned_be16(skb->data + pad_start) == ETH_P_8021Q)
+				pad_start += 4;
+			else
+				pad_start = 0;
 		}
 
 		if (pad_start) {
-- 
GitLab


From 68f1c3ea337fbc9a58463647be7582eae5a8134b Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Tue, 2 May 2023 11:10:05 +0800
Subject: [PATCH 0382/1806] wifi: mt76: mt7996: enable BSS_CHANGED_MU_GROUPS
 support

The Group ID Management frame is an Action frame of category VHT.
It is transmitted by the AP to assign or change the user position
of a STA for one or more group IDs.

Also, sniffer can use a given group id to monitor STA that belongs
to that group.

Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/init.c  |  1 +
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 23 +++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7996/regs.h  | 21 +++++++++++------
 3 files changed, 38 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
index f1b48cdda58f3..3569fef20cd94 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
@@ -183,6 +183,7 @@ mt7996_init_wiphy(struct ieee80211_hw *hw)
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_FILS_DISCOVERY);
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT);
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER);
 
 	if (!mdev->dev->of_node ||
 	    !of_property_read_bool(mdev->dev->of_node,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index f306e9c50ea3b..7a97b7180403d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -530,6 +530,26 @@ mt7996_get_rates_table(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	return mvif->basic_rates_idx;
 }
 
+static void
+mt7996_update_mu_group(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		       struct ieee80211_bss_conf *info)
+{
+	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_dev *dev = mt7996_hw_dev(hw);
+	u8 band = mvif->mt76.band_idx;
+	u32 *mu;
+
+	mu = (u32 *)info->mu_group.membership;
+	mt76_wr(dev, MT_WF_PHYRX_BAND_GID_TAB_VLD0(band), mu[0]);
+	mt76_wr(dev, MT_WF_PHYRX_BAND_GID_TAB_VLD1(band), mu[1]);
+
+	mu = (u32 *)info->mu_group.position;
+	mt76_wr(dev, MT_WF_PHYRX_BAND_GID_TAB_POS0(band), mu[0]);
+	mt76_wr(dev, MT_WF_PHYRX_BAND_GID_TAB_POS1(band), mu[1]);
+	mt76_wr(dev, MT_WF_PHYRX_BAND_GID_TAB_POS2(band), mu[2]);
+	mt76_wr(dev, MT_WF_PHYRX_BAND_GID_TAB_POS3(band), mu[3]);
+}
+
 static void mt7996_bss_info_changed(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
 				    struct ieee80211_bss_conf *info,
@@ -602,6 +622,9 @@ static void mt7996_bss_info_changed(struct ieee80211_hw *hw,
 	    changed & BSS_CHANGED_FILS_DISCOVERY)
 		mt7996_mcu_beacon_inband_discov(dev, vif, changed);
 
+	if (changed & BSS_CHANGED_MU_GROUPS)
+		mt7996_update_mu_group(hw, vif, info);
+
 	mutex_unlock(&dev->mt76.mutex);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/regs.h b/drivers/net/wireless/mediatek/mt76/mt7996/regs.h
index d1d3d154195d8..97beab924517b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/regs.h
@@ -557,22 +557,29 @@ enum base_rev {
 
 #define MT_PCIE1_MAC_INT_ENABLE			MT_PCIE1_MAC(0x188)
 
+/* PHYRX CSD */
+#define MT_WF_PHYRX_CSD_BASE			0x83000000
+#define MT_WF_PHYRX_CSD(_band, _wf, ofs)	(MT_WF_PHYRX_CSD_BASE + \
+						 ((_band) << 20) + \
+						 ((_wf) << 16) + (ofs))
+#define MT_WF_PHYRX_CSD_IRPI(_band, _wf)	MT_WF_PHYRX_CSD(_band, _wf, 0x1000)
+
 /* PHYRX CTRL */
 #define MT_WF_PHYRX_BAND_BASE			0x83080000
 #define MT_WF_PHYRX_BAND(_band, ofs)		(MT_WF_PHYRX_BAND_BASE + \
 						 ((_band) << 20) + (ofs))
 
+#define MT_WF_PHYRX_BAND_GID_TAB_VLD0(_band)	MT_WF_PHYRX_BAND(_band, 0x1054)
+#define MT_WF_PHYRX_BAND_GID_TAB_VLD1(_band)	MT_WF_PHYRX_BAND(_band, 0x1058)
+#define MT_WF_PHYRX_BAND_GID_TAB_POS0(_band)	MT_WF_PHYRX_BAND(_band, 0x105c)
+#define MT_WF_PHYRX_BAND_GID_TAB_POS1(_band)	MT_WF_PHYRX_BAND(_band, 0x1060)
+#define MT_WF_PHYRX_BAND_GID_TAB_POS2(_band)	MT_WF_PHYRX_BAND(_band, 0x1064)
+#define MT_WF_PHYRX_BAND_GID_TAB_POS3(_band)	MT_WF_PHYRX_BAND(_band, 0x1068)
+
 #define MT_WF_PHYRX_BAND_RX_CTRL1(_band)	MT_WF_PHYRX_BAND(_band, 0x2004)
 #define MT_WF_PHYRX_BAND_RX_CTRL1_IPI_EN	GENMASK(2, 0)
 #define MT_WF_PHYRX_BAND_RX_CTRL1_STSCNT_EN	GENMASK(11, 9)
 
-/* PHYRX CSD */
-#define MT_WF_PHYRX_CSD_BASE			0x83000000
-#define MT_WF_PHYRX_CSD(_band, _wf, ofs)	(MT_WF_PHYRX_CSD_BASE + \
-						 ((_band) << 20) + \
-						 ((_wf) << 16) + (ofs))
-#define MT_WF_PHYRX_CSD_IRPI(_band, _wf)	MT_WF_PHYRX_CSD(_band, _wf, 0x1000)
-
 /* PHYRX CSD BAND */
 #define MT_WF_PHYRX_CSD_BAND_RXTD12(_band)		MT_WF_PHYRX_BAND(_band, 0x8230)
 #define MT_WF_PHYRX_CSD_BAND_RXTD12_IRPI_SW_CLR_ONLY	BIT(18)
-- 
GitLab


From 905a0a6ac7a7709d3ac98ca8c98ca27dd1567b9b Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Tue, 2 May 2023 11:10:06 +0800
Subject: [PATCH 0383/1806] wifi: mt76: mt7615: enable BSS_CHANGED_MU_GROUPS
 support

The Group ID Management frame is an Action frame of category VHT.
It is transmitted by the AP to assign or change the user position
of a STA for one or more group IDs.

Also, sniffer can use a given group id to monitor STA that belongs
to that group.

Notify underlying driver of changes via BSS_CHANGED_MU_GROUPS.

Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7615/init.c  |  2 ++
 .../net/wireless/mediatek/mt76/mt7615/main.c  | 29 +++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7615/regs.h  |  9 ++++++
 3 files changed, 40 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
index 621e69f07e3c5..ab475c8418185 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
@@ -397,6 +397,8 @@ mt7615_init_wiphy(struct ieee80211_hw *hw)
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_SET_SCAN_DWELL);
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0);
+	if (!is_mt7622(&phy->dev->mt76))
+		wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER);
 
 	ieee80211_hw_set(hw, SINGLE_SCAN_ON_ALL_BANDS);
 	ieee80211_hw_set(hw, TX_STATUS_NO_AMPDU_LEN);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index dadb13f2ca095..4167aafa5b0ee 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -552,6 +552,32 @@ static void mt7615_configure_filter(struct ieee80211_hw *hw,
 	mt7615_mutex_release(dev);
 }
 
+static void
+mt7615_update_mu_group(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		       struct ieee80211_bss_conf *info)
+{
+	struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv;
+	struct mt7615_dev *dev = mt7615_hw_dev(hw);
+	u8 i, band = mvif->mt76.band_idx;
+	u32 *mu;
+
+	mu = (u32 *)info->mu_group.membership;
+	for (i = 0; i < WLAN_MEMBERSHIP_LEN / sizeof(*mu); i++) {
+		if (is_mt7663(&dev->mt76))
+			mt76_wr(dev, MT7663_WF_PHY_GID_TAB_VLD(band, i), mu[i]);
+		else
+			mt76_wr(dev, MT_WF_PHY_GID_TAB_VLD(band, i), mu[i]);
+	}
+
+	mu = (u32 *)info->mu_group.position;
+	for (i = 0; i < WLAN_USER_POSITION_LEN / sizeof(*mu); i++) {
+		if (is_mt7663(&dev->mt76))
+			mt76_wr(dev, MT7663_WF_PHY_GID_TAB_POS(band, i), mu[i]);
+		else
+			mt76_wr(dev, MT_WF_PHY_GID_TAB_POS(band, i), mu[i]);
+	}
+}
+
 static void mt7615_bss_info_changed(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
 				    struct ieee80211_bss_conf *info,
@@ -600,6 +626,9 @@ static void mt7615_bss_info_changed(struct ieee80211_hw *hw,
 	if (changed & BSS_CHANGED_ASSOC)
 		mt7615_mac_set_beacon_filter(phy, vif, vif->cfg.assoc);
 
+	if (changed & BSS_CHANGED_MU_GROUPS)
+		 mt7615_update_mu_group(hw, vif, info);
+
 	mt7615_mutex_release(dev);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/regs.h b/drivers/net/wireless/mediatek/mt76/mt7615/regs.h
index 7cecb22c569ef..806b3887c541c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/regs.h
@@ -212,6 +212,15 @@ enum mt7615_reg_base {
 
 #define MT7663_WF_PHY_R0_PHYCTRL_STS5(_phy)	MT_WF_PHY(0x0224 + ((_phy) << 12))
 
+#define MT_WF_PHY_GID_TAB_VLD(_phy, i)		MT_WF_PHY(0x0254 + (i) * 4 + \
+							  ((_phy) << 9))
+#define MT7663_WF_PHY_GID_TAB_VLD(_phy, i)	MT_WF_PHY(0x0254 + (i) * 4 + \
+							  ((_phy) << 12))
+#define MT_WF_PHY_GID_TAB_POS(_phy, i)		MT_WF_PHY(0x025c + (i) * 4 + \
+							  ((_phy) << 9))
+#define MT7663_WF_PHY_GID_TAB_POS(_phy, i)	MT_WF_PHY(0x025c + (i) * 4 + \
+							  ((_phy) << 12))
+
 #define MT_WF_PHY_MIN_PRI_PWR(_phy)	MT_WF_PHY((_phy) ? 0x084 : 0x229c)
 #define MT_WF_PHY_PD_OFDM_MASK(_phy)	((_phy) ? GENMASK(24, 16) : \
 					 GENMASK(28, 20))
-- 
GitLab


From 62561a47af587a863583ce1d607b519c0c4bb384 Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Sat, 6 May 2023 13:46:19 +0800
Subject: [PATCH 0384/1806] wifi: mt76: enable UNII-4 channel 177 support

Enable support for the 5GHz channel 177 with center frequency 5885MHz and
operating class 125 based on IEEE Std 802.11ax-2021 Table E-4.

Signed-off-by: Himanshu Goyal <himanshu.goyal@mediatek.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 467afef98ba20..cd3aac4cc06fe 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -76,6 +76,7 @@ static const struct ieee80211_channel mt76_channels_5ghz[] = {
 	CHAN5G(165, 5825),
 	CHAN5G(169, 5845),
 	CHAN5G(173, 5865),
+	CHAN5G(177, 5885),
 };
 
 static const struct ieee80211_channel mt76_channels_6ghz[] = {
-- 
GitLab


From 9a3994077d170ec9ac75e800932b5671d9940cd2 Mon Sep 17 00:00:00 2001
From: StanleyYP Wang <StanleyYP.Wang@mediatek.com>
Date: Tue, 9 May 2023 11:11:57 +0800
Subject: [PATCH 0385/1806] wifi: mt76: mt7915: fix background radar event
 being blocked

The background radar uses MT_RX_SEL2 as its band indication, so fix it.

Fixes: 7a53eecd5c87 (wifi: mt76: mt7915: check the correctness of event data)
Signed-off-by: StanleyYP Wang <StanleyYP.Wang@mediatek.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 9fcb22fa1f97e..088a065e37d5d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -274,7 +274,7 @@ mt7915_mcu_rx_radar_detected(struct mt7915_dev *dev, struct sk_buff *skb)
 
 	r = (struct mt7915_mcu_rdd_report *)skb->data;
 
-	if (r->band_idx > MT_BAND1)
+	if (r->band_idx > MT_RX_SEL2)
 		return;
 
 	if ((r->band_idx && !dev->phy.mt76->band_idx) &&
-- 
GitLab


From 943e4fb96e6f47c70a0a9d29d62cffc2479330e6 Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Wed, 10 May 2023 12:53:16 +0800
Subject: [PATCH 0386/1806] wifi: mt76: mt7915: report tx retries/failed counts
 for non-WED path

Get missing tx retries/failed counts from txfree done events and report
them via mt7915_sta_statistics().

Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt76_connac_mac.c  |  6 ++---
 .../net/wireless/mediatek/mt76/mt7915/init.c  |  2 ++
 .../net/wireless/mediatek/mt76/mt7915/mac.c   | 22 +++++++++++++++++--
 .../net/wireless/mediatek/mt76/mt7915/mac.h   |  7 +++++-
 .../net/wireless/mediatek/mt76/mt7915/main.c  | 12 +++++-----
 .../net/wireless/mediatek/mt76/mt7915/regs.h  |  3 +++
 6 files changed, 39 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index d39a3cc5e381f..3686684485420 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -729,17 +729,15 @@ bool mt76_connac2_mac_add_txs_skb(struct mt76_dev *dev, struct mt76_wcid *wcid,
 	skb = mt76_tx_status_skb_get(dev, wcid, pid, &list);
 	if (skb) {
 		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-		bool noacked = !(info->flags & IEEE80211_TX_STAT_ACK);
 
 		if (!(le32_to_cpu(txs_data[0]) & MT_TXS0_ACK_ERROR_MASK))
 			info->flags |= IEEE80211_TX_STAT_ACK;
 
 		info->status.ampdu_len = 1;
-		info->status.ampdu_ack_len = !noacked;
+		info->status.ampdu_ack_len =
+			!!(info->flags & IEEE80211_TX_STAT_ACK);
 		info->status.rates[0].idx = -1;
 
-		wcid->stats.tx_failed += noacked;
-
 		mt76_connac2_mac_fill_txs(dev, wcid, txs_data);
 		mt76_tx_status_skb_done(dev, skb, &list);
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index ac2049f49bb38..8d6e09605dc4e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -581,6 +581,8 @@ void mt7915_mac_init(struct mt7915_dev *dev)
 
 	if (!is_mt7915(&dev->mt76))
 		mt76_clear(dev, MT_MDP_DCR2, MT_MDP_DCR2_RX_TRANS_SHORT);
+	else
+		mt76_clear(dev, MT_PLE_HOST_RPT0, MT_PLE_HOST_RPT0_TX_LATENCY);
 
 	/* enable hardware de-agg */
 	mt76_set(dev, MT_MDP_DCR0, MT_MDP_DCR0_DAMSDU_EN);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 7df8d95fc3fbc..9b2ccd99854ea 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -951,6 +951,7 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len)
 	struct mt76_dev *mdev = &dev->mt76;
 	struct mt76_txwi_cache *txwi;
 	struct ieee80211_sta *sta = NULL;
+	struct mt76_wcid *wcid = NULL;
 	LIST_HEAD(free_list);
 	void *end = data + len;
 	bool v3, wake = false;
@@ -977,7 +978,6 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len)
 		info = le32_to_cpu(*cur_info);
 		if (info & MT_TX_FREE_PAIR) {
 			struct mt7915_sta *msta;
-			struct mt76_wcid *wcid;
 			u16 idx;
 
 			idx = FIELD_GET(MT_TX_FREE_WLAN_ID, info);
@@ -994,7 +994,25 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len)
 			continue;
 		}
 
-		if (v3 && (info & MT_TX_FREE_MPDU_HEADER))
+		if (!mtk_wed_device_active(&mdev->mmio.wed) && wcid) {
+			u32 tx_retries = 0, tx_failed = 0;
+
+			if (v3 && (info & MT_TX_FREE_MPDU_HEADER_V3)) {
+				tx_retries =
+					FIELD_GET(MT_TX_FREE_COUNT_V3, info) - 1;
+				tx_failed = tx_retries +
+					!!FIELD_GET(MT_TX_FREE_STAT_V3, info);
+			} else if (!v3 && (info & MT_TX_FREE_MPDU_HEADER)) {
+				tx_retries =
+					FIELD_GET(MT_TX_FREE_COUNT, info) - 1;
+				tx_failed = tx_retries +
+					!!FIELD_GET(MT_TX_FREE_STAT, info);
+			}
+			wcid->stats.tx_retries += tx_retries;
+			wcid->stats.tx_failed += tx_failed;
+		}
+
+		if (v3 && (info & MT_TX_FREE_MPDU_HEADER_V3))
 			continue;
 
 		for (i = 0; i < 1 + v3; i++) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.h b/drivers/net/wireless/mediatek/mt76/mt7915/mac.h
index ce94f87e2042a..448b1b3801909 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.h
@@ -9,7 +9,12 @@
 #define MT_TX_FREE_VER			GENMASK(18, 16)
 #define MT_TX_FREE_MSDU_CNT_V0		GENMASK(6, 0)
 /* 0: success, others: dropped */
-#define MT_TX_FREE_MPDU_HEADER		BIT(30)
+#define MT_TX_FREE_COUNT		GENMASK(12, 0)
+#define MT_TX_FREE_COUNT_V3		GENMASK(27, 24)
+#define MT_TX_FREE_STAT			GENMASK(14, 13)
+#define MT_TX_FREE_STAT_V3		GENMASK(29, 28)
+#define MT_TX_FREE_MPDU_HEADER		BIT(15)
+#define MT_TX_FREE_MPDU_HEADER_V3	BIT(30)
 #define MT_TX_FREE_MSDU_ID_V3		GENMASK(14, 0)
 
 #define MT_TXS5_F0_FINAL_MPDU		BIT(31)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index 1b361199c0616..706aca359ca3a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -1045,12 +1045,6 @@ static void mt7915_sta_statistics(struct ieee80211_hw *hw,
 		sinfo->tx_packets = msta->wcid.stats.tx_packets;
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
 
-		sinfo->tx_failed = msta->wcid.stats.tx_failed;
-		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
-
-		sinfo->tx_retries = msta->wcid.stats.tx_retries;
-		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES);
-
 		if (mtk_wed_get_rx_capa(&phy->dev->mt76.mmio.wed)) {
 			sinfo->rx_bytes = msta->wcid.stats.rx_bytes;
 			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64);
@@ -1060,6 +1054,12 @@ static void mt7915_sta_statistics(struct ieee80211_hw *hw,
 		}
 	}
 
+	sinfo->tx_failed = msta->wcid.stats.tx_failed;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
+
+	sinfo->tx_retries = msta->wcid.stats.tx_retries;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES);
+
 	sinfo->ack_signal = (s8)msta->ack_signal;
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h
index c8e478a55081a..71fa9576ad0e7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h
@@ -145,6 +145,9 @@ enum offs_rev {
 #define MT_PLE_BASE			0x820c0000
 #define MT_PLE(ofs)			(MT_PLE_BASE + (ofs))
 
+#define MT_PLE_HOST_RPT0		MT_PLE(0x030)
+#define MT_PLE_HOST_RPT0_TX_LATENCY	BIT(3)
+
 #define MT_FL_Q_EMPTY			MT_PLE(__OFFS(PLE_FL_Q_EMPTY))
 #define MT_FL_Q0_CTRL			MT_PLE(__OFFS(PLE_FL_Q_CTRL))
 #define MT_FL_Q2_CTRL			MT_PLE(__OFFS(PLE_FL_Q_CTRL) + 0x8)
-- 
GitLab


From 161a7528e4074d104305fc109c16134b4990070e Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Wed, 10 May 2023 12:53:17 +0800
Subject: [PATCH 0387/1806] wifi: mt76: mt7915: rework tx packets counting when
 WED is active

PPDU TxS can only report MPDU count whereas mac80211 requires MSDU scale
(NL80211_STA_INFO_TX_PACKETS), so switch to get MSDU counts from WA
statistic.

Note that mt7915 WA firmware only counts tx_packet for WED path, so driver
needs to take care of host path additionally.

Fixes: 43eaa3689507 ("wifi: mt76: add PPDU based TxS support for WED device")
Co-developed-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h     |  2 +-
 .../wireless/mediatek/mt76/mt76_connac_mac.c  |  9 ++-
 .../wireless/mediatek/mt76/mt76_connac_mcu.h  |  1 +
 .../net/wireless/mediatek/mt76/mt7915/main.c  |  6 +-
 .../net/wireless/mediatek/mt76/mt7915/mcu.c   | 74 +++++++++++++++++--
 .../wireless/mediatek/mt76/mt7915/mt7915.h    |  1 +
 6 files changed, 79 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 6b07b8fafec2f..0e9f4197213a3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -277,7 +277,7 @@ struct mt76_sta_stats {
 	u64 tx_mcs[16];		/* mcs idx */
 	u64 tx_bytes;
 	/* WED TX */
-	u32 tx_packets;
+	u32 tx_packets;		/* unit: MSDU */
 	u32 tx_retries;
 	u32 tx_failed;
 	/* WED RX */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index 3686684485420..f6346a4589786 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -523,7 +523,9 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi,
 
 		/* counting non-offloading skbs */
 		wcid->stats.tx_bytes += skb->len;
-		wcid->stats.tx_packets++;
+		/* mt7915 WA only counts WED path */
+		if (is_mt7915(dev) && mtk_wed_device_active(&dev->mmio.wed))
+			wcid->stats.tx_packets++;
 	}
 
 	val = FIELD_PREP(MT_TXD0_TX_BYTES, skb->len + sz_txd) |
@@ -606,12 +608,11 @@ bool mt76_connac2_mac_fill_txs(struct mt76_dev *dev, struct mt76_wcid *wcid,
 	txs = le32_to_cpu(txs_data[0]);
 
 	/* PPDU based reporting */
-	if (FIELD_GET(MT_TXS0_TXS_FORMAT, txs) > 1) {
+	if (mtk_wed_device_active(&dev->mmio.wed) &&
+	    FIELD_GET(MT_TXS0_TXS_FORMAT, txs) > 1) {
 		stats->tx_bytes +=
 			le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_BYTE) -
 			le32_get_bits(txs_data[7], MT_TXS7_MPDU_RETRY_BYTE);
-		stats->tx_packets +=
-			le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_CNT);
 		stats->tx_failed +=
 			le32_get_bits(txs_data[6], MT_TXS6_MPDU_FAIL_CNT);
 		stats->tx_retries +=
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index ca1ce97a6d2fd..7a52b68491b6e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -998,6 +998,7 @@ enum {
 	MCU_EXT_EVENT_ASSERT_DUMP = 0x23,
 	MCU_EXT_EVENT_RDD_REPORT = 0x3a,
 	MCU_EXT_EVENT_CSA_NOTIFY = 0x4f,
+	MCU_EXT_EVENT_WA_TX_STAT = 0x74,
 	MCU_EXT_EVENT_BCC_NOTIFY = 0x75,
 	MCU_EXT_EVENT_MURU_CTRL = 0x9f,
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index 706aca359ca3a..6512fdf842b0e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -1042,8 +1042,10 @@ static void mt7915_sta_statistics(struct ieee80211_hw *hw,
 		sinfo->tx_bytes = msta->wcid.stats.tx_bytes;
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64);
 
-		sinfo->tx_packets = msta->wcid.stats.tx_packets;
-		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
+		if (!mt7915_mcu_wed_wa_tx_stats(phy->dev, msta->wcid.idx)) {
+			sinfo->tx_packets = msta->wcid.stats.tx_packets;
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
+		}
 
 		if (mtk_wed_get_rx_capa(&phy->dev->mt76.mmio.wed)) {
 			sinfo->rx_bytes = msta->wcid.stats.rx_bytes;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 088a065e37d5d..8da9c87e98042 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -164,7 +164,9 @@ mt7915_mcu_parse_response(struct mt76_dev *mdev, int cmd,
 	}
 
 	rxd = (struct mt76_connac2_mcu_rxd *)skb->data;
-	if (seq != rxd->seq)
+	if (seq != rxd->seq &&
+	    !(rxd->eid == MCU_CMD_EXT_CID &&
+	      rxd->ext_eid == MCU_EXT_EVENT_WA_TX_STAT))
 		return -EAGAIN;
 
 	if (cmd == MCU_CMD(PATCH_SEM_CONTROL)) {
@@ -395,12 +397,14 @@ void mt7915_mcu_rx_event(struct mt7915_dev *dev, struct sk_buff *skb)
 	struct mt76_connac2_mcu_rxd *rxd;
 
 	rxd = (struct mt76_connac2_mcu_rxd *)skb->data;
-	if (rxd->ext_eid == MCU_EXT_EVENT_THERMAL_PROTECT ||
-	    rxd->ext_eid == MCU_EXT_EVENT_FW_LOG_2_HOST ||
-	    rxd->ext_eid == MCU_EXT_EVENT_ASSERT_DUMP ||
-	    rxd->ext_eid == MCU_EXT_EVENT_PS_SYNC ||
-	    rxd->ext_eid == MCU_EXT_EVENT_BCC_NOTIFY ||
-	    !rxd->seq)
+	if ((rxd->ext_eid == MCU_EXT_EVENT_THERMAL_PROTECT ||
+	     rxd->ext_eid == MCU_EXT_EVENT_FW_LOG_2_HOST ||
+	     rxd->ext_eid == MCU_EXT_EVENT_ASSERT_DUMP ||
+	     rxd->ext_eid == MCU_EXT_EVENT_PS_SYNC ||
+	     rxd->ext_eid == MCU_EXT_EVENT_BCC_NOTIFY ||
+	     !rxd->seq) &&
+	     !(rxd->eid == MCU_CMD_EXT_CID &&
+	       rxd->ext_eid == MCU_EXT_EVENT_WA_TX_STAT))
 		mt7915_mcu_rx_unsolicited_event(dev, skb);
 	else
 		mt76_mcu_rx_event(&dev->mt76, skb);
@@ -3733,6 +3737,62 @@ int mt7915_mcu_twt_agrt_update(struct mt7915_dev *dev,
 				 &req, sizeof(req), true);
 }
 
+int mt7915_mcu_wed_wa_tx_stats(struct mt7915_dev *dev, u16 wlan_idx)
+{
+	struct {
+		__le32 cmd;
+		__le32 num;
+		__le32 __rsv;
+		__le16 wlan_idx;
+	} req = {
+		.cmd = cpu_to_le32(0x15),
+		.num = cpu_to_le32(1),
+		.wlan_idx = cpu_to_le16(wlan_idx),
+	};
+	struct mt7915_mcu_wa_tx_stat {
+		__le16 wlan_idx;
+		u8 __rsv[2];
+
+		/* tx_bytes is deprecated since WA byte counter uses u32,
+		 * which easily leads to overflow.
+		 */
+		__le32 tx_bytes;
+		__le32 tx_packets;
+	} *res;
+	struct mt76_wcid *wcid;
+	struct sk_buff *skb;
+	int ret;
+
+	ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_WA_PARAM_CMD(QUERY),
+					&req, sizeof(req), true, &skb);
+	if (ret)
+		return ret;
+
+	if (!is_mt7915(&dev->mt76))
+		skb_pull(skb, 4);
+
+	res = (struct mt7915_mcu_wa_tx_stat *)skb->data;
+
+	if (le16_to_cpu(res->wlan_idx) != wlan_idx) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	rcu_read_lock();
+
+	wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
+	if (wcid)
+		wcid->stats.tx_packets += le32_to_cpu(res->tx_packets);
+	else
+		ret = -EINVAL;
+
+	rcu_read_unlock();
+out:
+	dev_kfree_skb(skb);
+
+	return ret;
+}
+
 int mt7915_mcu_rf_regval(struct mt7915_dev *dev, u32 regidx, u32 *val, bool set)
 {
 	struct {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index b3ead35307406..3053f4abf7dbe 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -539,6 +539,7 @@ int mt7915_mcu_get_rx_rate(struct mt7915_phy *phy, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta, struct rate_info *rate);
 int mt7915_mcu_rdd_background_enable(struct mt7915_phy *phy,
 				     struct cfg80211_chan_def *chandef);
+int mt7915_mcu_wed_wa_tx_stats(struct mt7915_dev *dev, u16 wcid);
 int mt7915_mcu_rf_regval(struct mt7915_dev *dev, u32 regidx, u32 *val, bool set);
 int mt7915_mcu_wa_cmd(struct mt7915_dev *dev, int cmd, u32 a1, u32 a2, u32 a3);
 int mt7915_mcu_fw_log_2_host(struct mt7915_dev *dev, u8 type, u8 ctrl);
-- 
GitLab


From f39d499345dddb8382986fd5a2a0e84a63b1a6d5 Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Wed, 10 May 2023 12:53:18 +0800
Subject: [PATCH 0388/1806] wifi: mt76: mt7915: rework tx bytes counting when
 WED is active

Concurrent binding/non-binding skbs could be handled anywhere which leads
to mixed byte counting, so switch to use PPDU TxS reporting regardless Tx
paths when WED is active.

Fixes: 43eaa3689507 ("wifi: mt76: add PPDU based TxS support for WED device")
Co-developed-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt76_connac_mac.c  |  2 --
 .../net/wireless/mediatek/mt76/mt7915/init.c  |  6 ++++
 .../net/wireless/mediatek/mt76/mt7915/mmio.c  | 30 ++-----------------
 drivers/net/wireless/mediatek/mt76/tx.c       |  9 +++++-
 4 files changed, 16 insertions(+), 31 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index f6346a4589786..3501f05031182 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -521,8 +521,6 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi,
 		q_idx = wmm_idx * MT76_CONNAC_MAX_WMM_SETS +
 			mt76_connac_lmac_mapping(skb_get_queue_mapping(skb));
 
-		/* counting non-offloading skbs */
-		wcid->stats.tx_bytes += skb->len;
 		/* mt7915 WA only counts WED path */
 		if (is_mt7915(dev) && mtk_wed_device_active(&dev->mmio.wed))
 			wcid->stats.tx_packets++;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index 8d6e09605dc4e..30c552a5f9206 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -499,6 +499,12 @@ mt7915_mac_init_band(struct mt7915_dev *dev, u8 band)
 	set = FIELD_PREP(MT_WTBLOFF_TOP_RSCR_RCPI_MODE, 0) |
 	      FIELD_PREP(MT_WTBLOFF_TOP_RSCR_RCPI_PARAM, 0x3);
 	mt76_rmw(dev, MT_WTBLOFF_TOP_RSCR(band), mask, set);
+
+	/* MT_TXD5_TX_STATUS_HOST (MPDU format) has higher priority than
+	 * MT_AGG_ACR_PPDU_TXS2H (PPDU format) even though ACR bit is set.
+	 */
+	if (mtk_wed_device_active(&dev->mt76.mmio.wed))
+		mt76_set(dev, MT_AGG_ACR4(band), MT_AGG_ACR_PPDU_TXS2H);
 }
 
 static void
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index 45f3558bf31c1..2fa059af23ded 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -545,8 +545,6 @@ static u32 mt7915_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val)
 static int mt7915_mmio_wed_offload_enable(struct mtk_wed_device *wed)
 {
 	struct mt7915_dev *dev;
-	struct mt7915_phy *phy;
-	int ret;
 
 	dev = container_of(wed, struct mt7915_dev, mt76.mmio.wed);
 
@@ -554,43 +552,19 @@ static int mt7915_mmio_wed_offload_enable(struct mtk_wed_device *wed)
 	dev->mt76.token_size = wed->wlan.token_start;
 	spin_unlock_bh(&dev->mt76.token_lock);
 
-	ret = wait_event_timeout(dev->mt76.tx_wait,
-				 !dev->mt76.wed_token_count, HZ);
-	if (!ret)
-		return -EAGAIN;
-
-	phy = &dev->phy;
-	mt76_set(dev, MT_AGG_ACR4(phy->mt76->band_idx), MT_AGG_ACR_PPDU_TXS2H);
-
-	phy = dev->mt76.phys[MT_BAND1] ? dev->mt76.phys[MT_BAND1]->priv : NULL;
-	if (phy)
-		mt76_set(dev, MT_AGG_ACR4(phy->mt76->band_idx),
-			 MT_AGG_ACR_PPDU_TXS2H);
-
-	return 0;
+	return !wait_event_timeout(dev->mt76.tx_wait,
+				   !dev->mt76.wed_token_count, HZ);
 }
 
 static void mt7915_mmio_wed_offload_disable(struct mtk_wed_device *wed)
 {
 	struct mt7915_dev *dev;
-	struct mt7915_phy *phy;
 
 	dev = container_of(wed, struct mt7915_dev, mt76.mmio.wed);
 
 	spin_lock_bh(&dev->mt76.token_lock);
 	dev->mt76.token_size = MT7915_TOKEN_SIZE;
 	spin_unlock_bh(&dev->mt76.token_lock);
-
-	/* MT_TXD5_TX_STATUS_HOST (MPDU format) has higher priority than
-	 * MT_AGG_ACR_PPDU_TXS2H (PPDU format) even though ACR bit is set.
-	 */
-	phy = &dev->phy;
-	mt76_clear(dev, MT_AGG_ACR4(phy->mt76->band_idx), MT_AGG_ACR_PPDU_TXS2H);
-
-	phy = dev->mt76.phys[MT_BAND1] ? dev->mt76.phys[MT_BAND1]->priv : NULL;
-	if (phy)
-		mt76_clear(dev, MT_AGG_ACR4(phy->mt76->band_idx),
-			   MT_AGG_ACR_PPDU_TXS2H);
 }
 
 static void mt7915_mmio_wed_release_rx_buf(struct mtk_wed_device *wed)
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 72b3ec715e47a..e9b9728458a9b 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -121,6 +121,7 @@ int
 mt76_tx_status_skb_add(struct mt76_dev *dev, struct mt76_wcid *wcid,
 		       struct sk_buff *skb)
 {
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct mt76_tx_cb *cb = mt76_tx_skb_cb(skb);
 	int pid;
@@ -134,8 +135,14 @@ mt76_tx_status_skb_add(struct mt76_dev *dev, struct mt76_wcid *wcid,
 		return MT_PACKET_ID_NO_ACK;
 
 	if (!(info->flags & (IEEE80211_TX_CTL_REQ_TX_STATUS |
-			     IEEE80211_TX_CTL_RATE_CTRL_PROBE)))
+			     IEEE80211_TX_CTL_RATE_CTRL_PROBE))) {
+		if (mtk_wed_device_active(&dev->mmio.wed) &&
+		    ((info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) ||
+		     ieee80211_is_data(hdr->frame_control)))
+			return MT_PACKET_ID_WED;
+
 		return MT_PACKET_ID_NO_SKB;
+	}
 
 	spin_lock_bh(&dev->status_lock);
 
-- 
GitLab


From e890c3cf7897b1d07b19124ad2e42c687b3b99e5 Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Wed, 10 May 2023 12:53:19 +0800
Subject: [PATCH 0389/1806] wifi: mt76: report non-binding skb tx rate when WED
 is active

AQL relies on accurate tx rate reporting, so add this patch for
non-binding skb rate when WED is enabled.

Co-developed-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/tx.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index e9b9728458a9b..6cc26cc6c5178 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -270,8 +270,15 @@ void __mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid_idx, struct sk_buff *
 #endif
 
 	if (cb->pktid < MT_PACKET_ID_FIRST) {
+		struct ieee80211_rate_status rs = {};
+
 		hw = mt76_tx_status_get_hw(dev, skb);
 		status.sta = wcid_to_sta(wcid);
+		if (status.sta && (wcid->rate.flags || wcid->rate.legacy)) {
+			rs.rate_idx = wcid->rate;
+			status.rates = &rs;
+			status.n_rates = 1;
+		}
 		spin_lock_bh(&dev->rx_lock);
 		ieee80211_tx_status_ext(hw, &status);
 		spin_unlock_bh(&dev->rx_lock);
-- 
GitLab


From 41bc54404687faa05404df0910890b062c705f54 Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Wed, 10 May 2023 12:53:20 +0800
Subject: [PATCH 0390/1806] wifi: mt76: mt7915: drop return in
 mt7915_sta_statistics

Avoid blocking other statistics sinfo->filled when txrate is
unavailable.

Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7915/main.c  | 27 +++++++++----------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index 6512fdf842b0e..85d4ea3d8064b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -1019,21 +1019,20 @@ static void mt7915_sta_statistics(struct ieee80211_hw *hw,
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE);
 	}
 
-	if (!txrate->legacy && !txrate->flags)
-		return;
-
-	if (txrate->legacy) {
-		sinfo->txrate.legacy = txrate->legacy;
-	} else {
-		sinfo->txrate.mcs = txrate->mcs;
-		sinfo->txrate.nss = txrate->nss;
-		sinfo->txrate.bw = txrate->bw;
-		sinfo->txrate.he_gi = txrate->he_gi;
-		sinfo->txrate.he_dcm = txrate->he_dcm;
-		sinfo->txrate.he_ru_alloc = txrate->he_ru_alloc;
+	if (txrate->legacy || txrate->flags) {
+		if (txrate->legacy) {
+			sinfo->txrate.legacy = txrate->legacy;
+		} else {
+			sinfo->txrate.mcs = txrate->mcs;
+			sinfo->txrate.nss = txrate->nss;
+			sinfo->txrate.bw = txrate->bw;
+			sinfo->txrate.he_gi = txrate->he_gi;
+			sinfo->txrate.he_dcm = txrate->he_dcm;
+			sinfo->txrate.he_ru_alloc = txrate->he_ru_alloc;
+		}
+		sinfo->txrate.flags = txrate->flags;
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 	}
-	sinfo->txrate.flags = txrate->flags;
-	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 
 	/* offloading flows bypass networking stack, so driver counts and
 	 * reports sta statistics via NL80211_STA_INFO when WED is active.
-- 
GitLab


From b34f346b917eafed6e61d737917f8543884fe2bf Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Wed, 10 May 2023 12:53:21 +0800
Subject: [PATCH 0391/1806] wifi: mt76: mt7996: drop return in
 mt7996_sta_statistics

Avoid blocking other statistics sinfo->filled when txrate is
unavailable.

Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 25 ++++++++++---------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 7a97b7180403d..0dbfb0db35a59 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -975,18 +975,19 @@ static void mt7996_sta_statistics(struct ieee80211_hw *hw,
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct rate_info *txrate = &msta->wcid.rate;
 
-	if (!txrate->legacy && !txrate->flags)
-		return;
-
-	if (txrate->legacy) {
-		sinfo->txrate.legacy = txrate->legacy;
-	} else {
-		sinfo->txrate.mcs = txrate->mcs;
-		sinfo->txrate.nss = txrate->nss;
-		sinfo->txrate.bw = txrate->bw;
-		sinfo->txrate.he_gi = txrate->he_gi;
-		sinfo->txrate.he_dcm = txrate->he_dcm;
-		sinfo->txrate.he_ru_alloc = txrate->he_ru_alloc;
+	if (txrate->legacy || txrate->flags) {
+		if (txrate->legacy) {
+			sinfo->txrate.legacy = txrate->legacy;
+		} else {
+			sinfo->txrate.mcs = txrate->mcs;
+			sinfo->txrate.nss = txrate->nss;
+			sinfo->txrate.bw = txrate->bw;
+			sinfo->txrate.he_gi = txrate->he_gi;
+			sinfo->txrate.he_dcm = txrate->he_dcm;
+			sinfo->txrate.he_ru_alloc = txrate->he_ru_alloc;
+		}
+		sinfo->txrate.flags = txrate->flags;
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 	}
 	sinfo->txrate.flags = txrate->flags;
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
-- 
GitLab


From d616d3680264beb9a9d2c4fc681064b06f447eeb Mon Sep 17 00:00:00 2001
From: Deren Wu <deren.wu@mediatek.com>
Date: Wed, 10 May 2023 14:51:13 +0800
Subject: [PATCH 0392/1806] wifi: mt76: mt7921: do not support one stream on
 secondary antenna only

mt7921 support following antenna combiantions only.
* primary + secondary (2x2)
* primary only        (1x1)

Since we cannot work on secondary antenna only, return error if the
antenna bitmap is 0x2 in .set_antenna().

For example:
iw phy0 set antenna 3 3 /* valid */
iw phy0 set antenna 1 1 /* valid */
iw phy0 set antenna 2 2 /* invalid */

Cc: stable@vger.kernel.org
Fixes: e0f9fdda81bd ("mt76: mt7921: add ieee80211_ops")
Suggested-by: Knox Chiou <knoxchiou@google.com>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 3b6adb29cbef1..0e3ada1e008cd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1363,7 +1363,7 @@ mt7921_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 		return -EINVAL;
 
 	if ((BIT(hweight8(tx_ant)) - 1) != tx_ant)
-		tx_ant = BIT(ffs(tx_ant) - 1) - 1;
+		return -EINVAL;
 
 	mt7921_mutex_acquire(dev);
 
-- 
GitLab


From 692031b9045ca0739232052d0cdb26a5d4e5b4b5 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 12 May 2023 15:11:58 +0200
Subject: [PATCH 0393/1806] wifi: mt76: mt7921: remove macro duplication in
 regs.h

Get rid of MT_MIB_RTS_COUNT_MASK marco duplication in mt7921/regs.h

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/regs.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
index e52977ff33493..b180142562a24 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
@@ -158,7 +158,6 @@
 
 #define MT_MIB_MB_SDR0(_band, n)	MT_WF_MIB(_band, 0x100 + ((n) << 4))
 #define MT_MIB_RTS_RETRIES_COUNT_MASK	GENMASK(31, 16)
-#define MT_MIB_RTS_COUNT_MASK		GENMASK(15, 0)
 
 #define MT_MIB_MB_BSDR0(_band)		MT_WF_MIB(_band, 0x688)
 #define MT_MIB_RTS_COUNT_MASK		GENMASK(15, 0)
-- 
GitLab


From 7f03a56314be00f0ecfa3ef27559d6cfa6ba0429 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 13 May 2023 00:29:53 +0200
Subject: [PATCH 0394/1806] wifi: mt76: mt7915: move mib_stats structure in
 mt76.h

mib_stats structure is shared by mostly all chipsets. Move it to shared
code.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h     | 63 +++++++++++++++++++
 .../wireless/mediatek/mt76/mt7915/debugfs.c   |  4 +-
 .../net/wireless/mediatek/mt76/mt7915/mac.c   |  2 +-
 .../net/wireless/mediatek/mt76/mt7915/main.c  |  4 +-
 .../wireless/mediatek/mt76/mt7915/mt7915.h    | 63 +------------------
 5 files changed, 69 insertions(+), 67 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 0e9f4197213a3..6d22482183d8a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -857,6 +857,69 @@ struct mt76_dev {
 	};
 };
 
+/* per-phy stats.  */
+struct mt76_mib_stats {
+	u32 ack_fail_cnt;
+	u32 fcs_err_cnt;
+	u32 rts_cnt;
+	u32 rts_retries_cnt;
+	u32 ba_miss_cnt;
+	u32 tx_bf_cnt;
+	u32 tx_mu_bf_cnt;
+	u32 tx_mu_mpdu_cnt;
+	u32 tx_mu_acked_mpdu_cnt;
+	u32 tx_su_acked_mpdu_cnt;
+	u32 tx_bf_ibf_ppdu_cnt;
+	u32 tx_bf_ebf_ppdu_cnt;
+
+	u32 tx_bf_rx_fb_all_cnt;
+	u32 tx_bf_rx_fb_eht_cnt;
+	u32 tx_bf_rx_fb_he_cnt;
+	u32 tx_bf_rx_fb_vht_cnt;
+	u32 tx_bf_rx_fb_ht_cnt;
+
+	u32 tx_bf_rx_fb_bw; /* value of last sample, not cumulative */
+	u32 tx_bf_rx_fb_nc_cnt;
+	u32 tx_bf_rx_fb_nr_cnt;
+	u32 tx_bf_fb_cpl_cnt;
+	u32 tx_bf_fb_trig_cnt;
+
+	u32 tx_ampdu_cnt;
+	u32 tx_stop_q_empty_cnt;
+	u32 tx_mpdu_attempts_cnt;
+	u32 tx_mpdu_success_cnt;
+	u32 tx_pkt_ebf_cnt;
+	u32 tx_pkt_ibf_cnt;
+
+	u32 tx_rwp_fail_cnt;
+	u32 tx_rwp_need_cnt;
+
+	/* rx stats */
+	u32 rx_fifo_full_cnt;
+	u32 channel_idle_cnt;
+	u32 primary_cca_busy_time;
+	u32 secondary_cca_busy_time;
+	u32 primary_energy_detect_time;
+	u32 cck_mdrdy_time;
+	u32 ofdm_mdrdy_time;
+	u32 green_mdrdy_time;
+	u32 rx_vector_mismatch_cnt;
+	u32 rx_delimiter_fail_cnt;
+	u32 rx_mrdy_cnt;
+	u32 rx_len_mismatch_cnt;
+	u32 rx_mpdu_cnt;
+	u32 rx_ampdu_cnt;
+	u32 rx_ampdu_bytes_cnt;
+	u32 rx_ampdu_valid_subframe_cnt;
+	u32 rx_ampdu_valid_subframe_bytes_cnt;
+	u32 rx_pfdrop_cnt;
+	u32 rx_vec_queue_overflow_drop_cnt;
+	u32 rx_ba_cnt;
+
+	u32 tx_amsdu[8];
+	u32 tx_amsdu_cnt;
+};
+
 struct mt76_power_limits {
 	s8 cck[4];
 	s8 ofdm[8];
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
index 879884ead660e..dd5c494efa5f0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
@@ -719,10 +719,10 @@ mt7915_ampdu_stat_read_phy(struct mt7915_phy *phy,
 static void
 mt7915_txbf_stat_read_phy(struct mt7915_phy *phy, struct seq_file *s)
 {
+	struct mt76_mib_stats *mib = &phy->mib;
 	static const char * const bw[] = {
 		"BW20", "BW40", "BW80", "BW160"
 	};
-	struct mib_stats *mib = &phy->mib;
 
 	/* Tx Beamformer monitor */
 	seq_puts(s, "\nTx Beamformer applied PPDU counts: ");
@@ -768,7 +768,7 @@ mt7915_tx_stats_show(struct seq_file *file, void *data)
 {
 	struct mt7915_phy *phy = file->private;
 	struct mt7915_dev *dev = phy->dev;
-	struct mib_stats *mib = &phy->mib;
+	struct mt76_mib_stats *mib = &phy->mib;
 	int i;
 
 	mutex_lock(&dev->mt76.mutex);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 9b2ccd99854ea..9e5eb0bfeb260 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1765,8 +1765,8 @@ void mt7915_reset(struct mt7915_dev *dev)
 
 void mt7915_mac_update_stats(struct mt7915_phy *phy)
 {
+	struct mt76_mib_stats *mib = &phy->mib;
 	struct mt7915_dev *dev = phy->dev;
-	struct mib_stats *mib = &phy->mib;
 	int i, aggr0 = 0, aggr1, cnt;
 	u8 band = phy->mt76->band_idx;
 	u32 val;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index 85d4ea3d8064b..e384c633e8111 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -842,7 +842,7 @@ mt7915_get_stats(struct ieee80211_hw *hw,
 {
 	struct mt7915_phy *phy = mt7915_hw_phy(hw);
 	struct mt7915_dev *dev = mt7915_hw_dev(hw);
-	struct mib_stats *mib = &phy->mib;
+	struct mt76_mib_stats *mib = &phy->mib;
 
 	mutex_lock(&dev->mt76.mutex);
 
@@ -1327,11 +1327,11 @@ void mt7915_get_et_stats(struct ieee80211_hw *hw,
 	struct mt7915_dev *dev = mt7915_hw_dev(hw);
 	struct mt7915_phy *phy = mt7915_hw_phy(hw);
 	struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv;
+	struct mt76_mib_stats *mib = &phy->mib;
 	struct mt76_ethtool_worker_info wi = {
 		.data = data,
 		.idx = mvif->mt76.idx,
 	};
-	struct mib_stats *mib = &phy->mib;
 	/* See mt7915_ampdu_stat_read_phy, etc */
 	int i, ei = 0, stats_size;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index 3053f4abf7dbe..41e0aafae9f8a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -157,67 +157,6 @@ struct mt7915_vif {
 	struct cfg80211_bitrate_mask bitrate_mask;
 };
 
-/* per-phy stats.  */
-struct mib_stats {
-	u32 ack_fail_cnt;
-	u32 fcs_err_cnt;
-	u32 rts_cnt;
-	u32 rts_retries_cnt;
-	u32 ba_miss_cnt;
-	u32 tx_bf_cnt;
-	u32 tx_mu_mpdu_cnt;
-	u32 tx_mu_acked_mpdu_cnt;
-	u32 tx_su_acked_mpdu_cnt;
-	u32 tx_bf_ibf_ppdu_cnt;
-	u32 tx_bf_ebf_ppdu_cnt;
-
-	u32 tx_bf_rx_fb_all_cnt;
-	u32 tx_bf_rx_fb_he_cnt;
-	u32 tx_bf_rx_fb_vht_cnt;
-	u32 tx_bf_rx_fb_ht_cnt;
-
-	u32 tx_bf_rx_fb_bw; /* value of last sample, not cumulative */
-	u32 tx_bf_rx_fb_nc_cnt;
-	u32 tx_bf_rx_fb_nr_cnt;
-	u32 tx_bf_fb_cpl_cnt;
-	u32 tx_bf_fb_trig_cnt;
-
-	u32 tx_ampdu_cnt;
-	u32 tx_stop_q_empty_cnt;
-	u32 tx_mpdu_attempts_cnt;
-	u32 tx_mpdu_success_cnt;
-	u32 tx_pkt_ebf_cnt;
-	u32 tx_pkt_ibf_cnt;
-
-	u32 tx_rwp_fail_cnt;
-	u32 tx_rwp_need_cnt;
-
-	/* rx stats */
-	u32 rx_fifo_full_cnt;
-	u32 channel_idle_cnt;
-	u32 primary_cca_busy_time;
-	u32 secondary_cca_busy_time;
-	u32 primary_energy_detect_time;
-	u32 cck_mdrdy_time;
-	u32 ofdm_mdrdy_time;
-	u32 green_mdrdy_time;
-	u32 rx_vector_mismatch_cnt;
-	u32 rx_delimiter_fail_cnt;
-	u32 rx_mrdy_cnt;
-	u32 rx_len_mismatch_cnt;
-	u32 rx_mpdu_cnt;
-	u32 rx_ampdu_cnt;
-	u32 rx_ampdu_bytes_cnt;
-	u32 rx_ampdu_valid_subframe_cnt;
-	u32 rx_ampdu_valid_subframe_bytes_cnt;
-	u32 rx_pfdrop_cnt;
-	u32 rx_vec_queue_overflow_drop_cnt;
-	u32 rx_ba_cnt;
-
-	u32 tx_amsdu[8];
-	u32 tx_amsdu_cnt;
-};
-
 /* crash-dump */
 struct mt7915_crash_data {
 	guid_t guid;
@@ -263,7 +202,7 @@ struct mt7915_phy {
 	u32 rx_ampdu_ts;
 	u32 ampdu_ref;
 
-	struct mib_stats mib;
+	struct mt76_mib_stats mib;
 	struct mt76_channel_state state_ts;
 
 #ifdef CONFIG_NL80211_TESTMODE
-- 
GitLab


From 98214484f2339c01fbb0fa3bfda3790f96fb0b9f Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 13 May 2023 00:29:54 +0200
Subject: [PATCH 0395/1806] wifi: mt76: mt7996: rely on mib_stats shared
 definition

Get rid of private copy of mib_stats structure.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7996/debugfs.c   |  4 +-
 .../net/wireless/mediatek/mt76/mt7996/mac.c   |  2 +-
 .../net/wireless/mediatek/mt76/mt7996/main.c  |  4 +-
 .../wireless/mediatek/mt76/mt7996/mt7996.h    | 56 +------------------
 4 files changed, 6 insertions(+), 60 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
index 513ab4ba41c96..4d40ec7ff57f5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
@@ -474,10 +474,10 @@ mt7996_ampdu_stat_read_phy(struct mt7996_phy *phy, struct seq_file *file)
 static void
 mt7996_txbf_stat_read_phy(struct mt7996_phy *phy, struct seq_file *s)
 {
+	struct mt76_mib_stats *mib = &phy->mib;
 	static const char * const bw[] = {
 		"BW20", "BW40", "BW80", "BW160"
 	};
-	struct mib_stats *mib = &phy->mib;
 
 	/* Tx Beamformer monitor */
 	seq_puts(s, "\nTx Beamformer applied PPDU counts: ");
@@ -523,7 +523,7 @@ mt7996_tx_stats_show(struct seq_file *file, void *data)
 {
 	struct mt7996_phy *phy = file->private;
 	struct mt7996_dev *dev = phy->dev;
-	struct mib_stats *mib = &phy->mib;
+	struct mt76_mib_stats *mib = &phy->mib;
 	int i;
 	u32 attempts, success, per;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 25c5deb15d213..d05d7e79781f6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2196,8 +2196,8 @@ void mt7996_reset(struct mt7996_dev *dev)
 
 void mt7996_mac_update_stats(struct mt7996_phy *phy)
 {
+	struct mt76_mib_stats *mib = &phy->mib;
 	struct mt7996_dev *dev = phy->dev;
-	struct mib_stats *mib = &phy->mib;
 	u8 band_idx = phy->mt76->band_idx;
 	u32 cnt;
 	int i;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 0dbfb0db35a59..9362f8487a0e1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -815,7 +815,7 @@ mt7996_get_stats(struct ieee80211_hw *hw,
 {
 	struct mt7996_phy *phy = mt7996_hw_phy(hw);
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
-	struct mib_stats *mib = &phy->mib;
+	struct mt76_mib_stats *mib = &phy->mib;
 
 	mutex_lock(&dev->mt76.mutex);
 
@@ -1221,11 +1221,11 @@ void mt7996_get_et_stats(struct ieee80211_hw *hw,
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mt7996_phy *phy = mt7996_hw_phy(hw);
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt76_mib_stats *mib = &phy->mib;
 	struct mt76_ethtool_worker_info wi = {
 		.data = data,
 		.idx = mvif->mt76.idx,
 	};
-	struct mib_stats *mib = &phy->mib;
 	/* See mt7996_ampdu_stat_read_phy, etc */
 	int i, ei = 0;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 4d7dcb95a620a..348d3ad3f9e75 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -130,60 +130,6 @@ struct mt7996_vif {
 	u8 beacon_rates_idx;
 };
 
-/* per-phy stats.  */
-struct mib_stats {
-	u32 ack_fail_cnt;
-	u32 fcs_err_cnt;
-	u32 rts_cnt;
-	u32 rts_retries_cnt;
-	u32 ba_miss_cnt;
-	u32 tx_mu_bf_cnt;
-	u32 tx_mu_mpdu_cnt;
-	u32 tx_mu_acked_mpdu_cnt;
-	u32 tx_su_acked_mpdu_cnt;
-	u32 tx_bf_ibf_ppdu_cnt;
-	u32 tx_bf_ebf_ppdu_cnt;
-
-	u32 tx_bf_rx_fb_all_cnt;
-	u32 tx_bf_rx_fb_eht_cnt;
-	u32 tx_bf_rx_fb_he_cnt;
-	u32 tx_bf_rx_fb_vht_cnt;
-	u32 tx_bf_rx_fb_ht_cnt;
-
-	u32 tx_bf_rx_fb_bw; /* value of last sample, not cumulative */
-	u32 tx_bf_rx_fb_nc_cnt;
-	u32 tx_bf_rx_fb_nr_cnt;
-	u32 tx_bf_fb_cpl_cnt;
-	u32 tx_bf_fb_trig_cnt;
-
-	u32 tx_ampdu_cnt;
-	u32 tx_stop_q_empty_cnt;
-	u32 tx_mpdu_attempts_cnt;
-	u32 tx_mpdu_success_cnt;
-	/* BF counter is PPDU-based, so remove MPDU-based BF counter */
-
-	u32 tx_rwp_fail_cnt;
-	u32 tx_rwp_need_cnt;
-
-	/* rx stats */
-	u32 rx_fifo_full_cnt;
-	u32 channel_idle_cnt;
-	u32 rx_vector_mismatch_cnt;
-	u32 rx_delimiter_fail_cnt;
-	u32 rx_len_mismatch_cnt;
-	u32 rx_mpdu_cnt;
-	u32 rx_ampdu_cnt;
-	u32 rx_ampdu_bytes_cnt;
-	u32 rx_ampdu_valid_subframe_cnt;
-	u32 rx_ampdu_valid_subframe_bytes_cnt;
-	u32 rx_pfdrop_cnt;
-	u32 rx_vec_queue_overflow_drop_cnt;
-	u32 rx_ba_cnt;
-
-	u32 tx_amsdu[8];
-	u32 tx_amsdu_cnt;
-};
-
 /* crash-dump */
 struct mt7996_crash_data {
 	guid_t guid;
@@ -222,7 +168,7 @@ struct mt7996_phy {
 	u32 rx_ampdu_ts;
 	u32 ampdu_ref;
 
-	struct mib_stats mib;
+	struct mt76_mib_stats mib;
 	struct mt76_channel_state state_ts;
 };
 
-- 
GitLab


From 52a1f158b3ff76d6501c061e3c6952801a2dc9a7 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 13 May 2023 00:29:55 +0200
Subject: [PATCH 0396/1806] wifi: mt76: mt7921: rely on mib_stats shared
 definition

Get rid of private copy of mib_stats structure.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7921/debugfs.c   |  2 +-
 .../net/wireless/mediatek/mt76/mt7921/mac.c   |  2 +-
 .../net/wireless/mediatek/mt76/mt7921/main.c  |  4 +--
 .../wireless/mediatek/mt76/mt7921/mt7921.h    | 31 +------------------
 4 files changed, 5 insertions(+), 34 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
index d6b6edba2fece..d6c66e775536c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
@@ -95,7 +95,7 @@ mt7921_tx_stats_show(struct seq_file *file, void *data)
 {
 	struct mt7921_dev *dev = file->private;
 	struct mt7921_phy *phy = &dev->phy;
-	struct mib_stats *mib = &phy->mib;
+	struct mt76_mib_stats *mib = &phy->mib;
 	int i;
 
 	mt7921_mutex_acquire(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index a671c601c5836..a2e9d7b654c51 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -952,8 +952,8 @@ EXPORT_SYMBOL_GPL(mt7921_reset);
 
 void mt7921_mac_update_mib_stats(struct mt7921_phy *phy)
 {
+	struct mt76_mib_stats *mib = &phy->mib;
 	struct mt7921_dev *dev = phy->dev;
-	struct mib_stats *mib = &phy->mib;
 	int i, aggr0 = 0, aggr1;
 	u32 val;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 0e3ada1e008cd..d183982c0b407 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -995,7 +995,7 @@ mt7921_get_stats(struct ieee80211_hw *hw,
 		 struct ieee80211_low_level_stats *stats)
 {
 	struct mt7921_phy *phy = mt7921_hw_phy(hw);
-	struct mib_stats *mib = &phy->mib;
+	struct mt76_mib_stats *mib = &phy->mib;
 
 	mt7921_mutex_acquire(phy->dev);
 
@@ -1133,7 +1133,7 @@ void mt7921_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	int stats_size = ARRAY_SIZE(mt7921_gstrings_stats);
 	struct mt7921_phy *phy = mt7921_hw_phy(hw);
 	struct mt7921_dev *dev = phy->dev;
-	struct mib_stats *mib = &phy->mib;
+	struct mt76_mib_stats *mib = &phy->mib;
 	struct mt76_ethtool_worker_info wi = {
 		.data = data,
 		.idx = mvif->mt76.idx,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 149acb1662d5d..76dc2538b9152 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -179,35 +179,6 @@ struct mt7921_vif {
 	struct ieee80211_chanctx_conf *ctx;
 };
 
-struct mib_stats {
-	u32 ack_fail_cnt;
-	u32 fcs_err_cnt;
-	u32 rts_cnt;
-	u32 rts_retries_cnt;
-	u32 ba_miss_cnt;
-
-	u32 tx_bf_ibf_ppdu_cnt;
-	u32 tx_bf_ebf_ppdu_cnt;
-	u32 tx_bf_rx_fb_all_cnt;
-	u32 tx_bf_rx_fb_he_cnt;
-	u32 tx_bf_rx_fb_vht_cnt;
-	u32 tx_bf_rx_fb_ht_cnt;
-
-	u32 tx_ampdu_cnt;
-	u32 tx_mpdu_attempts_cnt;
-	u32 tx_mpdu_success_cnt;
-	u32 tx_pkt_ebf_cnt;
-	u32 tx_pkt_ibf_cnt;
-
-	u32 rx_mpdu_cnt;
-	u32 rx_ampdu_cnt;
-	u32 rx_ampdu_bytes_cnt;
-	u32 rx_ba_cnt;
-
-	u32 tx_amsdu[8];
-	u32 tx_amsdu_cnt;
-};
-
 enum {
 	MT7921_CLC_POWER,
 	MT7921_CLC_CHAN,
@@ -247,7 +218,7 @@ struct mt7921_phy {
 	u32 rx_ampdu_ts;
 	u32 ampdu_ref;
 
-	struct mib_stats mib;
+	struct mt76_mib_stats mib;
 
 	u8 sta_work_count;
 
-- 
GitLab


From 7a01cad9f967d545feaf6999ee6f4a01bef400d8 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Mon, 15 May 2023 15:25:59 +0200
Subject: [PATCH 0397/1806] dt-bindings: net: wireless: mt76: add bindings for
 MT7981

Add mediatek,mt7981-wmac compatible string entry.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../devicetree/bindings/net/wireless/mediatek,mt76.yaml          | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml
index 67b63f119f642..9081731611ef2 100644
--- a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml
@@ -28,6 +28,7 @@ properties:
       - mediatek,mt76
       - mediatek,mt7628-wmac
       - mediatek,mt7622-wmac
+      - mediatek,mt7981-wmac
       - mediatek,mt7986-wmac
 
   reg:
-- 
GitLab


From 6bad146d162e92174b09522b357b64f8fda95246 Mon Sep 17 00:00:00 2001
From: Alexander Couzens <lynxis@fe80.eu>
Date: Mon, 15 May 2023 15:27:12 +0200
Subject: [PATCH 0398/1806] wifi: mt76: mt7915: add support for MT7981

Add support for the MediaTek MT7981 SoC which is similar to the MT7986
but with a newer IP cores and only 2x ARM Cortex-A53 instead of 4x.
Unlike MT7986 the MT7981 can only connect a single wireless frontend,
usually MT7976 is used for DBDC.

Signed-off-by: Alexander Couzens <lynxis@fe80.eu>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt76_connac.h  |  10 ++
 .../net/wireless/mediatek/mt76/mt7915/Kconfig |   6 +-
 .../wireless/mediatek/mt76/mt7915/Makefile    |   2 +-
 .../wireless/mediatek/mt76/mt7915/coredump.c  |   7 +-
 .../net/wireless/mediatek/mt76/mt7915/dma.c   |   6 +-
 .../wireless/mediatek/mt76/mt7915/eeprom.c    |   7 +-
 .../net/wireless/mediatek/mt76/mt7915/init.c  |   6 +-
 .../net/wireless/mediatek/mt76/mt7915/mac.c   |   2 +-
 .../net/wireless/mediatek/mt76/mt7915/mcu.c   |   3 +
 .../net/wireless/mediatek/mt76/mt7915/mmio.c  |  17 +-
 .../wireless/mediatek/mt76/mt7915/mt7915.h    |  14 +-
 .../net/wireless/mediatek/mt76/mt7915/regs.h  |  13 +-
 .../net/wireless/mediatek/mt76/mt7915/soc.c   | 162 ++++++++++++------
 13 files changed, 179 insertions(+), 76 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac.h
index 15653b274f83c..77ca8f057d615 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac.h
@@ -197,11 +197,21 @@ static inline bool is_mt7916(struct mt76_dev *dev)
 	return mt76_chip(dev) == 0x7906;
 }
 
+static inline bool is_mt7981(struct mt76_dev *dev)
+{
+	return mt76_chip(dev) == 0x7981;
+}
+
 static inline bool is_mt7986(struct mt76_dev *dev)
 {
 	return mt76_chip(dev) == 0x7986;
 }
 
+static inline bool is_mt798x(struct mt76_dev *dev)
+{
+	return is_mt7981(dev) || is_mt7986(dev);
+}
+
 static inline bool is_mt7996(struct mt76_dev *dev)
 {
 	return mt76_chip(dev) == 0x7990;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig b/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig
index d710726d47bfd..896ec38c23d9b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig
@@ -14,12 +14,12 @@ config MT7915E
 
 	  To compile this driver as a module, choose M here.
 
-config MT7986_WMAC
-	bool "MT7986 (SoC) WMAC support"
+config MT798X_WMAC
+	bool "MT798x (SoC) WMAC support"
 	depends on MT7915E
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	select REGMAP
 	help
-	  This adds support for the built-in WMAC on MT7986 SoC device
+	  This adds support for the built-in WMAC on MT7981 and MT7986 SoC device
 	  which has the same feature set as a MT7915, but enables 6E
 	  support.
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/Makefile b/drivers/net/wireless/mediatek/mt76/mt7915/Makefile
index 797ae49805c3d..e0ca638c91a5d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/Makefile
@@ -6,5 +6,5 @@ mt7915e-y := pci.o init.o dma.o eeprom.o main.o mcu.o mac.o \
 	     debugfs.o mmio.o
 
 mt7915e-$(CONFIG_NL80211_TESTMODE) += testmode.o
-mt7915e-$(CONFIG_MT7986_WMAC) += soc.o
+mt7915e-$(CONFIG_MT798X_WMAC) += soc.o
 mt7915e-$(CONFIG_DEV_COREDUMP) += coredump.o
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/coredump.c b/drivers/net/wireless/mediatek/mt76/mt7915/coredump.c
index d097a56dd33d1..5daf2258dfe6f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/coredump.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/coredump.c
@@ -52,7 +52,7 @@ static const struct mt7915_mem_region mt7916_mem_regions[] = {
 	},
 };
 
-static const struct mt7915_mem_region mt7986_mem_regions[] = {
+static const struct mt7915_mem_region mt798x_mem_regions[] = {
 	{
 		.start = 0x00800000,
 		.len = 0x0005ffff,
@@ -92,9 +92,10 @@ mt7915_coredump_get_mem_layout(struct mt7915_dev *dev, u32 *num)
 	case 0x7915:
 		*num = ARRAY_SIZE(mt7915_mem_regions);
 		return &mt7915_mem_regions[0];
+	case 0x7981:
 	case 0x7986:
-		*num = ARRAY_SIZE(mt7986_mem_regions);
-		return &mt7986_mem_regions[0];
+		*num = ARRAY_SIZE(mt798x_mem_regions);
+		return &mt798x_mem_regions[0];
 	case 0x7916:
 		*num = ARRAY_SIZE(mt7916_mem_regions);
 		return &mt7916_mem_regions[0];
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
index 43a5456d4b972..86a93dedb1bf5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
@@ -11,7 +11,7 @@ mt7915_init_tx_queues(struct mt7915_phy *phy, int idx, int n_desc, int ring_base
 	struct mt7915_dev *dev = phy->dev;
 
 	if (mtk_wed_device_active(&phy->dev->mt76.mmio.wed)) {
-		if (is_mt7986(&dev->mt76))
+		if (is_mt798x(&dev->mt76))
 			ring_base += MT_TXQ_ID(0) * MT_RING_SIZE;
 		else
 			ring_base = MT_WED_TX_RING_BASE;
@@ -370,7 +370,7 @@ static int mt7915_dma_enable(struct mt7915_dev *dev)
 		int ret;
 
 		wed_irq_mask |= MT_INT_TX_DONE_BAND0 | MT_INT_TX_DONE_BAND1;
-		if (!is_mt7986(&dev->mt76))
+		if (!is_mt798x(&dev->mt76))
 			mt76_wr(dev, MT_INT_WED_MASK_CSR, wed_irq_mask);
 		else
 			mt76_wr(dev, MT_INT_MASK_CSR, wed_irq_mask);
@@ -404,7 +404,7 @@ int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2)
 	mt7915_dma_disable(dev, true);
 
 	if (mtk_wed_device_active(&mdev->mmio.wed)) {
-		if (!is_mt7986(mdev)) {
+		if (!is_mt798x(mdev)) {
 			u8 wed_control_rx1 = is_mt7915(mdev) ? 1 : 2;
 
 			mt76_set(dev, MT_WFDMA_HOST_CONFIG,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
index a79628933948d..76be7308460b0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
@@ -39,6 +39,8 @@ static int mt7915_check_eeprom(struct mt7915_dev *dev)
 		return CHECK_EEPROM_ERR(is_mt7915(&dev->mt76));
 	case 0x7916:
 		return CHECK_EEPROM_ERR(is_mt7916(&dev->mt76));
+	case 0x7981:
+		return CHECK_EEPROM_ERR(is_mt7981(&dev->mt76));
 	case 0x7986:
 		return CHECK_EEPROM_ERR(is_mt7986(&dev->mt76));
 	default:
@@ -52,6 +54,9 @@ static char *mt7915_eeprom_name(struct mt7915_dev *dev)
 	case 0x7915:
 		return dev->dbdc_support ?
 		       MT7915_EEPROM_DEFAULT_DBDC : MT7915_EEPROM_DEFAULT;
+	case 0x7981:
+		/* mt7981 only supports mt7976 and only in DBDC mode */
+		return MT7981_EEPROM_MT7976_DEFAULT_DBDC;
 	case 0x7986:
 		switch (mt7915_check_adie(dev, true)) {
 		case MT7976_ONE_ADIE_DBDC:
@@ -215,7 +220,7 @@ void mt7915_eeprom_parse_hw_cap(struct mt7915_dev *dev,
 					eeprom[MT_EE_WIFI_CONF + 2 + band]);
 		}
 
-		if (!is_mt7986(&dev->mt76))
+		if (!is_mt798x(&dev->mt76))
 			nss_max = 2;
 	}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index 30c552a5f9206..07cdf14c515f8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -740,7 +740,7 @@ void mt7915_wfsys_reset(struct mt7915_dev *dev)
 		mt76_clear(dev, MT_TOP_MISC, MT_TOP_MISC_FW_STATE);
 
 		msleep(100);
-	} else if (is_mt7986(&dev->mt76)) {
+	} else if (is_mt798x(&dev->mt76)) {
 		mt7986_wmac_disable(dev);
 		msleep(20);
 
@@ -761,7 +761,7 @@ static bool mt7915_band_config(struct mt7915_dev *dev)
 
 	dev->phy.mt76->band_idx = 0;
 
-	if (is_mt7986(&dev->mt76)) {
+	if (is_mt798x(&dev->mt76)) {
 		u32 sku = mt7915_check_adie(dev, true);
 
 		/*
@@ -1170,7 +1170,7 @@ static void mt7915_stop_hardware(struct mt7915_dev *dev)
 	mt7915_dma_cleanup(dev);
 	tasklet_disable(&dev->mt76.irq_tasklet);
 
-	if (is_mt7986(&dev->mt76))
+	if (is_mt798x(&dev->mt76))
 		mt7986_wmac_disable(dev);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 9e5eb0bfeb260..14ea42732dedc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1594,7 +1594,7 @@ void mt7915_mac_reset_work(struct work_struct *work)
 
 	if (mtk_wed_device_active(&dev->mt76.mmio.wed)) {
 		mtk_wed_device_stop(&dev->mt76.mmio.wed);
-		if (!is_mt7986(&dev->mt76))
+		if (!is_mt798x(&dev->mt76))
 			mt76_wr(dev, MT_INT_WED_MASK_CSR, 0);
 	}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 8da9c87e98042..c9716422c803a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -13,6 +13,9 @@
 	case 0x7915:						\
 		_fw = MT7915_##name;				\
 		break;						\
+	case 0x7981:						\
+		_fw = MT7981_##name;				\
+		break;						\
 	case 0x7986:						\
 		_fw = MT7986_##name##__VA_ARGS__;		\
 		break;						\
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index 2fa059af23ded..fc7ace638ce8e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -417,7 +417,7 @@ static u32 mt7915_reg_map_l1(struct mt7915_dev *dev, u32 addr)
 	u32 base = FIELD_GET(MT_HIF_REMAP_L1_BASE, addr);
 	u32 l1_remap;
 
-	if (is_mt7986(&dev->mt76))
+	if (is_mt798x(&dev->mt76))
 		return MT_CONN_INFRA_OFFSET(addr);
 
 	l1_remap = is_mt7915(&dev->mt76) ?
@@ -447,7 +447,7 @@ static u32 mt7915_reg_map_l2(struct mt7915_dev *dev, u32 addr)
 		/* use read to push write */
 		dev->bus_ops->rr(&dev->mt76, MT_HIF_REMAP_L2);
 	} else {
-		u32 ofs = is_mt7986(&dev->mt76) ? 0x400000 : 0;
+		u32 ofs = is_mt798x(&dev->mt76) ? 0x400000 : 0;
 
 		offset = FIELD_GET(MT_HIF_REMAP_L2_OFFSET_MT7916, addr);
 		base = FIELD_GET(MT_HIF_REMAP_L2_BASE_MT7916, addr);
@@ -759,7 +759,7 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr,
 	wed->wlan.nbuf = MT7915_HW_TOKEN_SIZE;
 	wed->wlan.tx_tbit[0] = is_mt7915(&dev->mt76) ? 4 : 30;
 	wed->wlan.tx_tbit[1] = is_mt7915(&dev->mt76) ? 5 : 31;
-	wed->wlan.txfree_tbit = is_mt7986(&dev->mt76) ? 2 : 1;
+	wed->wlan.txfree_tbit = is_mt798x(&dev->mt76) ? 2 : 1;
 	wed->wlan.token_start = MT7915_TOKEN_SIZE - wed->wlan.nbuf;
 	wed->wlan.wcid_512 = !is_mt7915(&dev->mt76);
 
@@ -769,7 +769,7 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr,
 	if (is_mt7915(&dev->mt76)) {
 		wed->wlan.rx_tbit[0] = 16;
 		wed->wlan.rx_tbit[1] = 17;
-	} else if (is_mt7986(&dev->mt76)) {
+	} else if (is_mt798x(&dev->mt76)) {
 		wed->wlan.rx_tbit[0] = 22;
 		wed->wlan.rx_tbit[1] = 23;
 	} else {
@@ -827,6 +827,7 @@ static int mt7915_mmio_init(struct mt76_dev *mdev,
 		dev->reg.map = mt7916_reg_map;
 		dev->reg.map_size = ARRAY_SIZE(mt7916_reg_map);
 		break;
+	case 0x7981:
 	case 0x7986:
 		dev->reg.reg_rev = mt7986_reg;
 		dev->reg.offs_rev = mt7916_offs;
@@ -1036,8 +1037,8 @@ static int __init mt7915_init(void)
 	if (ret)
 		goto error_pci;
 
-	if (IS_ENABLED(CONFIG_MT7986_WMAC)) {
-		ret = platform_driver_register(&mt7986_wmac_driver);
+	if (IS_ENABLED(CONFIG_MT798X_WMAC)) {
+		ret = platform_driver_register(&mt798x_wmac_driver);
 		if (ret)
 			goto error_wmac;
 	}
@@ -1054,8 +1055,8 @@ error_pci:
 
 static void __exit mt7915_exit(void)
 {
-	if (IS_ENABLED(CONFIG_MT7986_WMAC))
-		platform_driver_unregister(&mt7986_wmac_driver);
+	if (IS_ENABLED(CONFIG_MT798X_WMAC))
+		platform_driver_unregister(&mt798x_wmac_driver);
 
 	pci_unregister_driver(&mt7915_pci_driver);
 	pci_unregister_driver(&mt7915_hif_driver);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index 41e0aafae9f8a..736f5fbfafc5c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -34,6 +34,10 @@
 #define MT7916_FIRMWARE_WM		"mediatek/mt7916_wm.bin"
 #define MT7916_ROM_PATCH		"mediatek/mt7916_rom_patch.bin"
 
+#define MT7981_FIRMWARE_WA		"mediatek/mt7981_wa.bin"
+#define MT7981_FIRMWARE_WM		"mediatek/mt7981_wm.bin"
+#define MT7981_ROM_PATCH		"mediatek/mt7981_rom_patch.bin"
+
 #define MT7986_FIRMWARE_WA		"mediatek/mt7986_wa.bin"
 #define MT7986_FIRMWARE_WM		"mediatek/mt7986_wm.bin"
 #define MT7986_FIRMWARE_WM_MT7975	"mediatek/mt7986_wm_mt7975.bin"
@@ -43,6 +47,9 @@
 #define MT7915_EEPROM_DEFAULT		"mediatek/mt7915_eeprom.bin"
 #define MT7915_EEPROM_DEFAULT_DBDC	"mediatek/mt7915_eeprom_dbdc.bin"
 #define MT7916_EEPROM_DEFAULT		"mediatek/mt7916_eeprom.bin"
+
+#define MT7981_EEPROM_MT7976_DEFAULT_DBDC	"mediatek/mt7981_eeprom_mt7976_dbdc.bin"
+
 #define MT7986_EEPROM_MT7975_DEFAULT		"mediatek/mt7986_eeprom_mt7975.bin"
 #define MT7986_EEPROM_MT7975_DUAL_DEFAULT	"mediatek/mt7986_eeprom_mt7975_dual.bin"
 #define MT7986_EEPROM_MT7976_DEFAULT		"mediatek/mt7986_eeprom_mt7976.bin"
@@ -359,8 +366,7 @@ mt7915_ext_phy(struct mt7915_dev *dev)
 static inline u32 mt7915_check_adie(struct mt7915_dev *dev, bool sku)
 {
 	u32 mask = sku ? MT_CONNINFRA_SKU_MASK : MT_ADIE_TYPE_MASK;
-
-	if (!is_mt7986(&dev->mt76))
+	if (!is_mt798x(&dev->mt76))
 		return 0;
 
 	return mt76_rr(dev, MT_CONNINFRA_SKU_DEC_ADDR) & mask;
@@ -370,9 +376,9 @@ extern const struct ieee80211_ops mt7915_ops;
 extern const struct mt76_testmode_ops mt7915_testmode_ops;
 extern struct pci_driver mt7915_pci_driver;
 extern struct pci_driver mt7915_hif_driver;
-extern struct platform_driver mt7986_wmac_driver;
+extern struct platform_driver mt798x_wmac_driver;
 
-#ifdef CONFIG_MT7986_WMAC
+#ifdef CONFIG_MT798X_WMAC
 int mt7986_wmac_enable(struct mt7915_dev *dev);
 void mt7986_wmac_disable(struct mt7915_dev *dev);
 #else
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h
index 71fa9576ad0e7..588cd87e24e9b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h
@@ -874,7 +874,12 @@ enum offs_rev {
 #define MT_AFE_RG_WBG_EN_WPLL_UP_MASK	BIT(20)
 #define MT_AFE_RG_WBG_EN_PLL_UP_MASK	(MT_AFE_RG_WBG_EN_BPLL_UP_MASK | \
 					 MT_AFE_RG_WBG_EN_WPLL_UP_MASK)
-#define MT_AFE_RG_WBG_EN_TXCAL_MASK	GENMASK(21, 17)
+#define MT_AFE_RG_WBG_EN_TXCAL_WF4	BIT(29)
+#define MT_AFE_RG_WBG_EN_TXCAL_BT	BIT(21)
+#define MT_AFE_RG_WBG_EN_TXCAL_WF3	BIT(20)
+#define MT_AFE_RG_WBG_EN_TXCAL_WF2	BIT(19)
+#define MT_AFE_RG_WBG_EN_TXCAL_WF1	BIT(18)
+#define MT_AFE_RG_WBG_EN_TXCAL_WF0	BIT(17)
 
 #define MT_ADIE_SLP_CTRL_BASE(_band)	(0x18005000 + ((_band) << 19))
 #define MT_ADIE_SLP_CTRL(_band, ofs)	(MT_ADIE_SLP_CTRL_BASE(_band) + (ofs))
@@ -1099,6 +1104,12 @@ enum offs_rev {
 #define MT_TOP_MCU_EMI_BASE		MT_TOP(0x1c4)
 #define MT_TOP_MCU_EMI_BASE_MASK	GENMASK(19, 0)
 
+#define MT_TOP_WF_AP_PERI_BASE		MT_TOP(0x1c8)
+#define MT_TOP_WF_AP_PERI_BASE_MASK	GENMASK(19, 0)
+
+#define MT_TOP_EFUSE_BASE		MT_TOP(0x1cc)
+#define MT_TOP_EFUSE_BASE_MASK		GENMASK(19, 0)
+
 #define MT_TOP_CONN_INFRA_WAKEUP	MT_TOP(0x1a0)
 #define MT_TOP_CONN_INFRA_WAKEUP_MASK	BIT(0)
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/soc.c b/drivers/net/wireless/mediatek/mt76/mt7915/soc.c
index 32c137066e7f7..1f23e60f97140 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/soc.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/soc.c
@@ -16,6 +16,9 @@
 
 #include "mt7915.h"
 
+#define MT7981_CON_INFRA_VERSION 0x02090000
+#define MT7986_CON_INFRA_VERSION 0x02070000
+
 /* INFRACFG */
 #define MT_INFRACFG_CONN2AP_SLPPROT	0x0d0
 #define MT_INFRACFG_AP2CONN_SLPPROT	0x0d4
@@ -167,10 +170,14 @@ static u32 mt76_wmac_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
 	return val;
 }
 
-static u8 mt7986_wmac_check_adie_type(struct mt7915_dev *dev)
+static u8 mt798x_wmac_check_adie_type(struct mt7915_dev *dev)
 {
 	u32 val;
 
+	/* Only DBDC A-die is used with MT7981 */
+	if (is_mt7981(&dev->mt76))
+		return ADIE_DBDC;
+
 	val = readl(dev->sku + MT_TOP_POS_SKU);
 
 	return FIELD_GET(MT_TOP_POS_SKU_ADIE_DBDC_MASK, val);
@@ -195,7 +202,7 @@ static int mt7986_wmac_gpio_setup(struct mt7915_dev *dev)
 	int ret;
 	u8 type;
 
-	type = mt7986_wmac_check_adie_type(dev);
+	type = mt798x_wmac_check_adie_type(dev);
 	pinctrl = devm_pinctrl_get(dev->mt76.dev);
 	if (IS_ERR(pinctrl))
 		return PTR_ERR(pinctrl);
@@ -257,16 +264,26 @@ static int mt7986_wmac_consys_lockup(struct mt7915_dev *dev, bool enable)
 	return 0;
 }
 
-static int mt7986_wmac_coninfra_check(struct mt7915_dev *dev)
+static int mt798x_wmac_coninfra_check(struct mt7915_dev *dev)
 {
 	u32 cur;
+	u32 con_infra_version;
+
+	if (is_mt7981(&dev->mt76)) {
+		con_infra_version = MT7981_CON_INFRA_VERSION;
+	} else if (is_mt7986(&dev->mt76)) {
+		con_infra_version = MT7986_CON_INFRA_VERSION;
+	} else {
+		WARN_ON(1);
+		return -EINVAL;
+	}
 
-	return read_poll_timeout(mt76_rr, cur, (cur == 0x02070000),
+	return read_poll_timeout(mt76_rr, cur, (cur == con_infra_version),
 				 USEC_PER_MSEC, 50 * USEC_PER_MSEC,
 				 false, dev, MT_CONN_INFRA_BASE);
 }
 
-static int mt7986_wmac_coninfra_setup(struct mt7915_dev *dev)
+static int mt798x_wmac_coninfra_setup(struct mt7915_dev *dev)
 {
 	struct device *pdev = dev->mt76.dev;
 	struct reserved_mem *rmem;
@@ -284,15 +301,25 @@ static int mt7986_wmac_coninfra_setup(struct mt7915_dev *dev)
 
 	val = (rmem->base >> 16) & MT_TOP_MCU_EMI_BASE_MASK;
 
-	/* Set conninfra subsys PLL check */
-	mt76_rmw_field(dev, MT_INFRA_CKGEN_BUS,
-		       MT_INFRA_CKGEN_BUS_RDY_SEL_MASK, 0x1);
-	mt76_rmw_field(dev, MT_INFRA_CKGEN_BUS,
-		       MT_INFRA_CKGEN_BUS_RDY_SEL_MASK, 0x1);
+	if (is_mt7986(&dev->mt76)) {
+		/* Set conninfra subsys PLL check */
+		mt76_rmw_field(dev, MT_INFRA_CKGEN_BUS,
+			       MT_INFRA_CKGEN_BUS_RDY_SEL_MASK, 0x1);
+		mt76_rmw_field(dev, MT_INFRA_CKGEN_BUS,
+			       MT_INFRA_CKGEN_BUS_RDY_SEL_MASK, 0x1);
+	}
 
 	mt76_rmw_field(dev, MT_TOP_MCU_EMI_BASE,
 		       MT_TOP_MCU_EMI_BASE_MASK, val);
 
+	if (is_mt7981(&dev->mt76)) {
+		mt76_rmw_field(dev, MT_TOP_WF_AP_PERI_BASE,
+			       MT_TOP_WF_AP_PERI_BASE_MASK, 0x300d0000 >> 16);
+
+		mt76_rmw_field(dev, MT_TOP_EFUSE_BASE,
+			       MT_TOP_EFUSE_BASE_MASK, 0x11f20000 >> 16);
+	}
+
 	mt76_wr(dev, MT_INFRA_BUS_EMI_START, rmem->base);
 	mt76_wr(dev, MT_INFRA_BUS_EMI_END, rmem->size);
 
@@ -305,15 +332,18 @@ static int mt7986_wmac_coninfra_setup(struct mt7915_dev *dev)
 	return 0;
 }
 
-static int mt7986_wmac_sku_setup(struct mt7915_dev *dev, u32 *adie_type)
+static int mt798x_wmac_sku_setup(struct mt7915_dev *dev, u32 *adie_type)
 {
 	int ret;
-	u32 adie_main, adie_ext;
+	u32 adie_main = 0, adie_ext = 0;
 
 	mt76_rmw_field(dev, MT_CONN_INFRA_ADIE_RESET,
 		       MT_CONN_INFRA_ADIE1_RESET_MASK, 0x1);
-	mt76_rmw_field(dev, MT_CONN_INFRA_ADIE_RESET,
-		       MT_CONN_INFRA_ADIE2_RESET_MASK, 0x1);
+
+	if (is_mt7986(&dev->mt76)) {
+		mt76_rmw_field(dev, MT_CONN_INFRA_ADIE_RESET,
+			       MT_CONN_INFRA_ADIE2_RESET_MASK, 0x1);
+	}
 
 	mt76_wmac_spi_lock(dev);
 
@@ -321,9 +351,11 @@ static int mt7986_wmac_sku_setup(struct mt7915_dev *dev, u32 *adie_type)
 	if (ret)
 		goto out;
 
-	ret = mt76_wmac_spi_read(dev, 1, MT_ADIE_CHIP_ID, &adie_ext);
-	if (ret)
-		goto out;
+	if (is_mt7986(&dev->mt76)) {
+		ret = mt76_wmac_spi_read(dev, 1, MT_ADIE_CHIP_ID, &adie_ext);
+		if (ret)
+			goto out;
+	}
 
 	*adie_type = FIELD_GET(MT_ADIE_CHIP_ID_MASK, adie_main) |
 		     (MT_ADIE_CHIP_ID_MASK & adie_ext);
@@ -470,7 +502,7 @@ static int mt7986_wmac_adie_xtal_trim_7976(struct mt7915_dev *dev, u8 adie)
 	return ret;
 }
 
-static int mt7986_wmac_adie_patch_7976(struct mt7915_dev *dev, u8 adie)
+static int mt798x_wmac_adie_patch_7976(struct mt7915_dev *dev, u8 adie)
 {
 	u32 id, version, rg_xo_01, rg_xo_03;
 	int ret;
@@ -489,7 +521,14 @@ static int mt7986_wmac_adie_patch_7976(struct mt7915_dev *dev, u8 adie)
 		rg_xo_01 = 0x1d59080f;
 		rg_xo_03 = 0x34c00fe0;
 	} else {
-		rg_xo_01 = 0x1959f80f;
+		if (is_mt7981(&dev->mt76)) {
+			rg_xo_01 = 0x1959c80f;
+		} else if (is_mt7986(&dev->mt76)) {
+			rg_xo_01 = 0x1959f80f;
+		} else {
+			WARN_ON(1);
+			return -EINVAL;
+		}
 		rg_xo_03 = 0x34d00fe0;
 	}
 
@@ -611,7 +650,15 @@ static int mt7986_wmac_adie_patch_7975(struct mt7915_dev *dev, u8 adie)
 		return ret;
 
 	/* turn on SX0 LTBUF */
-	ret = mt76_wmac_spi_write(dev, adie, 0x074, 0x00000002);
+	if (is_mt7981(&dev->mt76)) {
+		ret = mt76_wmac_spi_write(dev, adie, 0x074, 0x00000007);
+	} else if (is_mt7986(&dev->mt76)) {
+		ret = mt76_wmac_spi_write(dev, adie, 0x074, 0x00000002);
+	} else {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
 	if (ret)
 		return ret;
 
@@ -658,7 +705,10 @@ static int mt7986_wmac_adie_patch_7975(struct mt7915_dev *dev, u8 adie)
 		return ret;
 
 	/* set CKB driving and filter */
-	return mt76_wmac_spi_write(dev, adie, 0x2c8, 0x00000072);
+	if (is_mt7986(&dev->mt76))
+		return mt76_wmac_spi_write(dev, adie, 0x2c8, 0x00000072);
+
+	return ret;
 }
 
 static int mt7986_wmac_adie_cfg(struct mt7915_dev *dev, u8 adie, u32 adie_type)
@@ -686,7 +736,7 @@ static int mt7986_wmac_adie_cfg(struct mt7915_dev *dev, u8 adie, u32 adie_type)
 
 		ret = mt7986_wmac_adie_patch_7975(dev, adie);
 	} else if (is_7976(dev, adie, adie_type)) {
-		if (mt7986_wmac_check_adie_type(dev) == ADIE_DBDC) {
+		if (mt798x_wmac_check_adie_type(dev) == ADIE_DBDC) {
 			ret = mt76_wmac_spi_write(dev, adie,
 						  MT_ADIE_WRI_CK_SEL, 0x1c);
 			if (ret)
@@ -701,7 +751,7 @@ static int mt7986_wmac_adie_cfg(struct mt7915_dev *dev, u8 adie, u32 adie_type)
 		if (ret)
 			goto out;
 
-		ret = mt7986_wmac_adie_patch_7976(dev, adie);
+		ret = mt798x_wmac_adie_patch_7976(dev, adie);
 	}
 out:
 	mt76_wmac_spi_unlock(dev);
@@ -714,6 +764,7 @@ mt7986_wmac_afe_cal(struct mt7915_dev *dev, u8 adie, bool dbdc, u32 adie_type)
 {
 	int ret;
 	u8 idx;
+	u32 txcal;
 
 	mt76_wmac_spi_lock(dev);
 	if (is_7975(dev, adie, adie_type))
@@ -744,12 +795,18 @@ mt7986_wmac_afe_cal(struct mt7915_dev *dev, u8 adie, bool dbdc, u32 adie_type)
 		       MT_AFE_RG_WBG_EN_WPLL_UP_MASK, 0x1);
 	usleep_range(60, 100);
 
-	mt76_rmw_field(dev, MT_AFE_DIG_EN_01(idx),
-		       MT_AFE_RG_WBG_EN_TXCAL_MASK, 0x1f);
+	txcal = (MT_AFE_RG_WBG_EN_TXCAL_BT |
+		      MT_AFE_RG_WBG_EN_TXCAL_WF0 |
+		      MT_AFE_RG_WBG_EN_TXCAL_WF1 |
+		      MT_AFE_RG_WBG_EN_TXCAL_WF2 |
+		      MT_AFE_RG_WBG_EN_TXCAL_WF3);
+	if (is_mt7981(&dev->mt76))
+		txcal |= MT_AFE_RG_WBG_EN_TXCAL_WF4;
+
+	mt76_set(dev, MT_AFE_DIG_EN_01(idx), txcal);
 	usleep_range(800, 1000);
 
-	mt76_rmw(dev, MT_AFE_DIG_EN_01(idx),
-		 MT_AFE_RG_WBG_EN_TXCAL_MASK, 0x0);
+	mt76_clear(dev, MT_AFE_DIG_EN_01(idx), txcal);
 	mt76_rmw(dev, MT_AFE_DIG_EN_03(idx),
 		 MT_AFE_RG_WBG_EN_PLL_UP_MASK, 0x0);
 
@@ -806,7 +863,7 @@ static int mt7986_wmac_bus_timeout(struct mt7915_dev *dev)
 	mt76_rmw_field(dev, MT_INFRA_BUS_ON_TIMEOUT,
 		       MT_INFRA_BUS_TIMEOUT_EN_MASK, 0xf);
 
-	return mt7986_wmac_coninfra_check(dev);
+	return mt798x_wmac_coninfra_check(dev);
 }
 
 static void mt7986_wmac_clock_enable(struct mt7915_dev *dev, u32 adie_type)
@@ -876,14 +933,15 @@ static int mt7986_wmac_top_wfsys_wakeup(struct mt7915_dev *dev, bool enable)
 	if (!enable)
 		return 0;
 
-	return mt7986_wmac_coninfra_check(dev);
+	return mt798x_wmac_coninfra_check(dev);
 }
 
 static int mt7986_wmac_wm_enable(struct mt7915_dev *dev, bool enable)
 {
 	u32 cur;
 
-	mt76_wr(dev, MT_CONNINFRA_SKU_DEC_ADDR, 0);
+	if (is_mt7986(&dev->mt76))
+		mt76_wr(dev, MT_CONNINFRA_SKU_DEC_ADDR, 0);
 
 	mt76_rmw_field(dev, MT7986_TOP_WM_RESET,
 		       MT7986_TOP_WM_RESET_MASK, enable);
@@ -1006,7 +1064,7 @@ mt7986_wmac_adie_setup(struct mt7915_dev *dev, u8 adie, u32 adie_type)
 	if (ret)
 		return ret;
 
-	if (!adie && (mt7986_wmac_check_adie_type(dev) == ADIE_DBDC))
+	if (!adie && (mt798x_wmac_check_adie_type(dev) == ADIE_DBDC))
 		ret = mt7986_wmac_afe_cal(dev, adie, true, adie_type);
 
 	return ret;
@@ -1061,15 +1119,15 @@ int mt7986_wmac_enable(struct mt7915_dev *dev)
 	if (ret)
 		return ret;
 
-	ret = mt7986_wmac_coninfra_check(dev);
+	ret = mt798x_wmac_coninfra_check(dev);
 	if (ret)
 		return ret;
 
-	ret = mt7986_wmac_coninfra_setup(dev);
+	ret = mt798x_wmac_coninfra_setup(dev);
 	if (ret)
 		return ret;
 
-	ret = mt7986_wmac_sku_setup(dev, &adie_type);
+	ret = mt798x_wmac_sku_setup(dev, &adie_type);
 	if (ret)
 		return ret;
 
@@ -1077,9 +1135,12 @@ int mt7986_wmac_enable(struct mt7915_dev *dev)
 	if (ret)
 		return ret;
 
-	ret = mt7986_wmac_adie_setup(dev, 1, adie_type);
-	if (ret)
-		return ret;
+	/* mt7981 doesn't support a second a-die */
+	if (is_mt7986(&dev->mt76)) {
+		ret = mt7986_wmac_adie_setup(dev, 1, adie_type);
+		if (ret)
+			return ret;
+	}
 
 	ret = mt7986_wmac_subsys_powerup(dev, adie_type);
 	if (ret)
@@ -1132,7 +1193,7 @@ void mt7986_wmac_disable(struct mt7915_dev *dev)
 	mt7986_wmac_consys_reset(dev, false);
 }
 
-static int mt7986_wmac_init(struct mt7915_dev *dev)
+static int mt798x_wmac_init(struct mt7915_dev *dev)
 {
 	struct device *pdev = dev->mt76.dev;
 	struct platform_device *pfdev = to_platform_device(pdev);
@@ -1165,7 +1226,7 @@ static int mt7986_wmac_init(struct mt7915_dev *dev)
 	return 0;
 }
 
-static int mt7986_wmac_probe(struct platform_device *pdev)
+static int mt798x_wmac_probe(struct platform_device *pdev)
 {
 	void __iomem *mem_base;
 	struct mt7915_dev *dev;
@@ -1203,7 +1264,7 @@ static int mt7986_wmac_probe(struct platform_device *pdev)
 	if (ret)
 		goto free_device;
 
-	ret = mt7986_wmac_init(dev);
+	ret = mt798x_wmac_init(dev);
 	if (ret)
 		goto free_irq;
 
@@ -1225,7 +1286,7 @@ free_device:
 	return ret;
 }
 
-static int mt7986_wmac_remove(struct platform_device *pdev)
+static int mt798x_wmac_remove(struct platform_device *pdev)
 {
 	struct mt7915_dev *dev = platform_get_drvdata(pdev);
 
@@ -1234,20 +1295,21 @@ static int mt7986_wmac_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id mt7986_wmac_of_match[] = {
+static const struct of_device_id mt798x_wmac_of_match[] = {
+	{ .compatible = "mediatek,mt7981-wmac", .data = (u32 *)0x7981 },
 	{ .compatible = "mediatek,mt7986-wmac", .data = (u32 *)0x7986 },
 	{},
 };
 
-MODULE_DEVICE_TABLE(of, mt7986_wmac_of_match);
+MODULE_DEVICE_TABLE(of, mt798x_wmac_of_match);
 
-struct platform_driver mt7986_wmac_driver = {
+struct platform_driver mt798x_wmac_driver = {
 	.driver = {
-		.name = "mt7986-wmac",
-		.of_match_table = mt7986_wmac_of_match,
+		.name = "mt798x-wmac",
+		.of_match_table = mt798x_wmac_of_match,
 	},
-	.probe = mt7986_wmac_probe,
-	.remove = mt7986_wmac_remove,
+	.probe = mt798x_wmac_probe,
+	.remove = mt798x_wmac_remove,
 };
 
 MODULE_FIRMWARE(MT7986_FIRMWARE_WA);
@@ -1255,3 +1317,7 @@ MODULE_FIRMWARE(MT7986_FIRMWARE_WM);
 MODULE_FIRMWARE(MT7986_FIRMWARE_WM_MT7975);
 MODULE_FIRMWARE(MT7986_ROM_PATCH);
 MODULE_FIRMWARE(MT7986_ROM_PATCH_MT7975);
+
+MODULE_FIRMWARE(MT7981_FIRMWARE_WA);
+MODULE_FIRMWARE(MT7981_FIRMWARE_WM);
+MODULE_FIRMWARE(MT7981_ROM_PATCH);
-- 
GitLab


From 9aecfa754c7fc12c3f7feb669aec2f744e83954a Mon Sep 17 00:00:00 2001
From: Deren Wu <deren.wu@mediatek.com>
Date: Mon, 15 May 2023 23:18:50 +0800
Subject: [PATCH 0399/1806] wifi: mt76: mt7921e: report tx retries/failed
 counts in tx free event

Get missing tx retries/failed counts from txfree done events and report
them via mt7921_sta_statistics().

Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Reviewed-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/mac.c       | 8 +++++++-
 drivers/net/wireless/mediatek/mt76/mt7921/main.c      | 6 ++++++
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h
index fabf637bdf7f9..bd2a92467a97f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h
@@ -34,7 +34,7 @@ enum {
 
 #define MT_TX_FREE_MSDU_CNT		GENMASK(9, 0)
 #define MT_TX_FREE_WLAN_ID		GENMASK(23, 14)
-#define MT_TX_FREE_LATENCY		GENMASK(12, 0)
+#define MT_TX_FREE_COUNT		GENMASK(12, 0)
 /* 0: success, others: dropped */
 #define MT_TX_FREE_STATUS		GENMASK(14, 13)
 #define MT_TX_FREE_MSDU_ID		GENMASK(30, 16)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index a2e9d7b654c51..2d3f394039f6f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -614,6 +614,7 @@ static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
 	struct mt76_dev *mdev = &dev->mt76;
 	struct mt76_txwi_cache *txwi;
 	struct ieee80211_sta *sta = NULL;
+	struct mt76_wcid *wcid = NULL;
 	struct sk_buff *skb, *tmp;
 	void *end = data + len;
 	LIST_HEAD(free_list);
@@ -637,7 +638,6 @@ static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
 		 */
 		if (info & MT_TX_FREE_PAIR) {
 			struct mt7921_sta *msta;
-			struct mt76_wcid *wcid;
 			u16 idx;
 
 			count++;
@@ -658,6 +658,12 @@ static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
 		msdu = FIELD_GET(MT_TX_FREE_MSDU_ID, info);
 		stat = FIELD_GET(MT_TX_FREE_STATUS, info);
 
+		if (wcid) {
+			wcid->stats.tx_retries +=
+				FIELD_GET(MT_TX_FREE_COUNT, info) - 1;
+			wcid->stats.tx_failed += !!stat;
+		}
+
 		txwi = mt76_token_release(mdev, msdu, &wake);
 		if (!txwi)
 			continue;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index d183982c0b407..199da4b701a52 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1399,6 +1399,12 @@ static void mt7921_sta_statistics(struct ieee80211_hw *hw,
 		sinfo->txrate.he_dcm = txrate->he_dcm;
 		sinfo->txrate.he_ru_alloc = txrate->he_ru_alloc;
 	}
+	sinfo->tx_failed = msta->wcid.stats.tx_failed;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
+
+	sinfo->tx_retries = msta->wcid.stats.tx_retries;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES);
+
 	sinfo->txrate.flags = txrate->flags;
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 
-- 
GitLab


From b642f4c5f3de0a8f47808d32b1ebd9c427a42a66 Mon Sep 17 00:00:00 2001
From: Deren Wu <deren.wu@mediatek.com>
Date: Wed, 17 May 2023 17:18:24 +0800
Subject: [PATCH 0400/1806] wifi: mt76: mt7921: fix skb leak by txs missing in
 AMSDU

txs may be dropped if the frame is aggregated in AMSDU. When the problem
shows up, some SKBs would be hold in driver to cause network stopped
temporarily. Even if the problem can be recovered by txs timeout handling,
mt7921 still need to disable txs in AMSDU to avoid this issue.

Cc: stable@vger.kernel.org
Fixes: 163f4d22c118 ("mt76: mt7921: add MAC support")
Reviewed-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index 3501f05031182..f481ca3a0db85 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -495,6 +495,7 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi,
 				    BSS_CHANGED_BEACON_ENABLED));
 	bool inband_disc = !!(changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP |
 					 BSS_CHANGED_FILS_DISCOVERY));
+	bool amsdu_en = wcid->amsdu;
 
 	if (vif) {
 		struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv;
@@ -554,12 +555,14 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi,
 	txwi[4] = 0;
 
 	val = FIELD_PREP(MT_TXD5_PID, pid);
-	if (pid >= MT_PACKET_ID_FIRST)
+	if (pid >= MT_PACKET_ID_FIRST) {
 		val |= MT_TXD5_TX_STATUS_HOST;
+		amsdu_en = amsdu_en && !is_mt7921(dev);
+	}
 
 	txwi[5] = cpu_to_le32(val);
 	txwi[6] = 0;
-	txwi[7] = wcid->amsdu ? cpu_to_le32(MT_TXD7_HW_AMSDU) : 0;
+	txwi[7] = amsdu_en ? cpu_to_le32(MT_TXD7_HW_AMSDU) : 0;
 
 	if (is_8023)
 		mt76_connac2_mac_write_txwi_8023(txwi, skb, wcid);
-- 
GitLab


From 749c2c2b29dfb3a41cfdf9942581c2524664e969 Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Thu, 18 May 2023 01:34:42 +0800
Subject: [PATCH 0401/1806] wifi: mt76: add tx_nss histogram to ethtool stats

mt76_connac2_mac_fill_txs() counts tx_nss but ethtool doesn't show
stats. Add missing histogram accordingly.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c    | 3 +++
 drivers/net/wireless/mediatek/mt76/mt7915/main.c | 4 ++++
 drivers/net/wireless/mediatek/mt76/mt7921/main.c | 4 ++++
 drivers/net/wireless/mediatek/mt76/mt7996/main.c | 4 ++++
 4 files changed, 15 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index cd3aac4cc06fe..24ebf0504a3b2 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -1744,6 +1744,9 @@ void mt76_ethtool_worker(struct mt76_ethtool_worker_info *wi,
 	for (i = 0; i < (eht ? 14 : 12); i++)
 		data[ei++] += stats->tx_mcs[i];
 
+	for (i = 0; i < 4; i++)
+		data[ei++] += stats->tx_nss[i];
+
 	wi->worker_stat_count = ei - wi->initial_stat_idx;
 }
 EXPORT_SYMBOL_GPL(mt76_ethtool_worker);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index e384c633e8111..ecb27da27c6d0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -1280,6 +1280,10 @@ static const char mt7915_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"v_tx_mcs_9",
 	"v_tx_mcs_10",
 	"v_tx_mcs_11",
+	"v_tx_nss_1",
+	"v_tx_nss_2",
+	"v_tx_nss_3",
+	"v_tx_nss_4",
 };
 
 #define MT7915_SSTATS_LEN ARRAY_SIZE(mt7915_gstrings_stats)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 199da4b701a52..d520e68a8c82f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1077,6 +1077,10 @@ static const char mt7921_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"v_tx_mcs_9",
 	"v_tx_mcs_10",
 	"v_tx_mcs_11",
+	"v_tx_nss_1",
+	"v_tx_nss_2",
+	"v_tx_nss_3",
+	"v_tx_nss_4",
 };
 
 static void
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 9362f8487a0e1..073a9f91d9a5d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1177,6 +1177,10 @@ static const char mt7996_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"v_tx_mcs_11",
 	"v_tx_mcs_12",
 	"v_tx_mcs_13",
+	"v_tx_nss_1",
+	"v_tx_nss_2",
+	"v_tx_nss_3",
+	"v_tx_nss_4",
 };
 
 #define MT7996_SSTATS_LEN ARRAY_SIZE(mt7996_gstrings_stats)
-- 
GitLab


From 1258c156f2537786468c7fe04f547f64c97c1e12 Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Thu, 18 May 2023 01:34:43 +0800
Subject: [PATCH 0402/1806] wifi: mt76: mt7915: accumulate mu-mimo ofdma muru
 stats

The stats are clear-on-read, which makes it very difficult for tools
to adequately deal with wrapped stats and with keeping good totals.

So, accumulate these values when they are read from the firmware/radio
and present totals to user-space.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h     |  32 +++++
 .../wireless/mediatek/mt76/mt7915/debugfs.c   | 124 ++++++++----------
 .../net/wireless/mediatek/mt76/mt7915/mac.c   |   3 +
 .../net/wireless/mediatek/mt76/mt7915/main.c  |  63 +++++++++
 .../net/wireless/mediatek/mt76/mt7915/mcu.c   |  43 +++++-
 .../wireless/mediatek/mt76/mt7915/mt7915.h    |   2 +-
 6 files changed, 196 insertions(+), 71 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 6d22482183d8a..c11a417c5e37b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -918,6 +918,38 @@ struct mt76_mib_stats {
 
 	u32 tx_amsdu[8];
 	u32 tx_amsdu_cnt;
+
+	/* mcu_muru_stats */
+	u32 dl_cck_cnt;
+	u32 dl_ofdm_cnt;
+	u32 dl_htmix_cnt;
+	u32 dl_htgf_cnt;
+	u32 dl_vht_su_cnt;
+	u32 dl_vht_2mu_cnt;
+	u32 dl_vht_3mu_cnt;
+	u32 dl_vht_4mu_cnt;
+	u32 dl_he_su_cnt;
+	u32 dl_he_ext_su_cnt;
+	u32 dl_he_2ru_cnt;
+	u32 dl_he_2mu_cnt;
+	u32 dl_he_3ru_cnt;
+	u32 dl_he_3mu_cnt;
+	u32 dl_he_4ru_cnt;
+	u32 dl_he_4mu_cnt;
+	u32 dl_he_5to8ru_cnt;
+	u32 dl_he_9to16ru_cnt;
+	u32 dl_he_gtr16ru_cnt;
+
+	u32 ul_hetrig_su_cnt;
+	u32 ul_hetrig_2ru_cnt;
+	u32 ul_hetrig_3ru_cnt;
+	u32 ul_hetrig_4ru_cnt;
+	u32 ul_hetrig_5to8ru_cnt;
+	u32 ul_hetrig_9to16ru_cnt;
+	u32 ul_hetrig_gtr16ru_cnt;
+	u32 ul_hetrig_2mu_cnt;
+	u32 ul_hetrig_3mu_cnt;
+	u32 ul_hetrig_4mu_cnt;
 };
 
 struct mt76_power_limits {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
index dd5c494efa5f0..6c3696c8c7002 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
@@ -251,7 +251,6 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 {
 	struct mt7915_phy *phy = file->private;
 	struct mt7915_dev *dev = phy->dev;
-	struct mt7915_mcu_muru_stats mu_stats = {};
 	static const char * const dl_non_he_type[] = {
 		"CCK", "OFDM", "HT MIX", "HT GF",
 		"VHT SU", "VHT 2MU", "VHT 3MU", "VHT 4MU"
@@ -275,7 +274,7 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 
 	mutex_lock(&dev->mt76.mutex);
 
-	ret = mt7915_mcu_muru_debug_get(phy, &mu_stats);
+	ret = mt7915_mcu_muru_debug_get(phy);
 	if (ret)
 		goto exit;
 
@@ -285,14 +284,13 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 	for (i = 0; i < 5; i++)
 		seq_printf(file, "%8s | ", dl_non_he_type[i]);
 
-#define __dl_u32(s)     le32_to_cpu(mu_stats.dl.s)
 	seq_puts(file, "\nTotal Count:");
 	seq_printf(file, "%8u | %8u | %8u | %8u | %8u | ",
-		   __dl_u32(cck_cnt),
-		   __dl_u32(ofdm_cnt),
-		   __dl_u32(htmix_cnt),
-		   __dl_u32(htgf_cnt),
-		   __dl_u32(vht_su_cnt));
+		   phy->mib.dl_cck_cnt,
+		   phy->mib.dl_ofdm_cnt,
+		   phy->mib.dl_htmix_cnt,
+		   phy->mib.dl_htgf_cnt,
+		   phy->mib.dl_vht_su_cnt);
 
 	seq_puts(file, "\nDownlink MU-MIMO\nData Type:  ");
 
@@ -301,23 +299,23 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 
 	seq_puts(file, "\nTotal Count:");
 	seq_printf(file, "%8u | %8u | %8u | ",
-		   __dl_u32(vht_2mu_cnt),
-		   __dl_u32(vht_3mu_cnt),
-		   __dl_u32(vht_4mu_cnt));
+		   phy->mib.dl_vht_2mu_cnt,
+		   phy->mib.dl_vht_3mu_cnt,
+		   phy->mib.dl_vht_4mu_cnt);
 
-	sub_total_cnt = __dl_u32(vht_2mu_cnt) +
-		__dl_u32(vht_3mu_cnt) +
-		__dl_u32(vht_4mu_cnt);
+	sub_total_cnt = phy->mib.dl_vht_2mu_cnt +
+			phy->mib.dl_vht_3mu_cnt +
+			phy->mib.dl_vht_4mu_cnt;
 
 	seq_printf(file, "\nTotal non-HE MU-MIMO DL PPDU count: %lld",
 		   sub_total_cnt);
 
 	total_ppdu_cnt = sub_total_cnt +
-		__dl_u32(cck_cnt) +
-		__dl_u32(ofdm_cnt) +
-		__dl_u32(htmix_cnt) +
-		__dl_u32(htgf_cnt) +
-		__dl_u32(vht_su_cnt);
+			 phy->mib.dl_cck_cnt +
+			 phy->mib.dl_ofdm_cnt +
+			 phy->mib.dl_htmix_cnt +
+			 phy->mib.dl_htgf_cnt +
+			 phy->mib.dl_vht_su_cnt;
 
 	seq_printf(file, "\nAll non-HE DL PPDU count: %lld", total_ppdu_cnt);
 
@@ -329,8 +327,7 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 
 	seq_puts(file, "\nTotal Count:");
 	seq_printf(file, "%8u | %8u | ",
-		   __dl_u32(he_su_cnt),
-		   __dl_u32(he_ext_su_cnt));
+		   phy->mib.dl_he_su_cnt, phy->mib.dl_he_ext_su_cnt);
 
 	seq_puts(file, "\nDownlink MU-MIMO\nData Type:  ");
 
@@ -339,9 +336,8 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 
 	seq_puts(file, "\nTotal Count:");
 	seq_printf(file, "%8u | %8u | %8u | ",
-		   __dl_u32(he_2mu_cnt),
-		   __dl_u32(he_3mu_cnt),
-		   __dl_u32(he_4mu_cnt));
+		   phy->mib.dl_he_2mu_cnt, phy->mib.dl_he_3mu_cnt,
+		   phy->mib.dl_he_4mu_cnt);
 
 	seq_puts(file, "\nDownlink OFDMA\nData Type:  ");
 
@@ -350,37 +346,35 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 
 	seq_puts(file, "\nTotal Count:");
 	seq_printf(file, "%8u | %8u | %8u | %8u | %9u | %8u | ",
-		   __dl_u32(he_2ru_cnt),
-		   __dl_u32(he_3ru_cnt),
-		   __dl_u32(he_4ru_cnt),
-		   __dl_u32(he_5to8ru_cnt),
-		   __dl_u32(he_9to16ru_cnt),
-		   __dl_u32(he_gtr16ru_cnt));
-
-	sub_total_cnt = __dl_u32(he_2mu_cnt) +
-		__dl_u32(he_3mu_cnt) +
-		__dl_u32(he_4mu_cnt);
+		   phy->mib.dl_he_2ru_cnt,
+		   phy->mib.dl_he_3ru_cnt,
+		   phy->mib.dl_he_4ru_cnt,
+		   phy->mib.dl_he_5to8ru_cnt,
+		   phy->mib.dl_he_9to16ru_cnt,
+		   phy->mib.dl_he_gtr16ru_cnt);
+
+	sub_total_cnt = phy->mib.dl_he_2mu_cnt +
+			phy->mib.dl_he_3mu_cnt +
+			phy->mib.dl_he_4mu_cnt;
 	total_ppdu_cnt = sub_total_cnt;
 
 	seq_printf(file, "\nTotal HE MU-MIMO DL PPDU count: %lld",
 		   sub_total_cnt);
 
-	sub_total_cnt = __dl_u32(he_2ru_cnt) +
-		__dl_u32(he_3ru_cnt) +
-		__dl_u32(he_4ru_cnt) +
-		__dl_u32(he_5to8ru_cnt) +
-		__dl_u32(he_9to16ru_cnt) +
-		__dl_u32(he_gtr16ru_cnt);
+	sub_total_cnt = phy->mib.dl_he_2ru_cnt +
+			phy->mib.dl_he_3ru_cnt +
+			phy->mib.dl_he_4ru_cnt +
+			phy->mib.dl_he_5to8ru_cnt +
+			phy->mib.dl_he_9to16ru_cnt +
+			phy->mib.dl_he_gtr16ru_cnt;
 	total_ppdu_cnt += sub_total_cnt;
 
 	seq_printf(file, "\nTotal HE OFDMA DL PPDU count: %lld",
 		   sub_total_cnt);
 
-	total_ppdu_cnt += __dl_u32(he_su_cnt) +
-		__dl_u32(he_ext_su_cnt);
+	total_ppdu_cnt += phy->mib.dl_he_su_cnt + phy->mib.dl_he_ext_su_cnt;
 
 	seq_printf(file, "\nAll HE DL PPDU count: %lld", total_ppdu_cnt);
-#undef __dl_u32
 
 	/* HE Uplink */
 	seq_puts(file, "\n\nUplink");
@@ -389,12 +383,11 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 	for (i = 0; i < 3; i++)
 		seq_printf(file, "%8s | ", ul_he_type[i]);
 
-#define __ul_u32(s)     le32_to_cpu(mu_stats.ul.s)
 	seq_puts(file, "\nTotal Count:");
 	seq_printf(file, "%8u | %8u | %8u | ",
-		   __ul_u32(hetrig_2mu_cnt),
-		   __ul_u32(hetrig_3mu_cnt),
-		   __ul_u32(hetrig_4mu_cnt));
+		   phy->mib.ul_hetrig_2mu_cnt,
+		   phy->mib.ul_hetrig_3mu_cnt,
+		   phy->mib.ul_hetrig_4mu_cnt);
 
 	seq_puts(file, "\nTrigger-based Uplink OFDMA\nData Type:  ");
 
@@ -403,37 +396,36 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 
 	seq_puts(file, "\nTotal Count:");
 	seq_printf(file, "%8u | %8u | %8u | %8u | %8u | %9u |  %7u | ",
-		   __ul_u32(hetrig_su_cnt),
-		   __ul_u32(hetrig_2ru_cnt),
-		   __ul_u32(hetrig_3ru_cnt),
-		   __ul_u32(hetrig_4ru_cnt),
-		   __ul_u32(hetrig_5to8ru_cnt),
-		   __ul_u32(hetrig_9to16ru_cnt),
-		   __ul_u32(hetrig_gtr16ru_cnt));
-
-	sub_total_cnt = __ul_u32(hetrig_2mu_cnt) +
-		__ul_u32(hetrig_3mu_cnt) +
-		__ul_u32(hetrig_4mu_cnt);
+		   phy->mib.ul_hetrig_su_cnt,
+		   phy->mib.ul_hetrig_2ru_cnt,
+		   phy->mib.ul_hetrig_3ru_cnt,
+		   phy->mib.ul_hetrig_4ru_cnt,
+		   phy->mib.ul_hetrig_5to8ru_cnt,
+		   phy->mib.ul_hetrig_9to16ru_cnt,
+		   phy->mib.ul_hetrig_gtr16ru_cnt);
+
+	sub_total_cnt = phy->mib.ul_hetrig_2mu_cnt +
+			phy->mib.ul_hetrig_3mu_cnt +
+			phy->mib.ul_hetrig_4mu_cnt;
 	total_ppdu_cnt = sub_total_cnt;
 
 	seq_printf(file, "\nTotal HE MU-MIMO UL TB PPDU count: %lld",
 		   sub_total_cnt);
 
-	sub_total_cnt = __ul_u32(hetrig_2ru_cnt) +
-		__ul_u32(hetrig_3ru_cnt) +
-		__ul_u32(hetrig_4ru_cnt) +
-		__ul_u32(hetrig_5to8ru_cnt) +
-		__ul_u32(hetrig_9to16ru_cnt) +
-		__ul_u32(hetrig_gtr16ru_cnt);
+	sub_total_cnt = phy->mib.ul_hetrig_2ru_cnt +
+			phy->mib.ul_hetrig_3ru_cnt +
+			phy->mib.ul_hetrig_4ru_cnt +
+			phy->mib.ul_hetrig_5to8ru_cnt +
+			phy->mib.ul_hetrig_9to16ru_cnt +
+			phy->mib.ul_hetrig_gtr16ru_cnt;
 	total_ppdu_cnt += sub_total_cnt;
 
 	seq_printf(file, "\nTotal HE OFDMA UL TB PPDU count: %lld",
 		   sub_total_cnt);
 
-	total_ppdu_cnt += __ul_u32(hetrig_su_cnt);
+	total_ppdu_cnt += phy->mib.ul_hetrig_su_cnt;
 
 	seq_printf(file, "\nAll HE UL TB PPDU count: %lld\n", total_ppdu_cnt);
-#undef __ul_u32
 
 exit:
 	mutex_unlock(&dev->mt76.mutex);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 14ea42732dedc..4226fd496143d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -2072,6 +2072,9 @@ void mt7915_mac_work(struct work_struct *work)
 
 		mt7915_mac_update_stats(phy);
 		mt7915_mac_severe_check(phy);
+
+		if (phy->dev->muru_debug)
+			mt7915_mcu_muru_debug_get(phy);
 	}
 
 	mutex_unlock(&mphy->dev->mutex);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index ecb27da27c6d0..64c02734a3f21 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -1254,6 +1254,38 @@ static const char mt7915_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"rx_vec_queue_overflow_drop_cnt",
 	"rx_ba_cnt",
 
+	/* muru mu-mimo and ofdma related stats */
+	"dl_cck_cnt",
+	"dl_ofdm_cnt",
+	"dl_htmix_cnt",
+	"dl_htgf_cnt",
+	"dl_vht_su_cnt",
+	"dl_vht_2mu_cnt",
+	"dl_vht_3mu_cnt",
+	"dl_vht_4mu_cnt",
+	"dl_he_su_cnt",
+	"dl_he_ext_su_cnt",
+	"dl_he_2ru_cnt",
+	"dl_he_2mu_cnt",
+	"dl_he_3ru_cnt",
+	"dl_he_3mu_cnt",
+	"dl_he_4ru_cnt",
+	"dl_he_4mu_cnt",
+	"dl_he_5to8ru_cnt",
+	"dl_he_9to16ru_cnt",
+	"dl_he_gtr16ru_cnt",
+
+	"ul_hetrig_su_cnt",
+	"ul_hetrig_2ru_cnt",
+	"ul_hetrig_3ru_cnt",
+	"ul_hetrig_4ru_cnt",
+	"ul_hetrig_5to8ru_cnt",
+	"ul_hetrig_9to16ru_cnt",
+	"ul_hetrig_gtr16ru_cnt",
+	"ul_hetrig_2mu_cnt",
+	"ul_hetrig_3mu_cnt",
+	"ul_hetrig_4mu_cnt",
+
 	/* per vif counters */
 	"v_tx_mode_cck",
 	"v_tx_mode_ofdm",
@@ -1408,6 +1440,37 @@ void mt7915_get_et_stats(struct ieee80211_hw *hw,
 	data[ei++] = mib->rx_vec_queue_overflow_drop_cnt;
 	data[ei++] = mib->rx_ba_cnt;
 
+	data[ei++] = mib->dl_cck_cnt;
+	data[ei++] = mib->dl_ofdm_cnt;
+	data[ei++] = mib->dl_htmix_cnt;
+	data[ei++] = mib->dl_htgf_cnt;
+	data[ei++] = mib->dl_vht_su_cnt;
+	data[ei++] = mib->dl_vht_2mu_cnt;
+	data[ei++] = mib->dl_vht_3mu_cnt;
+	data[ei++] = mib->dl_vht_4mu_cnt;
+	data[ei++] = mib->dl_he_su_cnt;
+	data[ei++] = mib->dl_he_ext_su_cnt;
+	data[ei++] = mib->dl_he_2ru_cnt;
+	data[ei++] = mib->dl_he_2mu_cnt;
+	data[ei++] = mib->dl_he_3ru_cnt;
+	data[ei++] = mib->dl_he_3mu_cnt;
+	data[ei++] = mib->dl_he_4ru_cnt;
+	data[ei++] = mib->dl_he_4mu_cnt;
+	data[ei++] = mib->dl_he_5to8ru_cnt;
+	data[ei++] = mib->dl_he_9to16ru_cnt;
+	data[ei++] = mib->dl_he_gtr16ru_cnt;
+
+	data[ei++] = mib->ul_hetrig_su_cnt;
+	data[ei++] = mib->ul_hetrig_2ru_cnt;
+	data[ei++] = mib->ul_hetrig_3ru_cnt;
+	data[ei++] = mib->ul_hetrig_4ru_cnt;
+	data[ei++] = mib->ul_hetrig_5to8ru_cnt;
+	data[ei++] = mib->ul_hetrig_9to16ru_cnt;
+	data[ei++] = mib->ul_hetrig_gtr16ru_cnt;
+	data[ei++] = mib->ul_hetrig_2mu_cnt;
+	data[ei++] = mib->ul_hetrig_3mu_cnt;
+	data[ei++] = mib->ul_hetrig_4mu_cnt;
+
 	/* Add values for all stations owned by this vif */
 	wi.initial_stat_idx = ei;
 	ieee80211_iterate_stations_atomic(hw, mt7915_ethtool_worker, &wi);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index c9716422c803a..bb8ec0d1d01c3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -2119,12 +2119,11 @@ int mt7915_mcu_muru_debug_set(struct mt7915_dev *dev, bool enabled)
 				sizeof(data), false);
 }
 
-int mt7915_mcu_muru_debug_get(struct mt7915_phy *phy, void *ms)
+int mt7915_mcu_muru_debug_get(struct mt7915_phy *phy)
 {
 	struct mt7915_dev *dev = phy->dev;
 	struct sk_buff *skb;
-	struct mt7915_mcu_muru_stats *mu_stats =
-				(struct mt7915_mcu_muru_stats *)ms;
+	struct mt7915_mcu_muru_stats *mu_stats;
 	int ret;
 
 	struct {
@@ -2140,7 +2139,43 @@ int mt7915_mcu_muru_debug_get(struct mt7915_phy *phy, void *ms)
 	if (ret)
 		return ret;
 
-	memcpy(mu_stats, skb->data, sizeof(struct mt7915_mcu_muru_stats));
+	mu_stats = (struct mt7915_mcu_muru_stats *)(skb->data);
+
+	/* accumulate stats, these are clear-on-read */
+#define __dl_u32(s)	 phy->mib.dl_##s += le32_to_cpu(mu_stats->dl.s)
+#define __ul_u32(s)	 phy->mib.ul_##s += le32_to_cpu(mu_stats->ul.s)
+	__dl_u32(cck_cnt);
+	__dl_u32(ofdm_cnt);
+	__dl_u32(htmix_cnt);
+	__dl_u32(htgf_cnt);
+	__dl_u32(vht_su_cnt);
+	__dl_u32(vht_2mu_cnt);
+	__dl_u32(vht_3mu_cnt);
+	__dl_u32(vht_4mu_cnt);
+	__dl_u32(he_su_cnt);
+	__dl_u32(he_2ru_cnt);
+	__dl_u32(he_2mu_cnt);
+	__dl_u32(he_3ru_cnt);
+	__dl_u32(he_3mu_cnt);
+	__dl_u32(he_4ru_cnt);
+	__dl_u32(he_4mu_cnt);
+	__dl_u32(he_5to8ru_cnt);
+	__dl_u32(he_9to16ru_cnt);
+	__dl_u32(he_gtr16ru_cnt);
+
+	__ul_u32(hetrig_su_cnt);
+	__ul_u32(hetrig_2ru_cnt);
+	__ul_u32(hetrig_3ru_cnt);
+	__ul_u32(hetrig_4ru_cnt);
+	__ul_u32(hetrig_5to8ru_cnt);
+	__ul_u32(hetrig_9to16ru_cnt);
+	__ul_u32(hetrig_gtr16ru_cnt);
+	__ul_u32(hetrig_2mu_cnt);
+	__ul_u32(hetrig_3mu_cnt);
+	__ul_u32(hetrig_4mu_cnt);
+#undef __dl_u32
+#undef __ul_u32
+
 	dev_kfree_skb(skb);
 
 	return 0;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index 736f5fbfafc5c..0b8380bc05882 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -569,7 +569,7 @@ void mt7915_set_stream_he_caps(struct mt7915_phy *phy);
 void mt7915_set_stream_vht_txbf_caps(struct mt7915_phy *phy);
 void mt7915_update_channel(struct mt76_phy *mphy);
 int mt7915_mcu_muru_debug_set(struct mt7915_dev *dev, bool enable);
-int mt7915_mcu_muru_debug_get(struct mt7915_phy *phy, void *ms);
+int mt7915_mcu_muru_debug_get(struct mt7915_phy *phy);
 int mt7915_mcu_wed_enable_rx_stats(struct mt7915_dev *dev);
 int mt7915_init_debugfs(struct mt7915_phy *phy);
 void mt7915_debugfs_rx_fw_monitor(struct mt7915_dev *dev, const void *data, int len);
-- 
GitLab


From 0e5911bb7cc92c00dda9b4d635c1266b7ca915c6 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Thu, 18 May 2023 22:08:14 +0800
Subject: [PATCH 0403/1806] wifi: mt76: mt7921: fix non-PSC channel scan fail

Due to the scan command may only request legacy bands and PSC channel
in 6GHz band, we are unable to scan the APs on non-PSC channel in this
case. Enable WIPHY_FLAG_SPLIT_SCAN_6GHZ to support non-PSC channel
(obtained during scan on legacy bands) in 6GHz scan request.

Fixes: 50ac15a511e3 ("mt76: mt7921: add 6GHz support")
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/init.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index bf1da9fddfaba..f41975e37d06a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -113,7 +113,8 @@ mt7921_init_wiphy(struct ieee80211_hw *hw)
 	wiphy->max_sched_scan_ssids = MT76_CONNAC_MAX_SCHED_SCAN_SSID;
 	wiphy->max_match_sets = MT76_CONNAC_MAX_SCAN_MATCH;
 	wiphy->max_sched_scan_reqs = 1;
-	wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH;
+	wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH |
+			WIPHY_FLAG_SPLIT_SCAN_6GHZ;
 	wiphy->reg_notifier = mt7921_regd_notifier;
 
 	wiphy->features |= NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR |
-- 
GitLab


From 6ae39b7c7ed4d594cacb6b1d61fb6a8602df0c3c Mon Sep 17 00:00:00 2001
From: Ben Greear <greearb@candelatech.com>
Date: Fri, 2 Jun 2023 14:14:24 -0700
Subject: [PATCH 0404/1806] wifi: mt76: mt7921: Support temp sensor
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allow sensors tool to read radio's temperature, example:

mt7921_phy17-pci-1800
Adapter: PCI adapter
temp1:        +72.0°C

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/init.c  | 60 +++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7921/mcu.c   | 17 ++++++
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  1 +
 3 files changed, 78 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index f41975e37d06a..73a31efc08dad 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -2,6 +2,9 @@
 /* Copyright (C) 2020 MediaTek Inc. */
 
 #include <linux/etherdevice.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/thermal.h>
 #include <linux/firmware.h>
 #include "mt7921.h"
 #include "../mt76_connac2_mac.h"
@@ -51,6 +54,57 @@ static const struct ieee80211_iface_combination if_comb_chanctx[] = {
 	}
 };
 
+static ssize_t mt7921_thermal_temp_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	switch (to_sensor_dev_attr(attr)->index) {
+	case 0: {
+		struct mt7921_phy *phy = dev_get_drvdata(dev);
+		struct mt7921_dev *mdev = phy->dev;
+		int temperature;
+
+		mt7921_mutex_acquire(mdev);
+		temperature = mt7921_mcu_get_temperature(phy);
+		mt7921_mutex_release(mdev);
+
+		if (temperature < 0)
+			return temperature;
+		/* display in millidegree Celsius */
+		return sprintf(buf, "%u\n", temperature * 1000);
+	}
+	default:
+		return -EINVAL;
+	}
+}
+static SENSOR_DEVICE_ATTR_RO(temp1_input, mt7921_thermal_temp, 0);
+
+static struct attribute *mt7921_hwmon_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(mt7921_hwmon);
+
+static int mt7921_thermal_init(struct mt7921_phy *phy)
+{
+	struct wiphy *wiphy = phy->mt76->hw->wiphy;
+	struct device *hwmon;
+	const char *name;
+
+	if (!IS_REACHABLE(CONFIG_HWMON))
+		return 0;
+
+	name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7921_%s",
+			      wiphy_name(wiphy));
+
+	hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, name, phy,
+						       mt7921_hwmon_groups);
+	if (IS_ERR(hwmon))
+		return PTR_ERR(hwmon);
+
+	return 0;
+}
+
 static void
 mt7921_regd_notifier(struct wiphy *wiphy,
 		     struct regulatory_request *request)
@@ -363,6 +417,12 @@ static void mt7921_init_work(struct work_struct *work)
 		return;
 	}
 
+	ret = mt7921_thermal_init(&dev->phy);
+	if (ret) {
+		dev_err(dev->mt76.dev, "thermal init failed\n");
+		return;
+	}
+
 	/* we support chip reset now */
 	dev->hw_init_done = true;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index f55caa00ac69b..a0ad18c70b1ab 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -1305,6 +1305,23 @@ int mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
 	return 0;
 }
 
+int mt7921_mcu_get_temperature(struct mt7921_phy *phy)
+{
+	struct mt7921_dev *dev = phy->dev;
+	struct {
+		u8 ctrl_id;
+		u8 action;
+		u8 band_idx;
+		u8 rsv[5];
+	} req = {
+		.ctrl_id = THERMAL_SENSOR_TEMP_QUERY,
+		.band_idx = phy->mt76->band_idx,
+	};
+
+	return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(THERMAL_CTRL), &req,
+				 sizeof(req), true);
+}
+
 int mt7921_mcu_set_rxfilter(struct mt7921_dev *dev, u32 fif,
 			    u8 bit_op, u32 bit_map)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 76dc2538b9152..3776055201d06 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -511,6 +511,7 @@ int mt7921_mcu_set_sniffer(struct mt7921_dev *dev, struct ieee80211_vif *vif,
 			   bool enable);
 int mt7921_mcu_config_sniffer(struct mt7921_vif *vif,
 			      struct ieee80211_chanctx_conf *ctx);
+int mt7921_mcu_get_temperature(struct mt7921_phy *phy);
 
 int mt7921_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 				   enum mt76_txq_id qid, struct mt76_wcid *wcid,
-- 
GitLab


From 1e64fdd41c9d2c6f6c9ef0ce7d6854c70d812d0f Mon Sep 17 00:00:00 2001
From: Bo Jiao <Bo.Jiao@mediatek.com>
Date: Tue, 23 May 2023 02:49:53 +0800
Subject: [PATCH 0405/1806] wifi: mt76: mt7915: disable WFDMA Tx/Rx during SER
 recovery

Stop WFDMA transaction to avoid potential unexpected issue while doing
system recovery.

Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/dma.c      |   6 +
 .../net/wireless/mediatek/mt76/mt7915/dma.c   | 148 ++++++++++--------
 .../net/wireless/mediatek/mt76/mt7915/mac.c   |  25 ++-
 .../wireless/mediatek/mt76/mt7915/mt7915.h    |   1 +
 4 files changed, 107 insertions(+), 73 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 465190ebaf1c4..05d9ab3ce819b 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -466,6 +466,9 @@ mt76_dma_tx_queue_skb_raw(struct mt76_dev *dev, struct mt76_queue *q,
 	struct mt76_queue_buf buf = {};
 	dma_addr_t addr;
 
+	if (test_bit(MT76_MCU_RESET, &dev->phy.state))
+		goto error;
+
 	if (q->queued + 1 >= q->ndesc - 1)
 		goto error;
 
@@ -507,6 +510,9 @@ mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
 	dma_addr_t addr;
 	u8 *txwi;
 
+	if (test_bit(MT76_RESET, &dev->phy.state))
+		goto free_skb;
+
 	t = mt76_get_txwi(dev);
 	if (!t)
 		goto free_skb;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
index 86a93dedb1bf5..59a44d79aaedb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
@@ -250,12 +250,90 @@ static void mt7915_dma_disable(struct mt7915_dev *dev, bool rst)
 	}
 }
 
-static int mt7915_dma_enable(struct mt7915_dev *dev)
+int mt7915_dma_start(struct mt7915_dev *dev, bool reset, bool wed_reset)
 {
 	struct mt76_dev *mdev = &dev->mt76;
 	u32 hif1_ofs = 0;
 	u32 irq_mask;
 
+	if (dev->hif2)
+		hif1_ofs = MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0);
+
+	/* enable wpdma tx/rx */
+	if (!reset) {
+		mt76_set(dev, MT_WFDMA0_GLO_CFG,
+			MT_WFDMA0_GLO_CFG_TX_DMA_EN |
+			MT_WFDMA0_GLO_CFG_RX_DMA_EN |
+			MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+			MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+
+		if (is_mt7915(mdev))
+			mt76_set(dev, MT_WFDMA1_GLO_CFG,
+				MT_WFDMA1_GLO_CFG_TX_DMA_EN |
+				MT_WFDMA1_GLO_CFG_RX_DMA_EN |
+				MT_WFDMA1_GLO_CFG_OMIT_TX_INFO |
+				MT_WFDMA1_GLO_CFG_OMIT_RX_INFO);
+
+		if (dev->hif2) {
+			mt76_set(dev, MT_WFDMA0_GLO_CFG + hif1_ofs,
+				MT_WFDMA0_GLO_CFG_TX_DMA_EN |
+				MT_WFDMA0_GLO_CFG_RX_DMA_EN |
+				MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+				MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+
+			if (is_mt7915(mdev))
+				mt76_set(dev, MT_WFDMA1_GLO_CFG + hif1_ofs,
+					MT_WFDMA1_GLO_CFG_TX_DMA_EN |
+					MT_WFDMA1_GLO_CFG_RX_DMA_EN |
+					MT_WFDMA1_GLO_CFG_OMIT_TX_INFO |
+					MT_WFDMA1_GLO_CFG_OMIT_RX_INFO);
+
+			mt76_set(dev, MT_WFDMA_HOST_CONFIG,
+				MT_WFDMA_HOST_CONFIG_PDMA_BAND);
+		}
+	}
+
+	/* enable interrupts for TX/RX rings */
+	irq_mask = MT_INT_RX_DONE_MCU |
+		   MT_INT_TX_DONE_MCU |
+		   MT_INT_MCU_CMD;
+
+	if (!dev->phy.mt76->band_idx)
+		irq_mask |= MT_INT_BAND0_RX_DONE;
+
+	if (dev->dbdc_support || dev->phy.mt76->band_idx)
+		irq_mask |= MT_INT_BAND1_RX_DONE;
+
+	if (mtk_wed_device_active(&dev->mt76.mmio.wed) && wed_reset) {
+		u32 wed_irq_mask = irq_mask;
+		int ret;
+
+		wed_irq_mask |= MT_INT_TX_DONE_BAND0 | MT_INT_TX_DONE_BAND1;
+		if (!is_mt798x(&dev->mt76))
+			mt76_wr(dev, MT_INT_WED_MASK_CSR, wed_irq_mask);
+		else
+			mt76_wr(dev, MT_INT_MASK_CSR, wed_irq_mask);
+
+		ret = mt7915_mcu_wed_enable_rx_stats(dev);
+		if (ret)
+			return ret;
+
+		mtk_wed_device_start(&dev->mt76.mmio.wed, wed_irq_mask);
+	}
+
+	irq_mask = reset ? MT_INT_MCU_CMD : irq_mask;
+
+	mt7915_irq_enable(dev, irq_mask);
+	mt7915_irq_disable(dev, 0);
+
+	return 0;
+}
+
+static int mt7915_dma_enable(struct mt7915_dev *dev, bool reset)
+{
+	struct mt76_dev *mdev = &dev->mt76;
+	u32 hif1_ofs = 0;
+
 	if (dev->hif2)
 		hif1_ofs = MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0);
 
@@ -322,69 +400,7 @@ static int mt7915_dma_enable(struct mt7915_dev *dev)
 	mt76_poll(dev, MT_WFDMA_EXT_CSR_HIF_MISC,
 		  MT_WFDMA_EXT_CSR_HIF_MISC_BUSY, 0, 1000);
 
-	/* set WFDMA Tx/Rx */
-	mt76_set(dev, MT_WFDMA0_GLO_CFG,
-		 MT_WFDMA0_GLO_CFG_TX_DMA_EN |
-		 MT_WFDMA0_GLO_CFG_RX_DMA_EN |
-		 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-		 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
-
-	if (is_mt7915(mdev))
-		mt76_set(dev, MT_WFDMA1_GLO_CFG,
-			 MT_WFDMA1_GLO_CFG_TX_DMA_EN |
-			 MT_WFDMA1_GLO_CFG_RX_DMA_EN |
-			 MT_WFDMA1_GLO_CFG_OMIT_TX_INFO |
-			 MT_WFDMA1_GLO_CFG_OMIT_RX_INFO);
-
-	if (dev->hif2) {
-		mt76_set(dev, MT_WFDMA0_GLO_CFG + hif1_ofs,
-			 MT_WFDMA0_GLO_CFG_TX_DMA_EN |
-			 MT_WFDMA0_GLO_CFG_RX_DMA_EN |
-			 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-			 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
-
-		if (is_mt7915(mdev))
-			mt76_set(dev, MT_WFDMA1_GLO_CFG + hif1_ofs,
-				 MT_WFDMA1_GLO_CFG_TX_DMA_EN |
-				 MT_WFDMA1_GLO_CFG_RX_DMA_EN |
-				 MT_WFDMA1_GLO_CFG_OMIT_TX_INFO |
-				 MT_WFDMA1_GLO_CFG_OMIT_RX_INFO);
-
-		mt76_set(dev, MT_WFDMA_HOST_CONFIG,
-			 MT_WFDMA_HOST_CONFIG_PDMA_BAND);
-	}
-
-	/* enable interrupts for TX/RX rings */
-	irq_mask = MT_INT_RX_DONE_MCU |
-		   MT_INT_TX_DONE_MCU |
-		   MT_INT_MCU_CMD;
-
-	if (!dev->phy.mt76->band_idx)
-		irq_mask |= MT_INT_BAND0_RX_DONE;
-
-	if (dev->dbdc_support || dev->phy.mt76->band_idx)
-		irq_mask |= MT_INT_BAND1_RX_DONE;
-
-	if (mtk_wed_device_active(&dev->mt76.mmio.wed)) {
-		u32 wed_irq_mask = irq_mask;
-		int ret;
-
-		wed_irq_mask |= MT_INT_TX_DONE_BAND0 | MT_INT_TX_DONE_BAND1;
-		if (!is_mt798x(&dev->mt76))
-			mt76_wr(dev, MT_INT_WED_MASK_CSR, wed_irq_mask);
-		else
-			mt76_wr(dev, MT_INT_MASK_CSR, wed_irq_mask);
-
-		ret = mt7915_mcu_wed_enable_rx_stats(dev);
-		if (ret)
-			return ret;
-
-		mtk_wed_device_start(&dev->mt76.mmio.wed, wed_irq_mask);
-	}
-
-	mt7915_irq_enable(dev, irq_mask);
-
-	return 0;
+	return mt7915_dma_start(dev, reset, true);
 }
 
 int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2)
@@ -560,7 +576,7 @@ int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2)
 			  mt7915_poll_tx);
 	napi_enable(&dev->mt76.tx_napi);
 
-	mt7915_dma_enable(dev);
+	mt7915_dma_enable(dev, false);
 
 	return 0;
 }
@@ -642,7 +658,7 @@ int mt7915_dma_reset(struct mt7915_dev *dev, bool force)
 		mt76_rmw(dev, MT_WFDMA0_EXT0_CFG, MT_WFDMA0_EXT0_RXWB_KEEP,
 			 MT_WFDMA0_EXT0_RXWB_KEEP);
 
-	mt7915_dma_enable(dev);
+	mt7915_dma_enable(dev, !force);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 4226fd496143d..2bc2fefa1cd08 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1407,8 +1407,12 @@ mt7915_mac_restart(struct mt7915_dev *dev)
 
 	if (dev_is_pci(mdev->dev)) {
 		mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0);
-		if (dev->hif2)
-			mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE, 0x0);
+		if (dev->hif2) {
+			if (is_mt7915(mdev))
+				mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE, 0x0);
+			else
+				mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE_MT7916, 0x0);
+		}
 	}
 
 	set_bit(MT76_RESET, &dev->mphy.state);
@@ -1458,8 +1462,12 @@ mt7915_mac_restart(struct mt7915_dev *dev)
 	}
 	if (dev_is_pci(mdev->dev)) {
 		mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
-		if (dev->hif2)
-			mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE, 0xff);
+		if (dev->hif2) {
+			if (is_mt7915(mdev))
+				mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE, 0xff);
+			else
+				mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE_MT7916, 0xff);
+		}
 	}
 
 	/* load firmware */
@@ -1629,6 +1637,12 @@ void mt7915_mac_reset_work(struct work_struct *work)
 		mt7915_wait_reset_state(dev, MT_MCU_CMD_RECOVERY_DONE);
 	}
 
+	mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_RESET_DONE);
+	mt7915_wait_reset_state(dev, MT_MCU_CMD_NORMAL_STATE);
+
+	/* enable DMA Tx/Rx and interrupt */
+	mt7915_dma_start(dev, false, false);
+
 	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
 	clear_bit(MT76_RESET, &dev->mphy.state);
 	if (phy2)
@@ -1643,9 +1657,6 @@ void mt7915_mac_reset_work(struct work_struct *work)
 
 	tasklet_schedule(&dev->mt76.irq_tasklet);
 
-	mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_RESET_DONE);
-	mt7915_wait_reset_state(dev, MT_MCU_CMD_NORMAL_STATE);
-
 	mt76_worker_enable(&dev->mt76.tx_worker);
 
 	local_bh_disable();
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index 0b8380bc05882..93b536e01eb5c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -411,6 +411,7 @@ int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2);
 void mt7915_dma_prefetch(struct mt7915_dev *dev);
 void mt7915_dma_cleanup(struct mt7915_dev *dev);
 int mt7915_dma_reset(struct mt7915_dev *dev, bool force);
+int mt7915_dma_start(struct mt7915_dev *dev, bool reset, bool wed_reset);
 int mt7915_txbf_init(struct mt7915_dev *dev);
 void mt7915_init_txpower(struct mt7915_dev *dev,
 			 struct ieee80211_supported_band *sband);
-- 
GitLab


From 8e8c09c7d09020ddd1fb7c09423383aa5f88d391 Mon Sep 17 00:00:00 2001
From: Bo Jiao <Bo.Jiao@mediatek.com>
Date: Tue, 23 May 2023 02:49:54 +0800
Subject: [PATCH 0406/1806] wifi: mt76: mt7996: disable WFDMA Tx/Rx during SER
 recovery

Stop WFDMA transaction to avoid potential unexpected issue while doing
system recovery.

Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/dma.c   | 81 +++++++++++--------
 .../net/wireless/mediatek/mt76/mt7996/mac.c   |  9 ++-
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  1 +
 3 files changed, 55 insertions(+), 36 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
index 534143465d9b3..99b00a1357119 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
@@ -128,11 +128,55 @@ static void mt7996_dma_disable(struct mt7996_dev *dev, bool reset)
 	}
 }
 
-static int mt7996_dma_enable(struct mt7996_dev *dev)
+void mt7996_dma_start(struct mt7996_dev *dev, bool reset)
 {
 	u32 hif1_ofs = 0;
 	u32 irq_mask;
 
+	if (dev->hif2)
+		hif1_ofs = MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0);
+
+	/* enable WFDMA Tx/Rx */
+	if (!reset) {
+		mt76_set(dev, MT_WFDMA0_GLO_CFG,
+			 MT_WFDMA0_GLO_CFG_TX_DMA_EN |
+			 MT_WFDMA0_GLO_CFG_RX_DMA_EN |
+			 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+			 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+
+		if (dev->hif2)
+			mt76_set(dev, MT_WFDMA0_GLO_CFG + hif1_ofs,
+				 MT_WFDMA0_GLO_CFG_TX_DMA_EN |
+				 MT_WFDMA0_GLO_CFG_RX_DMA_EN |
+				 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+				 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+	}
+
+	/* enable interrupts for TX/RX rings */
+	irq_mask = MT_INT_MCU_CMD;
+	if (reset)
+		goto done;
+
+	irq_mask = MT_INT_RX_DONE_MCU | MT_INT_TX_DONE_MCU;
+
+	if (!dev->mphy.band_idx)
+		irq_mask |= MT_INT_BAND0_RX_DONE;
+
+	if (dev->dbdc_support)
+		irq_mask |= MT_INT_BAND1_RX_DONE;
+
+	if (dev->tbtc_support)
+		irq_mask |= MT_INT_BAND2_RX_DONE;
+
+done:
+	mt7996_irq_enable(dev, irq_mask);
+	mt7996_irq_disable(dev, 0);
+}
+
+static void mt7996_dma_enable(struct mt7996_dev *dev, bool reset)
+{
+	u32 hif1_ofs = 0;
+
 	if (dev->hif2)
 		hif1_ofs = MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0);
 
@@ -170,13 +214,6 @@ static int mt7996_dma_enable(struct mt7996_dev *dev)
 	mt76_poll(dev, MT_WFDMA_EXT_CSR_HIF_MISC,
 		  MT_WFDMA_EXT_CSR_HIF_MISC_BUSY, 0, 1000);
 
-	/* set WFDMA Tx/Rx */
-	mt76_set(dev, MT_WFDMA0_GLO_CFG,
-		 MT_WFDMA0_GLO_CFG_TX_DMA_EN |
-		 MT_WFDMA0_GLO_CFG_RX_DMA_EN |
-		 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-		 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
-
 	/* GLO_CFG_EXT0 */
 	mt76_set(dev, WF_WFDMA0_GLO_CFG_EXT0,
 		 WF_WFDMA0_GLO_CFG_EXT0_RX_WB_RXD |
@@ -187,12 +224,6 @@ static int mt7996_dma_enable(struct mt7996_dev *dev)
 		 WF_WFDMA0_GLO_CFG_EXT1_TX_FCTRL_MODE);
 
 	if (dev->hif2) {
-		mt76_set(dev, MT_WFDMA0_GLO_CFG + hif1_ofs,
-			 MT_WFDMA0_GLO_CFG_TX_DMA_EN |
-			 MT_WFDMA0_GLO_CFG_RX_DMA_EN |
-			 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-			 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
-
 		/* GLO_CFG_EXT0 */
 		mt76_set(dev, WF_WFDMA0_GLO_CFG_EXT0 + hif1_ofs,
 			 WF_WFDMA0_GLO_CFG_EXT0_RX_WB_RXD |
@@ -216,23 +247,7 @@ static int mt7996_dma_enable(struct mt7996_dev *dev)
 		/* TODO: redirect rx ring6 interrupt to pcie0 for wed function */
 	}
 
-	/* enable interrupts for TX/RX rings */
-	irq_mask = MT_INT_RX_DONE_MCU |
-		   MT_INT_TX_DONE_MCU |
-		   MT_INT_MCU_CMD;
-
-	if (!dev->mphy.band_idx)
-		irq_mask |= MT_INT_BAND0_RX_DONE;
-
-	if (dev->dbdc_support)
-		irq_mask |= MT_INT_BAND1_RX_DONE;
-
-	if (dev->tbtc_support)
-		irq_mask |= MT_INT_BAND2_RX_DONE;
-
-	mt7996_irq_enable(dev, irq_mask);
-
-	return 0;
+	mt7996_dma_start(dev, reset);
 }
 
 int mt7996_dma_init(struct mt7996_dev *dev)
@@ -347,7 +362,7 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 			  mt7996_poll_tx);
 	napi_enable(&dev->mt76.tx_napi);
 
-	mt7996_dma_enable(dev);
+	mt7996_dma_enable(dev, false);
 
 	return 0;
 }
@@ -413,7 +428,7 @@ void mt7996_dma_reset(struct mt7996_dev *dev, bool force)
 	mt76_for_each_q_rx(&dev->mt76, i)
 		mt76_queue_rx_reset(dev, i);
 
-	mt7996_dma_enable(dev);
+	mt7996_dma_enable(dev, !force);
 }
 
 void mt7996_dma_cleanup(struct mt7996_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index d05d7e79781f6..de15909033183 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2051,6 +2051,12 @@ void mt7996_mac_reset_work(struct work_struct *work)
 		mt7996_wait_reset_state(dev, MT_MCU_CMD_RECOVERY_DONE);
 	}
 
+	mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_RESET_DONE);
+	mt7996_wait_reset_state(dev, MT_MCU_CMD_NORMAL_STATE);
+
+	/* enable DMA Tx/Tx and interrupt */
+	mt7996_dma_start(dev, false);
+
 	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
 	clear_bit(MT76_RESET, &dev->mphy.state);
 	if (phy2)
@@ -2067,9 +2073,6 @@ void mt7996_mac_reset_work(struct work_struct *work)
 
 	tasklet_schedule(&dev->mt76.irq_tasklet);
 
-	mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_RESET_DONE);
-	mt7996_wait_reset_state(dev, MT_MCU_CMD_NORMAL_STATE);
-
 	mt76_worker_enable(&dev->mt76.tx_worker);
 
 	local_bh_disable();
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 348d3ad3f9e75..7b74477abbe3f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -351,6 +351,7 @@ int mt7996_dma_init(struct mt7996_dev *dev);
 void mt7996_dma_reset(struct mt7996_dev *dev, bool force);
 void mt7996_dma_prefetch(struct mt7996_dev *dev);
 void mt7996_dma_cleanup(struct mt7996_dev *dev);
+void mt7996_dma_start(struct mt7996_dev *dev, bool reset);
 void mt7996_init_txpower(struct mt7996_dev *dev,
 			 struct ieee80211_supported_band *sband);
 int mt7996_txbf_init(struct mt7996_dev *dev);
-- 
GitLab


From 0dde9c11cf58c1720556c778737d28d1945c8e07 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 27 May 2023 13:23:46 +0200
Subject: [PATCH 0407/1806] wifi: mt76: mt7921: make mt7921_mac_sta_poll static

Make mt7921_mac_sta_poll static since it is run just in mac.c

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/mac.c    | 3 +--
 drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 2d3f394039f6f..49f44b1e8d519 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -52,7 +52,7 @@ bool mt7921_mac_wtbl_update(struct mt7921_dev *dev, int idx, u32 mask)
 			 0, 5000);
 }
 
-void mt7921_mac_sta_poll(struct mt7921_dev *dev)
+static void mt7921_mac_sta_poll(struct mt7921_dev *dev)
 {
 	static const u8 ac_to_tid[] = {
 		[IEEE80211_AC_BE] = 0,
@@ -183,7 +183,6 @@ void mt7921_mac_sta_poll(struct mt7921_dev *dev)
 		ewma_avg_signal_add(&msta->avg_ack_signal, -msta->ack_signal);
 	}
 }
-EXPORT_SYMBOL_GPL(mt7921_mac_sta_poll);
 
 static void
 mt7921_get_status_freq_info(struct mt7921_dev *dev, struct mt76_phy *mphy,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 3776055201d06..523b177e23cd5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -484,7 +484,6 @@ int mt7921_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *msg,
 void mt7921_txwi_free(struct mt7921_dev *dev, struct mt76_txwi_cache *t,
 		      struct ieee80211_sta *sta, bool clear_status,
 		      struct list_head *free_list);
-void mt7921_mac_sta_poll(struct mt7921_dev *dev);
 int mt7921_mcu_parse_response(struct mt76_dev *mdev, int cmd,
 			      struct sk_buff *skb, int seq);
 
-- 
GitLab


From c4f0755823045b66484fb53d686f85d3151400f4 Mon Sep 17 00:00:00 2001
From: Rany Hany <rany_hany@riseup.net>
Date: Sun, 28 May 2023 21:04:28 +0300
Subject: [PATCH 0408/1806] wifi: mt76: mt7915: fix command timeout in AP stop
 period

Due to AP stop improperly, mt7915 driver would face random command timeout
by chip fw problem. Migrate AP start/stop process to .start_ap/.stop_ap and
congiure BSS network settings in both hooks.

The new flow is shown below.
* AP start
    .start_ap()
      configure BSS network resource
      set BSS to connected state
    .bss_info_changed()
      enable fw beacon offload

* AP stop
    .bss_info_changed()
      disable fw beacon offload (skip this command)
    .stop_ap()
      set BSS to disconnected state (beacon offload disabled automatically)
      destroy BSS network resource

Based on "mt76: mt7921: fix command timeout in AP stop period"

Signed-off-by: Rany Hany <rany_hany@riseup.net>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7915/main.c  | 63 +++++++++++++++----
 1 file changed, 50 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index 64c02734a3f21..679397dddf0f1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -599,6 +599,7 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw,
 {
 	struct mt7915_phy *phy = mt7915_hw_phy(hw);
 	struct mt7915_dev *dev = mt7915_hw_dev(hw);
+	int set_bss_info = -1, set_sta = -1;
 
 	mutex_lock(&dev->mt76.mutex);
 
@@ -607,15 +608,18 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw,
 	 * and then peer references bss_info_rfch to set bandwidth cap.
 	 */
 	if (changed & BSS_CHANGED_BSSID &&
-	    vif->type == NL80211_IFTYPE_STATION) {
-		bool join = !is_zero_ether_addr(info->bssid);
-
-		mt7915_mcu_add_bss_info(phy, vif, join);
-		mt7915_mcu_add_sta(dev, vif, NULL, join);
-	}
-
+	    vif->type == NL80211_IFTYPE_STATION)
+		set_bss_info = set_sta = !is_zero_ether_addr(info->bssid);
 	if (changed & BSS_CHANGED_ASSOC)
-		mt7915_mcu_add_bss_info(phy, vif, vif->cfg.assoc);
+		set_bss_info = vif->cfg.assoc;
+	if (changed & BSS_CHANGED_BEACON_ENABLED &&
+	    vif->type != NL80211_IFTYPE_AP)
+		set_bss_info = set_sta = info->enable_beacon;
+
+	if (set_bss_info == 1)
+		mt7915_mcu_add_bss_info(phy, vif, true);
+	if (set_sta == 1)
+		mt7915_mcu_add_sta(dev, vif, NULL, true);
 
 	if (changed & BSS_CHANGED_ERP_CTS_PROT)
 		mt7915_mac_enable_rtscts(dev, vif, info->use_cts_prot);
@@ -629,11 +633,6 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw,
 		}
 	}
 
-	if (changed & BSS_CHANGED_BEACON_ENABLED && info->enable_beacon) {
-		mt7915_mcu_add_bss_info(phy, vif, true);
-		mt7915_mcu_add_sta(dev, vif, NULL, true);
-	}
-
 	/* ensure that enable txcmd_mode after bss_info */
 	if (changed & (BSS_CHANGED_QOS | BSS_CHANGED_BEACON_ENABLED))
 		mt7915_mcu_set_tx(dev, vif);
@@ -650,6 +649,42 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw,
 		       BSS_CHANGED_FILS_DISCOVERY))
 		mt7915_mcu_add_beacon(hw, vif, info->enable_beacon, changed);
 
+	if (set_bss_info == 0)
+		mt7915_mcu_add_bss_info(phy, vif, false);
+	if (set_sta == 0)
+		mt7915_mcu_add_sta(dev, vif, NULL, false);
+
+	mutex_unlock(&dev->mt76.mutex);
+}
+
+static int
+mt7915_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		struct ieee80211_bss_conf *link_conf)
+{
+	struct mt7915_phy *phy = mt7915_hw_phy(hw);
+	struct mt7915_dev *dev = mt7915_hw_dev(hw);
+	int err;
+
+	mutex_lock(&dev->mt76.mutex);
+
+	err = mt7915_mcu_add_bss_info(phy, vif, true);
+	if (err)
+		goto out;
+	err = mt7915_mcu_add_sta(dev, vif, NULL, true);
+out:
+	mutex_unlock(&dev->mt76.mutex);
+
+	return err;
+}
+
+static void
+mt7915_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+	       struct ieee80211_bss_conf *link_conf)
+{
+	struct mt7915_dev *dev = mt7915_hw_dev(hw);
+
+	mutex_lock(&dev->mt76.mutex);
+	mt7915_mcu_add_sta(dev, vif, NULL, false);
 	mutex_unlock(&dev->mt76.mutex);
 }
 
@@ -1594,6 +1629,8 @@ const struct ieee80211_ops mt7915_ops = {
 	.conf_tx = mt7915_conf_tx,
 	.configure_filter = mt7915_configure_filter,
 	.bss_info_changed = mt7915_bss_info_changed,
+	.start_ap = mt7915_start_ap,
+	.stop_ap = mt7915_stop_ap,
 	.sta_add = mt7915_sta_add,
 	.sta_remove = mt7915_sta_remove,
 	.sta_pre_rcu_remove = mt76_sta_pre_rcu_remove,
-- 
GitLab


From d82e7c67b318e6f0399b72a9821a51e693a40381 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Mon, 29 May 2023 16:54:32 +0200
Subject: [PATCH 0409/1806] mt76: mt7996: rely on mt76_sta_stats in mt76_wcid

mt76 now accounts station stats in mt76_sta_stats available in mt76_wcid
struct. Get rid of mt7996 private copy.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c    | 7 ++++---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c   | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h | 2 --
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index de15909033183..bc8b9a6fc5a13 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -1329,9 +1329,10 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 }
 
 static bool
-mt7996_mac_add_txs_skb(struct mt7996_dev *dev, struct mt76_wcid *wcid, int pid,
-		       __le32 *txs_data, struct mt76_sta_stats *stats)
+mt7996_mac_add_txs_skb(struct mt7996_dev *dev, struct mt76_wcid *wcid,
+		       int pid, __le32 *txs_data)
 {
+	struct mt76_sta_stats *stats = &wcid->stats;
 	struct ieee80211_supported_band *sband;
 	struct mt76_dev *mdev = &dev->mt76;
 	struct mt76_phy *mphy;
@@ -1493,7 +1494,7 @@ static void mt7996_mac_add_txs(struct mt7996_dev *dev, void *data)
 
 	msta = container_of(wcid, struct mt7996_sta, wcid);
 
-	mt7996_mac_add_txs_skb(dev, wcid, pid, txs_data, &msta->stats);
+	mt7996_mac_add_txs_skb(dev, wcid, pid, txs_data);
 
 	if (!wcid->sta)
 		goto out;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 073a9f91d9a5d..7d674114653c4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1214,7 +1214,7 @@ static void mt7996_ethtool_worker(void *wi_data, struct ieee80211_sta *sta)
 	if (msta->vif->mt76.idx != wi->idx)
 		return;
 
-	mt76_ethtool_worker(wi, &msta->stats, true);
+	mt76_ethtool_worker(wi, &msta->wcid.stats, true);
 }
 
 static
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 7b74477abbe3f..fdc443b023802 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -106,8 +106,6 @@ struct mt7996_sta {
 	unsigned long jiffies;
 	unsigned long ampdu_state;
 
-	struct mt76_sta_stats stats;
-
 	struct mt76_connac_sta_key_conf bip;
 
 	struct {
-- 
GitLab


From f124ed65ab185ef6148b4cdc4207a5b0a0faa206 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Mon, 5 Jun 2023 08:51:43 +0200
Subject: [PATCH 0410/1806] wifi: mt76: mt7921: get rid of MT7921_RESET_TIMEOUT
 marco

MT7921_RESET_TIMEOUT is never used, so get rid of it.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 523b177e23cd5..7cad215cb748d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -19,7 +19,6 @@
 #define MT7921_PM_TIMEOUT		(HZ / 12)
 #define MT7921_HW_SCAN_TIMEOUT		(HZ / 10)
 #define MT7921_WATCHDOG_TIME		(HZ / 4)
-#define MT7921_RESET_TIMEOUT		(30 * HZ)
 
 #define MT7921_TX_RING_SIZE		2048
 #define MT7921_TX_MCU_RING_SIZE		256
-- 
GitLab


From d73dab22e7a8a8f31283ef90315bff085809b5cf Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Mon, 5 Jun 2023 23:21:32 +0800
Subject: [PATCH 0411/1806] wifi: mt76: mt7996: move radio ctrl commands to
 proper functions

Move radio enable/disable commands into functions for configuring
per-phy radio.

Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 7d674114653c4..9e5057df5f442 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -43,6 +43,10 @@ int mt7996_run(struct ieee80211_hw *hw)
 	if (ret)
 		goto out;
 
+	ret = mt7996_mcu_set_radio_en(phy, true);
+	if (ret)
+		goto out;
+
 	ret = mt7996_mcu_set_chan_info(phy, UNI_CHANNEL_RX_PATH);
 	if (ret)
 		goto out;
@@ -82,6 +86,8 @@ static void mt7996_stop(struct ieee80211_hw *hw)
 
 	mutex_lock(&dev->mt76.mutex);
 
+	mt7996_mcu_set_radio_en(phy, false);
+
 	clear_bit(MT76_STATE_RUNNING, &phy->mt76->state);
 
 	mutex_unlock(&dev->mt76.mutex);
@@ -190,10 +196,6 @@ static int mt7996_add_interface(struct ieee80211_hw *hw,
 	if (ret)
 		goto out;
 
-	ret = mt7996_mcu_set_radio_en(phy, true);
-	if (ret)
-		goto out;
-
 	dev->mt76.vif_mask |= BIT_ULL(mvif->mt76.idx);
 	phy->omac_mask |= BIT_ULL(mvif->mt76.omac_idx);
 
@@ -253,7 +255,6 @@ static void mt7996_remove_interface(struct ieee80211_hw *hw,
 		phy->monitor_vif = NULL;
 
 	mt7996_mcu_add_dev_info(phy, vif, false);
-	mt7996_mcu_set_radio_en(phy, false);
 
 	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
 
-- 
GitLab


From a32f063dfbe38a70cd670cdc2266b9fafdc998a8 Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Mon, 5 Jun 2023 23:21:33 +0800
Subject: [PATCH 0412/1806] wifi: mt76: connac: add support for dsp firmware
 download

Add FW_START_WORKING_PDA_DSP for the indication of starting DSP
firmware download, which is for phy-related control.
The firmware is transparent to the driver, but it's necessary for the
firmware download process.

Reviewed-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt76_connac_mcu.h  |  1 +
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 67 +++++++++----------
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  7 ++
 .../net/wireless/mediatek/mt76/mt7996/pci.c   |  1 +
 4 files changed, 42 insertions(+), 34 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index 7a52b68491b6e..ede011e88008f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -22,6 +22,7 @@
 
 #define FW_START_OVERRIDE		BIT(0)
 #define FW_START_WORKING_PDA_CR4	BIT(2)
+#define FW_START_WORKING_PDA_DSP	BIT(3)
 
 #define PATCH_SEC_NOT_SUPPORT		GENMASK(31, 0)
 #define PATCH_SEC_TYPE_MASK		GENMASK(15, 0)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 88e2f9d0e5130..545cc98749ac1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -2155,7 +2155,7 @@ out:
 static int
 mt7996_mcu_send_ram_firmware(struct mt7996_dev *dev,
 			     const struct mt7996_fw_trailer *hdr,
-			     const u8 *data, bool is_wa)
+			     const u8 *data, enum mt7996_ram_type type)
 {
 	int i, offset = 0;
 	u32 override = 0, option = 0;
@@ -2167,8 +2167,10 @@ mt7996_mcu_send_ram_firmware(struct mt7996_dev *dev,
 
 		region = (const struct mt7996_fw_region *)((const u8 *)hdr -
 			 (hdr->n_region - i) * sizeof(*region));
+		/* DSP and WA use same mode */
 		mode = mt76_connac_mcu_gen_dl_mode(&dev->mt76,
-						   region->feature_set, is_wa);
+						   region->feature_set,
+						   type != MT7996_RAM_TYPE_WM);
 		len = le32_to_cpu(region->len);
 		addr = le32_to_cpu(region->addr);
 
@@ -2195,19 +2197,22 @@ mt7996_mcu_send_ram_firmware(struct mt7996_dev *dev,
 	if (override)
 		option |= FW_START_OVERRIDE;
 
-	if (is_wa)
+	if (type == MT7996_RAM_TYPE_WA)
 		option |= FW_START_WORKING_PDA_CR4;
+	else if (type == MT7996_RAM_TYPE_DSP)
+		option |= FW_START_WORKING_PDA_DSP;
 
 	return mt76_connac_mcu_start_firmware(&dev->mt76, override, option);
 }
 
-static int mt7996_load_ram(struct mt7996_dev *dev)
+static int __mt7996_load_ram(struct mt7996_dev *dev, const char *fw_type,
+			     const char *fw_file, enum mt7996_ram_type ram_type)
 {
 	const struct mt7996_fw_trailer *hdr;
 	const struct firmware *fw;
 	int ret;
 
-	ret = request_firmware(&fw, MT7996_FIRMWARE_WM, dev->mt76.dev);
+	ret = request_firmware(&fw, fw_file, dev->mt76.dev);
 	if (ret)
 		return ret;
 
@@ -2217,37 +2222,13 @@ static int mt7996_load_ram(struct mt7996_dev *dev)
 		goto out;
 	}
 
-	hdr = (const struct mt7996_fw_trailer *)(fw->data + fw->size - sizeof(*hdr));
-
-	dev_info(dev->mt76.dev, "WM Firmware Version: %.10s, Build Time: %.15s\n",
-		 hdr->fw_ver, hdr->build_date);
+	hdr = (const void *)(fw->data + fw->size - sizeof(*hdr));
+	dev_info(dev->mt76.dev, "%s Firmware Version: %.10s, Build Time: %.15s\n",
+		 fw_type, hdr->fw_ver, hdr->build_date);
 
-	ret = mt7996_mcu_send_ram_firmware(dev, hdr, fw->data, false);
+	ret = mt7996_mcu_send_ram_firmware(dev, hdr, fw->data, ram_type);
 	if (ret) {
-		dev_err(dev->mt76.dev, "Failed to start WM firmware\n");
-		goto out;
-	}
-
-	release_firmware(fw);
-
-	ret = request_firmware(&fw, MT7996_FIRMWARE_WA, dev->mt76.dev);
-	if (ret)
-		return ret;
-
-	if (!fw || !fw->data || fw->size < sizeof(*hdr)) {
-		dev_err(dev->mt76.dev, "Invalid firmware\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	hdr = (const struct mt7996_fw_trailer *)(fw->data + fw->size - sizeof(*hdr));
-
-	dev_info(dev->mt76.dev, "WA Firmware Version: %.10s, Build Time: %.15s\n",
-		 hdr->fw_ver, hdr->build_date);
-
-	ret = mt7996_mcu_send_ram_firmware(dev, hdr, fw->data, true);
-	if (ret) {
-		dev_err(dev->mt76.dev, "Failed to start WA firmware\n");
+		dev_err(dev->mt76.dev, "Failed to start %s firmware\n", fw_type);
 		goto out;
 	}
 
@@ -2261,6 +2242,24 @@ out:
 	return ret;
 }
 
+static int mt7996_load_ram(struct mt7996_dev *dev)
+{
+	int ret;
+
+	ret = __mt7996_load_ram(dev, "WM", MT7996_FIRMWARE_WM,
+				MT7996_RAM_TYPE_WM);
+	if (ret)
+		return ret;
+
+	ret = __mt7996_load_ram(dev, "DSP", MT7996_FIRMWARE_DSP,
+				MT7996_RAM_TYPE_DSP);
+	if (ret)
+		return ret;
+
+	return __mt7996_load_ram(dev, "WA", MT7996_FIRMWARE_WA,
+				 MT7996_RAM_TYPE_WA);
+}
+
 static int
 mt7996_firmware_state(struct mt7996_dev *dev, bool wa)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index fdc443b023802..ae47412172eb5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -29,6 +29,7 @@
 
 #define MT7996_FIRMWARE_WA		"mediatek/mt7996/mt7996_wa.bin"
 #define MT7996_FIRMWARE_WM		"mediatek/mt7996/mt7996_wm.bin"
+#define MT7996_FIRMWARE_DSP		"mediatek/mt7996/mt7996_dsp.bin"
 #define MT7996_ROM_PATCH		"mediatek/mt7996/mt7996_rom_patch.bin"
 
 #define MT7996_EEPROM_DEFAULT		"mediatek/mt7996/mt7996_eeprom.bin"
@@ -52,6 +53,12 @@ struct mt7996_sta;
 struct mt7996_dfs_pulse;
 struct mt7996_dfs_pattern;
 
+enum mt7996_ram_type {
+	MT7996_RAM_TYPE_WM,
+	MT7996_RAM_TYPE_WA,
+	MT7996_RAM_TYPE_DSP,
+};
+
 enum mt7996_txq_id {
 	MT7996_TXQ_FWDL = 16,
 	MT7996_TXQ_MCU_WM,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/pci.c b/drivers/net/wireless/mediatek/mt76/mt7996/pci.c
index 64aee3fb54457..c5301050ff8b3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/pci.c
@@ -219,4 +219,5 @@ MODULE_DEVICE_TABLE(pci, mt7996_pci_device_table);
 MODULE_DEVICE_TABLE(pci, mt7996_hif_device_table);
 MODULE_FIRMWARE(MT7996_FIRMWARE_WA);
 MODULE_FIRMWARE(MT7996_FIRMWARE_WM);
+MODULE_FIRMWARE(MT7996_FIRMWARE_DSP);
 MODULE_FIRMWARE(MT7996_ROM_PATCH);
-- 
GitLab


From cc945b546227423488fe4be0ab92fd126b703246 Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Mon, 5 Jun 2023 23:21:34 +0800
Subject: [PATCH 0413/1806] wifi: mt76: mt7996: fix bss wlan_idx when sending
 bss_info command

The bmc_tx_wlan_idx should be the wlan_idx of the current bss rather
than peer AP's wlan_idx, otherwise there will appear some frame
decryption problems on station mode.

Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Reviewed-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 545cc98749ac1..6706d38cf4cf0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -712,6 +712,7 @@ mt7996_mcu_bss_basic_tlv(struct sk_buff *skb,
 	struct cfg80211_chan_def *chandef = &phy->chandef;
 	struct mt76_connac_bss_basic_tlv *bss;
 	u32 type = CONNECTION_INFRA_AP;
+	u16 sta_wlan_idx = wlan_idx;
 	struct tlv *tlv;
 	int idx;
 
@@ -731,7 +732,7 @@ mt7996_mcu_bss_basic_tlv(struct sk_buff *skb,
 				struct mt76_wcid *wcid;
 
 				wcid = (struct mt76_wcid *)sta->drv_priv;
-				wlan_idx = wcid->idx;
+				sta_wlan_idx = wcid->idx;
 			}
 			rcu_read_unlock();
 		}
@@ -751,7 +752,7 @@ mt7996_mcu_bss_basic_tlv(struct sk_buff *skb,
 	bss->bcn_interval = cpu_to_le16(vif->bss_conf.beacon_int);
 	bss->dtim_period = vif->bss_conf.dtim_period;
 	bss->bmc_tx_wlan_idx = cpu_to_le16(wlan_idx);
-	bss->sta_idx = cpu_to_le16(wlan_idx);
+	bss->sta_idx = cpu_to_le16(sta_wlan_idx);
 	bss->conn_type = cpu_to_le32(type);
 	bss->omac_idx = mvif->omac_idx;
 	bss->band_idx = mvif->band_idx;
-- 
GitLab


From 2b8ca09062b1bee0253b121c48345505df0c84aa Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Mon, 5 Jun 2023 23:21:36 +0800
Subject: [PATCH 0414/1806] wifi: mt76: mt7996: enable VHT extended NSS BW
 feature

Set SUPPORTS_VHT_EXT_NSS_BW to let the max BW capability correctly be
parsed by different devices.

Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/init.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
index 3569fef20cd94..38ff33a7fc12c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
@@ -218,6 +218,8 @@ mt7996_init_wiphy(struct ieee80211_hw *hw)
 			IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ;
 		phy->mt76->sband_5g.sband.ht_cap.ampdu_density =
 			IEEE80211_HT_MPDU_DENSITY_1;
+
+		ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW);
 	}
 
 	mt76_set_stream_caps(phy->mt76, true);
-- 
GitLab


From 83a10ae2d4c5b00fd597a7a7a5e7ceefef9bd116 Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Mon, 5 Jun 2023 23:21:37 +0800
Subject: [PATCH 0415/1806] wifi: mt76: connac: add support to set ifs time by
 mcu command

There's a race between driver and fw on some tx/rx control registers
when setting ifs, which will cause accidental hw queue pause problems.
Avoid this by setting ifs time with bss_info mcu command.

Reviewed-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt76_connac_mcu.h  |  1 +
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 27 +----------
 .../net/wireless/mediatek/mt76/mt7996/main.c  |  5 +-
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 46 +++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7996/mcu.h   | 17 +++++++
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  3 +-
 6 files changed, 70 insertions(+), 29 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index ede011e88008f..dcbb608360bfc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -1289,6 +1289,7 @@ enum {
 	UNI_BSS_INFO_UAPSD = 19,
 	UNI_BSS_INFO_PS = 21,
 	UNI_BSS_INFO_BCNFT = 22,
+	UNI_BSS_INFO_IFS_TIME = 23,
 	UNI_BSS_INFO_OFFLOAD = 25,
 	UNI_BSS_INFO_MLD = 26,
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index bc8b9a6fc5a13..a39bb39af5404 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -1615,20 +1615,19 @@ void mt7996_mac_reset_counters(struct mt7996_phy *phy)
 	mt7996_mcu_get_chan_mib_info(phy, true);
 }
 
-void mt7996_mac_set_timing(struct mt7996_phy *phy)
+void mt7996_mac_set_coverage_class(struct mt7996_phy *phy)
 {
 	s16 coverage_class = phy->coverage_class;
 	struct mt7996_dev *dev = phy->dev;
 	struct mt7996_phy *phy2 = mt7996_phy2(dev);
 	struct mt7996_phy *phy3 = mt7996_phy3(dev);
-	u32 val, reg_offset;
+	u32 reg_offset;
 	u32 cck = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, 231) |
 		  FIELD_PREP(MT_TIMEOUT_VAL_CCA, 48);
 	u32 ofdm = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, 60) |
 		   FIELD_PREP(MT_TIMEOUT_VAL_CCA, 28);
 	u8 band_idx = phy->mt76->band_idx;
 	int offset;
-	bool a_band = !(phy->mt76->chandef.chan->band == NL80211_BAND_2GHZ);
 
 	if (!test_bit(MT76_STATE_RUNNING, &phy->mt76->state))
 		return;
@@ -1641,34 +1640,12 @@ void mt7996_mac_set_timing(struct mt7996_phy *phy)
 		coverage_class = max_t(s16, coverage_class,
 				       phy3->coverage_class);
 
-	mt76_set(dev, MT_ARB_SCR(band_idx),
-		 MT_ARB_SCR_TX_DISABLE | MT_ARB_SCR_RX_DISABLE);
-	udelay(1);
-
 	offset = 3 * coverage_class;
 	reg_offset = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, offset) |
 		     FIELD_PREP(MT_TIMEOUT_VAL_CCA, offset);
 
 	mt76_wr(dev, MT_TMAC_CDTR(band_idx), cck + reg_offset);
 	mt76_wr(dev, MT_TMAC_ODTR(band_idx), ofdm + reg_offset);
-	mt76_wr(dev, MT_TMAC_ICR0(band_idx),
-		FIELD_PREP(MT_IFS_EIFS_OFDM, a_band ? 84 : 78) |
-		FIELD_PREP(MT_IFS_RIFS, 2) |
-		FIELD_PREP(MT_IFS_SIFS, 10) |
-		FIELD_PREP(MT_IFS_SLOT, phy->slottime));
-
-	if (!a_band)
-		mt76_wr(dev, MT_TMAC_ICR1(band_idx),
-			FIELD_PREP(MT_IFS_EIFS_CCK, 314));
-
-	if (phy->slottime < 20 || a_band)
-		val = MT7996_CFEND_RATE_DEFAULT;
-	else
-		val = MT7996_CFEND_RATE_11B;
-
-	mt76_rmw_field(dev, MT_RATE_HRCR0(band_idx), MT_RATE_HRCR0_CFEND_RATE, val);
-	mt76_clear(dev, MT_ARB_SCR(band_idx),
-		   MT_ARB_SCR_TX_DISABLE | MT_ARB_SCR_RX_DISABLE);
 }
 
 void mt7996_mac_enable_nf(struct mt7996_dev *dev, u8 band)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 9e5057df5f442..f173d197fcf64 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -287,7 +287,6 @@ int mt7996_set_channel(struct mt7996_phy *phy)
 	if (ret)
 		goto out;
 
-	mt7996_mac_set_timing(phy);
 	ret = mt7996_dfs_init_radar_detector(phy);
 	mt7996_mac_cca_stats_reset(phy);
 
@@ -584,7 +583,7 @@ static void mt7996_bss_info_changed(struct ieee80211_hw *hw,
 
 		if (slottime != phy->slottime) {
 			phy->slottime = slottime;
-			mt7996_mac_set_timing(phy);
+			mt7996_mcu_set_timing(phy, vif);
 		}
 	}
 
@@ -927,7 +926,7 @@ mt7996_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class)
 
 	mutex_lock(&dev->mt76.mutex);
 	phy->coverage_class = max_t(s16, coverage_class, 0);
-	mt7996_mac_set_timing(phy);
+	mt7996_mac_set_coverage_class(phy);
 	mutex_unlock(&dev->mt76.mutex);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 6706d38cf4cf0..0ede9769a8e8e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -701,6 +701,34 @@ mt7996_mcu_muar_config(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 				 sizeof(req), true);
 }
 
+static void
+mt7996_mcu_bss_ifs_timing_tlv(struct sk_buff *skb, struct ieee80211_vif *vif)
+{
+	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_phy *phy = mvif->phy;
+	struct bss_ifs_time_tlv *ifs_time;
+	struct tlv *tlv;
+	bool is_2ghz = phy->mt76->chandef.chan->band == NL80211_BAND_2GHZ;
+
+	tlv = mt7996_mcu_add_uni_tlv(skb, UNI_BSS_INFO_IFS_TIME, sizeof(*ifs_time));
+
+	ifs_time = (struct bss_ifs_time_tlv *)tlv;
+	ifs_time->slot_valid = true;
+	ifs_time->sifs_valid = true;
+	ifs_time->rifs_valid = true;
+	ifs_time->eifs_valid = true;
+
+	ifs_time->slot_time = cpu_to_le16(phy->slottime);
+	ifs_time->sifs_time = cpu_to_le16(10);
+	ifs_time->rifs_time = cpu_to_le16(2);
+	ifs_time->eifs_time = cpu_to_le16(is_2ghz ? 78 : 84);
+
+	if (is_2ghz) {
+		ifs_time->eifs_cck_valid = true;
+		ifs_time->eifs_cck_time = cpu_to_le16(314);
+	}
+}
+
 static int
 mt7996_mcu_bss_basic_tlv(struct sk_buff *skb,
 			 struct ieee80211_vif *vif,
@@ -826,6 +854,7 @@ int mt7996_mcu_add_bss_info(struct mt7996_phy *phy,
 		mt7996_mcu_bss_bmc_tlv(skb, vif, phy);
 		mt7996_mcu_bss_ra_tlv(skb, vif, phy);
 		mt7996_mcu_bss_txcmd_tlv(skb, true);
+		mt7996_mcu_bss_ifs_timing_tlv(skb, vif);
 
 		if (vif->bss_conf.he_support)
 			mt7996_mcu_bss_he_tlv(skb, vif, phy);
@@ -838,6 +867,23 @@ out:
 				     MCU_WMWA_UNI_CMD(BSS_INFO_UPDATE), true);
 }
 
+int mt7996_mcu_set_timing(struct mt7996_phy *phy, struct ieee80211_vif *vif)
+{
+	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_dev *dev = phy->dev;
+	struct sk_buff *skb;
+
+	skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->mt76,
+					 MT7996_BSS_UPDATE_MAX_SIZE);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	mt7996_mcu_bss_ifs_timing_tlv(skb, vif);
+
+	return mt76_mcu_skb_send_msg(&dev->mt76, skb,
+				     MCU_WMWA_UNI_CMD(BSS_INFO_UPDATE), true);
+}
+
 static int
 mt7996_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif,
 		  struct ieee80211_ampdu_params *params,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
index d7075a4d0667c..078f828586212 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
@@ -317,6 +317,22 @@ struct bss_sec_tlv {
 	u8 __rsv2[1];
 } __packed;
 
+struct bss_ifs_time_tlv {
+	__le16 tag;
+	__le16 len;
+	u8 slot_valid;
+	u8 sifs_valid;
+	u8 rifs_valid;
+	u8 eifs_valid;
+	__le16 slot_time;
+	__le16 sifs_time;
+	__le16 rifs_time;
+	__le16 eifs_time;
+	u8 eifs_cck_valid;
+	u8 rsv;
+	__le16 eifs_cck_time;
+} __packed;
+
 struct bss_power_save {
 	__le16 tag;
 	__le16 len;
@@ -552,6 +568,7 @@ enum {
 					 sizeof(struct bss_txcmd_tlv) +		\
 					 sizeof(struct bss_power_save) +	\
 					 sizeof(struct bss_sec_tlv) +		\
+					 sizeof(struct bss_ifs_time_tlv) +	\
 					 sizeof(struct bss_mld_tlv))
 
 #define MT7996_STA_UPDATE_MAX_SIZE	(sizeof(struct sta_req_hdr) +		\
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index ae47412172eb5..7862e66efc85c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -408,6 +408,7 @@ int mt7996_mcu_set_radar_th(struct mt7996_dev *dev, int index,
 			    const struct mt7996_dfs_pattern *pattern);
 int mt7996_mcu_set_radio_en(struct mt7996_phy *phy, bool enable);
 int mt7996_mcu_set_rts_thresh(struct mt7996_phy *phy, u32 val);
+int mt7996_mcu_set_timing(struct mt7996_phy *phy, struct ieee80211_vif *vif);
 int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch);
 int mt7996_mcu_rdd_cmd(struct mt7996_dev *dev, int cmd, u8 index,
 		       u8 rx_sel, u8 val);
@@ -471,7 +472,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 			   struct sk_buff *skb, struct mt76_wcid *wcid,
 			   struct ieee80211_key_conf *key, int pid,
 			   enum mt76_txq_id qid, u32 changed);
-void mt7996_mac_set_timing(struct mt7996_phy *phy);
+void mt7996_mac_set_coverage_class(struct mt7996_phy *phy);
 int mt7996_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
 void mt7996_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-- 
GitLab


From 9ffe0d5690ed916e09baad2cc9ee7ec65b110038 Mon Sep 17 00:00:00 2001
From: StanleyYP Wang <StanleyYP.Wang@mediatek.com>
Date: Mon, 5 Jun 2023 23:21:38 +0800
Subject: [PATCH 0416/1806] wifi: mt76: mt7996: use correct phy for background
 radar event

If driver directly uses the band_idx reported from the radar event to
access mt76_phy array, it will get the wrong phy for background radar.
Fix this by adjusting the statement.

Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Signed-off-by: StanleyYP Wang <StanleyYP.Wang@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 0ede9769a8e8e..20519bffce212 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -339,7 +339,11 @@ mt7996_mcu_rx_radar_detected(struct mt7996_dev *dev, struct sk_buff *skb)
 	if (r->band_idx >= ARRAY_SIZE(dev->mt76.phys))
 		return;
 
-	mphy = dev->mt76.phys[r->band_idx];
+	if (dev->rdd2_phy && r->band_idx == MT_RX_SEL2)
+		mphy = dev->rdd2_phy->mt76;
+	else
+		mphy = dev->mt76.phys[r->band_idx];
+
 	if (!mphy)
 		return;
 
-- 
GitLab


From 1634de418b3048c5f435b6ffd37f75943c554c04 Mon Sep 17 00:00:00 2001
From: StanleyYP Wang <StanleyYP.Wang@mediatek.com>
Date: Mon, 5 Jun 2023 23:21:39 +0800
Subject: [PATCH 0417/1806] wifi: mt76: mt7996: fix WA event ring size

Fix rx ring size of WA event to get rid of event loss and queue overflow
problems.

Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Signed-off-by: StanleyYP Wang <StanleyYP.Wang@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/dma.c    | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
index 99b00a1357119..586e247a1e064 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
@@ -308,7 +308,7 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 	/* event from WA */
 	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU_WA],
 			       MT_RXQ_ID(MT_RXQ_MCU_WA),
-			       MT7996_RX_MCU_RING_SIZE,
+			       MT7996_RX_MCU_RING_SIZE_WA,
 			       MT_RX_BUF_SIZE,
 			       MT_RXQ_RING_BASE(MT_RXQ_MCU_WA));
 	if (ret)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 7862e66efc85c..d93762c3c587a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -26,6 +26,7 @@
 
 #define MT7996_RX_RING_SIZE		1536
 #define MT7996_RX_MCU_RING_SIZE		512
+#define MT7996_RX_MCU_RING_SIZE_WA	1024
 
 #define MT7996_FIRMWARE_WA		"mediatek/mt7996/mt7996_wa.bin"
 #define MT7996_FIRMWARE_WM		"mediatek/mt7996/mt7996_wm.bin"
-- 
GitLab


From 94f096a14af2647d875ae6a9a09d32eb43393184 Mon Sep 17 00:00:00 2001
From: MeiChia Chiu <MeiChia.Chiu@mediatek.com>
Date: Mon, 5 Jun 2023 23:21:40 +0800
Subject: [PATCH 0418/1806] wifi: mt76: mt7996: add muru support

Add sta_rec_muru() fw command to support MU-MIMO and OFDMA features.

Signed-off-by: MeiChia Chiu <meichia.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt76_connac_mcu.h  |  3 +-
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 56 ++++++++++++++++++-
 2 files changed, 57 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index dcbb608360bfc..4543e5bf0482d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -519,7 +519,8 @@ struct sta_rec_muru {
 		u8 uo_ra;
 		u8 he_2x996_tone;
 		u8 rx_t_frame_11ac;
-		u8 rsv[3];
+		u8 rx_ctrl_frame_to_mbss;
+		u8 rsv[2];
 	} ofdma_ul;
 
 	struct {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 20519bffce212..611f6450520b5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -1101,6 +1101,59 @@ mt7996_mcu_sta_amsdu_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 	}
 }
 
+static void
+mt7996_mcu_sta_muru_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
+			struct ieee80211_vif *vif, struct ieee80211_sta *sta)
+{
+	struct ieee80211_he_cap_elem *elem = &sta->deflink.he_cap.he_cap_elem;
+	struct sta_rec_muru *muru;
+	struct tlv *tlv;
+
+	if (vif->type != NL80211_IFTYPE_STATION &&
+	    vif->type != NL80211_IFTYPE_AP)
+		return;
+
+	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_MURU, sizeof(*muru));
+
+	muru = (struct sta_rec_muru *)tlv;
+	muru->cfg.mimo_dl_en = vif->bss_conf.eht_mu_beamformer ||
+			       vif->bss_conf.he_mu_beamformer ||
+			       vif->bss_conf.vht_mu_beamformer ||
+			       vif->bss_conf.vht_mu_beamformee;
+	muru->cfg.ofdma_dl_en = true;
+
+	if (sta->deflink.vht_cap.vht_supported)
+		muru->mimo_dl.vht_mu_bfee =
+			!!(sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE);
+
+	if (!sta->deflink.he_cap.has_he)
+		return;
+
+	muru->mimo_dl.partial_bw_dl_mimo =
+		HE_PHY(CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO, elem->phy_cap_info[6]);
+
+	muru->mimo_ul.full_ul_mimo =
+		HE_PHY(CAP2_UL_MU_FULL_MU_MIMO, elem->phy_cap_info[2]);
+	muru->mimo_ul.partial_ul_mimo =
+		HE_PHY(CAP2_UL_MU_PARTIAL_MU_MIMO, elem->phy_cap_info[2]);
+
+	muru->ofdma_dl.punc_pream_rx =
+		HE_PHY(CAP1_PREAMBLE_PUNC_RX_MASK, elem->phy_cap_info[1]);
+	muru->ofdma_dl.he_20m_in_40m_2g =
+		HE_PHY(CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G, elem->phy_cap_info[8]);
+	muru->ofdma_dl.he_20m_in_160m =
+		HE_PHY(CAP8_20MHZ_IN_160MHZ_HE_PPDU, elem->phy_cap_info[8]);
+	muru->ofdma_dl.he_80m_in_160m =
+		HE_PHY(CAP8_80MHZ_IN_160MHZ_HE_PPDU, elem->phy_cap_info[8]);
+
+	muru->ofdma_ul.t_frame_dur =
+		HE_MAC(CAP1_TF_MAC_PAD_DUR_MASK, elem->mac_cap_info[1]);
+	muru->ofdma_ul.mu_cascading =
+		HE_MAC(CAP2_MU_CASCADING, elem->mac_cap_info[2]);
+	muru->ofdma_ul.uo_ra =
+		HE_MAC(CAP3_OFDMA_RA, elem->mac_cap_info[3]);
+}
+
 static inline bool
 mt7996_is_ebf_supported(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 			struct ieee80211_sta *sta, bool bfee)
@@ -1778,7 +1831,8 @@ int mt7996_mcu_add_sta(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 		mt7996_mcu_sta_he_6g_tlv(skb, sta);
 		/* starec eht */
 		mt7996_mcu_sta_eht_tlv(skb, sta);
-		/* TODO: starec muru */
+		/* starec muru */
+		mt7996_mcu_sta_muru_tlv(dev, skb, vif, sta);
 		/* starec bfee */
 		mt7996_mcu_sta_bfee_tlv(dev, skb, vif, sta);
 		/* starec hdr trans */
-- 
GitLab


From 037ae6d6d6d547c753334460c9d8d61a7db261df Mon Sep 17 00:00:00 2001
From: Howard Hsu <howard-yh.hsu@mediatek.com>
Date: Mon, 5 Jun 2023 23:21:41 +0800
Subject: [PATCH 0419/1806] wifi: mt76: mt7996: increase tx token size

Align tx token size to proprietary driver, which can improve peak
throughput under MU performance tests.

Signed-off-by: Howard Hsu <howard-yh.hsu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index d93762c3c587a..23de7508c954b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -36,7 +36,7 @@
 #define MT7996_EEPROM_DEFAULT		"mediatek/mt7996/mt7996_eeprom.bin"
 #define MT7996_EEPROM_SIZE		7680
 #define MT7996_EEPROM_BLOCK_SIZE	16
-#define MT7996_TOKEN_SIZE		8192
+#define MT7996_TOKEN_SIZE		16384
 
 #define MT7996_CFEND_RATE_DEFAULT	0x49	/* OFDM 24M */
 #define MT7996_CFEND_RATE_11B		0x03	/* 11B LP, 11M */
-- 
GitLab


From fbba711c3de73c57b476767ba0d5ae1e8b2faa8f Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:18 +0200
Subject: [PATCH 0420/1806] wifi: mt76: mt7915: move sta_poll_list and
 sta_poll_lock in mt76_dev

sta_poll_list and sta_poll_lock are used by most of the drivers, so move
them in mt76_dev structure.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c |  2 +
 drivers/net/wireless/mediatek/mt76/mt76.h     |  3 ++
 .../net/wireless/mediatek/mt76/mt7915/init.c  |  2 -
 .../net/wireless/mediatek/mt76/mt7915/mac.c   | 47 ++++++++++---------
 .../net/wireless/mediatek/mt76/mt7915/main.c  | 12 ++---
 .../wireless/mediatek/mt76/mt7915/mt7915.h    |  2 -
 6 files changed, 36 insertions(+), 32 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 24ebf0504a3b2..c0ff36a98bed3 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -661,6 +661,8 @@ mt76_alloc_device(struct device *pdev, unsigned int size,
 	idr_init(&dev->rx_token);
 
 	INIT_LIST_HEAD(&dev->wcid_list);
+	INIT_LIST_HEAD(&dev->sta_poll_list);
+	spin_lock_init(&dev->sta_poll_lock);
 
 	INIT_LIST_HEAD(&dev->txwi_cache);
 	INIT_LIST_HEAD(&dev->rxwi_cache);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index c11a417c5e37b..6becfcebb9260 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -823,6 +823,9 @@ struct mt76_dev {
 	struct mt76_wcid __rcu *wcid[MT76_N_WCIDS];
 	struct list_head wcid_list;
 
+	struct list_head sta_poll_list;
+	spinlock_t sta_poll_lock;
+
 	u32 rev;
 
 	struct tasklet_struct pre_tbtt_tasklet;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index 07cdf14c515f8..fffab468efebd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -1185,9 +1185,7 @@ int mt7915_register_device(struct mt7915_dev *dev)
 	INIT_WORK(&dev->rc_work, mt7915_mac_sta_rc_work);
 	INIT_DELAYED_WORK(&dev->mphy.mac_work, mt7915_mac_work);
 	INIT_LIST_HEAD(&dev->sta_rc_list);
-	INIT_LIST_HEAD(&dev->sta_poll_list);
 	INIT_LIST_HEAD(&dev->twt_list);
-	spin_lock_init(&dev->sta_poll_lock);
 
 	init_waitqueue_head(&dev->reset_wait);
 	INIT_WORK(&dev->reset_work, mt7915_mac_reset_work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 2bc2fefa1cd08..8ed217ee592ec 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -105,9 +105,9 @@ static void mt7915_mac_sta_poll(struct mt7915_dev *dev)
 	LIST_HEAD(sta_poll_list);
 	int i;
 
-	spin_lock_bh(&dev->sta_poll_lock);
-	list_splice_init(&dev->sta_poll_list, &sta_poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
+	list_splice_init(&dev->mt76.sta_poll_list, &sta_poll_list);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	rcu_read_lock();
 
@@ -118,15 +118,15 @@ static void mt7915_mac_sta_poll(struct mt7915_dev *dev)
 		s8 rssi[4];
 		u8 bw;
 
-		spin_lock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		if (list_empty(&sta_poll_list)) {
-			spin_unlock_bh(&dev->sta_poll_lock);
+			spin_unlock_bh(&dev->mt76.sta_poll_lock);
 			break;
 		}
 		msta = list_first_entry(&sta_poll_list,
 					struct mt7915_sta, poll_list);
 		list_del_init(&msta->poll_list);
-		spin_unlock_bh(&dev->sta_poll_lock);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		idx = msta->wcid.idx;
 
@@ -326,10 +326,11 @@ mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb,
 
 	if (status->wcid) {
 		msta = container_of(status->wcid, struct mt7915_sta, wcid);
-		spin_lock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		if (list_empty(&msta->poll_list))
-			list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-		spin_unlock_bh(&dev->sta_poll_lock);
+			list_add_tail(&msta->poll_list,
+				      &dev->mt76.sta_poll_list);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
 
 	status->freq = mphy->chandef.chan->center_freq;
@@ -892,10 +893,11 @@ mt7915_txwi_free(struct mt7915_dev *dev, struct mt76_txwi_cache *t,
 			msta = container_of(wcid, struct mt7915_sta, wcid);
 			sta = container_of((void *)msta, struct ieee80211_sta,
 					  drv_priv);
-			spin_lock_bh(&dev->sta_poll_lock);
+			spin_lock_bh(&mdev->sta_poll_lock);
 			if (list_empty(&msta->poll_list))
-				list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-			spin_unlock_bh(&dev->sta_poll_lock);
+				list_add_tail(&msta->poll_list,
+					      &mdev->sta_poll_list);
+			spin_unlock_bh(&mdev->sta_poll_lock);
 		}
 	}
 
@@ -987,10 +989,11 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len)
 				continue;
 
 			msta = container_of(wcid, struct mt7915_sta, wcid);
-			spin_lock_bh(&dev->sta_poll_lock);
+			spin_lock_bh(&mdev->sta_poll_lock);
 			if (list_empty(&msta->poll_list))
-				list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-			spin_unlock_bh(&dev->sta_poll_lock);
+				list_add_tail(&msta->poll_list,
+					      &mdev->sta_poll_list);
+			spin_unlock_bh(&mdev->sta_poll_lock);
 			continue;
 		}
 
@@ -1099,10 +1102,10 @@ static void mt7915_mac_add_txs(struct mt7915_dev *dev, void *data)
 	if (!wcid->sta)
 		goto out;
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (list_empty(&msta->poll_list))
-		list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+		list_add_tail(&msta->poll_list, &dev->mt76.sta_poll_list);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 out:
 	rcu_read_unlock();
@@ -2039,7 +2042,7 @@ void mt7915_mac_sta_rc_work(struct work_struct *work)
 	u32 changed;
 	LIST_HEAD(list);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	list_splice_init(&dev->sta_rc_list, &list);
 
 	while (!list_empty(&list)) {
@@ -2047,7 +2050,7 @@ void mt7915_mac_sta_rc_work(struct work_struct *work)
 		list_del_init(&msta->rc_list);
 		changed = msta->changed;
 		msta->changed = 0;
-		spin_unlock_bh(&dev->sta_poll_lock);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		sta = container_of((void *)msta, struct ieee80211_sta, drv_priv);
 		vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv);
@@ -2060,10 +2063,10 @@ void mt7915_mac_sta_rc_work(struct work_struct *work)
 		if (changed & IEEE80211_RC_SMPS_CHANGED)
 			mt7915_mcu_add_smps(dev, vif, sta);
 
-		spin_lock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
 	}
 
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 }
 
 void mt7915_mac_work(struct work_struct *work)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index 679397dddf0f1..bccb007752994 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -308,10 +308,10 @@ static void mt7915_remove_interface(struct ieee80211_hw *hw,
 	phy->omac_mask &= ~BIT_ULL(mvif->mt76.omac_idx);
 	mutex_unlock(&dev->mt76.mutex);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mt76_packet_id_flush(&dev->mt76, &msta->wcid);
 }
@@ -749,12 +749,12 @@ void mt7915_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	for (i = 0; i < ARRAY_SIZE(msta->twt.flow); i++)
 		mt7915_mac_twt_teardown_flow(dev, msta, i);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&mdev->sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
 	if (!list_empty(&msta->rc_list))
 		list_del_init(&msta->rc_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&mdev->sta_poll_lock);
 }
 
 static void mt7915_tx(struct ieee80211_hw *hw,
@@ -1109,11 +1109,11 @@ static void mt7915_sta_rc_work(void *data, struct ieee80211_sta *sta)
 	struct mt7915_dev *dev = msta->vif->phy->dev;
 	u32 *changed = data;
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	msta->changed |= *changed;
 	if (list_empty(&msta->rc_list))
 		list_add_tail(&msta->rc_list, &dev->sta_rc_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 }
 
 static void mt7915_sta_rc_update(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index 93b536e01eb5c..fe5f90822b348 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -274,9 +274,7 @@ struct mt7915_dev {
 #endif
 
 	struct list_head sta_rc_list;
-	struct list_head sta_poll_list;
 	struct list_head twt_list;
-	spinlock_t sta_poll_lock;
 
 	u32 hw_pattern;
 
-- 
GitLab


From c55e898bd9ca980e3e68152e7630aacf517c1648 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:19 +0200
Subject: [PATCH 0421/1806] wifi: mt76: mt7603: rely on shared sta_poll_list
 and sta_poll_lock

Rely on sta_poll_list and sta_poll_lock fields in mt76_dev structure
and get rid of private copies.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7603/init.c   |  2 --
 .../net/wireless/mediatek/mt76/mt7603/mac.c    | 18 +++++++++---------
 .../net/wireless/mediatek/mt76/mt7603/main.c   |  8 ++++----
 .../net/wireless/mediatek/mt76/mt7603/mt7603.h |  3 ---
 4 files changed, 13 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/init.c b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
index 9a2e632d577a9..0762de3ce5ac4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
@@ -500,8 +500,6 @@ int mt7603_register_device(struct mt7603_dev *dev)
 	bus_ops->rmw = mt7603_rmw;
 	dev->mt76.bus = bus_ops;
 
-	INIT_LIST_HEAD(&dev->sta_poll_list);
-	spin_lock_init(&dev->sta_poll_lock);
 	spin_lock_init(&dev->ps_lock);
 
 	INIT_DELAYED_WORK(&dev->mphy.mac_work, mt7603_mac_work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
index 12e0af52082a6..ac8a67e10a4d4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
@@ -412,16 +412,16 @@ void mt7603_mac_sta_poll(struct mt7603_dev *dev)
 	while (1) {
 		bool clear = false;
 
-		spin_lock_bh(&dev->sta_poll_lock);
-		if (list_empty(&dev->sta_poll_list)) {
-			spin_unlock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
+		if (list_empty(&dev->mt76.sta_poll_list)) {
+			spin_unlock_bh(&dev->mt76.sta_poll_lock);
 			break;
 		}
 
-		msta = list_first_entry(&dev->sta_poll_list, struct mt7603_sta,
-					poll_list);
+		msta = list_first_entry(&dev->mt76.sta_poll_list,
+					struct mt7603_sta, poll_list);
 		list_del_init(&msta->poll_list);
-		spin_unlock_bh(&dev->sta_poll_lock);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		addr = mt7603_wtbl4_addr(msta->wcid.idx);
 		for (i = 0; i < 4; i++) {
@@ -1268,9 +1268,9 @@ void mt7603_mac_add_txs(struct mt7603_dev *dev, void *data)
 	sta = wcid_to_sta(wcid);
 
 	if (list_empty(&msta->poll_list)) {
-		spin_lock_bh(&dev->sta_poll_lock);
-		list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-		spin_unlock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
+		list_add_tail(&msta->poll_list, &dev->mt76.sta_poll_list);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
 
 	if (mt7603_mac_add_txs_skb(dev, msta, pid, txs_data))
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index 1b1358c6bb464..6d2295cf5753b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -100,10 +100,10 @@ mt7603_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 
 	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mutex_lock(&dev->mt76.mutex);
 	dev->mt76.vif_mask &= ~BIT_ULL(mvif->idx);
@@ -388,10 +388,10 @@ mt7603_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	mt7603_filter_tx(dev, wcid->idx, true);
 	spin_unlock_bh(&dev->ps_lock);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&mdev->sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&mdev->sta_poll_lock);
 
 	mt7603_wtbl_clear(dev, wcid->idx);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
index 7c3be596da09b..689922d133e78 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
@@ -110,9 +110,6 @@ struct mt7603_dev {
 
 	u32 rxfilter;
 
-	struct list_head sta_poll_list;
-	spinlock_t sta_poll_lock;
-
 	struct mt7603_sta global_sta;
 
 	u32 agc0, agc3;
-- 
GitLab


From 57a3fac664ce192359271d7f6ddf1d55dff80cbc Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:20 +0200
Subject: [PATCH 0422/1806] wifi: mt76: mt7615: rely on shared sta_poll_list
 and sta_poll_lock

Rely on sta_poll_list and sta_poll_lock fields in mt76_dev structure
and get rid of private copies.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7615/init.c  |  2 --
 .../net/wireless/mediatek/mt76/mt7615/mac.c   | 23 ++++++++++---------
 .../net/wireless/mediatek/mt76/mt7615/main.c  |  8 +++----
 .../wireless/mediatek/mt76/mt7615/mt7615.h    |  3 ---
 4 files changed, 16 insertions(+), 20 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
index ab475c8418185..18a50ccff106a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
@@ -628,8 +628,6 @@ void mt7615_init_device(struct mt7615_dev *dev)
 	INIT_DELAYED_WORK(&dev->coredump.work, mt7615_coredump_work);
 	skb_queue_head_init(&dev->phy.scan_event_list);
 	skb_queue_head_init(&dev->coredump.msg_list);
-	INIT_LIST_HEAD(&dev->sta_poll_list);
-	spin_lock_init(&dev->sta_poll_lock);
 	init_waitqueue_head(&dev->reset_wait);
 	init_waitqueue_head(&dev->phy.roc_wait);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
index 64002484ccadb..f275c0fb0bf6b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
@@ -387,10 +387,11 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb)
 		struct mt7615_sta *msta;
 
 		msta = container_of(status->wcid, struct mt7615_sta, wcid);
-		spin_lock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		if (list_empty(&msta->poll_list))
-			list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-		spin_unlock_bh(&dev->sta_poll_lock);
+			list_add_tail(&msta->poll_list,
+				      &dev->mt76.sta_poll_list);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
 
 	if (mt76_is_mmio(&dev->mt76) && (rxd0 & csum_mask) == csum_mask &&
@@ -905,9 +906,9 @@ void mt7615_mac_sta_poll(struct mt7615_dev *dev)
 	int i;
 
 	INIT_LIST_HEAD(&sta_poll_list);
-	spin_lock_bh(&dev->sta_poll_lock);
-	list_splice_init(&dev->sta_poll_list, &sta_poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
+	list_splice_init(&dev->mt76.sta_poll_list, &sta_poll_list);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	while (!list_empty(&sta_poll_list)) {
 		bool clear = false;
@@ -915,9 +916,9 @@ void mt7615_mac_sta_poll(struct mt7615_dev *dev)
 		msta = list_first_entry(&sta_poll_list, struct mt7615_sta,
 					poll_list);
 
-		spin_lock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		list_del_init(&msta->poll_list);
-		spin_unlock_bh(&dev->sta_poll_lock);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		addr = mt7615_mac_wtbl_addr(dev, msta->wcid.idx) + 19 * 4;
 
@@ -1514,10 +1515,10 @@ static void mt7615_mac_add_txs(struct mt7615_dev *dev, void *data)
 	msta = container_of(wcid, struct mt7615_sta, wcid);
 	sta = wcid_to_sta(wcid);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (list_empty(&msta->poll_list))
-		list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+		list_add_tail(&msta->poll_list, &dev->mt76.sta_poll_list);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	if (mt7615_mac_add_txs_skb(dev, msta, pid, txs_data))
 		goto out;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index 4167aafa5b0ee..e14f1f30ac31c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -274,10 +274,10 @@ static void mt7615_remove_interface(struct ieee80211_hw *hw,
 
 	mt7615_mutex_release(dev);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mt76_packet_id_flush(&dev->mt76, &mvif->sta.wcid);
 }
@@ -705,10 +705,10 @@ void mt7615_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls)
 		mt7615_mcu_add_bss_info(phy, vif, sta, false);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&mdev->sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&mdev->sta_poll_lock);
 
 	mt76_connac_power_save_sched(phy->mt76, &dev->pm);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
index 582d1b5b7cb39..765ba986f07c4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
@@ -262,9 +262,6 @@ struct mt7615_dev {
 	wait_queue_head_t reset_wait;
 	u32 reset_state;
 
-	struct list_head sta_poll_list;
-	spinlock_t sta_poll_lock;
-
 	struct {
 		u8 n_pulses;
 		u32 period;
-- 
GitLab


From ea0f3867c017987bf4d6060e7665ecfffadb8cd9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:21 +0200
Subject: [PATCH 0423/1806] wifi: mt76: mt7996: rely on shared sta_poll_list
 and sta_poll_lock

Rely on sta_poll_list and sta_poll_lock fields in mt76_dev structure
and get rid of private copies.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/init.c  |  2 -
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 40 ++++++++++---------
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 12 +++---
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  2 -
 4 files changed, 27 insertions(+), 29 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
index 38ff33a7fc12c..e297e7cb3a7a4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
@@ -856,9 +856,7 @@ int mt7996_register_device(struct mt7996_dev *dev)
 	INIT_WORK(&dev->rc_work, mt7996_mac_sta_rc_work);
 	INIT_DELAYED_WORK(&dev->mphy.mac_work, mt7996_mac_work);
 	INIT_LIST_HEAD(&dev->sta_rc_list);
-	INIT_LIST_HEAD(&dev->sta_poll_list);
 	INIT_LIST_HEAD(&dev->twt_list);
-	spin_lock_init(&dev->sta_poll_lock);
 
 	init_waitqueue_head(&dev->reset_wait);
 	INIT_WORK(&dev->reset_work, mt7996_mac_reset_work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index a39bb39af5404..46b1dbcb4b458 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -111,9 +111,9 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 	LIST_HEAD(sta_poll_list);
 	int i;
 
-	spin_lock_bh(&dev->sta_poll_lock);
-	list_splice_init(&dev->sta_poll_list, &sta_poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
+	list_splice_init(&dev->mt76.sta_poll_list, &sta_poll_list);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	rcu_read_lock();
 
@@ -124,15 +124,15 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 		s8 rssi[4];
 		u8 bw;
 
-		spin_lock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		if (list_empty(&sta_poll_list)) {
-			spin_unlock_bh(&dev->sta_poll_lock);
+			spin_unlock_bh(&dev->mt76.sta_poll_lock);
 			break;
 		}
 		msta = list_first_entry(&sta_poll_list,
 					struct mt7996_sta, poll_list);
 		list_del_init(&msta->poll_list);
-		spin_unlock_bh(&dev->sta_poll_lock);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		idx = msta->wcid.idx;
 
@@ -681,10 +681,11 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, struct sk_buff *skb)
 		struct mt7996_sta *msta;
 
 		msta = container_of(status->wcid, struct mt7996_sta, wcid);
-		spin_lock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		if (list_empty(&msta->poll_list))
-			list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-		spin_unlock_bh(&dev->sta_poll_lock);
+			list_add_tail(&msta->poll_list,
+				      &dev->mt76.sta_poll_list);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
 
 	status->freq = mphy->chandef.chan->center_freq;
@@ -1291,10 +1292,11 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 				continue;
 
 			msta = container_of(wcid, struct mt7996_sta, wcid);
-			spin_lock_bh(&dev->sta_poll_lock);
+			spin_lock_bh(&mdev->sta_poll_lock);
 			if (list_empty(&msta->poll_list))
-				list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-			spin_unlock_bh(&dev->sta_poll_lock);
+				list_add_tail(&msta->poll_list,
+					      &mdev->sta_poll_list);
+			spin_unlock_bh(&mdev->sta_poll_lock);
 			continue;
 		}
 
@@ -1499,10 +1501,10 @@ static void mt7996_mac_add_txs(struct mt7996_dev *dev, void *data)
 	if (!wcid->sta)
 		goto out;
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (list_empty(&msta->poll_list))
-		list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+		list_add_tail(&msta->poll_list, &dev->mt76.sta_poll_list);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 out:
 	rcu_read_unlock();
@@ -2325,7 +2327,7 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 	u32 changed;
 	LIST_HEAD(list);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	list_splice_init(&dev->sta_rc_list, &list);
 
 	while (!list_empty(&list)) {
@@ -2333,7 +2335,7 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 		list_del_init(&msta->rc_list);
 		changed = msta->changed;
 		msta->changed = 0;
-		spin_unlock_bh(&dev->sta_poll_lock);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		sta = container_of((void *)msta, struct ieee80211_sta, drv_priv);
 		vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv);
@@ -2345,10 +2347,10 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 
 		/* TODO: smps change */
 
-		spin_lock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
 	}
 
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 }
 
 void mt7996_mac_work(struct work_struct *work)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index f173d197fcf64..975aac210a7dd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -263,10 +263,10 @@ static void mt7996_remove_interface(struct ieee80211_hw *hw,
 	phy->omac_mask &= ~BIT_ULL(mvif->mt76.omac_idx);
 	mutex_unlock(&dev->mt76.mutex);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mt76_packet_id_flush(&dev->mt76, &msta->wcid);
 }
@@ -689,12 +689,12 @@ void mt7996_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	for (i = 0; i < ARRAY_SIZE(msta->twt.flow); i++)
 		mt7996_mac_twt_teardown_flow(dev, msta, i);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&mdev->sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
 	if (!list_empty(&msta->rc_list))
 		list_del_init(&msta->rc_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&mdev->sta_poll_lock);
 }
 
 static void mt7996_tx(struct ieee80211_hw *hw,
@@ -1005,11 +1005,11 @@ static void mt7996_sta_rc_work(void *data, struct ieee80211_sta *sta)
 	struct mt7996_dev *dev = msta->vif->phy->dev;
 	u32 *changed = data;
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	msta->changed |= *changed;
 	if (list_empty(&msta->rc_list))
 		list_add_tail(&msta->rc_list, &dev->sta_rc_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 }
 
 static void mt7996_sta_rc_update(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 23de7508c954b..b45a9eecd71e7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -224,9 +224,7 @@ struct mt7996_dev {
 #endif
 
 	struct list_head sta_rc_list;
-	struct list_head sta_poll_list;
 	struct list_head twt_list;
-	spinlock_t sta_poll_lock;
 
 	u32 hw_pattern;
 
-- 
GitLab


From 419acc515dd32039da1ac48b13077912e9b1c2c4 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:22 +0200
Subject: [PATCH 0424/1806] wifi: mt76: mt7921: rely on shared sta_poll_list
 and sta_poll_lock

Rely on sta_poll_list and sta_poll_lock fields in mt76_dev structure
and get rid of private copies.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/init.c  |  2 --
 .../net/wireless/mediatek/mt76/mt7921/mac.c   | 32 ++++++++++---------
 .../net/wireless/mediatek/mt76/mt7921/main.c  |  8 ++---
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  3 --
 4 files changed, 21 insertions(+), 24 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 73a31efc08dad..94b7cdfd018bd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -456,8 +456,6 @@ int mt7921_register_device(struct mt7921_dev *dev)
 #endif
 	skb_queue_head_init(&dev->phy.scan_event_list);
 	skb_queue_head_init(&dev->coredump.msg_list);
-	INIT_LIST_HEAD(&dev->sta_poll_list);
-	spin_lock_init(&dev->sta_poll_lock);
 
 	INIT_WORK(&dev->reset_work, mt7921_mac_reset_work);
 	INIT_WORK(&dev->init_work, mt7921_init_work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 49f44b1e8d519..773db10a36f3c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -68,9 +68,9 @@ static void mt7921_mac_sta_poll(struct mt7921_dev *dev)
 	s8 rssi[4];
 	int i;
 
-	spin_lock_bh(&dev->sta_poll_lock);
-	list_splice_init(&dev->sta_poll_list, &sta_poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
+	list_splice_init(&dev->mt76.sta_poll_list, &sta_poll_list);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	while (true) {
 		bool clear = false;
@@ -78,15 +78,15 @@ static void mt7921_mac_sta_poll(struct mt7921_dev *dev)
 		u16 idx;
 		u8 bw;
 
-		spin_lock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		if (list_empty(&sta_poll_list)) {
-			spin_unlock_bh(&dev->sta_poll_lock);
+			spin_unlock_bh(&dev->mt76.sta_poll_lock);
 			break;
 		}
 		msta = list_first_entry(&sta_poll_list,
 					struct mt7921_sta, poll_list);
 		list_del_init(&msta->poll_list);
-		spin_unlock_bh(&dev->sta_poll_lock);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		idx = msta->wcid.idx;
 		addr = mt7921_mac_wtbl_lmac_addr(idx, MT_WTBL_AC0_CTT_OFFSET);
@@ -280,10 +280,11 @@ mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb)
 
 	if (status->wcid) {
 		msta = container_of(status->wcid, struct mt7921_sta, wcid);
-		spin_lock_bh(&dev->sta_poll_lock);
+		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		if (list_empty(&msta->poll_list))
-			list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-		spin_unlock_bh(&dev->sta_poll_lock);
+			list_add_tail(&msta->poll_list,
+				      &dev->mt76.sta_poll_list);
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
 
 	mt7921_get_status_freq_info(dev, mphy, status, chfreq);
@@ -566,10 +567,10 @@ void mt7921_mac_add_txs(struct mt7921_dev *dev, void *data)
 	if (!wcid->sta)
 		goto out;
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (list_empty(&msta->poll_list))
-		list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+		list_add_tail(&msta->poll_list, &dev->mt76.sta_poll_list);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 out:
 	rcu_read_unlock();
@@ -647,10 +648,11 @@ static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
 				continue;
 
 			msta = container_of(wcid, struct mt7921_sta, wcid);
-			spin_lock_bh(&dev->sta_poll_lock);
+			spin_lock_bh(&mdev->sta_poll_lock);
 			if (list_empty(&msta->poll_list))
-				list_add_tail(&msta->poll_list, &dev->sta_poll_list);
-			spin_unlock_bh(&dev->sta_poll_lock);
+				list_add_tail(&msta->poll_list,
+					      &mdev->sta_poll_list);
+			spin_unlock_bh(&mdev->sta_poll_lock);
 			continue;
 		}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index d520e68a8c82f..a5e6666907478 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -357,10 +357,10 @@ static void mt7921_remove_interface(struct ieee80211_hw *hw,
 	phy->omac_mask &= ~BIT_ULL(mvif->mt76.omac_idx);
 	mt7921_mutex_release(dev);
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mt76_packet_id_flush(&dev->mt76, &msta->wcid);
 }
@@ -842,10 +842,10 @@ void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 						    mvif->ctx);
 	}
 
-	spin_lock_bh(&dev->sta_poll_lock);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
-	spin_unlock_bh(&dev->sta_poll_lock);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mt76_connac_power_save_sched(&dev->mphy, &dev->pm);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 7cad215cb748d..20803968c779d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -274,9 +274,6 @@ struct mt7921_dev {
 	bool hw_init_done:1;
 	bool fw_assert:1;
 
-	struct list_head sta_poll_list;
-	spinlock_t sta_poll_lock;
-
 	struct work_struct init_work;
 
 	u8 fw_debug;
-- 
GitLab


From b73e1d9245eba06012792cd3c9ca96dad23904ee Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:23 +0200
Subject: [PATCH 0425/1806] wifi: mt76: mt7915: move poll_list in mt76_wcid

poll_list field is used by most of the drivers, so move it in mt76_wcid
structure.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h     |  2 ++
 .../net/wireless/mediatek/mt76/mt7915/mac.c   | 20 +++++++++----------
 .../net/wireless/mediatek/mt76/mt7915/main.c  | 12 +++++------
 .../wireless/mediatek/mt76/mt7915/mt7915.h    |  1 -
 4 files changed, 18 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 6becfcebb9260..97e72cf3bc8ef 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -336,6 +336,8 @@ struct mt76_wcid {
 	struct idr pktid;
 
 	struct mt76_sta_stats stats;
+
+	struct list_head poll_list;
 };
 
 struct mt76_txq {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 8ed217ee592ec..99383e4e113a0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -124,8 +124,8 @@ static void mt7915_mac_sta_poll(struct mt7915_dev *dev)
 			break;
 		}
 		msta = list_first_entry(&sta_poll_list,
-					struct mt7915_sta, poll_list);
-		list_del_init(&msta->poll_list);
+					struct mt7915_sta, wcid.poll_list);
+		list_del_init(&msta->wcid.poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		idx = msta->wcid.idx;
@@ -327,8 +327,8 @@ mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb,
 	if (status->wcid) {
 		msta = container_of(status->wcid, struct mt7915_sta, wcid);
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
-		if (list_empty(&msta->poll_list))
-			list_add_tail(&msta->poll_list,
+		if (list_empty(&msta->wcid.poll_list))
+			list_add_tail(&msta->wcid.poll_list,
 				      &dev->mt76.sta_poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
@@ -894,8 +894,8 @@ mt7915_txwi_free(struct mt7915_dev *dev, struct mt76_txwi_cache *t,
 			sta = container_of((void *)msta, struct ieee80211_sta,
 					  drv_priv);
 			spin_lock_bh(&mdev->sta_poll_lock);
-			if (list_empty(&msta->poll_list))
-				list_add_tail(&msta->poll_list,
+			if (list_empty(&msta->wcid.poll_list))
+				list_add_tail(&msta->wcid.poll_list,
 					      &mdev->sta_poll_list);
 			spin_unlock_bh(&mdev->sta_poll_lock);
 		}
@@ -990,8 +990,8 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len)
 
 			msta = container_of(wcid, struct mt7915_sta, wcid);
 			spin_lock_bh(&mdev->sta_poll_lock);
-			if (list_empty(&msta->poll_list))
-				list_add_tail(&msta->poll_list,
+			if (list_empty(&msta->wcid.poll_list))
+				list_add_tail(&msta->wcid.poll_list,
 					      &mdev->sta_poll_list);
 			spin_unlock_bh(&mdev->sta_poll_lock);
 			continue;
@@ -1103,8 +1103,8 @@ static void mt7915_mac_add_txs(struct mt7915_dev *dev, void *data)
 		goto out;
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (list_empty(&msta->poll_list))
-		list_add_tail(&msta->poll_list, &dev->mt76.sta_poll_list);
+	if (list_empty(&msta->wcid.poll_list))
+		list_add_tail(&msta->wcid.poll_list, &dev->mt76.sta_poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 out:
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index bccb007752994..f2f82eb617134 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -248,7 +248,7 @@ static int mt7915_add_interface(struct ieee80211_hw *hw,
 	idx = MT7915_WTBL_RESERVED - mvif->mt76.idx;
 
 	INIT_LIST_HEAD(&mvif->sta.rc_list);
-	INIT_LIST_HEAD(&mvif->sta.poll_list);
+	INIT_LIST_HEAD(&mvif->sta.wcid.poll_list);
 	mvif->sta.wcid.idx = idx;
 	mvif->sta.wcid.phy_idx = ext_phy;
 	mvif->sta.wcid.hw_key_idx = -1;
@@ -309,8 +309,8 @@ static void mt7915_remove_interface(struct ieee80211_hw *hw,
 	mutex_unlock(&dev->mt76.mutex);
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (!list_empty(&msta->poll_list))
-		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mt76_packet_id_flush(&dev->mt76, &msta->wcid);
@@ -714,7 +714,7 @@ int mt7915_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		return -ENOSPC;
 
 	INIT_LIST_HEAD(&msta->rc_list);
-	INIT_LIST_HEAD(&msta->poll_list);
+	INIT_LIST_HEAD(&msta->wcid.poll_list);
 	msta->vif = mvif;
 	msta->wcid.sta = 1;
 	msta->wcid.idx = idx;
@@ -750,8 +750,8 @@ void mt7915_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		mt7915_mac_twt_teardown_flow(dev, msta, i);
 
 	spin_lock_bh(&mdev->sta_poll_lock);
-	if (!list_empty(&msta->poll_list))
-		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
 	if (!list_empty(&msta->rc_list))
 		list_del_init(&msta->rc_list);
 	spin_unlock_bh(&mdev->sta_poll_lock);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index fe5f90822b348..a76dcceb0ec13 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -136,7 +136,6 @@ struct mt7915_sta {
 
 	struct mt7915_vif *vif;
 
-	struct list_head poll_list;
 	struct list_head rc_list;
 	u32 airtime_ac[8];
 
-- 
GitLab


From 2d29058e396a273ebb681559b135ff8bcb005e7c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:24 +0200
Subject: [PATCH 0426/1806] wifi: mt76: mt7603: rely on shared poll_list field

Rely on poll_list field in mt76_wcid structure and get rid of
private copy.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7603/mac.c    |  8 ++++----
 drivers/net/wireless/mediatek/mt76/mt7603/main.c   | 12 ++++++------
 drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h |  1 -
 3 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
index ac8a67e10a4d4..de11557eb04c3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
@@ -419,8 +419,8 @@ void mt7603_mac_sta_poll(struct mt7603_dev *dev)
 		}
 
 		msta = list_first_entry(&dev->mt76.sta_poll_list,
-					struct mt7603_sta, poll_list);
-		list_del_init(&msta->poll_list);
+					struct mt7603_sta, wcid.poll_list);
+		list_del_init(&msta->wcid.poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		addr = mt7603_wtbl4_addr(msta->wcid.idx);
@@ -1267,9 +1267,9 @@ void mt7603_mac_add_txs(struct mt7603_dev *dev, void *data)
 	msta = container_of(wcid, struct mt7603_sta, wcid);
 	sta = wcid_to_sta(wcid);
 
-	if (list_empty(&msta->poll_list)) {
+	if (list_empty(&msta->wcid.poll_list)) {
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
-		list_add_tail(&msta->poll_list, &dev->mt76.sta_poll_list);
+		list_add_tail(&msta->wcid.poll_list, &dev->mt76.sta_poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index 6d2295cf5753b..1d4893410ca56 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -66,7 +66,7 @@ mt7603_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 
 	idx = MT7603_WTBL_RESERVED - 1 - mvif->idx;
 	dev->mt76.vif_mask |= BIT_ULL(mvif->idx);
-	INIT_LIST_HEAD(&mvif->sta.poll_list);
+	INIT_LIST_HEAD(&mvif->sta.wcid.poll_list);
 	mvif->sta.wcid.idx = idx;
 	mvif->sta.wcid.hw_key_idx = -1;
 	mt76_packet_id_init(&mvif->sta.wcid);
@@ -101,8 +101,8 @@ mt7603_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (!list_empty(&msta->poll_list))
-		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mutex_lock(&dev->mt76.mutex);
@@ -351,7 +351,7 @@ mt7603_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	if (idx < 0)
 		return -ENOSPC;
 
-	INIT_LIST_HEAD(&msta->poll_list);
+	INIT_LIST_HEAD(&msta->wcid.poll_list);
 	__skb_queue_head_init(&msta->psq);
 	msta->ps = ~0;
 	msta->smps = ~0;
@@ -389,8 +389,8 @@ mt7603_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	spin_unlock_bh(&dev->ps_lock);
 
 	spin_lock_bh(&mdev->sta_poll_lock);
-	if (!list_empty(&msta->poll_list))
-		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
 	spin_unlock_bh(&mdev->sta_poll_lock);
 
 	mt7603_wtbl_clear(dev, wcid->idx);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
index 689922d133e78..354b189862f79 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
@@ -64,7 +64,6 @@ struct mt7603_sta {
 
 	struct mt7603_vif *vif;
 
-	struct list_head poll_list;
 	u32 tx_airtime_ac[4];
 
 	struct sk_buff_head psq;
-- 
GitLab


From 9d599f2d654639198478fb6e0a8bd381b283730e Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:25 +0200
Subject: [PATCH 0427/1806] wifi: mt76: mt7615: rely on shared poll_list field

Rely on poll_list field in mt76_wcid structure and get rid of
private copy.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7615/mac.c    | 12 ++++++------
 drivers/net/wireless/mediatek/mt76/mt7615/main.c   | 12 ++++++------
 drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h |  1 -
 3 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
index f275c0fb0bf6b..7ba789834e8df 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
@@ -388,8 +388,8 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb)
 
 		msta = container_of(status->wcid, struct mt7615_sta, wcid);
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
-		if (list_empty(&msta->poll_list))
-			list_add_tail(&msta->poll_list,
+		if (list_empty(&msta->wcid.poll_list))
+			list_add_tail(&msta->wcid.poll_list,
 				      &dev->mt76.sta_poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
@@ -914,10 +914,10 @@ void mt7615_mac_sta_poll(struct mt7615_dev *dev)
 		bool clear = false;
 
 		msta = list_first_entry(&sta_poll_list, struct mt7615_sta,
-					poll_list);
+					wcid.poll_list);
 
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
-		list_del_init(&msta->poll_list);
+		list_del_init(&msta->wcid.poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		addr = mt7615_mac_wtbl_addr(dev, msta->wcid.idx) + 19 * 4;
@@ -1516,8 +1516,8 @@ static void mt7615_mac_add_txs(struct mt7615_dev *dev, void *data)
 	sta = wcid_to_sta(wcid);
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (list_empty(&msta->poll_list))
-		list_add_tail(&msta->poll_list, &dev->mt76.sta_poll_list);
+	if (list_empty(&msta->wcid.poll_list))
+		list_add_tail(&msta->wcid.poll_list, &dev->mt76.sta_poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	if (mt7615_mac_add_txs_skb(dev, msta, pid, txs_data))
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index e14f1f30ac31c..200b1752ca77f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -222,7 +222,7 @@ static int mt7615_add_interface(struct ieee80211_hw *hw,
 
 	idx = MT7615_WTBL_RESERVED - mvif->mt76.idx;
 
-	INIT_LIST_HEAD(&mvif->sta.poll_list);
+	INIT_LIST_HEAD(&mvif->sta.wcid.poll_list);
 	mvif->sta.wcid.idx = idx;
 	mvif->sta.wcid.phy_idx = mvif->mt76.band_idx;
 	mvif->sta.wcid.hw_key_idx = -1;
@@ -275,8 +275,8 @@ static void mt7615_remove_interface(struct ieee80211_hw *hw,
 	mt7615_mutex_release(dev);
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (!list_empty(&msta->poll_list))
-		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mt76_packet_id_flush(&dev->mt76, &mvif->sta.wcid);
@@ -657,7 +657,7 @@ int mt7615_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	if (idx < 0)
 		return -ENOSPC;
 
-	INIT_LIST_HEAD(&msta->poll_list);
+	INIT_LIST_HEAD(&msta->wcid.poll_list);
 	msta->vif = mvif;
 	msta->wcid.sta = 1;
 	msta->wcid.idx = idx;
@@ -706,8 +706,8 @@ void mt7615_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		mt7615_mcu_add_bss_info(phy, vif, sta, false);
 
 	spin_lock_bh(&mdev->sta_poll_lock);
-	if (!list_empty(&msta->poll_list))
-		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
 	spin_unlock_bh(&mdev->sta_poll_lock);
 
 	mt76_connac_power_save_sched(phy->mt76, &dev->pm);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
index 765ba986f07c4..a20322aae9672 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
@@ -125,7 +125,6 @@ struct mt7615_sta {
 
 	struct mt7615_vif *vif;
 
-	struct list_head poll_list;
 	u32 airtime_ac[8];
 
 	struct ieee80211_tx_rate rates[4];
-- 
GitLab


From e3b0311fcc3a882724937cbe276b1969c9975711 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:26 +0200
Subject: [PATCH 0428/1806] wifi: mt76: mt7996: rely on shared poll_list field

Rely on poll_list field in mt76_wcid  structure and get rid of
private copy.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c  | 16 ++++++++--------
 drivers/net/wireless/mediatek/mt76/mt7996/main.c | 12 ++++++------
 .../net/wireless/mediatek/mt76/mt7996/mt7996.h   |  1 -
 3 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 46b1dbcb4b458..2adc2599d64d2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -130,8 +130,8 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 			break;
 		}
 		msta = list_first_entry(&sta_poll_list,
-					struct mt7996_sta, poll_list);
-		list_del_init(&msta->poll_list);
+					struct mt7996_sta, wcid.poll_list);
+		list_del_init(&msta->wcid.poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		idx = msta->wcid.idx;
@@ -682,8 +682,8 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, struct sk_buff *skb)
 
 		msta = container_of(status->wcid, struct mt7996_sta, wcid);
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
-		if (list_empty(&msta->poll_list))
-			list_add_tail(&msta->poll_list,
+		if (list_empty(&msta->wcid.poll_list))
+			list_add_tail(&msta->wcid.poll_list,
 				      &dev->mt76.sta_poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
@@ -1293,8 +1293,8 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 
 			msta = container_of(wcid, struct mt7996_sta, wcid);
 			spin_lock_bh(&mdev->sta_poll_lock);
-			if (list_empty(&msta->poll_list))
-				list_add_tail(&msta->poll_list,
+			if (list_empty(&msta->wcid.poll_list))
+				list_add_tail(&msta->wcid.poll_list,
 					      &mdev->sta_poll_list);
 			spin_unlock_bh(&mdev->sta_poll_lock);
 			continue;
@@ -1502,8 +1502,8 @@ static void mt7996_mac_add_txs(struct mt7996_dev *dev, void *data)
 		goto out;
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (list_empty(&msta->poll_list))
-		list_add_tail(&msta->poll_list, &dev->mt76.sta_poll_list);
+	if (list_empty(&msta->wcid.poll_list))
+		list_add_tail(&msta->wcid.poll_list, &dev->mt76.sta_poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 out:
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 975aac210a7dd..69b47136b8d7e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -202,7 +202,7 @@ static int mt7996_add_interface(struct ieee80211_hw *hw,
 	idx = MT7996_WTBL_RESERVED - mvif->mt76.idx;
 
 	INIT_LIST_HEAD(&mvif->sta.rc_list);
-	INIT_LIST_HEAD(&mvif->sta.poll_list);
+	INIT_LIST_HEAD(&mvif->sta.wcid.poll_list);
 	mvif->sta.wcid.idx = idx;
 	mvif->sta.wcid.phy_idx = band_idx;
 	mvif->sta.wcid.hw_key_idx = -1;
@@ -264,8 +264,8 @@ static void mt7996_remove_interface(struct ieee80211_hw *hw,
 	mutex_unlock(&dev->mt76.mutex);
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (!list_empty(&msta->poll_list))
-		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mt76_packet_id_flush(&dev->mt76, &msta->wcid);
@@ -654,7 +654,7 @@ int mt7996_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		return -ENOSPC;
 
 	INIT_LIST_HEAD(&msta->rc_list);
-	INIT_LIST_HEAD(&msta->poll_list);
+	INIT_LIST_HEAD(&msta->wcid.poll_list);
 	msta->vif = mvif;
 	msta->wcid.sta = 1;
 	msta->wcid.idx = idx;
@@ -690,8 +690,8 @@ void mt7996_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		mt7996_mac_twt_teardown_flow(dev, msta, i);
 
 	spin_lock_bh(&mdev->sta_poll_lock);
-	if (!list_empty(&msta->poll_list))
-		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
 	if (!list_empty(&msta->rc_list))
 		list_del_init(&msta->rc_list);
 	spin_unlock_bh(&mdev->sta_poll_lock);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index b45a9eecd71e7..e67d57a844267 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -103,7 +103,6 @@ struct mt7996_sta {
 
 	struct mt7996_vif *vif;
 
-	struct list_head poll_list;
 	struct list_head rc_list;
 	u32 airtime_ac[8];
 
-- 
GitLab


From d17a2fe830d7c458166a06ca222ed7f4d94c671f Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:27 +0200
Subject: [PATCH 0429/1806] wifi: mt76: mt7921: rely on shared poll_list field

Rely on poll_list field in mt76_wcid structure and get rid of
private copy.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/mac.c  | 16 ++++++++--------
 drivers/net/wireless/mediatek/mt76/mt7921/main.c | 12 ++++++------
 .../net/wireless/mediatek/mt76/mt7921/mt7921.h   |  1 -
 3 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 773db10a36f3c..c00342e874050 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -84,8 +84,8 @@ static void mt7921_mac_sta_poll(struct mt7921_dev *dev)
 			break;
 		}
 		msta = list_first_entry(&sta_poll_list,
-					struct mt7921_sta, poll_list);
-		list_del_init(&msta->poll_list);
+					struct mt7921_sta, wcid.poll_list);
+		list_del_init(&msta->wcid.poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		idx = msta->wcid.idx;
@@ -281,8 +281,8 @@ mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb)
 	if (status->wcid) {
 		msta = container_of(status->wcid, struct mt7921_sta, wcid);
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
-		if (list_empty(&msta->poll_list))
-			list_add_tail(&msta->poll_list,
+		if (list_empty(&msta->wcid.poll_list))
+			list_add_tail(&msta->wcid.poll_list,
 				      &dev->mt76.sta_poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
@@ -568,8 +568,8 @@ void mt7921_mac_add_txs(struct mt7921_dev *dev, void *data)
 		goto out;
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (list_empty(&msta->poll_list))
-		list_add_tail(&msta->poll_list, &dev->mt76.sta_poll_list);
+	if (list_empty(&msta->wcid.poll_list))
+		list_add_tail(&msta->wcid.poll_list, &dev->mt76.sta_poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 out:
@@ -649,8 +649,8 @@ static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
 
 			msta = container_of(wcid, struct mt7921_sta, wcid);
 			spin_lock_bh(&mdev->sta_poll_lock);
-			if (list_empty(&msta->poll_list))
-				list_add_tail(&msta->poll_list,
+			if (list_empty(&msta->wcid.poll_list))
+				list_add_tail(&msta->wcid.poll_list,
 					      &mdev->sta_poll_list);
 			spin_unlock_bh(&mdev->sta_poll_lock);
 			continue;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index a5e6666907478..49053d05c164a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -313,7 +313,7 @@ static int mt7921_add_interface(struct ieee80211_hw *hw,
 
 	idx = MT7921_WTBL_RESERVED - mvif->mt76.idx;
 
-	INIT_LIST_HEAD(&mvif->sta.poll_list);
+	INIT_LIST_HEAD(&mvif->sta.wcid.poll_list);
 	mvif->sta.wcid.idx = idx;
 	mvif->sta.wcid.phy_idx = mvif->mt76.band_idx;
 	mvif->sta.wcid.hw_key_idx = -1;
@@ -358,8 +358,8 @@ static void mt7921_remove_interface(struct ieee80211_hw *hw,
 	mt7921_mutex_release(dev);
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (!list_empty(&msta->poll_list))
-		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mt76_packet_id_flush(&dev->mt76, &msta->wcid);
@@ -764,7 +764,7 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	if (idx < 0)
 		return -ENOSPC;
 
-	INIT_LIST_HEAD(&msta->poll_list);
+	INIT_LIST_HEAD(&msta->wcid.poll_list);
 	msta->vif = mvif;
 	msta->wcid.sta = 1;
 	msta->wcid.idx = idx;
@@ -843,8 +843,8 @@ void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	}
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (!list_empty(&msta->poll_list))
-		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 	mt76_connac_power_save_sched(&dev->mphy, &dev->pm);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 20803968c779d..fe4de77a0c075 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -150,7 +150,6 @@ struct mt7921_sta {
 
 	struct mt7921_vif *vif;
 
-	struct list_head poll_list;
 	u32 airtime_ac[8];
 
 	int ack_signal;
-- 
GitLab


From ef591d74d4ba1273100d790f79059384f4547857 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:28 +0200
Subject: [PATCH 0430/1806] wifi: mt76: move ampdu_state in mt76_wcid

ampdu_state field is used by most of the drivers, so move it in
mt76_wcid structure.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h          | 1 +
 drivers/net/wireless/mediatek/mt76/mt7915/mac.c    | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7915/main.c   | 6 +++---
 drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h | 1 -
 drivers/net/wireless/mediatek/mt76/mt7921/mac.c    | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/main.c   | 6 +++---
 drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h | 1 -
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c    | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7996/main.c   | 6 +++---
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h | 1 -
 10 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 97e72cf3bc8ef..8ec77682d8e90 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -316,6 +316,7 @@ struct mt76_wcid {
 	int inactive_count;
 
 	struct rate_info rate;
+	unsigned long ampdu_state;
 
 	u16 idx;
 	u8 hw_key_idx;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 99383e4e113a0..b58e8275feef3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -863,7 +863,7 @@ mt7915_tx_check_aggr(struct ieee80211_sta *sta, __le32 *txwi)
 		return;
 
 	msta = (struct mt7915_sta *)sta->drv_priv;
-	if (!test_and_set_bit(tid, &msta->ampdu_state))
+	if (!test_and_set_bit(tid, &msta->wcid.ampdu_state))
 		ieee80211_start_tx_ba_session(sta, tid, 0);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index f2f82eb617134..decb60aac9dd9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -836,16 +836,16 @@ mt7915_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
 		mtxq->aggr = false;
-		clear_bit(tid, &msta->ampdu_state);
+		clear_bit(tid, &msta->wcid.ampdu_state);
 		ret = mt7915_mcu_add_tx_ba(dev, params, false);
 		break;
 	case IEEE80211_AMPDU_TX_START:
-		set_bit(tid, &msta->ampdu_state);
+		set_bit(tid, &msta->wcid.ampdu_state);
 		ret = IEEE80211_AMPDU_TX_START_IMMEDIATE;
 		break;
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 		mtxq->aggr = false;
-		clear_bit(tid, &msta->ampdu_state);
+		clear_bit(tid, &msta->wcid.ampdu_state);
 		ret = mt7915_mcu_add_tx_ba(dev, params, false);
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index a76dcceb0ec13..066934249a09e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -144,7 +144,6 @@ struct mt7915_sta {
 
 	unsigned long changed;
 	unsigned long jiffies;
-	unsigned long ampdu_state;
 	struct mt76_connac_sta_key_conf bip;
 
 	struct {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index c00342e874050..3e589748e1a3d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -531,7 +531,7 @@ static void mt7921_tx_check_aggr(struct ieee80211_sta *sta, __le32 *txwi)
 		return;
 
 	msta = (struct mt7921_sta *)sta->drv_priv;
-	if (!test_and_set_bit(tid, &msta->ampdu_state))
+	if (!test_and_set_bit(tid, &msta->wcid.ampdu_state))
 		ieee80211_start_tx_ba_session(sta, tid, 0);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 49053d05c164a..87067ac367ebd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -954,16 +954,16 @@ mt7921_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
 		mtxq->aggr = false;
-		clear_bit(tid, &msta->ampdu_state);
+		clear_bit(tid, &msta->wcid.ampdu_state);
 		mt7921_mcu_uni_tx_ba(dev, params, false);
 		break;
 	case IEEE80211_AMPDU_TX_START:
-		set_bit(tid, &msta->ampdu_state);
+		set_bit(tid, &msta->wcid.ampdu_state);
 		ret = IEEE80211_AMPDU_TX_START_IMMEDIATE;
 		break;
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 		mtxq->aggr = false;
-		clear_bit(tid, &msta->ampdu_state);
+		clear_bit(tid, &msta->wcid.ampdu_state);
 		mt7921_mcu_uni_tx_ba(dev, params, false);
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index fe4de77a0c075..2694ecb1fdcbd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -156,7 +156,6 @@ struct mt7921_sta {
 	struct ewma_avg_signal avg_ack_signal;
 
 	unsigned long last_txs;
-	unsigned long ampdu_state;
 
 	struct mt76_connac_sta_key_conf bip;
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 2adc2599d64d2..dfe70e0ff3297 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -1204,7 +1204,7 @@ mt7996_tx_check_aggr(struct ieee80211_sta *sta, __le32 *txwi)
 		return;
 
 	msta = (struct mt7996_sta *)sta->drv_priv;
-	if (!test_and_set_bit(tid, &msta->ampdu_state))
+	if (!test_and_set_bit(tid, &msta->wcid.ampdu_state))
 		ieee80211_start_tx_ba_session(sta, tid, 0);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 69b47136b8d7e..54858cfc93423 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -774,16 +774,16 @@ mt7996_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
 		mtxq->aggr = false;
-		clear_bit(tid, &msta->ampdu_state);
+		clear_bit(tid, &msta->wcid.ampdu_state);
 		ret = mt7996_mcu_add_tx_ba(dev, params, false);
 		break;
 	case IEEE80211_AMPDU_TX_START:
-		set_bit(tid, &msta->ampdu_state);
+		set_bit(tid, &msta->wcid.ampdu_state);
 		ret = IEEE80211_AMPDU_TX_START_IMMEDIATE;
 		break;
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 		mtxq->aggr = false;
-		clear_bit(tid, &msta->ampdu_state);
+		clear_bit(tid, &msta->wcid.ampdu_state);
 		ret = mt7996_mcu_add_tx_ba(dev, params, false);
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index e67d57a844267..79cb71c16264a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -111,7 +111,6 @@ struct mt7996_sta {
 
 	unsigned long changed;
 	unsigned long jiffies;
-	unsigned long ampdu_state;
 
 	struct mt76_connac_sta_key_conf bip;
 
-- 
GitLab


From c8e370feb361896376acc871e68408613034437b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:29 +0200
Subject: [PATCH 0431/1806] mt76: connac: move more mt7921/mt7915 mac shared
 code in connac lib

Move the following routines in mt76-connac lib since they are shared
between mt7915 and mt7921:
- mt76_connac2_tx_check_aggr
- mt76_connac2_txwi_free
- mt76_connac2_tx_token_put

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt76_connac.h  |  5 +
 .../wireless/mediatek/mt76/mt76_connac_mac.c  | 82 +++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7915/init.c  |  2 +-
 .../net/wireless/mediatek/mt76/mt7915/mac.c   | 91 +------------------
 .../wireless/mediatek/mt76/mt7915/mt7915.h    |  1 -
 .../net/wireless/mediatek/mt76/mt7921/mac.c   | 59 +-----------
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  4 -
 .../net/wireless/mediatek/mt76/mt7921/pci.c   |  2 +-
 .../wireless/mediatek/mt76/mt7921/pci_mac.c   | 16 +---
 9 files changed, 96 insertions(+), 166 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac.h
index 77ca8f057d615..d3bb9114160f4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac.h
@@ -419,5 +419,10 @@ int mt76_connac2_mac_fill_rx_rate(struct mt76_dev *dev,
 				  struct mt76_rx_status *status,
 				  struct ieee80211_supported_band *sband,
 				  __le32 *rxv, u8 *mode);
+void mt76_connac2_tx_check_aggr(struct ieee80211_sta *sta, __le32 *txwi);
+void mt76_connac2_txwi_free(struct mt76_dev *dev, struct mt76_txwi_cache *t,
+			    struct ieee80211_sta *sta,
+			    struct list_head *free_list);
+void mt76_connac2_tx_token_put(struct mt76_dev *dev);
 
 #endif /* __MT76_CONNAC_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index f481ca3a0db85..ee5177fd6ddea 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -1112,3 +1112,85 @@ int mt76_connac2_mac_fill_rx_rate(struct mt76_dev *dev,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mt76_connac2_mac_fill_rx_rate);
+
+void mt76_connac2_tx_check_aggr(struct ieee80211_sta *sta, __le32 *txwi)
+{
+	struct mt76_wcid *wcid;
+	u16 fc, tid;
+	u32 val;
+
+	if (!sta ||
+	    !(sta->deflink.ht_cap.ht_supported || sta->deflink.he_cap.has_he))
+		return;
+
+	tid = le32_get_bits(txwi[1], MT_TXD1_TID);
+	if (tid >= 6) /* skip VO queue */
+		return;
+
+	val = le32_to_cpu(txwi[2]);
+	fc = FIELD_GET(MT_TXD2_FRAME_TYPE, val) << 2 |
+	     FIELD_GET(MT_TXD2_SUB_TYPE, val) << 4;
+	if (unlikely(fc != (IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_DATA)))
+		return;
+
+	wcid = (struct mt76_wcid *)sta->drv_priv;
+	if (!test_and_set_bit(tid, &wcid->ampdu_state))
+		ieee80211_start_tx_ba_session(sta, tid, 0);
+}
+EXPORT_SYMBOL_GPL(mt76_connac2_tx_check_aggr);
+
+void mt76_connac2_txwi_free(struct mt76_dev *dev, struct mt76_txwi_cache *t,
+			    struct ieee80211_sta *sta,
+			    struct list_head *free_list)
+{
+	struct mt76_wcid *wcid;
+	__le32 *txwi;
+	u16 wcid_idx;
+
+	mt76_connac_txp_skb_unmap(dev, t);
+	if (!t->skb)
+		goto out;
+
+	txwi = (__le32 *)mt76_get_txwi_ptr(dev, t);
+	if (sta) {
+		wcid = (struct mt76_wcid *)sta->drv_priv;
+		wcid_idx = wcid->idx;
+	} else {
+		wcid_idx = le32_get_bits(txwi[1], MT_TXD1_WLAN_IDX);
+		wcid = rcu_dereference(dev->wcid[wcid_idx]);
+
+		if (wcid && wcid->sta) {
+			sta = container_of((void *)wcid, struct ieee80211_sta,
+					   drv_priv);
+			spin_lock_bh(&dev->sta_poll_lock);
+			if (list_empty(&wcid->poll_list))
+				list_add_tail(&wcid->poll_list,
+					      &dev->sta_poll_list);
+			spin_unlock_bh(&dev->sta_poll_lock);
+		}
+	}
+
+	if (sta && likely(t->skb->protocol != cpu_to_be16(ETH_P_PAE)))
+		mt76_connac2_tx_check_aggr(sta, txwi);
+
+	__mt76_tx_complete_skb(dev, wcid_idx, t->skb, free_list);
+out:
+	t->skb = NULL;
+	mt76_put_txwi(dev, t);
+}
+EXPORT_SYMBOL_GPL(mt76_connac2_txwi_free);
+
+void mt76_connac2_tx_token_put(struct mt76_dev *dev)
+{
+	struct mt76_txwi_cache *txwi;
+	int id;
+
+	spin_lock_bh(&dev->token_lock);
+	idr_for_each_entry(&dev->token, txwi, id) {
+		mt76_connac2_txwi_free(dev, txwi, NULL, NULL);
+		dev->token_count--;
+	}
+	spin_unlock_bh(&dev->token_lock);
+	idr_destroy(&dev->token);
+}
+EXPORT_SYMBOL_GPL(mt76_connac2_tx_token_put);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index fffab468efebd..ee976657bfc36 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -1166,7 +1166,7 @@ static void mt7915_unregister_ext_phy(struct mt7915_dev *dev)
 static void mt7915_stop_hardware(struct mt7915_dev *dev)
 {
 	mt7915_mcu_exit(dev);
-	mt7915_tx_token_put(dev);
+	mt76_connac2_tx_token_put(&dev->mt76);
 	mt7915_dma_cleanup(dev);
 	tasklet_disable(&dev->mt76.irq_tasklet);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index b58e8275feef3..b8b0c0fda7522 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -842,75 +842,6 @@ u32 mt7915_wed_init_buf(void *ptr, dma_addr_t phys, int token_id)
 	return MT_TXD_SIZE + sizeof(*txp);
 }
 
-static void
-mt7915_tx_check_aggr(struct ieee80211_sta *sta, __le32 *txwi)
-{
-	struct mt7915_sta *msta;
-	u16 fc, tid;
-	u32 val;
-
-	if (!sta || !(sta->deflink.ht_cap.ht_supported || sta->deflink.he_cap.has_he))
-		return;
-
-	tid = le32_get_bits(txwi[1], MT_TXD1_TID);
-	if (tid >= 6) /* skip VO queue */
-		return;
-
-	val = le32_to_cpu(txwi[2]);
-	fc = FIELD_GET(MT_TXD2_FRAME_TYPE, val) << 2 |
-	     FIELD_GET(MT_TXD2_SUB_TYPE, val) << 4;
-	if (unlikely(fc != (IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_DATA)))
-		return;
-
-	msta = (struct mt7915_sta *)sta->drv_priv;
-	if (!test_and_set_bit(tid, &msta->wcid.ampdu_state))
-		ieee80211_start_tx_ba_session(sta, tid, 0);
-}
-
-static void
-mt7915_txwi_free(struct mt7915_dev *dev, struct mt76_txwi_cache *t,
-		 struct ieee80211_sta *sta, struct list_head *free_list)
-{
-	struct mt76_dev *mdev = &dev->mt76;
-	struct mt7915_sta *msta;
-	struct mt76_wcid *wcid;
-	__le32 *txwi;
-	u16 wcid_idx;
-
-	mt76_connac_txp_skb_unmap(mdev, t);
-	if (!t->skb)
-		goto out;
-
-	txwi = (__le32 *)mt76_get_txwi_ptr(mdev, t);
-	if (sta) {
-		wcid = (struct mt76_wcid *)sta->drv_priv;
-		wcid_idx = wcid->idx;
-	} else {
-		wcid_idx = le32_get_bits(txwi[1], MT_TXD1_WLAN_IDX);
-		wcid = rcu_dereference(dev->mt76.wcid[wcid_idx]);
-
-		if (wcid && wcid->sta) {
-			msta = container_of(wcid, struct mt7915_sta, wcid);
-			sta = container_of((void *)msta, struct ieee80211_sta,
-					  drv_priv);
-			spin_lock_bh(&mdev->sta_poll_lock);
-			if (list_empty(&msta->wcid.poll_list))
-				list_add_tail(&msta->wcid.poll_list,
-					      &mdev->sta_poll_list);
-			spin_unlock_bh(&mdev->sta_poll_lock);
-		}
-	}
-
-	if (sta && likely(t->skb->protocol != cpu_to_be16(ETH_P_PAE)))
-		mt7915_tx_check_aggr(sta, txwi);
-
-	__mt76_tx_complete_skb(mdev, wcid_idx, t->skb, free_list);
-
-out:
-	t->skb = NULL;
-	mt76_put_txwi(mdev, t);
-}
-
 static void
 mt7915_mac_tx_free_prepare(struct mt7915_dev *dev)
 {
@@ -1031,7 +962,7 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len)
 			if (!txwi)
 				continue;
 
-			mt7915_txwi_free(dev, txwi, sta, &free_list);
+			mt76_connac2_txwi_free(mdev, txwi, sta, &free_list);
 		}
 	}
 
@@ -1063,7 +994,7 @@ mt7915_mac_tx_free_v0(struct mt7915_dev *dev, void *data, int len)
 		if (!txwi)
 			continue;
 
-		mt7915_txwi_free(dev, txwi, NULL, &free_list);
+		mt76_connac2_txwi_free(mdev, txwi, NULL, &free_list);
 	}
 
 	mt7915_mac_tx_free_done(dev, &free_list, wake);
@@ -1378,20 +1309,6 @@ mt7915_update_beacons(struct mt7915_dev *dev)
 		mt7915_update_vif_beacon, mphy_ext->hw);
 }
 
-void mt7915_tx_token_put(struct mt7915_dev *dev)
-{
-	struct mt76_txwi_cache *txwi;
-	int id;
-
-	spin_lock_bh(&dev->mt76.token_lock);
-	idr_for_each_entry(&dev->mt76.token, txwi, id) {
-		mt7915_txwi_free(dev, txwi, NULL, NULL);
-		dev->mt76.token_count--;
-	}
-	spin_unlock_bh(&dev->mt76.token_lock);
-	idr_destroy(&dev->mt76.token);
-}
-
 static int
 mt7915_mac_restart(struct mt7915_dev *dev)
 {
@@ -1440,7 +1357,7 @@ mt7915_mac_restart(struct mt7915_dev *dev)
 	napi_disable(&dev->mt76.tx_napi);
 
 	/* token reinit */
-	mt7915_tx_token_put(dev);
+	mt76_connac2_tx_token_put(&dev->mt76);
 	idr_init(&dev->mt76.token);
 
 	mt7915_dma_reset(dev, true);
@@ -1633,7 +1550,7 @@ void mt7915_mac_reset_work(struct work_struct *work)
 	if (mt7915_wait_reset_state(dev, MT_MCU_CMD_RESET_DONE)) {
 		mt7915_dma_reset(dev, false);
 
-		mt7915_tx_token_put(dev);
+		mt76_connac2_tx_token_put(&dev->mt76);
 		idr_init(&dev->mt76.token);
 
 		mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_DMA_INIT);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index 066934249a09e..0c7226b8c805e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -555,7 +555,6 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			  enum mt76_txq_id qid, struct mt76_wcid *wcid,
 			  struct ieee80211_sta *sta,
 			  struct mt76_tx_info *tx_info);
-void mt7915_tx_token_put(struct mt7915_dev *dev);
 void mt7915_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			 struct sk_buff *skb, u32 *info);
 bool mt7915_rx_check(struct mt76_dev *mdev, void *data, int len);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 3e589748e1a3d..368f92719abfc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -511,30 +511,6 @@ mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb)
 	return 0;
 }
 
-static void mt7921_tx_check_aggr(struct ieee80211_sta *sta, __le32 *txwi)
-{
-	struct mt7921_sta *msta;
-	u16 fc, tid;
-	u32 val;
-
-	if (!sta || !(sta->deflink.ht_cap.ht_supported || sta->deflink.he_cap.has_he))
-		return;
-
-	tid = le32_get_bits(txwi[1], MT_TXD1_TID);
-	if (tid >= 6) /* skip VO queue */
-		return;
-
-	val = le32_to_cpu(txwi[2]);
-	fc = FIELD_GET(MT_TXD2_FRAME_TYPE, val) << 2 |
-	     FIELD_GET(MT_TXD2_SUB_TYPE, val) << 4;
-	if (unlikely(fc != (IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_DATA)))
-		return;
-
-	msta = (struct mt7921_sta *)sta->drv_priv;
-	if (!test_and_set_bit(tid, &msta->wcid.ampdu_state))
-		ieee80211_start_tx_ba_session(sta, tid, 0);
-}
-
 void mt7921_mac_add_txs(struct mt7921_dev *dev, void *data)
 {
 	struct mt7921_sta *msta = NULL;
@@ -576,37 +552,6 @@ out:
 	rcu_read_unlock();
 }
 
-void mt7921_txwi_free(struct mt7921_dev *dev, struct mt76_txwi_cache *t,
-		      struct ieee80211_sta *sta, bool clear_status,
-		      struct list_head *free_list)
-{
-	struct mt76_dev *mdev = &dev->mt76;
-	__le32 *txwi;
-	u16 wcid_idx;
-
-	mt76_connac_txp_skb_unmap(mdev, t);
-	if (!t->skb)
-		goto out;
-
-	txwi = (__le32 *)mt76_get_txwi_ptr(mdev, t);
-	if (sta) {
-		struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
-
-		if (likely(t->skb->protocol != cpu_to_be16(ETH_P_PAE)))
-			mt7921_tx_check_aggr(sta, txwi);
-
-		wcid_idx = wcid->idx;
-	} else {
-		wcid_idx = le32_get_bits(txwi[1], MT_TXD1_WLAN_IDX);
-	}
-
-	__mt76_tx_complete_skb(mdev, wcid_idx, t->skb, free_list);
-out:
-	t->skb = NULL;
-	mt76_put_txwi(mdev, t);
-}
-EXPORT_SYMBOL_GPL(mt7921_txwi_free);
-
 static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
 {
 	struct mt76_connac_tx_free *free = data;
@@ -669,7 +614,7 @@ static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
 		if (!txwi)
 			continue;
 
-		mt7921_txwi_free(dev, txwi, sta, stat, &free_list);
+		mt76_connac2_txwi_free(mdev, txwi, sta, &free_list);
 	}
 
 	if (wake)
@@ -1235,7 +1180,7 @@ void mt7921_usb_sdio_tx_complete_skb(struct mt76_dev *mdev,
 	sta = wcid_to_sta(wcid);
 
 	if (sta && likely(e->skb->protocol != cpu_to_be16(ETH_P_PAE)))
-		mt7921_tx_check_aggr(sta, txwi);
+		mt76_connac2_tx_check_aggr(sta, txwi);
 
 	skb_pull(e->skb, headroom);
 	mt76_tx_complete_skb(mdev, e->wcid, e->skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 2694ecb1fdcbd..ec9879650174b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -442,7 +442,6 @@ int mt7921e_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			   struct mt76_tx_info *tx_info);
 
 void mt7921_tx_worker(struct mt76_worker *w);
-void mt7921_tx_token_put(struct mt7921_dev *dev);
 bool mt7921_rx_check(struct mt76_dev *mdev, void *data, int len);
 void mt7921_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			 struct sk_buff *skb, u32 *info);
@@ -475,9 +474,6 @@ int mt7921_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			void *data, int len);
 int mt7921_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *msg,
 			 struct netlink_callback *cb, void *data, int len);
-void mt7921_txwi_free(struct mt7921_dev *dev, struct mt76_txwi_cache *t,
-		      struct ieee80211_sta *sta, bool clear_status,
-		      struct list_head *free_list);
 int mt7921_mcu_parse_response(struct mt76_dev *mdev, int cmd,
 			      struct sk_buff *skb, int seq);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 95610a117d2f0..1b7f19939a696 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -115,7 +115,7 @@ static void mt7921e_unregister_device(struct mt7921_dev *dev)
 	cancel_work_sync(&pm->wake_work);
 	cancel_work_sync(&dev->reset_work);
 
-	mt7921_tx_token_put(dev);
+	mt76_connac2_tx_token_put(&dev->mt76);
 	__mt7921_mcu_drv_pmctrl(dev);
 	mt7921_dma_cleanup(dev);
 	mt7921_wfsys_reset(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
index 6053a2556c20c..978c90a034cf1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
@@ -53,20 +53,6 @@ int mt7921e_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	return 0;
 }
 
-void mt7921_tx_token_put(struct mt7921_dev *dev)
-{
-	struct mt76_txwi_cache *txwi;
-	int id;
-
-	spin_lock_bh(&dev->mt76.token_lock);
-	idr_for_each_entry(&dev->mt76.token, txwi, id) {
-		mt7921_txwi_free(dev, txwi, NULL, false, NULL);
-		dev->mt76.token_count--;
-	}
-	spin_unlock_bh(&dev->mt76.token_lock);
-	idr_destroy(&dev->mt76.token);
-}
-
 int mt7921e_mac_reset(struct mt7921_dev *dev)
 {
 	int i, err;
@@ -91,7 +77,7 @@ int mt7921e_mac_reset(struct mt7921_dev *dev)
 	napi_disable(&dev->mt76.napi[MT_RXQ_MCU_WA]);
 	napi_disable(&dev->mt76.tx_napi);
 
-	mt7921_tx_token_put(dev);
+	mt76_connac2_tx_token_put(&dev->mt76);
 	idr_init(&dev->mt76.token);
 
 	mt7921_wpdma_reset(dev, true);
-- 
GitLab


From 0cb065b9ade9cab8be3a75e8b1b734133c355b82 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:30 +0200
Subject: [PATCH 0432/1806] wifi: mt76: move rate info in mt76_vif

This is a preliminary patch to introduce mt76_connac3 mac library used
by WiFi7 chipsets (e.g. mt7996).

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h          |  3 +++
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c    | 10 +++++-----
 drivers/net/wireless/mediatek/mt76/mt7996/main.c   | 10 +++++-----
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h |  4 ----
 5 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 8ec77682d8e90..878087257ea7e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -705,6 +705,9 @@ struct mt76_vif {
 	u8 wmm_idx;
 	u8 scan_seq_num;
 	u8 cipher;
+	u8 basic_rates_idx;
+	u8 mcast_rates_idx;
+	u8 beacon_rates_idx;
 };
 
 struct mt76_phy {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index dfe70e0ff3297..6fc9260a2e924 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -1013,7 +1013,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 	u8 band_idx = (info->hw_queue & MT_TX_HW_QUEUE_PHY) >> 2;
 	u8 p_fmt, q_idx, omac_idx = 0, wmm_idx = 0;
 	bool is_8023 = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP;
-	struct mt7996_vif *mvif;
+	struct mt76_vif *mvif;
 	u16 tx_count = 15;
 	u32 val;
 	bool beacon = !!(changed & (BSS_CHANGED_BEACON |
@@ -1021,11 +1021,11 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 	bool inband_disc = !!(changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP |
 					 BSS_CHANGED_FILS_DISCOVERY));
 
-	mvif = vif ? (struct mt7996_vif *)vif->drv_priv : NULL;
+	mvif = vif ? (struct mt76_vif *)vif->drv_priv : NULL;
 	if (mvif) {
-		omac_idx = mvif->mt76.omac_idx;
-		wmm_idx = mvif->mt76.wmm_idx;
-		band_idx = mvif->mt76.band_idx;
+		omac_idx = mvif->omac_idx;
+		wmm_idx = mvif->wmm_idx;
+		band_idx = mvif->band_idx;
 	}
 
 	if (inband_disc) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 54858cfc93423..c3a479dc3f533 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -223,9 +223,9 @@ static int mt7996_add_interface(struct ieee80211_hw *hw,
 	vif->offload_flags |= IEEE80211_OFFLOAD_ENCAP_4ADDR;
 
 	if (phy->mt76->chandef.chan->band != NL80211_BAND_2GHZ)
-		mvif->basic_rates_idx = MT7996_BASIC_RATES_TBL + 4;
+		mvif->mt76.basic_rates_idx = MT7996_BASIC_RATES_TBL + 4;
 	else
-		mvif->basic_rates_idx = MT7996_BASIC_RATES_TBL;
+		mvif->mt76.basic_rates_idx = MT7996_BASIC_RATES_TBL;
 
 	mt7996_init_bitrate_mask(vif);
 
@@ -505,7 +505,7 @@ static u8
 mt7996_get_rates_table(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		       bool beacon, bool mcast)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv;
 	struct mt76_phy *mphy = hw->priv;
 	u16 rate;
 	u8 i, idx, ht;
@@ -517,7 +517,7 @@ mt7996_get_rates_table(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		struct mt7996_dev *dev = mt7996_hw_dev(hw);
 
 		/* must odd index */
-		idx = MT7996_BEACON_RATES_TBL + 2 * (mvif->mt76.idx % 20);
+		idx = MT7996_BEACON_RATES_TBL + 2 * (mvif->idx % 20);
 		mt7996_mac_set_fixed_rate_table(dev, idx, rate);
 		return idx;
 	}
@@ -555,7 +555,7 @@ static void mt7996_bss_info_changed(struct ieee80211_hw *hw,
 				    struct ieee80211_bss_conf *info,
 				    u64 changed)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv;
 	struct mt7996_phy *phy = mt7996_hw_phy(hw);
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 611f6450520b5..4a30db49ef33f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -604,7 +604,7 @@ static void
 mt7996_mcu_bss_bmc_tlv(struct sk_buff *skb, struct ieee80211_vif *vif,
 		       struct mt7996_phy *phy)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv;
 	struct bss_rate_tlv *bmc;
 	struct cfg80211_chan_def *chandef = &phy->mt76->chandef;
 	enum nl80211_band band = chandef->chan->band;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 79cb71c16264a..726c222e8e1e3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -128,10 +128,6 @@ struct mt7996_vif {
 
 	struct ieee80211_tx_queue_params queue_params[IEEE80211_NUM_ACS];
 	struct cfg80211_bitrate_mask bitrate_mask;
-
-	u8 basic_rates_idx;
-	u8 mcast_rates_idx;
-	u8 beacon_rates_idx;
 };
 
 /* crash-dump */
-- 
GitLab


From 4e9011fcdfc4f325df1661e600a0dcd9064c2bd9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:31 +0200
Subject: [PATCH 0433/1806] wifi: mt76: connac: move connac3 definitions in
 mt76_connac3_mac.h

Connac3 mac definitions are shared between WiFi7 chipsets so move them in
mt76_connac3_mac.h

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt76_connac3_mac.h | 325 ++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7996/mac.h   | 315 +----------------
 2 files changed, 326 insertions(+), 314 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
new file mode 100644
index 0000000000000..6663a0b46541a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
@@ -0,0 +1,325 @@
+/* SPDX-License-Identifier: ISC */
+/* Copyright (C) 2023 MediaTek Inc. */
+
+#ifndef __MT76_CONNAC3_MAC_H
+#define __MT76_CONNAC3_MAC_H
+
+#define MT_CT_PARSE_LEN			72
+#define MT_CT_DMA_BUF_NUM		2
+
+#define MT_RXD0_LENGTH			GENMASK(15, 0)
+#define MT_RXD0_PKT_FLAG                GENMASK(19, 16)
+#define MT_RXD0_PKT_TYPE		GENMASK(31, 27)
+
+#define MT_RXD0_MESH			BIT(18)
+#define MT_RXD0_MHCP			BIT(19)
+#define MT_RXD0_NORMAL_ETH_TYPE_OFS	GENMASK(22, 16)
+#define MT_RXD0_NORMAL_IP_SUM		BIT(23)
+#define MT_RXD0_NORMAL_UDP_TCP_SUM	BIT(24)
+
+#define MT_RXD0_SW_PKT_TYPE_MASK	GENMASK(31, 16)
+#define MT_RXD0_SW_PKT_TYPE_MAP		0x380F
+#define MT_RXD0_SW_PKT_TYPE_FRAME	0x3801
+
+/* RXD DW1 */
+#define MT_RXD1_NORMAL_WLAN_IDX		GENMASK(11, 0)
+#define MT_RXD1_NORMAL_GROUP_1		BIT(16)
+#define MT_RXD1_NORMAL_GROUP_2		BIT(17)
+#define MT_RXD1_NORMAL_GROUP_3		BIT(18)
+#define MT_RXD1_NORMAL_GROUP_4		BIT(19)
+#define MT_RXD1_NORMAL_GROUP_5		BIT(20)
+#define MT_RXD1_NORMAL_KEY_ID		GENMASK(22, 21)
+#define MT_RXD1_NORMAL_CM		BIT(23)
+#define MT_RXD1_NORMAL_CLM		BIT(24)
+#define MT_RXD1_NORMAL_ICV_ERR		BIT(25)
+#define MT_RXD1_NORMAL_TKIP_MIC_ERR	BIT(26)
+#define MT_RXD1_NORMAL_BAND_IDX		GENMASK(28, 27)
+#define MT_RXD1_NORMAL_SPP_EN		BIT(29)
+#define MT_RXD1_NORMAL_ADD_OM		BIT(30)
+#define MT_RXD1_NORMAL_SEC_DONE		BIT(31)
+
+/* RXD DW2 */
+#define MT_RXD2_NORMAL_BSSID		GENMASK(5, 0)
+#define MT_RXD2_NORMAL_MAC_HDR_LEN	GENMASK(12, 8)
+#define MT_RXD2_NORMAL_HDR_TRANS	BIT(7)
+#define MT_RXD2_NORMAL_HDR_OFFSET	GENMASK(15, 13)
+#define MT_RXD2_NORMAL_SEC_MODE		GENMASK(20, 16)
+#define MT_RXD2_NORMAL_MU_BAR		BIT(21)
+#define MT_RXD2_NORMAL_SW_BIT		BIT(22)
+#define MT_RXD2_NORMAL_AMSDU_ERR	BIT(23)
+#define MT_RXD2_NORMAL_MAX_LEN_ERROR	BIT(24)
+#define MT_RXD2_NORMAL_HDR_TRANS_ERROR	BIT(25)
+#define MT_RXD2_NORMAL_INT_FRAME	BIT(26)
+#define MT_RXD2_NORMAL_FRAG		BIT(27)
+#define MT_RXD2_NORMAL_NULL_FRAME	BIT(28)
+#define MT_RXD2_NORMAL_NDATA		BIT(29)
+#define MT_RXD2_NORMAL_NON_AMPDU	BIT(30)
+#define MT_RXD2_NORMAL_BF_REPORT	BIT(31)
+
+/* RXD DW3 */
+#define MT_RXD3_NORMAL_RXV_SEQ		GENMASK(7, 0)
+#define MT_RXD3_NORMAL_CH_FREQ		GENMASK(15, 8)
+#define MT_RXD3_NORMAL_ADDR_TYPE	GENMASK(17, 16)
+#define MT_RXD3_NORMAL_U2M		BIT(0)
+#define MT_RXD3_NORMAL_HTC_VLD		BIT(18)
+#define MT_RXD3_NORMAL_BEACON_MC	BIT(20)
+#define MT_RXD3_NORMAL_BEACON_UC	BIT(21)
+#define MT_RXD3_NORMAL_CO_ANT		BIT(22)
+#define MT_RXD3_NORMAL_FCS_ERR		BIT(24)
+#define MT_RXD3_NORMAL_VLAN2ETH		BIT(31)
+
+/* RXD DW4 */
+#define MT_RXD4_NORMAL_PAYLOAD_FORMAT	GENMASK(1, 0)
+#define MT_RXD4_FIRST_AMSDU_FRAME	GENMASK(1, 0)
+#define MT_RXD4_MID_AMSDU_FRAME		BIT(1)
+#define MT_RXD4_LAST_AMSDU_FRAME	BIT(0)
+
+#define MT_RXV_HDR_BAND_IDX		BIT(24)
+
+/* RXD GROUP4 */
+#define MT_RXD8_FRAME_CONTROL		GENMASK(15, 0)
+
+#define MT_RXD10_SEQ_CTRL		GENMASK(15, 0)
+#define MT_RXD10_QOS_CTL		GENMASK(31, 16)
+
+#define MT_RXD11_HT_CONTROL		GENMASK(31, 0)
+
+/* P-RXV */
+#define MT_PRXV_TX_RATE			GENMASK(6, 0)
+#define MT_PRXV_TX_DCM			BIT(4)
+#define MT_PRXV_TX_ER_SU_106T		BIT(5)
+#define MT_PRXV_NSTS			GENMASK(10, 7)
+#define MT_PRXV_TXBF			BIT(11)
+#define MT_PRXV_HT_AD_CODE		BIT(12)
+#define MT_PRXV_HE_RU_ALLOC		GENMASK(30, 22)
+#define MT_PRXV_RCPI3			GENMASK(31, 24)
+#define MT_PRXV_RCPI2			GENMASK(23, 16)
+#define MT_PRXV_RCPI1			GENMASK(15, 8)
+#define MT_PRXV_RCPI0			GENMASK(7, 0)
+#define MT_PRXV_HT_SHORT_GI		GENMASK(4, 3)
+#define MT_PRXV_HT_STBC			GENMASK(10, 9)
+#define MT_PRXV_TX_MODE			GENMASK(14, 11)
+#define MT_PRXV_FRAME_MODE		GENMASK(2, 0)
+#define MT_PRXV_DCM			BIT(5)
+
+/* C-RXV */
+#define MT_CRXV_HE_NUM_USER		GENMASK(26, 20)
+#define MT_CRXV_HE_LTF_SIZE		GENMASK(28, 27)
+#define MT_CRXV_HE_LDPC_EXT_SYM		BIT(30)
+
+#define MT_CRXV_HE_PE_DISAMBIG		BIT(1)
+#define MT_CRXV_HE_UPLINK		BIT(2)
+
+#define MT_CRXV_HE_MU_AID		GENMASK(27, 17)
+#define MT_CRXV_HE_BEAM_CHNG		BIT(29)
+
+#define MT_CRXV_HE_DOPPLER		BIT(0)
+#define MT_CRXV_HE_BSS_COLOR		GENMASK(15, 10)
+#define MT_CRXV_HE_TXOP_DUR		GENMASK(19, 17)
+
+#define MT_CRXV_HE_SR_MASK		GENMASK(11, 8)
+#define MT_CRXV_HE_SR1_MASK		GENMASK(16, 12)
+#define MT_CRXV_HE_SR2_MASK             GENMASK(20, 17)
+#define MT_CRXV_HE_SR3_MASK             GENMASK(24, 21)
+
+#define MT_CRXV_HE_RU0			GENMASK(8, 0)
+#define MT_CRXV_HE_RU1			GENMASK(17, 9)
+#define MT_CRXV_HE_RU2			GENMASK(26, 18)
+#define MT_CRXV_HE_RU3_L		GENMASK(31, 27)
+#define MT_CRXV_HE_RU3_H		GENMASK(3, 0)
+
+enum tx_header_format {
+	MT_HDR_FORMAT_802_3,
+	MT_HDR_FORMAT_CMD,
+	MT_HDR_FORMAT_802_11,
+	MT_HDR_FORMAT_802_11_EXT,
+};
+
+enum tx_pkt_type {
+	MT_TX_TYPE_CT,
+	MT_TX_TYPE_SF,
+	MT_TX_TYPE_CMD,
+	MT_TX_TYPE_FW,
+};
+
+enum tx_port_idx {
+	MT_TX_PORT_IDX_LMAC,
+	MT_TX_PORT_IDX_MCU
+};
+
+enum tx_mcu_port_q_idx {
+	MT_TX_MCU_PORT_RX_Q0 = 0x20,
+	MT_TX_MCU_PORT_RX_Q1,
+	MT_TX_MCU_PORT_RX_Q2,
+	MT_TX_MCU_PORT_RX_Q3,
+	MT_TX_MCU_PORT_RX_FWDL = 0x3e
+};
+
+enum tx_mgnt_type {
+	MT_TX_NORMAL,
+	MT_TX_TIMING,
+	MT_TX_ADDBA,
+};
+
+#define MT_CT_INFO_APPLY_TXD		BIT(0)
+#define MT_CT_INFO_COPY_HOST_TXD_ALL	BIT(1)
+#define MT_CT_INFO_MGMT_FRAME		BIT(2)
+#define MT_CT_INFO_NONE_CIPHER_FRAME	BIT(3)
+#define MT_CT_INFO_HSR2_TX		BIT(4)
+#define MT_CT_INFO_FROM_HOST		BIT(7)
+
+#define MT_TXD_SIZE			(8 * 4)
+
+#define MT_TXD0_Q_IDX			GENMASK(31, 25)
+#define MT_TXD0_PKT_FMT			GENMASK(24, 23)
+#define MT_TXD0_ETH_TYPE_OFFSET		GENMASK(22, 16)
+#define MT_TXD0_TX_BYTES		GENMASK(15, 0)
+
+#define MT_TXD1_FIXED_RATE		BIT(31)
+#define MT_TXD1_OWN_MAC			GENMASK(30, 25)
+#define MT_TXD1_TID			GENMASK(24, 21)
+#define MT_TXD1_BIP			BIT(24)
+#define MT_TXD1_ETH_802_3		BIT(20)
+#define MT_TXD1_HDR_INFO		GENMASK(20, 16)
+#define MT_TXD1_HDR_FORMAT		GENMASK(15, 14)
+#define MT_TXD1_TGID			GENMASK(13, 12)
+#define MT_TXD1_WLAN_IDX		GENMASK(11, 0)
+
+#define MT_TXD2_POWER_OFFSET		GENMASK(31, 26)
+#define MT_TXD2_MAX_TX_TIME		GENMASK(25, 16)
+#define MT_TXD2_FRAG			GENMASK(15, 14)
+#define MT_TXD2_HTC_VLD			BIT(13)
+#define MT_TXD2_DURATION		BIT(12)
+#define MT_TXD2_HDR_PAD			GENMASK(11, 10)
+#define MT_TXD2_RTS			BIT(9)
+#define MT_TXD2_OWN_MAC_MAP		BIT(8)
+#define MT_TXD2_BF_TYPE			GENMASK(6, 7)
+#define MT_TXD2_FRAME_TYPE		GENMASK(5, 4)
+#define MT_TXD2_SUB_TYPE		GENMASK(3, 0)
+
+#define MT_TXD3_SN_VALID		BIT(31)
+#define MT_TXD3_PN_VALID		BIT(30)
+#define MT_TXD3_SW_POWER_MGMT		BIT(29)
+#define MT_TXD3_BA_DISABLE		BIT(28)
+#define MT_TXD3_SEQ			GENMASK(27, 16)
+#define MT_TXD3_REM_TX_COUNT		GENMASK(15, 11)
+#define MT_TXD3_TX_COUNT		GENMASK(10, 6)
+#define MT_TXD3_HW_AMSDU		BIT(5)
+#define MT_TXD3_BCM			BIT(4)
+#define MT_TXD3_EEOSP			BIT(3)
+#define MT_TXD3_EMRD			BIT(2)
+#define MT_TXD3_PROTECT_FRAME		BIT(1)
+#define MT_TXD3_NO_ACK			BIT(0)
+
+#define MT_TXD4_PN_LOW			GENMASK(31, 0)
+
+#define MT_TXD5_PN_HIGH			GENMASK(31, 16)
+#define MT_TXD5_FL			BIT(15)
+#define MT_TXD5_BYPASS_TBB		BIT(14)
+#define MT_TXD5_BYPASS_RBB		BIT(13)
+#define MT_TXD5_BSS_COLOR_ZERO		BIT(12)
+#define MT_TXD5_TX_STATUS_HOST		BIT(10)
+#define MT_TXD5_TX_STATUS_MCU		BIT(9)
+#define MT_TXD5_TX_STATUS_FMT		BIT(8)
+#define MT_TXD5_PID			GENMASK(7, 0)
+
+#define MT_TXD6_TX_SRC			GENMASK(31, 30)
+#define MT_TXD6_VTA			BIT(28)
+#define MT_TXD6_BW			GENMASK(25, 22)
+#define MT_TXD6_TX_RATE			GENMASK(21, 16)
+#define MT_TXD6_TIMESTAMP_OFS_EN	BIT(15)
+#define MT_TXD6_TIMESTAMP_OFS_IDX	GENMASK(14, 10)
+#define MT_TXD6_MSDU_CNT		GENMASK(9, 4)
+#define MT_TXD6_DIS_MAT			BIT(3)
+#define MT_TXD6_DAS			BIT(2)
+#define MT_TXD6_AMSDU_CAP		BIT(1)
+
+#define MT_TXD7_TXD_LEN			GENMASK(31, 30)
+#define MT_TXD7_IP_SUM			BIT(29)
+#define MT_TXD7_DROP_BY_SDO		BIT(28)
+#define MT_TXD7_MAC_TXD			BIT(27)
+#define MT_TXD7_CTXD			BIT(26)
+#define MT_TXD7_CTXD_CNT		GENMASK(25, 22)
+#define MT_TXD7_UDP_TCP_SUM		BIT(15)
+#define MT_TXD7_TX_TIME			GENMASK(9, 0)
+
+#define MT_TX_RATE_STBC			BIT(14)
+#define MT_TX_RATE_NSS			GENMASK(13, 10)
+#define MT_TX_RATE_MODE			GENMASK(9, 6)
+#define MT_TX_RATE_SU_EXT_TONE		BIT(5)
+#define MT_TX_RATE_DCM			BIT(4)
+/* VHT/HE only use bits 0-3 */
+#define MT_TX_RATE_IDX			GENMASK(5, 0)
+
+#define MT_TXFREE0_PKT_TYPE		GENMASK(31, 27)
+#define MT_TXFREE0_MSDU_CNT		GENMASK(25, 16)
+#define MT_TXFREE0_RX_BYTE		GENMASK(15, 0)
+
+#define MT_TXFREE1_VER			GENMASK(18, 16)
+
+#define MT_TXFREE_INFO_PAIR		BIT(31)
+#define MT_TXFREE_INFO_HEADER		BIT(30)
+#define MT_TXFREE_INFO_WLAN_ID		GENMASK(23, 12)
+#define MT_TXFREE_INFO_MSDU_ID		GENMASK(14, 0)
+#define MT_TXFREE_INFO_COUNT		GENMASK(27, 24)
+#define MT_TXFREE_INFO_STAT		GENMASK(29, 28)
+
+#define MT_TXS0_BW			GENMASK(31, 29)
+#define MT_TXS0_TID			GENMASK(28, 26)
+#define MT_TXS0_AMPDU			BIT(25)
+#define MT_TXS0_TXS_FORMAT		GENMASK(24, 23)
+#define MT_TXS0_BA_ERROR		BIT(22)
+#define MT_TXS0_PS_FLAG			BIT(21)
+#define MT_TXS0_TXOP_TIMEOUT		BIT(20)
+#define MT_TXS0_BIP_ERROR		BIT(19)
+
+#define MT_TXS0_QUEUE_TIMEOUT		BIT(18)
+#define MT_TXS0_RTS_TIMEOUT		BIT(17)
+#define MT_TXS0_ACK_TIMEOUT		BIT(16)
+#define MT_TXS0_ACK_ERROR_MASK		GENMASK(18, 16)
+
+#define MT_TXS0_TX_STATUS_HOST		BIT(15)
+#define MT_TXS0_TX_STATUS_MCU		BIT(14)
+#define MT_TXS0_TX_RATE			GENMASK(13, 0)
+
+#define MT_TXS1_SEQNO			GENMASK(31, 20)
+#define MT_TXS1_RESP_RATE		GENMASK(19, 16)
+#define MT_TXS1_RXV_SEQNO		GENMASK(15, 8)
+#define MT_TXS1_TX_POWER_DBM		GENMASK(7, 0)
+
+#define MT_TXS2_BF_STATUS		GENMASK(31, 30)
+#define MT_TXS2_BAND			GENMASK(29, 28)
+#define MT_TXS2_WCID			GENMASK(27, 16)
+#define MT_TXS2_TX_DELAY		GENMASK(15, 0)
+
+#define MT_TXS3_PID			GENMASK(31, 24)
+#define MT_TXS3_RATE_STBC		BIT(7)
+#define MT_TXS3_FIXED_RATE		BIT(6)
+#define MT_TXS3_SRC			GENMASK(5, 4)
+#define MT_TXS3_SHARED_ANTENNA		BIT(3)
+#define MT_TXS3_LAST_TX_RATE		GENMASK(2, 0)
+
+#define MT_TXS4_TIMESTAMP		GENMASK(31, 0)
+
+#define MT_TXS5_F0_FINAL_MPDU		BIT(31)
+#define MT_TXS5_F0_QOS			BIT(30)
+#define MT_TXS5_F0_TX_COUNT		GENMASK(29, 25)
+#define MT_TXS5_F0_FRONT_TIME		GENMASK(24, 0)
+#define MT_TXS5_F1_MPDU_TX_COUNT	GENMASK(31, 24)
+#define MT_TXS5_F1_MPDU_TX_BYTES	GENMASK(23, 0)
+
+#define MT_TXS6_F0_NOISE_3		GENMASK(31, 24)
+#define MT_TXS6_F0_NOISE_2		GENMASK(23, 16)
+#define MT_TXS6_F0_NOISE_1		GENMASK(15, 8)
+#define MT_TXS6_F0_NOISE_0		GENMASK(7, 0)
+#define MT_TXS6_F1_MPDU_FAIL_COUNT	GENMASK(31, 24)
+#define MT_TXS6_F1_MPDU_FAIL_BYTES	GENMASK(23, 0)
+
+#define MT_TXS7_F0_RCPI_3		GENMASK(31, 24)
+#define MT_TXS7_F0_RCPI_2		GENMASK(23, 16)
+#define MT_TXS7_F0_RCPI_1		GENMASK(15, 8)
+#define MT_TXS7_F0_RCPI_0		GENMASK(7, 0)
+#define MT_TXS7_F1_MPDU_RETRY_COUNT	GENMASK(31, 24)
+#define MT_TXS7_F1_MPDU_RETRY_BYTES	GENMASK(23, 0)
+
+#endif /* __MT76_CONNAC3_MAC_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.h b/drivers/net/wireless/mediatek/mt76/mt7996/mac.h
index bc4e6c55373eb..e629324a5617e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.h
@@ -6,320 +6,7 @@
 #ifndef __MT7996_MAC_H
 #define __MT7996_MAC_H
 
-#define MT_CT_PARSE_LEN			72
-#define MT_CT_DMA_BUF_NUM		2
-
-#define MT_RXD0_LENGTH			GENMASK(15, 0)
-#define MT_RXD0_PKT_TYPE		GENMASK(31, 27)
-
-#define MT_RXD0_MESH			BIT(18)
-#define MT_RXD0_MHCP			BIT(19)
-#define MT_RXD0_NORMAL_ETH_TYPE_OFS	GENMASK(22, 16)
-#define MT_RXD0_NORMAL_IP_SUM		BIT(23)
-#define MT_RXD0_NORMAL_UDP_TCP_SUM	BIT(24)
-
-#define MT_RXD0_SW_PKT_TYPE_MASK	GENMASK(31, 16)
-#define MT_RXD0_SW_PKT_TYPE_MAP		0x380F
-#define MT_RXD0_SW_PKT_TYPE_FRAME	0x3801
-
-/* RXD DW1 */
-#define MT_RXD1_NORMAL_WLAN_IDX		GENMASK(11, 0)
-#define MT_RXD1_NORMAL_GROUP_1		BIT(16)
-#define MT_RXD1_NORMAL_GROUP_2		BIT(17)
-#define MT_RXD1_NORMAL_GROUP_3		BIT(18)
-#define MT_RXD1_NORMAL_GROUP_4		BIT(19)
-#define MT_RXD1_NORMAL_GROUP_5		BIT(20)
-#define MT_RXD1_NORMAL_KEY_ID		GENMASK(22, 21)
-#define MT_RXD1_NORMAL_CM		BIT(23)
-#define MT_RXD1_NORMAL_CLM		BIT(24)
-#define MT_RXD1_NORMAL_ICV_ERR		BIT(25)
-#define MT_RXD1_NORMAL_TKIP_MIC_ERR	BIT(26)
-#define MT_RXD1_NORMAL_BAND_IDX		GENMASK(28, 27)
-#define MT_RXD1_NORMAL_SPP_EN		BIT(29)
-#define MT_RXD1_NORMAL_ADD_OM		BIT(30)
-#define MT_RXD1_NORMAL_SEC_DONE		BIT(31)
-
-/* RXD DW2 */
-#define MT_RXD2_NORMAL_BSSID		GENMASK(5, 0)
-#define MT_RXD2_NORMAL_MAC_HDR_LEN	GENMASK(12, 8)
-#define MT_RXD2_NORMAL_HDR_TRANS	BIT(7)
-#define MT_RXD2_NORMAL_HDR_OFFSET	GENMASK(15, 13)
-#define MT_RXD2_NORMAL_SEC_MODE		GENMASK(20, 16)
-#define MT_RXD2_NORMAL_MU_BAR		BIT(21)
-#define MT_RXD2_NORMAL_SW_BIT		BIT(22)
-#define MT_RXD2_NORMAL_AMSDU_ERR	BIT(23)
-#define MT_RXD2_NORMAL_MAX_LEN_ERROR	BIT(24)
-#define MT_RXD2_NORMAL_HDR_TRANS_ERROR	BIT(25)
-#define MT_RXD2_NORMAL_INT_FRAME	BIT(26)
-#define MT_RXD2_NORMAL_FRAG		BIT(27)
-#define MT_RXD2_NORMAL_NULL_FRAME	BIT(28)
-#define MT_RXD2_NORMAL_NDATA		BIT(29)
-#define MT_RXD2_NORMAL_NON_AMPDU	BIT(30)
-#define MT_RXD2_NORMAL_BF_REPORT	BIT(31)
-
-/* RXD DW3 */
-#define MT_RXD3_NORMAL_RXV_SEQ		GENMASK(7, 0)
-#define MT_RXD3_NORMAL_CH_FREQ		GENMASK(15, 8)
-#define MT_RXD3_NORMAL_ADDR_TYPE	GENMASK(17, 16)
-#define MT_RXD3_NORMAL_U2M		BIT(0)
-#define MT_RXD3_NORMAL_HTC_VLD		BIT(18)
-#define MT_RXD3_NORMAL_BEACON_MC	BIT(20)
-#define MT_RXD3_NORMAL_BEACON_UC	BIT(21)
-#define MT_RXD3_NORMAL_CO_ANT		BIT(22)
-#define MT_RXD3_NORMAL_FCS_ERR		BIT(24)
-#define MT_RXD3_NORMAL_VLAN2ETH		BIT(31)
-
-/* RXD DW4 */
-#define MT_RXD4_NORMAL_PAYLOAD_FORMAT	GENMASK(1, 0)
-#define MT_RXD4_FIRST_AMSDU_FRAME	GENMASK(1, 0)
-#define MT_RXD4_MID_AMSDU_FRAME		BIT(1)
-#define MT_RXD4_LAST_AMSDU_FRAME	BIT(0)
-
-#define MT_RXV_HDR_BAND_IDX		BIT(24)
-
-/* RXD GROUP4 */
-#define MT_RXD8_FRAME_CONTROL		GENMASK(15, 0)
-
-#define MT_RXD10_SEQ_CTRL		GENMASK(15, 0)
-#define MT_RXD10_QOS_CTL		GENMASK(31, 16)
-
-#define MT_RXD11_HT_CONTROL		GENMASK(31, 0)
-
-/* P-RXV */
-#define MT_PRXV_TX_RATE			GENMASK(6, 0)
-#define MT_PRXV_TX_DCM			BIT(4)
-#define MT_PRXV_TX_ER_SU_106T		BIT(5)
-#define MT_PRXV_NSTS			GENMASK(10, 7)
-#define MT_PRXV_TXBF			BIT(11)
-#define MT_PRXV_HT_AD_CODE		BIT(12)
-#define MT_PRXV_HE_RU_ALLOC		GENMASK(30, 22)
-#define MT_PRXV_RCPI3			GENMASK(31, 24)
-#define MT_PRXV_RCPI2			GENMASK(23, 16)
-#define MT_PRXV_RCPI1			GENMASK(15, 8)
-#define MT_PRXV_RCPI0			GENMASK(7, 0)
-#define MT_PRXV_HT_SHORT_GI		GENMASK(4, 3)
-#define MT_PRXV_HT_STBC			GENMASK(10, 9)
-#define MT_PRXV_TX_MODE			GENMASK(14, 11)
-#define MT_PRXV_FRAME_MODE		GENMASK(2, 0)
-#define MT_PRXV_DCM			BIT(5)
-
-/* C-RXV */
-#define MT_CRXV_HE_NUM_USER		GENMASK(26, 20)
-#define MT_CRXV_HE_LTF_SIZE		GENMASK(28, 27)
-#define MT_CRXV_HE_LDPC_EXT_SYM		BIT(30)
-
-#define MT_CRXV_HE_PE_DISAMBIG		BIT(1)
-#define MT_CRXV_HE_UPLINK		BIT(2)
-
-#define MT_CRXV_HE_MU_AID		GENMASK(27, 17)
-#define MT_CRXV_HE_BEAM_CHNG		BIT(29)
-
-#define MT_CRXV_HE_DOPPLER		BIT(0)
-#define MT_CRXV_HE_BSS_COLOR		GENMASK(15, 10)
-#define MT_CRXV_HE_TXOP_DUR		GENMASK(19, 17)
-
-#define MT_CRXV_HE_SR_MASK		GENMASK(11, 8)
-#define MT_CRXV_HE_SR1_MASK		GENMASK(16, 12)
-#define MT_CRXV_HE_SR2_MASK             GENMASK(20, 17)
-#define MT_CRXV_HE_SR3_MASK             GENMASK(24, 21)
-
-#define MT_CRXV_HE_RU0			GENMASK(8, 0)
-#define MT_CRXV_HE_RU1			GENMASK(17, 9)
-#define MT_CRXV_HE_RU2			GENMASK(26, 18)
-#define MT_CRXV_HE_RU3_L		GENMASK(31, 27)
-#define MT_CRXV_HE_RU3_H		GENMASK(3, 0)
-
-enum tx_header_format {
-	MT_HDR_FORMAT_802_3,
-	MT_HDR_FORMAT_CMD,
-	MT_HDR_FORMAT_802_11,
-	MT_HDR_FORMAT_802_11_EXT,
-};
-
-enum tx_pkt_type {
-	MT_TX_TYPE_CT,
-	MT_TX_TYPE_SF,
-	MT_TX_TYPE_CMD,
-	MT_TX_TYPE_FW,
-};
-
-enum tx_port_idx {
-	MT_TX_PORT_IDX_LMAC,
-	MT_TX_PORT_IDX_MCU
-};
-
-enum tx_mcu_port_q_idx {
-	MT_TX_MCU_PORT_RX_Q0 = 0x20,
-	MT_TX_MCU_PORT_RX_Q1,
-	MT_TX_MCU_PORT_RX_Q2,
-	MT_TX_MCU_PORT_RX_Q3,
-	MT_TX_MCU_PORT_RX_FWDL = 0x3e
-};
-
-enum tx_mgnt_type {
-	MT_TX_NORMAL,
-	MT_TX_TIMING,
-	MT_TX_ADDBA,
-};
-
-#define MT_CT_INFO_APPLY_TXD		BIT(0)
-#define MT_CT_INFO_COPY_HOST_TXD_ALL	BIT(1)
-#define MT_CT_INFO_MGMT_FRAME		BIT(2)
-#define MT_CT_INFO_NONE_CIPHER_FRAME	BIT(3)
-#define MT_CT_INFO_HSR2_TX		BIT(4)
-#define MT_CT_INFO_FROM_HOST		BIT(7)
-
-#define MT_TXD_SIZE			(8 * 4)
-
-#define MT_TXD0_Q_IDX			GENMASK(31, 25)
-#define MT_TXD0_PKT_FMT			GENMASK(24, 23)
-#define MT_TXD0_ETH_TYPE_OFFSET		GENMASK(22, 16)
-#define MT_TXD0_TX_BYTES		GENMASK(15, 0)
-
-#define MT_TXD1_FIXED_RATE		BIT(31)
-#define MT_TXD1_OWN_MAC			GENMASK(30, 25)
-#define MT_TXD1_TID			GENMASK(24, 21)
-#define MT_TXD1_BIP			BIT(24)
-#define MT_TXD1_ETH_802_3		BIT(20)
-#define MT_TXD1_HDR_INFO		GENMASK(20, 16)
-#define MT_TXD1_HDR_FORMAT		GENMASK(15, 14)
-#define MT_TXD1_TGID			GENMASK(13, 12)
-#define MT_TXD1_WLAN_IDX		GENMASK(11, 0)
-
-#define MT_TXD2_POWER_OFFSET		GENMASK(31, 26)
-#define MT_TXD2_MAX_TX_TIME		GENMASK(25, 16)
-#define MT_TXD2_FRAG			GENMASK(15, 14)
-#define MT_TXD2_HTC_VLD			BIT(13)
-#define MT_TXD2_DURATION		BIT(12)
-#define MT_TXD2_HDR_PAD			GENMASK(11, 10)
-#define MT_TXD2_RTS			BIT(9)
-#define MT_TXD2_OWN_MAC_MAP		BIT(8)
-#define MT_TXD2_BF_TYPE			GENMASK(6, 7)
-#define MT_TXD2_FRAME_TYPE		GENMASK(5, 4)
-#define MT_TXD2_SUB_TYPE		GENMASK(3, 0)
-
-#define MT_TXD3_SN_VALID		BIT(31)
-#define MT_TXD3_PN_VALID		BIT(30)
-#define MT_TXD3_SW_POWER_MGMT		BIT(29)
-#define MT_TXD3_BA_DISABLE		BIT(28)
-#define MT_TXD3_SEQ			GENMASK(27, 16)
-#define MT_TXD3_REM_TX_COUNT		GENMASK(15, 11)
-#define MT_TXD3_TX_COUNT		GENMASK(10, 6)
-#define MT_TXD3_HW_AMSDU		BIT(5)
-#define MT_TXD3_BCM			BIT(4)
-#define MT_TXD3_EEOSP			BIT(3)
-#define MT_TXD3_EMRD			BIT(2)
-#define MT_TXD3_PROTECT_FRAME		BIT(1)
-#define MT_TXD3_NO_ACK			BIT(0)
-
-#define MT_TXD4_PN_LOW			GENMASK(31, 0)
-
-#define MT_TXD5_PN_HIGH			GENMASK(31, 16)
-#define MT_TXD5_FL			BIT(15)
-#define MT_TXD5_BYPASS_TBB		BIT(14)
-#define MT_TXD5_BYPASS_RBB		BIT(13)
-#define MT_TXD5_BSS_COLOR_ZERO		BIT(12)
-#define MT_TXD5_TX_STATUS_HOST		BIT(10)
-#define MT_TXD5_TX_STATUS_MCU		BIT(9)
-#define MT_TXD5_TX_STATUS_FMT		BIT(8)
-#define MT_TXD5_PID			GENMASK(7, 0)
-
-#define MT_TXD6_TX_SRC			GENMASK(31, 30)
-#define MT_TXD6_VTA			BIT(28)
-#define MT_TXD6_BW			GENMASK(25, 22)
-#define MT_TXD6_TX_RATE			GENMASK(21, 16)
-#define MT_TXD6_TIMESTAMP_OFS_EN	BIT(15)
-#define MT_TXD6_TIMESTAMP_OFS_IDX	GENMASK(14, 10)
-#define MT_TXD6_MSDU_CNT		GENMASK(9, 4)
-#define MT_TXD6_DIS_MAT			BIT(3)
-#define MT_TXD6_DAS			BIT(2)
-#define MT_TXD6_AMSDU_CAP		BIT(1)
-
-#define MT_TXD7_TXD_LEN			GENMASK(31, 30)
-#define MT_TXD7_IP_SUM			BIT(29)
-#define MT_TXD7_DROP_BY_SDO		BIT(28)
-#define MT_TXD7_MAC_TXD			BIT(27)
-#define MT_TXD7_CTXD			BIT(26)
-#define MT_TXD7_CTXD_CNT		GENMASK(25, 22)
-#define MT_TXD7_UDP_TCP_SUM		BIT(15)
-#define MT_TXD7_TX_TIME			GENMASK(9, 0)
-
-#define MT_TX_RATE_STBC			BIT(14)
-#define MT_TX_RATE_NSS			GENMASK(13, 10)
-#define MT_TX_RATE_MODE			GENMASK(9, 6)
-#define MT_TX_RATE_SU_EXT_TONE		BIT(5)
-#define MT_TX_RATE_DCM			BIT(4)
-/* VHT/HE only use bits 0-3 */
-#define MT_TX_RATE_IDX			GENMASK(5, 0)
-
-#define MT_TXFREE0_PKT_TYPE		GENMASK(31, 27)
-#define MT_TXFREE0_MSDU_CNT		GENMASK(25, 16)
-#define MT_TXFREE0_RX_BYTE		GENMASK(15, 0)
-
-#define MT_TXFREE1_VER			GENMASK(18, 16)
-
-#define MT_TXFREE_INFO_PAIR		BIT(31)
-#define MT_TXFREE_INFO_HEADER		BIT(30)
-#define MT_TXFREE_INFO_WLAN_ID		GENMASK(23, 12)
-#define MT_TXFREE_INFO_MSDU_ID		GENMASK(14, 0)
-
-#define MT_TXS0_BW			GENMASK(31, 29)
-#define MT_TXS0_TID			GENMASK(28, 26)
-#define MT_TXS0_AMPDU			BIT(25)
-#define MT_TXS0_TXS_FORMAT		GENMASK(24, 23)
-#define MT_TXS0_BA_ERROR		BIT(22)
-#define MT_TXS0_PS_FLAG			BIT(21)
-#define MT_TXS0_TXOP_TIMEOUT		BIT(20)
-#define MT_TXS0_BIP_ERROR		BIT(19)
-
-#define MT_TXS0_QUEUE_TIMEOUT		BIT(18)
-#define MT_TXS0_RTS_TIMEOUT		BIT(17)
-#define MT_TXS0_ACK_TIMEOUT		BIT(16)
-#define MT_TXS0_ACK_ERROR_MASK		GENMASK(18, 16)
-
-#define MT_TXS0_TX_STATUS_HOST		BIT(15)
-#define MT_TXS0_TX_STATUS_MCU		BIT(14)
-#define MT_TXS0_TX_RATE			GENMASK(13, 0)
-
-#define MT_TXS1_SEQNO			GENMASK(31, 20)
-#define MT_TXS1_RESP_RATE		GENMASK(19, 16)
-#define MT_TXS1_RXV_SEQNO		GENMASK(15, 8)
-#define MT_TXS1_TX_POWER_DBM		GENMASK(7, 0)
-
-#define MT_TXS2_BF_STATUS		GENMASK(31, 30)
-#define MT_TXS2_BAND			GENMASK(29, 28)
-#define MT_TXS2_WCID			GENMASK(27, 16)
-#define MT_TXS2_TX_DELAY		GENMASK(15, 0)
-
-#define MT_TXS3_PID			GENMASK(31, 24)
-#define MT_TXS3_RATE_STBC		BIT(7)
-#define MT_TXS3_FIXED_RATE		BIT(6)
-#define MT_TXS3_SRC			GENMASK(5, 4)
-#define MT_TXS3_SHARED_ANTENNA		BIT(3)
-#define MT_TXS3_LAST_TX_RATE		GENMASK(2, 0)
-
-#define MT_TXS4_TIMESTAMP		GENMASK(31, 0)
-
-#define MT_TXS5_F0_FINAL_MPDU		BIT(31)
-#define MT_TXS5_F0_QOS			BIT(30)
-#define MT_TXS5_F0_TX_COUNT		GENMASK(29, 25)
-#define MT_TXS5_F0_FRONT_TIME		GENMASK(24, 0)
-#define MT_TXS5_F1_MPDU_TX_COUNT	GENMASK(31, 24)
-#define MT_TXS5_F1_MPDU_TX_BYTES	GENMASK(23, 0)
-
-#define MT_TXS6_F0_NOISE_3		GENMASK(31, 24)
-#define MT_TXS6_F0_NOISE_2		GENMASK(23, 16)
-#define MT_TXS6_F0_NOISE_1		GENMASK(15, 8)
-#define MT_TXS6_F0_NOISE_0		GENMASK(7, 0)
-#define MT_TXS6_F1_MPDU_FAIL_COUNT	GENMASK(31, 24)
-#define MT_TXS6_F1_MPDU_FAIL_BYTES	GENMASK(23, 0)
-
-#define MT_TXS7_F0_RCPI_3		GENMASK(31, 24)
-#define MT_TXS7_F0_RCPI_2		GENMASK(23, 16)
-#define MT_TXS7_F0_RCPI_1		GENMASK(15, 8)
-#define MT_TXS7_F0_RCPI_0		GENMASK(7, 0)
-#define MT_TXS7_F1_MPDU_RETRY_COUNT	GENMASK(31, 24)
-#define MT_TXS7_F1_MPDU_RETRY_BYTES	GENMASK(23, 0)
+#include "../mt76_connac3_mac.h"
 
 struct mt7996_dfs_pulse {
 	u32 max_width;		/* us */
-- 
GitLab


From 46d3304d6552d6dfd715e66b4c28e7c70bedd2f7 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 22 Jun 2023 18:50:32 +0200
Subject: [PATCH 0434/1806] wifi: mt76: connac: add connac3 mac library

Introduce connac3_mac in mt76_connac library to reuse mac code shared
between WiFi7 chipsets. So far connac3 library contains just radiotap
parsing code.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/Makefile   |   2 +-
 .../net/wireless/mediatek/mt76/mt76_connac.h  |   3 +
 .../wireless/mediatek/mt76/mt76_connac3_mac.c | 182 ++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 180 +----------------
 4 files changed, 187 insertions(+), 180 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.c

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index 84c99b7e57f98..d8e8079c8b54f 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -27,7 +27,7 @@ mt76x02-lib-y := mt76x02_util.o mt76x02_mac.o mt76x02_mcu.o \
 
 mt76x02-usb-y := mt76x02_usb_mcu.o mt76x02_usb_core.o
 
-mt76-connac-lib-y := mt76_connac_mcu.o mt76_connac_mac.o
+mt76-connac-lib-y := mt76_connac_mcu.o mt76_connac_mac.o mt76_connac3_mac.o
 
 obj-$(CONFIG_MT76x0_COMMON) += mt76x0/
 obj-$(CONFIG_MT76x2_COMMON) += mt76x2/
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac.h
index d3bb9114160f4..22878f088804b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac.h
@@ -425,4 +425,7 @@ void mt76_connac2_txwi_free(struct mt76_dev *dev, struct mt76_txwi_cache *t,
 			    struct list_head *free_list);
 void mt76_connac2_tx_token_put(struct mt76_dev *dev);
 
+/* connac3 */
+void mt76_connac3_mac_decode_he_radiotap(struct sk_buff *skb, __le32 *rxv,
+					 u8 mode);
 #endif /* __MT76_CONNAC_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.c
new file mode 100644
index 0000000000000..73e9f283d0ae3
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: ISC
+/* Copyright (C) 2023 MediaTek Inc. */
+
+#include "mt76_connac.h"
+#include "mt76_connac3_mac.h"
+#include "dma.h"
+
+#define HE_BITS(f)		cpu_to_le16(IEEE80211_RADIOTAP_HE_##f)
+#define HE_PREP(f, m, v)	le16_encode_bits(le32_get_bits(v, MT_CRXV_HE_##m),\
+						 IEEE80211_RADIOTAP_HE_##f)
+
+static void
+mt76_connac3_mac_decode_he_radiotap_ru(struct mt76_rx_status *status,
+				       struct ieee80211_radiotap_he *he,
+				       __le32 *rxv)
+{
+	u32 ru = le32_get_bits(rxv[0], MT_PRXV_HE_RU_ALLOC), offs = 0;
+
+	status->bw = RATE_INFO_BW_HE_RU;
+
+	switch (ru) {
+	case 0 ... 36:
+		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_26;
+		offs = ru;
+		break;
+	case 37 ... 52:
+		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_52;
+		offs = ru - 37;
+		break;
+	case 53 ... 60:
+		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+		offs = ru - 53;
+		break;
+	case 61 ... 64:
+		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_242;
+		offs = ru - 61;
+		break;
+	case 65 ... 66:
+		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_484;
+		offs = ru - 65;
+		break;
+	case 67:
+		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_996;
+		break;
+	case 68:
+		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_2x996;
+		break;
+	}
+
+	he->data1 |= HE_BITS(DATA1_BW_RU_ALLOC_KNOWN);
+	he->data2 |= HE_BITS(DATA2_RU_OFFSET_KNOWN) |
+		     le16_encode_bits(offs,
+				      IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET);
+}
+
+#define MU_PREP(f, v)	le16_encode_bits(v, IEEE80211_RADIOTAP_HE_MU_##f)
+static void
+mt76_connac3_mac_decode_he_mu_radiotap(struct sk_buff *skb, __le32 *rxv)
+{
+	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
+	static const struct ieee80211_radiotap_he_mu mu_known = {
+		.flags1 = HE_BITS(MU_FLAGS1_SIG_B_MCS_KNOWN) |
+			  HE_BITS(MU_FLAGS1_SIG_B_DCM_KNOWN) |
+			  HE_BITS(MU_FLAGS1_CH1_RU_KNOWN) |
+			  HE_BITS(MU_FLAGS1_SIG_B_SYMS_USERS_KNOWN),
+		.flags2 = HE_BITS(MU_FLAGS2_BW_FROM_SIG_A_BW_KNOWN),
+	};
+	struct ieee80211_radiotap_he_mu *he_mu;
+
+	status->flag |= RX_FLAG_RADIOTAP_HE_MU;
+
+	he_mu = skb_push(skb, sizeof(mu_known));
+	memcpy(he_mu, &mu_known, sizeof(mu_known));
+
+	he_mu->flags1 |= MU_PREP(FLAGS1_SIG_B_MCS, status->rate_idx);
+	if (status->he_dcm)
+		he_mu->flags1 |= MU_PREP(FLAGS1_SIG_B_DCM, status->he_dcm);
+
+	he_mu->flags2 |= MU_PREP(FLAGS2_BW_FROM_SIG_A_BW, status->bw) |
+			 MU_PREP(FLAGS2_SIG_B_SYMS_USERS,
+				 le32_get_bits(rxv[4], MT_CRXV_HE_NUM_USER));
+
+	he_mu->ru_ch1[0] = le32_get_bits(rxv[16], MT_CRXV_HE_RU0) & 0xff;
+
+	if (status->bw >= RATE_INFO_BW_40) {
+		he_mu->flags1 |= HE_BITS(MU_FLAGS1_CH2_RU_KNOWN);
+		he_mu->ru_ch2[0] = le32_get_bits(rxv[16], MT_CRXV_HE_RU1) & 0xff;
+	}
+
+	if (status->bw >= RATE_INFO_BW_80) {
+		u32 ru_h, ru_l;
+
+		he_mu->ru_ch1[1] = le32_get_bits(rxv[16], MT_CRXV_HE_RU2) & 0xff;
+
+		ru_l = le32_get_bits(rxv[16], MT_CRXV_HE_RU3_L);
+		ru_h = le32_get_bits(rxv[17], MT_CRXV_HE_RU3_H) & 0x7;
+		he_mu->ru_ch2[1] = (u8)(ru_l | ru_h << 4);
+	}
+}
+
+void mt76_connac3_mac_decode_he_radiotap(struct sk_buff *skb, __le32 *rxv,
+					 u8 mode)
+{
+	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
+	static const struct ieee80211_radiotap_he known = {
+		.data1 = HE_BITS(DATA1_DATA_MCS_KNOWN) |
+			 HE_BITS(DATA1_DATA_DCM_KNOWN) |
+			 HE_BITS(DATA1_STBC_KNOWN) |
+			 HE_BITS(DATA1_CODING_KNOWN) |
+			 HE_BITS(DATA1_LDPC_XSYMSEG_KNOWN) |
+			 HE_BITS(DATA1_DOPPLER_KNOWN) |
+			 HE_BITS(DATA1_SPTL_REUSE_KNOWN) |
+			 HE_BITS(DATA1_BSS_COLOR_KNOWN),
+		.data2 = HE_BITS(DATA2_GI_KNOWN) |
+			 HE_BITS(DATA2_TXBF_KNOWN) |
+			 HE_BITS(DATA2_PE_DISAMBIG_KNOWN) |
+			 HE_BITS(DATA2_TXOP_KNOWN),
+	};
+	u32 ltf_size = le32_get_bits(rxv[4], MT_CRXV_HE_LTF_SIZE) + 1;
+	struct ieee80211_radiotap_he *he;
+
+	status->flag |= RX_FLAG_RADIOTAP_HE;
+
+	he = skb_push(skb, sizeof(known));
+	memcpy(he, &known, sizeof(known));
+
+	he->data3 = HE_PREP(DATA3_BSS_COLOR, BSS_COLOR, rxv[9]) |
+		    HE_PREP(DATA3_LDPC_XSYMSEG, LDPC_EXT_SYM, rxv[4]);
+	he->data4 = HE_PREP(DATA4_SU_MU_SPTL_REUSE, SR_MASK, rxv[13]);
+	he->data5 = HE_PREP(DATA5_PE_DISAMBIG, PE_DISAMBIG, rxv[5]) |
+		    le16_encode_bits(ltf_size,
+				     IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE);
+	if (le32_to_cpu(rxv[0]) & MT_PRXV_TXBF)
+		he->data5 |= HE_BITS(DATA5_TXBF);
+	he->data6 = HE_PREP(DATA6_TXOP, TXOP_DUR, rxv[9]) |
+		    HE_PREP(DATA6_DOPPLER, DOPPLER, rxv[9]);
+
+	switch (mode) {
+	case MT_PHY_TYPE_HE_SU:
+		he->data1 |= HE_BITS(DATA1_FORMAT_SU) |
+			     HE_BITS(DATA1_UL_DL_KNOWN) |
+			     HE_BITS(DATA1_BEAM_CHANGE_KNOWN) |
+			     HE_BITS(DATA1_BW_RU_ALLOC_KNOWN);
+
+		he->data3 |= HE_PREP(DATA3_BEAM_CHANGE, BEAM_CHNG, rxv[8]) |
+			     HE_PREP(DATA3_UL_DL, UPLINK, rxv[5]);
+		break;
+	case MT_PHY_TYPE_HE_EXT_SU:
+		he->data1 |= HE_BITS(DATA1_FORMAT_EXT_SU) |
+			     HE_BITS(DATA1_UL_DL_KNOWN) |
+			     HE_BITS(DATA1_BW_RU_ALLOC_KNOWN);
+
+		he->data3 |= HE_PREP(DATA3_UL_DL, UPLINK, rxv[5]);
+		break;
+	case MT_PHY_TYPE_HE_MU:
+		he->data1 |= HE_BITS(DATA1_FORMAT_MU) |
+			     HE_BITS(DATA1_UL_DL_KNOWN);
+
+		he->data3 |= HE_PREP(DATA3_UL_DL, UPLINK, rxv[5]);
+		he->data4 |= HE_PREP(DATA4_MU_STA_ID, MU_AID, rxv[8]);
+
+		mt76_connac3_mac_decode_he_radiotap_ru(status, he, rxv);
+		mt76_connac3_mac_decode_he_mu_radiotap(skb, rxv);
+		break;
+	case MT_PHY_TYPE_HE_TB:
+		he->data1 |= HE_BITS(DATA1_FORMAT_TRIG) |
+			     HE_BITS(DATA1_SPTL_REUSE2_KNOWN) |
+			     HE_BITS(DATA1_SPTL_REUSE3_KNOWN) |
+			     HE_BITS(DATA1_SPTL_REUSE4_KNOWN);
+
+		he->data4 |= HE_PREP(DATA4_TB_SPTL_REUSE1, SR_MASK, rxv[13]) |
+			     HE_PREP(DATA4_TB_SPTL_REUSE2, SR1_MASK, rxv[13]) |
+			     HE_PREP(DATA4_TB_SPTL_REUSE3, SR2_MASK, rxv[13]) |
+			     HE_PREP(DATA4_TB_SPTL_REUSE4, SR3_MASK, rxv[13]);
+
+		mt76_connac3_mac_decode_he_radiotap_ru(status, he, rxv);
+		break;
+	default:
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(mt76_connac3_mac_decode_he_radiotap);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 6fc9260a2e924..ac8759febe485 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -13,10 +13,6 @@
 
 #define to_rssi(field, rcpi)	((FIELD_GET(field, rcpi) - 220) / 2)
 
-#define HE_BITS(f)		cpu_to_le16(IEEE80211_RADIOTAP_HE_##f)
-#define HE_PREP(f, m, v)	le16_encode_bits(le32_get_bits(v, MT_CRXV_HE_##m),\
-						 IEEE80211_RADIOTAP_HE_##f)
-
 static const struct mt7996_dfs_radar_spec etsi_radar_specs = {
 	.pulse_th = { 110, -10, -80, 40, 5200, 128, 5200 },
 	.radar_pattern = {
@@ -263,180 +259,6 @@ void mt7996_mac_set_fixed_rate_table(struct mt7996_dev *dev,
 	mt76_wr(dev, MT_WTBL_ITCR, ctrl);
 }
 
-static void
-mt7996_mac_decode_he_radiotap_ru(struct mt76_rx_status *status,
-				 struct ieee80211_radiotap_he *he,
-				 __le32 *rxv)
-{
-	u32 ru, offs = 0;
-
-	ru = le32_get_bits(rxv[0], MT_PRXV_HE_RU_ALLOC);
-
-	status->bw = RATE_INFO_BW_HE_RU;
-
-	switch (ru) {
-	case 0 ... 36:
-		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_26;
-		offs = ru;
-		break;
-	case 37 ... 52:
-		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_52;
-		offs = ru - 37;
-		break;
-	case 53 ... 60:
-		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_106;
-		offs = ru - 53;
-		break;
-	case 61 ... 64:
-		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_242;
-		offs = ru - 61;
-		break;
-	case 65 ... 66:
-		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_484;
-		offs = ru - 65;
-		break;
-	case 67:
-		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_996;
-		break;
-	case 68:
-		status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_2x996;
-		break;
-	}
-
-	he->data1 |= HE_BITS(DATA1_BW_RU_ALLOC_KNOWN);
-	he->data2 |= HE_BITS(DATA2_RU_OFFSET_KNOWN) |
-		     le16_encode_bits(offs,
-				      IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET);
-}
-
-static void
-mt7996_mac_decode_he_mu_radiotap(struct sk_buff *skb, __le32 *rxv)
-{
-	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
-	static const struct ieee80211_radiotap_he_mu mu_known = {
-		.flags1 = HE_BITS(MU_FLAGS1_SIG_B_MCS_KNOWN) |
-			  HE_BITS(MU_FLAGS1_SIG_B_DCM_KNOWN) |
-			  HE_BITS(MU_FLAGS1_CH1_RU_KNOWN) |
-			  HE_BITS(MU_FLAGS1_SIG_B_SYMS_USERS_KNOWN),
-		.flags2 = HE_BITS(MU_FLAGS2_BW_FROM_SIG_A_BW_KNOWN),
-	};
-	struct ieee80211_radiotap_he_mu *he_mu = NULL;
-
-	status->flag |= RX_FLAG_RADIOTAP_HE_MU;
-
-	he_mu = skb_push(skb, sizeof(mu_known));
-	memcpy(he_mu, &mu_known, sizeof(mu_known));
-
-#define MU_PREP(f, v)	le16_encode_bits(v, IEEE80211_RADIOTAP_HE_MU_##f)
-
-	he_mu->flags1 |= MU_PREP(FLAGS1_SIG_B_MCS, status->rate_idx);
-	if (status->he_dcm)
-		he_mu->flags1 |= MU_PREP(FLAGS1_SIG_B_DCM, status->he_dcm);
-
-	he_mu->flags2 |= MU_PREP(FLAGS2_BW_FROM_SIG_A_BW, status->bw) |
-			 MU_PREP(FLAGS2_SIG_B_SYMS_USERS,
-				 le32_get_bits(rxv[4], MT_CRXV_HE_NUM_USER));
-
-	he_mu->ru_ch1[0] = le32_get_bits(rxv[16], MT_CRXV_HE_RU0) & 0xff;
-
-	if (status->bw >= RATE_INFO_BW_40) {
-		he_mu->flags1 |= HE_BITS(MU_FLAGS1_CH2_RU_KNOWN);
-		he_mu->ru_ch2[0] = le32_get_bits(rxv[16], MT_CRXV_HE_RU1) & 0xff;
-	}
-
-	if (status->bw >= RATE_INFO_BW_80) {
-		u32 ru_h, ru_l;
-
-		he_mu->ru_ch1[1] = le32_get_bits(rxv[16], MT_CRXV_HE_RU2) & 0xff;
-
-		ru_l = le32_get_bits(rxv[16], MT_CRXV_HE_RU3_L);
-		ru_h = le32_get_bits(rxv[17], MT_CRXV_HE_RU3_H) & 0x7;
-		he_mu->ru_ch2[1] = (u8)(ru_l | ru_h << 4);
-	}
-}
-
-static void
-mt7996_mac_decode_he_radiotap(struct sk_buff *skb, __le32 *rxv, u8 mode)
-{
-	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
-	static const struct ieee80211_radiotap_he known = {
-		.data1 = HE_BITS(DATA1_DATA_MCS_KNOWN) |
-			 HE_BITS(DATA1_DATA_DCM_KNOWN) |
-			 HE_BITS(DATA1_STBC_KNOWN) |
-			 HE_BITS(DATA1_CODING_KNOWN) |
-			 HE_BITS(DATA1_LDPC_XSYMSEG_KNOWN) |
-			 HE_BITS(DATA1_DOPPLER_KNOWN) |
-			 HE_BITS(DATA1_SPTL_REUSE_KNOWN) |
-			 HE_BITS(DATA1_BSS_COLOR_KNOWN),
-		.data2 = HE_BITS(DATA2_GI_KNOWN) |
-			 HE_BITS(DATA2_TXBF_KNOWN) |
-			 HE_BITS(DATA2_PE_DISAMBIG_KNOWN) |
-			 HE_BITS(DATA2_TXOP_KNOWN),
-	};
-	struct ieee80211_radiotap_he *he = NULL;
-	u32 ltf_size = le32_get_bits(rxv[4], MT_CRXV_HE_LTF_SIZE) + 1;
-
-	status->flag |= RX_FLAG_RADIOTAP_HE;
-
-	he = skb_push(skb, sizeof(known));
-	memcpy(he, &known, sizeof(known));
-
-	he->data3 = HE_PREP(DATA3_BSS_COLOR, BSS_COLOR, rxv[9]) |
-		    HE_PREP(DATA3_LDPC_XSYMSEG, LDPC_EXT_SYM, rxv[4]);
-	he->data4 = HE_PREP(DATA4_SU_MU_SPTL_REUSE, SR_MASK, rxv[13]);
-	he->data5 = HE_PREP(DATA5_PE_DISAMBIG, PE_DISAMBIG, rxv[5]) |
-		    le16_encode_bits(ltf_size,
-				     IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE);
-	if (le32_to_cpu(rxv[0]) & MT_PRXV_TXBF)
-		he->data5 |= HE_BITS(DATA5_TXBF);
-	he->data6 = HE_PREP(DATA6_TXOP, TXOP_DUR, rxv[9]) |
-		    HE_PREP(DATA6_DOPPLER, DOPPLER, rxv[9]);
-
-	switch (mode) {
-	case MT_PHY_TYPE_HE_SU:
-		he->data1 |= HE_BITS(DATA1_FORMAT_SU) |
-			     HE_BITS(DATA1_UL_DL_KNOWN) |
-			     HE_BITS(DATA1_BEAM_CHANGE_KNOWN) |
-			     HE_BITS(DATA1_BW_RU_ALLOC_KNOWN);
-
-		he->data3 |= HE_PREP(DATA3_BEAM_CHANGE, BEAM_CHNG, rxv[8]) |
-			     HE_PREP(DATA3_UL_DL, UPLINK, rxv[5]);
-		break;
-	case MT_PHY_TYPE_HE_EXT_SU:
-		he->data1 |= HE_BITS(DATA1_FORMAT_EXT_SU) |
-			     HE_BITS(DATA1_UL_DL_KNOWN) |
-			     HE_BITS(DATA1_BW_RU_ALLOC_KNOWN);
-
-		he->data3 |= HE_PREP(DATA3_UL_DL, UPLINK, rxv[5]);
-		break;
-	case MT_PHY_TYPE_HE_MU:
-		he->data1 |= HE_BITS(DATA1_FORMAT_MU) |
-			     HE_BITS(DATA1_UL_DL_KNOWN);
-
-		he->data3 |= HE_PREP(DATA3_UL_DL, UPLINK, rxv[5]);
-		he->data4 |= HE_PREP(DATA4_MU_STA_ID, MU_AID, rxv[8]);
-
-		mt7996_mac_decode_he_radiotap_ru(status, he, rxv);
-		mt7996_mac_decode_he_mu_radiotap(skb, rxv);
-		break;
-	case MT_PHY_TYPE_HE_TB:
-		he->data1 |= HE_BITS(DATA1_FORMAT_TRIG) |
-			     HE_BITS(DATA1_SPTL_REUSE2_KNOWN) |
-			     HE_BITS(DATA1_SPTL_REUSE3_KNOWN) |
-			     HE_BITS(DATA1_SPTL_REUSE4_KNOWN);
-
-		he->data4 |= HE_PREP(DATA4_TB_SPTL_REUSE1, SR_MASK, rxv[13]) |
-			     HE_PREP(DATA4_TB_SPTL_REUSE2, SR1_MASK, rxv[13]) |
-			     HE_PREP(DATA4_TB_SPTL_REUSE3, SR2_MASK, rxv[13]) |
-			     HE_PREP(DATA4_TB_SPTL_REUSE4, SR3_MASK, rxv[13]);
-
-		mt7996_mac_decode_he_radiotap_ru(status, he, rxv);
-		break;
-	default:
-		break;
-	}
-}
-
 /* The HW does not translate the mac header to 802.3 for mesh point */
 static int mt7996_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap)
 {
@@ -887,7 +709,7 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, struct sk_buff *skb)
 	}
 
 	if (rxv && mode >= MT_PHY_TYPE_HE_SU && !(status->flag & RX_FLAG_8023))
-		mt7996_mac_decode_he_radiotap(skb, rxv, mode);
+		mt76_connac3_mac_decode_he_radiotap(skb, rxv, mode);
 
 	if (!status->wcid || !ieee80211_is_data_qos(fc))
 		return 0;
-- 
GitLab


From f0ea27e7bfe1c34e1f451a63eb68faa1d4c3a86d Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@isovalent.com>
Date: Thu, 20 Jul 2023 17:30:05 +0200
Subject: [PATCH 0435/1806] udp: re-score reuseport groups when connected
 sockets are present

Contrary to TCP, UDP reuseport groups can contain TCP_ESTABLISHED
sockets. To support these properly we remember whether a group has
a connected socket and skip the fast reuseport early-return. In
effect we continue scoring all reuseport sockets and then choose the
one with the highest score.

The current code fails to re-calculate the score for the result of
lookup_reuseport. According to Kuniyuki Iwashima:

    1) SO_INCOMING_CPU is set
       -> selected sk might have +1 score

    2) BPF prog returns ESTABLISHED and/or SO_INCOMING_CPU sk
       -> selected sk will have more than 8

  Using the old score could trigger more lookups depending on the
  order that sockets are created.

    sk -> sk (SO_INCOMING_CPU) -> sk (ESTABLISHED)
    |     |
    `-> select the next SO_INCOMING_CPU sk
          |
          `-> select itself (We should save this lookup)

Fixes: efc6b6f6c311 ("udp: Improve load balancing for SO_REUSEPORT.")
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-1-7021b683cdae@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 net/ipv4/udp.c | 20 +++++++++++++++-----
 net/ipv6/udp.c | 19 ++++++++++++++-----
 2 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8c3ebd95f5b98..0d81339bda2f9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -451,14 +451,24 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
-			result = lookup_reuseport(net, sk, skb,
-						  saddr, sport, daddr, hnum);
+			badness = score;
+			result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
+			if (!result) {
+				result = sk;
+				continue;
+			}
+
 			/* Fall back to scoring if group has connections */
-			if (result && !reuseport_has_conns(sk))
+			if (!reuseport_has_conns(sk))
 				return result;
 
-			result = result ? : sk;
-			badness = score;
+			/* Reuseport logic returned an error, keep original score. */
+			if (IS_ERR(result))
+				continue;
+
+			badness = compute_score(result, net, saddr, sport,
+						daddr, hnum, dif, sdif);
+
 		}
 	}
 	return result;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 95c75d8f73d51..556d74a7d7ab1 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -194,14 +194,23 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
-			result = lookup_reuseport(net, sk, skb,
-						  saddr, sport, daddr, hnum);
+			badness = score;
+			result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
+			if (!result) {
+				result = sk;
+				continue;
+			}
+
 			/* Fall back to scoring if group has connections */
-			if (result && !reuseport_has_conns(sk))
+			if (!reuseport_has_conns(sk))
 				return result;
 
-			result = result ? : sk;
-			badness = score;
+			/* Reuseport logic returned an error, keep original score. */
+			if (IS_ERR(result))
+				continue;
+
+			badness = compute_score(sk, net, saddr, sport,
+						daddr, hnum, dif, sdif);
 		}
 	}
 	return result;
-- 
GitLab


From 67312adc96b5a585970d03b62412847afe2c6b01 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@isovalent.com>
Date: Thu, 20 Jul 2023 17:30:06 +0200
Subject: [PATCH 0436/1806] bpf: reject unhashed sockets in bpf_sk_assign

The semantics for bpf_sk_assign are as follows:

    sk = some_lookup_func()
    bpf_sk_assign(skb, sk)
    bpf_sk_release(sk)

That is, the sk is not consumed by bpf_sk_assign. The function
therefore needs to make sure that sk lives long enough to be
consumed from __inet_lookup_skb. The path through the stack for a
TCPv4 packet is roughly:

  netif_receive_skb_core: takes RCU read lock
    __netif_receive_skb_core:
      sch_handle_ingress:
        tcf_classify:
          bpf_sk_assign()
      deliver_ptype_list_skb:
        deliver_skb:
          ip_packet_type->func == ip_rcv:
            ip_rcv_core:
            ip_rcv_finish_core:
              dst_input:
                ip_local_deliver:
                  ip_local_deliver_finish:
                    ip_protocol_deliver_rcu:
                      tcp_v4_rcv:
                        __inet_lookup_skb:
                          skb_steal_sock

The existing helper takes advantage of the fact that everything
happens in the same RCU critical section: for sockets with
SOCK_RCU_FREE set bpf_sk_assign never takes a reference.
skb_steal_sock then checks SOCK_RCU_FREE again and does sock_put
if necessary.

This approach assumes that SOCK_RCU_FREE is never set on a sk
between bpf_sk_assign and skb_steal_sock, but this invariant is
violated by unhashed UDP sockets. A new UDP socket is created
in TCP_CLOSE state but without SOCK_RCU_FREE set. That flag is only
added in udp_lib_get_port() which happens when a socket is bound.

When bpf_sk_assign was added it wasn't possible to access unhashed
UDP sockets from BPF, so this wasn't a problem. This changed
in commit 0c48eefae712 ("sock_map: Lift socket state restriction
for datagram sockets"), but the helper wasn't adjusted accordingly.
The following sequence of events will therefore lead to a refcount
leak:

1. Add socket(AF_INET, SOCK_DGRAM) to a sockmap.
2. Pull socket out of sockmap and bpf_sk_assign it. Since
   SOCK_RCU_FREE is not set we increment the refcount.
3. bind() or connect() the socket, setting SOCK_RCU_FREE.
4. skb_steal_sock will now set refcounted = false due to
   SOCK_RCU_FREE.
5. tcp_v4_rcv() skips sock_put().

Fix the problem by rejecting unhashed sockets in bpf_sk_assign().
This matches the behaviour of __inet_lookup_skb which is ultimately
the goal of bpf_sk_assign().

Fixes: cf7fbe660f2d ("bpf: Add socket assign support")
Cc: Joe Stringer <joe@cilium.io>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-2-7021b683cdae@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 net/core/filter.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 797e8f0396964..b5b51ef48c5f8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7353,6 +7353,8 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
 		return -ENETUNREACH;
 	if (unlikely(sk_fullsock(sk) && sk->sk_reuseport))
 		return -ESOCKTNOSUPPORT;
+	if (sk_unhashed(sk))
+		return -EOPNOTSUPP;
 	if (sk_is_refcounted(sk) &&
 	    unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
 		return -ENOENT;
-- 
GitLab


From ce796e60b3b196b61fcc565df195443cbb846ef0 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@isovalent.com>
Date: Thu, 20 Jul 2023 17:30:07 +0200
Subject: [PATCH 0437/1806] net: export inet_lookup_reuseport and
 inet6_lookup_reuseport

Rename the existing reuseport helpers for IPv4 and IPv6 so that they
can be invoked in the follow up commit. Export them so that building
DCCP and IPv6 as a module works.

No change in functionality.

Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-3-7021b683cdae@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/net/inet6_hashtables.h |  7 +++++++
 include/net/inet_hashtables.h  |  5 +++++
 net/ipv4/inet_hashtables.c     | 15 ++++++++-------
 net/ipv6/inet6_hashtables.c    | 19 ++++++++++---------
 4 files changed, 30 insertions(+), 16 deletions(-)

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 56f1286583d3c..032ddab48f8f8 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -48,6 +48,13 @@ struct sock *__inet6_lookup_established(struct net *net,
 					const u16 hnum, const int dif,
 					const int sdif);
 
+struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
+				    struct sk_buff *skb, int doff,
+				    const struct in6_addr *saddr,
+				    __be16 sport,
+				    const struct in6_addr *daddr,
+				    unsigned short hnum);
+
 struct sock *inet6_lookup_listener(struct net *net,
 				   struct inet_hashinfo *hashinfo,
 				   struct sk_buff *skb, int doff,
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 99bd823e97f62..8734f3488f5d0 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -379,6 +379,11 @@ struct sock *__inet_lookup_established(struct net *net,
 				       const __be32 daddr, const u16 hnum,
 				       const int dif, const int sdif);
 
+struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
+				   struct sk_buff *skb, int doff,
+				   __be32 saddr, __be16 sport,
+				   __be32 daddr, unsigned short hnum);
+
 static inline struct sock *
 	inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
 				const __be32 saddr, const __be16 sport,
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 0819d6001b9ab..ecb838460629e 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -332,10 +332,10 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
-					    struct sk_buff *skb, int doff,
-					    __be32 saddr, __be16 sport,
-					    __be32 daddr, unsigned short hnum)
+struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
+				   struct sk_buff *skb, int doff,
+				   __be32 saddr, __be16 sport,
+				   __be32 daddr, unsigned short hnum)
 {
 	struct sock *reuse_sk = NULL;
 	u32 phash;
@@ -346,6 +346,7 @@ static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
 	}
 	return reuse_sk;
 }
+EXPORT_SYMBOL_GPL(inet_lookup_reuseport);
 
 /*
  * Here are some nice properties to exploit here. The BSD API
@@ -369,8 +370,8 @@ static struct sock *inet_lhash2_lookup(struct net *net,
 	sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
 		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
-			result = lookup_reuseport(net, sk, skb, doff,
-						  saddr, sport, daddr, hnum);
+			result = inet_lookup_reuseport(net, sk, skb, doff,
+						       saddr, sport, daddr, hnum);
 			if (result)
 				return result;
 
@@ -399,7 +400,7 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net,
 	if (no_reuseport || IS_ERR_OR_NULL(sk))
 		return sk;
 
-	reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+	reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
 	if (reuse_sk)
 		sk = reuse_sk;
 	return sk;
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b64b49012655e..b7c56867314ed 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -111,12 +111,12 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
-					    struct sk_buff *skb, int doff,
-					    const struct in6_addr *saddr,
-					    __be16 sport,
-					    const struct in6_addr *daddr,
-					    unsigned short hnum)
+struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
+				    struct sk_buff *skb, int doff,
+				    const struct in6_addr *saddr,
+				    __be16 sport,
+				    const struct in6_addr *daddr,
+				    unsigned short hnum)
 {
 	struct sock *reuse_sk = NULL;
 	u32 phash;
@@ -127,6 +127,7 @@ static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
 	}
 	return reuse_sk;
 }
+EXPORT_SYMBOL_GPL(inet6_lookup_reuseport);
 
 /* called with rcu_read_lock() */
 static struct sock *inet6_lhash2_lookup(struct net *net,
@@ -143,8 +144,8 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 	sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
 		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
-			result = lookup_reuseport(net, sk, skb, doff,
-						  saddr, sport, daddr, hnum);
+			result = inet6_lookup_reuseport(net, sk, skb, doff,
+							saddr, sport, daddr, hnum);
 			if (result)
 				return result;
 
@@ -175,7 +176,7 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net,
 	if (no_reuseport || IS_ERR_OR_NULL(sk))
 		return sk;
 
-	reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+	reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
 	if (reuse_sk)
 		sk = reuse_sk;
 	return sk;
-- 
GitLab


From 0f495f7617229772403e683033abc473f0f0553c Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@isovalent.com>
Date: Thu, 20 Jul 2023 17:30:08 +0200
Subject: [PATCH 0438/1806] net: remove duplicate reuseport_lookup functions

There are currently four copies of reuseport_lookup: one each for
(TCP, UDP)x(IPv4, IPv6). This forces us to duplicate all callers of
those functions as well. This is already the case for sk_lookup
helpers (inet,inet6,udp4,udp6)_lookup_run_bpf.

There are two differences between the reuseport_lookup helpers:

1. They call different hash functions depending on protocol
2. UDP reuseport_lookup checks that sk_state != TCP_ESTABLISHED

Move the check for sk_state into the caller and use the INDIRECT_CALL
infrastructure to cut down the helpers to one per IP version.

Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-4-7021b683cdae@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/net/inet6_hashtables.h | 11 ++++++++-
 include/net/inet_hashtables.h  | 15 ++++++++-----
 net/ipv4/inet_hashtables.c     | 20 +++++++++++------
 net/ipv4/udp.c                 | 34 +++++++++++-----------------
 net/ipv6/inet6_hashtables.c    | 14 ++++++++----
 net/ipv6/udp.c                 | 41 +++++++++++++---------------------
 6 files changed, 72 insertions(+), 63 deletions(-)

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 032ddab48f8f8..f89320b6fee31 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -48,12 +48,21 @@ struct sock *__inet6_lookup_established(struct net *net,
 					const u16 hnum, const int dif,
 					const int sdif);
 
+typedef u32 (inet6_ehashfn_t)(const struct net *net,
+			       const struct in6_addr *laddr, const u16 lport,
+			       const struct in6_addr *faddr, const __be16 fport);
+
+inet6_ehashfn_t inet6_ehashfn;
+
+INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn);
+
 struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
 				    struct sk_buff *skb, int doff,
 				    const struct in6_addr *saddr,
 				    __be16 sport,
 				    const struct in6_addr *daddr,
-				    unsigned short hnum);
+				    unsigned short hnum,
+				    inet6_ehashfn_t *ehashfn);
 
 struct sock *inet6_lookup_listener(struct net *net,
 				   struct inet_hashinfo *hashinfo,
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 8734f3488f5d0..ddfa2e67fdb51 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -379,10 +379,19 @@ struct sock *__inet_lookup_established(struct net *net,
 				       const __be32 daddr, const u16 hnum,
 				       const int dif, const int sdif);
 
+typedef u32 (inet_ehashfn_t)(const struct net *net,
+			      const __be32 laddr, const __u16 lport,
+			      const __be32 faddr, const __be16 fport);
+
+inet_ehashfn_t inet_ehashfn;
+
+INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn);
+
 struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
 				   struct sk_buff *skb, int doff,
 				   __be32 saddr, __be16 sport,
-				   __be32 daddr, unsigned short hnum);
+				   __be32 daddr, unsigned short hnum,
+				   inet_ehashfn_t *ehashfn);
 
 static inline struct sock *
 	inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
@@ -453,10 +462,6 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 			     refcounted);
 }
 
-u32 inet6_ehashfn(const struct net *net,
-		  const struct in6_addr *laddr, const u16 lport,
-		  const struct in6_addr *faddr, const __be16 fport);
-
 static inline void sk_daddr_set(struct sock *sk, __be32 addr)
 {
 	sk->sk_daddr = addr; /* alias of inet_daddr */
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index ecb838460629e..0a7a726464d9d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -28,9 +28,9 @@
 #include <net/tcp.h>
 #include <net/sock_reuseport.h>
 
-static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
-			const __u16 lport, const __be32 faddr,
-			const __be16 fport)
+u32 inet_ehashfn(const struct net *net, const __be32 laddr,
+		 const __u16 lport, const __be32 faddr,
+		 const __be16 fport)
 {
 	static u32 inet_ehash_secret __read_mostly;
 
@@ -39,6 +39,7 @@ static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
 	return __inet_ehashfn(laddr, lport, faddr, fport,
 			      inet_ehash_secret + net_hash_mix(net));
 }
+EXPORT_SYMBOL_GPL(inet_ehashfn);
 
 /* This function handles inet_sock, but also timewait and request sockets
  * for IPv4/IPv6.
@@ -332,16 +333,20 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
+INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn);
+
 struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
 				   struct sk_buff *skb, int doff,
 				   __be32 saddr, __be16 sport,
-				   __be32 daddr, unsigned short hnum)
+				   __be32 daddr, unsigned short hnum,
+				   inet_ehashfn_t *ehashfn)
 {
 	struct sock *reuse_sk = NULL;
 	u32 phash;
 
 	if (sk->sk_reuseport) {
-		phash = inet_ehashfn(net, daddr, hnum, saddr, sport);
+		phash = INDIRECT_CALL_2(ehashfn, udp_ehashfn, inet_ehashfn,
+					net, daddr, hnum, saddr, sport);
 		reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
 	}
 	return reuse_sk;
@@ -371,7 +376,7 @@ static struct sock *inet_lhash2_lookup(struct net *net,
 		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
 			result = inet_lookup_reuseport(net, sk, skb, doff,
-						       saddr, sport, daddr, hnum);
+						       saddr, sport, daddr, hnum, inet_ehashfn);
 			if (result)
 				return result;
 
@@ -400,7 +405,8 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net,
 	if (no_reuseport || IS_ERR_OR_NULL(sk))
 		return sk;
 
-	reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+	reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum,
+					 inet_ehashfn);
 	if (reuse_sk)
 		sk = reuse_sk;
 	return sk;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0d81339bda2f9..3abe8a1520daa 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -406,9 +406,9 @@ static int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
-		       const __u16 lport, const __be32 faddr,
-		       const __be16 fport)
+INDIRECT_CALLABLE_SCOPE
+u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport,
+		const __be32 faddr, const __be16 fport)
 {
 	static u32 udp_ehash_secret __read_mostly;
 
@@ -418,22 +418,6 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
 			      udp_ehash_secret + net_hash_mix(net));
 }
 
-static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
-				     struct sk_buff *skb,
-				     __be32 saddr, __be16 sport,
-				     __be32 daddr, unsigned short hnum)
-{
-	struct sock *reuse_sk = NULL;
-	u32 hash;
-
-	if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
-		hash = udp_ehashfn(net, daddr, hnum, saddr, sport);
-		reuse_sk = reuseport_select_sock(sk, hash, skb,
-						 sizeof(struct udphdr));
-	}
-	return reuse_sk;
-}
-
 /* called with rcu_read_lock() */
 static struct sock *udp4_lib_lookup2(struct net *net,
 				     __be32 saddr, __be16 sport,
@@ -452,7 +436,14 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
 			badness = score;
-			result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
+
+			if (sk->sk_state == TCP_ESTABLISHED) {
+				result = sk;
+				continue;
+			}
+
+			result = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+						       saddr, sport, daddr, hnum, udp_ehashfn);
 			if (!result) {
 				result = sk;
 				continue;
@@ -491,7 +482,8 @@ static struct sock *udp4_lookup_run_bpf(struct net *net,
 	if (no_reuseport || IS_ERR_OR_NULL(sk))
 		return sk;
 
-	reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
+	reuse_sk = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+					 saddr, sport, daddr, hnum, udp_ehashfn);
 	if (reuse_sk)
 		sk = reuse_sk;
 	return sk;
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b7c56867314ed..3616225c89ef6 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -39,6 +39,7 @@ u32 inet6_ehashfn(const struct net *net,
 	return __inet6_ehashfn(lhash, lport, fhash, fport,
 			       inet6_ehash_secret + net_hash_mix(net));
 }
+EXPORT_SYMBOL_GPL(inet6_ehashfn);
 
 /*
  * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
@@ -111,18 +112,22 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
+INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn);
+
 struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
 				    struct sk_buff *skb, int doff,
 				    const struct in6_addr *saddr,
 				    __be16 sport,
 				    const struct in6_addr *daddr,
-				    unsigned short hnum)
+				    unsigned short hnum,
+				    inet6_ehashfn_t *ehashfn)
 {
 	struct sock *reuse_sk = NULL;
 	u32 phash;
 
 	if (sk->sk_reuseport) {
-		phash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
+		phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn,
+					   net, daddr, hnum, saddr, sport);
 		reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
 	}
 	return reuse_sk;
@@ -145,7 +150,7 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
 			result = inet6_lookup_reuseport(net, sk, skb, doff,
-							saddr, sport, daddr, hnum);
+							saddr, sport, daddr, hnum, inet6_ehashfn);
 			if (result)
 				return result;
 
@@ -176,7 +181,8 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net,
 	if (no_reuseport || IS_ERR_OR_NULL(sk))
 		return sk;
 
-	reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+	reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+					  saddr, sport, daddr, hnum, inet6_ehashfn);
 	if (reuse_sk)
 		sk = reuse_sk;
 	return sk;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 556d74a7d7ab1..918ca1771710d 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -71,11 +71,12 @@ int udpv6_init_sock(struct sock *sk)
 	return 0;
 }
 
-static u32 udp6_ehashfn(const struct net *net,
-			const struct in6_addr *laddr,
-			const u16 lport,
-			const struct in6_addr *faddr,
-			const __be16 fport)
+INDIRECT_CALLABLE_SCOPE
+u32 udp6_ehashfn(const struct net *net,
+		 const struct in6_addr *laddr,
+		 const u16 lport,
+		 const struct in6_addr *faddr,
+		 const __be16 fport)
 {
 	static u32 udp6_ehash_secret __read_mostly;
 	static u32 udp_ipv6_hash_secret __read_mostly;
@@ -160,24 +161,6 @@ static int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
-				     struct sk_buff *skb,
-				     const struct in6_addr *saddr,
-				     __be16 sport,
-				     const struct in6_addr *daddr,
-				     unsigned int hnum)
-{
-	struct sock *reuse_sk = NULL;
-	u32 hash;
-
-	if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
-		hash = udp6_ehashfn(net, daddr, hnum, saddr, sport);
-		reuse_sk = reuseport_select_sock(sk, hash, skb,
-						 sizeof(struct udphdr));
-	}
-	return reuse_sk;
-}
-
 /* called with rcu_read_lock() */
 static struct sock *udp6_lib_lookup2(struct net *net,
 		const struct in6_addr *saddr, __be16 sport,
@@ -195,7 +178,14 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
 			badness = score;
-			result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
+
+			if (sk->sk_state == TCP_ESTABLISHED) {
+				result = sk;
+				continue;
+			}
+
+			result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+							saddr, sport, daddr, hnum, udp6_ehashfn);
 			if (!result) {
 				result = sk;
 				continue;
@@ -235,7 +225,8 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net,
 	if (no_reuseport || IS_ERR_OR_NULL(sk))
 		return sk;
 
-	reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
+	reuse_sk = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+					  saddr, sport, daddr, hnum, udp6_ehashfn);
 	if (reuse_sk)
 		sk = reuse_sk;
 	return sk;
-- 
GitLab


From 2a61776366bd17db9ac8c93ec32b8e0ae6b11cf2 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@isovalent.com>
Date: Thu, 20 Jul 2023 17:30:09 +0200
Subject: [PATCH 0439/1806] net: document inet[6]_lookup_reuseport sk_state
 requirements

The current implementation was extracted from inet[6]_lhash2_lookup
in commit 80b373f74f9e ("inet: Extract helper for selecting socket
from reuseport group") and commit 5df6531292b5 ("inet6: Extract helper
for selecting socket from reuseport group"). In the original context,
sk is always in TCP_LISTEN state and so did not have a separate check.

Add documentation that specifies which sk_state are valid to pass to
the function.

Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-5-7021b683cdae@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 net/ipv4/inet_hashtables.c  | 15 +++++++++++++++
 net/ipv6/inet6_hashtables.c | 15 +++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 0a7a726464d9d..e9cec4807694b 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -335,6 +335,21 @@ static inline int compute_score(struct sock *sk, struct net *net,
 
 INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn);
 
+/**
+ * inet_lookup_reuseport() - execute reuseport logic on AF_INET socket if necessary.
+ * @net: network namespace.
+ * @sk: AF_INET socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP.
+ * @skb: context for a potential SK_REUSEPORT program.
+ * @doff: header offset.
+ * @saddr: source address.
+ * @sport: source port.
+ * @daddr: destination address.
+ * @hnum: destination port in host byte order.
+ * @ehashfn: hash function used to generate the fallback hash.
+ *
+ * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
+ *         the selected sock or an error.
+ */
 struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
 				   struct sk_buff *skb, int doff,
 				   __be32 saddr, __be16 sport,
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 3616225c89ef6..f76dbbb293329 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -114,6 +114,21 @@ static inline int compute_score(struct sock *sk, struct net *net,
 
 INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn);
 
+/**
+ * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary.
+ * @net: network namespace.
+ * @sk: AF_INET6 socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP.
+ * @skb: context for a potential SK_REUSEPORT program.
+ * @doff: header offset.
+ * @saddr: source address.
+ * @sport: source port.
+ * @daddr: destination address.
+ * @hnum: destination port in host byte order.
+ * @ehashfn: hash function used to generate the fallback hash.
+ *
+ * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
+ *         the selected sock or an error.
+ */
 struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
 				    struct sk_buff *skb, int doff,
 				    const struct in6_addr *saddr,
-- 
GitLab


From 6c886db2e78ce1dee163d07240467770a235f33e Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@isovalent.com>
Date: Thu, 20 Jul 2023 17:30:10 +0200
Subject: [PATCH 0440/1806] net: remove duplicate sk_lookup helpers

Now that inet[6]_lookup_reuseport are parameterised on the ehashfn
we can remove two sk_lookup helpers.

Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-6-7021b683cdae@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/net/inet6_hashtables.h |  9 +++++++++
 include/net/inet_hashtables.h  |  7 +++++++
 net/ipv4/inet_hashtables.c     | 26 +++++++++++++-------------
 net/ipv4/udp.c                 | 32 +++++---------------------------
 net/ipv6/inet6_hashtables.c    | 31 ++++++++++++++++---------------
 net/ipv6/udp.c                 | 34 +++++-----------------------------
 6 files changed, 55 insertions(+), 84 deletions(-)

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index f89320b6fee31..a6722d6ef80fa 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -73,6 +73,15 @@ struct sock *inet6_lookup_listener(struct net *net,
 				   const unsigned short hnum,
 				   const int dif, const int sdif);
 
+struct sock *inet6_lookup_run_sk_lookup(struct net *net,
+					int protocol,
+					struct sk_buff *skb, int doff,
+					const struct in6_addr *saddr,
+					const __be16 sport,
+					const struct in6_addr *daddr,
+					const u16 hnum, const int dif,
+					inet6_ehashfn_t *ehashfn);
+
 static inline struct sock *__inet6_lookup(struct net *net,
 					  struct inet_hashinfo *hashinfo,
 					  struct sk_buff *skb, int doff,
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index ddfa2e67fdb51..c0532cc7587f7 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -393,6 +393,13 @@ struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
 				   __be32 daddr, unsigned short hnum,
 				   inet_ehashfn_t *ehashfn);
 
+struct sock *inet_lookup_run_sk_lookup(struct net *net,
+				       int protocol,
+				       struct sk_buff *skb, int doff,
+				       __be32 saddr, __be16 sport,
+				       __be32 daddr, u16 hnum, const int dif,
+				       inet_ehashfn_t *ehashfn);
+
 static inline struct sock *
 	inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
 				const __be32 saddr, const __be16 sport,
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index e9cec4807694b..6a872b8fb0d35 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -403,25 +403,23 @@ static struct sock *inet_lhash2_lookup(struct net *net,
 	return result;
 }
 
-static inline struct sock *inet_lookup_run_bpf(struct net *net,
-					       struct inet_hashinfo *hashinfo,
-					       struct sk_buff *skb, int doff,
-					       __be32 saddr, __be16 sport,
-					       __be32 daddr, u16 hnum, const int dif)
+struct sock *inet_lookup_run_sk_lookup(struct net *net,
+				       int protocol,
+				       struct sk_buff *skb, int doff,
+				       __be32 saddr, __be16 sport,
+				       __be32 daddr, u16 hnum, const int dif,
+				       inet_ehashfn_t *ehashfn)
 {
 	struct sock *sk, *reuse_sk;
 	bool no_reuseport;
 
-	if (hashinfo != net->ipv4.tcp_death_row.hashinfo)
-		return NULL; /* only TCP is supported */
-
-	no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport,
+	no_reuseport = bpf_sk_lookup_run_v4(net, protocol, saddr, sport,
 					    daddr, hnum, dif, &sk);
 	if (no_reuseport || IS_ERR_OR_NULL(sk))
 		return sk;
 
 	reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum,
-					 inet_ehashfn);
+					 ehashfn);
 	if (reuse_sk)
 		sk = reuse_sk;
 	return sk;
@@ -439,9 +437,11 @@ struct sock *__inet_lookup_listener(struct net *net,
 	unsigned int hash2;
 
 	/* Lookup redirect from BPF */
-	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
-		result = inet_lookup_run_bpf(net, hashinfo, skb, doff,
-					     saddr, sport, daddr, hnum, dif);
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+	    hashinfo == net->ipv4.tcp_death_row.hashinfo) {
+		result = inet_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
+						   saddr, sport, daddr, hnum, dif,
+						   inet_ehashfn);
 		if (result)
 			goto done;
 	}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3abe8a1520daa..456fb6ee6ee8e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -465,30 +465,6 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 	return result;
 }
 
-static struct sock *udp4_lookup_run_bpf(struct net *net,
-					struct udp_table *udptable,
-					struct sk_buff *skb,
-					__be32 saddr, __be16 sport,
-					__be32 daddr, u16 hnum, const int dif)
-{
-	struct sock *sk, *reuse_sk;
-	bool no_reuseport;
-
-	if (udptable != net->ipv4.udp_table)
-		return NULL; /* only UDP is supported */
-
-	no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport,
-					    daddr, hnum, dif, &sk);
-	if (no_reuseport || IS_ERR_OR_NULL(sk))
-		return sk;
-
-	reuse_sk = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
-					 saddr, sport, daddr, hnum, udp_ehashfn);
-	if (reuse_sk)
-		sk = reuse_sk;
-	return sk;
-}
-
 /* UDP is nearly always wildcards out the wazoo, it makes no sense to try
  * harder than this. -DaveM
  */
@@ -513,9 +489,11 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 		goto done;
 
 	/* Lookup redirect from BPF */
-	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
-		sk = udp4_lookup_run_bpf(net, udptable, skb,
-					 saddr, sport, daddr, hnum, dif);
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+	    udptable == net->ipv4.udp_table) {
+		sk = inet_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
+					       saddr, sport, daddr, hnum, dif,
+					       udp_ehashfn);
 		if (sk) {
 			result = sk;
 			goto done;
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index f76dbbb293329..7c9700c7c9c87 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -177,31 +177,30 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 	return result;
 }
 
-static inline struct sock *inet6_lookup_run_bpf(struct net *net,
-						struct inet_hashinfo *hashinfo,
-						struct sk_buff *skb, int doff,
-						const struct in6_addr *saddr,
-						const __be16 sport,
-						const struct in6_addr *daddr,
-						const u16 hnum, const int dif)
+struct sock *inet6_lookup_run_sk_lookup(struct net *net,
+					int protocol,
+					struct sk_buff *skb, int doff,
+					const struct in6_addr *saddr,
+					const __be16 sport,
+					const struct in6_addr *daddr,
+					const u16 hnum, const int dif,
+					inet6_ehashfn_t *ehashfn)
 {
 	struct sock *sk, *reuse_sk;
 	bool no_reuseport;
 
-	if (hashinfo != net->ipv4.tcp_death_row.hashinfo)
-		return NULL; /* only TCP is supported */
-
-	no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, saddr, sport,
+	no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport,
 					    daddr, hnum, dif, &sk);
 	if (no_reuseport || IS_ERR_OR_NULL(sk))
 		return sk;
 
 	reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
-					  saddr, sport, daddr, hnum, inet6_ehashfn);
+					  saddr, sport, daddr, hnum, ehashfn);
 	if (reuse_sk)
 		sk = reuse_sk;
 	return sk;
 }
+EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup);
 
 struct sock *inet6_lookup_listener(struct net *net,
 		struct inet_hashinfo *hashinfo,
@@ -215,9 +214,11 @@ struct sock *inet6_lookup_listener(struct net *net,
 	unsigned int hash2;
 
 	/* Lookup redirect from BPF */
-	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
-		result = inet6_lookup_run_bpf(net, hashinfo, skb, doff,
-					      saddr, sport, daddr, hnum, dif);
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+	    hashinfo == net->ipv4.tcp_death_row.hashinfo) {
+		result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
+						    saddr, sport, daddr, hnum, dif,
+						    inet6_ehashfn);
 		if (result)
 			goto done;
 	}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 918ca1771710d..4b8974a8c7a3b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -206,32 +206,6 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 	return result;
 }
 
-static inline struct sock *udp6_lookup_run_bpf(struct net *net,
-					       struct udp_table *udptable,
-					       struct sk_buff *skb,
-					       const struct in6_addr *saddr,
-					       __be16 sport,
-					       const struct in6_addr *daddr,
-					       u16 hnum, const int dif)
-{
-	struct sock *sk, *reuse_sk;
-	bool no_reuseport;
-
-	if (udptable != net->ipv4.udp_table)
-		return NULL; /* only UDP is supported */
-
-	no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport,
-					    daddr, hnum, dif, &sk);
-	if (no_reuseport || IS_ERR_OR_NULL(sk))
-		return sk;
-
-	reuse_sk = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
-					  saddr, sport, daddr, hnum, udp6_ehashfn);
-	if (reuse_sk)
-		sk = reuse_sk;
-	return sk;
-}
-
 /* rcu_read_lock() must be held */
 struct sock *__udp6_lib_lookup(struct net *net,
 			       const struct in6_addr *saddr, __be16 sport,
@@ -256,9 +230,11 @@ struct sock *__udp6_lib_lookup(struct net *net,
 		goto done;
 
 	/* Lookup redirect from BPF */
-	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
-		sk = udp6_lookup_run_bpf(net, udptable, skb,
-					 saddr, sport, daddr, hnum, dif);
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+	    udptable == net->ipv4.udp_table) {
+		sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
+						saddr, sport, daddr, hnum, dif,
+						udp6_ehashfn);
 		if (sk) {
 			result = sk;
 			goto done;
-- 
GitLab


From 9c02bec95954252c3c01bfbb3f7560e0b95ca955 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@isovalent.com>
Date: Thu, 20 Jul 2023 17:30:11 +0200
Subject: [PATCH 0441/1806] bpf, net: Support SO_REUSEPORT sockets with
 bpf_sk_assign

Currently the bpf_sk_assign helper in tc BPF context refuses SO_REUSEPORT
sockets. This means we can't use the helper to steer traffic to Envoy,
which configures SO_REUSEPORT on its sockets. In turn, we're blocked
from removing TPROXY from our setup.

The reason that bpf_sk_assign refuses such sockets is that the
bpf_sk_lookup helpers don't execute SK_REUSEPORT programs. Instead,
one of the reuseport sockets is selected by hash. This could cause
dispatch to the "wrong" socket:

    sk = bpf_sk_lookup_tcp(...) // select SO_REUSEPORT by hash
    bpf_sk_assign(skb, sk) // SK_REUSEPORT wasn't executed

Fixing this isn't as simple as invoking SK_REUSEPORT from the lookup
helpers unfortunately. In the tc context, L2 headers are at the start
of the skb, while SK_REUSEPORT expects L3 headers instead.

Instead, we execute the SK_REUSEPORT program when the assigned socket
is pulled out of the skb, further up the stack. This creates some
trickiness with regards to refcounting as bpf_sk_assign will put both
refcounted and RCU freed sockets in skb->sk. reuseport sockets are RCU
freed. We can infer that the sk_assigned socket is RCU freed if the
reuseport lookup succeeds, but convincing yourself of this fact isn't
straight forward. Therefore we defensively check refcounting on the
sk_assign sock even though it's probably not required in practice.

Fixes: 8e368dc72e86 ("bpf: Fix use of sk->sk_reuseport from sk_assign")
Fixes: cf7fbe660f2d ("bpf: Add socket assign support")
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Joe Stringer <joe@cilium.io>
Link: https://lore.kernel.org/bpf/CACAyw98+qycmpQzKupquhkxbvWK4OFyDuuLMBNROnfWMZxUWeA@mail.gmail.com/
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-7-7021b683cdae@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/net/inet6_hashtables.h | 56 +++++++++++++++++++++++++++++++---
 include/net/inet_hashtables.h  | 49 +++++++++++++++++++++++++++--
 include/net/sock.h             |  7 +++--
 include/uapi/linux/bpf.h       |  3 --
 net/core/filter.c              |  2 --
 net/ipv4/udp.c                 |  8 +++--
 net/ipv6/udp.c                 |  8 +++--
 tools/include/uapi/linux/bpf.h |  3 --
 8 files changed, 115 insertions(+), 21 deletions(-)

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index a6722d6ef80fa..284b5ce7205d9 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -103,6 +103,46 @@ static inline struct sock *__inet6_lookup(struct net *net,
 				     daddr, hnum, dif, sdif);
 }
 
+static inline
+struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
+			      const struct in6_addr *saddr, const __be16 sport,
+			      const struct in6_addr *daddr, const __be16 dport,
+			      bool *refcounted, inet6_ehashfn_t *ehashfn)
+{
+	struct sock *sk, *reuse_sk;
+	bool prefetched;
+
+	sk = skb_steal_sock(skb, refcounted, &prefetched);
+	if (!sk)
+		return NULL;
+
+	if (!prefetched)
+		return sk;
+
+	if (sk->sk_protocol == IPPROTO_TCP) {
+		if (sk->sk_state != TCP_LISTEN)
+			return sk;
+	} else if (sk->sk_protocol == IPPROTO_UDP) {
+		if (sk->sk_state != TCP_CLOSE)
+			return sk;
+	} else {
+		return sk;
+	}
+
+	reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+					  saddr, sport, daddr, ntohs(dport),
+					  ehashfn);
+	if (!reuse_sk)
+		return sk;
+
+	/* We've chosen a new reuseport sock which is never refcounted. This
+	 * implies that sk also isn't refcounted.
+	 */
+	WARN_ON_ONCE(*refcounted);
+
+	return reuse_sk;
+}
+
 static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 					      struct sk_buff *skb, int doff,
 					      const __be16 sport,
@@ -110,14 +150,20 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 					      int iif, int sdif,
 					      bool *refcounted)
 {
-	struct sock *sk = skb_steal_sock(skb, refcounted);
-
+	struct net *net = dev_net(skb_dst(skb)->dev);
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	struct sock *sk;
+
+	sk = inet6_steal_sock(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, dport,
+			      refcounted, inet6_ehashfn);
+	if (IS_ERR(sk))
+		return NULL;
 	if (sk)
 		return sk;
 
-	return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
-			      doff, &ipv6_hdr(skb)->saddr, sport,
-			      &ipv6_hdr(skb)->daddr, ntohs(dport),
+	return __inet6_lookup(net, hashinfo, skb,
+			      doff, &ip6h->saddr, sport,
+			      &ip6h->daddr, ntohs(dport),
 			      iif, sdif, refcounted);
 }
 
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index c0532cc7587f7..1177effabed35 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -449,6 +449,46 @@ static inline struct sock *inet_lookup(struct net *net,
 	return sk;
 }
 
+static inline
+struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff,
+			     const __be32 saddr, const __be16 sport,
+			     const __be32 daddr, const __be16 dport,
+			     bool *refcounted, inet_ehashfn_t *ehashfn)
+{
+	struct sock *sk, *reuse_sk;
+	bool prefetched;
+
+	sk = skb_steal_sock(skb, refcounted, &prefetched);
+	if (!sk)
+		return NULL;
+
+	if (!prefetched)
+		return sk;
+
+	if (sk->sk_protocol == IPPROTO_TCP) {
+		if (sk->sk_state != TCP_LISTEN)
+			return sk;
+	} else if (sk->sk_protocol == IPPROTO_UDP) {
+		if (sk->sk_state != TCP_CLOSE)
+			return sk;
+	} else {
+		return sk;
+	}
+
+	reuse_sk = inet_lookup_reuseport(net, sk, skb, doff,
+					 saddr, sport, daddr, ntohs(dport),
+					 ehashfn);
+	if (!reuse_sk)
+		return sk;
+
+	/* We've chosen a new reuseport sock which is never refcounted. This
+	 * implies that sk also isn't refcounted.
+	 */
+	WARN_ON_ONCE(*refcounted);
+
+	return reuse_sk;
+}
+
 static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 					     struct sk_buff *skb,
 					     int doff,
@@ -457,13 +497,18 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 					     const int sdif,
 					     bool *refcounted)
 {
-	struct sock *sk = skb_steal_sock(skb, refcounted);
+	struct net *net = dev_net(skb_dst(skb)->dev);
 	const struct iphdr *iph = ip_hdr(skb);
+	struct sock *sk;
 
+	sk = inet_steal_sock(net, skb, doff, iph->saddr, sport, iph->daddr, dport,
+			     refcounted, inet_ehashfn);
+	if (IS_ERR(sk))
+		return NULL;
 	if (sk)
 		return sk;
 
-	return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
+	return __inet_lookup(net, hashinfo, skb,
 			     doff, iph->saddr, sport,
 			     iph->daddr, dport, inet_iif(skb), sdif,
 			     refcounted);
diff --git a/include/net/sock.h b/include/net/sock.h
index 7ae44bf866af5..74cbfb15d2892 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2815,20 +2815,23 @@ sk_is_refcounted(struct sock *sk)
  * skb_steal_sock - steal a socket from an sk_buff
  * @skb: sk_buff to steal the socket from
  * @refcounted: is set to true if the socket is reference-counted
+ * @prefetched: is set to true if the socket was assigned from bpf
  */
 static inline struct sock *
-skb_steal_sock(struct sk_buff *skb, bool *refcounted)
+skb_steal_sock(struct sk_buff *skb, bool *refcounted, bool *prefetched)
 {
 	if (skb->sk) {
 		struct sock *sk = skb->sk;
 
 		*refcounted = true;
-		if (skb_sk_is_prefetched(skb))
+		*prefetched = skb_sk_is_prefetched(skb);
+		if (*prefetched)
 			*refcounted = sk_is_refcounted(sk);
 		skb->destructor = NULL;
 		skb->sk = NULL;
 		return sk;
 	}
+	*prefetched = false;
 	*refcounted = false;
 	return NULL;
 }
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 739c15906a65d..7fc98f4b63e94 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4198,9 +4198,6 @@ union bpf_attr {
  *		**-EOPNOTSUPP** if the operation is not supported, for example
  *		a call from outside of TC ingress.
  *
- *		**-ESOCKTNOSUPPORT** if the socket type is not supported
- *		(reuseport).
- *
  * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
  *	Description
  *		Helper is overloaded depending on BPF program type. This
diff --git a/net/core/filter.c b/net/core/filter.c
index b5b51ef48c5f8..7c37f4646c208 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7351,8 +7351,6 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
 		return -EOPNOTSUPP;
 	if (unlikely(dev_net(skb->dev) != sock_net(sk)))
 		return -ENETUNREACH;
-	if (unlikely(sk_fullsock(sk) && sk->sk_reuseport))
-		return -ESOCKTNOSUPPORT;
 	if (sk_unhashed(sk))
 		return -EOPNOTSUPP;
 	if (sk_is_refcounted(sk) &&
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 456fb6ee6ee8e..d89c4a39cf271 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2388,7 +2388,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp4_csum_init(skb, uh, proto))
 		goto csum_error;
 
-	sk = skb_steal_sock(skb, &refcounted);
+	sk = inet_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
+			     &refcounted, udp_ehashfn);
+	if (IS_ERR(sk))
+		goto no_sk;
+
 	if (sk) {
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
@@ -2409,7 +2413,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	if (sk)
 		return udp_unicast_rcv_skb(sk, skb, uh);
-
+no_sk:
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto drop;
 	nf_reset_ct(skb);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4b8974a8c7a3b..00996f0f7cfe5 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -964,7 +964,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		goto csum_error;
 
 	/* Check if the socket is already available, e.g. due to early demux */
-	sk = skb_steal_sock(skb, &refcounted);
+	sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
+			      &refcounted, udp6_ehashfn);
+	if (IS_ERR(sk))
+		goto no_sk;
+
 	if (sk) {
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
@@ -998,7 +1002,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			goto report_csum_error;
 		return udp6_unicast_rcv_skb(sk, skb, uh);
 	}
-
+no_sk:
 	reason = SKB_DROP_REASON_NO_SOCKET;
 
 	if (!uh->check)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 739c15906a65d..7fc98f4b63e94 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4198,9 +4198,6 @@ union bpf_attr {
  *		**-EOPNOTSUPP** if the operation is not supported, for example
  *		a call from outside of TC ingress.
  *
- *		**-ESOCKTNOSUPPORT** if the socket type is not supported
- *		(reuseport).
- *
  * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
  *	Description
  *		Helper is overloaded depending on BPF program type. This
-- 
GitLab


From 22408d58a42cb59b88dcec3694f477a838dd68ed Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 20 Jul 2023 17:30:12 +0200
Subject: [PATCH 0442/1806] selftests/bpf: Test that SO_REUSEPORT can be used
 with sk_assign helper

We use two programs to check that the new reuseport logic is executed
appropriately.

The first is a TC clsact program which bpf_sk_assigns
the skb to a UDP or TCP socket created by user space. Since the test
communicates via lo we see both directions of packets in the eBPF.
Traffic ingressing to the reuseport socket is identified by looking
at the destination port. For TCP, we additionally need to make sure
that we only assign the initial SYN packets towards our listening
socket. The network stack then creates a request socket which
transitions to ESTABLISHED after the 3WHS.

The second is a reuseport program which shares the fact that
it has been executed with user space. This tells us that the delayed
lookup mechanism is working.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: Lorenz Bauer <lmb@isovalent.com>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Cc: Joe Stringer <joe@cilium.io>
Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-8-7021b683cdae@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c |   3 +
 .../selftests/bpf/prog_tests/assign_reuse.c   | 199 ++++++++++++++++++
 .../selftests/bpf/progs/test_assign_reuse.c   | 142 +++++++++++++
 3 files changed, 344 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/assign_reuse.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_assign_reuse.c

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index a105c0cd008a4..8a33bcea97de8 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -423,6 +423,9 @@ fail:
 
 void close_netns(struct nstoken *token)
 {
+	if (!token)
+		return;
+
 	ASSERT_OK(setns(token->orig_netns_fd, CLONE_NEWNET), "setns");
 	close(token->orig_netns_fd);
 	free(token);
diff --git a/tools/testing/selftests/bpf/prog_tests/assign_reuse.c b/tools/testing/selftests/bpf/prog_tests/assign_reuse.c
new file mode 100644
index 0000000000000..989ee4d9785bb
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/assign_reuse.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <uapi/linux/if_link.h>
+#include <test_progs.h>
+
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+
+#include "network_helpers.h"
+#include "test_assign_reuse.skel.h"
+
+#define NS_TEST "assign_reuse"
+#define LOOPBACK 1
+#define PORT 4443
+
+static int attach_reuseport(int sock_fd, int prog_fd)
+{
+	return setsockopt(sock_fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF,
+			  &prog_fd, sizeof(prog_fd));
+}
+
+static __u64 cookie(int fd)
+{
+	__u64 cookie = 0;
+	socklen_t cookie_len = sizeof(cookie);
+	int ret;
+
+	ret = getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len);
+	ASSERT_OK(ret, "cookie");
+	ASSERT_GT(cookie, 0, "cookie_invalid");
+
+	return cookie;
+}
+
+static int echo_test_udp(int fd_sv)
+{
+	struct sockaddr_storage addr = {};
+	socklen_t len = sizeof(addr);
+	char buff[1] = {};
+	int fd_cl = -1, ret;
+
+	fd_cl = connect_to_fd(fd_sv, 100);
+	ASSERT_GT(fd_cl, 0, "create_client");
+	ASSERT_EQ(getsockname(fd_cl, (void *)&addr, &len), 0, "getsockname");
+
+	ASSERT_EQ(send(fd_cl, buff, sizeof(buff), 0), 1, "send_client");
+
+	ret = recv(fd_sv, buff, sizeof(buff), 0);
+	if (ret < 0) {
+		close(fd_cl);
+		return errno;
+	}
+
+	ASSERT_EQ(ret, 1, "recv_server");
+	ASSERT_EQ(sendto(fd_sv, buff, sizeof(buff), 0, (void *)&addr, len), 1, "send_server");
+	ASSERT_EQ(recv(fd_cl, buff, sizeof(buff), 0), 1, "recv_client");
+	close(fd_cl);
+	return 0;
+}
+
+static int echo_test_tcp(int fd_sv)
+{
+	char buff[1] = {};
+	int fd_cl = -1, fd_sv_cl = -1;
+
+	fd_cl = connect_to_fd(fd_sv, 100);
+	if (fd_cl < 0)
+		return errno;
+
+	fd_sv_cl = accept(fd_sv, NULL, NULL);
+	ASSERT_GE(fd_sv_cl, 0, "accept_fd");
+
+	ASSERT_EQ(send(fd_cl, buff, sizeof(buff), 0), 1, "send_client");
+	ASSERT_EQ(recv(fd_sv_cl, buff, sizeof(buff), 0), 1, "recv_server");
+	ASSERT_EQ(send(fd_sv_cl, buff, sizeof(buff), 0), 1, "send_server");
+	ASSERT_EQ(recv(fd_cl, buff, sizeof(buff), 0), 1, "recv_client");
+	close(fd_sv_cl);
+	close(fd_cl);
+	return 0;
+}
+
+void run_assign_reuse(int family, int sotype, const char *ip, __u16 port)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
+		.ifindex = LOOPBACK,
+		.attach_point = BPF_TC_INGRESS,
+	);
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, tc_opts,
+		.handle = 1,
+		.priority = 1,
+	);
+	bool hook_created = false, tc_attached = false;
+	int ret, fd_tc, fd_accept, fd_drop, fd_map;
+	int *fd_sv = NULL;
+	__u64 fd_val;
+	struct test_assign_reuse *skel;
+	const int zero = 0;
+
+	skel = test_assign_reuse__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	skel->rodata->dest_port = port;
+
+	ret = test_assign_reuse__load(skel);
+	if (!ASSERT_OK(ret, "skel_load"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->sk_cookie_seen, 0, "cookie_init");
+
+	fd_tc = bpf_program__fd(skel->progs.tc_main);
+	fd_accept = bpf_program__fd(skel->progs.reuse_accept);
+	fd_drop = bpf_program__fd(skel->progs.reuse_drop);
+	fd_map = bpf_map__fd(skel->maps.sk_map);
+
+	fd_sv = start_reuseport_server(family, sotype, ip, port, 100, 1);
+	if (!ASSERT_NEQ(fd_sv, NULL, "start_reuseport_server"))
+		goto cleanup;
+
+	ret = attach_reuseport(*fd_sv, fd_drop);
+	if (!ASSERT_OK(ret, "attach_reuseport"))
+		goto cleanup;
+
+	fd_val = *fd_sv;
+	ret = bpf_map_update_elem(fd_map, &zero, &fd_val, BPF_NOEXIST);
+	if (!ASSERT_OK(ret, "bpf_sk_map"))
+		goto cleanup;
+
+	ret = bpf_tc_hook_create(&tc_hook);
+	if (ret == 0)
+		hook_created = true;
+	ret = ret == -EEXIST ? 0 : ret;
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+		goto cleanup;
+
+	tc_opts.prog_fd = fd_tc;
+	ret = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach"))
+		goto cleanup;
+	tc_attached = true;
+
+	if (sotype == SOCK_STREAM)
+		ASSERT_EQ(echo_test_tcp(*fd_sv), ECONNREFUSED, "drop_tcp");
+	else
+		ASSERT_EQ(echo_test_udp(*fd_sv), EAGAIN, "drop_udp");
+	ASSERT_EQ(skel->bss->reuseport_executed, 1, "program executed once");
+
+	skel->bss->sk_cookie_seen = 0;
+	skel->bss->reuseport_executed = 0;
+	ASSERT_OK(attach_reuseport(*fd_sv, fd_accept), "attach_reuseport(accept)");
+
+	if (sotype == SOCK_STREAM)
+		ASSERT_EQ(echo_test_tcp(*fd_sv), 0, "echo_tcp");
+	else
+		ASSERT_EQ(echo_test_udp(*fd_sv), 0, "echo_udp");
+
+	ASSERT_EQ(skel->bss->sk_cookie_seen, cookie(*fd_sv),
+		  "cookie_mismatch");
+	ASSERT_EQ(skel->bss->reuseport_executed, 1, "program executed once");
+cleanup:
+	if (tc_attached) {
+		tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+		ret = bpf_tc_detach(&tc_hook, &tc_opts);
+		ASSERT_OK(ret, "bpf_tc_detach");
+	}
+	if (hook_created) {
+		tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+		bpf_tc_hook_destroy(&tc_hook);
+	}
+	test_assign_reuse__destroy(skel);
+	free_fds(fd_sv, 1);
+}
+
+void test_assign_reuse(void)
+{
+	struct nstoken *tok = NULL;
+
+	SYS(out, "ip netns add %s", NS_TEST);
+	SYS(cleanup, "ip -net %s link set dev lo up", NS_TEST);
+
+	tok = open_netns(NS_TEST);
+	if (!ASSERT_OK_PTR(tok, "netns token"))
+		return;
+
+	if (test__start_subtest("tcpv4"))
+		run_assign_reuse(AF_INET, SOCK_STREAM, "127.0.0.1", PORT);
+	if (test__start_subtest("tcpv6"))
+		run_assign_reuse(AF_INET6, SOCK_STREAM, "::1", PORT);
+	if (test__start_subtest("udpv4"))
+		run_assign_reuse(AF_INET, SOCK_DGRAM, "127.0.0.1", PORT);
+	if (test__start_subtest("udpv6"))
+		run_assign_reuse(AF_INET6, SOCK_DGRAM, "::1", PORT);
+
+cleanup:
+	close_netns(tok);
+	SYS_NOFAIL("ip netns delete %s", NS_TEST);
+out:
+	return;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_assign_reuse.c b/tools/testing/selftests/bpf/progs/test_assign_reuse.c
new file mode 100644
index 0000000000000..4f2e2321ea06b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_assign_reuse.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/pkt_cls.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+__u64 sk_cookie_seen;
+__u64 reuseport_executed;
+union {
+	struct tcphdr tcp;
+	struct udphdr udp;
+} headers;
+
+const volatile __u16 dest_port;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} sk_map SEC(".maps");
+
+SEC("sk_reuseport")
+int reuse_accept(struct sk_reuseport_md *ctx)
+{
+	reuseport_executed++;
+
+	if (ctx->ip_protocol == IPPROTO_TCP) {
+		if (ctx->data + sizeof(headers.tcp) > ctx->data_end)
+			return SK_DROP;
+
+		if (__builtin_memcmp(&headers.tcp, ctx->data, sizeof(headers.tcp)) != 0)
+			return SK_DROP;
+	} else if (ctx->ip_protocol == IPPROTO_UDP) {
+		if (ctx->data + sizeof(headers.udp) > ctx->data_end)
+			return SK_DROP;
+
+		if (__builtin_memcmp(&headers.udp, ctx->data, sizeof(headers.udp)) != 0)
+			return SK_DROP;
+	} else {
+		return SK_DROP;
+	}
+
+	sk_cookie_seen = bpf_get_socket_cookie(ctx->sk);
+	return SK_PASS;
+}
+
+SEC("sk_reuseport")
+int reuse_drop(struct sk_reuseport_md *ctx)
+{
+	reuseport_executed++;
+	sk_cookie_seen = 0;
+	return SK_DROP;
+}
+
+static int
+assign_sk(struct __sk_buff *skb)
+{
+	int zero = 0, ret = 0;
+	struct bpf_sock *sk;
+
+	sk = bpf_map_lookup_elem(&sk_map, &zero);
+	if (!sk)
+		return TC_ACT_SHOT;
+	ret = bpf_sk_assign(skb, sk, 0);
+	bpf_sk_release(sk);
+	return ret ? TC_ACT_SHOT : TC_ACT_OK;
+}
+
+static bool
+maybe_assign_tcp(struct __sk_buff *skb, struct tcphdr *th)
+{
+	if (th + 1 > (void *)(long)(skb->data_end))
+		return TC_ACT_SHOT;
+
+	if (!th->syn || th->ack || th->dest != bpf_htons(dest_port))
+		return TC_ACT_OK;
+
+	__builtin_memcpy(&headers.tcp, th, sizeof(headers.tcp));
+	return assign_sk(skb);
+}
+
+static bool
+maybe_assign_udp(struct __sk_buff *skb, struct udphdr *uh)
+{
+	if (uh + 1 > (void *)(long)(skb->data_end))
+		return TC_ACT_SHOT;
+
+	if (uh->dest != bpf_htons(dest_port))
+		return TC_ACT_OK;
+
+	__builtin_memcpy(&headers.udp, uh, sizeof(headers.udp));
+	return assign_sk(skb);
+}
+
+SEC("tc")
+int tc_main(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth;
+
+	eth = (struct ethhdr *)(data);
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)(data + sizeof(*eth));
+
+		if (iph + 1 > data_end)
+			return TC_ACT_SHOT;
+
+		if (iph->protocol == IPPROTO_TCP)
+			return maybe_assign_tcp(skb, (struct tcphdr *)(iph + 1));
+		else if (iph->protocol == IPPROTO_UDP)
+			return maybe_assign_udp(skb, (struct udphdr *)(iph + 1));
+		else
+			return TC_ACT_SHOT;
+	} else {
+		struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + sizeof(*eth));
+
+		if (ip6h + 1 > data_end)
+			return TC_ACT_SHOT;
+
+		if (ip6h->nexthdr == IPPROTO_TCP)
+			return maybe_assign_tcp(skb, (struct tcphdr *)(ip6h + 1));
+		else if (ip6h->nexthdr == IPPROTO_UDP)
+			return maybe_assign_udp(skb, (struct udphdr *)(ip6h + 1));
+		else
+			return TC_ACT_SHOT;
+	}
+}
-- 
GitLab


From 13fd5e14afa57ba82189d5fd9ceb0435e5693bcc Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 20 Jul 2023 11:48:15 +0100
Subject: [PATCH 0443/1806] selftests/xsk: Fix spelling mistake "querrying" ->
 "querying"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a spelling mistake in an error message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/r/20230720104815.123146-1-colin.i.king@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/xskxceiver.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 3ff4367066401..2827f2d7cf30f 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -2076,7 +2076,7 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 
 	err = bpf_xdp_query(ifobj->ifindex, XDP_FLAGS_DRV_MODE, &query_opts);
 	if (err) {
-		ksft_print_msg("Error querrying XDP capabilities\n");
+		ksft_print_msg("Error querying XDP capabilities\n");
 		exit_with_error(-err);
 	}
 	if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG)
-- 
GitLab


From 63e2da3b7f7f63f881aa508825b0c4241e9910e1 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Jul 2023 22:26:40 +0200
Subject: [PATCH 0444/1806] bpf: work around -Wuninitialized warning

Splitting these out into separate helper functions means that we
actually pass an uninitialized variable into another function call
if dec_active() happens to not be inlined, and CONFIG_PREEMPT_RT
is disabled:

kernel/bpf/memalloc.c: In function 'add_obj_to_free_list':
kernel/bpf/memalloc.c:200:9: error: 'flags' is used uninitialized [-Werror=uninitialized]
  200 |         dec_active(c, flags);

Avoid this by passing the flags by reference, so they either get
initialized and dereferenced through a pointer, or the pointer never
gets accessed at all.

Fixes: 18e027b1c7c6d ("bpf: Factor out inc/dec of active flag into helpers.")
Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20230725202653.2905259-1-arnd@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/memalloc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 51d6389e5152e..14d9b1a9a4cac 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -183,11 +183,11 @@ static void inc_active(struct bpf_mem_cache *c, unsigned long *flags)
 	WARN_ON_ONCE(local_inc_return(&c->active) != 1);
 }
 
-static void dec_active(struct bpf_mem_cache *c, unsigned long flags)
+static void dec_active(struct bpf_mem_cache *c, unsigned long *flags)
 {
 	local_dec(&c->active);
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		local_irq_restore(flags);
+		local_irq_restore(*flags);
 }
 
 static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
@@ -197,7 +197,7 @@ static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
 	inc_active(c, &flags);
 	__llist_add(obj, &c->free_llist);
 	c->free_cnt++;
-	dec_active(c, flags);
+	dec_active(c, &flags);
 }
 
 /* Mostly runs from irq_work except __init phase. */
@@ -344,7 +344,7 @@ static void free_bulk(struct bpf_mem_cache *c)
 			cnt = --c->free_cnt;
 		else
 			cnt = 0;
-		dec_active(c, flags);
+		dec_active(c, &flags);
 		if (llnode)
 			enque_to_free(tgt, llnode);
 	} while (cnt > (c->high_watermark + c->low_watermark) / 2);
@@ -384,7 +384,7 @@ static void check_free_by_rcu(struct bpf_mem_cache *c)
 		llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra_rcu))
 			if (__llist_add(llnode, &c->free_by_rcu))
 				c->free_by_rcu_tail = llnode;
-		dec_active(c, flags);
+		dec_active(c, &flags);
 	}
 
 	if (llist_empty(&c->free_by_rcu))
@@ -408,7 +408,7 @@ static void check_free_by_rcu(struct bpf_mem_cache *c)
 	inc_active(c, &flags);
 	WRITE_ONCE(c->waiting_for_gp.first, __llist_del_all(&c->free_by_rcu));
 	c->waiting_for_gp_tail = c->free_by_rcu_tail;
-	dec_active(c, flags);
+	dec_active(c, &flags);
 
 	if (unlikely(READ_ONCE(c->draining))) {
 		free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
-- 
GitLab


From f080864a9d906678e050f10f0e81add711b86fbc Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Mon, 24 Jul 2023 10:37:35 +0800
Subject: [PATCH 0445/1806] net: remove redundant NULL check in
 remove_xps_queue()

There are currently two paths that call remove_xps_queue():
1. __netif_set_xps_queue -> remove_xps_queue
2. clean_xps_maps -> remove_xps_queue_cpu -> remove_xps_queue
There is no need to check dev_maps in remove_xps_queue() because
dev_maps has been checked on these two paths.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Link: https://lore.kernel.org/r/20230724023735.2751602-1-shaozhengchao@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 8e7d0cb540cdb..e7ffcfa037f79 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2384,8 +2384,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps,
 	struct xps_map *map = NULL;
 	int pos;
 
-	if (dev_maps)
-		map = xmap_dereference(dev_maps->attr_map[tci]);
+	map = xmap_dereference(dev_maps->attr_map[tci]);
 	if (!map)
 		return false;
 
-- 
GitLab


From 8540336adadb84d5fc7864384e6d32506fa17560 Mon Sep 17 00:00:00 2001
From: Alexandra Winter <wintera@linux.ibm.com>
Date: Mon, 24 Jul 2023 15:15:46 +0200
Subject: [PATCH 0446/1806] s390/lcs: Remove FDDI option

The last s390 machine that supported FDDI was z900 ('7th generation',
released in 2000). The oldest machine generation currently supported by
the Linux kernel is MARCH_Z10 (released 2008). If there is still a usecase
for connecting a Linux on s390 instance to a LAN Channel Station (LCS), it
can only do so via Ethernet.

Randy Dunlap[1] found that LCS over FDDI has never worked, when FDDI
was compiled as module. Instead of fixing that, remove the FDDI option
from the lcs driver.

While at it, make the CONFIG_LCS description a bit more helpful.

References:
[1] https://lore.kernel.org/netdev/20230621213742.8245-1-rdunlap@infradead.org/

Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230724131546.3597001-1-wintera@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/s390/net/Kconfig |  5 ++---
 drivers/s390/net/lcs.c   | 39 ++++++---------------------------------
 2 files changed, 8 insertions(+), 36 deletions(-)

diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig
index 9c67b97faba2b..74760c1a163b9 100644
--- a/drivers/s390/net/Kconfig
+++ b/drivers/s390/net/Kconfig
@@ -5,12 +5,11 @@ menu "S/390 network device drivers"
 config LCS
 	def_tristate m
 	prompt "Lan Channel Station Interface"
-	depends on CCW && NETDEVICES && (ETHERNET || FDDI)
+	depends on CCW && NETDEVICES && ETHERNET
 	help
 	  Select this option if you want to use LCS networking on IBM System z.
-	  This device driver supports FDDI (IEEE 802.7) and Ethernet.
 	  To compile as a module, choose M. The module name is lcs.
-	  If you do not know what it is, it's safe to choose Y.
+	  If you do not use LCS, choose N.
 
 config CTCM
 	def_tristate m
diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c
index 9fd8e6f07a033..a1f2acd6fb8f6 100644
--- a/drivers/s390/net/lcs.c
+++ b/drivers/s390/net/lcs.c
@@ -17,7 +17,6 @@
 #include <linux/if.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
-#include <linux/fddidevice.h>
 #include <linux/inetdevice.h>
 #include <linux/in.h>
 #include <linux/igmp.h>
@@ -36,10 +35,6 @@
 #include "lcs.h"
 
 
-#if !defined(CONFIG_ETHERNET) && !defined(CONFIG_FDDI)
-#error Cannot compile lcs.c without some net devices switched on.
-#endif
-
 /*
  * initialization string for output
  */
@@ -1601,19 +1596,11 @@ lcs_startlan_auto(struct lcs_card *card)
 	int rc;
 
 	LCS_DBF_TEXT(2, trace, "strtauto");
-#ifdef CONFIG_ETHERNET
 	card->lan_type = LCS_FRAME_TYPE_ENET;
 	rc = lcs_send_startlan(card, LCS_INITIATOR_TCPIP);
 	if (rc == 0)
 		return 0;
 
-#endif
-#ifdef CONFIG_FDDI
-	card->lan_type = LCS_FRAME_TYPE_FDDI;
-	rc = lcs_send_startlan(card, LCS_INITIATOR_TCPIP);
-	if (rc == 0)
-		return 0;
-#endif
 	return -EIO;
 }
 
@@ -1806,22 +1793,16 @@ lcs_get_frames_cb(struct lcs_channel *channel, struct lcs_buffer *buffer)
 			card->stats.rx_errors++;
 			return;
 		}
-		/* What kind of frame is it? */
-		if (lcs_hdr->type == LCS_FRAME_TYPE_CONTROL) {
-			/* Control frame. */
+		if (lcs_hdr->type == LCS_FRAME_TYPE_CONTROL)
 			lcs_get_control(card, (struct lcs_cmd *) lcs_hdr);
-		} else if (lcs_hdr->type == LCS_FRAME_TYPE_ENET ||
-			   lcs_hdr->type == LCS_FRAME_TYPE_TR ||
-			   lcs_hdr->type == LCS_FRAME_TYPE_FDDI) {
-			/* Normal network packet. */
+		else if (lcs_hdr->type == LCS_FRAME_TYPE_ENET)
 			lcs_get_skb(card, (char *)(lcs_hdr + 1),
 				    lcs_hdr->offset - offset -
 				    sizeof(struct lcs_header));
-		} else {
-			/* Unknown frame type. */
-			; // FIXME: error message ?
-		}
-		/* Proceed to next frame. */
+		else
+			dev_info_once(&card->dev->dev,
+				      "Unknown frame type %d\n",
+				      lcs_hdr->type);
 		offset = lcs_hdr->offset;
 		lcs_hdr->offset = LCS_ILLEGAL_OFFSET;
 		lcs_hdr = (struct lcs_header *) (buffer->data + offset);
@@ -2140,18 +2121,10 @@ lcs_new_device(struct ccwgroup_device *ccwgdev)
 		goto netdev_out;
 	}
 	switch (card->lan_type) {
-#ifdef CONFIG_ETHERNET
 	case LCS_FRAME_TYPE_ENET:
 		card->lan_type_trans = eth_type_trans;
 		dev = alloc_etherdev(0);
 		break;
-#endif
-#ifdef CONFIG_FDDI
-	case LCS_FRAME_TYPE_FDDI:
-		card->lan_type_trans = fddi_type_trans;
-		dev = alloc_fddidev(0);
-		break;
-#endif
 	default:
 		LCS_DBF_TEXT(3, setup, "errinit");
 		pr_err(" Initialization failed\n");
-- 
GitLab


From 09bd2d7ddaedcdfa4aa3f4d54c103f984a93bd32 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 24 Jul 2023 16:57:14 +0100
Subject: [PATCH 0447/1806] net: mdio_bus: validate "addr" for
 mdiobus_is_registered_device()

mdiobus_is_registered_device() doesn't checking that "addr" was valid
before dereferencing bus->mdio_map[]. Extract the code that checks
this from mdiobus_get_phy(), and use it here as well.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/E1qNxvu-00111m-1V@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mdio_bus.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index bc04048de2faf..25dcaa49ab8be 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -107,16 +107,21 @@ int mdiobus_unregister_device(struct mdio_device *mdiodev)
 }
 EXPORT_SYMBOL(mdiobus_unregister_device);
 
-struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr)
+static struct mdio_device *mdiobus_find_device(struct mii_bus *bus, int addr)
 {
 	bool addr_valid = addr >= 0 && addr < ARRAY_SIZE(bus->mdio_map);
-	struct mdio_device *mdiodev;
 
 	if (WARN_ONCE(!addr_valid, "addr %d out of range\n", addr))
 		return NULL;
 
-	mdiodev = bus->mdio_map[addr];
+	return bus->mdio_map[addr];
+}
 
+struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr)
+{
+	struct mdio_device *mdiodev;
+
+	mdiodev = mdiobus_find_device(bus, addr);
 	if (!mdiodev)
 		return NULL;
 
@@ -129,7 +134,7 @@ EXPORT_SYMBOL(mdiobus_get_phy);
 
 bool mdiobus_is_registered_device(struct mii_bus *bus, int addr)
 {
-	return bus->mdio_map[addr];
+	return mdiobus_find_device(bus, addr) != NULL;
 }
 EXPORT_SYMBOL(mdiobus_is_registered_device);
 
-- 
GitLab


From 20bf98c94146eb6fe62177817cb32f53e72dd2e8 Mon Sep 17 00:00:00 2001
From: Johannes Zink <j.zink@pengutronix.de>
Date: Mon, 24 Jul 2023 12:01:31 +0200
Subject: [PATCH 0448/1806] net: stmmac: correct MAC propagation delay

The IEEE1588 Standard specifies that the timestamps of Packets must be
captured when the PTP message timestamp point (leading edge of first
octet after the start of frame delimiter) crosses the boundary between
the node and the network. As the MAC latches the timestamp at an
internal point, the captured timestamp must be corrected for the
additional path latency, as described in the publicly available
datasheet [1].

This patch only corrects for the MAC-Internal delay, which can be read
out from the MAC_Ingress_Timestamp_Latency register, since the Phy
framework currently does not support querying the Phy ingress and egress
latency. The Closs Domain Crossing Circuits errors as indicated in [1]
are already being accounted in the stmmac_get_tx_hwtstamp() function and
are not corrected here.

As the Latency varies for different link speeds and MII
modes of operation, the correction value needs to be updated on each
link state change.

As the delay also causes a phase shift in the timestamp counter compared
to the rest of the network, this correction will also reduce phase error
when generating PPS outputs from the timestamp counter.

[1] i.MX8MP Reference Manual, rev.1 Section 11.7.2.5.3 "Timestamp
correction"

Signed-off-by: Johannes Zink <j.zink@pengutronix.de>
Link: https://lore.kernel.org/r/20230719-stmmac_correct_mac_delay-v2-1-3366f38ee9a6@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/hwif.h    |  3 ++
 .../ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 43 +++++++++++++++++++
 .../net/ethernet/stmicro/stmmac/stmmac_main.c |  4 ++
 .../net/ethernet/stmicro/stmmac/stmmac_ptp.h  |  6 +++
 4 files changed, 56 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 652af8f6e75ff..40147ef249631 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -532,6 +532,7 @@ struct stmmac_hwtimestamp {
 	void (*get_systime) (void __iomem *ioaddr, u64 *systime);
 	void (*get_ptptime)(void __iomem *ioaddr, u64 *ptp_time);
 	void (*timestamp_interrupt)(struct stmmac_priv *priv);
+	void (*correct_latency)(struct stmmac_priv *priv);
 };
 
 #define stmmac_config_hw_tstamping(__priv, __args...) \
@@ -550,6 +551,8 @@ struct stmmac_hwtimestamp {
 	stmmac_do_void_callback(__priv, ptp, get_ptptime, __args)
 #define stmmac_timestamp_interrupt(__priv, __args...) \
 	stmmac_do_void_callback(__priv, ptp, timestamp_interrupt, __args)
+#define stmmac_correct_latency(__priv, __args...) \
+	stmmac_do_void_callback(__priv, ptp, correct_latency, __args)
 
 struct stmmac_tx_queue;
 struct stmmac_rx_queue;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index fa2c3ba7e9fe7..7e0fa024e0ad0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -60,6 +60,48 @@ static void config_sub_second_increment(void __iomem *ioaddr,
 		*ssinc = data;
 }
 
+static void correct_latency(struct stmmac_priv *priv)
+{
+	void __iomem *ioaddr = priv->ptpaddr;
+	u32 reg_tsic, reg_tsicsns;
+	u32 reg_tsec, reg_tsecsns;
+	u64 scaled_ns;
+	u32 val;
+
+	/* MAC-internal ingress latency */
+	scaled_ns = readl(ioaddr + PTP_TS_INGR_LAT);
+
+	/* See section 11.7.2.5.3.1 "Ingress Correction" on page 4001 of
+	 * i.MX8MP Applications Processor Reference Manual Rev. 1, 06/2021
+	 */
+	val = readl(ioaddr + PTP_TCR);
+	if (val & PTP_TCR_TSCTRLSSR)
+		/* nanoseconds field is in decimal format with granularity of 1ns/bit */
+		scaled_ns = ((u64)NSEC_PER_SEC << 16) - scaled_ns;
+	else
+		/* nanoseconds field is in binary format with granularity of ~0.466ns/bit */
+		scaled_ns = ((1ULL << 31) << 16) -
+			DIV_U64_ROUND_CLOSEST(scaled_ns * PSEC_PER_NSEC, 466U);
+
+	reg_tsic = scaled_ns >> 16;
+	reg_tsicsns = scaled_ns & 0xff00;
+
+	/* set bit 31 for 2's compliment */
+	reg_tsic |= BIT(31);
+
+	writel(reg_tsic, ioaddr + PTP_TS_INGR_CORR_NS);
+	writel(reg_tsicsns, ioaddr + PTP_TS_INGR_CORR_SNS);
+
+	/* MAC-internal egress latency */
+	scaled_ns = readl(ioaddr + PTP_TS_EGR_LAT);
+
+	reg_tsec = scaled_ns >> 16;
+	reg_tsecsns = scaled_ns & 0xff00;
+
+	writel(reg_tsec, ioaddr + PTP_TS_EGR_CORR_NS);
+	writel(reg_tsecsns, ioaddr + PTP_TS_EGR_CORR_SNS);
+}
+
 static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec)
 {
 	u32 value;
@@ -221,4 +263,5 @@ const struct stmmac_hwtimestamp stmmac_ptp = {
 	.get_systime = get_systime,
 	.get_ptptime = get_ptptime,
 	.timestamp_interrupt = timestamp_interrupt,
+	.correct_latency = correct_latency,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index e1f1c034d3259..19e46e8f626aa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -909,6 +909,8 @@ static int stmmac_init_ptp(struct stmmac_priv *priv)
 	priv->hwts_tx_en = 0;
 	priv->hwts_rx_en = 0;
 
+	stmmac_correct_latency(priv, priv);
+
 	return 0;
 }
 
@@ -1094,6 +1096,8 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 
 	if (priv->dma_cap.fpesel)
 		stmmac_fpe_link_state_handle(priv, true);
+
+	stmmac_correct_latency(priv, priv);
 }
 
 static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
index bf619295d079f..d1fe4b46f1629 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
@@ -26,6 +26,12 @@
 #define	PTP_ACR		0x40	/* Auxiliary Control Reg */
 #define	PTP_ATNR	0x48	/* Auxiliary Timestamp - Nanoseconds Reg */
 #define	PTP_ATSR	0x4c	/* Auxiliary Timestamp - Seconds Reg */
+#define	PTP_TS_INGR_CORR_NS	0x58	/* Ingress timestamp correction nanoseconds */
+#define	PTP_TS_EGR_CORR_NS	0x5C	/* Egress timestamp correction nanoseconds*/
+#define	PTP_TS_INGR_CORR_SNS	0x60	/* Ingress timestamp correction subnanoseconds */
+#define	PTP_TS_EGR_CORR_SNS	0x64	/* Egress timestamp correction subnanoseconds */
+#define	PTP_TS_INGR_LAT	0x68	/* MAC internal Ingress Latency */
+#define	PTP_TS_EGR_LAT	0x6c	/* MAC internal Egress Latency */
 
 #define	PTP_STNSUR_ADDSUB_SHIFT	31
 #define	PTP_DIGITAL_ROLLOVER_MODE	0x3B9ACA00	/* 10e9-1 ns */
-- 
GitLab


From 2303fae130640874823ea1bc7ec65c3cd074a7eb Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Mon, 24 Jul 2023 18:22:55 +0200
Subject: [PATCH 0449/1806] net: skbuff: remove unused HAVE_HW_TIME_STAMP
 feature define

Remove unused HAVE_HW_TIME_STAMP feature define (introduced by
commit ac45f602ee3d ("net: infrastructure for hardware time stamping").

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index faaba050f843d..16a49ba534e4a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -441,8 +441,6 @@ static inline bool skb_frag_must_loop(struct page *p)
 	     copied += p_len, p++, p_off = 0,				\
 	     p_len = min_t(u32, f_len - copied, PAGE_SIZE))		\
 
-#define HAVE_HW_TIME_STAMP
-
 /**
  * struct skb_shared_hwtstamps - hardware time stamps
  * @hwtstamp:		hardware time stamp transformed into duration
-- 
GitLab


From 02a894046d5ab7d0010f39ea54fde7e167919d04 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 29 Jun 2023 22:39:30 +0200
Subject: [PATCH 0450/1806] wifi: mt76: mt7915: fix capabilities in non-AP mode

Capabilities in vif->bss_conf are only initialized in AP mode.
For other modes, they should be enabled by default, in order to avoid a
mismatch.

Fixes: 885f7af7e544 ("wifi: mt76: mt7915: remove mt7915_mcu_beacon_check_caps()")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7915/main.c  | 21 +++++++++++++++
 .../net/wireless/mediatek/mt76/mt7915/mcu.c   | 27 ++++++++++---------
 .../wireless/mediatek/mt76/mt7915/mt7915.h    | 14 ++++++++++
 3 files changed, 50 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index decb60aac9dd9..eb95fb28d3549 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -269,6 +269,7 @@ static int mt7915_add_interface(struct ieee80211_hw *hw,
 	vif->offload_flags |= IEEE80211_OFFLOAD_ENCAP_4ADDR;
 
 	mt7915_init_bitrate_mask(vif);
+	memset(&mvif->cap, -1, sizeof(mvif->cap));
 
 	mt7915_mcu_add_bss_info(phy, vif, true);
 	mt7915_mcu_add_sta(dev, vif, NULL, true);
@@ -657,6 +658,24 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw,
 	mutex_unlock(&dev->mt76.mutex);
 }
 
+static void
+mt7915_vif_check_caps(struct mt7915_phy *phy, struct ieee80211_vif *vif)
+{
+	struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv;
+	struct mt7915_vif_cap *vc = &mvif->cap;
+
+	vc->ht_ldpc = vif->bss_conf.ht_ldpc;
+	vc->vht_ldpc = vif->bss_conf.vht_ldpc;
+	vc->vht_su_ebfer = vif->bss_conf.vht_su_beamformer;
+	vc->vht_su_ebfee = vif->bss_conf.vht_su_beamformee;
+	vc->vht_mu_ebfer = vif->bss_conf.vht_mu_beamformer;
+	vc->vht_mu_ebfee = vif->bss_conf.vht_mu_beamformee;
+	vc->he_ldpc = vif->bss_conf.he_ldpc;
+	vc->he_su_ebfer = vif->bss_conf.he_su_beamformer;
+	vc->he_su_ebfee = vif->bss_conf.he_su_beamformee;
+	vc->he_mu_ebfer = vif->bss_conf.he_mu_beamformer;
+}
+
 static int
 mt7915_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		struct ieee80211_bss_conf *link_conf)
@@ -667,6 +686,8 @@ mt7915_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	mutex_lock(&dev->mt76.mutex);
 
+	mt7915_vif_check_caps(phy, vif);
+
 	err = mt7915_mcu_add_bss_info(phy, vif, true);
 	if (err)
 		goto out;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index bb8ec0d1d01c3..5f4c2946b26b5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -713,6 +713,7 @@ static void
 mt7915_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta,
 		      struct ieee80211_vif *vif)
 {
+	struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv;
 	struct ieee80211_he_cap_elem *elem = &sta->deflink.he_cap.he_cap_elem;
 	struct ieee80211_he_mcs_nss_supp mcs_map;
 	struct sta_rec_he *he;
@@ -746,7 +747,7 @@ mt7915_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta,
 	     IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G))
 		cap |= STA_REC_HE_CAP_BW20_RU242_SUPPORT;
 
-	if (vif->bss_conf.he_ldpc &&
+	if (mvif->cap.he_ldpc &&
 	    (elem->phy_cap_info[1] &
 	     IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD))
 		cap |= STA_REC_HE_CAP_LDPC;
@@ -855,6 +856,7 @@ static void
 mt7915_mcu_sta_muru_tlv(struct mt7915_dev *dev, struct sk_buff *skb,
 			struct ieee80211_sta *sta, struct ieee80211_vif *vif)
 {
+	struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv;
 	struct ieee80211_he_cap_elem *elem = &sta->deflink.he_cap.he_cap_elem;
 	struct sta_rec_muru *muru;
 	struct tlv *tlv;
@@ -867,9 +869,9 @@ mt7915_mcu_sta_muru_tlv(struct mt7915_dev *dev, struct sk_buff *skb,
 
 	muru = (struct sta_rec_muru *)tlv;
 
-	muru->cfg.mimo_dl_en = vif->bss_conf.he_mu_beamformer ||
-			       vif->bss_conf.vht_mu_beamformer ||
-			       vif->bss_conf.vht_mu_beamformee;
+	muru->cfg.mimo_dl_en = mvif->cap.he_mu_ebfer ||
+			       mvif->cap.vht_mu_ebfer ||
+			       mvif->cap.vht_mu_ebfee;
 	if (!is_mt7915(&dev->mt76))
 		muru->cfg.mimo_ul_en = true;
 	muru->cfg.ofdma_dl_en = true;
@@ -1002,8 +1004,8 @@ mt7915_mcu_sta_wtbl_tlv(struct mt7915_dev *dev, struct sk_buff *skb,
 	mt76_connac_mcu_wtbl_hdr_trans_tlv(skb, vif, wcid, tlv, wtbl_hdr);
 	if (sta)
 		mt76_connac_mcu_wtbl_ht_tlv(&dev->mt76, skb, sta, tlv,
-					    wtbl_hdr, vif->bss_conf.ht_ldpc,
-					    vif->bss_conf.vht_ldpc);
+					    wtbl_hdr, mvif->cap.ht_ldpc,
+					    mvif->cap.vht_ldpc);
 
 	return 0;
 }
@@ -1012,6 +1014,7 @@ static inline bool
 mt7915_is_ebf_supported(struct mt7915_phy *phy, struct ieee80211_vif *vif,
 			struct ieee80211_sta *sta, bool bfee)
 {
+	struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv;
 	int tx_ant = hweight8(phy->mt76->chainmask) - 1;
 
 	if (vif->type != NL80211_IFTYPE_STATION &&
@@ -1025,10 +1028,10 @@ mt7915_is_ebf_supported(struct mt7915_phy *phy, struct ieee80211_vif *vif,
 		struct ieee80211_he_cap_elem *pe = &sta->deflink.he_cap.he_cap_elem;
 
 		if (bfee)
-			return vif->bss_conf.he_su_beamformee &&
+			return mvif->cap.he_su_ebfee &&
 			       HE_PHY(CAP3_SU_BEAMFORMER, pe->phy_cap_info[3]);
 		else
-			return vif->bss_conf.he_su_beamformer &&
+			return mvif->cap.he_su_ebfer &&
 			       HE_PHY(CAP4_SU_BEAMFORMEE, pe->phy_cap_info[4]);
 	}
 
@@ -1036,10 +1039,10 @@ mt7915_is_ebf_supported(struct mt7915_phy *phy, struct ieee80211_vif *vif,
 		u32 cap = sta->deflink.vht_cap.cap;
 
 		if (bfee)
-			return vif->bss_conf.vht_su_beamformee &&
+			return mvif->cap.vht_su_ebfee &&
 			       (cap & IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE);
 		else
-			return vif->bss_conf.vht_su_beamformer &&
+			return mvif->cap.vht_su_ebfer &&
 			       (cap & IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE);
 	}
 
@@ -1534,7 +1537,7 @@ mt7915_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7915_dev *dev,
 			cap |= STA_CAP_TX_STBC;
 		if (sta->deflink.ht_cap.cap & IEEE80211_HT_CAP_RX_STBC)
 			cap |= STA_CAP_RX_STBC;
-		if (vif->bss_conf.ht_ldpc &&
+		if (mvif->cap.ht_ldpc &&
 		    (sta->deflink.ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING))
 			cap |= STA_CAP_LDPC;
 
@@ -1560,7 +1563,7 @@ mt7915_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7915_dev *dev,
 			cap |= STA_CAP_VHT_TX_STBC;
 		if (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_RXSTBC_1)
 			cap |= STA_CAP_VHT_RX_STBC;
-		if (vif->bss_conf.vht_ldpc &&
+		if (mvif->cap.vht_ldpc &&
 		    (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC))
 			cap |= STA_CAP_VHT_LDPC;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index 0c7226b8c805e..0456e56f63480 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -152,9 +152,23 @@ struct mt7915_sta {
 	} twt;
 };
 
+struct mt7915_vif_cap {
+	bool ht_ldpc:1;
+	bool vht_ldpc:1;
+	bool he_ldpc:1;
+	bool vht_su_ebfer:1;
+	bool vht_su_ebfee:1;
+	bool vht_mu_ebfer:1;
+	bool vht_mu_ebfee:1;
+	bool he_su_ebfer:1;
+	bool he_su_ebfee:1;
+	bool he_mu_ebfer:1;
+};
+
 struct mt7915_vif {
 	struct mt76_vif mt76; /* must be first */
 
+	struct mt7915_vif_cap cap;
 	struct mt7915_sta sta;
 	struct mt7915_phy *phy;
 
-- 
GitLab


From 7d424a990e050ac09a0646edca083dcb4a516855 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Sat, 8 Jul 2023 20:29:35 +0200
Subject: [PATCH 0451/1806] wifi: mt76: split get_of_eeprom in subfunction

In preparation for NVMEM support, split get_of_eeprom() in subfunction
to tidy the code and facilitate the addition of alternative method to
get eeprom data. No behaviour change intended.

While at it also drop OF ifdef checks as OF have stubs and calling
of_get_property would result in the same error returned.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/eeprom.c | 51 ++++++++++++++-------
 1 file changed, 35 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/eeprom.c b/drivers/net/wireless/mediatek/mt76/eeprom.c
index dce851d42e083..c3a762074be8e 100644
--- a/drivers/net/wireless/mediatek/mt76/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/eeprom.c
@@ -9,31 +9,35 @@
 #include <linux/etherdevice.h>
 #include "mt76.h"
 
-int mt76_get_of_eeprom(struct mt76_dev *dev, void *eep, int offset, int len)
+static int mt76_get_of_eeprom_data(struct mt76_dev *dev, void *eep, int len)
 {
-#if defined(CONFIG_OF) && defined(CONFIG_MTD)
 	struct device_node *np = dev->dev->of_node;
-	struct mtd_info *mtd;
-	const __be32 *list;
 	const void *data;
-	const char *part;
-	phandle phandle;
 	int size;
-	size_t retlen;
-	int ret;
 
-	if (!np)
+	data = of_get_property(np, "mediatek,eeprom-data", &size);
+	if (!data)
 		return -ENOENT;
 
-	data = of_get_property(np, "mediatek,eeprom-data", &size);
-	if (data) {
-		if (size > len)
-			return -EINVAL;
+	if (size > len)
+		return -EINVAL;
 
-		memcpy(eep, data, size);
+	memcpy(eep, data, size);
 
-		return 0;
-	}
+	return 0;
+}
+
+static int mt76_get_of_epprom_from_mtd(struct mt76_dev *dev, void *eep, int offset, int len)
+{
+#ifdef CONFIG_MTD
+	struct device_node *np = dev->dev->of_node;
+	struct mtd_info *mtd;
+	const __be32 *list;
+	const char *part;
+	phandle phandle;
+	size_t retlen;
+	int size;
+	int ret;
 
 	list = of_get_property(np, "mediatek,mtd-eeprom", &size);
 	if (!list)
@@ -100,6 +104,21 @@ out_put_node:
 	return -ENOENT;
 #endif
 }
+
+int mt76_get_of_eeprom(struct mt76_dev *dev, void *eep, int offset, int len)
+{
+	struct device_node *np = dev->dev->of_node;
+	int ret;
+
+	if (!np)
+		return -ENOENT;
+
+	ret = mt76_get_of_eeprom_data(dev, eep, len);
+	if (!ret)
+		return 0;
+
+	return mt76_get_of_epprom_from_mtd(dev, eep, offset, len);
+}
 EXPORT_SYMBOL_GPL(mt76_get_of_eeprom);
 
 void
-- 
GitLab


From 5bef3a406c6e7c4a1d5db69938a08ea70aa9c388 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Sat, 8 Jul 2023 20:29:36 +0200
Subject: [PATCH 0452/1806] wifi: mt76: add support for providing eeprom in
 nvmem cells

Add support for providing eeprom in nvmem cells by adding nvmem cell as
an alternative source for mt76_get_of_eeprom().

Nvmem cells will follow standard nvmem cell definition and needs to be
called 'eeprom' to be correctly identified.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/eeprom.c | 38 ++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/eeprom.c b/drivers/net/wireless/mediatek/mt76/eeprom.c
index c3a762074be8e..36564930aef12 100644
--- a/drivers/net/wireless/mediatek/mt76/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/eeprom.c
@@ -6,6 +6,7 @@
 #include <linux/of_net.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
+#include <linux/nvmem-consumer.h>
 #include <linux/etherdevice.h>
 #include "mt76.h"
 
@@ -105,6 +106,37 @@ out_put_node:
 #endif
 }
 
+static int mt76_get_of_epprom_from_nvmem(struct mt76_dev *dev, void *eep, int len)
+{
+	struct device_node *np = dev->dev->of_node;
+	struct nvmem_cell *cell;
+	const void *data;
+	size_t retlen;
+	int ret = 0;
+
+	cell = of_nvmem_cell_get(np, "eeprom");
+	if (IS_ERR(cell))
+		return PTR_ERR(cell);
+
+	data = nvmem_cell_read(cell, &retlen);
+	nvmem_cell_put(cell);
+
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	if (retlen < len) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	memcpy(eep, data, len);
+
+exit:
+	kfree(data);
+
+	return ret;
+}
+
 int mt76_get_of_eeprom(struct mt76_dev *dev, void *eep, int offset, int len)
 {
 	struct device_node *np = dev->dev->of_node;
@@ -117,7 +149,11 @@ int mt76_get_of_eeprom(struct mt76_dev *dev, void *eep, int offset, int len)
 	if (!ret)
 		return 0;
 
-	return mt76_get_of_epprom_from_mtd(dev, eep, offset, len);
+	ret = mt76_get_of_epprom_from_mtd(dev, eep, offset, len);
+	if (!ret)
+		return 0;
+
+	return mt76_get_of_epprom_from_nvmem(dev, eep, len);
 }
 EXPORT_SYMBOL_GPL(mt76_get_of_eeprom);
 
-- 
GitLab


From f4b68370c343ed8a02cbe2d47761f5269ea77d2e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Mon, 8 May 2023 17:58:20 +0200
Subject: [PATCH 0453/1806] dt-bindings: mt76: support pointing to EEPROM using
 NVMEM cell
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All kind of calibration data should be described as NVMEM cells of NVMEM
devices. That is more generic solution than "mediatek,mtd-eeprom" which
is MTD specific.

Add support for EEPROM NVMEM cells and deprecate existing MTD-based
property.

Cc: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../bindings/net/wireless/mediatek,mt76.yaml         | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml
index 9081731611ef2..252207adbc54c 100644
--- a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml
@@ -72,6 +72,14 @@ properties:
 
   ieee80211-freq-limit: true
 
+  nvmem-cells:
+    items:
+      - description: NVMEM cell with EEPROM
+
+  nvmem-cell-names:
+    items:
+      - const: eeprom
+
   mediatek,eeprom-data:
     $ref: /schemas/types.yaml#/definitions/uint32-array
     description:
@@ -85,6 +93,7 @@ properties:
           - description: offset containing EEPROM data
     description:
       Phandle to a MTD partition + offset containing EEPROM data
+    deprecated: true
 
   big-endian:
     $ref: /schemas/types.yaml#/definitions/flag
@@ -259,7 +268,8 @@ examples:
       interrupt-parent = <&cpuintc>;
       interrupts = <6>;
 
-      mediatek,mtd-eeprom = <&factory 0x0>;
+      nvmem-cells = <&eeprom>;
+      nvmem-cell-names = "eeprom";
     };
 
   - |
-- 
GitLab


From 3ec5ac12ac8a4e6b1e085374325a5fbd1b650fd5 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Fri, 14 Jul 2023 10:57:15 +0200
Subject: [PATCH 0454/1806] wifi: mt76: mt7915: remove VHT160 capability on
 MT7915

The IEEE80211_VHT_CAP_EXT_NSS_BW value already indicates support for half-NSS
160 MHz support, so it is wrong to also advertise full 160 MHz support.

Fixes: c2f73eacee3b ("wifi: mt76: mt7915: add back 160MHz channel width support for MT7915")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/init.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index ee976657bfc36..78552f10b3779 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -414,7 +414,6 @@ mt7915_init_wiphy(struct mt7915_phy *phy)
 			if (!dev->dbdc_support)
 				vht_cap->cap |=
 					IEEE80211_VHT_CAP_SHORT_GI_160 |
-					IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ |
 					FIELD_PREP(IEEE80211_VHT_CAP_EXT_NSS_BW_MASK, 1);
 		} else {
 			vht_cap->cap |=
-- 
GitLab


From f090d0ca0de92aa378f342011d16f5d310a8383f Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 25 Jul 2023 12:37:59 +0200
Subject: [PATCH 0455/1806] wifi: mt76: mt7603: fix beacon interval after
 disabling a single vif

When disabling beacons on a vif, intval is 0. Ensure that dev->mt76.beacon_int
is not overwritten in this case, so that beacons continue to work for other
interfaces.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7603/beacon.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c b/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
index b65b0a88c1ded..888678732f290 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
@@ -161,7 +161,8 @@ void mt7603_beacon_set_timer(struct mt7603_dev *dev, int idx, int intval)
 		return;
 	}
 
-	dev->mt76.beacon_int = intval;
+	if (intval)
+		dev->mt76.beacon_int = intval;
 	mt76_wr(dev, MT_TBTT,
 		FIELD_PREP(MT_TBTT_PERIOD, intval) | MT_TBTT_CAL_ENABLE);
 
-- 
GitLab


From fe0ea395f0a35103f61e107b227bf8bc4b9765df Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 25 Jul 2023 21:06:03 +0200
Subject: [PATCH 0456/1806] wifi: mt76: mt7603: fix tx filter/flush function

Setting MT_TX_ABORT does not abort any transmission for a wtbl index on its
own. Instead, it modifies the behavior of a queue flush to make it selectively
flush packets for a particular wtbl index.
Adjust powersave filtering to make use of this in order to avoid running into
unnecessary timeouts while flushing

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7603/mac.c   | 21 ++++++++++++++-----
 .../net/wireless/mediatek/mt76/mt7603/main.c  |  5 ++++-
 .../wireless/mediatek/mt76/mt7603/mt7603.h    |  2 +-
 .../net/wireless/mediatek/mt76/mt7603/regs.h  |  7 +++++++
 4 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
index de11557eb04c3..99ae080502d80 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
@@ -178,8 +178,9 @@ mt7603_wtbl_set_skip_tx(struct mt7603_dev *dev, int idx, bool enabled)
 	mt76_wr(dev, addr + 3 * 4, val);
 }
 
-void mt7603_filter_tx(struct mt7603_dev *dev, int idx, bool abort)
+void mt7603_filter_tx(struct mt7603_dev *dev, int mac_idx, int idx, bool abort)
 {
+	u32 flush_mask;
 	int i, port, queue;
 
 	if (abort) {
@@ -195,6 +196,18 @@ void mt7603_filter_tx(struct mt7603_dev *dev, int idx, bool abort)
 	mt76_wr(dev, MT_TX_ABORT, MT_TX_ABORT_EN |
 			FIELD_PREP(MT_TX_ABORT_WCID, idx));
 
+	flush_mask = MT_WF_ARB_TX_FLUSH_AC0 |
+		     MT_WF_ARB_TX_FLUSH_AC1 |
+		     MT_WF_ARB_TX_FLUSH_AC2 |
+		     MT_WF_ARB_TX_FLUSH_AC3;
+	flush_mask <<= mac_idx;
+
+	mt76_wr(dev, MT_WF_ARB_TX_FLUSH_0, flush_mask);
+	mt76_poll(dev, MT_WF_ARB_TX_FLUSH_0, flush_mask, 0, 20000);
+	mt76_wr(dev, MT_WF_ARB_TX_START_0, flush_mask);
+
+	mt76_wr(dev, MT_TX_ABORT, 0);
+
 	for (i = 0; i < 4; i++) {
 		mt76_wr(dev, MT_DMA_FQCR0, MT_DMA_FQCR0_BUSY |
 			FIELD_PREP(MT_DMA_FQCR0_TARGET_WCID, idx) |
@@ -202,13 +215,11 @@ void mt7603_filter_tx(struct mt7603_dev *dev, int idx, bool abort)
 			FIELD_PREP(MT_DMA_FQCR0_DEST_PORT_ID, port) |
 			FIELD_PREP(MT_DMA_FQCR0_DEST_QUEUE_ID, queue));
 
-		mt76_poll(dev, MT_DMA_FQCR0, MT_DMA_FQCR0_BUSY, 0, 15000);
+		mt76_poll(dev, MT_DMA_FQCR0, MT_DMA_FQCR0_BUSY, 0, 5000);
 	}
 
 	WARN_ON_ONCE(mt76_rr(dev, MT_DMA_FQCR0) & MT_DMA_FQCR0_BUSY);
 
-	mt76_wr(dev, MT_TX_ABORT, 0);
-
 	mt7603_wtbl_set_skip_tx(dev, idx, false);
 }
 
@@ -245,7 +256,7 @@ void mt7603_wtbl_set_ps(struct mt7603_dev *dev, struct mt7603_sta *sta,
 	mt76_poll(dev, MT_PSE_RTA, MT_PSE_RTA_BUSY, 0, 5000);
 
 	if (enabled)
-		mt7603_filter_tx(dev, idx, false);
+		mt7603_filter_tx(dev, sta->vif->idx, idx, false);
 
 	addr = mt7603_wtbl1_addr(idx);
 	mt76_set(dev, MT_WTBL1_OR, MT_WTBL1_OR_PSM_WRITE);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index 1d4893410ca56..c213fd2a5216b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -69,6 +69,7 @@ mt7603_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	INIT_LIST_HEAD(&mvif->sta.wcid.poll_list);
 	mvif->sta.wcid.idx = idx;
 	mvif->sta.wcid.hw_key_idx = -1;
+	mvif->sta.vif = mvif;
 	mt76_packet_id_init(&mvif->sta.wcid);
 
 	eth_broadcast_addr(bc_addr);
@@ -357,6 +358,7 @@ mt7603_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	msta->smps = ~0;
 	msta->wcid.sta = 1;
 	msta->wcid.idx = idx;
+	msta->vif = mvif;
 	mt7603_wtbl_init(dev, idx, mvif->idx, sta->addr);
 	mt7603_wtbl_set_ps(dev, msta, false);
 
@@ -380,12 +382,13 @@ mt7603_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		  struct ieee80211_sta *sta)
 {
 	struct mt7603_dev *dev = container_of(mdev, struct mt7603_dev, mt76);
+	struct mt7603_vif *mvif = (struct mt7603_vif *)vif->drv_priv;
 	struct mt7603_sta *msta = (struct mt7603_sta *)sta->drv_priv;
 	struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
 
 	spin_lock_bh(&dev->ps_lock);
 	__skb_queue_purge(&msta->psq);
-	mt7603_filter_tx(dev, wcid->idx, true);
+	mt7603_filter_tx(dev, mvif->idx, wcid->idx, true);
 	spin_unlock_bh(&dev->ps_lock);
 
 	spin_lock_bh(&mdev->sta_poll_lock);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
index 354b189862f79..9e58df7042ad1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
@@ -230,7 +230,7 @@ void mt7603_wtbl_set_ps(struct mt7603_dev *dev, struct mt7603_sta *sta,
 			bool enabled);
 void mt7603_wtbl_set_smps(struct mt7603_dev *dev, struct mt7603_sta *sta,
 			  bool enabled);
-void mt7603_filter_tx(struct mt7603_dev *dev, int idx, bool abort);
+void mt7603_filter_tx(struct mt7603_dev *dev, int mac_idx, int idx, bool abort);
 
 int mt7603_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			  enum mt76_txq_id qid, struct mt76_wcid *wcid,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/regs.h b/drivers/net/wireless/mediatek/mt76/mt7603/regs.h
index 3b901090b29c6..a39c9a0fcb1cb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/regs.h
@@ -309,6 +309,13 @@ enum {
 #define MT_WF_ARB_TX_STOP_0		MT_WF_ARB(0x110)
 #define MT_WF_ARB_TX_STOP_1		MT_WF_ARB(0x114)
 
+#define MT_WF_ARB_TX_FLUSH_AC0		BIT(0)
+#define MT_WF_ARB_TX_FLUSH_AC1		BIT(5)
+#define MT_WF_ARB_TX_FLUSH_AC2		BIT(10)
+#define MT_WF_ARB_TX_FLUSH_AC3		BIT(16)
+#define MT_WF_ARB_TX_FLUSH_AC4		BIT(21)
+#define MT_WF_ARB_TX_FLUSH_AC5		BIT(26)
+
 #define MT_WF_ARB_BCN_START		MT_WF_ARB(0x118)
 #define MT_WF_ARB_BCN_START_BSSn(n)	BIT(0 + (n))
 #define MT_WF_ARB_BCN_START_T_PRE_TTTT	BIT(10)
-- 
GitLab


From 6db1b497b04e0e3dff755e0c2a6644c2379d32e2 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:47 +0800
Subject: [PATCH 0457/1806] wifi: mt76: mt7921: move common register definition
 in mt792x_regs.h

This is a preliminary patch in order to support new WiFi7 chips.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/regs.h  | 443 +----------------
 .../net/wireless/mediatek/mt76/mt792x_regs.h  | 460 ++++++++++++++++++
 2 files changed, 463 insertions(+), 440 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt792x_regs.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
index b180142562a24..fefc105395862 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
@@ -4,26 +4,7 @@
 #ifndef __MT7921_REGS_H
 #define __MT7921_REGS_H
 
-/* MCU WFDMA1 */
-#define MT_MCU_WFDMA1_BASE		0x3000
-#define MT_MCU_WFDMA1(ofs)		(MT_MCU_WFDMA1_BASE + (ofs))
-
-#define MT_MCU_INT_EVENT		MT_MCU_WFDMA1(0x108)
-#define MT_MCU_INT_EVENT_DMA_STOPPED	BIT(0)
-#define MT_MCU_INT_EVENT_DMA_INIT	BIT(1)
-#define MT_MCU_INT_EVENT_SER_TRIGGER	BIT(2)
-#define MT_MCU_INT_EVENT_RESET_DONE	BIT(3)
-
-#define MT_PLE_BASE			0x820c0000
-#define MT_PLE(ofs)			(MT_PLE_BASE + (ofs))
-
-#define MT_PLE_FL_Q0_CTRL		MT_PLE(0x3e0)
-#define MT_PLE_FL_Q1_CTRL		MT_PLE(0x3e4)
-#define MT_PLE_FL_Q2_CTRL		MT_PLE(0x3e8)
-#define MT_PLE_FL_Q3_CTRL		MT_PLE(0x3ec)
-
-#define MT_PLE_AC_QEMPTY(_n)		MT_PLE(0x500 + 0x40 * (_n))
-#define MT_PLE_AMSDU_PACK_MSDU_CNT(n)	MT_PLE(0x10e0 + ((n) << 2))
+#include "../mt792x_regs.h"
 
 #define MT_MDP_BASE			0x820cd000
 #define MT_MDP(ofs)			(MT_MDP_BASE + (ofs))
@@ -47,266 +28,6 @@
 #define MT_MDP_TO_HIF			0
 #define MT_MDP_TO_WM			1
 
-/* TMAC: band 0(0x21000), band 1(0xa1000) */
-#define MT_WF_TMAC_BASE(_band)		((_band) ? 0x820f4000 : 0x820e4000)
-#define MT_WF_TMAC(_band, ofs)		(MT_WF_TMAC_BASE(_band) + (ofs))
-
-#define MT_TMAC_TCR0(_band)		MT_WF_TMAC(_band, 0)
-#define MT_TMAC_TCR0_TBTT_STOP_CTRL	BIT(25)
-
-#define MT_TMAC_CDTR(_band)		MT_WF_TMAC(_band, 0x090)
-#define MT_TMAC_ODTR(_band)		MT_WF_TMAC(_band, 0x094)
-#define MT_TIMEOUT_VAL_PLCP		GENMASK(15, 0)
-#define MT_TIMEOUT_VAL_CCA		GENMASK(31, 16)
-
-#define MT_TMAC_ICR0(_band)		MT_WF_TMAC(_band, 0x0a4)
-#define MT_IFS_EIFS			GENMASK(8, 0)
-#define MT_IFS_RIFS			GENMASK(14, 10)
-#define MT_IFS_SIFS			GENMASK(22, 16)
-#define MT_IFS_SLOT			GENMASK(30, 24)
-
-#define MT_TMAC_CTCR0(_band)			MT_WF_TMAC(_band, 0x0f4)
-#define MT_TMAC_CTCR0_INS_DDLMT_REFTIME		GENMASK(5, 0)
-#define MT_TMAC_CTCR0_INS_DDLMT_EN		BIT(17)
-#define MT_TMAC_CTCR0_INS_DDLMT_VHT_SMPDU_EN	BIT(18)
-
-#define MT_TMAC_TRCR0(_band)		MT_WF_TMAC(_band, 0x09c)
-#define MT_TMAC_TFCR0(_band)		MT_WF_TMAC(_band, 0x1e0)
-
-#define MT_WF_DMA_BASE(_band)		((_band) ? 0x820f7000 : 0x820e7000)
-#define MT_WF_DMA(_band, ofs)		(MT_WF_DMA_BASE(_band) + (ofs))
-
-#define MT_DMA_DCR0(_band)		MT_WF_DMA(_band, 0x000)
-#define MT_DMA_DCR0_MAX_RX_LEN		GENMASK(15, 3)
-#define MT_DMA_DCR0_RXD_G5_EN		BIT(23)
-
-/* WTBLOFF TOP: band 0(0x820e9000),band 1(0x820f9000) */
-#define MT_WTBLOFF_TOP_BASE(_band)	((_band) ? 0x820f9000 : 0x820e9000)
-#define MT_WTBLOFF_TOP(_band, ofs)	(MT_WTBLOFF_TOP_BASE(_band) + (ofs))
-
-#define MT_WTBLOFF_TOP_RSCR(_band)	MT_WTBLOFF_TOP(_band, 0x008)
-#define MT_WTBLOFF_TOP_RSCR_RCPI_MODE	GENMASK(31, 30)
-#define MT_WTBLOFF_TOP_RSCR_RCPI_PARAM	GENMASK(25, 24)
-
-/* LPON: band 0(0x24200), band 1(0xa4200) */
-#define MT_WF_LPON_BASE(_band)		((_band) ? 0x820fb000 : 0x820eb000)
-#define MT_WF_LPON(_band, ofs)		(MT_WF_LPON_BASE(_band) + (ofs))
-
-#define MT_LPON_UTTR0(_band)		MT_WF_LPON(_band, 0x080)
-#define MT_LPON_UTTR1(_band)		MT_WF_LPON(_band, 0x084)
-
-#define MT_LPON_TCR(_band, n)		MT_WF_LPON(_band, 0x0a8 + (n) * 4)
-#define MT_LPON_TCR_SW_MODE		GENMASK(1, 0)
-#define MT_LPON_TCR_SW_WRITE		BIT(0)
-
-/* ETBF: band 0(0x24000), band 1(0xa4000) */
-#define MT_WF_ETBF_BASE(_band)		((_band) ? 0x820fa000 : 0x820ea000)
-#define MT_WF_ETBF(_band, ofs)		(MT_WF_ETBF_BASE(_band) + (ofs))
-
-#define MT_ETBF_TX_APP_CNT(_band)	MT_WF_ETBF(_band, 0x150)
-#define MT_ETBF_TX_IBF_CNT		GENMASK(31, 16)
-#define MT_ETBF_TX_EBF_CNT		GENMASK(15, 0)
-
-#define MT_ETBF_RX_FB_CNT(_band)	MT_WF_ETBF(_band, 0x158)
-#define MT_ETBF_RX_FB_ALL		GENMASK(31, 24)
-#define MT_ETBF_RX_FB_HE		GENMASK(23, 16)
-#define MT_ETBF_RX_FB_VHT		GENMASK(15, 8)
-#define MT_ETBF_RX_FB_HT		GENMASK(7, 0)
-
-/* MIB: band 0(0x24800), band 1(0xa4800) */
-#define MT_WF_MIB_BASE(_band)		((_band) ? 0x820fd000 : 0x820ed000)
-#define MT_WF_MIB(_band, ofs)		(MT_WF_MIB_BASE(_band) + (ofs))
-
-#define MT_MIB_SCR1(_band)		MT_WF_MIB(_band, 0x004)
-#define MT_MIB_TXDUR_EN			BIT(8)
-#define MT_MIB_RXDUR_EN			BIT(9)
-
-#define MT_MIB_SDR3(_band)		MT_WF_MIB(_band, 0x698)
-#define MT_MIB_SDR3_FCS_ERR_MASK	GENMASK(31, 16)
-
-#define MT_MIB_SDR5(_band)		MT_WF_MIB(_band, 0x780)
-
-#define MT_MIB_SDR9(_band)		MT_WF_MIB(_band, 0x02c)
-#define MT_MIB_SDR9_BUSY_MASK		GENMASK(23, 0)
-
-#define MT_MIB_SDR12(_band)		MT_WF_MIB(_band, 0x558)
-#define MT_MIB_SDR14(_band)		MT_WF_MIB(_band, 0x564)
-#define MT_MIB_SDR15(_band)		MT_WF_MIB(_band, 0x568)
-
-#define MT_MIB_SDR16(_band)		MT_WF_MIB(_band, 0x048)
-#define MT_MIB_SDR16_BUSY_MASK		GENMASK(23, 0)
-
-#define MT_MIB_SDR22(_band)		MT_WF_MIB(_band, 0x770)
-#define MT_MIB_SDR23(_band)		MT_WF_MIB(_band, 0x774)
-#define MT_MIB_SDR31(_band)		MT_WF_MIB(_band, 0x55c)
-
-#define MT_MIB_SDR32(_band)		MT_WF_MIB(_band, 0x7a8)
-#define MT_MIB_SDR9_IBF_CNT_MASK	GENMASK(31, 16)
-#define MT_MIB_SDR9_EBF_CNT_MASK	GENMASK(15, 0)
-
-#define MT_MIB_SDR34(_band)		MT_WF_MIB(_band, 0x090)
-#define MT_MIB_MU_BF_TX_CNT		GENMASK(15, 0)
-
-#define MT_MIB_SDR36(_band)		MT_WF_MIB(_band, 0x054)
-#define MT_MIB_SDR36_TXTIME_MASK	GENMASK(23, 0)
-#define MT_MIB_SDR37(_band)		MT_WF_MIB(_band, 0x058)
-#define MT_MIB_SDR37_RXTIME_MASK	GENMASK(23, 0)
-
-#define MT_MIB_DR8(_band)		MT_WF_MIB(_band, 0x0c0)
-#define MT_MIB_DR9(_band)		MT_WF_MIB(_band, 0x0c4)
-#define MT_MIB_DR11(_band)		MT_WF_MIB(_band, 0x0cc)
-
-#define MT_MIB_MB_SDR0(_band, n)	MT_WF_MIB(_band, 0x100 + ((n) << 4))
-#define MT_MIB_RTS_RETRIES_COUNT_MASK	GENMASK(31, 16)
-
-#define MT_MIB_MB_BSDR0(_band)		MT_WF_MIB(_band, 0x688)
-#define MT_MIB_RTS_COUNT_MASK		GENMASK(15, 0)
-#define MT_MIB_MB_BSDR1(_band)		MT_WF_MIB(_band, 0x690)
-#define MT_MIB_RTS_FAIL_COUNT_MASK	GENMASK(15, 0)
-#define MT_MIB_MB_BSDR2(_band)		MT_WF_MIB(_band, 0x518)
-#define MT_MIB_BA_FAIL_COUNT_MASK	GENMASK(15, 0)
-#define MT_MIB_MB_BSDR3(_band)		MT_WF_MIB(_band, 0x520)
-#define MT_MIB_ACK_FAIL_COUNT_MASK	GENMASK(15, 0)
-
-#define MT_MIB_MB_SDR2(_band, n)	MT_WF_MIB(_band, 0x108 + ((n) << 4))
-#define MT_MIB_FRAME_RETRIES_COUNT_MASK	GENMASK(15, 0)
-
-#define MT_TX_AGG_CNT(_band, n)		MT_WF_MIB(_band, 0x7dc + ((n) << 2))
-#define MT_TX_AGG_CNT2(_band, n)	MT_WF_MIB(_band, 0x7ec + ((n) << 2))
-#define MT_MIB_ARNG(_band, n)		MT_WF_MIB(_band, 0x0b0 + ((n) << 2))
-#define MT_MIB_ARNCR_RANGE(val, n)	(((val) >> ((n) << 3)) & GENMASK(7, 0))
-
-#define MT_WTBLON_TOP_BASE		0x820d4000
-#define MT_WTBLON_TOP(ofs)		(MT_WTBLON_TOP_BASE + (ofs))
-#define MT_WTBLON_TOP_WDUCR		MT_WTBLON_TOP(0x200)
-#define MT_WTBLON_TOP_WDUCR_GROUP	GENMASK(2, 0)
-
-#define MT_WTBL_UPDATE			MT_WTBLON_TOP(0x230)
-#define MT_WTBL_UPDATE_WLAN_IDX		GENMASK(9, 0)
-#define MT_WTBL_UPDATE_ADM_COUNT_CLEAR	BIT(12)
-#define MT_WTBL_UPDATE_BUSY		BIT(31)
-
-#define MT_WTBL_BASE			0x820d8000
-#define MT_WTBL_LMAC_ID			GENMASK(14, 8)
-#define MT_WTBL_LMAC_DW			GENMASK(7, 2)
-#define MT_WTBL_LMAC_OFFS(_id, _dw)	(MT_WTBL_BASE | \
-					FIELD_PREP(MT_WTBL_LMAC_ID, _id) | \
-					FIELD_PREP(MT_WTBL_LMAC_DW, _dw))
-
-/* AGG: band 0(0x20800), band 1(0xa0800) */
-#define MT_WF_AGG_BASE(_band)		((_band) ? 0x820f2000 : 0x820e2000)
-#define MT_WF_AGG(_band, ofs)		(MT_WF_AGG_BASE(_band) + (ofs))
-
-#define MT_AGG_AWSCR0(_band, _n)	MT_WF_AGG(_band, 0x05c + (_n) * 4)
-#define MT_AGG_PCR0(_band, _n)		MT_WF_AGG(_band, 0x06c + (_n) * 4)
-#define MT_AGG_PCR0_MM_PROT		BIT(0)
-#define MT_AGG_PCR0_GF_PROT		BIT(1)
-#define MT_AGG_PCR0_BW20_PROT		BIT(2)
-#define MT_AGG_PCR0_BW40_PROT		BIT(4)
-#define MT_AGG_PCR0_BW80_PROT		BIT(6)
-#define MT_AGG_PCR0_ERP_PROT		GENMASK(12, 8)
-#define MT_AGG_PCR0_VHT_PROT		BIT(13)
-#define MT_AGG_PCR0_PTA_WIN_DIS		BIT(15)
-
-#define MT_AGG_PCR1_RTS0_NUM_THRES	GENMASK(31, 23)
-#define MT_AGG_PCR1_RTS0_LEN_THRES	GENMASK(19, 0)
-
-#define MT_AGG_ACR0(_band)		MT_WF_AGG(_band, 0x084)
-#define MT_AGG_ACR_CFEND_RATE		GENMASK(13, 0)
-#define MT_AGG_ACR_BAR_RATE		GENMASK(29, 16)
-
-#define MT_AGG_MRCR(_band)		MT_WF_AGG(_band, 0x098)
-#define MT_AGG_MRCR_BAR_CNT_LIMIT	GENMASK(15, 12)
-#define MT_AGG_MRCR_LAST_RTS_CTS_RN	BIT(6)
-#define MT_AGG_MRCR_RTS_FAIL_LIMIT	GENMASK(11, 7)
-#define MT_AGG_MRCR_TXCMD_RTS_FAIL_LIMIT	GENMASK(28, 24)
-
-#define MT_AGG_ATCR1(_band)		MT_WF_AGG(_band, 0x0f0)
-#define MT_AGG_ATCR3(_band)		MT_WF_AGG(_band, 0x0f4)
-
-/* ARB: band 0(0x20c00), band 1(0xa0c00) */
-#define MT_WF_ARB_BASE(_band)		((_band) ? 0x820f3000 : 0x820e3000)
-#define MT_WF_ARB(_band, ofs)		(MT_WF_ARB_BASE(_band) + (ofs))
-
-#define MT_ARB_SCR(_band)		MT_WF_ARB(_band, 0x080)
-#define MT_ARB_SCR_TX_DISABLE		BIT(8)
-#define MT_ARB_SCR_RX_DISABLE		BIT(9)
-
-#define MT_ARB_DRNGR0(_band, _n)	MT_WF_ARB(_band, 0x194 + (_n) * 4)
-
-/* RMAC: band 0(0x21400), band 1(0xa1400) */
-#define MT_WF_RMAC_BASE(_band)		((_band) ? 0x820f5000 : 0x820e5000)
-#define MT_WF_RMAC(_band, ofs)		(MT_WF_RMAC_BASE(_band) + (ofs))
-
-#define MT_WF_RFCR(_band)		MT_WF_RMAC(_band, 0x000)
-#define MT_WF_RFCR_DROP_STBC_MULTI	BIT(0)
-#define MT_WF_RFCR_DROP_FCSFAIL		BIT(1)
-#define MT_WF_RFCR_DROP_VERSION		BIT(3)
-#define MT_WF_RFCR_DROP_PROBEREQ	BIT(4)
-#define MT_WF_RFCR_DROP_MCAST		BIT(5)
-#define MT_WF_RFCR_DROP_BCAST		BIT(6)
-#define MT_WF_RFCR_DROP_MCAST_FILTERED	BIT(7)
-#define MT_WF_RFCR_DROP_A3_MAC		BIT(8)
-#define MT_WF_RFCR_DROP_A3_BSSID	BIT(9)
-#define MT_WF_RFCR_DROP_A2_BSSID	BIT(10)
-#define MT_WF_RFCR_DROP_OTHER_BEACON	BIT(11)
-#define MT_WF_RFCR_DROP_FRAME_REPORT	BIT(12)
-#define MT_WF_RFCR_DROP_CTL_RSV		BIT(13)
-#define MT_WF_RFCR_DROP_CTS		BIT(14)
-#define MT_WF_RFCR_DROP_RTS		BIT(15)
-#define MT_WF_RFCR_DROP_DUPLICATE	BIT(16)
-#define MT_WF_RFCR_DROP_OTHER_BSS	BIT(17)
-#define MT_WF_RFCR_DROP_OTHER_UC	BIT(18)
-#define MT_WF_RFCR_DROP_OTHER_TIM	BIT(19)
-#define MT_WF_RFCR_DROP_NDPA		BIT(20)
-#define MT_WF_RFCR_DROP_UNWANTED_CTL	BIT(21)
-
-#define MT_WF_RFCR1(_band)		MT_WF_RMAC(_band, 0x004)
-#define MT_WF_RFCR1_DROP_ACK		BIT(4)
-#define MT_WF_RFCR1_DROP_BF_POLL	BIT(5)
-#define MT_WF_RFCR1_DROP_BA		BIT(6)
-#define MT_WF_RFCR1_DROP_CFEND		BIT(7)
-#define MT_WF_RFCR1_DROP_CFACK		BIT(8)
-
-#define MT_WF_RMAC_MIB_TIME0(_band)	MT_WF_RMAC(_band, 0x03c4)
-#define MT_WF_RMAC_MIB_RXTIME_CLR	BIT(31)
-#define MT_WF_RMAC_MIB_RXTIME_EN	BIT(30)
-
-#define MT_WF_RMAC_MIB_AIRTIME14(_band)	MT_WF_RMAC(_band, 0x03b8)
-#define MT_MIB_OBSSTIME_MASK		GENMASK(23, 0)
-#define MT_WF_RMAC_MIB_AIRTIME0(_band)	MT_WF_RMAC(_band, 0x0380)
-
-/* WFDMA0 */
-#define MT_WFDMA0_BASE			0xd4000
-#define MT_WFDMA0(ofs)			(MT_WFDMA0_BASE + (ofs))
-
-#define MT_WFDMA0_RST			MT_WFDMA0(0x100)
-#define MT_WFDMA0_RST_LOGIC_RST		BIT(4)
-#define MT_WFDMA0_RST_DMASHDL_ALL_RST	BIT(5)
-
-#define MT_WFDMA0_BUSY_ENA		MT_WFDMA0(0x13c)
-#define MT_WFDMA0_BUSY_ENA_TX_FIFO0	BIT(0)
-#define MT_WFDMA0_BUSY_ENA_TX_FIFO1	BIT(1)
-#define MT_WFDMA0_BUSY_ENA_RX_FIFO	BIT(2)
-
-#define MT_MCU_CMD			MT_WFDMA0(0x1f0)
-#define MT_MCU_CMD_WAKE_RX_PCIE		BIT(0)
-#define MT_MCU_CMD_STOP_DMA_FW_RELOAD	BIT(1)
-#define MT_MCU_CMD_STOP_DMA		BIT(2)
-#define MT_MCU_CMD_RESET_DONE		BIT(3)
-#define MT_MCU_CMD_RECOVERY_DONE	BIT(4)
-#define MT_MCU_CMD_NORMAL_STATE		BIT(5)
-#define MT_MCU_CMD_ERROR_MASK		GENMASK(5, 1)
-
-#define MT_MCU2HOST_SW_INT_ENA		MT_WFDMA0(0x1f4)
-
-#define MT_WFDMA0_HOST_INT_STA		MT_WFDMA0(0x200)
-#define HOST_RX_DONE_INT_STS0		BIT(0)	/* Rx mcu */
-#define HOST_RX_DONE_INT_STS2		BIT(2)	/* Rx data */
-#define HOST_RX_DONE_INT_STS4		BIT(22)	/* Rx mcu after fw downloaded */
-#define HOST_TX_DONE_INT_STS16		BIT(26)
-#define HOST_TX_DONE_INT_STS17		BIT(27) /* MCU tx done*/
-
 #define MT_WFDMA0_HOST_INT_ENA		MT_WFDMA0(0x204)
 #define HOST_RX_DONE_INT_ENA0		BIT(0)
 #define HOST_RX_DONE_INT_ENA1		BIT(1)
@@ -354,56 +75,8 @@
 					 MT_INT_TX_DONE_BAND0 |	\
 					GENMASK(18, 4))
 
-#define MT_WFDMA0_GLO_CFG		MT_WFDMA0(0x208)
-#define MT_WFDMA0_GLO_CFG_TX_DMA_EN	BIT(0)
-#define MT_WFDMA0_GLO_CFG_TX_DMA_BUSY	BIT(1)
-#define MT_WFDMA0_GLO_CFG_RX_DMA_EN	BIT(2)
-#define MT_WFDMA0_GLO_CFG_RX_DMA_BUSY	BIT(3)
-#define MT_WFDMA0_GLO_CFG_TX_WB_DDONE	BIT(6)
-#define MT_WFDMA0_GLO_CFG_FW_DWLD_BYPASS_DMASHDL BIT(9)
-#define MT_WFDMA0_GLO_CFG_FIFO_LITTLE_ENDIAN	BIT(12)
-#define MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN BIT(15)
-#define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2	BIT(21)
-#define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO	BIT(27)
-#define MT_WFDMA0_GLO_CFG_OMIT_TX_INFO	BIT(28)
-#define MT_WFDMA0_GLO_CFG_CLK_GAT_DIS	BIT(30)
-
-#define MT_WFDMA0_RST_DTX_PTR		MT_WFDMA0(0x20c)
-#define MT_WFDMA0_GLO_CFG_EXT0		MT_WFDMA0(0x2b0)
-#define MT_WFDMA0_CSR_TX_DMASHDL_ENABLE	BIT(6)
-#define MT_WFDMA0_PRI_DLY_INT_CFG0	MT_WFDMA0(0x2f0)
-
 #define MT_RX_DATA_RING_BASE		MT_WFDMA0(0x520)
 
-#define MT_WFDMA0_TX_RING0_EXT_CTRL	MT_WFDMA0(0x600)
-#define MT_WFDMA0_TX_RING1_EXT_CTRL	MT_WFDMA0(0x604)
-#define MT_WFDMA0_TX_RING2_EXT_CTRL	MT_WFDMA0(0x608)
-#define MT_WFDMA0_TX_RING3_EXT_CTRL	MT_WFDMA0(0x60c)
-#define MT_WFDMA0_TX_RING4_EXT_CTRL	MT_WFDMA0(0x610)
-#define MT_WFDMA0_TX_RING5_EXT_CTRL	MT_WFDMA0(0x614)
-#define MT_WFDMA0_TX_RING6_EXT_CTRL	MT_WFDMA0(0x618)
-#define MT_WFDMA0_TX_RING16_EXT_CTRL	MT_WFDMA0(0x640)
-#define MT_WFDMA0_TX_RING17_EXT_CTRL	MT_WFDMA0(0x644)
-
-#define MT_WPDMA0_MAX_CNT_MASK		GENMASK(7, 0)
-#define MT_WPDMA0_BASE_PTR_MASK		GENMASK(31, 16)
-
-#define MT_WFDMA0_RX_RING0_EXT_CTRL	MT_WFDMA0(0x680)
-#define MT_WFDMA0_RX_RING1_EXT_CTRL	MT_WFDMA0(0x684)
-#define MT_WFDMA0_RX_RING2_EXT_CTRL	MT_WFDMA0(0x688)
-#define MT_WFDMA0_RX_RING3_EXT_CTRL	MT_WFDMA0(0x68c)
-#define MT_WFDMA0_RX_RING4_EXT_CTRL	MT_WFDMA0(0x690)
-#define MT_WFDMA0_RX_RING5_EXT_CTRL	MT_WFDMA0(0x694)
-
-#define MT_TX_RING_BASE			MT_WFDMA0(0x300)
-#define MT_RX_EVENT_RING_BASE		MT_WFDMA0(0x500)
-
-/* WFDMA CSR */
-#define MT_WFDMA_EXT_CSR_BASE          0xd7000
-#define MT_WFDMA_EXT_CSR(ofs)          (MT_WFDMA_EXT_CSR_BASE + (ofs))
-#define MT_WFDMA_EXT_CSR_HIF_MISC	MT_WFDMA_EXT_CSR(0x44)
-#define MT_WFDMA_EXT_CSR_HIF_MISC_BUSY	BIT(0)
-
 #define MT_INFRA_CFG_BASE		0xfe000
 #define MT_INFRA(ofs)			(MT_INFRA_CFG_BASE + (ofs))
 
@@ -413,121 +86,11 @@
 #define MT_HIF_REMAP_L1_BASE		GENMASK(31, 16)
 #define MT_HIF_REMAP_BASE_L1		0x40000
 
-#define MT_SWDEF_BASE			0x41f200
-#define MT_SWDEF(ofs)			(MT_SWDEF_BASE + (ofs))
-#define MT_SWDEF_MODE			MT_SWDEF(0x3c)
-#define MT_SWDEF_NORMAL_MODE		0
-#define MT_SWDEF_ICAP_MODE		1
-#define MT_SWDEF_SPECTRUM_MODE		2
-
-#define MT_TOP_BASE			0x18060000
-#define MT_TOP(ofs)			(MT_TOP_BASE + (ofs))
-
-#define MT_TOP_LPCR_HOST_BAND0		MT_TOP(0x10)
-#define MT_TOP_LPCR_HOST_FW_OWN		BIT(0)
-#define MT_TOP_LPCR_HOST_DRV_OWN	BIT(1)
-
-#define MT_TOP_MISC			MT_TOP(0xf0)
-#define MT_TOP_MISC_FW_STATE		GENMASK(2, 0)
-
-#define MT_MCU_WPDMA0_BASE		0x54000000
-#define MT_MCU_WPDMA0(ofs)		(MT_MCU_WPDMA0_BASE + (ofs))
-
-#define MT_WFDMA_DUMMY_CR		MT_MCU_WPDMA0(0x120)
-#define MT_WFDMA_NEED_REINIT		BIT(1)
-
-#define MT_CBTOP_RGU(ofs)		(0x70002000 + (ofs))
-#define MT_CBTOP_RGU_WF_SUBSYS_RST	MT_CBTOP_RGU(0x600)
-#define MT_CBTOP_RGU_WF_SUBSYS_RST_WF_WHOLE_PATH BIT(0)
-
-#define MT_HW_BOUND			0x70010020
-#define MT_HW_CHIPID			0x70010200
-#define MT_HW_REV			0x70010204
-
-#define MT_PCIE_MAC_BASE		0x10000
-#define MT_PCIE_MAC(ofs)		(MT_PCIE_MAC_BASE + (ofs))
-#define MT_PCIE_MAC_INT_ENABLE		MT_PCIE_MAC(0x188)
-#define MT_PCIE_MAC_PM			MT_PCIE_MAC(0x194)
-#define MT_PCIE_MAC_PM_L0S_DIS		BIT(8)
-
-#define MT_DMA_SHDL(ofs)		(0x7c026000 + (ofs))
-#define MT_DMASHDL_SW_CONTROL		MT_DMA_SHDL(0x004)
-#define MT_DMASHDL_DMASHDL_BYPASS	BIT(28)
-#define MT_DMASHDL_OPTIONAL		MT_DMA_SHDL(0x008)
-#define MT_DMASHDL_PAGE			MT_DMA_SHDL(0x00c)
-#define MT_DMASHDL_GROUP_SEQ_ORDER	BIT(16)
-#define MT_DMASHDL_REFILL		MT_DMA_SHDL(0x010)
-#define MT_DMASHDL_REFILL_MASK		GENMASK(31, 16)
-#define MT_DMASHDL_PKT_MAX_SIZE		MT_DMA_SHDL(0x01c)
-#define MT_DMASHDL_PKT_MAX_SIZE_PLE	GENMASK(11, 0)
-#define MT_DMASHDL_PKT_MAX_SIZE_PSE	GENMASK(27, 16)
-
-#define MT_DMASHDL_GROUP_QUOTA(_n)	MT_DMA_SHDL(0x020 + ((_n) << 2))
-#define MT_DMASHDL_GROUP_QUOTA_MIN	GENMASK(11, 0)
-#define MT_DMASHDL_GROUP_QUOTA_MAX	GENMASK(27, 16)
-
-#define MT_DMASHDL_Q_MAP(_n)		MT_DMA_SHDL(0x060 + ((_n) << 2))
-#define MT_DMASHDL_Q_MAP_MASK		GENMASK(3, 0)
-#define MT_DMASHDL_Q_MAP_SHIFT(_n)	(4 * ((_n) % 8))
-
-#define MT_DMASHDL_SCHED_SET(_n)	MT_DMA_SHDL(0x070 + ((_n) << 2))
-
-#define MT_WFDMA_HOST_CONFIG		0x7c027030
-#define MT_WFDMA_HOST_CONFIG_USB_RXEVT_EP4_EN	BIT(6)
-
-#define MT_UMAC(ofs)			(0x74000000 + (ofs))
-#define MT_UDMA_TX_QSEL			MT_UMAC(0x008)
-#define MT_FW_DL_EN			BIT(3)
-
-#define MT_UDMA_WLCFG_1			MT_UMAC(0x00c)
-#define MT_WL_RX_AGG_PKT_LMT		GENMASK(7, 0)
-#define MT_WL_TX_TMOUT_LMT		GENMASK(27, 8)
-
-#define MT_UDMA_WLCFG_0			MT_UMAC(0x18)
-#define MT_WL_RX_AGG_TO			GENMASK(7, 0)
-#define MT_WL_RX_AGG_LMT		GENMASK(15, 8)
-#define MT_WL_TX_TMOUT_FUNC_EN		BIT(16)
-#define MT_WL_TX_DPH_CHK_EN		BIT(17)
-#define MT_WL_RX_MPSZ_PAD0		BIT(18)
-#define MT_WL_RX_FLUSH			BIT(19)
-#define MT_TICK_1US_EN			BIT(20)
-#define MT_WL_RX_AGG_EN			BIT(21)
-#define MT_WL_RX_EN			BIT(22)
-#define MT_WL_TX_EN			BIT(23)
-#define MT_WL_RX_BUSY			BIT(30)
-#define MT_WL_TX_BUSY			BIT(31)
-
-#define MT_UDMA_CONN_INFRA_STATUS	MT_UMAC(0xa20)
-#define MT_UDMA_CONN_WFSYS_INIT_DONE	BIT(22)
-#define MT_UDMA_CONN_INFRA_STATUS_SEL	MT_UMAC(0xa24)
-
-#define MT_SSUSB_EPCTL_CSR(ofs)		(0x74011800 + (ofs))
-#define MT_SSUSB_EPCTL_CSR_EP_RST_OPT	MT_SSUSB_EPCTL_CSR(0x090)
-
-#define MT_UWFDMA0(ofs)			(0x7c024000 + (ofs))
-#define MT_UWFDMA0_GLO_CFG		MT_UWFDMA0(0x208)
-#define MT_UWFDMA0_GLO_CFG_EXT0		MT_UWFDMA0(0x2b0)
-#define MT_UWFDMA0_TX_RING_EXT_CTRL(_n)	MT_UWFDMA0(0x600 + ((_n) << 2))
-
-#define MT_CONN_STATUS			0x7c053c10
-#define MT_WIFI_PATCH_DL_STATE		BIT(0)
-
-#define MT_CONN_ON_LPCTL		0x7c060010
-#define PCIE_LPCR_HOST_OWN_SYNC		BIT(2)
-#define PCIE_LPCR_HOST_CLR_OWN		BIT(1)
-#define PCIE_LPCR_HOST_SET_OWN		BIT(0)
-
 #define MT_WFSYS_SW_RST_B		0x18000140
 #define WFSYS_SW_RST_B			BIT(0)
 #define WFSYS_SW_INIT_DONE		BIT(4)
 
-#define MT_CONN_ON_MISC			0x7c0600f0
-#define MT_TOP_MISC2_FW_PWR_ON		BIT(0)
-#define MT_TOP_MISC2_FW_N9_RDY		GENMASK(1, 0)
-
-#define MT_WF_SW_DEF_CR(ofs)		(0x401a00 + (ofs))
-#define MT_WF_SW_DEF_CR_USB_MCU_EVENT	MT_WF_SW_DEF_CR(0x028)
-#define MT_WF_SW_SER_TRIGGER_SUSPEND	BIT(6)
-#define MT_WF_SW_SER_DONE_SUSPEND	BIT(7)
+#define MT_WTBLON_TOP_WDUCR		MT_WTBLON_TOP(0x200)
+#define MT_WTBLON_TOP_WDUCR_GROUP	GENMASK(2, 0)
 
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
new file mode 100644
index 0000000000000..aa6a677427a4d
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
@@ -0,0 +1,460 @@
+/* SPDX-License-Identifier: ISC */
+/* Copyright (C) 2023 MediaTek Inc. */
+
+#ifndef __MT792X_REGS_H
+#define __MT792X_REGS_H
+
+/* MCU WFDMA1 */
+#define MT_MCU_WFDMA1_BASE		0x3000
+#define MT_MCU_WFDMA1(ofs)		(MT_MCU_WFDMA1_BASE + (ofs))
+
+#define MT_MCU_INT_EVENT		MT_MCU_WFDMA1(0x108)
+#define MT_MCU_INT_EVENT_DMA_STOPPED	BIT(0)
+#define MT_MCU_INT_EVENT_DMA_INIT	BIT(1)
+#define MT_MCU_INT_EVENT_SER_TRIGGER	BIT(2)
+#define MT_MCU_INT_EVENT_RESET_DONE	BIT(3)
+
+#define MT_PLE_BASE			0x820c0000
+#define MT_PLE(ofs)			(MT_PLE_BASE + (ofs))
+
+#define MT_PLE_FL_Q0_CTRL		MT_PLE(0x3e0)
+#define MT_PLE_FL_Q1_CTRL		MT_PLE(0x3e4)
+#define MT_PLE_FL_Q2_CTRL		MT_PLE(0x3e8)
+#define MT_PLE_FL_Q3_CTRL		MT_PLE(0x3ec)
+
+#define MT_PLE_AC_QEMPTY(_n)		MT_PLE(0x500 + 0x40 * (_n))
+#define MT_PLE_AMSDU_PACK_MSDU_CNT(n)	MT_PLE(0x10e0 + ((n) << 2))
+
+/* TMAC: band 0(0x21000), band 1(0xa1000) */
+#define MT_WF_TMAC_BASE(_band)		((_band) ? 0x820f4000 : 0x820e4000)
+#define MT_WF_TMAC(_band, ofs)		(MT_WF_TMAC_BASE(_band) + (ofs))
+
+#define MT_TMAC_TCR0(_band)		MT_WF_TMAC(_band, 0)
+#define MT_TMAC_TCR0_TBTT_STOP_CTRL	BIT(25)
+
+#define MT_TMAC_CDTR(_band)		MT_WF_TMAC(_band, 0x090)
+#define MT_TMAC_ODTR(_band)		MT_WF_TMAC(_band, 0x094)
+#define MT_TIMEOUT_VAL_PLCP		GENMASK(15, 0)
+#define MT_TIMEOUT_VAL_CCA		GENMASK(31, 16)
+
+#define MT_TMAC_ICR0(_band)		MT_WF_TMAC(_band, 0x0a4)
+#define MT_IFS_EIFS			GENMASK(8, 0)
+#define MT_IFS_RIFS			GENMASK(14, 10)
+#define MT_IFS_SIFS			GENMASK(22, 16)
+#define MT_IFS_SLOT			GENMASK(30, 24)
+
+#define MT_TMAC_CTCR0(_band)			MT_WF_TMAC(_band, 0x0f4)
+#define MT_TMAC_CTCR0_INS_DDLMT_REFTIME		GENMASK(5, 0)
+#define MT_TMAC_CTCR0_INS_DDLMT_EN		BIT(17)
+#define MT_TMAC_CTCR0_INS_DDLMT_VHT_SMPDU_EN	BIT(18)
+
+#define MT_TMAC_TRCR0(_band)		MT_WF_TMAC(_band, 0x09c)
+#define MT_TMAC_TFCR0(_band)		MT_WF_TMAC(_band, 0x1e0)
+
+#define MT_WF_DMA_BASE(_band)		((_band) ? 0x820f7000 : 0x820e7000)
+#define MT_WF_DMA(_band, ofs)		(MT_WF_DMA_BASE(_band) + (ofs))
+
+#define MT_DMA_DCR0(_band)		MT_WF_DMA(_band, 0x000)
+#define MT_DMA_DCR0_MAX_RX_LEN		GENMASK(15, 3)
+#define MT_DMA_DCR0_RXD_G5_EN		BIT(23)
+
+/* WTBLOFF TOP: band 0(0x820e9000),band 1(0x820f9000) */
+#define MT_WTBLOFF_TOP_BASE(_band)	((_band) ? 0x820f9000 : 0x820e9000)
+#define MT_WTBLOFF_TOP(_band, ofs)	(MT_WTBLOFF_TOP_BASE(_band) + (ofs))
+
+#define MT_WTBLOFF_TOP_RSCR(_band)	MT_WTBLOFF_TOP(_band, 0x008)
+#define MT_WTBLOFF_TOP_RSCR_RCPI_MODE	GENMASK(31, 30)
+#define MT_WTBLOFF_TOP_RSCR_RCPI_PARAM	GENMASK(25, 24)
+
+/* LPON: band 0(0x24200), band 1(0xa4200) */
+#define MT_WF_LPON_BASE(_band)		((_band) ? 0x820fb000 : 0x820eb000)
+#define MT_WF_LPON(_band, ofs)		(MT_WF_LPON_BASE(_band) + (ofs))
+
+#define MT_LPON_UTTR0(_band)		MT_WF_LPON(_band, 0x080)
+#define MT_LPON_UTTR1(_band)		MT_WF_LPON(_band, 0x084)
+
+#define MT_LPON_TCR(_band, n)		MT_WF_LPON(_band, 0x0a8 + (n) * 4)
+#define MT_LPON_TCR_SW_MODE		GENMASK(1, 0)
+#define MT_LPON_TCR_SW_WRITE		BIT(0)
+
+/* ETBF: band 0(0x24000), band 1(0xa4000) */
+#define MT_WF_ETBF_BASE(_band)		((_band) ? 0x820fa000 : 0x820ea000)
+#define MT_WF_ETBF(_band, ofs)		(MT_WF_ETBF_BASE(_band) + (ofs))
+
+#define MT_ETBF_TX_APP_CNT(_band)	MT_WF_ETBF(_band, 0x150)
+#define MT_ETBF_TX_IBF_CNT		GENMASK(31, 16)
+#define MT_ETBF_TX_EBF_CNT		GENMASK(15, 0)
+
+#define MT_ETBF_RX_FB_CNT(_band)	MT_WF_ETBF(_band, 0x158)
+#define MT_ETBF_RX_FB_ALL		GENMASK(31, 24)
+#define MT_ETBF_RX_FB_HE		GENMASK(23, 16)
+#define MT_ETBF_RX_FB_VHT		GENMASK(15, 8)
+#define MT_ETBF_RX_FB_HT		GENMASK(7, 0)
+
+/* MIB: band 0(0x24800), band 1(0xa4800) */
+#define MT_WF_MIB_BASE(_band)		((_band) ? 0x820fd000 : 0x820ed000)
+#define MT_WF_MIB(_band, ofs)		(MT_WF_MIB_BASE(_band) + (ofs))
+
+#define MT_MIB_SCR1(_band)		MT_WF_MIB(_band, 0x004)
+#define MT_MIB_TXDUR_EN			BIT(8)
+#define MT_MIB_RXDUR_EN			BIT(9)
+
+#define MT_MIB_SDR3(_band)		MT_WF_MIB(_band, 0x698)
+#define MT_MIB_SDR3_FCS_ERR_MASK	GENMASK(31, 16)
+
+#define MT_MIB_SDR5(_band)		MT_WF_MIB(_band, 0x780)
+
+#define MT_MIB_SDR9(_band)		MT_WF_MIB(_band, 0x02c)
+#define MT_MIB_SDR9_BUSY_MASK		GENMASK(23, 0)
+
+#define MT_MIB_SDR12(_band)		MT_WF_MIB(_band, 0x558)
+#define MT_MIB_SDR14(_band)		MT_WF_MIB(_band, 0x564)
+#define MT_MIB_SDR15(_band)		MT_WF_MIB(_band, 0x568)
+
+#define MT_MIB_SDR16(_band)		MT_WF_MIB(_band, 0x048)
+#define MT_MIB_SDR16_BUSY_MASK		GENMASK(23, 0)
+
+#define MT_MIB_SDR22(_band)		MT_WF_MIB(_band, 0x770)
+#define MT_MIB_SDR23(_band)		MT_WF_MIB(_band, 0x774)
+#define MT_MIB_SDR31(_band)		MT_WF_MIB(_band, 0x55c)
+
+#define MT_MIB_SDR32(_band)		MT_WF_MIB(_band, 0x7a8)
+#define MT_MIB_SDR9_IBF_CNT_MASK	GENMASK(31, 16)
+#define MT_MIB_SDR9_EBF_CNT_MASK	GENMASK(15, 0)
+
+#define MT_MIB_SDR34(_band)		MT_WF_MIB(_band, 0x090)
+#define MT_MIB_MU_BF_TX_CNT		GENMASK(15, 0)
+
+#define MT_MIB_SDR36(_band)		MT_WF_MIB(_band, 0x054)
+#define MT_MIB_SDR36_TXTIME_MASK	GENMASK(23, 0)
+#define MT_MIB_SDR37(_band)		MT_WF_MIB(_band, 0x058)
+#define MT_MIB_SDR37_RXTIME_MASK	GENMASK(23, 0)
+
+#define MT_MIB_DR8(_band)		MT_WF_MIB(_band, 0x0c0)
+#define MT_MIB_DR9(_band)		MT_WF_MIB(_band, 0x0c4)
+#define MT_MIB_DR11(_band)		MT_WF_MIB(_band, 0x0cc)
+
+#define MT_MIB_MB_SDR0(_band, n)	MT_WF_MIB(_band, 0x100 + ((n) << 4))
+#define MT_MIB_RTS_RETRIES_COUNT_MASK	GENMASK(31, 16)
+
+#define MT_MIB_MB_BSDR0(_band)		MT_WF_MIB(_band, 0x688)
+#define MT_MIB_RTS_COUNT_MASK		GENMASK(15, 0)
+#define MT_MIB_MB_BSDR1(_band)		MT_WF_MIB(_band, 0x690)
+#define MT_MIB_RTS_FAIL_COUNT_MASK	GENMASK(15, 0)
+#define MT_MIB_MB_BSDR2(_band)		MT_WF_MIB(_band, 0x518)
+#define MT_MIB_BA_FAIL_COUNT_MASK	GENMASK(15, 0)
+#define MT_MIB_MB_BSDR3(_band)		MT_WF_MIB(_band, 0x520)
+#define MT_MIB_ACK_FAIL_COUNT_MASK	GENMASK(15, 0)
+
+#define MT_MIB_MB_SDR2(_band, n)	MT_WF_MIB(_band, 0x108 + ((n) << 4))
+#define MT_MIB_FRAME_RETRIES_COUNT_MASK	GENMASK(15, 0)
+
+#define MT_TX_AGG_CNT(_band, n)		MT_WF_MIB(_band, 0x7dc + ((n) << 2))
+#define MT_TX_AGG_CNT2(_band, n)	MT_WF_MIB(_band, 0x7ec + ((n) << 2))
+#define MT_MIB_ARNG(_band, n)		MT_WF_MIB(_band, 0x0b0 + ((n) << 2))
+#define MT_MIB_ARNCR_RANGE(val, n)	(((val) >> ((n) << 3)) & GENMASK(7, 0))
+
+#define MT_WTBLON_TOP_BASE		0x820d4000
+#define MT_WTBLON_TOP(ofs)		(MT_WTBLON_TOP_BASE + (ofs))
+
+#define MT_WTBL_UPDATE			MT_WTBLON_TOP(0x230)
+#define MT_WTBL_UPDATE_WLAN_IDX		GENMASK(9, 0)
+#define MT_WTBL_UPDATE_ADM_COUNT_CLEAR	BIT(12)
+#define MT_WTBL_UPDATE_BUSY		BIT(31)
+
+#define MT_WTBL_ITCR			MT_WTBLON_TOP(0x3b0)
+#define MT_WTBL_ITCR_WR			BIT(16)
+#define MT_WTBL_ITCR_EXEC		BIT(31)
+#define MT_WTBL_ITDR0			MT_WTBLON_TOP(0x3b8)
+#define MT_WTBL_ITDR1			MT_WTBLON_TOP(0x3bc)
+#define MT_WTBL_SPE_IDX_SEL		BIT(6)
+
+#define MT_WTBL_BASE			0x820d8000
+#define MT_WTBL_LMAC_ID			GENMASK(14, 8)
+#define MT_WTBL_LMAC_DW			GENMASK(7, 2)
+#define MT_WTBL_LMAC_OFFS(_id, _dw)	(MT_WTBL_BASE | \
+					 FIELD_PREP(MT_WTBL_LMAC_ID, _id) | \
+					 FIELD_PREP(MT_WTBL_LMAC_DW, _dw))
+
+/* AGG: band 0(0x20800), band 1(0xa0800) */
+#define MT_WF_AGG_BASE(_band)		((_band) ? 0x820f2000 : 0x820e2000)
+#define MT_WF_AGG(_band, ofs)		(MT_WF_AGG_BASE(_band) + (ofs))
+
+#define MT_AGG_AWSCR0(_band, _n)	MT_WF_AGG(_band, 0x05c + (_n) * 4)
+#define MT_AGG_PCR0(_band, _n)		MT_WF_AGG(_band, 0x06c + (_n) * 4)
+#define MT_AGG_PCR0_MM_PROT		BIT(0)
+#define MT_AGG_PCR0_GF_PROT		BIT(1)
+#define MT_AGG_PCR0_BW20_PROT		BIT(2)
+#define MT_AGG_PCR0_BW40_PROT		BIT(4)
+#define MT_AGG_PCR0_BW80_PROT		BIT(6)
+#define MT_AGG_PCR0_ERP_PROT		GENMASK(12, 8)
+#define MT_AGG_PCR0_VHT_PROT		BIT(13)
+#define MT_AGG_PCR0_PTA_WIN_DIS		BIT(15)
+
+#define MT_AGG_PCR1_RTS0_NUM_THRES	GENMASK(31, 23)
+#define MT_AGG_PCR1_RTS0_LEN_THRES	GENMASK(19, 0)
+
+#define MT_AGG_ACR0(_band)		MT_WF_AGG(_band, 0x084)
+#define MT_AGG_ACR_CFEND_RATE		GENMASK(13, 0)
+#define MT_AGG_ACR_BAR_RATE		GENMASK(29, 16)
+
+#define MT_AGG_MRCR(_band)		MT_WF_AGG(_band, 0x098)
+#define MT_AGG_MRCR_BAR_CNT_LIMIT	GENMASK(15, 12)
+#define MT_AGG_MRCR_LAST_RTS_CTS_RN	BIT(6)
+#define MT_AGG_MRCR_RTS_FAIL_LIMIT	GENMASK(11, 7)
+#define MT_AGG_MRCR_TXCMD_RTS_FAIL_LIMIT	GENMASK(28, 24)
+
+#define MT_AGG_ATCR1(_band)		MT_WF_AGG(_band, 0x0f0)
+#define MT_AGG_ATCR3(_band)		MT_WF_AGG(_band, 0x0f4)
+
+/* ARB: band 0(0x20c00), band 1(0xa0c00) */
+#define MT_WF_ARB_BASE(_band)		((_band) ? 0x820f3000 : 0x820e3000)
+#define MT_WF_ARB(_band, ofs)		(MT_WF_ARB_BASE(_band) + (ofs))
+
+#define MT_ARB_SCR(_band)		MT_WF_ARB(_band, 0x080)
+#define MT_ARB_SCR_TX_DISABLE		BIT(8)
+#define MT_ARB_SCR_RX_DISABLE		BIT(9)
+
+#define MT_ARB_DRNGR0(_band, _n)	MT_WF_ARB(_band, 0x194 + (_n) * 4)
+
+/* RMAC: band 0(0x21400), band 1(0xa1400) */
+#define MT_WF_RMAC_BASE(_band)		((_band) ? 0x820f5000 : 0x820e5000)
+#define MT_WF_RMAC(_band, ofs)		(MT_WF_RMAC_BASE(_band) + (ofs))
+
+#define MT_WF_RFCR(_band)		MT_WF_RMAC(_band, 0x000)
+#define MT_WF_RFCR_DROP_STBC_MULTI	BIT(0)
+#define MT_WF_RFCR_DROP_FCSFAIL		BIT(1)
+#define MT_WF_RFCR_DROP_VERSION		BIT(3)
+#define MT_WF_RFCR_DROP_PROBEREQ	BIT(4)
+#define MT_WF_RFCR_DROP_MCAST		BIT(5)
+#define MT_WF_RFCR_DROP_BCAST		BIT(6)
+#define MT_WF_RFCR_DROP_MCAST_FILTERED	BIT(7)
+#define MT_WF_RFCR_DROP_A3_MAC		BIT(8)
+#define MT_WF_RFCR_DROP_A3_BSSID	BIT(9)
+#define MT_WF_RFCR_DROP_A2_BSSID	BIT(10)
+#define MT_WF_RFCR_DROP_OTHER_BEACON	BIT(11)
+#define MT_WF_RFCR_DROP_FRAME_REPORT	BIT(12)
+#define MT_WF_RFCR_DROP_CTL_RSV		BIT(13)
+#define MT_WF_RFCR_DROP_CTS		BIT(14)
+#define MT_WF_RFCR_DROP_RTS		BIT(15)
+#define MT_WF_RFCR_DROP_DUPLICATE	BIT(16)
+#define MT_WF_RFCR_DROP_OTHER_BSS	BIT(17)
+#define MT_WF_RFCR_DROP_OTHER_UC	BIT(18)
+#define MT_WF_RFCR_DROP_OTHER_TIM	BIT(19)
+#define MT_WF_RFCR_DROP_NDPA		BIT(20)
+#define MT_WF_RFCR_DROP_UNWANTED_CTL	BIT(21)
+
+#define MT_WF_RFCR1(_band)		MT_WF_RMAC(_band, 0x004)
+#define MT_WF_RFCR1_DROP_ACK		BIT(4)
+#define MT_WF_RFCR1_DROP_BF_POLL	BIT(5)
+#define MT_WF_RFCR1_DROP_BA		BIT(6)
+#define MT_WF_RFCR1_DROP_CFEND		BIT(7)
+#define MT_WF_RFCR1_DROP_CFACK		BIT(8)
+
+#define MT_WF_RMAC_MIB_TIME0(_band)	MT_WF_RMAC(_band, 0x03c4)
+#define MT_WF_RMAC_MIB_RXTIME_CLR	BIT(31)
+#define MT_WF_RMAC_MIB_RXTIME_EN	BIT(30)
+
+#define MT_WF_RMAC_MIB_AIRTIME14(_band)	MT_WF_RMAC(_band, 0x03b8)
+#define MT_MIB_OBSSTIME_MASK		GENMASK(23, 0)
+#define MT_WF_RMAC_MIB_AIRTIME0(_band)	MT_WF_RMAC(_band, 0x0380)
+
+/* WFDMA0 */
+#define MT_WFDMA0_BASE			0xd4000
+#define MT_WFDMA0(ofs)			(MT_WFDMA0_BASE + (ofs))
+
+#define MT_WFDMA0_RST			MT_WFDMA0(0x100)
+#define MT_WFDMA0_RST_LOGIC_RST		BIT(4)
+#define MT_WFDMA0_RST_DMASHDL_ALL_RST	BIT(5)
+
+#define MT_WFDMA0_BUSY_ENA		MT_WFDMA0(0x13c)
+#define MT_WFDMA0_BUSY_ENA_TX_FIFO0	BIT(0)
+#define MT_WFDMA0_BUSY_ENA_TX_FIFO1	BIT(1)
+#define MT_WFDMA0_BUSY_ENA_RX_FIFO	BIT(2)
+
+#define MT_MCU_CMD			MT_WFDMA0(0x1f0)
+#define MT_MCU_CMD_WAKE_RX_PCIE		BIT(0)
+#define MT_MCU_CMD_STOP_DMA_FW_RELOAD	BIT(1)
+#define MT_MCU_CMD_STOP_DMA		BIT(2)
+#define MT_MCU_CMD_RESET_DONE		BIT(3)
+#define MT_MCU_CMD_RECOVERY_DONE	BIT(4)
+#define MT_MCU_CMD_NORMAL_STATE		BIT(5)
+#define MT_MCU_CMD_ERROR_MASK		GENMASK(5, 1)
+
+#define MT_MCU2HOST_SW_INT_ENA		MT_WFDMA0(0x1f4)
+
+#define MT_WFDMA0_HOST_INT_STA		MT_WFDMA0(0x200)
+#define HOST_RX_DONE_INT_STS0		BIT(0)	/* Rx mcu */
+#define HOST_RX_DONE_INT_STS2		BIT(2)	/* Rx data */
+#define HOST_RX_DONE_INT_STS4		BIT(22)	/* Rx mcu after fw downloaded */
+#define HOST_TX_DONE_INT_STS16		BIT(26)
+#define HOST_TX_DONE_INT_STS17		BIT(27) /* MCU tx done*/
+
+#define MT_WFDMA0_GLO_CFG		MT_WFDMA0(0x208)
+#define MT_WFDMA0_GLO_CFG_TX_DMA_EN	BIT(0)
+#define MT_WFDMA0_GLO_CFG_TX_DMA_BUSY	BIT(1)
+#define MT_WFDMA0_GLO_CFG_RX_DMA_EN	BIT(2)
+#define MT_WFDMA0_GLO_CFG_RX_DMA_BUSY	BIT(3)
+#define MT_WFDMA0_GLO_CFG_TX_WB_DDONE	BIT(6)
+#define MT_WFDMA0_GLO_CFG_FW_DWLD_BYPASS_DMASHDL BIT(9)
+#define MT_WFDMA0_GLO_CFG_FIFO_LITTLE_ENDIAN	BIT(12)
+#define MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN BIT(15)
+#define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2	BIT(21)
+#define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO	BIT(27)
+#define MT_WFDMA0_GLO_CFG_OMIT_TX_INFO	BIT(28)
+#define MT_WFDMA0_GLO_CFG_CLK_GAT_DIS	BIT(30)
+
+#define MT_WFDMA0_RST_DTX_PTR		MT_WFDMA0(0x20c)
+#define MT_WFDMA0_RST_DRX_PTR		MT_WFDMA0(0x280)
+#define MT_WFDMA0_GLO_CFG_EXT0		MT_WFDMA0(0x2b0)
+#define MT_WFDMA0_CSR_TX_DMASHDL_ENABLE	BIT(6)
+#define MT_WFDMA0_PRI_DLY_INT_CFG0	MT_WFDMA0(0x2f0)
+
+#define MT_WFDMA0_TX_RING0_EXT_CTRL	MT_WFDMA0(0x600)
+#define MT_WFDMA0_TX_RING1_EXT_CTRL	MT_WFDMA0(0x604)
+#define MT_WFDMA0_TX_RING2_EXT_CTRL	MT_WFDMA0(0x608)
+#define MT_WFDMA0_TX_RING3_EXT_CTRL	MT_WFDMA0(0x60c)
+#define MT_WFDMA0_TX_RING4_EXT_CTRL	MT_WFDMA0(0x610)
+#define MT_WFDMA0_TX_RING5_EXT_CTRL	MT_WFDMA0(0x614)
+#define MT_WFDMA0_TX_RING6_EXT_CTRL	MT_WFDMA0(0x618)
+#define MT_WFDMA0_TX_RING15_EXT_CTRL	MT_WFDMA0(0x63c)
+#define MT_WFDMA0_TX_RING16_EXT_CTRL	MT_WFDMA0(0x640)
+#define MT_WFDMA0_TX_RING17_EXT_CTRL	MT_WFDMA0(0x644)
+
+#define MT_WPDMA0_MAX_CNT_MASK		GENMASK(7, 0)
+#define MT_WPDMA0_BASE_PTR_MASK		GENMASK(31, 16)
+
+#define MT_WFDMA0_RX_RING0_EXT_CTRL	MT_WFDMA0(0x680)
+#define MT_WFDMA0_RX_RING1_EXT_CTRL	MT_WFDMA0(0x684)
+#define MT_WFDMA0_RX_RING2_EXT_CTRL	MT_WFDMA0(0x688)
+#define MT_WFDMA0_RX_RING3_EXT_CTRL	MT_WFDMA0(0x68c)
+#define MT_WFDMA0_RX_RING4_EXT_CTRL	MT_WFDMA0(0x690)
+#define MT_WFDMA0_RX_RING5_EXT_CTRL	MT_WFDMA0(0x694)
+#define MT_WFDMA0_RX_RING6_EXT_CTRL	MT_WFDMA0(0x698)
+#define MT_WFDMA0_RX_RING7_EXT_CTRL	MT_WFDMA0(0x69c)
+
+#define MT_TX_RING_BASE			MT_WFDMA0(0x300)
+#define MT_RX_EVENT_RING_BASE		MT_WFDMA0(0x500)
+
+/* WFDMA CSR */
+#define MT_WFDMA_EXT_CSR_BASE          0xd7000
+#define MT_WFDMA_EXT_CSR(ofs)          (MT_WFDMA_EXT_CSR_BASE + (ofs))
+#define MT_WFDMA_EXT_CSR_HIF_MISC	MT_WFDMA_EXT_CSR(0x44)
+#define MT_WFDMA_EXT_CSR_HIF_MISC_BUSY	BIT(0)
+
+#define MT_SWDEF_BASE			0x41f200
+#define MT_SWDEF(ofs)			(MT_SWDEF_BASE + (ofs))
+#define MT_SWDEF_MODE			MT_SWDEF(0x3c)
+#define MT_SWDEF_NORMAL_MODE		0
+#define MT_SWDEF_ICAP_MODE		1
+#define MT_SWDEF_SPECTRUM_MODE		2
+
+#define MT_TOP_BASE			0x18060000
+#define MT_TOP(ofs)			(MT_TOP_BASE + (ofs))
+
+#define MT_TOP_LPCR_HOST_BAND0		MT_TOP(0x10)
+#define MT_TOP_LPCR_HOST_FW_OWN		BIT(0)
+#define MT_TOP_LPCR_HOST_DRV_OWN	BIT(1)
+
+#define MT_TOP_MISC			MT_TOP(0xf0)
+#define MT_TOP_MISC_FW_STATE		GENMASK(2, 0)
+
+#define MT_MCU_WPDMA0_BASE		0x54000000
+#define MT_MCU_WPDMA0(ofs)		(MT_MCU_WPDMA0_BASE + (ofs))
+
+#define MT_WFDMA_DUMMY_CR		MT_MCU_WPDMA0(0x120)
+#define MT_WFDMA_NEED_REINIT		BIT(1)
+
+#define MT_CBTOP_RGU(ofs)		(0x70002000 + (ofs))
+#define MT_CBTOP_RGU_WF_SUBSYS_RST	MT_CBTOP_RGU(0x600)
+#define MT_CBTOP_RGU_WF_SUBSYS_RST_WF_WHOLE_PATH BIT(0)
+
+#define MT_HW_BOUND			0x70010020
+#define MT_HW_CHIPID			0x70010200
+#define MT_HW_REV			0x70010204
+
+#define MT_PCIE_MAC_BASE		0x10000
+#define MT_PCIE_MAC(ofs)		(MT_PCIE_MAC_BASE + (ofs))
+#define MT_PCIE_MAC_INT_ENABLE		MT_PCIE_MAC(0x188)
+#define MT_PCIE_MAC_PM			MT_PCIE_MAC(0x194)
+#define MT_PCIE_MAC_PM_L0S_DIS		BIT(8)
+
+#define MT_DMA_SHDL(ofs)		(0x7c026000 + (ofs))
+#define MT_DMASHDL_SW_CONTROL		MT_DMA_SHDL(0x004)
+#define MT_DMASHDL_DMASHDL_BYPASS	BIT(28)
+#define MT_DMASHDL_OPTIONAL		MT_DMA_SHDL(0x008)
+#define MT_DMASHDL_PAGE			MT_DMA_SHDL(0x00c)
+#define MT_DMASHDL_GROUP_SEQ_ORDER	BIT(16)
+#define MT_DMASHDL_REFILL		MT_DMA_SHDL(0x010)
+#define MT_DMASHDL_REFILL_MASK		GENMASK(31, 16)
+#define MT_DMASHDL_PKT_MAX_SIZE		MT_DMA_SHDL(0x01c)
+#define MT_DMASHDL_PKT_MAX_SIZE_PLE	GENMASK(11, 0)
+#define MT_DMASHDL_PKT_MAX_SIZE_PSE	GENMASK(27, 16)
+
+#define MT_DMASHDL_GROUP_QUOTA(_n)	MT_DMA_SHDL(0x020 + ((_n) << 2))
+#define MT_DMASHDL_GROUP_QUOTA_MIN	GENMASK(11, 0)
+#define MT_DMASHDL_GROUP_QUOTA_MAX	GENMASK(27, 16)
+
+#define MT_DMASHDL_Q_MAP(_n)		MT_DMA_SHDL(0x060 + ((_n) << 2))
+#define MT_DMASHDL_Q_MAP_MASK		GENMASK(3, 0)
+#define MT_DMASHDL_Q_MAP_SHIFT(_n)	(4 * ((_n) % 8))
+
+#define MT_DMASHDL_SCHED_SET(_n)	MT_DMA_SHDL(0x070 + ((_n) << 2))
+
+#define MT_WFDMA_HOST_CONFIG		0x7c027030
+#define MT_WFDMA_HOST_CONFIG_USB_RXEVT_EP4_EN	BIT(6)
+
+#define MT_UMAC(ofs)			(0x74000000 + (ofs))
+#define MT_UDMA_TX_QSEL			MT_UMAC(0x008)
+#define MT_FW_DL_EN			BIT(3)
+
+#define MT_UDMA_WLCFG_1			MT_UMAC(0x00c)
+#define MT_WL_RX_AGG_PKT_LMT		GENMASK(7, 0)
+#define MT_WL_TX_TMOUT_LMT		GENMASK(27, 8)
+
+#define MT_UDMA_WLCFG_0			MT_UMAC(0x18)
+#define MT_WL_RX_AGG_TO			GENMASK(7, 0)
+#define MT_WL_RX_AGG_LMT		GENMASK(15, 8)
+#define MT_WL_TX_TMOUT_FUNC_EN		BIT(16)
+#define MT_WL_TX_DPH_CHK_EN		BIT(17)
+#define MT_WL_RX_MPSZ_PAD0		BIT(18)
+#define MT_WL_RX_FLUSH			BIT(19)
+#define MT_TICK_1US_EN			BIT(20)
+#define MT_WL_RX_AGG_EN			BIT(21)
+#define MT_WL_RX_EN			BIT(22)
+#define MT_WL_TX_EN			BIT(23)
+#define MT_WL_RX_BUSY			BIT(30)
+#define MT_WL_TX_BUSY			BIT(31)
+
+#define MT_UDMA_CONN_INFRA_STATUS	MT_UMAC(0xa20)
+#define MT_UDMA_CONN_WFSYS_INIT_DONE	BIT(22)
+#define MT_UDMA_CONN_INFRA_STATUS_SEL	MT_UMAC(0xa24)
+
+#define MT_SSUSB_EPCTL_CSR(ofs)		(0x74011800 + (ofs))
+#define MT_SSUSB_EPCTL_CSR_EP_RST_OPT	MT_SSUSB_EPCTL_CSR(0x090)
+
+#define MT_UWFDMA0(ofs)			(0x7c024000 + (ofs))
+#define MT_UWFDMA0_GLO_CFG		MT_UWFDMA0(0x208)
+#define MT_UWFDMA0_GLO_CFG_EXT0		MT_UWFDMA0(0x2b0)
+#define MT_UWFDMA0_GLO_CFG_EXT1		MT_UWFDMA0(0x2b4)
+#define MT_UWFDMA0_TX_RING_EXT_CTRL(_n)	MT_UWFDMA0(0x600 + ((_n) << 2))
+
+#define MT_CONN_STATUS			0x7c053c10
+#define MT_WIFI_PATCH_DL_STATE		BIT(0)
+
+#define MT_CONN_ON_LPCTL		0x7c060010
+#define PCIE_LPCR_HOST_SET_OWN		BIT(0)
+#define PCIE_LPCR_HOST_CLR_OWN		BIT(1)
+#define PCIE_LPCR_HOST_OWN_SYNC		BIT(2)
+
+#define MT_CONN_ON_MISC			0x7c0600f0
+#define MT_TOP_MISC2_FW_PWR_ON		BIT(0)
+#define MT_TOP_MISC2_FW_N9_ON		BIT(1)
+#define MT_TOP_MISC2_FW_N9_RDY		GENMASK(1, 0)
+
+#define MT_WF_SW_DEF_CR(ofs)		(0x401a00 + (ofs))
+#define MT_WF_SW_DEF_CR_USB_MCU_EVENT	MT_WF_SW_DEF_CR(0x028)
+#define MT_WF_SW_SER_TRIGGER_SUSPEND	BIT(6)
+#define MT_WF_SW_SER_DONE_SUSPEND	BIT(7)
+
+#endif /* __MT792X_REGS_H */
-- 
GitLab


From 95a686dcaea0948d2e98fcac7f79df91c56d2f21 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:48 +0800
Subject: [PATCH 0458/1806] wifi: mt76: mt7921: convert acpisar and clc
 pointers to void

Convert acpisar and clc pointers in mt7921_dev structure to void.
This is a preliminary patch to add WiFi7 chipset support

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c | 5 +++--
 drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h   | 5 ++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c b/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
index 48dd0decac5dc..6feea2e515b34 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
@@ -308,6 +308,7 @@ int mt7921_init_acpi_sar_power(struct mt7921_phy *phy, bool set_default)
 
 u8 mt7921_acpi_get_flags(struct mt7921_phy *phy)
 {
+	struct mt7921_acpi_sar *acpisar = phy->acpisar;
 	struct mt7921_asar_fg *fg;
 	struct {
 		u8 acpi_idx;
@@ -319,10 +320,10 @@ u8 mt7921_acpi_get_flags(struct mt7921_phy *phy)
 	u8 flags = BIT(0);
 	int i, j;
 
-	if (!phy->acpisar)
+	if (!acpisar)
 		return 0;
 
-	fg = phy->acpisar->fg;
+	fg = acpisar->fg;
 	if (!fg)
 		return flags;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index ec9879650174b..2e29a6bda7ad8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -222,10 +222,9 @@ struct mt7921_phy {
 	struct sk_buff_head scan_event_list;
 	struct delayed_work scan_work;
 #ifdef CONFIG_ACPI
-	struct mt7921_acpi_sar *acpisar;
+	void *acpisar;
 #endif
-
-	struct mt7921_clc *clc[MT7921_CLC_MAX_NUM];
+	void *clc[MT7921_CLC_MAX_NUM];
 
 	struct work_struct roc_work;
 	struct timer_list roc_timer;
-- 
GitLab


From 15ca8970efdbe9e9cc56d334ad1556840d6f77a2 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:49 +0800
Subject: [PATCH 0459/1806] wifi: mt76: mt7921: rename mt7921_vif in mt792x_vif

This is a preliminary patch to introduce WiFi7 chipset support

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/init.c  |  2 +-
 .../net/wireless/mediatek/mt76/mt7921/mac.c   |  4 +-
 .../net/wireless/mediatek/mt76/mt7921/main.c  | 52 +++++++++----------
 .../net/wireless/mediatek/mt76/mt7921/mcu.c   | 20 +++----
 .../wireless/mediatek/mt76/mt7921/mt7921.h    | 12 ++---
 5 files changed, 45 insertions(+), 45 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 94b7cdfd018bd..f2a6fd61863b5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -141,7 +141,7 @@ mt7921_init_wiphy(struct ieee80211_hw *hw)
 	phy->slottime = 9;
 
 	hw->sta_data_size = sizeof(struct mt7921_sta);
-	hw->vif_data_size = sizeof(struct mt7921_vif);
+	hw->vif_data_size = sizeof(struct mt792x_vif);
 
 	if (dev->fw_features & MT7921_FW_CAP_CNM) {
 		wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 368f92719abfc..44b0122073f8d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -204,7 +204,7 @@ mt7921_mac_rssi_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
 {
 	struct sk_buff *skb = priv;
 	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct ieee80211_hdr *hdr = mt76_skb_get_hdr(skb);
 
 	if (status->signal > 0)
@@ -819,7 +819,7 @@ static void
 mt7921_vif_connect_iter(void *priv, u8 *mac,
 			struct ieee80211_vif *vif)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_dev *dev = mvif->phy->dev;
 	struct ieee80211_hw *hw = mt76_hw(dev);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 87067ac367ebd..de8c3a02cf4be 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -284,7 +284,7 @@ EXPORT_SYMBOL_GPL(mt7921_stop);
 static int mt7921_add_interface(struct ieee80211_hw *hw,
 				struct ieee80211_vif *vif)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	struct mt7921_phy *phy = mt7921_hw_phy(hw);
 	struct mt76_txq *mtxq;
@@ -341,7 +341,7 @@ out:
 static void mt7921_remove_interface(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_sta *msta = &mvif->sta;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	struct mt7921_phy *phy = mt7921_hw_phy(hw);
@@ -368,7 +368,7 @@ static void mt7921_remove_interface(struct ieee80211_hw *hw,
 static void mt7921_roc_iter(void *priv, u8 *mac,
 			    struct ieee80211_vif *vif)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_phy *phy = priv;
 
 	mt7921_mcu_abort_roc(phy, mvif, phy->roc_token_id);
@@ -399,7 +399,7 @@ void mt7921_roc_timer(struct timer_list *timer)
 	ieee80211_queue_work(phy->mt76->hw, &phy->roc_work);
 }
 
-static int mt7921_abort_roc(struct mt7921_phy *phy, struct mt7921_vif *vif)
+static int mt7921_abort_roc(struct mt7921_phy *phy, struct mt792x_vif *vif)
 {
 	int err = 0;
 
@@ -415,7 +415,7 @@ static int mt7921_abort_roc(struct mt7921_phy *phy, struct mt7921_vif *vif)
 }
 
 static int mt7921_set_roc(struct mt7921_phy *phy,
-			  struct mt7921_vif *vif,
+			  struct mt792x_vif *vif,
 			  struct ieee80211_channel *chan,
 			  int duration,
 			  enum mt7921_roc_req type)
@@ -450,7 +450,7 @@ static int mt7921_remain_on_channel(struct ieee80211_hw *hw,
 				    int duration,
 				    enum ieee80211_roc_type type)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_phy *phy = mt7921_hw_phy(hw);
 	int err;
 
@@ -464,7 +464,7 @@ static int mt7921_remain_on_channel(struct ieee80211_hw *hw,
 static int mt7921_cancel_remain_on_channel(struct ieee80211_hw *hw,
 					   struct ieee80211_vif *vif)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_phy *phy = mt7921_hw_phy(hw);
 
 	return mt7921_abort_roc(phy, mvif);
@@ -507,7 +507,7 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			  struct ieee80211_key_conf *key)
 {
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_sta *msta = sta ? (struct mt7921_sta *)sta->drv_priv :
 				  &mvif->sta;
 	struct mt76_wcid *wcid = &msta->wcid;
@@ -667,7 +667,7 @@ mt7921_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       unsigned int link_id, u16 queue,
 	       const struct ieee80211_tx_queue_params *params)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 
 	/* no need to update right away, we'll get BSS_CHANGED_QOS */
 	queue = mt76_connac_lmac_mapping(queue);
@@ -743,7 +743,7 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changed & BSS_CHANGED_ARP_FILTER) {
-		struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+		struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 
 		mt76_connac_mcu_update_arp_filter(&dev->mt76, &mvif->mt76,
 						  info);
@@ -757,7 +757,7 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 {
 	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
 	struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	int ret, idx;
 
 	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7921_WTBL_STA - 1);
@@ -798,7 +798,7 @@ void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 {
 	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
 	struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 
 	mt7921_mutex_acquire(dev);
 
@@ -832,7 +832,7 @@ void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
 
 	if (vif->type == NL80211_IFTYPE_STATION) {
-		struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+		struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 
 		mvif->wep_sta = NULL;
 		ewma_rssi_init(&mvif->rssi);
@@ -884,9 +884,9 @@ static void mt7921_tx(struct ieee80211_hw *hw,
 	}
 
 	if (vif && !control->sta) {
-		struct mt7921_vif *mvif;
+		struct mt792x_vif *mvif;
 
-		mvif = (struct mt7921_vif *)vif->drv_priv;
+		mvif = (struct mt792x_vif *)vif->drv_priv;
 		wcid = &mvif->sta.wcid;
 	}
 
@@ -1133,7 +1133,7 @@ static
 void mt7921_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			 struct ethtool_stats *stats, u64 *data)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	int stats_size = ARRAY_SIZE(mt7921_gstrings_stats);
 	struct mt7921_phy *phy = mt7921_hw_phy(hw);
 	struct mt7921_dev *dev = phy->dev;
@@ -1203,7 +1203,7 @@ void mt7921_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 static u64
 mt7921_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	u8 omac_idx = mvif->mt76.omac_idx;
 	union {
@@ -1229,7 +1229,7 @@ static void
 mt7921_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       u64 timestamp)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	u8 omac_idx = mvif->mt76.omac_idx;
 	union {
@@ -1521,7 +1521,7 @@ static void mt7921_ipv6_addr_change(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
 				    struct inet6_dev *idev)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_dev *dev = mvif->phy->dev;
 	struct inet6_ifaddr *ifa;
 	struct in6_addr ns_addrs[IEEE80211_BSS_ARP_ADDR_LIST_LEN];
@@ -1630,7 +1630,7 @@ static int
 mt7921_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		struct ieee80211_bss_conf *link_conf)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_phy *phy = mt7921_hw_phy(hw);
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	int err;
@@ -1658,7 +1658,7 @@ static void
 mt7921_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       struct ieee80211_bss_conf *link_conf)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_phy *phy = mt7921_hw_phy(hw);
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	int err;
@@ -1692,7 +1692,7 @@ mt7921_remove_chanctx(struct ieee80211_hw *hw,
 static void mt7921_ctx_iter(void *priv, u8 *mac,
 			    struct ieee80211_vif *vif)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct ieee80211_chanctx_conf *ctx = priv;
 
 	if (ctx != mvif->ctx)
@@ -1724,7 +1724,7 @@ mt7921_assign_vif_chanctx(struct ieee80211_hw *hw,
 			  struct ieee80211_bss_conf *link_conf,
 			  struct ieee80211_chanctx_conf *ctx)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 
 	mutex_lock(&dev->mt76.mutex);
@@ -1740,7 +1740,7 @@ mt7921_unassign_vif_chanctx(struct ieee80211_hw *hw,
 			    struct ieee80211_bss_conf *link_conf,
 			    struct ieee80211_chanctx_conf *ctx)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 
 	mutex_lock(&dev->mt76.mutex);
@@ -1752,7 +1752,7 @@ static void mt7921_mgd_prepare_tx(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
 				  struct ieee80211_prep_tx_info *info)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	u16 duration = info->duration ? info->duration :
 		       jiffies_to_msecs(HZ);
@@ -1767,7 +1767,7 @@ static void mt7921_mgd_complete_tx(struct ieee80211_hw *hw,
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_prep_tx_info *info)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 
 	mt7921_abort_roc(mvif->phy, mvif);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index a0ad18c70b1ab..4d8b4c8027399 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -96,7 +96,7 @@ static int
 mt7921_mcu_set_ipv6_ns_filter(struct mt76_dev *dev,
 			      struct ieee80211_vif *vif, bool suspend)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct {
 		struct {
 			u8 bss_idx;
@@ -543,7 +543,7 @@ EXPORT_SYMBOL_GPL(mt7921_run_firmware);
 
 int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct edca {
 		__le16 cw_min;
 		__le16 cw_max;
@@ -635,7 +635,7 @@ int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif)
 				 &req_mu, sizeof(req_mu), false);
 }
 
-int mt7921_mcu_set_roc(struct mt7921_phy *phy, struct mt7921_vif *vif,
+int mt7921_mcu_set_roc(struct mt7921_phy *phy, struct mt792x_vif *vif,
 		       struct ieee80211_channel *chan, int duration,
 		       enum mt7921_roc_req type, u8 token_id)
 {
@@ -702,7 +702,7 @@ int mt7921_mcu_set_roc(struct mt7921_phy *phy, struct mt7921_vif *vif,
 				 &req, sizeof(req), false);
 }
 
-int mt7921_mcu_abort_roc(struct mt7921_phy *phy, struct mt7921_vif *vif,
+int mt7921_mcu_abort_roc(struct mt7921_phy *phy, struct mt792x_vif *vif,
 			 u8 token_id)
 {
 	struct mt7921_dev *dev = phy->dev;
@@ -809,7 +809,7 @@ EXPORT_SYMBOL_GPL(mt7921_mcu_set_eeprom);
 
 int mt7921_mcu_uni_bss_ps(struct mt7921_dev *dev, struct ieee80211_vif *vif)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct {
 		struct {
 			u8 bss_idx;
@@ -848,7 +848,7 @@ static int
 mt7921_mcu_uni_bss_bcnft(struct mt7921_dev *dev, struct ieee80211_vif *vif,
 			 bool enable)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct {
 		struct {
 			u8 bss_idx;
@@ -884,7 +884,7 @@ int
 mt7921_mcu_set_bss_pm(struct mt7921_dev *dev, struct ieee80211_vif *vif,
 		      bool enable)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct {
 		u8 bss_idx;
 		u8 dtim_period;
@@ -922,7 +922,7 @@ int mt7921_mcu_sta_update(struct mt7921_dev *dev, struct ieee80211_sta *sta,
 			  struct ieee80211_vif *vif, bool enable,
 			  enum mt76_sta_info_state state)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	int rssi = -ewma_rssi_read(&mvif->rssi);
 	struct mt76_sta_cmd_info info = {
 		.sta = sta,
@@ -1074,7 +1074,7 @@ int mt7921_mcu_set_sniffer(struct mt7921_dev *dev, struct ieee80211_vif *vif,
 				 true);
 }
 
-int mt7921_mcu_config_sniffer(struct mt7921_vif *vif,
+int mt7921_mcu_config_sniffer(struct mt792x_vif *vif,
 			      struct ieee80211_chanctx_conf *ctx)
 {
 	struct cfg80211_chan_def *chandef = &ctx->def;
@@ -1148,7 +1148,7 @@ mt7921_mcu_uni_add_beacon_offload(struct mt7921_dev *dev,
 				  struct ieee80211_vif *vif,
 				  bool enable)
 {
-	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt76_wcid *wcid = &dev->mt76.global_wcid;
 	struct ieee80211_mutable_offsets offs;
 	struct {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 2e29a6bda7ad8..6ec5b19f3c251 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -127,7 +127,7 @@ struct mt7921_sdio_intr {
 #define to_rssi(field, rxv)		((FIELD_GET(field, rxv) - 220) / 2)
 #define to_rcpi(rssi)			(2 * (rssi) + 220)
 
-struct mt7921_vif;
+struct mt792x_vif;
 struct mt7921_sta;
 
 enum mt7921_txq_id {
@@ -148,7 +148,7 @@ DECLARE_EWMA(avg_signal, 10, 8)
 struct mt7921_sta {
 	struct mt76_wcid wcid; /* must be first */
 
-	struct mt7921_vif *vif;
+	struct mt792x_vif *vif;
 
 	u32 airtime_ac[8];
 
@@ -162,7 +162,7 @@ struct mt7921_sta {
 
 DECLARE_EWMA(rssi, 10, 8);
 
-struct mt7921_vif {
+struct mt792x_vif {
 	struct mt76_vif mt76; /* must be first */
 
 	struct mt7921_sta sta;
@@ -497,7 +497,7 @@ void mt7921_set_ipv6_ns_work(struct work_struct *work);
 
 int mt7921_mcu_set_sniffer(struct mt7921_dev *dev, struct ieee80211_vif *vif,
 			   bool enable);
-int mt7921_mcu_config_sniffer(struct mt7921_vif *vif,
+int mt7921_mcu_config_sniffer(struct mt792x_vif *vif,
 			      struct ieee80211_chanctx_conf *ctx);
 int mt7921_mcu_get_temperature(struct mt7921_phy *phy);
 
@@ -550,10 +550,10 @@ int mt7921_set_tx_sar_pwr(struct ieee80211_hw *hw,
 
 int mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
 		       enum environment_cap env_cap);
-int mt7921_mcu_set_roc(struct mt7921_phy *phy, struct mt7921_vif *vif,
+int mt7921_mcu_set_roc(struct mt7921_phy *phy, struct mt792x_vif *vif,
 		       struct ieee80211_channel *chan, int duration,
 		       enum mt7921_roc_req type, u8 token_id);
-int mt7921_mcu_abort_roc(struct mt7921_phy *phy, struct mt7921_vif *vif,
+int mt7921_mcu_abort_roc(struct mt7921_phy *phy, struct mt792x_vif *vif,
 			 u8 token_id);
 struct ieee80211_ops *mt7921_get_mac80211_ops(struct device *dev,
 					      void *drv_data, u8 *fw_features);
-- 
GitLab


From b7bfad2c83cdbbd7cd502bebdc75ef703c980634 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:50 +0800
Subject: [PATCH 0460/1806] wifi: mt76: mt7921: rename mt7921_sta in mt792x_sta

This is a preliminary patch to introduce WiFi7 chipset support

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/init.c  |  2 +-
 .../net/wireless/mediatek/mt76/mt7921/mac.c   | 22 +++++++++----------
 .../net/wireless/mediatek/mt76/mt7921/main.c  | 22 +++++++++----------
 .../net/wireless/mediatek/mt76/mt7921/mcu.c   |  8 +++----
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  8 +++----
 .../wireless/mediatek/mt76/mt7921/pci_mac.c   |  2 +-
 6 files changed, 32 insertions(+), 32 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index f2a6fd61863b5..df32f4f1b6366 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -140,7 +140,7 @@ mt7921_init_wiphy(struct ieee80211_hw *hw)
 
 	phy->slottime = 9;
 
-	hw->sta_data_size = sizeof(struct mt7921_sta);
+	hw->sta_data_size = sizeof(struct mt792x_sta);
 	hw->vif_data_size = sizeof(struct mt792x_vif);
 
 	if (dev->fw_features & MT7921_FW_CAP_CNM) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 44b0122073f8d..d4cf2ff18102e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -23,7 +23,7 @@ static u32 mt7921_mac_wtbl_lmac_addr(int idx, u8 offset)
 static struct mt76_wcid *mt7921_rx_get_wcid(struct mt7921_dev *dev,
 					    u16 idx, bool unicast)
 {
-	struct mt7921_sta *sta;
+	struct mt792x_sta *sta;
 	struct mt76_wcid *wcid;
 
 	if (idx >= ARRAY_SIZE(dev->mt76.wcid))
@@ -36,7 +36,7 @@ static struct mt76_wcid *mt7921_rx_get_wcid(struct mt7921_dev *dev,
 	if (!wcid->sta)
 		return NULL;
 
-	sta = container_of(wcid, struct mt7921_sta, wcid);
+	sta = container_of(wcid, struct mt792x_sta, wcid);
 	if (!sta->vif)
 		return NULL;
 
@@ -61,7 +61,7 @@ static void mt7921_mac_sta_poll(struct mt7921_dev *dev)
 		[IEEE80211_AC_VO] = 6
 	};
 	struct ieee80211_sta *sta;
-	struct mt7921_sta *msta;
+	struct mt792x_sta *msta;
 	u32 tx_time[IEEE80211_NUM_ACS], rx_time[IEEE80211_NUM_ACS];
 	LIST_HEAD(sta_poll_list);
 	struct rate_info *rate;
@@ -84,7 +84,7 @@ static void mt7921_mac_sta_poll(struct mt7921_dev *dev)
 			break;
 		}
 		msta = list_first_entry(&sta_poll_list,
-					struct mt7921_sta, wcid.poll_list);
+					struct mt792x_sta, wcid.poll_list);
 		list_del_init(&msta->wcid.poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
@@ -248,7 +248,7 @@ mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb)
 	u32 rxd2 = le32_to_cpu(rxd[2]);
 	u32 rxd3 = le32_to_cpu(rxd[3]);
 	u32 rxd4 = le32_to_cpu(rxd[4]);
-	struct mt7921_sta *msta = NULL;
+	struct mt792x_sta *msta = NULL;
 	u16 seq_ctrl = 0;
 	__le16 fc = 0;
 	u8 mode = 0;
@@ -279,7 +279,7 @@ mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb)
 	status->wcid = mt7921_rx_get_wcid(dev, idx, unicast);
 
 	if (status->wcid) {
-		msta = container_of(status->wcid, struct mt7921_sta, wcid);
+		msta = container_of(status->wcid, struct mt792x_sta, wcid);
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		if (list_empty(&msta->wcid.poll_list))
 			list_add_tail(&msta->wcid.poll_list,
@@ -513,7 +513,7 @@ mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb)
 
 void mt7921_mac_add_txs(struct mt7921_dev *dev, void *data)
 {
-	struct mt7921_sta *msta = NULL;
+	struct mt792x_sta *msta = NULL;
 	struct mt76_wcid *wcid;
 	__le32 *txs_data = data;
 	u16 wcidx;
@@ -537,7 +537,7 @@ void mt7921_mac_add_txs(struct mt7921_dev *dev, void *data)
 	if (!wcid)
 		goto out;
 
-	msta = container_of(wcid, struct mt7921_sta, wcid);
+	msta = container_of(wcid, struct mt792x_sta, wcid);
 
 	mt76_connac2_mac_add_txs_skb(&dev->mt76, wcid, pid, txs_data);
 	if (!wcid->sta)
@@ -582,7 +582,7 @@ static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
 		 * 1'b0: msdu_id with the same 'wcid pair' as above.
 		 */
 		if (info & MT_TX_FREE_PAIR) {
-			struct mt7921_sta *msta;
+			struct mt792x_sta *msta;
 			u16 idx;
 
 			count++;
@@ -592,7 +592,7 @@ static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
 			if (!sta)
 				continue;
 
-			msta = container_of(wcid, struct mt7921_sta, wcid);
+			msta = container_of(wcid, struct mt792x_sta, wcid);
 			spin_lock_bh(&mdev->sta_poll_lock);
 			if (list_empty(&msta->wcid.poll_list))
 				list_add_tail(&msta->wcid.poll_list,
@@ -1140,7 +1140,7 @@ int mt7921_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 		wcid = &dev->mt76.global_wcid;
 
 	if (sta) {
-		struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
+		struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 
 		if (time_after(jiffies, msta->last_txs + HZ / 4)) {
 			info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index de8c3a02cf4be..bd449423e5b3f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -342,7 +342,7 @@ static void mt7921_remove_interface(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_sta *msta = &mvif->sta;
+	struct mt792x_sta *msta = &mvif->sta;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	struct mt7921_phy *phy = mt7921_hw_phy(hw);
 	int idx = msta->wcid.idx;
@@ -508,7 +508,7 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 {
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_sta *msta = sta ? (struct mt7921_sta *)sta->drv_priv :
+	struct mt792x_sta *msta = sta ? (struct mt792x_sta *)sta->drv_priv :
 				  &mvif->sta;
 	struct mt76_wcid *wcid = &msta->wcid;
 	u8 *wcid_keyidx = &wcid->hw_key_idx;
@@ -756,7 +756,7 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta)
 {
 	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
-	struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
+	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	int ret, idx;
 
@@ -797,7 +797,7 @@ void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			  struct ieee80211_sta *sta)
 {
 	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
-	struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
+	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 
 	mt7921_mutex_acquire(dev);
@@ -822,7 +822,7 @@ void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta)
 {
 	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
-	struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
+	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 
 	mt76_connac_free_pending_tx_skbs(&dev->pm, &msta->wcid);
 	mt76_connac_pm_wake(&dev->mphy, &dev->pm);
@@ -877,9 +877,9 @@ static void mt7921_tx(struct ieee80211_hw *hw,
 	int qid;
 
 	if (control->sta) {
-		struct mt7921_sta *sta;
+		struct mt792x_sta *sta;
 
-		sta = (struct mt7921_sta *)control->sta->drv_priv;
+		sta = (struct mt792x_sta *)control->sta->drv_priv;
 		wcid = &sta->wcid;
 	}
 
@@ -924,7 +924,7 @@ mt7921_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	struct ieee80211_sta *sta = params->sta;
 	struct ieee80211_txq *txq = sta->txq[params->tid];
-	struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
+	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	u16 tid = params->tid;
 	u16 ssn = params->ssn;
 	struct mt76_txq *mtxq;
@@ -1120,7 +1120,7 @@ mt7921_get_et_sset_count(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 static void
 mt7921_ethtool_worker(void *wi_data, struct ieee80211_sta *sta)
 {
-	struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
+	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt76_ethtool_worker_info *wi = wi_data;
 
 	if (msta->vif->mt76.idx != wi->idx)
@@ -1387,7 +1387,7 @@ static void mt7921_sta_statistics(struct ieee80211_hw *hw,
 				  struct ieee80211_sta *sta,
 				  struct station_info *sinfo)
 {
-	struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
+	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct rate_info *txrate = &msta->wcid.rate;
 
 	if (!txrate->legacy && !txrate->flags)
@@ -1500,7 +1500,7 @@ static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw,
 					 struct ieee80211_sta *sta,
 					 bool enabled)
 {
-	struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
+	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 
 	mt7921_mutex_acquire(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 4d8b4c8027399..1d1e8ee5bd3d8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -343,7 +343,7 @@ int mt7921_mcu_uni_tx_ba(struct mt7921_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable)
 {
-	struct mt7921_sta *msta = (struct mt7921_sta *)params->sta->drv_priv;
+	struct mt792x_sta *msta = (struct mt792x_sta *)params->sta->drv_priv;
 
 	if (enable && !params->amsdu)
 		msta->wcid.amsdu = false;
@@ -357,7 +357,7 @@ int mt7921_mcu_uni_rx_ba(struct mt7921_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable)
 {
-	struct mt7921_sta *msta = (struct mt7921_sta *)params->sta->drv_priv;
+	struct mt792x_sta *msta = (struct mt792x_sta *)params->sta->drv_priv;
 
 	return mt76_connac_mcu_sta_ba(&dev->mt76, &msta->vif->mt76, params,
 				      MCU_UNI_CMD(STA_REC_UPDATE),
@@ -933,9 +933,9 @@ int mt7921_mcu_sta_update(struct mt7921_dev *dev, struct ieee80211_sta *sta,
 		.offload_fw = true,
 		.rcpi = to_rcpi(rssi),
 	};
-	struct mt7921_sta *msta;
+	struct mt792x_sta *msta;
 
-	msta = sta ? (struct mt7921_sta *)sta->drv_priv : NULL;
+	msta = sta ? (struct mt792x_sta *)sta->drv_priv : NULL;
 	info.wcid = msta ? &msta->wcid : &mvif->sta.wcid;
 	info.newly = msta ? state != MT76_STA_INFO_STATE_ASSOC : true;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 6ec5b19f3c251..4d409ba3fc21f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -128,7 +128,7 @@ struct mt7921_sdio_intr {
 #define to_rcpi(rssi)			(2 * (rssi) + 220)
 
 struct mt792x_vif;
-struct mt7921_sta;
+struct mt792x_sta;
 
 enum mt7921_txq_id {
 	MT7921_TXQ_BAND0,
@@ -145,7 +145,7 @@ enum mt7921_rxq_id {
 
 DECLARE_EWMA(avg_signal, 10, 8)
 
-struct mt7921_sta {
+struct mt792x_sta {
 	struct mt76_wcid wcid; /* must be first */
 
 	struct mt792x_vif *vif;
@@ -165,8 +165,8 @@ DECLARE_EWMA(rssi, 10, 8);
 struct mt792x_vif {
 	struct mt76_vif mt76; /* must be first */
 
-	struct mt7921_sta sta;
-	struct mt7921_sta *wep_sta;
+	struct mt792x_sta sta;
+	struct mt792x_sta *wep_sta;
 
 	struct mt7921_phy *phy;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
index 978c90a034cf1..32bba86727a53 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
@@ -32,7 +32,7 @@ int mt7921e_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 		return id;
 
 	if (sta) {
-		struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv;
+		struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 
 		if (time_after(jiffies, msta->last_txs + HZ / 4)) {
 			info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
-- 
GitLab


From 78562b2cafc61a0c08dc949eacb942ac756aae37 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:51 +0800
Subject: [PATCH 0461/1806] wifi: mt76: mt7921: rename mt7921_phy in mt792x_phy

This is a preliminary patch to introduce WiFi7 chipset support

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7921/acpi_sar.c  |  8 +--
 .../wireless/mediatek/mt76/mt7921/debugfs.c   |  4 +-
 .../net/wireless/mediatek/mt76/mt7921/init.c  |  6 +-
 .../net/wireless/mediatek/mt76/mt7921/mac.c   | 14 ++---
 .../net/wireless/mediatek/mt76/mt7921/main.c  | 58 +++++++++----------
 .../net/wireless/mediatek/mt76/mt7921/mcu.c   | 14 ++---
 .../wireless/mediatek/mt76/mt7921/mt7921.h    | 36 ++++++------
 .../wireless/mediatek/mt76/mt7921/testmode.c  |  4 +-
 8 files changed, 72 insertions(+), 72 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c b/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
index 6feea2e515b34..06f2acdbfe1c7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
@@ -193,7 +193,7 @@ int mt7921_init_acpi_sar(struct mt7921_dev *dev)
 }
 
 static s8
-mt7921_asar_get_geo_pwr(struct mt7921_phy *phy,
+mt7921_asar_get_geo_pwr(struct mt792x_phy *phy,
 			enum nl80211_band band, s8 dyn_power)
 {
 	struct mt7921_acpi_sar *asar = phy->acpisar;
@@ -248,7 +248,7 @@ mt7921_asar_get_geo_pwr(struct mt7921_phy *phy,
 }
 
 static s8
-mt7921_asar_range_pwr(struct mt7921_phy *phy,
+mt7921_asar_range_pwr(struct mt792x_phy *phy,
 		      const struct cfg80211_sar_freq_ranges *range,
 		      u8 idx)
 {
@@ -280,7 +280,7 @@ mt7921_asar_range_pwr(struct mt7921_phy *phy,
 	return mt7921_asar_get_geo_pwr(phy, band, limit[idx]);
 }
 
-int mt7921_init_acpi_sar_power(struct mt7921_phy *phy, bool set_default)
+int mt7921_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default)
 {
 	const struct cfg80211_sar_capa *capa = phy->mt76->hw->wiphy->sar_capa;
 	int i;
@@ -306,7 +306,7 @@ int mt7921_init_acpi_sar_power(struct mt7921_phy *phy, bool set_default)
 	return 0;
 }
 
-u8 mt7921_acpi_get_flags(struct mt7921_phy *phy)
+u8 mt7921_acpi_get_flags(struct mt792x_phy *phy)
 {
 	struct mt7921_acpi_sar *acpisar = phy->acpisar;
 	struct mt7921_asar_fg *fg;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
index d6c66e775536c..baa640e8a9825 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
@@ -58,7 +58,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_fw_debug, mt7921_fw_debug_get,
 			 mt7921_fw_debug_set, "%lld\n");
 
 static void
-mt7921_ampdu_stat_read_phy(struct mt7921_phy *phy,
+mt7921_ampdu_stat_read_phy(struct mt792x_phy *phy,
 			   struct seq_file *file)
 {
 	struct mt7921_dev *dev = file->private;
@@ -94,7 +94,7 @@ static int
 mt7921_tx_stats_show(struct seq_file *file, void *data)
 {
 	struct mt7921_dev *dev = file->private;
-	struct mt7921_phy *phy = &dev->phy;
+	struct mt792x_phy *phy = &dev->phy;
 	struct mt76_mib_stats *mib = &phy->mib;
 	int i;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index df32f4f1b6366..d383586eb429b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -60,7 +60,7 @@ static ssize_t mt7921_thermal_temp_show(struct device *dev,
 {
 	switch (to_sensor_dev_attr(attr)->index) {
 	case 0: {
-		struct mt7921_phy *phy = dev_get_drvdata(dev);
+		struct mt792x_phy *phy = dev_get_drvdata(dev);
 		struct mt7921_dev *mdev = phy->dev;
 		int temperature;
 
@@ -85,7 +85,7 @@ static struct attribute *mt7921_hwmon_attrs[] = {
 };
 ATTRIBUTE_GROUPS(mt7921_hwmon);
 
-static int mt7921_thermal_init(struct mt7921_phy *phy)
+static int mt7921_thermal_init(struct mt792x_phy *phy)
 {
 	struct wiphy *wiphy = phy->mt76->hw->wiphy;
 	struct device *hwmon;
@@ -126,7 +126,7 @@ mt7921_regd_notifier(struct wiphy *wiphy,
 static int
 mt7921_init_wiphy(struct ieee80211_hw *hw)
 {
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt7921_dev *dev = phy->dev;
 	struct wiphy *wiphy = hw->wiphy;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index d4cf2ff18102e..15c0e8be8f34d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -240,7 +240,7 @@ mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb)
 	u16 hdr_gap;
 	__le32 *rxv = NULL, *rxd = (__le32 *)skb->data;
 	struct mt76_phy *mphy = &dev->mt76.phy;
-	struct mt7921_phy *phy = &dev->phy;
+	struct mt792x_phy *phy = &dev->phy;
 	struct ieee80211_supported_band *sband;
 	u32 csum_status = *(u32 *)skb->cb;
 	u32 rxd0 = le32_to_cpu(rxd[0]);
@@ -699,7 +699,7 @@ void mt7921_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 }
 EXPORT_SYMBOL_GPL(mt7921_queue_rx_skb);
 
-void mt7921_mac_reset_counters(struct mt7921_phy *phy)
+void mt7921_mac_reset_counters(struct mt792x_phy *phy)
 {
 	struct mt7921_dev *dev = phy->dev;
 	int i;
@@ -721,7 +721,7 @@ void mt7921_mac_reset_counters(struct mt7921_phy *phy)
 	mt76_set(dev, MT_WF_RMAC_MIB_AIRTIME0(0), MT_WF_RMAC_MIB_RXTIME_CLR);
 }
 
-void mt7921_mac_set_timing(struct mt7921_phy *phy)
+void mt7921_mac_set_timing(struct mt792x_phy *phy)
 {
 	s16 coverage_class = phy->coverage_class;
 	struct mt7921_dev *dev = phy->dev;
@@ -763,7 +763,7 @@ void mt7921_mac_set_timing(struct mt7921_phy *phy)
 }
 
 static u8
-mt7921_phy_get_nf(struct mt7921_phy *phy, int idx)
+mt7921_phy_get_nf(struct mt792x_phy *phy, int idx)
 {
 	return 0;
 }
@@ -772,7 +772,7 @@ static void
 mt7921_phy_update_channel(struct mt76_phy *mphy, int idx)
 {
 	struct mt7921_dev *dev = container_of(mphy->dev, struct mt7921_dev, mt76);
-	struct mt7921_phy *phy = (struct mt7921_phy *)mphy->priv;
+	struct mt792x_phy *phy = (struct mt792x_phy *)mphy->priv;
 	struct mt76_channel_state *state;
 	u64 busy_time, tx_time, rx_time, obss_time;
 	int nf;
@@ -902,7 +902,7 @@ void mt7921_reset(struct mt76_dev *mdev)
 }
 EXPORT_SYMBOL_GPL(mt7921_reset);
 
-void mt7921_mac_update_mib_stats(struct mt7921_phy *phy)
+void mt7921_mac_update_mib_stats(struct mt792x_phy *phy)
 {
 	struct mt76_mib_stats *mib = &phy->mib;
 	struct mt7921_dev *dev = phy->dev;
@@ -964,7 +964,7 @@ void mt7921_mac_update_mib_stats(struct mt7921_phy *phy)
 
 void mt7921_mac_work(struct work_struct *work)
 {
-	struct mt7921_phy *phy;
+	struct mt792x_phy *phy;
 	struct mt76_phy *mphy;
 
 	mphy = (struct mt76_phy *)container_of(work, struct mt76_phy,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index bd449423e5b3f..fc9a306344cd9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -10,7 +10,7 @@
 #include "mcu.h"
 
 static int
-mt7921_init_he_caps(struct mt7921_phy *phy, enum nl80211_band band,
+mt7921_init_he_caps(struct mt792x_phy *phy, enum nl80211_band band,
 		    struct ieee80211_sband_iftype_data *data)
 {
 	int i, idx = 0;
@@ -185,7 +185,7 @@ mt7921_init_he_caps(struct mt7921_phy *phy, enum nl80211_band band,
 	return idx;
 }
 
-void mt7921_set_stream_he_caps(struct mt7921_phy *phy)
+void mt7921_set_stream_he_caps(struct mt792x_phy *phy)
 {
 	struct ieee80211_sband_iftype_data *data;
 	struct ieee80211_supported_band *band;
@@ -219,7 +219,7 @@ void mt7921_set_stream_he_caps(struct mt7921_phy *phy)
 	}
 }
 
-int __mt7921_start(struct mt7921_phy *phy)
+int __mt7921_start(struct mt792x_phy *phy)
 {
 	struct mt76_phy *mphy = phy->mt76;
 	int err;
@@ -252,7 +252,7 @@ EXPORT_SYMBOL_GPL(__mt7921_start);
 
 static int mt7921_start(struct ieee80211_hw *hw)
 {
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int err;
 
 	mt7921_mutex_acquire(phy->dev);
@@ -265,7 +265,7 @@ static int mt7921_start(struct ieee80211_hw *hw)
 void mt7921_stop(struct ieee80211_hw *hw)
 {
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	cancel_delayed_work_sync(&phy->mt76->mac_work);
 
@@ -286,7 +286,7 @@ static int mt7921_add_interface(struct ieee80211_hw *hw,
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt76_txq *mtxq;
 	int idx, ret = 0;
 
@@ -344,7 +344,7 @@ static void mt7921_remove_interface(struct ieee80211_hw *hw,
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_sta *msta = &mvif->sta;
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int idx = msta->wcid.idx;
 
 	mt7921_mutex_acquire(dev);
@@ -369,16 +369,16 @@ static void mt7921_roc_iter(void *priv, u8 *mac,
 			    struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_phy *phy = priv;
+	struct mt792x_phy *phy = priv;
 
 	mt7921_mcu_abort_roc(phy, mvif, phy->roc_token_id);
 }
 
 void mt7921_roc_work(struct work_struct *work)
 {
-	struct mt7921_phy *phy;
+	struct mt792x_phy *phy;
 
-	phy = (struct mt7921_phy *)container_of(work, struct mt7921_phy,
+	phy = (struct mt792x_phy *)container_of(work, struct mt792x_phy,
 						roc_work);
 
 	if (!test_and_clear_bit(MT76_STATE_ROC, &phy->mt76->state))
@@ -394,12 +394,12 @@ void mt7921_roc_work(struct work_struct *work)
 
 void mt7921_roc_timer(struct timer_list *timer)
 {
-	struct mt7921_phy *phy = from_timer(phy, timer, roc_timer);
+	struct mt792x_phy *phy = from_timer(phy, timer, roc_timer);
 
 	ieee80211_queue_work(phy->mt76->hw, &phy->roc_work);
 }
 
-static int mt7921_abort_roc(struct mt7921_phy *phy, struct mt792x_vif *vif)
+static int mt7921_abort_roc(struct mt792x_phy *phy, struct mt792x_vif *vif)
 {
 	int err = 0;
 
@@ -414,7 +414,7 @@ static int mt7921_abort_roc(struct mt7921_phy *phy, struct mt792x_vif *vif)
 	return err;
 }
 
-static int mt7921_set_roc(struct mt7921_phy *phy,
+static int mt7921_set_roc(struct mt792x_phy *phy,
 			  struct mt792x_vif *vif,
 			  struct ieee80211_channel *chan,
 			  int duration,
@@ -451,7 +451,7 @@ static int mt7921_remain_on_channel(struct ieee80211_hw *hw,
 				    enum ieee80211_roc_type type)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int err;
 
 	mt7921_mutex_acquire(phy->dev);
@@ -465,12 +465,12 @@ static int mt7921_cancel_remain_on_channel(struct ieee80211_hw *hw,
 					   struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	return mt7921_abort_roc(phy, mvif);
 }
 
-static int mt7921_set_channel(struct mt7921_phy *phy)
+static int mt7921_set_channel(struct mt792x_phy *phy)
 {
 	struct mt7921_dev *dev = phy->dev;
 	int ret;
@@ -631,7 +631,7 @@ void mt7921_set_runtime_pm(struct mt7921_dev *dev)
 static int mt7921_config(struct ieee80211_hw *hw, u32 changed)
 {
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int ret = 0;
 
 	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
@@ -710,7 +710,7 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 				    struct ieee80211_bss_conf *info,
 				    u64 changed)
 {
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 
 	mt7921_mutex_acquire(dev);
@@ -994,7 +994,7 @@ static int
 mt7921_get_stats(struct ieee80211_hw *hw,
 		 struct ieee80211_low_level_stats *stats)
 {
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt76_mib_stats *mib = &phy->mib;
 
 	mt7921_mutex_acquire(phy->dev);
@@ -1135,7 +1135,7 @@ void mt7921_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	int stats_size = ARRAY_SIZE(mt7921_gstrings_stats);
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt7921_dev *dev = phy->dev;
 	struct mt76_mib_stats *mib = &phy->mib;
 	struct mt76_ethtool_worker_info wi = {
@@ -1252,7 +1252,7 @@ mt7921_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 static void
 mt7921_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class)
 {
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt7921_dev *dev = phy->dev;
 
 	mt7921_mutex_acquire(dev);
@@ -1263,9 +1263,9 @@ mt7921_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class)
 
 void mt7921_scan_work(struct work_struct *work)
 {
-	struct mt7921_phy *phy;
+	struct mt792x_phy *phy;
 
-	phy = (struct mt7921_phy *)container_of(work, struct mt7921_phy,
+	phy = (struct mt792x_phy *)container_of(work, struct mt792x_phy,
 						scan_work.work);
 
 	while (true) {
@@ -1360,7 +1360,7 @@ static int
 mt7921_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 {
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int max_nss = hweight8(hw->wiphy->available_antennas_tx);
 
 	if (!tx_ant || tx_ant != rx_ant || ffs(tx_ant) > max_nss)
@@ -1424,7 +1424,7 @@ static int mt7921_suspend(struct ieee80211_hw *hw,
 			  struct cfg80211_wowlan *wowlan)
 {
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	cancel_delayed_work_sync(&phy->scan_work);
 	cancel_delayed_work_sync(&phy->mt76->mac_work);
@@ -1448,7 +1448,7 @@ static int mt7921_suspend(struct ieee80211_hw *hw,
 static int mt7921_resume(struct ieee80211_hw *hw)
 {
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	mt7921_mutex_acquire(dev);
 
@@ -1631,7 +1631,7 @@ mt7921_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		struct ieee80211_bss_conf *link_conf)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	int err;
 
@@ -1659,7 +1659,7 @@ mt7921_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       struct ieee80211_bss_conf *link_conf)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt7921_dev *dev = mt7921_hw_dev(hw);
 	int err;
 
@@ -1709,7 +1709,7 @@ mt7921_change_chanctx(struct ieee80211_hw *hw,
 		      struct ieee80211_chanctx_conf *ctx,
 		      u32 changed)
 {
-	struct mt7921_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	mt7921_mutex_acquire(phy->dev);
 	ieee80211_iterate_active_interfaces(phy->mt76->hw,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 1d1e8ee5bd3d8..06fecc9dc2203 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -160,7 +160,7 @@ static void
 mt7921_mcu_scan_event(struct mt7921_dev *dev, struct sk_buff *skb)
 {
 	struct mt76_phy *mphy = &dev->mt76.phy;
-	struct mt7921_phy *phy = (struct mt7921_phy *)mphy->priv;
+	struct mt792x_phy *phy = (struct mt792x_phy *)mphy->priv;
 
 	spin_lock_bh(&dev->mt76.lock);
 	__skb_queue_tail(&phy->scan_event_list, skb);
@@ -394,7 +394,7 @@ static int mt7921_load_clc(struct mt7921_dev *dev, const char *fw_name)
 	const struct mt76_connac2_fw_region *region;
 	const struct mt7921_clc *clc;
 	struct mt76_dev *mdev = &dev->mt76;
-	struct mt7921_phy *phy = &dev->phy;
+	struct mt792x_phy *phy = &dev->phy;
 	const struct firmware *fw;
 	int ret, i, len, offset = 0;
 	u8 *clc_base = NULL, hw_encap = 0;
@@ -635,7 +635,7 @@ int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif)
 				 &req_mu, sizeof(req_mu), false);
 }
 
-int mt7921_mcu_set_roc(struct mt7921_phy *phy, struct mt792x_vif *vif,
+int mt7921_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 		       struct ieee80211_channel *chan, int duration,
 		       enum mt7921_roc_req type, u8 token_id)
 {
@@ -702,7 +702,7 @@ int mt7921_mcu_set_roc(struct mt7921_phy *phy, struct mt792x_vif *vif,
 				 &req, sizeof(req), false);
 }
 
-int mt7921_mcu_abort_roc(struct mt7921_phy *phy, struct mt792x_vif *vif,
+int mt7921_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 			 u8 token_id)
 {
 	struct mt7921_dev *dev = phy->dev;
@@ -732,7 +732,7 @@ int mt7921_mcu_abort_roc(struct mt7921_phy *phy, struct mt792x_vif *vif,
 				 &req, sizeof(req), false);
 }
 
-int mt7921_mcu_set_chan_info(struct mt7921_phy *phy, int cmd)
+int mt7921_mcu_set_chan_info(struct mt792x_phy *phy, int cmd)
 {
 	struct mt7921_dev *dev = phy->dev;
 	struct cfg80211_chan_def *chandef = &phy->mt76->chandef;
@@ -1286,7 +1286,7 @@ int __mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
 int mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
 		       enum environment_cap env_cap)
 {
-	struct mt7921_phy *phy = (struct mt7921_phy *)&dev->phy;
+	struct mt792x_phy *phy = (struct mt792x_phy *)&dev->phy;
 	int i, ret;
 
 	/* submit all clc config */
@@ -1305,7 +1305,7 @@ int mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
 	return 0;
 }
 
-int mt7921_mcu_get_temperature(struct mt7921_phy *phy)
+int mt7921_mcu_get_temperature(struct mt792x_phy *phy)
 {
 	struct mt7921_dev *dev = phy->dev;
 	struct {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 4d409ba3fc21f..d9550b0aba617 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -168,7 +168,7 @@ struct mt792x_vif {
 	struct mt792x_sta sta;
 	struct mt792x_sta *wep_sta;
 
-	struct mt7921_phy *phy;
+	struct mt792x_phy *phy;
 
 	struct ewma_rssi rssi;
 
@@ -199,7 +199,7 @@ struct mt7921_clc {
 	u8 data[];
 } __packed;
 
-struct mt7921_phy {
+struct mt792x_phy {
 	struct mt76_phy *mt76;
 	struct mt7921_dev *dev;
 
@@ -264,7 +264,7 @@ struct mt7921_dev {
 	};
 
 	const struct mt76_bus_ops *bus_ops;
-	struct mt7921_phy phy;
+	struct mt792x_phy phy;
 
 	struct work_struct reset_work;
 	bool hw_full_reset:1;
@@ -317,7 +317,7 @@ struct mt7921_txpwr {
 	} data[TXPWR_MAX_NUM];
 };
 
-static inline struct mt7921_phy *
+static inline struct mt792x_phy *
 mt7921_hw_phy(struct ieee80211_hw *hw)
 {
 	struct mt76_phy *phy = hw->priv;
@@ -342,7 +342,7 @@ extern const struct ieee80211_ops mt7921_ops;
 
 u32 mt7921_reg_map(struct mt7921_dev *dev, u32 addr);
 
-int __mt7921_start(struct mt7921_phy *phy);
+int __mt7921_start(struct mt792x_phy *phy);
 int mt7921_register_device(struct mt7921_dev *dev);
 void mt7921_unregister_device(struct mt7921_dev *dev);
 int mt7921_dma_init(struct mt7921_dev *dev);
@@ -355,10 +355,10 @@ int mt7921_mcu_set_bss_pm(struct mt7921_dev *dev, struct ieee80211_vif *vif,
 int mt7921_mcu_sta_update(struct mt7921_dev *dev, struct ieee80211_sta *sta,
 			  struct ieee80211_vif *vif, bool enable,
 			  enum mt76_sta_info_state state);
-int mt7921_mcu_set_chan_info(struct mt7921_phy *phy, int cmd);
+int mt7921_mcu_set_chan_info(struct mt792x_phy *phy, int cmd);
 int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif);
 int mt7921_mcu_set_eeprom(struct mt7921_dev *dev);
-int mt7921_mcu_get_rx_rate(struct mt7921_phy *phy, struct ieee80211_vif *vif,
+int mt7921_mcu_get_rx_rate(struct mt792x_phy *phy, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta, struct rate_info *rate);
 int mt7921_mcu_fw_log_2_host(struct mt7921_dev *dev, u8 ctrl);
 void mt7921_mcu_rx_event(struct mt7921_dev *dev, struct sk_buff *skb);
@@ -423,8 +423,8 @@ mt7921_skb_add_usb_sdio_hdr(struct mt7921_dev *dev, struct sk_buff *skb,
 void mt7921_stop(struct ieee80211_hw *hw);
 int mt7921_mac_init(struct mt7921_dev *dev);
 bool mt7921_mac_wtbl_update(struct mt7921_dev *dev, int idx, u32 mask);
-void mt7921_mac_reset_counters(struct mt7921_phy *phy);
-void mt7921_mac_set_timing(struct mt7921_phy *phy);
+void mt7921_mac_reset_counters(struct mt792x_phy *phy);
+void mt7921_mac_set_timing(struct mt792x_phy *phy);
 int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
 void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
@@ -433,7 +433,7 @@ void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta);
 void mt7921_mac_work(struct work_struct *work);
 void mt7921_mac_reset_work(struct work_struct *work);
-void mt7921_mac_update_mib_stats(struct mt7921_phy *phy);
+void mt7921_mac_update_mib_stats(struct mt792x_phy *phy);
 void mt7921_reset(struct mt76_dev *mdev);
 int mt7921e_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			   enum mt76_txq_id qid, struct mt76_wcid *wcid,
@@ -445,7 +445,7 @@ bool mt7921_rx_check(struct mt76_dev *mdev, void *data, int len);
 void mt7921_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			 struct sk_buff *skb, u32 *info);
 void mt7921_stats_work(struct work_struct *work);
-void mt7921_set_stream_he_caps(struct mt7921_phy *phy);
+void mt7921_set_stream_he_caps(struct mt792x_phy *phy);
 void mt7921_update_channel(struct mt76_phy *mphy);
 int mt7921_init_debugfs(struct mt7921_dev *dev);
 
@@ -499,7 +499,7 @@ int mt7921_mcu_set_sniffer(struct mt7921_dev *dev, struct ieee80211_vif *vif,
 			   bool enable);
 int mt7921_mcu_config_sniffer(struct mt792x_vif *vif,
 			      struct ieee80211_chanctx_conf *ctx);
-int mt7921_mcu_get_temperature(struct mt7921_phy *phy);
+int mt7921_mcu_get_temperature(struct mt792x_phy *phy);
 
 int mt7921_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 				   enum mt76_txq_id qid, struct mt76_wcid *wcid,
@@ -524,8 +524,8 @@ int mt7921_mcu_uni_add_beacon_offload(struct mt7921_dev *dev,
 				      bool enable);
 #ifdef CONFIG_ACPI
 int mt7921_init_acpi_sar(struct mt7921_dev *dev);
-int mt7921_init_acpi_sar_power(struct mt7921_phy *phy, bool set_default);
-u8 mt7921_acpi_get_flags(struct mt7921_phy *phy);
+int mt7921_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default);
+u8 mt7921_acpi_get_flags(struct mt792x_phy *phy);
 #else
 static inline int
 mt7921_init_acpi_sar(struct mt7921_dev *dev)
@@ -534,13 +534,13 @@ mt7921_init_acpi_sar(struct mt7921_dev *dev)
 }
 
 static inline int
-mt7921_init_acpi_sar_power(struct mt7921_phy *phy, bool set_default)
+mt7921_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default)
 {
 	return 0;
 }
 
 static inline u8
-mt7921_acpi_get_flags(struct mt7921_phy *phy)
+mt7921_acpi_get_flags(struct mt792x_phy *phy)
 {
 	return 0;
 }
@@ -550,10 +550,10 @@ int mt7921_set_tx_sar_pwr(struct ieee80211_hw *hw,
 
 int mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
 		       enum environment_cap env_cap);
-int mt7921_mcu_set_roc(struct mt7921_phy *phy, struct mt792x_vif *vif,
+int mt7921_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 		       struct ieee80211_channel *chan, int duration,
 		       enum mt7921_roc_req type, u8 token_id);
-int mt7921_mcu_abort_roc(struct mt7921_phy *phy, struct mt792x_vif *vif,
+int mt7921_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 			 u8 token_id);
 struct ieee80211_ops *mt7921_get_mac80211_ops(struct device *dev,
 					      void *drv_data, u8 *fw_features);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c
index 7f408212e7163..208dcb2afbe79 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c
@@ -113,7 +113,7 @@ int mt7921_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct nlattr *tb[NUM_MT76_TM_ATTRS];
 	struct mt76_phy *mphy = hw->priv;
-	struct mt7921_phy *phy = mphy->priv;
+	struct mt792x_phy *phy = mphy->priv;
 	int err;
 
 	if (!test_bit(MT76_STATE_RUNNING, &mphy->state) ||
@@ -150,7 +150,7 @@ int mt7921_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *msg,
 {
 	struct nlattr *tb[NUM_MT76_TM_ATTRS];
 	struct mt76_phy *mphy = hw->priv;
-	struct mt7921_phy *phy = mphy->priv;
+	struct mt792x_phy *phy = mphy->priv;
 	int err;
 
 	if (!test_bit(MT76_STATE_RUNNING, &mphy->state) ||
-- 
GitLab


From 975e122ddb7cd6f67bff974d2ea00c5568d2014c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:52 +0800
Subject: [PATCH 0462/1806] wifi: mt76: mt7921: rename mt7921_dev in mt792x_dev

This is a preliminary patch to introduce WiFi7 chipset support

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7921/acpi_sar.c  |  12 +-
 .../wireless/mediatek/mt76/mt7921/debugfs.c   |  38 ++---
 .../net/wireless/mediatek/mt76/mt7921/dma.c   |  26 ++--
 .../net/wireless/mediatek/mt76/mt7921/init.c  |  20 +--
 .../net/wireless/mediatek/mt76/mt7921/mac.c   |  58 ++++----
 .../net/wireless/mediatek/mt76/mt7921/main.c  |  88 ++++++------
 .../net/wireless/mediatek/mt76/mt7921/mcu.c   |  74 +++++-----
 .../wireless/mediatek/mt76/mt7921/mt7921.h    | 132 +++++++++---------
 .../mediatek/mt76/mt7921/mt7921_trace.h       |   2 +-
 .../net/wireless/mediatek/mt76/mt7921/pci.c   |  26 ++--
 .../wireless/mediatek/mt76/mt7921/pci_mac.c   |   4 +-
 .../wireless/mediatek/mt76/mt7921/pci_mcu.c   |  12 +-
 .../net/wireless/mediatek/mt76/mt7921/sdio.c  |  14 +-
 .../wireless/mediatek/mt76/mt7921/sdio_mac.c  |   6 +-
 .../wireless/mediatek/mt76/mt7921/sdio_mcu.c  |  12 +-
 .../wireless/mediatek/mt76/mt7921/testmode.c  |   4 +-
 .../net/wireless/mediatek/mt76/mt7921/usb.c   |  20 +--
 .../wireless/mediatek/mt76/mt7921/usb_mac.c   |  16 +--
 18 files changed, 282 insertions(+), 282 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c b/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
index 06f2acdbfe1c7..057767ab45ffb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
@@ -5,7 +5,7 @@
 #include "mt7921.h"
 
 static int
-mt7921_acpi_read(struct mt7921_dev *dev, u8 *method, u8 **tbl, u32 *len)
+mt7921_acpi_read(struct mt792x_dev *dev, u8 *method, u8 **tbl, u32 *len)
 {
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *sar_root, *sar_unit;
@@ -65,7 +65,7 @@ free:
 
 /* MTCL : Country List Table for 6G band */
 static int
-mt7921_asar_acpi_read_mtcl(struct mt7921_dev *dev, u8 **table, u8 *version)
+mt7921_asar_acpi_read_mtcl(struct mt792x_dev *dev, u8 **table, u8 *version)
 {
 	*version = (mt7921_acpi_read(dev, MT7921_ACPI_MTCL, table, NULL) < 0)
 		   ? 1 : 2;
@@ -74,7 +74,7 @@ mt7921_asar_acpi_read_mtcl(struct mt7921_dev *dev, u8 **table, u8 *version)
 
 /* MTDS : Dynamic SAR Power Table */
 static int
-mt7921_asar_acpi_read_mtds(struct mt7921_dev *dev, u8 **table, u8 version)
+mt7921_asar_acpi_read_mtds(struct mt792x_dev *dev, u8 **table, u8 version)
 {
 	int len, ret, sarlen, prelen, tblcnt;
 	bool enable;
@@ -109,7 +109,7 @@ mt7921_asar_acpi_read_mtds(struct mt7921_dev *dev, u8 **table, u8 version)
 
 /* MTGS : Geo SAR Power Table */
 static int
-mt7921_asar_acpi_read_mtgs(struct mt7921_dev *dev, u8 **table, u8 version)
+mt7921_asar_acpi_read_mtgs(struct mt792x_dev *dev, u8 **table, u8 version)
 {
 	int len, ret = 0, sarlen, prelen, tblcnt;
 
@@ -140,7 +140,7 @@ mt7921_asar_acpi_read_mtgs(struct mt7921_dev *dev, u8 **table, u8 version)
 
 /* MTFG : Flag Table */
 static int
-mt7921_asar_acpi_read_mtfg(struct mt7921_dev *dev, u8 **table)
+mt7921_asar_acpi_read_mtfg(struct mt792x_dev *dev, u8 **table)
 {
 	int len, ret;
 
@@ -154,7 +154,7 @@ mt7921_asar_acpi_read_mtfg(struct mt7921_dev *dev, u8 **table)
 	return ret;
 }
 
-int mt7921_init_acpi_sar(struct mt7921_dev *dev)
+int mt7921_init_acpi_sar(struct mt792x_dev *dev)
 {
 	struct mt7921_acpi_sar *asar;
 	int ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
index baa640e8a9825..6137a10c022ab 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
@@ -6,7 +6,7 @@
 static int
 mt7921_reg_set(void *data, u64 val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 
 	mt7921_mutex_acquire(dev);
 	mt76_wr(dev, dev->mt76.debugfs_reg, val);
@@ -18,7 +18,7 @@ mt7921_reg_set(void *data, u64 val)
 static int
 mt7921_reg_get(void *data, u64 *val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 
 	mt7921_mutex_acquire(dev);
 	*val = mt76_rr(dev, dev->mt76.debugfs_reg);
@@ -32,7 +32,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_regval, mt7921_reg_get, mt7921_reg_set,
 static int
 mt7921_fw_debug_set(void *data, u64 val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 
 	mt7921_mutex_acquire(dev);
 
@@ -47,7 +47,7 @@ mt7921_fw_debug_set(void *data, u64 val)
 static int
 mt7921_fw_debug_get(void *data, u64 *val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 
 	*val = dev->fw_debug;
 
@@ -61,7 +61,7 @@ static void
 mt7921_ampdu_stat_read_phy(struct mt792x_phy *phy,
 			   struct seq_file *file)
 {
-	struct mt7921_dev *dev = file->private;
+	struct mt792x_dev *dev = file->private;
 	int bound[15], range[4], i;
 
 	if (!phy)
@@ -93,7 +93,7 @@ mt7921_ampdu_stat_read_phy(struct mt792x_phy *phy,
 static int
 mt7921_tx_stats_show(struct seq_file *file, void *data)
 {
-	struct mt7921_dev *dev = file->private;
+	struct mt792x_dev *dev = file->private;
 	struct mt792x_phy *phy = &dev->phy;
 	struct mt76_mib_stats *mib = &phy->mib;
 	int i;
@@ -123,7 +123,7 @@ DEFINE_SHOW_ATTRIBUTE(mt7921_tx_stats);
 static int
 mt7921_queues_acq(struct seq_file *s, void *data)
 {
-	struct mt7921_dev *dev = dev_get_drvdata(s->private);
+	struct mt792x_dev *dev = dev_get_drvdata(s->private);
 	int i;
 
 	mt7921_mutex_acquire(dev);
@@ -154,7 +154,7 @@ mt7921_queues_acq(struct seq_file *s, void *data)
 static int
 mt7921_queues_read(struct seq_file *s, void *data)
 {
-	struct mt7921_dev *dev = dev_get_drvdata(s->private);
+	struct mt792x_dev *dev = dev_get_drvdata(s->private);
 	struct {
 		struct mt76_queue *q;
 		char *queue;
@@ -211,7 +211,7 @@ mt7921_seq_puts_array(struct seq_file *file, const char *str,
 static int
 mt7921_txpwr(struct seq_file *s, void *data)
 {
-	struct mt7921_dev *dev = dev_get_drvdata(s->private);
+	struct mt792x_dev *dev = dev_get_drvdata(s->private);
 	struct mt7921_txpwr txpwr;
 	int ret;
 
@@ -263,7 +263,7 @@ mt7921_txpwr(struct seq_file *s, void *data)
 static int
 mt7921_pm_set(void *data, u64 val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 	struct mt76_connac_pm *pm = &dev->pm;
 
 	if (mt76_is_usb(&dev->mt76))
@@ -296,7 +296,7 @@ out:
 static int
 mt7921_pm_get(void *data, u64 *val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 
 	*val = dev->pm.enable_user;
 
@@ -308,7 +308,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_pm, mt7921_pm_get, mt7921_pm_set, "%lld\n");
 static int
 mt7921_deep_sleep_set(void *data, u64 val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 	struct mt76_connac_pm *pm = &dev->pm;
 	bool monitor = !!(dev->mphy.hw->conf.flags & IEEE80211_CONF_MONITOR);
 	bool enable = !!val;
@@ -332,7 +332,7 @@ out:
 static int
 mt7921_deep_sleep_get(void *data, u64 *val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 
 	*val = dev->pm.ds_enable_user;
 
@@ -345,7 +345,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_ds, mt7921_deep_sleep_get,
 static int
 mt7921_pm_stats(struct seq_file *s, void *data)
 {
-	struct mt7921_dev *dev = dev_get_drvdata(s->private);
+	struct mt792x_dev *dev = dev_get_drvdata(s->private);
 	struct mt76_connac_pm *pm = &dev->pm;
 
 	unsigned long awake_time = pm->stats.awake_time;
@@ -368,7 +368,7 @@ mt7921_pm_stats(struct seq_file *s, void *data)
 static int
 mt7921_pm_idle_timeout_set(void *data, u64 val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 
 	dev->pm.idle_timeout = msecs_to_jiffies(val);
 
@@ -378,7 +378,7 @@ mt7921_pm_idle_timeout_set(void *data, u64 val)
 static int
 mt7921_pm_idle_timeout_get(void *data, u64 *val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 
 	*val = jiffies_to_msecs(dev->pm.idle_timeout);
 
@@ -390,7 +390,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_pm_idle_timeout, mt7921_pm_idle_timeout_get,
 
 static int mt7921_chip_reset(void *data, u64 val)
 {
-	struct mt7921_dev *dev = data;
+	struct mt792x_dev *dev = data;
 	int ret = 0;
 
 	switch (val) {
@@ -414,7 +414,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_reset, NULL, mt7921_chip_reset, "%lld\n");
 static int
 mt7921s_sched_quota_read(struct seq_file *s, void *data)
 {
-	struct mt7921_dev *dev = dev_get_drvdata(s->private);
+	struct mt792x_dev *dev = dev_get_drvdata(s->private);
 	struct mt76_sdio *sdio = &dev->mt76.sdio;
 
 	seq_printf(s, "pse_data_quota\t%d\n", sdio->sched.pse_data_quota);
@@ -425,7 +425,7 @@ mt7921s_sched_quota_read(struct seq_file *s, void *data)
 	return 0;
 }
 
-int mt7921_init_debugfs(struct mt7921_dev *dev)
+int mt7921_init_debugfs(struct mt792x_dev *dev)
 {
 	struct dentry *dir;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
index 4153cd6c2a01d..3c628962641b6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
@@ -7,9 +7,9 @@
 
 static int mt7921_poll_tx(struct napi_struct *napi, int budget)
 {
-	struct mt7921_dev *dev;
+	struct mt792x_dev *dev;
 
-	dev = container_of(napi, struct mt7921_dev, mt76.tx_napi);
+	dev = container_of(napi, struct mt792x_dev, mt76.tx_napi);
 
 	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
 		napi_complete(napi);
@@ -27,10 +27,10 @@ static int mt7921_poll_tx(struct napi_struct *napi, int budget)
 
 static int mt7921_poll_rx(struct napi_struct *napi, int budget)
 {
-	struct mt7921_dev *dev;
+	struct mt792x_dev *dev;
 	int done;
 
-	dev = container_of(napi->dev, struct mt7921_dev, mt76.napi_dev);
+	dev = container_of(napi->dev, struct mt792x_dev, mt76.napi_dev);
 
 	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
 		napi_complete(napi);
@@ -43,7 +43,7 @@ static int mt7921_poll_rx(struct napi_struct *napi, int budget)
 	return done;
 }
 
-static void mt7921_dma_prefetch(struct mt7921_dev *dev)
+static void mt7921_dma_prefetch(struct mt792x_dev *dev)
 {
 #define PREFETCH(base, depth)	((base) << 16 | (depth))
 
@@ -64,7 +64,7 @@ static void mt7921_dma_prefetch(struct mt7921_dev *dev)
 	mt76_wr(dev, MT_WFDMA0_TX_RING17_EXT_CTRL, PREFETCH(0x380, 0x4));
 }
 
-static int mt7921_dma_disable(struct mt7921_dev *dev, bool force)
+static int mt7921_dma_disable(struct mt792x_dev *dev, bool force)
 {
 	/* disable WFDMA0 */
 	mt76_clear(dev, MT_WFDMA0_GLO_CFG,
@@ -98,7 +98,7 @@ static int mt7921_dma_disable(struct mt7921_dev *dev, bool force)
 	return 0;
 }
 
-static int mt7921_dma_enable(struct mt7921_dev *dev)
+static int mt7921_dma_enable(struct mt792x_dev *dev)
 {
 	/* configure perfetch settings */
 	mt7921_dma_prefetch(dev);
@@ -131,7 +131,7 @@ static int mt7921_dma_enable(struct mt7921_dev *dev)
 	return 0;
 }
 
-static int mt7921_dma_reset(struct mt7921_dev *dev, bool force)
+static int mt7921_dma_reset(struct mt792x_dev *dev, bool force)
 {
 	int i, err;
 
@@ -154,7 +154,7 @@ static int mt7921_dma_reset(struct mt7921_dev *dev, bool force)
 	return mt7921_dma_enable(dev);
 }
 
-int mt7921_wfsys_reset(struct mt7921_dev *dev)
+int mt7921_wfsys_reset(struct mt792x_dev *dev)
 {
 	mt76_clear(dev, MT_WFSYS_SW_RST_B, WFSYS_SW_RST_B);
 	msleep(50);
@@ -167,7 +167,7 @@ int mt7921_wfsys_reset(struct mt7921_dev *dev)
 	return 0;
 }
 
-int mt7921_wpdma_reset(struct mt7921_dev *dev, bool force)
+int mt7921_wpdma_reset(struct mt792x_dev *dev, bool force)
 {
 	int i, err;
 
@@ -196,7 +196,7 @@ int mt7921_wpdma_reset(struct mt7921_dev *dev, bool force)
 	return 0;
 }
 
-int mt7921_wpdma_reinit_cond(struct mt7921_dev *dev)
+int mt7921_wpdma_reinit_cond(struct mt792x_dev *dev)
 {
 	struct mt76_connac_pm *pm = &dev->pm;
 	int err;
@@ -221,7 +221,7 @@ int mt7921_wpdma_reinit_cond(struct mt7921_dev *dev)
 	return 0;
 }
 
-int mt7921_dma_init(struct mt7921_dev *dev)
+int mt7921_dma_init(struct mt792x_dev *dev)
 {
 	int ret;
 
@@ -286,7 +286,7 @@ int mt7921_dma_init(struct mt7921_dev *dev)
 	return mt7921_dma_enable(dev);
 }
 
-void mt7921_dma_cleanup(struct mt7921_dev *dev)
+void mt7921_dma_cleanup(struct mt792x_dev *dev)
 {
 	/* disable */
 	mt76_clear(dev, MT_WFDMA0_GLO_CFG,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index d383586eb429b..bace86813b768 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -61,7 +61,7 @@ static ssize_t mt7921_thermal_temp_show(struct device *dev,
 	switch (to_sensor_dev_attr(attr)->index) {
 	case 0: {
 		struct mt792x_phy *phy = dev_get_drvdata(dev);
-		struct mt7921_dev *mdev = phy->dev;
+		struct mt792x_dev *mdev = phy->dev;
 		int temperature;
 
 		mt7921_mutex_acquire(mdev);
@@ -110,7 +110,7 @@ mt7921_regd_notifier(struct wiphy *wiphy,
 		     struct regulatory_request *request)
 {
 	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	memcpy(dev->mt76.alpha2, request->alpha2, sizeof(dev->mt76.alpha2));
 	dev->mt76.region = request->dfs_region;
@@ -127,7 +127,7 @@ static int
 mt7921_init_wiphy(struct ieee80211_hw *hw)
 {
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 	struct wiphy *wiphy = hw->wiphy;
 
 	hw->queues = 4;
@@ -200,7 +200,7 @@ mt7921_init_wiphy(struct ieee80211_hw *hw)
 }
 
 static void
-mt7921_mac_init_band(struct mt7921_dev *dev, u8 band)
+mt7921_mac_init_band(struct mt792x_dev *dev, u8 band)
 {
 	u32 mask, set;
 
@@ -309,7 +309,7 @@ mt7921_get_mac80211_ops(struct device *dev, void *drv_data, u8 *fw_features)
 }
 EXPORT_SYMBOL_GPL(mt7921_get_mac80211_ops);
 
-int mt7921_mac_init(struct mt7921_dev *dev)
+int mt7921_mac_init(struct mt792x_dev *dev)
 {
 	int i;
 
@@ -329,7 +329,7 @@ int mt7921_mac_init(struct mt7921_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt7921_mac_init);
 
-static int __mt7921_init_hardware(struct mt7921_dev *dev)
+static int __mt7921_init_hardware(struct mt792x_dev *dev)
 {
 	int ret;
 
@@ -352,7 +352,7 @@ out:
 	return ret;
 }
 
-static int mt7921_init_hardware(struct mt7921_dev *dev)
+static int mt7921_init_hardware(struct mt792x_dev *dev)
 {
 	int ret, i;
 
@@ -374,7 +374,7 @@ static int mt7921_init_hardware(struct mt7921_dev *dev)
 	return 0;
 }
 
-static int mt7921_init_wcid(struct mt7921_dev *dev)
+static int mt7921_init_wcid(struct mt792x_dev *dev)
 {
 	int idx;
 
@@ -393,7 +393,7 @@ static int mt7921_init_wcid(struct mt7921_dev *dev)
 
 static void mt7921_init_work(struct work_struct *work)
 {
-	struct mt7921_dev *dev = container_of(work, struct mt7921_dev,
+	struct mt792x_dev *dev = container_of(work, struct mt792x_dev,
 					      init_work);
 	int ret;
 
@@ -429,7 +429,7 @@ static void mt7921_init_work(struct work_struct *work)
 	mt76_connac_mcu_set_deep_sleep(&dev->mt76, dev->pm.ds_enable);
 }
 
-int mt7921_register_device(struct mt7921_dev *dev)
+int mt7921_register_device(struct mt792x_dev *dev)
 {
 	struct ieee80211_hw *hw = mt76_hw(dev);
 	int ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 15c0e8be8f34d..a17d70aa90da9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -20,7 +20,7 @@ static u32 mt7921_mac_wtbl_lmac_addr(int idx, u8 offset)
 	return MT_WTBL_LMAC_OFFS(idx, 0) + offset * 4;
 }
 
-static struct mt76_wcid *mt7921_rx_get_wcid(struct mt7921_dev *dev,
+static struct mt76_wcid *mt7921_rx_get_wcid(struct mt792x_dev *dev,
 					    u16 idx, bool unicast)
 {
 	struct mt792x_sta *sta;
@@ -43,7 +43,7 @@ static struct mt76_wcid *mt7921_rx_get_wcid(struct mt7921_dev *dev,
 	return &sta->vif->sta.wcid;
 }
 
-bool mt7921_mac_wtbl_update(struct mt7921_dev *dev, int idx, u32 mask)
+bool mt7921_mac_wtbl_update(struct mt792x_dev *dev, int idx, u32 mask)
 {
 	mt76_rmw(dev, MT_WTBL_UPDATE, MT_WTBL_UPDATE_WLAN_IDX,
 		 FIELD_PREP(MT_WTBL_UPDATE_WLAN_IDX, idx) | mask);
@@ -52,7 +52,7 @@ bool mt7921_mac_wtbl_update(struct mt7921_dev *dev, int idx, u32 mask)
 			 0, 5000);
 }
 
-static void mt7921_mac_sta_poll(struct mt7921_dev *dev)
+static void mt7921_mac_sta_poll(struct mt792x_dev *dev)
 {
 	static const u8 ac_to_tid[] = {
 		[IEEE80211_AC_BE] = 0,
@@ -185,7 +185,7 @@ static void mt7921_mac_sta_poll(struct mt7921_dev *dev)
 }
 
 static void
-mt7921_get_status_freq_info(struct mt7921_dev *dev, struct mt76_phy *mphy,
+mt7921_get_status_freq_info(struct mt792x_dev *dev, struct mt76_phy *mphy,
 			    struct mt76_rx_status *status, u8 chfreq)
 {
 	if (chfreq > 180) {
@@ -217,7 +217,7 @@ mt7921_mac_rssi_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
 }
 
 static void
-mt7921_mac_assoc_rssi(struct mt7921_dev *dev, struct sk_buff *skb)
+mt7921_mac_assoc_rssi(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = mt76_skb_get_hdr(skb);
 
@@ -231,7 +231,7 @@ mt7921_mac_assoc_rssi(struct mt7921_dev *dev, struct sk_buff *skb)
 }
 
 static int
-mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb)
+mt7921_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	u32 csum_mask = MT_RXD0_NORMAL_IP_SUM | MT_RXD0_NORMAL_UDP_TCP_SUM;
 	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
@@ -511,7 +511,7 @@ mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb)
 	return 0;
 }
 
-void mt7921_mac_add_txs(struct mt7921_dev *dev, void *data)
+void mt7921_mac_add_txs(struct mt792x_dev *dev, void *data)
 {
 	struct mt792x_sta *msta = NULL;
 	struct mt76_wcid *wcid;
@@ -552,7 +552,7 @@ out:
 	rcu_read_unlock();
 }
 
-static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
+static void mt7921_mac_tx_free(struct mt792x_dev *dev, void *data, int len)
 {
 	struct mt76_connac_tx_free *free = data;
 	__le32 *tx_info = (__le32 *)(data + sizeof(*free));
@@ -634,7 +634,7 @@ static void mt7921_mac_tx_free(struct mt7921_dev *dev, void *data, int len)
 
 bool mt7921_rx_check(struct mt76_dev *mdev, void *data, int len)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	__le32 *rxd = (__le32 *)data;
 	__le32 *end = (__le32 *)&rxd[len / 4];
 	enum rx_pkt_type type;
@@ -659,7 +659,7 @@ EXPORT_SYMBOL_GPL(mt7921_rx_check);
 void mt7921_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			 struct sk_buff *skb, u32 *info)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	__le32 *rxd = (__le32 *)skb->data;
 	__le32 *end = (__le32 *)&skb->data[skb->len];
 	enum rx_pkt_type type;
@@ -701,7 +701,7 @@ EXPORT_SYMBOL_GPL(mt7921_queue_rx_skb);
 
 void mt7921_mac_reset_counters(struct mt792x_phy *phy)
 {
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 	int i;
 
 	for (i = 0; i < 4; i++) {
@@ -724,7 +724,7 @@ void mt7921_mac_reset_counters(struct mt792x_phy *phy)
 void mt7921_mac_set_timing(struct mt792x_phy *phy)
 {
 	s16 coverage_class = phy->coverage_class;
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 	u32 val, reg_offset;
 	u32 cck = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, 231) |
 		  FIELD_PREP(MT_TIMEOUT_VAL_CCA, 48);
@@ -771,7 +771,7 @@ mt7921_phy_get_nf(struct mt792x_phy *phy, int idx)
 static void
 mt7921_phy_update_channel(struct mt76_phy *mphy, int idx)
 {
-	struct mt7921_dev *dev = container_of(mphy->dev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mphy->dev, struct mt792x_dev, mt76);
 	struct mt792x_phy *phy = (struct mt792x_phy *)mphy->priv;
 	struct mt76_channel_state *state;
 	u64 busy_time, tx_time, rx_time, obss_time;
@@ -802,7 +802,7 @@ mt7921_phy_update_channel(struct mt76_phy *mphy, int idx)
 
 void mt7921_update_channel(struct mt76_phy *mphy)
 {
-	struct mt7921_dev *dev = container_of(mphy->dev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mphy->dev, struct mt792x_dev, mt76);
 
 	if (mt76_connac_pm_wake(mphy, &dev->pm))
 		return;
@@ -820,7 +820,7 @@ mt7921_vif_connect_iter(void *priv, u8 *mac,
 			struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_dev *dev = mvif->phy->dev;
+	struct mt792x_dev *dev = mvif->phy->dev;
 	struct ieee80211_hw *hw = mt76_hw(dev);
 
 	if (vif->type == NL80211_IFTYPE_STATION)
@@ -841,7 +841,7 @@ mt7921_vif_connect_iter(void *priv, u8 *mac,
 /* system error recovery */
 void mt7921_mac_reset_work(struct work_struct *work)
 {
-	struct mt7921_dev *dev = container_of(work, struct mt7921_dev,
+	struct mt792x_dev *dev = container_of(work, struct mt792x_dev,
 					      reset_work);
 	struct ieee80211_hw *hw = mt76_hw(dev);
 	struct mt76_connac_pm *pm = &dev->pm;
@@ -886,7 +886,7 @@ void mt7921_mac_reset_work(struct work_struct *work)
 
 void mt7921_reset(struct mt76_dev *mdev)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct mt76_connac_pm *pm = &dev->pm;
 
 	if (!dev->hw_init_done)
@@ -905,7 +905,7 @@ EXPORT_SYMBOL_GPL(mt7921_reset);
 void mt7921_mac_update_mib_stats(struct mt792x_phy *phy)
 {
 	struct mt76_mib_stats *mib = &phy->mib;
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 	int i, aggr0 = 0, aggr1;
 	u32 val;
 
@@ -989,10 +989,10 @@ void mt7921_mac_work(struct work_struct *work)
 
 void mt7921_pm_wake_work(struct work_struct *work)
 {
-	struct mt7921_dev *dev;
+	struct mt792x_dev *dev;
 	struct mt76_phy *mphy;
 
-	dev = (struct mt7921_dev *)container_of(work, struct mt7921_dev,
+	dev = (struct mt792x_dev *)container_of(work, struct mt792x_dev,
 						pm.wake_work);
 	mphy = dev->phy.mt76;
 
@@ -1022,11 +1022,11 @@ void mt7921_pm_wake_work(struct work_struct *work)
 
 void mt7921_pm_power_save_work(struct work_struct *work)
 {
-	struct mt7921_dev *dev;
+	struct mt792x_dev *dev;
 	unsigned long delta;
 	struct mt76_phy *mphy;
 
-	dev = (struct mt7921_dev *)container_of(work, struct mt7921_dev,
+	dev = (struct mt792x_dev *)container_of(work, struct mt792x_dev,
 						pm.ps_work.work);
 	mphy = dev->phy.mt76;
 
@@ -1059,10 +1059,10 @@ out:
 
 void mt7921_coredump_work(struct work_struct *work)
 {
-	struct mt7921_dev *dev;
+	struct mt792x_dev *dev;
 	char *dump, *data;
 
-	dev = (struct mt7921_dev *)container_of(work, struct mt7921_dev,
+	dev = (struct mt792x_dev *)container_of(work, struct mt792x_dev,
 						coredump.work.work);
 
 	if (time_is_after_jiffies(dev->coredump.last_activity +
@@ -1106,7 +1106,7 @@ void mt7921_coredump_work(struct work_struct *work)
 
 /* usb_sdio */
 static void
-mt7921_usb_sdio_write_txwi(struct mt7921_dev *dev, struct mt76_wcid *wcid,
+mt7921_usb_sdio_write_txwi(struct mt792x_dev *dev, struct mt76_wcid *wcid,
 			   enum mt76_txq_id qid, struct ieee80211_sta *sta,
 			   struct ieee80211_key_conf *key, int pid,
 			   struct sk_buff *skb)
@@ -1123,7 +1123,7 @@ int mt7921_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 				   struct ieee80211_sta *sta,
 				   struct mt76_tx_info *tx_info)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_info->skb);
 	struct ieee80211_key_conf *key = info->control.hw_key;
 	struct sk_buff *skb = tx_info->skb;
@@ -1189,7 +1189,7 @@ EXPORT_SYMBOL_GPL(mt7921_usb_sdio_tx_complete_skb);
 
 bool mt7921_usb_sdio_tx_status_data(struct mt76_dev *mdev, u8 *update)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 
 	mt7921_mutex_acquire(dev);
 	mt7921_mac_sta_poll(dev);
@@ -1202,8 +1202,8 @@ EXPORT_SYMBOL_GPL(mt7921_usb_sdio_tx_status_data);
 #if IS_ENABLED(CONFIG_IPV6)
 void mt7921_set_ipv6_ns_work(struct work_struct *work)
 {
-	struct mt7921_dev *dev = container_of(work, struct mt7921_dev,
-						ipv6_ns_work);
+	struct mt792x_dev *dev = container_of(work, struct mt792x_dev,
+					      ipv6_ns_work);
 	struct sk_buff *skb;
 	int ret = 0;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index fc9a306344cd9..2f597fb3ae5c7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -264,7 +264,7 @@ static int mt7921_start(struct ieee80211_hw *hw)
 
 void mt7921_stop(struct ieee80211_hw *hw)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	cancel_delayed_work_sync(&phy->mt76->mac_work);
@@ -285,7 +285,7 @@ static int mt7921_add_interface(struct ieee80211_hw *hw,
 				struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt76_txq *mtxq;
 	int idx, ret = 0;
@@ -343,7 +343,7 @@ static void mt7921_remove_interface(struct ieee80211_hw *hw,
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_sta *msta = &mvif->sta;
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int idx = msta->wcid.idx;
 
@@ -472,7 +472,7 @@ static int mt7921_cancel_remain_on_channel(struct ieee80211_hw *hw,
 
 static int mt7921_set_channel(struct mt792x_phy *phy)
 {
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 	int ret;
 
 	cancel_delayed_work_sync(&phy->mt76->mac_work);
@@ -506,7 +506,7 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			  struct ieee80211_vif *vif, struct ieee80211_sta *sta,
 			  struct ieee80211_key_conf *key)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_sta *msta = sta ? (struct mt792x_sta *)sta->drv_priv :
 				  &mvif->sta;
@@ -578,7 +578,7 @@ out:
 static void
 mt7921_pm_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
 {
-	struct mt7921_dev *dev = priv;
+	struct mt792x_dev *dev = priv;
 	struct ieee80211_hw *hw = mt76_hw(dev);
 	bool pm_enable = dev->pm.enable;
 	int err;
@@ -599,7 +599,7 @@ mt7921_pm_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
 static void
 mt7921_sniffer_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
 {
-	struct mt7921_dev *dev = priv;
+	struct mt792x_dev *dev = priv;
 	struct ieee80211_hw *hw = mt76_hw(dev);
 	struct mt76_connac_pm *pm = &dev->pm;
 	bool monitor = !!(hw->conf.flags & IEEE80211_CONF_MONITOR);
@@ -614,7 +614,7 @@ mt7921_sniffer_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
 		mt7921_mcu_set_beacon_filter(dev, vif, false);
 }
 
-void mt7921_set_runtime_pm(struct mt7921_dev *dev)
+void mt7921_set_runtime_pm(struct mt792x_dev *dev)
 {
 	struct ieee80211_hw *hw = mt76_hw(dev);
 	struct mt76_connac_pm *pm = &dev->pm;
@@ -630,7 +630,7 @@ void mt7921_set_runtime_pm(struct mt7921_dev *dev)
 
 static int mt7921_config(struct ieee80211_hw *hw, u32 changed)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int ret = 0;
 
@@ -686,7 +686,7 @@ static void mt7921_configure_filter(struct ieee80211_hw *hw,
 #define MT7921_FILTER_OTHER_BSS  BIT(6)
 #define MT7921_FILTER_ENABLE     BIT(31)
 
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	u32 flags = MT7921_FILTER_ENABLE;
 
 #define MT7921_FILTER(_fif, _type) do {			\
@@ -711,7 +711,7 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 				    u64 changed)
 {
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	mt7921_mutex_acquire(dev);
 
@@ -755,7 +755,7 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	int ret, idx;
@@ -796,7 +796,7 @@ EXPORT_SYMBOL_GPL(mt7921_mac_sta_add);
 void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			  struct ieee80211_sta *sta)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 
@@ -821,7 +821,7 @@ EXPORT_SYMBOL_GPL(mt7921_mac_sta_assoc);
 void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 
 	mt76_connac_free_pending_tx_skbs(&dev->pm, &msta->wcid);
@@ -853,7 +853,7 @@ EXPORT_SYMBOL_GPL(mt7921_mac_sta_remove);
 
 void mt7921_tx_worker(struct mt76_worker *w)
 {
-	struct mt7921_dev *dev = container_of(w, struct mt7921_dev,
+	struct mt792x_dev *dev = container_of(w, struct mt792x_dev,
 					      mt76.tx_worker);
 
 	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
@@ -869,7 +869,7 @@ static void mt7921_tx(struct ieee80211_hw *hw,
 		      struct ieee80211_tx_control *control,
 		      struct sk_buff *skb)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_vif *vif = info->control.vif;
@@ -907,7 +907,7 @@ static void mt7921_tx(struct ieee80211_hw *hw,
 
 static int mt7921_set_rts_threshold(struct ieee80211_hw *hw, u32 val)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	mt7921_mutex_acquire(dev);
 	mt76_connac_mcu_set_rts_thresh(&dev->mt76, val, 0);
@@ -921,7 +921,7 @@ mt7921_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		    struct ieee80211_ampdu_params *params)
 {
 	enum ieee80211_ampdu_mlme_action action = params->action;
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct ieee80211_sta *sta = params->sta;
 	struct ieee80211_txq *txq = sta->txq[params->tid];
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
@@ -979,7 +979,7 @@ static int mt7921_sta_state(struct ieee80211_hw *hw,
 			    enum ieee80211_sta_state old_state,
 			    enum ieee80211_sta_state new_state)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	if (dev->pm.ds_enable) {
 		mt7921_mutex_acquire(dev);
@@ -1087,7 +1087,7 @@ static void
 mt7921_get_et_strings(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		      u32 sset, u8 *data)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	if (sset != ETH_SS_STATS)
 		return;
@@ -1105,7 +1105,7 @@ static int
 mt7921_get_et_sset_count(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			 int sset)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	if (sset != ETH_SS_STATS)
 		return 0;
@@ -1136,7 +1136,7 @@ void mt7921_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	int stats_size = ARRAY_SIZE(mt7921_gstrings_stats);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 	struct mt76_mib_stats *mib = &phy->mib;
 	struct mt76_ethtool_worker_info wi = {
 		.data = data,
@@ -1204,7 +1204,7 @@ static u64
 mt7921_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	u8 omac_idx = mvif->mt76.omac_idx;
 	union {
 		u64 t64;
@@ -1230,7 +1230,7 @@ mt7921_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       u64 timestamp)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	u8 omac_idx = mvif->mt76.omac_idx;
 	union {
 		u64 t64;
@@ -1253,7 +1253,7 @@ static void
 mt7921_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class)
 {
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 
 	mt7921_mutex_acquire(dev);
 	phy->coverage_class = max_t(s16, coverage_class, 0);
@@ -1298,7 +1298,7 @@ static int
 mt7921_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       struct ieee80211_scan_request *req)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 	int err;
 
@@ -1312,7 +1312,7 @@ mt7921_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 static void
 mt7921_cancel_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 
 	mt7921_mutex_acquire(dev);
@@ -1325,7 +1325,7 @@ mt7921_start_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			struct cfg80211_sched_scan_request *req,
 			struct ieee80211_scan_ies *ies)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 	int err;
 
@@ -1345,7 +1345,7 @@ out:
 static int
 mt7921_stop_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 	int err;
 
@@ -1359,7 +1359,7 @@ mt7921_stop_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 static int
 mt7921_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int max_nss = hweight8(hw->wiphy->available_antennas_tx);
 
@@ -1423,7 +1423,7 @@ static void mt7921_sta_statistics(struct ieee80211_hw *hw,
 static int mt7921_suspend(struct ieee80211_hw *hw,
 			  struct cfg80211_wowlan *wowlan)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	cancel_delayed_work_sync(&phy->scan_work);
@@ -1447,7 +1447,7 @@ static int mt7921_suspend(struct ieee80211_hw *hw,
 
 static int mt7921_resume(struct ieee80211_hw *hw)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	mt7921_mutex_acquire(dev);
@@ -1468,7 +1468,7 @@ static int mt7921_resume(struct ieee80211_hw *hw)
 
 static void mt7921_set_wakeup(struct ieee80211_hw *hw, bool enabled)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt76_dev *mdev = &dev->mt76;
 
 	device_set_wakeup_enable(mdev->dev, enabled);
@@ -1478,7 +1478,7 @@ static void mt7921_set_rekey_data(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
 				  struct cfg80211_gtk_rekey_data *data)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	mt7921_mutex_acquire(dev);
 	mt76_connac_mcu_update_gtk_rekey(hw, vif, data);
@@ -1489,7 +1489,7 @@ static void mt7921_set_rekey_data(struct ieee80211_hw *hw,
 static void mt7921_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			 u32 queues, bool drop)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	wait_event_timeout(dev->mt76.tx_wait, !mt76_has_tx_pending(&dev->mphy),
 			   HZ / 2);
@@ -1501,7 +1501,7 @@ static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw,
 					 bool enabled)
 {
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	mt7921_mutex_acquire(dev);
 
@@ -1522,7 +1522,7 @@ static void mt7921_ipv6_addr_change(struct ieee80211_hw *hw,
 				    struct inet6_dev *idev)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_dev *dev = mvif->phy->dev;
+	struct mt792x_dev *dev = mvif->phy->dev;
 	struct inet6_ifaddr *ifa;
 	struct in6_addr ns_addrs[IEEE80211_BSS_ARP_ADDR_LIST_LEN];
 	struct sk_buff *skb;
@@ -1598,7 +1598,7 @@ int mt7921_set_tx_sar_pwr(struct ieee80211_hw *hw,
 static int mt7921_set_sar_specs(struct ieee80211_hw *hw,
 				const struct cfg80211_sar_specs *sar)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	int err;
 
 	mt7921_mutex_acquire(dev);
@@ -1619,7 +1619,7 @@ mt7921_channel_switch_beacon(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif,
 			     struct cfg80211_chan_def *chandef)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	mt7921_mutex_acquire(dev);
 	mt7921_mcu_uni_add_beacon_offload(dev, hw, vif, true);
@@ -1632,7 +1632,7 @@ mt7921_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	int err;
 
 	mt7921_mutex_acquire(dev);
@@ -1660,7 +1660,7 @@ mt7921_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	int err;
 
 	mt7921_mutex_acquire(dev);
@@ -1725,7 +1725,7 @@ mt7921_assign_vif_chanctx(struct ieee80211_hw *hw,
 			  struct ieee80211_chanctx_conf *ctx)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	mutex_lock(&dev->mt76.mutex);
 	mvif->ctx = ctx;
@@ -1741,7 +1741,7 @@ mt7921_unassign_vif_chanctx(struct ieee80211_hw *hw,
 			    struct ieee80211_chanctx_conf *ctx)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	mutex_lock(&dev->mt76.mutex);
 	mvif->ctx = NULL;
@@ -1753,7 +1753,7 @@ static void mt7921_mgd_prepare_tx(struct ieee80211_hw *hw,
 				  struct ieee80211_prep_tx_info *info)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	u16 duration = info->duration ? info->duration :
 		       jiffies_to_msecs(HZ);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 06fecc9dc2203..db3394ba4e45f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -69,7 +69,7 @@ int mt7921_mcu_parse_response(struct mt76_dev *mdev, int cmd,
 }
 EXPORT_SYMBOL_GPL(mt7921_mcu_parse_response);
 
-static int mt7921_mcu_read_eeprom(struct mt7921_dev *dev, u32 offset, u8 *val)
+static int mt7921_mcu_read_eeprom(struct mt792x_dev *dev, u32 offset, u8 *val)
 {
 	struct mt7921_mcu_eeprom_info *res, req = {
 		.addr = cpu_to_le32(round_down(offset,
@@ -134,7 +134,7 @@ void mt7921_mcu_set_suspend_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
 #endif /* CONFIG_PM */
 
 static void
-mt7921_mcu_uni_roc_event(struct mt7921_dev *dev, struct sk_buff *skb)
+mt7921_mcu_uni_roc_event(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct mt7921_roc_grant_tlv *grant;
 	struct mt76_connac2_mcu_rxd *rxd;
@@ -157,7 +157,7 @@ mt7921_mcu_uni_roc_event(struct mt7921_dev *dev, struct sk_buff *skb)
 }
 
 static void
-mt7921_mcu_scan_event(struct mt7921_dev *dev, struct sk_buff *skb)
+mt7921_mcu_scan_event(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct mt76_phy *mphy = &dev->mt76.phy;
 	struct mt792x_phy *phy = (struct mt792x_phy *)mphy->priv;
@@ -188,7 +188,7 @@ mt7921_mcu_connection_loss_iter(void *priv, u8 *mac,
 }
 
 static void
-mt7921_mcu_connection_loss_event(struct mt7921_dev *dev, struct sk_buff *skb)
+mt7921_mcu_connection_loss_event(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct mt76_connac_beacon_loss_event *event;
 	struct mt76_phy *mphy = &dev->mt76.phy;
@@ -202,7 +202,7 @@ mt7921_mcu_connection_loss_event(struct mt7921_dev *dev, struct sk_buff *skb)
 }
 
 static void
-mt7921_mcu_debug_msg_event(struct mt7921_dev *dev, struct sk_buff *skb)
+mt7921_mcu_debug_msg_event(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct mt7921_debug_msg {
 		__le16 id;
@@ -229,7 +229,7 @@ mt7921_mcu_debug_msg_event(struct mt7921_dev *dev, struct sk_buff *skb)
 }
 
 static void
-mt7921_mcu_low_power_event(struct mt7921_dev *dev, struct sk_buff *skb)
+mt7921_mcu_low_power_event(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct mt7921_mcu_lp_event {
 		u8 state;
@@ -243,7 +243,7 @@ mt7921_mcu_low_power_event(struct mt7921_dev *dev, struct sk_buff *skb)
 }
 
 static void
-mt7921_mcu_tx_done_event(struct mt7921_dev *dev, struct sk_buff *skb)
+mt7921_mcu_tx_done_event(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct mt7921_mcu_tx_done_event *event;
 
@@ -254,7 +254,7 @@ mt7921_mcu_tx_done_event(struct mt7921_dev *dev, struct sk_buff *skb)
 }
 
 static void
-mt7921_mcu_rx_unsolicited_event(struct mt7921_dev *dev, struct sk_buff *skb)
+mt7921_mcu_rx_unsolicited_event(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct mt76_connac2_mcu_rxd *rxd;
 
@@ -288,7 +288,7 @@ mt7921_mcu_rx_unsolicited_event(struct mt7921_dev *dev, struct sk_buff *skb)
 }
 
 static void
-mt7921_mcu_uni_rx_unsolicited_event(struct mt7921_dev *dev,
+mt7921_mcu_uni_rx_unsolicited_event(struct mt792x_dev *dev,
 				    struct sk_buff *skb)
 {
 	struct mt76_connac2_mcu_rxd *rxd;
@@ -305,7 +305,7 @@ mt7921_mcu_uni_rx_unsolicited_event(struct mt7921_dev *dev,
 	dev_kfree_skb(skb);
 }
 
-void mt7921_mcu_rx_event(struct mt7921_dev *dev, struct sk_buff *skb)
+void mt7921_mcu_rx_event(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct mt76_connac2_mcu_rxd *rxd;
 
@@ -339,7 +339,7 @@ void mt7921_mcu_rx_event(struct mt7921_dev *dev, struct sk_buff *skb)
 }
 
 /** starec & wtbl **/
-int mt7921_mcu_uni_tx_ba(struct mt7921_dev *dev,
+int mt7921_mcu_uni_tx_ba(struct mt792x_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable)
 {
@@ -353,7 +353,7 @@ int mt7921_mcu_uni_tx_ba(struct mt7921_dev *dev,
 				      enable, true);
 }
 
-int mt7921_mcu_uni_rx_ba(struct mt7921_dev *dev,
+int mt7921_mcu_uni_rx_ba(struct mt792x_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable)
 {
@@ -364,7 +364,7 @@ int mt7921_mcu_uni_rx_ba(struct mt7921_dev *dev,
 				      enable, false);
 }
 
-static char *mt7921_patch_name(struct mt7921_dev *dev)
+static char *mt7921_patch_name(struct mt792x_dev *dev)
 {
 	char *ret;
 
@@ -376,7 +376,7 @@ static char *mt7921_patch_name(struct mt7921_dev *dev)
 	return ret;
 }
 
-static char *mt7921_ram_name(struct mt7921_dev *dev)
+static char *mt7921_ram_name(struct mt792x_dev *dev)
 {
 	char *ret;
 
@@ -388,7 +388,7 @@ static char *mt7921_ram_name(struct mt7921_dev *dev)
 	return ret;
 }
 
-static int mt7921_load_clc(struct mt7921_dev *dev, const char *fw_name)
+static int mt7921_load_clc(struct mt792x_dev *dev, const char *fw_name)
 {
 	const struct mt76_connac2_fw_trailer *hdr;
 	const struct mt76_connac2_fw_region *region;
@@ -472,7 +472,7 @@ out:
 	return ret;
 }
 
-static int mt7921_load_firmware(struct mt7921_dev *dev)
+static int mt7921_load_firmware(struct mt792x_dev *dev)
 {
 	int ret;
 
@@ -507,7 +507,7 @@ static int mt7921_load_firmware(struct mt7921_dev *dev)
 	return 0;
 }
 
-int mt7921_mcu_fw_log_2_host(struct mt7921_dev *dev, u8 ctrl)
+int mt7921_mcu_fw_log_2_host(struct mt792x_dev *dev, u8 ctrl)
 {
 	struct {
 		u8 ctrl_val;
@@ -520,7 +520,7 @@ int mt7921_mcu_fw_log_2_host(struct mt7921_dev *dev, u8 ctrl)
 				 &data, sizeof(data), false);
 }
 
-int mt7921_run_firmware(struct mt7921_dev *dev)
+int mt7921_run_firmware(struct mt792x_dev *dev)
 {
 	int err;
 
@@ -541,7 +541,7 @@ int mt7921_run_firmware(struct mt7921_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt7921_run_firmware);
 
-int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif)
+int mt7921_mcu_set_tx(struct mt792x_dev *dev, struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct edca {
@@ -640,7 +640,7 @@ int mt7921_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 		       enum mt7921_roc_req type, u8 token_id)
 {
 	int center_ch = ieee80211_frequency_to_channel(chan->center_freq);
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 	struct {
 		struct {
 			u8 rsv[4];
@@ -705,7 +705,7 @@ int mt7921_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 int mt7921_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 			 u8 token_id)
 {
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 	struct {
 		struct {
 			u8 rsv[4];
@@ -734,7 +734,7 @@ int mt7921_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 
 int mt7921_mcu_set_chan_info(struct mt792x_phy *phy, int cmd)
 {
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 	struct cfg80211_chan_def *chandef = &phy->mt76->chandef;
 	int freq1 = chandef->center_freq1;
 	struct {
@@ -791,7 +791,7 @@ int mt7921_mcu_set_chan_info(struct mt792x_phy *phy, int cmd)
 	return mt76_mcu_send_msg(&dev->mt76, cmd, &req, sizeof(req), true);
 }
 
-int mt7921_mcu_set_eeprom(struct mt7921_dev *dev)
+int mt7921_mcu_set_eeprom(struct mt792x_dev *dev)
 {
 	struct req_hdr {
 		u8 buffer_mode;
@@ -807,7 +807,7 @@ int mt7921_mcu_set_eeprom(struct mt7921_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt7921_mcu_set_eeprom);
 
-int mt7921_mcu_uni_bss_ps(struct mt7921_dev *dev, struct ieee80211_vif *vif)
+int mt7921_mcu_uni_bss_ps(struct mt792x_dev *dev, struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct {
@@ -845,7 +845,7 @@ int mt7921_mcu_uni_bss_ps(struct mt7921_dev *dev, struct ieee80211_vif *vif)
 }
 
 static int
-mt7921_mcu_uni_bss_bcnft(struct mt7921_dev *dev, struct ieee80211_vif *vif,
+mt7921_mcu_uni_bss_bcnft(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 			 bool enable)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
@@ -881,7 +881,7 @@ mt7921_mcu_uni_bss_bcnft(struct mt7921_dev *dev, struct ieee80211_vif *vif,
 }
 
 int
-mt7921_mcu_set_bss_pm(struct mt7921_dev *dev, struct ieee80211_vif *vif,
+mt7921_mcu_set_bss_pm(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 		      bool enable)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
@@ -918,7 +918,7 @@ mt7921_mcu_set_bss_pm(struct mt7921_dev *dev, struct ieee80211_vif *vif,
 				 &req, sizeof(req), false);
 }
 
-int mt7921_mcu_sta_update(struct mt7921_dev *dev, struct ieee80211_sta *sta,
+int mt7921_mcu_sta_update(struct mt792x_dev *dev, struct ieee80211_sta *sta,
 			  struct ieee80211_vif *vif, bool enable,
 			  enum mt76_sta_info_state state)
 {
@@ -942,7 +942,7 @@ int mt7921_mcu_sta_update(struct mt7921_dev *dev, struct ieee80211_sta *sta,
 	return mt76_connac_mcu_sta_cmd(&dev->mphy, &info);
 }
 
-int mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev)
+int mt7921_mcu_drv_pmctrl(struct mt792x_dev *dev)
 {
 	struct mt76_phy *mphy = &dev->mt76.phy;
 	struct mt76_connac_pm *pm = &dev->pm;
@@ -964,7 +964,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(mt7921_mcu_drv_pmctrl);
 
-int mt7921_mcu_fw_pmctrl(struct mt7921_dev *dev)
+int mt7921_mcu_fw_pmctrl(struct mt792x_dev *dev)
 {
 	struct mt76_phy *mphy = &dev->mt76.phy;
 	struct mt76_connac_pm *pm = &dev->pm;
@@ -986,7 +986,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(mt7921_mcu_fw_pmctrl);
 
-int mt7921_mcu_set_beacon_filter(struct mt7921_dev *dev,
+int mt7921_mcu_set_beacon_filter(struct mt792x_dev *dev,
 				 struct ieee80211_vif *vif,
 				 bool enable)
 {
@@ -1021,7 +1021,7 @@ int mt7921_mcu_set_beacon_filter(struct mt7921_dev *dev,
 	return 0;
 }
 
-int mt7921_get_txpwr_info(struct mt7921_dev *dev, struct mt7921_txpwr *txpwr)
+int mt7921_get_txpwr_info(struct mt792x_dev *dev, struct mt7921_txpwr *txpwr)
 {
 	struct mt7921_txpwr_event *event;
 	struct mt7921_txpwr_req req = {
@@ -1044,7 +1044,7 @@ int mt7921_get_txpwr_info(struct mt7921_dev *dev, struct mt7921_txpwr *txpwr)
 	return 0;
 }
 
-int mt7921_mcu_set_sniffer(struct mt7921_dev *dev, struct ieee80211_vif *vif,
+int mt7921_mcu_set_sniffer(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 			   bool enable)
 {
 	struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv;
@@ -1143,7 +1143,7 @@ int mt7921_mcu_config_sniffer(struct mt792x_vif *vif,
 }
 
 int
-mt7921_mcu_uni_add_beacon_offload(struct mt7921_dev *dev,
+mt7921_mcu_uni_add_beacon_offload(struct mt792x_dev *dev,
 				  struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
 				  bool enable)
@@ -1221,7 +1221,7 @@ mt7921_mcu_uni_add_beacon_offload(struct mt7921_dev *dev,
 }
 
 static
-int __mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
+int __mt7921_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 			 enum environment_cap env_cap,
 			 struct mt7921_clc *clc,
 			 u8 idx)
@@ -1283,7 +1283,7 @@ int __mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
 	return 0;
 }
 
-int mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
+int mt7921_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 		       enum environment_cap env_cap)
 {
 	struct mt792x_phy *phy = (struct mt792x_phy *)&dev->phy;
@@ -1307,7 +1307,7 @@ int mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
 
 int mt7921_mcu_get_temperature(struct mt792x_phy *phy)
 {
-	struct mt7921_dev *dev = phy->dev;
+	struct mt792x_dev *dev = phy->dev;
 	struct {
 		u8 ctrl_id;
 		u8 action;
@@ -1322,7 +1322,7 @@ int mt7921_mcu_get_temperature(struct mt792x_phy *phy)
 				 sizeof(req), true);
 }
 
-int mt7921_mcu_set_rxfilter(struct mt7921_dev *dev, u32 fif,
+int mt7921_mcu_set_rxfilter(struct mt792x_dev *dev, u32 fif,
 			    u8 bit_op, u32 bit_map)
 {
 	struct {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index d9550b0aba617..617aecd425444 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -201,7 +201,7 @@ struct mt7921_clc {
 
 struct mt792x_phy {
 	struct mt76_phy *mt76;
-	struct mt7921_dev *dev;
+	struct mt792x_dev *dev;
 
 	struct ieee80211_sband_iftype_data iftype[NUM_NL80211_BANDS][NUM_NL80211_IFTYPES];
 
@@ -250,14 +250,14 @@ enum mt7921_eeprom_field {
 #define __mt7921_mcu_drv_pmctrl(dev)	((dev)->hif_ops->drv_own(dev))
 #define	__mt7921_mcu_fw_pmctrl(dev)	((dev)->hif_ops->fw_own(dev))
 struct mt7921_hif_ops {
-	int (*init_reset)(struct mt7921_dev *dev);
-	int (*reset)(struct mt7921_dev *dev);
-	int (*mcu_init)(struct mt7921_dev *dev);
-	int (*drv_own)(struct mt7921_dev *dev);
-	int (*fw_own)(struct mt7921_dev *dev);
+	int (*init_reset)(struct mt792x_dev *dev);
+	int (*reset)(struct mt792x_dev *dev);
+	int (*mcu_init)(struct mt792x_dev *dev);
+	int (*drv_own)(struct mt792x_dev *dev);
+	int (*fw_own)(struct mt792x_dev *dev);
 };
 
-struct mt7921_dev {
+struct mt792x_dev {
 	union { /* must be first */
 		struct mt76_dev mt76;
 		struct mt76_phy mphy;
@@ -325,12 +325,12 @@ mt7921_hw_phy(struct ieee80211_hw *hw)
 	return phy->priv;
 }
 
-static inline struct mt7921_dev *
+static inline struct mt792x_dev *
 mt7921_hw_dev(struct ieee80211_hw *hw)
 {
 	struct mt76_phy *phy = hw->priv;
 
-	return container_of(phy->dev, struct mt7921_dev, mt76);
+	return container_of(phy->dev, struct mt792x_dev, mt76);
 }
 
 #define mt7921_mutex_acquire(dev)	\
@@ -340,33 +340,33 @@ mt7921_hw_dev(struct ieee80211_hw *hw)
 
 extern const struct ieee80211_ops mt7921_ops;
 
-u32 mt7921_reg_map(struct mt7921_dev *dev, u32 addr);
+u32 mt7921_reg_map(struct mt792x_dev *dev, u32 addr);
 
 int __mt7921_start(struct mt792x_phy *phy);
-int mt7921_register_device(struct mt7921_dev *dev);
-void mt7921_unregister_device(struct mt7921_dev *dev);
-int mt7921_dma_init(struct mt7921_dev *dev);
-int mt7921_wpdma_reset(struct mt7921_dev *dev, bool force);
-int mt7921_wpdma_reinit_cond(struct mt7921_dev *dev);
-void mt7921_dma_cleanup(struct mt7921_dev *dev);
-int mt7921_run_firmware(struct mt7921_dev *dev);
-int mt7921_mcu_set_bss_pm(struct mt7921_dev *dev, struct ieee80211_vif *vif,
+int mt7921_register_device(struct mt792x_dev *dev);
+void mt7921_unregister_device(struct mt792x_dev *dev);
+int mt7921_dma_init(struct mt792x_dev *dev);
+int mt7921_wpdma_reset(struct mt792x_dev *dev, bool force);
+int mt7921_wpdma_reinit_cond(struct mt792x_dev *dev);
+void mt7921_dma_cleanup(struct mt792x_dev *dev);
+int mt7921_run_firmware(struct mt792x_dev *dev);
+int mt7921_mcu_set_bss_pm(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 			  bool enable);
-int mt7921_mcu_sta_update(struct mt7921_dev *dev, struct ieee80211_sta *sta,
+int mt7921_mcu_sta_update(struct mt792x_dev *dev, struct ieee80211_sta *sta,
 			  struct ieee80211_vif *vif, bool enable,
 			  enum mt76_sta_info_state state);
 int mt7921_mcu_set_chan_info(struct mt792x_phy *phy, int cmd);
-int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif);
-int mt7921_mcu_set_eeprom(struct mt7921_dev *dev);
+int mt7921_mcu_set_tx(struct mt792x_dev *dev, struct ieee80211_vif *vif);
+int mt7921_mcu_set_eeprom(struct mt792x_dev *dev);
 int mt7921_mcu_get_rx_rate(struct mt792x_phy *phy, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta, struct rate_info *rate);
-int mt7921_mcu_fw_log_2_host(struct mt7921_dev *dev, u8 ctrl);
-void mt7921_mcu_rx_event(struct mt7921_dev *dev, struct sk_buff *skb);
-int mt7921_mcu_set_rxfilter(struct mt7921_dev *dev, u32 fif,
+int mt7921_mcu_fw_log_2_host(struct mt792x_dev *dev, u8 ctrl);
+void mt7921_mcu_rx_event(struct mt792x_dev *dev, struct sk_buff *skb);
+int mt7921_mcu_set_rxfilter(struct mt792x_dev *dev, u32 fif,
 			    u8 bit_op, u32 bit_map);
 
 static inline u32
-mt7921_reg_map_l1(struct mt7921_dev *dev, u32 addr)
+mt7921_reg_map_l1(struct mt792x_dev *dev, u32 addr)
 {
 	u32 offset = FIELD_GET(MT_HIF_REMAP_L1_OFFSET, addr);
 	u32 base = FIELD_GET(MT_HIF_REMAP_L1_BASE, addr);
@@ -379,19 +379,19 @@ mt7921_reg_map_l1(struct mt7921_dev *dev, u32 addr)
 }
 
 static inline u32
-mt7921_l1_rr(struct mt7921_dev *dev, u32 addr)
+mt7921_l1_rr(struct mt792x_dev *dev, u32 addr)
 {
 	return mt76_rr(dev, mt7921_reg_map_l1(dev, addr));
 }
 
 static inline void
-mt7921_l1_wr(struct mt7921_dev *dev, u32 addr, u32 val)
+mt7921_l1_wr(struct mt792x_dev *dev, u32 addr, u32 val)
 {
 	mt76_wr(dev, mt7921_reg_map_l1(dev, addr), val);
 }
 
 static inline u32
-mt7921_l1_rmw(struct mt7921_dev *dev, u32 addr, u32 mask, u32 val)
+mt7921_l1_rmw(struct mt792x_dev *dev, u32 addr, u32 mask, u32 val)
 {
 	val |= mt7921_l1_rr(dev, addr) & ~mask;
 	mt7921_l1_wr(dev, addr, val);
@@ -402,13 +402,13 @@ mt7921_l1_rmw(struct mt7921_dev *dev, u32 addr, u32 mask, u32 val)
 #define mt7921_l1_set(dev, addr, val)	mt7921_l1_rmw(dev, addr, 0, val)
 #define mt7921_l1_clear(dev, addr, val)	mt7921_l1_rmw(dev, addr, val, 0)
 
-static inline bool mt7921_dma_need_reinit(struct mt7921_dev *dev)
+static inline bool mt7921_dma_need_reinit(struct mt792x_dev *dev)
 {
 	return !mt76_get_field(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT);
 }
 
 static inline void
-mt7921_skb_add_usb_sdio_hdr(struct mt7921_dev *dev, struct sk_buff *skb,
+mt7921_skb_add_usb_sdio_hdr(struct mt792x_dev *dev, struct sk_buff *skb,
 			    int type)
 {
 	u32 hdr, len;
@@ -421,8 +421,8 @@ mt7921_skb_add_usb_sdio_hdr(struct mt7921_dev *dev, struct sk_buff *skb,
 }
 
 void mt7921_stop(struct ieee80211_hw *hw);
-int mt7921_mac_init(struct mt7921_dev *dev);
-bool mt7921_mac_wtbl_update(struct mt7921_dev *dev, int idx, u32 mask);
+int mt7921_mac_init(struct mt792x_dev *dev);
+bool mt7921_mac_wtbl_update(struct mt792x_dev *dev, int idx, u32 mask);
 void mt7921_mac_reset_counters(struct mt792x_phy *phy);
 void mt7921_mac_set_timing(struct mt792x_phy *phy);
 int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
@@ -447,28 +447,28 @@ void mt7921_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 void mt7921_stats_work(struct work_struct *work);
 void mt7921_set_stream_he_caps(struct mt792x_phy *phy);
 void mt7921_update_channel(struct mt76_phy *mphy);
-int mt7921_init_debugfs(struct mt7921_dev *dev);
+int mt7921_init_debugfs(struct mt792x_dev *dev);
 
-int mt7921_mcu_set_beacon_filter(struct mt7921_dev *dev,
+int mt7921_mcu_set_beacon_filter(struct mt792x_dev *dev,
 				 struct ieee80211_vif *vif,
 				 bool enable);
-int mt7921_mcu_uni_tx_ba(struct mt7921_dev *dev,
+int mt7921_mcu_uni_tx_ba(struct mt792x_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable);
-int mt7921_mcu_uni_rx_ba(struct mt7921_dev *dev,
+int mt7921_mcu_uni_rx_ba(struct mt792x_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable);
 void mt7921_scan_work(struct work_struct *work);
 void mt7921_roc_work(struct work_struct *work);
 void mt7921_roc_timer(struct timer_list *timer);
-int mt7921_mcu_uni_bss_ps(struct mt7921_dev *dev, struct ieee80211_vif *vif);
-int mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev);
-int mt7921_mcu_fw_pmctrl(struct mt7921_dev *dev);
+int mt7921_mcu_uni_bss_ps(struct mt792x_dev *dev, struct ieee80211_vif *vif);
+int mt7921_mcu_drv_pmctrl(struct mt792x_dev *dev);
+int mt7921_mcu_fw_pmctrl(struct mt792x_dev *dev);
 void mt7921_pm_wake_work(struct work_struct *work);
 void mt7921_pm_power_save_work(struct work_struct *work);
 void mt7921_coredump_work(struct work_struct *work);
-int mt7921_wfsys_reset(struct mt7921_dev *dev);
-int mt7921_get_txpwr_info(struct mt7921_dev *dev, struct mt7921_txpwr *txpwr);
+int mt7921_wfsys_reset(struct mt792x_dev *dev);
+int mt7921_get_txpwr_info(struct mt792x_dev *dev, struct mt7921_txpwr *txpwr);
 int mt7921_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			void *data, int len);
 int mt7921_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *msg,
@@ -476,26 +476,26 @@ int mt7921_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *msg,
 int mt7921_mcu_parse_response(struct mt76_dev *mdev, int cmd,
 			      struct sk_buff *skb, int seq);
 
-int mt7921e_driver_own(struct mt7921_dev *dev);
-int mt7921e_mac_reset(struct mt7921_dev *dev);
-int mt7921e_mcu_init(struct mt7921_dev *dev);
-int mt7921s_wfsys_reset(struct mt7921_dev *dev);
-int mt7921s_mac_reset(struct mt7921_dev *dev);
-int mt7921s_init_reset(struct mt7921_dev *dev);
-int __mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev);
-int mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev);
-int mt7921e_mcu_fw_pmctrl(struct mt7921_dev *dev);
-
-int mt7921s_mcu_init(struct mt7921_dev *dev);
-int mt7921s_mcu_drv_pmctrl(struct mt7921_dev *dev);
-int mt7921s_mcu_fw_pmctrl(struct mt7921_dev *dev);
-void mt7921_mac_add_txs(struct mt7921_dev *dev, void *data);
-void mt7921_set_runtime_pm(struct mt7921_dev *dev);
+int mt7921e_driver_own(struct mt792x_dev *dev);
+int mt7921e_mac_reset(struct mt792x_dev *dev);
+int mt7921e_mcu_init(struct mt792x_dev *dev);
+int mt7921s_wfsys_reset(struct mt792x_dev *dev);
+int mt7921s_mac_reset(struct mt792x_dev *dev);
+int mt7921s_init_reset(struct mt792x_dev *dev);
+int __mt7921e_mcu_drv_pmctrl(struct mt792x_dev *dev);
+int mt7921e_mcu_drv_pmctrl(struct mt792x_dev *dev);
+int mt7921e_mcu_fw_pmctrl(struct mt792x_dev *dev);
+
+int mt7921s_mcu_init(struct mt792x_dev *dev);
+int mt7921s_mcu_drv_pmctrl(struct mt792x_dev *dev);
+int mt7921s_mcu_fw_pmctrl(struct mt792x_dev *dev);
+void mt7921_mac_add_txs(struct mt792x_dev *dev, void *data);
+void mt7921_set_runtime_pm(struct mt792x_dev *dev);
 void mt7921_mcu_set_suspend_iter(void *priv, u8 *mac,
 				 struct ieee80211_vif *vif);
 void mt7921_set_ipv6_ns_work(struct work_struct *work);
 
-int mt7921_mcu_set_sniffer(struct mt7921_dev *dev, struct ieee80211_vif *vif,
+int mt7921_mcu_set_sniffer(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 			   bool enable);
 int mt7921_mcu_config_sniffer(struct mt792x_vif *vif,
 			      struct ieee80211_chanctx_conf *ctx);
@@ -513,22 +513,22 @@ bool mt7921_usb_sdio_tx_status_data(struct mt76_dev *mdev, u8 *update);
 #define MT_USB_TYPE_VENDOR	(USB_TYPE_VENDOR | 0x1f)
 #define MT_USB_TYPE_UHW_VENDOR	(USB_TYPE_VENDOR | 0x1e)
 
-int mt7921u_mcu_power_on(struct mt7921_dev *dev);
-int mt7921u_wfsys_reset(struct mt7921_dev *dev);
-int mt7921u_dma_init(struct mt7921_dev *dev, bool resume);
-int mt7921u_init_reset(struct mt7921_dev *dev);
-int mt7921u_mac_reset(struct mt7921_dev *dev);
-int mt7921_mcu_uni_add_beacon_offload(struct mt7921_dev *dev,
+int mt7921u_mcu_power_on(struct mt792x_dev *dev);
+int mt7921u_wfsys_reset(struct mt792x_dev *dev);
+int mt7921u_dma_init(struct mt792x_dev *dev, bool resume);
+int mt7921u_init_reset(struct mt792x_dev *dev);
+int mt7921u_mac_reset(struct mt792x_dev *dev);
+int mt7921_mcu_uni_add_beacon_offload(struct mt792x_dev *dev,
 				      struct ieee80211_hw *hw,
 				      struct ieee80211_vif *vif,
 				      bool enable);
 #ifdef CONFIG_ACPI
-int mt7921_init_acpi_sar(struct mt7921_dev *dev);
+int mt7921_init_acpi_sar(struct mt792x_dev *dev);
 int mt7921_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default);
 u8 mt7921_acpi_get_flags(struct mt792x_phy *phy);
 #else
 static inline int
-mt7921_init_acpi_sar(struct mt7921_dev *dev)
+mt7921_init_acpi_sar(struct mt792x_dev *dev)
 {
 	return 0;
 }
@@ -548,7 +548,7 @@ mt7921_acpi_get_flags(struct mt792x_phy *phy)
 int mt7921_set_tx_sar_pwr(struct ieee80211_hw *hw,
 			  const struct cfg80211_sar_specs *sar);
 
-int mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2,
+int mt7921_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 		       enum environment_cap env_cap);
 int mt7921_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 		       struct ieee80211_channel *chan, int duration,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921_trace.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921_trace.h
index 9bc4db67f352d..9426fda69c309 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921_trace.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921_trace.h
@@ -21,7 +21,7 @@
 #define LP_STATE_PR_ARG	__entry->lp_state ? "lp ready" : "lp not ready"
 
 TRACE_EVENT(lp_event,
-	TP_PROTO(struct mt7921_dev *dev, u8 lp_state),
+	TP_PROTO(struct mt792x_dev *dev, u8 lp_state),
 
 	TP_ARGS(dev, lp_state),
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 1b7f19939a696..517e4d541bdc3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -41,7 +41,7 @@ mt7921_rx_poll_complete(struct mt76_dev *mdev, enum mt76_rxq_id q)
 
 static irqreturn_t mt7921_irq_handler(int irq, void *dev_instance)
 {
-	struct mt7921_dev *dev = dev_instance;
+	struct mt792x_dev *dev = dev_instance;
 
 	mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0);
 
@@ -55,7 +55,7 @@ static irqreturn_t mt7921_irq_handler(int irq, void *dev_instance)
 
 static void mt7921_irq_tasklet(unsigned long data)
 {
-	struct mt7921_dev *dev = (struct mt7921_dev *)data;
+	struct mt792x_dev *dev = (struct mt792x_dev *)data;
 	u32 intr, mask = 0;
 
 	mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0);
@@ -97,12 +97,12 @@ static void mt7921_irq_tasklet(unsigned long data)
 		napi_schedule(&dev->mt76.napi[MT_RXQ_MAIN]);
 }
 
-static int mt7921e_init_reset(struct mt7921_dev *dev)
+static int mt7921e_init_reset(struct mt792x_dev *dev)
 {
 	return mt7921_wpdma_reset(dev, true);
 }
 
-static void mt7921e_unregister_device(struct mt7921_dev *dev)
+static void mt7921e_unregister_device(struct mt792x_dev *dev)
 {
 	int i;
 	struct mt76_connac_pm *pm = &dev->pm;
@@ -124,7 +124,7 @@ static void mt7921e_unregister_device(struct mt7921_dev *dev)
 	tasklet_disable(&dev->mt76.irq_tasklet);
 }
 
-static u32 __mt7921_reg_addr(struct mt7921_dev *dev, u32 addr)
+static u32 __mt7921_reg_addr(struct mt792x_dev *dev, u32 addr)
 {
 	static const struct mt76_connac_reg_map fixed_map[] = {
 		{ 0x820d0000, 0x30000, 0x10000 }, /* WF_LMAC_TOP (WF_WTBLON) */
@@ -203,7 +203,7 @@ static u32 __mt7921_reg_addr(struct mt7921_dev *dev, u32 addr)
 
 static u32 mt7921_rr(struct mt76_dev *mdev, u32 offset)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	u32 addr = __mt7921_reg_addr(dev, offset);
 
 	return dev->bus_ops->rr(mdev, addr);
@@ -211,7 +211,7 @@ static u32 mt7921_rr(struct mt76_dev *mdev, u32 offset)
 
 static void mt7921_wr(struct mt76_dev *mdev, u32 offset, u32 val)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	u32 addr = __mt7921_reg_addr(dev, offset);
 
 	dev->bus_ops->wr(mdev, addr, val);
@@ -219,7 +219,7 @@ static void mt7921_wr(struct mt76_dev *mdev, u32 offset, u32 val)
 
 static u32 mt7921_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	u32 addr = __mt7921_reg_addr(dev, offset);
 
 	return dev->bus_ops->rmw(mdev, addr, mask, val);
@@ -256,7 +256,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 	};
 	struct ieee80211_ops *ops;
 	struct mt76_bus_ops *bus_ops;
-	struct mt7921_dev *dev;
+	struct mt792x_dev *dev;
 	struct mt76_dev *mdev;
 	u8 features;
 	int ret;
@@ -303,7 +303,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 
 	pci_set_drvdata(pdev, mdev);
 
-	dev = container_of(mdev, struct mt7921_dev, mt76);
+	dev = container_of(mdev, struct mt792x_dev, mt76);
 	dev->fw_features = features;
 	dev->hif_ops = &mt7921_pcie_ops;
 	mt76_mmio_init(&dev->mt76, pcim_iomap_table(pdev)[0]);
@@ -373,7 +373,7 @@ err_free_pci_vec:
 static void mt7921_pci_remove(struct pci_dev *pdev)
 {
 	struct mt76_dev *mdev = pci_get_drvdata(pdev);
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 
 	mt7921e_unregister_device(dev);
 	devm_free_irq(&pdev->dev, pdev->irq, dev);
@@ -385,7 +385,7 @@ static int mt7921_pci_suspend(struct device *device)
 {
 	struct pci_dev *pdev = to_pci_dev(device);
 	struct mt76_dev *mdev = pci_get_drvdata(pdev);
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct mt76_connac_pm *pm = &dev->pm;
 	int i, err;
 
@@ -459,7 +459,7 @@ static int mt7921_pci_resume(struct device *device)
 {
 	struct pci_dev *pdev = to_pci_dev(device);
 	struct mt76_dev *mdev = pci_get_drvdata(pdev);
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct mt76_connac_pm *pm = &dev->pm;
 	int i, err;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
index 32bba86727a53..7323388327f40 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
@@ -10,7 +10,7 @@ int mt7921e_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			   struct ieee80211_sta *sta,
 			   struct mt76_tx_info *tx_info)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_info->skb);
 	struct ieee80211_key_conf *key = info->control.hw_key;
 	struct mt76_connac_hw_txp *txp;
@@ -53,7 +53,7 @@ int mt7921e_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	return 0;
 }
 
-int mt7921e_mac_reset(struct mt7921_dev *dev)
+int mt7921e_mac_reset(struct mt792x_dev *dev)
 {
 	int i, err;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c
index 1aefbb6cf0ab1..5a30cd0b9382b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c
@@ -4,7 +4,7 @@
 #include "mt7921.h"
 #include "mcu.h"
 
-int mt7921e_driver_own(struct mt7921_dev *dev)
+int mt7921e_driver_own(struct mt792x_dev *dev)
 {
 	u32 reg = mt7921_reg_map_l1(dev, MT_TOP_LPCR_HOST_BAND0);
 
@@ -22,7 +22,7 @@ static int
 mt7921_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 			int cmd, int *seq)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	enum mt76_mcuq_id txq = MT_MCUQ_WM;
 	int ret;
 
@@ -38,7 +38,7 @@ mt7921_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 	return mt76_tx_queue_skb_raw(dev, mdev->q_mcu[txq], skb, 0);
 }
 
-int mt7921e_mcu_init(struct mt7921_dev *dev)
+int mt7921e_mcu_init(struct mt792x_dev *dev)
 {
 	static const struct mt76_mcu_ops mt7921_mcu_ops = {
 		.headroom = sizeof(struct mt76_connac2_mcu_txd),
@@ -62,7 +62,7 @@ int mt7921e_mcu_init(struct mt7921_dev *dev)
 	return err;
 }
 
-int __mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev)
+int __mt7921e_mcu_drv_pmctrl(struct mt792x_dev *dev)
 {
 	int i, err = 0;
 
@@ -81,7 +81,7 @@ int __mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev)
 	return err;
 }
 
-int mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev)
+int mt7921e_mcu_drv_pmctrl(struct mt792x_dev *dev)
 {
 	struct mt76_phy *mphy = &dev->mt76.phy;
 	struct mt76_connac_pm *pm = &dev->pm;
@@ -101,7 +101,7 @@ out:
 	return err;
 }
 
-int mt7921e_mcu_fw_pmctrl(struct mt7921_dev *dev)
+int mt7921e_mcu_fw_pmctrl(struct mt792x_dev *dev)
 {
 	struct mt76_phy *mphy = &dev->mt76.phy;
 	struct mt76_connac_pm *pm = &dev->pm;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index a77a309c0d606..86da0cbbdf3b2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -27,7 +27,7 @@ static void mt7921s_txrx_worker(struct mt76_worker *w)
 	struct mt76_sdio *sdio = container_of(w, struct mt76_sdio,
 					      txrx_worker);
 	struct mt76_dev *mdev = container_of(sdio, struct mt76_dev, sdio);
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 
 	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
 		queue_work(mdev->wq, &dev->pm.wake_work);
@@ -38,7 +38,7 @@ static void mt7921s_txrx_worker(struct mt76_worker *w)
 	mt76_connac_pm_unref(&dev->mphy, &dev->pm);
 }
 
-static void mt7921s_unregister_device(struct mt7921_dev *dev)
+static void mt7921s_unregister_device(struct mt792x_dev *dev)
 {
 	struct mt76_connac_pm *pm = &dev->pm;
 
@@ -122,7 +122,7 @@ static int mt7921s_probe(struct sdio_func *func,
 		.fw_own = mt7921s_mcu_fw_pmctrl,
 	};
 	struct ieee80211_ops *ops;
-	struct mt7921_dev *dev;
+	struct mt792x_dev *dev;
 	struct mt76_dev *mdev;
 	u8 features;
 	int ret;
@@ -136,7 +136,7 @@ static int mt7921s_probe(struct sdio_func *func,
 	if (!mdev)
 		return -ENOMEM;
 
-	dev = container_of(mdev, struct mt7921_dev, mt76);
+	dev = container_of(mdev, struct mt792x_dev, mt76);
 	dev->fw_features = features;
 	dev->hif_ops = &mt7921_sdio_ops;
 	sdio_set_drvdata(func, dev);
@@ -196,7 +196,7 @@ error:
 
 static void mt7921s_remove(struct sdio_func *func)
 {
-	struct mt7921_dev *dev = sdio_get_drvdata(func);
+	struct mt792x_dev *dev = sdio_get_drvdata(func);
 
 	mt7921s_unregister_device(dev);
 }
@@ -204,7 +204,7 @@ static void mt7921s_remove(struct sdio_func *func)
 static int mt7921s_suspend(struct device *__dev)
 {
 	struct sdio_func *func = dev_to_sdio_func(__dev);
-	struct mt7921_dev *dev = sdio_get_drvdata(func);
+	struct mt792x_dev *dev = sdio_get_drvdata(func);
 	struct mt76_connac_pm *pm = &dev->pm;
 	struct mt76_dev *mdev = &dev->mt76;
 	int err;
@@ -277,7 +277,7 @@ restore_suspend:
 static int mt7921s_resume(struct device *__dev)
 {
 	struct sdio_func *func = dev_to_sdio_func(__dev);
-	struct mt7921_dev *dev = sdio_get_drvdata(func);
+	struct mt792x_dev *dev = sdio_get_drvdata(func);
 	struct mt76_connac_pm *pm = &dev->pm;
 	struct mt76_dev *mdev = &dev->mt76;
 	int err;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c
index cff9925c41eab..8edd0291c1280 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c
@@ -30,7 +30,7 @@ static u32 mt7921s_read_whcr(struct mt76_dev *dev)
 	return sdio_readl(dev->sdio.func, MCR_WHCR, NULL);
 }
 
-int mt7921s_wfsys_reset(struct mt7921_dev *dev)
+int mt7921s_wfsys_reset(struct mt792x_dev *dev)
 {
 	struct mt76_sdio *sdio = &dev->mt76.sdio;
 	u32 val, status;
@@ -71,7 +71,7 @@ int mt7921s_wfsys_reset(struct mt7921_dev *dev)
 	return 0;
 }
 
-int mt7921s_init_reset(struct mt7921_dev *dev)
+int mt7921s_init_reset(struct mt792x_dev *dev)
 {
 	set_bit(MT76_MCU_RESET, &dev->mphy.state);
 
@@ -91,7 +91,7 @@ int mt7921s_init_reset(struct mt7921_dev *dev)
 	return 0;
 }
 
-int mt7921s_mac_reset(struct mt7921_dev *dev)
+int mt7921s_mac_reset(struct mt792x_dev *dev)
 {
 	int err;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c
index 177679ce1c804..360de6a0de2be 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c
@@ -16,7 +16,7 @@ static int
 mt7921s_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 			 int cmd, int *seq)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	enum mt7921_sdio_pkt_type type = MT7921_SDIO_CMD;
 	enum mt76_mcuq_id txq = MT_MCUQ_WM;
 	int ret, pad;
@@ -51,14 +51,14 @@ mt7921s_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 	return ret;
 }
 
-static u32 mt7921s_read_rm3r(struct mt7921_dev *dev)
+static u32 mt7921s_read_rm3r(struct mt792x_dev *dev)
 {
 	struct mt76_sdio *sdio = &dev->mt76.sdio;
 
 	return sdio_readl(sdio->func, MCR_D2HRM3R, NULL);
 }
 
-static u32 mt7921s_clear_rm3r_drv_own(struct mt7921_dev *dev)
+static u32 mt7921s_clear_rm3r_drv_own(struct mt792x_dev *dev)
 {
 	struct mt76_sdio *sdio = &dev->mt76.sdio;
 	u32 val;
@@ -71,7 +71,7 @@ static u32 mt7921s_clear_rm3r_drv_own(struct mt7921_dev *dev)
 	return val;
 }
 
-int mt7921s_mcu_init(struct mt7921_dev *dev)
+int mt7921s_mcu_init(struct mt792x_dev *dev)
 {
 	static const struct mt76_mcu_ops mt7921s_mcu_ops = {
 		.headroom = MT_SDIO_HDR_SIZE +
@@ -97,7 +97,7 @@ int mt7921s_mcu_init(struct mt7921_dev *dev)
 	return 0;
 }
 
-int mt7921s_mcu_drv_pmctrl(struct mt7921_dev *dev)
+int mt7921s_mcu_drv_pmctrl(struct mt792x_dev *dev)
 {
 	struct sdio_func *func = dev->mt76.sdio.func;
 	struct mt76_phy *mphy = &dev->mt76.phy;
@@ -133,7 +133,7 @@ int mt7921s_mcu_drv_pmctrl(struct mt7921_dev *dev)
 	return 0;
 }
 
-int mt7921s_mcu_fw_pmctrl(struct mt7921_dev *dev)
+int mt7921s_mcu_fw_pmctrl(struct mt792x_dev *dev)
 {
 	struct sdio_func *func = dev->mt76.sdio.func;
 	struct mt76_phy *mphy = &dev->mt76.phy;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c
index 208dcb2afbe79..3c2165095ddd1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c
@@ -31,7 +31,7 @@ static const struct nla_policy mt7921_tm_policy[NUM_MT7921_TM_ATTRS] = {
 };
 
 static int
-mt7921_tm_set(struct mt7921_dev *dev, struct mt7921_tm_cmd *req)
+mt7921_tm_set(struct mt792x_dev *dev, struct mt7921_tm_cmd *req)
 {
 	struct mt7921_rftest_cmd cmd = {
 		.action = req->action,
@@ -82,7 +82,7 @@ out:
 }
 
 static int
-mt7921_tm_query(struct mt7921_dev *dev, struct mt7921_tm_cmd *req,
+mt7921_tm_query(struct mt792x_dev *dev, struct mt7921_tm_cmd *req,
 		struct mt7921_tm_evt *evt_resp)
 {
 	struct mt7921_rftest_cmd cmd = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index 1f302c4303391..898cb1de9400e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -82,7 +82,7 @@ static void mt7921u_copy(struct mt76_dev *dev, u32 offset,
 	mutex_unlock(&usb->usb_ctrl_mtx);
 }
 
-int mt7921u_mcu_power_on(struct mt7921_dev *dev)
+int mt7921u_mcu_power_on(struct mt792x_dev *dev)
 {
 	int ret;
 
@@ -105,7 +105,7 @@ static int
 mt7921u_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 			 int cmd, int *seq)
 {
-	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	u32 pad, ep;
 	int ret;
 
@@ -131,7 +131,7 @@ mt7921u_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 	return ret;
 }
 
-static int mt7921u_mcu_init(struct mt7921_dev *dev)
+static int mt7921u_mcu_init(struct mt792x_dev *dev)
 {
 	static const struct mt76_mcu_ops mcu_ops = {
 		.headroom = MT_SDIO_HDR_SIZE +
@@ -157,13 +157,13 @@ static int mt7921u_mcu_init(struct mt7921_dev *dev)
 
 static void mt7921u_stop(struct ieee80211_hw *hw)
 {
-	struct mt7921_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	mt76u_stop_tx(&dev->mt76);
 	mt7921_stop(hw);
 }
 
-static void mt7921u_cleanup(struct mt7921_dev *dev)
+static void mt7921u_cleanup(struct mt792x_dev *dev)
 {
 	clear_bit(MT76_STATE_INITIALIZED, &dev->mphy.state);
 	mt7921u_wfsys_reset(dev);
@@ -207,7 +207,7 @@ static int mt7921u_probe(struct usb_interface *usb_intf,
 	struct usb_device *udev = interface_to_usbdev(usb_intf);
 	struct ieee80211_ops *ops;
 	struct ieee80211_hw *hw;
-	struct mt7921_dev *dev;
+	struct mt792x_dev *dev;
 	struct mt76_dev *mdev;
 	u8 features;
 	int ret;
@@ -222,7 +222,7 @@ static int mt7921u_probe(struct usb_interface *usb_intf,
 	if (!mdev)
 		return -ENOMEM;
 
-	dev = container_of(mdev, struct mt7921_dev, mt76);
+	dev = container_of(mdev, struct mt792x_dev, mt76);
 	dev->fw_features = features;
 	dev->hif_ops = &hif_ops;
 
@@ -284,7 +284,7 @@ error:
 
 static void mt7921u_disconnect(struct usb_interface *usb_intf)
 {
-	struct mt7921_dev *dev = usb_get_intfdata(usb_intf);
+	struct mt792x_dev *dev = usb_get_intfdata(usb_intf);
 
 	cancel_work_sync(&dev->init_work);
 	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state))
@@ -302,7 +302,7 @@ static void mt7921u_disconnect(struct usb_interface *usb_intf)
 #ifdef CONFIG_PM
 static int mt7921u_suspend(struct usb_interface *intf, pm_message_t state)
 {
-	struct mt7921_dev *dev = usb_get_intfdata(intf);
+	struct mt792x_dev *dev = usb_get_intfdata(intf);
 	struct mt76_connac_pm *pm = &dev->pm;
 	int err;
 
@@ -329,7 +329,7 @@ failed:
 
 static int mt7921u_resume(struct usb_interface *intf)
 {
-	struct mt7921_dev *dev = usb_get_intfdata(intf);
+	struct mt792x_dev *dev = usb_get_intfdata(intf);
 	struct mt76_connac_pm *pm = &dev->pm;
 	bool reinit = true;
 	int err, i;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c
index 50eb6e7fd6b53..f612873c704bf 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c
@@ -32,7 +32,7 @@ static void mt7921u_uhw_wr(struct mt76_dev *dev, u32 addr, u32 val)
 	mutex_unlock(&dev->usb.usb_ctrl_mtx);
 }
 
-static void mt7921u_dma_prefetch(struct mt7921_dev *dev)
+static void mt7921u_dma_prefetch(struct mt792x_dev *dev)
 {
 	mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(0),
 		 MT_WPDMA0_MAX_CNT_MASK, 4);
@@ -70,7 +70,7 @@ static void mt7921u_dma_prefetch(struct mt7921_dev *dev)
 		 MT_WPDMA0_BASE_PTR_MASK,  0x2c0);
 }
 
-static void mt7921u_wfdma_init(struct mt7921_dev *dev)
+static void mt7921u_wfdma_init(struct mt792x_dev *dev)
 {
 	mt7921u_dma_prefetch(dev);
 
@@ -90,7 +90,7 @@ static void mt7921u_wfdma_init(struct mt7921_dev *dev)
 	mt76_set(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT);
 }
 
-static int mt7921u_dma_rx_evt_ep4(struct mt7921_dev *dev)
+static int mt7921u_dma_rx_evt_ep4(struct mt792x_dev *dev)
 {
 	if (!mt76_poll(dev, MT_UWFDMA0_GLO_CFG,
 		       MT_WFDMA0_GLO_CFG_RX_DMA_BUSY, 0, 1000))
@@ -104,7 +104,7 @@ static int mt7921u_dma_rx_evt_ep4(struct mt7921_dev *dev)
 	return 0;
 }
 
-static void mt7921u_epctl_rst_opt(struct mt7921_dev *dev, bool reset)
+static void mt7921u_epctl_rst_opt(struct mt792x_dev *dev, bool reset)
 {
 	u32 val;
 
@@ -121,7 +121,7 @@ static void mt7921u_epctl_rst_opt(struct mt7921_dev *dev, bool reset)
 	mt7921u_uhw_wr(&dev->mt76, MT_SSUSB_EPCTL_CSR_EP_RST_OPT, val);
 }
 
-int mt7921u_dma_init(struct mt7921_dev *dev, bool resume)
+int mt7921u_dma_init(struct mt792x_dev *dev, bool resume)
 {
 	int err;
 
@@ -148,7 +148,7 @@ int mt7921u_dma_init(struct mt7921_dev *dev, bool resume)
 	return 0;
 }
 
-int mt7921u_wfsys_reset(struct mt7921_dev *dev)
+int mt7921u_wfsys_reset(struct mt792x_dev *dev)
 {
 	u32 val;
 	int i;
@@ -180,7 +180,7 @@ int mt7921u_wfsys_reset(struct mt7921_dev *dev)
 	return 0;
 }
 
-int mt7921u_init_reset(struct mt7921_dev *dev)
+int mt7921u_init_reset(struct mt792x_dev *dev)
 {
 	set_bit(MT76_RESET, &dev->mphy.state);
 
@@ -197,7 +197,7 @@ int mt7921u_init_reset(struct mt7921_dev *dev)
 	return mt76u_resume_rx(&dev->mt76);
 }
 
-int mt7921u_mac_reset(struct mt7921_dev *dev)
+int mt7921u_mac_reset(struct mt792x_dev *dev)
 {
 	int err;
 
-- 
GitLab


From 838cc6679733584d6f1c1e8423a1ad5aa5cb9ad0 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:53 +0800
Subject: [PATCH 0463/1806] wifi: mt76: mt7921: rename mt7921_hif_ops in
 mt792x_hif_ops

This is a preliminary patch to introduce WiFi7 chipset support

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h | 4 ++--
 drivers/net/wireless/mediatek/mt76/mt7921/pci.c    | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/sdio.c   | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/usb.c    | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 617aecd425444..e84c6a56d40e6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -249,7 +249,7 @@ enum mt7921_eeprom_field {
 #define mt7921_mcu_init(dev)		((dev)->hif_ops->mcu_init(dev))
 #define __mt7921_mcu_drv_pmctrl(dev)	((dev)->hif_ops->drv_own(dev))
 #define	__mt7921_mcu_fw_pmctrl(dev)	((dev)->hif_ops->fw_own(dev))
-struct mt7921_hif_ops {
+struct mt792x_hif_ops {
 	int (*init_reset)(struct mt792x_dev *dev);
 	int (*reset)(struct mt792x_dev *dev);
 	int (*mcu_init)(struct mt792x_dev *dev);
@@ -278,7 +278,7 @@ struct mt792x_dev {
 
 	struct mt76_connac_pm pm;
 	struct mt76_connac_coredump coredump;
-	const struct mt7921_hif_ops *hif_ops;
+	const struct mt792x_hif_ops *hif_ops;
 
 	struct work_struct ipv6_ns_work;
 	/* IPv6 addresses for WoWLAN */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 517e4d541bdc3..4227b5028a6ff 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -247,7 +247,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 		.sta_remove = mt7921_mac_sta_remove,
 		.update_survey = mt7921_update_channel,
 	};
-	static const struct mt7921_hif_ops mt7921_pcie_ops = {
+	static const struct mt792x_hif_ops mt7921_pcie_ops = {
 		.init_reset = mt7921e_init_reset,
 		.reset = mt7921e_mac_reset,
 		.mcu_init = mt7921e_mcu_init,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index 86da0cbbdf3b2..b438947c2bd8b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -114,7 +114,7 @@ static int mt7921s_probe(struct sdio_func *func,
 		.rd_rp = mt76s_rd_rp,
 		.type = MT76_BUS_SDIO,
 	};
-	static const struct mt7921_hif_ops mt7921_sdio_ops = {
+	static const struct mt792x_hif_ops mt7921_sdio_ops = {
 		.init_reset = mt7921s_init_reset,
 		.reset = mt7921s_mac_reset,
 		.mcu_init = mt7921s_mcu_init,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index 898cb1de9400e..b02a6d03c645c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -191,7 +191,7 @@ static int mt7921u_probe(struct usb_interface *usb_intf,
 		.sta_remove = mt7921_mac_sta_remove,
 		.update_survey = mt7921_update_channel,
 	};
-	static const struct mt7921_hif_ops hif_ops = {
+	static const struct mt792x_hif_ops hif_ops = {
 		.mcu_init = mt7921u_mcu_init,
 		.init_reset = mt7921u_init_reset,
 		.reset = mt7921u_mac_reset,
-- 
GitLab


From 1c42e0f283598b43b74318ef54f3d8a57ab46324 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:54 +0800
Subject: [PATCH 0464/1806] wifi: mt76: mt792x: move shared structure
 definition in mt792x.h

This is a preliminary patch to introduce WiFi7 chipset support

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7921/mt7921.h    | 111 +--------------
 drivers/net/wireless/mediatek/mt76/mt792x.h   | 129 ++++++++++++++++++
 2 files changed, 130 insertions(+), 110 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt792x.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index e84c6a56d40e6..b04d78a5d51ab 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -4,9 +4,7 @@
 #ifndef __MT7921_H
 #define __MT7921_H
 
-#include <linux/interrupt.h>
-#include <linux/ktime.h>
-#include "../mt76_connac_mcu.h"
+#include "../mt792x.h"
 #include "regs.h"
 #include "acpi_sar.h"
 
@@ -127,9 +125,6 @@ struct mt7921_sdio_intr {
 #define to_rssi(field, rxv)		((FIELD_GET(field, rxv) - 220) / 2)
 #define to_rcpi(rssi)			(2 * (rssi) + 220)
 
-struct mt792x_vif;
-struct mt792x_sta;
-
 enum mt7921_txq_id {
 	MT7921_TXQ_BAND0,
 	MT7921_TXQ_BAND1,
@@ -143,39 +138,6 @@ enum mt7921_rxq_id {
 	MT7921_RXQ_MCU_WM = 0,
 };
 
-DECLARE_EWMA(avg_signal, 10, 8)
-
-struct mt792x_sta {
-	struct mt76_wcid wcid; /* must be first */
-
-	struct mt792x_vif *vif;
-
-	u32 airtime_ac[8];
-
-	int ack_signal;
-	struct ewma_avg_signal avg_ack_signal;
-
-	unsigned long last_txs;
-
-	struct mt76_connac_sta_key_conf bip;
-};
-
-DECLARE_EWMA(rssi, 10, 8);
-
-struct mt792x_vif {
-	struct mt76_vif mt76; /* must be first */
-
-	struct mt792x_sta sta;
-	struct mt792x_sta *wep_sta;
-
-	struct mt792x_phy *phy;
-
-	struct ewma_rssi rssi;
-
-	struct ieee80211_tx_queue_params queue_params[IEEE80211_NUM_ACS];
-	struct ieee80211_chanctx_conf *ctx;
-};
-
 enum {
 	MT7921_CLC_POWER,
 	MT7921_CLC_CHAN,
@@ -199,40 +161,6 @@ struct mt7921_clc {
 	u8 data[];
 } __packed;
 
-struct mt792x_phy {
-	struct mt76_phy *mt76;
-	struct mt792x_dev *dev;
-
-	struct ieee80211_sband_iftype_data iftype[NUM_NL80211_BANDS][NUM_NL80211_IFTYPES];
-
-	u64 omac_mask;
-
-	u16 noise;
-
-	s16 coverage_class;
-	u8 slottime;
-
-	u32 rx_ampdu_ts;
-	u32 ampdu_ref;
-
-	struct mt76_mib_stats mib;
-
-	u8 sta_work_count;
-
-	struct sk_buff_head scan_event_list;
-	struct delayed_work scan_work;
-#ifdef CONFIG_ACPI
-	void *acpisar;
-#endif
-	void *clc[MT7921_CLC_MAX_NUM];
-
-	struct work_struct roc_work;
-	struct timer_list roc_timer;
-	wait_queue_head_t roc_wait;
-	u8 roc_token_id;
-	bool roc_grant;
-};
-
 enum mt7921_eeprom_field {
 	MT_EE_CHIP_ID =		0x000,
 	MT_EE_VERSION =		0x002,
@@ -249,43 +177,6 @@ enum mt7921_eeprom_field {
 #define mt7921_mcu_init(dev)		((dev)->hif_ops->mcu_init(dev))
 #define __mt7921_mcu_drv_pmctrl(dev)	((dev)->hif_ops->drv_own(dev))
 #define	__mt7921_mcu_fw_pmctrl(dev)	((dev)->hif_ops->fw_own(dev))
-struct mt792x_hif_ops {
-	int (*init_reset)(struct mt792x_dev *dev);
-	int (*reset)(struct mt792x_dev *dev);
-	int (*mcu_init)(struct mt792x_dev *dev);
-	int (*drv_own)(struct mt792x_dev *dev);
-	int (*fw_own)(struct mt792x_dev *dev);
-};
-
-struct mt792x_dev {
-	union { /* must be first */
-		struct mt76_dev mt76;
-		struct mt76_phy mphy;
-	};
-
-	const struct mt76_bus_ops *bus_ops;
-	struct mt792x_phy phy;
-
-	struct work_struct reset_work;
-	bool hw_full_reset:1;
-	bool hw_init_done:1;
-	bool fw_assert:1;
-
-	struct work_struct init_work;
-
-	u8 fw_debug;
-	u8 fw_features;
-
-	struct mt76_connac_pm pm;
-	struct mt76_connac_coredump coredump;
-	const struct mt792x_hif_ops *hif_ops;
-
-	struct work_struct ipv6_ns_work;
-	/* IPv6 addresses for WoWLAN */
-	struct sk_buff_head ipv6_ns_list;
-
-	enum environment_cap country_ie_env;
-};
 
 enum {
 	TXPWR_USER,
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
new file mode 100644
index 0000000000000..2c17c2e71af15
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: ISC */
+/* Copyright (C) 2023 MediaTek Inc. */
+
+#ifndef __MT792X_H
+#define __MT792X_H
+
+#include <linux/interrupt.h>
+#include <linux/ktime.h>
+
+#include "mt76_connac_mcu.h"
+
+struct mt792x_vif;
+struct mt792x_sta;
+
+enum {
+	MT792x_CLC_POWER,
+	MT792x_CLC_CHAN,
+	MT792x_CLC_MAX_NUM,
+};
+
+DECLARE_EWMA(avg_signal, 10, 8)
+
+struct mt792x_sta {
+	struct mt76_wcid wcid; /* must be first */
+
+	struct mt792x_vif *vif;
+
+	u32 airtime_ac[8];
+
+	int ack_signal;
+	struct ewma_avg_signal avg_ack_signal;
+
+	unsigned long last_txs;
+
+	struct mt76_connac_sta_key_conf bip;
+};
+
+DECLARE_EWMA(rssi, 10, 8);
+
+struct mt792x_vif {
+	struct mt76_vif mt76; /* must be first */
+
+	struct mt792x_sta sta;
+	struct mt792x_sta *wep_sta;
+
+	struct mt792x_phy *phy;
+
+	struct ewma_rssi rssi;
+
+	struct ieee80211_tx_queue_params queue_params[IEEE80211_NUM_ACS];
+	struct ieee80211_chanctx_conf *ctx;
+};
+
+struct mt792x_phy {
+	struct mt76_phy *mt76;
+	struct mt792x_dev *dev;
+
+	struct ieee80211_sband_iftype_data iftype[NUM_NL80211_BANDS][NUM_NL80211_IFTYPES];
+
+	u64 omac_mask;
+
+	u16 noise;
+
+	s16 coverage_class;
+	u8 slottime;
+
+	u32 rx_ampdu_ts;
+	u32 ampdu_ref;
+
+	struct mt76_mib_stats mib;
+
+	u8 sta_work_count;
+
+	struct sk_buff_head scan_event_list;
+	struct delayed_work scan_work;
+#ifdef CONFIG_ACPI
+	void *acpisar;
+#endif
+	void *clc[MT792x_CLC_MAX_NUM];
+
+	struct work_struct roc_work;
+	struct timer_list roc_timer;
+	wait_queue_head_t roc_wait;
+	u8 roc_token_id;
+	bool roc_grant;
+};
+
+struct mt792x_hif_ops {
+	int (*init_reset)(struct mt792x_dev *dev);
+	int (*reset)(struct mt792x_dev *dev);
+	int (*mcu_init)(struct mt792x_dev *dev);
+	int (*drv_own)(struct mt792x_dev *dev);
+	int (*fw_own)(struct mt792x_dev *dev);
+};
+
+struct mt792x_dev {
+	union { /* must be first */
+		struct mt76_dev mt76;
+		struct mt76_phy mphy;
+	};
+
+	const struct mt76_bus_ops *bus_ops;
+	struct mt792x_phy phy;
+
+	struct work_struct reset_work;
+	bool hw_full_reset:1;
+	bool hw_init_done:1;
+	bool fw_assert:1;
+	bool has_eht:1;
+
+	struct work_struct init_work;
+
+	u8 fw_debug;
+	u8 fw_features;
+
+	struct mt76_connac_pm pm;
+	struct mt76_connac_coredump coredump;
+	const struct mt792x_hif_ops *hif_ops;
+
+	struct work_struct ipv6_ns_work;
+	/* IPv6 addresses for WoWLAN */
+	struct sk_buff_head ipv6_ns_list;
+
+	enum environment_cap country_ie_env;
+	u32 backup_l1;
+	u32 backup_l2;
+};
+
+#endif /* __MT7925_H */
-- 
GitLab


From c605d0ce025358d50209468ede7b15a3d2656c1a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:55 +0800
Subject: [PATCH 0465/1806] wifi: mt76: mt7921: move
 mt792x_mutex_{acquire/release} in mt792x.h

This is a preliminary patch to introduce WiFi7 chipset support

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7921/debugfs.c   |  32 ++--
 .../net/wireless/mediatek/mt76/mt7921/init.c  |   8 +-
 .../net/wireless/mediatek/mt76/mt7921/mac.c   |  12 +-
 .../net/wireless/mediatek/mt76/mt7921/main.c  | 144 +++++++++---------
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |   5 -
 drivers/net/wireless/mediatek/mt76/mt792x.h   |   5 +
 6 files changed, 103 insertions(+), 103 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
index 6137a10c022ab..0c94fa7ae4851 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
@@ -8,9 +8,9 @@ mt7921_reg_set(void *data, u64 val)
 {
 	struct mt792x_dev *dev = data;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	mt76_wr(dev, dev->mt76.debugfs_reg, val);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return 0;
 }
@@ -20,9 +20,9 @@ mt7921_reg_get(void *data, u64 *val)
 {
 	struct mt792x_dev *dev = data;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	*val = mt76_rr(dev, dev->mt76.debugfs_reg);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return 0;
 }
@@ -34,12 +34,12 @@ mt7921_fw_debug_set(void *data, u64 val)
 {
 	struct mt792x_dev *dev = data;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	dev->fw_debug = (u8)val;
 	mt7921_mcu_fw_log_2_host(dev, dev->fw_debug);
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return 0;
 }
@@ -98,7 +98,7 @@ mt7921_tx_stats_show(struct seq_file *file, void *data)
 	struct mt76_mib_stats *mib = &phy->mib;
 	int i;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	mt7921_ampdu_stat_read_phy(phy, file);
 
@@ -113,7 +113,7 @@ mt7921_tx_stats_show(struct seq_file *file, void *data)
 			seq_puts(file, "\n");
 	}
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return 0;
 }
@@ -126,7 +126,7 @@ mt7921_queues_acq(struct seq_file *s, void *data)
 	struct mt792x_dev *dev = dev_get_drvdata(s->private);
 	int i;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	for (i = 0; i < 4; i++) {
 		u32 ctrl, val, qlen = 0;
@@ -146,7 +146,7 @@ mt7921_queues_acq(struct seq_file *s, void *data)
 		seq_printf(s, "AC%d: queued=%d\n", i, qlen);
 	}
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return 0;
 }
@@ -215,9 +215,9 @@ mt7921_txpwr(struct seq_file *s, void *data)
 	struct mt7921_txpwr txpwr;
 	int ret;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	ret = mt7921_get_txpwr_info(dev, &txpwr);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	if (ret)
 		return ret;
@@ -316,7 +316,7 @@ mt7921_deep_sleep_set(void *data, u64 val)
 	if (mt76_is_usb(&dev->mt76))
 		return -EOPNOTSUPP;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	if (pm->ds_enable_user == enable)
 		goto out;
 
@@ -324,7 +324,7 @@ mt7921_deep_sleep_set(void *data, u64 val)
 	pm->ds_enable = enable && !monitor;
 	mt76_connac_mcu_set_deep_sleep(&dev->mt76, pm->ds_enable);
 out:
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return 0;
 }
@@ -400,9 +400,9 @@ static int mt7921_chip_reset(void *data, u64 val)
 		break;
 	default:
 		/* Collect the core dump before reset wifisys. */
-		mt7921_mutex_acquire(dev);
+		mt792x_mutex_acquire(dev);
 		ret = mt76_connac_mcu_chip_config(&dev->mt76);
-		mt7921_mutex_release(dev);
+		mt792x_mutex_release(dev);
 		break;
 	}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index bace86813b768..100479c2e9f12 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -64,9 +64,9 @@ static ssize_t mt7921_thermal_temp_show(struct device *dev,
 		struct mt792x_dev *mdev = phy->dev;
 		int temperature;
 
-		mt7921_mutex_acquire(mdev);
+		mt792x_mutex_acquire(mdev);
 		temperature = mt7921_mcu_get_temperature(phy);
-		mt7921_mutex_release(mdev);
+		mt792x_mutex_release(mdev);
 
 		if (temperature < 0)
 			return temperature;
@@ -116,11 +116,11 @@ mt7921_regd_notifier(struct wiphy *wiphy,
 	dev->mt76.region = request->dfs_region;
 	dev->country_ie_env = request->country_ie_env;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	mt7921_mcu_set_clc(dev, request->alpha2, request->country_ie_env);
 	mt76_connac_mcu_set_channel_domain(hw->priv);
 	mt7921_set_tx_sar_pwr(hw, NULL);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 
 static int
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index a17d70aa90da9..49ba23ecf495c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -971,7 +971,7 @@ void mt7921_mac_work(struct work_struct *work)
 					       mac_work.work);
 	phy = mphy->priv;
 
-	mt7921_mutex_acquire(phy->dev);
+	mt792x_mutex_acquire(phy->dev);
 
 	mt76_update_survey(mphy);
 	if (++mphy->mac_work_count == 2) {
@@ -980,7 +980,7 @@ void mt7921_mac_work(struct work_struct *work)
 		mt7921_mac_update_mib_stats(phy);
 	}
 
-	mt7921_mutex_release(phy->dev);
+	mt792x_mutex_release(phy->dev);
 
 	mt76_tx_status_check(mphy->dev, false);
 	ieee80211_queue_delayed_work(phy->mt76->hw, &mphy->mac_work,
@@ -1191,9 +1191,9 @@ bool mt7921_usb_sdio_tx_status_data(struct mt76_dev *mdev, u8 *update)
 {
 	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	mt7921_mac_sta_poll(dev);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return false;
 }
@@ -1213,10 +1213,10 @@ void mt7921_set_ipv6_ns_work(struct work_struct *work)
 		if (!skb)
 			break;
 
-		mt7921_mutex_acquire(dev);
+		mt792x_mutex_acquire(dev);
 		ret = mt76_mcu_skb_send_msg(&dev->mt76, skb,
 					    MCU_UNI_CMD(OFFLOAD), true);
-		mt7921_mutex_release(dev);
+		mt792x_mutex_release(dev);
 
 	} while (!ret);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 2f597fb3ae5c7..2cd85fdd15f65 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -255,9 +255,9 @@ static int mt7921_start(struct ieee80211_hw *hw)
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int err;
 
-	mt7921_mutex_acquire(phy->dev);
+	mt792x_mutex_acquire(phy->dev);
 	err = __mt7921_start(phy);
-	mt7921_mutex_release(phy->dev);
+	mt792x_mutex_release(phy->dev);
 
 	return err;
 }
@@ -274,10 +274,10 @@ void mt7921_stop(struct ieee80211_hw *hw)
 	cancel_work_sync(&dev->reset_work);
 	mt76_connac_free_pending_tx_skbs(&dev->pm, NULL);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	clear_bit(MT76_STATE_RUNNING, &phy->mt76->state);
 	mt76_connac_mcu_set_mac_enable(&dev->mt76, 0, false, false);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 EXPORT_SYMBOL_GPL(mt7921_stop);
 
@@ -290,7 +290,7 @@ static int mt7921_add_interface(struct ieee80211_hw *hw,
 	struct mt76_txq *mtxq;
 	int idx, ret = 0;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	mvif->mt76.idx = __ffs64(~dev->mt76.vif_mask);
 	if (mvif->mt76.idx >= MT7921_MAX_INTERFACES) {
@@ -333,7 +333,7 @@ static int mt7921_add_interface(struct ieee80211_hw *hw,
 
 	vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER;
 out:
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return ret;
 }
@@ -347,7 +347,7 @@ static void mt7921_remove_interface(struct ieee80211_hw *hw,
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int idx = msta->wcid.idx;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	mt76_connac_free_pending_tx_skbs(&dev->pm, &msta->wcid);
 	mt76_connac_mcu_uni_add_dev(&dev->mphy, vif, &mvif->sta.wcid, false);
 
@@ -355,7 +355,7 @@ static void mt7921_remove_interface(struct ieee80211_hw *hw,
 
 	dev->mt76.vif_mask &= ~BIT_ULL(mvif->mt76.idx);
 	phy->omac_mask &= ~BIT_ULL(mvif->mt76.omac_idx);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	if (!list_empty(&msta->wcid.poll_list))
@@ -384,11 +384,11 @@ void mt7921_roc_work(struct work_struct *work)
 	if (!test_and_clear_bit(MT76_STATE_ROC, &phy->mt76->state))
 		return;
 
-	mt7921_mutex_acquire(phy->dev);
+	mt792x_mutex_acquire(phy->dev);
 	ieee80211_iterate_active_interfaces(phy->mt76->hw,
 					    IEEE80211_IFACE_ITER_RESUME_ALL,
 					    mt7921_roc_iter, phy);
-	mt7921_mutex_release(phy->dev);
+	mt792x_mutex_release(phy->dev);
 	ieee80211_remain_on_channel_expired(phy->mt76->hw);
 }
 
@@ -406,10 +406,10 @@ static int mt7921_abort_roc(struct mt792x_phy *phy, struct mt792x_vif *vif)
 	del_timer_sync(&phy->roc_timer);
 	cancel_work_sync(&phy->roc_work);
 
-	mt7921_mutex_acquire(phy->dev);
+	mt792x_mutex_acquire(phy->dev);
 	if (test_and_clear_bit(MT76_STATE_ROC, &phy->mt76->state))
 		err = mt7921_mcu_abort_roc(phy, vif, phy->roc_token_id);
-	mt7921_mutex_release(phy->dev);
+	mt792x_mutex_release(phy->dev);
 
 	return err;
 }
@@ -454,9 +454,9 @@ static int mt7921_remain_on_channel(struct ieee80211_hw *hw,
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int err;
 
-	mt7921_mutex_acquire(phy->dev);
+	mt792x_mutex_acquire(phy->dev);
 	err = mt7921_set_roc(phy, mvif, chan, duration, MT7921_ROC_REQ_ROC);
-	mt7921_mutex_release(phy->dev);
+	mt792x_mutex_release(phy->dev);
 
 	return err;
 }
@@ -477,7 +477,7 @@ static int mt7921_set_channel(struct mt792x_phy *phy)
 
 	cancel_delayed_work_sync(&phy->mt76->mac_work);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	set_bit(MT76_RESET, &phy->mt76->state);
 
 	mt76_set_channel(phy->mt76);
@@ -493,7 +493,7 @@ static int mt7921_set_channel(struct mt792x_phy *phy)
 
 out:
 	clear_bit(MT76_RESET, &phy->mt76->state);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	mt76_worker_schedule(&dev->mt76.tx_worker);
 	ieee80211_queue_delayed_work(phy->mt76->hw, &phy->mt76->mac_work,
@@ -546,7 +546,7 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		return -EOPNOTSUPP;
 	}
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	if (cmd == SET_KEY) {
 		*wcid_keyidx = idx;
@@ -570,7 +570,7 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 					      key, MCU_UNI_CMD(STA_REC_UPDATE),
 					      &mvif->wep_sta->wcid, cmd);
 out:
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return err;
 }
@@ -642,7 +642,7 @@ static int mt7921_config(struct ieee80211_hw *hw, u32 changed)
 		ieee80211_wake_queues(hw);
 	}
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	if (changed & IEEE80211_CONF_CHANGE_POWER) {
 		ret = mt7921_set_tx_sar_pwr(hw, NULL);
@@ -657,7 +657,7 @@ static int mt7921_config(struct ieee80211_hw *hw, u32 changed)
 	}
 
 out:
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return ret;
 }
@@ -698,9 +698,9 @@ static void mt7921_configure_filter(struct ieee80211_hw *hw,
 	MT7921_FILTER(FIF_CONTROL, CONTROL);
 	MT7921_FILTER(FIF_OTHER_BSS, OTHER_BSS);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	mt7921_mcu_set_rxfilter(dev, flags, 0, 0);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	*total_flags &= (FIF_OTHER_BSS | FIF_FCSFAIL | FIF_CONTROL);
 }
@@ -713,7 +713,7 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	if (changed & BSS_CHANGED_ERP_SLOT) {
 		int slottime = info->use_short_slot ? 9 : 20;
@@ -749,7 +749,7 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 						  info);
 	}
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 
 int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
@@ -800,7 +800,7 @@ void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls)
 		mt76_connac_mcu_uni_add_bss(&dev->mphy, vif, &mvif->sta.wcid,
@@ -814,7 +814,7 @@ void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 
 	mt7921_mcu_sta_update(dev, sta, vif, true, MT76_STA_INFO_STATE_ASSOC);
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 EXPORT_SYMBOL_GPL(mt7921_mac_sta_assoc);
 
@@ -909,9 +909,9 @@ static int mt7921_set_rts_threshold(struct ieee80211_hw *hw, u32 val)
 {
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	mt76_connac_mcu_set_rts_thresh(&dev->mt76, val, 0);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return 0;
 }
@@ -935,7 +935,7 @@ mt7921_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	mtxq = (struct mt76_txq *)txq->drv_priv;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
 		mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, ssn,
@@ -968,7 +968,7 @@ mt7921_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
 	}
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return ret;
 }
@@ -982,9 +982,9 @@ static int mt7921_sta_state(struct ieee80211_hw *hw,
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
 	if (dev->pm.ds_enable) {
-		mt7921_mutex_acquire(dev);
+		mt792x_mutex_acquire(dev);
 		mt76_connac_sta_state_dp(&dev->mt76, old_state, new_state);
-		mt7921_mutex_release(dev);
+		mt792x_mutex_release(dev);
 	}
 
 	return mt76_sta_state(hw, vif, sta, old_state, new_state);
@@ -997,14 +997,14 @@ mt7921_get_stats(struct ieee80211_hw *hw,
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt76_mib_stats *mib = &phy->mib;
 
-	mt7921_mutex_acquire(phy->dev);
+	mt792x_mutex_acquire(phy->dev);
 
 	stats->dot11RTSSuccessCount = mib->rts_cnt;
 	stats->dot11RTSFailureCount = mib->rts_retries_cnt;
 	stats->dot11FCSErrorCount = mib->fcs_err_cnt;
 	stats->dot11ACKFailureCount = mib->ack_fail_cnt;
 
-	mt7921_mutex_release(phy->dev);
+	mt792x_mutex_release(phy->dev);
 
 	return 0;
 }
@@ -1144,7 +1144,7 @@ void mt7921_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	};
 	int i, ei = 0;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	mt7921_mac_update_mib_stats(phy);
 
@@ -1184,7 +1184,7 @@ void mt7921_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	wi.initial_stat_idx = ei;
 	ieee80211_iterate_stations_atomic(hw, mt7921_ethtool_worker, &wi);
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	if (!wi.sta_count)
 		return;
@@ -1212,7 +1212,7 @@ mt7921_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	} tsf;
 	u16 n;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	n = omac_idx > HW_BSSID_MAX ? HW_BSSID_0 : omac_idx;
 	/* TSF software read */
@@ -1220,7 +1220,7 @@ mt7921_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	tsf.t32[0] = mt76_rr(dev, MT_LPON_UTTR0(0));
 	tsf.t32[1] = mt76_rr(dev, MT_LPON_UTTR1(0));
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return tsf.t64;
 }
@@ -1238,7 +1238,7 @@ mt7921_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	} tsf = { .t64 = timestamp, };
 	u16 n;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	n = omac_idx > HW_BSSID_MAX ? HW_BSSID_0 : omac_idx;
 	mt76_wr(dev, MT_LPON_UTTR0(0), tsf.t32[0]);
@@ -1246,7 +1246,7 @@ mt7921_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	/* TSF software overwrite */
 	mt76_set(dev, MT_LPON_TCR(0, n), MT_LPON_TCR_SW_WRITE);
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 
 static void
@@ -1255,10 +1255,10 @@ mt7921_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class)
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt792x_dev *dev = phy->dev;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	phy->coverage_class = max_t(s16, coverage_class, 0);
 	mt7921_mac_set_timing(phy);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 
 void mt7921_scan_work(struct work_struct *work)
@@ -1302,9 +1302,9 @@ mt7921_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct mt76_phy *mphy = hw->priv;
 	int err;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	err = mt76_connac_mcu_hw_scan(mphy, vif, req);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return err;
 }
@@ -1315,9 +1315,9 @@ mt7921_cancel_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	mt76_connac_mcu_cancel_hw_scan(mphy, vif);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 
 static int
@@ -1329,7 +1329,7 @@ mt7921_start_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct mt76_phy *mphy = hw->priv;
 	int err;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	err = mt76_connac_mcu_sched_scan_req(mphy, vif, req);
 	if (err < 0)
@@ -1337,7 +1337,7 @@ mt7921_start_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	err = mt76_connac_mcu_sched_scan_enable(mphy, vif, true);
 out:
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return err;
 }
@@ -1349,9 +1349,9 @@ mt7921_stop_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	struct mt76_phy *mphy = hw->priv;
 	int err;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	err = mt76_connac_mcu_sched_scan_enable(mphy, vif, false);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return err;
 }
@@ -1369,7 +1369,7 @@ mt7921_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 	if ((BIT(hweight8(tx_ant)) - 1) != tx_ant)
 		return -EINVAL;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	phy->mt76->antenna_mask = tx_ant;
 	phy->mt76->chainmask = tx_ant;
@@ -1377,7 +1377,7 @@ mt7921_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 	mt76_set_stream_caps(phy->mt76, true);
 	mt7921_set_stream_he_caps(phy);
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return 0;
 }
@@ -1432,7 +1432,7 @@ static int mt7921_suspend(struct ieee80211_hw *hw,
 	cancel_delayed_work_sync(&dev->pm.ps_work);
 	mt76_connac_free_pending_tx_skbs(&dev->pm, NULL);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	clear_bit(MT76_STATE_RUNNING, &phy->mt76->state);
 	ieee80211_iterate_active_interfaces(hw,
@@ -1440,7 +1440,7 @@ static int mt7921_suspend(struct ieee80211_hw *hw,
 					    mt7921_mcu_set_suspend_iter,
 					    &dev->mphy);
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return 0;
 }
@@ -1450,7 +1450,7 @@ static int mt7921_resume(struct ieee80211_hw *hw)
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	set_bit(MT76_STATE_RUNNING, &phy->mt76->state);
 	ieee80211_iterate_active_interfaces(hw,
@@ -1461,7 +1461,7 @@ static int mt7921_resume(struct ieee80211_hw *hw)
 	ieee80211_queue_delayed_work(hw, &phy->mt76->mac_work,
 				     MT7921_WATCHDOG_TIME);
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return 0;
 }
@@ -1480,9 +1480,9 @@ static void mt7921_set_rekey_data(struct ieee80211_hw *hw,
 {
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	mt76_connac_mcu_update_gtk_rekey(hw, vif, data);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 #endif /* CONFIG_PM */
 
@@ -1503,7 +1503,7 @@ static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw,
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	if (enabled)
 		set_bit(MT_WCID_FLAG_HDR_TRANS, &msta->wcid.flags);
@@ -1513,7 +1513,7 @@ static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw,
 	mt76_connac_mcu_sta_update_hdr_trans(&dev->mt76, vif, &msta->wcid,
 					     MCU_UNI_CMD(STA_REC_UPDATE));
 
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1601,7 +1601,7 @@ static int mt7921_set_sar_specs(struct ieee80211_hw *hw,
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	int err;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	err = mt7921_mcu_set_clc(dev, dev->mt76.alpha2,
 				 dev->country_ie_env);
 	if (err < 0)
@@ -1609,7 +1609,7 @@ static int mt7921_set_sar_specs(struct ieee80211_hw *hw,
 
 	err = mt7921_set_tx_sar_pwr(hw, sar);
 out:
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return err;
 }
@@ -1621,9 +1621,9 @@ mt7921_channel_switch_beacon(struct ieee80211_hw *hw,
 {
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	mt7921_mcu_uni_add_beacon_offload(dev, hw, vif, true);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 
 static int
@@ -1635,7 +1635,7 @@ mt7921_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	int err;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	err = mt76_connac_mcu_uni_add_bss(phy->mt76, vif, &mvif->sta.wcid,
 					  true, mvif->ctx);
@@ -1649,7 +1649,7 @@ mt7921_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	err = mt7921_mcu_sta_update(dev, NULL, vif, true,
 				    MT76_STA_INFO_STATE_NONE);
 out:
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 
 	return err;
 }
@@ -1663,7 +1663,7 @@ mt7921_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct mt792x_dev *dev = mt7921_hw_dev(hw);
 	int err;
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 
 	err = mt7921_mcu_set_bss_pm(dev, vif, false);
 	if (err)
@@ -1673,7 +1673,7 @@ mt7921_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 				    mvif->ctx);
 
 out:
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 
 static int
@@ -1711,11 +1711,11 @@ mt7921_change_chanctx(struct ieee80211_hw *hw,
 {
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
-	mt7921_mutex_acquire(phy->dev);
+	mt792x_mutex_acquire(phy->dev);
 	ieee80211_iterate_active_interfaces(phy->mt76->hw,
 					    IEEE80211_IFACE_ITER_ACTIVE,
 					    mt7921_ctx_iter, ctx);
-	mt7921_mutex_release(phy->dev);
+	mt792x_mutex_release(phy->dev);
 }
 
 static int
@@ -1757,10 +1757,10 @@ static void mt7921_mgd_prepare_tx(struct ieee80211_hw *hw,
 	u16 duration = info->duration ? info->duration :
 		       jiffies_to_msecs(HZ);
 
-	mt7921_mutex_acquire(dev);
+	mt792x_mutex_acquire(dev);
 	mt7921_set_roc(mvif->phy, mvif, mvif->ctx->def.chan, duration,
 		       MT7921_ROC_REQ_JOIN);
-	mt7921_mutex_release(dev);
+	mt792x_mutex_release(dev);
 }
 
 static void mt7921_mgd_complete_tx(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index b04d78a5d51ab..2ca8560aa5231 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -224,11 +224,6 @@ mt7921_hw_dev(struct ieee80211_hw *hw)
 	return container_of(phy->dev, struct mt792x_dev, mt76);
 }
 
-#define mt7921_mutex_acquire(dev)	\
-	mt76_connac_mutex_acquire(&(dev)->mt76, &(dev)->pm)
-#define mt7921_mutex_release(dev)	\
-	mt76_connac_mutex_release(&(dev)->mt76, &(dev)->pm)
-
 extern const struct ieee80211_ops mt7921_ops;
 
 u32 mt7921_reg_map(struct mt792x_dev *dev, u32 addr);
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 2c17c2e71af15..bc7d11acfa6a3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -126,4 +126,9 @@ struct mt792x_dev {
 	u32 backup_l2;
 };
 
+#define mt792x_mutex_acquire(dev)	\
+	mt76_connac_mutex_acquire(&(dev)->mt76, &(dev)->pm)
+#define mt792x_mutex_release(dev)	\
+	mt76_connac_mutex_release(&(dev)->mt76, &(dev)->pm)
+
 #endif /* __MT7925_H */
-- 
GitLab


From 20249e1a853c412f452aa6ee0beb752360e69f17 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:56 +0800
Subject: [PATCH 0466/1806] wifi: mt76: mt7921: move mt792x_hw_dev in mt792x.h

This is a preliminary patch to introduce WiFi7 chipset support

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/init.c  |  2 +-
 .../net/wireless/mediatek/mt76/mt7921/main.c  | 66 +++++++++----------
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  8 ---
 .../net/wireless/mediatek/mt76/mt7921/usb.c   |  2 +-
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  8 +++
 5 files changed, 43 insertions(+), 43 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 100479c2e9f12..d78cdaaf5bb65 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -110,7 +110,7 @@ mt7921_regd_notifier(struct wiphy *wiphy,
 		     struct regulatory_request *request)
 {
 	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	memcpy(dev->mt76.alpha2, request->alpha2, sizeof(dev->mt76.alpha2));
 	dev->mt76.region = request->dfs_region;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 2cd85fdd15f65..7213718ae3998 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -264,7 +264,7 @@ static int mt7921_start(struct ieee80211_hw *hw)
 
 void mt7921_stop(struct ieee80211_hw *hw)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	cancel_delayed_work_sync(&phy->mt76->mac_work);
@@ -285,7 +285,7 @@ static int mt7921_add_interface(struct ieee80211_hw *hw,
 				struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	struct mt76_txq *mtxq;
 	int idx, ret = 0;
@@ -343,7 +343,7 @@ static void mt7921_remove_interface(struct ieee80211_hw *hw,
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_sta *msta = &mvif->sta;
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int idx = msta->wcid.idx;
 
@@ -506,7 +506,7 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			  struct ieee80211_vif *vif, struct ieee80211_sta *sta,
 			  struct ieee80211_key_conf *key)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_sta *msta = sta ? (struct mt792x_sta *)sta->drv_priv :
 				  &mvif->sta;
@@ -630,7 +630,7 @@ void mt7921_set_runtime_pm(struct mt792x_dev *dev)
 
 static int mt7921_config(struct ieee80211_hw *hw, u32 changed)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int ret = 0;
 
@@ -686,7 +686,7 @@ static void mt7921_configure_filter(struct ieee80211_hw *hw,
 #define MT7921_FILTER_OTHER_BSS  BIT(6)
 #define MT7921_FILTER_ENABLE     BIT(31)
 
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	u32 flags = MT7921_FILTER_ENABLE;
 
 #define MT7921_FILTER(_fif, _type) do {			\
@@ -711,7 +711,7 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 				    u64 changed)
 {
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	mt792x_mutex_acquire(dev);
 
@@ -869,7 +869,7 @@ static void mt7921_tx(struct ieee80211_hw *hw,
 		      struct ieee80211_tx_control *control,
 		      struct sk_buff *skb)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_vif *vif = info->control.vif;
@@ -907,7 +907,7 @@ static void mt7921_tx(struct ieee80211_hw *hw,
 
 static int mt7921_set_rts_threshold(struct ieee80211_hw *hw, u32 val)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	mt792x_mutex_acquire(dev);
 	mt76_connac_mcu_set_rts_thresh(&dev->mt76, val, 0);
@@ -921,7 +921,7 @@ mt7921_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		    struct ieee80211_ampdu_params *params)
 {
 	enum ieee80211_ampdu_mlme_action action = params->action;
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct ieee80211_sta *sta = params->sta;
 	struct ieee80211_txq *txq = sta->txq[params->tid];
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
@@ -979,7 +979,7 @@ static int mt7921_sta_state(struct ieee80211_hw *hw,
 			    enum ieee80211_sta_state old_state,
 			    enum ieee80211_sta_state new_state)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	if (dev->pm.ds_enable) {
 		mt792x_mutex_acquire(dev);
@@ -1087,7 +1087,7 @@ static void
 mt7921_get_et_strings(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		      u32 sset, u8 *data)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	if (sset != ETH_SS_STATS)
 		return;
@@ -1105,7 +1105,7 @@ static int
 mt7921_get_et_sset_count(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			 int sset)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	if (sset != ETH_SS_STATS)
 		return 0;
@@ -1204,7 +1204,7 @@ static u64
 mt7921_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	u8 omac_idx = mvif->mt76.omac_idx;
 	union {
 		u64 t64;
@@ -1230,7 +1230,7 @@ mt7921_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       u64 timestamp)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	u8 omac_idx = mvif->mt76.omac_idx;
 	union {
 		u64 t64;
@@ -1298,7 +1298,7 @@ static int
 mt7921_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       struct ieee80211_scan_request *req)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 	int err;
 
@@ -1312,7 +1312,7 @@ mt7921_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 static void
 mt7921_cancel_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 
 	mt792x_mutex_acquire(dev);
@@ -1325,7 +1325,7 @@ mt7921_start_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			struct cfg80211_sched_scan_request *req,
 			struct ieee80211_scan_ies *ies)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 	int err;
 
@@ -1345,7 +1345,7 @@ out:
 static int
 mt7921_stop_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt76_phy *mphy = hw->priv;
 	int err;
 
@@ -1359,7 +1359,7 @@ mt7921_stop_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 static int
 mt7921_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 	int max_nss = hweight8(hw->wiphy->available_antennas_tx);
 
@@ -1423,7 +1423,7 @@ static void mt7921_sta_statistics(struct ieee80211_hw *hw,
 static int mt7921_suspend(struct ieee80211_hw *hw,
 			  struct cfg80211_wowlan *wowlan)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	cancel_delayed_work_sync(&phy->scan_work);
@@ -1447,7 +1447,7 @@ static int mt7921_suspend(struct ieee80211_hw *hw,
 
 static int mt7921_resume(struct ieee80211_hw *hw)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
 
 	mt792x_mutex_acquire(dev);
@@ -1468,7 +1468,7 @@ static int mt7921_resume(struct ieee80211_hw *hw)
 
 static void mt7921_set_wakeup(struct ieee80211_hw *hw, bool enabled)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt76_dev *mdev = &dev->mt76;
 
 	device_set_wakeup_enable(mdev->dev, enabled);
@@ -1478,7 +1478,7 @@ static void mt7921_set_rekey_data(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
 				  struct cfg80211_gtk_rekey_data *data)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	mt792x_mutex_acquire(dev);
 	mt76_connac_mcu_update_gtk_rekey(hw, vif, data);
@@ -1489,7 +1489,7 @@ static void mt7921_set_rekey_data(struct ieee80211_hw *hw,
 static void mt7921_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			 u32 queues, bool drop)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	wait_event_timeout(dev->mt76.tx_wait, !mt76_has_tx_pending(&dev->mphy),
 			   HZ / 2);
@@ -1501,7 +1501,7 @@ static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw,
 					 bool enabled)
 {
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	mt792x_mutex_acquire(dev);
 
@@ -1598,7 +1598,7 @@ int mt7921_set_tx_sar_pwr(struct ieee80211_hw *hw,
 static int mt7921_set_sar_specs(struct ieee80211_hw *hw,
 				const struct cfg80211_sar_specs *sar)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	int err;
 
 	mt792x_mutex_acquire(dev);
@@ -1619,7 +1619,7 @@ mt7921_channel_switch_beacon(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif,
 			     struct cfg80211_chan_def *chandef)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	mt792x_mutex_acquire(dev);
 	mt7921_mcu_uni_add_beacon_offload(dev, hw, vif, true);
@@ -1632,7 +1632,7 @@ mt7921_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	int err;
 
 	mt792x_mutex_acquire(dev);
@@ -1660,7 +1660,7 @@ mt7921_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	int err;
 
 	mt792x_mutex_acquire(dev);
@@ -1725,7 +1725,7 @@ mt7921_assign_vif_chanctx(struct ieee80211_hw *hw,
 			  struct ieee80211_chanctx_conf *ctx)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	mutex_lock(&dev->mt76.mutex);
 	mvif->ctx = ctx;
@@ -1741,7 +1741,7 @@ mt7921_unassign_vif_chanctx(struct ieee80211_hw *hw,
 			    struct ieee80211_chanctx_conf *ctx)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	mutex_lock(&dev->mt76.mutex);
 	mvif->ctx = NULL;
@@ -1753,7 +1753,7 @@ static void mt7921_mgd_prepare_tx(struct ieee80211_hw *hw,
 				  struct ieee80211_prep_tx_info *info)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	u16 duration = info->duration ? info->duration :
 		       jiffies_to_msecs(HZ);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 2ca8560aa5231..ad18fcc4a7b07 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -216,14 +216,6 @@ mt7921_hw_phy(struct ieee80211_hw *hw)
 	return phy->priv;
 }
 
-static inline struct mt792x_dev *
-mt7921_hw_dev(struct ieee80211_hw *hw)
-{
-	struct mt76_phy *phy = hw->priv;
-
-	return container_of(phy->dev, struct mt792x_dev, mt76);
-}
-
 extern const struct ieee80211_ops mt7921_ops;
 
 u32 mt7921_reg_map(struct mt792x_dev *dev, u32 addr);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index b02a6d03c645c..9d54be3d3d038 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -157,7 +157,7 @@ static int mt7921u_mcu_init(struct mt792x_dev *dev)
 
 static void mt7921u_stop(struct ieee80211_hw *hw)
 {
-	struct mt792x_dev *dev = mt7921_hw_dev(hw);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	mt76u_stop_tx(&dev->mt76);
 	mt7921_stop(hw);
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index bc7d11acfa6a3..9c724bc156afa 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -126,6 +126,14 @@ struct mt792x_dev {
 	u32 backup_l2;
 };
 
+static inline struct mt792x_dev *
+mt792x_hw_dev(struct ieee80211_hw *hw)
+{
+	struct mt76_phy *phy = hw->priv;
+
+	return container_of(phy->dev, struct mt792x_dev, mt76);
+}
+
 #define mt792x_mutex_acquire(dev)	\
 	mt76_connac_mutex_acquire(&(dev)->mt76, &(dev)->pm)
 #define mt792x_mutex_release(dev)	\
-- 
GitLab


From c74df1c067f2af0a3758a5ab02806f501473797c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:57 +0800
Subject: [PATCH 0467/1806] wifi: mt76: mt792x: introduce mt792x-lib module

mt792x-lib module will contain the shared code between mt7921 and new
MT79 WiFi7 chipset

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/Kconfig    |   4 +
 drivers/net/wireless/mediatek/mt76/Makefile   |   4 +
 .../net/wireless/mediatek/mt76/mt7921/Kconfig |   2 +-
 .../wireless/mediatek/mt76/mt7921/Makefile    |   4 +-
 .../wireless/mediatek/mt76/mt7921/debugfs.c   |   2 +-
 .../net/wireless/mediatek/mt76/mt7921/init.c  |  16 +-
 .../net/wireless/mediatek/mt76/mt7921/mac.c   | 148 +----
 .../net/wireless/mediatek/mt76/mt7921/main.c  | 535 ++----------------
 .../net/wireless/mediatek/mt76/mt7921/mcu.c   |   2 +-
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  25 +-
 .../net/wireless/mediatek/mt76/mt7921/regs.h  |   4 +
 .../wireless/mediatek/mt76/mt7921/sdio_mcu.c  |   2 +-
 .../net/wireless/mediatek/mt76/mt7921/trace.c |  12 -
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  61 ++
 .../net/wireless/mediatek/mt76/mt792x_core.c  | 469 +++++++++++++++
 .../net/wireless/mediatek/mt76/mt792x_mac.c   | 136 +++++
 .../net/wireless/mediatek/mt76/mt792x_regs.h  |   3 -
 .../net/wireless/mediatek/mt76/mt792x_trace.c |  14 +
 .../{mt7921/mt7921_trace.h => mt792x_trace.h} |  14 +-
 19 files changed, 763 insertions(+), 694 deletions(-)
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt7921/trace.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt792x_core.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt792x_mac.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt792x_trace.c
 rename drivers/net/wireless/mediatek/mt76/{mt7921/mt7921_trace.h => mt792x_trace.h} (72%)

diff --git a/drivers/net/wireless/mediatek/mt76/Kconfig b/drivers/net/wireless/mediatek/mt76/Kconfig
index 18152c16c36f2..1ddf195597a8e 100644
--- a/drivers/net/wireless/mediatek/mt76/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/Kconfig
@@ -29,6 +29,10 @@ config MT76_CONNAC_LIB
 	tristate
 	select MT76_CORE
 
+config MT792x_LIB
+	tristate
+	select MT76_CONNAC_LIB
+
 source "drivers/net/wireless/mediatek/mt76/mt76x0/Kconfig"
 source "drivers/net/wireless/mediatek/mt76/mt76x2/Kconfig"
 source "drivers/net/wireless/mediatek/mt76/mt7603/Kconfig"
diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index d8e8079c8b54f..a20eebba04bac 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_MT76_SDIO) += mt76-sdio.o
 obj-$(CONFIG_MT76x02_LIB) += mt76x02-lib.o
 obj-$(CONFIG_MT76x02_USB) += mt76x02-usb.o
 obj-$(CONFIG_MT76_CONNAC_LIB) += mt76-connac-lib.o
+obj-$(CONFIG_MT792x_LIB) += mt792x-lib.o
 
 mt76-y := \
 	mmio.o util.o trace.o dma.o mac80211.o debugfs.o eeprom.o \
@@ -19,6 +20,7 @@ mt76-sdio-y := sdio.o sdio_txrx.o
 CFLAGS_trace.o := -I$(src)
 CFLAGS_usb_trace.o := -I$(src)
 CFLAGS_mt76x02_trace.o := -I$(src)
+CFLAGS_mt792x_trace.o := -I$(src)
 
 mt76x02-lib-y := mt76x02_util.o mt76x02_mac.o mt76x02_mcu.o \
 		 mt76x02_eeprom.o mt76x02_phy.o mt76x02_mmio.o \
@@ -29,6 +31,8 @@ mt76x02-usb-y := mt76x02_usb_mcu.o mt76x02_usb_core.o
 
 mt76-connac-lib-y := mt76_connac_mcu.o mt76_connac_mac.o mt76_connac3_mac.o
 
+mt792x-lib-y := mt792x_core.o mt792x_mac.o mt792x_trace.o
+
 obj-$(CONFIG_MT76x0_COMMON) += mt76x0/
 obj-$(CONFIG_MT76x2_COMMON) += mt76x2/
 obj-$(CONFIG_MT7603E) += mt7603/
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/Kconfig b/drivers/net/wireless/mediatek/mt76/mt7921/Kconfig
index adff2d7350b57..b92630cdf88b6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: ISC
 config MT7921_COMMON
 	tristate
-	select MT76_CONNAC_LIB
+	select MT792x_LIB
 	select WANT_DEV_COREDUMP
 
 config MT7921E
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/Makefile b/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
index e5d2d2e131a2b..fd82dff76dae6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
@@ -5,9 +5,7 @@ obj-$(CONFIG_MT7921E) += mt7921e.o
 obj-$(CONFIG_MT7921S) += mt7921s.o
 obj-$(CONFIG_MT7921U) += mt7921u.o
 
-CFLAGS_trace.o := -I$(src)
-
-mt7921-common-y := mac.o mcu.o main.o init.o debugfs.o trace.o
+mt7921-common-y := mac.o mcu.o main.o init.o debugfs.o
 mt7921-common-$(CONFIG_NL80211_TESTMODE) += testmode.o
 mt7921-common-$(CONFIG_ACPI) += acpi_sar.o
 mt7921e-y := pci.o pci_mac.o pci_mcu.o dma.o
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
index 0c94fa7ae4851..59920cffee6a7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
@@ -67,7 +67,7 @@ mt7921_ampdu_stat_read_phy(struct mt792x_phy *phy,
 	if (!phy)
 		return;
 
-	mt7921_mac_update_mib_stats(phy);
+	mt792x_mac_update_mib_stats(phy);
 
 	/* Tx ampdu stat */
 	for (i = 0; i < ARRAY_SIZE(range); i++)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index d78cdaaf5bb65..449ce34a6dcf3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -12,7 +12,7 @@
 
 static const struct ieee80211_iface_limit if_limits[] = {
 	{
-		.max = MT7921_MAX_INTERFACES,
+		.max = MT792x_MAX_INTERFACES,
 		.types = BIT(NL80211_IFTYPE_STATION)
 	},
 	{
@@ -25,7 +25,7 @@ static const struct ieee80211_iface_combination if_comb[] = {
 	{
 		.limits = if_limits,
 		.n_limits = ARRAY_SIZE(if_limits),
-		.max_interfaces = MT7921_MAX_INTERFACES,
+		.max_interfaces = MT792x_MAX_INTERFACES,
 		.num_different_channels = 1,
 		.beacon_int_infra_match = true,
 	},
@@ -126,7 +126,7 @@ mt7921_regd_notifier(struct wiphy *wiphy,
 static int
 mt7921_init_wiphy(struct ieee80211_hw *hw)
 {
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 	struct mt792x_dev *dev = phy->dev;
 	struct wiphy *wiphy = hw->wiphy;
 
@@ -319,7 +319,7 @@ int mt7921_mac_init(struct mt792x_dev *dev)
 	/* enable hardware rx header translation */
 	mt76_set(dev, MT_MDP_DCR0, MT_MDP_DCR0_RX_HDR_TRANS_EN);
 
-	for (i = 0; i < MT7921_WTBL_SIZE; i++)
+	for (i = 0; i < MT792x_WTBL_SIZE; i++)
 		mt7921_mac_wtbl_update(dev, i,
 				       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
 	for (i = 0; i < 2; i++)
@@ -379,7 +379,7 @@ static int mt7921_init_wcid(struct mt792x_dev *dev)
 	int idx;
 
 	/* Beacon and mgmt frames should occupy wcid 0 */
-	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7921_WTBL_STA - 1);
+	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT792x_WTBL_STA - 1);
 	if (idx)
 		return -ENOSPC;
 
@@ -437,7 +437,7 @@ int mt7921_register_device(struct mt792x_dev *dev)
 	dev->phy.dev = dev;
 	dev->phy.mt76 = &dev->mt76.phy;
 	dev->mt76.phy.priv = &dev->phy;
-	dev->mt76.tx_worker.fn = mt7921_tx_worker;
+	dev->mt76.tx_worker.fn = mt792x_tx_worker;
 
 	INIT_DELAYED_WORK(&dev->pm.ps_work, mt7921_pm_power_save_work);
 	INIT_WORK(&dev->pm.wake_work, mt7921_pm_wake_work);
@@ -447,7 +447,7 @@ int mt7921_register_device(struct mt792x_dev *dev)
 	if (mt76_is_sdio(&dev->mt76))
 		init_waitqueue_head(&dev->mt76.sdio.wait);
 	spin_lock_init(&dev->pm.txq_lock);
-	INIT_DELAYED_WORK(&dev->mphy.mac_work, mt7921_mac_work);
+	INIT_DELAYED_WORK(&dev->mphy.mac_work, mt792x_mac_work);
 	INIT_DELAYED_WORK(&dev->phy.scan_work, mt7921_scan_work);
 	INIT_DELAYED_WORK(&dev->coredump.work, mt7921_coredump_work);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -461,7 +461,7 @@ int mt7921_register_device(struct mt792x_dev *dev)
 	INIT_WORK(&dev->init_work, mt7921_init_work);
 
 	INIT_WORK(&dev->phy.roc_work, mt7921_roc_work);
-	timer_setup(&dev->phy.roc_timer, mt7921_roc_timer, 0);
+	timer_setup(&dev->phy.roc_timer, mt792x_roc_timer, 0);
 	init_waitqueue_head(&dev->phy.roc_wait);
 
 	dev->pm.idle_timeout = MT7921_PM_TIMEOUT;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 49ba23ecf495c..40f006664ad7d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -15,6 +15,15 @@
 
 #define MT_WTBL_AC0_CTT_OFFSET		20
 
+bool mt7921_mac_wtbl_update(struct mt792x_dev *dev, int idx, u32 mask)
+{
+	mt76_rmw(dev, MT_WTBL_UPDATE, MT_WTBL_UPDATE_WLAN_IDX,
+		 FIELD_PREP(MT_WTBL_UPDATE_WLAN_IDX, idx) | mask);
+
+	return mt76_poll(dev, MT_WTBL_UPDATE, MT_WTBL_UPDATE_BUSY,
+			 0, 5000);
+}
+
 static u32 mt7921_mac_wtbl_lmac_addr(int idx, u8 offset)
 {
 	return MT_WTBL_LMAC_OFFS(idx, 0) + offset * 4;
@@ -43,15 +52,6 @@ static struct mt76_wcid *mt7921_rx_get_wcid(struct mt792x_dev *dev,
 	return &sta->vif->sta.wcid;
 }
 
-bool mt7921_mac_wtbl_update(struct mt792x_dev *dev, int idx, u32 mask)
-{
-	mt76_rmw(dev, MT_WTBL_UPDATE, MT_WTBL_UPDATE_WLAN_IDX,
-		 FIELD_PREP(MT_WTBL_UPDATE_WLAN_IDX, idx) | mask);
-
-	return mt76_poll(dev, MT_WTBL_UPDATE, MT_WTBL_UPDATE_BUSY,
-			 0, 5000);
-}
-
 static void mt7921_mac_sta_poll(struct mt792x_dev *dev)
 {
 	static const u8 ac_to_tid[] = {
@@ -528,7 +528,7 @@ void mt7921_mac_add_txs(struct mt792x_dev *dev, void *data)
 	if (pid < MT_PACKET_ID_FIRST)
 		return;
 
-	if (wcidx >= MT7921_WTBL_SIZE)
+	if (wcidx >= MT792x_WTBL_SIZE)
 		return;
 
 	rcu_read_lock();
@@ -721,47 +721,6 @@ void mt7921_mac_reset_counters(struct mt792x_phy *phy)
 	mt76_set(dev, MT_WF_RMAC_MIB_AIRTIME0(0), MT_WF_RMAC_MIB_RXTIME_CLR);
 }
 
-void mt7921_mac_set_timing(struct mt792x_phy *phy)
-{
-	s16 coverage_class = phy->coverage_class;
-	struct mt792x_dev *dev = phy->dev;
-	u32 val, reg_offset;
-	u32 cck = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, 231) |
-		  FIELD_PREP(MT_TIMEOUT_VAL_CCA, 48);
-	u32 ofdm = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, 60) |
-		   FIELD_PREP(MT_TIMEOUT_VAL_CCA, 28);
-	bool is_2ghz = phy->mt76->chandef.chan->band == NL80211_BAND_2GHZ;
-	int sifs = is_2ghz ? 10 : 16, offset;
-
-	if (!test_bit(MT76_STATE_RUNNING, &phy->mt76->state))
-		return;
-
-	mt76_set(dev, MT_ARB_SCR(0),
-		 MT_ARB_SCR_TX_DISABLE | MT_ARB_SCR_RX_DISABLE);
-	udelay(1);
-
-	offset = 3 * coverage_class;
-	reg_offset = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, offset) |
-		     FIELD_PREP(MT_TIMEOUT_VAL_CCA, offset);
-
-	mt76_wr(dev, MT_TMAC_CDTR(0), cck + reg_offset);
-	mt76_wr(dev, MT_TMAC_ODTR(0), ofdm + reg_offset);
-	mt76_wr(dev, MT_TMAC_ICR0(0),
-		FIELD_PREP(MT_IFS_EIFS, 360) |
-		FIELD_PREP(MT_IFS_RIFS, 2) |
-		FIELD_PREP(MT_IFS_SIFS, sifs) |
-		FIELD_PREP(MT_IFS_SLOT, phy->slottime));
-
-	if (phy->slottime < 20 || !is_2ghz)
-		val = MT7921_CFEND_RATE_DEFAULT;
-	else
-		val = MT7921_CFEND_RATE_11B;
-
-	mt76_rmw_field(dev, MT_AGG_ACR0(0), MT_AGG_ACR_CFEND_RATE, val);
-	mt76_clear(dev, MT_ARB_SCR(0),
-		   MT_ARB_SCR_TX_DISABLE | MT_ARB_SCR_RX_DISABLE);
-}
-
 static u8
 mt7921_phy_get_nf(struct mt792x_phy *phy, int idx)
 {
@@ -902,91 +861,6 @@ void mt7921_reset(struct mt76_dev *mdev)
 }
 EXPORT_SYMBOL_GPL(mt7921_reset);
 
-void mt7921_mac_update_mib_stats(struct mt792x_phy *phy)
-{
-	struct mt76_mib_stats *mib = &phy->mib;
-	struct mt792x_dev *dev = phy->dev;
-	int i, aggr0 = 0, aggr1;
-	u32 val;
-
-	mib->fcs_err_cnt += mt76_get_field(dev, MT_MIB_SDR3(0),
-					   MT_MIB_SDR3_FCS_ERR_MASK);
-	mib->ack_fail_cnt += mt76_get_field(dev, MT_MIB_MB_BSDR3(0),
-					    MT_MIB_ACK_FAIL_COUNT_MASK);
-	mib->ba_miss_cnt += mt76_get_field(dev, MT_MIB_MB_BSDR2(0),
-					   MT_MIB_BA_FAIL_COUNT_MASK);
-	mib->rts_cnt += mt76_get_field(dev, MT_MIB_MB_BSDR0(0),
-				       MT_MIB_RTS_COUNT_MASK);
-	mib->rts_retries_cnt += mt76_get_field(dev, MT_MIB_MB_BSDR1(0),
-					       MT_MIB_RTS_FAIL_COUNT_MASK);
-
-	mib->tx_ampdu_cnt += mt76_rr(dev, MT_MIB_SDR12(0));
-	mib->tx_mpdu_attempts_cnt += mt76_rr(dev, MT_MIB_SDR14(0));
-	mib->tx_mpdu_success_cnt += mt76_rr(dev, MT_MIB_SDR15(0));
-
-	val = mt76_rr(dev, MT_MIB_SDR32(0));
-	mib->tx_pkt_ebf_cnt += FIELD_GET(MT_MIB_SDR9_EBF_CNT_MASK, val);
-	mib->tx_pkt_ibf_cnt += FIELD_GET(MT_MIB_SDR9_IBF_CNT_MASK, val);
-
-	val = mt76_rr(dev, MT_ETBF_TX_APP_CNT(0));
-	mib->tx_bf_ibf_ppdu_cnt += FIELD_GET(MT_ETBF_TX_IBF_CNT, val);
-	mib->tx_bf_ebf_ppdu_cnt += FIELD_GET(MT_ETBF_TX_EBF_CNT, val);
-
-	val = mt76_rr(dev, MT_ETBF_RX_FB_CNT(0));
-	mib->tx_bf_rx_fb_all_cnt += FIELD_GET(MT_ETBF_RX_FB_ALL, val);
-	mib->tx_bf_rx_fb_he_cnt += FIELD_GET(MT_ETBF_RX_FB_HE, val);
-	mib->tx_bf_rx_fb_vht_cnt += FIELD_GET(MT_ETBF_RX_FB_VHT, val);
-	mib->tx_bf_rx_fb_ht_cnt += FIELD_GET(MT_ETBF_RX_FB_HT, val);
-
-	mib->rx_mpdu_cnt += mt76_rr(dev, MT_MIB_SDR5(0));
-	mib->rx_ampdu_cnt += mt76_rr(dev, MT_MIB_SDR22(0));
-	mib->rx_ampdu_bytes_cnt += mt76_rr(dev, MT_MIB_SDR23(0));
-	mib->rx_ba_cnt += mt76_rr(dev, MT_MIB_SDR31(0));
-
-	for (i = 0; i < ARRAY_SIZE(mib->tx_amsdu); i++) {
-		val = mt76_rr(dev, MT_PLE_AMSDU_PACK_MSDU_CNT(i));
-		mib->tx_amsdu[i] += val;
-		mib->tx_amsdu_cnt += val;
-	}
-
-	for (i = 0, aggr1 = aggr0 + 8; i < 4; i++) {
-		u32 val2;
-
-		val = mt76_rr(dev, MT_TX_AGG_CNT(0, i));
-		val2 = mt76_rr(dev, MT_TX_AGG_CNT2(0, i));
-
-		phy->mt76->aggr_stats[aggr0++] += val & 0xffff;
-		phy->mt76->aggr_stats[aggr0++] += val >> 16;
-		phy->mt76->aggr_stats[aggr1++] += val2 & 0xffff;
-		phy->mt76->aggr_stats[aggr1++] += val2 >> 16;
-	}
-}
-
-void mt7921_mac_work(struct work_struct *work)
-{
-	struct mt792x_phy *phy;
-	struct mt76_phy *mphy;
-
-	mphy = (struct mt76_phy *)container_of(work, struct mt76_phy,
-					       mac_work.work);
-	phy = mphy->priv;
-
-	mt792x_mutex_acquire(phy->dev);
-
-	mt76_update_survey(mphy);
-	if (++mphy->mac_work_count == 2) {
-		mphy->mac_work_count = 0;
-
-		mt7921_mac_update_mib_stats(phy);
-	}
-
-	mt792x_mutex_release(phy->dev);
-
-	mt76_tx_status_check(mphy->dev, false);
-	ieee80211_queue_delayed_work(phy->mt76->hw, &mphy->mac_work,
-				     MT7921_WATCHDOG_TIME);
-}
-
 void mt7921_pm_wake_work(struct work_struct *work)
 {
 	struct mt792x_dev *dev;
@@ -1013,7 +887,7 @@ void mt7921_pm_wake_work(struct work_struct *work)
 		}
 		if (test_bit(MT76_STATE_RUNNING, &mphy->state))
 			ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
-						     MT7921_WATCHDOG_TIME);
+						     MT792x_WATCHDOG_TIME);
 	}
 
 	ieee80211_wake_queues(mphy->hw);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 7213718ae3998..2239688075169 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -244,7 +244,7 @@ int __mt7921_start(struct mt792x_phy *phy)
 	set_bit(MT76_STATE_RUNNING, &mphy->state);
 
 	ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
-				     MT7921_WATCHDOG_TIME);
+				     MT792x_WATCHDOG_TIME);
 
 	return 0;
 }
@@ -252,7 +252,7 @@ EXPORT_SYMBOL_GPL(__mt7921_start);
 
 static int mt7921_start(struct ieee80211_hw *hw)
 {
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 	int err;
 
 	mt792x_mutex_acquire(phy->dev);
@@ -265,7 +265,7 @@ static int mt7921_start(struct ieee80211_hw *hw)
 void mt7921_stop(struct ieee80211_hw *hw)
 {
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 
 	cancel_delayed_work_sync(&phy->mt76->mac_work);
 
@@ -281,19 +281,19 @@ void mt7921_stop(struct ieee80211_hw *hw)
 }
 EXPORT_SYMBOL_GPL(mt7921_stop);
 
-static int mt7921_add_interface(struct ieee80211_hw *hw,
-				struct ieee80211_vif *vif)
+static int
+mt7921_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 	struct mt76_txq *mtxq;
 	int idx, ret = 0;
 
 	mt792x_mutex_acquire(dev);
 
 	mvif->mt76.idx = __ffs64(~dev->mt76.vif_mask);
-	if (mvif->mt76.idx >= MT7921_MAX_INTERFACES) {
+	if (mvif->mt76.idx >= MT792x_MAX_INTERFACES) {
 		ret = -ENOSPC;
 		goto out;
 	}
@@ -311,7 +311,7 @@ static int mt7921_add_interface(struct ieee80211_hw *hw,
 	dev->mt76.vif_mask |= BIT_ULL(mvif->mt76.idx);
 	phy->omac_mask |= BIT_ULL(mvif->mt76.omac_idx);
 
-	idx = MT7921_WTBL_RESERVED - mvif->mt76.idx;
+	idx = MT792x_WTBL_RESERVED - mvif->mt76.idx;
 
 	INIT_LIST_HEAD(&mvif->sta.wcid.poll_list);
 	mvif->sta.wcid.idx = idx;
@@ -338,33 +338,6 @@ out:
 	return ret;
 }
 
-static void mt7921_remove_interface(struct ieee80211_hw *hw,
-				    struct ieee80211_vif *vif)
-{
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_sta *msta = &mvif->sta;
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	int idx = msta->wcid.idx;
-
-	mt792x_mutex_acquire(dev);
-	mt76_connac_free_pending_tx_skbs(&dev->pm, &msta->wcid);
-	mt76_connac_mcu_uni_add_dev(&dev->mphy, vif, &mvif->sta.wcid, false);
-
-	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
-
-	dev->mt76.vif_mask &= ~BIT_ULL(mvif->mt76.idx);
-	phy->omac_mask &= ~BIT_ULL(mvif->mt76.omac_idx);
-	mt792x_mutex_release(dev);
-
-	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (!list_empty(&msta->wcid.poll_list))
-		list_del_init(&msta->wcid.poll_list);
-	spin_unlock_bh(&dev->mt76.sta_poll_lock);
-
-	mt76_packet_id_flush(&dev->mt76, &msta->wcid);
-}
-
 static void mt7921_roc_iter(void *priv, u8 *mac,
 			    struct ieee80211_vif *vif)
 {
@@ -392,13 +365,6 @@ void mt7921_roc_work(struct work_struct *work)
 	ieee80211_remain_on_channel_expired(phy->mt76->hw);
 }
 
-void mt7921_roc_timer(struct timer_list *timer)
-{
-	struct mt792x_phy *phy = from_timer(phy, timer, roc_timer);
-
-	ieee80211_queue_work(phy->mt76->hw, &phy->roc_work);
-}
-
 static int mt7921_abort_roc(struct mt792x_phy *phy, struct mt792x_vif *vif)
 {
 	int err = 0;
@@ -451,7 +417,7 @@ static int mt7921_remain_on_channel(struct ieee80211_hw *hw,
 				    enum ieee80211_roc_type type)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 	int err;
 
 	mt792x_mutex_acquire(phy->dev);
@@ -465,7 +431,7 @@ static int mt7921_cancel_remain_on_channel(struct ieee80211_hw *hw,
 					   struct ieee80211_vif *vif)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 
 	return mt7921_abort_roc(phy, mvif);
 }
@@ -486,7 +452,7 @@ static int mt7921_set_channel(struct mt792x_phy *phy)
 	if (ret)
 		goto out;
 
-	mt7921_mac_set_timing(phy);
+	mt792x_mac_set_timeing(phy);
 
 	mt7921_mac_reset_counters(phy);
 	phy->noise = 0;
@@ -497,7 +463,7 @@ out:
 
 	mt76_worker_schedule(&dev->mt76.tx_worker);
 	ieee80211_queue_delayed_work(phy->mt76->hw, &phy->mt76->mac_work,
-				     MT7921_WATCHDOG_TIME);
+				     MT792x_WATCHDOG_TIME);
 
 	return ret;
 }
@@ -631,7 +597,7 @@ void mt7921_set_runtime_pm(struct mt792x_dev *dev)
 static int mt7921_config(struct ieee80211_hw *hw, u32 changed)
 {
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 	int ret = 0;
 
 	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
@@ -662,20 +628,6 @@ out:
 	return ret;
 }
 
-static int
-mt7921_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-	       unsigned int link_id, u16 queue,
-	       const struct ieee80211_tx_queue_params *params)
-{
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-
-	/* no need to update right away, we'll get BSS_CHANGED_QOS */
-	queue = mt76_connac_lmac_mapping(queue);
-	mvif->queue_params[queue] = *params;
-
-	return 0;
-}
-
 static void mt7921_configure_filter(struct ieee80211_hw *hw,
 				    unsigned int changed_flags,
 				    unsigned int *total_flags,
@@ -710,7 +662,7 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 				    struct ieee80211_bss_conf *info,
 				    u64 changed)
 {
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
 	mt792x_mutex_acquire(dev);
@@ -720,7 +672,7 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 
 		if (slottime != phy->slottime) {
 			phy->slottime = slottime;
-			mt7921_mac_set_timing(phy);
+			mt792x_mac_set_timeing(phy);
 		}
 	}
 
@@ -760,7 +712,7 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	int ret, idx;
 
-	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7921_WTBL_STA - 1);
+	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT792x_WTBL_STA - 1);
 	if (idx < 0)
 		return -ENOSPC;
 
@@ -851,60 +803,6 @@ void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 }
 EXPORT_SYMBOL_GPL(mt7921_mac_sta_remove);
 
-void mt7921_tx_worker(struct mt76_worker *w)
-{
-	struct mt792x_dev *dev = container_of(w, struct mt792x_dev,
-					      mt76.tx_worker);
-
-	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
-		queue_work(dev->mt76.wq, &dev->pm.wake_work);
-		return;
-	}
-
-	mt76_txq_schedule_all(&dev->mphy);
-	mt76_connac_pm_unref(&dev->mphy, &dev->pm);
-}
-
-static void mt7921_tx(struct ieee80211_hw *hw,
-		      struct ieee80211_tx_control *control,
-		      struct sk_buff *skb)
-{
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	struct mt76_phy *mphy = hw->priv;
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_vif *vif = info->control.vif;
-	struct mt76_wcid *wcid = &dev->mt76.global_wcid;
-	int qid;
-
-	if (control->sta) {
-		struct mt792x_sta *sta;
-
-		sta = (struct mt792x_sta *)control->sta->drv_priv;
-		wcid = &sta->wcid;
-	}
-
-	if (vif && !control->sta) {
-		struct mt792x_vif *mvif;
-
-		mvif = (struct mt792x_vif *)vif->drv_priv;
-		wcid = &mvif->sta.wcid;
-	}
-
-	if (mt76_connac_pm_ref(mphy, &dev->pm)) {
-		mt76_tx(mphy, control->sta, wcid, skb);
-		mt76_connac_pm_unref(mphy, &dev->pm);
-		return;
-	}
-
-	qid = skb_get_queue_mapping(skb);
-	if (qid >= MT_TXQ_PSD) {
-		qid = IEEE80211_AC_BE;
-		skb_set_queue_mapping(skb, qid);
-	}
-
-	mt76_connac_pm_queue_skb(hw, &dev->pm, wcid, skb);
-}
-
 static int mt7921_set_rts_threshold(struct ieee80211_hw *hw, u32 val)
 {
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
@@ -990,277 +888,6 @@ static int mt7921_sta_state(struct ieee80211_hw *hw,
 	return mt76_sta_state(hw, vif, sta, old_state, new_state);
 }
 
-static int
-mt7921_get_stats(struct ieee80211_hw *hw,
-		 struct ieee80211_low_level_stats *stats)
-{
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt76_mib_stats *mib = &phy->mib;
-
-	mt792x_mutex_acquire(phy->dev);
-
-	stats->dot11RTSSuccessCount = mib->rts_cnt;
-	stats->dot11RTSFailureCount = mib->rts_retries_cnt;
-	stats->dot11FCSErrorCount = mib->fcs_err_cnt;
-	stats->dot11ACKFailureCount = mib->ack_fail_cnt;
-
-	mt792x_mutex_release(phy->dev);
-
-	return 0;
-}
-
-static const char mt7921_gstrings_stats[][ETH_GSTRING_LEN] = {
-	/* tx counters */
-	"tx_ampdu_cnt",
-	"tx_mpdu_attempts",
-	"tx_mpdu_success",
-	"tx_pkt_ebf_cnt",
-	"tx_pkt_ibf_cnt",
-	"tx_ampdu_len:0-1",
-	"tx_ampdu_len:2-10",
-	"tx_ampdu_len:11-19",
-	"tx_ampdu_len:20-28",
-	"tx_ampdu_len:29-37",
-	"tx_ampdu_len:38-46",
-	"tx_ampdu_len:47-55",
-	"tx_ampdu_len:56-79",
-	"tx_ampdu_len:80-103",
-	"tx_ampdu_len:104-127",
-	"tx_ampdu_len:128-151",
-	"tx_ampdu_len:152-175",
-	"tx_ampdu_len:176-199",
-	"tx_ampdu_len:200-223",
-	"tx_ampdu_len:224-247",
-	"ba_miss_count",
-	"tx_beamformer_ppdu_iBF",
-	"tx_beamformer_ppdu_eBF",
-	"tx_beamformer_rx_feedback_all",
-	"tx_beamformer_rx_feedback_he",
-	"tx_beamformer_rx_feedback_vht",
-	"tx_beamformer_rx_feedback_ht",
-	"tx_msdu_pack_1",
-	"tx_msdu_pack_2",
-	"tx_msdu_pack_3",
-	"tx_msdu_pack_4",
-	"tx_msdu_pack_5",
-	"tx_msdu_pack_6",
-	"tx_msdu_pack_7",
-	"tx_msdu_pack_8",
-	/* rx counters */
-	"rx_mpdu_cnt",
-	"rx_ampdu_cnt",
-	"rx_ampdu_bytes_cnt",
-	"rx_ba_cnt",
-	/* per vif counters */
-	"v_tx_mode_cck",
-	"v_tx_mode_ofdm",
-	"v_tx_mode_ht",
-	"v_tx_mode_ht_gf",
-	"v_tx_mode_vht",
-	"v_tx_mode_he_su",
-	"v_tx_mode_he_ext_su",
-	"v_tx_mode_he_tb",
-	"v_tx_mode_he_mu",
-	"v_tx_bw_20",
-	"v_tx_bw_40",
-	"v_tx_bw_80",
-	"v_tx_bw_160",
-	"v_tx_mcs_0",
-	"v_tx_mcs_1",
-	"v_tx_mcs_2",
-	"v_tx_mcs_3",
-	"v_tx_mcs_4",
-	"v_tx_mcs_5",
-	"v_tx_mcs_6",
-	"v_tx_mcs_7",
-	"v_tx_mcs_8",
-	"v_tx_mcs_9",
-	"v_tx_mcs_10",
-	"v_tx_mcs_11",
-	"v_tx_nss_1",
-	"v_tx_nss_2",
-	"v_tx_nss_3",
-	"v_tx_nss_4",
-};
-
-static void
-mt7921_get_et_strings(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		      u32 sset, u8 *data)
-{
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-
-	if (sset != ETH_SS_STATS)
-		return;
-
-	memcpy(data, *mt7921_gstrings_stats, sizeof(mt7921_gstrings_stats));
-
-	if (mt76_is_sdio(&dev->mt76))
-		return;
-
-	data += sizeof(mt7921_gstrings_stats);
-	page_pool_ethtool_stats_get_strings(data);
-}
-
-static int
-mt7921_get_et_sset_count(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			 int sset)
-{
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-
-	if (sset != ETH_SS_STATS)
-		return 0;
-
-	if (mt76_is_sdio(&dev->mt76))
-		return ARRAY_SIZE(mt7921_gstrings_stats);
-
-	return ARRAY_SIZE(mt7921_gstrings_stats) +
-	       page_pool_ethtool_stats_get_count();
-}
-
-static void
-mt7921_ethtool_worker(void *wi_data, struct ieee80211_sta *sta)
-{
-	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
-	struct mt76_ethtool_worker_info *wi = wi_data;
-
-	if (msta->vif->mt76.idx != wi->idx)
-		return;
-
-	mt76_ethtool_worker(wi, &msta->wcid.stats, false);
-}
-
-static
-void mt7921_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			 struct ethtool_stats *stats, u64 *data)
-{
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	int stats_size = ARRAY_SIZE(mt7921_gstrings_stats);
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt792x_dev *dev = phy->dev;
-	struct mt76_mib_stats *mib = &phy->mib;
-	struct mt76_ethtool_worker_info wi = {
-		.data = data,
-		.idx = mvif->mt76.idx,
-	};
-	int i, ei = 0;
-
-	mt792x_mutex_acquire(dev);
-
-	mt7921_mac_update_mib_stats(phy);
-
-	data[ei++] = mib->tx_ampdu_cnt;
-	data[ei++] = mib->tx_mpdu_attempts_cnt;
-	data[ei++] = mib->tx_mpdu_success_cnt;
-	data[ei++] = mib->tx_pkt_ebf_cnt;
-	data[ei++] = mib->tx_pkt_ibf_cnt;
-
-	/* Tx ampdu stat */
-	for (i = 0; i < 15; i++)
-		data[ei++] = phy->mt76->aggr_stats[i];
-
-	data[ei++] = phy->mib.ba_miss_cnt;
-
-	/* Tx Beamformer monitor */
-	data[ei++] = mib->tx_bf_ibf_ppdu_cnt;
-	data[ei++] = mib->tx_bf_ebf_ppdu_cnt;
-
-	/* Tx Beamformer Rx feedback monitor */
-	data[ei++] = mib->tx_bf_rx_fb_all_cnt;
-	data[ei++] = mib->tx_bf_rx_fb_he_cnt;
-	data[ei++] = mib->tx_bf_rx_fb_vht_cnt;
-	data[ei++] = mib->tx_bf_rx_fb_ht_cnt;
-
-	/* Tx amsdu info (pack-count histogram) */
-	for (i = 0; i < ARRAY_SIZE(mib->tx_amsdu); i++)
-		data[ei++] = mib->tx_amsdu[i];
-
-	/* rx counters */
-	data[ei++] = mib->rx_mpdu_cnt;
-	data[ei++] = mib->rx_ampdu_cnt;
-	data[ei++] = mib->rx_ampdu_bytes_cnt;
-	data[ei++] = mib->rx_ba_cnt;
-
-	/* Add values for all stations owned by this vif */
-	wi.initial_stat_idx = ei;
-	ieee80211_iterate_stations_atomic(hw, mt7921_ethtool_worker, &wi);
-
-	mt792x_mutex_release(dev);
-
-	if (!wi.sta_count)
-		return;
-
-	ei += wi.worker_stat_count;
-
-	if (!mt76_is_sdio(&dev->mt76)) {
-		mt76_ethtool_page_pool_stats(&dev->mt76, &data[ei], &ei);
-		stats_size += page_pool_ethtool_stats_get_count();
-	}
-
-	if (ei != stats_size)
-		dev_err(dev->mt76.dev, "ei: %d  SSTATS_LEN: %d", ei, stats_size);
-}
-
-static u64
-mt7921_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
-{
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	u8 omac_idx = mvif->mt76.omac_idx;
-	union {
-		u64 t64;
-		u32 t32[2];
-	} tsf;
-	u16 n;
-
-	mt792x_mutex_acquire(dev);
-
-	n = omac_idx > HW_BSSID_MAX ? HW_BSSID_0 : omac_idx;
-	/* TSF software read */
-	mt76_set(dev, MT_LPON_TCR(0, n), MT_LPON_TCR_SW_MODE);
-	tsf.t32[0] = mt76_rr(dev, MT_LPON_UTTR0(0));
-	tsf.t32[1] = mt76_rr(dev, MT_LPON_UTTR1(0));
-
-	mt792x_mutex_release(dev);
-
-	return tsf.t64;
-}
-
-static void
-mt7921_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-	       u64 timestamp)
-{
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	u8 omac_idx = mvif->mt76.omac_idx;
-	union {
-		u64 t64;
-		u32 t32[2];
-	} tsf = { .t64 = timestamp, };
-	u16 n;
-
-	mt792x_mutex_acquire(dev);
-
-	n = omac_idx > HW_BSSID_MAX ? HW_BSSID_0 : omac_idx;
-	mt76_wr(dev, MT_LPON_UTTR0(0), tsf.t32[0]);
-	mt76_wr(dev, MT_LPON_UTTR1(0), tsf.t32[1]);
-	/* TSF software overwrite */
-	mt76_set(dev, MT_LPON_TCR(0, n), MT_LPON_TCR_SW_WRITE);
-
-	mt792x_mutex_release(dev);
-}
-
-static void
-mt7921_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class)
-{
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
-	struct mt792x_dev *dev = phy->dev;
-
-	mt792x_mutex_acquire(dev);
-	phy->coverage_class = max_t(s16, coverage_class, 0);
-	mt7921_mac_set_timing(phy);
-	mt792x_mutex_release(dev);
-}
-
 void mt7921_scan_work(struct work_struct *work)
 {
 	struct mt792x_phy *phy;
@@ -1360,7 +987,7 @@ static int
 mt7921_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 {
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 	int max_nss = hweight8(hw->wiphy->available_antennas_tx);
 
 	if (!tx_ant || tx_ant != rx_ant || ffs(tx_ant) > max_nss)
@@ -1382,49 +1009,12 @@ mt7921_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 	return 0;
 }
 
-static void mt7921_sta_statistics(struct ieee80211_hw *hw,
-				  struct ieee80211_vif *vif,
-				  struct ieee80211_sta *sta,
-				  struct station_info *sinfo)
-{
-	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
-	struct rate_info *txrate = &msta->wcid.rate;
-
-	if (!txrate->legacy && !txrate->flags)
-		return;
-
-	if (txrate->legacy) {
-		sinfo->txrate.legacy = txrate->legacy;
-	} else {
-		sinfo->txrate.mcs = txrate->mcs;
-		sinfo->txrate.nss = txrate->nss;
-		sinfo->txrate.bw = txrate->bw;
-		sinfo->txrate.he_gi = txrate->he_gi;
-		sinfo->txrate.he_dcm = txrate->he_dcm;
-		sinfo->txrate.he_ru_alloc = txrate->he_ru_alloc;
-	}
-	sinfo->tx_failed = msta->wcid.stats.tx_failed;
-	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
-
-	sinfo->tx_retries = msta->wcid.stats.tx_retries;
-	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES);
-
-	sinfo->txrate.flags = txrate->flags;
-	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
-
-	sinfo->ack_signal = (s8)msta->ack_signal;
-	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL);
-
-	sinfo->avg_ack_signal = -(s8)ewma_avg_signal_read(&msta->avg_ack_signal);
-	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG);
-}
-
 #ifdef CONFIG_PM
 static int mt7921_suspend(struct ieee80211_hw *hw,
 			  struct cfg80211_wowlan *wowlan)
 {
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 
 	cancel_delayed_work_sync(&phy->scan_work);
 	cancel_delayed_work_sync(&phy->mt76->mac_work);
@@ -1448,7 +1038,7 @@ static int mt7921_suspend(struct ieee80211_hw *hw,
 static int mt7921_resume(struct ieee80211_hw *hw)
 {
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 
 	mt792x_mutex_acquire(dev);
 
@@ -1459,21 +1049,13 @@ static int mt7921_resume(struct ieee80211_hw *hw)
 					    &dev->mphy);
 
 	ieee80211_queue_delayed_work(hw, &phy->mt76->mac_work,
-				     MT7921_WATCHDOG_TIME);
+				     MT792x_WATCHDOG_TIME);
 
 	mt792x_mutex_release(dev);
 
 	return 0;
 }
 
-static void mt7921_set_wakeup(struct ieee80211_hw *hw, bool enabled)
-{
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	struct mt76_dev *mdev = &dev->mt76;
-
-	device_set_wakeup_enable(mdev->dev, enabled);
-}
-
 static void mt7921_set_rekey_data(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
 				  struct cfg80211_gtk_rekey_data *data)
@@ -1486,15 +1068,6 @@ static void mt7921_set_rekey_data(struct ieee80211_hw *hw,
 }
 #endif /* CONFIG_PM */
 
-static void mt7921_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			 u32 queues, bool drop)
-{
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-
-	wait_event_timeout(dev->mt76.tx_wait, !mt76_has_tx_pending(&dev->mphy),
-			   HZ / 2);
-}
-
 static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw,
 					 struct ieee80211_vif *vif,
 					 struct ieee80211_sta *sta,
@@ -1588,7 +1161,7 @@ int mt7921_set_tx_sar_pwr(struct ieee80211_hw *hw,
 			return err;
 	}
 
-	mt7921_init_acpi_sar_power(mt7921_hw_phy(hw), !sar);
+	mt7921_init_acpi_sar_power(mt792x_hw_phy(hw), !sar);
 
 	err = mt76_connac_mcu_set_rate_txpower(mphy);
 
@@ -1631,7 +1204,7 @@ mt7921_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		struct ieee80211_bss_conf *link_conf)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	int err;
 
@@ -1659,7 +1232,7 @@ mt7921_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       struct ieee80211_bss_conf *link_conf)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	int err;
 
@@ -1709,7 +1282,7 @@ mt7921_change_chanctx(struct ieee80211_hw *hw,
 		      struct ieee80211_chanctx_conf *ctx,
 		      u32 changed)
 {
-	struct mt792x_phy *phy = mt7921_hw_phy(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 
 	mt792x_mutex_acquire(phy->dev);
 	ieee80211_iterate_active_interfaces(phy->mt76->hw,
@@ -1718,36 +1291,6 @@ mt7921_change_chanctx(struct ieee80211_hw *hw,
 	mt792x_mutex_release(phy->dev);
 }
 
-static int
-mt7921_assign_vif_chanctx(struct ieee80211_hw *hw,
-			  struct ieee80211_vif *vif,
-			  struct ieee80211_bss_conf *link_conf,
-			  struct ieee80211_chanctx_conf *ctx)
-{
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-
-	mutex_lock(&dev->mt76.mutex);
-	mvif->ctx = ctx;
-	mutex_unlock(&dev->mt76.mutex);
-
-	return 0;
-}
-
-static void
-mt7921_unassign_vif_chanctx(struct ieee80211_hw *hw,
-			    struct ieee80211_vif *vif,
-			    struct ieee80211_bss_conf *link_conf,
-			    struct ieee80211_chanctx_conf *ctx)
-{
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-
-	mutex_lock(&dev->mt76.mutex);
-	mvif->ctx = NULL;
-	mutex_unlock(&dev->mt76.mutex);
-}
-
 static void mt7921_mgd_prepare_tx(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
 				  struct ieee80211_prep_tx_info *info)
@@ -1773,13 +1316,13 @@ static void mt7921_mgd_complete_tx(struct ieee80211_hw *hw,
 }
 
 const struct ieee80211_ops mt7921_ops = {
-	.tx = mt7921_tx,
+	.tx = mt792x_tx,
 	.start = mt7921_start,
 	.stop = mt7921_stop,
 	.add_interface = mt7921_add_interface,
-	.remove_interface = mt7921_remove_interface,
+	.remove_interface = mt792x_remove_interface,
 	.config = mt7921_config,
-	.conf_tx = mt7921_conf_tx,
+	.conf_tx = mt792x_conf_tx,
 	.configure_filter = mt7921_configure_filter,
 	.bss_info_changed = mt7921_bss_info_changed,
 	.start_ap = mt7921_start_ap,
@@ -1797,19 +1340,19 @@ const struct ieee80211_ops mt7921_ops = {
 	.release_buffered_frames = mt76_release_buffered_frames,
 	.channel_switch_beacon = mt7921_channel_switch_beacon,
 	.get_txpower = mt76_get_txpower,
-	.get_stats = mt7921_get_stats,
-	.get_et_sset_count = mt7921_get_et_sset_count,
-	.get_et_strings = mt7921_get_et_strings,
-	.get_et_stats = mt7921_get_et_stats,
-	.get_tsf = mt7921_get_tsf,
-	.set_tsf = mt7921_set_tsf,
+	.get_stats = mt792x_get_stats,
+	.get_et_sset_count = mt792x_get_et_sset_count,
+	.get_et_strings = mt792x_get_et_strings,
+	.get_et_stats = mt792x_get_et_stats,
+	.get_tsf = mt792x_get_tsf,
+	.set_tsf = mt792x_set_tsf,
 	.get_survey = mt76_get_survey,
 	.get_antenna = mt76_get_antenna,
 	.set_antenna = mt7921_set_antenna,
-	.set_coverage_class = mt7921_set_coverage_class,
+	.set_coverage_class = mt792x_set_coverage_class,
 	.hw_scan = mt7921_hw_scan,
 	.cancel_hw_scan = mt7921_cancel_hw_scan,
-	.sta_statistics = mt7921_sta_statistics,
+	.sta_statistics = mt792x_sta_statistics,
 	.sched_scan_start = mt7921_start_sched_scan,
 	.sched_scan_stop = mt7921_stop_sched_scan,
 	CFG80211_TESTMODE_CMD(mt7921_testmode_cmd)
@@ -1817,18 +1360,18 @@ const struct ieee80211_ops mt7921_ops = {
 #ifdef CONFIG_PM
 	.suspend = mt7921_suspend,
 	.resume = mt7921_resume,
-	.set_wakeup = mt7921_set_wakeup,
+	.set_wakeup = mt792x_set_wakeup,
 	.set_rekey_data = mt7921_set_rekey_data,
 #endif /* CONFIG_PM */
-	.flush = mt7921_flush,
+	.flush = mt792x_flush,
 	.set_sar_specs = mt7921_set_sar_specs,
 	.remain_on_channel = mt7921_remain_on_channel,
 	.cancel_remain_on_channel = mt7921_cancel_remain_on_channel,
 	.add_chanctx = mt7921_add_chanctx,
 	.remove_chanctx = mt7921_remove_chanctx,
 	.change_chanctx = mt7921_change_chanctx,
-	.assign_vif_chanctx = mt7921_assign_vif_chanctx,
-	.unassign_vif_chanctx = mt7921_unassign_vif_chanctx,
+	.assign_vif_chanctx = mt792x_assign_vif_chanctx,
+	.unassign_vif_chanctx = mt792x_unassign_vif_chanctx,
 	.mgd_prepare_tx = mt7921_mgd_prepare_tx,
 	.mgd_complete_tx = mt7921_mgd_complete_tx,
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index db3394ba4e45f..3dd9ff5e466b9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -4,9 +4,9 @@
 #include <linux/fs.h>
 #include <linux/firmware.h>
 #include "mt7921.h"
-#include "mt7921_trace.h"
 #include "mcu.h"
 #include "../mt76_connac2_mac.h"
+#include "../mt792x_trace.h"
 
 #define MT_STA_BFER			BIT(0)
 #define MT_STA_BFEE			BIT(1)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index ad18fcc4a7b07..4722952bb846d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -8,15 +8,8 @@
 #include "regs.h"
 #include "acpi_sar.h"
 
-#define MT7921_MAX_INTERFACES		4
-#define MT7921_WTBL_SIZE		20
-#define MT7921_WTBL_RESERVED		(MT7921_WTBL_SIZE - 1)
-#define MT7921_WTBL_STA			(MT7921_WTBL_RESERVED - \
-					 MT7921_MAX_INTERFACES)
-
 #define MT7921_PM_TIMEOUT		(HZ / 12)
 #define MT7921_HW_SCAN_TIMEOUT		(HZ / 10)
-#define MT7921_WATCHDOG_TIME		(HZ / 4)
 
 #define MT7921_TX_RING_SIZE		2048
 #define MT7921_TX_MCU_RING_SIZE		256
@@ -43,9 +36,6 @@
 
 #define MT7921_EEPROM_BLOCK_SIZE	16
 
-#define MT7921_CFEND_RATE_DEFAULT	0x49	/* OFDM 24M */
-#define MT7921_CFEND_RATE_11B		0x03	/* 11B LP, 11M */
-
 #define MT7921_SKU_RATE_NUM		161
 #define MT7921_SKU_MAX_DELTA_IDX	MT7921_SKU_RATE_NUM
 #define MT7921_SKU_TABLE_SIZE		(MT7921_SKU_RATE_NUM + 1)
@@ -208,14 +198,6 @@ struct mt7921_txpwr {
 	} data[TXPWR_MAX_NUM];
 };
 
-static inline struct mt792x_phy *
-mt7921_hw_phy(struct ieee80211_hw *hw)
-{
-	struct mt76_phy *phy = hw->priv;
-
-	return phy->priv;
-}
-
 extern const struct ieee80211_ops mt7921_ops;
 
 u32 mt7921_reg_map(struct mt792x_dev *dev, u32 addr);
@@ -300,25 +282,21 @@ mt7921_skb_add_usb_sdio_hdr(struct mt792x_dev *dev, struct sk_buff *skb,
 
 void mt7921_stop(struct ieee80211_hw *hw);
 int mt7921_mac_init(struct mt792x_dev *dev);
-bool mt7921_mac_wtbl_update(struct mt792x_dev *dev, int idx, u32 mask);
 void mt7921_mac_reset_counters(struct mt792x_phy *phy);
-void mt7921_mac_set_timing(struct mt792x_phy *phy);
+bool mt7921_mac_wtbl_update(struct mt792x_dev *dev, int idx, u32 mask);
 int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
 void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			  struct ieee80211_sta *sta);
 void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta);
-void mt7921_mac_work(struct work_struct *work);
 void mt7921_mac_reset_work(struct work_struct *work);
-void mt7921_mac_update_mib_stats(struct mt792x_phy *phy);
 void mt7921_reset(struct mt76_dev *mdev);
 int mt7921e_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			   enum mt76_txq_id qid, struct mt76_wcid *wcid,
 			   struct ieee80211_sta *sta,
 			   struct mt76_tx_info *tx_info);
 
-void mt7921_tx_worker(struct mt76_worker *w);
 bool mt7921_rx_check(struct mt76_dev *mdev, void *data, int len);
 void mt7921_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			 struct sk_buff *skb, u32 *info);
@@ -338,7 +316,6 @@ int mt7921_mcu_uni_rx_ba(struct mt792x_dev *dev,
 			 bool enable);
 void mt7921_scan_work(struct work_struct *work);
 void mt7921_roc_work(struct work_struct *work);
-void mt7921_roc_timer(struct timer_list *timer);
 int mt7921_mcu_uni_bss_ps(struct mt792x_dev *dev, struct ieee80211_vif *vif);
 int mt7921_mcu_drv_pmctrl(struct mt792x_dev *dev);
 int mt7921_mcu_fw_pmctrl(struct mt792x_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
index fefc105395862..c5ca1b931584d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
@@ -93,4 +93,8 @@
 #define MT_WTBLON_TOP_WDUCR		MT_WTBLON_TOP(0x200)
 #define MT_WTBLON_TOP_WDUCR_GROUP	GENMASK(2, 0)
 
+#define MT_WTBL_UPDATE			MT_WTBLON_TOP(0x230)
+#define MT_WTBL_UPDATE_WLAN_IDX		GENMASK(9, 0)
+#define MT_WTBL_UPDATE_ADM_COUNT_CLEAR	BIT(12)
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c
index 360de6a0de2be..310eeca024ad8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c
@@ -23,7 +23,7 @@ mt7921s_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 
 	/* We just return in case firmware assertion to avoid blocking the
 	 * common workqueue to run, for example, the coredump work might be
-	 * blocked by mt7921_mac_work that is excuting register access via sdio
+	 * blocked by mt792x_mac_work that is excuting register access via sdio
 	 * bus.
 	 */
 	if (dev->fw_assert)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/trace.c b/drivers/net/wireless/mediatek/mt76/mt7921/trace.c
deleted file mode 100644
index 4dc3c7b89ebd5..0000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt7921/trace.c
+++ /dev/null
@@ -1,12 +0,0 @@
-// SPDX-License-Identifier: ISC
-/*
- * Copyright (C) 2021 Lorenzo Bianconi <lorenzo@kernel.org>
- */
-
-#include <linux/module.h>
-
-#ifndef __CHECKER__
-#define CREATE_TRACE_POINTS
-#include "mt7921_trace.h"
-
-#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 9c724bc156afa..83236a6c300e4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -9,6 +9,19 @@
 
 #include "mt76_connac_mcu.h"
 
+#define MT792x_MAX_INTERFACES	4
+#define MT792x_WTBL_SIZE	20
+#define MT792x_WTBL_RESERVED	(MT792x_WTBL_SIZE - 1)
+#define MT792x_WTBL_STA		(MT792x_WTBL_RESERVED - MT792x_MAX_INTERFACES)
+
+#define MT792x_CFEND_RATE_DEFAULT	0x49	/* OFDM 24M */
+#define MT792x_CFEND_RATE_11B		0x03	/* 11B LP, 11M */
+
+/* NOTE: used to map mt76_rates. idx may change if firmware expands table */
+#define MT792x_BASIC_RATES_TBL	11
+
+#define MT792x_WATCHDOG_TIME	(HZ / 4)
+
 struct mt792x_vif;
 struct mt792x_sta;
 
@@ -134,9 +147,57 @@ mt792x_hw_dev(struct ieee80211_hw *hw)
 	return container_of(phy->dev, struct mt792x_dev, mt76);
 }
 
+static inline struct mt792x_phy *
+mt792x_hw_phy(struct ieee80211_hw *hw)
+{
+	struct mt76_phy *phy = hw->priv;
+
+	return phy->priv;
+}
+
 #define mt792x_mutex_acquire(dev)	\
 	mt76_connac_mutex_acquire(&(dev)->mt76, &(dev)->pm)
 #define mt792x_mutex_release(dev)	\
 	mt76_connac_mutex_release(&(dev)->mt76, &(dev)->pm)
 
+void mt792x_mac_update_mib_stats(struct mt792x_phy *phy);
+void mt792x_mac_set_timeing(struct mt792x_phy *phy);
+void mt792x_mac_work(struct work_struct *work);
+void mt792x_remove_interface(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif);
+void mt792x_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
+	       struct sk_buff *skb);
+int mt792x_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   unsigned int link_id, u16 queue,
+		   const struct ieee80211_tx_queue_params *params);
+int mt792x_get_stats(struct ieee80211_hw *hw,
+		     struct ieee80211_low_level_stats *stats);
+u64 mt792x_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
+void mt792x_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		    u64 timestamp);
+void mt792x_tx_worker(struct mt76_worker *w);
+void mt792x_roc_timer(struct timer_list *timer);
+void mt792x_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		  u32 queues, bool drop);
+int mt792x_assign_vif_chanctx(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_bss_conf *link_conf,
+			      struct ieee80211_chanctx_conf *ctx);
+void mt792x_unassign_vif_chanctx(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif,
+				 struct ieee80211_bss_conf *link_conf,
+				 struct ieee80211_chanctx_conf *ctx);
+void mt792x_set_wakeup(struct ieee80211_hw *hw, bool enabled);
+void mt792x_get_et_strings(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			   u32 sset, u8 *data);
+int mt792x_get_et_sset_count(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			     int sset);
+void mt792x_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 struct ethtool_stats *stats, u64 *data);
+void mt792x_sta_statistics(struct ieee80211_hw *hw,
+			   struct ieee80211_vif *vif,
+			   struct ieee80211_sta *sta,
+			   struct station_info *sinfo);
+void mt792x_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class);
+
 #endif /* __MT7925_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
new file mode 100644
index 0000000000000..fa648b1333979
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -0,0 +1,469 @@
+// SPDX-License-Identifier: ISC
+/* Copyright (C) 2023 MediaTek Inc. */
+
+#include <linux/module.h>
+
+#include "mt792x.h"
+#include "mt792x_regs.h"
+
+void mt792x_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
+	       struct sk_buff *skb)
+{
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+	struct mt76_phy *mphy = hw->priv;
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_vif *vif = info->control.vif;
+	struct mt76_wcid *wcid = &dev->mt76.global_wcid;
+	int qid;
+
+	if (control->sta) {
+		struct mt792x_sta *sta;
+
+		sta = (struct mt792x_sta *)control->sta->drv_priv;
+		wcid = &sta->wcid;
+	}
+
+	if (vif && !control->sta) {
+		struct mt792x_vif *mvif;
+
+		mvif = (struct mt792x_vif *)vif->drv_priv;
+		wcid = &mvif->sta.wcid;
+	}
+
+	if (mt76_connac_pm_ref(mphy, &dev->pm)) {
+		mt76_tx(mphy, control->sta, wcid, skb);
+		mt76_connac_pm_unref(mphy, &dev->pm);
+		return;
+	}
+
+	qid = skb_get_queue_mapping(skb);
+	if (qid >= MT_TXQ_PSD) {
+		qid = IEEE80211_AC_BE;
+		skb_set_queue_mapping(skb, qid);
+	}
+
+	mt76_connac_pm_queue_skb(hw, &dev->pm, wcid, skb);
+}
+EXPORT_SYMBOL_GPL(mt792x_tx);
+
+void mt792x_remove_interface(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif)
+{
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+	struct mt792x_sta *msta = &mvif->sta;
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
+	int idx = msta->wcid.idx;
+
+	mt792x_mutex_acquire(dev);
+	mt76_connac_free_pending_tx_skbs(&dev->pm, &msta->wcid);
+	mt76_connac_mcu_uni_add_dev(&dev->mphy, vif, &mvif->sta.wcid, false);
+
+	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
+
+	dev->mt76.vif_mask &= ~BIT_ULL(mvif->mt76.idx);
+	phy->omac_mask &= ~BIT_ULL(mvif->mt76.omac_idx);
+	mt792x_mutex_release(dev);
+
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
+	if (!list_empty(&msta->wcid.poll_list))
+		list_del_init(&msta->wcid.poll_list);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
+
+	mt76_packet_id_flush(&dev->mt76, &msta->wcid);
+}
+EXPORT_SYMBOL_GPL(mt792x_remove_interface);
+
+int mt792x_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   unsigned int link_id, u16 queue,
+		   const struct ieee80211_tx_queue_params *params)
+{
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+
+	/* no need to update right away, we'll get BSS_CHANGED_QOS */
+	queue = mt76_connac_lmac_mapping(queue);
+	mvif->queue_params[queue] = *params;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_conf_tx);
+
+int mt792x_get_stats(struct ieee80211_hw *hw,
+		     struct ieee80211_low_level_stats *stats)
+{
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
+	struct mt76_mib_stats *mib = &phy->mib;
+
+	mt792x_mutex_acquire(phy->dev);
+
+	stats->dot11RTSSuccessCount = mib->rts_cnt;
+	stats->dot11RTSFailureCount = mib->rts_retries_cnt;
+	stats->dot11FCSErrorCount = mib->fcs_err_cnt;
+	stats->dot11ACKFailureCount = mib->ack_fail_cnt;
+
+	mt792x_mutex_release(phy->dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_get_stats);
+
+u64 mt792x_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
+{
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+	u8 omac_idx = mvif->mt76.omac_idx;
+	union {
+		u64 t64;
+		u32 t32[2];
+	} tsf;
+	u16 n;
+
+	mt792x_mutex_acquire(dev);
+
+	n = omac_idx > HW_BSSID_MAX ? HW_BSSID_0 : omac_idx;
+	/* TSF software read */
+	mt76_set(dev, MT_LPON_TCR(0, n), MT_LPON_TCR_SW_MODE);
+	tsf.t32[0] = mt76_rr(dev, MT_LPON_UTTR0(0));
+	tsf.t32[1] = mt76_rr(dev, MT_LPON_UTTR1(0));
+
+	mt792x_mutex_release(dev);
+
+	return tsf.t64;
+}
+EXPORT_SYMBOL_GPL(mt792x_get_tsf);
+
+void mt792x_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		    u64 timestamp)
+{
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+	u8 omac_idx = mvif->mt76.omac_idx;
+	union {
+		u64 t64;
+		u32 t32[2];
+	} tsf = { .t64 = timestamp, };
+	u16 n;
+
+	mt792x_mutex_acquire(dev);
+
+	n = omac_idx > HW_BSSID_MAX ? HW_BSSID_0 : omac_idx;
+	mt76_wr(dev, MT_LPON_UTTR0(0), tsf.t32[0]);
+	mt76_wr(dev, MT_LPON_UTTR1(0), tsf.t32[1]);
+	/* TSF software overwrite */
+	mt76_set(dev, MT_LPON_TCR(0, n), MT_LPON_TCR_SW_WRITE);
+
+	mt792x_mutex_release(dev);
+}
+EXPORT_SYMBOL_GPL(mt792x_set_tsf);
+
+void mt792x_tx_worker(struct mt76_worker *w)
+{
+	struct mt792x_dev *dev = container_of(w, struct mt792x_dev,
+					      mt76.tx_worker);
+
+	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
+		queue_work(dev->mt76.wq, &dev->pm.wake_work);
+		return;
+	}
+
+	mt76_txq_schedule_all(&dev->mphy);
+	mt76_connac_pm_unref(&dev->mphy, &dev->pm);
+}
+EXPORT_SYMBOL_GPL(mt792x_tx_worker);
+
+void mt792x_roc_timer(struct timer_list *timer)
+{
+	struct mt792x_phy *phy = from_timer(phy, timer, roc_timer);
+
+	ieee80211_queue_work(phy->mt76->hw, &phy->roc_work);
+}
+EXPORT_SYMBOL_GPL(mt792x_roc_timer);
+
+void mt792x_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		  u32 queues, bool drop)
+{
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+
+	wait_event_timeout(dev->mt76.tx_wait,
+			   !mt76_has_tx_pending(&dev->mphy), HZ / 2);
+}
+EXPORT_SYMBOL_GPL(mt792x_flush);
+
+int mt792x_assign_vif_chanctx(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_bss_conf *link_conf,
+			      struct ieee80211_chanctx_conf *ctx)
+{
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+
+	mutex_lock(&dev->mt76.mutex);
+	mvif->ctx = ctx;
+	mutex_unlock(&dev->mt76.mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_assign_vif_chanctx);
+
+void mt792x_unassign_vif_chanctx(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif,
+				 struct ieee80211_bss_conf *link_conf,
+				 struct ieee80211_chanctx_conf *ctx)
+{
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+
+	mutex_lock(&dev->mt76.mutex);
+	mvif->ctx = NULL;
+	mutex_unlock(&dev->mt76.mutex);
+}
+EXPORT_SYMBOL_GPL(mt792x_unassign_vif_chanctx);
+
+void mt792x_set_wakeup(struct ieee80211_hw *hw, bool enabled)
+{
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+	struct mt76_dev *mdev = &dev->mt76;
+
+	device_set_wakeup_enable(mdev->dev, enabled);
+}
+EXPORT_SYMBOL_GPL(mt792x_set_wakeup);
+
+static const char mt792x_gstrings_stats[][ETH_GSTRING_LEN] = {
+	/* tx counters */
+	"tx_ampdu_cnt",
+	"tx_mpdu_attempts",
+	"tx_mpdu_success",
+	"tx_pkt_ebf_cnt",
+	"tx_pkt_ibf_cnt",
+	"tx_ampdu_len:0-1",
+	"tx_ampdu_len:2-10",
+	"tx_ampdu_len:11-19",
+	"tx_ampdu_len:20-28",
+	"tx_ampdu_len:29-37",
+	"tx_ampdu_len:38-46",
+	"tx_ampdu_len:47-55",
+	"tx_ampdu_len:56-79",
+	"tx_ampdu_len:80-103",
+	"tx_ampdu_len:104-127",
+	"tx_ampdu_len:128-151",
+	"tx_ampdu_len:152-175",
+	"tx_ampdu_len:176-199",
+	"tx_ampdu_len:200-223",
+	"tx_ampdu_len:224-247",
+	"ba_miss_count",
+	"tx_beamformer_ppdu_iBF",
+	"tx_beamformer_ppdu_eBF",
+	"tx_beamformer_rx_feedback_all",
+	"tx_beamformer_rx_feedback_he",
+	"tx_beamformer_rx_feedback_vht",
+	"tx_beamformer_rx_feedback_ht",
+	"tx_msdu_pack_1",
+	"tx_msdu_pack_2",
+	"tx_msdu_pack_3",
+	"tx_msdu_pack_4",
+	"tx_msdu_pack_5",
+	"tx_msdu_pack_6",
+	"tx_msdu_pack_7",
+	"tx_msdu_pack_8",
+	/* rx counters */
+	"rx_mpdu_cnt",
+	"rx_ampdu_cnt",
+	"rx_ampdu_bytes_cnt",
+	"rx_ba_cnt",
+	/* per vif counters */
+	"v_tx_mode_cck",
+	"v_tx_mode_ofdm",
+	"v_tx_mode_ht",
+	"v_tx_mode_ht_gf",
+	"v_tx_mode_vht",
+	"v_tx_mode_he_su",
+	"v_tx_mode_he_ext_su",
+	"v_tx_mode_he_tb",
+	"v_tx_mode_he_mu",
+	"v_tx_mode_eht_su",
+	"v_tx_mode_eht_trig",
+	"v_tx_mode_eht_mu",
+	"v_tx_bw_20",
+	"v_tx_bw_40",
+	"v_tx_bw_80",
+	"v_tx_bw_160",
+	"v_tx_mcs_0",
+	"v_tx_mcs_1",
+	"v_tx_mcs_2",
+	"v_tx_mcs_3",
+	"v_tx_mcs_4",
+	"v_tx_mcs_5",
+	"v_tx_mcs_6",
+	"v_tx_mcs_7",
+	"v_tx_mcs_8",
+	"v_tx_mcs_9",
+	"v_tx_mcs_10",
+	"v_tx_mcs_11",
+	"v_tx_mcs_12",
+	"v_tx_mcs_13",
+	"v_tx_nss_1",
+	"v_tx_nss_2",
+	"v_tx_nss_3",
+	"v_tx_nss_4",
+};
+
+void mt792x_get_et_strings(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			   u32 sset, u8 *data)
+{
+	if (sset != ETH_SS_STATS)
+		return;
+
+	memcpy(data, *mt792x_gstrings_stats, sizeof(mt792x_gstrings_stats));
+
+	data += sizeof(mt792x_gstrings_stats);
+	page_pool_ethtool_stats_get_strings(data);
+}
+EXPORT_SYMBOL_GPL(mt792x_get_et_strings);
+
+int mt792x_get_et_sset_count(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			     int sset)
+{
+	if (sset != ETH_SS_STATS)
+		return 0;
+
+	return ARRAY_SIZE(mt792x_gstrings_stats) +
+	       page_pool_ethtool_stats_get_count();
+}
+EXPORT_SYMBOL_GPL(mt792x_get_et_sset_count);
+
+static void
+mt792x_ethtool_worker(void *wi_data, struct ieee80211_sta *sta)
+{
+	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
+	struct mt76_ethtool_worker_info *wi = wi_data;
+
+	if (msta->vif->mt76.idx != wi->idx)
+		return;
+
+	mt76_ethtool_worker(wi, &msta->wcid.stats, true);
+}
+
+void mt792x_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 struct ethtool_stats *stats, u64 *data)
+{
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+	int stats_size = ARRAY_SIZE(mt792x_gstrings_stats);
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
+	struct mt792x_dev *dev = phy->dev;
+	struct mt76_mib_stats *mib = &phy->mib;
+	struct mt76_ethtool_worker_info wi = {
+		.data = data,
+		.idx = mvif->mt76.idx,
+	};
+	int i, ei = 0;
+
+	mt792x_mutex_acquire(dev);
+
+	mt792x_mac_update_mib_stats(phy);
+
+	data[ei++] = mib->tx_ampdu_cnt;
+	data[ei++] = mib->tx_mpdu_attempts_cnt;
+	data[ei++] = mib->tx_mpdu_success_cnt;
+	data[ei++] = mib->tx_pkt_ebf_cnt;
+	data[ei++] = mib->tx_pkt_ibf_cnt;
+
+	/* Tx ampdu stat */
+	for (i = 0; i < 15; i++)
+		data[ei++] = phy->mt76->aggr_stats[i];
+
+	data[ei++] = phy->mib.ba_miss_cnt;
+
+	/* Tx Beamformer monitor */
+	data[ei++] = mib->tx_bf_ibf_ppdu_cnt;
+	data[ei++] = mib->tx_bf_ebf_ppdu_cnt;
+
+	/* Tx Beamformer Rx feedback monitor */
+	data[ei++] = mib->tx_bf_rx_fb_all_cnt;
+	data[ei++] = mib->tx_bf_rx_fb_he_cnt;
+	data[ei++] = mib->tx_bf_rx_fb_vht_cnt;
+	data[ei++] = mib->tx_bf_rx_fb_ht_cnt;
+
+	/* Tx amsdu info (pack-count histogram) */
+	for (i = 0; i < ARRAY_SIZE(mib->tx_amsdu); i++)
+		data[ei++] = mib->tx_amsdu[i];
+
+	/* rx counters */
+	data[ei++] = mib->rx_mpdu_cnt;
+	data[ei++] = mib->rx_ampdu_cnt;
+	data[ei++] = mib->rx_ampdu_bytes_cnt;
+	data[ei++] = mib->rx_ba_cnt;
+
+	/* Add values for all stations owned by this vif */
+	wi.initial_stat_idx = ei;
+	ieee80211_iterate_stations_atomic(hw, mt792x_ethtool_worker, &wi);
+
+	mt792x_mutex_release(dev);
+
+	if (!wi.sta_count)
+		return;
+
+	ei += wi.worker_stat_count;
+
+	mt76_ethtool_page_pool_stats(&dev->mt76, &data[ei], &ei);
+	stats_size += page_pool_ethtool_stats_get_count();
+
+	if (ei != stats_size)
+		dev_err(dev->mt76.dev, "ei: %d  SSTATS_LEN: %d", ei,
+			stats_size);
+}
+EXPORT_SYMBOL_GPL(mt792x_get_et_stats);
+
+void mt792x_sta_statistics(struct ieee80211_hw *hw,
+			   struct ieee80211_vif *vif,
+			   struct ieee80211_sta *sta,
+			   struct station_info *sinfo)
+{
+	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
+	struct rate_info *txrate = &msta->wcid.rate;
+
+	if (!txrate->legacy && !txrate->flags)
+		return;
+
+	if (txrate->legacy) {
+		sinfo->txrate.legacy = txrate->legacy;
+	} else {
+		sinfo->txrate.mcs = txrate->mcs;
+		sinfo->txrate.nss = txrate->nss;
+		sinfo->txrate.bw = txrate->bw;
+		sinfo->txrate.he_gi = txrate->he_gi;
+		sinfo->txrate.he_dcm = txrate->he_dcm;
+		sinfo->txrate.he_ru_alloc = txrate->he_ru_alloc;
+	}
+	sinfo->tx_failed = msta->wcid.stats.tx_failed;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
+
+	sinfo->tx_retries = msta->wcid.stats.tx_retries;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES);
+
+	sinfo->txrate.flags = txrate->flags;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
+
+	sinfo->ack_signal = (s8)msta->ack_signal;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL);
+
+	sinfo->avg_ack_signal = -(s8)ewma_avg_signal_read(&msta->avg_ack_signal);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG);
+}
+EXPORT_SYMBOL_GPL(mt792x_sta_statistics);
+
+void mt792x_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class)
+{
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
+	struct mt792x_dev *dev = phy->dev;
+
+	mt792x_mutex_acquire(dev);
+
+	phy->coverage_class = max_t(s16, coverage_class, 0);
+	mt792x_mac_set_timeing(phy);
+
+	mt792x_mutex_release(dev);
+}
+EXPORT_SYMBOL_GPL(mt792x_set_coverage_class);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
new file mode 100644
index 0000000000000..862cca816aae8
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: ISC
+/* Copyright (C) 2023 MediaTek Inc. */
+
+#include <linux/module.h>
+
+#include "mt792x.h"
+#include "mt792x_regs.h"
+
+void mt792x_mac_work(struct work_struct *work)
+{
+	struct mt792x_phy *phy;
+	struct mt76_phy *mphy;
+
+	mphy = (struct mt76_phy *)container_of(work, struct mt76_phy,
+					       mac_work.work);
+	phy = mphy->priv;
+
+	mt792x_mutex_acquire(phy->dev);
+
+	mt76_update_survey(mphy);
+	if (++mphy->mac_work_count == 2) {
+		mphy->mac_work_count = 0;
+
+		mt792x_mac_update_mib_stats(phy);
+	}
+
+	mt792x_mutex_release(phy->dev);
+
+	mt76_tx_status_check(mphy->dev, false);
+	ieee80211_queue_delayed_work(phy->mt76->hw, &mphy->mac_work,
+				     MT792x_WATCHDOG_TIME);
+}
+EXPORT_SYMBOL_GPL(mt792x_mac_work);
+
+void mt792x_mac_set_timeing(struct mt792x_phy *phy)
+{
+	s16 coverage_class = phy->coverage_class;
+	struct mt792x_dev *dev = phy->dev;
+	u32 val, reg_offset;
+	u32 cck = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, 231) |
+		  FIELD_PREP(MT_TIMEOUT_VAL_CCA, 48);
+	u32 ofdm = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, 60) |
+		   FIELD_PREP(MT_TIMEOUT_VAL_CCA, 28);
+	bool is_2ghz = phy->mt76->chandef.chan->band == NL80211_BAND_2GHZ;
+	int sifs = is_2ghz ? 10 : 16, offset;
+
+	if (!test_bit(MT76_STATE_RUNNING, &phy->mt76->state))
+		return;
+
+	mt76_set(dev, MT_ARB_SCR(0),
+		 MT_ARB_SCR_TX_DISABLE | MT_ARB_SCR_RX_DISABLE);
+	udelay(1);
+
+	offset = 3 * coverage_class;
+	reg_offset = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, offset) |
+		     FIELD_PREP(MT_TIMEOUT_VAL_CCA, offset);
+
+	mt76_wr(dev, MT_TMAC_CDTR(0), cck + reg_offset);
+	mt76_wr(dev, MT_TMAC_ODTR(0), ofdm + reg_offset);
+	mt76_wr(dev, MT_TMAC_ICR0(0),
+		FIELD_PREP(MT_IFS_EIFS, 360) |
+		FIELD_PREP(MT_IFS_RIFS, 2) |
+		FIELD_PREP(MT_IFS_SIFS, sifs) |
+		FIELD_PREP(MT_IFS_SLOT, phy->slottime));
+
+	if (phy->slottime < 20 || !is_2ghz)
+		val = MT792x_CFEND_RATE_DEFAULT;
+	else
+		val = MT792x_CFEND_RATE_11B;
+
+	mt76_rmw_field(dev, MT_AGG_ACR0(0), MT_AGG_ACR_CFEND_RATE, val);
+	mt76_clear(dev, MT_ARB_SCR(0),
+		   MT_ARB_SCR_TX_DISABLE | MT_ARB_SCR_RX_DISABLE);
+}
+EXPORT_SYMBOL_GPL(mt792x_mac_set_timeing);
+
+void mt792x_mac_update_mib_stats(struct mt792x_phy *phy)
+{
+	struct mt76_mib_stats *mib = &phy->mib;
+	struct mt792x_dev *dev = phy->dev;
+	int i, aggr0 = 0, aggr1;
+	u32 val;
+
+	mib->fcs_err_cnt += mt76_get_field(dev, MT_MIB_SDR3(0),
+					   MT_MIB_SDR3_FCS_ERR_MASK);
+	mib->ack_fail_cnt += mt76_get_field(dev, MT_MIB_MB_BSDR3(0),
+					    MT_MIB_ACK_FAIL_COUNT_MASK);
+	mib->ba_miss_cnt += mt76_get_field(dev, MT_MIB_MB_BSDR2(0),
+					   MT_MIB_BA_FAIL_COUNT_MASK);
+	mib->rts_cnt += mt76_get_field(dev, MT_MIB_MB_BSDR0(0),
+				       MT_MIB_RTS_COUNT_MASK);
+	mib->rts_retries_cnt += mt76_get_field(dev, MT_MIB_MB_BSDR1(0),
+					       MT_MIB_RTS_FAIL_COUNT_MASK);
+
+	mib->tx_ampdu_cnt += mt76_rr(dev, MT_MIB_SDR12(0));
+	mib->tx_mpdu_attempts_cnt += mt76_rr(dev, MT_MIB_SDR14(0));
+	mib->tx_mpdu_success_cnt += mt76_rr(dev, MT_MIB_SDR15(0));
+
+	val = mt76_rr(dev, MT_MIB_SDR32(0));
+	mib->tx_pkt_ebf_cnt += FIELD_GET(MT_MIB_SDR9_EBF_CNT_MASK, val);
+	mib->tx_pkt_ibf_cnt += FIELD_GET(MT_MIB_SDR9_IBF_CNT_MASK, val);
+
+	val = mt76_rr(dev, MT_ETBF_TX_APP_CNT(0));
+	mib->tx_bf_ibf_ppdu_cnt += FIELD_GET(MT_ETBF_TX_IBF_CNT, val);
+	mib->tx_bf_ebf_ppdu_cnt += FIELD_GET(MT_ETBF_TX_EBF_CNT, val);
+
+	val = mt76_rr(dev, MT_ETBF_RX_FB_CNT(0));
+	mib->tx_bf_rx_fb_all_cnt += FIELD_GET(MT_ETBF_RX_FB_ALL, val);
+	mib->tx_bf_rx_fb_he_cnt += FIELD_GET(MT_ETBF_RX_FB_HE, val);
+	mib->tx_bf_rx_fb_vht_cnt += FIELD_GET(MT_ETBF_RX_FB_VHT, val);
+	mib->tx_bf_rx_fb_ht_cnt += FIELD_GET(MT_ETBF_RX_FB_HT, val);
+
+	mib->rx_mpdu_cnt += mt76_rr(dev, MT_MIB_SDR5(0));
+	mib->rx_ampdu_cnt += mt76_rr(dev, MT_MIB_SDR22(0));
+	mib->rx_ampdu_bytes_cnt += mt76_rr(dev, MT_MIB_SDR23(0));
+	mib->rx_ba_cnt += mt76_rr(dev, MT_MIB_SDR31(0));
+
+	for (i = 0; i < ARRAY_SIZE(mib->tx_amsdu); i++) {
+		val = mt76_rr(dev, MT_PLE_AMSDU_PACK_MSDU_CNT(i));
+		mib->tx_amsdu[i] += val;
+		mib->tx_amsdu_cnt += val;
+	}
+
+	for (i = 0, aggr1 = aggr0 + 8; i < 4; i++) {
+		u32 val2;
+
+		val = mt76_rr(dev, MT_TX_AGG_CNT(0, i));
+		val2 = mt76_rr(dev, MT_TX_AGG_CNT2(0, i));
+
+		phy->mt76->aggr_stats[aggr0++] += val & 0xffff;
+		phy->mt76->aggr_stats[aggr0++] += val >> 16;
+		phy->mt76->aggr_stats[aggr1++] += val2 & 0xffff;
+		phy->mt76->aggr_stats[aggr1++] += val2 >> 16;
+	}
+}
+EXPORT_SYMBOL_GPL(mt792x_mac_update_mib_stats);
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
index aa6a677427a4d..5f2407fbf95f6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
@@ -157,9 +157,6 @@
 #define MT_WTBLON_TOP_BASE		0x820d4000
 #define MT_WTBLON_TOP(ofs)		(MT_WTBLON_TOP_BASE + (ofs))
 
-#define MT_WTBL_UPDATE			MT_WTBLON_TOP(0x230)
-#define MT_WTBL_UPDATE_WLAN_IDX		GENMASK(9, 0)
-#define MT_WTBL_UPDATE_ADM_COUNT_CLEAR	BIT(12)
 #define MT_WTBL_UPDATE_BUSY		BIT(31)
 
 #define MT_WTBL_ITCR			MT_WTBLON_TOP(0x3b0)
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_trace.c b/drivers/net/wireless/mediatek/mt76/mt792x_trace.c
new file mode 100644
index 0000000000000..b6f284fb929d5
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_trace.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: ISC
+/*
+ * Copyright (C) 2023 Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include <linux/module.h>
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "mt792x_trace.h"
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(lp_event);
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921_trace.h b/drivers/net/wireless/mediatek/mt76/mt792x_trace.h
similarity index 72%
rename from drivers/net/wireless/mediatek/mt76/mt7921/mt7921_trace.h
rename to drivers/net/wireless/mediatek/mt76/mt792x_trace.h
index 9426fda69c309..61f2aa2606562 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921_trace.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_trace.h
@@ -1,20 +1,20 @@
 /* SPDX-License-Identifier: ISC */
 /*
- * Copyright (C) 2021 Lorenzo Bianconi <lorenzo@kernel.org>
+ * Copyright (C) 2023 Lorenzo Bianconi <lorenzo@kernel.org>
  */
 
-#if !defined(__MT7921_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
-#define __MT7921_TRACE_H
+#if !defined(__MT792X_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __MT792X_TRACE_H
 
 #include <linux/tracepoint.h>
-#include "mt7921.h"
+#include "mt792x.h"
 
 #undef TRACE_SYSTEM
-#define TRACE_SYSTEM mt7921
+#define TRACE_SYSTEM mt792x
 
 #define MAXNAME		32
 #define DEV_ENTRY	__array(char, wiphy_name, 32)
-#define DEV_ASSIGN	strlcpy(__entry->wiphy_name,	\
+#define DEV_ASSIGN	strscpy(__entry->wiphy_name,	\
 				wiphy_name(mt76_hw(dev)->wiphy), MAXNAME)
 #define DEV_PR_FMT	"%s"
 #define DEV_PR_ARG	__entry->wiphy_name
@@ -46,6 +46,6 @@ TRACE_EVENT(lp_event,
 #undef TRACE_INCLUDE_PATH
 #define TRACE_INCLUDE_PATH .
 #undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_FILE mt7921_trace
+#define TRACE_INCLUDE_FILE mt792x_trace
 
 #include <trace/define_trace.h>
-- 
GitLab


From 311f121c240967ad4add9e4b00fbd5204e9b93f7 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:58 +0800
Subject: [PATCH 0468/1806] wifi: mt76: mt7921: move mac shared code in
 mt792x-lib module

Reduce duplicated code moving mac shared code in mt792x-lib module.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7921/debugfs.c   |   2 +-
 .../net/wireless/mediatek/mt76/mt7921/mac.c   | 170 +-----------------
 .../net/wireless/mediatek/mt76/mt7921/main.c  |   4 +-
 .../net/wireless/mediatek/mt76/mt7921/mcu.c   |   6 +-
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |   3 -
 .../net/wireless/mediatek/mt76/mt7921/pci.c   |   6 +-
 .../net/wireless/mediatek/mt76/mt7921/sdio.c  |   6 +-
 .../net/wireless/mediatek/mt76/mt7921/usb.c   |   6 +-
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  20 +++
 .../net/wireless/mediatek/mt76/mt792x_mac.c   | 148 +++++++++++++++
 10 files changed, 187 insertions(+), 184 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
index 59920cffee6a7..7d5211b99340b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
@@ -396,7 +396,7 @@ static int mt7921_chip_reset(void *data, u64 val)
 	switch (val) {
 	case 1:
 		/* Reset wifisys directly. */
-		mt7921_reset(&dev->mt76);
+		mt792x_reset(&dev->mt76);
 		break;
 	default:
 		/* Collect the core dump before reset wifisys. */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 40f006664ad7d..70382194825ac 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -29,29 +29,6 @@ static u32 mt7921_mac_wtbl_lmac_addr(int idx, u8 offset)
 	return MT_WTBL_LMAC_OFFS(idx, 0) + offset * 4;
 }
 
-static struct mt76_wcid *mt7921_rx_get_wcid(struct mt792x_dev *dev,
-					    u16 idx, bool unicast)
-{
-	struct mt792x_sta *sta;
-	struct mt76_wcid *wcid;
-
-	if (idx >= ARRAY_SIZE(dev->mt76.wcid))
-		return NULL;
-
-	wcid = rcu_dereference(dev->mt76.wcid[idx]);
-	if (unicast || !wcid)
-		return wcid;
-
-	if (!wcid->sta)
-		return NULL;
-
-	sta = container_of(wcid, struct mt792x_sta, wcid);
-	if (!sta->vif)
-		return NULL;
-
-	return &sta->vif->sta.wcid;
-}
-
 static void mt7921_mac_sta_poll(struct mt792x_dev *dev)
 {
 	static const u8 ac_to_tid[] = {
@@ -184,52 +161,6 @@ static void mt7921_mac_sta_poll(struct mt792x_dev *dev)
 	}
 }
 
-static void
-mt7921_get_status_freq_info(struct mt792x_dev *dev, struct mt76_phy *mphy,
-			    struct mt76_rx_status *status, u8 chfreq)
-{
-	if (chfreq > 180) {
-		status->band = NL80211_BAND_6GHZ;
-		chfreq = (chfreq - 181) * 4 + 1;
-	} else if (chfreq > 14) {
-		status->band = NL80211_BAND_5GHZ;
-	} else {
-		status->band = NL80211_BAND_2GHZ;
-	}
-	status->freq = ieee80211_channel_to_frequency(chfreq, status->band);
-}
-
-static void
-mt7921_mac_rssi_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
-{
-	struct sk_buff *skb = priv;
-	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct ieee80211_hdr *hdr = mt76_skb_get_hdr(skb);
-
-	if (status->signal > 0)
-		return;
-
-	if (!ether_addr_equal(vif->addr, hdr->addr1))
-		return;
-
-	ewma_rssi_add(&mvif->rssi, -status->signal);
-}
-
-static void
-mt7921_mac_assoc_rssi(struct mt792x_dev *dev, struct sk_buff *skb)
-{
-	struct ieee80211_hdr *hdr = mt76_skb_get_hdr(skb);
-
-	if (!ieee80211_is_assoc_resp(hdr->frame_control) &&
-	    !ieee80211_is_auth(hdr->frame_control))
-		return;
-
-	ieee80211_iterate_active_interfaces_atomic(mt76_hw(dev),
-		IEEE80211_IFACE_ITER_RESUME_ALL,
-		mt7921_mac_rssi_iter, skb);
-}
-
 static int
 mt7921_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
 {
@@ -276,7 +207,7 @@ mt7921_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
 	chfreq = FIELD_GET(MT_RXD3_NORMAL_CH_FREQ, rxd3);
 	unicast = FIELD_GET(MT_RXD3_NORMAL_ADDR_TYPE, rxd3) == MT_RXD3_NORMAL_U2M;
 	idx = FIELD_GET(MT_RXD1_NORMAL_WLAN_IDX, rxd1);
-	status->wcid = mt7921_rx_get_wcid(dev, idx, unicast);
+	status->wcid = mt792x_rx_get_wcid(dev, idx, unicast);
 
 	if (status->wcid) {
 		msta = container_of(status->wcid, struct mt792x_sta, wcid);
@@ -287,7 +218,7 @@ mt7921_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 	}
 
-	mt7921_get_status_freq_info(dev, mphy, status, chfreq);
+	mt792x_get_status_freq_info(status, chfreq);
 
 	switch (status->band) {
 	case NL80211_BAND_5GHZ:
@@ -496,7 +427,7 @@ mt7921_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
 		status->flag |= RX_FLAG_8023;
 	}
 
-	mt7921_mac_assoc_rssi(dev, skb);
+	mt792x_mac_assoc_rssi(dev, skb);
 
 	if (rxv && mode >= MT_PHY_TYPE_HE_SU && !(status->flag & RX_FLAG_8023))
 		mt76_connac2_mac_decode_he_radiotap(&dev->mt76, skb, rxv, mode);
@@ -699,81 +630,6 @@ void mt7921_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 }
 EXPORT_SYMBOL_GPL(mt7921_queue_rx_skb);
 
-void mt7921_mac_reset_counters(struct mt792x_phy *phy)
-{
-	struct mt792x_dev *dev = phy->dev;
-	int i;
-
-	for (i = 0; i < 4; i++) {
-		mt76_rr(dev, MT_TX_AGG_CNT(0, i));
-		mt76_rr(dev, MT_TX_AGG_CNT2(0, i));
-	}
-
-	dev->mt76.phy.survey_time = ktime_get_boottime();
-	memset(phy->mt76->aggr_stats, 0, sizeof(phy->mt76->aggr_stats));
-
-	/* reset airtime counters */
-	mt76_rr(dev, MT_MIB_SDR9(0));
-	mt76_rr(dev, MT_MIB_SDR36(0));
-	mt76_rr(dev, MT_MIB_SDR37(0));
-
-	mt76_set(dev, MT_WF_RMAC_MIB_TIME0(0), MT_WF_RMAC_MIB_RXTIME_CLR);
-	mt76_set(dev, MT_WF_RMAC_MIB_AIRTIME0(0), MT_WF_RMAC_MIB_RXTIME_CLR);
-}
-
-static u8
-mt7921_phy_get_nf(struct mt792x_phy *phy, int idx)
-{
-	return 0;
-}
-
-static void
-mt7921_phy_update_channel(struct mt76_phy *mphy, int idx)
-{
-	struct mt792x_dev *dev = container_of(mphy->dev, struct mt792x_dev, mt76);
-	struct mt792x_phy *phy = (struct mt792x_phy *)mphy->priv;
-	struct mt76_channel_state *state;
-	u64 busy_time, tx_time, rx_time, obss_time;
-	int nf;
-
-	busy_time = mt76_get_field(dev, MT_MIB_SDR9(idx),
-				   MT_MIB_SDR9_BUSY_MASK);
-	tx_time = mt76_get_field(dev, MT_MIB_SDR36(idx),
-				 MT_MIB_SDR36_TXTIME_MASK);
-	rx_time = mt76_get_field(dev, MT_MIB_SDR37(idx),
-				 MT_MIB_SDR37_RXTIME_MASK);
-	obss_time = mt76_get_field(dev, MT_WF_RMAC_MIB_AIRTIME14(idx),
-				   MT_MIB_OBSSTIME_MASK);
-
-	nf = mt7921_phy_get_nf(phy, idx);
-	if (!phy->noise)
-		phy->noise = nf << 4;
-	else if (nf)
-		phy->noise += nf - (phy->noise >> 4);
-
-	state = mphy->chan_state;
-	state->cc_busy += busy_time;
-	state->cc_tx += tx_time;
-	state->cc_rx += rx_time + obss_time;
-	state->cc_bss_rx += rx_time;
-	state->noise = -(phy->noise >> 4);
-}
-
-void mt7921_update_channel(struct mt76_phy *mphy)
-{
-	struct mt792x_dev *dev = container_of(mphy->dev, struct mt792x_dev, mt76);
-
-	if (mt76_connac_pm_wake(mphy, &dev->pm))
-		return;
-
-	mt7921_phy_update_channel(mphy, 0);
-	/* reset obss airtime */
-	mt76_set(dev, MT_WF_RMAC_MIB_TIME0(0), MT_WF_RMAC_MIB_RXTIME_CLR);
-
-	mt76_connac_power_save_sched(mphy, &dev->pm);
-}
-EXPORT_SYMBOL_GPL(mt7921_update_channel);
-
 static void
 mt7921_vif_connect_iter(void *priv, u8 *mac,
 			struct ieee80211_vif *vif)
@@ -843,24 +699,6 @@ void mt7921_mac_reset_work(struct work_struct *work)
 	mt76_connac_power_save_sched(&dev->mt76.phy, pm);
 }
 
-void mt7921_reset(struct mt76_dev *mdev)
-{
-	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
-	struct mt76_connac_pm *pm = &dev->pm;
-
-	if (!dev->hw_init_done)
-		return;
-
-	if (dev->hw_full_reset)
-		return;
-
-	if (pm->suspended)
-		return;
-
-	queue_work(dev->mt76.wq, &dev->reset_work);
-}
-EXPORT_SYMBOL_GPL(mt7921_reset);
-
 void mt7921_pm_wake_work(struct work_struct *work)
 {
 	struct mt792x_dev *dev;
@@ -975,7 +813,7 @@ void mt7921_coredump_work(struct work_struct *work)
 		dev_coredumpv(dev->mt76.dev, dump, MT76_CONNAC_COREDUMP_SZ,
 			      GFP_KERNEL);
 
-	mt7921_reset(&dev->mt76);
+	mt792x_reset(&dev->mt76);
 }
 
 /* usb_sdio */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 2239688075169..73f29fed216fe 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -240,7 +240,7 @@ int __mt7921_start(struct mt792x_phy *phy)
 	if (err)
 		return err;
 
-	mt7921_mac_reset_counters(phy);
+	mt792x_mac_reset_counters(phy);
 	set_bit(MT76_STATE_RUNNING, &mphy->state);
 
 	ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
@@ -454,7 +454,7 @@ static int mt7921_set_channel(struct mt792x_phy *phy)
 
 	mt792x_mac_set_timeing(phy);
 
-	mt7921_mac_reset_counters(phy);
+	mt792x_mac_reset_counters(phy);
 	phy->noise = 0;
 
 out:
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 3dd9ff5e466b9..ed02fa48841ca 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -25,7 +25,7 @@ int mt7921_mcu_parse_response(struct mt76_dev *mdev, int cmd,
 	if (!skb) {
 		dev_err(mdev->dev, "Message %08x (seq %d) timeout\n",
 			cmd, seq);
-		mt7921_reset(mdev);
+		mt792x_reset(mdev);
 
 		return -ETIMEDOUT;
 	}
@@ -958,7 +958,7 @@ out:
 	mutex_unlock(&pm->mutex);
 
 	if (err)
-		mt7921_reset(&dev->mt76);
+		mt792x_reset(&dev->mt76);
 
 	return err;
 }
@@ -980,7 +980,7 @@ out:
 	mutex_unlock(&pm->mutex);
 
 	if (err)
-		mt7921_reset(&dev->mt76);
+		mt792x_reset(&dev->mt76);
 
 	return err;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 4722952bb846d..31fa51b8695e1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -282,7 +282,6 @@ mt7921_skb_add_usb_sdio_hdr(struct mt792x_dev *dev, struct sk_buff *skb,
 
 void mt7921_stop(struct ieee80211_hw *hw);
 int mt7921_mac_init(struct mt792x_dev *dev);
-void mt7921_mac_reset_counters(struct mt792x_phy *phy);
 bool mt7921_mac_wtbl_update(struct mt792x_dev *dev, int idx, u32 mask);
 int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
@@ -291,7 +290,6 @@ void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta);
 void mt7921_mac_reset_work(struct work_struct *work);
-void mt7921_reset(struct mt76_dev *mdev);
 int mt7921e_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			   enum mt76_txq_id qid, struct mt76_wcid *wcid,
 			   struct ieee80211_sta *sta,
@@ -302,7 +300,6 @@ void mt7921_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			 struct sk_buff *skb, u32 *info);
 void mt7921_stats_work(struct work_struct *work);
 void mt7921_set_stream_he_caps(struct mt792x_phy *phy);
-void mt7921_update_channel(struct mt76_phy *mphy);
 int mt7921_init_debugfs(struct mt792x_dev *dev);
 
 int mt7921_mcu_set_beacon_filter(struct mt792x_dev *dev,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 4227b5028a6ff..67eaa6232a02b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -245,7 +245,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 		.sta_add = mt7921_mac_sta_add,
 		.sta_assoc = mt7921_mac_sta_assoc,
 		.sta_remove = mt7921_mac_sta_remove,
-		.update_survey = mt7921_update_channel,
+		.update_survey = mt792x_update_channel,
 	};
 	static const struct mt792x_hif_ops mt7921_pcie_ops = {
 		.init_reset = mt7921e_init_reset,
@@ -450,7 +450,7 @@ restore_suspend:
 	pm->suspended = false;
 
 	if (err < 0)
-		mt7921_reset(&dev->mt76);
+		mt792x_reset(&dev->mt76);
 
 	return err;
 }
@@ -500,7 +500,7 @@ failed:
 	pm->suspended = false;
 
 	if (err < 0)
-		mt7921_reset(&dev->mt76);
+		mt792x_reset(&dev->mt76);
 
 	return err;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index b438947c2bd8b..f0117ac345945 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -102,7 +102,7 @@ static int mt7921s_probe(struct sdio_func *func,
 		.sta_add = mt7921_mac_sta_add,
 		.sta_assoc = mt7921_mac_sta_assoc,
 		.sta_remove = mt7921_mac_sta_remove,
-		.update_survey = mt7921_update_channel,
+		.update_survey = mt792x_update_channel,
 	};
 	static const struct mt76_bus_ops mt7921s_ops = {
 		.rr = mt76s_rr,
@@ -269,7 +269,7 @@ restore_suspend:
 	pm->suspended = false;
 
 	if (err < 0)
-		mt7921_reset(&dev->mt76);
+		mt792x_reset(&dev->mt76);
 
 	return err;
 }
@@ -302,7 +302,7 @@ failed:
 	pm->suspended = false;
 
 	if (err < 0)
-		mt7921_reset(&dev->mt76);
+		mt792x_reset(&dev->mt76);
 
 	return err;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index 9d54be3d3d038..3bf902cacd284 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -189,7 +189,7 @@ static int mt7921u_probe(struct usb_interface *usb_intf,
 		.sta_add = mt7921_mac_sta_add,
 		.sta_assoc = mt7921_mac_sta_assoc,
 		.sta_remove = mt7921_mac_sta_remove,
-		.update_survey = mt7921_update_channel,
+		.update_survey = mt792x_update_channel,
 	};
 	static const struct mt792x_hif_ops hif_ops = {
 		.mcu_init = mt7921u_mcu_init,
@@ -322,7 +322,7 @@ failed:
 	pm->suspended = false;
 
 	if (err < 0)
-		mt7921_reset(&dev->mt76);
+		mt792x_reset(&dev->mt76);
 
 	return err;
 }
@@ -364,7 +364,7 @@ failed:
 	pm->suspended = false;
 
 	if (err < 0)
-		mt7921_reset(&dev->mt76);
+		mt792x_reset(&dev->mt76);
 
 	return err;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 83236a6c300e4..f0f9fb3fd9703 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -155,11 +155,31 @@ mt792x_hw_phy(struct ieee80211_hw *hw)
 	return phy->priv;
 }
 
+static inline void
+mt792x_get_status_freq_info(struct mt76_rx_status *status, u8 chfreq)
+{
+	if (chfreq > 180) {
+		status->band = NL80211_BAND_6GHZ;
+		chfreq = (chfreq - 181) * 4 + 1;
+	} else if (chfreq > 14) {
+		status->band = NL80211_BAND_5GHZ;
+	} else {
+		status->band = NL80211_BAND_2GHZ;
+	}
+	status->freq = ieee80211_channel_to_frequency(chfreq, status->band);
+}
+
 #define mt792x_mutex_acquire(dev)	\
 	mt76_connac_mutex_acquire(&(dev)->mt76, &(dev)->pm)
 #define mt792x_mutex_release(dev)	\
 	mt76_connac_mutex_release(&(dev)->mt76, &(dev)->pm)
 
+void mt792x_reset(struct mt76_dev *mdev);
+void mt792x_update_channel(struct mt76_phy *mphy);
+void mt792x_mac_reset_counters(struct mt792x_phy *phy);
+void mt792x_mac_assoc_rssi(struct mt792x_dev *dev, struct sk_buff *skb);
+struct mt76_wcid *mt792x_rx_get_wcid(struct mt792x_dev *dev, u16 idx,
+				     bool unicast);
 void mt792x_mac_update_mib_stats(struct mt792x_phy *phy);
 void mt792x_mac_set_timeing(struct mt792x_phy *phy);
 void mt792x_mac_work(struct work_struct *work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
index 862cca816aae8..130b4352cf92d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
@@ -134,3 +134,151 @@ void mt792x_mac_update_mib_stats(struct mt792x_phy *phy)
 	}
 }
 EXPORT_SYMBOL_GPL(mt792x_mac_update_mib_stats);
+
+struct mt76_wcid *mt792x_rx_get_wcid(struct mt792x_dev *dev, u16 idx,
+				     bool unicast)
+{
+	struct mt792x_sta *sta;
+	struct mt76_wcid *wcid;
+
+	if (idx >= ARRAY_SIZE(dev->mt76.wcid))
+		return NULL;
+
+	wcid = rcu_dereference(dev->mt76.wcid[idx]);
+	if (unicast || !wcid)
+		return wcid;
+
+	if (!wcid->sta)
+		return NULL;
+
+	sta = container_of(wcid, struct mt792x_sta, wcid);
+	if (!sta->vif)
+		return NULL;
+
+	return &sta->vif->sta.wcid;
+}
+EXPORT_SYMBOL_GPL(mt792x_rx_get_wcid);
+
+static void
+mt792x_mac_rssi_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
+{
+	struct sk_buff *skb = priv;
+	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+	struct ieee80211_hdr *hdr = mt76_skb_get_hdr(skb);
+
+	if (status->signal > 0)
+		return;
+
+	if (!ether_addr_equal(vif->addr, hdr->addr1))
+		return;
+
+	ewma_rssi_add(&mvif->rssi, -status->signal);
+}
+
+void mt792x_mac_assoc_rssi(struct mt792x_dev *dev, struct sk_buff *skb)
+{
+	struct ieee80211_hdr *hdr = mt76_skb_get_hdr(skb);
+
+	if (!ieee80211_is_assoc_resp(hdr->frame_control) &&
+	    !ieee80211_is_auth(hdr->frame_control))
+		return;
+
+	ieee80211_iterate_active_interfaces_atomic(mt76_hw(dev),
+		IEEE80211_IFACE_ITER_RESUME_ALL,
+		mt792x_mac_rssi_iter, skb);
+}
+EXPORT_SYMBOL_GPL(mt792x_mac_assoc_rssi);
+
+void mt792x_mac_reset_counters(struct mt792x_phy *phy)
+{
+	struct mt792x_dev *dev = phy->dev;
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		mt76_rr(dev, MT_TX_AGG_CNT(0, i));
+		mt76_rr(dev, MT_TX_AGG_CNT2(0, i));
+	}
+
+	dev->mt76.phy.survey_time = ktime_get_boottime();
+	memset(phy->mt76->aggr_stats, 0, sizeof(phy->mt76->aggr_stats));
+
+	/* reset airtime counters */
+	mt76_rr(dev, MT_MIB_SDR9(0));
+	mt76_rr(dev, MT_MIB_SDR36(0));
+	mt76_rr(dev, MT_MIB_SDR37(0));
+
+	mt76_set(dev, MT_WF_RMAC_MIB_TIME0(0), MT_WF_RMAC_MIB_RXTIME_CLR);
+	mt76_set(dev, MT_WF_RMAC_MIB_AIRTIME0(0), MT_WF_RMAC_MIB_RXTIME_CLR);
+}
+EXPORT_SYMBOL_GPL(mt792x_mac_reset_counters);
+
+static u8
+mt792x_phy_get_nf(struct mt792x_phy *phy, int idx)
+{
+	return 0;
+}
+
+static void
+mt792x_phy_update_channel(struct mt76_phy *mphy, int idx)
+{
+	struct mt792x_dev *dev = container_of(mphy->dev, struct mt792x_dev, mt76);
+	struct mt792x_phy *phy = (struct mt792x_phy *)mphy->priv;
+	struct mt76_channel_state *state;
+	u64 busy_time, tx_time, rx_time, obss_time;
+	int nf;
+
+	busy_time = mt76_get_field(dev, MT_MIB_SDR9(idx),
+				   MT_MIB_SDR9_BUSY_MASK);
+	tx_time = mt76_get_field(dev, MT_MIB_SDR36(idx),
+				 MT_MIB_SDR36_TXTIME_MASK);
+	rx_time = mt76_get_field(dev, MT_MIB_SDR37(idx),
+				 MT_MIB_SDR37_RXTIME_MASK);
+	obss_time = mt76_get_field(dev, MT_WF_RMAC_MIB_AIRTIME14(idx),
+				   MT_MIB_OBSSTIME_MASK);
+
+	nf = mt792x_phy_get_nf(phy, idx);
+	if (!phy->noise)
+		phy->noise = nf << 4;
+	else if (nf)
+		phy->noise += nf - (phy->noise >> 4);
+
+	state = mphy->chan_state;
+	state->cc_busy += busy_time;
+	state->cc_tx += tx_time;
+	state->cc_rx += rx_time + obss_time;
+	state->cc_bss_rx += rx_time;
+	state->noise = -(phy->noise >> 4);
+}
+
+void mt792x_update_channel(struct mt76_phy *mphy)
+{
+	struct mt792x_dev *dev = container_of(mphy->dev, struct mt792x_dev, mt76);
+
+	if (mt76_connac_pm_wake(mphy, &dev->pm))
+		return;
+
+	mt792x_phy_update_channel(mphy, 0);
+	/* reset obss airtime */
+	mt76_set(dev, MT_WF_RMAC_MIB_TIME0(0), MT_WF_RMAC_MIB_RXTIME_CLR);
+	mt76_connac_power_save_sched(mphy, &dev->pm);
+}
+EXPORT_SYMBOL_GPL(mt792x_update_channel);
+
+void mt792x_reset(struct mt76_dev *mdev)
+{
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
+	struct mt76_connac_pm *pm = &dev->pm;
+
+	if (!dev->hw_init_done)
+		return;
+
+	if (dev->hw_full_reset)
+		return;
+
+	if (pm->suspended)
+		return;
+
+	queue_work(dev->mt76.wq, &dev->reset_work);
+}
+EXPORT_SYMBOL_GPL(mt792x_reset);
-- 
GitLab


From c693f2f068c0b21235994b7722bc635e854857a1 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:05:59 +0800
Subject: [PATCH 0469/1806] wifi: mt76: mt7921: move dma shared code in
 mt792x-lib module

Reduce duplicated code moving dma shared code in mt792x-lib module.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/dma.c   | 102 +-----------------
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |   7 --
 .../net/wireless/mediatek/mt76/mt7921/pci.c   |   6 +-
 .../net/wireless/mediatek/mt76/mt7921/regs.h  |   2 -
 .../net/wireless/mediatek/mt76/mt7921/usb.c   |   2 +-
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  10 ++
 .../net/wireless/mediatek/mt76/mt792x_core.c  |  98 ++++++++++++++++-
 .../net/wireless/mediatek/mt76/mt792x_regs.h  |   3 +
 8 files changed, 119 insertions(+), 111 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
index 3c628962641b6..9dcda35cdf73b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
@@ -25,24 +25,6 @@ static int mt7921_poll_tx(struct napi_struct *napi, int budget)
 	return 0;
 }
 
-static int mt7921_poll_rx(struct napi_struct *napi, int budget)
-{
-	struct mt792x_dev *dev;
-	int done;
-
-	dev = container_of(napi->dev, struct mt792x_dev, mt76.napi_dev);
-
-	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
-		napi_complete(napi);
-		queue_work(dev->mt76.wq, &dev->pm.wake_work);
-		return 0;
-	}
-	done = mt76_dma_rx_poll(napi, budget);
-	mt76_connac_pm_unref(&dev->mphy, &dev->pm);
-
-	return done;
-}
-
 static void mt7921_dma_prefetch(struct mt792x_dev *dev)
 {
 #define PREFETCH(base, depth)	((base) << 16 | (depth))
@@ -64,40 +46,6 @@ static void mt7921_dma_prefetch(struct mt792x_dev *dev)
 	mt76_wr(dev, MT_WFDMA0_TX_RING17_EXT_CTRL, PREFETCH(0x380, 0x4));
 }
 
-static int mt7921_dma_disable(struct mt792x_dev *dev, bool force)
-{
-	/* disable WFDMA0 */
-	mt76_clear(dev, MT_WFDMA0_GLO_CFG,
-		   MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN |
-		   MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN |
-		   MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO |
-		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
-
-	if (!mt76_poll_msec_tick(dev, MT_WFDMA0_GLO_CFG,
-				 MT_WFDMA0_GLO_CFG_TX_DMA_BUSY |
-				 MT_WFDMA0_GLO_CFG_RX_DMA_BUSY, 0, 100, 1))
-		return -ETIMEDOUT;
-
-	/* disable dmashdl */
-	mt76_clear(dev, MT_WFDMA0_GLO_CFG_EXT0,
-		   MT_WFDMA0_CSR_TX_DMASHDL_ENABLE);
-	mt76_set(dev, MT_DMASHDL_SW_CONTROL, MT_DMASHDL_DMASHDL_BYPASS);
-
-	if (force) {
-		/* reset */
-		mt76_clear(dev, MT_WFDMA0_RST,
-			   MT_WFDMA0_RST_DMASHDL_ALL_RST |
-			   MT_WFDMA0_RST_LOGIC_RST);
-
-		mt76_set(dev, MT_WFDMA0_RST,
-			 MT_WFDMA0_RST_DMASHDL_ALL_RST |
-			 MT_WFDMA0_RST_LOGIC_RST);
-	}
-
-	return 0;
-}
-
 static int mt7921_dma_enable(struct mt792x_dev *dev)
 {
 	/* configure perfetch settings */
@@ -135,7 +83,7 @@ static int mt7921_dma_reset(struct mt792x_dev *dev, bool force)
 {
 	int i, err;
 
-	err = mt7921_dma_disable(dev, force);
+	err = mt792x_dma_disable(dev, force);
 	if (err)
 		return err;
 
@@ -154,19 +102,6 @@ static int mt7921_dma_reset(struct mt792x_dev *dev, bool force)
 	return mt7921_dma_enable(dev);
 }
 
-int mt7921_wfsys_reset(struct mt792x_dev *dev)
-{
-	mt76_clear(dev, MT_WFSYS_SW_RST_B, WFSYS_SW_RST_B);
-	msleep(50);
-	mt76_set(dev, MT_WFSYS_SW_RST_B, WFSYS_SW_RST_B);
-
-	if (!__mt76_poll_msec(&dev->mt76, MT_WFSYS_SW_RST_B,
-			      WFSYS_SW_INIT_DONE, WFSYS_SW_INIT_DONE, 500))
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
 int mt7921_wpdma_reset(struct mt792x_dev *dev, bool force)
 {
 	int i, err;
@@ -182,7 +117,7 @@ int mt7921_wpdma_reset(struct mt792x_dev *dev, bool force)
 		mt76_queue_rx_cleanup(dev, &dev->mt76.q_rx[i]);
 
 	if (force) {
-		err = mt7921_wfsys_reset(dev);
+		err = mt792x_wfsys_reset(dev, MT_WFSYS_SW_RST_B);
 		if (err)
 			return err;
 	}
@@ -202,7 +137,7 @@ int mt7921_wpdma_reinit_cond(struct mt792x_dev *dev)
 	int err;
 
 	/* check if the wpdma must be reinitialized */
-	if (mt7921_dma_need_reinit(dev)) {
+	if (mt792x_dma_need_reinit(dev)) {
 		/* disable interrutpts */
 		mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0);
 		mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0);
@@ -227,7 +162,7 @@ int mt7921_dma_init(struct mt792x_dev *dev)
 
 	mt76_dma_attach(&dev->mt76);
 
-	ret = mt7921_dma_disable(dev, true);
+	ret = mt792x_dma_disable(dev, true);
 	if (ret)
 		return ret;
 
@@ -275,7 +210,7 @@ int mt7921_dma_init(struct mt792x_dev *dev)
 	if (ret)
 		return ret;
 
-	ret = mt76_init_queues(dev, mt7921_poll_rx);
+	ret = mt76_init_queues(dev, mt792x_poll_rx);
 	if (ret < 0)
 		return ret;
 
@@ -285,30 +220,3 @@ int mt7921_dma_init(struct mt792x_dev *dev)
 
 	return mt7921_dma_enable(dev);
 }
-
-void mt7921_dma_cleanup(struct mt792x_dev *dev)
-{
-	/* disable */
-	mt76_clear(dev, MT_WFDMA0_GLO_CFG,
-		   MT_WFDMA0_GLO_CFG_TX_DMA_EN |
-		   MT_WFDMA0_GLO_CFG_RX_DMA_EN |
-		   MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN |
-		   MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO |
-		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
-
-	mt76_poll_msec_tick(dev, MT_WFDMA0_GLO_CFG,
-			    MT_WFDMA0_GLO_CFG_TX_DMA_BUSY |
-			    MT_WFDMA0_GLO_CFG_RX_DMA_BUSY, 0, 100, 1);
-
-	/* reset */
-	mt76_clear(dev, MT_WFDMA0_RST,
-		   MT_WFDMA0_RST_DMASHDL_ALL_RST |
-		   MT_WFDMA0_RST_LOGIC_RST);
-
-	mt76_set(dev, MT_WFDMA0_RST,
-		 MT_WFDMA0_RST_DMASHDL_ALL_RST |
-		 MT_WFDMA0_RST_LOGIC_RST);
-
-	mt76_dma_cleanup(&dev->mt76);
-}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 31fa51b8695e1..b8699c942b349 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -208,7 +208,6 @@ void mt7921_unregister_device(struct mt792x_dev *dev);
 int mt7921_dma_init(struct mt792x_dev *dev);
 int mt7921_wpdma_reset(struct mt792x_dev *dev, bool force);
 int mt7921_wpdma_reinit_cond(struct mt792x_dev *dev);
-void mt7921_dma_cleanup(struct mt792x_dev *dev);
 int mt7921_run_firmware(struct mt792x_dev *dev);
 int mt7921_mcu_set_bss_pm(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 			  bool enable);
@@ -262,11 +261,6 @@ mt7921_l1_rmw(struct mt792x_dev *dev, u32 addr, u32 mask, u32 val)
 #define mt7921_l1_set(dev, addr, val)	mt7921_l1_rmw(dev, addr, 0, val)
 #define mt7921_l1_clear(dev, addr, val)	mt7921_l1_rmw(dev, addr, val, 0)
 
-static inline bool mt7921_dma_need_reinit(struct mt792x_dev *dev)
-{
-	return !mt76_get_field(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT);
-}
-
 static inline void
 mt7921_skb_add_usb_sdio_hdr(struct mt792x_dev *dev, struct sk_buff *skb,
 			    int type)
@@ -319,7 +313,6 @@ int mt7921_mcu_fw_pmctrl(struct mt792x_dev *dev);
 void mt7921_pm_wake_work(struct work_struct *work);
 void mt7921_pm_power_save_work(struct work_struct *work);
 void mt7921_coredump_work(struct work_struct *work);
-int mt7921_wfsys_reset(struct mt792x_dev *dev);
 int mt7921_get_txpwr_info(struct mt792x_dev *dev, struct mt7921_txpwr *txpwr);
 int mt7921_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			void *data, int len);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 67eaa6232a02b..4d929cf8d8548 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -117,8 +117,8 @@ static void mt7921e_unregister_device(struct mt792x_dev *dev)
 
 	mt76_connac2_tx_token_put(&dev->mt76);
 	__mt7921_mcu_drv_pmctrl(dev);
-	mt7921_dma_cleanup(dev);
-	mt7921_wfsys_reset(dev);
+	mt792x_dma_cleanup(dev);
+	mt792x_wfsys_reset(dev, MT_WFSYS_SW_RST_B);
 	skb_queue_purge(&dev->mt76.mcu.res_q);
 
 	tasklet_disable(&dev->mt76.irq_tasklet);
@@ -337,7 +337,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 		    (mt7921_l1_rr(dev, MT_HW_REV) & 0xff);
 	dev_info(mdev->dev, "ASIC revision: %04x\n", mdev->rev);
 
-	ret = mt7921_wfsys_reset(dev);
+	ret = mt792x_wfsys_reset(dev, MT_WFSYS_SW_RST_B);
 	if (ret)
 		goto err_free_dev;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
index c5ca1b931584d..083d655f82e50 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
@@ -87,8 +87,6 @@
 #define MT_HIF_REMAP_BASE_L1		0x40000
 
 #define MT_WFSYS_SW_RST_B		0x18000140
-#define WFSYS_SW_RST_B			BIT(0)
-#define WFSYS_SW_INIT_DONE		BIT(4)
 
 #define MT_WTBLON_TOP_WDUCR		MT_WTBLON_TOP(0x200)
 #define MT_WTBLON_TOP_WDUCR_GROUP	GENMASK(2, 0)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index 3bf902cacd284..c7368cf676a96 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -349,7 +349,7 @@ static int mt7921u_resume(struct usb_interface *intf)
 		msleep(20);
 	}
 
-	if (reinit || mt7921_dma_need_reinit(dev)) {
+	if (reinit || mt792x_dma_need_reinit(dev)) {
 		err = mt7921u_dma_init(dev, true);
 		if (err)
 			goto failed;
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index f0f9fb3fd9703..fa199cc05c601 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -8,6 +8,7 @@
 #include <linux/ktime.h>
 
 #include "mt76_connac_mcu.h"
+#include "mt792x_regs.h"
 
 #define MT792x_MAX_INTERFACES	4
 #define MT792x_WTBL_SIZE	20
@@ -169,6 +170,11 @@ mt792x_get_status_freq_info(struct mt76_rx_status *status, u8 chfreq)
 	status->freq = ieee80211_channel_to_frequency(chfreq, status->band);
 }
 
+static inline bool mt792x_dma_need_reinit(struct mt792x_dev *dev)
+{
+	return !mt76_get_field(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT);
+}
+
 #define mt792x_mutex_acquire(dev)	\
 	mt76_connac_mutex_acquire(&(dev)->mt76, &(dev)->pm)
 #define mt792x_mutex_release(dev)	\
@@ -219,5 +225,9 @@ void mt792x_sta_statistics(struct ieee80211_hw *hw,
 			   struct ieee80211_sta *sta,
 			   struct station_info *sinfo);
 void mt792x_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class);
+void mt792x_dma_cleanup(struct mt792x_dev *dev);
+int mt792x_dma_disable(struct mt792x_dev *dev, bool force);
+int mt792x_poll_rx(struct napi_struct *napi, int budget);
+int mt792x_wfsys_reset(struct mt792x_dev *dev, u32 addr);
 
 #endif /* __MT7925_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index fa648b1333979..b176ce53996e4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -4,7 +4,7 @@
 #include <linux/module.h>
 
 #include "mt792x.h"
-#include "mt792x_regs.h"
+#include "dma.h"
 
 void mt792x_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
 	       struct sk_buff *skb)
@@ -465,5 +465,101 @@ void mt792x_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class)
 }
 EXPORT_SYMBOL_GPL(mt792x_set_coverage_class);
 
+int mt792x_dma_disable(struct mt792x_dev *dev, bool force)
+{
+	/* disable WFDMA0 */
+	mt76_clear(dev, MT_WFDMA0_GLO_CFG,
+		   MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN |
+		   MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN |
+		   MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO |
+		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+
+	if (!mt76_poll_msec_tick(dev, MT_WFDMA0_GLO_CFG,
+				 MT_WFDMA0_GLO_CFG_TX_DMA_BUSY |
+				 MT_WFDMA0_GLO_CFG_RX_DMA_BUSY, 0, 100, 1))
+		return -ETIMEDOUT;
+
+	/* disable dmashdl */
+	mt76_clear(dev, MT_WFDMA0_GLO_CFG_EXT0,
+		   MT_WFDMA0_CSR_TX_DMASHDL_ENABLE);
+	mt76_set(dev, MT_DMASHDL_SW_CONTROL, MT_DMASHDL_DMASHDL_BYPASS);
+
+	if (force) {
+		/* reset */
+		mt76_clear(dev, MT_WFDMA0_RST,
+			   MT_WFDMA0_RST_DMASHDL_ALL_RST |
+			   MT_WFDMA0_RST_LOGIC_RST);
+
+		mt76_set(dev, MT_WFDMA0_RST,
+			 MT_WFDMA0_RST_DMASHDL_ALL_RST |
+			 MT_WFDMA0_RST_LOGIC_RST);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_dma_disable);
+
+void mt792x_dma_cleanup(struct mt792x_dev *dev)
+{
+	/* disable */
+	mt76_clear(dev, MT_WFDMA0_GLO_CFG,
+		   MT_WFDMA0_GLO_CFG_TX_DMA_EN |
+		   MT_WFDMA0_GLO_CFG_RX_DMA_EN |
+		   MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN |
+		   MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO |
+		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+
+	mt76_poll_msec_tick(dev, MT_WFDMA0_GLO_CFG,
+			    MT_WFDMA0_GLO_CFG_TX_DMA_BUSY |
+			    MT_WFDMA0_GLO_CFG_RX_DMA_BUSY, 0, 100, 1);
+
+	/* reset */
+	mt76_clear(dev, MT_WFDMA0_RST,
+		   MT_WFDMA0_RST_DMASHDL_ALL_RST |
+		   MT_WFDMA0_RST_LOGIC_RST);
+
+	mt76_set(dev, MT_WFDMA0_RST,
+		 MT_WFDMA0_RST_DMASHDL_ALL_RST |
+		 MT_WFDMA0_RST_LOGIC_RST);
+
+	mt76_dma_cleanup(&dev->mt76);
+}
+EXPORT_SYMBOL_GPL(mt792x_dma_cleanup);
+
+int mt792x_poll_rx(struct napi_struct *napi, int budget)
+{
+	struct mt792x_dev *dev;
+	int done;
+
+	dev = container_of(napi->dev, struct mt792x_dev, mt76.napi_dev);
+
+	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
+		napi_complete(napi);
+		queue_work(dev->mt76.wq, &dev->pm.wake_work);
+		return 0;
+	}
+	done = mt76_dma_rx_poll(napi, budget);
+	mt76_connac_pm_unref(&dev->mphy, &dev->pm);
+
+	return done;
+}
+EXPORT_SYMBOL_GPL(mt792x_poll_rx);
+
+int mt792x_wfsys_reset(struct mt792x_dev *dev, u32 addr)
+{
+	mt76_clear(dev, addr, WFSYS_SW_RST_B);
+	msleep(50);
+	mt76_set(dev, addr, WFSYS_SW_RST_B);
+
+	if (!__mt76_poll_msec(&dev->mt76, addr, WFSYS_SW_INIT_DONE,
+			      WFSYS_SW_INIT_DONE, 500))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_wfsys_reset);
+
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
index 5f2407fbf95f6..9c6308ef4cb39 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
@@ -454,4 +454,7 @@
 #define MT_WF_SW_SER_TRIGGER_SUSPEND	BIT(6)
 #define MT_WF_SW_SER_DONE_SUSPEND	BIT(7)
 
+#define WFSYS_SW_RST_B			BIT(0)
+#define WFSYS_SW_INIT_DONE		BIT(4)
+
 #endif /* __MT792X_REGS_H */
-- 
GitLab


From 974e759c3fd99813bd2b537acb8bb936c5f2bae7 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:06:00 +0800
Subject: [PATCH 0470/1806] wifi: mt76: mt7921: move debugfs shared code in
 mt792x-lib module

Reduce duplicated code moving debugfs shared code in mt792x-lib module.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/Makefile   |   3 +-
 .../wireless/mediatek/mt76/mt7921/debugfs.c   | 178 +-----------------
 drivers/net/wireless/mediatek/mt76/mt792x.h   |   6 +
 .../wireless/mediatek/mt76/mt792x_debugfs.c   | 168 +++++++++++++++++
 4 files changed, 183 insertions(+), 172 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt792x_debugfs.c

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index a20eebba04bac..a45853ab958f4 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -31,7 +31,8 @@ mt76x02-usb-y := mt76x02_usb_mcu.o mt76x02_usb_core.o
 
 mt76-connac-lib-y := mt76_connac_mcu.o mt76_connac_mac.o mt76_connac3_mac.o
 
-mt792x-lib-y := mt792x_core.o mt792x_mac.o mt792x_trace.o
+mt792x-lib-y := mt792x_core.o mt792x_mac.o mt792x_trace.o \
+		mt792x_debugfs.o
 
 obj-$(CONFIG_MT76x0_COMMON) += mt76x0/
 obj-$(CONFIG_MT76x2_COMMON) += mt76x2/
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
index 7d5211b99340b..616b66a3fde2b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
@@ -57,128 +57,7 @@ mt7921_fw_debug_get(void *data, u64 *val)
 DEFINE_DEBUGFS_ATTRIBUTE(fops_fw_debug, mt7921_fw_debug_get,
 			 mt7921_fw_debug_set, "%lld\n");
 
-static void
-mt7921_ampdu_stat_read_phy(struct mt792x_phy *phy,
-			   struct seq_file *file)
-{
-	struct mt792x_dev *dev = file->private;
-	int bound[15], range[4], i;
-
-	if (!phy)
-		return;
-
-	mt792x_mac_update_mib_stats(phy);
-
-	/* Tx ampdu stat */
-	for (i = 0; i < ARRAY_SIZE(range); i++)
-		range[i] = mt76_rr(dev, MT_MIB_ARNG(0, i));
-
-	for (i = 0; i < ARRAY_SIZE(bound); i++)
-		bound[i] = MT_MIB_ARNCR_RANGE(range[i / 4], i % 4) + 1;
-
-	seq_printf(file, "\nPhy0\n");
-
-	seq_printf(file, "Length: %8d | ", bound[0]);
-	for (i = 0; i < ARRAY_SIZE(bound) - 1; i++)
-		seq_printf(file, "%3d  %3d | ", bound[i] + 1, bound[i + 1]);
-
-	seq_puts(file, "\nCount:  ");
-	for (i = 0; i < ARRAY_SIZE(bound); i++)
-		seq_printf(file, "%8d | ", phy->mt76->aggr_stats[i]);
-	seq_puts(file, "\n");
-
-	seq_printf(file, "BA miss count: %d\n", phy->mib.ba_miss_cnt);
-}
-
-static int
-mt7921_tx_stats_show(struct seq_file *file, void *data)
-{
-	struct mt792x_dev *dev = file->private;
-	struct mt792x_phy *phy = &dev->phy;
-	struct mt76_mib_stats *mib = &phy->mib;
-	int i;
-
-	mt792x_mutex_acquire(dev);
-
-	mt7921_ampdu_stat_read_phy(phy, file);
-
-	seq_puts(file, "Tx MSDU stat:\n");
-	for (i = 0; i < ARRAY_SIZE(mib->tx_amsdu); i++) {
-		seq_printf(file, "AMSDU pack count of %d MSDU in TXD: %8d ",
-			   i + 1, mib->tx_amsdu[i]);
-		if (mib->tx_amsdu_cnt)
-			seq_printf(file, "(%3d%%)\n",
-				   mib->tx_amsdu[i] * 100 / mib->tx_amsdu_cnt);
-		else
-			seq_puts(file, "\n");
-	}
-
-	mt792x_mutex_release(dev);
-
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mt7921_tx_stats);
-
-static int
-mt7921_queues_acq(struct seq_file *s, void *data)
-{
-	struct mt792x_dev *dev = dev_get_drvdata(s->private);
-	int i;
-
-	mt792x_mutex_acquire(dev);
-
-	for (i = 0; i < 4; i++) {
-		u32 ctrl, val, qlen = 0;
-		int j;
-
-		val = mt76_rr(dev, MT_PLE_AC_QEMPTY(i));
-		ctrl = BIT(31) | BIT(11) | (i << 24);
-
-		for (j = 0; j < 32; j++) {
-			if (val & BIT(j))
-				continue;
-
-			mt76_wr(dev, MT_PLE_FL_Q0_CTRL, ctrl | j);
-			qlen += mt76_get_field(dev, MT_PLE_FL_Q3_CTRL,
-					       GENMASK(11, 0));
-		}
-		seq_printf(s, "AC%d: queued=%d\n", i, qlen);
-	}
-
-	mt792x_mutex_release(dev);
-
-	return 0;
-}
-
-static int
-mt7921_queues_read(struct seq_file *s, void *data)
-{
-	struct mt792x_dev *dev = dev_get_drvdata(s->private);
-	struct {
-		struct mt76_queue *q;
-		char *queue;
-	} queue_map[] = {
-		{ dev->mphy.q_tx[MT_TXQ_BE],	 "WFDMA0" },
-		{ dev->mt76.q_mcu[MT_MCUQ_WM],	 "MCUWM"  },
-		{ dev->mt76.q_mcu[MT_MCUQ_FWDL], "MCUFWQ" },
-	};
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(queue_map); i++) {
-		struct mt76_queue *q = queue_map[i].q;
-
-		if (!q)
-			continue;
-
-		seq_printf(s,
-			   "%s:	queued=%d head=%d tail=%d\n",
-			   queue_map[i].queue, q->queued, q->head,
-			   q->tail);
-	}
-
-	return 0;
-}
+DEFINE_SHOW_ATTRIBUTE(mt792x_tx_stats);
 
 static void
 mt7921_seq_puts_array(struct seq_file *file, const char *str,
@@ -342,51 +221,8 @@ mt7921_deep_sleep_get(void *data, u64 *val)
 DEFINE_DEBUGFS_ATTRIBUTE(fops_ds, mt7921_deep_sleep_get,
 			 mt7921_deep_sleep_set, "%lld\n");
 
-static int
-mt7921_pm_stats(struct seq_file *s, void *data)
-{
-	struct mt792x_dev *dev = dev_get_drvdata(s->private);
-	struct mt76_connac_pm *pm = &dev->pm;
-
-	unsigned long awake_time = pm->stats.awake_time;
-	unsigned long doze_time = pm->stats.doze_time;
-
-	if (!test_bit(MT76_STATE_PM, &dev->mphy.state))
-		awake_time += jiffies - pm->stats.last_wake_event;
-	else
-		doze_time += jiffies - pm->stats.last_doze_event;
-
-	seq_printf(s, "awake time: %14u\ndoze time: %15u\n",
-		   jiffies_to_msecs(awake_time),
-		   jiffies_to_msecs(doze_time));
-
-	seq_printf(s, "low power wakes: %9d\n", pm->stats.lp_wake);
-
-	return 0;
-}
-
-static int
-mt7921_pm_idle_timeout_set(void *data, u64 val)
-{
-	struct mt792x_dev *dev = data;
-
-	dev->pm.idle_timeout = msecs_to_jiffies(val);
-
-	return 0;
-}
-
-static int
-mt7921_pm_idle_timeout_get(void *data, u64 *val)
-{
-	struct mt792x_dev *dev = data;
-
-	*val = jiffies_to_msecs(dev->pm.idle_timeout);
-
-	return 0;
-}
-
-DEFINE_DEBUGFS_ATTRIBUTE(fops_pm_idle_timeout, mt7921_pm_idle_timeout_get,
-			 mt7921_pm_idle_timeout_set, "%lld\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_pm_idle_timeout, mt792x_pm_idle_timeout_get,
+			 mt792x_pm_idle_timeout_set, "%lld\n");
 
 static int mt7921_chip_reset(void *data, u64 val)
 {
@@ -435,23 +271,23 @@ int mt7921_init_debugfs(struct mt792x_dev *dev)
 
 	if (mt76_is_mmio(&dev->mt76))
 		debugfs_create_devm_seqfile(dev->mt76.dev, "xmit-queues",
-					    dir, mt7921_queues_read);
+					    dir, mt792x_queues_read);
 	else
 		debugfs_create_devm_seqfile(dev->mt76.dev, "xmit-queues",
 					    dir, mt76_queues_read);
 
 	debugfs_create_devm_seqfile(dev->mt76.dev, "acq", dir,
-				    mt7921_queues_acq);
+				    mt792x_queues_acq);
 	debugfs_create_devm_seqfile(dev->mt76.dev, "txpower_sku", dir,
 				    mt7921_txpwr);
-	debugfs_create_file("tx_stats", 0400, dir, dev, &mt7921_tx_stats_fops);
+	debugfs_create_file("tx_stats", 0400, dir, dev, &mt792x_tx_stats_fops);
 	debugfs_create_file("fw_debug", 0600, dir, dev, &fops_fw_debug);
 	debugfs_create_file("runtime-pm", 0600, dir, dev, &fops_pm);
 	debugfs_create_file("idle-timeout", 0600, dir, dev,
 			    &fops_pm_idle_timeout);
 	debugfs_create_file("chip_reset", 0600, dir, dev, &fops_reset);
 	debugfs_create_devm_seqfile(dev->mt76.dev, "runtime_pm_stats", dir,
-				    mt7921_pm_stats);
+				    mt792x_pm_stats);
 	debugfs_create_file("deep-sleep", 0600, dir, dev, &fops_ds);
 	if (mt76_is_sdio(&dev->mt76))
 		debugfs_create_devm_seqfile(dev->mt76.dev, "sched-quota", dir,
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index fa199cc05c601..1fd53a29fef1f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -229,5 +229,11 @@ void mt792x_dma_cleanup(struct mt792x_dev *dev);
 int mt792x_dma_disable(struct mt792x_dev *dev, bool force);
 int mt792x_poll_rx(struct napi_struct *napi, int budget);
 int mt792x_wfsys_reset(struct mt792x_dev *dev, u32 addr);
+int mt792x_tx_stats_show(struct seq_file *file, void *data);
+int mt792x_queues_acq(struct seq_file *s, void *data);
+int mt792x_queues_read(struct seq_file *s, void *data);
+int mt792x_pm_stats(struct seq_file *s, void *data);
+int mt792x_pm_idle_timeout_set(void *data, u64 val);
+int mt792x_pm_idle_timeout_get(void *data, u64 *val);
 
 #endif /* __MT7925_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_debugfs.c b/drivers/net/wireless/mediatek/mt76/mt792x_debugfs.c
new file mode 100644
index 0000000000000..9858d9a93851a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_debugfs.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: ISC
+/* Copyright (C) 2023 MediaTek Inc. */
+
+#include "mt792x.h"
+
+static void
+mt792x_ampdu_stat_read_phy(struct mt792x_phy *phy,
+			   struct seq_file *file)
+{
+	struct mt792x_dev *dev = file->private;
+	int bound[15], range[4], i;
+
+	if (!phy)
+		return;
+
+	mt792x_mac_update_mib_stats(phy);
+
+	/* Tx ampdu stat */
+	for (i = 0; i < ARRAY_SIZE(range); i++)
+		range[i] = mt76_rr(dev, MT_MIB_ARNG(0, i));
+
+	for (i = 0; i < ARRAY_SIZE(bound); i++)
+		bound[i] = MT_MIB_ARNCR_RANGE(range[i / 4], i % 4) + 1;
+
+	seq_puts(file, "\nPhy0\n");
+
+	seq_printf(file, "Length: %8d | ", bound[0]);
+	for (i = 0; i < ARRAY_SIZE(bound) - 1; i++)
+		seq_printf(file, "%3d  %3d | ", bound[i] + 1, bound[i + 1]);
+
+	seq_puts(file, "\nCount:  ");
+	for (i = 0; i < ARRAY_SIZE(bound); i++)
+		seq_printf(file, "%8d | ", phy->mt76->aggr_stats[i]);
+	seq_puts(file, "\n");
+
+	seq_printf(file, "BA miss count: %d\n", phy->mib.ba_miss_cnt);
+}
+
+int mt792x_tx_stats_show(struct seq_file *file, void *data)
+{
+	struct mt792x_dev *dev = file->private;
+	struct mt792x_phy *phy = &dev->phy;
+	struct mt76_mib_stats *mib = &phy->mib;
+	int i;
+
+	mt792x_mutex_acquire(dev);
+
+	mt792x_ampdu_stat_read_phy(phy, file);
+
+	seq_puts(file, "Tx MSDU stat:\n");
+	for (i = 0; i < ARRAY_SIZE(mib->tx_amsdu); i++) {
+		seq_printf(file, "AMSDU pack count of %d MSDU in TXD: %8d ",
+			   i + 1, mib->tx_amsdu[i]);
+		if (mib->tx_amsdu_cnt)
+			seq_printf(file, "(%3d%%)\n",
+				   mib->tx_amsdu[i] * 100 / mib->tx_amsdu_cnt);
+		else
+			seq_puts(file, "\n");
+	}
+
+	mt792x_mutex_release(dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_tx_stats_show);
+
+int mt792x_queues_acq(struct seq_file *s, void *data)
+{
+	struct mt792x_dev *dev = dev_get_drvdata(s->private);
+	int i;
+
+	mt792x_mutex_acquire(dev);
+
+	for (i = 0; i < 4; i++) {
+		u32 ctrl, val, qlen = 0;
+		int j;
+
+		val = mt76_rr(dev, MT_PLE_AC_QEMPTY(i));
+		ctrl = BIT(31) | BIT(11) | (i << 24);
+
+		for (j = 0; j < 32; j++) {
+			if (val & BIT(j))
+				continue;
+
+			mt76_wr(dev, MT_PLE_FL_Q0_CTRL, ctrl | j);
+			qlen += mt76_get_field(dev, MT_PLE_FL_Q3_CTRL,
+					       GENMASK(11, 0));
+		}
+		seq_printf(s, "AC%d: queued=%d\n", i, qlen);
+	}
+
+	mt792x_mutex_release(dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_queues_acq);
+
+int mt792x_queues_read(struct seq_file *s, void *data)
+{
+	struct mt792x_dev *dev = dev_get_drvdata(s->private);
+	struct {
+		struct mt76_queue *q;
+		char *queue;
+	} queue_map[] = {
+		{ dev->mphy.q_tx[MT_TXQ_BE],	 "WFDMA0" },
+		{ dev->mt76.q_mcu[MT_MCUQ_WM],	 "MCUWM"  },
+		{ dev->mt76.q_mcu[MT_MCUQ_FWDL], "MCUFWQ" },
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(queue_map); i++) {
+		struct mt76_queue *q = queue_map[i].q;
+
+		if (!q)
+			continue;
+
+		seq_printf(s,
+			   "%s:	queued=%d head=%d tail=%d\n",
+			   queue_map[i].queue, q->queued, q->head,
+			   q->tail);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_queues_read);
+
+int mt792x_pm_stats(struct seq_file *s, void *data)
+{
+	struct mt792x_dev *dev = dev_get_drvdata(s->private);
+	struct mt76_connac_pm *pm = &dev->pm;
+
+	unsigned long awake_time = pm->stats.awake_time;
+	unsigned long doze_time = pm->stats.doze_time;
+
+	if (!test_bit(MT76_STATE_PM, &dev->mphy.state))
+		awake_time += jiffies - pm->stats.last_wake_event;
+	else
+		doze_time += jiffies - pm->stats.last_doze_event;
+
+	seq_printf(s, "awake time: %14u\ndoze time: %15u\n",
+		   jiffies_to_msecs(awake_time),
+		   jiffies_to_msecs(doze_time));
+
+	seq_printf(s, "low power wakes: %9d\n", pm->stats.lp_wake);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_pm_stats);
+
+int mt792x_pm_idle_timeout_set(void *data, u64 val)
+{
+	struct mt792x_dev *dev = data;
+
+	dev->pm.idle_timeout = msecs_to_jiffies(val);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_pm_idle_timeout_set);
+
+int mt792x_pm_idle_timeout_get(void *data, u64 *val)
+{
+	struct mt792x_dev *dev = data;
+
+	*val = jiffies_to_msecs(dev->pm.idle_timeout);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_pm_idle_timeout_get);
-- 
GitLab


From e8a264ccd2de0db8ffc2c6ed2c23644ed15854d4 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:06:01 +0800
Subject: [PATCH 0471/1806] wifi: mt76: mt7921: move init shared code in
 mt792x-lib module

Reduce duplicated code moving init shared code in mt792x-lib module.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/init.c  | 254 +-----------------
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |   5 -
 .../net/wireless/mediatek/mt76/mt7921/pci.c   |   4 +-
 .../net/wireless/mediatek/mt76/mt7921/sdio.c  |   4 +-
 .../net/wireless/mediatek/mt76/mt7921/usb.c   |   4 +-
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  22 ++
 .../net/wireless/mediatek/mt76/mt792x_core.c  | 227 ++++++++++++++++
 .../net/wireless/mediatek/mt76/mt792x_mac.c   |  29 ++
 8 files changed, 288 insertions(+), 261 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 449ce34a6dcf3..0a6f8f42b2e4f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -10,50 +10,6 @@
 #include "../mt76_connac2_mac.h"
 #include "mcu.h"
 
-static const struct ieee80211_iface_limit if_limits[] = {
-	{
-		.max = MT792x_MAX_INTERFACES,
-		.types = BIT(NL80211_IFTYPE_STATION)
-	},
-	{
-		.max = 1,
-		.types = BIT(NL80211_IFTYPE_AP)
-	}
-};
-
-static const struct ieee80211_iface_combination if_comb[] = {
-	{
-		.limits = if_limits,
-		.n_limits = ARRAY_SIZE(if_limits),
-		.max_interfaces = MT792x_MAX_INTERFACES,
-		.num_different_channels = 1,
-		.beacon_int_infra_match = true,
-	},
-};
-
-static const struct ieee80211_iface_limit if_limits_chanctx[] = {
-	{
-		.max = 2,
-		.types = BIT(NL80211_IFTYPE_STATION) |
-			 BIT(NL80211_IFTYPE_P2P_CLIENT)
-	},
-	{
-		.max = 1,
-		.types = BIT(NL80211_IFTYPE_AP) |
-			 BIT(NL80211_IFTYPE_P2P_GO)
-	}
-};
-
-static const struct ieee80211_iface_combination if_comb_chanctx[] = {
-	{
-		.limits = if_limits_chanctx,
-		.n_limits = ARRAY_SIZE(if_limits_chanctx),
-		.max_interfaces = 2,
-		.num_different_channels = 2,
-		.beacon_int_infra_match = false,
-	}
-};
-
 static ssize_t mt7921_thermal_temp_show(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
@@ -123,192 +79,6 @@ mt7921_regd_notifier(struct wiphy *wiphy,
 	mt792x_mutex_release(dev);
 }
 
-static int
-mt7921_init_wiphy(struct ieee80211_hw *hw)
-{
-	struct mt792x_phy *phy = mt792x_hw_phy(hw);
-	struct mt792x_dev *dev = phy->dev;
-	struct wiphy *wiphy = hw->wiphy;
-
-	hw->queues = 4;
-	hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
-	hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
-	hw->netdev_features = NETIF_F_RXCSUM;
-
-	hw->radiotap_timestamp.units_pos =
-		IEEE80211_RADIOTAP_TIMESTAMP_UNIT_US;
-
-	phy->slottime = 9;
-
-	hw->sta_data_size = sizeof(struct mt792x_sta);
-	hw->vif_data_size = sizeof(struct mt792x_vif);
-
-	if (dev->fw_features & MT7921_FW_CAP_CNM) {
-		wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
-		wiphy->iface_combinations = if_comb_chanctx;
-		wiphy->n_iface_combinations = ARRAY_SIZE(if_comb_chanctx);
-	} else {
-		wiphy->flags &= ~WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
-		wiphy->iface_combinations = if_comb;
-		wiphy->n_iface_combinations = ARRAY_SIZE(if_comb);
-	}
-	wiphy->flags &= ~(WIPHY_FLAG_IBSS_RSN | WIPHY_FLAG_4ADDR_AP |
-			  WIPHY_FLAG_4ADDR_STATION);
-	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) |
-				 BIT(NL80211_IFTYPE_AP) |
-				 BIT(NL80211_IFTYPE_P2P_CLIENT) |
-				 BIT(NL80211_IFTYPE_P2P_GO);
-	wiphy->max_remain_on_channel_duration = 5000;
-	wiphy->max_scan_ie_len = MT76_CONNAC_SCAN_IE_LEN;
-	wiphy->max_scan_ssids = 4;
-	wiphy->max_sched_scan_plan_interval =
-		MT76_CONNAC_MAX_TIME_SCHED_SCAN_INTERVAL;
-	wiphy->max_sched_scan_ie_len = IEEE80211_MAX_DATA_LEN;
-	wiphy->max_sched_scan_ssids = MT76_CONNAC_MAX_SCHED_SCAN_SSID;
-	wiphy->max_match_sets = MT76_CONNAC_MAX_SCAN_MATCH;
-	wiphy->max_sched_scan_reqs = 1;
-	wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH |
-			WIPHY_FLAG_SPLIT_SCAN_6GHZ;
-	wiphy->reg_notifier = mt7921_regd_notifier;
-
-	wiphy->features |= NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR |
-			   NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR;
-	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_SET_SCAN_DWELL);
-	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_LEGACY);
-	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_HT);
-	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_VHT);
-	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_HE);
-	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT);
-	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0);
-
-	ieee80211_hw_set(hw, SINGLE_SCAN_ON_ALL_BANDS);
-	ieee80211_hw_set(hw, HAS_RATE_CONTROL);
-	ieee80211_hw_set(hw, SUPPORTS_TX_ENCAP_OFFLOAD);
-	ieee80211_hw_set(hw, SUPPORTS_RX_DECAP_OFFLOAD);
-	ieee80211_hw_set(hw, WANT_MONITOR_VIF);
-	ieee80211_hw_set(hw, SUPPORTS_PS);
-	ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS);
-	ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW);
-	ieee80211_hw_set(hw, CONNECTION_MONITOR);
-
-	if (dev->pm.enable)
-		ieee80211_hw_set(hw, CONNECTION_MONITOR);
-
-	hw->max_tx_fragments = 4;
-
-	return 0;
-}
-
-static void
-mt7921_mac_init_band(struct mt792x_dev *dev, u8 band)
-{
-	u32 mask, set;
-
-	mt76_rmw_field(dev, MT_TMAC_CTCR0(band),
-		       MT_TMAC_CTCR0_INS_DDLMT_REFTIME, 0x3f);
-	mt76_set(dev, MT_TMAC_CTCR0(band),
-		 MT_TMAC_CTCR0_INS_DDLMT_VHT_SMPDU_EN |
-		 MT_TMAC_CTCR0_INS_DDLMT_EN);
-
-	mt76_set(dev, MT_WF_RMAC_MIB_TIME0(band), MT_WF_RMAC_MIB_RXTIME_EN);
-	mt76_set(dev, MT_WF_RMAC_MIB_AIRTIME0(band), MT_WF_RMAC_MIB_RXTIME_EN);
-
-	/* enable MIB tx-rx time reporting */
-	mt76_set(dev, MT_MIB_SCR1(band), MT_MIB_TXDUR_EN);
-	mt76_set(dev, MT_MIB_SCR1(band), MT_MIB_RXDUR_EN);
-
-	mt76_rmw_field(dev, MT_DMA_DCR0(band), MT_DMA_DCR0_MAX_RX_LEN, 1536);
-	/* disable rx rate report by default due to hw issues */
-	mt76_clear(dev, MT_DMA_DCR0(band), MT_DMA_DCR0_RXD_G5_EN);
-
-	/* filter out non-resp frames and get instantaneous signal reporting */
-	mask = MT_WTBLOFF_TOP_RSCR_RCPI_MODE | MT_WTBLOFF_TOP_RSCR_RCPI_PARAM;
-	set = FIELD_PREP(MT_WTBLOFF_TOP_RSCR_RCPI_MODE, 0) |
-	      FIELD_PREP(MT_WTBLOFF_TOP_RSCR_RCPI_PARAM, 0x3);
-	mt76_rmw(dev, MT_WTBLOFF_TOP_RSCR(band), mask, set);
-}
-
-static u8
-mt7921_get_offload_capability(struct device *dev, const char *fw_wm)
-{
-	const struct mt76_connac2_fw_trailer *hdr;
-	struct mt7921_realease_info *rel_info;
-	const struct firmware *fw;
-	int ret, i, offset = 0;
-	const u8 *data, *end;
-	u8 offload_caps = 0;
-
-	ret = request_firmware(&fw, fw_wm, dev);
-	if (ret)
-		return ret;
-
-	if (!fw || !fw->data || fw->size < sizeof(*hdr)) {
-		dev_err(dev, "Invalid firmware\n");
-		goto out;
-	}
-
-	data = fw->data;
-	hdr = (const void *)(fw->data + fw->size - sizeof(*hdr));
-
-	for (i = 0; i < hdr->n_region; i++) {
-		const struct mt76_connac2_fw_region *region;
-
-		region = (const void *)((const u8 *)hdr -
-					(hdr->n_region - i) * sizeof(*region));
-		offset += le32_to_cpu(region->len);
-	}
-
-	data += offset + 16;
-	rel_info = (struct mt7921_realease_info *)data;
-	data += sizeof(*rel_info);
-	end = data + le16_to_cpu(rel_info->len);
-
-	while (data < end) {
-		rel_info = (struct mt7921_realease_info *)data;
-		data += sizeof(*rel_info);
-
-		if (rel_info->tag == MT7921_FW_TAG_FEATURE) {
-			struct mt7921_fw_features *features;
-
-			features = (struct mt7921_fw_features *)data;
-			offload_caps = features->data;
-			break;
-		}
-
-		data += le16_to_cpu(rel_info->len) + rel_info->pad_len;
-	}
-
-out:
-	release_firmware(fw);
-
-	return offload_caps;
-}
-
-struct ieee80211_ops *
-mt7921_get_mac80211_ops(struct device *dev, void *drv_data, u8 *fw_features)
-{
-	struct ieee80211_ops *ops;
-
-	ops = devm_kmemdup(dev, &mt7921_ops, sizeof(mt7921_ops), GFP_KERNEL);
-	if (!ops)
-		return NULL;
-
-	*fw_features = mt7921_get_offload_capability(dev, drv_data);
-	if (!(*fw_features & MT7921_FW_CAP_CNM)) {
-		ops->remain_on_channel = NULL;
-		ops->cancel_remain_on_channel = NULL;
-		ops->add_chanctx = NULL;
-		ops->remove_chanctx = NULL;
-		ops->change_chanctx = NULL;
-		ops->assign_vif_chanctx = NULL;
-		ops->unassign_vif_chanctx = NULL;
-		ops->mgd_prepare_tx = NULL;
-		ops->mgd_complete_tx = NULL;
-	}
-	return ops;
-}
-EXPORT_SYMBOL_GPL(mt7921_get_mac80211_ops);
-
 int mt7921_mac_init(struct mt792x_dev *dev)
 {
 	int i;
@@ -323,7 +93,7 @@ int mt7921_mac_init(struct mt792x_dev *dev)
 		mt7921_mac_wtbl_update(dev, i,
 				       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
 	for (i = 0; i < 2; i++)
-		mt7921_mac_init_band(dev, i);
+		mt792x_mac_init_band(dev, i);
 
 	return mt76_connac_mcu_set_rts_thresh(&dev->mt76, 0x92b, 0);
 }
@@ -374,23 +144,6 @@ static int mt7921_init_hardware(struct mt792x_dev *dev)
 	return 0;
 }
 
-static int mt7921_init_wcid(struct mt792x_dev *dev)
-{
-	int idx;
-
-	/* Beacon and mgmt frames should occupy wcid 0 */
-	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT792x_WTBL_STA - 1);
-	if (idx)
-		return -ENOSPC;
-
-	dev->mt76.global_wcid.idx = idx;
-	dev->mt76.global_wcid.hw_key_idx = -1;
-	dev->mt76.global_wcid.tx_info |= MT_WCID_TX_INFO_SET;
-	rcu_assign_pointer(dev->mt76.wcid[idx], &dev->mt76.global_wcid);
-
-	return 0;
-}
-
 static void mt7921_init_work(struct work_struct *work)
 {
 	struct mt792x_dev *dev = container_of(work, struct mt792x_dev,
@@ -479,14 +232,15 @@ int mt7921_register_device(struct mt792x_dev *dev)
 
 	mt7921_init_acpi_sar(dev);
 
-	ret = mt7921_init_wcid(dev);
+	ret = mt792x_init_wcid(dev);
 	if (ret)
 		return ret;
 
-	ret = mt7921_init_wiphy(hw);
+	ret = mt792x_init_wiphy(hw);
 	if (ret)
 		return ret;
 
+	hw->wiphy->reg_notifier = mt7921_regd_notifier;
 	dev->mphy.sband_2g.sband.ht_cap.cap |=
 			IEEE80211_HT_CAP_LDPC_CODING |
 			IEEE80211_HT_CAP_MAX_AMSDU;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index b8699c942b349..fc952c30ca079 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -22,9 +22,6 @@
 #define MT7921_MCU_INIT_RETRY_COUNT	10
 #define MT7921_WFSYS_INIT_RETRY_COUNT	2
 
-#define MT7921_FW_TAG_FEATURE		4
-#define MT7921_FW_CAP_CNM		BIT(7)
-
 #define MT7921_FIRMWARE_WM		"mediatek/WIFI_RAM_CODE_MT7961_1.bin"
 #define MT7921_ROM_PATCH		"mediatek/WIFI_MT7961_patch_mcu_1_2_hdr.bin"
 
@@ -400,6 +397,4 @@ int mt7921_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 		       enum mt7921_roc_req type, u8 token_id);
 int mt7921_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_vif *vif,
 			 u8 token_id);
-struct ieee80211_ops *mt7921_get_mac80211_ops(struct device *dev,
-					      void *drv_data, u8 *fw_features);
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 4d929cf8d8548..58f6f5a76498f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -288,8 +288,8 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 	if (mt7921_disable_aspm)
 		mt76_pci_disable_aspm(pdev);
 
-	ops = mt7921_get_mac80211_ops(&pdev->dev, (void *)id->driver_data,
-				      &features);
+	ops = mt792x_get_mac80211_ops(&pdev->dev, &mt7921_ops,
+				      (void *)id->driver_data, &features);
 	if (!ops) {
 		ret = -ENOMEM;
 		goto err_free_pci_vec;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index f0117ac345945..84b3886569419 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -127,8 +127,8 @@ static int mt7921s_probe(struct sdio_func *func,
 	u8 features;
 	int ret;
 
-	ops = mt7921_get_mac80211_ops(&func->dev, (void *)id->driver_data,
-				      &features);
+	ops = mt792x_get_mac80211_ops(&func->dev, &mt7921_ops,
+				      (void *)id->driver_data, &features);
 	if (!ops)
 		return -ENOMEM;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index c7368cf676a96..0a31e70763249 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -212,8 +212,8 @@ static int mt7921u_probe(struct usb_interface *usb_intf,
 	u8 features;
 	int ret;
 
-	ops = mt7921_get_mac80211_ops(&usb_intf->dev, (void *)id->driver_info,
-				      &features);
+	ops = mt792x_get_mac80211_ops(&usb_intf->dev, &mt7921_ops,
+				      (void *)id->driver_info, &features);
 	if (!ops)
 		return -ENOMEM;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 1fd53a29fef1f..f13779d199836 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -18,6 +18,9 @@
 #define MT792x_CFEND_RATE_DEFAULT	0x49	/* OFDM 24M */
 #define MT792x_CFEND_RATE_11B		0x03	/* 11B LP, 11M */
 
+#define MT792x_FW_TAG_FEATURE	4
+#define MT792x_FW_CAP_CNM	BIT(7)
+
 /* NOTE: used to map mt76_rates. idx may change if firmware expands table */
 #define MT792x_BASIC_RATES_TBL	11
 
@@ -26,6 +29,18 @@
 struct mt792x_vif;
 struct mt792x_sta;
 
+struct mt792x_realease_info {
+	__le16 len;
+	u8 pad_len;
+	u8 tag;
+} __packed;
+
+struct mt792x_fw_features {
+	u8 segment;
+	u8 data;
+	u8 rsv[14];
+} __packed;
+
 enum {
 	MT792x_CLC_POWER,
 	MT792x_CLC_CHAN,
@@ -183,6 +198,7 @@ static inline bool mt792x_dma_need_reinit(struct mt792x_dev *dev)
 void mt792x_reset(struct mt76_dev *mdev);
 void mt792x_update_channel(struct mt76_phy *mphy);
 void mt792x_mac_reset_counters(struct mt792x_phy *phy);
+void mt792x_mac_init_band(struct mt792x_dev *dev, u8 band);
 void mt792x_mac_assoc_rssi(struct mt792x_dev *dev, struct sk_buff *skb);
 struct mt76_wcid *mt792x_rx_get_wcid(struct mt792x_dev *dev, u16 idx,
 				     bool unicast);
@@ -235,5 +251,11 @@ int mt792x_queues_read(struct seq_file *s, void *data);
 int mt792x_pm_stats(struct seq_file *s, void *data);
 int mt792x_pm_idle_timeout_set(void *data, u64 val);
 int mt792x_pm_idle_timeout_get(void *data, u64 *val);
+int mt792x_init_wiphy(struct ieee80211_hw *hw);
+struct ieee80211_ops *
+mt792x_get_mac80211_ops(struct device *dev,
+			const struct ieee80211_ops *mac80211_ops,
+			void *drv_data, u8 *fw_features);
+int mt792x_init_wcid(struct mt792x_dev *dev);
 
 #endif /* __MT7925_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index b176ce53996e4..87d2a614e5905 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -2,10 +2,55 @@
 /* Copyright (C) 2023 MediaTek Inc. */
 
 #include <linux/module.h>
+#include <linux/firmware.h>
 
 #include "mt792x.h"
 #include "dma.h"
 
+static const struct ieee80211_iface_limit if_limits[] = {
+	{
+		.max = MT792x_MAX_INTERFACES,
+		.types = BIT(NL80211_IFTYPE_STATION)
+	},
+	{
+		.max = 1,
+		.types = BIT(NL80211_IFTYPE_AP)
+	}
+};
+
+static const struct ieee80211_iface_combination if_comb[] = {
+	{
+		.limits = if_limits,
+		.n_limits = ARRAY_SIZE(if_limits),
+		.max_interfaces = MT792x_MAX_INTERFACES,
+		.num_different_channels = 1,
+		.beacon_int_infra_match = true,
+	},
+};
+
+static const struct ieee80211_iface_limit if_limits_chanctx[] = {
+	{
+		.max = 2,
+		.types = BIT(NL80211_IFTYPE_STATION) |
+			 BIT(NL80211_IFTYPE_P2P_CLIENT)
+	},
+	{
+		.max = 1,
+		.types = BIT(NL80211_IFTYPE_AP) |
+			 BIT(NL80211_IFTYPE_P2P_GO)
+	}
+};
+
+static const struct ieee80211_iface_combination if_comb_chanctx[] = {
+	{
+		.limits = if_limits_chanctx,
+		.n_limits = ARRAY_SIZE(if_limits_chanctx),
+		.max_interfaces = 2,
+		.num_different_channels = 2,
+		.beacon_int_infra_match = false,
+	}
+};
+
 void mt792x_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
 	       struct sk_buff *skb)
 {
@@ -561,5 +606,187 @@ int mt792x_wfsys_reset(struct mt792x_dev *dev, u32 addr)
 }
 EXPORT_SYMBOL_GPL(mt792x_wfsys_reset);
 
+int mt792x_init_wiphy(struct ieee80211_hw *hw)
+{
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
+	struct mt792x_dev *dev = phy->dev;
+	struct wiphy *wiphy = hw->wiphy;
+
+	hw->queues = 4;
+	if (dev->has_eht) {
+		hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_EHT;
+		hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_EHT;
+	} else {
+		hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
+		hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
+	}
+	hw->netdev_features = NETIF_F_RXCSUM;
+
+	hw->radiotap_timestamp.units_pos =
+		IEEE80211_RADIOTAP_TIMESTAMP_UNIT_US;
+
+	phy->slottime = 9;
+
+	hw->sta_data_size = sizeof(struct mt792x_sta);
+	hw->vif_data_size = sizeof(struct mt792x_vif);
+
+	if (dev->fw_features & MT792x_FW_CAP_CNM) {
+		wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
+		wiphy->iface_combinations = if_comb_chanctx;
+		wiphy->n_iface_combinations = ARRAY_SIZE(if_comb_chanctx);
+	} else {
+		wiphy->flags &= ~WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
+		wiphy->iface_combinations = if_comb;
+		wiphy->n_iface_combinations = ARRAY_SIZE(if_comb);
+	}
+	wiphy->flags &= ~(WIPHY_FLAG_IBSS_RSN | WIPHY_FLAG_4ADDR_AP |
+			  WIPHY_FLAG_4ADDR_STATION);
+	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) |
+				 BIT(NL80211_IFTYPE_AP) |
+				 BIT(NL80211_IFTYPE_P2P_CLIENT) |
+				 BIT(NL80211_IFTYPE_P2P_GO);
+	wiphy->max_remain_on_channel_duration = 5000;
+	wiphy->max_scan_ie_len = MT76_CONNAC_SCAN_IE_LEN;
+	wiphy->max_scan_ssids = 4;
+	wiphy->max_sched_scan_plan_interval =
+		MT76_CONNAC_MAX_TIME_SCHED_SCAN_INTERVAL;
+	wiphy->max_sched_scan_ie_len = IEEE80211_MAX_DATA_LEN;
+	wiphy->max_sched_scan_ssids = MT76_CONNAC_MAX_SCHED_SCAN_SSID;
+	wiphy->max_match_sets = MT76_CONNAC_MAX_SCAN_MATCH;
+	wiphy->max_sched_scan_reqs = 1;
+	wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH |
+			WIPHY_FLAG_SPLIT_SCAN_6GHZ;
+
+	wiphy->features |= NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR |
+			   NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR;
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_SET_SCAN_DWELL);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_LEGACY);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_HT);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_VHT);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_HE);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0);
+
+	ieee80211_hw_set(hw, SINGLE_SCAN_ON_ALL_BANDS);
+	ieee80211_hw_set(hw, HAS_RATE_CONTROL);
+	ieee80211_hw_set(hw, SUPPORTS_TX_ENCAP_OFFLOAD);
+	ieee80211_hw_set(hw, SUPPORTS_RX_DECAP_OFFLOAD);
+	ieee80211_hw_set(hw, WANT_MONITOR_VIF);
+	ieee80211_hw_set(hw, SUPPORTS_PS);
+	ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS);
+	ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW);
+	ieee80211_hw_set(hw, CONNECTION_MONITOR);
+
+	if (dev->pm.enable)
+		ieee80211_hw_set(hw, CONNECTION_MONITOR);
+
+	hw->max_tx_fragments = 4;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_init_wiphy);
+
+static u8
+mt792x_get_offload_capability(struct device *dev, const char *fw_wm)
+{
+	const struct mt76_connac2_fw_trailer *hdr;
+	struct mt792x_realease_info *rel_info;
+	const struct firmware *fw;
+	int ret, i, offset = 0;
+	const u8 *data, *end;
+	u8 offload_caps = 0;
+
+	ret = request_firmware(&fw, fw_wm, dev);
+	if (ret)
+		return ret;
+
+	if (!fw || !fw->data || fw->size < sizeof(*hdr)) {
+		dev_err(dev, "Invalid firmware\n");
+		goto out;
+	}
+
+	data = fw->data;
+	hdr = (const void *)(fw->data + fw->size - sizeof(*hdr));
+
+	for (i = 0; i < hdr->n_region; i++) {
+		const struct mt76_connac2_fw_region *region;
+
+		region = (const void *)((const u8 *)hdr -
+					(hdr->n_region - i) * sizeof(*region));
+		offset += le32_to_cpu(region->len);
+	}
+
+	data += offset + 16;
+	rel_info = (struct mt792x_realease_info *)data;
+	data += sizeof(*rel_info);
+	end = data + le16_to_cpu(rel_info->len);
+
+	while (data < end) {
+		rel_info = (struct mt792x_realease_info *)data;
+		data += sizeof(*rel_info);
+
+		if (rel_info->tag == MT792x_FW_TAG_FEATURE) {
+			struct mt792x_fw_features *features;
+
+			features = (struct mt792x_fw_features *)data;
+			offload_caps = features->data;
+			break;
+		}
+
+		data += le16_to_cpu(rel_info->len) + rel_info->pad_len;
+	}
+
+out:
+	release_firmware(fw);
+
+	return offload_caps;
+}
+
+struct ieee80211_ops *
+mt792x_get_mac80211_ops(struct device *dev,
+			const struct ieee80211_ops *mac80211_ops,
+			void *drv_data, u8 *fw_features)
+{
+	struct ieee80211_ops *ops;
+
+	ops = devm_kmemdup(dev, mac80211_ops, sizeof(struct ieee80211_ops),
+			   GFP_KERNEL);
+	if (!ops)
+		return NULL;
+
+	*fw_features = mt792x_get_offload_capability(dev, drv_data);
+	if (!(*fw_features & MT792x_FW_CAP_CNM)) {
+		ops->remain_on_channel = NULL;
+		ops->cancel_remain_on_channel = NULL;
+		ops->add_chanctx = NULL;
+		ops->remove_chanctx = NULL;
+		ops->change_chanctx = NULL;
+		ops->assign_vif_chanctx = NULL;
+		ops->unassign_vif_chanctx = NULL;
+		ops->mgd_prepare_tx = NULL;
+		ops->mgd_complete_tx = NULL;
+	}
+	return ops;
+}
+EXPORT_SYMBOL_GPL(mt792x_get_mac80211_ops);
+
+int mt792x_init_wcid(struct mt792x_dev *dev)
+{
+	int idx;
+
+	/* Beacon and mgmt frames should occupy wcid 0 */
+	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT792x_WTBL_STA - 1);
+	if (idx)
+		return -ENOSPC;
+
+	dev->mt76.global_wcid.idx = idx;
+	dev->mt76.global_wcid.hw_key_idx = -1;
+	dev->mt76.global_wcid.tx_info |= MT_WCID_TX_INFO_SET;
+	rcu_assign_pointer(dev->mt76.wcid[idx], &dev->mt76.global_wcid);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_init_wcid);
+
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
index 130b4352cf92d..9603c4eedb2bc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
@@ -282,3 +282,32 @@ void mt792x_reset(struct mt76_dev *mdev)
 	queue_work(dev->mt76.wq, &dev->reset_work);
 }
 EXPORT_SYMBOL_GPL(mt792x_reset);
+
+void mt792x_mac_init_band(struct mt792x_dev *dev, u8 band)
+{
+	u32 mask, set;
+
+	mt76_rmw_field(dev, MT_TMAC_CTCR0(band),
+		       MT_TMAC_CTCR0_INS_DDLMT_REFTIME, 0x3f);
+	mt76_set(dev, MT_TMAC_CTCR0(band),
+		 MT_TMAC_CTCR0_INS_DDLMT_VHT_SMPDU_EN |
+		 MT_TMAC_CTCR0_INS_DDLMT_EN);
+
+	mt76_set(dev, MT_WF_RMAC_MIB_TIME0(band), MT_WF_RMAC_MIB_RXTIME_EN);
+	mt76_set(dev, MT_WF_RMAC_MIB_AIRTIME0(band), MT_WF_RMAC_MIB_RXTIME_EN);
+
+	/* enable MIB tx-rx time reporting */
+	mt76_set(dev, MT_MIB_SCR1(band), MT_MIB_TXDUR_EN);
+	mt76_set(dev, MT_MIB_SCR1(band), MT_MIB_RXDUR_EN);
+
+	mt76_rmw_field(dev, MT_DMA_DCR0(band), MT_DMA_DCR0_MAX_RX_LEN, 1536);
+	/* disable rx rate report by default due to hw issues */
+	mt76_clear(dev, MT_DMA_DCR0(band), MT_DMA_DCR0_RXD_G5_EN);
+
+	/* filter out non-resp frames and get instantaneous signal reporting */
+	mask = MT_WTBLOFF_TOP_RSCR_RCPI_MODE | MT_WTBLOFF_TOP_RSCR_RCPI_PARAM;
+	set = FIELD_PREP(MT_WTBLOFF_TOP_RSCR_RCPI_MODE, 0) |
+	      FIELD_PREP(MT_WTBLOFF_TOP_RSCR_RCPI_PARAM, 0x3);
+	mt76_rmw(dev, MT_WTBLOFF_TOP_RSCR(band), mask, set);
+}
+EXPORT_SYMBOL_GPL(mt792x_mac_init_band);
-- 
GitLab


From c9072f112fcf7b31c33a0097a3e020fe077f82bf Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:06:02 +0800
Subject: [PATCH 0472/1806] wifi: mt76: mt792x: introduce mt792x_irq_map

mt792x_irq_map will be use to share the irq code shared between mt7921
and mt7925

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/dma.c   |  9 ++--
 .../net/wireless/mediatek/mt76/mt7921/pci.c   | 53 ++++++++++++-------
 .../wireless/mediatek/mt76/mt7921/pci_mac.c   |  8 +--
 .../net/wireless/mediatek/mt76/mt7921/regs.h  | 17 ------
 drivers/net/wireless/mediatek/mt76/mt792x.h   | 14 +++++
 .../net/wireless/mediatek/mt76/mt792x_regs.h  | 19 +++++++
 6 files changed, 77 insertions(+), 43 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
index 9dcda35cdf73b..1ac66526eb02c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
@@ -19,7 +19,8 @@ static int mt7921_poll_tx(struct napi_struct *napi, int budget)
 
 	mt76_connac_tx_cleanup(&dev->mt76);
 	if (napi_complete(napi))
-		mt76_connac_irq_enable(&dev->mt76, MT_INT_TX_DONE_ALL);
+		mt76_connac_irq_enable(&dev->mt76,
+				       dev->irq_map->tx.all_complete_mask);
 	mt76_connac_pm_unref(&dev->mphy, &dev->pm);
 
 	return 0;
@@ -72,8 +73,8 @@ static int mt7921_dma_enable(struct mt792x_dev *dev)
 
 	/* enable interrupts for TX/RX rings */
 	mt76_connac_irq_enable(&dev->mt76,
-			       MT_INT_RX_DONE_ALL | MT_INT_TX_DONE_ALL |
-			       MT_INT_MCU_CMD);
+			       dev->irq_map->tx.all_complete_mask |
+			       MT_INT_RX_DONE_ALL | MT_INT_MCU_CMD);
 	mt76_set(dev, MT_MCU2HOST_SW_INT_ENA, MT_MCU_CMD_WAKE_RX_PCIE);
 
 	return 0;
@@ -139,7 +140,7 @@ int mt7921_wpdma_reinit_cond(struct mt792x_dev *dev)
 	/* check if the wpdma must be reinitialized */
 	if (mt792x_dma_need_reinit(dev)) {
 		/* disable interrutpts */
-		mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0);
+		mt76_wr(dev, dev->irq_map->host_irq_enable, 0);
 		mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0);
 
 		err = mt7921_wpdma_reset(dev, false);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 58f6f5a76498f..606a7e41a2403 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -31,19 +31,22 @@ MODULE_PARM_DESC(disable_aspm, "disable PCI ASPM support");
 static void
 mt7921_rx_poll_complete(struct mt76_dev *mdev, enum mt76_rxq_id q)
 {
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
+	const struct mt792x_irq_map *irq_map = dev->irq_map;
+
 	if (q == MT_RXQ_MAIN)
-		mt76_connac_irq_enable(mdev, MT_INT_RX_DONE_DATA);
+		mt76_connac_irq_enable(mdev, irq_map->rx.data_complete_mask);
 	else if (q == MT_RXQ_MCU_WA)
-		mt76_connac_irq_enable(mdev, MT_INT_RX_DONE_WM2);
+		mt76_connac_irq_enable(mdev, irq_map->rx.wm2_complete_mask);
 	else
-		mt76_connac_irq_enable(mdev, MT_INT_RX_DONE_WM);
+		mt76_connac_irq_enable(mdev, irq_map->rx.wm_complete_mask);
 }
 
 static irqreturn_t mt7921_irq_handler(int irq, void *dev_instance)
 {
 	struct mt792x_dev *dev = dev_instance;
 
-	mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0);
+	mt76_wr(dev, dev->irq_map->host_irq_enable, 0);
 
 	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state))
 		return IRQ_NONE;
@@ -56,9 +59,10 @@ static irqreturn_t mt7921_irq_handler(int irq, void *dev_instance)
 static void mt7921_irq_tasklet(unsigned long data)
 {
 	struct mt792x_dev *dev = (struct mt792x_dev *)data;
+	const struct mt792x_irq_map *irq_map = dev->irq_map;
 	u32 intr, mask = 0;
 
-	mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0);
+	mt76_wr(dev, irq_map->host_irq_enable, 0);
 
 	intr = mt76_rr(dev, MT_WFDMA0_HOST_INT_STA);
 	intr &= dev->mt76.mmio.irqmask;
@@ -67,8 +71,8 @@ static void mt7921_irq_tasklet(unsigned long data)
 	trace_dev_irq(&dev->mt76, intr, dev->mt76.mmio.irqmask);
 
 	mask |= intr & MT_INT_RX_DONE_ALL;
-	if (intr & MT_INT_TX_DONE_MCU)
-		mask |= MT_INT_TX_DONE_MCU;
+	if (intr & irq_map->tx.mcu_complete_mask)
+		mask |= irq_map->tx.mcu_complete_mask;
 
 	if (intr & MT_INT_MCU_CMD) {
 		u32 intr_sw;
@@ -77,23 +81,23 @@ static void mt7921_irq_tasklet(unsigned long data)
 		/* ack MCU2HOST_SW_INT_STA */
 		mt76_wr(dev, MT_MCU_CMD, intr_sw);
 		if (intr_sw & MT_MCU_CMD_WAKE_RX_PCIE) {
-			mask |= MT_INT_RX_DONE_DATA;
-			intr |= MT_INT_RX_DONE_DATA;
+			mask |= irq_map->rx.data_complete_mask;
+			intr |= irq_map->rx.data_complete_mask;
 		}
 	}
 
-	mt76_set_irq_mask(&dev->mt76, MT_WFDMA0_HOST_INT_ENA, mask, 0);
+	mt76_set_irq_mask(&dev->mt76, irq_map->host_irq_enable, mask, 0);
 
-	if (intr & MT_INT_TX_DONE_ALL)
+	if (intr & irq_map->tx.all_complete_mask)
 		napi_schedule(&dev->mt76.tx_napi);
 
-	if (intr & MT_INT_RX_DONE_WM)
+	if (intr & irq_map->rx.wm_complete_mask)
 		napi_schedule(&dev->mt76.napi[MT_RXQ_MCU]);
 
-	if (intr & MT_INT_RX_DONE_WM2)
+	if (intr & irq_map->rx.wm2_complete_mask)
 		napi_schedule(&dev->mt76.napi[MT_RXQ_MCU_WA]);
 
-	if (intr & MT_INT_RX_DONE_DATA)
+	if (intr & irq_map->rx.data_complete_mask)
 		napi_schedule(&dev->mt76.napi[MT_RXQ_MAIN]);
 }
 
@@ -254,6 +258,18 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 		.drv_own = mt7921e_mcu_drv_pmctrl,
 		.fw_own = mt7921e_mcu_fw_pmctrl,
 	};
+	static const struct mt792x_irq_map irq_map = {
+		.host_irq_enable = MT_WFDMA0_HOST_INT_ENA,
+		.tx = {
+			.all_complete_mask = MT_INT_TX_DONE_ALL,
+			.mcu_complete_mask = MT_INT_TX_DONE_MCU,
+		},
+		.rx = {
+			.data_complete_mask = MT_INT_RX_DONE_DATA,
+			.wm_complete_mask = MT_INT_RX_DONE_WM,
+			.wm2_complete_mask = MT_INT_RX_DONE_WM2,
+		},
+	};
 	struct ieee80211_ops *ops;
 	struct mt76_bus_ops *bus_ops;
 	struct mt792x_dev *dev;
@@ -306,6 +322,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 	dev = container_of(mdev, struct mt792x_dev, mt76);
 	dev->fw_features = features;
 	dev->hif_ops = &mt7921_pcie_ops;
+	dev->irq_map = &irq_map;
 	mt76_mmio_init(&dev->mt76, pcim_iomap_table(pdev)[0]);
 	tasklet_init(&mdev->irq_tasklet, mt7921_irq_tasklet, (unsigned long)dev);
 
@@ -341,7 +358,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		goto err_free_dev;
 
-	mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0);
+	mt76_wr(dev, irq_map.host_irq_enable, 0);
 
 	mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
 
@@ -424,7 +441,7 @@ static int mt7921_pci_suspend(struct device *device)
 		   MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN);
 
 	/* disable interrupt */
-	mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0);
+	mt76_wr(dev, dev->irq_map->host_irq_enable, 0);
 	mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0);
 	synchronize_irq(pdev->irq);
 	tasklet_kill(&mdev->irq_tasklet);
@@ -472,8 +489,8 @@ static int mt7921_pci_resume(struct device *device)
 	/* enable interrupt */
 	mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
 	mt76_connac_irq_enable(&dev->mt76,
-			       MT_INT_RX_DONE_ALL | MT_INT_TX_DONE_ALL |
-			       MT_INT_MCU_CMD);
+			       dev->irq_map->tx.all_complete_mask |
+			       MT_INT_RX_DONE_ALL | MT_INT_MCU_CMD);
 	mt76_set(dev, MT_MCU2HOST_SW_INT_ENA, MT_MCU_CMD_WAKE_RX_PCIE);
 
 	/* put dma enabled */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
index 7323388327f40..1f508244d6157 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
@@ -61,7 +61,7 @@ int mt7921e_mac_reset(struct mt792x_dev *dev)
 
 	mt76_connac_free_pending_tx_skbs(&dev->pm, NULL);
 
-	mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0);
+	mt76_wr(dev, dev->irq_map->host_irq_enable, 0);
 	mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0);
 
 	set_bit(MT76_RESET, &dev->mphy.state);
@@ -92,9 +92,9 @@ int mt7921e_mac_reset(struct mt792x_dev *dev)
 	dev->fw_assert = false;
 	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
 
-	mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA,
-		MT_INT_RX_DONE_ALL | MT_INT_TX_DONE_ALL |
-		MT_INT_MCU_CMD);
+	mt76_wr(dev, dev->irq_map->host_irq_enable,
+		dev->irq_map->tx.all_complete_mask |
+		MT_INT_RX_DONE_ALL | MT_INT_MCU_CMD);
 	mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
 
 	err = mt7921e_driver_own(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
index 083d655f82e50..43427a3a48af0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
@@ -29,18 +29,6 @@
 #define MT_MDP_TO_WM			1
 
 #define MT_WFDMA0_HOST_INT_ENA		MT_WFDMA0(0x204)
-#define HOST_RX_DONE_INT_ENA0		BIT(0)
-#define HOST_RX_DONE_INT_ENA1		BIT(1)
-#define HOST_RX_DONE_INT_ENA2		BIT(2)
-#define HOST_RX_DONE_INT_ENA3		BIT(3)
-#define HOST_TX_DONE_INT_ENA0		BIT(4)
-#define HOST_TX_DONE_INT_ENA1		BIT(5)
-#define HOST_TX_DONE_INT_ENA2		BIT(6)
-#define HOST_TX_DONE_INT_ENA3		BIT(7)
-#define HOST_TX_DONE_INT_ENA4		BIT(8)
-#define HOST_TX_DONE_INT_ENA5		BIT(9)
-#define HOST_TX_DONE_INT_ENA6		BIT(10)
-#define HOST_TX_DONE_INT_ENA7		BIT(11)
 #define HOST_TX_DONE_INT_ENA8		BIT(12)
 #define HOST_TX_DONE_INT_ENA9		BIT(13)
 #define HOST_TX_DONE_INT_ENA10		BIT(14)
@@ -48,14 +36,10 @@
 #define HOST_TX_DONE_INT_ENA12		BIT(16)
 #define HOST_TX_DONE_INT_ENA13		BIT(17)
 #define HOST_TX_DONE_INT_ENA14		BIT(18)
-#define HOST_RX_COHERENT_EN		BIT(20)
-#define HOST_TX_COHERENT_EN		BIT(21)
 #define HOST_RX_DONE_INT_ENA4		BIT(22)
 #define HOST_RX_DONE_INT_ENA5		BIT(23)
 #define HOST_TX_DONE_INT_ENA16		BIT(26)
 #define HOST_TX_DONE_INT_ENA17		BIT(27)
-#define MCU2HOST_SW_INT_ENA		BIT(29)
-#define HOST_TX_DONE_INT_ENA18		BIT(30)
 
 /* WFDMA interrupt */
 #define MT_INT_RX_DONE_DATA		HOST_RX_DONE_INT_ENA2
@@ -67,7 +51,6 @@
 #define MT_INT_TX_DONE_MCU_WM		HOST_TX_DONE_INT_ENA17
 #define MT_INT_TX_DONE_FWDL		HOST_TX_DONE_INT_ENA16
 #define MT_INT_TX_DONE_BAND0		HOST_TX_DONE_INT_ENA0
-#define MT_INT_MCU_CMD			MCU2HOST_SW_INT_ENA
 
 #define MT_INT_TX_DONE_MCU		(MT_INT_TX_DONE_MCU_WM |	\
 					 MT_INT_TX_DONE_FWDL)
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index f13779d199836..6fd1f542da178 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -114,6 +114,19 @@ struct mt792x_phy {
 	bool roc_grant;
 };
 
+struct mt792x_irq_map {
+	u32 host_irq_enable;
+	struct {
+		u32 all_complete_mask;
+		u32 mcu_complete_mask;
+	} tx;
+	struct {
+		u32 data_complete_mask;
+		u32 wm_complete_mask;
+		u32 wm2_complete_mask;
+	} rx;
+};
+
 struct mt792x_hif_ops {
 	int (*init_reset)(struct mt792x_dev *dev);
 	int (*reset)(struct mt792x_dev *dev);
@@ -145,6 +158,7 @@ struct mt792x_dev {
 	struct mt76_connac_pm pm;
 	struct mt76_connac_coredump coredump;
 	const struct mt792x_hif_ops *hif_ops;
+	const struct mt792x_irq_map *irq_map;
 
 	struct work_struct ipv6_ns_work;
 	/* IPv6 addresses for WoWLAN */
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
index 9c6308ef4cb39..a99af23e4b564 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h
@@ -301,6 +301,25 @@
 #define MT_WFDMA0_GLO_CFG_OMIT_TX_INFO	BIT(28)
 #define MT_WFDMA0_GLO_CFG_CLK_GAT_DIS	BIT(30)
 
+#define HOST_RX_DONE_INT_ENA0		BIT(0)
+#define HOST_RX_DONE_INT_ENA1		BIT(1)
+#define HOST_RX_DONE_INT_ENA2		BIT(2)
+#define HOST_RX_DONE_INT_ENA3		BIT(3)
+#define HOST_TX_DONE_INT_ENA0		BIT(4)
+#define HOST_TX_DONE_INT_ENA1		BIT(5)
+#define HOST_TX_DONE_INT_ENA2		BIT(6)
+#define HOST_TX_DONE_INT_ENA3		BIT(7)
+#define HOST_TX_DONE_INT_ENA4		BIT(8)
+#define HOST_TX_DONE_INT_ENA5		BIT(9)
+#define HOST_TX_DONE_INT_ENA6		BIT(10)
+#define HOST_TX_DONE_INT_ENA7		BIT(11)
+#define HOST_RX_COHERENT_EN		BIT(20)
+#define HOST_TX_COHERENT_EN		BIT(21)
+#define MCU2HOST_SW_INT_ENA		BIT(29)
+#define HOST_TX_DONE_INT_ENA18		BIT(30)
+
+#define MT_INT_MCU_CMD			MCU2HOST_SW_INT_ENA
+
 #define MT_WFDMA0_RST_DTX_PTR		MT_WFDMA0(0x20c)
 #define MT_WFDMA0_RST_DRX_PTR		MT_WFDMA0(0x280)
 #define MT_WFDMA0_GLO_CFG_EXT0		MT_WFDMA0(0x2b0)
-- 
GitLab


From ff6551740000eac6a63445d30d5bac5c0ca900c3 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:14 +0800
Subject: [PATCH 0473/1806] wifi: mt76: mt792x: move more dma shared code in
 mt792x_dma

Rely on irq_map support, move more dma shared code between mt7921 and
mt7925 in mt792x_dma.c
Move the following dma code in mt792x-lib
- mt792x_dma_enable
- mt792x_dma_reset
- mt792x_wpdma_reset
- mt792x_wpdma_reinit_cond

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/Makefile   |   2 +-
 .../net/wireless/mediatek/mt76/mt7921/dma.c   | 156 +-------
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |   2 -
 .../net/wireless/mediatek/mt76/mt7921/pci.c   |  88 +----
 .../wireless/mediatek/mt76/mt7921/pci_mac.c   |   2 +-
 .../wireless/mediatek/mt76/mt7921/pci_mcu.c   |   2 +-
 drivers/net/wireless/mediatek/mt76/mt792x.h   |   9 +-
 .../net/wireless/mediatek/mt76/mt792x_core.c  |  96 -----
 .../net/wireless/mediatek/mt76/mt792x_dma.c   | 344 ++++++++++++++++++
 9 files changed, 364 insertions(+), 337 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt792x_dma.c

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index a45853ab958f4..d6231948dd6ee 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -32,7 +32,7 @@ mt76x02-usb-y := mt76x02_usb_mcu.o mt76x02_usb_core.o
 mt76-connac-lib-y := mt76_connac_mcu.o mt76_connac_mac.o mt76_connac3_mac.o
 
 mt792x-lib-y := mt792x_core.o mt792x_mac.o mt792x_trace.o \
-		mt792x_debugfs.o
+		mt792x_debugfs.o mt792x_dma.o
 
 obj-$(CONFIG_MT76x0_COMMON) += mt76x0/
 obj-$(CONFIG_MT76x2_COMMON) += mt76x2/
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
index 1ac66526eb02c..fdc598e099f66 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
@@ -5,158 +5,6 @@
 #include "../dma.h"
 #include "../mt76_connac2_mac.h"
 
-static int mt7921_poll_tx(struct napi_struct *napi, int budget)
-{
-	struct mt792x_dev *dev;
-
-	dev = container_of(napi, struct mt792x_dev, mt76.tx_napi);
-
-	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
-		napi_complete(napi);
-		queue_work(dev->mt76.wq, &dev->pm.wake_work);
-		return 0;
-	}
-
-	mt76_connac_tx_cleanup(&dev->mt76);
-	if (napi_complete(napi))
-		mt76_connac_irq_enable(&dev->mt76,
-				       dev->irq_map->tx.all_complete_mask);
-	mt76_connac_pm_unref(&dev->mphy, &dev->pm);
-
-	return 0;
-}
-
-static void mt7921_dma_prefetch(struct mt792x_dev *dev)
-{
-#define PREFETCH(base, depth)	((base) << 16 | (depth))
-
-	mt76_wr(dev, MT_WFDMA0_RX_RING0_EXT_CTRL, PREFETCH(0x0, 0x4));
-	mt76_wr(dev, MT_WFDMA0_RX_RING2_EXT_CTRL, PREFETCH(0x40, 0x4));
-	mt76_wr(dev, MT_WFDMA0_RX_RING3_EXT_CTRL, PREFETCH(0x80, 0x4));
-	mt76_wr(dev, MT_WFDMA0_RX_RING4_EXT_CTRL, PREFETCH(0xc0, 0x4));
-	mt76_wr(dev, MT_WFDMA0_RX_RING5_EXT_CTRL, PREFETCH(0x100, 0x4));
-
-	mt76_wr(dev, MT_WFDMA0_TX_RING0_EXT_CTRL, PREFETCH(0x140, 0x4));
-	mt76_wr(dev, MT_WFDMA0_TX_RING1_EXT_CTRL, PREFETCH(0x180, 0x4));
-	mt76_wr(dev, MT_WFDMA0_TX_RING2_EXT_CTRL, PREFETCH(0x1c0, 0x4));
-	mt76_wr(dev, MT_WFDMA0_TX_RING3_EXT_CTRL, PREFETCH(0x200, 0x4));
-	mt76_wr(dev, MT_WFDMA0_TX_RING4_EXT_CTRL, PREFETCH(0x240, 0x4));
-	mt76_wr(dev, MT_WFDMA0_TX_RING5_EXT_CTRL, PREFETCH(0x280, 0x4));
-	mt76_wr(dev, MT_WFDMA0_TX_RING6_EXT_CTRL, PREFETCH(0x2c0, 0x4));
-	mt76_wr(dev, MT_WFDMA0_TX_RING16_EXT_CTRL, PREFETCH(0x340, 0x4));
-	mt76_wr(dev, MT_WFDMA0_TX_RING17_EXT_CTRL, PREFETCH(0x380, 0x4));
-}
-
-static int mt7921_dma_enable(struct mt792x_dev *dev)
-{
-	/* configure perfetch settings */
-	mt7921_dma_prefetch(dev);
-
-	/* reset dma idx */
-	mt76_wr(dev, MT_WFDMA0_RST_DTX_PTR, ~0);
-
-	/* configure delay interrupt */
-	mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG0, 0);
-
-	mt76_set(dev, MT_WFDMA0_GLO_CFG,
-		 MT_WFDMA0_GLO_CFG_TX_WB_DDONE |
-		 MT_WFDMA0_GLO_CFG_FIFO_LITTLE_ENDIAN |
-		 MT_WFDMA0_GLO_CFG_CLK_GAT_DIS |
-		 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-		 MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN |
-		 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
-
-	mt76_set(dev, MT_WFDMA0_GLO_CFG,
-		 MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN);
-
-	mt76_set(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT);
-
-	/* enable interrupts for TX/RX rings */
-	mt76_connac_irq_enable(&dev->mt76,
-			       dev->irq_map->tx.all_complete_mask |
-			       MT_INT_RX_DONE_ALL | MT_INT_MCU_CMD);
-	mt76_set(dev, MT_MCU2HOST_SW_INT_ENA, MT_MCU_CMD_WAKE_RX_PCIE);
-
-	return 0;
-}
-
-static int mt7921_dma_reset(struct mt792x_dev *dev, bool force)
-{
-	int i, err;
-
-	err = mt792x_dma_disable(dev, force);
-	if (err)
-		return err;
-
-	/* reset hw queues */
-	for (i = 0; i < __MT_TXQ_MAX; i++)
-		mt76_queue_reset(dev, dev->mphy.q_tx[i]);
-
-	for (i = 0; i < __MT_MCUQ_MAX; i++)
-		mt76_queue_reset(dev, dev->mt76.q_mcu[i]);
-
-	mt76_for_each_q_rx(&dev->mt76, i)
-		mt76_queue_reset(dev, &dev->mt76.q_rx[i]);
-
-	mt76_tx_status_check(&dev->mt76, true);
-
-	return mt7921_dma_enable(dev);
-}
-
-int mt7921_wpdma_reset(struct mt792x_dev *dev, bool force)
-{
-	int i, err;
-
-	/* clean up hw queues */
-	for (i = 0; i < ARRAY_SIZE(dev->mt76.phy.q_tx); i++)
-		mt76_queue_tx_cleanup(dev, dev->mphy.q_tx[i], true);
-
-	for (i = 0; i < ARRAY_SIZE(dev->mt76.q_mcu); i++)
-		mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[i], true);
-
-	mt76_for_each_q_rx(&dev->mt76, i)
-		mt76_queue_rx_cleanup(dev, &dev->mt76.q_rx[i]);
-
-	if (force) {
-		err = mt792x_wfsys_reset(dev, MT_WFSYS_SW_RST_B);
-		if (err)
-			return err;
-	}
-	err = mt7921_dma_reset(dev, force);
-	if (err)
-		return err;
-
-	mt76_for_each_q_rx(&dev->mt76, i)
-		mt76_queue_rx_reset(dev, i);
-
-	return 0;
-}
-
-int mt7921_wpdma_reinit_cond(struct mt792x_dev *dev)
-{
-	struct mt76_connac_pm *pm = &dev->pm;
-	int err;
-
-	/* check if the wpdma must be reinitialized */
-	if (mt792x_dma_need_reinit(dev)) {
-		/* disable interrutpts */
-		mt76_wr(dev, dev->irq_map->host_irq_enable, 0);
-		mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0);
-
-		err = mt7921_wpdma_reset(dev, false);
-		if (err) {
-			dev_err(dev->mt76.dev, "wpdma reset failed\n");
-			return err;
-		}
-
-		/* enable interrutpts */
-		mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
-		pm->stats.lp_wake++;
-	}
-
-	return 0;
-}
-
 int mt7921_dma_init(struct mt792x_dev *dev)
 {
 	int ret;
@@ -216,8 +64,8 @@ int mt7921_dma_init(struct mt792x_dev *dev)
 		return ret;
 
 	netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi,
-			  mt7921_poll_tx);
+			  mt792x_poll_tx);
 	napi_enable(&dev->mt76.tx_napi);
 
-	return mt7921_dma_enable(dev);
+	return mt792x_dma_enable(dev);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index fc952c30ca079..b797d8bab5e23 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -203,8 +203,6 @@ int __mt7921_start(struct mt792x_phy *phy);
 int mt7921_register_device(struct mt792x_dev *dev);
 void mt7921_unregister_device(struct mt792x_dev *dev);
 int mt7921_dma_init(struct mt792x_dev *dev);
-int mt7921_wpdma_reset(struct mt792x_dev *dev, bool force);
-int mt7921_wpdma_reinit_cond(struct mt792x_dev *dev);
 int mt7921_run_firmware(struct mt792x_dev *dev);
 int mt7921_mcu_set_bss_pm(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 			  bool enable);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 606a7e41a2403..d11406c87df73 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -10,7 +10,6 @@
 #include "mt7921.h"
 #include "../mt76_connac2_mac.h"
 #include "mcu.h"
-#include "../trace.h"
 
 static const struct pci_device_id mt7921_pci_device_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7961),
@@ -28,82 +27,9 @@ static bool mt7921_disable_aspm;
 module_param_named(disable_aspm, mt7921_disable_aspm, bool, 0644);
 MODULE_PARM_DESC(disable_aspm, "disable PCI ASPM support");
 
-static void
-mt7921_rx_poll_complete(struct mt76_dev *mdev, enum mt76_rxq_id q)
-{
-	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
-	const struct mt792x_irq_map *irq_map = dev->irq_map;
-
-	if (q == MT_RXQ_MAIN)
-		mt76_connac_irq_enable(mdev, irq_map->rx.data_complete_mask);
-	else if (q == MT_RXQ_MCU_WA)
-		mt76_connac_irq_enable(mdev, irq_map->rx.wm2_complete_mask);
-	else
-		mt76_connac_irq_enable(mdev, irq_map->rx.wm_complete_mask);
-}
-
-static irqreturn_t mt7921_irq_handler(int irq, void *dev_instance)
-{
-	struct mt792x_dev *dev = dev_instance;
-
-	mt76_wr(dev, dev->irq_map->host_irq_enable, 0);
-
-	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state))
-		return IRQ_NONE;
-
-	tasklet_schedule(&dev->mt76.irq_tasklet);
-
-	return IRQ_HANDLED;
-}
-
-static void mt7921_irq_tasklet(unsigned long data)
-{
-	struct mt792x_dev *dev = (struct mt792x_dev *)data;
-	const struct mt792x_irq_map *irq_map = dev->irq_map;
-	u32 intr, mask = 0;
-
-	mt76_wr(dev, irq_map->host_irq_enable, 0);
-
-	intr = mt76_rr(dev, MT_WFDMA0_HOST_INT_STA);
-	intr &= dev->mt76.mmio.irqmask;
-	mt76_wr(dev, MT_WFDMA0_HOST_INT_STA, intr);
-
-	trace_dev_irq(&dev->mt76, intr, dev->mt76.mmio.irqmask);
-
-	mask |= intr & MT_INT_RX_DONE_ALL;
-	if (intr & irq_map->tx.mcu_complete_mask)
-		mask |= irq_map->tx.mcu_complete_mask;
-
-	if (intr & MT_INT_MCU_CMD) {
-		u32 intr_sw;
-
-		intr_sw = mt76_rr(dev, MT_MCU_CMD);
-		/* ack MCU2HOST_SW_INT_STA */
-		mt76_wr(dev, MT_MCU_CMD, intr_sw);
-		if (intr_sw & MT_MCU_CMD_WAKE_RX_PCIE) {
-			mask |= irq_map->rx.data_complete_mask;
-			intr |= irq_map->rx.data_complete_mask;
-		}
-	}
-
-	mt76_set_irq_mask(&dev->mt76, irq_map->host_irq_enable, mask, 0);
-
-	if (intr & irq_map->tx.all_complete_mask)
-		napi_schedule(&dev->mt76.tx_napi);
-
-	if (intr & irq_map->rx.wm_complete_mask)
-		napi_schedule(&dev->mt76.napi[MT_RXQ_MCU]);
-
-	if (intr & irq_map->rx.wm2_complete_mask)
-		napi_schedule(&dev->mt76.napi[MT_RXQ_MCU_WA]);
-
-	if (intr & irq_map->rx.data_complete_mask)
-		napi_schedule(&dev->mt76.napi[MT_RXQ_MAIN]);
-}
-
 static int mt7921e_init_reset(struct mt792x_dev *dev)
 {
-	return mt7921_wpdma_reset(dev, true);
+	return mt792x_wpdma_reset(dev, true);
 }
 
 static void mt7921e_unregister_device(struct mt792x_dev *dev)
@@ -122,7 +48,7 @@ static void mt7921e_unregister_device(struct mt792x_dev *dev)
 	mt76_connac2_tx_token_put(&dev->mt76);
 	__mt7921_mcu_drv_pmctrl(dev);
 	mt792x_dma_cleanup(dev);
-	mt792x_wfsys_reset(dev, MT_WFSYS_SW_RST_B);
+	mt792x_wfsys_reset(dev);
 	skb_queue_purge(&dev->mt76.mcu.res_q);
 
 	tasklet_disable(&dev->mt76.irq_tasklet);
@@ -245,7 +171,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 		.tx_complete_skb = mt76_connac_tx_complete_skb,
 		.rx_check = mt7921_rx_check,
 		.rx_skb = mt7921_queue_rx_skb,
-		.rx_poll_complete = mt7921_rx_poll_complete,
+		.rx_poll_complete = mt792x_rx_poll_complete,
 		.sta_add = mt7921_mac_sta_add,
 		.sta_assoc = mt7921_mac_sta_assoc,
 		.sta_remove = mt7921_mac_sta_remove,
@@ -324,7 +250,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 	dev->hif_ops = &mt7921_pcie_ops;
 	dev->irq_map = &irq_map;
 	mt76_mmio_init(&dev->mt76, pcim_iomap_table(pdev)[0]);
-	tasklet_init(&mdev->irq_tasklet, mt7921_irq_tasklet, (unsigned long)dev);
+	tasklet_init(&mdev->irq_tasklet, mt792x_irq_tasklet, (unsigned long)dev);
 
 	dev->phy.dev = dev;
 	dev->phy.mt76 = &dev->mt76.phy;
@@ -354,7 +280,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 		    (mt7921_l1_rr(dev, MT_HW_REV) & 0xff);
 	dev_info(mdev->dev, "ASIC revision: %04x\n", mdev->rev);
 
-	ret = mt792x_wfsys_reset(dev, MT_WFSYS_SW_RST_B);
+	ret = mt792x_wfsys_reset(dev);
 	if (ret)
 		goto err_free_dev;
 
@@ -362,7 +288,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 
 	mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
 
-	ret = devm_request_irq(mdev->dev, pdev->irq, mt7921_irq_handler,
+	ret = devm_request_irq(mdev->dev, pdev->irq, mt792x_irq_handler,
 			       IRQF_SHARED, KBUILD_MODNAME, dev);
 	if (ret)
 		goto err_free_dev;
@@ -484,7 +410,7 @@ static int mt7921_pci_resume(struct device *device)
 	if (err < 0)
 		goto failed;
 
-	mt7921_wpdma_reinit_cond(dev);
+	mt792x_wpdma_reinit_cond(dev);
 
 	/* enable interrupt */
 	mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
index 1f508244d6157..bd3f004d1a186 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
@@ -80,7 +80,7 @@ int mt7921e_mac_reset(struct mt792x_dev *dev)
 	mt76_connac2_tx_token_put(&dev->mt76);
 	idr_init(&dev->mt76.token);
 
-	mt7921_wpdma_reset(dev, true);
+	mt792x_wpdma_reset(dev, true);
 
 	local_bh_disable();
 	mt76_for_each_q_rx(&dev->mt76, i) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c
index 5a30cd0b9382b..57bd02746f5f5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c
@@ -91,7 +91,7 @@ int mt7921e_mcu_drv_pmctrl(struct mt792x_dev *dev)
 	if (err < 0)
 		goto out;
 
-	mt7921_wpdma_reinit_cond(dev);
+	mt792x_wpdma_reinit_cond(dev);
 	clear_bit(MT76_STATE_PM, &mphy->state);
 
 	pm->stats.last_wake_event = jiffies;
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 6fd1f542da178..894fb0fe8cba2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -256,9 +256,16 @@ void mt792x_sta_statistics(struct ieee80211_hw *hw,
 			   struct station_info *sinfo);
 void mt792x_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class);
 void mt792x_dma_cleanup(struct mt792x_dev *dev);
+int mt792x_dma_enable(struct mt792x_dev *dev);
+int mt792x_wpdma_reset(struct mt792x_dev *dev, bool force);
+int mt792x_wpdma_reinit_cond(struct mt792x_dev *dev);
 int mt792x_dma_disable(struct mt792x_dev *dev, bool force);
+irqreturn_t mt792x_irq_handler(int irq, void *dev_instance);
+void mt792x_rx_poll_complete(struct mt76_dev *mdev, enum mt76_rxq_id q);
+int mt792x_poll_tx(struct napi_struct *napi, int budget);
 int mt792x_poll_rx(struct napi_struct *napi, int budget);
-int mt792x_wfsys_reset(struct mt792x_dev *dev, u32 addr);
+void mt792x_irq_tasklet(unsigned long data);
+int mt792x_wfsys_reset(struct mt792x_dev *dev);
 int mt792x_tx_stats_show(struct seq_file *file, void *data);
 int mt792x_queues_acq(struct seq_file *s, void *data);
 int mt792x_queues_read(struct seq_file *s, void *data);
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index 87d2a614e5905..a4aa9694de7f6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -510,102 +510,6 @@ void mt792x_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class)
 }
 EXPORT_SYMBOL_GPL(mt792x_set_coverage_class);
 
-int mt792x_dma_disable(struct mt792x_dev *dev, bool force)
-{
-	/* disable WFDMA0 */
-	mt76_clear(dev, MT_WFDMA0_GLO_CFG,
-		   MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN |
-		   MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN |
-		   MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO |
-		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
-
-	if (!mt76_poll_msec_tick(dev, MT_WFDMA0_GLO_CFG,
-				 MT_WFDMA0_GLO_CFG_TX_DMA_BUSY |
-				 MT_WFDMA0_GLO_CFG_RX_DMA_BUSY, 0, 100, 1))
-		return -ETIMEDOUT;
-
-	/* disable dmashdl */
-	mt76_clear(dev, MT_WFDMA0_GLO_CFG_EXT0,
-		   MT_WFDMA0_CSR_TX_DMASHDL_ENABLE);
-	mt76_set(dev, MT_DMASHDL_SW_CONTROL, MT_DMASHDL_DMASHDL_BYPASS);
-
-	if (force) {
-		/* reset */
-		mt76_clear(dev, MT_WFDMA0_RST,
-			   MT_WFDMA0_RST_DMASHDL_ALL_RST |
-			   MT_WFDMA0_RST_LOGIC_RST);
-
-		mt76_set(dev, MT_WFDMA0_RST,
-			 MT_WFDMA0_RST_DMASHDL_ALL_RST |
-			 MT_WFDMA0_RST_LOGIC_RST);
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mt792x_dma_disable);
-
-void mt792x_dma_cleanup(struct mt792x_dev *dev)
-{
-	/* disable */
-	mt76_clear(dev, MT_WFDMA0_GLO_CFG,
-		   MT_WFDMA0_GLO_CFG_TX_DMA_EN |
-		   MT_WFDMA0_GLO_CFG_RX_DMA_EN |
-		   MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN |
-		   MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO |
-		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
-
-	mt76_poll_msec_tick(dev, MT_WFDMA0_GLO_CFG,
-			    MT_WFDMA0_GLO_CFG_TX_DMA_BUSY |
-			    MT_WFDMA0_GLO_CFG_RX_DMA_BUSY, 0, 100, 1);
-
-	/* reset */
-	mt76_clear(dev, MT_WFDMA0_RST,
-		   MT_WFDMA0_RST_DMASHDL_ALL_RST |
-		   MT_WFDMA0_RST_LOGIC_RST);
-
-	mt76_set(dev, MT_WFDMA0_RST,
-		 MT_WFDMA0_RST_DMASHDL_ALL_RST |
-		 MT_WFDMA0_RST_LOGIC_RST);
-
-	mt76_dma_cleanup(&dev->mt76);
-}
-EXPORT_SYMBOL_GPL(mt792x_dma_cleanup);
-
-int mt792x_poll_rx(struct napi_struct *napi, int budget)
-{
-	struct mt792x_dev *dev;
-	int done;
-
-	dev = container_of(napi->dev, struct mt792x_dev, mt76.napi_dev);
-
-	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
-		napi_complete(napi);
-		queue_work(dev->mt76.wq, &dev->pm.wake_work);
-		return 0;
-	}
-	done = mt76_dma_rx_poll(napi, budget);
-	mt76_connac_pm_unref(&dev->mphy, &dev->pm);
-
-	return done;
-}
-EXPORT_SYMBOL_GPL(mt792x_poll_rx);
-
-int mt792x_wfsys_reset(struct mt792x_dev *dev, u32 addr)
-{
-	mt76_clear(dev, addr, WFSYS_SW_RST_B);
-	msleep(50);
-	mt76_set(dev, addr, WFSYS_SW_RST_B);
-
-	if (!__mt76_poll_msec(&dev->mt76, addr, WFSYS_SW_INIT_DONE,
-			      WFSYS_SW_INIT_DONE, 500))
-		return -ETIMEDOUT;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mt792x_wfsys_reset);
-
 int mt792x_init_wiphy(struct ieee80211_hw *hw)
 {
 	struct mt792x_phy *phy = mt792x_hw_phy(hw);
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_dma.c b/drivers/net/wireless/mediatek/mt76/mt792x_dma.c
new file mode 100644
index 0000000000000..a3dbd3865b2f5
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_dma.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: ISC
+/* Copyright (C) 2023 MediaTek Inc. */
+
+#include <linux/module.h>
+#include <linux/firmware.h>
+
+#include "mt792x.h"
+#include "dma.h"
+#include "trace.h"
+
+irqreturn_t mt792x_irq_handler(int irq, void *dev_instance)
+{
+	struct mt792x_dev *dev = dev_instance;
+
+	mt76_wr(dev, dev->irq_map->host_irq_enable, 0);
+
+	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state))
+		return IRQ_NONE;
+
+	tasklet_schedule(&dev->mt76.irq_tasklet);
+
+	return IRQ_HANDLED;
+}
+EXPORT_SYMBOL_GPL(mt792x_irq_handler);
+
+void mt792x_irq_tasklet(unsigned long data)
+{
+	struct mt792x_dev *dev = (struct mt792x_dev *)data;
+	const struct mt792x_irq_map *irq_map = dev->irq_map;
+	u32 intr, mask = 0;
+
+	mt76_wr(dev, irq_map->host_irq_enable, 0);
+
+	intr = mt76_rr(dev, MT_WFDMA0_HOST_INT_STA);
+	intr &= dev->mt76.mmio.irqmask;
+	mt76_wr(dev, MT_WFDMA0_HOST_INT_STA, intr);
+
+	trace_dev_irq(&dev->mt76, intr, dev->mt76.mmio.irqmask);
+
+	mask |= intr & (irq_map->rx.data_complete_mask |
+			irq_map->rx.wm_complete_mask |
+			irq_map->rx.wm2_complete_mask);
+	if (intr & dev->irq_map->tx.mcu_complete_mask)
+		mask |= dev->irq_map->tx.mcu_complete_mask;
+
+	if (intr & MT_INT_MCU_CMD) {
+		u32 intr_sw;
+
+		intr_sw = mt76_rr(dev, MT_MCU_CMD);
+		/* ack MCU2HOST_SW_INT_STA */
+		mt76_wr(dev, MT_MCU_CMD, intr_sw);
+		if (intr_sw & MT_MCU_CMD_WAKE_RX_PCIE) {
+			mask |= irq_map->rx.data_complete_mask;
+			intr |= irq_map->rx.data_complete_mask;
+		}
+	}
+
+	mt76_set_irq_mask(&dev->mt76, irq_map->host_irq_enable, mask, 0);
+
+	if (intr & dev->irq_map->tx.all_complete_mask)
+		napi_schedule(&dev->mt76.tx_napi);
+
+	if (intr & irq_map->rx.wm_complete_mask)
+		napi_schedule(&dev->mt76.napi[MT_RXQ_MCU]);
+
+	if (intr & irq_map->rx.wm2_complete_mask)
+		napi_schedule(&dev->mt76.napi[MT_RXQ_MCU_WA]);
+
+	if (intr & irq_map->rx.data_complete_mask)
+		napi_schedule(&dev->mt76.napi[MT_RXQ_MAIN]);
+}
+EXPORT_SYMBOL_GPL(mt792x_irq_tasklet);
+
+void mt792x_rx_poll_complete(struct mt76_dev *mdev, enum mt76_rxq_id q)
+{
+	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
+	const struct mt792x_irq_map *irq_map = dev->irq_map;
+
+	if (q == MT_RXQ_MAIN)
+		mt76_connac_irq_enable(mdev, irq_map->rx.data_complete_mask);
+	else if (q == MT_RXQ_MCU_WA)
+		mt76_connac_irq_enable(mdev, irq_map->rx.wm2_complete_mask);
+	else
+		mt76_connac_irq_enable(mdev, irq_map->rx.wm_complete_mask);
+}
+EXPORT_SYMBOL_GPL(mt792x_rx_poll_complete);
+
+#define PREFETCH(base, depth)	((base) << 16 | (depth))
+static void mt792x_dma_prefetch(struct mt792x_dev *dev)
+{
+	mt76_wr(dev, MT_WFDMA0_RX_RING0_EXT_CTRL, PREFETCH(0x0, 0x4));
+	mt76_wr(dev, MT_WFDMA0_RX_RING2_EXT_CTRL, PREFETCH(0x40, 0x4));
+	mt76_wr(dev, MT_WFDMA0_RX_RING3_EXT_CTRL, PREFETCH(0x80, 0x4));
+	mt76_wr(dev, MT_WFDMA0_RX_RING4_EXT_CTRL, PREFETCH(0xc0, 0x4));
+	mt76_wr(dev, MT_WFDMA0_RX_RING5_EXT_CTRL, PREFETCH(0x100, 0x4));
+
+	mt76_wr(dev, MT_WFDMA0_TX_RING0_EXT_CTRL, PREFETCH(0x140, 0x4));
+	mt76_wr(dev, MT_WFDMA0_TX_RING1_EXT_CTRL, PREFETCH(0x180, 0x4));
+	mt76_wr(dev, MT_WFDMA0_TX_RING2_EXT_CTRL, PREFETCH(0x1c0, 0x4));
+	mt76_wr(dev, MT_WFDMA0_TX_RING3_EXT_CTRL, PREFETCH(0x200, 0x4));
+	mt76_wr(dev, MT_WFDMA0_TX_RING4_EXT_CTRL, PREFETCH(0x240, 0x4));
+	mt76_wr(dev, MT_WFDMA0_TX_RING5_EXT_CTRL, PREFETCH(0x280, 0x4));
+	mt76_wr(dev, MT_WFDMA0_TX_RING6_EXT_CTRL, PREFETCH(0x2c0, 0x4));
+	mt76_wr(dev, MT_WFDMA0_TX_RING16_EXT_CTRL, PREFETCH(0x340, 0x4));
+	mt76_wr(dev, MT_WFDMA0_TX_RING17_EXT_CTRL, PREFETCH(0x380, 0x4));
+}
+
+int mt792x_dma_enable(struct mt792x_dev *dev)
+{
+	/* configure perfetch settings */
+	mt792x_dma_prefetch(dev);
+
+	/* reset dma idx */
+	mt76_wr(dev, MT_WFDMA0_RST_DTX_PTR, ~0);
+
+	/* configure delay interrupt */
+	mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG0, 0);
+
+	mt76_set(dev, MT_WFDMA0_GLO_CFG,
+		 MT_WFDMA0_GLO_CFG_TX_WB_DDONE |
+		 MT_WFDMA0_GLO_CFG_FIFO_LITTLE_ENDIAN |
+		 MT_WFDMA0_GLO_CFG_CLK_GAT_DIS |
+		 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+		 MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN |
+		 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+
+	mt76_set(dev, MT_WFDMA0_GLO_CFG,
+		 MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN);
+
+	mt76_set(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT);
+
+	/* enable interrupts for TX/RX rings */
+	mt76_connac_irq_enable(&dev->mt76,
+			       dev->irq_map->tx.all_complete_mask |
+			       dev->irq_map->rx.data_complete_mask |
+			       dev->irq_map->rx.wm2_complete_mask |
+			       dev->irq_map->rx.wm_complete_mask |
+			       MT_INT_MCU_CMD);
+	mt76_set(dev, MT_MCU2HOST_SW_INT_ENA, MT_MCU_CMD_WAKE_RX_PCIE);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_dma_enable);
+
+static int
+mt792x_dma_reset(struct mt792x_dev *dev, bool force)
+{
+	int i, err;
+
+	err = mt792x_dma_disable(dev, force);
+	if (err)
+		return err;
+
+	/* reset hw queues */
+	for (i = 0; i < __MT_TXQ_MAX; i++)
+		mt76_queue_reset(dev, dev->mphy.q_tx[i]);
+
+	for (i = 0; i < __MT_MCUQ_MAX; i++)
+		mt76_queue_reset(dev, dev->mt76.q_mcu[i]);
+
+	mt76_for_each_q_rx(&dev->mt76, i)
+		mt76_queue_reset(dev, &dev->mt76.q_rx[i]);
+
+	mt76_tx_status_check(&dev->mt76, true);
+
+	return mt792x_dma_enable(dev);
+}
+
+int mt792x_wpdma_reset(struct mt792x_dev *dev, bool force)
+{
+	int i, err;
+
+	/* clean up hw queues */
+	for (i = 0; i < ARRAY_SIZE(dev->mt76.phy.q_tx); i++)
+		mt76_queue_tx_cleanup(dev, dev->mphy.q_tx[i], true);
+
+	for (i = 0; i < ARRAY_SIZE(dev->mt76.q_mcu); i++)
+		mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[i], true);
+
+	mt76_for_each_q_rx(&dev->mt76, i)
+		mt76_queue_rx_cleanup(dev, &dev->mt76.q_rx[i]);
+
+	if (force) {
+		err = mt792x_wfsys_reset(dev);
+		if (err)
+			return err;
+	}
+	err = mt792x_dma_reset(dev, force);
+	if (err)
+		return err;
+
+	mt76_for_each_q_rx(&dev->mt76, i)
+		mt76_queue_rx_reset(dev, i);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_wpdma_reset);
+
+int mt792x_wpdma_reinit_cond(struct mt792x_dev *dev)
+{
+	struct mt76_connac_pm *pm = &dev->pm;
+	int err;
+
+	/* check if the wpdma must be reinitialized */
+	if (mt792x_dma_need_reinit(dev)) {
+		/* disable interrutpts */
+		mt76_wr(dev, dev->irq_map->host_irq_enable, 0);
+		mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0);
+
+		err = mt792x_wpdma_reset(dev, false);
+		if (err) {
+			dev_err(dev->mt76.dev, "wpdma reset failed\n");
+			return err;
+		}
+
+		/* enable interrutpts */
+		mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
+		pm->stats.lp_wake++;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_wpdma_reinit_cond);
+
+int mt792x_dma_disable(struct mt792x_dev *dev, bool force)
+{
+	/* disable WFDMA0 */
+	mt76_clear(dev, MT_WFDMA0_GLO_CFG,
+		   MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN |
+		   MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN |
+		   MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO |
+		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+
+	if (!mt76_poll_msec_tick(dev, MT_WFDMA0_GLO_CFG,
+				 MT_WFDMA0_GLO_CFG_TX_DMA_BUSY |
+				 MT_WFDMA0_GLO_CFG_RX_DMA_BUSY, 0, 100, 1))
+		return -ETIMEDOUT;
+
+	/* disable dmashdl */
+	mt76_clear(dev, MT_WFDMA0_GLO_CFG_EXT0,
+		   MT_WFDMA0_CSR_TX_DMASHDL_ENABLE);
+	mt76_set(dev, MT_DMASHDL_SW_CONTROL, MT_DMASHDL_DMASHDL_BYPASS);
+
+	if (force) {
+		/* reset */
+		mt76_clear(dev, MT_WFDMA0_RST,
+			   MT_WFDMA0_RST_DMASHDL_ALL_RST |
+			   MT_WFDMA0_RST_LOGIC_RST);
+
+		mt76_set(dev, MT_WFDMA0_RST,
+			 MT_WFDMA0_RST_DMASHDL_ALL_RST |
+			 MT_WFDMA0_RST_LOGIC_RST);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_dma_disable);
+
+void mt792x_dma_cleanup(struct mt792x_dev *dev)
+{
+	/* disable */
+	mt76_clear(dev, MT_WFDMA0_GLO_CFG,
+		   MT_WFDMA0_GLO_CFG_TX_DMA_EN |
+		   MT_WFDMA0_GLO_CFG_RX_DMA_EN |
+		   MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN |
+		   MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO |
+		   MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+
+	mt76_poll_msec_tick(dev, MT_WFDMA0_GLO_CFG,
+			    MT_WFDMA0_GLO_CFG_TX_DMA_BUSY |
+			    MT_WFDMA0_GLO_CFG_RX_DMA_BUSY, 0, 100, 1);
+
+	/* reset */
+	mt76_clear(dev, MT_WFDMA0_RST,
+		   MT_WFDMA0_RST_DMASHDL_ALL_RST |
+		   MT_WFDMA0_RST_LOGIC_RST);
+
+	mt76_set(dev, MT_WFDMA0_RST,
+		 MT_WFDMA0_RST_DMASHDL_ALL_RST |
+		 MT_WFDMA0_RST_LOGIC_RST);
+
+	mt76_dma_cleanup(&dev->mt76);
+}
+EXPORT_SYMBOL_GPL(mt792x_dma_cleanup);
+
+int mt792x_poll_tx(struct napi_struct *napi, int budget)
+{
+	struct mt792x_dev *dev;
+
+	dev = container_of(napi, struct mt792x_dev, mt76.tx_napi);
+
+	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
+		napi_complete(napi);
+		queue_work(dev->mt76.wq, &dev->pm.wake_work);
+		return 0;
+	}
+
+	mt76_connac_tx_cleanup(&dev->mt76);
+	if (napi_complete(napi))
+		mt76_connac_irq_enable(&dev->mt76,
+				       dev->irq_map->tx.all_complete_mask);
+	mt76_connac_pm_unref(&dev->mphy, &dev->pm);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_poll_tx);
+
+int mt792x_poll_rx(struct napi_struct *napi, int budget)
+{
+	struct mt792x_dev *dev;
+	int done;
+
+	dev = container_of(napi->dev, struct mt792x_dev, mt76.napi_dev);
+
+	if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) {
+		napi_complete(napi);
+		queue_work(dev->mt76.wq, &dev->pm.wake_work);
+		return 0;
+	}
+	done = mt76_dma_rx_poll(napi, budget);
+	mt76_connac_pm_unref(&dev->mphy, &dev->pm);
+
+	return done;
+}
+EXPORT_SYMBOL_GPL(mt792x_poll_rx);
+
+int mt792x_wfsys_reset(struct mt792x_dev *dev)
+{
+	u32 addr = is_mt7921(&dev->mt76) ? 0x18000140 : 0x7c000140;
+
+	mt76_clear(dev, addr, WFSYS_SW_RST_B);
+	msleep(50);
+	mt76_set(dev, addr, WFSYS_SW_RST_B);
+
+	if (!__mt76_poll_msec(&dev->mt76, addr, WFSYS_SW_INIT_DONE,
+			      WFSYS_SW_INIT_DONE, 500))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_wfsys_reset);
+
-- 
GitLab


From 5c041325cd0b1307b196c686f87f8531d4d3f105 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:15 +0800
Subject: [PATCH 0474/1806] wifi: mt76: mt7921: move hif_ops macro in mt792x.h

Move the following hif_ops macro in mt792x.h:
- mt7925_init_reset
- mt7925_dev_reset
- mt7925_mcu_init
- __mt7925_mcu_drv_pmctrl
- __mt7925_mcu_fw_pmctrl

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/init.c     | 4 ++--
 drivers/net/wireless/mediatek/mt76/mt7921/mac.c      | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/mcu.c      | 8 ++++----
 drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h   | 6 ------
 drivers/net/wireless/mediatek/mt76/mt7921/pci.c      | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/testmode.c | 2 +-
 drivers/net/wireless/mediatek/mt76/mt792x.h          | 6 ++++++
 7 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 0a6f8f42b2e4f..6b8e31110fdff 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -107,7 +107,7 @@ static int __mt7921_init_hardware(struct mt792x_dev *dev)
 	 * which should be set before firmware download stage.
 	 */
 	mt76_wr(dev, MT_SWDEF_MODE, MT_SWDEF_NORMAL_MODE);
-	ret = mt7921_mcu_init(dev);
+	ret = mt792x_mcu_init(dev);
 	if (ret)
 		goto out;
 
@@ -133,7 +133,7 @@ static int mt7921_init_hardware(struct mt792x_dev *dev)
 		if (!ret)
 			break;
 
-		mt7921_init_reset(dev);
+		mt792x_init_reset(dev);
 	}
 
 	if (i == MT7921_MCU_INIT_RETRY_COUNT) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 70382194825ac..25d853a75a234 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -672,7 +672,7 @@ void mt7921_mac_reset_work(struct work_struct *work)
 
 	for (i = 0; i < 10; i++) {
 		mutex_lock(&dev->mt76.mutex);
-		ret = mt7921_dev_reset(dev);
+		ret = mt792x_dev_reset(dev);
 		mutex_unlock(&dev->mt76.mutex);
 
 		if (!ret)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index ed02fa48841ca..9bfa79893b10e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -482,9 +482,9 @@ static int mt7921_load_firmware(struct mt792x_dev *dev)
 
 	if (mt76_is_sdio(&dev->mt76)) {
 		/* activate again */
-		ret = __mt7921_mcu_fw_pmctrl(dev);
+		ret = __mt792x_mcu_fw_pmctrl(dev);
 		if (!ret)
-			ret = __mt7921_mcu_drv_pmctrl(dev);
+			ret = __mt792x_mcu_drv_pmctrl(dev);
 	}
 
 	ret = mt76_connac2_load_ram(&dev->mt76, mt7921_ram_name(dev), NULL);
@@ -953,7 +953,7 @@ int mt7921_mcu_drv_pmctrl(struct mt792x_dev *dev)
 	if (!test_bit(MT76_STATE_PM, &mphy->state))
 		goto out;
 
-	err = __mt7921_mcu_drv_pmctrl(dev);
+	err = __mt792x_mcu_drv_pmctrl(dev);
 out:
 	mutex_unlock(&pm->mutex);
 
@@ -975,7 +975,7 @@ int mt7921_mcu_fw_pmctrl(struct mt792x_dev *dev)
 	if (mt76_connac_skip_fw_pmctrl(mphy, pm))
 		goto out;
 
-	err = __mt7921_mcu_fw_pmctrl(dev);
+	err = __mt792x_mcu_fw_pmctrl(dev);
 out:
 	mutex_unlock(&pm->mutex);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index b797d8bab5e23..86b8c98e3f699 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -159,12 +159,6 @@ enum mt7921_eeprom_field {
 
 #define MT_EE_HW_TYPE_ENCAP			BIT(0)
 
-#define mt7921_init_reset(dev)		((dev)->hif_ops->init_reset(dev))
-#define mt7921_dev_reset(dev)		((dev)->hif_ops->reset(dev))
-#define mt7921_mcu_init(dev)		((dev)->hif_ops->mcu_init(dev))
-#define __mt7921_mcu_drv_pmctrl(dev)	((dev)->hif_ops->drv_own(dev))
-#define	__mt7921_mcu_fw_pmctrl(dev)	((dev)->hif_ops->fw_own(dev))
-
 enum {
 	TXPWR_USER,
 	TXPWR_EEPROM,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index d11406c87df73..7e9bb1879f9c5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -46,7 +46,7 @@ static void mt7921e_unregister_device(struct mt792x_dev *dev)
 	cancel_work_sync(&dev->reset_work);
 
 	mt76_connac2_tx_token_put(&dev->mt76);
-	__mt7921_mcu_drv_pmctrl(dev);
+	__mt792x_mcu_drv_pmctrl(dev);
 	mt792x_dma_cleanup(dev);
 	mt792x_wfsys_reset(dev);
 	skb_queue_purge(&dev->mt76.mcu.res_q);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c
index 3c2165095ddd1..e838d93477c19 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/testmode.c
@@ -57,7 +57,7 @@ mt7921_tm_set(struct mt792x_dev *dev, struct mt7921_tm_cmd *req)
 		pm->enable = false;
 		cancel_delayed_work_sync(&pm->ps_work);
 		cancel_work_sync(&pm->wake_work);
-		__mt7921_mcu_drv_pmctrl(dev);
+		__mt792x_mcu_drv_pmctrl(dev);
 
 		phy->test.state = MT76_TM_STATE_ON;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 894fb0fe8cba2..1c2829cd954d2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -127,6 +127,12 @@ struct mt792x_irq_map {
 	} rx;
 };
 
+#define mt792x_init_reset(dev)		((dev)->hif_ops->init_reset(dev))
+#define mt792x_dev_reset(dev)		((dev)->hif_ops->reset(dev))
+#define mt792x_mcu_init(dev)		((dev)->hif_ops->mcu_init(dev))
+#define __mt792x_mcu_drv_pmctrl(dev)	((dev)->hif_ops->drv_own(dev))
+#define	__mt792x_mcu_fw_pmctrl(dev)	((dev)->hif_ops->fw_own(dev))
+
 struct mt792x_hif_ops {
 	int (*init_reset)(struct mt792x_dev *dev);
 	int (*reset)(struct mt792x_dev *dev);
-- 
GitLab


From c21a7f9f406bba3f7ee8ce788ef48592c8c3ba8f Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:16 +0800
Subject: [PATCH 0475/1806] wifi: mt76: mt7921: move shared runtime-pm code on
 mt792x-lib

Moving hif_ops marcos in mt792x.h, we can move shared runtime-pm code
between mt7925 and mt7921 in mt792x-lib module.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/init.c  |  4 +-
 .../net/wireless/mediatek/mt76/mt7921/mac.c   | 70 ------------------
 .../net/wireless/mediatek/mt76/mt7921/mcu.c   | 44 ------------
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  4 --
 .../net/wireless/mediatek/mt76/mt7921/pci.c   |  6 +-
 .../net/wireless/mediatek/mt76/mt7921/sdio.c  |  6 +-
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  4 ++
 .../net/wireless/mediatek/mt76/mt792x_core.c  | 44 ++++++++++++
 .../net/wireless/mediatek/mt76/mt792x_mac.c   | 72 +++++++++++++++++++
 9 files changed, 128 insertions(+), 126 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 6b8e31110fdff..c47fb07fcb2ea 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -192,8 +192,8 @@ int mt7921_register_device(struct mt792x_dev *dev)
 	dev->mt76.phy.priv = &dev->phy;
 	dev->mt76.tx_worker.fn = mt792x_tx_worker;
 
-	INIT_DELAYED_WORK(&dev->pm.ps_work, mt7921_pm_power_save_work);
-	INIT_WORK(&dev->pm.wake_work, mt7921_pm_wake_work);
+	INIT_DELAYED_WORK(&dev->pm.ps_work, mt792x_pm_power_save_work);
+	INIT_WORK(&dev->pm.wake_work, mt792x_pm_wake_work);
 	spin_lock_init(&dev->pm.wake.lock);
 	mutex_init(&dev->pm.mutex);
 	init_waitqueue_head(&dev->pm.wait);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 25d853a75a234..21f9374542290 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -699,76 +699,6 @@ void mt7921_mac_reset_work(struct work_struct *work)
 	mt76_connac_power_save_sched(&dev->mt76.phy, pm);
 }
 
-void mt7921_pm_wake_work(struct work_struct *work)
-{
-	struct mt792x_dev *dev;
-	struct mt76_phy *mphy;
-
-	dev = (struct mt792x_dev *)container_of(work, struct mt792x_dev,
-						pm.wake_work);
-	mphy = dev->phy.mt76;
-
-	if (!mt7921_mcu_drv_pmctrl(dev)) {
-		struct mt76_dev *mdev = &dev->mt76;
-		int i;
-
-		if (mt76_is_sdio(mdev)) {
-			mt76_connac_pm_dequeue_skbs(mphy, &dev->pm);
-			mt76_worker_schedule(&mdev->sdio.txrx_worker);
-		} else {
-			local_bh_disable();
-			mt76_for_each_q_rx(mdev, i)
-				napi_schedule(&mdev->napi[i]);
-			local_bh_enable();
-			mt76_connac_pm_dequeue_skbs(mphy, &dev->pm);
-			mt76_connac_tx_cleanup(mdev);
-		}
-		if (test_bit(MT76_STATE_RUNNING, &mphy->state))
-			ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
-						     MT792x_WATCHDOG_TIME);
-	}
-
-	ieee80211_wake_queues(mphy->hw);
-	wake_up(&dev->pm.wait);
-}
-
-void mt7921_pm_power_save_work(struct work_struct *work)
-{
-	struct mt792x_dev *dev;
-	unsigned long delta;
-	struct mt76_phy *mphy;
-
-	dev = (struct mt792x_dev *)container_of(work, struct mt792x_dev,
-						pm.ps_work.work);
-	mphy = dev->phy.mt76;
-
-	delta = dev->pm.idle_timeout;
-	if (test_bit(MT76_HW_SCANNING, &mphy->state) ||
-	    test_bit(MT76_HW_SCHED_SCANNING, &mphy->state) ||
-	    dev->fw_assert)
-		goto out;
-
-	if (mutex_is_locked(&dev->mt76.mutex))
-		/* if mt76 mutex is held we should not put the device
-		 * to sleep since we are currently accessing device
-		 * register map. We need to wait for the next power_save
-		 * trigger.
-		 */
-		goto out;
-
-	if (time_is_after_jiffies(dev->pm.last_activity + delta)) {
-		delta = dev->pm.last_activity + delta - jiffies;
-		goto out;
-	}
-
-	if (!mt7921_mcu_fw_pmctrl(dev)) {
-		cancel_delayed_work_sync(&mphy->mac_work);
-		return;
-	}
-out:
-	queue_delayed_work(dev->mt76.wq, &dev->pm.ps_work, delta);
-}
-
 void mt7921_coredump_work(struct work_struct *work)
 {
 	struct mt792x_dev *dev;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 9bfa79893b10e..bd40ca4894473 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -942,50 +942,6 @@ int mt7921_mcu_sta_update(struct mt792x_dev *dev, struct ieee80211_sta *sta,
 	return mt76_connac_mcu_sta_cmd(&dev->mphy, &info);
 }
 
-int mt7921_mcu_drv_pmctrl(struct mt792x_dev *dev)
-{
-	struct mt76_phy *mphy = &dev->mt76.phy;
-	struct mt76_connac_pm *pm = &dev->pm;
-	int err = 0;
-
-	mutex_lock(&pm->mutex);
-
-	if (!test_bit(MT76_STATE_PM, &mphy->state))
-		goto out;
-
-	err = __mt792x_mcu_drv_pmctrl(dev);
-out:
-	mutex_unlock(&pm->mutex);
-
-	if (err)
-		mt792x_reset(&dev->mt76);
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(mt7921_mcu_drv_pmctrl);
-
-int mt7921_mcu_fw_pmctrl(struct mt792x_dev *dev)
-{
-	struct mt76_phy *mphy = &dev->mt76.phy;
-	struct mt76_connac_pm *pm = &dev->pm;
-	int err = 0;
-
-	mutex_lock(&pm->mutex);
-
-	if (mt76_connac_skip_fw_pmctrl(mphy, pm))
-		goto out;
-
-	err = __mt792x_mcu_fw_pmctrl(dev);
-out:
-	mutex_unlock(&pm->mutex);
-
-	if (err)
-		mt792x_reset(&dev->mt76);
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(mt7921_mcu_fw_pmctrl);
-
 int mt7921_mcu_set_beacon_filter(struct mt792x_dev *dev,
 				 struct ieee80211_vif *vif,
 				 bool enable)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 86b8c98e3f699..4a3416a287112 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -297,10 +297,6 @@ int mt7921_mcu_uni_rx_ba(struct mt792x_dev *dev,
 void mt7921_scan_work(struct work_struct *work);
 void mt7921_roc_work(struct work_struct *work);
 int mt7921_mcu_uni_bss_ps(struct mt792x_dev *dev, struct ieee80211_vif *vif);
-int mt7921_mcu_drv_pmctrl(struct mt792x_dev *dev);
-int mt7921_mcu_fw_pmctrl(struct mt792x_dev *dev);
-void mt7921_pm_wake_work(struct work_struct *work);
-void mt7921_pm_power_save_work(struct work_struct *work);
 void mt7921_coredump_work(struct work_struct *work);
 int mt7921_get_txpwr_info(struct mt792x_dev *dev, struct mt7921_txpwr *txpwr);
 int mt7921_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 7e9bb1879f9c5..7419076b77cb9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -337,7 +337,7 @@ static int mt7921_pci_suspend(struct device *device)
 	cancel_delayed_work_sync(&pm->ps_work);
 	cancel_work_sync(&pm->wake_work);
 
-	err = mt7921_mcu_drv_pmctrl(dev);
+	err = mt792x_mcu_drv_pmctrl(dev);
 	if (err < 0)
 		goto restore_suspend;
 
@@ -372,7 +372,7 @@ static int mt7921_pci_suspend(struct device *device)
 	synchronize_irq(pdev->irq);
 	tasklet_kill(&mdev->irq_tasklet);
 
-	err = mt7921_mcu_fw_pmctrl(dev);
+	err = mt792x_mcu_fw_pmctrl(dev);
 	if (err)
 		goto restore_napi;
 
@@ -406,7 +406,7 @@ static int mt7921_pci_resume(struct device *device)
 	struct mt76_connac_pm *pm = &dev->pm;
 	int i, err;
 
-	err = mt7921_mcu_drv_pmctrl(dev);
+	err = mt792x_mcu_drv_pmctrl(dev);
 	if (err < 0)
 		goto failed;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index 84b3886569419..dc1beb76df3e1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -216,7 +216,7 @@ static int mt7921s_suspend(struct device *__dev)
 	cancel_delayed_work_sync(&pm->ps_work);
 	cancel_work_sync(&pm->wake_work);
 
-	err = mt7921_mcu_drv_pmctrl(dev);
+	err = mt792x_mcu_drv_pmctrl(dev);
 	if (err < 0)
 		goto restore_suspend;
 
@@ -244,7 +244,7 @@ static int mt7921s_suspend(struct device *__dev)
 	mt76_worker_disable(&mdev->sdio.txrx_worker);
 	mt76_worker_disable(&mdev->sdio.net_worker);
 
-	err = mt7921_mcu_fw_pmctrl(dev);
+	err = mt792x_mcu_fw_pmctrl(dev);
 	if (err)
 		goto restore_txrx_worker;
 
@@ -284,7 +284,7 @@ static int mt7921s_resume(struct device *__dev)
 
 	clear_bit(MT76_STATE_SUSPEND, &mdev->phy.state);
 
-	err = mt7921_mcu_drv_pmctrl(dev);
+	err = mt792x_mcu_drv_pmctrl(dev);
 	if (err < 0)
 		goto failed;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 1c2829cd954d2..470017f6f9829 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -215,6 +215,8 @@ static inline bool mt792x_dma_need_reinit(struct mt792x_dev *dev)
 #define mt792x_mutex_release(dev)	\
 	mt76_connac_mutex_release(&(dev)->mt76, &(dev)->pm)
 
+void mt792x_pm_wake_work(struct work_struct *work);
+void mt792x_pm_power_save_work(struct work_struct *work);
 void mt792x_reset(struct mt76_dev *mdev);
 void mt792x_update_channel(struct mt76_phy *mphy);
 void mt792x_mac_reset_counters(struct mt792x_phy *phy);
@@ -284,5 +286,7 @@ mt792x_get_mac80211_ops(struct device *dev,
 			const struct ieee80211_ops *mac80211_ops,
 			void *drv_data, u8 *fw_features);
 int mt792x_init_wcid(struct mt792x_dev *dev);
+int mt792x_mcu_drv_pmctrl(struct mt792x_dev *dev);
+int mt792x_mcu_fw_pmctrl(struct mt792x_dev *dev);
 
 #endif /* __MT7925_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index a4aa9694de7f6..234aac4e37425 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -692,5 +692,49 @@ int mt792x_init_wcid(struct mt792x_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt792x_init_wcid);
 
+int mt792x_mcu_drv_pmctrl(struct mt792x_dev *dev)
+{
+	struct mt76_phy *mphy = &dev->mt76.phy;
+	struct mt76_connac_pm *pm = &dev->pm;
+	int err = 0;
+
+	mutex_lock(&pm->mutex);
+
+	if (!test_bit(MT76_STATE_PM, &mphy->state))
+		goto out;
+
+	err = __mt792x_mcu_drv_pmctrl(dev);
+out:
+	mutex_unlock(&pm->mutex);
+
+	if (err)
+		mt792x_reset(&dev->mt76);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt792x_mcu_drv_pmctrl);
+
+int mt792x_mcu_fw_pmctrl(struct mt792x_dev *dev)
+{
+	struct mt76_phy *mphy = &dev->mt76.phy;
+	struct mt76_connac_pm *pm = &dev->pm;
+	int err = 0;
+
+	mutex_lock(&pm->mutex);
+
+	if (mt76_connac_skip_fw_pmctrl(mphy, pm))
+		goto out;
+
+	err = __mt792x_mcu_fw_pmctrl(dev);
+out:
+	mutex_unlock(&pm->mutex);
+
+	if (err)
+		mt792x_reset(&dev->mt76);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt792x_mcu_fw_pmctrl);
+
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
index 9603c4eedb2bc..5d1f8229fdc1d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
@@ -311,3 +311,75 @@ void mt792x_mac_init_band(struct mt792x_dev *dev, u8 band)
 	mt76_rmw(dev, MT_WTBLOFF_TOP_RSCR(band), mask, set);
 }
 EXPORT_SYMBOL_GPL(mt792x_mac_init_band);
+
+void mt792x_pm_wake_work(struct work_struct *work)
+{
+	struct mt792x_dev *dev;
+	struct mt76_phy *mphy;
+
+	dev = (struct mt792x_dev *)container_of(work, struct mt792x_dev,
+						pm.wake_work);
+	mphy = dev->phy.mt76;
+
+	if (!mt792x_mcu_drv_pmctrl(dev)) {
+		struct mt76_dev *mdev = &dev->mt76;
+		int i;
+
+		if (mt76_is_sdio(mdev)) {
+			mt76_connac_pm_dequeue_skbs(mphy, &dev->pm);
+			mt76_worker_schedule(&mdev->sdio.txrx_worker);
+		} else {
+			local_bh_disable();
+			mt76_for_each_q_rx(mdev, i)
+				napi_schedule(&mdev->napi[i]);
+			local_bh_enable();
+			mt76_connac_pm_dequeue_skbs(mphy, &dev->pm);
+			mt76_connac_tx_cleanup(mdev);
+		}
+		if (test_bit(MT76_STATE_RUNNING, &mphy->state))
+			ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
+						     MT792x_WATCHDOG_TIME);
+	}
+
+	ieee80211_wake_queues(mphy->hw);
+	wake_up(&dev->pm.wait);
+}
+EXPORT_SYMBOL_GPL(mt792x_pm_wake_work);
+
+void mt792x_pm_power_save_work(struct work_struct *work)
+{
+	struct mt792x_dev *dev;
+	unsigned long delta;
+	struct mt76_phy *mphy;
+
+	dev = (struct mt792x_dev *)container_of(work, struct mt792x_dev,
+						pm.ps_work.work);
+	mphy = dev->phy.mt76;
+
+	delta = dev->pm.idle_timeout;
+	if (test_bit(MT76_HW_SCANNING, &mphy->state) ||
+	    test_bit(MT76_HW_SCHED_SCANNING, &mphy->state) ||
+	    dev->fw_assert)
+		goto out;
+
+	if (mutex_is_locked(&dev->mt76.mutex))
+		/* if mt76 mutex is held we should not put the device
+		 * to sleep since we are currently accessing device
+		 * register map. We need to wait for the next power_save
+		 * trigger.
+		 */
+		goto out;
+
+	if (time_is_after_jiffies(dev->pm.last_activity + delta)) {
+		delta = dev->pm.last_activity + delta - jiffies;
+		goto out;
+	}
+
+	if (!mt792x_mcu_fw_pmctrl(dev)) {
+		cancel_delayed_work_sync(&mphy->mac_work);
+		return;
+	}
+out:
+	queue_delayed_work(dev->mt76.wq, &dev->pm.ps_work, delta);
+}
+EXPORT_SYMBOL_GPL(mt792x_pm_power_save_work);
-- 
GitLab


From 1c0254967d94bf5826ae5ea5f84960172db955ff Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:17 +0800
Subject: [PATCH 0476/1806] wifi: mt76: mt7921: move runtime-pm pci code in
 mt792x-lib

Move the following runtime-pm pci routines in mt792x-lib since they are
shared between mt7921 and mt7925 chipsets:
- __mt7921e_mcu_drv_pmctrl
- mt7921e_mcu_drv_pmctrl
- mt7921e_mcu_fw_pmctrl

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/init.c  |  4 +-
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  7 --
 .../net/wireless/mediatek/mt76/mt7921/pci.c   |  8 +--
 .../wireless/mediatek/mt76/mt7921/pci_mac.c   |  2 +-
 .../wireless/mediatek/mt76/mt7921/pci_mcu.c   | 65 ------------------
 .../wireless/mediatek/mt76/mt7921/usb_mac.c   |  4 +-
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  8 +++
 .../net/wireless/mediatek/mt76/mt792x_core.c  | 68 +++++++++++++++++++
 8 files changed, 85 insertions(+), 81 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index c47fb07fcb2ea..3ff0205919c29 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -128,7 +128,7 @@ static int mt7921_init_hardware(struct mt792x_dev *dev)
 
 	set_bit(MT76_STATE_INITIALIZED, &dev->mphy.state);
 
-	for (i = 0; i < MT7921_MCU_INIT_RETRY_COUNT; i++) {
+	for (i = 0; i < MT792x_MCU_INIT_RETRY_COUNT; i++) {
 		ret = __mt7921_init_hardware(dev);
 		if (!ret)
 			break;
@@ -136,7 +136,7 @@ static int mt7921_init_hardware(struct mt792x_dev *dev)
 		mt792x_init_reset(dev);
 	}
 
-	if (i == MT7921_MCU_INIT_RETRY_COUNT) {
+	if (i == MT792x_MCU_INIT_RETRY_COUNT) {
 		dev_err(dev->mt76.dev, "hardware init failed\n");
 		return ret;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 4a3416a287112..0c60a15590417 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -18,10 +18,6 @@
 #define MT7921_RX_RING_SIZE		1536
 #define MT7921_RX_MCU_RING_SIZE		512
 
-#define MT7921_DRV_OWN_RETRY_COUNT	10
-#define MT7921_MCU_INIT_RETRY_COUNT	10
-#define MT7921_WFSYS_INIT_RETRY_COUNT	2
-
 #define MT7921_FIRMWARE_WM		"mediatek/WIFI_RAM_CODE_MT7961_1.bin"
 #define MT7921_ROM_PATCH		"mediatek/WIFI_MT7961_patch_mcu_1_2_hdr.bin"
 
@@ -312,9 +308,6 @@ int mt7921e_mcu_init(struct mt792x_dev *dev);
 int mt7921s_wfsys_reset(struct mt792x_dev *dev);
 int mt7921s_mac_reset(struct mt792x_dev *dev);
 int mt7921s_init_reset(struct mt792x_dev *dev);
-int __mt7921e_mcu_drv_pmctrl(struct mt792x_dev *dev);
-int mt7921e_mcu_drv_pmctrl(struct mt792x_dev *dev);
-int mt7921e_mcu_fw_pmctrl(struct mt792x_dev *dev);
 
 int mt7921s_mcu_init(struct mt792x_dev *dev);
 int mt7921s_mcu_drv_pmctrl(struct mt792x_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 7419076b77cb9..c3f22ce9f5c46 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -181,8 +181,8 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 		.init_reset = mt7921e_init_reset,
 		.reset = mt7921e_mac_reset,
 		.mcu_init = mt7921e_mcu_init,
-		.drv_own = mt7921e_mcu_drv_pmctrl,
-		.fw_own = mt7921e_mcu_fw_pmctrl,
+		.drv_own = mt792xe_mcu_drv_pmctrl,
+		.fw_own = mt792xe_mcu_fw_pmctrl,
 	};
 	static const struct mt792x_irq_map irq_map = {
 		.host_irq_enable = MT_WFDMA0_HOST_INT_ENA,
@@ -268,11 +268,11 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 	bus_ops->rmw = mt7921_rmw;
 	dev->mt76.bus = bus_ops;
 
-	ret = mt7921e_mcu_fw_pmctrl(dev);
+	ret = mt792xe_mcu_fw_pmctrl(dev);
 	if (ret)
 		goto err_free_dev;
 
-	ret = __mt7921e_mcu_drv_pmctrl(dev);
+	ret = __mt792xe_mcu_drv_pmctrl(dev);
 	if (ret)
 		goto err_free_dev;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
index bd3f004d1a186..e7a995e7e70a3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
@@ -57,7 +57,7 @@ int mt7921e_mac_reset(struct mt792x_dev *dev)
 {
 	int i, err;
 
-	mt7921e_mcu_drv_pmctrl(dev);
+	mt792xe_mcu_drv_pmctrl(dev);
 
 	mt76_connac_free_pending_tx_skbs(&dev->pm, NULL);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c
index 57bd02746f5f5..4cf1f2f0f9688 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c
@@ -61,68 +61,3 @@ int mt7921e_mcu_init(struct mt792x_dev *dev)
 
 	return err;
 }
-
-int __mt7921e_mcu_drv_pmctrl(struct mt792x_dev *dev)
-{
-	int i, err = 0;
-
-	for (i = 0; i < MT7921_DRV_OWN_RETRY_COUNT; i++) {
-		mt76_wr(dev, MT_CONN_ON_LPCTL, PCIE_LPCR_HOST_CLR_OWN);
-		if (mt76_poll_msec_tick(dev, MT_CONN_ON_LPCTL,
-					PCIE_LPCR_HOST_OWN_SYNC, 0, 50, 1))
-			break;
-	}
-
-	if (i == MT7921_DRV_OWN_RETRY_COUNT) {
-		dev_err(dev->mt76.dev, "driver own failed\n");
-		err = -EIO;
-	}
-
-	return err;
-}
-
-int mt7921e_mcu_drv_pmctrl(struct mt792x_dev *dev)
-{
-	struct mt76_phy *mphy = &dev->mt76.phy;
-	struct mt76_connac_pm *pm = &dev->pm;
-	int err;
-
-	err = __mt7921e_mcu_drv_pmctrl(dev);
-	if (err < 0)
-		goto out;
-
-	mt792x_wpdma_reinit_cond(dev);
-	clear_bit(MT76_STATE_PM, &mphy->state);
-
-	pm->stats.last_wake_event = jiffies;
-	pm->stats.doze_time += pm->stats.last_wake_event -
-			       pm->stats.last_doze_event;
-out:
-	return err;
-}
-
-int mt7921e_mcu_fw_pmctrl(struct mt792x_dev *dev)
-{
-	struct mt76_phy *mphy = &dev->mt76.phy;
-	struct mt76_connac_pm *pm = &dev->pm;
-	int i;
-
-	for (i = 0; i < MT7921_DRV_OWN_RETRY_COUNT; i++) {
-		mt76_wr(dev, MT_CONN_ON_LPCTL, PCIE_LPCR_HOST_SET_OWN);
-		if (mt76_poll_msec_tick(dev, MT_CONN_ON_LPCTL,
-					PCIE_LPCR_HOST_OWN_SYNC, 4, 50, 1))
-			break;
-	}
-
-	if (i == MT7921_DRV_OWN_RETRY_COUNT) {
-		dev_err(dev->mt76.dev, "firmware own failed\n");
-		clear_bit(MT76_STATE_PM, &mphy->state);
-		return -EIO;
-	}
-
-	pm->stats.last_doze_event = jiffies;
-	pm->stats.awake_time += pm->stats.last_doze_event -
-				pm->stats.last_wake_event;
-
-	return 0;
-}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c
index f612873c704bf..f7cb6c542af54 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c
@@ -166,7 +166,7 @@ int mt7921u_wfsys_reset(struct mt792x_dev *dev)
 	mt7921u_uhw_wr(&dev->mt76, MT_CBTOP_RGU_WF_SUBSYS_RST, val);
 
 	mt7921u_uhw_wr(&dev->mt76, MT_UDMA_CONN_INFRA_STATUS_SEL, 0);
-	for (i = 0; i < MT7921_WFSYS_INIT_RETRY_COUNT; i++) {
+	for (i = 0; i < MT792x_WFSYS_INIT_RETRY_COUNT; i++) {
 		val = mt7921u_uhw_rr(&dev->mt76, MT_UDMA_CONN_INFRA_STATUS);
 		if (val & MT_UDMA_CONN_WFSYS_INIT_DONE)
 			break;
@@ -174,7 +174,7 @@ int mt7921u_wfsys_reset(struct mt792x_dev *dev)
 		msleep(100);
 	}
 
-	if (i == MT7921_WFSYS_INIT_RETRY_COUNT)
+	if (i == MT792x_WFSYS_INIT_RETRY_COUNT)
 		return -ETIMEDOUT;
 
 	return 0;
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 470017f6f9829..54ff9627530f0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -26,6 +26,10 @@
 
 #define MT792x_WATCHDOG_TIME	(HZ / 4)
 
+#define MT792x_DRV_OWN_RETRY_COUNT	10
+#define MT792x_MCU_INIT_RETRY_COUNT	10
+#define MT792x_WFSYS_INIT_RETRY_COUNT	2
+
 struct mt792x_vif;
 struct mt792x_sta;
 
@@ -289,4 +293,8 @@ int mt792x_init_wcid(struct mt792x_dev *dev);
 int mt792x_mcu_drv_pmctrl(struct mt792x_dev *dev);
 int mt792x_mcu_fw_pmctrl(struct mt792x_dev *dev);
 
+int __mt792xe_mcu_drv_pmctrl(struct mt792x_dev *dev);
+int mt792xe_mcu_drv_pmctrl(struct mt792x_dev *dev);
+int mt792xe_mcu_fw_pmctrl(struct mt792x_dev *dev);
+
 #endif /* __MT7925_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index 234aac4e37425..f7dfc2189cc83 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -736,5 +736,73 @@ out:
 }
 EXPORT_SYMBOL_GPL(mt792x_mcu_fw_pmctrl);
 
+int __mt792xe_mcu_drv_pmctrl(struct mt792x_dev *dev)
+{
+	int i, err = 0;
+
+	for (i = 0; i < MT792x_DRV_OWN_RETRY_COUNT; i++) {
+		mt76_wr(dev, MT_CONN_ON_LPCTL, PCIE_LPCR_HOST_CLR_OWN);
+		if (mt76_poll_msec_tick(dev, MT_CONN_ON_LPCTL,
+					PCIE_LPCR_HOST_OWN_SYNC, 0, 50, 1))
+			break;
+	}
+
+	if (i == MT792x_DRV_OWN_RETRY_COUNT) {
+		dev_err(dev->mt76.dev, "driver own failed\n");
+		err = -EIO;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(__mt792xe_mcu_drv_pmctrl);
+
+int mt792xe_mcu_drv_pmctrl(struct mt792x_dev *dev)
+{
+	struct mt76_phy *mphy = &dev->mt76.phy;
+	struct mt76_connac_pm *pm = &dev->pm;
+	int err;
+
+	err = __mt792xe_mcu_drv_pmctrl(dev);
+	if (err < 0)
+		goto out;
+
+	mt792x_wpdma_reinit_cond(dev);
+	clear_bit(MT76_STATE_PM, &mphy->state);
+
+	pm->stats.last_wake_event = jiffies;
+	pm->stats.doze_time += pm->stats.last_wake_event -
+			       pm->stats.last_doze_event;
+out:
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt792xe_mcu_drv_pmctrl);
+
+int mt792xe_mcu_fw_pmctrl(struct mt792x_dev *dev)
+{
+	struct mt76_phy *mphy = &dev->mt76.phy;
+	struct mt76_connac_pm *pm = &dev->pm;
+	int i;
+
+	for (i = 0; i < MT792x_DRV_OWN_RETRY_COUNT; i++) {
+		mt76_wr(dev, MT_CONN_ON_LPCTL, PCIE_LPCR_HOST_SET_OWN);
+		if (mt76_poll_msec_tick(dev, MT_CONN_ON_LPCTL,
+					PCIE_LPCR_HOST_OWN_SYNC, 4, 50, 1))
+			break;
+	}
+
+	if (i == MT792x_DRV_OWN_RETRY_COUNT) {
+		dev_err(dev->mt76.dev, "firmware own failed\n");
+		clear_bit(MT76_STATE_PM, &mphy->state);
+		return -EIO;
+	}
+
+	pm->stats.last_doze_event = jiffies;
+	pm->stats.awake_time += pm->stats.last_doze_event -
+				pm->stats.last_wake_event;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792xe_mcu_fw_pmctrl);
+
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
-- 
GitLab


From 29f5a494f7a22ab4661dc835c1d208e1a61793e7 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:18 +0800
Subject: [PATCH 0477/1806] wifi: mt76: mt7921: move acpi_sar code in
 mt792x-lib module

Move acpi_sar code in mt792x-lib module since it is shared between
mt7921 and mt7925 driver.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/Makefile   |   1 +
 .../wireless/mediatek/mt76/mt7921/Makefile    |   1 -
 .../wireless/mediatek/mt76/mt7921/acpi_sar.h  | 105 ---------------
 .../net/wireless/mediatek/mt76/mt7921/init.c  |   2 +-
 .../net/wireless/mediatek/mt76/mt7921/main.c  |  11 +-
 .../net/wireless/mediatek/mt76/mt7921/mcu.c   |   2 +-
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  24 ----
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  23 ++++
 .../{mt7921/acpi_sar.c => mt792x_acpi_sar.c}  | 125 ++++++++++--------
 .../wireless/mediatek/mt76/mt792x_acpi_sar.h  | 105 +++++++++++++++
 10 files changed, 202 insertions(+), 197 deletions(-)
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.h
 rename drivers/net/wireless/mediatek/mt76/{mt7921/acpi_sar.c => mt792x_acpi_sar.c} (64%)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index d6231948dd6ee..f8a1928d62b26 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -33,6 +33,7 @@ mt76-connac-lib-y := mt76_connac_mcu.o mt76_connac_mac.o mt76_connac3_mac.o
 
 mt792x-lib-y := mt792x_core.o mt792x_mac.o mt792x_trace.o \
 		mt792x_debugfs.o mt792x_dma.o
+mt792x-lib-$(CONFIG_ACPI) += mt792x_acpi_sar.o
 
 obj-$(CONFIG_MT76x0_COMMON) += mt76x0/
 obj-$(CONFIG_MT76x2_COMMON) += mt76x2/
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/Makefile b/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
index fd82dff76dae6..f380ec4b6de16 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
@@ -7,7 +7,6 @@ obj-$(CONFIG_MT7921U) += mt7921u.o
 
 mt7921-common-y := mac.o mcu.o main.o init.o debugfs.o
 mt7921-common-$(CONFIG_NL80211_TESTMODE) += testmode.o
-mt7921-common-$(CONFIG_ACPI) += acpi_sar.o
 mt7921e-y := pci.o pci_mac.o pci_mcu.o dma.o
 mt7921s-y := sdio.o sdio_mac.o sdio_mcu.o
 mt7921u-y := usb.o usb_mac.o
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.h b/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.h
deleted file mode 100644
index 6f2c4a5725720..0000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.h
+++ /dev/null
@@ -1,105 +0,0 @@
-/* SPDX-License-Identifier: ISC */
-/* Copyright (C) 2022 MediaTek Inc. */
-
-#ifndef __MT7921_ACPI_SAR_H
-#define __MT7921_ACPI_SAR_H
-
-#define MT7921_ASAR_MIN_DYN		1
-#define MT7921_ASAR_MAX_DYN		8
-#define MT7921_ASAR_MIN_GEO		3
-#define MT7921_ASAR_MAX_GEO		8
-#define MT7921_ASAR_MIN_FG		8
-
-#define MT7921_ACPI_MTCL		"MTCL"
-#define MT7921_ACPI_MTDS		"MTDS"
-#define MT7921_ACPI_MTGS		"MTGS"
-#define MT7921_ACPI_MTFG		"MTFG"
-
-struct mt7921_asar_dyn_limit {
-	u8 idx;
-	u8 frp[5];
-} __packed;
-
-struct mt7921_asar_dyn {
-	u8 names[4];
-	u8 enable;
-	u8 nr_tbl;
-	DECLARE_FLEX_ARRAY(struct mt7921_asar_dyn_limit, tbl);
-} __packed;
-
-struct mt7921_asar_dyn_limit_v2 {
-	u8 idx;
-	u8 frp[11];
-} __packed;
-
-struct mt7921_asar_dyn_v2 {
-	u8 names[4];
-	u8 enable;
-	u8 rsvd;
-	u8 nr_tbl;
-	DECLARE_FLEX_ARRAY(struct mt7921_asar_dyn_limit_v2, tbl);
-} __packed;
-
-struct mt7921_asar_geo_band {
-	u8 pwr;
-	u8 offset;
-} __packed;
-
-struct mt7921_asar_geo_limit {
-	u8 idx;
-	/* 0:2G, 1:5G */
-	struct mt7921_asar_geo_band band[2];
-} __packed;
-
-struct mt7921_asar_geo {
-	u8 names[4];
-	u8 version;
-	u8 nr_tbl;
-	DECLARE_FLEX_ARRAY(struct mt7921_asar_geo_limit, tbl);
-} __packed;
-
-struct mt7921_asar_geo_limit_v2 {
-	u8 idx;
-	/* 0:2G, 1:5G, 2:6G */
-	struct mt7921_asar_geo_band band[3];
-} __packed;
-
-struct mt7921_asar_geo_v2 {
-	u8 names[4];
-	u8 version;
-	u8 rsvd;
-	u8 nr_tbl;
-	DECLARE_FLEX_ARRAY(struct mt7921_asar_geo_limit_v2, tbl);
-} __packed;
-
-struct mt7921_asar_cl {
-	u8 names[4];
-	u8 version;
-	u8 mode_6g;
-	u8 cl6g[6];
-} __packed;
-
-struct mt7921_asar_fg {
-	u8 names[4];
-	u8 version;
-	u8 rsvd;
-	u8 nr_flag;
-	u8 rsvd1;
-	u8 flag[];
-} __packed;
-
-struct mt7921_acpi_sar {
-	u8 ver;
-	union {
-		struct mt7921_asar_dyn *dyn;
-		struct mt7921_asar_dyn_v2 *dyn_v2;
-	};
-	union {
-		struct mt7921_asar_geo *geo;
-		struct mt7921_asar_geo_v2 *geo_v2;
-	};
-	struct mt7921_asar_cl *countrylist;
-	struct mt7921_asar_fg *fg;
-};
-
-#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 3ff0205919c29..7b8876bf8fc8c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -230,7 +230,7 @@ int mt7921_register_device(struct mt792x_dev *dev)
 	if (!mt76_is_mmio(&dev->mt76))
 		hw->extra_tx_headroom += MT_SDIO_TXD_SIZE + MT_SDIO_HDR_SIZE;
 
-	mt7921_init_acpi_sar(dev);
+	mt792x_init_acpi_sar(dev);
 
 	ret = mt792x_init_wcid(dev);
 	if (ret)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 73f29fed216fe..0844d28b3223d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1153,19 +1153,16 @@ int mt7921_set_tx_sar_pwr(struct ieee80211_hw *hw,
 			  const struct cfg80211_sar_specs *sar)
 {
 	struct mt76_phy *mphy = hw->priv;
-	int err;
 
 	if (sar) {
-		err = mt76_init_sar_power(hw, sar);
+		int err = mt76_init_sar_power(hw, sar);
+
 		if (err)
 			return err;
 	}
+	mt792x_init_acpi_sar_power(mt792x_hw_phy(hw), !sar);
 
-	mt7921_init_acpi_sar_power(mt792x_hw_phy(hw), !sar);
-
-	err = mt76_connac_mcu_set_rate_txpower(mphy);
-
-	return err;
+	return mt76_connac_mcu_set_rate_txpower(mphy);
 }
 
 static int mt7921_set_sar_specs(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index bd40ca4894473..e9caf750bca55 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -1197,7 +1197,7 @@ int __mt7921_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 	} __packed req = {
 		.idx = idx,
 		.env = env_cap,
-		.acpi_conf = mt7921_acpi_get_flags(&dev->phy),
+		.acpi_conf = mt792x_acpi_get_flags(&dev->phy),
 	};
 	int ret, valid_cnt = 0;
 	u8 i, *pos;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 0c60a15590417..3ba873ec6bc47 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -6,7 +6,6 @@
 
 #include "../mt792x.h"
 #include "regs.h"
-#include "acpi_sar.h"
 
 #define MT7921_PM_TIMEOUT		(HZ / 12)
 #define MT7921_HW_SCAN_TIMEOUT		(HZ / 10)
@@ -345,29 +344,6 @@ int mt7921_mcu_uni_add_beacon_offload(struct mt792x_dev *dev,
 				      struct ieee80211_hw *hw,
 				      struct ieee80211_vif *vif,
 				      bool enable);
-#ifdef CONFIG_ACPI
-int mt7921_init_acpi_sar(struct mt792x_dev *dev);
-int mt7921_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default);
-u8 mt7921_acpi_get_flags(struct mt792x_phy *phy);
-#else
-static inline int
-mt7921_init_acpi_sar(struct mt792x_dev *dev)
-{
-	return 0;
-}
-
-static inline int
-mt7921_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default)
-{
-	return 0;
-}
-
-static inline u8
-mt7921_acpi_get_flags(struct mt792x_phy *phy)
-{
-	return 0;
-}
-#endif
 int mt7921_set_tx_sar_pwr(struct ieee80211_hw *hw,
 			  const struct cfg80211_sar_specs *sar);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 54ff9627530f0..1ed688186fe74 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -9,6 +9,7 @@
 
 #include "mt76_connac_mcu.h"
 #include "mt792x_regs.h"
+#include "mt792x_acpi_sar.h"
 
 #define MT792x_MAX_INTERFACES	4
 #define MT792x_WTBL_SIZE	20
@@ -297,4 +298,26 @@ int __mt792xe_mcu_drv_pmctrl(struct mt792x_dev *dev);
 int mt792xe_mcu_drv_pmctrl(struct mt792x_dev *dev);
 int mt792xe_mcu_fw_pmctrl(struct mt792x_dev *dev);
 
+#ifdef CONFIG_ACPI
+int mt792x_init_acpi_sar(struct mt792x_dev *dev);
+int mt792x_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default);
+u8 mt792x_acpi_get_flags(struct mt792x_phy *phy);
+#else
+static inline int mt792x_init_acpi_sar(struct mt792x_dev *dev)
+{
+	return 0;
+}
+
+static inline int mt792x_init_acpi_sar_power(struct mt792x_phy *phy,
+					     bool set_default)
+{
+	return 0;
+}
+
+static inline u8 mt792x_acpi_get_flags(struct mt792x_phy *phy)
+{
+	return 0;
+}
+#endif
+
 #endif /* __MT7925_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c
similarity index 64%
rename from drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
rename to drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c
index 057767ab45ffb..303c0f5c9c662 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/acpi_sar.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c
@@ -1,15 +1,15 @@
 // SPDX-License-Identifier: ISC
-/* Copyright (C) 2022 MediaTek Inc. */
+/* Copyright (C) 2023 MediaTek Inc. */
 
 #include <linux/acpi.h>
-#include "mt7921.h"
+#include "mt792x.h"
 
 static int
-mt7921_acpi_read(struct mt792x_dev *dev, u8 *method, u8 **tbl, u32 *len)
+mt792x_acpi_read(struct mt792x_dev *dev, u8 *method, u8 **tbl, u32 *len)
 {
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
-	union acpi_object *sar_root, *sar_unit;
 	struct mt76_dev *mdev = &dev->mt76;
+	union acpi_object *sar_root;
 	acpi_handle root, handle;
 	acpi_status status;
 	u32 i = 0;
@@ -45,18 +45,20 @@ mt7921_acpi_read(struct mt792x_dev *dev, u8 *method, u8 **tbl, u32 *len)
 			goto free;
 		}
 	}
+
 	if (len)
 		*len = sar_root->package.count;
 
 	for (i = 0; i < sar_root->package.count; i++) {
-		sar_unit = &sar_root->package.elements[i];
+		union acpi_object *sar_unit = &sar_root->package.elements[i];
 
 		if (sar_unit->type != ACPI_TYPE_INTEGER)
 			break;
+
 		*(*tbl + i) = (u8)sar_unit->integer.value;
 	}
-	ret = (i == sar_root->package.count) ? 0 : -EINVAL;
 
+	ret = i == sar_root->package.count ? 0 : -EINVAL;
 free:
 	kfree(sar_root);
 
@@ -64,36 +66,37 @@ free:
 }
 
 /* MTCL : Country List Table for 6G band */
-static int
-mt7921_asar_acpi_read_mtcl(struct mt792x_dev *dev, u8 **table, u8 *version)
+static void
+mt792x_asar_acpi_read_mtcl(struct mt792x_dev *dev, u8 **table, u8 *version)
 {
-	*version = (mt7921_acpi_read(dev, MT7921_ACPI_MTCL, table, NULL) < 0)
-		   ? 1 : 2;
-	return 0;
+	if (mt792x_acpi_read(dev, MT792x_ACPI_MTCL, table, NULL) < 0)
+		*version = 1;
+	else
+		*version = 2;
 }
 
 /* MTDS : Dynamic SAR Power Table */
 static int
-mt7921_asar_acpi_read_mtds(struct mt792x_dev *dev, u8 **table, u8 version)
+mt792x_asar_acpi_read_mtds(struct mt792x_dev *dev, u8 **table, u8 version)
 {
 	int len, ret, sarlen, prelen, tblcnt;
 	bool enable;
 
-	ret = mt7921_acpi_read(dev, MT7921_ACPI_MTDS, table, &len);
+	ret = mt792x_acpi_read(dev, MT792x_ACPI_MTDS, table, &len);
 	if (ret)
 		return ret;
 
 	/* Table content validation */
 	switch (version) {
 	case 1:
-		enable = ((struct mt7921_asar_dyn *)*table)->enable;
-		sarlen = sizeof(struct mt7921_asar_dyn_limit);
-		prelen = sizeof(struct mt7921_asar_dyn);
+		enable = ((struct mt792x_asar_dyn *)*table)->enable;
+		sarlen = sizeof(struct mt792x_asar_dyn_limit);
+		prelen = sizeof(struct mt792x_asar_dyn);
 		break;
 	case 2:
-		enable = ((struct mt7921_asar_dyn_v2 *)*table)->enable;
-		sarlen = sizeof(struct mt7921_asar_dyn_limit_v2);
-		prelen = sizeof(struct mt7921_asar_dyn_v2);
+		enable = ((struct mt792x_asar_dyn_v2 *)*table)->enable;
+		sarlen = sizeof(struct mt792x_asar_dyn_limit_v2);
+		prelen = sizeof(struct mt792x_asar_dyn_v2);
 		break;
 	default:
 		return -EINVAL;
@@ -101,88 +104,89 @@ mt7921_asar_acpi_read_mtds(struct mt792x_dev *dev, u8 **table, u8 version)
 
 	tblcnt = (len - prelen) / sarlen;
 	if (!enable ||
-	    tblcnt > MT7921_ASAR_MAX_DYN || tblcnt < MT7921_ASAR_MIN_DYN)
-		ret = -EINVAL;
+	    tblcnt > MT792x_ASAR_MAX_DYN || tblcnt < MT792x_ASAR_MIN_DYN)
+		return -EINVAL;
 
-	return ret;
+	return 0;
 }
 
 /* MTGS : Geo SAR Power Table */
 static int
-mt7921_asar_acpi_read_mtgs(struct mt792x_dev *dev, u8 **table, u8 version)
+mt792x_asar_acpi_read_mtgs(struct mt792x_dev *dev, u8 **table, u8 version)
 {
-	int len, ret = 0, sarlen, prelen, tblcnt;
+	int len, ret, sarlen, prelen, tblcnt;
 
-	ret = mt7921_acpi_read(dev, MT7921_ACPI_MTGS, table, &len);
+	ret = mt792x_acpi_read(dev, MT792x_ACPI_MTGS, table, &len);
 	if (ret)
 		return ret;
 
 	/* Table content validation */
 	switch (version) {
 	case 1:
-		sarlen = sizeof(struct mt7921_asar_geo_limit);
-		prelen = sizeof(struct mt7921_asar_geo);
+		sarlen = sizeof(struct mt792x_asar_geo_limit);
+		prelen = sizeof(struct mt792x_asar_geo);
 		break;
 	case 2:
-		sarlen = sizeof(struct mt7921_asar_geo_limit_v2);
-		prelen = sizeof(struct mt7921_asar_geo_v2);
+		sarlen = sizeof(struct mt792x_asar_geo_limit_v2);
+		prelen = sizeof(struct mt792x_asar_geo_v2);
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	tblcnt = (len - prelen) / sarlen;
-	if (tblcnt > MT7921_ASAR_MAX_GEO || tblcnt < MT7921_ASAR_MIN_GEO)
-		ret = -EINVAL;
+	if (tblcnt > MT792x_ASAR_MAX_GEO || tblcnt < MT792x_ASAR_MIN_GEO)
+		return -EINVAL;
 
-	return ret;
+	return 0;
 }
 
 /* MTFG : Flag Table */
 static int
-mt7921_asar_acpi_read_mtfg(struct mt792x_dev *dev, u8 **table)
+mt792x_asar_acpi_read_mtfg(struct mt792x_dev *dev, u8 **table)
 {
 	int len, ret;
 
-	ret = mt7921_acpi_read(dev, MT7921_ACPI_MTFG, table, &len);
+	ret = mt792x_acpi_read(dev, MT792x_ACPI_MTFG, table, &len);
 	if (ret)
 		return ret;
 
-	if (len < MT7921_ASAR_MIN_FG)
-		ret = -EINVAL;
+	if (len < MT792x_ASAR_MIN_FG)
+		return -EINVAL;
 
-	return ret;
+	return 0;
 }
 
-int mt7921_init_acpi_sar(struct mt792x_dev *dev)
+int mt792x_init_acpi_sar(struct mt792x_dev *dev)
 {
-	struct mt7921_acpi_sar *asar;
+	struct mt792x_acpi_sar *asar;
 	int ret;
 
 	asar = devm_kzalloc(dev->mt76.dev, sizeof(*asar), GFP_KERNEL);
 	if (!asar)
 		return -ENOMEM;
 
-	mt7921_asar_acpi_read_mtcl(dev, (u8 **)&asar->countrylist, &asar->ver);
+	mt792x_asar_acpi_read_mtcl(dev, (u8 **)&asar->countrylist, &asar->ver);
 
 	/* MTDS is mandatory. Return error if table is invalid */
-	ret = mt7921_asar_acpi_read_mtds(dev, (u8 **)&asar->dyn, asar->ver);
+	ret = mt792x_asar_acpi_read_mtds(dev, (u8 **)&asar->dyn, asar->ver);
 	if (ret) {
 		devm_kfree(dev->mt76.dev, asar->dyn);
 		devm_kfree(dev->mt76.dev, asar->countrylist);
 		devm_kfree(dev->mt76.dev, asar);
+
 		return ret;
 	}
 
 	/* MTGS is optional */
-	ret = mt7921_asar_acpi_read_mtgs(dev, (u8 **)&asar->geo, asar->ver);
+	ret = mt792x_asar_acpi_read_mtgs(dev, (u8 **)&asar->geo, asar->ver);
 	if (ret) {
 		devm_kfree(dev->mt76.dev, asar->geo);
 		asar->geo = NULL;
 	}
 
 	/* MTFG is optional */
-	ret = mt7921_asar_acpi_read_mtfg(dev, (u8 **)&asar->fg);
+	ret = mt792x_asar_acpi_read_mtfg(dev, (u8 **)&asar->fg);
 	if (ret) {
 		devm_kfree(dev->mt76.dev, asar->fg);
 		asar->fg = NULL;
@@ -191,13 +195,14 @@ int mt7921_init_acpi_sar(struct mt792x_dev *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mt792x_init_acpi_sar);
 
 static s8
-mt7921_asar_get_geo_pwr(struct mt792x_phy *phy,
+mt792x_asar_get_geo_pwr(struct mt792x_phy *phy,
 			enum nl80211_band band, s8 dyn_power)
 {
-	struct mt7921_acpi_sar *asar = phy->acpisar;
-	struct mt7921_asar_geo_band *band_pwr;
+	struct mt792x_acpi_sar *asar = phy->acpisar;
+	struct mt792x_asar_geo_band *band_pwr;
 	s8 geo_power;
 	u8 idx, max;
 
@@ -248,12 +253,12 @@ mt7921_asar_get_geo_pwr(struct mt792x_phy *phy,
 }
 
 static s8
-mt7921_asar_range_pwr(struct mt792x_phy *phy,
+mt792x_asar_range_pwr(struct mt792x_phy *phy,
 		      const struct cfg80211_sar_freq_ranges *range,
 		      u8 idx)
 {
 	const struct cfg80211_sar_capa *capa = phy->mt76->hw->wiphy->sar_capa;
-	struct mt7921_acpi_sar *asar = phy->acpisar;
+	struct mt792x_acpi_sar *asar = phy->acpisar;
 	u8 *limit, band, max;
 
 	if (!capa)
@@ -277,10 +282,10 @@ mt7921_asar_range_pwr(struct mt792x_phy *phy,
 	else
 		band = NL80211_BAND_2GHZ;
 
-	return mt7921_asar_get_geo_pwr(phy, band, limit[idx]);
+	return mt792x_asar_get_geo_pwr(phy, band, limit[idx]);
 }
 
-int mt7921_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default)
+int mt792x_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default)
 {
 	const struct cfg80211_sar_capa *capa = phy->mt76->hw->wiphy->sar_capa;
 	int i;
@@ -300,22 +305,23 @@ int mt7921_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default)
 			continue;
 
 		frp->power = min_t(s8, set_default ? 127 : frp->power,
-				   mt7921_asar_range_pwr(phy, frp->range, i));
+				   mt792x_asar_range_pwr(phy, frp->range, i));
 	}
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mt792x_init_acpi_sar_power);
 
-u8 mt7921_acpi_get_flags(struct mt792x_phy *phy)
+u8 mt792x_acpi_get_flags(struct mt792x_phy *phy)
 {
-	struct mt7921_acpi_sar *acpisar = phy->acpisar;
-	struct mt7921_asar_fg *fg;
+	struct mt792x_acpi_sar *acpisar = phy->acpisar;
+	struct mt792x_asar_fg *fg;
 	struct {
 		u8 acpi_idx;
 		u8 chip_idx;
 	} map[] = {
-		{1, 1},
-		{4, 2},
+		{ 1, 1 },
+		{ 4, 2 },
 	};
 	u8 flags = BIT(0);
 	int i, j;
@@ -330,12 +336,15 @@ u8 mt7921_acpi_get_flags(struct mt792x_phy *phy)
 	/* pickup necessary settings per device and
 	 * translate the index of bitmap for chip command.
 	 */
-	for (i = 0; i < fg->nr_flag; i++)
-		for (j = 0; j < ARRAY_SIZE(map); j++)
+	for (i = 0; i < fg->nr_flag; i++) {
+		for (j = 0; j < ARRAY_SIZE(map); j++) {
 			if (fg->flag[i] == map[j].acpi_idx) {
 				flags |= BIT(map[j].chip_idx);
 				break;
 			}
+		}
+	}
 
 	return flags;
 }
+EXPORT_SYMBOL_GPL(mt792x_acpi_get_flags);
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h
new file mode 100644
index 0000000000000..d6d332e863ba9
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: ISC */
+/* Copyright (C) 2023 MediaTek Inc. */
+
+#ifndef __MT7921_ACPI_SAR_H
+#define __MT7921_ACPI_SAR_H
+
+#define MT792x_ASAR_MIN_DYN		1
+#define MT792x_ASAR_MAX_DYN		8
+#define MT792x_ASAR_MIN_GEO		3
+#define MT792x_ASAR_MAX_GEO		8
+#define MT792x_ASAR_MIN_FG		8
+
+#define MT792x_ACPI_MTCL		"MTCL"
+#define MT792x_ACPI_MTDS		"MTDS"
+#define MT792x_ACPI_MTGS		"MTGS"
+#define MT792x_ACPI_MTFG		"MTFG"
+
+struct mt792x_asar_dyn_limit {
+	u8 idx;
+	u8 frp[5];
+} __packed;
+
+struct mt792x_asar_dyn {
+	u8 names[4];
+	u8 enable;
+	u8 nr_tbl;
+	DECLARE_FLEX_ARRAY(struct mt792x_asar_dyn_limit, tbl);
+} __packed;
+
+struct mt792x_asar_dyn_limit_v2 {
+	u8 idx;
+	u8 frp[11];
+} __packed;
+
+struct mt792x_asar_dyn_v2 {
+	u8 names[4];
+	u8 enable;
+	u8 rsvd;
+	u8 nr_tbl;
+	DECLARE_FLEX_ARRAY(struct mt792x_asar_dyn_limit_v2, tbl);
+} __packed;
+
+struct mt792x_asar_geo_band {
+	u8 pwr;
+	u8 offset;
+} __packed;
+
+struct mt792x_asar_geo_limit {
+	u8 idx;
+	/* 0:2G, 1:5G */
+	struct mt792x_asar_geo_band band[2];
+} __packed;
+
+struct mt792x_asar_geo {
+	u8 names[4];
+	u8 version;
+	u8 nr_tbl;
+	DECLARE_FLEX_ARRAY(struct mt792x_asar_geo_limit, tbl);
+} __packed;
+
+struct mt792x_asar_geo_limit_v2 {
+	u8 idx;
+	/* 0:2G, 1:5G, 2:6G */
+	struct mt792x_asar_geo_band band[3];
+} __packed;
+
+struct mt792x_asar_geo_v2 {
+	u8 names[4];
+	u8 version;
+	u8 rsvd;
+	u8 nr_tbl;
+	DECLARE_FLEX_ARRAY(struct mt792x_asar_geo_limit_v2, tbl);
+} __packed;
+
+struct mt792x_asar_cl {
+	u8 names[4];
+	u8 version;
+	u8 mode_6g;
+	u8 cl6g[6];
+} __packed;
+
+struct mt792x_asar_fg {
+	u8 names[4];
+	u8 version;
+	u8 rsvd;
+	u8 nr_flag;
+	u8 rsvd1;
+	u8 flag[];
+} __packed;
+
+struct mt792x_acpi_sar {
+	u8 ver;
+	union {
+		struct mt792x_asar_dyn *dyn;
+		struct mt792x_asar_dyn_v2 *dyn_v2;
+	};
+	union {
+		struct mt792x_asar_geo *geo;
+		struct mt792x_asar_geo_v2 *geo_v2;
+	};
+	struct mt792x_asar_cl *countrylist;
+	struct mt792x_asar_fg *fg;
+};
+
+#endif
-- 
GitLab


From d28e1a48952e60fe47bba5b79fdbafc65f6c892b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:19 +0800
Subject: [PATCH 0478/1806] wifi: mt76: mt792x: introduce mt792x-usb module

Add usb shared code between mt7921 and mt7925 chipset to mt792x-usb module.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/Kconfig    |   4 +
 drivers/net/wireless/mediatek/mt76/Makefile   |   2 +
 .../net/wireless/mediatek/mt76/mt7921/Kconfig |   2 +-
 .../wireless/mediatek/mt76/mt7921/Makefile    |   2 +-
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |   8 -
 .../net/wireless/mediatek/mt76/mt7921/usb.c   | 162 ++++++--------
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  13 ++
 .../mt76/{mt7921/usb_mac.c => mt792x_usb.c}   | 203 +++++++++++-------
 8 files changed, 208 insertions(+), 188 deletions(-)
 rename drivers/net/wireless/mediatek/mt76/{mt7921/usb_mac.c => mt792x_usb.c} (51%)

diff --git a/drivers/net/wireless/mediatek/mt76/Kconfig b/drivers/net/wireless/mediatek/mt76/Kconfig
index 1ddf195597a8e..7eb1b0b63d11b 100644
--- a/drivers/net/wireless/mediatek/mt76/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/Kconfig
@@ -33,6 +33,10 @@ config MT792x_LIB
 	tristate
 	select MT76_CONNAC_LIB
 
+config MT792x_USB
+	tristate
+	select MT76_USB
+
 source "drivers/net/wireless/mediatek/mt76/mt76x0/Kconfig"
 source "drivers/net/wireless/mediatek/mt76/mt76x2/Kconfig"
 source "drivers/net/wireless/mediatek/mt76/mt7603/Kconfig"
diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index f8a1928d62b26..85c4799be9543 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_MT76x02_LIB) += mt76x02-lib.o
 obj-$(CONFIG_MT76x02_USB) += mt76x02-usb.o
 obj-$(CONFIG_MT76_CONNAC_LIB) += mt76-connac-lib.o
 obj-$(CONFIG_MT792x_LIB) += mt792x-lib.o
+obj-$(CONFIG_MT792x_USB) += mt792x-usb.o
 
 mt76-y := \
 	mmio.o util.o trace.o dma.o mac80211.o debugfs.o eeprom.o \
@@ -34,6 +35,7 @@ mt76-connac-lib-y := mt76_connac_mcu.o mt76_connac_mac.o mt76_connac3_mac.o
 mt792x-lib-y := mt792x_core.o mt792x_mac.o mt792x_trace.o \
 		mt792x_debugfs.o mt792x_dma.o
 mt792x-lib-$(CONFIG_ACPI) += mt792x_acpi_sar.o
+mt792x-usb-y := mt792x_usb.o
 
 obj-$(CONFIG_MT76x0_COMMON) += mt76x0/
 obj-$(CONFIG_MT76x2_COMMON) += mt76x2/
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/Kconfig b/drivers/net/wireless/mediatek/mt76/mt7921/Kconfig
index b92630cdf88b6..7ed51e057857c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/Kconfig
@@ -27,7 +27,7 @@ config MT7921S
 
 config MT7921U
 	tristate "MediaTek MT7921U (USB) support"
-	select MT76_USB
+	select MT792x_USB
 	select MT7921_COMMON
 	depends on MAC80211
 	depends on USB
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/Makefile b/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
index f380ec4b6de16..964eb55824cd0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
@@ -9,4 +9,4 @@ mt7921-common-y := mac.o mcu.o main.o init.o debugfs.o
 mt7921-common-$(CONFIG_NL80211_TESTMODE) += testmode.o
 mt7921e-y := pci.o pci_mac.o pci_mcu.o dma.o
 mt7921s-y := sdio.o sdio_mac.o sdio_mcu.o
-mt7921u-y := usb.o usb_mac.o
+mt7921u-y := usb.o
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 3ba873ec6bc47..cb22be083242e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -332,14 +332,6 @@ void mt7921_usb_sdio_tx_complete_skb(struct mt76_dev *mdev,
 bool mt7921_usb_sdio_tx_status_data(struct mt76_dev *mdev, u8 *update);
 
 /* usb */
-#define MT_USB_TYPE_VENDOR	(USB_TYPE_VENDOR | 0x1f)
-#define MT_USB_TYPE_UHW_VENDOR	(USB_TYPE_VENDOR | 0x1e)
-
-int mt7921u_mcu_power_on(struct mt792x_dev *dev);
-int mt7921u_wfsys_reset(struct mt792x_dev *dev);
-int mt7921u_dma_init(struct mt792x_dev *dev, bool resume);
-int mt7921u_init_reset(struct mt792x_dev *dev);
-int mt7921u_mac_reset(struct mt792x_dev *dev);
 int mt7921_mcu_uni_add_beacon_offload(struct mt792x_dev *dev,
 				      struct ieee80211_hw *hw,
 				      struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index 0a31e70763249..c3981bc893aca 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -24,83 +24,6 @@ static const struct usb_device_id mt7921u_device_table[] = {
 	{ },
 };
 
-static u32 mt7921u_rr(struct mt76_dev *dev, u32 addr)
-{
-	u32 ret;
-
-	mutex_lock(&dev->usb.usb_ctrl_mtx);
-	ret = ___mt76u_rr(dev, MT_VEND_READ_EXT,
-			  USB_DIR_IN | MT_USB_TYPE_VENDOR, addr);
-	mutex_unlock(&dev->usb.usb_ctrl_mtx);
-
-	return ret;
-}
-
-static void mt7921u_wr(struct mt76_dev *dev, u32 addr, u32 val)
-{
-	mutex_lock(&dev->usb.usb_ctrl_mtx);
-	___mt76u_wr(dev, MT_VEND_WRITE_EXT,
-		    USB_DIR_OUT | MT_USB_TYPE_VENDOR, addr, val);
-	mutex_unlock(&dev->usb.usb_ctrl_mtx);
-}
-
-static u32 mt7921u_rmw(struct mt76_dev *dev, u32 addr,
-		       u32 mask, u32 val)
-{
-	mutex_lock(&dev->usb.usb_ctrl_mtx);
-	val |= ___mt76u_rr(dev, MT_VEND_READ_EXT,
-			   USB_DIR_IN | MT_USB_TYPE_VENDOR, addr) & ~mask;
-	___mt76u_wr(dev, MT_VEND_WRITE_EXT,
-		    USB_DIR_OUT | MT_USB_TYPE_VENDOR, addr, val);
-	mutex_unlock(&dev->usb.usb_ctrl_mtx);
-
-	return val;
-}
-
-static void mt7921u_copy(struct mt76_dev *dev, u32 offset,
-			 const void *data, int len)
-{
-	struct mt76_usb *usb = &dev->usb;
-	int ret, i = 0, batch_len;
-	const u8 *val = data;
-
-	len = round_up(len, 4);
-
-	mutex_lock(&usb->usb_ctrl_mtx);
-	while (i < len) {
-		batch_len = min_t(int, usb->data_len, len - i);
-		memcpy(usb->data, val + i, batch_len);
-		ret = __mt76u_vendor_request(dev, MT_VEND_WRITE_EXT,
-					     USB_DIR_OUT | MT_USB_TYPE_VENDOR,
-					     (offset + i) >> 16, offset + i,
-					     usb->data, batch_len);
-		if (ret < 0)
-			break;
-
-		i += batch_len;
-	}
-	mutex_unlock(&usb->usb_ctrl_mtx);
-}
-
-int mt7921u_mcu_power_on(struct mt792x_dev *dev)
-{
-	int ret;
-
-	ret = mt76u_vendor_request(&dev->mt76, MT_VEND_POWER_ON,
-				   USB_DIR_OUT | MT_USB_TYPE_VENDOR,
-				   0x0, 0x1, NULL, 0);
-	if (ret)
-		return ret;
-
-	if (!mt76_poll_msec(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_PWR_ON,
-			    MT_TOP_MISC2_FW_PWR_ON, 500)) {
-		dev_err(dev->mt76.dev, "Timeout for power on\n");
-		ret = -EIO;
-	}
-
-	return ret;
-}
-
 static int
 mt7921u_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 			 int cmd, int *seq)
@@ -155,20 +78,69 @@ static int mt7921u_mcu_init(struct mt792x_dev *dev)
 	return 0;
 }
 
-static void mt7921u_stop(struct ieee80211_hw *hw)
+static int mt7921u_mac_reset(struct mt792x_dev *dev)
 {
-	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+	int err;
+
+	mt76_txq_schedule_all(&dev->mphy);
+	mt76_worker_disable(&dev->mt76.tx_worker);
+
+	set_bit(MT76_RESET, &dev->mphy.state);
+	set_bit(MT76_MCU_RESET, &dev->mphy.state);
 
+	wake_up(&dev->mt76.mcu.wait);
+	skb_queue_purge(&dev->mt76.mcu.res_q);
+
+	mt76u_stop_rx(&dev->mt76);
 	mt76u_stop_tx(&dev->mt76);
-	mt7921_stop(hw);
+
+	mt792xu_wfsys_reset(dev);
+
+	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
+	err = mt76u_resume_rx(&dev->mt76);
+	if (err)
+		goto out;
+
+	err = mt792xu_mcu_power_on(dev);
+	if (err)
+		goto out;
+
+	err = mt792xu_dma_init(dev, false);
+	if (err)
+		goto out;
+
+	mt76_wr(dev, MT_SWDEF_MODE, MT_SWDEF_NORMAL_MODE);
+	mt76_set(dev, MT_UDMA_TX_QSEL, MT_FW_DL_EN);
+
+	err = mt7921_run_firmware(dev);
+	if (err)
+		goto out;
+
+	mt76_clear(dev, MT_UDMA_TX_QSEL, MT_FW_DL_EN);
+
+	err = mt7921_mcu_set_eeprom(dev);
+	if (err)
+		goto out;
+
+	err = mt7921_mac_init(dev);
+	if (err)
+		goto out;
+
+	err = __mt7921_start(&dev->phy);
+out:
+	clear_bit(MT76_RESET, &dev->mphy.state);
+
+	mt76_worker_enable(&dev->mt76.tx_worker);
+
+	return err;
 }
 
-static void mt7921u_cleanup(struct mt792x_dev *dev)
+static void mt7921u_stop(struct ieee80211_hw *hw)
 {
-	clear_bit(MT76_STATE_INITIALIZED, &dev->mphy.state);
-	mt7921u_wfsys_reset(dev);
-	skb_queue_purge(&dev->mt76.mcu.res_q);
-	mt76u_queues_deinit(&dev->mt76);
+	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+
+	mt76u_stop_tx(&dev->mt76);
+	mt7921_stop(hw);
 }
 
 static int mt7921u_probe(struct usb_interface *usb_intf,
@@ -193,15 +165,15 @@ static int mt7921u_probe(struct usb_interface *usb_intf,
 	};
 	static const struct mt792x_hif_ops hif_ops = {
 		.mcu_init = mt7921u_mcu_init,
-		.init_reset = mt7921u_init_reset,
+		.init_reset = mt792xu_init_reset,
 		.reset = mt7921u_mac_reset,
 	};
 	static struct mt76_bus_ops bus_ops = {
-		.rr = mt7921u_rr,
-		.wr = mt7921u_wr,
-		.rmw = mt7921u_rmw,
+		.rr = mt792xu_rr,
+		.wr = mt792xu_wr,
+		.rmw = mt792xu_rmw,
 		.read_copy = mt76u_read_copy,
-		.write_copy = mt7921u_copy,
+		.write_copy = mt792xu_copy,
 		.type = MT76_BUS_USB,
 	};
 	struct usb_device *udev = interface_to_usbdev(usb_intf);
@@ -240,12 +212,12 @@ static int mt7921u_probe(struct usb_interface *usb_intf,
 	dev_dbg(mdev->dev, "ASIC revision: %04x\n", mdev->rev);
 
 	if (mt76_get_field(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_N9_RDY)) {
-		ret = mt7921u_wfsys_reset(dev);
+		ret = mt792xu_wfsys_reset(dev);
 		if (ret)
 			goto error;
 	}
 
-	ret = mt7921u_mcu_power_on(dev);
+	ret = mt792xu_mcu_power_on(dev);
 	if (ret)
 		goto error;
 
@@ -257,7 +229,7 @@ static int mt7921u_probe(struct usb_interface *usb_intf,
 	if (ret)
 		goto error;
 
-	ret = mt7921u_dma_init(dev, false);
+	ret = mt792xu_dma_init(dev, false);
 	if (ret)
 		goto error;
 
@@ -291,7 +263,7 @@ static void mt7921u_disconnect(struct usb_interface *usb_intf)
 		return;
 
 	mt76_unregister_device(&dev->mt76);
-	mt7921u_cleanup(dev);
+	mt792xu_cleanup(dev);
 
 	usb_set_intfdata(usb_intf, NULL);
 	usb_put_dev(interface_to_usbdev(usb_intf));
@@ -350,7 +322,7 @@ static int mt7921u_resume(struct usb_interface *intf)
 	}
 
 	if (reinit || mt792x_dma_need_reinit(dev)) {
-		err = mt7921u_dma_init(dev, true);
+		err = mt792xu_dma_init(dev, true);
 		if (err)
 			goto failed;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 1ed688186fe74..b226a863e5de3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -294,6 +294,19 @@ int mt792x_init_wcid(struct mt792x_dev *dev);
 int mt792x_mcu_drv_pmctrl(struct mt792x_dev *dev);
 int mt792x_mcu_fw_pmctrl(struct mt792x_dev *dev);
 
+/* usb */
+#define MT_USB_TYPE_VENDOR	(USB_TYPE_VENDOR | 0x1f)
+#define MT_USB_TYPE_UHW_VENDOR	(USB_TYPE_VENDOR | 0x1e)
+int mt792xu_dma_init(struct mt792x_dev *dev, bool resume);
+int mt792xu_mcu_power_on(struct mt792x_dev *dev);
+int mt792xu_wfsys_reset(struct mt792x_dev *dev);
+int mt792xu_init_reset(struct mt792x_dev *dev);
+u32 mt792xu_rr(struct mt76_dev *dev, u32 addr);
+void mt792xu_wr(struct mt76_dev *dev, u32 addr, u32 val);
+u32 mt792xu_rmw(struct mt76_dev *dev, u32 addr, u32 mask, u32 val);
+void mt792xu_copy(struct mt76_dev *dev, u32 offset, const void *data, int len);
+void mt792xu_cleanup(struct mt792x_dev *dev);
+
 int __mt792xe_mcu_drv_pmctrl(struct mt792x_dev *dev);
 int mt792xe_mcu_drv_pmctrl(struct mt792x_dev *dev);
 int mt792xe_mcu_fw_pmctrl(struct mt792x_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
similarity index 51%
rename from drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c
rename to drivers/net/wireless/mediatek/mt76/mt792x_usb.c
index f7cb6c542af54..97480c9c99743 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: ISC
-/* Copyright (C) 2022 MediaTek Inc.
+/* Copyright (C) 2023 MediaTek Inc.
  *
  * Author: Lorenzo Bianconi <lorenzo@kernel.org>
  */
@@ -8,11 +8,99 @@
 #include <linux/module.h>
 #include <linux/usb.h>
 
-#include "mt7921.h"
-#include "mcu.h"
-#include "../mt76_connac2_mac.h"
+#include "mt792x.h"
+#include "mt76_connac2_mac.h"
 
-static u32 mt7921u_uhw_rr(struct mt76_dev *dev, u32 addr)
+u32 mt792xu_rr(struct mt76_dev *dev, u32 addr)
+{
+	u32 ret;
+
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	ret = ___mt76u_rr(dev, MT_VEND_READ_EXT,
+			  USB_DIR_IN | MT_USB_TYPE_VENDOR, addr);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt792xu_rr);
+
+void mt792xu_wr(struct mt76_dev *dev, u32 addr, u32 val)
+{
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	___mt76u_wr(dev, MT_VEND_WRITE_EXT,
+		    USB_DIR_OUT | MT_USB_TYPE_VENDOR, addr, val);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+}
+EXPORT_SYMBOL_GPL(mt792xu_wr);
+
+u32 mt792xu_rmw(struct mt76_dev *dev, u32 addr, u32 mask, u32 val)
+{
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	val |= ___mt76u_rr(dev, MT_VEND_READ_EXT,
+			   USB_DIR_IN | MT_USB_TYPE_VENDOR, addr) & ~mask;
+	___mt76u_wr(dev, MT_VEND_WRITE_EXT,
+		    USB_DIR_OUT | MT_USB_TYPE_VENDOR, addr, val);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(mt792xu_rmw);
+
+void mt792xu_copy(struct mt76_dev *dev, u32 offset, const void *data, int len)
+{
+	struct mt76_usb *usb = &dev->usb;
+	int ret, i = 0, batch_len;
+	const u8 *val = data;
+
+	len = round_up(len, 4);
+
+	mutex_lock(&usb->usb_ctrl_mtx);
+	while (i < len) {
+		batch_len = min_t(int, usb->data_len, len - i);
+		memcpy(usb->data, val + i, batch_len);
+		ret = __mt76u_vendor_request(dev, MT_VEND_WRITE_EXT,
+					     USB_DIR_OUT | MT_USB_TYPE_VENDOR,
+					     (offset + i) >> 16, offset + i,
+					     usb->data, batch_len);
+		if (ret < 0)
+			break;
+
+		i += batch_len;
+	}
+	mutex_unlock(&usb->usb_ctrl_mtx);
+}
+EXPORT_SYMBOL_GPL(mt792xu_copy);
+
+int mt792xu_mcu_power_on(struct mt792x_dev *dev)
+{
+	int ret;
+
+	ret = mt76u_vendor_request(&dev->mt76, MT_VEND_POWER_ON,
+				   USB_DIR_OUT | MT_USB_TYPE_VENDOR,
+				   0x0, 0x1, NULL, 0);
+	if (ret)
+		return ret;
+
+	if (!mt76_poll_msec(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_PWR_ON,
+			    MT_TOP_MISC2_FW_PWR_ON, 500)) {
+		dev_err(dev->mt76.dev, "Timeout for power on\n");
+		ret = -EIO;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt792xu_mcu_power_on);
+
+void mt792xu_cleanup(struct mt792x_dev *dev)
+{
+	clear_bit(MT76_STATE_INITIALIZED, &dev->mphy.state);
+	mt792xu_wfsys_reset(dev);
+	skb_queue_purge(&dev->mt76.mcu.res_q);
+	mt76u_queues_deinit(&dev->mt76);
+}
+EXPORT_SYMBOL_GPL(mt792xu_cleanup);
+
+static u32 mt792xu_uhw_rr(struct mt76_dev *dev, u32 addr)
 {
 	u32 ret;
 
@@ -24,7 +112,7 @@ static u32 mt7921u_uhw_rr(struct mt76_dev *dev, u32 addr)
 	return ret;
 }
 
-static void mt7921u_uhw_wr(struct mt76_dev *dev, u32 addr, u32 val)
+static void mt792xu_uhw_wr(struct mt76_dev *dev, u32 addr, u32 val)
 {
 	mutex_lock(&dev->usb.usb_ctrl_mtx);
 	___mt76u_wr(dev, MT_VEND_WRITE,
@@ -32,7 +120,7 @@ static void mt7921u_uhw_wr(struct mt76_dev *dev, u32 addr, u32 val)
 	mutex_unlock(&dev->usb.usb_ctrl_mtx);
 }
 
-static void mt7921u_dma_prefetch(struct mt792x_dev *dev)
+static void mt792xu_dma_prefetch(struct mt792x_dev *dev)
 {
 	mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(0),
 		 MT_WPDMA0_MAX_CNT_MASK, 4);
@@ -70,9 +158,9 @@ static void mt7921u_dma_prefetch(struct mt792x_dev *dev)
 		 MT_WPDMA0_BASE_PTR_MASK,  0x2c0);
 }
 
-static void mt7921u_wfdma_init(struct mt792x_dev *dev)
+static void mt792xu_wfdma_init(struct mt792x_dev *dev)
 {
-	mt7921u_dma_prefetch(dev);
+	mt792xu_dma_prefetch(dev);
 
 	mt76_clear(dev, MT_UWFDMA0_GLO_CFG, MT_WFDMA0_GLO_CFG_OMIT_RX_INFO);
 	mt76_set(dev, MT_UWFDMA0_GLO_CFG,
@@ -90,7 +178,7 @@ static void mt7921u_wfdma_init(struct mt792x_dev *dev)
 	mt76_set(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT);
 }
 
-static int mt7921u_dma_rx_evt_ep4(struct mt792x_dev *dev)
+static int mt792xu_dma_rx_evt_ep4(struct mt792x_dev *dev)
 {
 	if (!mt76_poll(dev, MT_UWFDMA0_GLO_CFG,
 		       MT_WFDMA0_GLO_CFG_RX_DMA_BUSY, 0, 1000))
@@ -104,7 +192,7 @@ static int mt7921u_dma_rx_evt_ep4(struct mt792x_dev *dev)
 	return 0;
 }
 
-static void mt7921u_epctl_rst_opt(struct mt792x_dev *dev, bool reset)
+static void mt792xu_epctl_rst_opt(struct mt792x_dev *dev, bool reset)
 {
 	u32 val;
 
@@ -113,19 +201,19 @@ static void mt7921u_epctl_rst_opt(struct mt792x_dev *dev, bool reset)
 	 * bits[20,21]: in blk ep 4-5
 	 * bits[22]: in int ep 6
 	 */
-	val = mt7921u_uhw_rr(&dev->mt76, MT_SSUSB_EPCTL_CSR_EP_RST_OPT);
+	val = mt792xu_uhw_rr(&dev->mt76, MT_SSUSB_EPCTL_CSR_EP_RST_OPT);
 	if (reset)
 		val |= GENMASK(9, 4) | GENMASK(22, 20);
 	else
 		val &= ~(GENMASK(9, 4) | GENMASK(22, 20));
-	mt7921u_uhw_wr(&dev->mt76, MT_SSUSB_EPCTL_CSR_EP_RST_OPT, val);
+	mt792xu_uhw_wr(&dev->mt76, MT_SSUSB_EPCTL_CSR_EP_RST_OPT, val);
 }
 
-int mt7921u_dma_init(struct mt792x_dev *dev, bool resume)
+int mt792xu_dma_init(struct mt792x_dev *dev, bool resume)
 {
 	int err;
 
-	mt7921u_wfdma_init(dev);
+	mt792xu_wfdma_init(dev);
 
 	mt76_clear(dev, MT_UDMA_WLCFG_0, MT_WL_RX_FLUSH);
 
@@ -139,35 +227,36 @@ int mt7921u_dma_init(struct mt792x_dev *dev, bool resume)
 	if (resume)
 		return 0;
 
-	err = mt7921u_dma_rx_evt_ep4(dev);
+	err = mt792xu_dma_rx_evt_ep4(dev);
 	if (err)
 		return err;
 
-	mt7921u_epctl_rst_opt(dev, false);
+	mt792xu_epctl_rst_opt(dev, false);
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mt792xu_dma_init);
 
-int mt7921u_wfsys_reset(struct mt792x_dev *dev)
+int mt792xu_wfsys_reset(struct mt792x_dev *dev)
 {
 	u32 val;
 	int i;
 
-	mt7921u_epctl_rst_opt(dev, false);
+	mt792xu_epctl_rst_opt(dev, false);
 
-	val = mt7921u_uhw_rr(&dev->mt76, MT_CBTOP_RGU_WF_SUBSYS_RST);
+	val = mt792xu_uhw_rr(&dev->mt76, MT_CBTOP_RGU_WF_SUBSYS_RST);
 	val |= MT_CBTOP_RGU_WF_SUBSYS_RST_WF_WHOLE_PATH;
-	mt7921u_uhw_wr(&dev->mt76, MT_CBTOP_RGU_WF_SUBSYS_RST, val);
+	mt792xu_uhw_wr(&dev->mt76, MT_CBTOP_RGU_WF_SUBSYS_RST, val);
 
 	usleep_range(10, 20);
 
-	val = mt7921u_uhw_rr(&dev->mt76, MT_CBTOP_RGU_WF_SUBSYS_RST);
+	val = mt792xu_uhw_rr(&dev->mt76, MT_CBTOP_RGU_WF_SUBSYS_RST);
 	val &= ~MT_CBTOP_RGU_WF_SUBSYS_RST_WF_WHOLE_PATH;
-	mt7921u_uhw_wr(&dev->mt76, MT_CBTOP_RGU_WF_SUBSYS_RST, val);
+	mt792xu_uhw_wr(&dev->mt76, MT_CBTOP_RGU_WF_SUBSYS_RST, val);
 
-	mt7921u_uhw_wr(&dev->mt76, MT_UDMA_CONN_INFRA_STATUS_SEL, 0);
+	mt792xu_uhw_wr(&dev->mt76, MT_UDMA_CONN_INFRA_STATUS_SEL, 0);
 	for (i = 0; i < MT792x_WFSYS_INIT_RETRY_COUNT; i++) {
-		val = mt7921u_uhw_rr(&dev->mt76, MT_UDMA_CONN_INFRA_STATUS);
+		val = mt792xu_uhw_rr(&dev->mt76, MT_UDMA_CONN_INFRA_STATUS);
 		if (val & MT_UDMA_CONN_WFSYS_INIT_DONE)
 			break;
 
@@ -179,8 +268,9 @@ int mt7921u_wfsys_reset(struct mt792x_dev *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mt792xu_wfsys_reset);
 
-int mt7921u_init_reset(struct mt792x_dev *dev)
+int mt792xu_init_reset(struct mt792x_dev *dev)
 {
 	set_bit(MT76_RESET, &dev->mphy.state);
 
@@ -190,66 +280,13 @@ int mt7921u_init_reset(struct mt792x_dev *dev)
 	mt76u_stop_rx(&dev->mt76);
 	mt76u_stop_tx(&dev->mt76);
 
-	mt7921u_wfsys_reset(dev);
+	mt792xu_wfsys_reset(dev);
 
 	clear_bit(MT76_RESET, &dev->mphy.state);
 
 	return mt76u_resume_rx(&dev->mt76);
 }
+EXPORT_SYMBOL_GPL(mt792xu_init_reset);
 
-int mt7921u_mac_reset(struct mt792x_dev *dev)
-{
-	int err;
-
-	mt76_txq_schedule_all(&dev->mphy);
-	mt76_worker_disable(&dev->mt76.tx_worker);
-
-	set_bit(MT76_RESET, &dev->mphy.state);
-	set_bit(MT76_MCU_RESET, &dev->mphy.state);
-
-	wake_up(&dev->mt76.mcu.wait);
-	skb_queue_purge(&dev->mt76.mcu.res_q);
-
-	mt76u_stop_rx(&dev->mt76);
-	mt76u_stop_tx(&dev->mt76);
-
-	mt7921u_wfsys_reset(dev);
-
-	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
-	err = mt76u_resume_rx(&dev->mt76);
-	if (err)
-		goto out;
-
-	err = mt7921u_mcu_power_on(dev);
-	if (err)
-		goto out;
-
-	err = mt7921u_dma_init(dev, false);
-	if (err)
-		goto out;
-
-	mt76_wr(dev, MT_SWDEF_MODE, MT_SWDEF_NORMAL_MODE);
-	mt76_set(dev, MT_UDMA_TX_QSEL, MT_FW_DL_EN);
-
-	err = mt7921_run_firmware(dev);
-	if (err)
-		goto out;
-
-	mt76_clear(dev, MT_UDMA_TX_QSEL, MT_FW_DL_EN);
-
-	err = mt7921_mcu_set_eeprom(dev);
-	if (err)
-		goto out;
-
-	err = mt7921_mac_init(dev);
-	if (err)
-		goto out;
-
-	err = __mt7921_start(&dev->phy);
-out:
-	clear_bit(MT76_RESET, &dev->mphy.state);
-
-	mt76_worker_enable(&dev->mt76.tx_worker);
-
-	return err;
-}
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
-- 
GitLab


From 583204ae70f9f4d1cf8f2874a6c0706e5528eab1 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:20 +0800
Subject: [PATCH 0479/1806] wifi: mt76: mt792x: move mt7921_load_firmware in
 mt792x-lib module

mt7921_load_firmware routine is shared between mt7921 and mt7925 chipset
so move it in mt792x-lib module.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/mcu.c   | 63 +------------------
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  6 --
 drivers/net/wireless/mediatek/mt76/mt792x.h   | 28 +++++++++
 .../net/wireless/mediatek/mt76/mt792x_core.c  | 36 +++++++++++
 4 files changed, 66 insertions(+), 67 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index e9caf750bca55..4b77d95af9589 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -364,30 +364,6 @@ int mt7921_mcu_uni_rx_ba(struct mt792x_dev *dev,
 				      enable, false);
 }
 
-static char *mt7921_patch_name(struct mt792x_dev *dev)
-{
-	char *ret;
-
-	if (is_mt7922(&dev->mt76))
-		ret = MT7922_ROM_PATCH;
-	else
-		ret = MT7921_ROM_PATCH;
-
-	return ret;
-}
-
-static char *mt7921_ram_name(struct mt792x_dev *dev)
-{
-	char *ret;
-
-	if (is_mt7922(&dev->mt76))
-		ret = MT7922_FIRMWARE_WM;
-	else
-		ret = MT7921_FIRMWARE_WM;
-
-	return ret;
-}
-
 static int mt7921_load_clc(struct mt792x_dev *dev, const char *fw_name)
 {
 	const struct mt76_connac2_fw_trailer *hdr;
@@ -472,41 +448,6 @@ out:
 	return ret;
 }
 
-static int mt7921_load_firmware(struct mt792x_dev *dev)
-{
-	int ret;
-
-	ret = mt76_connac2_load_patch(&dev->mt76, mt7921_patch_name(dev));
-	if (ret)
-		return ret;
-
-	if (mt76_is_sdio(&dev->mt76)) {
-		/* activate again */
-		ret = __mt792x_mcu_fw_pmctrl(dev);
-		if (!ret)
-			ret = __mt792x_mcu_drv_pmctrl(dev);
-	}
-
-	ret = mt76_connac2_load_ram(&dev->mt76, mt7921_ram_name(dev), NULL);
-	if (ret)
-		return ret;
-
-	if (!mt76_poll_msec(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_N9_RDY,
-			    MT_TOP_MISC2_FW_N9_RDY, 1500)) {
-		dev_err(dev->mt76.dev, "Timeout for initializing firmware\n");
-
-		return -EIO;
-	}
-
-#ifdef CONFIG_PM
-	dev->mt76.hw->wiphy->wowlan = &mt76_connac_wowlan_support;
-#endif /* CONFIG_PM */
-
-	dev_dbg(dev->mt76.dev, "Firmware init done\n");
-
-	return 0;
-}
-
 int mt7921_mcu_fw_log_2_host(struct mt792x_dev *dev, u8 ctrl)
 {
 	struct {
@@ -524,7 +465,7 @@ int mt7921_run_firmware(struct mt792x_dev *dev)
 {
 	int err;
 
-	err = mt7921_load_firmware(dev);
+	err = mt792x_load_firmware(dev);
 	if (err)
 		return err;
 
@@ -533,7 +474,7 @@ int mt7921_run_firmware(struct mt792x_dev *dev)
 		return err;
 
 	set_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state);
-	err = mt7921_load_clc(dev, mt7921_ram_name(dev));
+	err = mt7921_load_clc(dev, mt792x_ram_name(dev));
 	if (err)
 		return err;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index cb22be083242e..e458ddb7d99a7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -17,12 +17,6 @@
 #define MT7921_RX_RING_SIZE		1536
 #define MT7921_RX_MCU_RING_SIZE		512
 
-#define MT7921_FIRMWARE_WM		"mediatek/WIFI_RAM_CODE_MT7961_1.bin"
-#define MT7921_ROM_PATCH		"mediatek/WIFI_MT7961_patch_mcu_1_2_hdr.bin"
-
-#define MT7922_FIRMWARE_WM		"mediatek/WIFI_RAM_CODE_MT7922_1.bin"
-#define MT7922_ROM_PATCH		"mediatek/WIFI_MT7922_patch_mcu_1_1_hdr.bin"
-
 #define MT7921_EEPROM_SIZE		3584
 #define MT7921_TOKEN_SIZE		8192
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index b226a863e5de3..700cd0ccc5d39 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -31,6 +31,12 @@
 #define MT792x_MCU_INIT_RETRY_COUNT	10
 #define MT792x_WFSYS_INIT_RETRY_COUNT	2
 
+#define MT7921_FIRMWARE_WM	"mediatek/WIFI_RAM_CODE_MT7961_1.bin"
+#define MT7922_FIRMWARE_WM	"mediatek/WIFI_RAM_CODE_MT7922_1.bin"
+
+#define MT7921_ROM_PATCH	"mediatek/WIFI_MT7961_patch_mcu_1_2_hdr.bin"
+#define MT7922_ROM_PATCH	"mediatek/WIFI_MT7922_patch_mcu_1_1_hdr.bin"
+
 struct mt792x_vif;
 struct mt792x_sta;
 
@@ -294,6 +300,28 @@ int mt792x_init_wcid(struct mt792x_dev *dev);
 int mt792x_mcu_drv_pmctrl(struct mt792x_dev *dev);
 int mt792x_mcu_fw_pmctrl(struct mt792x_dev *dev);
 
+static inline char *mt792x_ram_name(struct mt792x_dev *dev)
+{
+	switch (mt76_chip(&dev->mt76)) {
+	case 0x7922:
+		return MT7922_FIRMWARE_WM;
+	default:
+		return MT7921_FIRMWARE_WM;
+	}
+}
+
+static inline char *mt792x_patch_name(struct mt792x_dev *dev)
+{
+	switch (mt76_chip(&dev->mt76)) {
+	case 0x7922:
+		return MT7922_ROM_PATCH;
+	default:
+		return MT7921_ROM_PATCH;
+	}
+}
+
+int mt792x_load_firmware(struct mt792x_dev *dev);
+
 /* usb */
 #define MT_USB_TYPE_VENDOR	(USB_TYPE_VENDOR | 0x1f)
 #define MT_USB_TYPE_UHW_VENDOR	(USB_TYPE_VENDOR | 0x1e)
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index f7dfc2189cc83..46be7f996c7e1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -804,5 +804,41 @@ int mt792xe_mcu_fw_pmctrl(struct mt792x_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt792xe_mcu_fw_pmctrl);
 
+int mt792x_load_firmware(struct mt792x_dev *dev)
+{
+	int ret;
+
+	ret = mt76_connac2_load_patch(&dev->mt76, mt792x_patch_name(dev));
+	if (ret)
+		return ret;
+
+	if (mt76_is_sdio(&dev->mt76)) {
+		/* activate again */
+		ret = __mt792x_mcu_fw_pmctrl(dev);
+		if (!ret)
+			ret = __mt792x_mcu_drv_pmctrl(dev);
+	}
+
+	ret = mt76_connac2_load_ram(&dev->mt76, mt792x_ram_name(dev), NULL);
+	if (ret)
+		return ret;
+
+	if (!mt76_poll_msec(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_N9_RDY,
+			    MT_TOP_MISC2_FW_N9_RDY, 1500)) {
+		dev_err(dev->mt76.dev, "Timeout for initializing firmware\n");
+
+		return -EIO;
+	}
+
+#ifdef CONFIG_PM
+	dev->mt76.hw->wiphy->wowlan = &mt76_connac_wowlan_support;
+#endif /* CONFIG_PM */
+
+	dev_dbg(dev->mt76.dev, "Firmware init done\n");
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt792x_load_firmware);
+
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
-- 
GitLab


From 81d4c943a168fc32eeb77e9b97ffd650db932ded Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:21 +0800
Subject: [PATCH 0480/1806] wifi: mt76: mt76_connac3: move lmac queue
 enumeration in mt76_connac3_mac.h

This is a preliminary patch to introduce mt7925 chip support

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt76_connac3_mac.h  | 14 ++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h | 14 --------------
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
index 6663a0b46541a..68ca0844cbbfa 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
@@ -4,6 +4,20 @@
 #ifndef __MT76_CONNAC3_MAC_H
 #define __MT76_CONNAC3_MAC_H
 
+enum {
+	MT_CTX0,
+	MT_HIF0 = 0x0,
+
+	MT_LMAC_AC00 = 0x0,
+	MT_LMAC_AC01,
+	MT_LMAC_AC02,
+	MT_LMAC_AC03,
+	MT_LMAC_ALTX0 = 0x10,
+	MT_LMAC_BMC0,
+	MT_LMAC_BCN0,
+	MT_LMAC_PSMP0,
+};
+
 #define MT_CT_PARSE_LEN			72
 #define MT_CT_DMA_BUF_NUM		2
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 726c222e8e1e3..7354e5cf8e674 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -254,20 +254,6 @@ enum {
 	__MT_WFDMA_MAX,
 };
 
-enum {
-	MT_CTX0,
-	MT_HIF0 = 0x0,
-
-	MT_LMAC_AC00 = 0x0,
-	MT_LMAC_AC01,
-	MT_LMAC_AC02,
-	MT_LMAC_AC03,
-	MT_LMAC_ALTX0 = 0x10,
-	MT_LMAC_BMC0,
-	MT_LMAC_BCN0,
-	MT_LMAC_PSMP0,
-};
-
 enum {
 	MT_RX_SEL0,
 	MT_RX_SEL1,
-- 
GitLab


From 7d403f3a19c6687f51c5e7423e28ddfd00983477 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:22 +0800
Subject: [PATCH 0481/1806] wifi: mt76: mt792x: move MT7921_PM_TIMEOUT and
 MT7921_HW_SCAN_TIMEOUT in common code

MT7921_PM_TIMEOUT is shared between mt7925 and mt7921 so move it in
mt792x module.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/init.c   | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/mcu.c    | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h | 3 ---
 drivers/net/wireless/mediatek/mt76/mt792x.h        | 3 +++
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 7b8876bf8fc8c..ff63f37f67d9c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -217,7 +217,7 @@ int mt7921_register_device(struct mt792x_dev *dev)
 	timer_setup(&dev->phy.roc_timer, mt792x_roc_timer, 0);
 	init_waitqueue_head(&dev->phy.roc_wait);
 
-	dev->pm.idle_timeout = MT7921_PM_TIMEOUT;
+	dev->pm.idle_timeout = MT792x_PM_TIMEOUT;
 	dev->pm.stats.last_wake_event = jiffies;
 	dev->pm.stats.last_doze_event = jiffies;
 	if (!mt76_is_usb(&dev->mt76)) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 4b77d95af9589..90c93970acabc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -167,7 +167,7 @@ mt7921_mcu_scan_event(struct mt792x_dev *dev, struct sk_buff *skb)
 	spin_unlock_bh(&dev->mt76.lock);
 
 	ieee80211_queue_delayed_work(mphy->hw, &phy->scan_work,
-				     MT7921_HW_SCAN_TIMEOUT);
+				     MT792x_HW_SCAN_TIMEOUT);
 }
 
 static void
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index e458ddb7d99a7..0f8b93a2be3a0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -7,9 +7,6 @@
 #include "../mt792x.h"
 #include "regs.h"
 
-#define MT7921_PM_TIMEOUT		(HZ / 12)
-#define MT7921_HW_SCAN_TIMEOUT		(HZ / 10)
-
 #define MT7921_TX_RING_SIZE		2048
 #define MT7921_TX_MCU_RING_SIZE		256
 #define MT7921_TX_FWDL_RING_SIZE	128
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 700cd0ccc5d39..d80f80bc76565 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -11,6 +11,9 @@
 #include "mt792x_regs.h"
 #include "mt792x_acpi_sar.h"
 
+#define MT792x_PM_TIMEOUT	(HZ / 12)
+#define MT792x_HW_SCAN_TIMEOUT	(HZ / 10)
+
 #define MT792x_MAX_INTERFACES	4
 #define MT792x_WTBL_SIZE	20
 #define MT792x_WTBL_RESERVED	(MT792x_WTBL_SIZE - 1)
-- 
GitLab


From 2e7f7a2c871cd3b4a01c0a325f86f5b112f3b50f Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:23 +0800
Subject: [PATCH 0482/1806] wifi: mt76: mt7921: move mt7921_dma_init in pci.c

Move mt7921_dma_init routine in pci.c and make it static since it is run
just in mt7921_pci_probe(). Get rid of dma.c.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7921/Makefile    |  2 +-
 .../net/wireless/mediatek/mt76/mt7921/dma.c   | 71 -------------------
 .../wireless/mediatek/mt76/mt7921/mt7921.h    |  1 -
 .../net/wireless/mediatek/mt76/mt7921/pci.c   | 66 +++++++++++++++++
 4 files changed, 67 insertions(+), 73 deletions(-)
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt7921/dma.c

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/Makefile b/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
index 964eb55824cd0..849be9e848e0a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/Makefile
@@ -7,6 +7,6 @@ obj-$(CONFIG_MT7921U) += mt7921u.o
 
 mt7921-common-y := mac.o mcu.o main.o init.o debugfs.o
 mt7921-common-$(CONFIG_NL80211_TESTMODE) += testmode.o
-mt7921e-y := pci.o pci_mac.o pci_mcu.o dma.o
+mt7921e-y := pci.o pci_mac.o pci_mcu.o
 mt7921s-y := sdio.o sdio_mac.o sdio_mcu.o
 mt7921u-y := usb.o
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
deleted file mode 100644
index fdc598e099f66..0000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
+++ /dev/null
@@ -1,71 +0,0 @@
-// SPDX-License-Identifier: ISC
-/* Copyright (C) 2020 MediaTek Inc. */
-
-#include "mt7921.h"
-#include "../dma.h"
-#include "../mt76_connac2_mac.h"
-
-int mt7921_dma_init(struct mt792x_dev *dev)
-{
-	int ret;
-
-	mt76_dma_attach(&dev->mt76);
-
-	ret = mt792x_dma_disable(dev, true);
-	if (ret)
-		return ret;
-
-	/* init tx queue */
-	ret = mt76_connac_init_tx_queues(dev->phy.mt76, MT7921_TXQ_BAND0,
-					 MT7921_TX_RING_SIZE,
-					 MT_TX_RING_BASE, 0);
-	if (ret)
-		return ret;
-
-	mt76_wr(dev, MT_WFDMA0_TX_RING0_EXT_CTRL, 0x4);
-
-	/* command to WM */
-	ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_WM, MT7921_TXQ_MCU_WM,
-				  MT7921_TX_MCU_RING_SIZE, MT_TX_RING_BASE);
-	if (ret)
-		return ret;
-
-	/* firmware download */
-	ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_FWDL, MT7921_TXQ_FWDL,
-				  MT7921_TX_FWDL_RING_SIZE, MT_TX_RING_BASE);
-	if (ret)
-		return ret;
-
-	/* event from WM before firmware download */
-	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU],
-			       MT7921_RXQ_MCU_WM,
-			       MT7921_RX_MCU_RING_SIZE,
-			       MT_RX_BUF_SIZE, MT_RX_EVENT_RING_BASE);
-	if (ret)
-		return ret;
-
-	/* Change mcu queue after firmware download */
-	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU_WA],
-			       MT7921_RXQ_MCU_WM,
-			       MT7921_RX_MCU_RING_SIZE,
-			       MT_RX_BUF_SIZE, MT_WFDMA0(0x540));
-	if (ret)
-		return ret;
-
-	/* rx data */
-	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN],
-			       MT7921_RXQ_BAND0, MT7921_RX_RING_SIZE,
-			       MT_RX_BUF_SIZE, MT_RX_DATA_RING_BASE);
-	if (ret)
-		return ret;
-
-	ret = mt76_init_queues(dev, mt792x_poll_rx);
-	if (ret < 0)
-		return ret;
-
-	netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi,
-			  mt792x_poll_tx);
-	napi_enable(&dev->mt76.tx_napi);
-
-	return mt792x_dma_enable(dev);
-}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 0f8b93a2be3a0..87dd06855f685 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -182,7 +182,6 @@ u32 mt7921_reg_map(struct mt792x_dev *dev, u32 addr);
 int __mt7921_start(struct mt792x_phy *phy);
 int mt7921_register_device(struct mt792x_dev *dev);
 void mt7921_unregister_device(struct mt792x_dev *dev);
-int mt7921_dma_init(struct mt792x_dev *dev);
 int mt7921_run_firmware(struct mt792x_dev *dev);
 int mt7921_mcu_set_bss_pm(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 			  bool enable);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index c3f22ce9f5c46..3dda84a937175 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -9,6 +9,7 @@
 
 #include "mt7921.h"
 #include "../mt76_connac2_mac.h"
+#include "../dma.h"
 #include "mcu.h"
 
 static const struct pci_device_id mt7921_pci_device_table[] = {
@@ -155,6 +156,71 @@ static u32 mt7921_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val)
 	return dev->bus_ops->rmw(mdev, addr, mask, val);
 }
 
+static int mt7921_dma_init(struct mt792x_dev *dev)
+{
+	int ret;
+
+	mt76_dma_attach(&dev->mt76);
+
+	ret = mt792x_dma_disable(dev, true);
+	if (ret)
+		return ret;
+
+	/* init tx queue */
+	ret = mt76_connac_init_tx_queues(dev->phy.mt76, MT7921_TXQ_BAND0,
+					 MT7921_TX_RING_SIZE,
+					 MT_TX_RING_BASE, 0);
+	if (ret)
+		return ret;
+
+	mt76_wr(dev, MT_WFDMA0_TX_RING0_EXT_CTRL, 0x4);
+
+	/* command to WM */
+	ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_WM, MT7921_TXQ_MCU_WM,
+				  MT7921_TX_MCU_RING_SIZE, MT_TX_RING_BASE);
+	if (ret)
+		return ret;
+
+	/* firmware download */
+	ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_FWDL, MT7921_TXQ_FWDL,
+				  MT7921_TX_FWDL_RING_SIZE, MT_TX_RING_BASE);
+	if (ret)
+		return ret;
+
+	/* event from WM before firmware download */
+	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU],
+			       MT7921_RXQ_MCU_WM,
+			       MT7921_RX_MCU_RING_SIZE,
+			       MT_RX_BUF_SIZE, MT_RX_EVENT_RING_BASE);
+	if (ret)
+		return ret;
+
+	/* Change mcu queue after firmware download */
+	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU_WA],
+			       MT7921_RXQ_MCU_WM,
+			       MT7921_RX_MCU_RING_SIZE,
+			       MT_RX_BUF_SIZE, MT_WFDMA0(0x540));
+	if (ret)
+		return ret;
+
+	/* rx data */
+	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN],
+			       MT7921_RXQ_BAND0, MT7921_RX_RING_SIZE,
+			       MT_RX_BUF_SIZE, MT_RX_DATA_RING_BASE);
+	if (ret)
+		return ret;
+
+	ret = mt76_init_queues(dev, mt792x_poll_rx);
+	if (ret < 0)
+		return ret;
+
+	netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi,
+			  mt792x_poll_tx);
+	napi_enable(&dev->mt76.tx_napi);
+
+	return mt792x_dma_enable(dev);
+}
+
 static int mt7921_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *id)
 {
-- 
GitLab


From fc80731ba06316da80be2993c91c315c9923dac0 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 28 Jun 2023 15:07:24 +0800
Subject: [PATCH 0483/1806] wifi: mt76: mt7921: move mt7921u_disconnect
 mt792x-lib

mt7921u_disconnect routine is shared between mt7921 and mt7925 so move
it in mt792x-usb module.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7921/usb.c   | 19 +----------------
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  2 +-
 .../net/wireless/mediatek/mt76/mt792x_usb.c   | 21 +++++++++++++++++--
 3 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index c3981bc893aca..59cd3d98bf908 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -254,23 +254,6 @@ error:
 	return ret;
 }
 
-static void mt7921u_disconnect(struct usb_interface *usb_intf)
-{
-	struct mt792x_dev *dev = usb_get_intfdata(usb_intf);
-
-	cancel_work_sync(&dev->init_work);
-	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state))
-		return;
-
-	mt76_unregister_device(&dev->mt76);
-	mt792xu_cleanup(dev);
-
-	usb_set_intfdata(usb_intf, NULL);
-	usb_put_dev(interface_to_usbdev(usb_intf));
-
-	mt76_free_device(&dev->mt76);
-}
-
 #ifdef CONFIG_PM
 static int mt7921u_suspend(struct usb_interface *intf, pm_message_t state)
 {
@@ -350,7 +333,7 @@ static struct usb_driver mt7921u_driver = {
 	.name		= KBUILD_MODNAME,
 	.id_table	= mt7921u_device_table,
 	.probe		= mt7921u_probe,
-	.disconnect	= mt7921u_disconnect,
+	.disconnect	= mt792xu_disconnect,
 #ifdef CONFIG_PM
 	.suspend	= mt7921u_suspend,
 	.resume		= mt7921u_resume,
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index d80f80bc76565..5d5ab8630041b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -336,7 +336,7 @@ u32 mt792xu_rr(struct mt76_dev *dev, u32 addr);
 void mt792xu_wr(struct mt76_dev *dev, u32 addr, u32 val);
 u32 mt792xu_rmw(struct mt76_dev *dev, u32 addr, u32 mask, u32 val);
 void mt792xu_copy(struct mt76_dev *dev, u32 offset, const void *data, int len);
-void mt792xu_cleanup(struct mt792x_dev *dev);
+void mt792xu_disconnect(struct usb_interface *usb_intf);
 
 int __mt792xe_mcu_drv_pmctrl(struct mt792x_dev *dev);
 int mt792xe_mcu_drv_pmctrl(struct mt792x_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
index 97480c9c99743..20e7f9c7c88c0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
@@ -91,14 +91,13 @@ int mt792xu_mcu_power_on(struct mt792x_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt792xu_mcu_power_on);
 
-void mt792xu_cleanup(struct mt792x_dev *dev)
+static void mt792xu_cleanup(struct mt792x_dev *dev)
 {
 	clear_bit(MT76_STATE_INITIALIZED, &dev->mphy.state);
 	mt792xu_wfsys_reset(dev);
 	skb_queue_purge(&dev->mt76.mcu.res_q);
 	mt76u_queues_deinit(&dev->mt76);
 }
-EXPORT_SYMBOL_GPL(mt792xu_cleanup);
 
 static u32 mt792xu_uhw_rr(struct mt76_dev *dev, u32 addr)
 {
@@ -288,5 +287,23 @@ int mt792xu_init_reset(struct mt792x_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt792xu_init_reset);
 
+void mt792xu_disconnect(struct usb_interface *usb_intf)
+{
+	struct mt792x_dev *dev = usb_get_intfdata(usb_intf);
+
+	cancel_work_sync(&dev->init_work);
+	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state))
+		return;
+
+	mt76_unregister_device(&dev->mt76);
+	mt792xu_cleanup(dev);
+
+	usb_set_intfdata(usb_intf, NULL);
+	usb_put_dev(interface_to_usbdev(usb_intf));
+
+	mt76_free_device(&dev->mt76);
+}
+EXPORT_SYMBOL_GPL(mt792xu_disconnect);
+
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
-- 
GitLab


From 74f12d511625e603fac8c0c2b6872e687e56dd61 Mon Sep 17 00:00:00 2001
From: Lin Ma <linma@zju.edu.cn>
Date: Sun, 23 Jul 2023 16:03:50 +0800
Subject: [PATCH 0484/1806] wifi: mt76: testmode: add nla_policy for
 MT76_TM_ATTR_TX_LENGTH

It seems that the nla_policy in mt76_tm_policy is missed for attribute
MT76_TM_ATTR_TX_LENGTH. This patch adds the correct description to make
sure the

  u32 val = nla_get_u32(tb[MT76_TM_ATTR_TX_LENGTH]);

in function mt76_testmode_cmd() is safe and will not result in
out-of-attribute read.

Fixes: f0efa8621550 ("mt76: add API for testmode support")
Signed-off-by: Lin Ma <linma@zju.edu.cn>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/testmode.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/testmode.c b/drivers/net/wireless/mediatek/mt76/testmode.c
index 0accc71a91c9a..4644dace9bb34 100644
--- a/drivers/net/wireless/mediatek/mt76/testmode.c
+++ b/drivers/net/wireless/mediatek/mt76/testmode.c
@@ -8,6 +8,7 @@ const struct nla_policy mt76_tm_policy[NUM_MT76_TM_ATTRS] = {
 	[MT76_TM_ATTR_RESET] = { .type = NLA_FLAG },
 	[MT76_TM_ATTR_STATE] = { .type = NLA_U8 },
 	[MT76_TM_ATTR_TX_COUNT] = { .type = NLA_U32 },
+	[MT76_TM_ATTR_TX_LENGTH] = { .type = NLA_U32 },
 	[MT76_TM_ATTR_TX_RATE_MODE] = { .type = NLA_U8 },
 	[MT76_TM_ATTR_TX_RATE_NSS] = { .type = NLA_U8 },
 	[MT76_TM_ATTR_TX_RATE_IDX] = { .type = NLA_U8 },
-- 
GitLab


From 8b305ee2a91c3c4c89cb82ea940265b247eb0a13 Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Tue, 25 Jul 2023 16:54:30 -0700
Subject: [PATCH 0485/1806] net: phy: smsc: add WoL support to LAN8740/LAN8742
 PHYs

Microchip LAN8740/LAN8742 PHYs support basic unicast, broadcast, and
Magic Packet WoL.  They have one pattern filter matching up to 128 bytes
of frame data, which can be used to implement ARP or multicast WoL.

ARP WoL matches any ARP frame with broadcast address.

Multicast WoL matches any multicast frame.

Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/1690329270-2873-1-git-send-email-Tristram.Ha@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/Kconfig |   1 +
 drivers/net/phy/smsc.c  | 252 +++++++++++++++++++++++++++++++++++++++-
 include/linux/smscphy.h |  34 ++++++
 3 files changed, 285 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 87b8238587173..67aaeb75301fb 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -350,6 +350,7 @@ config ROCKCHIP_PHY
 
 config SMSC_PHY
 	tristate "SMSC PHYs"
+	select CRC16
 	help
 	  Currently supports the LAN83C185, LAN8187 and LAN8700 PHYs
 
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 6929307502151..c88edb19d2e71 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -20,6 +20,8 @@
 #include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/netdevice.h>
+#include <linux/crc16.h>
+#include <linux/etherdevice.h>
 #include <linux/smscphy.h>
 
 /* Vendor-specific PHY Definitions */
@@ -51,6 +53,7 @@ struct smsc_phy_priv {
 	unsigned int edpd_enable:1;
 	unsigned int edpd_mode_set_by_user:1;
 	unsigned int edpd_max_wait_ms;
+	bool wol_arp;
 };
 
 static int smsc_phy_ack_interrupt(struct phy_device *phydev)
@@ -258,6 +261,243 @@ int lan87xx_read_status(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(lan87xx_read_status);
 
+static int lan874x_phy_config_init(struct phy_device *phydev)
+{
+	u16 val;
+	int rc;
+
+	/* Setup LED2/nINT/nPME pin to function as nPME.  May need user option
+	 * to use LED1/nINT/nPME.
+	 */
+	val = MII_LAN874X_PHY_PME2_SET;
+
+	/* The bits MII_LAN874X_PHY_WOL_PFDA_FR, MII_LAN874X_PHY_WOL_WUFR,
+	 * MII_LAN874X_PHY_WOL_MPR, and MII_LAN874X_PHY_WOL_BCAST_FR need to
+	 * be cleared to de-assert PME signal after a WoL event happens, but
+	 * using PME auto clear gets around that.
+	 */
+	val |= MII_LAN874X_PHY_PME_SELF_CLEAR;
+	rc = phy_write_mmd(phydev, MDIO_MMD_PCS, MII_LAN874X_PHY_MMD_WOL_WUCSR,
+			   val);
+	if (rc < 0)
+		return rc;
+
+	/* set nPME self clear delay time */
+	rc = phy_write_mmd(phydev, MDIO_MMD_PCS, MII_LAN874X_PHY_MMD_MCFGR,
+			   MII_LAN874X_PHY_PME_SELF_CLEAR_DELAY);
+	if (rc < 0)
+		return rc;
+
+	return smsc_phy_config_init(phydev);
+}
+
+static void lan874x_get_wol(struct phy_device *phydev,
+			    struct ethtool_wolinfo *wol)
+{
+	struct smsc_phy_priv *priv = phydev->priv;
+	int rc;
+
+	wol->supported = (WAKE_UCAST | WAKE_BCAST | WAKE_MAGIC |
+			  WAKE_ARP | WAKE_MCAST);
+	wol->wolopts = 0;
+
+	rc = phy_read_mmd(phydev, MDIO_MMD_PCS, MII_LAN874X_PHY_MMD_WOL_WUCSR);
+	if (rc < 0)
+		return;
+
+	if (rc & MII_LAN874X_PHY_WOL_PFDAEN)
+		wol->wolopts |= WAKE_UCAST;
+
+	if (rc & MII_LAN874X_PHY_WOL_BCSTEN)
+		wol->wolopts |= WAKE_BCAST;
+
+	if (rc & MII_LAN874X_PHY_WOL_MPEN)
+		wol->wolopts |= WAKE_MAGIC;
+
+	if (rc & MII_LAN874X_PHY_WOL_WUEN) {
+		if (priv->wol_arp)
+			wol->wolopts |= WAKE_ARP;
+		else
+			wol->wolopts |= WAKE_MCAST;
+	}
+}
+
+static u16 smsc_crc16(const u8 *buffer, size_t len)
+{
+	return bitrev16(crc16(0xFFFF, buffer, len));
+}
+
+static int lan874x_chk_wol_pattern(const u8 pattern[], const u16 *mask,
+				   u8 len, u8 *data, u8 *datalen)
+{
+	size_t i, j, k;
+	int ret = 0;
+	u16 bits;
+
+	/* Pattern filtering can match up to 128 bytes of frame data.  There
+	 * are 8 registers to program the 16-bit masks, where each bit means
+	 * the byte will be compared.  The frame data will then go through a
+	 * CRC16 calculation for hardware comparison.  This helper function
+	 * makes sure only relevant frame data are included in this
+	 * calculation.  It provides a warning when the masks and expected
+	 * data size do not match.
+	 */
+	i = 0;
+	k = 0;
+	while (len > 0) {
+		bits = *mask;
+		for (j = 0; j < 16; j++, i++, len--) {
+			/* No more pattern. */
+			if (!len) {
+				/* The rest of bitmap is not empty. */
+				if (bits)
+					ret = i + 1;
+				break;
+			}
+			if (bits & 1)
+				data[k++] = pattern[i];
+			bits >>= 1;
+		}
+		mask++;
+	}
+	*datalen = k;
+	return ret;
+}
+
+static int lan874x_set_wol_pattern(struct phy_device *phydev, u16 val,
+				   const u8 data[], u8 datalen,
+				   const u16 *mask, u8 masklen)
+{
+	u16 crc, reg;
+	int rc;
+
+	/* Starting pattern offset is set before calling this function. */
+	val |= MII_LAN874X_PHY_WOL_FILTER_EN;
+	rc = phy_write_mmd(phydev, MDIO_MMD_PCS,
+			   MII_LAN874X_PHY_MMD_WOL_WUF_CFGA, val);
+	if (rc < 0)
+		return rc;
+
+	crc = smsc_crc16(data, datalen);
+	rc = phy_write_mmd(phydev, MDIO_MMD_PCS,
+			   MII_LAN874X_PHY_MMD_WOL_WUF_CFGB, crc);
+	if (rc < 0)
+		return rc;
+
+	masklen = (masklen + 15) & ~0xf;
+	reg = MII_LAN874X_PHY_MMD_WOL_WUF_MASK7;
+	while (masklen >= 16) {
+		rc = phy_write_mmd(phydev, MDIO_MMD_PCS, reg, *mask);
+		if (rc < 0)
+			return rc;
+		reg--;
+		mask++;
+		masklen -= 16;
+	}
+
+	/* Clear out the rest of mask registers. */
+	while (reg != MII_LAN874X_PHY_MMD_WOL_WUF_MASK0) {
+		phy_write_mmd(phydev, MDIO_MMD_PCS, reg, 0);
+		reg--;
+	}
+	return rc;
+}
+
+static int lan874x_set_wol(struct phy_device *phydev,
+			   struct ethtool_wolinfo *wol)
+{
+	struct net_device *ndev = phydev->attached_dev;
+	struct smsc_phy_priv *priv = phydev->priv;
+	u16 val, val_wucsr;
+	u8 data[128];
+	u8 datalen;
+	int rc;
+
+	/* lan874x has only one WoL filter pattern */
+	if ((wol->wolopts & (WAKE_ARP | WAKE_MCAST)) ==
+	    (WAKE_ARP | WAKE_MCAST)) {
+		phydev_info(phydev,
+			    "lan874x WoL supports one of ARP|MCAST at a time\n");
+		return -EOPNOTSUPP;
+	}
+
+	rc = phy_read_mmd(phydev, MDIO_MMD_PCS, MII_LAN874X_PHY_MMD_WOL_WUCSR);
+	if (rc < 0)
+		return rc;
+
+	val_wucsr = rc;
+
+	if (wol->wolopts & WAKE_UCAST)
+		val_wucsr |= MII_LAN874X_PHY_WOL_PFDAEN;
+	else
+		val_wucsr &= ~MII_LAN874X_PHY_WOL_PFDAEN;
+
+	if (wol->wolopts & WAKE_BCAST)
+		val_wucsr |= MII_LAN874X_PHY_WOL_BCSTEN;
+	else
+		val_wucsr &= ~MII_LAN874X_PHY_WOL_BCSTEN;
+
+	if (wol->wolopts & WAKE_MAGIC)
+		val_wucsr |= MII_LAN874X_PHY_WOL_MPEN;
+	else
+		val_wucsr &= ~MII_LAN874X_PHY_WOL_MPEN;
+
+	/* Need to use pattern matching */
+	if (wol->wolopts & (WAKE_ARP | WAKE_MCAST))
+		val_wucsr |= MII_LAN874X_PHY_WOL_WUEN;
+	else
+		val_wucsr &= ~MII_LAN874X_PHY_WOL_WUEN;
+
+	if (wol->wolopts & WAKE_ARP) {
+		const u8 pattern[2] = { 0x08, 0x06 };
+		const u16 mask[1] = { 0x0003 };
+
+		rc = lan874x_chk_wol_pattern(pattern, mask, 2, data,
+					     &datalen);
+		if (rc)
+			phydev_dbg(phydev, "pattern not valid at %d\n", rc);
+
+		/* Need to match broadcast destination address and provided
+		 * data pattern at offset 12.
+		 */
+		val = 12 | MII_LAN874X_PHY_WOL_FILTER_BCSTEN;
+		rc = lan874x_set_wol_pattern(phydev, val, data, datalen, mask,
+					     2);
+		if (rc < 0)
+			return rc;
+		priv->wol_arp = true;
+	}
+
+	if (wol->wolopts & WAKE_MCAST) {
+		/* Need to match multicast destination address. */
+		val = MII_LAN874X_PHY_WOL_FILTER_MCASTTEN;
+		rc = lan874x_set_wol_pattern(phydev, val, data, 0, NULL, 0);
+		if (rc < 0)
+			return rc;
+		priv->wol_arp = false;
+	}
+
+	if (wol->wolopts & (WAKE_MAGIC | WAKE_UCAST)) {
+		const u8 *mac = (const u8 *)ndev->dev_addr;
+		int i, reg;
+
+		reg = MII_LAN874X_PHY_MMD_WOL_RX_ADDRC;
+		for (i = 0; i < 6; i += 2, reg--) {
+			rc = phy_write_mmd(phydev, MDIO_MMD_PCS, reg,
+					   ((mac[i + 1] << 8) | mac[i]));
+			if (rc < 0)
+				return rc;
+		}
+	}
+
+	rc = phy_write_mmd(phydev, MDIO_MMD_PCS, MII_LAN874X_PHY_MMD_WOL_WUCSR,
+			   val_wucsr);
+	if (rc < 0)
+		return rc;
+
+	return 0;
+}
+
 static int smsc_get_sset_count(struct phy_device *phydev)
 {
 	return ARRAY_SIZE(smsc_hw_stats);
@@ -533,7 +773,7 @@ static struct phy_driver smsc_phy_driver[] = {
 
 	/* basic functions */
 	.read_status	= lan87xx_read_status,
-	.config_init	= smsc_phy_config_init,
+	.config_init	= lan874x_phy_config_init,
 	.soft_reset	= smsc_phy_reset,
 
 	/* IRQ related */
@@ -548,6 +788,10 @@ static struct phy_driver smsc_phy_driver[] = {
 	.get_tunable	= smsc_phy_get_tunable,
 	.set_tunable	= smsc_phy_set_tunable,
 
+	/* WoL */
+	.set_wol	= lan874x_set_wol,
+	.get_wol	= lan874x_get_wol,
+
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -566,7 +810,7 @@ static struct phy_driver smsc_phy_driver[] = {
 
 	/* basic functions */
 	.read_status	= lan87xx_read_status,
-	.config_init	= smsc_phy_config_init,
+	.config_init	= lan874x_phy_config_init,
 	.soft_reset	= smsc_phy_reset,
 
 	/* IRQ related */
@@ -581,6 +825,10 @@ static struct phy_driver smsc_phy_driver[] = {
 	.get_tunable	= smsc_phy_get_tunable,
 	.set_tunable	= smsc_phy_set_tunable,
 
+	/* WoL */
+	.set_wol	= lan874x_set_wol,
+	.get_wol	= lan874x_get_wol,
+
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 } };
diff --git a/include/linux/smscphy.h b/include/linux/smscphy.h
index e1c88627755a9..1a6a851d2cf80 100644
--- a/include/linux/smscphy.h
+++ b/include/linux/smscphy.h
@@ -38,4 +38,38 @@ int smsc_phy_set_tunable(struct phy_device *phydev,
 			 struct ethtool_tunable *tuna, const void *data);
 int smsc_phy_probe(struct phy_device *phydev);
 
+#define MII_LAN874X_PHY_MMD_WOL_WUCSR		0x8010
+#define MII_LAN874X_PHY_MMD_WOL_WUF_CFGA	0x8011
+#define MII_LAN874X_PHY_MMD_WOL_WUF_CFGB	0x8012
+#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK0	0x8021
+#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK1	0x8022
+#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK2	0x8023
+#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK3	0x8024
+#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK4	0x8025
+#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK5	0x8026
+#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK6	0x8027
+#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK7	0x8028
+#define MII_LAN874X_PHY_MMD_WOL_RX_ADDRA	0x8061
+#define MII_LAN874X_PHY_MMD_WOL_RX_ADDRB	0x8062
+#define MII_LAN874X_PHY_MMD_WOL_RX_ADDRC	0x8063
+#define MII_LAN874X_PHY_MMD_MCFGR		0x8064
+
+#define MII_LAN874X_PHY_PME1_SET		(2 << 13)
+#define MII_LAN874X_PHY_PME2_SET		(2 << 11)
+#define MII_LAN874X_PHY_PME_SELF_CLEAR		BIT(9)
+#define MII_LAN874X_PHY_WOL_PFDA_FR		BIT(7)
+#define MII_LAN874X_PHY_WOL_WUFR		BIT(6)
+#define MII_LAN874X_PHY_WOL_MPR			BIT(5)
+#define MII_LAN874X_PHY_WOL_BCAST_FR		BIT(4)
+#define MII_LAN874X_PHY_WOL_PFDAEN		BIT(3)
+#define MII_LAN874X_PHY_WOL_WUEN		BIT(2)
+#define MII_LAN874X_PHY_WOL_MPEN		BIT(1)
+#define MII_LAN874X_PHY_WOL_BCSTEN		BIT(0)
+
+#define MII_LAN874X_PHY_WOL_FILTER_EN		BIT(15)
+#define MII_LAN874X_PHY_WOL_FILTER_MCASTTEN	BIT(9)
+#define MII_LAN874X_PHY_WOL_FILTER_BCSTEN	BIT(8)
+
+#define MII_LAN874X_PHY_PME_SELF_CLEAR_DELAY	0x1000 /* 81 milliseconds */
+
 #endif /* __LINUX_SMSCPHY_H__ */
-- 
GitLab


From 73365fe44aa52fcd3e634e502937eb029abd0ee0 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 25 Jul 2023 17:46:37 +0200
Subject: [PATCH 0486/1806] bcmasp: BCMASP should depend on ARCH_BRCMSTB

The Broadcom ASP 2.0 Ethernet controller is only present on Broadcom STB
SoCs.  Hence add a dependency on ARCH_BRCMSTB, to prevent asking the
user about this driver when configuring a kernel without Broadcom
ARM-based set-top box chipset support.

Fixes: 490cb412007de593 ("net: bcmasp: Add support for ASP2.0 Ethernet controller")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Florian Fainelli <florian.fainelli@broadcom.com>
Acked-by: Justin Chen <justin.chen@broadcom.com>
Link: https://lore.kernel.org/r/1e8b998aa8dcc6e38323e295ee2430b48245cc79.1690299794.git.geert+renesas@glider.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index d4166141145d6..75ca3ddda1f5e 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -257,6 +257,7 @@ config BNXT_HWMON
 
 config BCMASP
 	tristate "Broadcom ASP 2.0 Ethernet support"
+	depends on ARCH_BRCMSTB || COMPILE_TEST
 	default ARCH_BRCMSTB
 	depends on OF
 	select MII
-- 
GitLab


From c1b0b6118b48100de0465b09201445df292647c1 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 25 Jul 2023 14:37:11 +0200
Subject: [PATCH 0487/1806] dt-bindings: net: qca,ar803x: add missing
 unevaluatedProperties for each regulator

Each regulator node, which references common regulator.yaml schema,
should disallow additional or unevaluated properties.  Otherwise
mistakes in properties will go unnoticed.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230725123711.149230-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/qca,ar803x.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/qca,ar803x.yaml b/Documentation/devicetree/bindings/net/qca,ar803x.yaml
index 161d289193165..3acd09f0da863 100644
--- a/Documentation/devicetree/bindings/net/qca,ar803x.yaml
+++ b/Documentation/devicetree/bindings/net/qca,ar803x.yaml
@@ -75,6 +75,7 @@ properties:
     description:
       Initial data for the VDDIO regulator. Set this to 1.5V or 1.8V.
     $ref: /schemas/regulator/regulator.yaml
+    unevaluatedProperties: false
 
   vddh-regulator:
     type: object
@@ -82,6 +83,7 @@ properties:
       Dummy subnode to model the external connection of the PHY VDDH
       regulator to VDDIO.
     $ref: /schemas/regulator/regulator.yaml
+    unevaluatedProperties: false
 
 unevaluatedProperties: false
 
-- 
GitLab


From 68bf5100fadffbba297f9142bf005767e571d726 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Tue, 25 Jul 2023 14:04:01 +0200
Subject: [PATCH 0488/1806] mlxsw: reg: Move 'mpsc' definition in
 'mlxsw_reg_infos'

The array 'mlxsw_reg_infos' is ordered by registers' IDs. The ID of MPSC
register is 0x9080, so it should be after MCDA (register ID 0x9063) and
not after MTUTC (register ID 0x9055). Note that the register's fields are
defined in the correct place in the file, only the definition in
'mlxsw_reg_infos' is wrong. This issue was found while adding new
register which supposed to be before mpsc.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/c5e270cd5769f301fe81235622215143506e1b48.1690281940.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index df63f39233724..a209f98dafa26 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -12974,10 +12974,10 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(mcion),
 	MLXSW_REG(mtpps),
 	MLXSW_REG(mtutc),
-	MLXSW_REG(mpsc),
 	MLXSW_REG(mcqi),
 	MLXSW_REG(mcc),
 	MLXSW_REG(mcda),
+	MLXSW_REG(mpsc),
 	MLXSW_REG(mgpc),
 	MLXSW_REG(mprs),
 	MLXSW_REG(mogcr),
-- 
GitLab


From 7447eda4065e377e09d6ef9ecc8bf3219548d0ed Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Tue, 25 Jul 2023 14:04:02 +0200
Subject: [PATCH 0489/1806] mlxsw: reg: Add Management Capabilities Mask
 Register

MCAM register reports the device supported management features. Querying
this register exposes if features are supported with the current
firmware version in the current ASIC. Then, the driver can separate
between different implementations dynamically.

MCAM register supports querying whether the MCIA register supports 128
bytes payloads or only 48 bytes. Add support for the register as
preparation for allowing larger MCIA transactions.

Note that the access to the bits in the field 'mng_feature_cap_mask' is
not same to other mask fields in other registers. In most of the cases
bit #0 is the first one in the last dword, in MCAM register, bits #0-#31
are in the first dword and so on. Declare the mask field using bits
arrays per dword to simplify the access.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/1427a3f57ba93db1c5dd4f982bfb31dd5c82356e.1690281940.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 74 +++++++++++++++++++++++
 1 file changed, 74 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index a209f98dafa26..d2391707dc043 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -10581,6 +10581,79 @@ static inline void mlxsw_reg_mcda_pack(char *payload, u32 update_handle,
 		mlxsw_reg_mcda_data_set(payload, i, *(u32 *) &data[i * 4]);
 }
 
+/* MCAM - Management Capabilities Mask Register
+ * --------------------------------------------
+ * Reports the device supported management features.
+ */
+#define MLXSW_REG_MCAM_ID 0x907F
+#define MLXSW_REG_MCAM_LEN 0x48
+
+MLXSW_REG_DEFINE(mcam, MLXSW_REG_MCAM_ID, MLXSW_REG_MCAM_LEN);
+
+enum mlxsw_reg_mcam_feature_group {
+	/* Enhanced features. */
+	MLXSW_REG_MCAM_FEATURE_GROUP_ENHANCED_FEATURES,
+};
+
+/* reg_mcam_feature_group
+ * Feature list mask index.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mcam, feature_group, 0x00, 16, 8);
+
+enum mlxsw_reg_mcam_mng_feature_cap_mask_bits {
+	/* If set, MCIA supports 128 bytes payloads. Otherwise, 48 bytes. */
+	MLXSW_REG_MCAM_MCIA_128B = 34,
+};
+
+#define MLXSW_REG_BYTES_PER_DWORD 0x4
+
+/* reg_mcam_mng_feature_cap_mask
+ * Supported port's enhanced features.
+ * Based on feature_group index.
+ * When bit is set, the feature is supported in the device.
+ * Access: RO
+ */
+#define MLXSW_REG_MCAM_MNG_FEATURE_CAP_MASK_DWORD(_dw_num, _offset)	 \
+	MLXSW_ITEM_BIT_ARRAY(reg, mcam, mng_feature_cap_mask_dw##_dw_num, \
+			     _offset, MLXSW_REG_BYTES_PER_DWORD, 1)
+
+/* The access to the bits in the field 'mng_feature_cap_mask' is not same to
+ * other mask fields in other registers. In most of the cases bit #0 is the
+ * first one in the last dword. In MCAM register, the first dword contains bits
+ * #0-#31 and so on, so the access to the bits is simpler using bit array per
+ * dword. Declare each dword of 'mng_feature_cap_mask' field separately.
+ */
+MLXSW_REG_MCAM_MNG_FEATURE_CAP_MASK_DWORD(0, 0x28);
+MLXSW_REG_MCAM_MNG_FEATURE_CAP_MASK_DWORD(1, 0x2C);
+MLXSW_REG_MCAM_MNG_FEATURE_CAP_MASK_DWORD(2, 0x30);
+MLXSW_REG_MCAM_MNG_FEATURE_CAP_MASK_DWORD(3, 0x34);
+
+static inline void
+mlxsw_reg_mcam_pack(char *payload, enum mlxsw_reg_mcam_feature_group feat_group)
+{
+	MLXSW_REG_ZERO(mcam, payload);
+	mlxsw_reg_mcam_feature_group_set(payload, feat_group);
+}
+
+static inline void
+mlxsw_reg_mcam_unpack(char *payload,
+		      enum mlxsw_reg_mcam_mng_feature_cap_mask_bits bit,
+		      bool *p_mng_feature_cap_val)
+{
+	int offset = bit % (MLXSW_REG_BYTES_PER_DWORD * BITS_PER_BYTE);
+	int dword = bit / (MLXSW_REG_BYTES_PER_DWORD * BITS_PER_BYTE);
+	u8 (*getters[])(const char *, u16) = {
+		mlxsw_reg_mcam_mng_feature_cap_mask_dw0_get,
+		mlxsw_reg_mcam_mng_feature_cap_mask_dw1_get,
+		mlxsw_reg_mcam_mng_feature_cap_mask_dw2_get,
+		mlxsw_reg_mcam_mng_feature_cap_mask_dw3_get,
+	};
+
+	if (!WARN_ON_ONCE(dword >= ARRAY_SIZE(getters)))
+		*p_mng_feature_cap_val = getters[dword](payload, offset);
+}
+
 /* MPSC - Monitoring Packet Sampling Configuration Register
  * --------------------------------------------------------
  * MPSC Register is used to configure the Packet Sampling mechanism.
@@ -12977,6 +13050,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(mcqi),
 	MLXSW_REG(mcc),
 	MLXSW_REG(mcda),
+	MLXSW_REG(mcam),
 	MLXSW_REG(mpsc),
 	MLXSW_REG(mgpc),
 	MLXSW_REG(mprs),
-- 
GitLab


From 3930dcc5e404079d8aabe577f61742b7e9590811 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 25 Jul 2023 14:04:03 +0200
Subject: [PATCH 0490/1806] mlxsw: reg: Remove unused function argument

The 'lock' argument is always set to the default value of '0'. Remove it
from the arguments list.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/fb5dd22830622ceeda1c2d6431c27fccd0687aca.1690281940.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_env.c | 10 +++++-----
 drivers/net/ethernet/mellanox/mlxsw/reg.h      | 12 +-----------
 2 files changed, 6 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index 0107cbc32fc76..679f7488ba10f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -111,7 +111,7 @@ mlxsw_env_validate_cable_ident(struct mlxsw_core *core, u8 slot_index, int id,
 	if (err)
 		return err;
 
-	mlxsw_reg_mcia_pack(mcia_pl, slot_index, id, 0,
+	mlxsw_reg_mcia_pack(mcia_pl, slot_index, id,
 			    MLXSW_REG_MCIA_PAGE0_LO_OFF, 0, 1,
 			    MLXSW_REG_MCIA_I2C_ADDR_LOW);
 	err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl);
@@ -188,7 +188,7 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, u8 slot_index,
 		}
 	}
 
-	mlxsw_reg_mcia_pack(mcia_pl, slot_index, module, 0, page, offset, size,
+	mlxsw_reg_mcia_pack(mcia_pl, slot_index, module, page, offset, size,
 			    i2c_addr);
 
 	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcia), mcia_pl);
@@ -266,12 +266,12 @@ mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, u8 slot_index,
 			page = MLXSW_REG_MCIA_TH_PAGE_CMIS_NUM;
 		else
 			page = MLXSW_REG_MCIA_TH_PAGE_NUM;
-		mlxsw_reg_mcia_pack(mcia_pl, slot_index, module, 0, page,
+		mlxsw_reg_mcia_pack(mcia_pl, slot_index, module, page,
 				    MLXSW_REG_MCIA_TH_PAGE_OFF + off,
 				    MLXSW_REG_MCIA_TH_ITEM_SIZE,
 				    MLXSW_REG_MCIA_I2C_ADDR_LOW);
 	} else {
-		mlxsw_reg_mcia_pack(mcia_pl, slot_index, module, 0,
+		mlxsw_reg_mcia_pack(mcia_pl, slot_index, module,
 				    MLXSW_REG_MCIA_PAGE0_LO,
 				    off, MLXSW_REG_MCIA_TH_ITEM_SIZE,
 				    MLXSW_REG_MCIA_I2C_ADDR_HIGH);
@@ -491,7 +491,7 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core,
 		size = min_t(u8, page->length - bytes_read,
 			     MLXSW_REG_MCIA_EEPROM_SIZE);
 
-		mlxsw_reg_mcia_pack(mcia_pl, slot_index, module, 0, page->page,
+		mlxsw_reg_mcia_pack(mcia_pl, slot_index, module, page->page,
 				    device_addr + bytes_read, size,
 				    page->i2c_address);
 		mlxsw_reg_mcia_bank_number_set(mcia_pl, page->bank);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index d2391707dc043..3b297797ced40 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -9644,14 +9644,6 @@ static inline void mlxsw_reg_mtbr_temp_unpack(char *payload, int rec_ind,
 
 MLXSW_REG_DEFINE(mcia, MLXSW_REG_MCIA_ID, MLXSW_REG_MCIA_LEN);
 
-/* reg_mcia_l
- * Lock bit. Setting this bit will lock the access to the specific
- * cable. Used for updating a full page in a cable EPROM. Any access
- * other then subsequence writes will fail while the port is locked.
- * Access: RW
- */
-MLXSW_ITEM32(reg, mcia, l, 0x00, 31, 1);
-
 /* reg_mcia_module
  * Module number.
  * Access: Index
@@ -9764,14 +9756,12 @@ MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_REG_MCIA_EEPROM_SIZE);
 				MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH + 1)
 
 static inline void mlxsw_reg_mcia_pack(char *payload, u8 slot_index, u8 module,
-				       u8 lock, u8 page_number,
-				       u16 device_addr, u8 size,
+				       u8 page_number, u16 device_addr, u8 size,
 				       u8 i2c_device_addr)
 {
 	MLXSW_REG_ZERO(mcia, payload);
 	mlxsw_reg_mcia_slot_set(payload, slot_index);
 	mlxsw_reg_mcia_module_set(payload, module);
-	mlxsw_reg_mcia_l_set(payload, lock);
 	mlxsw_reg_mcia_page_number_set(payload, page_number);
 	mlxsw_reg_mcia_device_address_set(payload, device_addr);
 	mlxsw_reg_mcia_size_set(payload, size);
-- 
GitLab


From c8dbf67883db98a1987eefd4872cf997c64ce7e7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 25 Jul 2023 14:04:04 +0200
Subject: [PATCH 0491/1806] mlxsw: reg: Increase Management Cable Info Access
 Register length

The layout of the register always supported 128 bytes payloads, but the
driver defined the register with a shorter length because it uses a
maximum payload size of 48 bytes. Increase the register's length in
preparation for using 128 bytes payloads.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/ba5c0f631e2cfd61bd21218d0cbfe03fbfe521f9.1690281940.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 3b297797ced40..7a0023ae95863 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -9640,7 +9640,7 @@ static inline void mlxsw_reg_mtbr_temp_unpack(char *payload, int rec_ind,
  */
 
 #define MLXSW_REG_MCIA_ID 0x9014
-#define MLXSW_REG_MCIA_LEN 0x40
+#define MLXSW_REG_MCIA_LEN 0x94
 
 MLXSW_REG_DEFINE(mcia, MLXSW_REG_MCIA_ID, MLXSW_REG_MCIA_LEN);
 
-- 
GitLab


From 1f4aea1f72da039d830862bc690dbd2d355dc992 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 25 Jul 2023 14:04:05 +0200
Subject: [PATCH 0492/1806] mlxsw: core_env: Read transceiver module EEPROM in
 128 bytes chunks

Old firmware versions could only read up to 48 bytes from a transceiver
module's EEPROM in one go. Newer versions can read up to 128 bytes,
resulting in fewer transactions.

Query support for the new capability during driver initialization and if
supported, read up to 128 bytes in one go.

This is going to be especially useful for upcoming transceiver module
firmware flashing support.

Before:

 # perf stat -e devlink:devlink_hwmsg -- ethtool -m swp11 page 0x1 offset 128 length 128 i2c 0x50
 [...]
  Performance counter stats for 'ethtool -m swp11 page 0x1 offset 128 length 128 i2c 0x50':

                  3      devlink:devlink_hwmsg

After:

 # perf stat -e devlink:devlink_hwmsg -- ethtool -m swp11 page 0x1 offset 128 length 128 i2c 0x50
 [...]
  Performance counter stats for 'ethtool -m swp11 page 0x1 offset 128 length 128 i2c 0x50':

                  1      devlink:devlink_hwmsg

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/99d1618e8cd5acefb2f795dfde1a5b41caa07dcb.1690281940.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlxsw/core_env.c    | 35 +++++++++++++++----
 drivers/net/ethernet/mellanox/mlxsw/reg.h     |  3 +-
 2 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index 679f7488ba10f..d637c0348fa15 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -32,6 +32,7 @@ struct mlxsw_env {
 	const struct mlxsw_bus_info *bus_info;
 	u8 max_module_count; /* Maximum number of modules per-slot. */
 	u8 num_of_slots; /* Including the main board. */
+	u8 max_eeprom_len; /* Maximum module EEPROM transaction length. */
 	struct mutex line_cards_lock; /* Protects line cards. */
 	struct mlxsw_env_line_card *line_cards[];
 };
@@ -146,6 +147,7 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, u8 slot_index,
 			      int module, u16 offset, u16 size, void *data,
 			      bool qsfp, unsigned int *p_read_size)
 {
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
 	char mcia_pl[MLXSW_REG_MCIA_LEN];
 	char *eeprom_tmp;
 	u16 i2c_addr;
@@ -153,11 +155,7 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, u8 slot_index,
 	int status;
 	int err;
 
-	/* MCIA register accepts buffer size <= 48. Page of size 128 should be
-	 * read by chunks of size 48, 48, 32. Align the size of the last chunk
-	 * to avoid reading after the end of the page.
-	 */
-	size = min_t(u16, size, MLXSW_REG_MCIA_EEPROM_SIZE);
+	size = min_t(u16, size, mlxsw_env->max_eeprom_len);
 
 	if (offset < MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH &&
 	    offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH)
@@ -489,7 +487,7 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core,
 		u8 size;
 
 		size = min_t(u8, page->length - bytes_read,
-			     MLXSW_REG_MCIA_EEPROM_SIZE);
+			     mlxsw_env->max_eeprom_len);
 
 		mlxsw_reg_mcia_pack(mcia_pl, slot_index, module, page->page,
 				    device_addr + bytes_read, size,
@@ -1359,6 +1357,26 @@ static struct mlxsw_linecards_event_ops mlxsw_env_event_ops = {
 	.got_inactive = mlxsw_env_got_inactive,
 };
 
+static int mlxsw_env_max_module_eeprom_len_query(struct mlxsw_env *mlxsw_env)
+{
+	char mcam_pl[MLXSW_REG_MCAM_LEN];
+	bool mcia_128b_supported;
+	int err;
+
+	mlxsw_reg_mcam_pack(mcam_pl,
+			    MLXSW_REG_MCAM_FEATURE_GROUP_ENHANCED_FEATURES);
+	err = mlxsw_reg_query(mlxsw_env->core, MLXSW_REG(mcam), mcam_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_MCIA_128B,
+			      &mcia_128b_supported);
+
+	mlxsw_env->max_eeprom_len = mcia_128b_supported ? 128 : 48;
+
+	return 0;
+}
+
 int mlxsw_env_init(struct mlxsw_core *mlxsw_core,
 		   const struct mlxsw_bus_info *bus_info,
 		   struct mlxsw_env **p_env)
@@ -1427,10 +1445,15 @@ int mlxsw_env_init(struct mlxsw_core *mlxsw_core,
 	if (err)
 		goto err_type_set;
 
+	err = mlxsw_env_max_module_eeprom_len_query(env);
+	if (err)
+		goto err_eeprom_len_query;
+
 	env->line_cards[0]->active = true;
 
 	return 0;
 
+err_eeprom_len_query:
 err_type_set:
 	mlxsw_env_module_event_disable(env, 0);
 err_mlxsw_env_module_event_enable:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 7a0023ae95863..4b90ae44b4765 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -9708,7 +9708,6 @@ MLXSW_ITEM32(reg, mcia, size, 0x08, 0, 16);
 
 #define MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH	256
 #define MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH	128
-#define MLXSW_REG_MCIA_EEPROM_SIZE		48
 #define MLXSW_REG_MCIA_I2C_ADDR_LOW		0x50
 #define MLXSW_REG_MCIA_I2C_ADDR_HIGH		0x51
 #define MLXSW_REG_MCIA_PAGE0_LO_OFF		0xa0
@@ -9745,7 +9744,7 @@ enum mlxsw_reg_mcia_eeprom_module_info {
  * Bytes to read/write.
  * Access: RW
  */
-MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_REG_MCIA_EEPROM_SIZE);
+MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, 128);
 
 /* This is used to access the optional upper pages (1-3) in the QSFP+
  * memory map. Page 1 is available on offset 256 through 383, page 2 -
-- 
GitLab


From f44a90104ee5aceaf39b5a10787ab34c46c987ba Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 24 Jul 2023 15:18:58 -0600
Subject: [PATCH 0493/1806] net: dsa: Explicitly include correct DT includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20230724211859.805481-1-robh@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/b53/b53_mdio.c             | 1 +
 drivers/net/dsa/b53/b53_mmap.c             | 1 +
 drivers/net/dsa/hirschmann/hellcreek.c     | 1 -
 drivers/net/dsa/hirschmann/hellcreek_ptp.c | 1 +
 drivers/net/dsa/lan9303-core.c             | 1 +
 drivers/net/dsa/microchip/ksz8863_smi.c    | 3 +++
 drivers/net/dsa/microchip/ksz_common.c     | 2 +-
 drivers/net/dsa/mt7530-mmio.c              | 3 ++-
 drivers/net/dsa/mv88e6xxx/chip.c           | 2 +-
 drivers/net/dsa/ocelot/felix_vsc9959.c     | 1 +
 drivers/net/dsa/ocelot/seville_vsc9953.c   | 3 ++-
 drivers/net/dsa/qca/qca8k-leds.c           | 1 +
 drivers/net/dsa/realtek/realtek-mdio.c     | 2 +-
 drivers/net/dsa/realtek/realtek-smi.c      | 1 -
 drivers/net/dsa/sja1105/sja1105_main.c     | 1 -
 drivers/net/dsa/vitesse-vsc73xx-core.c     | 1 -
 drivers/net/dsa/xrs700x/xrs700x.c          | 2 +-
 17 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c
index 8b422b298cd51..4d55d8d183768 100644
--- a/drivers/net/dsa/b53/b53_mdio.c
+++ b/drivers/net/dsa/b53/b53_mdio.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/phy.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/delay.h>
 #include <linux/brcmphy.h>
 #include <linux/rtnetlink.h>
diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c
index 5db1ed26f03a2..5e39641ea8872 100644
--- a/drivers/net/dsa/b53/b53_mmap.c
+++ b/drivers/net/dsa/b53/b53_mmap.c
@@ -19,6 +19,7 @@
 #include <linux/bits.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/b53.h>
diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c
index af50001ccdd4e..720f4e4ed0b03 100644
--- a/drivers/net/dsa/hirschmann/hellcreek.c
+++ b/drivers/net/dsa/hirschmann/hellcreek.c
@@ -11,7 +11,6 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_mdio.h>
 #include <linux/platform_device.h>
 #include <linux/bitops.h>
diff --git a/drivers/net/dsa/hirschmann/hellcreek_ptp.c b/drivers/net/dsa/hirschmann/hellcreek_ptp.c
index 3e44ccb7db84c..5249a1c2a80b8 100644
--- a/drivers/net/dsa/hirschmann/hellcreek_ptp.c
+++ b/drivers/net/dsa/hirschmann/hellcreek_ptp.c
@@ -9,6 +9,7 @@
  *	    Kurt Kanzenbach <kurt@linutronix.de>
  */
 
+#include <linux/of.h>
 #include <linux/ptp_clock_kernel.h>
 #include "hellcreek.h"
 #include "hellcreek_ptp.h"
diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c
index b0da1e4de63c3..ee67adeb2cdbf 100644
--- a/drivers/net/dsa/lan9303-core.c
+++ b/drivers/net/dsa/lan9303-core.c
@@ -8,6 +8,7 @@
 #include <linux/regmap.h>
 #include <linux/mutex.h>
 #include <linux/mii.h>
+#include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/if_bridge.h>
 #include <linux/if_vlan.h>
diff --git a/drivers/net/dsa/microchip/ksz8863_smi.c b/drivers/net/dsa/microchip/ksz8863_smi.c
index fd6e2e69a42ae..5711a59e2ac94 100644
--- a/drivers/net/dsa/microchip/ksz8863_smi.c
+++ b/drivers/net/dsa/microchip/ksz8863_smi.c
@@ -5,6 +5,9 @@
  * Copyright (C) 2019 Pengutronix, Michael Grzeschik <kernel@pengutronix.de>
  */
 
+#include <linux/mod_devicetable.h>
+#include <linux/property.h>
+
 #include "ksz8.h"
 #include "ksz_common.h"
 
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 1de2251a42dc3..2414c1f8bc2de 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -18,8 +18,8 @@
 #include <linux/if_vlan.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
+#include <linux/of.h>
 #include <linux/of_mdio.h>
-#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/micrel_phy.h>
 #include <net/dsa.h>
diff --git a/drivers/net/dsa/mt7530-mmio.c b/drivers/net/dsa/mt7530-mmio.c
index 1a3d4b692f349..0a6a2fe34e64f 100644
--- a/drivers/net/dsa/mt7530-mmio.c
+++ b/drivers/net/dsa/mt7530-mmio.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 11a2e3d384841..bce9c9e437520 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -23,7 +23,7 @@
 #include <linux/list.h>
 #include <linux/mdio.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
 #include <linux/platform_data/mv88e6xxx.h>
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 1c113957fcf45..dce3548dcd057 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -16,6 +16,7 @@
 #include <net/pkt_sched.h>
 #include <linux/iopoll.h>
 #include <linux/mdio.h>
+#include <linux/of.h>
 #include <linux/pci.h>
 #include <linux/time.h>
 #include "felix.h"
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index 15003b2af264d..8f912bda120b3 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -2,13 +2,14 @@
 /* Distributed Switch Architecture VSC9953 driver
  * Copyright (C) 2020, Maxim Kochetkov <fido_max@inbox.ru>
  */
+#include <linux/platform_device.h>
 #include <linux/types.h>
 #include <soc/mscc/ocelot_vcap.h>
 #include <soc/mscc/ocelot_sys.h>
 #include <soc/mscc/ocelot.h>
 #include <linux/mdio/mdio-mscc-miim.h>
+#include <linux/mod_devicetable.h>
 #include <linux/of_mdio.h>
-#include <linux/of_platform.h>
 #include <linux/pcs-lynx.h>
 #include <linux/dsa/ocelot.h>
 #include <linux/iopoll.h>
diff --git a/drivers/net/dsa/qca/qca8k-leds.c b/drivers/net/dsa/qca/qca8k-leds.c
index 1261e0bb21efe..e8c16e76e34bb 100644
--- a/drivers/net/dsa/qca/qca8k-leds.c
+++ b/drivers/net/dsa/qca/qca8k-leds.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <net/dsa.h>
 
diff --git a/drivers/net/dsa/realtek/realtek-mdio.c b/drivers/net/dsa/realtek/realtek-mdio.c
index 5a8fe707ca25e..4310e7793e586 100644
--- a/drivers/net/dsa/realtek/realtek-mdio.c
+++ b/drivers/net/dsa/realtek/realtek-mdio.c
@@ -20,7 +20,7 @@
  */
 
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/overflow.h>
 #include <linux/regmap.h>
 
diff --git a/drivers/net/dsa/realtek/realtek-smi.c b/drivers/net/dsa/realtek/realtek-smi.c
index 1b447d96b9c46..c2bd8bb6c9c22 100644
--- a/drivers/net/dsa/realtek/realtek-smi.c
+++ b/drivers/net/dsa/realtek/realtek-smi.c
@@ -31,7 +31,6 @@
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_mdio.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 52dd52d6c43d0..331bb1c6676ac 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -15,7 +15,6 @@
 #include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
-#include <linux/of_device.h>
 #include <linux/pcs/pcs-xpcs.h>
 #include <linux/netdev_features.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index ef1a4a7c47b23..4f09e7438f3b9 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -18,7 +18,6 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_mdio.h>
 #include <linux/bitops.h>
 #include <linux/if_bridge.h>
diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c
index fa622639d6401..753fef757f116 100644
--- a/drivers/net/dsa/xrs700x/xrs700x.c
+++ b/drivers/net/dsa/xrs700x/xrs700x.c
@@ -7,7 +7,7 @@
 #include <net/dsa.h>
 #include <linux/etherdevice.h>
 #include <linux/if_bridge.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/netdev_features.h>
 #include <linux/if_hsr.h>
 #include "xrs700x.h"
-- 
GitLab


From ac3cb6de32b62f08d76109e98e174ce0ebf3c022 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 24 Jul 2023 15:19:05 -0600
Subject: [PATCH 0494/1806] net: phy/pcs: Explicitly include correct DT
 includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230724211905.805665-1-robh@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-rzn1-miic.c   | 1 +
 drivers/net/phy/marvell-88x2222.c | 1 -
 drivers/net/phy/mediatek-ge-soc.c | 2 --
 3 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c
index 323bec5e57f83..e5d642c67a2ca 100644
--- a/drivers/net/pcs/pcs-rzn1-miic.c
+++ b/drivers/net/pcs/pcs-rzn1-miic.c
@@ -12,6 +12,7 @@
 #include <linux/of_platform.h>
 #include <linux/pcs-rzn1-miic.h>
 #include <linux/phylink.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <dt-bindings/net/pcs-rzn1-miic.h>
 
diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c
index f83cae64585d5..e3aa30dad2e63 100644
--- a/drivers/net/phy/marvell-88x2222.c
+++ b/drivers/net/phy/marvell-88x2222.c
@@ -14,7 +14,6 @@
 #include <linux/mdio.h>
 #include <linux/marvell_phy.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_gpio.h>
 #include <linux/sfp.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek-ge-soc.c
index 95369171a7ba6..da512fab0eb0b 100644
--- a/drivers/net/phy/mediatek-ge-soc.c
+++ b/drivers/net/phy/mediatek-ge-soc.c
@@ -2,8 +2,6 @@
 #include <linux/bitfield.h>
 #include <linux/module.h>
 #include <linux/nvmem-consumer.h>
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/phy.h>
 
-- 
GitLab


From 1cbf487d7d3af19fc50dd7e350c20ba0731d745f Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 25 Jul 2023 01:51:16 +0100
Subject: [PATCH 0495/1806] dt-bindings: net: mediatek,net: add missing
 mediatek,mt7621-eth

Document the Ethernet controller found in the MediaTek MT7621 MIPS SoC
family which is supported by the mtk_eth_soc driver.

Fixes: 889bcbdeee57 ("net: ethernet: mediatek: support MT7621 SoC ethernet hardware")
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/ec4371c4b5a331c5217b5f13a0c9e6c444838e14.1690246066.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/mediatek,net.yaml | 27 ++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml
index acb2b2ac4fe1e..38aa3d97ee234 100644
--- a/Documentation/devicetree/bindings/net/mediatek,net.yaml
+++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml
@@ -19,6 +19,7 @@ properties:
     enum:
       - mediatek,mt2701-eth
       - mediatek,mt7623-eth
+      - mediatek,mt7621-eth
       - mediatek,mt7622-eth
       - mediatek,mt7629-eth
       - mediatek,mt7981-eth
@@ -32,7 +33,7 @@ properties:
   clock-names: true
 
   interrupts:
-    minItems: 3
+    minItems: 1
     maxItems: 4
 
   power-domains:
@@ -131,6 +132,30 @@ allOf:
 
         mediatek,wed-pcie: false
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - mediatek,mt7621-eth
+    then:
+      properties:
+        interrupts:
+          maxItems: 1
+
+        clocks:
+          minItems: 2
+          maxItems: 2
+
+        clock-names:
+          items:
+            - const: ethif
+            - const: fe
+
+        mediatek,wed: false
+
+        mediatek,wed-pcie: false
+
   - if:
       properties:
         compatible:
-- 
GitLab


From c94a9aabec36d16d5183f672d3c05ddd0042db88 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 25 Jul 2023 01:51:33 +0100
Subject: [PATCH 0496/1806] dt-bindings: net: mediatek,net: add mt7988-eth
 binding

Introduce DT bindings for the MT7988 SoC to mediatek,net.yaml.
The MT7988 SoC got 3 Ethernet MACs operating at a maximum of
10 Gigabit/sec supported by 2 packet processor engines for
offloading tasks.
The first MAC is hard-wired to a built-in switch which exposes
four 1000Base-T PHYs as user ports.
It also comes with built-in 2500Base-T PHY which can be used
with the 2nd GMAC.
The 2nd and 3rd GMAC can be connected to external PHYs or provide
SFP(+) cages attached via SGMII, 1000Base-X, 2500Base-X, USXGMII,
5GBase-KR or 10GBase-KR.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/3c83d2c0d629dac064ec4396132538c52e77a57f.1690246066.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/mediatek,net.yaml | 82 +++++++++++++++++--
 1 file changed, 76 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml
index 38aa3d97ee234..8d3554818c377 100644
--- a/Documentation/devicetree/bindings/net/mediatek,net.yaml
+++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml
@@ -24,6 +24,7 @@ properties:
       - mediatek,mt7629-eth
       - mediatek,mt7981-eth
       - mediatek,mt7986-eth
+      - mediatek,mt7988-eth
       - ralink,rt5350-eth
 
   reg:
@@ -61,6 +62,12 @@ properties:
       Phandle to the mediatek hifsys controller used to provide various clocks
       and reset to the system.
 
+  mediatek,infracfg:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      Phandle to the syscon node that handles the path from GMAC to
+      PHY variants.
+
   mediatek,sgmiisys:
     $ref: /schemas/types.yaml#/definitions/phandle-array
     minItems: 1
@@ -122,6 +129,8 @@ allOf:
             - const: gp1
             - const: gp2
 
+        mediatek,infracfg: false
+
         mediatek,pctl:
           $ref: /schemas/types.yaml#/definitions/phandle
           description:
@@ -152,6 +161,8 @@ allOf:
             - const: ethif
             - const: fe
 
+        mediatek,infracfg: false
+
         mediatek,wed: false
 
         mediatek,wed-pcie: false
@@ -184,6 +195,8 @@ allOf:
             - const: sgmii_ck
             - const: eth2pll
 
+        mediatek,infracfg: false
+
         mediatek,sgmiisys:
           minItems: 1
           maxItems: 1
@@ -229,12 +242,6 @@ allOf:
             - const: sgmii_ck
             - const: eth2pll
 
-        mediatek,infracfg:
-          $ref: /schemas/types.yaml#/definitions/phandle
-          description:
-            Phandle to the syscon node that handles the path from GMAC to
-            PHY variants.
-
         mediatek,sgmiisys:
           minItems: 2
           maxItems: 2
@@ -275,6 +282,8 @@ allOf:
             - const: netsys0
             - const: netsys1
 
+        mediatek,infracfg: false
+
         mediatek,sgmiisys:
           minItems: 2
           maxItems: 2
@@ -311,6 +320,67 @@ allOf:
             - const: netsys0
             - const: netsys1
 
+        mediatek,infracfg: false
+
+        mediatek,sgmiisys:
+          minItems: 2
+          maxItems: 2
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: mediatek,mt7988-eth
+    then:
+      properties:
+        interrupts:
+          minItems: 4
+
+        clocks:
+          minItems: 34
+          maxItems: 34
+
+        clock-names:
+          items:
+            - const: crypto
+            - const: fe
+            - const: gp2
+            - const: gp1
+            - const: gp3
+            - const: ethwarp_wocpu2
+            - const: ethwarp_wocpu1
+            - const: ethwarp_wocpu0
+            - const: esw
+            - const: netsys0
+            - const: netsys1
+            - const: sgmii_tx250m
+            - const: sgmii_rx250m
+            - const: sgmii2_tx250m
+            - const: sgmii2_rx250m
+            - const: top_usxgmii0_sel
+            - const: top_usxgmii1_sel
+            - const: top_sgm0_sel
+            - const: top_sgm1_sel
+            - const: top_xfi_phy0_xtal_sel
+            - const: top_xfi_phy1_xtal_sel
+            - const: top_eth_gmii_sel
+            - const: top_eth_refck_50m_sel
+            - const: top_eth_sys_200m_sel
+            - const: top_eth_sys_sel
+            - const: top_eth_xgmii_sel
+            - const: top_eth_mii_sel
+            - const: top_netsys_sel
+            - const: top_netsys_500m_sel
+            - const: top_netsys_pao_2x_sel
+            - const: top_netsys_sync_250m_sel
+            - const: top_netsys_ppefb_250m_sel
+            - const: top_netsys_warp_sel
+            - const: wocpu1
+            - const: wocpu0
+            - const: xgp1
+            - const: xgp2
+            - const: xgp3
+
         mediatek,sgmiisys:
           minItems: 2
           maxItems: 2
-- 
GitLab


From a008e2a84e6b2b598af6fadf6c8f756d4fe639ca Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 25 Jul 2023 01:52:02 +0100
Subject: [PATCH 0497/1806] net: ethernet: mtk_eth_soc: add version in
 mtk_soc_data

Introduce version field in mtk_soc_data data structure in order to
make mtk_eth driver easier to maintain for chipset configuration
codebase. Get rid of MTK_NETSYS_V2 bit in chip capabilities.
This is a preliminary patch to introduce support for MT7988 SoC.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/e52fae302ca135436e5cdd26d38d87be2da63055.1690246066.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c   | 55 +++++++++++--------
 drivers/net/ethernet/mediatek/mtk_eth_soc.h   | 36 +++++++-----
 drivers/net/ethernet/mediatek/mtk_ppe.c       | 18 +++---
 .../net/ethernet/mediatek/mtk_ppe_offload.c   |  2 +-
 drivers/net/ethernet/mediatek/mtk_wed.c       |  4 +-
 5 files changed, 66 insertions(+), 49 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 7490d48000c26..206cffb0e5acf 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -593,7 +593,7 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 	      FIELD_PREP(MTK_QTX_SCH_MIN_RATE_MAN, 1) |
 	      FIELD_PREP(MTK_QTX_SCH_MIN_RATE_EXP, 4) |
 	      MTK_QTX_SCH_LEAKY_BUCKET_SIZE;
-	if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v1(eth))
 		val |= MTK_QTX_SCH_LEAKY_BUCKET_EN;
 
 	if (IS_ENABLED(CONFIG_SOC_MT7621)) {
@@ -970,7 +970,7 @@ static bool mtk_rx_get_desc(struct mtk_eth *eth, struct mtk_rx_dma_v2 *rxd,
 	rxd->rxd1 = READ_ONCE(dma_rxd->rxd1);
 	rxd->rxd3 = READ_ONCE(dma_rxd->rxd3);
 	rxd->rxd4 = READ_ONCE(dma_rxd->rxd4);
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(eth)) {
 		rxd->rxd5 = READ_ONCE(dma_rxd->rxd5);
 		rxd->rxd6 = READ_ONCE(dma_rxd->rxd6);
 	}
@@ -1028,7 +1028,7 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 
 		txd->txd3 = TX_DMA_PLEN0(MTK_QDMA_PAGE_SIZE);
 		txd->txd4 = 0;
-		if (MTK_HAS_CAPS(soc->caps, MTK_NETSYS_V2)) {
+		if (mtk_is_netsys_v2_or_greater(eth)) {
 			txd->txd5 = 0;
 			txd->txd6 = 0;
 			txd->txd7 = 0;
@@ -1219,7 +1219,7 @@ static void mtk_tx_set_dma_desc(struct net_device *dev, void *txd,
 	struct mtk_mac *mac = netdev_priv(dev);
 	struct mtk_eth *eth = mac->hw;
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		mtk_tx_set_dma_desc_v2(dev, txd, info);
 	else
 		mtk_tx_set_dma_desc_v1(dev, txd, info);
@@ -1526,7 +1526,7 @@ static void mtk_update_rx_cpu_idx(struct mtk_eth *eth)
 
 static bool mtk_page_pool_enabled(struct mtk_eth *eth)
 {
-	return MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2);
+	return eth->soc->version == 2;
 }
 
 static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth,
@@ -1868,7 +1868,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 			break;
 
 		/* find out which mac the packet come from. values start at 1 */
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+		if (mtk_is_netsys_v2_or_greater(eth))
 			mac = RX_DMA_GET_SPORT_V2(trxd.rxd5) - 1;
 		else if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628) &&
 			 !(trxd.rxd4 & RX_DMA_SPECIAL_TAG))
@@ -1964,7 +1964,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		skb->dev = netdev;
 		bytes += skb->len;
 
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+		if (mtk_is_netsys_v2_or_greater(eth)) {
 			reason = FIELD_GET(MTK_RXD5_PPE_CPU_REASON, trxd.rxd5);
 			hash = trxd.rxd5 & MTK_RXD5_FOE_ENTRY;
 			if (hash != MTK_RXD5_FOE_ENTRY)
@@ -1989,8 +1989,8 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		/* When using VLAN untagging in combination with DSA, the
 		 * hardware treats the MTK special tag as a VLAN and untags it.
 		 */
-		if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2) &&
-		    (trxd.rxd2 & RX_DMA_VTAG) && netdev_uses_dsa(netdev)) {
+		if (mtk_is_netsys_v1(eth) && (trxd.rxd2 & RX_DMA_VTAG) &&
+		    netdev_uses_dsa(netdev)) {
 			unsigned int port = RX_DMA_VPID(trxd.rxd3) & GENMASK(2, 0);
 
 			if (port < ARRAY_SIZE(eth->dsa_meta) &&
@@ -2300,7 +2300,7 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 		txd->txd2 = next_ptr;
 		txd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU;
 		txd->txd4 = 0;
-		if (MTK_HAS_CAPS(soc->caps, MTK_NETSYS_V2)) {
+		if (mtk_is_netsys_v2_or_greater(eth)) {
 			txd->txd5 = 0;
 			txd->txd6 = 0;
 			txd->txd7 = 0;
@@ -2353,14 +2353,14 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 			      FIELD_PREP(MTK_QTX_SCH_MIN_RATE_MAN, 1) |
 			      FIELD_PREP(MTK_QTX_SCH_MIN_RATE_EXP, 4) |
 			      MTK_QTX_SCH_LEAKY_BUCKET_SIZE;
-			if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+			if (mtk_is_netsys_v1(eth))
 				val |= MTK_QTX_SCH_LEAKY_BUCKET_EN;
 			mtk_w32(eth, val, soc->reg_map->qdma.qtx_sch + ofs);
 			ofs += MTK_QTX_OFFSET;
 		}
 		val = MTK_QDMA_TX_SCH_MAX_WFQ | (MTK_QDMA_TX_SCH_MAX_WFQ << 16);
 		mtk_w32(eth, val, soc->reg_map->qdma.tx_sch_rate);
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+		if (mtk_is_netsys_v2_or_greater(eth))
 			mtk_w32(eth, val, soc->reg_map->qdma.tx_sch_rate + 4);
 	} else {
 		mtk_w32(eth, ring->phys_pdma, MT7628_TX_BASE_PTR0);
@@ -2489,7 +2489,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 
 		rxd->rxd3 = 0;
 		rxd->rxd4 = 0;
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+		if (mtk_is_netsys_v2_or_greater(eth)) {
 			rxd->rxd5 = 0;
 			rxd->rxd6 = 0;
 			rxd->rxd7 = 0;
@@ -3037,7 +3037,7 @@ static int mtk_start_dma(struct mtk_eth *eth)
 		       MTK_TX_BT_32DWORDS | MTK_NDP_CO_PRO |
 		       MTK_RX_2B_OFFSET | MTK_TX_WB_DDONE;
 
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+		if (mtk_is_netsys_v2_or_greater(eth))
 			val |= MTK_MUTLI_CNT | MTK_RESV_BUF |
 			       MTK_WCOMP_EN | MTK_DMAD_WR_WDONE |
 			       MTK_CHK_DDONE_EN | MTK_LEAKY_BUCKET_EN;
@@ -3183,7 +3183,7 @@ static int mtk_open(struct net_device *dev)
 	phylink_start(mac->phylink);
 	netif_tx_start_all_queues(dev);
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		return 0;
 
 	if (mtk_uses_dsa(dev) && !eth->prog) {
@@ -3449,7 +3449,7 @@ static void mtk_hw_reset(struct mtk_eth *eth)
 {
 	u32 val;
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(eth)) {
 		regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN, 0);
 		val = RSTCTRL_PPE0_V2;
 	} else {
@@ -3461,7 +3461,7 @@ static void mtk_hw_reset(struct mtk_eth *eth)
 
 	ethsys_reset(eth, RSTCTRL_ETH | RSTCTRL_FE | val);
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN,
 			     0x3ffffff);
 }
@@ -3487,7 +3487,7 @@ static void mtk_hw_warm_reset(struct mtk_eth *eth)
 		return;
 	}
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		rst_mask = RSTCTRL_ETH | RSTCTRL_PPE0_V2;
 	else
 		rst_mask = RSTCTRL_ETH | RSTCTRL_PPE0;
@@ -3657,7 +3657,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	else
 		mtk_hw_reset(eth);
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(eth)) {
 		/* Set FE to PDMAv2 if necessary */
 		val = mtk_r32(eth, MTK_FE_GLO_MISC);
 		mtk_w32(eth,  val | BIT(4), MTK_FE_GLO_MISC);
@@ -3694,7 +3694,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	 */
 	val = mtk_r32(eth, MTK_CDMQ_IG_CTRL);
 	mtk_w32(eth, val | MTK_CDMQ_STAG_EN, MTK_CDMQ_IG_CTRL);
-	if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v1(eth)) {
 		val = mtk_r32(eth, MTK_CDMP_IG_CTRL);
 		mtk_w32(eth, val | MTK_CDMP_STAG_EN, MTK_CDMP_IG_CTRL);
 
@@ -3716,7 +3716,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask, reg_map->qdma.int_grp + 4);
 	mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(eth)) {
 		/* PSE should not drop port8 and port9 packets from WDMA Tx */
 		mtk_w32(eth, 0x00000300, PSE_DROP_CFG);
 
@@ -4521,7 +4521,7 @@ static int mtk_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(eth)) {
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 		if (!res) {
 			err = -EINVAL;
@@ -4629,9 +4629,8 @@ static int mtk_probe(struct platform_device *pdev)
 	}
 
 	if (eth->soc->offload_version) {
-		u32 num_ppe;
+		u32 num_ppe = mtk_is_netsys_v2_or_greater(eth) ? 2 : 1;
 
-		num_ppe = MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2) ? 2 : 1;
 		num_ppe = min_t(u32, ARRAY_SIZE(eth->ppe), num_ppe);
 		for (i = 0; i < num_ppe; i++) {
 			u32 ppe_addr = eth->soc->reg_map->ppe_base + i * 0x400;
@@ -4723,6 +4722,7 @@ static const struct mtk_soc_data mt2701_data = {
 	.hw_features = MTK_HW_FEATURES,
 	.required_clks = MT7623_CLKS_BITMAP,
 	.required_pctl = true,
+	.version = 1,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma),
 		.rxd_size = sizeof(struct mtk_rx_dma),
@@ -4739,6 +4739,7 @@ static const struct mtk_soc_data mt7621_data = {
 	.hw_features = MTK_HW_FEATURES,
 	.required_clks = MT7621_CLKS_BITMAP,
 	.required_pctl = false,
+	.version = 1,
 	.offload_version = 1,
 	.hash_offset = 2,
 	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
@@ -4759,6 +4760,7 @@ static const struct mtk_soc_data mt7622_data = {
 	.hw_features = MTK_HW_FEATURES,
 	.required_clks = MT7622_CLKS_BITMAP,
 	.required_pctl = false,
+	.version = 1,
 	.offload_version = 2,
 	.hash_offset = 2,
 	.has_accounting = true,
@@ -4779,6 +4781,7 @@ static const struct mtk_soc_data mt7623_data = {
 	.hw_features = MTK_HW_FEATURES,
 	.required_clks = MT7623_CLKS_BITMAP,
 	.required_pctl = true,
+	.version = 1,
 	.offload_version = 1,
 	.hash_offset = 2,
 	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
@@ -4801,6 +4804,7 @@ static const struct mtk_soc_data mt7629_data = {
 	.required_clks = MT7629_CLKS_BITMAP,
 	.required_pctl = false,
 	.has_accounting = true,
+	.version = 1,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma),
 		.rxd_size = sizeof(struct mtk_rx_dma),
@@ -4818,6 +4822,7 @@ static const struct mtk_soc_data mt7981_data = {
 	.hw_features = MTK_HW_FEATURES,
 	.required_clks = MT7981_CLKS_BITMAP,
 	.required_pctl = false,
+	.version = 2,
 	.offload_version = 2,
 	.hash_offset = 4,
 	.has_accounting = true,
@@ -4839,6 +4844,7 @@ static const struct mtk_soc_data mt7986_data = {
 	.hw_features = MTK_HW_FEATURES,
 	.required_clks = MT7986_CLKS_BITMAP,
 	.required_pctl = false,
+	.version = 2,
 	.offload_version = 2,
 	.hash_offset = 4,
 	.has_accounting = true,
@@ -4859,6 +4865,7 @@ static const struct mtk_soc_data rt5350_data = {
 	.hw_features = MTK_HW_FEATURES_MT7628,
 	.required_clks = MT7628_CLKS_BITMAP,
 	.required_pctl = false,
+	.version = 1,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma),
 		.rxd_size = sizeof(struct mtk_rx_dma),
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 28adda0c90c0d..8ca368973e922 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -820,7 +820,6 @@ enum mkt_eth_capabilities {
 	MTK_SHARED_INT_BIT,
 	MTK_TRGMII_MT7621_CLK_BIT,
 	MTK_QDMA_BIT,
-	MTK_NETSYS_V2_BIT,
 	MTK_SOC_MT7628_BIT,
 	MTK_RSTCTRL_PPE1_BIT,
 	MTK_U3_COPHY_V2_BIT,
@@ -855,7 +854,6 @@ enum mkt_eth_capabilities {
 #define MTK_SHARED_INT		BIT(MTK_SHARED_INT_BIT)
 #define MTK_TRGMII_MT7621_CLK	BIT(MTK_TRGMII_MT7621_CLK_BIT)
 #define MTK_QDMA		BIT(MTK_QDMA_BIT)
-#define MTK_NETSYS_V2		BIT(MTK_NETSYS_V2_BIT)
 #define MTK_SOC_MT7628		BIT(MTK_SOC_MT7628_BIT)
 #define MTK_RSTCTRL_PPE1	BIT(MTK_RSTCTRL_PPE1_BIT)
 #define MTK_U3_COPHY_V2		BIT(MTK_U3_COPHY_V2_BIT)
@@ -934,11 +932,11 @@ enum mkt_eth_capabilities {
 #define MT7981_CAPS  (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | MTK_GMAC2_GEPHY | \
 		      MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \
 		      MTK_MUX_U3_GMAC2_TO_QPHY | MTK_U3_COPHY_V2 | \
-		      MTK_NETSYS_V2 | MTK_RSTCTRL_PPE1)
+		      MTK_RSTCTRL_PPE1)
 
 #define MT7986_CAPS  (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | \
 		      MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \
-		      MTK_NETSYS_V2 | MTK_RSTCTRL_PPE1)
+		      MTK_RSTCTRL_PPE1)
 
 struct mtk_tx_dma_desc_info {
 	dma_addr_t	addr;
@@ -1009,6 +1007,7 @@ struct mtk_reg_map {
  * @required_pctl		A bool value to show whether the SoC requires
  *				the extra setup for those pins used by GMAC.
  * @hash_offset			Flow table hash offset.
+ * @version			SoC version.
  * @foe_entry_size		Foe table entry size.
  * @has_accounting		Bool indicating support for accounting of
  *				offloaded flows.
@@ -1027,6 +1026,7 @@ struct mtk_soc_data {
 	bool		required_pctl;
 	u8		offload_version;
 	u8		hash_offset;
+	u8		version;
 	u16		foe_entry_size;
 	netdev_features_t hw_features;
 	bool		has_accounting;
@@ -1183,6 +1183,16 @@ struct mtk_mac {
 /* the struct describing the SoC. these are declared in the soc_xyz.c files */
 extern const struct of_device_id of_mtk_match[];
 
+static inline bool mtk_is_netsys_v1(struct mtk_eth *eth)
+{
+	return eth->soc->version == 1;
+}
+
+static inline bool mtk_is_netsys_v2_or_greater(struct mtk_eth *eth)
+{
+	return eth->soc->version > 1;
+}
+
 static inline struct mtk_foe_entry *
 mtk_foe_get_entry(struct mtk_ppe *ppe, u16 hash)
 {
@@ -1193,7 +1203,7 @@ mtk_foe_get_entry(struct mtk_ppe *ppe, u16 hash)
 
 static inline u32 mtk_get_ib1_ts_mask(struct mtk_eth *eth)
 {
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		return MTK_FOE_IB1_BIND_TIMESTAMP_V2;
 
 	return MTK_FOE_IB1_BIND_TIMESTAMP;
@@ -1201,7 +1211,7 @@ static inline u32 mtk_get_ib1_ts_mask(struct mtk_eth *eth)
 
 static inline u32 mtk_get_ib1_ppoe_mask(struct mtk_eth *eth)
 {
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		return MTK_FOE_IB1_BIND_PPPOE_V2;
 
 	return MTK_FOE_IB1_BIND_PPPOE;
@@ -1209,7 +1219,7 @@ static inline u32 mtk_get_ib1_ppoe_mask(struct mtk_eth *eth)
 
 static inline u32 mtk_get_ib1_vlan_tag_mask(struct mtk_eth *eth)
 {
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		return MTK_FOE_IB1_BIND_VLAN_TAG_V2;
 
 	return MTK_FOE_IB1_BIND_VLAN_TAG;
@@ -1217,7 +1227,7 @@ static inline u32 mtk_get_ib1_vlan_tag_mask(struct mtk_eth *eth)
 
 static inline u32 mtk_get_ib1_vlan_layer_mask(struct mtk_eth *eth)
 {
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		return MTK_FOE_IB1_BIND_VLAN_LAYER_V2;
 
 	return MTK_FOE_IB1_BIND_VLAN_LAYER;
@@ -1225,7 +1235,7 @@ static inline u32 mtk_get_ib1_vlan_layer_mask(struct mtk_eth *eth)
 
 static inline u32 mtk_prep_ib1_vlan_layer(struct mtk_eth *eth, u32 val)
 {
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		return FIELD_PREP(MTK_FOE_IB1_BIND_VLAN_LAYER_V2, val);
 
 	return FIELD_PREP(MTK_FOE_IB1_BIND_VLAN_LAYER, val);
@@ -1233,7 +1243,7 @@ static inline u32 mtk_prep_ib1_vlan_layer(struct mtk_eth *eth, u32 val)
 
 static inline u32 mtk_get_ib1_vlan_layer(struct mtk_eth *eth, u32 val)
 {
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		return FIELD_GET(MTK_FOE_IB1_BIND_VLAN_LAYER_V2, val);
 
 	return FIELD_GET(MTK_FOE_IB1_BIND_VLAN_LAYER, val);
@@ -1241,7 +1251,7 @@ static inline u32 mtk_get_ib1_vlan_layer(struct mtk_eth *eth, u32 val)
 
 static inline u32 mtk_get_ib1_pkt_type_mask(struct mtk_eth *eth)
 {
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		return MTK_FOE_IB1_PACKET_TYPE_V2;
 
 	return MTK_FOE_IB1_PACKET_TYPE;
@@ -1249,7 +1259,7 @@ static inline u32 mtk_get_ib1_pkt_type_mask(struct mtk_eth *eth)
 
 static inline u32 mtk_get_ib1_pkt_type(struct mtk_eth *eth, u32 val)
 {
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		return FIELD_GET(MTK_FOE_IB1_PACKET_TYPE_V2, val);
 
 	return FIELD_GET(MTK_FOE_IB1_PACKET_TYPE, val);
@@ -1257,7 +1267,7 @@ static inline u32 mtk_get_ib1_pkt_type(struct mtk_eth *eth, u32 val)
 
 static inline u32 mtk_get_ib2_multicast_mask(struct mtk_eth *eth)
 {
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(eth))
 		return MTK_FOE_IB2_MULTICAST_V2;
 
 	return MTK_FOE_IB2_MULTICAST;
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c
index 9129821f3ab8f..2f0e682449ef6 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.c
@@ -208,7 +208,7 @@ int mtk_foe_entry_prepare(struct mtk_eth *eth, struct mtk_foe_entry *entry,
 
 	memset(entry, 0, sizeof(*entry));
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(eth)) {
 		val = FIELD_PREP(MTK_FOE_IB1_STATE, MTK_FOE_STATE_BIND) |
 		      FIELD_PREP(MTK_FOE_IB1_PACKET_TYPE_V2, type) |
 		      FIELD_PREP(MTK_FOE_IB1_UDP, l4proto == IPPROTO_UDP) |
@@ -272,7 +272,7 @@ int mtk_foe_entry_set_pse_port(struct mtk_eth *eth,
 	u32 *ib2 = mtk_foe_entry_ib2(eth, entry);
 	u32 val = *ib2;
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(eth)) {
 		val &= ~MTK_FOE_IB2_DEST_PORT_V2;
 		val |= FIELD_PREP(MTK_FOE_IB2_DEST_PORT_V2, port);
 	} else {
@@ -423,7 +423,7 @@ int mtk_foe_entry_set_wdma(struct mtk_eth *eth, struct mtk_foe_entry *entry,
 	struct mtk_foe_mac_info *l2 = mtk_foe_entry_l2(eth, entry);
 	u32 *ib2 = mtk_foe_entry_ib2(eth, entry);
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(eth)) {
 		*ib2 &= ~MTK_FOE_IB2_PORT_MG_V2;
 		*ib2 |=  FIELD_PREP(MTK_FOE_IB2_RX_IDX, txq) |
 			 MTK_FOE_IB2_WDMA_WINFO_V2;
@@ -447,7 +447,7 @@ int mtk_foe_entry_set_queue(struct mtk_eth *eth, struct mtk_foe_entry *entry,
 {
 	u32 *ib2 = mtk_foe_entry_ib2(eth, entry);
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(eth)) {
 		*ib2 &= ~MTK_FOE_IB2_QID_V2;
 		*ib2 |= FIELD_PREP(MTK_FOE_IB2_QID_V2, queue);
 		*ib2 |= MTK_FOE_IB2_PSE_QOS_V2;
@@ -603,7 +603,7 @@ __mtk_foe_entry_commit(struct mtk_ppe *ppe, struct mtk_foe_entry *entry,
 	struct mtk_foe_entry *hwe;
 	u32 val;
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(eth)) {
 		entry->ib1 &= ~MTK_FOE_IB1_BIND_TIMESTAMP_V2;
 		entry->ib1 |= FIELD_PREP(MTK_FOE_IB1_BIND_TIMESTAMP_V2,
 					 timestamp);
@@ -619,7 +619,7 @@ __mtk_foe_entry_commit(struct mtk_ppe *ppe, struct mtk_foe_entry *entry,
 	hwe->ib1 = entry->ib1;
 
 	if (ppe->accounting) {
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+		if (mtk_is_netsys_v2_or_greater(eth))
 			val = MTK_FOE_IB2_MIB_CNT_V2;
 		else
 			val = MTK_FOE_IB2_MIB_CNT;
@@ -979,7 +979,7 @@ void mtk_ppe_start(struct mtk_ppe *ppe)
 			 MTK_PPE_SCAN_MODE_KEEPALIVE_AGE) |
 	      FIELD_PREP(MTK_PPE_TB_CFG_ENTRY_NUM,
 			 MTK_PPE_ENTRIES_SHIFT);
-	if (MTK_HAS_CAPS(ppe->eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(ppe->eth))
 		val |= MTK_PPE_TB_CFG_INFO_SEL;
 	ppe_w32(ppe, MTK_PPE_TB_CFG, val);
 
@@ -995,7 +995,7 @@ void mtk_ppe_start(struct mtk_ppe *ppe)
 	      MTK_PPE_FLOW_CFG_IP4_NAPT |
 	      MTK_PPE_FLOW_CFG_IP4_DSLITE |
 	      MTK_PPE_FLOW_CFG_IP4_NAT_FRAG;
-	if (MTK_HAS_CAPS(ppe->eth->soc->caps, MTK_NETSYS_V2))
+	if (mtk_is_netsys_v2_or_greater(ppe->eth))
 		val |= MTK_PPE_MD_TOAP_BYP_CRSN0 |
 		       MTK_PPE_MD_TOAP_BYP_CRSN1 |
 		       MTK_PPE_MD_TOAP_BYP_CRSN2 |
@@ -1037,7 +1037,7 @@ void mtk_ppe_start(struct mtk_ppe *ppe)
 
 	ppe_w32(ppe, MTK_PPE_DEFAULT_CPU_PORT, 0);
 
-	if (MTK_HAS_CAPS(ppe->eth->soc->caps, MTK_NETSYS_V2)) {
+	if (mtk_is_netsys_v2_or_greater(ppe->eth)) {
 		ppe_w32(ppe, MTK_PPE_DEFAULT_CPU_PORT1, 0xcb777);
 		ppe_w32(ppe, MTK_PPE_SBW_CTRL, 0x7f);
 	}
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index 02eebff02d457..a70a5417c1734 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -193,7 +193,7 @@ mtk_flow_set_output_device(struct mtk_eth *eth, struct mtk_foe_entry *foe,
 	if (mtk_flow_get_wdma_info(dev, dest_mac, &info) == 0) {
 		mtk_foe_entry_set_wdma(eth, foe, info.wdma_idx, info.queue,
 				       info.bss, info.wcid);
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+		if (mtk_is_netsys_v2_or_greater(eth)) {
 			switch (info.wdma_idx) {
 			case 0:
 				pse_port = 8;
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index 985cff910f30c..5f062ecb402cc 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -1091,7 +1091,7 @@ mtk_wed_rx_reset(struct mtk_wed_device *dev)
 	} else {
 		struct mtk_eth *eth = dev->hw->eth;
 
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+		if (mtk_is_netsys_v2_or_greater(eth))
 			wed_set(dev, MTK_WED_RESET_IDX,
 				MTK_WED_RESET_IDX_RX_V2);
 		else
@@ -1907,7 +1907,7 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth,
 	hw->wdma = wdma;
 	hw->index = index;
 	hw->irq = irq;
-	hw->version = MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2) ? 2 : 1;
+	hw->version = mtk_is_netsys_v1(eth) ? 1 : 2;
 
 	if (hw->version == 1) {
 		hw->mirror = syscon_regmap_lookup_by_phandle(eth_np,
-- 
GitLab


From 6ca265571b9e04ecc805e51c30e2949c9714dcaa Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 25 Jul 2023 01:52:27 +0100
Subject: [PATCH 0498/1806] net: ethernet: mtk_eth_soc: increase MAX_DEVS to 3

This is a preliminary patch to add MT7988 SoC support since it runs 3
macs instead of 2.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/3563e5fab367e7d79a7f1296fabaa5c20f202d7a.1690246066.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 8ca368973e922..9623b909387a3 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -1043,8 +1043,8 @@ struct mtk_soc_data {
 
 #define MTK_DMA_MONITOR_TIMEOUT		msecs_to_jiffies(1000)
 
-/* currently no SoC has more than 2 macs */
-#define MTK_MAX_DEVS			2
+/* currently no SoC has more than 3 macs */
+#define MTK_MAX_DEVS	3
 
 /* struct mtk_eth -	This is the main datasructure for holding the state
  *			of the driver
-- 
GitLab


From e05fd6274ee657cbf1689aba23ee900727cd4b8c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 25 Jul 2023 01:52:44 +0100
Subject: [PATCH 0499/1806] net: ethernet: mtk_eth_soc: rely on MTK_MAX_DEVS
 and remove MTK_MAC_COUNT

Get rid of MTK_MAC_COUNT since it is a duplicated of MTK_MAX_DEVS.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/1856f4266f2fc80677807b1bad867659e7b00c65.1690246066.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 49 ++++++++++++---------
 drivers/net/ethernet/mediatek/mtk_eth_soc.h |  1 -
 2 files changed, 27 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 206cffb0e5acf..67109a38df31a 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -896,7 +896,7 @@ static void mtk_stats_update(struct mtk_eth *eth)
 {
 	int i;
 
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
 		if (!eth->mac[i] || !eth->mac[i]->hw_stats)
 			continue;
 		if (spin_trylock(&eth->mac[i]->hw_stats->stats_lock)) {
@@ -1401,7 +1401,7 @@ static int mtk_queue_stopped(struct mtk_eth *eth)
 {
 	int i;
 
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
 		if (!eth->netdev[i])
 			continue;
 		if (netif_queue_stopped(eth->netdev[i]))
@@ -1415,7 +1415,7 @@ static void mtk_wake_queue(struct mtk_eth *eth)
 {
 	int i;
 
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
 		if (!eth->netdev[i])
 			continue;
 		netif_tx_wake_all_queues(eth->netdev[i]);
@@ -1874,7 +1874,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 			 !(trxd.rxd4 & RX_DMA_SPECIAL_TAG))
 			mac = RX_DMA_GET_SPORT(trxd.rxd4) - 1;
 
-		if (unlikely(mac < 0 || mac >= MTK_MAC_COUNT ||
+		if (unlikely(mac < 0 || mac >= MTK_MAX_DEVS ||
 			     !eth->netdev[mac]))
 			goto release_desc;
 
@@ -2911,7 +2911,7 @@ static void mtk_dma_free(struct mtk_eth *eth)
 	const struct mtk_soc_data *soc = eth->soc;
 	int i;
 
-	for (i = 0; i < MTK_MAC_COUNT; i++)
+	for (i = 0; i < MTK_MAX_DEVS; i++)
 		if (eth->netdev[i])
 			netdev_reset_queue(eth->netdev[i]);
 	if (eth->scratch_ring) {
@@ -3065,8 +3065,13 @@ static void mtk_gdm_config(struct mtk_eth *eth, u32 config)
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
 		return;
 
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
-		u32 val = mtk_r32(eth, MTK_GDMA_FWD_CFG(i));
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
+		u32 val;
+
+		if (!eth->netdev[i])
+			continue;
+
+		val = mtk_r32(eth, MTK_GDMA_FWD_CFG(i));
 
 		/* default setup the forward port to send frame to PDMA */
 		val &= ~0xffff;
@@ -3076,7 +3081,7 @@ static void mtk_gdm_config(struct mtk_eth *eth, u32 config)
 
 		val |= config;
 
-		if (eth->netdev[i] && netdev_uses_dsa(eth->netdev[i]))
+		if (netdev_uses_dsa(eth->netdev[i]))
 			val |= MTK_GDMA_SPECIAL_TAG;
 
 		mtk_w32(eth, val, MTK_GDMA_FWD_CFG(i));
@@ -3678,15 +3683,15 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	 * up with the more appropriate value when mtk_mac_config call is being
 	 * invoked.
 	 */
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
 		struct net_device *dev = eth->netdev[i];
 
-		mtk_w32(eth, MAC_MCR_FORCE_LINK_DOWN, MTK_MAC_MCR(i));
-		if (dev) {
-			struct mtk_mac *mac = netdev_priv(dev);
+		if (!dev)
+			continue;
 
-			mtk_set_mcr_max_rx(mac, dev->mtu + MTK_RX_ETH_HLEN);
-		}
+		mtk_w32(eth, MAC_MCR_FORCE_LINK_DOWN, MTK_MAC_MCR(i));
+		mtk_set_mcr_max_rx(netdev_priv(dev),
+				   dev->mtu + MTK_RX_ETH_HLEN);
 	}
 
 	/* Indicates CDM to parse the MTK special tag from CPU
@@ -3866,7 +3871,7 @@ static void mtk_pending_work(struct work_struct *work)
 	mtk_prepare_for_reset(eth);
 
 	/* stop all devices to make sure that dma is properly shut down */
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
 		if (!eth->netdev[i] || !netif_running(eth->netdev[i]))
 			continue;
 
@@ -3882,8 +3887,8 @@ static void mtk_pending_work(struct work_struct *work)
 	mtk_hw_init(eth, true);
 
 	/* restart DMA and enable IRQs */
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
-		if (!test_bit(i, &restart))
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
+		if (!eth->netdev[i] || !test_bit(i, &restart))
 			continue;
 
 		if (mtk_open(eth->netdev[i])) {
@@ -3910,7 +3915,7 @@ static int mtk_free_dev(struct mtk_eth *eth)
 {
 	int i;
 
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
 		if (!eth->netdev[i])
 			continue;
 		free_netdev(eth->netdev[i]);
@@ -3929,7 +3934,7 @@ static int mtk_unreg_dev(struct mtk_eth *eth)
 {
 	int i;
 
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
 		struct mtk_mac *mac;
 		if (!eth->netdev[i])
 			continue;
@@ -4231,7 +4236,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	}
 
 	id = be32_to_cpup(_id);
-	if (id >= MTK_MAC_COUNT) {
+	if (id >= MTK_MAX_DEVS) {
 		dev_err(eth->dev, "%d is not a valid mac id\n", id);
 		return -EINVAL;
 	}
@@ -4391,7 +4396,7 @@ void mtk_eth_set_dma_device(struct mtk_eth *eth, struct device *dma_dev)
 
 	rtnl_lock();
 
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
 		dev = eth->netdev[i];
 
 		if (!dev || !(dev->flags & IFF_UP))
@@ -4697,7 +4702,7 @@ static int mtk_remove(struct platform_device *pdev)
 	int i;
 
 	/* stop all devices to make sure that dma is properly shut down */
-	for (i = 0; i < MTK_MAC_COUNT; i++) {
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
 		if (!eth->netdev[i])
 			continue;
 		mtk_stop(eth->netdev[i]);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 9623b909387a3..4dc5611f859b0 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -33,7 +33,6 @@
 #define MTK_TX_DMA_BUF_LEN_V2	0xffff
 #define MTK_QDMA_RING_SIZE	2048
 #define MTK_DMA_SIZE		512
-#define MTK_MAC_COUNT		2
 #define MTK_RX_ETH_HLEN		(ETH_HLEN + ETH_FCS_LEN)
 #define MTK_RX_HLEN		(NET_SKB_PAD + MTK_RX_ETH_HLEN + NET_IP_ALIGN)
 #define MTK_DMA_DUMMY_DESC	0xffffffff
-- 
GitLab


From 1953f134a1a8b4732f6e1b15d0407959bf60209d Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 25 Jul 2023 01:52:59 +0100
Subject: [PATCH 0500/1806] net: ethernet: mtk_eth_soc: add NETSYS_V3 version
 support

Introduce NETSYS_V3 chipset version support.
This is a preliminary patch to introduce support for MT7988 SoC.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/0db2260910755d76fa48e303b9f9bdf4e5a82340.1690246066.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 105 ++++++++++++++------
 drivers/net/ethernet/mediatek/mtk_eth_soc.h |  48 +++++++--
 2 files changed, 116 insertions(+), 37 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 67109a38df31a..1344e2fc6d6f2 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -876,17 +876,32 @@ void mtk_stats_update_mac(struct mtk_mac *mac)
 			mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x20 + offs);
 		hw_stats->rx_flow_control_packets +=
 			mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x24 + offs);
-		hw_stats->tx_skip +=
-			mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x28 + offs);
-		hw_stats->tx_collisions +=
-			mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x2c + offs);
-		hw_stats->tx_bytes +=
-			mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x30 + offs);
-		stats =  mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x34 + offs);
-		if (stats)
-			hw_stats->tx_bytes += (stats << 32);
-		hw_stats->tx_packets +=
-			mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x38 + offs);
+
+		if (mtk_is_netsys_v3_or_greater(eth)) {
+			hw_stats->tx_skip +=
+				mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x50 + offs);
+			hw_stats->tx_collisions +=
+				mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x54 + offs);
+			hw_stats->tx_bytes +=
+				mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x40 + offs);
+			stats =  mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x44 + offs);
+			if (stats)
+				hw_stats->tx_bytes += (stats << 32);
+			hw_stats->tx_packets +=
+				mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x48 + offs);
+		} else {
+			hw_stats->tx_skip +=
+				mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x28 + offs);
+			hw_stats->tx_collisions +=
+				mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x2c + offs);
+			hw_stats->tx_bytes +=
+				mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x30 + offs);
+			stats =  mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x34 + offs);
+			if (stats)
+				hw_stats->tx_bytes += (stats << 32);
+			hw_stats->tx_packets +=
+				mtk_r32(mac->hw, reg_map->gdm1_cnt + 0x38 + offs);
+		}
 	}
 
 	u64_stats_update_end(&hw_stats->syncp);
@@ -1190,7 +1205,10 @@ static void mtk_tx_set_dma_desc_v2(struct net_device *dev, void *txd,
 		data |= TX_DMA_LS0;
 	WRITE_ONCE(desc->txd3, data);
 
-	data = (mac->id + 1) << TX_DMA_FPORT_SHIFT_V2; /* forward port */
+	if (mac->id == MTK_GMAC3_ID)
+		data = PSE_GDM3_PORT;
+	else
+		data = (mac->id + 1) << TX_DMA_FPORT_SHIFT_V2; /* forward port */
 	data |= TX_DMA_SWC_V2 | QID_BITS_V2(info->qid);
 	WRITE_ONCE(desc->txd4, data);
 
@@ -1201,6 +1219,8 @@ static void mtk_tx_set_dma_desc_v2(struct net_device *dev, void *txd,
 		/* tx checksum offload */
 		if (info->csum)
 			data |= TX_DMA_CHKSUM_V2;
+		if (mtk_is_netsys_v3_or_greater(eth) && netdev_uses_dsa(dev))
+			data |= TX_DMA_SPTAG_V3;
 	}
 	WRITE_ONCE(desc->txd5, data);
 
@@ -1266,8 +1286,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	mtk_tx_set_dma_desc(dev, itxd, &txd_info);
 
 	itx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
-	itx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 :
-			  MTK_TX_FLAGS_FPORT1;
+	itx_buf->mac_id = mac->id;
 	setup_tx_buf(eth, itx_buf, itxd_pdma, txd_info.addr, txd_info.size,
 		     k++);
 
@@ -1315,8 +1334,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 				memset(tx_buf, 0, sizeof(*tx_buf));
 			tx_buf->data = (void *)MTK_DMA_DUMMY_DESC;
 			tx_buf->flags |= MTK_TX_FLAGS_PAGE0;
-			tx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 :
-					 MTK_TX_FLAGS_FPORT1;
+			tx_buf->mac_id = mac->id;
 
 			setup_tx_buf(eth, tx_buf, txd_pdma, txd_info.addr,
 				     txd_info.size, k++);
@@ -1618,7 +1636,7 @@ static int mtk_xdp_frame_map(struct mtk_eth *eth, struct net_device *dev,
 	}
 	mtk_tx_set_dma_desc(dev, txd, txd_info);
 
-	tx_buf->flags |= !mac->id ? MTK_TX_FLAGS_FPORT0 : MTK_TX_FLAGS_FPORT1;
+	tx_buf->mac_id = mac->id;
 	tx_buf->type = dma_map ? MTK_TYPE_XDP_NDO : MTK_TYPE_XDP_TX;
 	tx_buf->data = (void *)MTK_DMA_DUMMY_DESC;
 
@@ -1868,11 +1886,24 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 			break;
 
 		/* find out which mac the packet come from. values start at 1 */
-		if (mtk_is_netsys_v2_or_greater(eth))
-			mac = RX_DMA_GET_SPORT_V2(trxd.rxd5) - 1;
-		else if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628) &&
-			 !(trxd.rxd4 & RX_DMA_SPECIAL_TAG))
+		if (mtk_is_netsys_v2_or_greater(eth)) {
+			u32 val = RX_DMA_GET_SPORT_V2(trxd.rxd5);
+
+			switch (val) {
+			case PSE_GDM1_PORT:
+			case PSE_GDM2_PORT:
+				mac = val - 1;
+				break;
+			case PSE_GDM3_PORT:
+				mac = MTK_GMAC3_ID;
+				break;
+			default:
+				break;
+			}
+		} else if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628) &&
+			   !(trxd.rxd4 & RX_DMA_SPECIAL_TAG)) {
 			mac = RX_DMA_GET_SPORT(trxd.rxd4) - 1;
+		}
 
 		if (unlikely(mac < 0 || mac >= MTK_MAX_DEVS ||
 			     !eth->netdev[mac]))
@@ -2094,7 +2125,6 @@ static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget,
 
 	while ((cpu != dma) && budget) {
 		u32 next_cpu = desc->txd2;
-		int mac = 0;
 
 		desc = mtk_qdma_phys_to_virt(ring, desc->txd2);
 		if ((desc->txd3 & TX_DMA_OWNER_CPU) == 0)
@@ -2102,15 +2132,13 @@ static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget,
 
 		tx_buf = mtk_desc_to_tx_buf(ring, desc,
 					    eth->soc->txrx.txd_size);
-		if (tx_buf->flags & MTK_TX_FLAGS_FPORT1)
-			mac = 1;
-
 		if (!tx_buf->data)
 			break;
 
 		if (tx_buf->data != (void *)MTK_DMA_DUMMY_DESC) {
 			if (tx_buf->type == MTK_TYPE_SKB)
-				mtk_poll_tx_done(eth, state, mac, tx_buf->data);
+				mtk_poll_tx_done(eth, state, tx_buf->mac_id,
+						 tx_buf->data);
 
 			budget--;
 		}
@@ -3721,7 +3749,24 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask, reg_map->qdma.int_grp + 4);
 	mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
 
-	if (mtk_is_netsys_v2_or_greater(eth)) {
+	if (mtk_is_netsys_v3_or_greater(eth)) {
+		/* PSE should not drop port1, port8 and port9 packets */
+		mtk_w32(eth, 0x00000302, PSE_DROP_CFG);
+
+		/* GDM and CDM Threshold */
+		mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES);
+		mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES);
+
+		/* Disable GDM1 RX CRC stripping */
+		mtk_m32(eth, MTK_GDMA_STRP_CRC, 0, MTK_GDMA_FWD_CFG(0));
+
+		/* PSE GDM3 MIB counter has incorrect hw default values,
+		 * so the driver ought to read clear the values beforehand
+		 * in case ethtool retrieve wrong mib values.
+		 */
+		for (i = 0; i < 0x80; i += 0x4)
+			mtk_r32(eth, reg_map->gdm1_cnt + 0x100 + i);
+	} else if (!mtk_is_netsys_v1(eth)) {
 		/* PSE should not drop port8 and port9 packets from WDMA Tx */
 		mtk_w32(eth, 0x00000300, PSE_DROP_CFG);
 
@@ -4284,7 +4329,11 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	}
 	spin_lock_init(&mac->hw_stats->stats_lock);
 	u64_stats_init(&mac->hw_stats->syncp);
-	mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET;
+
+	if (mtk_is_netsys_v3_or_greater(eth))
+		mac->hw_stats->reg_offset = id * 0x80;
+	else
+		mac->hw_stats->reg_offset = id * 0x40;
 
 	/* phylink create */
 	err = of_get_phy_mode(np, &phy_mode);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 4dc5611f859b0..3959bb39995fc 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -122,6 +122,7 @@
 #define MTK_GDMA_ICS_EN		BIT(22)
 #define MTK_GDMA_TCS_EN		BIT(21)
 #define MTK_GDMA_UCS_EN		BIT(20)
+#define MTK_GDMA_STRP_CRC	BIT(16)
 #define MTK_GDMA_TO_PDMA	0x0
 #define MTK_GDMA_DROP_ALL       0x7777
 
@@ -287,8 +288,6 @@
 /* QDMA Interrupt grouping registers */
 #define MTK_RLS_DONE_INT	BIT(0)
 
-#define MTK_STAT_OFFSET		0x40
-
 /* QDMA TX NUM */
 #define QID_BITS_V2(x)		(((x) & 0x3f) << 16)
 #define MTK_QDMA_GMAC2_QID	8
@@ -301,6 +300,8 @@
 #define TX_DMA_CHKSUM_V2	(0x7 << 28)
 #define TX_DMA_TSO_V2		BIT(31)
 
+#define TX_DMA_SPTAG_V3         BIT(27)
+
 /* QDMA V2 descriptor txd4 */
 #define TX_DMA_FPORT_SHIFT_V2	8
 #define TX_DMA_FPORT_MASK_V2	0xf
@@ -634,12 +635,6 @@ enum mtk_tx_flags {
 	 */
 	MTK_TX_FLAGS_SINGLE0	= 0x01,
 	MTK_TX_FLAGS_PAGE0	= 0x02,
-
-	/* MTK_TX_FLAGS_FPORTx allows tracking which port the transmitted
-	 * SKB out instead of looking up through hardware TX descriptor.
-	 */
-	MTK_TX_FLAGS_FPORT0	= 0x04,
-	MTK_TX_FLAGS_FPORT1	= 0x08,
 };
 
 /* This enum allows us to identify how the clock is defined on the array of the
@@ -725,6 +720,35 @@ enum mtk_dev_state {
 	MTK_RESETTING
 };
 
+/* PSE Port Definition */
+enum mtk_pse_port {
+	PSE_ADMA_PORT = 0,
+	PSE_GDM1_PORT,
+	PSE_GDM2_PORT,
+	PSE_PPE0_PORT,
+	PSE_PPE1_PORT,
+	PSE_QDMA_TX_PORT,
+	PSE_QDMA_RX_PORT,
+	PSE_DROP_PORT,
+	PSE_WDMA0_PORT,
+	PSE_WDMA1_PORT,
+	PSE_TDMA_PORT,
+	PSE_NONE_PORT,
+	PSE_PPE2_PORT,
+	PSE_WDMA2_PORT,
+	PSE_EIP197_PORT,
+	PSE_GDM3_PORT,
+	PSE_PORT_MAX
+};
+
+/* GMAC Identifier */
+enum mtk_gmac_id {
+	MTK_GMAC1_ID = 0,
+	MTK_GMAC2_ID,
+	MTK_GMAC3_ID,
+	MTK_GMAC_ID_MAX
+};
+
 enum mtk_tx_buf_type {
 	MTK_TYPE_SKB,
 	MTK_TYPE_XDP_TX,
@@ -743,7 +767,8 @@ struct mtk_tx_buf {
 	enum mtk_tx_buf_type type;
 	void *data;
 
-	u32 flags;
+	u16 mac_id;
+	u16 flags;
 	DEFINE_DMA_UNMAP_ADDR(dma_addr0);
 	DEFINE_DMA_UNMAP_LEN(dma_len0);
 	DEFINE_DMA_UNMAP_ADDR(dma_addr1);
@@ -1192,6 +1217,11 @@ static inline bool mtk_is_netsys_v2_or_greater(struct mtk_eth *eth)
 	return eth->soc->version > 1;
 }
 
+static inline bool mtk_is_netsys_v3_or_greater(struct mtk_eth *eth)
+{
+	return eth->soc->version > 2;
+}
+
 static inline struct mtk_foe_entry *
 mtk_foe_get_entry(struct mtk_ppe *ppe, u16 hash)
 {
-- 
GitLab


From 51a4df60db5c2071782ba42a6803bb682e1d1f0a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 25 Jul 2023 01:53:13 +0100
Subject: [PATCH 0501/1806] net: ethernet: mtk_eth_soc: convert caps in
 mtk_soc_data struct to u64

This is a preliminary patch to introduce support for MT7988 SoC.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/9499ac3670b2fc5b444404b84e8a4a169beabbf2.1690246066.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_path.c | 22 ++++----
 drivers/net/ethernet/mediatek/mtk_eth_soc.h  | 56 ++++++++++----------
 2 files changed, 39 insertions(+), 39 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_path.c b/drivers/net/ethernet/mediatek/mtk_eth_path.c
index 317e447f49916..34ac492e047cb 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_path.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_path.c
@@ -15,10 +15,10 @@
 struct mtk_eth_muxc {
 	const char	*name;
 	int		cap_bit;
-	int		(*set_path)(struct mtk_eth *eth, int path);
+	int		(*set_path)(struct mtk_eth *eth, u64 path);
 };
 
-static const char *mtk_eth_path_name(int path)
+static const char *mtk_eth_path_name(u64 path)
 {
 	switch (path) {
 	case MTK_ETH_PATH_GMAC1_RGMII:
@@ -40,7 +40,7 @@ static const char *mtk_eth_path_name(int path)
 	}
 }
 
-static int set_mux_gdm1_to_gmac1_esw(struct mtk_eth *eth, int path)
+static int set_mux_gdm1_to_gmac1_esw(struct mtk_eth *eth, u64 path)
 {
 	bool updated = true;
 	u32 val, mask, set;
@@ -71,7 +71,7 @@ static int set_mux_gdm1_to_gmac1_esw(struct mtk_eth *eth, int path)
 	return 0;
 }
 
-static int set_mux_gmac2_gmac0_to_gephy(struct mtk_eth *eth, int path)
+static int set_mux_gmac2_gmac0_to_gephy(struct mtk_eth *eth, u64 path)
 {
 	unsigned int val = 0;
 	bool updated = true;
@@ -94,7 +94,7 @@ static int set_mux_gmac2_gmac0_to_gephy(struct mtk_eth *eth, int path)
 	return 0;
 }
 
-static int set_mux_u3_gmac2_to_qphy(struct mtk_eth *eth, int path)
+static int set_mux_u3_gmac2_to_qphy(struct mtk_eth *eth, u64 path)
 {
 	unsigned int val = 0, mask = 0, reg = 0;
 	bool updated = true;
@@ -125,7 +125,7 @@ static int set_mux_u3_gmac2_to_qphy(struct mtk_eth *eth, int path)
 	return 0;
 }
 
-static int set_mux_gmac1_gmac2_to_sgmii_rgmii(struct mtk_eth *eth, int path)
+static int set_mux_gmac1_gmac2_to_sgmii_rgmii(struct mtk_eth *eth, u64 path)
 {
 	unsigned int val = 0;
 	bool updated = true;
@@ -163,7 +163,7 @@ static int set_mux_gmac1_gmac2_to_sgmii_rgmii(struct mtk_eth *eth, int path)
 	return 0;
 }
 
-static int set_mux_gmac12_to_gephy_sgmii(struct mtk_eth *eth, int path)
+static int set_mux_gmac12_to_gephy_sgmii(struct mtk_eth *eth, u64 path)
 {
 	unsigned int val = 0;
 	bool updated = true;
@@ -218,7 +218,7 @@ static const struct mtk_eth_muxc mtk_eth_muxc[] = {
 	},
 };
 
-static int mtk_eth_mux_setup(struct mtk_eth *eth, int path)
+static int mtk_eth_mux_setup(struct mtk_eth *eth, u64 path)
 {
 	int i, err = 0;
 
@@ -249,7 +249,7 @@ out:
 
 int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id)
 {
-	int path;
+	u64 path;
 
 	path = (mac_id == 0) ?  MTK_ETH_PATH_GMAC1_SGMII :
 				MTK_ETH_PATH_GMAC2_SGMII;
@@ -260,7 +260,7 @@ int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id)
 
 int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id)
 {
-	int path = 0;
+	u64 path = 0;
 
 	if (mac_id == 1)
 		path = MTK_ETH_PATH_GMAC2_GEPHY;
@@ -274,7 +274,7 @@ int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id)
 
 int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id)
 {
-	int path;
+	u64 path;
 
 	path = (mac_id == 0) ?  MTK_ETH_PATH_GMAC1_RGMII :
 				MTK_ETH_PATH_GMAC2_RGMII;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 3959bb39995fc..9fe6e44f5e327 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -866,41 +866,41 @@ enum mkt_eth_capabilities {
 };
 
 /* Supported hardware group on SoCs */
-#define MTK_RGMII		BIT(MTK_RGMII_BIT)
-#define MTK_TRGMII		BIT(MTK_TRGMII_BIT)
-#define MTK_SGMII		BIT(MTK_SGMII_BIT)
-#define MTK_ESW			BIT(MTK_ESW_BIT)
-#define MTK_GEPHY		BIT(MTK_GEPHY_BIT)
-#define MTK_MUX			BIT(MTK_MUX_BIT)
-#define MTK_INFRA		BIT(MTK_INFRA_BIT)
-#define MTK_SHARED_SGMII	BIT(MTK_SHARED_SGMII_BIT)
-#define MTK_HWLRO		BIT(MTK_HWLRO_BIT)
-#define MTK_SHARED_INT		BIT(MTK_SHARED_INT_BIT)
-#define MTK_TRGMII_MT7621_CLK	BIT(MTK_TRGMII_MT7621_CLK_BIT)
-#define MTK_QDMA		BIT(MTK_QDMA_BIT)
-#define MTK_SOC_MT7628		BIT(MTK_SOC_MT7628_BIT)
-#define MTK_RSTCTRL_PPE1	BIT(MTK_RSTCTRL_PPE1_BIT)
-#define MTK_U3_COPHY_V2		BIT(MTK_U3_COPHY_V2_BIT)
+#define MTK_RGMII		BIT_ULL(MTK_RGMII_BIT)
+#define MTK_TRGMII		BIT_ULL(MTK_TRGMII_BIT)
+#define MTK_SGMII		BIT_ULL(MTK_SGMII_BIT)
+#define MTK_ESW			BIT_ULL(MTK_ESW_BIT)
+#define MTK_GEPHY		BIT_ULL(MTK_GEPHY_BIT)
+#define MTK_MUX			BIT_ULL(MTK_MUX_BIT)
+#define MTK_INFRA		BIT_ULL(MTK_INFRA_BIT)
+#define MTK_SHARED_SGMII	BIT_ULL(MTK_SHARED_SGMII_BIT)
+#define MTK_HWLRO		BIT_ULL(MTK_HWLRO_BIT)
+#define MTK_SHARED_INT		BIT_ULL(MTK_SHARED_INT_BIT)
+#define MTK_TRGMII_MT7621_CLK	BIT_ULL(MTK_TRGMII_MT7621_CLK_BIT)
+#define MTK_QDMA		BIT_ULL(MTK_QDMA_BIT)
+#define MTK_SOC_MT7628		BIT_ULL(MTK_SOC_MT7628_BIT)
+#define MTK_RSTCTRL_PPE1	BIT_ULL(MTK_RSTCTRL_PPE1_BIT)
+#define MTK_U3_COPHY_V2		BIT_ULL(MTK_U3_COPHY_V2_BIT)
 
 #define MTK_ETH_MUX_GDM1_TO_GMAC1_ESW		\
-	BIT(MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT)
+	BIT_ULL(MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT)
 #define MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY	\
-	BIT(MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY_BIT)
+	BIT_ULL(MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY_BIT)
 #define MTK_ETH_MUX_U3_GMAC2_TO_QPHY		\
-	BIT(MTK_ETH_MUX_U3_GMAC2_TO_QPHY_BIT)
+	BIT_ULL(MTK_ETH_MUX_U3_GMAC2_TO_QPHY_BIT)
 #define MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII	\
-	BIT(MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII_BIT)
+	BIT_ULL(MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII_BIT)
 #define MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII	\
-	BIT(MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII_BIT)
+	BIT_ULL(MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII_BIT)
 
 /* Supported path present on SoCs */
-#define MTK_ETH_PATH_GMAC1_RGMII	BIT(MTK_ETH_PATH_GMAC1_RGMII_BIT)
-#define MTK_ETH_PATH_GMAC1_TRGMII	BIT(MTK_ETH_PATH_GMAC1_TRGMII_BIT)
-#define MTK_ETH_PATH_GMAC1_SGMII	BIT(MTK_ETH_PATH_GMAC1_SGMII_BIT)
-#define MTK_ETH_PATH_GMAC2_RGMII	BIT(MTK_ETH_PATH_GMAC2_RGMII_BIT)
-#define MTK_ETH_PATH_GMAC2_SGMII	BIT(MTK_ETH_PATH_GMAC2_SGMII_BIT)
-#define MTK_ETH_PATH_GMAC2_GEPHY	BIT(MTK_ETH_PATH_GMAC2_GEPHY_BIT)
-#define MTK_ETH_PATH_GDM1_ESW		BIT(MTK_ETH_PATH_GDM1_ESW_BIT)
+#define MTK_ETH_PATH_GMAC1_RGMII	BIT_ULL(MTK_ETH_PATH_GMAC1_RGMII_BIT)
+#define MTK_ETH_PATH_GMAC1_TRGMII	BIT_ULL(MTK_ETH_PATH_GMAC1_TRGMII_BIT)
+#define MTK_ETH_PATH_GMAC1_SGMII	BIT_ULL(MTK_ETH_PATH_GMAC1_SGMII_BIT)
+#define MTK_ETH_PATH_GMAC2_RGMII	BIT_ULL(MTK_ETH_PATH_GMAC2_RGMII_BIT)
+#define MTK_ETH_PATH_GMAC2_SGMII	BIT_ULL(MTK_ETH_PATH_GMAC2_SGMII_BIT)
+#define MTK_ETH_PATH_GMAC2_GEPHY	BIT_ULL(MTK_ETH_PATH_GMAC2_GEPHY_BIT)
+#define MTK_ETH_PATH_GDM1_ESW		BIT_ULL(MTK_ETH_PATH_GDM1_ESW_BIT)
 
 #define MTK_GMAC1_RGMII		(MTK_ETH_PATH_GMAC1_RGMII | MTK_RGMII)
 #define MTK_GMAC1_TRGMII	(MTK_ETH_PATH_GMAC1_TRGMII | MTK_TRGMII)
@@ -1045,7 +1045,7 @@ struct mtk_reg_map {
 struct mtk_soc_data {
 	const struct mtk_reg_map *reg_map;
 	u32             ana_rgc3;
-	u32		caps;
+	u64		caps;
 	u32		required_clks;
 	bool		required_pctl;
 	u8		offload_version;
-- 
GitLab


From c75e416ccfd29257f39e88d0d4b3ced405d5bf01 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 25 Jul 2023 01:53:28 +0100
Subject: [PATCH 0502/1806] net: ethernet: mtk_eth_soc: convert clock bitmap to
 u64

The to-be-added MT7988 SoC adds many new clocks which need to be
controlled by the Ethernet driver, which will result in their total
number exceeding 32.
Prepare by converting clock bitmaps into 64-bit types.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/6960a39bb0078cf84d7642a9558e6a91c6cc9df3.1690246066.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.h | 96 +++++++++++----------
 1 file changed, 49 insertions(+), 47 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 9fe6e44f5e327..5902944ddb4fa 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -666,54 +666,56 @@ enum mtk_clks_map {
 	MTK_CLK_MAX
 };
 
-#define MT7623_CLKS_BITMAP	(BIT(MTK_CLK_ETHIF) | BIT(MTK_CLK_ESW) |  \
-				 BIT(MTK_CLK_GP1) | BIT(MTK_CLK_GP2) | \
-				 BIT(MTK_CLK_TRGPLL))
-#define MT7622_CLKS_BITMAP	(BIT(MTK_CLK_ETHIF) | BIT(MTK_CLK_ESW) |  \
-				 BIT(MTK_CLK_GP0) | BIT(MTK_CLK_GP1) | \
-				 BIT(MTK_CLK_GP2) | \
-				 BIT(MTK_CLK_SGMII_TX_250M) | \
-				 BIT(MTK_CLK_SGMII_RX_250M) | \
-				 BIT(MTK_CLK_SGMII_CDR_REF) | \
-				 BIT(MTK_CLK_SGMII_CDR_FB) | \
-				 BIT(MTK_CLK_SGMII_CK) | \
-				 BIT(MTK_CLK_ETH2PLL))
+#define MT7623_CLKS_BITMAP	(BIT_ULL(MTK_CLK_ETHIF) | BIT_ULL(MTK_CLK_ESW) |  \
+				 BIT_ULL(MTK_CLK_GP1) | BIT_ULL(MTK_CLK_GP2) | \
+				 BIT_ULL(MTK_CLK_TRGPLL))
+#define MT7622_CLKS_BITMAP	(BIT_ULL(MTK_CLK_ETHIF) | BIT_ULL(MTK_CLK_ESW) |  \
+				 BIT_ULL(MTK_CLK_GP0) | BIT_ULL(MTK_CLK_GP1) | \
+				 BIT_ULL(MTK_CLK_GP2) | \
+				 BIT_ULL(MTK_CLK_SGMII_TX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII_RX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII_CDR_REF) | \
+				 BIT_ULL(MTK_CLK_SGMII_CDR_FB) | \
+				 BIT_ULL(MTK_CLK_SGMII_CK) | \
+				 BIT_ULL(MTK_CLK_ETH2PLL))
 #define MT7621_CLKS_BITMAP	(0)
 #define MT7628_CLKS_BITMAP	(0)
-#define MT7629_CLKS_BITMAP	(BIT(MTK_CLK_ETHIF) | BIT(MTK_CLK_ESW) |  \
-				 BIT(MTK_CLK_GP0) | BIT(MTK_CLK_GP1) | \
-				 BIT(MTK_CLK_GP2) | BIT(MTK_CLK_FE) | \
-				 BIT(MTK_CLK_SGMII_TX_250M) | \
-				 BIT(MTK_CLK_SGMII_RX_250M) | \
-				 BIT(MTK_CLK_SGMII_CDR_REF) | \
-				 BIT(MTK_CLK_SGMII_CDR_FB) | \
-				 BIT(MTK_CLK_SGMII2_TX_250M) | \
-				 BIT(MTK_CLK_SGMII2_RX_250M) | \
-				 BIT(MTK_CLK_SGMII2_CDR_REF) | \
-				 BIT(MTK_CLK_SGMII2_CDR_FB) | \
-				 BIT(MTK_CLK_SGMII_CK) | \
-				 BIT(MTK_CLK_ETH2PLL) | BIT(MTK_CLK_SGMIITOP))
-#define MT7981_CLKS_BITMAP	(BIT(MTK_CLK_FE) | BIT(MTK_CLK_GP2) | BIT(MTK_CLK_GP1) | \
-				 BIT(MTK_CLK_WOCPU0) | \
-				 BIT(MTK_CLK_SGMII_TX_250M) | \
-				 BIT(MTK_CLK_SGMII_RX_250M) | \
-				 BIT(MTK_CLK_SGMII_CDR_REF) | \
-				 BIT(MTK_CLK_SGMII_CDR_FB) | \
-				 BIT(MTK_CLK_SGMII2_TX_250M) | \
-				 BIT(MTK_CLK_SGMII2_RX_250M) | \
-				 BIT(MTK_CLK_SGMII2_CDR_REF) | \
-				 BIT(MTK_CLK_SGMII2_CDR_FB) | \
-				 BIT(MTK_CLK_SGMII_CK))
-#define MT7986_CLKS_BITMAP	(BIT(MTK_CLK_FE) | BIT(MTK_CLK_GP2) | BIT(MTK_CLK_GP1) | \
-				 BIT(MTK_CLK_WOCPU1) | BIT(MTK_CLK_WOCPU0) | \
-				 BIT(MTK_CLK_SGMII_TX_250M) | \
-				 BIT(MTK_CLK_SGMII_RX_250M) | \
-				 BIT(MTK_CLK_SGMII_CDR_REF) | \
-				 BIT(MTK_CLK_SGMII_CDR_FB) | \
-				 BIT(MTK_CLK_SGMII2_TX_250M) | \
-				 BIT(MTK_CLK_SGMII2_RX_250M) | \
-				 BIT(MTK_CLK_SGMII2_CDR_REF) | \
-				 BIT(MTK_CLK_SGMII2_CDR_FB))
+#define MT7629_CLKS_BITMAP	(BIT_ULL(MTK_CLK_ETHIF) | BIT_ULL(MTK_CLK_ESW) |  \
+				 BIT_ULL(MTK_CLK_GP0) | BIT_ULL(MTK_CLK_GP1) | \
+				 BIT_ULL(MTK_CLK_GP2) | BIT_ULL(MTK_CLK_FE) | \
+				 BIT_ULL(MTK_CLK_SGMII_TX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII_RX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII_CDR_REF) | \
+				 BIT_ULL(MTK_CLK_SGMII_CDR_FB) | \
+				 BIT_ULL(MTK_CLK_SGMII2_TX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII2_RX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII2_CDR_REF) | \
+				 BIT_ULL(MTK_CLK_SGMII2_CDR_FB) | \
+				 BIT_ULL(MTK_CLK_SGMII_CK) | \
+				 BIT_ULL(MTK_CLK_ETH2PLL) | BIT_ULL(MTK_CLK_SGMIITOP))
+#define MT7981_CLKS_BITMAP	(BIT_ULL(MTK_CLK_FE) | BIT_ULL(MTK_CLK_GP2) | \
+				 BIT_ULL(MTK_CLK_GP1) | \
+				 BIT_ULL(MTK_CLK_WOCPU0) | \
+				 BIT_ULL(MTK_CLK_SGMII_TX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII_RX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII_CDR_REF) | \
+				 BIT_ULL(MTK_CLK_SGMII_CDR_FB) | \
+				 BIT_ULL(MTK_CLK_SGMII2_TX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII2_RX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII2_CDR_REF) | \
+				 BIT_ULL(MTK_CLK_SGMII2_CDR_FB) | \
+				 BIT_ULL(MTK_CLK_SGMII_CK))
+#define MT7986_CLKS_BITMAP	(BIT_ULL(MTK_CLK_FE) | BIT_ULL(MTK_CLK_GP2) | \
+				 BIT_ULL(MTK_CLK_GP1) | \
+				 BIT_ULL(MTK_CLK_WOCPU1) | BIT_ULL(MTK_CLK_WOCPU0) | \
+				 BIT_ULL(MTK_CLK_SGMII_TX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII_RX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII_CDR_REF) | \
+				 BIT_ULL(MTK_CLK_SGMII_CDR_FB) | \
+				 BIT_ULL(MTK_CLK_SGMII2_TX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII2_RX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII2_CDR_REF) | \
+				 BIT_ULL(MTK_CLK_SGMII2_CDR_FB))
 
 enum mtk_dev_state {
 	MTK_HW_INIT,
@@ -1046,7 +1048,7 @@ struct mtk_soc_data {
 	const struct mtk_reg_map *reg_map;
 	u32             ana_rgc3;
 	u64		caps;
-	u32		required_clks;
+	u64		required_clks;
 	bool		required_pctl;
 	u8		offload_version;
 	u8		hash_offset;
-- 
GitLab


From 445eb6448ed3bf02a76f183e8499d11459281205 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 25 Jul 2023 01:57:42 +0100
Subject: [PATCH 0503/1806] net: ethernet: mtk_eth_soc: add basic support for
 MT7988 SoC

Introduce support for ethernet chip available in MT7988 SoC to
mtk_eth_soc driver. As a first step support only the first GMAC which
is hard-wired to the internal DSA switch having 4 built-in gigabit
Ethernet PHYs.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/25c8377095b95d186872eeda7aa055da83e8f0ca.1690246605.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_path.c |  14 +-
 drivers/net/ethernet/mediatek/mtk_eth_soc.c  | 201 +++++++++++++++++--
 drivers/net/ethernet/mediatek/mtk_eth_soc.h  |  86 +++++++-
 3 files changed, 273 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_path.c b/drivers/net/ethernet/mediatek/mtk_eth_path.c
index 34ac492e047cb..7c27a19c4d8f4 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_path.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_path.c
@@ -43,7 +43,7 @@ static const char *mtk_eth_path_name(u64 path)
 static int set_mux_gdm1_to_gmac1_esw(struct mtk_eth *eth, u64 path)
 {
 	bool updated = true;
-	u32 val, mask, set;
+	u32 mask, set, reg;
 
 	switch (path) {
 	case MTK_ETH_PATH_GMAC1_SGMII:
@@ -59,11 +59,13 @@ static int set_mux_gdm1_to_gmac1_esw(struct mtk_eth *eth, u64 path)
 		break;
 	}
 
-	if (updated) {
-		val = mtk_r32(eth, MTK_MAC_MISC);
-		val = (val & mask) | set;
-		mtk_w32(eth, val, MTK_MAC_MISC);
-	}
+	if (mtk_is_netsys_v3_or_greater(eth))
+		reg = MTK_MAC_MISC_V3;
+	else
+		reg = MTK_MAC_MISC;
+
+	if (updated)
+		mtk_m32(eth, mask, set, reg);
 
 	dev_dbg(eth->dev, "path %s in %s updated = %d\n",
 		mtk_eth_path_name(path), __func__, updated);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 1344e2fc6d6f2..30e3935e83f9a 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -152,6 +152,54 @@ static const struct mtk_reg_map mt7986_reg_map = {
 	.pse_oq_sta		= 0x01a0,
 };
 
+static const struct mtk_reg_map mt7988_reg_map = {
+	.tx_irq_mask		= 0x461c,
+	.tx_irq_status		= 0x4618,
+	.pdma = {
+		.rx_ptr		= 0x6900,
+		.rx_cnt_cfg	= 0x6904,
+		.pcrx_ptr	= 0x6908,
+		.glo_cfg	= 0x6a04,
+		.rst_idx	= 0x6a08,
+		.delay_irq	= 0x6a0c,
+		.irq_status	= 0x6a20,
+		.irq_mask	= 0x6a28,
+		.adma_rx_dbg0	= 0x6a38,
+		.int_grp	= 0x6a50,
+	},
+	.qdma = {
+		.qtx_cfg	= 0x4400,
+		.qtx_sch	= 0x4404,
+		.rx_ptr		= 0x4500,
+		.rx_cnt_cfg	= 0x4504,
+		.qcrx_ptr	= 0x4508,
+		.glo_cfg	= 0x4604,
+		.rst_idx	= 0x4608,
+		.delay_irq	= 0x460c,
+		.fc_th		= 0x4610,
+		.int_grp	= 0x4620,
+		.hred		= 0x4644,
+		.ctx_ptr	= 0x4700,
+		.dtx_ptr	= 0x4704,
+		.crx_ptr	= 0x4710,
+		.drx_ptr	= 0x4714,
+		.fq_head	= 0x4720,
+		.fq_tail	= 0x4724,
+		.fq_count	= 0x4728,
+		.fq_blen	= 0x472c,
+		.tx_sch_rate	= 0x4798,
+	},
+	.gdm1_cnt		= 0x1c00,
+	.gdma_to_ppe		= 0x3333,
+	.ppe_base		= 0x2000,
+	.wdma_base = {
+		[0]		= 0x4800,
+		[1]		= 0x4c00,
+	},
+	.pse_iq_sta		= 0x0180,
+	.pse_oq_sta		= 0x01a0,
+};
+
 /* strings used by ethtool */
 static const struct mtk_ethtool_stats {
 	char str[ETH_GSTRING_LEN];
@@ -179,10 +227,54 @@ static const struct mtk_ethtool_stats {
 };
 
 static const char * const mtk_clks_source_name[] = {
-	"ethif", "sgmiitop", "esw", "gp0", "gp1", "gp2", "fe", "trgpll",
-	"sgmii_tx250m", "sgmii_rx250m", "sgmii_cdr_ref", "sgmii_cdr_fb",
-	"sgmii2_tx250m", "sgmii2_rx250m", "sgmii2_cdr_ref", "sgmii2_cdr_fb",
-	"sgmii_ck", "eth2pll", "wocpu0", "wocpu1", "netsys0", "netsys1"
+	"ethif",
+	"sgmiitop",
+	"esw",
+	"gp0",
+	"gp1",
+	"gp2",
+	"gp3",
+	"xgp1",
+	"xgp2",
+	"xgp3",
+	"crypto",
+	"fe",
+	"trgpll",
+	"sgmii_tx250m",
+	"sgmii_rx250m",
+	"sgmii_cdr_ref",
+	"sgmii_cdr_fb",
+	"sgmii2_tx250m",
+	"sgmii2_rx250m",
+	"sgmii2_cdr_ref",
+	"sgmii2_cdr_fb",
+	"sgmii_ck",
+	"eth2pll",
+	"wocpu0",
+	"wocpu1",
+	"netsys0",
+	"netsys1",
+	"ethwarp_wocpu2",
+	"ethwarp_wocpu1",
+	"ethwarp_wocpu0",
+	"top_usxgmii0_sel",
+	"top_usxgmii1_sel",
+	"top_sgm0_sel",
+	"top_sgm1_sel",
+	"top_xfi_phy0_xtal_sel",
+	"top_xfi_phy1_xtal_sel",
+	"top_eth_gmii_sel",
+	"top_eth_refck_50m_sel",
+	"top_eth_sys_200m_sel",
+	"top_eth_sys_sel",
+	"top_eth_xgmii_sel",
+	"top_eth_mii_sel",
+	"top_netsys_sel",
+	"top_netsys_500m_sel",
+	"top_netsys_pao_2x_sel",
+	"top_netsys_sync_250m_sel",
+	"top_netsys_ppefb_250m_sel",
+	"top_netsys_warp_sel",
 };
 
 void mtk_w32(struct mtk_eth *eth, u32 val, unsigned reg)
@@ -195,7 +287,7 @@ u32 mtk_r32(struct mtk_eth *eth, unsigned reg)
 	return __raw_readl(eth->base + reg);
 }
 
-static u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned reg)
+u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned int reg)
 {
 	u32 val;
 
@@ -400,6 +492,19 @@ static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth,
 	dev_err(eth->dev, "Missing PLL configuration, ethernet may not work\n");
 }
 
+static void mtk_setup_bridge_switch(struct mtk_eth *eth)
+{
+	/* Force Port1 XGMAC Link Up */
+	mtk_m32(eth, 0, MTK_XGMAC_FORCE_LINK(MTK_GMAC1_ID),
+		MTK_XGMAC_STS(MTK_GMAC1_ID));
+
+	/* Adjust GSW bridge IPG to 11 */
+	mtk_m32(eth, GSWTX_IPG_MASK | GSWRX_IPG_MASK,
+		(GSW_IPG_11 << GSWTX_IPG_SHIFT) |
+		(GSW_IPG_11 << GSWRX_IPG_SHIFT),
+		MTK_GSW_CFG);
+}
+
 static struct phylink_pcs *mtk_mac_select_pcs(struct phylink_config *config,
 					      phy_interface_t interface)
 {
@@ -459,6 +564,8 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 					goto init_err;
 			}
 			break;
+		case PHY_INTERFACE_MODE_INTERNAL:
+			break;
 		default:
 			goto err_phy;
 		}
@@ -528,6 +635,15 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 		return;
 	}
 
+	/* Setup gmac */
+	if (mtk_is_netsys_v3_or_greater(eth) &&
+	    mac->interface == PHY_INTERFACE_MODE_INTERNAL) {
+		mtk_w32(mac->hw, MTK_GDMA_XGDM_SEL, MTK_GDMA_EG_CTRL(mac->id));
+		mtk_w32(mac->hw, MAC_MCR_FORCE_LINK_DOWN, MTK_MAC_MCR(mac->id));
+
+		mtk_setup_bridge_switch(eth);
+	}
+
 	return;
 
 err_phy:
@@ -740,11 +856,15 @@ static int mtk_mdio_init(struct mtk_eth *eth)
 	}
 	divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
 
+	/* Configure MDC Turbo Mode */
+	if (mtk_is_netsys_v3_or_greater(eth))
+		mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
+
 	/* Configure MDC Divider */
-	val = mtk_r32(eth, MTK_PPSC);
-	val &= ~PPSC_MDC_CFG;
-	val |= FIELD_PREP(PPSC_MDC_CFG, divider) | PPSC_MDC_TURBO;
-	mtk_w32(eth, val, MTK_PPSC);
+	val = FIELD_PREP(PPSC_MDC_CFG, divider);
+	if (!mtk_is_netsys_v3_or_greater(eth))
+		val |= PPSC_MDC_TURBO;
+	mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
 
 	dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / divider);
 
@@ -1205,10 +1325,19 @@ static void mtk_tx_set_dma_desc_v2(struct net_device *dev, void *txd,
 		data |= TX_DMA_LS0;
 	WRITE_ONCE(desc->txd3, data);
 
-	if (mac->id == MTK_GMAC3_ID)
-		data = PSE_GDM3_PORT;
-	else
-		data = (mac->id + 1) << TX_DMA_FPORT_SHIFT_V2; /* forward port */
+	 /* set forward port */
+	switch (mac->id) {
+	case MTK_GMAC1_ID:
+		data = PSE_GDM1_PORT << TX_DMA_FPORT_SHIFT_V2;
+		break;
+	case MTK_GMAC2_ID:
+		data = PSE_GDM2_PORT << TX_DMA_FPORT_SHIFT_V2;
+		break;
+	case MTK_GMAC3_ID:
+		data = PSE_GDM3_PORT << TX_DMA_FPORT_SHIFT_V2;
+		break;
+	}
+
 	data |= TX_DMA_SWC_V2 | QID_BITS_V2(info->qid);
 	WRITE_ONCE(desc->txd4, data);
 
@@ -4387,6 +4516,17 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 			  mac->phylink_config.supported_interfaces);
 	}
 
+	if (mtk_is_netsys_v3_or_greater(mac->hw) &&
+	    MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW_BIT) &&
+	    id == MTK_GMAC1_ID) {
+		mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE |
+						       MAC_SYM_PAUSE |
+						       MAC_10000FD;
+		phy_interface_zero(mac->phylink_config.supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  mac->phylink_config.supported_interfaces);
+	}
+
 	phylink = phylink_create(&mac->phylink_config,
 				 of_fwnode_handle(mac->of_node),
 				 phy_mode, &mtk_phylink_ops);
@@ -4913,6 +5053,24 @@ static const struct mtk_soc_data mt7986_data = {
 	},
 };
 
+static const struct mtk_soc_data mt7988_data = {
+	.reg_map = &mt7988_reg_map,
+	.ana_rgc3 = 0x128,
+	.caps = MT7988_CAPS,
+	.hw_features = MTK_HW_FEATURES,
+	.required_clks = MT7988_CLKS_BITMAP,
+	.required_pctl = false,
+	.version = 3,
+	.txrx = {
+		.txd_size = sizeof(struct mtk_tx_dma_v2),
+		.rxd_size = sizeof(struct mtk_rx_dma_v2),
+		.rx_irq_done_mask = MTK_RX_DONE_INT_V2,
+		.rx_dma_l4_valid = RX_DMA_L4_VALID_V2,
+		.dma_max_len = MTK_TX_DMA_BUF_LEN_V2,
+		.dma_len_offset = 8,
+	},
+};
+
 static const struct mtk_soc_data rt5350_data = {
 	.reg_map = &mt7628_reg_map,
 	.caps = MT7628_CAPS,
@@ -4931,14 +5089,15 @@ static const struct mtk_soc_data rt5350_data = {
 };
 
 const struct of_device_id of_mtk_match[] = {
-	{ .compatible = "mediatek,mt2701-eth", .data = &mt2701_data},
-	{ .compatible = "mediatek,mt7621-eth", .data = &mt7621_data},
-	{ .compatible = "mediatek,mt7622-eth", .data = &mt7622_data},
-	{ .compatible = "mediatek,mt7623-eth", .data = &mt7623_data},
-	{ .compatible = "mediatek,mt7629-eth", .data = &mt7629_data},
-	{ .compatible = "mediatek,mt7981-eth", .data = &mt7981_data},
-	{ .compatible = "mediatek,mt7986-eth", .data = &mt7986_data},
-	{ .compatible = "ralink,rt5350-eth", .data = &rt5350_data},
+	{ .compatible = "mediatek,mt2701-eth", .data = &mt2701_data },
+	{ .compatible = "mediatek,mt7621-eth", .data = &mt7621_data },
+	{ .compatible = "mediatek,mt7622-eth", .data = &mt7622_data },
+	{ .compatible = "mediatek,mt7623-eth", .data = &mt7623_data },
+	{ .compatible = "mediatek,mt7629-eth", .data = &mt7629_data },
+	{ .compatible = "mediatek,mt7981-eth", .data = &mt7981_data },
+	{ .compatible = "mediatek,mt7986-eth", .data = &mt7986_data },
+	{ .compatible = "mediatek,mt7988-eth", .data = &mt7988_data },
+	{ .compatible = "ralink,rt5350-eth", .data = &rt5350_data },
 	{},
 };
 MODULE_DEVICE_TABLE(of, of_mtk_match);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 5902944ddb4fa..80d17729e5578 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -117,7 +117,8 @@
 #define MTK_CDMP_EG_CTRL	0x404
 
 /* GDM Exgress Control Register */
-#define MTK_GDMA_FWD_CFG(x)	(0x500 + (x * 0x1000))
+#define MTK_GDMA_FWD_CFG(x)	({ typeof(x) _x = (x); (_x == MTK_GMAC3_ID) ?	\
+				   0x540 : 0x500 + (_x * 0x1000); })
 #define MTK_GDMA_SPECIAL_TAG	BIT(24)
 #define MTK_GDMA_ICS_EN		BIT(22)
 #define MTK_GDMA_TCS_EN		BIT(21)
@@ -126,6 +127,11 @@
 #define MTK_GDMA_TO_PDMA	0x0
 #define MTK_GDMA_DROP_ALL       0x7777
 
+/* GDM Egress Control Register */
+#define MTK_GDMA_EG_CTRL(x)	({ typeof(x) _x = (x); (_x == MTK_GMAC3_ID) ?	\
+				   0x544 : 0x504 + (_x * 0x1000); })
+#define MTK_GDMA_XGDM_SEL	BIT(31)
+
 /* Unicast Filter MAC Address Register - Low */
 #define MTK_GDMA_MAC_ADRL(x)	(0x508 + (x * 0x1000))
 
@@ -389,7 +395,26 @@
 #define PHY_IAC_TIMEOUT		HZ
 
 #define MTK_MAC_MISC		0x1000c
+#define MTK_MAC_MISC_V3		0x10010
 #define MTK_MUX_TO_ESW		BIT(0)
+#define MISC_MDC_TURBO		BIT(4)
+
+/* XMAC status registers */
+#define MTK_XGMAC_STS(x)	(((x) == MTK_GMAC3_ID) ? 0x1001C : 0x1000C)
+#define MTK_XGMAC_FORCE_LINK(x)	(((x) == MTK_GMAC2_ID) ? BIT(31) : BIT(15))
+#define MTK_USXGMII_PCS_LINK	BIT(8)
+#define MTK_XGMAC_RX_FC		BIT(5)
+#define MTK_XGMAC_TX_FC		BIT(4)
+#define MTK_USXGMII_PCS_MODE	GENMASK(3, 1)
+#define MTK_XGMAC_LINK_STS	BIT(0)
+
+/* GSW bridge registers */
+#define MTK_GSW_CFG		(0x10080)
+#define GSWTX_IPG_MASK		GENMASK(19, 16)
+#define GSWTX_IPG_SHIFT		16
+#define GSWRX_IPG_MASK		GENMASK(3, 0)
+#define GSWRX_IPG_SHIFT		0
+#define GSW_IPG_11		11
 
 /* Mac control registers */
 #define MTK_MAC_MCR(x)		(0x10100 + (x * 0x100))
@@ -647,6 +672,11 @@ enum mtk_clks_map {
 	MTK_CLK_GP0,
 	MTK_CLK_GP1,
 	MTK_CLK_GP2,
+	MTK_CLK_GP3,
+	MTK_CLK_XGP1,
+	MTK_CLK_XGP2,
+	MTK_CLK_XGP3,
+	MTK_CLK_CRYPTO,
 	MTK_CLK_FE,
 	MTK_CLK_TRGPLL,
 	MTK_CLK_SGMII_TX_250M,
@@ -663,6 +693,27 @@ enum mtk_clks_map {
 	MTK_CLK_WOCPU1,
 	MTK_CLK_NETSYS0,
 	MTK_CLK_NETSYS1,
+	MTK_CLK_ETHWARP_WOCPU2,
+	MTK_CLK_ETHWARP_WOCPU1,
+	MTK_CLK_ETHWARP_WOCPU0,
+	MTK_CLK_TOP_USXGMII_SBUS_0_SEL,
+	MTK_CLK_TOP_USXGMII_SBUS_1_SEL,
+	MTK_CLK_TOP_SGM_0_SEL,
+	MTK_CLK_TOP_SGM_1_SEL,
+	MTK_CLK_TOP_XFI_PHY_0_XTAL_SEL,
+	MTK_CLK_TOP_XFI_PHY_1_XTAL_SEL,
+	MTK_CLK_TOP_ETH_GMII_SEL,
+	MTK_CLK_TOP_ETH_REFCK_50M_SEL,
+	MTK_CLK_TOP_ETH_SYS_200M_SEL,
+	MTK_CLK_TOP_ETH_SYS_SEL,
+	MTK_CLK_TOP_ETH_XGMII_SEL,
+	MTK_CLK_TOP_ETH_MII_SEL,
+	MTK_CLK_TOP_NETSYS_SEL,
+	MTK_CLK_TOP_NETSYS_500M_SEL,
+	MTK_CLK_TOP_NETSYS_PAO_2X_SEL,
+	MTK_CLK_TOP_NETSYS_SYNC_250M_SEL,
+	MTK_CLK_TOP_NETSYS_PPEFB_250M_SEL,
+	MTK_CLK_TOP_NETSYS_WARP_SEL,
 	MTK_CLK_MAX
 };
 
@@ -716,6 +767,36 @@ enum mtk_clks_map {
 				 BIT_ULL(MTK_CLK_SGMII2_RX_250M) | \
 				 BIT_ULL(MTK_CLK_SGMII2_CDR_REF) | \
 				 BIT_ULL(MTK_CLK_SGMII2_CDR_FB))
+#define MT7988_CLKS_BITMAP	(BIT_ULL(MTK_CLK_FE) | BIT_ULL(MTK_CLK_ESW) | \
+				 BIT_ULL(MTK_CLK_GP1) | BIT_ULL(MTK_CLK_GP2) | \
+				 BIT_ULL(MTK_CLK_GP3) | BIT_ULL(MTK_CLK_XGP1) | \
+				 BIT_ULL(MTK_CLK_XGP2) | BIT_ULL(MTK_CLK_XGP3) | \
+				 BIT_ULL(MTK_CLK_CRYPTO) | \
+				 BIT_ULL(MTK_CLK_SGMII_TX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII_RX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII2_TX_250M) | \
+				 BIT_ULL(MTK_CLK_SGMII2_RX_250M) | \
+				 BIT_ULL(MTK_CLK_ETHWARP_WOCPU2) | \
+				 BIT_ULL(MTK_CLK_ETHWARP_WOCPU1) | \
+				 BIT_ULL(MTK_CLK_ETHWARP_WOCPU0) | \
+				 BIT_ULL(MTK_CLK_TOP_USXGMII_SBUS_0_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_USXGMII_SBUS_1_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_SGM_0_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_SGM_1_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_XFI_PHY_0_XTAL_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_XFI_PHY_1_XTAL_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_ETH_GMII_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_ETH_REFCK_50M_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_ETH_SYS_200M_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_ETH_SYS_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_ETH_XGMII_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_ETH_MII_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_NETSYS_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_NETSYS_500M_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_NETSYS_PAO_2X_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_NETSYS_SYNC_250M_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_NETSYS_PPEFB_250M_SEL) | \
+				 BIT_ULL(MTK_CLK_TOP_NETSYS_WARP_SEL))
 
 enum mtk_dev_state {
 	MTK_HW_INIT,
@@ -964,6 +1045,8 @@ enum mkt_eth_capabilities {
 		      MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \
 		      MTK_RSTCTRL_PPE1)
 
+#define MT7988_CAPS  (MTK_GDM1_ESW | MTK_QDMA | MTK_RSTCTRL_PPE1)
+
 struct mtk_tx_dma_desc_info {
 	dma_addr_t	addr;
 	u32		size;
@@ -1309,6 +1392,7 @@ void mtk_stats_update_mac(struct mtk_mac *mac);
 
 void mtk_w32(struct mtk_eth *eth, u32 val, unsigned reg);
 u32 mtk_r32(struct mtk_eth *eth, unsigned reg);
+u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned int reg);
 
 int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id);
 int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id);
-- 
GitLab


From bc758ade614576d1c1b167af0246ada8c916c804 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 25 Jul 2023 08:39:47 +0300
Subject: [PATCH 0504/1806] net/mlx4: clean up a type issue

These functions returns type bool, not pointers, so return false instead
of NULL.

Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/52d0814a-7287-4160-94b5-ac7939ac61c6@moroto.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/mcg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index f1716a83a4d33..24d0c7c46878f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -294,7 +294,7 @@ static bool check_duplicate_entry(struct mlx4_dev *dev, u8 port,
 	struct mlx4_promisc_qp *dqp, *tmp_dqp;
 
 	if (port < 1 || port > dev->caps.num_ports)
-		return NULL;
+		return false;
 
 	s_steer = &mlx4_priv(dev)->steer[port - 1];
 
@@ -375,7 +375,7 @@ static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 port,
 	bool ret = false;
 
 	if (port < 1 || port > dev->caps.num_ports)
-		return NULL;
+		return false;
 
 	s_steer = &mlx4_priv(dev)->steer[port - 1];
 
-- 
GitLab


From a927d77778e380ffd6ffea1f2037c6bdb23af99a Mon Sep 17 00:00:00 2001
From: Zhu Wang <wangzhu9@huawei.com>
Date: Wed, 26 Jul 2023 18:15:31 +0800
Subject: [PATCH 0505/1806] nf_conntrack: fix -Wunused-const-variable=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When building with W=1, the following warning occurs.

net/netfilter/nf_conntrack_proto_dccp.c:72:27: warning: ‘dccp_state_names’ defined but not used [-Wunused-const-variable=]
 static const char * const dccp_state_names[] = {

We include dccp_state_names in the macro
CONFIG_NF_CONNTRACK_PROCFS, since it is only used in the place
which is included in the macro CONFIG_NF_CONNTRACK_PROCFS.

Fixes: 2bc780499aa3 ("[NETFILTER]: nf_conntrack: add DCCP protocol support")
Signed-off-by: Zhu Wang <wangzhu9@huawei.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_conntrack_proto_dccp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index d4fd626d2b8c3..e2db1f4ec2df9 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -69,6 +69,7 @@
 
 #define DCCP_MSL (2 * 60 * HZ)
 
+#ifdef CONFIG_NF_CONNTRACK_PROCFS
 static const char * const dccp_state_names[] = {
 	[CT_DCCP_NONE]		= "NONE",
 	[CT_DCCP_REQUEST]	= "REQUEST",
@@ -81,6 +82,7 @@ static const char * const dccp_state_names[] = {
 	[CT_DCCP_IGNORE]	= "IGNORE",
 	[CT_DCCP_INVALID]	= "INVALID",
 };
+#endif
 
 #define sNO	CT_DCCP_NONE
 #define sRQ	CT_DCCP_REQUEST
-- 
GitLab


From 5fac9b7c16c50c6c7699517f582b56e3743f453a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Jul 2023 09:52:29 +0200
Subject: [PATCH 0506/1806] netlink: allow be16 and be32 types in all uint
 policy checks

__NLA_IS_BEINT_TYPE(tp) isn't useful.  NLA_BE16/32 are identical to
NLA_U16/32, the only difference is that it tells the netlink validation
functions that byteorder conversion might be needed before comparing
the value to the policy min/max ones.

After this change all policy macros that can be used with UINT types,
such as NLA_POLICY_MASK() can also be used with NLA_BE16/32.

This will be used to validate nf_tables flag attributes which
are in bigendian byte order.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netlink.h | 10 +++-------
 lib/nlattr.c          |  6 ++++++
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/include/net/netlink.h b/include/net/netlink.h
index b12cd957abb4b..8a7cd1170e1f7 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -375,12 +375,11 @@ struct nla_policy {
 #define NLA_POLICY_BITFIELD32(valid) \
 	{ .type = NLA_BITFIELD32, .bitfield32_valid = valid }
 
-#define __NLA_IS_UINT_TYPE(tp)						\
-	(tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || tp == NLA_U64)
+#define __NLA_IS_UINT_TYPE(tp)					\
+	(tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 ||	\
+	 tp == NLA_U64 || tp == NLA_BE16 || tp == NLA_BE32)
 #define __NLA_IS_SINT_TYPE(tp)						\
 	(tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64)
-#define __NLA_IS_BEINT_TYPE(tp)						\
-	(tp == NLA_BE16 || tp == NLA_BE32)
 
 #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition))
 #define NLA_ENSURE_UINT_TYPE(tp)			\
@@ -394,7 +393,6 @@ struct nla_policy {
 #define NLA_ENSURE_INT_OR_BINARY_TYPE(tp)		\
 	(__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) ||		\
 		      __NLA_IS_SINT_TYPE(tp) ||		\
-		      __NLA_IS_BEINT_TYPE(tp) ||	\
 		      tp == NLA_MSECS ||		\
 		      tp == NLA_BINARY) + tp)
 #define NLA_ENSURE_NO_VALIDATION_PTR(tp)		\
@@ -402,8 +400,6 @@ struct nla_policy {
 		      tp != NLA_REJECT &&		\
 		      tp != NLA_NESTED &&		\
 		      tp != NLA_NESTED_ARRAY) + tp)
-#define NLA_ENSURE_BEINT_TYPE(tp)			\
-	(__NLA_ENSURE(__NLA_IS_BEINT_TYPE(tp)) + tp)
 
 #define NLA_POLICY_RANGE(tp, _min, _max) {		\
 	.type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp),	\
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 489e15bde5c1d..7a2b6c38fd597 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -355,6 +355,12 @@ static int nla_validate_mask(const struct nla_policy *pt,
 	case NLA_U64:
 		value = nla_get_u64(nla);
 		break;
+	case NLA_BE16:
+		value = ntohs(nla_get_be16(nla));
+		break;
+	case NLA_BE32:
+		value = ntohl(nla_get_be32(nla));
+		break;
 	default:
 		return -EINVAL;
 	}
-- 
GitLab


From 100a11b69842ab568cff2a59959daf317be525c9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Jul 2023 09:52:30 +0200
Subject: [PATCH 0507/1806] netfilter: nf_tables: use NLA_POLICY_MASK to test
 for valid flag options

nf_tables relies on manual test of netlink attributes coming from userspace
even in cases where this could be handled via netlink policy.

Convert a bunch of 'flag' attributes to use NLA_POLICY_MASK checks.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_fib.c    | 13 +++++++------
 net/netfilter/nft_lookup.c |  6 ++----
 net/netfilter/nft_masq.c   |  8 +++-----
 net/netfilter/nft_nat.c    |  8 +++-----
 net/netfilter/nft_redir.c  |  8 +++-----
 5 files changed, 18 insertions(+), 25 deletions(-)

diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index 6e049fd48760b..601c9e09d07aa 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -14,17 +14,18 @@
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_fib.h>
 
+#define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \
+			NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF | \
+			NFTA_FIB_F_PRESENT)
+
 const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = {
 	[NFTA_FIB_DREG]		= { .type = NLA_U32 },
 	[NFTA_FIB_RESULT]	= { .type = NLA_U32 },
-	[NFTA_FIB_FLAGS]	= { .type = NLA_U32 },
+	[NFTA_FIB_FLAGS]	=
+		NLA_POLICY_MASK(NLA_BE32, NFTA_FIB_F_ALL),
 };
 EXPORT_SYMBOL(nft_fib_policy);
 
-#define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \
-			NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF | \
-			NFTA_FIB_F_PRESENT)
-
 int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		     const struct nft_data **data)
 {
@@ -77,7 +78,7 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 
 	priv->flags = ntohl(nla_get_be32(tb[NFTA_FIB_FLAGS]));
 
-	if (priv->flags == 0 || (priv->flags & ~NFTA_FIB_F_ALL))
+	if (priv->flags == 0)
 		return -EINVAL;
 
 	if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) ==
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 29ac48cdd6db7..870e5b113d13e 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -90,7 +90,8 @@ static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = {
 	[NFTA_LOOKUP_SET_ID]	= { .type = NLA_U32 },
 	[NFTA_LOOKUP_SREG]	= { .type = NLA_U32 },
 	[NFTA_LOOKUP_DREG]	= { .type = NLA_U32 },
-	[NFTA_LOOKUP_FLAGS]	= { .type = NLA_U32 },
+	[NFTA_LOOKUP_FLAGS]	=
+		NLA_POLICY_MASK(NLA_BE32, NFT_LOOKUP_F_INV),
 };
 
 static int nft_lookup_init(const struct nft_ctx *ctx,
@@ -120,9 +121,6 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_LOOKUP_FLAGS]) {
 		flags = ntohl(nla_get_be32(tb[NFTA_LOOKUP_FLAGS]));
 
-		if (flags & ~NFT_LOOKUP_F_INV)
-			return -EINVAL;
-
 		if (flags & NFT_LOOKUP_F_INV)
 			priv->invert = true;
 	}
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index b115d77fbbc7c..8a14aaca93bbd 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -20,7 +20,8 @@ struct nft_masq {
 };
 
 static const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = {
-	[NFTA_MASQ_FLAGS]		= { .type = NLA_U32 },
+	[NFTA_MASQ_FLAGS]		=
+		NLA_POLICY_MASK(NLA_BE32, NF_NAT_RANGE_MASK),
 	[NFTA_MASQ_REG_PROTO_MIN]	= { .type = NLA_U32 },
 	[NFTA_MASQ_REG_PROTO_MAX]	= { .type = NLA_U32 },
 };
@@ -47,11 +48,8 @@ static int nft_masq_init(const struct nft_ctx *ctx,
 	struct nft_masq *priv = nft_expr_priv(expr);
 	int err;
 
-	if (tb[NFTA_MASQ_FLAGS]) {
+	if (tb[NFTA_MASQ_FLAGS])
 		priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS]));
-		if (priv->flags & ~NF_NAT_RANGE_MASK)
-			return -EINVAL;
-	}
 
 	if (tb[NFTA_MASQ_REG_PROTO_MIN]) {
 		err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MIN],
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 5c29915ab0289..583885ce72328 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -132,7 +132,8 @@ static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
 	[NFTA_NAT_REG_ADDR_MAX]	 = { .type = NLA_U32 },
 	[NFTA_NAT_REG_PROTO_MIN] = { .type = NLA_U32 },
 	[NFTA_NAT_REG_PROTO_MAX] = { .type = NLA_U32 },
-	[NFTA_NAT_FLAGS]	 = { .type = NLA_U32 },
+	[NFTA_NAT_FLAGS]	 =
+		NLA_POLICY_MASK(NLA_BE32, NF_NAT_RANGE_MASK),
 };
 
 static int nft_nat_validate(const struct nft_ctx *ctx,
@@ -246,11 +247,8 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		priv->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
-	if (tb[NFTA_NAT_FLAGS]) {
+	if (tb[NFTA_NAT_FLAGS])
 		priv->flags |= ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS]));
-		if (priv->flags & ~NF_NAT_RANGE_MASK)
-			return -EOPNOTSUPP;
-	}
 
 	return nf_ct_netns_get(ctx->net, family);
 }
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index a70196ffcb1e6..a58bd8d291ff2 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -22,7 +22,8 @@ struct nft_redir {
 static const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = {
 	[NFTA_REDIR_REG_PROTO_MIN]	= { .type = NLA_U32 },
 	[NFTA_REDIR_REG_PROTO_MAX]	= { .type = NLA_U32 },
-	[NFTA_REDIR_FLAGS]		= { .type = NLA_U32 },
+	[NFTA_REDIR_FLAGS]		=
+		NLA_POLICY_MASK(NLA_BE32, NF_NAT_RANGE_MASK),
 };
 
 static int nft_redir_validate(const struct nft_ctx *ctx,
@@ -68,11 +69,8 @@ static int nft_redir_init(const struct nft_ctx *ctx,
 		priv->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
-	if (tb[NFTA_REDIR_FLAGS]) {
+	if (tb[NFTA_REDIR_FLAGS])
 		priv->flags = ntohl(nla_get_be32(tb[NFTA_REDIR_FLAGS]));
-		if (priv->flags & ~NF_NAT_RANGE_MASK)
-			return -EINVAL;
-	}
 
 	return nf_ct_netns_get(ctx->net, ctx->family);
 }
-- 
GitLab


From 0c805e80e35d042a41c8702fa13f453a504d2ede Mon Sep 17 00:00:00 2001
From: Lin Ma <linma@zju.edu.cn>
Date: Wed, 12 Jul 2023 21:32:36 +0800
Subject: [PATCH 0508/1806] netfilter: conntrack: validate cta_ip via parsing

In current ctnetlink_parse_tuple_ip() function, nested parsing and
validation is splitting as two parts,  which could be cleanup to a
simplified form. As the nla_parse_nested_deprecated function
supports validation in the fly. These two finially reach same place
__nla_validate_parse with same validate flag.

nla_parse_nested_deprecated
  __nla_parse(.., NL_VALIDATE_LIBERAL, ..)
    __nla_validate_parse

nla_validate_nested_deprecated
  __nla_validate_nested(.., NL_VALIDATE_LIBERAL, ..)
    __nla_validate
      __nla_validate_parse

This commit removes the call to nla_validate_nested_deprecated and pass
cta_ip_nla_policy when do parsing.

Signed-off-by: Lin Ma <linma@zju.edu.cn>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_conntrack_netlink.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 69c8c8c7e9b8e..334db22199c1d 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1321,15 +1321,11 @@ static int ctnetlink_parse_tuple_ip(struct nlattr *attr,
 	struct nlattr *tb[CTA_IP_MAX+1];
 	int ret = 0;
 
-	ret = nla_parse_nested_deprecated(tb, CTA_IP_MAX, attr, NULL, NULL);
+	ret = nla_parse_nested_deprecated(tb, CTA_IP_MAX, attr,
+					  cta_ip_nla_policy, NULL);
 	if (ret < 0)
 		return ret;
 
-	ret = nla_validate_nested_deprecated(attr, CTA_IP_MAX,
-					     cta_ip_nla_policy, NULL);
-	if (ret)
-		return ret;
-
 	switch (tuple->src.l3num) {
 	case NFPROTO_IPV4:
 		ret = ipv4_nlattr_to_tuple(tb, tuple, flags);
-- 
GitLab


From 86e9c9aa2358a74bcc5e63f9fc69c2d01e64c002 Mon Sep 17 00:00:00 2001
From: Jeremy Sowden <jeremy@azazel.net>
Date: Tue, 20 Jun 2023 19:11:00 +0100
Subject: [PATCH 0509/1806] lib/ts_bm: add helper to reduce indentation and
 improve readability

The flow-control of `bm_find` is very deeply nested with a conditional
comparing a ternary expression against the pattern inside a for-loop
inside a while-loop inside a for-loop.

Move the inner for-loop into a helper function to reduce the amount of
indentation and make the code easier to read.

Fix indentation and trailing white-space in preceding debug logging
statement.

Signed-off-by: Jeremy Sowden <jeremy@azazel.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 lib/ts_bm.c | 43 ++++++++++++++++++++++++++++++-------------
 1 file changed, 30 insertions(+), 13 deletions(-)

diff --git a/lib/ts_bm.c b/lib/ts_bm.c
index c8ecbf74ef295..e5f30f9177df9 100644
--- a/lib/ts_bm.c
+++ b/lib/ts_bm.c
@@ -55,6 +55,24 @@ struct ts_bm
 	unsigned int	good_shift[];
 };
 
+static unsigned int matchpat(const u8 *pattern, unsigned int patlen,
+			     const u8 *text, bool icase)
+{
+	unsigned int i;
+
+	for (i = 0; i < patlen; i++) {
+		u8 t = *(text-i);
+
+		if (icase)
+			t = toupper(t);
+
+		if (t != *(pattern-i))
+			break;
+	}
+
+	return i;
+}
+
 static unsigned int bm_find(struct ts_config *conf, struct ts_state *state)
 {
 	struct ts_bm *bm = ts_config_priv(conf);
@@ -72,19 +90,18 @@ static unsigned int bm_find(struct ts_config *conf, struct ts_state *state)
 			break;
 
 		while (shift < text_len) {
-			DEBUGP("Searching in position %d (%c)\n", 
-				shift, text[shift]);
-			for (i = 0; i < bm->patlen; i++) 
-				if ((icase ? toupper(text[shift-i])
-				    : text[shift-i])
-					!= bm->pattern[bm->patlen-1-i])
-				     goto next;
-
-			/* London calling... */
-			DEBUGP("found!\n");
-			return consumed + (shift-(bm->patlen-1));
-
-next:			bs = bm->bad_shift[text[shift-i]];
+			DEBUGP("Searching in position %d (%c)\n",
+			       shift, text[shift]);
+
+			i = matchpat(&bm->pattern[bm->patlen-1], bm->patlen,
+				     &text[shift], icase);
+			if (i == bm->patlen) {
+				/* London calling... */
+				DEBUGP("found!\n");
+				return consumed + (shift-(bm->patlen-1));
+			}
+
+			bs = bm->bad_shift[text[shift-i]];
 
 			/* Now jumping to... */
 			shift = max_t(int, shift-i+bs, shift+bm->good_shift[i]);
-- 
GitLab


From 051e77e33946f932e6879bf4df2773e3c998c3a7 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Date: Tue, 25 Jul 2023 20:29:09 +0300
Subject: [PATCH 0510/1806] virtio/vsock: rework MSG_PEEK for SOCK_STREAM

This reworks current implementation of MSG_PEEK logic:
1) Replaces 'skb_queue_walk_safe()' with 'skb_queue_walk()'. There is
   no need in the first one, as there are no removes of skb in loop.
2) Removes nested while loop - MSG_PEEK logic could be implemented
   without it: just iterate over skbs without removing it and copy
   data from each until destination buffer is not full.

Signed-off-by: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Reviewed-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/vmw_vsock/virtio_transport_common.c | 41 ++++++++++++-------------
 1 file changed, 19 insertions(+), 22 deletions(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index b769fc2589315..2ee40574c3398 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -348,37 +348,34 @@ virtio_transport_stream_do_peek(struct vsock_sock *vsk,
 				size_t len)
 {
 	struct virtio_vsock_sock *vvs = vsk->trans;
-	size_t bytes, total = 0, off;
-	struct sk_buff *skb, *tmp;
-	int err = -EFAULT;
+	struct sk_buff *skb;
+	size_t total = 0;
+	int err;
 
 	spin_lock_bh(&vvs->rx_lock);
 
-	skb_queue_walk_safe(&vvs->rx_queue, skb,  tmp) {
-		off = 0;
+	skb_queue_walk(&vvs->rx_queue, skb) {
+		size_t bytes;
 
-		if (total == len)
-			break;
+		bytes = len - total;
+		if (bytes > skb->len)
+			bytes = skb->len;
 
-		while (total < len && off < skb->len) {
-			bytes = len - total;
-			if (bytes > skb->len - off)
-				bytes = skb->len - off;
+		spin_unlock_bh(&vvs->rx_lock);
 
-			/* sk_lock is held by caller so no one else can dequeue.
-			 * Unlock rx_lock since memcpy_to_msg() may sleep.
-			 */
-			spin_unlock_bh(&vvs->rx_lock);
+		/* sk_lock is held by caller so no one else can dequeue.
+		 * Unlock rx_lock since memcpy_to_msg() may sleep.
+		 */
+		err = memcpy_to_msg(msg, skb->data, bytes);
+		if (err)
+			goto out;
 
-			err = memcpy_to_msg(msg, skb->data + off, bytes);
-			if (err)
-				goto out;
+		total += bytes;
 
-			spin_lock_bh(&vvs->rx_lock);
+		spin_lock_bh(&vvs->rx_lock);
 
-			total += bytes;
-			off += bytes;
-		}
+		if (total == len)
+			break;
 	}
 
 	spin_unlock_bh(&vvs->rx_lock);
-- 
GitLab


From a75f501de88e58db24dc8822505f924cd1085ac6 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Date: Tue, 25 Jul 2023 20:29:10 +0300
Subject: [PATCH 0511/1806] virtio/vsock: support MSG_PEEK for SOCK_SEQPACKET

This adds support of MSG_PEEK flag for SOCK_SEQPACKET type of socket.
Difference with SOCK_STREAM is that this callback returns either length
of the message or error.

Signed-off-by: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/vmw_vsock/virtio_transport_common.c | 63 +++++++++++++++++++++++--
 1 file changed, 60 insertions(+), 3 deletions(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 2ee40574c3398..352d042b130b5 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -460,6 +460,63 @@ out:
 	return err;
 }
 
+static ssize_t
+virtio_transport_seqpacket_do_peek(struct vsock_sock *vsk,
+				   struct msghdr *msg)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	struct sk_buff *skb;
+	size_t total, len;
+
+	spin_lock_bh(&vvs->rx_lock);
+
+	if (!vvs->msg_count) {
+		spin_unlock_bh(&vvs->rx_lock);
+		return 0;
+	}
+
+	total = 0;
+	len = msg_data_left(msg);
+
+	skb_queue_walk(&vvs->rx_queue, skb) {
+		struct virtio_vsock_hdr *hdr;
+
+		if (total < len) {
+			size_t bytes;
+			int err;
+
+			bytes = len - total;
+			if (bytes > skb->len)
+				bytes = skb->len;
+
+			spin_unlock_bh(&vvs->rx_lock);
+
+			/* sk_lock is held by caller so no one else can dequeue.
+			 * Unlock rx_lock since memcpy_to_msg() may sleep.
+			 */
+			err = memcpy_to_msg(msg, skb->data, bytes);
+			if (err)
+				return err;
+
+			spin_lock_bh(&vvs->rx_lock);
+		}
+
+		total += skb->len;
+		hdr = virtio_vsock_hdr(skb);
+
+		if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) {
+			if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOR)
+				msg->msg_flags |= MSG_EOR;
+
+			break;
+		}
+	}
+
+	spin_unlock_bh(&vvs->rx_lock);
+
+	return total;
+}
+
 static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk,
 						 struct msghdr *msg,
 						 int flags)
@@ -554,9 +611,9 @@ virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
 				   int flags)
 {
 	if (flags & MSG_PEEK)
-		return -EOPNOTSUPP;
-
-	return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags);
+		return virtio_transport_seqpacket_do_peek(vsk, msg);
+	else
+		return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue);
 
-- 
GitLab


From 587ed79f62a7569cbe386bbe6102800992f73001 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Date: Tue, 25 Jul 2023 20:29:11 +0300
Subject: [PATCH 0512/1806] vsock/test: rework MSG_PEEK test for SOCK_STREAM

This new version makes test more complicated by adding empty read,
partial read and data comparisons between MSG_PEEK and normal reads.

Signed-off-by: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/vsock/vsock_test.c | 78 ++++++++++++++++++++++++++++++--
 1 file changed, 75 insertions(+), 3 deletions(-)

diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index ac1bd3ac1533a..444a3ff0681f2 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -255,9 +255,14 @@ static void test_stream_multiconn_server(const struct test_opts *opts)
 		close(fds[i]);
 }
 
+#define MSG_PEEK_BUF_LEN 64
+
 static void test_stream_msg_peek_client(const struct test_opts *opts)
 {
+	unsigned char buf[MSG_PEEK_BUF_LEN];
+	ssize_t send_size;
 	int fd;
+	int i;
 
 	fd = vsock_stream_connect(opts->peer_cid, 1234);
 	if (fd < 0) {
@@ -265,12 +270,32 @@ static void test_stream_msg_peek_client(const struct test_opts *opts)
 		exit(EXIT_FAILURE);
 	}
 
-	send_byte(fd, 1, 0);
+	for (i = 0; i < sizeof(buf); i++)
+		buf[i] = rand() & 0xFF;
+
+	control_expectln("SRVREADY");
+
+	send_size = send(fd, buf, sizeof(buf), 0);
+
+	if (send_size < 0) {
+		perror("send");
+		exit(EXIT_FAILURE);
+	}
+
+	if (send_size != sizeof(buf)) {
+		fprintf(stderr, "Invalid send size %zi\n", send_size);
+		exit(EXIT_FAILURE);
+	}
+
 	close(fd);
 }
 
 static void test_stream_msg_peek_server(const struct test_opts *opts)
 {
+	unsigned char buf_half[MSG_PEEK_BUF_LEN / 2];
+	unsigned char buf_normal[MSG_PEEK_BUF_LEN];
+	unsigned char buf_peek[MSG_PEEK_BUF_LEN];
+	ssize_t res;
 	int fd;
 
 	fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
@@ -279,8 +304,55 @@ static void test_stream_msg_peek_server(const struct test_opts *opts)
 		exit(EXIT_FAILURE);
 	}
 
-	recv_byte(fd, 1, MSG_PEEK);
-	recv_byte(fd, 1, 0);
+	/* Peek from empty socket. */
+	res = recv(fd, buf_peek, sizeof(buf_peek), MSG_PEEK | MSG_DONTWAIT);
+	if (res != -1) {
+		fprintf(stderr, "expected recv(2) failure, got %zi\n", res);
+		exit(EXIT_FAILURE);
+	}
+
+	if (errno != EAGAIN) {
+		perror("EAGAIN expected");
+		exit(EXIT_FAILURE);
+	}
+
+	control_writeln("SRVREADY");
+
+	/* Peek part of data. */
+	res = recv(fd, buf_half, sizeof(buf_half), MSG_PEEK);
+	if (res != sizeof(buf_half)) {
+		fprintf(stderr, "recv(2) + MSG_PEEK, expected %zu, got %zi\n",
+			sizeof(buf_half), res);
+		exit(EXIT_FAILURE);
+	}
+
+	/* Peek whole data. */
+	res = recv(fd, buf_peek, sizeof(buf_peek), MSG_PEEK);
+	if (res != sizeof(buf_peek)) {
+		fprintf(stderr, "recv(2) + MSG_PEEK, expected %zu, got %zi\n",
+			sizeof(buf_peek), res);
+		exit(EXIT_FAILURE);
+	}
+
+	/* Compare partial and full peek. */
+	if (memcmp(buf_half, buf_peek, sizeof(buf_half))) {
+		fprintf(stderr, "Partial peek data mismatch\n");
+		exit(EXIT_FAILURE);
+	}
+
+	res = recv(fd, buf_normal, sizeof(buf_normal), 0);
+	if (res != sizeof(buf_normal)) {
+		fprintf(stderr, "recv(2), expected %zu, got %zi\n",
+			sizeof(buf_normal), res);
+		exit(EXIT_FAILURE);
+	}
+
+	/* Compare full peek and normal read. */
+	if (memcmp(buf_peek, buf_normal, sizeof(buf_peek))) {
+		fprintf(stderr, "Full peek data mismatch\n");
+		exit(EXIT_FAILURE);
+	}
+
 	close(fd);
 }
 
-- 
GitLab


From 8a0697f23e5a6e03a31f9dfb96755521aa9b9fc1 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Date: Tue, 25 Jul 2023 20:29:12 +0300
Subject: [PATCH 0513/1806] vsock/test: MSG_PEEK test for SOCK_SEQPACKET

This adds MSG_PEEK test for SOCK_SEQPACKET. It works in the same way as
SOCK_STREAM test, except it also tests MSG_TRUNC flag.

Signed-off-by: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/vsock/vsock_test.c | 58 +++++++++++++++++++++++++++++---
 1 file changed, 54 insertions(+), 4 deletions(-)

diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 444a3ff0681f2..90718c2fd4ea9 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -257,14 +257,19 @@ static void test_stream_multiconn_server(const struct test_opts *opts)
 
 #define MSG_PEEK_BUF_LEN 64
 
-static void test_stream_msg_peek_client(const struct test_opts *opts)
+static void test_msg_peek_client(const struct test_opts *opts,
+				 bool seqpacket)
 {
 	unsigned char buf[MSG_PEEK_BUF_LEN];
 	ssize_t send_size;
 	int fd;
 	int i;
 
-	fd = vsock_stream_connect(opts->peer_cid, 1234);
+	if (seqpacket)
+		fd = vsock_seqpacket_connect(opts->peer_cid, 1234);
+	else
+		fd = vsock_stream_connect(opts->peer_cid, 1234);
+
 	if (fd < 0) {
 		perror("connect");
 		exit(EXIT_FAILURE);
@@ -290,7 +295,8 @@ static void test_stream_msg_peek_client(const struct test_opts *opts)
 	close(fd);
 }
 
-static void test_stream_msg_peek_server(const struct test_opts *opts)
+static void test_msg_peek_server(const struct test_opts *opts,
+				 bool seqpacket)
 {
 	unsigned char buf_half[MSG_PEEK_BUF_LEN / 2];
 	unsigned char buf_normal[MSG_PEEK_BUF_LEN];
@@ -298,7 +304,11 @@ static void test_stream_msg_peek_server(const struct test_opts *opts)
 	ssize_t res;
 	int fd;
 
-	fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
+	if (seqpacket)
+		fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL);
+	else
+		fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
+
 	if (fd < 0) {
 		perror("accept");
 		exit(EXIT_FAILURE);
@@ -340,6 +350,21 @@ static void test_stream_msg_peek_server(const struct test_opts *opts)
 		exit(EXIT_FAILURE);
 	}
 
+	if (seqpacket) {
+		/* This type of socket supports MSG_TRUNC flag,
+		 * so check it with MSG_PEEK. We must get length
+		 * of the message.
+		 */
+		res = recv(fd, buf_half, sizeof(buf_half), MSG_PEEK |
+			   MSG_TRUNC);
+		if (res != sizeof(buf_peek)) {
+			fprintf(stderr,
+				"recv(2) + MSG_PEEK | MSG_TRUNC, exp %zu, got %zi\n",
+				sizeof(buf_half), res);
+			exit(EXIT_FAILURE);
+		}
+	}
+
 	res = recv(fd, buf_normal, sizeof(buf_normal), 0);
 	if (res != sizeof(buf_normal)) {
 		fprintf(stderr, "recv(2), expected %zu, got %zi\n",
@@ -356,6 +381,16 @@ static void test_stream_msg_peek_server(const struct test_opts *opts)
 	close(fd);
 }
 
+static void test_stream_msg_peek_client(const struct test_opts *opts)
+{
+	return test_msg_peek_client(opts, false);
+}
+
+static void test_stream_msg_peek_server(const struct test_opts *opts)
+{
+	return test_msg_peek_server(opts, false);
+}
+
 #define SOCK_BUF_SIZE (2 * 1024 * 1024)
 #define MAX_MSG_SIZE (32 * 1024)
 
@@ -1125,6 +1160,16 @@ static void test_stream_virtio_skb_merge_server(const struct test_opts *opts)
 	close(fd);
 }
 
+static void test_seqpacket_msg_peek_client(const struct test_opts *opts)
+{
+	return test_msg_peek_client(opts, true);
+}
+
+static void test_seqpacket_msg_peek_server(const struct test_opts *opts)
+{
+	return test_msg_peek_server(opts, true);
+}
+
 static struct test_case test_cases[] = {
 	{
 		.name = "SOCK_STREAM connection reset",
@@ -1200,6 +1245,11 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_virtio_skb_merge_client,
 		.run_server = test_stream_virtio_skb_merge_server,
 	},
+	{
+		.name = "SOCK_SEQPACKET MSG_PEEK",
+		.run_client = test_seqpacket_msg_peek_client,
+		.run_server = test_seqpacket_msg_peek_server,
+	},
 	{},
 };
 
-- 
GitLab


From 1ad8237e971630c66a1a6194491e0837b64d00e0 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 21 Jun 2023 12:36:55 +0300
Subject: [PATCH 0514/1806] wifi: wil6210: fix fortify warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When compiling with gcc 13.1 and CONFIG_FORTIFY_SOURCE=y,
I've noticed the following:

In function ‘fortify_memcpy_chk’,
    inlined from ‘wil_rx_crypto_check_edma’ at drivers/net/wireless/ath/wil6210/txrx_edma.c:566:2:
./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Wattribute-warning]
  529 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

where the compiler complains on:

const u8 *pn;
...
pn = (u8 *)&st->ext.pn_15_0;
...
memcpy(cc->pn, pn, IEEE80211_GCMP_PN_LEN);

and:

In function ‘fortify_memcpy_chk’,
    inlined from ‘wil_rx_crypto_check’ at drivers/net/wireless/ath/wil6210/txrx.c:684:2:
./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Wattribute-warning]
  529 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

where the compiler complains on:

const u8 *pn = (u8 *)&d->mac.pn_15_0;
...
memcpy(cc->pn, pn, IEEE80211_GCMP_PN_LEN);

In both cases, the fortification logic interprets 'memcpy()' as 6-byte
overread of 2-byte field 'pn_15_0' of 'struct wil_rx_status_extension'
and 'pn_15_0' of 'struct vring_rx_mac', respectively. To silence
these warnings, last two fields of the aforementioned structures
are grouped using 'struct_group_attr(pn, __packed' quirk.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230621093711.80118-1-dmantipov@yandex.ru
---
 drivers/net/wireless/ath/wil6210/txrx.c      | 2 +-
 drivers/net/wireless/ath/wil6210/txrx.h      | 6 ++++--
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 2 +-
 drivers/net/wireless/ath/wil6210/txrx_edma.h | 6 ++++--
 4 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 237cbd5c5060b..f29ac6de71399 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -666,7 +666,7 @@ static int wil_rx_crypto_check(struct wil6210_priv *wil, struct sk_buff *skb)
 	struct wil_tid_crypto_rx *c = mc ? &s->group_crypto_rx :
 				      &s->tid_crypto_rx[tid];
 	struct wil_tid_crypto_rx_single *cc = &c->key_id[key_id];
-	const u8 *pn = (u8 *)&d->mac.pn_15_0;
+	const u8 *pn = (u8 *)&d->mac.pn;
 
 	if (!cc->key_set) {
 		wil_err_ratelimited(wil,
diff --git a/drivers/net/wireless/ath/wil6210/txrx.h b/drivers/net/wireless/ath/wil6210/txrx.h
index 1ae1bec1b97f1..689f68d89a440 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.h
+++ b/drivers/net/wireless/ath/wil6210/txrx.h
@@ -343,8 +343,10 @@ struct vring_rx_mac {
 	u32 d0;
 	u32 d1;
 	u16 w4;
-	u16 pn_15_0;
-	u32 pn_47_16;
+	struct_group_attr(pn, __packed,
+		u16 pn_15_0;
+		u32 pn_47_16;
+	);
 } __packed;
 
 /* Rx descriptor - DMA part
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index 201c8c35e0c9e..1ba1f21ebea26 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -548,7 +548,7 @@ static int wil_rx_crypto_check_edma(struct wil6210_priv *wil,
 	s = &wil->sta[cid];
 	c = mc ? &s->group_crypto_rx : &s->tid_crypto_rx[tid];
 	cc = &c->key_id[key_id];
-	pn = (u8 *)&st->ext.pn_15_0;
+	pn = (u8 *)&st->ext.pn;
 
 	if (!cc->key_set) {
 		wil_err_ratelimited(wil,
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.h b/drivers/net/wireless/ath/wil6210/txrx_edma.h
index c736f7413a35f..ee90e225bb050 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.h
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.h
@@ -330,8 +330,10 @@ struct wil_rx_status_extension {
 	u32 d0;
 	u32 d1;
 	__le16 seq_num; /* only lower 12 bits */
-	u16 pn_15_0;
-	u32 pn_47_16;
+	struct_group_attr(pn, __packed,
+		u16 pn_15_0;
+		u32 pn_47_16;
+	);
 } __packed;
 
 struct wil_rx_status_extended {
-- 
GitLab


From f3fbda3396f39c9849ea31c19c9b188905b1691d Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 20 Jun 2023 15:18:45 -0700
Subject: [PATCH 0515/1806] ice: Correctly initialize queue context values

The ice_alloc_lan_q_ctx function allocates the queue context array for a
given traffic class. This function uses devm_kcalloc which will
zero-allocate the structure. Thus, prior to any queue being setup by
ice_ena_vsi_txq, the q_ctx structure will have a q_handle of 0 and a q_teid
of 0. These are potentially valid values.

Modify the ice_alloc_lan_q_ctx function to initialize every member of the
q_ctx array to have invalid values. Modify ice_dis_vsi_txq to ensure that
it assigns q_teid to an invalid value when it assigns q_handle to the
invalid value as well.

This will allow other code to check whether the queue context is currently
valid before operating on it.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c |  1 +
 drivers/net/ethernet/intel/ice/ice_sched.c  | 23 ++++++++++++++++-----
 2 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index e16d4c83ed5f9..8ff3d6d847976 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -4700,6 +4700,7 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues,
 			break;
 		ice_free_sched_node(pi, node);
 		q_ctx->q_handle = ICE_INVAL_Q_HANDLE;
+		q_ctx->q_teid = ICE_INVAL_TEID;
 	}
 	mutex_unlock(&pi->sched_lock);
 	kfree(qg_list);
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index b664d60fd037e..79a8972873f12 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -569,18 +569,24 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs)
 {
 	struct ice_vsi_ctx *vsi_ctx;
 	struct ice_q_ctx *q_ctx;
+	u16 idx;
 
 	vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle);
 	if (!vsi_ctx)
 		return -EINVAL;
 	/* allocate LAN queue contexts */
 	if (!vsi_ctx->lan_q_ctx[tc]) {
-		vsi_ctx->lan_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw),
-						      new_numqs,
-						      sizeof(*q_ctx),
-						      GFP_KERNEL);
-		if (!vsi_ctx->lan_q_ctx[tc])
+		q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs,
+				     sizeof(*q_ctx), GFP_KERNEL);
+		if (!q_ctx)
 			return -ENOMEM;
+
+		for (idx = 0; idx < new_numqs; idx++) {
+			q_ctx[idx].q_handle = ICE_INVAL_Q_HANDLE;
+			q_ctx[idx].q_teid = ICE_INVAL_TEID;
+		}
+
+		vsi_ctx->lan_q_ctx[tc] = q_ctx;
 		vsi_ctx->num_lan_q_entries[tc] = new_numqs;
 		return 0;
 	}
@@ -592,9 +598,16 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs)
 				     sizeof(*q_ctx), GFP_KERNEL);
 		if (!q_ctx)
 			return -ENOMEM;
+
 		memcpy(q_ctx, vsi_ctx->lan_q_ctx[tc],
 		       prev_num * sizeof(*q_ctx));
 		devm_kfree(ice_hw_to_dev(hw), vsi_ctx->lan_q_ctx[tc]);
+
+		for (idx = prev_num; idx < new_numqs; idx++) {
+			q_ctx[idx].q_handle = ICE_INVAL_Q_HANDLE;
+			q_ctx[idx].q_teid = ICE_INVAL_TEID;
+		}
+
 		vsi_ctx->lan_q_ctx[tc] = q_ctx;
 		vsi_ctx->num_lan_q_entries[tc] = new_numqs;
 	}
-- 
GitLab


From bb52f42acef6ac317ee298d39909ce17bbaddb82 Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 20 Jun 2023 15:18:46 -0700
Subject: [PATCH 0516/1806] ice: Add driver support for firmware changes for
 LAG

Add the defines, fields, and detection code for FW support of LAG for
SRIOV.  Also exposes some previously static functions to allow access
in the lag code.

Clean up code that is unused or not needed for LAG support.  Also add
an ordered workqueue for processing LAG events.

Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h          |  5 ++
 .../net/ethernet/intel/ice/ice_adminq_cmd.h   |  3 ++
 drivers/net/ethernet/intel/ice/ice_common.c   |  8 +++
 drivers/net/ethernet/intel/ice/ice_lag.c      | 53 ++++++++++---------
 drivers/net/ethernet/intel/ice/ice_lib.c      |  2 +-
 drivers/net/ethernet/intel/ice/ice_lib.h      |  1 +
 drivers/net/ethernet/intel/ice/ice_main.c     | 22 ++++++--
 drivers/net/ethernet/intel/ice/ice_type.h     |  2 +
 8 files changed, 66 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 9109006336f0d..5ac0ad12f9f17 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -200,6 +200,8 @@ enum ice_feature {
 	ICE_F_PTP_EXTTS,
 	ICE_F_SMA_CTRL,
 	ICE_F_GNSS,
+	ICE_F_ROCE_LAG,
+	ICE_F_SRIOV_LAG,
 	ICE_F_MAX
 };
 
@@ -569,6 +571,7 @@ struct ice_pf {
 	struct mutex sw_mutex;		/* lock for protecting VSI alloc flow */
 	struct mutex tc_mutex;		/* lock to protect TC changes */
 	struct mutex adev_mutex;	/* lock to protect aux device access */
+	struct mutex lag_mutex;		/* protect ice_lag struct in PF */
 	u32 msg_enable;
 	struct ice_ptp ptp;
 	struct gnss_serial *gnss_serial;
@@ -639,6 +642,8 @@ struct ice_pf {
 	struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES];
 };
 
+extern struct workqueue_struct *ice_lag_wq;
+
 struct ice_netdev_priv {
 	struct ice_vsi *vsi;
 	struct ice_repr *repr;
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 63d3e1dcbba55..1d4227b024d31 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -120,6 +120,9 @@ struct ice_aqc_list_caps_elem {
 #define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE		0x0076
 #define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT		0x0077
 #define ICE_AQC_CAPS_NVM_MGMT				0x0080
+#define ICE_AQC_CAPS_FW_LAG_SUPPORT			0x0092
+#define ICE_AQC_BIT_ROCEV2_LAG				0x01
+#define ICE_AQC_BIT_SRIOV_LAG				0x02
 
 	u8 major_ver;
 	u8 minor_ver;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 8ff3d6d847976..3853ef22429f1 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -2241,6 +2241,14 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 			  "%s: reset_restrict_support = %d\n", prefix,
 			  caps->reset_restrict_support);
 		break;
+	case ICE_AQC_CAPS_FW_LAG_SUPPORT:
+		caps->roce_lag = !!(number & ICE_AQC_BIT_ROCEV2_LAG);
+		ice_debug(hw, ICE_DBG_INIT, "%s: roce_lag = %u\n",
+			  prefix, caps->roce_lag);
+		caps->sriov_lag = !!(number & ICE_AQC_BIT_SRIOV_LAG);
+		ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n",
+			  prefix, caps->sriov_lag);
+		break;
 	default:
 		/* Not one of the recognized common capabilities */
 		found = false;
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 5a7753bda3245..d018e68f5a6d9 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -4,8 +4,12 @@
 /* Link Aggregation code */
 
 #include "ice.h"
+#include "ice_lib.h"
 #include "ice_lag.h"
 
+#define ICE_LAG_RES_SHARED	BIT(14)
+#define ICE_LAG_RES_VALID	BIT(15)
+
 /**
  * ice_lag_set_primary - set PF LAG state as Primary
  * @lag: LAG info struct
@@ -225,6 +229,26 @@ static void ice_lag_unregister(struct ice_lag *lag, struct net_device *netdev)
 	lag->role = ICE_LAG_NONE;
 }
 
+/**
+ * ice_lag_init_feature_support_flag - Check for NVM support for LAG
+ * @pf: PF struct
+ */
+static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
+{
+	struct ice_hw_common_caps *caps;
+
+	caps = &pf->hw.dev_caps.common_cap;
+	if (caps->roce_lag)
+		ice_set_feature_support(pf, ICE_F_ROCE_LAG);
+	else
+		ice_clear_feature_support(pf, ICE_F_ROCE_LAG);
+
+	if (caps->sriov_lag)
+		ice_set_feature_support(pf, ICE_F_SRIOV_LAG);
+	else
+		ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
+}
+
 /**
  * ice_lag_changeupper_event - handle LAG changeupper event
  * @lag: LAG info struct
@@ -264,26 +288,6 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 	ice_display_lag_info(lag);
 }
 
-/**
- * ice_lag_changelower_event - handle LAG changelower event
- * @lag: LAG info struct
- * @ptr: opaque data pointer
- *
- * ptr to be cast to netdev_notifier_changelowerstate_info
- */
-static void ice_lag_changelower_event(struct ice_lag *lag, void *ptr)
-{
-	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
-
-	if (netdev != lag->netdev)
-		return;
-
-	netdev_dbg(netdev, "bonding info\n");
-
-	if (!netif_is_lag_port(netdev))
-		netdev_dbg(netdev, "CHANGELOWER rcvd, but netdev not in LAG. Bail\n");
-}
-
 /**
  * ice_lag_event_handler - handle LAG events from netdev
  * @notif_blk: notifier block registered by this netdev
@@ -310,9 +314,6 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event,
 	case NETDEV_CHANGEUPPER:
 		ice_lag_changeupper_event(lag, ptr);
 		break;
-	case NETDEV_CHANGELOWERSTATE:
-		ice_lag_changelower_event(lag, ptr);
-		break;
 	case NETDEV_BONDING_INFO:
 		ice_lag_info_event(lag, ptr);
 		break;
@@ -379,6 +380,8 @@ int ice_init_lag(struct ice_pf *pf)
 	struct ice_vsi *vsi;
 	int err;
 
+	ice_lag_init_feature_support_flag(pf);
+
 	pf->lag = kzalloc(sizeof(*lag), GFP_KERNEL);
 	if (!pf->lag)
 		return -ENOMEM;
@@ -435,9 +438,7 @@ void ice_deinit_lag(struct ice_pf *pf)
 	if (lag->pf)
 		ice_unregister_lag_handler(lag);
 
-	dev_put(lag->upper_netdev);
-
-	dev_put(lag->peer_netdev);
+	flush_workqueue(ice_lag_wq);
 
 	kfree(lag);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index a43c23c80565b..077f2e91ae1a1 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -3970,7 +3970,7 @@ bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f)
  * @pf: pointer to the struct ice_pf instance
  * @f: feature enum to set
  */
-static void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f)
+void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f)
 {
 	if (f < 0 || f >= ICE_F_MAX)
 		return;
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 1628385a96726..dd53fe968ad86 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -163,6 +163,7 @@ int ice_vsi_del_vlan_zero(struct ice_vsi *vsi);
 bool ice_vsi_has_non_zero_vlans(struct ice_vsi *vsi);
 u16 ice_vsi_num_non_zero_vlans(struct ice_vsi *vsi);
 bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f);
+void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f);
 void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f);
 void ice_init_feature_support(struct ice_pf *pf);
 bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 9b36cce306b89..7f7728dadcbbf 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -64,6 +64,7 @@ struct device *ice_hw_to_dev(struct ice_hw *hw)
 }
 
 static struct workqueue_struct *ice_wq;
+struct workqueue_struct *ice_lag_wq;
 static const struct net_device_ops ice_netdev_safe_mode_ops;
 static const struct net_device_ops ice_netdev_ops;
 
@@ -3795,6 +3796,7 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf)
 static void ice_deinit_pf(struct ice_pf *pf)
 {
 	ice_service_task_stop(pf);
+	mutex_destroy(&pf->lag_mutex);
 	mutex_destroy(&pf->adev_mutex);
 	mutex_destroy(&pf->sw_mutex);
 	mutex_destroy(&pf->tc_mutex);
@@ -3875,6 +3877,7 @@ static int ice_init_pf(struct ice_pf *pf)
 	mutex_init(&pf->sw_mutex);
 	mutex_init(&pf->tc_mutex);
 	mutex_init(&pf->adev_mutex);
+	mutex_init(&pf->lag_mutex);
 
 	INIT_HLIST_HEAD(&pf->aq_wait_list);
 	spin_lock_init(&pf->aq_wait_lock);
@@ -5571,7 +5574,7 @@ static struct pci_driver ice_driver = {
  */
 static int __init ice_module_init(void)
 {
-	int status;
+	int status = -ENOMEM;
 
 	pr_info("%s\n", ice_driver_string);
 	pr_info("%s\n", ice_copyright);
@@ -5579,15 +5582,27 @@ static int __init ice_module_init(void)
 	ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME);
 	if (!ice_wq) {
 		pr_err("Failed to create workqueue\n");
-		return -ENOMEM;
+		return status;
+	}
+
+	ice_lag_wq = alloc_ordered_workqueue("ice_lag_wq", 0);
+	if (!ice_lag_wq) {
+		pr_err("Failed to create LAG workqueue\n");
+		goto err_dest_wq;
 	}
 
 	status = pci_register_driver(&ice_driver);
 	if (status) {
 		pr_err("failed to register PCI driver, err %d\n", status);
-		destroy_workqueue(ice_wq);
+		goto err_dest_lag_wq;
 	}
 
+	return 0;
+
+err_dest_lag_wq:
+	destroy_workqueue(ice_lag_wq);
+err_dest_wq:
+	destroy_workqueue(ice_wq);
 	return status;
 }
 module_init(ice_module_init);
@@ -5602,6 +5617,7 @@ static void __exit ice_module_exit(void)
 {
 	pci_unregister_driver(&ice_driver);
 	destroy_workqueue(ice_wq);
+	destroy_workqueue(ice_lag_wq);
 	pr_info("module unloaded\n");
 }
 module_exit(ice_module_exit);
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index df9171a1a34f0..e82f38c2a9402 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -277,6 +277,8 @@ struct ice_hw_common_caps {
 	u8 dcb;
 	u8 ieee_1588;
 	u8 rdma;
+	u8 roce_lag;
+	u8 sriov_lag;
 
 	bool nvm_update_pending_nvm;
 	bool nvm_update_pending_orom;
-- 
GitLab


From 23ccae5ce15f33001f34ed1b9e2ac312bb5e8615 Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 20 Jun 2023 15:18:47 -0700
Subject: [PATCH 0517/1806] ice: changes to the interface with the HW and FW
 for SRIOV_VF+LAG

Add defines needed for interaction with the FW admin queue interface
in relation to supporting LAG and SRIOV VFs interacting.

Add code, or make non-static previously static functions, to access
the new and changed admin queue calls for LAG.

Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_adminq_cmd.h   | 50 +++++++++++-
 drivers/net/ethernet/intel/ice/ice_common.c   | 47 +++++++++++
 drivers/net/ethernet/intel/ice/ice_common.h   |  4 +
 drivers/net/ethernet/intel/ice/ice_sched.c    | 14 ++--
 drivers/net/ethernet/intel/ice/ice_sched.h    | 21 +++++
 drivers/net/ethernet/intel/ice/ice_switch.c   | 78 ++++++++++++++-----
 drivers/net/ethernet/intel/ice/ice_switch.h   | 26 +++++++
 7 files changed, 211 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 1d4227b024d31..c0ad34b425312 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -235,6 +235,8 @@ struct ice_aqc_set_port_params {
 #define ICE_AQC_SET_P_PARAMS_DOUBLE_VLAN_ENA	BIT(2)
 	__le16 bad_frame_vsi;
 	__le16 swid;
+#define ICE_AQC_PORT_SWID_VALID			BIT(15)
+#define ICE_AQC_PORT_SWID_M			0xFF
 	u8 reserved[10];
 };
 
@@ -244,10 +246,12 @@ struct ice_aqc_set_port_params {
  * Allocate Resources command (indirect 0x0208)
  * Free Resources command (indirect 0x0209)
  * Get Allocated Resource Descriptors Command (indirect 0x020A)
+ * Share Resource command (indirect 0x020B)
  */
 #define ICE_AQC_RES_TYPE_VSI_LIST_REP			0x03
 #define ICE_AQC_RES_TYPE_VSI_LIST_PRUNE			0x04
 #define ICE_AQC_RES_TYPE_RECIPE				0x05
+#define ICE_AQC_RES_TYPE_SWID				0x07
 #define ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK		0x21
 #define ICE_AQC_RES_TYPE_FDIR_GUARANTEED_ENTRIES	0x22
 #define ICE_AQC_RES_TYPE_FDIR_SHARED_ENTRIES		0x23
@@ -267,6 +271,7 @@ struct ice_aqc_set_port_params {
 
 /* Allocate Resources command (indirect 0x0208)
  * Free Resources command (indirect 0x0209)
+ * Share Resource command (indirect 0x020B)
  */
 struct ice_aqc_alloc_free_res_cmd {
 	__le16 num_entries; /* Number of Resource entries */
@@ -821,7 +826,11 @@ struct ice_aqc_txsched_move_grp_info_hdr {
 	__le32 src_parent_teid;
 	__le32 dest_parent_teid;
 	__le16 num_elems;
-	__le16 reserved;
+	u8 mode;
+#define ICE_AQC_MOVE_ELEM_MODE_SAME_PF		0x0
+#define ICE_AQC_MOVE_ELEM_MODE_GIVE_OWN		0x1
+#define ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN		0x2
+	u8 reserved;
 };
 
 struct ice_aqc_move_elem {
@@ -1926,6 +1935,42 @@ struct ice_aqc_dis_txq_item {
 	__le16 q_id[];
 } __packed;
 
+/* Move/Reconfigure Tx queue (indirect 0x0C32) */
+struct ice_aqc_cfg_txqs {
+	u8 cmd_type;
+#define ICE_AQC_Q_CFG_MOVE_NODE		0x1
+#define ICE_AQC_Q_CFG_TC_CHNG		0x2
+#define ICE_AQC_Q_CFG_MOVE_TC_CHNG	0x3
+#define ICE_AQC_Q_CFG_SUBSEQ_CALL	BIT(2)
+#define ICE_AQC_Q_CFG_FLUSH		BIT(3)
+	u8 num_qs;
+	u8 port_num_chng;
+#define ICE_AQC_Q_CFG_SRC_PRT_M		0x7
+#define ICE_AQC_Q_CFG_DST_PRT_S		3
+#define ICE_AQC_Q_CFG_DST_PRT_M		(0x7 << ICE_AQC_Q_CFG_DST_PRT_S)
+	u8 time_out;
+#define ICE_AQC_Q_CFG_TIMEOUT_S		2
+#define ICE_AQC_Q_CFG_TIMEOUT_M		(0x1F << ICE_AQC_Q_CFG_TIMEOUT_S)
+	__le32 blocked_cgds;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Per Q struct for Move/Reconfigure Tx LAN Queues (indirect 0x0C32) */
+struct ice_aqc_cfg_txq_perq {
+	__le16 q_handle;
+	u8 tc;
+	u8 rsvd;
+	__le32 q_teid;
+};
+
+/* The buffer for Move/Reconfigure Tx LAN Queues (indirect 0x0C32) */
+struct ice_aqc_cfg_txqs_buf {
+	__le32 src_parent_teid;
+	__le32 dst_parent_teid;
+	struct ice_aqc_cfg_txq_perq queue_info[];
+};
+
 /* Add Tx RDMA Queue Set (indirect 0x0C33) */
 struct ice_aqc_add_rdma_qset {
 	u8 num_qset_grps;
@@ -2184,6 +2229,7 @@ struct ice_aq_desc {
 		struct ice_aqc_neigh_dev_req neigh_dev;
 		struct ice_aqc_add_txqs add_txqs;
 		struct ice_aqc_dis_txqs dis_txqs;
+		struct ice_aqc_cfg_txqs cfg_txqs;
 		struct ice_aqc_add_rdma_qset add_rdma_qset;
 		struct ice_aqc_add_get_update_free_vsi vsi_cmd;
 		struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res;
@@ -2266,6 +2312,7 @@ enum ice_adminq_opc {
 	/* Alloc/Free/Get Resources */
 	ice_aqc_opc_alloc_res				= 0x0208,
 	ice_aqc_opc_free_res				= 0x0209,
+	ice_aqc_opc_share_res				= 0x020B,
 	ice_aqc_opc_set_vlan_mode_parameters		= 0x020C,
 	ice_aqc_opc_get_vlan_mode_parameters		= 0x020D,
 
@@ -2359,6 +2406,7 @@ enum ice_adminq_opc {
 	/* Tx queue handling commands/events */
 	ice_aqc_opc_add_txqs				= 0x0C30,
 	ice_aqc_opc_dis_txqs				= 0x0C31,
+	ice_aqc_opc_cfg_txqs				= 0x0C32,
 	ice_aqc_opc_add_rdma_qset			= 0x0C33,
 
 	/* package commands */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 3853ef22429f1..dade0a50299c3 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -4229,6 +4229,53 @@ do_aq:
 	return status;
 }
 
+/**
+ * ice_aq_cfg_lan_txq
+ * @hw: pointer to the hardware structure
+ * @buf: buffer for command
+ * @buf_size: size of buffer in bytes
+ * @num_qs: number of queues being configured
+ * @oldport: origination lport
+ * @newport: destination lport
+ * @cd: pointer to command details structure or NULL
+ *
+ * Move/Configure LAN Tx queue (0x0C32)
+ *
+ * There is a better AQ command to use for moving nodes, so only coding
+ * this one for configuring the node.
+ */
+int
+ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf,
+		   u16 buf_size, u16 num_qs, u8 oldport, u8 newport,
+		   struct ice_sq_cd *cd)
+{
+	struct ice_aqc_cfg_txqs *cmd;
+	struct ice_aq_desc desc;
+	int status;
+
+	cmd = &desc.params.cfg_txqs;
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_cfg_txqs);
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	if (!buf)
+		return -EINVAL;
+
+	cmd->cmd_type = ICE_AQC_Q_CFG_TC_CHNG;
+	cmd->num_qs = num_qs;
+	cmd->port_num_chng = (oldport & ICE_AQC_Q_CFG_SRC_PRT_M);
+	cmd->port_num_chng |= (newport << ICE_AQC_Q_CFG_DST_PRT_S) &
+			      ICE_AQC_Q_CFG_DST_PRT_M;
+	cmd->time_out = (5 << ICE_AQC_Q_CFG_TIMEOUT_S) &
+			ICE_AQC_Q_CFG_TIMEOUT_M;
+	cmd->blocked_cgds = 0;
+
+	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+	if (status)
+		ice_debug(hw, ICE_DBG_SCHED, "Failed to reconfigure nodes %d\n",
+			  hw->adminq.sq_last_status);
+	return status;
+}
+
 /**
  * ice_aq_add_rdma_qsets
  * @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 81961a7d65985..df12a9d8d28ca 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -186,6 +186,10 @@ int
 ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle,
 		u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
 		struct ice_sq_cd *cd);
+int
+ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf,
+		   u16 buf_size, u16 num_qs, u8 oldport, u8 newport,
+		   struct ice_sq_cd *cd);
 int ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle);
 void ice_replay_post(struct ice_hw *hw);
 void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf);
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 79a8972873f12..f4677704b95e2 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -447,7 +447,7 @@ ice_aq_cfg_sched_elems(struct ice_hw *hw, u16 elems_req,
  *
  * Move scheduling elements (0x0408)
  */
-static int
+int
 ice_aq_move_sched_elems(struct ice_hw *hw, u16 grps_req,
 			struct ice_aqc_move_elem *buf, u16 buf_size,
 			u16 *grps_movd, struct ice_sq_cd *cd)
@@ -526,7 +526,7 @@ ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size,
  *
  * This function suspends or resumes HW nodes
  */
-static int
+int
 ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids,
 			       bool suspend)
 {
@@ -1057,7 +1057,7 @@ ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi,
  *
  * This function add nodes to a given layer.
  */
-static int
+int
 ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
 			     struct ice_sched_node *tc_node,
 			     struct ice_sched_node *parent, u8 layer,
@@ -1132,7 +1132,7 @@ static u8 ice_sched_get_qgrp_layer(struct ice_hw *hw)
  *
  * This function returns the current VSI layer number
  */
-static u8 ice_sched_get_vsi_layer(struct ice_hw *hw)
+u8 ice_sched_get_vsi_layer(struct ice_hw *hw)
 {
 	/* Num Layers       VSI layer
 	 *     9               6
@@ -1155,7 +1155,7 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw)
  *
  * This function returns the current aggregator layer number
  */
-static u8 ice_sched_get_agg_layer(struct ice_hw *hw)
+u8 ice_sched_get_agg_layer(struct ice_hw *hw)
 {
 	/* Num Layers       aggregator layer
 	 *     9               4
@@ -1590,7 +1590,7 @@ ice_sched_get_vsi_node(struct ice_port_info *pi, struct ice_sched_node *tc_node,
  * This function retrieves an aggregator node for a given aggregator ID from
  * a given TC branch
  */
-static struct ice_sched_node *
+struct ice_sched_node *
 ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node,
 		       u32 agg_id)
 {
@@ -2152,7 +2152,7 @@ ice_get_agg_info(struct ice_hw *hw, u32 agg_id)
  * This function walks through the aggregator subtree to find a free parent
  * node
  */
-static struct ice_sched_node *
+struct ice_sched_node *
 ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node,
 			      u16 *num_nodes)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index 9c100747445aa..8bd26353d76a5 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -146,8 +146,29 @@ ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id,
 				 enum ice_agg_type agg_type, u8 tc,
 				 enum ice_rl_type rl_type, u32 bw);
 int ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes);
+int
+ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids,
+			       bool suspend);
+struct ice_sched_node *
+ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node,
+		       u32 agg_id);
+u8 ice_sched_get_agg_layer(struct ice_hw *hw);
+u8 ice_sched_get_vsi_layer(struct ice_hw *hw);
+struct ice_sched_node *
+ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node,
+			      u16 *num_nodes);
+int
+ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
+			     struct ice_sched_node *tc_node,
+			     struct ice_sched_node *parent, u8 layer,
+			     u16 num_nodes, u32 *first_node_teid,
+			     u16 *num_nodes_added);
 void ice_sched_replay_agg_vsi_preinit(struct ice_hw *hw);
 void ice_sched_replay_agg(struct ice_hw *hw);
+int
+ice_aq_move_sched_elems(struct ice_hw *hw, u16 grps_req,
+			struct ice_aqc_move_elem *buf, u16 buf_size,
+			u16 *grps_movd, struct ice_sq_cd *cd);
 int ice_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle);
 int ice_sched_replay_q_bw(struct ice_port_info *pi, struct ice_q_ctx *q_ctx);
 #endif /* _ICE_SCHED_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 813fef5fd7482..8c332d24c7c58 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -20,10 +20,10 @@
  * byte 0 = 0x2: to identify it as locally administered DA MAC
  * byte 6 = 0x2: to identify it as locally administered SA MAC
  * byte 12 = 0x81 & byte 13 = 0x00:
- *	In case of VLAN filter first two bytes defines ether type (0x8100)
- *	and remaining two bytes are placeholder for programming a given VLAN ID
- *	In case of Ether type filter it is treated as header without VLAN tag
- *	and byte 12 and 13 is used to program a given Ether type instead
+ *      In case of VLAN filter first two bytes defines ether type (0x8100)
+ *      and remaining two bytes are placeholder for programming a given VLAN ID
+ *      In case of Ether type filter it is treated as header without VLAN tag
+ *      and byte 12 and 13 is used to program a given Ether type instead
  */
 #define DUMMY_ETH_HDR_LEN		16
 static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0,
@@ -1369,14 +1369,6 @@ static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = {
 	ICE_PKT_PROFILE(tcp, 0),
 };
 
-#define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l)	struct_size((s), hdr_data, (l))
-#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s)	\
-	ICE_SW_RULE_RX_TX_HDR_SIZE((s), DUMMY_ETH_HDR_LEN)
-#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s)	\
-	ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0)
-#define ICE_SW_RULE_LG_ACT_SIZE(s, n)		struct_size((s), act, (n))
-#define ICE_SW_RULE_VSI_LIST_SIZE(s, n)		struct_size((s), vsi, (n))
-
 /* this is a recipe to profile association bitmap */
 static DECLARE_BITMAP(recipe_to_profile[ICE_MAX_NUM_RECIPES],
 			  ICE_MAX_NUM_PROFILES);
@@ -1841,8 +1833,13 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id,
 	    lkup_type == ICE_SW_LKUP_DFLT) {
 		sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_REP);
 	} else if (lkup_type == ICE_SW_LKUP_VLAN) {
-		sw_buf->res_type =
-			cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE);
+		if (opc == ice_aqc_opc_alloc_res)
+			sw_buf->res_type =
+				cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE |
+					    ICE_AQC_RES_TYPE_FLAG_SHARED);
+		else
+			sw_buf->res_type =
+				cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE);
 	} else {
 		status = -EINVAL;
 		goto ice_aq_alloc_free_vsi_list_exit;
@@ -1910,7 +1907,7 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz,
  *
  * Add(0x0290)
  */
-static int
+int
 ice_aq_add_recipe(struct ice_hw *hw,
 		  struct ice_aqc_recipe_data_elem *s_recipe_list,
 		  u16 num_recipes, struct ice_sq_cd *cd)
@@ -1947,7 +1944,7 @@ ice_aq_add_recipe(struct ice_hw *hw,
  * The caller must supply enough space in s_recipe_list to hold all possible
  * recipes and *num_recipes must equal ICE_MAX_NUM_RECIPES.
  */
-static int
+int
 ice_aq_get_recipe(struct ice_hw *hw,
 		  struct ice_aqc_recipe_data_elem *s_recipe_list,
 		  u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd)
@@ -2040,7 +2037,7 @@ error_out:
  * @cd: pointer to command details structure or NULL
  * Recipe to profile association (0x0291)
  */
-static int
+int
 ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
 			     struct ice_sq_cd *cd)
 {
@@ -2066,7 +2063,7 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
  * @cd: pointer to command details structure or NULL
  * Associate profile ID with given recipe (0x0293)
  */
-static int
+int
 ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
 			     struct ice_sq_cd *cd)
 {
@@ -2090,7 +2087,7 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
  * @hw: pointer to the hardware structure
  * @rid: recipe ID returned as response to AQ call
  */
-static int ice_alloc_recipe(struct ice_hw *hw, u16 *rid)
+int ice_alloc_recipe(struct ice_hw *hw, u16 *rid)
 {
 	struct ice_aqc_alloc_free_res_elem *sw_buf;
 	u16 buf_len;
@@ -3122,7 +3119,7 @@ ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info)
  * handle element. This can be extended further to search VSI list with more
  * than 1 vsi_count. Returns pointer to VSI list entry if found.
  */
-static struct ice_vsi_list_map_info *
+struct ice_vsi_list_map_info *
 ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle,
 			u16 *vsi_list_id)
 {
@@ -3133,7 +3130,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle,
 
 	list_head = &sw->recp_list[recp_id].filt_rules;
 	list_for_each_entry(list_itr, list_head, list_entry) {
-		if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) {
+		if (list_itr->vsi_list_info) {
 			map_info = list_itr->vsi_list_info;
 			if (test_bit(vsi_handle, map_info->vsi_map)) {
 				*vsi_list_id = map_info->vsi_list_id;
@@ -4544,6 +4541,45 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
 	.offs		= {__VA_ARGS__},	\
 }
 
+/**
+ * ice_share_res - set a resource as shared or dedicated
+ * @hw: hw struct of original owner of resource
+ * @type: resource type
+ * @shared: is the resource being set to shared
+ * @res_id: resource id (descriptor)
+ */
+int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id)
+{
+	struct ice_aqc_alloc_free_res_elem *buf;
+	u16 buf_len;
+	int status;
+
+	buf_len = struct_size(buf, elem, 1);
+	buf = kzalloc(buf_len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	buf->num_elems = cpu_to_le16(1);
+	if (shared)
+		buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) &
+					     ICE_AQC_RES_TYPE_M) |
+					    ICE_AQC_RES_TYPE_FLAG_SHARED);
+	else
+		buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) &
+					     ICE_AQC_RES_TYPE_M) &
+					    ~ICE_AQC_RES_TYPE_FLAG_SHARED);
+
+	buf->elem[0].e.sw_resp = cpu_to_le16(res_id);
+	status = ice_aq_alloc_free_res(hw, 1, buf, buf_len,
+				       ice_aqc_opc_share_res, NULL);
+	if (status)
+		ice_debug(hw, ICE_DBG_SW, "Could not set resource type %u id %u to %s\n",
+			  type, res_id, shared ? "SHARED" : "DEDICATED");
+
+	kfree(buf);
+	return status;
+}
+
 /* This is mapping table entry that maps every word within a given protocol
  * structure to the real byte offset as per the specification of that
  * protocol header.
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index 10f5a0ae199e8..51cd14952cd1f 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -22,6 +22,14 @@
 #define ICE_PROFID_IPV6_GTPU_TEID			46
 #define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER		70
 
+#define ICE_SW_RULE_VSI_LIST_SIZE(s, n)		struct_size((s), vsi, (n))
+#define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l)	struct_size((s), hdr_data, (l))
+#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s)	\
+	ICE_SW_RULE_RX_TX_HDR_SIZE((s), DUMMY_ETH_HDR_LEN)
+#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s)	\
+	ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0)
+#define ICE_SW_RULE_LG_ACT_SIZE(s, n)		struct_size((s), act, (n))
+
 /* VSI context structure for add/get/update/free operations */
 struct ice_vsi_ctx {
 	u16 vsi_num;
@@ -345,6 +353,7 @@ ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
 int
 ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
 		  u16 counter_id);
+int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id);
 
 /* Switch/bridge related commands */
 void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup);
@@ -401,4 +410,21 @@ int
 ice_update_recipe_lkup_idx(struct ice_hw *hw,
 			   struct ice_update_recipe_lkup_idx_params *params);
 void ice_change_proto_id_to_dvm(void);
+struct ice_vsi_list_map_info *
+ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle,
+			u16 *vsi_list_id);
+int ice_alloc_recipe(struct ice_hw *hw, u16 *rid);
+int ice_aq_get_recipe(struct ice_hw *hw,
+		      struct ice_aqc_recipe_data_elem *s_recipe_list,
+		      u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd);
+int ice_aq_add_recipe(struct ice_hw *hw,
+		      struct ice_aqc_recipe_data_elem *s_recipe_list,
+		      u16 num_recipes, struct ice_sq_cd *cd);
+int
+ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
+			     struct ice_sq_cd *cd);
+int
+ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
+			     struct ice_sq_cd *cd);
+
 #endif /* _ICE_SWITCH_H_ */
-- 
GitLab


From 41ccedf5ca8fcd9fc97f977887625c035d9b15df Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 20 Jun 2023 15:18:48 -0700
Subject: [PATCH 0518/1806] ice: implement lag netdev event handler

The event handler for LAG will create a work item to place on the ordered
workqueue to be processed.

Add in defines for training packets and new recipes to be used by the
switching block of the HW for LAG packet steering.

Update the ice_lag struct to reflect the new processing methodology.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lag.c | 124 ++++++++++++++++++++---
 drivers/net/ethernet/intel/ice/ice_lag.h |  30 +++++-
 2 files changed, 140 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index d018e68f5a6d9..5725772cf8f48 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -56,11 +56,10 @@ static void ice_lag_set_backup(struct ice_lag *lag)
  */
 static void ice_display_lag_info(struct ice_lag *lag)
 {
-	const char *name, *peer, *upper, *role, *bonded, *primary;
+	const char *name, *upper, *role, *bonded, *primary;
 	struct device *dev = &lag->pf->pdev->dev;
 
 	name = lag->netdev ? netdev_name(lag->netdev) : "unset";
-	peer = lag->peer_netdev ? netdev_name(lag->peer_netdev) : "unset";
 	upper = lag->upper_netdev ? netdev_name(lag->upper_netdev) : "unset";
 	primary = lag->primary ? "TRUE" : "FALSE";
 	bonded = lag->bonded ? "BONDED" : "UNBONDED";
@@ -82,8 +81,8 @@ static void ice_display_lag_info(struct ice_lag *lag)
 		role = "ERROR";
 	}
 
-	dev_dbg(dev, "%s %s, peer:%s, upper:%s, role:%s, primary:%s\n", name,
-		bonded, peer, upper, role, primary);
+	dev_dbg(dev, "%s %s, upper:%s, role:%s, primary:%s\n", name, bonded,
+		upper, role, primary);
 }
 
 /**
@@ -198,7 +197,6 @@ ice_lag_unlink(struct ice_lag *lag,
 		lag->upper_netdev = NULL;
 	}
 
-	lag->peer_netdev = NULL;
 	ice_set_rdma_cap(pf);
 	lag->bonded = false;
 	lag->role = ICE_LAG_NONE;
@@ -288,6 +286,59 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 	ice_display_lag_info(lag);
 }
 
+/**
+ * ice_lag_process_event - process a task assigned to the lag_wq
+ * @work: pointer to work_struct
+ */
+static void ice_lag_process_event(struct work_struct *work)
+{
+	struct netdev_notifier_changeupper_info *info;
+	struct ice_lag_work *lag_work;
+	struct net_device *netdev;
+	struct list_head *tmp, *n;
+	struct ice_pf *pf;
+
+	lag_work = container_of(work, struct ice_lag_work, lag_task);
+	pf = lag_work->lag->pf;
+
+	mutex_lock(&pf->lag_mutex);
+	lag_work->lag->netdev_head = &lag_work->netdev_list.node;
+
+	switch (lag_work->event) {
+	case NETDEV_CHANGEUPPER:
+		info = &lag_work->info.changeupper_info;
+		ice_lag_changeupper_event(lag_work->lag, info);
+		break;
+	case NETDEV_BONDING_INFO:
+		ice_lag_info_event(lag_work->lag, &lag_work->info.bonding_info);
+		break;
+	case NETDEV_UNREGISTER:
+		if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) {
+			netdev = lag_work->info.bonding_info.info.dev;
+			if ((netdev == lag_work->lag->netdev ||
+			     lag_work->lag->primary) && lag_work->lag->bonded)
+				ice_lag_unregister(lag_work->lag, netdev);
+		}
+		break;
+	default:
+		break;
+	}
+
+	/* cleanup resources allocated for this work item */
+	list_for_each_safe(tmp, n, &lag_work->netdev_list.node) {
+		struct ice_lag_netdev_list *entry;
+
+		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	lag_work->lag->netdev_head = NULL;
+
+	mutex_unlock(&pf->lag_mutex);
+
+	kfree(lag_work);
+}
+
 /**
  * ice_lag_event_handler - handle LAG events from netdev
  * @notif_blk: notifier block registered by this netdev
@@ -299,31 +350,79 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event,
 		      void *ptr)
 {
 	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct net_device *upper_netdev;
+	struct ice_lag_work *lag_work;
 	struct ice_lag *lag;
 
-	lag = container_of(notif_blk, struct ice_lag, notif_block);
+	if (!netif_is_ice(netdev))
+		return NOTIFY_DONE;
+
+	if (event != NETDEV_CHANGEUPPER && event != NETDEV_BONDING_INFO &&
+	    event != NETDEV_UNREGISTER)
+		return NOTIFY_DONE;
 
+	if (!(netdev->priv_flags & IFF_BONDING))
+		return NOTIFY_DONE;
+
+	lag = container_of(notif_blk, struct ice_lag, notif_block);
 	if (!lag->netdev)
 		return NOTIFY_DONE;
 
-	/* Check that the netdev is in the working namespace */
 	if (!net_eq(dev_net(netdev), &init_net))
 		return NOTIFY_DONE;
 
+	/* This memory will be freed at the end of ice_lag_process_event */
+	lag_work = kzalloc(sizeof(*lag_work), GFP_KERNEL);
+	if (!lag_work)
+		return -ENOMEM;
+
+	lag_work->event_netdev = netdev;
+	lag_work->lag = lag;
+	lag_work->event = event;
+	if (event == NETDEV_CHANGEUPPER) {
+		struct netdev_notifier_changeupper_info *info;
+
+		info = ptr;
+		upper_netdev = info->upper_dev;
+	} else {
+		upper_netdev = netdev_master_upper_dev_get(netdev);
+	}
+
+	INIT_LIST_HEAD(&lag_work->netdev_list.node);
+	if (upper_netdev) {
+		struct ice_lag_netdev_list *nd_list;
+		struct net_device *tmp_nd;
+
+		rcu_read_lock();
+		for_each_netdev_in_bond_rcu(upper_netdev, tmp_nd) {
+			nd_list = kzalloc(sizeof(*nd_list), GFP_KERNEL);
+			if (!nd_list)
+				break;
+
+			nd_list->netdev = tmp_nd;
+			list_add(&nd_list->node, &lag_work->netdev_list.node);
+		}
+		rcu_read_unlock();
+	}
+
 	switch (event) {
 	case NETDEV_CHANGEUPPER:
-		ice_lag_changeupper_event(lag, ptr);
+		lag_work->info.changeupper_info =
+			*((struct netdev_notifier_changeupper_info *)ptr);
 		break;
 	case NETDEV_BONDING_INFO:
-		ice_lag_info_event(lag, ptr);
-		break;
-	case NETDEV_UNREGISTER:
-		ice_lag_unregister(lag, netdev);
+		lag_work->info.bonding_info =
+			*((struct netdev_notifier_bonding_info *)ptr);
 		break;
 	default:
+		lag_work->info.notifier_info =
+			*((struct netdev_notifier_info *)ptr);
 		break;
 	}
 
+	INIT_WORK(&lag_work->lag_task, ice_lag_process_event);
+	queue_work(ice_lag_wq, &lag_work->lag_task);
+
 	return NOTIFY_DONE;
 }
 
@@ -398,7 +497,6 @@ int ice_init_lag(struct ice_pf *pf)
 	lag->netdev = vsi->netdev;
 	lag->role = ICE_LAG_NONE;
 	lag->bonded = false;
-	lag->peer_netdev = NULL;
 	lag->upper_netdev = NULL;
 	lag->notif_block.notifier_call = NULL;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index 2c373676c42f2..a4314a46c82c4 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -14,20 +14,48 @@ enum ice_lag_role {
 	ICE_LAG_UNSET
 };
 
+#define ICE_LAG_INVALID_PORT 0xFF
+
 struct ice_pf;
+struct ice_vf;
+
+struct ice_lag_netdev_list {
+	struct list_head node;
+	struct net_device *netdev;
+};
 
 /* LAG info struct */
 struct ice_lag {
 	struct ice_pf *pf; /* backlink to PF struct */
 	struct net_device *netdev; /* this PF's netdev */
-	struct net_device *peer_netdev;
 	struct net_device *upper_netdev; /* upper bonding netdev */
+	struct list_head *netdev_head;
 	struct notifier_block notif_block;
+	s32 bond_mode;
+	u16 bond_swid; /* swid for primary interface */
+	u8 active_port; /* lport value for the current active port */
 	u8 bonded:1; /* currently bonded */
 	u8 primary:1; /* this is primary */
+	u16 pf_recipe;
+	u16 pf_rule_id;
+	u16 cp_rule_idx;
 	u8 role;
 };
 
+/* LAG workqueue struct */
+struct ice_lag_work {
+	struct work_struct lag_task;
+	struct ice_lag_netdev_list netdev_list;
+	struct ice_lag *lag;
+	unsigned long event;
+	struct net_device *event_netdev;
+	union {
+		struct netdev_notifier_changeupper_info changeupper_info;
+		struct netdev_notifier_bonding_info bonding_info;
+		struct netdev_notifier_info notifier_info;
+	} info;
+};
+
 int ice_init_lag(struct ice_pf *pf);
 void ice_deinit_lag(struct ice_pf *pf);
 #endif /* _ICE_LAG_H_ */
-- 
GitLab


From ec5a6c5f79ed7ff3e26418dce330d2a583e57fb0 Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 20 Jun 2023 15:18:49 -0700
Subject: [PATCH 0519/1806] ice: process events created by lag netdev event
 handler

Add in the function framework for the processing of LAG events.  Also add
in helper function to perform common tasks.

Add the basis of the process of linking a lower netdev to an upper netdev.

Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lag.c      | 559 +++++++++++++++---
 drivers/net/ethernet/intel/ice/ice_lag.h      |   1 +
 drivers/net/ethernet/intel/ice/ice_switch.c   |  10 +-
 drivers/net/ethernet/intel/ice/ice_switch.h   |   3 +
 drivers/net/ethernet/intel/ice/ice_virtchnl.c |   2 +
 5 files changed, 501 insertions(+), 74 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 5725772cf8f48..ac4deb5af1189 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -10,6 +10,13 @@
 #define ICE_LAG_RES_SHARED	BIT(14)
 #define ICE_LAG_RES_VALID	BIT(15)
 
+#define ICE_RECIPE_LEN			64
+static const u8 ice_dflt_vsi_rcp[ICE_RECIPE_LEN] = {
+	0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	0x85, 0, 0x01, 0, 0, 0, 0xff, 0xff, 0x08, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0x30, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
+
 /**
  * ice_lag_set_primary - set PF LAG state as Primary
  * @lag: LAG info struct
@@ -50,6 +57,147 @@ static void ice_lag_set_backup(struct ice_lag *lag)
 	lag->role = ICE_LAG_BACKUP;
 }
 
+/**
+ * ice_netdev_to_lag - return pointer to associated lag struct from netdev
+ * @netdev: pointer to net_device struct to query
+ */
+static struct ice_lag *ice_netdev_to_lag(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np;
+	struct ice_vsi *vsi;
+
+	if (!netif_is_ice(netdev))
+		return NULL;
+
+	np = netdev_priv(netdev);
+	if (!np)
+		return NULL;
+
+	vsi = np->vsi;
+	if (!vsi)
+		return NULL;
+
+	return vsi->back->lag;
+}
+
+/**
+ * ice_lag_find_primary - returns pointer to primary interfaces lag struct
+ * @lag: local interfaces lag struct
+ */
+static struct ice_lag *ice_lag_find_primary(struct ice_lag *lag)
+{
+	struct ice_lag *primary_lag = NULL;
+	struct list_head *tmp;
+
+	list_for_each(tmp, lag->netdev_head) {
+		struct ice_lag_netdev_list *entry;
+		struct ice_lag *tmp_lag;
+
+		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
+		tmp_lag = ice_netdev_to_lag(entry->netdev);
+		if (tmp_lag && tmp_lag->primary) {
+			primary_lag = tmp_lag;
+			break;
+		}
+	}
+
+	return primary_lag;
+}
+
+/**
+ * ice_lag_cfg_dflt_fltr - Add/Remove default VSI rule for LAG
+ * @lag: lag struct for local interface
+ * @add: boolean on whether we are adding filters
+ */
+static int
+ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add)
+{
+	struct ice_sw_rule_lkup_rx_tx *s_rule;
+	u16 s_rule_sz, vsi_num;
+	struct ice_hw *hw;
+	u32 act, opc;
+	u8 *eth_hdr;
+	int err;
+
+	hw = &lag->pf->hw;
+	vsi_num = ice_get_hw_vsi_num(hw, 0);
+
+	s_rule_sz = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule);
+	s_rule = kzalloc(s_rule_sz, GFP_KERNEL);
+	if (!s_rule) {
+		dev_err(ice_pf_to_dev(lag->pf), "error allocating rule for LAG default VSI\n");
+		return -ENOMEM;
+	}
+
+	if (add) {
+		eth_hdr = s_rule->hdr_data;
+		ice_fill_eth_hdr(eth_hdr);
+
+		act = (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) &
+			ICE_SINGLE_ACT_VSI_ID_M;
+		act |= ICE_SINGLE_ACT_VSI_FORWARDING |
+			ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE;
+
+		s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX);
+		s_rule->recipe_id = cpu_to_le16(lag->pf_recipe);
+		s_rule->src = cpu_to_le16(hw->port_info->lport);
+		s_rule->act = cpu_to_le32(act);
+		s_rule->hdr_len = cpu_to_le16(DUMMY_ETH_HDR_LEN);
+		opc = ice_aqc_opc_add_sw_rules;
+	} else {
+		s_rule->index = cpu_to_le16(lag->pf_rule_id);
+		opc = ice_aqc_opc_remove_sw_rules;
+	}
+
+	err = ice_aq_sw_rules(&lag->pf->hw, s_rule, s_rule_sz, 1, opc, NULL);
+	if (err)
+		goto dflt_fltr_free;
+
+	if (add)
+		lag->pf_rule_id = le16_to_cpu(s_rule->index);
+	else
+		lag->pf_rule_id = 0;
+
+dflt_fltr_free:
+	kfree(s_rule);
+	return err;
+}
+
+/**
+ * ice_lag_cfg_pf_fltrs - set filters up for new active port
+ * @lag: local interfaces lag struct
+ * @ptr: opaque data containing notifier event
+ */
+static void
+ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr)
+{
+	struct netdev_notifier_bonding_info *info;
+	struct netdev_bonding_info *bonding_info;
+	struct net_device *event_netdev;
+	struct device *dev;
+
+	event_netdev = netdev_notifier_info_to_dev(ptr);
+	/* not for this netdev */
+	if (event_netdev != lag->netdev)
+		return;
+
+	info = (struct netdev_notifier_bonding_info *)ptr;
+	bonding_info = &info->bonding_info;
+	dev = ice_pf_to_dev(lag->pf);
+
+	/* interface not active - remove old default VSI rule */
+	if (bonding_info->slave.state && lag->pf_rule_id) {
+		if (ice_lag_cfg_dflt_fltr(lag, false))
+			dev_err(dev, "Error removing old default VSI filter\n");
+		return;
+	}
+
+	/* interface becoming active - add new default VSI rule */
+	if (!bonding_info->slave.state && !lag->pf_rule_id)
+		if (ice_lag_cfg_dflt_fltr(lag, true))
+			dev_err(dev, "Error adding new default VSI filter\n");
+}
+
 /**
  * ice_display_lag_info - print LAG info
  * @lag: LAG info struct
@@ -85,6 +233,83 @@ static void ice_display_lag_info(struct ice_lag *lag)
 		upper, role, primary);
 }
 
+/**
+ * ice_lag_move_vf_node_tc - move scheduling nodes for one VF on one TC
+ * @lag: lag info struct
+ * @oldport: lport of previous nodes location
+ * @newport: lport of destination nodes location
+ * @vsi_num: array index of VSI in PF space
+ * @tc: traffic class to move
+ */
+static void
+ice_lag_move_vf_node_tc(struct ice_lag *lag, u8 oldport, u8 newport,
+			u16 vsi_num, u8 tc)
+{
+}
+
+/**
+ * ice_lag_move_single_vf_nodes - Move Tx scheduling nodes for single VF
+ * @lag: primary interface LAG struct
+ * @oldport: lport of previous interface
+ * @newport: lport of destination interface
+ * @vsi_num: SW index of VF's VSI
+ */
+static void
+ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport,
+			     u16 vsi_num)
+{
+	u8 tc;
+
+	ice_for_each_traffic_class(tc)
+		ice_lag_move_vf_node_tc(lag, oldport, newport, vsi_num, tc);
+}
+
+/**
+ * ice_lag_move_new_vf_nodes - Move Tx scheduling nodes for a VF if required
+ * @vf: the VF to move Tx nodes for
+ *
+ * Called just after configuring new VF queues. Check whether the VF Tx
+ * scheduling nodes need to be updated to fail over to the active port. If so,
+ * move them now.
+ */
+void ice_lag_move_new_vf_nodes(struct ice_vf *vf)
+{
+}
+
+/**
+ * ice_lag_move_vf_nodes - move Tx scheduling nodes for all VFs to new port
+ * @lag: lag info struct
+ * @oldport: lport of previous interface
+ * @newport: lport of destination interface
+ */
+static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport)
+{
+	struct ice_pf *pf;
+	int i;
+
+	if (!lag->primary)
+		return;
+
+	pf = lag->pf;
+	ice_for_each_vsi(pf, i)
+		if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF ||
+				   pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL))
+			ice_lag_move_single_vf_nodes(lag, oldport, newport, i);
+}
+
+#define ICE_LAG_SRIOV_CP_RECIPE		10
+#define ICE_LAG_SRIOV_TRAIN_PKT_LEN	16
+
+/**
+ * ice_lag_cfg_cp_fltr - configure filter for control packets
+ * @lag: local interface's lag struct
+ * @add: add or remove rule
+ */
+static void
+ice_lag_cfg_cp_fltr(struct ice_lag *lag, bool add)
+{
+}
+
 /**
  * ice_lag_info_event - handle NETDEV_BONDING_INFO event
  * @lag: LAG info struct
@@ -126,105 +351,168 @@ lag_out:
 	ice_display_lag_info(lag);
 }
 
+/**
+ * ice_lag_reclaim_vf_tc - move scheduling nodes back to primary interface
+ * @lag: primary interface lag struct
+ * @src_hw: HW struct current node location
+ * @vsi_num: VSI index in PF space
+ * @tc: traffic class to move
+ */
+static void
+ice_lag_reclaim_vf_tc(struct ice_lag *lag, struct ice_hw *src_hw, u16 vsi_num,
+		      u8 tc)
+{
+}
+
+/**
+ * ice_lag_reclaim_vf_nodes - When interface leaving bond primary reclaims nodes
+ * @lag: primary interface lag struct
+ * @src_hw: HW struct for current node location
+ */
+static void
+ice_lag_reclaim_vf_nodes(struct ice_lag *lag, struct ice_hw *src_hw)
+{
+	struct ice_pf *pf;
+	int i, tc;
+
+	if (!lag->primary || !src_hw)
+		return;
+
+	pf = lag->pf;
+	ice_for_each_vsi(pf, i)
+		if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF ||
+				   pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL))
+			ice_for_each_traffic_class(tc)
+				ice_lag_reclaim_vf_tc(lag, src_hw, i, tc);
+}
+
 /**
  * ice_lag_link - handle LAG link event
  * @lag: LAG info struct
- * @info: info from the netdev notifier
  */
-static void
-ice_lag_link(struct ice_lag *lag, struct netdev_notifier_changeupper_info *info)
+static void ice_lag_link(struct ice_lag *lag)
 {
-	struct net_device *netdev_tmp, *upper = info->upper_dev;
 	struct ice_pf *pf = lag->pf;
-	int peers = 0;
 
 	if (lag->bonded)
 		dev_warn(ice_pf_to_dev(pf), "%s Already part of a bond\n",
 			 netdev_name(lag->netdev));
 
-	rcu_read_lock();
-	for_each_netdev_in_bond_rcu(upper, netdev_tmp)
-		peers++;
-	rcu_read_unlock();
-
-	if (lag->upper_netdev != upper) {
-		dev_hold(upper);
-		lag->upper_netdev = upper;
-	}
-
-	ice_clear_rdma_cap(pf);
-
 	lag->bonded = true;
 	lag->role = ICE_LAG_UNSET;
-
-	/* if this is the first element in an LAG mark as primary */
-	lag->primary = !!(peers == 1);
 }
 
 /**
  * ice_lag_unlink - handle unlink event
  * @lag: LAG info struct
- * @info: info from netdev notification
  */
-static void
-ice_lag_unlink(struct ice_lag *lag,
-	       struct netdev_notifier_changeupper_info *info)
+static void ice_lag_unlink(struct ice_lag *lag)
 {
-	struct net_device *netdev_tmp, *upper = info->upper_dev;
+	u8 pri_port, act_port, loc_port;
 	struct ice_pf *pf = lag->pf;
-	bool found = false;
 
 	if (!lag->bonded) {
 		netdev_dbg(lag->netdev, "bonding unlink event on non-LAG netdev\n");
 		return;
 	}
 
-	/* determine if we are in the new LAG config or not */
-	rcu_read_lock();
-	for_each_netdev_in_bond_rcu(upper, netdev_tmp) {
-		if (netdev_tmp == lag->netdev) {
-			found = true;
-			break;
+	if (lag->primary) {
+		act_port = lag->active_port;
+		pri_port = lag->pf->hw.port_info->lport;
+		if (act_port != pri_port && act_port != ICE_LAG_INVALID_PORT)
+			ice_lag_move_vf_nodes(lag, act_port, pri_port);
+		lag->primary = false;
+		lag->active_port = ICE_LAG_INVALID_PORT;
+	} else {
+		struct ice_lag *primary_lag;
+
+		primary_lag = ice_lag_find_primary(lag);
+		if (primary_lag) {
+			act_port = primary_lag->active_port;
+			pri_port = primary_lag->pf->hw.port_info->lport;
+			loc_port = pf->hw.port_info->lport;
+			if (act_port == loc_port &&
+			    act_port != ICE_LAG_INVALID_PORT) {
+				ice_lag_reclaim_vf_nodes(primary_lag,
+							 &lag->pf->hw);
+				primary_lag->active_port = ICE_LAG_INVALID_PORT;
+			}
 		}
 	}
-	rcu_read_unlock();
-
-	if (found)
-		return;
-
-	if (lag->upper_netdev) {
-		dev_put(lag->upper_netdev);
-		lag->upper_netdev = NULL;
-	}
 
-	ice_set_rdma_cap(pf);
 	lag->bonded = false;
 	lag->role = ICE_LAG_NONE;
+	lag->upper_netdev = NULL;
 }
 
 /**
- * ice_lag_unregister - handle netdev unregister events
- * @lag: LAG info struct
- * @netdev: netdev reporting the event
+ * ice_lag_link_unlink - helper function to call lag_link/unlink
+ * @lag: lag info struct
+ * @ptr: opaque pointer data
  */
-static void ice_lag_unregister(struct ice_lag *lag, struct net_device *netdev)
+static void ice_lag_link_unlink(struct ice_lag *lag, void *ptr)
 {
-	struct ice_pf *pf = lag->pf;
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_changeupper_info *info = ptr;
 
-	/* check to see if this event is for this netdev
-	 * check that we are in an aggregate
-	 */
-	if (netdev != lag->netdev || !lag->bonded)
+	if (netdev != lag->netdev)
 		return;
 
-	if (lag->upper_netdev) {
-		dev_put(lag->upper_netdev);
-		lag->upper_netdev = NULL;
-		ice_set_rdma_cap(pf);
-	}
-	/* perform some cleanup in case we come back */
-	lag->bonded = false;
-	lag->role = ICE_LAG_NONE;
+	if (info->linking)
+		ice_lag_link(lag);
+	else
+		ice_lag_unlink(lag);
+}
+
+/**
+ * ice_lag_set_swid - set the SWID on secondary interface
+ * @primary_swid: primary interface's SWID
+ * @local_lag: local interfaces LAG struct
+ * @link: Is this a linking activity
+ *
+ * If link is false, then primary_swid should be expected to not be valid
+ */
+static void
+ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
+		 bool link)
+{
+}
+
+/**
+ * ice_lag_primary_swid - set/clear the SHARED attrib of primary's SWID
+ * @lag: primary interfaces lag struct
+ * @link: is this a linking activity
+ *
+ * Implement setting primary SWID as shared using 0x020B
+ */
+static void ice_lag_primary_swid(struct ice_lag *lag, bool link)
+{
+	struct ice_hw *hw;
+	u16 swid;
+
+	hw = &lag->pf->hw;
+	swid = hw->port_info->sw_id;
+
+	if (ice_share_res(hw, ICE_AQC_RES_TYPE_SWID, link, swid))
+		dev_warn(ice_pf_to_dev(lag->pf), "Failure to set primary interface shared status\n");
+}
+
+/**
+ * ice_lag_add_prune_list - Adds event_pf's VSI to primary's prune list
+ * @lag: lag info struct
+ * @event_pf: PF struct for VSI we are adding to primary's prune list
+ */
+static void ice_lag_add_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
+{
+}
+
+/**
+ * ice_lag_del_prune_list - Remove secondary's vsi from primary's prune list
+ * @lag: primary interface's ice_lag struct
+ * @event_pf: PF struct for unlinking interface
+ */
+static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
+{
 }
 
 /**
@@ -257,6 +545,7 @@ static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
 static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 {
 	struct netdev_notifier_changeupper_info *info;
+	struct ice_lag *primary_lag;
 	struct net_device *netdev;
 
 	info = ptr;
@@ -266,24 +555,107 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 	if (netdev != lag->netdev)
 		return;
 
-	if (!info->upper_dev) {
-		netdev_dbg(netdev, "changeupper rcvd, but no upper defined\n");
-		return;
+	primary_lag = ice_lag_find_primary(lag);
+	if (info->linking) {
+		lag->upper_netdev = info->upper_dev;
+		/* If there is not already a primary interface in the LAG,
+		 * then mark this one as primary.
+		 */
+		if (!primary_lag) {
+			lag->primary = true;
+			/* Configure primary's SWID to be shared */
+			ice_lag_primary_swid(lag, true);
+			primary_lag = lag;
+		} else {
+			u16 swid;
+
+			swid = primary_lag->pf->hw.port_info->sw_id;
+			ice_lag_set_swid(swid, lag, true);
+			ice_lag_add_prune_list(primary_lag, lag->pf);
+		}
+		/* add filter for primary control packets */
+		ice_lag_cfg_cp_fltr(lag, true);
+	} else {
+		if (!primary_lag && lag->primary)
+			primary_lag = lag;
+
+		if (primary_lag) {
+			if (!lag->primary) {
+				ice_lag_set_swid(0, lag, false);
+			} else {
+				ice_lag_primary_swid(lag, false);
+				ice_lag_del_prune_list(primary_lag, lag->pf);
+			}
+			ice_lag_cfg_cp_fltr(lag, false);
+		}
 	}
+}
+
+/**
+ * ice_lag_monitor_link - monitor interfaces entering/leaving the aggregate
+ * @lag: lag info struct
+ * @ptr: opaque data containing notifier event
+ *
+ * This function only operates after a primary has been set.
+ */
+static void ice_lag_monitor_link(struct ice_lag *lag, void *ptr)
+{
+}
+
+/**
+ * ice_lag_monitor_active - main PF keep track of which port is active
+ * @lag: lag info struct
+ * @ptr: opaque data containing notifier event
+ *
+ * This function is for the primary PF to monitor changes in which port is
+ * active and handle changes for SRIOV VF functionality
+ */
+static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
+{
+}
+
+/**
+ * ice_lag_chk_comp - evaluate bonded interface for feature support
+ * @lag: lag info struct
+ * @ptr: opaque data for netdev event info
+ */
+static bool
+ice_lag_chk_comp(struct ice_lag *lag, void *ptr)
+{
+	return true;
+}
+
+/**
+ * ice_lag_unregister - handle netdev unregister events
+ * @lag: LAG info struct
+ * @event_netdev: netdev struct for target of notifier event
+ */
+static void
+ice_lag_unregister(struct ice_lag *lag, struct net_device *event_netdev)
+{
+}
 
-	netdev_dbg(netdev, "bonding %s\n", info->linking ? "LINK" : "UNLINK");
+/**
+ * ice_lag_monitor_rdma - set and clear rdma functionality
+ * @lag: pointer to lag struct
+ * @ptr: opaque data for netdev event info
+ */
+static void
+ice_lag_monitor_rdma(struct ice_lag *lag, void *ptr)
+{
+	struct netdev_notifier_changeupper_info *info;
+	struct net_device *netdev;
+
+	info = ptr;
+	netdev = netdev_notifier_info_to_dev(ptr);
 
-	if (!netif_is_lag_master(info->upper_dev)) {
-		netdev_dbg(netdev, "changeupper rcvd, but not primary. bail\n");
+	if (netdev != lag->netdev)
 		return;
-	}
 
 	if (info->linking)
-		ice_lag_link(lag, info);
+		ice_clear_rdma_cap(lag->pf);
 	else
-		ice_lag_unlink(lag, info);
-
-	ice_display_lag_info(lag);
+		ice_set_rdma_cap(lag->pf);
 }
 
 /**
@@ -307,16 +679,31 @@ static void ice_lag_process_event(struct work_struct *work)
 	switch (lag_work->event) {
 	case NETDEV_CHANGEUPPER:
 		info = &lag_work->info.changeupper_info;
-		ice_lag_changeupper_event(lag_work->lag, info);
+		if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) {
+			ice_lag_monitor_link(lag_work->lag, info);
+			ice_lag_changeupper_event(lag_work->lag, info);
+			ice_lag_link_unlink(lag_work->lag, info);
+		}
+		ice_lag_monitor_rdma(lag_work->lag, info);
 		break;
 	case NETDEV_BONDING_INFO:
+		if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) {
+			if (!ice_lag_chk_comp(lag_work->lag,
+					      &lag_work->info.bonding_info)) {
+				goto lag_cleanup;
+			}
+			ice_lag_monitor_active(lag_work->lag,
+					       &lag_work->info.bonding_info);
+			ice_lag_cfg_pf_fltrs(lag_work->lag,
+					     &lag_work->info.bonding_info);
+		}
 		ice_lag_info_event(lag_work->lag, &lag_work->info.bonding_info);
 		break;
 	case NETDEV_UNREGISTER:
 		if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) {
 			netdev = lag_work->info.bonding_info.info.dev;
-			if ((netdev == lag_work->lag->netdev ||
-			     lag_work->lag->primary) && lag_work->lag->bonded)
+			if (netdev == lag_work->lag->netdev &&
+			    lag_work->lag->bonded)
 				ice_lag_unregister(lag_work->lag, netdev);
 		}
 		break;
@@ -324,6 +711,7 @@ static void ice_lag_process_event(struct work_struct *work)
 		break;
 	}
 
+lag_cleanup:
 	/* cleanup resources allocated for this work item */
 	list_for_each_safe(tmp, n, &lag_work->netdev_list.node) {
 		struct ice_lag_netdev_list *entry;
@@ -465,6 +853,22 @@ static void ice_unregister_lag_handler(struct ice_lag *lag)
 	}
 }
 
+/**
+ * ice_create_lag_recipe
+ * @hw: pointer to HW struct
+ * @base_recipe: recipe to base the new recipe on
+ * @prio: priority for new recipe
+ *
+ * function returns 0 on error
+ */
+static u16 ice_create_lag_recipe(struct ice_hw *hw, const u8 *base_recipe,
+				 u8 prio)
+{
+	u16 rid = 0;
+
+	return rid;
+}
+
 /**
  * ice_init_lag - initialize support for LAG
  * @pf: PF struct
@@ -506,6 +910,12 @@ int ice_init_lag(struct ice_pf *pf)
 		goto lag_error;
 	}
 
+	lag->pf_recipe = ice_create_lag_recipe(&pf->hw, ice_dflt_vsi_rcp, 1);
+	if (!lag->pf_recipe) {
+		err = -EINVAL;
+		goto lag_error;
+	}
+
 	ice_display_lag_info(lag);
 
 	dev_dbg(dev, "INIT LAG complete\n");
@@ -538,6 +948,9 @@ void ice_deinit_lag(struct ice_pf *pf)
 
 	flush_workqueue(ice_lag_wq);
 
+	ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1,
+			&pf->lag->pf_recipe);
+
 	kfree(lag);
 
 	pf->lag = NULL;
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index a4314a46c82c4..df4af5184a75c 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -56,6 +56,7 @@ struct ice_lag_work {
 	} info;
 };
 
+void ice_lag_move_new_vf_nodes(struct ice_vf *vf);
 int ice_init_lag(struct ice_pf *pf);
 void ice_deinit_lag(struct ice_pf *pf);
 #endif /* _ICE_LAG_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 8c332d24c7c58..91bc92f5059b1 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -25,7 +25,6 @@
  *      In case of Ether type filter it is treated as header without VLAN tag
  *      and byte 12 and 13 is used to program a given Ether type instead
  */
-#define DUMMY_ETH_HDR_LEN		16
 static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0,
 							0x2, 0, 0, 0, 0, 0,
 							0x81, 0, 0, 0};
@@ -2460,6 +2459,15 @@ static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi)
 	}
 }
 
+/**
+ * ice_fill_eth_hdr - helper to copy dummy_eth_hdr into supplied buffer
+ * @eth_hdr: pointer to buffer to populate
+ */
+void ice_fill_eth_hdr(u8 *eth_hdr)
+{
+	memcpy(eth_hdr, dummy_eth_header, DUMMY_ETH_HDR_LEN);
+}
+
 /**
  * ice_fill_sw_rule - Helper function to fill switch rule structure
  * @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index 51cd14952cd1f..250823ac173a9 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -30,6 +30,8 @@
 	ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0)
 #define ICE_SW_RULE_LG_ACT_SIZE(s, n)		struct_size((s), act, (n))
 
+#define DUMMY_ETH_HDR_LEN		16
+
 /* VSI context structure for add/get/update/free operations */
 struct ice_vsi_ctx {
 	u16 vsi_num;
@@ -402,6 +404,7 @@ u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle);
 
 int ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle);
 void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw);
+void ice_fill_eth_hdr(u8 *eth_hdr);
 
 int
 ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz,
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index efbc2968a7bf6..625da88e79659 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -1724,6 +1724,8 @@ error_param:
 				vf->vf_id, i);
 	}
 
+	ice_lag_move_new_vf_nodes(vf);
+
 	/* send the response to the VF */
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
 				     VIRTCHNL_STATUS_ERR_PARAM, NULL, 0);
-- 
GitLab


From 1e0f9881ef79af9629bbf3cc3b307498d2e015ac Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 20 Jun 2023 15:18:50 -0700
Subject: [PATCH 0520/1806] ice: Flesh out implementation of support for SRIOV
 on bonded interface

Add in the functions that will allow a VF created on the primary interface
of a bond to "fail-over" to another PF interface in the bond and continue
to Tx and Rx.

Add in an ordered take-down path for the bonded interface.

Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lag.c | 826 ++++++++++++++++++++++-
 1 file changed, 816 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index ac4deb5af1189..f054bf6181dad 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -10,6 +10,11 @@
 #define ICE_LAG_RES_SHARED	BIT(14)
 #define ICE_LAG_RES_VALID	BIT(15)
 
+#define LACP_TRAIN_PKT_LEN		16
+static const u8 lacp_train_pkt[LACP_TRAIN_PKT_LEN] = { 0, 0, 0, 0, 0, 0,
+						       0, 0, 0, 0, 0, 0,
+						       0x88, 0x09, 0, 0 };
+
 #define ICE_RECIPE_LEN			64
 static const u8 ice_dflt_vsi_rcp[ICE_RECIPE_LEN] = {
 	0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -57,6 +62,39 @@ static void ice_lag_set_backup(struct ice_lag *lag)
 	lag->role = ICE_LAG_BACKUP;
 }
 
+/**
+ * netif_is_same_ice - determine if netdev is on the same ice NIC as local PF
+ * @pf: local PF struct
+ * @netdev: netdev we are evaluating
+ */
+static bool netif_is_same_ice(struct ice_pf *pf, struct net_device *netdev)
+{
+	struct ice_netdev_priv *np;
+	struct ice_pf *test_pf;
+	struct ice_vsi *vsi;
+
+	if (!netif_is_ice(netdev))
+		return false;
+
+	np = netdev_priv(netdev);
+	if (!np)
+		return false;
+
+	vsi = np->vsi;
+	if (!vsi)
+		return false;
+
+	test_pf = vsi->back;
+	if (!test_pf)
+		return false;
+
+	if (pf->pdev->bus != test_pf->pdev->bus ||
+	    pf->pdev->slot != test_pf->pdev->slot)
+		return false;
+
+	return true;
+}
+
 /**
  * ice_netdev_to_lag - return pointer to associated lag struct from netdev
  * @netdev: pointer to net_device struct to query
@@ -80,6 +118,38 @@ static struct ice_lag *ice_netdev_to_lag(struct net_device *netdev)
 	return vsi->back->lag;
 }
 
+/**
+ * ice_lag_find_hw_by_lport - return an hw struct from bond members lport
+ * @lag: lag struct
+ * @lport: lport value to search for
+ */
+static struct ice_hw *
+ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport)
+{
+	struct ice_lag_netdev_list *entry;
+	struct net_device *tmp_netdev;
+	struct ice_netdev_priv *np;
+	struct list_head *tmp;
+	struct ice_hw *hw;
+
+	list_for_each(tmp, lag->netdev_head) {
+		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
+		tmp_netdev = entry->netdev;
+		if (!tmp_netdev || !netif_is_ice(tmp_netdev))
+			continue;
+
+		np = netdev_priv(tmp_netdev);
+		if (!np || !np->vsi)
+			continue;
+
+		hw = &np->vsi->back->hw;
+		if (hw->port_info->lport == lport)
+			return hw;
+	}
+
+	return NULL;
+}
+
 /**
  * ice_lag_find_primary - returns pointer to primary interfaces lag struct
  * @lag: local interfaces lag struct
@@ -233,6 +303,123 @@ static void ice_display_lag_info(struct ice_lag *lag)
 		upper, role, primary);
 }
 
+/**
+ * ice_lag_qbuf_recfg - generate a buffer of queues for a reconfigure command
+ * @hw: HW struct that contains the queue contexts
+ * @qbuf: pointer to buffer to populate
+ * @vsi_num: index of the VSI in PF space
+ * @numq: number of queues to search for
+ * @tc: traffic class that contains the queues
+ *
+ * function returns the number of valid queues in buffer
+ */
+static u16
+ice_lag_qbuf_recfg(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *qbuf,
+		   u16 vsi_num, u16 numq, u8 tc)
+{
+	struct ice_q_ctx *q_ctx;
+	u16 qid, count = 0;
+	struct ice_pf *pf;
+	int i;
+
+	pf = hw->back;
+	for (i = 0; i < numq; i++) {
+		q_ctx = ice_get_lan_q_ctx(hw, vsi_num, tc, i);
+		if (!q_ctx) {
+			dev_dbg(ice_hw_to_dev(hw), "%s queue %d NO Q CONTEXT\n",
+				__func__, i);
+			continue;
+		}
+		if (q_ctx->q_teid == ICE_INVAL_TEID) {
+			dev_dbg(ice_hw_to_dev(hw), "%s queue %d INVAL TEID\n",
+				__func__, i);
+			continue;
+		}
+		if (q_ctx->q_handle == ICE_INVAL_Q_HANDLE) {
+			dev_dbg(ice_hw_to_dev(hw), "%s queue %d INVAL Q HANDLE\n",
+				__func__, i);
+			continue;
+		}
+
+		qid = pf->vsi[vsi_num]->txq_map[q_ctx->q_handle];
+		qbuf->queue_info[count].q_handle = cpu_to_le16(qid);
+		qbuf->queue_info[count].tc = tc;
+		qbuf->queue_info[count].q_teid = cpu_to_le32(q_ctx->q_teid);
+		count++;
+	}
+
+	return count;
+}
+
+/**
+ * ice_lag_get_sched_parent - locate or create a sched node parent
+ * @hw: HW struct for getting parent in
+ * @tc: traffic class on parent/node
+ */
+static struct ice_sched_node *
+ice_lag_get_sched_parent(struct ice_hw *hw, u8 tc)
+{
+	struct ice_sched_node *tc_node, *aggnode, *parent = NULL;
+	u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 };
+	struct ice_port_info *pi = hw->port_info;
+	struct device *dev;
+	u8 aggl, vsil;
+	int n;
+
+	dev = ice_hw_to_dev(hw);
+
+	tc_node = ice_sched_get_tc_node(pi, tc);
+	if (!tc_node) {
+		dev_warn(dev, "Failure to find TC node for LAG move\n");
+		return parent;
+	}
+
+	aggnode = ice_sched_get_agg_node(pi, tc_node, ICE_DFLT_AGG_ID);
+	if (!aggnode) {
+		dev_warn(dev, "Failure to find aggregate node for LAG move\n");
+		return parent;
+	}
+
+	aggl = ice_sched_get_agg_layer(hw);
+	vsil = ice_sched_get_vsi_layer(hw);
+
+	for (n = aggl + 1; n < vsil; n++)
+		num_nodes[n] = 1;
+
+	for (n = 0; n < aggnode->num_children; n++) {
+		parent = ice_sched_get_free_vsi_parent(hw, aggnode->children[n],
+						       num_nodes);
+		if (parent)
+			return parent;
+	}
+
+	/* if free parent not found - add one */
+	parent = aggnode;
+	for (n = aggl + 1; n < vsil; n++) {
+		u16 num_nodes_added;
+		u32 first_teid;
+		int err;
+
+		err = ice_sched_add_nodes_to_layer(pi, tc_node, parent, n,
+						   num_nodes[n], &first_teid,
+						   &num_nodes_added);
+		if (err || num_nodes[n] != num_nodes_added)
+			return NULL;
+
+		if (num_nodes_added)
+			parent = ice_sched_find_node_by_teid(tc_node,
+							     first_teid);
+		else
+			parent = parent->children[0];
+		if (!parent) {
+			dev_warn(dev, "Failure to add new parent for LAG move\n");
+			return parent;
+		}
+	}
+
+	return parent;
+}
+
 /**
  * ice_lag_move_vf_node_tc - move scheduling nodes for one VF on one TC
  * @lag: lag info struct
@@ -245,6 +432,110 @@ static void
 ice_lag_move_vf_node_tc(struct ice_lag *lag, u8 oldport, u8 newport,
 			u16 vsi_num, u8 tc)
 {
+	u16 numq, valq, buf_size, num_moved, qbuf_size;
+	struct device *dev = ice_pf_to_dev(lag->pf);
+	struct ice_aqc_cfg_txqs_buf *qbuf;
+	struct ice_aqc_move_elem *buf;
+	struct ice_sched_node *n_prt;
+	struct ice_hw *new_hw = NULL;
+	__le32 teid, parent_teid;
+	struct ice_vsi_ctx *ctx;
+	u32 tmp_teid;
+
+	ctx = ice_get_vsi_ctx(&lag->pf->hw, vsi_num);
+	if (!ctx) {
+		dev_warn(dev, "Unable to locate VSI context for LAG failover\n");
+		return;
+	}
+
+	/* check to see if this VF is enabled on this TC */
+	if (!ctx->sched.vsi_node[tc])
+		return;
+
+	/* locate HW struct for destination port */
+	new_hw = ice_lag_find_hw_by_lport(lag, newport);
+	if (!new_hw) {
+		dev_warn(dev, "Unable to locate HW struct for LAG node destination\n");
+		return;
+	}
+
+	numq = ctx->num_lan_q_entries[tc];
+	teid = ctx->sched.vsi_node[tc]->info.node_teid;
+	tmp_teid = le32_to_cpu(teid);
+	parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid;
+	/* if no teid assigned or numq == 0, then this TC is not active */
+	if (!tmp_teid || !numq)
+		return;
+
+	/* suspend VSI subtree for Traffic Class "tc" on
+	 * this VF's VSI
+	 */
+	if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, true))
+		dev_dbg(dev, "Problem suspending traffic for LAG node move\n");
+
+	/* reconfigure all VF's queues on this Traffic Class
+	 * to new port
+	 */
+	qbuf_size = struct_size(qbuf, queue_info, numq);
+	qbuf = kzalloc(qbuf_size, GFP_KERNEL);
+	if (!qbuf) {
+		dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n");
+		goto resume_traffic;
+	}
+
+	/* add the per queue info for the reconfigure command buffer */
+	valq = ice_lag_qbuf_recfg(&lag->pf->hw, qbuf, vsi_num, numq, tc);
+	if (!valq) {
+		dev_dbg(dev, "No valid queues found for LAG failover\n");
+		goto qbuf_none;
+	}
+
+	if (ice_aq_cfg_lan_txq(&lag->pf->hw, qbuf, qbuf_size, valq, oldport,
+			       newport, NULL)) {
+		dev_warn(dev, "Failure to configure queues for LAG failover\n");
+		goto qbuf_err;
+	}
+
+qbuf_none:
+	kfree(qbuf);
+
+	/* find new parent in destination port's tree for VF VSI node on this
+	 * Traffic Class
+	 */
+	n_prt = ice_lag_get_sched_parent(new_hw, tc);
+	if (!n_prt)
+		goto resume_traffic;
+
+	/* Move Vf's VSI node for this TC to newport's scheduler tree */
+	buf_size = struct_size(buf, teid, 1);
+	buf = kzalloc(buf_size, GFP_KERNEL);
+	if (!buf) {
+		dev_warn(dev, "Failure to alloc memory for VF node failover\n");
+		goto resume_traffic;
+	}
+
+	buf->hdr.src_parent_teid = parent_teid;
+	buf->hdr.dest_parent_teid = n_prt->info.node_teid;
+	buf->hdr.num_elems = cpu_to_le16(1);
+	buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN;
+	buf->teid[0] = teid;
+
+	if (ice_aq_move_sched_elems(&lag->pf->hw, 1, buf, buf_size, &num_moved,
+				    NULL))
+		dev_warn(dev, "Failure to move VF nodes for failover\n");
+	else
+		ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]);
+
+	kfree(buf);
+	goto resume_traffic;
+
+qbuf_err:
+	kfree(qbuf);
+
+resume_traffic:
+	/* restart traffic for VSI node */
+	if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, false))
+		dev_dbg(dev, "Problem restarting traffic for LAG node move\n");
 }
 
 /**
@@ -274,6 +565,66 @@ ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport,
  */
 void ice_lag_move_new_vf_nodes(struct ice_vf *vf)
 {
+	struct ice_lag_netdev_list ndlist;
+	struct list_head *tmp, *n;
+	u8 pri_port, act_port;
+	struct ice_lag *lag;
+	struct ice_vsi *vsi;
+	struct ice_pf *pf;
+
+	vsi = ice_get_vf_vsi(vf);
+
+	if (WARN_ON(!vsi))
+		return;
+
+	if (WARN_ON(vsi->type != ICE_VSI_VF))
+		return;
+
+	pf = vf->pf;
+	lag = pf->lag;
+
+	mutex_lock(&pf->lag_mutex);
+	if (!lag->bonded)
+		goto new_vf_unlock;
+
+	pri_port = pf->hw.port_info->lport;
+	act_port = lag->active_port;
+
+	if (lag->upper_netdev) {
+		struct ice_lag_netdev_list *nl;
+		struct net_device *tmp_nd;
+
+		INIT_LIST_HEAD(&ndlist.node);
+		rcu_read_lock();
+		for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
+			nl = kzalloc(sizeof(*nl), GFP_KERNEL);
+			if (!nl)
+				break;
+
+			nl->netdev = tmp_nd;
+			list_add(&nl->node, &ndlist.node);
+		}
+		rcu_read_unlock();
+	}
+
+	lag->netdev_head = &ndlist.node;
+
+	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) &&
+	    lag->bonded && lag->primary && pri_port != act_port &&
+	    !list_empty(lag->netdev_head))
+		ice_lag_move_single_vf_nodes(lag, pri_port, act_port, vsi->idx);
+
+	list_for_each_safe(tmp, n, &ndlist.node) {
+		struct ice_lag_netdev_list *entry;
+
+		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	lag->netdev_head = NULL;
+
+new_vf_unlock:
+	mutex_unlock(&pf->lag_mutex);
 }
 
 /**
@@ -308,6 +659,50 @@ static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport)
 static void
 ice_lag_cfg_cp_fltr(struct ice_lag *lag, bool add)
 {
+	struct ice_sw_rule_lkup_rx_tx *s_rule = NULL;
+	struct ice_vsi *vsi;
+	u16 buf_len, opc;
+
+	vsi = lag->pf->vsi[0];
+
+	buf_len = ICE_SW_RULE_RX_TX_HDR_SIZE(s_rule,
+					     ICE_LAG_SRIOV_TRAIN_PKT_LEN);
+	s_rule = kzalloc(buf_len, GFP_KERNEL);
+	if (!s_rule) {
+		netdev_warn(lag->netdev, "-ENOMEM error configuring CP filter\n");
+		return;
+	}
+
+	if (add) {
+		s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX);
+		s_rule->recipe_id = cpu_to_le16(ICE_LAG_SRIOV_CP_RECIPE);
+		s_rule->src = cpu_to_le16(vsi->port_info->lport);
+		s_rule->act = cpu_to_le32(ICE_FWD_TO_VSI |
+					  ICE_SINGLE_ACT_LAN_ENABLE |
+					  ICE_SINGLE_ACT_VALID_BIT |
+					  ((vsi->vsi_num <<
+					    ICE_SINGLE_ACT_VSI_ID_S) &
+					   ICE_SINGLE_ACT_VSI_ID_M));
+		s_rule->hdr_len = cpu_to_le16(ICE_LAG_SRIOV_TRAIN_PKT_LEN);
+		memcpy(s_rule->hdr_data, lacp_train_pkt, LACP_TRAIN_PKT_LEN);
+		opc = ice_aqc_opc_add_sw_rules;
+	} else {
+		opc = ice_aqc_opc_remove_sw_rules;
+		s_rule->index = cpu_to_le16(lag->cp_rule_idx);
+	}
+	if (ice_aq_sw_rules(&lag->pf->hw, s_rule, buf_len, 1, opc, NULL)) {
+		netdev_warn(lag->netdev, "Error %s CP rule for fail-over\n",
+			    add ? "ADDING" : "REMOVING");
+		goto cp_free;
+	}
+
+	if (add)
+		lag->cp_rule_idx = le16_to_cpu(s_rule->index);
+	else
+		lag->cp_rule_idx = 0;
+
+cp_free:
+	kfree(s_rule);
 }
 
 /**
@@ -362,6 +757,100 @@ static void
 ice_lag_reclaim_vf_tc(struct ice_lag *lag, struct ice_hw *src_hw, u16 vsi_num,
 		      u8 tc)
 {
+	u16 numq, valq, buf_size, num_moved, qbuf_size;
+	struct device *dev = ice_pf_to_dev(lag->pf);
+	struct ice_aqc_cfg_txqs_buf *qbuf;
+	struct ice_aqc_move_elem *buf;
+	struct ice_sched_node *n_prt;
+	__le32 teid, parent_teid;
+	struct ice_vsi_ctx *ctx;
+	struct ice_hw *hw;
+	u32 tmp_teid;
+
+	hw = &lag->pf->hw;
+	ctx = ice_get_vsi_ctx(hw, vsi_num);
+	if (!ctx) {
+		dev_warn(dev, "Unable to locate VSI context for LAG reclaim\n");
+		return;
+	}
+
+	/* check to see if this VF is enabled on this TC */
+	if (!ctx->sched.vsi_node[tc])
+		return;
+
+	numq = ctx->num_lan_q_entries[tc];
+	teid = ctx->sched.vsi_node[tc]->info.node_teid;
+	tmp_teid = le32_to_cpu(teid);
+	parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid;
+
+	/* if !teid or !numq, then this TC is not active */
+	if (!tmp_teid || !numq)
+		return;
+
+	/* suspend traffic */
+	if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true))
+		dev_dbg(dev, "Problem suspending traffic for LAG node move\n");
+
+	/* reconfig queues for new port */
+	qbuf_size = struct_size(qbuf, queue_info, numq);
+	qbuf = kzalloc(qbuf_size, GFP_KERNEL);
+	if (!qbuf) {
+		dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n");
+		goto resume_reclaim;
+	}
+
+	/* add the per queue info for the reconfigure command buffer */
+	valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc);
+	if (!valq) {
+		dev_dbg(dev, "No valid queues found for LAG reclaim\n");
+		goto reclaim_none;
+	}
+
+	if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq,
+			       src_hw->port_info->lport, hw->port_info->lport,
+			       NULL)) {
+		dev_warn(dev, "Failure to configure queues for LAG failover\n");
+		goto reclaim_qerr;
+	}
+
+reclaim_none:
+	kfree(qbuf);
+
+	/* find parent in primary tree */
+	n_prt = ice_lag_get_sched_parent(hw, tc);
+	if (!n_prt)
+		goto resume_reclaim;
+
+	/* Move node to new parent */
+	buf_size = struct_size(buf, teid, 1);
+	buf = kzalloc(buf_size, GFP_KERNEL);
+	if (!buf) {
+		dev_warn(dev, "Failure to alloc memory for VF node failover\n");
+		goto resume_reclaim;
+	}
+
+	buf->hdr.src_parent_teid = parent_teid;
+	buf->hdr.dest_parent_teid = n_prt->info.node_teid;
+	buf->hdr.num_elems = cpu_to_le16(1);
+	buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN;
+	buf->teid[0] = teid;
+
+	if (ice_aq_move_sched_elems(&lag->pf->hw, 1, buf, buf_size, &num_moved,
+				    NULL))
+		dev_warn(dev, "Failure to move VF nodes for LAG reclaim\n");
+	else
+		ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]);
+
+	kfree(buf);
+	goto resume_reclaim;
+
+reclaim_qerr:
+	kfree(qbuf);
+
+resume_reclaim:
+	/* restart traffic */
+	if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false))
+		dev_warn(dev, "Problem restarting traffic for LAG node reclaim\n");
 }
 
 /**
@@ -476,6 +965,65 @@ static void
 ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
 		 bool link)
 {
+	struct ice_aqc_alloc_free_res_elem *buf;
+	struct ice_aqc_set_port_params *cmd;
+	struct ice_aq_desc desc;
+	u16 buf_len, swid;
+	int status;
+
+	buf_len = struct_size(buf, elem, 1);
+	buf = kzalloc(buf_len, GFP_KERNEL);
+	if (!buf) {
+		dev_err(ice_pf_to_dev(local_lag->pf), "-ENOMEM error setting SWID\n");
+		return;
+	}
+
+	buf->num_elems = cpu_to_le16(1);
+	buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_SWID);
+	/* if unlinnking need to free the shared resource */
+	if (!link && local_lag->bond_swid) {
+		buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid);
+		status = ice_aq_alloc_free_res(&local_lag->pf->hw, 1, buf,
+					       buf_len, ice_aqc_opc_free_res,
+					       NULL);
+		if (status)
+			dev_err(ice_pf_to_dev(local_lag->pf), "Error freeing SWID during LAG unlink\n");
+		local_lag->bond_swid = 0;
+	}
+
+	if (link) {
+		buf->res_type |=  cpu_to_le16(ICE_LAG_RES_SHARED |
+					      ICE_LAG_RES_VALID);
+		/* store the primary's SWID in case it leaves bond first */
+		local_lag->bond_swid = primary_swid;
+		buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid);
+	} else {
+		buf->elem[0].e.sw_resp =
+			cpu_to_le16(local_lag->pf->hw.port_info->sw_id);
+	}
+
+	status = ice_aq_alloc_free_res(&local_lag->pf->hw, 1, buf, buf_len,
+				       ice_aqc_opc_alloc_res, NULL);
+	if (status)
+		dev_err(ice_pf_to_dev(local_lag->pf), "Error subscribing to SWID 0x%04X\n",
+			local_lag->bond_swid);
+
+	kfree(buf);
+
+	/* Configure port param SWID to correct value */
+	if (link)
+		swid = primary_swid;
+	else
+		swid = local_lag->pf->hw.port_info->sw_id;
+
+	cmd = &desc.params.set_port_params;
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params);
+
+	cmd->swid = cpu_to_le16(ICE_AQC_PORT_SWID_VALID | swid);
+	status = ice_aq_send_cmd(&local_lag->pf->hw, &desc, NULL, 0, NULL);
+	if (status)
+		dev_err(ice_pf_to_dev(local_lag->pf), "Error setting SWID in port params %d\n",
+			status);
 }
 
 /**
@@ -504,6 +1052,38 @@ static void ice_lag_primary_swid(struct ice_lag *lag, bool link)
  */
 static void ice_lag_add_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
 {
+	u16 num_vsi, rule_buf_sz, vsi_list_id, event_vsi_num, prim_vsi_idx;
+	struct ice_sw_rule_vsi_list *s_rule = NULL;
+	struct device *dev;
+
+	num_vsi = 1;
+
+	dev = ice_pf_to_dev(lag->pf);
+	event_vsi_num = event_pf->vsi[0]->vsi_num;
+	prim_vsi_idx = lag->pf->vsi[0]->idx;
+
+	if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN,
+				     prim_vsi_idx, &vsi_list_id)) {
+		dev_warn(dev, "Could not locate prune list when setting up SRIOV LAG\n");
+		return;
+	}
+
+	rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi);
+	s_rule = kzalloc(rule_buf_sz, GFP_KERNEL);
+	if (!s_rule) {
+		dev_warn(dev, "Error allocating space for prune list when configuring SRIOV LAG\n");
+		return;
+	}
+
+	s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_PRUNE_LIST_SET);
+	s_rule->index = cpu_to_le16(vsi_list_id);
+	s_rule->number_vsi = cpu_to_le16(num_vsi);
+	s_rule->vsi[0] = cpu_to_le16(event_vsi_num);
+
+	if (ice_aq_sw_rules(&event_pf->hw, s_rule, rule_buf_sz, 1,
+			    ice_aqc_opc_update_sw_rules, NULL))
+		dev_warn(dev, "Error adding VSI prune list\n");
+	kfree(s_rule);
 }
 
 /**
@@ -513,6 +1093,39 @@ static void ice_lag_add_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
  */
 static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
 {
+	u16 num_vsi, vsi_num, vsi_idx, rule_buf_sz, vsi_list_id;
+	struct ice_sw_rule_vsi_list *s_rule = NULL;
+	struct device *dev;
+
+	num_vsi = 1;
+
+	dev = ice_pf_to_dev(lag->pf);
+	vsi_num = event_pf->vsi[0]->vsi_num;
+	vsi_idx = lag->pf->vsi[0]->idx;
+
+	if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN,
+				     vsi_idx, &vsi_list_id)) {
+		dev_warn(dev, "Could not locate prune list when unwinding SRIOV LAG\n");
+		return;
+	}
+
+	rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi);
+	s_rule = kzalloc(rule_buf_sz, GFP_KERNEL);
+	if (!s_rule) {
+		dev_warn(dev, "Error allocating prune list when unwinding SRIOV LAG\n");
+		return;
+	}
+
+	s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_PRUNE_LIST_CLEAR);
+	s_rule->index = cpu_to_le16(vsi_list_id);
+	s_rule->number_vsi = cpu_to_le16(num_vsi);
+	s_rule->vsi[0] = cpu_to_le16(vsi_num);
+
+	if (ice_aq_sw_rules(&event_pf->hw, (struct ice_aqc_sw_rules *)s_rule,
+			    rule_buf_sz, 1, ice_aqc_opc_update_sw_rules, NULL))
+		dev_warn(dev, "Error clearing VSI prune list\n");
+
+	kfree(s_rule);
 }
 
 /**
@@ -539,8 +1152,6 @@ static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
  * ice_lag_changeupper_event - handle LAG changeupper event
  * @lag: LAG info struct
  * @ptr: opaque pointer data
- *
- * ptr is to be cast into netdev_notifier_changeupper_info
  */
 static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 {
@@ -600,6 +1211,40 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
  */
 static void ice_lag_monitor_link(struct ice_lag *lag, void *ptr)
 {
+	struct netdev_notifier_changeupper_info *info;
+	struct ice_hw *prim_hw, *active_hw;
+	struct net_device *event_netdev;
+	struct ice_pf *pf;
+	u8 prim_port;
+
+	if (!lag->primary)
+		return;
+
+	event_netdev = netdev_notifier_info_to_dev(ptr);
+	if (!netif_is_same_ice(lag->pf, event_netdev))
+		return;
+
+	pf = lag->pf;
+	prim_hw = &pf->hw;
+	prim_port = prim_hw->port_info->lport;
+
+	info = (struct netdev_notifier_changeupper_info *)ptr;
+	if (info->upper_dev != lag->upper_netdev)
+		return;
+
+	if (!info->linking) {
+		/* Since there are only two interfaces allowed in SRIOV+LAG, if
+		 * one port is leaving, then nodes need to be on primary
+		 * interface.
+		 */
+		if (prim_port != lag->active_port &&
+		    lag->active_port != ICE_LAG_INVALID_PORT) {
+			active_hw = ice_lag_find_hw_by_lport(lag,
+							     lag->active_port);
+			ice_lag_reclaim_vf_nodes(lag, active_hw);
+			lag->active_port = ICE_LAG_INVALID_PORT;
+		}
+	}
 }
 
 /**
@@ -612,6 +1257,67 @@ static void ice_lag_monitor_link(struct ice_lag *lag, void *ptr)
  */
 static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 {
+	struct net_device *event_netdev, *event_upper;
+	struct netdev_notifier_bonding_info *info;
+	struct netdev_bonding_info *bonding_info;
+	struct ice_netdev_priv *event_np;
+	struct ice_pf *pf, *event_pf;
+	u8 prim_port, event_port;
+
+	if (!lag->primary)
+		return;
+
+	pf = lag->pf;
+	if (!pf)
+		return;
+
+	event_netdev = netdev_notifier_info_to_dev(ptr);
+	rcu_read_lock();
+	event_upper = netdev_master_upper_dev_get_rcu(event_netdev);
+	rcu_read_unlock();
+	if (!netif_is_ice(event_netdev) || event_upper != lag->upper_netdev)
+		return;
+
+	event_np = netdev_priv(event_netdev);
+	event_pf = event_np->vsi->back;
+	event_port = event_pf->hw.port_info->lport;
+	prim_port = pf->hw.port_info->lport;
+
+	info = (struct netdev_notifier_bonding_info *)ptr;
+	bonding_info = &info->bonding_info;
+
+	if (!bonding_info->slave.state) {
+		/* if no port is currently active, then nodes and filters exist
+		 * on primary port, check if we need to move them
+		 */
+		if (lag->active_port == ICE_LAG_INVALID_PORT) {
+			if (event_port != prim_port)
+				ice_lag_move_vf_nodes(lag, prim_port,
+						      event_port);
+			lag->active_port = event_port;
+			return;
+		}
+
+		/* active port is already set and is current event port */
+		if (lag->active_port == event_port)
+			return;
+		/* new active port */
+		ice_lag_move_vf_nodes(lag, lag->active_port, event_port);
+		lag->active_port = event_port;
+	} else {
+		/* port not set as currently active (e.g. new active port
+		 * has already claimed the nodes and filters
+		 */
+		if (lag->active_port != event_port)
+			return;
+		/* This is the case when neither port is active (both link down)
+		 * Link down on the bond - set active port to invalid and move
+		 * nodes and filters back to primary if not already there
+		 */
+		if (event_port != prim_port)
+			ice_lag_move_vf_nodes(lag, event_port, prim_port);
+		lag->active_port = ICE_LAG_INVALID_PORT;
+	}
 }
 
 /**
@@ -622,6 +1328,68 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 static bool
 ice_lag_chk_comp(struct ice_lag *lag, void *ptr)
 {
+	struct net_device *event_netdev, *event_upper;
+	struct netdev_notifier_bonding_info *info;
+	struct netdev_bonding_info *bonding_info;
+	struct list_head *tmp;
+	int count = 0;
+
+	if (!lag->primary)
+		return true;
+
+	event_netdev = netdev_notifier_info_to_dev(ptr);
+	rcu_read_lock();
+	event_upper = netdev_master_upper_dev_get_rcu(event_netdev);
+	rcu_read_unlock();
+	if (event_upper != lag->upper_netdev)
+		return true;
+
+	info = (struct netdev_notifier_bonding_info *)ptr;
+	bonding_info = &info->bonding_info;
+	lag->bond_mode = bonding_info->master.bond_mode;
+	if (lag->bond_mode != BOND_MODE_ACTIVEBACKUP) {
+		netdev_info(lag->netdev, "Bond Mode not ACTIVE-BACKUP\n");
+		return false;
+	}
+
+	list_for_each(tmp, lag->netdev_head) {
+		struct ice_dcbx_cfg *dcb_cfg, *peer_dcb_cfg;
+		struct ice_lag_netdev_list *entry;
+		struct ice_netdev_priv *peer_np;
+		struct net_device *peer_netdev;
+		struct ice_vsi *vsi, *peer_vsi;
+
+		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
+		peer_netdev = entry->netdev;
+		if (!netif_is_ice(peer_netdev)) {
+			netdev_info(lag->netdev, "Found non-ice netdev in LAG\n");
+			return false;
+		}
+
+		count++;
+		if (count > 2) {
+			netdev_info(lag->netdev, "Found more than two netdevs in LAG\n");
+			return false;
+		}
+
+		peer_np = netdev_priv(peer_netdev);
+		vsi = ice_get_main_vsi(lag->pf);
+		peer_vsi = peer_np->vsi;
+		if (lag->pf->pdev->bus != peer_vsi->back->pdev->bus ||
+		    lag->pf->pdev->slot != peer_vsi->back->pdev->slot) {
+			netdev_info(lag->netdev, "Found netdev on different device in LAG\n");
+			return false;
+		}
+
+		dcb_cfg = &vsi->port_info->qos_cfg.local_dcbx_cfg;
+		peer_dcb_cfg = &peer_vsi->port_info->qos_cfg.local_dcbx_cfg;
+		if (memcmp(dcb_cfg, peer_dcb_cfg,
+			   sizeof(struct ice_dcbx_cfg))) {
+			netdev_info(lag->netdev, "Found netdev with different DCB config in LAG\n");
+			return false;
+		}
+	}
+
 	return true;
 }
 
@@ -856,17 +1624,40 @@ static void ice_unregister_lag_handler(struct ice_lag *lag)
 /**
  * ice_create_lag_recipe
  * @hw: pointer to HW struct
+ * @rid: pointer to u16 to pass back recipe index
  * @base_recipe: recipe to base the new recipe on
  * @prio: priority for new recipe
  *
  * function returns 0 on error
  */
-static u16 ice_create_lag_recipe(struct ice_hw *hw, const u8 *base_recipe,
-				 u8 prio)
+static int ice_create_lag_recipe(struct ice_hw *hw, u16 *rid,
+				 const u8 *base_recipe, u8 prio)
 {
-	u16 rid = 0;
+	struct ice_aqc_recipe_data_elem *new_rcp;
+	int err;
+
+	err = ice_alloc_recipe(hw, rid);
+	if (err)
+		return err;
+
+	new_rcp = kzalloc(ICE_RECIPE_LEN * ICE_MAX_NUM_RECIPES, GFP_KERNEL);
+	if (!new_rcp)
+		return -ENOMEM;
+
+	memcpy(new_rcp, base_recipe, ICE_RECIPE_LEN);
+	new_rcp->content.act_ctrl_fwd_priority = prio;
+	new_rcp->content.rid = *rid | ICE_AQ_RECIPE_ID_IS_ROOT;
+	new_rcp->recipe_indx = *rid;
+	bitmap_zero((unsigned long *)new_rcp->recipe_bitmap,
+		    ICE_MAX_NUM_RECIPES);
+	set_bit(*rid, (unsigned long *)new_rcp->recipe_bitmap);
 
-	return rid;
+	err = ice_aq_add_recipe(hw, new_rcp, 1, NULL);
+	if (err)
+		*rid = 0;
+
+	kfree(new_rcp);
+	return err;
 }
 
 /**
@@ -881,7 +1672,8 @@ int ice_init_lag(struct ice_pf *pf)
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_lag *lag;
 	struct ice_vsi *vsi;
-	int err;
+	u64 recipe_bits = 0;
+	int n, err;
 
 	ice_lag_init_feature_support_flag(pf);
 
@@ -900,6 +1692,7 @@ int ice_init_lag(struct ice_pf *pf)
 	lag->pf = pf;
 	lag->netdev = vsi->netdev;
 	lag->role = ICE_LAG_NONE;
+	lag->active_port = ICE_LAG_INVALID_PORT;
 	lag->bonded = false;
 	lag->upper_netdev = NULL;
 	lag->notif_block.notifier_call = NULL;
@@ -910,10 +1703,23 @@ int ice_init_lag(struct ice_pf *pf)
 		goto lag_error;
 	}
 
-	lag->pf_recipe = ice_create_lag_recipe(&pf->hw, ice_dflt_vsi_rcp, 1);
-	if (!lag->pf_recipe) {
-		err = -EINVAL;
+	err = ice_create_lag_recipe(&pf->hw, &lag->pf_recipe, ice_dflt_vsi_rcp,
+				    1);
+	if (err)
 		goto lag_error;
+
+	/* associate recipes to profiles */
+	for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) {
+		err = ice_aq_get_recipe_to_profile(&pf->hw, n,
+						   (u8 *)&recipe_bits, NULL);
+		if (err)
+			continue;
+
+		if (recipe_bits & BIT(ICE_SW_LKUP_DFLT)) {
+			recipe_bits |= BIT(lag->pf_recipe);
+			ice_aq_map_recipe_to_profile(&pf->hw, n,
+						     (u8 *)&recipe_bits, NULL);
+		}
 	}
 
 	ice_display_lag_info(lag);
-- 
GitLab


From ba789fb45697e98a3fce9d0f26e41067a65a8a05 Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 20 Jun 2023 15:18:51 -0700
Subject: [PATCH 0521/1806] ice: support non-standard teardown of bond
 interface

Code for supporting removal of the PF driver (NETDEV_UNREGISTER) events for
both when the bond has the primary interface as active and when failed over
to thew secondary interface.

Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lag.c | 47 ++++++++++++++++++++----
 1 file changed, 40 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index f054bf6181dad..33aedbc506a0e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -1190,15 +1190,16 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 		if (!primary_lag && lag->primary)
 			primary_lag = lag;
 
-		if (primary_lag) {
-			if (!lag->primary) {
-				ice_lag_set_swid(0, lag, false);
-			} else {
+		if (!lag->primary) {
+			ice_lag_set_swid(0, lag, false);
+		} else {
+			if (primary_lag && lag->primary) {
 				ice_lag_primary_swid(lag, false);
 				ice_lag_del_prune_list(primary_lag, lag->pf);
 			}
-			ice_lag_cfg_cp_fltr(lag, false);
 		}
+		/* remove filter for control packets */
+		ice_lag_cfg_cp_fltr(lag, false);
 	}
 }
 
@@ -1401,6 +1402,38 @@ ice_lag_chk_comp(struct ice_lag *lag, void *ptr)
 static void
 ice_lag_unregister(struct ice_lag *lag, struct net_device *event_netdev)
 {
+	struct ice_netdev_priv *np;
+	struct ice_pf *event_pf;
+	struct ice_lag *p_lag;
+
+	p_lag = ice_lag_find_primary(lag);
+	np = netdev_priv(event_netdev);
+	event_pf = np->vsi->back;
+
+	if (p_lag) {
+		if (p_lag->active_port != p_lag->pf->hw.port_info->lport &&
+		    p_lag->active_port != ICE_LAG_INVALID_PORT) {
+			struct ice_hw *active_hw;
+
+			active_hw = ice_lag_find_hw_by_lport(lag,
+							     p_lag->active_port);
+			if (active_hw)
+				ice_lag_reclaim_vf_nodes(p_lag, active_hw);
+			lag->active_port = ICE_LAG_INVALID_PORT;
+		}
+	}
+
+	/* primary processing for primary */
+	if (lag->primary && lag->netdev == event_netdev)
+		ice_lag_primary_swid(lag, false);
+
+	/* primary processing for secondary */
+	if (lag->primary && lag->netdev != event_netdev)
+		ice_lag_del_prune_list(lag, event_pf);
+
+	/* secondary processing for secondary */
+	if (!lag->primary && lag->netdev == event_netdev)
+		ice_lag_set_swid(0, lag, false);
 }
 
 /**
@@ -1470,8 +1503,8 @@ static void ice_lag_process_event(struct work_struct *work)
 	case NETDEV_UNREGISTER:
 		if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) {
 			netdev = lag_work->info.bonding_info.info.dev;
-			if (netdev == lag_work->lag->netdev &&
-			    lag_work->lag->bonded)
+			if ((netdev == lag_work->lag->netdev ||
+			     lag_work->lag->primary) && lag_work->lag->bonded)
 				ice_lag_unregister(lag_work->lag, netdev);
 		}
 		break;
-- 
GitLab


From bf65da2eb279f27d6933e11a713a55fe49e71671 Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 20 Jun 2023 15:18:52 -0700
Subject: [PATCH 0522/1806] ice: enforce interface eligibility and add
 messaging for SRIOV LAG

Implement checks on what interfaces are eligible for supporting SRIOV VFs
when a member of an aggregate interface.

Implement unwind path for interfaces that become ineligible.

checks for the SRIOV LAG feature bit wrap most of the functional code for
manipulating resources that apply to this feature.  Utilize this bit
to track compliant aggregates.  Also flag any new entries into the
aggregate as not supporting SRIOV LAG for the time they are in the
non-compliant aggregate.

Once an aggregate has been flagged as non-compliant, only unpopulating the
aggregate and re-populating it will return SRIOV LAG functionality.

Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lag.c | 89 ++++++++++++++++++++++--
 1 file changed, 84 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 33aedbc506a0e..fecc77279647a 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -889,6 +889,7 @@ static void ice_lag_link(struct ice_lag *lag)
 
 	lag->bonded = true;
 	lag->role = ICE_LAG_UNSET;
+	netdev_info(lag->netdev, "Shared SR-IOV resources in bond are active\n");
 }
 
 /**
@@ -1333,6 +1334,7 @@ ice_lag_chk_comp(struct ice_lag *lag, void *ptr)
 	struct netdev_notifier_bonding_info *info;
 	struct netdev_bonding_info *bonding_info;
 	struct list_head *tmp;
+	struct device *dev;
 	int count = 0;
 
 	if (!lag->primary)
@@ -1345,11 +1347,21 @@ ice_lag_chk_comp(struct ice_lag *lag, void *ptr)
 	if (event_upper != lag->upper_netdev)
 		return true;
 
+	dev = ice_pf_to_dev(lag->pf);
+
+	/* only supporting switchdev mode for SRIOV VF LAG.
+	 * primary interface has to be in switchdev mode
+	 */
+	if (!ice_is_switchdev_running(lag->pf)) {
+		dev_info(dev, "Primary interface not in switchdev mode - VF LAG disabled\n");
+		return false;
+	}
+
 	info = (struct netdev_notifier_bonding_info *)ptr;
 	bonding_info = &info->bonding_info;
 	lag->bond_mode = bonding_info->master.bond_mode;
 	if (lag->bond_mode != BOND_MODE_ACTIVEBACKUP) {
-		netdev_info(lag->netdev, "Bond Mode not ACTIVE-BACKUP\n");
+		dev_info(dev, "Bond Mode not ACTIVE-BACKUP - VF LAG disabled\n");
 		return false;
 	}
 
@@ -1359,17 +1371,19 @@ ice_lag_chk_comp(struct ice_lag *lag, void *ptr)
 		struct ice_netdev_priv *peer_np;
 		struct net_device *peer_netdev;
 		struct ice_vsi *vsi, *peer_vsi;
+		struct ice_pf *peer_pf;
 
 		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
 		peer_netdev = entry->netdev;
 		if (!netif_is_ice(peer_netdev)) {
-			netdev_info(lag->netdev, "Found non-ice netdev in LAG\n");
+			dev_info(dev, "Found %s non-ice netdev in LAG - VF LAG disabled\n",
+				 netdev_name(peer_netdev));
 			return false;
 		}
 
 		count++;
 		if (count > 2) {
-			netdev_info(lag->netdev, "Found more than two netdevs in LAG\n");
+			dev_info(dev, "Found more than two netdevs in LAG - VF LAG disabled\n");
 			return false;
 		}
 
@@ -1378,7 +1392,8 @@ ice_lag_chk_comp(struct ice_lag *lag, void *ptr)
 		peer_vsi = peer_np->vsi;
 		if (lag->pf->pdev->bus != peer_vsi->back->pdev->bus ||
 		    lag->pf->pdev->slot != peer_vsi->back->pdev->slot) {
-			netdev_info(lag->netdev, "Found netdev on different device in LAG\n");
+			dev_info(dev, "Found %s on different device in LAG - VF LAG disabled\n",
+				 netdev_name(peer_netdev));
 			return false;
 		}
 
@@ -1386,7 +1401,15 @@ ice_lag_chk_comp(struct ice_lag *lag, void *ptr)
 		peer_dcb_cfg = &peer_vsi->port_info->qos_cfg.local_dcbx_cfg;
 		if (memcmp(dcb_cfg, peer_dcb_cfg,
 			   sizeof(struct ice_dcbx_cfg))) {
-			netdev_info(lag->netdev, "Found netdev with different DCB config in LAG\n");
+			dev_info(dev, "Found %s with different DCB in LAG - VF LAG disabled\n",
+				 netdev_name(peer_netdev));
+			return false;
+		}
+
+		peer_pf = peer_vsi->back;
+		if (test_bit(ICE_FLAG_FW_LLDP_AGENT, peer_pf->flags)) {
+			dev_warn(dev, "Found %s with FW LLDP agent active - VF LAG disabled\n",
+				 netdev_name(peer_netdev));
 			return false;
 		}
 	}
@@ -1459,6 +1482,58 @@ ice_lag_monitor_rdma(struct ice_lag *lag, void *ptr)
 		ice_set_rdma_cap(lag->pf);
 }
 
+/**
+ * ice_lag_chk_disabled_bond - monitor interfaces entering/leaving disabled bond
+ * @lag: lag info struct
+ * @ptr: opaque data containing event
+ *
+ * as interfaces enter a bond - determine if the bond is currently
+ * SRIOV LAG compliant and flag if not.  As interfaces leave the
+ * bond, reset their compliant status.
+ */
+static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct ice_lag *prim_lag;
+
+	if (netdev != lag->netdev)
+		return;
+
+	if (info->linking) {
+		prim_lag = ice_lag_find_primary(lag);
+		if (prim_lag &&
+		    !ice_is_feature_supported(prim_lag->pf, ICE_F_SRIOV_LAG)) {
+			ice_clear_feature_support(lag->pf, ICE_F_SRIOV_LAG);
+			netdev_info(netdev, "Interface added to non-compliant SRIOV LAG aggregate\n");
+		}
+	} else {
+		ice_lag_init_feature_support_flag(lag->pf);
+	}
+}
+
+/**
+ * ice_lag_disable_sriov_bond - set members of bond as not supporting SRIOV LAG
+ * @lag: primary interfaces lag struct
+ */
+static void ice_lag_disable_sriov_bond(struct ice_lag *lag)
+{
+	struct ice_lag_netdev_list *entry;
+	struct ice_netdev_priv *np;
+	struct net_device *netdev;
+	struct list_head *tmp;
+	struct ice_pf *pf;
+
+	list_for_each(tmp, lag->netdev_head) {
+		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
+		netdev = entry->netdev;
+		np = netdev_priv(netdev);
+		pf = np->vsi->back;
+
+		ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
+	}
+}
+
 /**
  * ice_lag_process_event - process a task assigned to the lag_wq
  * @work: pointer to work_struct
@@ -1480,6 +1555,7 @@ static void ice_lag_process_event(struct work_struct *work)
 	switch (lag_work->event) {
 	case NETDEV_CHANGEUPPER:
 		info = &lag_work->info.changeupper_info;
+		ice_lag_chk_disabled_bond(lag_work->lag, info);
 		if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) {
 			ice_lag_monitor_link(lag_work->lag, info);
 			ice_lag_changeupper_event(lag_work->lag, info);
@@ -1491,6 +1567,9 @@ static void ice_lag_process_event(struct work_struct *work)
 		if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) {
 			if (!ice_lag_chk_comp(lag_work->lag,
 					      &lag_work->info.bonding_info)) {
+				netdev = lag_work->info.bonding_info.info.dev;
+				ice_lag_disable_sriov_bond(lag_work->lag);
+				ice_lag_unregister(lag_work->lag, netdev);
 				goto lag_cleanup;
 			}
 			ice_lag_monitor_active(lag_work->lag,
-- 
GitLab


From ab2ed5d77ab9c438d1ca8ebb230cf8eb699c163f Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 20 Jun 2023 15:18:53 -0700
Subject: [PATCH 0523/1806] ice: enforce no DCB config changing when in bond

To support SRIOV LAG, the driver cannot allow changes to an interface's DCB
configuration when in a bond.  This would break the ability to modify
interfaces Tx scheduling for fail-over interfaces.

Block kernel generated DCB config events when in a bond.

Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_dcb_nl.c | 50 +++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
index 3eb01731e496b..e1fbc6de452df 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
@@ -70,6 +70,11 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets)
 	    !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
 		return -EINVAL;
 
+	if (pf->lag && pf->lag->bonded) {
+		netdev_err(netdev, "DCB changes not allowed when in a bond\n");
+		return -EINVAL;
+	}
+
 	new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg;
 
 	mutex_lock(&pf->tc_mutex);
@@ -170,6 +175,11 @@ static u8 ice_dcbnl_setdcbx(struct net_device *netdev, u8 mode)
 	if (mode == pf->dcbx_cap)
 		return ICE_DCB_NO_HW_CHG;
 
+	if (pf->lag && pf->lag->bonded) {
+		netdev_err(netdev, "DCB changes not allowed when in a bond\n");
+		return ICE_DCB_NO_HW_CHG;
+	}
+
 	qos_cfg = &pf->hw.port_info->qos_cfg;
 
 	/* DSCP configuration is not DCBx negotiated */
@@ -261,6 +271,11 @@ static int ice_dcbnl_setpfc(struct net_device *netdev, struct ieee_pfc *pfc)
 	    !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
 		return -EINVAL;
 
+	if (pf->lag && pf->lag->bonded) {
+		netdev_err(netdev, "DCB changes not allowed when in a bond\n");
+		return -EINVAL;
+	}
+
 	mutex_lock(&pf->tc_mutex);
 
 	new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg;
@@ -323,6 +338,11 @@ static void ice_dcbnl_set_pfc_cfg(struct net_device *netdev, int prio, u8 set)
 	if (prio >= ICE_MAX_USER_PRIORITY)
 		return;
 
+	if (pf->lag && pf->lag->bonded) {
+		netdev_err(netdev, "DCB changes not allowed when in a bond\n");
+		return;
+	}
+
 	new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg;
 
 	new_cfg->pfc.pfccap = pf->hw.func_caps.common_cap.maxtc;
@@ -379,6 +399,11 @@ static u8 ice_dcbnl_setstate(struct net_device *netdev, u8 state)
 	    !(pf->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
 		return ICE_DCB_NO_HW_CHG;
 
+	if (pf->lag && pf->lag->bonded) {
+		netdev_err(netdev, "DCB changes not allowed when in a bond\n");
+		return ICE_DCB_NO_HW_CHG;
+	}
+
 	/* Nothing to do */
 	if (!!state == test_bit(ICE_FLAG_DCB_ENA, pf->flags))
 		return ICE_DCB_NO_HW_CHG;
@@ -451,6 +476,11 @@ ice_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 	if (tc >= ICE_MAX_TRAFFIC_CLASS)
 		return;
 
+	if (pf->lag && pf->lag->bonded) {
+		netdev_err(netdev, "DCB changes not allowed when in a bond\n");
+		return;
+	}
+
 	new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg;
 
 	/* prio_type, bwg_id and bw_pct per UP are not supported */
@@ -505,6 +535,11 @@ ice_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int pgid, u8 bw_pct)
 	if (pgid >= ICE_MAX_TRAFFIC_CLASS)
 		return;
 
+	if (pf->lag && pf->lag->bonded) {
+		netdev_err(netdev, "DCB changes not allowed when in a bond\n");
+		return;
+	}
+
 	new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg;
 
 	new_cfg->etscfg.tcbwtable[pgid] = bw_pct;
@@ -725,6 +760,11 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app)
 		return -EINVAL;
 	}
 
+	if (pf->lag && pf->lag->bonded) {
+		netdev_err(netdev, "DCB changes not allowed when in a bond\n");
+		return -EINVAL;
+	}
+
 	max_tc = pf->hw.func_caps.common_cap.maxtc;
 	if (app->priority >= max_tc) {
 		netdev_err(netdev, "TC %d out of range, max TC %d\n",
@@ -836,6 +876,11 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app)
 		return -EINVAL;
 	}
 
+	if (pf->lag && pf->lag->bonded) {
+		netdev_err(netdev, "DCB changes not allowed when in a bond\n");
+		return -EINVAL;
+	}
+
 	mutex_lock(&pf->tc_mutex);
 	old_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
 
@@ -937,6 +982,11 @@ static u8 ice_dcbnl_cee_set_all(struct net_device *netdev)
 	    !(pf->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
 		return ICE_DCB_NO_HW_CHG;
 
+	if (pf->lag && pf->lag->bonded) {
+		netdev_err(netdev, "DCB changes not allowed when in a bond\n");
+		return ICE_DCB_NO_HW_CHG;
+	}
+
 	new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg;
 
 	mutex_lock(&pf->tc_mutex);
-- 
GitLab


From 3579aa86fb4046a378f7d68583cfb7f62e0feabd Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 20 Jun 2023 15:18:54 -0700
Subject: [PATCH 0524/1806] ice: update reset path for SRIOV LAG support

Add code to rebuild the LAG resources when rebuilding the state of the
interface after a reset.

Also added in a function for building per-queue information into the buffer
used to configure VF queues for LAG fail-over.  This improves code reuse.

Due to differences in timing per interface for recovering from a reset, add
in the ability to retry on non-local dependencies where needed.

Reviewed-by: Daniel Machon <daniel.machon@microchip.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lag.c  | 231 +++++++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_lag.h  |   3 +
 drivers/net/ethernet/intel/ice/ice_main.c |  14 +-
 3 files changed, 244 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index fecc77279647a..36b7044717e81 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -961,6 +961,7 @@ static void ice_lag_link_unlink(struct ice_lag *lag, void *ptr)
  * @link: Is this a linking activity
  *
  * If link is false, then primary_swid should be expected to not be valid
+ * This function should never be called in interrupt context.
  */
 static void
 ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
@@ -970,7 +971,7 @@ ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
 	struct ice_aqc_set_port_params *cmd;
 	struct ice_aq_desc desc;
 	u16 buf_len, swid;
-	int status;
+	int status, i;
 
 	buf_len = struct_size(buf, elem, 1);
 	buf = kzalloc(buf_len, GFP_KERNEL);
@@ -1021,7 +1022,20 @@ ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params);
 
 	cmd->swid = cpu_to_le16(ICE_AQC_PORT_SWID_VALID | swid);
-	status = ice_aq_send_cmd(&local_lag->pf->hw, &desc, NULL, 0, NULL);
+	/* If this is happening in reset context, it is possible that the
+	 * primary interface has not finished setting its SWID to SHARED
+	 * yet.  Allow retries to account for this timing issue between
+	 * interfaces.
+	 */
+	for (i = 0; i < ICE_LAG_RESET_RETRIES; i++) {
+		status = ice_aq_send_cmd(&local_lag->pf->hw, &desc, NULL, 0,
+					 NULL);
+		if (!status)
+			break;
+
+		usleep_range(1000, 2000);
+	}
+
 	if (status)
 		dev_err(ice_pf_to_dev(local_lag->pf), "Error setting SWID in port params %d\n",
 			status);
@@ -1029,7 +1043,7 @@ ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
 
 /**
  * ice_lag_primary_swid - set/clear the SHARED attrib of primary's SWID
- * @lag: primary interfaces lag struct
+ * @lag: primary interface's lag struct
  * @link: is this a linking activity
  *
  * Implement setting primary SWID as shared using 0x020B
@@ -1772,6 +1786,135 @@ static int ice_create_lag_recipe(struct ice_hw *hw, u16 *rid,
 	return err;
 }
 
+/**
+ * ice_lag_move_vf_nodes_tc_sync - move a VF's nodes for a tc during reset
+ * @lag: primary interfaces lag struct
+ * @dest_hw: HW struct for destination's interface
+ * @vsi_num: VSI index in PF space
+ * @tc: traffic class to move
+ */
+static void
+ice_lag_move_vf_nodes_tc_sync(struct ice_lag *lag, struct ice_hw *dest_hw,
+			      u16 vsi_num, u8 tc)
+{
+	u16 numq, valq, buf_size, num_moved, qbuf_size;
+	struct device *dev = ice_pf_to_dev(lag->pf);
+	struct ice_aqc_cfg_txqs_buf *qbuf;
+	struct ice_aqc_move_elem *buf;
+	struct ice_sched_node *n_prt;
+	__le32 teid, parent_teid;
+	struct ice_vsi_ctx *ctx;
+	struct ice_hw *hw;
+	u32 tmp_teid;
+
+	hw = &lag->pf->hw;
+	ctx = ice_get_vsi_ctx(hw, vsi_num);
+	if (!ctx) {
+		dev_warn(dev, "LAG rebuild failed after reset due to VSI Context failure\n");
+		return;
+	}
+
+	if (!ctx->sched.vsi_node[tc])
+		return;
+
+	numq = ctx->num_lan_q_entries[tc];
+	teid = ctx->sched.vsi_node[tc]->info.node_teid;
+	tmp_teid = le32_to_cpu(teid);
+	parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid;
+
+	if (!tmp_teid || !numq)
+		return;
+
+	if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true))
+		dev_dbg(dev, "Problem suspending traffic during reset rebuild\n");
+
+	/* reconfig queues for new port */
+	qbuf_size = struct_size(qbuf, queue_info, numq);
+	qbuf = kzalloc(qbuf_size, GFP_KERNEL);
+	if (!qbuf) {
+		dev_warn(dev, "Failure allocating VF queue recfg buffer for reset rebuild\n");
+		goto resume_sync;
+	}
+
+	/* add the per queue info for the reconfigure command buffer */
+	valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc);
+	if (!valq) {
+		dev_warn(dev, "Failure to reconfig queues for LAG reset rebuild\n");
+		goto sync_none;
+	}
+
+	if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, hw->port_info->lport,
+			       dest_hw->port_info->lport, NULL)) {
+		dev_warn(dev, "Failure to configure queues for LAG reset rebuild\n");
+		goto sync_qerr;
+	}
+
+sync_none:
+	kfree(qbuf);
+
+	/* find parent in destination tree */
+	n_prt = ice_lag_get_sched_parent(dest_hw, tc);
+	if (!n_prt)
+		goto resume_sync;
+
+	/* Move node to new parent */
+	buf_size = struct_size(buf, teid, 1);
+	buf = kzalloc(buf_size, GFP_KERNEL);
+	if (!buf) {
+		dev_warn(dev, "Failure to alloc for VF node move in reset rebuild\n");
+		goto resume_sync;
+	}
+
+	buf->hdr.src_parent_teid = parent_teid;
+	buf->hdr.dest_parent_teid = n_prt->info.node_teid;
+	buf->hdr.num_elems = cpu_to_le16(1);
+	buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN;
+	buf->teid[0] = teid;
+
+	if (ice_aq_move_sched_elems(&lag->pf->hw, 1, buf, buf_size, &num_moved,
+				    NULL))
+		dev_warn(dev, "Failure to move VF nodes for LAG reset rebuild\n");
+	else
+		ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]);
+
+	kfree(buf);
+	goto resume_sync;
+
+sync_qerr:
+	kfree(qbuf);
+
+resume_sync:
+	if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false))
+		dev_warn(dev, "Problem restarting traffic for LAG node reset rebuild\n");
+}
+
+/**
+ * ice_lag_move_vf_nodes_sync - move vf nodes to active interface
+ * @lag: primary interfaces lag struct
+ * @dest_hw: lport value for currently active port
+ *
+ * This function is used in a reset context, outside of event handling,
+ * to move the VF nodes to the secondary interface when that interface
+ * is the active interface during a reset rebuild
+ */
+static void
+ice_lag_move_vf_nodes_sync(struct ice_lag *lag, struct ice_hw *dest_hw)
+{
+	struct ice_pf *pf;
+	int i, tc;
+
+	if (!lag->primary || !dest_hw)
+		return;
+
+	pf = lag->pf;
+	ice_for_each_vsi(pf, i)
+		if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF ||
+				   pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL))
+			ice_for_each_traffic_class(tc)
+				ice_lag_move_vf_nodes_tc_sync(lag, dest_hw, i,
+							      tc);
+}
+
 /**
  * ice_init_lag - initialize support for LAG
  * @pf: PF struct
@@ -1873,3 +2016,85 @@ void ice_deinit_lag(struct ice_pf *pf)
 
 	pf->lag = NULL;
 }
+
+/**
+ * ice_lag_rebuild - rebuild lag resources after reset
+ * @pf: pointer to local pf struct
+ *
+ * PF resets are promoted to CORER resets when interface in an aggregate.  This
+ * means that we need to rebuild the PF resources for the interface.  Since
+ * this will happen outside the normal event processing, need to acquire the lag
+ * lock.
+ *
+ * This function will also evaluate the VF resources if this is the primary
+ * interface.
+ */
+void ice_lag_rebuild(struct ice_pf *pf)
+{
+	struct ice_lag_netdev_list ndlist;
+	struct ice_lag *lag, *prim_lag;
+	struct list_head *tmp, *n;
+	u8 act_port, loc_port;
+
+	if (!pf->lag || !pf->lag->bonded)
+		return;
+
+	mutex_lock(&pf->lag_mutex);
+
+	lag = pf->lag;
+	if (lag->primary) {
+		prim_lag = lag;
+	} else {
+		struct ice_lag_netdev_list *nl;
+		struct net_device *tmp_nd;
+
+		INIT_LIST_HEAD(&ndlist.node);
+		rcu_read_lock();
+		for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
+			nl = kzalloc(sizeof(*nl), GFP_KERNEL);
+			if (!nl)
+				break;
+
+			nl->netdev = tmp_nd;
+			list_add(&nl->node, &ndlist.node);
+		}
+		rcu_read_unlock();
+		lag->netdev_head = &ndlist.node;
+		prim_lag = ice_lag_find_primary(lag);
+	}
+
+	if (!prim_lag) {
+		dev_dbg(ice_pf_to_dev(pf), "No primary interface in aggregate, can't rebuild\n");
+		goto lag_rebuild_out;
+	}
+
+	act_port = prim_lag->active_port;
+	loc_port = lag->pf->hw.port_info->lport;
+
+	/* configure SWID for this port */
+	if (lag->primary) {
+		ice_lag_primary_swid(lag, true);
+	} else {
+		ice_lag_set_swid(prim_lag->pf->hw.port_info->sw_id, lag, true);
+		ice_lag_add_prune_list(prim_lag, pf);
+		if (act_port == loc_port)
+			ice_lag_move_vf_nodes_sync(prim_lag, &pf->hw);
+	}
+
+	ice_lag_cfg_cp_fltr(lag, true);
+
+	if (lag->pf_rule_id)
+		if (ice_lag_cfg_dflt_fltr(lag, true))
+			dev_err(ice_pf_to_dev(pf), "Error adding default VSI rule in rebuild\n");
+
+	ice_clear_rdma_cap(pf);
+lag_rebuild_out:
+	list_for_each_safe(tmp, n, &ndlist.node) {
+		struct ice_lag_netdev_list *entry;
+
+		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	mutex_unlock(&pf->lag_mutex);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index df4af5184a75c..18075b82485aa 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -16,6 +16,8 @@ enum ice_lag_role {
 
 #define ICE_LAG_INVALID_PORT 0xFF
 
+#define ICE_LAG_RESET_RETRIES		5
+
 struct ice_pf;
 struct ice_vf;
 
@@ -59,4 +61,5 @@ struct ice_lag_work {
 void ice_lag_move_new_vf_nodes(struct ice_vf *vf);
 int ice_init_lag(struct ice_pf *pf);
 void ice_deinit_lag(struct ice_pf *pf);
+void ice_lag_rebuild(struct ice_pf *pf);
 #endif /* _ICE_LAG_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 7f7728dadcbbf..20d5ed572a8c6 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -636,6 +636,11 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	dev_dbg(dev, "reset_type 0x%x requested\n", reset_type);
 
+	if (pf->lag && pf->lag->bonded && reset_type == ICE_RESET_PFR) {
+		dev_dbg(dev, "PFR on a bonded interface, promoting to CORER\n");
+		reset_type = ICE_RESET_CORER;
+	}
+
 	ice_prepare_for_reset(pf, reset_type);
 
 	/* trigger the reset */
@@ -719,8 +724,13 @@ static void ice_reset_subtask(struct ice_pf *pf)
 	}
 
 	/* No pending resets to finish processing. Check for new resets */
-	if (test_bit(ICE_PFR_REQ, pf->state))
+	if (test_bit(ICE_PFR_REQ, pf->state)) {
 		reset_type = ICE_RESET_PFR;
+		if (pf->lag && pf->lag->bonded) {
+			dev_dbg(ice_pf_to_dev(pf), "PFR on a bonded interface, promoting to CORER\n");
+			reset_type = ICE_RESET_CORER;
+		}
+	}
 	if (test_bit(ICE_CORER_REQ, pf->state))
 		reset_type = ICE_RESET_CORER;
 	if (test_bit(ICE_GLOBR_REQ, pf->state))
@@ -7373,6 +7383,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 	clear_bit(ICE_RESET_FAILED, pf->state);
 
 	ice_plug_aux_dev(pf);
+	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
+		ice_lag_rebuild(pf);
 	return;
 
 err_vsi_rebuild:
-- 
GitLab


From 02ceda65f014e357d4142e9c004f40b3b3d61857 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@nvidia.com>
Date: Tue, 13 Jun 2023 10:42:05 +0300
Subject: [PATCH 0525/1806] net/mlx5: Use shared code for checking lag is
 supported

Move shared function to check lag is supported to lag header file.

Signed-off-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c     |  6 ++----
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 10 ----------
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h | 12 ++++++++++--
 3 files changed, 12 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index edb06fb9bbc52..7909f378dc935 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -36,6 +36,7 @@
 #include <linux/mlx5/vport.h>
 #include "mlx5_core.h"
 #include "devlink.h"
+#include "lag/lag.h"
 
 /* intf dev list mutex */
 static DEFINE_MUTEX(mlx5_intf_mutex);
@@ -587,10 +588,7 @@ static int next_phys_dev_lag(struct device *dev, const void *data)
 	if (!mdev)
 		return 0;
 
-	if (!MLX5_CAP_GEN(mdev, vport_group_manager) ||
-	    !MLX5_CAP_GEN(mdev, lag_master) ||
-	    (MLX5_CAP_GEN(mdev, num_lag_ports) > MLX5_MAX_PORTS ||
-	     MLX5_CAP_GEN(mdev, num_lag_ports) <= 1))
+	if (!mlx5_lag_is_supported(mdev))
 		return 0;
 
 	return _next_phys_dev(mdev, data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index f0a074b2fcdf3..900a18883f280 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1268,16 +1268,6 @@ recheck:
 	mlx5_ldev_put(ldev);
 }
 
-bool mlx5_lag_is_supported(struct mlx5_core_dev *dev)
-{
-	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
-	    !MLX5_CAP_GEN(dev, lag_master) ||
-	    MLX5_CAP_GEN(dev, num_lag_ports) < 2 ||
-	    MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_MAX_PORTS)
-		return false;
-	return true;
-}
-
 void mlx5_lag_add_mdev(struct mlx5_core_dev *dev)
 {
 	int err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index a061b1873e270..481e92f39fe61 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -74,8 +74,6 @@ struct mlx5_lag {
 	struct lag_mpesw	  lag_mpesw;
 };
 
-bool mlx5_lag_is_supported(struct mlx5_core_dev *dev);
-
 static inline struct mlx5_lag *
 mlx5_lag_dev(struct mlx5_core_dev *dev)
 {
@@ -115,4 +113,14 @@ void mlx5_lag_remove_devices(struct mlx5_lag *ldev);
 int mlx5_deactivate_lag(struct mlx5_lag *ldev);
 void mlx5_lag_add_devices(struct mlx5_lag *ldev);
 
+static inline bool mlx5_lag_is_supported(struct mlx5_core_dev *dev)
+{
+	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
+	    !MLX5_CAP_GEN(dev, lag_master) ||
+	    MLX5_CAP_GEN(dev, num_lag_ports) < 2 ||
+	    MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_MAX_PORTS)
+		return false;
+	return true;
+}
+
 #endif /* __MLX5_LAG_H__ */
-- 
GitLab


From 88d162b479815f5d6b6a4ff5fdb07aec9dc6280c Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@nvidia.com>
Date: Thu, 4 May 2023 12:14:00 +0300
Subject: [PATCH 0526/1806] net/mlx5: Devcom, Infrastructure changes

Update devcom infrastructure to be more generic, without
depending on max supported ports definition or a device guid,
and also more encapsulated so callers don't need to pass
the register devcom component id per event call.

Signed-off-by: Eli Cohen <elic@nvidia.com>
Signed-off-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_rep.c  |  21 +-
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   |  36 +-
 .../ethernet/mellanox/mlx5/core/esw/bridge.c  |  22 +-
 .../mellanox/mlx5/core/esw/bridge_mcast.c     |  17 +-
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |   3 +
 .../mellanox/mlx5/core/eswitch_offloads.c     |  47 +-
 .../net/ethernet/mellanox/mlx5/core/lag/lag.c |   2 +-
 .../ethernet/mellanox/mlx5/core/lib/devcom.c  | 448 ++++++++++--------
 .../ethernet/mellanox/mlx5/core/lib/devcom.h  |  74 ++-
 .../net/ethernet/mellanox/mlx5/core/main.c    |  12 +-
 include/linux/mlx5/driver.h                   |   4 +-
 11 files changed, 359 insertions(+), 327 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 152b62138450f..ca4f57f5064f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -399,15 +399,13 @@ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw,
 }
 
 static int mlx5e_sqs2vport_add_peers_rules(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep,
-					   struct mlx5_devcom *devcom,
 					   struct mlx5e_rep_sq *rep_sq, int i)
 {
-	struct mlx5_eswitch *peer_esw = NULL;
 	struct mlx5_flow_handle *flow_rule;
-	int tmp;
+	struct mlx5_devcom_comp_dev *tmp;
+	struct mlx5_eswitch *peer_esw;
 
-	mlx5_devcom_for_each_peer_entry(devcom, MLX5_DEVCOM_ESW_OFFLOADS,
-					peer_esw, tmp) {
+	mlx5_devcom_for_each_peer_entry(esw->devcom, peer_esw, tmp) {
 		u16 peer_rule_idx = MLX5_CAP_GEN(peer_esw->dev, vhca_id);
 		struct mlx5e_rep_sq_peer *sq_peer;
 		int err;
@@ -443,7 +441,6 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
 	struct mlx5_flow_handle *flow_rule;
 	struct mlx5e_rep_priv *rpriv;
 	struct mlx5e_rep_sq *rep_sq;
-	struct mlx5_devcom *devcom;
 	bool devcom_locked = false;
 	int err;
 	int i;
@@ -451,10 +448,10 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
 	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return 0;
 
-	devcom = esw->dev->priv.devcom;
 	rpriv = mlx5e_rep_to_rep_priv(rep);
-	if (mlx5_devcom_comp_is_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS) &&
-	    mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS))
+
+	if (mlx5_devcom_comp_is_ready(esw->devcom) &&
+	    mlx5_devcom_for_each_peer_begin(esw->devcom))
 		devcom_locked = true;
 
 	for (i = 0; i < sqns_num; i++) {
@@ -477,7 +474,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
 
 		xa_init(&rep_sq->sq_peer);
 		if (devcom_locked) {
-			err = mlx5e_sqs2vport_add_peers_rules(esw, rep, devcom, rep_sq, i);
+			err = mlx5e_sqs2vport_add_peers_rules(esw, rep, rep_sq, i);
 			if (err) {
 				mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule);
 				xa_destroy(&rep_sq->sq_peer);
@@ -490,7 +487,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
 	}
 
 	if (devcom_locked)
-		mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+		mlx5_devcom_for_each_peer_end(esw->devcom);
 
 	return 0;
 
@@ -498,7 +495,7 @@ out_err:
 	mlx5e_sqs2vport_stop(esw, rep);
 
 	if (devcom_locked)
-		mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+		mlx5_devcom_for_each_peer_end(esw->devcom);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 8d0a3f69693e1..22bc886206533 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1668,11 +1668,10 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro
 {
 	struct mlx5e_priv *out_priv, *route_priv;
 	struct mlx5_core_dev *route_mdev;
-	struct mlx5_devcom *devcom;
+	struct mlx5_devcom_comp_dev *pos;
 	struct mlx5_eswitch *esw;
 	u16 vhca_id;
 	int err;
-	int i;
 
 	out_priv = netdev_priv(out_dev);
 	esw = out_priv->mdev->priv.eswitch;
@@ -1688,10 +1687,8 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro
 		return err;
 
 	rcu_read_lock();
-	devcom = out_priv->mdev->priv.devcom;
 	err = -ENODEV;
-	mlx5_devcom_for_each_peer_entry_rcu(devcom, MLX5_DEVCOM_ESW_OFFLOADS,
-					    esw, i) {
+	mlx5_devcom_for_each_peer_entry_rcu(esw->devcom, esw, pos) {
 		err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport);
 		if (!err)
 			break;
@@ -2031,15 +2028,15 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow)
 {
 	if (mlx5e_is_eswitch_flow(flow)) {
-		struct mlx5_devcom *devcom = flow->priv->mdev->priv.devcom;
+		struct mlx5_devcom_comp_dev *devcom = flow->priv->mdev->priv.eswitch->devcom;
 
-		if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) {
+		if (!mlx5_devcom_for_each_peer_begin(devcom)) {
 			mlx5e_tc_del_fdb_flow(priv, flow);
 			return;
 		}
 
 		mlx5e_tc_del_fdb_peers_flow(flow);
-		mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+		mlx5_devcom_for_each_peer_end(devcom);
 		mlx5e_tc_del_fdb_flow(priv, flow);
 	} else {
 		mlx5e_tc_del_nic_flow(priv, flow);
@@ -4216,8 +4213,7 @@ static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow)
 		flow_flag_test(flow, INGRESS);
 	bool act_is_encap = !!(attr->action &
 			       MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT);
-	bool esw_paired = mlx5_devcom_comp_is_ready(esw_attr->in_mdev->priv.devcom,
-						    MLX5_DEVCOM_ESW_OFFLOADS);
+	bool esw_paired = mlx5_devcom_comp_is_ready(esw_attr->in_mdev->priv.eswitch->devcom);
 
 	if (!esw_paired)
 		return false;
@@ -4471,14 +4467,13 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 		   struct net_device *filter_dev,
 		   struct mlx5e_tc_flow **__flow)
 {
-	struct mlx5_devcom *devcom = priv->mdev->priv.devcom;
+	struct mlx5_devcom_comp_dev *devcom = priv->mdev->priv.eswitch->devcom, *pos;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *in_rep = rpriv->rep;
 	struct mlx5_core_dev *in_mdev = priv->mdev;
 	struct mlx5_eswitch *peer_esw;
 	struct mlx5e_tc_flow *flow;
 	int err;
-	int i;
 
 	flow = __mlx5e_add_fdb_flow(priv, f, flow_flags, filter_dev, in_rep,
 				    in_mdev);
@@ -4490,27 +4485,25 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 		return 0;
 	}
 
-	if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) {
+	if (!mlx5_devcom_for_each_peer_begin(devcom)) {
 		err = -ENODEV;
 		goto clean_flow;
 	}
 
-	mlx5_devcom_for_each_peer_entry(devcom,
-					MLX5_DEVCOM_ESW_OFFLOADS,
-					peer_esw, i) {
+	mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) {
 		err = mlx5e_tc_add_fdb_peer_flow(f, flow, flow_flags, peer_esw);
 		if (err)
 			goto peer_clean;
 	}
 
-	mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	mlx5_devcom_for_each_peer_end(devcom);
 
 	*__flow = flow;
 	return 0;
 
 peer_clean:
 	mlx5e_tc_del_fdb_peers_flow(flow);
-	mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	mlx5_devcom_for_each_peer_end(devcom);
 clean_flow:
 	mlx5e_tc_del_fdb_flow(priv, flow);
 	return err;
@@ -4728,7 +4721,7 @@ int mlx5e_tc_fill_action_stats(struct mlx5e_priv *priv,
 int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		       struct flow_cls_offload *f, unsigned long flags)
 {
-	struct mlx5_devcom *devcom = priv->mdev->priv.devcom;
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 	struct mlx5e_tc_flow *flow;
 	struct mlx5_fc *counter;
@@ -4764,7 +4757,7 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	/* Under multipath it's possible for one rule to be currently
 	 * un-offloaded while the other rule is offloaded.
 	 */
-	if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS))
+	if (esw && !mlx5_devcom_for_each_peer_begin(esw->devcom))
 		goto out;
 
 	if (flow_flag_test(flow, DUP)) {
@@ -4795,7 +4788,8 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	}
 
 no_peer_counter:
-	mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	if (esw)
+		mlx5_devcom_for_each_peer_end(esw->devcom);
 out:
 	flow_stats_update(&f->stats, bytes, packets, 0, lastuse,
 			  FLOW_ACTION_HW_STATS_DELAYED);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index f4fe1daa4afd5..e36294b7ade27 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -652,30 +652,30 @@ mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, u16 esw_owner_vhca_id,
 					 struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
 					 struct mlx5_esw_bridge *bridge)
 {
-	struct mlx5_devcom *devcom = bridge->br_offloads->esw->dev->priv.devcom;
+	struct mlx5_devcom_comp_dev *devcom = bridge->br_offloads->esw->devcom, *pos;
 	struct mlx5_eswitch *tmp, *peer_esw = NULL;
 	static struct mlx5_flow_handle *handle;
-	int i;
 
-	if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS))
+	if (!mlx5_devcom_for_each_peer_begin(devcom))
 		return ERR_PTR(-ENODEV);
 
-	mlx5_devcom_for_each_peer_entry(devcom,
-					MLX5_DEVCOM_ESW_OFFLOADS,
-					tmp, i) {
+	mlx5_devcom_for_each_peer_entry(devcom, tmp, pos) {
 		if (mlx5_esw_is_owner(tmp, vport_num, esw_owner_vhca_id)) {
 			peer_esw = tmp;
 			break;
 		}
 	}
+
 	if (!peer_esw) {
-		mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
-		return ERR_PTR(-ENODEV);
+		handle = ERR_PTR(-ENODEV);
+		goto out;
 	}
 
 	handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id,
 							      bridge, peer_esw);
-	mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+
+out:
+	mlx5_devcom_for_each_peer_end(devcom);
 	return handle;
 }
 
@@ -1391,8 +1391,8 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_ow
 						    mlx5_fc_id(counter), bridge);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
-		esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d)\n",
-			 vport_num, err);
+		esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d,peer=%d)\n",
+			 vport_num, err, peer);
 		goto err_ingress_flow_create;
 	}
 	entry->ingress_handle = handle;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c
index 2455f8b93c1e5..7a01714b37800 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c
@@ -539,30 +539,29 @@ mlx5_esw_bridge_mcast_filter_flow_create(struct mlx5_esw_bridge_port *port)
 static struct mlx5_flow_handle *
 mlx5_esw_bridge_mcast_filter_flow_peer_create(struct mlx5_esw_bridge_port *port)
 {
-	struct mlx5_devcom *devcom = port->bridge->br_offloads->esw->dev->priv.devcom;
+	struct mlx5_devcom_comp_dev *devcom = port->bridge->br_offloads->esw->devcom, *pos;
 	struct mlx5_eswitch *tmp, *peer_esw = NULL;
 	static struct mlx5_flow_handle *handle;
-	int i;
 
-	if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS))
+	if (!mlx5_devcom_for_each_peer_begin(devcom))
 		return ERR_PTR(-ENODEV);
 
-	mlx5_devcom_for_each_peer_entry(devcom,
-					MLX5_DEVCOM_ESW_OFFLOADS,
-					tmp, i) {
+	mlx5_devcom_for_each_peer_entry(devcom, tmp, pos) {
 		if (mlx5_esw_is_owner(tmp, port->vport_num, port->esw_owner_vhca_id)) {
 			peer_esw = tmp;
 			break;
 		}
 	}
+
 	if (!peer_esw) {
-		mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
-		return ERR_PTR(-ENODEV);
+		handle = ERR_PTR(-ENODEV);
+		goto out;
 	}
 
 	handle = mlx5_esw_bridge_mcast_flow_with_esw_create(port, peer_esw);
 
-	mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+out:
+	mlx5_devcom_for_each_peer_end(devcom);
 	return handle;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index ae0dc8a3060d7..6d9378b0bce59 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -354,6 +354,7 @@ struct mlx5_eswitch {
 	}  params;
 	struct blocking_notifier_head n_head;
 	struct xarray paired;
+	struct mlx5_devcom_comp_dev *devcom;
 };
 
 void esw_offloads_disable(struct mlx5_eswitch *esw);
@@ -383,6 +384,7 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw);
 void mlx5_eswitch_disable(struct mlx5_eswitch *esw);
 void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw);
 void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw);
+bool mlx5_esw_offloads_devcom_is_ready(struct mlx5_eswitch *esw);
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 			       u16 vport, const u8 *mac);
 int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
@@ -818,6 +820,7 @@ static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool cle
 static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw) {}
 static inline void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw) {}
 static inline void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) {}
+static inline bool mlx5_esw_offloads_devcom_is_ready(struct mlx5_eswitch *esw) { return false; }
 static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; }
 static inline
 int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index bdfe609cc9ec4..11cce630c1b80 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2811,7 +2811,6 @@ static int mlx5_esw_offloads_devcom_event(int event,
 					  void *event_data)
 {
 	struct mlx5_eswitch *esw = my_data;
-	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
 	struct mlx5_eswitch *peer_esw = event_data;
 	u16 esw_i, peer_esw_i;
 	bool esw_paired;
@@ -2833,6 +2832,7 @@ static int mlx5_esw_offloads_devcom_event(int event,
 		err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true);
 		if (err)
 			goto err_out;
+
 		err = mlx5_esw_offloads_pair(esw, peer_esw);
 		if (err)
 			goto err_peer;
@@ -2851,7 +2851,7 @@ static int mlx5_esw_offloads_devcom_event(int event,
 
 		esw->num_peers++;
 		peer_esw->num_peers++;
-		mlx5_devcom_comp_set_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true);
+		mlx5_devcom_comp_set_ready(esw->devcom, true);
 		break;
 
 	case ESW_OFFLOADS_DEVCOM_UNPAIR:
@@ -2861,7 +2861,7 @@ static int mlx5_esw_offloads_devcom_event(int event,
 		peer_esw->num_peers--;
 		esw->num_peers--;
 		if (!esw->num_peers && !peer_esw->num_peers)
-			mlx5_devcom_comp_set_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false);
+			mlx5_devcom_comp_set_ready(esw->devcom, false);
 		xa_erase(&peer_esw->paired, esw_i);
 		xa_erase(&esw->paired, peer_esw_i);
 		mlx5_esw_offloads_unpair(peer_esw, esw);
@@ -2888,7 +2888,7 @@ err_out:
 
 void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw)
 {
-	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
+	u64 guid;
 	int i;
 
 	for (i = 0; i < MLX5_MAX_PORTS; i++)
@@ -2902,34 +2902,41 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw)
 		return;
 
 	xa_init(&esw->paired);
-	mlx5_devcom_register_component(devcom,
-				       MLX5_DEVCOM_ESW_OFFLOADS,
-				       mlx5_esw_offloads_devcom_event,
-				       esw);
+	guid = mlx5_query_nic_system_image_guid(esw->dev);
 
 	esw->num_peers = 0;
-	mlx5_devcom_send_event(devcom,
-			       MLX5_DEVCOM_ESW_OFFLOADS,
+	esw->devcom = mlx5_devcom_register_component(esw->dev->priv.devc,
+						     MLX5_DEVCOM_ESW_OFFLOADS,
+						     guid,
+						     mlx5_esw_offloads_devcom_event,
+						     esw);
+	if (IS_ERR_OR_NULL(esw->devcom))
+		return;
+
+	mlx5_devcom_send_event(esw->devcom,
 			       ESW_OFFLOADS_DEVCOM_PAIR,
-			       ESW_OFFLOADS_DEVCOM_UNPAIR, esw);
+			       ESW_OFFLOADS_DEVCOM_UNPAIR,
+			       esw);
 }
 
 void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
 {
-	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
-
-	if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
+	if (IS_ERR_OR_NULL(esw->devcom))
 		return;
 
-	if (!mlx5_lag_is_supported(esw->dev))
-		return;
-
-	mlx5_devcom_send_event(devcom, MLX5_DEVCOM_ESW_OFFLOADS,
+	mlx5_devcom_send_event(esw->devcom,
+			       ESW_OFFLOADS_DEVCOM_UNPAIR,
 			       ESW_OFFLOADS_DEVCOM_UNPAIR,
-			       ESW_OFFLOADS_DEVCOM_UNPAIR, esw);
+			       esw);
 
-	mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	mlx5_devcom_unregister_component(esw->devcom);
 	xa_destroy(&esw->paired);
+	esw->devcom = NULL;
+}
+
+bool mlx5_esw_offloads_devcom_is_ready(struct mlx5_eswitch *esw)
+{
+	return mlx5_devcom_comp_is_ready(esw->devcom);
 }
 
 bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 900a18883f280..af3fac090b828 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -835,7 +835,7 @@ static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev)
 	dev = ldev->pf[MLX5_LAG_P1].dev;
 	if (is_mdev_switchdev_mode(dev) &&
 	    mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) &&
-	    mlx5_devcom_comp_is_ready(dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS) &&
+	    mlx5_esw_offloads_devcom_is_ready(dev->priv.eswitch) &&
 	    MLX5_CAP_ESW(dev, esw_shared_ingress_acl) &&
 	    mlx5_eswitch_get_npeers(dev->priv.eswitch) == MLX5_CAP_GEN(dev, num_lag_ports) - 1)
 		return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
index 78c94b22bdc09..feb62d9526435 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
@@ -2,214 +2,273 @@
 /* Copyright (c) 2018 Mellanox Technologies */
 
 #include <linux/mlx5/vport.h>
+#include <linux/list.h>
 #include "lib/devcom.h"
 #include "mlx5_core.h"
 
-static LIST_HEAD(devcom_list);
+static LIST_HEAD(devcom_dev_list);
+static LIST_HEAD(devcom_comp_list);
+/* protect device list */
+static DEFINE_MUTEX(dev_list_lock);
+/* protect component list */
+static DEFINE_MUTEX(comp_list_lock);
 
-#define devcom_for_each_component(priv, comp, iter) \
-	for (iter = 0; \
-	     comp = &(priv)->components[iter], iter < MLX5_DEVCOM_NUM_COMPONENTS; \
-	     iter++)
+#define devcom_for_each_component(iter) \
+	list_for_each_entry(iter, &devcom_comp_list, comp_list)
 
-struct mlx5_devcom_component {
-	struct {
-		void __rcu *data;
-	} device[MLX5_DEVCOM_PORTS_SUPPORTED];
+struct mlx5_devcom_dev {
+	struct list_head list;
+	struct mlx5_core_dev *dev;
+	struct kref ref;
+};
 
+struct mlx5_devcom_comp {
+	struct list_head comp_list;
+	enum mlx5_devcom_component id;
+	u64 key;
+	struct list_head comp_dev_list_head;
 	mlx5_devcom_event_handler_t handler;
-	struct rw_semaphore sem;
+	struct kref ref;
 	bool ready;
+	struct rw_semaphore sem;
 };
 
-struct mlx5_devcom_list {
+struct mlx5_devcom_comp_dev {
 	struct list_head list;
-
-	struct mlx5_devcom_component components[MLX5_DEVCOM_NUM_COMPONENTS];
-	struct mlx5_core_dev *devs[MLX5_DEVCOM_PORTS_SUPPORTED];
+	struct mlx5_devcom_comp *comp;
+	struct mlx5_devcom_dev *devc;
+	void __rcu *data;
 };
 
-struct mlx5_devcom {
-	struct mlx5_devcom_list *priv;
-	int idx;
-};
-
-static struct mlx5_devcom_list *mlx5_devcom_list_alloc(void)
+static bool devcom_dev_exists(struct mlx5_core_dev *dev)
 {
-	struct mlx5_devcom_component *comp;
-	struct mlx5_devcom_list *priv;
-	int i;
-
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return NULL;
+	struct mlx5_devcom_dev *iter;
 
-	devcom_for_each_component(priv, comp, i)
-		init_rwsem(&comp->sem);
+	list_for_each_entry(iter, &devcom_dev_list, list)
+		if (iter->dev == dev)
+			return true;
 
-	return priv;
+	return false;
 }
 
-static struct mlx5_devcom *mlx5_devcom_alloc(struct mlx5_devcom_list *priv,
-					     u8 idx)
+static struct mlx5_devcom_dev *
+mlx5_devcom_dev_alloc(struct mlx5_core_dev *dev)
 {
-	struct mlx5_devcom *devcom;
+	struct mlx5_devcom_dev *devc;
 
-	devcom = kzalloc(sizeof(*devcom), GFP_KERNEL);
-	if (!devcom)
+	devc = kzalloc(sizeof(*devc), GFP_KERNEL);
+	if (!devc)
 		return NULL;
 
-	devcom->priv = priv;
-	devcom->idx = idx;
-	return devcom;
+	devc->dev = dev;
+	kref_init(&devc->ref);
+	return devc;
 }
 
-/* Must be called with intf_mutex held */
-struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev)
+struct mlx5_devcom_dev *
+mlx5_devcom_register_device(struct mlx5_core_dev *dev)
 {
-	struct mlx5_devcom_list *priv = NULL, *iter;
-	struct mlx5_devcom *devcom = NULL;
-	bool new_priv = false;
-	u64 sguid0, sguid1;
-	int idx, i;
-
-	if (!mlx5_core_is_pf(dev))
-		return NULL;
-	if (MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_DEVCOM_PORTS_SUPPORTED)
-		return NULL;
-
-	mlx5_dev_list_lock();
-	sguid0 = mlx5_query_nic_system_image_guid(dev);
-	list_for_each_entry(iter, &devcom_list, list) {
-		/* There is at least one device in iter */
-		struct mlx5_core_dev *tmp_dev;
-
-		idx = -1;
-		for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) {
-			if (iter->devs[i])
-				tmp_dev = iter->devs[i];
-			else
-				idx = i;
-		}
-
-		if (idx == -1)
-			continue;
-
-		sguid1 = mlx5_query_nic_system_image_guid(tmp_dev);
-		if (sguid0 != sguid1)
-			continue;
-
-		priv = iter;
-		break;
-	}
+	struct mlx5_devcom_dev *devc;
 
-	if (!priv) {
-		priv = mlx5_devcom_list_alloc();
-		if (!priv) {
-			devcom = ERR_PTR(-ENOMEM);
-			goto out;
-		}
+	mutex_lock(&dev_list_lock);
 
-		idx = 0;
-		new_priv = true;
+	if (devcom_dev_exists(dev)) {
+		devc = ERR_PTR(-EEXIST);
+		goto out;
 	}
 
-	priv->devs[idx] = dev;
-	devcom = mlx5_devcom_alloc(priv, idx);
-	if (!devcom) {
-		if (new_priv)
-			kfree(priv);
-		devcom = ERR_PTR(-ENOMEM);
+	devc = mlx5_devcom_dev_alloc(dev);
+	if (!devc) {
+		devc = ERR_PTR(-ENOMEM);
 		goto out;
 	}
 
-	if (new_priv)
-		list_add(&priv->list, &devcom_list);
+	list_add_tail(&devc->list, &devcom_dev_list);
 out:
-	mlx5_dev_list_unlock();
-	return devcom;
+	mutex_unlock(&dev_list_lock);
+	return devc;
 }
 
-/* Must be called with intf_mutex held */
-void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom)
+static void
+mlx5_devcom_dev_release(struct kref *ref)
 {
-	struct mlx5_devcom_list *priv;
-	int i;
+	struct mlx5_devcom_dev *devc = container_of(ref, struct mlx5_devcom_dev, ref);
 
-	if (IS_ERR_OR_NULL(devcom))
-		return;
+	mutex_lock(&dev_list_lock);
+	list_del(&devc->list);
+	mutex_unlock(&dev_list_lock);
+	kfree(devc);
+}
 
-	mlx5_dev_list_lock();
-	priv = devcom->priv;
-	priv->devs[devcom->idx] = NULL;
+void mlx5_devcom_unregister_device(struct mlx5_devcom_dev *devc)
+{
+	if (!IS_ERR_OR_NULL(devc))
+		kref_put(&devc->ref, mlx5_devcom_dev_release);
+}
 
-	kfree(devcom);
+static struct mlx5_devcom_comp *
+mlx5_devcom_comp_alloc(u64 id, u64 key, mlx5_devcom_event_handler_t handler)
+{
+	struct mlx5_devcom_comp *comp;
 
-	for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++)
-		if (priv->devs[i])
-			break;
+	comp = kzalloc(sizeof(*comp), GFP_KERNEL);
+	if (!comp)
+		return ERR_PTR(-ENOMEM);
 
-	if (i != MLX5_DEVCOM_PORTS_SUPPORTED)
-		goto out;
+	comp->id = id;
+	comp->key = key;
+	comp->handler = handler;
+	init_rwsem(&comp->sem);
+	kref_init(&comp->ref);
+	INIT_LIST_HEAD(&comp->comp_dev_list_head);
 
-	list_del(&priv->list);
-	kfree(priv);
-out:
-	mlx5_dev_list_unlock();
+	return comp;
 }
 
-void mlx5_devcom_register_component(struct mlx5_devcom *devcom,
-				    enum mlx5_devcom_components id,
-				    mlx5_devcom_event_handler_t handler,
-				    void *data)
+static void
+mlx5_devcom_comp_release(struct kref *ref)
 {
-	struct mlx5_devcom_component *comp;
+	struct mlx5_devcom_comp *comp = container_of(ref, struct mlx5_devcom_comp, ref);
 
-	if (IS_ERR_OR_NULL(devcom))
-		return;
+	mutex_lock(&comp_list_lock);
+	list_del(&comp->comp_list);
+	mutex_unlock(&comp_list_lock);
+	kfree(comp);
+}
+
+static struct mlx5_devcom_comp_dev *
+devcom_alloc_comp_dev(struct mlx5_devcom_dev *devc,
+		      struct mlx5_devcom_comp *comp,
+		      void *data)
+{
+	struct mlx5_devcom_comp_dev *devcom;
 
-	WARN_ON(!data);
+	devcom = kzalloc(sizeof(*devcom), GFP_KERNEL);
+	if (!devcom)
+		return ERR_PTR(-ENOMEM);
+
+	kref_get(&devc->ref);
+	devcom->devc = devc;
+	devcom->comp = comp;
+	rcu_assign_pointer(devcom->data, data);
 
-	comp = &devcom->priv->components[id];
 	down_write(&comp->sem);
-	comp->handler = handler;
-	rcu_assign_pointer(comp->device[devcom->idx].data, data);
+	list_add_tail(&devcom->list, &comp->comp_dev_list_head);
 	up_write(&comp->sem);
+
+	return devcom;
 }
 
-void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom,
-				      enum mlx5_devcom_components id)
+static void
+devcom_free_comp_dev(struct mlx5_devcom_comp_dev *devcom)
 {
-	struct mlx5_devcom_component *comp;
-
-	if (IS_ERR_OR_NULL(devcom))
-		return;
+	struct mlx5_devcom_comp *comp = devcom->comp;
 
-	comp = &devcom->priv->components[id];
 	down_write(&comp->sem);
-	RCU_INIT_POINTER(comp->device[devcom->idx].data, NULL);
+	list_del(&devcom->list);
 	up_write(&comp->sem);
-	synchronize_rcu();
+
+	kref_put(&devcom->devc->ref, mlx5_devcom_dev_release);
+	kfree(devcom);
+	kref_put(&comp->ref, mlx5_devcom_comp_release);
 }
 
-int mlx5_devcom_send_event(struct mlx5_devcom *devcom,
-			   enum mlx5_devcom_components id,
+static bool
+devcom_component_equal(struct mlx5_devcom_comp *devcom,
+		       enum mlx5_devcom_component id,
+		       u64 key)
+{
+	return devcom->id == id && devcom->key == key;
+}
+
+static struct mlx5_devcom_comp *
+devcom_component_get(struct mlx5_devcom_dev *devc,
+		     enum mlx5_devcom_component id,
+		     u64 key,
+		     mlx5_devcom_event_handler_t handler)
+{
+	struct mlx5_devcom_comp *comp;
+
+	devcom_for_each_component(comp) {
+		if (devcom_component_equal(comp, id, key)) {
+			if (handler == comp->handler) {
+				kref_get(&comp->ref);
+				return comp;
+			}
+
+			mlx5_core_err(devc->dev,
+				      "Cannot register existing devcom component with different handler\n");
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	return NULL;
+}
+
+struct mlx5_devcom_comp_dev *
+mlx5_devcom_register_component(struct mlx5_devcom_dev *devc,
+			       enum mlx5_devcom_component id,
+			       u64 key,
+			       mlx5_devcom_event_handler_t handler,
+			       void *data)
+{
+	struct mlx5_devcom_comp_dev *devcom;
+	struct mlx5_devcom_comp *comp;
+
+	if (IS_ERR_OR_NULL(devc))
+		return NULL;
+
+	mutex_lock(&comp_list_lock);
+	comp = devcom_component_get(devc, id, key, handler);
+	if (IS_ERR(comp)) {
+		devcom = ERR_PTR(-EINVAL);
+		goto out_unlock;
+	}
+
+	if (!comp) {
+		comp = mlx5_devcom_comp_alloc(id, key, handler);
+		if (IS_ERR(comp)) {
+			devcom = ERR_CAST(comp);
+			goto out_unlock;
+		}
+		list_add_tail(&comp->comp_list, &devcom_comp_list);
+	}
+	mutex_unlock(&comp_list_lock);
+
+	devcom = devcom_alloc_comp_dev(devc, comp, data);
+	if (IS_ERR(devcom))
+		kref_put(&comp->ref, mlx5_devcom_comp_release);
+
+	return devcom;
+
+out_unlock:
+	mutex_unlock(&comp_list_lock);
+	return devcom;
+}
+
+void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom)
+{
+	if (!IS_ERR_OR_NULL(devcom))
+		devcom_free_comp_dev(devcom);
+}
+
+int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom,
 			   int event, int rollback_event,
 			   void *event_data)
 {
-	struct mlx5_devcom_component *comp;
-	int err = -ENODEV, i;
+	struct mlx5_devcom_comp *comp = devcom->comp;
+	struct mlx5_devcom_comp_dev *pos;
+	int err = 0;
+	void *data;
 
 	if (IS_ERR_OR_NULL(devcom))
-		return err;
+		return -ENODEV;
 
-	comp = &devcom->priv->components[id];
 	down_write(&comp->sem);
-	for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) {
-		void *data = rcu_dereference_protected(comp->device[i].data,
-						       lockdep_is_held(&comp->sem));
+	list_for_each_entry(pos, &comp->comp_dev_list_head, list) {
+		data = rcu_dereference_protected(pos->data, lockdep_is_held(&comp->sem));
 
-		if (i != devcom->idx && data) {
+		if (pos != devcom && data) {
 			err = comp->handler(event, data, event_data);
 			if (err)
 				goto rollback;
@@ -220,48 +279,43 @@ int mlx5_devcom_send_event(struct mlx5_devcom *devcom,
 	return 0;
 
 rollback:
-	while (i--) {
-		void *data = rcu_dereference_protected(comp->device[i].data,
-						       lockdep_is_held(&comp->sem));
+	if (list_entry_is_head(pos, &comp->comp_dev_list_head, list))
+		goto out;
+	pos = list_prev_entry(pos, list);
+	list_for_each_entry_from_reverse(pos, &comp->comp_dev_list_head, list) {
+		data = rcu_dereference_protected(pos->data, lockdep_is_held(&comp->sem));
 
-		if (i != devcom->idx && data)
+		if (pos != devcom && data)
 			comp->handler(rollback_event, data, event_data);
 	}
-
+out:
 	up_write(&comp->sem);
 	return err;
 }
 
-void mlx5_devcom_comp_set_ready(struct mlx5_devcom *devcom,
-				enum mlx5_devcom_components id,
-				bool ready)
+void mlx5_devcom_comp_set_ready(struct mlx5_devcom_comp_dev *devcom, bool ready)
 {
-	struct mlx5_devcom_component *comp;
-
-	comp = &devcom->priv->components[id];
-	WARN_ON(!rwsem_is_locked(&comp->sem));
+	WARN_ON(!rwsem_is_locked(&devcom->comp->sem));
 
-	WRITE_ONCE(comp->ready, ready);
+	WRITE_ONCE(devcom->comp->ready, ready);
 }
 
-bool mlx5_devcom_comp_is_ready(struct mlx5_devcom *devcom,
-			       enum mlx5_devcom_components id)
+bool mlx5_devcom_comp_is_ready(struct mlx5_devcom_comp_dev *devcom)
 {
 	if (IS_ERR_OR_NULL(devcom))
 		return false;
 
-	return READ_ONCE(devcom->priv->components[id].ready);
+	return READ_ONCE(devcom->comp->ready);
 }
 
-bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom *devcom,
-				     enum mlx5_devcom_components id)
+bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom_comp_dev *devcom)
 {
-	struct mlx5_devcom_component *comp;
+	struct mlx5_devcom_comp *comp;
 
 	if (IS_ERR_OR_NULL(devcom))
 		return false;
 
-	comp = &devcom->priv->components[id];
+	comp = devcom->comp;
 	down_read(&comp->sem);
 	if (!READ_ONCE(comp->ready)) {
 		up_read(&comp->sem);
@@ -271,74 +325,60 @@ bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom *devcom,
 	return true;
 }
 
-void mlx5_devcom_for_each_peer_end(struct mlx5_devcom *devcom,
-				   enum mlx5_devcom_components id)
+void mlx5_devcom_for_each_peer_end(struct mlx5_devcom_comp_dev *devcom)
 {
-	struct mlx5_devcom_component *comp = &devcom->priv->components[id];
-
-	up_read(&comp->sem);
+	up_read(&devcom->comp->sem);
 }
 
-void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom *devcom,
-				     enum mlx5_devcom_components id,
-				     int *i)
+void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom_comp_dev *devcom,
+				     struct mlx5_devcom_comp_dev **pos)
 {
-	struct mlx5_devcom_component *comp;
-	void *ret;
-	int idx;
+	struct mlx5_devcom_comp *comp = devcom->comp;
+	struct mlx5_devcom_comp_dev *tmp;
+	void *data;
 
-	comp = &devcom->priv->components[id];
+	tmp = list_prepare_entry(*pos, &comp->comp_dev_list_head, list);
 
-	if (*i == MLX5_DEVCOM_PORTS_SUPPORTED)
-		return NULL;
-	for (idx = *i; idx < MLX5_DEVCOM_PORTS_SUPPORTED; idx++) {
-		if (idx != devcom->idx) {
-			ret = rcu_dereference_protected(comp->device[idx].data,
-							lockdep_is_held(&comp->sem));
-			if (ret)
+	list_for_each_entry_continue(tmp, &comp->comp_dev_list_head, list) {
+		if (tmp != devcom) {
+			data = rcu_dereference_protected(tmp->data, lockdep_is_held(&comp->sem));
+			if (data)
 				break;
 		}
 	}
 
-	if (idx == MLX5_DEVCOM_PORTS_SUPPORTED) {
-		*i = idx;
+	if (list_entry_is_head(tmp, &comp->comp_dev_list_head, list))
 		return NULL;
-	}
-	*i = idx + 1;
 
-	return ret;
+	*pos = tmp;
+	return data;
 }
 
-void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom *devcom,
-					 enum mlx5_devcom_components id,
-					 int *i)
+void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom_comp_dev *devcom,
+					 struct mlx5_devcom_comp_dev **pos)
 {
-	struct mlx5_devcom_component *comp;
-	void *ret;
-	int idx;
+	struct mlx5_devcom_comp *comp = devcom->comp;
+	struct mlx5_devcom_comp_dev *tmp;
+	void *data;
 
-	comp = &devcom->priv->components[id];
+	tmp = list_prepare_entry(*pos, &comp->comp_dev_list_head, list);
 
-	if (*i == MLX5_DEVCOM_PORTS_SUPPORTED)
-		return NULL;
-	for (idx = *i; idx < MLX5_DEVCOM_PORTS_SUPPORTED; idx++) {
-		if (idx != devcom->idx) {
+	list_for_each_entry_continue(tmp, &comp->comp_dev_list_head, list) {
+		if (tmp != devcom) {
 			/* This can change concurrently, however 'data' pointer will remain
 			 * valid for the duration of RCU read section.
 			 */
 			if (!READ_ONCE(comp->ready))
 				return NULL;
-			ret = rcu_dereference(comp->device[idx].data);
-			if (ret)
+			data = rcu_dereference(tmp->data);
+			if (data)
 				break;
 		}
 	}
 
-	if (idx == MLX5_DEVCOM_PORTS_SUPPORTED) {
-		*i = idx;
+	if (list_entry_is_head(tmp, &comp->comp_dev_list_head, list))
 		return NULL;
-	}
-	*i = idx + 1;
 
-	return ret;
+	*pos = tmp;
+	return data;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
index d953a01b8eaac..8389ac0af708e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -6,11 +6,8 @@
 
 #include <linux/mlx5/driver.h>
 
-#define MLX5_DEVCOM_PORTS_SUPPORTED 4
-
-enum mlx5_devcom_components {
+enum mlx5_devcom_component {
 	MLX5_DEVCOM_ESW_OFFLOADS,
-
 	MLX5_DEVCOM_NUM_COMPONENTS,
 };
 
@@ -18,45 +15,40 @@ typedef int (*mlx5_devcom_event_handler_t)(int event,
 					   void *my_data,
 					   void *event_data);
 
-struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev);
-void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom);
+struct mlx5_devcom_dev *mlx5_devcom_register_device(struct mlx5_core_dev *dev);
+void mlx5_devcom_unregister_device(struct mlx5_devcom_dev *devc);
 
-void mlx5_devcom_register_component(struct mlx5_devcom *devcom,
-				    enum mlx5_devcom_components id,
-				    mlx5_devcom_event_handler_t handler,
-				    void *data);
-void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom,
-				      enum mlx5_devcom_components id);
+struct mlx5_devcom_comp_dev *
+mlx5_devcom_register_component(struct mlx5_devcom_dev *devc,
+			       enum mlx5_devcom_component id,
+			       u64 key,
+			       mlx5_devcom_event_handler_t handler,
+			       void *data);
+void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom);
 
-int mlx5_devcom_send_event(struct mlx5_devcom *devcom,
-			   enum mlx5_devcom_components id,
+int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom,
 			   int event, int rollback_event,
 			   void *event_data);
 
-void mlx5_devcom_comp_set_ready(struct mlx5_devcom *devcom,
-				enum mlx5_devcom_components id,
-				bool ready);
-bool mlx5_devcom_comp_is_ready(struct mlx5_devcom *devcom,
-			       enum mlx5_devcom_components id);
-
-bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom *devcom,
-				     enum mlx5_devcom_components id);
-void mlx5_devcom_for_each_peer_end(struct mlx5_devcom *devcom,
-				   enum mlx5_devcom_components id);
-void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom *devcom,
-				     enum mlx5_devcom_components id, int *i);
-
-#define mlx5_devcom_for_each_peer_entry(devcom, id, data, i)			\
-	for (i = 0, data = mlx5_devcom_get_next_peer_data(devcom, id, &i);	\
-	     data;								\
-	     data = mlx5_devcom_get_next_peer_data(devcom, id, &i))
-
-void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom *devcom,
-					 enum mlx5_devcom_components id, int *i);
-
-#define mlx5_devcom_for_each_peer_entry_rcu(devcom, id, data, i)		\
-	for (i = 0, data = mlx5_devcom_get_next_peer_data_rcu(devcom, id, &i);	\
-	     data;								\
-	     data = mlx5_devcom_get_next_peer_data_rcu(devcom, id, &i))
-
-#endif
+void mlx5_devcom_comp_set_ready(struct mlx5_devcom_comp_dev *devcom, bool ready);
+bool mlx5_devcom_comp_is_ready(struct mlx5_devcom_comp_dev *devcom);
+
+bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom_comp_dev *devcom);
+void mlx5_devcom_for_each_peer_end(struct mlx5_devcom_comp_dev *devcom);
+void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom_comp_dev *devcom,
+				     struct mlx5_devcom_comp_dev **pos);
+
+#define mlx5_devcom_for_each_peer_entry(devcom, data, pos)                    \
+	for (pos = NULL, data = mlx5_devcom_get_next_peer_data(devcom, &pos); \
+	     data;                                                            \
+	     data = mlx5_devcom_get_next_peer_data(devcom, &pos))
+
+void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom_comp_dev *devcom,
+					 struct mlx5_devcom_comp_dev **pos);
+
+#define mlx5_devcom_for_each_peer_entry_rcu(devcom, data, pos)                    \
+	for (pos = NULL, data = mlx5_devcom_get_next_peer_data_rcu(devcom, &pos); \
+	     data;								  \
+	     data = mlx5_devcom_get_next_peer_data_rcu(devcom, &pos))
+
+#endif /* __LIB_MLX5_DEVCOM_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 88dbea6631d50..a79c9b8286a7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -951,10 +951,10 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 {
 	int err;
 
-	dev->priv.devcom = mlx5_devcom_register_device(dev);
-	if (IS_ERR(dev->priv.devcom))
-		mlx5_core_err(dev, "failed to register with devcom (0x%p)\n",
-			      dev->priv.devcom);
+	dev->priv.devc = mlx5_devcom_register_device(dev);
+	if (IS_ERR(dev->priv.devc))
+		mlx5_core_warn(dev, "failed to register devcom device %ld\n",
+			       PTR_ERR(dev->priv.devc));
 
 	err = mlx5_query_board_id(dev);
 	if (err) {
@@ -1089,7 +1089,7 @@ err_eq_cleanup:
 err_irq_cleanup:
 	mlx5_irq_table_cleanup(dev);
 err_devcom:
-	mlx5_devcom_unregister_device(dev->priv.devcom);
+	mlx5_devcom_unregister_device(dev->priv.devc);
 
 	return err;
 }
@@ -1118,7 +1118,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
 	mlx5_irq_table_cleanup(dev);
-	mlx5_devcom_unregister_device(dev->priv.devcom);
+	mlx5_devcom_unregister_device(dev->priv.devc);
 }
 
 static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeout)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 25d0528f92197..56dd3dfe23041 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -501,7 +501,7 @@ struct mlx5_events;
 struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
-struct mlx5_devcom;
+struct mlx5_devcom_dev;
 struct mlx5_fw_reset;
 struct mlx5_eq_table;
 struct mlx5_irq_table;
@@ -618,7 +618,7 @@ struct mlx5_priv {
 	struct mlx5_core_sriov	sriov;
 	struct mlx5_lag		*lag;
 	u32			flags;
-	struct mlx5_devcom	*devcom;
+	struct mlx5_devcom_dev	*devc;
 	struct mlx5_fw_reset	*fw_reset;
 	struct mlx5_core_roce	roce;
 	struct mlx5_fc_stats		fc_stats;
-- 
GitLab


From 1161d22ded072335c950723af2f21fd52ba47cbb Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@nvidia.com>
Date: Mon, 22 May 2023 18:16:50 +0300
Subject: [PATCH 0527/1806] net/mlx5e: E-Switch, Register devcom device with
 switch id key

Register devcom devices with switch id instead of guid.
Devcom interface is used to sync between ports in the eswitch,
e.g. Adding miss rules between the ports.
New eswitch devices could have the same guid but a different
switch id so its more correct to group according to switch id
which is the identifier if the ports are on the same eswitch.

Signed-off-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c          | 9 +++++++--
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h        | 4 ++--
 .../net/ethernet/mellanox/mlx5/core/eswitch_offloads.c   | 7 ++-----
 3 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 22bc886206533..507825a1abc8b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -5194,11 +5194,12 @@ void mlx5e_tc_ht_cleanup(struct rhashtable *tc_ht)
 int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv)
 {
 	const size_t sz_enc_opts = sizeof(struct tunnel_match_enc_opts);
+	struct netdev_phys_item_id ppid;
 	struct mlx5e_rep_priv *rpriv;
 	struct mapping_ctx *mapping;
 	struct mlx5_eswitch *esw;
 	struct mlx5e_priv *priv;
-	u64 mapping_id;
+	u64 mapping_id, key;
 	int err = 0;
 
 	rpriv = container_of(uplink_priv, struct mlx5e_rep_priv, uplink_priv);
@@ -5252,7 +5253,11 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv)
 		goto err_action_counter;
 	}
 
-	mlx5_esw_offloads_devcom_init(esw);
+	err = dev_get_port_parent_id(priv->netdev, &ppid, false);
+	if (!err) {
+		memcpy(&key, &ppid.id, sizeof(key));
+		mlx5_esw_offloads_devcom_init(esw, key);
+	}
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 6d9378b0bce59..9b5a1651b8776 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -382,7 +382,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs);
 void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf);
 void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw);
 void mlx5_eswitch_disable(struct mlx5_eswitch *esw);
-void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw);
+void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key);
 void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw);
 bool mlx5_esw_offloads_devcom_is_ready(struct mlx5_eswitch *esw);
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
@@ -818,7 +818,7 @@ static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
 static inline int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { return 0; }
 static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) {}
 static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw) {}
-static inline void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw) {}
+static inline void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key) {}
 static inline void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) {}
 static inline bool mlx5_esw_offloads_devcom_is_ready(struct mlx5_eswitch *esw) { return false; }
 static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 11cce630c1b80..7d100cd4afaba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2886,9 +2886,8 @@ err_out:
 	return err;
 }
 
-void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw)
+void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key)
 {
-	u64 guid;
 	int i;
 
 	for (i = 0; i < MLX5_MAX_PORTS; i++)
@@ -2902,12 +2901,10 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw)
 		return;
 
 	xa_init(&esw->paired);
-	guid = mlx5_query_nic_system_image_guid(esw->dev);
-
 	esw->num_peers = 0;
 	esw->devcom = mlx5_devcom_register_component(esw->dev->priv.devc,
 						     MLX5_DEVCOM_ESW_OFFLOADS,
-						     guid,
+						     key,
 						     mlx5_esw_offloads_devcom_event,
 						     esw);
 	if (IS_ERR_OR_NULL(esw->devcom))
-- 
GitLab


From e2bb7984719bb1138e955ba3bbafd3a16d1cb8e3 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@nvidia.com>
Date: Tue, 23 May 2023 11:50:17 +0300
Subject: [PATCH 0528/1806] net/mlx5e: E-Switch, Allow devcom initialization on
 more vports

New features could use the devcom interface but not necessarily
the lag feature although for vport managers and ECPF
still check for lag support.

Signed-off-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 7d100cd4afaba..b4b8cb7885739 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2897,7 +2897,8 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key)
 	if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
 		return;
 
-	if (!mlx5_lag_is_supported(esw->dev))
+	if ((MLX5_VPORT_MANAGER(esw->dev) || mlx5_core_is_ecpf_esw_manager(esw->dev)) &&
+	    !mlx5_lag_is_supported(esw->dev))
 		return;
 
 	xa_init(&esw->paired);
-- 
GitLab


From 58db72869a9f8e01910844ca145efc2ea91bbbf9 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Wed, 18 Jan 2023 16:52:17 +0200
Subject: [PATCH 0529/1806] net/mlx5: Re-organize mlx5_cmd struct

Downstream patch will split mlx5_cmd_init() to probe and reload
routines. As a preparation, organize mlx5_cmd struct so that any
field that will be used in the reload routine are grouped at new
nested struct.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 94 +++++++++----------
 .../net/ethernet/mellanox/mlx5/core/debugfs.c |  4 +-
 include/linux/mlx5/driver.h                   | 21 +++--
 3 files changed, 60 insertions(+), 59 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index d532883b42d7c..f175af528fe00 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -162,18 +162,18 @@ static int cmd_alloc_index(struct mlx5_cmd *cmd)
 	int ret;
 
 	spin_lock_irqsave(&cmd->alloc_lock, flags);
-	ret = find_first_bit(&cmd->bitmask, cmd->max_reg_cmds);
-	if (ret < cmd->max_reg_cmds)
-		clear_bit(ret, &cmd->bitmask);
+	ret = find_first_bit(&cmd->vars.bitmask, cmd->vars.max_reg_cmds);
+	if (ret < cmd->vars.max_reg_cmds)
+		clear_bit(ret, &cmd->vars.bitmask);
 	spin_unlock_irqrestore(&cmd->alloc_lock, flags);
 
-	return ret < cmd->max_reg_cmds ? ret : -ENOMEM;
+	return ret < cmd->vars.max_reg_cmds ? ret : -ENOMEM;
 }
 
 static void cmd_free_index(struct mlx5_cmd *cmd, int idx)
 {
 	lockdep_assert_held(&cmd->alloc_lock);
-	set_bit(idx, &cmd->bitmask);
+	set_bit(idx, &cmd->vars.bitmask);
 }
 
 static void cmd_ent_get(struct mlx5_cmd_work_ent *ent)
@@ -192,7 +192,7 @@ static void cmd_ent_put(struct mlx5_cmd_work_ent *ent)
 
 	if (ent->idx >= 0) {
 		cmd_free_index(cmd, ent->idx);
-		up(ent->page_queue ? &cmd->pages_sem : &cmd->sem);
+		up(ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem);
 	}
 
 	cmd_free_ent(ent);
@@ -202,7 +202,7 @@ out:
 
 static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx)
 {
-	return cmd->cmd_buf + (idx << cmd->log_stride);
+	return cmd->cmd_buf + (idx << cmd->vars.log_stride);
 }
 
 static int mlx5_calc_cmd_blocks(struct mlx5_cmd_msg *msg)
@@ -974,7 +974,7 @@ static void cmd_work_handler(struct work_struct *work)
 	cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD));
 
 	complete(&ent->handling);
-	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
+	sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem;
 	down(sem);
 	if (!ent->page_queue) {
 		alloc_ret = cmd_alloc_index(cmd);
@@ -994,9 +994,9 @@ static void cmd_work_handler(struct work_struct *work)
 		}
 		ent->idx = alloc_ret;
 	} else {
-		ent->idx = cmd->max_reg_cmds;
+		ent->idx = cmd->vars.max_reg_cmds;
 		spin_lock_irqsave(&cmd->alloc_lock, flags);
-		clear_bit(ent->idx, &cmd->bitmask);
+		clear_bit(ent->idx, &cmd->vars.bitmask);
 		spin_unlock_irqrestore(&cmd->alloc_lock, flags);
 	}
 
@@ -1572,15 +1572,15 @@ void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode)
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int i;
 
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		down(&cmd->sem);
-	down(&cmd->pages_sem);
+	for (i = 0; i < cmd->vars.max_reg_cmds; i++)
+		down(&cmd->vars.sem);
+	down(&cmd->vars.pages_sem);
 
 	cmd->allowed_opcode = opcode;
 
-	up(&cmd->pages_sem);
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		up(&cmd->sem);
+	up(&cmd->vars.pages_sem);
+	for (i = 0; i < cmd->vars.max_reg_cmds; i++)
+		up(&cmd->vars.sem);
 }
 
 static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
@@ -1588,15 +1588,15 @@ static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int i;
 
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		down(&cmd->sem);
-	down(&cmd->pages_sem);
+	for (i = 0; i < cmd->vars.max_reg_cmds; i++)
+		down(&cmd->vars.sem);
+	down(&cmd->vars.pages_sem);
 
 	cmd->mode = mode;
 
-	up(&cmd->pages_sem);
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		up(&cmd->sem);
+	up(&cmd->vars.pages_sem);
+	for (i = 0; i < cmd->vars.max_reg_cmds; i++)
+		up(&cmd->vars.sem);
 }
 
 static int cmd_comp_notifier(struct notifier_block *nb,
@@ -1655,7 +1655,7 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
 
 	/* there can be at most 32 command queues */
 	vector = vec & 0xffffffff;
-	for (i = 0; i < (1 << cmd->log_sz); i++) {
+	for (i = 0; i < (1 << cmd->vars.log_sz); i++) {
 		if (test_bit(i, &vector)) {
 			ent = cmd->ent_arr[i];
 
@@ -1744,7 +1744,7 @@ static void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev)
 	/* wait for pending handlers to complete */
 	mlx5_eq_synchronize_cmd_irq(dev);
 	spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
-	vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
+	vector = ~dev->cmd.vars.bitmask & ((1ul << (1 << dev->cmd.vars.log_sz)) - 1);
 	if (!vector)
 		goto no_trig;
 
@@ -1753,14 +1753,14 @@ static void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev)
 	 * to guarantee pending commands will not get freed in the meanwhile.
 	 * For that reason, it also has to be done inside the alloc_lock.
 	 */
-	for_each_set_bit(i, &bitmask, (1 << cmd->log_sz))
+	for_each_set_bit(i, &bitmask, (1 << cmd->vars.log_sz))
 		cmd_ent_get(cmd->ent_arr[i]);
 	vector |= MLX5_TRIGGERED_CMD_COMP;
 	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
 
 	mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
 	mlx5_cmd_comp_handler(dev, vector, true);
-	for_each_set_bit(i, &bitmask, (1 << cmd->log_sz))
+	for_each_set_bit(i, &bitmask, (1 << cmd->vars.log_sz))
 		cmd_ent_put(cmd->ent_arr[i]);
 	return;
 
@@ -1773,22 +1773,22 @@ void mlx5_cmd_flush(struct mlx5_core_dev *dev)
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int i;
 
-	for (i = 0; i < cmd->max_reg_cmds; i++) {
-		while (down_trylock(&cmd->sem)) {
+	for (i = 0; i < cmd->vars.max_reg_cmds; i++) {
+		while (down_trylock(&cmd->vars.sem)) {
 			mlx5_cmd_trigger_completions(dev);
 			cond_resched();
 		}
 	}
 
-	while (down_trylock(&cmd->pages_sem)) {
+	while (down_trylock(&cmd->vars.pages_sem)) {
 		mlx5_cmd_trigger_completions(dev);
 		cond_resched();
 	}
 
 	/* Unlock cmdif */
-	up(&cmd->pages_sem);
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		up(&cmd->sem);
+	up(&cmd->vars.pages_sem);
+	for (i = 0; i < cmd->vars.max_reg_cmds; i++)
+		up(&cmd->vars.sem);
 }
 
 static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size,
@@ -1858,7 +1858,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		/* atomic context may not sleep */
 		if (callback)
 			return -EINVAL;
-		down(&dev->cmd.throttle_sem);
+		down(&dev->cmd.vars.throttle_sem);
 	}
 
 	pages_queue = is_manage_pages(in);
@@ -1903,7 +1903,7 @@ out_in:
 	free_msg(dev, inb);
 out_up:
 	if (throttle_op)
-		up(&dev->cmd.throttle_sem);
+		up(&dev->cmd.vars.throttle_sem);
 	return err;
 }
 
@@ -2213,16 +2213,16 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 		goto err_free_pool;
 
 	cmd_l = ioread32be(&dev->iseg->cmdq_addr_l_sz) & 0xff;
-	cmd->log_sz = cmd_l >> 4 & 0xf;
-	cmd->log_stride = cmd_l & 0xf;
-	if (1 << cmd->log_sz > MLX5_MAX_COMMANDS) {
+	cmd->vars.log_sz = cmd_l >> 4 & 0xf;
+	cmd->vars.log_stride = cmd_l & 0xf;
+	if (1 << cmd->vars.log_sz > MLX5_MAX_COMMANDS) {
 		mlx5_core_err(dev, "firmware reports too many outstanding commands %d\n",
-			      1 << cmd->log_sz);
+			      1 << cmd->vars.log_sz);
 		err = -EINVAL;
 		goto err_free_page;
 	}
 
-	if (cmd->log_sz + cmd->log_stride > MLX5_ADAPTER_PAGE_SHIFT) {
+	if (cmd->vars.log_sz + cmd->vars.log_stride > MLX5_ADAPTER_PAGE_SHIFT) {
 		mlx5_core_err(dev, "command queue size overflow\n");
 		err = -EINVAL;
 		goto err_free_page;
@@ -2230,13 +2230,13 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 
 	cmd->state = MLX5_CMDIF_STATE_DOWN;
 	cmd->checksum_disabled = 1;
-	cmd->max_reg_cmds = (1 << cmd->log_sz) - 1;
-	cmd->bitmask = (1UL << cmd->max_reg_cmds) - 1;
+	cmd->vars.max_reg_cmds = (1 << cmd->vars.log_sz) - 1;
+	cmd->vars.bitmask = (1UL << cmd->vars.max_reg_cmds) - 1;
 
-	cmd->cmdif_rev = ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16;
-	if (cmd->cmdif_rev > CMD_IF_REV) {
+	cmd->vars.cmdif_rev = ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16;
+	if (cmd->vars.cmdif_rev > CMD_IF_REV) {
 		mlx5_core_err(dev, "driver does not support command interface version. driver %d, firmware %d\n",
-			      CMD_IF_REV, cmd->cmdif_rev);
+			      CMD_IF_REV, cmd->vars.cmdif_rev);
 		err = -EOPNOTSUPP;
 		goto err_free_page;
 	}
@@ -2246,9 +2246,9 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	for (i = 0; i < MLX5_CMD_OP_MAX; i++)
 		spin_lock_init(&cmd->stats[i].lock);
 
-	sema_init(&cmd->sem, cmd->max_reg_cmds);
-	sema_init(&cmd->pages_sem, 1);
-	sema_init(&cmd->throttle_sem, DIV_ROUND_UP(cmd->max_reg_cmds, 2));
+	sema_init(&cmd->vars.sem, cmd->vars.max_reg_cmds);
+	sema_init(&cmd->vars.pages_sem, 1);
+	sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
 
 	cmd_h = (u32)((u64)(cmd->dma) >> 32);
 	cmd_l = (u32)(cmd->dma);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 2138f28a29318..9a826fb3ca38a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -176,8 +176,8 @@ static ssize_t slots_read(struct file *filp, char __user *buf, size_t count,
 	int ret;
 
 	cmd = filp->private_data;
-	weight = bitmap_weight(&cmd->bitmask, cmd->max_reg_cmds);
-	field = cmd->max_reg_cmds - weight;
+	weight = bitmap_weight(&cmd->vars.bitmask, cmd->vars.max_reg_cmds);
+	field = cmd->vars.max_reg_cmds - weight;
 	ret = snprintf(tbuf, sizeof(tbuf), "%d\n", field);
 	return simple_read_from_buffer(buf, count, pos, tbuf, ret);
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 56dd3dfe23041..39c5f4087c39d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -287,18 +287,23 @@ struct mlx5_cmd_stats {
 struct mlx5_cmd {
 	struct mlx5_nb    nb;
 
+	/* members which needs to be queried or reinitialized each reload */
+	struct {
+		u16		cmdif_rev;
+		u8		log_sz;
+		u8		log_stride;
+		int		max_reg_cmds;
+		unsigned long	bitmask;
+		struct semaphore sem;
+		struct semaphore pages_sem;
+		struct semaphore throttle_sem;
+	} vars;
 	enum mlx5_cmdif_state	state;
 	void	       *cmd_alloc_buf;
 	dma_addr_t	alloc_dma;
 	int		alloc_size;
 	void	       *cmd_buf;
 	dma_addr_t	dma;
-	u16		cmdif_rev;
-	u8		log_sz;
-	u8		log_stride;
-	int		max_reg_cmds;
-	int		events;
-	u32 __iomem    *vector;
 
 	/* protect command queue allocations
 	 */
@@ -308,12 +313,8 @@ struct mlx5_cmd {
 	 */
 	spinlock_t	token_lock;
 	u8		token;
-	unsigned long	bitmask;
 	char		wq_name[MLX5_CMD_WQ_MAX_NAME];
 	struct workqueue_struct *wq;
-	struct semaphore sem;
-	struct semaphore pages_sem;
-	struct semaphore throttle_sem;
 	int	mode;
 	u16     allowed_opcode;
 	struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS];
-- 
GitLab


From 0714ec9ea1f291447a925657e0808f34b8fbce2b Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Sun, 29 Jan 2023 12:08:30 +0200
Subject: [PATCH 0530/1806] net/mlx5: Remove redundant cmdif revision check

mlx5 is checking the cmdif revision twice, for no reason.
Remove the latter check.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index f175af528fe00..9ced943ebd0d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -2191,16 +2191,15 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	int align = roundup_pow_of_two(size);
 	struct mlx5_cmd *cmd = &dev->cmd;
 	u32 cmd_h, cmd_l;
-	u16 cmd_if_rev;
 	int err;
 	int i;
 
 	memset(cmd, 0, sizeof(*cmd));
-	cmd_if_rev = cmdif_rev(dev);
-	if (cmd_if_rev != CMD_IF_REV) {
+	cmd->vars.cmdif_rev = cmdif_rev(dev);
+	if (cmd->vars.cmdif_rev != CMD_IF_REV) {
 		mlx5_core_err(dev,
 			      "Driver cmdif rev(%d) differs from firmware's(%d)\n",
-			      CMD_IF_REV, cmd_if_rev);
+			      CMD_IF_REV, cmd->vars.cmdif_rev);
 		return -EINVAL;
 	}
 
@@ -2233,14 +2232,6 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	cmd->vars.max_reg_cmds = (1 << cmd->vars.log_sz) - 1;
 	cmd->vars.bitmask = (1UL << cmd->vars.max_reg_cmds) - 1;
 
-	cmd->vars.cmdif_rev = ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16;
-	if (cmd->vars.cmdif_rev > CMD_IF_REV) {
-		mlx5_core_err(dev, "driver does not support command interface version. driver %d, firmware %d\n",
-			      CMD_IF_REV, cmd->vars.cmdif_rev);
-		err = -EOPNOTSUPP;
-		goto err_free_page;
-	}
-
 	spin_lock_init(&cmd->alloc_lock);
 	spin_lock_init(&cmd->token_lock);
 	for (i = 0; i < MLX5_CMD_OP_MAX; i++)
-- 
GitLab


From 06cd555f73caec515a14d42ef052221fa2587ff9 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Wed, 18 Jan 2023 20:55:54 +0200
Subject: [PATCH 0531/1806] net/mlx5: split mlx5_cmd_init() to probe and reload
 routines

There is no need to destroy and allocate cmd SW structs during reload,
this is time consuming for no reason.
Hence, split mlx5_cmd_init() to probe and reload routines.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 121 ++++++++++--------
 .../net/ethernet/mellanox/mlx5/core/main.c    |  15 ++-
 .../ethernet/mellanox/mlx5/core/mlx5_core.h   |   2 +
 3 files changed, 82 insertions(+), 56 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 9ced943ebd0d1..45edd5a110c86 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1548,7 +1548,6 @@ static void clean_debug_files(struct mlx5_core_dev *dev)
 	if (!mlx5_debugfs_root)
 		return;
 
-	mlx5_cmdif_debugfs_cleanup(dev);
 	debugfs_remove_recursive(dbg->dbg_root);
 }
 
@@ -1563,8 +1562,6 @@ static void create_debugfs_files(struct mlx5_core_dev *dev)
 	debugfs_create_file("out_len", 0600, dbg->dbg_root, dev, &olfops);
 	debugfs_create_u8("status", 0600, dbg->dbg_root, &dbg->status);
 	debugfs_create_file("run", 0200, dbg->dbg_root, dev, &fops);
-
-	mlx5_cmdif_debugfs_init(dev);
 }
 
 void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode)
@@ -2190,19 +2187,10 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	int size = sizeof(struct mlx5_cmd_prot_block);
 	int align = roundup_pow_of_two(size);
 	struct mlx5_cmd *cmd = &dev->cmd;
-	u32 cmd_h, cmd_l;
+	u32 cmd_l;
 	int err;
 	int i;
 
-	memset(cmd, 0, sizeof(*cmd));
-	cmd->vars.cmdif_rev = cmdif_rev(dev);
-	if (cmd->vars.cmdif_rev != CMD_IF_REV) {
-		mlx5_core_err(dev,
-			      "Driver cmdif rev(%d) differs from firmware's(%d)\n",
-			      CMD_IF_REV, cmd->vars.cmdif_rev);
-		return -EINVAL;
-	}
-
 	cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
 	if (!cmd->pool)
 		return -ENOMEM;
@@ -2211,43 +2199,93 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	if (err)
 		goto err_free_pool;
 
+	cmd_l = (u32)(cmd->dma);
+	if (cmd_l & 0xfff) {
+		mlx5_core_err(dev, "invalid command queue address\n");
+		err = -ENOMEM;
+		goto err_cmd_page;
+	}
+	cmd->checksum_disabled = 1;
+
+	spin_lock_init(&cmd->alloc_lock);
+	spin_lock_init(&cmd->token_lock);
+	for (i = 0; i < MLX5_CMD_OP_MAX; i++)
+		spin_lock_init(&cmd->stats[i].lock);
+
+	create_msg_cache(dev);
+
+	set_wqname(dev);
+	cmd->wq = create_singlethread_workqueue(cmd->wq_name);
+	if (!cmd->wq) {
+		mlx5_core_err(dev, "failed to create command workqueue\n");
+		err = -ENOMEM;
+		goto err_cache;
+	}
+
+	mlx5_cmdif_debugfs_init(dev);
+
+	return 0;
+
+err_cache:
+	destroy_msg_cache(dev);
+err_cmd_page:
+	free_cmd_page(dev, cmd);
+err_free_pool:
+	dma_pool_destroy(cmd->pool);
+	return err;
+}
+
+void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
+{
+	struct mlx5_cmd *cmd = &dev->cmd;
+
+	mlx5_cmdif_debugfs_cleanup(dev);
+	destroy_workqueue(cmd->wq);
+	destroy_msg_cache(dev);
+	free_cmd_page(dev, cmd);
+	dma_pool_destroy(cmd->pool);
+}
+
+int mlx5_cmd_enable(struct mlx5_core_dev *dev)
+{
+	struct mlx5_cmd *cmd = &dev->cmd;
+	u32 cmd_h, cmd_l;
+
+	memset(&cmd->vars, 0, sizeof(cmd->vars));
+	cmd->vars.cmdif_rev = cmdif_rev(dev);
+	if (cmd->vars.cmdif_rev != CMD_IF_REV) {
+		mlx5_core_err(dev,
+			      "Driver cmdif rev(%d) differs from firmware's(%d)\n",
+			      CMD_IF_REV, cmd->vars.cmdif_rev);
+		return -EINVAL;
+	}
+
 	cmd_l = ioread32be(&dev->iseg->cmdq_addr_l_sz) & 0xff;
 	cmd->vars.log_sz = cmd_l >> 4 & 0xf;
 	cmd->vars.log_stride = cmd_l & 0xf;
 	if (1 << cmd->vars.log_sz > MLX5_MAX_COMMANDS) {
 		mlx5_core_err(dev, "firmware reports too many outstanding commands %d\n",
 			      1 << cmd->vars.log_sz);
-		err = -EINVAL;
-		goto err_free_page;
+		return -EINVAL;
 	}
 
 	if (cmd->vars.log_sz + cmd->vars.log_stride > MLX5_ADAPTER_PAGE_SHIFT) {
 		mlx5_core_err(dev, "command queue size overflow\n");
-		err = -EINVAL;
-		goto err_free_page;
+		return -EINVAL;
 	}
 
 	cmd->state = MLX5_CMDIF_STATE_DOWN;
-	cmd->checksum_disabled = 1;
 	cmd->vars.max_reg_cmds = (1 << cmd->vars.log_sz) - 1;
 	cmd->vars.bitmask = (1UL << cmd->vars.max_reg_cmds) - 1;
 
-	spin_lock_init(&cmd->alloc_lock);
-	spin_lock_init(&cmd->token_lock);
-	for (i = 0; i < MLX5_CMD_OP_MAX; i++)
-		spin_lock_init(&cmd->stats[i].lock);
-
 	sema_init(&cmd->vars.sem, cmd->vars.max_reg_cmds);
 	sema_init(&cmd->vars.pages_sem, 1);
 	sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
 
 	cmd_h = (u32)((u64)(cmd->dma) >> 32);
 	cmd_l = (u32)(cmd->dma);
-	if (cmd_l & 0xfff) {
-		mlx5_core_err(dev, "invalid command queue address\n");
-		err = -ENOMEM;
-		goto err_free_page;
-	}
+	if (WARN_ON(cmd_l & 0xfff))
+		return -EINVAL;
 
 	iowrite32be(cmd_h, &dev->iseg->cmdq_addr_h);
 	iowrite32be(cmd_l, &dev->iseg->cmdq_addr_l_sz);
@@ -2260,40 +2298,17 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	cmd->mode = CMD_MODE_POLLING;
 	cmd->allowed_opcode = CMD_ALLOWED_OPCODE_ALL;
 
-	create_msg_cache(dev);
-
-	set_wqname(dev);
-	cmd->wq = create_singlethread_workqueue(cmd->wq_name);
-	if (!cmd->wq) {
-		mlx5_core_err(dev, "failed to create command workqueue\n");
-		err = -ENOMEM;
-		goto err_cache;
-	}
-
 	create_debugfs_files(dev);
 
 	return 0;
-
-err_cache:
-	destroy_msg_cache(dev);
-
-err_free_page:
-	free_cmd_page(dev, cmd);
-
-err_free_pool:
-	dma_pool_destroy(cmd->pool);
-	return err;
 }
 
-void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
+void mlx5_cmd_disable(struct mlx5_core_dev *dev)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 
 	clean_debug_files(dev);
-	destroy_workqueue(cmd->wq);
-	destroy_msg_cache(dev);
-	free_cmd_page(dev, cmd);
-	dma_pool_destroy(cmd->pool);
+	flush_workqueue(cmd->wq);
 }
 
 void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a79c9b8286a7d..740d4476c413b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1142,7 +1142,7 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 		return err;
 	}
 
-	err = mlx5_cmd_init(dev);
+	err = mlx5_cmd_enable(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed initializing command interface, aborting\n");
 		return err;
@@ -1196,7 +1196,7 @@ stop_health_poll:
 	mlx5_stop_health_poll(dev, boot);
 err_cmd_cleanup:
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
-	mlx5_cmd_cleanup(dev);
+	mlx5_cmd_disable(dev);
 
 	return err;
 }
@@ -1207,7 +1207,7 @@ static void mlx5_function_disable(struct mlx5_core_dev *dev, bool boot)
 	mlx5_core_disable_hca(dev, 0);
 	mlx5_stop_health_poll(dev, boot);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
-	mlx5_cmd_cleanup(dev);
+	mlx5_cmd_disable(dev);
 }
 
 static int mlx5_function_open(struct mlx5_core_dev *dev)
@@ -1796,6 +1796,12 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	debugfs_create_file("vhca_id", 0400, priv->dbg.dbg_root, dev, &vhca_id_fops);
 	INIT_LIST_HEAD(&priv->traps);
 
+	err = mlx5_cmd_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed initializing cmdif SW structs, aborting\n");
+		goto err_cmd_init;
+	}
+
 	err = mlx5_tout_init(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed initializing timeouts, aborting\n");
@@ -1841,6 +1847,8 @@ err_pagealloc_init:
 err_health_init:
 	mlx5_tout_cleanup(dev);
 err_timeout_init:
+	mlx5_cmd_cleanup(dev);
+err_cmd_init:
 	debugfs_remove(dev->priv.dbg.dbg_root);
 	mutex_destroy(&priv->pgdir_mutex);
 	mutex_destroy(&priv->alloc_mutex);
@@ -1863,6 +1871,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_health_cleanup(dev);
 	mlx5_tout_cleanup(dev);
+	mlx5_cmd_cleanup(dev);
 	debugfs_remove_recursive(dev->priv.dbg.dbg_root);
 	mutex_destroy(&priv->pgdir_mutex);
 	mutex_destroy(&priv->alloc_mutex);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index c4be257c043d4..43b0144121ca2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -178,6 +178,8 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev);
 int mlx5_query_board_id(struct mlx5_core_dev *dev);
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
+int mlx5_cmd_enable(struct mlx5_core_dev *dev);
+void mlx5_cmd_disable(struct mlx5_core_dev *dev);
 void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
 			enum mlx5_cmdif_state cmdif_state);
 int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id);
-- 
GitLab


From b90ebfc018b087ba1e4981b298b58733236ff296 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 19 Jan 2023 09:10:50 +0200
Subject: [PATCH 0532/1806] net/mlx5: Allocate command stats with xarray

Command stats is an array with more than 2K entries, which amounts to
~180KB. This is way more than actually needed, as only ~190 entries
are being used.

Therefore, replace the array with xarray.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 15 +++++-----
 .../net/ethernet/mellanox/mlx5/core/debugfs.c | 30 ++++++++++++++++++-
 include/linux/mlx5/driver.h                   |  2 +-
 3 files changed, 37 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 45edd5a110c86..afb348579577c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1225,8 +1225,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 		goto out_free;
 
 	ds = ent->ts2 - ent->ts1;
-	if (ent->op < MLX5_CMD_OP_MAX) {
-		stats = &cmd->stats[ent->op];
+	stats = xa_load(&cmd->stats, ent->op);
+	if (stats) {
 		spin_lock_irq(&stats->lock);
 		stats->sum += ds;
 		++stats->n;
@@ -1695,8 +1695,8 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
 
 			if (ent->callback) {
 				ds = ent->ts2 - ent->ts1;
-				if (ent->op < MLX5_CMD_OP_MAX) {
-					stats = &cmd->stats[ent->op];
+				stats = xa_load(&cmd->stats, ent->op);
+				if (stats) {
 					spin_lock_irqsave(&stats->lock, flags);
 					stats->sum += ds;
 					++stats->n;
@@ -1923,7 +1923,9 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status,
 	if (!err || !(strcmp(namep, "unknown command opcode")))
 		return;
 
-	stats = &dev->cmd.stats[opcode];
+	stats = xa_load(&dev->cmd.stats, opcode);
+	if (!stats)
+		return;
 	spin_lock_irq(&stats->lock);
 	stats->failed++;
 	if (err < 0)
@@ -2189,7 +2191,6 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	struct mlx5_cmd *cmd = &dev->cmd;
 	u32 cmd_l;
 	int err;
-	int i;
 
 	cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
 	if (!cmd->pool)
@@ -2209,8 +2210,6 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 
 	spin_lock_init(&cmd->alloc_lock);
 	spin_lock_init(&cmd->token_lock);
-	for (i = 0; i < MLX5_CMD_OP_MAX; i++)
-		spin_lock_init(&cmd->stats[i].lock);
 
 	create_msg_cache(dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 9a826fb3ca38a..09652dc891154 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -188,6 +188,24 @@ static const struct file_operations slots_fops = {
 	.read	= slots_read,
 };
 
+static struct mlx5_cmd_stats *
+mlx5_cmdif_alloc_stats(struct xarray *stats_xa, int opcode)
+{
+	struct mlx5_cmd_stats *stats = kzalloc(sizeof(*stats), GFP_KERNEL);
+	int err;
+
+	if (!stats)
+		return NULL;
+
+	err = xa_insert(stats_xa, opcode, stats, GFP_KERNEL);
+	if (err) {
+		kfree(stats);
+		return NULL;
+	}
+	spin_lock_init(&stats->lock);
+	return stats;
+}
+
 void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_cmd_stats *stats;
@@ -200,10 +218,14 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev)
 
 	debugfs_create_file("slots_inuse", 0400, *cmd, &dev->cmd, &slots_fops);
 
+	xa_init(&dev->cmd.stats);
+
 	for (i = 0; i < MLX5_CMD_OP_MAX; i++) {
-		stats = &dev->cmd.stats[i];
 		namep = mlx5_command_str(i);
 		if (strcmp(namep, "unknown command opcode")) {
+			stats = mlx5_cmdif_alloc_stats(&dev->cmd.stats, i);
+			if (!stats)
+				continue;
 			stats->root = debugfs_create_dir(namep, *cmd);
 
 			debugfs_create_file("average", 0400, stats->root, stats,
@@ -224,7 +246,13 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev)
 
 void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev)
 {
+	struct mlx5_cmd_stats *stats;
+	unsigned long i;
+
 	debugfs_remove_recursive(dev->priv.dbg.cmdif_debugfs);
+	xa_for_each(&dev->cmd.stats, i, stats)
+		kfree(stats);
+	xa_destroy(&dev->cmd.stats);
 }
 
 void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 39c5f4087c39d..f21703fb75fde 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -322,7 +322,7 @@ struct mlx5_cmd {
 	struct mlx5_cmd_debug dbg;
 	struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES];
 	int checksum_disabled;
-	struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX];
+	struct xarray stats;
 };
 
 struct mlx5_cmd_mailbox {
-- 
GitLab


From 9ec85cc9c90e7cc2d91531132e9c1f1ebe067ce2 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Sun, 2 Jul 2023 01:19:29 +0300
Subject: [PATCH 0533/1806] net/mlx5e: Remove duplicate code for user flow

Flow table and priority detection is same for IP user flows and other L4
flows. Hence, use same code for all these flow types.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index aac32e505c14f..08eb186615c8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -96,10 +96,6 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
 	case UDP_V4_FLOW:
 	case TCP_V6_FLOW:
 	case UDP_V6_FLOW:
-		max_tuples = ETHTOOL_NUM_L3_L4_FTS;
-		prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
-		eth_ft = &ethtool->l3_l4_ft[prio];
-		break;
 	case IP_USER_FLOW:
 	case IPV6_USER_FLOW:
 		max_tuples = ETHTOOL_NUM_L3_L4_FTS;
-- 
GitLab


From b9335a757232e9ac03e5fc8ed71d834661b7a8ac Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Sun, 2 Jul 2023 01:25:08 +0300
Subject: [PATCH 0534/1806] net/mlx5e: Make flow classification filters static

Get and set flow classification filters are used in a single file.
Hence, make them static.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h         | 3 ---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 6 +++---
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index b1807bfb815f1..0f8f70b914855 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1167,9 +1167,6 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc);
 int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key,
 		   const u8 hfunc);
-int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
-		    u32 *rule_locs);
-int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd);
 u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv);
 u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv);
 int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 27861b68ced57..04195a673a6be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -2163,8 +2163,8 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev)
 	return priv->channels.params.pflags;
 }
 
-int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
-		    u32 *rule_locs)
+static int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
+			   u32 *rule_locs)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
@@ -2181,7 +2181,7 @@ int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
 	return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs);
 }
 
-int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
-- 
GitLab


From 550449d8e3890b19a6d780cb5854af1ff0a8961b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 1 Jun 2023 08:22:43 +0200
Subject: [PATCH 0535/1806] net/mlx5: Don't check vport->enabled in port ops

vport->enabled is always set for a vport for which a devlink port is
registered, therefore the checks in the ops are pointless.
Remove those.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 28 ++++---------------
 1 file changed, 6 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b4b8cb7885739..c192000e36147 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4125,7 +4125,6 @@ int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enab
 {
 	struct mlx5_eswitch *esw;
 	struct mlx5_vport *vport;
-	int err = -EOPNOTSUPP;
 
 	esw = mlx5_devlink_eswitch_get(port->devlink);
 	if (IS_ERR(esw))
@@ -4133,7 +4132,7 @@ int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enab
 
 	if (!MLX5_CAP_GEN(esw->dev, migration)) {
 		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support migration");
-		return err;
+		return -EOPNOTSUPP;
 	}
 
 	vport = mlx5_devlink_port_fn_get_vport(port, esw);
@@ -4143,12 +4142,9 @@ int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enab
 	}
 
 	mutex_lock(&esw->state_lock);
-	if (vport->enabled) {
-		*is_enabled = vport->info.mig_enabled;
-		err = 0;
-	}
+	*is_enabled = vport->info.mig_enabled;
 	mutex_unlock(&esw->state_lock);
-	return err;
+	return 0;
 }
 
 int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
@@ -4177,10 +4173,6 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
 	}
 
 	mutex_lock(&esw->state_lock);
-	if (!vport->enabled) {
-		NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
-		goto out;
-	}
 
 	if (vport->info.mig_enabled == enable) {
 		err = 0;
@@ -4224,7 +4216,6 @@ int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled,
 {
 	struct mlx5_eswitch *esw;
 	struct mlx5_vport *vport;
-	int err = -EOPNOTSUPP;
 
 	esw = mlx5_devlink_eswitch_get(port->devlink);
 	if (IS_ERR(esw))
@@ -4237,12 +4228,9 @@ int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled,
 	}
 
 	mutex_lock(&esw->state_lock);
-	if (vport->enabled) {
-		*is_enabled = vport->info.roce_enabled;
-		err = 0;
-	}
+	*is_enabled = vport->info.roce_enabled;
 	mutex_unlock(&esw->state_lock);
-	return err;
+	return 0;
 }
 
 int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable,
@@ -4251,10 +4239,10 @@ int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable,
 	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
 	struct mlx5_eswitch *esw;
 	struct mlx5_vport *vport;
-	int err = -EOPNOTSUPP;
 	void *query_ctx;
 	void *hca_caps;
 	u16 vport_num;
+	int err;
 
 	esw = mlx5_devlink_eswitch_get(port->devlink);
 	if (IS_ERR(esw))
@@ -4268,10 +4256,6 @@ int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable,
 	vport_num = vport->vport;
 
 	mutex_lock(&esw->state_lock);
-	if (!vport->enabled) {
-		NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
-		goto out;
-	}
 
 	if (vport->info.roce_enabled == enable) {
 		err = 0;
-- 
GitLab


From 3e82a9cf579e18ca6b7cd0344597e5e8c5869fdb Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Wed, 31 May 2023 13:25:15 +0200
Subject: [PATCH 0536/1806] net/mlx5: Remove pointless devlink_rate checks

It is guaranteed that the devlink rate leaf is created during init paths.
No need to check during cleanup. Remove the checks.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/esw/devlink_port.c   | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index af779c700278e..433541ac36a77 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -132,10 +132,8 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo
 	if (IS_ERR(vport))
 		return;
 
-	if (vport->dl_port->devlink_rate) {
-		mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
-		devl_rate_leaf_destroy(vport->dl_port);
-	}
+	mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
+	devl_rate_leaf_destroy(vport->dl_port);
 
 	devl_port_unregister(vport->dl_port);
 	mlx5_esw_dl_port_free(vport->dl_port);
@@ -211,10 +209,8 @@ void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num
 	if (IS_ERR(vport))
 		return;
 
-	if (vport->dl_port->devlink_rate) {
-		mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
-		devl_rate_leaf_destroy(vport->dl_port);
-	}
+	mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
+	devl_rate_leaf_destroy(vport->dl_port);
 
 	devl_port_unregister(vport->dl_port);
 	vport->dl_port = NULL;
-- 
GitLab


From b71863876f840a12642ee4dc483471aec8793ba6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 25 May 2023 09:15:20 +0200
Subject: [PATCH 0537/1806] net/mlx5: Make mlx5_esw_offloads_rep_load/unload()
 static

mlx5_esw_offloads_rep_load/unload() functions are not used
outside of eswitch_offloads.c. Make them static.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h          | 3 ---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 4 ++--
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 9b5a1651b8776..6f360a15aa62d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -730,9 +730,6 @@ void mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw,
 int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num);
 void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num);
 
-int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num);
-void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num);
-
 int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num,
 			    enum mlx5_eswitch_vport_event enabled_events);
 void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index c192000e36147..b4df57962b2b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2391,7 +2391,7 @@ static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
 		__esw_offloads_unload_rep(esw, rep, rep_type);
 }
 
-int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num)
+static int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct mlx5_eswitch_rep *rep;
 	int rep_type;
@@ -2415,7 +2415,7 @@ err_reps:
 	return err;
 }
 
-void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num)
+static void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct mlx5_eswitch_rep *rep;
 	int rep_type;
-- 
GitLab


From 329980d05d8ce9682a94fb3a6e4e6fc930293a01 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 25 May 2023 09:25:48 +0200
Subject: [PATCH 0538/1806] net/mlx5: Make mlx5_eswitch_load/unload_vport()
 static

mlx5_eswitch_load/unload_vport()() functions are not used
outside of eswitch.c. Make them static.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 7 +++----
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 4 ----
 2 files changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 243c455f10297..4b13269f49e0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1068,9 +1068,8 @@ static void mlx5_eswitch_clear_ec_vf_vports_info(struct mlx5_eswitch *esw)
 	}
 }
 
-/* Public E-Switch API */
-int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num,
-			    enum mlx5_eswitch_vport_event enabled_events)
+static int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num,
+				   enum mlx5_eswitch_vport_event enabled_events)
 {
 	int err;
 
@@ -1089,7 +1088,7 @@ err_rep:
 	return err;
 }
 
-void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num)
+static void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	esw_offloads_unload_rep(esw, vport_num);
 	mlx5_esw_vport_disable(esw, vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 6f360a15aa62d..837bdd03557ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -730,10 +730,6 @@ void mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw,
 int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num);
 void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num);
 
-int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num,
-			    enum mlx5_eswitch_vport_event enabled_events);
-void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num);
-
 int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
 				enum mlx5_eswitch_vport_event enabled_events);
 void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs);
-- 
GitLab


From 9eca8bb8da4385b02bd02b6876af8d4225bf4713 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 25 May 2023 09:42:09 +0200
Subject: [PATCH 0539/1806] net/mlx5: Give esw_offloads_load/unload_rep()
 "mlx5_" prefix

As esw_offloads_load/unload_rep() are used outside eswitch.c it is nicer
for them to have "mlx5_" prefix. Add it.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c      |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h      |  4 ++--
 .../net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 10 +++++-----
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 4b13269f49e0a..4a7a13169a90c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1077,7 +1077,7 @@ static int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num,
 	if (err)
 		return err;
 
-	err = esw_offloads_load_rep(esw, vport_num);
+	err = mlx5_esw_offloads_load_rep(esw, vport_num);
 	if (err)
 		goto err_rep;
 
@@ -1090,7 +1090,7 @@ err_rep:
 
 static void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	esw_offloads_unload_rep(esw, vport_num);
+	mlx5_esw_offloads_unload_rep(esw, vport_num);
 	mlx5_esw_vport_disable(esw, vport_num);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 837bdd03557ba..2944c92074870 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -727,8 +727,8 @@ void mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw,
 				   u16 vport,
 				   struct mlx5_flow_spec *spec);
 
-int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num);
-void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num);
+int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num);
+void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num);
 
 int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
 				enum mlx5_eswitch_vport_event enabled_events);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b4df57962b2b1..f83667b4339ec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2425,7 +2425,7 @@ static void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num
 		__esw_offloads_unload_rep(esw, rep, rep_type);
 }
 
-int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
+int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	int err;
 
@@ -2449,7 +2449,7 @@ load_err:
 	return err;
 }
 
-void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return;
@@ -3361,7 +3361,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 			vport->info.link_state = MLX5_VPORT_ADMIN_STATE_DOWN;
 
 	/* Uplink vport rep must load first. */
-	err = esw_offloads_load_rep(esw, MLX5_VPORT_UPLINK);
+	err = mlx5_esw_offloads_load_rep(esw, MLX5_VPORT_UPLINK);
 	if (err)
 		goto err_uplink;
 
@@ -3372,7 +3372,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	return 0;
 
 err_vports:
-	esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
+	mlx5_esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
 err_uplink:
 	esw_offloads_steering_cleanup(esw);
 err_steering_init:
@@ -3410,7 +3410,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 void esw_offloads_disable(struct mlx5_eswitch *esw)
 {
 	mlx5_eswitch_disable_pf_vf_vports(esw);
-	esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
+	mlx5_esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
 	esw_set_passing_vport_metadata(esw, false);
 	esw_offloads_steering_cleanup(esw);
 	mapping_destroy(esw->offloads.reg_c0_obj_pool);
-- 
GitLab


From ef27ba5c845d22de79447d7da8e12471168a8e77 Mon Sep 17 00:00:00 2001
From: Patrick Rohr <prohr@google.com>
Date: Wed, 26 Jul 2023 11:47:42 -0700
Subject: [PATCH 0540/1806] net: remove comment in ndisc_router_discovery

Removes superfluous (and misplaced) comment from ndisc_router_discovery.

Signed-off-by: Patrick Rohr <prohr@google.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230726184742.342825-1-prohr@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ndisc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 29ddad1c1a2f3..95750fbf6782e 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1266,10 +1266,6 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
 	}
 #endif
 
-	/*
-	 *	set the RA_RECV flag in the interface
-	 */
-
 	in6_dev = __in6_dev_get(skb->dev);
 	if (!in6_dev) {
 		ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n",
-- 
GitLab


From 4d66f235c7904576a7df396791b96bc7d259507b Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 26 Jul 2023 22:31:41 +0800
Subject: [PATCH 0541/1806] bridge: Remove unused declaration
 br_multicast_set_hash_max()

Since commit 19e3a9c90c53 ("net: bridge: convert multicast to generic rhashtable")
this is not used, so can remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20230726143141.11704-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_private.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 51e4ca54b5377..a1f4acfa69949 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -974,7 +974,6 @@ int br_multicast_set_vlan_router(struct net_bridge_vlan *v, u8 mcast_router);
 int br_multicast_toggle(struct net_bridge *br, unsigned long val,
 			struct netlink_ext_ack *extack);
 int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val);
-int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val);
 int br_multicast_set_igmp_version(struct net_bridge_mcast *brmctx,
 				  unsigned long val);
 #if IS_ENABLED(CONFIG_IPV6)
-- 
GitLab


From d4a80cc69aea74fe220dc9faa0d6d62e4dfa871a Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 26 Jul 2023 22:32:39 +0800
Subject: [PATCH 0542/1806] dccp: Remove unused declaration
 dccp_feat_initialise_sysctls()

This is never used, so can remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230726143239.9904-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/dccp/feat.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/dccp/feat.h b/net/dccp/feat.h
index d76c9be5bfca0..57d9c026aa3f5 100644
--- a/net/dccp/feat.h
+++ b/net/dccp/feat.h
@@ -105,7 +105,6 @@ extern int	     sysctl_dccp_rx_ccid;
 extern int	     sysctl_dccp_tx_ccid;
 
 int dccp_feat_init(struct sock *sk);
-void dccp_feat_initialise_sysctls(void);
 int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local,
 			  u8 const *list, u8 len);
 int dccp_feat_parse_options(struct sock *, struct dccp_request_sock *,
-- 
GitLab


From d0358c1a37db4c46b9a1cd6c1b36e5a24ff970f9 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 26 Jul 2023 22:37:15 +0800
Subject: [PATCH 0543/1806] net: Remove unused declaration dev_restart()

This is not used, so can remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230726143715.24700-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 11652e464f5df..32a4cdf37dd47 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3130,8 +3130,6 @@ struct net_device *netdev_get_by_name(struct net *net, const char *name,
 				      netdevice_tracker *tracker, gfp_t gfp);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
 struct net_device *dev_get_by_napi_id(unsigned int napi_id);
-int dev_restart(struct net_device *dev);
-
 
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 				  unsigned short type,
-- 
GitLab


From 994650353cae9e10cca7fd61de79c911aa8ed287 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 26 Jul 2023 22:40:54 +0800
Subject: [PATCH 0544/1806] net: datalink: Remove unused declarations

These declarations is not used after ipx protocol removed.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230726144054.28780-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/datalink.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/datalink.h b/include/net/datalink.h
index c837ffc7ebf8a..6c529a40e00db 100644
--- a/include/net/datalink.h
+++ b/include/net/datalink.h
@@ -23,6 +23,4 @@ struct datalink_proto {
 	struct list_head node;
 };
 
-struct datalink_proto *make_EII_client(void);
-void destroy_EII_client(struct datalink_proto *dl);
 #endif
-- 
GitLab


From 10d78a66a5f29fbbde1b09b5139c17c436b08c6e Mon Sep 17 00:00:00 2001
From: "Jose E. Marchesi" <jose.marchesi@oracle.com>
Date: Wed, 26 Jul 2023 11:25:43 +0200
Subject: [PATCH 0545/1806] bpf, docs: fix BPF_NEG entry in instruction-set.rst

This patch fixes the documentation of the BPF_NEG instruction to
denote that it does not use the source register operand.

Signed-off-by: Jose E. Marchesi <jose.marchesi@oracle.com>
Acked-by: Dave Thaler <dthaler@microsoft.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230726092543.6362-1-jose.marchesi@oracle.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/bpf/standardization/instruction-set.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 751e657973f0b..6ef5534b410a9 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -165,7 +165,7 @@ BPF_OR    0x40   dst \|= src
 BPF_AND   0x50   dst &= src
 BPF_LSH   0x60   dst <<= (src & mask)
 BPF_RSH   0x70   dst >>= (src & mask)
-BPF_NEG   0x80   dst = -src
+BPF_NEG   0x80   dst = -dst
 BPF_MOD   0x90   dst = (src != 0) ? (dst % src) : dst
 BPF_XOR   0xa0   dst ^= src
 BPF_MOV   0xb0   dst = src
-- 
GitLab


From 1f9a1ea821ff25353a0e80d971e7958cd55b47a3 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:11:56 -0700
Subject: [PATCH 0546/1806] bpf: Support new sign-extension load insns

Add interpreter/jit support for new sign-extension load insns
which adds a new mode (BPF_MEMSX).
Also add verifier support to recognize these insns and to
do proper verification with new insns. In verifier, besides
to deduce proper bounds for the dst_reg, probed memory access
is also properly handled.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011156.3711870-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c    |  42 +++++++++-
 include/linux/filter.h         |   3 +
 include/uapi/linux/bpf.h       |   1 +
 kernel/bpf/core.c              |  21 +++++
 kernel/bpf/verifier.c          | 140 +++++++++++++++++++++++++++------
 tools/include/uapi/linux/bpf.h |   1 +
 6 files changed, 181 insertions(+), 27 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 83c4b45dc65f9..54478a9c93e1f 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -779,6 +779,29 @@ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 	*pprog = prog;
 }
 
+/* LDSX: dst_reg = *(s8*)(src_reg + off) */
+static void emit_ldsx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
+{
+	u8 *prog = *pprog;
+
+	switch (size) {
+	case BPF_B:
+		/* Emit 'movsx rax, byte ptr [rax + off]' */
+		EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xBE);
+		break;
+	case BPF_H:
+		/* Emit 'movsx rax, word ptr [rax + off]' */
+		EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xBF);
+		break;
+	case BPF_W:
+		/* Emit 'movsx rax, dword ptr [rax+0x14]' */
+		EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x63);
+		break;
+	}
+	emit_insn_suffix(&prog, src_reg, dst_reg, off);
+	*pprog = prog;
+}
+
 /* STX: *(u8*)(dst_reg + off) = src_reg */
 static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 {
@@ -1370,9 +1393,17 @@ st:			if (is_imm8(insn->off))
 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
 		case BPF_LDX | BPF_MEM | BPF_DW:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+			/* LDXS: dst_reg = *(s8*)(src_reg + off) */
+		case BPF_LDX | BPF_MEMSX | BPF_B:
+		case BPF_LDX | BPF_MEMSX | BPF_H:
+		case BPF_LDX | BPF_MEMSX | BPF_W:
+		case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
+		case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
+		case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
 			insn_off = insn->off;
 
-			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
+			if (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+			    BPF_MODE(insn->code) == BPF_PROBE_MEMSX) {
 				/* Conservatively check that src_reg + insn->off is a kernel address:
 				 *   src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE
 				 * src_reg is used as scratch for src_reg += insn->off and restored
@@ -1415,8 +1446,13 @@ st:			if (is_imm8(insn->off))
 				start_of_ldx = prog;
 				end_of_jmp[-1] = start_of_ldx - end_of_jmp;
 			}
-			emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off);
-			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
+			if (BPF_MODE(insn->code) == BPF_PROBE_MEMSX ||
+			    BPF_MODE(insn->code) == BPF_MEMSX)
+				emit_ldsx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off);
+			else
+				emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off);
+			if (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+			    BPF_MODE(insn->code) == BPF_PROBE_MEMSX) {
 				struct exception_table_entry *ex;
 				u8 *_insn = image + proglen + (start_of_ldx - temp);
 				s64 delta;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index f69114083ec71..a93242b5516b7 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -69,6 +69,9 @@ struct ctl_table_header;
 /* unused opcode to mark special load instruction. Same as BPF_ABS */
 #define BPF_PROBE_MEM	0x20
 
+/* unused opcode to mark special ldsx instruction. Same as BPF_IND */
+#define BPF_PROBE_MEMSX	0x40
+
 /* unused opcode to mark call to interpreter with arguments */
 #define BPF_CALL_ARGS	0xe0
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7fc98f4b63e94..14fd26b09e4b3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -19,6 +19,7 @@
 
 /* ld/ldx fields */
 #define BPF_DW		0x18	/* double word (64-bit) */
+#define BPF_MEMSX	0x80	/* load with sign extension */
 #define BPF_ATOMIC	0xc0	/* atomic memory ops - op type in immediate */
 #define BPF_XADD	0xc0	/* exclusive add - legacy name */
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index dc85240a01342..01b72fc001f6d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1610,6 +1610,9 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 	INSN_3(LDX, MEM, H),			\
 	INSN_3(LDX, MEM, W),			\
 	INSN_3(LDX, MEM, DW),			\
+	INSN_3(LDX, MEMSX, B),			\
+	INSN_3(LDX, MEMSX, H),			\
+	INSN_3(LDX, MEMSX, W),			\
 	/*   Immediate based. */		\
 	INSN_3(LD, IMM, DW)
 
@@ -1666,6 +1669,9 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
 		[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
 		[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
 		[BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW,
+		[BPF_LDX | BPF_PROBE_MEMSX | BPF_B] = &&LDX_PROBE_MEMSX_B,
+		[BPF_LDX | BPF_PROBE_MEMSX | BPF_H] = &&LDX_PROBE_MEMSX_H,
+		[BPF_LDX | BPF_PROBE_MEMSX | BPF_W] = &&LDX_PROBE_MEMSX_W,
 	};
 #undef BPF_INSN_3_LBL
 #undef BPF_INSN_2_LBL
@@ -1942,6 +1948,21 @@ out:
 	LDST(DW, u64)
 #undef LDST
 
+#define LDSX(SIZEOP, SIZE)						\
+	LDX_MEMSX_##SIZEOP:						\
+		DST = *(SIZE *)(unsigned long) (SRC + insn->off);	\
+		CONT;							\
+	LDX_PROBE_MEMSX_##SIZEOP:					\
+		bpf_probe_read_kernel(&DST, sizeof(SIZE),		\
+				      (const void *)(long) (SRC + insn->off));	\
+		DST = *((SIZE *)&DST);					\
+		CONT;
+
+	LDSX(B,   s8)
+	LDSX(H,  s16)
+	LDSX(W,  s32)
+#undef LDSX
+
 #define ATOMIC_ALU_OP(BOP, KOP)						\
 		case BOP:						\
 			if (BPF_SIZE(insn->code) == BPF_W)		\
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 71473c19093d3..b154854034e00 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5827,6 +5827,84 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
 	__reg_combine_64_into_32(reg);
 }
 
+static void set_sext64_default_val(struct bpf_reg_state *reg, int size)
+{
+	if (size == 1) {
+		reg->smin_value = reg->s32_min_value = S8_MIN;
+		reg->smax_value = reg->s32_max_value = S8_MAX;
+	} else if (size == 2) {
+		reg->smin_value = reg->s32_min_value = S16_MIN;
+		reg->smax_value = reg->s32_max_value = S16_MAX;
+	} else {
+		/* size == 4 */
+		reg->smin_value = reg->s32_min_value = S32_MIN;
+		reg->smax_value = reg->s32_max_value = S32_MAX;
+	}
+	reg->umin_value = reg->u32_min_value = 0;
+	reg->umax_value = U64_MAX;
+	reg->u32_max_value = U32_MAX;
+	reg->var_off = tnum_unknown;
+}
+
+static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size)
+{
+	s64 init_s64_max, init_s64_min, s64_max, s64_min, u64_cval;
+	u64 top_smax_value, top_smin_value;
+	u64 num_bits = size * 8;
+
+	if (tnum_is_const(reg->var_off)) {
+		u64_cval = reg->var_off.value;
+		if (size == 1)
+			reg->var_off = tnum_const((s8)u64_cval);
+		else if (size == 2)
+			reg->var_off = tnum_const((s16)u64_cval);
+		else
+			/* size == 4 */
+			reg->var_off = tnum_const((s32)u64_cval);
+
+		u64_cval = reg->var_off.value;
+		reg->smax_value = reg->smin_value = u64_cval;
+		reg->umax_value = reg->umin_value = u64_cval;
+		reg->s32_max_value = reg->s32_min_value = u64_cval;
+		reg->u32_max_value = reg->u32_min_value = u64_cval;
+		return;
+	}
+
+	top_smax_value = ((u64)reg->smax_value >> num_bits) << num_bits;
+	top_smin_value = ((u64)reg->smin_value >> num_bits) << num_bits;
+
+	if (top_smax_value != top_smin_value)
+		goto out;
+
+	/* find the s64_min and s64_min after sign extension */
+	if (size == 1) {
+		init_s64_max = (s8)reg->smax_value;
+		init_s64_min = (s8)reg->smin_value;
+	} else if (size == 2) {
+		init_s64_max = (s16)reg->smax_value;
+		init_s64_min = (s16)reg->smin_value;
+	} else {
+		init_s64_max = (s32)reg->smax_value;
+		init_s64_min = (s32)reg->smin_value;
+	}
+
+	s64_max = max(init_s64_max, init_s64_min);
+	s64_min = min(init_s64_max, init_s64_min);
+
+	/* both of s64_max/s64_min positive or negative */
+	if (s64_max >= 0 == s64_min >= 0) {
+		reg->smin_value = reg->s32_min_value = s64_min;
+		reg->smax_value = reg->s32_max_value = s64_max;
+		reg->umin_value = reg->u32_min_value = s64_min;
+		reg->umax_value = reg->u32_max_value = s64_max;
+		reg->var_off = tnum_range(s64_min, s64_max);
+		return;
+	}
+
+out:
+	set_sext64_default_val(reg, size);
+}
+
 static bool bpf_map_is_rdonly(const struct bpf_map *map)
 {
 	/* A map is considered read-only if the following condition are true:
@@ -5847,7 +5925,8 @@ static bool bpf_map_is_rdonly(const struct bpf_map *map)
 	       !bpf_map_write_active(map);
 }
 
-static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
+static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val,
+			       bool is_ldsx)
 {
 	void *ptr;
 	u64 addr;
@@ -5860,13 +5939,13 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
 
 	switch (size) {
 	case sizeof(u8):
-		*val = (u64)*(u8 *)ptr;
+		*val = is_ldsx ? (s64)*(s8 *)ptr : (u64)*(u8 *)ptr;
 		break;
 	case sizeof(u16):
-		*val = (u64)*(u16 *)ptr;
+		*val = is_ldsx ? (s64)*(s16 *)ptr : (u64)*(u16 *)ptr;
 		break;
 	case sizeof(u32):
-		*val = (u64)*(u32 *)ptr;
+		*val = is_ldsx ? (s64)*(s32 *)ptr : (u64)*(u32 *)ptr;
 		break;
 	case sizeof(u64):
 		*val = *(u64 *)ptr;
@@ -6285,7 +6364,7 @@ static int check_stack_access_within_bounds(
  */
 static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
 			    int off, int bpf_size, enum bpf_access_type t,
-			    int value_regno, bool strict_alignment_once)
+			    int value_regno, bool strict_alignment_once, bool is_ldsx)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = regs + regno;
@@ -6346,7 +6425,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				u64 val = 0;
 
 				err = bpf_map_direct_read(map, map_off, size,
-							  &val);
+							  &val, is_ldsx);
 				if (err)
 					return err;
 
@@ -6516,8 +6595,11 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 
 	if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
 	    regs[value_regno].type == SCALAR_VALUE) {
-		/* b/h/w load zero-extends, mark upper bits as known 0 */
-		coerce_reg_to_size(&regs[value_regno], size);
+		if (!is_ldsx)
+			/* b/h/w load zero-extends, mark upper bits as known 0 */
+			coerce_reg_to_size(&regs[value_regno], size);
+		else
+			coerce_reg_to_size_sx(&regs[value_regno], size);
 	}
 	return err;
 }
@@ -6609,17 +6691,17 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 	 * case to simulate the register fill.
 	 */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-			       BPF_SIZE(insn->code), BPF_READ, -1, true);
+			       BPF_SIZE(insn->code), BPF_READ, -1, true, false);
 	if (!err && load_reg >= 0)
 		err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 				       BPF_SIZE(insn->code), BPF_READ, load_reg,
-				       true);
+				       true, false);
 	if (err)
 		return err;
 
 	/* Check whether we can write into the same memory. */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-			       BPF_SIZE(insn->code), BPF_WRITE, -1, true);
+			       BPF_SIZE(insn->code), BPF_WRITE, -1, true, false);
 	if (err)
 		return err;
 
@@ -6865,7 +6947,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 				return zero_size_allowed ? 0 : -EACCES;
 
 			return check_mem_access(env, env->insn_idx, regno, offset, BPF_B,
-						atype, -1, false);
+						atype, -1, false, false);
 		}
 
 		fallthrough;
@@ -7237,7 +7319,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
 		/* we write BPF_DW bits (8 bytes) at a time */
 		for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) {
 			err = check_mem_access(env, insn_idx, regno,
-					       i, BPF_DW, BPF_WRITE, -1, false);
+					       i, BPF_DW, BPF_WRITE, -1, false, false);
 			if (err)
 				return err;
 		}
@@ -7330,7 +7412,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
 
 		for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) {
 			err = check_mem_access(env, insn_idx, regno,
-					       i, BPF_DW, BPF_WRITE, -1, false);
+					       i, BPF_DW, BPF_WRITE, -1, false, false);
 			if (err)
 				return err;
 		}
@@ -9474,7 +9556,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	 */
 	for (i = 0; i < meta.access_size; i++) {
 		err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
-				       BPF_WRITE, -1, false);
+				       BPF_WRITE, -1, false, false);
 		if (err)
 			return err;
 	}
@@ -16202,7 +16284,7 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ
 			 * Have to support a use case when one path through
 			 * the program yields TRUSTED pointer while another
 			 * is UNTRUSTED. Fallback to UNTRUSTED to generate
-			 * BPF_PROBE_MEM.
+			 * BPF_PROBE_MEM/BPF_PROBE_MEMSX.
 			 */
 			*prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
 		} else {
@@ -16343,7 +16425,8 @@ static int do_check(struct bpf_verifier_env *env)
 			 */
 			err = check_mem_access(env, env->insn_idx, insn->src_reg,
 					       insn->off, BPF_SIZE(insn->code),
-					       BPF_READ, insn->dst_reg, false);
+					       BPF_READ, insn->dst_reg, false,
+					       BPF_MODE(insn->code) == BPF_MEMSX);
 			if (err)
 				return err;
 
@@ -16380,7 +16463,7 @@ static int do_check(struct bpf_verifier_env *env)
 			/* check that memory (dst_reg + off) is writeable */
 			err = check_mem_access(env, env->insn_idx, insn->dst_reg,
 					       insn->off, BPF_SIZE(insn->code),
-					       BPF_WRITE, insn->src_reg, false);
+					       BPF_WRITE, insn->src_reg, false, false);
 			if (err)
 				return err;
 
@@ -16405,7 +16488,7 @@ static int do_check(struct bpf_verifier_env *env)
 			/* check that memory (dst_reg + off) is writeable */
 			err = check_mem_access(env, env->insn_idx, insn->dst_reg,
 					       insn->off, BPF_SIZE(insn->code),
-					       BPF_WRITE, -1, false);
+					       BPF_WRITE, -1, false, false);
 			if (err)
 				return err;
 
@@ -16833,7 +16916,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		if (BPF_CLASS(insn->code) == BPF_LDX &&
-		    (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
+		    ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) ||
+		    insn->imm != 0)) {
 			verbose(env, "BPF_LDX uses reserved fields\n");
 			return -EINVAL;
 		}
@@ -17531,7 +17615,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
 		    insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
 		    insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
-		    insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) {
+		    insn->code == (BPF_LDX | BPF_MEM | BPF_DW) ||
+		    insn->code == (BPF_LDX | BPF_MEMSX | BPF_B) ||
+		    insn->code == (BPF_LDX | BPF_MEMSX | BPF_H) ||
+		    insn->code == (BPF_LDX | BPF_MEMSX | BPF_W)) {
 			type = BPF_READ;
 		} else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
 			   insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
@@ -17590,8 +17677,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		 */
 		case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED:
 			if (type == BPF_READ) {
-				insn->code = BPF_LDX | BPF_PROBE_MEM |
-					BPF_SIZE((insn)->code);
+				if (BPF_MODE(insn->code) == BPF_MEM)
+					insn->code = BPF_LDX | BPF_PROBE_MEM |
+						     BPF_SIZE((insn)->code);
+				else
+					insn->code = BPF_LDX | BPF_PROBE_MEMSX |
+						     BPF_SIZE((insn)->code);
 				env->prog->aux->num_exentries++;
 			}
 			continue;
@@ -17779,7 +17870,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		insn = func[i]->insnsi;
 		for (j = 0; j < func[i]->len; j++, insn++) {
 			if (BPF_CLASS(insn->code) == BPF_LDX &&
-			    BPF_MODE(insn->code) == BPF_PROBE_MEM)
+			    (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+			     BPF_MODE(insn->code) == BPF_PROBE_MEMSX))
 				num_exentries++;
 		}
 		func[i]->aux->num_exentries = num_exentries;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7fc98f4b63e94..14fd26b09e4b3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -19,6 +19,7 @@
 
 /* ld/ldx fields */
 #define BPF_DW		0x18	/* double word (64-bit) */
+#define BPF_MEMSX	0x80	/* load with sign extension */
 #define BPF_ATOMIC	0xc0	/* atomic memory ops - op type in immediate */
 #define BPF_XADD	0xc0	/* exclusive add - legacy name */
 
-- 
GitLab


From 8100928c881482a73ed8bd499d602bab0fe55608 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:12:02 -0700
Subject: [PATCH 0547/1806] bpf: Support new sign-extension mov insns

Add interpreter/jit support for new sign-extension mov insns.
The original 'MOV' insn is extended to support reg-to-reg
signed version for both ALU and ALU64 operations. For ALU mode,
the insn->off value of 8 or 16 indicates sign-extension
from 8- or 16-bit value to 32-bit value. For ALU64 mode,
the insn->off value of 8/16/32 indicates sign-extension
from 8-, 16- or 32-bit value to 64-bit value.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011202.3712300-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c |  43 +++++++++-
 kernel/bpf/core.c           |  28 ++++++-
 kernel/bpf/verifier.c       | 157 ++++++++++++++++++++++++++++++------
 3 files changed, 197 insertions(+), 31 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 54478a9c93e1f..031ef3c4185da 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -701,6 +701,38 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
 	*pprog = prog;
 }
 
+static void emit_movsx_reg(u8 **pprog, int num_bits, bool is64, u32 dst_reg,
+			   u32 src_reg)
+{
+	u8 *prog = *pprog;
+
+	if (is64) {
+		/* movs[b,w,l]q dst, src */
+		if (num_bits == 8)
+			EMIT4(add_2mod(0x48, src_reg, dst_reg), 0x0f, 0xbe,
+			      add_2reg(0xC0, src_reg, dst_reg));
+		else if (num_bits == 16)
+			EMIT4(add_2mod(0x48, src_reg, dst_reg), 0x0f, 0xbf,
+			      add_2reg(0xC0, src_reg, dst_reg));
+		else if (num_bits == 32)
+			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x63,
+			      add_2reg(0xC0, src_reg, dst_reg));
+	} else {
+		/* movs[b,w]l dst, src */
+		if (num_bits == 8) {
+			EMIT4(add_2mod(0x40, src_reg, dst_reg), 0x0f, 0xbe,
+			      add_2reg(0xC0, src_reg, dst_reg));
+		} else if (num_bits == 16) {
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT1(add_2mod(0x40, src_reg, dst_reg));
+			EMIT3(add_2mod(0x0f, src_reg, dst_reg), 0xbf,
+			      add_2reg(0xC0, src_reg, dst_reg));
+		}
+	}
+
+	*pprog = prog;
+}
+
 /* Emit the suffix (ModR/M etc) for addressing *(ptr_reg + off) and val_reg */
 static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off)
 {
@@ -1051,9 +1083,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 
 		case BPF_ALU64 | BPF_MOV | BPF_X:
 		case BPF_ALU | BPF_MOV | BPF_X:
-			emit_mov_reg(&prog,
-				     BPF_CLASS(insn->code) == BPF_ALU64,
-				     dst_reg, src_reg);
+			if (insn->off == 0)
+				emit_mov_reg(&prog,
+					     BPF_CLASS(insn->code) == BPF_ALU64,
+					     dst_reg, src_reg);
+			else
+				emit_movsx_reg(&prog, insn->off,
+					       BPF_CLASS(insn->code) == BPF_ALU64,
+					       dst_reg, src_reg);
 			break;
 
 			/* neg dst */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 01b72fc001f6d..c37c454b09ebb 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -61,6 +61,7 @@
 #define AX	regs[BPF_REG_AX]
 #define ARG1	regs[BPF_REG_ARG1]
 #define CTX	regs[BPF_REG_CTX]
+#define OFF	insn->off
 #define IMM	insn->imm
 
 struct bpf_mem_alloc bpf_global_ma;
@@ -1739,13 +1740,36 @@ select_insn:
 		DST = -DST;
 		CONT;
 	ALU_MOV_X:
-		DST = (u32) SRC;
+		switch (OFF) {
+		case 0:
+			DST = (u32) SRC;
+			break;
+		case 8:
+			DST = (u32)(s8) SRC;
+			break;
+		case 16:
+			DST = (u32)(s16) SRC;
+			break;
+		}
 		CONT;
 	ALU_MOV_K:
 		DST = (u32) IMM;
 		CONT;
 	ALU64_MOV_X:
-		DST = SRC;
+		switch (OFF) {
+		case 0:
+			DST = SRC;
+			break;
+		case 8:
+			DST = (s8) SRC;
+			break;
+		case 16:
+			DST = (s16) SRC;
+			break;
+		case 32:
+			DST = (s32) SRC;
+			break;
+		}
 		CONT;
 	ALU64_MOV_K:
 		DST = IMM;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b154854034e00..2f3eebcd962f0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3421,7 +3421,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 			return 0;
 		if (opcode == BPF_MOV) {
 			if (BPF_SRC(insn->code) == BPF_X) {
-				/* dreg = sreg
+				/* dreg = sreg or dreg = (s8, s16, s32)sreg
 				 * dreg needs precision after this insn
 				 * sreg needs precision before this insn
 				 */
@@ -5905,6 +5905,69 @@ out:
 	set_sext64_default_val(reg, size);
 }
 
+static void set_sext32_default_val(struct bpf_reg_state *reg, int size)
+{
+	if (size == 1) {
+		reg->s32_min_value = S8_MIN;
+		reg->s32_max_value = S8_MAX;
+	} else {
+		/* size == 2 */
+		reg->s32_min_value = S16_MIN;
+		reg->s32_max_value = S16_MAX;
+	}
+	reg->u32_min_value = 0;
+	reg->u32_max_value = U32_MAX;
+}
+
+static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
+{
+	s32 init_s32_max, init_s32_min, s32_max, s32_min, u32_val;
+	u32 top_smax_value, top_smin_value;
+	u32 num_bits = size * 8;
+
+	if (tnum_is_const(reg->var_off)) {
+		u32_val = reg->var_off.value;
+		if (size == 1)
+			reg->var_off = tnum_const((s8)u32_val);
+		else
+			reg->var_off = tnum_const((s16)u32_val);
+
+		u32_val = reg->var_off.value;
+		reg->s32_min_value = reg->s32_max_value = u32_val;
+		reg->u32_min_value = reg->u32_max_value = u32_val;
+		return;
+	}
+
+	top_smax_value = ((u32)reg->s32_max_value >> num_bits) << num_bits;
+	top_smin_value = ((u32)reg->s32_min_value >> num_bits) << num_bits;
+
+	if (top_smax_value != top_smin_value)
+		goto out;
+
+	/* find the s32_min and s32_min after sign extension */
+	if (size == 1) {
+		init_s32_max = (s8)reg->s32_max_value;
+		init_s32_min = (s8)reg->s32_min_value;
+	} else {
+		/* size == 2 */
+		init_s32_max = (s16)reg->s32_max_value;
+		init_s32_min = (s16)reg->s32_min_value;
+	}
+	s32_max = max(init_s32_max, init_s32_min);
+	s32_min = min(init_s32_max, init_s32_min);
+
+	if (s32_min >= 0 == s32_max >= 0) {
+		reg->s32_min_value = s32_min;
+		reg->s32_max_value = s32_max;
+		reg->u32_min_value = (u32)s32_min;
+		reg->u32_max_value = (u32)s32_max;
+		return;
+	}
+
+out:
+	set_sext32_default_val(reg, size);
+}
+
 static bool bpf_map_is_rdonly(const struct bpf_map *map)
 {
 	/* A map is considered read-only if the following condition are true:
@@ -13038,11 +13101,24 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	} else if (opcode == BPF_MOV) {
 
 		if (BPF_SRC(insn->code) == BPF_X) {
-			if (insn->imm != 0 || insn->off != 0) {
+			if (insn->imm != 0) {
 				verbose(env, "BPF_MOV uses reserved fields\n");
 				return -EINVAL;
 			}
 
+			if (BPF_CLASS(insn->code) == BPF_ALU) {
+				if (insn->off != 0 && insn->off != 8 && insn->off != 16) {
+					verbose(env, "BPF_MOV uses reserved fields\n");
+					return -EINVAL;
+				}
+			} else {
+				if (insn->off != 0 && insn->off != 8 && insn->off != 16 &&
+				    insn->off != 32) {
+					verbose(env, "BPF_MOV uses reserved fields\n");
+					return -EINVAL;
+				}
+			}
+
 			/* check src operand */
 			err = check_reg_arg(env, insn->src_reg, SRC_OP);
 			if (err)
@@ -13066,18 +13142,33 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 				       !tnum_is_const(src_reg->var_off);
 
 			if (BPF_CLASS(insn->code) == BPF_ALU64) {
-				/* case: R1 = R2
-				 * copy register state to dest reg
-				 */
-				if (need_id)
-					/* Assign src and dst registers the same ID
-					 * that will be used by find_equal_scalars()
-					 * to propagate min/max range.
+				if (insn->off == 0) {
+					/* case: R1 = R2
+					 * copy register state to dest reg
 					 */
-					src_reg->id = ++env->id_gen;
-				copy_register_state(dst_reg, src_reg);
-				dst_reg->live |= REG_LIVE_WRITTEN;
-				dst_reg->subreg_def = DEF_NOT_SUBREG;
+					if (need_id)
+						/* Assign src and dst registers the same ID
+						 * that will be used by find_equal_scalars()
+						 * to propagate min/max range.
+						 */
+						src_reg->id = ++env->id_gen;
+					copy_register_state(dst_reg, src_reg);
+					dst_reg->live |= REG_LIVE_WRITTEN;
+					dst_reg->subreg_def = DEF_NOT_SUBREG;
+				} else {
+					/* case: R1 = (s8, s16 s32)R2 */
+					bool no_sext;
+
+					no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+					if (no_sext && need_id)
+						src_reg->id = ++env->id_gen;
+					copy_register_state(dst_reg, src_reg);
+					if (!no_sext)
+						dst_reg->id = 0;
+					coerce_reg_to_size_sx(dst_reg, insn->off >> 3);
+					dst_reg->live |= REG_LIVE_WRITTEN;
+					dst_reg->subreg_def = DEF_NOT_SUBREG;
+				}
 			} else {
 				/* R1 = (u32) R2 */
 				if (is_pointer_value(env, insn->src_reg)) {
@@ -13086,19 +13177,33 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 						insn->src_reg);
 					return -EACCES;
 				} else if (src_reg->type == SCALAR_VALUE) {
-					bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX;
-
-					if (is_src_reg_u32 && need_id)
-						src_reg->id = ++env->id_gen;
-					copy_register_state(dst_reg, src_reg);
-					/* Make sure ID is cleared if src_reg is not in u32 range otherwise
-					 * dst_reg min/max could be incorrectly
-					 * propagated into src_reg by find_equal_scalars()
-					 */
-					if (!is_src_reg_u32)
-						dst_reg->id = 0;
-					dst_reg->live |= REG_LIVE_WRITTEN;
-					dst_reg->subreg_def = env->insn_idx + 1;
+					if (insn->off == 0) {
+						bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX;
+
+						if (is_src_reg_u32 && need_id)
+							src_reg->id = ++env->id_gen;
+						copy_register_state(dst_reg, src_reg);
+						/* Make sure ID is cleared if src_reg is not in u32
+						 * range otherwise dst_reg min/max could be incorrectly
+						 * propagated into src_reg by find_equal_scalars()
+						 */
+						if (!is_src_reg_u32)
+							dst_reg->id = 0;
+						dst_reg->live |= REG_LIVE_WRITTEN;
+						dst_reg->subreg_def = env->insn_idx + 1;
+					} else {
+						/* case: W1 = (s8, s16)W2 */
+						bool no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+
+						if (no_sext && need_id)
+							src_reg->id = ++env->id_gen;
+						copy_register_state(dst_reg, src_reg);
+						if (!no_sext)
+							dst_reg->id = 0;
+						dst_reg->live |= REG_LIVE_WRITTEN;
+						dst_reg->subreg_def = env->insn_idx + 1;
+						coerce_subreg_to_size_sx(dst_reg, insn->off >> 3);
+					}
 				} else {
 					mark_reg_unknown(env, regs,
 							 insn->dst_reg);
-- 
GitLab


From 1f1e864b65554e33fe74e3377e58b12f4302f2eb Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:12:07 -0700
Subject: [PATCH 0548/1806] bpf: Handle sign-extenstin ctx member accesses

Currently, if user accesses a ctx member with signed types,
the compiler will generate an unsigned load followed by
necessary left and right shifts.

With the introduction of sign-extension load, compiler may
just emit a ldsx insn instead. Let us do a final movsx sign
extension to the final unsigned ctx load result to
satisfy original sign extension requirement.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011207.3712528-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2f3eebcd962f0..7a6945be07e39 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -17716,6 +17716,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		bpf_convert_ctx_access_t convert_ctx_access;
+		u8 mode;
 
 		if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
 		    insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
@@ -17797,6 +17798,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 
 		ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size;
 		size = BPF_LDST_BYTES(insn);
+		mode = BPF_MODE(insn->code);
 
 		/* If the read access is a narrower load of the field,
 		 * convert to a 4/8-byte load, to minimum program type specific
@@ -17856,6 +17858,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 								(1ULL << size * 8) - 1);
 			}
 		}
+		if (mode == BPF_MEMSX)
+			insn_buf[cnt++] = BPF_RAW_INSN(BPF_ALU64 | BPF_MOV | BPF_X,
+						       insn->dst_reg, insn->dst_reg,
+						       size * 8, 0);
 
 		new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
 		if (!new_prog)
-- 
GitLab


From 0845c3db7bf5c4ceb7100bcd8fd594d9ccf3c29a Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:12:13 -0700
Subject: [PATCH 0549/1806] bpf: Support new unconditional bswap instruction

The existing 'be' and 'le' insns will do conditional bswap
depends on host endianness. This patch implements
unconditional bswap insns.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011213.3712808-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c |  1 +
 kernel/bpf/core.c           | 14 ++++++++++++++
 kernel/bpf/verifier.c       |  7 +++++--
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 031ef3c4185da..4942a4c188b98 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1322,6 +1322,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 			break;
 
 		case BPF_ALU | BPF_END | BPF_FROM_BE:
+		case BPF_ALU64 | BPF_END | BPF_FROM_LE:
 			switch (imm32) {
 			case 16:
 				/* Emit 'ror %ax, 8' to swap lower 2 bytes */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c37c454b09ebb..ad58697cec4be 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1524,6 +1524,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 	INSN_3(ALU64, DIV,  X),			\
 	INSN_3(ALU64, MOD,  X),			\
 	INSN_2(ALU64, NEG),			\
+	INSN_3(ALU64, END, TO_LE),		\
 	/*   Immediate based. */		\
 	INSN_3(ALU64, ADD,  K),			\
 	INSN_3(ALU64, SUB,  K),			\
@@ -1848,6 +1849,19 @@ select_insn:
 			break;
 		}
 		CONT;
+	ALU64_END_TO_LE:
+		switch (IMM) {
+		case 16:
+			DST = (__force u16) __swab16(DST);
+			break;
+		case 32:
+			DST = (__force u32) __swab32(DST);
+			break;
+		case 64:
+			DST = (__force u64) __swab64(DST);
+			break;
+		}
+		CONT;
 
 	/* CALL */
 	JMP_CALL:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7a6945be07e39..a3dcaeed82175 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3012,8 +3012,10 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		}
 	}
 
+	if (class == BPF_ALU64 && op == BPF_END && (insn->imm == 16 || insn->imm == 32))
+		return false;
+
 	if (class == BPF_ALU64 || class == BPF_JMP ||
-	    /* BPF_END always use BPF_ALU class. */
 	    (class == BPF_ALU && op == BPF_END && insn->imm == 64))
 		return true;
 
@@ -13076,7 +13078,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		} else {
 			if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
 			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
-			    BPF_CLASS(insn->code) == BPF_ALU64) {
+			    (BPF_CLASS(insn->code) == BPF_ALU64 &&
+			     BPF_SRC(insn->code) != BPF_TO_LE)) {
 				verbose(env, "BPF_END uses reserved fields\n");
 				return -EINVAL;
 			}
-- 
GitLab


From ec0e2da95f72d4a46050a4d994e4fe471474fd80 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:12:19 -0700
Subject: [PATCH 0550/1806] bpf: Support new signed div/mod instructions.

Add interpreter/jit support for new signed div/mod insns.
The new signed div/mod instructions are encoded with
unsigned div/mod instructions plus insn->off == 1.
Also add basic verifier support to ensure new insns get
accepted.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011219.3714605-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c |  27 ++++++---
 kernel/bpf/core.c           | 110 ++++++++++++++++++++++++++++++------
 kernel/bpf/verifier.c       |   6 +-
 3 files changed, 117 insertions(+), 26 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 4942a4c188b98..a89b62eb2b400 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1194,15 +1194,26 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 				/* mov rax, dst_reg */
 				emit_mov_reg(&prog, is64, BPF_REG_0, dst_reg);
 
-			/*
-			 * xor edx, edx
-			 * equivalent to 'xor rdx, rdx', but one byte less
-			 */
-			EMIT2(0x31, 0xd2);
+			if (insn->off == 0) {
+				/*
+				 * xor edx, edx
+				 * equivalent to 'xor rdx, rdx', but one byte less
+				 */
+				EMIT2(0x31, 0xd2);
 
-			/* div src_reg */
-			maybe_emit_1mod(&prog, src_reg, is64);
-			EMIT2(0xF7, add_1reg(0xF0, src_reg));
+				/* div src_reg */
+				maybe_emit_1mod(&prog, src_reg, is64);
+				EMIT2(0xF7, add_1reg(0xF0, src_reg));
+			} else {
+				if (BPF_CLASS(insn->code) == BPF_ALU)
+					EMIT1(0x99); /* cdq */
+				else
+					EMIT2(0x48, 0x99); /* cqo */
+
+				/* idiv src_reg */
+				maybe_emit_1mod(&prog, src_reg, is64);
+				EMIT2(0xF7, add_1reg(0xF8, src_reg));
+			}
 
 			if (BPF_OP(insn->code) == BPF_MOD &&
 			    dst_reg != BPF_REG_3)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ad58697cec4be..3fe895199f6e2 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1792,36 +1792,114 @@ select_insn:
 		(*(s64 *) &DST) >>= IMM;
 		CONT;
 	ALU64_MOD_X:
-		div64_u64_rem(DST, SRC, &AX);
-		DST = AX;
+		switch (OFF) {
+		case 0:
+			div64_u64_rem(DST, SRC, &AX);
+			DST = AX;
+			break;
+		case 1:
+			AX = div64_s64(DST, SRC);
+			DST = DST - AX * SRC;
+			break;
+		}
 		CONT;
 	ALU_MOD_X:
-		AX = (u32) DST;
-		DST = do_div(AX, (u32) SRC);
+		switch (OFF) {
+		case 0:
+			AX = (u32) DST;
+			DST = do_div(AX, (u32) SRC);
+			break;
+		case 1:
+			AX = abs((s32)DST);
+			AX = do_div(AX, abs((s32)SRC));
+			if ((s32)DST < 0)
+				DST = (u32)-AX;
+			else
+				DST = (u32)AX;
+			break;
+		}
 		CONT;
 	ALU64_MOD_K:
-		div64_u64_rem(DST, IMM, &AX);
-		DST = AX;
+		switch (OFF) {
+		case 0:
+			div64_u64_rem(DST, IMM, &AX);
+			DST = AX;
+			break;
+		case 1:
+			AX = div64_s64(DST, IMM);
+			DST = DST - AX * IMM;
+			break;
+		}
 		CONT;
 	ALU_MOD_K:
-		AX = (u32) DST;
-		DST = do_div(AX, (u32) IMM);
+		switch (OFF) {
+		case 0:
+			AX = (u32) DST;
+			DST = do_div(AX, (u32) IMM);
+			break;
+		case 1:
+			AX = abs((s32)DST);
+			AX = do_div(AX, abs((s32)IMM));
+			if ((s32)DST < 0)
+				DST = (u32)-AX;
+			else
+				DST = (u32)AX;
+			break;
+		}
 		CONT;
 	ALU64_DIV_X:
-		DST = div64_u64(DST, SRC);
+		switch (OFF) {
+		case 0:
+			DST = div64_u64(DST, SRC);
+			break;
+		case 1:
+			DST = div64_s64(DST, SRC);
+			break;
+		}
 		CONT;
 	ALU_DIV_X:
-		AX = (u32) DST;
-		do_div(AX, (u32) SRC);
-		DST = (u32) AX;
+		switch (OFF) {
+		case 0:
+			AX = (u32) DST;
+			do_div(AX, (u32) SRC);
+			DST = (u32) AX;
+			break;
+		case 1:
+			AX = abs((s32)DST);
+			do_div(AX, abs((s32)SRC));
+			if ((s32)DST < 0 == (s32)SRC < 0)
+				DST = (u32)AX;
+			else
+				DST = (u32)-AX;
+			break;
+		}
 		CONT;
 	ALU64_DIV_K:
-		DST = div64_u64(DST, IMM);
+		switch (OFF) {
+		case 0:
+			DST = div64_u64(DST, IMM);
+			break;
+		case 1:
+			DST = div64_s64(DST, IMM);
+			break;
+		}
 		CONT;
 	ALU_DIV_K:
-		AX = (u32) DST;
-		do_div(AX, (u32) IMM);
-		DST = (u32) AX;
+		switch (OFF) {
+		case 0:
+			AX = (u32) DST;
+			do_div(AX, (u32) IMM);
+			DST = (u32) AX;
+			break;
+		case 1:
+			AX = abs((s32)DST);
+			do_div(AX, abs((s32)IMM));
+			if ((s32)DST < 0 == (s32)IMM < 0)
+				DST = (u32)AX;
+			else
+				DST = (u32)-AX;
+			break;
+		}
 		CONT;
 	ALU_END_TO_BE:
 		switch (IMM) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a3dcaeed82175..c0aceedfcb9cb 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -13237,7 +13237,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	} else {	/* all other ALU ops: and, sub, xor, add, ... */
 
 		if (BPF_SRC(insn->code) == BPF_X) {
-			if (insn->imm != 0 || insn->off != 0) {
+			if (insn->imm != 0 || insn->off > 1 ||
+			    (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
 				verbose(env, "BPF_ALU uses reserved fields\n");
 				return -EINVAL;
 			}
@@ -13246,7 +13247,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			if (err)
 				return err;
 		} else {
-			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
+			if (insn->src_reg != BPF_REG_0 || insn->off > 1 ||
+			    (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
 				verbose(env, "BPF_ALU uses reserved fields\n");
 				return -EINVAL;
 			}
-- 
GitLab


From 7058e3a31ee4b9240cccab5bc13c1afbfa3d16a0 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:12:25 -0700
Subject: [PATCH 0551/1806] bpf: Fix jit blinding with new sdiv/smov insns

Handle new insns properly in bpf_jit_blind_insn() function.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011225.3715812-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/filter.h | 14 ++++++++++----
 kernel/bpf/core.c      |  4 ++--
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index a93242b5516b7..f5eabe3fa5e8e 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -93,22 +93,28 @@ struct ctl_table_header;
 
 /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
 
-#define BPF_ALU64_REG(OP, DST, SRC)				\
+#define BPF_ALU64_REG_OFF(OP, DST, SRC, OFF)			\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_X,	\
 		.dst_reg = DST,					\
 		.src_reg = SRC,					\
-		.off   = 0,					\
+		.off   = OFF,					\
 		.imm   = 0 })
 
-#define BPF_ALU32_REG(OP, DST, SRC)				\
+#define BPF_ALU64_REG(OP, DST, SRC)				\
+	BPF_ALU64_REG_OFF(OP, DST, SRC, 0)
+
+#define BPF_ALU32_REG_OFF(OP, DST, SRC, OFF)			\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU | BPF_OP(OP) | BPF_X,		\
 		.dst_reg = DST,					\
 		.src_reg = SRC,					\
-		.off   = 0,					\
+		.off   = OFF,					\
 		.imm   = 0 })
 
+#define BPF_ALU32_REG(OP, DST, SRC)				\
+	BPF_ALU32_REG_OFF(OP, DST, SRC, 0)
+
 /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
 
 #define BPF_ALU64_IMM(OP, DST, IMM)				\
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 3fe895199f6e2..646d2fe537bea 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1272,7 +1272,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
 	case BPF_ALU | BPF_MOD | BPF_K:
 		*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
 		*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
-		*to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX);
+		*to++ = BPF_ALU32_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off);
 		break;
 
 	case BPF_ALU64 | BPF_ADD | BPF_K:
@@ -1286,7 +1286,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
 	case BPF_ALU64 | BPF_MOD | BPF_K:
 		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
 		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
-		*to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX);
+		*to++ = BPF_ALU64_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off);
 		break;
 
 	case BPF_JMP | BPF_JEQ  | BPF_K:
-- 
GitLab


From 4cd58e9af8b9d9fff6b7145e742abbfcda0af4af Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:12:31 -0700
Subject: [PATCH 0552/1806] bpf: Support new 32bit offset jmp instruction

Add interpreter/jit/verifier support for 32bit offset jmp instruction.
If a conditional jmp instruction needs more than 16bit offset,
it can be simulated with a conditional jmp + a 32bit jmp insn.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011231.3716103-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 28 ++++++++++++++++++----------
 kernel/bpf/core.c           | 19 ++++++++++++++++---
 kernel/bpf/verifier.c       | 32 ++++++++++++++++++++++----------
 3 files changed, 56 insertions(+), 23 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a89b62eb2b400..a5930042139d3 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1815,16 +1815,24 @@ emit_cond_jmp:		/* Convert BPF opcode to x86 */
 			break;
 
 		case BPF_JMP | BPF_JA:
-			if (insn->off == -1)
-				/* -1 jmp instructions will always jump
-				 * backwards two bytes. Explicitly handling
-				 * this case avoids wasting too many passes
-				 * when there are long sequences of replaced
-				 * dead code.
-				 */
-				jmp_offset = -2;
-			else
-				jmp_offset = addrs[i + insn->off] - addrs[i];
+		case BPF_JMP32 | BPF_JA:
+			if (BPF_CLASS(insn->code) == BPF_JMP) {
+				if (insn->off == -1)
+					/* -1 jmp instructions will always jump
+					 * backwards two bytes. Explicitly handling
+					 * this case avoids wasting too many passes
+					 * when there are long sequences of replaced
+					 * dead code.
+					 */
+					jmp_offset = -2;
+				else
+					jmp_offset = addrs[i + insn->off] - addrs[i];
+			} else {
+				if (insn->imm == -1)
+					jmp_offset = -2;
+				else
+					jmp_offset = addrs[i + insn->imm] - addrs[i];
+			}
 
 			if (!jmp_offset) {
 				/*
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 646d2fe537bea..db0b631908c24 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -373,7 +373,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
 {
 	const s32 off_min = S16_MIN, off_max = S16_MAX;
 	s32 delta = end_new - end_old;
-	s32 off = insn->off;
+	s32 off;
+
+	if (insn->code == (BPF_JMP32 | BPF_JA))
+		off = insn->imm;
+	else
+		off = insn->off;
 
 	if (curr < pos && curr + off + 1 >= end_old)
 		off += delta;
@@ -381,8 +386,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
 		off -= delta;
 	if (off < off_min || off > off_max)
 		return -ERANGE;
-	if (!probe_pass)
-		insn->off = off;
+	if (!probe_pass) {
+		if (insn->code == (BPF_JMP32 | BPF_JA))
+			insn->imm = off;
+		else
+			insn->off = off;
+	}
 	return 0;
 }
 
@@ -1593,6 +1602,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 	INSN_3(JMP, JSLE, K),			\
 	INSN_3(JMP, JSET, K),			\
 	INSN_2(JMP, JA),			\
+	INSN_2(JMP32, JA),			\
 	/* Store instructions. */		\
 	/*   Register based. */			\
 	INSN_3(STX, MEM,  B),			\
@@ -1989,6 +1999,9 @@ out:
 	JMP_JA:
 		insn += insn->off;
 		CONT;
+	JMP32_JA:
+		insn += insn->imm;
+		CONT;
 	JMP_EXIT:
 		return BPF_R0;
 	/* JMP */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c0aceedfcb9cb..0b1ada93582b4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2855,7 +2855,10 @@ static int check_subprogs(struct bpf_verifier_env *env)
 			goto next;
 		if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
 			goto next;
-		off = i + insn[i].off + 1;
+		if (code == (BPF_JMP32 | BPF_JA))
+			off = i + insn[i].imm + 1;
+		else
+			off = i + insn[i].off + 1;
 		if (off < subprog_start || off >= subprog_end) {
 			verbose(env, "jump out of range from insn %d to %d\n", i, off);
 			return -EINVAL;
@@ -2867,6 +2870,7 @@ next:
 			 * or unconditional jump back
 			 */
 			if (code != (BPF_JMP | BPF_EXIT) &&
+			    code != (BPF_JMP32 | BPF_JA) &&
 			    code != (BPF_JMP | BPF_JA)) {
 				verbose(env, "last insn is not an exit or jmp\n");
 				return -EINVAL;
@@ -14792,7 +14796,7 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 static int visit_insn(int t, struct bpf_verifier_env *env)
 {
 	struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t];
-	int ret;
+	int ret, off;
 
 	if (bpf_pseudo_func(insn))
 		return visit_func_call_insn(t, insns, env, true);
@@ -14840,14 +14844,19 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 		if (BPF_SRC(insn->code) != BPF_K)
 			return -EINVAL;
 
+		if (BPF_CLASS(insn->code) == BPF_JMP)
+			off = insn->off;
+		else
+			off = insn->imm;
+
 		/* unconditional jump with single edge */
-		ret = push_insn(t, t + insn->off + 1, FALLTHROUGH, env,
+		ret = push_insn(t, t + off + 1, FALLTHROUGH, env,
 				true);
 		if (ret)
 			return ret;
 
-		mark_prune_point(env, t + insn->off + 1);
-		mark_jmp_point(env, t + insn->off + 1);
+		mark_prune_point(env, t + off + 1);
+		mark_jmp_point(env, t + off + 1);
 
 		return ret;
 
@@ -16643,15 +16652,18 @@ static int do_check(struct bpf_verifier_env *env)
 				mark_reg_scratched(env, BPF_REG_0);
 			} else if (opcode == BPF_JA) {
 				if (BPF_SRC(insn->code) != BPF_K ||
-				    insn->imm != 0 ||
 				    insn->src_reg != BPF_REG_0 ||
 				    insn->dst_reg != BPF_REG_0 ||
-				    class == BPF_JMP32) {
+				    (class == BPF_JMP && insn->imm != 0) ||
+				    (class == BPF_JMP32 && insn->off != 0)) {
 					verbose(env, "BPF_JA uses reserved fields\n");
 					return -EINVAL;
 				}
 
-				env->insn_idx += insn->off + 1;
+				if (class == BPF_JMP)
+					env->insn_idx += insn->off + 1;
+				else
+					env->insn_idx += insn->imm + 1;
 				continue;
 
 			} else if (opcode == BPF_EXIT) {
@@ -17498,13 +17510,13 @@ static bool insn_is_cond_jump(u8 code)
 {
 	u8 op;
 
+	op = BPF_OP(code);
 	if (BPF_CLASS(code) == BPF_JMP32)
-		return true;
+		return op != BPF_JA;
 
 	if (BPF_CLASS(code) != BPF_JMP)
 		return false;
 
-	op = BPF_OP(code);
 	return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
 }
 
-- 
GitLab


From f835bb6222998c8655bc4e85287d42b57c17b208 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Wed, 28 Jun 2023 15:29:51 -0700
Subject: [PATCH 0553/1806] bpf: Add kernel/bpftool asm support for new
 instructions

Add asm support for new instructions so kernel verifier and bpftool
xlated insn dumps can have proper asm syntax for new instructions.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/disasm.c | 57 ++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 51 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index 7b4afb7d96db1..d7bff608f2993 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -87,6 +87,17 @@ const char *const bpf_alu_string[16] = {
 	[BPF_END >> 4]  = "endian",
 };
 
+const char *const bpf_alu_sign_string[16] = {
+	[BPF_DIV >> 4]  = "s/=",
+	[BPF_MOD >> 4]  = "s%=",
+};
+
+const char *const bpf_movsx_string[4] = {
+	[0] = "(s8)",
+	[1] = "(s16)",
+	[3] = "(s32)",
+};
+
 static const char *const bpf_atomic_alu_string[16] = {
 	[BPF_ADD >> 4]  = "add",
 	[BPF_AND >> 4]  = "and",
@@ -101,6 +112,12 @@ static const char *const bpf_ldst_string[] = {
 	[BPF_DW >> 3] = "u64",
 };
 
+static const char *const bpf_ldsx_string[] = {
+	[BPF_W >> 3]  = "s32",
+	[BPF_H >> 3]  = "s16",
+	[BPF_B >> 3]  = "s8",
+};
+
 static const char *const bpf_jmp_string[16] = {
 	[BPF_JA >> 4]   = "jmp",
 	[BPF_JEQ >> 4]  = "==",
@@ -128,6 +145,26 @@ static void print_bpf_end_insn(bpf_insn_print_t verbose,
 		insn->imm, insn->dst_reg);
 }
 
+static void print_bpf_bswap_insn(bpf_insn_print_t verbose,
+			       void *private_data,
+			       const struct bpf_insn *insn)
+{
+	verbose(private_data, "(%02x) r%d = bswap%d r%d\n",
+		insn->code, insn->dst_reg,
+		insn->imm, insn->dst_reg);
+}
+
+static bool is_sdiv_smod(const struct bpf_insn *insn)
+{
+	return (BPF_OP(insn->code)  == BPF_DIV || BPF_OP(insn->code) == BPF_MOD) &&
+	       insn->off == 1;
+}
+
+static bool is_movsx(const struct bpf_insn *insn)
+{
+	return BPF_OP(insn->code) == BPF_MOV && insn->off != 0;
+}
+
 void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 		    const struct bpf_insn *insn,
 		    bool allow_ptr_leaks)
@@ -138,7 +175,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 	if (class == BPF_ALU || class == BPF_ALU64) {
 		if (BPF_OP(insn->code) == BPF_END) {
 			if (class == BPF_ALU64)
-				verbose(cbs->private_data, "BUG_alu64_%02x\n", insn->code);
+				print_bpf_bswap_insn(verbose, cbs->private_data, insn);
 			else
 				print_bpf_end_insn(verbose, cbs->private_data, insn);
 		} else if (BPF_OP(insn->code) == BPF_NEG) {
@@ -147,17 +184,20 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 				insn->dst_reg, class == BPF_ALU ? 'w' : 'r',
 				insn->dst_reg);
 		} else if (BPF_SRC(insn->code) == BPF_X) {
-			verbose(cbs->private_data, "(%02x) %c%d %s %c%d\n",
+			verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n",
 				insn->code, class == BPF_ALU ? 'w' : 'r',
 				insn->dst_reg,
-				bpf_alu_string[BPF_OP(insn->code) >> 4],
+				is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4]
+						   : bpf_alu_string[BPF_OP(insn->code) >> 4],
+				is_movsx(insn) ? bpf_movsx_string[(insn->off >> 3) - 1] : "",
 				class == BPF_ALU ? 'w' : 'r',
 				insn->src_reg);
 		} else {
 			verbose(cbs->private_data, "(%02x) %c%d %s %d\n",
 				insn->code, class == BPF_ALU ? 'w' : 'r',
 				insn->dst_reg,
-				bpf_alu_string[BPF_OP(insn->code) >> 4],
+				is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4]
+						   : bpf_alu_string[BPF_OP(insn->code) >> 4],
 				insn->imm);
 		}
 	} else if (class == BPF_STX) {
@@ -218,13 +258,15 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 			verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
 		}
 	} else if (class == BPF_LDX) {
-		if (BPF_MODE(insn->code) != BPF_MEM) {
+		if (BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) {
 			verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code);
 			return;
 		}
 		verbose(cbs->private_data, "(%02x) r%d = *(%s *)(r%d %+d)\n",
 			insn->code, insn->dst_reg,
-			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+			BPF_MODE(insn->code) == BPF_MEM ?
+				 bpf_ldst_string[BPF_SIZE(insn->code) >> 3] :
+				 bpf_ldsx_string[BPF_SIZE(insn->code) >> 3],
 			insn->src_reg, insn->off);
 	} else if (class == BPF_LD) {
 		if (BPF_MODE(insn->code) == BPF_ABS) {
@@ -279,6 +321,9 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 		} else if (insn->code == (BPF_JMP | BPF_JA)) {
 			verbose(cbs->private_data, "(%02x) goto pc%+d\n",
 				insn->code, insn->off);
+		} else if (insn->code == (BPF_JMP32 | BPF_JA)) {
+			verbose(cbs->private_data, "(%02x) gotol pc%+d\n",
+				insn->code, insn->imm);
 		} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
 			verbose(cbs->private_data, "(%02x) exit\n", insn->code);
 		} else if (BPF_SRC(insn->code) == BPF_X) {
-- 
GitLab


From 86180493a2ef572d703ed3a486ab347b194ce4d9 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:12:44 -0700
Subject: [PATCH 0554/1806] selftests/bpf: Fix a test_verifier failure

The following test_verifier subtest failed due to
new encoding for BSWAP.

  $ ./test_verifier
  ...
  #99/u invalid 64-bit BPF_END FAIL
  Unexpected success to load!
  verification time 215 usec
  stack depth 0
  processed 3 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0
  #99/p invalid 64-bit BPF_END FAIL
  Unexpected success to load!
  verification time 198 usec
  stack depth 0
  processed 3 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0

Tighten the test so it still reports a failure.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011244.3717464-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/verifier/basic_instr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/verifier/basic_instr.c b/tools/testing/selftests/bpf/verifier/basic_instr.c
index 071dbc889e8c6..bd928a72ad73e 100644
--- a/tools/testing/selftests/bpf/verifier/basic_instr.c
+++ b/tools/testing/selftests/bpf/verifier/basic_instr.c
@@ -176,11 +176,11 @@
 	.retval = 1,
 },
 {
-	"invalid 64-bit BPF_END",
+	"invalid 64-bit BPF_END with BPF_TO_BE",
 	.insns = {
 	BPF_MOV32_IMM(BPF_REG_0, 0),
 	{
-		.code  = BPF_ALU64 | BPF_END | BPF_TO_LE,
+		.code  = BPF_ALU64 | BPF_END | BPF_TO_BE,
 		.dst_reg = BPF_REG_0,
 		.src_reg = 0,
 		.off   = 0,
@@ -188,7 +188,7 @@
 	},
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "unknown opcode d7",
+	.errstr = "unknown opcode df",
 	.result = REJECT,
 },
 {
-- 
GitLab


From a5d0c26a2784890d803fca5e0dd27c590472b43d Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:12:50 -0700
Subject: [PATCH 0555/1806] selftests/bpf: Add a cpuv4 test runner for cpu=v4
 testing

Similar to no-alu32 runner, if clang compiler supports -mcpu=v4,
a cpuv4 runner is created to test bpf programs compiled with
-mcpu=v4.

The following are some num-of-insn statistics for each newer
instructions based on existing selftests, excluding subsequent
cpuv4 insn specific tests.

   insn pattern                # of instructions
   reg = (s8)reg               4
   reg = (s16)reg              4
   reg = (s32)reg              144
   reg = *(s8 *)(reg + off)    13
   reg = *(s16 *)(reg + off)   14
   reg = *(s32 *)(reg + off)   15215
   reg = bswap16 reg           142
   reg = bswap32 reg           38
   reg = bswap64 reg           14
   reg s/= reg                 0
   reg s%= reg                 0
   gotol <offset>              58

Note that in llvm -mcpu=v4 implementation, the compiler is a little
bit conservative about generating 'gotol' insn (32-bit branch offset)
as it didn't precise count the number of insns (e.g., some insns are
debug insns, etc.). Compared to old 'goto' insn, newer 'gotol' insn
should have comparable verification states to 'goto' insn.

With current patch set, all selftests passed with -mcpu=v4
when running test_progs-cpuv4 binary. The -mcpu=v3 and -mcpu=v2 run
are also successful.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011250.3718252-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/.gitignore |  2 ++
 tools/testing/selftests/bpf/Makefile   | 28 ++++++++++++++++++++++----
 2 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 116fecf80ca1b..110518ba48042 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -13,6 +13,7 @@ test_dev_cgroup
 /test_progs
 /test_progs-no_alu32
 /test_progs-bpf_gcc
+/test_progs-cpuv4
 test_verifier_log
 feature
 test_sock
@@ -36,6 +37,7 @@ test_cpp
 *.lskel.h
 /no_alu32
 /bpf_gcc
+/cpuv4
 /host-tools
 /tools
 /runqslower
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 882be03b179fa..6a45719a8d472 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -33,9 +33,13 @@ CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS)	\
 LDFLAGS += $(SAN_LDFLAGS)
 LDLIBS += -lelf -lz -lrt -lpthread
 
-# Silence some warnings when compiled with clang
 ifneq ($(LLVM),)
+# Silence some warnings when compiled with clang
 CFLAGS += -Wno-unused-command-line-argument
+# Check whether cpu=v4 is supported or not by clang
+ifneq ($(shell $(CLANG) --target=bpf -mcpu=help 2>&1 | grep 'v4'),)
+CLANG_CPUV4 := 1
+endif
 endif
 
 # Order correspond to 'make run_tests' order
@@ -51,6 +55,10 @@ ifneq ($(BPF_GCC),)
 TEST_GEN_PROGS += test_progs-bpf_gcc
 endif
 
+ifneq ($(CLANG_CPUV4),)
+TEST_GEN_PROGS += test_progs-cpuv4
+endif
+
 TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o
 TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c)
 
@@ -383,6 +391,11 @@ define CLANG_NOALU32_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
 	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2
 endef
+# Similar to CLANG_BPF_BUILD_RULE, but with cpu-v4
+define CLANG_CPUV4_BPF_BUILD_RULE
+	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
+	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v4 -o $2
+endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
 	$(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
@@ -425,7 +438,7 @@ LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(ske
 # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
 # Parameters:
 # $1 - test runner base binary name (e.g., test_progs)
-# $2 - test runner extra "flavor" (e.g., no_alu32, gcc-bpf, etc)
+# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc)
 define DEFINE_TEST_RUNNER
 
 TRUNNER_OUTPUT := $(OUTPUT)$(if $2,/)$2
@@ -453,7 +466,7 @@ endef
 # Using TRUNNER_XXX variables, provided by callers of DEFINE_TEST_RUNNER and
 # set up by DEFINE_TEST_RUNNER itself, create test runner build rules with:
 # $1 - test runner base binary name (e.g., test_progs)
-# $2 - test runner extra "flavor" (e.g., no_alu32, gcc-bpf, etc)
+# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc)
 define DEFINE_TEST_RUNNER_RULES
 
 ifeq ($($(TRUNNER_OUTPUT)-dir),)
@@ -584,6 +597,13 @@ TRUNNER_BPF_BUILD_RULE := CLANG_NOALU32_BPF_BUILD_RULE
 TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
 $(eval $(call DEFINE_TEST_RUNNER,test_progs,no_alu32))
 
+# Define test_progs-cpuv4 test runner.
+ifneq ($(CLANG_CPUV4),)
+TRUNNER_BPF_BUILD_RULE := CLANG_CPUV4_BPF_BUILD_RULE
+TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
+$(eval $(call DEFINE_TEST_RUNNER,test_progs,cpuv4))
+endif
+
 # Define test_progs BPF-GCC-flavored test runner.
 ifneq ($(BPF_GCC),)
 TRUNNER_BPF_BUILD_RULE := GCC_BPF_BUILD_RULE
@@ -681,7 +701,7 @@ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)	\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
 	feature bpftool							\
 	$(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h	\
-			       no_alu32 bpf_gcc bpf_testmod.ko		\
+			       no_alu32 cpuv4 bpf_gcc bpf_testmod.ko	\
 			       liburandom_read.so)
 
 .PHONY: docs docs-clean
-- 
GitLab


From 147c8f4470eeae14c566984bd81b33334866ce10 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:13:04 -0700
Subject: [PATCH 0556/1806] selftests/bpf: Add unit tests for new
 sign-extension load insns

Add unit tests for new ldsx insns. The test includes sign-extension
with a single value or with a value range.

If cpuv4 is not supported due to
  (1) older compiler, e.g., less than clang version 18, or
  (2) test runner test_progs and test_progs-no_alu32 which tests
      cpu v2 and v3, or
  (3) non-x86_64 arch not supporting new insns in jit yet,
a dummy program is added with below output:
  #318/1   verifier_ldsx/cpuv4 is not supported by compiler or jit, use a dummy test:OK
  #318     verifier_ldsx:OK
to indicate the test passed with a dummy test instead of actually
testing cpuv4. I am using a dummy prog to avoid changing the
verifier testing infrastructure. Once clang 18 is widely available
and other architectures support cpuv4, at least for CI run,
the dummy program can be removed.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011304.3719139-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/verifier.c       |   2 +
 .../selftests/bpf/progs/verifier_ldsx.c       | 131 ++++++++++++++++++
 2 files changed, 133 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_ldsx.c

diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index c375e59ff28da..6eec6a9463c8e 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -31,6 +31,7 @@
 #include "verifier_int_ptr.skel.h"
 #include "verifier_jeq_infer_not_null.skel.h"
 #include "verifier_ld_ind.skel.h"
+#include "verifier_ldsx.skel.h"
 #include "verifier_leak_ptr.skel.h"
 #include "verifier_loops1.skel.h"
 #include "verifier_lwt.skel.h"
@@ -133,6 +134,7 @@ void test_verifier_helper_value_access(void)  { RUN(verifier_helper_value_access
 void test_verifier_int_ptr(void)              { RUN(verifier_int_ptr); }
 void test_verifier_jeq_infer_not_null(void)   { RUN(verifier_jeq_infer_not_null); }
 void test_verifier_ld_ind(void)               { RUN(verifier_ld_ind); }
+void test_verifier_ldsx(void)                  { RUN(verifier_ldsx); }
 void test_verifier_leak_ptr(void)             { RUN(verifier_leak_ptr); }
 void test_verifier_loops1(void)               { RUN(verifier_loops1); }
 void test_verifier_lwt(void)                  { RUN(verifier_lwt); }
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
new file mode 100644
index 0000000000000..3c3d1bddd67f9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+
+SEC("socket")
+__description("LDSX, S8")
+__success __success_unpriv __retval(-2)
+__naked void ldsx_s8(void)
+{
+	asm volatile ("					\
+	r1 = 0x3fe;					\
+	*(u64 *)(r10 - 8) = r1;				\
+	r0 = *(s8 *)(r10 - 8);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S16")
+__success __success_unpriv __retval(-2)
+__naked void ldsx_s16(void)
+{
+	asm volatile ("					\
+	r1 = 0x3fffe;					\
+	*(u64 *)(r10 - 8) = r1;				\
+	r0 = *(s16 *)(r10 - 8);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S32")
+__success __success_unpriv __retval(-1)
+__naked void ldsx_s32(void)
+{
+	asm volatile ("					\
+	r1 = 0xfffffffe;				\
+	*(u64 *)(r10 - 8) = r1;				\
+	r0 = *(s32 *)(r10 - 8);				\
+	r0 >>= 1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S8 range checking, privileged")
+__log_level(2) __success __retval(1)
+__msg("R1_w=scalar(smin=-128,smax=127)")
+__naked void ldsx_s8_range_priv(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	*(u64 *)(r10 - 8) = r0;				\
+	r1 = *(s8 *)(r10 - 8);				\
+	/* r1 with s8 range */				\
+	if r1 s> 0x7f goto l0_%=;			\
+	if r1 s< -0x80 goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S16 range checking")
+__success __success_unpriv __retval(1)
+__naked void ldsx_s16_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	*(u64 *)(r10 - 8) = r0;				\
+	r1 = *(s16 *)(r10 - 8);				\
+	/* r1 with s16 range */				\
+	if r1 s> 0x7fff goto l0_%=;			\
+	if r1 s< -0x8000 goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S32 range checking")
+__success __success_unpriv __retval(1)
+__naked void ldsx_s32_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	*(u64 *)(r10 - 8) = r0;				\
+	r1 = *(s32 *)(r10 - 8);				\
+	/* r1 with s16 range */				\
+	if r1 s> 0x7fffFFFF goto l0_%=;			\
+	if r1 s< -0x80000000 goto l0_%=;		\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From f02ec3ff3f09b191a6fde8dcf805da6a01baea97 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:13:09 -0700
Subject: [PATCH 0557/1806] selftests/bpf: Add unit tests for new
 sign-extension mov insns

Add unit tests for movsx insns.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011309.3719295-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/verifier.c       |   2 +
 .../selftests/bpf/progs/verifier_movsx.c      | 213 ++++++++++++++++++
 2 files changed, 215 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_movsx.c

diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 6eec6a9463c8e..037af7799cdf6 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -41,6 +41,7 @@
 #include "verifier_map_ret_val.skel.h"
 #include "verifier_masking.skel.h"
 #include "verifier_meta_access.skel.h"
+#include "verifier_movsx.skel.h"
 #include "verifier_netfilter_ctx.skel.h"
 #include "verifier_netfilter_retcode.skel.h"
 #include "verifier_prevent_map_lookup.skel.h"
@@ -144,6 +145,7 @@ void test_verifier_map_ptr_mixing(void)       { RUN(verifier_map_ptr_mixing); }
 void test_verifier_map_ret_val(void)          { RUN(verifier_map_ret_val); }
 void test_verifier_masking(void)              { RUN(verifier_masking); }
 void test_verifier_meta_access(void)          { RUN(verifier_meta_access); }
+void test_verifier_movsx(void)                 { RUN(verifier_movsx); }
 void test_verifier_netfilter_ctx(void)        { RUN(verifier_netfilter_ctx); }
 void test_verifier_netfilter_retcode(void)    { RUN(verifier_netfilter_retcode); }
 void test_verifier_prevent_map_lookup(void)   { RUN(verifier_prevent_map_lookup); }
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
new file mode 100644
index 0000000000000..9568089932d78
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+
+SEC("socket")
+__description("MOV32SX, S8")
+__success __success_unpriv __retval(0x23)
+__naked void mov32sx_s8(void)
+{
+	asm volatile ("					\
+	w0 = 0xff23;					\
+	w0 = (s8)w0;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S16")
+__success __success_unpriv __retval(0xFFFFff23)
+__naked void mov32sx_s16(void)
+{
+	asm volatile ("					\
+	w0 = 0xff23;					\
+	w0 = (s16)w0;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S8")
+__success __success_unpriv __retval(-2)
+__naked void mov64sx_s8(void)
+{
+	asm volatile ("					\
+	r0 = 0x1fe;					\
+	r0 = (s8)r0;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S16")
+__success __success_unpriv __retval(0xf23)
+__naked void mov64sx_s16(void)
+{
+	asm volatile ("					\
+	r0 = 0xf0f23;					\
+	r0 = (s16)r0;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S32")
+__success __success_unpriv __retval(-1)
+__naked void mov64sx_s32(void)
+{
+	asm volatile ("					\
+	r0 = 0xfffffffe;				\
+	r0 = (s32)r0;					\
+	r0 >>= 1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S8, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov32sx_s8_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = (s8)w0;					\
+	/* w1 with s8 range */				\
+	if w1 s> 0x7f goto l0_%=;			\
+	if w1 s< -0x80 goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S16, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov32sx_s16_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = (s16)w0;					\
+	/* w1 with s16 range */				\
+	if w1 s> 0x7fff goto l0_%=;			\
+	if w1 s< -0x80ff goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S16, range_check 2")
+__success __success_unpriv __retval(1)
+__naked void mov32sx_s16_range_2(void)
+{
+	asm volatile ("					\
+	r1 = 65535;					\
+	w2 = (s16)w1;					\
+	r2 >>= 1;					\
+	if r2 != 0x7fffFFFF goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 0;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S8, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov64sx_s8_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = (s8)r0;					\
+	/* r1 with s8 range */				\
+	if r1 s> 0x7f goto l0_%=;			\
+	if r1 s< -0x80 goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S16, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov64sx_s16_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = (s16)r0;					\
+	/* r1 with s16 range */				\
+	if r1 s> 0x7fff goto l0_%=;			\
+	if r1 s< -0x8000 goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S32, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov64sx_s32_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = (s32)r0;					\
+	/* r1 with s32 range */				\
+	if r1 s> 0x7fffffff goto l0_%=;			\
+	if r1 s< -0x80000000 goto l0_%=;		\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From 79dbabc175408f7f6a7d156ab8fd68539703459c Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:13:14 -0700
Subject: [PATCH 0558/1806] selftests/bpf: Add unit tests for new bswap insns

Add unit tests for bswap insns.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011314.3720109-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/verifier.c       |  2 +
 .../selftests/bpf/progs/verifier_bswap.c      | 59 +++++++++++++++++++
 2 files changed, 61 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_bswap.c

diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 037af7799cdf6..885532540bc3c 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -11,6 +11,7 @@
 #include "verifier_bounds_deduction_non_const.skel.h"
 #include "verifier_bounds_mix_sign_unsign.skel.h"
 #include "verifier_bpf_get_stack.skel.h"
+#include "verifier_bswap.skel.h"
 #include "verifier_btf_ctx_access.skel.h"
 #include "verifier_cfg.skel.h"
 #include "verifier_cgroup_inv_retcode.skel.h"
@@ -115,6 +116,7 @@ void test_verifier_bounds_deduction(void)     { RUN(verifier_bounds_deduction);
 void test_verifier_bounds_deduction_non_const(void)     { RUN(verifier_bounds_deduction_non_const); }
 void test_verifier_bounds_mix_sign_unsign(void) { RUN(verifier_bounds_mix_sign_unsign); }
 void test_verifier_bpf_get_stack(void)        { RUN(verifier_bpf_get_stack); }
+void test_verifier_bswap(void)                { RUN(verifier_bswap); }
 void test_verifier_btf_ctx_access(void)       { RUN(verifier_btf_ctx_access); }
 void test_verifier_cfg(void)                  { RUN(verifier_cfg); }
 void test_verifier_cgroup_inv_retcode(void)   { RUN(verifier_cgroup_inv_retcode); }
diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
new file mode 100644
index 0000000000000..724bb38988b53
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+
+SEC("socket")
+__description("BSWAP, 16")
+__success __success_unpriv __retval(0x23ff)
+__naked void bswap_16(void)
+{
+	asm volatile ("					\
+	r0 = 0xff23;					\
+	r0 = bswap16 r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("BSWAP, 32")
+__success __success_unpriv __retval(0x23ff0000)
+__naked void bswap_32(void)
+{
+	asm volatile ("					\
+	r0 = 0xff23;					\
+	r0 = bswap32 r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("BSWAP, 64")
+__success __success_unpriv __retval(0x34ff12ff)
+__naked void bswap_64(void)
+{
+	asm volatile ("					\
+	r0 = %[u64_val] ll;					\
+	r0 = bswap64 r0;				\
+	exit;						\
+"	:
+	: [u64_val]"i"(0xff12ff34ff56ff78ull)
+	: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From de1c26809ec37b632ad7bcec3bba8b849eb44d43 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:13:21 -0700
Subject: [PATCH 0559/1806] selftests/bpf: Add unit tests for new sdiv/smod
 insns

Add unit tests for sdiv/smod insns.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011321.3720500-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/verifier.c       |   2 +
 .../selftests/bpf/progs/verifier_sdiv.c       | 781 ++++++++++++++++++
 2 files changed, 783 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_sdiv.c

diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 885532540bc3c..a591d7b673f19 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -54,6 +54,7 @@
 #include "verifier_ringbuf.skel.h"
 #include "verifier_runtime_jit.skel.h"
 #include "verifier_scalar_ids.skel.h"
+#include "verifier_sdiv.skel.h"
 #include "verifier_search_pruning.skel.h"
 #include "verifier_sock.skel.h"
 #include "verifier_spill_fill.skel.h"
@@ -159,6 +160,7 @@ void test_verifier_regalloc(void)             { RUN(verifier_regalloc); }
 void test_verifier_ringbuf(void)              { RUN(verifier_ringbuf); }
 void test_verifier_runtime_jit(void)          { RUN(verifier_runtime_jit); }
 void test_verifier_scalar_ids(void)           { RUN(verifier_scalar_ids); }
+void test_verifier_sdiv(void)                 { RUN(verifier_sdiv); }
 void test_verifier_search_pruning(void)       { RUN(verifier_search_pruning); }
 void test_verifier_sock(void)                 { RUN(verifier_sock); }
 void test_verifier_spill_fill(void)           { RUN(verifier_spill_fill); }
diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
new file mode 100644
index 0000000000000..f61a9a1058c8e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -0,0 +1,781 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_imm_1(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_imm_2(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_imm_3(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_imm_4(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_imm_5(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_imm_6(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 7")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_imm_7(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 8")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_imm_8(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_reg_1(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w1 = 2;						\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_reg_2(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w1 = -2;					\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_reg_3(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w1 = -2;					\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_reg_4(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w1 = 2;						\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_reg_5(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = -2;					\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_reg_6(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w1 = -2;					\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 7")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_reg_7(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 2;						\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 8")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_reg_8(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w1 = 2;						\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_imm_1(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_imm_2(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv64_non_zero_imm_3(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_imm_4(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_imm_5(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv64_non_zero_imm_6(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_reg_1(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r1 = 2;						\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_reg_2(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r1 = -2;					\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv64_non_zero_reg_3(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r1 = -2;					\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_reg_4(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r1 = 2;						\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_reg_5(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r1 = -2;					\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv64_non_zero_reg_6(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r1 = -2;					\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_imm_1(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod32_non_zero_imm_2(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_imm_3(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_imm_4(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_imm_5(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_imm_6(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_reg_1(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w1 = 2;						\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod32_non_zero_reg_2(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w1 = -2;					\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_reg_3(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w1 = -2;					\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_reg_4(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w1 = 2;						\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_reg_5(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = -2;					\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_reg_6(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w1 = -2;					\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_imm_1(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_imm_2(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_imm_3(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_imm_4(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(-0)
+__naked void smod64_non_zero_imm_5(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_imm_6(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 7")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_imm_7(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 8")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_imm_8(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_reg_1(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r1 = 2;						\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_reg_2(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r1 = -2;					\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_reg_3(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r1 = -2;					\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_4(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r1 = 2;						\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_5(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r1 = -2;					\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_6(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r1 = -2;					\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 7")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_7(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r1 = 2;						\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 8")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_reg_8(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r1 = 2;						\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, zero divisor")
+__success __success_unpriv __retval(0)
+__naked void sdiv32_zero_divisor(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 0;						\
+	w2 = -1;					\
+	w2 s/= w1;					\
+	w0 = w2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, zero divisor")
+__success __success_unpriv __retval(0)
+__naked void sdiv64_zero_divisor(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r1 = 0;						\
+	r2 = -1;					\
+	r2 s/= r1;					\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, zero divisor")
+__success __success_unpriv __retval(-1)
+__naked void smod32_zero_divisor(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 0;						\
+	w2 = -1;					\
+	w2 s%%= w1;					\
+	w0 = w2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, zero divisor")
+__success __success_unpriv __retval(-1)
+__naked void smod64_zero_divisor(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r1 = 0;						\
+	r2 = -1;					\
+	r2 s%%= r1;					\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From 613dad498072f20d9bfd996422f0fd8e9a2f6c0d Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:13:29 -0700
Subject: [PATCH 0560/1806] selftests/bpf: Add unit tests for new gotol insn

Add unit tests for gotol insn.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011329.3721881-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/verifier.c       |  2 +
 .../selftests/bpf/progs/verifier_gotol.c      | 44 +++++++++++++++++++
 2 files changed, 46 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_gotol.c

diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index a591d7b673f19..e3e68c97b40cf 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -25,6 +25,7 @@
 #include "verifier_direct_stack_access_wraparound.skel.h"
 #include "verifier_div0.skel.h"
 #include "verifier_div_overflow.skel.h"
+#include "verifier_gotol.skel.h"
 #include "verifier_helper_access_var_len.skel.h"
 #include "verifier_helper_packet_access.skel.h"
 #include "verifier_helper_restricted.skel.h"
@@ -131,6 +132,7 @@ void test_verifier_direct_packet_access(void) { RUN(verifier_direct_packet_acces
 void test_verifier_direct_stack_access_wraparound(void) { RUN(verifier_direct_stack_access_wraparound); }
 void test_verifier_div0(void)                 { RUN(verifier_div0); }
 void test_verifier_div_overflow(void)         { RUN(verifier_div_overflow); }
+void test_verifier_gotol(void)                { RUN(verifier_gotol); }
 void test_verifier_helper_access_var_len(void) { RUN(verifier_helper_access_var_len); }
 void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_access); }
 void test_verifier_helper_restricted(void)    { RUN(verifier_helper_restricted); }
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
new file mode 100644
index 0000000000000..ce48f7757db24
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+
+SEC("socket")
+__description("gotol, small_imm")
+__success __success_unpriv __retval(1)
+__naked void gotol_small_imm(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 == 0 goto l0_%=;				\
+	gotol l1_%=;					\
+l2_%=:							\
+	gotol l3_%=;					\
+l1_%=:							\
+	r0 = 1;						\
+	gotol l2_%=;					\
+l0_%=:							\
+	r0 = 2;						\
+l3_%=:							\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From 0c606571ae07568b18c112d011dc8cd01d6ae346 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:13:36 -0700
Subject: [PATCH 0561/1806] selftests/bpf: Test ldsx with more complex cases

The following ldsx cases are tested:
  - signed readonly map value
  - read/write map value
  - probed memory
  - not-narrowed ctx field access
  - narrowed ctx field access.

Without previous proper verifier/git handling, the test will fail.

If cpuv4 is not supported either by compiler or by jit,
the test will be skipped.

  # ./test_progs -t ldsx_insn
  #113/1   ldsx_insn/map_val and probed_memory:SKIP
  #113/2   ldsx_insn/ctx_member_sign_ext:SKIP
  #113/3   ldsx_insn/ctx_member_narrow_sign_ext:SKIP
  #113     ldsx_insn:SKIP
  Summary: 1/0 PASSED, 3 SKIPPED, 0 FAILED

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011336.3723434-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/bpf_testmod/bpf_testmod.c   |   9 +-
 .../selftests/bpf/prog_tests/test_ldsx_insn.c | 139 ++++++++++++++++++
 .../selftests/bpf/progs/test_ldsx_insn.c      | 118 +++++++++++++++
 3 files changed, 265 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_ldsx_insn.c

diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index a6f991b56345d..cefc5dd72573c 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -98,6 +98,12 @@ bpf_testmod_test_struct_arg_8(u64 a, void *b, short c, int d, void *e,
 	return bpf_testmod_test_struct_arg_result;
 }
 
+noinline int
+bpf_testmod_test_arg_ptr_to_struct(struct bpf_testmod_struct_arg_1 *a) {
+	bpf_testmod_test_struct_arg_result = a->a;
+	return bpf_testmod_test_struct_arg_result;
+}
+
 __bpf_kfunc void
 bpf_testmod_test_mod_kfunc(int i)
 {
@@ -240,7 +246,7 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 		.off = off,
 		.len = len,
 	};
-	struct bpf_testmod_struct_arg_1 struct_arg1 = {10};
+	struct bpf_testmod_struct_arg_1 struct_arg1 = {10}, struct_arg1_2 = {-1};
 	struct bpf_testmod_struct_arg_2 struct_arg2 = {2, 3};
 	struct bpf_testmod_struct_arg_3 *struct_arg3;
 	struct bpf_testmod_struct_arg_4 struct_arg4 = {21, 22};
@@ -259,6 +265,7 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 	(void)bpf_testmod_test_struct_arg_8(16, (void *)17, 18, 19,
 					    (void *)20, struct_arg4, 23);
 
+	(void)bpf_testmod_test_arg_ptr_to_struct(&struct_arg1_2);
 
 	struct_arg3 = kmalloc((sizeof(struct bpf_testmod_struct_arg_3) +
 				sizeof(int)), GFP_KERNEL);
diff --git a/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c b/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c
new file mode 100644
index 0000000000000..375677c191462
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates.*/
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_ldsx_insn.skel.h"
+
+static void test_map_val_and_probed_memory(void)
+{
+	struct test_ldsx_insn *skel;
+	int err;
+
+	skel = test_ldsx_insn__open();
+	if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open"))
+		return;
+
+	if (skel->rodata->skip) {
+		test__skip();
+		goto out;
+	}
+
+	bpf_program__set_autoload(skel->progs.rdonly_map_prog, true);
+	bpf_program__set_autoload(skel->progs.map_val_prog, true);
+	bpf_program__set_autoload(skel->progs.test_ptr_struct_arg, true);
+
+	err = test_ldsx_insn__load(skel);
+	if (!ASSERT_OK(err, "test_ldsx_insn__load"))
+		goto out;
+
+	err = test_ldsx_insn__attach(skel);
+	if (!ASSERT_OK(err, "test_ldsx_insn__attach"))
+		goto out;
+
+	ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+	ASSERT_EQ(skel->bss->done1, 1, "done1");
+	ASSERT_EQ(skel->bss->ret1, 1, "ret1");
+	ASSERT_EQ(skel->bss->done2, 1, "done2");
+	ASSERT_EQ(skel->bss->ret2, 1, "ret2");
+	ASSERT_EQ(skel->bss->int_member, -1, "int_member");
+
+out:
+	test_ldsx_insn__destroy(skel);
+}
+
+static void test_ctx_member_sign_ext(void)
+{
+	struct test_ldsx_insn *skel;
+	int err, fd, cgroup_fd;
+	char buf[16] = {0};
+	socklen_t optlen;
+
+	cgroup_fd = test__join_cgroup("/ldsx_test");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /ldsx_test"))
+		return;
+
+	skel = test_ldsx_insn__open();
+	if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open"))
+		goto close_cgroup_fd;
+
+	if (skel->rodata->skip) {
+		test__skip();
+		goto destroy_skel;
+	}
+
+	bpf_program__set_autoload(skel->progs._getsockopt, true);
+
+	err = test_ldsx_insn__load(skel);
+	if (!ASSERT_OK(err, "test_ldsx_insn__load"))
+		goto destroy_skel;
+
+	skel->links._getsockopt =
+		bpf_program__attach_cgroup(skel->progs._getsockopt, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links._getsockopt, "getsockopt_link"))
+		goto destroy_skel;
+
+	fd = socket(AF_INET, SOCK_STREAM, 0);
+	if (!ASSERT_GE(fd, 0, "socket"))
+		goto destroy_skel;
+
+	optlen = sizeof(buf);
+	(void)getsockopt(fd, SOL_IP, IP_TTL, buf, &optlen);
+
+	ASSERT_EQ(skel->bss->set_optlen, -1, "optlen");
+	ASSERT_EQ(skel->bss->set_retval, -1, "retval");
+
+	close(fd);
+destroy_skel:
+	test_ldsx_insn__destroy(skel);
+close_cgroup_fd:
+	close(cgroup_fd);
+}
+
+static void test_ctx_member_narrow_sign_ext(void)
+{
+	struct test_ldsx_insn *skel;
+	struct __sk_buff skb = {};
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .ctx_in = &skb,
+		    .ctx_size_in = sizeof(skb),
+	);
+	int err, prog_fd;
+
+	skel = test_ldsx_insn__open();
+	if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open"))
+		return;
+
+	if (skel->rodata->skip) {
+		test__skip();
+		goto out;
+	}
+
+	bpf_program__set_autoload(skel->progs._tc, true);
+
+	err = test_ldsx_insn__load(skel);
+	if (!ASSERT_OK(err, "test_ldsx_insn__load"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs._tc);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+
+	ASSERT_EQ(skel->bss->set_mark, -2, "set_mark");
+
+out:
+	test_ldsx_insn__destroy(skel);
+}
+
+void test_ldsx_insn(void)
+{
+	if (test__start_subtest("map_val and probed_memory"))
+		test_map_val_and_probed_memory();
+	if (test__start_subtest("ctx_member_sign_ext"))
+		test_ctx_member_sign_ext();
+	if (test__start_subtest("ctx_member_narrow_sign_ext"))
+		test_ctx_member_narrow_sign_ext();
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
new file mode 100644
index 0000000000000..321abf8628017
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+const volatile int skip = 0;
+#else
+const volatile int skip = 1;
+#endif
+
+volatile const short val1 = -1;
+volatile const int val2 = -1;
+short val3 = -1;
+int val4 = -1;
+int done1, done2, ret1, ret2;
+
+SEC("?raw_tp/sys_enter")
+int rdonly_map_prog(const void *ctx)
+{
+	if (done1)
+		return 0;
+
+	done1 = 1;
+	/* val1/val2 readonly map */
+	if (val1 == val2)
+		ret1 = 1;
+	return 0;
+
+}
+
+SEC("?raw_tp/sys_enter")
+int map_val_prog(const void *ctx)
+{
+	if (done2)
+		return 0;
+
+	done2 = 1;
+	/* val1/val2 regular read/write map */
+	if (val3 == val4)
+		ret2 = 1;
+	return 0;
+
+}
+
+struct bpf_testmod_struct_arg_1 {
+	int a;
+};
+
+long long int_member;
+
+SEC("?fentry/bpf_testmod_test_arg_ptr_to_struct")
+int BPF_PROG2(test_ptr_struct_arg, struct bpf_testmod_struct_arg_1 *, p)
+{
+	/* probed memory access */
+	int_member = p->a;
+        return 0;
+}
+
+long long set_optlen, set_retval;
+
+SEC("?cgroup/getsockopt")
+int _getsockopt(volatile struct bpf_sockopt *ctx)
+{
+	int old_optlen, old_retval;
+
+	old_optlen = ctx->optlen;
+	old_retval = ctx->retval;
+
+	ctx->optlen = -1;
+	ctx->retval = -1;
+
+	/* sign extension for ctx member */
+	set_optlen = ctx->optlen;
+	set_retval = ctx->retval;
+
+	ctx->optlen = old_optlen;
+	ctx->retval = old_retval;
+
+	return 0;
+}
+
+long long set_mark;
+
+SEC("?tc")
+int _tc(volatile struct __sk_buff *skb)
+{
+	long long tmp_mark;
+	int old_mark;
+
+	old_mark = skb->mark;
+
+	skb->mark = 0xf6fe;
+
+	/* narrowed sign extension for ctx member */
+#if __clang_major__ >= 18
+	/* force narrow one-byte signed load. Otherwise, compiler may
+	 * generate a 32-bit unsigned load followed by an s8 movsx.
+	 */
+	asm volatile ("r1 = *(s8 *)(%[ctx] + %[off_mark])\n\t"
+		      "%[tmp_mark] = r1"
+		      : [tmp_mark]"=r"(tmp_mark)
+		      : [ctx]"r"(skb),
+			[off_mark]"i"(offsetof(struct __sk_buff, mark))
+		      : "r1");
+#else
+	tmp_mark = (char)skb->mark;
+#endif
+	set_mark = tmp_mark;
+
+	skb->mark = old_mark;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From 245d4c40c09bd8d5a71640950eeb074880925b9a Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 18:13:42 -0700
Subject: [PATCH 0562/1806] docs/bpf: Add documentation for new instructions

Add documentation in instruction-set.rst for new instruction encoding
and their corresponding operations. Also removed the question
related to 'no BPF_SDIV' in bpf_design_QA.rst since we have
BPF_SDIV insn now.

Cc: bpf@ietf.org
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728011342.3724411-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/bpf/bpf_design_QA.rst           |   5 -
 .../bpf/standardization/instruction-set.rst   | 115 ++++++++++++------
 2 files changed, 79 insertions(+), 41 deletions(-)

diff --git a/Documentation/bpf/bpf_design_QA.rst b/Documentation/bpf/bpf_design_QA.rst
index 38372a956d651..eb19c945f4d57 100644
--- a/Documentation/bpf/bpf_design_QA.rst
+++ b/Documentation/bpf/bpf_design_QA.rst
@@ -140,11 +140,6 @@ A: Because if we picked one-to-one relationship to x64 it would have made
 it more complicated to support on arm64 and other archs. Also it
 needs div-by-zero runtime check.
 
-Q: Why there is no BPF_SDIV for signed divide operation?
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-A: Because it would be rarely used. llvm errors in such case and
-prints a suggestion to use unsigned divide instead.
-
 Q: Why BPF has implicit prologue and epilogue?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 A: Because architectures like sparc have register windows and in general
diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 6ef5534b410a9..23e880a83a1f5 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -154,24 +154,27 @@ otherwise identical operations.
 The 'code' field encodes the operation as below, where 'src' and 'dst' refer
 to the values of the source and destination registers, respectively.
 
-========  =====  ==========================================================
-code      value  description
-========  =====  ==========================================================
-BPF_ADD   0x00   dst += src
-BPF_SUB   0x10   dst -= src
-BPF_MUL   0x20   dst \*= src
-BPF_DIV   0x30   dst = (src != 0) ? (dst / src) : 0
-BPF_OR    0x40   dst \|= src
-BPF_AND   0x50   dst &= src
-BPF_LSH   0x60   dst <<= (src & mask)
-BPF_RSH   0x70   dst >>= (src & mask)
-BPF_NEG   0x80   dst = -dst
-BPF_MOD   0x90   dst = (src != 0) ? (dst % src) : dst
-BPF_XOR   0xa0   dst ^= src
-BPF_MOV   0xb0   dst = src
-BPF_ARSH  0xc0   sign extending dst >>= (src & mask)
-BPF_END   0xd0   byte swap operations (see `Byte swap instructions`_ below)
-========  =====  ==========================================================
+========  =====  =======  ==========================================================
+code      value  offset   description
+========  =====  =======  ==========================================================
+BPF_ADD   0x00   0        dst += src
+BPF_SUB   0x10   0        dst -= src
+BPF_MUL   0x20   0        dst \*= src
+BPF_DIV   0x30   0        dst = (src != 0) ? (dst / src) : 0
+BPF_SDIV  0x30   1        dst = (src != 0) ? (dst s/ src) : 0
+BPF_OR    0x40   0        dst \|= src
+BPF_AND   0x50   0        dst &= src
+BPF_LSH   0x60   0        dst <<= (src & mask)
+BPF_RSH   0x70   0        dst >>= (src & mask)
+BPF_NEG   0x80   0        dst = -dst
+BPF_MOD   0x90   0        dst = (src != 0) ? (dst % src) : dst
+BPF_SMOD  0x90   1        dst = (src != 0) ? (dst s% src) : dst
+BPF_XOR   0xa0   0        dst ^= src
+BPF_MOV   0xb0   0        dst = src
+BPF_MOVSX 0xb0   8/16/32  dst = (s8,s16,s32)src
+BPF_ARSH  0xc0   0        sign extending dst >>= (src & mask)
+BPF_END   0xd0   0        byte swap operations (see `Byte swap instructions`_ below)
+========  =====  ============  ==========================================================
 
 Underflow and overflow are allowed during arithmetic operations, meaning
 the 64-bit or 32-bit value will wrap. If eBPF program execution would
@@ -198,11 +201,20 @@ where '(u32)' indicates that the upper 32 bits are zeroed.
 
   dst = dst ^ imm32
 
-Also note that the division and modulo operations are unsigned. Thus, for
-``BPF_ALU``, 'imm' is first interpreted as an unsigned 32-bit value, whereas
-for ``BPF_ALU64``, 'imm' is first sign extended to 64 bits and the result
-interpreted as an unsigned 64-bit value. There are no instructions for
-signed division or modulo.
+Note that most instructions have instruction offset of 0. But three instructions
+(BPF_SDIV, BPF_SMOD, BPF_MOVSX) have non-zero offset.
+
+The devision and modulo operations support both unsigned and signed flavors.
+For unsigned operation (BPF_DIV and BPF_MOD), for ``BPF_ALU``, 'imm' is first
+interpreted as an unsigned 32-bit value, whereas for ``BPF_ALU64``, 'imm' is
+first sign extended to 64 bits and the result interpreted as an unsigned 64-bit
+value.  For signed operation (BPF_SDIV and BPF_SMOD), for ``BPF_ALU``, 'imm' is
+interpreted as a signed value. For ``BPF_ALU64``, the 'imm' is sign extended
+from 32 to 64 and interpreted as a signed 64-bit value.
+
+Instruction BPF_MOVSX does move operation with sign extension.
+``BPF_ALU | MOVSX`` sign extendes 8-bit and 16-bit into 32-bit and upper 32-bit are zeroed.
+``BPF_ALU64 | MOVSX`` sign extends 8-bit, 16-bit and 32-bit into 64-bit.
 
 Shift operations use a mask of 0x3F (63) for 64-bit operations and 0x1F (31)
 for 32-bit operations.
@@ -210,21 +222,23 @@ for 32-bit operations.
 Byte swap instructions
 ~~~~~~~~~~~~~~~~~~~~~~
 
-The byte swap instructions use an instruction class of ``BPF_ALU`` and a 4-bit
-'code' field of ``BPF_END``.
+The byte swap instructions use instruction classes of ``BPF_ALU`` and ``BPF_ALU64``
+and a 4-bit 'code' field of ``BPF_END``.
 
 The byte swap instructions operate on the destination register
 only and do not use a separate source register or immediate value.
 
-The 1-bit source operand field in the opcode is used to select what byte
-order the operation convert from or to:
+For ``BPF_ALU``, the 1-bit source operand field in the opcode is used to select what byte
+order the operation convert from or to. For ``BPF_ALU64``, the 1-bit source operand
+field in the opcode is not used and must be 0.
 
-=========  =====  =================================================
-source     value  description
-=========  =====  =================================================
-BPF_TO_LE  0x00   convert between host byte order and little endian
-BPF_TO_BE  0x08   convert between host byte order and big endian
-=========  =====  =================================================
+=========  =========  =====  =================================================
+class      source     value  description
+=========  =========  =====  =================================================
+BPF_ALU    BPF_TO_LE  0x00   convert between host byte order and little endian
+BPF_ALU    BPF_TO_BE  0x08   convert between host byte order and big endian
+BPF_ALU64  BPF_TO_LE  0x00   do byte swap unconditionally
+=========  =========  =====  =================================================
 
 The 'imm' field encodes the width of the swap operations.  The following widths
 are supported: 16, 32 and 64.
@@ -239,6 +253,12 @@ Examples:
 
   dst = htobe64(dst)
 
+``BPF_ALU64 | BPF_TO_LE | BPF_END`` with imm = 16/32/64 means::
+
+  dst = bswap16 dst
+  dst = bswap32 dst
+  dst = bswap64 dst
+
 Jump instructions
 -----------------
 
@@ -249,7 +269,8 @@ The 'code' field encodes the operation as below:
 ========  =====  ===  ===========================================  =========================================
 code      value  src  description                                  notes
 ========  =====  ===  ===========================================  =========================================
-BPF_JA    0x0    0x0  PC += offset                                 BPF_JMP only
+BPF_JA    0x0    0x0  PC += offset                                 BPF_JMP class
+BPF_JA    0x0    0x0  PC += imm                                    BPF_JMP32 class
 BPF_JEQ   0x1    any  PC += offset if dst == src
 BPF_JGT   0x2    any  PC += offset if dst > src                    unsigned
 BPF_JGE   0x3    any  PC += offset if dst >= src                   unsigned
@@ -278,6 +299,16 @@ Example:
 
 where 's>=' indicates a signed '>=' comparison.
 
+``BPF_JA | BPF_K | BPF_JMP32`` (0x06) means::
+
+  gotol +imm
+
+where 'imm' means the branch offset comes from insn 'imm' field.
+
+Note there are two flavors of BPF_JA instrions. BPF_JMP class permits 16-bit jump offset while
+BPF_JMP32 permits 32-bit jump offset. A >16bit conditional jmp can be converted to a <16bit
+conditional jmp plus a 32-bit unconditional jump.
+
 Helper functions
 ~~~~~~~~~~~~~~~~
 
@@ -320,6 +351,7 @@ The mode modifier is one of:
   BPF_ABS        0x20   legacy BPF packet access (absolute)   `Legacy BPF Packet access instructions`_
   BPF_IND        0x40   legacy BPF packet access (indirect)   `Legacy BPF Packet access instructions`_
   BPF_MEM        0x60   regular load and store operations     `Regular load and store operations`_
+  BPF_MEMSX      0x80   sign-extension load operations        `Sign-extension load operations`_
   BPF_ATOMIC     0xc0   atomic operations                     `Atomic operations`_
   =============  =====  ====================================  =============
 
@@ -350,9 +382,20 @@ instructions that transfer data between a register and memory.
 
 ``BPF_MEM | <size> | BPF_LDX`` means::
 
-  dst = *(size *) (src + offset)
+  dst = *(unsigned size *) (src + offset)
+
+Where size is one of: ``BPF_B``, ``BPF_H``, ``BPF_W``, or ``BPF_DW`` and
+'unsigned size' is one of u8, u16, u32 and u64.
+
+The ``BPF_MEMSX`` mode modifier is used to encode sign-extension load
+instructions that transfer data between a register and memory.
+
+``BPF_MEMSX | <size> | BPF_LDX`` means::
+
+  dst = *(signed size *) (src + offset)
 
-Where size is one of: ``BPF_B``, ``BPF_H``, ``BPF_W``, or ``BPF_DW``.
+Where size is one of: ``BPF_B``, ``BPF_H`` or ``BPF_W``, and
+'signed size' is one of s8, s16 and s32.
 
 Atomic operations
 -----------------
-- 
GitLab


From e22e358bbeb3256e2eb854493b46c815402087bb Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 26 Jul 2023 21:15:51 +0200
Subject: [PATCH 0563/1806] net/tls: handle MSG_EOR for tls_sw TX flow

tls_sw_sendmsg() already handles MSG_MORE, but bails
out on MSG_EOR.
Seeing that MSG_EOR is basically the opposite of
MSG_MORE this patch adds handling MSG_EOR by treating
it as the negation of MSG_MORE.
And erroring out if MSG_EOR is specified with MSG_MORE.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230726191556.41714-2-hare@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 53f944e6d8ef2..9aef45e870a56 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -984,6 +984,9 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 	int ret = 0;
 	int pending;
 
+	if (!eor && (msg->msg_flags & MSG_EOR))
+		return -EINVAL;
+
 	if (unlikely(msg->msg_controllen)) {
 		ret = tls_process_cmsg(sk, msg, &record_type);
 		if (ret) {
@@ -1193,7 +1196,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int ret;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
-			       MSG_CMSG_COMPAT | MSG_SPLICE_PAGES |
+			       MSG_CMSG_COMPAT | MSG_SPLICE_PAGES | MSG_EOR |
 			       MSG_SENDPAGE_NOPOLICY))
 		return -EOPNOTSUPP;
 
-- 
GitLab


From c004b0e00c94322a2f82a8b0b7711ed938097774 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 26 Jul 2023 21:15:52 +0200
Subject: [PATCH 0564/1806] net/tls: handle MSG_EOR for tls_device TX flow

tls_push_data() MSG_MORE, but bails out on MSG_EOR.
Seeing that MSG_EOR is basically the opposite of MSG_MORE
this patch adds handling MSG_EOR by treating it as the
absence of MSG_MORE.
Consequently we should return an error when both are set.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230726191556.41714-3-hare@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_device.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 2021fe557e503..5df18f696d7f8 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -441,9 +441,13 @@ static int tls_push_data(struct sock *sk,
 	long timeo;
 
 	if (flags &
-	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SPLICE_PAGES))
+	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
+	      MSG_SPLICE_PAGES | MSG_EOR))
 		return -EOPNOTSUPP;
 
+	if ((flags & (MSG_MORE | MSG_EOR)) == (MSG_MORE | MSG_EOR))
+		return -EINVAL;
+
 	if (unlikely(sk->sk_err))
 		return -sk->sk_err;
 
-- 
GitLab


From 8790c6a4f54d455ee85453f9493b4cd60a01dc38 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 26 Jul 2023 21:15:53 +0200
Subject: [PATCH 0565/1806] selftests/net/tls: add test for MSG_EOR

As the recent patch is modifying the behaviour for TLS re MSG_EOR
handling we should be having a test for it.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230726191556.41714-4-hare@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index a3c57004344c6..4b63708c6a818 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -486,6 +486,17 @@ TEST_F(tls, msg_more_unsent)
 	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
 }
 
+TEST_F(tls, msg_eor)
+{
+	char const *test_str = "test_read";
+	int send_len = 10;
+	char buf[10];
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, MSG_EOR), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
 TEST_F(tls, sendmsg_single)
 {
 	struct msghdr msg;
-- 
GitLab


From 11863c6d440d34c4b967e517739b38a7e68ed092 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 26 Jul 2023 21:15:54 +0200
Subject: [PATCH 0566/1806] net/tls: Use tcp_read_sock() instead of
 ops->read_sock()

TLS resets the protocol operations, so the read_sock() callback might
be changed, too.
In this case using sock->ops->readsock() in tls_strp_read_copyin() will
enter an infinite recursion if the read_sock() callback is calling
tls_rx_rec_wait() which will call into sock->ops->readsock() via
tls_strp_read_copyin().
But as tls_strp_read_copyin() is supposed to produce data from the
consumed socket and that socket is always a TCP socket we can call
tcp_read_sock() directly without having to deal with callbacks.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230726191556.41714-5-hare@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_strp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c
index f37f4a0fcd3c2..ca1e0e198ceb4 100644
--- a/net/tls/tls_strp.c
+++ b/net/tls/tls_strp.c
@@ -369,7 +369,6 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb,
 
 static int tls_strp_read_copyin(struct tls_strparser *strp)
 {
-	struct socket *sock = strp->sk->sk_socket;
 	read_descriptor_t desc;
 
 	desc.arg.data = strp;
@@ -377,7 +376,7 @@ static int tls_strp_read_copyin(struct tls_strparser *strp)
 	desc.count = 1; /* give more than one skb per call */
 
 	/* sk should be locked here, so okay to do read_sock */
-	sock->ops->read_sock(strp->sk, &desc, tls_strp_copyin);
+	tcp_read_sock(strp->sk, &desc, tls_strp_copyin);
 
 	return desc.error;
 }
-- 
GitLab


From f9ae3204fb45d0749befc1cdff50f691c7461e5a Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 26 Jul 2023 21:15:55 +0200
Subject: [PATCH 0567/1806] net/tls: split tls_rx_reader_lock

Split tls_rx_reader_{lock,unlock} into an 'acquire/release' and
the actual locking part.
With that we can use the tls_rx_reader_lock in situations where
the socket is already locked.

Suggested-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230726191556.41714-6-hare@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 38 ++++++++++++++++++++++----------------
 1 file changed, 22 insertions(+), 16 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 9aef45e870a56..d0636ea130091 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1848,13 +1848,10 @@ tls_read_flush_backlog(struct sock *sk, struct tls_prot_info *prot,
 	return sk_flush_backlog(sk);
 }
 
-static int tls_rx_reader_lock(struct sock *sk, struct tls_sw_context_rx *ctx,
-			      bool nonblock)
+static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx,
+				 bool nonblock)
 {
 	long timeo;
-	int err;
-
-	lock_sock(sk);
 
 	timeo = sock_rcvtimeo(sk, nonblock);
 
@@ -1868,26 +1865,30 @@ static int tls_rx_reader_lock(struct sock *sk, struct tls_sw_context_rx *ctx,
 			      !READ_ONCE(ctx->reader_present), &wait);
 		remove_wait_queue(&ctx->wq, &wait);
 
-		if (timeo <= 0) {
-			err = -EAGAIN;
-			goto err_unlock;
-		}
-		if (signal_pending(current)) {
-			err = sock_intr_errno(timeo);
-			goto err_unlock;
-		}
+		if (timeo <= 0)
+			return -EAGAIN;
+		if (signal_pending(current))
+			return sock_intr_errno(timeo);
 	}
 
 	WRITE_ONCE(ctx->reader_present, 1);
 
 	return 0;
+}
 
-err_unlock:
-	release_sock(sk);
+static int tls_rx_reader_lock(struct sock *sk, struct tls_sw_context_rx *ctx,
+			      bool nonblock)
+{
+	int err;
+
+	lock_sock(sk);
+	err = tls_rx_reader_acquire(sk, ctx, nonblock);
+	if (err)
+		release_sock(sk);
 	return err;
 }
 
-static void tls_rx_reader_unlock(struct sock *sk, struct tls_sw_context_rx *ctx)
+static void tls_rx_reader_release(struct sock *sk, struct tls_sw_context_rx *ctx)
 {
 	if (unlikely(ctx->reader_contended)) {
 		if (wq_has_sleeper(&ctx->wq))
@@ -1899,6 +1900,11 @@ static void tls_rx_reader_unlock(struct sock *sk, struct tls_sw_context_rx *ctx)
 	}
 
 	WRITE_ONCE(ctx->reader_present, 0);
+}
+
+static void tls_rx_reader_unlock(struct sock *sk, struct tls_sw_context_rx *ctx)
+{
+	tls_rx_reader_release(sk, ctx);
 	release_sock(sk);
 }
 
-- 
GitLab


From 662fbcec32f4af6bdcf5b4006b792ebe9543d945 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 26 Jul 2023 21:15:56 +0200
Subject: [PATCH 0568/1806] net/tls: implement ->read_sock()

Implement ->read_sock() function for use with nvme-tcp.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Cc: Boris Pismenny <boris.pismenny@gmail.com>
Link: https://lore.kernel.org/r/20230726191556.41714-7-hare@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls.h      |  2 +
 net/tls/tls_main.c |  2 +
 net/tls/tls_sw.c   | 99 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 103 insertions(+)

diff --git a/net/tls/tls.h b/net/tls/tls.h
index 86cef1c68e03b..7e4d45537deb0 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -110,6 +110,8 @@ bool tls_sw_sock_is_readable(struct sock *sk);
 ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
 			   struct pipe_inode_info *pipe,
 			   size_t len, unsigned int flags);
+int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
+		     sk_read_actor_t read_actor);
 
 int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 void tls_device_splice_eof(struct socket *sock);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index b6896126bb922..7dbb8cd8f809b 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -962,10 +962,12 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG]
 	ops[TLS_BASE][TLS_SW  ] = ops[TLS_BASE][TLS_BASE];
 	ops[TLS_BASE][TLS_SW  ].splice_read	= tls_sw_splice_read;
 	ops[TLS_BASE][TLS_SW  ].poll		= tls_sk_poll;
+	ops[TLS_BASE][TLS_SW  ].read_sock	= tls_sw_read_sock;
 
 	ops[TLS_SW  ][TLS_SW  ] = ops[TLS_SW  ][TLS_BASE];
 	ops[TLS_SW  ][TLS_SW  ].splice_read	= tls_sw_splice_read;
 	ops[TLS_SW  ][TLS_SW  ].poll		= tls_sk_poll;
+	ops[TLS_SW  ][TLS_SW  ].read_sock	= tls_sw_read_sock;
 
 #ifdef CONFIG_TLS_DEVICE
 	ops[TLS_HW  ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index d0636ea130091..9c1f13541708d 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2202,6 +2202,105 @@ splice_requeue:
 	goto splice_read_end;
 }
 
+int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
+		     sk_read_actor_t read_actor)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+	struct tls_prot_info *prot = &tls_ctx->prot_info;
+	struct strp_msg *rxm = NULL;
+	struct sk_buff *skb = NULL;
+	struct sk_psock *psock;
+	size_t flushed_at = 0;
+	bool released = true;
+	struct tls_msg *tlm;
+	ssize_t copied = 0;
+	ssize_t decrypted;
+	int err, used;
+
+	psock = sk_psock_get(sk);
+	if (psock) {
+		sk_psock_put(sk, psock);
+		return -EINVAL;
+	}
+	err = tls_rx_reader_acquire(sk, ctx, true);
+	if (err < 0)
+		return err;
+
+	/* If crypto failed the connection is broken */
+	err = ctx->async_wait.err;
+	if (err)
+		goto read_sock_end;
+
+	decrypted = 0;
+	do {
+		if (!skb_queue_empty(&ctx->rx_list)) {
+			skb = __skb_dequeue(&ctx->rx_list);
+			rxm = strp_msg(skb);
+			tlm = tls_msg(skb);
+		} else {
+			struct tls_decrypt_arg darg;
+			int to_decrypt;
+
+			err = tls_rx_rec_wait(sk, NULL, true, released);
+			if (err <= 0)
+				goto read_sock_end;
+
+			memset(&darg.inargs, 0, sizeof(darg.inargs));
+
+			rxm = strp_msg(tls_strp_msg(ctx));
+			tlm = tls_msg(tls_strp_msg(ctx));
+
+			to_decrypt = rxm->full_len - prot->overhead_size;
+
+			err = tls_rx_one_record(sk, NULL, &darg);
+			if (err < 0) {
+				tls_err_abort(sk, -EBADMSG);
+				goto read_sock_end;
+			}
+
+			released = tls_read_flush_backlog(sk, prot, rxm->full_len, to_decrypt,
+							  decrypted, &flushed_at);
+			skb = darg.skb;
+			decrypted += rxm->full_len;
+
+			tls_rx_rec_done(ctx);
+		}
+
+		/* read_sock does not support reading control messages */
+		if (tlm->control != TLS_RECORD_TYPE_DATA) {
+			err = -EINVAL;
+			goto read_sock_requeue;
+		}
+
+		used = read_actor(desc, skb, rxm->offset, rxm->full_len);
+		if (used <= 0) {
+			if (!copied)
+				err = used;
+			goto read_sock_requeue;
+		}
+		copied += used;
+		if (used < rxm->full_len) {
+			rxm->offset += used;
+			rxm->full_len -= used;
+			if (!desc->count)
+				goto read_sock_requeue;
+		} else {
+			consume_skb(skb);
+			if (!desc->count)
+				skb = NULL;
+		}
+	} while (skb);
+
+read_sock_end:
+	tls_rx_reader_release(sk, ctx);
+	return copied ? : err;
+
+read_sock_requeue:
+	__skb_queue_head(&ctx->rx_list, skb);
+	goto read_sock_end;
+}
+
 bool tls_sw_sock_is_readable(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
-- 
GitLab


From d928d14be6514af9da37009c2091270c5c714366 Mon Sep 17 00:00:00 2001
From: Andrew Halaney <ahalaney@redhat.com>
Date: Tue, 25 Jul 2023 16:04:25 -0500
Subject: [PATCH 0569/1806] net: stmmac: Make ptp_clk_freq_config variable type
 explicit

The priv variable is _always_ of type (struct stmmac_priv *), so let's
stop using (void *) since it isn't abstracting anything.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230725211853.895832-3-ahalaney@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 3 +--
 include/linux/stmmac.h                            | 4 +++-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 0ffae785d8bd9..979c755964b14 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -257,9 +257,8 @@ static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data)
 /* Program PTP Clock Frequency for different variant of
  * Intel mGBE that has slightly different GPO mapping
  */
-static void intel_mgbe_ptp_clk_freq_config(void *npriv)
+static void intel_mgbe_ptp_clk_freq_config(struct stmmac_priv *priv)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)npriv;
 	struct intel_priv_data *intel_priv;
 	u32 gpio_value;
 
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index ef67dba775d04..3d07025102242 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -76,6 +76,8 @@
 			| DMA_AXI_BLEN_32 | DMA_AXI_BLEN_64 \
 			| DMA_AXI_BLEN_128 | DMA_AXI_BLEN_256)
 
+struct stmmac_priv;
+
 /* Platfrom data for platform device structure's platform_data field */
 
 struct stmmac_mdio_bus_data {
@@ -258,7 +260,7 @@ struct plat_stmmacenet_data {
 	int (*serdes_powerup)(struct net_device *ndev, void *priv);
 	void (*serdes_powerdown)(struct net_device *ndev, void *priv);
 	void (*speed_mode_2500)(struct net_device *ndev, void *priv);
-	void (*ptp_clk_freq_config)(void *priv);
+	void (*ptp_clk_freq_config)(struct stmmac_priv *priv);
 	int (*init)(struct platform_device *pdev, void *priv);
 	void (*exit)(struct platform_device *pdev, void *priv);
 	struct mac_device_info *(*setup)(void *priv);
-- 
GitLab


From db845b9b2040f4ed5f8bce6cd30103e3b8557566 Mon Sep 17 00:00:00 2001
From: Andrew Halaney <ahalaney@redhat.com>
Date: Tue, 25 Jul 2023 16:04:26 -0500
Subject: [PATCH 0570/1806] net: stmmac: dwmac-qcom-ethqos: Use max frequency
 for clk_ptp_ref

Qualcomm clocks can set their frequency to a variety of levels
generally. Let's use the max for clk_ptp_ref to ensure the best
timestamping resolution possible.

Without this, the default value of the clock is used. For sa8775p-ride
this is 19.2 MHz, far less than the 230.4 MHz possible.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20230725211853.895832-4-ahalaney@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../stmicro/stmmac/dwmac-qcom-ethqos.c         | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 735525ba8b931..a855018748011 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -694,6 +694,23 @@ static void ethqos_clks_disable(void *data)
 	ethqos_clks_config(data, false);
 }
 
+static void ethqos_ptp_clk_freq_config(struct stmmac_priv *priv)
+{
+	struct plat_stmmacenet_data *plat_dat = priv->plat;
+	int err;
+
+	if (!plat_dat->clk_ptp_ref)
+		return;
+
+	/* Max the PTP ref clock out to get the best resolution possible */
+	err = clk_set_rate(plat_dat->clk_ptp_ref, ULONG_MAX);
+	if (err)
+		netdev_err(priv->dev, "Failed to max out clk_ptp_ref: %d\n", err);
+	plat_dat->clk_ptp_rate = clk_get_rate(plat_dat->clk_ptp_ref);
+
+	netdev_dbg(priv->dev, "PTP rate %d\n", plat_dat->clk_ptp_rate);
+}
+
 static int qcom_ethqos_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
@@ -779,6 +796,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	plat_dat->bsp_priv = ethqos;
 	plat_dat->fix_mac_speed = ethqos_fix_mac_speed;
 	plat_dat->dump_debug_regs = rgmii_dump;
+	plat_dat->ptp_clk_freq_config = ethqos_ptp_clk_freq_config;
 	plat_dat->has_gmac4 = 1;
 	if (ethqos->has_emac_ge_3)
 		plat_dat->dwmac4_addrs = &data->dwmac4_addrs;
-- 
GitLab


From 81b04a800d3c537d1d9ac1f0c2192011c4ebabb7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 26 Jul 2023 15:40:54 -0700
Subject: [PATCH 0571/1806] Revert "net: stmmac: correct MAC propagation delay"

This reverts commit 20bf98c94146eb6fe62177817cb32f53e72dd2e8.

Richard raised concerns about correctness of the code on previous
generations of the HW.

Fixes: 20bf98c94146 ("net: stmmac: correct MAC propagation delay")
Link: https://lore.kernel.org/all/ZMGIuKVP7BEotbrn@hoboy.vegasvil.org/
Link: https://lore.kernel.org/r/20230726224054.3241127-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/hwif.h    |  3 --
 .../ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 43 -------------------
 .../net/ethernet/stmicro/stmmac/stmmac_main.c |  4 --
 .../net/ethernet/stmicro/stmmac/stmmac_ptp.h  |  6 ---
 4 files changed, 56 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 40147ef249631..652af8f6e75ff 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -532,7 +532,6 @@ struct stmmac_hwtimestamp {
 	void (*get_systime) (void __iomem *ioaddr, u64 *systime);
 	void (*get_ptptime)(void __iomem *ioaddr, u64 *ptp_time);
 	void (*timestamp_interrupt)(struct stmmac_priv *priv);
-	void (*correct_latency)(struct stmmac_priv *priv);
 };
 
 #define stmmac_config_hw_tstamping(__priv, __args...) \
@@ -551,8 +550,6 @@ struct stmmac_hwtimestamp {
 	stmmac_do_void_callback(__priv, ptp, get_ptptime, __args)
 #define stmmac_timestamp_interrupt(__priv, __args...) \
 	stmmac_do_void_callback(__priv, ptp, timestamp_interrupt, __args)
-#define stmmac_correct_latency(__priv, __args...) \
-	stmmac_do_void_callback(__priv, ptp, correct_latency, __args)
 
 struct stmmac_tx_queue;
 struct stmmac_rx_queue;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 7e0fa024e0ad0..fa2c3ba7e9fe7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -60,48 +60,6 @@ static void config_sub_second_increment(void __iomem *ioaddr,
 		*ssinc = data;
 }
 
-static void correct_latency(struct stmmac_priv *priv)
-{
-	void __iomem *ioaddr = priv->ptpaddr;
-	u32 reg_tsic, reg_tsicsns;
-	u32 reg_tsec, reg_tsecsns;
-	u64 scaled_ns;
-	u32 val;
-
-	/* MAC-internal ingress latency */
-	scaled_ns = readl(ioaddr + PTP_TS_INGR_LAT);
-
-	/* See section 11.7.2.5.3.1 "Ingress Correction" on page 4001 of
-	 * i.MX8MP Applications Processor Reference Manual Rev. 1, 06/2021
-	 */
-	val = readl(ioaddr + PTP_TCR);
-	if (val & PTP_TCR_TSCTRLSSR)
-		/* nanoseconds field is in decimal format with granularity of 1ns/bit */
-		scaled_ns = ((u64)NSEC_PER_SEC << 16) - scaled_ns;
-	else
-		/* nanoseconds field is in binary format with granularity of ~0.466ns/bit */
-		scaled_ns = ((1ULL << 31) << 16) -
-			DIV_U64_ROUND_CLOSEST(scaled_ns * PSEC_PER_NSEC, 466U);
-
-	reg_tsic = scaled_ns >> 16;
-	reg_tsicsns = scaled_ns & 0xff00;
-
-	/* set bit 31 for 2's compliment */
-	reg_tsic |= BIT(31);
-
-	writel(reg_tsic, ioaddr + PTP_TS_INGR_CORR_NS);
-	writel(reg_tsicsns, ioaddr + PTP_TS_INGR_CORR_SNS);
-
-	/* MAC-internal egress latency */
-	scaled_ns = readl(ioaddr + PTP_TS_EGR_LAT);
-
-	reg_tsec = scaled_ns >> 16;
-	reg_tsecsns = scaled_ns & 0xff00;
-
-	writel(reg_tsec, ioaddr + PTP_TS_EGR_CORR_NS);
-	writel(reg_tsecsns, ioaddr + PTP_TS_EGR_CORR_SNS);
-}
-
 static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec)
 {
 	u32 value;
@@ -263,5 +221,4 @@ const struct stmmac_hwtimestamp stmmac_ptp = {
 	.get_systime = get_systime,
 	.get_ptptime = get_ptptime,
 	.timestamp_interrupt = timestamp_interrupt,
-	.correct_latency = correct_latency,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 19e46e8f626aa..e1f1c034d3259 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -909,8 +909,6 @@ static int stmmac_init_ptp(struct stmmac_priv *priv)
 	priv->hwts_tx_en = 0;
 	priv->hwts_rx_en = 0;
 
-	stmmac_correct_latency(priv, priv);
-
 	return 0;
 }
 
@@ -1096,8 +1094,6 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 
 	if (priv->dma_cap.fpesel)
 		stmmac_fpe_link_state_handle(priv, true);
-
-	stmmac_correct_latency(priv, priv);
 }
 
 static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
index d1fe4b46f1629..bf619295d079f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
@@ -26,12 +26,6 @@
 #define	PTP_ACR		0x40	/* Auxiliary Control Reg */
 #define	PTP_ATNR	0x48	/* Auxiliary Timestamp - Nanoseconds Reg */
 #define	PTP_ATSR	0x4c	/* Auxiliary Timestamp - Seconds Reg */
-#define	PTP_TS_INGR_CORR_NS	0x58	/* Ingress timestamp correction nanoseconds */
-#define	PTP_TS_EGR_CORR_NS	0x5C	/* Egress timestamp correction nanoseconds*/
-#define	PTP_TS_INGR_CORR_SNS	0x60	/* Ingress timestamp correction subnanoseconds */
-#define	PTP_TS_EGR_CORR_SNS	0x64	/* Egress timestamp correction subnanoseconds */
-#define	PTP_TS_INGR_LAT	0x68	/* MAC internal Ingress Latency */
-#define	PTP_TS_EGR_LAT	0x6c	/* MAC internal Egress Latency */
 
 #define	PTP_STNSUR_ADDSUB_SHIFT	31
 #define	PTP_DIGITAL_ROLLOVER_MODE	0x3B9ACA00	/* 10e9-1 ns */
-- 
GitLab


From 3d40aed862874db14e1dd41fd6f12636dcfdcc3e Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 26 Jul 2023 19:49:39 -0600
Subject: [PATCH 0572/1806] net: Explicitly include correct DT includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Acked-by: Alex Elder <elder@linaro.org>
Reviewed-by: Bhupesh Sharma <bhupesh.sharma@linaro.org>
Reviewed-by: Wei Fang <wei.fang@nxp.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230727014944.3972546-1-robh@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aeroflex/greth.c                   | 4 ++--
 drivers/net/ethernet/amd/sunlance.c                     | 2 +-
 drivers/net/ethernet/apm/xgene-v2/main.h                | 1 +
 drivers/net/ethernet/arc/emac_main.c                    | 2 +-
 drivers/net/ethernet/atheros/ag71xx.c                   | 3 ++-
 drivers/net/ethernet/cadence/macb_main.c                | 1 -
 drivers/net/ethernet/cirrus/cs89x0.c                    | 1 -
 drivers/net/ethernet/ezchip/nps_enet.c                  | 5 ++---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c          | 3 ++-
 drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c      | 2 ++
 drivers/net/ethernet/freescale/enetc/enetc_ierb.c       | 2 +-
 drivers/net/ethernet/freescale/fec_mpc52xx.c            | 4 ++--
 drivers/net/ethernet/freescale/fec_mpc52xx_phy.c        | 3 ++-
 drivers/net/ethernet/freescale/fec_ptp.c                | 1 -
 drivers/net/ethernet/freescale/fman/fman.c              | 1 +
 drivers/net/ethernet/freescale/fman/fman_port.c         | 1 +
 drivers/net/ethernet/freescale/fman/mac.c               | 2 ++
 drivers/net/ethernet/freescale/fs_enet/mac-fcc.c        | 1 -
 drivers/net/ethernet/freescale/fs_enet/mac-fec.c        | 1 -
 drivers/net/ethernet/freescale/fs_enet/mac-scc.c        | 1 -
 drivers/net/ethernet/freescale/fsl_pq_mdio.c            | 1 +
 drivers/net/ethernet/freescale/gianfar.c                | 2 +-
 drivers/net/ethernet/freescale/gianfar_ethtool.c        | 2 ++
 drivers/net/ethernet/freescale/ucc_geth.c               | 3 ++-
 drivers/net/ethernet/freescale/xgmac_mdio.c             | 4 ++--
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c       | 3 ---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c       | 4 ----
 drivers/net/ethernet/ibm/ehea/ehea_main.c               | 1 +
 drivers/net/ethernet/ibm/emac/core.c                    | 1 +
 drivers/net/ethernet/ibm/emac/core.h                    | 1 -
 drivers/net/ethernet/ibm/emac/mal.c                     | 2 ++
 drivers/net/ethernet/ibm/emac/rgmii.c                   | 2 ++
 drivers/net/ethernet/ibm/emac/tah.c                     | 2 ++
 drivers/net/ethernet/ibm/emac/zmii.c                    | 2 ++
 drivers/net/ethernet/korina.c                           | 2 +-
 drivers/net/ethernet/marvell/mvmdio.c                   | 2 +-
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c         | 1 -
 drivers/net/ethernet/marvell/prestera/prestera_rxtx.c   | 3 ---
 drivers/net/ethernet/marvell/sky2.c                     | 1 -
 drivers/net/ethernet/mediatek/mtk_eth_soc.c             | 3 ++-
 drivers/net/ethernet/mediatek/mtk_star_emac.c           | 1 -
 drivers/net/ethernet/mediatek/mtk_wed.c                 | 1 +
 drivers/net/ethernet/mediatek/mtk_wed_wo.c              | 3 +--
 drivers/net/ethernet/microchip/lan966x/lan966x_main.c   | 3 ++-
 drivers/net/ethernet/mscc/ocelot_fdma.c                 | 1 -
 drivers/net/ethernet/mscc/ocelot_vsc7514.c              | 3 ++-
 drivers/net/ethernet/ni/nixge.c                         | 5 ++---
 drivers/net/ethernet/qualcomm/emac/emac-sgmii.c         | 2 ++
 drivers/net/ethernet/qualcomm/emac/emac.c               | 1 -
 drivers/net/ethernet/qualcomm/qca_spi.c                 | 1 -
 drivers/net/ethernet/qualcomm/qca_uart.c                | 1 -
 drivers/net/ethernet/renesas/ravb_main.c                | 3 +--
 drivers/net/ethernet/renesas/rswitch.c                  | 3 +--
 drivers/net/ethernet/renesas/sh_eth.c                   | 2 --
 drivers/net/ethernet/smsc/smsc911x.c                    | 1 -
 drivers/net/ethernet/socionext/sni_ave.c                | 3 ++-
 drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c         | 1 -
 drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c     | 1 -
 drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c    | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c     | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c       | 1 -
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 1 -
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c          | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c    | 4 +++-
 drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c         | 1 -
 drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c       | 1 -
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c       | 3 ++-
 drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c       | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c    | 3 ++-
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c   | 1 -
 drivers/net/ethernet/sun/niu.c                          | 2 +-
 drivers/net/ethernet/sun/sunbmac.c                      | 2 +-
 drivers/net/ethernet/sun/sungem.c                       | 1 +
 drivers/net/ethernet/sun/sunhme.c                       | 3 ++-
 drivers/net/ethernet/sun/sunqe.c                        | 2 +-
 drivers/net/ethernet/ti/am65-cpsw-nuss.c                | 1 +
 drivers/net/ethernet/ti/cpsw-common.c                   | 1 -
 drivers/net/ethernet/ti/cpsw-phy-sel.c                  | 1 -
 drivers/net/ethernet/ti/davinci_mdio.c                  | 1 -
 drivers/net/ethernet/via/via-rhine.c                    | 2 +-
 drivers/net/ethernet/via/via-velocity.c                 | 2 +-
 drivers/net/ethernet/xilinx/ll_temac.h                  | 1 +
 drivers/net/ethernet/xilinx/ll_temac_main.c             | 4 +---
 drivers/net/ethernet/xilinx/ll_temac_mdio.c             | 2 +-
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c       | 3 ++-
 drivers/net/ethernet/xilinx/xilinx_emaclite.c           | 4 ++--
 drivers/net/ieee802154/ca8210.c                         | 1 -
 drivers/net/ipa/ipa_main.c                              | 2 +-
 net/core/of_net.c                                       | 1 +
 90 files changed, 88 insertions(+), 92 deletions(-)

diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index aa0d2f3aaeaaa..597a02c75d527 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -29,9 +29,9 @@
 #include <linux/io.h>
 #include <linux/crc32.h>
 #include <linux/mii.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/of_net.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
 #include <asm/byteorder.h>
diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index 68ca1225eedc1..33bb539ad70a8 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -92,7 +92,7 @@ static char lancestr[] = "LANCE";
 #include <linux/bitops.h>
 #include <linux/dma-mapping.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
 #include <linux/gfp.h>
 #include <linux/pgtable.h>
 
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h
index b3985a7be59d1..7be6f83e22fe0 100644
--- a/drivers/net/ethernet/apm/xgene-v2/main.h
+++ b/drivers/net/ethernet/apm/xgene-v2/main.h
@@ -22,6 +22,7 @@
 #include <linux/of_mdio.h>
 #include <linux/prefetch.h>
 #include <linux/phy.h>
+#include <linux/platform_device.h>
 #include <net/ip.h>
 #include "mac.h"
 #include "enet.h"
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index 2b427d8a18315..31ee477dd131e 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -15,11 +15,11 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-#include <linux/of_platform.h>
 
 #include "emac.h"
 
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index ff1a5edf8df11..009e0b3066fa3 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -29,9 +29,10 @@
 
 #include <linux/if_vlan.h>
 #include <linux/mfd/syscon.h>
+#include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/phylink.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f6a0f12a6d520..b61566afb2f45 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -26,7 +26,6 @@
 #include <linux/platform_device.h>
 #include <linux/phylink.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_gpio.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c
index 276c32c3926a7..7c51fd9fc9bee 100644
--- a/drivers/net/ethernet/cirrus/cs89x0.c
+++ b/drivers/net/ethernet/cirrus/cs89x0.c
@@ -54,7 +54,6 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index f1eb660aaee2e..edf000e7bab45 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -6,10 +6,9 @@
 #include <linux/module.h>
 #include <linux/etherdevice.h>
 #include <linux/interrupt.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
+#include <linux/mod_devicetable.h>
 #include <linux/of_net.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include "nps_enet.h"
 
 #define DRV_NAME			"nps_mgt_enet"
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 85e38a1ec22a4..dcbc598b11c6c 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -7,8 +7,8 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/init.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_platform.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/io.h>
@@ -17,6 +17,7 @@
 #include <linux/icmp.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/platform_device.h>
 #include <linux/udp.h>
 #include <linux/tcp.h>
 #include <linux/net.h>
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
index 9c71cbbb13d8a..5bd0b36d1feb5 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -6,7 +6,9 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/string.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/net_tstamp.h>
 #include <linux/fsl/ptp_qoriq.h>
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c
index b307bef4dc298..d39617ab93069 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c
@@ -18,8 +18,8 @@
  */
 
 #include <linux/io.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include "enetc.h"
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c
index 984ece5cd64f6..ebae71ec26c6e 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c
@@ -29,12 +29,12 @@
 #include <linux/crc32.h>
 #include <linux/hardirq.h>
 #include <linux/delay.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c b/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c
index 61d3776d67509..39689826cc8ff 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c
@@ -13,10 +13,11 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
-#include <linux/of_platform.h>
 #include <linux/slab.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_mdio.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/mpc52xx.h>
 #include "fec_mpc52xx.h"
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index afc658d2c2711..fc4674cb65be5 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -30,7 +30,6 @@
 #include <linux/phy.h>
 #include <linux/fec.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_gpio.h>
 #include <linux/of_net.h>
 
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index 9d85fb136e345..d96028f01770c 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -7,6 +7,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/fsl/guts.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index ab90fe2bee5e3..406e75e9e5ea2 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -6,6 +6,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/io.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index c5045891d694b..b6c7c4c0b367d 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -12,12 +12,14 @@
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
 #include <linux/device.h>
+#include <linux/of_platform.h>
 #include <linux/phy.h>
 #include <linux/netdevice.h>
 #include <linux/phy_fixed.h>
 #include <linux/phylink.h>
 #include <linux/etherdevice.h>
 #include <linux/libfdt_env.h>
+#include <linux/platform_device.h>
 
 #include "mac.h"
 #include "fman_mac.h"
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index b47490be872cf..925428f1b0c85 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -32,7 +32,6 @@
 #include <linux/platform_device.h>
 #include <linux/phy.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/gfp.h>
 #include <linux/pgtable.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index 61f4b6e50d29b..f609dc112458c 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -32,7 +32,6 @@
 #include <linux/fs.h>
 #include <linux/platform_device.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/gfp.h>
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index 64300ac13e025..66d40da5cde00 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -32,7 +32,6 @@
 #include <linux/platform_device.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
 
 #include <asm/irq.h>
 #include <linux/uaccess.h>
diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 01d594886f52b..eee675a25b2c3 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/platform_device.h>
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 0c898f9ee3581..e3dfbd7a42361 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -60,6 +60,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
+#include <linux/platform_device.h>
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/unistd.h>
@@ -75,7 +76,6 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
-#include <linux/of_platform.h>
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index b2b0d3c26fcc1..7a15b9245698b 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -38,7 +38,9 @@
 #include <linux/phy.h>
 #include <linux/sort.h>
 #include <linux/if_vlan.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/fsl/ptp_qoriq.h>
 
 #include "gianfar.h"
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 2b3a15f24e7c3..ab421243a4192 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -28,11 +28,12 @@
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
 #include <linux/workqueue.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 #include <linux/uaccess.h>
 #include <asm/irq.h>
diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c
index a13b4ba4d6e16..65dc07d0df0fc 100644
--- a/drivers/net/ethernet/freescale/xgmac_mdio.c
+++ b/drivers/net/ethernet/freescale/xgmac_mdio.c
@@ -19,10 +19,10 @@
 #include <linux/kernel.h>
 #include <linux/mdio.h>
 #include <linux/module.h>
-#include <linux/of_address.h>
+#include <linux/of.h>
 #include <linux/of_mdio.h>
-#include <linux/of_platform.h>
 #include <linux/phy.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 
 /* Number of microseconds to wait for a register to respond */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index a7eb87da4e707..a08d1f0a5a165 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -9,9 +9,6 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/platform_device.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
 
 #include "hns_dsaf_ppe.h"
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index e2ff3ca198d1b..93344563a259f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -11,10 +11,6 @@
 #include <linux/etherdevice.h>
 #include <asm/cacheflush.h>
 #include <linux/platform_device.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
-#include <linux/of_irq.h>
 #include <linux/spinlock.h>
 
 #include "hns_dsaf_main.h"
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index b4aff59b3eb4f..0a56e97524646 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -31,6 +31,7 @@
 #include <linux/prefetch.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/platform_device.h>
 
 #include <net/ip.h>
 
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index c97095abd26ab..0c314bf974808 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -38,6 +38,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 89a1b0fea158f..295516b076626 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -27,7 +27,6 @@
 #include <linux/netdevice.h>
 #include <linux/dma-mapping.h>
 #include <linux/spinlock.h>
-#include <linux/of_platform.h>
 #include <linux/slab.h>
 
 #include <asm/io.h>
diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index ff5487bbebe37..c3236b59e7e93 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -22,7 +22,9 @@
 
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
+#include <linux/platform_device.h>
 
 #include "core.h"
 #include <asm/dcr-regs.h>
diff --git a/drivers/net/ethernet/ibm/emac/rgmii.c b/drivers/net/ethernet/ibm/emac/rgmii.c
index 50358cf001306..fd437f986edfd 100644
--- a/drivers/net/ethernet/ibm/emac/rgmii.c
+++ b/drivers/net/ethernet/ibm/emac/rgmii.c
@@ -19,7 +19,9 @@
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/ethtool.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 
 #include "emac.h"
diff --git a/drivers/net/ethernet/ibm/emac/tah.c b/drivers/net/ethernet/ibm/emac/tah.c
index 008bbdaf1204e..aae9a88d95d76 100644
--- a/drivers/net/ethernet/ibm/emac/tah.c
+++ b/drivers/net/ethernet/ibm/emac/tah.c
@@ -14,7 +14,9 @@
  *
  * Copyright (c) 2005 Eugene Surovegin <ebs@ebshome.net>
  */
+#include <linux/mod_devicetable.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 
 #include "emac.h"
diff --git a/drivers/net/ethernet/ibm/emac/zmii.c b/drivers/net/ethernet/ibm/emac/zmii.c
index 57a25c7a9e70d..6337388ee5f4a 100644
--- a/drivers/net/ethernet/ibm/emac/zmii.c
+++ b/drivers/net/ethernet/ibm/emac/zmii.c
@@ -19,7 +19,9 @@
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/ethtool.h>
+#include <linux/mod_devicetable.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 
 #include "emac.h"
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index 2b9335cb4bb3a..25f7a2a3b847a 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -43,7 +43,7 @@
 #include <linux/ioport.h>
 #include <linux/iopoll.h>
 #include <linux/in.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/slab.h>
 #include <linux/string.h>
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index 8662543ca5c87..a1a80f13b1e89 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -24,8 +24,8 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/of_mdio.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 1fec84b4c068d..9e1b596c8f088 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -24,7 +24,6 @@
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/phy.h>
 #include <linux/phylink.h>
 #include <linux/phy/phy.h>
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c
index 9277a8fd1339d..cc2a9ae794bea 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c
@@ -5,9 +5,6 @@
 #include <linux/dmapool.h>
 #include <linux/etherdevice.h>
 #include <linux/if_vlan.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
-#include <linux/of.h>
 #include <linux/platform_device.h>
 
 #include "prestera_dsa.h"
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 7c487f9b36ec6..c4cca27fb0d53 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -32,7 +32,6 @@
 #include <linux/prefetch.h>
 #include <linux/debugfs.h>
 #include <linux/mii.h>
-#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/dmi.h>
 
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 30e3935e83f9a..38f39be04eaed 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -6,11 +6,12 @@
  *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
  */
 
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/of_address.h>
 #include <linux/mfd/syscon.h>
+#include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 02c03325911f4..31aebeb2e2858 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index 5f062ecb402cc..00aeee0d5e45f 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2021 Felix Fietkau <nbd@nbd.name> */
 
 #include <linux/kernel.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/bitfield.h>
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c
index 69fba29055e91..3bd51a3d66500 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c
@@ -7,10 +7,9 @@
 
 #include <linux/kernel.h>
 #include <linux/dma-mapping.h>
-#include <linux/of_platform.h>
 #include <linux/interrupt.h>
-#include <linux/of_address.h>
 #include <linux/mfd/syscon.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/bitfield.h>
 
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index fbb0bb4594cd7..73f20683210ed 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -5,9 +5,10 @@
 #include <linux/if_vlan.h>
 #include <linux/iopoll.h>
 #include <linux/ip.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/phy/phy.h>
+#include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <net/addrconf.h>
 
diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c
index 83a3ce0c568e8..312a468321544 100644
--- a/drivers/net/ethernet/mscc/ocelot_fdma.c
+++ b/drivers/net/ethernet/mscc/ocelot_fdma.c
@@ -12,7 +12,6 @@
 #include <linux/dmapool.h>
 #include <linux/dsa/ocelot.h>
 #include <linux/netdevice.h>
-#include <linux/of_platform.h>
 #include <linux/skbuff.h>
 
 #include "ocelot_fdma.h"
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 97e90e2869d4a..151b424653483 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -10,8 +10,9 @@
 #include <linux/of_net.h>
 #include <linux/netdevice.h>
 #include <linux/phylink.h>
+#include <linux/of.h>
 #include <linux/of_mdio.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/skbuff.h>
 #include <net/switchdev.h>
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 0fd156286d4d7..ba27bbc68f854 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -7,11 +7,10 @@
 #include <linux/etherdevice.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
-#include <linux/of_address.h>
+#include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-#include <linux/of_platform.h>
-#include <linux/of_irq.h>
+#include <linux/platform_device.h>
 #include <linux/skbuff.h>
 #include <linux/phy.h>
 #include <linux/mii.h>
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
index 802ef81493e0f..e4bc18009d087 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
@@ -8,7 +8,9 @@
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/acpi.h>
+#include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/of_platform.h>
 #include "emac.h"
 #include "emac-mac.h"
 #include "emac-sgmii.h"
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index eaa50050aa0b7..19bb16daf4e7e 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -11,7 +11,6 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
-#include <linux/of_device.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
 #include <linux/acpi.h>
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 4a1b94e5a8ea9..bec723028e96c 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -35,7 +35,6 @@
 #include <linux/moduleparam.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/sched.h>
 #include <linux/skbuff.h>
diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c
index 26646cb6a20a6..ace99c62d03a8 100644
--- a/drivers/net/ethernet/qualcomm/qca_uart.c
+++ b/drivers/net/ethernet/qualcomm/qca_uart.c
@@ -32,7 +32,6 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/sched.h>
 #include <linux/serdev.h>
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 4d6b3b7d6abb3..7df9f9f8e1340 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -21,10 +21,9 @@
 #include <linux/module.h>
 #include <linux/net_tstamp.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 4e412ac0965a4..0ba7fb75d5893 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -12,11 +12,10 @@
 #include <linux/module.h>
 #include <linux/net_tstamp.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/phy/phy.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index d8ec729825be4..274ea16c0a1f7 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -19,8 +19,6 @@
 #include <linux/mdio-bitbang.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
 #include <linux/of_net.h>
 #include <linux/phy.h>
 #include <linux/cache.h>
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index c362bff3cb835..cb590db625e83 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -43,7 +43,6 @@
 #include <linux/smsc911x.h>
 #include <linux/device.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_gpio.h>
 #include <linux/of_net.h>
 #include <linux/acpi.h>
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 492c39c08af1d..4838d2383a43c 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -15,10 +15,11 @@
 #include <linux/mii.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
+#include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
-#include <linux/of_platform.h>
 #include <linux/phy.h>
+#include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index b5efd9c2eac78..74c10373cc399 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -14,7 +14,7 @@
 #include <linux/iopoll.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index b9378a63f0e87..92e06a96757ac 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -12,7 +12,6 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
index 8063ba1c3ce83..e22ef0d6bc73d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
@@ -11,7 +11,6 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index 4d877d75642d9..7580077383c0a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -7,8 +7,8 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_net.h>
+#include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/stmmac.h>
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 92b16048f91c0..0b159dc0d5f60 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -13,7 +13,7 @@
 #include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
index 42954020de2ce..f91753565d608 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
@@ -12,7 +12,6 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/mfd/syscon.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index a855018748011..5b3df27035ec9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -3,7 +3,6 @@
 
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/platform_device.h>
 #include <linux/phy.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index d81591b470a28..35789cb549f72 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -14,8 +14,8 @@
 #include <linux/of_net.h>
 #include <linux/gpio.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/of_gpio.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 #include <linux/delay.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
index d3a39d2fb3a9d..b1c5f2527c0d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
@@ -7,8 +7,10 @@
  *
  */
 
+#include <linux/mod_devicetable.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/mfd/syscon.h>
-#include <linux/of_device.h>
 #include <linux/regmap.h>
 
 #include "stmmac_platform.h"
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index dcbb17c4f07ad..ef03e46694918 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -17,7 +17,6 @@
 #include <linux/regmap.h>
 #include <linux/clk.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_net.h>
 
 #include "stmmac_platform.h"
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
index bdb4de59a6727..3a09085819dc5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
@@ -11,7 +11,6 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index b607279e8cbd7..c23420863a8d3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -11,9 +11,10 @@
 #include <linux/mdio-mux.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
+#include <linux/of_platform.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
index 99e2e5a5cd60e..2bc6ef1eca1fe 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/platform_device.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/module.h>
 #include <linux/stmmac.h>
 #include <linux/clk.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
index acbb284be1741..a8731ce0fff09 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
@@ -6,7 +6,8 @@
  */
 
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/of_net.h>
 #include <linux/stmmac.h>
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 23d53ea04b24d..be8e79c7aa349 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -15,7 +15,6 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
-#include <linux/of_device.h>
 #include <linux/of_mdio.h>
 
 #include "stmmac.h"
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 7a2e767762974..011d74087f860 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -31,7 +31,7 @@
 #include <linux/slab.h>
 
 #include <linux/io.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 
 #include "niu.h"
 
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index 34b94153bf0ce..cc34d92d2e3da 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -25,7 +25,7 @@
 #include <linux/bitops.h>
 #include <linux/dma-mapping.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
 #include <linux/gfp.h>
 
 #include <asm/auxio.h>
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index 4154e68639ace..9bd1df8308d24 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -40,6 +40,7 @@
 #include <linux/bitops.h>
 #include <linux/mm.h>
 #include <linux/gfp.h>
+#include <linux/of.h>
 
 #include <asm/io.h>
 #include <asm/byteorder.h>
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index b93613cd19947..b983b9c23be68 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -32,9 +32,10 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
-#include <linux/of_device.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/pci.h>
+#include <linux/platform_device.h>
 #include <linux/random.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c
index 6418fcc3139f4..b37360f449726 100644
--- a/drivers/net/ethernet/sun/sunqe.c
+++ b/drivers/net/ethernet/sun/sunqe.c
@@ -27,8 +27,8 @@
 #include <linux/bitops.h>
 #include <linux/dma-mapping.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/pgtable.h>
+#include <linux/platform_device.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index bebcfd5e6b579..bea6fc0f324ce 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -19,6 +19,7 @@
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/of_device.h>
+#include <linux/of_platform.h>
 #include <linux/phylink.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/ethernet/ti/cpsw-common.c b/drivers/net/ethernet/ti/cpsw-common.c
index bfa81bbfce3f2..26dc906eae90b 100644
--- a/drivers/net/ethernet/ti/cpsw-common.c
+++ b/drivers/net/ethernet/ti/cpsw-common.c
@@ -3,7 +3,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/regmap.h>
 #include <linux/mfd/syscon.h>
 
diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c
index 25e707d7b87ce..4edb7963f856f 100644
--- a/drivers/net/ethernet/ti/cpsw-phy-sel.c
+++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c
@@ -12,7 +12,6 @@
 #include <linux/netdevice.h>
 #include <linux/phy.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 
 #include "cpsw.h"
 
diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index 23169e36a3d4c..89b6d23e9937d 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -23,7 +23,6 @@
 #include <linux/pm_runtime.h>
 #include <linux/davinci_emac.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_mdio.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/mdio-bitbang.h>
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index d716e6fe26e1c..3e09e50364907 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -94,7 +94,7 @@ static const int multicast_filter_limit = 32;
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/pci.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 86f7843b4591c..731f689412e65 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -57,8 +57,8 @@
 #include <linux/if.h>
 #include <linux/uaccess.h>
 #include <linux/proc_fs.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/inetdevice.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h
index 6668d1b760d8d..90d122d5475cf 100644
--- a/drivers/net/ethernet/xilinx/ll_temac.h
+++ b/drivers/net/ethernet/xilinx/ll_temac.h
@@ -5,6 +5,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/spinlock.h>
 
 #ifdef CONFIG_PPC_DCR
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index e0ac1bcd9925c..0bf9cdee1df2a 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -35,12 +35,10 @@
 #include <linux/netdevice.h>
 #include <linux/if_ether.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-#include <linux/of_platform.h>
-#include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
 #include <linux/tcp.h>      /* needed for sizeof(tcphdr) */
diff --git a/drivers/net/ethernet/xilinx/ll_temac_mdio.c b/drivers/net/ethernet/xilinx/ll_temac_mdio.c
index 2371c072b53f3..07a9fb49eda1a 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_mdio.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_mdio.c
@@ -10,8 +10,8 @@
 #include <linux/mutex.h>
 #include <linux/phy.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/of_mdio.h>
 #include <linux/platform_data/xilinx-ll-temac.h>
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 8e32dc50a4080..b7ec4dafae90c 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -27,11 +27,12 @@
 #include <linux/etherdevice.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
+#include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-#include <linux/of_platform.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <linux/skbuff.h>
 #include <linux/math64.h>
 #include <linux/phy.h>
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index ad2c30d9a4824..b358ecc672278 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/platform_device.h>
 #include <linux/uaccess.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
@@ -15,9 +16,8 @@
 #include <linux/ethtool.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
-#include <linux/of_platform.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/phy.h>
diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index f9b10e84de067..aebb19f1b3a41 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -57,7 +57,6 @@
 #include <linux/io.h>
 #include <linux/kfifo.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_gpio.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c
index 6a2f2fc2f501e..da853353a5c72 100644
--- a/drivers/net/ipa/ipa_main.c
+++ b/drivers/net/ipa/ipa_main.c
@@ -13,8 +13,8 @@
 #include <linux/firmware.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/firmware/qcom/qcom_scm.h>
 #include <linux/soc/qcom/mdt_loader.h>
diff --git a/net/core/of_net.c b/net/core/of_net.c
index 55d3fe2292694..93ea425b9248a 100644
--- a/net/core/of_net.c
+++ b/net/core/of_net.c
@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/of_net.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/phy.h>
 #include <linux/export.h>
 #include <linux/device.h>
-- 
GitLab


From 8c07fb0d647772018e0562fc4e920e081efb4c80 Mon Sep 17 00:00:00 2001
From: John Watts <contact@jookia.org>
Date: Sat, 22 Jul 2023 08:15:50 +1000
Subject: [PATCH 0573/1806] dt-bindings: net: can: Add support for Allwinner D1
 CAN controller

The Allwinner D1 has two CAN controllers, both a variant of the R40
controller. Unfortunately the registers for the D1 controllers are
moved around enough to be incompatible and require a new compatible.

Introduce the "allwinner,sun20i-d1-can" compatible to support this.

Signed-off-by: John Watts <contact@jookia.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/all/20230721221552.1973203-3-contact@jookia.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../bindings/net/can/allwinner,sun4i-a10-can.yaml           | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/can/allwinner,sun4i-a10-can.yaml b/Documentation/devicetree/bindings/net/can/allwinner,sun4i-a10-can.yaml
index 9c494957a07aa..e42ea28d6ab42 100644
--- a/Documentation/devicetree/bindings/net/can/allwinner,sun4i-a10-can.yaml
+++ b/Documentation/devicetree/bindings/net/can/allwinner,sun4i-a10-can.yaml
@@ -21,6 +21,7 @@ properties:
           - const: allwinner,sun4i-a10-can
       - const: allwinner,sun4i-a10-can
       - const: allwinner,sun8i-r40-can
+      - const: allwinner,sun20i-d1-can
 
   reg:
     maxItems: 1
@@ -37,8 +38,9 @@ properties:
 if:
   properties:
     compatible:
-      contains:
-        const: allwinner,sun8i-r40-can
+      enum:
+        - allwinner,sun8i-r40-can
+        - allwinner,sun20i-d1-can
 
 then:
   required:
-- 
GitLab


From 6ea1ad888f5900953a21853e709fa499fdfcb317 Mon Sep 17 00:00:00 2001
From: John Watts <contact@jookia.org>
Date: Sat, 22 Jul 2023 08:15:51 +1000
Subject: [PATCH 0574/1806] riscv: dts: allwinner: d1: Add CAN controller nodes

The Allwinner D1, T113 provide two CAN controllers that are variants
of the R40 controller.

I have tested support for these controllers on two boards:

- A Lichee Panel RV 86 Panel running a D1 chip
- A Mango Pi MQ Dual running a T113-s3 chip

Both of these fully support both CAN controllers.

Signed-off-by: John Watts <contact@jookia.org>
Link: https://lore.kernel.org/all/20230721221552.1973203-4-contact@jookia.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../boot/dts/allwinner/sunxi-d1s-t113.dtsi    | 30 +++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi b/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi
index 1bb1e5cae6021..4086c0cc0f9da 100644
--- a/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi
+++ b/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi
@@ -131,6 +131,18 @@
 				pins = "PB6", "PB7";
 				function = "uart3";
 			};
+
+			/omit-if-no-ref/
+			can0_pins: can0-pins {
+				pins = "PB2", "PB3";
+				function = "can0";
+			};
+
+			/omit-if-no-ref/
+			can1_pins: can1-pins {
+				pins = "PB4", "PB5";
+				function = "can1";
+			};
 		};
 
 		ccu: clock-controller@2001000 {
@@ -879,5 +891,23 @@
 			clock-names = "bus", "hosc", "ahb";
 			#clock-cells = <1>;
 		};
+
+		can0: can@2504000 {
+			compatible = "allwinner,sun20i-d1-can";
+			reg = <0x02504000 0x400>;
+			interrupts = <SOC_PERIPHERAL_IRQ(21) IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_CAN0>;
+			resets = <&ccu RST_BUS_CAN0>;
+			status = "disabled";
+		};
+
+		can1: can@2504400 {
+			compatible = "allwinner,sun20i-d1-can";
+			reg = <0x02504400 0x400>;
+			interrupts = <SOC_PERIPHERAL_IRQ(22) IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_CAN1>;
+			resets = <&ccu RST_BUS_CAN1>;
+			status = "disabled";
+		};
 	};
 };
-- 
GitLab


From 8cda0c6dfd42ee6f2586e7dffb553aaf1fcb62ca Mon Sep 17 00:00:00 2001
From: John Watts <contact@jookia.org>
Date: Sat, 22 Jul 2023 08:15:52 +1000
Subject: [PATCH 0575/1806] can: sun4i_can: Add acceptance register quirk

The Allwinner D1's CAN controllers have the ACPC and ACPM registers
moved down. Compensate for this by adding an offset quirk for the
acceptance registers.

Signed-off-by: John Watts <contact@jookia.org>
Link: https://lore.kernel.org/all/20230721221552.1973203-5-contact@jookia.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/sun4i_can.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index 0827830bbf28c..1f90fe6dbb8bb 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -205,9 +205,11 @@
  * struct sun4ican_quirks - Differences between SoC variants.
  *
  * @has_reset: SoC needs reset deasserted.
+ * @acp_offset: Offset of ACPC and ACPM registers
  */
 struct sun4ican_quirks {
 	bool has_reset;
+	int acp_offset;
 };
 
 struct sun4ican_priv {
@@ -216,6 +218,7 @@ struct sun4ican_priv {
 	struct clk *clk;
 	struct reset_control *reset;
 	spinlock_t cmdreg_lock;	/* lock for concurrent cmd register writes */
+	int acp_offset;
 };
 
 static const struct can_bittiming_const sun4ican_bittiming_const = {
@@ -338,8 +341,8 @@ static int sun4i_can_start(struct net_device *dev)
 	}
 
 	/* set filters - we accept all */
-	writel(0x00000000, priv->base + SUN4I_REG_ACPC_ADDR);
-	writel(0xFFFFFFFF, priv->base + SUN4I_REG_ACPM_ADDR);
+	writel(0x00000000, priv->base + SUN4I_REG_ACPC_ADDR + priv->acp_offset);
+	writel(0xFFFFFFFF, priv->base + SUN4I_REG_ACPM_ADDR + priv->acp_offset);
 
 	/* clear error counters and error code capture */
 	writel(0, priv->base + SUN4I_REG_ERRC_ADDR);
@@ -768,10 +771,12 @@ static const struct ethtool_ops sun4ican_ethtool_ops = {
 
 static const struct sun4ican_quirks sun4ican_quirks_a10 = {
 	.has_reset = false,
+	.acp_offset = 0,
 };
 
 static const struct sun4ican_quirks sun4ican_quirks_r40 = {
 	.has_reset = true,
+	.acp_offset = 0,
 };
 
 static const struct of_device_id sun4ican_of_match[] = {
@@ -870,6 +875,7 @@ static int sun4ican_probe(struct platform_device *pdev)
 	priv->base = addr;
 	priv->clk = clk;
 	priv->reset = reset;
+	priv->acp_offset = quirks->acp_offset;
 	spin_lock_init(&priv->cmdreg_lock);
 
 	platform_set_drvdata(pdev, dev);
-- 
GitLab


From e58ee933c27a2ddd587752788dd843817008313f Mon Sep 17 00:00:00 2001
From: Gerhard Uttenthaler <uttenthaler@ems-wuensche.com>
Date: Thu, 20 Jul 2023 16:40:32 +0200
Subject: [PATCH 0576/1806] MAINTAINERS: Add myself as maintainer of the
 ems_pci.c driver

At the suggestion of Marc Kleine-Budde [1], I add myself as maintainer
of the ems_pci.c driver.

[1] https://lore.kernel.org/all/20230720-purplish-quizzical-247024e66671-mkl@pengutronix.de

Signed-off-by: Gerhard Uttenthaler <uttenthaler@ems-wuensche.com>
Link: https://lore.kernel.org/all/20230720144032.28960-1-uttenthaler@ems-wuensche.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 MAINTAINERS | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 24eb7ed6211f2..c4f95a9d03b9e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7606,6 +7606,13 @@ L:	linux-mmc@vger.kernel.org
 S:	Supported
 F:	drivers/mmc/host/cqhci*
 
+EMS CPC-PCI CAN DRIVER
+M:	Gerhard Uttenthaler <uttenthaler@ems-wuensche.com>
+M:	support@ems-wuensche.com
+L:	linux-can@vger.kernel.org
+S:	Maintained
+F:	drivers/net/can/sja1000/ems_pci.c
+
 EMULEX 10Gbps iSCSI - OneConnect DRIVER
 M:	Ketan Mukadam <ketan.mukadam@broadcom.com>
 L:	linux-scsi@vger.kernel.org
-- 
GitLab


From 8abb95250ae6af2d51993da8fcae18da2ce24cc4 Mon Sep 17 00:00:00 2001
From: John Watts <contact@jookia.org>
Date: Sat, 22 Jul 2023 08:15:53 +1000
Subject: [PATCH 0577/1806] can: sun4i_can: Add support for the Allwinner D1

The controllers present in the D1 are extremely similar to the R40
and require the same reset quirks, but An extra quirk is needed to support
receiving packets.

Signed-off-by: John Watts <contact@jookia.org>
Link: https://lore.kernel.org/all/20230721221552.1973203-6-contact@jookia.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/Kconfig     |  4 ++--
 drivers/net/can/sun4i_can.c | 12 +++++++++++-
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 18e4a6e94ba93..649453a3c8588 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -190,10 +190,10 @@ config CAN_SLCAN
 
 config CAN_SUN4I
 	tristate "Allwinner A10 CAN controller"
-	depends on MACH_SUN4I || MACH_SUN7I || COMPILE_TEST
+	depends on MACH_SUN4I || MACH_SUN7I || RISCV || COMPILE_TEST
 	help
 	  Say Y here if you want to use CAN controller found on Allwinner
-	  A10/A20 SoCs.
+	  A10/A20/D1 SoCs.
 
 	  To compile this driver as a module, choose M here: the module will
 	  be called sun4i_can.
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index 1f90fe6dbb8bb..c508a328e38d4 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -91,6 +91,8 @@
 #define SUN4I_REG_BUF12_ADDR	0x0070	/* CAN Tx/Rx Buffer 12 */
 #define SUN4I_REG_ACPC_ADDR	0x0040	/* CAN Acceptance Code 0 */
 #define SUN4I_REG_ACPM_ADDR	0x0044	/* CAN Acceptance Mask 0 */
+#define SUN4I_REG_ACPC_ADDR_D1	0x0028	/* CAN Acceptance Code 0 on the D1 */
+#define SUN4I_REG_ACPM_ADDR_D1	0x002C	/* CAN Acceptance Mask 0 on the D1 */
 #define SUN4I_REG_RBUF_RBACK_START_ADDR	0x0180	/* CAN transmit buffer start */
 #define SUN4I_REG_RBUF_RBACK_END_ADDR	0x01b0	/* CAN transmit buffer end */
 
@@ -779,6 +781,11 @@ static const struct sun4ican_quirks sun4ican_quirks_r40 = {
 	.acp_offset = 0,
 };
 
+static const struct sun4ican_quirks sun4ican_quirks_d1 = {
+	.has_reset = true,
+	.acp_offset = (SUN4I_REG_ACPC_ADDR_D1 - SUN4I_REG_ACPC_ADDR),
+};
+
 static const struct of_device_id sun4ican_of_match[] = {
 	{
 		.compatible = "allwinner,sun4i-a10-can",
@@ -789,6 +796,9 @@ static const struct of_device_id sun4ican_of_match[] = {
 	}, {
 		.compatible = "allwinner,sun8i-r40-can",
 		.data = &sun4ican_quirks_r40
+	}, {
+		.compatible = "allwinner,sun20i-d1-can",
+		.data = &sun4ican_quirks_d1
 	}, {
 		/* sentinel */
 	},
@@ -913,4 +923,4 @@ module_platform_driver(sun4i_can_driver);
 MODULE_AUTHOR("Peter Chen <xingkongcp@gmail.com>");
 MODULE_AUTHOR("Gerhard Bertelsmann <info@gerhard-bertelsmann.de>");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_DESCRIPTION("CAN driver for Allwinner SoCs (A10/A20)");
+MODULE_DESCRIPTION("CAN driver for Allwinner SoCs (A10/A20/D1)");
-- 
GitLab


From 74dedbd74d2bfac24b44acb268ea77faa9fc9c41 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Fri, 21 Jul 2023 20:07:58 +0200
Subject: [PATCH 0578/1806] can: peak_usb: remove unused/legacy
 peak_usb_netif_rx() function

Remove unused/legacy peak_usb_netif_rx() function (not longer used
since commit 28e0a70cede3 ("can: peak_usb: CANFD: store 64-bits hw
timestamps").

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Link: https://lore.kernel.org/all/20230721180758.26199-1-ps.report@gmx.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/peak_usb/pcan_usb_core.c | 13 -------------
 drivers/net/can/usb/peak_usb/pcan_usb_core.h |  2 --
 2 files changed, 15 deletions(-)

diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index d881e1d301832..24ad9f593a773 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -214,19 +214,6 @@ void peak_usb_get_ts_time(struct peak_time_ref *time_ref, u32 ts, ktime_t *time)
 	}
 }
 
-/*
- * post received skb after having set any hw timestamp
- */
-int peak_usb_netif_rx(struct sk_buff *skb,
-		      struct peak_time_ref *time_ref, u32 ts_low)
-{
-	struct skb_shared_hwtstamps *hwts = skb_hwtstamps(skb);
-
-	peak_usb_get_ts_time(time_ref, ts_low, &hwts->hwtstamp);
-
-	return netif_rx(skb);
-}
-
 /* post received skb with native 64-bit hw timestamp */
 int peak_usb_netif_rx_64(struct sk_buff *skb, u32 ts_low, u32 ts_high)
 {
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h
index 980e315186cfd..f6cf84bb718f0 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h
@@ -142,8 +142,6 @@ void peak_usb_init_time_ref(struct peak_time_ref *time_ref,
 void peak_usb_update_ts_now(struct peak_time_ref *time_ref, u32 ts_now);
 void peak_usb_set_ts_now(struct peak_time_ref *time_ref, u32 ts_now);
 void peak_usb_get_ts_time(struct peak_time_ref *time_ref, u32 ts, ktime_t *tv);
-int peak_usb_netif_rx(struct sk_buff *skb,
-		      struct peak_time_ref *time_ref, u32 ts_low);
 int peak_usb_netif_rx_64(struct sk_buff *skb, u32 ts_low, u32 ts_high);
 void peak_usb_async_complete(struct urb *urb);
 void peak_usb_restart_complete(struct peak_usb_device *dev);
-- 
GitLab


From 07382e6b68a742f18d57a27fec5fd0c2b0b61b40 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 24 Jul 2023 15:18:40 -0600
Subject: [PATCH 0579/1806] can: Explicitly include correct DT includes, part 2

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/all/20230724211841.805053-1-robh@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/bxcan.c                    | 1 -
 drivers/net/can/ifi_canfd/ifi_canfd.c      | 1 -
 drivers/net/can/m_can/m_can.c              | 1 -
 drivers/net/can/m_can/m_can.h              | 1 -
 drivers/net/can/rcar/rcar_canfd.c          | 1 -
 drivers/net/can/sja1000/sja1000_platform.c | 1 -
 drivers/net/can/sun4i_can.c                | 1 -
 drivers/net/can/ti_hecc.c                  | 1 -
 8 files changed, 8 deletions(-)

diff --git a/drivers/net/can/bxcan.c b/drivers/net/can/bxcan.c
index 39de7164bc4e1..49cf9682b9254 100644
--- a/drivers/net/can/bxcan.c
+++ b/drivers/net/can/bxcan.c
@@ -23,7 +23,6 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 
diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c
index 1d6642c94f2f5..72307297d75e4 100644
--- a/drivers/net/can/ifi_canfd/ifi_canfd.c
+++ b/drivers/net/can/ifi_canfd/ifi_canfd.c
@@ -20,7 +20,6 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 
 #include <linux/can/dev.h>
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 13fd84b2e2dde..a6263a617ac93 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -19,7 +19,6 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/phy/phy.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h
index 2ac18ac867a45..c543928c756fc 100644
--- a/drivers/net/can/m_can/m_can.h
+++ b/drivers/net/can/m_can/m_can.h
@@ -23,7 +23,6 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/phy/phy.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index e4d7489134399..b828427187353 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -34,7 +34,6 @@
 #include <linux/moduleparam.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c
index 4e59952c66d49..33f0e46ab1c2f 100644
--- a/drivers/net/can/sja1000/sja1000_platform.c
+++ b/drivers/net/can/sja1000/sja1000_platform.c
@@ -17,7 +17,6 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 
 #include "sja1000.h"
 
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index c508a328e38d4..ab8d017846869 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -59,7 +59,6 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 54284661992eb..a8243acde92d7 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -21,7 +21,6 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/regulator/consumer.h>
 
 #include <linux/can/dev.h>
-- 
GitLab


From f1a14714bf48f87fa8e774f415ea9815daf3750d Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Tue, 18 Jul 2023 11:11:22 +0200
Subject: [PATCH 0580/1806] can: gs_usb: remove leading space from goto labels

Remove leading spaces from goto labels in accordance with the kernel
encoding style.

Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-1-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index bd9eb066ecf15..c604377138fd0 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -645,7 +645,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 		netif_rx(skb);
 	}
 
- resubmit_urb:
+resubmit_urb:
 	usb_fill_bulk_urb(urb, usbcan->udev,
 			  usb_rcvbulkpipe(usbcan->udev, GS_USB_ENDPOINT_IN),
 			  hf, dev->parent->hf_size_rx,
@@ -655,7 +655,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 
 	/* USB failure take down all interfaces */
 	if (rc == -ENODEV) {
- device_detach:
+device_detach:
 		for (rc = 0; rc < GS_MAX_INTF; rc++) {
 			if (usbcan->canch[rc])
 				netif_device_detach(usbcan->canch[rc]->netdev);
@@ -818,12 +818,12 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb,
 
 	return NETDEV_TX_OK;
 
- badidx:
+badidx:
 	kfree(hf);
- nomem_hf:
+nomem_hf:
 	usb_free_urb(urb);
 
- nomem_urb:
+nomem_urb:
 	gs_free_tx_context(txc);
 	dev_kfree_skb(skb);
 	stats->tx_dropped++;
@@ -1354,7 +1354,7 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 
 	return dev;
 
- out_free_candev:
+out_free_candev:
 	free_candev(dev->netdev);
 	return ERR_PTR(rc);
 }
-- 
GitLab


From 5780148bedd6aa7e51d3a18cd70f5b9b6cefb79e Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 6 Jul 2023 13:08:43 +0200
Subject: [PATCH 0581/1806] can: gs_usb: gs_usb_probe(): align block comment

Indent block comment so that it aligns the * on each line.

Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-2-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index c604377138fd0..966e00ea768de 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -1443,8 +1443,8 @@ static int gs_usb_probe(struct usb_interface *intf,
 		dev->canch[i]->parent = dev;
 
 		/* set RX packet size based on FD and if hardware
-                * timestamps are supported.
-		*/
+		 * timestamps are supported.
+		 */
 		if (dev->canch[i]->can.ctrlmode_supported & CAN_CTRLMODE_FD) {
 			if (dev->canch[i]->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
 				hf_size_rx = struct_size(hf, canfd_ts, 1);
-- 
GitLab


From a2002f455c0e1f1c8802e7bdafe370d47d4328de Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 6 Jul 2023 13:04:45 +0200
Subject: [PATCH 0582/1806] can: gs_usb: gs_usb_set_timestamp(): remove return
 statements form void function

Remove the return statements from void gs_usb_set_timestamp()
function, as it's not generally useful.

Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-3-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 966e00ea768de..1e08d38b0f967 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -520,8 +520,6 @@ static void gs_usb_set_timestamp(struct gs_can *dev, struct sk_buff *skb,
 		timestamp = le32_to_cpu(hf->classic_can_ts->timestamp_us);
 
 	gs_usb_skb_set_timestamp(dev, skb, timestamp);
-
-	return;
 }
 
 static void gs_usb_receive_bulk_callback(struct urb *urb)
-- 
GitLab


From b6980ad3a90c73c95cab97e9a33129b8f53e2a5b Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 6 Jul 2023 16:16:33 +0200
Subject: [PATCH 0583/1806] can: gs_usb: uniformly use "parent" as variable
 name for struct gs_usb

To ease readability and maintainability uniformly use the variable
name "parent" for the struct gs_usb in the gs_usb driver.

Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-4-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 62 ++++++++++++++++++------------------
 1 file changed, 31 insertions(+), 31 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 1e08d38b0f967..441143ad740b3 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -524,7 +524,7 @@ static void gs_usb_set_timestamp(struct gs_can *dev, struct sk_buff *skb,
 
 static void gs_usb_receive_bulk_callback(struct urb *urb)
 {
-	struct gs_usb *usbcan = urb->context;
+	struct gs_usb *parent = urb->context;
 	struct gs_can *dev;
 	struct net_device *netdev;
 	int rc;
@@ -535,7 +535,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 	struct canfd_frame *cfd;
 	struct sk_buff *skb;
 
-	BUG_ON(!usbcan);
+	BUG_ON(!parent);
 
 	switch (urb->status) {
 	case 0: /* success */
@@ -552,7 +552,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 	if (hf->channel >= GS_MAX_INTF)
 		goto device_detach;
 
-	dev = usbcan->canch[hf->channel];
+	dev = parent->canch[hf->channel];
 
 	netdev = dev->netdev;
 	stats = &netdev->stats;
@@ -644,10 +644,10 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 	}
 
 resubmit_urb:
-	usb_fill_bulk_urb(urb, usbcan->udev,
-			  usb_rcvbulkpipe(usbcan->udev, GS_USB_ENDPOINT_IN),
+	usb_fill_bulk_urb(urb, parent->udev,
+			  usb_rcvbulkpipe(parent->udev, GS_USB_ENDPOINT_IN),
 			  hf, dev->parent->hf_size_rx,
-			  gs_usb_receive_bulk_callback, usbcan);
+			  gs_usb_receive_bulk_callback, parent);
 
 	rc = usb_submit_urb(urb, GFP_ATOMIC);
 
@@ -655,8 +655,8 @@ resubmit_urb:
 	if (rc == -ENODEV) {
 device_detach:
 		for (rc = 0; rc < GS_MAX_INTF; rc++) {
-			if (usbcan->canch[rc])
-				netif_device_detach(usbcan->canch[rc]->netdev);
+			if (parent->canch[rc])
+				netif_device_detach(parent->canch[rc]->netdev);
 		}
 	}
 }
@@ -1369,7 +1369,7 @@ static int gs_usb_probe(struct usb_interface *intf,
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
 	struct gs_host_frame *hf;
-	struct gs_usb *dev;
+	struct gs_usb *parent;
 	struct gs_host_config hconf = {
 		.byte_order = cpu_to_le32(0x0000beef),
 	};
@@ -1412,49 +1412,49 @@ static int gs_usb_probe(struct usb_interface *intf,
 		return -EINVAL;
 	}
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
+	parent = kzalloc(sizeof(*parent), GFP_KERNEL);
+	if (!parent)
 		return -ENOMEM;
 
-	init_usb_anchor(&dev->rx_submitted);
+	init_usb_anchor(&parent->rx_submitted);
 
-	usb_set_intfdata(intf, dev);
-	dev->udev = udev;
+	usb_set_intfdata(intf, parent);
+	parent->udev = udev;
 
 	for (i = 0; i < icount; i++) {
 		unsigned int hf_size_rx = 0;
 
-		dev->canch[i] = gs_make_candev(i, intf, &dconf);
-		if (IS_ERR_OR_NULL(dev->canch[i])) {
+		parent->canch[i] = gs_make_candev(i, intf, &dconf);
+		if (IS_ERR_OR_NULL(parent->canch[i])) {
 			/* save error code to return later */
-			rc = PTR_ERR(dev->canch[i]);
+			rc = PTR_ERR(parent->canch[i]);
 
 			/* on failure destroy previously created candevs */
 			icount = i;
 			for (i = 0; i < icount; i++)
-				gs_destroy_candev(dev->canch[i]);
+				gs_destroy_candev(parent->canch[i]);
 
-			usb_kill_anchored_urbs(&dev->rx_submitted);
-			kfree(dev);
+			usb_kill_anchored_urbs(&parent->rx_submitted);
+			kfree(parent);
 			return rc;
 		}
-		dev->canch[i]->parent = dev;
+		parent->canch[i]->parent = parent;
 
 		/* set RX packet size based on FD and if hardware
 		 * timestamps are supported.
 		 */
-		if (dev->canch[i]->can.ctrlmode_supported & CAN_CTRLMODE_FD) {
-			if (dev->canch[i]->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
+		if (parent->canch[i]->can.ctrlmode_supported & CAN_CTRLMODE_FD) {
+			if (parent->canch[i]->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
 				hf_size_rx = struct_size(hf, canfd_ts, 1);
 			else
 				hf_size_rx = struct_size(hf, canfd, 1);
 		} else {
-			if (dev->canch[i]->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
+			if (parent->canch[i]->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
 				hf_size_rx = struct_size(hf, classic_can_ts, 1);
 			else
 				hf_size_rx = struct_size(hf, classic_can, 1);
 		}
-		dev->hf_size_rx = max(dev->hf_size_rx, hf_size_rx);
+		parent->hf_size_rx = max(parent->hf_size_rx, hf_size_rx);
 	}
 
 	return 0;
@@ -1462,22 +1462,22 @@ static int gs_usb_probe(struct usb_interface *intf,
 
 static void gs_usb_disconnect(struct usb_interface *intf)
 {
-	struct gs_usb *dev = usb_get_intfdata(intf);
+	struct gs_usb *parent = usb_get_intfdata(intf);
 	unsigned int i;
 
 	usb_set_intfdata(intf, NULL);
 
-	if (!dev) {
+	if (!parent) {
 		dev_err(&intf->dev, "Disconnect (nodata)\n");
 		return;
 	}
 
 	for (i = 0; i < GS_MAX_INTF; i++)
-		if (dev->canch[i])
-			gs_destroy_candev(dev->canch[i]);
+		if (parent->canch[i])
+			gs_destroy_candev(parent->canch[i]);
 
-	usb_kill_anchored_urbs(&dev->rx_submitted);
-	kfree(dev);
+	usb_kill_anchored_urbs(&parent->rx_submitted);
+	kfree(parent);
 }
 
 static const struct usb_device_id gs_usb_table[] = {
-- 
GitLab


From fcb880ef2f55b9d50baf42c7efa5c45a9baabea9 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 3 Jul 2023 20:37:20 +0200
Subject: [PATCH 0584/1806] can: gs_usb: gs_usb_receive_bulk_callback(): make
 use of netdev

Make use the previously assigned variable netdev instead of using
dev->netdev.

Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-5-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 441143ad740b3..04cbe949c2906 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -565,7 +565,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 
 	if (hf->echo_id == -1) { /* normal rx */
 		if (hf->flags & GS_CAN_FLAG_FD) {
-			skb = alloc_canfd_skb(dev->netdev, &cfd);
+			skb = alloc_canfd_skb(netdev, &cfd);
 			if (!skb)
 				return;
 
@@ -578,7 +578,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 
 			memcpy(cfd->data, hf->canfd->data, cfd->len);
 		} else {
-			skb = alloc_can_skb(dev->netdev, &cf);
+			skb = alloc_can_skb(netdev, &cf);
 			if (!skb)
 				return;
 
-- 
GitLab


From 55ad95d944251bb53df958e408964be2499603fd Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 3 Jul 2023 20:39:19 +0200
Subject: [PATCH 0585/1806] can: gs_usb: gs_usb_receive_bulk_callback(): make
 use of stats

Make use the previously assigned variable stats instead of using
netdev->stats.

Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-6-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 04cbe949c2906..0d0a3405ba198 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -594,8 +594,8 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 
 		gs_usb_set_timestamp(dev, skb, hf);
 
-		netdev->stats.rx_packets++;
-		netdev->stats.rx_bytes += hf->can_dlc;
+		stats->rx_packets++;
+		stats->rx_bytes += hf->can_dlc;
 
 		netif_rx(skb);
 	} else { /* echo_id == hf->echo_id */
@@ -619,9 +619,9 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 		skb = dev->can.echo_skb[hf->echo_id];
 		gs_usb_set_timestamp(dev, skb, hf);
 
-		netdev->stats.tx_packets++;
-		netdev->stats.tx_bytes += can_get_echo_skb(netdev, hf->echo_id,
-							   NULL);
+		stats->tx_packets++;
+		stats->tx_bytes += can_get_echo_skb(netdev, hf->echo_id,
+						    NULL);
 
 		gs_free_tx_context(txc);
 
-- 
GitLab


From 6c8bc15f02b85bc8f47074110d8fd8caf7a1e42d Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Tue, 4 Jul 2023 11:23:37 +0200
Subject: [PATCH 0586/1806] can: gs_usb: gs_usb_receive_bulk_callback(): count
 RX overflow errors also in case of OOM

In case of an RX overflow error from the CAN controller and an OOM
where no skb can be allocated, the error counters are not incremented.

Fix this by first incrementing the error counters and then allocate
the skb.

Fixes: d08e973a77d1 ("can: gs_usb: Added support for the GS_USB CAN devices")
Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-7-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 0d0a3405ba198..e302d7d568aa4 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -631,6 +631,9 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 	}
 
 	if (hf->flags & GS_CAN_FLAG_OVERFLOW) {
+		stats->rx_over_errors++;
+		stats->rx_errors++;
+
 		skb = alloc_can_err_skb(netdev, &cf);
 		if (!skb)
 			goto resubmit_urb;
@@ -638,8 +641,6 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 		cf->can_id |= CAN_ERR_CRTL;
 		cf->len = CAN_ERR_DLC;
 		cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
-		stats->rx_over_errors++;
-		stats->rx_errors++;
 		netif_rx(skb);
 	}
 
-- 
GitLab


From 1494ffe4cbe0f97af9c57a4cc37131c8efbe79fc Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 12 Jul 2023 15:49:43 +0200
Subject: [PATCH 0587/1806] can: gs_usb: gs_can_start_xmit(), gs_can_open():
 clean up printouts in error path

Remove unnecessary "out of memory" message from the error path of
gs_can_start_xmit() and gs_can_open().

Convert the printout in case of a failing usb_submit_urb() in
gs_can_open() from numbers to human readable error codes.

Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-8-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index e302d7d568aa4..a5cab6a070024 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -741,10 +741,8 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb,
 		goto nomem_urb;
 
 	hf = kmalloc(dev->hf_size_tx, GFP_ATOMIC);
-	if (!hf) {
-		netdev_err(netdev, "No memory left for USB buffer\n");
+	if (!hf)
 		goto nomem_hf;
-	}
 
 	idx = txc->echo_id;
 
@@ -877,8 +875,6 @@ static int gs_can_open(struct net_device *netdev)
 			buf = kmalloc(dev->parent->hf_size_rx,
 				      GFP_KERNEL);
 			if (!buf) {
-				netdev_err(netdev,
-					   "No memory left for USB buffer\n");
 				rc = -ENOMEM;
 				goto out_usb_free_urb;
 			}
@@ -901,7 +897,8 @@ static int gs_can_open(struct net_device *netdev)
 					netif_device_detach(dev->netdev);
 
 				netdev_err(netdev,
-					   "usb_submit failed (err=%d)\n", rc);
+					   "usb_submit_urb() failed, error %pe\n",
+					   ERR_PTR(rc));
 
 				goto out_usb_unanchor_urb;
 			}
-- 
GitLab


From 5c6c313acdfc3455b20ac1dc9655aa4afcf51ab1 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 8 Feb 2023 10:26:33 +0100
Subject: [PATCH 0588/1806] can: gs_usb: gs_can_close(): don't complain about
 failed device reset during ndo_stop

When the USB device is unplugged, gs_can_close() (which implements the
struct net_device_ops::ndo_stop callback) is called. In this function
an attempt is made to shut down the USB device with a USB control
message. For disconnected devices this will fail and a warning message
is printed.

Silence the driver by removing the printout of the error message if
the reset command fails.

Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-9-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index a5cab6a070024..7718f6a4367eb 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -1029,9 +1029,7 @@ static int gs_can_close(struct net_device *netdev)
 	dev->can.state = CAN_STATE_STOPPED;
 
 	/* reset the device */
-	rc = gs_cmd_reset(dev);
-	if (rc < 0)
-		netdev_warn(netdev, "Couldn't shutdown device (err=%d)", rc);
+	gs_cmd_reset(dev);
 
 	/* reset tx contexts */
 	for (rc = 0; rc < GS_MAX_TX_URBS; rc++) {
-- 
GitLab


From 5391e0cbae02cdf2df501f104c2c7dc0bceeec3d Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 6 Jul 2023 11:38:25 +0200
Subject: [PATCH 0589/1806] can: gs_usb: gs_destroy_candev(): remove not needed
 usb_kill_anchored_urbs()

In gs_destroy_candev(), the netdev is unregistered first, then all
anchored TX URBs (dev->tx_submitted) are disposed with
usb_kill_anchored_urbs().

The call to usb_kill_anchored_urbs() is not needed, as
unregister_candev() calls gs_can_close(), which already disposes the
TX URBS.

Remove not needed call to usb_kill_anchored_urbs() from
gs_destroy_candev().

Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-10-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 7718f6a4367eb..5a0017b985321 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -1356,7 +1356,6 @@ out_free_candev:
 static void gs_destroy_candev(struct gs_can *dev)
 {
 	unregister_candev(dev->netdev);
-	usb_kill_anchored_urbs(&dev->tx_submitted);
 	free_candev(dev->netdev);
 }
 
-- 
GitLab


From d4cfb83d566c56d062a73d94a9fc7ec258a437c2 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 6 Jul 2023 11:38:25 +0200
Subject: [PATCH 0590/1806] can: gs_usb: gs_usb_disconnect(): remove not needed
 usb_kill_anchored_urbs()

In gs_usb_disconnect(), all channels are destroyed first, then all
anchored RX URBs (parent->rx_submitted) are disposed with
usb_kill_anchored_urbs().

The call to usb_kill_anchored_urbs() is not needed, as
gs_destroy_candev() of the last active channel already disposes the RX
URBS.

Remove not needed call to usb_kill_anchored_urbs() from
gs_usb_disconnect().

Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-11-c3b9154ec605@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 5a0017b985321..6caf3974e0283 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -1471,7 +1471,6 @@ static void gs_usb_disconnect(struct usb_interface *intf)
 		if (parent->canch[i])
 			gs_destroy_candev(parent->canch[i]);
 
-	usb_kill_anchored_urbs(&parent->rx_submitted);
 	kfree(parent);
 }
 
-- 
GitLab


From 2e3df4a3b3178006d530f4c4d0e91f3d96cddb3c Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Fri, 2 Jun 2023 09:36:38 +0200
Subject: [PATCH 0591/1806] can: rx-offload: rename rx_offload_get_echo_skb()
 -> can_rx_offload_get_echo_skb_queue_timestamp()

Rename the rx_offload_get_echo_skb() function to
can_rx_offload_get_echo_skb_queue_timestamp(), since it inserts the
echo skb into the rx-offload queue sorted by timestamp.

This is a preparation for adding
can_rx_offload_get_echo_skb_queue_tail(), which adds the echo skb to
the end of the queue. This is intended for devices that do not support
timestamps.

Link: https://lore.kernel.org/all/20230718-gs_usb-rx-offload-v2-1-716e542d14d5@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev/rx-offload.c              | 9 +++++----
 drivers/net/can/flexcan/flexcan-core.c        | 4 ++--
 drivers/net/can/m_can/m_can.c                 | 8 ++++----
 drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c | 6 +++---
 drivers/net/can/ti_hecc.c                     | 4 ++--
 include/linux/can/rx-offload.h                | 6 +++---
 6 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/net/can/dev/rx-offload.c b/drivers/net/can/dev/rx-offload.c
index 161e45a7e8c11..6e87ad9083467 100644
--- a/drivers/net/can/dev/rx-offload.c
+++ b/drivers/net/can/dev/rx-offload.c
@@ -240,9 +240,10 @@ int can_rx_offload_queue_timestamp(struct can_rx_offload *offload,
 }
 EXPORT_SYMBOL_GPL(can_rx_offload_queue_timestamp);
 
-unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload,
-					 unsigned int idx, u32 timestamp,
-					 unsigned int *frame_len_ptr)
+unsigned int
+can_rx_offload_get_echo_skb_queue_timestamp(struct can_rx_offload *offload,
+					    unsigned int idx, u32 timestamp,
+					    unsigned int *frame_len_ptr)
 {
 	struct net_device *dev = offload->dev;
 	struct net_device_stats *stats = &dev->stats;
@@ -262,7 +263,7 @@ unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload,
 
 	return len;
 }
-EXPORT_SYMBOL_GPL(can_rx_offload_get_echo_skb);
+EXPORT_SYMBOL_GPL(can_rx_offload_get_echo_skb_queue_timestamp);
 
 int can_rx_offload_queue_tail(struct can_rx_offload *offload,
 			      struct sk_buff *skb)
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index ff0fc18baf133..48273d51f2711 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -1097,8 +1097,8 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 
 		handled = IRQ_HANDLED;
 		stats->tx_bytes +=
-			can_rx_offload_get_echo_skb(&priv->offload, 0,
-						    reg_ctrl << 16, NULL);
+			can_rx_offload_get_echo_skb_queue_timestamp(&priv->offload, 0,
+								    reg_ctrl << 16, NULL);
 		stats->tx_packets++;
 
 		/* after sending a RTR frame MB is in RX mode */
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index a6263a617ac93..d204703521d28 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1016,10 +1016,10 @@ static void m_can_tx_update_stats(struct m_can_classdev *cdev,
 
 	if (cdev->is_peripheral)
 		stats->tx_bytes +=
-			can_rx_offload_get_echo_skb(&cdev->offload,
-						    msg_mark,
-						    timestamp,
-						    NULL);
+			can_rx_offload_get_echo_skb_queue_timestamp(&cdev->offload,
+								    msg_mark,
+								    timestamp,
+								    NULL);
 	else
 		stats->tx_bytes += can_get_echo_skb(dev, msg_mark, NULL);
 
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
index 237617b0c125f..e5bd57b65aafe 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
@@ -111,9 +111,9 @@ mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
 	if (skb)
 		mcp251xfd_skb_set_timestamp(priv, skb, hw_tef_obj->ts);
 	stats->tx_bytes +=
-		can_rx_offload_get_echo_skb(&priv->offload,
-					    tef_tail, hw_tef_obj->ts,
-					    frame_len_ptr);
+		can_rx_offload_get_echo_skb_queue_timestamp(&priv->offload,
+							    tef_tail, hw_tef_obj->ts,
+							    frame_len_ptr);
 	stats->tx_packets++;
 	priv->tef->tail++;
 
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index a8243acde92d7..5aab440074c69 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -747,8 +747,8 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 			spin_unlock_irqrestore(&priv->mbx_lock, flags);
 			stamp = hecc_read_stamp(priv, mbxno);
 			stats->tx_bytes +=
-				can_rx_offload_get_echo_skb(&priv->offload,
-							    mbxno, stamp, NULL);
+				can_rx_offload_get_echo_skb_queue_timestamp(&priv->offload,
+									    mbxno, stamp, NULL);
 			stats->tx_packets++;
 			--priv->tx_tail;
 		}
diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h
index c205c51d79c90..e3b4199732c6a 100644
--- a/include/linux/can/rx-offload.h
+++ b/include/linux/can/rx-offload.h
@@ -44,9 +44,9 @@ int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload,
 int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload);
 int can_rx_offload_queue_timestamp(struct can_rx_offload *offload,
 				   struct sk_buff *skb, u32 timestamp);
-unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload,
-					 unsigned int idx, u32 timestamp,
-					 unsigned int *frame_len_ptr);
+unsigned int can_rx_offload_get_echo_skb_queue_timestamp(struct can_rx_offload *offload,
+							 unsigned int idx, u32 timestamp,
+							 unsigned int *frame_len_ptr);
 int can_rx_offload_queue_tail(struct can_rx_offload *offload,
 			      struct sk_buff *skb);
 void can_rx_offload_irq_finish(struct can_rx_offload *offload);
-- 
GitLab


From 8e0e2950c9ef48f7f40a7175048744ec2390b16e Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 3 Jul 2023 18:18:19 +0200
Subject: [PATCH 0592/1806] can: rx-offload: add
 can_rx_offload_get_echo_skb_queue_tail()

Add can_rx_offload_get_echo_skb_queue_tail(). This function addds the
echo skb at the end of rx-offload the queue. This is intended for
devices without timestamp support.

Link: https://lore.kernel.org/all/20230718-gs_usb-rx-offload-v2-2-716e542d14d5@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev/rx-offload.c | 27 ++++++++++++++++++++++++++-
 include/linux/can/rx-offload.h   |  5 ++++-
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/dev/rx-offload.c b/drivers/net/can/dev/rx-offload.c
index 6e87ad9083467..77091f7d1fa75 100644
--- a/drivers/net/can/dev/rx-offload.c
+++ b/drivers/net/can/dev/rx-offload.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2014      Protonic Holland,
  *                         David Jander
- * Copyright (C) 2014-2021 Pengutronix,
+ * Copyright (C) 2014-2021, 2023 Pengutronix,
  *                         Marc Kleine-Budde <kernel@pengutronix.de>
  */
 
@@ -280,6 +280,31 @@ int can_rx_offload_queue_tail(struct can_rx_offload *offload,
 }
 EXPORT_SYMBOL_GPL(can_rx_offload_queue_tail);
 
+unsigned int
+can_rx_offload_get_echo_skb_queue_tail(struct can_rx_offload *offload,
+				       unsigned int idx,
+				       unsigned int *frame_len_ptr)
+{
+	struct net_device *dev = offload->dev;
+	struct net_device_stats *stats = &dev->stats;
+	struct sk_buff *skb;
+	unsigned int len;
+	int err;
+
+	skb = __can_get_echo_skb(dev, idx, &len, frame_len_ptr);
+	if (!skb)
+		return 0;
+
+	err = can_rx_offload_queue_tail(offload, skb);
+	if (err) {
+		stats->rx_errors++;
+		stats->tx_fifo_errors++;
+	}
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(can_rx_offload_get_echo_skb_queue_tail);
+
 void can_rx_offload_irq_finish(struct can_rx_offload *offload)
 {
 	unsigned long flags;
diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h
index e3b4199732c6a..d29bb45219470 100644
--- a/include/linux/can/rx-offload.h
+++ b/include/linux/can/rx-offload.h
@@ -3,7 +3,7 @@
  * linux/can/rx-offload.h
  *
  * Copyright (c) 2014 David Jander, Protonic Holland
- * Copyright (c) 2014-2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
+ * Copyright (c) 2014-2017, 2023 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
  */
 
 #ifndef _CAN_RX_OFFLOAD_H
@@ -49,6 +49,9 @@ unsigned int can_rx_offload_get_echo_skb_queue_timestamp(struct can_rx_offload *
 							 unsigned int *frame_len_ptr);
 int can_rx_offload_queue_tail(struct can_rx_offload *offload,
 			      struct sk_buff *skb);
+unsigned int can_rx_offload_get_echo_skb_queue_tail(struct can_rx_offload *offload,
+						    unsigned int idx,
+						    unsigned int *frame_len_ptr);
 void can_rx_offload_irq_finish(struct can_rx_offload *offload);
 void can_rx_offload_threaded_irq_finish(struct can_rx_offload *offload);
 void can_rx_offload_del(struct can_rx_offload *offload);
-- 
GitLab


From 24bc41b4558347672a3db61009c339b1f5692169 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Fri, 2 Jun 2023 09:29:07 +0200
Subject: [PATCH 0593/1806] can: gs_usb: convert to NAPI/rx-offload to avoid
 OoO reception

The driver used to pass received CAN frames/skbs to the network stack
with netif_rx(). In netif_rx() the skbs are queued to the local CPU.
If IRQs are handled in round robin, OoO packets may occur.

To avoid out-of-order reception convert the driver from netif_rx() to
NAPI.

For USB devices with timestamping support use the rx-offload helper
can_rx_offload_queue_timestamp() for the RX, and
can_rx_offload_get_echo_skb_queue_timestamp() for the TX path. Devices
without timestamping support use can_rx_offload_queue_tail() for RX,
and can_rx_offload_get_echo_skb_queue_tail() for the TX path.

Link: https://lore.kernel.org/all/559D628C.5020100@hartkopp.net
Link: https://github.com/candle-usb/candleLight_fw/issues/166
Link: https://lore.kernel.org/all/20230718-gs_usb-rx-offload-v2-3-716e542d14d5@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/Kconfig  |  1 +
 drivers/net/can/usb/gs_usb.c | 85 ++++++++++++++++++++++++++++--------
 2 files changed, 67 insertions(+), 19 deletions(-)

diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index 58fcd2b348207..d1450722cb3c8 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -52,6 +52,7 @@ config CAN_F81604
 
 config CAN_GS_USB
 	tristate "Geschwister Schneider UG and candleLight compatible interfaces"
+	select CAN_RX_OFFLOAD
 	help
 	  This driver supports the Geschwister Schneider and
 	  bytewerk.org candleLight compatible
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 6caf3974e0283..95b0fdb602c8f 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2013-2016 Geschwister Schneider Technologie-,
  * Entwicklungs- und Vertriebs UG (Haftungsbeschränkt).
  * Copyright (C) 2016 Hubert Denkmair
+ * Copyright (c) 2023 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
  *
  * Many thanks to all socketcan devs!
  */
@@ -24,6 +25,7 @@
 #include <linux/can.h>
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
+#include <linux/can/rx-offload.h>
 
 /* Device specific constants */
 #define USB_GS_USB_1_VENDOR_ID 0x1d50
@@ -282,6 +284,8 @@ struct gs_host_frame {
 #define GS_MAX_TX_URBS 10
 /* Only launch a max of GS_MAX_RX_URBS usb requests at a time. */
 #define GS_MAX_RX_URBS 30
+#define GS_NAPI_WEIGHT 32
+
 /* Maximum number of interfaces the driver supports per device.
  * Current hardware only supports 3 interfaces. The future may vary.
  */
@@ -295,6 +299,7 @@ struct gs_tx_context {
 struct gs_can {
 	struct can_priv can; /* must be the first member */
 
+	struct can_rx_offload offload;
 	struct gs_usb *parent;
 
 	struct net_device *netdev;
@@ -506,20 +511,59 @@ static void gs_update_state(struct gs_can *dev, struct can_frame *cf)
 	}
 }
 
-static void gs_usb_set_timestamp(struct gs_can *dev, struct sk_buff *skb,
-				 const struct gs_host_frame *hf)
+static u32 gs_usb_set_timestamp(struct gs_can *dev, struct sk_buff *skb,
+				const struct gs_host_frame *hf)
 {
 	u32 timestamp;
 
-	if (!(dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP))
-		return;
-
 	if (hf->flags & GS_CAN_FLAG_FD)
 		timestamp = le32_to_cpu(hf->canfd_ts->timestamp_us);
 	else
 		timestamp = le32_to_cpu(hf->classic_can_ts->timestamp_us);
 
-	gs_usb_skb_set_timestamp(dev, skb, timestamp);
+	if (skb)
+		gs_usb_skb_set_timestamp(dev, skb, timestamp);
+
+	return timestamp;
+}
+
+static void gs_usb_rx_offload(struct gs_can *dev, struct sk_buff *skb,
+			      const struct gs_host_frame *hf)
+{
+	struct can_rx_offload *offload = &dev->offload;
+	int rc;
+
+	if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) {
+		const u32 ts = gs_usb_set_timestamp(dev, skb, hf);
+
+		rc = can_rx_offload_queue_timestamp(offload, skb, ts);
+	} else {
+		rc = can_rx_offload_queue_tail(offload, skb);
+	}
+
+	if (rc)
+		dev->netdev->stats.rx_fifo_errors++;
+}
+
+static unsigned int
+gs_usb_get_echo_skb(struct gs_can *dev, struct sk_buff *skb,
+		    const struct gs_host_frame *hf)
+{
+	struct can_rx_offload *offload = &dev->offload;
+	const u32 echo_id = hf->echo_id;
+	unsigned int len;
+
+	if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) {
+		const u32 ts = gs_usb_set_timestamp(dev, skb, hf);
+
+		len = can_rx_offload_get_echo_skb_queue_timestamp(offload, echo_id,
+								  ts, NULL);
+	} else {
+		len = can_rx_offload_get_echo_skb_queue_tail(offload, echo_id,
+							     NULL);
+	}
+
+	return len;
 }
 
 static void gs_usb_receive_bulk_callback(struct urb *urb)
@@ -592,12 +636,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 				gs_update_state(dev, cf);
 		}
 
-		gs_usb_set_timestamp(dev, skb, hf);
-
-		stats->rx_packets++;
-		stats->rx_bytes += hf->can_dlc;
-
-		netif_rx(skb);
+		gs_usb_rx_offload(dev, skb, hf);
 	} else { /* echo_id == hf->echo_id */
 		if (hf->echo_id >= GS_MAX_TX_URBS) {
 			netdev_err(netdev,
@@ -617,12 +656,8 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 		}
 
 		skb = dev->can.echo_skb[hf->echo_id];
-		gs_usb_set_timestamp(dev, skb, hf);
-
 		stats->tx_packets++;
-		stats->tx_bytes += can_get_echo_skb(netdev, hf->echo_id,
-						    NULL);
-
+		stats->tx_bytes += gs_usb_get_echo_skb(dev, skb, hf);
 		gs_free_tx_context(txc);
 
 		atomic_dec(&dev->active_tx_urbs);
@@ -641,9 +676,12 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 		cf->can_id |= CAN_ERR_CRTL;
 		cf->len = CAN_ERR_DLC;
 		cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
-		netif_rx(skb);
+
+		gs_usb_rx_offload(dev, skb, hf);
 	}
 
+	can_rx_offload_irq_finish(&dev->offload);
+
 resubmit_urb:
 	usb_fill_bulk_urb(urb, parent->udev,
 			  usb_rcvbulkpipe(parent->udev, GS_USB_ENDPOINT_IN),
@@ -857,6 +895,8 @@ static int gs_can_open(struct net_device *netdev)
 			dev->hf_size_tx = struct_size(hf, classic_can, 1);
 	}
 
+	can_rx_offload_enable(&dev->offload);
+
 	if (!parent->active_channels) {
 		if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
 			gs_usb_timestamp_init(parent);
@@ -965,6 +1005,7 @@ out_usb_kill_anchored_urbs:
 			gs_usb_timestamp_stop(parent);
 	}
 
+	can_rx_offload_disable(&dev->offload);
 	close_candev(netdev);
 
 	return rc;
@@ -1037,6 +1078,8 @@ static int gs_can_close(struct net_device *netdev)
 		dev->tx_context[rc].echo_id = GS_MAX_TX_URBS;
 	}
 
+	can_rx_offload_disable(&dev->offload);
+
 	/* close the netdev */
 	close_candev(netdev);
 
@@ -1336,6 +1379,7 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 		dev->can.data_bittiming_const = &dev->data_bt_const;
 	}
 
+	can_rx_offload_add_manual(netdev, &dev->offload, GS_NAPI_WEIGHT);
 	SET_NETDEV_DEV(netdev, &intf->dev);
 
 	rc = register_candev(dev->netdev);
@@ -1343,11 +1387,13 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 		dev_err(&intf->dev,
 			"Couldn't register candev for channel %d (%pe)\n",
 			channel, ERR_PTR(rc));
-		goto out_free_candev;
+		goto out_can_rx_offload_del;
 	}
 
 	return dev;
 
+out_can_rx_offload_del:
+	can_rx_offload_del(&dev->offload);
 out_free_candev:
 	free_candev(dev->netdev);
 	return ERR_PTR(rc);
@@ -1356,6 +1402,7 @@ out_free_candev:
 static void gs_destroy_candev(struct gs_can *dev)
 {
 	unregister_candev(dev->netdev);
+	can_rx_offload_del(&dev->offload);
 	free_candev(dev->netdev);
 }
 
-- 
GitLab


From 801b27e88046cb0b34df7d645afb6ba5fc6f677c Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Tue, 25 Jul 2023 20:56:54 +0000
Subject: [PATCH 0594/1806] net: ethtool: Unify ETHTOOL_{G,S}RXFH rxnfc copy

ETHTOOL_GRXFH correctly copies in the full struct ethtool_rxnfc when
FLOW_RSS is set; ETHTOOL_SRXFH needs a similar code path to handle the
FLOW_RSS case so that ethtool can set the flow hash for custom RSS
contexts (if supported by the driver).

The copy code from ETHTOOL_GRXFH has been pulled out in to a helper so
that it can be called in both ETHTOOL_{G,S}RXFH code paths.

Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/ioctl.c | 75 +++++++++++++++++++++++----------------------
 1 file changed, 38 insertions(+), 37 deletions(-)

diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 4a51e0ec295cf..7d40e7913e76e 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -907,6 +907,38 @@ static int ethtool_rxnfc_copy_to_compat(void __user *useraddr,
 	return 0;
 }
 
+static int ethtool_rxnfc_copy_struct(u32 cmd, struct ethtool_rxnfc *info,
+				     size_t *info_size, void __user *useraddr)
+{
+	/* struct ethtool_rxnfc was originally defined for
+	 * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data
+	 * members.  User-space might still be using that
+	 * definition.
+	 */
+	if (cmd == ETHTOOL_GRXFH || cmd == ETHTOOL_SRXFH)
+		*info_size = (offsetof(struct ethtool_rxnfc, data) +
+			      sizeof(info->data));
+
+	if (ethtool_rxnfc_copy_from_user(info, useraddr, *info_size))
+		return -EFAULT;
+
+	if ((cmd == ETHTOOL_GRXFH || cmd == ETHTOOL_SRXFH) && info->flow_type & FLOW_RSS) {
+		*info_size = sizeof(*info);
+		if (ethtool_rxnfc_copy_from_user(info, useraddr, *info_size))
+			return -EFAULT;
+		/* Since malicious users may modify the original data,
+		 * we need to check whether FLOW_RSS is still requested.
+		 */
+		if (!(info->flow_type & FLOW_RSS))
+			return -EINVAL;
+	}
+
+	if (info->cmd != cmd)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int ethtool_rxnfc_copy_to_user(void __user *useraddr,
 				      const struct ethtool_rxnfc *rxnfc,
 				      size_t size, const u32 *rule_buf)
@@ -944,16 +976,9 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 	if (!dev->ethtool_ops->set_rxnfc)
 		return -EOPNOTSUPP;
 
-	/* struct ethtool_rxnfc was originally defined for
-	 * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data
-	 * members.  User-space might still be using that
-	 * definition. */
-	if (cmd == ETHTOOL_SRXFH)
-		info_size = (offsetof(struct ethtool_rxnfc, data) +
-			     sizeof(info.data));
-
-	if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
-		return -EFAULT;
+	rc = ethtool_rxnfc_copy_struct(cmd, &info, &info_size, useraddr);
+	if (rc)
+		return rc;
 
 	rc = dev->ethtool_ops->set_rxnfc(dev, &info);
 	if (rc)
@@ -978,33 +1003,9 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
 	if (!ops->get_rxnfc)
 		return -EOPNOTSUPP;
 
-	/* struct ethtool_rxnfc was originally defined for
-	 * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data
-	 * members.  User-space might still be using that
-	 * definition. */
-	if (cmd == ETHTOOL_GRXFH)
-		info_size = (offsetof(struct ethtool_rxnfc, data) +
-			     sizeof(info.data));
-
-	if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
-		return -EFAULT;
-
-	/* If FLOW_RSS was requested then user-space must be using the
-	 * new definition, as FLOW_RSS is newer.
-	 */
-	if (cmd == ETHTOOL_GRXFH && info.flow_type & FLOW_RSS) {
-		info_size = sizeof(info);
-		if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
-			return -EFAULT;
-		/* Since malicious users may modify the original data,
-		 * we need to check whether FLOW_RSS is still requested.
-		 */
-		if (!(info.flow_type & FLOW_RSS))
-			return -EINVAL;
-	}
-
-	if (info.cmd != cmd)
-		return -EINVAL;
+	ret = ethtool_rxnfc_copy_struct(cmd, &info, &info_size, useraddr);
+	if (ret)
+		return ret;
 
 	if (info.cmd == ETHTOOL_GRXCLSRLALL) {
 		if (info.rule_cnt > 0) {
-- 
GitLab


From 0212e5d915a293dcde06415f8c82d31576576a97 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Tue, 25 Jul 2023 20:56:55 +0000
Subject: [PATCH 0595/1806] net/mlx5: Fix flowhash key set/get for custom RSS

mlx5 flow hash field retrieval and set only worked on the default
RSS context as of commit f01cc58c18d6 ("net/mlx5e: Support multiple RSS
contexts"), not custom RSS contexts.

For example, before this patch attempting to retrieve the flow hash fields
for RSS context 1 fails:

$ sudo ethtool -u eth1 rx-flow-hash tcp4 context 1
Cannot get RX network flow hashing options: Invalid argument

This patch fixes getting and setting the flow hash fields for contexts
other than the default context.

Getting the flow hash fields for RSS context 1:

$ sudo ethtool -u eth1 rx-flow-hash tcp4 context 1
For RSS context 1:
TCP over IPV4 flows use these fields for computing Hash flow key:
IP DA

Now, setting the flash hash fields to a custom value:

$ sudo ethtool -U eth1 rx-flow-hash tcp4 sdfn context 1

And retrieving them again:

$ sudo ethtool -u eth1 rx-flow-hash tcp4 context 1
For RSS context 1:
TCP over IPV4 flows use these fields for computing Hash flow key:
IP SA
IP DA
L4 bytes 0 & 1 [TCP/UDP src port]
L4 bytes 2 & 3 [TCP/UDP dst port]

Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlx5/core/en/rx_res.c   | 25 +++++++++++---
 .../ethernet/mellanox/mlx5/core/en/rx_res.h   |  7 ++--
 .../mellanox/mlx5/core/en_fs_ethtool.c        | 33 ++++++++++++++-----
 3 files changed, 48 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index e1095bc365436..56e6b8c7501fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -218,17 +218,32 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 	return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, res->rss_nch);
 }
 
-u8 mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt)
+int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
+				     enum mlx5_traffic_types tt)
 {
-	struct mlx5e_rss *rss = res->rss[0];
+	struct mlx5e_rss *rss;
+
+	if (rss_idx >= MLX5E_MAX_NUM_RSS)
+		return -EINVAL;
+
+	rss = res->rss[rss_idx];
+	if (!rss)
+		return -ENOENT;
 
 	return mlx5e_rss_get_hash_fields(rss, tt);
 }
 
-int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt,
-				     u8 rx_hash_fields)
+int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
+				     enum mlx5_traffic_types tt, u8 rx_hash_fields)
 {
-	struct mlx5e_rss *rss = res->rss[0];
+	struct mlx5e_rss *rss;
+
+	if (rss_idx >= MLX5E_MAX_NUM_RSS)
+		return -EINVAL;
+
+	rss = res->rss[rss_idx];
+	if (!rss)
+		return -ENOENT;
 
 	return mlx5e_rss_set_hash_fields(rss, tt, rx_hash_fields);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index 5d5f64fab60ff..580fe8bc3cd2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -48,9 +48,10 @@ int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 			      const u32 *indir, const u8 *key, const u8 *hfunc);
 
-u8 mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
-int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt,
-				     u8 rx_hash_fields);
+int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
+				     enum mlx5_traffic_types tt);
+int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
+				     enum mlx5_traffic_types tt, u8 rx_hash_fields);
 int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res,
 					struct mlx5e_packet_merge_param *pkt_merge_param);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index aac32e505c14f..aed599db9d843 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -900,10 +900,16 @@ static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
 				  struct ethtool_rxnfc *nfc)
 {
 	u8 rx_hash_field = 0;
+	u32 flow_type = 0;
+	u32 rss_idx = 0;
 	int err;
 	int tt;
 
-	tt = flow_type_to_traffic_type(nfc->flow_type);
+	if (nfc->flow_type & FLOW_RSS)
+		rss_idx = nfc->rss_context;
+
+	flow_type = flow_type_mask(nfc->flow_type);
+	tt = flow_type_to_traffic_type(flow_type);
 	if (tt < 0)
 		return tt;
 
@@ -911,10 +917,10 @@ static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
 	 *  on src IP, dest IP, TCP/UDP src port and TCP/UDP dest
 	 *  port.
 	 */
-	if (nfc->flow_type != TCP_V4_FLOW &&
-	    nfc->flow_type != TCP_V6_FLOW &&
-	    nfc->flow_type != UDP_V4_FLOW &&
-	    nfc->flow_type != UDP_V6_FLOW)
+	if (flow_type != TCP_V4_FLOW &&
+	    flow_type != TCP_V6_FLOW &&
+	    flow_type != UDP_V4_FLOW &&
+	    flow_type != UDP_V6_FLOW)
 		return -EOPNOTSUPP;
 
 	if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
@@ -931,7 +937,7 @@ static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
 		rx_hash_field |= MLX5_HASH_FIELD_SEL_L4_DPORT;
 
 	mutex_lock(&priv->state_lock);
-	err = mlx5e_rx_res_rss_set_hash_fields(priv->rx_res, tt, rx_hash_field);
+	err = mlx5e_rx_res_rss_set_hash_fields(priv->rx_res, rss_idx, tt, rx_hash_field);
 	mutex_unlock(&priv->state_lock);
 
 	return err;
@@ -940,14 +946,23 @@ static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
 static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv,
 				  struct ethtool_rxnfc *nfc)
 {
-	u32 hash_field = 0;
+	int hash_field = 0;
+	u32 flow_type = 0;
+	u32 rss_idx = 0;
 	int tt;
 
-	tt = flow_type_to_traffic_type(nfc->flow_type);
+	if (nfc->flow_type & FLOW_RSS)
+		rss_idx = nfc->rss_context;
+
+	flow_type = flow_type_mask(nfc->flow_type);
+	tt = flow_type_to_traffic_type(flow_type);
 	if (tt < 0)
 		return tt;
 
-	hash_field = mlx5e_rx_res_rss_get_hash_fields(priv->rx_res, tt);
+	hash_field = mlx5e_rx_res_rss_get_hash_fields(priv->rx_res, rss_idx, tt);
+	if (hash_field < 0)
+		return hash_field;
+
 	nfc->data = 0;
 
 	if (hash_field & MLX5_HASH_FIELD_SEL_SRC_IP)
-- 
GitLab


From 806521bc48aac06d8aa22a9e1d8b5bdf2377bbdc Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:40:43 +0100
Subject: [PATCH 0596/1806] sfc: Remove falcon references

Siena was using functions from the Falcon architecture.
These start with the efx_farch prefix.
Now that both of these are in separate modules the references
are no longer used in the sfc.ko module.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/farch_regs.h | 2929 -------------------------
 drivers/net/ethernet/sfc/mcdi.c       |    1 -
 drivers/net/ethernet/sfc/net_driver.h |    5 +-
 drivers/net/ethernet/sfc/nic.c        |  153 --
 drivers/net/ethernet/sfc/nic.h        |   83 -
 drivers/net/ethernet/sfc/ptp.c        |    1 -
 6 files changed, 2 insertions(+), 3170 deletions(-)
 delete mode 100644 drivers/net/ethernet/sfc/farch_regs.h

diff --git a/drivers/net/ethernet/sfc/farch_regs.h b/drivers/net/ethernet/sfc/farch_regs.h
deleted file mode 100644
index d138be423e638..0000000000000
--- a/drivers/net/ethernet/sfc/farch_regs.h
+++ /dev/null
@@ -1,2929 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/****************************************************************************
- * Driver for Solarflare network controllers and boards
- * Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2012 Solarflare Communications Inc.
- */
-
-#ifndef EFX_FARCH_REGS_H
-#define EFX_FARCH_REGS_H
-
-/*
- * Falcon hardware architecture definitions have a name prefix following
- * the format:
- *
- *     F<type>_<min-rev><max-rev>_
- *
- * The following <type> strings are used:
- *
- *             MMIO register  MC register  Host memory structure
- * -------------------------------------------------------------
- * Address     R              MCR
- * Bitfield    RF             MCRF         SF
- * Enumerator  FE             MCFE         SE
- *
- * <min-rev> is the first revision to which the definition applies:
- *
- *     A: Falcon A1 (SFC4000AB)
- *     B: Falcon B0 (SFC4000BA)
- *     C: Siena A0 (SFL9021AA)
- *
- * If the definition has been changed or removed in later revisions
- * then <max-rev> is the last revision to which the definition applies;
- * otherwise it is "Z".
- */
-
-/**************************************************************************
- *
- * Falcon/Siena registers and descriptors
- *
- **************************************************************************
- */
-
-/* ADR_REGION_REG: Address region register */
-#define	FR_AZ_ADR_REGION 0x00000000
-#define	FRF_AZ_ADR_REGION3_LBN 96
-#define	FRF_AZ_ADR_REGION3_WIDTH 18
-#define	FRF_AZ_ADR_REGION2_LBN 64
-#define	FRF_AZ_ADR_REGION2_WIDTH 18
-#define	FRF_AZ_ADR_REGION1_LBN 32
-#define	FRF_AZ_ADR_REGION1_WIDTH 18
-#define	FRF_AZ_ADR_REGION0_LBN 0
-#define	FRF_AZ_ADR_REGION0_WIDTH 18
-
-/* INT_EN_REG_KER: Kernel driver Interrupt enable register */
-#define	FR_AZ_INT_EN_KER 0x00000010
-#define	FRF_AZ_KER_INT_LEVE_SEL_LBN 8
-#define	FRF_AZ_KER_INT_LEVE_SEL_WIDTH 6
-#define	FRF_AZ_KER_INT_CHAR_LBN 4
-#define	FRF_AZ_KER_INT_CHAR_WIDTH 1
-#define	FRF_AZ_KER_INT_KER_LBN 3
-#define	FRF_AZ_KER_INT_KER_WIDTH 1
-#define	FRF_AZ_DRV_INT_EN_KER_LBN 0
-#define	FRF_AZ_DRV_INT_EN_KER_WIDTH 1
-
-/* INT_EN_REG_CHAR: Char Driver interrupt enable register */
-#define	FR_BZ_INT_EN_CHAR 0x00000020
-#define	FRF_BZ_CHAR_INT_LEVE_SEL_LBN 8
-#define	FRF_BZ_CHAR_INT_LEVE_SEL_WIDTH 6
-#define	FRF_BZ_CHAR_INT_CHAR_LBN 4
-#define	FRF_BZ_CHAR_INT_CHAR_WIDTH 1
-#define	FRF_BZ_CHAR_INT_KER_LBN 3
-#define	FRF_BZ_CHAR_INT_KER_WIDTH 1
-#define	FRF_BZ_DRV_INT_EN_CHAR_LBN 0
-#define	FRF_BZ_DRV_INT_EN_CHAR_WIDTH 1
-
-/* INT_ADR_REG_KER: Interrupt host address for Kernel driver */
-#define	FR_AZ_INT_ADR_KER 0x00000030
-#define	FRF_AZ_NORM_INT_VEC_DIS_KER_LBN 64
-#define	FRF_AZ_NORM_INT_VEC_DIS_KER_WIDTH 1
-#define	FRF_AZ_INT_ADR_KER_LBN 0
-#define	FRF_AZ_INT_ADR_KER_WIDTH 64
-
-/* INT_ADR_REG_CHAR: Interrupt host address for Char driver */
-#define	FR_BZ_INT_ADR_CHAR 0x00000040
-#define	FRF_BZ_NORM_INT_VEC_DIS_CHAR_LBN 64
-#define	FRF_BZ_NORM_INT_VEC_DIS_CHAR_WIDTH 1
-#define	FRF_BZ_INT_ADR_CHAR_LBN 0
-#define	FRF_BZ_INT_ADR_CHAR_WIDTH 64
-
-/* INT_ACK_KER: Kernel interrupt acknowledge register */
-#define	FR_AA_INT_ACK_KER 0x00000050
-#define	FRF_AA_INT_ACK_KER_FIELD_LBN 0
-#define	FRF_AA_INT_ACK_KER_FIELD_WIDTH 32
-
-/* INT_ISR0_REG: Function 0 Interrupt Acknowledge Status register */
-#define	FR_BZ_INT_ISR0 0x00000090
-#define	FRF_BZ_INT_ISR_REG_LBN 0
-#define	FRF_BZ_INT_ISR_REG_WIDTH 64
-
-/* HW_INIT_REG: Hardware initialization register */
-#define	FR_AZ_HW_INIT 0x000000c0
-#define	FRF_BB_BDMRD_CPLF_FULL_LBN 124
-#define	FRF_BB_BDMRD_CPLF_FULL_WIDTH 1
-#define	FRF_BB_PCIE_CPL_TIMEOUT_CTRL_LBN 121
-#define	FRF_BB_PCIE_CPL_TIMEOUT_CTRL_WIDTH 3
-#define	FRF_CZ_TX_MRG_TAGS_LBN 120
-#define	FRF_CZ_TX_MRG_TAGS_WIDTH 1
-#define	FRF_AB_TRGT_MASK_ALL_LBN 100
-#define	FRF_AB_TRGT_MASK_ALL_WIDTH 1
-#define	FRF_AZ_DOORBELL_DROP_LBN 92
-#define	FRF_AZ_DOORBELL_DROP_WIDTH 8
-#define	FRF_AB_TX_RREQ_MASK_EN_LBN 76
-#define	FRF_AB_TX_RREQ_MASK_EN_WIDTH 1
-#define	FRF_AB_PE_EIDLE_DIS_LBN 75
-#define	FRF_AB_PE_EIDLE_DIS_WIDTH 1
-#define	FRF_AA_FC_BLOCKING_EN_LBN 45
-#define	FRF_AA_FC_BLOCKING_EN_WIDTH 1
-#define	FRF_BZ_B2B_REQ_EN_LBN 45
-#define	FRF_BZ_B2B_REQ_EN_WIDTH 1
-#define	FRF_AA_B2B_REQ_EN_LBN 44
-#define	FRF_AA_B2B_REQ_EN_WIDTH 1
-#define	FRF_BB_FC_BLOCKING_EN_LBN 44
-#define	FRF_BB_FC_BLOCKING_EN_WIDTH 1
-#define	FRF_AZ_POST_WR_MASK_LBN 40
-#define	FRF_AZ_POST_WR_MASK_WIDTH 4
-#define	FRF_AZ_TLP_TC_LBN 34
-#define	FRF_AZ_TLP_TC_WIDTH 3
-#define	FRF_AZ_TLP_ATTR_LBN 32
-#define	FRF_AZ_TLP_ATTR_WIDTH 2
-#define	FRF_AB_INTB_VEC_LBN 24
-#define	FRF_AB_INTB_VEC_WIDTH 5
-#define	FRF_AB_INTA_VEC_LBN 16
-#define	FRF_AB_INTA_VEC_WIDTH 5
-#define	FRF_AZ_WD_TIMER_LBN 8
-#define	FRF_AZ_WD_TIMER_WIDTH 8
-#define	FRF_AZ_US_DISABLE_LBN 5
-#define	FRF_AZ_US_DISABLE_WIDTH 1
-#define	FRF_AZ_TLP_EP_LBN 4
-#define	FRF_AZ_TLP_EP_WIDTH 1
-#define	FRF_AZ_ATTR_SEL_LBN 3
-#define	FRF_AZ_ATTR_SEL_WIDTH 1
-#define	FRF_AZ_TD_SEL_LBN 1
-#define	FRF_AZ_TD_SEL_WIDTH 1
-#define	FRF_AZ_TLP_TD_LBN 0
-#define	FRF_AZ_TLP_TD_WIDTH 1
-
-/* EE_SPI_HCMD_REG: SPI host command register */
-#define	FR_AB_EE_SPI_HCMD 0x00000100
-#define	FRF_AB_EE_SPI_HCMD_CMD_EN_LBN 31
-#define	FRF_AB_EE_SPI_HCMD_CMD_EN_WIDTH 1
-#define	FRF_AB_EE_WR_TIMER_ACTIVE_LBN 28
-#define	FRF_AB_EE_WR_TIMER_ACTIVE_WIDTH 1
-#define	FRF_AB_EE_SPI_HCMD_SF_SEL_LBN 24
-#define	FRF_AB_EE_SPI_HCMD_SF_SEL_WIDTH 1
-#define	FRF_AB_EE_SPI_HCMD_DABCNT_LBN 16
-#define	FRF_AB_EE_SPI_HCMD_DABCNT_WIDTH 5
-#define	FRF_AB_EE_SPI_HCMD_READ_LBN 15
-#define	FRF_AB_EE_SPI_HCMD_READ_WIDTH 1
-#define	FRF_AB_EE_SPI_HCMD_DUBCNT_LBN 12
-#define	FRF_AB_EE_SPI_HCMD_DUBCNT_WIDTH 2
-#define	FRF_AB_EE_SPI_HCMD_ADBCNT_LBN 8
-#define	FRF_AB_EE_SPI_HCMD_ADBCNT_WIDTH 2
-#define	FRF_AB_EE_SPI_HCMD_ENC_LBN 0
-#define	FRF_AB_EE_SPI_HCMD_ENC_WIDTH 8
-
-/* USR_EV_CFG: User Level Event Configuration register */
-#define	FR_CZ_USR_EV_CFG 0x00000100
-#define	FRF_CZ_USREV_DIS_LBN 16
-#define	FRF_CZ_USREV_DIS_WIDTH 1
-#define	FRF_CZ_DFLT_EVQ_LBN 0
-#define	FRF_CZ_DFLT_EVQ_WIDTH 10
-
-/* EE_SPI_HADR_REG: SPI host address register */
-#define	FR_AB_EE_SPI_HADR 0x00000110
-#define	FRF_AB_EE_SPI_HADR_DUBYTE_LBN 24
-#define	FRF_AB_EE_SPI_HADR_DUBYTE_WIDTH 8
-#define	FRF_AB_EE_SPI_HADR_ADR_LBN 0
-#define	FRF_AB_EE_SPI_HADR_ADR_WIDTH 24
-
-/* EE_SPI_HDATA_REG: SPI host data register */
-#define	FR_AB_EE_SPI_HDATA 0x00000120
-#define	FRF_AB_EE_SPI_HDATA3_LBN 96
-#define	FRF_AB_EE_SPI_HDATA3_WIDTH 32
-#define	FRF_AB_EE_SPI_HDATA2_LBN 64
-#define	FRF_AB_EE_SPI_HDATA2_WIDTH 32
-#define	FRF_AB_EE_SPI_HDATA1_LBN 32
-#define	FRF_AB_EE_SPI_HDATA1_WIDTH 32
-#define	FRF_AB_EE_SPI_HDATA0_LBN 0
-#define	FRF_AB_EE_SPI_HDATA0_WIDTH 32
-
-/* EE_BASE_PAGE_REG: Expansion ROM base mirror register */
-#define	FR_AB_EE_BASE_PAGE 0x00000130
-#define	FRF_AB_EE_EXPROM_MASK_LBN 16
-#define	FRF_AB_EE_EXPROM_MASK_WIDTH 13
-#define	FRF_AB_EE_EXP_ROM_WINDOW_BASE_LBN 0
-#define	FRF_AB_EE_EXP_ROM_WINDOW_BASE_WIDTH 13
-
-/* EE_VPD_CFG0_REG: SPI/VPD configuration register 0 */
-#define	FR_AB_EE_VPD_CFG0 0x00000140
-#define	FRF_AB_EE_SF_FASTRD_EN_LBN 127
-#define	FRF_AB_EE_SF_FASTRD_EN_WIDTH 1
-#define	FRF_AB_EE_SF_CLOCK_DIV_LBN 120
-#define	FRF_AB_EE_SF_CLOCK_DIV_WIDTH 7
-#define	FRF_AB_EE_VPD_WIP_POLL_LBN 119
-#define	FRF_AB_EE_VPD_WIP_POLL_WIDTH 1
-#define	FRF_AB_EE_EE_CLOCK_DIV_LBN 112
-#define	FRF_AB_EE_EE_CLOCK_DIV_WIDTH 7
-#define	FRF_AB_EE_EE_WR_TMR_VALUE_LBN 96
-#define	FRF_AB_EE_EE_WR_TMR_VALUE_WIDTH 16
-#define	FRF_AB_EE_VPDW_LENGTH_LBN 80
-#define	FRF_AB_EE_VPDW_LENGTH_WIDTH 15
-#define	FRF_AB_EE_VPDW_BASE_LBN 64
-#define	FRF_AB_EE_VPDW_BASE_WIDTH 15
-#define	FRF_AB_EE_VPD_WR_CMD_EN_LBN 56
-#define	FRF_AB_EE_VPD_WR_CMD_EN_WIDTH 8
-#define	FRF_AB_EE_VPD_BASE_LBN 32
-#define	FRF_AB_EE_VPD_BASE_WIDTH 24
-#define	FRF_AB_EE_VPD_LENGTH_LBN 16
-#define	FRF_AB_EE_VPD_LENGTH_WIDTH 15
-#define	FRF_AB_EE_VPD_AD_SIZE_LBN 8
-#define	FRF_AB_EE_VPD_AD_SIZE_WIDTH 5
-#define	FRF_AB_EE_VPD_ACCESS_ON_LBN 5
-#define	FRF_AB_EE_VPD_ACCESS_ON_WIDTH 1
-#define	FRF_AB_EE_VPD_ACCESS_BLOCK_LBN 4
-#define	FRF_AB_EE_VPD_ACCESS_BLOCK_WIDTH 1
-#define	FRF_AB_EE_VPD_DEV_SF_SEL_LBN 2
-#define	FRF_AB_EE_VPD_DEV_SF_SEL_WIDTH 1
-#define	FRF_AB_EE_VPD_EN_AD9_MODE_LBN 1
-#define	FRF_AB_EE_VPD_EN_AD9_MODE_WIDTH 1
-#define	FRF_AB_EE_VPD_EN_LBN 0
-#define	FRF_AB_EE_VPD_EN_WIDTH 1
-
-/* EE_VPD_SW_CNTL_REG: VPD access SW control register */
-#define	FR_AB_EE_VPD_SW_CNTL 0x00000150
-#define	FRF_AB_EE_VPD_CYCLE_PENDING_LBN 31
-#define	FRF_AB_EE_VPD_CYCLE_PENDING_WIDTH 1
-#define	FRF_AB_EE_VPD_CYC_WRITE_LBN 28
-#define	FRF_AB_EE_VPD_CYC_WRITE_WIDTH 1
-#define	FRF_AB_EE_VPD_CYC_ADR_LBN 0
-#define	FRF_AB_EE_VPD_CYC_ADR_WIDTH 15
-
-/* EE_VPD_SW_DATA_REG: VPD access SW data register */
-#define	FR_AB_EE_VPD_SW_DATA 0x00000160
-#define	FRF_AB_EE_VPD_CYC_DAT_LBN 0
-#define	FRF_AB_EE_VPD_CYC_DAT_WIDTH 32
-
-/* PBMX_DBG_IADDR_REG: Capture Module address register */
-#define	FR_CZ_PBMX_DBG_IADDR 0x000001f0
-#define	FRF_CZ_PBMX_DBG_IADDR_LBN 0
-#define	FRF_CZ_PBMX_DBG_IADDR_WIDTH 32
-
-/* PCIE_CORE_INDIRECT_REG: Indirect Access to PCIE Core registers */
-#define	FR_BB_PCIE_CORE_INDIRECT 0x000001f0
-#define	FRF_BB_PCIE_CORE_TARGET_DATA_LBN 32
-#define	FRF_BB_PCIE_CORE_TARGET_DATA_WIDTH 32
-#define	FRF_BB_PCIE_CORE_INDIRECT_ACCESS_DIR_LBN 15
-#define	FRF_BB_PCIE_CORE_INDIRECT_ACCESS_DIR_WIDTH 1
-#define	FRF_BB_PCIE_CORE_TARGET_REG_ADRS_LBN 0
-#define	FRF_BB_PCIE_CORE_TARGET_REG_ADRS_WIDTH 12
-
-/* PBMX_DBG_IDATA_REG: Capture Module data register */
-#define	FR_CZ_PBMX_DBG_IDATA 0x000001f8
-#define	FRF_CZ_PBMX_DBG_IDATA_LBN 0
-#define	FRF_CZ_PBMX_DBG_IDATA_WIDTH 64
-
-/* NIC_STAT_REG: NIC status register */
-#define	FR_AB_NIC_STAT 0x00000200
-#define	FRF_BB_AER_DIS_LBN 34
-#define	FRF_BB_AER_DIS_WIDTH 1
-#define	FRF_BB_EE_STRAP_EN_LBN 31
-#define	FRF_BB_EE_STRAP_EN_WIDTH 1
-#define	FRF_BB_EE_STRAP_LBN 24
-#define	FRF_BB_EE_STRAP_WIDTH 4
-#define	FRF_BB_REVISION_ID_LBN 17
-#define	FRF_BB_REVISION_ID_WIDTH 7
-#define	FRF_AB_ONCHIP_SRAM_LBN 16
-#define	FRF_AB_ONCHIP_SRAM_WIDTH 1
-#define	FRF_AB_SF_PRST_LBN 9
-#define	FRF_AB_SF_PRST_WIDTH 1
-#define	FRF_AB_EE_PRST_LBN 8
-#define	FRF_AB_EE_PRST_WIDTH 1
-#define	FRF_AB_ATE_MODE_LBN 3
-#define	FRF_AB_ATE_MODE_WIDTH 1
-#define	FRF_AB_STRAP_PINS_LBN 0
-#define	FRF_AB_STRAP_PINS_WIDTH 3
-
-/* GPIO_CTL_REG: GPIO control register */
-#define	FR_AB_GPIO_CTL 0x00000210
-#define	FRF_AB_GPIO_OUT3_LBN 112
-#define	FRF_AB_GPIO_OUT3_WIDTH 16
-#define	FRF_AB_GPIO_IN3_LBN 104
-#define	FRF_AB_GPIO_IN3_WIDTH 8
-#define	FRF_AB_GPIO_PWRUP_VALUE3_LBN 96
-#define	FRF_AB_GPIO_PWRUP_VALUE3_WIDTH 8
-#define	FRF_AB_GPIO_OUT2_LBN 80
-#define	FRF_AB_GPIO_OUT2_WIDTH 16
-#define	FRF_AB_GPIO_IN2_LBN 72
-#define	FRF_AB_GPIO_IN2_WIDTH 8
-#define	FRF_AB_GPIO_PWRUP_VALUE2_LBN 64
-#define	FRF_AB_GPIO_PWRUP_VALUE2_WIDTH 8
-#define	FRF_AB_GPIO15_OEN_LBN 63
-#define	FRF_AB_GPIO15_OEN_WIDTH 1
-#define	FRF_AB_GPIO14_OEN_LBN 62
-#define	FRF_AB_GPIO14_OEN_WIDTH 1
-#define	FRF_AB_GPIO13_OEN_LBN 61
-#define	FRF_AB_GPIO13_OEN_WIDTH 1
-#define	FRF_AB_GPIO12_OEN_LBN 60
-#define	FRF_AB_GPIO12_OEN_WIDTH 1
-#define	FRF_AB_GPIO11_OEN_LBN 59
-#define	FRF_AB_GPIO11_OEN_WIDTH 1
-#define	FRF_AB_GPIO10_OEN_LBN 58
-#define	FRF_AB_GPIO10_OEN_WIDTH 1
-#define	FRF_AB_GPIO9_OEN_LBN 57
-#define	FRF_AB_GPIO9_OEN_WIDTH 1
-#define	FRF_AB_GPIO8_OEN_LBN 56
-#define	FRF_AB_GPIO8_OEN_WIDTH 1
-#define	FRF_AB_GPIO15_OUT_LBN 55
-#define	FRF_AB_GPIO15_OUT_WIDTH 1
-#define	FRF_AB_GPIO14_OUT_LBN 54
-#define	FRF_AB_GPIO14_OUT_WIDTH 1
-#define	FRF_AB_GPIO13_OUT_LBN 53
-#define	FRF_AB_GPIO13_OUT_WIDTH 1
-#define	FRF_AB_GPIO12_OUT_LBN 52
-#define	FRF_AB_GPIO12_OUT_WIDTH 1
-#define	FRF_AB_GPIO11_OUT_LBN 51
-#define	FRF_AB_GPIO11_OUT_WIDTH 1
-#define	FRF_AB_GPIO10_OUT_LBN 50
-#define	FRF_AB_GPIO10_OUT_WIDTH 1
-#define	FRF_AB_GPIO9_OUT_LBN 49
-#define	FRF_AB_GPIO9_OUT_WIDTH 1
-#define	FRF_AB_GPIO8_OUT_LBN 48
-#define	FRF_AB_GPIO8_OUT_WIDTH 1
-#define	FRF_AB_GPIO15_IN_LBN 47
-#define	FRF_AB_GPIO15_IN_WIDTH 1
-#define	FRF_AB_GPIO14_IN_LBN 46
-#define	FRF_AB_GPIO14_IN_WIDTH 1
-#define	FRF_AB_GPIO13_IN_LBN 45
-#define	FRF_AB_GPIO13_IN_WIDTH 1
-#define	FRF_AB_GPIO12_IN_LBN 44
-#define	FRF_AB_GPIO12_IN_WIDTH 1
-#define	FRF_AB_GPIO11_IN_LBN 43
-#define	FRF_AB_GPIO11_IN_WIDTH 1
-#define	FRF_AB_GPIO10_IN_LBN 42
-#define	FRF_AB_GPIO10_IN_WIDTH 1
-#define	FRF_AB_GPIO9_IN_LBN 41
-#define	FRF_AB_GPIO9_IN_WIDTH 1
-#define	FRF_AB_GPIO8_IN_LBN 40
-#define	FRF_AB_GPIO8_IN_WIDTH 1
-#define	FRF_AB_GPIO15_PWRUP_VALUE_LBN 39
-#define	FRF_AB_GPIO15_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO14_PWRUP_VALUE_LBN 38
-#define	FRF_AB_GPIO14_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO13_PWRUP_VALUE_LBN 37
-#define	FRF_AB_GPIO13_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO12_PWRUP_VALUE_LBN 36
-#define	FRF_AB_GPIO12_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO11_PWRUP_VALUE_LBN 35
-#define	FRF_AB_GPIO11_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO10_PWRUP_VALUE_LBN 34
-#define	FRF_AB_GPIO10_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO9_PWRUP_VALUE_LBN 33
-#define	FRF_AB_GPIO9_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO8_PWRUP_VALUE_LBN 32
-#define	FRF_AB_GPIO8_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_CLK156_OUT_EN_LBN 31
-#define	FRF_AB_CLK156_OUT_EN_WIDTH 1
-#define	FRF_AB_USE_NIC_CLK_LBN 30
-#define	FRF_AB_USE_NIC_CLK_WIDTH 1
-#define	FRF_AB_GPIO5_OEN_LBN 29
-#define	FRF_AB_GPIO5_OEN_WIDTH 1
-#define	FRF_AB_GPIO4_OEN_LBN 28
-#define	FRF_AB_GPIO4_OEN_WIDTH 1
-#define	FRF_AB_GPIO3_OEN_LBN 27
-#define	FRF_AB_GPIO3_OEN_WIDTH 1
-#define	FRF_AB_GPIO2_OEN_LBN 26
-#define	FRF_AB_GPIO2_OEN_WIDTH 1
-#define	FRF_AB_GPIO1_OEN_LBN 25
-#define	FRF_AB_GPIO1_OEN_WIDTH 1
-#define	FRF_AB_GPIO0_OEN_LBN 24
-#define	FRF_AB_GPIO0_OEN_WIDTH 1
-#define	FRF_AB_GPIO7_OUT_LBN 23
-#define	FRF_AB_GPIO7_OUT_WIDTH 1
-#define	FRF_AB_GPIO6_OUT_LBN 22
-#define	FRF_AB_GPIO6_OUT_WIDTH 1
-#define	FRF_AB_GPIO5_OUT_LBN 21
-#define	FRF_AB_GPIO5_OUT_WIDTH 1
-#define	FRF_AB_GPIO4_OUT_LBN 20
-#define	FRF_AB_GPIO4_OUT_WIDTH 1
-#define	FRF_AB_GPIO3_OUT_LBN 19
-#define	FRF_AB_GPIO3_OUT_WIDTH 1
-#define	FRF_AB_GPIO2_OUT_LBN 18
-#define	FRF_AB_GPIO2_OUT_WIDTH 1
-#define	FRF_AB_GPIO1_OUT_LBN 17
-#define	FRF_AB_GPIO1_OUT_WIDTH 1
-#define	FRF_AB_GPIO0_OUT_LBN 16
-#define	FRF_AB_GPIO0_OUT_WIDTH 1
-#define	FRF_AB_GPIO7_IN_LBN 15
-#define	FRF_AB_GPIO7_IN_WIDTH 1
-#define	FRF_AB_GPIO6_IN_LBN 14
-#define	FRF_AB_GPIO6_IN_WIDTH 1
-#define	FRF_AB_GPIO5_IN_LBN 13
-#define	FRF_AB_GPIO5_IN_WIDTH 1
-#define	FRF_AB_GPIO4_IN_LBN 12
-#define	FRF_AB_GPIO4_IN_WIDTH 1
-#define	FRF_AB_GPIO3_IN_LBN 11
-#define	FRF_AB_GPIO3_IN_WIDTH 1
-#define	FRF_AB_GPIO2_IN_LBN 10
-#define	FRF_AB_GPIO2_IN_WIDTH 1
-#define	FRF_AB_GPIO1_IN_LBN 9
-#define	FRF_AB_GPIO1_IN_WIDTH 1
-#define	FRF_AB_GPIO0_IN_LBN 8
-#define	FRF_AB_GPIO0_IN_WIDTH 1
-#define	FRF_AB_GPIO7_PWRUP_VALUE_LBN 7
-#define	FRF_AB_GPIO7_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO6_PWRUP_VALUE_LBN 6
-#define	FRF_AB_GPIO6_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO5_PWRUP_VALUE_LBN 5
-#define	FRF_AB_GPIO5_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO4_PWRUP_VALUE_LBN 4
-#define	FRF_AB_GPIO4_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO3_PWRUP_VALUE_LBN 3
-#define	FRF_AB_GPIO3_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO2_PWRUP_VALUE_LBN 2
-#define	FRF_AB_GPIO2_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO1_PWRUP_VALUE_LBN 1
-#define	FRF_AB_GPIO1_PWRUP_VALUE_WIDTH 1
-#define	FRF_AB_GPIO0_PWRUP_VALUE_LBN 0
-#define	FRF_AB_GPIO0_PWRUP_VALUE_WIDTH 1
-
-/* GLB_CTL_REG: Global control register */
-#define	FR_AB_GLB_CTL 0x00000220
-#define	FRF_AB_EXT_PHY_RST_CTL_LBN 63
-#define	FRF_AB_EXT_PHY_RST_CTL_WIDTH 1
-#define	FRF_AB_XAUI_SD_RST_CTL_LBN 62
-#define	FRF_AB_XAUI_SD_RST_CTL_WIDTH 1
-#define	FRF_AB_PCIE_SD_RST_CTL_LBN 61
-#define	FRF_AB_PCIE_SD_RST_CTL_WIDTH 1
-#define	FRF_AA_PCIX_RST_CTL_LBN 60
-#define	FRF_AA_PCIX_RST_CTL_WIDTH 1
-#define	FRF_BB_BIU_RST_CTL_LBN 60
-#define	FRF_BB_BIU_RST_CTL_WIDTH 1
-#define	FRF_AB_PCIE_STKY_RST_CTL_LBN 59
-#define	FRF_AB_PCIE_STKY_RST_CTL_WIDTH 1
-#define	FRF_AB_PCIE_NSTKY_RST_CTL_LBN 58
-#define	FRF_AB_PCIE_NSTKY_RST_CTL_WIDTH 1
-#define	FRF_AB_PCIE_CORE_RST_CTL_LBN 57
-#define	FRF_AB_PCIE_CORE_RST_CTL_WIDTH 1
-#define	FRF_AB_XGRX_RST_CTL_LBN 56
-#define	FRF_AB_XGRX_RST_CTL_WIDTH 1
-#define	FRF_AB_XGTX_RST_CTL_LBN 55
-#define	FRF_AB_XGTX_RST_CTL_WIDTH 1
-#define	FRF_AB_EM_RST_CTL_LBN 54
-#define	FRF_AB_EM_RST_CTL_WIDTH 1
-#define	FRF_AB_EV_RST_CTL_LBN 53
-#define	FRF_AB_EV_RST_CTL_WIDTH 1
-#define	FRF_AB_SR_RST_CTL_LBN 52
-#define	FRF_AB_SR_RST_CTL_WIDTH 1
-#define	FRF_AB_RX_RST_CTL_LBN 51
-#define	FRF_AB_RX_RST_CTL_WIDTH 1
-#define	FRF_AB_TX_RST_CTL_LBN 50
-#define	FRF_AB_TX_RST_CTL_WIDTH 1
-#define	FRF_AB_EE_RST_CTL_LBN 49
-#define	FRF_AB_EE_RST_CTL_WIDTH 1
-#define	FRF_AB_CS_RST_CTL_LBN 48
-#define	FRF_AB_CS_RST_CTL_WIDTH 1
-#define	FRF_AB_HOT_RST_CTL_LBN 40
-#define	FRF_AB_HOT_RST_CTL_WIDTH 2
-#define	FRF_AB_RST_EXT_PHY_LBN 31
-#define	FRF_AB_RST_EXT_PHY_WIDTH 1
-#define	FRF_AB_RST_XAUI_SD_LBN 30
-#define	FRF_AB_RST_XAUI_SD_WIDTH 1
-#define	FRF_AB_RST_PCIE_SD_LBN 29
-#define	FRF_AB_RST_PCIE_SD_WIDTH 1
-#define	FRF_AA_RST_PCIX_LBN 28
-#define	FRF_AA_RST_PCIX_WIDTH 1
-#define	FRF_BB_RST_BIU_LBN 28
-#define	FRF_BB_RST_BIU_WIDTH 1
-#define	FRF_AB_RST_PCIE_STKY_LBN 27
-#define	FRF_AB_RST_PCIE_STKY_WIDTH 1
-#define	FRF_AB_RST_PCIE_NSTKY_LBN 26
-#define	FRF_AB_RST_PCIE_NSTKY_WIDTH 1
-#define	FRF_AB_RST_PCIE_CORE_LBN 25
-#define	FRF_AB_RST_PCIE_CORE_WIDTH 1
-#define	FRF_AB_RST_XGRX_LBN 24
-#define	FRF_AB_RST_XGRX_WIDTH 1
-#define	FRF_AB_RST_XGTX_LBN 23
-#define	FRF_AB_RST_XGTX_WIDTH 1
-#define	FRF_AB_RST_EM_LBN 22
-#define	FRF_AB_RST_EM_WIDTH 1
-#define	FRF_AB_RST_EV_LBN 21
-#define	FRF_AB_RST_EV_WIDTH 1
-#define	FRF_AB_RST_SR_LBN 20
-#define	FRF_AB_RST_SR_WIDTH 1
-#define	FRF_AB_RST_RX_LBN 19
-#define	FRF_AB_RST_RX_WIDTH 1
-#define	FRF_AB_RST_TX_LBN 18
-#define	FRF_AB_RST_TX_WIDTH 1
-#define	FRF_AB_RST_SF_LBN 17
-#define	FRF_AB_RST_SF_WIDTH 1
-#define	FRF_AB_RST_CS_LBN 16
-#define	FRF_AB_RST_CS_WIDTH 1
-#define	FRF_AB_INT_RST_DUR_LBN 4
-#define	FRF_AB_INT_RST_DUR_WIDTH 3
-#define	FRF_AB_EXT_PHY_RST_DUR_LBN 1
-#define	FRF_AB_EXT_PHY_RST_DUR_WIDTH 3
-#define	FFE_AB_EXT_PHY_RST_DUR_10240US 7
-#define	FFE_AB_EXT_PHY_RST_DUR_5120US 6
-#define	FFE_AB_EXT_PHY_RST_DUR_2560US 5
-#define	FFE_AB_EXT_PHY_RST_DUR_1280US 4
-#define	FFE_AB_EXT_PHY_RST_DUR_640US 3
-#define	FFE_AB_EXT_PHY_RST_DUR_320US 2
-#define	FFE_AB_EXT_PHY_RST_DUR_160US 1
-#define	FFE_AB_EXT_PHY_RST_DUR_80US 0
-#define	FRF_AB_SWRST_LBN 0
-#define	FRF_AB_SWRST_WIDTH 1
-
-/* FATAL_INTR_REG_KER: Fatal interrupt register for Kernel */
-#define	FR_AZ_FATAL_INTR_KER 0x00000230
-#define	FRF_CZ_SRAM_PERR_INT_P_KER_EN_LBN 44
-#define	FRF_CZ_SRAM_PERR_INT_P_KER_EN_WIDTH 1
-#define	FRF_AB_PCI_BUSERR_INT_KER_EN_LBN 43
-#define	FRF_AB_PCI_BUSERR_INT_KER_EN_WIDTH 1
-#define	FRF_CZ_MBU_PERR_INT_KER_EN_LBN 43
-#define	FRF_CZ_MBU_PERR_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_SRAM_OOB_INT_KER_EN_LBN 42
-#define	FRF_AZ_SRAM_OOB_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_BUFID_OOB_INT_KER_EN_LBN 41
-#define	FRF_AZ_BUFID_OOB_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_MEM_PERR_INT_KER_EN_LBN 40
-#define	FRF_AZ_MEM_PERR_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_RBUF_OWN_INT_KER_EN_LBN 39
-#define	FRF_AZ_RBUF_OWN_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_TBUF_OWN_INT_KER_EN_LBN 38
-#define	FRF_AZ_TBUF_OWN_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_RDESCQ_OWN_INT_KER_EN_LBN 37
-#define	FRF_AZ_RDESCQ_OWN_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_TDESCQ_OWN_INT_KER_EN_LBN 36
-#define	FRF_AZ_TDESCQ_OWN_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_EVQ_OWN_INT_KER_EN_LBN 35
-#define	FRF_AZ_EVQ_OWN_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_EVF_OFLO_INT_KER_EN_LBN 34
-#define	FRF_AZ_EVF_OFLO_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_ILL_ADR_INT_KER_EN_LBN 33
-#define	FRF_AZ_ILL_ADR_INT_KER_EN_WIDTH 1
-#define	FRF_AZ_SRM_PERR_INT_KER_EN_LBN 32
-#define	FRF_AZ_SRM_PERR_INT_KER_EN_WIDTH 1
-#define	FRF_CZ_SRAM_PERR_INT_P_KER_LBN 12
-#define	FRF_CZ_SRAM_PERR_INT_P_KER_WIDTH 1
-#define	FRF_AB_PCI_BUSERR_INT_KER_LBN 11
-#define	FRF_AB_PCI_BUSERR_INT_KER_WIDTH 1
-#define	FRF_CZ_MBU_PERR_INT_KER_LBN 11
-#define	FRF_CZ_MBU_PERR_INT_KER_WIDTH 1
-#define	FRF_AZ_SRAM_OOB_INT_KER_LBN 10
-#define	FRF_AZ_SRAM_OOB_INT_KER_WIDTH 1
-#define	FRF_AZ_BUFID_DC_OOB_INT_KER_LBN 9
-#define	FRF_AZ_BUFID_DC_OOB_INT_KER_WIDTH 1
-#define	FRF_AZ_MEM_PERR_INT_KER_LBN 8
-#define	FRF_AZ_MEM_PERR_INT_KER_WIDTH 1
-#define	FRF_AZ_RBUF_OWN_INT_KER_LBN 7
-#define	FRF_AZ_RBUF_OWN_INT_KER_WIDTH 1
-#define	FRF_AZ_TBUF_OWN_INT_KER_LBN 6
-#define	FRF_AZ_TBUF_OWN_INT_KER_WIDTH 1
-#define	FRF_AZ_RDESCQ_OWN_INT_KER_LBN 5
-#define	FRF_AZ_RDESCQ_OWN_INT_KER_WIDTH 1
-#define	FRF_AZ_TDESCQ_OWN_INT_KER_LBN 4
-#define	FRF_AZ_TDESCQ_OWN_INT_KER_WIDTH 1
-#define	FRF_AZ_EVQ_OWN_INT_KER_LBN 3
-#define	FRF_AZ_EVQ_OWN_INT_KER_WIDTH 1
-#define	FRF_AZ_EVF_OFLO_INT_KER_LBN 2
-#define	FRF_AZ_EVF_OFLO_INT_KER_WIDTH 1
-#define	FRF_AZ_ILL_ADR_INT_KER_LBN 1
-#define	FRF_AZ_ILL_ADR_INT_KER_WIDTH 1
-#define	FRF_AZ_SRM_PERR_INT_KER_LBN 0
-#define	FRF_AZ_SRM_PERR_INT_KER_WIDTH 1
-
-/* FATAL_INTR_REG_CHAR: Fatal interrupt register for Char */
-#define	FR_BZ_FATAL_INTR_CHAR 0x00000240
-#define	FRF_CZ_SRAM_PERR_INT_P_CHAR_EN_LBN 44
-#define	FRF_CZ_SRAM_PERR_INT_P_CHAR_EN_WIDTH 1
-#define	FRF_BB_PCI_BUSERR_INT_CHAR_EN_LBN 43
-#define	FRF_BB_PCI_BUSERR_INT_CHAR_EN_WIDTH 1
-#define	FRF_CZ_MBU_PERR_INT_CHAR_EN_LBN 43
-#define	FRF_CZ_MBU_PERR_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_SRAM_OOB_INT_CHAR_EN_LBN 42
-#define	FRF_BZ_SRAM_OOB_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_BUFID_OOB_INT_CHAR_EN_LBN 41
-#define	FRF_BZ_BUFID_OOB_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_MEM_PERR_INT_CHAR_EN_LBN 40
-#define	FRF_BZ_MEM_PERR_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_RBUF_OWN_INT_CHAR_EN_LBN 39
-#define	FRF_BZ_RBUF_OWN_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_TBUF_OWN_INT_CHAR_EN_LBN 38
-#define	FRF_BZ_TBUF_OWN_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_RDESCQ_OWN_INT_CHAR_EN_LBN 37
-#define	FRF_BZ_RDESCQ_OWN_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_TDESCQ_OWN_INT_CHAR_EN_LBN 36
-#define	FRF_BZ_TDESCQ_OWN_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_EVQ_OWN_INT_CHAR_EN_LBN 35
-#define	FRF_BZ_EVQ_OWN_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_EVF_OFLO_INT_CHAR_EN_LBN 34
-#define	FRF_BZ_EVF_OFLO_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_ILL_ADR_INT_CHAR_EN_LBN 33
-#define	FRF_BZ_ILL_ADR_INT_CHAR_EN_WIDTH 1
-#define	FRF_BZ_SRM_PERR_INT_CHAR_EN_LBN 32
-#define	FRF_BZ_SRM_PERR_INT_CHAR_EN_WIDTH 1
-#define	FRF_CZ_SRAM_PERR_INT_P_CHAR_LBN 12
-#define	FRF_CZ_SRAM_PERR_INT_P_CHAR_WIDTH 1
-#define	FRF_BB_PCI_BUSERR_INT_CHAR_LBN 11
-#define	FRF_BB_PCI_BUSERR_INT_CHAR_WIDTH 1
-#define	FRF_CZ_MBU_PERR_INT_CHAR_LBN 11
-#define	FRF_CZ_MBU_PERR_INT_CHAR_WIDTH 1
-#define	FRF_BZ_SRAM_OOB_INT_CHAR_LBN 10
-#define	FRF_BZ_SRAM_OOB_INT_CHAR_WIDTH 1
-#define	FRF_BZ_BUFID_DC_OOB_INT_CHAR_LBN 9
-#define	FRF_BZ_BUFID_DC_OOB_INT_CHAR_WIDTH 1
-#define	FRF_BZ_MEM_PERR_INT_CHAR_LBN 8
-#define	FRF_BZ_MEM_PERR_INT_CHAR_WIDTH 1
-#define	FRF_BZ_RBUF_OWN_INT_CHAR_LBN 7
-#define	FRF_BZ_RBUF_OWN_INT_CHAR_WIDTH 1
-#define	FRF_BZ_TBUF_OWN_INT_CHAR_LBN 6
-#define	FRF_BZ_TBUF_OWN_INT_CHAR_WIDTH 1
-#define	FRF_BZ_RDESCQ_OWN_INT_CHAR_LBN 5
-#define	FRF_BZ_RDESCQ_OWN_INT_CHAR_WIDTH 1
-#define	FRF_BZ_TDESCQ_OWN_INT_CHAR_LBN 4
-#define	FRF_BZ_TDESCQ_OWN_INT_CHAR_WIDTH 1
-#define	FRF_BZ_EVQ_OWN_INT_CHAR_LBN 3
-#define	FRF_BZ_EVQ_OWN_INT_CHAR_WIDTH 1
-#define	FRF_BZ_EVF_OFLO_INT_CHAR_LBN 2
-#define	FRF_BZ_EVF_OFLO_INT_CHAR_WIDTH 1
-#define	FRF_BZ_ILL_ADR_INT_CHAR_LBN 1
-#define	FRF_BZ_ILL_ADR_INT_CHAR_WIDTH 1
-#define	FRF_BZ_SRM_PERR_INT_CHAR_LBN 0
-#define	FRF_BZ_SRM_PERR_INT_CHAR_WIDTH 1
-
-/* DP_CTRL_REG: Datapath control register */
-#define	FR_BZ_DP_CTRL 0x00000250
-#define	FRF_BZ_FLS_EVQ_ID_LBN 0
-#define	FRF_BZ_FLS_EVQ_ID_WIDTH 12
-
-/* MEM_STAT_REG: Memory status register */
-#define	FR_AZ_MEM_STAT 0x00000260
-#define	FRF_AB_MEM_PERR_VEC_LBN 53
-#define	FRF_AB_MEM_PERR_VEC_WIDTH 38
-#define	FRF_AB_MBIST_CORR_LBN 38
-#define	FRF_AB_MBIST_CORR_WIDTH 15
-#define	FRF_AB_MBIST_ERR_LBN 0
-#define	FRF_AB_MBIST_ERR_WIDTH 40
-#define	FRF_CZ_MEM_PERR_VEC_LBN 0
-#define	FRF_CZ_MEM_PERR_VEC_WIDTH 35
-
-/* CS_DEBUG_REG: Debug register */
-#define	FR_AZ_CS_DEBUG 0x00000270
-#define	FRF_AB_GLB_DEBUG2_SEL_LBN 50
-#define	FRF_AB_GLB_DEBUG2_SEL_WIDTH 3
-#define	FRF_AB_DEBUG_BLK_SEL2_LBN 47
-#define	FRF_AB_DEBUG_BLK_SEL2_WIDTH 3
-#define	FRF_AB_DEBUG_BLK_SEL1_LBN 44
-#define	FRF_AB_DEBUG_BLK_SEL1_WIDTH 3
-#define	FRF_AB_DEBUG_BLK_SEL0_LBN 41
-#define	FRF_AB_DEBUG_BLK_SEL0_WIDTH 3
-#define	FRF_CZ_CS_PORT_NUM_LBN 40
-#define	FRF_CZ_CS_PORT_NUM_WIDTH 2
-#define	FRF_AB_MISC_DEBUG_ADDR_LBN 36
-#define	FRF_AB_MISC_DEBUG_ADDR_WIDTH 5
-#define	FRF_AB_SERDES_DEBUG_ADDR_LBN 31
-#define	FRF_AB_SERDES_DEBUG_ADDR_WIDTH 5
-#define	FRF_CZ_CS_PORT_FPE_LBN 1
-#define	FRF_CZ_CS_PORT_FPE_WIDTH 35
-#define	FRF_AB_EM_DEBUG_ADDR_LBN 26
-#define	FRF_AB_EM_DEBUG_ADDR_WIDTH 5
-#define	FRF_AB_SR_DEBUG_ADDR_LBN 21
-#define	FRF_AB_SR_DEBUG_ADDR_WIDTH 5
-#define	FRF_AB_EV_DEBUG_ADDR_LBN 16
-#define	FRF_AB_EV_DEBUG_ADDR_WIDTH 5
-#define	FRF_AB_RX_DEBUG_ADDR_LBN 11
-#define	FRF_AB_RX_DEBUG_ADDR_WIDTH 5
-#define	FRF_AB_TX_DEBUG_ADDR_LBN 6
-#define	FRF_AB_TX_DEBUG_ADDR_WIDTH 5
-#define	FRF_AB_CS_BIU_DEBUG_ADDR_LBN 1
-#define	FRF_AB_CS_BIU_DEBUG_ADDR_WIDTH 5
-#define	FRF_AZ_CS_DEBUG_EN_LBN 0
-#define	FRF_AZ_CS_DEBUG_EN_WIDTH 1
-
-/* DRIVER_REG: Driver scratch register [0-7] */
-#define	FR_AZ_DRIVER 0x00000280
-#define	FR_AZ_DRIVER_STEP 16
-#define	FR_AZ_DRIVER_ROWS 8
-#define	FRF_AZ_DRIVER_DW0_LBN 0
-#define	FRF_AZ_DRIVER_DW0_WIDTH 32
-
-/* ALTERA_BUILD_REG: Altera build register */
-#define	FR_AZ_ALTERA_BUILD 0x00000300
-#define	FRF_AZ_ALTERA_BUILD_VER_LBN 0
-#define	FRF_AZ_ALTERA_BUILD_VER_WIDTH 32
-
-/* CSR_SPARE_REG: Spare register */
-#define	FR_AZ_CSR_SPARE 0x00000310
-#define	FRF_AB_MEM_PERR_EN_LBN 64
-#define	FRF_AB_MEM_PERR_EN_WIDTH 38
-#define	FRF_CZ_MEM_PERR_EN_LBN 64
-#define	FRF_CZ_MEM_PERR_EN_WIDTH 35
-#define	FRF_AB_MEM_PERR_EN_TX_DATA_LBN 72
-#define	FRF_AB_MEM_PERR_EN_TX_DATA_WIDTH 2
-#define	FRF_AZ_CSR_SPARE_BITS_LBN 0
-#define	FRF_AZ_CSR_SPARE_BITS_WIDTH 32
-
-/* PCIE_SD_CTL0123_REG: PCIE SerDes control register 0 to 3 */
-#define	FR_AB_PCIE_SD_CTL0123 0x00000320
-#define	FRF_AB_PCIE_TESTSIG_H_LBN 96
-#define	FRF_AB_PCIE_TESTSIG_H_WIDTH 19
-#define	FRF_AB_PCIE_TESTSIG_L_LBN 64
-#define	FRF_AB_PCIE_TESTSIG_L_WIDTH 19
-#define	FRF_AB_PCIE_OFFSET_LBN 56
-#define	FRF_AB_PCIE_OFFSET_WIDTH 8
-#define	FRF_AB_PCIE_OFFSETEN_H_LBN 55
-#define	FRF_AB_PCIE_OFFSETEN_H_WIDTH 1
-#define	FRF_AB_PCIE_OFFSETEN_L_LBN 54
-#define	FRF_AB_PCIE_OFFSETEN_L_WIDTH 1
-#define	FRF_AB_PCIE_HIVMODE_H_LBN 53
-#define	FRF_AB_PCIE_HIVMODE_H_WIDTH 1
-#define	FRF_AB_PCIE_HIVMODE_L_LBN 52
-#define	FRF_AB_PCIE_HIVMODE_L_WIDTH 1
-#define	FRF_AB_PCIE_PARRESET_H_LBN 51
-#define	FRF_AB_PCIE_PARRESET_H_WIDTH 1
-#define	FRF_AB_PCIE_PARRESET_L_LBN 50
-#define	FRF_AB_PCIE_PARRESET_L_WIDTH 1
-#define	FRF_AB_PCIE_LPBKWDRV_H_LBN 49
-#define	FRF_AB_PCIE_LPBKWDRV_H_WIDTH 1
-#define	FRF_AB_PCIE_LPBKWDRV_L_LBN 48
-#define	FRF_AB_PCIE_LPBKWDRV_L_WIDTH 1
-#define	FRF_AB_PCIE_LPBK_LBN 40
-#define	FRF_AB_PCIE_LPBK_WIDTH 8
-#define	FRF_AB_PCIE_PARLPBK_LBN 32
-#define	FRF_AB_PCIE_PARLPBK_WIDTH 8
-#define	FRF_AB_PCIE_RXTERMADJ_H_LBN 30
-#define	FRF_AB_PCIE_RXTERMADJ_H_WIDTH 2
-#define	FRF_AB_PCIE_RXTERMADJ_L_LBN 28
-#define	FRF_AB_PCIE_RXTERMADJ_L_WIDTH 2
-#define	FFE_AB_PCIE_RXTERMADJ_MIN15PCNT 3
-#define	FFE_AB_PCIE_RXTERMADJ_PL10PCNT 2
-#define	FFE_AB_PCIE_RXTERMADJ_MIN17PCNT 1
-#define	FFE_AB_PCIE_RXTERMADJ_NOMNL 0
-#define	FRF_AB_PCIE_TXTERMADJ_H_LBN 26
-#define	FRF_AB_PCIE_TXTERMADJ_H_WIDTH 2
-#define	FRF_AB_PCIE_TXTERMADJ_L_LBN 24
-#define	FRF_AB_PCIE_TXTERMADJ_L_WIDTH 2
-#define	FFE_AB_PCIE_TXTERMADJ_MIN15PCNT 3
-#define	FFE_AB_PCIE_TXTERMADJ_PL10PCNT 2
-#define	FFE_AB_PCIE_TXTERMADJ_MIN17PCNT 1
-#define	FFE_AB_PCIE_TXTERMADJ_NOMNL 0
-#define	FRF_AB_PCIE_RXEQCTL_H_LBN 18
-#define	FRF_AB_PCIE_RXEQCTL_H_WIDTH 2
-#define	FRF_AB_PCIE_RXEQCTL_L_LBN 16
-#define	FRF_AB_PCIE_RXEQCTL_L_WIDTH 2
-#define	FFE_AB_PCIE_RXEQCTL_OFF_ALT 3
-#define	FFE_AB_PCIE_RXEQCTL_OFF 2
-#define	FFE_AB_PCIE_RXEQCTL_MIN 1
-#define	FFE_AB_PCIE_RXEQCTL_MAX 0
-#define	FRF_AB_PCIE_HIDRV_LBN 8
-#define	FRF_AB_PCIE_HIDRV_WIDTH 8
-#define	FRF_AB_PCIE_LODRV_LBN 0
-#define	FRF_AB_PCIE_LODRV_WIDTH 8
-
-/* PCIE_SD_CTL45_REG: PCIE SerDes control register 4 and 5 */
-#define	FR_AB_PCIE_SD_CTL45 0x00000330
-#define	FRF_AB_PCIE_DTX7_LBN 60
-#define	FRF_AB_PCIE_DTX7_WIDTH 4
-#define	FRF_AB_PCIE_DTX6_LBN 56
-#define	FRF_AB_PCIE_DTX6_WIDTH 4
-#define	FRF_AB_PCIE_DTX5_LBN 52
-#define	FRF_AB_PCIE_DTX5_WIDTH 4
-#define	FRF_AB_PCIE_DTX4_LBN 48
-#define	FRF_AB_PCIE_DTX4_WIDTH 4
-#define	FRF_AB_PCIE_DTX3_LBN 44
-#define	FRF_AB_PCIE_DTX3_WIDTH 4
-#define	FRF_AB_PCIE_DTX2_LBN 40
-#define	FRF_AB_PCIE_DTX2_WIDTH 4
-#define	FRF_AB_PCIE_DTX1_LBN 36
-#define	FRF_AB_PCIE_DTX1_WIDTH 4
-#define	FRF_AB_PCIE_DTX0_LBN 32
-#define	FRF_AB_PCIE_DTX0_WIDTH 4
-#define	FRF_AB_PCIE_DEQ7_LBN 28
-#define	FRF_AB_PCIE_DEQ7_WIDTH 4
-#define	FRF_AB_PCIE_DEQ6_LBN 24
-#define	FRF_AB_PCIE_DEQ6_WIDTH 4
-#define	FRF_AB_PCIE_DEQ5_LBN 20
-#define	FRF_AB_PCIE_DEQ5_WIDTH 4
-#define	FRF_AB_PCIE_DEQ4_LBN 16
-#define	FRF_AB_PCIE_DEQ4_WIDTH 4
-#define	FRF_AB_PCIE_DEQ3_LBN 12
-#define	FRF_AB_PCIE_DEQ3_WIDTH 4
-#define	FRF_AB_PCIE_DEQ2_LBN 8
-#define	FRF_AB_PCIE_DEQ2_WIDTH 4
-#define	FRF_AB_PCIE_DEQ1_LBN 4
-#define	FRF_AB_PCIE_DEQ1_WIDTH 4
-#define	FRF_AB_PCIE_DEQ0_LBN 0
-#define	FRF_AB_PCIE_DEQ0_WIDTH 4
-
-/* PCIE_PCS_CTL_STAT_REG: PCIE PCS control and status register */
-#define	FR_AB_PCIE_PCS_CTL_STAT 0x00000340
-#define	FRF_AB_PCIE_PRBSERRCOUNT0_H_LBN 52
-#define	FRF_AB_PCIE_PRBSERRCOUNT0_H_WIDTH 4
-#define	FRF_AB_PCIE_PRBSERRCOUNT0_L_LBN 48
-#define	FRF_AB_PCIE_PRBSERRCOUNT0_L_WIDTH 4
-#define	FRF_AB_PCIE_PRBSERR_LBN 40
-#define	FRF_AB_PCIE_PRBSERR_WIDTH 8
-#define	FRF_AB_PCIE_PRBSERRH0_LBN 32
-#define	FRF_AB_PCIE_PRBSERRH0_WIDTH 8
-#define	FRF_AB_PCIE_FASTINIT_H_LBN 15
-#define	FRF_AB_PCIE_FASTINIT_H_WIDTH 1
-#define	FRF_AB_PCIE_FASTINIT_L_LBN 14
-#define	FRF_AB_PCIE_FASTINIT_L_WIDTH 1
-#define	FRF_AB_PCIE_CTCDISABLE_H_LBN 13
-#define	FRF_AB_PCIE_CTCDISABLE_H_WIDTH 1
-#define	FRF_AB_PCIE_CTCDISABLE_L_LBN 12
-#define	FRF_AB_PCIE_CTCDISABLE_L_WIDTH 1
-#define	FRF_AB_PCIE_PRBSSYNC_H_LBN 11
-#define	FRF_AB_PCIE_PRBSSYNC_H_WIDTH 1
-#define	FRF_AB_PCIE_PRBSSYNC_L_LBN 10
-#define	FRF_AB_PCIE_PRBSSYNC_L_WIDTH 1
-#define	FRF_AB_PCIE_PRBSERRACK_H_LBN 9
-#define	FRF_AB_PCIE_PRBSERRACK_H_WIDTH 1
-#define	FRF_AB_PCIE_PRBSERRACK_L_LBN 8
-#define	FRF_AB_PCIE_PRBSERRACK_L_WIDTH 1
-#define	FRF_AB_PCIE_PRBSSEL_LBN 0
-#define	FRF_AB_PCIE_PRBSSEL_WIDTH 8
-
-/* DEBUG_DATA_OUT_REG: Live Debug and Debug 2 out ports */
-#define	FR_BB_DEBUG_DATA_OUT 0x00000350
-#define	FRF_BB_DEBUG2_PORT_LBN 25
-#define	FRF_BB_DEBUG2_PORT_WIDTH 15
-#define	FRF_BB_DEBUG1_PORT_LBN 0
-#define	FRF_BB_DEBUG1_PORT_WIDTH 25
-
-/* EVQ_RPTR_REGP0: Event queue read pointer register */
-#define	FR_BZ_EVQ_RPTR_P0 0x00000400
-#define	FR_BZ_EVQ_RPTR_P0_STEP 8192
-#define	FR_BZ_EVQ_RPTR_P0_ROWS 1024
-/* EVQ_RPTR_REG_KER: Event queue read pointer register */
-#define	FR_AA_EVQ_RPTR_KER 0x00011b00
-#define	FR_AA_EVQ_RPTR_KER_STEP 4
-#define	FR_AA_EVQ_RPTR_KER_ROWS 4
-/* EVQ_RPTR_REG: Event queue read pointer register */
-#define	FR_BZ_EVQ_RPTR 0x00fa0000
-#define	FR_BZ_EVQ_RPTR_STEP 16
-#define	FR_BB_EVQ_RPTR_ROWS 4096
-#define	FR_CZ_EVQ_RPTR_ROWS 1024
-/* EVQ_RPTR_REGP123: Event queue read pointer register */
-#define	FR_BB_EVQ_RPTR_P123 0x01000400
-#define	FR_BB_EVQ_RPTR_P123_STEP 8192
-#define	FR_BB_EVQ_RPTR_P123_ROWS 3072
-#define	FRF_AZ_EVQ_RPTR_VLD_LBN 15
-#define	FRF_AZ_EVQ_RPTR_VLD_WIDTH 1
-#define	FRF_AZ_EVQ_RPTR_LBN 0
-#define	FRF_AZ_EVQ_RPTR_WIDTH 15
-
-/* TIMER_COMMAND_REGP0: Timer Command Registers */
-#define	FR_BZ_TIMER_COMMAND_P0 0x00000420
-#define	FR_BZ_TIMER_COMMAND_P0_STEP 8192
-#define	FR_BZ_TIMER_COMMAND_P0_ROWS 1024
-/* TIMER_COMMAND_REG_KER: Timer Command Registers */
-#define	FR_AA_TIMER_COMMAND_KER 0x00000420
-#define	FR_AA_TIMER_COMMAND_KER_STEP 8192
-#define	FR_AA_TIMER_COMMAND_KER_ROWS 4
-/* TIMER_COMMAND_REGP123: Timer Command Registers */
-#define	FR_BB_TIMER_COMMAND_P123 0x01000420
-#define	FR_BB_TIMER_COMMAND_P123_STEP 8192
-#define	FR_BB_TIMER_COMMAND_P123_ROWS 3072
-#define	FRF_CZ_TC_TIMER_MODE_LBN 14
-#define	FRF_CZ_TC_TIMER_MODE_WIDTH 2
-#define	FRF_AB_TC_TIMER_MODE_LBN 12
-#define	FRF_AB_TC_TIMER_MODE_WIDTH 2
-#define	FRF_CZ_TC_TIMER_VAL_LBN 0
-#define	FRF_CZ_TC_TIMER_VAL_WIDTH 14
-#define	FRF_AB_TC_TIMER_VAL_LBN 0
-#define	FRF_AB_TC_TIMER_VAL_WIDTH 12
-
-/* DRV_EV_REG: Driver generated event register */
-#define	FR_AZ_DRV_EV 0x00000440
-#define	FRF_AZ_DRV_EV_QID_LBN 64
-#define	FRF_AZ_DRV_EV_QID_WIDTH 12
-#define	FRF_AZ_DRV_EV_DATA_LBN 0
-#define	FRF_AZ_DRV_EV_DATA_WIDTH 64
-
-/* EVQ_CTL_REG: Event queue control register */
-#define	FR_AZ_EVQ_CTL 0x00000450
-#define	FRF_CZ_RX_EVQ_WAKEUP_MASK_LBN 15
-#define	FRF_CZ_RX_EVQ_WAKEUP_MASK_WIDTH 10
-#define	FRF_BB_RX_EVQ_WAKEUP_MASK_LBN 15
-#define	FRF_BB_RX_EVQ_WAKEUP_MASK_WIDTH 6
-#define	FRF_AZ_EVQ_OWNERR_CTL_LBN 14
-#define	FRF_AZ_EVQ_OWNERR_CTL_WIDTH 1
-#define	FRF_AZ_EVQ_FIFO_AF_TH_LBN 7
-#define	FRF_AZ_EVQ_FIFO_AF_TH_WIDTH 7
-#define	FRF_AZ_EVQ_FIFO_NOTAF_TH_LBN 0
-#define	FRF_AZ_EVQ_FIFO_NOTAF_TH_WIDTH 7
-
-/* EVQ_CNT1_REG: Event counter 1 register */
-#define	FR_AZ_EVQ_CNT1 0x00000460
-#define	FRF_AZ_EVQ_CNT_PRE_FIFO_LBN 120
-#define	FRF_AZ_EVQ_CNT_PRE_FIFO_WIDTH 7
-#define	FRF_AZ_EVQ_CNT_TOBIU_LBN 100
-#define	FRF_AZ_EVQ_CNT_TOBIU_WIDTH 20
-#define	FRF_AZ_EVQ_TX_REQ_CNT_LBN 80
-#define	FRF_AZ_EVQ_TX_REQ_CNT_WIDTH 20
-#define	FRF_AZ_EVQ_RX_REQ_CNT_LBN 60
-#define	FRF_AZ_EVQ_RX_REQ_CNT_WIDTH 20
-#define	FRF_AZ_EVQ_EM_REQ_CNT_LBN 40
-#define	FRF_AZ_EVQ_EM_REQ_CNT_WIDTH 20
-#define	FRF_AZ_EVQ_CSR_REQ_CNT_LBN 20
-#define	FRF_AZ_EVQ_CSR_REQ_CNT_WIDTH 20
-#define	FRF_AZ_EVQ_ERR_REQ_CNT_LBN 0
-#define	FRF_AZ_EVQ_ERR_REQ_CNT_WIDTH 20
-
-/* EVQ_CNT2_REG: Event counter 2 register */
-#define	FR_AZ_EVQ_CNT2 0x00000470
-#define	FRF_AZ_EVQ_UPD_REQ_CNT_LBN 104
-#define	FRF_AZ_EVQ_UPD_REQ_CNT_WIDTH 20
-#define	FRF_AZ_EVQ_CLR_REQ_CNT_LBN 84
-#define	FRF_AZ_EVQ_CLR_REQ_CNT_WIDTH 20
-#define	FRF_AZ_EVQ_RDY_CNT_LBN 80
-#define	FRF_AZ_EVQ_RDY_CNT_WIDTH 4
-#define	FRF_AZ_EVQ_WU_REQ_CNT_LBN 60
-#define	FRF_AZ_EVQ_WU_REQ_CNT_WIDTH 20
-#define	FRF_AZ_EVQ_WET_REQ_CNT_LBN 40
-#define	FRF_AZ_EVQ_WET_REQ_CNT_WIDTH 20
-#define	FRF_AZ_EVQ_INIT_REQ_CNT_LBN 20
-#define	FRF_AZ_EVQ_INIT_REQ_CNT_WIDTH 20
-#define	FRF_AZ_EVQ_TM_REQ_CNT_LBN 0
-#define	FRF_AZ_EVQ_TM_REQ_CNT_WIDTH 20
-
-/* USR_EV_REG: Event mailbox register */
-#define	FR_CZ_USR_EV 0x00000540
-#define	FR_CZ_USR_EV_STEP 8192
-#define	FR_CZ_USR_EV_ROWS 1024
-#define	FRF_CZ_USR_EV_DATA_LBN 0
-#define	FRF_CZ_USR_EV_DATA_WIDTH 32
-
-/* BUF_TBL_CFG_REG: Buffer table configuration register */
-#define	FR_AZ_BUF_TBL_CFG 0x00000600
-#define	FRF_AZ_BUF_TBL_MODE_LBN 3
-#define	FRF_AZ_BUF_TBL_MODE_WIDTH 1
-
-/* SRM_RX_DC_CFG_REG: SRAM receive descriptor cache configuration register */
-#define	FR_AZ_SRM_RX_DC_CFG 0x00000610
-#define	FRF_AZ_SRM_CLK_TMP_EN_LBN 21
-#define	FRF_AZ_SRM_CLK_TMP_EN_WIDTH 1
-#define	FRF_AZ_SRM_RX_DC_BASE_ADR_LBN 0
-#define	FRF_AZ_SRM_RX_DC_BASE_ADR_WIDTH 21
-
-/* SRM_TX_DC_CFG_REG: SRAM transmit descriptor cache configuration register */
-#define	FR_AZ_SRM_TX_DC_CFG 0x00000620
-#define	FRF_AZ_SRM_TX_DC_BASE_ADR_LBN 0
-#define	FRF_AZ_SRM_TX_DC_BASE_ADR_WIDTH 21
-
-/* SRM_CFG_REG: SRAM configuration register */
-#define	FR_AZ_SRM_CFG 0x00000630
-#define	FRF_AZ_SRM_OOB_ADR_INTEN_LBN 5
-#define	FRF_AZ_SRM_OOB_ADR_INTEN_WIDTH 1
-#define	FRF_AZ_SRM_OOB_BUF_INTEN_LBN 4
-#define	FRF_AZ_SRM_OOB_BUF_INTEN_WIDTH 1
-#define	FRF_AZ_SRM_INIT_EN_LBN 3
-#define	FRF_AZ_SRM_INIT_EN_WIDTH 1
-#define	FRF_AZ_SRM_NUM_BANK_LBN 2
-#define	FRF_AZ_SRM_NUM_BANK_WIDTH 1
-#define	FRF_AZ_SRM_BANK_SIZE_LBN 0
-#define	FRF_AZ_SRM_BANK_SIZE_WIDTH 2
-
-/* BUF_TBL_UPD_REG: Buffer table update register */
-#define	FR_AZ_BUF_TBL_UPD 0x00000650
-#define	FRF_AZ_BUF_UPD_CMD_LBN 63
-#define	FRF_AZ_BUF_UPD_CMD_WIDTH 1
-#define	FRF_AZ_BUF_CLR_CMD_LBN 62
-#define	FRF_AZ_BUF_CLR_CMD_WIDTH 1
-#define	FRF_AZ_BUF_CLR_END_ID_LBN 32
-#define	FRF_AZ_BUF_CLR_END_ID_WIDTH 20
-#define	FRF_AZ_BUF_CLR_START_ID_LBN 0
-#define	FRF_AZ_BUF_CLR_START_ID_WIDTH 20
-
-/* SRM_UPD_EVQ_REG: Buffer table update register */
-#define	FR_AZ_SRM_UPD_EVQ 0x00000660
-#define	FRF_AZ_SRM_UPD_EVQ_ID_LBN 0
-#define	FRF_AZ_SRM_UPD_EVQ_ID_WIDTH 12
-
-/* SRAM_PARITY_REG: SRAM parity register. */
-#define	FR_AZ_SRAM_PARITY 0x00000670
-#define	FRF_CZ_BYPASS_ECC_LBN 3
-#define	FRF_CZ_BYPASS_ECC_WIDTH 1
-#define	FRF_CZ_SEC_INT_LBN 2
-#define	FRF_CZ_SEC_INT_WIDTH 1
-#define	FRF_CZ_FORCE_SRAM_DOUBLE_ERR_LBN 1
-#define	FRF_CZ_FORCE_SRAM_DOUBLE_ERR_WIDTH 1
-#define	FRF_AB_FORCE_SRAM_PERR_LBN 0
-#define	FRF_AB_FORCE_SRAM_PERR_WIDTH 1
-#define	FRF_CZ_FORCE_SRAM_SINGLE_ERR_LBN 0
-#define	FRF_CZ_FORCE_SRAM_SINGLE_ERR_WIDTH 1
-
-/* RX_CFG_REG: Receive configuration register */
-#define	FR_AZ_RX_CFG 0x00000800
-#define	FRF_CZ_RX_MIN_KBUF_SIZE_LBN 72
-#define	FRF_CZ_RX_MIN_KBUF_SIZE_WIDTH 14
-#define	FRF_CZ_RX_HDR_SPLIT_EN_LBN 71
-#define	FRF_CZ_RX_HDR_SPLIT_EN_WIDTH 1
-#define	FRF_CZ_RX_HDR_SPLIT_PLD_BUF_SIZE_LBN 62
-#define	FRF_CZ_RX_HDR_SPLIT_PLD_BUF_SIZE_WIDTH 9
-#define	FRF_CZ_RX_HDR_SPLIT_HDR_BUF_SIZE_LBN 53
-#define	FRF_CZ_RX_HDR_SPLIT_HDR_BUF_SIZE_WIDTH 9
-#define	FRF_CZ_RX_PRE_RFF_IPG_LBN 49
-#define	FRF_CZ_RX_PRE_RFF_IPG_WIDTH 4
-#define	FRF_BZ_RX_TCP_SUP_LBN 48
-#define	FRF_BZ_RX_TCP_SUP_WIDTH 1
-#define	FRF_BZ_RX_INGR_EN_LBN 47
-#define	FRF_BZ_RX_INGR_EN_WIDTH 1
-#define	FRF_BZ_RX_IP_HASH_LBN 46
-#define	FRF_BZ_RX_IP_HASH_WIDTH 1
-#define	FRF_BZ_RX_HASH_ALG_LBN 45
-#define	FRF_BZ_RX_HASH_ALG_WIDTH 1
-#define	FRF_BZ_RX_HASH_INSRT_HDR_LBN 44
-#define	FRF_BZ_RX_HASH_INSRT_HDR_WIDTH 1
-#define	FRF_BZ_RX_DESC_PUSH_EN_LBN 43
-#define	FRF_BZ_RX_DESC_PUSH_EN_WIDTH 1
-#define	FRF_BZ_RX_RDW_PATCH_EN_LBN 42
-#define	FRF_BZ_RX_RDW_PATCH_EN_WIDTH 1
-#define	FRF_BB_RX_PCI_BURST_SIZE_LBN 39
-#define	FRF_BB_RX_PCI_BURST_SIZE_WIDTH 3
-#define	FRF_BZ_RX_OWNERR_CTL_LBN 38
-#define	FRF_BZ_RX_OWNERR_CTL_WIDTH 1
-#define	FRF_BZ_RX_XON_TX_TH_LBN 33
-#define	FRF_BZ_RX_XON_TX_TH_WIDTH 5
-#define	FRF_AA_RX_DESC_PUSH_EN_LBN 35
-#define	FRF_AA_RX_DESC_PUSH_EN_WIDTH 1
-#define	FRF_AA_RX_RDW_PATCH_EN_LBN 34
-#define	FRF_AA_RX_RDW_PATCH_EN_WIDTH 1
-#define	FRF_AA_RX_PCI_BURST_SIZE_LBN 31
-#define	FRF_AA_RX_PCI_BURST_SIZE_WIDTH 3
-#define	FRF_BZ_RX_XOFF_TX_TH_LBN 28
-#define	FRF_BZ_RX_XOFF_TX_TH_WIDTH 5
-#define	FRF_AA_RX_OWNERR_CTL_LBN 30
-#define	FRF_AA_RX_OWNERR_CTL_WIDTH 1
-#define	FRF_AA_RX_XON_TX_TH_LBN 25
-#define	FRF_AA_RX_XON_TX_TH_WIDTH 5
-#define	FRF_BZ_RX_USR_BUF_SIZE_LBN 19
-#define	FRF_BZ_RX_USR_BUF_SIZE_WIDTH 9
-#define	FRF_AA_RX_XOFF_TX_TH_LBN 20
-#define	FRF_AA_RX_XOFF_TX_TH_WIDTH 5
-#define	FRF_AA_RX_USR_BUF_SIZE_LBN 11
-#define	FRF_AA_RX_USR_BUF_SIZE_WIDTH 9
-#define	FRF_BZ_RX_XON_MAC_TH_LBN 10
-#define	FRF_BZ_RX_XON_MAC_TH_WIDTH 9
-#define	FRF_AA_RX_XON_MAC_TH_LBN 6
-#define	FRF_AA_RX_XON_MAC_TH_WIDTH 5
-#define	FRF_BZ_RX_XOFF_MAC_TH_LBN 1
-#define	FRF_BZ_RX_XOFF_MAC_TH_WIDTH 9
-#define	FRF_AA_RX_XOFF_MAC_TH_LBN 1
-#define	FRF_AA_RX_XOFF_MAC_TH_WIDTH 5
-#define	FRF_AZ_RX_XOFF_MAC_EN_LBN 0
-#define	FRF_AZ_RX_XOFF_MAC_EN_WIDTH 1
-
-/* RX_FILTER_CTL_REG: Receive filter control registers */
-#define	FR_BZ_RX_FILTER_CTL 0x00000810
-#define	FRF_CZ_ETHERNET_WILDCARD_SEARCH_LIMIT_LBN 94
-#define	FRF_CZ_ETHERNET_WILDCARD_SEARCH_LIMIT_WIDTH 8
-#define	FRF_CZ_ETHERNET_FULL_SEARCH_LIMIT_LBN 86
-#define	FRF_CZ_ETHERNET_FULL_SEARCH_LIMIT_WIDTH 8
-#define	FRF_CZ_RX_FILTER_ALL_VLAN_ETHERTYPES_LBN 85
-#define	FRF_CZ_RX_FILTER_ALL_VLAN_ETHERTYPES_WIDTH 1
-#define	FRF_CZ_RX_VLAN_MATCH_ETHERTYPE_LBN 69
-#define	FRF_CZ_RX_VLAN_MATCH_ETHERTYPE_WIDTH 16
-#define	FRF_CZ_MULTICAST_NOMATCH_Q_ID_LBN 57
-#define	FRF_CZ_MULTICAST_NOMATCH_Q_ID_WIDTH 12
-#define	FRF_CZ_MULTICAST_NOMATCH_RSS_ENABLED_LBN 56
-#define	FRF_CZ_MULTICAST_NOMATCH_RSS_ENABLED_WIDTH 1
-#define	FRF_CZ_MULTICAST_NOMATCH_IP_OVERRIDE_LBN 55
-#define	FRF_CZ_MULTICAST_NOMATCH_IP_OVERRIDE_WIDTH 1
-#define	FRF_CZ_UNICAST_NOMATCH_Q_ID_LBN 43
-#define	FRF_CZ_UNICAST_NOMATCH_Q_ID_WIDTH 12
-#define	FRF_CZ_UNICAST_NOMATCH_RSS_ENABLED_LBN 42
-#define	FRF_CZ_UNICAST_NOMATCH_RSS_ENABLED_WIDTH 1
-#define	FRF_CZ_UNICAST_NOMATCH_IP_OVERRIDE_LBN 41
-#define	FRF_CZ_UNICAST_NOMATCH_IP_OVERRIDE_WIDTH 1
-#define	FRF_BZ_SCATTER_ENBL_NO_MATCH_Q_LBN 40
-#define	FRF_BZ_SCATTER_ENBL_NO_MATCH_Q_WIDTH 1
-#define	FRF_BZ_UDP_FULL_SRCH_LIMIT_LBN 32
-#define	FRF_BZ_UDP_FULL_SRCH_LIMIT_WIDTH 8
-#define	FRF_BZ_NUM_KER_LBN 24
-#define	FRF_BZ_NUM_KER_WIDTH 2
-#define	FRF_BZ_UDP_WILD_SRCH_LIMIT_LBN 16
-#define	FRF_BZ_UDP_WILD_SRCH_LIMIT_WIDTH 8
-#define	FRF_BZ_TCP_WILD_SRCH_LIMIT_LBN 8
-#define	FRF_BZ_TCP_WILD_SRCH_LIMIT_WIDTH 8
-#define	FRF_BZ_TCP_FULL_SRCH_LIMIT_LBN 0
-#define	FRF_BZ_TCP_FULL_SRCH_LIMIT_WIDTH 8
-
-/* RX_FLUSH_DESCQ_REG: Receive flush descriptor queue register */
-#define	FR_AZ_RX_FLUSH_DESCQ 0x00000820
-#define	FRF_AZ_RX_FLUSH_DESCQ_CMD_LBN 24
-#define	FRF_AZ_RX_FLUSH_DESCQ_CMD_WIDTH 1
-#define	FRF_AZ_RX_FLUSH_DESCQ_LBN 0
-#define	FRF_AZ_RX_FLUSH_DESCQ_WIDTH 12
-
-/* RX_DESC_UPD_REGP0: Receive descriptor update register. */
-#define	FR_BZ_RX_DESC_UPD_P0 0x00000830
-#define	FR_BZ_RX_DESC_UPD_P0_STEP 8192
-#define	FR_BZ_RX_DESC_UPD_P0_ROWS 1024
-/* RX_DESC_UPD_REG_KER: Receive descriptor update register. */
-#define	FR_AA_RX_DESC_UPD_KER 0x00000830
-#define	FR_AA_RX_DESC_UPD_KER_STEP 8192
-#define	FR_AA_RX_DESC_UPD_KER_ROWS 4
-/* RX_DESC_UPD_REGP123: Receive descriptor update register. */
-#define	FR_BB_RX_DESC_UPD_P123 0x01000830
-#define	FR_BB_RX_DESC_UPD_P123_STEP 8192
-#define	FR_BB_RX_DESC_UPD_P123_ROWS 3072
-#define	FRF_AZ_RX_DESC_WPTR_LBN 96
-#define	FRF_AZ_RX_DESC_WPTR_WIDTH 12
-#define	FRF_AZ_RX_DESC_PUSH_CMD_LBN 95
-#define	FRF_AZ_RX_DESC_PUSH_CMD_WIDTH 1
-#define	FRF_AZ_RX_DESC_LBN 0
-#define	FRF_AZ_RX_DESC_WIDTH 64
-
-/* RX_DC_CFG_REG: Receive descriptor cache configuration register */
-#define	FR_AZ_RX_DC_CFG 0x00000840
-#define	FRF_AB_RX_MAX_PF_LBN 2
-#define	FRF_AB_RX_MAX_PF_WIDTH 2
-#define	FRF_AZ_RX_DC_SIZE_LBN 0
-#define	FRF_AZ_RX_DC_SIZE_WIDTH 2
-#define	FFE_AZ_RX_DC_SIZE_64 3
-#define	FFE_AZ_RX_DC_SIZE_32 2
-#define	FFE_AZ_RX_DC_SIZE_16 1
-#define	FFE_AZ_RX_DC_SIZE_8 0
-
-/* RX_DC_PF_WM_REG: Receive descriptor cache pre-fetch watermark register */
-#define	FR_AZ_RX_DC_PF_WM 0x00000850
-#define	FRF_AZ_RX_DC_PF_HWM_LBN 6
-#define	FRF_AZ_RX_DC_PF_HWM_WIDTH 6
-#define	FRF_AZ_RX_DC_PF_LWM_LBN 0
-#define	FRF_AZ_RX_DC_PF_LWM_WIDTH 6
-
-/* RX_RSS_TKEY_REG: RSS Toeplitz hash key */
-#define	FR_BZ_RX_RSS_TKEY 0x00000860
-#define	FRF_BZ_RX_RSS_TKEY_HI_LBN 64
-#define	FRF_BZ_RX_RSS_TKEY_HI_WIDTH 64
-#define	FRF_BZ_RX_RSS_TKEY_LO_LBN 0
-#define	FRF_BZ_RX_RSS_TKEY_LO_WIDTH 64
-
-/* RX_NODESC_DROP_REG: Receive dropped packet counter register */
-#define	FR_AZ_RX_NODESC_DROP 0x00000880
-#define	FRF_CZ_RX_NODESC_DROP_CNT_LBN 0
-#define	FRF_CZ_RX_NODESC_DROP_CNT_WIDTH 32
-#define	FRF_AB_RX_NODESC_DROP_CNT_LBN 0
-#define	FRF_AB_RX_NODESC_DROP_CNT_WIDTH 16
-
-/* RX_SELF_RST_REG: Receive self reset register */
-#define	FR_AA_RX_SELF_RST 0x00000890
-#define	FRF_AA_RX_ISCSI_DIS_LBN 17
-#define	FRF_AA_RX_ISCSI_DIS_WIDTH 1
-#define	FRF_AA_RX_SW_RST_REG_LBN 16
-#define	FRF_AA_RX_SW_RST_REG_WIDTH 1
-#define FRF_AA_RX_NODESC_WAIT_DIS_LBN 9
-#define FRF_AA_RX_NODESC_WAIT_DIS_WIDTH 1
-#define	FRF_AA_RX_SELF_RST_EN_LBN 8
-#define	FRF_AA_RX_SELF_RST_EN_WIDTH 1
-#define	FRF_AA_RX_MAX_PF_LAT_LBN 4
-#define	FRF_AA_RX_MAX_PF_LAT_WIDTH 4
-#define	FRF_AA_RX_MAX_LU_LAT_LBN 0
-#define	FRF_AA_RX_MAX_LU_LAT_WIDTH 4
-
-/* RX_DEBUG_REG: undocumented register */
-#define	FR_AZ_RX_DEBUG 0x000008a0
-#define	FRF_AZ_RX_DEBUG_LBN 0
-#define	FRF_AZ_RX_DEBUG_WIDTH 64
-
-/* RX_PUSH_DROP_REG: Receive descriptor push dropped counter register */
-#define	FR_AZ_RX_PUSH_DROP 0x000008b0
-#define	FRF_AZ_RX_PUSH_DROP_CNT_LBN 0
-#define	FRF_AZ_RX_PUSH_DROP_CNT_WIDTH 32
-
-/* RX_RSS_IPV6_REG1: IPv6 RSS Toeplitz hash key low bytes */
-#define	FR_CZ_RX_RSS_IPV6_REG1 0x000008d0
-#define	FRF_CZ_RX_RSS_IPV6_TKEY_LO_LBN 0
-#define	FRF_CZ_RX_RSS_IPV6_TKEY_LO_WIDTH 128
-
-/* RX_RSS_IPV6_REG2: IPv6 RSS Toeplitz hash key middle bytes */
-#define	FR_CZ_RX_RSS_IPV6_REG2 0x000008e0
-#define	FRF_CZ_RX_RSS_IPV6_TKEY_MID_LBN 0
-#define	FRF_CZ_RX_RSS_IPV6_TKEY_MID_WIDTH 128
-
-/* RX_RSS_IPV6_REG3: IPv6 RSS Toeplitz hash key upper bytes and IPv6 RSS settings */
-#define	FR_CZ_RX_RSS_IPV6_REG3 0x000008f0
-#define	FRF_CZ_RX_RSS_IPV6_THASH_ENABLE_LBN 66
-#define	FRF_CZ_RX_RSS_IPV6_THASH_ENABLE_WIDTH 1
-#define	FRF_CZ_RX_RSS_IPV6_IP_THASH_ENABLE_LBN 65
-#define	FRF_CZ_RX_RSS_IPV6_IP_THASH_ENABLE_WIDTH 1
-#define	FRF_CZ_RX_RSS_IPV6_TCP_SUPPRESS_LBN 64
-#define	FRF_CZ_RX_RSS_IPV6_TCP_SUPPRESS_WIDTH 1
-#define	FRF_CZ_RX_RSS_IPV6_TKEY_HI_LBN 0
-#define	FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH 64
-
-/* TX_FLUSH_DESCQ_REG: Transmit flush descriptor queue register */
-#define	FR_AZ_TX_FLUSH_DESCQ 0x00000a00
-#define	FRF_AZ_TX_FLUSH_DESCQ_CMD_LBN 12
-#define	FRF_AZ_TX_FLUSH_DESCQ_CMD_WIDTH 1
-#define	FRF_AZ_TX_FLUSH_DESCQ_LBN 0
-#define	FRF_AZ_TX_FLUSH_DESCQ_WIDTH 12
-
-/* TX_DESC_UPD_REGP0: Transmit descriptor update register. */
-#define	FR_BZ_TX_DESC_UPD_P0 0x00000a10
-#define	FR_BZ_TX_DESC_UPD_P0_STEP 8192
-#define	FR_BZ_TX_DESC_UPD_P0_ROWS 1024
-/* TX_DESC_UPD_REG_KER: Transmit descriptor update register. */
-#define	FR_AA_TX_DESC_UPD_KER 0x00000a10
-#define	FR_AA_TX_DESC_UPD_KER_STEP 8192
-#define	FR_AA_TX_DESC_UPD_KER_ROWS 8
-/* TX_DESC_UPD_REGP123: Transmit descriptor update register. */
-#define	FR_BB_TX_DESC_UPD_P123 0x01000a10
-#define	FR_BB_TX_DESC_UPD_P123_STEP 8192
-#define	FR_BB_TX_DESC_UPD_P123_ROWS 3072
-#define	FRF_AZ_TX_DESC_WPTR_LBN 96
-#define	FRF_AZ_TX_DESC_WPTR_WIDTH 12
-#define	FRF_AZ_TX_DESC_PUSH_CMD_LBN 95
-#define	FRF_AZ_TX_DESC_PUSH_CMD_WIDTH 1
-#define	FRF_AZ_TX_DESC_LBN 0
-#define	FRF_AZ_TX_DESC_WIDTH 95
-
-/* TX_DC_CFG_REG: Transmit descriptor cache configuration register */
-#define	FR_AZ_TX_DC_CFG 0x00000a20
-#define	FRF_AZ_TX_DC_SIZE_LBN 0
-#define	FRF_AZ_TX_DC_SIZE_WIDTH 2
-#define	FFE_AZ_TX_DC_SIZE_32 2
-#define	FFE_AZ_TX_DC_SIZE_16 1
-#define	FFE_AZ_TX_DC_SIZE_8 0
-
-/* TX_CHKSM_CFG_REG: Transmit checksum configuration register */
-#define	FR_AA_TX_CHKSM_CFG 0x00000a30
-#define	FRF_AA_TX_Q_CHKSM_DIS_96_127_LBN 96
-#define	FRF_AA_TX_Q_CHKSM_DIS_96_127_WIDTH 32
-#define	FRF_AA_TX_Q_CHKSM_DIS_64_95_LBN 64
-#define	FRF_AA_TX_Q_CHKSM_DIS_64_95_WIDTH 32
-#define	FRF_AA_TX_Q_CHKSM_DIS_32_63_LBN 32
-#define	FRF_AA_TX_Q_CHKSM_DIS_32_63_WIDTH 32
-#define	FRF_AA_TX_Q_CHKSM_DIS_0_31_LBN 0
-#define	FRF_AA_TX_Q_CHKSM_DIS_0_31_WIDTH 32
-
-/* TX_CFG_REG: Transmit configuration register */
-#define	FR_AZ_TX_CFG 0x00000a50
-#define	FRF_CZ_TX_CONT_LOOKUP_THRESH_RANGE_LBN 114
-#define	FRF_CZ_TX_CONT_LOOKUP_THRESH_RANGE_WIDTH 8
-#define	FRF_CZ_TX_FILTER_TEST_MODE_BIT_LBN 113
-#define	FRF_CZ_TX_FILTER_TEST_MODE_BIT_WIDTH 1
-#define	FRF_CZ_TX_ETH_FILTER_WILD_SEARCH_RANGE_LBN 105
-#define	FRF_CZ_TX_ETH_FILTER_WILD_SEARCH_RANGE_WIDTH 8
-#define	FRF_CZ_TX_ETH_FILTER_FULL_SEARCH_RANGE_LBN 97
-#define	FRF_CZ_TX_ETH_FILTER_FULL_SEARCH_RANGE_WIDTH 8
-#define	FRF_CZ_TX_UDPIP_FILTER_WILD_SEARCH_RANGE_LBN 89
-#define	FRF_CZ_TX_UDPIP_FILTER_WILD_SEARCH_RANGE_WIDTH 8
-#define	FRF_CZ_TX_UDPIP_FILTER_FULL_SEARCH_RANGE_LBN 81
-#define	FRF_CZ_TX_UDPIP_FILTER_FULL_SEARCH_RANGE_WIDTH 8
-#define	FRF_CZ_TX_TCPIP_FILTER_WILD_SEARCH_RANGE_LBN 73
-#define	FRF_CZ_TX_TCPIP_FILTER_WILD_SEARCH_RANGE_WIDTH 8
-#define	FRF_CZ_TX_TCPIP_FILTER_FULL_SEARCH_RANGE_LBN 65
-#define	FRF_CZ_TX_TCPIP_FILTER_FULL_SEARCH_RANGE_WIDTH 8
-#define	FRF_CZ_TX_FILTER_ALL_VLAN_ETHERTYPES_BIT_LBN 64
-#define	FRF_CZ_TX_FILTER_ALL_VLAN_ETHERTYPES_BIT_WIDTH 1
-#define	FRF_CZ_TX_VLAN_MATCH_ETHERTYPE_RANGE_LBN 48
-#define	FRF_CZ_TX_VLAN_MATCH_ETHERTYPE_RANGE_WIDTH 16
-#define	FRF_CZ_TX_FILTER_EN_BIT_LBN 47
-#define	FRF_CZ_TX_FILTER_EN_BIT_WIDTH 1
-#define	FRF_AZ_TX_IP_ID_P0_OFS_LBN 16
-#define	FRF_AZ_TX_IP_ID_P0_OFS_WIDTH 15
-#define	FRF_AZ_TX_NO_EOP_DISC_EN_LBN 5
-#define	FRF_AZ_TX_NO_EOP_DISC_EN_WIDTH 1
-#define	FRF_AZ_TX_P1_PRI_EN_LBN 4
-#define	FRF_AZ_TX_P1_PRI_EN_WIDTH 1
-#define	FRF_AZ_TX_OWNERR_CTL_LBN 2
-#define	FRF_AZ_TX_OWNERR_CTL_WIDTH 1
-#define	FRF_AA_TX_NON_IP_DROP_DIS_LBN 1
-#define	FRF_AA_TX_NON_IP_DROP_DIS_WIDTH 1
-#define	FRF_AZ_TX_IP_ID_REP_EN_LBN 0
-#define	FRF_AZ_TX_IP_ID_REP_EN_WIDTH 1
-
-/* TX_PUSH_DROP_REG: Transmit push dropped register */
-#define	FR_AZ_TX_PUSH_DROP 0x00000a60
-#define	FRF_AZ_TX_PUSH_DROP_CNT_LBN 0
-#define	FRF_AZ_TX_PUSH_DROP_CNT_WIDTH 32
-
-/* TX_RESERVED_REG: Transmit configuration register */
-#define	FR_AZ_TX_RESERVED 0x00000a80
-#define	FRF_AZ_TX_EVT_CNT_LBN 121
-#define	FRF_AZ_TX_EVT_CNT_WIDTH 7
-#define	FRF_AZ_TX_PREF_AGE_CNT_LBN 119
-#define	FRF_AZ_TX_PREF_AGE_CNT_WIDTH 2
-#define	FRF_AZ_TX_RD_COMP_TMR_LBN 96
-#define	FRF_AZ_TX_RD_COMP_TMR_WIDTH 23
-#define	FRF_AZ_TX_PUSH_EN_LBN 89
-#define	FRF_AZ_TX_PUSH_EN_WIDTH 1
-#define	FRF_AZ_TX_PUSH_CHK_DIS_LBN 88
-#define	FRF_AZ_TX_PUSH_CHK_DIS_WIDTH 1
-#define	FRF_AZ_TX_D_FF_FULL_P0_LBN 85
-#define	FRF_AZ_TX_D_FF_FULL_P0_WIDTH 1
-#define	FRF_AZ_TX_DMAR_ST_P0_LBN 81
-#define	FRF_AZ_TX_DMAR_ST_P0_WIDTH 1
-#define	FRF_AZ_TX_DMAQ_ST_LBN 78
-#define	FRF_AZ_TX_DMAQ_ST_WIDTH 1
-#define	FRF_AZ_TX_RX_SPACER_LBN 64
-#define	FRF_AZ_TX_RX_SPACER_WIDTH 8
-#define	FRF_AZ_TX_DROP_ABORT_EN_LBN 60
-#define	FRF_AZ_TX_DROP_ABORT_EN_WIDTH 1
-#define	FRF_AZ_TX_SOFT_EVT_EN_LBN 59
-#define	FRF_AZ_TX_SOFT_EVT_EN_WIDTH 1
-#define	FRF_AZ_TX_PS_EVT_DIS_LBN 58
-#define	FRF_AZ_TX_PS_EVT_DIS_WIDTH 1
-#define	FRF_AZ_TX_RX_SPACER_EN_LBN 57
-#define	FRF_AZ_TX_RX_SPACER_EN_WIDTH 1
-#define	FRF_AZ_TX_XP_TIMER_LBN 52
-#define	FRF_AZ_TX_XP_TIMER_WIDTH 5
-#define	FRF_AZ_TX_PREF_SPACER_LBN 44
-#define	FRF_AZ_TX_PREF_SPACER_WIDTH 8
-#define	FRF_AZ_TX_PREF_WD_TMR_LBN 22
-#define	FRF_AZ_TX_PREF_WD_TMR_WIDTH 22
-#define	FRF_AZ_TX_ONLY1TAG_LBN 21
-#define	FRF_AZ_TX_ONLY1TAG_WIDTH 1
-#define	FRF_AZ_TX_PREF_THRESHOLD_LBN 19
-#define	FRF_AZ_TX_PREF_THRESHOLD_WIDTH 2
-#define	FRF_AZ_TX_ONE_PKT_PER_Q_LBN 18
-#define	FRF_AZ_TX_ONE_PKT_PER_Q_WIDTH 1
-#define	FRF_AZ_TX_DIS_NON_IP_EV_LBN 17
-#define	FRF_AZ_TX_DIS_NON_IP_EV_WIDTH 1
-#define	FRF_AA_TX_DMA_FF_THR_LBN 16
-#define	FRF_AA_TX_DMA_FF_THR_WIDTH 1
-#define	FRF_AZ_TX_DMA_SPACER_LBN 8
-#define	FRF_AZ_TX_DMA_SPACER_WIDTH 8
-#define	FRF_AA_TX_TCP_DIS_LBN 7
-#define	FRF_AA_TX_TCP_DIS_WIDTH 1
-#define	FRF_BZ_TX_FLUSH_MIN_LEN_EN_LBN 7
-#define	FRF_BZ_TX_FLUSH_MIN_LEN_EN_WIDTH 1
-#define	FRF_AA_TX_IP_DIS_LBN 6
-#define	FRF_AA_TX_IP_DIS_WIDTH 1
-#define	FRF_AZ_TX_MAX_CPL_LBN 2
-#define	FRF_AZ_TX_MAX_CPL_WIDTH 2
-#define	FFE_AZ_TX_MAX_CPL_16 3
-#define	FFE_AZ_TX_MAX_CPL_8 2
-#define	FFE_AZ_TX_MAX_CPL_4 1
-#define	FFE_AZ_TX_MAX_CPL_NOLIMIT 0
-#define	FRF_AZ_TX_MAX_PREF_LBN 0
-#define	FRF_AZ_TX_MAX_PREF_WIDTH 2
-#define	FFE_AZ_TX_MAX_PREF_32 3
-#define	FFE_AZ_TX_MAX_PREF_16 2
-#define	FFE_AZ_TX_MAX_PREF_8 1
-#define	FFE_AZ_TX_MAX_PREF_OFF 0
-
-/* TX_PACE_REG: Transmit pace control register */
-#define	FR_BZ_TX_PACE 0x00000a90
-#define	FRF_BZ_TX_PACE_SB_NOT_AF_LBN 19
-#define	FRF_BZ_TX_PACE_SB_NOT_AF_WIDTH 10
-#define	FRF_BZ_TX_PACE_SB_AF_LBN 9
-#define	FRF_BZ_TX_PACE_SB_AF_WIDTH 10
-#define	FRF_BZ_TX_PACE_FB_BASE_LBN 5
-#define	FRF_BZ_TX_PACE_FB_BASE_WIDTH 4
-#define	FRF_BZ_TX_PACE_BIN_TH_LBN 0
-#define	FRF_BZ_TX_PACE_BIN_TH_WIDTH 5
-
-/* TX_PACE_DROP_QID_REG: PACE Drop QID Counter */
-#define	FR_BZ_TX_PACE_DROP_QID 0x00000aa0
-#define	FRF_BZ_TX_PACE_QID_DRP_CNT_LBN 0
-#define	FRF_BZ_TX_PACE_QID_DRP_CNT_WIDTH 16
-
-/* TX_VLAN_REG: Transmit VLAN tag register */
-#define	FR_BB_TX_VLAN 0x00000ae0
-#define	FRF_BB_TX_VLAN_EN_LBN 127
-#define	FRF_BB_TX_VLAN_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN7_PORT1_EN_LBN 125
-#define	FRF_BB_TX_VLAN7_PORT1_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN7_PORT0_EN_LBN 124
-#define	FRF_BB_TX_VLAN7_PORT0_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN7_LBN 112
-#define	FRF_BB_TX_VLAN7_WIDTH 12
-#define	FRF_BB_TX_VLAN6_PORT1_EN_LBN 109
-#define	FRF_BB_TX_VLAN6_PORT1_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN6_PORT0_EN_LBN 108
-#define	FRF_BB_TX_VLAN6_PORT0_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN6_LBN 96
-#define	FRF_BB_TX_VLAN6_WIDTH 12
-#define	FRF_BB_TX_VLAN5_PORT1_EN_LBN 93
-#define	FRF_BB_TX_VLAN5_PORT1_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN5_PORT0_EN_LBN 92
-#define	FRF_BB_TX_VLAN5_PORT0_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN5_LBN 80
-#define	FRF_BB_TX_VLAN5_WIDTH 12
-#define	FRF_BB_TX_VLAN4_PORT1_EN_LBN 77
-#define	FRF_BB_TX_VLAN4_PORT1_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN4_PORT0_EN_LBN 76
-#define	FRF_BB_TX_VLAN4_PORT0_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN4_LBN 64
-#define	FRF_BB_TX_VLAN4_WIDTH 12
-#define	FRF_BB_TX_VLAN3_PORT1_EN_LBN 61
-#define	FRF_BB_TX_VLAN3_PORT1_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN3_PORT0_EN_LBN 60
-#define	FRF_BB_TX_VLAN3_PORT0_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN3_LBN 48
-#define	FRF_BB_TX_VLAN3_WIDTH 12
-#define	FRF_BB_TX_VLAN2_PORT1_EN_LBN 45
-#define	FRF_BB_TX_VLAN2_PORT1_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN2_PORT0_EN_LBN 44
-#define	FRF_BB_TX_VLAN2_PORT0_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN2_LBN 32
-#define	FRF_BB_TX_VLAN2_WIDTH 12
-#define	FRF_BB_TX_VLAN1_PORT1_EN_LBN 29
-#define	FRF_BB_TX_VLAN1_PORT1_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN1_PORT0_EN_LBN 28
-#define	FRF_BB_TX_VLAN1_PORT0_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN1_LBN 16
-#define	FRF_BB_TX_VLAN1_WIDTH 12
-#define	FRF_BB_TX_VLAN0_PORT1_EN_LBN 13
-#define	FRF_BB_TX_VLAN0_PORT1_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN0_PORT0_EN_LBN 12
-#define	FRF_BB_TX_VLAN0_PORT0_EN_WIDTH 1
-#define	FRF_BB_TX_VLAN0_LBN 0
-#define	FRF_BB_TX_VLAN0_WIDTH 12
-
-/* TX_IPFIL_PORTEN_REG: Transmit filter control register */
-#define	FR_BZ_TX_IPFIL_PORTEN 0x00000af0
-#define	FRF_BZ_TX_MADR0_FIL_EN_LBN 64
-#define	FRF_BZ_TX_MADR0_FIL_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL31_PORT_EN_LBN 62
-#define	FRF_BB_TX_IPFIL31_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL30_PORT_EN_LBN 60
-#define	FRF_BB_TX_IPFIL30_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL29_PORT_EN_LBN 58
-#define	FRF_BB_TX_IPFIL29_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL28_PORT_EN_LBN 56
-#define	FRF_BB_TX_IPFIL28_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL27_PORT_EN_LBN 54
-#define	FRF_BB_TX_IPFIL27_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL26_PORT_EN_LBN 52
-#define	FRF_BB_TX_IPFIL26_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL25_PORT_EN_LBN 50
-#define	FRF_BB_TX_IPFIL25_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL24_PORT_EN_LBN 48
-#define	FRF_BB_TX_IPFIL24_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL23_PORT_EN_LBN 46
-#define	FRF_BB_TX_IPFIL23_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL22_PORT_EN_LBN 44
-#define	FRF_BB_TX_IPFIL22_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL21_PORT_EN_LBN 42
-#define	FRF_BB_TX_IPFIL21_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL20_PORT_EN_LBN 40
-#define	FRF_BB_TX_IPFIL20_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL19_PORT_EN_LBN 38
-#define	FRF_BB_TX_IPFIL19_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL18_PORT_EN_LBN 36
-#define	FRF_BB_TX_IPFIL18_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL17_PORT_EN_LBN 34
-#define	FRF_BB_TX_IPFIL17_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL16_PORT_EN_LBN 32
-#define	FRF_BB_TX_IPFIL16_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL15_PORT_EN_LBN 30
-#define	FRF_BB_TX_IPFIL15_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL14_PORT_EN_LBN 28
-#define	FRF_BB_TX_IPFIL14_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL13_PORT_EN_LBN 26
-#define	FRF_BB_TX_IPFIL13_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL12_PORT_EN_LBN 24
-#define	FRF_BB_TX_IPFIL12_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL11_PORT_EN_LBN 22
-#define	FRF_BB_TX_IPFIL11_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL10_PORT_EN_LBN 20
-#define	FRF_BB_TX_IPFIL10_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL9_PORT_EN_LBN 18
-#define	FRF_BB_TX_IPFIL9_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL8_PORT_EN_LBN 16
-#define	FRF_BB_TX_IPFIL8_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL7_PORT_EN_LBN 14
-#define	FRF_BB_TX_IPFIL7_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL6_PORT_EN_LBN 12
-#define	FRF_BB_TX_IPFIL6_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL5_PORT_EN_LBN 10
-#define	FRF_BB_TX_IPFIL5_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL4_PORT_EN_LBN 8
-#define	FRF_BB_TX_IPFIL4_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL3_PORT_EN_LBN 6
-#define	FRF_BB_TX_IPFIL3_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL2_PORT_EN_LBN 4
-#define	FRF_BB_TX_IPFIL2_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL1_PORT_EN_LBN 2
-#define	FRF_BB_TX_IPFIL1_PORT_EN_WIDTH 1
-#define	FRF_BB_TX_IPFIL0_PORT_EN_LBN 0
-#define	FRF_BB_TX_IPFIL0_PORT_EN_WIDTH 1
-
-/* TX_IPFIL_TBL: Transmit IP source address filter table */
-#define	FR_BB_TX_IPFIL_TBL 0x00000b00
-#define	FR_BB_TX_IPFIL_TBL_STEP 16
-#define	FR_BB_TX_IPFIL_TBL_ROWS 16
-#define	FRF_BB_TX_IPFIL_MASK_1_LBN 96
-#define	FRF_BB_TX_IPFIL_MASK_1_WIDTH 32
-#define	FRF_BB_TX_IP_SRC_ADR_1_LBN 64
-#define	FRF_BB_TX_IP_SRC_ADR_1_WIDTH 32
-#define	FRF_BB_TX_IPFIL_MASK_0_LBN 32
-#define	FRF_BB_TX_IPFIL_MASK_0_WIDTH 32
-#define	FRF_BB_TX_IP_SRC_ADR_0_LBN 0
-#define	FRF_BB_TX_IP_SRC_ADR_0_WIDTH 32
-
-/* MD_TXD_REG: PHY management transmit data register */
-#define	FR_AB_MD_TXD 0x00000c00
-#define	FRF_AB_MD_TXD_LBN 0
-#define	FRF_AB_MD_TXD_WIDTH 16
-
-/* MD_RXD_REG: PHY management receive data register */
-#define	FR_AB_MD_RXD 0x00000c10
-#define	FRF_AB_MD_RXD_LBN 0
-#define	FRF_AB_MD_RXD_WIDTH 16
-
-/* MD_CS_REG: PHY management configuration & status register */
-#define	FR_AB_MD_CS 0x00000c20
-#define	FRF_AB_MD_RD_EN_CMD_LBN 15
-#define	FRF_AB_MD_RD_EN_CMD_WIDTH 1
-#define	FRF_AB_MD_WR_EN_CMD_LBN 14
-#define	FRF_AB_MD_WR_EN_CMD_WIDTH 1
-#define	FRF_AB_MD_ADDR_CMD_LBN 13
-#define	FRF_AB_MD_ADDR_CMD_WIDTH 1
-#define	FRF_AB_MD_PT_LBN 7
-#define	FRF_AB_MD_PT_WIDTH 3
-#define	FRF_AB_MD_PL_LBN 6
-#define	FRF_AB_MD_PL_WIDTH 1
-#define	FRF_AB_MD_INT_CLR_LBN 5
-#define	FRF_AB_MD_INT_CLR_WIDTH 1
-#define	FRF_AB_MD_GC_LBN 4
-#define	FRF_AB_MD_GC_WIDTH 1
-#define	FRF_AB_MD_PRSP_LBN 3
-#define	FRF_AB_MD_PRSP_WIDTH 1
-#define	FRF_AB_MD_RIC_LBN 2
-#define	FRF_AB_MD_RIC_WIDTH 1
-#define	FRF_AB_MD_RDC_LBN 1
-#define	FRF_AB_MD_RDC_WIDTH 1
-#define	FRF_AB_MD_WRC_LBN 0
-#define	FRF_AB_MD_WRC_WIDTH 1
-
-/* MD_PHY_ADR_REG: PHY management PHY address register */
-#define	FR_AB_MD_PHY_ADR 0x00000c30
-#define	FRF_AB_MD_PHY_ADR_LBN 0
-#define	FRF_AB_MD_PHY_ADR_WIDTH 16
-
-/* MD_ID_REG: PHY management ID register */
-#define	FR_AB_MD_ID 0x00000c40
-#define	FRF_AB_MD_PRT_ADR_LBN 11
-#define	FRF_AB_MD_PRT_ADR_WIDTH 5
-#define	FRF_AB_MD_DEV_ADR_LBN 6
-#define	FRF_AB_MD_DEV_ADR_WIDTH 5
-
-/* MD_STAT_REG: PHY management status & mask register */
-#define	FR_AB_MD_STAT 0x00000c50
-#define	FRF_AB_MD_PINT_LBN 4
-#define	FRF_AB_MD_PINT_WIDTH 1
-#define	FRF_AB_MD_DONE_LBN 3
-#define	FRF_AB_MD_DONE_WIDTH 1
-#define	FRF_AB_MD_BSERR_LBN 2
-#define	FRF_AB_MD_BSERR_WIDTH 1
-#define	FRF_AB_MD_LNFL_LBN 1
-#define	FRF_AB_MD_LNFL_WIDTH 1
-#define	FRF_AB_MD_BSY_LBN 0
-#define	FRF_AB_MD_BSY_WIDTH 1
-
-/* MAC_STAT_DMA_REG: Port MAC statistical counter DMA register */
-#define	FR_AB_MAC_STAT_DMA 0x00000c60
-#define	FRF_AB_MAC_STAT_DMA_CMD_LBN 48
-#define	FRF_AB_MAC_STAT_DMA_CMD_WIDTH 1
-#define	FRF_AB_MAC_STAT_DMA_ADR_LBN 0
-#define	FRF_AB_MAC_STAT_DMA_ADR_WIDTH 48
-
-/* MAC_CTRL_REG: Port MAC control register */
-#define	FR_AB_MAC_CTRL 0x00000c80
-#define	FRF_AB_MAC_XOFF_VAL_LBN 16
-#define	FRF_AB_MAC_XOFF_VAL_WIDTH 16
-#define	FRF_BB_TXFIFO_DRAIN_EN_LBN 7
-#define	FRF_BB_TXFIFO_DRAIN_EN_WIDTH 1
-#define	FRF_AB_MAC_XG_DISTXCRC_LBN 5
-#define	FRF_AB_MAC_XG_DISTXCRC_WIDTH 1
-#define	FRF_AB_MAC_BCAD_ACPT_LBN 4
-#define	FRF_AB_MAC_BCAD_ACPT_WIDTH 1
-#define	FRF_AB_MAC_UC_PROM_LBN 3
-#define	FRF_AB_MAC_UC_PROM_WIDTH 1
-#define	FRF_AB_MAC_LINK_STATUS_LBN 2
-#define	FRF_AB_MAC_LINK_STATUS_WIDTH 1
-#define	FRF_AB_MAC_SPEED_LBN 0
-#define	FRF_AB_MAC_SPEED_WIDTH 2
-#define	FFE_AB_MAC_SPEED_10G 3
-#define	FFE_AB_MAC_SPEED_1G 2
-#define	FFE_AB_MAC_SPEED_100M 1
-#define	FFE_AB_MAC_SPEED_10M 0
-
-/* GEN_MODE_REG: General Purpose mode register (external interrupt mask) */
-#define	FR_BB_GEN_MODE 0x00000c90
-#define	FRF_BB_XFP_PHY_INT_POL_SEL_LBN 3
-#define	FRF_BB_XFP_PHY_INT_POL_SEL_WIDTH 1
-#define	FRF_BB_XG_PHY_INT_POL_SEL_LBN 2
-#define	FRF_BB_XG_PHY_INT_POL_SEL_WIDTH 1
-#define	FRF_BB_XFP_PHY_INT_MASK_LBN 1
-#define	FRF_BB_XFP_PHY_INT_MASK_WIDTH 1
-#define	FRF_BB_XG_PHY_INT_MASK_LBN 0
-#define	FRF_BB_XG_PHY_INT_MASK_WIDTH 1
-
-/* MAC_MC_HASH_REG0: Multicast address hash table */
-#define	FR_AB_MAC_MC_HASH_REG0 0x00000ca0
-#define	FRF_AB_MAC_MCAST_HASH0_LBN 0
-#define	FRF_AB_MAC_MCAST_HASH0_WIDTH 128
-
-/* MAC_MC_HASH_REG1: Multicast address hash table */
-#define	FR_AB_MAC_MC_HASH_REG1 0x00000cb0
-#define	FRF_AB_MAC_MCAST_HASH1_LBN 0
-#define	FRF_AB_MAC_MCAST_HASH1_WIDTH 128
-
-/* GM_CFG1_REG: GMAC configuration register 1 */
-#define	FR_AB_GM_CFG1 0x00000e00
-#define	FRF_AB_GM_SW_RST_LBN 31
-#define	FRF_AB_GM_SW_RST_WIDTH 1
-#define	FRF_AB_GM_SIM_RST_LBN 30
-#define	FRF_AB_GM_SIM_RST_WIDTH 1
-#define	FRF_AB_GM_RST_RX_MAC_CTL_LBN 19
-#define	FRF_AB_GM_RST_RX_MAC_CTL_WIDTH 1
-#define	FRF_AB_GM_RST_TX_MAC_CTL_LBN 18
-#define	FRF_AB_GM_RST_TX_MAC_CTL_WIDTH 1
-#define	FRF_AB_GM_RST_RX_FUNC_LBN 17
-#define	FRF_AB_GM_RST_RX_FUNC_WIDTH 1
-#define	FRF_AB_GM_RST_TX_FUNC_LBN 16
-#define	FRF_AB_GM_RST_TX_FUNC_WIDTH 1
-#define	FRF_AB_GM_LOOP_LBN 8
-#define	FRF_AB_GM_LOOP_WIDTH 1
-#define	FRF_AB_GM_RX_FC_EN_LBN 5
-#define	FRF_AB_GM_RX_FC_EN_WIDTH 1
-#define	FRF_AB_GM_TX_FC_EN_LBN 4
-#define	FRF_AB_GM_TX_FC_EN_WIDTH 1
-#define	FRF_AB_GM_SYNC_RXEN_LBN 3
-#define	FRF_AB_GM_SYNC_RXEN_WIDTH 1
-#define	FRF_AB_GM_RX_EN_LBN 2
-#define	FRF_AB_GM_RX_EN_WIDTH 1
-#define	FRF_AB_GM_SYNC_TXEN_LBN 1
-#define	FRF_AB_GM_SYNC_TXEN_WIDTH 1
-#define	FRF_AB_GM_TX_EN_LBN 0
-#define	FRF_AB_GM_TX_EN_WIDTH 1
-
-/* GM_CFG2_REG: GMAC configuration register 2 */
-#define	FR_AB_GM_CFG2 0x00000e10
-#define	FRF_AB_GM_PAMBL_LEN_LBN 12
-#define	FRF_AB_GM_PAMBL_LEN_WIDTH 4
-#define	FRF_AB_GM_IF_MODE_LBN 8
-#define	FRF_AB_GM_IF_MODE_WIDTH 2
-#define	FFE_AB_IF_MODE_BYTE_MODE 2
-#define	FFE_AB_IF_MODE_NIBBLE_MODE 1
-#define	FRF_AB_GM_HUGE_FRM_EN_LBN 5
-#define	FRF_AB_GM_HUGE_FRM_EN_WIDTH 1
-#define	FRF_AB_GM_LEN_CHK_LBN 4
-#define	FRF_AB_GM_LEN_CHK_WIDTH 1
-#define	FRF_AB_GM_PAD_CRC_EN_LBN 2
-#define	FRF_AB_GM_PAD_CRC_EN_WIDTH 1
-#define	FRF_AB_GM_CRC_EN_LBN 1
-#define	FRF_AB_GM_CRC_EN_WIDTH 1
-#define	FRF_AB_GM_FD_LBN 0
-#define	FRF_AB_GM_FD_WIDTH 1
-
-/* GM_IPG_REG: GMAC IPG register */
-#define	FR_AB_GM_IPG 0x00000e20
-#define	FRF_AB_GM_NONB2B_IPG1_LBN 24
-#define	FRF_AB_GM_NONB2B_IPG1_WIDTH 7
-#define	FRF_AB_GM_NONB2B_IPG2_LBN 16
-#define	FRF_AB_GM_NONB2B_IPG2_WIDTH 7
-#define	FRF_AB_GM_MIN_IPG_ENF_LBN 8
-#define	FRF_AB_GM_MIN_IPG_ENF_WIDTH 8
-#define	FRF_AB_GM_B2B_IPG_LBN 0
-#define	FRF_AB_GM_B2B_IPG_WIDTH 7
-
-/* GM_HD_REG: GMAC half duplex register */
-#define	FR_AB_GM_HD 0x00000e30
-#define	FRF_AB_GM_ALT_BOFF_VAL_LBN 20
-#define	FRF_AB_GM_ALT_BOFF_VAL_WIDTH 4
-#define	FRF_AB_GM_ALT_BOFF_EN_LBN 19
-#define	FRF_AB_GM_ALT_BOFF_EN_WIDTH 1
-#define	FRF_AB_GM_BP_NO_BOFF_LBN 18
-#define	FRF_AB_GM_BP_NO_BOFF_WIDTH 1
-#define	FRF_AB_GM_DIS_BOFF_LBN 17
-#define	FRF_AB_GM_DIS_BOFF_WIDTH 1
-#define	FRF_AB_GM_EXDEF_TX_EN_LBN 16
-#define	FRF_AB_GM_EXDEF_TX_EN_WIDTH 1
-#define	FRF_AB_GM_RTRY_LIMIT_LBN 12
-#define	FRF_AB_GM_RTRY_LIMIT_WIDTH 4
-#define	FRF_AB_GM_COL_WIN_LBN 0
-#define	FRF_AB_GM_COL_WIN_WIDTH 10
-
-/* GM_MAX_FLEN_REG: GMAC maximum frame length register */
-#define	FR_AB_GM_MAX_FLEN 0x00000e40
-#define	FRF_AB_GM_MAX_FLEN_LBN 0
-#define	FRF_AB_GM_MAX_FLEN_WIDTH 16
-
-/* GM_TEST_REG: GMAC test register */
-#define	FR_AB_GM_TEST 0x00000e70
-#define	FRF_AB_GM_MAX_BOFF_LBN 3
-#define	FRF_AB_GM_MAX_BOFF_WIDTH 1
-#define	FRF_AB_GM_REG_TX_FLOW_EN_LBN 2
-#define	FRF_AB_GM_REG_TX_FLOW_EN_WIDTH 1
-#define	FRF_AB_GM_TEST_PAUSE_LBN 1
-#define	FRF_AB_GM_TEST_PAUSE_WIDTH 1
-#define	FRF_AB_GM_SHORT_SLOT_LBN 0
-#define	FRF_AB_GM_SHORT_SLOT_WIDTH 1
-
-/* GM_ADR1_REG: GMAC station address register 1 */
-#define	FR_AB_GM_ADR1 0x00000f00
-#define	FRF_AB_GM_ADR_B0_LBN 24
-#define	FRF_AB_GM_ADR_B0_WIDTH 8
-#define	FRF_AB_GM_ADR_B1_LBN 16
-#define	FRF_AB_GM_ADR_B1_WIDTH 8
-#define	FRF_AB_GM_ADR_B2_LBN 8
-#define	FRF_AB_GM_ADR_B2_WIDTH 8
-#define	FRF_AB_GM_ADR_B3_LBN 0
-#define	FRF_AB_GM_ADR_B3_WIDTH 8
-
-/* GM_ADR2_REG: GMAC station address register 2 */
-#define	FR_AB_GM_ADR2 0x00000f10
-#define	FRF_AB_GM_ADR_B4_LBN 24
-#define	FRF_AB_GM_ADR_B4_WIDTH 8
-#define	FRF_AB_GM_ADR_B5_LBN 16
-#define	FRF_AB_GM_ADR_B5_WIDTH 8
-
-/* GMF_CFG0_REG: GMAC FIFO configuration register 0 */
-#define	FR_AB_GMF_CFG0 0x00000f20
-#define	FRF_AB_GMF_FTFENRPLY_LBN 20
-#define	FRF_AB_GMF_FTFENRPLY_WIDTH 1
-#define	FRF_AB_GMF_STFENRPLY_LBN 19
-#define	FRF_AB_GMF_STFENRPLY_WIDTH 1
-#define	FRF_AB_GMF_FRFENRPLY_LBN 18
-#define	FRF_AB_GMF_FRFENRPLY_WIDTH 1
-#define	FRF_AB_GMF_SRFENRPLY_LBN 17
-#define	FRF_AB_GMF_SRFENRPLY_WIDTH 1
-#define	FRF_AB_GMF_WTMENRPLY_LBN 16
-#define	FRF_AB_GMF_WTMENRPLY_WIDTH 1
-#define	FRF_AB_GMF_FTFENREQ_LBN 12
-#define	FRF_AB_GMF_FTFENREQ_WIDTH 1
-#define	FRF_AB_GMF_STFENREQ_LBN 11
-#define	FRF_AB_GMF_STFENREQ_WIDTH 1
-#define	FRF_AB_GMF_FRFENREQ_LBN 10
-#define	FRF_AB_GMF_FRFENREQ_WIDTH 1
-#define	FRF_AB_GMF_SRFENREQ_LBN 9
-#define	FRF_AB_GMF_SRFENREQ_WIDTH 1
-#define	FRF_AB_GMF_WTMENREQ_LBN 8
-#define	FRF_AB_GMF_WTMENREQ_WIDTH 1
-#define	FRF_AB_GMF_HSTRSTFT_LBN 4
-#define	FRF_AB_GMF_HSTRSTFT_WIDTH 1
-#define	FRF_AB_GMF_HSTRSTST_LBN 3
-#define	FRF_AB_GMF_HSTRSTST_WIDTH 1
-#define	FRF_AB_GMF_HSTRSTFR_LBN 2
-#define	FRF_AB_GMF_HSTRSTFR_WIDTH 1
-#define	FRF_AB_GMF_HSTRSTSR_LBN 1
-#define	FRF_AB_GMF_HSTRSTSR_WIDTH 1
-#define	FRF_AB_GMF_HSTRSTWT_LBN 0
-#define	FRF_AB_GMF_HSTRSTWT_WIDTH 1
-
-/* GMF_CFG1_REG: GMAC FIFO configuration register 1 */
-#define	FR_AB_GMF_CFG1 0x00000f30
-#define	FRF_AB_GMF_CFGFRTH_LBN 16
-#define	FRF_AB_GMF_CFGFRTH_WIDTH 5
-#define	FRF_AB_GMF_CFGXOFFRTX_LBN 0
-#define	FRF_AB_GMF_CFGXOFFRTX_WIDTH 16
-
-/* GMF_CFG2_REG: GMAC FIFO configuration register 2 */
-#define	FR_AB_GMF_CFG2 0x00000f40
-#define	FRF_AB_GMF_CFGHWM_LBN 16
-#define	FRF_AB_GMF_CFGHWM_WIDTH 6
-#define	FRF_AB_GMF_CFGLWM_LBN 0
-#define	FRF_AB_GMF_CFGLWM_WIDTH 6
-
-/* GMF_CFG3_REG: GMAC FIFO configuration register 3 */
-#define	FR_AB_GMF_CFG3 0x00000f50
-#define	FRF_AB_GMF_CFGHWMFT_LBN 16
-#define	FRF_AB_GMF_CFGHWMFT_WIDTH 6
-#define	FRF_AB_GMF_CFGFTTH_LBN 0
-#define	FRF_AB_GMF_CFGFTTH_WIDTH 6
-
-/* GMF_CFG4_REG: GMAC FIFO configuration register 4 */
-#define	FR_AB_GMF_CFG4 0x00000f60
-#define	FRF_AB_GMF_HSTFLTRFRM_LBN 0
-#define	FRF_AB_GMF_HSTFLTRFRM_WIDTH 18
-
-/* GMF_CFG5_REG: GMAC FIFO configuration register 5 */
-#define	FR_AB_GMF_CFG5 0x00000f70
-#define	FRF_AB_GMF_CFGHDPLX_LBN 22
-#define	FRF_AB_GMF_CFGHDPLX_WIDTH 1
-#define	FRF_AB_GMF_SRFULL_LBN 21
-#define	FRF_AB_GMF_SRFULL_WIDTH 1
-#define	FRF_AB_GMF_HSTSRFULLCLR_LBN 20
-#define	FRF_AB_GMF_HSTSRFULLCLR_WIDTH 1
-#define	FRF_AB_GMF_CFGBYTMODE_LBN 19
-#define	FRF_AB_GMF_CFGBYTMODE_WIDTH 1
-#define	FRF_AB_GMF_HSTDRPLT64_LBN 18
-#define	FRF_AB_GMF_HSTDRPLT64_WIDTH 1
-#define	FRF_AB_GMF_HSTFLTRFRMDC_LBN 0
-#define	FRF_AB_GMF_HSTFLTRFRMDC_WIDTH 18
-
-/* TX_SRC_MAC_TBL: Transmit IP source address filter table */
-#define	FR_BB_TX_SRC_MAC_TBL 0x00001000
-#define	FR_BB_TX_SRC_MAC_TBL_STEP 16
-#define	FR_BB_TX_SRC_MAC_TBL_ROWS 16
-#define	FRF_BB_TX_SRC_MAC_ADR_1_LBN 64
-#define	FRF_BB_TX_SRC_MAC_ADR_1_WIDTH 48
-#define	FRF_BB_TX_SRC_MAC_ADR_0_LBN 0
-#define	FRF_BB_TX_SRC_MAC_ADR_0_WIDTH 48
-
-/* TX_SRC_MAC_CTL_REG: Transmit MAC source address filter control */
-#define	FR_BB_TX_SRC_MAC_CTL 0x00001100
-#define	FRF_BB_TX_SRC_DROP_CTR_LBN 16
-#define	FRF_BB_TX_SRC_DROP_CTR_WIDTH 16
-#define	FRF_BB_TX_SRC_FLTR_EN_LBN 15
-#define	FRF_BB_TX_SRC_FLTR_EN_WIDTH 1
-#define	FRF_BB_TX_DROP_CTR_CLR_LBN 12
-#define	FRF_BB_TX_DROP_CTR_CLR_WIDTH 1
-#define	FRF_BB_TX_MAC_QID_SEL_LBN 0
-#define	FRF_BB_TX_MAC_QID_SEL_WIDTH 3
-
-/* XM_ADR_LO_REG: XGMAC address register low */
-#define	FR_AB_XM_ADR_LO 0x00001200
-#define	FRF_AB_XM_ADR_LO_LBN 0
-#define	FRF_AB_XM_ADR_LO_WIDTH 32
-
-/* XM_ADR_HI_REG: XGMAC address register high */
-#define	FR_AB_XM_ADR_HI 0x00001210
-#define	FRF_AB_XM_ADR_HI_LBN 0
-#define	FRF_AB_XM_ADR_HI_WIDTH 16
-
-/* XM_GLB_CFG_REG: XGMAC global configuration */
-#define	FR_AB_XM_GLB_CFG 0x00001220
-#define	FRF_AB_XM_RMTFLT_GEN_LBN 17
-#define	FRF_AB_XM_RMTFLT_GEN_WIDTH 1
-#define	FRF_AB_XM_DEBUG_MODE_LBN 16
-#define	FRF_AB_XM_DEBUG_MODE_WIDTH 1
-#define	FRF_AB_XM_RX_STAT_EN_LBN 11
-#define	FRF_AB_XM_RX_STAT_EN_WIDTH 1
-#define	FRF_AB_XM_TX_STAT_EN_LBN 10
-#define	FRF_AB_XM_TX_STAT_EN_WIDTH 1
-#define	FRF_AB_XM_RX_JUMBO_MODE_LBN 6
-#define	FRF_AB_XM_RX_JUMBO_MODE_WIDTH 1
-#define	FRF_AB_XM_WAN_MODE_LBN 5
-#define	FRF_AB_XM_WAN_MODE_WIDTH 1
-#define	FRF_AB_XM_INTCLR_MODE_LBN 3
-#define	FRF_AB_XM_INTCLR_MODE_WIDTH 1
-#define	FRF_AB_XM_CORE_RST_LBN 0
-#define	FRF_AB_XM_CORE_RST_WIDTH 1
-
-/* XM_TX_CFG_REG: XGMAC transmit configuration */
-#define	FR_AB_XM_TX_CFG 0x00001230
-#define	FRF_AB_XM_TX_PROG_LBN 24
-#define	FRF_AB_XM_TX_PROG_WIDTH 1
-#define	FRF_AB_XM_IPG_LBN 16
-#define	FRF_AB_XM_IPG_WIDTH 4
-#define	FRF_AB_XM_FCNTL_LBN 10
-#define	FRF_AB_XM_FCNTL_WIDTH 1
-#define	FRF_AB_XM_TXCRC_LBN 8
-#define	FRF_AB_XM_TXCRC_WIDTH 1
-#define	FRF_AB_XM_EDRC_LBN 6
-#define	FRF_AB_XM_EDRC_WIDTH 1
-#define	FRF_AB_XM_AUTO_PAD_LBN 5
-#define	FRF_AB_XM_AUTO_PAD_WIDTH 1
-#define	FRF_AB_XM_TX_PRMBL_LBN 2
-#define	FRF_AB_XM_TX_PRMBL_WIDTH 1
-#define	FRF_AB_XM_TXEN_LBN 1
-#define	FRF_AB_XM_TXEN_WIDTH 1
-#define	FRF_AB_XM_TX_RST_LBN 0
-#define	FRF_AB_XM_TX_RST_WIDTH 1
-
-/* XM_RX_CFG_REG: XGMAC receive configuration */
-#define	FR_AB_XM_RX_CFG 0x00001240
-#define	FRF_AB_XM_PASS_LENERR_LBN 26
-#define	FRF_AB_XM_PASS_LENERR_WIDTH 1
-#define	FRF_AB_XM_PASS_CRC_ERR_LBN 25
-#define	FRF_AB_XM_PASS_CRC_ERR_WIDTH 1
-#define	FRF_AB_XM_PASS_PRMBLE_ERR_LBN 24
-#define	FRF_AB_XM_PASS_PRMBLE_ERR_WIDTH 1
-#define	FRF_AB_XM_REJ_BCAST_LBN 20
-#define	FRF_AB_XM_REJ_BCAST_WIDTH 1
-#define	FRF_AB_XM_ACPT_ALL_MCAST_LBN 11
-#define	FRF_AB_XM_ACPT_ALL_MCAST_WIDTH 1
-#define	FRF_AB_XM_ACPT_ALL_UCAST_LBN 9
-#define	FRF_AB_XM_ACPT_ALL_UCAST_WIDTH 1
-#define	FRF_AB_XM_AUTO_DEPAD_LBN 8
-#define	FRF_AB_XM_AUTO_DEPAD_WIDTH 1
-#define	FRF_AB_XM_RXCRC_LBN 3
-#define	FRF_AB_XM_RXCRC_WIDTH 1
-#define	FRF_AB_XM_RX_PRMBL_LBN 2
-#define	FRF_AB_XM_RX_PRMBL_WIDTH 1
-#define	FRF_AB_XM_RXEN_LBN 1
-#define	FRF_AB_XM_RXEN_WIDTH 1
-#define	FRF_AB_XM_RX_RST_LBN 0
-#define	FRF_AB_XM_RX_RST_WIDTH 1
-
-/* XM_MGT_INT_MASK: documentation to be written for sum_XM_MGT_INT_MASK */
-#define	FR_AB_XM_MGT_INT_MASK 0x00001250
-#define	FRF_AB_XM_MSK_STA_INTR_LBN 16
-#define	FRF_AB_XM_MSK_STA_INTR_WIDTH 1
-#define	FRF_AB_XM_MSK_STAT_CNTR_HF_LBN 9
-#define	FRF_AB_XM_MSK_STAT_CNTR_HF_WIDTH 1
-#define	FRF_AB_XM_MSK_STAT_CNTR_OF_LBN 8
-#define	FRF_AB_XM_MSK_STAT_CNTR_OF_WIDTH 1
-#define	FRF_AB_XM_MSK_PRMBLE_ERR_LBN 2
-#define	FRF_AB_XM_MSK_PRMBLE_ERR_WIDTH 1
-#define	FRF_AB_XM_MSK_RMTFLT_LBN 1
-#define	FRF_AB_XM_MSK_RMTFLT_WIDTH 1
-#define	FRF_AB_XM_MSK_LCLFLT_LBN 0
-#define	FRF_AB_XM_MSK_LCLFLT_WIDTH 1
-
-/* XM_FC_REG: XGMAC flow control register */
-#define	FR_AB_XM_FC 0x00001270
-#define	FRF_AB_XM_PAUSE_TIME_LBN 16
-#define	FRF_AB_XM_PAUSE_TIME_WIDTH 16
-#define	FRF_AB_XM_RX_MAC_STAT_LBN 11
-#define	FRF_AB_XM_RX_MAC_STAT_WIDTH 1
-#define	FRF_AB_XM_TX_MAC_STAT_LBN 10
-#define	FRF_AB_XM_TX_MAC_STAT_WIDTH 1
-#define	FRF_AB_XM_MCNTL_PASS_LBN 8
-#define	FRF_AB_XM_MCNTL_PASS_WIDTH 2
-#define	FRF_AB_XM_REJ_CNTL_UCAST_LBN 6
-#define	FRF_AB_XM_REJ_CNTL_UCAST_WIDTH 1
-#define	FRF_AB_XM_REJ_CNTL_MCAST_LBN 5
-#define	FRF_AB_XM_REJ_CNTL_MCAST_WIDTH 1
-#define	FRF_AB_XM_ZPAUSE_LBN 2
-#define	FRF_AB_XM_ZPAUSE_WIDTH 1
-#define	FRF_AB_XM_XMIT_PAUSE_LBN 1
-#define	FRF_AB_XM_XMIT_PAUSE_WIDTH 1
-#define	FRF_AB_XM_DIS_FCNTL_LBN 0
-#define	FRF_AB_XM_DIS_FCNTL_WIDTH 1
-
-/* XM_PAUSE_TIME_REG: XGMAC pause time register */
-#define	FR_AB_XM_PAUSE_TIME 0x00001290
-#define	FRF_AB_XM_TX_PAUSE_CNT_LBN 16
-#define	FRF_AB_XM_TX_PAUSE_CNT_WIDTH 16
-#define	FRF_AB_XM_RX_PAUSE_CNT_LBN 0
-#define	FRF_AB_XM_RX_PAUSE_CNT_WIDTH 16
-
-/* XM_TX_PARAM_REG: XGMAC transmit parameter register */
-#define	FR_AB_XM_TX_PARAM 0x000012d0
-#define	FRF_AB_XM_TX_JUMBO_MODE_LBN 31
-#define	FRF_AB_XM_TX_JUMBO_MODE_WIDTH 1
-#define	FRF_AB_XM_MAX_TX_FRM_SIZE_HI_LBN 19
-#define	FRF_AB_XM_MAX_TX_FRM_SIZE_HI_WIDTH 11
-#define	FRF_AB_XM_MAX_TX_FRM_SIZE_LO_LBN 16
-#define	FRF_AB_XM_MAX_TX_FRM_SIZE_LO_WIDTH 3
-#define	FRF_AB_XM_PAD_CHAR_LBN 0
-#define	FRF_AB_XM_PAD_CHAR_WIDTH 8
-
-/* XM_RX_PARAM_REG: XGMAC receive parameter register */
-#define	FR_AB_XM_RX_PARAM 0x000012e0
-#define	FRF_AB_XM_MAX_RX_FRM_SIZE_HI_LBN 3
-#define	FRF_AB_XM_MAX_RX_FRM_SIZE_HI_WIDTH 11
-#define	FRF_AB_XM_MAX_RX_FRM_SIZE_LO_LBN 0
-#define	FRF_AB_XM_MAX_RX_FRM_SIZE_LO_WIDTH 3
-
-/* XM_MGT_INT_MSK_REG: XGMAC management interrupt mask register */
-#define	FR_AB_XM_MGT_INT_MSK 0x000012f0
-#define	FRF_AB_XM_STAT_CNTR_OF_LBN 9
-#define	FRF_AB_XM_STAT_CNTR_OF_WIDTH 1
-#define	FRF_AB_XM_STAT_CNTR_HF_LBN 8
-#define	FRF_AB_XM_STAT_CNTR_HF_WIDTH 1
-#define	FRF_AB_XM_PRMBLE_ERR_LBN 2
-#define	FRF_AB_XM_PRMBLE_ERR_WIDTH 1
-#define	FRF_AB_XM_RMTFLT_LBN 1
-#define	FRF_AB_XM_RMTFLT_WIDTH 1
-#define	FRF_AB_XM_LCLFLT_LBN 0
-#define	FRF_AB_XM_LCLFLT_WIDTH 1
-
-/* XX_PWR_RST_REG: XGXS/XAUI powerdown/reset register */
-#define	FR_AB_XX_PWR_RST 0x00001300
-#define	FRF_AB_XX_PWRDND_SIG_LBN 31
-#define	FRF_AB_XX_PWRDND_SIG_WIDTH 1
-#define	FRF_AB_XX_PWRDNC_SIG_LBN 30
-#define	FRF_AB_XX_PWRDNC_SIG_WIDTH 1
-#define	FRF_AB_XX_PWRDNB_SIG_LBN 29
-#define	FRF_AB_XX_PWRDNB_SIG_WIDTH 1
-#define	FRF_AB_XX_PWRDNA_SIG_LBN 28
-#define	FRF_AB_XX_PWRDNA_SIG_WIDTH 1
-#define	FRF_AB_XX_SIM_MODE_LBN 27
-#define	FRF_AB_XX_SIM_MODE_WIDTH 1
-#define	FRF_AB_XX_RSTPLLCD_SIG_LBN 25
-#define	FRF_AB_XX_RSTPLLCD_SIG_WIDTH 1
-#define	FRF_AB_XX_RSTPLLAB_SIG_LBN 24
-#define	FRF_AB_XX_RSTPLLAB_SIG_WIDTH 1
-#define	FRF_AB_XX_RESETD_SIG_LBN 23
-#define	FRF_AB_XX_RESETD_SIG_WIDTH 1
-#define	FRF_AB_XX_RESETC_SIG_LBN 22
-#define	FRF_AB_XX_RESETC_SIG_WIDTH 1
-#define	FRF_AB_XX_RESETB_SIG_LBN 21
-#define	FRF_AB_XX_RESETB_SIG_WIDTH 1
-#define	FRF_AB_XX_RESETA_SIG_LBN 20
-#define	FRF_AB_XX_RESETA_SIG_WIDTH 1
-#define	FRF_AB_XX_RSTXGXSRX_SIG_LBN 18
-#define	FRF_AB_XX_RSTXGXSRX_SIG_WIDTH 1
-#define	FRF_AB_XX_RSTXGXSTX_SIG_LBN 17
-#define	FRF_AB_XX_RSTXGXSTX_SIG_WIDTH 1
-#define	FRF_AB_XX_SD_RST_ACT_LBN 16
-#define	FRF_AB_XX_SD_RST_ACT_WIDTH 1
-#define	FRF_AB_XX_PWRDND_EN_LBN 15
-#define	FRF_AB_XX_PWRDND_EN_WIDTH 1
-#define	FRF_AB_XX_PWRDNC_EN_LBN 14
-#define	FRF_AB_XX_PWRDNC_EN_WIDTH 1
-#define	FRF_AB_XX_PWRDNB_EN_LBN 13
-#define	FRF_AB_XX_PWRDNB_EN_WIDTH 1
-#define	FRF_AB_XX_PWRDNA_EN_LBN 12
-#define	FRF_AB_XX_PWRDNA_EN_WIDTH 1
-#define	FRF_AB_XX_RSTPLLCD_EN_LBN 9
-#define	FRF_AB_XX_RSTPLLCD_EN_WIDTH 1
-#define	FRF_AB_XX_RSTPLLAB_EN_LBN 8
-#define	FRF_AB_XX_RSTPLLAB_EN_WIDTH 1
-#define	FRF_AB_XX_RESETD_EN_LBN 7
-#define	FRF_AB_XX_RESETD_EN_WIDTH 1
-#define	FRF_AB_XX_RESETC_EN_LBN 6
-#define	FRF_AB_XX_RESETC_EN_WIDTH 1
-#define	FRF_AB_XX_RESETB_EN_LBN 5
-#define	FRF_AB_XX_RESETB_EN_WIDTH 1
-#define	FRF_AB_XX_RESETA_EN_LBN 4
-#define	FRF_AB_XX_RESETA_EN_WIDTH 1
-#define	FRF_AB_XX_RSTXGXSRX_EN_LBN 2
-#define	FRF_AB_XX_RSTXGXSRX_EN_WIDTH 1
-#define	FRF_AB_XX_RSTXGXSTX_EN_LBN 1
-#define	FRF_AB_XX_RSTXGXSTX_EN_WIDTH 1
-#define	FRF_AB_XX_RST_XX_EN_LBN 0
-#define	FRF_AB_XX_RST_XX_EN_WIDTH 1
-
-/* XX_SD_CTL_REG: XGXS/XAUI powerdown/reset control register */
-#define	FR_AB_XX_SD_CTL 0x00001310
-#define	FRF_AB_XX_TERMADJ1_LBN 17
-#define	FRF_AB_XX_TERMADJ1_WIDTH 1
-#define	FRF_AB_XX_TERMADJ0_LBN 16
-#define	FRF_AB_XX_TERMADJ0_WIDTH 1
-#define	FRF_AB_XX_HIDRVD_LBN 15
-#define	FRF_AB_XX_HIDRVD_WIDTH 1
-#define	FRF_AB_XX_LODRVD_LBN 14
-#define	FRF_AB_XX_LODRVD_WIDTH 1
-#define	FRF_AB_XX_HIDRVC_LBN 13
-#define	FRF_AB_XX_HIDRVC_WIDTH 1
-#define	FRF_AB_XX_LODRVC_LBN 12
-#define	FRF_AB_XX_LODRVC_WIDTH 1
-#define	FRF_AB_XX_HIDRVB_LBN 11
-#define	FRF_AB_XX_HIDRVB_WIDTH 1
-#define	FRF_AB_XX_LODRVB_LBN 10
-#define	FRF_AB_XX_LODRVB_WIDTH 1
-#define	FRF_AB_XX_HIDRVA_LBN 9
-#define	FRF_AB_XX_HIDRVA_WIDTH 1
-#define	FRF_AB_XX_LODRVA_LBN 8
-#define	FRF_AB_XX_LODRVA_WIDTH 1
-#define	FRF_AB_XX_LPBKD_LBN 3
-#define	FRF_AB_XX_LPBKD_WIDTH 1
-#define	FRF_AB_XX_LPBKC_LBN 2
-#define	FRF_AB_XX_LPBKC_WIDTH 1
-#define	FRF_AB_XX_LPBKB_LBN 1
-#define	FRF_AB_XX_LPBKB_WIDTH 1
-#define	FRF_AB_XX_LPBKA_LBN 0
-#define	FRF_AB_XX_LPBKA_WIDTH 1
-
-/* XX_TXDRV_CTL_REG: XAUI SerDes transmit drive control register */
-#define	FR_AB_XX_TXDRV_CTL 0x00001320
-#define	FRF_AB_XX_DEQD_LBN 28
-#define	FRF_AB_XX_DEQD_WIDTH 4
-#define	FRF_AB_XX_DEQC_LBN 24
-#define	FRF_AB_XX_DEQC_WIDTH 4
-#define	FRF_AB_XX_DEQB_LBN 20
-#define	FRF_AB_XX_DEQB_WIDTH 4
-#define	FRF_AB_XX_DEQA_LBN 16
-#define	FRF_AB_XX_DEQA_WIDTH 4
-#define	FRF_AB_XX_DTXD_LBN 12
-#define	FRF_AB_XX_DTXD_WIDTH 4
-#define	FRF_AB_XX_DTXC_LBN 8
-#define	FRF_AB_XX_DTXC_WIDTH 4
-#define	FRF_AB_XX_DTXB_LBN 4
-#define	FRF_AB_XX_DTXB_WIDTH 4
-#define	FRF_AB_XX_DTXA_LBN 0
-#define	FRF_AB_XX_DTXA_WIDTH 4
-
-/* XX_PRBS_CTL_REG: documentation to be written for sum_XX_PRBS_CTL_REG */
-#define	FR_AB_XX_PRBS_CTL 0x00001330
-#define	FRF_AB_XX_CH3_RX_PRBS_SEL_LBN 30
-#define	FRF_AB_XX_CH3_RX_PRBS_SEL_WIDTH 2
-#define	FRF_AB_XX_CH3_RX_PRBS_INV_LBN 29
-#define	FRF_AB_XX_CH3_RX_PRBS_INV_WIDTH 1
-#define	FRF_AB_XX_CH3_RX_PRBS_CHKEN_LBN 28
-#define	FRF_AB_XX_CH3_RX_PRBS_CHKEN_WIDTH 1
-#define	FRF_AB_XX_CH2_RX_PRBS_SEL_LBN 26
-#define	FRF_AB_XX_CH2_RX_PRBS_SEL_WIDTH 2
-#define	FRF_AB_XX_CH2_RX_PRBS_INV_LBN 25
-#define	FRF_AB_XX_CH2_RX_PRBS_INV_WIDTH 1
-#define	FRF_AB_XX_CH2_RX_PRBS_CHKEN_LBN 24
-#define	FRF_AB_XX_CH2_RX_PRBS_CHKEN_WIDTH 1
-#define	FRF_AB_XX_CH1_RX_PRBS_SEL_LBN 22
-#define	FRF_AB_XX_CH1_RX_PRBS_SEL_WIDTH 2
-#define	FRF_AB_XX_CH1_RX_PRBS_INV_LBN 21
-#define	FRF_AB_XX_CH1_RX_PRBS_INV_WIDTH 1
-#define	FRF_AB_XX_CH1_RX_PRBS_CHKEN_LBN 20
-#define	FRF_AB_XX_CH1_RX_PRBS_CHKEN_WIDTH 1
-#define	FRF_AB_XX_CH0_RX_PRBS_SEL_LBN 18
-#define	FRF_AB_XX_CH0_RX_PRBS_SEL_WIDTH 2
-#define	FRF_AB_XX_CH0_RX_PRBS_INV_LBN 17
-#define	FRF_AB_XX_CH0_RX_PRBS_INV_WIDTH 1
-#define	FRF_AB_XX_CH0_RX_PRBS_CHKEN_LBN 16
-#define	FRF_AB_XX_CH0_RX_PRBS_CHKEN_WIDTH 1
-#define	FRF_AB_XX_CH3_TX_PRBS_SEL_LBN 14
-#define	FRF_AB_XX_CH3_TX_PRBS_SEL_WIDTH 2
-#define	FRF_AB_XX_CH3_TX_PRBS_INV_LBN 13
-#define	FRF_AB_XX_CH3_TX_PRBS_INV_WIDTH 1
-#define	FRF_AB_XX_CH3_TX_PRBS_CHKEN_LBN 12
-#define	FRF_AB_XX_CH3_TX_PRBS_CHKEN_WIDTH 1
-#define	FRF_AB_XX_CH2_TX_PRBS_SEL_LBN 10
-#define	FRF_AB_XX_CH2_TX_PRBS_SEL_WIDTH 2
-#define	FRF_AB_XX_CH2_TX_PRBS_INV_LBN 9
-#define	FRF_AB_XX_CH2_TX_PRBS_INV_WIDTH 1
-#define	FRF_AB_XX_CH2_TX_PRBS_CHKEN_LBN 8
-#define	FRF_AB_XX_CH2_TX_PRBS_CHKEN_WIDTH 1
-#define	FRF_AB_XX_CH1_TX_PRBS_SEL_LBN 6
-#define	FRF_AB_XX_CH1_TX_PRBS_SEL_WIDTH 2
-#define	FRF_AB_XX_CH1_TX_PRBS_INV_LBN 5
-#define	FRF_AB_XX_CH1_TX_PRBS_INV_WIDTH 1
-#define	FRF_AB_XX_CH1_TX_PRBS_CHKEN_LBN 4
-#define	FRF_AB_XX_CH1_TX_PRBS_CHKEN_WIDTH 1
-#define	FRF_AB_XX_CH0_TX_PRBS_SEL_LBN 2
-#define	FRF_AB_XX_CH0_TX_PRBS_SEL_WIDTH 2
-#define	FRF_AB_XX_CH0_TX_PRBS_INV_LBN 1
-#define	FRF_AB_XX_CH0_TX_PRBS_INV_WIDTH 1
-#define	FRF_AB_XX_CH0_TX_PRBS_CHKEN_LBN 0
-#define	FRF_AB_XX_CH0_TX_PRBS_CHKEN_WIDTH 1
-
-/* XX_PRBS_CHK_REG: documentation to be written for sum_XX_PRBS_CHK_REG */
-#define	FR_AB_XX_PRBS_CHK 0x00001340
-#define	FRF_AB_XX_REV_LB_EN_LBN 16
-#define	FRF_AB_XX_REV_LB_EN_WIDTH 1
-#define	FRF_AB_XX_CH3_DEG_DET_LBN 15
-#define	FRF_AB_XX_CH3_DEG_DET_WIDTH 1
-#define	FRF_AB_XX_CH3_LFSR_LOCK_IND_LBN 14
-#define	FRF_AB_XX_CH3_LFSR_LOCK_IND_WIDTH 1
-#define	FRF_AB_XX_CH3_PRBS_FRUN_LBN 13
-#define	FRF_AB_XX_CH3_PRBS_FRUN_WIDTH 1
-#define	FRF_AB_XX_CH3_ERR_CHK_LBN 12
-#define	FRF_AB_XX_CH3_ERR_CHK_WIDTH 1
-#define	FRF_AB_XX_CH2_DEG_DET_LBN 11
-#define	FRF_AB_XX_CH2_DEG_DET_WIDTH 1
-#define	FRF_AB_XX_CH2_LFSR_LOCK_IND_LBN 10
-#define	FRF_AB_XX_CH2_LFSR_LOCK_IND_WIDTH 1
-#define	FRF_AB_XX_CH2_PRBS_FRUN_LBN 9
-#define	FRF_AB_XX_CH2_PRBS_FRUN_WIDTH 1
-#define	FRF_AB_XX_CH2_ERR_CHK_LBN 8
-#define	FRF_AB_XX_CH2_ERR_CHK_WIDTH 1
-#define	FRF_AB_XX_CH1_DEG_DET_LBN 7
-#define	FRF_AB_XX_CH1_DEG_DET_WIDTH 1
-#define	FRF_AB_XX_CH1_LFSR_LOCK_IND_LBN 6
-#define	FRF_AB_XX_CH1_LFSR_LOCK_IND_WIDTH 1
-#define	FRF_AB_XX_CH1_PRBS_FRUN_LBN 5
-#define	FRF_AB_XX_CH1_PRBS_FRUN_WIDTH 1
-#define	FRF_AB_XX_CH1_ERR_CHK_LBN 4
-#define	FRF_AB_XX_CH1_ERR_CHK_WIDTH 1
-#define	FRF_AB_XX_CH0_DEG_DET_LBN 3
-#define	FRF_AB_XX_CH0_DEG_DET_WIDTH 1
-#define	FRF_AB_XX_CH0_LFSR_LOCK_IND_LBN 2
-#define	FRF_AB_XX_CH0_LFSR_LOCK_IND_WIDTH 1
-#define	FRF_AB_XX_CH0_PRBS_FRUN_LBN 1
-#define	FRF_AB_XX_CH0_PRBS_FRUN_WIDTH 1
-#define	FRF_AB_XX_CH0_ERR_CHK_LBN 0
-#define	FRF_AB_XX_CH0_ERR_CHK_WIDTH 1
-
-/* XX_PRBS_ERR_REG: documentation to be written for sum_XX_PRBS_ERR_REG */
-#define	FR_AB_XX_PRBS_ERR 0x00001350
-#define	FRF_AB_XX_CH3_PRBS_ERR_CNT_LBN 24
-#define	FRF_AB_XX_CH3_PRBS_ERR_CNT_WIDTH 8
-#define	FRF_AB_XX_CH2_PRBS_ERR_CNT_LBN 16
-#define	FRF_AB_XX_CH2_PRBS_ERR_CNT_WIDTH 8
-#define	FRF_AB_XX_CH1_PRBS_ERR_CNT_LBN 8
-#define	FRF_AB_XX_CH1_PRBS_ERR_CNT_WIDTH 8
-#define	FRF_AB_XX_CH0_PRBS_ERR_CNT_LBN 0
-#define	FRF_AB_XX_CH0_PRBS_ERR_CNT_WIDTH 8
-
-/* XX_CORE_STAT_REG: XAUI XGXS core status register */
-#define	FR_AB_XX_CORE_STAT 0x00001360
-#define	FRF_AB_XX_FORCE_SIG3_LBN 31
-#define	FRF_AB_XX_FORCE_SIG3_WIDTH 1
-#define	FRF_AB_XX_FORCE_SIG3_VAL_LBN 30
-#define	FRF_AB_XX_FORCE_SIG3_VAL_WIDTH 1
-#define	FRF_AB_XX_FORCE_SIG2_LBN 29
-#define	FRF_AB_XX_FORCE_SIG2_WIDTH 1
-#define	FRF_AB_XX_FORCE_SIG2_VAL_LBN 28
-#define	FRF_AB_XX_FORCE_SIG2_VAL_WIDTH 1
-#define	FRF_AB_XX_FORCE_SIG1_LBN 27
-#define	FRF_AB_XX_FORCE_SIG1_WIDTH 1
-#define	FRF_AB_XX_FORCE_SIG1_VAL_LBN 26
-#define	FRF_AB_XX_FORCE_SIG1_VAL_WIDTH 1
-#define	FRF_AB_XX_FORCE_SIG0_LBN 25
-#define	FRF_AB_XX_FORCE_SIG0_WIDTH 1
-#define	FRF_AB_XX_FORCE_SIG0_VAL_LBN 24
-#define	FRF_AB_XX_FORCE_SIG0_VAL_WIDTH 1
-#define	FRF_AB_XX_XGXS_LB_EN_LBN 23
-#define	FRF_AB_XX_XGXS_LB_EN_WIDTH 1
-#define	FRF_AB_XX_XGMII_LB_EN_LBN 22
-#define	FRF_AB_XX_XGMII_LB_EN_WIDTH 1
-#define	FRF_AB_XX_MATCH_FAULT_LBN 21
-#define	FRF_AB_XX_MATCH_FAULT_WIDTH 1
-#define	FRF_AB_XX_ALIGN_DONE_LBN 20
-#define	FRF_AB_XX_ALIGN_DONE_WIDTH 1
-#define	FRF_AB_XX_SYNC_STAT3_LBN 19
-#define	FRF_AB_XX_SYNC_STAT3_WIDTH 1
-#define	FRF_AB_XX_SYNC_STAT2_LBN 18
-#define	FRF_AB_XX_SYNC_STAT2_WIDTH 1
-#define	FRF_AB_XX_SYNC_STAT1_LBN 17
-#define	FRF_AB_XX_SYNC_STAT1_WIDTH 1
-#define	FRF_AB_XX_SYNC_STAT0_LBN 16
-#define	FRF_AB_XX_SYNC_STAT0_WIDTH 1
-#define	FRF_AB_XX_COMMA_DET_CH3_LBN 15
-#define	FRF_AB_XX_COMMA_DET_CH3_WIDTH 1
-#define	FRF_AB_XX_COMMA_DET_CH2_LBN 14
-#define	FRF_AB_XX_COMMA_DET_CH2_WIDTH 1
-#define	FRF_AB_XX_COMMA_DET_CH1_LBN 13
-#define	FRF_AB_XX_COMMA_DET_CH1_WIDTH 1
-#define	FRF_AB_XX_COMMA_DET_CH0_LBN 12
-#define	FRF_AB_XX_COMMA_DET_CH0_WIDTH 1
-#define	FRF_AB_XX_CGRP_ALIGN_CH3_LBN 11
-#define	FRF_AB_XX_CGRP_ALIGN_CH3_WIDTH 1
-#define	FRF_AB_XX_CGRP_ALIGN_CH2_LBN 10
-#define	FRF_AB_XX_CGRP_ALIGN_CH2_WIDTH 1
-#define	FRF_AB_XX_CGRP_ALIGN_CH1_LBN 9
-#define	FRF_AB_XX_CGRP_ALIGN_CH1_WIDTH 1
-#define	FRF_AB_XX_CGRP_ALIGN_CH0_LBN 8
-#define	FRF_AB_XX_CGRP_ALIGN_CH0_WIDTH 1
-#define	FRF_AB_XX_CHAR_ERR_CH3_LBN 7
-#define	FRF_AB_XX_CHAR_ERR_CH3_WIDTH 1
-#define	FRF_AB_XX_CHAR_ERR_CH2_LBN 6
-#define	FRF_AB_XX_CHAR_ERR_CH2_WIDTH 1
-#define	FRF_AB_XX_CHAR_ERR_CH1_LBN 5
-#define	FRF_AB_XX_CHAR_ERR_CH1_WIDTH 1
-#define	FRF_AB_XX_CHAR_ERR_CH0_LBN 4
-#define	FRF_AB_XX_CHAR_ERR_CH0_WIDTH 1
-#define	FRF_AB_XX_DISPERR_CH3_LBN 3
-#define	FRF_AB_XX_DISPERR_CH3_WIDTH 1
-#define	FRF_AB_XX_DISPERR_CH2_LBN 2
-#define	FRF_AB_XX_DISPERR_CH2_WIDTH 1
-#define	FRF_AB_XX_DISPERR_CH1_LBN 1
-#define	FRF_AB_XX_DISPERR_CH1_WIDTH 1
-#define	FRF_AB_XX_DISPERR_CH0_LBN 0
-#define	FRF_AB_XX_DISPERR_CH0_WIDTH 1
-
-/* RX_DESC_PTR_TBL_KER: Receive descriptor pointer table */
-#define	FR_AA_RX_DESC_PTR_TBL_KER 0x00011800
-#define	FR_AA_RX_DESC_PTR_TBL_KER_STEP 16
-#define	FR_AA_RX_DESC_PTR_TBL_KER_ROWS 4
-/* RX_DESC_PTR_TBL: Receive descriptor pointer table */
-#define	FR_BZ_RX_DESC_PTR_TBL 0x00f40000
-#define	FR_BZ_RX_DESC_PTR_TBL_STEP 16
-#define	FR_BB_RX_DESC_PTR_TBL_ROWS 4096
-#define	FR_CZ_RX_DESC_PTR_TBL_ROWS 1024
-#define	FRF_CZ_RX_HDR_SPLIT_LBN 90
-#define	FRF_CZ_RX_HDR_SPLIT_WIDTH 1
-#define	FRF_AA_RX_RESET_LBN 89
-#define	FRF_AA_RX_RESET_WIDTH 1
-#define	FRF_AZ_RX_ISCSI_DDIG_EN_LBN 88
-#define	FRF_AZ_RX_ISCSI_DDIG_EN_WIDTH 1
-#define	FRF_AZ_RX_ISCSI_HDIG_EN_LBN 87
-#define	FRF_AZ_RX_ISCSI_HDIG_EN_WIDTH 1
-#define	FRF_AZ_RX_DESC_PREF_ACT_LBN 86
-#define	FRF_AZ_RX_DESC_PREF_ACT_WIDTH 1
-#define	FRF_AZ_RX_DC_HW_RPTR_LBN 80
-#define	FRF_AZ_RX_DC_HW_RPTR_WIDTH 6
-#define	FRF_AZ_RX_DESCQ_HW_RPTR_LBN 68
-#define	FRF_AZ_RX_DESCQ_HW_RPTR_WIDTH 12
-#define	FRF_AZ_RX_DESCQ_SW_WPTR_LBN 56
-#define	FRF_AZ_RX_DESCQ_SW_WPTR_WIDTH 12
-#define	FRF_AZ_RX_DESCQ_BUF_BASE_ID_LBN 36
-#define	FRF_AZ_RX_DESCQ_BUF_BASE_ID_WIDTH 20
-#define	FRF_AZ_RX_DESCQ_EVQ_ID_LBN 24
-#define	FRF_AZ_RX_DESCQ_EVQ_ID_WIDTH 12
-#define	FRF_AZ_RX_DESCQ_OWNER_ID_LBN 10
-#define	FRF_AZ_RX_DESCQ_OWNER_ID_WIDTH 14
-#define	FRF_AZ_RX_DESCQ_LABEL_LBN 5
-#define	FRF_AZ_RX_DESCQ_LABEL_WIDTH 5
-#define	FRF_AZ_RX_DESCQ_SIZE_LBN 3
-#define	FRF_AZ_RX_DESCQ_SIZE_WIDTH 2
-#define	FFE_AZ_RX_DESCQ_SIZE_4K 3
-#define	FFE_AZ_RX_DESCQ_SIZE_2K 2
-#define	FFE_AZ_RX_DESCQ_SIZE_1K 1
-#define	FFE_AZ_RX_DESCQ_SIZE_512 0
-#define	FRF_AZ_RX_DESCQ_TYPE_LBN 2
-#define	FRF_AZ_RX_DESCQ_TYPE_WIDTH 1
-#define	FRF_AZ_RX_DESCQ_JUMBO_LBN 1
-#define	FRF_AZ_RX_DESCQ_JUMBO_WIDTH 1
-#define	FRF_AZ_RX_DESCQ_EN_LBN 0
-#define	FRF_AZ_RX_DESCQ_EN_WIDTH 1
-
-/* TX_DESC_PTR_TBL_KER: Transmit descriptor pointer */
-#define	FR_AA_TX_DESC_PTR_TBL_KER 0x00011900
-#define	FR_AA_TX_DESC_PTR_TBL_KER_STEP 16
-#define	FR_AA_TX_DESC_PTR_TBL_KER_ROWS 8
-/* TX_DESC_PTR_TBL: Transmit descriptor pointer */
-#define	FR_BZ_TX_DESC_PTR_TBL 0x00f50000
-#define	FR_BZ_TX_DESC_PTR_TBL_STEP 16
-#define	FR_BB_TX_DESC_PTR_TBL_ROWS 4096
-#define	FR_CZ_TX_DESC_PTR_TBL_ROWS 1024
-#define	FRF_CZ_TX_DPT_Q_MASK_WIDTH_LBN 94
-#define	FRF_CZ_TX_DPT_Q_MASK_WIDTH_WIDTH 2
-#define	FRF_CZ_TX_DPT_ETH_FILT_EN_LBN 93
-#define	FRF_CZ_TX_DPT_ETH_FILT_EN_WIDTH 1
-#define	FRF_CZ_TX_DPT_IP_FILT_EN_LBN 92
-#define	FRF_CZ_TX_DPT_IP_FILT_EN_WIDTH 1
-#define	FRF_BZ_TX_NON_IP_DROP_DIS_LBN 91
-#define	FRF_BZ_TX_NON_IP_DROP_DIS_WIDTH 1
-#define	FRF_BZ_TX_IP_CHKSM_DIS_LBN 90
-#define	FRF_BZ_TX_IP_CHKSM_DIS_WIDTH 1
-#define	FRF_BZ_TX_TCP_CHKSM_DIS_LBN 89
-#define	FRF_BZ_TX_TCP_CHKSM_DIS_WIDTH 1
-#define	FRF_AZ_TX_DESCQ_EN_LBN 88
-#define	FRF_AZ_TX_DESCQ_EN_WIDTH 1
-#define	FRF_AZ_TX_ISCSI_DDIG_EN_LBN 87
-#define	FRF_AZ_TX_ISCSI_DDIG_EN_WIDTH 1
-#define	FRF_AZ_TX_ISCSI_HDIG_EN_LBN 86
-#define	FRF_AZ_TX_ISCSI_HDIG_EN_WIDTH 1
-#define	FRF_AZ_TX_DC_HW_RPTR_LBN 80
-#define	FRF_AZ_TX_DC_HW_RPTR_WIDTH 6
-#define	FRF_AZ_TX_DESCQ_HW_RPTR_LBN 68
-#define	FRF_AZ_TX_DESCQ_HW_RPTR_WIDTH 12
-#define	FRF_AZ_TX_DESCQ_SW_WPTR_LBN 56
-#define	FRF_AZ_TX_DESCQ_SW_WPTR_WIDTH 12
-#define	FRF_AZ_TX_DESCQ_BUF_BASE_ID_LBN 36
-#define	FRF_AZ_TX_DESCQ_BUF_BASE_ID_WIDTH 20
-#define	FRF_AZ_TX_DESCQ_EVQ_ID_LBN 24
-#define	FRF_AZ_TX_DESCQ_EVQ_ID_WIDTH 12
-#define	FRF_AZ_TX_DESCQ_OWNER_ID_LBN 10
-#define	FRF_AZ_TX_DESCQ_OWNER_ID_WIDTH 14
-#define	FRF_AZ_TX_DESCQ_LABEL_LBN 5
-#define	FRF_AZ_TX_DESCQ_LABEL_WIDTH 5
-#define	FRF_AZ_TX_DESCQ_SIZE_LBN 3
-#define	FRF_AZ_TX_DESCQ_SIZE_WIDTH 2
-#define	FFE_AZ_TX_DESCQ_SIZE_4K 3
-#define	FFE_AZ_TX_DESCQ_SIZE_2K 2
-#define	FFE_AZ_TX_DESCQ_SIZE_1K 1
-#define	FFE_AZ_TX_DESCQ_SIZE_512 0
-#define	FRF_AZ_TX_DESCQ_TYPE_LBN 1
-#define	FRF_AZ_TX_DESCQ_TYPE_WIDTH 2
-#define	FRF_AZ_TX_DESCQ_FLUSH_LBN 0
-#define	FRF_AZ_TX_DESCQ_FLUSH_WIDTH 1
-
-/* EVQ_PTR_TBL_KER: Event queue pointer table */
-#define	FR_AA_EVQ_PTR_TBL_KER 0x00011a00
-#define	FR_AA_EVQ_PTR_TBL_KER_STEP 16
-#define	FR_AA_EVQ_PTR_TBL_KER_ROWS 4
-/* EVQ_PTR_TBL: Event queue pointer table */
-#define	FR_BZ_EVQ_PTR_TBL 0x00f60000
-#define	FR_BZ_EVQ_PTR_TBL_STEP 16
-#define	FR_CZ_EVQ_PTR_TBL_ROWS 1024
-#define	FR_BB_EVQ_PTR_TBL_ROWS 4096
-#define	FRF_BZ_EVQ_RPTR_IGN_LBN 40
-#define	FRF_BZ_EVQ_RPTR_IGN_WIDTH 1
-#define	FRF_AB_EVQ_WKUP_OR_INT_EN_LBN 39
-#define	FRF_AB_EVQ_WKUP_OR_INT_EN_WIDTH 1
-#define	FRF_CZ_EVQ_DOS_PROTECT_EN_LBN 39
-#define	FRF_CZ_EVQ_DOS_PROTECT_EN_WIDTH 1
-#define	FRF_AZ_EVQ_NXT_WPTR_LBN 24
-#define	FRF_AZ_EVQ_NXT_WPTR_WIDTH 15
-#define	FRF_AZ_EVQ_EN_LBN 23
-#define	FRF_AZ_EVQ_EN_WIDTH 1
-#define	FRF_AZ_EVQ_SIZE_LBN 20
-#define	FRF_AZ_EVQ_SIZE_WIDTH 3
-#define	FFE_AZ_EVQ_SIZE_32K 6
-#define	FFE_AZ_EVQ_SIZE_16K 5
-#define	FFE_AZ_EVQ_SIZE_8K 4
-#define	FFE_AZ_EVQ_SIZE_4K 3
-#define	FFE_AZ_EVQ_SIZE_2K 2
-#define	FFE_AZ_EVQ_SIZE_1K 1
-#define	FFE_AZ_EVQ_SIZE_512 0
-#define	FRF_AZ_EVQ_BUF_BASE_ID_LBN 0
-#define	FRF_AZ_EVQ_BUF_BASE_ID_WIDTH 20
-
-/* BUF_HALF_TBL_KER: Buffer table in half buffer table mode direct access by driver */
-#define	FR_AA_BUF_HALF_TBL_KER 0x00018000
-#define	FR_AA_BUF_HALF_TBL_KER_STEP 8
-#define	FR_AA_BUF_HALF_TBL_KER_ROWS 4096
-/* BUF_HALF_TBL: Buffer table in half buffer table mode direct access by driver */
-#define	FR_BZ_BUF_HALF_TBL 0x00800000
-#define	FR_BZ_BUF_HALF_TBL_STEP 8
-#define	FR_CZ_BUF_HALF_TBL_ROWS 147456
-#define	FR_BB_BUF_HALF_TBL_ROWS 524288
-#define	FRF_AZ_BUF_ADR_HBUF_ODD_LBN 44
-#define	FRF_AZ_BUF_ADR_HBUF_ODD_WIDTH 20
-#define	FRF_AZ_BUF_OWNER_ID_HBUF_ODD_LBN 32
-#define	FRF_AZ_BUF_OWNER_ID_HBUF_ODD_WIDTH 12
-#define	FRF_AZ_BUF_ADR_HBUF_EVEN_LBN 12
-#define	FRF_AZ_BUF_ADR_HBUF_EVEN_WIDTH 20
-#define	FRF_AZ_BUF_OWNER_ID_HBUF_EVEN_LBN 0
-#define	FRF_AZ_BUF_OWNER_ID_HBUF_EVEN_WIDTH 12
-
-/* BUF_FULL_TBL_KER: Buffer table in full buffer table mode direct access by driver */
-#define	FR_AA_BUF_FULL_TBL_KER 0x00018000
-#define	FR_AA_BUF_FULL_TBL_KER_STEP 8
-#define	FR_AA_BUF_FULL_TBL_KER_ROWS 4096
-/* BUF_FULL_TBL: Buffer table in full buffer table mode direct access by driver */
-#define	FR_BZ_BUF_FULL_TBL 0x00800000
-#define	FR_BZ_BUF_FULL_TBL_STEP 8
-#define	FR_CZ_BUF_FULL_TBL_ROWS 147456
-#define	FR_BB_BUF_FULL_TBL_ROWS 917504
-#define	FRF_AZ_BUF_FULL_UNUSED_LBN 51
-#define	FRF_AZ_BUF_FULL_UNUSED_WIDTH 13
-#define	FRF_AZ_IP_DAT_BUF_SIZE_LBN 50
-#define	FRF_AZ_IP_DAT_BUF_SIZE_WIDTH 1
-#define	FRF_AZ_BUF_ADR_REGION_LBN 48
-#define	FRF_AZ_BUF_ADR_REGION_WIDTH 2
-#define	FFE_AZ_BUF_ADR_REGN3 3
-#define	FFE_AZ_BUF_ADR_REGN2 2
-#define	FFE_AZ_BUF_ADR_REGN1 1
-#define	FFE_AZ_BUF_ADR_REGN0 0
-#define	FRF_AZ_BUF_ADR_FBUF_LBN 14
-#define	FRF_AZ_BUF_ADR_FBUF_WIDTH 34
-#define	FRF_AZ_BUF_OWNER_ID_FBUF_LBN 0
-#define	FRF_AZ_BUF_OWNER_ID_FBUF_WIDTH 14
-
-/* RX_FILTER_TBL0: TCP/IPv4 Receive filter table */
-#define	FR_BZ_RX_FILTER_TBL0 0x00f00000
-#define	FR_BZ_RX_FILTER_TBL0_STEP 32
-#define	FR_BZ_RX_FILTER_TBL0_ROWS 8192
-/* RX_FILTER_TBL1: TCP/IPv4 Receive filter table */
-#define	FR_BB_RX_FILTER_TBL1 0x00f00010
-#define	FR_BB_RX_FILTER_TBL1_STEP 32
-#define	FR_BB_RX_FILTER_TBL1_ROWS 8192
-#define	FRF_BZ_RSS_EN_LBN 110
-#define	FRF_BZ_RSS_EN_WIDTH 1
-#define	FRF_BZ_SCATTER_EN_LBN 109
-#define	FRF_BZ_SCATTER_EN_WIDTH 1
-#define	FRF_BZ_TCP_UDP_LBN 108
-#define	FRF_BZ_TCP_UDP_WIDTH 1
-#define	FRF_BZ_RXQ_ID_LBN 96
-#define	FRF_BZ_RXQ_ID_WIDTH 12
-#define	FRF_BZ_DEST_IP_LBN 64
-#define	FRF_BZ_DEST_IP_WIDTH 32
-#define	FRF_BZ_DEST_PORT_TCP_LBN 48
-#define	FRF_BZ_DEST_PORT_TCP_WIDTH 16
-#define	FRF_BZ_SRC_IP_LBN 16
-#define	FRF_BZ_SRC_IP_WIDTH 32
-#define	FRF_BZ_SRC_TCP_DEST_UDP_LBN 0
-#define	FRF_BZ_SRC_TCP_DEST_UDP_WIDTH 16
-
-/* RX_MAC_FILTER_TBL0: Receive Ethernet filter table */
-#define	FR_CZ_RX_MAC_FILTER_TBL0 0x00f00010
-#define	FR_CZ_RX_MAC_FILTER_TBL0_STEP 32
-#define	FR_CZ_RX_MAC_FILTER_TBL0_ROWS 512
-#define	FRF_CZ_RMFT_RSS_EN_LBN 75
-#define	FRF_CZ_RMFT_RSS_EN_WIDTH 1
-#define	FRF_CZ_RMFT_SCATTER_EN_LBN 74
-#define	FRF_CZ_RMFT_SCATTER_EN_WIDTH 1
-#define	FRF_CZ_RMFT_IP_OVERRIDE_LBN 73
-#define	FRF_CZ_RMFT_IP_OVERRIDE_WIDTH 1
-#define	FRF_CZ_RMFT_RXQ_ID_LBN 61
-#define	FRF_CZ_RMFT_RXQ_ID_WIDTH 12
-#define	FRF_CZ_RMFT_WILDCARD_MATCH_LBN 60
-#define	FRF_CZ_RMFT_WILDCARD_MATCH_WIDTH 1
-#define	FRF_CZ_RMFT_DEST_MAC_LBN 12
-#define	FRF_CZ_RMFT_DEST_MAC_WIDTH 48
-#define	FRF_CZ_RMFT_VLAN_ID_LBN 0
-#define	FRF_CZ_RMFT_VLAN_ID_WIDTH 12
-
-/* TIMER_TBL: Timer table */
-#define	FR_BZ_TIMER_TBL 0x00f70000
-#define	FR_BZ_TIMER_TBL_STEP 16
-#define	FR_CZ_TIMER_TBL_ROWS 1024
-#define	FR_BB_TIMER_TBL_ROWS 4096
-#define	FRF_CZ_TIMER_Q_EN_LBN 33
-#define	FRF_CZ_TIMER_Q_EN_WIDTH 1
-#define	FRF_CZ_INT_ARMD_LBN 32
-#define	FRF_CZ_INT_ARMD_WIDTH 1
-#define	FRF_CZ_INT_PEND_LBN 31
-#define	FRF_CZ_INT_PEND_WIDTH 1
-#define	FRF_CZ_HOST_NOTIFY_MODE_LBN 30
-#define	FRF_CZ_HOST_NOTIFY_MODE_WIDTH 1
-#define	FRF_CZ_RELOAD_TIMER_VAL_LBN 16
-#define	FRF_CZ_RELOAD_TIMER_VAL_WIDTH 14
-#define	FRF_CZ_TIMER_MODE_LBN 14
-#define	FRF_CZ_TIMER_MODE_WIDTH 2
-#define	FFE_CZ_TIMER_MODE_INT_HLDOFF 3
-#define	FFE_CZ_TIMER_MODE_TRIG_START 2
-#define	FFE_CZ_TIMER_MODE_IMMED_START 1
-#define	FFE_CZ_TIMER_MODE_DIS 0
-#define	FRF_BB_TIMER_MODE_LBN 12
-#define	FRF_BB_TIMER_MODE_WIDTH 2
-#define	FFE_BB_TIMER_MODE_INT_HLDOFF 2
-#define	FFE_BB_TIMER_MODE_TRIG_START 2
-#define	FFE_BB_TIMER_MODE_IMMED_START 1
-#define	FFE_BB_TIMER_MODE_DIS 0
-#define	FRF_CZ_TIMER_VAL_LBN 0
-#define	FRF_CZ_TIMER_VAL_WIDTH 14
-#define	FRF_BB_TIMER_VAL_LBN 0
-#define	FRF_BB_TIMER_VAL_WIDTH 12
-
-/* TX_PACE_TBL: Transmit pacing table */
-#define	FR_BZ_TX_PACE_TBL 0x00f80000
-#define	FR_BZ_TX_PACE_TBL_STEP 16
-#define	FR_CZ_TX_PACE_TBL_ROWS 1024
-#define	FR_BB_TX_PACE_TBL_ROWS 4096
-#define	FRF_BZ_TX_PACE_LBN 0
-#define	FRF_BZ_TX_PACE_WIDTH 5
-
-/* RX_INDIRECTION_TBL: RX Indirection Table */
-#define	FR_BZ_RX_INDIRECTION_TBL 0x00fb0000
-#define	FR_BZ_RX_INDIRECTION_TBL_STEP 16
-#define	FR_BZ_RX_INDIRECTION_TBL_ROWS 128
-#define	FRF_BZ_IT_QUEUE_LBN 0
-#define	FRF_BZ_IT_QUEUE_WIDTH 6
-
-/* TX_FILTER_TBL0: TCP/IPv4 Transmit filter table */
-#define	FR_CZ_TX_FILTER_TBL0 0x00fc0000
-#define	FR_CZ_TX_FILTER_TBL0_STEP 16
-#define	FR_CZ_TX_FILTER_TBL0_ROWS 8192
-#define	FRF_CZ_TIFT_TCP_UDP_LBN 108
-#define	FRF_CZ_TIFT_TCP_UDP_WIDTH 1
-#define	FRF_CZ_TIFT_TXQ_ID_LBN 96
-#define	FRF_CZ_TIFT_TXQ_ID_WIDTH 12
-#define	FRF_CZ_TIFT_DEST_IP_LBN 64
-#define	FRF_CZ_TIFT_DEST_IP_WIDTH 32
-#define	FRF_CZ_TIFT_DEST_PORT_TCP_LBN 48
-#define	FRF_CZ_TIFT_DEST_PORT_TCP_WIDTH 16
-#define	FRF_CZ_TIFT_SRC_IP_LBN 16
-#define	FRF_CZ_TIFT_SRC_IP_WIDTH 32
-#define	FRF_CZ_TIFT_SRC_TCP_DEST_UDP_LBN 0
-#define	FRF_CZ_TIFT_SRC_TCP_DEST_UDP_WIDTH 16
-
-/* TX_MAC_FILTER_TBL0: Transmit Ethernet filter table */
-#define	FR_CZ_TX_MAC_FILTER_TBL0 0x00fe0000
-#define	FR_CZ_TX_MAC_FILTER_TBL0_STEP 16
-#define	FR_CZ_TX_MAC_FILTER_TBL0_ROWS 512
-#define	FRF_CZ_TMFT_TXQ_ID_LBN 61
-#define	FRF_CZ_TMFT_TXQ_ID_WIDTH 12
-#define	FRF_CZ_TMFT_WILDCARD_MATCH_LBN 60
-#define	FRF_CZ_TMFT_WILDCARD_MATCH_WIDTH 1
-#define	FRF_CZ_TMFT_SRC_MAC_LBN 12
-#define	FRF_CZ_TMFT_SRC_MAC_WIDTH 48
-#define	FRF_CZ_TMFT_VLAN_ID_LBN 0
-#define	FRF_CZ_TMFT_VLAN_ID_WIDTH 12
-
-/* MC_TREG_SMEM: MC Shared Memory */
-#define	FR_CZ_MC_TREG_SMEM 0x00ff0000
-#define	FR_CZ_MC_TREG_SMEM_STEP 4
-#define	FR_CZ_MC_TREG_SMEM_ROWS 512
-#define	FRF_CZ_MC_TREG_SMEM_ROW_LBN 0
-#define	FRF_CZ_MC_TREG_SMEM_ROW_WIDTH 32
-
-/* MSIX_VECTOR_TABLE: MSIX Vector Table */
-#define	FR_BB_MSIX_VECTOR_TABLE 0x00ff0000
-#define	FR_BZ_MSIX_VECTOR_TABLE_STEP 16
-#define	FR_BB_MSIX_VECTOR_TABLE_ROWS 64
-/* MSIX_VECTOR_TABLE: MSIX Vector Table */
-#define	FR_CZ_MSIX_VECTOR_TABLE 0x00000000
-/* FR_BZ_MSIX_VECTOR_TABLE_STEP 16 */
-#define	FR_CZ_MSIX_VECTOR_TABLE_ROWS 1024
-#define	FRF_BZ_MSIX_VECTOR_RESERVED_LBN 97
-#define	FRF_BZ_MSIX_VECTOR_RESERVED_WIDTH 31
-#define	FRF_BZ_MSIX_VECTOR_MASK_LBN 96
-#define	FRF_BZ_MSIX_VECTOR_MASK_WIDTH 1
-#define	FRF_BZ_MSIX_MESSAGE_DATA_LBN 64
-#define	FRF_BZ_MSIX_MESSAGE_DATA_WIDTH 32
-#define	FRF_BZ_MSIX_MESSAGE_ADDRESS_HI_LBN 32
-#define	FRF_BZ_MSIX_MESSAGE_ADDRESS_HI_WIDTH 32
-#define	FRF_BZ_MSIX_MESSAGE_ADDRESS_LO_LBN 0
-#define	FRF_BZ_MSIX_MESSAGE_ADDRESS_LO_WIDTH 32
-
-/* MSIX_PBA_TABLE: MSIX Pending Bit Array */
-#define	FR_BB_MSIX_PBA_TABLE 0x00ff2000
-#define	FR_BZ_MSIX_PBA_TABLE_STEP 4
-#define	FR_BB_MSIX_PBA_TABLE_ROWS 2
-/* MSIX_PBA_TABLE: MSIX Pending Bit Array */
-#define	FR_CZ_MSIX_PBA_TABLE 0x00008000
-/* FR_BZ_MSIX_PBA_TABLE_STEP 4 */
-#define	FR_CZ_MSIX_PBA_TABLE_ROWS 32
-#define	FRF_BZ_MSIX_PBA_PEND_DWORD_LBN 0
-#define	FRF_BZ_MSIX_PBA_PEND_DWORD_WIDTH 32
-
-/* SRM_DBG_REG: SRAM debug access */
-#define	FR_BZ_SRM_DBG 0x03000000
-#define	FR_BZ_SRM_DBG_STEP 8
-#define	FR_CZ_SRM_DBG_ROWS 262144
-#define	FR_BB_SRM_DBG_ROWS 2097152
-#define	FRF_BZ_SRM_DBG_LBN 0
-#define	FRF_BZ_SRM_DBG_WIDTH 64
-
-/* TB_MSIX_PBA_TABLE: MSIX Pending Bit Array */
-#define	FR_CZ_TB_MSIX_PBA_TABLE 0x00008000
-#define	FR_CZ_TB_MSIX_PBA_TABLE_STEP 4
-#define	FR_CZ_TB_MSIX_PBA_TABLE_ROWS 1024
-#define	FRF_CZ_TB_MSIX_PBA_PEND_DWORD_LBN 0
-#define	FRF_CZ_TB_MSIX_PBA_PEND_DWORD_WIDTH 32
-
-/* DRIVER_EV */
-#define	FSF_AZ_DRIVER_EV_SUBCODE_LBN 56
-#define	FSF_AZ_DRIVER_EV_SUBCODE_WIDTH 4
-#define	FSE_BZ_TX_DSC_ERROR_EV 15
-#define	FSE_BZ_RX_DSC_ERROR_EV 14
-#define	FSE_AA_RX_RECOVER_EV 11
-#define	FSE_AZ_TIMER_EV 10
-#define	FSE_AZ_TX_PKT_NON_TCP_UDP 9
-#define	FSE_AZ_WAKE_UP_EV 6
-#define	FSE_AZ_SRM_UPD_DONE_EV 5
-#define	FSE_AB_EVQ_NOT_EN_EV 3
-#define	FSE_AZ_EVQ_INIT_DONE_EV 2
-#define	FSE_AZ_RX_DESCQ_FLS_DONE_EV 1
-#define	FSE_AZ_TX_DESCQ_FLS_DONE_EV 0
-#define	FSF_AZ_DRIVER_EV_SUBDATA_LBN 0
-#define	FSF_AZ_DRIVER_EV_SUBDATA_WIDTH 14
-
-/* EVENT_ENTRY */
-#define	FSF_AZ_EV_CODE_LBN 60
-#define	FSF_AZ_EV_CODE_WIDTH 4
-#define	FSE_CZ_EV_CODE_MCDI_EV 12
-#define	FSE_CZ_EV_CODE_USER_EV 8
-#define	FSE_AZ_EV_CODE_DRV_GEN_EV 7
-#define	FSE_AZ_EV_CODE_GLOBAL_EV 6
-#define	FSE_AZ_EV_CODE_DRIVER_EV 5
-#define	FSE_AZ_EV_CODE_TX_EV 2
-#define	FSE_AZ_EV_CODE_RX_EV 0
-#define	FSF_AZ_EV_DATA_LBN 0
-#define	FSF_AZ_EV_DATA_WIDTH 60
-
-/* GLOBAL_EV */
-#define	FSF_BB_GLB_EV_RX_RECOVERY_LBN 12
-#define	FSF_BB_GLB_EV_RX_RECOVERY_WIDTH 1
-#define	FSF_AA_GLB_EV_RX_RECOVERY_LBN 11
-#define	FSF_AA_GLB_EV_RX_RECOVERY_WIDTH 1
-#define	FSF_BB_GLB_EV_XG_MGT_INTR_LBN 11
-#define	FSF_BB_GLB_EV_XG_MGT_INTR_WIDTH 1
-#define	FSF_AB_GLB_EV_XFP_PHY0_INTR_LBN 10
-#define	FSF_AB_GLB_EV_XFP_PHY0_INTR_WIDTH 1
-#define	FSF_AB_GLB_EV_XG_PHY0_INTR_LBN 9
-#define	FSF_AB_GLB_EV_XG_PHY0_INTR_WIDTH 1
-#define	FSF_AB_GLB_EV_G_PHY0_INTR_LBN 7
-#define	FSF_AB_GLB_EV_G_PHY0_INTR_WIDTH 1
-
-/* LEGACY_INT_VEC */
-#define	FSF_AZ_NET_IVEC_FATAL_INT_LBN 64
-#define	FSF_AZ_NET_IVEC_FATAL_INT_WIDTH 1
-#define	FSF_AZ_NET_IVEC_INT_Q_LBN 40
-#define	FSF_AZ_NET_IVEC_INT_Q_WIDTH 4
-#define	FSF_AZ_NET_IVEC_INT_FLAG_LBN 32
-#define	FSF_AZ_NET_IVEC_INT_FLAG_WIDTH 1
-#define	FSF_AZ_NET_IVEC_EVQ_FIFO_HF_LBN 1
-#define	FSF_AZ_NET_IVEC_EVQ_FIFO_HF_WIDTH 1
-#define	FSF_AZ_NET_IVEC_EVQ_FIFO_AF_LBN 0
-#define	FSF_AZ_NET_IVEC_EVQ_FIFO_AF_WIDTH 1
-
-/* MC_XGMAC_FLTR_RULE_DEF */
-#define	FSF_CZ_MC_XFRC_MODE_LBN 416
-#define	FSF_CZ_MC_XFRC_MODE_WIDTH 1
-#define	FSE_CZ_MC_XFRC_MODE_LAYERED 1
-#define	FSE_CZ_MC_XFRC_MODE_SIMPLE 0
-#define	FSF_CZ_MC_XFRC_HASH_LBN 384
-#define	FSF_CZ_MC_XFRC_HASH_WIDTH 32
-#define	FSF_CZ_MC_XFRC_LAYER4_BYTE_MASK_LBN 256
-#define	FSF_CZ_MC_XFRC_LAYER4_BYTE_MASK_WIDTH 128
-#define	FSF_CZ_MC_XFRC_LAYER3_BYTE_MASK_LBN 128
-#define	FSF_CZ_MC_XFRC_LAYER3_BYTE_MASK_WIDTH 128
-#define	FSF_CZ_MC_XFRC_LAYER2_OR_SIMPLE_BYTE_MASK_LBN 0
-#define	FSF_CZ_MC_XFRC_LAYER2_OR_SIMPLE_BYTE_MASK_WIDTH 128
-
-/* RX_EV */
-#define	FSF_CZ_RX_EV_PKT_NOT_PARSED_LBN 58
-#define	FSF_CZ_RX_EV_PKT_NOT_PARSED_WIDTH 1
-#define	FSF_CZ_RX_EV_IPV6_PKT_LBN 57
-#define	FSF_CZ_RX_EV_IPV6_PKT_WIDTH 1
-#define	FSF_AZ_RX_EV_PKT_OK_LBN 56
-#define	FSF_AZ_RX_EV_PKT_OK_WIDTH 1
-#define	FSF_AZ_RX_EV_PAUSE_FRM_ERR_LBN 55
-#define	FSF_AZ_RX_EV_PAUSE_FRM_ERR_WIDTH 1
-#define	FSF_AZ_RX_EV_BUF_OWNER_ID_ERR_LBN 54
-#define	FSF_AZ_RX_EV_BUF_OWNER_ID_ERR_WIDTH 1
-#define	FSF_AZ_RX_EV_IP_FRAG_ERR_LBN 53
-#define	FSF_AZ_RX_EV_IP_FRAG_ERR_WIDTH 1
-#define	FSF_AZ_RX_EV_IP_HDR_CHKSUM_ERR_LBN 52
-#define	FSF_AZ_RX_EV_IP_HDR_CHKSUM_ERR_WIDTH 1
-#define	FSF_AZ_RX_EV_TCP_UDP_CHKSUM_ERR_LBN 51
-#define	FSF_AZ_RX_EV_TCP_UDP_CHKSUM_ERR_WIDTH 1
-#define	FSF_AZ_RX_EV_ETH_CRC_ERR_LBN 50
-#define	FSF_AZ_RX_EV_ETH_CRC_ERR_WIDTH 1
-#define	FSF_AZ_RX_EV_FRM_TRUNC_LBN 49
-#define	FSF_AZ_RX_EV_FRM_TRUNC_WIDTH 1
-#define	FSF_AA_RX_EV_DRIB_NIB_LBN 49
-#define	FSF_AA_RX_EV_DRIB_NIB_WIDTH 1
-#define	FSF_AZ_RX_EV_TOBE_DISC_LBN 47
-#define	FSF_AZ_RX_EV_TOBE_DISC_WIDTH 1
-#define	FSF_AZ_RX_EV_PKT_TYPE_LBN 44
-#define	FSF_AZ_RX_EV_PKT_TYPE_WIDTH 3
-#define	FSE_AZ_RX_EV_PKT_TYPE_VLAN_JUMBO 5
-#define	FSE_AZ_RX_EV_PKT_TYPE_VLAN_LLC 4
-#define	FSE_AZ_RX_EV_PKT_TYPE_VLAN 3
-#define	FSE_AZ_RX_EV_PKT_TYPE_JUMBO 2
-#define	FSE_AZ_RX_EV_PKT_TYPE_LLC 1
-#define	FSE_AZ_RX_EV_PKT_TYPE_ETH 0
-#define	FSF_AZ_RX_EV_HDR_TYPE_LBN 42
-#define	FSF_AZ_RX_EV_HDR_TYPE_WIDTH 2
-#define	FSE_AZ_RX_EV_HDR_TYPE_OTHER 3
-#define	FSE_AB_RX_EV_HDR_TYPE_IPV4_OTHER 2
-#define	FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_OTHER 2
-#define	FSE_AB_RX_EV_HDR_TYPE_IPV4_UDP 1
-#define	FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP 1
-#define	FSE_AB_RX_EV_HDR_TYPE_IPV4_TCP 0
-#define	FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP 0
-#define	FSF_AZ_RX_EV_DESC_Q_EMPTY_LBN 41
-#define	FSF_AZ_RX_EV_DESC_Q_EMPTY_WIDTH 1
-#define	FSF_AZ_RX_EV_MCAST_HASH_MATCH_LBN 40
-#define	FSF_AZ_RX_EV_MCAST_HASH_MATCH_WIDTH 1
-#define	FSF_AZ_RX_EV_MCAST_PKT_LBN 39
-#define	FSF_AZ_RX_EV_MCAST_PKT_WIDTH 1
-#define	FSF_AA_RX_EV_RECOVERY_FLAG_LBN 37
-#define	FSF_AA_RX_EV_RECOVERY_FLAG_WIDTH 1
-#define	FSF_AZ_RX_EV_Q_LABEL_LBN 32
-#define	FSF_AZ_RX_EV_Q_LABEL_WIDTH 5
-#define	FSF_AZ_RX_EV_JUMBO_CONT_LBN 31
-#define	FSF_AZ_RX_EV_JUMBO_CONT_WIDTH 1
-#define	FSF_AZ_RX_EV_PORT_LBN 30
-#define	FSF_AZ_RX_EV_PORT_WIDTH 1
-#define	FSF_AZ_RX_EV_BYTE_CNT_LBN 16
-#define	FSF_AZ_RX_EV_BYTE_CNT_WIDTH 14
-#define	FSF_AZ_RX_EV_SOP_LBN 15
-#define	FSF_AZ_RX_EV_SOP_WIDTH 1
-#define	FSF_AZ_RX_EV_ISCSI_PKT_OK_LBN 14
-#define	FSF_AZ_RX_EV_ISCSI_PKT_OK_WIDTH 1
-#define	FSF_AZ_RX_EV_ISCSI_DDIG_ERR_LBN 13
-#define	FSF_AZ_RX_EV_ISCSI_DDIG_ERR_WIDTH 1
-#define	FSF_AZ_RX_EV_ISCSI_HDIG_ERR_LBN 12
-#define	FSF_AZ_RX_EV_ISCSI_HDIG_ERR_WIDTH 1
-#define	FSF_AZ_RX_EV_DESC_PTR_LBN 0
-#define	FSF_AZ_RX_EV_DESC_PTR_WIDTH 12
-
-/* RX_KER_DESC */
-#define	FSF_AZ_RX_KER_BUF_SIZE_LBN 48
-#define	FSF_AZ_RX_KER_BUF_SIZE_WIDTH 14
-#define	FSF_AZ_RX_KER_BUF_REGION_LBN 46
-#define	FSF_AZ_RX_KER_BUF_REGION_WIDTH 2
-#define	FSF_AZ_RX_KER_BUF_ADDR_LBN 0
-#define	FSF_AZ_RX_KER_BUF_ADDR_WIDTH 46
-
-/* RX_USER_DESC */
-#define	FSF_AZ_RX_USER_2BYTE_OFFSET_LBN 20
-#define	FSF_AZ_RX_USER_2BYTE_OFFSET_WIDTH 12
-#define	FSF_AZ_RX_USER_BUF_ID_LBN 0
-#define	FSF_AZ_RX_USER_BUF_ID_WIDTH 20
-
-/* TX_EV */
-#define	FSF_AZ_TX_EV_PKT_ERR_LBN 38
-#define	FSF_AZ_TX_EV_PKT_ERR_WIDTH 1
-#define	FSF_AZ_TX_EV_PKT_TOO_BIG_LBN 37
-#define	FSF_AZ_TX_EV_PKT_TOO_BIG_WIDTH 1
-#define	FSF_AZ_TX_EV_Q_LABEL_LBN 32
-#define	FSF_AZ_TX_EV_Q_LABEL_WIDTH 5
-#define	FSF_AZ_TX_EV_PORT_LBN 16
-#define	FSF_AZ_TX_EV_PORT_WIDTH 1
-#define	FSF_AZ_TX_EV_WQ_FF_FULL_LBN 15
-#define	FSF_AZ_TX_EV_WQ_FF_FULL_WIDTH 1
-#define	FSF_AZ_TX_EV_BUF_OWNER_ID_ERR_LBN 14
-#define	FSF_AZ_TX_EV_BUF_OWNER_ID_ERR_WIDTH 1
-#define	FSF_AZ_TX_EV_COMP_LBN 12
-#define	FSF_AZ_TX_EV_COMP_WIDTH 1
-#define	FSF_AZ_TX_EV_DESC_PTR_LBN 0
-#define	FSF_AZ_TX_EV_DESC_PTR_WIDTH 12
-
-/* TX_KER_DESC */
-#define	FSF_AZ_TX_KER_CONT_LBN 62
-#define	FSF_AZ_TX_KER_CONT_WIDTH 1
-#define	FSF_AZ_TX_KER_BYTE_COUNT_LBN 48
-#define	FSF_AZ_TX_KER_BYTE_COUNT_WIDTH 14
-#define	FSF_AZ_TX_KER_BUF_REGION_LBN 46
-#define	FSF_AZ_TX_KER_BUF_REGION_WIDTH 2
-#define	FSF_AZ_TX_KER_BUF_ADDR_LBN 0
-#define	FSF_AZ_TX_KER_BUF_ADDR_WIDTH 46
-
-/* TX_USER_DESC */
-#define	FSF_AZ_TX_USER_SW_EV_EN_LBN 48
-#define	FSF_AZ_TX_USER_SW_EV_EN_WIDTH 1
-#define	FSF_AZ_TX_USER_CONT_LBN 46
-#define	FSF_AZ_TX_USER_CONT_WIDTH 1
-#define	FSF_AZ_TX_USER_BYTE_CNT_LBN 33
-#define	FSF_AZ_TX_USER_BYTE_CNT_WIDTH 13
-#define	FSF_AZ_TX_USER_BUF_ID_LBN 13
-#define	FSF_AZ_TX_USER_BUF_ID_WIDTH 20
-#define	FSF_AZ_TX_USER_BYTE_OFS_LBN 0
-#define	FSF_AZ_TX_USER_BYTE_OFS_WIDTH 13
-
-/* USER_EV */
-#define	FSF_CZ_USER_QID_LBN 32
-#define	FSF_CZ_USER_QID_WIDTH 10
-#define	FSF_CZ_USER_EV_REG_VALUE_LBN 0
-#define	FSF_CZ_USER_EV_REG_VALUE_WIDTH 32
-
-/**************************************************************************
- *
- * Falcon B0 PCIe core indirect registers
- *
- **************************************************************************
- */
-
-#define FPCR_BB_PCIE_DEVICE_CTRL_STAT 0x68
-
-#define FPCR_BB_PCIE_LINK_CTRL_STAT 0x70
-
-#define FPCR_BB_ACK_RPL_TIMER 0x700
-#define FPCRF_BB_ACK_TL_LBN 0
-#define FPCRF_BB_ACK_TL_WIDTH 16
-#define FPCRF_BB_RPL_TL_LBN 16
-#define FPCRF_BB_RPL_TL_WIDTH 16
-
-#define FPCR_BB_ACK_FREQ 0x70C
-#define FPCRF_BB_ACK_FREQ_LBN 0
-#define FPCRF_BB_ACK_FREQ_WIDTH 7
-
-/**************************************************************************
- *
- * Pseudo-registers and fields
- *
- **************************************************************************
- */
-
-/* Interrupt acknowledge work-around register (A0/A1 only) */
-#define FR_AA_WORK_AROUND_BROKEN_PCI_READS 0x0070
-
-/* EE_SPI_HCMD_REG: SPI host command register */
-/* Values for the EE_SPI_HCMD_SF_SEL register field */
-#define FFE_AB_SPI_DEVICE_EEPROM 0
-#define FFE_AB_SPI_DEVICE_FLASH 1
-
-/* NIC_STAT_REG: NIC status register */
-#define FRF_AB_STRAP_10G_LBN 2
-#define FRF_AB_STRAP_10G_WIDTH 1
-#define FRF_AA_STRAP_PCIE_LBN 0
-#define FRF_AA_STRAP_PCIE_WIDTH 1
-
-/* FATAL_INTR_REG_KER: Fatal interrupt register for Kernel */
-#define FRF_AZ_FATAL_INTR_LBN 0
-#define FRF_AZ_FATAL_INTR_WIDTH 12
-
-/* SRM_CFG_REG: SRAM configuration register */
-/* We treat the number of SRAM banks and bank size as a single field */
-#define	FRF_AZ_SRM_NB_SZ_LBN FRF_AZ_SRM_BANK_SIZE_LBN
-#define	FRF_AZ_SRM_NB_SZ_WIDTH \
-	(FRF_AZ_SRM_BANK_SIZE_WIDTH + FRF_AZ_SRM_NUM_BANK_WIDTH)
-#define FFE_AB_SRM_NB1_SZ2M 0
-#define FFE_AB_SRM_NB1_SZ4M 1
-#define FFE_AB_SRM_NB1_SZ8M 2
-#define FFE_AB_SRM_NB_SZ_DEF 3
-#define FFE_AB_SRM_NB2_SZ4M 4
-#define FFE_AB_SRM_NB2_SZ8M 5
-#define FFE_AB_SRM_NB2_SZ16M 6
-#define FFE_AB_SRM_NB_SZ_RES 7
-
-/* RX_DESC_UPD_REGP0: Receive descriptor update register. */
-/* We write just the last dword of these registers */
-#define	FR_AZ_RX_DESC_UPD_DWORD_P0 \
-	(BUILD_BUG_ON_ZERO(FR_AA_RX_DESC_UPD_KER != FR_BZ_RX_DESC_UPD_P0) + \
-	 FR_BZ_RX_DESC_UPD_P0 + 3 * 4)
-#define	FRF_AZ_RX_DESC_WPTR_DWORD_LBN (FRF_AZ_RX_DESC_WPTR_LBN - 3 * 32)
-#define	FRF_AZ_RX_DESC_WPTR_DWORD_WIDTH FRF_AZ_RX_DESC_WPTR_WIDTH
-
-/* TX_DESC_UPD_REGP0: Transmit descriptor update register. */
-#define FR_AZ_TX_DESC_UPD_DWORD_P0 \
-	(BUILD_BUG_ON_ZERO(FR_AA_TX_DESC_UPD_KER != FR_BZ_TX_DESC_UPD_P0) + \
-	 FR_BZ_TX_DESC_UPD_P0 + 3 * 4)
-#define	FRF_AZ_TX_DESC_WPTR_DWORD_LBN (FRF_AZ_TX_DESC_WPTR_LBN - 3 * 32)
-#define	FRF_AZ_TX_DESC_WPTR_DWORD_WIDTH FRF_AZ_TX_DESC_WPTR_WIDTH
-
-/* GMF_CFG4_REG: GMAC FIFO configuration register 4 */
-#define FRF_AB_GMF_HSTFLTRFRM_PAUSE_LBN 12
-#define FRF_AB_GMF_HSTFLTRFRM_PAUSE_WIDTH 1
-
-/* GMF_CFG5_REG: GMAC FIFO configuration register 5 */
-#define FRF_AB_GMF_HSTFLTRFRMDC_PAUSE_LBN 12
-#define FRF_AB_GMF_HSTFLTRFRMDC_PAUSE_WIDTH 1
-
-/* XM_TX_PARAM_REG: XGMAC transmit parameter register */
-#define	FRF_AB_XM_MAX_TX_FRM_SIZE_LBN FRF_AB_XM_MAX_TX_FRM_SIZE_LO_LBN
-#define	FRF_AB_XM_MAX_TX_FRM_SIZE_WIDTH (FRF_AB_XM_MAX_TX_FRM_SIZE_HI_WIDTH + \
-					 FRF_AB_XM_MAX_TX_FRM_SIZE_LO_WIDTH)
-
-/* XM_RX_PARAM_REG: XGMAC receive parameter register */
-#define	FRF_AB_XM_MAX_RX_FRM_SIZE_LBN FRF_AB_XM_MAX_RX_FRM_SIZE_LO_LBN
-#define	FRF_AB_XM_MAX_RX_FRM_SIZE_WIDTH (FRF_AB_XM_MAX_RX_FRM_SIZE_HI_WIDTH + \
-					 FRF_AB_XM_MAX_RX_FRM_SIZE_LO_WIDTH)
-
-/* XX_TXDRV_CTL_REG: XAUI SerDes transmit drive control register */
-/* Default values */
-#define FFE_AB_XX_TXDRV_DEQ_DEF 0xe /* deq=.6 */
-#define FFE_AB_XX_TXDRV_DTX_DEF 0x5 /* 1.25 */
-#define FFE_AB_XX_SD_CTL_DRV_DEF 0  /* 20mA */
-
-/* XX_CORE_STAT_REG: XAUI XGXS core status register */
-/* XGXS all-lanes status fields */
-#define	FRF_AB_XX_SYNC_STAT_LBN FRF_AB_XX_SYNC_STAT0_LBN
-#define	FRF_AB_XX_SYNC_STAT_WIDTH 4
-#define	FRF_AB_XX_COMMA_DET_LBN FRF_AB_XX_COMMA_DET_CH0_LBN
-#define	FRF_AB_XX_COMMA_DET_WIDTH 4
-#define	FRF_AB_XX_CHAR_ERR_LBN FRF_AB_XX_CHAR_ERR_CH0_LBN
-#define	FRF_AB_XX_CHAR_ERR_WIDTH 4
-#define	FRF_AB_XX_DISPERR_LBN FRF_AB_XX_DISPERR_CH0_LBN
-#define	FRF_AB_XX_DISPERR_WIDTH 4
-#define	FFE_AB_XX_STAT_ALL_LANES 0xf
-#define	FRF_AB_XX_FORCE_SIG_LBN FRF_AB_XX_FORCE_SIG0_VAL_LBN
-#define	FRF_AB_XX_FORCE_SIG_WIDTH 8
-#define	FFE_AB_XX_FORCE_SIG_ALL_LANES 0xff
-
-/* RX_MAC_FILTER_TBL0 */
-/* RMFT_DEST_MAC is wider than 32 bits */
-#define FRF_CZ_RMFT_DEST_MAC_LO_LBN FRF_CZ_RMFT_DEST_MAC_LBN
-#define FRF_CZ_RMFT_DEST_MAC_LO_WIDTH 32
-#define FRF_CZ_RMFT_DEST_MAC_HI_LBN (FRF_CZ_RMFT_DEST_MAC_LBN + 32)
-#define FRF_CZ_RMFT_DEST_MAC_HI_WIDTH (FRF_CZ_RMFT_DEST_MAC_WIDTH - 32)
-
-/* TX_MAC_FILTER_TBL0 */
-/* TMFT_SRC_MAC is wider than 32 bits */
-#define FRF_CZ_TMFT_SRC_MAC_LO_LBN FRF_CZ_TMFT_SRC_MAC_LBN
-#define FRF_CZ_TMFT_SRC_MAC_LO_WIDTH 32
-#define FRF_CZ_TMFT_SRC_MAC_HI_LBN (FRF_CZ_TMFT_SRC_MAC_LBN + 32)
-#define FRF_CZ_TMFT_SRC_MAC_HI_WIDTH (FRF_CZ_TMFT_SRC_MAC_WIDTH - 32)
-
-/* TX_PACE_TBL */
-/* Values >20 are documented as reserved, but will result in a queue going
- * into the fast bin with a pace value of zero. */
-#define FFE_BZ_TX_PACE_OFF 0
-#define FFE_BZ_TX_PACE_RESERVED 21
-
-/* DRIVER_EV */
-/* Sub-fields of an RX flush completion event */
-#define FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL_LBN 12
-#define FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL_WIDTH 1
-#define FSF_AZ_DRIVER_EV_RX_DESCQ_ID_LBN 0
-#define FSF_AZ_DRIVER_EV_RX_DESCQ_ID_WIDTH 12
-
-/* EVENT_ENTRY */
-/* Magic number field for event test */
-#define FSF_AZ_DRV_GEN_EV_MAGIC_LBN 0
-#define FSF_AZ_DRV_GEN_EV_MAGIC_WIDTH 32
-
-/* RX packet prefix */
-#define FS_BZ_RX_PREFIX_HASH_OFST 12
-#define FS_BZ_RX_PREFIX_SIZE 16
-
-#endif /* EFX_FARCH_REGS_H */
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index a7f2c31071e83..86cfd4713b11e 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -10,7 +10,6 @@
 #include "net_driver.h"
 #include "nic.h"
 #include "io.h"
-#include "farch_regs.h"
 #include "mcdi_pcol.h"
 
 /**************************************************************************
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index a7a22b0197947..b64a68a51050b 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -237,7 +237,7 @@ struct efx_tx_buffer {
  *	Normally this will equal @write_count, but as option descriptors
  *	don't produce completion events, they won't update this.
  *	Filled in iff @efx->type->option_descriptors; only used for PIO.
- *	Thus, this is written and used on EF10, and neither on farch.
+ *	Thus, this is only written and used on EF10.
  * @old_read_count: The value of read_count when last checked.
  *	This is here for performance reasons.  The xmit path will
  *	only get the up-to-date value of read_count if this
@@ -1288,8 +1288,7 @@ struct efx_udp_tunnel {
  * @set_wol: Push WoL configuration to the NIC
  * @resume_wol: Synchronise WoL state between driver and MC (e.g. after resume)
  * @get_fec_stats: Get standard FEC statistics.
- * @test_chip: Test registers.  May use efx_farch_test_registers(), and is
- *	expected to reset the NIC.
+ * @test_chip: Test registers. This is expected to reset the NIC.
  * @test_nvram: Test validity of NVRAM contents
  * @mcdi_request: Send an MCDI request with the given header and SDU.
  *	The SDU length may be any value from 0 up to the protocol-
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 63e2394382bb7..7e057741425f6 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -17,7 +17,6 @@
 #include "efx.h"
 #include "nic.h"
 #include "ef10_regs.h"
-#include "farch_regs.h"
 #include "io.h"
 #include "workarounds.h"
 #include "mcdi_pcol.h"
@@ -172,10 +171,6 @@ void efx_nic_fini_interrupt(struct efx_nic *efx)
 
 /* Register dump */
 
-#define REGISTER_REVISION_FA	1
-#define REGISTER_REVISION_FB	2
-#define REGISTER_REVISION_FC	3
-#define REGISTER_REVISION_FZ	3	/* last Falcon arch revision */
 #define REGISTER_REVISION_ED	4
 #define REGISTER_REVISION_EZ	4	/* latest EF10 revision */
 
@@ -189,117 +184,9 @@ struct efx_nic_reg {
 	REGISTER_REVISION_ ## arch ## min_rev,				\
 	REGISTER_REVISION_ ## arch ## max_rev				\
 }
-#define REGISTER_AA(name) REGISTER(name, F, A, A)
-#define REGISTER_AB(name) REGISTER(name, F, A, B)
-#define REGISTER_AZ(name) REGISTER(name, F, A, Z)
-#define REGISTER_BB(name) REGISTER(name, F, B, B)
-#define REGISTER_BZ(name) REGISTER(name, F, B, Z)
-#define REGISTER_CZ(name) REGISTER(name, F, C, Z)
 #define REGISTER_DZ(name) REGISTER(name, E, D, Z)
 
 static const struct efx_nic_reg efx_nic_regs[] = {
-	REGISTER_AZ(ADR_REGION),
-	REGISTER_AZ(INT_EN_KER),
-	REGISTER_BZ(INT_EN_CHAR),
-	REGISTER_AZ(INT_ADR_KER),
-	REGISTER_BZ(INT_ADR_CHAR),
-	/* INT_ACK_KER is WO */
-	/* INT_ISR0 is RC */
-	REGISTER_AZ(HW_INIT),
-	REGISTER_CZ(USR_EV_CFG),
-	REGISTER_AB(EE_SPI_HCMD),
-	REGISTER_AB(EE_SPI_HADR),
-	REGISTER_AB(EE_SPI_HDATA),
-	REGISTER_AB(EE_BASE_PAGE),
-	REGISTER_AB(EE_VPD_CFG0),
-	/* EE_VPD_SW_CNTL and EE_VPD_SW_DATA are not used */
-	/* PMBX_DBG_IADDR and PBMX_DBG_IDATA are indirect */
-	/* PCIE_CORE_INDIRECT is indirect */
-	REGISTER_AB(NIC_STAT),
-	REGISTER_AB(GPIO_CTL),
-	REGISTER_AB(GLB_CTL),
-	/* FATAL_INTR_KER and FATAL_INTR_CHAR are partly RC */
-	REGISTER_BZ(DP_CTRL),
-	REGISTER_AZ(MEM_STAT),
-	REGISTER_AZ(CS_DEBUG),
-	REGISTER_AZ(ALTERA_BUILD),
-	REGISTER_AZ(CSR_SPARE),
-	REGISTER_AB(PCIE_SD_CTL0123),
-	REGISTER_AB(PCIE_SD_CTL45),
-	REGISTER_AB(PCIE_PCS_CTL_STAT),
-	/* DEBUG_DATA_OUT is not used */
-	/* DRV_EV is WO */
-	REGISTER_AZ(EVQ_CTL),
-	REGISTER_AZ(EVQ_CNT1),
-	REGISTER_AZ(EVQ_CNT2),
-	REGISTER_AZ(BUF_TBL_CFG),
-	REGISTER_AZ(SRM_RX_DC_CFG),
-	REGISTER_AZ(SRM_TX_DC_CFG),
-	REGISTER_AZ(SRM_CFG),
-	/* BUF_TBL_UPD is WO */
-	REGISTER_AZ(SRM_UPD_EVQ),
-	REGISTER_AZ(SRAM_PARITY),
-	REGISTER_AZ(RX_CFG),
-	REGISTER_BZ(RX_FILTER_CTL),
-	/* RX_FLUSH_DESCQ is WO */
-	REGISTER_AZ(RX_DC_CFG),
-	REGISTER_AZ(RX_DC_PF_WM),
-	REGISTER_BZ(RX_RSS_TKEY),
-	/* RX_NODESC_DROP is RC */
-	REGISTER_AA(RX_SELF_RST),
-	/* RX_DEBUG, RX_PUSH_DROP are not used */
-	REGISTER_CZ(RX_RSS_IPV6_REG1),
-	REGISTER_CZ(RX_RSS_IPV6_REG2),
-	REGISTER_CZ(RX_RSS_IPV6_REG3),
-	/* TX_FLUSH_DESCQ is WO */
-	REGISTER_AZ(TX_DC_CFG),
-	REGISTER_AA(TX_CHKSM_CFG),
-	REGISTER_AZ(TX_CFG),
-	/* TX_PUSH_DROP is not used */
-	REGISTER_AZ(TX_RESERVED),
-	REGISTER_BZ(TX_PACE),
-	/* TX_PACE_DROP_QID is RC */
-	REGISTER_BB(TX_VLAN),
-	REGISTER_BZ(TX_IPFIL_PORTEN),
-	REGISTER_AB(MD_TXD),
-	REGISTER_AB(MD_RXD),
-	REGISTER_AB(MD_CS),
-	REGISTER_AB(MD_PHY_ADR),
-	REGISTER_AB(MD_ID),
-	/* MD_STAT is RC */
-	REGISTER_AB(MAC_STAT_DMA),
-	REGISTER_AB(MAC_CTRL),
-	REGISTER_BB(GEN_MODE),
-	REGISTER_AB(MAC_MC_HASH_REG0),
-	REGISTER_AB(MAC_MC_HASH_REG1),
-	REGISTER_AB(GM_CFG1),
-	REGISTER_AB(GM_CFG2),
-	/* GM_IPG and GM_HD are not used */
-	REGISTER_AB(GM_MAX_FLEN),
-	/* GM_TEST is not used */
-	REGISTER_AB(GM_ADR1),
-	REGISTER_AB(GM_ADR2),
-	REGISTER_AB(GMF_CFG0),
-	REGISTER_AB(GMF_CFG1),
-	REGISTER_AB(GMF_CFG2),
-	REGISTER_AB(GMF_CFG3),
-	REGISTER_AB(GMF_CFG4),
-	REGISTER_AB(GMF_CFG5),
-	REGISTER_BB(TX_SRC_MAC_CTL),
-	REGISTER_AB(XM_ADR_LO),
-	REGISTER_AB(XM_ADR_HI),
-	REGISTER_AB(XM_GLB_CFG),
-	REGISTER_AB(XM_TX_CFG),
-	REGISTER_AB(XM_RX_CFG),
-	REGISTER_AB(XM_MGT_INT_MASK),
-	REGISTER_AB(XM_FC),
-	REGISTER_AB(XM_PAUSE_TIME),
-	REGISTER_AB(XM_TX_PARAM),
-	REGISTER_AB(XM_RX_PARAM),
-	/* XM_MGT_INT_MSK (note no 'A') is RC */
-	REGISTER_AB(XX_PWR_RST),
-	REGISTER_AB(XX_SD_CTL),
-	REGISTER_AB(XX_TXDRV_CTL),
 	/* XX_PRBS_CTL, XX_PRBS_CHK and XX_PRBS_ERR are not used */
 	/* XX_CORE_STAT is partly RC */
 	REGISTER_DZ(BIU_HW_REV_ID),
@@ -325,49 +212,9 @@ struct efx_nic_reg_table {
 		arch, min_rev, max_rev,					\
 		arch ## R_ ## min_rev ## max_rev ## _ ## name ## _STEP,	\
 		arch ## R_ ## min_rev ## max_rev ## _ ## name ## _ROWS)
-#define REGISTER_TABLE_AA(name) REGISTER_TABLE(name, F, A, A)
-#define REGISTER_TABLE_AZ(name) REGISTER_TABLE(name, F, A, Z)
-#define REGISTER_TABLE_BB(name) REGISTER_TABLE(name, F, B, B)
-#define REGISTER_TABLE_BZ(name) REGISTER_TABLE(name, F, B, Z)
-#define REGISTER_TABLE_BB_CZ(name)					\
-	REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, F, B, B,	\
-				  FR_BZ_ ## name ## _STEP,		\
-				  FR_BB_ ## name ## _ROWS),		\
-	REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, F, C, Z,	\
-				  FR_BZ_ ## name ## _STEP,		\
-				  FR_CZ_ ## name ## _ROWS)
-#define REGISTER_TABLE_CZ(name) REGISTER_TABLE(name, F, C, Z)
 #define REGISTER_TABLE_DZ(name) REGISTER_TABLE(name, E, D, Z)
 
 static const struct efx_nic_reg_table efx_nic_reg_tables[] = {
-	/* DRIVER is not used */
-	/* EVQ_RPTR, TIMER_COMMAND, USR_EV and {RX,TX}_DESC_UPD are WO */
-	REGISTER_TABLE_BB(TX_IPFIL_TBL),
-	REGISTER_TABLE_BB(TX_SRC_MAC_TBL),
-	REGISTER_TABLE_AA(RX_DESC_PTR_TBL_KER),
-	REGISTER_TABLE_BB_CZ(RX_DESC_PTR_TBL),
-	REGISTER_TABLE_AA(TX_DESC_PTR_TBL_KER),
-	REGISTER_TABLE_BB_CZ(TX_DESC_PTR_TBL),
-	REGISTER_TABLE_AA(EVQ_PTR_TBL_KER),
-	REGISTER_TABLE_BB_CZ(EVQ_PTR_TBL),
-	/* We can't reasonably read all of the buffer table (up to 8MB!).
-	 * However this driver will only use a few entries.  Reading
-	 * 1K entries allows for some expansion of queue count and
-	 * size before we need to change the version. */
-	REGISTER_TABLE_DIMENSIONS(BUF_FULL_TBL_KER, FR_AA_BUF_FULL_TBL_KER,
-				  F, A, A, 8, 1024),
-	REGISTER_TABLE_DIMENSIONS(BUF_FULL_TBL, FR_BZ_BUF_FULL_TBL,
-				  F, B, Z, 8, 1024),
-	REGISTER_TABLE_CZ(RX_MAC_FILTER_TBL0),
-	REGISTER_TABLE_BB_CZ(TIMER_TBL),
-	REGISTER_TABLE_BB_CZ(TX_PACE_TBL),
-	REGISTER_TABLE_BZ(RX_INDIRECTION_TBL),
-	/* TX_FILTER_TBL0 is huge and not used by this driver */
-	REGISTER_TABLE_CZ(TX_MAC_FILTER_TBL0),
-	REGISTER_TABLE_CZ(MC_TREG_SMEM),
-	/* MSIX_PBA_TABLE is not mapped */
-	/* SRM_DBG is not mapped (and is redundant with BUF_FLL_TBL) */
-	REGISTER_TABLE_BZ(RX_FILTER_TBL0),
 	REGISTER_TABLE_DZ(BIU_MC_SFT_STATUS),
 };
 
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 251868235ae49..bd17962436ba3 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -11,8 +11,6 @@
 #include "nic_common.h"
 #include "efx.h"
 
-u32 efx_farch_fpga_ver(struct efx_nic *efx);
-
 enum {
 	PHY_TYPE_NONE = 0,
 	PHY_TYPE_TXC43128 = 1,
@@ -304,89 +302,8 @@ int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
 extern const struct efx_nic_type efx_hunt_a0_nic_type;
 extern const struct efx_nic_type efx_hunt_a0_vf_nic_type;
 
-int falcon_probe_board(struct efx_nic *efx, u16 revision_info);
-
-/* Falcon/Siena queue operations */
-int efx_farch_tx_probe(struct efx_tx_queue *tx_queue);
-void efx_farch_tx_init(struct efx_tx_queue *tx_queue);
-void efx_farch_tx_fini(struct efx_tx_queue *tx_queue);
-void efx_farch_tx_remove(struct efx_tx_queue *tx_queue);
-void efx_farch_tx_write(struct efx_tx_queue *tx_queue);
-unsigned int efx_farch_tx_limit_len(struct efx_tx_queue *tx_queue,
-				    dma_addr_t dma_addr, unsigned int len);
-int efx_farch_rx_probe(struct efx_rx_queue *rx_queue);
-void efx_farch_rx_init(struct efx_rx_queue *rx_queue);
-void efx_farch_rx_fini(struct efx_rx_queue *rx_queue);
-void efx_farch_rx_remove(struct efx_rx_queue *rx_queue);
-void efx_farch_rx_write(struct efx_rx_queue *rx_queue);
-void efx_farch_rx_defer_refill(struct efx_rx_queue *rx_queue);
-int efx_farch_ev_probe(struct efx_channel *channel);
-int efx_farch_ev_init(struct efx_channel *channel);
-void efx_farch_ev_fini(struct efx_channel *channel);
-void efx_farch_ev_remove(struct efx_channel *channel);
-int efx_farch_ev_process(struct efx_channel *channel, int quota);
-void efx_farch_ev_read_ack(struct efx_channel *channel);
-void efx_farch_ev_test_generate(struct efx_channel *channel);
-
-/* Falcon/Siena filter operations */
-int efx_farch_filter_table_probe(struct efx_nic *efx);
-void efx_farch_filter_table_restore(struct efx_nic *efx);
-void efx_farch_filter_table_remove(struct efx_nic *efx);
-void efx_farch_filter_update_rx_scatter(struct efx_nic *efx);
-s32 efx_farch_filter_insert(struct efx_nic *efx, struct efx_filter_spec *spec,
-			    bool replace);
-int efx_farch_filter_remove_safe(struct efx_nic *efx,
-				 enum efx_filter_priority priority,
-				 u32 filter_id);
-int efx_farch_filter_get_safe(struct efx_nic *efx,
-			      enum efx_filter_priority priority, u32 filter_id,
-			      struct efx_filter_spec *);
-int efx_farch_filter_clear_rx(struct efx_nic *efx,
-			      enum efx_filter_priority priority);
-u32 efx_farch_filter_count_rx_used(struct efx_nic *efx,
-				   enum efx_filter_priority priority);
-u32 efx_farch_filter_get_rx_id_limit(struct efx_nic *efx);
-s32 efx_farch_filter_get_rx_ids(struct efx_nic *efx,
-				enum efx_filter_priority priority, u32 *buf,
-				u32 size);
-#ifdef CONFIG_RFS_ACCEL
-bool efx_farch_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
-				     unsigned int index);
-#endif
-void efx_farch_filter_sync_rx_mode(struct efx_nic *efx);
-
-/* Falcon/Siena interrupts */
-void efx_farch_irq_enable_master(struct efx_nic *efx);
-int efx_farch_irq_test_generate(struct efx_nic *efx);
-void efx_farch_irq_disable_master(struct efx_nic *efx);
-irqreturn_t efx_farch_msi_interrupt(int irq, void *dev_id);
-irqreturn_t efx_farch_legacy_interrupt(int irq, void *dev_id);
-irqreturn_t efx_farch_fatal_interrupt(struct efx_nic *efx);
-
 /* Global Resources */
 void siena_prepare_flush(struct efx_nic *efx);
-int efx_farch_fini_dmaq(struct efx_nic *efx);
-void efx_farch_finish_flr(struct efx_nic *efx);
 void siena_finish_flush(struct efx_nic *efx);
-void falcon_start_nic_stats(struct efx_nic *efx);
-void falcon_stop_nic_stats(struct efx_nic *efx);
-int falcon_reset_xaui(struct efx_nic *efx);
-void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw);
-void efx_farch_init_common(struct efx_nic *efx);
-void efx_farch_rx_push_indir_table(struct efx_nic *efx);
-void efx_farch_rx_pull_indir_table(struct efx_nic *efx);
-
-/* Tests */
-struct efx_farch_register_test {
-	unsigned address;
-	efx_oword_t mask;
-};
-
-int efx_farch_test_registers(struct efx_nic *efx,
-			     const struct efx_farch_register_test *regs,
-			     size_t n_regs);
-
-void efx_farch_generate_event(struct efx_nic *efx, unsigned int evq,
-			      efx_qword_t *event);
 
 #endif /* EFX_NIC_H */
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 0c40571133cb9..9c17cd24c5492 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -43,7 +43,6 @@
 #include "mcdi.h"
 #include "mcdi_pcol.h"
 #include "io.h"
-#include "farch_regs.h"
 #include "tx.h"
 #include "nic.h" /* indirectly includes ptp.h */
 #include "efx_channels.h"
-- 
GitLab


From e714e5b24413e725cbb5148e605c4fa352693523 Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:40:48 +0100
Subject: [PATCH 0597/1806] sfc: Remove siena_nic_data and stats

These are no longer used, and the two  Siena specific functions are
no longer present in sfc.ko.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/nic.h | 95 ----------------------------------
 1 file changed, 95 deletions(-)

diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index bd17962436ba3..1db64fc6e9097 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -23,97 +23,6 @@ enum {
 	PHY_TYPE_SFT9001B = 10,
 };
 
-enum {
-	SIENA_STAT_tx_bytes = GENERIC_STAT_COUNT,
-	SIENA_STAT_tx_good_bytes,
-	SIENA_STAT_tx_bad_bytes,
-	SIENA_STAT_tx_packets,
-	SIENA_STAT_tx_bad,
-	SIENA_STAT_tx_pause,
-	SIENA_STAT_tx_control,
-	SIENA_STAT_tx_unicast,
-	SIENA_STAT_tx_multicast,
-	SIENA_STAT_tx_broadcast,
-	SIENA_STAT_tx_lt64,
-	SIENA_STAT_tx_64,
-	SIENA_STAT_tx_65_to_127,
-	SIENA_STAT_tx_128_to_255,
-	SIENA_STAT_tx_256_to_511,
-	SIENA_STAT_tx_512_to_1023,
-	SIENA_STAT_tx_1024_to_15xx,
-	SIENA_STAT_tx_15xx_to_jumbo,
-	SIENA_STAT_tx_gtjumbo,
-	SIENA_STAT_tx_collision,
-	SIENA_STAT_tx_single_collision,
-	SIENA_STAT_tx_multiple_collision,
-	SIENA_STAT_tx_excessive_collision,
-	SIENA_STAT_tx_deferred,
-	SIENA_STAT_tx_late_collision,
-	SIENA_STAT_tx_excessive_deferred,
-	SIENA_STAT_tx_non_tcpudp,
-	SIENA_STAT_tx_mac_src_error,
-	SIENA_STAT_tx_ip_src_error,
-	SIENA_STAT_rx_bytes,
-	SIENA_STAT_rx_good_bytes,
-	SIENA_STAT_rx_bad_bytes,
-	SIENA_STAT_rx_packets,
-	SIENA_STAT_rx_good,
-	SIENA_STAT_rx_bad,
-	SIENA_STAT_rx_pause,
-	SIENA_STAT_rx_control,
-	SIENA_STAT_rx_unicast,
-	SIENA_STAT_rx_multicast,
-	SIENA_STAT_rx_broadcast,
-	SIENA_STAT_rx_lt64,
-	SIENA_STAT_rx_64,
-	SIENA_STAT_rx_65_to_127,
-	SIENA_STAT_rx_128_to_255,
-	SIENA_STAT_rx_256_to_511,
-	SIENA_STAT_rx_512_to_1023,
-	SIENA_STAT_rx_1024_to_15xx,
-	SIENA_STAT_rx_15xx_to_jumbo,
-	SIENA_STAT_rx_gtjumbo,
-	SIENA_STAT_rx_bad_gtjumbo,
-	SIENA_STAT_rx_overflow,
-	SIENA_STAT_rx_false_carrier,
-	SIENA_STAT_rx_symbol_error,
-	SIENA_STAT_rx_align_error,
-	SIENA_STAT_rx_length_error,
-	SIENA_STAT_rx_internal_error,
-	SIENA_STAT_rx_nodesc_drop_cnt,
-	SIENA_STAT_COUNT
-};
-
-/**
- * struct siena_nic_data - Siena NIC state
- * @efx: Pointer back to main interface structure
- * @wol_filter_id: Wake-on-LAN packet filter id
- * @stats: Hardware statistics
- * @vf: Array of &struct siena_vf objects
- * @vf_buftbl_base: The zeroth buffer table index used to back VF queues.
- * @vfdi_status: Common VFDI status page to be dmad to VF address space.
- * @local_addr_list: List of local addresses. Protected by %local_lock.
- * @local_page_list: List of DMA addressable pages used to broadcast
- *	%local_addr_list. Protected by %local_lock.
- * @local_lock: Mutex protecting %local_addr_list and %local_page_list.
- * @peer_work: Work item to broadcast peer addresses to VMs.
- */
-struct siena_nic_data {
-	struct efx_nic *efx;
-	int wol_filter_id;
-	u64 stats[SIENA_STAT_COUNT];
-#ifdef CONFIG_SFC_SRIOV
-	struct siena_vf *vf;
-	struct efx_channel *vfdi_channel;
-	unsigned vf_buftbl_base;
-	struct efx_buffer vfdi_status;
-	struct list_head local_addr_list;
-	struct list_head local_page_list;
-	struct mutex local_lock;
-	struct work_struct peer_work;
-#endif
-};
-
 enum {
 	EF10_STAT_port_tx_bytes = GENERIC_STAT_COUNT,
 	EF10_STAT_port_tx_packets,
@@ -302,8 +211,4 @@ int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
 extern const struct efx_nic_type efx_hunt_a0_nic_type;
 extern const struct efx_nic_type efx_hunt_a0_vf_nic_type;
 
-/* Global Resources */
-void siena_prepare_flush(struct efx_nic *efx);
-void siena_finish_flush(struct efx_nic *efx);
-
 #endif /* EFX_NIC_H */
-- 
GitLab


From f294c1f7bfbdc7fb86ca177e9fe592d830820299 Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:40:54 +0100
Subject: [PATCH 0598/1806] sfc: Remove support for siena high priority queue

This also removes TC support code, since that was never supported for EF10.
TC support for EF100 is not handled from efx.c.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/efx.c        |  1 -
 drivers/net/ethernet/sfc/efx.h        |  2 --
 drivers/net/ethernet/sfc/net_driver.h |  4 +--
 drivers/net/ethernet/sfc/tx.c         | 45 +--------------------------
 4 files changed, 2 insertions(+), 50 deletions(-)

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index d670a319b3799..19f4b4d0b851b 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -605,7 +605,6 @@ static const struct net_device_ops efx_netdev_ops = {
 #endif
 	.ndo_get_phys_port_id   = efx_get_phys_port_id,
 	.ndo_get_phys_port_name	= efx_get_phys_port_name,
-	.ndo_setup_tc		= efx_setup_tc,
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	= efx_filter_rfs,
 #endif
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 4239c7ece1235..48d3623735ba6 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -30,8 +30,6 @@ static inline netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct
 			       tx_queue, skb);
 }
 void efx_xmit_done_single(struct efx_tx_queue *tx_queue);
-int efx_setup_tc(struct net_device *net_dev, enum tc_setup_type type,
-		 void *type_data);
 extern unsigned int efx_piobuf_size;
 
 /* RX */
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index b64a68a51050b..25013caaeefb1 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -67,9 +67,7 @@
 #define EFX_MAX_CORE_TX_QUEUES	(EFX_MAX_TX_TC * EFX_MAX_CHANNELS)
 #define EFX_TXQ_TYPE_OUTER_CSUM	1	/* Outer checksum offload */
 #define EFX_TXQ_TYPE_INNER_CSUM	2	/* Inner checksum offload */
-#define EFX_TXQ_TYPE_HIGHPRI	4	/* High-priority (for TC) */
-#define EFX_TXQ_TYPES		8
-/* HIGHPRI is Siena-only, and INNER_CSUM is EF10, so no need for both */
+#define EFX_TXQ_TYPES		4
 #define EFX_MAX_TXQ_PER_CHANNEL	4
 #define EFX_MAX_TX_QUEUES	(EFX_MAX_TXQ_PER_CHANNEL * EFX_MAX_CHANNELS)
 
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 4ed4082836a94..fe2d476028e72 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -517,13 +517,8 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb,
 	unsigned index, type;
 
 	EFX_WARN_ON_PARANOID(!netif_device_present(net_dev));
-
 	index = skb_get_queue_mapping(skb);
 	type = efx_tx_csum_type_skb(skb);
-	if (index >= efx->n_tx_channels) {
-		index -= efx->n_tx_channels;
-		type |= EFX_TXQ_TYPE_HIGHPRI;
-	}
 
 	/* PTP "event" packet */
 	if (unlikely(efx_xmit_with_hwtstamp(skb)) &&
@@ -603,43 +598,5 @@ void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue)
 	/* Must be inverse of queue lookup in efx_hard_start_xmit() */
 	tx_queue->core_txq =
 		netdev_get_tx_queue(efx->net_dev,
-				    tx_queue->channel->channel +
-				    ((tx_queue->type & EFX_TXQ_TYPE_HIGHPRI) ?
-				     efx->n_tx_channels : 0));
-}
-
-int efx_setup_tc(struct net_device *net_dev, enum tc_setup_type type,
-		 void *type_data)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-	struct tc_mqprio_qopt *mqprio = type_data;
-	unsigned tc, num_tc;
-
-	if (type != TC_SETUP_QDISC_MQPRIO)
-		return -EOPNOTSUPP;
-
-	/* Only Siena supported highpri queues */
-	if (efx_nic_rev(efx) > EFX_REV_SIENA_A0)
-		return -EOPNOTSUPP;
-
-	num_tc = mqprio->num_tc;
-
-	if (num_tc > EFX_MAX_TX_TC)
-		return -EINVAL;
-
-	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
-
-	if (num_tc == net_dev->num_tc)
-		return 0;
-
-	for (tc = 0; tc < num_tc; tc++) {
-		net_dev->tc_to_txq[tc].offset = tc * efx->n_tx_channels;
-		net_dev->tc_to_txq[tc].count = efx->n_tx_channels;
-	}
-
-	net_dev->num_tc = num_tc;
-
-	return netif_set_real_num_tx_queues(net_dev,
-					    max_t(int, num_tc, 1) *
-					    efx->n_tx_channels);
+				    tx_queue->channel->channel);
 }
-- 
GitLab


From 958d58bb994092d22c0aaaf81279e6d47e3cda97 Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:40:59 +0100
Subject: [PATCH 0599/1806] sfc: Remove EFX_REV_SIENA_A0

The workarounds for bug 8568 and 17213 are no longer needed.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/nic_common.h  | 3 +--
 drivers/net/ethernet/sfc/workarounds.h | 7 -------
 2 files changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/sfc/nic_common.h b/drivers/net/ethernet/sfc/nic_common.h
index 0cef35c0c559a..e35ecbe8842ec 100644
--- a/drivers/net/ethernet/sfc/nic_common.h
+++ b/drivers/net/ethernet/sfc/nic_common.h
@@ -15,11 +15,10 @@
 #include "ptp.h"
 
 enum {
-	/* Revisions 0-2 were Falcon A0, A1 and B0 respectively.
+	/* Revisions 0-3 were Falcon A0, A1, B0 and Siena respectively.
 	 * They are not supported by this driver but these revision numbers
 	 * form part of the ethtool API for register dumping.
 	 */
-	EFX_REV_SIENA_A0 = 3,
 	EFX_REV_HUNT_A0 = 4,
 	EFX_REV_EF100 = 5,
 };
diff --git a/drivers/net/ethernet/sfc/workarounds.h b/drivers/net/ethernet/sfc/workarounds.h
index 815be2d20c4b5..e10e7f84958df 100644
--- a/drivers/net/ethernet/sfc/workarounds.h
+++ b/drivers/net/ethernet/sfc/workarounds.h
@@ -12,14 +12,7 @@
  * Bug numbers are from Solarflare's Bugzilla.
  */
 
-#define EFX_WORKAROUND_SIENA(efx) (efx_nic_rev(efx) == EFX_REV_SIENA_A0)
 #define EFX_WORKAROUND_EF10(efx) (efx_nic_rev(efx) >= EFX_REV_HUNT_A0)
-#define EFX_WORKAROUND_10G(efx) 1
-
-/* Bit-bashed I2C reads cause performance drop */
-#define EFX_WORKAROUND_7884 EFX_WORKAROUND_10G
-/* Legacy interrupt storm when interrupt fifo fills */
-#define EFX_WORKAROUND_17213 EFX_WORKAROUND_SIENA
 
 /* Lockup when writing event block registers at gen2/gen3 */
 #define EFX_EF10_WORKAROUND_35388(efx)					\
-- 
GitLab


From 1c145a5dc3701018ea5b3ea4ef0d5ae3ec7cbb41 Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:41:05 +0100
Subject: [PATCH 0600/1806] sfc: Remove PTP code for Siena

rx_tx_inline is now always true.
The special event list is no longer needed, event handling is always
inline.
Event MCDI_EVENT_CODE_PTP_RX is no longer needed.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/mcdi.c |   1 -
 drivers/net/ethernet/sfc/ptp.c  | 226 +-------------------------------
 2 files changed, 1 insertion(+), 226 deletions(-)

diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index 86cfd4713b11e..f7ffaa14fda47 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -1357,7 +1357,6 @@ void efx_mcdi_process_event(struct efx_channel *channel,
 			efx->type->sriov_flr(efx,
 					     MCDI_EVENT_FIELD(*event, FLR_VF));
 		break;
-	case MCDI_EVENT_CODE_PTP_RX:
 	case MCDI_EVENT_CODE_PTP_FAULT:
 	case MCDI_EVENT_CODE_PTP_PPS:
 		efx_ptp_event(efx, event);
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 9c17cd24c5492..3eab1802f6b07 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -86,9 +86,6 @@
 #define PTP_V1_VERSION_LENGTH	2
 #define PTP_V1_VERSION_OFFSET	28
 
-#define PTP_V1_UUID_LENGTH	6
-#define PTP_V1_UUID_OFFSET	50
-
 #define PTP_V1_SEQUENCE_LENGTH	2
 #define PTP_V1_SEQUENCE_OFFSET	58
 
@@ -100,17 +97,6 @@
 #define PTP_V2_VERSION_LENGTH	1
 #define PTP_V2_VERSION_OFFSET	29
 
-#define PTP_V2_UUID_LENGTH	8
-#define PTP_V2_UUID_OFFSET	48
-
-/* Although PTP V2 UUIDs are comprised a ClockIdentity (8) and PortNumber (2),
- * the MC only captures the last six bytes of the clock identity. These values
- * reflect those, not the ones used in the standard.  The standard permits
- * mapping of V1 UUIDs to V2 UUIDs with these same values.
- */
-#define PTP_V2_MC_UUID_LENGTH	6
-#define PTP_V2_MC_UUID_OFFSET	50
-
 #define PTP_V2_SEQUENCE_LENGTH	2
 #define PTP_V2_SEQUENCE_OFFSET	58
 
@@ -166,14 +152,12 @@ enum ptp_packet_state {
 
 /**
  * struct efx_ptp_match - Matching structure, stored in sk_buff's cb area.
- * @words: UUID and (partial) sequence number
  * @expiry: Time after which the packet should be delivered irrespective of
  *            event arrival.
  * @state: The state of the packet - whether it is ready for processing or
  *         whether that is of no interest.
  */
 struct efx_ptp_match {
-	u32 words[DIV_ROUND_UP(PTP_V1_UUID_LENGTH, 4)];
 	unsigned long expiry;
 	enum ptp_packet_state state;
 };
@@ -235,15 +219,9 @@ struct efx_ptp_rxfilter {
 /**
  * struct efx_ptp_data - Precision Time Protocol (PTP) state
  * @efx: The NIC context
- * @channel: The PTP channel (Siena only)
- * @rx_ts_inline: Flag for whether RX timestamps are inline (else they are
- *	separate events)
+ * @channel: The PTP channel (for Medford and Medford2)
  * @rxq: Receive SKB queue (awaiting timestamps)
  * @txq: Transmit SKB queue
- * @evt_list: List of MC receive events awaiting packets
- * @evt_free_list: List of free events
- * @evt_lock: Lock for manipulating evt_list and evt_free_list
- * @rx_evts: Instantiated events (on evt_list and evt_free_list)
  * @workwq: Work queue for processing pending PTP operations
  * @work: Work task
  * @cleanup_work: Work task for periodic cleanup
@@ -309,13 +287,8 @@ struct efx_ptp_rxfilter {
 struct efx_ptp_data {
 	struct efx_nic *efx;
 	struct efx_channel *channel;
-	bool rx_ts_inline;
 	struct sk_buff_head rxq;
 	struct sk_buff_head txq;
-	struct list_head evt_list;
-	struct list_head evt_free_list;
-	spinlock_t evt_lock;
-	struct efx_ptp_event_rx rx_evts[MAX_RECEIVE_EVENTS];
 	struct workqueue_struct *workwq;
 	struct work_struct work;
 	struct delayed_work cleanup_work;
@@ -464,25 +437,6 @@ size_t efx_ptp_update_stats(struct efx_nic *efx, u64 *stats)
 	return PTP_STAT_COUNT;
 }
 
-/* For Siena platforms NIC time is s and ns */
-static void efx_ptp_ns_to_s_ns(s64 ns, u32 *nic_major, u32 *nic_minor)
-{
-	struct timespec64 ts = ns_to_timespec64(ns);
-	*nic_major = (u32)ts.tv_sec;
-	*nic_minor = ts.tv_nsec;
-}
-
-static ktime_t efx_ptp_s_ns_to_ktime_correction(u32 nic_major, u32 nic_minor,
-						s32 correction)
-{
-	ktime_t kt = ktime_set(nic_major, nic_minor);
-	if (correction >= 0)
-		kt = ktime_add_ns(kt, (u64)correction);
-	else
-		kt = ktime_sub_ns(kt, (u64)-correction);
-	return kt;
-}
-
 /* To convert from s27 format to ns we multiply then divide by a power of 2.
  * For the conversion from ns to s27, the operation is also converted to a
  * multiply and shift.
@@ -696,12 +650,6 @@ static int efx_ptp_get_attributes(struct efx_nic *efx)
 		ptp->nic_time.minor_max = 1 << 27;
 		ptp->nic_time.sync_event_minor_shift = 19;
 		break;
-	case MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS:
-		ptp->ns_to_nic_time = efx_ptp_ns_to_s_ns;
-		ptp->nic_to_kernel_time = efx_ptp_s_ns_to_ktime_correction;
-		ptp->nic_time.minor_max = 1000000000;
-		ptp->nic_time.sync_event_minor_shift = 22;
-		break;
 	case MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_QTR_NANOSECONDS:
 		ptp->ns_to_nic_time = efx_ptp_ns_to_s_qns;
 		ptp->nic_to_kernel_time = efx_ptp_s_qns_to_ktime_correction;
@@ -1216,76 +1164,6 @@ fail:
 	return;
 }
 
-static void efx_ptp_drop_time_expired_events(struct efx_nic *efx)
-{
-	struct efx_ptp_data *ptp = efx->ptp_data;
-	struct list_head *cursor;
-	struct list_head *next;
-
-	if (ptp->rx_ts_inline)
-		return;
-
-	/* Drop time-expired events */
-	spin_lock_bh(&ptp->evt_lock);
-	list_for_each_safe(cursor, next, &ptp->evt_list) {
-		struct efx_ptp_event_rx *evt;
-
-		evt = list_entry(cursor, struct efx_ptp_event_rx,
-				 link);
-		if (time_after(jiffies, evt->expiry)) {
-			list_move(&evt->link, &ptp->evt_free_list);
-			netif_warn(efx, hw, efx->net_dev,
-				   "PTP rx event dropped\n");
-		}
-	}
-	spin_unlock_bh(&ptp->evt_lock);
-}
-
-static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx,
-					      struct sk_buff *skb)
-{
-	struct efx_ptp_data *ptp = efx->ptp_data;
-	bool evts_waiting;
-	struct list_head *cursor;
-	struct list_head *next;
-	struct efx_ptp_match *match;
-	enum ptp_packet_state rc = PTP_PACKET_STATE_UNMATCHED;
-
-	WARN_ON_ONCE(ptp->rx_ts_inline);
-
-	spin_lock_bh(&ptp->evt_lock);
-	evts_waiting = !list_empty(&ptp->evt_list);
-	spin_unlock_bh(&ptp->evt_lock);
-
-	if (!evts_waiting)
-		return PTP_PACKET_STATE_UNMATCHED;
-
-	match = (struct efx_ptp_match *)skb->cb;
-	/* Look for a matching timestamp in the event queue */
-	spin_lock_bh(&ptp->evt_lock);
-	list_for_each_safe(cursor, next, &ptp->evt_list) {
-		struct efx_ptp_event_rx *evt;
-
-		evt = list_entry(cursor, struct efx_ptp_event_rx, link);
-		if ((evt->seq0 == match->words[0]) &&
-		    (evt->seq1 == match->words[1])) {
-			struct skb_shared_hwtstamps *timestamps;
-
-			/* Match - add in hardware timestamp */
-			timestamps = skb_hwtstamps(skb);
-			timestamps->hwtstamp = evt->hwtimestamp;
-
-			match->state = PTP_PACKET_STATE_MATCHED;
-			rc = PTP_PACKET_STATE_MATCHED;
-			list_move(&evt->link, &ptp->evt_free_list);
-			break;
-		}
-	}
-	spin_unlock_bh(&ptp->evt_lock);
-
-	return rc;
-}
-
 /* Process any queued receive events and corresponding packets
  *
  * q is returned with all the packets that are ready for delivery.
@@ -1301,9 +1179,6 @@ static void efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q)
 		match = (struct efx_ptp_match *)skb->cb;
 		if (match->state == PTP_PACKET_STATE_MATCH_UNWANTED) {
 			__skb_queue_tail(q, skb);
-		} else if (efx_ptp_match_rx(efx, skb) ==
-			   PTP_PACKET_STATE_MATCHED) {
-			__skb_queue_tail(q, skb);
 		} else if (time_after(jiffies, match->expiry)) {
 			match->state = PTP_PACKET_STATE_TIMED_OUT;
 			++ptp->rx_no_timestamp;
@@ -1580,8 +1455,6 @@ fail:
 static int efx_ptp_stop(struct efx_nic *efx)
 {
 	struct efx_ptp_data *ptp = efx->ptp_data;
-	struct list_head *cursor;
-	struct list_head *next;
 	int rc;
 
 	if (ptp == NULL)
@@ -1596,13 +1469,6 @@ static int efx_ptp_stop(struct efx_nic *efx)
 	efx_ptp_deliver_rx_queue(&efx->ptp_data->rxq);
 	skb_queue_purge(&efx->ptp_data->txq);
 
-	/* Drop any pending receive events */
-	spin_lock_bh(&efx->ptp_data->evt_lock);
-	list_for_each_safe(cursor, next, &efx->ptp_data->evt_list) {
-		list_move(cursor, &efx->ptp_data->evt_free_list);
-	}
-	spin_unlock_bh(&efx->ptp_data->evt_lock);
-
 	return rc;
 }
 
@@ -1642,8 +1508,6 @@ static void efx_ptp_worker(struct work_struct *work)
 		return;
 	}
 
-	efx_ptp_drop_time_expired_events(efx);
-
 	__skb_queue_head_init(&tempq);
 	efx_ptp_process_events(efx, &tempq);
 
@@ -1692,7 +1556,6 @@ int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel)
 {
 	struct efx_ptp_data *ptp;
 	int rc = 0;
-	unsigned int pos;
 
 	if (efx->ptp_data) {
 		efx->ptp_data->channel = channel;
@@ -1706,7 +1569,6 @@ int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel)
 
 	ptp->efx = efx;
 	ptp->channel = channel;
-	ptp->rx_ts_inline = efx_nic_rev(efx) >= EFX_REV_HUNT_A0;
 
 	rc = efx_nic_alloc_buffer(efx, &ptp->start, sizeof(int), GFP_KERNEL);
 	if (rc != 0)
@@ -1733,12 +1595,6 @@ int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel)
 	ptp->config.flags = 0;
 	ptp->config.tx_type = HWTSTAMP_TX_OFF;
 	ptp->config.rx_filter = HWTSTAMP_FILTER_NONE;
-	INIT_LIST_HEAD(&ptp->evt_list);
-	INIT_LIST_HEAD(&ptp->evt_free_list);
-	spin_lock_init(&ptp->evt_lock);
-	for (pos = 0; pos < MAX_RECEIVE_EVENTS; pos++)
-		list_add(&ptp->rx_evts[pos].link, &ptp->evt_free_list);
-
 	INIT_LIST_HEAD(&ptp->rxfilters_mcast);
 	INIT_LIST_HEAD(&ptp->rxfilters_ucast);
 
@@ -1878,7 +1734,6 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb)
 	struct efx_nic *efx = channel->efx;
 	struct efx_ptp_data *ptp = efx->ptp_data;
 	struct efx_ptp_match *match = (struct efx_ptp_match *)skb->cb;
-	u8 *match_data_012, *match_data_345;
 	unsigned int version;
 	u8 *data;
 
@@ -1894,12 +1749,6 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb)
 		if (version != PTP_VERSION_V1) {
 			return false;
 		}
-
-		/* PTP V1 uses all six bytes of the UUID to match the packet
-		 * to the timestamp
-		 */
-		match_data_012 = data + PTP_V1_UUID_OFFSET;
-		match_data_345 = data + PTP_V1_UUID_OFFSET + 3;
 	} else {
 		if (!pskb_may_pull(skb, PTP_V2_MIN_LENGTH)) {
 			return false;
@@ -1909,21 +1758,6 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb)
 		if ((version & PTP_VERSION_V2_MASK) != PTP_VERSION_V2) {
 			return false;
 		}
-
-		/* The original V2 implementation uses bytes 2-7 of
-		 * the UUID to match the packet to the timestamp. This
-		 * discards two of the bytes of the MAC address used
-		 * to create the UUID (SF bug 33070).  The PTP V2
-		 * enhanced mode fixes this issue and uses bytes 0-2
-		 * and byte 5-7 of the UUID.
-		 */
-		match_data_345 = data + PTP_V2_UUID_OFFSET + 5;
-		if (ptp->mode == MC_CMD_PTP_MODE_V2) {
-			match_data_012 = data + PTP_V2_UUID_OFFSET + 2;
-		} else {
-			match_data_012 = data + PTP_V2_UUID_OFFSET + 0;
-			BUG_ON(ptp->mode != MC_CMD_PTP_MODE_V2_ENHANCED);
-		}
 	}
 
 	/* Does this packet require timestamping? */
@@ -1935,17 +1769,6 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb)
 		 */
 		BUILD_BUG_ON(PTP_V1_SEQUENCE_OFFSET != PTP_V2_SEQUENCE_OFFSET);
 		BUILD_BUG_ON(PTP_V1_SEQUENCE_LENGTH != PTP_V2_SEQUENCE_LENGTH);
-
-		/* Extract UUID/Sequence information */
-		match->words[0] = (match_data_012[0]         |
-				   (match_data_012[1] << 8)  |
-				   (match_data_012[2] << 16) |
-				   (match_data_345[0] << 24));
-		match->words[1] = (match_data_345[1]         |
-				   (match_data_345[2] << 8)  |
-				   (data[PTP_V1_SEQUENCE_OFFSET +
-					 PTP_V1_SEQUENCE_LENGTH - 1] <<
-				    16));
 	} else {
 		match->state = PTP_PACKET_STATE_MATCH_UNWANTED;
 	}
@@ -2109,50 +1932,6 @@ static void ptp_event_failure(struct efx_nic *efx, int expected_frag_len)
 	queue_work(ptp->workwq, &ptp->work);
 }
 
-/* Process a completed receive event.  Put it on the event queue and
- * start worker thread.  This is required because event and their
- * correspoding packets may come in either order.
- */
-static void ptp_event_rx(struct efx_nic *efx, struct efx_ptp_data *ptp)
-{
-	struct efx_ptp_event_rx *evt = NULL;
-
-	if (WARN_ON_ONCE(ptp->rx_ts_inline))
-		return;
-
-	if (ptp->evt_frag_idx != 3) {
-		ptp_event_failure(efx, 3);
-		return;
-	}
-
-	spin_lock_bh(&ptp->evt_lock);
-	if (!list_empty(&ptp->evt_free_list)) {
-		evt = list_first_entry(&ptp->evt_free_list,
-				       struct efx_ptp_event_rx, link);
-		list_del(&evt->link);
-
-		evt->seq0 = EFX_QWORD_FIELD(ptp->evt_frags[2], MCDI_EVENT_DATA);
-		evt->seq1 = (EFX_QWORD_FIELD(ptp->evt_frags[2],
-					     MCDI_EVENT_SRC)        |
-			     (EFX_QWORD_FIELD(ptp->evt_frags[1],
-					      MCDI_EVENT_SRC) << 8) |
-			     (EFX_QWORD_FIELD(ptp->evt_frags[0],
-					      MCDI_EVENT_SRC) << 16));
-		evt->hwtimestamp = efx->ptp_data->nic_to_kernel_time(
-			EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA),
-			EFX_QWORD_FIELD(ptp->evt_frags[1], MCDI_EVENT_DATA),
-			ptp->ts_corrections.ptp_rx);
-		evt->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS);
-		list_add_tail(&evt->link, &ptp->evt_list);
-
-		queue_work(ptp->workwq, &ptp->work);
-	} else if (net_ratelimit()) {
-		/* Log a rate-limited warning message. */
-		netif_err(efx, rx_err, efx->net_dev, "PTP event queue overflow\n");
-	}
-	spin_unlock_bh(&ptp->evt_lock);
-}
-
 static void ptp_event_fault(struct efx_nic *efx, struct efx_ptp_data *ptp)
 {
 	int code = EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA);
@@ -2199,9 +1978,6 @@ void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev)
 	if (!MCDI_EVENT_FIELD(*ev, CONT)) {
 		/* Process resulting event */
 		switch (code) {
-		case MCDI_EVENT_CODE_PTP_RX:
-			ptp_event_rx(efx, ptp);
-			break;
 		case MCDI_EVENT_CODE_PTP_FAULT:
 			ptp_event_fault(efx, ptp);
 			break;
-- 
GitLab


From a623b3a58a85114d40d4857d1a0d269006a3ae7d Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:41:10 +0100
Subject: [PATCH 0601/1806] sfc: Remove some NIC type indirections that are no
 longer needed

The special handling for SRIOV reset and FLR is not needed on EF10.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c       | 2 --
 drivers/net/ethernet/sfc/ef10_sriov.h | 2 --
 drivers/net/ethernet/sfc/efx_common.c | 2 --
 drivers/net/ethernet/sfc/mcdi.c       | 5 -----
 drivers/net/ethernet/sfc/net_driver.h | 8 --------
 5 files changed, 19 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 8c019f382a7f3..fca0cf3385106 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -4267,8 +4267,6 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.sriov_init = efx_ef10_sriov_init,
 	.sriov_fini = efx_ef10_sriov_fini,
 	.sriov_wanted = efx_ef10_sriov_wanted,
-	.sriov_reset = efx_ef10_sriov_reset,
-	.sriov_flr = efx_ef10_sriov_flr,
 	.sriov_set_vf_mac = efx_ef10_sriov_set_vf_mac,
 	.sriov_set_vf_vlan = efx_ef10_sriov_set_vf_vlan,
 	.sriov_set_vf_spoofchk = efx_ef10_sriov_set_vf_spoofchk,
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.h b/drivers/net/ethernet/sfc/ef10_sriov.h
index 3c703ca878b0a..be419c9c5dec5 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.h
+++ b/drivers/net/ethernet/sfc/ef10_sriov.h
@@ -35,9 +35,7 @@ static inline bool efx_ef10_sriov_wanted(struct efx_nic *efx)
 
 int efx_ef10_sriov_configure(struct efx_nic *efx, int num_vfs);
 int efx_ef10_sriov_init(struct efx_nic *efx);
-static inline void efx_ef10_sriov_reset(struct efx_nic *efx) {}
 void efx_ef10_sriov_fini(struct efx_nic *efx);
-static inline void efx_ef10_sriov_flr(struct efx_nic *efx, unsigned vf_i) {}
 
 int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf, const u8 *mac);
 
diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
index 361687de308dc..c8d8f1e9a21a9 100644
--- a/drivers/net/ethernet/sfc/efx_common.c
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -785,8 +785,6 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
 	mutex_unlock(&efx->rss_lock);
 	efx->type->filter_table_restore(efx);
 	up_write(&efx->filter_sem);
-	if (efx->type->sriov_reset)
-		efx->type->sriov_reset(efx);
 
 	mutex_unlock(&efx->mac_lock);
 
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index f7ffaa14fda47..d23da96273389 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -1352,11 +1352,6 @@ void efx_mcdi_process_event(struct efx_channel *channel,
 	case MCDI_EVENT_CODE_MAC_STATS_DMA:
 		/* MAC stats are gather lazily.  We can ignore this. */
 		break;
-	case MCDI_EVENT_CODE_FLR:
-		if (efx->type->sriov_flr)
-			efx->type->sriov_flr(efx,
-					     MCDI_EVENT_FIELD(*event, FLR_VF));
-		break;
 	case MCDI_EVENT_CODE_PTP_FAULT:
 	case MCDI_EVENT_CODE_PTP_PPS:
 		efx_ptp_event(efx, event);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 25013caaeefb1..474ee577bf0ff 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -1261,10 +1261,6 @@ struct efx_udp_tunnel {
  * @remove_port: Free resources allocated by probe_port()
  * @handle_global_event: Handle a "global" event (may be %NULL)
  * @fini_dmaq: Flush and finalise DMA queues (RX and TX queues)
- * @prepare_flush: Prepare the hardware for flushing the DMA queues
- *	(for Falcon architecture)
- * @finish_flush: Clean up after flushing the DMA queues (for Falcon
- *	architecture)
  * @prepare_flr: Prepare for an FLR
  * @finish_flr: Clean up after an FLR
  * @describe_stats: Describe statistics for ethtool
@@ -1411,8 +1407,6 @@ struct efx_nic_type {
 	void (*remove_port)(struct efx_nic *efx);
 	bool (*handle_global_event)(struct efx_channel *channel, efx_qword_t *);
 	int (*fini_dmaq)(struct efx_nic *efx);
-	void (*prepare_flush)(struct efx_nic *efx);
-	void (*finish_flush)(struct efx_nic *efx);
 	void (*prepare_flr)(struct efx_nic *efx);
 	void (*finish_flr)(struct efx_nic *efx);
 	size_t (*describe_stats)(struct efx_nic *efx, u8 *names);
@@ -1528,8 +1522,6 @@ struct efx_nic_type {
 	int (*sriov_init)(struct efx_nic *efx);
 	void (*sriov_fini)(struct efx_nic *efx);
 	bool (*sriov_wanted)(struct efx_nic *efx);
-	void (*sriov_reset)(struct efx_nic *efx);
-	void (*sriov_flr)(struct efx_nic *efx, unsigned vf_i);
 	int (*sriov_set_vf_mac)(struct efx_nic *efx, int vf_i, const u8 *mac);
 	int (*sriov_set_vf_vlan)(struct efx_nic *efx, int vf_i, u16 vlan,
 				 u8 qos);
-- 
GitLab


From a847431c5ba59c478cfa2aa269854912e774a4a4 Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:41:15 +0100
Subject: [PATCH 0602/1806] sfc: Filter cleanups for Falcon and Siena

unicast_filter and multicast_hash are no longer needed.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/mcdi_port_common.c |  5 -----
 drivers/net/ethernet/sfc/net_driver.h       | 18 ------------------
 2 files changed, 23 deletions(-)

diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.c b/drivers/net/ethernet/sfc/mcdi_port_common.c
index 0ab14f3d01d4d..76ea26722ca46 100644
--- a/drivers/net/ethernet/sfc/mcdi_port_common.c
+++ b/drivers/net/ethernet/sfc/mcdi_port_common.c
@@ -1106,11 +1106,6 @@ int efx_mcdi_set_mac(struct efx_nic *efx)
 
 	MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_MTU, efx_calc_mac_mtu(efx));
 	MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_DRAIN, 0);
-
-	/* Set simple MAC filter for Siena */
-	MCDI_POPULATE_DWORD_1(cmdbytes, SET_MAC_IN_REJECT,
-			      SET_MAC_IN_REJECT_UNCST, efx->unicast_filter);
-
 	MCDI_POPULATE_DWORD_1(cmdbytes, SET_MAC_IN_FLAGS,
 			      SET_MAC_IN_FLAG_INCLUDE_FCS,
 			      !!(efx->net_dev->features & NETIF_F_RXFCS));
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 474ee577bf0ff..6654fbb8f4c01 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -752,18 +752,6 @@ struct efx_hw_stat_desc {
 	u16 offset;
 };
 
-/* Number of bits used in a multicast filter hash address */
-#define EFX_MCAST_HASH_BITS 8
-
-/* Number of (single-bit) entries in a multicast filter hash */
-#define EFX_MCAST_HASH_ENTRIES (1 << EFX_MCAST_HASH_BITS)
-
-/* An Efx multicast filter hash */
-union efx_multicast_hash {
-	u8 byte[EFX_MCAST_HASH_ENTRIES / 8];
-	efx_oword_t oword[EFX_MCAST_HASH_ENTRIES / sizeof(efx_oword_t) / 8];
-};
-
 struct vfdi_status;
 
 /* The reserved RSS context value */
@@ -955,10 +943,6 @@ struct efx_mae;
  *	see &enum ethtool_fec_config_bits.
  * @link_state: Current state of the link
  * @n_link_state_changes: Number of times the link has changed state
- * @unicast_filter: Flag for Falcon-arch simple unicast filter.
- *	Protected by @mac_lock.
- * @multicast_hash: Multicast hash table for Falcon-arch.
- *	Protected by @mac_lock.
  * @wanted_fc: Wanted flow control flags
  * @fc_disable: When non-zero flow control is disabled. Typically used to
  *	ensure that network back pressure doesn't delay dma queue flushes.
@@ -1137,8 +1121,6 @@ struct efx_nic {
 	struct efx_link_state link_state;
 	unsigned int n_link_state_changes;
 
-	bool unicast_filter;
-	union efx_multicast_hash multicast_hash;
 	u8 wanted_fc;
 	unsigned fc_disable;
 
-- 
GitLab


From d73e77153b4db65fccb49e8a6849c496e6f2e9f2 Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:41:21 +0100
Subject: [PATCH 0603/1806] sfc: Remove struct efx_special_buffer

The attributes index and entries are no longer needed, so use
struct efx_buffer instead.
next_buffer_table was also Siena specific.
Removed some checkpatch warnings.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c           |  2 +-
 drivers/net/ethernet/sfc/ef100_nic.c      |  2 +-
 drivers/net/ethernet/sfc/ef100_tx.c       |  6 ++---
 drivers/net/ethernet/sfc/efx_channels.c   | 30 +----------------------
 drivers/net/ethernet/sfc/mcdi_functions.c | 24 +++++++++---------
 drivers/net/ethernet/sfc/net_driver.h     | 28 +++------------------
 drivers/net/ethernet/sfc/nic_common.h     |  6 ++---
 drivers/net/ethernet/sfc/tx_tso.c         |  2 +-
 8 files changed, 25 insertions(+), 75 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index fca0cf3385106..6dfa062feebcb 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -2209,7 +2209,7 @@ static int efx_ef10_tx_probe(struct efx_tx_queue *tx_queue)
 	/* low two bits of label are what we want for type */
 	BUILD_BUG_ON((EFX_TXQ_TYPE_OUTER_CSUM | EFX_TXQ_TYPE_INNER_CSUM) != 3);
 	tx_queue->type = tx_queue->label & 3;
-	return efx_nic_alloc_buffer(tx_queue->efx, &tx_queue->txd.buf,
+	return efx_nic_alloc_buffer(tx_queue->efx, &tx_queue->txd,
 				    (tx_queue->ptr_mask + 1) *
 				    sizeof(efx_qword_t),
 				    GFP_KERNEL);
diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c
index 7adde9639c8ab..f3e8ed578c09e 100644
--- a/drivers/net/ethernet/sfc/ef100_nic.c
+++ b/drivers/net/ethernet/sfc/ef100_nic.c
@@ -224,7 +224,7 @@ int efx_ef100_init_datapath_caps(struct efx_nic *efx)
 static int ef100_ev_probe(struct efx_channel *channel)
 {
 	/* Allocate an extra descriptor for the QMDA status completion entry */
-	return efx_nic_alloc_buffer(channel->efx, &channel->eventq.buf,
+	return efx_nic_alloc_buffer(channel->efx, &channel->eventq,
 				    (channel->eventq_mask + 2) *
 				    sizeof(efx_qword_t),
 				    GFP_KERNEL);
diff --git a/drivers/net/ethernet/sfc/ef100_tx.c b/drivers/net/ethernet/sfc/ef100_tx.c
index 849e5555bd128..e6b6be5495817 100644
--- a/drivers/net/ethernet/sfc/ef100_tx.c
+++ b/drivers/net/ethernet/sfc/ef100_tx.c
@@ -23,7 +23,7 @@
 int ef100_tx_probe(struct efx_tx_queue *tx_queue)
 {
 	/* Allocate an extra descriptor for the QMDA status completion entry */
-	return efx_nic_alloc_buffer(tx_queue->efx, &tx_queue->txd.buf,
+	return efx_nic_alloc_buffer(tx_queue->efx, &tx_queue->txd,
 				    (tx_queue->ptr_mask + 2) *
 				    sizeof(efx_oword_t),
 				    GFP_KERNEL);
@@ -101,8 +101,8 @@ static bool ef100_tx_can_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 
 static efx_oword_t *ef100_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index)
 {
-	if (likely(tx_queue->txd.buf.addr))
-		return ((efx_oword_t *)tx_queue->txd.buf.addr) + index;
+	if (likely(tx_queue->txd.addr))
+		return ((efx_oword_t *)tx_queue->txd.addr) + index;
 	else
 		return NULL;
 }
diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c
index 41b33a75333cd..8d2d7ea2ebefc 100644
--- a/drivers/net/ethernet/sfc/efx_channels.c
+++ b/drivers/net/ethernet/sfc/efx_channels.c
@@ -713,9 +713,6 @@ int efx_probe_channels(struct efx_nic *efx)
 	struct efx_channel *channel;
 	int rc;
 
-	/* Restart special buffer allocation */
-	efx->next_buffer_table = 0;
-
 	/* Probe channels in reverse, so that any 'extra' channels
 	 * use the start of the buffer table. This allows the traffic
 	 * channels to be resized without moving them or wasting the
@@ -849,36 +846,14 @@ int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
 	struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel,
 			   *ptp_channel = efx_ptp_channel(efx);
 	struct efx_ptp_data *ptp_data = efx->ptp_data;
-	unsigned int i, next_buffer_table = 0;
 	u32 old_rxq_entries, old_txq_entries;
+	unsigned int i;
 	int rc, rc2;
 
 	rc = efx_check_disabled(efx);
 	if (rc)
 		return rc;
 
-	/* Not all channels should be reallocated. We must avoid
-	 * reallocating their buffer table entries.
-	 */
-	efx_for_each_channel(channel, efx) {
-		struct efx_rx_queue *rx_queue;
-		struct efx_tx_queue *tx_queue;
-
-		if (channel->type->copy)
-			continue;
-		next_buffer_table = max(next_buffer_table,
-					channel->eventq.index +
-					channel->eventq.entries);
-		efx_for_each_channel_rx_queue(rx_queue, channel)
-			next_buffer_table = max(next_buffer_table,
-						rx_queue->rxd.index +
-						rx_queue->rxd.entries);
-		efx_for_each_channel_tx_queue(tx_queue, channel)
-			next_buffer_table = max(next_buffer_table,
-						tx_queue->txd.index +
-						tx_queue->txd.entries);
-	}
-
 	efx_device_detach_sync(efx);
 	efx_stop_all(efx);
 	efx_soft_disable_interrupts(efx);
@@ -904,9 +879,6 @@ int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
 	for (i = 0; i < efx->n_channels; i++)
 		swap(efx->channel[i], other_channel[i]);
 
-	/* Restart buffer table allocation */
-	efx->next_buffer_table = next_buffer_table;
-
 	for (i = 0; i < efx->n_channels; i++) {
 		channel = efx->channel[i];
 		if (!channel->type->copy)
diff --git a/drivers/net/ethernet/sfc/mcdi_functions.c b/drivers/net/ethernet/sfc/mcdi_functions.c
index d3e6d8239f5c8..ff8424167384b 100644
--- a/drivers/net/ethernet/sfc/mcdi_functions.c
+++ b/drivers/net/ethernet/sfc/mcdi_functions.c
@@ -62,7 +62,7 @@ int efx_mcdi_alloc_vis(struct efx_nic *efx, unsigned int min_vis,
 
 int efx_mcdi_ev_probe(struct efx_channel *channel)
 {
-	return efx_nic_alloc_buffer(channel->efx, &channel->eventq.buf,
+	return efx_nic_alloc_buffer(channel->efx, &channel->eventq,
 				    (channel->eventq_mask + 1) *
 				    sizeof(efx_qword_t),
 				    GFP_KERNEL);
@@ -74,14 +74,14 @@ int efx_mcdi_ev_init(struct efx_channel *channel, bool v1_cut_thru, bool v2)
 			 MC_CMD_INIT_EVQ_V2_IN_LEN(EFX_MAX_EVQ_SIZE * 8 /
 						   EFX_BUF_SIZE));
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_INIT_EVQ_V2_OUT_LEN);
-	size_t entries = channel->eventq.buf.len / EFX_BUF_SIZE;
+	size_t entries = channel->eventq.len / EFX_BUF_SIZE;
 	struct efx_nic *efx = channel->efx;
 	size_t inlen, outlen;
 	dma_addr_t dma_addr;
 	int rc, i;
 
 	/* Fill event queue with all ones (i.e. empty events) */
-	memset(channel->eventq.buf.addr, 0xff, channel->eventq.buf.len);
+	memset(channel->eventq.addr, 0xff, channel->eventq.len);
 
 	MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_SIZE, channel->eventq_mask + 1);
 	MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_INSTANCE, channel->channel);
@@ -112,7 +112,7 @@ int efx_mcdi_ev_init(struct efx_channel *channel, bool v1_cut_thru, bool v2)
 				      INIT_EVQ_IN_FLAG_CUT_THRU, v1_cut_thru);
 	}
 
-	dma_addr = channel->eventq.buf.dma_addr;
+	dma_addr = channel->eventq.dma_addr;
 	for (i = 0; i < entries; ++i) {
 		MCDI_SET_ARRAY_QWORD(inbuf, INIT_EVQ_IN_DMA_ADDR, i, dma_addr);
 		dma_addr += EFX_BUF_SIZE;
@@ -134,7 +134,7 @@ int efx_mcdi_ev_init(struct efx_channel *channel, bool v1_cut_thru, bool v2)
 
 void efx_mcdi_ev_remove(struct efx_channel *channel)
 {
-	efx_nic_free_buffer(channel->efx, &channel->eventq.buf);
+	efx_nic_free_buffer(channel->efx, &channel->eventq);
 }
 
 void efx_mcdi_ev_fini(struct efx_channel *channel)
@@ -166,7 +166,7 @@ int efx_mcdi_tx_init(struct efx_tx_queue *tx_queue)
 						       EFX_BUF_SIZE));
 	bool csum_offload = tx_queue->type & EFX_TXQ_TYPE_OUTER_CSUM;
 	bool inner_csum = tx_queue->type & EFX_TXQ_TYPE_INNER_CSUM;
-	size_t entries = tx_queue->txd.buf.len / EFX_BUF_SIZE;
+	size_t entries = tx_queue->txd.len / EFX_BUF_SIZE;
 	struct efx_channel *channel = tx_queue->channel;
 	struct efx_nic *efx = tx_queue->efx;
 	dma_addr_t dma_addr;
@@ -182,7 +182,7 @@ int efx_mcdi_tx_init(struct efx_tx_queue *tx_queue)
 	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_OWNER_ID, 0);
 	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_PORT_ID, efx->vport_id);
 
-	dma_addr = tx_queue->txd.buf.dma_addr;
+	dma_addr = tx_queue->txd.dma_addr;
 
 	netif_dbg(efx, hw, efx->net_dev, "pushing TXQ %d. %zu entries (%llx)\n",
 		  tx_queue->queue, entries, (u64)dma_addr);
@@ -240,7 +240,7 @@ fail:
 
 void efx_mcdi_tx_remove(struct efx_tx_queue *tx_queue)
 {
-	efx_nic_free_buffer(tx_queue->efx, &tx_queue->txd.buf);
+	efx_nic_free_buffer(tx_queue->efx, &tx_queue->txd);
 }
 
 void efx_mcdi_tx_fini(struct efx_tx_queue *tx_queue)
@@ -269,7 +269,7 @@ fail:
 
 int efx_mcdi_rx_probe(struct efx_rx_queue *rx_queue)
 {
-	return efx_nic_alloc_buffer(rx_queue->efx, &rx_queue->rxd.buf,
+	return efx_nic_alloc_buffer(rx_queue->efx, &rx_queue->rxd,
 				    (rx_queue->ptr_mask + 1) *
 				    sizeof(efx_qword_t),
 				    GFP_KERNEL);
@@ -278,7 +278,7 @@ int efx_mcdi_rx_probe(struct efx_rx_queue *rx_queue)
 void efx_mcdi_rx_init(struct efx_rx_queue *rx_queue)
 {
 	struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
-	size_t entries = rx_queue->rxd.buf.len / EFX_BUF_SIZE;
+	size_t entries = rx_queue->rxd.len / EFX_BUF_SIZE;
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_INIT_RXQ_V4_IN_LEN);
 	struct efx_nic *efx = rx_queue->efx;
 	unsigned int buffer_size;
@@ -306,7 +306,7 @@ void efx_mcdi_rx_init(struct efx_rx_queue *rx_queue)
 	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_PORT_ID, efx->vport_id);
 	MCDI_SET_DWORD(inbuf, INIT_RXQ_V4_IN_BUFFER_SIZE_BYTES, buffer_size);
 
-	dma_addr = rx_queue->rxd.buf.dma_addr;
+	dma_addr = rx_queue->rxd.dma_addr;
 
 	netif_dbg(efx, hw, efx->net_dev, "pushing RXQ %d. %zu entries (%llx)\n",
 		  efx_rx_queue_index(rx_queue), entries, (u64)dma_addr);
@@ -325,7 +325,7 @@ void efx_mcdi_rx_init(struct efx_rx_queue *rx_queue)
 
 void efx_mcdi_rx_remove(struct efx_rx_queue *rx_queue)
 {
-	efx_nic_free_buffer(rx_queue->efx, &rx_queue->rxd.buf);
+	efx_nic_free_buffer(rx_queue->efx, &rx_queue->rxd);
 }
 
 void efx_mcdi_rx_fini(struct efx_rx_queue *rx_queue)
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 6654fbb8f4c01..27d86e90a3bb5 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -122,26 +122,6 @@ struct efx_buffer {
 	unsigned int len;
 };
 
-/**
- * struct efx_special_buffer - DMA buffer entered into buffer table
- * @buf: Standard &struct efx_buffer
- * @index: Buffer index within controller;s buffer table
- * @entries: Number of buffer table entries
- *
- * The NIC has a buffer table that maps buffers of size %EFX_BUF_SIZE.
- * Event and descriptor rings are addressed via one or more buffer
- * table entries (and so can be physically non-contiguous, although we
- * currently do not take advantage of that).  On Falcon and Siena we
- * have to take care of allocating and initialising the entries
- * ourselves.  On later hardware this is managed by the firmware and
- * @index and @entries are left as 0.
- */
-struct efx_special_buffer {
-	struct efx_buffer buf;
-	unsigned int index;
-	unsigned int entries;
-};
-
 /**
  * struct efx_tx_buffer - buffer state for a TX descriptor
  * @skb: When @flags & %EFX_TX_BUF_SKB, the associated socket buffer to be
@@ -268,7 +248,7 @@ struct efx_tx_queue {
 	struct netdev_queue *core_txq;
 	struct efx_tx_buffer *buffer;
 	struct efx_buffer *cb_page;
-	struct efx_special_buffer txd;
+	struct efx_buffer txd;
 	unsigned int ptr_mask;
 	void __iomem *piobuf;
 	unsigned int piobuf_offset;
@@ -397,7 +377,7 @@ struct efx_rx_queue {
 	struct efx_nic *efx;
 	int core_index;
 	struct efx_rx_buffer *buffer;
-	struct efx_special_buffer rxd;
+	struct efx_buffer rxd;
 	unsigned int ptr_mask;
 	bool refill_enabled;
 	bool flush_pending;
@@ -513,7 +493,7 @@ struct efx_channel {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	unsigned long busy_poll_state;
 #endif
-	struct efx_special_buffer eventq;
+	struct efx_buffer eventq;
 	unsigned int eventq_mask;
 	unsigned int eventq_read_ptr;
 	int event_test_cpu;
@@ -881,7 +861,6 @@ struct efx_mae;
  * @tx_dc_base: Base qword address in SRAM of TX queue descriptor caches
  * @rx_dc_base: Base qword address in SRAM of RX queue descriptor caches
  * @sram_lim_qw: Qword address limit of SRAM
- * @next_buffer_table: First available buffer table id
  * @n_channels: Number of channels in use
  * @n_rx_channels: Number of channels used for RX (= number of RX queues)
  * @n_tx_channels: Number of channels used for TX
@@ -1046,7 +1025,6 @@ struct efx_nic {
 	unsigned tx_dc_base;
 	unsigned rx_dc_base;
 	unsigned sram_lim_qw;
-	unsigned next_buffer_table;
 
 	unsigned int max_channels;
 	unsigned int max_vis;
diff --git a/drivers/net/ethernet/sfc/nic_common.h b/drivers/net/ethernet/sfc/nic_common.h
index e35ecbe8842ec..47b1c46c069d2 100644
--- a/drivers/net/ethernet/sfc/nic_common.h
+++ b/drivers/net/ethernet/sfc/nic_common.h
@@ -32,7 +32,7 @@ static inline int efx_nic_rev(struct efx_nic *efx)
 static inline efx_qword_t *efx_event(struct efx_channel *channel,
 				     unsigned int index)
 {
-	return ((efx_qword_t *) (channel->eventq.buf.addr)) +
+	return ((efx_qword_t *)(channel->eventq.addr)) +
 		(index & channel->eventq_mask);
 }
 
@@ -58,7 +58,7 @@ static inline int efx_event_present(efx_qword_t *event)
 static inline efx_qword_t *
 efx_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index)
 {
-	return ((efx_qword_t *) (tx_queue->txd.buf.addr)) + index;
+	return ((efx_qword_t *)(tx_queue->txd.addr)) + index;
 }
 
 /* Report whether this TX queue would be empty for the given write_count.
@@ -98,7 +98,7 @@ static inline bool efx_nic_may_push_tx_desc(struct efx_tx_queue *tx_queue,
 static inline efx_qword_t *
 efx_rx_desc(struct efx_rx_queue *rx_queue, unsigned int index)
 {
-	return ((efx_qword_t *) (rx_queue->rxd.buf.addr)) + index;
+	return ((efx_qword_t *)(rx_queue->rxd.addr)) + index;
 }
 
 /* Alignment of PCIe DMA boundaries (4KB) */
diff --git a/drivers/net/ethernet/sfc/tx_tso.c b/drivers/net/ethernet/sfc/tx_tso.c
index d381d8164f07c..64a6768f75ea1 100644
--- a/drivers/net/ethernet/sfc/tx_tso.c
+++ b/drivers/net/ethernet/sfc/tx_tso.c
@@ -85,7 +85,7 @@ static inline void prefetch_ptr(struct efx_tx_queue *tx_queue)
 	prefetch(ptr);
 	prefetch(ptr + 0x80);
 
-	ptr = (char *) (((efx_qword_t *)tx_queue->txd.buf.addr) + insert_ptr);
+	ptr = (char *)(((efx_qword_t *)tx_queue->txd.addr) + insert_ptr);
 	prefetch(ptr);
 	prefetch(ptr + 0x80);
 }
-- 
GitLab


From ae9d445cd41fc71205f97c4f7710bb90c570cf5e Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:41:26 +0100
Subject: [PATCH 0604/1806] sfc: Miscellaneous comment removals

Remove comments that only apply to Falcon and Siena.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/efx_common.c | 5 -----
 drivers/net/ethernet/sfc/filter.h     | 7 -------
 drivers/net/ethernet/sfc/nic_common.h | 4 +---
 drivers/net/ethernet/sfc/selftest.c   | 7 +------
 4 files changed, 2 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
index c8d8f1e9a21a9..175bd9cdfdac3 100644
--- a/drivers/net/ethernet/sfc/efx_common.c
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -35,11 +35,6 @@ MODULE_PARM_DESC(debug, "Bitmapped debugging message enable value");
 
 /* This is the time (in jiffies) between invocations of the hardware
  * monitor.
- * On Falcon-based NICs, this will:
- * - Check the on-board hardware monitor;
- * - Poll the link state and reconfigure the hardware as necessary.
- * On Siena-based NICs for power systems with EEH support, this will give EEH a
- * chance to start.
  */
 static unsigned int efx_monitor_interval = 1 * HZ;
 
diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h
index 5f201a547e5b5..0d45900afa76f 100644
--- a/drivers/net/ethernet/sfc/filter.h
+++ b/drivers/net/ethernet/sfc/filter.h
@@ -30,13 +30,6 @@
  *
  * Only some combinations are supported, depending on NIC type:
  *
- * - Falcon supports RX filters matching by {TCP,UDP}/IPv4 4-tuple or
- *   local 2-tuple (only implemented for Falcon B0)
- *
- * - Siena supports RX and TX filters matching by {TCP,UDP}/IPv4 4-tuple
- *   or local 2-tuple, or local MAC with or without outer VID, and RX
- *   default filters
- *
  * - Huntington supports filter matching controlled by firmware, potentially
  *   using {TCP,UDP}/IPv{4,6} 4-tuple or local 2-tuple, local MAC or I/G bit,
  *   with or without outer and inner VID
diff --git a/drivers/net/ethernet/sfc/nic_common.h b/drivers/net/ethernet/sfc/nic_common.h
index 47b1c46c069d2..466df5348b29f 100644
--- a/drivers/net/ethernet/sfc/nic_common.h
+++ b/drivers/net/ethernet/sfc/nic_common.h
@@ -79,9 +79,7 @@ int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
 
 /* Decide whether to push a TX descriptor to the NIC vs merely writing
  * the doorbell.  This can reduce latency when we are adding a single
- * descriptor to an empty queue, but is otherwise pointless.  Further,
- * Falcon and Siena have hardware bugs (SF bug 33851) that may be
- * triggered if we don't check this.
+ * descriptor to an empty queue, but is otherwise pointless.
  * We use the write_count used for the last doorbell push, to get the
  * NIC's view of the tx queue.
  */
diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c
index 96d856b9043c4..40d9bf642408c 100644
--- a/drivers/net/ethernet/sfc/selftest.c
+++ b/drivers/net/ethernet/sfc/selftest.c
@@ -38,8 +38,7 @@
 /*
  * Loopback test packet structure
  *
- * The self-test should stress every RSS vector, and unfortunately
- * Falcon only performs RSS on TCP/UDP packets.
+ * The self-test should stress every RSS vector.
  */
 struct efx_loopback_payload {
 	char pad[2]; /* Ensures ip is 4-byte aligned */
@@ -581,10 +580,6 @@ efx_test_loopback(struct efx_tx_queue *tx_queue,
 	return 0;
 }
 
-/* Wait for link up. On Falcon, we would prefer to rely on efx_monitor, but
- * any contention on the mac lock (via e.g. efx_mac_mcast_work) causes it
- * to delay and retry. Therefore, it's safer to just poll directly. Wait
- * for link up and any faults to dissipate. */
 static int efx_wait_for_link(struct efx_nic *efx)
 {
 	struct efx_link_state *link_state = &efx->link_state;
-- 
GitLab


From b0d1fe9bcdc66406dcc650ec0b750bd3c2ce2005 Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:41:32 +0100
Subject: [PATCH 0605/1806] sfc: Cleanups in io.h

Most of the Falcon locking description does not apply to EF10.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/io.h  | 84 ++++------------------------------
 drivers/net/ethernet/sfc/nic.c |  5 --
 2 files changed, 9 insertions(+), 80 deletions(-)

diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h
index 30439cc83a891..7432c09010d63 100644
--- a/drivers/net/ethernet/sfc/io.h
+++ b/drivers/net/ethernet/sfc/io.h
@@ -17,46 +17,22 @@
  *
  **************************************************************************
  *
- * Notes on locking strategy for the Falcon architecture:
- *
- * Many CSRs are very wide and cannot be read or written atomically.
- * Writes from the host are buffered by the Bus Interface Unit (BIU)
- * up to 128 bits.  Whenever the host writes part of such a register,
- * the BIU collects the written value and does not write to the
- * underlying register until all 4 dwords have been written.  A
- * similar buffering scheme applies to host access to the NIC's 64-bit
- * SRAM.
- *
- * Writes to different CSRs and 64-bit SRAM words must be serialised,
- * since interleaved access can result in lost writes.  We use
- * efx_nic::biu_lock for this.
- *
- * We also serialise reads from 128-bit CSRs and SRAM with the same
- * spinlock.  This may not be necessary, but it doesn't really matter
- * as there are no such reads on the fast path.
+ * The EF10 architecture exposes very few registers to the host and
+ * most of them are only 32 bits wide.  The only exceptions are the MC
+ * doorbell register pair, which has its own latching, and
+ * TX_DESC_UPD.
  *
- * The DMA descriptor pointers (RX_DESC_UPD and TX_DESC_UPD) are
- * 128-bit but are special-cased in the BIU to avoid the need for
- * locking in the host:
+ * The TX_DESC_UPD DMA descriptor pointer is 128-bits but is a special
+ * case in the BIU to avoid the need for locking in the host:
  *
- * - They are write-only.
- * - The semantics of writing to these registers are such that
+ * - It is write-only.
+ * - The semantics of writing to this register is such that
  *   replacing the low 96 bits with zero does not affect functionality.
- * - If the host writes to the last dword address of such a register
+ * - If the host writes to the last dword address of the register
  *   (i.e. the high 32 bits) the underlying register will always be
  *   written.  If the collector and the current write together do not
  *   provide values for all 128 bits of the register, the low 96 bits
  *   will be written as zero.
- * - If the host writes to the address of any other part of such a
- *   register while the collector already holds values for some other
- *   register, the write is discarded and the collector maintains its
- *   current state.
- *
- * The EF10 architecture exposes very few registers to the host and
- * most of them are only 32 bits wide.  The only exceptions are the MC
- * doorbell register pair, which has its own latching, and
- * TX_DESC_UPD, which works in a similar way to the Falcon
- * architecture.
  */
 
 #if BITS_PER_LONG == 64
@@ -125,27 +101,6 @@ static inline void efx_writeo(struct efx_nic *efx, const efx_oword_t *value,
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
-/* Write 64-bit SRAM through the supplied mapping, locking as appropriate. */
-static inline void efx_sram_writeq(struct efx_nic *efx, void __iomem *membase,
-				   const efx_qword_t *value, unsigned int index)
-{
-	unsigned int addr = index * sizeof(*value);
-	unsigned long flags __attribute__ ((unused));
-
-	netif_vdbg(efx, hw, efx->net_dev,
-		   "writing SRAM address %x with " EFX_QWORD_FMT "\n",
-		   addr, EFX_QWORD_VAL(*value));
-
-	spin_lock_irqsave(&efx->biu_lock, flags);
-#ifdef EFX_USE_QWORD_IO
-	__raw_writeq((__force u64)value->u64[0], membase + addr);
-#else
-	__raw_writel((__force u32)value->u32[0], membase + addr);
-	__raw_writel((__force u32)value->u32[1], membase + addr + 4);
-#endif
-	spin_unlock_irqrestore(&efx->biu_lock, flags);
-}
-
 /* Write a 32-bit CSR or the last dword of a special 128-bit CSR */
 static inline void efx_writed(struct efx_nic *efx, const efx_dword_t *value,
 			      unsigned int reg)
@@ -176,27 +131,6 @@ static inline void efx_reado(struct efx_nic *efx, efx_oword_t *value,
 		   EFX_OWORD_VAL(*value));
 }
 
-/* Read 64-bit SRAM through the supplied mapping, locking as appropriate. */
-static inline void efx_sram_readq(struct efx_nic *efx, void __iomem *membase,
-				  efx_qword_t *value, unsigned int index)
-{
-	unsigned int addr = index * sizeof(*value);
-	unsigned long flags __attribute__ ((unused));
-
-	spin_lock_irqsave(&efx->biu_lock, flags);
-#ifdef EFX_USE_QWORD_IO
-	value->u64[0] = (__force __le64)__raw_readq(membase + addr);
-#else
-	value->u32[0] = (__force __le32)__raw_readl(membase + addr);
-	value->u32[1] = (__force __le32)__raw_readl(membase + addr + 4);
-#endif
-	spin_unlock_irqrestore(&efx->biu_lock, flags);
-
-	netif_vdbg(efx, hw, efx->net_dev,
-		   "read from SRAM address %x, got "EFX_QWORD_FMT"\n",
-		   addr, EFX_QWORD_VAL(*value));
-}
-
 /* Read a 32-bit CSR or SRAM */
 static inline void efx_readd(struct efx_nic *efx, efx_dword_t *value,
 				unsigned int reg)
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 7e057741425f6..a33ed473cc8af 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -272,11 +272,6 @@ void efx_nic_get_regs(struct efx_nic *efx, void *buf)
 			case 4: /* 32-bit SRAM */
 				efx_readd(efx, buf, table->offset + 4 * i);
 				break;
-			case 8: /* 64-bit SRAM */
-				efx_sram_readq(efx,
-					       efx->membase + table->offset,
-					       buf, i);
-				break;
 			case 16: /* 128-bit-readable register */
 				efx_reado_table(efx, buf, table->offset, i);
 				break;
-- 
GitLab


From 3771c878b460c11acab5fc72f393a1b27612ac49 Mon Sep 17 00:00:00 2001
From: Martin Habets <habetsm.xilinx@gmail.com>
Date: Thu, 27 Jul 2023 11:41:37 +0100
Subject: [PATCH 0606/1806] sfc: Remove vfdi.h

It was only used for Siena SRIOV, so nothing includes it any more
in this directory.

Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/vfdi.h | 252 --------------------------------
 1 file changed, 252 deletions(-)
 delete mode 100644 drivers/net/ethernet/sfc/vfdi.h

diff --git a/drivers/net/ethernet/sfc/vfdi.h b/drivers/net/ethernet/sfc/vfdi.h
deleted file mode 100644
index 480b872eb4d1d..0000000000000
--- a/drivers/net/ethernet/sfc/vfdi.h
+++ /dev/null
@@ -1,252 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/****************************************************************************
- * Driver for Solarflare network controllers and boards
- * Copyright 2010-2012 Solarflare Communications Inc.
- */
-#ifndef _VFDI_H
-#define _VFDI_H
-
-/**
- * DOC: Virtual Function Driver Interface
- *
- * This file contains software structures used to form a two way
- * communication channel between the VF driver and the PF driver,
- * named Virtual Function Driver Interface (VFDI).
- *
- * For the purposes of VFDI, a page is a memory region with size and
- * alignment of 4K.  All addresses are DMA addresses to be used within
- * the domain of the relevant VF.
- *
- * The only hardware-defined channels for a VF driver to communicate
- * with the PF driver are the event mailboxes (%FR_CZ_USR_EV
- * registers).  Writing to these registers generates an event with
- * EV_CODE = EV_CODE_USR_EV, USER_QID set to the index of the mailbox
- * and USER_EV_REG_VALUE set to the value written.  The PF driver may
- * direct or disable delivery of these events by setting
- * %FR_CZ_USR_EV_CFG.
- *
- * The PF driver can send arbitrary events to arbitrary event queues.
- * However, for consistency, VFDI events from the PF are defined to
- * follow the same form and be sent to the first event queue assigned
- * to the VF while that queue is enabled by the VF driver.
- *
- * The general form of the variable bits of VFDI events is:
- *
- *       0             16                       24   31
- *      | DATA        | TYPE                   | SEQ   |
- *
- * SEQ is a sequence number which should be incremented by 1 (modulo
- * 256) for each event.  The sequence numbers used in each direction
- * are independent.
- *
- * The VF submits requests of type &struct vfdi_req by sending the
- * address of the request (ADDR) in a series of 4 events:
- *
- *       0             16                       24   31
- *      | ADDR[0:15]  | VFDI_EV_TYPE_REQ_WORD0 | SEQ   |
- *      | ADDR[16:31] | VFDI_EV_TYPE_REQ_WORD1 | SEQ+1 |
- *      | ADDR[32:47] | VFDI_EV_TYPE_REQ_WORD2 | SEQ+2 |
- *      | ADDR[48:63] | VFDI_EV_TYPE_REQ_WORD3 | SEQ+3 |
- *
- * The address must be page-aligned.  After receiving such a valid
- * series of events, the PF driver will attempt to read the request
- * and write a response to the same address.  In case of an invalid
- * sequence of events or a DMA error, there will be no response.
- *
- * The VF driver may request that the PF driver writes status
- * information into its domain asynchronously.  After writing the
- * status, the PF driver will send an event of the form:
- *
- *       0             16                       24   31
- *      | reserved    | VFDI_EV_TYPE_STATUS    | SEQ   |
- *
- * In case the VF must be reset for any reason, the PF driver will
- * send an event of the form:
- *
- *       0             16                       24   31
- *      | reserved    | VFDI_EV_TYPE_RESET     | SEQ   |
- *
- * It is then the responsibility of the VF driver to request
- * reinitialisation of its queues.
- */
-#define VFDI_EV_SEQ_LBN 24
-#define VFDI_EV_SEQ_WIDTH 8
-#define VFDI_EV_TYPE_LBN 16
-#define VFDI_EV_TYPE_WIDTH 8
-#define VFDI_EV_TYPE_REQ_WORD0 0
-#define VFDI_EV_TYPE_REQ_WORD1 1
-#define VFDI_EV_TYPE_REQ_WORD2 2
-#define VFDI_EV_TYPE_REQ_WORD3 3
-#define VFDI_EV_TYPE_STATUS 4
-#define VFDI_EV_TYPE_RESET 5
-#define VFDI_EV_DATA_LBN 0
-#define VFDI_EV_DATA_WIDTH 16
-
-struct vfdi_endpoint {
-	u8 mac_addr[ETH_ALEN];
-	__be16 tci;
-};
-
-/**
- * enum vfdi_op - VFDI operation enumeration
- * @VFDI_OP_RESPONSE: Indicates a response to the request.
- * @VFDI_OP_INIT_EVQ: Initialize SRAM entries and initialize an EVQ.
- * @VFDI_OP_INIT_RXQ: Initialize SRAM entries and initialize an RXQ.
- * @VFDI_OP_INIT_TXQ: Initialize SRAM entries and initialize a TXQ.
- * @VFDI_OP_FINI_ALL_QUEUES: Flush all queues, finalize all queues, then
- *	finalize the SRAM entries.
- * @VFDI_OP_INSERT_FILTER: Insert a MAC filter targeting the given RXQ.
- * @VFDI_OP_REMOVE_ALL_FILTERS: Remove all filters.
- * @VFDI_OP_SET_STATUS_PAGE: Set the DMA page(s) used for status updates
- *	from PF and write the initial status.
- * @VFDI_OP_CLEAR_STATUS_PAGE: Clear the DMA page(s) used for status
- *	updates from PF.
- */
-enum vfdi_op {
-	VFDI_OP_RESPONSE = 0,
-	VFDI_OP_INIT_EVQ = 1,
-	VFDI_OP_INIT_RXQ = 2,
-	VFDI_OP_INIT_TXQ = 3,
-	VFDI_OP_FINI_ALL_QUEUES = 4,
-	VFDI_OP_INSERT_FILTER = 5,
-	VFDI_OP_REMOVE_ALL_FILTERS = 6,
-	VFDI_OP_SET_STATUS_PAGE = 7,
-	VFDI_OP_CLEAR_STATUS_PAGE = 8,
-	VFDI_OP_LIMIT,
-};
-
-/* Response codes for VFDI operations. Other values may be used in future. */
-#define VFDI_RC_SUCCESS		0
-#define VFDI_RC_ENOMEM		(-12)
-#define VFDI_RC_EINVAL		(-22)
-#define VFDI_RC_EOPNOTSUPP	(-95)
-#define VFDI_RC_ETIMEDOUT	(-110)
-
-/**
- * struct vfdi_req - Request from VF driver to PF driver
- * @op: Operation code or response indicator, taken from &enum vfdi_op.
- * @rc: Response code.  Set to 0 on success or a negative error code on failure.
- * @u.init_evq.index: Index of event queue to create.
- * @u.init_evq.buf_count: Number of 4k buffers backing event queue.
- * @u.init_evq.addr: Array of length %u.init_evq.buf_count containing DMA
- *	address of each page backing the event queue.
- * @u.init_rxq.index: Index of receive queue to create.
- * @u.init_rxq.buf_count: Number of 4k buffers backing receive queue.
- * @u.init_rxq.evq: Instance of event queue to target receive events at.
- * @u.init_rxq.label: Label used in receive events.
- * @u.init_rxq.flags: Unused.
- * @u.init_rxq.addr: Array of length %u.init_rxq.buf_count containing DMA
- *	address of each page backing the receive queue.
- * @u.init_txq.index: Index of transmit queue to create.
- * @u.init_txq.buf_count: Number of 4k buffers backing transmit queue.
- * @u.init_txq.evq: Instance of event queue to target transmit completion
- *	events at.
- * @u.init_txq.label: Label used in transmit completion events.
- * @u.init_txq.flags: Checksum offload flags.
- * @u.init_txq.addr: Array of length %u.init_txq.buf_count containing DMA
- *	address of each page backing the transmit queue.
- * @u.mac_filter.rxq: Insert MAC filter at VF local address/VLAN targeting
- *	all traffic at this receive queue.
- * @u.mac_filter.flags: MAC filter flags.
- * @u.set_status_page.dma_addr: Base address for the &struct vfdi_status.
- *	This address must be page-aligned and the PF may write up to a
- *	whole page (allowing for extension of the structure).
- * @u.set_status_page.peer_page_count: Number of additional pages the VF
- *	has provided into which peer addresses may be DMAd.
- * @u.set_status_page.peer_page_addr: Array of DMA addresses of pages.
- *	If the number of peers exceeds 256, then the VF must provide
- *	additional pages in this array. The PF will then DMA up to
- *	512 vfdi_endpoint structures into each page.  These addresses
- *	must be page-aligned.
- */
-struct vfdi_req {
-	u32 op;
-	u32 reserved1;
-	s32 rc;
-	u32 reserved2;
-	union {
-		struct {
-			u32 index;
-			u32 buf_count;
-			u64 addr[];
-		} init_evq;
-		struct {
-			u32 index;
-			u32 buf_count;
-			u32 evq;
-			u32 label;
-			u32 flags;
-#define VFDI_RXQ_FLAG_SCATTER_EN 1
-			u32 reserved;
-			u64 addr[];
-		} init_rxq;
-		struct {
-			u32 index;
-			u32 buf_count;
-			u32 evq;
-			u32 label;
-			u32 flags;
-#define VFDI_TXQ_FLAG_IP_CSUM_DIS 1
-#define VFDI_TXQ_FLAG_TCPUDP_CSUM_DIS 2
-			u32 reserved;
-			u64 addr[];
-		} init_txq;
-		struct {
-			u32 rxq;
-			u32 flags;
-#define VFDI_MAC_FILTER_FLAG_RSS 1
-#define VFDI_MAC_FILTER_FLAG_SCATTER 2
-		} mac_filter;
-		struct {
-			u64 dma_addr;
-			u64 peer_page_count;
-			u64 peer_page_addr[];
-		} set_status_page;
-	} u;
-};
-
-/**
- * struct vfdi_status - Status provided by PF driver to VF driver
- * @generation_start: A generation count DMA'd to VF *before* the
- *	rest of the structure.
- * @generation_end: A generation count DMA'd to VF *after* the
- *	rest of the structure.
- * @version: Version of this structure; currently set to 1.  Later
- *	versions must either be layout-compatible or only be sent to VFs
- *	that specifically request them.
- * @length: Total length of this structure including embedded tables
- * @vi_scale: log2 the number of VIs available on this VF. This quantity
- *	is used by the hardware for register decoding.
- * @max_tx_channels: The maximum number of transmit queues the VF can use.
- * @rss_rxq_count: The number of receive queues present in the shared RSS
- *	indirection table.
- * @peer_count: Total number of peers in the complete peer list. If larger
- *	than ARRAY_SIZE(%peers), then the VF must provide sufficient
- *	additional pages each of which is filled with vfdi_endpoint structures.
- * @local: The MAC address and outer VLAN tag of *this* VF
- * @peers: Table of peer addresses.  The @tci fields in these structures
- *	are currently unused and must be ignored.  Additional peers are
- *	written into any additional pages provided by the VF.
- * @timer_quantum_ns: Timer quantum (nominal period between timer ticks)
- *	for interrupt moderation timers, in nanoseconds. This member is only
- *	present if @length is sufficiently large.
- */
-struct vfdi_status {
-	u32 generation_start;
-	u32 generation_end;
-	u32 version;
-	u32 length;
-	u8 vi_scale;
-	u8 max_tx_channels;
-	u8 rss_rxq_count;
-	u8 reserved1;
-	u16 peer_count;
-	u16 reserved2;
-	struct vfdi_endpoint local;
-	struct vfdi_endpoint peers[256];
-
-	/* Members below here extend version 1 of this structure */
-	u32 timer_quantum_ns;
-};
-
-#endif
-- 
GitLab


From c8ba75c4eb846888f8f2730690b99cb5bf7b337c Mon Sep 17 00:00:00 2001
From: Alex Maftei <alex.maftei@amd.com>
Date: Tue, 25 Jul 2023 22:53:33 +0100
Subject: [PATCH 0607/1806] selftests/ptp: Add -x option for testing
 PTP_SYS_OFFSET_EXTENDED

The -x option (where 'x' stands for eXtended) takes an argument which
represents the number of samples to request from the PTP device.
The help message will display the maximum number of samples allowed.
Providing an invalid argument will also display the maximum number of
samples allowed.

Signed-off-by: Alex Maftei <alex.maftei@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/ptp/testptp.c | 44 +++++++++++++++++++++++++--
 1 file changed, 42 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c
index e9438a1862adf..71ceb6444af40 100644
--- a/tools/testing/selftests/ptp/testptp.c
+++ b/tools/testing/selftests/ptp/testptp.c
@@ -143,8 +143,9 @@ static void usage(char *progname)
 		" -S         set the system time from the ptp clock time\n"
 		" -t val     shift the ptp clock time by 'val' seconds\n"
 		" -T val     set the ptp clock time to 'val' seconds\n"
+		" -x val     get an extended ptp clock time with the desired number of samples (up to %d)\n"
 		" -z         test combinations of rising/falling external time stamp flags\n",
-		progname);
+		progname, PTP_MAX_SAMPLES);
 }
 
 int main(int argc, char *argv[])
@@ -158,6 +159,7 @@ int main(int argc, char *argv[])
 	struct timex tx;
 	struct ptp_clock_time *pct;
 	struct ptp_sys_offset *sysoff;
+	struct ptp_sys_offset_extended *soe;
 
 	char *progname;
 	unsigned int i;
@@ -176,6 +178,7 @@ int main(int argc, char *argv[])
 	int index = 0;
 	int list_pins = 0;
 	int pct_offset = 0;
+	int getextended = 0;
 	int n_samples = 0;
 	int pin_index = -1, pin_func;
 	int pps = -1;
@@ -190,7 +193,7 @@ int main(int argc, char *argv[])
 
 	progname = strrchr(argv[0], '/');
 	progname = progname ? 1+progname : argv[0];
-	while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:o:p:P:sSt:T:w:z"))) {
+	while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:z"))) {
 		switch (c) {
 		case 'c':
 			capabilities = 1;
@@ -255,6 +258,15 @@ int main(int argc, char *argv[])
 		case 'w':
 			pulsewidth = atoi(optarg);
 			break;
+		case 'x':
+			getextended = atoi(optarg);
+			if (getextended < 1 || getextended > PTP_MAX_SAMPLES) {
+				fprintf(stderr,
+					"number of extended timestamp samples must be between 1 and %d; was asked for %d\n",
+					PTP_MAX_SAMPLES, getextended);
+				return -1;
+			}
+			break;
 		case 'z':
 			flagtest = 1;
 			break;
@@ -535,6 +547,34 @@ int main(int argc, char *argv[])
 		free(sysoff);
 	}
 
+	if (getextended) {
+		soe = calloc(1, sizeof(*soe));
+		if (!soe) {
+			perror("calloc");
+			return -1;
+		}
+
+		soe->n_samples = getextended;
+
+		if (ioctl(fd, PTP_SYS_OFFSET_EXTENDED, soe)) {
+			perror("PTP_SYS_OFFSET_EXTENDED");
+		} else {
+			printf("extended timestamp request returned %d samples\n",
+			       getextended);
+
+			for (i = 0; i < getextended; i++) {
+				printf("sample #%2d: system time before: %lld.%09u\n",
+				       i, soe->ts[i][0].sec, soe->ts[i][0].nsec);
+				printf("            phc time: %lld.%09u\n",
+				       soe->ts[i][1].sec, soe->ts[i][1].nsec);
+				printf("            system time after: %lld.%09u\n",
+				       soe->ts[i][2].sec, soe->ts[i][2].nsec);
+			}
+		}
+
+		free(soe);
+	}
+
 	close(fd);
 	return 0;
 }
-- 
GitLab


From 3cf119ad5dc2b5c11385106d6d0ba86fbb47324c Mon Sep 17 00:00:00 2001
From: Alex Maftei <alex.maftei@amd.com>
Date: Tue, 25 Jul 2023 22:53:34 +0100
Subject: [PATCH 0608/1806] selftests/ptp: Add -X option for testing
 PTP_SYS_OFFSET_PRECISE

The -X option was chosen because X looks like a cross, and the underlying
callback is 'get cross timestamp'.

Signed-off-by: Alex Maftei <alex.maftei@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/ptp/testptp.c | 31 ++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c
index 71ceb6444af40..c9f6cca4feb45 100644
--- a/tools/testing/selftests/ptp/testptp.c
+++ b/tools/testing/selftests/ptp/testptp.c
@@ -144,6 +144,7 @@ static void usage(char *progname)
 		" -t val     shift the ptp clock time by 'val' seconds\n"
 		" -T val     set the ptp clock time to 'val' seconds\n"
 		" -x val     get an extended ptp clock time with the desired number of samples (up to %d)\n"
+		" -X         get a ptp clock cross timestamp\n"
 		" -z         test combinations of rising/falling external time stamp flags\n",
 		progname, PTP_MAX_SAMPLES);
 }
@@ -160,6 +161,7 @@ int main(int argc, char *argv[])
 	struct ptp_clock_time *pct;
 	struct ptp_sys_offset *sysoff;
 	struct ptp_sys_offset_extended *soe;
+	struct ptp_sys_offset_precise *xts;
 
 	char *progname;
 	unsigned int i;
@@ -179,6 +181,7 @@ int main(int argc, char *argv[])
 	int list_pins = 0;
 	int pct_offset = 0;
 	int getextended = 0;
+	int getcross = 0;
 	int n_samples = 0;
 	int pin_index = -1, pin_func;
 	int pps = -1;
@@ -193,7 +196,7 @@ int main(int argc, char *argv[])
 
 	progname = strrchr(argv[0], '/');
 	progname = progname ? 1+progname : argv[0];
-	while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:z"))) {
+	while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:Xz"))) {
 		switch (c) {
 		case 'c':
 			capabilities = 1;
@@ -267,6 +270,9 @@ int main(int argc, char *argv[])
 				return -1;
 			}
 			break;
+		case 'X':
+			getcross = 1;
+			break;
 		case 'z':
 			flagtest = 1;
 			break;
@@ -575,6 +581,29 @@ int main(int argc, char *argv[])
 		free(soe);
 	}
 
+	if (getcross) {
+		xts = calloc(1, sizeof(*xts));
+		if (!xts) {
+			perror("calloc");
+			return -1;
+		}
+
+		if (ioctl(fd, PTP_SYS_OFFSET_PRECISE, xts)) {
+			perror("PTP_SYS_OFFSET_PRECISE");
+		} else {
+			puts("system and phc crosstimestamping request okay");
+
+			printf("device time: %lld.%09u\n",
+			       xts->device.sec, xts->device.nsec);
+			printf("system time: %lld.%09u\n",
+			       xts->sys_realtime.sec, xts->sys_realtime.nsec);
+			printf("monoraw time: %lld.%09u\n",
+			       xts->sys_monoraw.sec, xts->sys_monoraw.nsec);
+		}
+
+		free(xts);
+	}
+
 	close(fd);
 	return 0;
 }
-- 
GitLab


From 7f6c40391a048c5d0f593f285bee45f7f98a3ca4 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 26 Jul 2023 10:39:05 +0800
Subject: [PATCH 0609/1806] IPv6: add extack info for IPv6 address add/delete

Add extack info for IPv6 address add/delete, which would be useful for
users to understand the problem without having to read kernel code.

Suggested-by: Beniamino Galvani <bgalvani@redhat.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h |  2 +-
 net/ipv6/addrconf.c     | 77 +++++++++++++++++++++++++++++------------
 net/ipv6/anycast.c      |  2 +-
 net/ipv6/route.c        |  5 +--
 4 files changed, 59 insertions(+), 27 deletions(-)

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 3556595ce59a8..b32539bb0fb05 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -156,7 +156,7 @@ void fib6_force_start_gc(struct net *net);
 
 struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev,
 				     const struct in6_addr *addr, bool anycast,
-				     gfp_t gfp_flags);
+				     gfp_t gfp_flags, struct netlink_ext_ack *extack);
 
 struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
 			       int flags);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 94d1fdb0393f9..5daf6a4986f8d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1063,20 +1063,28 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
 	struct fib6_info *f6i = NULL;
 	int err = 0;
 
-	if (addr_type == IPV6_ADDR_ANY ||
-	    (addr_type & IPV6_ADDR_MULTICAST &&
-	     !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) ||
-	    (!(idev->dev->flags & IFF_LOOPBACK) &&
-	     !netif_is_l3_master(idev->dev) &&
-	     addr_type & IPV6_ADDR_LOOPBACK))
+	if (addr_type == IPV6_ADDR_ANY) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid address");
 		return ERR_PTR(-EADDRNOTAVAIL);
+	} else if (addr_type & IPV6_ADDR_MULTICAST &&
+		   !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot assign multicast address without \"IFA_F_MCAUTOJOIN\" flag");
+		return ERR_PTR(-EADDRNOTAVAIL);
+	} else if (!(idev->dev->flags & IFF_LOOPBACK) &&
+		   !netif_is_l3_master(idev->dev) &&
+		   addr_type & IPV6_ADDR_LOOPBACK) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot assign loopback address on this device");
+		return ERR_PTR(-EADDRNOTAVAIL);
+	}
 
 	if (idev->dead) {
-		err = -ENODEV;			/*XXX*/
+		NL_SET_ERR_MSG_MOD(extack, "device is going away");
+		err = -ENODEV;
 		goto out;
 	}
 
 	if (idev->cnf.disable_ipv6) {
+		NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device");
 		err = -EACCES;
 		goto out;
 	}
@@ -1103,7 +1111,7 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
 		goto out;
 	}
 
-	f6i = addrconf_f6i_alloc(net, idev, cfg->pfx, false, gfp_flags);
+	f6i = addrconf_f6i_alloc(net, idev, cfg->pfx, false, gfp_flags, extack);
 	if (IS_ERR(f6i)) {
 		err = PTR_ERR(f6i);
 		f6i = NULL;
@@ -2927,30 +2935,40 @@ static int inet6_addr_add(struct net *net, int ifindex,
 
 	ASSERT_RTNL();
 
-	if (cfg->plen > 128)
+	if (cfg->plen > 128) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid prefix length");
 		return -EINVAL;
+	}
 
 	/* check the lifetime */
-	if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft)
+	if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft) {
+		NL_SET_ERR_MSG_MOD(extack, "address lifetime invalid");
 		return -EINVAL;
+	}
 
-	if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64)
+	if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64) {
+		NL_SET_ERR_MSG_MOD(extack, "address with \"mngtmpaddr\" flag must have a prefix length of 64");
 		return -EINVAL;
+	}
 
 	dev = __dev_get_by_index(net, ifindex);
 	if (!dev)
 		return -ENODEV;
 
 	idev = addrconf_add_dev(dev);
-	if (IS_ERR(idev))
+	if (IS_ERR(idev)) {
+		NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device");
 		return PTR_ERR(idev);
+	}
 
 	if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) {
 		int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk,
 					 true, cfg->pfx, ifindex);
 
-		if (ret < 0)
+		if (ret < 0) {
+			NL_SET_ERR_MSG_MOD(extack, "Multicast auto join failed");
 			return ret;
+		}
 	}
 
 	cfg->scope = ipv6_addr_scope(cfg->pfx);
@@ -3007,22 +3025,29 @@ static int inet6_addr_add(struct net *net, int ifindex,
 }
 
 static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
-			  const struct in6_addr *pfx, unsigned int plen)
+			  const struct in6_addr *pfx, unsigned int plen,
+			  struct netlink_ext_ack *extack)
 {
 	struct inet6_ifaddr *ifp;
 	struct inet6_dev *idev;
 	struct net_device *dev;
 
-	if (plen > 128)
+	if (plen > 128) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid prefix length");
 		return -EINVAL;
+	}
 
 	dev = __dev_get_by_index(net, ifindex);
-	if (!dev)
+	if (!dev) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface");
 		return -ENODEV;
+	}
 
 	idev = __in6_dev_get(dev);
-	if (!idev)
+	if (!idev) {
+		NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device");
 		return -ENXIO;
+	}
 
 	read_lock_bh(&idev->lock);
 	list_for_each_entry(ifp, &idev->addr_list, if_list) {
@@ -3045,6 +3070,8 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
 		}
 	}
 	read_unlock_bh(&idev->lock);
+
+	NL_SET_ERR_MSG_MOD(extack, "address not found");
 	return -EADDRNOTAVAIL;
 }
 
@@ -3087,7 +3114,7 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg)
 
 	rtnl_lock();
 	err = inet6_addr_del(net, ireq.ifr6_ifindex, 0, &ireq.ifr6_addr,
-			     ireq.ifr6_prefixlen);
+			     ireq.ifr6_prefixlen, NULL);
 	rtnl_unlock();
 	return err;
 }
@@ -3490,7 +3517,7 @@ static int fixup_permanent_addr(struct net *net,
 		struct fib6_info *f6i, *prev;
 
 		f6i = addrconf_f6i_alloc(net, idev, &ifp->addr, false,
-					 GFP_ATOMIC);
+					 GFP_ATOMIC, NULL);
 		if (IS_ERR(f6i))
 			return PTR_ERR(f6i);
 
@@ -4700,7 +4727,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	ifa_flags &= IFA_F_MANAGETEMPADDR;
 
 	return inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx,
-			      ifm->ifa_prefixlen);
+			      ifm->ifa_prefixlen, extack);
 }
 
 static int modify_prefix_route(struct inet6_ifaddr *ifp,
@@ -4905,8 +4932,10 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	dev =  __dev_get_by_index(net, ifm->ifa_index);
-	if (!dev)
+	if (!dev) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface");
 		return -ENODEV;
+	}
 
 	if (tb[IFA_FLAGS])
 		cfg.ifa_flags = nla_get_u32(tb[IFA_FLAGS]);
@@ -4941,10 +4970,12 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	if (nlh->nlmsg_flags & NLM_F_EXCL ||
-	    !(nlh->nlmsg_flags & NLM_F_REPLACE))
+	    !(nlh->nlmsg_flags & NLM_F_REPLACE)) {
+		NL_SET_ERR_MSG_MOD(extack, "address already assigned");
 		err = -EEXIST;
-	else
+	} else {
 		err = inet6_addr_modify(net, ifa, &cfg);
+	}
 
 	in6_ifa_put(ifa);
 
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index dacdea7fcb628..bb17f484ee2cd 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -305,7 +305,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
 	}
 
 	net = dev_net(idev->dev);
-	f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC);
+	f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC, NULL);
 	if (IS_ERR(f6i)) {
 		err = PTR_ERR(f6i);
 		goto out;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 64e873f5895f1..c90700aed3a19 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4543,7 +4543,8 @@ static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff
 struct fib6_info *addrconf_f6i_alloc(struct net *net,
 				     struct inet6_dev *idev,
 				     const struct in6_addr *addr,
-				     bool anycast, gfp_t gfp_flags)
+				     bool anycast, gfp_t gfp_flags,
+				     struct netlink_ext_ack *extack)
 {
 	struct fib6_config cfg = {
 		.fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL,
@@ -4565,7 +4566,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 		cfg.fc_flags |= RTF_LOCAL;
 	}
 
-	f6i = ip6_route_info_create(&cfg, gfp_flags, NULL);
+	f6i = ip6_route_info_create(&cfg, gfp_flags, extack);
 	if (!IS_ERR(f6i)) {
 		f6i->dst_nocount = true;
 
-- 
GitLab


From 09fedc731874123e0f6e5e5e3572db0c60378c2a Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 22:57:40 -0700
Subject: [PATCH 0610/1806] bpf: Fix compilation warning with -Wparentheses
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The kernel test robot reported compilation warnings when -Wparentheses is
added to KBUILD_CFLAGS with gcc compiler. The following is the error message:

  .../bpf-next/kernel/bpf/verifier.c: In function ‘coerce_reg_to_size_sx’:
  .../bpf-next/kernel/bpf/verifier.c:5901:14:
    error: suggest parentheses around comparison in operand of ‘==’ [-Werror=parentheses]
    if (s64_max >= 0 == s64_min >= 0) {
        ~~~~~~~~^~~~
  .../bpf-next/kernel/bpf/verifier.c: In function ‘coerce_subreg_to_size_sx’:
  .../bpf-next/kernel/bpf/verifier.c:5965:14:
    error: suggest parentheses around comparison in operand of ‘==’ [-Werror=parentheses]
    if (s32_min >= 0 == s32_max >= 0) {
        ~~~~~~~~^~~~

To fix the issue, add proper parentheses for the above '>=' condition
to silence the warning/error.

I tried a few clang compilers like clang16 and clang18 and they do not emit
such warnings with -Wparentheses.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202307281133.wi0c4SqG-lkp@intel.com/
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230728055740.2284534-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/core.c     | 4 ++--
 kernel/bpf/verifier.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index db0b631908c24..baccdec22f199 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1877,7 +1877,7 @@ select_insn:
 		case 1:
 			AX = abs((s32)DST);
 			do_div(AX, abs((s32)SRC));
-			if ((s32)DST < 0 == (s32)SRC < 0)
+			if (((s32)DST < 0) == ((s32)SRC < 0))
 				DST = (u32)AX;
 			else
 				DST = (u32)-AX;
@@ -1904,7 +1904,7 @@ select_insn:
 		case 1:
 			AX = abs((s32)DST);
 			do_div(AX, abs((s32)IMM));
-			if ((s32)DST < 0 == (s32)IMM < 0)
+			if (((s32)DST < 0) == ((s32)IMM < 0))
 				DST = (u32)AX;
 			else
 				DST = (u32)-AX;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0b1ada93582b4..e7b1af016841f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5898,7 +5898,7 @@ static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size)
 	s64_min = min(init_s64_max, init_s64_min);
 
 	/* both of s64_max/s64_min positive or negative */
-	if (s64_max >= 0 == s64_min >= 0) {
+	if ((s64_max >= 0) == (s64_min >= 0)) {
 		reg->smin_value = reg->s32_min_value = s64_min;
 		reg->smax_value = reg->s32_max_value = s64_max;
 		reg->umin_value = reg->u32_min_value = s64_min;
@@ -5962,7 +5962,7 @@ static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
 	s32_max = max(init_s32_max, init_s32_min);
 	s32_min = min(init_s32_max, init_s32_min);
 
-	if (s32_min >= 0 == s32_max >= 0) {
+	if ((s32_min >= 0) == (s32_max >= 0)) {
 		reg->s32_min_value = s32_min;
 		reg->s32_max_value = s32_max;
 		reg->u32_min_value = (u32)s32_min;
-- 
GitLab


From a76584fc9ff6b32f9839036eb15f4ca4d2586173 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 27 Jul 2023 22:57:45 -0700
Subject: [PATCH 0611/1806] selftests/bpf: Enable test test_progs-cpuv4 for gcc
 build kernel

Currently, test_progs-cpuv4 is generated with clang build kernel
when bpf cpu=v4 is supported by the clang compiler.
Let us enable test_progs-cpuv4 for gcc build kernel as well.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728055745.2285202-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/Makefile | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 6a45719a8d472..73a6ca80fa16d 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -36,11 +36,12 @@ LDLIBS += -lelf -lz -lrt -lpthread
 ifneq ($(LLVM),)
 # Silence some warnings when compiled with clang
 CFLAGS += -Wno-unused-command-line-argument
-# Check whether cpu=v4 is supported or not by clang
+endif
+
+# Check whether bpf cpu=v4 is supported or not by clang
 ifneq ($(shell $(CLANG) --target=bpf -mcpu=help 2>&1 | grep 'v4'),)
 CLANG_CPUV4 := 1
 endif
-endif
 
 # Order correspond to 'make run_tests' order
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-- 
GitLab


From e5c157f081abf6ecfda72661d1c2700ded9a90a3 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Thu, 27 Jul 2023 09:29:58 -0700
Subject: [PATCH 0612/1806] ynl: expose xdp-zc-max-segs

Also rename it to dashes, to match the rest. And fix unrelated
spelling error while we're at it.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230727163001.3952878-2-sdf@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index e41015310a6e3..1c7284fd535bd 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -14,7 +14,7 @@ definitions:
       -
         name: basic
         doc:
-          XDP feautues set supported by all drivers
+          XDP features set supported by all drivers
           (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
       -
         name: redirect
@@ -63,7 +63,7 @@ attribute-sets:
         enum: xdp-act
         enum-as-flags: true
       -
-        name: xdp_zc_max_segs
+        name: xdp-zc-max-segs
         doc: max fragment count supported by ZC driver
         type: u32
         checks:
@@ -83,6 +83,7 @@ operations:
           attributes:
             - ifindex
             - xdp-features
+            - xdp-zc-max-segs
       dump:
         reply: *dev-all
     -
-- 
GitLab


From 37844828d290d2cb3906e2acc7846ad37b04db63 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Thu, 27 Jul 2023 09:29:59 -0700
Subject: [PATCH 0613/1806] ynl: mark max/mask as private for kdoc

Simon mentioned in another thread that it makes kdoc happy
and Jakub confirms that commit e27cb89a22ad ("scripts: kernel-doc: support
private / public marking for enums") actually added the needed
support.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230727163001.3952878-3-sdf@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 71c5e79e877f0..650be9b8b6937 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -2125,6 +2125,7 @@ def render_uapi(family, cw):
 
             if const.get('render-max', False):
                 cw.nl()
+                cw.p('/* private: */')
                 if const['type'] == 'flags':
                     max_name = c_upper(name_pfx + 'mask')
                     max_val = f' = {enum.get_mask()},'
-- 
GitLab


From 25b5a2a1905fd8631c73596f98793f7494f29f2a Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Thu, 27 Jul 2023 09:30:00 -0700
Subject: [PATCH 0614/1806] ynl: regenerate all headers

Also add support to pass topdir to ynl-regen.sh (Jakub) and call
it from the makefile to update the UAPI headers.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Co-developed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230727163001.3952878-4-sdf@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/netdev.h           | 3 ++-
 tools/include/uapi/linux/netdev.h     | 3 ++-
 tools/net/ynl/Makefile                | 1 +
 tools/net/ynl/generated/netdev-user.c | 6 ++++++
 tools/net/ynl/generated/netdev-user.h | 2 ++
 tools/net/ynl/ynl-regen.sh            | 5 +++++
 6 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index bf71698a1e82a..c1634b95c223a 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -11,7 +11,7 @@
 
 /**
  * enum netdev_xdp_act
- * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers
+ * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers
  *   (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
  * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
  * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
@@ -34,6 +34,7 @@ enum netdev_xdp_act {
 	NETDEV_XDP_ACT_RX_SG = 32,
 	NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
 
+	/* private: */
 	NETDEV_XDP_ACT_MASK = 127,
 };
 
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index bf71698a1e82a..c1634b95c223a 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -11,7 +11,7 @@
 
 /**
  * enum netdev_xdp_act
- * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers
+ * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers
  *   (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
  * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
  * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
@@ -34,6 +34,7 @@ enum netdev_xdp_act {
 	NETDEV_XDP_ACT_RX_SG = 32,
 	NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
 
+	/* private: */
 	NETDEV_XDP_ACT_MASK = 127,
 };
 
diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile
index d664b36deb5b5..8156f03e23acf 100644
--- a/tools/net/ynl/Makefile
+++ b/tools/net/ynl/Makefile
@@ -3,6 +3,7 @@
 SUBDIRS = lib generated samples
 
 all: $(SUBDIRS)
+	./ynl-regen.sh -f -p $(PWD)/../../../
 
 $(SUBDIRS):
 	@if [ -f "$@/Makefile" ] ; then \
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index 4eb8aefef0cd2..68b408ca0f7f1 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -50,6 +50,7 @@ struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = {
 	[NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
 	[NETDEV_A_DEV_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, },
 	[NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, },
+	[NETDEV_A_DEV_XDP_ZC_MAX_SEGS] = { .name = "xdp-zc-max-segs", .type = YNL_PT_U32, },
 };
 
 struct ynl_policy_nest netdev_dev_nest = {
@@ -91,6 +92,11 @@ int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 				return MNL_CB_ERROR;
 			dst->_present.xdp_features = 1;
 			dst->xdp_features = mnl_attr_get_u64(attr);
+		} else if (type == NETDEV_A_DEV_XDP_ZC_MAX_SEGS) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.xdp_zc_max_segs = 1;
+			dst->xdp_zc_max_segs = mnl_attr_get_u32(attr);
 		}
 	}
 
diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h
index 5554dc69bb9c8..0952d3261f4d5 100644
--- a/tools/net/ynl/generated/netdev-user.h
+++ b/tools/net/ynl/generated/netdev-user.h
@@ -47,10 +47,12 @@ struct netdev_dev_get_rsp {
 	struct {
 		__u32 ifindex:1;
 		__u32 xdp_features:1;
+		__u32 xdp_zc_max_segs:1;
 	} _present;
 
 	__u32 ifindex;
 	__u64 xdp_features;
+	__u32 xdp_zc_max_segs;
 };
 
 void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp);
diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh
index 8d4ca6a505826..bdba24066cf10 100755
--- a/tools/net/ynl/ynl-regen.sh
+++ b/tools/net/ynl/ynl-regen.sh
@@ -4,15 +4,18 @@
 TOOL=$(dirname $(realpath $0))/ynl-gen-c.py
 
 force=
+search=
 
 while [ ! -z "$1" ]; do
   case "$1" in
     -f ) force=yes; shift ;;
+    -p ) search=$2; shift 2 ;;
     * )  echo "Unrecognized option '$1'"; exit 1 ;;
   esac
 done
 
 KDIR=$(dirname $(dirname $(dirname $(dirname $(realpath $0)))))
+pushd ${search:-$KDIR} >>/dev/null
 
 files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\|user\)')
 for f in $files; do
@@ -30,3 +33,5 @@ for f in $files; do
     $TOOL --mode ${params[2]} --${params[3]} --spec $KDIR/${params[0]} \
 	  $args -o $f
 done
+
+popd >>/dev/null
-- 
GitLab


From 26fdb67e8b4ae08eaab40a63c2e3a5e48f9c31f5 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Thu, 27 Jul 2023 09:30:01 -0700
Subject: [PATCH 0615/1806] ynl: print xdp-zc-max-segs in the sample

Technically we don't have to keep extending the sample, but it
feels useful to run these tools locally to confirm everything
is working.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230727163001.3952878-5-sdf@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/samples/netdev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/net/ynl/samples/netdev.c b/tools/net/ynl/samples/netdev.c
index d31268aa47c5d..06433400ddddb 100644
--- a/tools/net/ynl/samples/netdev.c
+++ b/tools/net/ynl/samples/netdev.c
@@ -38,6 +38,8 @@ static void netdev_print_device(struct netdev_dev_get_rsp *d, unsigned int op)
 			printf(" %s", netdev_xdp_act_str(1 << i));
 	}
 
+	printf(" xdp-zc-max-segs=%u", d->xdp_zc_max_segs);
+
 	name = netdev_op_str(op);
 	if (name)
 		printf(" (ntf: %s)", name);
-- 
GitLab


From d1a02358d48d659c2400fa3bbaf9cde2cf9f5040 Mon Sep 17 00:00:00 2001
From: YiFei Zhu <zhuyifei@google.com>
Date: Fri, 28 Jul 2023 04:33:59 +0000
Subject: [PATCH 0616/1806] bpf: Non-atomically allocate freelist during
 prefill

In internal testing of test_maps, we sometimes observed failures like:
  test_maps: test_maps.c:173: void test_hashmap_percpu(unsigned int, void *):
    Assertion `bpf_map_update_elem(fd, &key, value, BPF_ANY) == 0' failed.
where the errno is ENOMEM. After some troubleshooting and enabling
the warnings, we saw:
  [   91.304708] percpu: allocation failed, size=8 align=8 atomic=1, atomic alloc failed, no space left
  [   91.304716] CPU: 51 PID: 24145 Comm: test_maps Kdump: loaded Tainted: G                 N 6.1.38-smp-DEV #7
  [   91.304719] Hardware name: Google Astoria/astoria, BIOS 0.20230627.0-0 06/27/2023
  [   91.304721] Call Trace:
  [   91.304724]  <TASK>
  [   91.304730]  [<ffffffffa7ef83b9>] dump_stack_lvl+0x59/0x88
  [   91.304737]  [<ffffffffa7ef83f8>] dump_stack+0x10/0x18
  [   91.304738]  [<ffffffffa75caa0c>] pcpu_alloc+0x6fc/0x870
  [   91.304741]  [<ffffffffa75ca302>] __alloc_percpu_gfp+0x12/0x20
  [   91.304743]  [<ffffffffa756785e>] alloc_bulk+0xde/0x1e0
  [   91.304746]  [<ffffffffa7566c02>] bpf_mem_alloc_init+0xd2/0x2f0
  [   91.304747]  [<ffffffffa7547c69>] htab_map_alloc+0x479/0x650
  [   91.304750]  [<ffffffffa751d6e0>] map_create+0x140/0x2e0
  [   91.304752]  [<ffffffffa751d413>] __sys_bpf+0x5a3/0x6c0
  [   91.304753]  [<ffffffffa751c3ec>] __x64_sys_bpf+0x1c/0x30
  [   91.304754]  [<ffffffffa7ef847a>] do_syscall_64+0x5a/0x80
  [   91.304756]  [<ffffffffa800009b>] entry_SYSCALL_64_after_hwframe+0x63/0xcd

This makes sense, because in atomic context, percpu allocation would
not create new chunks; it would only create in non-atomic contexts.
And if during prefill all precpu chunks are full, -ENOMEM would
happen immediately upon next unit_alloc.

Prefill phase does not actually run in atomic context, so we can
use this fact to allocate non-atomically with GFP_KERNEL instead
of GFP_NOWAIT. This avoids the immediate -ENOMEM.

GFP_NOWAIT has to be used in unit_alloc when bpf program runs
in atomic context. Even if bpf program runs in non-atomic context,
in most cases, rcu read lock is enabled for the program so
GFP_NOWAIT is still needed. This is often also the case for
BPF_MAP_UPDATE_ELEM syscalls.

Signed-off-by: YiFei Zhu <zhuyifei@google.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20230728043359.3324347-1-zhuyifei@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/memalloc.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 14d9b1a9a4cac..9c49ae53deaf8 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -201,12 +201,16 @@ static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
 }
 
 /* Mostly runs from irq_work except __init phase. */
-static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
+static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic)
 {
 	struct mem_cgroup *memcg = NULL, *old_memcg;
+	gfp_t gfp;
 	void *obj;
 	int i;
 
+	gfp = __GFP_NOWARN | __GFP_ACCOUNT;
+	gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL;
+
 	for (i = 0; i < cnt; i++) {
 		/*
 		 * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is
@@ -238,7 +242,7 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 		 * will allocate from the current numa node which is what we
 		 * want here.
 		 */
-		obj = __alloc(c, node, GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT);
+		obj = __alloc(c, node, gfp);
 		if (!obj)
 			break;
 		add_obj_to_free_list(c, obj);
@@ -429,7 +433,7 @@ static void bpf_mem_refill(struct irq_work *work)
 		/* irq_work runs on this cpu and kmalloc will allocate
 		 * from the current numa node which is what we want here.
 		 */
-		alloc_bulk(c, c->batch, NUMA_NO_NODE);
+		alloc_bulk(c, c->batch, NUMA_NO_NODE, true);
 	else if (cnt > c->high_watermark)
 		free_bulk(c);
 
@@ -477,7 +481,7 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 	 * prog won't be doing more than 4 map_update_elem from
 	 * irq disabled region
 	 */
-	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu));
+	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
 }
 
 /* When size != 0 bpf_mem_cache for each cpu.
-- 
GitLab


From 759ab1edb56c88906830fd6b2e7b12514dd32758 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 26 Jul 2023 11:55:29 -0700
Subject: [PATCH 0617/1806] net: store netdevs in an xarray

Iterating over the netdev hash table for netlink dumps is hard.
Dumps are done in "chunks" so we need to save the position
after each chunk, so we know where to restart from. Because
netdevs are stored in a hash table we remember which bucket
we were in and how many devices we dumped.

Since we don't hold any locks across the "chunks" - devices may
come and go while we're dumping. If that happens we may miss
a device (if device is deleted from the bucket we were in).
We indicate to user space that this may have happened by setting
NLM_F_DUMP_INTR. User space is supposed to dump again (I think)
if it sees that. Somehow I doubt most user space gets this right..

To illustrate let's look at an example:

               System state:
  start:       # [A, B, C]
  del:  B      # [A, C]

with the hash table we may dump [A, B], missing C completely even
tho it existed both before and after the "del B".

Add an xarray and use it to allocate ifindexes. This way we
can iterate ifindexes in order, without the worry that we'll
skip one. We may still generate a dump of a state which "never
existed", for example for a set of values and sequence of ops:

               System state:
  start:       # [A, B]
  add:  C      # [A, C, B]
  del:  B      # [A, C]

we may generate a dump of [A], if C got an index between A and B.
System has never been in such state. But I'm 90% sure that's perfectly
fine, important part is that we can't _miss_ devices which exist before
and after. User space which wants to mirror kernel's state subscribes
to notifications and does periodic dumps so it will know that C exists
from the notification about its creation or from the next dump
(next dump is _guaranteed_ to include C, if it doesn't get removed).

To avoid any perf regressions keep the hash table for now. Most
net namespaces have very few devices and microbenchmarking 1M lookups
on Skylake I get the following results (not counting loopback
to number of devs):

 #devs | hash |  xa  | delta
    2  | 18.3 | 20.1 | + 9.8%
   16  | 18.3 | 20.1 | + 9.5%
   64  | 18.3 | 26.3 | +43.8%
  128  | 20.4 | 26.3 | +28.6%
  256  | 20.0 | 26.4 | +32.1%
 1024  | 26.6 | 26.7 | + 0.2%
 8192  |541.3 | 33.5 | -93.8%

No surprises since the hash table has 256 entries.
The microbenchmark scans indexes in order, if the pattern is more
random xa starts to win at 512 devices already. But that's a lot
of devices, in practice.

Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230726185530.2247698-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/net_namespace.h |  4 +-
 net/core/dev.c              | 82 ++++++++++++++++++++++++-------------
 2 files changed, 57 insertions(+), 29 deletions(-)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 78beaa765c733..9f6add96de2d7 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -42,6 +42,7 @@
 #include <linux/idr.h>
 #include <linux/skbuff.h>
 #include <linux/notifier.h>
+#include <linux/xarray.h>
 
 struct user_namespace;
 struct proc_dir_entry;
@@ -69,7 +70,7 @@ struct net {
 	atomic_t		dev_unreg_count;
 
 	unsigned int		dev_base_seq;	/* protected by rtnl_mutex */
-	int			ifindex;
+	u32			ifindex;
 
 	spinlock_t		nsid_lock;
 	atomic_t		fnhe_genid;
@@ -110,6 +111,7 @@ struct net {
 
 	struct hlist_head 	*dev_name_head;
 	struct hlist_head	*dev_index_head;
+	struct xarray		dev_by_index;
 	struct raw_notifier_head	netdev_chain;
 
 	/* Note that @hash_mix can be read millions times per second,
diff --git a/net/core/dev.c b/net/core/dev.c
index e7ffcfa037f79..b58674774a57b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -388,6 +388,8 @@ static void list_netdevice(struct net_device *dev)
 	hlist_add_head_rcu(&dev->index_hlist,
 			   dev_index_hash(net, dev->ifindex));
 	write_unlock(&dev_base_lock);
+	/* We reserved the ifindex, this can't fail */
+	WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL));
 
 	dev_base_seq_inc(net);
 }
@@ -397,8 +399,12 @@ static void list_netdevice(struct net_device *dev)
  */
 static void unlist_netdevice(struct net_device *dev, bool lock)
 {
+	struct net *net = dev_net(dev);
+
 	ASSERT_RTNL();
 
+	xa_erase(&net->dev_by_index, dev->ifindex);
+
 	/* Unlink dev from the device chain */
 	if (lock)
 		write_lock(&dev_base_lock);
@@ -9565,23 +9571,35 @@ err_out:
 }
 
 /**
- *	dev_new_index	-	allocate an ifindex
- *	@net: the applicable net namespace
+ * dev_index_reserve() - allocate an ifindex in a namespace
+ * @net: the applicable net namespace
+ * @ifindex: requested ifindex, pass %0 to get one allocated
+ *
+ * Allocate a ifindex for a new device. Caller must either use the ifindex
+ * to store the device (via list_netdevice()) or call dev_index_release()
+ * to give the index up.
  *
- *	Returns a suitable unique value for a new device interface
- *	number.  The caller must hold the rtnl semaphore or the
- *	dev_base_lock to be sure it remains unique.
+ * Return: a suitable unique value for a new device interface number or -errno.
  */
-static int dev_new_index(struct net *net)
+static int dev_index_reserve(struct net *net, u32 ifindex)
 {
-	int ifindex = net->ifindex;
+	int err;
 
-	for (;;) {
-		if (++ifindex <= 0)
-			ifindex = 1;
-		if (!__dev_get_by_index(net, ifindex))
-			return net->ifindex = ifindex;
-	}
+	if (!ifindex)
+		err = xa_alloc_cyclic(&net->dev_by_index, &ifindex, NULL,
+				      xa_limit_31b, &net->ifindex, GFP_KERNEL);
+	else
+		err = xa_insert(&net->dev_by_index, ifindex, NULL, GFP_KERNEL);
+	if (err < 0)
+		return err;
+
+	return ifindex;
+}
+
+static void dev_index_release(struct net *net, int ifindex)
+{
+	/* Expect only unused indexes, unlist_netdevice() removes the used */
+	WARN_ON(xa_erase(&net->dev_by_index, ifindex));
 }
 
 /* Delayed registration/unregisteration */
@@ -10051,11 +10069,10 @@ int register_netdevice(struct net_device *dev)
 		goto err_uninit;
 	}
 
-	ret = -EBUSY;
-	if (!dev->ifindex)
-		dev->ifindex = dev_new_index(net);
-	else if (__dev_get_by_index(net, dev->ifindex))
+	ret = dev_index_reserve(net, dev->ifindex);
+	if (ret < 0)
 		goto err_uninit;
+	dev->ifindex = ret;
 
 	/* Transfer changeable features to wanted_features and enable
 	 * software offloads (GSO and GRO).
@@ -10102,7 +10119,7 @@ int register_netdevice(struct net_device *dev)
 	ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
 	ret = notifier_to_errno(ret);
 	if (ret)
-		goto err_uninit;
+		goto err_ifindex_release;
 
 	ret = netdev_register_kobject(dev);
 	write_lock(&dev_base_lock);
@@ -10158,6 +10175,8 @@ out:
 
 err_uninit_notify:
 	call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev);
+err_ifindex_release:
+	dev_index_release(net, dev->ifindex);
 err_uninit:
 	if (dev->netdev_ops->ndo_uninit)
 		dev->netdev_ops->ndo_uninit(dev);
@@ -11035,9 +11054,19 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	}
 
 	/* Check that new_ifindex isn't used yet. */
-	err = -EBUSY;
-	if (new_ifindex && __dev_get_by_index(net, new_ifindex))
-		goto out;
+	if (new_ifindex) {
+		err = dev_index_reserve(net, new_ifindex);
+		if (err < 0)
+			goto out;
+	} else {
+		/* If there is an ifindex conflict assign a new one */
+		err = dev_index_reserve(net, dev->ifindex);
+		if (err == -EBUSY)
+			err = dev_index_reserve(net, 0);
+		if (err < 0)
+			goto out;
+		new_ifindex = err;
+	}
 
 	/*
 	 * And now a mini version of register_netdevice unregister_netdevice.
@@ -11065,13 +11094,6 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	rcu_barrier();
 
 	new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL);
-	/* If there is an ifindex conflict assign a new one */
-	if (!new_ifindex) {
-		if (__dev_get_by_index(net, dev->ifindex))
-			new_ifindex = dev_new_index(net);
-		else
-			new_ifindex = dev->ifindex;
-	}
 
 	rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid,
 			    new_ifindex);
@@ -11249,6 +11271,9 @@ static int __net_init netdev_init(struct net *net)
 	if (net->dev_index_head == NULL)
 		goto err_idx;
 
+	net->ifindex = 1;
+	xa_init_flags(&net->dev_by_index, XA_FLAGS_ALLOC);
+
 	RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain);
 
 	return 0;
@@ -11346,6 +11371,7 @@ static void __net_exit netdev_exit(struct net *net)
 {
 	kfree(net->dev_name_head);
 	kfree(net->dev_index_head);
+	xa_destroy(&net->dev_by_index);
 	if (net != &init_net)
 		WARN_ON_ONCE(!list_empty(&net->dev_base_head));
 }
-- 
GitLab


From 84e00d9bd4e472bd9b145ed40dbd132dd7a15462 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 26 Jul 2023 11:55:30 -0700
Subject: [PATCH 0618/1806] net: convert some netlink netdev iterators to
 depend on the xarray

Reap the benefits of easier iteration thanks to the xarray.
Convert just the genetlink ones, those are easier to test.

Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230726185530.2247698-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  3 ++
 net/core/netdev-genl.c    | 37 +++++---------------
 net/ethtool/netlink.c     | 65 ++++++++++-------------------------
 net/ethtool/tunnels.c     | 71 ++++++++++++++-------------------------
 4 files changed, 54 insertions(+), 122 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 32a4cdf37dd47..84c36a7f873fd 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3016,6 +3016,9 @@ extern rwlock_t				dev_base_lock;		/* Device list lock */
 			if (netdev_master_upper_dev_get_rcu(slave) == (bond))
 #define net_device_entry(lh)	list_entry(lh, struct net_device, dev_list)
 
+#define for_each_netdev_dump(net, d, ifindex)				\
+	xa_for_each_start(&(net)->dev_by_index, (ifindex), (d), (ifindex))
+
 static inline struct net_device *next_net_device(struct net_device *dev)
 {
 	struct list_head *lh;
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 65ef4867fc495..797c813c7c77b 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -101,43 +101,22 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
 	struct net_device *netdev;
-	int idx = 0, s_idx;
-	int h, s_h;
-	int err;
-
-	s_h = cb->args[0];
-	s_idx = cb->args[1];
+	int err = 0;
 
 	rtnl_lock();
-
-	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
-		struct hlist_head *head;
-
-		idx = 0;
-		head = &net->dev_index_head[h];
-		hlist_for_each_entry(netdev, head, index_hlist) {
-			if (idx < s_idx)
-				goto cont;
-			err = netdev_nl_dev_fill(netdev, skb,
-						 NETLINK_CB(cb->skb).portid,
-						 cb->nlh->nlmsg_seq, 0,
-						 NETDEV_CMD_DEV_GET);
-			if (err < 0)
-				break;
-cont:
-			idx++;
-		}
+	for_each_netdev_dump(net, netdev, cb->args[0]) {
+		err = netdev_nl_dev_fill(netdev, skb,
+					 NETLINK_CB(cb->skb).portid,
+					 cb->nlh->nlmsg_seq, 0,
+					 NETDEV_CMD_DEV_GET);
+		if (err < 0)
+			break;
 	}
-
 	rtnl_unlock();
 
 	if (err != -EMSGSIZE)
 		return err;
 
-	cb->args[1] = idx;
-	cb->args[0] = h;
-	cb->seq = net->dev_base_seq;
-
 	return skb->len;
 }
 
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 39a459b0111b4..ae344f1b0bbd1 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -252,8 +252,7 @@ int ethnl_multicast(struct sk_buff *skb, struct net_device *dev)
  * @ops:        request ops of currently processed message type
  * @req_info:   parsed request header of processed request
  * @reply_data: data needed to compose the reply
- * @pos_hash:   saved iteration position - hashbucket
- * @pos_idx:    saved iteration position - index
+ * @pos_ifindex: saved iteration position - ifindex
  *
  * These parameters are kept in struct netlink_callback as context preserved
  * between iterations. They are initialized by ethnl_default_start() and used
@@ -263,8 +262,7 @@ struct ethnl_dump_ctx {
 	const struct ethnl_request_ops	*ops;
 	struct ethnl_req_info		*req_info;
 	struct ethnl_reply_data		*reply_data;
-	int				pos_hash;
-	int				pos_idx;
+	unsigned long			pos_ifindex;
 };
 
 static const struct ethnl_request_ops *
@@ -490,55 +488,27 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 {
 	struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb);
 	struct net *net = sock_net(skb->sk);
-	int s_idx = ctx->pos_idx;
-	int h, idx = 0;
+	struct net_device *dev;
 	int ret = 0;
 
 	rtnl_lock();
-	for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
-		struct hlist_head *head;
-		struct net_device *dev;
-		unsigned int seq;
-
-		head = &net->dev_index_head[h];
-
-restart_chain:
-		seq = net->dev_base_seq;
-		cb->seq = seq;
-		idx = 0;
-		hlist_for_each_entry(dev, head, index_hlist) {
-			if (idx < s_idx)
-				goto cont;
-			dev_hold(dev);
-			rtnl_unlock();
-
-			ret = ethnl_default_dump_one(skb, dev, ctx, cb);
-			dev_put(dev);
-			if (ret < 0) {
-				if (ret == -EOPNOTSUPP)
-					goto lock_and_cont;
-				if (likely(skb->len))
-					ret = skb->len;
-				goto out;
-			}
-lock_and_cont:
-			rtnl_lock();
-			if (net->dev_base_seq != seq) {
-				s_idx = idx + 1;
-				goto restart_chain;
-			}
-cont:
-			idx++;
-		}
+	for_each_netdev_dump(net, dev, ctx->pos_ifindex) {
+		dev_hold(dev);
+		rtnl_unlock();
+
+		ret = ethnl_default_dump_one(skb, dev, ctx, cb);
+
+		rtnl_lock();
+		dev_put(dev);
 
+		if (ret < 0 && ret != -EOPNOTSUPP) {
+			if (likely(skb->len))
+				ret = skb->len;
+			break;
+		}
 	}
 	rtnl_unlock();
 
-out:
-	ctx->pos_hash = h;
-	ctx->pos_idx = idx;
-	nl_dump_check_consistent(cb, nlmsg_hdr(skb));
-
 	return ret;
 }
 
@@ -584,8 +554,7 @@ static int ethnl_default_start(struct netlink_callback *cb)
 	ctx->ops = ops;
 	ctx->req_info = req_info;
 	ctx->reply_data = reply_data;
-	ctx->pos_hash = 0;
-	ctx->pos_idx = 0;
+	ctx->pos_ifindex = 0;
 
 	return 0;
 
diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c
index 67fb414ca859b..05f752557b5e0 100644
--- a/net/ethtool/tunnels.c
+++ b/net/ethtool/tunnels.c
@@ -212,8 +212,7 @@ err_unlock_rtnl:
 
 struct ethnl_tunnel_info_dump_ctx {
 	struct ethnl_req_info	req_info;
-	int			pos_hash;
-	int			pos_idx;
+	unsigned long		ifindex;
 };
 
 int ethnl_tunnel_info_start(struct netlink_callback *cb)
@@ -243,57 +242,39 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx;
 	struct net *net = sock_net(skb->sk);
-	int s_idx = ctx->pos_idx;
-	int h, idx = 0;
+	struct net_device *dev;
 	int ret = 0;
 	void *ehdr;
 
 	rtnl_lock();
-	cb->seq = net->dev_base_seq;
-	for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
-		struct hlist_head *head;
-		struct net_device *dev;
-
-		head = &net->dev_index_head[h];
-		idx = 0;
-		hlist_for_each_entry(dev, head, index_hlist) {
-			if (idx < s_idx)
-				goto cont;
-
-			ehdr = ethnl_dump_put(skb, cb,
-					      ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY);
-			if (!ehdr) {
-				ret = -EMSGSIZE;
-				goto out;
-			}
-
-			ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_TUNNEL_INFO_HEADER);
-			if (ret < 0) {
-				genlmsg_cancel(skb, ehdr);
-				goto out;
-			}
-
-			ctx->req_info.dev = dev;
-			ret = ethnl_tunnel_info_fill_reply(&ctx->req_info, skb);
-			ctx->req_info.dev = NULL;
-			if (ret < 0) {
-				genlmsg_cancel(skb, ehdr);
-				if (ret == -EOPNOTSUPP)
-					goto cont;
-				goto out;
-			}
-			genlmsg_end(skb, ehdr);
-cont:
-			idx++;
+	for_each_netdev_dump(net, dev, ctx->ifindex) {
+		ehdr = ethnl_dump_put(skb, cb,
+				      ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY);
+		if (!ehdr) {
+			ret = -EMSGSIZE;
+			break;
 		}
+
+		ret = ethnl_fill_reply_header(skb, dev,
+					      ETHTOOL_A_TUNNEL_INFO_HEADER);
+		if (ret < 0) {
+			genlmsg_cancel(skb, ehdr);
+			break;
+		}
+
+		ctx->req_info.dev = dev;
+		ret = ethnl_tunnel_info_fill_reply(&ctx->req_info, skb);
+		ctx->req_info.dev = NULL;
+		if (ret < 0) {
+			genlmsg_cancel(skb, ehdr);
+			if (ret == -EOPNOTSUPP)
+				continue;
+			break;
+		}
+		genlmsg_end(skb, ehdr);
 	}
-out:
 	rtnl_unlock();
 
-	ctx->pos_hash = h;
-	ctx->pos_idx = idx;
-	nl_dump_check_consistent(cb, nlmsg_hdr(skb));
-
 	if (ret == -EMSGSIZE && skb->len)
 		return skb->len;
 	return ret;
-- 
GitLab


From 5027d54a9c30bc7ec808360378e2b4753f053f25 Mon Sep 17 00:00:00 2001
From: Patrick Rohr <prohr@google.com>
Date: Wed, 26 Jul 2023 16:07:01 -0700
Subject: [PATCH 0619/1806] net: change accept_ra_min_rtr_lft to affect all RA
 lifetimes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

accept_ra_min_rtr_lft only considered the lifetime of the default route
and discarded entire RAs accordingly.

This change renames accept_ra_min_rtr_lft to accept_ra_min_lft, and
applies the value to individual RA sections; in particular, router
lifetime, PIO preferred lifetime, and RIO lifetime. If any of those
lifetimes are lower than the configured value, the specific RA section
is ignored.

In order for the sysctl to be useful to Android, it should really apply
to all lifetimes in the RA, since that is what determines the minimum
frequency at which RAs must be processed by the kernel. Android uses
hardware offloads to drop RAs for a fraction of the minimum of all
lifetimes present in the RA (some networks have very frequent RAs (5s)
with high lifetimes (2h)). Despite this, we have encountered networks
that set the router lifetime to 30s which results in very frequent CPU
wakeups. Instead of disabling IPv6 (and dropping IPv6 ethertype in the
WiFi firmware) entirely on such networks, it seems better to ignore the
misconfigured routers while still processing RAs from other IPv6 routers
on the same network (i.e. to support IoT applications).

The previous implementation dropped the entire RA based on router
lifetime. This turned out to be hard to expand to the other lifetimes
present in the RA in a consistent manner; dropping the entire RA based
on RIO/PIO lifetimes would essentially require parsing the whole thing
twice.

Fixes: 1671bcfd76fd ("net: add sysctl accept_ra_min_rtr_lft")
Cc: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Patrick Rohr <prohr@google.com>
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230726230701.919212-1-prohr@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/ip-sysctl.rst |  8 ++++----
 include/linux/ipv6.h                   |  2 +-
 include/uapi/linux/ipv6.h              |  2 +-
 net/ipv6/addrconf.c                    | 13 ++++++++-----
 net/ipv6/ndisc.c                       | 27 +++++++++++---------------
 5 files changed, 25 insertions(+), 27 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 37603ad6126b3..a66054d0763a6 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -2288,11 +2288,11 @@ accept_ra_min_hop_limit - INTEGER
 
 	Default: 1
 
-accept_ra_min_rtr_lft - INTEGER
-	Minimum acceptable router lifetime in Router Advertisement.
+accept_ra_min_lft - INTEGER
+	Minimum acceptable lifetime value in Router Advertisement.
 
-	RAs with a router lifetime less than this value shall be
-	ignored. RAs with a router lifetime of 0 are unaffected.
+	RA sections with a lifetime less than this value shall be
+	ignored. Zero lifetimes stay unaffected.
 
 	Default: 0
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 0295b47c10a32..5883551b1ee87 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -33,7 +33,7 @@ struct ipv6_devconf {
 	__s32		accept_ra_defrtr;
 	__u32		ra_defrtr_metric;
 	__s32		accept_ra_min_hop_limit;
-	__s32		accept_ra_min_rtr_lft;
+	__s32		accept_ra_min_lft;
 	__s32		accept_ra_pinfo;
 	__s32		ignore_routes_with_linkdown;
 #ifdef CONFIG_IPV6_ROUTER_PREF
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 8b6bcbf6ed4a8..cf592d7b630fe 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -198,7 +198,7 @@ enum {
 	DEVCONF_IOAM6_ID_WIDE,
 	DEVCONF_NDISC_EVICT_NOCARRIER,
 	DEVCONF_ACCEPT_UNTRACKED_NA,
-	DEVCONF_ACCEPT_RA_MIN_RTR_LFT,
+	DEVCONF_ACCEPT_RA_MIN_LFT,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 5daf6a4986f8d..5184bd0ceb126 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -202,7 +202,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.ra_defrtr_metric	= IP6_RT_PRIO_USER,
 	.accept_ra_from_local	= 0,
 	.accept_ra_min_hop_limit= 1,
-	.accept_ra_min_rtr_lft	= 0,
+	.accept_ra_min_lft	= 0,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -263,7 +263,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.ra_defrtr_metric	= IP6_RT_PRIO_USER,
 	.accept_ra_from_local	= 0,
 	.accept_ra_min_hop_limit= 1,
-	.accept_ra_min_rtr_lft	= 0,
+	.accept_ra_min_lft	= 0,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -2741,6 +2741,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 		return;
 	}
 
+	if (valid_lft != 0 && valid_lft < in6_dev->cnf.accept_ra_min_lft)
+		return;
+
 	/*
 	 *	Two things going on here:
 	 *	1) Add routes for on-link prefixes
@@ -5635,7 +5638,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide;
 	array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier;
 	array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na;
-	array[DEVCONF_ACCEPT_RA_MIN_RTR_LFT] = cnf->accept_ra_min_rtr_lft;
+	array[DEVCONF_ACCEPT_RA_MIN_LFT] = cnf->accept_ra_min_lft;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -6830,8 +6833,8 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
-		.procname	= "accept_ra_min_rtr_lft",
-		.data		= &ipv6_devconf.accept_ra_min_rtr_lft,
+		.procname	= "accept_ra_min_lft",
+		.data		= &ipv6_devconf.accept_ra_min_lft,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 95750fbf6782e..c394799be38f8 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1276,8 +1276,6 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
 	if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts))
 		return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
 
-	lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
-
 	if (!ipv6_accept_ra(in6_dev)) {
 		ND_PRINTK(2, info,
 			  "RA: %s, did not accept ra for dev: %s\n",
@@ -1285,13 +1283,6 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
 		goto skip_linkparms;
 	}
 
-	if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) {
-		ND_PRINTK(2, info,
-			  "RA: router lifetime (%ds) is too short: %s\n",
-			  lifetime, skb->dev->name);
-		goto skip_linkparms;
-	}
-
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	/* skip link-specific parameters from interior routers */
 	if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) {
@@ -1332,6 +1323,14 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
 		goto skip_defrtr;
 	}
 
+	lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
+	if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_lft) {
+		ND_PRINTK(2, info,
+			  "RA: router lifetime (%ds) is too short: %s\n",
+			  lifetime, skb->dev->name);
+		goto skip_defrtr;
+	}
+
 	/* Do not accept RA with source-addr found on local machine unless
 	 * accept_ra_from_local is set to true.
 	 */
@@ -1495,13 +1494,6 @@ skip_linkparms:
 		goto out;
 	}
 
-	if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) {
-		ND_PRINTK(2, info,
-			  "RA: router lifetime (%ds) is too short: %s\n",
-			  lifetime, skb->dev->name);
-		goto out;
-	}
-
 #ifdef CONFIG_IPV6_ROUTE_INFO
 	if (!in6_dev->cnf.accept_ra_from_local &&
 	    ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr,
@@ -1526,6 +1518,9 @@ skip_linkparms:
 			if (ri->prefix_len == 0 &&
 			    !in6_dev->cnf.accept_ra_defrtr)
 				continue;
+			if (ri->lifetime != 0 &&
+			    ntohl(ri->lifetime) < in6_dev->cnf.accept_ra_min_lft)
+				continue;
 			if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen)
 				continue;
 			if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
-- 
GitLab


From 569f98b36b38387133862a0fce37896f05c042d6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 27 Jul 2023 17:59:19 +0200
Subject: [PATCH 0620/1806] mlxsw: spectrum: Drop unused functions
 mlxsw_sp_port_lower_dev_hold/_put()

As of commit 151b89f6025a ("mlxsw: spectrum_router: Reuse work neighbor
initialization in work scheduler"), the functions
mlxsw_sp_port_lower_dev_hold() and mlxsw_sp_port_dev_put() have no users.
Drop them.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/d0adcd7cb4ea19416294a0f861100edba84c9f36.1690471774.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 17 -----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h |  2 --
 2 files changed, 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f0f6af3ec7c57..9dbd5edff0b02 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4112,23 +4112,6 @@ struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev)
 	return (struct mlxsw_sp_port *)priv.data;
 }
 
-struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev)
-{
-	struct mlxsw_sp_port *mlxsw_sp_port;
-
-	rcu_read_lock();
-	mlxsw_sp_port = mlxsw_sp_port_dev_lower_find_rcu(dev);
-	if (mlxsw_sp_port)
-		dev_hold(mlxsw_sp_port->dev);
-	rcu_read_unlock();
-	return mlxsw_sp_port;
-}
-
-void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	dev_put(mlxsw_sp_port->dev);
-}
-
 int mlxsw_sp_parsing_depth_inc(struct mlxsw_sp *mlxsw_sp)
 {
 	char mprs_pl[MLXSW_REG_MPRS_LEN];
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 65eaa181e0aa6..62151f0531aee 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -720,8 +720,6 @@ int mlxsw_sp_txhdr_ptp_data_construct(struct mlxsw_core *mlxsw_core,
 bool mlxsw_sp_port_dev_check(const struct net_device *dev);
 struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev);
 struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev);
-struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev);
-void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port);
 struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev);
 int mlxsw_sp_parsing_depth_inc(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_parsing_depth_dec(struct mlxsw_sp *mlxsw_sp);
-- 
GitLab


From 16f8c846cd6f8c5c45392e0f3dde843983adb9ab Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 27 Jul 2023 17:59:20 +0200
Subject: [PATCH 0621/1806] mlxsw: spectrum_nve: Do not take reference when
 looking up netdevice

mlxsw_sp_nve_fid_disable() is always called under RTNL. It is therefore
safe to call __dev_get_by_index() to get the netdevice pointer without
bumping the reference count, because we can be sure the netdevice is not
going away. That then obviates the need to put the netdevice later in the
function.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/341d1046f89d8d839d9d00e4a3d58cdc351e9397.1690471774.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
index d2b57a045aa48..5479a1c19d2ee 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
@@ -989,6 +989,9 @@ void mlxsw_sp_nve_fid_disable(struct mlxsw_sp *mlxsw_sp,
 	int nve_ifindex;
 	__be32 vni;
 
+	/* Necessary for __dev_get_by_index() below. */
+	ASSERT_RTNL();
+
 	mlxsw_sp_nve_flood_ip_flush(mlxsw_sp, fid);
 	mlxsw_sp_nve_fdb_flush_by_fid(mlxsw_sp, fid_index);
 	mlxsw_sp_nve_ipv6_addr_flush_by_fid(mlxsw_sp, fid_index);
@@ -997,15 +1000,13 @@ void mlxsw_sp_nve_fid_disable(struct mlxsw_sp *mlxsw_sp,
 		    mlxsw_sp_fid_vni(fid, &vni)))
 		goto out;
 
-	nve_dev = dev_get_by_index(mlxsw_sp_net(mlxsw_sp), nve_ifindex);
+	nve_dev = __dev_get_by_index(mlxsw_sp_net(mlxsw_sp), nve_ifindex);
 	if (!nve_dev)
 		goto out;
 
 	mlxsw_sp_nve_fdb_clear_offload(mlxsw_sp, fid, nve_dev, vni);
 	mlxsw_sp_fid_fdb_clear_offload(fid, nve_dev);
 
-	dev_put(nve_dev);
-
 out:
 	mlxsw_sp_fid_vni_clear(fid);
 	mlxsw_sp_nve_tunnel_fini(mlxsw_sp);
-- 
GitLab


From 1ae489ab43e0a74d96d41a607c1d924f8ba47186 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 27 Jul 2023 17:59:21 +0200
Subject: [PATCH 0622/1806] mlxsw: spectrum_switchdev: Use tracker helpers to
 hold & put netdevices

Using the tracking helpers makes it easier to debug netdevice refcount
imbalances when CONFIG_NET_DEV_REFCNT_TRACKER is enabled.

Convert dev_hold() / dev_put() to netdev_hold() / netdev_put() in the
switchdev module.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/774c3d7b5b0231f1435df2ec9dd660192e382756.1690471774.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index dffb67c1038e2..5376d4af5f912 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -3380,6 +3380,7 @@ out:
 
 struct mlxsw_sp_switchdev_event_work {
 	struct work_struct work;
+	netdevice_tracker dev_tracker;
 	union {
 		struct switchdev_notifier_fdb_info fdb_info;
 		struct switchdev_notifier_vxlan_fdb_info vxlan_fdb_info;
@@ -3536,8 +3537,8 @@ static void mlxsw_sp_switchdev_bridge_fdb_event_work(struct work_struct *work)
 out:
 	rtnl_unlock();
 	kfree(switchdev_work->fdb_info.addr);
+	netdev_put(dev, &switchdev_work->dev_tracker);
 	kfree(switchdev_work);
-	dev_put(dev);
 }
 
 static void
@@ -3692,8 +3693,8 @@ static void mlxsw_sp_switchdev_vxlan_fdb_event_work(struct work_struct *work)
 
 out:
 	rtnl_unlock();
+	netdev_put(dev, &switchdev_work->dev_tracker);
 	kfree(switchdev_work);
-	dev_put(dev);
 }
 
 static int
@@ -3793,7 +3794,7 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused,
 		 * upper device containig mlxsw_sp_port or just a
 		 * mlxsw_sp_port
 		 */
-		dev_hold(dev);
+		netdev_hold(dev, &switchdev_work->dev_tracker, GFP_ATOMIC);
 		break;
 	case SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE:
 	case SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE:
@@ -3803,7 +3804,7 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused,
 							    info);
 		if (err)
 			goto err_vxlan_work_prepare;
-		dev_hold(dev);
+		netdev_hold(dev, &switchdev_work->dev_tracker, GFP_ATOMIC);
 		break;
 	default:
 		kfree(switchdev_work);
-- 
GitLab


From deeaa3716f4fa2dd1722de8e1b203217e7dd677f Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 27 Jul 2023 17:59:22 +0200
Subject: [PATCH 0623/1806] mlxsw: spectrum_router: FIB: Use tracker helpers to
 hold & put netdevices

Using the tracking helpers makes it easier to debug netdevice refcount
imbalances when CONFIG_NET_DEV_REFCNT_TRACKER is enabled.

Convert dev_hold() / dev_put() to netdev_hold() / netdev_put() in the
router code that deals with FIB events.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/5221a92e751c40447c55959f622267ccc999ed04.1690471774.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 57f0faac836c9..0744497f27628 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -7547,6 +7547,7 @@ struct mlxsw_sp_fib6_event_work {
 
 struct mlxsw_sp_fib_event_work {
 	struct work_struct work;
+	netdevice_tracker dev_tracker;
 	union {
 		struct mlxsw_sp_fib6_event_work fib6_work;
 		struct fib_entry_notifier_info fen_info;
@@ -7720,12 +7721,12 @@ static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work)
 						    &fib_work->ven_info);
 		if (err)
 			dev_warn(mlxsw_sp->bus_info->dev, "MR VIF add failed.\n");
-		dev_put(fib_work->ven_info.dev);
+		netdev_put(fib_work->ven_info.dev, &fib_work->dev_tracker);
 		break;
 	case FIB_EVENT_VIF_DEL:
 		mlxsw_sp_router_fibmr_vif_del(mlxsw_sp,
 					      &fib_work->ven_info);
-		dev_put(fib_work->ven_info.dev);
+		netdev_put(fib_work->ven_info.dev, &fib_work->dev_tracker);
 		break;
 	}
 	mutex_unlock(&mlxsw_sp->router->lock);
@@ -7796,7 +7797,8 @@ mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event_work *fib_work,
 	case FIB_EVENT_VIF_ADD:
 	case FIB_EVENT_VIF_DEL:
 		memcpy(&fib_work->ven_info, info, sizeof(fib_work->ven_info));
-		dev_hold(fib_work->ven_info.dev);
+		netdev_hold(fib_work->ven_info.dev, &fib_work->dev_tracker,
+			    GFP_ATOMIC);
 		break;
 	}
 }
-- 
GitLab


From b17b2d57b7c1193a1b86c07b3ff0beca7a607a95 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 27 Jul 2023 17:59:23 +0200
Subject: [PATCH 0624/1806] mlxsw: spectrum_router: hw_stats: Use tracker
 helpers to hold & put netdevices

Using the tracking helpers makes it easier to debug netdevice refcount
imbalances when CONFIG_NET_DEV_REFCNT_TRACKER is enabled.

Convert dev_hold() / dev_put() to netdev_hold() / netdev_put() in the
router code that deals with hw_stats events.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/b972314cfef4f4c24e66e60d13cffa5d606d1bf3.1690471774.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 0744497f27628..3ecd34ad0743d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8308,6 +8308,7 @@ mlxsw_sp_router_port_l3_stats_report_delta(struct mlxsw_sp_rif *rif,
 struct mlxsw_sp_router_hwstats_notify_work {
 	struct work_struct work;
 	struct net_device *dev;
+	netdevice_tracker dev_tracker;
 };
 
 static void mlxsw_sp_router_hwstats_notify_work(struct work_struct *work)
@@ -8319,7 +8320,7 @@ static void mlxsw_sp_router_hwstats_notify_work(struct work_struct *work)
 	rtnl_lock();
 	rtnl_offload_xstats_notify(hws_work->dev);
 	rtnl_unlock();
-	dev_put(hws_work->dev);
+	netdev_put(hws_work->dev, &hws_work->dev_tracker);
 	kfree(hws_work);
 }
 
@@ -8339,7 +8340,7 @@ mlxsw_sp_router_hwstats_notify_schedule(struct net_device *dev)
 		return;
 
 	INIT_WORK(&hws_work->work, mlxsw_sp_router_hwstats_notify_work);
-	dev_hold(dev);
+	netdev_hold(dev, &hws_work->dev_tracker, GFP_KERNEL);
 	hws_work->dev = dev;
 	mlxsw_core_schedule_work(&hws_work->work);
 }
-- 
GitLab


From d0e0e880122fb865884ef86372cd6221225c6459 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 27 Jul 2023 17:59:24 +0200
Subject: [PATCH 0625/1806] mlxsw: spectrum_router: RIF: Use tracker helpers to
 hold & put netdevices

Using the tracking helpers makes it easier to debug netdevice refcount
imbalances when CONFIG_NET_DEV_REFCNT_TRACKER is enabled.

Convert dev_hold() / dev_put() to netdev_hold() / netdev_put() in the
router code that deals with RIF allocation.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/8b7701a7b439ac268e4be4040eff99d01e27ae47.1690471775.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 3ecd34ad0743d..59d12cf459395 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -71,6 +71,7 @@ static const struct rhashtable_params mlxsw_sp_crif_ht_params = {
 
 struct mlxsw_sp_rif {
 	struct mlxsw_sp_crif *crif; /* NULL for underlay RIF */
+	netdevice_tracker dev_tracker;
 	struct list_head neigh_list;
 	struct mlxsw_sp_fid *fid;
 	unsigned char addr[ETH_ALEN];
@@ -8412,7 +8413,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 		err = -ENOMEM;
 		goto err_rif_alloc;
 	}
-	dev_hold(params->dev);
+	netdev_hold(params->dev, &rif->dev_tracker, GFP_KERNEL);
 	mlxsw_sp->router->rifs[rif_index] = rif;
 	rif->mlxsw_sp = mlxsw_sp;
 	rif->ops = ops;
@@ -8469,7 +8470,7 @@ err_configure:
 		mlxsw_sp_fid_put(fid);
 err_fid_get:
 	mlxsw_sp->router->rifs[rif_index] = NULL;
-	dev_put(params->dev);
+	netdev_put(params->dev, &rif->dev_tracker);
 	mlxsw_sp_rif_free(rif);
 err_rif_alloc:
 err_crif_lookup:
@@ -8511,7 +8512,7 @@ static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 		/* Loopback RIFs are not associated with a FID. */
 		mlxsw_sp_fid_put(fid);
 	mlxsw_sp->router->rifs[rif->rif_index] = NULL;
-	dev_put(dev);
+	netdev_put(dev, &rif->dev_tracker);
 	mlxsw_sp_rif_free(rif);
 	mlxsw_sp_rif_index_free(mlxsw_sp, rif_index, rif_entries);
 	vr->rif_count--;
-- 
GitLab


From cb2116204169b24fbb667c823e8fced069d5e561 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 27 Jul 2023 17:59:25 +0200
Subject: [PATCH 0626/1806] mlxsw: spectrum_router: IPv6 events: Use tracker
 helpers to hold & put netdevices

Using the tracking helpers makes it easier to debug netdevice refcount
imbalances when CONFIG_NET_DEV_REFCNT_TRACKER is enabled.

Convert dev_hold() / dev_put() to netdev_hold() / netdev_put() in the
router code that deals with IPv6 address events.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/f0af6ad4722b4ca6e598fd4fda8311a3041651ec.1690471775.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 59d12cf459395..debd2c466f11c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -9333,6 +9333,7 @@ struct mlxsw_sp_inet6addr_event_work {
 	struct work_struct work;
 	struct mlxsw_sp *mlxsw_sp;
 	struct net_device *dev;
+	netdevice_tracker dev_tracker;
 	unsigned long event;
 };
 
@@ -9356,7 +9357,7 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work)
 out:
 	mutex_unlock(&mlxsw_sp->router->lock);
 	rtnl_unlock();
-	dev_put(dev);
+	netdev_put(dev, &inet6addr_work->dev_tracker);
 	kfree(inet6addr_work);
 }
 
@@ -9382,7 +9383,7 @@ static int mlxsw_sp_inet6addr_event(struct notifier_block *nb,
 	inet6addr_work->mlxsw_sp = router->mlxsw_sp;
 	inet6addr_work->dev = dev;
 	inet6addr_work->event = event;
-	dev_hold(dev);
+	netdev_hold(dev, &inet6addr_work->dev_tracker, GFP_ATOMIC);
 	mlxsw_core_schedule_work(&inet6addr_work->work);
 
 	return NOTIFY_DONE;
-- 
GitLab


From 833c4a8105ac8c2df42ec061be09a5a682454f69 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 27 Jul 2023 12:07:25 -0700
Subject: [PATCH 0627/1806] eth: bnxt: fix one of the W=1 warnings about
 fortified memcpy()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix a W=1 warning with gcc 13.1:

In function ‘fortify_memcpy_chk’,
    inlined from ‘bnxt_hwrm_queue_cos2bw_cfg’ at drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c:133:3:
include/linux/fortify-string.h:592:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning]
  592 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The field group is already defined and starts at queue_id:

struct bnxt_cos2bw_cfg {
	u8			pad[3];
	struct_group_attr(cfg, __packed,
		u8		queue_id;
		__le32		min_bw;

Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20230727190726.1859515-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index caab3d626a2a9..31f85f3e23641 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -130,7 +130,7 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets,
 					    BW_VALUE_UNIT_PERCENT1_100);
 		}
 		data = &req->unused_0 + qidx * (sizeof(cos2bw) - 4);
-		memcpy(data, &cos2bw.queue_id, sizeof(cos2bw) - 4);
+		memcpy(data, &cos2bw.cfg, sizeof(cos2bw) - 4);
 		if (qidx == 0) {
 			req->queue_id0 = cos2bw.queue_id;
 			req->unused_0 = 0;
-- 
GitLab


From 9f49db62f58eceffd8345abe8ec110f1fb142ab6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 27 Jul 2023 12:07:26 -0700
Subject: [PATCH 0628/1806] eth: bnxt: fix warning for define in struct_group

Fix C=1 warning with sparse 0.6.4:

drivers/net/ethernet/broadcom/bnxt/bnxt.c: note: in included file:
drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h:30:1: warning: directive in macro's argument list

Don't put defines in a struct_group().

Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20230727190726.1859515-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
index 7167425221615..5b2a6f678244b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
@@ -27,11 +27,12 @@ struct bnxt_cos2bw_cfg {
 		u8		queue_id;
 		__le32		min_bw;
 		__le32		max_bw;
-#define BW_VALUE_UNIT_PERCENT1_100		(0x1UL << 29)
 		u8		tsa;
 		u8		pri_lvl;
 		u8		bw_weight;
 	);
+/* for min_bw / max_bw */
+#define BW_VALUE_UNIT_PERCENT1_100		(0x1UL << 29)
 	u8			unused;
 };
 
-- 
GitLab


From 222a6c42e9ef131fd20463bf95d7ce7b39bee2f8 Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Thu, 27 Jul 2023 22:01:01 +0530
Subject: [PATCH 0629/1806] octeontx2-af: Initialize 'cntr_val' to fix
 uninitialized symbol error

drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c:860
otx2_tc_update_mcam_table_del_req()
error: uninitialized symbol 'cntr_val'.

Fixes: ec87f05402f5 ("octeontx2-af: Install TC filter rules in hardware based on priority")
Signed-off-by: Suman Ghosh <sumang@marvell.com>
Link: https://lore.kernel.org/r/20230727163101.2793453-1-sumang@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 1e6fc23eca4fe..0915a0121316a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -841,7 +841,7 @@ static int otx2_tc_update_mcam_table_del_req(struct otx2_nic *nic,
 	struct list_head *pos, *n;
 	struct otx2_tc_flow *tmp;
 	int i = 0, index = 0;
-	u16 cntr_val;
+	u16 cntr_val = 0;
 
 	/* Find and delete the entry from the list and re-install
 	 * all the entries from beginning to the index of the
@@ -880,7 +880,7 @@ static int otx2_tc_update_mcam_table_add_req(struct otx2_nic *nic,
 	int mcam_idx = flow_cfg->max_flows - flow_cfg->nr_flows - 1;
 	struct otx2_tc_flow *tmp;
 	int list_idx, i;
-	u16 cntr_val;
+	u16 cntr_val = 0;
 
 	/* Find the index of the entry(list_idx) whose priority
 	 * is greater than the new entry and re-install all
-- 
GitLab


From 6a7eccef47b205ae66371a26d36dfb2529835075 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 27 Jul 2023 13:35:23 -0400
Subject: [PATCH 0630/1806] net/tls: Move TLS protocol elements to a separate
 header

Kernel TLS consumers will need definitions of various parts of the
TLS protocol, but often do not need the function declarations and
other infrastructure provided in <net/tls.h>.

Break out existing standardized protocol elements into a separate
header, and make room for a few more elements in subsequent patches.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://lore.kernel.org/r/169047931374.5241.7713175865185969309.stgit@oracle-102.nfsv4bat.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../chelsio/inline_crypto/chtls/chtls.h       |  1 +
 include/net/tls.h                             |  4 ---
 include/net/tls_prot.h                        | 26 +++++++++++++++++++
 net/sunrpc/svcsock.c                          |  1 +
 net/sunrpc/xprtsock.c                         |  1 +
 net/tls/tls.h                                 |  1 +
 6 files changed, 30 insertions(+), 4 deletions(-)
 create mode 100644 include/net/tls_prot.h

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
index 68562a82d0368..62f62bff74a5f 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
@@ -22,6 +22,7 @@
 #include <crypto/internal/hash.h>
 #include <linux/tls.h>
 #include <net/tls.h>
+#include <net/tls_prot.h>
 #include <net/tls_toe.h>
 
 #include "t4fw_api.h"
diff --git a/include/net/tls.h b/include/net/tls.h
index 5e71dd3df8ca0..06fca91603465 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -69,10 +69,6 @@ extern const struct tls_cipher_size_desc tls_cipher_size_desc[];
 
 #define TLS_CRYPTO_INFO_READY(info)	((info)->cipher_type)
 
-#define TLS_RECORD_TYPE_ALERT		0x15
-#define TLS_RECORD_TYPE_HANDSHAKE	0x16
-#define TLS_RECORD_TYPE_DATA		0x17
-
 #define TLS_AAD_SPACE_SIZE		13
 
 #define MAX_IV_SIZE			16
diff --git a/include/net/tls_prot.h b/include/net/tls_prot.h
new file mode 100644
index 0000000000000..47d6cfd1619ef
--- /dev/null
+++ b/include/net/tls_prot.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ *
+ * TLS Protocol definitions
+ *
+ * From https://www.iana.org/assignments/tls-parameters/tls-parameters.xhtml
+ */
+
+#ifndef _TLS_PROT_H
+#define _TLS_PROT_H
+
+/*
+ * TLS Record protocol: ContentType
+ */
+enum {
+	TLS_RECORD_TYPE_CHANGE_CIPHER_SPEC = 20,
+	TLS_RECORD_TYPE_ALERT = 21,
+	TLS_RECORD_TYPE_HANDSHAKE = 22,
+	TLS_RECORD_TYPE_DATA = 23,
+	TLS_RECORD_TYPE_HEARTBEAT = 24,
+	TLS_RECORD_TYPE_TLS12_CID = 25,
+	TLS_RECORD_TYPE_ACK = 26,
+};
+
+#endif /* _TLS_PROT_H */
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index e43f263824114..449df8cabfcb4 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -44,6 +44,7 @@
 #include <net/tcp.h>
 #include <net/tcp_states.h>
 #include <net/tls.h>
+#include <net/tls_prot.h>
 #include <net/handshake.h>
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9f010369100a2..9457ebf22fb17 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -48,6 +48,7 @@
 #include <net/udp.h>
 #include <net/tcp.h>
 #include <net/tls.h>
+#include <net/tls_prot.h>
 #include <net/handshake.h>
 
 #include <linux/bvec.h>
diff --git a/net/tls/tls.h b/net/tls/tls.h
index 86cef1c68e03b..26a0358f6f49e 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -39,6 +39,7 @@
 #include <linux/types.h>
 #include <linux/skmsg.h>
 #include <net/tls.h>
+#include <net/tls_prot.h>
 
 #define TLS_PAGE_ORDER	(min_t(unsigned int, PAGE_ALLOC_COSTLY_ORDER,	\
 			       TLS_MAX_PAYLOAD_SIZE >> PAGE_SHIFT))
-- 
GitLab


From 0257427146e84af365612508ace9d0d87dfb7d7a Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 27 Jul 2023 13:35:50 -0400
Subject: [PATCH 0631/1806] net/tls: Add TLS Alert definitions

I'm about to add support for kernel handshake API consumers to send
TLS Alerts, so introduce the needed protocol definitions in the new
header tls_prot.h.

This presages support for Closure alerts. Also, support for alerts
is a pre-requite for handling session re-keying, where one peer will
signal the need for a re-key by sending a TLS Alert.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://lore.kernel.org/r/169047934064.5241.8377890858495063518.stgit@oracle-102.nfsv4bat.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tls_prot.h | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/include/net/tls_prot.h b/include/net/tls_prot.h
index 47d6cfd1619ef..68a40756440b3 100644
--- a/include/net/tls_prot.h
+++ b/include/net/tls_prot.h
@@ -23,4 +23,46 @@ enum {
 	TLS_RECORD_TYPE_ACK = 26,
 };
 
+/*
+ * TLS Alert protocol: AlertLevel
+ */
+enum {
+	TLS_ALERT_LEVEL_WARNING = 1,
+	TLS_ALERT_LEVEL_FATAL = 2,
+};
+
+/*
+ * TLS Alert protocol: AlertDescription
+ */
+enum {
+	TLS_ALERT_DESC_CLOSE_NOTIFY = 0,
+	TLS_ALERT_DESC_UNEXPECTED_MESSAGE = 10,
+	TLS_ALERT_DESC_BAD_RECORD_MAC = 20,
+	TLS_ALERT_DESC_RECORD_OVERFLOW = 22,
+	TLS_ALERT_DESC_HANDSHAKE_FAILURE = 40,
+	TLS_ALERT_DESC_BAD_CERTIFICATE = 42,
+	TLS_ALERT_DESC_UNSUPPORTED_CERTIFICATE = 43,
+	TLS_ALERT_DESC_CERTIFICATE_REVOKED = 44,
+	TLS_ALERT_DESC_CERTIFICATE_EXPIRED = 45,
+	TLS_ALERT_DESC_CERTIFICATE_UNKNOWN = 46,
+	TLS_ALERT_DESC_ILLEGAL_PARAMETER = 47,
+	TLS_ALERT_DESC_UNKNOWN_CA = 48,
+	TLS_ALERT_DESC_ACCESS_DENIED = 49,
+	TLS_ALERT_DESC_DECODE_ERROR = 50,
+	TLS_ALERT_DESC_DECRYPT_ERROR = 51,
+	TLS_ALERT_DESC_TOO_MANY_CIDS_REQUESTED	= 52,
+	TLS_ALERT_DESC_PROTOCOL_VERSION = 70,
+	TLS_ALERT_DESC_INSUFFICIENT_SECURITY = 71,
+	TLS_ALERT_DESC_INTERNAL_ERROR = 80,
+	TLS_ALERT_DESC_INAPPROPRIATE_FALLBACK = 86,
+	TLS_ALERT_DESC_USER_CANCELED = 90,
+	TLS_ALERT_DESC_MISSING_EXTENSION = 109,
+	TLS_ALERT_DESC_UNSUPPORTED_EXTENSION = 110,
+	TLS_ALERT_DESC_UNRECOGNIZED_NAME = 112,
+	TLS_ALERT_DESC_BAD_CERTIFICATE_STATUS_RESPONSE = 113,
+	TLS_ALERT_DESC_UNKNOWN_PSK_IDENTITY = 115,
+	TLS_ALERT_DESC_CERTIFICATE_REQUIRED = 116,
+	TLS_ALERT_DESC_NO_APPLICATION_PROTOCOL = 120,
+};
+
 #endif /* _TLS_PROT_H */
-- 
GitLab


From 35b1b538d422fd765d88fbdaaa6e06ee466d9f93 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 27 Jul 2023 13:36:17 -0400
Subject: [PATCH 0632/1806] net/handshake: Add API for sending TLS Closure
 alerts

This helper sends an alert only if a TLS session was established.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://lore.kernel.org/r/169047936730.5241.618595693821012638.stgit@oracle-102.nfsv4bat.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/handshake.h   |  1 +
 net/handshake/Makefile    |  2 +-
 net/handshake/alert.c     | 61 +++++++++++++++++++++++++++++++++++++++
 net/handshake/handshake.h |  6 ++++
 net/handshake/tlshd.c     | 23 +++++++++++++++
 5 files changed, 92 insertions(+), 1 deletion(-)
 create mode 100644 net/handshake/alert.c

diff --git a/include/net/handshake.h b/include/net/handshake.h
index 2e26e436e85f5..bb88dfa6e3c93 100644
--- a/include/net/handshake.h
+++ b/include/net/handshake.h
@@ -40,5 +40,6 @@ int tls_server_hello_x509(const struct tls_handshake_args *args, gfp_t flags);
 int tls_server_hello_psk(const struct tls_handshake_args *args, gfp_t flags);
 
 bool tls_handshake_cancel(struct sock *sk);
+void tls_handshake_close(struct socket *sock);
 
 #endif /* _NET_HANDSHAKE_H */
diff --git a/net/handshake/Makefile b/net/handshake/Makefile
index 247d73c6ff6ea..ef4d9a2112bd6 100644
--- a/net/handshake/Makefile
+++ b/net/handshake/Makefile
@@ -8,6 +8,6 @@
 #
 
 obj-y += handshake.o
-handshake-y := genl.o netlink.o request.o tlshd.o trace.o
+handshake-y := alert.o genl.o netlink.o request.o tlshd.o trace.o
 
 obj-$(CONFIG_NET_HANDSHAKE_KUNIT_TEST) += handshake-test.o
diff --git a/net/handshake/alert.c b/net/handshake/alert.c
new file mode 100644
index 0000000000000..2f1a16868ff61
--- /dev/null
+++ b/net/handshake/alert.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Handle the TLS Alert protocol
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/inet.h>
+
+#include <net/sock.h>
+#include <net/handshake.h>
+#include <net/tls.h>
+#include <net/tls_prot.h>
+
+#include "handshake.h"
+
+/**
+ * tls_alert_send - send a TLS Alert on a kTLS socket
+ * @sock: open kTLS socket to send on
+ * @level: TLS Alert level
+ * @description: TLS Alert description
+ *
+ * Returns zero on success or a negative errno.
+ */
+int tls_alert_send(struct socket *sock, u8 level, u8 description)
+{
+	u8 record_type = TLS_RECORD_TYPE_ALERT;
+	u8 buf[CMSG_SPACE(sizeof(record_type))];
+	struct msghdr msg = { 0 };
+	struct cmsghdr *cmsg;
+	struct kvec iov;
+	u8 alert[2];
+	int ret;
+
+	alert[0] = level;
+	alert[1] = description;
+	iov.iov_base = alert;
+	iov.iov_len = sizeof(alert);
+
+	memset(buf, 0, sizeof(buf));
+	msg.msg_control = buf;
+	msg.msg_controllen = sizeof(buf);
+	msg.msg_flags = MSG_DONTWAIT;
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_TLS;
+	cmsg->cmsg_type = TLS_SET_RECORD_TYPE;
+	cmsg->cmsg_len = CMSG_LEN(sizeof(record_type));
+	memcpy(CMSG_DATA(cmsg), &record_type, sizeof(record_type));
+
+	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, iov.iov_len);
+	ret = sock_sendmsg(sock, &msg);
+	return ret < 0 ? ret : 0;
+}
diff --git a/net/handshake/handshake.h b/net/handshake/handshake.h
index 4dac965c99df0..a48163765a7a1 100644
--- a/net/handshake/handshake.h
+++ b/net/handshake/handshake.h
@@ -41,8 +41,11 @@ struct handshake_req {
 
 enum hr_flags_bits {
 	HANDSHAKE_F_REQ_COMPLETED,
+	HANDSHAKE_F_REQ_SESSION,
 };
 
+struct genl_info;
+
 /* Invariants for all handshake requests for one transport layer
  * security protocol
  */
@@ -63,6 +66,9 @@ enum hp_flags_bits {
 	HANDSHAKE_F_PROTO_NOTIFY,
 };
 
+/* alert.c */
+int tls_alert_send(struct socket *sock, u8 level, u8 description);
+
 /* netlink.c */
 int handshake_genl_notify(struct net *net, const struct handshake_proto *proto,
 			  gfp_t flags);
diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c
index b735f5cced2f5..bbfb4095ddd6b 100644
--- a/net/handshake/tlshd.c
+++ b/net/handshake/tlshd.c
@@ -18,6 +18,7 @@
 #include <net/sock.h>
 #include <net/handshake.h>
 #include <net/genetlink.h>
+#include <net/tls_prot.h>
 
 #include <uapi/linux/keyctl.h>
 #include <uapi/linux/handshake.h>
@@ -100,6 +101,9 @@ static void tls_handshake_done(struct handshake_req *req,
 	if (info)
 		tls_handshake_remote_peerids(treq, info);
 
+	if (!status)
+		set_bit(HANDSHAKE_F_REQ_SESSION, &req->hr_flags);
+
 	treq->th_consumer_done(treq->th_consumer_data, -status,
 			       treq->th_peerid[0]);
 }
@@ -424,3 +428,22 @@ bool tls_handshake_cancel(struct sock *sk)
 	return handshake_req_cancel(sk);
 }
 EXPORT_SYMBOL(tls_handshake_cancel);
+
+/**
+ * tls_handshake_close - send a Closure alert
+ * @sock: an open socket
+ *
+ */
+void tls_handshake_close(struct socket *sock)
+{
+	struct handshake_req *req;
+
+	req = handshake_req_hash_lookup(sock->sk);
+	if (!req)
+		return;
+	if (!test_and_clear_bit(HANDSHAKE_F_REQ_SESSION, &req->hr_flags))
+		return;
+	tls_alert_send(sock, TLS_ALERT_LEVEL_WARNING,
+		       TLS_ALERT_DESC_CLOSE_NOTIFY);
+}
+EXPORT_SYMBOL(tls_handshake_close);
-- 
GitLab


From 5dd5ad682cfe9550a37634a8f55780ebd74edbe8 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 27 Jul 2023 13:36:44 -0400
Subject: [PATCH 0633/1806] SUNRPC: Send TLS Closure alerts before closing a
 TCP socket

Before closing a TCP connection, the TLS protocol wants peers to
send session close Alert notifications. Add those in both the RPC
client and server.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://lore.kernel.org/r/169047939404.5241.14392506226409865832.stgit@oracle-102.nfsv4bat.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sunrpc/svcsock.c  | 2 ++
 net/sunrpc/xprtsock.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 449df8cabfcb4..cca6ee7160200 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1622,6 +1622,8 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt)
 {
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
 
+	tls_handshake_close(svsk->sk_sock);
+
 	svc_sock_detach(xprt);
 
 	if (!test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9457ebf22fb17..5096aa62de5cf 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1293,6 +1293,8 @@ static void xs_close(struct rpc_xprt *xprt)
 
 	dprintk("RPC:       xs_close xprt %p\n", xprt);
 
+	if (transport->sock)
+		tls_handshake_close(transport->sock);
 	xs_reset_transport(transport);
 	xprt->reestablish_timeout = 0;
 }
-- 
GitLab


From 39d0e38dcced8d4da92cd11f3ff618bacc42d8a9 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 27 Jul 2023 13:37:10 -0400
Subject: [PATCH 0634/1806] net/handshake: Add helpers for parsing incoming TLS
 Alerts

Kernel TLS consumers can replace common TLS Alert parsing code with
these helpers.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://lore.kernel.org/r/169047942074.5241.13791647439480672048.stgit@oracle-102.nfsv4bat.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/handshake.h |  4 ++++
 net/handshake/alert.c   | 42 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)

diff --git a/include/net/handshake.h b/include/net/handshake.h
index bb88dfa6e3c93..8ebd4f9ed26e6 100644
--- a/include/net/handshake.h
+++ b/include/net/handshake.h
@@ -42,4 +42,8 @@ int tls_server_hello_psk(const struct tls_handshake_args *args, gfp_t flags);
 bool tls_handshake_cancel(struct sock *sk);
 void tls_handshake_close(struct socket *sock);
 
+u8 tls_get_record_type(const struct sock *sk, const struct cmsghdr *msg);
+void tls_alert_recv(const struct sock *sk, const struct msghdr *msg,
+		    u8 *level, u8 *description);
+
 #endif /* _NET_HANDSHAKE_H */
diff --git a/net/handshake/alert.c b/net/handshake/alert.c
index 2f1a16868ff61..286bf94d93a31 100644
--- a/net/handshake/alert.c
+++ b/net/handshake/alert.c
@@ -59,3 +59,45 @@ int tls_alert_send(struct socket *sock, u8 level, u8 description)
 	ret = sock_sendmsg(sock, &msg);
 	return ret < 0 ? ret : 0;
 }
+
+/**
+ * tls_get_record_type - Look for TLS RECORD_TYPE information
+ * @sk: socket (for IP address information)
+ * @cmsg: incoming message to be parsed
+ *
+ * Returns zero or a TLS_RECORD_TYPE value.
+ */
+u8 tls_get_record_type(const struct sock *sk, const struct cmsghdr *cmsg)
+{
+	u8 record_type;
+
+	if (cmsg->cmsg_level != SOL_TLS)
+		return 0;
+	if (cmsg->cmsg_type != TLS_GET_RECORD_TYPE)
+		return 0;
+
+	record_type = *((u8 *)CMSG_DATA(cmsg));
+	return record_type;
+}
+EXPORT_SYMBOL(tls_get_record_type);
+
+/**
+ * tls_alert_recv - Parse TLS Alert messages
+ * @sk: socket (for IP address information)
+ * @msg: incoming message to be parsed
+ * @level: OUT - TLS AlertLevel value
+ * @description: OUT - TLS AlertDescription value
+ *
+ */
+void tls_alert_recv(const struct sock *sk, const struct msghdr *msg,
+		    u8 *level, u8 *description)
+{
+	const struct kvec *iov;
+	u8 *data;
+
+	iov = msg->msg_iter.kvec;
+	data = iov->iov_base;
+	*level = data[0];
+	*description = data[1];
+}
+EXPORT_SYMBOL(tls_alert_recv);
-- 
GitLab


From 39067dda1d865d7fac1f56c18479e67b0917bbe4 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 27 Jul 2023 13:37:37 -0400
Subject: [PATCH 0635/1806] SUNRPC: Use new helpers to handle TLS Alerts

Use the helpers to parse the level and description fields in
incoming alerts. "Warning" alerts are discarded, and "fatal"
alerts mean the session is no longer valid.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://lore.kernel.org/r/169047944747.5241.1974889594004407123.stgit@oracle-102.nfsv4bat.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sunrpc/svcsock.c  | 47 +++++++++++++++++++++++--------------------
 net/sunrpc/xprtsock.c | 42 +++++++++++++++++++++-----------------
 2 files changed, 48 insertions(+), 41 deletions(-)

diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index cca6ee7160200..2ed29e40c6a9b 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -43,7 +43,6 @@
 #include <net/udp.h>
 #include <net/tcp.h>
 #include <net/tcp_states.h>
-#include <net/tls.h>
 #include <net/tls_prot.h>
 #include <net/handshake.h>
 #include <linux/uaccess.h>
@@ -227,27 +226,30 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
 }
 
 static int
-svc_tcp_sock_process_cmsg(struct svc_sock *svsk, struct msghdr *msg,
+svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
 			  struct cmsghdr *cmsg, int ret)
 {
-	if (cmsg->cmsg_level == SOL_TLS &&
-	    cmsg->cmsg_type == TLS_GET_RECORD_TYPE) {
-		u8 content_type = *((u8 *)CMSG_DATA(cmsg));
-
-		switch (content_type) {
-		case TLS_RECORD_TYPE_DATA:
-			/* TLS sets EOR at the end of each application data
-			 * record, even though there might be more frames
-			 * waiting to be decrypted.
-			 */
-			msg->msg_flags &= ~MSG_EOR;
-			break;
-		case TLS_RECORD_TYPE_ALERT:
-			ret = -ENOTCONN;
-			break;
-		default:
-			ret = -EAGAIN;
-		}
+	u8 content_type = tls_get_record_type(sock->sk, cmsg);
+	u8 level, description;
+
+	switch (content_type) {
+	case 0:
+		break;
+	case TLS_RECORD_TYPE_DATA:
+		/* TLS sets EOR at the end of each application data
+		 * record, even though there might be more frames
+		 * waiting to be decrypted.
+		 */
+		msg->msg_flags &= ~MSG_EOR;
+		break;
+	case TLS_RECORD_TYPE_ALERT:
+		tls_alert_recv(sock->sk, msg, &level, &description);
+		ret = (level == TLS_ALERT_LEVEL_FATAL) ?
+			-ENOTCONN : -EAGAIN;
+		break;
+	default:
+		/* discard this record type */
+		ret = -EAGAIN;
 	}
 	return ret;
 }
@@ -259,13 +261,14 @@ svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg)
 		struct cmsghdr	cmsg;
 		u8		buf[CMSG_SPACE(sizeof(u8))];
 	} u;
+	struct socket *sock = svsk->sk_sock;
 	int ret;
 
 	msg->msg_control = &u;
 	msg->msg_controllen = sizeof(u);
-	ret = sock_recvmsg(svsk->sk_sock, msg, MSG_DONTWAIT);
+	ret = sock_recvmsg(sock, msg, MSG_DONTWAIT);
 	if (unlikely(msg->msg_controllen != sizeof(u)))
-		ret = svc_tcp_sock_process_cmsg(svsk, msg, &u.cmsg, ret);
+		ret = svc_tcp_sock_process_cmsg(sock, msg, &u.cmsg, ret);
 	return ret;
 }
 
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 5096aa62de5cf..268a2cc61acd1 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -47,7 +47,6 @@
 #include <net/checksum.h>
 #include <net/udp.h>
 #include <net/tcp.h>
-#include <net/tls.h>
 #include <net/tls_prot.h>
 #include <net/handshake.h>
 
@@ -361,24 +360,27 @@ static int
 xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
 		     struct cmsghdr *cmsg, int ret)
 {
-	if (cmsg->cmsg_level == SOL_TLS &&
-	    cmsg->cmsg_type == TLS_GET_RECORD_TYPE) {
-		u8 content_type = *((u8 *)CMSG_DATA(cmsg));
-
-		switch (content_type) {
-		case TLS_RECORD_TYPE_DATA:
-			/* TLS sets EOR at the end of each application data
-			 * record, even though there might be more frames
-			 * waiting to be decrypted.
-			 */
-			msg->msg_flags &= ~MSG_EOR;
-			break;
-		case TLS_RECORD_TYPE_ALERT:
-			ret = -ENOTCONN;
-			break;
-		default:
-			ret = -EAGAIN;
-		}
+	u8 content_type = tls_get_record_type(sock->sk, cmsg);
+	u8 level, description;
+
+	switch (content_type) {
+	case 0:
+		break;
+	case TLS_RECORD_TYPE_DATA:
+		/* TLS sets EOR at the end of each application data
+		 * record, even though there might be more frames
+		 * waiting to be decrypted.
+		 */
+		msg->msg_flags &= ~MSG_EOR;
+		break;
+	case TLS_RECORD_TYPE_ALERT:
+		tls_alert_recv(sock->sk, msg, &level, &description);
+		ret = (level == TLS_ALERT_LEVEL_FATAL) ?
+			-EACCES : -EAGAIN;
+		break;
+	default:
+		/* discard this record type */
+		ret = -EAGAIN;
 	}
 	return ret;
 }
@@ -778,6 +780,8 @@ static void xs_stream_data_receive(struct sock_xprt *transport)
 	}
 	if (ret == -ESHUTDOWN)
 		kernel_sock_shutdown(transport->sock, SHUT_RDWR);
+	else if (ret == -EACCES)
+		xprt_wake_pending_tasks(&transport->xprt, -EACCES);
 	else
 		xs_poll_check_readable(transport);
 out:
-- 
GitLab


From b470985c76df6d53a9454670fb7551e1197f55e2 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 27 Jul 2023 13:38:04 -0400
Subject: [PATCH 0636/1806] net/handshake: Trace events for TLS Alert helpers

Add observability for the new TLS Alert infrastructure.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://lore.kernel.org/r/169047947409.5241.14548832149596892717.stgit@oracle-102.nfsv4bat.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/trace/events/handshake.h | 160 +++++++++++++++++++++++++++++++
 net/handshake/alert.c            |   7 ++
 net/handshake/trace.c            |   2 +
 3 files changed, 169 insertions(+)

diff --git a/include/trace/events/handshake.h b/include/trace/events/handshake.h
index 8dadcab5f12af..bdd8a03cf5ba1 100644
--- a/include/trace/events/handshake.h
+++ b/include/trace/events/handshake.h
@@ -6,7 +6,86 @@
 #define _TRACE_HANDSHAKE_H
 
 #include <linux/net.h>
+#include <net/tls_prot.h>
 #include <linux/tracepoint.h>
+#include <trace/events/net_probe_common.h>
+
+#define TLS_RECORD_TYPE_LIST \
+	record_type(CHANGE_CIPHER_SPEC) \
+	record_type(ALERT) \
+	record_type(HANDSHAKE) \
+	record_type(DATA) \
+	record_type(HEARTBEAT) \
+	record_type(TLS12_CID) \
+	record_type_end(ACK)
+
+#undef record_type
+#undef record_type_end
+#define record_type(x)		TRACE_DEFINE_ENUM(TLS_RECORD_TYPE_##x);
+#define record_type_end(x)	TRACE_DEFINE_ENUM(TLS_RECORD_TYPE_##x);
+
+TLS_RECORD_TYPE_LIST
+
+#undef record_type
+#undef record_type_end
+#define record_type(x)		{ TLS_RECORD_TYPE_##x, #x },
+#define record_type_end(x)	{ TLS_RECORD_TYPE_##x, #x }
+
+#define show_tls_content_type(type) \
+	__print_symbolic(type, TLS_RECORD_TYPE_LIST)
+
+TRACE_DEFINE_ENUM(TLS_ALERT_LEVEL_WARNING);
+TRACE_DEFINE_ENUM(TLS_ALERT_LEVEL_FATAL);
+
+#define show_tls_alert_level(level) \
+	__print_symbolic(level, \
+		{ TLS_ALERT_LEVEL_WARNING,	"Warning" }, \
+		{ TLS_ALERT_LEVEL_FATAL,	"Fatal" })
+
+#define TLS_ALERT_DESCRIPTION_LIST \
+	alert_description(CLOSE_NOTIFY) \
+	alert_description(UNEXPECTED_MESSAGE) \
+	alert_description(BAD_RECORD_MAC) \
+	alert_description(RECORD_OVERFLOW) \
+	alert_description(HANDSHAKE_FAILURE) \
+	alert_description(BAD_CERTIFICATE) \
+	alert_description(UNSUPPORTED_CERTIFICATE) \
+	alert_description(CERTIFICATE_REVOKED) \
+	alert_description(CERTIFICATE_EXPIRED) \
+	alert_description(CERTIFICATE_UNKNOWN) \
+	alert_description(ILLEGAL_PARAMETER) \
+	alert_description(UNKNOWN_CA) \
+	alert_description(ACCESS_DENIED) \
+	alert_description(DECODE_ERROR) \
+	alert_description(DECRYPT_ERROR) \
+	alert_description(TOO_MANY_CIDS_REQUESTED) \
+	alert_description(PROTOCOL_VERSION) \
+	alert_description(INSUFFICIENT_SECURITY) \
+	alert_description(INTERNAL_ERROR) \
+	alert_description(INAPPROPRIATE_FALLBACK) \
+	alert_description(USER_CANCELED) \
+	alert_description(MISSING_EXTENSION) \
+	alert_description(UNSUPPORTED_EXTENSION) \
+	alert_description(UNRECOGNIZED_NAME) \
+	alert_description(BAD_CERTIFICATE_STATUS_RESPONSE) \
+	alert_description(UNKNOWN_PSK_IDENTITY) \
+	alert_description(CERTIFICATE_REQUIRED) \
+	alert_description_end(NO_APPLICATION_PROTOCOL)
+
+#undef alert_description
+#undef alert_description_end
+#define alert_description(x)		TRACE_DEFINE_ENUM(TLS_ALERT_DESC_##x);
+#define alert_description_end(x)	TRACE_DEFINE_ENUM(TLS_ALERT_DESC_##x);
+
+TLS_ALERT_DESCRIPTION_LIST
+
+#undef alert_description
+#undef alert_description_end
+#define alert_description(x)		{ TLS_ALERT_DESC_##x, #x },
+#define alert_description_end(x)	{ TLS_ALERT_DESC_##x, #x }
+
+#define show_tls_alert_description(desc) \
+	__print_symbolic(desc, TLS_ALERT_DESCRIPTION_LIST)
 
 DECLARE_EVENT_CLASS(handshake_event_class,
 	TP_PROTO(
@@ -106,6 +185,47 @@ DECLARE_EVENT_CLASS(handshake_error_class,
 		),						\
 		TP_ARGS(net, req, sk, err))
 
+DECLARE_EVENT_CLASS(handshake_alert_class,
+	TP_PROTO(
+		const struct sock *sk,
+		unsigned char level,
+		unsigned char description
+	),
+	TP_ARGS(sk, level, description),
+	TP_STRUCT__entry(
+		/* sockaddr_in6 is always bigger than sockaddr_in */
+		__array(__u8, saddr, sizeof(struct sockaddr_in6))
+		__array(__u8, daddr, sizeof(struct sockaddr_in6))
+		__field(unsigned int, netns_ino)
+		__field(unsigned long, level)
+		__field(unsigned long, description)
+	),
+	TP_fast_assign(
+		const struct inet_sock *inet = inet_sk(sk);
+
+		memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
+		memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
+		TP_STORE_ADDR_PORTS(__entry, inet, sk);
+
+		__entry->netns_ino = sock_net(sk)->ns.inum;
+		__entry->level = level;
+		__entry->description = description;
+	),
+	TP_printk("src=%pISpc dest=%pISpc %s: %s",
+		__entry->saddr, __entry->daddr,
+		show_tls_alert_level(__entry->level),
+		show_tls_alert_description(__entry->description)
+	)
+);
+#define DEFINE_HANDSHAKE_ALERT(name)				\
+	DEFINE_EVENT(handshake_alert_class, name,		\
+		TP_PROTO(					\
+			const struct sock *sk,			\
+			unsigned char level,			\
+			unsigned char description		\
+		),						\
+		TP_ARGS(sk, level, description))
+
 
 /*
  * Request lifetime events
@@ -154,6 +274,46 @@ DEFINE_HANDSHAKE_ERROR(handshake_cmd_accept_err);
 DEFINE_HANDSHAKE_FD_EVENT(handshake_cmd_done);
 DEFINE_HANDSHAKE_ERROR(handshake_cmd_done_err);
 
+/*
+ * TLS Record events
+ */
+
+TRACE_EVENT(tls_contenttype,
+	TP_PROTO(
+		const struct sock *sk,
+		unsigned char type
+	),
+	TP_ARGS(sk, type),
+	TP_STRUCT__entry(
+		/* sockaddr_in6 is always bigger than sockaddr_in */
+		__array(__u8, saddr, sizeof(struct sockaddr_in6))
+		__array(__u8, daddr, sizeof(struct sockaddr_in6))
+		__field(unsigned int, netns_ino)
+		__field(unsigned long, type)
+	),
+	TP_fast_assign(
+		const struct inet_sock *inet = inet_sk(sk);
+
+		memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
+		memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
+		TP_STORE_ADDR_PORTS(__entry, inet, sk);
+
+		__entry->netns_ino = sock_net(sk)->ns.inum;
+		__entry->type = type;
+	),
+	TP_printk("src=%pISpc dest=%pISpc %s",
+		__entry->saddr, __entry->daddr,
+		show_tls_content_type(__entry->type)
+	)
+);
+
+/*
+ * TLS Alert events
+ */
+
+DEFINE_HANDSHAKE_ALERT(tls_alert_send);
+DEFINE_HANDSHAKE_ALERT(tls_alert_recv);
+
 #endif /* _TRACE_HANDSHAKE_H */
 
 #include <trace/define_trace.h>
diff --git a/net/handshake/alert.c b/net/handshake/alert.c
index 286bf94d93a31..329d919846837 100644
--- a/net/handshake/alert.c
+++ b/net/handshake/alert.c
@@ -21,6 +21,8 @@
 
 #include "handshake.h"
 
+#include <trace/events/handshake.h>
+
 /**
  * tls_alert_send - send a TLS Alert on a kTLS socket
  * @sock: open kTLS socket to send on
@@ -39,6 +41,8 @@ int tls_alert_send(struct socket *sock, u8 level, u8 description)
 	u8 alert[2];
 	int ret;
 
+	trace_tls_alert_send(sock->sk, level, description);
+
 	alert[0] = level;
 	alert[1] = description;
 	iov.iov_base = alert;
@@ -77,6 +81,7 @@ u8 tls_get_record_type(const struct sock *sk, const struct cmsghdr *cmsg)
 		return 0;
 
 	record_type = *((u8 *)CMSG_DATA(cmsg));
+	trace_tls_contenttype(sk, record_type);
 	return record_type;
 }
 EXPORT_SYMBOL(tls_get_record_type);
@@ -99,5 +104,7 @@ void tls_alert_recv(const struct sock *sk, const struct msghdr *msg,
 	data = iov->iov_base;
 	*level = data[0];
 	*description = data[1];
+
+	trace_tls_alert_recv(sk, *level, *description);
 }
 EXPORT_SYMBOL(tls_alert_recv);
diff --git a/net/handshake/trace.c b/net/handshake/trace.c
index 1c4d8e27e17a7..44432d0857b9a 100644
--- a/net/handshake/trace.c
+++ b/net/handshake/trace.c
@@ -8,8 +8,10 @@
  */
 
 #include <linux/types.h>
+#include <linux/ipv6.h>
 
 #include <net/sock.h>
+#include <net/inet_sock.h>
 #include <net/netlink.h>
 #include <net/genetlink.h>
 
-- 
GitLab


From 3bdd85e2e3508a5f10949cae66c1d9e21a82d16f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Wed, 26 Jul 2023 17:45:22 +0100
Subject: [PATCH 0637/1806] net: ethernet: slicoss: remove redundant increment
 of pointer data

The pointer data is being incremented but this change to the pointer
is not used afterwards. The increment is redundant and can be removed.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Acked-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Link: https://lore.kernel.org/r/20230726164522.369206-1-colin.i.king@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/alacritech/slicoss.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c
index a30d0f172986b..78231c85234d0 100644
--- a/drivers/net/ethernet/alacritech/slicoss.c
+++ b/drivers/net/ethernet/alacritech/slicoss.c
@@ -1520,10 +1520,8 @@ static void slic_get_ethtool_stats(struct net_device *dev,
 
 static void slic_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 {
-	if (stringset == ETH_SS_STATS) {
+	if (stringset == ETH_SS_STATS)
 		memcpy(data, slic_stats_strings, sizeof(slic_stats_strings));
-		data += sizeof(slic_stats_strings);
-	}
 }
 
 static void slic_get_drvinfo(struct net_device *dev,
-- 
GitLab


From ee932bf940d4f624041293fab216cb1783b5df6b Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Fri, 28 Jul 2023 15:51:05 -0700
Subject: [PATCH 0638/1806] docs/bpf: Improve documentation for cpu=v4
 instructions

Improve documentation for cpu=v4 instructions based on
David's suggestions.

Cc: bpf@ietf.org
Suggested-by: David Vernet <void@manifault.com>
Acked-by: David Vernet <void@manifault.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230728225105.919595-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/standardization/instruction-set.rst   | 54 +++++++++++--------
 1 file changed, 32 insertions(+), 22 deletions(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 23e880a83a1f5..fb8154cedd841 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -174,7 +174,7 @@ BPF_MOV   0xb0   0        dst = src
 BPF_MOVSX 0xb0   8/16/32  dst = (s8,s16,s32)src
 BPF_ARSH  0xc0   0        sign extending dst >>= (src & mask)
 BPF_END   0xd0   0        byte swap operations (see `Byte swap instructions`_ below)
-========  =====  ============  ==========================================================
+========  =====  =======  ==========================================================
 
 Underflow and overflow are allowed during arithmetic operations, meaning
 the 64-bit or 32-bit value will wrap. If eBPF program execution would
@@ -201,26 +201,32 @@ where '(u32)' indicates that the upper 32 bits are zeroed.
 
   dst = dst ^ imm32
 
-Note that most instructions have instruction offset of 0. But three instructions
-(BPF_SDIV, BPF_SMOD, BPF_MOVSX) have non-zero offset.
+Note that most instructions have instruction offset of 0. Only three instructions
+(``BPF_SDIV``, ``BPF_SMOD``, ``BPF_MOVSX``) have a non-zero offset.
 
 The devision and modulo operations support both unsigned and signed flavors.
-For unsigned operation (BPF_DIV and BPF_MOD), for ``BPF_ALU``, 'imm' is first
-interpreted as an unsigned 32-bit value, whereas for ``BPF_ALU64``, 'imm' is
-first sign extended to 64 bits and the result interpreted as an unsigned 64-bit
-value.  For signed operation (BPF_SDIV and BPF_SMOD), for ``BPF_ALU``, 'imm' is
-interpreted as a signed value. For ``BPF_ALU64``, the 'imm' is sign extended
-from 32 to 64 and interpreted as a signed 64-bit value.
 
-Instruction BPF_MOVSX does move operation with sign extension.
-``BPF_ALU | MOVSX`` sign extendes 8-bit and 16-bit into 32-bit and upper 32-bit are zeroed.
-``BPF_ALU64 | MOVSX`` sign extends 8-bit, 16-bit and 32-bit into 64-bit.
+For unsigned operations (``BPF_DIV`` and ``BPF_MOD``), for ``BPF_ALU``,
+'imm' is interpreted as a 32-bit unsigned value. For ``BPF_ALU64``,
+'imm' is first sign extended from 32 to 64 bits, and then interpreted as
+a 64-bit unsigned value.
+
+For signed operations (``BPF_SDIV`` and ``BPF_SMOD``), for ``BPF_ALU``,
+'imm' is interpreted as a 32-bit signed value. For ``BPF_ALU64``, 'imm'
+is first sign extended from 32 to 64 bits, and then interpreted as a
+64-bit signed value.
+
+The ``BPF_MOVSX`` instruction does a move operation with sign extension.
+``BPF_ALU | BPF_MOVSX`` sign extends 8-bit and 16-bit operands into 32
+bit operands, and zeroes the remaining upper 32 bits.
+``BPF_ALU64 | BPF_MOVSX`` sign extends 8-bit, 16-bit, and 32-bit
+operands into 64 bit operands.
 
 Shift operations use a mask of 0x3F (63) for 64-bit operations and 0x1F (31)
 for 32-bit operations.
 
 Byte swap instructions
-~~~~~~~~~~~~~~~~~~~~~~
+----------------------
 
 The byte swap instructions use instruction classes of ``BPF_ALU`` and ``BPF_ALU64``
 and a 4-bit 'code' field of ``BPF_END``.
@@ -228,16 +234,17 @@ and a 4-bit 'code' field of ``BPF_END``.
 The byte swap instructions operate on the destination register
 only and do not use a separate source register or immediate value.
 
-For ``BPF_ALU``, the 1-bit source operand field in the opcode is used to select what byte
-order the operation convert from or to. For ``BPF_ALU64``, the 1-bit source operand
-field in the opcode is not used and must be 0.
+For ``BPF_ALU``, the 1-bit source operand field in the opcode is used to
+select what byte order the operation converts from or to. For
+``BPF_ALU64``, the 1-bit source operand field in the opcode is reserved
+and must be set to 0.
 
 =========  =========  =====  =================================================
 class      source     value  description
 =========  =========  =====  =================================================
 BPF_ALU    BPF_TO_LE  0x00   convert between host byte order and little endian
 BPF_ALU    BPF_TO_BE  0x08   convert between host byte order and big endian
-BPF_ALU64  BPF_TO_LE  0x00   do byte swap unconditionally
+BPF_ALU64  Reserved   0x00   do byte swap unconditionally
 =========  =========  =====  =================================================
 
 The 'imm' field encodes the width of the swap operations.  The following widths
@@ -305,9 +312,12 @@ where 's>=' indicates a signed '>=' comparison.
 
 where 'imm' means the branch offset comes from insn 'imm' field.
 
-Note there are two flavors of BPF_JA instrions. BPF_JMP class permits 16-bit jump offset while
-BPF_JMP32 permits 32-bit jump offset. A >16bit conditional jmp can be converted to a <16bit
-conditional jmp plus a 32-bit unconditional jump.
+Note that there are two flavors of ``BPF_JA`` instructions. The
+``BPF_JMP`` class permits a 16-bit jump offset specified by the 'offset'
+field, whereas the ``BPF_JMP32`` class permits a 32-bit jump offset
+specified by the 'imm' field. A > 16-bit conditional jump may be
+converted to a < 16-bit conditional jump plus a 32-bit unconditional
+jump.
 
 Helper functions
 ~~~~~~~~~~~~~~~~
@@ -385,7 +395,7 @@ instructions that transfer data between a register and memory.
   dst = *(unsigned size *) (src + offset)
 
 Where size is one of: ``BPF_B``, ``BPF_H``, ``BPF_W``, or ``BPF_DW`` and
-'unsigned size' is one of u8, u16, u32 and u64.
+'unsigned size' is one of u8, u16, u32 or u64.
 
 The ``BPF_MEMSX`` mode modifier is used to encode sign-extension load
 instructions that transfer data between a register and memory.
@@ -395,7 +405,7 @@ instructions that transfer data between a register and memory.
   dst = *(signed size *) (src + offset)
 
 Where size is one of: ``BPF_B``, ``BPF_H`` or ``BPF_W``, and
-'signed size' is one of s8, s16 and s32.
+'signed size' is one of s8, s16 or s32.
 
 Atomic operations
 -----------------
-- 
GitLab


From 9abddac583d68e16258d5e0b95dc1b3ca1886173 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Fri, 21 Jul 2023 14:22:45 -0600
Subject: [PATCH 0639/1806] netfilter: defrag: Add glue hooks for
 enabling/disabling defrag

We want to be able to enable/disable IP packet defrag from core
bpf/netfilter code. In other words, execute code from core that could
possibly be built as a module.

To help avoid symbol resolution errors, use glue hooks that the modules
will register callbacks with during module init.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Reviewed-by: Florian Westphal <fw@strlen.de>
Link: https://lore.kernel.org/r/f6a8824052441b72afe5285acedbd634bd3384c1.1689970773.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/netfilter.h                 | 10 ++++++++++
 net/ipv4/netfilter/nf_defrag_ipv4.c       | 17 ++++++++++++++++-
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 11 +++++++++++
 net/netfilter/core.c                      |  6 ++++++
 4 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index d4fed4c508ca3..d68644b7c299e 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -11,6 +11,7 @@
 #include <linux/wait.h>
 #include <linux/list.h>
 #include <linux/static_key.h>
+#include <linux/module.h>
 #include <linux/netfilter_defs.h>
 #include <linux/netdevice.h>
 #include <linux/sockptr.h>
@@ -481,6 +482,15 @@ struct nfnl_ct_hook {
 };
 extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook;
 
+struct nf_defrag_hook {
+	struct module *owner;
+	int (*enable)(struct net *net);
+	void (*disable)(struct net *net);
+};
+
+extern const struct nf_defrag_hook __rcu *nf_defrag_v4_hook;
+extern const struct nf_defrag_hook __rcu *nf_defrag_v6_hook;
+
 /*
  * nf_skb_duplicated - TEE target has sent a packet
  *
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index e61ea428ea187..a9ba7de092c42 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -7,6 +7,7 @@
 #include <linux/ip.h>
 #include <linux/netfilter.h>
 #include <linux/module.h>
+#include <linux/rcupdate.h>
 #include <linux/skbuff.h>
 #include <net/netns/generic.h>
 #include <net/route.h>
@@ -113,17 +114,31 @@ static void __net_exit defrag4_net_exit(struct net *net)
 	}
 }
 
+static const struct nf_defrag_hook defrag_hook = {
+	.owner = THIS_MODULE,
+	.enable = nf_defrag_ipv4_enable,
+	.disable = nf_defrag_ipv4_disable,
+};
+
 static struct pernet_operations defrag4_net_ops = {
 	.exit = defrag4_net_exit,
 };
 
 static int __init nf_defrag_init(void)
 {
-	return register_pernet_subsys(&defrag4_net_ops);
+	int err;
+
+	err = register_pernet_subsys(&defrag4_net_ops);
+	if (err)
+		return err;
+
+	rcu_assign_pointer(nf_defrag_v4_hook, &defrag_hook);
+	return err;
 }
 
 static void __exit nf_defrag_fini(void)
 {
+	rcu_assign_pointer(nf_defrag_v4_hook, NULL);
 	unregister_pernet_subsys(&defrag4_net_ops);
 }
 
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index cb4eb1d2c620b..d59b296b4f519 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/icmp.h>
+#include <linux/rcupdate.h>
 #include <linux/sysctl.h>
 #include <net/ipv6_frag.h>
 
@@ -96,6 +97,12 @@ static void __net_exit defrag6_net_exit(struct net *net)
 	}
 }
 
+static const struct nf_defrag_hook defrag_hook = {
+	.owner = THIS_MODULE,
+	.enable = nf_defrag_ipv6_enable,
+	.disable = nf_defrag_ipv6_disable,
+};
+
 static struct pernet_operations defrag6_net_ops = {
 	.exit = defrag6_net_exit,
 };
@@ -114,6 +121,9 @@ static int __init nf_defrag_init(void)
 		pr_err("nf_defrag_ipv6: can't register pernet ops\n");
 		goto cleanup_frag6;
 	}
+
+	rcu_assign_pointer(nf_defrag_v6_hook, &defrag_hook);
+
 	return ret;
 
 cleanup_frag6:
@@ -124,6 +134,7 @@ cleanup_frag6:
 
 static void __exit nf_defrag_fini(void)
 {
+	rcu_assign_pointer(nf_defrag_v6_hook, NULL);
 	unregister_pernet_subsys(&defrag6_net_ops);
 	nf_ct_frag6_cleanup();
 }
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 5f76ae86a6561..ef4e76e5aef9f 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -680,6 +680,12 @@ EXPORT_SYMBOL_GPL(nfnl_ct_hook);
 const struct nf_ct_hook __rcu *nf_ct_hook __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_hook);
 
+const struct nf_defrag_hook __rcu *nf_defrag_v4_hook __read_mostly;
+EXPORT_SYMBOL_GPL(nf_defrag_v4_hook);
+
+const struct nf_defrag_hook __rcu *nf_defrag_v6_hook __read_mostly;
+EXPORT_SYMBOL_GPL(nf_defrag_v6_hook);
+
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 u8 nf_ctnetlink_has_listener;
 EXPORT_SYMBOL_GPL(nf_ctnetlink_has_listener);
-- 
GitLab


From 91721c2d02d3a0141df8a4787c7079b89b0d0607 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Fri, 21 Jul 2023 14:22:46 -0600
Subject: [PATCH 0640/1806] netfilter: bpf: Support BPF_F_NETFILTER_IP_DEFRAG
 in netfilter link

This commit adds support for enabling IP defrag using pre-existing
netfilter defrag support. Basically all the flag does is bump a refcnt
while the link the active. Checks are also added to ensure the prog
requesting defrag support is run _after_ netfilter defrag hooks.

We also take care to avoid any issues w.r.t. module unloading -- while
defrag is active on a link, the module is prevented from unloading.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Reviewed-by: Florian Westphal <fw@strlen.de>
Link: https://lore.kernel.org/r/5cff26f97e55161b7d56b09ddcf5f8888a5add1d.1689970773.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       |   5 ++
 net/netfilter/nf_bpf_link.c    | 123 +++++++++++++++++++++++++++++----
 tools/include/uapi/linux/bpf.h |   5 ++
 3 files changed, 118 insertions(+), 15 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 14fd26b09e4b3..70da852006952 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1188,6 +1188,11 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_KPROBE_MULTI_RETURN	(1U << 0)
 
+/* link_create.netfilter.flags used in LINK_CREATE command for
+ * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
+ */
+#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *
diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index c36da56d756f4..8fe594bbc7e24 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/kmod.h>
+#include <linux/module.h>
 #include <linux/netfilter.h>
 
 #include <net/netfilter/nf_bpf_link.h>
@@ -23,8 +25,88 @@ struct bpf_nf_link {
 	struct nf_hook_ops hook_ops;
 	struct net *net;
 	u32 dead;
+	const struct nf_defrag_hook *defrag_hook;
 };
 
+static const struct nf_defrag_hook *
+get_proto_defrag_hook(struct bpf_nf_link *link,
+		      const struct nf_defrag_hook __rcu *global_hook,
+		      const char *mod)
+{
+	const struct nf_defrag_hook *hook;
+	int err;
+
+	/* RCU protects us from races against module unloading */
+	rcu_read_lock();
+	hook = rcu_dereference(global_hook);
+	if (!hook) {
+		rcu_read_unlock();
+		err = request_module(mod);
+		if (err)
+			return ERR_PTR(err < 0 ? err : -EINVAL);
+
+		rcu_read_lock();
+		hook = rcu_dereference(global_hook);
+	}
+
+	if (hook && try_module_get(hook->owner)) {
+		/* Once we have a refcnt on the module, we no longer need RCU */
+		hook = rcu_pointer_handoff(hook);
+	} else {
+		WARN_ONCE(!hook, "%s has bad registration", mod);
+		hook = ERR_PTR(-ENOENT);
+	}
+	rcu_read_unlock();
+
+	if (!IS_ERR(hook)) {
+		err = hook->enable(link->net);
+		if (err) {
+			module_put(hook->owner);
+			hook = ERR_PTR(err);
+		}
+	}
+
+	return hook;
+}
+
+static int bpf_nf_enable_defrag(struct bpf_nf_link *link)
+{
+	const struct nf_defrag_hook __maybe_unused *hook;
+
+	switch (link->hook_ops.pf) {
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
+	case NFPROTO_IPV4:
+		hook = get_proto_defrag_hook(link, nf_defrag_v4_hook, "nf_defrag_ipv4");
+		if (IS_ERR(hook))
+			return PTR_ERR(hook);
+
+		link->defrag_hook = hook;
+		return 0;
+#endif
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
+	case NFPROTO_IPV6:
+		hook = get_proto_defrag_hook(link, nf_defrag_v6_hook, "nf_defrag_ipv6");
+		if (IS_ERR(hook))
+			return PTR_ERR(hook);
+
+		link->defrag_hook = hook;
+		return 0;
+#endif
+	default:
+		return -EAFNOSUPPORT;
+	}
+}
+
+static void bpf_nf_disable_defrag(struct bpf_nf_link *link)
+{
+	const struct nf_defrag_hook *hook = link->defrag_hook;
+
+	if (!hook)
+		return;
+	hook->disable(link->net);
+	module_put(hook->owner);
+}
+
 static void bpf_nf_link_release(struct bpf_link *link)
 {
 	struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link);
@@ -32,11 +114,11 @@ static void bpf_nf_link_release(struct bpf_link *link)
 	if (nf_link->dead)
 		return;
 
-	/* prevent hook-not-found warning splat from netfilter core when
-	 * .detach was already called
-	 */
-	if (!cmpxchg(&nf_link->dead, 0, 1))
+	/* do not double release in case .detach was already called */
+	if (!cmpxchg(&nf_link->dead, 0, 1)) {
 		nf_unregister_net_hook(nf_link->net, &nf_link->hook_ops);
+		bpf_nf_disable_defrag(nf_link);
+	}
 }
 
 static void bpf_nf_link_dealloc(struct bpf_link *link)
@@ -92,6 +174,8 @@ static const struct bpf_link_ops bpf_nf_link_lops = {
 
 static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr)
 {
+	int prio;
+
 	switch (attr->link_create.netfilter.pf) {
 	case NFPROTO_IPV4:
 	case NFPROTO_IPV6:
@@ -102,19 +186,18 @@ static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr)
 		return -EAFNOSUPPORT;
 	}
 
-	if (attr->link_create.netfilter.flags)
+	if (attr->link_create.netfilter.flags & ~BPF_F_NETFILTER_IP_DEFRAG)
 		return -EOPNOTSUPP;
 
-	/* make sure conntrack confirm is always last.
-	 *
-	 * In the future, if userspace can e.g. request defrag, then
-	 * "defrag_requested && prio before NF_IP_PRI_CONNTRACK_DEFRAG"
-	 * should fail.
-	 */
-	switch (attr->link_create.netfilter.priority) {
-	case NF_IP_PRI_FIRST: return -ERANGE; /* sabotage_in and other warts */
-	case NF_IP_PRI_LAST: return -ERANGE; /* e.g. conntrack confirm */
-	}
+	/* make sure conntrack confirm is always last */
+	prio = attr->link_create.netfilter.priority;
+	if (prio == NF_IP_PRI_FIRST)
+		return -ERANGE;  /* sabotage_in and other warts */
+	else if (prio == NF_IP_PRI_LAST)
+		return -ERANGE;  /* e.g. conntrack confirm */
+	else if ((attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) &&
+		 prio <= NF_IP_PRI_CONNTRACK_DEFRAG)
+		return -ERANGE;  /* cannot use defrag if prog runs before nf_defrag */
 
 	return 0;
 }
@@ -149,6 +232,7 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 
 	link->net = net;
 	link->dead = false;
+	link->defrag_hook = NULL;
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err) {
@@ -156,8 +240,17 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 		return err;
 	}
 
+	if (attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) {
+		err = bpf_nf_enable_defrag(link);
+		if (err) {
+			bpf_link_cleanup(&link_primer);
+			return err;
+		}
+	}
+
 	err = nf_register_net_hook(net, &link->hook_ops);
 	if (err) {
+		bpf_nf_disable_defrag(link);
 		bpf_link_cleanup(&link_primer);
 		return err;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 14fd26b09e4b3..70da852006952 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1188,6 +1188,11 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_KPROBE_MULTI_RETURN	(1U << 0)
 
+/* link_create.netfilter.flags used in LINK_CREATE command for
+ * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
+ */
+#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *
-- 
GitLab


From 3495e89cdc3ab71719bd88c03dbd624c49ee70d2 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Fri, 21 Jul 2023 14:22:47 -0600
Subject: [PATCH 0641/1806] bpf: selftests: Support not connecting client
 socket

For connectionless protocols or raw sockets we do not want to actually
connect() to the server.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/525c13d66dac2d640a1db922546842c051c6f2e6.1689970773.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c | 5 +++--
 tools/testing/selftests/bpf/network_helpers.h | 1 +
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 8a33bcea97de8..4dcd63a2369fa 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -301,8 +301,9 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 		       strlen(opts->cc) + 1))
 		goto error_close;
 
-	if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail))
-		goto error_close;
+	if (!opts->noconnect)
+		if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail))
+			goto error_close;
 
 	return fd;
 
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 694185644da6b..87894dc984dda 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -21,6 +21,7 @@ struct network_helper_opts {
 	const char *cc;
 	int timeout_ms;
 	bool must_fail;
+	bool noconnect;
 };
 
 /* ipv4 test vector */
-- 
GitLab


From e15a22095608ae5e1da5892da739d83b49b3bba5 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Fri, 21 Jul 2023 14:22:48 -0600
Subject: [PATCH 0642/1806] bpf: selftests: Support custom type and proto for
 client sockets

Extend connect_to_fd_opts() to take optional type and protocol
parameters for the client socket. These parameters are useful when
opening a raw socket to send IP fragments.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/9067db539efdfd608aa86a2b143c521337c111fc.1689970773.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c | 21 +++++++++++++------
 tools/testing/selftests/bpf/network_helpers.h |  2 ++
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 4dcd63a2369fa..da72a3a662300 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -270,14 +270,23 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 		opts = &default_opts;
 
 	optlen = sizeof(type);
-	if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
-		log_err("getsockopt(SOL_TYPE)");
-		return -1;
+
+	if (opts->type) {
+		type = opts->type;
+	} else {
+		if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
+			log_err("getsockopt(SOL_TYPE)");
+			return -1;
+		}
 	}
 
-	if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) {
-		log_err("getsockopt(SOL_PROTOCOL)");
-		return -1;
+	if (opts->proto) {
+		protocol = opts->proto;
+	} else {
+		if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) {
+			log_err("getsockopt(SOL_PROTOCOL)");
+			return -1;
+		}
 	}
 
 	addrlen = sizeof(addr);
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 87894dc984dda..5eccc67d1a998 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -22,6 +22,8 @@ struct network_helper_opts {
 	int timeout_ms;
 	bool must_fail;
 	bool noconnect;
+	int type;
+	int proto;
 };
 
 /* ipv4 test vector */
-- 
GitLab


From c313eae739b9a0fc5fbe655cece38eae0a90ec42 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Fri, 21 Jul 2023 14:22:49 -0600
Subject: [PATCH 0643/1806] bpf: selftests: Add defrag selftests

These selftests tests 2 major scenarios: the BPF based defragmentation
can successfully be done and that packet pointers are invalidated after
calls to the kfunc. The logic is similar for both ipv4 and ipv6.

In the first scenario, we create a UDP client and UDP echo server. The
the server side is fairly straightforward: we attach the prog and simply
echo back the message.

The on the client side, we send fragmented packets to and expect the
reassembled message back from the server.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/33e40fdfddf43be93f2cb259303f132f46750953.1689970773.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/Makefile          |   4 +-
 .../selftests/bpf/generate_udp_fragments.py   |  90 ++++++
 .../selftests/bpf/ip_check_defrag_frags.h     |  57 ++++
 .../bpf/prog_tests/ip_check_defrag.c          | 283 ++++++++++++++++++
 .../selftests/bpf/progs/ip_check_defrag.c     | 104 +++++++
 5 files changed, 536 insertions(+), 2 deletions(-)
 create mode 100755 tools/testing/selftests/bpf/generate_udp_fragments.py
 create mode 100644 tools/testing/selftests/bpf/ip_check_defrag_frags.h
 create mode 100644 tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c
 create mode 100644 tools/testing/selftests/bpf/progs/ip_check_defrag.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 73a6ca80fa16d..e4e1e64922684 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -579,8 +579,8 @@ TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c	\
 			 network_helpers.c testing_helpers.c		\
 			 btf_helpers.c flow_dissector_load.h		\
 			 cap_helpers.c test_loader.c xsk.c disasm.c	\
-			 json_writer.c unpriv_helpers.c
-
+			 json_writer.c unpriv_helpers.c 		\
+			 ip_check_defrag_frags.h
 TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko	\
 		       $(OUTPUT)/liburandom_read.so			\
 		       $(OUTPUT)/xdp_synproxy				\
diff --git a/tools/testing/selftests/bpf/generate_udp_fragments.py b/tools/testing/selftests/bpf/generate_udp_fragments.py
new file mode 100755
index 0000000000000..2b8a1187991ce
--- /dev/null
+++ b/tools/testing/selftests/bpf/generate_udp_fragments.py
@@ -0,0 +1,90 @@
+#!/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+This script helps generate fragmented UDP packets.
+
+While it is technically possible to dynamically generate
+fragmented packets in C, it is much harder to read and write
+said code. `scapy` is relatively industry standard and really
+easy to read / write.
+
+So we choose to write this script that generates a valid C
+header. Rerun script and commit generated file after any
+modifications.
+"""
+
+import argparse
+import os
+
+from scapy.all import *
+
+
+# These constants must stay in sync with `ip_check_defrag.c`
+VETH1_ADDR = "172.16.1.200"
+VETH0_ADDR6 = "fc00::100"
+VETH1_ADDR6 = "fc00::200"
+CLIENT_PORT = 48878
+SERVER_PORT = 48879
+MAGIC_MESSAGE = "THIS IS THE ORIGINAL MESSAGE, PLEASE REASSEMBLE ME"
+
+
+def print_header(f):
+    f.write("// SPDX-License-Identifier: GPL-2.0\n")
+    f.write("/* DO NOT EDIT -- this file is generated */\n")
+    f.write("\n")
+    f.write("#ifndef _IP_CHECK_DEFRAG_FRAGS_H\n")
+    f.write("#define _IP_CHECK_DEFRAG_FRAGS_H\n")
+    f.write("\n")
+    f.write("#include <stdint.h>\n")
+    f.write("\n")
+
+
+def print_frags(f, frags, v6):
+    for idx, frag in enumerate(frags):
+        # 10 bytes per line to keep width in check
+        chunks = [frag[i : i + 10] for i in range(0, len(frag), 10)]
+        chunks_fmted = [", ".join([str(hex(b)) for b in chunk]) for chunk in chunks]
+        suffix = "6" if v6 else ""
+
+        f.write(f"static uint8_t frag{suffix}_{idx}[] = {{\n")
+        for chunk in chunks_fmted:
+            f.write(f"\t{chunk},\n")
+        f.write(f"}};\n")
+
+
+def print_trailer(f):
+    f.write("\n")
+    f.write("#endif /* _IP_CHECK_DEFRAG_FRAGS_H */\n")
+
+
+def main(f):
+    # srcip of 0 is filled in by IP_HDRINCL
+    sip = "0.0.0.0"
+    sip6 = VETH0_ADDR6
+    dip = VETH1_ADDR
+    dip6 = VETH1_ADDR6
+    sport = CLIENT_PORT
+    dport = SERVER_PORT
+    payload = MAGIC_MESSAGE.encode()
+
+    # Disable UDPv4 checksums to keep code simpler
+    pkt = IP(src=sip,dst=dip) / UDP(sport=sport,dport=dport,chksum=0) / Raw(load=payload)
+    # UDPv6 requires a checksum
+    # Also pin the ipv6 fragment header ID, otherwise it's a random value
+    pkt6 = IPv6(src=sip6,dst=dip6) / IPv6ExtHdrFragment(id=0xBEEF) / UDP(sport=sport,dport=dport) / Raw(load=payload)
+
+    frags = [f.build() for f in pkt.fragment(24)]
+    frags6 = [f.build() for f in fragment6(pkt6, 72)]
+
+    print_header(f)
+    print_frags(f, frags, False)
+    print_frags(f, frags6, True)
+    print_trailer(f)
+
+
+if __name__ == "__main__":
+    dir = os.path.dirname(os.path.realpath(__file__))
+    header = f"{dir}/ip_check_defrag_frags.h"
+    with open(header, "w") as f:
+        main(f)
diff --git a/tools/testing/selftests/bpf/ip_check_defrag_frags.h b/tools/testing/selftests/bpf/ip_check_defrag_frags.h
new file mode 100644
index 0000000000000..70ab7e9fa22b2
--- /dev/null
+++ b/tools/testing/selftests/bpf/ip_check_defrag_frags.h
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* DO NOT EDIT -- this file is generated */
+
+#ifndef _IP_CHECK_DEFRAG_FRAGS_H
+#define _IP_CHECK_DEFRAG_FRAGS_H
+
+#include <stdint.h>
+
+static uint8_t frag_0[] = {
+	0x45, 0x0, 0x0, 0x2c, 0x0, 0x1, 0x20, 0x0, 0x40, 0x11,
+	0xac, 0xe8, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+	0xbe, 0xee, 0xbe, 0xef, 0x0, 0x3a, 0x0, 0x0, 0x54, 0x48,
+	0x49, 0x53, 0x20, 0x49, 0x53, 0x20, 0x54, 0x48, 0x45, 0x20,
+	0x4f, 0x52, 0x49, 0x47,
+};
+static uint8_t frag_1[] = {
+	0x45, 0x0, 0x0, 0x2c, 0x0, 0x1, 0x20, 0x3, 0x40, 0x11,
+	0xac, 0xe5, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+	0x49, 0x4e, 0x41, 0x4c, 0x20, 0x4d, 0x45, 0x53, 0x53, 0x41,
+	0x47, 0x45, 0x2c, 0x20, 0x50, 0x4c, 0x45, 0x41, 0x53, 0x45,
+	0x20, 0x52, 0x45, 0x41,
+};
+static uint8_t frag_2[] = {
+	0x45, 0x0, 0x0, 0x1e, 0x0, 0x1, 0x0, 0x6, 0x40, 0x11,
+	0xcc, 0xf0, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+	0x53, 0x53, 0x45, 0x4d, 0x42, 0x4c, 0x45, 0x20, 0x4d, 0x45,
+};
+static uint8_t frag6_0[] = {
+	0x60, 0x0, 0x0, 0x0, 0x0, 0x20, 0x2c, 0x40, 0xfc, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+	0x11, 0x0, 0x0, 0x1, 0x0, 0x0, 0xbe, 0xef, 0xbe, 0xee,
+	0xbe, 0xef, 0x0, 0x3a, 0xd0, 0xf8, 0x54, 0x48, 0x49, 0x53,
+	0x20, 0x49, 0x53, 0x20, 0x54, 0x48, 0x45, 0x20, 0x4f, 0x52,
+	0x49, 0x47,
+};
+static uint8_t frag6_1[] = {
+	0x60, 0x0, 0x0, 0x0, 0x0, 0x20, 0x2c, 0x40, 0xfc, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+	0x11, 0x0, 0x0, 0x19, 0x0, 0x0, 0xbe, 0xef, 0x49, 0x4e,
+	0x41, 0x4c, 0x20, 0x4d, 0x45, 0x53, 0x53, 0x41, 0x47, 0x45,
+	0x2c, 0x20, 0x50, 0x4c, 0x45, 0x41, 0x53, 0x45, 0x20, 0x52,
+	0x45, 0x41,
+};
+static uint8_t frag6_2[] = {
+	0x60, 0x0, 0x0, 0x0, 0x0, 0x12, 0x2c, 0x40, 0xfc, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+	0x11, 0x0, 0x0, 0x30, 0x0, 0x0, 0xbe, 0xef, 0x53, 0x53,
+	0x45, 0x4d, 0x42, 0x4c, 0x45, 0x20, 0x4d, 0x45,
+};
+
+#endif /* _IP_CHECK_DEFRAG_FRAGS_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c b/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c
new file mode 100644
index 0000000000000..57c814f5f6a71
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <net/if.h>
+#include <linux/netfilter.h>
+#include <network_helpers.h>
+#include "ip_check_defrag.skel.h"
+#include "ip_check_defrag_frags.h"
+
+/*
+ * This selftest spins up a client and an echo server, each in their own
+ * network namespace. The client will send a fragmented message to the server.
+ * The prog attached to the server will shoot down any fragments. Thus, if
+ * the server is able to correctly echo back the message to the client, we will
+ * have verified that netfilter is reassembling packets for us.
+ *
+ * Topology:
+ * =========
+ *           NS0         |         NS1
+ *                       |
+ *         client        |       server
+ *       ----------      |     ----------
+ *       |  veth0  | --------- |  veth1  |
+ *       ----------    peer    ----------
+ *                       |
+ *                       |       with bpf
+ */
+
+#define NS0		"defrag_ns0"
+#define NS1		"defrag_ns1"
+#define VETH0		"veth0"
+#define VETH1		"veth1"
+#define VETH0_ADDR	"172.16.1.100"
+#define VETH0_ADDR6	"fc00::100"
+/* The following constants must stay in sync with `generate_udp_fragments.py` */
+#define VETH1_ADDR	"172.16.1.200"
+#define VETH1_ADDR6	"fc00::200"
+#define CLIENT_PORT	48878
+#define SERVER_PORT	48879
+#define MAGIC_MESSAGE	"THIS IS THE ORIGINAL MESSAGE, PLEASE REASSEMBLE ME"
+
+static int setup_topology(bool ipv6)
+{
+	bool up;
+	int i;
+
+	SYS(fail, "ip netns add " NS0);
+	SYS(fail, "ip netns add " NS1);
+	SYS(fail, "ip link add " VETH0 " netns " NS0 " type veth peer name " VETH1 " netns " NS1);
+	if (ipv6) {
+		SYS(fail, "ip -6 -net " NS0 " addr add " VETH0_ADDR6 "/64 dev " VETH0 " nodad");
+		SYS(fail, "ip -6 -net " NS1 " addr add " VETH1_ADDR6 "/64 dev " VETH1 " nodad");
+	} else {
+		SYS(fail, "ip -net " NS0 " addr add " VETH0_ADDR "/24 dev " VETH0);
+		SYS(fail, "ip -net " NS1 " addr add " VETH1_ADDR "/24 dev " VETH1);
+	}
+	SYS(fail, "ip -net " NS0 " link set dev " VETH0 " up");
+	SYS(fail, "ip -net " NS1 " link set dev " VETH1 " up");
+
+	/* Wait for up to 5s for links to come up */
+	for (i = 0; i < 5; ++i) {
+		if (ipv6)
+			up = !system("ip netns exec " NS0 " ping -6 -c 1 -W 1 " VETH1_ADDR6 " &>/dev/null");
+		else
+			up = !system("ip netns exec " NS0 " ping -c 1 -W 1 " VETH1_ADDR " &>/dev/null");
+
+		if (up)
+			break;
+	}
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void cleanup_topology(void)
+{
+	SYS_NOFAIL("test -f /var/run/netns/" NS0 " && ip netns delete " NS0);
+	SYS_NOFAIL("test -f /var/run/netns/" NS1 " && ip netns delete " NS1);
+}
+
+static int attach(struct ip_check_defrag *skel, bool ipv6)
+{
+	LIBBPF_OPTS(bpf_netfilter_opts, opts,
+		    .pf = ipv6 ? NFPROTO_IPV6 : NFPROTO_IPV4,
+		    .priority = 42,
+		    .flags = BPF_F_NETFILTER_IP_DEFRAG);
+	struct nstoken *nstoken;
+	int err = -1;
+
+	nstoken = open_netns(NS1);
+
+	skel->links.defrag = bpf_program__attach_netfilter(skel->progs.defrag, &opts);
+	if (!ASSERT_OK_PTR(skel->links.defrag, "program attach"))
+		goto out;
+
+	err = 0;
+out:
+	close_netns(nstoken);
+	return err;
+}
+
+static int send_frags(int client)
+{
+	struct sockaddr_storage saddr;
+	struct sockaddr *saddr_p;
+	socklen_t saddr_len;
+	int err;
+
+	saddr_p = (struct sockaddr *)&saddr;
+	err = make_sockaddr(AF_INET, VETH1_ADDR, SERVER_PORT, &saddr, &saddr_len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		return -1;
+
+	err = sendto(client, frag_0, sizeof(frag_0), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag_0"))
+		return -1;
+
+	err = sendto(client, frag_1, sizeof(frag_1), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag_1"))
+		return -1;
+
+	err = sendto(client, frag_2, sizeof(frag_2), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag_2"))
+		return -1;
+
+	return 0;
+}
+
+static int send_frags6(int client)
+{
+	struct sockaddr_storage saddr;
+	struct sockaddr *saddr_p;
+	socklen_t saddr_len;
+	int err;
+
+	saddr_p = (struct sockaddr *)&saddr;
+	/* Port needs to be set to 0 for raw ipv6 socket for some reason */
+	err = make_sockaddr(AF_INET6, VETH1_ADDR6, 0, &saddr, &saddr_len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		return -1;
+
+	err = sendto(client, frag6_0, sizeof(frag6_0), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag6_0"))
+		return -1;
+
+	err = sendto(client, frag6_1, sizeof(frag6_1), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag6_1"))
+		return -1;
+
+	err = sendto(client, frag6_2, sizeof(frag6_2), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag6_2"))
+		return -1;
+
+	return 0;
+}
+
+void test_bpf_ip_check_defrag_ok(bool ipv6)
+{
+	struct network_helper_opts rx_opts = {
+		.timeout_ms = 1000,
+		.noconnect = true,
+	};
+	struct network_helper_opts tx_ops = {
+		.timeout_ms = 1000,
+		.type = SOCK_RAW,
+		.proto = IPPROTO_RAW,
+		.noconnect = true,
+	};
+	struct sockaddr_storage caddr;
+	struct ip_check_defrag *skel;
+	struct nstoken *nstoken;
+	int client_tx_fd = -1;
+	int client_rx_fd = -1;
+	socklen_t caddr_len;
+	int srv_fd = -1;
+	char buf[1024];
+	int len, err;
+
+	skel = ip_check_defrag__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	if (!ASSERT_OK(setup_topology(ipv6), "setup_topology"))
+		goto out;
+
+	if (!ASSERT_OK(attach(skel, ipv6), "attach"))
+		goto out;
+
+	/* Start server in ns1 */
+	nstoken = open_netns(NS1);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns1"))
+		goto out;
+	srv_fd = start_server(ipv6 ? AF_INET6 : AF_INET, SOCK_DGRAM, NULL, SERVER_PORT, 0);
+	close_netns(nstoken);
+	if (!ASSERT_GE(srv_fd, 0, "start_server"))
+		goto out;
+
+	/* Open tx raw socket in ns0 */
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+		goto out;
+	client_tx_fd = connect_to_fd_opts(srv_fd, &tx_ops);
+	close_netns(nstoken);
+	if (!ASSERT_GE(client_tx_fd, 0, "connect_to_fd_opts"))
+		goto out;
+
+	/* Open rx socket in ns0 */
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+		goto out;
+	client_rx_fd = connect_to_fd_opts(srv_fd, &rx_opts);
+	close_netns(nstoken);
+	if (!ASSERT_GE(client_rx_fd, 0, "connect_to_fd_opts"))
+		goto out;
+
+	/* Bind rx socket to a premeditated port */
+	memset(&caddr, 0, sizeof(caddr));
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+		goto out;
+	if (ipv6) {
+		struct sockaddr_in6 *c = (struct sockaddr_in6 *)&caddr;
+
+		c->sin6_family = AF_INET6;
+		inet_pton(AF_INET6, VETH0_ADDR6, &c->sin6_addr);
+		c->sin6_port = htons(CLIENT_PORT);
+		err = bind(client_rx_fd, (struct sockaddr *)c, sizeof(*c));
+	} else {
+		struct sockaddr_in *c = (struct sockaddr_in *)&caddr;
+
+		c->sin_family = AF_INET;
+		inet_pton(AF_INET, VETH0_ADDR, &c->sin_addr);
+		c->sin_port = htons(CLIENT_PORT);
+		err = bind(client_rx_fd, (struct sockaddr *)c, sizeof(*c));
+	}
+	close_netns(nstoken);
+	if (!ASSERT_OK(err, "bind"))
+		goto out;
+
+	/* Send message in fragments */
+	if (ipv6) {
+		if (!ASSERT_OK(send_frags6(client_tx_fd), "send_frags6"))
+			goto out;
+	} else {
+		if (!ASSERT_OK(send_frags(client_tx_fd), "send_frags"))
+			goto out;
+	}
+
+	if (!ASSERT_EQ(skel->bss->shootdowns, 0, "shootdowns"))
+		goto out;
+
+	/* Receive reassembled msg on server and echo back to client */
+	caddr_len = sizeof(caddr);
+	len = recvfrom(srv_fd, buf, sizeof(buf), 0, (struct sockaddr *)&caddr, &caddr_len);
+	if (!ASSERT_GE(len, 0, "server recvfrom"))
+		goto out;
+	len = sendto(srv_fd, buf, len, 0, (struct sockaddr *)&caddr, caddr_len);
+	if (!ASSERT_GE(len, 0, "server sendto"))
+		goto out;
+
+	/* Expect reassembed message to be echoed back */
+	len = recvfrom(client_rx_fd, buf, sizeof(buf), 0, NULL, NULL);
+	if (!ASSERT_EQ(len, sizeof(MAGIC_MESSAGE) - 1, "client short read"))
+		goto out;
+
+out:
+	if (client_rx_fd != -1)
+		close(client_rx_fd);
+	if (client_tx_fd != -1)
+		close(client_tx_fd);
+	if (srv_fd != -1)
+		close(srv_fd);
+	cleanup_topology();
+	ip_check_defrag__destroy(skel);
+}
+
+void test_bpf_ip_check_defrag(void)
+{
+	if (test__start_subtest("v4"))
+		test_bpf_ip_check_defrag_ok(false);
+	if (test__start_subtest("v6"))
+		test_bpf_ip_check_defrag_ok(true);
+}
diff --git a/tools/testing/selftests/bpf/progs/ip_check_defrag.c b/tools/testing/selftests/bpf/progs/ip_check_defrag.c
new file mode 100644
index 0000000000000..1c2b6c1616b05
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/ip_check_defrag.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+
+#define NF_DROP			0
+#define NF_ACCEPT		1
+#define ETH_P_IP		0x0800
+#define ETH_P_IPV6		0x86DD
+#define IP_MF			0x2000
+#define IP_OFFSET		0x1FFF
+#define NEXTHDR_FRAGMENT	44
+
+extern int bpf_dynptr_from_skb(struct sk_buff *skb, __u64 flags,
+			      struct bpf_dynptr *ptr__uninit) __ksym;
+extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, uint32_t offset,
+			      void *buffer, uint32_t buffer__sz) __ksym;
+
+volatile int shootdowns = 0;
+
+static bool is_frag_v4(struct iphdr *iph)
+{
+	int offset;
+	int flags;
+
+	offset = bpf_ntohs(iph->frag_off);
+	flags = offset & ~IP_OFFSET;
+	offset &= IP_OFFSET;
+	offset <<= 3;
+
+	return (flags & IP_MF) || offset;
+}
+
+static bool is_frag_v6(struct ipv6hdr *ip6h)
+{
+	/* Simplifying assumption that there are no extension headers
+	 * between fixed header and fragmentation header. This assumption
+	 * is only valid in this test case. It saves us the hassle of
+	 * searching all potential extension headers.
+	 */
+	return ip6h->nexthdr == NEXTHDR_FRAGMENT;
+}
+
+static int handle_v4(struct sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	u8 iph_buf[20] = {};
+	struct iphdr *iph;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr))
+		return NF_DROP;
+
+	iph = bpf_dynptr_slice(&ptr, 0, iph_buf, sizeof(iph_buf));
+	if (!iph)
+		return NF_DROP;
+
+	/* Shootdown any frags */
+	if (is_frag_v4(iph)) {
+		shootdowns++;
+		return NF_DROP;
+	}
+
+	return NF_ACCEPT;
+}
+
+static int handle_v6(struct sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ipv6hdr *ip6h;
+	u8 ip6h_buf[40] = {};
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr))
+		return NF_DROP;
+
+	ip6h = bpf_dynptr_slice(&ptr, 0, ip6h_buf, sizeof(ip6h_buf));
+	if (!ip6h)
+		return NF_DROP;
+
+	/* Shootdown any frags */
+	if (is_frag_v6(ip6h)) {
+		shootdowns++;
+		return NF_DROP;
+	}
+
+	return NF_ACCEPT;
+}
+
+SEC("netfilter")
+int defrag(struct bpf_nf_ctx *ctx)
+{
+	struct sk_buff *skb = ctx->skb;
+
+	switch (bpf_ntohs(skb->protocol)) {
+	case ETH_P_IP:
+		return handle_v4(skb);
+	case ETH_P_IPV6:
+		return handle_v6(skb);
+	default:
+		return NF_ACCEPT;
+	}
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From 57df0fb9d511f91202114813e90128d65c0589f0 Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 26 Jul 2023 11:08:07 +0800
Subject: [PATCH 0644/1806] r8152: adjust generic_ocp_write function

Reduce the control transfer if all bytes of first or the last DWORD are
written.

The original method is to split the control transfer into three parts
(the first DWORD, middle continuous data, and the last DWORD). However,
they could be combined if whole bytes of the first DWORD or last DWORD
are written. That is, the first DWORD or the last DWORD could be combined
with the middle continuous data, if the byte_en is 0xff.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Link: https://lore.kernel.org/r/20230726030808.9093-418-nic_swsd@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 0738baa5b82e4..f6578a99dbac4 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1314,16 +1314,24 @@ static int generic_ocp_write(struct r8152 *tp, u16 index, u16 byteen,
 	byteen_end = byteen & BYTE_EN_END_MASK;
 
 	byen = byteen_start | (byteen_start << 4);
-	ret = set_registers(tp, index, type | byen, 4, data);
-	if (ret < 0)
-		goto error1;
 
-	index += 4;
-	data += 4;
-	size -= 4;
+	/* Split the first DWORD if the byte_en is not 0xff */
+	if (byen != BYTE_EN_DWORD) {
+		ret = set_registers(tp, index, type | byen, 4, data);
+		if (ret < 0)
+			goto error1;
 
-	if (size) {
+		index += 4;
+		data += 4;
 		size -= 4;
+	}
+
+	if (size) {
+		byen = byteen_end | (byteen_end >> 4);
+
+		/* Split the last DWORD if the byte_en is not 0xff */
+		if (byen != BYTE_EN_DWORD)
+			size -= 4;
 
 		while (size) {
 			if (size > limit) {
@@ -1350,10 +1358,9 @@ static int generic_ocp_write(struct r8152 *tp, u16 index, u16 byteen,
 			}
 		}
 
-		byen = byteen_end | (byteen_end >> 4);
-		ret = set_registers(tp, index, type | byen, 4, data);
-		if (ret < 0)
-			goto error1;
+		/* Set the last DWORD */
+		if (byen != BYTE_EN_DWORD)
+			ret = set_registers(tp, index, type | byen, 4, data);
 	}
 
 error1:
-- 
GitLab


From e5c266a61186b462c388c53a3564c375e72f2244 Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 26 Jul 2023 11:08:08 +0800
Subject: [PATCH 0645/1806] r8152: set bp in bulk

PLA_BP_0 ~ PLA_BP_15 (0xfc28 ~ 0xfc46) are continuous registers, so we
could combine the control transfers into one control transfer.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Link: https://lore.kernel.org/r/20230726030808.9093-419-nic_swsd@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c | 75 ++++++++++++++---------------------------
 1 file changed, 25 insertions(+), 50 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index f6578a99dbac4..db9897e825b45 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3978,29 +3978,10 @@ static void rtl_reset_bmu(struct r8152 *tp)
 /* Clear the bp to stop the firmware before loading a new one */
 static void rtl_clear_bp(struct r8152 *tp, u16 type)
 {
-	switch (tp->version) {
-	case RTL_VER_01:
-	case RTL_VER_02:
-	case RTL_VER_07:
-		break;
-	case RTL_VER_03:
-	case RTL_VER_04:
-	case RTL_VER_05:
-	case RTL_VER_06:
-		ocp_write_byte(tp, type, PLA_BP_EN, 0);
-		break;
-	case RTL_VER_14:
-		ocp_write_word(tp, type, USB_BP2_EN, 0);
+	u16 bp[16] = {0};
+	u16 bp_num;
 
-		ocp_write_word(tp, type, USB_BP_8, 0);
-		ocp_write_word(tp, type, USB_BP_9, 0);
-		ocp_write_word(tp, type, USB_BP_10, 0);
-		ocp_write_word(tp, type, USB_BP_11, 0);
-		ocp_write_word(tp, type, USB_BP_12, 0);
-		ocp_write_word(tp, type, USB_BP_13, 0);
-		ocp_write_word(tp, type, USB_BP_14, 0);
-		ocp_write_word(tp, type, USB_BP_15, 0);
-		break;
+	switch (tp->version) {
 	case RTL_VER_08:
 	case RTL_VER_09:
 	case RTL_VER_10:
@@ -4008,32 +3989,31 @@ static void rtl_clear_bp(struct r8152 *tp, u16 type)
 	case RTL_VER_12:
 	case RTL_VER_13:
 	case RTL_VER_15:
-	default:
 		if (type == MCU_TYPE_USB) {
 			ocp_write_word(tp, MCU_TYPE_USB, USB_BP2_EN, 0);
-
-			ocp_write_word(tp, MCU_TYPE_USB, USB_BP_8, 0);
-			ocp_write_word(tp, MCU_TYPE_USB, USB_BP_9, 0);
-			ocp_write_word(tp, MCU_TYPE_USB, USB_BP_10, 0);
-			ocp_write_word(tp, MCU_TYPE_USB, USB_BP_11, 0);
-			ocp_write_word(tp, MCU_TYPE_USB, USB_BP_12, 0);
-			ocp_write_word(tp, MCU_TYPE_USB, USB_BP_13, 0);
-			ocp_write_word(tp, MCU_TYPE_USB, USB_BP_14, 0);
-			ocp_write_word(tp, MCU_TYPE_USB, USB_BP_15, 0);
-		} else {
-			ocp_write_byte(tp, MCU_TYPE_PLA, PLA_BP_EN, 0);
+			bp_num = 16;
+			break;
 		}
+		fallthrough;
+	case RTL_VER_03:
+	case RTL_VER_04:
+	case RTL_VER_05:
+	case RTL_VER_06:
+		ocp_write_byte(tp, type, PLA_BP_EN, 0);
+		fallthrough;
+	case RTL_VER_01:
+	case RTL_VER_02:
+	case RTL_VER_07:
+		bp_num = 8;
+		break;
+	case RTL_VER_14:
+	default:
+		ocp_write_word(tp, type, USB_BP2_EN, 0);
+		bp_num = 16;
 		break;
 	}
 
-	ocp_write_word(tp, type, PLA_BP_0, 0);
-	ocp_write_word(tp, type, PLA_BP_1, 0);
-	ocp_write_word(tp, type, PLA_BP_2, 0);
-	ocp_write_word(tp, type, PLA_BP_3, 0);
-	ocp_write_word(tp, type, PLA_BP_4, 0);
-	ocp_write_word(tp, type, PLA_BP_5, 0);
-	ocp_write_word(tp, type, PLA_BP_6, 0);
-	ocp_write_word(tp, type, PLA_BP_7, 0);
+	generic_ocp_write(tp, PLA_BP_0, BYTE_EN_DWORD, bp_num << 1, bp, type);
 
 	/* wait 3 ms to make sure the firmware is stopped */
 	usleep_range(3000, 6000);
@@ -5007,10 +4987,9 @@ static void rtl8152_fw_phy_nc_apply(struct r8152 *tp, struct fw_phy_nc *phy)
 
 static void rtl8152_fw_mac_apply(struct r8152 *tp, struct fw_mac *mac)
 {
-	u16 bp_en_addr, bp_index, type, bp_num, fw_ver_reg;
+	u16 bp_en_addr, type, fw_ver_reg;
 	u32 length;
 	u8 *data;
-	int i;
 
 	switch (__le32_to_cpu(mac->blk_hdr.type)) {
 	case RTL_FW_PLA:
@@ -5052,12 +5031,8 @@ static void rtl8152_fw_mac_apply(struct r8152 *tp, struct fw_mac *mac)
 	ocp_write_word(tp, type, __le16_to_cpu(mac->bp_ba_addr),
 		       __le16_to_cpu(mac->bp_ba_value));
 
-	bp_index = __le16_to_cpu(mac->bp_start);
-	bp_num = __le16_to_cpu(mac->bp_num);
-	for (i = 0; i < bp_num; i++) {
-		ocp_write_word(tp, type, bp_index, __le16_to_cpu(mac->bp[i]));
-		bp_index += 2;
-	}
+	generic_ocp_write(tp, __le16_to_cpu(mac->bp_start), BYTE_EN_DWORD,
+			  __le16_to_cpu(mac->bp_num) << 1, mac->bp, type);
 
 	bp_en_addr = __le16_to_cpu(mac->bp_en_addr);
 	if (bp_en_addr)
-- 
GitLab


From 61c5145317a23b3ee03d3aa01d46df57d75e4dee Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 26 Jul 2023 22:38:16 +0800
Subject: [PATCH 0646/1806] bonding: 3ad: Remove unused declaration
 bond_3ad_update_lacp_active()

This is not used since commit 3a755cd8b7c6 ("bonding: add new option lacp_active")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://lore.kernel.org/r/20230726143816.15280-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/bond_3ad.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h
index a016f275cb016..c5e57c6bd8736 100644
--- a/include/net/bond_3ad.h
+++ b/include/net/bond_3ad.h
@@ -301,7 +301,6 @@ int  __bond_3ad_get_active_agg_info(struct bonding *bond,
 int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
 			 struct slave *slave);
 int bond_3ad_set_carrier(struct bonding *bond);
-void bond_3ad_update_lacp_active(struct bonding *bond);
 void bond_3ad_update_lacp_rate(struct bonding *bond);
 void bond_3ad_update_ad_actor_settings(struct bonding *bond);
 int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats);
-- 
GitLab


From c88c157d25d96ed760b91837aec81f19c44b0bf3 Mon Sep 17 00:00:00 2001
From: Chen Jiahao <chenjiahao16@huawei.com>
Date: Thu, 27 Jul 2023 19:55:51 +0800
Subject: [PATCH 0647/1806] net: bcmasp: Clean up redundant dev_err_probe()

Referring to platform_get_irq()'s definition, the return value has
already been checked, error message also been printed via
dev_err_probe() if ret < 0. Calling dev_err_probe() one more time
outside platform_get_irq() is obviously redundant.

Removing dev_err_probe() outside platform_get_irq() to clean up
above problem.

Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Justin Chen <justin.chen@broadcom.com>
Link: https://lore.kernel.org/r/20230727115551.2655840-1-chenjiahao16@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index a9984efff6d18..eb35ced1c8ba7 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -1232,7 +1232,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 
 	priv->irq = platform_get_irq(pdev, 0);
 	if (priv->irq <= 0)
-		return dev_err_probe(dev, -EINVAL, "invalid interrupt\n");
+		return -EINVAL;
 
 	priv->clk = devm_clk_get_optional_enabled(dev, "sw_asp");
 	if (IS_ERR(priv->clk))
-- 
GitLab


From 58ea461b690cb093ef3f502e51adbb03d2ea61d8 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 27 Jul 2023 09:02:26 +0200
Subject: [PATCH 0648/1806] net: ethernet: mtk_eth_soc: enable page_pool
 support for MT7988 SoC

In order to recycle pages, enable page_pool allocator for MT7988 SoC.

Tested-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/fd4e8693980e47385a543e7b002eec0b88bd09df.1690440675.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 38f39be04eaed..bd1e4921c7b4e 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1674,7 +1674,7 @@ static void mtk_update_rx_cpu_idx(struct mtk_eth *eth)
 
 static bool mtk_page_pool_enabled(struct mtk_eth *eth)
 {
-	return eth->soc->version == 2;
+	return mtk_is_netsys_v2_or_greater(eth);
 }
 
 static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth,
-- 
GitLab


From 88efedf517e69a4b12e4dd40c44c2e298f53fa83 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 27 Jul 2023 09:07:28 +0200
Subject: [PATCH 0649/1806] net: ethernet: mtk_eth_soc: enable nft hw
 flowtable_offload for MT7988 SoC

Enable hw Packet Process Engine (PPE) for MT7988 SoC.

Tested-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/5e86341b0220a49620dadc02d77970de5ded9efc.1690441576.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c |  3 +++
 drivers/net/ethernet/mediatek/mtk_ppe.c     | 19 +++++++++++++++----
 drivers/net/ethernet/mediatek/mtk_ppe.h     | 19 ++++++++++++++++++-
 3 files changed, 36 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index bd1e4921c7b4e..05be702f19c5e 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -5062,6 +5062,9 @@ static const struct mtk_soc_data mt7988_data = {
 	.required_clks = MT7988_CLKS_BITMAP,
 	.required_pctl = false,
 	.version = 3,
+	.offload_version = 2,
+	.hash_offset = 4,
+	.foe_entry_size = MTK_FOE_ENTRY_V3_SIZE,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma_v2),
 		.rxd_size = sizeof(struct mtk_rx_dma_v2),
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c
index 2f0e682449ef6..bf1ecb0c1c109 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.c
@@ -423,13 +423,22 @@ int mtk_foe_entry_set_wdma(struct mtk_eth *eth, struct mtk_foe_entry *entry,
 	struct mtk_foe_mac_info *l2 = mtk_foe_entry_l2(eth, entry);
 	u32 *ib2 = mtk_foe_entry_ib2(eth, entry);
 
-	if (mtk_is_netsys_v2_or_greater(eth)) {
+	switch (eth->soc->version) {
+	case 3:
+		*ib2 &= ~MTK_FOE_IB2_PORT_MG_V2;
+		*ib2 |=  FIELD_PREP(MTK_FOE_IB2_RX_IDX, txq) |
+			 MTK_FOE_IB2_WDMA_WINFO_V2;
+		l2->w3info = FIELD_PREP(MTK_FOE_WINFO_WCID_V3, wcid) |
+			     FIELD_PREP(MTK_FOE_WINFO_BSS_V3, bss);
+		break;
+	case 2:
 		*ib2 &= ~MTK_FOE_IB2_PORT_MG_V2;
 		*ib2 |=  FIELD_PREP(MTK_FOE_IB2_RX_IDX, txq) |
 			 MTK_FOE_IB2_WDMA_WINFO_V2;
 		l2->winfo = FIELD_PREP(MTK_FOE_WINFO_WCID, wcid) |
 			    FIELD_PREP(MTK_FOE_WINFO_BSS, bss);
-	} else {
+		break;
+	default:
 		*ib2 &= ~MTK_FOE_IB2_PORT_MG;
 		*ib2 |= MTK_FOE_IB2_WDMA_WINFO;
 		if (wdma_idx)
@@ -437,6 +446,7 @@ int mtk_foe_entry_set_wdma(struct mtk_eth *eth, struct mtk_foe_entry *entry,
 		l2->vlan2 = FIELD_PREP(MTK_FOE_VLAN2_WINFO_BSS, bss) |
 			    FIELD_PREP(MTK_FOE_VLAN2_WINFO_WCID, wcid) |
 			    FIELD_PREP(MTK_FOE_VLAN2_WINFO_RING, txq);
+		break;
 	}
 
 	return 0;
@@ -964,8 +974,7 @@ void mtk_ppe_start(struct mtk_ppe *ppe)
 	mtk_ppe_init_foe_table(ppe);
 	ppe_w32(ppe, MTK_PPE_TB_BASE, ppe->foe_phys);
 
-	val = MTK_PPE_TB_CFG_ENTRY_80B |
-	      MTK_PPE_TB_CFG_AGE_NON_L4 |
+	val = MTK_PPE_TB_CFG_AGE_NON_L4 |
 	      MTK_PPE_TB_CFG_AGE_UNBIND |
 	      MTK_PPE_TB_CFG_AGE_TCP |
 	      MTK_PPE_TB_CFG_AGE_UDP |
@@ -981,6 +990,8 @@ void mtk_ppe_start(struct mtk_ppe *ppe)
 			 MTK_PPE_ENTRIES_SHIFT);
 	if (mtk_is_netsys_v2_or_greater(ppe->eth))
 		val |= MTK_PPE_TB_CFG_INFO_SEL;
+	if (!mtk_is_netsys_v3_or_greater(ppe->eth))
+		val |= MTK_PPE_TB_CFG_ENTRY_80B;
 	ppe_w32(ppe, MTK_PPE_TB_CFG, val);
 
 	ppe_w32(ppe, MTK_PPE_IP_PROTO_CHK,
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h
index fb6bf58172d98..e3d0ec72bc699 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.h
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.h
@@ -85,6 +85,17 @@ enum {
 #define MTK_FOE_WINFO_BSS		GENMASK(5, 0)
 #define MTK_FOE_WINFO_WCID		GENMASK(15, 6)
 
+#define MTK_FOE_WINFO_BSS_V3		GENMASK(23, 16)
+#define MTK_FOE_WINFO_WCID_V3		GENMASK(15, 0)
+
+#define MTK_FOE_WINFO_PAO_USR_INFO	GENMASK(15, 0)
+#define MTK_FOE_WINFO_PAO_TID		GENMASK(19, 16)
+#define MTK_FOE_WINFO_PAO_IS_FIXEDRATE	BIT(20)
+#define MTK_FOE_WINFO_PAO_IS_PRIOR	BIT(21)
+#define MTK_FOE_WINFO_PAO_IS_SP		BIT(22)
+#define MTK_FOE_WINFO_PAO_HF		BIT(23)
+#define MTK_FOE_WINFO_PAO_AMSDU_EN	BIT(24)
+
 enum {
 	MTK_FOE_STATE_INVALID,
 	MTK_FOE_STATE_UNBIND,
@@ -106,8 +117,13 @@ struct mtk_foe_mac_info {
 	u16 pppoe_id;
 	u16 src_mac_lo;
 
+	/* netsys_v2 */
 	u16 minfo;
 	u16 winfo;
+
+	/* netsys_v3 */
+	u32 w3info;
+	u32 wpao;
 };
 
 /* software-only entry type */
@@ -218,6 +234,7 @@ struct mtk_foe_ipv6_6rd {
 
 #define MTK_FOE_ENTRY_V1_SIZE	80
 #define MTK_FOE_ENTRY_V2_SIZE	96
+#define MTK_FOE_ENTRY_V3_SIZE	128
 
 struct mtk_foe_entry {
 	u32 ib1;
@@ -228,7 +245,7 @@ struct mtk_foe_entry {
 		struct mtk_foe_ipv4_dslite dslite;
 		struct mtk_foe_ipv6 ipv6;
 		struct mtk_foe_ipv6_6rd ipv6_6rd;
-		u32 data[23];
+		u32 data[31];
 	};
 };
 
-- 
GitLab


From 64a37272fa5fb2d951ebd1a96fd42b045d64924c Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Thu, 27 Jul 2023 08:57:41 +0800
Subject: [PATCH 0650/1806] team: Remove NULL check before dev_{put, hold}

The call netdev_{put, hold} of dev_{put, hold} will check NULL,
so there is no need to check before using dev_{put, hold},
remove it to silence the warning:

./drivers/net/team/team.c:2325:3-10: WARNING: NULL check before dev_{put, hold} functions is not needed.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=5991
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index d3dc22509ea58..bc50fc3f69135 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2321,8 +2321,7 @@ static struct team *team_nl_team_get(struct genl_info *info)
 	ifindex = nla_get_u32(info->attrs[TEAM_ATTR_TEAM_IFINDEX]);
 	dev = dev_get_by_index(net, ifindex);
 	if (!dev || dev->netdev_ops != &team_netdev_ops) {
-		if (dev)
-			dev_put(dev);
+		dev_put(dev);
 		return NULL;
 	}
 
-- 
GitLab


From fb213ecbb8ac56b2d5569737f59126e91f87829a Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sat, 29 Jul 2023 17:42:51 -0700
Subject: [PATCH 0651/1806] docs/bpf: Fix malformed documentation

Two issues are fixed:
  1. Malformed table due to newly-introduced BPF_MOVSX
  2. Missing reference link for ``Sign-extension load operations``

Fixes: 245d4c40c09b ("docs/bpf: Add documentation for new instructions")
Cc: bpf@ietf.org
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202307291840.Cqhj7uox-lkp@intel.com/
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230730004251.381307-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/standardization/instruction-set.rst   | 45 ++++++++++---------
 1 file changed, 24 insertions(+), 21 deletions(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index fb8154cedd841..655494ac7af6a 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -154,27 +154,27 @@ otherwise identical operations.
 The 'code' field encodes the operation as below, where 'src' and 'dst' refer
 to the values of the source and destination registers, respectively.
 
-========  =====  =======  ==========================================================
-code      value  offset   description
-========  =====  =======  ==========================================================
-BPF_ADD   0x00   0        dst += src
-BPF_SUB   0x10   0        dst -= src
-BPF_MUL   0x20   0        dst \*= src
-BPF_DIV   0x30   0        dst = (src != 0) ? (dst / src) : 0
-BPF_SDIV  0x30   1        dst = (src != 0) ? (dst s/ src) : 0
-BPF_OR    0x40   0        dst \|= src
-BPF_AND   0x50   0        dst &= src
-BPF_LSH   0x60   0        dst <<= (src & mask)
-BPF_RSH   0x70   0        dst >>= (src & mask)
-BPF_NEG   0x80   0        dst = -dst
-BPF_MOD   0x90   0        dst = (src != 0) ? (dst % src) : dst
-BPF_SMOD  0x90   1        dst = (src != 0) ? (dst s% src) : dst
-BPF_XOR   0xa0   0        dst ^= src
-BPF_MOV   0xb0   0        dst = src
-BPF_MOVSX 0xb0   8/16/32  dst = (s8,s16,s32)src
-BPF_ARSH  0xc0   0        sign extending dst >>= (src & mask)
-BPF_END   0xd0   0        byte swap operations (see `Byte swap instructions`_ below)
-========  =====  =======  ==========================================================
+=========  =====  =======  ==========================================================
+code       value  offset   description
+=========  =====  =======  ==========================================================
+BPF_ADD    0x00   0        dst += src
+BPF_SUB    0x10   0        dst -= src
+BPF_MUL    0x20   0        dst \*= src
+BPF_DIV    0x30   0        dst = (src != 0) ? (dst / src) : 0
+BPF_SDIV   0x30   1        dst = (src != 0) ? (dst s/ src) : 0
+BPF_OR     0x40   0        dst \|= src
+BPF_AND    0x50   0        dst &= src
+BPF_LSH    0x60   0        dst <<= (src & mask)
+BPF_RSH    0x70   0        dst >>= (src & mask)
+BPF_NEG    0x80   0        dst = -dst
+BPF_MOD    0x90   0        dst = (src != 0) ? (dst % src) : dst
+BPF_SMOD   0x90   1        dst = (src != 0) ? (dst s% src) : dst
+BPF_XOR    0xa0   0        dst ^= src
+BPF_MOV    0xb0   0        dst = src
+BPF_MOVSX  0xb0   8/16/32  dst = (s8,s16,s32)src
+BPF_ARSH   0xc0   0        sign extending dst >>= (src & mask)
+BPF_END    0xd0   0        byte swap operations (see `Byte swap instructions`_ below)
+=========  =====  =======  ==========================================================
 
 Underflow and overflow are allowed during arithmetic operations, meaning
 the 64-bit or 32-bit value will wrap. If eBPF program execution would
@@ -397,6 +397,9 @@ instructions that transfer data between a register and memory.
 Where size is one of: ``BPF_B``, ``BPF_H``, ``BPF_W``, or ``BPF_DW`` and
 'unsigned size' is one of u8, u16, u32 or u64.
 
+Sign-extension load operations
+------------------------------
+
 The ``BPF_MEMSX`` mode modifier is used to encode sign-extension load
 instructions that transfer data between a register and memory.
 
-- 
GitLab


From 2b3082c6ef3b0104d822f6f18d2afbe5fc9a5c2c Mon Sep 17 00:00:00 2001
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: Sat, 29 Jul 2023 04:52:15 +0530
Subject: [PATCH 0652/1806] net: flow_dissector: Use 64bits for used_keys

As 32bits of dissector->used_keys are exhausted,
increase the size to 64bits.

This is base change for ESP/AH flow dissector patch.
Please find patch and discussions at
https://lore.kernel.org/netdev/ZMDNjD46BvZ5zp5I@corigine.com/T/#t

Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Reviewed-by: Petr Machata <petrm@nvidia.com> # for mlxsw
Tested-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Martin Habets <habetsm.xilinx@gmail.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix_vsc9959.c        |  8 +--
 drivers/net/dsa/sja1105/sja1105_flower.c      |  8 +--
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c  |  6 +-
 .../ethernet/chelsio/cxgb4/cxgb4_tc_flower.c  | 18 ++---
 .../freescale/dpaa2/dpaa2-switch-flower.c     | 22 +++---
 .../net/ethernet/freescale/enetc/enetc_qos.c  |  8 +--
 .../hisilicon/hns3/hns3pf/hclge_main.c        | 16 ++---
 drivers/net/ethernet/intel/i40e/i40e_main.c   | 18 ++---
 drivers/net/ethernet/intel/iavf/iavf_main.c   | 18 ++---
 drivers/net/ethernet/intel/ice/ice_tc_lib.c   | 44 ++++++------
 drivers/net/ethernet/intel/igb/igb_main.c     |  8 +--
 .../ethernet/marvell/octeontx2/nic/otx2_tc.c  | 18 ++---
 .../marvell/prestera/prestera_flower.c        | 20 +++---
 .../mellanox/mlx5/core/en/tc/ct_fs_smfs.c     | 25 ++++---
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 44 ++++++------
 .../ethernet/mellanox/mlxsw/spectrum_flower.c | 22 +++---
 .../microchip/lan966x/lan966x_tc_flower.c     |  4 +-
 .../microchip/sparx5/sparx5_tc_flower.c       |  4 +-
 drivers/net/ethernet/microchip/vcap/vcap_tc.c | 18 ++---
 drivers/net/ethernet/microchip/vcap/vcap_tc.h |  2 +-
 drivers/net/ethernet/mscc/ocelot_flower.c     | 28 ++++----
 .../ethernet/netronome/nfp/flower/conntrack.c | 43 ++++++------
 .../ethernet/netronome/nfp/flower/offload.c   | 64 +++++++++---------
 .../net/ethernet/qlogic/qede/qede_filter.c    | 12 ++--
 drivers/net/ethernet/sfc/tc.c                 | 67 ++++++++++---------
 .../stmicro/stmmac/stmmac_selftests.c         |  6 +-
 drivers/net/ethernet/ti/am65-cpsw-qos.c       |  6 +-
 drivers/net/ethernet/ti/cpsw_priv.c           |  6 +-
 include/net/flow_dissector.h                  |  5 +-
 net/core/flow_dissector.c                     |  2 +-
 net/ethtool/ioctl.c                           | 16 ++---
 net/netfilter/nf_flow_table_offload.c         | 22 +++---
 net/netfilter/nf_tables_offload.c             | 13 ++--
 net/netfilter/nft_cmp.c                       |  2 +-
 34 files changed, 317 insertions(+), 306 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index dce3548dcd057..4a6e52929d25a 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1746,10 +1746,10 @@ static int vsc9959_stream_identify(struct flow_cls_offload *f,
 	struct flow_dissector *dissector = rule->match.dissector;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS)))
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS)))
 		return -EOPNOTSUPP;
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
diff --git a/drivers/net/dsa/sja1105/sja1105_flower.c b/drivers/net/dsa/sja1105/sja1105_flower.c
index fad5afe3819cc..9e8ca182c722b 100644
--- a/drivers/net/dsa/sja1105/sja1105_flower.c
+++ b/drivers/net/dsa/sja1105/sja1105_flower.c
@@ -205,10 +205,10 @@ static int sja1105_flower_parse_key(struct sja1105_private *priv,
 	u16 pcp = U16_MAX;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS))) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Unsupported keys used");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index d8afcf8d6b30e..38d89d80b4a9c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -373,9 +373,9 @@ static int bnxt_tc_parse_flow(struct bnxt *bp,
 	struct flow_dissector *dissector = rule->match.dissector;
 
 	/* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */
-	if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 ||
-	    (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) == 0) {
-		netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x\n",
+	if ((dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) == 0 ||
+	    (dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC)) == 0) {
+		netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%llx\n",
 			    dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index d3541159487dd..72ac4a34424b9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -313,15 +313,15 @@ static int cxgb4_validate_flow_match(struct net_device *dev,
 	u16 ethtype_key = 0;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_IP))) {
-		netdev_warn(dev, "Unsupported key used: 0x%x\n",
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IP))) {
+		netdev_warn(dev, "Unsupported key used: 0x%llx\n",
 			    dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
index c39b866e2582d..4798fb7fe35d1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
@@ -17,14 +17,14 @@ static int dpaa2_switch_flower_parse_key(struct flow_cls_offload *cls,
 	struct dpsw_acl_fields *acl_h, *acl_m;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_IP) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS))) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Unsupported keys used");
 		return -EOPNOTSUPP;
@@ -539,9 +539,9 @@ static int dpaa2_switch_flower_parse_mirror_key(struct flow_cls_offload *cls,
 	int ret = -EOPNOTSUPP;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN))) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Mirroring is supported only per VLAN");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
index 270cbd5e8684c..2513b44056c19 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
@@ -483,13 +483,13 @@ struct enetc_psfp {
 static struct actions_fwd enetc_act_fwd[] = {
 	{
 		BIT(FLOW_ACTION_GATE),
-		BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS),
+		BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS),
 		FILTER_ACTION_TYPE_PSFP
 	},
 	{
 		BIT(FLOW_ACTION_POLICE) |
 		BIT(FLOW_ACTION_GATE),
-		BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS),
+		BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS),
 		FILTER_ACTION_TYPE_PSFP
 	},
 	/* example for ACL actions */
@@ -1069,8 +1069,8 @@ revert_sid:
 	return err;
 }
 
-static struct actions_fwd *enetc_check_flow_actions(u64 acts,
-						    unsigned int inputkeys)
+static struct actions_fwd *
+enetc_check_flow_actions(u64 acts, unsigned long long inputkeys)
 {
 	int i;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index bf675c15fbb9c..83ab89f442502 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7315,14 +7315,14 @@ static int hclge_parse_cls_flower(struct hclge_dev *hdev,
 	struct flow_dissector *dissector = flow->match.dissector;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS))) {
-		dev_err(&hdev->pdev->dev, "unsupported key set: %#x\n",
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS))) {
+		dev_err(&hdev->pdev->dev, "unsupported key set: %#llx\n",
 			dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 982ae70c51e8c..3d0d6974c2a79 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -8525,15 +8525,15 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 	u8 field_flags = 0;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
-		dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n",
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
+		dev_err(&pf->pdev->dev, "Unsupported key used: 0x%llx\n",
 			dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 9610ca770349e..7b300c86ceda7 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3744,15 +3744,15 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 	struct virtchnl_filter *vf = &filter->f;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
-		dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n",
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
+		dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%llx\n",
 			dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index 4a34ef5f58d36..38547db1ec4ec 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -1343,24 +1343,24 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 	dissector = rule->match.dissector;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_CVLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) |
-	      BIT(FLOW_DISSECTOR_KEY_IP) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_IP) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_PPPOE) |
-	      BIT(FLOW_DISSECTOR_KEY_L2TPV3))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PPPOE) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_L2TPV3))) {
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported key used");
 		return -EOPNOTSUPP;
 	}
@@ -1382,10 +1382,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 		 */
 		headers = &fltr->inner_headers;
 	} else if (dissector->used_keys &
-		  (BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
-		   BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
-		   BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
-		   BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))) {
+		  (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
+		   BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
+		   BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+		   BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) {
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel");
 		return -EOPNOTSUPP;
 	} else {
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 9a2561409b06f..9f63a10c6f809 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2615,10 +2615,10 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter,
 	struct netlink_ext_ack *extack = f->common.extack;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN))) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Unsupported key used, only BASIC, CONTROL, ETH_ADDRS and VLAN are supported");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 0915a0121316a..5a44e9b96fc06 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -454,15 +454,15 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 	dissector = rule->match.dissector;
 
 	if ((dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_IP))))  {
-		netdev_info(nic->netdev, "unsupported flow used key 0x%x",
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IP))))  {
+		netdev_info(nic->netdev, "unsupported flow used key 0x%llx",
 			    dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.c b/drivers/net/ethernet/marvell/prestera/prestera_flower.c
index 3e20e71b0f81a..8b9455d8a4f7a 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_flower.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.c
@@ -202,16 +202,16 @@ static int prestera_flower_parse(struct prestera_flow_block *block,
 	int err;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_META) |
-	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_ICMP) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS_RANGE) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_META) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ICMP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS_RANGE) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN))) {
 		NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported key");
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
index 2b80fe73549d2..8c531f4ec9129 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
@@ -221,16 +221,21 @@ mlx5_ct_fs_smfs_destroy(struct mlx5_ct_fs *fs)
 }
 
 static inline bool
-mlx5_tc_ct_valid_used_dissector_keys(const u32 used_keys)
+mlx5_tc_ct_valid_used_dissector_keys(const u64 used_keys)
 {
-#define DISS_BIT(name) BIT(FLOW_DISSECTOR_KEY_ ## name)
-	const u32 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) | DISS_BIT(META);
-	const u32 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) | DISS_BIT(PORTS) | DISS_BIT(TCP);
-	const u32 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) | DISS_BIT(PORTS) | DISS_BIT(TCP);
-	const u32 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) | DISS_BIT(PORTS);
-	const u32 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) | DISS_BIT(PORTS);
-	const u32 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS);
-	const u32 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS);
+#define DISS_BIT(name) BIT_ULL(FLOW_DISSECTOR_KEY_ ## name)
+	const u64 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) |
+				DISS_BIT(META);
+	const u64 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) |
+				DISS_BIT(PORTS) | DISS_BIT(TCP);
+	const u64 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) |
+				DISS_BIT(PORTS) | DISS_BIT(TCP);
+	const u64 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) |
+				DISS_BIT(PORTS);
+	const u64 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) |
+				 DISS_BIT(PORTS);
+	const u64 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS);
+	const u64 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS);
 
 	return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp ||
 		used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre);
@@ -247,7 +252,7 @@ mlx5_ct_fs_smfs_ct_validate_flow_rule(struct mlx5_ct_fs *fs, struct flow_rule *f
 	struct flow_match_tcp tcp;
 
 	if (!mlx5_tc_ct_valid_used_dissector_keys(flow_rule->match.dissector->used_keys)) {
-		ct_dbg("rule uses unexpected dissectors (0x%08x)",
+		ct_dbg("rule uses unexpected dissectors (0x%016llx)",
 		       flow_rule->match.dissector->used_keys);
 		return false;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 507825a1abc8b..dfd282319753f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2590,29 +2590,29 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	match_level = outer_match_level;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_META) |
-	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_CVLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_PORTS)	|
-	      BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_TCP) |
-	      BIT(FLOW_DISSECTOR_KEY_IP)  |
-	      BIT(FLOW_DISSECTOR_KEY_CT) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_IP) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) |
-	      BIT(FLOW_DISSECTOR_KEY_ICMP) |
-	      BIT(FLOW_DISSECTOR_KEY_MPLS))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_META) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS)	|
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_TCP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IP)  |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CT) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ICMP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_MPLS))) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported key");
-		netdev_dbg(priv->netdev, "Unsupported key used: 0x%x\n",
+		netdev_dbg(priv->netdev, "Unsupported key used: 0x%llx\n",
 			   dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 8329100479b3c..af3f57d017ec0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -558,17 +558,17 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_META) |
-	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS_RANGE) |
-	      BIT(FLOW_DISSECTOR_KEY_TCP) |
-	      BIT(FLOW_DISSECTOR_KEY_IP) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_META) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS_RANGE) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_TCP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN))) {
 		dev_err(mlxsw_sp->bus_info->dev, "Unsupported key\n");
 		NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported key");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c
index 96b3def6c4741..d696cf9dbd198 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c
@@ -75,7 +75,7 @@ lan966x_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st)
 			goto out;
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL);
 
 	return err;
 
@@ -172,7 +172,7 @@ lan966x_tc_flower_handler_basic_usage(struct vcap_tc_flower_parse_usage *st)
 		}
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_BASIC);
 	return err;
 out:
 	NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_proto parse error");
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
index 3f87a5285a6de..906299ad84251 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
@@ -126,7 +126,7 @@ sparx5_tc_flower_handler_basic_usage(struct vcap_tc_flower_parse_usage *st)
 		}
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_BASIC);
 
 	return err;
 
@@ -175,7 +175,7 @@ sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st)
 			goto out;
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL);
 
 	return err;
 
diff --git a/drivers/net/ethernet/microchip/vcap/vcap_tc.c b/drivers/net/ethernet/microchip/vcap/vcap_tc.c
index 09abe7944af61..27e2dffb65e69 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_tc.c
+++ b/drivers/net/ethernet/microchip/vcap/vcap_tc.c
@@ -50,7 +50,7 @@ int vcap_tc_flower_handler_ethaddr_usage(struct vcap_tc_flower_parse_usage *st)
 			goto out;
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS);
 
 	return err;
 
@@ -86,7 +86,7 @@ int vcap_tc_flower_handler_ipv4_usage(struct vcap_tc_flower_parse_usage *st)
 		}
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS);
 
 	return err;
 
@@ -124,7 +124,7 @@ int vcap_tc_flower_handler_ipv6_usage(struct vcap_tc_flower_parse_usage *st)
 				goto out;
 		}
 	}
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS);
 	return err;
 out:
 	NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv6_addr parse error");
@@ -158,7 +158,7 @@ int vcap_tc_flower_handler_portnum_usage(struct vcap_tc_flower_parse_usage *st)
 			goto out;
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_PORTS);
 
 	return err;
 
@@ -201,7 +201,7 @@ int vcap_tc_flower_handler_cvlan_usage(struct vcap_tc_flower_parse_usage *st)
 			goto out;
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN);
 
 	return 0;
 out:
@@ -238,7 +238,7 @@ int vcap_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st,
 	if (mt.mask->vlan_tpid)
 		st->tpid = be16_to_cpu(mt.key->vlan_tpid);
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN);
 
 	return 0;
 out:
@@ -313,7 +313,7 @@ int vcap_tc_flower_handler_tcp_usage(struct vcap_tc_flower_parse_usage *st)
 			goto out;
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_TCP);
 
 	return err;
 
@@ -376,7 +376,7 @@ int vcap_tc_flower_handler_arp_usage(struct vcap_tc_flower_parse_usage *st)
 			goto out;
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ARP);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_ARP);
 
 	return 0;
 
@@ -401,7 +401,7 @@ int vcap_tc_flower_handler_ip_usage(struct vcap_tc_flower_parse_usage *st)
 			goto out;
 	}
 
-	st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IP);
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_IP);
 
 	return err;
 
diff --git a/drivers/net/ethernet/microchip/vcap/vcap_tc.h b/drivers/net/ethernet/microchip/vcap/vcap_tc.h
index 071f892f9aa46..49b02d0329066 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_tc.h
+++ b/drivers/net/ethernet/microchip/vcap/vcap_tc.h
@@ -14,7 +14,7 @@ struct vcap_tc_flower_parse_usage {
 	u16 l3_proto;
 	u8 l4_proto;
 	u16 tpid;
-	unsigned int used_keys;
+	unsigned long long used_keys;
 };
 
 int vcap_tc_flower_handler_ethaddr_usage(struct vcap_tc_flower_parse_usage *st);
diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index e0916afcddfb9..33b438c6aec5b 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -581,14 +581,14 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress,
 	int ret;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_META) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_META) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS))) {
 		return -EOPNOTSUPP;
 	}
 
@@ -641,12 +641,12 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress,
 		 * then just bail out
 		 */
 		if ((dissector->used_keys &
-		    (BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-		     BIT(FLOW_DISSECTOR_KEY_BASIC) |
-		     BIT(FLOW_DISSECTOR_KEY_CONTROL))) !=
-		    (BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-		     BIT(FLOW_DISSECTOR_KEY_BASIC) |
-		     BIT(FLOW_DISSECTOR_KEY_CONTROL)))
+		    (BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+		     BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+		     BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL))) !=
+		    (BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+		     BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+		     BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)))
 			return -EOPNOTSUPP;
 
 		flow_rule_match_eth_addrs(rule, &match);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
index 73032173ac4eb..2643c4b3ff1f4 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
@@ -61,7 +61,7 @@ bool is_pre_ct_flow(struct flow_cls_offload *flow)
 	struct flow_match_ct ct;
 	int i;
 
-	if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) {
+	if (dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CT)) {
 		flow_rule_match_ct(rule, &ct);
 		if (ct.key->ct_state)
 			return false;
@@ -94,7 +94,7 @@ bool is_post_ct_flow(struct flow_cls_offload *flow)
 	struct flow_match_ct ct;
 	int i;
 
-	if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) {
+	if (dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CT)) {
 		flow_rule_match_ct(rule, &ct);
 		if (ct.key->ct_state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED)
 			return true;
@@ -236,10 +236,11 @@ static bool nfp_ct_merge_check_cannot_skip(struct nfp_fl_ct_flow_entry *entry1,
 static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			      struct nfp_fl_ct_flow_entry *entry2)
 {
-	unsigned int ovlp_keys = entry1->rule->match.dissector->used_keys &
-				 entry2->rule->match.dissector->used_keys;
+	unsigned long long ovlp_keys;
 	bool out, is_v6 = false;
 	u8 ip_proto = 0;
+	ovlp_keys = entry1->rule->match.dissector->used_keys &
+			entry2->rule->match.dissector->used_keys;
 	/* Temporary buffer for mangling keys, 64 is enough to cover max
 	 * struct size of key in various fields that may be mangled.
 	 * Supported fields to mangle:
@@ -257,7 +258,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 	/* Check the overlapped fields one by one, the unmasked part
 	 * should not conflict with each other.
 	 */
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) {
 		struct flow_match_control match1, match2;
 
 		flow_rule_match_control(entry1->rule, &match1);
@@ -267,7 +268,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC)) {
 		struct flow_match_basic match1, match2;
 
 		flow_rule_match_basic(entry1->rule, &match1);
@@ -289,7 +290,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 	 * will be do merge check when do nft and post ct merge,
 	 * so skip this ip merge check here.
 	 */
-	if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS)) &&
+	if ((ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS)) &&
 	    nfp_ct_merge_check_cannot_skip(entry1, entry2)) {
 		struct flow_match_ipv4_addrs match1, match2;
 
@@ -311,7 +312,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 	 * will be do merge check when do nft and post ct merge,
 	 * so skip this ip merge check here.
 	 */
-	if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS)) &&
+	if ((ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS)) &&
 	    nfp_ct_merge_check_cannot_skip(entry1, entry2)) {
 		struct flow_match_ipv6_addrs match1, match2;
 
@@ -333,7 +334,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 	 * will be do merge check when do nft and post ct merge,
 	 * so skip this tport merge check here.
 	 */
-	if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_PORTS)) &&
+	if ((ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_PORTS)) &&
 	    nfp_ct_merge_check_cannot_skip(entry1, entry2)) {
 		enum flow_action_mangle_base htype = FLOW_ACT_MANGLE_UNSPEC;
 		struct flow_match_ports match1, match2;
@@ -355,7 +356,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
 		struct flow_match_eth_addrs match1, match2;
 
 		flow_rule_match_eth_addrs(entry1->rule, &match1);
@@ -371,7 +372,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_VLAN)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN)) {
 		struct flow_match_vlan match1, match2;
 
 		flow_rule_match_vlan(entry1->rule, &match1);
@@ -381,7 +382,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_MPLS)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_MPLS)) {
 		struct flow_match_mpls match1, match2;
 
 		flow_rule_match_mpls(entry1->rule, &match1);
@@ -391,7 +392,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_TCP)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_TCP)) {
 		struct flow_match_tcp match1, match2;
 
 		flow_rule_match_tcp(entry1->rule, &match1);
@@ -401,7 +402,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IP)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_IP)) {
 		struct flow_match_ip match1, match2;
 
 		flow_rule_match_ip(entry1->rule, &match1);
@@ -413,7 +414,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID)) {
 		struct flow_match_enc_keyid match1, match2;
 
 		flow_rule_match_enc_keyid(entry1->rule, &match1);
@@ -423,7 +424,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
 		struct flow_match_ipv4_addrs match1, match2;
 
 		flow_rule_match_enc_ipv4_addrs(entry1->rule, &match1);
@@ -433,7 +434,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
 		struct flow_match_ipv6_addrs match1, match2;
 
 		flow_rule_match_enc_ipv6_addrs(entry1->rule, &match1);
@@ -443,7 +444,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
 		struct flow_match_control match1, match2;
 
 		flow_rule_match_enc_control(entry1->rule, &match1);
@@ -453,7 +454,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IP)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP)) {
 		struct flow_match_ip match1, match2;
 
 		flow_rule_match_enc_ip(entry1->rule, &match1);
@@ -463,7 +464,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
 			goto check_failed;
 	}
 
-	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_OPTS)) {
+	if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS)) {
 		struct flow_match_enc_opts match1, match2;
 
 		flow_rule_match_enc_opts(entry1->rule, &match1);
@@ -589,7 +590,7 @@ static int nfp_ct_check_meta(struct nfp_fl_ct_flow_entry *post_ct_entry,
 	int i;
 
 	ct_met = get_flow_act(nft_entry->rule, FLOW_ACTION_CT_METADATA);
-	if (ct_met && (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT))) {
+	if (ct_met && (dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CT))) {
 		u32 *act_lbl;
 
 		act_lbl = ct_met->ct_metadata.labels;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 18328eb7f5c33..c153f0575b924 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -24,43 +24,43 @@
 	 FLOW_DIS_FIRST_FRAG)
 
 #define NFP_FLOWER_WHITELIST_DISSECTOR \
-	(BIT(FLOW_DISSECTOR_KEY_CONTROL) | \
-	 BIT(FLOW_DISSECTOR_KEY_BASIC) | \
-	 BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | \
-	 BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | \
-	 BIT(FLOW_DISSECTOR_KEY_TCP) | \
-	 BIT(FLOW_DISSECTOR_KEY_PORTS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \
-	 BIT(FLOW_DISSECTOR_KEY_VLAN) | \
-	 BIT(FLOW_DISSECTOR_KEY_CVLAN) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_IP) | \
-	 BIT(FLOW_DISSECTOR_KEY_MPLS) | \
-	 BIT(FLOW_DISSECTOR_KEY_CT) | \
-	 BIT(FLOW_DISSECTOR_KEY_META) | \
-	 BIT(FLOW_DISSECTOR_KEY_IP))
+	(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_TCP) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_MPLS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_CT) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_META) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_IP))
 
 #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR \
-	(BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_IP))
+	(BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP))
 
 #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R \
-	(BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS))
+	(BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS))
 
 #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR_V6_R \
-	(BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS))
+	(BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
+	 BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS))
 
 #define NFP_FLOWER_MERGE_FIELDS \
 	(NFP_FLOWER_LAYER_PORT | \
@@ -1303,7 +1303,7 @@ static bool offload_pre_check(struct flow_cls_offload *flow)
 	struct flow_dissector *dissector = rule->match.dissector;
 	struct flow_match_ct ct;
 
-	if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) {
+	if (dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CT)) {
 		flow_rule_match_ct(rule, &ct);
 		/* Allow special case where CT match is all 0 */
 		if (memchr_inv(ct.key, 0, sizeof(*ct.key)))
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index 3010833ddde33..a5ac21a0ee33f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1827,12 +1827,12 @@ qede_parse_flow_attr(struct qede_dev *edev, __be16 proto,
 	memset(tuple, 0, sizeof(*tuple));
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS))) {
-		DP_NOTICE(edev, "Unsupported key set:0x%x\n",
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS))) {
+		DP_NOTICE(edev, "Unsupported key set:0x%llx\n",
 			  dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 15ebd39739224..4dc8811592461 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -201,23 +201,23 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx,
 		}
 	}
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_CVLAN) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_IP) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_TCP) |
-	      BIT(FLOW_DISSECTOR_KEY_IP))) {
-		NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported flower keys %#x",
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_TCP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IP))) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported flower keys %#llx",
 				       dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
@@ -228,12 +228,13 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx,
 	    !(match->value.eth_proto == htons(ETH_P_IP) ||
 	      match->value.eth_proto == htons(ETH_P_IPV6)))
 		if (dissector->used_keys &
-		    (BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
-		     BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-		     BIT(FLOW_DISSECTOR_KEY_PORTS) |
-		     BIT(FLOW_DISSECTOR_KEY_IP) |
-		     BIT(FLOW_DISSECTOR_KEY_TCP))) {
-			NL_SET_ERR_MSG_FMT_MOD(extack, "L3/L4 flower keys %#x require protocol ipv[46]",
+		    (BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+		     BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+		     BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+		     BIT_ULL(FLOW_DISSECTOR_KEY_IP) |
+		     BIT_ULL(FLOW_DISSECTOR_KEY_TCP))) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "L3/L4 flower keys %#llx require protocol ipv[46]",
 					       dissector->used_keys);
 			return -EINVAL;
 		}
@@ -281,9 +282,10 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx,
 	if ((match->value.ip_proto != IPPROTO_UDP &&
 	     match->value.ip_proto != IPPROTO_TCP) || !IS_ALL_ONES(match->mask.ip_proto))
 		if (dissector->used_keys &
-		    (BIT(FLOW_DISSECTOR_KEY_PORTS) |
-		     BIT(FLOW_DISSECTOR_KEY_TCP))) {
-			NL_SET_ERR_MSG_FMT_MOD(extack, "L4 flower keys %#x require ipproto udp or tcp",
+		    (BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+		     BIT_ULL(FLOW_DISSECTOR_KEY_TCP))) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "L4 flower keys %#llx require ipproto udp or tcp",
 					       dissector->used_keys);
 			return -EINVAL;
 		}
@@ -344,12 +346,13 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx,
 		MAP_ENC_KEY_AND_MASK(PORTS, ports, enc_ports, dst, enc_dport);
 		MAP_ENC_KEY_AND_MASK(KEYID, enc_keyid, enc_keyid, keyid, enc_keyid);
 	} else if (dissector->used_keys &
-		   (BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
-		    BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
-		    BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
-		    BIT(FLOW_DISSECTOR_KEY_ENC_IP) |
-		    BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))) {
-		NL_SET_ERR_MSG_FMT_MOD(extack, "Flower enc keys require enc_control (keys: %#x)",
+		   (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+		    BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
+		    BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
+		    BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) |
+		    BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Flower enc keys require enc_control (keys: %#llx)",
 				       dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index 687f43cd466c6..f9e43fc32ee84 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -1355,7 +1355,7 @@ static int __stmmac_test_l3filt(struct stmmac_priv *priv, u32 dst, u32 src,
 		goto cleanup_rss;
 	}
 
-	dissector->used_keys |= (1 << FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+	dissector->used_keys |= (1ULL << FLOW_DISSECTOR_KEY_IPV4_ADDRS);
 	dissector->offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] = 0;
 
 	cls = kzalloc(sizeof(*cls), GFP_KERNEL);
@@ -1481,8 +1481,8 @@ static int __stmmac_test_l4filt(struct stmmac_priv *priv, u32 dst, u32 src,
 		goto cleanup_rss;
 	}
 
-	dissector->used_keys |= (1 << FLOW_DISSECTOR_KEY_BASIC);
-	dissector->used_keys |= (1 << FLOW_DISSECTOR_KEY_PORTS);
+	dissector->used_keys |= (1ULL << FLOW_DISSECTOR_KEY_BASIC);
+	dissector->used_keys |= (1ULL << FLOW_DISSECTOR_KEY_PORTS);
 	dissector->offset[FLOW_DISSECTOR_KEY_BASIC] = 0;
 	dissector->offset[FLOW_DISSECTOR_KEY_PORTS] = offsetof(typeof(keys), key);
 
diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c
index eced87fa261c9..9ac2ff05d5017 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-qos.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c
@@ -624,9 +624,9 @@ static int am65_cpsw_qos_clsflower_add_policer(struct am65_cpsw_port *port,
 	int ret;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS))) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Unsupported keys used");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index e966dd47e2db3..ae52cdbcf8cc5 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -1396,9 +1396,9 @@ static int cpsw_qos_clsflower_add_policer(struct cpsw_priv *priv,
 	int ret;
 
 	if (dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
-	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS))) {
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS))) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Unsupported keys used");
 		return -EOPNOTSUPP;
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 8664ed4fbbdf3..830f06b2f36d2 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -370,7 +370,8 @@ struct flow_dissector_key {
 };
 
 struct flow_dissector {
-	unsigned int used_keys; /* each bit repesents presence of one key id */
+	unsigned long long  used_keys;
+		/* each bit represents presence of one key id */
 	unsigned short int offset[FLOW_DISSECTOR_KEY_MAX];
 };
 
@@ -430,7 +431,7 @@ void skb_flow_get_icmp_tci(const struct sk_buff *skb,
 static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector,
 				      enum flow_dissector_key_id key_id)
 {
-	return flow_dissector->used_keys & (1 << key_id);
+	return flow_dissector->used_keys & (1ULL << key_id);
 }
 
 static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissector,
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 85a2d0d9bd395..ed5dfa376024f 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -40,7 +40,7 @@
 static void dissector_set_key(struct flow_dissector *flow_dissector,
 			      enum flow_dissector_key_id key_id)
 {
-	flow_dissector->used_keys |= (1 << key_id);
+	flow_dissector->used_keys |= (1ULL << key_id);
 }
 
 void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 7d40e7913e76e..0b0ce4f81c017 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -3208,7 +3208,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 		if (v4_m_spec->ip4src ||
 		    v4_m_spec->ip4dst) {
 			match->dissector.used_keys |=
-				BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+				BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS);
 			match->dissector.offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] =
 				offsetof(struct ethtool_rx_flow_key, ipv4);
 		}
@@ -3223,7 +3223,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 		if (v4_m_spec->psrc ||
 		    v4_m_spec->pdst) {
 			match->dissector.used_keys |=
-				BIT(FLOW_DISSECTOR_KEY_PORTS);
+				BIT_ULL(FLOW_DISSECTOR_KEY_PORTS);
 			match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] =
 				offsetof(struct ethtool_rx_flow_key, tp);
 		}
@@ -3260,7 +3260,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 		if (!ipv6_addr_any((struct in6_addr *)v6_m_spec->ip6src) ||
 		    !ipv6_addr_any((struct in6_addr *)v6_m_spec->ip6dst)) {
 			match->dissector.used_keys |=
-				BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS);
+				BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS);
 			match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] =
 				offsetof(struct ethtool_rx_flow_key, ipv6);
 		}
@@ -3275,7 +3275,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 		if (v6_m_spec->psrc ||
 		    v6_m_spec->pdst) {
 			match->dissector.used_keys |=
-				BIT(FLOW_DISSECTOR_KEY_PORTS);
+				BIT_ULL(FLOW_DISSECTOR_KEY_PORTS);
 			match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] =
 				offsetof(struct ethtool_rx_flow_key, tp);
 		}
@@ -3283,7 +3283,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 			match->key.ip.tos = v6_spec->tclass;
 			match->mask.ip.tos = v6_m_spec->tclass;
 			match->dissector.used_keys |=
-				BIT(FLOW_DISSECTOR_KEY_IP);
+				BIT_ULL(FLOW_DISSECTOR_KEY_IP);
 			match->dissector.offset[FLOW_DISSECTOR_KEY_IP] =
 				offsetof(struct ethtool_rx_flow_key, ip);
 		}
@@ -3307,7 +3307,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 		break;
 	}
 
-	match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC);
+	match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_BASIC);
 	match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] =
 		offsetof(struct ethtool_rx_flow_key, basic);
 
@@ -3340,7 +3340,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 		if (ext_m_spec->vlan_etype ||
 		    ext_m_spec->vlan_tci) {
 			match->dissector.used_keys |=
-				BIT(FLOW_DISSECTOR_KEY_VLAN);
+				BIT_ULL(FLOW_DISSECTOR_KEY_VLAN);
 			match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] =
 				offsetof(struct ethtool_rx_flow_key, vlan);
 		}
@@ -3355,7 +3355,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 		       ETH_ALEN);
 
 		match->dissector.used_keys |=
-			BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS);
+			BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS);
 		match->dissector.offset[FLOW_DISSECTOR_KEY_ETH_ADDRS] =
 			offsetof(struct ethtool_rx_flow_key, eth_addrs);
 	}
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 1c26f03fc6617..a010b25076ca0 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -34,7 +34,7 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match,
 {
 	struct nf_flow_key *mask = &match->mask;
 	struct nf_flow_key *key = &match->key;
-	unsigned int enc_keys;
+	unsigned long long enc_keys;
 
 	if (!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX))
 		return;
@@ -43,8 +43,8 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match,
 	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
 	key->enc_key_id.keyid = tunnel_id_to_key32(tun_info->key.tun_id);
 	mask->enc_key_id.keyid = 0xffffffff;
-	enc_keys = BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
-		   BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL);
+	enc_keys = BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+		   BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL);
 
 	if (ip_tunnel_info_af(tun_info) == AF_INET) {
 		NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
@@ -55,7 +55,7 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match,
 			mask->enc_ipv4.src = 0xffffffff;
 		if (key->enc_ipv4.dst)
 			mask->enc_ipv4.dst = 0xffffffff;
-		enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
+		enc_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
 		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 	} else {
 		memcpy(&key->enc_ipv6.src, &tun_info->key.u.ipv6.dst,
@@ -70,7 +70,7 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match,
 			   sizeof(struct in6_addr)))
 			memset(&mask->enc_ipv6.dst, 0xff,
 			       sizeof(struct in6_addr));
-		enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS);
+		enc_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS);
 		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 	}
 
@@ -163,14 +163,14 @@ static int nf_flow_rule_match(struct nf_flow_match *match,
 		return -EOPNOTSUPP;
 	}
 	mask->control.addr_type = 0xffff;
-	match->dissector.used_keys |= BIT(key->control.addr_type);
+	match->dissector.used_keys |= BIT_ULL(key->control.addr_type);
 	mask->basic.n_proto = 0xffff;
 
 	switch (tuple->l4proto) {
 	case IPPROTO_TCP:
 		key->tcp.flags = 0;
 		mask->tcp.flags = cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16);
-		match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP);
+		match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_TCP);
 		break;
 	case IPPROTO_UDP:
 	case IPPROTO_GRE:
@@ -182,9 +182,9 @@ static int nf_flow_rule_match(struct nf_flow_match *match,
 	key->basic.ip_proto = tuple->l4proto;
 	mask->basic.ip_proto = 0xff;
 
-	match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_META) |
-				      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
-				      BIT(FLOW_DISSECTOR_KEY_BASIC);
+	match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_META) |
+				      BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+				      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC);
 
 	switch (tuple->l4proto) {
 	case IPPROTO_TCP:
@@ -194,7 +194,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match,
 		key->tp.dst = tuple->dst_port;
 		mask->tp.dst = 0xffff;
 
-		match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS);
+		match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_PORTS);
 		break;
 	}
 
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 910ef881c3b85..12ab78fa5d842 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -35,12 +35,12 @@ void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow,
 	struct nft_flow_key *mask = &match->mask;
 	struct nft_flow_key *key = &match->key;
 
-	if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL))
+	if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL))
 		return;
 
 	key->control.addr_type = addr_type;
 	mask->control.addr_type = 0xffff;
-	match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL);
+	match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL);
 	match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] =
 		offsetof(struct nft_flow_key, control);
 }
@@ -59,7 +59,7 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx,
 		.mask	= match->mask.basic.n_proto,
 	};
 
-	if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_VLAN) &&
+	if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) &&
 	    (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) ||
 	     match->key.vlan.vlan_tpid == htons(ETH_P_8021AD))) {
 		match->key.basic.n_proto = match->key.cvlan.vlan_tpid;
@@ -70,8 +70,9 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx,
 		match->mask.vlan.vlan_tpid = ethertype.mask;
 		match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] =
 			offsetof(struct nft_flow_key, cvlan);
-		match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN);
-	} else if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC) &&
+		match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN);
+	} else if (match->dissector.used_keys &
+		   BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) &&
 		   (match->key.basic.n_proto == htons(ETH_P_8021Q) ||
 		    match->key.basic.n_proto == htons(ETH_P_8021AD))) {
 		match->key.basic.n_proto = match->key.vlan.vlan_tpid;
@@ -80,7 +81,7 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx,
 		match->mask.vlan.vlan_tpid = ethertype.mask;
 		match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] =
 			offsetof(struct nft_flow_key, vlan);
-		match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN);
+		match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN);
 	}
 }
 
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 6eb21a4f56989..cd4652259095c 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -162,7 +162,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx,
 	memcpy(key + reg->offset, data, reg->len);
 	memcpy(mask + reg->offset, datamask, reg->len);
 
-	flow->match.dissector.used_keys |= BIT(reg->key);
+	flow->match.dissector.used_keys |= BIT_ULL(reg->key);
 	flow->match.dissector.offset[reg->key] = reg->base_offset;
 
 	if (reg->key == FLOW_DISSECTOR_KEY_META &&
-- 
GitLab


From 53b8d2be4d71953cce547696c39a2a3cb0f1ee48 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Mon, 31 Jul 2023 15:52:52 +0800
Subject: [PATCH 0653/1806] can: flexcan: fix the return value handle for
 platform_get_irq()

There is no possible for platform_get_irq() to return 0
and the return value of platform_get_irq() is more sensible
to show the error reason.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Link: https://lore.kernel.org/all/20230731075252.359965-1-ruanjinjie@huawei.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan/flexcan-core.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index 48273d51f2711..add39e922b890 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -2089,8 +2089,8 @@ static int flexcan_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq <= 0)
-		return -ENODEV;
+	if (irq < 0)
+		return irq;
 
 	regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(regs))
@@ -2167,13 +2167,13 @@ static int flexcan_probe(struct platform_device *pdev)
 
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3) {
 		priv->irq_boff = platform_get_irq(pdev, 1);
-		if (priv->irq_boff <= 0) {
-			err = -ENODEV;
+		if (priv->irq_boff < 0) {
+			err = priv->irq_boff;
 			goto failed_platform_get_irq;
 		}
 		priv->irq_err = platform_get_irq(pdev, 2);
-		if (priv->irq_err <= 0) {
-			err = -ENODEV;
+		if (priv->irq_err < 0) {
+			err = priv->irq_err;
 			goto failed_platform_get_irq;
 		}
 	}
-- 
GitLab


From 8936bf53a091ad6a34b480c22002f1cb2422ab38 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 28 Jul 2023 17:48:13 -0700
Subject: [PATCH 0654/1806] net: Use sockaddr_storage for
 getsockopt(SO_PEERNAME).

Commit df8fc4e934c1 ("kbuild: Enable -fstrict-flex-arrays=3") started
applying strict rules to standard string functions.

It does not work well with conventional socket code around each protocol-
specific sockaddr_XXX struct, which is cast from sockaddr_storage and has
a bigger size than fortified functions expect.  See these commits:

 commit 06d4c8a80836 ("af_unix: Fix fortify_panic() in unix_bind_bsd().")
 commit ecb4534b6a1c ("af_unix: Terminate sun_path when bind()ing pathname socket.")
 commit a0ade8404c3b ("af_packet: Fix warning of fortified memcpy() in packet_getname().")

We must cast the protocol-specific address back to sockaddr_storage
to call such functions.

However, in the case of getsockaddr(SO_PEERNAME), the rationale is a bit
unclear as the buffer is defined by char[128] which is the same size as
sockaddr_storage.

Let's use sockaddr_storage explicitly.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index ab1e8d1bd5a1f..4ad267ba00992 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1806,14 +1806,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 
 	case SO_PEERNAME:
 	{
-		char address[128];
+		struct sockaddr_storage address;
 
-		lv = sock->ops->getname(sock, (struct sockaddr *)address, 2);
+		lv = sock->ops->getname(sock, (struct sockaddr *)&address, 2);
 		if (lv < 0)
 			return -ENOTCONN;
 		if (lv < len)
 			return -EINVAL;
-		if (copy_to_sockptr(optval, address, len))
+		if (copy_to_sockptr(optval, &address, len))
 			return -EFAULT;
 		goto lenout;
 	}
-- 
GitLab


From e332873dc7e21282420cde9bee73e0ffaeb5cb31 Mon Sep 17 00:00:00 2001
From: Markus Schneider-Pargmann <msp@baylibre.com>
Date: Fri, 28 Jul 2023 16:19:18 +0200
Subject: [PATCH 0655/1806] dt-bindings: can: tcan4x5x: Add tcan4552 and
 tcan4553 variants

These two new chips do not have state or wake pins.

Signed-off-by: Markus Schneider-Pargmann <msp@baylibre.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/all/20230728141923.162477-2-msp@baylibre.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../devicetree/bindings/net/can/tcan4x5x.txt          | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt
index e3501bfa22e90..170e23f0610db 100644
--- a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt
+++ b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt
@@ -4,7 +4,10 @@ Texas Instruments TCAN4x5x CAN Controller
 This file provides device node information for the TCAN4x5x interface contains.
 
 Required properties:
-	- compatible: "ti,tcan4x5x"
+	- compatible:
+		"ti,tcan4552", "ti,tcan4x5x"
+		"ti,tcan4553", "ti,tcan4x5x" or
+		"ti,tcan4x5x"
 	- reg: 0
 	- #address-cells: 1
 	- #size-cells: 0
@@ -21,8 +24,10 @@ Optional properties:
 	- reset-gpios: Hardwired output GPIO. If not defined then software
 		       reset.
 	- device-state-gpios: Input GPIO that indicates if the device is in
-			      a sleep state or if the device is active.
-	- device-wake-gpios: Wake up GPIO to wake up the TCAN device.
+			      a sleep state or if the device is active. Not
+			      available with tcan4552/4553.
+	- device-wake-gpios: Wake up GPIO to wake up the TCAN device. Not
+			     available with tcan4552/4553.
 
 Example:
 tcan4x5x: tcan4x5x@0 {
-- 
GitLab


From fbe534f7bf213d485b0ed5362b24a41bf3e18803 Mon Sep 17 00:00:00 2001
From: Markus Schneider-Pargmann <msp@baylibre.com>
Date: Fri, 28 Jul 2023 16:19:19 +0200
Subject: [PATCH 0656/1806] can: tcan4x5x: Remove reserved register 0x814 from
 writable table

The mentioned register is not writable. It is reserved and should not be
written.

Fixes: 39dbb21b6a29 ("can: tcan4x5x: Specify separate read/write ranges")
Signed-off-by: Markus Schneider-Pargmann <msp@baylibre.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Link: https://lore.kernel.org/all/20230728141923.162477-3-msp@baylibre.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/tcan4x5x-regmap.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/can/m_can/tcan4x5x-regmap.c b/drivers/net/can/m_can/tcan4x5x-regmap.c
index 2b218ce04e9f2..fafa6daa67e69 100644
--- a/drivers/net/can/m_can/tcan4x5x-regmap.c
+++ b/drivers/net/can/m_can/tcan4x5x-regmap.c
@@ -95,7 +95,6 @@ static const struct regmap_range tcan4x5x_reg_table_wr_range[] = {
 	regmap_reg_range(0x000c, 0x0010),
 	/* Device configuration registers and Interrupt Flags*/
 	regmap_reg_range(0x0800, 0x080c),
-	regmap_reg_range(0x0814, 0x0814),
 	regmap_reg_range(0x0820, 0x0820),
 	regmap_reg_range(0x0830, 0x0830),
 	/* M_CAN */
-- 
GitLab


From c1b17ea7dd7ca7a199d85e42fd3f8e3d46816b73 Mon Sep 17 00:00:00 2001
From: Markus Schneider-Pargmann <msp@baylibre.com>
Date: Fri, 28 Jul 2023 16:19:20 +0200
Subject: [PATCH 0657/1806] can: tcan4x5x: Check size of mram configuration

To reduce debugging effort in case the mram is misconfigured, add this
size check of the DT configuration. Currently if the mram configuration
doesn't fit into the available MRAM it just overwrites other areas of
the MRAM.

Signed-off-by: Markus Schneider-Pargmann <msp@baylibre.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Link: https://lore.kernel.org/all/20230728141923.162477-4-msp@baylibre.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c         | 16 ++++++++++++++++
 drivers/net/can/m_can/m_can.h         |  1 +
 drivers/net/can/m_can/tcan4x5x-core.c |  5 +++++
 3 files changed, 22 insertions(+)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index d204703521d28..16ecc11c7f62a 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1913,6 +1913,22 @@ static int register_m_can_dev(struct net_device *dev)
 	return register_candev(dev);
 }
 
+int m_can_check_mram_cfg(struct m_can_classdev *cdev, u32 mram_max_size)
+{
+	u32 total_size;
+
+	total_size = cdev->mcfg[MRAM_TXB].off - cdev->mcfg[MRAM_SIDF].off +
+			cdev->mcfg[MRAM_TXB].num * TXB_ELEMENT_SIZE;
+	if (total_size > mram_max_size) {
+		dev_err(cdev->dev, "Total size of mram config(%u) exceeds mram(%u)\n",
+			total_size, mram_max_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(m_can_check_mram_cfg);
+
 static void m_can_of_parse_mram(struct m_can_classdev *cdev,
 				const u32 *mram_config_vals)
 {
diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h
index c543928c756fc..520e14277dff5 100644
--- a/drivers/net/can/m_can/m_can.h
+++ b/drivers/net/can/m_can/m_can.h
@@ -103,6 +103,7 @@ int m_can_class_register(struct m_can_classdev *cdev);
 void m_can_class_unregister(struct m_can_classdev *cdev);
 int m_can_class_get_clocks(struct m_can_classdev *cdev);
 int m_can_init_ram(struct m_can_classdev *priv);
+int m_can_check_mram_cfg(struct m_can_classdev *cdev, u32 mram_max_size);
 
 int m_can_class_suspend(struct device *dev);
 int m_can_class_resume(struct device *dev);
diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c
index 2342aa011647c..e706518176e4d 100644
--- a/drivers/net/can/m_can/tcan4x5x-core.c
+++ b/drivers/net/can/m_can/tcan4x5x-core.c
@@ -80,6 +80,7 @@
 	 TCAN4X5X_MCAN_IR_RF1F)
 
 #define TCAN4X5X_MRAM_START 0x8000
+#define TCAN4X5X_MRAM_SIZE 0x800
 #define TCAN4X5X_MCAN_OFFSET 0x1000
 
 #define TCAN4X5X_CLEAR_ALL_INT 0xffffffff
@@ -307,6 +308,10 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 	if (!mcan_class)
 		return -ENOMEM;
 
+	ret = m_can_check_mram_cfg(mcan_class, TCAN4X5X_MRAM_SIZE);
+	if (ret)
+		goto out_m_can_class_free_dev;
+
 	priv = cdev_to_priv(mcan_class);
 
 	priv->power = devm_regulator_get_optional(&spi->dev, "vsup");
-- 
GitLab


From 0d6f3b25ac2fa13fddc6106239f7fa7795c8e808 Mon Sep 17 00:00:00 2001
From: Markus Schneider-Pargmann <msp@baylibre.com>
Date: Fri, 28 Jul 2023 16:19:21 +0200
Subject: [PATCH 0658/1806] can: tcan4x5x: Rename ID registers to match
 datasheet

The datasheet calls these registers ID1 and ID2. Rename these to avoid
confusion.

Signed-off-by: Markus Schneider-Pargmann <msp@baylibre.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Link: https://lore.kernel.org/all/20230728141923.162477-5-msp@baylibre.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/tcan4x5x-core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c
index e706518176e4d..fb9375fa20ec0 100644
--- a/drivers/net/can/m_can/tcan4x5x-core.c
+++ b/drivers/net/can/m_can/tcan4x5x-core.c
@@ -6,8 +6,8 @@
 
 #define TCAN4X5X_EXT_CLK_DEF 40000000
 
-#define TCAN4X5X_DEV_ID0 0x00
-#define TCAN4X5X_DEV_ID1 0x04
+#define TCAN4X5X_DEV_ID1 0x00
+#define TCAN4X5X_DEV_ID2 0x04
 #define TCAN4X5X_REV 0x08
 #define TCAN4X5X_STATUS 0x0C
 #define TCAN4X5X_ERROR_STATUS_MASK 0x10
-- 
GitLab


From 142c6dc6d9d7c27157e41985519464d5985e3d95 Mon Sep 17 00:00:00 2001
From: Markus Schneider-Pargmann <msp@baylibre.com>
Date: Fri, 28 Jul 2023 16:19:22 +0200
Subject: [PATCH 0659/1806] can: tcan4x5x: Add support for tcan4552/4553

tcan4552 and tcan4553 do not have wake or state pins, so they are
currently not compatible with the generic driver. The generic driver
uses tcan4x5x_disable_state() and tcan4x5x_disable_wake() if the gpios
are not defined. These functions use register bits that are not
available in tcan4552/4553.

This patch adds support by introducing version information to reflect if
the chip has wake and state pins. Also the version is now checked.

Signed-off-by: Markus Schneider-Pargmann <msp@baylibre.com>
Link: https://lore.kernel.org/all/20230728141923.162477-6-msp@baylibre.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/tcan4x5x-core.c | 104 ++++++++++++++++++++++----
 1 file changed, 90 insertions(+), 14 deletions(-)

diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c
index fb9375fa20ec0..2d329b4e4f52c 100644
--- a/drivers/net/can/m_can/tcan4x5x-core.c
+++ b/drivers/net/can/m_can/tcan4x5x-core.c
@@ -7,6 +7,7 @@
 #define TCAN4X5X_EXT_CLK_DEF 40000000
 
 #define TCAN4X5X_DEV_ID1 0x00
+#define TCAN4X5X_DEV_ID1_TCAN 0x4e414354 /* ASCII TCAN */
 #define TCAN4X5X_DEV_ID2 0x04
 #define TCAN4X5X_REV 0x08
 #define TCAN4X5X_STATUS 0x0C
@@ -103,6 +104,37 @@
 #define TCAN4X5X_WD_3_S_TIMER BIT(29)
 #define TCAN4X5X_WD_6_S_TIMER (BIT(28) | BIT(29))
 
+struct tcan4x5x_version_info {
+	const char *name;
+	u32 id2_register;
+
+	bool has_wake_pin;
+	bool has_state_pin;
+};
+
+enum {
+	TCAN4552 = 0,
+	TCAN4553,
+	TCAN4X5X,
+};
+
+static const struct tcan4x5x_version_info tcan4x5x_versions[] = {
+	[TCAN4552] = {
+		.name = "4552",
+		.id2_register = 0x32353534,
+	},
+	[TCAN4553] = {
+		.name = "4553",
+		.id2_register = 0x32353534,
+	},
+	/* generic version with no id2_register at the end */
+	[TCAN4X5X] = {
+		.name = "generic",
+		.has_wake_pin = true,
+		.has_state_pin = true,
+	},
+};
+
 static inline struct tcan4x5x_priv *cdev_to_priv(struct m_can_classdev *cdev)
 {
 	return container_of(cdev, struct tcan4x5x_priv, cdev);
@@ -254,18 +286,53 @@ static int tcan4x5x_disable_state(struct m_can_classdev *cdev)
 				  TCAN4X5X_DISABLE_INH_MSK, 0x01);
 }
 
-static int tcan4x5x_get_gpios(struct m_can_classdev *cdev)
+static const struct tcan4x5x_version_info
+*tcan4x5x_find_version(struct tcan4x5x_priv *priv)
+{
+	u32 val;
+	int ret;
+
+	ret = regmap_read(priv->regmap, TCAN4X5X_DEV_ID1, &val);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (val != TCAN4X5X_DEV_ID1_TCAN) {
+		dev_err(&priv->spi->dev, "Not a tcan device %x\n", val);
+		return ERR_PTR(-ENODEV);
+	}
+
+	ret = regmap_read(priv->regmap, TCAN4X5X_DEV_ID2, &val);
+	if (ret)
+		return ERR_PTR(ret);
+
+	for (int i = 0; i != ARRAY_SIZE(tcan4x5x_versions); ++i) {
+		const struct tcan4x5x_version_info *vinfo = &tcan4x5x_versions[i];
+
+		if (!vinfo->id2_register || val == vinfo->id2_register) {
+			dev_info(&priv->spi->dev, "Detected TCAN device version %s\n",
+				 vinfo->name);
+			return vinfo;
+		}
+	}
+
+	return &tcan4x5x_versions[TCAN4X5X];
+}
+
+static int tcan4x5x_get_gpios(struct m_can_classdev *cdev,
+			      const struct tcan4x5x_version_info *version_info)
 {
 	struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev);
 	int ret;
 
-	tcan4x5x->device_wake_gpio = devm_gpiod_get(cdev->dev, "device-wake",
-						    GPIOD_OUT_HIGH);
-	if (IS_ERR(tcan4x5x->device_wake_gpio)) {
-		if (PTR_ERR(tcan4x5x->device_wake_gpio) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
+	if (version_info->has_wake_pin) {
+		tcan4x5x->device_wake_gpio = devm_gpiod_get(cdev->dev, "device-wake",
+							    GPIOD_OUT_HIGH);
+		if (IS_ERR(tcan4x5x->device_wake_gpio)) {
+			if (PTR_ERR(tcan4x5x->device_wake_gpio) == -EPROBE_DEFER)
+				return -EPROBE_DEFER;
 
-		tcan4x5x_disable_wake(cdev);
+			tcan4x5x_disable_wake(cdev);
+		}
 	}
 
 	tcan4x5x->reset_gpio = devm_gpiod_get_optional(cdev->dev, "reset",
@@ -277,12 +344,14 @@ static int tcan4x5x_get_gpios(struct m_can_classdev *cdev)
 	if (ret)
 		return ret;
 
-	tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev,
-							      "device-state",
-							      GPIOD_IN);
-	if (IS_ERR(tcan4x5x->device_state_gpio)) {
-		tcan4x5x->device_state_gpio = NULL;
-		tcan4x5x_disable_state(cdev);
+	if (version_info->has_state_pin) {
+		tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev,
+								      "device-state",
+								      GPIOD_IN);
+		if (IS_ERR(tcan4x5x->device_state_gpio)) {
+			tcan4x5x->device_state_gpio = NULL;
+			tcan4x5x_disable_state(cdev);
+		}
 	}
 
 	return 0;
@@ -299,6 +368,7 @@ static struct m_can_ops tcan4x5x_ops = {
 
 static int tcan4x5x_can_probe(struct spi_device *spi)
 {
+	const struct tcan4x5x_version_info *version_info;
 	struct tcan4x5x_priv *priv;
 	struct m_can_classdev *mcan_class;
 	int freq, ret;
@@ -361,7 +431,13 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 	if (ret)
 		goto out_m_can_class_free_dev;
 
-	ret = tcan4x5x_get_gpios(mcan_class);
+	version_info = tcan4x5x_find_version(priv);
+	if (IS_ERR(version_info)) {
+		ret = PTR_ERR(version_info);
+		goto out_power;
+	}
+
+	ret = tcan4x5x_get_gpios(mcan_class, version_info);
 	if (ret)
 		goto out_power;
 
-- 
GitLab


From 35e7aaab3e0058dba3eaf082c3f1ccee96c20b1c Mon Sep 17 00:00:00 2001
From: Markus Schneider-Pargmann <msp@baylibre.com>
Date: Fri, 28 Jul 2023 16:19:23 +0200
Subject: [PATCH 0660/1806] can: tcan4x5x: Add error messages in probe

To be able to understand issues during probe easier, add error messages
if something fails.

Signed-off-by: Markus Schneider-Pargmann <msp@baylibre.com>
Link: https://lore.kernel.org/all/20230728141923.162477-7-msp@baylibre.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/tcan4x5x-core.c | 29 +++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c
index 2d329b4e4f52c..8a4143809d337 100644
--- a/drivers/net/can/m_can/tcan4x5x-core.c
+++ b/drivers/net/can/m_can/tcan4x5x-core.c
@@ -402,6 +402,8 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 
 	/* Sanity check */
 	if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF) {
+		dev_err(&spi->dev, "Clock frequency is out of supported range %d\n",
+			freq);
 		ret = -ERANGE;
 		goto out_m_can_class_free_dev;
 	}
@@ -420,16 +422,23 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 	/* Configure the SPI bus */
 	spi->bits_per_word = 8;
 	ret = spi_setup(spi);
-	if (ret)
+	if (ret) {
+		dev_err(&spi->dev, "SPI setup failed %pe\n", ERR_PTR(ret));
 		goto out_m_can_class_free_dev;
+	}
 
 	ret = tcan4x5x_regmap_init(priv);
-	if (ret)
+	if (ret) {
+		dev_err(&spi->dev, "regmap init failed %pe\n", ERR_PTR(ret));
 		goto out_m_can_class_free_dev;
+	}
 
 	ret = tcan4x5x_power_enable(priv->power, 1);
-	if (ret)
+	if (ret) {
+		dev_err(&spi->dev, "Enabling regulator failed %pe\n",
+			ERR_PTR(ret));
 		goto out_m_can_class_free_dev;
+	}
 
 	version_info = tcan4x5x_find_version(priv);
 	if (IS_ERR(version_info)) {
@@ -438,16 +447,24 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 	}
 
 	ret = tcan4x5x_get_gpios(mcan_class, version_info);
-	if (ret)
+	if (ret) {
+		dev_err(&spi->dev, "Getting gpios failed %pe\n", ERR_PTR(ret));
 		goto out_power;
+	}
 
 	ret = tcan4x5x_init(mcan_class);
-	if (ret)
+	if (ret) {
+		dev_err(&spi->dev, "tcan initialization failed %pe\n",
+			ERR_PTR(ret));
 		goto out_power;
+	}
 
 	ret = m_can_class_register(mcan_class);
-	if (ret)
+	if (ret) {
+		dev_err(&spi->dev, "Failed registering m_can device %pe\n",
+			ERR_PTR(ret));
 		goto out_power;
+	}
 
 	netdev_info(mcan_class->net, "TCAN4X5X successfully initialized.\n");
 	return 0;
-- 
GitLab


From 3bb014c72b087fa1d440d1b83cb3dfcfc4d24cff Mon Sep 17 00:00:00 2001
From: Yuanjun Gong <ruc_gongyuanjun@163.com>
Date: Mon, 17 Jul 2023 22:50:08 +0800
Subject: [PATCH 0661/1806] wifi: mt76: mt76x02: fix return value check in
 mt76x02_mac_process_rx

in mt76x02_mac_process_rx(), return an error code if an
unexpected result is returned by pskb_trim.

Signed-off-by: Yuanjun Gong <ruc_gongyuanjun@163.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index 3e41d809ade39..d5db6ffd6d365 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -853,7 +853,8 @@ int mt76x02_mac_process_rx(struct mt76x02_dev *dev, struct sk_buff *skb,
 	if (WARN_ON_ONCE(len > skb->len))
 		return -EINVAL;
 
-	pskb_trim(skb, len);
+	if (pskb_trim(skb, len))
+		return -EINVAL;
 
 	status->chains = BIT(0);
 	signal = mt76x02_mac_get_rssi(dev, rxwi->rssi[0], 0);
-- 
GitLab


From 4f1875c288dfc1ccea81fc17fef1d30c9d8498b2 Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Thu, 27 Jul 2023 02:35:05 +0800
Subject: [PATCH 0662/1806] wifi: mt76: mt7915: fix tlv length of
 mt7915_mcu_get_chan_mib_info

Correct per-device TLV lengths to avoid invalid operation in firmware.
(  64.040375:28:STATS-E)statsGetSingleHWCounter: MIB counter index = 65472 not supported.
This happens on mt7916/mt7986.

Fixes: b0bfa00595be ("wifi: mt76: mt7915: improve accuracy of time_busy calculation")
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 5f4c2946b26b5..50ae7bf3af91c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -3038,7 +3038,7 @@ int mt7915_mcu_get_chan_mib_info(struct mt7915_phy *phy, bool chan_switch)
 	}
 
 	ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_EXT_CMD(GET_MIB_INFO),
-					req, sizeof(req), true, &skb);
+					req, len * sizeof(req[0]), true, &skb);
 	if (ret)
 		return ret;
 
-- 
GitLab


From 6c0570bc21ec2073890aa252c8420ca7bec402e4 Mon Sep 17 00:00:00 2001
From: Ryder Lee <ryder.lee@mediatek.com>
Date: Thu, 27 Jul 2023 02:35:06 +0800
Subject: [PATCH 0663/1806] wifi: mt76: mt7915: fix power-limits while
 chan_switch

If user changes the channel without completely disabling the interface the
txpower_sku values reported track the old channel the device was operating on.
If user bounces the interface the correct power tables are applied.

mt7915_sku_group_len array gets updated before the channel switch happens so it
uses data from the old channel.

Fixes: ecb187a74e18 ("mt76: mt7915: rework the flow of txpower setting")
Fixes: f1d962369d56 ("mt76: mt7915: implement HE per-rate tx power support")
Reported-By: Chad Monroe <chad.monroe@smartrg.com>
Tested-by: Chad Monroe <chad.monroe@smartrg.com>
Signed-off-by: Allen Ye <allen.ye@mediatek.com>
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index eb95fb28d3549..8ebbf186fab23 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -471,7 +471,8 @@ static int mt7915_config(struct ieee80211_hw *hw, u32 changed)
 		ieee80211_wake_queues(hw);
 	}
 
-	if (changed & IEEE80211_CONF_CHANGE_POWER) {
+	if (changed & (IEEE80211_CONF_CHANGE_POWER |
+		       IEEE80211_CONF_CHANGE_CHANNEL)) {
 		ret = mt7915_mcu_set_txpower_sku(phy);
 		if (ret)
 			return ret;
-- 
GitLab


From 74bdfab4fd7c641e55f7fe9d1be9687eeb01df67 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@isovalent.com>
Date: Mon, 31 Jul 2023 11:42:53 +0200
Subject: [PATCH 0664/1806] net: remove duplicate INDIRECT_CALLABLE_DECLARE of
 udp[6]_ehashfn

There are already INDIRECT_CALLABLE_DECLARE in the hashtable
headers, no need to declare them again.

Fixes: 0f495f761722 ("net: remove duplicate reuseport_lookup functions")
Suggested-by: Martin Lau <martin.lau@linux.dev>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230731-indir-call-v1-1-4cd0aeaee64f@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 net/ipv4/inet_hashtables.c  | 2 --
 net/ipv6/inet6_hashtables.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 6a872b8fb0d35..7876b7d703cb5 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -333,8 +333,6 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn);
-
 /**
  * inet_lookup_reuseport() - execute reuseport logic on AF_INET socket if necessary.
  * @net: network namespace.
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 7c9700c7c9c87..b0e8d278e8a9b 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -112,8 +112,6 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn);
-
 /**
  * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary.
  * @net: network namespace.
-- 
GitLab


From 2628d40899d1acb5120993bef651595787ddaa8e Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 28 Jul 2023 21:21:13 +0800
Subject: [PATCH 0665/1806] devlink: Remove unused extern declaration
 devlink_port_region_destroy()

devlink_port_region_destroy() is never implemented since
commit 544e7c33ec2f ("net: devlink: Add support for port regions").

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230728132113.32888-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/devlink.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 0cdb4b16e5b59..a1a8e1b6e7dfc 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1790,8 +1790,6 @@ devlink_port_region_create(struct devlink_port *port,
 			   u32 region_max_snapshots, u64 region_size);
 void devl_region_destroy(struct devlink_region *region);
 void devlink_region_destroy(struct devlink_region *region);
-void devlink_port_region_destroy(struct devlink_region *region);
-
 int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id);
 void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id);
 int devlink_region_snapshot_create(struct devlink_region *region,
-- 
GitLab


From 68223f96997e8ac2bb1751a72a211d1551a0dbcd Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 29 Jul 2023 20:26:44 +0800
Subject: [PATCH 0666/1806] tcp: Remove unused function declarations

commit 8a59f9d1e3d4 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()")
left behind tcp_bpf_get_proto() declaration. And tcp_v4_tw_remember_stamp()
function is remove in ccb7c410ddc0 ("timewait_sock: Create and use getpeer op.").
Since commit 686989700cab ("tcp: simplify tcp_mark_skb_lost")
tcp_skb_mark_lost_uncond_verify() declaration is not used anymore.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230729122644.10648-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6ebf54992ffee..6d77c08d83b76 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -323,7 +323,6 @@ int tcp_v4_early_demux(struct sk_buff *skb);
 int tcp_v4_rcv(struct sk_buff *skb);
 
 void tcp_remove_empty_skb(struct sock *sk);
-int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
 int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size);
 int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
@@ -622,7 +621,6 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb,
 void tcp_rearm_rto(struct sock *sk);
 void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
 void tcp_reset(struct sock *sk, struct sk_buff *skb);
-void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb);
 void tcp_fin(struct sock *sk);
 void tcp_check_space(struct sock *sk);
 void tcp_sack_compress_send_ack(struct sock *sk);
@@ -2360,7 +2358,6 @@ struct sk_msg;
 struct sk_psock;
 
 #ifdef CONFIG_BPF_SYSCALL
-struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
 int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
 void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
 #endif /* CONFIG_BPF_SYSCALL */
-- 
GitLab


From 230f3d53a5477bf8b04e649dca67da85635cd1eb Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Fri, 28 Jul 2023 10:13:36 -0700
Subject: [PATCH 0667/1806] i40e: remove i40e_status

Replace uses of i40e_status to as equivalent as possible error codes.
Remove enum i40e_status as it is no longer needed

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230728171336.2446156-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_adminq.c |  49 +++--
 drivers/net/ethernet/intel/i40e/i40e_adminq.h |   3 +-
 drivers/net/ethernet/intel/i40e/i40e_common.c | 116 ++++++------
 drivers/net/ethernet/intel/i40e/i40e_dcb.c    |  20 +-
 drivers/net/ethernet/intel/i40e/i40e_ddp.c    |   2 +-
 .../net/ethernet/intel/i40e/i40e_debugfs.c    |   4 +-
 drivers/net/ethernet/intel/i40e/i40e_diag.c   |   6 +-
 .../net/ethernet/intel/i40e/i40e_ethtool.c    |   2 +-
 drivers/net/ethernet/intel/i40e/i40e_hmc.c    |  21 +-
 .../net/ethernet/intel/i40e/i40e_lan_hmc.c    |  54 +++---
 drivers/net/ethernet/intel/i40e/i40e_main.c   |  48 ++---
 drivers/net/ethernet/intel/i40e/i40e_nvm.c    |  52 ++---
 drivers/net/ethernet/intel/i40e/i40e_ptp.c    |   2 +-
 drivers/net/ethernet/intel/i40e/i40e_status.h |  43 -----
 drivers/net/ethernet/intel/i40e/i40e_type.h   |   1 -
 .../ethernet/intel/i40e/i40e_virtchnl_pf.c    | 179 +++++++++---------
 16 files changed, 275 insertions(+), 327 deletions(-)
 delete mode 100644 drivers/net/ethernet/intel/i40e/i40e_status.h

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 86fac8f959bb0..100eb77b8dfe6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
-#include "i40e_status.h"
 #include "i40e_type.h"
 #include "i40e_register.h"
 #include "i40e_adminq.h"
@@ -284,7 +283,7 @@ static int i40e_config_asq_regs(struct i40e_hw *hw)
 	/* Check one register to verify that config was applied */
 	reg = rd32(hw, hw->aq.asq.bal);
 	if (reg != lower_32_bits(hw->aq.asq.desc_buf.pa))
-		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+		ret_code = -EIO;
 
 	return ret_code;
 }
@@ -316,7 +315,7 @@ static int i40e_config_arq_regs(struct i40e_hw *hw)
 	/* Check one register to verify that config was applied */
 	reg = rd32(hw, hw->aq.arq.bal);
 	if (reg != lower_32_bits(hw->aq.arq.desc_buf.pa))
-		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+		ret_code = -EIO;
 
 	return ret_code;
 }
@@ -340,14 +339,14 @@ static int i40e_init_asq(struct i40e_hw *hw)
 
 	if (hw->aq.asq.count > 0) {
 		/* queue already initialized */
-		ret_code = I40E_ERR_NOT_READY;
+		ret_code = -EBUSY;
 		goto init_adminq_exit;
 	}
 
 	/* verify input for valid configuration */
 	if ((hw->aq.num_asq_entries == 0) ||
 	    (hw->aq.asq_buf_size == 0)) {
-		ret_code = I40E_ERR_CONFIG;
+		ret_code = -EIO;
 		goto init_adminq_exit;
 	}
 
@@ -399,14 +398,14 @@ static int i40e_init_arq(struct i40e_hw *hw)
 
 	if (hw->aq.arq.count > 0) {
 		/* queue already initialized */
-		ret_code = I40E_ERR_NOT_READY;
+		ret_code = -EBUSY;
 		goto init_adminq_exit;
 	}
 
 	/* verify input for valid configuration */
 	if ((hw->aq.num_arq_entries == 0) ||
 	    (hw->aq.arq_buf_size == 0)) {
-		ret_code = I40E_ERR_CONFIG;
+		ret_code = -EIO;
 		goto init_adminq_exit;
 	}
 
@@ -452,7 +451,7 @@ static int i40e_shutdown_asq(struct i40e_hw *hw)
 	mutex_lock(&hw->aq.asq_mutex);
 
 	if (hw->aq.asq.count == 0) {
-		ret_code = I40E_ERR_NOT_READY;
+		ret_code = -EBUSY;
 		goto shutdown_asq_out;
 	}
 
@@ -486,7 +485,7 @@ static int i40e_shutdown_arq(struct i40e_hw *hw)
 	mutex_lock(&hw->aq.arq_mutex);
 
 	if (hw->aq.arq.count == 0) {
-		ret_code = I40E_ERR_NOT_READY;
+		ret_code = -EBUSY;
 		goto shutdown_arq_out;
 	}
 
@@ -594,7 +593,7 @@ int i40e_init_adminq(struct i40e_hw *hw)
 	    (hw->aq.num_asq_entries == 0) ||
 	    (hw->aq.arq_buf_size == 0) ||
 	    (hw->aq.asq_buf_size == 0)) {
-		ret_code = I40E_ERR_CONFIG;
+		ret_code = -EIO;
 		goto init_adminq_exit;
 	}
 
@@ -626,13 +625,13 @@ int i40e_init_adminq(struct i40e_hw *hw)
 							&hw->aq.api_maj_ver,
 							&hw->aq.api_min_ver,
 							NULL);
-		if (ret_code != I40E_ERR_ADMIN_QUEUE_TIMEOUT)
+		if (ret_code != -EIO)
 			break;
 		retry++;
 		msleep(100);
 		i40e_resume_aq(hw);
 	} while (retry < 10);
-	if (ret_code != I40E_SUCCESS)
+	if (ret_code != 0)
 		goto init_adminq_free_arq;
 
 	/* Some features were introduced in different FW API version
@@ -672,7 +671,7 @@ int i40e_init_adminq(struct i40e_hw *hw)
 		hw->flags |= I40E_HW_FLAG_802_1AD_CAPABLE;
 
 	if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) {
-		ret_code = I40E_ERR_FIRMWARE_API_VERSION;
+		ret_code = -EIO;
 		goto init_adminq_free_arq;
 	}
 
@@ -799,7 +798,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 	if (hw->aq.asq.count == 0) {
 		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
 			   "AQTX: Admin queue not initialized.\n");
-		status = I40E_ERR_QUEUE_EMPTY;
+		status = -EIO;
 		goto asq_send_command_error;
 	}
 
@@ -809,7 +808,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 	if (val >= hw->aq.num_asq_entries) {
 		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
 			   "AQTX: head overrun at %d\n", val);
-		status = I40E_ERR_ADMIN_QUEUE_FULL;
+		status = -ENOSPC;
 		goto asq_send_command_error;
 	}
 
@@ -840,7 +839,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 			   I40E_DEBUG_AQ_MESSAGE,
 			   "AQTX: Invalid buffer size: %d.\n",
 			   buff_size);
-		status = I40E_ERR_INVALID_SIZE;
+		status = -EINVAL;
 		goto asq_send_command_error;
 	}
 
@@ -848,7 +847,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 		i40e_debug(hw,
 			   I40E_DEBUG_AQ_MESSAGE,
 			   "AQTX: Async flag not set along with postpone flag");
-		status = I40E_ERR_PARAM;
+		status = -EINVAL;
 		goto asq_send_command_error;
 	}
 
@@ -863,7 +862,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 		i40e_debug(hw,
 			   I40E_DEBUG_AQ_MESSAGE,
 			   "AQTX: Error queue is full.\n");
-		status = I40E_ERR_ADMIN_QUEUE_FULL;
+		status = -ENOSPC;
 		goto asq_send_command_error;
 	}
 
@@ -940,9 +939,9 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 		if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK)
 			status = 0;
 		else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY)
-			status = I40E_ERR_NOT_READY;
+			status = -EBUSY;
 		else
-			status = I40E_ERR_ADMIN_QUEUE_ERROR;
+			status = -EIO;
 		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
 	}
 
@@ -960,11 +959,11 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 		if (rd32(hw, hw->aq.asq.len) & I40E_GL_ATQLEN_ATQCRIT_MASK) {
 			i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
 				   "AQTX: AQ Critical error.\n");
-			status = I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR;
+			status = -EIO;
 		} else {
 			i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
 				   "AQTX: Writeback timeout.\n");
-			status = I40E_ERR_ADMIN_QUEUE_TIMEOUT;
+			status = -EIO;
 		}
 	}
 
@@ -1106,7 +1105,7 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 	if (hw->aq.arq.count == 0) {
 		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
 			   "AQRX: Admin queue not initialized.\n");
-		ret_code = I40E_ERR_QUEUE_EMPTY;
+		ret_code = -EIO;
 		goto clean_arq_element_err;
 	}
 
@@ -1114,7 +1113,7 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 	ntu = rd32(hw, hw->aq.arq.head) & I40E_PF_ARQH_ARQH_MASK;
 	if (ntu == ntc) {
 		/* nothing to do - shouldn't need to update ring's values */
-		ret_code = I40E_ERR_ADMIN_QUEUE_NO_WORK;
+		ret_code = -EALREADY;
 		goto clean_arq_element_out;
 	}
 
@@ -1126,7 +1125,7 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 		(enum i40e_admin_queue_err)le16_to_cpu(desc->retval);
 	flags = le16_to_cpu(desc->flags);
 	if (flags & I40E_AQ_FLAG_ERR) {
-		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+		ret_code = -EIO;
 		i40e_debug(hw,
 			   I40E_DEBUG_AQ_MESSAGE,
 			   "AQRX: Event received with error 0x%X.\n",
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
index ee394aacef4d1..267f2e0a21ce8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
@@ -5,7 +5,6 @@
 #define _I40E_ADMINQ_H_
 
 #include "i40e_osdep.h"
-#include "i40e_status.h"
 #include "i40e_adminq_cmd.h"
 
 #define I40E_ADMINQ_DESC(R, i)   \
@@ -117,7 +116,7 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc)
 	};
 
 	/* aq_rc is invalid if AQ timed out */
-	if (aq_ret == I40E_ERR_ADMIN_QUEUE_TIMEOUT)
+	if (aq_ret == -EIO)
 		return -EAGAIN;
 
 	if (!((u32)aq_rc < (sizeof(aq_to_posix) / sizeof((aq_to_posix)[0]))))
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index ed88e38d488b2..eeef20f771062 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -56,7 +56,7 @@ int i40e_set_mac_type(struct i40e_hw *hw)
 			break;
 		}
 	} else {
-		status = I40E_ERR_DEVICE_NOT_SUPPORTED;
+		status = -ENODEV;
 	}
 
 	hw_dbg(hw, "i40e_set_mac_type found mac: %d, returns: %d\n",
@@ -660,7 +660,7 @@ int i40e_init_shared_code(struct i40e_hw *hw)
 	case I40E_MAC_X722:
 		break;
 	default:
-		return I40E_ERR_DEVICE_NOT_SUPPORTED;
+		return -ENODEV;
 	}
 
 	hw->phy.get_link_info = true;
@@ -780,7 +780,7 @@ int i40e_get_port_mac_addr(struct i40e_hw *hw, u8 *mac_addr)
 	if (flags & I40E_AQC_PORT_ADDR_VALID)
 		ether_addr_copy(mac_addr, addrs.port_mac);
 	else
-		status = I40E_ERR_INVALID_MAC_ADDR;
+		status = -EINVAL;
 
 	return status;
 }
@@ -858,7 +858,7 @@ int i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num,
 	pba_size--;
 	if (pba_num_size < (((u32)pba_size * 2) + 1)) {
 		hw_dbg(hw, "Buffer too small for PBA data.\n");
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 	}
 
 	for (i = 0; i < pba_size; i++) {
@@ -955,7 +955,7 @@ static int i40e_poll_globr(struct i40e_hw *hw,
 	hw_dbg(hw, "Global reset failed.\n");
 	hw_dbg(hw, "I40E_GLGEN_RSTAT = 0x%x\n", reg);
 
-	return I40E_ERR_RESET_FAILED;
+	return -EIO;
 }
 
 #define I40E_PF_RESET_WAIT_COUNT_A0	200
@@ -995,7 +995,7 @@ int i40e_pf_reset(struct i40e_hw *hw)
 	}
 	if (reg & I40E_GLGEN_RSTAT_DEVSTATE_MASK) {
 		hw_dbg(hw, "Global reset polling failed to complete.\n");
-		return I40E_ERR_RESET_FAILED;
+		return -EIO;
 	}
 
 	/* Now Wait for the FW to be ready */
@@ -1014,7 +1014,7 @@ int i40e_pf_reset(struct i40e_hw *hw)
 		     I40E_GLNVM_ULD_CONF_GLOBAL_DONE_MASK))) {
 		hw_dbg(hw, "wait for FW Reset complete timedout\n");
 		hw_dbg(hw, "I40E_GLNVM_ULD = 0x%x\n", reg);
-		return I40E_ERR_RESET_FAILED;
+		return -EIO;
 	}
 
 	/* If there was a Global Reset in progress when we got here,
@@ -1040,10 +1040,10 @@ int i40e_pf_reset(struct i40e_hw *hw)
 		}
 		if (reg2 & I40E_GLGEN_RSTAT_DEVSTATE_MASK) {
 			if (i40e_poll_globr(hw, grst_del))
-				return I40E_ERR_RESET_FAILED;
+				return -EIO;
 		} else if (reg & I40E_PFGEN_CTRL_PFSWR_MASK) {
 			hw_dbg(hw, "PF reset polling failed to complete.\n");
-			return I40E_ERR_RESET_FAILED;
+			return -EIO;
 		}
 	}
 
@@ -1318,7 +1318,7 @@ i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
 	int status;
 
 	if (!abilities)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	do {
 		i40e_fill_default_direct_cmd_desc(&desc,
@@ -1341,12 +1341,12 @@ i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
 
 		switch (hw->aq.asq_last_status) {
 		case I40E_AQ_RC_EIO:
-			status = I40E_ERR_UNKNOWN_PHY;
+			status = -EIO;
 			break;
 		case I40E_AQ_RC_EAGAIN:
 			usleep_range(1000, 2000);
 			total_delay++;
-			status = I40E_ERR_TIMEOUT;
+			status = -EIO;
 			break;
 		/* also covers I40E_AQ_RC_OK */
 		default:
@@ -1396,7 +1396,7 @@ int i40e_aq_set_phy_config(struct i40e_hw *hw,
 	int status;
 
 	if (!config)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_phy_config);
@@ -2312,7 +2312,7 @@ int i40e_aq_send_driver_version(struct i40e_hw *hw,
 	u16 len;
 
 	if (dv == NULL)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_driver_version);
 
@@ -2430,7 +2430,7 @@ int i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid,
 
 	/* SEIDs need to either both be set or both be 0 for floating VEB */
 	if (!!uplink_seid != !!downlink_seid)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_veb);
 
@@ -2485,7 +2485,7 @@ int i40e_aq_get_veb_parameters(struct i40e_hw *hw,
 	int status;
 
 	if (veb_seid == 0)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_veb_parameters);
@@ -2575,7 +2575,7 @@ i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid,
 	u16 buf_size;
 
 	if (count == 0 || !mv_list || !hw)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	buf_size = i40e_prepare_add_macvlan(mv_list, &desc, count, seid);
 
@@ -2608,7 +2608,7 @@ i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid,
 	u16 buf_size;
 
 	if (count == 0 || !mv_list || !hw)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	buf_size = i40e_prepare_add_macvlan(mv_list, &desc, count, seid);
 
@@ -2638,7 +2638,7 @@ i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid,
 	int status;
 
 	if (count == 0 || !mv_list || !hw)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	buf_size = count * sizeof(*mv_list);
 
@@ -2685,7 +2685,7 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid,
 	u16 buf_size;
 
 	if (count == 0 || !mv_list || !hw)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	buf_size = count * sizeof(*mv_list);
 
@@ -2791,7 +2791,7 @@ int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
 	if (!(rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS ||
 	    rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS)) {
 		if (count == 0 || !mr_list)
-			return I40E_ERR_PARAM;
+			return -EINVAL;
 	}
 
 	return i40e_mirrorrule_op(hw, i40e_aqc_opc_add_mirror_rule, sw_seid,
@@ -2827,7 +2827,7 @@ int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
 		 * not matter.
 		 */
 		if (count == 0 || !mr_list)
-			return I40E_ERR_PARAM;
+			return -EINVAL;
 	}
 
 	return i40e_mirrorrule_op(hw, i40e_aqc_opc_delete_mirror_rule, sw_seid,
@@ -2892,7 +2892,7 @@ int i40e_aq_debug_read_register(struct i40e_hw *hw,
 	int status;
 
 	if (reg_val == NULL)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_debug_read_reg);
 
@@ -3031,7 +3031,7 @@ int i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer,
 
 	/* In offset the highest byte must be zeroed. */
 	if (offset & 0xFF000000) {
-		status = I40E_ERR_PARAM;
+		status = -EINVAL;
 		goto i40e_aq_read_nvm_exit;
 	}
 
@@ -3076,7 +3076,7 @@ int i40e_aq_erase_nvm(struct i40e_hw *hw, u8 module_pointer,
 
 	/* In offset the highest byte must be zeroed. */
 	if (offset & 0xFF000000) {
-		status = I40E_ERR_PARAM;
+		status = -EINVAL;
 		goto i40e_aq_erase_nvm_exit;
 	}
 
@@ -3368,7 +3368,7 @@ int i40e_aq_discover_capabilities(struct i40e_hw *hw,
 
 	if (list_type_opc != i40e_aqc_opc_list_func_capabilities &&
 		list_type_opc != i40e_aqc_opc_list_dev_capabilities) {
-		status = I40E_ERR_PARAM;
+		status = -EINVAL;
 		goto exit;
 	}
 
@@ -3416,7 +3416,7 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 
 	/* In offset the highest byte must be zeroed. */
 	if (offset & 0xFF000000) {
-		status = I40E_ERR_PARAM;
+		status = -EINVAL;
 		goto i40e_aq_update_nvm_exit;
 	}
 
@@ -3473,7 +3473,7 @@ int i40e_aq_rearrange_nvm(struct i40e_hw *hw,
 			 I40E_AQ_NVM_REARRANGE_TO_STRUCT);
 
 	if (!rearrange_nvm) {
-		status = I40E_ERR_PARAM;
+		status = -EINVAL;
 		goto i40e_aq_rearrange_nvm_exit;
 	}
 
@@ -3510,7 +3510,7 @@ int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 	int status;
 
 	if (buff_size == 0 || !buff)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_get_mib);
 	/* Indirect Command */
@@ -3558,7 +3558,7 @@ i40e_aq_set_lldp_mib(struct i40e_hw *hw,
 
 	cmd = (struct i40e_aqc_lldp_set_local_mib *)&desc.params.raw;
 	if (buff_size == 0 || !buff)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_lldp_set_local_mib);
@@ -3627,7 +3627,7 @@ i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore,
 	if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)) {
 		i40e_debug(hw, I40E_DEBUG_ALL,
 			   "Restore LLDP not supported by current FW version.\n");
-		return I40E_ERR_DEVICE_NOT_SUPPORTED;
+		return -ENODEV;
 	}
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_restore);
@@ -3729,7 +3729,7 @@ i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable,
 	int status;
 
 	if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE))
-		return I40E_ERR_DEVICE_NOT_SUPPORTED;
+		return -ENODEV;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_dcb_parameters);
@@ -3760,7 +3760,7 @@ int i40e_aq_get_cee_dcb_config(struct i40e_hw *hw,
 	int status;
 
 	if (buff_size == 0 || !buff)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_cee_dcb_cfg);
 
@@ -3848,7 +3848,7 @@ int i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,
 	int status;
 
 	if (seid == 0)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_delete_element);
 
@@ -3922,7 +3922,7 @@ static int i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid,
 		cmd_param_flag = false;
 		break;
 	default:
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 	}
 
 	i40e_fill_default_direct_cmd_desc(&desc, opcode);
@@ -4148,7 +4148,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw,
 		fcoe_filt_size <<= (u32)settings->fcoe_filt_num;
 		break;
 	default:
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 	}
 
 	switch (settings->fcoe_cntx_num) {
@@ -4160,7 +4160,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw,
 		fcoe_cntx_size <<= (u32)settings->fcoe_cntx_num;
 		break;
 	default:
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 	}
 
 	/* Validate PE settings passed */
@@ -4178,7 +4178,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw,
 	case I40E_HASH_FILTER_SIZE_1M:
 		break;
 	default:
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 	}
 
 	switch (settings->pe_cntx_num) {
@@ -4194,7 +4194,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw,
 	case I40E_DMA_CNTX_SIZE_256K:
 		break;
 	default:
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 	}
 
 	/* FCHSIZE + FCDSIZE should not be greater than PMFCOEFMAX */
@@ -4202,7 +4202,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw,
 	fcoe_fmax = (val & I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_MASK)
 		     >> I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_SHIFT;
 	if (fcoe_filt_size + fcoe_cntx_size >  fcoe_fmax)
-		return I40E_ERR_INVALID_SIZE;
+		return -EINVAL;
 
 	return 0;
 }
@@ -4224,7 +4224,7 @@ int i40e_set_filter_control(struct i40e_hw *hw,
 	u32 val;
 
 	if (!settings)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	/* Validate the input settings */
 	ret = i40e_validate_filter_settings(hw, settings);
@@ -4306,7 +4306,7 @@ int i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw,
 	int status;
 
 	if (vsi_seid == 0)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	if (is_add) {
 		i40e_fill_default_direct_cmd_desc(&desc,
@@ -4381,7 +4381,7 @@ static int i40e_aq_alternate_read(struct i40e_hw *hw,
 	int status;
 
 	if (!reg_val0)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_alternate_read);
 	cmd_resp->address0 = cpu_to_le32(reg_addr0);
@@ -4517,7 +4517,7 @@ int i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id,
 	int status;
 
 	if (buff_size == 0 || !buff)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_debug_dump_internals);
@@ -4635,7 +4635,7 @@ int i40e_read_phy_register_clause22(struct i40e_hw *hw,
 				    u16 reg, u8 phy_addr, u16 *value)
 {
 	u8 port_num = (u8)hw->func_caps.mdio_port_num;
-	int status = I40E_ERR_TIMEOUT;
+	int status = -EIO;
 	u32 command = 0;
 	u16 retry = 1000;
 
@@ -4680,7 +4680,7 @@ int i40e_write_phy_register_clause22(struct i40e_hw *hw,
 				     u16 reg, u8 phy_addr, u16 value)
 {
 	u8 port_num = (u8)hw->func_caps.mdio_port_num;
-	int status = I40E_ERR_TIMEOUT;
+	int status = -EIO;
 	u32 command  = 0;
 	u16 retry = 1000;
 
@@ -4721,7 +4721,7 @@ int i40e_read_phy_register_clause45(struct i40e_hw *hw,
 				    u8 page, u16 reg, u8 phy_addr, u16 *value)
 {
 	u8 port_num = hw->func_caps.mdio_port_num;
-	int status = I40E_ERR_TIMEOUT;
+	int status = -EIO;
 	u32 command = 0;
 	u16 retry = 1000;
 
@@ -4755,7 +4755,7 @@ int i40e_read_phy_register_clause45(struct i40e_hw *hw,
 		  (I40E_MDIO_CLAUSE45_STCODE_MASK) |
 		  (I40E_GLGEN_MSCA_MDICMD_MASK) |
 		  (I40E_GLGEN_MSCA_MDIINPROGEN_MASK);
-	status = I40E_ERR_TIMEOUT;
+	status = -EIO;
 	retry = 1000;
 	wr32(hw, I40E_GLGEN_MSCA(port_num), command);
 	do {
@@ -4795,7 +4795,7 @@ int i40e_write_phy_register_clause45(struct i40e_hw *hw,
 				     u8 page, u16 reg, u8 phy_addr, u16 value)
 {
 	u8 port_num = hw->func_caps.mdio_port_num;
-	int status = I40E_ERR_TIMEOUT;
+	int status = -EIO;
 	u16 retry = 1000;
 	u32 command = 0;
 
@@ -4831,7 +4831,7 @@ int i40e_write_phy_register_clause45(struct i40e_hw *hw,
 		  (I40E_MDIO_CLAUSE45_STCODE_MASK) |
 		  (I40E_GLGEN_MSCA_MDICMD_MASK) |
 		  (I40E_GLGEN_MSCA_MDIINPROGEN_MASK);
-	status = I40E_ERR_TIMEOUT;
+	status = -EIO;
 	retry = 1000;
 	wr32(hw, I40E_GLGEN_MSCA(port_num), command);
 	do {
@@ -4880,7 +4880,7 @@ int i40e_write_phy_register(struct i40e_hw *hw,
 							  phy_addr, value);
 		break;
 	default:
-		status = I40E_ERR_UNKNOWN_PHY;
+		status = -EIO;
 		break;
 	}
 
@@ -4919,7 +4919,7 @@ int i40e_read_phy_register(struct i40e_hw *hw,
 							 phy_addr, value);
 		break;
 	default:
-		status = I40E_ERR_UNKNOWN_PHY;
+		status = -EIO;
 		break;
 	}
 
@@ -5109,7 +5109,7 @@ int i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr,
 					       I40E_PHY_COM_REG_PAGE, true,
 					       I40E_PHY_LED_PROV_REG_1,
 					       &reg_val_aq, NULL);
-		if (status == I40E_SUCCESS)
+		if (status == 0)
 			*val = (u16)reg_val_aq;
 		return status;
 	}
@@ -5204,7 +5204,7 @@ int i40e_aq_rx_ctl_read_register(struct i40e_hw *hw,
 	int status;
 
 	if (!reg_val)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_rx_ctl_reg_read);
 
@@ -5644,7 +5644,7 @@ i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
 
 	if (track_id == I40E_DDP_TRACKID_INVALID) {
 		i40e_debug(hw, I40E_DEBUG_PACKAGE, "Invalid track_id\n");
-		return I40E_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 	}
 
 	dev_cnt = profile->device_table_count;
@@ -5657,7 +5657,7 @@ i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
 	if (dev_cnt && i == dev_cnt) {
 		i40e_debug(hw, I40E_DEBUG_PACKAGE,
 			   "Device doesn't support DDP\n");
-		return I40E_ERR_DEVICE_NOT_SUPPORTED;
+		return -ENODEV;
 	}
 
 	I40E_SECTION_TABLE(profile, sec_tbl);
@@ -5672,14 +5672,14 @@ i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
 			    sec->section.type == SECTION_TYPE_RB_AQ) {
 				i40e_debug(hw, I40E_DEBUG_PACKAGE,
 					   "Not a roll-back package\n");
-				return I40E_NOT_SUPPORTED;
+				return -EOPNOTSUPP;
 			}
 		} else {
 			if (sec->section.type == SECTION_TYPE_RB_AQ ||
 			    sec->section.type == SECTION_TYPE_RB_MMIO) {
 				i40e_debug(hw, I40E_DEBUG_PACKAGE,
 					   "Not an original package\n");
-				return I40E_NOT_SUPPORTED;
+				return -EOPNOTSUPP;
 			}
 		}
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 90638b67f8dc8..f81e744c0fb36 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -17,7 +17,7 @@ int i40e_get_dcbx_status(struct i40e_hw *hw, u16 *status)
 	u32 reg;
 
 	if (!status)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	reg = rd32(hw, I40E_PRTDCB_GENS);
 	*status = (u16)((reg & I40E_PRTDCB_GENS_DCBX_STATUS_MASK) >>
@@ -508,7 +508,7 @@ int i40e_lldp_to_dcb_config(u8 *lldpmib,
 	u16 type;
 
 	if (!lldpmib || !dcbcfg)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	/* set to the start of LLDPDU */
 	lldpmib += ETH_HLEN;
@@ -874,7 +874,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change)
 	int ret = 0;
 
 	if (!hw->func_caps.dcb)
-		return I40E_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 
 	/* Read LLDP NVM area */
 	if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT) {
@@ -885,7 +885,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change)
 		else if (hw->mac.type == I40E_MAC_X722)
 			offset = I40E_LLDP_CURRENT_STATUS_X722_OFFSET;
 		else
-			return I40E_NOT_SUPPORTED;
+			return -EOPNOTSUPP;
 
 		ret = i40e_read_nvm_module_data(hw,
 						I40E_SR_EMP_SR_SETTINGS_PTR,
@@ -897,7 +897,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change)
 		ret = i40e_read_lldp_cfg(hw, &lldp_cfg);
 	}
 	if (ret)
-		return I40E_ERR_NOT_READY;
+		return -EBUSY;
 
 	/* Get the LLDP AdminStatus for the current port */
 	adminstatus = lldp_cfg.adminstatus >> (hw->port * 4);
@@ -906,7 +906,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change)
 	/* LLDP agent disabled */
 	if (!adminstatus) {
 		hw->dcbx_status = I40E_DCBX_STATUS_DISABLED;
-		return I40E_ERR_NOT_READY;
+		return -EBUSY;
 	}
 
 	/* Get DCBX status */
@@ -922,7 +922,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change)
 		if (ret)
 			return ret;
 	} else if (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED) {
-		return I40E_ERR_NOT_READY;
+		return -EBUSY;
 	}
 
 	/* Configure the LLDP MIB change event */
@@ -949,7 +949,7 @@ i40e_get_fw_lldp_status(struct i40e_hw *hw,
 	int ret;
 
 	if (!lldp_status)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	/* Allocate buffer for the LLDPDU */
 	ret = i40e_allocate_virt_mem(hw, &mem, I40E_LLDPDU_SIZE);
@@ -1299,7 +1299,7 @@ int i40e_dcb_config_to_lldp(u8 *lldpmib, u16 *miblen,
 			      sizeof(tlv->typelength) + length);
 	} while (tlvid < I40E_TLV_ID_END_OF_LLDPPDU);
 	*miblen = offset;
-	return I40E_SUCCESS;
+	return 0;
 }
 
 /**
@@ -1957,7 +1957,7 @@ int i40e_read_lldp_cfg(struct i40e_hw *hw,
 	u32 mem;
 
 	if (!lldp_cfg)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
 	if (ret)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
index 7e8183762fd95..969120587cad8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
@@ -344,7 +344,7 @@ int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size,
 	if (is_add) {
 		status = i40e_write_profile(&pf->hw, profile_hdr, track_id);
 		if (status) {
-			if (status == I40E_ERR_DEVICE_NOT_SUPPORTED) {
+			if (status == -ENODEV) {
 				netdev_err(netdev,
 					   "Profile is not supported by the device.");
 				return -EPERM;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 62497f5565c59..1a497cb077100 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -1309,7 +1309,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 		ret = i40e_asq_send_command(&pf->hw, desc, NULL, 0, NULL);
 		if (!ret) {
 			dev_info(&pf->pdev->dev, "AQ command sent Status : Success\n");
-		} else if (ret == I40E_ERR_ADMIN_QUEUE_ERROR) {
+		} else if (ret == -EIO) {
 			dev_info(&pf->pdev->dev,
 				 "AQ command send failed Opcode %x AQ Error: %d\n",
 				 desc->opcode, pf->hw.aq.asq_last_status);
@@ -1370,7 +1370,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 					    buffer_len, NULL);
 		if (!ret) {
 			dev_info(&pf->pdev->dev, "AQ command sent Status : Success\n");
-		} else if (ret == I40E_ERR_ADMIN_QUEUE_ERROR) {
+		} else if (ret == -EIO) {
 			dev_info(&pf->pdev->dev,
 				 "AQ command send failed Opcode %x AQ Error: %d\n",
 				 desc->opcode, pf->hw.aq.asq_last_status);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c
index 97fe1787a8f4a..b1ad7c4259b96 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_diag.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c
@@ -28,7 +28,7 @@ static int i40e_diag_reg_pattern_test(struct i40e_hw *hw,
 			i40e_debug(hw, I40E_DEBUG_DIAG,
 				   "%s: reg pattern test failed - reg 0x%08x pat 0x%08x val 0x%08x\n",
 				   __func__, reg, pat, val);
-			return I40E_ERR_DIAG_TEST_FAILED;
+			return -EIO;
 		}
 	}
 
@@ -38,7 +38,7 @@ static int i40e_diag_reg_pattern_test(struct i40e_hw *hw,
 		i40e_debug(hw, I40E_DEBUG_DIAG,
 			   "%s: reg restore test failed - reg 0x%08x orig_val 0x%08x val 0x%08x\n",
 			   __func__, reg, orig_val, val);
-		return I40E_ERR_DIAG_TEST_FAILED;
+		return -EIO;
 	}
 
 	return 0;
@@ -127,5 +127,5 @@ int i40e_diag_eeprom_test(struct i40e_hw *hw)
 	     BIT(I40E_SR_CONTROL_WORD_1_SHIFT)))
 		return i40e_validate_nvm_checksum(hw, NULL);
 	else
-		return I40E_ERR_DIAG_TEST_FAILED;
+		return -EIO;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index afc4fa8c66af4..bd1321bf7e268 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -5699,8 +5699,8 @@ static int i40e_set_eee(struct net_device *netdev, struct ethtool_eee *edata)
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
 	struct i40e_hw *hw = &pf->hw;
-	int status = I40E_SUCCESS;
 	__le16 eee_capability;
+	int status = 0;
 
 	/* Deny parameters we don't support */
 	if (i40e_is_eee_param_supported(netdev, edata))
diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c
index 46f7950a0049a..96ee63aca7a10 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_hmc.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c
@@ -4,7 +4,6 @@
 #include "i40e.h"
 #include "i40e_osdep.h"
 #include "i40e_register.h"
-#include "i40e_status.h"
 #include "i40e_alloc.h"
 #include "i40e_hmc.h"
 #include "i40e_type.h"
@@ -26,18 +25,18 @@ int i40e_add_sd_table_entry(struct i40e_hw *hw,
 	enum i40e_memory_type mem_type __attribute__((unused));
 	struct i40e_hmc_sd_entry *sd_entry;
 	bool dma_mem_alloc_done = false;
-	int ret_code = I40E_SUCCESS;
 	struct i40e_dma_mem mem;
+	int ret_code = 0;
 	u64 alloc_len;
 
 	if (NULL == hmc_info->sd_table.sd_entry) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_add_sd_table_entry: bad sd_entry\n");
 		goto exit;
 	}
 
 	if (sd_index >= hmc_info->sd_table.sd_cnt) {
-		ret_code = I40E_ERR_INVALID_SD_INDEX;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_add_sd_table_entry: bad sd_index\n");
 		goto exit;
 	}
@@ -121,7 +120,7 @@ int i40e_add_pd_table_entry(struct i40e_hw *hw,
 	u64 *pd_addr;
 
 	if (pd_index / I40E_HMC_PD_CNT_IN_SD >= hmc_info->sd_table.sd_cnt) {
-		ret_code = I40E_ERR_INVALID_PAGE_DESC_INDEX;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_add_pd_table_entry: bad pd_index\n");
 		goto exit;
 	}
@@ -200,13 +199,13 @@ int i40e_remove_pd_bp(struct i40e_hw *hw,
 	sd_idx = idx / I40E_HMC_PD_CNT_IN_SD;
 	rel_pd_idx = idx % I40E_HMC_PD_CNT_IN_SD;
 	if (sd_idx >= hmc_info->sd_table.sd_cnt) {
-		ret_code = I40E_ERR_INVALID_PAGE_DESC_INDEX;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_remove_pd_bp: bad idx\n");
 		goto exit;
 	}
 	sd_entry = &hmc_info->sd_table.sd_entry[sd_idx];
 	if (I40E_SD_TYPE_PAGED != sd_entry->entry_type) {
-		ret_code = I40E_ERR_INVALID_SD_TYPE;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_remove_pd_bp: wrong sd_entry type\n");
 		goto exit;
 	}
@@ -251,7 +250,7 @@ int i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info,
 	sd_entry = &hmc_info->sd_table.sd_entry[idx];
 	I40E_DEC_BP_REFCNT(&sd_entry->u.bp);
 	if (sd_entry->u.bp.ref_cnt) {
-		ret_code = I40E_ERR_NOT_READY;
+		ret_code = -EBUSY;
 		goto exit;
 	}
 	I40E_DEC_SD_REFCNT(&hmc_info->sd_table);
@@ -276,7 +275,7 @@ int i40e_remove_sd_bp_new(struct i40e_hw *hw,
 	struct i40e_hmc_sd_entry *sd_entry;
 
 	if (!is_pf)
-		return I40E_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 
 	/* get the entry and decrease its ref counter */
 	sd_entry = &hmc_info->sd_table.sd_entry[idx];
@@ -299,7 +298,7 @@ int i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info,
 	sd_entry = &hmc_info->sd_table.sd_entry[idx];
 
 	if (sd_entry->u.pd_table.ref_cnt) {
-		ret_code = I40E_ERR_NOT_READY;
+		ret_code = -EBUSY;
 		goto exit;
 	}
 
@@ -325,7 +324,7 @@ int i40e_remove_pd_page_new(struct i40e_hw *hw,
 	struct i40e_hmc_sd_entry *sd_entry;
 
 	if (!is_pf)
-		return I40E_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 
 	sd_entry = &hmc_info->sd_table.sd_entry[idx];
 	I40E_CLEAR_PF_SD_ENTRY(hw, idx, I40E_SD_TYPE_PAGED);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
index 40c101f286d19..474365bf06480 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
@@ -111,7 +111,7 @@ int i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num,
 
 	/* validate values requested by driver don't exceed HMC capacity */
 	if (txq_num > obj->max_cnt) {
-		ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_init_lan_hmc: Tx context: asks for 0x%x but max allowed is 0x%x, returns error %d\n",
 			  txq_num, obj->max_cnt, ret_code);
 		goto init_lan_hmc_out;
@@ -134,7 +134,7 @@ int i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num,
 
 	/* validate values requested by driver don't exceed HMC capacity */
 	if (rxq_num > obj->max_cnt) {
-		ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_init_lan_hmc: Rx context: asks for 0x%x but max allowed is 0x%x, returns error %d\n",
 			  rxq_num, obj->max_cnt, ret_code);
 		goto init_lan_hmc_out;
@@ -157,7 +157,7 @@ int i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num,
 
 	/* validate values requested by driver don't exceed HMC capacity */
 	if (fcoe_cntx_num > obj->max_cnt) {
-		ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_init_lan_hmc: FCoE context: asks for 0x%x but max allowed is 0x%x, returns error %d\n",
 			  fcoe_cntx_num, obj->max_cnt, ret_code);
 		goto init_lan_hmc_out;
@@ -180,7 +180,7 @@ int i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num,
 
 	/* validate values requested by driver don't exceed HMC capacity */
 	if (fcoe_filt_num > obj->max_cnt) {
-		ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_init_lan_hmc: FCoE filter: asks for 0x%x but max allowed is 0x%x, returns error %d\n",
 			  fcoe_filt_num, obj->max_cnt, ret_code);
 		goto init_lan_hmc_out;
@@ -289,30 +289,30 @@ static int i40e_create_lan_hmc_object(struct i40e_hw *hw,
 	u32 i, j;
 
 	if (NULL == info) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_create_lan_hmc_object: bad info ptr\n");
 		goto exit;
 	}
 	if (NULL == info->hmc_info) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_create_lan_hmc_object: bad hmc_info ptr\n");
 		goto exit;
 	}
 	if (I40E_HMC_INFO_SIGNATURE != info->hmc_info->signature) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_create_lan_hmc_object: bad signature\n");
 		goto exit;
 	}
 
 	if (info->start_idx >= info->hmc_info->hmc_obj[info->rsrc_type].cnt) {
-		ret_code = I40E_ERR_INVALID_HMC_OBJ_INDEX;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_create_lan_hmc_object: returns error %d\n",
 			  ret_code);
 		goto exit;
 	}
 	if ((info->start_idx + info->count) >
 	    info->hmc_info->hmc_obj[info->rsrc_type].cnt) {
-		ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_create_lan_hmc_object: returns error %d\n",
 			  ret_code);
 		goto exit;
@@ -324,8 +324,8 @@ static int i40e_create_lan_hmc_object(struct i40e_hw *hw,
 				 &sd_idx, &sd_lmt);
 	if (sd_idx >= info->hmc_info->sd_table.sd_cnt ||
 	    sd_lmt > info->hmc_info->sd_table.sd_cnt) {
-			ret_code = I40E_ERR_INVALID_SD_INDEX;
-			goto exit;
+		ret_code = -EINVAL;
+		goto exit;
 	}
 	/* find pd index */
 	I40E_FIND_PD_INDEX_LIMIT(info->hmc_info, info->rsrc_type,
@@ -393,7 +393,7 @@ static int i40e_create_lan_hmc_object(struct i40e_hw *hw,
 						     j, sd_entry->entry_type);
 				break;
 			default:
-				ret_code = I40E_ERR_INVALID_SD_TYPE;
+				ret_code = -EINVAL;
 				goto exit;
 			}
 		}
@@ -417,7 +417,7 @@ exit_sd_error:
 			i40e_remove_sd_bp(hw, info->hmc_info, (j - 1));
 			break;
 		default:
-			ret_code = I40E_ERR_INVALID_SD_TYPE;
+			ret_code = -EINVAL;
 			break;
 		}
 		j--;
@@ -474,7 +474,7 @@ try_type_paged:
 		break;
 	default:
 		/* unsupported type */
-		ret_code = I40E_ERR_INVALID_SD_TYPE;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_configure_lan_hmc: Unknown SD type: %d\n",
 			  ret_code);
 		goto configure_lan_hmc_out;
@@ -530,34 +530,34 @@ static int i40e_delete_lan_hmc_object(struct i40e_hw *hw,
 	u32 i, j;
 
 	if (NULL == info) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_delete_hmc_object: bad info ptr\n");
 		goto exit;
 	}
 	if (NULL == info->hmc_info) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_delete_hmc_object: bad info->hmc_info ptr\n");
 		goto exit;
 	}
 	if (I40E_HMC_INFO_SIGNATURE != info->hmc_info->signature) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_delete_hmc_object: bad hmc_info->signature\n");
 		goto exit;
 	}
 
 	if (NULL == info->hmc_info->sd_table.sd_entry) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_delete_hmc_object: bad sd_entry\n");
 		goto exit;
 	}
 
 	if (NULL == info->hmc_info->hmc_obj) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_delete_hmc_object: bad hmc_info->hmc_obj\n");
 		goto exit;
 	}
 	if (info->start_idx >= info->hmc_info->hmc_obj[info->rsrc_type].cnt) {
-		ret_code = I40E_ERR_INVALID_HMC_OBJ_INDEX;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_delete_hmc_object: returns error %d\n",
 			  ret_code);
 		goto exit;
@@ -565,7 +565,7 @@ static int i40e_delete_lan_hmc_object(struct i40e_hw *hw,
 
 	if ((info->start_idx + info->count) >
 	    info->hmc_info->hmc_obj[info->rsrc_type].cnt) {
-		ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_delete_hmc_object: returns error %d\n",
 			  ret_code);
 		goto exit;
@@ -599,7 +599,7 @@ static int i40e_delete_lan_hmc_object(struct i40e_hw *hw,
 				 &sd_idx, &sd_lmt);
 	if (sd_idx >= info->hmc_info->sd_table.sd_cnt ||
 	    sd_lmt > info->hmc_info->sd_table.sd_cnt) {
-		ret_code = I40E_ERR_INVALID_SD_INDEX;
+		ret_code = -EINVAL;
 		goto exit;
 	}
 
@@ -987,29 +987,29 @@ int i40e_hmc_get_object_va(struct i40e_hw *hw, u8 **object_base,
 	int ret_code = 0;
 
 	if (NULL == hmc_info) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_hmc_get_object_va: bad hmc_info ptr\n");
 		goto exit;
 	}
 	if (NULL == hmc_info->hmc_obj) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_hmc_get_object_va: bad hmc_info->hmc_obj ptr\n");
 		goto exit;
 	}
 	if (NULL == object_base) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_hmc_get_object_va: bad object_base ptr\n");
 		goto exit;
 	}
 	if (I40E_HMC_INFO_SIGNATURE != hmc_info->signature) {
-		ret_code = I40E_ERR_BAD_PTR;
+		ret_code = -EINVAL;
 		hw_dbg(hw, "i40e_hmc_get_object_va: bad hmc_info->signature\n");
 		goto exit;
 	}
 	if (obj_idx >= hmc_info->hmc_obj[rsrc_type].cnt) {
 		hw_dbg(hw, "i40e_hmc_get_object_va: returns error %d\n",
 			  ret_code);
-		ret_code = I40E_ERR_INVALID_HMC_OBJ_INDEX;
+		ret_code = -EINVAL;
 		goto exit;
 	}
 	/* find sd index and limit */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 3d0d6974c2a79..a5ba873c3b245 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -5709,7 +5709,7 @@ int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset)
 	int ret;
 
 	if (!vsi)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 	pf = vsi->back;
 	hw = &pf->hw;
 
@@ -7153,7 +7153,7 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 	 */
 	if (pf->hw_features & I40E_HW_NO_DCB_SUPPORT) {
 		dev_info(&pf->pdev->dev, "DCB is not supported.\n");
-		err = I40E_NOT_SUPPORTED;
+		err = -EOPNOTSUPP;
 		goto out;
 	}
 	if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) {
@@ -7463,7 +7463,7 @@ static int i40e_force_link_state(struct i40e_pf *pf, bool is_up)
 	if (pf->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED)
 		non_zero_phy_type = true;
 	else if (is_up && abilities.phy_type != 0 && abilities.link_speed != 0)
-		return I40E_SUCCESS;
+		return 0;
 
 	/* To force link we need to set bits for all supported PHY types,
 	 * but there are now more than 32, so we need to split the bitmap
@@ -7514,7 +7514,7 @@ static int i40e_force_link_state(struct i40e_pf *pf, bool is_up)
 
 	i40e_aq_set_link_restart_an(hw, is_up, NULL);
 
-	return I40E_SUCCESS;
+	return 0;
 }
 
 /**
@@ -8361,7 +8361,7 @@ int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
 	};
 
 	if (filter->flags >= ARRAY_SIZE(flag_table))
-		return I40E_ERR_CONFIG;
+		return -EIO;
 
 	memset(&cld_filter, 0, sizeof(cld_filter));
 
@@ -8575,7 +8575,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n",
 					match.mask->dst);
-				return I40E_ERR_CONFIG;
+				return -EIO;
 			}
 		}
 
@@ -8585,7 +8585,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n",
 					match.mask->src);
-				return I40E_ERR_CONFIG;
+				return -EIO;
 			}
 		}
 		ether_addr_copy(filter->dst_mac, match.key->dst);
@@ -8603,7 +8603,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 			} else {
 				dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n",
 					match.mask->vlan_id);
-				return I40E_ERR_CONFIG;
+				return -EIO;
 			}
 		}
 
@@ -8627,7 +8627,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4b\n",
 					&match.mask->dst);
-				return I40E_ERR_CONFIG;
+				return -EIO;
 			}
 		}
 
@@ -8637,13 +8637,13 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ip src mask %pI4b\n",
 					&match.mask->src);
-				return I40E_ERR_CONFIG;
+				return -EIO;
 			}
 		}
 
 		if (field_flags & I40E_CLOUD_FIELD_TEN_ID) {
 			dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n");
-			return I40E_ERR_CONFIG;
+			return -EIO;
 		}
 		filter->dst_ipv4 = match.key->dst;
 		filter->src_ipv4 = match.key->src;
@@ -8661,7 +8661,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 		    ipv6_addr_loopback(&match.key->src)) {
 			dev_err(&pf->pdev->dev,
 				"Bad ipv6, addr is LOOPBACK\n");
-			return I40E_ERR_CONFIG;
+			return -EIO;
 		}
 		if (!ipv6_addr_any(&match.mask->dst) ||
 		    !ipv6_addr_any(&match.mask->src))
@@ -8683,7 +8683,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 			} else {
 				dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n",
 					be16_to_cpu(match.mask->src));
-				return I40E_ERR_CONFIG;
+				return -EIO;
 			}
 		}
 
@@ -8693,7 +8693,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 			} else {
 				dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n",
 					be16_to_cpu(match.mask->dst));
-				return I40E_ERR_CONFIG;
+				return -EIO;
 			}
 		}
 
@@ -9901,11 +9901,11 @@ static void i40e_link_event(struct i40e_pf *pf)
 	status = i40e_get_link_status(&pf->hw, &new_link);
 
 	/* On success, disable temp link polling */
-	if (status == I40E_SUCCESS) {
+	if (status == 0) {
 		clear_bit(__I40E_TEMP_LINK_POLLING, pf->state);
 	} else {
 		/* Enable link polling temporarily until i40e_get_link_status
-		 * returns I40E_SUCCESS
+		 * returns 0
 		 */
 		set_bit(__I40E_TEMP_LINK_POLLING, pf->state);
 		dev_dbg(&pf->pdev->dev, "couldn't get link state, status: %d\n",
@@ -10159,7 +10159,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 
 	do {
 		ret = i40e_clean_arq_element(hw, &event, &pending);
-		if (ret == I40E_ERR_ADMIN_QUEUE_NO_WORK)
+		if (ret == -EALREADY)
 			break;
 		else if (ret) {
 			dev_info(&pf->pdev->dev, "ARQ event error %d\n", ret);
@@ -12569,7 +12569,7 @@ int i40e_commit_partition_bw_setting(struct i40e_pf *pf)
 		dev_info(&pf->pdev->dev,
 			 "Commit BW only works on partition 1! This is partition %d",
 			 pf->hw.partition_id);
-		ret = I40E_NOT_SUPPORTED;
+		ret = -EOPNOTSUPP;
 		goto bw_commit_out;
 	}
 
@@ -12651,10 +12651,10 @@ static bool i40e_is_total_port_shutdown_enabled(struct i40e_pf *pf)
 #define I40E_LINK_BEHAVIOR_WORD_LENGTH		0x1
 #define I40E_LINK_BEHAVIOR_OS_FORCED_ENABLED	BIT(0)
 #define I40E_LINK_BEHAVIOR_PORT_BIT_LENGTH	4
-	int read_status = I40E_SUCCESS;
 	u16 sr_emp_sr_settings_ptr = 0;
 	u16 features_enable = 0;
 	u16 link_behavior = 0;
+	int read_status = 0;
 	bool ret = false;
 
 	read_status = i40e_read_nvm_word(&pf->hw,
@@ -15462,12 +15462,12 @@ static int i40e_pf_loop_reset(struct i40e_pf *pf)
 	int ret;
 
 	ret = i40e_pf_reset(hw);
-	while (ret != I40E_SUCCESS && time_before(jiffies, time_end)) {
+	while (ret != 0 && time_before(jiffies, time_end)) {
 		usleep_range(10000, 20000);
 		ret = i40e_pf_reset(hw);
 	}
 
-	if (ret == I40E_SUCCESS)
+	if (ret == 0)
 		pf->pfr_count++;
 	else
 		dev_info(&pf->pdev->dev, "PF reset failed: %d\n", ret);
@@ -15510,10 +15510,10 @@ static int i40e_handle_resets(struct i40e_pf *pf)
 	const int pfr = i40e_pf_loop_reset(pf);
 	const bool is_empr = i40e_check_fw_empr(pf);
 
-	if (is_empr || pfr != I40E_SUCCESS)
+	if (is_empr || pfr != 0)
 		dev_crit(&pf->pdev->dev, "Entering recovery mode due to repeated FW resets. This may take several minutes. Refer to the Intel(R) Ethernet Adapters and Devices User Guide.\n");
 
-	return is_empr ? I40E_ERR_RESET_FAILED : pfr;
+	return is_empr ? -EIO : pfr;
 }
 
 /**
@@ -15806,7 +15806,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	err = i40e_init_adminq(hw);
 	if (err) {
-		if (err == I40E_ERR_FIRMWARE_API_VERSION)
+		if (err == -EIO)
 			dev_info(&pdev->dev,
 				 "The driver for the device stopped because the NVM image v%u.%u is newer than expected v%u.%u. You must install the most recent version of the network driver.\n",
 				 hw->aq.api_maj_ver,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 9da0c87f03288..4bb300fbb777b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -37,7 +37,7 @@ int i40e_init_nvm(struct i40e_hw *hw)
 		nvm->blank_nvm_mode = false;
 	} else { /* Blank programming mode */
 		nvm->blank_nvm_mode = true;
-		ret_code = I40E_ERR_NVM_BLANK_MODE;
+		ret_code = -EIO;
 		i40e_debug(hw, I40E_DEBUG_NVM, "NVM init error: unsupported blank mode.\n");
 	}
 
@@ -111,8 +111,8 @@ i40e_i40e_acquire_nvm_exit:
  **/
 void i40e_release_nvm(struct i40e_hw *hw)
 {
-	int ret_code = I40E_SUCCESS;
 	u32 total_delay = 0;
+	int ret_code = 0;
 
 	if (hw->nvm.blank_nvm_mode)
 		return;
@@ -122,7 +122,7 @@ void i40e_release_nvm(struct i40e_hw *hw)
 	/* there are some rare cases when trying to release the resource
 	 * results in an admin Q timeout, so handle them correctly
 	 */
-	while ((ret_code == I40E_ERR_ADMIN_QUEUE_TIMEOUT) &&
+	while ((ret_code == -EIO) &&
 	       (total_delay < hw->aq.asq_cmd_timeout)) {
 		usleep_range(1000, 2000);
 		ret_code = i40e_aq_release_resource(hw,
@@ -140,7 +140,7 @@ void i40e_release_nvm(struct i40e_hw *hw)
  **/
 static int i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw)
 {
-	int ret_code = I40E_ERR_TIMEOUT;
+	int ret_code = -EIO;
 	u32 srctl, wait_cnt;
 
 	/* Poll the I40E_GLNVM_SRCTL until the done bit is set */
@@ -152,7 +152,7 @@ static int i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw)
 		}
 		udelay(5);
 	}
-	if (ret_code == I40E_ERR_TIMEOUT)
+	if (ret_code == -EIO)
 		i40e_debug(hw, I40E_DEBUG_NVM, "Done bit in GLNVM_SRCTL not set");
 	return ret_code;
 }
@@ -168,14 +168,14 @@ static int i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw)
 static int i40e_read_nvm_word_srctl(struct i40e_hw *hw, u16 offset,
 				    u16 *data)
 {
-	int ret_code = I40E_ERR_TIMEOUT;
+	int ret_code = -EIO;
 	u32 sr_reg;
 
 	if (offset >= hw->nvm.sr_size) {
 		i40e_debug(hw, I40E_DEBUG_NVM,
 			   "NVM read error: offset %d beyond Shadow RAM limit %d\n",
 			   offset, hw->nvm.sr_size);
-		ret_code = I40E_ERR_PARAM;
+		ret_code = -EINVAL;
 		goto read_nvm_exit;
 	}
 
@@ -222,7 +222,7 @@ static int i40e_read_nvm_aq(struct i40e_hw *hw,
 			    bool last_command)
 {
 	struct i40e_asq_cmd_details cmd_details;
-	int ret_code = I40E_ERR_NVM;
+	int ret_code = -EIO;
 
 	memset(&cmd_details, 0, sizeof(cmd_details));
 	cmd_details.wb_desc = &hw->nvm_wb_desc;
@@ -267,7 +267,7 @@ static int i40e_read_nvm_aq(struct i40e_hw *hw,
 static int i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset,
 				 u16 *data)
 {
-	int ret_code = I40E_ERR_TIMEOUT;
+	int ret_code = -EIO;
 
 	ret_code = i40e_read_nvm_aq(hw, 0x0, offset, 1, data, true);
 	*data = le16_to_cpu(*(__le16 *)data);
@@ -348,7 +348,7 @@ int i40e_read_nvm_module_data(struct i40e_hw *hw,
 			i40e_debug(hw, I40E_DEBUG_ALL,
 				   "Reading nvm word failed.Error code: %d.\n",
 				   status);
-			return I40E_ERR_NVM;
+			return -EIO;
 		}
 	}
 #define I40E_NVM_INVALID_PTR_VAL 0x7FFF
@@ -358,7 +358,7 @@ int i40e_read_nvm_module_data(struct i40e_hw *hw,
 	if (ptr_value == I40E_NVM_INVALID_PTR_VAL ||
 	    ptr_value == I40E_NVM_INVALID_VAL) {
 		i40e_debug(hw, I40E_DEBUG_ALL, "Pointer not initialized.\n");
-		return I40E_ERR_BAD_PTR;
+		return -EINVAL;
 	}
 
 	/* Check whether the module is in SR mapped area or outside */
@@ -367,7 +367,7 @@ int i40e_read_nvm_module_data(struct i40e_hw *hw,
 		i40e_debug(hw, I40E_DEBUG_ALL,
 			   "Reading nvm data failed. Pointer points outside of the Shared RAM mapped area.\n");
 
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 	} else {
 		/* Read from the Shadow RAM */
 
@@ -377,7 +377,7 @@ int i40e_read_nvm_module_data(struct i40e_hw *hw,
 			i40e_debug(hw, I40E_DEBUG_ALL,
 				   "Reading nvm word failed.Error code: %d.\n",
 				   status);
-			return I40E_ERR_NVM;
+			return -EIO;
 		}
 
 		offset = ptr_value + module_offset + specific_ptr +
@@ -549,7 +549,7 @@ static int i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer,
 			     bool last_command)
 {
 	struct i40e_asq_cmd_details cmd_details;
-	int ret_code = I40E_ERR_NVM;
+	int ret_code = -EIO;
 
 	memset(&cmd_details, 0, sizeof(cmd_details));
 	cmd_details.wb_desc = &hw->nvm_wb_desc;
@@ -614,7 +614,7 @@ static int i40e_calc_nvm_checksum(struct i40e_hw *hw,
 	/* read pointer to VPD area */
 	ret_code = __i40e_read_nvm_word(hw, I40E_SR_VPD_PTR, &vpd_module);
 	if (ret_code) {
-		ret_code = I40E_ERR_NVM_CHECKSUM;
+		ret_code = -EIO;
 		goto i40e_calc_nvm_checksum_exit;
 	}
 
@@ -622,7 +622,7 @@ static int i40e_calc_nvm_checksum(struct i40e_hw *hw,
 	ret_code = __i40e_read_nvm_word(hw, I40E_SR_PCIE_ALT_AUTO_LOAD_PTR,
 					&pcie_alt_module);
 	if (ret_code) {
-		ret_code = I40E_ERR_NVM_CHECKSUM;
+		ret_code = -EIO;
 		goto i40e_calc_nvm_checksum_exit;
 	}
 
@@ -636,7 +636,7 @@ static int i40e_calc_nvm_checksum(struct i40e_hw *hw,
 
 			ret_code = __i40e_read_nvm_buffer(hw, i, &words, data);
 			if (ret_code) {
-				ret_code = I40E_ERR_NVM_CHECKSUM;
+				ret_code = -EIO;
 				goto i40e_calc_nvm_checksum_exit;
 			}
 		}
@@ -724,7 +724,7 @@ int i40e_validate_nvm_checksum(struct i40e_hw *hw,
 	 * calculated checksum
 	 */
 	if (checksum_local != checksum_sr)
-		ret_code = I40E_ERR_NVM_CHECKSUM;
+		ret_code = -EIO;
 
 	/* If the user cares, return the calculated checksum */
 	if (checksum)
@@ -839,7 +839,7 @@ int i40e_nvmupd_command(struct i40e_hw *hw,
 	if (upd_cmd == I40E_NVMUPD_STATUS) {
 		if (!cmd->data_size) {
 			*perrno = -EFAULT;
-			return I40E_ERR_BUF_TOO_SHORT;
+			return -EINVAL;
 		}
 
 		bytes[0] = hw->nvmupd_state;
@@ -896,7 +896,7 @@ int i40e_nvmupd_command(struct i40e_hw *hw,
 			break;
 		}
 
-		status = I40E_ERR_NOT_READY;
+		status = -EBUSY;
 		*perrno = -EBUSY;
 		break;
 
@@ -904,7 +904,7 @@ int i40e_nvmupd_command(struct i40e_hw *hw,
 		/* invalid state, should never happen */
 		i40e_debug(hw, I40E_DEBUG_NVM,
 			   "NVMUPD: no such state %d\n", hw->nvmupd_state);
-		status = I40E_NOT_SUPPORTED;
+		status = -EOPNOTSUPP;
 		*perrno = -ESRCH;
 		break;
 	}
@@ -1045,7 +1045,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw,
 		i40e_debug(hw, I40E_DEBUG_NVM,
 			   "NVMUPD: bad cmd %s in init state\n",
 			   i40e_nvm_update_state_str[upd_cmd]);
-		status = I40E_ERR_NVM;
+		status = -EIO;
 		*perrno = -ESRCH;
 		break;
 	}
@@ -1087,7 +1087,7 @@ static int i40e_nvmupd_state_reading(struct i40e_hw *hw,
 		i40e_debug(hw, I40E_DEBUG_NVM,
 			   "NVMUPD: bad cmd %s in reading state.\n",
 			   i40e_nvm_update_state_str[upd_cmd]);
-		status = I40E_NOT_SUPPORTED;
+		status = -EOPNOTSUPP;
 		*perrno = -ESRCH;
 		break;
 	}
@@ -1174,7 +1174,7 @@ retry:
 		i40e_debug(hw, I40E_DEBUG_NVM,
 			   "NVMUPD: bad cmd %s in writing state.\n",
 			   i40e_nvm_update_state_str[upd_cmd]);
-		status = I40E_NOT_SUPPORTED;
+		status = -EOPNOTSUPP;
 		*perrno = -ESRCH;
 		break;
 	}
@@ -1398,7 +1398,7 @@ static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
 			   "NVMUPD: not enough aq desc bytes for exec, size %d < %d\n",
 			   cmd->data_size, aq_desc_len);
 		*perrno = -EINVAL;
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 	}
 	aq_desc = (struct i40e_aq_desc *)bytes;
 
@@ -1473,7 +1473,7 @@ static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw,
 		i40e_debug(hw, I40E_DEBUG_NVM, "%s: offset too big %d > %d\n",
 			   __func__, cmd->offset, aq_total_len);
 		*perrno = -EINVAL;
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 	}
 
 	/* check copylength range */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index c37abbb3cd068..8a26811140b47 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -1132,7 +1132,7 @@ int i40e_ptp_alloc_pins(struct i40e_pf *pf)
 
 	if (!pf->ptp_pins) {
 		dev_warn(&pf->pdev->dev, "Cannot allocate memory for PTP pins structure.\n");
-		return -I40E_ERR_NO_MEMORY;
+		return -ENOMEM;
 	}
 
 	pf->ptp_pins->sdp3_2 = off;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_status.h b/drivers/net/ethernet/intel/i40e/i40e_status.h
deleted file mode 100644
index 4d2782e76038b..0000000000000
--- a/drivers/net/ethernet/intel/i40e/i40e_status.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_STATUS_H_
-#define _I40E_STATUS_H_
-
-/* Error Codes */
-enum i40e_status_code {
-	I40E_SUCCESS				= 0,
-	I40E_ERR_NVM				= -1,
-	I40E_ERR_NVM_CHECKSUM			= -2,
-	I40E_ERR_CONFIG				= -4,
-	I40E_ERR_PARAM				= -5,
-	I40E_ERR_UNKNOWN_PHY			= -7,
-	I40E_ERR_INVALID_MAC_ADDR		= -10,
-	I40E_ERR_DEVICE_NOT_SUPPORTED		= -11,
-	I40E_ERR_RESET_FAILED			= -15,
-	I40E_ERR_NO_AVAILABLE_VSI		= -17,
-	I40E_ERR_NO_MEMORY			= -18,
-	I40E_ERR_BAD_PTR			= -19,
-	I40E_ERR_INVALID_SIZE			= -26,
-	I40E_ERR_QUEUE_EMPTY			= -32,
-	I40E_ERR_TIMEOUT			= -37,
-	I40E_ERR_INVALID_SD_INDEX		= -45,
-	I40E_ERR_INVALID_PAGE_DESC_INDEX	= -46,
-	I40E_ERR_INVALID_SD_TYPE		= -47,
-	I40E_ERR_INVALID_HMC_OBJ_INDEX		= -49,
-	I40E_ERR_INVALID_HMC_OBJ_COUNT		= -50,
-	I40E_ERR_ADMIN_QUEUE_ERROR		= -53,
-	I40E_ERR_ADMIN_QUEUE_TIMEOUT		= -54,
-	I40E_ERR_BUF_TOO_SHORT			= -55,
-	I40E_ERR_ADMIN_QUEUE_FULL		= -56,
-	I40E_ERR_ADMIN_QUEUE_NO_WORK		= -57,
-	I40E_ERR_NVM_BLANK_MODE			= -59,
-	I40E_ERR_NOT_IMPLEMENTED		= -60,
-	I40E_ERR_DIAG_TEST_FAILED		= -62,
-	I40E_ERR_NOT_READY			= -63,
-	I40E_NOT_SUPPORTED			= -64,
-	I40E_ERR_FIRMWARE_API_VERSION		= -65,
-	I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR	= -66,
-};
-
-#endif /* _I40E_STATUS_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 388c3d36d96a5..5f61546f50d8f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -4,7 +4,6 @@
 #ifndef _I40E_TYPE_H_
 #define _I40E_TYPE_H_
 
-#include "i40e_status.h"
 #include "i40e_osdep.h"
 #include "i40e_register.h"
 #include "i40e_adminq.h"
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 398fb4854cbe0..98aca9f8b602d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1346,14 +1346,14 @@ static int i40e_config_vf_promiscuous_mode(struct i40e_vf *vf,
 					   bool alluni)
 {
 	struct i40e_pf *pf = vf->pf;
-	int aq_ret = I40E_SUCCESS;
 	struct i40e_vsi *vsi;
+	int aq_ret = 0;
 	u16 num_vlans;
 	s16 *vl;
 
 	vsi = i40e_find_vsi_from_id(pf, vsi_id);
 	if (!i40e_vc_isvalid_vsi_id(vf, vsi_id) || !vsi)
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	if (vf->port_vlan_id) {
 		aq_ret = i40e_set_vsi_promisc(vf, vsi->seid, allmulti,
@@ -1363,7 +1363,7 @@ static int i40e_config_vf_promiscuous_mode(struct i40e_vf *vf,
 		i40e_get_vlan_list_sync(vsi, &num_vlans, &vl);
 
 		if (!vl)
-			return I40E_ERR_NO_MEMORY;
+			return -ENOMEM;
 
 		aq_ret = i40e_set_vsi_promisc(vf, vsi->seid, allmulti, alluni,
 					      vl, num_vlans);
@@ -2037,7 +2037,7 @@ static int i40e_vc_get_version_msg(struct i40e_vf *vf, u8 *msg)
 	if (VF_IS_V10(&vf->vf_ver))
 		info.minor = VIRTCHNL_VERSION_MINOR_NO_VF_CAPS;
 	return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_VERSION,
-				      I40E_SUCCESS, (u8 *)&info,
+				      0, (u8 *)&info,
 				      sizeof(struct virtchnl_version_info));
 }
 
@@ -2099,14 +2099,14 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	int ret;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_INIT)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
 	len = struct_size(vfres, vsi_res, num_vsis);
 	vfres = kzalloc(len, GFP_KERNEL);
 	if (!vfres) {
-		aq_ret = I40E_ERR_NO_MEMORY;
+		aq_ret = -ENOMEM;
 		len = 0;
 		goto err;
 	}
@@ -2159,7 +2159,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 			dev_err(&pf->pdev->dev,
 				"VF %d requested polling mode: this feature is supported only when the device is running in single function per port (SFP) mode\n",
 				 vf->vf_id);
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 			goto err;
 		}
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING;
@@ -2227,7 +2227,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg)
 	int aq_ret = 0;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err_out;
 	}
 	if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) {
@@ -2243,12 +2243,12 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg)
 	}
 
 	if (info->flags > I40E_MAX_VF_PROMISC_FLAGS) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err_out;
 	}
 
 	if (!i40e_vc_isvalid_vsi_id(vf, info->vsi_id)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err_out;
 	}
 
@@ -2315,17 +2315,17 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 	int aq_ret = 0;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	if (!i40e_vc_isvalid_vsi_id(vf, qci->vsi_id)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	if (qci->num_queue_pairs > I40E_MAX_VF_QUEUES) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
@@ -2333,7 +2333,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 		for (i = 0; i < vf->num_tc; i++)
 			num_qps_all += vf->ch[i].num_qps;
 		if (num_qps_all != qci->num_queue_pairs) {
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 			goto error_param;
 		}
 	}
@@ -2346,7 +2346,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 		if (!vf->adq_enabled) {
 			if (!i40e_vc_isvalid_queue_id(vf, vsi_id,
 						      qpi->txq.queue_id)) {
-				aq_ret = I40E_ERR_PARAM;
+				aq_ret = -EINVAL;
 				goto error_param;
 			}
 
@@ -2355,14 +2355,14 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 			if (qpi->txq.vsi_id != qci->vsi_id ||
 			    qpi->rxq.vsi_id != qci->vsi_id ||
 			    qpi->rxq.queue_id != vsi_queue_id) {
-				aq_ret = I40E_ERR_PARAM;
+				aq_ret = -EINVAL;
 				goto error_param;
 			}
 		}
 
 		if (vf->adq_enabled) {
 			if (idx >= ARRAY_SIZE(vf->ch)) {
-				aq_ret = I40E_ERR_NO_AVAILABLE_VSI;
+				aq_ret = -ENODEV;
 				goto error_param;
 			}
 			vsi_id = vf->ch[idx].vsi_id;
@@ -2372,7 +2372,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 					     &qpi->rxq) ||
 		    i40e_config_vsi_tx_queue(vf, vsi_id, vsi_queue_id,
 					     &qpi->txq)) {
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 			goto error_param;
 		}
 
@@ -2383,7 +2383,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 		 */
 		if (vf->adq_enabled) {
 			if (idx >= ARRAY_SIZE(vf->ch)) {
-				aq_ret = I40E_ERR_NO_AVAILABLE_VSI;
+				aq_ret = -ENODEV;
 				goto error_param;
 			}
 			if (j == (vf->ch[idx].num_qps - 1)) {
@@ -2406,7 +2406,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 			vsi->num_queue_pairs = vf->ch[i].num_qps;
 
 			if (i40e_update_adq_vsi_queues(vsi, i)) {
-				aq_ret = I40E_ERR_CONFIG;
+				aq_ret = -EIO;
 				goto error_param;
 			}
 		}
@@ -2464,13 +2464,13 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg)
 	int i;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	if (irqmap_info->num_vectors >
 	    vf->pf->hw.func_caps.num_msix_vectors_vf) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
@@ -2479,18 +2479,18 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg)
 		/* validate msg params */
 		if (!i40e_vc_isvalid_vector_id(vf, map->vector_id) ||
 		    !i40e_vc_isvalid_vsi_id(vf, map->vsi_id)) {
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 			goto error_param;
 		}
 		vsi_id = map->vsi_id;
 
 		if (i40e_validate_queue_map(vf, vsi_id, map->rxq_map)) {
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 			goto error_param;
 		}
 
 		if (i40e_validate_queue_map(vf, vsi_id, map->txq_map)) {
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 			goto error_param;
 		}
 
@@ -2579,29 +2579,29 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
 	int i;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	if (!i40e_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	if (!i40e_vc_validate_vqs_bitmaps(vqs)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	/* Use the queue bit map sent by the VF */
 	if (i40e_ctrl_vf_rx_rings(pf->vsi[vf->lan_vsi_idx], vqs->rx_queues,
 				  true)) {
-		aq_ret = I40E_ERR_TIMEOUT;
+		aq_ret = -EIO;
 		goto error_param;
 	}
 	if (i40e_ctrl_vf_tx_rings(pf->vsi[vf->lan_vsi_idx], vqs->tx_queues,
 				  true)) {
-		aq_ret = I40E_ERR_TIMEOUT;
+		aq_ret = -EIO;
 		goto error_param;
 	}
 
@@ -2610,7 +2610,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
 		/* zero belongs to LAN VSI */
 		for (i = 1; i < vf->num_tc; i++) {
 			if (i40e_vsi_start_rings(pf->vsi[vf->ch[i].vsi_idx]))
-				aq_ret = I40E_ERR_TIMEOUT;
+				aq_ret = -EIO;
 		}
 	}
 
@@ -2636,29 +2636,29 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg)
 	int aq_ret = 0;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	if (!i40e_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	if (!i40e_vc_validate_vqs_bitmaps(vqs)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	/* Use the queue bit map sent by the VF */
 	if (i40e_ctrl_vf_tx_rings(pf->vsi[vf->lan_vsi_idx], vqs->tx_queues,
 				  false)) {
-		aq_ret = I40E_ERR_TIMEOUT;
+		aq_ret = -EIO;
 		goto error_param;
 	}
 	if (i40e_ctrl_vf_rx_rings(pf->vsi[vf->lan_vsi_idx], vqs->rx_queues,
 				  false)) {
-		aq_ret = I40E_ERR_TIMEOUT;
+		aq_ret = -EIO;
 		goto error_param;
 	}
 error_param:
@@ -2790,18 +2790,18 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg)
 	memset(&stats, 0, sizeof(struct i40e_eth_stats));
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	if (!i40e_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vsi) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 	i40e_update_eth_stats(vsi);
@@ -2862,7 +2862,7 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
 		    is_zero_ether_addr(addr)) {
 			dev_err(&pf->pdev->dev, "invalid VF MAC addr %pM\n",
 				addr);
-			return I40E_ERR_INVALID_MAC_ADDR;
+			return -EINVAL;
 		}
 
 		/* If the host VMM administrator has set the VF MAC address
@@ -2998,7 +2998,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
 	    !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) {
-		ret = I40E_ERR_PARAM;
+		ret = -EINVAL;
 		goto error_param;
 	}
 
@@ -3027,7 +3027,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 				dev_err(&pf->pdev->dev,
 					"Unable to add MAC filter %pM for VF %d\n",
 					al->list[i].addr, vf->vf_id);
-				ret = I40E_ERR_PARAM;
+				ret = -EINVAL;
 				spin_unlock_bh(&vsi->mac_filter_hash_lock);
 				goto error_param;
 			}
@@ -3067,7 +3067,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
 	    !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) {
-		ret = I40E_ERR_PARAM;
+		ret = -EINVAL;
 		goto error_param;
 	}
 
@@ -3076,7 +3076,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 		    is_zero_ether_addr(al->list[i].addr)) {
 			dev_err(&pf->pdev->dev, "Invalid MAC addr %pM for VF %d\n",
 				al->list[i].addr, vf->vf_id);
-			ret = I40E_ERR_INVALID_MAC_ADDR;
+			ret = -EINVAL;
 			goto error_param;
 		}
 		if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr))
@@ -3088,7 +3088,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 	/* delete addresses from the list */
 	for (i = 0; i < al->num_elements; i++)
 		if (i40e_del_mac_filter(vsi, al->list[i].addr)) {
-			ret = I40E_ERR_INVALID_MAC_ADDR;
+			ret = -EINVAL;
 			spin_unlock_bh(&vsi->mac_filter_hash_lock);
 			goto error_param;
 		}
@@ -3149,13 +3149,13 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg)
 	}
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	for (i = 0; i < vfl->num_elements; i++) {
 		if (vfl->vlan_id[i] > I40E_MAX_VLANID) {
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 			dev_err(&pf->pdev->dev,
 				"invalid VF VLAN id %d\n", vfl->vlan_id[i]);
 			goto error_param;
@@ -3163,7 +3163,7 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg)
 	}
 	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (vsi->info.pvid) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
@@ -3214,13 +3214,13 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg)
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	for (i = 0; i < vfl->num_elements; i++) {
 		if (vfl->vlan_id[i] > I40E_MAX_VLANID) {
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 			goto error_param;
 		}
 	}
@@ -3228,7 +3228,7 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg)
 	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (vsi->info.pvid) {
 		if (vfl->num_elements > 1 || vfl->vlan_id[0])
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 		goto error_param;
 	}
 
@@ -3269,7 +3269,7 @@ static int i40e_vc_rdma_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !test_bit(I40E_VF_STATE_RDMAENA, &vf->vf_states)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
@@ -3298,13 +3298,13 @@ static int i40e_vc_rdma_qvmap_msg(struct i40e_vf *vf, u8 *msg, bool config)
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !test_bit(I40E_VF_STATE_RDMAENA, &vf->vf_states)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto error_param;
 	}
 
 	if (config) {
 		if (i40e_config_rdma_qvlist(vf, qvlist_info))
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 	} else {
 		i40e_release_rdma_qvlist(vf);
 	}
@@ -3335,7 +3335,7 @@ static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg)
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vrk->vsi_id) ||
 	    vrk->key_len != I40E_HKEY_ARRAY_SIZE) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -3366,13 +3366,13 @@ static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg)
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vrl->vsi_id) ||
 	    vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
 	for (i = 0; i < vrl->lut_entries; i++)
 		if (vrl->lut[i] >= vf->num_queue_pairs) {
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 			goto err;
 		}
 
@@ -3399,14 +3399,14 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg)
 	int len = 0;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 	len = sizeof(struct virtchnl_rss_hena);
 
 	vrh = kzalloc(len, GFP_KERNEL);
 	if (!vrh) {
-		aq_ret = I40E_ERR_NO_MEMORY;
+		aq_ret = -ENOMEM;
 		len = 0;
 		goto err;
 	}
@@ -3435,7 +3435,7 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg)
 	int aq_ret = 0;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 	i40e_write_rx_ctl(hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)vrh->hena);
@@ -3460,7 +3460,7 @@ static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg)
 	int aq_ret = 0;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -3486,7 +3486,7 @@ static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg)
 	int aq_ret = 0;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -3574,7 +3574,7 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf,
 			dev_err(&pf->pdev->dev,
 				"VF %d not trusted, make VF trusted to add advanced mode ADq cloud filters\n",
 				vf->vf_id);
-			return I40E_ERR_CONFIG;
+			return -EIO;
 		}
 	}
 
@@ -3627,9 +3627,9 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf,
 		}
 	}
 
-	return I40E_SUCCESS;
+	return 0;
 err:
-	return I40E_ERR_CONFIG;
+	return -EIO;
 }
 
 /**
@@ -3713,7 +3713,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	int i, ret;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -3721,7 +3721,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		dev_info(&pf->pdev->dev,
 			 "VF %d: ADq not enabled, can't apply cloud filter\n",
 			 vf->vf_id);
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -3729,7 +3729,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		dev_info(&pf->pdev->dev,
 			 "VF %d: Invalid input, can't apply cloud filter\n",
 			 vf->vf_id);
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -3844,7 +3844,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	int i, ret;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err_out;
 	}
 
@@ -3852,7 +3852,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		dev_info(&pf->pdev->dev,
 			 "VF %d: ADq is not enabled, can't apply cloud filter\n",
 			 vf->vf_id);
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err_out;
 	}
 
@@ -3860,7 +3860,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		dev_info(&pf->pdev->dev,
 			 "VF %d: Invalid input/s, can't apply cloud filter\n",
 			 vf->vf_id);
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err_out;
 	}
 
@@ -3953,7 +3953,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 	u64 speed = 0;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -3961,7 +3961,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 	if (vf->spoofchk) {
 		dev_err(&pf->pdev->dev,
 			"Spoof check is ON, turn it OFF to enable ADq\n");
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -3969,7 +3969,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 		dev_err(&pf->pdev->dev,
 			"VF %d attempting to enable ADq, but hasn't properly negotiated that capability\n",
 			vf->vf_id);
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -3978,7 +3978,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 		dev_err(&pf->pdev->dev,
 			"VF %d trying to set %u TCs, valid range 1-%u TCs per VF\n",
 			vf->vf_id, tci->num_tc, I40E_MAX_VF_VSI);
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -3990,7 +3990,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 				"VF %d: TC %d trying to set %u queues, valid range 1-%u queues per TC\n",
 				vf->vf_id, i, tci->list[i].count,
 				I40E_DEFAULT_QUEUES_PER_VF);
-			aq_ret = I40E_ERR_PARAM;
+			aq_ret = -EINVAL;
 			goto err;
 		}
 
@@ -4001,7 +4001,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 		dev_err(&pf->pdev->dev,
 			"No queues left to allocate to VF %d\n",
 			vf->vf_id);
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	} else {
 		/* we need to allocate max VF queues to enable ADq so as to
@@ -4016,7 +4016,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 	if (speed == SPEED_UNKNOWN) {
 		dev_err(&pf->pdev->dev,
 			"Cannot detect link speed\n");
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -4029,7 +4029,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 					"Invalid max tx rate %llu specified for VF %d.",
 					tci->list[i].max_tx_rate,
 					vf->vf_id);
-				aq_ret = I40E_ERR_PARAM;
+				aq_ret = -EINVAL;
 				goto err;
 			} else {
 				vf->ch[i].max_tx_rate =
@@ -4045,7 +4045,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 	/* reset the VF in order to allocate resources */
 	i40e_vc_reset_vf(vf, true);
 
-	return I40E_SUCCESS;
+	return 0;
 
 	/* send the response to the VF */
 err:
@@ -4064,7 +4064,7 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg)
 	int aq_ret = 0;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 		goto err;
 	}
 
@@ -4079,13 +4079,13 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg)
 	} else {
 		dev_info(&pf->pdev->dev, "VF %d trying to delete queue channels but ADq isn't enabled\n",
 			 vf->vf_id);
-		aq_ret = I40E_ERR_PARAM;
+		aq_ret = -EINVAL;
 	}
 
 	/* reset the VF in order to allocate resources */
 	i40e_vc_reset_vf(vf, true);
 
-	return I40E_SUCCESS;
+	return 0;
 
 err:
 	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DISABLE_CHANNELS,
@@ -4119,21 +4119,16 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 
 	/* Check if VF is disabled. */
 	if (test_bit(I40E_VF_STATE_DISABLED, &vf->vf_states))
-		return I40E_ERR_PARAM;
+		return -EINVAL;
 
 	/* perform basic checks on the msg */
 	ret = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen);
 
 	if (ret) {
-		i40e_vc_send_resp_to_vf(vf, v_opcode, I40E_ERR_PARAM);
+		i40e_vc_send_resp_to_vf(vf, v_opcode, -EINVAL);
 		dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d\n",
 			local_vf_id, v_opcode, msglen);
-		switch (ret) {
-		case VIRTCHNL_STATUS_ERR_PARAM:
-			return -EPERM;
-		default:
-			return -EINVAL;
-		}
+		return ret;
 	}
 
 	switch (v_opcode) {
@@ -4226,7 +4221,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 		dev_err(&pf->pdev->dev, "Unsupported opcode %d from VF %d\n",
 			v_opcode, local_vf_id);
 		ret = i40e_vc_send_resp_to_vf(vf, v_opcode,
-					      I40E_ERR_NOT_IMPLEMENTED);
+					      -EOPNOTSUPP);
 		break;
 	}
 
-- 
GitLab


From 165f6890586edbf5257560ff955b2076f0b4b854 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Fri, 28 Jul 2023 11:29:26 -0600
Subject: [PATCH 0668/1806] selftests: connector: Fix Makefile to include
 KHDR_INCLUDES
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The test compile fails with following errors. Fix the Makefile
CFLAGS to include KHDR_INCLUDES to pull in uapi defines.

gcc -Wall     proc_filter.c  -o ../tools/testing/selftests/connector/proc_filter
proc_filter.c: In function ‘send_message’:
proc_filter.c:22:33: error: invalid application of ‘sizeof’ to incomplete type ‘struct proc_input’
   22 |                          sizeof(struct proc_input))
      |                                 ^~~~~~
proc_filter.c:42:19: note: in expansion of macro ‘NL_MESSAGE_SIZE’
   42 |         char buff[NL_MESSAGE_SIZE];
      |                   ^~~~~~~~~~~~~~~
proc_filter.c:22:33: error: invalid application of ‘sizeof’ to incomplete type ‘struct proc_input’
   22 |                          sizeof(struct proc_input))
      |                                 ^~~~~~
proc_filter.c:48:34: note: in expansion of macro ‘NL_MESSAGE_SIZE’
   48 |                 hdr->nlmsg_len = NL_MESSAGE_SIZE;
      |                                  ^~~~~~~~~~~~~~~
`

Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Link: https://lore.kernel.org/all/CA+G9fYt=6ysz636XcQ=-KJp7vJcMZ=NjbQBrn77v7vnTcfP2cA@mail.gmail.com/
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/d0055c8cdf18516db8ba9edec99cfc5c08f32a7c.1690564372.git.skhan@linuxfoundation.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/connector/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/connector/Makefile b/tools/testing/selftests/connector/Makefile
index 21c9f3a973a0e..92188b9bac5c3 100644
--- a/tools/testing/selftests/connector/Makefile
+++ b/tools/testing/selftests/connector/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-CFLAGS += -Wall
+CFLAGS += -Wall $(KHDR_INCLUDES)
 
 TEST_GEN_PROGS = proc_filter
 
-- 
GitLab


From f4dcfa6fa1a80869ab4bb0eec2e45bb526134fb1 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Fri, 28 Jul 2023 11:29:27 -0600
Subject: [PATCH 0669/1806] selftests: connector: Add .gitignore and poupulate
 it with test

Add gitignore and poupulate it with test name - proc_filter

Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/e3d04cc34e9af07909dc882b50fb1b6f1ce7705b.1690564372.git.skhan@linuxfoundation.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/connector/.gitignore | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 tools/testing/selftests/connector/.gitignore

diff --git a/tools/testing/selftests/connector/.gitignore b/tools/testing/selftests/connector/.gitignore
new file mode 100644
index 0000000000000..c90098199a44a
--- /dev/null
+++ b/tools/testing/selftests/connector/.gitignore
@@ -0,0 +1 @@
+proc_filter
-- 
GitLab


From 4cbc32a8a2b44fc7e91ae3006e5da3eaf630e383 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 29 Jul 2023 20:19:29 +0800
Subject: [PATCH 0670/1806] net/smc: Remove unused function declarations

commit f9aab6f2ce57 ("net/smc: immediate freeing in smc_lgr_cleanup_early()")
left behind smc_lgr_schedule_free_work_fast() declaration.
And since commit 349d43127dac ("net/smc: fix kernel panic caused by race of smc_sock")
smc_ib_modify_qp_reset() is not used anymore.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Link: https://lore.kernel.org/r/20230729121929.17180-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/smc/smc_core.h | 1 -
 net/smc/smc_ib.h   | 1 -
 2 files changed, 2 deletions(-)

diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 1645fba0d2d38..3c1b31bfa1cf3 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -539,7 +539,6 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini);
 
 void smc_conn_free(struct smc_connection *conn);
 int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini);
-void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr);
 int smc_core_init(void);
 void smc_core_exit(void);
 
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 034295676e881..4df5f8c8a0a1c 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -96,7 +96,6 @@ void smc_ib_destroy_queue_pair(struct smc_link *lnk);
 int smc_ib_create_queue_pair(struct smc_link *lnk);
 int smc_ib_ready_link(struct smc_link *lnk);
 int smc_ib_modify_qp_rts(struct smc_link *lnk);
-int smc_ib_modify_qp_reset(struct smc_link *lnk);
 int smc_ib_modify_qp_error(struct smc_link *lnk);
 long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev);
 int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
-- 
GitLab


From 634e44971981b1c197fa3152d7a6930c8150060e Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 29 Jul 2023 20:20:36 +0800
Subject: [PATCH 0671/1806] vsock: Remove unused function declarations

These are never implemented since introduction in
commit d021c344051a ("VSOCK: Introduce VM Sockets")

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://lore.kernel.org/r/20230729122036.32988-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/vmci_transport.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/vmw_vsock/vmci_transport.h b/net/vmw_vsock/vmci_transport.h
index b7b0721942821..dbda3ababa14a 100644
--- a/net/vmw_vsock/vmci_transport.h
+++ b/net/vmw_vsock/vmci_transport.h
@@ -116,9 +116,6 @@ struct vmci_transport {
 	spinlock_t lock; /* protects sk. */
 };
 
-int vmci_transport_register(void);
-void vmci_transport_unregister(void);
-
 int vmci_transport_send_wrote_bh(struct sockaddr_vm *dst,
 				 struct sockaddr_vm *src);
 int vmci_transport_send_read_bh(struct sockaddr_vm *dst,
-- 
GitLab


From df41fa677d9b4717c930afbe88b06f5cefdacb21 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <florian.fainelli@broadcom.com>
Date: Fri, 28 Jul 2023 11:39:45 -0700
Subject: [PATCH 0672/1806] net: bcmgenet: Remove TX ring full logging

There is no need to spam the kernel log with such an indication, remove
this message.

Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230728183945.760531-1-florian.fainelli@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 2b5761ad2f92f..24bade875ca6a 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2077,12 +2077,8 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	spin_lock(&ring->lock);
 	if (ring->free_bds <= (nr_frags + 1)) {
-		if (!netif_tx_queue_stopped(txq)) {
+		if (!netif_tx_queue_stopped(txq))
 			netif_tx_stop_queue(txq);
-			netdev_err(dev,
-				   "%s: tx ring %d full when queue %d awake\n",
-				   __func__, index, ring->queue);
-		}
 		ret = NETDEV_TX_BUSY;
 		goto out;
 	}
-- 
GitLab


From 079082c60affefeb9d2bd4176a4f2b390a9ccfda Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Fri, 28 Jul 2023 23:47:17 +0200
Subject: [PATCH 0673/1806] tcx: Fix splat during dev unregister

During unregister_netdevice_many_notify(), the ordering of our concerned
function calls is like this:

  unregister_netdevice_many_notify
    dev_shutdown
	qdisc_put
            clsact_destroy
    tcx_uninstall

The syzbot reproducer triggered a case that the qdisc refcnt is not
zero during dev_shutdown().

tcx_uninstall() will then WARN_ON_ONCE(tcx_entry(entry)->miniq_active)
because the miniq is still active and the entry should not be freed.
The latter assumed that qdisc destruction happens before tcx teardown.

This fix is to avoid tcx_uninstall() doing tcx_entry_free() when the
miniq is still alive and let the clsact_destroy() do the free later, so
that we do not assume any specific ordering for either of them.

If still active, tcx_uninstall() does clear the entry when flushing out
the prog/link. clsact_destroy() will then notice the "!tcx_entry_is_active()"
and then does the tcx_entry_free() eventually.

Fixes: e420bed02507 ("bpf: Add fd-based tcx multi-prog infra with link support")
Reported-by: syzbot+376a289e86a0fd02b9ba@syzkaller.appspotmail.com
Reported-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: syzbot+376a289e86a0fd02b9ba@syzkaller.appspotmail.com
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/222255fe07cb58f15ee662e7ee78328af5b438e4.1690549248.git.daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/bpf_mprog.h | 16 ++++++++++++++++
 kernel/bpf/tcx.c          | 12 ++++++++----
 2 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/include/linux/bpf_mprog.h b/include/linux/bpf_mprog.h
index 2b429488f8402..929225f7b0959 100644
--- a/include/linux/bpf_mprog.h
+++ b/include/linux/bpf_mprog.h
@@ -256,6 +256,22 @@ static inline void bpf_mprog_entry_copy(struct bpf_mprog_entry *dst,
 	memcpy(dst->fp_items, src->fp_items, sizeof(src->fp_items));
 }
 
+static inline void bpf_mprog_entry_clear(struct bpf_mprog_entry *dst)
+{
+	memset(dst->fp_items, 0, sizeof(dst->fp_items));
+}
+
+static inline void bpf_mprog_clear_all(struct bpf_mprog_entry *entry,
+				       struct bpf_mprog_entry **entry_new)
+{
+	struct bpf_mprog_entry *peer;
+
+	peer = bpf_mprog_peer(entry);
+	bpf_mprog_entry_clear(peer);
+	peer->parent->count = 0;
+	*entry_new = peer;
+}
+
 static inline void bpf_mprog_entry_grow(struct bpf_mprog_entry *entry, int idx)
 {
 	int total = bpf_mprog_total(entry);
diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c
index 69a272712b29f..13f0b5dc8262a 100644
--- a/kernel/bpf/tcx.c
+++ b/kernel/bpf/tcx.c
@@ -94,15 +94,19 @@ out:
 
 void tcx_uninstall(struct net_device *dev, bool ingress)
 {
+	struct bpf_mprog_entry *entry, *entry_new = NULL;
 	struct bpf_tuple tuple = {};
-	struct bpf_mprog_entry *entry;
 	struct bpf_mprog_fp *fp;
 	struct bpf_mprog_cp *cp;
+	bool active;
 
 	entry = tcx_entry_fetch(dev, ingress);
 	if (!entry)
 		return;
-	tcx_entry_update(dev, NULL, ingress);
+	active = tcx_entry(entry)->miniq_active;
+	if (active)
+		bpf_mprog_clear_all(entry, &entry_new);
+	tcx_entry_update(dev, entry_new, ingress);
 	tcx_entry_sync();
 	bpf_mprog_foreach_tuple(entry, fp, cp, tuple) {
 		if (tuple.link)
@@ -111,8 +115,8 @@ void tcx_uninstall(struct net_device *dev, bool ingress)
 			bpf_prog_put(tuple.prog);
 		tcx_skeys_dec(ingress);
 	}
-	WARN_ON_ONCE(tcx_entry(entry)->miniq_active);
-	tcx_entry_free(entry);
+	if (!active)
+		tcx_entry_free(entry);
 }
 
 int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
-- 
GitLab


From e99688eba2e90a600956e936bc335ece902a5d7f Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Mon, 31 Jul 2023 13:45:34 -0700
Subject: [PATCH 0674/1806] bpf: Fix an array-index-out-of-bounds issue in
 disasm.c

syzbot reported an array-index-out-of-bounds when printing out bpf
insns. Further investigation shows the insn is illegal but
is printed out due to log level 1 or 2 before actual insn verification
in do_check().

This particular illegal insn is a MOVSX insn with offset value 2.
The legal offset value for MOVSX should be 8, 16 and 32.
The disasm sign-extension-size array index is calculated as
 (insn->off / 8) - 1
and offset value 2 gives an out-of-bound index -1.

Tighten the checking for MOVSX insn in disasm.c to avoid
array-index-out-of-bounds issue.

Reported-by: syzbot+3758842a6c01012aa73b@syzkaller.appspotmail.com
Fixes: f835bb622299 ("bpf: Add kernel/bpftool asm support for new instructions")
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20230731204534.1975311-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/disasm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index d7bff608f2993..ef7c107c7b8f2 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -162,7 +162,8 @@ static bool is_sdiv_smod(const struct bpf_insn *insn)
 
 static bool is_movsx(const struct bpf_insn *insn)
 {
-	return BPF_OP(insn->code) == BPF_MOV && insn->off != 0;
+	return BPF_OP(insn->code) == BPF_MOV &&
+	       (insn->off == 8 || insn->off == 16 || insn->off == 32);
 }
 
 void print_bpf_insn(const struct bpf_insn_cbs *cbs,
-- 
GitLab


From 81584c23f249ac2d809e2f89b76a7a9a02c09d8a Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Mon, 31 Jul 2023 15:55:00 -0600
Subject: [PATCH 0675/1806] netfilter: bpf: Only define get_proto_defrag_hook()
 if necessary

Before, we were getting this warning:

  net/netfilter/nf_bpf_link.c:32:1: warning: 'get_proto_defrag_hook' defined but not used [-Wunused-function]

Guard the definition with CONFIG_NF_DEFRAG_IPV[4|6].

Fixes: 91721c2d02d3 ("netfilter: bpf: Support BPF_F_NETFILTER_IP_DEFRAG in netfilter link")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202307291213.fZ0zDmoG-lkp@intel.com/
Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/b128b6489f0066db32c4772ae4aaee1480495929.1690840454.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/netfilter/nf_bpf_link.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index 8fe594bbc7e24..e502ec00b2fe1 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -28,6 +28,7 @@ struct bpf_nf_link {
 	const struct nf_defrag_hook *defrag_hook;
 };
 
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 static const struct nf_defrag_hook *
 get_proto_defrag_hook(struct bpf_nf_link *link,
 		      const struct nf_defrag_hook __rcu *global_hook,
@@ -68,6 +69,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link,
 
 	return hook;
 }
+#endif
 
 static int bpf_nf_enable_defrag(struct bpf_nf_link *link)
 {
-- 
GitLab


From 2d20bfc315eb62172f78423044eaac1fe75617d4 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Fri, 28 Jul 2023 09:49:41 +0800
Subject: [PATCH 0676/1806] bpf, cpumap: Remove unused cmap field from
 bpf_cpu_map_entry

Since commit cdfafe98cabe ("xdp: Make cpumap flush_list common for all
map instances"), cmap is no longer used, so just remove it.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230728014942.892272-2-houtao@huaweicloud.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/cpumap.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 6ae02be7a48e3..0a16e30b16ef1 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -60,8 +60,6 @@ struct bpf_cpu_map_entry {
 	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
 	struct xdp_bulk_queue __percpu *bulkq;
 
-	struct bpf_cpu_map *cmap;
-
 	/* Queue with potential multi-producers, and single-consumer kthread */
 	struct ptr_ring *queue;
 	struct task_struct *kthread;
@@ -588,7 +586,6 @@ static long cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 		rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu);
 		if (!rcpu)
 			return -ENOMEM;
-		rcpu->cmap = cmap;
 	}
 	rcu_read_lock();
 	__cpu_map_entry_replace(cmap, key_cpu, rcpu);
-- 
GitLab


From 1ea66e89f68cd463ae189fb5d491df52e330136a Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Fri, 28 Jul 2023 09:49:42 +0800
Subject: [PATCH 0677/1806] bpf, devmap: Remove unused dtab field from
 bpf_dtab_netdev

Commit 96360004b862 ("xdp: Make devmap flush_list common for all map
instances") removes the use of bpf_dtab_netdev::dtab in bq_enqueue(),
so just remove dtab from bpf_dtab_netdev.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20230728014942.892272-3-houtao@huaweicloud.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/devmap.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 49cc0b5671c61..4d42f6ed6c11a 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -65,7 +65,6 @@ struct xdp_dev_bulk_queue {
 struct bpf_dtab_netdev {
 	struct net_device *dev; /* must be first member, due to tracepoint */
 	struct hlist_node index_hlist;
-	struct bpf_dtab *dtab;
 	struct bpf_prog *xdp_prog;
 	struct rcu_head rcu;
 	unsigned int idx;
@@ -874,7 +873,6 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 	}
 
 	dev->idx = idx;
-	dev->dtab = dtab;
 	if (prog) {
 		dev->xdp_prog = prog;
 		dev->val.bpf_prog.id = prog->aux->id;
-- 
GitLab


From 04786c0659dbacf1f626f70c2b19c1bc334f1098 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Fri, 28 Jul 2023 18:24:03 -0600
Subject: [PATCH 0678/1806] selftests: connector: Fix input argument error
 paths to skip

Fix input argument parsing paths to skip from their error legs.
This fix helps to avoid false test failure reports without running
the test.

Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Reviewed-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Link: https://lore.kernel.org/r/20230729002403.4278-1-skhan@linuxfoundation.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/connector/proc_filter.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/connector/proc_filter.c b/tools/testing/selftests/connector/proc_filter.c
index 4fe8c6763fd8e..4a825b997666e 100644
--- a/tools/testing/selftests/connector/proc_filter.c
+++ b/tools/testing/selftests/connector/proc_filter.c
@@ -248,7 +248,7 @@ int main(int argc, char *argv[])
 
 	if (argc > 2) {
 		printf("Expected 0(assume no-filter) or 1 argument(-f)\n");
-		exit(1);
+		exit(KSFT_SKIP);
 	}
 
 	if (argc == 2) {
@@ -256,7 +256,7 @@ int main(int argc, char *argv[])
 			filter = 1;
 		} else {
 			printf("Valid option : -f (for filter feature)\n");
-			exit(1);
+			exit(KSFT_SKIP);
 		}
 	}
 
-- 
GitLab


From 2f48401dd0f2d93a41d28bb8dc3474158f4e906c Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 29 Jul 2023 20:34:56 +0800
Subject: [PATCH 0679/1806] net/hsr: Remove unused function declarations

commit f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
introducted these but never implemented.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230729123456.36340-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/hsr/hsr_netlink.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/hsr/hsr_netlink.h b/net/hsr/hsr_netlink.h
index 501552d9753b9..8c99e64e1ceab 100644
--- a/net/hsr/hsr_netlink.h
+++ b/net/hsr/hsr_netlink.h
@@ -23,7 +23,5 @@ void __exit hsr_netlink_exit(void);
 void hsr_nl_ringerror(struct hsr_priv *hsr, unsigned char addr[ETH_ALEN],
 		      struct hsr_port *port);
 void hsr_nl_nodedown(struct hsr_priv *hsr, unsigned char addr[ETH_ALEN]);
-void hsr_nl_framedrop(int dropcount, int dev_idx);
-void hsr_nl_linkdown(int dev_idx);
 
 #endif /* __HSR_NETLINK_H */
-- 
GitLab


From 03668c65d153579c1725ef439b6676ef3742522e Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Sun, 30 Jul 2023 10:05:15 +0200
Subject: [PATCH 0680/1806] selftests: mptcp: join: rework detailed report

This patch modifies how the detailed results are printed, mainly to
improve what is displayed in case of issue:

- Now the test name (title) is printed earlier, when starting the test
  if it is not intentionally skipped: by doing that, errors linked to
  a test will be printed after having written the test name and then
  avoid confusions.

- Due to the previous item, it is required to add a new line after
  having printed the test name because in case of error with a command,
  it is better not to have the output in the middle of the screen.

- Each check is printed on a dedicated line with aligned status (ok,
  skip, fail): it is easier to spot which one has failed, simpler to
  manage in the code not having to deal with alignment case by case and
  helpers can be used to uniform what is done. These helpers can also be
  useful later to do more actions depending on the results or change in
  one place what is printed.

- Info messages have been reduced and aligned as well. And info messages
  about the creation of the default test files of 1 KB are no longer
  printed.

Example:

  001 no JOIN
        syn                                 [ ok ]
        synack                              [ ok ]
        ack                                 [ ok ]

Or with a skip and a failure:

  001 no JOIN
        syn                                 [ ok ]
        synack                              [fail] got 42 JOIN[s] synack expected 0
  Server ns stats
  (...)
  Client ns stats
  (...)
        ack                                 [skip]

Or with info:

  104 Infinite map
        Test file (size 128 KB) for client
        Test file (size 128 KB) for server
        file received by server has inverted byte at 169
        5 corrupted pkts
        syn                                 [ ok ]
        synack                              [ ok ]

While at it, verify_listener_events() now also print more info in case
of failure and in pm_nl_check_endpoint(), the test is marked as failed
instead of skipped if no ID has been given (internal selftest issue).

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Link: https://lore.kernel.org/r/20230730-upstream-net-next-20230728-mptcp-selftests-misc-v1-1-7e9cc530a9cd@tessares.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 450 +++++++++---------
 1 file changed, 214 insertions(+), 236 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 1640749750d4d..6da3a6c98ba7a 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -49,7 +49,7 @@ declare -a only_tests_names
 declare -A failed_tests
 TEST_COUNT=0
 TEST_NAME=""
-nr_blank=40
+nr_blank=6
 
 # These var are used only in some tests, make sure they are not already set
 unset FAILING_LINKS
@@ -187,8 +187,8 @@ init() {
 
 	trap cleanup EXIT
 
-	make_file "$cin" "client" 1
-	make_file "$sin" "server" 1
+	make_file "$cin" "client" 1 >/dev/null
+	make_file "$sin" "server" 1 >/dev/null
 }
 
 cleanup()
@@ -200,10 +200,37 @@ cleanup()
 	cleanup_partial
 }
 
-# $1: msg
 print_title()
 {
-	printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${1}"
+	printf "%03u %s\n" "${TEST_COUNT}" "${TEST_NAME}"
+}
+
+print_check()
+{
+	printf "%-${nr_blank}s%-36s" " " "${*}"
+}
+
+print_info()
+{
+	# It can be empty, no need to print anything then
+	[ -z "${1}" ] && return
+
+	printf "%-${nr_blank}sInfo: %s\n" " " "${*}"
+}
+
+print_ok()
+{
+	echo "[ ok ]${1:+ ${*}}"
+}
+
+print_fail()
+{
+	echo "[fail]${1:+ ${*}}"
+}
+
+print_skip()
+{
+	echo "[skip]${1:+ ${*}}"
 }
 
 # [ $1: fail msg ]
@@ -213,8 +240,8 @@ mark_as_skipped()
 
 	mptcp_lib_fail_if_expected_feature "${msg}"
 
-	print_title "[ skip ] ${msg}"
-	printf "\n"
+	print_check "${msg}"
+	print_skip
 
 	last_test_skipped=1
 }
@@ -278,6 +305,8 @@ reset()
 		return 1
 	fi
 
+	print_title
+
 	if [ "${init}" != "1" ]; then
 		init
 	else
@@ -458,10 +487,13 @@ reset_with_tcp_filter()
 	fi
 }
 
+# $1: err msg
 fail_test()
 {
 	ret=1
 
+	print_fail "${@}"
+
 	# just in case a test is marked twice as failed
 	if [ ${last_test_failed} -eq 0 ]; then
 		failed_tests[${TEST_COUNT}]="${TEST_NAME}"
@@ -482,7 +514,7 @@ get_failed_tests_ids()
 print_file_err()
 {
 	ls -l "$1" 1>&2
-	echo "Trailing bytes are: "
+	echo -n "Trailing bytes are: "
 	tail -c 27 "$1"
 }
 
@@ -500,8 +532,7 @@ check_transfer()
 		# when truncating we must check the size explicitly
 		out_size=$(wc -c $out | awk '{print $1}')
 		if [ $out_size -ne $bytes ]; then
-			echo "[ FAIL ] $what output file has wrong size ($out_size, $bytes)"
-			fail_test
+			fail_test "$what output file has wrong size ($out_size, $bytes)"
 			return 1
 		fi
 
@@ -516,14 +547,13 @@ check_transfer()
 	cmp -l "$in" "$out" | while read -r i a b; do
 		local sum=$((0${a} + 0${b}))
 		if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then
-			echo "[ FAIL ] $what does not match (in, out):"
+			fail_test "$what does not match (in, out):"
 			print_file_err "$in"
 			print_file_err "$out"
-			fail_test
 
 			return 1
 		else
-			echo "$what has inverted byte at ${i}"
+			print_info "$what has inverted byte at ${i}"
 		fi
 	done
 
@@ -537,8 +567,7 @@ do_ping()
 	local connect_addr="$3"
 
 	if ! ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null; then
-		echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2
-		fail_test
+		fail_test "$listener_ns -> $connect_addr connectivity"
 	fi
 }
 
@@ -776,10 +805,9 @@ pm_nl_change_endpoint()
 pm_nl_check_endpoint()
 {
 	local line expected_line
-	local need_title=$1
-	local msg="$2"
-	local ns=$3
-	local addr=$4
+	local msg="$1"
+	local ns=$2
+	local addr=$3
 	local _flags=""
 	local flags
 	local _port
@@ -788,13 +816,9 @@ pm_nl_check_endpoint()
 	local _id
 	local id
 
-	if [ "${need_title}" = 1 ]; then
-		printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}"
-	else
-		printf "%-${nr_blank}s %s" " " "${msg}"
-	fi
+	print_check "${msg}"
 
-	shift 4
+	shift 3
 	while [ -n "$1" ]; do
 		if [ $1 = "flags" ]; then
 			_flags=$2
@@ -817,7 +841,7 @@ pm_nl_check_endpoint()
 	done
 
 	if [ -z "$id" ]; then
-		echo "[skip] bad test - missing endpoint id"
+		test_fail "bad test - missing endpoint id"
 		return
 	fi
 
@@ -840,10 +864,9 @@ pm_nl_check_endpoint()
 		[ -n "$_port" ] && expected_line="$expected_line $_port"
 	fi
 	if [ "$line" = "$expected_line" ]; then
-		echo "[ ok ]"
+		print_ok
 	else
-		echo "[fail] expected '$expected_line' found '$line'"
-		fail_test
+		fail_test "expected '$expected_line' found '$line'"
 	fi
 }
 
@@ -1058,8 +1081,7 @@ do_transfer()
 	local trunc_size=""
 	if [ -n "${fastclose}" ]; then
 		if [ ${test_linkfail} -le 1 ]; then
-			echo "fastclose tests need test_linkfail argument"
-			fail_test
+			fail_test "fastclose tests need test_linkfail argument"
 			return 1
 		fi
 
@@ -1074,8 +1096,7 @@ do_transfer()
 			extra_srv_args="-f ${test_linkfail}"
 			extra_cl_args="-f -1"
 		else
-			echo "wrong/unknown fastclose spec ${side}"
-			fail_test
+			fail_test "wrong/unknown fastclose spec ${side}"
 			return 1
 		fi
 	fi
@@ -1136,7 +1157,7 @@ do_transfer()
 		nstat | grep Tcp > /tmp/${connector_ns}.out
 
 	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
-		echo " client exit code $retc, server $rets" 1>&2
+		fail_test "client exit code $retc, server $rets"
 		echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2
 		ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port"
 		cat /tmp/${listener_ns}.out
@@ -1145,7 +1166,6 @@ do_transfer()
 		cat /tmp/${connector_ns}.out
 
 		cat "$capout"
-		fail_test
 		return 1
 	fi
 
@@ -1180,7 +1200,7 @@ make_file()
 	dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null
 	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
 
-	echo "Created $name (size $size KB) containing data sent by $who"
+	print_info "Test file (size $size KB) for $who"
 }
 
 run_tests()
@@ -1261,36 +1281,34 @@ chk_csum_nr()
 		csum_ns2=${csum_ns2:1}
 	fi
 
-	printf "%-${nr_blank}s %s" " " "sum"
+	print_check "sum"
 	count=$(get_counter ${ns1} "MPTcpExtDataCsumErr")
 	if [ "$count" != "$csum_ns1" ]; then
 		extra_msg="$extra_msg ns1=$count"
 	fi
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } ||
 	   { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then
-		echo "[fail] got $count data checksum error[s] expected $csum_ns1"
-		fail_test
+		fail_test "got $count data checksum error[s] expected $csum_ns1"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
-	echo -n " - csum  "
+	print_check "csum"
 	count=$(get_counter ${ns2} "MPTcpExtDataCsumErr")
 	if [ "$count" != "$csum_ns2" ]; then
 		extra_msg="$extra_msg ns2=$count"
 	fi
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } ||
 	   { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then
-		echo "[fail] got $count data checksum error[s] expected $csum_ns2"
-		fail_test
+		fail_test "got $count data checksum error[s] expected $csum_ns2"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo "$extra_msg"
+	print_info "$extra_msg"
 }
 
 chk_fail_nr()
@@ -1308,7 +1326,7 @@ chk_fail_nr()
 	if [[ $ns_invert = "invert" ]]; then
 		ns_tx=$ns2
 		ns_rx=$ns1
-		extra_msg=" invert"
+		extra_msg="invert"
 	fi
 
 	if [[ "${fail_tx}" = "-"* ]]; then
@@ -1320,37 +1338,35 @@ chk_fail_nr()
 		fail_rx=${fail_rx:1}
 	fi
 
-	printf "%-${nr_blank}s %s" " " "ftx"
+	print_check "ftx"
 	count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx")
 	if [ "$count" != "$fail_tx" ]; then
 		extra_msg="$extra_msg,tx=$count"
 	fi
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } ||
 	   { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then
-		echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx"
-		fail_test
+		fail_test "got $count MP_FAIL[s] TX expected $fail_tx"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo -n " - failrx"
+	print_check "failrx"
 	count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx")
 	if [ "$count" != "$fail_rx" ]; then
 		extra_msg="$extra_msg,rx=$count"
 	fi
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } ||
 	   { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then
-		echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx"
-		fail_test
+		fail_test "got $count MP_FAIL[s] RX expected $fail_rx"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo "$extra_msg"
+	print_info "$extra_msg"
 }
 
 chk_fclose_nr()
@@ -1361,39 +1377,37 @@ chk_fclose_nr()
 	local count
 	local ns_tx=$ns2
 	local ns_rx=$ns1
-	local extra_msg="   "
+	local extra_msg=""
 
 	if [[ $ns_invert = "invert" ]]; then
 		ns_tx=$ns1
 		ns_rx=$ns2
-		extra_msg=${extra_msg}"invert"
+		extra_msg="invert"
 	fi
 
-	printf "%-${nr_blank}s %s" " " "ctx"
+	print_check "ctx"
 	count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ "$count" != "$fclose_tx" ]; then
 		extra_msg="$extra_msg,tx=$count"
-		echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx"
-		fail_test
+		fail_test "got $count MP_FASTCLOSE[s] TX expected $fclose_tx"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo -n " - fclzrx"
+	print_check "fclzrx"
 	count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ "$count" != "$fclose_rx" ]; then
 		extra_msg="$extra_msg,rx=$count"
-		echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx"
-		fail_test
+		fail_test "got $count MP_FASTCLOSE[s] RX expected $fclose_rx"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo "$extra_msg"
+	print_info "$extra_msg"
 }
 
 chk_rst_nr()
@@ -1409,32 +1423,30 @@ chk_rst_nr()
 	if [[ $ns_invert = "invert" ]]; then
 		ns_tx=$ns2
 		ns_rx=$ns1
-		extra_msg="   invert"
+		extra_msg="invert"
 	fi
 
-	printf "%-${nr_blank}s %s" " " "rtx"
+	print_check "rtx"
 	count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ $count -lt $rst_tx ]; then
-		echo "[fail] got $count MP_RST[s] TX expected $rst_tx"
-		fail_test
+		fail_test "got $count MP_RST[s] TX expected $rst_tx"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo -n " - rstrx "
+	print_check "rstrx"
 	count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ "$count" -lt "$rst_rx" ]; then
-		echo "[fail] got $count MP_RST[s] RX expected $rst_rx"
-		fail_test
+		fail_test "got $count MP_RST[s] RX expected $rst_rx"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo "$extra_msg"
+	print_info "$extra_msg"
 }
 
 chk_infi_nr()
@@ -1443,26 +1455,24 @@ chk_infi_nr()
 	local infi_rx=$2
 	local count
 
-	printf "%-${nr_blank}s %s" " " "itx"
+	print_check "itx"
 	count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ "$count" != "$infi_tx" ]; then
-		echo "[fail] got $count infinite map[s] TX expected $infi_tx"
-		fail_test
+		fail_test "got $count infinite map[s] TX expected $infi_tx"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo -n " - infirx"
+	print_check "infirx"
 	count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx")
 	if [ -z "$count" ]; then
-		echo "[skip]"
+		print_skip
 	elif [ "$count" != "$infi_rx" ]; then
-		echo "[fail] got $count infinite map[s] RX expected $infi_rx"
-		fail_test
+		fail_test "got $count infinite map[s] RX expected $infi_rx"
 	else
-		echo "[ ok ]"
+		print_ok
 	fi
 }
 
@@ -1479,51 +1489,47 @@ chk_join_nr()
 	local corrupted_pkts=${9:-0}
 	local count
 	local with_cookie
-	local title="${TEST_NAME}"
 
 	if [ "${corrupted_pkts}" -gt 0 ]; then
-		title+=": ${corrupted_pkts} corrupted pkts"
+		print_info "${corrupted_pkts} corrupted pkts"
 	fi
 
-	printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn"
+	print_check "syn"
 	count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ "$count" != "$syn_nr" ]; then
-		echo "[fail] got $count JOIN[s] syn expected $syn_nr"
-		fail_test
+		fail_test "got $count JOIN[s] syn expected $syn_nr"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo -n " - synack"
+	print_check "synack"
 	with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies)
 	count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ "$count" != "$syn_ack_nr" ]; then
 		# simult connections exceeding the limit with cookie enabled could go up to
 		# synack validation as the conn limit can be enforced reliably only after
 		# the subflow creation
 		if [ "$with_cookie" = 2 ] && [ "$count" -gt "$syn_ack_nr" ] && [ "$count" -le "$syn_nr" ]; then
-			echo -n "[ ok ]"
+			print_ok
 		else
-			echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr"
-			fail_test
+			fail_test "got $count JOIN[s] synack expected $syn_ack_nr"
 		fi
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo -n " - ack"
+	print_check "ack"
 	count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx")
 	if [ -z "$count" ]; then
-		echo "[skip]"
+		print_skip
 	elif [ "$count" != "$ack_nr" ]; then
-		echo "[fail] got $count JOIN[s] ack expected $ack_nr"
-		fail_test
+		fail_test "got $count JOIN[s] ack expected $ack_nr"
 	else
-		echo "[ ok ]"
+		print_ok
 	fi
 	if [ $validate_checksum -eq 1 ]; then
 		chk_csum_nr $csum_ns1 $csum_ns2
@@ -1548,22 +1554,21 @@ chk_stale_nr()
 	local stale_nr
 	local recover_nr
 
-	printf "%-${nr_blank}s %-18s" " " "stale"
+	print_check "stale"
 
 	stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale")
 	recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover")
 	if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then
-		echo "[skip]"
+		print_skip
 	elif [ $stale_nr -lt $stale_min ] ||
 	   { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } ||
 	   [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then
-		echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \
+		fail_test "got $stale_nr stale[s] $recover_nr recover[s], " \
 		     " expected stale in range [$stale_min..$stale_max]," \
-		     " stale-recover delta $stale_delta "
-		fail_test
+		     " stale-recover delta $stale_delta"
 		dump_stats=1
 	else
-		echo "[ ok ]"
+		print_ok
 	fi
 
 	if [ "${dump_stats}" = 1 ]; then
@@ -1588,103 +1593,93 @@ chk_add_nr()
 
 	timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout)
 
-	printf "%-${nr_blank}s %s" " " "add"
+	print_check "add"
 	count=$(get_counter ${ns2} "MPTcpExtAddAddr")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	# if the test configured a short timeout tolerate greater then expected
 	# add addrs options, due to retransmissions
 	elif [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then
-		echo "[fail] got $count ADD_ADDR[s] expected $add_nr"
-		fail_test
+		fail_test "got $count ADD_ADDR[s] expected $add_nr"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo -n " - echo  "
+	print_check "echo"
 	count=$(get_counter ${ns1} "MPTcpExtEchoAdd")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ "$count" != "$echo_nr" ]; then
-		echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr"
-		fail_test
+		fail_test "got $count ADD_ADDR echo[s] expected $echo_nr"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
 	if [ $port_nr -gt 0 ]; then
-		echo -n " - pt "
+		print_check "pt"
 		count=$(get_counter ${ns2} "MPTcpExtPortAdd")
 		if [ -z "$count" ]; then
-			echo "[skip]"
+			print_skip
 		elif [ "$count" != "$port_nr" ]; then
-			echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr"
-			fail_test
+			fail_test "got $count ADD_ADDR[s] with a port-number expected $port_nr"
 		else
-			echo "[ ok ]"
+			print_ok
 		fi
 
-		printf "%-${nr_blank}s %s" " " "syn"
+		print_check "syn"
 		count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx")
 		if [ -z "$count" ]; then
-			echo -n "[skip]"
+			print_skip
 		elif [ "$count" != "$syn_nr" ]; then
-			echo "[fail] got $count JOIN[s] syn with a different \
-				port-number expected $syn_nr"
-			fail_test
+			fail_test "got $count JOIN[s] syn with a different \
+				   port-number expected $syn_nr"
 		else
-			echo -n "[ ok ]"
+			print_ok
 		fi
 
-		echo -n " - synack"
+		print_check "synack"
 		count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx")
 		if [ -z "$count" ]; then
-			echo -n "[skip]"
+			print_skip
 		elif [ "$count" != "$syn_ack_nr" ]; then
-			echo "[fail] got $count JOIN[s] synack with a different \
-				port-number expected $syn_ack_nr"
-			fail_test
+			fail_test "got $count JOIN[s] synack with a different \
+				   port-number expected $syn_ack_nr"
 		else
-			echo -n "[ ok ]"
+			print_ok
 		fi
 
-		echo -n " - ack"
+		print_check "ack"
 		count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx")
 		if [ -z "$count" ]; then
-			echo "[skip]"
+			print_skip
 		elif [ "$count" != "$ack_nr" ]; then
-			echo "[fail] got $count JOIN[s] ack with a different \
-				port-number expected $ack_nr"
-			fail_test
+			fail_test "got $count JOIN[s] ack with a different \
+				   port-number expected $ack_nr"
 		else
-			echo "[ ok ]"
+			print_ok
 		fi
 
-		printf "%-${nr_blank}s %s" " " "syn"
+		print_check "syn"
 		count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx")
 		if [ -z "$count" ]; then
-			echo -n "[skip]"
+			print_skip
 		elif [ "$count" != "$mis_syn_nr" ]; then
-			echo "[fail] got $count JOIN[s] syn with a mismatched \
-				port-number expected $mis_syn_nr"
-			fail_test
+			fail_test "got $count JOIN[s] syn with a mismatched \
+				   port-number expected $mis_syn_nr"
 		else
-			echo -n "[ ok ]"
+			print_ok
 		fi
 
-		echo -n " - ack   "
+		print_check "ack"
 		count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx")
 		if [ -z "$count" ]; then
-			echo "[skip]"
+			print_skip
 		elif [ "$count" != "$mis_ack_nr" ]; then
-			echo "[fail] got $count JOIN[s] ack with a mismatched \
-				port-number expected $mis_ack_nr"
-			fail_test
+			fail_test "got $count JOIN[s] ack with a mismatched \
+				   port-number expected $mis_ack_nr"
 		else
-			echo "[ ok ]"
+			print_ok
 		fi
-	else
-		echo ""
 	fi
 }
 
@@ -1697,28 +1692,26 @@ chk_add_tx_nr()
 
 	timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout)
 
-	printf "%-${nr_blank}s %s" " " "add TX"
+	print_check "add TX"
 	count=$(get_counter ${ns1} "MPTcpExtAddAddrTx")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	# if the test configured a short timeout tolerate greater then expected
 	# add addrs options, due to retransmissions
 	elif [ "$count" != "$add_tx_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_tx_nr" ]; }; then
-		echo "[fail] got $count ADD_ADDR[s] TX, expected $add_tx_nr"
-		fail_test
+		fail_test "got $count ADD_ADDR[s] TX, expected $add_tx_nr"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo -n " - echo TX "
+	print_check "echo TX"
 	count=$(get_counter ${ns2} "MPTcpExtEchoAddTx")
 	if [ -z "$count" ]; then
-		echo "[skip]"
+		print_skip
 	elif [ "$count" != "$echo_tx_nr" ]; then
-		echo "[fail] got $count ADD_ADDR echo[s] TX, expected $echo_tx_nr"
-		fail_test
+		fail_test "got $count ADD_ADDR echo[s] TX, expected $echo_tx_nr"
 	else
-		echo "[ ok ]"
+		print_ok
 	fi
 }
 
@@ -1746,24 +1739,23 @@ chk_rm_nr()
 	elif [ $invert = "true" ]; then
 		addr_ns=$ns2
 		subflow_ns=$ns1
-		extra_msg="   invert"
+		extra_msg="invert"
 	fi
 
-	printf "%-${nr_blank}s %s" " " "rm "
+	print_check "rm"
 	count=$(get_counter ${addr_ns} "MPTcpExtRmAddr")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ "$count" != "$rm_addr_nr" ]; then
-		echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr"
-		fail_test
+		fail_test "got $count RM_ADDR[s] expected $rm_addr_nr"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo -n " - rmsf  "
+	print_check "rmsf"
 	count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ -n "$simult" ]; then
 		local cnt suffix
 
@@ -1775,34 +1767,31 @@ chk_rm_nr()
 		[ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]"
 		if [ $count -ge "$rm_subflow_nr" ] && \
 		   [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then
-			echo -n "[ ok ] $suffix"
+			print_ok "$suffix"
 		else
-			echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]"
-			fail_test
+			fail_test "got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]"
 		fi
 	elif [ "$count" != "$rm_subflow_nr" ]; then
-		echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr"
-		fail_test
+		fail_test "got $count RM_SUBFLOW[s] expected $rm_subflow_nr"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo "$extra_msg"
+	print_info "$extra_msg"
 }
 
 chk_rm_tx_nr()
 {
 	local rm_addr_tx_nr=$1
 
-	printf "%-${nr_blank}s %s" " " "rm TX "
+	print_check "rm TX"
 	count=$(get_counter ${ns2} "MPTcpExtRmAddrTx")
 	if [ -z "$count" ]; then
-		echo "[skip]"
+		print_skip
 	elif [ "$count" != "$rm_addr_tx_nr" ]; then
-		echo "[fail] got $count RM_ADDR[s] expected $rm_addr_tx_nr"
-		fail_test
+		fail_test "got $count RM_ADDR[s] expected $rm_addr_tx_nr"
 	else
-		echo "[ ok ]"
+		print_ok
 	fi
 }
 
@@ -1812,52 +1801,44 @@ chk_prio_nr()
 	local mp_prio_nr_rx=$2
 	local count
 
-	printf "%-${nr_blank}s %s" " " "ptx"
+	print_check "ptx"
 	count=$(get_counter ${ns1} "MPTcpExtMPPrioTx")
 	if [ -z "$count" ]; then
-		echo -n "[skip]"
+		print_skip
 	elif [ "$count" != "$mp_prio_nr_tx" ]; then
-		echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx"
-		fail_test
+		fail_test "got $count MP_PRIO[s] TX expected $mp_prio_nr_tx"
 	else
-		echo -n "[ ok ]"
+		print_ok
 	fi
 
-	echo -n " - prx   "
+	print_check "prx"
 	count=$(get_counter ${ns1} "MPTcpExtMPPrioRx")
 	if [ -z "$count" ]; then
-		echo "[skip]"
+		print_skip
 	elif [ "$count" != "$mp_prio_nr_rx" ]; then
-		echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx"
-		fail_test
+		fail_test "got $count MP_PRIO[s] RX expected $mp_prio_nr_rx"
 	else
-		echo "[ ok ]"
+		print_ok
 	fi
 }
 
 chk_subflow_nr()
 {
-	local need_title="$1"
-	local msg="$2"
-	local subflow_nr=$3
+	local msg="$1"
+	local subflow_nr=$2
 	local cnt1
 	local cnt2
 	local dump_stats
 
-	if [ -n "${need_title}" ]; then
-		printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}"
-	else
-		printf "%-${nr_blank}s %s" " " "${msg}"
-	fi
+	print_check "${msg}"
 
 	cnt1=$(ss -N $ns1 -tOni | grep -c token)
 	cnt2=$(ss -N $ns2 -tOni | grep -c token)
 	if [ "$cnt1" != "$subflow_nr" ] || [ "$cnt2" != "$subflow_nr" ]; then
-		echo "[fail] got $cnt1:$cnt2 subflows expected $subflow_nr"
-		fail_test
+		fail_test "got $cnt1:$cnt2 subflows expected $subflow_nr"
 		dump_stats=1
 	else
-		echo "[ ok ]"
+		print_ok
 	fi
 
 	if [ "${dump_stats}" = 1 ]; then
@@ -1877,7 +1858,7 @@ chk_mptcp_info()
 	local cnt2
 	local dump_stats
 
-	printf "%-${nr_blank}s %-30s" " " "mptcp_info $info1:$info2=$exp1:$exp2"
+	print_check "mptcp_info ${info1:0:8}=$exp1:$exp2"
 
 	cnt1=$(ss -N $ns1 -inmHM | grep "$info1:" |
 	       sed -n 's/.*\('"$info1"':\)\([[:digit:]]*\).*$/\2/p;q')
@@ -1888,11 +1869,10 @@ chk_mptcp_info()
 	[ -z "$cnt2" ] && cnt2=0
 
 	if [ "$cnt1" != "$exp1" ] || [ "$cnt2" != "$exp2" ]; then
-		echo "[fail] got $cnt1:$cnt2 $info1:$info2 expected $exp1:$exp2"
-		fail_test
+		fail_test "got $cnt1:$cnt2 $info1:$info2 expected $exp1:$exp2"
 		dump_stats=1
 	else
-		echo "[ ok ]"
+		print_ok
 	fi
 
 	if [ "$dump_stats" = 1 ]; then
@@ -1914,13 +1894,12 @@ chk_link_usage()
 	local tx_rate=$((tx_link * 100 / tx_total))
 	local tolerance=5
 
-	printf "%-${nr_blank}s %-18s" " " "link usage"
+	print_check "link usage"
 	if [ $tx_rate -lt $((expected_rate - tolerance)) ] || \
 	   [ $tx_rate -gt $((expected_rate + tolerance)) ]; then
-		echo "[fail] got $tx_rate% usage, expected $expected_rate%"
-		fail_test
+		fail_test "got $tx_rate% usage, expected $expected_rate%"
 	else
-		echo "[ ok ]"
+		print_ok
 	fi
 }
 
@@ -2835,15 +2814,15 @@ verify_listener_events()
 	if [ $e_type = $LISTENER_CREATED ]; then
 		name="LISTENER_CREATED"
 	elif [ $e_type = $LISTENER_CLOSED ]; then
-		name="LISTENER_CLOSED"
+		name="LISTENER_CLOSED "
 	else
 		name="$e_type"
 	fi
 
-	printf "%-${nr_blank}s %s %s:%s " " " "$name" "$e_saddr" "$e_sport"
+	print_check "$name $e_saddr:$e_sport"
 
 	if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then
-		printf "[skip]: event not supported\n"
+		print_skip "event not supported"
 		return
 	fi
 
@@ -2860,11 +2839,10 @@ verify_listener_events()
 	   [ $family ] && [ $family = $e_family ] &&
 	   [ $saddr ] && [ $saddr = $e_saddr ] &&
 	   [ $sport ] && [ $sport = $e_sport ]; then
-		echo "[ ok ]"
+		print_ok
 		return 0
 	fi
-	fail_test
-	echo "[fail]"
+	fail_test "$e_type:$type $e_family:$family $e_saddr:$saddr $e_sport:$sport"
 }
 
 add_addr_ports_tests()
@@ -3469,17 +3447,17 @@ endpoint_tests()
 			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
 
 		wait_mpj $ns1
-		pm_nl_check_endpoint 1 "creation" \
+		pm_nl_check_endpoint "creation" \
 			$ns2 10.0.2.2 id 1 flags implicit
 		chk_mptcp_info subflows 1 subflows 1
 		chk_mptcp_info add_addr_signal 1 add_addr_accepted 1
 
 		pm_nl_add_endpoint $ns2 10.0.2.2 id 33
-		pm_nl_check_endpoint 0 "ID change is prevented" \
+		pm_nl_check_endpoint "ID change is prevented" \
 			$ns2 10.0.2.2 id 1 flags implicit
 
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags signal
-		pm_nl_check_endpoint 0 "modif is allowed" \
+		pm_nl_check_endpoint "modif is allowed" \
 			$ns2 10.0.2.2 id 1 flags signal
 		kill_tests_wait
 	fi
@@ -3493,17 +3471,17 @@ endpoint_tests()
 			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
 
 		wait_mpj $ns2
-		chk_subflow_nr needtitle "before delete" 2
+		chk_subflow_nr "before delete" 2
 		chk_mptcp_info subflows 1 subflows 1
 
 		pm_nl_del_endpoint $ns2 2 10.0.2.2
 		sleep 0.5
-		chk_subflow_nr "" "after delete" 1
+		chk_subflow_nr "after delete" 1
 		chk_mptcp_info subflows 0 subflows 0
 
 		pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow
 		wait_mpj $ns2
-		chk_subflow_nr "" "after re-add" 2
+		chk_subflow_nr "after re-add" 2
 		chk_mptcp_info subflows 1 subflows 1
 		kill_tests_wait
 	fi
-- 
GitLab


From 9466df1a27d55842bec496d3a84e98ee938c31aa Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Sun, 30 Jul 2023 10:05:16 +0200
Subject: [PATCH 0681/1806] selftests: mptcp: join: colored results

Thanks to the parent commit, it is easy to change the output and add
some colours to help spotting issues.

The colours are not used if stdout is redirected or if NO_COLOR env var
is set to 1 as specified in https://no-color.org.

It is possible to force displaying the colours even if stdout is
redirected by setting this env var:

  SELFTESTS_MPTCP_LIB_COLOR_FORCE=1

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Link: https://lore.kernel.org/r/20230730-upstream-net-next-20230728-mptcp-selftests-misc-v1-2-7e9cc530a9cd@tessares.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh |  8 ++--
 .../testing/selftests/net/mptcp/mptcp_lib.sh  | 39 +++++++++++++++++++
 2 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 6da3a6c98ba7a..136d20641fcea 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -215,22 +215,22 @@ print_info()
 	# It can be empty, no need to print anything then
 	[ -z "${1}" ] && return
 
-	printf "%-${nr_blank}sInfo: %s\n" " " "${*}"
+	mptcp_lib_print_info "      Info: ${*}"
 }
 
 print_ok()
 {
-	echo "[ ok ]${1:+ ${*}}"
+	mptcp_lib_print_ok "[ ok ]${1:+ ${*}}"
 }
 
 print_fail()
 {
-	echo "[fail]${1:+ ${*}}"
+	mptcp_lib_print_err "[fail]${1:+ ${*}}"
 }
 
 print_skip()
 {
-	echo "[skip]${1:+ ${*}}"
+	mptcp_lib_print_warn "[skip]${1:+ ${*}}"
 }
 
 # [ $1: fail msg ]
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index b1a0fdd0408b5..92a5befe80394 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -4,10 +4,49 @@
 readonly KSFT_PASS=0
 readonly KSFT_FAIL=1
 readonly KSFT_SKIP=4
+
+# shellcheck disable=SC2155 # declare and assign separately
 readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g')
 
 MPTCP_LIB_SUBTESTS=()
 
+# only if supported (or forced) and not disabled, see no-color.org
+if { [ -t 1 ] || [ "${SELFTESTS_MPTCP_LIB_COLOR_FORCE:-}" = "1" ]; } &&
+   [ "${NO_COLOR:-}" != "1" ]; then
+	readonly MPTCP_LIB_COLOR_RED="\E[1;31m"
+	readonly MPTCP_LIB_COLOR_GREEN="\E[1;32m"
+	readonly MPTCP_LIB_COLOR_YELLOW="\E[1;33m"
+	readonly MPTCP_LIB_COLOR_BLUE="\E[1;34m"
+	readonly MPTCP_LIB_COLOR_RESET="\E[0m"
+else
+	readonly MPTCP_LIB_COLOR_RED=
+	readonly MPTCP_LIB_COLOR_GREEN=
+	readonly MPTCP_LIB_COLOR_YELLOW=
+	readonly MPTCP_LIB_COLOR_BLUE=
+	readonly MPTCP_LIB_COLOR_RESET=
+fi
+
+# $1: color, $2: text
+mptcp_lib_print_color() {
+	echo -e "${MPTCP_LIB_START_PRINT:-}${*}${MPTCP_LIB_COLOR_RESET}"
+}
+
+mptcp_lib_print_ok() {
+	mptcp_lib_print_color "${MPTCP_LIB_COLOR_GREEN}${*}"
+}
+
+mptcp_lib_print_warn() {
+	mptcp_lib_print_color "${MPTCP_LIB_COLOR_YELLOW}${*}"
+}
+
+mptcp_lib_print_info() {
+	mptcp_lib_print_color "${MPTCP_LIB_COLOR_BLUE}${*}"
+}
+
+mptcp_lib_print_err() {
+	mptcp_lib_print_color "${MPTCP_LIB_COLOR_RED}${*}"
+}
+
 # SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all
 # features using the last version of the kernel and the selftests to make sure
 # a test is not being skipped by mistake.
-- 
GitLab


From 1dc88d241f9260fac6477ad040a5f1edbc3c2968 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Sun, 30 Jul 2023 10:05:17 +0200
Subject: [PATCH 0682/1806] selftests: mptcp: pm_nl_ctl: always look for errors

If a Netlink command for the MPTCP path-managers is not valid, it is
important to check if there are errors. If yes, they need to be reported
instead of being ignored and exiting without errors.

Now if no replies are expected, an ACK from the kernelspace is asked by
the userspace in order to always expect a reply. We can use the same
buffer that is currently always >1024 bytes. Then we can check if there
is an error (err->error), print it if any and report the error.

After this modification, it is required to mute expected errors in
mptcp_join.sh and pm_netlink.sh selftests:

- when trying to add a bad endpoint, e.g. duplicated
- when trying to set the two limits above the hard limit

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Link: https://lore.kernel.org/r/20230730-upstream-net-next-20230728-mptcp-selftests-misc-v1-3-7e9cc530a9cd@tessares.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh |  2 +-
 .../testing/selftests/net/mptcp/pm_netlink.sh |  6 ++--
 tools/testing/selftests/net/mptcp/pm_nl_ctl.c | 33 ++++++++++++-------
 3 files changed, 26 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 136d20641fcea..63658b0416fb6 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3452,7 +3452,7 @@ endpoint_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_mptcp_info add_addr_signal 1 add_addr_accepted 1
 
-		pm_nl_add_endpoint $ns2 10.0.2.2 id 33
+		pm_nl_add_endpoint $ns2 10.0.2.2 id 33 2>/dev/null
 		pm_nl_check_endpoint "ID change is prevented" \
 			$ns2 10.0.2.2 id 1 flags implicit
 
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index f32038fe1ee5b..8f4ff123a7eb9 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -99,7 +99,7 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" \
 "id 1 flags  10.0.1.1
 id 3 flags signal,backup 10.0.1.3" "dump addrs after del"
 
-ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3 2>/dev/null
 check "ip netns exec $ns1 ./pm_nl_ctl get 4" "" "duplicate addr"
 
 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.4 flags signal
@@ -127,10 +127,10 @@ id 8 flags signal 10.0.1.8" "id limit"
 ip netns exec $ns1 ./pm_nl_ctl flush
 check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs"
 
-ip netns exec $ns1 ./pm_nl_ctl limits 9 1
+ip netns exec $ns1 ./pm_nl_ctl limits 9 1 2>/dev/null
 check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "rcv addrs above hard limit"
 
-ip netns exec $ns1 ./pm_nl_ctl limits 1 9
+ip netns exec $ns1 ./pm_nl_ctl limits 1 9 2>/dev/null
 check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "subflows above hard limit"
 
 ip netns exec $ns1 ./pm_nl_ctl limits 8 8
diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
index 1887bd61bd9a5..49369c4a5f261 100644
--- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
+++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
@@ -66,20 +66,25 @@ static int init_genl_req(char *data, int family, int cmd, int version)
 	return off;
 }
 
-static void nl_error(struct nlmsghdr *nh)
+static int nl_error(struct nlmsghdr *nh)
 {
 	struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(nh);
 	int len = nh->nlmsg_len - sizeof(*nh);
 	uint32_t off;
 
-	if (len < sizeof(struct nlmsgerr))
+	if (len < sizeof(struct nlmsgerr)) {
 		error(1, 0, "netlink error message truncated %d min %ld", len,
 		      sizeof(struct nlmsgerr));
+		return -1;
+	}
 
-	if (!err->error) {
+	if (err->error) {
 		/* check messages from kernel */
 		struct rtattr *attrs = (struct rtattr *)NLMSG_DATA(nh);
 
+		fprintf(stderr, "netlink error %d (%s)\n",
+			err->error, strerror(-err->error));
+
 		while (RTA_OK(attrs, len)) {
 			if (attrs->rta_type == NLMSGERR_ATTR_MSG)
 				fprintf(stderr, "netlink ext ack msg: %s\n",
@@ -91,9 +96,10 @@ static void nl_error(struct nlmsghdr *nh)
 			}
 			attrs = RTA_NEXT(attrs, len);
 		}
-	} else {
-		fprintf(stderr, "netlink error %d", err->error);
+		return -1;
 	}
+
+	return 0;
 }
 
 static int capture_events(int fd, int event_group)
@@ -198,7 +204,7 @@ static int capture_events(int fd, int event_group)
 	return 0;
 }
 
-/* do a netlink command and, if max > 0, fetch the reply  */
+/* do a netlink command and, if max > 0, fetch the reply ; nh's size >1024B */
 static int do_nl_req(int fd, struct nlmsghdr *nh, int len, int max)
 {
 	struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
@@ -207,12 +213,16 @@ static int do_nl_req(int fd, struct nlmsghdr *nh, int len, int max)
 	int rem, ret;
 	int err = 0;
 
+	/* If no expected answer, ask for an ACK to look for errors if any */
+	if (max == 0) {
+		nh->nlmsg_flags |= NLM_F_ACK;
+		max = 1024;
+	}
+
 	nh->nlmsg_len = len;
 	ret = sendto(fd, data, len, 0, (void *)&nladdr, sizeof(nladdr));
 	if (ret != len)
 		error(1, errno, "send netlink: %uB != %uB\n", ret, len);
-	if (max == 0)
-		return 0;
 
 	addr_len = sizeof(nladdr);
 	rem = ret = recvfrom(fd, data, max, 0, (void *)&nladdr, &addr_len);
@@ -221,10 +231,11 @@ static int do_nl_req(int fd, struct nlmsghdr *nh, int len, int max)
 
 	/* Beware: the NLMSG_NEXT macro updates the 'rem' argument */
 	for (; NLMSG_OK(nh, rem); nh = NLMSG_NEXT(nh, rem)) {
-		if (nh->nlmsg_type == NLMSG_ERROR) {
-			nl_error(nh);
+		if (nh->nlmsg_type == NLMSG_DONE)
+			break;
+
+		if (nh->nlmsg_type == NLMSG_ERROR && nl_error(nh))
 			err = 1;
-		}
 	}
 	if (err)
 		error(1, 0, "bailing out due to netlink error[s]");
-- 
GitLab


From 6a5c8c69a4c771625ea25fb2bc916d274516288a Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Sun, 30 Jul 2023 10:05:18 +0200
Subject: [PATCH 0683/1806] selftests: mptcp: userspace_pm: unmute unexpected
 errors

All pm_nl_ctl commands were muted. If there was an unexpected error with
one of them, this was simply not visible in the logs, making the
analysis very hard. It could also hide misuse of commands by mistake.

Now the output is only muted when we do expect to have an error, e.g.
when giving invalid arguments on purpose.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Link: https://lore.kernel.org/r/20230730-upstream-net-next-20230728-mptcp-selftests-misc-v1-4-7e9cc530a9cd@tessares.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/net/mptcp/userspace_pm.sh       | 100 +++++++++---------
 1 file changed, 50 insertions(+), 50 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 23f8959a8ea8e..b25a3e33eb253 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -380,7 +380,7 @@ test_announce()
 	:>"$server_evts"
 	ip netns exec "$ns2"\
 	   ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id $client_addr_id dev\
-	   ns2eth1 > /dev/null 2>&1
+	   ns2eth1
 	print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, reuse port"
 	sleep 0.5
 	verify_announce_event $server_evts $ANNOUNCED $server4_token "10.0.2.2" $client_addr_id \
@@ -389,7 +389,7 @@ test_announce()
 	# ADD_ADDR6 from the client to server machine reusing the subflow port
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl ann\
-	   dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1 > /dev/null 2>&1
+	   dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1
 	print_test "ADD_ADDR6 id:${client_addr_id} dead:beef:2::2 (ns2) => ns1, reuse port"
 	sleep 0.5
 	verify_announce_event "$server_evts" "$ANNOUNCED" "$server6_token" "dead:beef:2::2"\
@@ -399,7 +399,7 @@ test_announce()
 	:>"$server_evts"
 	client_addr_id=$((client_addr_id+1))
 	ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\
-	   $client_addr_id dev ns2eth1 port $new4_port > /dev/null 2>&1
+	   $client_addr_id dev ns2eth1 port $new4_port
 	print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, new port"
 	sleep 0.5
 	verify_announce_event "$server_evts" "$ANNOUNCED" "$server4_token" "10.0.2.2"\
@@ -410,7 +410,7 @@ test_announce()
 
 	# ADD_ADDR from the server to client machine reusing the subflow port
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
-	   $server_addr_id dev ns1eth2 > /dev/null 2>&1
+	   $server_addr_id dev ns1eth2
 	print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\
@@ -419,7 +419,7 @@ test_announce()
 	# ADD_ADDR6 from the server to client machine reusing the subflow port
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\
-	   $server_addr_id dev ns1eth2 > /dev/null 2>&1
+	   $server_addr_id dev ns1eth2
 	print_test "ADD_ADDR6 id:${server_addr_id} dead:beef:2::1 (ns1) => ns2, reuse port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "dead:beef:2::1"\
@@ -429,7 +429,7 @@ test_announce()
 	:>"$client_evts"
 	server_addr_id=$((server_addr_id+1))
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
-	   $server_addr_id dev ns1eth2 port $new4_port > /dev/null 2>&1
+	   $server_addr_id dev ns1eth2 port $new4_port
 	print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, new port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\
@@ -490,7 +490,7 @@ test_remove()
 	# RM_ADDR from the client to server machine
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
-	   $client_addr_id > /dev/null 2>&1
+	   $client_addr_id
 	print_test "RM_ADDR id:${client_addr_id} ns2 => ns1"
 	sleep 0.5
 	verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id"
@@ -499,7 +499,7 @@ test_remove()
 	:>"$server_evts"
 	client_addr_id=$(( client_addr_id - 1 ))
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
-	   $client_addr_id > /dev/null 2>&1
+	   $client_addr_id
 	print_test "RM_ADDR id:${client_addr_id} ns2 => ns1"
 	sleep 0.5
 	verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id"
@@ -507,7 +507,7 @@ test_remove()
 	# RM_ADDR6 from the client to server machine
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client6_token" id\
-	   $client_addr_id > /dev/null 2>&1
+	   $client_addr_id
 	print_test "RM_ADDR6 id:${client_addr_id} ns2 => ns1"
 	sleep 0.5
 	verify_remove_event "$server_evts" "$REMOVED" "$server6_token" "$client_addr_id"
@@ -517,7 +517,7 @@ test_remove()
 
 	# RM_ADDR from the server to client machine
 	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\
-	   $server_addr_id > /dev/null 2>&1
+	   $server_addr_id
 	print_test "RM_ADDR id:${server_addr_id} ns1 => ns2"
 	sleep 0.5
 	verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id"
@@ -526,7 +526,7 @@ test_remove()
 	:>"$client_evts"
 	server_addr_id=$(( server_addr_id - 1 ))
 	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\
-	   $server_addr_id > /dev/null 2>&1
+	   $server_addr_id
 	print_test "RM_ADDR id:${server_addr_id} ns1 => ns2"
 	sleep 0.5
 	verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id"
@@ -534,7 +534,7 @@ test_remove()
 	# RM_ADDR6 from the server to client machine
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server6_token" id\
-	   $server_addr_id > /dev/null 2>&1
+	   $server_addr_id
 	print_test "RM_ADDR6 id:${server_addr_id} ns1 => ns2"
 	sleep 0.5
 	verify_remove_event "$client_evts" "$REMOVED" "$client6_token" "$server_addr_id"
@@ -610,18 +610,18 @@ test_subflows()
 
 	# Attempt to add a listener at 10.0.2.2:<subflow-port>
 	ip netns exec "$ns2" ./pm_nl_ctl listen 10.0.2.2\
-	   "$client4_port" > /dev/null 2>&1 &
+	   "$client4_port" &
 	local listener_pid=$!
 
 	# ADD_ADDR from client to server machine reusing the subflow port
 	ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\
-	   $client_addr_id > /dev/null 2>&1
+	   $client_addr_id
 	sleep 0.5
 
 	# CREATE_SUBFLOW from server to client machine
 	:>"$server_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2\
-	   rport "$client4_port" token "$server4_token" > /dev/null 2>&1
+	   rport "$client4_port" token "$server4_token"
 	sleep 0.5
 	verify_subflow_events $server_evts $SUB_ESTABLISHED $server4_token $AF_INET "10.0.2.1" \
 			      "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2"
@@ -635,31 +635,31 @@ test_subflows()
 	# DESTROY_SUBFLOW from server to client machine
 	:>"$server_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl dsf lip 10.0.2.1 lport "$sport" rip 10.0.2.2 rport\
-	   "$client4_port" token "$server4_token" > /dev/null 2>&1
+	   "$client4_port" token "$server4_token"
 	sleep 0.5
 	verify_subflow_events "$server_evts" "$SUB_CLOSED" "$server4_token" "$AF_INET" "10.0.2.1"\
 			      "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2"
 
 	# RM_ADDR from client to server machine
 	ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\
-	   "$client4_token" > /dev/null 2>&1
+	   "$client4_token"
 	sleep 0.5
 
 	# Attempt to add a listener at dead:beef:2::2:<subflow-port>
 	ip netns exec "$ns2" ./pm_nl_ctl listen dead:beef:2::2\
-	   "$client6_port" > /dev/null 2>&1 &
+	   "$client6_port" &
 	listener_pid=$!
 
 	# ADD_ADDR6 from client to server machine reusing the subflow port
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl ann dead:beef:2::2 token "$client6_token" id\
-	   $client_addr_id > /dev/null 2>&1
+	   $client_addr_id
 	sleep 0.5
 
 	# CREATE_SUBFLOW6 from server to client machine
 	:>"$server_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl csf lip dead:beef:2::1 lid 23 rip\
-	   dead:beef:2::2 rport "$client6_port" token "$server6_token" > /dev/null 2>&1
+	   dead:beef:2::2 rport "$client6_port" token "$server6_token"
 	sleep 0.5
 	verify_subflow_events "$server_evts" "$SUB_ESTABLISHED" "$server6_token" "$AF_INET6"\
 			      "dead:beef:2::1" "dead:beef:2::2" "$client6_port" "23"\
@@ -673,7 +673,7 @@ test_subflows()
 	# DESTROY_SUBFLOW6 from server to client machine
 	:>"$server_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl dsf lip dead:beef:2::1 lport "$sport" rip\
-	   dead:beef:2::2 rport "$client6_port" token "$server6_token" > /dev/null 2>&1
+	   dead:beef:2::2 rport "$client6_port" token "$server6_token"
 	sleep 0.5
 	verify_subflow_events "$server_evts" "$SUB_CLOSED" "$server6_token" "$AF_INET6"\
 			      "dead:beef:2::1" "dead:beef:2::2" "$client6_port" "23"\
@@ -681,24 +681,24 @@ test_subflows()
 
 	# RM_ADDR from client to server machine
 	ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\
-	   "$client6_token" > /dev/null 2>&1
+	   "$client6_token"
 	sleep 0.5
 
 	# Attempt to add a listener at 10.0.2.2:<new-port>
 	ip netns exec "$ns2" ./pm_nl_ctl listen 10.0.2.2\
-	   $new4_port > /dev/null 2>&1 &
+	   $new4_port &
 	listener_pid=$!
 
 	# ADD_ADDR from client to server machine using a new port
 	:>"$server_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\
-	   $client_addr_id port $new4_port > /dev/null 2>&1
+	   $client_addr_id port $new4_port
 	sleep 0.5
 
 	# CREATE_SUBFLOW from server to client machine
 	:>"$server_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2 rport\
-	   $new4_port token "$server4_token" > /dev/null 2>&1
+	   $new4_port token "$server4_token"
 	sleep 0.5
 	verify_subflow_events "$server_evts" "$SUB_ESTABLISHED" "$server4_token" "$AF_INET"\
 			      "10.0.2.1" "10.0.2.2" "$new4_port" "23"\
@@ -712,32 +712,32 @@ test_subflows()
 	# DESTROY_SUBFLOW from server to client machine
 	:>"$server_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl dsf lip 10.0.2.1 lport "$sport" rip 10.0.2.2 rport\
-	   $new4_port token "$server4_token" > /dev/null 2>&1
+	   $new4_port token "$server4_token"
 	sleep 0.5
 	verify_subflow_events "$server_evts" "$SUB_CLOSED" "$server4_token" "$AF_INET" "10.0.2.1"\
 			      "10.0.2.2" "$new4_port" "23" "$client_addr_id" "ns1" "ns2"
 
 	# RM_ADDR from client to server machine
 	ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\
-	   "$client4_token" > /dev/null 2>&1
+	   "$client4_token"
 
 	# Capture events on the network namespace running the client
 	:>"$client_evts"
 
 	# Attempt to add a listener at 10.0.2.1:<subflow-port>
 	ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\
-	   $app4_port > /dev/null 2>&1 &
+	   $app4_port &
 	listener_pid=$!
 
 	# ADD_ADDR from server to client machine reusing the subflow port
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
-	   $server_addr_id > /dev/null 2>&1
+	   $server_addr_id
 	sleep 0.5
 
 	# CREATE_SUBFLOW from client to server machine
 	:>"$client_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\
-	   $app4_port token "$client4_token" > /dev/null 2>&1
+	   $app4_port token "$client4_token"
 	sleep 0.5
 	verify_subflow_events $client_evts $SUB_ESTABLISHED $client4_token $AF_INET "10.0.2.2"\
 			      "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1"
@@ -750,31 +750,31 @@ test_subflows()
 	# DESTROY_SUBFLOW from client to server machine
 	:>"$client_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\
-	   $app4_port token "$client4_token" > /dev/null 2>&1
+	   $app4_port token "$client4_token"
 	sleep 0.5
 	verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client4_token" "$AF_INET" "10.0.2.2"\
 			      "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1"
 
 	# RM_ADDR from server to client machine
 	ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
-	   "$server4_token" > /dev/null 2>&1
+	   "$server4_token"
 	sleep 0.5
 
 	# Attempt to add a listener at dead:beef:2::1:<subflow-port>
 	ip netns exec "$ns1" ./pm_nl_ctl listen dead:beef:2::1\
-	   $app6_port > /dev/null 2>&1 &
+	   $app6_port &
 	listener_pid=$!
 
 	# ADD_ADDR6 from server to client machine reusing the subflow port
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\
-	   $server_addr_id > /dev/null 2>&1
+	   $server_addr_id
 	sleep 0.5
 
 	# CREATE_SUBFLOW6 from client to server machine
 	:>"$client_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl csf lip dead:beef:2::2 lid 23 rip\
-	   dead:beef:2::1 rport $app6_port token "$client6_token" > /dev/null 2>&1
+	   dead:beef:2::1 rport $app6_port token "$client6_token"
 	sleep 0.5
 	verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\
 			      "$AF_INET6" "dead:beef:2::2"\
@@ -789,31 +789,31 @@ test_subflows()
 	# DESTROY_SUBFLOW6 from client to server machine
 	:>"$client_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl dsf lip dead:beef:2::2 lport "$sport" rip\
-	   dead:beef:2::1 rport $app6_port token "$client6_token" > /dev/null 2>&1
+	   dead:beef:2::1 rport $app6_port token "$client6_token"
 	sleep 0.5
 	verify_subflow_events $client_evts $SUB_CLOSED $client6_token $AF_INET6 "dead:beef:2::2"\
 			      "dead:beef:2::1" "$app6_port" "23" "$server_addr_id" "ns2" "ns1"
 
 	# RM_ADDR6 from server to client machine
 	ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
-	   "$server6_token" > /dev/null 2>&1
+	   "$server6_token"
 	sleep 0.5
 
 	# Attempt to add a listener at 10.0.2.1:<new-port>
 	ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\
-	   $new4_port > /dev/null 2>&1 &
+	   $new4_port &
 	listener_pid=$!
 
 	# ADD_ADDR from server to client machine using a new port
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
-	   $server_addr_id port $new4_port > /dev/null 2>&1
+	   $server_addr_id port $new4_port
 	sleep 0.5
 
 	# CREATE_SUBFLOW from client to server machine
 	:>"$client_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\
-	   $new4_port token "$client4_token" > /dev/null 2>&1
+	   $new4_port token "$client4_token"
 	sleep 0.5
 	verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client4_token" "$AF_INET"\
 			      "10.0.2.2" "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1"
@@ -826,14 +826,14 @@ test_subflows()
 	# DESTROY_SUBFLOW from client to server machine
 	:>"$client_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\
-	   $new4_port token "$client4_token" > /dev/null 2>&1
+	   $new4_port token "$client4_token"
 	sleep 0.5
 	verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client4_token" "$AF_INET" "10.0.2.2"\
 			      "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1"
 
 	# RM_ADDR from server to client machine
 	ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
-	   "$server4_token" > /dev/null 2>&1
+	   "$server4_token"
 }
 
 test_subflows_v4_v6_mix()
@@ -842,14 +842,14 @@ test_subflows_v4_v6_mix()
 
 	# Attempt to add a listener at 10.0.2.1:<subflow-port>
 	ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\
-	   $app6_port > /dev/null 2>&1 &
+	   $app6_port &
 	local listener_pid=$!
 
 	# ADD_ADDR4 from server to client machine reusing the subflow port on
 	# the established v6 connection
 	:>"$client_evts"
 	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\
-	   $server_addr_id dev ns1eth2 > /dev/null 2>&1
+	   $server_addr_id dev ns1eth2
 	print_test "ADD_ADDR4 id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port"
 	sleep 0.5
 	verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\
@@ -858,7 +858,7 @@ test_subflows_v4_v6_mix()
 	# CREATE_SUBFLOW from client to server machine
 	:>"$client_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\
-	   $app6_port token "$client6_token" > /dev/null 2>&1
+	   $app6_port token "$client6_token"
 	sleep 0.5
 	verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\
 			      "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\
@@ -872,7 +872,7 @@ test_subflows_v4_v6_mix()
 	# DESTROY_SUBFLOW from client to server machine
 	:>"$client_evts"
 	ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\
-	   $app6_port token "$client6_token" > /dev/null 2>&1
+	   $app6_port token "$client6_token"
 	sleep 0.5
 	verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client6_token" \
 			      "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\
@@ -880,7 +880,7 @@ test_subflows_v4_v6_mix()
 
 	# RM_ADDR from server to client machine
 	ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
-	   "$server6_token" > /dev/null 2>&1
+	   "$server6_token"
 	sleep 0.5
 }
 
@@ -965,7 +965,7 @@ test_listener()
 
 	# Attempt to add a listener at 10.0.2.2:<subflow-port>
 	ip netns exec $ns2 ./pm_nl_ctl listen 10.0.2.2\
-		$client4_port > /dev/null 2>&1 &
+		$client4_port &
 	local listener_pid=$!
 
 	sleep 0.5
@@ -973,12 +973,12 @@ test_listener()
 
 	# ADD_ADDR from client to server machine reusing the subflow port
 	ip netns exec $ns2 ./pm_nl_ctl ann 10.0.2.2 token $client4_token id\
-		$client_addr_id > /dev/null 2>&1
+		$client_addr_id
 	sleep 0.5
 
 	# CREATE_SUBFLOW from server to client machine
 	ip netns exec $ns1 ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2\
-		rport $client4_port token $server4_token > /dev/null 2>&1
+		rport $client4_port token $server4_token
 	sleep 0.5
 
 	# Delete the listener from the client ns, if one was created
-- 
GitLab


From 8798481b667fa7c9bbd5aa843bf1557ada699964 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Fri, 28 Jul 2023 12:35:33 -0300
Subject: [PATCH 0684/1806] net/sched: wrap open coded Qdics class filter
 counter

The 'filter_cnt' counter is used to control a Qdisc class lifetime.
Each filter referecing this class by its id will eventually
increment/decrement this counter in their respective
'add/update/delete' routines.
As these operations are always serialized under rtnl lock, we don't
need an atomic type like 'refcount_t'.

It also means that we lose the overflow/underflow checks already
present in refcount_t, which are valuable to hunt down bugs
where the unsigned counter wraps around as it aids automated tools
like syzkaller to scream in such situations.

Wrap the open coded increment/decrement into helper functions and
add overflow checks to the operations.

Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/sch_generic.h | 26 ++++++++++++++++++++++++++
 net/sched/sch_drr.c       |  9 ++++-----
 net/sched/sch_hfsc.c      |  8 ++++----
 net/sched/sch_htb.c       |  8 +++-----
 net/sched/sch_qfq.c       | 10 ++++------
 5 files changed, 41 insertions(+), 20 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 15be2d96b06de..f232512505f89 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -599,6 +599,7 @@ get_default_qdisc_ops(const struct net_device *dev, int ntx)
 
 struct Qdisc_class_common {
 	u32			classid;
+	unsigned int		filter_cnt;
 	struct hlist_node	hnode;
 };
 
@@ -633,6 +634,31 @@ qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id)
 	return NULL;
 }
 
+static inline bool qdisc_class_in_use(const struct Qdisc_class_common *cl)
+{
+	return cl->filter_cnt > 0;
+}
+
+static inline void qdisc_class_get(struct Qdisc_class_common *cl)
+{
+	unsigned int res;
+
+	if (check_add_overflow(cl->filter_cnt, 1, &res))
+		WARN(1, "Qdisc class overflow");
+
+	cl->filter_cnt = res;
+}
+
+static inline void qdisc_class_put(struct Qdisc_class_common *cl)
+{
+	unsigned int res;
+
+	if (check_sub_overflow(cl->filter_cnt, 1, &res))
+		WARN(1, "Qdisc class underflow");
+
+	cl->filter_cnt = res;
+}
+
 static inline int tc_classid_to_hwtc(struct net_device *dev, u32 classid)
 {
 	u32 hwtc = TC_H_MIN(classid) - TC_H_MIN_PRIORITY;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index e35a4e90f4e6c..1b22b3b741c9a 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -17,7 +17,6 @@
 
 struct drr_class {
 	struct Qdisc_class_common	common;
-	unsigned int			filter_cnt;
 
 	struct gnet_stats_basic_sync		bstats;
 	struct gnet_stats_queue		qstats;
@@ -150,7 +149,7 @@ static int drr_delete_class(struct Qdisc *sch, unsigned long arg,
 	struct drr_sched *q = qdisc_priv(sch);
 	struct drr_class *cl = (struct drr_class *)arg;
 
-	if (cl->filter_cnt > 0)
+	if (qdisc_class_in_use(&cl->common))
 		return -EBUSY;
 
 	sch_tree_lock(sch);
@@ -187,8 +186,8 @@ static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent,
 {
 	struct drr_class *cl = drr_find_class(sch, classid);
 
-	if (cl != NULL)
-		cl->filter_cnt++;
+	if (cl)
+		qdisc_class_get(&cl->common);
 
 	return (unsigned long)cl;
 }
@@ -197,7 +196,7 @@ static void drr_unbind_tcf(struct Qdisc *sch, unsigned long arg)
 {
 	struct drr_class *cl = (struct drr_class *)arg;
 
-	cl->filter_cnt--;
+	qdisc_class_put(&cl->common);
 }
 
 static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 70b0c5873d326..896cb401fdb93 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -116,7 +116,6 @@ struct hfsc_class {
 	struct net_rate_estimator __rcu *rate_est;
 	struct tcf_proto __rcu *filter_list; /* filter list */
 	struct tcf_block *block;
-	unsigned int	filter_cnt;	/* filter count */
 	unsigned int	level;		/* class level in hierarchy */
 
 	struct hfsc_sched *sched;	/* scheduler data */
@@ -1094,7 +1093,8 @@ hfsc_delete_class(struct Qdisc *sch, unsigned long arg,
 	struct hfsc_sched *q = qdisc_priv(sch);
 	struct hfsc_class *cl = (struct hfsc_class *)arg;
 
-	if (cl->level > 0 || cl->filter_cnt > 0 || cl == &q->root)
+	if (cl->level > 0 || qdisc_class_in_use(&cl->cl_common) ||
+	    cl == &q->root)
 		return -EBUSY;
 
 	sch_tree_lock(sch);
@@ -1223,7 +1223,7 @@ hfsc_bind_tcf(struct Qdisc *sch, unsigned long parent, u32 classid)
 	if (cl != NULL) {
 		if (p != NULL && p->level <= cl->level)
 			return 0;
-		cl->filter_cnt++;
+		qdisc_class_get(&cl->cl_common);
 	}
 
 	return (unsigned long)cl;
@@ -1234,7 +1234,7 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg)
 {
 	struct hfsc_class *cl = (struct hfsc_class *)arg;
 
-	cl->filter_cnt--;
+	qdisc_class_put(&cl->cl_common);
 }
 
 static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg,
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 333800a7d4ebe..05c8291865ae8 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -102,7 +102,6 @@ struct htb_class {
 
 	struct tcf_proto __rcu	*filter_list;	/* class attached filters */
 	struct tcf_block	*block;
-	int			filter_cnt;
 
 	int			level;		/* our level (see above) */
 	unsigned int		children;
@@ -1710,7 +1709,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg,
 	 * tc subsys guarantee us that in htb_destroy it holds no class
 	 * refs so that we can remove children safely there ?
 	 */
-	if (cl->children || cl->filter_cnt)
+	if (cl->children || qdisc_class_in_use(&cl->common))
 		return -EBUSY;
 
 	if (!cl->level && htb_parent_last_child(cl))
@@ -2107,7 +2106,7 @@ static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent,
 	 * be broken by class during destroy IIUC.
 	 */
 	if (cl)
-		cl->filter_cnt++;
+		qdisc_class_get(&cl->common);
 	return (unsigned long)cl;
 }
 
@@ -2115,8 +2114,7 @@ static void htb_unbind_filter(struct Qdisc *sch, unsigned long arg)
 {
 	struct htb_class *cl = (struct htb_class *)arg;
 
-	if (cl)
-		cl->filter_cnt--;
+	qdisc_class_put(&cl->common);
 }
 
 static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg)
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index befaf74b33caa..7addc15f01b5c 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -130,8 +130,6 @@ struct qfq_aggregate;
 struct qfq_class {
 	struct Qdisc_class_common common;
 
-	unsigned int filter_cnt;
-
 	struct gnet_stats_basic_sync bstats;
 	struct gnet_stats_queue qstats;
 	struct net_rate_estimator __rcu *rate_est;
@@ -545,7 +543,7 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg,
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl = (struct qfq_class *)arg;
 
-	if (cl->filter_cnt > 0)
+	if (qdisc_class_in_use(&cl->common))
 		return -EBUSY;
 
 	sch_tree_lock(sch);
@@ -580,8 +578,8 @@ static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent,
 {
 	struct qfq_class *cl = qfq_find_class(sch, classid);
 
-	if (cl != NULL)
-		cl->filter_cnt++;
+	if (cl)
+		qdisc_class_get(&cl->common);
 
 	return (unsigned long)cl;
 }
@@ -590,7 +588,7 @@ static void qfq_unbind_tcf(struct Qdisc *sch, unsigned long arg)
 {
 	struct qfq_class *cl = (struct qfq_class *)arg;
 
-	cl->filter_cnt--;
+	qdisc_class_put(&cl->common);
 }
 
 static int qfq_graft_class(struct Qdisc *sch, unsigned long arg,
-- 
GitLab


From daf8d9181b9b4b58d3b182d1fea10dec75c5de88 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Fri, 28 Jul 2023 12:35:34 -0300
Subject: [PATCH 0685/1806] net/sched: sch_drr: warn about class in use while
 deleting

Add extack to warn that delete was rejected because
the class is still in use

Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/sch_drr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 1b22b3b741c9a..19901e77cd3b7 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -149,8 +149,10 @@ static int drr_delete_class(struct Qdisc *sch, unsigned long arg,
 	struct drr_sched *q = qdisc_priv(sch);
 	struct drr_class *cl = (struct drr_class *)arg;
 
-	if (qdisc_class_in_use(&cl->common))
+	if (qdisc_class_in_use(&cl->common)) {
+		NL_SET_ERR_MSG(extack, "DRR class is in use");
 		return -EBUSY;
+	}
 
 	sch_tree_lock(sch);
 
-- 
GitLab


From 8e4553ef3ed5ea6d58e7ab89955e2a56be4aa4f4 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Fri, 28 Jul 2023 12:35:35 -0300
Subject: [PATCH 0686/1806] net/sched: sch_hfsc: warn about class in use while
 deleting

Add extack to warn that delete was rejected because
the class is still in use

Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/sch_hfsc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 896cb401fdb93..98805303218da 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1094,8 +1094,10 @@ hfsc_delete_class(struct Qdisc *sch, unsigned long arg,
 	struct hfsc_class *cl = (struct hfsc_class *)arg;
 
 	if (cl->level > 0 || qdisc_class_in_use(&cl->cl_common) ||
-	    cl == &q->root)
+	    cl == &q->root) {
+		NL_SET_ERR_MSG(extack, "HFSC class in use");
 		return -EBUSY;
+	}
 
 	sch_tree_lock(sch);
 
-- 
GitLab


From 7118f56e04d4f89318ad222e210ba70da19a8d15 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Fri, 28 Jul 2023 12:35:36 -0300
Subject: [PATCH 0687/1806] net/sched: sch_htb: warn about class in use while
 deleting

Add extack to warn that delete was rejected because
the class is still in use

Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/sch_htb.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 05c8291865ae8..0d947414e6161 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1709,8 +1709,10 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg,
 	 * tc subsys guarantee us that in htb_destroy it holds no class
 	 * refs so that we can remove children safely there ?
 	 */
-	if (cl->children || qdisc_class_in_use(&cl->common))
+	if (cl->children || qdisc_class_in_use(&cl->common)) {
+		NL_SET_ERR_MSG(extack, "HTB class in use");
 		return -EBUSY;
+	}
 
 	if (!cl->level && htb_parent_last_child(cl))
 		last_child = 1;
-- 
GitLab


From e20e75017c5a3dbc4a3cc505d8ad57487b500bbb Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Fri, 28 Jul 2023 12:35:37 -0300
Subject: [PATCH 0688/1806] net/sched: sch_qfq: warn about class in use while
 deleting

Add extack to warn that delete was rejected because
the class is still in use

Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/sch_qfq.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 7addc15f01b5c..1a25752f1a9a6 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -543,8 +543,10 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg,
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl = (struct qfq_class *)arg;
 
-	if (qdisc_class_in_use(&cl->common))
+	if (qdisc_class_in_use(&cl->common)) {
+		NL_SET_ERR_MSG_MOD(extack, "QFQ class in use");
 		return -EBUSY;
+	}
 
 	sch_tree_lock(sch);
 
-- 
GitLab


From de9db136dcc3b60ba99f1f5034fc6ae7af45fa99 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Sun, 30 Jul 2023 09:41:09 +0200
Subject: [PATCH 0689/1806] net: dsa: tag_qca: return early if dev is not found

Currently checksum is recalculated and dsa tag stripped even if we later
don't find the dev.

To improve code, exit early if we don't find the dev and skip additional
operation on the skb since it will be freed anyway.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20230730074113.21889-1-ansuelsmth@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/dsa/tag_qca.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index e757c8de06f16..e5ff7c34e577c 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -75,10 +75,6 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev)
 		return NULL;
 	}
 
-	/* Remove QCA tag and recalculate checksum */
-	skb_pull_rcsum(skb, QCA_HDR_LEN);
-	dsa_strip_etype_header(skb, QCA_HDR_LEN);
-
 	/* Get source port information */
 	port = FIELD_GET(QCA_HDR_RECV_SOURCE_PORT, hdr);
 
@@ -86,6 +82,10 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev)
 	if (!skb->dev)
 		return NULL;
 
+	/* Remove QCA tag and recalculate checksum */
+	skb_pull_rcsum(skb, QCA_HDR_LEN);
+	dsa_strip_etype_header(skb, QCA_HDR_LEN);
+
 	return skb;
 }
 
-- 
GitLab


From 23cfc7172e5297d0bee49ac6f6f8248d1cf0820d Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Sun, 30 Jul 2023 09:41:10 +0200
Subject: [PATCH 0690/1806] net: dsa: qca8k: make learning configurable and
 keep off if standalone

Address learning should initially be turned off by the driver for port
operation in standalone mode, then the DSA core handles changes to it
via ds->ops->port_bridge_flags().

Currently this is not the case for qca8k where learning is enabled
unconditionally in qca8k_setup for every user port.

Handle ports configured in standalone mode by making the learning
configurable and not enabling it by default.

Implement .port_pre_bridge_flags and .port_bridge_flags dsa ops to
enable learning for bridge that request it and tweak
.port_stp_state_set to correctly disable learning when port is
configured in standalone mode.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20230730074113.21889-2-ansuelsmth@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/qca/qca8k-8xxx.c   |  7 +++--
 drivers/net/dsa/qca/qca8k-common.c | 48 ++++++++++++++++++++++++++++++
 drivers/net/dsa/qca/qca8k.h        |  6 ++++
 3 files changed, 58 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index 47b9f5bf98fb5..dcef16c2a075d 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -1870,9 +1870,8 @@ qca8k_setup(struct dsa_switch *ds)
 			if (ret)
 				return ret;
 
-			/* Enable ARP Auto-learning by default */
-			ret = regmap_set_bits(priv->regmap, QCA8K_PORT_LOOKUP_CTRL(i),
-					      QCA8K_PORT_LOOKUP_LEARN);
+			ret = regmap_clear_bits(priv->regmap, QCA8K_PORT_LOOKUP_CTRL(i),
+						QCA8K_PORT_LOOKUP_LEARN);
 			if (ret)
 				return ret;
 
@@ -1978,6 +1977,8 @@ static const struct dsa_switch_ops qca8k_switch_ops = {
 	.port_change_mtu	= qca8k_port_change_mtu,
 	.port_max_mtu		= qca8k_port_max_mtu,
 	.port_stp_state_set	= qca8k_port_stp_state_set,
+	.port_pre_bridge_flags	= qca8k_port_pre_bridge_flags,
+	.port_bridge_flags	= qca8k_port_bridge_flags,
 	.port_bridge_join	= qca8k_port_bridge_join,
 	.port_bridge_leave	= qca8k_port_bridge_leave,
 	.port_fast_age		= qca8k_port_fast_age,
diff --git a/drivers/net/dsa/qca/qca8k-common.c b/drivers/net/dsa/qca/qca8k-common.c
index 13b8452ce5b2b..fce04ce12cf98 100644
--- a/drivers/net/dsa/qca/qca8k-common.c
+++ b/drivers/net/dsa/qca/qca8k-common.c
@@ -565,9 +565,26 @@ int qca8k_get_mac_eee(struct dsa_switch *ds, int port,
 	return 0;
 }
 
+static int qca8k_port_configure_learning(struct dsa_switch *ds, int port,
+					 bool learning)
+{
+	struct qca8k_priv *priv = ds->priv;
+
+	if (learning)
+		return regmap_set_bits(priv->regmap,
+				       QCA8K_PORT_LOOKUP_CTRL(port),
+				       QCA8K_PORT_LOOKUP_LEARN);
+	else
+		return regmap_clear_bits(priv->regmap,
+					 QCA8K_PORT_LOOKUP_CTRL(port),
+					 QCA8K_PORT_LOOKUP_LEARN);
+}
+
 void qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 {
+	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct qca8k_priv *priv = ds->priv;
+	bool learning = false;
 	u32 stp_state;
 
 	switch (state) {
@@ -582,8 +599,11 @@ void qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 		break;
 	case BR_STATE_LEARNING:
 		stp_state = QCA8K_PORT_LOOKUP_STATE_LEARNING;
+		learning = dp->learning;
 		break;
 	case BR_STATE_FORWARDING:
+		learning = dp->learning;
+		fallthrough;
 	default:
 		stp_state = QCA8K_PORT_LOOKUP_STATE_FORWARD;
 		break;
@@ -591,6 +611,34 @@ void qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 
 	qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port),
 		  QCA8K_PORT_LOOKUP_STATE_MASK, stp_state);
+
+	qca8k_port_configure_learning(ds, port, learning);
+}
+
+int qca8k_port_pre_bridge_flags(struct dsa_switch *ds, int port,
+				struct switchdev_brport_flags flags,
+				struct netlink_ext_ack *extack)
+{
+	if (flags.mask & ~BR_LEARNING)
+		return -EINVAL;
+
+	return 0;
+}
+
+int qca8k_port_bridge_flags(struct dsa_switch *ds, int port,
+			    struct switchdev_brport_flags flags,
+			    struct netlink_ext_ack *extack)
+{
+	int ret;
+
+	if (flags.mask & BR_LEARNING) {
+		ret = qca8k_port_configure_learning(ds, port,
+						    flags.val & BR_LEARNING);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 int qca8k_port_bridge_join(struct dsa_switch *ds, int port,
diff --git a/drivers/net/dsa/qca/qca8k.h b/drivers/net/dsa/qca/qca8k.h
index c5cc8a172d65c..8f88b7db384d0 100644
--- a/drivers/net/dsa/qca/qca8k.h
+++ b/drivers/net/dsa/qca/qca8k.h
@@ -522,6 +522,12 @@ int qca8k_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e);
 
 /* Common bridge function */
 void qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state);
+int qca8k_port_pre_bridge_flags(struct dsa_switch *ds, int port,
+				struct switchdev_brport_flags flags,
+				struct netlink_ext_ack *extack);
+int qca8k_port_bridge_flags(struct dsa_switch *ds, int port,
+			    struct switchdev_brport_flags flags,
+			    struct netlink_ext_ack *extack);
 int qca8k_port_bridge_join(struct dsa_switch *ds, int port,
 			   struct dsa_bridge bridge,
 			   bool *tx_fwd_offload,
-- 
GitLab


From 18e8feae4a807994e4906d659116d249bfecd4c5 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Sun, 30 Jul 2023 09:41:11 +0200
Subject: [PATCH 0691/1806] net: dsa: qca8k: limit user ports access to the
 first CPU port on setup

In preparation for multi-CPU support, set CPU port LOOKUP MEMBER outside
the port loop and setup the LOOKUP MEMBER mask for user ports only to
the first CPU port.

This is to handle flooding condition where every CPU port is set as
target and prevent packet duplication for unknown frames from user ports.

Secondary CPU port LOOKUP MEMBER mask will be setup later when
port_change_master will be implemented.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://lore.kernel.org/r/20230730074113.21889-3-ansuelsmth@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/qca/qca8k-8xxx.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index dcef16c2a075d..acee5fe6567f9 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -1850,18 +1850,16 @@ qca8k_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
+	/* CPU port gets connected to all user ports of the switch */
+	ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(cpu_port),
+			QCA8K_PORT_LOOKUP_MEMBER, dsa_user_ports(ds));
+	if (ret)
+		return ret;
+
 	/* Setup connection between CPU port & user ports
 	 * Configure specific switch configuration for ports
 	 */
 	for (i = 0; i < QCA8K_NUM_PORTS; i++) {
-		/* CPU port gets connected to all user ports of the switch */
-		if (dsa_is_cpu_port(ds, i)) {
-			ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i),
-					QCA8K_PORT_LOOKUP_MEMBER, dsa_user_ports(ds));
-			if (ret)
-				return ret;
-		}
-
 		/* Individual user ports get connected to CPU port only */
 		if (dsa_is_user_port(ds, i)) {
 			ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i),
-- 
GitLab


From a9108b0712bf018dc69020864b21485b71b17dfc Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Sun, 30 Jul 2023 09:41:12 +0200
Subject: [PATCH 0692/1806] net: dsa: qca8k: move qca8xxx hol fixup to separate
 function

Move qca8xxx hol fixup to separate function to tidy things up and to
permit using a more efficent loop in future patch.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20230730074113.21889-4-ansuelsmth@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/qca/qca8k-8xxx.c | 78 +++++++++++++++++---------------
 1 file changed, 42 insertions(+), 36 deletions(-)

diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index acee5fe6567f9..f2cf8f77d3d19 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -1756,6 +1756,46 @@ static int qca8k_connect_tag_protocol(struct dsa_switch *ds,
 	return 0;
 }
 
+static void qca8k_setup_hol_fixup(struct qca8k_priv *priv, int port)
+{
+	u32 mask;
+
+	switch (port) {
+	/* The 2 CPU port and port 5 requires some different
+	 * priority than any other ports.
+	 */
+	case 0:
+	case 5:
+	case 6:
+		mask = QCA8K_PORT_HOL_CTRL0_EG_PRI0(0x3) |
+			QCA8K_PORT_HOL_CTRL0_EG_PRI1(0x4) |
+			QCA8K_PORT_HOL_CTRL0_EG_PRI2(0x4) |
+			QCA8K_PORT_HOL_CTRL0_EG_PRI3(0x4) |
+			QCA8K_PORT_HOL_CTRL0_EG_PRI4(0x6) |
+			QCA8K_PORT_HOL_CTRL0_EG_PRI5(0x8) |
+			QCA8K_PORT_HOL_CTRL0_EG_PORT(0x1e);
+		break;
+	default:
+		mask = QCA8K_PORT_HOL_CTRL0_EG_PRI0(0x3) |
+			QCA8K_PORT_HOL_CTRL0_EG_PRI1(0x4) |
+			QCA8K_PORT_HOL_CTRL0_EG_PRI2(0x6) |
+			QCA8K_PORT_HOL_CTRL0_EG_PRI3(0x8) |
+			QCA8K_PORT_HOL_CTRL0_EG_PORT(0x19);
+	}
+	regmap_write(priv->regmap, QCA8K_REG_PORT_HOL_CTRL0(port), mask);
+
+	mask = QCA8K_PORT_HOL_CTRL1_ING(0x6) |
+	       QCA8K_PORT_HOL_CTRL1_EG_PRI_BUF_EN |
+	       QCA8K_PORT_HOL_CTRL1_EG_PORT_BUF_EN |
+	       QCA8K_PORT_HOL_CTRL1_WRED_EN;
+	regmap_update_bits(priv->regmap, QCA8K_REG_PORT_HOL_CTRL1(port),
+			   QCA8K_PORT_HOL_CTRL1_ING_BUF_MASK |
+			   QCA8K_PORT_HOL_CTRL1_EG_PRI_BUF_EN |
+			   QCA8K_PORT_HOL_CTRL1_EG_PORT_BUF_EN |
+			   QCA8K_PORT_HOL_CTRL1_WRED_EN,
+			   mask);
+}
+
 static int
 qca8k_setup(struct dsa_switch *ds)
 {
@@ -1895,42 +1935,8 @@ qca8k_setup(struct dsa_switch *ds)
 		 * missing settings to improve switch stability under load condition.
 		 * This problem is limited to qca8337 and other qca8k switch are not affected.
 		 */
-		if (priv->switch_id == QCA8K_ID_QCA8337) {
-			switch (i) {
-			/* The 2 CPU port and port 5 requires some different
-			 * priority than any other ports.
-			 */
-			case 0:
-			case 5:
-			case 6:
-				mask = QCA8K_PORT_HOL_CTRL0_EG_PRI0(0x3) |
-					QCA8K_PORT_HOL_CTRL0_EG_PRI1(0x4) |
-					QCA8K_PORT_HOL_CTRL0_EG_PRI2(0x4) |
-					QCA8K_PORT_HOL_CTRL0_EG_PRI3(0x4) |
-					QCA8K_PORT_HOL_CTRL0_EG_PRI4(0x6) |
-					QCA8K_PORT_HOL_CTRL0_EG_PRI5(0x8) |
-					QCA8K_PORT_HOL_CTRL0_EG_PORT(0x1e);
-				break;
-			default:
-				mask = QCA8K_PORT_HOL_CTRL0_EG_PRI0(0x3) |
-					QCA8K_PORT_HOL_CTRL0_EG_PRI1(0x4) |
-					QCA8K_PORT_HOL_CTRL0_EG_PRI2(0x6) |
-					QCA8K_PORT_HOL_CTRL0_EG_PRI3(0x8) |
-					QCA8K_PORT_HOL_CTRL0_EG_PORT(0x19);
-			}
-			qca8k_write(priv, QCA8K_REG_PORT_HOL_CTRL0(i), mask);
-
-			mask = QCA8K_PORT_HOL_CTRL1_ING(0x6) |
-			QCA8K_PORT_HOL_CTRL1_EG_PRI_BUF_EN |
-			QCA8K_PORT_HOL_CTRL1_EG_PORT_BUF_EN |
-			QCA8K_PORT_HOL_CTRL1_WRED_EN;
-			qca8k_rmw(priv, QCA8K_REG_PORT_HOL_CTRL1(i),
-				  QCA8K_PORT_HOL_CTRL1_ING_BUF_MASK |
-				  QCA8K_PORT_HOL_CTRL1_EG_PRI_BUF_EN |
-				  QCA8K_PORT_HOL_CTRL1_EG_PORT_BUF_EN |
-				  QCA8K_PORT_HOL_CTRL1_WRED_EN,
-				  mask);
-		}
+		if (priv->switch_id == QCA8K_ID_QCA8337)
+			qca8k_setup_hol_fixup(priv, i);
 	}
 
 	/* Special GLOBAL_FC_THRESH value are needed for ar8327 switch */
-- 
GitLab


From 01e6f8ad8d26ced14b0cf288c42e55d03a7c5070 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Sun, 30 Jul 2023 09:41:13 +0200
Subject: [PATCH 0693/1806] net: dsa: qca8k: use dsa_for_each macro instead of
 for loop

Convert for loop to dsa_for_each macro to save some redundant write on
unconnected/unused port and tidy things up.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20230730074113.21889-5-ansuelsmth@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/qca/qca8k-8xxx.c | 107 ++++++++++++++++---------------
 1 file changed, 54 insertions(+), 53 deletions(-)

diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index f2cf8f77d3d19..de1dc22cf6831 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -1800,7 +1800,8 @@ static int
 qca8k_setup(struct dsa_switch *ds)
 {
 	struct qca8k_priv *priv = ds->priv;
-	int cpu_port, ret, i;
+	struct dsa_port *dp;
+	int cpu_port, ret;
 	u32 mask;
 
 	cpu_port = qca8k_find_cpu_port(ds);
@@ -1855,27 +1856,27 @@ qca8k_setup(struct dsa_switch *ds)
 		dev_warn(priv->dev, "mib init failed");
 
 	/* Initial setup of all ports */
-	for (i = 0; i < QCA8K_NUM_PORTS; i++) {
+	dsa_switch_for_each_port(dp, ds) {
 		/* Disable forwarding by default on all ports */
-		ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i),
+		ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(dp->index),
 				QCA8K_PORT_LOOKUP_MEMBER, 0);
 		if (ret)
 			return ret;
+	}
 
-		/* Enable QCA header mode on all cpu ports */
-		if (dsa_is_cpu_port(ds, i)) {
-			ret = qca8k_write(priv, QCA8K_REG_PORT_HDR_CTRL(i),
-					  FIELD_PREP(QCA8K_PORT_HDR_CTRL_TX_MASK, QCA8K_PORT_HDR_CTRL_ALL) |
-					  FIELD_PREP(QCA8K_PORT_HDR_CTRL_RX_MASK, QCA8K_PORT_HDR_CTRL_ALL));
-			if (ret) {
-				dev_err(priv->dev, "failed enabling QCA header mode");
-				return ret;
-			}
+	/* Disable MAC by default on all user ports */
+	dsa_switch_for_each_user_port(dp, ds)
+		qca8k_port_set_status(priv, dp->index, 0);
+
+	/* Enable QCA header mode on all cpu ports */
+	dsa_switch_for_each_cpu_port(dp, ds) {
+		ret = qca8k_write(priv, QCA8K_REG_PORT_HDR_CTRL(dp->index),
+				  FIELD_PREP(QCA8K_PORT_HDR_CTRL_TX_MASK, QCA8K_PORT_HDR_CTRL_ALL) |
+				  FIELD_PREP(QCA8K_PORT_HDR_CTRL_RX_MASK, QCA8K_PORT_HDR_CTRL_ALL));
+		if (ret) {
+			dev_err(priv->dev, "failed enabling QCA header mode on port %d", dp->index);
+			return ret;
 		}
-
-		/* Disable MAC by default on all user ports */
-		if (dsa_is_user_port(ds, i))
-			qca8k_port_set_status(priv, i, 0);
 	}
 
 	/* Forward all unknown frames to CPU port for Linux processing
@@ -1897,48 +1898,48 @@ qca8k_setup(struct dsa_switch *ds)
 		return ret;
 
 	/* Setup connection between CPU port & user ports
-	 * Configure specific switch configuration for ports
+	 * Individual user ports get connected to CPU port only
 	 */
-	for (i = 0; i < QCA8K_NUM_PORTS; i++) {
-		/* Individual user ports get connected to CPU port only */
-		if (dsa_is_user_port(ds, i)) {
-			ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i),
-					QCA8K_PORT_LOOKUP_MEMBER,
-					BIT(cpu_port));
-			if (ret)
-				return ret;
-
-			ret = regmap_clear_bits(priv->regmap, QCA8K_PORT_LOOKUP_CTRL(i),
-						QCA8K_PORT_LOOKUP_LEARN);
-			if (ret)
-				return ret;
-
-			/* For port based vlans to work we need to set the
-			 * default egress vid
-			 */
-			ret = qca8k_rmw(priv, QCA8K_EGRESS_VLAN(i),
-					QCA8K_EGREES_VLAN_PORT_MASK(i),
-					QCA8K_EGREES_VLAN_PORT(i, QCA8K_PORT_VID_DEF));
-			if (ret)
-				return ret;
-
-			ret = qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(i),
-					  QCA8K_PORT_VLAN_CVID(QCA8K_PORT_VID_DEF) |
-					  QCA8K_PORT_VLAN_SVID(QCA8K_PORT_VID_DEF));
-			if (ret)
-				return ret;
-		}
+	dsa_switch_for_each_user_port(dp, ds) {
+		u8 port = dp->index;
+
+		ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port),
+				QCA8K_PORT_LOOKUP_MEMBER,
+				BIT(cpu_port));
+		if (ret)
+			return ret;
+
+		ret = regmap_clear_bits(priv->regmap, QCA8K_PORT_LOOKUP_CTRL(port),
+					QCA8K_PORT_LOOKUP_LEARN);
+		if (ret)
+			return ret;
 
-		/* The port 5 of the qca8337 have some problem in flood condition. The
-		 * original legacy driver had some specific buffer and priority settings
-		 * for the different port suggested by the QCA switch team. Add this
-		 * missing settings to improve switch stability under load condition.
-		 * This problem is limited to qca8337 and other qca8k switch are not affected.
+		/* For port based vlans to work we need to set the
+		 * default egress vid
 		 */
-		if (priv->switch_id == QCA8K_ID_QCA8337)
-			qca8k_setup_hol_fixup(priv, i);
+		ret = qca8k_rmw(priv, QCA8K_EGRESS_VLAN(port),
+				QCA8K_EGREES_VLAN_PORT_MASK(port),
+				QCA8K_EGREES_VLAN_PORT(port, QCA8K_PORT_VID_DEF));
+		if (ret)
+			return ret;
+
+		ret = qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(port),
+				  QCA8K_PORT_VLAN_CVID(QCA8K_PORT_VID_DEF) |
+				  QCA8K_PORT_VLAN_SVID(QCA8K_PORT_VID_DEF));
+		if (ret)
+			return ret;
 	}
 
+	/* The port 5 of the qca8337 have some problem in flood condition. The
+	 * original legacy driver had some specific buffer and priority settings
+	 * for the different port suggested by the QCA switch team. Add this
+	 * missing settings to improve switch stability under load condition.
+	 * This problem is limited to qca8337 and other qca8k switch are not affected.
+	 */
+	if (priv->switch_id == QCA8K_ID_QCA8337)
+		dsa_switch_for_each_available_port(dp, ds)
+			qca8k_setup_hol_fixup(priv, dp->index);
+
 	/* Special GLOBAL_FC_THRESH value are needed for ar8327 switch */
 	if (priv->switch_id == QCA8K_ID_QCA8327) {
 		mask = QCA8K_GLOBAL_FC_GOL_XON_THRES(288) |
-- 
GitLab


From 942999c48cb382feb53c6da7679a994c97963836 Mon Sep 17 00:00:00 2001
From: Larry Finger <Larry.Finger@lwfinger.net>
Date: Mon, 24 Jul 2023 13:39:27 -0500
Subject: [PATCH 0694/1806] wifi: rtw89: Fix loading of compressed firmware

When using compressed firmware, the early firmware load feature will fail.
In most cases, the only downside is that if a device has more than one
firmware version available, only the last one listed will be loaded.
In at least two cases, there is no firmware loaded, and the device fails
initialization. See https://github.com/lwfinger/rtw89/issues/259 and
https://bugzilla.opensuse.org/show_bug.cgi?id=1212808 for examples of
the failure.

When firmware_class.dyndbg=+p" added to the kernel boot parameters, the
following is found:

finger@localhost:~/rtw89>sudo dmesg -t | grep rtw89
firmware_class: __allocate_fw_priv: fw-rtw89/rtw8852b_fw-1.bin fw_priv=00000000638862fb
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/5.14.21-150500.53-default/rtw89/rtw8852b_fw-1.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/rtw89/rtw8852b_fw-1.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/5.14.21-150500.53-default/rtw89/rtw8852b_fw-1.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/rtw89/rtw8852b_fw-1.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: Direct firmware load for rtw89/rtw8852b_fw-1.bin failed with error -2
firmware_class: __free_fw_priv: fw-rtw89/rtw8852b_fw-1.bin fw_priv=00000000638862fb data=00000000307c30c7 size=0
firmware_class: __allocate_fw_priv: fw-rtw89/rtw8852b_fw.bin fw_priv=00000000638862fb
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/5.14.21-150500.53-default/rtw89/rtw8852b_fw.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/rtw89/rtw8852b_fw.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/5.14.21-150500.53-default/rtw89/rtw8852b_fw.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/rtw89/rtw8852b_fw.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: Direct firmware load for rtw89/rtw8852b_fw.bin failed with error -2
firmware_class: __free_fw_priv: fw-rtw89/rtw8852b_fw.bin fw_priv=00000000638862fb data=00000000307c30c7 size=0
rtw89_8852be 0000:02:00.0: failed to early request firmware: -2
firmware_class: __allocate_fw_priv: fw-rtw89/rtw8852b_fw.bin fw_priv=00000000638862fb
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/5.14.21-150500.53-default/rtw89/rtw8852b_fw.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/rtw89/rtw8852b_fw.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/5.14.21-150500.53-default/rtw89/rtw8852b_fw.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/rtw89/rtw8852b_fw.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/5.14.21-150500.53-default/rtw89/rtw8852b_fw.bin.xz failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/rtw89/rtw8852b_fw.bin.xz failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/5.14.21-150500.53-default/rtw89/rtw8852b_fw.bin.xz failed for no such file or directory.
rtw89_8852be 0000:02:00.0: Loading firmware from /lib/firmware/rtw89/rtw8852b_fw.bin.xz
rtw89_8852be 0000:02:00.0: f/w decompressing rtw89/rtw8852b_fw.bin
firmware_class: fw_set_page_data: fw-rtw89/rtw8852b_fw.bin fw_priv=00000000638862fb data=000000004ed6c2f7 size=1035232
rtw89_8852be 0000:02:00.0: Firmware version 0.27.32.1, cmd version 0, type 1
rtw89_8852be 0000:02:00.0: Firmware version 0.27.32.1, cmd version 0, type 3

The key is that firmware version 0.27.32.1 is loaded.

With this patch, the following is obtained:

firmware_class: __free_fw_priv: fw-rtw89/rtw8852b_fw.bin fw_priv=000000000849addc data=00000000fd3cabe2 size=1035232
firmware_class: fw_name_devm_release: fw_name-rtw89/rtw8852b_fw.bin devm-000000002d8c3343 released
firmware_class: __allocate_fw_priv: fw-rtw89/rtw8852b_fw-1.bin fw_priv=000000009e1a6364
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/6.4.3-1-default/rtw89/rtw8852b_fw-1.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/rtw89/rtw8852b_fw-1.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/6.4.3-1-default/rtw89/rtw8852b_fw-1.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/rtw89/rtw8852b_fw-1.bin failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/6.4.3-1-default/rtw89/rtw8852b_fw-1.bin.zst failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/rtw89/rtw8852b_fw-1.bin.zst failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/6.4.3-1-default/rtw89/rtw8852b_fw-1.bin.zst failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/rtw89/rtw8852b_fw-1.bin.zst failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/6.4.3-1-default/rtw89/rtw8852b_fw-1.bin.xz failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/updates/rtw89/rtw8852b_fw-1.bin.xz failed for no such file or directory.
rtw89_8852be 0000:02:00.0: loading /lib/firmware/6.4.3-1-default/rtw89/rtw8852b_fw-1.bin.xz failed for no such file or directory.
rtw89_8852be 0000:02:00.0: Loading firmware from /lib/firmware/rtw89/rtw8852b_fw-1.bin.xz
rtw89_8852be 0000:02:00.0: f/w decompressing rtw89/rtw8852b_fw-1.bin
firmware_class: fw_set_page_data: fw-rtw89/rtw8852b_fw-1.bin fw_priv=000000009e1a6364 data=00000000fd3cabe2 size=1184992
rtw89_8852be 0000:02:00.0: Loaded FW: rtw89/rtw8852b_fw-1.bin, sha256: 8539efc75f513f4585cf0cd6e79e6507da47fce87225f2d0de391a03aefe9ac8
rtw89_8852be 0000:02:00.0: loaded firmware rtw89/rtw8852b_fw-1.bin
rtw89_8852be 0000:02:00.0: Firmware version 0.29.29.1, cmd version 0, type 5
rtw89_8852be 0000:02:00.0: Firmware version 0.29.29.1, cmd version 0, type 3

Now, version 0.29.29.1 is loaded.

Fixes: ffde7f3476a6 ("wifi: rtw89: add firmware format version to backward compatible with older drivers")
Cc: Ping-Ke Shih <pkshih@realtek.com>
Cc: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230724183927.28553-1-Larry.Finger@lwfinger.net
---
 drivers/net/wireless/realtek/rtw89/fw.c | 27 +++----------------------
 1 file changed, 3 insertions(+), 24 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 9637f5e48d842..d44628a900465 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -312,31 +312,17 @@ rtw89_early_fw_feature_recognize(struct device *device,
 				 struct rtw89_fw_info *early_fw,
 				 int *used_fw_format)
 {
-	union rtw89_compat_fw_hdr buf = {};
 	const struct firmware *firmware;
-	bool full_req = false;
 	char fw_name[64];
 	int fw_format;
 	u32 ver_code;
 	int ret;
 
-	/* If SECURITY_LOADPIN_ENFORCE is enabled, reading partial files will
-	 * be denied (-EPERM). Then, we don't get right firmware things as
-	 * expected. So, in this case, we have to request full firmware here.
-	 */
-	if (IS_ENABLED(CONFIG_SECURITY_LOADPIN_ENFORCE))
-		full_req = true;
-
 	for (fw_format = chip->fw_format_max; fw_format >= 0; fw_format--) {
 		rtw89_fw_get_filename(fw_name, sizeof(fw_name),
 				      chip->fw_basename, fw_format);
 
-		if (full_req)
-			ret = request_firmware(&firmware, fw_name, device);
-		else
-			ret = request_partial_firmware_into_buf(&firmware, fw_name,
-								device, &buf, sizeof(buf),
-								0);
+		ret = request_firmware(&firmware, fw_name, device);
 		if (!ret) {
 			dev_info(device, "loaded firmware %s\n", fw_name);
 			*used_fw_format = fw_format;
@@ -349,10 +335,7 @@ rtw89_early_fw_feature_recognize(struct device *device,
 		return NULL;
 	}
 
-	if (full_req)
-		ver_code = rtw89_compat_fw_hdr_ver_code(firmware->data);
-	else
-		ver_code = rtw89_compat_fw_hdr_ver_code(&buf);
+	ver_code = rtw89_compat_fw_hdr_ver_code(firmware->data);
 
 	if (!ver_code)
 		goto out;
@@ -360,11 +343,7 @@ rtw89_early_fw_feature_recognize(struct device *device,
 	rtw89_fw_iterate_feature_cfg(early_fw, chip, ver_code);
 
 out:
-	if (full_req)
-		return firmware;
-
-	release_firmware(firmware);
-	return NULL;
+	return firmware;
 }
 
 int rtw89_fw_recognize(struct rtw89_dev *rtwdev)
-- 
GitLab


From f698afa7ce374d41d8c2d145b11983800acd32d1 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 28 Jul 2023 15:02:43 +0800
Subject: [PATCH 0695/1806] wifi: rtw89: add chip_info::chip_gen to determine
 chip generation

The coming WiFi 7 chip is 8922AE which uses different hardware rate and
register naming rule. Adding a chip_info::chip_gen field can help to
do things by generations accordingly.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230728070252.66525-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h     | 9 +++++++++
 drivers/net/wireless/realtek/rtw89/rtw8851b.c | 1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c | 1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c | 1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c | 1 +
 5 files changed, 13 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index d2c67db97db1a..d44f428d30b45 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -109,6 +109,14 @@ enum rtw89_core_chip_id {
 	RTL8852B,
 	RTL8852C,
 	RTL8851B,
+	RTL8922A,
+};
+
+enum rtw89_chip_gen {
+	RTW89_CHIP_AX,
+	RTW89_CHIP_BE,
+
+	RTW89_CHIP_GEN_NUM,
 };
 
 enum rtw89_cv {
@@ -3177,6 +3185,7 @@ struct rtw89_antdiv_info {
 
 struct rtw89_chip_info {
 	enum rtw89_core_chip_id chip_id;
+	enum rtw89_chip_gen chip_gen;
 	const struct rtw89_chip_ops *ops;
 	const char *fw_basename;
 	u8 fw_format_max;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index c3ffcb645ebf7..456b8369fb068 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2334,6 +2334,7 @@ static const struct wiphy_wowlan_support rtw_wowlan_stub_8851b = {
 
 const struct rtw89_chip_info rtw8851b_chip_info = {
 	.chip_id		= RTL8851B,
+	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8851b_chip_ops,
 	.fw_basename		= RTW8851B_FW_BASENAME,
 	.fw_format_max		= RTW8851B_FW_FORMAT_MAX,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 6257414a3b4bd..0fc5eb777a4aa 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2071,6 +2071,7 @@ static const struct rtw89_chip_ops rtw8852a_chip_ops = {
 
 const struct rtw89_chip_info rtw8852a_chip_info = {
 	.chip_id		= RTL8852A,
+	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8852a_chip_ops,
 	.fw_basename		= RTW8852A_FW_BASENAME,
 	.fw_format_max		= RTW8852A_FW_FORMAT_MAX,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 718f993da62af..d76d74cc867ad 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -2503,6 +2503,7 @@ static const struct wiphy_wowlan_support rtw_wowlan_stub_8852b = {
 
 const struct rtw89_chip_info rtw8852b_chip_info = {
 	.chip_id		= RTL8852B,
+	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8852b_chip_ops,
 	.fw_basename		= RTW8852B_FW_BASENAME,
 	.fw_format_max		= RTW8852B_FW_FORMAT_MAX,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 9c7c9812d4f45..f269832b2bc6f 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2802,6 +2802,7 @@ static const struct rtw89_chip_ops rtw8852c_chip_ops = {
 
 const struct rtw89_chip_info rtw8852c_chip_info = {
 	.chip_id		= RTL8852C,
+	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8852c_chip_ops,
 	.fw_basename		= RTW8852C_FW_BASENAME,
 	.fw_format_max		= RTW8852C_FW_FORMAT_MAX,
-- 
GitLab


From 9e5c6c0df94ec70d74d22d7d74759f4aad452451 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 28 Jul 2023 15:02:44 +0800
Subject: [PATCH 0696/1806] wifi: rtw89: define hardware rate v1 for WiFi 7
 chips

To support EHT rate, hardware rate v1 is introduced. The CCK and OFDM rates
are persistent. HT/VHT/HE rates use different rate code from original, and
add new code for EHT rates.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230728070252.66525-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h | 188 ++++++++++++++++++++++
 1 file changed, 188 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index d44f428d30b45..81643a9b4e85f 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -395,6 +395,194 @@ enum rtw89_hw_rate {
 	RTW89_HW_RATE_HE_NSS4_MCS9	= 0x1B9,
 	RTW89_HW_RATE_HE_NSS4_MCS10	= 0x1BA,
 	RTW89_HW_RATE_HE_NSS4_MCS11	= 0x1BB,
+
+	RTW89_HW_RATE_V1_MCS0		= 0x100,
+	RTW89_HW_RATE_V1_MCS1		= 0x101,
+	RTW89_HW_RATE_V1_MCS2		= 0x102,
+	RTW89_HW_RATE_V1_MCS3		= 0x103,
+	RTW89_HW_RATE_V1_MCS4		= 0x104,
+	RTW89_HW_RATE_V1_MCS5		= 0x105,
+	RTW89_HW_RATE_V1_MCS6		= 0x106,
+	RTW89_HW_RATE_V1_MCS7		= 0x107,
+	RTW89_HW_RATE_V1_MCS8		= 0x108,
+	RTW89_HW_RATE_V1_MCS9		= 0x109,
+	RTW89_HW_RATE_V1_MCS10		= 0x10A,
+	RTW89_HW_RATE_V1_MCS11		= 0x10B,
+	RTW89_HW_RATE_V1_MCS12		= 0x10C,
+	RTW89_HW_RATE_V1_MCS13		= 0x10D,
+	RTW89_HW_RATE_V1_MCS14		= 0x10E,
+	RTW89_HW_RATE_V1_MCS15		= 0x10F,
+	RTW89_HW_RATE_V1_MCS16		= 0x110,
+	RTW89_HW_RATE_V1_MCS17		= 0x111,
+	RTW89_HW_RATE_V1_MCS18		= 0x112,
+	RTW89_HW_RATE_V1_MCS19		= 0x113,
+	RTW89_HW_RATE_V1_MCS20		= 0x114,
+	RTW89_HW_RATE_V1_MCS21		= 0x115,
+	RTW89_HW_RATE_V1_MCS22		= 0x116,
+	RTW89_HW_RATE_V1_MCS23		= 0x117,
+	RTW89_HW_RATE_V1_MCS24		= 0x118,
+	RTW89_HW_RATE_V1_MCS25		= 0x119,
+	RTW89_HW_RATE_V1_MCS26		= 0x11A,
+	RTW89_HW_RATE_V1_MCS27		= 0x11B,
+	RTW89_HW_RATE_V1_MCS28		= 0x11C,
+	RTW89_HW_RATE_V1_MCS29		= 0x11D,
+	RTW89_HW_RATE_V1_MCS30		= 0x11E,
+	RTW89_HW_RATE_V1_MCS31		= 0x11F,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS0	= 0x200,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS1	= 0x201,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS2	= 0x202,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS3	= 0x203,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS4	= 0x204,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS5	= 0x205,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS6	= 0x206,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS7	= 0x207,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS8	= 0x208,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS9	= 0x209,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS10	= 0x20A,
+	RTW89_HW_RATE_V1_VHT_NSS1_MCS11	= 0x20B,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS0	= 0x220,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS1	= 0x221,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS2	= 0x222,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS3	= 0x223,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS4	= 0x224,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS5	= 0x225,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS6	= 0x226,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS7	= 0x227,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS8	= 0x228,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS9	= 0x229,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS10	= 0x22A,
+	RTW89_HW_RATE_V1_VHT_NSS2_MCS11	= 0x22B,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS0	= 0x240,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS1	= 0x241,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS2	= 0x242,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS3	= 0x243,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS4	= 0x244,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS5	= 0x245,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS6	= 0x246,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS7	= 0x247,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS8	= 0x248,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS9	= 0x249,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS10	= 0x24A,
+	RTW89_HW_RATE_V1_VHT_NSS3_MCS11	= 0x24B,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS0	= 0x260,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS1	= 0x261,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS2	= 0x262,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS3	= 0x263,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS4	= 0x264,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS5	= 0x265,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS6	= 0x266,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS7	= 0x267,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS8	= 0x268,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS9	= 0x269,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS10	= 0x26A,
+	RTW89_HW_RATE_V1_VHT_NSS4_MCS11	= 0x26B,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS0	= 0x300,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS1	= 0x301,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS2	= 0x302,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS3	= 0x303,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS4	= 0x304,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS5	= 0x305,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS6	= 0x306,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS7	= 0x307,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS8	= 0x308,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS9	= 0x309,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS10	= 0x30A,
+	RTW89_HW_RATE_V1_HE_NSS1_MCS11	= 0x30B,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS0	= 0x320,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS1	= 0x321,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS2	= 0x322,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS3	= 0x323,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS4	= 0x324,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS5	= 0x325,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS6	= 0x326,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS7	= 0x327,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS8	= 0x328,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS9	= 0x329,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS10	= 0x32A,
+	RTW89_HW_RATE_V1_HE_NSS2_MCS11	= 0x32B,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS0	= 0x340,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS1	= 0x341,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS2	= 0x342,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS3	= 0x343,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS4	= 0x344,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS5	= 0x345,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS6	= 0x346,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS7	= 0x347,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS8	= 0x348,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS9	= 0x349,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS10	= 0x34A,
+	RTW89_HW_RATE_V1_HE_NSS3_MCS11	= 0x34B,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS0	= 0x360,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS1	= 0x361,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS2	= 0x362,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS3	= 0x363,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS4	= 0x364,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS5	= 0x365,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS6	= 0x366,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS7	= 0x367,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS8	= 0x368,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS9	= 0x369,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS10	= 0x36A,
+	RTW89_HW_RATE_V1_HE_NSS4_MCS11	= 0x36B,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS0	= 0x400,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS1	= 0x401,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS2	= 0x402,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS3	= 0x403,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS4	= 0x404,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS5	= 0x405,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS6	= 0x406,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS7	= 0x407,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS8	= 0x408,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS9	= 0x409,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS10	= 0x40A,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS11	= 0x40B,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS12	= 0x40C,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS13	= 0x40D,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS14	= 0x40E,
+	RTW89_HW_RATE_V1_EHT_NSS1_MCS15	= 0x40F,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS0	= 0x420,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS1	= 0x421,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS2	= 0x422,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS3	= 0x423,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS4	= 0x424,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS5	= 0x425,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS6	= 0x426,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS7	= 0x427,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS8	= 0x428,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS9	= 0x429,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS10	= 0x42A,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS11	= 0x42B,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS12	= 0x42C,
+	RTW89_HW_RATE_V1_EHT_NSS2_MCS13	= 0x42D,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS0	= 0x440,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS1	= 0x441,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS2	= 0x442,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS3	= 0x443,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS4	= 0x444,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS5	= 0x445,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS6	= 0x446,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS7	= 0x447,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS8	= 0x448,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS9	= 0x449,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS10	= 0x44A,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS11	= 0x44B,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS12	= 0x44C,
+	RTW89_HW_RATE_V1_EHT_NSS3_MCS13	= 0x44D,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS0	= 0x460,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS1	= 0x461,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS2	= 0x462,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS3	= 0x463,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS4	= 0x464,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS5	= 0x465,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS6	= 0x466,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS7	= 0x467,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS8	= 0x468,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS9	= 0x469,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS10	= 0x46A,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS11	= 0x46B,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS12	= 0x46C,
+	RTW89_HW_RATE_V1_EHT_NSS4_MCS13	= 0x46D,
+
 	RTW89_HW_RATE_NR,
 
 	RTW89_HW_RATE_MASK_MOD = GENMASK(8, 7),
-- 
GitLab


From 2ef14155c29b69c40350ee845a8dc051283e1ac2 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Fri, 28 Jul 2023 15:02:45 +0800
Subject: [PATCH 0697/1806] wifi: rtw89: phy: rate pattern handles HW rate by
 chip gen

Rate pattern is controlled by 'iw bitrates' to fix rate as desired, and
we extend to support v1 rate.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230728070252.66525-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/phy.c | 43 +++++++++++++++---------
 1 file changed, 28 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index fb15c852fdd48..e0d4b97a372d6 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -444,6 +444,12 @@ static bool __check_rate_pattern(struct rtw89_phy_rate_pattern *next,
 	return true;
 }
 
+#define RTW89_HW_RATE_BY_CHIP_GEN(rate) \
+	{ \
+		[RTW89_CHIP_AX] = RTW89_HW_RATE_ ## rate, \
+		[RTW89_CHIP_BE] = RTW89_HW_RATE_V1_ ## rate, \
+	}
+
 void rtw89_phy_rate_pattern_vif(struct rtw89_dev *rtwdev,
 				struct ieee80211_vif *vif,
 				const struct cfg80211_bitrate_mask *mask)
@@ -452,39 +458,46 @@ void rtw89_phy_rate_pattern_vif(struct rtw89_dev *rtwdev,
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	struct rtw89_phy_rate_pattern next_pattern = {0};
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
-	static const u16 hw_rate_he[] = {RTW89_HW_RATE_HE_NSS1_MCS0,
-					 RTW89_HW_RATE_HE_NSS2_MCS0,
-					 RTW89_HW_RATE_HE_NSS3_MCS0,
-					 RTW89_HW_RATE_HE_NSS4_MCS0};
-	static const u16 hw_rate_vht[] = {RTW89_HW_RATE_VHT_NSS1_MCS0,
-					  RTW89_HW_RATE_VHT_NSS2_MCS0,
-					  RTW89_HW_RATE_VHT_NSS3_MCS0,
-					  RTW89_HW_RATE_VHT_NSS4_MCS0};
-	static const u16 hw_rate_ht[] = {RTW89_HW_RATE_MCS0,
-					 RTW89_HW_RATE_MCS8,
-					 RTW89_HW_RATE_MCS16,
-					 RTW89_HW_RATE_MCS24};
+	static const u16 hw_rate_he[][RTW89_CHIP_GEN_NUM] = {
+		RTW89_HW_RATE_BY_CHIP_GEN(HE_NSS1_MCS0),
+		RTW89_HW_RATE_BY_CHIP_GEN(HE_NSS2_MCS0),
+		RTW89_HW_RATE_BY_CHIP_GEN(HE_NSS3_MCS0),
+		RTW89_HW_RATE_BY_CHIP_GEN(HE_NSS4_MCS0),
+	};
+	static const u16 hw_rate_vht[][RTW89_CHIP_GEN_NUM] = {
+		RTW89_HW_RATE_BY_CHIP_GEN(VHT_NSS1_MCS0),
+		RTW89_HW_RATE_BY_CHIP_GEN(VHT_NSS2_MCS0),
+		RTW89_HW_RATE_BY_CHIP_GEN(VHT_NSS3_MCS0),
+		RTW89_HW_RATE_BY_CHIP_GEN(VHT_NSS4_MCS0),
+	};
+	static const u16 hw_rate_ht[][RTW89_CHIP_GEN_NUM] = {
+		RTW89_HW_RATE_BY_CHIP_GEN(MCS0),
+		RTW89_HW_RATE_BY_CHIP_GEN(MCS8),
+		RTW89_HW_RATE_BY_CHIP_GEN(MCS16),
+		RTW89_HW_RATE_BY_CHIP_GEN(MCS24),
+	};
 	u8 band = chan->band_type;
 	enum nl80211_band nl_band = rtw89_hw_to_nl80211_band(band);
+	enum rtw89_chip_gen chip_gen = rtwdev->chip->chip_gen;
 	u8 tx_nss = rtwdev->hal.tx_nss;
 	u8 i;
 
 	for (i = 0; i < tx_nss; i++)
-		if (!__check_rate_pattern(&next_pattern, hw_rate_he[i],
+		if (!__check_rate_pattern(&next_pattern, hw_rate_he[i][chip_gen],
 					  RA_MASK_HE_RATES, RTW89_RA_MODE_HE,
 					  mask->control[nl_band].he_mcs[i],
 					  0, true))
 			goto out;
 
 	for (i = 0; i < tx_nss; i++)
-		if (!__check_rate_pattern(&next_pattern, hw_rate_vht[i],
+		if (!__check_rate_pattern(&next_pattern, hw_rate_vht[i][chip_gen],
 					  RA_MASK_VHT_RATES, RTW89_RA_MODE_VHT,
 					  mask->control[nl_band].vht_mcs[i],
 					  0, true))
 			goto out;
 
 	for (i = 0; i < tx_nss; i++)
-		if (!__check_rate_pattern(&next_pattern, hw_rate_ht[i],
+		if (!__check_rate_pattern(&next_pattern, hw_rate_ht[i][chip_gen],
 					  RA_MASK_HT_RATES, RTW89_RA_MODE_HT,
 					  mask->control[nl_band].ht_mcs[i],
 					  0, true))
-- 
GitLab


From 401b0c161b09682aa633aa7e2cf996a26a67f46c Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 28 Jul 2023 15:02:46 +0800
Subject: [PATCH 0698/1806] wifi: rtw89: use struct to set RA H2C command

RA (rate adaptive) H2C command is used to tell firmware which rates can
be used for specified MAC ID. Basically, this commit doesn't change result.
Only change to set two 32-bit instead of continual 8-byte rate masks one
by one. Originally, we only set 5-byte masks, because existing WiFi 6
2SS chips only need 5-byte masks. Setting two 32-bit masks will be more
efficient and also can support coming WiFi 7 2SS chips containing more
rates.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230728070252.66525-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c |  79 +++++-----
 drivers/net/wireless/realtek/rtw89/fw.h | 187 +++++-------------------
 2 files changed, 73 insertions(+), 193 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index d44628a900465..e77a76cf9348f 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -1882,61 +1882,60 @@ fail:
 	return ret;
 }
 
-#define H2C_RA_LEN 16
 int rtw89_fw_h2c_ra(struct rtw89_dev *rtwdev, struct rtw89_ra_info *ra, bool csi)
 {
 	struct sk_buff *skb;
-	u8 *cmd;
+	struct rtw89_h2c_ra *h2c;
+	u32 len = sizeof(*h2c);
 	int ret;
 
-	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, H2C_RA_LEN);
+	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
 	if (!skb) {
 		rtw89_err(rtwdev, "failed to alloc skb for h2c join\n");
 		return -ENOMEM;
 	}
-	skb_put(skb, H2C_RA_LEN);
-	cmd = skb->data;
+	skb_put(skb, len);
+	h2c = (struct rtw89_h2c_ra *)skb->data;
 	rtw89_debug(rtwdev, RTW89_DBG_RA,
 		    "ra cmd msk: %llx ", ra->ra_mask);
 
-	RTW89_SET_FWCMD_RA_MODE(cmd, ra->mode_ctrl);
-	RTW89_SET_FWCMD_RA_BW_CAP(cmd, ra->bw_cap);
-	RTW89_SET_FWCMD_RA_MACID(cmd, ra->macid);
-	RTW89_SET_FWCMD_RA_DCM(cmd, ra->dcm_cap);
-	RTW89_SET_FWCMD_RA_ER(cmd, ra->er_cap);
-	RTW89_SET_FWCMD_RA_INIT_RATE_LV(cmd, ra->init_rate_lv);
-	RTW89_SET_FWCMD_RA_UPD_ALL(cmd, ra->upd_all);
-	RTW89_SET_FWCMD_RA_SGI(cmd, ra->en_sgi);
-	RTW89_SET_FWCMD_RA_LDPC(cmd, ra->ldpc_cap);
-	RTW89_SET_FWCMD_RA_STBC(cmd, ra->stbc_cap);
-	RTW89_SET_FWCMD_RA_SS_NUM(cmd, ra->ss_num);
-	RTW89_SET_FWCMD_RA_GILTF(cmd, ra->giltf);
-	RTW89_SET_FWCMD_RA_UPD_BW_NSS_MASK(cmd, ra->upd_bw_nss_mask);
-	RTW89_SET_FWCMD_RA_UPD_MASK(cmd, ra->upd_mask);
-	RTW89_SET_FWCMD_RA_MASK_0(cmd, FIELD_GET(MASKBYTE0, ra->ra_mask));
-	RTW89_SET_FWCMD_RA_MASK_1(cmd, FIELD_GET(MASKBYTE1, ra->ra_mask));
-	RTW89_SET_FWCMD_RA_MASK_2(cmd, FIELD_GET(MASKBYTE2, ra->ra_mask));
-	RTW89_SET_FWCMD_RA_MASK_3(cmd, FIELD_GET(MASKBYTE3, ra->ra_mask));
-	RTW89_SET_FWCMD_RA_MASK_4(cmd, FIELD_GET(MASKBYTE4, ra->ra_mask));
-	RTW89_SET_FWCMD_RA_FIX_GILTF_EN(cmd, ra->fix_giltf_en);
-	RTW89_SET_FWCMD_RA_FIX_GILTF(cmd, ra->fix_giltf);
-
-	if (csi) {
-		RTW89_SET_FWCMD_RA_BFEE_CSI_CTL(cmd, 1);
-		RTW89_SET_FWCMD_RA_BAND_NUM(cmd, ra->band_num);
-		RTW89_SET_FWCMD_RA_CR_TBL_SEL(cmd, ra->cr_tbl_sel);
-		RTW89_SET_FWCMD_RA_FIXED_CSI_RATE_EN(cmd, ra->fixed_csi_rate_en);
-		RTW89_SET_FWCMD_RA_RA_CSI_RATE_EN(cmd, ra->ra_csi_rate_en);
-		RTW89_SET_FWCMD_RA_FIXED_CSI_MCS_SS_IDX(cmd, ra->csi_mcs_ss_idx);
-		RTW89_SET_FWCMD_RA_FIXED_CSI_MODE(cmd, ra->csi_mode);
-		RTW89_SET_FWCMD_RA_FIXED_CSI_GI_LTF(cmd, ra->csi_gi_ltf);
-		RTW89_SET_FWCMD_RA_FIXED_CSI_BW(cmd, ra->csi_bw);
-	}
-
+	h2c->w0 = le32_encode_bits(ra->mode_ctrl, RTW89_H2C_RA_W0_MODE) |
+		  le32_encode_bits(ra->bw_cap, RTW89_H2C_RA_W0_BW_CAP) |
+		  le32_encode_bits(ra->macid, RTW89_H2C_RA_W0_MACID) |
+		  le32_encode_bits(ra->dcm_cap, RTW89_H2C_RA_W0_DCM) |
+		  le32_encode_bits(ra->er_cap, RTW89_H2C_RA_W0_ER) |
+		  le32_encode_bits(ra->init_rate_lv, RTW89_H2C_RA_W0_INIT_RATE_LV) |
+		  le32_encode_bits(ra->upd_all, RTW89_H2C_RA_W0_UPD_ALL) |
+		  le32_encode_bits(ra->en_sgi, RTW89_H2C_RA_W0_SGI) |
+		  le32_encode_bits(ra->ldpc_cap, RTW89_H2C_RA_W0_LDPC) |
+		  le32_encode_bits(ra->stbc_cap, RTW89_H2C_RA_W0_STBC) |
+		  le32_encode_bits(ra->ss_num, RTW89_H2C_RA_W0_SS_NUM) |
+		  le32_encode_bits(ra->giltf, RTW89_H2C_RA_W0_GILTF) |
+		  le32_encode_bits(ra->upd_bw_nss_mask, RTW89_H2C_RA_W0_UPD_BW_NSS_MASK) |
+		  le32_encode_bits(ra->upd_mask, RTW89_H2C_RA_W0_UPD_MASK);
+	h2c->w1 = le32_encode_bits(ra->ra_mask, RTW89_H2C_RA_W1_RAMASK_LO32);
+	h2c->w2 = le32_encode_bits(ra->ra_mask >> 32, RTW89_H2C_RA_W2_RAMASK_HI32);
+	h2c->w3 = le32_encode_bits(ra->fix_giltf_en, RTW89_H2C_RA_W3_FIX_GILTF_EN) |
+		  le32_encode_bits(ra->fix_giltf, RTW89_H2C_RA_W3_FIX_GILTF);
+
+	if (!csi)
+		goto done;
+
+	h2c->w2 |= le32_encode_bits(1, RTW89_H2C_RA_W2_BFEE_CSI_CTL);
+	h2c->w3 |= le32_encode_bits(ra->band_num, RTW89_H2C_RA_W3_BAND_NUM) |
+		   le32_encode_bits(ra->cr_tbl_sel, RTW89_H2C_RA_W3_CR_TBL_SEL) |
+		   le32_encode_bits(ra->fixed_csi_rate_en, RTW89_H2C_RA_W3_FIXED_CSI_RATE_EN) |
+		   le32_encode_bits(ra->ra_csi_rate_en, RTW89_H2C_RA_W3_RA_CSI_RATE_EN) |
+		   le32_encode_bits(ra->csi_mcs_ss_idx, RTW89_H2C_RA_W3_FIXED_CSI_MCS_SS_IDX) |
+		   le32_encode_bits(ra->csi_mode, RTW89_H2C_RA_W3_FIXED_CSI_MODE) |
+		   le32_encode_bits(ra->csi_gi_ltf, RTW89_H2C_RA_W3_FIXED_CSI_GI_LTF) |
+		   le32_encode_bits(ra->csi_bw, RTW89_H2C_RA_W3_FIXED_CSI_BW);
+
+done:
 	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
 			      H2C_CAT_OUTSRC, H2C_CL_OUTSRC_RA,
 			      H2C_FUNC_OUTSRC_RA_MACIDCFG, 0, 0,
-			      H2C_RA_LEN);
+			      len);
 
 	ret = rtw89_h2c_tx(rtwdev, skb, false);
 	if (ret) {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 45f927dc212ef..5e7f528c71e7c 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -291,160 +291,41 @@ struct rtw89_pktofld_info {
 	bool cancel;
 };
 
-static inline void RTW89_SET_FWCMD_RA_IS_DIS(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, BIT(0));
-}
-
-static inline void RTW89_SET_FWCMD_RA_MODE(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, GENMASK(5, 1));
-}
-
-static inline void RTW89_SET_FWCMD_RA_BW_CAP(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, GENMASK(7, 6));
-}
-
-static inline void RTW89_SET_FWCMD_RA_MACID(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, GENMASK(15, 8));
-}
-
-static inline void RTW89_SET_FWCMD_RA_DCM(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, BIT(16));
-}
-
-static inline void RTW89_SET_FWCMD_RA_ER(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, BIT(17));
-}
-
-static inline void RTW89_SET_FWCMD_RA_INIT_RATE_LV(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, GENMASK(19, 18));
-}
-
-static inline void RTW89_SET_FWCMD_RA_UPD_ALL(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, BIT(20));
-}
-
-static inline void RTW89_SET_FWCMD_RA_SGI(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, BIT(21));
-}
-
-static inline void RTW89_SET_FWCMD_RA_LDPC(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, BIT(22));
-}
-
-static inline void RTW89_SET_FWCMD_RA_STBC(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, BIT(23));
-}
-
-static inline void RTW89_SET_FWCMD_RA_SS_NUM(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, GENMASK(26, 24));
-}
-
-static inline void RTW89_SET_FWCMD_RA_GILTF(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, GENMASK(29, 27));
-}
-
-static inline void RTW89_SET_FWCMD_RA_UPD_BW_NSS_MASK(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, BIT(30));
-}
-
-static inline void RTW89_SET_FWCMD_RA_UPD_MASK(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, BIT(31));
-}
-
-static inline void RTW89_SET_FWCMD_RA_MASK_0(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x01, val, GENMASK(7, 0));
-}
-
-static inline void RTW89_SET_FWCMD_RA_MASK_1(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x01, val, GENMASK(15, 8));
-}
-
-static inline void RTW89_SET_FWCMD_RA_MASK_2(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x01, val, GENMASK(23, 16));
-}
-
-static inline void RTW89_SET_FWCMD_RA_MASK_3(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x01, val, GENMASK(31, 24));
-}
-
-static inline void RTW89_SET_FWCMD_RA_MASK_4(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x02, val, GENMASK(7, 0));
-}
-
-static inline void RTW89_SET_FWCMD_RA_BFEE_CSI_CTL(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x02, val, BIT(31));
-}
-
-static inline void RTW89_SET_FWCMD_RA_BAND_NUM(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x03, val, GENMASK(7, 0));
-}
-
-static inline void RTW89_SET_FWCMD_RA_RA_CSI_RATE_EN(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x03, val, BIT(8));
-}
-
-static inline void RTW89_SET_FWCMD_RA_FIXED_CSI_RATE_EN(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x03, val, BIT(9));
-}
-
-static inline void RTW89_SET_FWCMD_RA_CR_TBL_SEL(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x03, val, BIT(10));
-}
-
-static inline void RTW89_SET_FWCMD_RA_FIX_GILTF_EN(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x03, val, BIT(11));
-}
-
-static inline void RTW89_SET_FWCMD_RA_FIX_GILTF(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x03, val, GENMASK(14, 12));
-}
-
-static inline void RTW89_SET_FWCMD_RA_FIXED_CSI_MCS_SS_IDX(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x03, val, GENMASK(23, 16));
-}
-
-static inline void RTW89_SET_FWCMD_RA_FIXED_CSI_MODE(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x03, val, GENMASK(25, 24));
-}
-
-static inline void RTW89_SET_FWCMD_RA_FIXED_CSI_GI_LTF(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x03, val, GENMASK(28, 26));
-}
+struct rtw89_h2c_ra {
+	__le32 w0;
+	__le32 w1;
+	__le32 w2;
+	__le32 w3;
+} __packed;
 
-static inline void RTW89_SET_FWCMD_RA_FIXED_CSI_BW(void *cmd, u32 val)
-{
-	le32p_replace_bits((__le32 *)(cmd) + 0x03, val, GENMASK(31, 29));
-}
+#define RTW89_H2C_RA_W0_IS_DIS BIT(0)
+#define RTW89_H2C_RA_W0_MODE GENMASK(5, 1)
+#define RTW89_H2C_RA_W0_BW_CAP GENMASK(7, 6)
+#define RTW89_H2C_RA_W0_MACID GENMASK(15, 8)
+#define RTW89_H2C_RA_W0_DCM BIT(16)
+#define RTW89_H2C_RA_W0_ER BIT(17)
+#define RTW89_H2C_RA_W0_INIT_RATE_LV GENMASK(19, 18)
+#define RTW89_H2C_RA_W0_UPD_ALL BIT(20)
+#define RTW89_H2C_RA_W0_SGI BIT(21)
+#define RTW89_H2C_RA_W0_LDPC BIT(22)
+#define RTW89_H2C_RA_W0_STBC BIT(23)
+#define RTW89_H2C_RA_W0_SS_NUM GENMASK(26, 24)
+#define RTW89_H2C_RA_W0_GILTF GENMASK(29, 27)
+#define RTW89_H2C_RA_W0_UPD_BW_NSS_MASK BIT(30)
+#define RTW89_H2C_RA_W0_UPD_MASK BIT(31)
+#define RTW89_H2C_RA_W1_RAMASK_LO32 GENMASK(31, 0)
+#define RTW89_H2C_RA_W2_RAMASK_HI32 GENMASK(30, 0)
+#define RTW89_H2C_RA_W2_BFEE_CSI_CTL BIT(31)
+#define RTW89_H2C_RA_W3_BAND_NUM GENMASK(7, 0)
+#define RTW89_H2C_RA_W3_RA_CSI_RATE_EN BIT(8)
+#define RTW89_H2C_RA_W3_FIXED_CSI_RATE_EN BIT(9)
+#define RTW89_H2C_RA_W3_CR_TBL_SEL BIT(10)
+#define RTW89_H2C_RA_W3_FIX_GILTF_EN BIT(11)
+#define RTW89_H2C_RA_W3_FIX_GILTF GENMASK(14, 12)
+#define RTW89_H2C_RA_W3_FIXED_CSI_MCS_SS_IDX GENMASK(23, 16)
+#define RTW89_H2C_RA_W3_FIXED_CSI_MODE GENMASK(25, 24)
+#define RTW89_H2C_RA_W3_FIXED_CSI_GI_LTF GENMASK(28, 26)
+#define RTW89_H2C_RA_W3_FIXED_CSI_BW GENMASK(31, 29)
 
 static inline void RTW89_SET_FWCMD_SEC_IDX(void *cmd, u32 val)
 {
-- 
GitLab


From c97683ff01a47d0dcd7092c5e7d39685910262a1 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 28 Jul 2023 15:02:47 +0800
Subject: [PATCH 0699/1806] wifi: rtw89: add H2C RA command V1 to support WiFi
 7 chips

H2C RA V1 command adds two words to support WiFi 7 chips, which can
possibly support up to 4SS rates. Because current chips have only 2SS
rates, leave the fields blank for now. The main changes are to set
extended bits of EHT mode and bandwidth -- add a bit for EHT mode; add a
bit to enumerate 320MHz channel bandwidth.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230728070252.66525-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |  5 +++--
 drivers/net/wireless/realtek/rtw89/fw.c   | 18 +++++++++++++++++-
 drivers/net/wireless/realtek/rtw89/fw.h   | 11 +++++++++++
 3 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 81643a9b4e85f..43e02a28e4cd4 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -2700,9 +2700,10 @@ struct rtw89_ra_info {
 	 * Bit2 : HT
 	 * Bit3 : VHT
 	 * Bit4 : HE
+	 * Bit5 : EHT
 	 */
-	u8 mode_ctrl:5;
-	u8 bw_cap:2;
+	u8 mode_ctrl:6;
+	u8 bw_cap:3; /* enum rtw89_bandwidth */
 	u8 macid;
 	u8 dcm_cap:1;
 	u8 er_cap:1;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index e77a76cf9348f..cf22e50bced85 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -1884,11 +1884,19 @@ fail:
 
 int rtw89_fw_h2c_ra(struct rtw89_dev *rtwdev, struct rtw89_ra_info *ra, bool csi)
 {
-	struct sk_buff *skb;
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	struct rtw89_h2c_ra_v1 *h2c_v1;
 	struct rtw89_h2c_ra *h2c;
 	u32 len = sizeof(*h2c);
+	bool format_v1 = false;
+	struct sk_buff *skb;
 	int ret;
 
+	if (chip->chip_gen == RTW89_CHIP_BE) {
+		len = sizeof(*h2c_v1);
+		format_v1 = true;
+	}
+
 	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
 	if (!skb) {
 		rtw89_err(rtwdev, "failed to alloc skb for h2c join\n");
@@ -1918,6 +1926,14 @@ int rtw89_fw_h2c_ra(struct rtw89_dev *rtwdev, struct rtw89_ra_info *ra, bool csi
 	h2c->w3 = le32_encode_bits(ra->fix_giltf_en, RTW89_H2C_RA_W3_FIX_GILTF_EN) |
 		  le32_encode_bits(ra->fix_giltf, RTW89_H2C_RA_W3_FIX_GILTF);
 
+	if (!format_v1)
+		goto csi;
+
+	h2c_v1 = (struct rtw89_h2c_ra_v1 *)h2c;
+	h2c_v1->w4 = le32_encode_bits(ra->mode_ctrl, RTW89_H2C_RA_V1_W4_MODE_EHT) |
+		     le32_encode_bits(ra->bw_cap, RTW89_H2C_RA_V1_W4_BW_EHT);
+
+csi:
 	if (!csi)
 		goto done;
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 5e7f528c71e7c..831dbe6023935 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -327,6 +327,17 @@ struct rtw89_h2c_ra {
 #define RTW89_H2C_RA_W3_FIXED_CSI_GI_LTF GENMASK(28, 26)
 #define RTW89_H2C_RA_W3_FIXED_CSI_BW GENMASK(31, 29)
 
+struct rtw89_h2c_ra_v1 {
+	struct rtw89_h2c_ra v0;
+	__le32 w4;
+	__le32 w5;
+} __packed;
+
+#define RTW89_H2C_RA_V1_W4_MODE_EHT GENMASK(6, 0)
+#define RTW89_H2C_RA_V1_W4_BW_EHT GENMASK(10, 8)
+#define RTW89_H2C_RA_V1_W4_RAMASK_UHL16 GENMASK(31, 16)
+#define RTW89_H2C_RA_V1_W5_RAMASK_UHH16 GENMASK(15, 0)
+
 static inline void RTW89_SET_FWCMD_SEC_IDX(void *cmd, u32 val)
 {
 	le32p_replace_bits((__le32 *)(cmd) + 0x00, val, GENMASK(7, 0));
-- 
GitLab


From c342ac2195161611b51927eefab18879155b110e Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 28 Jul 2023 15:02:48 +0800
Subject: [PATCH 0700/1806] wifi: rtw89: use struct to access firmware C2H
 event header

Firmware C2H events contain two-word header which can indicate category,
class, function and length of received events. Use struct to access them,
and doesn't change logic at all.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230728070252.66525-7-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c |  9 +++++----
 drivers/net/wireless/realtek/rtw89/fw.h | 17 +++++++++--------
 2 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index cf22e50bced85..f8616c178de7e 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -2809,12 +2809,13 @@ void rtw89_fw_free_all_early_h2c(struct rtw89_dev *rtwdev)
 
 static void rtw89_fw_c2h_parse_attr(struct sk_buff *c2h)
 {
+	const struct rtw89_c2h_hdr *hdr = (const struct rtw89_c2h_hdr *)c2h->data;
 	struct rtw89_fw_c2h_attr *attr = RTW89_SKB_C2H_CB(c2h);
 
-	attr->category = RTW89_GET_C2H_CATEGORY(c2h->data);
-	attr->class = RTW89_GET_C2H_CLASS(c2h->data);
-	attr->func = RTW89_GET_C2H_FUNC(c2h->data);
-	attr->len = RTW89_GET_C2H_LEN(c2h->data);
+	attr->category = le32_get_bits(hdr->w0, RTW89_C2H_HDR_W0_CATEGORY);
+	attr->class = le32_get_bits(hdr->w0, RTW89_C2H_HDR_W0_CLASS);
+	attr->func = le32_get_bits(hdr->w0, RTW89_C2H_HDR_W0_FUNC);
+	attr->len = le32_get_bits(hdr->w1, RTW89_C2H_HDR_W1_LEN);
 }
 
 static bool rtw89_fw_c2h_chk_atomic(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 831dbe6023935..becd8acce9c1d 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -3101,14 +3101,15 @@ inline void RTW89_SET_FWCMD_MCC_SET_DURATION_DURATION_Y(void *cmd, u32 val)
 
 #define RTW89_C2H_HEADER_LEN 8
 
-#define RTW89_GET_C2H_CATEGORY(c2h) \
-	le32_get_bits(*((const __le32 *)c2h), GENMASK(1, 0))
-#define RTW89_GET_C2H_CLASS(c2h) \
-	le32_get_bits(*((const __le32 *)c2h), GENMASK(7, 2))
-#define RTW89_GET_C2H_FUNC(c2h) \
-	le32_get_bits(*((const __le32 *)c2h), GENMASK(15, 8))
-#define RTW89_GET_C2H_LEN(c2h) \
-	le32_get_bits(*((const __le32 *)(c2h) + 1), GENMASK(13, 0))
+struct rtw89_c2h_hdr {
+	__le32 w0;
+	__le32 w1;
+} __packed;
+
+#define RTW89_C2H_HDR_W0_CATEGORY GENMASK(1, 0)
+#define RTW89_C2H_HDR_W0_CLASS GENMASK(7, 2)
+#define RTW89_C2H_HDR_W0_FUNC GENMASK(15, 8)
+#define RTW89_C2H_HDR_W1_LEN GENMASK(13, 0)
 
 struct rtw89_fw_c2h_attr {
 	u8 category;
-- 
GitLab


From 57cafeb18f06d3f4eaea9145d3396fdb8c699acc Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 28 Jul 2023 15:02:49 +0800
Subject: [PATCH 0701/1806] wifi: rtw89: use struct to access RA report

RA (rate adaptive), a mechanism to select proper rate, is implemented in
firmware, and this report is used to tell driver TX rate it is currently
using. Use struct to access this report, and doesn't change logic at all.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230728070252.66525-8-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.h  | 24 ++++++++++++------------
 drivers/net/wireless/realtek/rtw89/phy.c | 13 +++++++------
 2 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index becd8acce9c1d..586f9707a5ed7 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -3160,18 +3160,18 @@ struct rtw89_c2h_mac_bcnfltr_rpt {
 #define RTW89_C2H_MAC_BCNFLTR_RPT_W2_EVENT GENMASK(11, 10)
 #define RTW89_C2H_MAC_BCNFLTR_RPT_W2_MA GENMASK(23, 16)
 
-#define RTW89_GET_PHY_C2H_RA_RPT_MACID(c2h) \
-	le32_get_bits(*((const __le32 *)(c2h) + 2), GENMASK(15, 0))
-#define RTW89_GET_PHY_C2H_RA_RPT_RETRY_RATIO(c2h) \
-	le32_get_bits(*((const __le32 *)(c2h) + 2), GENMASK(23, 16))
-#define RTW89_GET_PHY_C2H_RA_RPT_MCSNSS(c2h) \
-	le32_get_bits(*((const __le32 *)(c2h) + 3), GENMASK(6, 0))
-#define RTW89_GET_PHY_C2H_RA_RPT_MD_SEL(c2h) \
-	le32_get_bits(*((const __le32 *)(c2h) + 3), GENMASK(9, 8))
-#define RTW89_GET_PHY_C2H_RA_RPT_GILTF(c2h) \
-	le32_get_bits(*((const __le32 *)(c2h) + 3), GENMASK(12, 10))
-#define RTW89_GET_PHY_C2H_RA_RPT_BW(c2h) \
-	le32_get_bits(*((const __le32 *)(c2h) + 3), GENMASK(14, 13))
+struct rtw89_c2h_ra_rpt {
+	struct rtw89_c2h_hdr hdr;
+	__le32 w2;
+	__le32 w3;
+} __packed;
+
+#define RTW89_C2H_RA_RPT_W2_MACID GENMASK(15, 0)
+#define RTW89_C2H_RA_RPT_W2_RETRY_RATIO GENMASK(23, 16)
+#define RTW89_C2H_RA_RPT_W3_MCSNSS GENMASK(6, 0)
+#define RTW89_C2H_RA_RPT_W3_MD_SEL GENMASK(9, 8)
+#define RTW89_C2H_RA_RPT_W3_GILTF GENMASK(12, 10)
+#define RTW89_C2H_RA_RPT_W3_BW GENMASK(14, 13)
 
 /* VHT, HE, HT-old: [6:4]: NSS, [3:0]: MCS
  * HT-new: [6:5]: NA, [4:0]: MCS
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index e0d4b97a372d6..19a0c7ce0451c 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -2244,21 +2244,22 @@ static void rtw89_phy_c2h_ra_rpt_iter(void *data, struct ieee80211_sta *sta)
 	struct rtw89_phy_iter_ra_data *ra_data = (struct rtw89_phy_iter_ra_data *)data;
 	struct rtw89_dev *rtwdev = ra_data->rtwdev;
 	struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv;
+	const struct rtw89_c2h_ra_rpt *c2h =
+		(const struct rtw89_c2h_ra_rpt *)ra_data->c2h->data;
 	struct rtw89_ra_report *ra_report = &rtwsta->ra_report;
-	struct sk_buff *c2h = ra_data->c2h;
 	u8 mode, rate, bw, giltf, mac_id;
 	u16 legacy_bitrate;
 	bool valid;
 	u8 mcs = 0;
 
-	mac_id = RTW89_GET_PHY_C2H_RA_RPT_MACID(c2h->data);
+	mac_id = le32_get_bits(c2h->w2, RTW89_C2H_RA_RPT_W2_MACID);
 	if (mac_id != rtwsta->mac_id)
 		return;
 
-	rate = RTW89_GET_PHY_C2H_RA_RPT_MCSNSS(c2h->data);
-	bw = RTW89_GET_PHY_C2H_RA_RPT_BW(c2h->data);
-	giltf = RTW89_GET_PHY_C2H_RA_RPT_GILTF(c2h->data);
-	mode = RTW89_GET_PHY_C2H_RA_RPT_MD_SEL(c2h->data);
+	rate = le32_get_bits(c2h->w3, RTW89_C2H_RA_RPT_W3_MCSNSS);
+	bw = le32_get_bits(c2h->w3, RTW89_C2H_RA_RPT_W3_BW);
+	giltf = le32_get_bits(c2h->w3, RTW89_C2H_RA_RPT_W3_GILTF);
+	mode = le32_get_bits(c2h->w3, RTW89_C2H_RA_RPT_W3_MD_SEL);
 
 	if (mode == RTW89_RA_RPT_MODE_LEGACY) {
 		valid = rtw89_ra_report_to_bitrate(rtwdev, rate, &legacy_bitrate);
-- 
GitLab


From 5c152231c341f0ea00b3ebd64cf6718b10106dab Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 28 Jul 2023 15:02:50 +0800
Subject: [PATCH 0702/1806] wifi: rtw89: add C2H RA event V1 to support WiFi 7
 chips

WiFi 7 chips have more rate mode (EHT), higher MCS and more bandwidth, so
define and use reserved bits to carry these information in C2H events.
Also, the SS/MCS encoded bits of VHT and HE are changed, so define V1 masks
for them.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230728070252.66525-9-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |  2 ++
 drivers/net/wireless/realtek/rtw89/fw.h   | 14 +++++++--
 drivers/net/wireless/realtek/rtw89/phy.c  | 35 +++++++++++++++++++----
 3 files changed, 42 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 43e02a28e4cd4..24c1097467885 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -587,6 +587,8 @@ enum rtw89_hw_rate {
 
 	RTW89_HW_RATE_MASK_MOD = GENMASK(8, 7),
 	RTW89_HW_RATE_MASK_VAL = GENMASK(6, 0),
+	RTW89_HW_RATE_V1_MASK_MOD = GENMASK(10, 8),
+	RTW89_HW_RATE_V1_MASK_VAL = GENMASK(7, 0),
 };
 
 /* 2G channels,
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 586f9707a5ed7..49ecf070de712 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -3168,16 +3168,24 @@ struct rtw89_c2h_ra_rpt {
 
 #define RTW89_C2H_RA_RPT_W2_MACID GENMASK(15, 0)
 #define RTW89_C2H_RA_RPT_W2_RETRY_RATIO GENMASK(23, 16)
+#define RTW89_C2H_RA_RPT_W2_MCSNSS_B7 BIT(31)
 #define RTW89_C2H_RA_RPT_W3_MCSNSS GENMASK(6, 0)
 #define RTW89_C2H_RA_RPT_W3_MD_SEL GENMASK(9, 8)
 #define RTW89_C2H_RA_RPT_W3_GILTF GENMASK(12, 10)
 #define RTW89_C2H_RA_RPT_W3_BW GENMASK(14, 13)
-
-/* VHT, HE, HT-old: [6:4]: NSS, [3:0]: MCS
- * HT-new: [6:5]: NA, [4:0]: MCS
+#define RTW89_C2H_RA_RPT_W3_MD_SEL_B2 BIT(15)
+#define RTW89_C2H_RA_RPT_W3_BW_B2 BIT(16)
+
+/* For WiFi 6 chips:
+ *   VHT, HE, HT-old: [6:4]: NSS, [3:0]: MCS
+ *   HT-new: [6:5]: NA, [4:0]: MCS
+ * For WiFi 7 chips (V1):
+ *   HT, VHT, HE, EHT: [7:5]: NSS, [4:0]: MCS
  */
 #define RTW89_RA_RATE_MASK_NSS GENMASK(6, 4)
 #define RTW89_RA_RATE_MASK_MCS GENMASK(3, 0)
+#define RTW89_RA_RATE_MASK_NSS_V1 GENMASK(7, 5)
+#define RTW89_RA_RATE_MASK_MCS_V1 GENMASK(4, 0)
 #define RTW89_RA_RATE_MASK_HT_MCS GENMASK(4, 0)
 #define RTW89_MK_HT_RATE(nss, mcs) (FIELD_PREP(GENMASK(4, 3), nss) | \
 				    FIELD_PREP(GENMASK(2, 0), mcs))
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 19a0c7ce0451c..1940f4457677c 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -2247,10 +2247,13 @@ static void rtw89_phy_c2h_ra_rpt_iter(void *data, struct ieee80211_sta *sta)
 	const struct rtw89_c2h_ra_rpt *c2h =
 		(const struct rtw89_c2h_ra_rpt *)ra_data->c2h->data;
 	struct rtw89_ra_report *ra_report = &rtwsta->ra_report;
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	bool format_v1 = chip->chip_gen == RTW89_CHIP_BE;
 	u8 mode, rate, bw, giltf, mac_id;
 	u16 legacy_bitrate;
 	bool valid;
 	u8 mcs = 0;
+	u8 t;
 
 	mac_id = le32_get_bits(c2h->w2, RTW89_C2H_RA_RPT_W2_MACID);
 	if (mac_id != rtwsta->mac_id)
@@ -2261,6 +2264,15 @@ static void rtw89_phy_c2h_ra_rpt_iter(void *data, struct ieee80211_sta *sta)
 	giltf = le32_get_bits(c2h->w3, RTW89_C2H_RA_RPT_W3_GILTF);
 	mode = le32_get_bits(c2h->w3, RTW89_C2H_RA_RPT_W3_MD_SEL);
 
+	if (format_v1) {
+		t = le32_get_bits(c2h->w2, RTW89_C2H_RA_RPT_W2_MCSNSS_B7);
+		rate |= u8_encode_bits(t, BIT(7));
+		t = le32_get_bits(c2h->w3, RTW89_C2H_RA_RPT_W3_BW_B2);
+		bw |= u8_encode_bits(t, BIT(2));
+		t = le32_get_bits(c2h->w3, RTW89_C2H_RA_RPT_W3_MD_SEL_B2);
+		mode |= u8_encode_bits(t, BIT(2));
+	}
+
 	if (mode == RTW89_RA_RPT_MODE_LEGACY) {
 		valid = rtw89_ra_report_to_bitrate(rtwdev, rate, &legacy_bitrate);
 		if (!valid)
@@ -2287,16 +2299,24 @@ static void rtw89_phy_c2h_ra_rpt_iter(void *data, struct ieee80211_sta *sta)
 		break;
 	case RTW89_RA_RPT_MODE_VHT:
 		ra_report->txrate.flags |= RATE_INFO_FLAGS_VHT_MCS;
-		ra_report->txrate.mcs = FIELD_GET(RTW89_RA_RATE_MASK_MCS, rate);
-		ra_report->txrate.nss = FIELD_GET(RTW89_RA_RATE_MASK_NSS, rate) + 1;
+		ra_report->txrate.mcs = format_v1 ?
+			u8_get_bits(rate, RTW89_RA_RATE_MASK_MCS_V1) :
+			u8_get_bits(rate, RTW89_RA_RATE_MASK_MCS);
+		ra_report->txrate.nss = format_v1 ?
+			u8_get_bits(rate, RTW89_RA_RATE_MASK_NSS_V1) + 1 :
+			u8_get_bits(rate, RTW89_RA_RATE_MASK_NSS) + 1;
 		if (giltf)
 			ra_report->txrate.flags |= RATE_INFO_FLAGS_SHORT_GI;
 		mcs = ra_report->txrate.mcs;
 		break;
 	case RTW89_RA_RPT_MODE_HE:
 		ra_report->txrate.flags |= RATE_INFO_FLAGS_HE_MCS;
-		ra_report->txrate.mcs = FIELD_GET(RTW89_RA_RATE_MASK_MCS, rate);
-		ra_report->txrate.nss = FIELD_GET(RTW89_RA_RATE_MASK_NSS, rate) + 1;
+		ra_report->txrate.mcs = format_v1 ?
+			u8_get_bits(rate, RTW89_RA_RATE_MASK_MCS_V1) :
+			u8_get_bits(rate, RTW89_RA_RATE_MASK_MCS);
+		ra_report->txrate.nss  = format_v1 ?
+			u8_get_bits(rate, RTW89_RA_RATE_MASK_NSS_V1) + 1 :
+			u8_get_bits(rate, RTW89_RA_RATE_MASK_NSS) + 1;
 		if (giltf == RTW89_GILTF_2XHE08 || giltf == RTW89_GILTF_1XHE08)
 			ra_report->txrate.he_gi = NL80211_RATE_INFO_HE_GI_0_8;
 		else if (giltf == RTW89_GILTF_2XHE16 || giltf == RTW89_GILTF_1XHE16)
@@ -2309,8 +2329,11 @@ static void rtw89_phy_c2h_ra_rpt_iter(void *data, struct ieee80211_sta *sta)
 
 	ra_report->txrate.bw = rtw89_hw_to_rate_info_bw(bw);
 	ra_report->bit_rate = cfg80211_calculate_bitrate(&ra_report->txrate);
-	ra_report->hw_rate = FIELD_PREP(RTW89_HW_RATE_MASK_MOD, mode) |
-			     FIELD_PREP(RTW89_HW_RATE_MASK_VAL, rate);
+	ra_report->hw_rate = format_v1 ?
+			     u16_encode_bits(mode, RTW89_HW_RATE_V1_MASK_MOD) |
+			     u16_encode_bits(rate, RTW89_HW_RATE_V1_MASK_VAL) :
+			     u16_encode_bits(mode, RTW89_HW_RATE_MASK_MOD) |
+			     u16_encode_bits(rate, RTW89_HW_RATE_MASK_VAL);
 	ra_report->might_fallback_legacy = mcs <= 2;
 	sta->deflink.agg.max_rc_amsdu_len = get_max_amsdu_len(rtwdev, ra_report);
 	rtwsta->max_agg_wait = sta->deflink.agg.max_rc_amsdu_len / 1500 - 1;
-- 
GitLab


From ae775faa875029a9f3a246ed0a4a97b0473171a7 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 28 Jul 2023 15:02:51 +0800
Subject: [PATCH 0703/1806] wifi: rtw89: add to display hardware rates v1
 histogram in debugfs

The upcoming WiFi 7 chips support EHT rates, and hardware rate codes are
changed too, so modify to adapt the changes. (EHT counters are still zeros
in below example)

RX count:
   Legacy: [0, 0, 0, 0]
     OFDM: [0, 0, 0, 0, 0, 0, 0, 0]
     HT 0: [0, 0, 0, 0, 0, 0, 0, 0]
     HT 1: [0, 0, 0, 0, 0, 0, 0, 0]
  VHT 1SS: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0][0, 0]
  VHT 2SS: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0][0, 0]
   HE 1SS: [0, 0, 42, 0, 43, 90, 75, 0, 26, 20, 260, 7]
   HE 2SS: [0, 96, 232, 84, 125, 184, 52, 0, 0, 0, 0, 0]
  EHT 1SS: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0][0, 0]
  EHT 2SS: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230728070252.66525-10-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h  |  1 +
 drivers/net/wireless/realtek/rtw89/debug.c | 35 +++++++++++++++-------
 2 files changed, 25 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 24c1097467885..f3f7abddd3c0b 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -584,6 +584,7 @@ enum rtw89_hw_rate {
 	RTW89_HW_RATE_V1_EHT_NSS4_MCS13	= 0x46D,
 
 	RTW89_HW_RATE_NR,
+	RTW89_HW_RATE_INVAL,
 
 	RTW89_HW_RATE_MASK_MOD = GENMASK(8, 7),
 	RTW89_HW_RATE_MASK_VAL = GENMASK(6, 0),
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index ce5a9ac081457..f67af8aa2358f 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -3325,20 +3325,26 @@ rtw89_debug_append_rx_rate(struct seq_file *m, struct rtw89_pkt_stat *pkt_stat,
 			   pkt_stat->rx_rate_cnt[first_rate + i]);
 }
 
+#define FIRST_RATE_SAME(rate) {RTW89_HW_RATE_ ## rate, RTW89_HW_RATE_ ## rate}
+#define FIRST_RATE_ENUM(rate) {RTW89_HW_RATE_ ## rate, RTW89_HW_RATE_V1_ ## rate}
+#define FIRST_RATE_GEV1(rate) {RTW89_HW_RATE_INVAL, RTW89_HW_RATE_V1_ ## rate}
+
 static const struct rtw89_rx_rate_cnt_info {
-	enum rtw89_hw_rate first_rate;
+	enum rtw89_hw_rate first_rate[RTW89_CHIP_GEN_NUM];
 	int len;
 	int ext;
 	const char *rate_mode;
 } rtw89_rx_rate_cnt_infos[] = {
-	{RTW89_HW_RATE_CCK1, 4, 0, "Legacy:"},
-	{RTW89_HW_RATE_OFDM6, 8, 0, "OFDM:"},
-	{RTW89_HW_RATE_MCS0, 8, 0, "HT 0:"},
-	{RTW89_HW_RATE_MCS8, 8, 0, "HT 1:"},
-	{RTW89_HW_RATE_VHT_NSS1_MCS0, 10, 2, "VHT 1SS:"},
-	{RTW89_HW_RATE_VHT_NSS2_MCS0, 10, 2, "VHT 2SS:"},
-	{RTW89_HW_RATE_HE_NSS1_MCS0, 12, 0, "HE 1SS:"},
-	{RTW89_HW_RATE_HE_NSS2_MCS0, 12, 0, "HE 2ss:"},
+	{FIRST_RATE_SAME(CCK1), 4, 0, "Legacy:"},
+	{FIRST_RATE_SAME(OFDM6), 8, 0, "OFDM:"},
+	{FIRST_RATE_ENUM(MCS0), 8, 0, "HT 0:"},
+	{FIRST_RATE_ENUM(MCS8), 8, 0, "HT 1:"},
+	{FIRST_RATE_ENUM(VHT_NSS1_MCS0), 10, 2, "VHT 1SS:"},
+	{FIRST_RATE_ENUM(VHT_NSS2_MCS0), 10, 2, "VHT 2SS:"},
+	{FIRST_RATE_ENUM(HE_NSS1_MCS0), 12, 0, "HE 1SS:"},
+	{FIRST_RATE_ENUM(HE_NSS2_MCS0), 12, 0, "HE 2SS:"},
+	{FIRST_RATE_GEV1(EHT_NSS1_MCS0), 14, 2, "EHT 1SS:"},
+	{FIRST_RATE_GEV1(EHT_NSS2_MCS0), 14, 0, "EHT 2SS:"},
 };
 
 static int rtw89_debug_priv_phy_info_get(struct seq_file *m, void *v)
@@ -3347,7 +3353,9 @@ static int rtw89_debug_priv_phy_info_get(struct seq_file *m, void *v)
 	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	struct rtw89_traffic_stats *stats = &rtwdev->stats;
 	struct rtw89_pkt_stat *pkt_stat = &rtwdev->phystat.last_pkt_stat;
+	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_rx_rate_cnt_info *info;
+	enum rtw89_hw_rate first_rate;
 	int i;
 
 	seq_printf(m, "TP TX: %u [%u] Mbps (lv: %d), RX: %u [%u] Mbps (lv: %d)\n",
@@ -3359,15 +3367,20 @@ static int rtw89_debug_priv_phy_info_get(struct seq_file *m, void *v)
 		   stats->rx_avg_len);
 
 	seq_puts(m, "RX count:\n");
+
 	for (i = 0; i < ARRAY_SIZE(rtw89_rx_rate_cnt_infos); i++) {
 		info = &rtw89_rx_rate_cnt_infos[i];
+		first_rate = info->first_rate[chip->chip_gen];
+		if (first_rate >= RTW89_HW_RATE_NR)
+			continue;
+
 		seq_printf(m, "%10s [", info->rate_mode);
 		rtw89_debug_append_rx_rate(m, pkt_stat,
-					   info->first_rate, info->len);
+					   first_rate, info->len);
 		if (info->ext) {
 			seq_puts(m, "][");
 			rtw89_debug_append_rx_rate(m, pkt_stat,
-						   info->first_rate + info->len, info->ext);
+						   first_rate + info->len, info->ext);
 		}
 		seq_puts(m, "]\n");
 	}
-- 
GitLab


From 023d2f14abf806ae1231e567e8bded78e83abdc0 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 28 Jul 2023 15:02:52 +0800
Subject: [PATCH 0704/1806] wifi: rtw89: get data rate mode/NSS/MCS v1 from RX
 descriptor

The data rate from RX descriptor also uses hardware rate v1 for WiFi 7
chips. The rate code contains three parts -- mode, NSS and MCS. For
CCK/OFDM/HT rates, NSS/MCS parts are the same as before. VHT/HE/EHT rates
are changed and listed as below:

     mode    NSS    MCS
V0   [8:7]   [6:4]  [3:0]
V1   [10:8]  [7:5]  [4:0]

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230728070252.66525-11-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c | 24 ++++++------
 drivers/net/wireless/realtek/rtw89/phy.c  |  2 +-
 drivers/net/wireless/realtek/rtw89/txrx.h | 47 ++++++++++++++++++++---
 3 files changed, 55 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 69b181fa29667..ec244849e5014 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -1456,16 +1456,16 @@ static bool rtw89_core_rx_ppdu_match(struct rtw89_dev *rtwdev,
 	bool ret;
 
 	data_rate = desc_info->data_rate;
-	data_rate_mode = GET_DATA_RATE_MODE(data_rate);
+	data_rate_mode = rtw89_get_data_rate_mode(rtwdev, data_rate);
 	if (data_rate_mode == DATA_RATE_MODE_NON_HT) {
-		rate_idx = GET_DATA_RATE_NOT_HT_IDX(data_rate);
+		rate_idx = rtw89_get_data_not_ht_idx(rtwdev, data_rate);
 		/* rate_idx is still hardware value here */
 	} else if (data_rate_mode == DATA_RATE_MODE_HT) {
-		rate_idx = GET_DATA_RATE_HT_IDX(data_rate);
+		rate_idx = rtw89_get_data_ht_mcs(rtwdev, data_rate);
 	} else if (data_rate_mode == DATA_RATE_MODE_VHT) {
-		rate_idx = GET_DATA_RATE_VHT_HE_IDX(data_rate);
+		rate_idx = rtw89_get_data_mcs(rtwdev, data_rate);
 	} else if (data_rate_mode == DATA_RATE_MODE_HE) {
-		rate_idx = GET_DATA_RATE_VHT_HE_IDX(data_rate);
+		rate_idx = rtw89_get_data_mcs(rtwdev, data_rate);
 	} else {
 		rtw89_warn(rtwdev, "invalid RX rate mode %d\n", data_rate_mode);
 	}
@@ -1929,26 +1929,26 @@ static void rtw89_core_update_rx_status(struct rtw89_dev *rtwdev,
 	rx_status->bw = rtw89_hw_to_rate_info_bw(desc_info->bw);
 
 	data_rate = desc_info->data_rate;
-	data_rate_mode = GET_DATA_RATE_MODE(data_rate);
+	data_rate_mode = rtw89_get_data_rate_mode(rtwdev, data_rate);
 	if (data_rate_mode == DATA_RATE_MODE_NON_HT) {
 		rx_status->encoding = RX_ENC_LEGACY;
-		rx_status->rate_idx = GET_DATA_RATE_NOT_HT_IDX(data_rate);
+		rx_status->rate_idx = rtw89_get_data_not_ht_idx(rtwdev, data_rate);
 		/* convert rate_idx after we get the correct band */
 	} else if (data_rate_mode == DATA_RATE_MODE_HT) {
 		rx_status->encoding = RX_ENC_HT;
-		rx_status->rate_idx = GET_DATA_RATE_HT_IDX(data_rate);
+		rx_status->rate_idx = rtw89_get_data_ht_mcs(rtwdev, data_rate);
 		if (desc_info->gi_ltf)
 			rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 	} else if (data_rate_mode == DATA_RATE_MODE_VHT) {
 		rx_status->encoding = RX_ENC_VHT;
-		rx_status->rate_idx = GET_DATA_RATE_VHT_HE_IDX(data_rate);
-		rx_status->nss = GET_DATA_RATE_NSS(data_rate) + 1;
+		rx_status->rate_idx = rtw89_get_data_mcs(rtwdev, data_rate);
+		rx_status->nss = rtw89_get_data_nss(rtwdev, data_rate) + 1;
 		if (desc_info->gi_ltf)
 			rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 	} else if (data_rate_mode == DATA_RATE_MODE_HE) {
 		rx_status->encoding = RX_ENC_HE;
-		rx_status->rate_idx = GET_DATA_RATE_VHT_HE_IDX(data_rate);
-		rx_status->nss = GET_DATA_RATE_NSS(data_rate) + 1;
+		rx_status->rate_idx = rtw89_get_data_mcs(rtwdev, data_rate);
+		rx_status->nss = rtw89_get_data_nss(rtwdev, data_rate) + 1;
 	} else {
 		rtw89_warn(rtwdev, "invalid RX rate mode %d\n", data_rate_mode);
 	}
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 1940f4457677c..abe0f5179a382 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -3014,7 +3014,7 @@ static void rtw89_phy_antdiv_sts_instance_add(struct rtw89_dev *rtwdev,
 					      struct rtw89_rx_phy_ppdu *phy_ppdu,
 					      struct rtw89_antdiv_stats *stats)
 {
-	if (GET_DATA_RATE_MODE(phy_ppdu->rate) == DATA_RATE_MODE_NON_HT) {
+	if (rtw89_get_data_rate_mode(rtwdev, phy_ppdu->rate) == DATA_RATE_MODE_NON_HT) {
 		if (phy_ppdu->rate < RTW89_HW_RATE_OFDM6) {
 			ewma_rssi_add(&stats->cck_rssi_avg, phy_ppdu->rssi_avg);
 			stats->pkt_cnt_cck++;
diff --git a/drivers/net/wireless/realtek/rtw89/txrx.h b/drivers/net/wireless/realtek/rtw89/txrx.h
index ec96da36eacc6..02cff0f7d86b9 100644
--- a/drivers/net/wireless/realtek/rtw89/txrx.h
+++ b/drivers/net/wireless/realtek/rtw89/txrx.h
@@ -8,19 +8,56 @@
 #include "debug.h"
 
 #define DATA_RATE_MODE_CTRL_MASK	GENMASK(8, 7)
+#define DATA_RATE_MODE_CTRL_MASK_V1	GENMASK(10, 8)
 #define DATA_RATE_NOT_HT_IDX_MASK	GENMASK(3, 0)
 #define DATA_RATE_MODE_NON_HT		0x0
 #define DATA_RATE_HT_IDX_MASK		GENMASK(4, 0)
+#define DATA_RATE_HT_IDX_MASK_V1	GENMASK(4, 0)
 #define DATA_RATE_MODE_HT		0x1
 #define DATA_RATE_VHT_HE_NSS_MASK	GENMASK(6, 4)
 #define DATA_RATE_VHT_HE_IDX_MASK	GENMASK(3, 0)
+#define DATA_RATE_NSS_MASK_V1		GENMASK(7, 5)
+#define DATA_RATE_MCS_MASK_V1		GENMASK(4, 0)
 #define DATA_RATE_MODE_VHT		0x2
 #define DATA_RATE_MODE_HE		0x3
-#define GET_DATA_RATE_MODE(r)		FIELD_GET(DATA_RATE_MODE_CTRL_MASK, r)
-#define GET_DATA_RATE_NOT_HT_IDX(r)	FIELD_GET(DATA_RATE_NOT_HT_IDX_MASK, r)
-#define GET_DATA_RATE_HT_IDX(r)		FIELD_GET(DATA_RATE_HT_IDX_MASK, r)
-#define GET_DATA_RATE_VHT_HE_IDX(r)	FIELD_GET(DATA_RATE_VHT_HE_IDX_MASK, r)
-#define GET_DATA_RATE_NSS(r)		FIELD_GET(DATA_RATE_VHT_HE_NSS_MASK, r)
+#define DATA_RATE_MODE_EHT		0x4
+
+static inline u8 rtw89_get_data_rate_mode(struct rtw89_dev *rtwdev, u16 hw_rate)
+{
+	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE)
+		return u16_get_bits(hw_rate, DATA_RATE_MODE_CTRL_MASK_V1);
+
+	return u16_get_bits(hw_rate, DATA_RATE_MODE_CTRL_MASK);
+}
+
+static inline u8 rtw89_get_data_not_ht_idx(struct rtw89_dev *rtwdev, u16 hw_rate)
+{
+	return u16_get_bits(hw_rate, DATA_RATE_NOT_HT_IDX_MASK);
+}
+
+static inline u8 rtw89_get_data_ht_mcs(struct rtw89_dev *rtwdev, u16 hw_rate)
+{
+	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE)
+		return u16_get_bits(hw_rate, DATA_RATE_HT_IDX_MASK_V1);
+
+	return u16_get_bits(hw_rate, DATA_RATE_HT_IDX_MASK);
+}
+
+static inline u8 rtw89_get_data_mcs(struct rtw89_dev *rtwdev, u16 hw_rate)
+{
+	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE)
+		return u16_get_bits(hw_rate, DATA_RATE_MCS_MASK_V1);
+
+	return u16_get_bits(hw_rate, DATA_RATE_VHT_HE_IDX_MASK);
+}
+
+static inline u8 rtw89_get_data_nss(struct rtw89_dev *rtwdev, u16 hw_rate)
+{
+	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE)
+		return u16_get_bits(hw_rate, DATA_RATE_NSS_MASK_V1);
+
+	return u16_get_bits(hw_rate, DATA_RATE_VHT_HE_NSS_MASK);
+}
 
 /* TX WD BODY DWORD 0 */
 #define RTW89_TXWD_BODY0_WP_OFFSET GENMASK(31, 24)
-- 
GitLab


From 646462f860f12a2e24e6b2ed856cf6645c02397d Mon Sep 17 00:00:00 2001
From: Prasurjya Rohan Saikia <prasurjya.rohansaikia@microchip.com>
Date: Mon, 10 Jul 2023 09:44:03 +0000
Subject: [PATCH 0705/1806] wifi: wilc1000: remove use of has_thrpt_enh3 flag

The 'enhance throughput flow' algorithm is used by default. So older
sections of the code are removed so as to always use this new algorithm.

Signed-off-by: Prasurjya Rohan Saikia <prasurjya.rohansaikia@microchip.com>
Acked-by: Ajay Kathat <ajay.kathat@microchip.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230710094401.235222-1-prasurjya.rohansaikia@microchip.com
---
 .../net/wireless/microchip/wilc1000/sdio.c    | 103 ++----------------
 1 file changed, 10 insertions(+), 93 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index a05bda7b9a3ba..87948ba69a222 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -28,7 +28,6 @@ struct wilc_sdio {
 	bool irq_gpio;
 	u32 block_size;
 	bool isinit;
-	int has_thrpt_enh3;
 	u8 *cmd53_buf;
 };
 
@@ -722,21 +721,12 @@ static int wilc_sdio_init(struct wilc *wilc, bool resume)
 	 *      make sure can read back chip id correctly
 	 **/
 	if (!resume) {
-		int rev;
-
 		ret = wilc_sdio_read_reg(wilc, WILC_CHIPID, &chipid);
 		if (ret) {
 			dev_err(&func->dev, "Fail cmd read chip id...\n");
 			return ret;
 		}
 		dev_err(&func->dev, "chipid (%08x)\n", chipid);
-		rev = FIELD_GET(WILC_CHIP_REV_FIELD, chipid);
-		if (rev > FIELD_GET(WILC_CHIP_REV_FIELD, WILC_1000_BASE_ID_2A))
-			sdio_priv->has_thrpt_enh3 = 1;
-		else
-			sdio_priv->has_thrpt_enh3 = 0;
-		dev_info(&func->dev, "has_thrpt_enh3 = %d...\n",
-			 sdio_priv->has_thrpt_enh3);
 	}
 
 	sdio_priv->isinit = true;
@@ -809,102 +799,29 @@ static int wilc_sdio_clear_int_ext(struct wilc *wilc, u32 val)
 	struct sdio_func *func = dev_to_sdio_func(wilc->dev);
 	struct wilc_sdio *sdio_priv = wilc->bus_data;
 	int ret;
-	int vmm_ctl;
-
-	if (sdio_priv->has_thrpt_enh3) {
-		u32 reg = 0;
-
-		if (sdio_priv->irq_gpio)
-			reg = val & (BIT(MAX_NUM_INT) - 1);
-
-		/* select VMM table 0 */
-		if (val & SEL_VMM_TBL0)
-			reg |= BIT(5);
-		/* select VMM table 1 */
-		if (val & SEL_VMM_TBL1)
-			reg |= BIT(6);
-		/* enable VMM */
-		if (val & EN_VMM)
-			reg |= BIT(7);
-		if (reg) {
-			struct sdio_cmd52 cmd;
-
-			cmd.read_write = 1;
-			cmd.function = 0;
-			cmd.raw = 0;
-			cmd.address = WILC_SDIO_IRQ_CLEAR_FLAG_REG;
-			cmd.data = reg;
-
-			ret = wilc_sdio_cmd52(wilc, &cmd);
-			if (ret) {
-				dev_err(&func->dev,
-					"Failed cmd52, set (%02x) data (%d) ...\n",
-					cmd.address, __LINE__);
-				return ret;
-			}
-		}
-		return 0;
-	}
-	if (sdio_priv->irq_gpio) {
-		/* has_thrpt_enh2 uses register 0xf8 to clear interrupts. */
-		/*
-		 * Cannot clear multiple interrupts.
-		 * Must clear each interrupt individually.
-		 */
-		u32 flags;
-		int i;
-
-		flags = val & (BIT(MAX_NUM_INT) - 1);
-		for (i = 0; i < NUM_INT_EXT && flags; i++) {
-			if (flags & BIT(i)) {
-				struct sdio_cmd52 cmd;
-
-				cmd.read_write = 1;
-				cmd.function = 0;
-				cmd.raw = 0;
-				cmd.address = WILC_SDIO_IRQ_CLEAR_FLAG_REG;
-				cmd.data = BIT(i);
-
-				ret = wilc_sdio_cmd52(wilc, &cmd);
-				if (ret) {
-					dev_err(&func->dev,
-						"Failed cmd52, set (%02x) data (%d) ...\n",
-						cmd.address, __LINE__);
-					return ret;
-				}
-				flags &= ~BIT(i);
-			}
-		}
+	u32 reg = 0;
 
-		for (i = NUM_INT_EXT; i < MAX_NUM_INT && flags; i++) {
-			if (flags & BIT(i)) {
-				dev_err(&func->dev,
-					"Unexpected interrupt cleared %d...\n",
-					i);
-				flags &= ~BIT(i);
-			}
-		}
-	}
+	if (sdio_priv->irq_gpio)
+		reg = val & (BIT(MAX_NUM_INT) - 1);
 
-	vmm_ctl = 0;
 	/* select VMM table 0 */
 	if (val & SEL_VMM_TBL0)
-		vmm_ctl |= BIT(0);
+		reg |= BIT(5);
 	/* select VMM table 1 */
 	if (val & SEL_VMM_TBL1)
-		vmm_ctl |= BIT(1);
+		reg |= BIT(6);
 	/* enable VMM */
 	if (val & EN_VMM)
-		vmm_ctl |= BIT(2);
-
-	if (vmm_ctl) {
+		reg |= BIT(7);
+	if (reg) {
 		struct sdio_cmd52 cmd;
 
 		cmd.read_write = 1;
 		cmd.function = 0;
 		cmd.raw = 0;
-		cmd.address = WILC_SDIO_VMM_TBL_CTRL_REG;
-		cmd.data = vmm_ctl;
+		cmd.address = WILC_SDIO_IRQ_CLEAR_FLAG_REG;
+		cmd.data = reg;
+
 		ret = wilc_sdio_cmd52(wilc, &cmd);
 		if (ret) {
 			dev_err(&func->dev,
-- 
GitLab


From 11958528161731c58e105b501ed60b83a91ea941 Mon Sep 17 00:00:00 2001
From: Polaris Pi <pinkperfect2021@gmail.com>
Date: Sun, 23 Jul 2023 07:07:41 +0000
Subject: [PATCH 0706/1806] wifi: mwifiex: Fix OOB and integer underflow when
 rx packets

Make sure mwifiex_process_mgmt_packet,
mwifiex_process_sta_rx_packet and mwifiex_process_uap_rx_packet,
mwifiex_uap_queue_bridged_pkt and mwifiex_process_rx_packet
not out-of-bounds access the skb->data buffer.

Fixes: 2dbaf751b1de ("mwifiex: report received management frames to cfg80211")
Signed-off-by: Polaris Pi <pinkperfect2021@gmail.com>
Reviewed-by: Matthew Wang <matthewmwang@chromium.org>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230723070741.1544662-1-pinkperfect2021@gmail.com
---
 drivers/net/wireless/marvell/mwifiex/sta_rx.c | 11 ++++++++++-
 .../net/wireless/marvell/mwifiex/uap_txrx.c   | 19 +++++++++++++++++++
 drivers/net/wireless/marvell/mwifiex/util.c   | 10 +++++++---
 3 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/sta_rx.c b/drivers/net/wireless/marvell/mwifiex/sta_rx.c
index 13659b02ba882..f2899d53a43f9 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_rx.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_rx.c
@@ -86,6 +86,14 @@ int mwifiex_process_rx_packet(struct mwifiex_private *priv,
 	rx_pkt_len = le16_to_cpu(local_rx_pd->rx_pkt_length);
 	rx_pkt_hdr = (void *)local_rx_pd + rx_pkt_off;
 
+	if (sizeof(*rx_pkt_hdr) + rx_pkt_off > skb->len) {
+		mwifiex_dbg(priv->adapter, ERROR,
+			    "wrong rx packet offset: len=%d, rx_pkt_off=%d\n",
+			    skb->len, rx_pkt_off);
+		priv->stats.rx_dropped++;
+		dev_kfree_skb_any(skb);
+	}
+
 	if ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header,
 		     sizeof(bridge_tunnel_header))) ||
 	    (!memcmp(&rx_pkt_hdr->rfc1042_hdr, rfc1042_header,
@@ -194,7 +202,8 @@ int mwifiex_process_sta_rx_packet(struct mwifiex_private *priv,
 
 	rx_pkt_hdr = (void *)local_rx_pd + rx_pkt_offset;
 
-	if ((rx_pkt_offset + rx_pkt_length) > (u16) skb->len) {
+	if ((rx_pkt_offset + rx_pkt_length) > skb->len ||
+	    sizeof(rx_pkt_hdr->eth803_hdr) + rx_pkt_offset > skb->len) {
 		mwifiex_dbg(adapter, ERROR,
 			    "wrong rx packet: len=%d, rx_pkt_offset=%d, rx_pkt_length=%d\n",
 			    skb->len, rx_pkt_offset, rx_pkt_length);
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
index e495f7eaea033..04ff051f5d186 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
@@ -103,6 +103,15 @@ static void mwifiex_uap_queue_bridged_pkt(struct mwifiex_private *priv,
 		return;
 	}
 
+	if (sizeof(*rx_pkt_hdr) +
+	    le16_to_cpu(uap_rx_pd->rx_pkt_offset) > skb->len) {
+		mwifiex_dbg(adapter, ERROR,
+			    "wrong rx packet offset: len=%d,rx_pkt_offset=%d\n",
+			    skb->len, le16_to_cpu(uap_rx_pd->rx_pkt_offset));
+		priv->stats.rx_dropped++;
+		dev_kfree_skb_any(skb);
+	}
+
 	if ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header,
 		     sizeof(bridge_tunnel_header))) ||
 	    (!memcmp(&rx_pkt_hdr->rfc1042_hdr, rfc1042_header,
@@ -367,6 +376,16 @@ int mwifiex_process_uap_rx_packet(struct mwifiex_private *priv,
 	rx_pkt_type = le16_to_cpu(uap_rx_pd->rx_pkt_type);
 	rx_pkt_hdr = (void *)uap_rx_pd + le16_to_cpu(uap_rx_pd->rx_pkt_offset);
 
+	if (le16_to_cpu(uap_rx_pd->rx_pkt_offset) +
+	    sizeof(rx_pkt_hdr->eth803_hdr) > skb->len) {
+		mwifiex_dbg(adapter, ERROR,
+			    "wrong rx packet for struct ethhdr: len=%d, offset=%d\n",
+			    skb->len, le16_to_cpu(uap_rx_pd->rx_pkt_offset));
+		priv->stats.rx_dropped++;
+		dev_kfree_skb_any(skb);
+		return 0;
+	}
+
 	ether_addr_copy(ta, rx_pkt_hdr->eth803_hdr.h_source);
 
 	if ((le16_to_cpu(uap_rx_pd->rx_pkt_offset) +
diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c
index 94c2d219835da..745b1d925b217 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.c
+++ b/drivers/net/wireless/marvell/mwifiex/util.c
@@ -393,11 +393,15 @@ mwifiex_process_mgmt_packet(struct mwifiex_private *priv,
 	}
 
 	rx_pd = (struct rxpd *)skb->data;
+	pkt_len = le16_to_cpu(rx_pd->rx_pkt_length);
+	if (pkt_len < sizeof(struct ieee80211_hdr) + sizeof(pkt_len)) {
+		mwifiex_dbg(priv->adapter, ERROR, "invalid rx_pkt_length");
+		return -1;
+	}
 
 	skb_pull(skb, le16_to_cpu(rx_pd->rx_pkt_offset));
 	skb_pull(skb, sizeof(pkt_len));
-
-	pkt_len = le16_to_cpu(rx_pd->rx_pkt_length);
+	pkt_len -= sizeof(pkt_len);
 
 	ieee_hdr = (void *)skb->data;
 	if (ieee80211_is_mgmt(ieee_hdr->frame_control)) {
@@ -410,7 +414,7 @@ mwifiex_process_mgmt_packet(struct mwifiex_private *priv,
 		skb->data + sizeof(struct ieee80211_hdr),
 		pkt_len - sizeof(struct ieee80211_hdr));
 
-	pkt_len -= ETH_ALEN + sizeof(pkt_len);
+	pkt_len -= ETH_ALEN;
 	rx_pd->rx_pkt_length = cpu_to_le16(pkt_len);
 
 	cfg80211_rx_mgmt(&priv->wdev, priv->roc_cfg.chan.center_freq,
-- 
GitLab


From 6fd879f9783bdbaea758681b9d4e2e7c306293fd Mon Sep 17 00:00:00 2001
From: Amisha Patel <amisha.patel@microchip.com>
Date: Mon, 24 Jul 2023 16:40:00 +0000
Subject: [PATCH 0707/1806] wifi: wilc1000: add SPI commands retry mechanism

In some situations like, chip wake-up with powersave enabled, SPI
commands are failing temporarily. Reissuing commands after reset helps
to overcome the failure. So, add the retry limit and reset command
sequence API for read/write SPI commands.

Signed-off-by: Amisha Patel <amisha.patel@microchip.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230724163955.4583-1-amisha.patel@microchip.com
---
 drivers/net/wireless/microchip/wilc1000/spi.c | 148 ++++++++++++------
 1 file changed, 103 insertions(+), 45 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c
index b0fc5e68feeca..77b4cdff73c37 100644
--- a/drivers/net/wireless/microchip/wilc1000/spi.c
+++ b/drivers/net/wireless/microchip/wilc1000/spi.c
@@ -74,6 +74,7 @@ static int wilc_spi_reset(struct wilc *wilc);
 #define CMD_SINGLE_READ				0xca
 #define CMD_RESET				0xcf
 
+#define SPI_RETRY_MAX_LIMIT			10
 #define SPI_ENABLE_VMM_RETRY_LIMIT		2
 
 /* SPI response fields (section 11.1.2 in ATWILC1000 User Guide): */
@@ -830,59 +831,91 @@ static int wilc_spi_special_cmd(struct wilc *wilc, u8 cmd)
 	return 0;
 }
 
+static void wilc_spi_reset_cmd_sequence(struct wilc *wl, u8 attempt, u32 addr)
+{
+	struct spi_device *spi = to_spi_device(wl->dev);
+	struct wilc_spi *spi_priv = wl->bus_data;
+
+	if (!spi_priv->probing_crc)
+		dev_err(&spi->dev, "Reset and retry %d %x\n", attempt, addr);
+
+	usleep_range(1000, 1100);
+	wilc_spi_reset(wl);
+	usleep_range(1000, 1100);
+}
+
 static int wilc_spi_read_reg(struct wilc *wilc, u32 addr, u32 *data)
 {
 	struct spi_device *spi = to_spi_device(wilc->dev);
 	int result;
 	u8 cmd = CMD_SINGLE_READ;
 	u8 clockless = 0;
+	u8 i;
 
-	if (addr < WILC_SPI_CLOCKLESS_ADDR_LIMIT) {
+	if (addr <= WILC_SPI_CLOCKLESS_ADDR_LIMIT) {
 		/* Clockless register */
 		cmd = CMD_INTERNAL_READ;
 		clockless = 1;
 	}
 
-	result = wilc_spi_single_read(wilc, cmd, addr, data, clockless);
-	if (result) {
+	for (i = 0; i < SPI_RETRY_MAX_LIMIT; i++) {
+		result = wilc_spi_single_read(wilc, cmd, addr, data, clockless);
+		if (!result) {
+			le32_to_cpus(data);
+			return 0;
+		}
+
+		/* retry is not applicable for clockless registers */
+		if (clockless)
+			break;
+
 		dev_err(&spi->dev, "Failed cmd, read reg (%08x)...\n", addr);
-		return result;
+		wilc_spi_reset_cmd_sequence(wilc, i, addr);
 	}
 
-	le32_to_cpus(data);
-
-	return 0;
+	return result;
 }
 
 static int wilc_spi_read(struct wilc *wilc, u32 addr, u8 *buf, u32 size)
 {
 	struct spi_device *spi = to_spi_device(wilc->dev);
 	int result;
+	u8 i;
 
 	if (size <= 4)
 		return -EINVAL;
 
-	result = wilc_spi_dma_rw(wilc, CMD_DMA_EXT_READ, addr, buf, size);
-	if (result) {
+	for (i = 0; i < SPI_RETRY_MAX_LIMIT; i++) {
+		result = wilc_spi_dma_rw(wilc, CMD_DMA_EXT_READ, addr,
+					 buf, size);
+		if (!result)
+			return 0;
+
 		dev_err(&spi->dev, "Failed cmd, read block (%08x)...\n", addr);
-		return result;
+
+		wilc_spi_reset_cmd_sequence(wilc, i, addr);
 	}
 
-	return 0;
+	return result;
 }
 
 static int spi_internal_write(struct wilc *wilc, u32 adr, u32 dat)
 {
 	struct spi_device *spi = to_spi_device(wilc->dev);
 	int result;
+	u8 i;
 
-	result = wilc_spi_write_cmd(wilc, CMD_INTERNAL_WRITE, adr, dat, 0);
-	if (result) {
+	for (i = 0; i < SPI_RETRY_MAX_LIMIT; i++) {
+		result = wilc_spi_write_cmd(wilc, CMD_INTERNAL_WRITE, adr,
+					    dat, 0);
+		if (!result)
+			return 0;
 		dev_err(&spi->dev, "Failed internal write cmd...\n");
-		return result;
+
+		wilc_spi_reset_cmd_sequence(wilc, i, adr);
 	}
 
-	return 0;
+	return result;
 }
 
 static int spi_internal_read(struct wilc *wilc, u32 adr, u32 *data)
@@ -890,17 +923,22 @@ static int spi_internal_read(struct wilc *wilc, u32 adr, u32 *data)
 	struct spi_device *spi = to_spi_device(wilc->dev);
 	struct wilc_spi *spi_priv = wilc->bus_data;
 	int result;
+	u8 i;
 
-	result = wilc_spi_single_read(wilc, CMD_INTERNAL_READ, adr, data, 0);
-	if (result) {
+	for (i = 0; i < SPI_RETRY_MAX_LIMIT; i++) {
+		result = wilc_spi_single_read(wilc, CMD_INTERNAL_READ, adr,
+					      data, 0);
+		if (!result) {
+			le32_to_cpus(data);
+			return 0;
+		}
 		if (!spi_priv->probing_crc)
 			dev_err(&spi->dev, "Failed internal read cmd...\n");
-		return result;
-	}
 
-	le32_to_cpus(data);
+		wilc_spi_reset_cmd_sequence(wilc, i, adr);
+	}
 
-	return 0;
+	return result;
 }
 
 /********************************************
@@ -915,20 +953,27 @@ static int wilc_spi_write_reg(struct wilc *wilc, u32 addr, u32 data)
 	int result;
 	u8 cmd = CMD_SINGLE_WRITE;
 	u8 clockless = 0;
+	u8 i;
 
-	if (addr < WILC_SPI_CLOCKLESS_ADDR_LIMIT) {
+	if (addr <= WILC_SPI_CLOCKLESS_ADDR_LIMIT) {
 		/* Clockless register */
 		cmd = CMD_INTERNAL_WRITE;
 		clockless = 1;
 	}
 
-	result = wilc_spi_write_cmd(wilc, cmd, addr, data, clockless);
-	if (result) {
+	for (i = 0; i < SPI_RETRY_MAX_LIMIT; i++) {
+		result = wilc_spi_write_cmd(wilc, cmd, addr, data, clockless);
+		if (!result)
+			return 0;
+
 		dev_err(&spi->dev, "Failed cmd, write reg (%08x)...\n", addr);
-		return result;
-	}
 
-	return 0;
+		if (clockless)
+			break;
+
+		wilc_spi_reset_cmd_sequence(wilc, i, addr);
+	}
+	return result;
 }
 
 static int spi_data_rsp(struct wilc *wilc, u8 cmd)
@@ -981,6 +1026,7 @@ static int wilc_spi_write(struct wilc *wilc, u32 addr, u8 *buf, u32 size)
 {
 	struct spi_device *spi = to_spi_device(wilc->dev);
 	int result;
+	u8 i;
 
 	/*
 	 * has to be greated than 4
@@ -988,26 +1034,38 @@ static int wilc_spi_write(struct wilc *wilc, u32 addr, u8 *buf, u32 size)
 	if (size <= 4)
 		return -EINVAL;
 
-	result = wilc_spi_dma_rw(wilc, CMD_DMA_EXT_WRITE, addr, NULL, size);
-	if (result) {
-		dev_err(&spi->dev,
-			"Failed cmd, write block (%08x)...\n", addr);
-		return result;
-	}
+	for (i = 0; i < SPI_RETRY_MAX_LIMIT; i++) {
+		result = wilc_spi_dma_rw(wilc, CMD_DMA_EXT_WRITE, addr,
+					 NULL, size);
+		if (result) {
+			dev_err(&spi->dev,
+				"Failed cmd, write block (%08x)...\n", addr);
+			wilc_spi_reset_cmd_sequence(wilc, i, addr);
+			continue;
+		}
 
-	/*
-	 * Data
-	 */
-	result = spi_data_write(wilc, buf, size);
-	if (result) {
-		dev_err(&spi->dev, "Failed block data write...\n");
-		return result;
-	}
+		/*
+		 * Data
+		 */
+		result = spi_data_write(wilc, buf, size);
+		if (result) {
+			dev_err(&spi->dev, "Failed block data write...\n");
+			wilc_spi_reset_cmd_sequence(wilc, i, addr);
+			continue;
+		}
 
-	/*
-	 * Data response
-	 */
-	return spi_data_rsp(wilc, CMD_DMA_EXT_WRITE);
+		/*
+		 * Data response
+		 */
+		result = spi_data_rsp(wilc, CMD_DMA_EXT_WRITE);
+		if (result) {
+			dev_err(&spi->dev, "Failed block data rsp...\n");
+			wilc_spi_reset_cmd_sequence(wilc, i, addr);
+			continue;
+		}
+		break;
+	}
+	return result;
 }
 
 /********************************************
-- 
GitLab


From e7899a90cebec045ce88505d496d8453174044c2 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 24 Jul 2023 15:19:13 -0600
Subject: [PATCH 0708/1806] wifi: drivers: Explicitly include correct DT
 includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230724211914.805876-1-robh@kernel.org
---
 drivers/net/wireless/ath/ath10k/ahb.c            | 2 +-
 drivers/net/wireless/ath/ath11k/qmi.c            | 1 -
 drivers/net/wireless/ath/wcn36xx/main.c          | 3 +--
 drivers/net/wireless/intersil/orinoco/airport.c  | 2 +-
 drivers/net/wireless/mediatek/mt76/mt7915/init.c | 1 +
 drivers/net/wireless/mediatek/mt76/mt7915/soc.c  | 1 -
 drivers/net/wireless/mediatek/mt76/mt7996/init.c | 1 +
 drivers/net/wireless/silabs/wfx/bus_sdio.c       | 2 +-
 8 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/ahb.c b/drivers/net/wireless/ath/ath10k/ahb.c
index 4a006fb4d424b..76efea2f11389 100644
--- a/drivers/net/wireless/ath/ath10k/ahb.c
+++ b/drivers/net/wireless/ath/ath10k/ahb.c
@@ -5,7 +5,7 @@
  */
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/reset.h>
 #include "core.h"
diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index d4eaf7d2ba841..98efa0f299cac 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -13,7 +13,6 @@
 #include <linux/of_address.h>
 #include <linux/ioport.h>
 #include <linux/firmware.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 
 #define SLEEP_CLOCK_SELECT_INTERNAL_BIT	0x02
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 8dbd115a393c7..2bd1163177f08 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -19,9 +19,8 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/platform_device.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
 #include <linux/rpmsg.h>
 #include <linux/soc/qcom/smem_state.h>
 #include <linux/soc/qcom/wcnss_ctrl.h>
diff --git a/drivers/net/wireless/intersil/orinoco/airport.c b/drivers/net/wireless/intersil/orinoco/airport.c
index a890bfa0d5cc4..45ac00fdafa58 100644
--- a/drivers/net/wireless/intersil/orinoco/airport.c
+++ b/drivers/net/wireless/intersil/orinoco/airport.c
@@ -18,7 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <linux/of_device.h>
+#include <linux/mod_devicetable.h>
 #include <asm/pmac_feature.h>
 
 #include "orinoco.h"
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index ac2049f49bb38..aec47de35f53e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -4,6 +4,7 @@
 #include <linux/etherdevice.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
+#include <linux/of.h>
 #include <linux/thermal.h>
 #include "mt7915.h"
 #include "mac.h"
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/soc.c b/drivers/net/wireless/mediatek/mt76/mt7915/soc.c
index 32c137066e7f7..701a27ffa4c2e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/soc.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/soc.c
@@ -6,7 +6,6 @@
 #include <linux/platform_device.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/of_gpio.h>
 #include <linux/iopoll.h>
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
index f1b48cdda58f3..5c980534f6114 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/etherdevice.h>
+#include <linux/of.h>
 #include <linux/thermal.h>
 #include "mt7996.h"
 #include "mac.h"
diff --git a/drivers/net/wireless/silabs/wfx/bus_sdio.c b/drivers/net/wireless/silabs/wfx/bus_sdio.c
index 51a0d58a9070f..909d5f346a01b 100644
--- a/drivers/net/wireless/silabs/wfx/bus_sdio.c
+++ b/drivers/net/wireless/silabs/wfx/bus_sdio.c
@@ -10,7 +10,7 @@
 #include <linux/mmc/sdio_func.h>
 #include <linux/mmc/card.h>
 #include <linux/interrupt.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/irq.h>
 #include <linux/align.h>
-- 
GitLab


From c1861ff1d63d0a185df6e2f0ec21455467aeb16c Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Tue, 25 Jul 2023 09:04:43 +0300
Subject: [PATCH 0709/1806] wifi: libertas: add missing calls to
 cancel_work_sync()

Add missing 'cancel_work_sync()' in 'if_sdio_remove()'
and on error handling path in 'if_sdio_probe()'.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Tested-by: Dan Williams <dcbw@redhat.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230725060531.72968-1-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/libertas/if_sdio.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/marvell/libertas/if_sdio.c b/drivers/net/wireless/marvell/libertas/if_sdio.c
index a63c5e622ee37..a35b33e84670a 100644
--- a/drivers/net/wireless/marvell/libertas/if_sdio.c
+++ b/drivers/net/wireless/marvell/libertas/if_sdio.c
@@ -1233,6 +1233,7 @@ err_activate_card:
 	flush_workqueue(card->workqueue);
 	lbs_remove_card(priv);
 free:
+	cancel_work_sync(&card->packet_worker);
 	destroy_workqueue(card->workqueue);
 err_queue:
 	while (card->packets) {
@@ -1277,6 +1278,7 @@ static void if_sdio_remove(struct sdio_func *func)
 	lbs_stop_card(card->priv);
 	lbs_remove_card(card->priv);
 
+	cancel_work_sync(&card->packet_worker);
 	destroy_workqueue(card->workqueue);
 
 	while (card->packets) {
-- 
GitLab


From ce44fdf9c9d28e0d1ee99d77e11b182a7e5aa729 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Tue, 25 Jul 2023 09:04:44 +0300
Subject: [PATCH 0710/1806] wifi: libertas: use convenient lists to manage SDIO
 packets

Use convenient lists to manage SDIO packets, adjust
'struct if_sdio_packet', 'struct if_sdio_card' and
related code accordingly.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230725060531.72968-2-dmantipov@yandex.ru
---
 .../net/wireless/marvell/libertas/if_sdio.c   | 37 +++++++------------
 1 file changed, 13 insertions(+), 24 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/if_sdio.c b/drivers/net/wireless/marvell/libertas/if_sdio.c
index a35b33e84670a..c72081cf8a85c 100644
--- a/drivers/net/wireless/marvell/libertas/if_sdio.c
+++ b/drivers/net/wireless/marvell/libertas/if_sdio.c
@@ -101,7 +101,7 @@ MODULE_FIRMWARE("sd8688_helper.bin");
 MODULE_FIRMWARE("sd8688.bin");
 
 struct if_sdio_packet {
-	struct if_sdio_packet	*next;
+	struct list_head	list;
 	u16			nb;
 	u8			buffer[] __aligned(4);
 };
@@ -119,7 +119,7 @@ struct if_sdio_card {
 	u8			buffer[65536] __attribute__((aligned(4)));
 
 	spinlock_t		lock;
-	struct if_sdio_packet	*packets;
+	struct list_head	packets;
 
 	struct workqueue_struct	*workqueue;
 	struct work_struct	packet_worker;
@@ -404,9 +404,10 @@ static void if_sdio_host_to_card_worker(struct work_struct *work)
 
 	while (1) {
 		spin_lock_irqsave(&card->lock, flags);
-		packet = card->packets;
+		packet = list_first_entry_or_null(&card->packets,
+						  struct if_sdio_packet, list);
 		if (packet)
-			card->packets = packet->next;
+			list_del(&packet->list);
 		spin_unlock_irqrestore(&card->lock, flags);
 
 		if (!packet)
@@ -909,7 +910,7 @@ static int if_sdio_host_to_card(struct lbs_private *priv,
 {
 	int ret;
 	struct if_sdio_card *card;
-	struct if_sdio_packet *packet, *cur;
+	struct if_sdio_packet *packet;
 	u16 size;
 	unsigned long flags;
 
@@ -934,7 +935,6 @@ static int if_sdio_host_to_card(struct lbs_private *priv,
 		goto out;
 	}
 
-	packet->next = NULL;
 	packet->nb = size;
 
 	/*
@@ -949,14 +949,7 @@ static int if_sdio_host_to_card(struct lbs_private *priv,
 
 	spin_lock_irqsave(&card->lock, flags);
 
-	if (!card->packets)
-		card->packets = packet;
-	else {
-		cur = card->packets;
-		while (cur->next)
-			cur = cur->next;
-		cur->next = packet;
-	}
+	list_add_tail(&packet->list, &card->packets);
 
 	switch (type) {
 	case MVMS_CMD:
@@ -1137,7 +1130,7 @@ static int if_sdio_probe(struct sdio_func *func,
 	struct lbs_private *priv;
 	int ret, i;
 	unsigned int model;
-	struct if_sdio_packet *packet;
+	struct if_sdio_packet *packet, *tmp;
 
 	for (i = 0;i < func->card->num_info;i++) {
 		if (sscanf(func->card->info[i],
@@ -1178,6 +1171,8 @@ static int if_sdio_probe(struct sdio_func *func,
 	}
 
 	spin_lock_init(&card->lock);
+	INIT_LIST_HEAD(&card->packets);
+
 	card->workqueue = alloc_workqueue("libertas_sdio", WQ_MEM_RECLAIM, 0);
 	if (unlikely(!card->workqueue)) {
 		ret = -ENOMEM;
@@ -1236,11 +1231,8 @@ free:
 	cancel_work_sync(&card->packet_worker);
 	destroy_workqueue(card->workqueue);
 err_queue:
-	while (card->packets) {
-		packet = card->packets;
-		card->packets = card->packets->next;
+	list_for_each_entry_safe(packet, tmp, &card->packets, list)
 		kfree(packet);
-	}
 
 	kfree(card);
 
@@ -1250,7 +1242,7 @@ err_queue:
 static void if_sdio_remove(struct sdio_func *func)
 {
 	struct if_sdio_card *card;
-	struct if_sdio_packet *packet;
+	struct if_sdio_packet *packet, *tmp;
 
 	card = sdio_get_drvdata(func);
 
@@ -1281,11 +1273,8 @@ static void if_sdio_remove(struct sdio_func *func)
 	cancel_work_sync(&card->packet_worker);
 	destroy_workqueue(card->workqueue);
 
-	while (card->packets) {
-		packet = card->packets;
-		card->packets = card->packets->next;
+	list_for_each_entry_safe(packet, tmp, &card->packets, list)
 		kfree(packet);
-	}
 
 	kfree(card);
 }
-- 
GitLab


From 2c531d28f8e938db0dfdee16f251b1ca55bc4a8b Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Tue, 25 Jul 2023 09:04:45 +0300
Subject: [PATCH 0711/1806] wifi: libertas: simplify list operations in
 free_if_spi_card()

Use 'list_for_each_entry_safe()' to simplify
list operations in 'free_if_spi_card()'.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230725060531.72968-3-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/libertas/if_spi.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/if_spi.c b/drivers/net/wireless/marvell/libertas/if_spi.c
index 1225fc0e3352f..3d53e444ba19d 100644
--- a/drivers/net/wireless/marvell/libertas/if_spi.c
+++ b/drivers/net/wireless/marvell/libertas/if_spi.c
@@ -76,16 +76,13 @@ struct if_spi_card {
 
 static void free_if_spi_card(struct if_spi_card *card)
 {
-	struct list_head *cursor, *next;
-	struct if_spi_packet *packet;
+	struct if_spi_packet *packet, *tmp;
 
-	list_for_each_safe(cursor, next, &card->cmd_packet_list) {
-		packet = container_of(cursor, struct if_spi_packet, list);
+	list_for_each_entry_safe(packet, tmp, &card->cmd_packet_list, list) {
 		list_del(&packet->list);
 		kfree(packet);
 	}
-	list_for_each_safe(cursor, next, &card->data_packet_list) {
-		packet = container_of(cursor, struct if_spi_packet, list);
+	list_for_each_entry_safe(packet, tmp, &card->data_packet_list, list) {
 		list_del(&packet->list);
 		kfree(packet);
 	}
-- 
GitLab


From 6c968e90198fbb2d923c4e47b7303c3ad2c25a71 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Tue, 25 Jul 2023 09:04:46 +0300
Subject: [PATCH 0712/1806] wifi: libertas: cleanup SDIO reset

Embed SDIO reset worker in 'struct if_sdio_card' and so
drop 'reset_host' and 'card_reset_work' static variables,
adjust related code. Not sure whether it's possible to do
something useful on 'mmc_add_host()' error, so just add
'dev_err()' to emit an error message.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230725060531.72968-4-dmantipov@yandex.ru
---
 .../net/wireless/marvell/libertas/if_sdio.c   | 34 ++++++++++++-------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/if_sdio.c b/drivers/net/wireless/marvell/libertas/if_sdio.c
index c72081cf8a85c..524034699972d 100644
--- a/drivers/net/wireless/marvell/libertas/if_sdio.c
+++ b/drivers/net/wireless/marvell/libertas/if_sdio.c
@@ -123,6 +123,7 @@ struct if_sdio_card {
 
 	struct workqueue_struct	*workqueue;
 	struct work_struct	packet_worker;
+	struct work_struct	reset_worker;
 
 	u8			rx_unit;
 };
@@ -1022,10 +1023,19 @@ static int if_sdio_reset_deep_sleep_wakeup(struct lbs_private *priv)
 
 }
 
-static struct mmc_host *reset_host;
-
 static void if_sdio_reset_card_worker(struct work_struct *work)
 {
+	int ret;
+	const char *name;
+	struct device *dev;
+	struct if_sdio_card *card;
+	struct mmc_host *reset_host;
+
+	card = container_of(work, struct if_sdio_card, reset_worker);
+	reset_host = card->func->card->host;
+	name = card->priv->dev->name;
+	dev = &card->func->dev;
+
 	/*
 	 * The actual reset operation must be run outside of lbs_thread. This
 	 * is because mmc_remove_host() will cause the device to be instantly
@@ -1036,21 +1046,19 @@ static void if_sdio_reset_card_worker(struct work_struct *work)
 	 * instance for that reason.
 	 */
 
-	pr_info("Resetting card...");
+	dev_info(dev, "resetting card %s...", name);
 	mmc_remove_host(reset_host);
-	mmc_add_host(reset_host);
+	ret = mmc_add_host(reset_host);
+	if (ret)
+		dev_err(dev, "%s: can't add mmc host, error %d\n", name, ret);
 }
-static DECLARE_WORK(card_reset_work, if_sdio_reset_card_worker);
 
 static void if_sdio_reset_card(struct lbs_private *priv)
 {
 	struct if_sdio_card *card = priv->card;
 
-	if (work_pending(&card_reset_work))
-		return;
-
-	reset_host = card->func->card->host;
-	schedule_work(&card_reset_work);
+	if (!work_pending(&card->reset_worker))
+		schedule_work(&card->reset_worker);
 }
 
 static int if_sdio_power_save(struct lbs_private *priv)
@@ -1178,6 +1186,8 @@ static int if_sdio_probe(struct sdio_func *func,
 		ret = -ENOMEM;
 		goto err_queue;
 	}
+
+	INIT_WORK(&card->reset_worker, if_sdio_reset_card_worker);
 	INIT_WORK(&card->packet_worker, if_sdio_host_to_card_worker);
 	init_waitqueue_head(&card->pwron_waitq);
 
@@ -1229,6 +1239,7 @@ err_activate_card:
 	lbs_remove_card(priv);
 free:
 	cancel_work_sync(&card->packet_worker);
+	cancel_work_sync(&card->reset_worker);
 	destroy_workqueue(card->workqueue);
 err_queue:
 	list_for_each_entry_safe(packet, tmp, &card->packets, list)
@@ -1271,6 +1282,7 @@ static void if_sdio_remove(struct sdio_func *func)
 	lbs_remove_card(card->priv);
 
 	cancel_work_sync(&card->packet_worker);
+	cancel_work_sync(&card->reset_worker);
 	destroy_workqueue(card->workqueue);
 
 	list_for_each_entry_safe(packet, tmp, &card->packets, list)
@@ -1394,8 +1406,6 @@ static void __exit if_sdio_exit_module(void)
 	/* Set the flag as user is removing this module. */
 	user_rmmod = 1;
 
-	cancel_work_sync(&card_reset_work);
-
 	sdio_unregister_driver(&if_sdio_driver);
 }
 
-- 
GitLab


From 3e14212f79fd05c4f5bdfa4eba5ae53f75900410 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Tue, 25 Jul 2023 09:04:47 +0300
Subject: [PATCH 0713/1806] wifi: libertas: handle possible spu_write_u16()
 errors

Check and handle (well, report at least, as it's done through the rest
of the module) possible 'spu_write_u16()' errors in 'if_spi_e2h()'.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230725060531.72968-5-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/libertas/if_spi.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/if_spi.c b/drivers/net/wireless/marvell/libertas/if_spi.c
index 3d53e444ba19d..8690b0114e235 100644
--- a/drivers/net/wireless/marvell/libertas/if_spi.c
+++ b/drivers/net/wireless/marvell/libertas/if_spi.c
@@ -826,11 +826,16 @@ static void if_spi_e2h(struct if_spi_card *card)
 		goto out;
 
 	/* re-enable the card event interrupt */
-	spu_write_u16(card, IF_SPI_HOST_INT_STATUS_REG,
-			~IF_SPI_HICU_CARD_EVENT);
+	err = spu_write_u16(card, IF_SPI_HOST_INT_STATUS_REG,
+			    ~IF_SPI_HICU_CARD_EVENT);
+	if (err)
+		goto out;
 
 	/* generate a card interrupt */
-	spu_write_u16(card, IF_SPI_CARD_INT_CAUSE_REG, IF_SPI_CIC_HOST_EVENT);
+	err = spu_write_u16(card, IF_SPI_CARD_INT_CAUSE_REG,
+			    IF_SPI_CIC_HOST_EVENT);
+	if (err)
+		goto out;
 
 	lbs_queue_event(priv, cause & 0xff);
 out:
-- 
GitLab


From f5343efdf5b5d66844ce041e5dcd585ee5697747 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Tue, 25 Jul 2023 09:04:48 +0300
Subject: [PATCH 0714/1806] wifi: libertas: prefer kstrtoX() for simple integer
 conversions

Prefer 'kstrtoX()' family of functions over 'sscanf()' to convert
strings to integers and always check results of the conversions.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230725060531.72968-6-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/libertas/mesh.c | 51 +++++++++++++-------
 1 file changed, 33 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/mesh.c b/drivers/net/wireless/marvell/libertas/mesh.c
index 90ffe8d1e0e81..2dd635935448b 100644
--- a/drivers/net/wireless/marvell/libertas/mesh.c
+++ b/drivers/net/wireless/marvell/libertas/mesh.c
@@ -188,8 +188,11 @@ static ssize_t anycast_mask_store(struct device *dev,
 	uint32_t datum;
 	int ret;
 
+	ret = kstrtouint(buf, 16, &datum);
+	if (ret)
+		return ret;
+
 	memset(&mesh_access, 0, sizeof(mesh_access));
-	sscanf(buf, "%x", &datum);
 	mesh_access.data[0] = cpu_to_le32(datum);
 
 	ret = lbs_mesh_access(priv, CMD_ACT_MESH_SET_ANYCAST, &mesh_access);
@@ -241,15 +244,14 @@ static ssize_t prb_rsp_limit_store(struct device *dev,
 	int ret;
 	unsigned long retry_limit;
 
-	memset(&mesh_access, 0, sizeof(mesh_access));
-	mesh_access.data[0] = cpu_to_le32(CMD_ACT_SET);
-
 	ret = kstrtoul(buf, 10, &retry_limit);
 	if (ret)
 		return ret;
 	if (retry_limit > 15)
 		return -ENOTSUPP;
 
+	memset(&mesh_access, 0, sizeof(mesh_access));
+	mesh_access.data[0] = cpu_to_le32(CMD_ACT_SET);
 	mesh_access.data[1] = cpu_to_le32(retry_limit);
 
 	ret = lbs_mesh_access(priv, CMD_ACT_MESH_SET_GET_PRB_RSP_LIMIT,
@@ -285,9 +287,12 @@ static ssize_t lbs_mesh_store(struct device *dev,
 			      const char *buf, size_t count)
 {
 	struct lbs_private *priv = to_net_dev(dev)->ml_priv;
-	int enable;
+	int ret, enable;
+
+	ret = kstrtoint(buf, 16, &enable);
+	if (ret)
+		return ret;
 
-	sscanf(buf, "%x", &enable);
 	enable = !!enable;
 	if (enable == !!priv->mesh_dev)
 		return count;
@@ -387,11 +392,13 @@ static ssize_t bootflag_store(struct device *dev, struct device_attribute *attr,
 	uint32_t datum;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
-	ret = sscanf(buf, "%d", &datum);
-	if ((ret != 1) || (datum > 1))
+	ret = kstrtouint(buf, 10, &datum);
+	if (ret)
+		return ret;
+	if (datum > 1)
 		return -EINVAL;
 
+	memset(&cmd, 0, sizeof(cmd));
 	*((__le32 *)&cmd.data[0]) = cpu_to_le32(!!datum);
 	cmd.length = cpu_to_le16(sizeof(uint32_t));
 	ret = lbs_mesh_config_send(priv, &cmd, CMD_ACT_MESH_CONFIG_SET,
@@ -438,11 +445,14 @@ static ssize_t boottime_store(struct device *dev,
 	uint32_t datum;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
-	ret = sscanf(buf, "%d", &datum);
-	if ((ret != 1) || (datum > 255))
+	ret = kstrtouint(buf, 10, &datum);
+	if (ret)
+		return ret;
+	if (datum > 255)
 		return -EINVAL;
 
+	memset(&cmd, 0, sizeof(cmd));
+
 	/* A too small boot time will result in the device booting into
 	 * standalone (no-host) mode before the host can take control of it,
 	 * so the change will be hard to revert.  This may be a desired
@@ -497,11 +507,13 @@ static ssize_t channel_store(struct device *dev, struct device_attribute *attr,
 	uint32_t datum;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
-	ret = sscanf(buf, "%d", &datum);
-	if (ret != 1 || datum < 1 || datum > 11)
+	ret = kstrtouint(buf, 10, &datum);
+	if (ret)
+		return ret;
+	if (datum < 1 || datum > 11)
 		return -EINVAL;
 
+	memset(&cmd, 0, sizeof(cmd));
 	*((__le16 *)&cmd.data[0]) = cpu_to_le16(datum);
 	cmd.length = cpu_to_le16(sizeof(uint16_t));
 	ret = lbs_mesh_config_send(priv, &cmd, CMD_ACT_MESH_CONFIG_SET,
@@ -626,11 +638,14 @@ static ssize_t protocol_id_store(struct device *dev,
 	uint32_t datum;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
-	ret = sscanf(buf, "%d", &datum);
-	if ((ret != 1) || (datum > 255))
+	ret = kstrtouint(buf, 10, &datum);
+	if (ret)
+		return ret;
+	if (datum > 255)
 		return -EINVAL;
 
+	memset(&cmd, 0, sizeof(cmd));
+
 	/* fetch all other Information Element parameters */
 	ret = mesh_get_default_parameters(dev, &defs);
 
-- 
GitLab


From d3c4db86c71164ed9ae17b4026e1acde460a18ab Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <ykaliuta@redhat.com>
Date: Tue, 1 Aug 2023 10:52:22 +0300
Subject: [PATCH 0715/1806] tracing: bpf: use struct trace_entry in struct
 syscall_tp_t

bpf tracepoint program uses struct trace_event_raw_sys_enter as
argument where trace_entry is the first field. Use the same instead
of unsigned long long since if it's amended (for example by RT
patch) it accesses data with wrong offset.

Signed-off-by: Yauheni Kaliuta <ykaliuta@redhat.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230801075222.7717-1-ykaliuta@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/trace_syscalls.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 942ddbdace4a4..de753403cdafb 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -555,12 +555,15 @@ static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *re
 			       struct syscall_trace_enter *rec)
 {
 	struct syscall_tp_t {
-		unsigned long long regs;
+		struct trace_entry ent;
 		unsigned long syscall_nr;
 		unsigned long args[SYSCALL_DEFINE_MAXARGS];
-	} param;
+	} __aligned(8) param;
 	int i;
 
+	BUILD_BUG_ON(sizeof(param.ent) < sizeof(void *));
+
+	/* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
 	*(struct pt_regs **)&param = regs;
 	param.syscall_nr = rec->nr;
 	for (i = 0; i < sys_data->nb_args; i++)
@@ -657,11 +660,12 @@ static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *reg
 			      struct syscall_trace_exit *rec)
 {
 	struct syscall_tp_t {
-		unsigned long long regs;
+		struct trace_entry ent;
 		unsigned long syscall_nr;
 		unsigned long ret;
-	} param;
+	} __aligned(8) param;
 
+	/* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
 	*(struct pt_regs **)&param = regs;
 	param.syscall_nr = rec->nr;
 	param.ret = rec->ret;
-- 
GitLab


From 005c9600003eabcb22336f37e149eed08f0a946a Mon Sep 17 00:00:00 2001
From: Atul Raut <rauji.raut@gmail.com>
Date: Sun, 30 Jul 2023 16:14:42 -0700
Subject: [PATCH 0716/1806] net/macmace: Replace zero-length array with
 DECLARE_FLEX_ARRAY() helper

Since zero-length arrays are deprecated, we are replacing
them with C99 flexible-array members. As a result, instead
of declaring a zero-length array, use the new
DECLARE_FLEX_ARRAY() helper macro.

This fixes warnings such as:
./drivers/net/ethernet/apple/macmace.c:80:4-8: WARNING use flexible-array member instead (https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays)

Signed-off-by: Atul Raut <rauji.raut@gmail.com>
Link: https://lore.kernel.org/r/20230730231442.15003-1-rauji.raut@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/apple/macmace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/apple/macmace.c b/drivers/net/ethernet/apple/macmace.c
index 8fcaf16399201..8775c3234e91f 100644
--- a/drivers/net/ethernet/apple/macmace.c
+++ b/drivers/net/ethernet/apple/macmace.c
@@ -77,7 +77,7 @@ struct mace_frame {
 	u8	pad4;
 	u32	pad5;
 	u32	pad6;
-	u8	data[1];
+	DECLARE_FLEX_ARRAY(u8, data);
 	/* And frame continues.. */
 };
 
-- 
GitLab


From ceaac91dcd065db781d1ed5dfaef0686b8ec44dc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 31 Jul 2023 10:11:58 -0700
Subject: [PATCH 0717/1806] net: make sure we never create ifindex = 0

Instead of allocating from 1 use proper xa_init flag,
to protect ourselves from IDs wrapping back to 0.

Fixes: 759ab1edb56c ("net: store netdevs in an xarray")
Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Link: https://lore.kernel.org/all/20230728162350.2a6d4979@hermes.local/
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230731171159.988962-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index b58674774a57b..10e5a036c706a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11271,8 +11271,7 @@ static int __net_init netdev_init(struct net *net)
 	if (net->dev_index_head == NULL)
 		goto err_idx;
 
-	net->ifindex = 1;
-	xa_init_flags(&net->dev_by_index, XA_FLAGS_ALLOC);
+	xa_init_flags(&net->dev_by_index, XA_FLAGS_ALLOC1);
 
 	RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain);
 
-- 
GitLab


From 999d0863ff6416dd33c904f496bf363c8afb6540 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 31 Jul 2023 22:04:37 +0800
Subject: [PATCH 0718/1806] inet6: Remove unused function declaration
 udpv6_connect()

This is never implemented since the beginning of git history.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230731140437.37056-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/transp_v6.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index d27b1caf37537..1a97e3f32029a 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -33,8 +33,6 @@ void udplitev6_exit(void);
 int tcpv6_init(void);
 void tcpv6_exit(void);
 
-int udpv6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
-
 /* this does all the common and the specific ctl work */
 void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
 			   struct sk_buff *skb);
-- 
GitLab


From 308d7982dcdc9259ef4a815fe08913087a2c0ea3 Mon Sep 17 00:00:00 2001
From: Gavin Li <gavinl@nvidia.com>
Date: Mon, 31 Jul 2023 10:06:54 +0300
Subject: [PATCH 0719/1806] virtio_net: extract interrupt coalescing settings
 to a structure

Extract interrupt coalescing settings to a structure so that it could be
reused in other data structures.

Signed-off-by: Gavin Li <gavinl@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Heng Qi <hengqi@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230731070656.96411-2-gavinl@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 35 +++++++++++++++++++----------------
 1 file changed, 19 insertions(+), 16 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 1270c8d23463f..b1e2e63edd352 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -126,6 +126,11 @@ static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = {
 #define VIRTNET_SQ_STATS_LEN	ARRAY_SIZE(virtnet_sq_stats_desc)
 #define VIRTNET_RQ_STATS_LEN	ARRAY_SIZE(virtnet_rq_stats_desc)
 
+struct virtnet_interrupt_coalesce {
+	u32 max_packets;
+	u32 max_usecs;
+};
+
 /* Internal representation of a send virtqueue */
 struct send_queue {
 	/* Virtqueue associated with this send _queue */
@@ -281,10 +286,8 @@ struct virtnet_info {
 	u32 speed;
 
 	/* Interrupt coalescing settings */
-	u32 tx_usecs;
-	u32 rx_usecs;
-	u32 tx_max_packets;
-	u32 rx_max_packets;
+	struct virtnet_interrupt_coalesce intr_coal_tx;
+	struct virtnet_interrupt_coalesce intr_coal_rx;
 
 	unsigned long guest_offloads;
 	unsigned long guest_offloads_capable;
@@ -3056,8 +3059,8 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 		return -EINVAL;
 
 	/* Save parameters */
-	vi->tx_usecs = ec->tx_coalesce_usecs;
-	vi->tx_max_packets = ec->tx_max_coalesced_frames;
+	vi->intr_coal_tx.max_usecs = ec->tx_coalesce_usecs;
+	vi->intr_coal_tx.max_packets = ec->tx_max_coalesced_frames;
 
 	vi->ctrl->coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs);
 	vi->ctrl->coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames);
@@ -3069,8 +3072,8 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 		return -EINVAL;
 
 	/* Save parameters */
-	vi->rx_usecs = ec->rx_coalesce_usecs;
-	vi->rx_max_packets = ec->rx_max_coalesced_frames;
+	vi->intr_coal_rx.max_usecs = ec->rx_coalesce_usecs;
+	vi->intr_coal_rx.max_packets = ec->rx_max_coalesced_frames;
 
 	return 0;
 }
@@ -3132,10 +3135,10 @@ static int virtnet_get_coalesce(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) {
-		ec->rx_coalesce_usecs = vi->rx_usecs;
-		ec->tx_coalesce_usecs = vi->tx_usecs;
-		ec->tx_max_coalesced_frames = vi->tx_max_packets;
-		ec->rx_max_coalesced_frames = vi->rx_max_packets;
+		ec->rx_coalesce_usecs = vi->intr_coal_rx.max_usecs;
+		ec->tx_coalesce_usecs = vi->intr_coal_tx.max_usecs;
+		ec->tx_max_coalesced_frames = vi->intr_coal_tx.max_packets;
+		ec->rx_max_coalesced_frames = vi->intr_coal_rx.max_packets;
 	} else {
 		ec->rx_max_coalesced_frames = 1;
 
@@ -4119,10 +4122,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 	}
 
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) {
-		vi->rx_usecs = 0;
-		vi->tx_usecs = 0;
-		vi->tx_max_packets = 0;
-		vi->rx_max_packets = 0;
+		vi->intr_coal_rx.max_usecs = 0;
+		vi->intr_coal_tx.max_usecs = 0;
+		vi->intr_coal_tx.max_packets = 0;
+		vi->intr_coal_rx.max_packets = 0;
 	}
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT))
-- 
GitLab


From 394bd87764b615b0fc17d34127a1cc7da76ff49f Mon Sep 17 00:00:00 2001
From: Gavin Li <gavinl@nvidia.com>
Date: Mon, 31 Jul 2023 10:06:55 +0300
Subject: [PATCH 0720/1806] virtio_net: support per queue interrupt coalesce
 command

Add interrupt_coalesce config in send_queue and receive_queue to cache user
config.

Send per virtqueue interrupt moderation config to underlying device in
order to have more efficient interrupt moderation and cpu utilization of
guest VM.

Additionally, address all the VQs when updating the global configuration,
as now the individual VQs configuration can diverge from the global
configuration.

Signed-off-by: Gavin Li <gavinl@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Heng Qi <hengqi@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20230731070656.96411-3-gavinl@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c        | 149 ++++++++++++++++++++++++++++++--
 include/uapi/linux/virtio_net.h |  14 +++
 2 files changed, 155 insertions(+), 8 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b1e2e63edd352..77805796fddd2 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -144,6 +144,8 @@ struct send_queue {
 
 	struct virtnet_sq_stats stats;
 
+	struct virtnet_interrupt_coalesce intr_coal;
+
 	struct napi_struct napi;
 
 	/* Record whether sq is in reset state. */
@@ -161,6 +163,8 @@ struct receive_queue {
 
 	struct virtnet_rq_stats stats;
 
+	struct virtnet_interrupt_coalesce intr_coal;
+
 	/* Chain pages by the private ptr. */
 	struct page *pages;
 
@@ -212,6 +216,7 @@ struct control_buf {
 	struct virtio_net_ctrl_rss rss;
 	struct virtio_net_ctrl_coal_tx coal_tx;
 	struct virtio_net_ctrl_coal_rx coal_rx;
+	struct virtio_net_ctrl_coal_vq coal_vq;
 };
 
 struct virtnet_info {
@@ -3078,6 +3083,55 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 	return 0;
 }
 
+static int virtnet_send_ctrl_coal_vq_cmd(struct virtnet_info *vi,
+					 u16 vqn, u32 max_usecs, u32 max_packets)
+{
+	struct scatterlist sgs;
+
+	vi->ctrl->coal_vq.vqn = cpu_to_le16(vqn);
+	vi->ctrl->coal_vq.coal.max_usecs = cpu_to_le32(max_usecs);
+	vi->ctrl->coal_vq.coal.max_packets = cpu_to_le32(max_packets);
+	sg_init_one(&sgs, &vi->ctrl->coal_vq, sizeof(vi->ctrl->coal_vq));
+
+	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
+				  VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET,
+				  &sgs))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int virtnet_send_notf_coal_vq_cmds(struct virtnet_info *vi,
+					  struct ethtool_coalesce *ec,
+					  u16 queue)
+{
+	int err;
+
+	if (ec->rx_coalesce_usecs || ec->rx_max_coalesced_frames) {
+		err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue),
+						    ec->rx_coalesce_usecs,
+						    ec->rx_max_coalesced_frames);
+		if (err)
+			return err;
+		/* Save parameters */
+		vi->rq[queue].intr_coal.max_usecs = ec->rx_coalesce_usecs;
+		vi->rq[queue].intr_coal.max_packets = ec->rx_max_coalesced_frames;
+	}
+
+	if (ec->tx_coalesce_usecs || ec->tx_max_coalesced_frames) {
+		err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue),
+						    ec->tx_coalesce_usecs,
+						    ec->tx_max_coalesced_frames);
+		if (err)
+			return err;
+		/* Save parameters */
+		vi->sq[queue].intr_coal.max_usecs = ec->tx_coalesce_usecs;
+		vi->sq[queue].intr_coal.max_packets = ec->tx_max_coalesced_frames;
+	}
+
+	return 0;
+}
+
 static int virtnet_coal_params_supported(struct ethtool_coalesce *ec)
 {
 	/* usecs coalescing is supported only if VIRTIO_NET_F_NOTF_COAL
@@ -3093,22 +3147,42 @@ static int virtnet_coal_params_supported(struct ethtool_coalesce *ec)
 	return 0;
 }
 
+static int virtnet_should_update_vq_weight(int dev_flags, int weight,
+					   int vq_weight, bool *should_update)
+{
+	if (weight ^ vq_weight) {
+		if (dev_flags & IFF_UP)
+			return -EBUSY;
+		*should_update = true;
+	}
+
+	return 0;
+}
+
 static int virtnet_set_coalesce(struct net_device *dev,
 				struct ethtool_coalesce *ec,
 				struct kernel_ethtool_coalesce *kernel_coal,
 				struct netlink_ext_ack *extack)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
-	int ret, i, napi_weight;
+	int ret, queue_number, napi_weight;
 	bool update_napi = false;
 
 	/* Can't change NAPI weight if the link is up */
 	napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0;
-	if (napi_weight ^ vi->sq[0].napi.weight) {
-		if (dev->flags & IFF_UP)
-			return -EBUSY;
-		else
-			update_napi = true;
+	for (queue_number = 0; queue_number < vi->max_queue_pairs; queue_number++) {
+		ret = virtnet_should_update_vq_weight(dev->flags, napi_weight,
+						      vi->sq[queue_number].napi.weight,
+						      &update_napi);
+		if (ret)
+			return ret;
+
+		if (update_napi) {
+			/* All queues that belong to [queue_number, vi->max_queue_pairs] will be
+			 * updated for the sake of simplicity, which might not be necessary
+			 */
+			break;
+		}
 	}
 
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL))
@@ -3120,8 +3194,8 @@ static int virtnet_set_coalesce(struct net_device *dev,
 		return ret;
 
 	if (update_napi) {
-		for (i = 0; i < vi->max_queue_pairs; i++)
-			vi->sq[i].napi.weight = napi_weight;
+		for (; queue_number < vi->max_queue_pairs; queue_number++)
+			vi->sq[queue_number].napi.weight = napi_weight;
 	}
 
 	return ret;
@@ -3149,6 +3223,63 @@ static int virtnet_get_coalesce(struct net_device *dev,
 	return 0;
 }
 
+static int virtnet_set_per_queue_coalesce(struct net_device *dev,
+					  u32 queue,
+					  struct ethtool_coalesce *ec)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	int ret, napi_weight;
+	bool update_napi = false;
+
+	if (queue >= vi->max_queue_pairs)
+		return -EINVAL;
+
+	/* Can't change NAPI weight if the link is up */
+	napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0;
+	ret = virtnet_should_update_vq_weight(dev->flags, napi_weight,
+					      vi->sq[queue].napi.weight,
+					      &update_napi);
+	if (ret)
+		return ret;
+
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
+		ret = virtnet_send_notf_coal_vq_cmds(vi, ec, queue);
+	else
+		ret = virtnet_coal_params_supported(ec);
+
+	if (ret)
+		return ret;
+
+	if (update_napi)
+		vi->sq[queue].napi.weight = napi_weight;
+
+	return 0;
+}
+
+static int virtnet_get_per_queue_coalesce(struct net_device *dev,
+					  u32 queue,
+					  struct ethtool_coalesce *ec)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+
+	if (queue >= vi->max_queue_pairs)
+		return -EINVAL;
+
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) {
+		ec->rx_coalesce_usecs = vi->rq[queue].intr_coal.max_usecs;
+		ec->tx_coalesce_usecs = vi->sq[queue].intr_coal.max_usecs;
+		ec->tx_max_coalesced_frames = vi->sq[queue].intr_coal.max_packets;
+		ec->rx_max_coalesced_frames = vi->rq[queue].intr_coal.max_packets;
+	} else {
+		ec->rx_max_coalesced_frames = 1;
+
+		if (vi->sq[0].napi.weight)
+			ec->tx_max_coalesced_frames = 1;
+	}
+
+	return 0;
+}
+
 static void virtnet_init_settings(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -3279,6 +3410,8 @@ static const struct ethtool_ops virtnet_ethtool_ops = {
 	.set_link_ksettings = virtnet_set_link_ksettings,
 	.set_coalesce = virtnet_set_coalesce,
 	.get_coalesce = virtnet_get_coalesce,
+	.set_per_queue_coalesce = virtnet_set_per_queue_coalesce,
+	.get_per_queue_coalesce = virtnet_get_per_queue_coalesce,
 	.get_rxfh_key_size = virtnet_get_rxfh_key_size,
 	.get_rxfh_indir_size = virtnet_get_rxfh_indir_size,
 	.get_rxfh = virtnet_get_rxfh,
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 12c1c9699935e..cc65ef0f3c3e2 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -56,6 +56,7 @@
 #define VIRTIO_NET_F_MQ	22	/* Device supports Receive Flow
 					 * Steering */
 #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
+#define VIRTIO_NET_F_VQ_NOTF_COAL 52	/* Device supports virtqueue notification coalescing */
 #define VIRTIO_NET_F_NOTF_COAL	53	/* Device supports notifications coalescing */
 #define VIRTIO_NET_F_GUEST_USO4	54	/* Guest can handle USOv4 in. */
 #define VIRTIO_NET_F_GUEST_USO6	55	/* Guest can handle USOv6 in. */
@@ -391,5 +392,18 @@ struct virtio_net_ctrl_coal_rx {
 };
 
 #define VIRTIO_NET_CTRL_NOTF_COAL_RX_SET		1
+#define VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET		2
+#define VIRTIO_NET_CTRL_NOTF_COAL_VQ_GET		3
+
+struct virtio_net_ctrl_coal {
+	__le32 max_packets;
+	__le32 max_usecs;
+};
+
+struct  virtio_net_ctrl_coal_vq {
+	__le16 vqn;
+	__le16 reserved;
+	struct virtio_net_ctrl_coal coal;
+};
 
 #endif /* _UAPI_LINUX_VIRTIO_NET_H */
-- 
GitLab


From 8af3bf668382eeaba90b15bb37d1bd23c6b55a1e Mon Sep 17 00:00:00 2001
From: Gavin Li <gavinl@nvidia.com>
Date: Mon, 31 Jul 2023 10:06:56 +0300
Subject: [PATCH 0721/1806] virtio_net: enable per queue interrupt coalesce
 feature

Enable per queue interrupt coalesce feature bit in driver and validate its
dependency with control queue.

Signed-off-by: Gavin Li <gavinl@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Heng Qi <hengqi@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20230731070656.96411-4-gavinl@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 77805796fddd2..c615bbf24c0df 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -4088,6 +4088,8 @@ static bool virtnet_validate_features(struct virtio_device *vdev)
 	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_HASH_REPORT,
 			     "VIRTIO_NET_F_CTRL_VQ") ||
 	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_NOTF_COAL,
+			     "VIRTIO_NET_F_CTRL_VQ") ||
+	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_VQ_NOTF_COAL,
 			     "VIRTIO_NET_F_CTRL_VQ"))) {
 		return false;
 	}
@@ -4512,6 +4514,7 @@ static struct virtio_device_id id_table[] = {
 	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
 	VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \
 	VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL, \
+	VIRTIO_NET_F_VQ_NOTF_COAL, \
 	VIRTIO_NET_F_GUEST_HDRLEN
 
 static unsigned int features[] = {
-- 
GitLab


From ac0687e821cffab24da4531372dc67ba2fac843d Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:09 +0300
Subject: [PATCH 0722/1806] net: phy: nxp-c45-tja11xx: use phylib master/slave
 implementation

Remove the custom implementation of master/save setup and read status
and use genphy_c45_config_aneg and genphy_c45_read_status since phylib
has support for master/slave setup and master/slave status.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230731091619.77961-2-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 77 +------------------------------
 1 file changed, 2 insertions(+), 75 deletions(-)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 029875a59ff89..41b8af0547e42 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -19,13 +19,6 @@
 
 #define PHY_ID_TJA_1103			0x001BB010
 
-#define PMAPMD_B100T1_PMAPMD_CTL	0x0834
-#define B100T1_PMAPMD_CONFIG_EN		BIT(15)
-#define B100T1_PMAPMD_MASTER		BIT(14)
-#define MASTER_MODE			(B100T1_PMAPMD_CONFIG_EN | \
-					 B100T1_PMAPMD_MASTER)
-#define SLAVE_MODE			(B100T1_PMAPMD_CONFIG_EN)
-
 #define VEND1_DEVICE_CONTROL		0x0040
 #define DEVICE_CONTROL_RESET		BIT(15)
 #define DEVICE_CONTROL_CONFIG_GLOBAL_EN	BIT(14)
@@ -988,72 +981,6 @@ static int nxp_c45_cable_test_get_status(struct phy_device *phydev,
 	return nxp_c45_start_op(phydev);
 }
 
-static int nxp_c45_setup_master_slave(struct phy_device *phydev)
-{
-	switch (phydev->master_slave_set) {
-	case MASTER_SLAVE_CFG_MASTER_FORCE:
-	case MASTER_SLAVE_CFG_MASTER_PREFERRED:
-		phy_write_mmd(phydev, MDIO_MMD_PMAPMD, PMAPMD_B100T1_PMAPMD_CTL,
-			      MASTER_MODE);
-		break;
-	case MASTER_SLAVE_CFG_SLAVE_PREFERRED:
-	case MASTER_SLAVE_CFG_SLAVE_FORCE:
-		phy_write_mmd(phydev, MDIO_MMD_PMAPMD, PMAPMD_B100T1_PMAPMD_CTL,
-			      SLAVE_MODE);
-		break;
-	case MASTER_SLAVE_CFG_UNKNOWN:
-	case MASTER_SLAVE_CFG_UNSUPPORTED:
-		return 0;
-	default:
-		phydev_warn(phydev, "Unsupported Master/Slave mode\n");
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static int nxp_c45_read_master_slave(struct phy_device *phydev)
-{
-	int reg;
-
-	phydev->master_slave_get = MASTER_SLAVE_CFG_UNKNOWN;
-	phydev->master_slave_state = MASTER_SLAVE_STATE_UNKNOWN;
-
-	reg = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, PMAPMD_B100T1_PMAPMD_CTL);
-	if (reg < 0)
-		return reg;
-
-	if (reg & B100T1_PMAPMD_MASTER) {
-		phydev->master_slave_get = MASTER_SLAVE_CFG_MASTER_FORCE;
-		phydev->master_slave_state = MASTER_SLAVE_STATE_MASTER;
-	} else {
-		phydev->master_slave_get = MASTER_SLAVE_CFG_SLAVE_FORCE;
-		phydev->master_slave_state = MASTER_SLAVE_STATE_SLAVE;
-	}
-
-	return 0;
-}
-
-static int nxp_c45_config_aneg(struct phy_device *phydev)
-{
-	return nxp_c45_setup_master_slave(phydev);
-}
-
-static int nxp_c45_read_status(struct phy_device *phydev)
-{
-	int ret;
-
-	ret = genphy_c45_read_status(phydev);
-	if (ret)
-		return ret;
-
-	ret = nxp_c45_read_master_slave(phydev);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
 static int nxp_c45_get_sqi(struct phy_device *phydev)
 {
 	int reg;
@@ -1355,11 +1282,11 @@ static struct phy_driver nxp_c45_driver[] = {
 		.features		= PHY_BASIC_T1_FEATURES,
 		.probe			= nxp_c45_probe,
 		.soft_reset		= nxp_c45_soft_reset,
-		.config_aneg		= nxp_c45_config_aneg,
+		.config_aneg		= genphy_c45_config_aneg,
 		.config_init		= nxp_c45_config_init,
 		.config_intr		= nxp_c45_config_intr,
 		.handle_interrupt	= nxp_c45_handle_interrupt,
-		.read_status		= nxp_c45_read_status,
+		.read_status		= genphy_c45_read_status,
 		.suspend		= genphy_c45_pma_suspend,
 		.resume			= genphy_c45_pma_resume,
 		.get_sset_count		= nxp_c45_get_sset_count,
-- 
GitLab


From 643480a1a73d489a355e908dc317af889ace127a Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:10 +0300
Subject: [PATCH 0723/1806] net: phy: nxp-c45-tja11xx: remove RX BIST frame
 counters

Remove RX BIST frame counters from the PHY statistics.
In production mode, these counters are always read as 0.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230731091619.77961-3-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 41b8af0547e42..f1f15a1b6cfc7 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -81,9 +81,6 @@
 #define VEND1_SYMBOL_ERROR_COUNTER	0x8350
 #define VEND1_LINK_DROP_COUNTER		0x8352
 #define VEND1_LINK_LOSSES_AND_FAILURES	0x8353
-#define VEND1_R_GOOD_FRAME_CNT		0xA950
-#define VEND1_R_BAD_FRAME_CNT		0xA952
-#define VEND1_R_RXER_FRAME_CNT		0xA954
 #define VEND1_RX_PREAMBLE_COUNT		0xAFCE
 #define VEND1_TX_PREAMBLE_COUNT		0xAFCF
 #define VEND1_RX_IPG_LENGTH		0xAFD0
@@ -809,12 +806,6 @@ static const struct nxp_c45_phy_stats nxp_c45_hw_stats[] = {
 		VEND1_LINK_LOSSES_AND_FAILURES, 10, GENMASK(15, 10) },
 	{ "phy_link_failure_cnt", MDIO_MMD_VEND1,
 		VEND1_LINK_LOSSES_AND_FAILURES, 0, GENMASK(9, 0) },
-	{ "r_good_frame_cnt", MDIO_MMD_VEND1,
-		VEND1_R_GOOD_FRAME_CNT, 0, GENMASK(15, 0) },
-	{ "r_bad_frame_cnt", MDIO_MMD_VEND1,
-		VEND1_R_BAD_FRAME_CNT, 0, GENMASK(15, 0) },
-	{ "r_rxer_frame_cnt", MDIO_MMD_VEND1,
-		VEND1_R_RXER_FRAME_CNT, 0, GENMASK(15, 0) },
 	{ "rx_preamble_count", MDIO_MMD_VEND1,
 		VEND1_RX_PREAMBLE_COUNT, 0, GENMASK(5, 0) },
 	{ "tx_preamble_count", MDIO_MMD_VEND1,
-- 
GitLab


From 6c0c85da044e92543a40294f024235f60adc4315 Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:11 +0300
Subject: [PATCH 0724/1806] net: phy: nxp-c45-tja11xx: prepare the ground for
 TJA1120

Between TJA1120 and TJA1103 the hardware was improved, but some register
addresses were changed and some bit fields were moved from one register
to another.

Introduce the nxp_c45_reg_field structure and its associated functions to
abstract the differences between the PHYs.

Remove the defined bits and register addresses that are not common
between TJA1103 and TJA1120 and replace them with reg_fields and
register addresses from phydev->drv->driver_data.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Link: https://lore.kernel.org/r/20230731091619.77961-4-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 574 +++++++++++++++++++++---------
 1 file changed, 406 insertions(+), 168 deletions(-)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index f1f15a1b6cfc7..d5981985b320d 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -41,10 +41,8 @@
 #define SQI_MASK			GENMASK(2, 0)
 #define MAX_SQI				SQI_MASK
 
-#define VEND1_CABLE_TEST		0x8330
 #define CABLE_TEST_ENABLE		BIT(15)
 #define CABLE_TEST_START		BIT(14)
-#define CABLE_TEST_VALID		BIT(13)
 #define CABLE_TEST_OK			0x00
 #define CABLE_TEST_SHORTED		0x01
 #define CABLE_TEST_OPEN			0x02
@@ -89,59 +87,18 @@
 
 #define VEND1_PTP_CONFIG		0x1102
 #define EXT_TRG_EDGE			BIT(1)
-#define PPS_OUT_POL			BIT(2)
-#define PPS_OUT_EN			BIT(3)
 
-#define VEND1_LTC_LOAD_CTRL		0x1105
-#define READ_LTC			BIT(2)
-#define LOAD_LTC			BIT(0)
-
-#define VEND1_LTC_WR_NSEC_0		0x1106
-#define VEND1_LTC_WR_NSEC_1		0x1107
-#define VEND1_LTC_WR_SEC_0		0x1108
-#define VEND1_LTC_WR_SEC_1		0x1109
-
-#define VEND1_LTC_RD_NSEC_0		0x110A
-#define VEND1_LTC_RD_NSEC_1		0x110B
-#define VEND1_LTC_RD_SEC_0		0x110C
-#define VEND1_LTC_RD_SEC_1		0x110D
-
-#define VEND1_RATE_ADJ_SUBNS_0		0x110F
-#define VEND1_RATE_ADJ_SUBNS_1		0x1110
 #define CLK_RATE_ADJ_LD			BIT(15)
 #define CLK_RATE_ADJ_DIR		BIT(14)
 
-#define VEND1_HW_LTC_LOCK_CTRL		0x1115
-#define HW_LTC_LOCK_EN			BIT(0)
-
-#define VEND1_PTP_IRQ_EN		0x1131
-#define VEND1_PTP_IRQ_STATUS		0x1132
-#define PTP_IRQ_EGR_TS			BIT(0)
-
 #define VEND1_RX_TS_INSRT_CTRL		0x114D
-#define RX_TS_INSRT_MODE2		0x02
+#define TJA1103_RX_TS_INSRT_MODE2	0x02
 
 #define VEND1_EGR_RING_DATA_0		0x114E
-#define VEND1_EGR_RING_DATA_1_SEQ_ID	0x114F
-#define VEND1_EGR_RING_DATA_2_NSEC_15_0	0x1150
-#define VEND1_EGR_RING_DATA_3		0x1151
 #define VEND1_EGR_RING_CTRL		0x1154
 
-#define VEND1_EXT_TRG_TS_DATA_0		0x1121
-#define VEND1_EXT_TRG_TS_DATA_1		0x1122
-#define VEND1_EXT_TRG_TS_DATA_2		0x1123
-#define VEND1_EXT_TRG_TS_DATA_3		0x1124
-#define VEND1_EXT_TRG_TS_DATA_4		0x1125
-#define VEND1_EXT_TRG_TS_CTRL		0x1126
-
-#define RING_DATA_0_DOMAIN_NUMBER	GENMASK(7, 0)
-#define RING_DATA_0_MSG_TYPE		GENMASK(11, 8)
-#define RING_DATA_0_SEC_4_2		GENMASK(14, 2)
 #define RING_DATA_0_TS_VALID		BIT(15)
 
-#define RING_DATA_3_NSEC_29_16		GENMASK(13, 0)
-#define RING_DATA_3_SEC_1_0		GENMASK(15, 14)
-#define RING_DATA_5_SEC_16_5		GENMASK(15, 4)
 #define RING_DONE			BIT(0)
 
 #define TS_SEC_MASK			GENMASK(1, 0)
@@ -152,18 +109,11 @@
 #define VEND1_PORT_PTP_CONTROL		0x9000
 #define PORT_PTP_CONTROL_BYPASS		BIT(11)
 
-#define VEND1_PTP_CLK_PERIOD		0x1104
 #define PTP_CLK_PERIOD_100BT1		15ULL
 
-#define VEND1_EVENT_MSG_FILT		0x1148
 #define EVENT_MSG_FILT_ALL		0x0F
 #define EVENT_MSG_FILT_NONE		0x00
 
-#define VEND1_TX_PIPE_DLY_NS		0x1149
-#define VEND1_TX_PIPEDLY_SUBNS		0x114A
-#define VEND1_RX_PIPE_DLY_NS		0x114B
-#define VEND1_RX_PIPEDLY_SUBNS		0x114C
-
 #define VEND1_GPIO_FUNC_CONFIG_BASE	0x2C40
 #define GPIO_FUNC_EN			BIT(15)
 #define GPIO_FUNC_PTP			BIT(6)
@@ -181,8 +131,8 @@
 #define MAX_ID_PS			2260U
 #define DEFAULT_ID_PS			2000U
 
-#define PPM_TO_SUBNS_INC(ppb)	div_u64(GENMASK_ULL(31, 0) * (ppb) * \
-					PTP_CLK_PERIOD_100BT1, NSEC_PER_SEC)
+#define PPM_TO_SUBNS_INC(ppb, ptp_clk_period) div_u64(GENMASK_ULL(31, 0) * \
+	(ppb) * (ptp_clk_period), NSEC_PER_SEC)
 
 #define NXP_C45_SKB_CB(skb)	((struct nxp_c45_skb_cb *)(skb)->cb)
 
@@ -191,6 +141,21 @@ struct nxp_c45_skb_cb {
 	unsigned int type;
 };
 
+#define NXP_C45_REG_FIELD(_reg, _devad, _offset, _size)	\
+	((struct nxp_c45_reg_field) {			\
+		.reg = _reg,				\
+		.devad =  _devad,			\
+		.offset = _offset,			\
+		.size = _size,				\
+	})
+
+struct nxp_c45_reg_field {
+	u16 reg;
+	u8 devad;
+	u8 offset;
+	u8 size;
+};
+
 struct nxp_c45_hwts {
 	u32	nsec;
 	u32	sec;
@@ -199,7 +164,69 @@ struct nxp_c45_hwts {
 	u8	msg_type;
 };
 
+struct nxp_c45_regmap {
+	/* PTP config regs. */
+	u16 vend1_ptp_clk_period;
+	u16 vend1_event_msg_filt;
+
+	/* LTC bits and regs. */
+	struct nxp_c45_reg_field ltc_read;
+	struct nxp_c45_reg_field ltc_write;
+	struct nxp_c45_reg_field ltc_lock_ctrl;
+	u16 vend1_ltc_wr_nsec_0;
+	u16 vend1_ltc_wr_nsec_1;
+	u16 vend1_ltc_wr_sec_0;
+	u16 vend1_ltc_wr_sec_1;
+	u16 vend1_ltc_rd_nsec_0;
+	u16 vend1_ltc_rd_nsec_1;
+	u16 vend1_ltc_rd_sec_0;
+	u16 vend1_ltc_rd_sec_1;
+	u16 vend1_rate_adj_subns_0;
+	u16 vend1_rate_adj_subns_1;
+
+	/* External trigger reg fields. */
+	struct nxp_c45_reg_field irq_egr_ts_en;
+	struct nxp_c45_reg_field irq_egr_ts_status;
+	struct nxp_c45_reg_field domain_number;
+	struct nxp_c45_reg_field msg_type;
+	struct nxp_c45_reg_field sequence_id;
+	struct nxp_c45_reg_field sec_1_0;
+	struct nxp_c45_reg_field sec_4_2;
+	struct nxp_c45_reg_field nsec_15_0;
+	struct nxp_c45_reg_field nsec_29_16;
+
+	/* PPS and EXT Trigger bits and regs. */
+	struct nxp_c45_reg_field pps_enable;
+	struct nxp_c45_reg_field pps_polarity;
+	u16 vend1_ext_trg_data_0;
+	u16 vend1_ext_trg_data_1;
+	u16 vend1_ext_trg_data_2;
+	u16 vend1_ext_trg_data_3;
+	u16 vend1_ext_trg_ctrl;
+
+	/* Cable test reg fields. */
+	u16 cable_test;
+	struct nxp_c45_reg_field cable_test_valid;
+	struct nxp_c45_reg_field cable_test_result;
+};
+
+struct nxp_c45_phy_stats {
+	const char	*name;
+	const struct nxp_c45_reg_field counter;
+};
+
+struct nxp_c45_phy_data {
+	const struct nxp_c45_regmap *regmap;
+	const struct nxp_c45_phy_stats *stats;
+	int n_stats;
+	u8 ptp_clk_period;
+	void (*counters_enable)(struct phy_device *phydev);
+	void (*ptp_init)(struct phy_device *phydev);
+	void (*ptp_enable)(struct phy_device *phydev, bool enable);
+};
+
 struct nxp_c45_phy {
+	const struct nxp_c45_phy_data *phy_data;
 	struct phy_device *phydev;
 	struct mii_timestamper mii_ts;
 	struct ptp_clock *ptp_clock;
@@ -217,13 +244,86 @@ struct nxp_c45_phy {
 	bool extts;
 };
 
-struct nxp_c45_phy_stats {
-	const char	*name;
-	u8		mmd;
-	u16		reg;
-	u8		off;
-	u16		mask;
-};
+static const
+struct nxp_c45_phy_data *nxp_c45_get_data(struct phy_device *phydev)
+{
+	return phydev->drv->driver_data;
+}
+
+static const
+struct nxp_c45_regmap *nxp_c45_get_regmap(struct phy_device *phydev)
+{
+	const struct nxp_c45_phy_data *phy_data = nxp_c45_get_data(phydev);
+
+	return phy_data->regmap;
+}
+
+static int nxp_c45_read_reg_field(struct phy_device *phydev,
+				  const struct nxp_c45_reg_field *reg_field)
+{
+	u16 mask;
+	int ret;
+
+	if (reg_field->size == 0) {
+		phydev_err(phydev, "Trying to read a reg field of size 0.\n");
+		return -EINVAL;
+	}
+
+	ret = phy_read_mmd(phydev, reg_field->devad, reg_field->reg);
+	if (ret < 0)
+		return ret;
+
+	mask = reg_field->size == 1 ? BIT(reg_field->offset) :
+		GENMASK(reg_field->offset + reg_field->size - 1,
+			reg_field->offset);
+	ret &= mask;
+	ret >>= reg_field->offset;
+
+	return ret;
+}
+
+static int nxp_c45_write_reg_field(struct phy_device *phydev,
+				   const struct nxp_c45_reg_field *reg_field,
+				   u16 val)
+{
+	u16 mask;
+	u16 set;
+
+	if (reg_field->size == 0) {
+		phydev_err(phydev, "Trying to write a reg field of size 0.\n");
+		return -EINVAL;
+	}
+
+	mask = reg_field->size == 1 ? BIT(reg_field->offset) :
+		GENMASK(reg_field->offset + reg_field->size - 1,
+			reg_field->offset);
+	set = val << reg_field->offset;
+
+	return phy_modify_mmd_changed(phydev, reg_field->devad,
+				      reg_field->reg, mask, set);
+}
+
+static int nxp_c45_set_reg_field(struct phy_device *phydev,
+				 const struct nxp_c45_reg_field *reg_field)
+{
+	if (reg_field->size != 1) {
+		phydev_err(phydev, "Trying to set a reg field of size different than 1.\n");
+		return -EINVAL;
+	}
+
+	return nxp_c45_write_reg_field(phydev, reg_field, 1);
+}
+
+static int nxp_c45_clear_reg_field(struct phy_device *phydev,
+				   const struct nxp_c45_reg_field *reg_field)
+{
+	if (reg_field->size != 1) {
+		phydev_err(phydev, "Trying to set a reg field of size different than 1.\n");
+		return -EINVAL;
+	}
+
+	return nxp_c45_write_reg_field(phydev, reg_field, 0);
+}
 
 static bool nxp_c45_poll_txts(struct phy_device *phydev)
 {
@@ -235,17 +335,17 @@ static int _nxp_c45_ptp_gettimex64(struct ptp_clock_info *ptp,
 				   struct ptp_system_timestamp *sts)
 {
 	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(priv->phydev);
 
-	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_LOAD_CTRL,
-		      READ_LTC);
+	nxp_c45_set_reg_field(priv->phydev, &regmap->ltc_read);
 	ts->tv_nsec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
-				   VEND1_LTC_RD_NSEC_0);
+				   regmap->vend1_ltc_rd_nsec_0);
 	ts->tv_nsec |= phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
-				    VEND1_LTC_RD_NSEC_1) << 16;
+				    regmap->vend1_ltc_rd_nsec_1) << 16;
 	ts->tv_sec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
-				  VEND1_LTC_RD_SEC_0);
+				  regmap->vend1_ltc_rd_sec_0);
 	ts->tv_sec |= phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
-				   VEND1_LTC_RD_SEC_1) << 16;
+				   regmap->vend1_ltc_rd_sec_1) << 16;
 
 	return 0;
 }
@@ -267,17 +367,17 @@ static int _nxp_c45_ptp_settime64(struct ptp_clock_info *ptp,
 				  const struct timespec64 *ts)
 {
 	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(priv->phydev);
 
-	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_NSEC_0,
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, regmap->vend1_ltc_wr_nsec_0,
 		      ts->tv_nsec);
-	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_NSEC_1,
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, regmap->vend1_ltc_wr_nsec_1,
 		      ts->tv_nsec >> 16);
-	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_SEC_0,
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, regmap->vend1_ltc_wr_sec_0,
 		      ts->tv_sec);
-	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_SEC_1,
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, regmap->vend1_ltc_wr_sec_1,
 		      ts->tv_sec >> 16);
-	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_LOAD_CTRL,
-		      LOAD_LTC);
+	nxp_c45_set_reg_field(priv->phydev, &regmap->ltc_write);
 
 	return 0;
 }
@@ -297,6 +397,8 @@ static int nxp_c45_ptp_settime64(struct ptp_clock_info *ptp,
 static int nxp_c45_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 {
 	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+	const struct nxp_c45_phy_data *data = nxp_c45_get_data(priv->phydev);
+	const struct nxp_c45_regmap *regmap = data->regmap;
 	s32 ppb = scaled_ppm_to_ppb(scaled_ppm);
 	u64 subns_inc_val;
 	bool inc;
@@ -305,16 +407,18 @@ static int nxp_c45_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	inc = ppb >= 0;
 	ppb = abs(ppb);
 
-	subns_inc_val = PPM_TO_SUBNS_INC(ppb);
+	subns_inc_val = PPM_TO_SUBNS_INC(ppb, data->ptp_clk_period);
 
-	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_RATE_ADJ_SUBNS_0,
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1,
+		      regmap->vend1_rate_adj_subns_0,
 		      subns_inc_val);
 	subns_inc_val >>= 16;
 	subns_inc_val |= CLK_RATE_ADJ_LD;
 	if (inc)
 		subns_inc_val |= CLK_RATE_ADJ_DIR;
 
-	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_RATE_ADJ_SUBNS_1,
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1,
+		      regmap->vend1_rate_adj_subns_1,
 		      subns_inc_val);
 	mutex_unlock(&priv->ptp_lock);
 
@@ -358,21 +462,25 @@ static bool nxp_c45_match_ts(struct ptp_header *header,
 static void nxp_c45_get_extts(struct nxp_c45_phy *priv,
 			      struct timespec64 *extts)
 {
+	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(priv->phydev);
+
 	extts->tv_nsec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
-				      VEND1_EXT_TRG_TS_DATA_0);
+				      regmap->vend1_ext_trg_data_0);
 	extts->tv_nsec |= phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
-				       VEND1_EXT_TRG_TS_DATA_1) << 16;
+				       regmap->vend1_ext_trg_data_1) << 16;
 	extts->tv_sec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
-				     VEND1_EXT_TRG_TS_DATA_2);
+				     regmap->vend1_ext_trg_data_2);
 	extts->tv_sec |= phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
-				      VEND1_EXT_TRG_TS_DATA_3) << 16;
-	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EXT_TRG_TS_CTRL,
-		      RING_DONE);
+				      regmap->vend1_ext_trg_data_3) << 16;
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1,
+		      regmap->vend1_ext_trg_ctrl, RING_DONE);
 }
 
 static bool nxp_c45_get_hwtxts(struct nxp_c45_phy *priv,
 			       struct nxp_c45_hwts *hwts)
 {
+	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(priv->phydev);
+	struct phy_device *phydev = priv->phydev;
 	bool valid;
 	u16 reg;
 
@@ -384,16 +492,18 @@ static bool nxp_c45_get_hwtxts(struct nxp_c45_phy *priv,
 	if (!valid)
 		goto nxp_c45_get_hwtxts_out;
 
-	hwts->domain_number = reg;
-	hwts->msg_type = (reg & RING_DATA_0_MSG_TYPE) >> 8;
-	hwts->sec = (reg & RING_DATA_0_SEC_4_2) >> 10;
-	hwts->sequence_id = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
-					 VEND1_EGR_RING_DATA_1_SEQ_ID);
-	hwts->nsec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
-				  VEND1_EGR_RING_DATA_2_NSEC_15_0);
-	reg = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_DATA_3);
-	hwts->nsec |= (reg & RING_DATA_3_NSEC_29_16) << 16;
-	hwts->sec |= (reg & RING_DATA_3_SEC_1_0) >> 14;
+	hwts->domain_number =
+		nxp_c45_read_reg_field(phydev, &regmap->domain_number);
+	hwts->msg_type =
+		nxp_c45_read_reg_field(phydev, &regmap->msg_type);
+	hwts->sequence_id =
+		nxp_c45_read_reg_field(phydev, &regmap->sequence_id);
+	hwts->nsec =
+		nxp_c45_read_reg_field(phydev, &regmap->nsec_15_0);
+	hwts->nsec |=
+		nxp_c45_read_reg_field(phydev, &regmap->nsec_29_16) << 16;
+	hwts->sec = nxp_c45_read_reg_field(phydev, &regmap->sec_1_0);
+	hwts->sec |= nxp_c45_read_reg_field(phydev, &regmap->sec_4_2) << 2;
 
 nxp_c45_get_hwtxts_out:
 	mutex_unlock(&priv->ptp_lock);
@@ -498,6 +608,7 @@ static void nxp_c45_gpio_config(struct nxp_c45_phy *priv,
 static int nxp_c45_perout_enable(struct nxp_c45_phy *priv,
 				 struct ptp_perout_request *perout, int on)
 {
+	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(priv->phydev);
 	struct phy_device *phydev = priv->phydev;
 	int pin;
 
@@ -509,10 +620,10 @@ static int nxp_c45_perout_enable(struct nxp_c45_phy *priv,
 		return pin;
 
 	if (!on) {
-		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PTP_CONFIG,
-				   PPS_OUT_EN);
-		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PTP_CONFIG,
-				   PPS_OUT_POL);
+		nxp_c45_clear_reg_field(priv->phydev,
+					&regmap->pps_enable);
+		nxp_c45_clear_reg_field(priv->phydev,
+					&regmap->pps_polarity);
 
 		nxp_c45_gpio_config(priv, pin, GPIO_DISABLE);
 
@@ -541,16 +652,16 @@ static int nxp_c45_perout_enable(struct nxp_c45_phy *priv,
 		}
 
 		if (perout->phase.nsec == 0)
-			phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
-					   VEND1_PTP_CONFIG, PPS_OUT_POL);
+			nxp_c45_clear_reg_field(priv->phydev,
+						&regmap->pps_polarity);
 		else
-			phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
-					 VEND1_PTP_CONFIG, PPS_OUT_POL);
+			nxp_c45_set_reg_field(priv->phydev,
+					      &regmap->pps_polarity);
 	}
 
 	nxp_c45_gpio_config(priv, pin, GPIO_PPS_OUT_CFG);
 
-	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PTP_CONFIG, PPS_OUT_EN);
+	nxp_c45_set_reg_field(priv->phydev, &regmap->pps_enable);
 
 	return 0;
 }
@@ -725,6 +836,7 @@ static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts,
 	struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy,
 						mii_ts);
 	struct phy_device *phydev = priv->phydev;
+	const struct nxp_c45_phy_data *data;
 	struct hwtstamp_config cfg;
 
 	if (copy_from_user(&cfg, ifreq->ifr_data, sizeof(cfg)))
@@ -733,6 +845,7 @@ static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts,
 	if (cfg.tx_type < 0 || cfg.tx_type > HWTSTAMP_TX_ON)
 		return -ERANGE;
 
+	data = nxp_c45_get_data(phydev);
 	priv->hwts_tx = cfg.tx_type;
 
 	switch (cfg.rx_filter) {
@@ -750,27 +863,24 @@ static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts,
 	}
 
 	if (priv->hwts_rx || priv->hwts_tx) {
-		phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_EVENT_MSG_FILT,
+		phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			      data->regmap->vend1_event_msg_filt,
 			      EVENT_MSG_FILT_ALL);
-		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
-				   VEND1_PORT_PTP_CONTROL,
-				   PORT_PTP_CONTROL_BYPASS);
+		data->ptp_enable(phydev, true);
 	} else {
-		phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_EVENT_MSG_FILT,
+		phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			      data->regmap->vend1_event_msg_filt,
 			      EVENT_MSG_FILT_NONE);
-		phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_PTP_CONTROL,
-				 PORT_PTP_CONTROL_BYPASS);
+		data->ptp_enable(phydev, false);
 	}
 
 	if (nxp_c45_poll_txts(priv->phydev))
 		goto nxp_c45_no_ptp_irq;
 
 	if (priv->hwts_tx)
-		phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
-				 VEND1_PTP_IRQ_EN, PTP_IRQ_EGR_TS);
+		nxp_c45_set_reg_field(phydev, &data->regmap->irq_egr_ts_en);
 	else
-		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
-				   VEND1_PTP_IRQ_EN, PTP_IRQ_EGR_TS);
+		nxp_c45_clear_reg_field(phydev, &data->regmap->irq_egr_ts_en);
 
 nxp_c45_no_ptp_irq:
 	return copy_to_user(ifreq->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
@@ -795,57 +905,79 @@ static int nxp_c45_ts_info(struct mii_timestamper *mii_ts,
 	return 0;
 }
 
-static const struct nxp_c45_phy_stats nxp_c45_hw_stats[] = {
-	{ "phy_symbol_error_cnt", MDIO_MMD_VEND1,
-		VEND1_SYMBOL_ERROR_COUNTER, 0, GENMASK(15, 0) },
-	{ "phy_link_status_drop_cnt", MDIO_MMD_VEND1,
-		VEND1_LINK_DROP_COUNTER, 8, GENMASK(13, 8) },
-	{ "phy_link_availability_drop_cnt", MDIO_MMD_VEND1,
-		VEND1_LINK_DROP_COUNTER, 0, GENMASK(5, 0) },
-	{ "phy_link_loss_cnt", MDIO_MMD_VEND1,
-		VEND1_LINK_LOSSES_AND_FAILURES, 10, GENMASK(15, 10) },
-	{ "phy_link_failure_cnt", MDIO_MMD_VEND1,
-		VEND1_LINK_LOSSES_AND_FAILURES, 0, GENMASK(9, 0) },
-	{ "rx_preamble_count", MDIO_MMD_VEND1,
-		VEND1_RX_PREAMBLE_COUNT, 0, GENMASK(5, 0) },
-	{ "tx_preamble_count", MDIO_MMD_VEND1,
-		VEND1_TX_PREAMBLE_COUNT, 0, GENMASK(5, 0) },
-	{ "rx_ipg_length", MDIO_MMD_VEND1,
-		VEND1_RX_IPG_LENGTH, 0, GENMASK(8, 0) },
-	{ "tx_ipg_length", MDIO_MMD_VEND1,
-		VEND1_TX_IPG_LENGTH, 0, GENMASK(8, 0) },
+static const struct nxp_c45_phy_stats common_hw_stats[] = {
+	{ "phy_link_status_drop_cnt",
+		NXP_C45_REG_FIELD(0x8352, MDIO_MMD_VEND1, 8, 6), },
+	{ "phy_link_availability_drop_cnt",
+		NXP_C45_REG_FIELD(0x8352, MDIO_MMD_VEND1, 0, 6), },
+	{ "phy_link_loss_cnt",
+		NXP_C45_REG_FIELD(0x8353, MDIO_MMD_VEND1, 10, 6), },
+	{ "phy_link_failure_cnt",
+		NXP_C45_REG_FIELD(0x8353, MDIO_MMD_VEND1, 0, 10), },
+	{ "phy_symbol_error_cnt",
+		NXP_C45_REG_FIELD(0x8350, MDIO_MMD_VEND1, 0, 16) },
+};
+
+static const struct nxp_c45_phy_stats tja1103_hw_stats[] = {
+	{ "rx_preamble_count",
+		NXP_C45_REG_FIELD(0xAFCE, MDIO_MMD_VEND1, 0, 6), },
+	{ "tx_preamble_count",
+		NXP_C45_REG_FIELD(0xAFCF, MDIO_MMD_VEND1, 0, 6), },
+	{ "rx_ipg_length",
+		NXP_C45_REG_FIELD(0xAFD0, MDIO_MMD_VEND1, 0, 9), },
+	{ "tx_ipg_length",
+		NXP_C45_REG_FIELD(0xAFD1, MDIO_MMD_VEND1, 0, 9), },
 };
 
 static int nxp_c45_get_sset_count(struct phy_device *phydev)
 {
-	return ARRAY_SIZE(nxp_c45_hw_stats);
+	const struct nxp_c45_phy_data *phy_data = nxp_c45_get_data(phydev);
+
+	return ARRAY_SIZE(common_hw_stats) + (phy_data ? phy_data->n_stats : 0);
 }
 
 static void nxp_c45_get_strings(struct phy_device *phydev, u8 *data)
 {
+	const struct nxp_c45_phy_data *phy_data = nxp_c45_get_data(phydev);
+	size_t count = nxp_c45_get_sset_count(phydev);
+	size_t idx;
 	size_t i;
 
-	for (i = 0; i < ARRAY_SIZE(nxp_c45_hw_stats); i++) {
-		strncpy(data + i * ETH_GSTRING_LEN,
-			nxp_c45_hw_stats[i].name, ETH_GSTRING_LEN);
+	for (i = 0; i < count; i++) {
+		if (i < ARRAY_SIZE(common_hw_stats)) {
+			strscpy(data + i * ETH_GSTRING_LEN,
+				common_hw_stats[i].name, ETH_GSTRING_LEN);
+			continue;
+		}
+		idx = i - ARRAY_SIZE(common_hw_stats);
+		strscpy(data + i * ETH_GSTRING_LEN,
+			phy_data->stats[idx].name, ETH_GSTRING_LEN);
 	}
 }
 
 static void nxp_c45_get_stats(struct phy_device *phydev,
 			      struct ethtool_stats *stats, u64 *data)
 {
+	const struct nxp_c45_phy_data *phy_data = nxp_c45_get_data(phydev);
+	size_t count = nxp_c45_get_sset_count(phydev);
+	const struct nxp_c45_reg_field *reg_field;
+	size_t idx;
 	size_t i;
 	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(nxp_c45_hw_stats); i++) {
-		ret = phy_read_mmd(phydev, nxp_c45_hw_stats[i].mmd,
-				   nxp_c45_hw_stats[i].reg);
-		if (ret < 0) {
-			data[i] = U64_MAX;
+	for (i = 0; i < count; i++) {
+		if (i < ARRAY_SIZE(common_hw_stats)) {
+			reg_field = &common_hw_stats[i].counter;
 		} else {
-			data[i] = ret & nxp_c45_hw_stats[i].mask;
-			data[i] >>= nxp_c45_hw_stats[i].off;
+			idx = i - ARRAY_SIZE(common_hw_stats);
+			reg_field = &phy_data->stats[idx].counter;
 		}
+
+		ret = nxp_c45_read_reg_field(phydev, reg_field);
+		if (ret < 0)
+			data[i] = U64_MAX;
+		else
+			data[i] = ret;
 	}
 }
 
@@ -884,6 +1016,7 @@ static int nxp_c45_config_intr(struct phy_device *phydev)
 
 static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev)
 {
+	const struct nxp_c45_phy_data *data = nxp_c45_get_data(phydev);
 	struct nxp_c45_phy *priv = phydev->priv;
 	irqreturn_t ret = IRQ_NONE;
 	struct nxp_c45_hwts hwts;
@@ -901,8 +1034,8 @@ static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev)
 	 * The irq signal will be asserted until the EGR TS FIFO will be
 	 * emptied.
 	 */
-	irq = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_PTP_IRQ_STATUS);
-	if (irq & PTP_IRQ_EGR_TS) {
+	irq = nxp_c45_read_reg_field(phydev, &data->regmap->irq_egr_ts_status);
+	if (irq) {
 		while (nxp_c45_get_hwtxts(priv, &hwts))
 			nxp_c45_process_txts(priv, &hwts);
 
@@ -929,24 +1062,28 @@ static int nxp_c45_soft_reset(struct phy_device *phydev)
 
 static int nxp_c45_cable_test_start(struct phy_device *phydev)
 {
-	return phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_CABLE_TEST,
-			     CABLE_TEST_ENABLE | CABLE_TEST_START);
+	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(phydev);
+
+	return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, regmap->cable_test,
+				CABLE_TEST_ENABLE | CABLE_TEST_START);
 }
 
 static int nxp_c45_cable_test_get_status(struct phy_device *phydev,
 					 bool *finished)
 {
+	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(phydev);
 	int ret;
 	u8 cable_test_result;
 
-	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_CABLE_TEST);
-	if (!(ret & CABLE_TEST_VALID)) {
+	ret = nxp_c45_read_reg_field(phydev, &regmap->cable_test_valid);
+	if (!ret) {
 		*finished = false;
 		return 0;
 	}
 
 	*finished = true;
-	cable_test_result = ret & GENMASK(2, 0);
+	cable_test_result = nxp_c45_read_reg_field(phydev,
+						   &regmap->cable_test_result);
 
 	switch (cable_test_result) {
 	case CABLE_TEST_OK:
@@ -966,7 +1103,7 @@ static int nxp_c45_cable_test_get_status(struct phy_device *phydev,
 					ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC);
 	}
 
-	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_CABLE_TEST,
+	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, regmap->cable_test,
 			   CABLE_TEST_ENABLE);
 
 	return nxp_c45_start_op(phydev);
@@ -1005,6 +1142,28 @@ static int nxp_c45_check_delay(struct phy_device *phydev, u32 delay)
 	return 0;
 }
 
+static void nxp_c45_counters_enable(struct phy_device *phydev)
+{
+	const struct nxp_c45_phy_data *data = nxp_c45_get_data(phydev);
+
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_LINK_DROP_COUNTER,
+			 COUNTER_EN);
+
+	data->counters_enable(phydev);
+}
+
+static void nxp_c45_ptp_init(struct phy_device *phydev)
+{
+	const struct nxp_c45_phy_data *data = nxp_c45_get_data(phydev);
+
+	phy_write_mmd(phydev, MDIO_MMD_VEND1,
+		      data->regmap->vend1_ptp_clk_period,
+		      data->ptp_clk_period);
+	nxp_c45_clear_reg_field(phydev, &data->regmap->ltc_lock_ctrl);
+
+	data->ptp_init(phydev);
+}
+
 static u64 nxp_c45_get_phase_shift(u64 phase_offset_raw)
 {
 	/* The delay in degree phase is 73.8 + phase_offset_raw * 0.9.
@@ -1182,31 +1341,14 @@ static int nxp_c45_config_init(struct phy_device *phydev)
 	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PHY_CONFIG,
 			 PHY_CONFIG_AUTO);
 
-	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_LINK_DROP_COUNTER,
-			 COUNTER_EN);
-	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_RX_PREAMBLE_COUNT,
-			 COUNTER_EN);
-	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_TX_PREAMBLE_COUNT,
-			 COUNTER_EN);
-	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_RX_IPG_LENGTH,
-			 COUNTER_EN);
-	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_TX_IPG_LENGTH,
-			 COUNTER_EN);
-
 	ret = nxp_c45_set_phy_mode(phydev);
 	if (ret)
 		return ret;
 
 	phydev->autoneg = AUTONEG_DISABLE;
 
-	phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_PTP_CLK_PERIOD,
-		      PTP_CLK_PERIOD_100BT1);
-	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_HW_LTC_LOCK_CTRL,
-			   HW_LTC_LOCK_EN);
-	phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_RX_TS_INSRT_CTRL,
-		      RX_TS_INSRT_MODE2);
-	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_FUNC_ENABLES,
-			 PTP_ENABLE);
+	nxp_c45_counters_enable(phydev);
+	nxp_c45_ptp_init(phydev);
 
 	return nxp_c45_start_op(phydev);
 }
@@ -1266,11 +1408,107 @@ static void nxp_c45_remove(struct phy_device *phydev)
 	skb_queue_purge(&priv->rx_queue);
 }
 
+static void tja1103_counters_enable(struct phy_device *phydev)
+{
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_RX_PREAMBLE_COUNT,
+			 COUNTER_EN);
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_TX_PREAMBLE_COUNT,
+			 COUNTER_EN);
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_RX_IPG_LENGTH,
+			 COUNTER_EN);
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_TX_IPG_LENGTH,
+			 COUNTER_EN);
+}
+
+static void tja1103_ptp_init(struct phy_device *phydev)
+{
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_RX_TS_INSRT_CTRL,
+		      TJA1103_RX_TS_INSRT_MODE2);
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_FUNC_ENABLES,
+			 PTP_ENABLE);
+}
+
+static void tja1103_ptp_enable(struct phy_device *phydev, bool enable)
+{
+	if (enable)
+		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				   VEND1_PORT_PTP_CONTROL,
+				   PORT_PTP_CONTROL_BYPASS);
+	else
+		phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 VEND1_PORT_PTP_CONTROL,
+				 PORT_PTP_CONTROL_BYPASS);
+}
+
+static const struct nxp_c45_regmap tja1103_regmap = {
+	.vend1_ptp_clk_period	= 0x1104,
+	.vend1_event_msg_filt	= 0x1148,
+	.pps_enable		=
+		NXP_C45_REG_FIELD(0x1102, MDIO_MMD_VEND1, 3, 1),
+	.pps_polarity		=
+		NXP_C45_REG_FIELD(0x1102, MDIO_MMD_VEND1, 2, 1),
+	.ltc_lock_ctrl		=
+		NXP_C45_REG_FIELD(0x1115, MDIO_MMD_VEND1, 0, 1),
+	.ltc_read		=
+		NXP_C45_REG_FIELD(0x1105, MDIO_MMD_VEND1, 2, 1),
+	.ltc_write		=
+		NXP_C45_REG_FIELD(0x1105, MDIO_MMD_VEND1, 0, 1),
+	.vend1_ltc_wr_nsec_0	= 0x1106,
+	.vend1_ltc_wr_nsec_1	= 0x1107,
+	.vend1_ltc_wr_sec_0	= 0x1108,
+	.vend1_ltc_wr_sec_1	= 0x1109,
+	.vend1_ltc_rd_nsec_0	= 0x110A,
+	.vend1_ltc_rd_nsec_1	= 0x110B,
+	.vend1_ltc_rd_sec_0	= 0x110C,
+	.vend1_ltc_rd_sec_1	= 0x110D,
+	.vend1_rate_adj_subns_0	= 0x110F,
+	.vend1_rate_adj_subns_1	= 0x1110,
+	.irq_egr_ts_en		=
+		NXP_C45_REG_FIELD(0x1131, MDIO_MMD_VEND1, 0, 1),
+	.irq_egr_ts_status	=
+		NXP_C45_REG_FIELD(0x1132, MDIO_MMD_VEND1, 0, 1),
+	.domain_number		=
+		NXP_C45_REG_FIELD(0x114E, MDIO_MMD_VEND1, 0, 8),
+	.msg_type		=
+		NXP_C45_REG_FIELD(0x114E, MDIO_MMD_VEND1, 8, 4),
+	.sequence_id		=
+		NXP_C45_REG_FIELD(0x114F, MDIO_MMD_VEND1, 0, 16),
+	.sec_1_0		=
+		NXP_C45_REG_FIELD(0x1151, MDIO_MMD_VEND1, 14, 2),
+	.sec_4_2		=
+		NXP_C45_REG_FIELD(0x114E, MDIO_MMD_VEND1, 12, 3),
+	.nsec_15_0		=
+		NXP_C45_REG_FIELD(0x1150, MDIO_MMD_VEND1, 0, 16),
+	.nsec_29_16		=
+		NXP_C45_REG_FIELD(0x1151, MDIO_MMD_VEND1, 0, 14),
+	.vend1_ext_trg_data_0	= 0x1121,
+	.vend1_ext_trg_data_1	= 0x1122,
+	.vend1_ext_trg_data_2	= 0x1123,
+	.vend1_ext_trg_data_3	= 0x1124,
+	.vend1_ext_trg_ctrl	= 0x1126,
+	.cable_test		= 0x8330,
+	.cable_test_valid	=
+		NXP_C45_REG_FIELD(0x8330, MDIO_MMD_VEND1, 13, 1),
+	.cable_test_result	=
+		NXP_C45_REG_FIELD(0x8330, MDIO_MMD_VEND1, 0, 3),
+};
+
+static const struct nxp_c45_phy_data tja1103_phy_data = {
+	.regmap = &tja1103_regmap,
+	.stats = tja1103_hw_stats,
+	.n_stats = ARRAY_SIZE(tja1103_hw_stats),
+	.ptp_clk_period = PTP_CLK_PERIOD_100BT1,
+	.counters_enable = tja1103_counters_enable,
+	.ptp_init = tja1103_ptp_init,
+	.ptp_enable = tja1103_ptp_enable,
+};
+
 static struct phy_driver nxp_c45_driver[] = {
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103),
 		.name			= "NXP C45 TJA1103",
 		.features		= PHY_BASIC_T1_FEATURES,
+		.driver_data		= &tja1103_phy_data,
 		.probe			= nxp_c45_probe,
 		.soft_reset		= nxp_c45_soft_reset,
 		.config_aneg		= genphy_c45_config_aneg,
-- 
GitLab


From 369da333569eb82c9ce5e63f5f224c7416b251b6 Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:12 +0300
Subject: [PATCH 0725/1806] net: phy: nxp-c45-tja11xx: use get_features

PHY_BASIC_T1_FEATURES are not the right features supported by TJA1103
anymore.
For example ethtool reports:
	[root@alarm ~]# ethtool end0
	Settings for end0:
	        Supported ports: [ TP ]
	        Supported link modes:   100baseT1/Full
	                                10baseT1L/Full

10baseT1L/Full is not supported by TJA1103 and supported ports list is
not completed. The PHY also have a MII port.

genphy_c45_pma_read_abilities implementation can detect the PHY features
and they look like this.
[root@alarm ~]# ethtool end0
Settings for end0:
        Supported ports: [ TP    MII ]
        Supported link modes:   100baseT1/Full
        Supported pause frame use: Symmetric
        Supports auto-negotiation: No
        Supported FEC modes: Not reported
        Advertised link modes:  100baseT1/Full
        Advertised pause frame use: Symmetric
        Advertised auto-negotiation: No
        Advertised FEC modes: Not reported
        Speed: 100Mb/s
        Duplex: Full
        Auto-negotiation: off
        master-slave cfg: forced master
        master-slave status: master
        Port: Twisted Pair
        PHYAD: 1
        Transceiver: external
        MDI-X: Unknown
        Supports Wake-on: g
        Wake-on: d
        Link detected: yes
        SQI: 7/7

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230731091619.77961-5-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index d5981985b320d..573083f0550f2 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -1353,6 +1353,14 @@ static int nxp_c45_config_init(struct phy_device *phydev)
 	return nxp_c45_start_op(phydev);
 }
 
+static int nxp_c45_get_features(struct phy_device *phydev)
+{
+	linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, phydev->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, phydev->supported);
+
+	return genphy_c45_pma_read_abilities(phydev);
+}
+
 static int nxp_c45_probe(struct phy_device *phydev)
 {
 	struct nxp_c45_phy *priv;
@@ -1507,7 +1515,7 @@ static struct phy_driver nxp_c45_driver[] = {
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103),
 		.name			= "NXP C45 TJA1103",
-		.features		= PHY_BASIC_T1_FEATURES,
+		.get_features		= nxp_c45_get_features,
 		.driver_data		= &tja1103_phy_data,
 		.probe			= nxp_c45_probe,
 		.soft_reset		= nxp_c45_soft_reset,
-- 
GitLab


From f1fe5dff2b8aa85acdab84eb9feae634ac92c54d Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:13 +0300
Subject: [PATCH 0726/1806] net: phy: nxp-c45-tja11xx: add TJA1120 support

Add TJA1120 driver entry and its driver_data.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230731091619.77961-6-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/Kconfig           |   2 +-
 drivers/net/phy/nxp-c45-tja11xx.c | 159 ++++++++++++++++++++++++++++++
 2 files changed, 160 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 67aaeb75301fb..107880d13d219 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -306,7 +306,7 @@ config NXP_C45_TJA11XX_PHY
 	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  Enable support for NXP C45 TJA11XX PHYs.
-	  Currently supports only the TJA1103 PHY.
+	  Currently supports the TJA1103 and TJA1120 PHYs.
 
 config NXP_TJA11XX_PHY
 	tristate "NXP TJA11xx PHYs support"
diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 573083f0550f2..dbfaf1e07ad59 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -18,12 +18,17 @@
 #include <linux/net_tstamp.h>
 
 #define PHY_ID_TJA_1103			0x001BB010
+#define PHY_ID_TJA_1120			0x001BB031
 
 #define VEND1_DEVICE_CONTROL		0x0040
 #define DEVICE_CONTROL_RESET		BIT(15)
 #define DEVICE_CONTROL_CONFIG_GLOBAL_EN	BIT(14)
 #define DEVICE_CONTROL_CONFIG_ALL_EN	BIT(13)
 
+#define VEND1_DEVICE_CONFIG		0x0048
+
+#define TJA1120_VEND1_EXT_TS_MODE	0x1012
+
 #define VEND1_PHY_IRQ_ACK		0x80A0
 #define VEND1_PHY_IRQ_EN		0x80A1
 #define VEND1_PHY_IRQ_STATUS		0x80A2
@@ -76,6 +81,14 @@
 #define MII_BASIC_CONFIG_RMII		0x5
 #define MII_BASIC_CONFIG_MII		0x4
 
+#define VEND1_SYMBOL_ERROR_CNT_XTD	0x8351
+#define EXTENDED_CNT_EN			BIT(15)
+#define VEND1_MONITOR_STATUS		0xAC80
+#define MONITOR_RESET			BIT(15)
+#define VEND1_MONITOR_CONFIG		0xAC86
+#define LOST_FRAMES_CNT_EN		BIT(9)
+#define ALL_FRAMES_CNT_EN		BIT(8)
+
 #define VEND1_SYMBOL_ERROR_COUNTER	0x8350
 #define VEND1_LINK_DROP_COUNTER		0x8352
 #define VEND1_LINK_LOSSES_AND_FAILURES	0x8353
@@ -94,6 +107,10 @@
 #define VEND1_RX_TS_INSRT_CTRL		0x114D
 #define TJA1103_RX_TS_INSRT_MODE2	0x02
 
+#define TJA1120_RX_TS_INSRT_CTRL	0x9012
+#define TJA1120_RX_TS_INSRT_EN		BIT(15)
+#define TJA1120_TS_INSRT_MODE		BIT(4)
+
 #define VEND1_EGR_RING_DATA_0		0x114E
 #define VEND1_EGR_RING_CTRL		0x1154
 
@@ -110,6 +127,7 @@
 #define PORT_PTP_CONTROL_BYPASS		BIT(11)
 
 #define PTP_CLK_PERIOD_100BT1		15ULL
+#define PTP_CLK_PERIOD_1000BT1		8ULL
 
 #define EVENT_MSG_FILT_ALL		0x0F
 #define EVENT_MSG_FILT_NONE		0x00
@@ -929,6 +947,27 @@ static const struct nxp_c45_phy_stats tja1103_hw_stats[] = {
 		NXP_C45_REG_FIELD(0xAFD1, MDIO_MMD_VEND1, 0, 9), },
 };
 
+static const struct nxp_c45_phy_stats tja1120_hw_stats[] = {
+	{ "phy_symbol_error_cnt_ext",
+		NXP_C45_REG_FIELD(0x8351, MDIO_MMD_VEND1, 0, 14) },
+	{ "tx_frames_xtd",
+		NXP_C45_REG_FIELD(0xACA1, MDIO_MMD_VEND1, 0, 8), },
+	{ "tx_frames",
+		NXP_C45_REG_FIELD(0xACA0, MDIO_MMD_VEND1, 0, 16), },
+	{ "rx_frames_xtd",
+		NXP_C45_REG_FIELD(0xACA3, MDIO_MMD_VEND1, 0, 8), },
+	{ "rx_frames",
+		NXP_C45_REG_FIELD(0xACA2, MDIO_MMD_VEND1, 0, 16), },
+	{ "tx_lost_frames_xtd",
+		NXP_C45_REG_FIELD(0xACA5, MDIO_MMD_VEND1, 0, 8), },
+	{ "tx_lost_frames",
+		NXP_C45_REG_FIELD(0xACA4, MDIO_MMD_VEND1, 0, 16), },
+	{ "rx_lost_frames_xtd",
+		NXP_C45_REG_FIELD(0xACA7, MDIO_MMD_VEND1, 0, 8), },
+	{ "rx_lost_frames",
+		NXP_C45_REG_FIELD(0xACA6, MDIO_MMD_VEND1, 0, 16), },
+};
+
 static int nxp_c45_get_sset_count(struct phy_device *phydev)
 {
 	const struct nxp_c45_phy_data *phy_data = nxp_c45_get_data(phydev);
@@ -1511,6 +1550,101 @@ static const struct nxp_c45_phy_data tja1103_phy_data = {
 	.ptp_enable = tja1103_ptp_enable,
 };
 
+static void tja1120_counters_enable(struct phy_device *phydev)
+{
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_SYMBOL_ERROR_CNT_XTD,
+			 EXTENDED_CNT_EN);
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_MONITOR_STATUS,
+			 MONITOR_RESET);
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_MONITOR_CONFIG,
+			 ALL_FRAMES_CNT_EN | LOST_FRAMES_CNT_EN);
+}
+
+static void tja1120_ptp_init(struct phy_device *phydev)
+{
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, TJA1120_RX_TS_INSRT_CTRL,
+		      TJA1120_RX_TS_INSRT_EN | TJA1120_TS_INSRT_MODE);
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, TJA1120_VEND1_EXT_TS_MODE,
+		      TJA1120_TS_INSRT_MODE);
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_DEVICE_CONFIG,
+			 PTP_ENABLE);
+}
+
+static void tja1120_ptp_enable(struct phy_device *phydev, bool enable)
+{
+	if (enable)
+		phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 VEND1_PORT_FUNC_ENABLES,
+				 PTP_ENABLE);
+	else
+		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				   VEND1_PORT_FUNC_ENABLES,
+				   PTP_ENABLE);
+}
+
+static const struct nxp_c45_regmap tja1120_regmap = {
+	.vend1_ptp_clk_period	= 0x1020,
+	.vend1_event_msg_filt	= 0x9010,
+	.pps_enable		=
+		NXP_C45_REG_FIELD(0x1006, MDIO_MMD_VEND1, 4, 1),
+	.pps_polarity		=
+		NXP_C45_REG_FIELD(0x1006, MDIO_MMD_VEND1, 5, 1),
+	.ltc_lock_ctrl		=
+		NXP_C45_REG_FIELD(0x1006, MDIO_MMD_VEND1, 2, 1),
+	.ltc_read		=
+		NXP_C45_REG_FIELD(0x1000, MDIO_MMD_VEND1, 1, 1),
+	.ltc_write		=
+		NXP_C45_REG_FIELD(0x1000, MDIO_MMD_VEND1, 2, 1),
+	.vend1_ltc_wr_nsec_0	= 0x1040,
+	.vend1_ltc_wr_nsec_1	= 0x1041,
+	.vend1_ltc_wr_sec_0	= 0x1042,
+	.vend1_ltc_wr_sec_1	= 0x1043,
+	.vend1_ltc_rd_nsec_0	= 0x1048,
+	.vend1_ltc_rd_nsec_1	= 0x1049,
+	.vend1_ltc_rd_sec_0	= 0x104A,
+	.vend1_ltc_rd_sec_1	= 0x104B,
+	.vend1_rate_adj_subns_0	= 0x1030,
+	.vend1_rate_adj_subns_1	= 0x1031,
+	.irq_egr_ts_en		=
+		NXP_C45_REG_FIELD(0x900A, MDIO_MMD_VEND1, 1, 1),
+	.irq_egr_ts_status	=
+		NXP_C45_REG_FIELD(0x900C, MDIO_MMD_VEND1, 1, 1),
+	.domain_number		=
+		NXP_C45_REG_FIELD(0x9061, MDIO_MMD_VEND1, 8, 8),
+	.msg_type		=
+		NXP_C45_REG_FIELD(0x9061, MDIO_MMD_VEND1, 4, 4),
+	.sequence_id		=
+		NXP_C45_REG_FIELD(0x9062, MDIO_MMD_VEND1, 0, 16),
+	.sec_1_0		=
+		NXP_C45_REG_FIELD(0x9065, MDIO_MMD_VEND1, 0, 2),
+	.sec_4_2		=
+		NXP_C45_REG_FIELD(0x9065, MDIO_MMD_VEND1, 2, 3),
+	.nsec_15_0		=
+		NXP_C45_REG_FIELD(0x9063, MDIO_MMD_VEND1, 0, 16),
+	.nsec_29_16		=
+		NXP_C45_REG_FIELD(0x9064, MDIO_MMD_VEND1, 0, 14),
+	.vend1_ext_trg_data_0	= 0x1071,
+	.vend1_ext_trg_data_1	= 0x1072,
+	.vend1_ext_trg_data_2	= 0x1073,
+	.vend1_ext_trg_data_3	= 0x1074,
+	.vend1_ext_trg_ctrl	= 0x1075,
+	.cable_test		= 0x8360,
+	.cable_test_valid	=
+		NXP_C45_REG_FIELD(0x8361, MDIO_MMD_VEND1, 15, 1),
+	.cable_test_result	=
+		NXP_C45_REG_FIELD(0x8361, MDIO_MMD_VEND1, 0, 3),
+};
+
+static const struct nxp_c45_phy_data tja1120_phy_data = {
+	.regmap = &tja1120_regmap,
+	.stats = tja1120_hw_stats,
+	.n_stats = ARRAY_SIZE(tja1120_hw_stats),
+	.ptp_clk_period = PTP_CLK_PERIOD_1000BT1,
+	.counters_enable = tja1120_counters_enable,
+	.ptp_init = tja1120_ptp_init,
+	.ptp_enable = tja1120_ptp_enable,
+};
+
 static struct phy_driver nxp_c45_driver[] = {
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103),
@@ -1536,12 +1670,37 @@ static struct phy_driver nxp_c45_driver[] = {
 		.get_sqi_max		= nxp_c45_get_sqi_max,
 		.remove			= nxp_c45_remove,
 	},
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1120),
+		.name			= "NXP C45 TJA1120",
+		.get_features		= nxp_c45_get_features,
+		.driver_data		= &tja1120_phy_data,
+		.probe			= nxp_c45_probe,
+		.soft_reset		= nxp_c45_soft_reset,
+		.config_aneg		= genphy_c45_config_aneg,
+		.config_init		= nxp_c45_config_init,
+		.config_intr		= nxp_c45_config_intr,
+		.handle_interrupt	= nxp_c45_handle_interrupt,
+		.read_status		= genphy_c45_read_status,
+		.suspend		= genphy_c45_pma_suspend,
+		.resume			= genphy_c45_pma_resume,
+		.get_sset_count		= nxp_c45_get_sset_count,
+		.get_strings		= nxp_c45_get_strings,
+		.get_stats		= nxp_c45_get_stats,
+		.cable_test_start	= nxp_c45_cable_test_start,
+		.cable_test_get_status	= nxp_c45_cable_test_get_status,
+		.set_loopback		= genphy_c45_loopback,
+		.get_sqi		= nxp_c45_get_sqi,
+		.get_sqi_max		= nxp_c45_get_sqi_max,
+		.remove			= nxp_c45_remove,
+	},
 };
 
 module_phy_driver(nxp_c45_driver);
 
 static struct mdio_device_id __maybe_unused nxp_c45_tbl[] = {
 	{ PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103) },
+	{ PHY_ID_MATCH_MODEL(PHY_ID_TJA_1120) },
 	{ /*sentinel*/ },
 };
 
-- 
GitLab


From b0b2247d815d0f6806b702022052e208c3c2d56a Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:14 +0300
Subject: [PATCH 0727/1806] net: phy: nxp-c45-tja11xx: enable LTC sampling on
 both ext_ts edges

The external trigger configuration for TJA1120 has changed. The PHY
supports sampling of the LTC on rising and on falling edge.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230731091619.77961-7-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 60 ++++++++++++++++++++++++++-----
 1 file changed, 52 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index dbfaf1e07ad59..8393c17a83cc1 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -101,6 +101,10 @@
 #define VEND1_PTP_CONFIG		0x1102
 #define EXT_TRG_EDGE			BIT(1)
 
+#define TJA1120_SYNC_TRIG_FILTER	0x1010
+#define PTP_TRIG_RISE_TS		BIT(3)
+#define PTP_TRIG_FALLING_TS		BIT(2)
+
 #define CLK_RATE_ADJ_LD			BIT(15)
 #define CLK_RATE_ADJ_DIR		BIT(14)
 
@@ -238,6 +242,7 @@ struct nxp_c45_phy_data {
 	const struct nxp_c45_phy_stats *stats;
 	int n_stats;
 	u8 ptp_clk_period;
+	bool ext_ts_both_edges;
 	void (*counters_enable)(struct phy_device *phydev);
 	void (*ptp_init)(struct phy_device *phydev);
 	void (*ptp_enable)(struct phy_device *phydev, bool enable);
@@ -684,9 +689,48 @@ static int nxp_c45_perout_enable(struct nxp_c45_phy *priv,
 	return 0;
 }
 
+static void nxp_c45_set_rising_or_falling(struct phy_device *phydev,
+					  struct ptp_extts_request *extts)
+{
+	if (extts->flags & PTP_RISING_EDGE)
+		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				   VEND1_PTP_CONFIG, EXT_TRG_EDGE);
+
+	if (extts->flags & PTP_FALLING_EDGE)
+		phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 VEND1_PTP_CONFIG, EXT_TRG_EDGE);
+}
+
+static void nxp_c45_set_rising_and_falling(struct phy_device *phydev,
+					   struct ptp_extts_request *extts)
+{
+	/* PTP_EXTTS_REQUEST may have only the PTP_ENABLE_FEATURE flag set. In
+	 * this case external ts will be enabled on rising edge.
+	 */
+	if (extts->flags & PTP_RISING_EDGE ||
+	    extts->flags == PTP_ENABLE_FEATURE)
+		phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 TJA1120_SYNC_TRIG_FILTER,
+				 PTP_TRIG_RISE_TS);
+	else
+		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				   TJA1120_SYNC_TRIG_FILTER,
+				   PTP_TRIG_RISE_TS);
+
+	if (extts->flags & PTP_FALLING_EDGE)
+		phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 TJA1120_SYNC_TRIG_FILTER,
+				 PTP_TRIG_FALLING_TS);
+	else
+		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				   TJA1120_SYNC_TRIG_FILTER,
+				   PTP_TRIG_FALLING_TS);
+}
+
 static int nxp_c45_extts_enable(struct nxp_c45_phy *priv,
 				struct ptp_extts_request *extts, int on)
 {
+	const struct nxp_c45_phy_data *data = nxp_c45_get_data(priv->phydev);
 	int pin;
 
 	if (extts->flags & ~(PTP_ENABLE_FEATURE |
@@ -697,7 +741,8 @@ static int nxp_c45_extts_enable(struct nxp_c45_phy *priv,
 
 	/* Sampling on both edges is not supported */
 	if ((extts->flags & PTP_RISING_EDGE) &&
-	    (extts->flags & PTP_FALLING_EDGE))
+	    (extts->flags & PTP_FALLING_EDGE) &&
+	    !data->ext_ts_both_edges)
 		return -EOPNOTSUPP;
 
 	pin = ptp_find_pin(priv->ptp_clock, PTP_PF_EXTTS, extts->index);
@@ -711,13 +756,10 @@ static int nxp_c45_extts_enable(struct nxp_c45_phy *priv,
 		return 0;
 	}
 
-	if (extts->flags & PTP_RISING_EDGE)
-		phy_clear_bits_mmd(priv->phydev, MDIO_MMD_VEND1,
-				   VEND1_PTP_CONFIG, EXT_TRG_EDGE);
-
-	if (extts->flags & PTP_FALLING_EDGE)
-		phy_set_bits_mmd(priv->phydev, MDIO_MMD_VEND1,
-				 VEND1_PTP_CONFIG, EXT_TRG_EDGE);
+	if (data->ext_ts_both_edges)
+		nxp_c45_set_rising_and_falling(priv->phydev, extts);
+	else
+		nxp_c45_set_rising_or_falling(priv->phydev, extts);
 
 	nxp_c45_gpio_config(priv, pin, GPIO_EXTTS_OUT_CFG);
 	priv->extts = true;
@@ -1545,6 +1587,7 @@ static const struct nxp_c45_phy_data tja1103_phy_data = {
 	.stats = tja1103_hw_stats,
 	.n_stats = ARRAY_SIZE(tja1103_hw_stats),
 	.ptp_clk_period = PTP_CLK_PERIOD_100BT1,
+	.ext_ts_both_edges = false,
 	.counters_enable = tja1103_counters_enable,
 	.ptp_init = tja1103_ptp_init,
 	.ptp_enable = tja1103_ptp_enable,
@@ -1640,6 +1683,7 @@ static const struct nxp_c45_phy_data tja1120_phy_data = {
 	.stats = tja1120_hw_stats,
 	.n_stats = ARRAY_SIZE(tja1120_hw_stats),
 	.ptp_clk_period = PTP_CLK_PERIOD_1000BT1,
+	.ext_ts_both_edges = true,
 	.counters_enable = tja1120_counters_enable,
 	.ptp_init = tja1120_ptp_init,
 	.ptp_enable = tja1120_ptp_enable,
-- 
GitLab


From bdb4c5b8852029d9a82f366885071ba27d254366 Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:15 +0300
Subject: [PATCH 0728/1806] net: phy: nxp-c45-tja11xx: read egress ts on
 TJA1120

The egress timestamp FIFO/circular buffer work different on TJA1120 than
TJA1103.

For TJA1103 the new timestamp should be manually moved from the FIFO to
the hardware buffer before checking if the timestamp is valid.

For TJA1120 the hardware will move automatically the new timestamp
from the FIFO to the buffer and the user should check the valid bit, read
the timestamp and unlock the buffer by writing any of the buffer
registers(which are read only).

Another change for the TJA1120 is the behaviour of the EGR TS IRQ bit.
This bit was a self-clear bit for TJA1103, but now should be cleared
before reading the timestamp.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Link: https://lore.kernel.org/r/20230731091619.77961-8-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 110 +++++++++++++++++++++++++-----
 1 file changed, 92 insertions(+), 18 deletions(-)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 8393c17a83cc1..e596ffcf86835 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -29,6 +29,11 @@
 
 #define TJA1120_VEND1_EXT_TS_MODE	0x1012
 
+#define TJA1120_EGRESS_TS_DATA_S	0x9060
+#define TJA1120_EGRESS_TS_END		0x9067
+#define TJA1120_TS_VALID		BIT(0)
+#define TJA1120_MORE_TS			BIT(15)
+
 #define VEND1_PHY_IRQ_ACK		0x80A0
 #define VEND1_PHY_IRQ_EN		0x80A1
 #define VEND1_PHY_IRQ_STATUS		0x80A2
@@ -59,6 +64,12 @@
 #define VEND1_PORT_ABILITIES		0x8046
 #define PTP_ABILITY			BIT(3)
 
+#define VEND1_PORT_FUNC_IRQ_EN		0x807A
+#define PTP_IRQS			BIT(3)
+
+#define VEND1_PTP_IRQ_ACK		0x9008
+#define EGR_TS_IRQ			BIT(1)
+
 #define VEND1_PORT_INFRA_CONTROL	0xAC00
 #define PORT_INFRA_CONTROL_EN		BIT(14)
 
@@ -158,6 +169,8 @@
 
 #define NXP_C45_SKB_CB(skb)	((struct nxp_c45_skb_cb *)(skb)->cb)
 
+struct nxp_c45_phy;
+
 struct nxp_c45_skb_cb {
 	struct ptp_header *header;
 	unsigned int type;
@@ -243,7 +256,10 @@ struct nxp_c45_phy_data {
 	int n_stats;
 	u8 ptp_clk_period;
 	bool ext_ts_both_edges;
+	bool ack_ptp_irq;
 	void (*counters_enable)(struct phy_device *phydev);
+	bool (*get_egressts)(struct nxp_c45_phy *priv,
+			     struct nxp_c45_hwts *hwts);
 	void (*ptp_init)(struct phy_device *phydev);
 	void (*ptp_enable)(struct phy_device *phydev, bool enable);
 };
@@ -499,21 +515,11 @@ static void nxp_c45_get_extts(struct nxp_c45_phy *priv,
 		      regmap->vend1_ext_trg_ctrl, RING_DONE);
 }
 
-static bool nxp_c45_get_hwtxts(struct nxp_c45_phy *priv,
-			       struct nxp_c45_hwts *hwts)
+static void nxp_c45_read_egress_ts(struct nxp_c45_phy *priv,
+				   struct nxp_c45_hwts *hwts)
 {
 	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(priv->phydev);
 	struct phy_device *phydev = priv->phydev;
-	bool valid;
-	u16 reg;
-
-	mutex_lock(&priv->ptp_lock);
-	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_CTRL,
-		      RING_DONE);
-	reg = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_DATA_0);
-	valid = !!(reg & RING_DATA_0_TS_VALID);
-	if (!valid)
-		goto nxp_c45_get_hwtxts_out;
 
 	hwts->domain_number =
 		nxp_c45_read_reg_field(phydev, &regmap->domain_number);
@@ -527,12 +533,72 @@ static bool nxp_c45_get_hwtxts(struct nxp_c45_phy *priv,
 		nxp_c45_read_reg_field(phydev, &regmap->nsec_29_16) << 16;
 	hwts->sec = nxp_c45_read_reg_field(phydev, &regmap->sec_1_0);
 	hwts->sec |= nxp_c45_read_reg_field(phydev, &regmap->sec_4_2) << 2;
+}
+
+static bool nxp_c45_get_hwtxts(struct nxp_c45_phy *priv,
+			       struct nxp_c45_hwts *hwts)
+{
+	bool valid;
+	u16 reg;
 
+	mutex_lock(&priv->ptp_lock);
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_CTRL,
+		      RING_DONE);
+	reg = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_DATA_0);
+	valid = !!(reg & RING_DATA_0_TS_VALID);
+	if (!valid)
+		goto nxp_c45_get_hwtxts_out;
+
+	nxp_c45_read_egress_ts(priv, hwts);
 nxp_c45_get_hwtxts_out:
 	mutex_unlock(&priv->ptp_lock);
 	return valid;
 }
 
+static bool tja1120_egress_ts_is_valid(struct phy_device *phydev)
+{
+	bool valid;
+	u16 reg;
+
+	reg = phy_read_mmd(phydev, MDIO_MMD_VEND1, TJA1120_EGRESS_TS_DATA_S);
+	valid = !!(reg & TJA1120_TS_VALID);
+
+	return valid;
+}
+
+static bool tja1120_get_hwtxts(struct nxp_c45_phy *priv,
+			       struct nxp_c45_hwts *hwts)
+{
+	struct phy_device *phydev = priv->phydev;
+	bool more_ts;
+	bool valid;
+	u16 reg;
+
+	mutex_lock(&priv->ptp_lock);
+	reg = phy_read_mmd(phydev, MDIO_MMD_VEND1, TJA1120_EGRESS_TS_END);
+	more_ts = !!(reg & TJA1120_MORE_TS);
+	valid = tja1120_egress_ts_is_valid(phydev);
+	if (!valid) {
+		if (!more_ts)
+			goto tja1120_get_hwtxts_out;
+
+		/* Bug workaround for TJA1120 engineering samples: move the
+		 * new timestamp from the FIFO to the buffer.
+		 */
+		phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			      TJA1120_EGRESS_TS_END, TJA1120_TS_VALID);
+		valid = tja1120_egress_ts_is_valid(phydev);
+		if (!valid)
+			goto tja1120_get_hwtxts_out;
+	}
+	nxp_c45_read_egress_ts(priv, hwts);
+	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, TJA1120_EGRESS_TS_DATA_S,
+			   TJA1120_TS_VALID);
+tja1120_get_hwtxts_out:
+	mutex_unlock(&priv->ptp_lock);
+	return valid;
+}
+
 static void nxp_c45_process_txts(struct nxp_c45_phy *priv,
 				 struct nxp_c45_hwts *txts)
 {
@@ -571,6 +637,7 @@ static void nxp_c45_process_txts(struct nxp_c45_phy *priv,
 static long nxp_c45_do_aux_work(struct ptp_clock_info *ptp)
 {
 	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+	const struct nxp_c45_phy_data *data = nxp_c45_get_data(priv->phydev);
 	bool poll_txts = nxp_c45_poll_txts(priv->phydev);
 	struct skb_shared_hwtstamps *shhwtstamps_rx;
 	struct ptp_clock_event event;
@@ -582,7 +649,7 @@ static long nxp_c45_do_aux_work(struct ptp_clock_info *ptp)
 	u32 ts_raw;
 
 	while (!skb_queue_empty_lockless(&priv->tx_queue) && poll_txts) {
-		txts_valid = nxp_c45_get_hwtxts(priv, &hwts);
+		txts_valid = data->get_egressts(priv, &hwts);
 		if (unlikely(!txts_valid)) {
 			/* Still more skbs in the queue */
 			reschedule = true;
@@ -1111,13 +1178,16 @@ static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev)
 		ret = IRQ_HANDLED;
 	}
 
-	/* There is no need for ACK.
-	 * The irq signal will be asserted until the EGR TS FIFO will be
-	 * emptied.
-	 */
 	irq = nxp_c45_read_reg_field(phydev, &data->regmap->irq_egr_ts_status);
 	if (irq) {
-		while (nxp_c45_get_hwtxts(priv, &hwts))
+		/* If ack_ptp_irq is false, the IRQ bit is self-clear and will
+		 * be cleared when the EGR TS FIFO is empty. Otherwise, the
+		 * IRQ bit should be cleared before reading the timestamp,
+		 */
+		if (data->ack_ptp_irq)
+			phy_write_mmd(phydev, MDIO_MMD_VEND1,
+				      VEND1_PTP_IRQ_ACK, EGR_TS_IRQ);
+		while (data->get_egressts(priv, &hwts))
 			nxp_c45_process_txts(priv, &hwts);
 
 		ret = IRQ_HANDLED;
@@ -1588,7 +1658,9 @@ static const struct nxp_c45_phy_data tja1103_phy_data = {
 	.n_stats = ARRAY_SIZE(tja1103_hw_stats),
 	.ptp_clk_period = PTP_CLK_PERIOD_100BT1,
 	.ext_ts_both_edges = false,
+	.ack_ptp_irq = false,
 	.counters_enable = tja1103_counters_enable,
+	.get_egressts = nxp_c45_get_hwtxts,
 	.ptp_init = tja1103_ptp_init,
 	.ptp_enable = tja1103_ptp_enable,
 };
@@ -1684,7 +1756,9 @@ static const struct nxp_c45_phy_data tja1120_phy_data = {
 	.n_stats = ARRAY_SIZE(tja1120_hw_stats),
 	.ptp_clk_period = PTP_CLK_PERIOD_1000BT1,
 	.ext_ts_both_edges = true,
+	.ack_ptp_irq = true,
 	.counters_enable = tja1120_counters_enable,
+	.get_egressts = tja1120_get_hwtxts,
 	.ptp_init = tja1120_ptp_init,
 	.ptp_enable = tja1120_ptp_enable,
 };
-- 
GitLab


From 425c8348df7b868bc25dce85758e5dc3d63de91d Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:16 +0300
Subject: [PATCH 0729/1806] net: phy: nxp-c45-tja11xx: handle FUSA irq

TJA1120 and TJA1103 have a set of functional safety hardware tests
executed after every reset, and when the tests are done, the IRQ line is
asserted. For the moment, the purpose of these handlers is to acknowledge
the IRQ and not to check the FUSA tests status.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230731091619.77961-9-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 79 ++++++++++++++++++++++++++++++-
 1 file changed, 77 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index e596ffcf86835..a52067da9dbf9 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -29,6 +29,11 @@
 
 #define TJA1120_VEND1_EXT_TS_MODE	0x1012
 
+#define TJA1120_GLOBAL_INFRA_IRQ_ACK	0x2C08
+#define TJA1120_GLOBAL_INFRA_IRQ_EN	0x2C0A
+#define TJA1120_GLOBAL_INFRA_IRQ_STATUS	0x2C0C
+#define TJA1120_DEV_BOOT_DONE		BIT(1)
+
 #define TJA1120_EGRESS_TS_DATA_S	0x9060
 #define TJA1120_EGRESS_TS_END		0x9067
 #define TJA1120_TS_VALID		BIT(0)
@@ -39,6 +44,9 @@
 #define VEND1_PHY_IRQ_STATUS		0x80A2
 #define PHY_IRQ_LINK_EVENT		BIT(1)
 
+#define VEND1_ALWAYS_ACCESSIBLE		0x801F
+#define FUSA_PASS			BIT(4)
+
 #define VEND1_PHY_CONTROL		0x8100
 #define PHY_CONFIG_EN			BIT(14)
 #define PHY_START_OP			BIT(0)
@@ -262,6 +270,8 @@ struct nxp_c45_phy_data {
 			     struct nxp_c45_hwts *hwts);
 	void (*ptp_init)(struct phy_device *phydev);
 	void (*ptp_enable)(struct phy_device *phydev, bool enable);
+	void (*nmi_handler)(struct phy_device *phydev,
+			    irqreturn_t *irq_status);
 };
 
 struct nxp_c45_phy {
@@ -1162,6 +1172,37 @@ static int nxp_c45_config_intr(struct phy_device *phydev)
 					  VEND1_PHY_IRQ_EN, PHY_IRQ_LINK_EVENT);
 }
 
+static int tja1103_config_intr(struct phy_device *phydev)
+{
+	int ret;
+
+	/* We can't disable the FUSA IRQ for TJA1103, but we can clean it up. */
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_ALWAYS_ACCESSIBLE,
+			    FUSA_PASS);
+	if (ret)
+		return ret;
+
+	return nxp_c45_config_intr(phydev);
+}
+
+static int tja1120_config_intr(struct phy_device *phydev)
+{
+	int ret;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+				       TJA1120_GLOBAL_INFRA_IRQ_EN,
+				       TJA1120_DEV_BOOT_DONE);
+	else
+		ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+					 TJA1120_GLOBAL_INFRA_IRQ_EN,
+					 TJA1120_DEV_BOOT_DONE);
+	if (ret)
+		return ret;
+
+	return nxp_c45_config_intr(phydev);
+}
+
 static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev)
 {
 	const struct nxp_c45_phy_data *data = nxp_c45_get_data(phydev);
@@ -1193,6 +1234,8 @@ static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev)
 		ret = IRQ_HANDLED;
 	}
 
+	data->nmi_handler(phydev, &ret);
+
 	return ret;
 }
 
@@ -1599,6 +1642,21 @@ static void tja1103_ptp_enable(struct phy_device *phydev, bool enable)
 				 PORT_PTP_CONTROL_BYPASS);
 }
 
+static void tja1103_nmi_handler(struct phy_device *phydev,
+				irqreturn_t *irq_status)
+{
+	int ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+			   VEND1_ALWAYS_ACCESSIBLE);
+	if (ret & FUSA_PASS) {
+		phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			      VEND1_ALWAYS_ACCESSIBLE,
+			      FUSA_PASS);
+		*irq_status = IRQ_HANDLED;
+	}
+}
+
 static const struct nxp_c45_regmap tja1103_regmap = {
 	.vend1_ptp_clk_period	= 0x1104,
 	.vend1_event_msg_filt	= 0x1148,
@@ -1663,6 +1721,7 @@ static const struct nxp_c45_phy_data tja1103_phy_data = {
 	.get_egressts = nxp_c45_get_hwtxts,
 	.ptp_init = tja1103_ptp_init,
 	.ptp_enable = tja1103_ptp_enable,
+	.nmi_handler = tja1103_nmi_handler,
 };
 
 static void tja1120_counters_enable(struct phy_device *phydev)
@@ -1697,6 +1756,21 @@ static void tja1120_ptp_enable(struct phy_device *phydev, bool enable)
 				   PTP_ENABLE);
 }
 
+static void tja1120_nmi_handler(struct phy_device *phydev,
+				irqreturn_t *irq_status)
+{
+	int ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+			   TJA1120_GLOBAL_INFRA_IRQ_STATUS);
+	if (ret & TJA1120_DEV_BOOT_DONE) {
+		phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			      TJA1120_GLOBAL_INFRA_IRQ_ACK,
+			      TJA1120_DEV_BOOT_DONE);
+		*irq_status = IRQ_HANDLED;
+	}
+}
+
 static const struct nxp_c45_regmap tja1120_regmap = {
 	.vend1_ptp_clk_period	= 0x1020,
 	.vend1_event_msg_filt	= 0x9010,
@@ -1761,6 +1835,7 @@ static const struct nxp_c45_phy_data tja1120_phy_data = {
 	.get_egressts = tja1120_get_hwtxts,
 	.ptp_init = tja1120_ptp_init,
 	.ptp_enable = tja1120_ptp_enable,
+	.nmi_handler = tja1120_nmi_handler,
 };
 
 static struct phy_driver nxp_c45_driver[] = {
@@ -1773,7 +1848,7 @@ static struct phy_driver nxp_c45_driver[] = {
 		.soft_reset		= nxp_c45_soft_reset,
 		.config_aneg		= genphy_c45_config_aneg,
 		.config_init		= nxp_c45_config_init,
-		.config_intr		= nxp_c45_config_intr,
+		.config_intr		= tja1103_config_intr,
 		.handle_interrupt	= nxp_c45_handle_interrupt,
 		.read_status		= genphy_c45_read_status,
 		.suspend		= genphy_c45_pma_suspend,
@@ -1797,7 +1872,7 @@ static struct phy_driver nxp_c45_driver[] = {
 		.soft_reset		= nxp_c45_soft_reset,
 		.config_aneg		= genphy_c45_config_aneg,
 		.config_init		= nxp_c45_config_init,
-		.config_intr		= nxp_c45_config_intr,
+		.config_intr		= tja1120_config_intr,
 		.handle_interrupt	= nxp_c45_handle_interrupt,
 		.read_status		= genphy_c45_read_status,
 		.suspend		= genphy_c45_pma_suspend,
-- 
GitLab


From c552c110d4794fc12e0faa4d1cc928fccdfce3f2 Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:17 +0300
Subject: [PATCH 0730/1806] net: phy: nxp-c45-tja11xx: run cable test with the
 PHY in test mode

For TJA1120, the enable bit for cable test is not writable if the PHY is
not in test mode.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230731091619.77961-10-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index a52067da9dbf9..92a2eca2a02c6 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -145,6 +145,7 @@
 
 #define VEND1_PORT_FUNC_ENABLES		0x8048
 #define PTP_ENABLE			BIT(3)
+#define PHY_TEST_ENABLE			BIT(0)
 
 #define VEND1_PORT_PTP_CONTROL		0x9000
 #define PORT_PTP_CONTROL_BYPASS		BIT(11)
@@ -1258,6 +1259,8 @@ static int nxp_c45_cable_test_start(struct phy_device *phydev)
 {
 	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(phydev);
 
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+			 VEND1_PORT_FUNC_ENABLES, PHY_TEST_ENABLE);
 	return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, regmap->cable_test,
 				CABLE_TEST_ENABLE | CABLE_TEST_START);
 }
@@ -1299,6 +1302,8 @@ static int nxp_c45_cable_test_get_status(struct phy_device *phydev,
 
 	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, regmap->cable_test,
 			   CABLE_TEST_ENABLE);
+	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+			   VEND1_PORT_FUNC_ENABLES, PHY_TEST_ENABLE);
 
 	return nxp_c45_start_op(phydev);
 }
-- 
GitLab


From 08e6547c8468863734a847154aee390f2a44befe Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:18 +0300
Subject: [PATCH 0731/1806] net: phy: nxp-c45-tja11xx: read ext trig ts on
 TJA1120

On TJA1120, the external trigger timestamp now has a VALID bit. This
changes the logic and we can't use the TJA1103 procedure.

For TJA1103, we can always read a valid timestamp from the registers,
compare the new timestamp with the old timestamp and, if they are not the
same, an event occurred. This logic cannot be applied for TJA1120 because
the timestamp is 0 if the VALID bit is not set.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Link: https://lore.kernel.org/r/20230731091619.77961-11-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 64 ++++++++++++++++++++++++++++---
 1 file changed, 58 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 92a2eca2a02c6..48657307ffb5a 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -34,6 +34,8 @@
 #define TJA1120_GLOBAL_INFRA_IRQ_STATUS	0x2C0C
 #define TJA1120_DEV_BOOT_DONE		BIT(1)
 
+#define TJA1120_VEND1_PTP_TRIG_DATA_S	0x1070
+
 #define TJA1120_EGRESS_TS_DATA_S	0x9060
 #define TJA1120_EGRESS_TS_END		0x9067
 #define TJA1120_TS_VALID		BIT(0)
@@ -269,6 +271,7 @@ struct nxp_c45_phy_data {
 	void (*counters_enable)(struct phy_device *phydev);
 	bool (*get_egressts)(struct nxp_c45_phy *priv,
 			     struct nxp_c45_hwts *hwts);
+	bool (*get_extts)(struct nxp_c45_phy *priv, struct timespec64 *extts);
 	void (*ptp_init)(struct phy_device *phydev);
 	void (*ptp_enable)(struct phy_device *phydev, bool enable);
 	void (*nmi_handler)(struct phy_device *phydev,
@@ -509,7 +512,7 @@ static bool nxp_c45_match_ts(struct ptp_header *header,
 	       header->domain_number  == hwts->domain_number;
 }
 
-static void nxp_c45_get_extts(struct nxp_c45_phy *priv,
+static bool nxp_c45_get_extts(struct nxp_c45_phy *priv,
 			      struct timespec64 *extts)
 {
 	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(priv->phydev);
@@ -524,6 +527,53 @@ static void nxp_c45_get_extts(struct nxp_c45_phy *priv,
 				      regmap->vend1_ext_trg_data_3) << 16;
 	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1,
 		      regmap->vend1_ext_trg_ctrl, RING_DONE);
+
+	return true;
+}
+
+static bool tja1120_extts_is_valid(struct phy_device *phydev)
+{
+	bool valid;
+	int reg;
+
+	reg = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+			   TJA1120_VEND1_PTP_TRIG_DATA_S);
+	valid = !!(reg & TJA1120_TS_VALID);
+
+	return valid;
+}
+
+static bool tja1120_get_extts(struct nxp_c45_phy *priv,
+			      struct timespec64 *extts)
+{
+	const struct nxp_c45_regmap *regmap = nxp_c45_get_regmap(priv->phydev);
+	struct phy_device *phydev = priv->phydev;
+	bool more_ts;
+	bool valid;
+	u16 reg;
+
+	reg = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+			   regmap->vend1_ext_trg_ctrl);
+	more_ts = !!(reg & TJA1120_MORE_TS);
+
+	valid = tja1120_extts_is_valid(phydev);
+	if (!valid) {
+		if (!more_ts)
+			goto tja1120_get_extts_out;
+
+		/* Bug workaround for TJA1120 engineering samples: move the new
+		 * timestamp from the FIFO to the buffer.
+		 */
+		phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			      regmap->vend1_ext_trg_ctrl, RING_DONE);
+		valid = tja1120_extts_is_valid(phydev);
+		if (!valid)
+			goto tja1120_get_extts_out;
+	}
+
+	nxp_c45_get_extts(priv, extts);
+tja1120_get_extts_out:
+	return valid;
 }
 
 static void nxp_c45_read_egress_ts(struct nxp_c45_phy *priv,
@@ -656,12 +706,12 @@ static long nxp_c45_do_aux_work(struct ptp_clock_info *ptp)
 	bool reschedule = false;
 	struct timespec64 ts;
 	struct sk_buff *skb;
-	bool txts_valid;
+	bool ts_valid;
 	u32 ts_raw;
 
 	while (!skb_queue_empty_lockless(&priv->tx_queue) && poll_txts) {
-		txts_valid = data->get_egressts(priv, &hwts);
-		if (unlikely(!txts_valid)) {
+		ts_valid = data->get_egressts(priv, &hwts);
+		if (unlikely(!ts_valid)) {
 			/* Still more skbs in the queue */
 			reschedule = true;
 			break;
@@ -683,8 +733,8 @@ static long nxp_c45_do_aux_work(struct ptp_clock_info *ptp)
 	}
 
 	if (priv->extts) {
-		nxp_c45_get_extts(priv, &ts);
-		if (timespec64_compare(&ts, &priv->extts_ts) != 0) {
+		ts_valid = data->get_extts(priv, &ts);
+		if (ts_valid && timespec64_compare(&ts, &priv->extts_ts) != 0) {
 			priv->extts_ts = ts;
 			event.index = priv->extts_index;
 			event.type = PTP_CLOCK_EXTTS;
@@ -1724,6 +1774,7 @@ static const struct nxp_c45_phy_data tja1103_phy_data = {
 	.ack_ptp_irq = false,
 	.counters_enable = tja1103_counters_enable,
 	.get_egressts = nxp_c45_get_hwtxts,
+	.get_extts = nxp_c45_get_extts,
 	.ptp_init = tja1103_ptp_init,
 	.ptp_enable = tja1103_ptp_enable,
 	.nmi_handler = tja1103_nmi_handler,
@@ -1838,6 +1889,7 @@ static const struct nxp_c45_phy_data tja1120_phy_data = {
 	.ack_ptp_irq = true,
 	.counters_enable = tja1120_counters_enable,
 	.get_egressts = tja1120_get_hwtxts,
+	.get_extts = tja1120_get_extts,
 	.ptp_init = tja1120_ptp_init,
 	.ptp_enable = tja1120_ptp_enable,
 	.nmi_handler = tja1120_nmi_handler,
-- 
GitLab


From 68c6af72047ca77e6b56bf5ae550f980a0ed704d Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Mon, 31 Jul 2023 12:16:19 +0300
Subject: [PATCH 0732/1806] net: phy: nxp-c45-tja11xx: reset PCS if the link
 goes down

During PTP testing on early TJA1120 engineering samples I observed that
if the link is lost and recovered, the tx timestamps will be randomly
lost. To avoid this HW issue, the PCS should be reset.

Resetting the PCS will break the link and we should reset the PCS on
LINK UP -> LINK DOWN transition, otherwise we will trigger and infinite
loop of LINK UP -> LINK DOWN events.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230731091619.77961-12-radu-nicolae.pirea@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 48657307ffb5a..7ab080ff02dfa 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -56,6 +56,9 @@
 #define VEND1_PHY_CONFIG		0x8108
 #define PHY_CONFIG_AUTO			BIT(0)
 
+#define TJA1120_EPHY_RESETS		0x810A
+#define EPHY_PCS_RESET			BIT(3)
+
 #define VEND1_SIGNAL_QUALITY		0x8320
 #define SQI_VALID			BIT(14)
 #define SQI_MASK			GENMASK(2, 0)
@@ -1371,6 +1374,19 @@ static int nxp_c45_get_sqi(struct phy_device *phydev)
 	return reg;
 }
 
+static void tja1120_link_change_notify(struct phy_device *phydev)
+{
+	/* Bug workaround for TJA1120 enegineering samples: fix egress
+	 * timestamps lost after link recovery.
+	 */
+	if (phydev->state == PHY_NOLINK) {
+		phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 TJA1120_EPHY_RESETS, EPHY_PCS_RESET);
+		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				   TJA1120_EPHY_RESETS, EPHY_PCS_RESET);
+	}
+}
+
 static int nxp_c45_get_sqi_max(struct phy_device *phydev)
 {
 	return MAX_SQI;
@@ -1932,6 +1948,7 @@ static struct phy_driver nxp_c45_driver[] = {
 		.config_intr		= tja1120_config_intr,
 		.handle_interrupt	= nxp_c45_handle_interrupt,
 		.read_status		= genphy_c45_read_status,
+		.link_change_notify	= tja1120_link_change_notify,
 		.suspend		= genphy_c45_pma_suspend,
 		.resume			= genphy_c45_pma_resume,
 		.get_sset_count		= nxp_c45_get_sset_count,
-- 
GitLab


From db31e6f170f33e19d6b204acc265a23c86b654a1 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Wed, 2 Aug 2023 11:09:00 +0800
Subject: [PATCH 0733/1806] can: c_can: Do not check for 0 return after calling
 platform_get_irq()

It is not possible for platform_get_irq() to return 0. Use the
return value from platform_get_irq().

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Link: https://lore.kernel.org/all/20230802030900.2271322-1-ruanjinjie@huawei.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/c_can/c_can_platform.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 925930b6c4ca5..f44ba2600415f 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -285,8 +285,8 @@ static int c_can_plat_probe(struct platform_device *pdev)
 
 	/* get the platform data */
 	irq = platform_get_irq(pdev, 0);
-	if (irq <= 0) {
-		ret = -ENODEV;
+	if (irq < 0) {
+		ret = irq;
 		goto exit;
 	}
 
-- 
GitLab


From 10857e6779054f79a7569eaaaa85dfa71b73acc1 Mon Sep 17 00:00:00 2001
From: Rohan G Thomas <rohan.g.thomas@intel.com>
Date: Mon, 31 Jul 2023 19:50:41 +0800
Subject: [PATCH 0734/1806] net: stmmac: XGMAC support for mdio C22 addr > 3

For XGMAC versions < 2.2 number of supported mdio C22 addresses is
restricted to 3. From XGMAC version 2.2 there are no restrictions on
the C22 addresses, it supports all valid mdio addresses(0 to 31).

Signed-off-by: Rohan G Thomas <rohan.g.thomas@intel.com>
Acked-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h  |  1 +
 .../net/ethernet/stmicro/stmmac/stmmac_mdio.c | 36 ++++++++++++-------
 2 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 57f2137bbe9d9..c67171975d5c7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -35,6 +35,7 @@
 #define DWMAC_CORE_5_10		0x51
 #define DWMAC_CORE_5_20		0x52
 #define DWXGMAC_CORE_2_10	0x21
+#define DWXGMAC_CORE_2_20	0x22
 #define DWXLGMAC_CORE_2_00	0x20
 
 /* Device ID */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 3db1cb0fd160c..dd9e2fec53281 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -62,11 +62,16 @@ static void stmmac_xgmac2_c45_format(struct stmmac_priv *priv, int phyaddr,
 static void stmmac_xgmac2_c22_format(struct stmmac_priv *priv, int phyaddr,
 				     int phyreg, u32 *hw_addr)
 {
-	u32 tmp;
+	u32 tmp = 0;
 
+	if (priv->synopsys_id < DWXGMAC_CORE_2_20) {
+		/* Until ver 2.20 XGMAC does not support C22 addr >= 4. Those
+		 * bits above bit 3 of XGMAC_MDIO_C22P register are reserved.
+		 */
+		tmp = readl(priv->ioaddr + XGMAC_MDIO_C22P);
+		tmp &= ~MII_XGMAC_C22P_MASK;
+	}
 	/* Set port as Clause 22 */
-	tmp = readl(priv->ioaddr + XGMAC_MDIO_C22P);
-	tmp &= ~MII_XGMAC_C22P_MASK;
 	tmp |= BIT(phyaddr);
 	writel(tmp, priv->ioaddr + XGMAC_MDIO_C22P);
 
@@ -132,8 +137,9 @@ static int stmmac_xgmac2_mdio_read_c22(struct mii_bus *bus, int phyaddr,
 
 	priv = netdev_priv(ndev);
 
-	/* HW does not support C22 addr >= 4 */
-	if (phyaddr > MII_XGMAC_MAX_C22ADDR)
+	/* Until ver 2.20 XGMAC does not support C22 addr >= 4 */
+	if (priv->synopsys_id < DWXGMAC_CORE_2_20 &&
+	    phyaddr > MII_XGMAC_MAX_C22ADDR)
 		return -ENODEV;
 
 	stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr);
@@ -209,8 +215,9 @@ static int stmmac_xgmac2_mdio_write_c22(struct mii_bus *bus, int phyaddr,
 
 	priv = netdev_priv(ndev);
 
-	/* HW does not support C22 addr >= 4 */
-	if (phyaddr > MII_XGMAC_MAX_C22ADDR)
+	/* Until ver 2.20 XGMAC does not support C22 addr >= 4 */
+	if (priv->synopsys_id < DWXGMAC_CORE_2_20 &&
+	    phyaddr > MII_XGMAC_MAX_C22ADDR)
 		return -ENODEV;
 
 	stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr);
@@ -551,13 +558,18 @@ int stmmac_mdio_register(struct net_device *ndev)
 		new_bus->read_c45 = &stmmac_xgmac2_mdio_read_c45;
 		new_bus->write_c45 = &stmmac_xgmac2_mdio_write_c45;
 
-		/* Right now only C22 phys are supported */
-		max_addr = MII_XGMAC_MAX_C22ADDR + 1;
+		if (priv->synopsys_id < DWXGMAC_CORE_2_20) {
+			/* Right now only C22 phys are supported */
+			max_addr = MII_XGMAC_MAX_C22ADDR + 1;
 
-		/* Check if DT specified an unsupported phy addr */
-		if (priv->plat->phy_addr > MII_XGMAC_MAX_C22ADDR)
-			dev_err(dev, "Unsupported phy_addr (max=%d)\n",
+			/* Check if DT specified an unsupported phy addr */
+			if (priv->plat->phy_addr > MII_XGMAC_MAX_C22ADDR)
+				dev_err(dev, "Unsupported phy_addr (max=%d)\n",
 					MII_XGMAC_MAX_C22ADDR);
+		} else {
+			/* XGMAC version 2.20 onwards support 32 phy addr */
+			max_addr = PHY_MAX_ADDR;
+		}
 	} else {
 		new_bus->read = &stmmac_mdio_read_c22;
 		new_bus->write = &stmmac_mdio_write_c22;
-- 
GitLab


From eb1388553ef4f30d75ed7d5b8eb55ed849f685b5 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 31 Jul 2023 17:47:15 +0200
Subject: [PATCH 0735/1806] selftests: router_bridge: Add remastering tests

Add two tests to deslave a port from and reenslave to a bridge. This should
retain the ability of the system to forward traffic, but on an offloading
driver that is sensitive to ordering of operations, it might not.

The first test does this configuration in a way that relies on
vlan_default_pvid to assign the PVID. The second test disables that
autoconfiguration and configures PVID by hand in a separate step.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/router_bridge.sh | 26 +++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/router_bridge.sh b/tools/testing/selftests/net/forwarding/router_bridge.sh
index 4f33db04699d0..0182eb2abfa68 100755
--- a/tools/testing/selftests/net/forwarding/router_bridge.sh
+++ b/tools/testing/selftests/net/forwarding/router_bridge.sh
@@ -20,6 +20,9 @@
 # +---------------------------------------------------------------------------+
 
 ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	config_remaster
 	ping_ipv4
 	ping_ipv6
 	config_remove_pvid
@@ -28,6 +31,9 @@ ALL_TESTS="
 	config_add_pvid
 	ping_ipv4
 	ping_ipv6
+	config_late_pvid
+	ping_ipv4
+	ping_ipv6
 "
 NUM_NETIFS=4
 source lib.sh
@@ -86,6 +92,15 @@ router_destroy()
 	ip link del dev br1
 }
 
+config_remaster()
+{
+	log_info "Remaster bridge slave"
+
+	ip link set dev $swp1 nomaster
+	sleep 2
+	ip link set dev $swp1 master br1
+}
+
 config_remove_pvid()
 {
 	log_info "Remove PVID from the bridge"
@@ -102,6 +117,17 @@ config_add_pvid()
 	sleep 2
 }
 
+config_late_pvid()
+{
+	log_info "Add bridge PVID after enslaving port"
+
+	ip link set dev $swp1 nomaster
+	ip link set dev br1 type bridge vlan_default_pvid 0
+	sleep 2
+	ip link set dev $swp1 master br1
+	ip link set dev br1 type bridge vlan_default_pvid 1
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
GitLab


From 0a06e0c1af97e5b9510cf29b7a7ac2e9dc4b612c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 31 Jul 2023 17:47:16 +0200
Subject: [PATCH 0736/1806] selftests: router_bridge_1d: Add a new selftest

Add a selftest to verify that routing through a 1d bridge works when VLAN
upper of a physical port is used instead of a physical port. Also verify
that when a port is attached to an already-configured bridge, the
configuration is applied.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/forwarding/Makefile |   1 +
 .../net/forwarding/router_bridge_1d.sh        | 185 ++++++++++++++++++
 2 files changed, 186 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_bridge_1d.sh

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 2d8bb72762a47..96b6dcefbc651 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -64,6 +64,7 @@ TEST_PROGS = bridge_igmp.sh \
 	q_in_vni_ipv6.sh \
 	q_in_vni.sh \
 	router_bridge.sh \
+	router_bridge_1d.sh \
 	router_bridge_vlan.sh \
 	router_bridge_pvid_vlan_upper.sh \
 	router_bridge_vlan_upper_pvid.sh \
diff --git a/tools/testing/selftests/net/forwarding/router_bridge_1d.sh b/tools/testing/selftests/net/forwarding/router_bridge_1d.sh
new file mode 100755
index 0000000000000..6d51f2ca72a21
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_bridge_1d.sh
@@ -0,0 +1,185 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +---------------------------------------------+      +----------------------+
+# | H1 (vrf)                                    |      |             H2 (vrf) |
+# |    + $h1.100            + $h1.200           |      |  + $h2               |
+# |    | 192.0.2.1/28       | 192.0.2.17/28     |      |  | 192.0.2.130/28    |
+# |    | 2001:db8:1::1/64   | 2001:db8:3::1/64  |      |  | 192.0.2.146/28    |
+# |    \_________ __________/                   |      |  | 2001:db8:2::2/64  |
+# |              V                              |      |  | 2001:db8:4::2/64  |
+# |              + $h1                          |      |  |                   |
+# +--------------|------------------------------+      +--|-------------------+
+#                |                                        |
+# +--------------|----------------------------------------|-------------------+
+# | SW           + $swp1                                  + $swp2             |
+# |              |                                          192.0.2.129/28    |
+# |              |                                          192.0.2.145/28    |
+# |              |                                          2001:db8:2::1/64  |
+# |      ________^___________________________               2001:db8:4::1/64  |
+# |     /                                    \                                |
+# | +---|------------------------------+ +---|------------------------------+ |
+# | |   + $swp1.100   BR1 (802.1d)     | |   + $swp1.200   BR2 (802.1d)     | |
+# | |                 192.0.2.2/28     | |                 192.0.2.18/28    | |
+# | |                 2001:db8:1::2/64 | |                 2001:db8:3::2/64 | |
+# | |                                  | |                                  | |
+# | +----------------------------------+ +----------------------------------+ |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	config_remaster
+	ping_ipv4
+	ping_ipv6
+"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+	vlan_create $h1 100 v$h1 192.0.2.1/28 2001:db8:1::1/64
+	vlan_create $h1 200 v$h1 192.0.2.17/28 2001:db8:3::1/64
+	ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2
+	ip -4 route add 192.0.2.144/28 vrf v$h1 nexthop via 192.0.2.18
+	ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+	ip -6 route add 2001:db8:4::/64 vrf v$h1 nexthop via 2001:db8:3::2
+}
+
+h1_destroy()
+{
+	ip -6 route del 2001:db8:4::/64 vrf v$h1
+	ip -6 route del 2001:db8:2::/64 vrf v$h1
+	ip -4 route del 192.0.2.144/28 vrf v$h1
+	ip -4 route del 192.0.2.128/28 vrf v$h1
+	vlan_destroy $h1 200
+	vlan_destroy $h1 100
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 \
+			   192.0.2.146/28 2001:db8:4::2/64
+	ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129
+	ip -4 route add 192.0.2.16/28 vrf v$h2 nexthop via 192.0.2.145
+	ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+	ip -6 route add 2001:db8:3::/64 vrf v$h2 nexthop via 2001:db8:4::1
+}
+
+h2_destroy()
+{
+	ip -6 route del 2001:db8:3::/64 vrf v$h2
+	ip -6 route del 2001:db8:1::/64 vrf v$h2
+	ip -4 route del 192.0.2.16/28 vrf v$h2
+	ip -4 route del 192.0.2.0/28 vrf v$h2
+	simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64 \
+			   192.0.2.146/28 2001:db8:4::2/64
+}
+
+router_create()
+{
+	ip link set dev $swp1 up
+
+	vlan_create $swp1 100
+	ip link add name br1 type bridge vlan_filtering 0
+	ip link set dev br1 address $(mac_get $swp1.100)
+	ip link set dev $swp1.100 master br1
+	__addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+	ip link set dev br1 up
+
+	vlan_create $swp1 200
+	ip link add name br2 type bridge vlan_filtering 0
+	ip link set dev br2 address $(mac_get $swp1.200)
+	ip link set dev $swp1.200 master br2
+	__addr_add_del br2 add 192.0.2.18/28 2001:db8:3::2/64
+	ip link set dev br2 up
+
+	ip link set dev $swp2 up
+	__addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64 \
+				 192.0.2.145/28 2001:db8:4::1/64
+}
+
+router_destroy()
+{
+	__addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64 \
+				 192.0.2.145/28 2001:db8:4::1/64
+	ip link set dev $swp2 down
+
+	__addr_add_del br2 del 192.0.2.18/28 2001:db8:3::2/64
+	ip link set dev $swp1.200 nomaster
+	ip link del dev br2
+	vlan_destroy $swp1 200
+
+	__addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
+	ip link set dev $swp1.100 nomaster
+	ip link del dev br1
+	vlan_destroy $swp1 100
+
+	ip link set dev $swp1 down
+}
+
+config_remaster()
+{
+	log_info "Remaster bridge slaves"
+
+	ip link set dev $swp1.100 nomaster
+	ip link set dev $swp1.200 nomaster
+	sleep 2
+	ip link set dev $swp1.200 master br2
+	ip link set dev $swp1.100 master br1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.130 ": via 100"
+	ping_test $h1 192.0.2.146 ": via 200"
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2 ": via 100"
+	ping6_test $h1 2001:db8:4::2 ": via 200"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From 49e15dec8b90314ad94f20c5435810dd3229df98 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 31 Jul 2023 17:47:17 +0200
Subject: [PATCH 0737/1806] selftests: router_bridge_vlan_upper: Add a new
 selftest

Add a selftest that verifies routing through VLAN bridge uppers.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/forwarding/Makefile |   1 +
 .../forwarding/router_bridge_vlan_upper.sh    | 169 ++++++++++++++++++
 2 files changed, 170 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_bridge_vlan_upper.sh

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 96b6dcefbc651..44a0308d8bc22 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -66,6 +66,7 @@ TEST_PROGS = bridge_igmp.sh \
 	router_bridge.sh \
 	router_bridge_1d.sh \
 	router_bridge_vlan.sh \
+	router_bridge_vlan_upper.sh \
 	router_bridge_pvid_vlan_upper.sh \
 	router_bridge_vlan_upper_pvid.sh \
 	router_broadcast.sh \
diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper.sh
new file mode 100755
index 0000000000000..215309ea1c8c0
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper.sh
@@ -0,0 +1,169 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +------------------------+                           +----------------------+
+# | H1 (vrf)               |                           |             H2 (vrf) |
+# |    + $h1.555           |                           |  + $h2.777           |
+# |    | 192.0.2.1/28      |                           |  | 192.0.2.18/28     |
+# |    | 2001:db8:1::1/64  |                           |  | 2001:db8:2::2/64  |
+# |    |                   |                           |  |                   |
+# |    + $h1               |                           |  + $h2               |
+# +----|-------------------+                           +--|-------------------+
+#      |                                                  |
+# +----|--------------------------------------------------|-------------------+
+# | SW |                                                  |                   |
+# | +--|--------------------------------------------------|-----------------+ |
+# | |  + $swp1                   BR1 (802.1q)             + $swp2           | |
+# | |                                                                       | |
+# | +------+------------------------------------------+---------------------+ |
+# |        |                                          |                       |
+# |        + br1.555                                  + br1.777               |
+# |          192.0.2.2/28                               192.0.2.17/28         |
+# |          2001:db8:1::2/64                           2001:db8:2::1/64      |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	respin_config
+	ping_ipv4
+	ping_ipv6
+"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+	vlan_create $h1 555 v$h1 192.0.2.1/28 2001:db8:1::1/64
+	ip -4 route add 192.0.2.16/28 vrf v$h1 nexthop via 192.0.2.2
+	ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip -6 route del 2001:db8:2::/64 vrf v$h1
+	ip -4 route del 192.0.2.16/28 vrf v$h1
+	vlan_destroy $h1 555
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2
+	vlan_create $h2 777 v$h2 192.0.2.18/28 2001:db8:2::2/64
+	ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.17
+	ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip -6 route del 2001:db8:1::/64 vrf v$h2
+	ip -4 route del 192.0.2.0/28 vrf v$h2
+	vlan_destroy $h2 777
+	simple_if_fini $h2
+}
+
+router_create()
+{
+	ip link add name br1 address $(mac_get $swp1) \
+		type bridge vlan_filtering 1
+	ip link set dev br1 up
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp2 master br1
+	ip link set dev $swp1 up
+	ip link set dev $swp2 up
+
+	bridge vlan add dev br1 vid 555 self
+	bridge vlan add dev br1 vid 777 self
+	bridge vlan add dev $swp1 vid 555
+	bridge vlan add dev $swp2 vid 777
+
+	vlan_create br1 555 "" 192.0.2.2/28 2001:db8:1::2/64
+	vlan_create br1 777 "" 192.0.2.17/28 2001:db8:2::1/64
+}
+
+router_destroy()
+{
+	vlan_destroy br1 777
+	vlan_destroy br1 555
+
+	bridge vlan del dev $swp2 vid 777
+	bridge vlan del dev $swp1 vid 555
+	bridge vlan del dev br1 vid 777 self
+	bridge vlan del dev br1 vid 555 self
+
+	ip link set dev $swp2 down nomaster
+	ip link set dev $swp1 down nomaster
+
+	ip link set dev br1 down
+	ip link del dev br1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.18
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+respin_config()
+{
+	log_info "Remaster bridge slave"
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 nomaster
+
+	sleep 2
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp2 master br1
+
+	bridge vlan add dev $swp1 vid 555
+	bridge vlan add dev $swp2 vid 777
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From 3f0c4e70a9efbfbac6205e0cb2a79ccd5810589b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 31 Jul 2023 17:47:18 +0200
Subject: [PATCH 0738/1806] selftests: router_bridge_lag: Add a new selftest

Add a selftest to verify that routing through a bridge works when LAG is
used instead of physical ports.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/forwarding/Makefile |   1 +
 .../net/forwarding/router_bridge_lag.sh       | 323 ++++++++++++++++++
 2 files changed, 324 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_bridge_lag.sh

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 44a0308d8bc22..2fd0f4f872109 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -65,6 +65,7 @@ TEST_PROGS = bridge_igmp.sh \
 	q_in_vni.sh \
 	router_bridge.sh \
 	router_bridge_1d.sh \
+	router_bridge_lag.sh \
 	router_bridge_vlan.sh \
 	router_bridge_vlan_upper.sh \
 	router_bridge_pvid_vlan_upper.sh \
diff --git a/tools/testing/selftests/net/forwarding/router_bridge_lag.sh b/tools/testing/selftests/net/forwarding/router_bridge_lag.sh
new file mode 100755
index 0000000000000..f05ffe213c461
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_bridge_lag.sh
@@ -0,0 +1,323 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +----------------------------+                   +--------------------------+
+# | H1 (vrf)                   |                   |                 H2 (vrf) |
+# |                            |                   |                          |
+# |        + LAG1 (team)       |                   |     + LAG4 (team)        |
+# |        | 192.0.2.1/28      |                   |     | 192.0.2.130/28     |
+# |        | 2001:db8:1::1/64  |                   |     | 2001:db8:2::2/64   |
+# |      __^___                |                   |   __^_____               |
+# |     /      \               |                   |  /        \              |
+# |    + $h1    + $h4          |                   | + $h2      + $h3         |
+# |    |        |              |                   | |          |             |
+# +----|--------|--------------+                   +-|----------|-------------+
+#      |        |                                    |          |
+# +----|--------|------------------------------------|----------|-------------+
+# | SW |        |                                    |          |             |
+# |    + $swp1  + $swp4                              + $swp2    + $swp3       |
+# |     \__ ___/                                      \__ _____/              |
+# |        v                                             v                    |
+# | +------|-------------------------------+             |                    |
+# | |      + LAG2       BR1 (802.1q)       |             + LAG3 (team)        |
+# | |        (team)       192.0.2.2/28     |               192.0.2.129/28     |
+# | |                     2001:db8:1::2/64 |               2001:db8:2::1/64   |
+# | |                                      |                                  |
+# | +--------------------------------------+                                  |
+# +---------------------------------------------------------------------------+
+
+: ${ALL_TESTS:="
+	ping_ipv4
+	ping_ipv6
+
+	$(: exercise remastering of LAG2 slaves )
+	config_deslave_swp4
+	config_wait
+	ping_ipv4
+	ping_ipv6
+	config_enslave_swp4
+	config_deslave_swp1
+	config_wait
+	ping_ipv4
+	ping_ipv6
+	config_deslave_swp4
+	config_enslave_swp1
+	config_enslave_swp4
+	config_wait
+	ping_ipv4
+	ping_ipv6
+
+	$(: exercise remastering of LAG2 itself )
+	config_remaster_lag2
+	config_wait
+	ping_ipv4
+	ping_ipv6
+
+	$(: exercise remastering of LAG3 slaves )
+	config_deslave_swp2
+	config_wait
+	ping_ipv4
+	ping_ipv6
+	config_enslave_swp2
+	config_deslave_swp3
+	config_wait
+	ping_ipv4
+	ping_ipv6
+	config_deslave_swp2
+	config_enslave_swp3
+	config_enslave_swp2
+	config_wait
+	ping_ipv4
+	ping_ipv6
+
+	$(: move LAG3 to a bridge and then out )
+	config_remaster_lag3
+	config_wait
+	ping_ipv4
+	ping_ipv6
+    "}
+NUM_NETIFS=8
+: ${lib_dir:=.}
+source $lib_dir/lib.sh
+$EXTRA_SOURCE
+
+h1_create()
+{
+	team_create lag1 lacp
+	ip link set dev lag1 address $(mac_get $h1)
+	ip link set dev $h1 master lag1
+	ip link set dev $h4 master lag1
+	simple_if_init lag1 192.0.2.1/28 2001:db8:1::1/64
+	ip link set dev $h1 up
+	ip link set dev $h4 up
+	ip -4 route add 192.0.2.128/28 vrf vlag1 nexthop via 192.0.2.2
+	ip -6 route add 2001:db8:2::/64 vrf vlag1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip -6 route del 2001:db8:2::/64 vrf vlag1
+	ip -4 route del 192.0.2.128/28 vrf vlag1
+	ip link set dev $h4 down
+	ip link set dev $h1 down
+	simple_if_fini lag1 192.0.2.1/28 2001:db8:1::1/64
+	ip link set dev $h4 nomaster
+	ip link set dev $h1 nomaster
+	team_destroy lag1
+}
+
+h2_create()
+{
+	team_create lag4 lacp
+	ip link set dev lag4 address $(mac_get $h2)
+	ip link set dev $h2 master lag4
+	ip link set dev $h3 master lag4
+	simple_if_init lag4 192.0.2.130/28 2001:db8:2::2/64
+	ip link set dev $h2 up
+	ip link set dev $h3 up
+	ip -4 route add 192.0.2.0/28 vrf vlag4 nexthop via 192.0.2.129
+	ip -6 route add 2001:db8:1::/64 vrf vlag4 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip -6 route del 2001:db8:1::/64 vrf vlag4
+	ip -4 route del 192.0.2.0/28 vrf vlag4
+	ip link set dev $h3 down
+	ip link set dev $h2 down
+	simple_if_fini lag4 192.0.2.130/28 2001:db8:2::2/64
+	ip link set dev $h3 nomaster
+	ip link set dev $h2 nomaster
+	team_destroy lag4
+}
+
+router_create()
+{
+	team_create lag2 lacp
+	ip link set dev lag2 address $(mac_get $swp1)
+	ip link set dev $swp1 master lag2
+	ip link set dev $swp4 master lag2
+
+	ip link add name br1 address $(mac_get lag2) \
+		type bridge vlan_filtering 1
+	ip link set dev lag2 master br1
+
+	ip link set dev $swp1 up
+	ip link set dev $swp4 up
+	ip link set dev br1 up
+
+	__addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+
+	team_create lag3 lacp
+	ip link set dev lag3 address $(mac_get $swp2)
+	ip link set dev $swp2 master lag3
+	ip link set dev $swp3 master lag3
+	ip link set dev $swp2 up
+	ip link set dev $swp3 up
+	__addr_add_del lag3 add 192.0.2.129/28 2001:db8:2::1/64
+}
+
+router_destroy()
+{
+	__addr_add_del lag3 del 192.0.2.129/28 2001:db8:2::1/64
+	ip link set dev $swp3 down
+	ip link set dev $swp2 down
+	ip link set dev $swp3 nomaster
+	ip link set dev $swp2 nomaster
+	team_destroy lag3
+
+	__addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
+
+	ip link set dev $swp4 down
+	ip link set dev $swp1 down
+	ip link set dev br1 down
+
+	ip link set dev lag2 nomaster
+	ip link del dev br1
+
+	ip link set dev $swp4 nomaster
+	ip link set dev $swp1 nomaster
+	team_destroy lag2
+}
+
+config_remaster_lag2()
+{
+	log_info "Remaster bridge slave"
+
+	ip link set dev lag2 nomaster
+	sleep 2
+	ip link set dev lag2 master br1
+}
+
+config_remaster_lag3()
+{
+	log_info "Move lag3 to the bridge, then out again"
+
+	ip link set dev lag3 master br1
+	sleep 2
+	ip link set dev lag3 nomaster
+}
+
+config_deslave()
+{
+	local netdev=$1; shift
+
+	log_info "Deslave $netdev"
+	ip link set dev $netdev down
+	ip link set dev $netdev nomaster
+	ip link set dev $netdev up
+}
+
+config_deslave_swp1()
+{
+	config_deslave $swp1
+}
+
+config_deslave_swp2()
+{
+	config_deslave $swp2
+}
+
+config_deslave_swp3()
+{
+	config_deslave $swp3
+}
+
+config_deslave_swp4()
+{
+	config_deslave $swp4
+}
+
+config_enslave()
+{
+	local netdev=$1; shift
+	local master=$1; shift
+
+	log_info "Enslave $netdev to $master"
+	ip link set dev $netdev down
+	ip link set dev $netdev master $master
+	ip link set dev $netdev up
+}
+
+config_enslave_swp1()
+{
+	config_enslave $swp1 lag2
+}
+
+config_enslave_swp2()
+{
+	config_enslave $swp2 lag3
+}
+
+config_enslave_swp3()
+{
+	config_enslave $swp3 lag3
+}
+
+config_enslave_swp4()
+{
+	config_enslave $swp4 lag2
+}
+
+config_wait()
+{
+	setup_wait_dev lag2
+	setup_wait_dev lag3
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	h4=${NETIFS[p7]}
+	swp4=${NETIFS[p8]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test lag1 192.0.2.130
+}
+
+ping_ipv6()
+{
+	ping6_test lag1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From 24e84656e43260ea39a22efc56825e1dadfdaa5f Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 31 Jul 2023 17:47:19 +0200
Subject: [PATCH 0739/1806] selftests: router_bridge_1d_lag: Add a new selftest

Add a selftest to verify that routing through several bridges works when
LAG VLANs are used instead of physical ports, and that routing through LAG
VLANs themselves works as physical ports are de/enslaved.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/forwarding/Makefile |   1 +
 .../net/forwarding/router_bridge_1d_lag.sh    | 408 ++++++++++++++++++
 2 files changed, 409 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 2fd0f4f872109..74e754e266c3b 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -65,6 +65,7 @@ TEST_PROGS = bridge_igmp.sh \
 	q_in_vni.sh \
 	router_bridge.sh \
 	router_bridge_1d.sh \
+	router_bridge_1d_lag.sh \
 	router_bridge_lag.sh \
 	router_bridge_vlan.sh \
 	router_bridge_vlan_upper.sh \
diff --git a/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh b/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh
new file mode 100755
index 0000000000000..e064b946e8213
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh
@@ -0,0 +1,408 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +--------------------------------------------+
+# | H1 (vrf)                                   |
+# |                                            |
+# |    + LAG1.100          + LAG1.200          |
+# |    | 192.0.2.1/28      | 192.0.2.17/28     |
+# |    | 2001:db8:1::1/64  | 2001:db8:3:1/64   |
+# |    \___________ _______/                   |
+# |                v                           |
+# |                + LAG1 (team)               |
+# |                |                           |
+# |            ____^____                       |
+# |           /         \                      |
+# |          + $h1       + $h4                 |
+# |          |           |                     |
+# +----------|-----------|---------------------+
+#            |           |
+# +----------|-----------|---------------------+
+# | SW       |           |                     |
+# |          + $swp1     + $swp4               |
+# |           \____ ____/                      |
+# |                v                           |
+# |    LAG2 (team) +                           |
+# |                |                           |
+# |         _______^______________             |
+# |        /                      \            |
+# | +------|------------+ +-------|----------+ |
+# | |      + LAG2.100   | |       + LAG2.200 | |
+# | |                   | |                  | |
+# | |  BR1 (802.1d)     | | BR2 (802.1d)     | |
+# | |  192.0.2.2/28     | | 192.0.2.18/28    | |
+# | |  2001:db8:1::2/64 | | 2001:db8:3:2/64  | |
+# | |                   | |                  | |
+# | +-------------------+ +------------------+ |
+# |                                            |
+# |  + LAG3.100             + LAG3.200         |
+# |  | 192.0.2.129/28       | 192.0.2.145/28   |
+# |  | 2001:db8:2::1/64     | 2001:db8:4::1/64 |
+# |  |                      |                  |
+# |  \_________ ___________/                   |
+# |            v                               |
+# |            + LAG3 (team)                   |
+# |        ____|____                           |
+# |       /         \                          |
+# |       + $swp2   + $swp3                    |
+# |       |         |                          |
+# +-------|---------|--------------------------+
+#         |         |
+# +-------|---------|--------------------------+
+# |       |         |                          |
+# |       + $h2     + $h3                      |
+# |       \____ ___/                           |
+# |            |                               |
+# |            + LAG4 (team)                   |
+# |            |                               |
+# |  __________^__________                     |
+# | /                     \                    |
+# | |                     |                    |
+# | + LAG4.100            + LAG4.200           |
+# |   192.0.2.130/28        192.0.2.146/28     |
+# |   2001:db8:2::2/64      2001:db8:4::2/64   |
+# |                                            |
+# | H2 (vrf)                                   |
+# +--------------------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+
+	$(: exercise remastering of LAG2 slaves )
+	config_deslave_swp4
+	config_wait
+	ping_ipv4
+	ping_ipv6
+	config_enslave_swp4
+	config_deslave_swp1
+	config_wait
+	ping_ipv4
+	ping_ipv6
+	config_deslave_swp4
+	config_enslave_swp1
+	config_enslave_swp4
+	config_wait
+	ping_ipv4
+	ping_ipv6
+
+	$(: exercise remastering of LAG2 itself )
+	config_remaster_lag2
+	config_wait
+	ping_ipv4
+	ping_ipv6
+
+	$(: exercise remastering of LAG3 slaves )
+	config_deslave_swp2
+	config_wait
+	ping_ipv4
+	ping_ipv6
+	config_enslave_swp2
+	config_deslave_swp3
+	config_wait
+	ping_ipv4
+	ping_ipv6
+	config_deslave_swp2
+	config_enslave_swp3
+	config_enslave_swp2
+	config_wait
+	ping_ipv4
+	ping_ipv6
+"
+NUM_NETIFS=8
+source lib.sh
+
+h1_create()
+{
+	team_create lag1 lacp
+	ip link set dev lag1 addrgenmode none
+	ip link set dev lag1 address $(mac_get $h1)
+	ip link set dev $h1 master lag1
+	ip link set dev $h4 master lag1
+	simple_if_init lag1
+	ip link set dev $h1 up
+	ip link set dev $h4 up
+
+	vlan_create lag1 100 vlag1 192.0.2.1/28 2001:db8:1::1/64
+	vlan_create lag1 200 vlag1 192.0.2.17/28 2001:db8:3::1/64
+
+	ip -4 route add 192.0.2.128/28 vrf vlag1 nexthop via 192.0.2.2
+	ip -6 route add 2001:db8:2::/64 vrf vlag1 nexthop via 2001:db8:1::2
+
+	ip -4 route add 192.0.2.144/28 vrf vlag1 nexthop via 192.0.2.18
+	ip -6 route add 2001:db8:4::/64 vrf vlag1 nexthop via 2001:db8:3::2
+}
+
+h1_destroy()
+{
+	ip -6 route del 2001:db8:4::/64 vrf vlag1
+	ip -4 route del 192.0.2.144/28 vrf vlag1
+
+	ip -6 route del 2001:db8:2::/64 vrf vlag1
+	ip -4 route del 192.0.2.128/28 vrf vlag1
+
+	vlan_destroy lag1 200
+	vlan_destroy lag1 100
+
+	ip link set dev $h4 down
+	ip link set dev $h1 down
+	simple_if_fini lag1
+	ip link set dev $h4 nomaster
+	ip link set dev $h1 nomaster
+	team_destroy lag1
+}
+
+h2_create()
+{
+	team_create lag4 lacp
+	ip link set dev lag4 addrgenmode none
+	ip link set dev lag4 address $(mac_get $h2)
+	ip link set dev $h2 master lag4
+	ip link set dev $h3 master lag4
+	simple_if_init lag4
+	ip link set dev $h2 up
+	ip link set dev $h3 up
+
+	vlan_create lag4 100 vlag4 192.0.2.130/28 2001:db8:2::2/64
+	vlan_create lag4 200 vlag4 192.0.2.146/28 2001:db8:4::2/64
+
+	ip -4 route add 192.0.2.0/28 vrf vlag4 nexthop via 192.0.2.129
+	ip -6 route add 2001:db8:1::/64 vrf vlag4 nexthop via 2001:db8:2::1
+
+	ip -4 route add 192.0.2.16/28 vrf vlag4 nexthop via 192.0.2.145
+	ip -6 route add 2001:db8:3::/64 vrf vlag4 nexthop via 2001:db8:4::1
+}
+
+h2_destroy()
+{
+	ip -6 route del 2001:db8:3::/64 vrf vlag4
+	ip -4 route del 192.0.2.16/28 vrf vlag4
+
+	ip -6 route del 2001:db8:1::/64 vrf vlag4
+	ip -4 route del 192.0.2.0/28 vrf vlag4
+
+	vlan_destroy lag4 200
+	vlan_destroy lag4 100
+
+	ip link set dev $h3 down
+	ip link set dev $h2 down
+	simple_if_fini lag4
+	ip link set dev $h3 nomaster
+	ip link set dev $h2 nomaster
+	team_destroy lag4
+}
+
+router_create()
+{
+	team_create lag2 lacp
+	ip link set dev lag2 addrgenmode none
+	ip link set dev lag2 address $(mac_get $swp1)
+	ip link set dev $swp1 master lag2
+	ip link set dev $swp4 master lag2
+
+	vlan_create lag2 100
+	vlan_create lag2 200
+
+	ip link add name br1 type bridge vlan_filtering 0
+	ip link set dev br1 address $(mac_get lag2.100)
+	ip link set dev lag2.100 master br1
+
+	ip link add name br2 type bridge vlan_filtering 0
+	ip link set dev br2 address $(mac_get lag2.200)
+	ip link set dev lag2.200 master br2
+
+	ip link set dev $swp1 up
+	ip link set dev $swp4 up
+	ip link set dev br1 up
+	ip link set dev br2 up
+
+	__addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+	__addr_add_del br2 add 192.0.2.18/28 2001:db8:3::2/64
+
+	team_create lag3 lacp
+	ip link set dev lag3 addrgenmode none
+	ip link set dev lag3 address $(mac_get $swp2)
+	ip link set dev $swp2 master lag3
+	ip link set dev $swp3 master lag3
+	ip link set dev $swp2 up
+	ip link set dev $swp3 up
+
+	vlan_create lag3 100
+	vlan_create lag3 200
+
+	__addr_add_del lag3.100 add 192.0.2.129/28 2001:db8:2::1/64
+	__addr_add_del lag3.200 add 192.0.2.145/28 2001:db8:4::1/64
+}
+
+router_destroy()
+{
+	__addr_add_del lag3.200 del 192.0.2.145/28 2001:db8:4::1/64
+	__addr_add_del lag3.100 del 192.0.2.129/28 2001:db8:2::1/64
+
+	vlan_destroy lag3 200
+	vlan_destroy lag3 100
+
+	ip link set dev $swp3 down
+	ip link set dev $swp2 down
+	ip link set dev $swp3 nomaster
+	ip link set dev $swp2 nomaster
+	team_destroy lag3
+
+	__addr_add_del br2 del 192.0.2.18/28 2001:db8:3::2/64
+	__addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
+
+	ip link set dev br2 down
+	ip link set dev br1 down
+	ip link set dev $swp4 down
+	ip link set dev $swp1 down
+
+	ip link set dev lag2.200 nomaster
+	ip link del dev br2
+
+	ip link set dev lag2.100 nomaster
+	ip link del dev br1
+
+	vlan_destroy lag2 200
+	vlan_destroy lag2 100
+
+	ip link set dev $swp4 nomaster
+	ip link set dev $swp1 nomaster
+	team_destroy lag2
+}
+
+config_remaster_lag2()
+{
+	log_info "Remaster bridge slaves"
+
+	ip link set dev lag2.200 nomaster
+	ip link set dev lag2.100 nomaster
+	sleep 2
+	ip link set dev lag2.100 master br1
+	ip link set dev lag2.200 master br2
+}
+
+config_deslave()
+{
+	local netdev=$1; shift
+
+	log_info "Deslave $netdev"
+	ip link set dev $netdev down
+	ip link set dev $netdev nomaster
+	ip link set dev $netdev up
+}
+
+config_deslave_swp1()
+{
+	config_deslave $swp1
+}
+
+config_deslave_swp2()
+{
+	config_deslave $swp2
+}
+
+config_deslave_swp3()
+{
+	config_deslave $swp3
+}
+
+config_deslave_swp4()
+{
+	config_deslave $swp4
+}
+
+config_enslave()
+{
+	local netdev=$1; shift
+	local master=$1; shift
+
+	log_info "Enslave $netdev to $master"
+	ip link set dev $netdev down
+	ip link set dev $netdev master $master
+	ip link set dev $netdev up
+}
+
+config_enslave_swp1()
+{
+	config_enslave $swp1 lag2
+}
+
+config_enslave_swp2()
+{
+	config_enslave $swp2 lag3
+}
+
+config_enslave_swp3()
+{
+	config_enslave $swp3 lag3
+}
+
+config_enslave_swp4()
+{
+	config_enslave $swp4 lag2
+}
+
+config_wait()
+{
+	setup_wait_dev lag2
+	setup_wait_dev lag3
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	h4=${NETIFS[p7]}
+	swp4=${NETIFS[p8]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test lag1.100 192.0.2.130 ": via 100"
+	ping_test lag1.200 192.0.2.146 ": via 200"
+}
+
+ping_ipv6()
+{
+	ping6_test lag1.100 2001:db8:2::2 ": via 100"
+	ping6_test lag1.200 2001:db8:4::2 ": via 200"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From 4308967d98c377a5d34db4f1111e6900a202dd24 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 31 Jul 2023 17:47:20 +0200
Subject: [PATCH 0740/1806] selftests: mlxsw: rif_lag: Add a new selftest

This test verifies driver behavior with regards to creation of RIFs for a
LAG as ports are added or removed to/from it.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/rif_lag.sh    | 136 ++++++++++++++++++
 1 file changed, 136 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh
new file mode 100755
index 0000000000000..e28f978104f3e
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh
@@ -0,0 +1,136 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	lag_rif_add
+	lag_rif_nomaster
+	lag_rif_remaster
+	lag_rif_nomaster_addr
+"
+
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+
+	team_create lag1 lacp
+	ip link set dev lag1 addrgenmode none
+	ip link set dev lag1 address $(mac_get $swp1)
+
+	team_create lag2 lacp
+	ip link set dev lag2 addrgenmode none
+	ip link set dev lag2 address $(mac_get $swp2)
+
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 master lag2
+	ip link set dev $swp2 up
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp2 down
+
+	ip link set dev $swp1 nomaster
+	ip link set dev $swp1 down
+
+	ip link del dev lag2
+	ip link del dev lag1
+}
+
+lag_rif_add()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	__addr_add_del lag1 add 192.0.2.2/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIF for LAG on address addition"
+}
+
+lag_rif_nomaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 nomaster
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 - 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Drop RIF for LAG on port deslavement"
+}
+
+lag_rif_remaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 down
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+	setup_wait_dev $swp1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIF for LAG on port reenslavement"
+}
+
+lag_rif_nomaster_addr()
+{
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+
+	# Adding an address while the port is LAG'd shouldn't generate a RIF.
+	__addr_add_del $swp1 add 192.0.2.65/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "After adding IP: Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	# Removing the port from LAG should drop RIF for the LAG (as tested in
+	# lag_rif_nomaster), but since the port now has an address, it should
+	# gain a RIF.
+	ip link set dev $swp1 nomaster
+	sleep 1
+	local rifs_occ_t2=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0))
+
+	((expected_rifs == rifs_occ_t2))
+	check_err $? "After deslaving: Expected $expected_rifs RIFs, $rifs_occ_t2 are used"
+
+	__addr_add_del $swp1 del 192.0.2.65/28
+	log_test "Add RIF for port on deslavement from LAG"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From 6b3f46837c32e3c4007176111069d22762bedaaa Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 31 Jul 2023 17:47:21 +0200
Subject: [PATCH 0741/1806] selftests: mlxsw: rif_lag_vlan: Add a new selftest

This test verifies driver behavior with regards to creation of RIFs for LAG
VLAN uppers as ports are added or removed to/from the LAG.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/rif_lag_vlan.sh         | 146 ++++++++++++++++++
 1 file changed, 146 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh
new file mode 100755
index 0000000000000..6318cfa6434c2
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh
@@ -0,0 +1,146 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	lag_rif_add
+	lag_rif_nomaster
+	lag_rif_remaster
+	lag_rif_nomaster_addr
+"
+
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+
+	team_create lag1 lacp
+	ip link set dev lag1 addrgenmode none
+	ip link set dev lag1 address $(mac_get $swp1)
+
+	team_create lag2 lacp
+	ip link set dev lag2 addrgenmode none
+	ip link set dev lag2 address $(mac_get $swp2)
+
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 master lag2
+	ip link set dev $swp2 up
+
+	vlan_create lag1 100
+	ip link set dev lag1.100 addrgenmode none
+
+	vlan_create lag1 200
+	ip link set dev lag1.200 addrgenmode none
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link del dev lag1.200
+	ip link del dev lag1.100
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp2 down
+
+	ip link set dev $swp1 nomaster
+	ip link set dev $swp1 down
+
+	ip link del dev lag2
+	ip link del dev lag1
+}
+
+lag_rif_add()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	__addr_add_del lag1.100 add 192.0.2.2/28
+	__addr_add_del lag1.200 add 192.0.2.18/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 2))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIFs for LAG VLANs on address addition"
+}
+
+lag_rif_nomaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 nomaster
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 - 2))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Drop RIFs for LAG VLANs on port deslavement"
+}
+
+lag_rif_remaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 down
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+	setup_wait_dev $swp1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 2))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIFs for LAG VLANs on port reenslavement"
+}
+
+lag_rif_nomaster_addr()
+{
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+
+	# Adding an address while the port is LAG'd shouldn't generate a RIF.
+	__addr_add_del $swp1 add 192.0.2.65/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "After adding IP: Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	# Removing the port from LAG should drop two RIFs for the LAG VLANs (as
+	# tested in lag_rif_nomaster), but since the port now has an address, it
+	# should gain a RIF.
+	ip link set dev $swp1 nomaster
+	sleep 1
+	local rifs_occ_t2=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 - 1))
+
+	((expected_rifs == rifs_occ_t2))
+	check_err $? "After deslaving: Expected $expected_rifs RIFs, $rifs_occ_t2 are used"
+
+	__addr_add_del $swp1 del 192.0.2.65/28
+	log_test "Add RIF for port on deslavement from LAG"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From 67d5ffb9ed513d08ff81fefde6abc00440d9d4ce Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 31 Jul 2023 17:47:22 +0200
Subject: [PATCH 0742/1806] selftests: mlxsw: rif_bridge: Add a new selftest

This test verifies driver behavior with regards to creation of RIFs for a
bridge as LAGs are added or removed to/from it, and ports added or removed
to/from the LAG.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/rif_bridge.sh | 183 ++++++++++++++++++
 1 file changed, 183 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh
new file mode 100755
index 0000000000000..b79542a4dcc71
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh
@@ -0,0 +1,183 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	bridge_rif_add
+	bridge_rif_nomaster
+	bridge_rif_remaster
+	bridge_rif_nomaster_addr
+	bridge_rif_nomaster_port
+	bridge_rif_remaster_port
+"
+
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+
+	team_create lag1 lacp
+	ip link set dev lag1 addrgenmode none
+	ip link set dev lag1 address $(mac_get $swp1)
+
+	team_create lag2 lacp
+	ip link set dev lag2 addrgenmode none
+	ip link set dev lag2 address $(mac_get $swp2)
+
+	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 addrgenmode none
+	ip link set dev br1 address $(mac_get lag1)
+	ip link set dev br1 up
+
+	ip link set dev lag1 master br1
+
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 master lag2
+	ip link set dev $swp2 up
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp2 down
+
+	ip link set dev $swp1 nomaster
+	ip link set dev $swp1 down
+
+	ip link del dev lag2
+	ip link set dev lag1 nomaster
+	ip link del dev lag1
+
+	ip link del dev br1
+}
+
+bridge_rif_add()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	__addr_add_del br1 add 192.0.2.2/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIF for bridge on address addition"
+}
+
+bridge_rif_nomaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev lag1 nomaster
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 - 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Drop RIF for bridge on LAG deslavement"
+}
+
+bridge_rif_remaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev lag1 master br1
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIF for bridge on LAG reenslavement"
+}
+
+bridge_rif_nomaster_addr()
+{
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+
+	# Adding an address while the LAG is enslaved shouldn't generate a RIF.
+	__addr_add_del lag1 add 192.0.2.65/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "After adding IP: Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	# Removing the LAG from the bridge should drop RIF for the bridge (as
+	# tested in bridge_rif_lag_nomaster), but since the LAG now has an
+	# address, it should gain a RIF.
+	ip link set dev lag1 nomaster
+	sleep 1
+	local rifs_occ_t2=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0))
+
+	((expected_rifs == rifs_occ_t2))
+	check_err $? "After deslaving: Expected $expected_rifs RIFs, $rifs_occ_t2 are used"
+
+	log_test "Add RIF for LAG on deslavement from bridge"
+
+	__addr_add_del lag1 del 192.0.2.65/28
+	ip link set dev lag1 master br1
+	sleep 1
+}
+
+bridge_rif_nomaster_port()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 nomaster
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 - 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Drop RIF for bridge on deslavement of port from LAG"
+}
+
+bridge_rif_remaster_port()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 down
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+	setup_wait_dev $swp1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIF for bridge on reenslavement of port to LAG"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
GitLab


From a67fa91130ca3c20d2529b7c98ea6e8ef7addfa5 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 31 Jul 2023 16:41:10 +0200
Subject: [PATCH 0743/1806] net: stmmac: dwmac-oxnas: remove obsolete dwmac
 glue driver

Due to lack of maintenance and stall of development for a few years now,
and since no new features will ever be added upstream, remove support
for OX810 and OX820 ethernet.

Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Daniel Golle <daniel@makrotopia.org>
Acked-by: Andy Shevchenko <andy@kernel.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/Kconfig   |  11 -
 drivers/net/ethernet/stmicro/stmmac/Makefile  |   1 -
 .../net/ethernet/stmicro/stmmac/dwmac-oxnas.c | 244 ------------------
 3 files changed, 256 deletions(-)
 delete mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c

diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 5583f0b055ec7..06c6871f87886 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -121,17 +121,6 @@ config DWMAC_MESON
 	  the stmmac device driver. This driver is used for Meson6,
 	  Meson8, Meson8b and GXBB SoCs.
 
-config DWMAC_OXNAS
-	tristate "Oxford Semiconductor OXNAS dwmac support"
-	default ARCH_OXNAS
-	depends on OF && COMMON_CLK && (ARCH_OXNAS || COMPILE_TEST)
-	select MFD_SYSCON
-	help
-	  Support for Ethernet controller on Oxford Semiconductor OXNAS SoCs.
-
-	  This selects the Oxford Semiconductor OXNASSoC glue layer support for
-	  the stmmac device driver. This driver is used for OX820.
-
 config DWMAC_QCOM_ETHQOS
 	tristate "Qualcomm ETHQOS support"
 	default ARCH_QCOM
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 7dd3d388068bd..5b57aee19267f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_DWMAC_IPQ806X)	+= dwmac-ipq806x.o
 obj-$(CONFIG_DWMAC_LPC18XX)	+= dwmac-lpc18xx.o
 obj-$(CONFIG_DWMAC_MEDIATEK)	+= dwmac-mediatek.o
 obj-$(CONFIG_DWMAC_MESON)	+= dwmac-meson.o dwmac-meson8b.o
-obj-$(CONFIG_DWMAC_OXNAS)	+= dwmac-oxnas.o
 obj-$(CONFIG_DWMAC_QCOM_ETHQOS)	+= dwmac-qcom-ethqos.o
 obj-$(CONFIG_DWMAC_ROCKCHIP)	+= dwmac-rk.o
 obj-$(CONFIG_DWMAC_SOCFPGA)	+= dwmac-altr-socfpga.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
deleted file mode 100644
index f91753565d608..0000000000000
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
+++ /dev/null
@@ -1,244 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Oxford Semiconductor OXNAS DWMAC glue layer
- *
- * Copyright (C) 2016 Neil Armstrong <narmstrong@baylibre.com>
- * Copyright (C) 2014 Daniel Golle <daniel@makrotopia.org>
- * Copyright (C) 2013 Ma Haijun <mahaijuns@gmail.com>
- * Copyright (C) 2012 John Crispin <blogic@openwrt.org>
- */
-
-#include <linux/device.h>
-#include <linux/io.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/regmap.h>
-#include <linux/mfd/syscon.h>
-#include <linux/stmmac.h>
-
-#include "stmmac_platform.h"
-
-/* System Control regmap offsets */
-#define OXNAS_DWMAC_CTRL_REGOFFSET	0x78
-#define OXNAS_DWMAC_DELAY_REGOFFSET	0x100
-
-/* Control Register */
-#define DWMAC_CKEN_RX_IN        14
-#define DWMAC_CKEN_RXN_OUT      13
-#define DWMAC_CKEN_RX_OUT       12
-#define DWMAC_CKEN_TX_IN        10
-#define DWMAC_CKEN_TXN_OUT      9
-#define DWMAC_CKEN_TX_OUT       8
-#define DWMAC_RX_SOURCE         7
-#define DWMAC_TX_SOURCE         6
-#define DWMAC_LOW_TX_SOURCE     4
-#define DWMAC_AUTO_TX_SOURCE    3
-#define DWMAC_RGMII             2
-#define DWMAC_SIMPLE_MUX        1
-#define DWMAC_CKEN_GTX          0
-
-/* Delay register */
-#define DWMAC_TX_VARDELAY_SHIFT		0
-#define DWMAC_TXN_VARDELAY_SHIFT	8
-#define DWMAC_RX_VARDELAY_SHIFT		16
-#define DWMAC_RXN_VARDELAY_SHIFT	24
-#define DWMAC_TX_VARDELAY(d)		((d) << DWMAC_TX_VARDELAY_SHIFT)
-#define DWMAC_TXN_VARDELAY(d)		((d) << DWMAC_TXN_VARDELAY_SHIFT)
-#define DWMAC_RX_VARDELAY(d)		((d) << DWMAC_RX_VARDELAY_SHIFT)
-#define DWMAC_RXN_VARDELAY(d)		((d) << DWMAC_RXN_VARDELAY_SHIFT)
-
-struct oxnas_dwmac;
-
-struct oxnas_dwmac_data {
-	int (*setup)(struct oxnas_dwmac *dwmac);
-};
-
-struct oxnas_dwmac {
-	struct device	*dev;
-	struct clk	*clk;
-	struct regmap	*regmap;
-	const struct oxnas_dwmac_data	*data;
-};
-
-static int oxnas_dwmac_setup_ox810se(struct oxnas_dwmac *dwmac)
-{
-	unsigned int value;
-	int ret;
-
-	ret = regmap_read(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, &value);
-	if (ret < 0)
-		return ret;
-
-	/* Enable GMII_GTXCLK to follow GMII_REFCLK, required for gigabit PHY */
-	value |= BIT(DWMAC_CKEN_GTX)		|
-		 /* Use simple mux for 25/125 Mhz clock switching */
-		 BIT(DWMAC_SIMPLE_MUX);
-
-	regmap_write(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, value);
-
-	return 0;
-}
-
-static int oxnas_dwmac_setup_ox820(struct oxnas_dwmac *dwmac)
-{
-	unsigned int value;
-	int ret;
-
-	ret = regmap_read(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, &value);
-	if (ret < 0)
-		return ret;
-
-	/* Enable GMII_GTXCLK to follow GMII_REFCLK, required for gigabit PHY */
-	value |= BIT(DWMAC_CKEN_GTX)		|
-		 /* Use simple mux for 25/125 Mhz clock switching */
-		BIT(DWMAC_SIMPLE_MUX)		|
-		/* set auto switch tx clock source */
-		BIT(DWMAC_AUTO_TX_SOURCE)	|
-		/* enable tx & rx vardelay */
-		BIT(DWMAC_CKEN_TX_OUT)		|
-		BIT(DWMAC_CKEN_TXN_OUT)	|
-		BIT(DWMAC_CKEN_TX_IN)		|
-		BIT(DWMAC_CKEN_RX_OUT)		|
-		BIT(DWMAC_CKEN_RXN_OUT)	|
-		BIT(DWMAC_CKEN_RX_IN);
-	regmap_write(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, value);
-
-	/* set tx & rx vardelay */
-	value = DWMAC_TX_VARDELAY(4)	|
-		DWMAC_TXN_VARDELAY(2)	|
-		DWMAC_RX_VARDELAY(10)	|
-		DWMAC_RXN_VARDELAY(8);
-	regmap_write(dwmac->regmap, OXNAS_DWMAC_DELAY_REGOFFSET, value);
-
-	return 0;
-}
-
-static int oxnas_dwmac_init(struct platform_device *pdev, void *priv)
-{
-	struct oxnas_dwmac *dwmac = priv;
-	int ret;
-
-	/* Reset HW here before changing the glue configuration */
-	ret = device_reset(dwmac->dev);
-	if (ret)
-		return ret;
-
-	ret = clk_prepare_enable(dwmac->clk);
-	if (ret)
-		return ret;
-
-	ret = dwmac->data->setup(dwmac);
-	if (ret)
-		clk_disable_unprepare(dwmac->clk);
-
-	return ret;
-}
-
-static void oxnas_dwmac_exit(struct platform_device *pdev, void *priv)
-{
-	struct oxnas_dwmac *dwmac = priv;
-
-	clk_disable_unprepare(dwmac->clk);
-}
-
-static int oxnas_dwmac_probe(struct platform_device *pdev)
-{
-	struct plat_stmmacenet_data *plat_dat;
-	struct stmmac_resources stmmac_res;
-	struct oxnas_dwmac *dwmac;
-	int ret;
-
-	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
-	if (ret)
-		return ret;
-
-	plat_dat = stmmac_probe_config_dt(pdev, stmmac_res.mac);
-	if (IS_ERR(plat_dat))
-		return PTR_ERR(plat_dat);
-
-	dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL);
-	if (!dwmac) {
-		ret = -ENOMEM;
-		goto err_remove_config_dt;
-	}
-
-	dwmac->data = (const struct oxnas_dwmac_data *)of_device_get_match_data(&pdev->dev);
-	if (!dwmac->data) {
-		ret = -EINVAL;
-		goto err_remove_config_dt;
-	}
-
-	dwmac->dev = &pdev->dev;
-	plat_dat->bsp_priv = dwmac;
-	plat_dat->init = oxnas_dwmac_init;
-	plat_dat->exit = oxnas_dwmac_exit;
-
-	dwmac->regmap = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
-							"oxsemi,sys-ctrl");
-	if (IS_ERR(dwmac->regmap)) {
-		dev_err(&pdev->dev, "failed to have sysctrl regmap\n");
-		ret = PTR_ERR(dwmac->regmap);
-		goto err_remove_config_dt;
-	}
-
-	dwmac->clk = devm_clk_get(&pdev->dev, "gmac");
-	if (IS_ERR(dwmac->clk)) {
-		ret = PTR_ERR(dwmac->clk);
-		goto err_remove_config_dt;
-	}
-
-	ret = oxnas_dwmac_init(pdev, plat_dat->bsp_priv);
-	if (ret)
-		goto err_remove_config_dt;
-
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-	if (ret)
-		goto err_dwmac_exit;
-
-
-	return 0;
-
-err_dwmac_exit:
-	oxnas_dwmac_exit(pdev, plat_dat->bsp_priv);
-err_remove_config_dt:
-	stmmac_remove_config_dt(pdev, plat_dat);
-
-	return ret;
-}
-
-static const struct oxnas_dwmac_data ox810se_dwmac_data = {
-	.setup = oxnas_dwmac_setup_ox810se,
-};
-
-static const struct oxnas_dwmac_data ox820_dwmac_data = {
-	.setup = oxnas_dwmac_setup_ox820,
-};
-
-static const struct of_device_id oxnas_dwmac_match[] = {
-	{
-		.compatible = "oxsemi,ox810se-dwmac",
-		.data = &ox810se_dwmac_data,
-	},
-	{
-		.compatible = "oxsemi,ox820-dwmac",
-		.data = &ox820_dwmac_data,
-	},
-	{ }
-};
-MODULE_DEVICE_TABLE(of, oxnas_dwmac_match);
-
-static struct platform_driver oxnas_dwmac_driver = {
-	.probe  = oxnas_dwmac_probe,
-	.remove_new = stmmac_pltfr_remove,
-	.driver = {
-		.name           = "oxnas-dwmac",
-		.pm		= &stmmac_pltfr_pm_ops,
-		.of_match_table = oxnas_dwmac_match,
-	},
-};
-module_platform_driver(oxnas_dwmac_driver);
-
-MODULE_AUTHOR("Neil Armstrong <narmstrong@baylibre.com>");
-MODULE_DESCRIPTION("Oxford Semiconductor OXNAS DWMAC glue layer");
-MODULE_LICENSE("GPL v2");
-- 
GitLab


From 6d7d66ac9ce13ca8145b5c1ade08e622dd191395 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 31 Jul 2023 16:41:11 +0200
Subject: [PATCH 0744/1806] dt-bindings: net: oxnas-dwmac: remove obsolete
 bindings

Due to lack of maintenance and stall of development for a few years now,
and since no new features will ever be added upstream, remove the
OX810 and OX820 dwmac glue.

Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Daniel Golle <daniel@makrotopia.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/net/oxnas-dwmac.txt   | 41 -------------------
 1 file changed, 41 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/net/oxnas-dwmac.txt

diff --git a/Documentation/devicetree/bindings/net/oxnas-dwmac.txt b/Documentation/devicetree/bindings/net/oxnas-dwmac.txt
deleted file mode 100644
index 27db496f1ce82..0000000000000
--- a/Documentation/devicetree/bindings/net/oxnas-dwmac.txt
+++ /dev/null
@@ -1,41 +0,0 @@
-* Oxford Semiconductor OXNAS DWMAC Ethernet controller
-
-The device inherits all the properties of the dwmac/stmmac devices
-described in the file stmmac.txt in the current directory with the
-following changes.
-
-Required properties on all platforms:
-
-- compatible:	For the OX820 SoC, it should be :
-		- "oxsemi,ox820-dwmac" to select glue
-		- "snps,dwmac-3.512" to select IP version.
-		For the OX810SE SoC, it should be :
-		- "oxsemi,ox810se-dwmac" to select glue
-		- "snps,dwmac-3.512" to select IP version.
-
-- clocks: Should contain phandles to the following clocks
-- clock-names:	Should contain the following:
-		- "stmmaceth" for the host clock - see stmmac.txt
-		- "gmac" for the peripheral gate clock
-
-- oxsemi,sys-ctrl: a phandle to the system controller syscon node
-
-Example :
-
-etha: ethernet@40400000 {
-	compatible = "oxsemi,ox820-dwmac", "snps,dwmac-3.512";
-	reg = <0x40400000 0x2000>;
-	interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
-		     <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
-	interrupt-names = "macirq", "eth_wake_irq";
-	mac-address = [000000000000]; /* Filled in by U-Boot */
-	phy-mode = "rgmii";
-
-	clocks = <&stdclk CLK_820_ETHA>, <&gmacclk>;
-	clock-names = "gmac", "stmmaceth";
-	resets = <&reset RESET_MAC>;
-
-	/* Regmap for sys registers */
-	oxsemi,sys-ctrl = <&sys>;
-
-};
-- 
GitLab


From a57c34a80cbe15e36e12d42a4ddc5160a5bbb1a4 Mon Sep 17 00:00:00 2001
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: Tue, 1 Aug 2023 07:10:58 +0530
Subject: [PATCH 0745/1806] net: flow_dissector: Add IPSEC dissector

Support for dissecting IPSEC field SPI (which is
32bits in size) for ESP and AH packets.

Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_dissector.h |  9 ++++++
 net/core/flow_dissector.c    | 53 +++++++++++++++++++++++++++++++++++-
 2 files changed, 61 insertions(+), 1 deletion(-)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 830f06b2f36d2..1a7131d6cb0e4 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -301,6 +301,14 @@ struct flow_dissector_key_l2tpv3 {
 	__be32 session_id;
 };
 
+/**
+ * struct flow_dissector_key_ipsec:
+ * @spi: identifier for a ipsec connection
+ */
+struct flow_dissector_key_ipsec {
+	__be32 spi;
+};
+
 /**
  * struct flow_dissector_key_cfm
  * @mdl_ver: maintenance domain level (mdl) and cfm protocol version
@@ -354,6 +362,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_PPPOE, /* struct flow_dissector_key_pppoe */
 	FLOW_DISSECTOR_KEY_L2TPV3, /* struct flow_dissector_key_l2tpv3 */
 	FLOW_DISSECTOR_KEY_CFM, /* struct flow_dissector_key_cfm */
+	FLOW_DISSECTOR_KEY_IPSEC, /* struct flow_dissector_key_ipsec */
 
 	FLOW_DISSECTOR_KEY_MAX,
 };
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index ed5dfa376024f..89d15ceaf9afd 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -205,6 +205,50 @@ static void __skb_flow_dissect_icmp(const struct sk_buff *skb,
 	skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen);
 }
 
+static void __skb_flow_dissect_ah(const struct sk_buff *skb,
+				  struct flow_dissector *flow_dissector,
+				  void *target_container, const void *data,
+				  int nhoff, int hlen)
+{
+	struct flow_dissector_key_ipsec *key_ah;
+	struct ip_auth_hdr _hdr, *hdr;
+
+	if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC))
+		return;
+
+	hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
+	if (!hdr)
+		return;
+
+	key_ah = skb_flow_dissector_target(flow_dissector,
+					   FLOW_DISSECTOR_KEY_IPSEC,
+					   target_container);
+
+	key_ah->spi = hdr->spi;
+}
+
+static void __skb_flow_dissect_esp(const struct sk_buff *skb,
+				   struct flow_dissector *flow_dissector,
+				   void *target_container, const void *data,
+				   int nhoff, int hlen)
+{
+	struct flow_dissector_key_ipsec *key_esp;
+	struct ip_esp_hdr _hdr, *hdr;
+
+	if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC))
+		return;
+
+	hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
+	if (!hdr)
+		return;
+
+	key_esp = skb_flow_dissector_target(flow_dissector,
+					    FLOW_DISSECTOR_KEY_IPSEC,
+					    target_container);
+
+	key_esp->spi = hdr->spi;
+}
+
 static void __skb_flow_dissect_l2tpv3(const struct sk_buff *skb,
 				      struct flow_dissector *flow_dissector,
 				      void *target_container, const void *data,
@@ -1571,7 +1615,14 @@ ip_proto_again:
 		__skb_flow_dissect_l2tpv3(skb, flow_dissector, target_container,
 					  data, nhoff, hlen);
 		break;
-
+	case IPPROTO_ESP:
+		__skb_flow_dissect_esp(skb, flow_dissector, target_container,
+				       data, nhoff, hlen);
+		break;
+	case IPPROTO_AH:
+		__skb_flow_dissect_ah(skb, flow_dissector, target_container,
+				      data, nhoff, hlen);
+		break;
 	default:
 		break;
 	}
-- 
GitLab


From 4c13eda757e3ca72f523d07ed9e5f3e72b374299 Mon Sep 17 00:00:00 2001
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: Tue, 1 Aug 2023 07:10:59 +0530
Subject: [PATCH 0746/1806] tc: flower: support for SPI

tc flower rules support to classify ESP/AH
packets matching SPI field.

Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_cls.h |  3 +++
 net/sched/cls_flower.c       | 35 +++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 7865f5a9885b9..75506f1573400 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -598,6 +598,9 @@ enum {
 
 	TCA_FLOWER_KEY_CFM,		/* nested */
 
+	TCA_FLOWER_KEY_SPI,		/* be32 */
+	TCA_FLOWER_KEY_SPI_MASK,	/* be32 */
+
 	__TCA_FLOWER_MAX,
 };
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 8da9d039d964e..eca2602728454 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -72,6 +72,7 @@ struct fl_flow_key {
 	struct flow_dissector_key_num_of_vlans num_of_vlans;
 	struct flow_dissector_key_pppoe pppoe;
 	struct flow_dissector_key_l2tpv3 l2tpv3;
+	struct flow_dissector_key_ipsec ipsec;
 	struct flow_dissector_key_cfm cfm;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
@@ -726,6 +727,8 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_PPPOE_SID]	= { .type = NLA_U16 },
 	[TCA_FLOWER_KEY_PPP_PROTO]	= { .type = NLA_U16 },
 	[TCA_FLOWER_KEY_L2TPV3_SID]	= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_SPI]		= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_SPI_MASK]	= { .type = NLA_U32 },
 	[TCA_FLOWER_L2_MISS]		= NLA_POLICY_MAX(NLA_U8, 1),
 	[TCA_FLOWER_KEY_CFM]		= { .type = NLA_NESTED },
 };
@@ -795,6 +798,24 @@ static void fl_set_key_val(struct nlattr **tb,
 		nla_memcpy(mask, tb[mask_type], len);
 }
 
+static int fl_set_key_spi(struct nlattr **tb, struct fl_flow_key *key,
+			  struct fl_flow_key *mask,
+			  struct netlink_ext_ack *extack)
+{
+	if (key->basic.ip_proto != IPPROTO_ESP &&
+	    key->basic.ip_proto != IPPROTO_AH) {
+		NL_SET_ERR_MSG(extack,
+			       "Protocol must be either ESP or AH");
+		return -EINVAL;
+	}
+
+	fl_set_key_val(tb, &key->ipsec.spi,
+		       TCA_FLOWER_KEY_SPI,
+		       &mask->ipsec.spi, TCA_FLOWER_KEY_SPI_MASK,
+		       sizeof(key->ipsec.spi));
+	return 0;
+}
+
 static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key,
 				 struct fl_flow_key *mask,
 				 struct netlink_ext_ack *extack)
@@ -1894,6 +1915,12 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 			return ret;
 	}
 
+	if (tb[TCA_FLOWER_KEY_SPI]) {
+		ret = fl_set_key_spi(tb, key, mask, extack);
+		if (ret)
+			return ret;
+	}
+
 	if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
 	    tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) {
 		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
@@ -2066,6 +2093,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
 			     FLOW_DISSECTOR_KEY_PPPOE, pppoe);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_L2TPV3, l2tpv3);
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+			     FLOW_DISSECTOR_KEY_IPSEC, ipsec);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_CFM, cfm);
 
@@ -3364,6 +3393,12 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
 				 sizeof(key->l2tpv3.session_id)))
 		goto nla_put_failure;
 
+	if (key->ipsec.spi &&
+	    fl_dump_key_val(skb, &key->ipsec.spi, TCA_FLOWER_KEY_SPI,
+			    &mask->ipsec.spi, TCA_FLOWER_KEY_SPI_MASK,
+			    sizeof(key->ipsec.spi)))
+		goto nla_put_failure;
+
 	if ((key->basic.ip_proto == IPPROTO_TCP ||
 	     key->basic.ip_proto == IPPROTO_UDP ||
 	     key->basic.ip_proto == IPPROTO_SCTP) &&
-- 
GitLab


From c8915d7329d6e9164c5c847dc1c56a2c0437053f Mon Sep 17 00:00:00 2001
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: Tue, 1 Aug 2023 07:11:00 +0530
Subject: [PATCH 0747/1806] tc: flower: Enable offload support IPSEC SPI field.

This patch enables offload for TC classifier
flower rules which matches against SPI field.

Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_offload.h | 6 ++++++
 net/core/flow_offload.c    | 7 +++++++
 2 files changed, 13 insertions(+)

diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 118082eae48c0..9efa9a59e81f6 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -64,6 +64,10 @@ struct flow_match_tcp {
 	struct flow_dissector_key_tcp *key, *mask;
 };
 
+struct flow_match_ipsec {
+	struct flow_dissector_key_ipsec *key, *mask;
+};
+
 struct flow_match_mpls {
 	struct flow_dissector_key_mpls *key, *mask;
 };
@@ -116,6 +120,8 @@ void flow_rule_match_ports_range(const struct flow_rule *rule,
 				 struct flow_match_ports_range *out);
 void flow_rule_match_tcp(const struct flow_rule *rule,
 			 struct flow_match_tcp *out);
+void flow_rule_match_ipsec(const struct flow_rule *rule,
+			   struct flow_match_ipsec *out);
 void flow_rule_match_icmp(const struct flow_rule *rule,
 			  struct flow_match_icmp *out);
 void flow_rule_match_mpls(const struct flow_rule *rule,
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index acfc1f88ea79a..bc5169482710b 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -146,6 +146,13 @@ void flow_rule_match_tcp(const struct flow_rule *rule,
 }
 EXPORT_SYMBOL(flow_rule_match_tcp);
 
+void flow_rule_match_ipsec(const struct flow_rule *rule,
+			   struct flow_match_ipsec *out)
+{
+	FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPSEC, out);
+}
+EXPORT_SYMBOL(flow_rule_match_ipsec);
+
 void flow_rule_match_icmp(const struct flow_rule *rule,
 			  struct flow_match_icmp *out)
 {
-- 
GitLab


From 73b4c04e2e9af8075b87475cb7486f561dcecebd Mon Sep 17 00:00:00 2001
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: Tue, 1 Aug 2023 07:11:01 +0530
Subject: [PATCH 0748/1806] octeontx2-pf: TC flower offload support for SPI
 field

Driver support to offload TC flower rules which matches
against SPI field of IPSEC packets (AH/ESP).

Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/octeontx2/af/mbox.h  |  4 +++
 .../net/ethernet/marvell/octeontx2/af/npc.h   |  1 +
 .../marvell/octeontx2/af/rvu_debugfs.c        |  4 +++
 .../marvell/octeontx2/af/rvu_npc_fs.c         | 11 ++++++++
 .../ethernet/marvell/octeontx2/nic/otx2_tc.c  | 27 +++++++++++++++++++
 5 files changed, 47 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index ed66c59891028..a8f3c8faf8afa 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -1451,6 +1451,10 @@ struct flow_msg {
 		__be32 ip4dst;
 		__be32 ip6dst[4];
 	};
+	union {
+		__be32 spi;
+	};
+
 	u8 tos;
 	u8 ip_ver;
 	u8 ip_proto;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index 9beeead56d7b1..534f20c0c5df0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -204,6 +204,7 @@ enum key_fields {
 	NPC_DPORT_UDP,
 	NPC_SPORT_SCTP,
 	NPC_DPORT_SCTP,
+	NPC_IPSEC_SPI,
 	NPC_HEADER_FIELDS_MAX,
 	NPC_CHAN = NPC_HEADER_FIELDS_MAX, /* Valid when Rx */
 	NPC_PF_FUNC, /* Valid when Tx */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 3b26893efdf8b..7cd33edca3658 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -2827,6 +2827,10 @@ static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s,
 			seq_printf(s, "%d ", ntohs(rule->packet.dport));
 			seq_printf(s, "mask 0x%x\n", ntohs(rule->mask.dport));
 			break;
+		case NPC_IPSEC_SPI:
+			seq_printf(s, "0x%x ", ntohl(rule->packet.spi));
+			seq_printf(s, "mask 0x%x\n", ntohl(rule->mask.spi));
+			break;
 		default:
 			seq_puts(s, "\n");
 			break;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index 9c365cc3e7364..bb715e616fad0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -41,6 +41,7 @@ static const char * const npc_flow_names[] = {
 	[NPC_SPORT_SCTP] = "sctp source port",
 	[NPC_DPORT_SCTP] = "sctp destination port",
 	[NPC_LXMB]	= "Mcast/Bcast header ",
+	[NPC_IPSEC_SPI] = "SPI ",
 	[NPC_UNKNOWN]	= "unknown",
 };
 
@@ -513,6 +514,10 @@ do {									       \
 	NPC_SCAN_HDR(NPC_VLAN_TAG1, NPC_LID_LB, NPC_LT_LB_CTAG, 2, 2);
 	NPC_SCAN_HDR(NPC_VLAN_TAG2, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 2, 2);
 	NPC_SCAN_HDR(NPC_DMAC, NPC_LID_LA, la_ltype, la_start, 6);
+
+	NPC_SCAN_HDR(NPC_IPSEC_SPI, NPC_LID_LD, NPC_LT_LD_AH, 4, 4);
+	NPC_SCAN_HDR(NPC_IPSEC_SPI, NPC_LID_LE, NPC_LT_LE_ESP, 0, 4);
+
 	/* SMAC follows the DMAC(which is 6 bytes) */
 	NPC_SCAN_HDR(NPC_SMAC, NPC_LID_LA, la_ltype, la_start + 6, 6);
 	/* PF_FUNC is 2 bytes at 0th byte of NPC_LT_LA_IH_NIX_ETHER */
@@ -564,6 +569,9 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf)
 		if (!npc_check_field(rvu, blkaddr, NPC_LB, intf))
 			*features &= ~BIT_ULL(NPC_OUTER_VID);
 
+	if (*features & (BIT_ULL(NPC_IPPROTO_AH) | BIT_ULL(NPC_IPPROTO_ESP)))
+		*features |= BIT_ULL(NPC_IPSEC_SPI);
+
 	/* for vlan ethertypes corresponding layer type should be in the key */
 	if (npc_check_field(rvu, blkaddr, NPC_LB, intf))
 		*features |= BIT_ULL(NPC_VLAN_ETYPE_CTAG) |
@@ -930,6 +938,9 @@ do {									      \
 	NPC_WRITE_FLOW(NPC_DPORT_SCTP, dport, ntohs(pkt->dport), 0,
 		       ntohs(mask->dport), 0);
 
+	NPC_WRITE_FLOW(NPC_IPSEC_SPI, spi, ntohl(pkt->spi), 0,
+		       ntohl(mask->spi), 0);
+
 	NPC_WRITE_FLOW(NPC_OUTER_VID, vlan_tci, ntohs(pkt->vlan_tci), 0,
 		       ntohs(mask->vlan_tci), 0);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 5a44e9b96fc06..4bb511e3cbe5a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -461,6 +461,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT(FLOW_DISSECTOR_KEY_IPSEC) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_IP))))  {
 		netdev_info(nic->netdev, "unsupported flow used key 0x%llx",
 			    dissector->used_keys);
@@ -482,6 +483,8 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 		     match.key->ip_proto != IPPROTO_UDP &&
 		     match.key->ip_proto != IPPROTO_SCTP &&
 		     match.key->ip_proto != IPPROTO_ICMP &&
+		     match.key->ip_proto != IPPROTO_ESP &&
+		     match.key->ip_proto != IPPROTO_AH &&
 		     match.key->ip_proto != IPPROTO_ICMPV6)) {
 			netdev_info(nic->netdev,
 				    "ip_proto=0x%x not supported\n",
@@ -501,6 +504,10 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 			req->features |= BIT_ULL(NPC_IPPROTO_ICMP);
 		else if (ip_proto == IPPROTO_ICMPV6)
 			req->features |= BIT_ULL(NPC_IPPROTO_ICMP6);
+		else if (ip_proto == IPPROTO_ESP)
+			req->features |= BIT_ULL(NPC_IPPROTO_ESP);
+		else if (ip_proto == IPPROTO_AH)
+			req->features |= BIT_ULL(NPC_IPPROTO_AH);
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
@@ -545,6 +552,26 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 		}
 	}
 
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPSEC)) {
+		struct flow_match_ipsec match;
+
+		flow_rule_match_ipsec(rule, &match);
+		if (!match.mask->spi) {
+			NL_SET_ERR_MSG_MOD(extack, "spi index not specified");
+			return -EOPNOTSUPP;
+		}
+		if (ip_proto != IPPROTO_ESP &&
+		    ip_proto != IPPROTO_AH) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "SPI index is valid only for ESP/AH proto");
+			return -EOPNOTSUPP;
+		}
+
+		flow_spec->spi = match.key->spi;
+		flow_mask->spi = match.mask->spi;
+		req->features |= BIT_ULL(NPC_IPSEC_SPI);
+	}
+
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
 		struct flow_match_ip match;
 
-- 
GitLab


From 745d7e38e95d782053188be0a8e262ca02bcd6c4 Mon Sep 17 00:00:00 2001
From: Ante Knezic <ante.knezic@helmholz.de>
Date: Tue, 1 Aug 2023 08:48:15 +0200
Subject: [PATCH 0749/1806] net: dsa: mv88e6xxx: Add erratum 3.14 for 88E6390X
 and 88E6190X

Fixes XAUI/RXAUI lane alignment errors.
Issue causes dropped packets when trying to communicate over
fiber via SERDES lanes of port 9 and 10.
Errata document applies only to 88E6190X and 88E6390X devices.
Requires poking in undocumented registers.

Signed-off-by: Ante Knezic <ante.knezic@helmholz.de>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/pcs-639x.c | 45 ++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
index 98dd49dac4215..ba373656bfe14 100644
--- a/drivers/net/dsa/mv88e6xxx/pcs-639x.c
+++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
@@ -20,6 +20,7 @@ struct mv88e639x_pcs {
 	struct mdio_device mdio;
 	struct phylink_pcs sgmii_pcs;
 	struct phylink_pcs xg_pcs;
+	bool erratum_3_14;
 	bool supports_5g;
 	phy_interface_t interface;
 	unsigned int irq;
@@ -205,13 +206,53 @@ static void mv88e639x_sgmii_pcs_pre_config(struct phylink_pcs *pcs,
 	mv88e639x_sgmii_pcs_control_pwr(mpcs, false);
 }
 
+static int mv88e6390_erratum_3_14(struct mv88e639x_pcs *mpcs)
+{
+	const int lanes[] = { MV88E6390_PORT9_LANE0, MV88E6390_PORT9_LANE1,
+		MV88E6390_PORT9_LANE2, MV88E6390_PORT9_LANE3,
+		MV88E6390_PORT10_LANE0, MV88E6390_PORT10_LANE1,
+		MV88E6390_PORT10_LANE2, MV88E6390_PORT10_LANE3 };
+	int err, i;
+
+	/* 88e6190x and 88e6390x errata 3.14:
+	 * After chip reset, SERDES reconfiguration or SERDES core
+	 * Software Reset, the SERDES lanes may not be properly aligned
+	 * resulting in CRC errors
+	 */
+
+	for (i = 0; i < ARRAY_SIZE(lanes); i++) {
+		err = mdiobus_c45_write(mpcs->mdio.bus, lanes[i],
+					MDIO_MMD_PHYXS,
+					0xf054, 0x400C);
+		if (err)
+			return err;
+
+		err = mdiobus_c45_write(mpcs->mdio.bus, lanes[i],
+					MDIO_MMD_PHYXS,
+					0xf054, 0x4000);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int mv88e639x_sgmii_pcs_post_config(struct phylink_pcs *pcs,
 					   phy_interface_t interface)
 {
 	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
+	int err;
 
 	mv88e639x_sgmii_pcs_control_pwr(mpcs, true);
 
+	if (mpcs->erratum_3_14) {
+		err = mv88e6390_erratum_3_14(mpcs);
+		if (err)
+			dev_err(mpcs->mdio.dev.parent,
+				"failed to apply erratum 3.14: %pe\n",
+				ERR_PTR(err));
+	}
+
 	return 0;
 }
 
@@ -524,6 +565,10 @@ static int mv88e6390_pcs_init(struct mv88e6xxx_chip *chip, int port)
 	mpcs->xg_pcs.ops = &mv88e6390_xg_pcs_ops;
 	mpcs->xg_pcs.neg_mode = true;
 
+	if (chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6190X ||
+	    chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6390X)
+		mpcs->erratum_3_14 = true;
+
 	err = mv88e639x_pcs_setup_irq(mpcs, chip, port);
 	if (err)
 		goto err_free;
-- 
GitLab


From 61f4d2044aeb702fea236101883b59ea270ab2f7 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 1 Aug 2023 14:44:19 +0530
Subject: [PATCH 0750/1806] net: ti: icssg-prueth: Add Firmware Interface for
 ICSSG Ethernet driver.

Add firmware interface related headers and macros for ICSSG Ethernet
driver. These macros will be later used by the ICSSG ethernet driver.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/ti/icssg/icssg_switch_map.h  | 234 ++++++++++++++++++
 1 file changed, 234 insertions(+)
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_switch_map.h

diff --git a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
new file mode 100644
index 0000000000000..424a7e945ea84
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
@@ -0,0 +1,234 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Texas Instruments ICSSG Ethernet driver
+ *
+ * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#ifndef __NET_TI_ICSSG_SWITCH_MAP_H
+#define __NET_TI_ICSSG_SWITCH_MAP_H
+
+/************************* Ethernet Switch Constants *********************/
+
+/* if bucket size is changed in firmware then this too should be changed
+ * because it directly impacts FDB ageing calculation
+ */
+#define NUMBER_OF_FDB_BUCKET_ENTRIES            (4)
+
+/* This is fixed in ICSSG */
+#define SIZE_OF_FDB                             (2048)
+
+#define FW_LINK_SPEED_1G                           (0x00)
+#define FW_LINK_SPEED_100M                         (0x01)
+#define FW_LINK_SPEED_10M                          (0x02)
+#define FW_LINK_SPEED_HD                           (0x80)
+
+/* Time after which FDB entries are checked for aged out values.
+ * Values are in nanoseconds
+ */
+#define FDB_AGEING_TIMEOUT_OFFSET                          0x0014
+
+/* Default VLAN tag for Host Port */
+#define HOST_PORT_DF_VLAN_OFFSET                           0x001C
+
+/* Same as HOST_PORT_DF_VLAN_OFFSET */
+#define EMAC_ICSSG_SWITCH_PORT0_DEFAULT_VLAN_OFFSET        HOST_PORT_DF_VLAN_OFFSET
+
+/* Default VLAN tag for P1 Port */
+#define P1_PORT_DF_VLAN_OFFSET                             0x0020
+
+/* Same as P1_PORT_DF_VLAN_OFFSET */
+#define EMAC_ICSSG_SWITCH_PORT1_DEFAULT_VLAN_OFFSET        P1_PORT_DF_VLAN_OFFSET
+
+/* default VLAN tag for P2 Port */
+#define P2_PORT_DF_VLAN_OFFSET                             0x0024
+
+/* Same as P2_PORT_DF_VLAN_OFFSET */
+#define EMAC_ICSSG_SWITCH_PORT2_DEFAULT_VLAN_OFFSET        P2_PORT_DF_VLAN_OFFSET
+
+/* VLAN-FID Table offset. 4096 VIDs. 2B per VID = 8KB = 0x2000 */
+#define VLAN_STATIC_REG_TABLE_OFFSET                       0x0100
+
+/* VLAN-FID Table offset for EMAC  */
+#define EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET        VLAN_STATIC_REG_TABLE_OFFSET
+
+/* Packet descriptor Q reserved memory */
+#define PORT_DESC0_HI                                      0x2104
+
+/* Packet descriptor Q reserved memory */
+#define PORT_DESC0_LO                                      0x2F6C
+
+/* Packet descriptor Q reserved memory */
+#define PORT_DESC1_HI                                      0x3DD4
+
+/* Packet descriptor Q reserved memory */
+#define PORT_DESC1_LO                                      0x4C3C
+
+/* Packet descriptor Q reserved memory */
+#define HOST_DESC0_HI                                      0x5AA4
+
+/* Packet descriptor Q reserved memory */
+#define HOST_DESC0_LO                                      0x5F0C
+
+/* Packet descriptor Q reserved memory */
+#define HOST_DESC1_HI                                      0x6374
+
+/* Packet descriptor Q reserved memory */
+#define HOST_DESC1_LO                                      0x67DC
+
+/* Special packet descriptor Q reserved memory */
+#define HOST_SPPD0                                         0x7AAC
+
+/* Special acket descriptor Q reserved memory */
+#define HOST_SPPD1                                         0x7EAC
+
+/* IEP count cycle counter*/
+#define TIMESYNC_FW_WC_CYCLECOUNT_OFFSET                   0x83EC
+
+/* IEP count hi roll over count */
+#define TIMESYNC_FW_WC_HI_ROLLOVER_COUNT_OFFSET            0x83F4
+
+/* IEP count hi sw counter */
+#define TIMESYNC_FW_WC_COUNT_HI_SW_OFFSET_OFFSET           0x83F8
+
+/* Set clock descriptor */
+#define TIMESYNC_FW_WC_SETCLOCK_DESC_OFFSET                0x83FC
+
+/* IEP count syncout reduction factor */
+#define TIMESYNC_FW_WC_SYNCOUT_REDUCTION_FACTOR_OFFSET     0x843C
+
+/* IEP count syncout reduction counter */
+#define TIMESYNC_FW_WC_SYNCOUT_REDUCTION_COUNT_OFFSET      0x8440
+
+/* IEP count syncout start time cycle counter */
+#define TIMESYNC_FW_WC_SYNCOUT_START_TIME_CYCLECOUNT_OFFSET 0x8444
+
+/* Control variable to generate SYNC1 */
+#define TIMESYNC_FW_WC_ISOM_PIN_SIGNAL_EN_OFFSET           0x844C
+
+/* SystemTime Sync0 periodicity */
+#define TIMESYNC_FW_ST_SYNCOUT_PERIOD_OFFSET               0x8450
+
+/* pktTxDelay for P1 = link speed dependent p1 mac delay + p1 phy delay */
+#define TIMESYNC_FW_WC_PKTTXDELAY_P1_OFFSET                0x8454
+
+/* pktTxDelay for P2 = link speed dependent p2 mac delay + p2 phy delay */
+#define TIMESYNC_FW_WC_PKTTXDELAY_P2_OFFSET                0x8458
+
+/* Set clock operation done signal for next task */
+#define TIMESYNC_FW_SIG_PNFW_OFFSET                        0x845C
+
+/* Set clock operation done signal for next task */
+#define TIMESYNC_FW_SIG_TIMESYNCFW_OFFSET                  0x8460
+
+/* New list is copied at this time */
+#define TAS_CONFIG_CHANGE_TIME                             0x000C
+
+/* config change error counter */
+#define TAS_CONFIG_CHANGE_ERROR_COUNTER                    0x0014
+
+/* TAS List update pending flag */
+#define TAS_CONFIG_PENDING                                 0x0018
+
+/* TAS list update trigger flag */
+#define TAS_CONFIG_CHANGE                                  0x0019
+
+/* List length for new TAS schedule */
+#define TAS_ADMIN_LIST_LENGTH                              0x001A
+
+/* Currently active TAS list index */
+#define TAS_ACTIVE_LIST_INDEX                              0x001B
+
+/* Cycle time for the new TAS schedule */
+#define TAS_ADMIN_CYCLE_TIME                               0x001C
+
+/* Cycle counts remaining till the TAS list update */
+#define TAS_CONFIG_CHANGE_CYCLE_COUNT                      0x0020
+
+/* Base Flow ID for sending  Packets to Host for Slice0 */
+#define PSI_L_REGULAR_FLOW_ID_BASE_OFFSET                  0x0024
+
+/* Same as PSI_L_REGULAR_FLOW_ID_BASE_OFFSET */
+#define EMAC_ICSSG_SWITCH_PSI_L_REGULAR_FLOW_ID_BASE_OFFSET PSI_L_REGULAR_FLOW_ID_BASE_OFFSET
+
+/* Base Flow ID for sending mgmt and Tx TS to Host for Slice0 */
+#define PSI_L_MGMT_FLOW_ID_OFFSET                          0x0026
+
+/* Same as PSI_L_MGMT_FLOW_ID_OFFSET */
+#define EMAC_ICSSG_SWITCH_PSI_L_MGMT_FLOW_ID_BASE_OFFSET   PSI_L_MGMT_FLOW_ID_OFFSET
+
+/* Queue number for Special  Packets written here */
+#define SPL_PKT_DEFAULT_PRIORITY                           0x0028
+
+/* Express Preemptible Queue Mask */
+#define EXPRESS_PRE_EMPTIVE_Q_MASK                         0x0029
+
+/* Port1/Port2 Default Queue number for untagged  Packets, only 1B is used */
+#define QUEUE_NUM_UNTAGGED                                 0x002A
+
+/* Stores the table used for priority regeneration. 1B per PCP/Queue */
+#define PORT_Q_PRIORITY_REGEN_OFFSET                       0x002C
+
+/* For marking Packet as priority/express (this feature is disabled) or
+ * cut-through/S&F.
+ */
+#define EXPRESS_PRE_EMPTIVE_Q_MAP                          0x0034
+
+/* Stores the table used for priority mapping. 1B per PCP/Queue */
+#define PORT_Q_PRIORITY_MAPPING_OFFSET                     0x003C
+
+/* Used to notify the FW of the current link speed */
+#define PORT_LINK_SPEED_OFFSET                             0x00A8
+
+/* TAS gate mask for windows list0 */
+#define TAS_GATE_MASK_LIST0                                0x0100
+
+/* TAS gate mask for windows list1 */
+#define TAS_GATE_MASK_LIST1                                0x0350
+
+/* Memory to Enable/Disable Preemption on TX side */
+#define PRE_EMPTION_ENABLE_TX                              0x05A0
+
+/* Active State of Preemption on TX side */
+#define PRE_EMPTION_ACTIVE_TX                              0x05A1
+
+/* Memory to Enable/Disable Verify State Machine Preemption */
+#define PRE_EMPTION_ENABLE_VERIFY                          0x05A2
+
+/* Verify Status of State Machine */
+#define PRE_EMPTION_VERIFY_STATUS                          0x05A3
+
+/* Non Final Fragment Size supported by Link Partner */
+#define PRE_EMPTION_ADD_FRAG_SIZE_REMOTE                   0x05A4
+
+/* Non Final Fragment Size supported by Firmware */
+#define PRE_EMPTION_ADD_FRAG_SIZE_LOCAL                    0x05A6
+
+/* Time in ms the State machine waits for respond Packet */
+#define PRE_EMPTION_VERIFY_TIME                            0x05A8
+
+/* Memory used for R30 related management commands */
+#define MGR_R30_CMD_OFFSET                                 0x05AC
+
+/* HW Buffer Pool0 base address */
+#define BUFFER_POOL_0_ADDR_OFFSET                          0x05BC
+
+/* 16B for Host Egress MSMC Q (Pre-emptible) context */
+#define HOST_RX_Q_PRE_CONTEXT_OFFSET                       0x0684
+
+/* Buffer for 8 FDB entries to be added by 'Add Multiple FDB entries IOCTL' */
+#define FDB_CMD_BUFFER                                     0x0894
+
+/* TAS queue max sdu length list */
+#define TAS_QUEUE_MAX_SDU_LIST                             0x08FA
+
+/* Used by FW to generate random number with the SEED value */
+#define HD_RAND_SEED_OFFSET                                0x0934
+
+/* 16B for Host Egress MSMC Q (Express) context */
+#define HOST_RX_Q_EXP_CONTEXT_OFFSET                       0x0940
+
+/* Start of 32 bits PA_STAT counters */
+#define PA_STAT_32b_START_OFFSET                           0x0080
+
+#endif /* __NET_TI_ICSSG_SWITCH_MAP_H  */
-- 
GitLab


From b6ba7752149de52fde1253d1b203a96e1ee89afc Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 1 Aug 2023 14:44:20 +0530
Subject: [PATCH 0751/1806] net: ti: icssg-prueth: Add mii helper apis and
 macros

Add MII helper APIs and MACROs. These APIs and MACROs will be later used
by ICSSG Ethernet driver. Also introduce icssg_prueth.h which has
definition of prueth related structures.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/icssg/icssg_mii_cfg.c | 120 +++++++++++
 drivers/net/ethernet/ti/icssg/icssg_mii_rt.h  | 151 ++++++++++++++
 drivers/net/ethernet/ti/icssg/icssg_prueth.h  | 197 ++++++++++++++++++
 3 files changed, 468 insertions(+)
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_mii_cfg.c
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_mii_rt.h
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_prueth.h

diff --git a/drivers/net/ethernet/ti/icssg/icssg_mii_cfg.c b/drivers/net/ethernet/ti/icssg/icssg_mii_cfg.c
new file mode 100644
index 0000000000000..92718ae40d7e5
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_mii_cfg.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Texas Instruments ICSSG Ethernet Driver
+ *
+ * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/regmap.h>
+#include <linux/types.h>
+
+#include "icssg_mii_rt.h"
+#include "icssg_prueth.h"
+
+void icssg_mii_update_ipg(struct regmap *mii_rt, int mii, u32 ipg)
+{
+	u32 val;
+
+	if (mii == ICSS_MII0) {
+		regmap_write(mii_rt, PRUSS_MII_RT_TX_IPG0, ipg);
+	} else {
+		regmap_read(mii_rt, PRUSS_MII_RT_TX_IPG0, &val);
+		regmap_write(mii_rt, PRUSS_MII_RT_TX_IPG1, ipg);
+		regmap_write(mii_rt, PRUSS_MII_RT_TX_IPG0, val);
+	}
+}
+
+void icssg_mii_update_mtu(struct regmap *mii_rt, int mii, int mtu)
+{
+	mtu += (ETH_HLEN + ETH_FCS_LEN);
+	if (mii == ICSS_MII0) {
+		regmap_update_bits(mii_rt,
+				   PRUSS_MII_RT_RX_FRMS0,
+				   PRUSS_MII_RT_RX_FRMS_MAX_FRM_MASK,
+				   (mtu - 1) << PRUSS_MII_RT_RX_FRMS_MAX_FRM_SHIFT);
+	} else {
+		regmap_update_bits(mii_rt,
+				   PRUSS_MII_RT_RX_FRMS1,
+				   PRUSS_MII_RT_RX_FRMS_MAX_FRM_MASK,
+				   (mtu - 1) << PRUSS_MII_RT_RX_FRMS_MAX_FRM_SHIFT);
+	}
+}
+
+void icssg_update_rgmii_cfg(struct regmap *miig_rt, struct prueth_emac *emac)
+{
+	u32 gig_en_mask, gig_val = 0, full_duplex_mask, full_duplex_val = 0;
+	int slice = prueth_emac_slice(emac);
+	u32 inband_en_mask, inband_val = 0;
+
+	gig_en_mask = (slice == ICSS_MII0) ? RGMII_CFG_GIG_EN_MII0 :
+					RGMII_CFG_GIG_EN_MII1;
+	if (emac->speed == SPEED_1000)
+		gig_val = gig_en_mask;
+	regmap_update_bits(miig_rt, RGMII_CFG_OFFSET, gig_en_mask, gig_val);
+
+	inband_en_mask = (slice == ICSS_MII0) ? RGMII_CFG_INBAND_EN_MII0 :
+					RGMII_CFG_INBAND_EN_MII1;
+	if (emac->speed == SPEED_10 && phy_interface_mode_is_rgmii(emac->phy_if))
+		inband_val = inband_en_mask;
+	regmap_update_bits(miig_rt, RGMII_CFG_OFFSET, inband_en_mask, inband_val);
+
+	full_duplex_mask = (slice == ICSS_MII0) ? RGMII_CFG_FULL_DUPLEX_MII0 :
+					   RGMII_CFG_FULL_DUPLEX_MII1;
+	if (emac->duplex == DUPLEX_FULL)
+		full_duplex_val = full_duplex_mask;
+	regmap_update_bits(miig_rt, RGMII_CFG_OFFSET, full_duplex_mask,
+			   full_duplex_val);
+}
+
+void icssg_miig_set_interface_mode(struct regmap *miig_rt, int mii, phy_interface_t phy_if)
+{
+	u32 val, mask, shift;
+
+	mask = mii == ICSS_MII0 ? ICSSG_CFG_MII0_MODE : ICSSG_CFG_MII1_MODE;
+	shift =  mii == ICSS_MII0 ? ICSSG_CFG_MII0_MODE_SHIFT : ICSSG_CFG_MII1_MODE_SHIFT;
+
+	val = MII_MODE_RGMII;
+	if (phy_if == PHY_INTERFACE_MODE_MII)
+		val = MII_MODE_MII;
+
+	val <<= shift;
+	regmap_update_bits(miig_rt, ICSSG_CFG_OFFSET, mask, val);
+	regmap_read(miig_rt, ICSSG_CFG_OFFSET, &val);
+}
+
+u32 icssg_rgmii_cfg_get_bitfield(struct regmap *miig_rt, u32 mask, u32 shift)
+{
+	u32 val;
+
+	regmap_read(miig_rt, RGMII_CFG_OFFSET, &val);
+	val &= mask;
+	val >>= shift;
+
+	return val;
+}
+
+u32 icssg_rgmii_get_speed(struct regmap *miig_rt, int mii)
+{
+	u32 shift = RGMII_CFG_SPEED_MII0_SHIFT, mask = RGMII_CFG_SPEED_MII0;
+
+	if (mii == ICSS_MII1) {
+		shift = RGMII_CFG_SPEED_MII1_SHIFT;
+		mask = RGMII_CFG_SPEED_MII1;
+	}
+
+	return icssg_rgmii_cfg_get_bitfield(miig_rt, mask, shift);
+}
+
+u32 icssg_rgmii_get_fullduplex(struct regmap *miig_rt, int mii)
+{
+	u32 shift = RGMII_CFG_FULLDUPLEX_MII0_SHIFT;
+	u32 mask = RGMII_CFG_FULLDUPLEX_MII0;
+
+	if (mii == ICSS_MII1) {
+		shift = RGMII_CFG_FULLDUPLEX_MII1_SHIFT;
+		mask = RGMII_CFG_FULLDUPLEX_MII1;
+	}
+
+	return icssg_rgmii_cfg_get_bitfield(miig_rt, mask, shift);
+}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_mii_rt.h b/drivers/net/ethernet/ti/icssg/icssg_mii_rt.h
new file mode 100644
index 0000000000000..55a59bf5299c0
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_mii_rt.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* PRU-ICSS MII_RT register definitions
+ *
+ * Copyright (C) 2015-2022 Texas Instruments Incorporated - https://www.ti.com
+ */
+
+#ifndef __NET_PRUSS_MII_RT_H__
+#define __NET_PRUSS_MII_RT_H__
+
+#include <linux/if_ether.h>
+#include <linux/phy.h>
+
+/* PRUSS_MII_RT Registers */
+#define PRUSS_MII_RT_RXCFG0		0x0
+#define PRUSS_MII_RT_RXCFG1		0x4
+#define PRUSS_MII_RT_TXCFG0		0x10
+#define PRUSS_MII_RT_TXCFG1		0x14
+#define PRUSS_MII_RT_TX_CRC0		0x20
+#define PRUSS_MII_RT_TX_CRC1		0x24
+#define PRUSS_MII_RT_TX_IPG0		0x30
+#define PRUSS_MII_RT_TX_IPG1		0x34
+#define PRUSS_MII_RT_PRS0		0x38
+#define PRUSS_MII_RT_PRS1		0x3c
+#define PRUSS_MII_RT_RX_FRMS0		0x40
+#define PRUSS_MII_RT_RX_FRMS1		0x44
+#define PRUSS_MII_RT_RX_PCNT0		0x48
+#define PRUSS_MII_RT_RX_PCNT1		0x4c
+#define PRUSS_MII_RT_RX_ERR0		0x50
+#define PRUSS_MII_RT_RX_ERR1		0x54
+
+/* PRUSS_MII_RT_RXCFG0/1 bits */
+#define PRUSS_MII_RT_RXCFG_RX_ENABLE		BIT(0)
+#define PRUSS_MII_RT_RXCFG_RX_DATA_RDY_MODE_DIS	BIT(1)
+#define PRUSS_MII_RT_RXCFG_RX_CUT_PREAMBLE	BIT(2)
+#define PRUSS_MII_RT_RXCFG_RX_MUX_SEL		BIT(3)
+#define PRUSS_MII_RT_RXCFG_RX_L2_EN		BIT(4)
+#define PRUSS_MII_RT_RXCFG_RX_BYTE_SWAP		BIT(5)
+#define PRUSS_MII_RT_RXCFG_RX_AUTO_FWD_PRE	BIT(6)
+#define PRUSS_MII_RT_RXCFG_RX_L2_EOF_SCLR_DIS	BIT(9)
+
+/* PRUSS_MII_RT_TXCFG0/1 bits */
+#define PRUSS_MII_RT_TXCFG_TX_ENABLE		BIT(0)
+#define PRUSS_MII_RT_TXCFG_TX_AUTO_PREAMBLE	BIT(1)
+#define PRUSS_MII_RT_TXCFG_TX_EN_MODE		BIT(2)
+#define PRUSS_MII_RT_TXCFG_TX_BYTE_SWAP		BIT(3)
+#define PRUSS_MII_RT_TXCFG_TX_MUX_SEL		BIT(8)
+#define PRUSS_MII_RT_TXCFG_PRE_TX_AUTO_SEQUENCE	BIT(9)
+#define PRUSS_MII_RT_TXCFG_PRE_TX_AUTO_ESC_ERR	BIT(10)
+#define PRUSS_MII_RT_TXCFG_TX_32_MODE_EN	BIT(11)
+#define PRUSS_MII_RT_TXCFG_TX_IPG_WIRE_CLK_EN	BIT(12)	/* SR2.0 onwards */
+
+#define PRUSS_MII_RT_TXCFG_TX_START_DELAY_SHIFT	16
+#define PRUSS_MII_RT_TXCFG_TX_START_DELAY_MASK	GENMASK(25, 16)
+
+#define PRUSS_MII_RT_TXCFG_TX_CLK_DELAY_SHIFT	28
+#define PRUSS_MII_RT_TXCFG_TX_CLK_DELAY_MASK	GENMASK(30, 28)
+
+/* PRUSS_MII_RT_TX_IPG0/1 bits */
+#define PRUSS_MII_RT_TX_IPG_IPG_SHIFT	0
+#define PRUSS_MII_RT_TX_IPG_IPG_MASK	GENMASK(9, 0)
+
+/* PRUSS_MII_RT_PRS0/1 bits */
+#define PRUSS_MII_RT_PRS_COL	BIT(0)
+#define PRUSS_MII_RT_PRS_CRS	BIT(1)
+
+/* PRUSS_MII_RT_RX_FRMS0/1 bits */
+#define PRUSS_MII_RT_RX_FRMS_MIN_FRM_SHIFT	0
+#define PRUSS_MII_RT_RX_FRMS_MIN_FRM_MASK	GENMASK(15, 0)
+
+#define PRUSS_MII_RT_RX_FRMS_MAX_FRM_SHIFT	16
+#define PRUSS_MII_RT_RX_FRMS_MAX_FRM_MASK	GENMASK(31, 16)
+
+/* Min/Max in MII_RT_RX_FRMS */
+/* For EMAC and Switch */
+#define PRUSS_MII_RT_RX_FRMS_MAX	(VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
+#define PRUSS_MII_RT_RX_FRMS_MIN_FRM	(64)
+
+/* for HSR and PRP */
+#define PRUSS_MII_RT_RX_FRMS_MAX_FRM_LRE	(PRUSS_MII_RT_RX_FRMS_MAX + \
+						 ICSS_LRE_TAG_RCT_SIZE)
+/* PRUSS_MII_RT_RX_PCNT0/1 bits */
+#define PRUSS_MII_RT_RX_PCNT_MIN_PCNT_SHIFT	0
+#define PRUSS_MII_RT_RX_PCNT_MIN_PCNT_MASK	GENMASK(3, 0)
+
+#define PRUSS_MII_RT_RX_PCNT_MAX_PCNT_SHIFT	4
+#define PRUSS_MII_RT_RX_PCNT_MAX_PCNT_MASK	GENMASK(7, 4)
+
+/* PRUSS_MII_RT_RX_ERR0/1 bits */
+#define PRUSS_MII_RT_RX_ERR_MIN_PCNT_ERR	BIT(0)
+#define PRUSS_MII_RT_RX_ERR_MAX_PCNT_ERR	BIT(1)
+#define PRUSS_MII_RT_RX_ERR_MIN_FRM_ERR		BIT(2)
+#define PRUSS_MII_RT_RX_ERR_MAX_FRM_ERR		BIT(3)
+
+#define ICSSG_CFG_OFFSET	0
+#define RGMII_CFG_OFFSET	4
+
+/* Constant to choose between MII0 and MII1 */
+#define ICSS_MII0	0
+#define ICSS_MII1	1
+
+/* ICSSG_CFG Register bits */
+#define ICSSG_CFG_SGMII_MODE	BIT(16)
+#define ICSSG_CFG_TX_PRU_EN	BIT(11)
+#define ICSSG_CFG_RX_SFD_TX_SOF_EN	BIT(10)
+#define ICSSG_CFG_RTU_PRU_PSI_SHARE_EN	BIT(9)
+#define ICSSG_CFG_IEP1_TX_EN	BIT(8)
+#define ICSSG_CFG_MII1_MODE	GENMASK(6, 5)
+#define ICSSG_CFG_MII1_MODE_SHIFT	5
+#define ICSSG_CFG_MII0_MODE	GENMASK(4, 3)
+#define ICSSG_CFG_MII0_MODE_SHIFT	3
+#define ICSSG_CFG_RX_L2_G_EN	BIT(2)
+#define ICSSG_CFG_TX_L2_EN	BIT(1)
+#define ICSSG_CFG_TX_L1_EN	BIT(0)
+
+enum mii_mode {
+	MII_MODE_MII = 0,
+	MII_MODE_RGMII
+};
+
+/* RGMII CFG Register bits */
+#define RGMII_CFG_INBAND_EN_MII0	BIT(16)
+#define RGMII_CFG_GIG_EN_MII0	BIT(17)
+#define RGMII_CFG_INBAND_EN_MII1	BIT(20)
+#define RGMII_CFG_GIG_EN_MII1	BIT(21)
+#define RGMII_CFG_FULL_DUPLEX_MII0	BIT(18)
+#define RGMII_CFG_FULL_DUPLEX_MII1	BIT(22)
+#define RGMII_CFG_SPEED_MII0	GENMASK(2, 1)
+#define RGMII_CFG_SPEED_MII1	GENMASK(6, 5)
+#define RGMII_CFG_SPEED_MII0_SHIFT	1
+#define RGMII_CFG_SPEED_MII1_SHIFT	5
+#define RGMII_CFG_FULLDUPLEX_MII0	BIT(3)
+#define RGMII_CFG_FULLDUPLEX_MII1	BIT(7)
+#define RGMII_CFG_FULLDUPLEX_MII0_SHIFT	3
+#define RGMII_CFG_FULLDUPLEX_MII1_SHIFT	7
+#define RGMII_CFG_SPEED_10M	0
+#define RGMII_CFG_SPEED_100M	1
+#define RGMII_CFG_SPEED_1G	2
+
+struct regmap;
+struct prueth_emac;
+
+void icssg_mii_update_ipg(struct regmap *mii_rt, int mii, u32 ipg);
+void icssg_mii_update_mtu(struct regmap *mii_rt, int mii, int mtu);
+void icssg_update_rgmii_cfg(struct regmap *miig_rt, struct prueth_emac *emac);
+u32 icssg_rgmii_cfg_get_bitfield(struct regmap *miig_rt, u32 mask, u32 shift);
+u32 icssg_rgmii_get_speed(struct regmap *miig_rt, int mii);
+u32 icssg_rgmii_get_fullduplex(struct regmap *miig_rt, int mii);
+void icssg_miig_set_interface_mode(struct regmap *miig_rt, int mii, phy_interface_t phy_if);
+
+#endif /* __NET_PRUSS_MII_RT_H__ */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
new file mode 100644
index 0000000000000..8512f19a9b4d4
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -0,0 +1,197 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Texas Instruments ICSSG Ethernet driver
+ *
+ * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#ifndef __NET_TI_ICSSG_PRUETH_H
+#define __NET_TI_ICSSG_PRUETH_H
+
+#include <linux/etherdevice.h>
+#include <linux/genalloc.h>
+#include <linux/if_vlan.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/net_tstamp.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/remoteproc/pruss.h>
+#include <linux/pruss_driver.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/remoteproc.h>
+
+#include <linux/dma-mapping.h>
+#include <linux/dma/ti-cppi5.h>
+#include <linux/dma/k3-udma-glue.h>
+
+#include <net/devlink.h>
+
+#include "icssg_switch_map.h"
+
+#define ICSS_SLICE0	0
+#define ICSS_SLICE1	1
+
+#define ICSSG_MAX_RFLOWS	8	/* per slice */
+
+/* In switch mode there are 3 real ports i.e. 3 mac addrs.
+ * however Linux sees only the host side port. The other 2 ports
+ * are the switch ports.
+ * In emac mode there are 2 real ports i.e. 2 mac addrs.
+ * Linux sees both the ports.
+ */
+enum prueth_port {
+	PRUETH_PORT_HOST = 0,	/* host side port */
+	PRUETH_PORT_MII0,	/* physical port RG/SG MII 0 */
+	PRUETH_PORT_MII1,	/* physical port RG/SG MII 1 */
+	PRUETH_PORT_INVALID,	/* Invalid prueth port */
+};
+
+enum prueth_mac {
+	PRUETH_MAC0 = 0,
+	PRUETH_MAC1,
+	PRUETH_NUM_MACS,
+	PRUETH_MAC_INVALID,
+};
+
+struct prueth_tx_chn {
+	struct device *dma_dev;
+	struct napi_struct napi_tx;
+	struct k3_cppi_desc_pool *desc_pool;
+	struct k3_udma_glue_tx_channel *tx_chn;
+	struct prueth_emac *emac;
+	u32 id;
+	u32 descs_num;
+	unsigned int irq;
+	char name[32];
+};
+
+struct prueth_rx_chn {
+	struct device *dev;
+	struct device *dma_dev;
+	struct k3_cppi_desc_pool *desc_pool;
+	struct k3_udma_glue_rx_channel *rx_chn;
+	u32 descs_num;
+	unsigned int irq[ICSSG_MAX_RFLOWS];	/* separate irq per flow */
+	char name[32];
+};
+
+/* There are 4 Tx DMA channels, but the highest priority is CH3 (thread 3)
+ * and lower three are lower priority channels or threads.
+ */
+#define PRUETH_MAX_TX_QUEUES	4
+
+/* data for each emac port */
+struct prueth_emac {
+	bool fw_running;
+	struct prueth *prueth;
+	struct net_device *ndev;
+	u8 mac_addr[6];
+	struct napi_struct napi_rx;
+	u32 msg_enable;
+
+	int link;
+	int speed;
+	int duplex;
+
+	const char *phy_id;
+	struct device_node *phy_node;
+	phy_interface_t phy_if;
+	enum prueth_port port_id;
+
+	/* DMA related */
+	struct prueth_tx_chn tx_chns[PRUETH_MAX_TX_QUEUES];
+	struct completion tdown_complete;
+	atomic_t tdown_cnt;
+	struct prueth_rx_chn rx_chns;
+	int rx_flow_id_base;
+	int tx_ch_num;
+
+	spinlock_t lock;	/* serialize access */
+
+	unsigned long state;
+	struct completion cmd_complete;
+	/* Mutex to serialize access to firmware command interface */
+	struct mutex cmd_lock;
+	struct work_struct rx_mode_work;
+	struct workqueue_struct	*cmd_wq;
+
+	struct pruss_mem_region dram;
+};
+
+/**
+ * struct prueth_pdata - PRUeth platform data
+ * @fdqring_mode: Free desc queue mode
+ * @quirk_10m_link_issue: 10M link detect errata
+ */
+struct prueth_pdata {
+	enum k3_ring_mode fdqring_mode;
+	u32	quirk_10m_link_issue:1;
+};
+
+/**
+ * struct prueth - PRUeth structure
+ * @dev: device
+ * @pruss: pruss handle
+ * @pru: rproc instances of PRUs
+ * @rtu: rproc instances of RTUs
+ * @txpru: rproc instances of TX_PRUs
+ * @shram: PRUSS shared RAM region
+ * @sram_pool: MSMC RAM pool for buffers
+ * @msmcram: MSMC RAM region
+ * @eth_node: DT node for the port
+ * @emac: private EMAC data structure
+ * @registered_netdevs: list of registered netdevs
+ * @miig_rt: regmap to mii_g_rt block
+ * @mii_rt: regmap to mii_rt block
+ * @pru_id: ID for each of the PRUs
+ * @pdev: pointer to ICSSG platform device
+ * @pdata: pointer to platform data for ICSSG driver
+ * @icssg_hwcmdseq: seq counter or HWQ messages
+ * @emacs_initialized: num of EMACs/ext ports that are up/running
+ */
+struct prueth {
+	struct device *dev;
+	struct pruss *pruss;
+	struct rproc *pru[PRUSS_NUM_PRUS];
+	struct rproc *rtu[PRUSS_NUM_PRUS];
+	struct rproc *txpru[PRUSS_NUM_PRUS];
+	struct pruss_mem_region shram;
+	struct gen_pool *sram_pool;
+	struct pruss_mem_region msmcram;
+
+	struct device_node *eth_node[PRUETH_NUM_MACS];
+	struct prueth_emac *emac[PRUETH_NUM_MACS];
+	struct net_device *registered_netdevs[PRUETH_NUM_MACS];
+	struct regmap *miig_rt;
+	struct regmap *mii_rt;
+
+	enum pruss_pru_id pru_id[PRUSS_NUM_PRUS];
+	struct platform_device *pdev;
+	struct prueth_pdata pdata;
+	u8 icssg_hwcmdseq;
+
+	int emacs_initialized;
+};
+
+/* get PRUSS SLICE number from prueth_emac */
+static inline int prueth_emac_slice(struct prueth_emac *emac)
+{
+	switch (emac->port_id) {
+	case PRUETH_PORT_MII0:
+		return ICSS_SLICE0;
+	case PRUETH_PORT_MII1:
+		return ICSS_SLICE1;
+	default:
+		return -EINVAL;
+	}
+}
+
+#endif /* __NET_TI_ICSSG_PRUETH_H */
-- 
GitLab


From e9b4ece7d74b52bc5800afd4dfe32a8960a9d491 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 1 Aug 2023 14:44:21 +0530
Subject: [PATCH 0752/1806] net: ti: icssg-prueth: Add Firmware config and
 classification APIs.

Add icssg_config.h / .c and icssg_classifier.c files. These are firmware
configuration and classification related files. These will be used by
ICSSG ethernet driver.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/ti/icssg/icssg_classifier.c  | 367 ++++++++++++++
 drivers/net/ethernet/ti/icssg/icssg_config.c  | 450 ++++++++++++++++++
 drivers/net/ethernet/ti/icssg/icssg_config.h  | 200 ++++++++
 drivers/net/ethernet/ti/icssg/icssg_prueth.h  |  15 +
 4 files changed, 1032 insertions(+)
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_classifier.c
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_config.c
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_config.h

diff --git a/drivers/net/ethernet/ti/icssg/icssg_classifier.c b/drivers/net/ethernet/ti/icssg/icssg_classifier.c
new file mode 100644
index 0000000000000..6df53ab17fbc5
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_classifier.c
@@ -0,0 +1,367 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Texas Instruments ICSSG Ethernet Driver
+ *
+ * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/types.h>
+#include <linux/regmap.h>
+
+#include "icssg_prueth.h"
+
+#define ICSSG_NUM_CLASSIFIERS	16
+#define ICSSG_NUM_FT1_SLOTS	8
+#define ICSSG_NUM_FT3_SLOTS	16
+
+#define ICSSG_NUM_CLASSIFIERS_IN_USE	5
+
+/* Filter 1 - FT1 */
+#define FT1_NUM_SLOTS	8
+#define FT1_SLOT_SIZE	0x10	/* bytes */
+
+/* offsets from FT1 slot base i.e. slot 1 start */
+#define FT1_DA0		0x0
+#define FT1_DA1		0x4
+#define FT1_DA0_MASK	0x8
+#define FT1_DA1_MASK	0xc
+
+#define FT1_N_REG(slize, n, reg)	\
+	(offs[slice].ft1_slot_base + FT1_SLOT_SIZE * (n) + (reg))
+
+#define FT1_LEN_MASK		GENMASK(19, 16)
+#define FT1_LEN_SHIFT		16
+#define FT1_LEN(len)		(((len) << FT1_LEN_SHIFT) & FT1_LEN_MASK)
+#define FT1_START_MASK		GENMASK(14, 0)
+#define FT1_START(start)	((start) & FT1_START_MASK)
+#define FT1_MATCH_SLOT(n)	(GENMASK(23, 16) & (BIT(n) << 16))
+
+/* FT1 config type */
+enum ft1_cfg_type {
+	FT1_CFG_TYPE_DISABLED = 0,
+	FT1_CFG_TYPE_EQ,
+	FT1_CFG_TYPE_GT,
+	FT1_CFG_TYPE_LT,
+};
+
+#define FT1_CFG_SHIFT(n)	(2 * (n))
+#define FT1_CFG_MASK(n)		(0x3 << FT1_CFG_SHIFT((n)))
+
+/* Filter 3 -  FT3 */
+#define FT3_NUM_SLOTS	16
+#define FT3_SLOT_SIZE	0x20	/* bytes */
+
+/* offsets from FT3 slot n's base */
+#define FT3_START		0
+#define FT3_START_AUTO		0x4
+#define FT3_START_OFFSET	0x8
+#define FT3_JUMP_OFFSET		0xc
+#define FT3_LEN			0x10
+#define FT3_CFG			0x14
+#define FT3_T			0x18
+#define FT3_T_MASK		0x1c
+
+#define FT3_N_REG(slize, n, reg)	\
+	(offs[slice].ft3_slot_base + FT3_SLOT_SIZE * (n) + (reg))
+
+/* offsets from rx_class n's base */
+#define RX_CLASS_AND_EN		0
+#define RX_CLASS_OR_EN		0x4
+#define RX_CLASS_NUM_SLOTS	16
+#define RX_CLASS_EN_SIZE	0x8	/* bytes */
+
+#define RX_CLASS_N_REG(slice, n, reg)	\
+	(offs[slice].rx_class_base + RX_CLASS_EN_SIZE * (n) + (reg))
+
+/* RX Class Gates */
+#define RX_CLASS_GATES_SIZE	0x4	/* bytes */
+
+#define RX_CLASS_GATES_N_REG(slice, n)	\
+	(offs[slice].rx_class_gates_base + RX_CLASS_GATES_SIZE * (n))
+
+#define RX_CLASS_GATES_ALLOW_MASK	BIT(6)
+#define RX_CLASS_GATES_RAW_MASK		BIT(5)
+#define RX_CLASS_GATES_PHASE_MASK	BIT(4)
+
+/* RX Class traffic data matching bits */
+#define RX_CLASS_FT_UC				BIT(31)
+#define RX_CLASS_FT_MC			BIT(30)
+#define RX_CLASS_FT_BC			BIT(29)
+#define RX_CLASS_FT_FW			BIT(28)
+#define RX_CLASS_FT_RCV			BIT(27)
+#define RX_CLASS_FT_VLAN		BIT(26)
+#define RX_CLASS_FT_DA_P		BIT(25)
+#define RX_CLASS_FT_DA_I		BIT(24)
+#define RX_CLASS_FT_FT1_MATCH_MASK	GENMASK(23, 16)
+#define RX_CLASS_FT_FT1_MATCH_SHIFT	16
+#define RX_CLASS_FT_FT3_MATCH_MASK	GENMASK(15, 0)
+#define RX_CLASS_FT_FT3_MATCH_SHIFT	0
+
+#define RX_CLASS_FT_FT1_MATCH(slot)	\
+	((BIT(slot) << RX_CLASS_FT_FT1_MATCH_SHIFT) & \
+	RX_CLASS_FT_FT1_MATCH_MASK)
+
+/* RX class type */
+enum rx_class_sel_type {
+	RX_CLASS_SEL_TYPE_OR = 0,
+	RX_CLASS_SEL_TYPE_AND = 1,
+	RX_CLASS_SEL_TYPE_OR_AND_AND = 2,
+	RX_CLASS_SEL_TYPE_OR_OR_AND = 3,
+};
+
+#define FT1_CFG_SHIFT(n)	(2 * (n))
+#define FT1_CFG_MASK(n)		(0x3 << FT1_CFG_SHIFT((n)))
+
+#define RX_CLASS_SEL_SHIFT(n)	(2 * (n))
+#define RX_CLASS_SEL_MASK(n)	(0x3 << RX_CLASS_SEL_SHIFT((n)))
+
+#define ICSSG_CFG_OFFSET	0
+#define MAC_INTERFACE_0		0x18
+#define MAC_INTERFACE_1		0x1c
+
+#define ICSSG_CFG_RX_L2_G_EN	BIT(2)
+
+/* These are register offsets per PRU */
+struct miig_rt_offsets {
+	u32 mac0;
+	u32 mac1;
+	u32 ft1_start_len;
+	u32 ft1_cfg;
+	u32 ft1_slot_base;
+	u32 ft3_slot_base;
+	u32 ft3_p_base;
+	u32 ft_rx_ptr;
+	u32 rx_class_base;
+	u32 rx_class_cfg1;
+	u32 rx_class_cfg2;
+	u32 rx_class_gates_base;
+	u32 rx_green;
+	u32 rx_rate_cfg_base;
+	u32 rx_rate_src_sel0;
+	u32 rx_rate_src_sel1;
+	u32 tx_rate_cfg_base;
+	u32 stat_base;
+	u32 tx_hsr_tag;
+	u32 tx_hsr_seq;
+	u32 tx_vlan_type;
+	u32 tx_vlan_ins;
+};
+
+/* These are the offset values for miig_rt_offsets registers */
+static const struct miig_rt_offsets offs[] = {
+	/* PRU0 */
+	{
+		0x8,
+		0xc,
+		0x80,
+		0x84,
+		0x88,
+		0x108,
+		0x308,
+		0x408,
+		0x40c,
+		0x48c,
+		0x490,
+		0x494,
+		0x4d4,
+		0x4e4,
+		0x504,
+		0x508,
+		0x50c,
+		0x54c,
+		0x63c,
+		0x640,
+		0x644,
+		0x648,
+	},
+	/* PRU1 */
+	{
+		0x10,
+		0x14,
+		0x64c,
+		0x650,
+		0x654,
+		0x6d4,
+		0x8d4,
+		0x9d4,
+		0x9d8,
+		0xa58,
+		0xa5c,
+		0xa60,
+		0xaa0,
+		0xab0,
+		0xad0,
+		0xad4,
+		0xad8,
+		0xb18,
+		0xc08,
+		0xc0c,
+		0xc10,
+		0xc14,
+	},
+};
+
+static void rx_class_ft1_set_start_len(struct regmap *miig_rt, int slice,
+				       u16 start, u8 len)
+{
+	u32 offset, val;
+
+	offset = offs[slice].ft1_start_len;
+	val = FT1_LEN(len) | FT1_START(start);
+	regmap_write(miig_rt, offset, val);
+}
+
+static void rx_class_ft1_set_da(struct regmap *miig_rt, int slice,
+				int n, const u8 *addr)
+{
+	u32 offset;
+
+	offset = FT1_N_REG(slice, n, FT1_DA0);
+	regmap_write(miig_rt, offset, (u32)(addr[0] | addr[1] << 8 |
+		     addr[2] << 16 | addr[3] << 24));
+	offset = FT1_N_REG(slice, n, FT1_DA1);
+	regmap_write(miig_rt, offset, (u32)(addr[4] | addr[5] << 8));
+}
+
+static void rx_class_ft1_set_da_mask(struct regmap *miig_rt, int slice,
+				     int n, const u8 *addr)
+{
+	u32 offset;
+
+	offset = FT1_N_REG(slice, n, FT1_DA0_MASK);
+	regmap_write(miig_rt, offset, (u32)(addr[0] | addr[1] << 8 |
+		     addr[2] << 16 | addr[3] << 24));
+	offset = FT1_N_REG(slice, n, FT1_DA1_MASK);
+	regmap_write(miig_rt, offset, (u32)(addr[4] | addr[5] << 8));
+}
+
+static void rx_class_ft1_cfg_set_type(struct regmap *miig_rt, int slice, int n,
+				      enum ft1_cfg_type type)
+{
+	u32 offset;
+
+	offset = offs[slice].ft1_cfg;
+	regmap_update_bits(miig_rt, offset, FT1_CFG_MASK(n),
+			   type << FT1_CFG_SHIFT(n));
+}
+
+static void rx_class_sel_set_type(struct regmap *miig_rt, int slice, int n,
+				  enum rx_class_sel_type type)
+{
+	u32 offset;
+
+	offset = offs[slice].rx_class_cfg1;
+	regmap_update_bits(miig_rt, offset, RX_CLASS_SEL_MASK(n),
+			   type << RX_CLASS_SEL_SHIFT(n));
+}
+
+static void rx_class_set_and(struct regmap *miig_rt, int slice, int n,
+			     u32 data)
+{
+	u32 offset;
+
+	offset = RX_CLASS_N_REG(slice, n, RX_CLASS_AND_EN);
+	regmap_write(miig_rt, offset, data);
+}
+
+static void rx_class_set_or(struct regmap *miig_rt, int slice, int n,
+			    u32 data)
+{
+	u32 offset;
+
+	offset = RX_CLASS_N_REG(slice, n, RX_CLASS_OR_EN);
+	regmap_write(miig_rt, offset, data);
+}
+
+void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac)
+{
+	regmap_write(miig_rt, MAC_INTERFACE_0, (u32)(mac[0] | mac[1] << 8 |
+		     mac[2] << 16 | mac[3] << 24));
+	regmap_write(miig_rt, MAC_INTERFACE_1, (u32)(mac[4] | mac[5] << 8));
+}
+
+void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac)
+{
+	regmap_write(miig_rt, offs[slice].mac0, (u32)(mac[0] | mac[1] << 8 |
+		     mac[2] << 16 | mac[3] << 24));
+	regmap_write(miig_rt, offs[slice].mac1, (u32)(mac[4] | mac[5] << 8));
+}
+
+/* disable all RX traffic */
+void icssg_class_disable(struct regmap *miig_rt, int slice)
+{
+	u32 data, offset;
+	int n;
+
+	/* Enable RX_L2_G */
+	regmap_update_bits(miig_rt, ICSSG_CFG_OFFSET, ICSSG_CFG_RX_L2_G_EN,
+			   ICSSG_CFG_RX_L2_G_EN);
+
+	for (n = 0; n < ICSSG_NUM_CLASSIFIERS; n++) {
+		/* AND_EN = 0 */
+		rx_class_set_and(miig_rt, slice, n, 0);
+		/* OR_EN = 0 */
+		rx_class_set_or(miig_rt, slice, n, 0);
+
+		/* set CFG1 to OR */
+		rx_class_sel_set_type(miig_rt, slice, n, RX_CLASS_SEL_TYPE_OR);
+
+		/* configure gate */
+		offset = RX_CLASS_GATES_N_REG(slice, n);
+		regmap_read(miig_rt, offset, &data);
+		/* clear class_raw so we go through filters */
+		data &= ~RX_CLASS_GATES_RAW_MASK;
+		/* set allow and phase mask */
+		data |= RX_CLASS_GATES_ALLOW_MASK | RX_CLASS_GATES_PHASE_MASK;
+		regmap_write(miig_rt, offset, data);
+	}
+
+	/* FT1 Disabled */
+	for (n = 0; n < ICSSG_NUM_FT1_SLOTS; n++) {
+		const u8 addr[] = { 0, 0, 0, 0, 0, 0, };
+
+		rx_class_ft1_cfg_set_type(miig_rt, slice, n,
+					  FT1_CFG_TYPE_DISABLED);
+		rx_class_ft1_set_da(miig_rt, slice, n, addr);
+		rx_class_ft1_set_da_mask(miig_rt, slice, n, addr);
+	}
+
+	/* clear CFG2 */
+	regmap_write(miig_rt, offs[slice].rx_class_cfg2, 0);
+}
+
+void icssg_class_default(struct regmap *miig_rt, int slice, bool allmulti)
+{
+	u32 data;
+
+	/* defaults */
+	icssg_class_disable(miig_rt, slice);
+
+	/* Setup Classifier */
+	/* match on Broadcast or MAC_PRU address */
+	data = RX_CLASS_FT_BC | RX_CLASS_FT_DA_P;
+
+	/* multicast */
+	if (allmulti)
+		data |= RX_CLASS_FT_MC;
+
+	rx_class_set_or(miig_rt, slice, 0, data);
+
+	/* set CFG1 for OR_OR_AND for classifier */
+	rx_class_sel_set_type(miig_rt, slice, 0, RX_CLASS_SEL_TYPE_OR_OR_AND);
+
+	/* clear CFG2 */
+	regmap_write(miig_rt, offs[slice].rx_class_cfg2, 0);
+}
+
+/* required for SAV check */
+void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr)
+{
+	const u8 mask_addr[] = { 0, 0, 0, 0, 0, 0, };
+
+	rx_class_ft1_set_start_len(miig_rt, slice, 0, 6);
+	rx_class_ft1_set_da(miig_rt, slice, 0, mac_addr);
+	rx_class_ft1_set_da_mask(miig_rt, slice, 0, mask_addr);
+	rx_class_ft1_cfg_set_type(miig_rt, slice, 0, FT1_CFG_TYPE_EQ);
+}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
new file mode 100644
index 0000000000000..ab648d3efe855
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -0,0 +1,450 @@
+// SPDX-License-Identifier: GPL-2.0
+/* ICSSG Ethernet driver
+ *
+ * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com
+ */
+
+#include <linux/iopoll.h>
+#include <linux/regmap.h>
+#include <uapi/linux/if_ether.h>
+#include "icssg_config.h"
+#include "icssg_prueth.h"
+#include "icssg_switch_map.h"
+#include "icssg_mii_rt.h"
+
+/* TX IPG Values to be set for 100M link speed. These values are
+ * in ocp_clk cycles. So need change if ocp_clk is changed for a specific
+ * h/w design.
+ */
+
+/* IPG is in core_clk cycles */
+#define MII_RT_TX_IPG_100M	0x17
+#define MII_RT_TX_IPG_1G	0xb
+
+#define	ICSSG_QUEUES_MAX		64
+#define	ICSSG_QUEUE_OFFSET		0xd00
+#define	ICSSG_QUEUE_PEEK_OFFSET		0xe00
+#define	ICSSG_QUEUE_CNT_OFFSET		0xe40
+#define	ICSSG_QUEUE_RESET_OFFSET	0xf40
+
+#define	ICSSG_NUM_TX_QUEUES	8
+
+#define	RECYCLE_Q_SLICE0	16
+#define	RECYCLE_Q_SLICE1	17
+
+#define	ICSSG_NUM_OTHER_QUEUES	5	/* port, host and special queues */
+
+#define	PORT_HI_Q_SLICE0	32
+#define	PORT_LO_Q_SLICE0	33
+#define	HOST_HI_Q_SLICE0	34
+#define	HOST_LO_Q_SLICE0	35
+#define	HOST_SPL_Q_SLICE0	40	/* Special Queue */
+
+#define	PORT_HI_Q_SLICE1	36
+#define	PORT_LO_Q_SLICE1	37
+#define	HOST_HI_Q_SLICE1	38
+#define	HOST_LO_Q_SLICE1	39
+#define	HOST_SPL_Q_SLICE1	41	/* Special Queue */
+
+#define MII_RXCFG_DEFAULT	(PRUSS_MII_RT_RXCFG_RX_ENABLE | \
+				 PRUSS_MII_RT_RXCFG_RX_DATA_RDY_MODE_DIS | \
+				 PRUSS_MII_RT_RXCFG_RX_L2_EN | \
+				 PRUSS_MII_RT_RXCFG_RX_L2_EOF_SCLR_DIS)
+
+#define MII_TXCFG_DEFAULT	(PRUSS_MII_RT_TXCFG_TX_ENABLE | \
+				 PRUSS_MII_RT_TXCFG_TX_AUTO_PREAMBLE | \
+				 PRUSS_MII_RT_TXCFG_TX_32_MODE_EN | \
+				 PRUSS_MII_RT_TXCFG_TX_IPG_WIRE_CLK_EN)
+
+#define ICSSG_CFG_DEFAULT	(ICSSG_CFG_TX_L1_EN | \
+				 ICSSG_CFG_TX_L2_EN | ICSSG_CFG_RX_L2_G_EN | \
+				 ICSSG_CFG_TX_PRU_EN | \
+				 ICSSG_CFG_SGMII_MODE)
+
+#define FDB_GEN_CFG1		0x60
+#define SMEM_VLAN_OFFSET	8
+#define SMEM_VLAN_OFFSET_MASK	GENMASK(25, 8)
+
+#define FDB_GEN_CFG2		0x64
+#define FDB_VLAN_EN		BIT(6)
+#define FDB_HOST_EN		BIT(2)
+#define FDB_PRU1_EN		BIT(1)
+#define FDB_PRU0_EN		BIT(0)
+#define FDB_EN_ALL		(FDB_PRU0_EN | FDB_PRU1_EN | \
+				 FDB_HOST_EN | FDB_VLAN_EN)
+
+/**
+ * struct map - ICSSG Queue Map
+ * @queue: Queue number
+ * @pd_addr_start: Packet descriptor queue reserved memory
+ * @flags: Flags
+ * @special: Indicates whether this queue is a special queue or not
+ */
+struct map {
+	int queue;
+	u32 pd_addr_start;
+	u32 flags;
+	bool special;
+};
+
+/* Hardware queue map for ICSSG */
+static const struct map hwq_map[2][ICSSG_NUM_OTHER_QUEUES] = {
+	{
+		{ PORT_HI_Q_SLICE0, PORT_DESC0_HI, 0x200000, 0 },
+		{ PORT_LO_Q_SLICE0, PORT_DESC0_LO, 0, 0 },
+		{ HOST_HI_Q_SLICE0, HOST_DESC0_HI, 0x200000, 0 },
+		{ HOST_LO_Q_SLICE0, HOST_DESC0_LO, 0, 0 },
+		{ HOST_SPL_Q_SLICE0, HOST_SPPD0, 0x400000, 1 },
+	},
+	{
+		{ PORT_HI_Q_SLICE1, PORT_DESC1_HI, 0xa00000, 0 },
+		{ PORT_LO_Q_SLICE1, PORT_DESC1_LO, 0x800000, 0 },
+		{ HOST_HI_Q_SLICE1, HOST_DESC1_HI, 0xa00000, 0 },
+		{ HOST_LO_Q_SLICE1, HOST_DESC1_LO, 0x800000, 0 },
+		{ HOST_SPL_Q_SLICE1, HOST_SPPD1, 0xc00000, 1 },
+	},
+};
+
+static void icssg_config_mii_init(struct prueth_emac *emac)
+{
+	u32 rxcfg, txcfg, rxcfg_reg, txcfg_reg, pcnt_reg;
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+	struct regmap *mii_rt;
+
+	mii_rt = prueth->mii_rt;
+
+	rxcfg_reg = (slice == ICSS_MII0) ? PRUSS_MII_RT_RXCFG0 :
+				       PRUSS_MII_RT_RXCFG1;
+	txcfg_reg = (slice == ICSS_MII0) ? PRUSS_MII_RT_TXCFG0 :
+				       PRUSS_MII_RT_TXCFG1;
+	pcnt_reg = (slice == ICSS_MII0) ? PRUSS_MII_RT_RX_PCNT0 :
+				       PRUSS_MII_RT_RX_PCNT1;
+
+	rxcfg = MII_RXCFG_DEFAULT;
+	txcfg = MII_TXCFG_DEFAULT;
+
+	if (slice == ICSS_MII1)
+		rxcfg |= PRUSS_MII_RT_RXCFG_RX_MUX_SEL;
+
+	/* In MII mode TX lines swapped inside ICSSG, so TX_MUX_SEL cfg need
+	 * to be swapped also comparing to RGMII mode.
+	 */
+	if (emac->phy_if == PHY_INTERFACE_MODE_MII && slice == ICSS_MII0)
+		txcfg |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL;
+	else if (emac->phy_if != PHY_INTERFACE_MODE_MII && slice == ICSS_MII1)
+		txcfg |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL;
+
+	regmap_write(mii_rt, rxcfg_reg, rxcfg);
+	regmap_write(mii_rt, txcfg_reg, txcfg);
+	regmap_write(mii_rt, pcnt_reg, 0x1);
+}
+
+static void icssg_miig_queues_init(struct prueth *prueth, int slice)
+{
+	struct regmap *miig_rt = prueth->miig_rt;
+	void __iomem *smem = prueth->shram.va;
+	u8 pd[ICSSG_SPECIAL_PD_SIZE];
+	int queue = 0, i, j;
+	u32 *pdword;
+
+	/* reset hwqueues */
+	if (slice)
+		queue = ICSSG_NUM_TX_QUEUES;
+
+	for (i = 0; i < ICSSG_NUM_TX_QUEUES; i++) {
+		regmap_write(miig_rt, ICSSG_QUEUE_RESET_OFFSET, queue);
+		queue++;
+	}
+
+	queue = slice ? RECYCLE_Q_SLICE1 : RECYCLE_Q_SLICE0;
+	regmap_write(miig_rt, ICSSG_QUEUE_RESET_OFFSET, queue);
+
+	for (i = 0; i < ICSSG_NUM_OTHER_QUEUES; i++) {
+		regmap_write(miig_rt, ICSSG_QUEUE_RESET_OFFSET,
+			     hwq_map[slice][i].queue);
+	}
+
+	/* initialize packet descriptors in SMEM */
+	/* push pakcet descriptors to hwqueues */
+
+	pdword = (u32 *)pd;
+	for (j = 0; j < ICSSG_NUM_OTHER_QUEUES; j++) {
+		const struct map *mp;
+		int pd_size, num_pds;
+		u32 pdaddr;
+
+		mp = &hwq_map[slice][j];
+		if (mp->special) {
+			pd_size = ICSSG_SPECIAL_PD_SIZE;
+			num_pds = ICSSG_NUM_SPECIAL_PDS;
+		} else	{
+			pd_size = ICSSG_NORMAL_PD_SIZE;
+			num_pds = ICSSG_NUM_NORMAL_PDS;
+		}
+
+		for (i = 0; i < num_pds; i++) {
+			memset(pd, 0, pd_size);
+
+			pdword[0] &= ICSSG_FLAG_MASK;
+			pdword[0] |= mp->flags;
+			pdaddr = mp->pd_addr_start + i * pd_size;
+
+			memcpy_toio(smem + pdaddr, pd, pd_size);
+			queue = mp->queue;
+			regmap_write(miig_rt, ICSSG_QUEUE_OFFSET + 4 * queue,
+				     pdaddr);
+		}
+	}
+}
+
+void icssg_config_ipg(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+
+	switch (emac->speed) {
+	case SPEED_1000:
+		icssg_mii_update_ipg(prueth->mii_rt, slice, MII_RT_TX_IPG_1G);
+		break;
+	case SPEED_100:
+		icssg_mii_update_ipg(prueth->mii_rt, slice, MII_RT_TX_IPG_100M);
+		break;
+	default:
+		/* Other links speeds not supported */
+		netdev_err(emac->ndev, "Unsupported link speed\n");
+		return;
+	}
+}
+
+static void emac_r30_cmd_init(struct prueth_emac *emac)
+{
+	struct icssg_r30_cmd __iomem *p;
+	int i;
+
+	p = emac->dram.va + MGR_R30_CMD_OFFSET;
+
+	for (i = 0; i < 4; i++)
+		writel(EMAC_NONE, &p->cmd[i]);
+}
+
+static int emac_r30_is_done(struct prueth_emac *emac)
+{
+	const struct icssg_r30_cmd __iomem *p;
+	u32 cmd;
+	int i;
+
+	p = emac->dram.va + MGR_R30_CMD_OFFSET;
+
+	for (i = 0; i < 4; i++) {
+		cmd = readl(&p->cmd[i]);
+		if (cmd != EMAC_NONE)
+			return 0;
+	}
+
+	return 1;
+}
+
+static int prueth_emac_buffer_setup(struct prueth_emac *emac)
+{
+	struct icssg_buffer_pool_cfg __iomem *bpool_cfg;
+	struct icssg_rxq_ctx __iomem *rxq_ctx;
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+	u32 addr;
+	int i;
+
+	/* Layout to have 64KB aligned buffer pool
+	 * |BPOOL0|BPOOL1|RX_CTX0|RX_CTX1|
+	 */
+
+	addr = lower_32_bits(prueth->msmcram.pa);
+	if (slice)
+		addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE;
+
+	if (addr % SZ_64K) {
+		dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n");
+		return -EINVAL;
+	}
+
+	bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET;
+	/* workaround for f/w bug. bpool 0 needs to be initilalized */
+	writel(addr, &bpool_cfg[0].addr);
+	writel(0, &bpool_cfg[0].len);
+
+	for (i = PRUETH_EMAC_BUF_POOL_START;
+	     i < PRUETH_EMAC_BUF_POOL_START + PRUETH_NUM_BUF_POOLS;
+	     i++) {
+		writel(addr, &bpool_cfg[i].addr);
+		writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len);
+		addr += PRUETH_EMAC_BUF_POOL_SIZE;
+	}
+
+	if (!slice)
+		addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE;
+	else
+		addr += PRUETH_EMAC_RX_CTX_BUF_SIZE * 2;
+
+	/* Pre-emptible RX buffer queue */
+	rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET;
+	for (i = 0; i < 3; i++)
+		writel(addr, &rxq_ctx->start[i]);
+
+	addr += PRUETH_EMAC_RX_CTX_BUF_SIZE;
+	writel(addr, &rxq_ctx->end);
+
+	/* Express RX buffer queue */
+	rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET;
+	for (i = 0; i < 3; i++)
+		writel(addr, &rxq_ctx->start[i]);
+
+	addr += PRUETH_EMAC_RX_CTX_BUF_SIZE;
+	writel(addr, &rxq_ctx->end);
+
+	return 0;
+}
+
+static void icssg_init_emac_mode(struct prueth *prueth)
+{
+	/* When the device is configured as a bridge and it is being brought
+	 * back to the emac mode, the host mac address has to be set as 0.
+	 */
+	u8 mac[ETH_ALEN] = { 0 };
+
+	if (prueth->emacs_initialized)
+		return;
+
+	regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1,
+			   SMEM_VLAN_OFFSET_MASK, 0);
+	regmap_write(prueth->miig_rt, FDB_GEN_CFG2, 0);
+	/* Clear host MAC address */
+	icssg_class_set_host_mac_addr(prueth->miig_rt, mac);
+}
+
+int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
+{
+	void __iomem *config = emac->dram.va + ICSSG_CONFIG_OFFSET;
+	struct icssg_flow_cfg __iomem *flow_cfg;
+	int ret;
+
+	icssg_init_emac_mode(prueth);
+
+	memset_io(config, 0, TAS_GATE_MASK_LIST0);
+	icssg_miig_queues_init(prueth, slice);
+
+	emac->speed = SPEED_1000;
+	emac->duplex = DUPLEX_FULL;
+	if (!phy_interface_mode_is_rgmii(emac->phy_if)) {
+		emac->speed = SPEED_100;
+		emac->duplex = DUPLEX_FULL;
+	}
+	regmap_update_bits(prueth->miig_rt, ICSSG_CFG_OFFSET,
+			   ICSSG_CFG_DEFAULT, ICSSG_CFG_DEFAULT);
+	icssg_miig_set_interface_mode(prueth->miig_rt, slice, emac->phy_if);
+	icssg_config_mii_init(emac);
+	icssg_config_ipg(emac);
+	icssg_update_rgmii_cfg(prueth->miig_rt, emac);
+
+	/* set GPI mode */
+	pruss_cfg_gpimode(prueth->pruss, prueth->pru_id[slice],
+			  PRUSS_GPI_MODE_MII);
+
+	/* enable XFR shift for PRU and RTU */
+	pruss_cfg_xfr_enable(prueth->pruss, PRU_TYPE_PRU, true);
+	pruss_cfg_xfr_enable(prueth->pruss, PRU_TYPE_RTU, true);
+
+	/* set C28 to 0x100 */
+	pru_rproc_set_ctable(prueth->pru[slice], PRU_C28, 0x100 << 8);
+	pru_rproc_set_ctable(prueth->rtu[slice], PRU_C28, 0x100 << 8);
+	pru_rproc_set_ctable(prueth->txpru[slice], PRU_C28, 0x100 << 8);
+
+	flow_cfg = config + PSI_L_REGULAR_FLOW_ID_BASE_OFFSET;
+	writew(emac->rx_flow_id_base, &flow_cfg->rx_base_flow);
+	writew(0, &flow_cfg->mgm_base_flow);
+	writeb(0, config + SPL_PKT_DEFAULT_PRIORITY);
+	writeb(0, config + QUEUE_NUM_UNTAGGED);
+
+	ret = prueth_emac_buffer_setup(emac);
+	if (ret)
+		return ret;
+
+	emac_r30_cmd_init(emac);
+
+	return 0;
+}
+
+/* Bitmask for ICSSG r30 commands */
+static const struct icssg_r30_cmd emac_r32_bitmask[] = {
+	{{0xffff0004, 0xffff0100, 0xffff0100, EMAC_NONE}},	/* EMAC_PORT_DISABLE */
+	{{0xfffb0040, 0xfeff0200, 0xfeff0200, EMAC_NONE}},	/* EMAC_PORT_BLOCK */
+	{{0xffbb0000, 0xfcff0000, 0xdcff0000, EMAC_NONE}},	/* EMAC_PORT_FORWARD */
+	{{0xffbb0000, 0xfcff0000, 0xfcff2000, EMAC_NONE}},	/* EMAC_PORT_FORWARD_WO_LEARNING */
+	{{0xffff0001, EMAC_NONE,  EMAC_NONE, EMAC_NONE}},	/* ACCEPT ALL */
+	{{0xfffe0002, EMAC_NONE,  EMAC_NONE, EMAC_NONE}},	/* ACCEPT TAGGED */
+	{{0xfffc0000, EMAC_NONE,  EMAC_NONE, EMAC_NONE}},	/* ACCEPT UNTAGGED and PRIO */
+	{{EMAC_NONE,  0xffff0020, EMAC_NONE, EMAC_NONE}},	/* TAS Trigger List change */
+	{{EMAC_NONE,  0xdfff1000, EMAC_NONE, EMAC_NONE}},	/* TAS set state ENABLE*/
+	{{EMAC_NONE,  0xefff2000, EMAC_NONE, EMAC_NONE}},	/* TAS set state RESET*/
+	{{EMAC_NONE,  0xcfff0000, EMAC_NONE, EMAC_NONE}},	/* TAS set state DISABLE*/
+	{{EMAC_NONE,  EMAC_NONE,  0xffff0400, EMAC_NONE}},	/* UC flooding ENABLE*/
+	{{EMAC_NONE,  EMAC_NONE,  0xfbff0000, EMAC_NONE}},	/* UC flooding DISABLE*/
+	{{EMAC_NONE,  EMAC_NONE,  0xffff0800, EMAC_NONE}},	/* MC flooding ENABLE*/
+	{{EMAC_NONE,  EMAC_NONE,  0xf7ff0000, EMAC_NONE}},	/* MC flooding DISABLE*/
+	{{EMAC_NONE,  0xffff4000, EMAC_NONE, EMAC_NONE}},	/* Preemption on Tx ENABLE*/
+	{{EMAC_NONE,  0xbfff0000, EMAC_NONE, EMAC_NONE}},	/* Preemption on Tx DISABLE*/
+	{{0xffff0010,  EMAC_NONE, 0xffff0010, EMAC_NONE}},	/* VLAN AWARE*/
+	{{0xffef0000,  EMAC_NONE, 0xffef0000, EMAC_NONE}}	/* VLAN UNWARE*/
+};
+
+int emac_set_port_state(struct prueth_emac *emac,
+			enum icssg_port_state_cmd cmd)
+{
+	struct icssg_r30_cmd __iomem *p;
+	int ret = -ETIMEDOUT;
+	int done = 0;
+	int i;
+
+	p = emac->dram.va + MGR_R30_CMD_OFFSET;
+
+	if (cmd >= ICSSG_EMAC_PORT_MAX_COMMANDS) {
+		netdev_err(emac->ndev, "invalid port command\n");
+		return -EINVAL;
+	}
+
+	/* only one command at a time allowed to firmware */
+	mutex_lock(&emac->cmd_lock);
+
+	for (i = 0; i < 4; i++)
+		writel(emac_r32_bitmask[cmd].cmd[i], &p->cmd[i]);
+
+	/* wait for done */
+	ret = read_poll_timeout(emac_r30_is_done, done, done == 1,
+				1000, 10000, false, emac);
+
+	if (ret == -ETIMEDOUT)
+		netdev_err(emac->ndev, "timeout waiting for command done\n");
+
+	mutex_unlock(&emac->cmd_lock);
+
+	return ret;
+}
+
+void icssg_config_set_speed(struct prueth_emac *emac)
+{
+	u8 fw_speed;
+
+	switch (emac->speed) {
+	case SPEED_1000:
+		fw_speed = FW_LINK_SPEED_1G;
+		break;
+	case SPEED_100:
+		fw_speed = FW_LINK_SPEED_100M;
+		break;
+	default:
+		/* Other links speeds not supported */
+		netdev_err(emac->ndev, "Unsupported link speed\n");
+		return;
+	}
+
+	writeb(fw_speed, emac->dram.va + PORT_LINK_SPEED_OFFSET);
+}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h
new file mode 100644
index 0000000000000..43eb0922172ac
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.h
@@ -0,0 +1,200 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Texas Instruments ICSSG Ethernet driver
+ *
+ * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#ifndef __NET_TI_ICSSG_CONFIG_H
+#define __NET_TI_ICSSG_CONFIG_H
+
+struct icssg_buffer_pool_cfg {
+	__le32	addr;
+	__le32	len;
+} __packed;
+
+struct icssg_flow_cfg {
+	__le16 rx_base_flow;
+	__le16 mgm_base_flow;
+} __packed;
+
+#define PRUETH_PKT_TYPE_CMD	0x10
+#define PRUETH_NAV_PS_DATA_SIZE	16	/* Protocol specific data size */
+#define PRUETH_NAV_SW_DATA_SIZE	16	/* SW related data size */
+#define PRUETH_MAX_TX_DESC	512
+#define PRUETH_MAX_RX_DESC	512
+#define PRUETH_MAX_RX_FLOWS	1	/* excluding default flow */
+#define PRUETH_RX_FLOW_DATA	0
+
+#define PRUETH_EMAC_BUF_POOL_SIZE	SZ_8K
+#define PRUETH_EMAC_POOLS_PER_SLICE	24
+#define PRUETH_EMAC_BUF_POOL_START	8
+#define PRUETH_NUM_BUF_POOLS	8
+#define PRUETH_EMAC_RX_CTX_BUF_SIZE	SZ_16K	/* per slice */
+#define MSMC_RAM_SIZE	\
+	(2 * (PRUETH_EMAC_BUF_POOL_SIZE * PRUETH_NUM_BUF_POOLS + \
+	 PRUETH_EMAC_RX_CTX_BUF_SIZE * 2))
+
+struct icssg_rxq_ctx {
+	__le32 start[3];
+	__le32 end;
+} __packed;
+
+/* Load time Fiwmware Configuration */
+
+#define ICSSG_FW_MGMT_CMD_HEADER	0x81
+#define ICSSG_FW_MGMT_FDB_CMD_TYPE	0x03
+#define ICSSG_FW_MGMT_CMD_TYPE		0x04
+#define ICSSG_FW_MGMT_PKT		0x80000000
+
+struct icssg_r30_cmd {
+	u32 cmd[4];
+} __packed;
+
+enum icssg_port_state_cmd {
+	ICSSG_EMAC_PORT_DISABLE = 0,
+	ICSSG_EMAC_PORT_BLOCK,
+	ICSSG_EMAC_PORT_FORWARD,
+	ICSSG_EMAC_PORT_FORWARD_WO_LEARNING,
+	ICSSG_EMAC_PORT_ACCEPT_ALL,
+	ICSSG_EMAC_PORT_ACCEPT_TAGGED,
+	ICSSG_EMAC_PORT_ACCEPT_UNTAGGED_N_PRIO,
+	ICSSG_EMAC_PORT_TAS_TRIGGER,
+	ICSSG_EMAC_PORT_TAS_ENABLE,
+	ICSSG_EMAC_PORT_TAS_RESET,
+	ICSSG_EMAC_PORT_TAS_DISABLE,
+	ICSSG_EMAC_PORT_UC_FLOODING_ENABLE,
+	ICSSG_EMAC_PORT_UC_FLOODING_DISABLE,
+	ICSSG_EMAC_PORT_MC_FLOODING_ENABLE,
+	ICSSG_EMAC_PORT_MC_FLOODING_DISABLE,
+	ICSSG_EMAC_PORT_PREMPT_TX_ENABLE,
+	ICSSG_EMAC_PORT_PREMPT_TX_DISABLE,
+	ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE,
+	ICSSG_EMAC_PORT_VLAN_AWARE_DISABLE,
+	ICSSG_EMAC_PORT_MAX_COMMANDS
+};
+
+#define EMAC_NONE           0xffff0000
+#define EMAC_PRU0_P_DI      0xffff0004
+#define EMAC_PRU1_P_DI      0xffff0040
+#define EMAC_TX_P_DI        0xffff0100
+
+#define EMAC_PRU0_P_EN      0xfffb0000
+#define EMAC_PRU1_P_EN      0xffbf0000
+#define EMAC_TX_P_EN        0xfeff0000
+
+#define EMAC_P_BLOCK        0xffff0040
+#define EMAC_TX_P_BLOCK     0xffff0200
+#define EMAC_P_UNBLOCK      0xffbf0000
+#define EMAC_TX_P_UNBLOCK   0xfdff0000
+#define EMAC_LEAN_EN        0xfff70000
+#define EMAC_LEAN_DI        0xffff0008
+
+#define EMAC_ACCEPT_ALL     0xffff0001
+#define EMAC_ACCEPT_TAG     0xfffe0002
+#define EMAC_ACCEPT_PRIOR   0xfffc0000
+
+/* Config area lies in DRAM */
+#define ICSSG_CONFIG_OFFSET	0x0
+
+/* Config area lies in shared RAM */
+#define ICSSG_CONFIG_OFFSET_SLICE0   0
+#define ICSSG_CONFIG_OFFSET_SLICE1   0x8000
+
+#define ICSSG_NUM_NORMAL_PDS	64
+#define ICSSG_NUM_SPECIAL_PDS	16
+
+#define ICSSG_NORMAL_PD_SIZE	8
+#define ICSSG_SPECIAL_PD_SIZE	20
+
+#define ICSSG_FLAG_MASK		0xff00ffff
+
+struct icssg_setclock_desc {
+	u8 request;
+	u8 restore;
+	u8 acknowledgment;
+	u8 cmp_status;
+	u32 margin;
+	u32 cyclecounter0_set;
+	u32 cyclecounter1_set;
+	u32 iepcount_set;
+	u32 rsvd1;
+	u32 rsvd2;
+	u32 CMP0_current;
+	u32 iepcount_current;
+	u32 difference;
+	u32 cyclecounter0_new;
+	u32 cyclecounter1_new;
+	u32 CMP0_new;
+} __packed;
+
+#define ICSSG_CMD_POP_SLICE0	56
+#define ICSSG_CMD_POP_SLICE1	60
+
+#define ICSSG_CMD_PUSH_SLICE0	57
+#define ICSSG_CMD_PUSH_SLICE1	61
+
+#define ICSSG_RSP_POP_SLICE0	58
+#define ICSSG_RSP_POP_SLICE1	62
+
+#define ICSSG_RSP_PUSH_SLICE0	56
+#define ICSSG_RSP_PUSH_SLICE1	60
+
+#define ICSSG_TS_POP_SLICE0	59
+#define ICSSG_TS_POP_SLICE1	63
+
+#define ICSSG_TS_PUSH_SLICE0	40
+#define ICSSG_TS_PUSH_SLICE1	41
+
+/* FDB FID_C2 flag definitions */
+/* Indicates host port membership.*/
+#define ICSSG_FDB_ENTRY_P0_MEMBERSHIP         BIT(0)
+/* Indicates that MAC ID is connected to physical port 1 */
+#define ICSSG_FDB_ENTRY_P1_MEMBERSHIP         BIT(1)
+/* Indicates that MAC ID is connected to physical port 2 */
+#define ICSSG_FDB_ENTRY_P2_MEMBERSHIP         BIT(2)
+/* Ageable bit is set for learned entries and cleared for static entries */
+#define ICSSG_FDB_ENTRY_AGEABLE               BIT(3)
+/* If set for DA then packet is determined to be a special packet */
+#define ICSSG_FDB_ENTRY_BLOCK                 BIT(4)
+/* If set for DA then the SA from the packet is not learned */
+#define ICSSG_FDB_ENTRY_SECURE                BIT(5)
+/* If set, it means packet has been seen recently with source address + FID
+ * matching MAC address/FID of entry
+ */
+#define ICSSG_FDB_ENTRY_TOUCHED               BIT(6)
+/* Set if entry is valid */
+#define ICSSG_FDB_ENTRY_VALID                 BIT(7)
+
+/**
+ * struct prueth_vlan_tbl - VLAN table entries struct in ICSSG SMEM
+ * @fid_c1: membership and forwarding rules flag to this table. See
+ *          above to defines for bit definitions
+ * @fid: FDB index for this VID (there is 1-1 mapping b/w VID and FID)
+ */
+struct prueth_vlan_tbl {
+	u8 fid_c1;
+	u8 fid;
+} __packed;
+
+/**
+ * struct prueth_fdb_slot - Result of FDB slot lookup
+ * @mac: MAC address
+ * @fid: fid to be associated with MAC
+ * @fid_c2: FID_C2 entry for this MAC
+ */
+struct prueth_fdb_slot {
+	u8 mac[ETH_ALEN];
+	u8 fid;
+	u8 fid_c2;
+} __packed;
+
+enum icssg_ietfpe_verify_states {
+	ICSSG_IETFPE_STATE_UNKNOWN = 0,
+	ICSSG_IETFPE_STATE_INITIAL,
+	ICSSG_IETFPE_STATE_VERIFYING,
+	ICSSG_IETFPE_STATE_SUCCEEDED,
+	ICSSG_IETFPE_STATE_FAILED,
+	ICSSG_IETFPE_STATE_DISABLED
+};
+#endif /* __NET_TI_ICSSG_CONFIG_H */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 8512f19a9b4d4..e93488a79dbff 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -194,4 +194,19 @@ static inline int prueth_emac_slice(struct prueth_emac *emac)
 	}
 }
 
+/* Classifier helpers */
+void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac);
+void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac);
+void icssg_class_disable(struct regmap *miig_rt, int slice);
+void icssg_class_default(struct regmap *miig_rt, int slice, bool allmulti);
+void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr);
+
+/* config helpers */
+void icssg_config_ipg(struct prueth_emac *emac);
+int icssg_config(struct prueth *prueth, struct prueth_emac *emac,
+		 int slice);
+int emac_set_port_state(struct prueth_emac *emac,
+			enum icssg_port_state_cmd state);
+void icssg_config_set_speed(struct prueth_emac *emac);
+
 #endif /* __NET_TI_ICSSG_PRUETH_H */
-- 
GitLab


From b8d5008f8c517b7cd61855fdb574b1ee80bcf4a3 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 1 Aug 2023 14:44:22 +0530
Subject: [PATCH 0753/1806] net: ti: icssg-prueth: Add icssg queues APIs and
 macros

Add icssg_queue.c file. This file introduces macros and APIs related to
ICSSG queues. These will be used by ICSSG Ethernet driver.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.h |  5 ++
 drivers/net/ethernet/ti/icssg/icssg_queues.c | 50 ++++++++++++++++++++
 2 files changed, 55 insertions(+)
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_queues.c

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index e93488a79dbff..42fdf4005010a 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -209,4 +209,9 @@ int emac_set_port_state(struct prueth_emac *emac,
 			enum icssg_port_state_cmd state);
 void icssg_config_set_speed(struct prueth_emac *emac);
 
+/* Buffer queue helpers */
+int icssg_queue_pop(struct prueth *prueth, u8 queue);
+void icssg_queue_push(struct prueth *prueth, int queue, u16 addr);
+u32 icssg_queue_level(struct prueth *prueth, int queue);
+
 #endif /* __NET_TI_ICSSG_PRUETH_H */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_queues.c b/drivers/net/ethernet/ti/icssg/icssg_queues.c
new file mode 100644
index 0000000000000..3c34f61ad40b0
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_queues.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* ICSSG Buffer queue helpers
+ *
+ * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com
+ */
+
+#include <linux/regmap.h>
+#include "icssg_prueth.h"
+
+#define ICSSG_QUEUES_MAX		64
+#define ICSSG_QUEUE_OFFSET		0xd00
+#define ICSSG_QUEUE_PEEK_OFFSET		0xe00
+#define ICSSG_QUEUE_CNT_OFFSET		0xe40
+#define	ICSSG_QUEUE_RESET_OFFSET	0xf40
+
+int icssg_queue_pop(struct prueth *prueth, u8 queue)
+{
+	u32 val, cnt;
+
+	if (queue >= ICSSG_QUEUES_MAX)
+		return -EINVAL;
+
+	regmap_read(prueth->miig_rt, ICSSG_QUEUE_CNT_OFFSET + 4 * queue, &cnt);
+	if (!cnt)
+		return -EINVAL;
+
+	regmap_read(prueth->miig_rt, ICSSG_QUEUE_OFFSET + 4 * queue, &val);
+
+	return val;
+}
+
+void icssg_queue_push(struct prueth *prueth, int queue, u16 addr)
+{
+	if (queue >= ICSSG_QUEUES_MAX)
+		return;
+
+	regmap_write(prueth->miig_rt, ICSSG_QUEUE_OFFSET + 4 * queue, addr);
+}
+
+u32 icssg_queue_level(struct prueth *prueth, int queue)
+{
+	u32 reg;
+
+	if (queue >= ICSSG_QUEUES_MAX)
+		return 0;
+
+	regmap_read(prueth->miig_rt, ICSSG_QUEUE_CNT_OFFSET + 4 * queue, &reg);
+
+	return reg;
+}
-- 
GitLab


From 172e604a8c62d01779cf6b22cdaa2cc5e17c879a Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 1 Aug 2023 14:44:23 +0530
Subject: [PATCH 0754/1806] dt-bindings: net: Add ICSSG Ethernet

Add a YAML binding document for the ICSSG Programmable real time unit
based Ethernet hardware. The ICSSG driver uses the PRU and PRUSS consumer
APIs to interface the PRUs and load/run the firmware for supporting
ethernet functionality.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../bindings/net/ti,icssg-prueth.yaml         | 184 ++++++++++++++++++
 1 file changed, 184 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml

diff --git a/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml b/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml
new file mode 100644
index 0000000000000..8ec30b3eb7600
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml
@@ -0,0 +1,184 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/ti,icssg-prueth.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments ICSSG PRUSS Ethernet
+
+maintainers:
+  - Md Danish Anwar <danishanwar@ti.com>
+
+description:
+  Ethernet based on the Programmable Real-Time Unit and Industrial
+  Communication Subsystem.
+
+allOf:
+  - $ref: /schemas/remoteproc/ti,pru-consumer.yaml#
+
+properties:
+  compatible:
+    enum:
+      - ti,am654-icssg-prueth  # for AM65x SoC family
+
+  sram:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      phandle to MSMC SRAM node
+
+  dmas:
+    maxItems: 10
+
+  dma-names:
+    items:
+      - const: tx0-0
+      - const: tx0-1
+      - const: tx0-2
+      - const: tx0-3
+      - const: tx1-0
+      - const: tx1-1
+      - const: tx1-2
+      - const: tx1-3
+      - const: rx0
+      - const: rx1
+
+  ti,mii-g-rt:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      phandle to MII_G_RT module's syscon regmap.
+
+  ti,mii-rt:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      phandle to MII_RT module's syscon regmap
+
+  interrupts:
+    maxItems: 2
+    description:
+      Interrupt specifiers to TX timestamp IRQ.
+
+  interrupt-names:
+    items:
+      - const: tx_ts0
+      - const: tx_ts1
+
+  ethernet-ports:
+    type: object
+    additionalProperties: false
+
+    properties:
+      '#address-cells':
+        const: 1
+      '#size-cells':
+        const: 0
+
+    patternProperties:
+      ^port@[0-1]$:
+        type: object
+        description: ICSSG PRUETH external ports
+        $ref: ethernet-controller.yaml#
+        unevaluatedProperties: false
+
+        properties:
+          reg:
+            items:
+              - enum: [0, 1]
+            description: ICSSG PRUETH port number
+
+          interrupts:
+            maxItems: 1
+
+          ti,syscon-rgmii-delay:
+            items:
+              - items:
+                  - description: phandle to system controller node
+                  - description: The offset to ICSSG control register
+            $ref: /schemas/types.yaml#/definitions/phandle-array
+            description:
+              phandle to system controller node and register offset
+              to ICSSG control register for RGMII transmit delay
+
+        required:
+          - reg
+    anyOf:
+      - required:
+          - port@0
+      - required:
+          - port@1
+
+required:
+  - compatible
+  - sram
+  - dmas
+  - dma-names
+  - ethernet-ports
+  - ti,mii-g-rt
+  - interrupts
+  - interrupt-names
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    /* Example k3-am654 base board SR2.0, dual-emac */
+    pruss2_eth: ethernet {
+        compatible = "ti,am654-icssg-prueth";
+        pinctrl-names = "default";
+        pinctrl-0 = <&icssg2_rgmii_pins_default>;
+        sram = <&msmc_ram>;
+
+        ti,prus = <&pru2_0>, <&rtu2_0>, <&tx_pru2_0>,
+                  <&pru2_1>, <&rtu2_1>, <&tx_pru2_1>;
+        firmware-name = "ti-pruss/am65x-pru0-prueth-fw.elf",
+                        "ti-pruss/am65x-rtu0-prueth-fw.elf",
+                        "ti-pruss/am65x-txpru0-prueth-fw.elf",
+                        "ti-pruss/am65x-pru1-prueth-fw.elf",
+                        "ti-pruss/am65x-rtu1-prueth-fw.elf",
+                        "ti-pruss/am65x-txpru1-prueth-fw.elf";
+        ti,pruss-gp-mux-sel = <2>,      /* MII mode */
+                              <2>,
+                              <2>,
+                              <2>,      /* MII mode */
+                              <2>,
+                              <2>;
+        dmas = <&main_udmap 0xc300>, /* egress slice 0 */
+               <&main_udmap 0xc301>, /* egress slice 0 */
+               <&main_udmap 0xc302>, /* egress slice 0 */
+               <&main_udmap 0xc303>, /* egress slice 0 */
+               <&main_udmap 0xc304>, /* egress slice 1 */
+               <&main_udmap 0xc305>, /* egress slice 1 */
+               <&main_udmap 0xc306>, /* egress slice 1 */
+               <&main_udmap 0xc307>, /* egress slice 1 */
+               <&main_udmap 0x4300>, /* ingress slice 0 */
+               <&main_udmap 0x4301>; /* ingress slice 1 */
+        dma-names = "tx0-0", "tx0-1", "tx0-2", "tx0-3",
+                    "tx1-0", "tx1-1", "tx1-2", "tx1-3",
+                    "rx0", "rx1";
+        ti,mii-g-rt = <&icssg2_mii_g_rt>;
+        interrupt-parent = <&icssg2_intc>;
+        interrupts = <24 0 2>, <25 1 3>;
+        interrupt-names = "tx_ts0", "tx_ts1";
+        ethernet-ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+            pruss2_emac0: port@0 {
+                reg = <0>;
+                phy-handle = <&pruss2_eth0_phy>;
+                phy-mode = "rgmii-id";
+                interrupts-extended = <&icssg2_intc 24>;
+                ti,syscon-rgmii-delay = <&scm_conf 0x4120>;
+                /* Filled in by bootloader */
+                local-mac-address = [00 00 00 00 00 00];
+            };
+
+            pruss2_emac1: port@1 {
+                reg = <1>;
+                phy-handle = <&pruss2_eth1_phy>;
+                phy-mode = "rgmii-id";
+                interrupts-extended = <&icssg2_intc 25>;
+                ti,syscon-rgmii-delay = <&scm_conf 0x4124>;
+                /* Filled in by bootloader */
+                local-mac-address = [00 00 00 00 00 00];
+            };
+        };
+    };
-- 
GitLab


From 128d5874c0822105ae9556d5435fb8562aff2e3b Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Tue, 1 Aug 2023 14:44:24 +0530
Subject: [PATCH 0755/1806] net: ti: icssg-prueth: Add ICSSG ethernet driver

This is the Ethernet driver for TI AM654 Silicon rev. 2
with the ICSSG PRU Sub-system running dual-EMAC firmware.

The Programmable Real-time Unit and Industrial Communication Subsystem
Gigabit (PRU_ICSSG) is a low-latency microcontroller subsystem in the TI
SoCs. This subsystem is provided for the use cases like implementation of
custom peripheral interfaces, offloading of tasks from the other
processor cores of the SoC, etc.

Every ICSSG core has two Programmable Real-Time Unit(PRUs),
two auxiliary Real-Time Transfer Unit (RT_PRUs), and
two Transmit Real-Time Transfer Units (TX_PRUs). Each one of these runs
its own firmware. Every ICSSG core has two MII ports connect to these
PRUs and also a MDIO port.

The cores can run different firmwares to support different protocols and
features like switch-dev, timestamping, etc.

It uses System DMA to transfer and receive packets and
shared memory register emulation between the firmware and
driver for control and configuration.

This patch adds support for basic EMAC functionality with 1Gbps
and 100Mbps link speed. 10M and half duplex mode are not supported
currently as they require IEP, the support for which will be added later.
Support for switch-dev, timestamp, etc. will be added later
by subsequent patch series.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/Kconfig              |   13 +
 drivers/net/ethernet/ti/Makefile             |    8 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 1809 ++++++++++++++++++
 drivers/net/ethernet/ti/icssg/icssg_prueth.h |   32 +
 4 files changed, 1862 insertions(+)
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_prueth.c

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index fce06663e1e11..63e510b6860fd 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -183,4 +183,17 @@ config CPMAC
 	help
 	  TI AR7 CPMAC Ethernet support
 
+config TI_ICSSG_PRUETH
+	tristate "TI Gigabit PRU Ethernet driver"
+	select PHYLIB
+	depends on PRU_REMOTEPROC
+	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
+	help
+	  Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem.
+	  This subsystem is available starting with the AM65 platform.
+
+	  This driver requires firmware binaries which will run on the PRUs
+	  to support the Ethernet operation. Currently, it supports Ethernet
+	  with 1G and 100M link speed.
+
 endif # NET_VENDOR_TI
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 75f761efbea71..efb050cbb4a8f 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -28,3 +28,11 @@ obj-$(CONFIG_TI_K3_AM65_CPSW_NUSS) += ti-am65-cpsw-nuss.o
 ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o k3-cppi-desc-pool.o am65-cpsw-qos.o
 ti-am65-cpsw-nuss-$(CONFIG_TI_K3_AM65_CPSW_SWITCHDEV) += am65-cpsw-switchdev.o
 obj-$(CONFIG_TI_K3_AM65_CPTS) += am65-cpts.o
+
+obj-$(CONFIG_TI_ICSSG_PRUETH) += icssg-prueth.o
+icssg-prueth-y := k3-cppi-desc-pool.o \
+		  icssg/icssg_prueth.o \
+		  icssg/icssg_classifier.o \
+		  icssg/icssg_queues.o \
+		  icssg/icssg_config.o \
+		  icssg/icssg_mii_cfg.o \
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
new file mode 100644
index 0000000000000..1869e38f898f1
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -0,0 +1,1809 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Texas Instruments ICSSG Ethernet Driver
+ *
+ * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma/ti-cppi5.h>
+#include <linux/etherdevice.h>
+#include <linux/genalloc.h>
+#include <linux/if_vlan.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/remoteproc/pruss.h>
+#include <linux/regmap.h>
+#include <linux/remoteproc.h>
+
+#include "icssg_prueth.h"
+#include "icssg_mii_rt.h"
+#include "../k3-cppi-desc-pool.h"
+
+#define PRUETH_MODULE_DESCRIPTION "PRUSS ICSSG Ethernet driver"
+
+/* Netif debug messages possible */
+#define PRUETH_EMAC_DEBUG       (NETIF_MSG_DRV | \
+				 NETIF_MSG_PROBE | \
+				 NETIF_MSG_LINK | \
+				 NETIF_MSG_TIMER | \
+				 NETIF_MSG_IFDOWN | \
+				 NETIF_MSG_IFUP | \
+				 NETIF_MSG_RX_ERR | \
+				 NETIF_MSG_TX_ERR | \
+				 NETIF_MSG_TX_QUEUED | \
+				 NETIF_MSG_INTR | \
+				 NETIF_MSG_TX_DONE | \
+				 NETIF_MSG_RX_STATUS | \
+				 NETIF_MSG_PKTDATA | \
+				 NETIF_MSG_HW | \
+				 NETIF_MSG_WOL)
+
+#define prueth_napi_to_emac(napi) container_of(napi, struct prueth_emac, napi_rx)
+
+/* CTRLMMR_ICSSG_RGMII_CTRL register bits */
+#define ICSSG_CTRL_RGMII_ID_MODE                BIT(24)
+
+static void prueth_cleanup_rx_chns(struct prueth_emac *emac,
+				   struct prueth_rx_chn *rx_chn,
+				   int max_rflows)
+{
+	if (rx_chn->desc_pool)
+		k3_cppi_desc_pool_destroy(rx_chn->desc_pool);
+
+	if (rx_chn->rx_chn)
+		k3_udma_glue_release_rx_chn(rx_chn->rx_chn);
+}
+
+static void prueth_cleanup_tx_chns(struct prueth_emac *emac)
+{
+	int i;
+
+	for (i = 0; i < emac->tx_ch_num; i++) {
+		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
+
+		if (tx_chn->desc_pool)
+			k3_cppi_desc_pool_destroy(tx_chn->desc_pool);
+
+		if (tx_chn->tx_chn)
+			k3_udma_glue_release_tx_chn(tx_chn->tx_chn);
+
+		/* Assume prueth_cleanup_tx_chns() is called at the
+		 * end after all channel resources are freed
+		 */
+		memset(tx_chn, 0, sizeof(*tx_chn));
+	}
+}
+
+static void prueth_ndev_del_tx_napi(struct prueth_emac *emac, int num)
+{
+	int i;
+
+	for (i = 0; i < num; i++) {
+		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
+
+		if (tx_chn->irq)
+			free_irq(tx_chn->irq, tx_chn);
+		netif_napi_del(&tx_chn->napi_tx);
+	}
+}
+
+static void prueth_xmit_free(struct prueth_tx_chn *tx_chn,
+			     struct cppi5_host_desc_t *desc)
+{
+	struct cppi5_host_desc_t *first_desc, *next_desc;
+	dma_addr_t buf_dma, next_desc_dma;
+	u32 buf_dma_len;
+
+	first_desc = desc;
+	next_desc = first_desc;
+
+	cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len);
+	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
+
+	dma_unmap_single(tx_chn->dma_dev, buf_dma, buf_dma_len,
+			 DMA_TO_DEVICE);
+
+	next_desc_dma = cppi5_hdesc_get_next_hbdesc(first_desc);
+	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
+	while (next_desc_dma) {
+		next_desc = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
+						       next_desc_dma);
+		cppi5_hdesc_get_obuf(next_desc, &buf_dma, &buf_dma_len);
+		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
+
+		dma_unmap_page(tx_chn->dma_dev, buf_dma, buf_dma_len,
+			       DMA_TO_DEVICE);
+
+		next_desc_dma = cppi5_hdesc_get_next_hbdesc(next_desc);
+		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
+
+		k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
+	}
+
+	k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc);
+}
+
+static int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
+				    int budget)
+{
+	struct net_device *ndev = emac->ndev;
+	struct cppi5_host_desc_t *desc_tx;
+	struct netdev_queue *netif_txq;
+	struct prueth_tx_chn *tx_chn;
+	unsigned int total_bytes = 0;
+	struct sk_buff *skb;
+	dma_addr_t desc_dma;
+	int res, num_tx = 0;
+	void **swdata;
+
+	tx_chn = &emac->tx_chns[chn];
+
+	while (true) {
+		res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
+		if (res == -ENODATA)
+			break;
+
+		/* teardown completion */
+		if (cppi5_desc_is_tdcm(desc_dma)) {
+			if (atomic_dec_and_test(&emac->tdown_cnt))
+				complete(&emac->tdown_complete);
+			break;
+		}
+
+		desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
+						     desc_dma);
+		swdata = cppi5_hdesc_get_swdata(desc_tx);
+
+		skb = *(swdata);
+		prueth_xmit_free(tx_chn, desc_tx);
+
+		ndev = skb->dev;
+		ndev->stats.tx_packets++;
+		ndev->stats.tx_bytes += skb->len;
+		total_bytes += skb->len;
+		napi_consume_skb(skb, budget);
+		num_tx++;
+	}
+
+	if (!num_tx)
+		return 0;
+
+	netif_txq = netdev_get_tx_queue(ndev, chn);
+	netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
+
+	if (netif_tx_queue_stopped(netif_txq)) {
+		/* If the TX queue was stopped, wake it now
+		 * if we have enough room.
+		 */
+		__netif_tx_lock(netif_txq, smp_processor_id());
+		if (netif_running(ndev) &&
+		    (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >=
+		     MAX_SKB_FRAGS))
+			netif_tx_wake_queue(netif_txq);
+		__netif_tx_unlock(netif_txq);
+	}
+
+	return num_tx;
+}
+
+static int emac_napi_tx_poll(struct napi_struct *napi_tx, int budget)
+{
+	struct prueth_tx_chn *tx_chn = prueth_napi_to_tx_chn(napi_tx);
+	struct prueth_emac *emac = tx_chn->emac;
+	int num_tx_packets;
+
+	num_tx_packets = emac_tx_complete_packets(emac, tx_chn->id, budget);
+
+	if (num_tx_packets >= budget)
+		return budget;
+
+	if (napi_complete_done(napi_tx, num_tx_packets))
+		enable_irq(tx_chn->irq);
+
+	return num_tx_packets;
+}
+
+static irqreturn_t prueth_tx_irq(int irq, void *dev_id)
+{
+	struct prueth_tx_chn *tx_chn = dev_id;
+
+	disable_irq_nosync(irq);
+	napi_schedule(&tx_chn->napi_tx);
+
+	return IRQ_HANDLED;
+}
+
+static int prueth_ndev_add_tx_napi(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	int i, ret;
+
+	for (i = 0; i < emac->tx_ch_num; i++) {
+		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
+
+		netif_napi_add_tx(emac->ndev, &tx_chn->napi_tx, emac_napi_tx_poll);
+		ret = request_irq(tx_chn->irq, prueth_tx_irq,
+				  IRQF_TRIGGER_HIGH, tx_chn->name,
+				  tx_chn);
+		if (ret) {
+			netif_napi_del(&tx_chn->napi_tx);
+			dev_err(prueth->dev, "unable to request TX IRQ %d\n",
+				tx_chn->irq);
+			goto fail;
+		}
+	}
+
+	return 0;
+fail:
+	prueth_ndev_del_tx_napi(emac, i);
+	return ret;
+}
+
+static int prueth_init_tx_chns(struct prueth_emac *emac)
+{
+	static const struct k3_ring_cfg ring_cfg = {
+		.elm_size = K3_RINGACC_RING_ELSIZE_8,
+		.mode = K3_RINGACC_RING_MODE_RING,
+		.flags = 0,
+		.size = PRUETH_MAX_TX_DESC,
+	};
+	struct k3_udma_glue_tx_channel_cfg tx_cfg;
+	struct device *dev = emac->prueth->dev;
+	struct net_device *ndev = emac->ndev;
+	int ret, slice, i;
+	u32 hdesc_size;
+
+	slice = prueth_emac_slice(emac);
+	if (slice < 0)
+		return slice;
+
+	init_completion(&emac->tdown_complete);
+
+	hdesc_size = cppi5_hdesc_calc_size(true, PRUETH_NAV_PS_DATA_SIZE,
+					   PRUETH_NAV_SW_DATA_SIZE);
+	memset(&tx_cfg, 0, sizeof(tx_cfg));
+	tx_cfg.swdata_size = PRUETH_NAV_SW_DATA_SIZE;
+	tx_cfg.tx_cfg = ring_cfg;
+	tx_cfg.txcq_cfg = ring_cfg;
+
+	for (i = 0; i < emac->tx_ch_num; i++) {
+		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
+
+		/* To differentiate channels for SLICE0 vs SLICE1 */
+		snprintf(tx_chn->name, sizeof(tx_chn->name),
+			 "tx%d-%d", slice, i);
+
+		tx_chn->emac = emac;
+		tx_chn->id = i;
+		tx_chn->descs_num = PRUETH_MAX_TX_DESC;
+
+		tx_chn->tx_chn =
+			k3_udma_glue_request_tx_chn(dev, tx_chn->name,
+						    &tx_cfg);
+		if (IS_ERR(tx_chn->tx_chn)) {
+			ret = PTR_ERR(tx_chn->tx_chn);
+			tx_chn->tx_chn = NULL;
+			netdev_err(ndev,
+				   "Failed to request tx dma ch: %d\n", ret);
+			goto fail;
+		}
+
+		tx_chn->dma_dev = k3_udma_glue_tx_get_dma_device(tx_chn->tx_chn);
+		tx_chn->desc_pool =
+			k3_cppi_desc_pool_create_name(tx_chn->dma_dev,
+						      tx_chn->descs_num,
+						      hdesc_size,
+						      tx_chn->name);
+		if (IS_ERR(tx_chn->desc_pool)) {
+			ret = PTR_ERR(tx_chn->desc_pool);
+			tx_chn->desc_pool = NULL;
+			netdev_err(ndev, "Failed to create tx pool: %d\n", ret);
+			goto fail;
+		}
+
+		tx_chn->irq = k3_udma_glue_tx_get_irq(tx_chn->tx_chn);
+		if (tx_chn->irq <= 0) {
+			ret = -EINVAL;
+			netdev_err(ndev, "failed to get tx irq\n");
+			goto fail;
+		}
+
+		snprintf(tx_chn->name, sizeof(tx_chn->name), "%s-tx%d",
+			 dev_name(dev), tx_chn->id);
+	}
+
+	return 0;
+
+fail:
+	prueth_cleanup_tx_chns(emac);
+	return ret;
+}
+
+static int prueth_init_rx_chns(struct prueth_emac *emac,
+			       struct prueth_rx_chn *rx_chn,
+			       char *name, u32 max_rflows,
+			       u32 max_desc_num)
+{
+	struct k3_udma_glue_rx_channel_cfg rx_cfg;
+	struct device *dev = emac->prueth->dev;
+	struct net_device *ndev = emac->ndev;
+	u32 fdqring_id, hdesc_size;
+	int i, ret = 0, slice;
+
+	slice = prueth_emac_slice(emac);
+	if (slice < 0)
+		return slice;
+
+	/* To differentiate channels for SLICE0 vs SLICE1 */
+	snprintf(rx_chn->name, sizeof(rx_chn->name), "%s%d", name, slice);
+
+	hdesc_size = cppi5_hdesc_calc_size(true, PRUETH_NAV_PS_DATA_SIZE,
+					   PRUETH_NAV_SW_DATA_SIZE);
+	memset(&rx_cfg, 0, sizeof(rx_cfg));
+	rx_cfg.swdata_size = PRUETH_NAV_SW_DATA_SIZE;
+	rx_cfg.flow_id_num = max_rflows;
+	rx_cfg.flow_id_base = -1; /* udmax will auto select flow id base */
+
+	/* init all flows */
+	rx_chn->dev = dev;
+	rx_chn->descs_num = max_desc_num;
+
+	rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, rx_chn->name,
+						     &rx_cfg);
+	if (IS_ERR(rx_chn->rx_chn)) {
+		ret = PTR_ERR(rx_chn->rx_chn);
+		rx_chn->rx_chn = NULL;
+		netdev_err(ndev, "Failed to request rx dma ch: %d\n", ret);
+		goto fail;
+	}
+
+	rx_chn->dma_dev = k3_udma_glue_rx_get_dma_device(rx_chn->rx_chn);
+	rx_chn->desc_pool = k3_cppi_desc_pool_create_name(rx_chn->dma_dev,
+							  rx_chn->descs_num,
+							  hdesc_size,
+							  rx_chn->name);
+	if (IS_ERR(rx_chn->desc_pool)) {
+		ret = PTR_ERR(rx_chn->desc_pool);
+		rx_chn->desc_pool = NULL;
+		netdev_err(ndev, "Failed to create rx pool: %d\n", ret);
+		goto fail;
+	}
+
+	emac->rx_flow_id_base = k3_udma_glue_rx_get_flow_id_base(rx_chn->rx_chn);
+	netdev_dbg(ndev, "flow id base = %d\n", emac->rx_flow_id_base);
+
+	fdqring_id = K3_RINGACC_RING_ID_ANY;
+	for (i = 0; i < rx_cfg.flow_id_num; i++) {
+		struct k3_ring_cfg rxring_cfg = {
+			.elm_size = K3_RINGACC_RING_ELSIZE_8,
+			.mode = K3_RINGACC_RING_MODE_RING,
+			.flags = 0,
+		};
+		struct k3_ring_cfg fdqring_cfg = {
+			.elm_size = K3_RINGACC_RING_ELSIZE_8,
+			.flags = K3_RINGACC_RING_SHARED,
+		};
+		struct k3_udma_glue_rx_flow_cfg rx_flow_cfg = {
+			.rx_cfg = rxring_cfg,
+			.rxfdq_cfg = fdqring_cfg,
+			.ring_rxq_id = K3_RINGACC_RING_ID_ANY,
+			.src_tag_lo_sel =
+				K3_UDMA_GLUE_SRC_TAG_LO_USE_REMOTE_SRC_TAG,
+		};
+
+		rx_flow_cfg.ring_rxfdq0_id = fdqring_id;
+		rx_flow_cfg.rx_cfg.size = max_desc_num;
+		rx_flow_cfg.rxfdq_cfg.size = max_desc_num;
+		rx_flow_cfg.rxfdq_cfg.mode = emac->prueth->pdata.fdqring_mode;
+
+		ret = k3_udma_glue_rx_flow_init(rx_chn->rx_chn,
+						i, &rx_flow_cfg);
+		if (ret) {
+			netdev_err(ndev, "Failed to init rx flow%d %d\n",
+				   i, ret);
+			goto fail;
+		}
+		if (!i)
+			fdqring_id = k3_udma_glue_rx_flow_get_fdq_id(rx_chn->rx_chn,
+								     i);
+		rx_chn->irq[i] = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i);
+		if (rx_chn->irq[i] <= 0) {
+			ret = rx_chn->irq[i];
+			netdev_err(ndev, "Failed to get rx dma irq");
+			goto fail;
+		}
+	}
+
+	return 0;
+
+fail:
+	prueth_cleanup_rx_chns(emac, rx_chn, max_rflows);
+	return ret;
+}
+
+static int prueth_dma_rx_push(struct prueth_emac *emac,
+			      struct sk_buff *skb,
+			      struct prueth_rx_chn *rx_chn)
+{
+	struct net_device *ndev = emac->ndev;
+	struct cppi5_host_desc_t *desc_rx;
+	u32 pkt_len = skb_tailroom(skb);
+	dma_addr_t desc_dma;
+	dma_addr_t buf_dma;
+	void **swdata;
+
+	desc_rx = k3_cppi_desc_pool_alloc(rx_chn->desc_pool);
+	if (!desc_rx) {
+		netdev_err(ndev, "rx push: failed to allocate descriptor\n");
+		return -ENOMEM;
+	}
+	desc_dma = k3_cppi_desc_pool_virt2dma(rx_chn->desc_pool, desc_rx);
+
+	buf_dma = dma_map_single(rx_chn->dma_dev, skb->data, pkt_len, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(rx_chn->dma_dev, buf_dma))) {
+		k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
+		netdev_err(ndev, "rx push: failed to map rx pkt buffer\n");
+		return -EINVAL;
+	}
+
+	cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT,
+			 PRUETH_NAV_PS_DATA_SIZE);
+	k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma);
+	cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb));
+
+	swdata = cppi5_hdesc_get_swdata(desc_rx);
+	*swdata = skb;
+
+	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, 0,
+					desc_rx, desc_dma);
+}
+
+static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
+{
+	struct prueth_rx_chn *rx_chn = &emac->rx_chns;
+	u32 buf_dma_len, pkt_len, port_id = 0;
+	struct net_device *ndev = emac->ndev;
+	struct cppi5_host_desc_t *desc_rx;
+	struct sk_buff *skb, *new_skb;
+	dma_addr_t desc_dma, buf_dma;
+	void **swdata;
+	int ret;
+
+	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma);
+	if (ret) {
+		if (ret != -ENODATA)
+			netdev_err(ndev, "rx pop: failed: %d\n", ret);
+		return ret;
+	}
+
+	if (cppi5_desc_is_tdcm(desc_dma)) /* Teardown ? */
+		return 0;
+
+	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
+
+	swdata = cppi5_hdesc_get_swdata(desc_rx);
+	skb = *swdata;
+
+	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
+	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
+	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
+	/* firmware adds 4 CRC bytes, strip them */
+	pkt_len -= 4;
+	cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL);
+
+	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
+	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
+
+	skb->dev = ndev;
+	new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE);
+	/* if allocation fails we drop the packet but push the
+	 * descriptor back to the ring with old skb to prevent a stall
+	 */
+	if (!new_skb) {
+		ndev->stats.rx_dropped++;
+		new_skb = skb;
+	} else {
+		/* send the filled skb up the n/w stack */
+		skb_put(skb, pkt_len);
+		skb->protocol = eth_type_trans(skb, ndev);
+		napi_gro_receive(&emac->napi_rx, skb);
+		ndev->stats.rx_bytes += pkt_len;
+		ndev->stats.rx_packets++;
+	}
+
+	/* queue another RX DMA */
+	ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_chns);
+	if (WARN_ON(ret < 0)) {
+		dev_kfree_skb_any(new_skb);
+		ndev->stats.rx_errors++;
+		ndev->stats.rx_dropped++;
+	}
+
+	return ret;
+}
+
+static void prueth_rx_cleanup(void *data, dma_addr_t desc_dma)
+{
+	struct prueth_rx_chn *rx_chn = data;
+	struct cppi5_host_desc_t *desc_rx;
+	struct sk_buff *skb;
+	dma_addr_t buf_dma;
+	u32 buf_dma_len;
+	void **swdata;
+
+	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
+	swdata = cppi5_hdesc_get_swdata(desc_rx);
+	skb = *swdata;
+	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
+	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
+
+	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len,
+			 DMA_FROM_DEVICE);
+	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
+
+	dev_kfree_skb_any(skb);
+}
+
+/**
+ * emac_ndo_start_xmit - EMAC Transmit function
+ * @skb: SKB pointer
+ * @ndev: EMAC network adapter
+ *
+ * Called by the system to transmit a packet  - we queue the packet in
+ * EMAC hardware transmit queue
+ * Doesn't wait for completion we'll check for TX completion in
+ * emac_tx_complete_packets().
+ *
+ * Return: enum netdev_tx
+ */
+static enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct cppi5_host_desc_t *first_desc, *next_desc, *cur_desc;
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct netdev_queue *netif_txq;
+	struct prueth_tx_chn *tx_chn;
+	dma_addr_t desc_dma, buf_dma;
+	int i, ret = 0, q_idx;
+	void **swdata;
+	u32 pkt_len;
+	u32 *epib;
+
+	pkt_len = skb_headlen(skb);
+	q_idx = skb_get_queue_mapping(skb);
+
+	tx_chn = &emac->tx_chns[q_idx];
+	netif_txq = netdev_get_tx_queue(ndev, q_idx);
+
+	/* Map the linear buffer */
+	buf_dma = dma_map_single(tx_chn->dma_dev, skb->data, pkt_len, DMA_TO_DEVICE);
+	if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) {
+		netdev_err(ndev, "tx: failed to map skb buffer\n");
+		ret = NETDEV_TX_OK;
+		goto drop_free_skb;
+	}
+
+	first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
+	if (!first_desc) {
+		netdev_dbg(ndev, "tx: failed to allocate descriptor\n");
+		dma_unmap_single(tx_chn->dma_dev, buf_dma, pkt_len, DMA_TO_DEVICE);
+		goto drop_stop_q_busy;
+	}
+
+	cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT,
+			 PRUETH_NAV_PS_DATA_SIZE);
+	cppi5_hdesc_set_pkttype(first_desc, 0);
+	epib = first_desc->epib;
+	epib[0] = 0;
+	epib[1] = 0;
+
+	/* set dst tag to indicate internal qid at the firmware which is at
+	 * bit8..bit15. bit0..bit7 indicates port num for directed
+	 * packets in case of switch mode operation
+	 */
+	cppi5_desc_set_tags_ids(&first_desc->hdr, 0, (emac->port_id | (q_idx << 8)));
+	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
+	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
+	swdata = cppi5_hdesc_get_swdata(first_desc);
+	*swdata = skb;
+
+	/* Handle the case where skb is fragmented in pages */
+	cur_desc = first_desc;
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+		u32 frag_size = skb_frag_size(frag);
+
+		next_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
+		if (!next_desc) {
+			netdev_err(ndev,
+				   "tx: failed to allocate frag. descriptor\n");
+			goto free_desc_stop_q_busy;
+		}
+
+		buf_dma = skb_frag_dma_map(tx_chn->dma_dev, frag, 0, frag_size,
+					   DMA_TO_DEVICE);
+		if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) {
+			netdev_err(ndev, "tx: Failed to map skb page\n");
+			k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
+			ret = NETDEV_TX_OK;
+			goto drop_free_descs;
+		}
+
+		cppi5_hdesc_reset_hbdesc(next_desc);
+		k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
+		cppi5_hdesc_attach_buf(next_desc,
+				       buf_dma, frag_size, buf_dma, frag_size);
+
+		desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool,
+						      next_desc);
+		k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &desc_dma);
+		cppi5_hdesc_link_hbdesc(cur_desc, desc_dma);
+
+		pkt_len += frag_size;
+		cur_desc = next_desc;
+	}
+	WARN_ON_ONCE(pkt_len != skb->len);
+
+	/* report bql before sending packet */
+	netdev_tx_sent_queue(netif_txq, pkt_len);
+
+	cppi5_hdesc_set_pktlen(first_desc, pkt_len);
+	desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
+	/* cppi5_desc_dump(first_desc, 64); */
+
+	skb_tx_timestamp(skb);  /* SW timestamp if SKBTX_IN_PROGRESS not set */
+	ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+	if (ret) {
+		netdev_err(ndev, "tx: push failed: %d\n", ret);
+		goto drop_free_descs;
+	}
+
+	if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) < MAX_SKB_FRAGS) {
+		netif_tx_stop_queue(netif_txq);
+		/* Barrier, so that stop_queue visible to other cpus */
+		smp_mb__after_atomic();
+
+		if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >=
+		    MAX_SKB_FRAGS)
+			netif_tx_wake_queue(netif_txq);
+	}
+
+	return NETDEV_TX_OK;
+
+drop_free_descs:
+	prueth_xmit_free(tx_chn, first_desc);
+
+drop_free_skb:
+	dev_kfree_skb_any(skb);
+
+	/* error */
+	ndev->stats.tx_dropped++;
+	netdev_err(ndev, "tx: error: %d\n", ret);
+
+	return ret;
+
+free_desc_stop_q_busy:
+	prueth_xmit_free(tx_chn, first_desc);
+
+drop_stop_q_busy:
+	netif_tx_stop_queue(netif_txq);
+	return NETDEV_TX_BUSY;
+}
+
+static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma)
+{
+	struct prueth_tx_chn *tx_chn = data;
+	struct cppi5_host_desc_t *desc_tx;
+	struct sk_buff *skb;
+	void **swdata;
+
+	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
+	swdata = cppi5_hdesc_get_swdata(desc_tx);
+	skb = *(swdata);
+	prueth_xmit_free(tx_chn, desc_tx);
+
+	dev_kfree_skb_any(skb);
+}
+
+static irqreturn_t prueth_rx_irq(int irq, void *dev_id)
+{
+	struct prueth_emac *emac = dev_id;
+
+	disable_irq_nosync(irq);
+	napi_schedule(&emac->napi_rx);
+
+	return IRQ_HANDLED;
+}
+
+struct icssg_firmwares {
+	char *pru;
+	char *rtu;
+	char *txpru;
+};
+
+static struct icssg_firmwares icssg_emac_firmwares[] = {
+	{
+		.pru = "ti-pruss/am65x-sr2-pru0-prueth-fw.elf",
+		.rtu = "ti-pruss/am65x-sr2-rtu0-prueth-fw.elf",
+		.txpru = "ti-pruss/am65x-sr2-txpru0-prueth-fw.elf",
+	},
+	{
+		.pru = "ti-pruss/am65x-sr2-pru1-prueth-fw.elf",
+		.rtu = "ti-pruss/am65x-sr2-rtu1-prueth-fw.elf",
+		.txpru = "ti-pruss/am65x-sr2-txpru1-prueth-fw.elf",
+	}
+};
+
+static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac)
+{
+	struct icssg_firmwares *firmwares;
+	struct device *dev = prueth->dev;
+	int slice, ret;
+
+	firmwares = icssg_emac_firmwares;
+
+	slice = prueth_emac_slice(emac);
+	if (slice < 0) {
+		netdev_err(emac->ndev, "invalid port\n");
+		return -EINVAL;
+	}
+
+	ret = icssg_config(prueth, emac, slice);
+	if (ret)
+		return ret;
+
+	ret = rproc_set_firmware(prueth->pru[slice], firmwares[slice].pru);
+	ret = rproc_boot(prueth->pru[slice]);
+	if (ret) {
+		dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret);
+		return -EINVAL;
+	}
+
+	ret = rproc_set_firmware(prueth->rtu[slice], firmwares[slice].rtu);
+	ret = rproc_boot(prueth->rtu[slice]);
+	if (ret) {
+		dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret);
+		goto halt_pru;
+	}
+
+	ret = rproc_set_firmware(prueth->txpru[slice], firmwares[slice].txpru);
+	ret = rproc_boot(prueth->txpru[slice]);
+	if (ret) {
+		dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret);
+		goto halt_rtu;
+	}
+
+	emac->fw_running = 1;
+	return 0;
+
+halt_rtu:
+	rproc_shutdown(prueth->rtu[slice]);
+
+halt_pru:
+	rproc_shutdown(prueth->pru[slice]);
+
+	return ret;
+}
+
+static void prueth_emac_stop(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	int slice;
+
+	switch (emac->port_id) {
+	case PRUETH_PORT_MII0:
+		slice = ICSS_SLICE0;
+		break;
+	case PRUETH_PORT_MII1:
+		slice = ICSS_SLICE1;
+		break;
+	default:
+		netdev_err(emac->ndev, "invalid port\n");
+		return;
+	}
+
+	emac->fw_running = 0;
+	rproc_shutdown(prueth->txpru[slice]);
+	rproc_shutdown(prueth->rtu[slice]);
+	rproc_shutdown(prueth->pru[slice]);
+}
+
+/* called back by PHY layer if there is change in link state of hw port*/
+static void emac_adjust_link(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct phy_device *phydev = ndev->phydev;
+	struct prueth *prueth = emac->prueth;
+	bool new_state = false;
+	unsigned long flags;
+
+	if (phydev->link) {
+		/* check the mode of operation - full/half duplex */
+		if (phydev->duplex != emac->duplex) {
+			new_state = true;
+			emac->duplex = phydev->duplex;
+		}
+		if (phydev->speed != emac->speed) {
+			new_state = true;
+			emac->speed = phydev->speed;
+		}
+		if (!emac->link) {
+			new_state = true;
+			emac->link = 1;
+		}
+	} else if (emac->link) {
+		new_state = true;
+		emac->link = 0;
+
+		/* f/w should support 100 & 1000 */
+		emac->speed = SPEED_1000;
+
+		/* half duplex may not be supported by f/w */
+		emac->duplex = DUPLEX_FULL;
+	}
+
+	if (new_state) {
+		phy_print_status(phydev);
+
+		/* update RGMII and MII configuration based on PHY negotiated
+		 * values
+		 */
+		if (emac->link) {
+			/* Set the RGMII cfg for gig en and full duplex */
+			icssg_update_rgmii_cfg(prueth->miig_rt, emac);
+
+			/* update the Tx IPG based on 100M/1G speed */
+			spin_lock_irqsave(&emac->lock, flags);
+			icssg_config_ipg(emac);
+			spin_unlock_irqrestore(&emac->lock, flags);
+			icssg_config_set_speed(emac);
+			emac_set_port_state(emac, ICSSG_EMAC_PORT_FORWARD);
+
+		} else {
+			emac_set_port_state(emac, ICSSG_EMAC_PORT_DISABLE);
+		}
+	}
+
+	if (emac->link) {
+		/* reactivate the transmit queue */
+		netif_tx_wake_all_queues(ndev);
+	} else {
+		netif_tx_stop_all_queues(ndev);
+	}
+}
+
+static int emac_napi_rx_poll(struct napi_struct *napi_rx, int budget)
+{
+	struct prueth_emac *emac = prueth_napi_to_emac(napi_rx);
+	int rx_flow = PRUETH_RX_FLOW_DATA;
+	int flow = PRUETH_MAX_RX_FLOWS;
+	int num_rx = 0;
+	int cur_budget;
+	int ret;
+
+	while (flow--) {
+		cur_budget = budget - num_rx;
+
+		while (cur_budget--) {
+			ret = emac_rx_packet(emac, flow);
+			if (ret)
+				break;
+			num_rx++;
+		}
+
+		if (num_rx >= budget)
+			break;
+	}
+
+	if (num_rx < budget && napi_complete_done(napi_rx, num_rx))
+		enable_irq(emac->rx_chns.irq[rx_flow]);
+
+	return num_rx;
+}
+
+static int prueth_prepare_rx_chan(struct prueth_emac *emac,
+				  struct prueth_rx_chn *chn,
+				  int buf_size)
+{
+	struct sk_buff *skb;
+	int i, ret;
+
+	for (i = 0; i < chn->descs_num; i++) {
+		skb = __netdev_alloc_skb_ip_align(NULL, buf_size, GFP_KERNEL);
+		if (!skb)
+			return -ENOMEM;
+
+		ret = prueth_dma_rx_push(emac, skb, chn);
+		if (ret < 0) {
+			netdev_err(emac->ndev,
+				   "cannot submit skb for rx chan %s ret %d\n",
+				   chn->name, ret);
+			kfree_skb(skb);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void prueth_reset_tx_chan(struct prueth_emac *emac, int ch_num,
+				 bool free_skb)
+{
+	int i;
+
+	for (i = 0; i < ch_num; i++) {
+		if (free_skb)
+			k3_udma_glue_reset_tx_chn(emac->tx_chns[i].tx_chn,
+						  &emac->tx_chns[i],
+						  prueth_tx_cleanup);
+		k3_udma_glue_disable_tx_chn(emac->tx_chns[i].tx_chn);
+	}
+}
+
+static void prueth_reset_rx_chan(struct prueth_rx_chn *chn,
+				 int num_flows, bool disable)
+{
+	int i;
+
+	for (i = 0; i < num_flows; i++)
+		k3_udma_glue_reset_rx_chn(chn->rx_chn, i, chn,
+					  prueth_rx_cleanup, !!i);
+	if (disable)
+		k3_udma_glue_disable_rx_chn(chn->rx_chn);
+}
+
+static int emac_phy_connect(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	struct net_device *ndev = emac->ndev;
+	/* connect PHY */
+	ndev->phydev = of_phy_connect(emac->ndev, emac->phy_node,
+				      &emac_adjust_link, 0,
+				      emac->phy_if);
+	if (!ndev->phydev) {
+		dev_err(prueth->dev, "couldn't connect to phy %s\n",
+			emac->phy_node->full_name);
+		return -ENODEV;
+	}
+
+	/* remove unsupported modes */
+	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT);
+	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT);
+	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
+	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_Pause_BIT);
+	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_Asym_Pause_BIT);
+
+	if (emac->phy_if == PHY_INTERFACE_MODE_MII)
+		phy_set_max_speed(ndev->phydev, SPEED_100);
+
+	return 0;
+}
+
+/**
+ * emac_ndo_open - EMAC device open
+ * @ndev: network adapter device
+ *
+ * Called when system wants to start the interface.
+ *
+ * Return: 0 for a successful open, or appropriate error code
+ */
+static int emac_ndo_open(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int ret, i, num_data_chn = emac->tx_ch_num;
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+	struct device *dev = prueth->dev;
+	int max_rx_flows;
+	int rx_flow;
+
+	/* clear SMEM and MSMC settings for all slices */
+	if (!prueth->emacs_initialized) {
+		memset_io(prueth->msmcram.va, 0, prueth->msmcram.size);
+		memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS);
+	}
+
+	/* set h/w MAC as user might have re-configured */
+	ether_addr_copy(emac->mac_addr, ndev->dev_addr);
+
+	icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
+	icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
+
+	icssg_class_default(prueth->miig_rt, slice, 0);
+
+	/* Notify the stack of the actual queue counts. */
+	ret = netif_set_real_num_tx_queues(ndev, num_data_chn);
+	if (ret) {
+		dev_err(dev, "cannot set real number of tx queues\n");
+		return ret;
+	}
+
+	init_completion(&emac->cmd_complete);
+	ret = prueth_init_tx_chns(emac);
+	if (ret) {
+		dev_err(dev, "failed to init tx channel: %d\n", ret);
+		return ret;
+	}
+
+	max_rx_flows = PRUETH_MAX_RX_FLOWS;
+	ret = prueth_init_rx_chns(emac, &emac->rx_chns, "rx",
+				  max_rx_flows, PRUETH_MAX_RX_DESC);
+	if (ret) {
+		dev_err(dev, "failed to init rx channel: %d\n", ret);
+		goto cleanup_tx;
+	}
+
+	ret = prueth_ndev_add_tx_napi(emac);
+	if (ret)
+		goto cleanup_rx;
+
+	/* we use only the highest priority flow for now i.e. @irq[3] */
+	rx_flow = PRUETH_RX_FLOW_DATA;
+	ret = request_irq(emac->rx_chns.irq[rx_flow], prueth_rx_irq,
+			  IRQF_TRIGGER_HIGH, dev_name(dev), emac);
+	if (ret) {
+		dev_err(dev, "unable to request RX IRQ\n");
+		goto cleanup_napi;
+	}
+
+	/* reset and start PRU firmware */
+	ret = prueth_emac_start(prueth, emac);
+	if (ret)
+		goto free_rx_irq;
+
+	icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu);
+
+	/* Prepare RX */
+	ret = prueth_prepare_rx_chan(emac, &emac->rx_chns, PRUETH_MAX_PKT_SIZE);
+	if (ret)
+		goto stop;
+
+	ret = k3_udma_glue_enable_rx_chn(emac->rx_chns.rx_chn);
+	if (ret)
+		goto reset_rx_chn;
+
+	for (i = 0; i < emac->tx_ch_num; i++) {
+		ret = k3_udma_glue_enable_tx_chn(emac->tx_chns[i].tx_chn);
+		if (ret)
+			goto reset_tx_chan;
+	}
+
+	/* Enable NAPI in Tx and Rx direction */
+	for (i = 0; i < emac->tx_ch_num; i++)
+		napi_enable(&emac->tx_chns[i].napi_tx);
+	napi_enable(&emac->napi_rx);
+
+	/* start PHY */
+	phy_start(ndev->phydev);
+
+	prueth->emacs_initialized++;
+
+	return 0;
+
+reset_tx_chan:
+	/* Since interface is not yet up, there is wouldn't be
+	 * any SKB for completion. So set false to free_skb
+	 */
+	prueth_reset_tx_chan(emac, i, false);
+reset_rx_chn:
+	prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, false);
+stop:
+	prueth_emac_stop(emac);
+free_rx_irq:
+	free_irq(emac->rx_chns.irq[rx_flow], emac);
+cleanup_napi:
+	prueth_ndev_del_tx_napi(emac, emac->tx_ch_num);
+cleanup_rx:
+	prueth_cleanup_rx_chns(emac, &emac->rx_chns, max_rx_flows);
+cleanup_tx:
+	prueth_cleanup_tx_chns(emac);
+
+	return ret;
+}
+
+/**
+ * emac_ndo_stop - EMAC device stop
+ * @ndev: network adapter device
+ *
+ * Called when system wants to stop or down the interface.
+ *
+ * Return: Always 0 (Success)
+ */
+static int emac_ndo_stop(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+	int rx_flow = PRUETH_RX_FLOW_DATA;
+	int max_rx_flows;
+	int ret, i;
+
+	/* inform the upper layers. */
+	netif_tx_stop_all_queues(ndev);
+
+	/* block packets from wire */
+	if (ndev->phydev)
+		phy_stop(ndev->phydev);
+
+	icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac));
+
+	atomic_set(&emac->tdown_cnt, emac->tx_ch_num);
+	/* ensure new tdown_cnt value is visible */
+	smp_mb__after_atomic();
+	/* tear down and disable UDMA channels */
+	reinit_completion(&emac->tdown_complete);
+	for (i = 0; i < emac->tx_ch_num; i++)
+		k3_udma_glue_tdown_tx_chn(emac->tx_chns[i].tx_chn, false);
+
+	ret = wait_for_completion_timeout(&emac->tdown_complete,
+					  msecs_to_jiffies(1000));
+	if (!ret)
+		netdev_err(ndev, "tx teardown timeout\n");
+
+	prueth_reset_tx_chan(emac, emac->tx_ch_num, true);
+	for (i = 0; i < emac->tx_ch_num; i++)
+		napi_disable(&emac->tx_chns[i].napi_tx);
+
+	max_rx_flows = PRUETH_MAX_RX_FLOWS;
+	k3_udma_glue_tdown_rx_chn(emac->rx_chns.rx_chn, true);
+
+	prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, true);
+
+	napi_disable(&emac->napi_rx);
+
+	cancel_work_sync(&emac->rx_mode_work);
+
+	/* stop PRUs */
+	prueth_emac_stop(emac);
+
+	free_irq(emac->rx_chns.irq[rx_flow], emac);
+	prueth_ndev_del_tx_napi(emac, emac->tx_ch_num);
+	prueth_cleanup_tx_chns(emac);
+
+	prueth_cleanup_rx_chns(emac, &emac->rx_chns, max_rx_flows);
+	prueth_cleanup_tx_chns(emac);
+
+	prueth->emacs_initialized--;
+
+	return 0;
+}
+
+static void emac_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue)
+{
+	ndev->stats.tx_errors++;
+}
+
+static void emac_ndo_set_rx_mode_work(struct work_struct *work)
+{
+	struct prueth_emac *emac = container_of(work, struct prueth_emac, rx_mode_work);
+	struct net_device *ndev = emac->ndev;
+	bool promisc, allmulti;
+
+	if (!netif_running(ndev))
+		return;
+
+	promisc = ndev->flags & IFF_PROMISC;
+	allmulti = ndev->flags & IFF_ALLMULTI;
+	emac_set_port_state(emac, ICSSG_EMAC_PORT_UC_FLOODING_DISABLE);
+	emac_set_port_state(emac, ICSSG_EMAC_PORT_MC_FLOODING_DISABLE);
+
+	if (promisc) {
+		emac_set_port_state(emac, ICSSG_EMAC_PORT_UC_FLOODING_ENABLE);
+		emac_set_port_state(emac, ICSSG_EMAC_PORT_MC_FLOODING_ENABLE);
+		return;
+	}
+
+	if (allmulti) {
+		emac_set_port_state(emac, ICSSG_EMAC_PORT_MC_FLOODING_ENABLE);
+		return;
+	}
+
+	if (!netdev_mc_empty(ndev)) {
+		emac_set_port_state(emac, ICSSG_EMAC_PORT_MC_FLOODING_ENABLE);
+		return;
+	}
+}
+
+/**
+ * emac_ndo_set_rx_mode - EMAC set receive mode function
+ * @ndev: The EMAC network adapter
+ *
+ * Called when system wants to set the receive mode of the device.
+ *
+ */
+static void emac_ndo_set_rx_mode(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	queue_work(emac->cmd_wq, &emac->rx_mode_work);
+}
+
+static int emac_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
+{
+	return phy_do_ioctl(ndev, ifr, cmd);
+}
+
+static const struct net_device_ops emac_netdev_ops = {
+	.ndo_open = emac_ndo_open,
+	.ndo_stop = emac_ndo_stop,
+	.ndo_start_xmit = emac_ndo_start_xmit,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_validate_addr = eth_validate_addr,
+	.ndo_tx_timeout = emac_ndo_tx_timeout,
+	.ndo_set_rx_mode = emac_ndo_set_rx_mode,
+	.ndo_eth_ioctl = emac_ndo_ioctl,
+};
+
+/* get emac_port corresponding to eth_node name */
+static int prueth_node_port(struct device_node *eth_node)
+{
+	u32 port_id;
+	int ret;
+
+	ret = of_property_read_u32(eth_node, "reg", &port_id);
+	if (ret)
+		return ret;
+
+	if (port_id == 0)
+		return PRUETH_PORT_MII0;
+	else if (port_id == 1)
+		return PRUETH_PORT_MII1;
+	else
+		return PRUETH_PORT_INVALID;
+}
+
+/* get MAC instance corresponding to eth_node name */
+static int prueth_node_mac(struct device_node *eth_node)
+{
+	u32 port_id;
+	int ret;
+
+	ret = of_property_read_u32(eth_node, "reg", &port_id);
+	if (ret)
+		return ret;
+
+	if (port_id == 0)
+		return PRUETH_MAC0;
+	else if (port_id == 1)
+		return PRUETH_MAC1;
+	else
+		return PRUETH_MAC_INVALID;
+}
+
+static int prueth_netdev_init(struct prueth *prueth,
+			      struct device_node *eth_node)
+{
+	int ret, num_tx_chn = PRUETH_MAX_TX_QUEUES;
+	struct prueth_emac *emac;
+	struct net_device *ndev;
+	enum prueth_port port;
+	enum prueth_mac mac;
+
+	port = prueth_node_port(eth_node);
+	if (port == PRUETH_PORT_INVALID)
+		return -EINVAL;
+
+	mac = prueth_node_mac(eth_node);
+	if (mac == PRUETH_MAC_INVALID)
+		return -EINVAL;
+
+	ndev = alloc_etherdev_mq(sizeof(*emac), num_tx_chn);
+	if (!ndev)
+		return -ENOMEM;
+
+	emac = netdev_priv(ndev);
+	emac->prueth = prueth;
+	emac->ndev = ndev;
+	emac->port_id = port;
+	emac->cmd_wq = create_singlethread_workqueue("icssg_cmd_wq");
+	if (!emac->cmd_wq) {
+		ret = -ENOMEM;
+		goto free_ndev;
+	}
+	INIT_WORK(&emac->rx_mode_work, emac_ndo_set_rx_mode_work);
+
+	ret = pruss_request_mem_region(prueth->pruss,
+				       port == PRUETH_PORT_MII0 ?
+				       PRUSS_MEM_DRAM0 : PRUSS_MEM_DRAM1,
+				       &emac->dram);
+	if (ret) {
+		dev_err(prueth->dev, "unable to get DRAM: %d\n", ret);
+		ret = -ENOMEM;
+		goto free_wq;
+	}
+
+	emac->tx_ch_num = 1;
+
+	SET_NETDEV_DEV(ndev, prueth->dev);
+	spin_lock_init(&emac->lock);
+	mutex_init(&emac->cmd_lock);
+
+	emac->phy_node = of_parse_phandle(eth_node, "phy-handle", 0);
+	if (!emac->phy_node && !of_phy_is_fixed_link(eth_node)) {
+		dev_err(prueth->dev, "couldn't find phy-handle\n");
+		ret = -ENODEV;
+		goto free;
+	} else if (of_phy_is_fixed_link(eth_node)) {
+		ret = of_phy_register_fixed_link(eth_node);
+		if (ret) {
+			ret = dev_err_probe(prueth->dev, ret,
+					    "failed to register fixed-link phy\n");
+			goto free;
+		}
+
+		emac->phy_node = eth_node;
+	}
+
+	ret = of_get_phy_mode(eth_node, &emac->phy_if);
+	if (ret) {
+		dev_err(prueth->dev, "could not get phy-mode property\n");
+		goto free;
+	}
+
+	if (emac->phy_if != PHY_INTERFACE_MODE_MII &&
+	    !phy_interface_mode_is_rgmii(emac->phy_if)) {
+		dev_err(prueth->dev, "PHY mode unsupported %s\n", phy_modes(emac->phy_if));
+		ret = -EINVAL;
+		goto free;
+	}
+
+	/* AM65 SR2.0 has TX Internal delay always enabled by hardware
+	 * and it is not possible to disable TX Internal delay. The below
+	 * switch case block describes how we handle different phy modes
+	 * based on hardware restriction.
+	 */
+	switch (emac->phy_if) {
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		emac->phy_if = PHY_INTERFACE_MODE_RGMII_RXID;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		emac->phy_if = PHY_INTERFACE_MODE_RGMII;
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		dev_err(prueth->dev, "RGMII mode without TX delay is not supported");
+		ret = -EINVAL;
+		goto free;
+	default:
+		break;
+	}
+
+	/* get mac address from DT and set private and netdev addr */
+	ret = of_get_ethdev_address(eth_node, ndev);
+	if (!is_valid_ether_addr(ndev->dev_addr)) {
+		eth_hw_addr_random(ndev);
+		dev_warn(prueth->dev, "port %d: using random MAC addr: %pM\n",
+			 port, ndev->dev_addr);
+	}
+	ether_addr_copy(emac->mac_addr, ndev->dev_addr);
+
+	ndev->min_mtu = PRUETH_MIN_PKT_SIZE;
+	ndev->max_mtu = PRUETH_MAX_MTU;
+	ndev->netdev_ops = &emac_netdev_ops;
+	ndev->hw_features = NETIF_F_SG;
+	ndev->features = ndev->hw_features;
+
+	netif_napi_add(ndev, &emac->napi_rx, emac_napi_rx_poll);
+	prueth->emac[mac] = emac;
+
+	return 0;
+
+free:
+	pruss_release_mem_region(prueth->pruss, &emac->dram);
+free_wq:
+	destroy_workqueue(emac->cmd_wq);
+free_ndev:
+	emac->ndev = NULL;
+	prueth->emac[mac] = NULL;
+	free_netdev(ndev);
+
+	return ret;
+}
+
+static void prueth_netdev_exit(struct prueth *prueth,
+			       struct device_node *eth_node)
+{
+	struct prueth_emac *emac;
+	enum prueth_mac mac;
+
+	mac = prueth_node_mac(eth_node);
+	if (mac == PRUETH_MAC_INVALID)
+		return;
+
+	emac = prueth->emac[mac];
+	if (!emac)
+		return;
+
+	if (of_phy_is_fixed_link(emac->phy_node))
+		of_phy_deregister_fixed_link(emac->phy_node);
+
+	netif_napi_del(&emac->napi_rx);
+
+	pruss_release_mem_region(prueth->pruss, &emac->dram);
+	destroy_workqueue(emac->cmd_wq);
+	free_netdev(emac->ndev);
+	prueth->emac[mac] = NULL;
+}
+
+static int prueth_get_cores(struct prueth *prueth, int slice)
+{
+	struct device *dev = prueth->dev;
+	enum pruss_pru_id pruss_id;
+	struct device_node *np;
+	int idx = -1, ret;
+
+	np = dev->of_node;
+
+	switch (slice) {
+	case ICSS_SLICE0:
+		idx = 0;
+		break;
+	case ICSS_SLICE1:
+		idx = 3;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	prueth->pru[slice] = pru_rproc_get(np, idx, &pruss_id);
+	if (IS_ERR(prueth->pru[slice])) {
+		ret = PTR_ERR(prueth->pru[slice]);
+		prueth->pru[slice] = NULL;
+		return dev_err_probe(dev, ret, "unable to get PRU%d\n", slice);
+	}
+	prueth->pru_id[slice] = pruss_id;
+
+	idx++;
+	prueth->rtu[slice] = pru_rproc_get(np, idx, NULL);
+	if (IS_ERR(prueth->rtu[slice])) {
+		ret = PTR_ERR(prueth->rtu[slice]);
+		prueth->rtu[slice] = NULL;
+		return dev_err_probe(dev, ret, "unable to get RTU%d\n", slice);
+	}
+
+	idx++;
+	prueth->txpru[slice] = pru_rproc_get(np, idx, NULL);
+	if (IS_ERR(prueth->txpru[slice])) {
+		ret = PTR_ERR(prueth->txpru[slice]);
+		prueth->txpru[slice] = NULL;
+		return dev_err_probe(dev, ret, "unable to get TX_PRU%d\n", slice);
+	}
+
+	return 0;
+}
+
+static void prueth_put_cores(struct prueth *prueth, int slice)
+{
+	if (prueth->txpru[slice])
+		pru_rproc_put(prueth->txpru[slice]);
+
+	if (prueth->rtu[slice])
+		pru_rproc_put(prueth->rtu[slice]);
+
+	if (prueth->pru[slice])
+		pru_rproc_put(prueth->pru[slice]);
+}
+
+static const struct of_device_id prueth_dt_match[];
+
+static int prueth_probe(struct platform_device *pdev)
+{
+	struct device_node *eth_node, *eth_ports_node;
+	struct device_node  *eth0_node = NULL;
+	struct device_node  *eth1_node = NULL;
+	struct genpool_data_align gp_data = {
+		.align = SZ_64K,
+	};
+	const struct of_device_id *match;
+	struct device *dev = &pdev->dev;
+	struct device_node *np;
+	struct prueth *prueth;
+	struct pruss *pruss;
+	u32 msmc_ram_size;
+	int i, ret;
+
+	np = dev->of_node;
+
+	match = of_match_device(prueth_dt_match, dev);
+	if (!match)
+		return -ENODEV;
+
+	prueth = devm_kzalloc(dev, sizeof(*prueth), GFP_KERNEL);
+	if (!prueth)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, prueth);
+	prueth->pdev = pdev;
+	prueth->pdata = *(const struct prueth_pdata *)match->data;
+
+	prueth->dev = dev;
+	eth_ports_node = of_get_child_by_name(np, "ethernet-ports");
+	if (!eth_ports_node)
+		return -ENOENT;
+
+	for_each_child_of_node(eth_ports_node, eth_node) {
+		u32 reg;
+
+		if (strcmp(eth_node->name, "port"))
+			continue;
+		ret = of_property_read_u32(eth_node, "reg", &reg);
+		if (ret < 0) {
+			dev_err(dev, "%pOF error reading port_id %d\n",
+				eth_node, ret);
+		}
+
+		of_node_get(eth_node);
+
+		if (reg == 0) {
+			eth0_node = eth_node;
+			if (!of_device_is_available(eth0_node)) {
+				of_node_put(eth0_node);
+				eth0_node = NULL;
+			}
+		} else if (reg == 1) {
+			eth1_node = eth_node;
+			if (!of_device_is_available(eth1_node)) {
+				of_node_put(eth1_node);
+				eth1_node = NULL;
+			}
+		} else {
+			dev_err(dev, "port reg should be 0 or 1\n");
+		}
+	}
+
+	of_node_put(eth_ports_node);
+
+	/* At least one node must be present and available else we fail */
+	if (!eth0_node && !eth1_node) {
+		dev_err(dev, "neither port0 nor port1 node available\n");
+		return -ENODEV;
+	}
+
+	if (eth0_node == eth1_node) {
+		dev_err(dev, "port0 and port1 can't have same reg\n");
+		of_node_put(eth0_node);
+		return -ENODEV;
+	}
+
+	prueth->eth_node[PRUETH_MAC0] = eth0_node;
+	prueth->eth_node[PRUETH_MAC1] = eth1_node;
+
+	prueth->miig_rt = syscon_regmap_lookup_by_phandle(np, "ti,mii-g-rt");
+	if (IS_ERR(prueth->miig_rt)) {
+		dev_err(dev, "couldn't get ti,mii-g-rt syscon regmap\n");
+		return -ENODEV;
+	}
+
+	prueth->mii_rt = syscon_regmap_lookup_by_phandle(np, "ti,mii-rt");
+	if (IS_ERR(prueth->mii_rt)) {
+		dev_err(dev, "couldn't get ti,mii-rt syscon regmap\n");
+		return -ENODEV;
+	}
+
+	if (eth0_node) {
+		ret = prueth_get_cores(prueth, ICSS_SLICE0);
+		if (ret)
+			goto put_cores;
+	}
+
+	if (eth1_node) {
+		ret = prueth_get_cores(prueth, ICSS_SLICE1);
+		if (ret)
+			goto put_cores;
+	}
+
+	pruss = pruss_get(eth0_node ?
+			  prueth->pru[ICSS_SLICE0] : prueth->pru[ICSS_SLICE1]);
+	if (IS_ERR(pruss)) {
+		ret = PTR_ERR(pruss);
+		dev_err(dev, "unable to get pruss handle\n");
+		goto put_cores;
+	}
+
+	prueth->pruss = pruss;
+
+	ret = pruss_request_mem_region(pruss, PRUSS_MEM_SHRD_RAM2,
+				       &prueth->shram);
+	if (ret) {
+		dev_err(dev, "unable to get PRUSS SHRD RAM2: %d\n", ret);
+		pruss_put(prueth->pruss);
+	}
+
+	prueth->sram_pool = of_gen_pool_get(np, "sram", 0);
+	if (!prueth->sram_pool) {
+		dev_err(dev, "unable to get SRAM pool\n");
+		ret = -ENODEV;
+
+		goto put_mem;
+	}
+
+	msmc_ram_size = MSMC_RAM_SIZE;
+
+	/* NOTE: FW bug needs buffer base to be 64KB aligned */
+	prueth->msmcram.va =
+		(void __iomem *)gen_pool_alloc_algo(prueth->sram_pool,
+						    msmc_ram_size,
+						    gen_pool_first_fit_align,
+						    &gp_data);
+
+	if (!prueth->msmcram.va) {
+		ret = -ENOMEM;
+		dev_err(dev, "unable to allocate MSMC resource\n");
+		goto put_mem;
+	}
+	prueth->msmcram.pa = gen_pool_virt_to_phys(prueth->sram_pool,
+						   (unsigned long)prueth->msmcram.va);
+	prueth->msmcram.size = msmc_ram_size;
+	memset_io(prueth->msmcram.va, 0, msmc_ram_size);
+	dev_dbg(dev, "sram: pa %llx va %p size %zx\n", prueth->msmcram.pa,
+		prueth->msmcram.va, prueth->msmcram.size);
+
+	/* setup netdev interfaces */
+	if (eth0_node) {
+		ret = prueth_netdev_init(prueth, eth0_node);
+		if (ret) {
+			dev_err_probe(dev, ret, "netdev init %s failed\n",
+				      eth0_node->name);
+			goto netdev_exit;
+		}
+	}
+
+	if (eth1_node) {
+		ret = prueth_netdev_init(prueth, eth1_node);
+		if (ret) {
+			dev_err_probe(dev, ret, "netdev init %s failed\n",
+				      eth1_node->name);
+			goto netdev_exit;
+		}
+	}
+
+	/* register the network devices */
+	if (eth0_node) {
+		ret = register_netdev(prueth->emac[PRUETH_MAC0]->ndev);
+		if (ret) {
+			dev_err(dev, "can't register netdev for port MII0");
+			goto netdev_exit;
+		}
+
+		prueth->registered_netdevs[PRUETH_MAC0] = prueth->emac[PRUETH_MAC0]->ndev;
+
+		emac_phy_connect(prueth->emac[PRUETH_MAC0]);
+		phy_attached_info(prueth->emac[PRUETH_MAC0]->ndev->phydev);
+	}
+
+	if (eth1_node) {
+		ret = register_netdev(prueth->emac[PRUETH_MAC1]->ndev);
+		if (ret) {
+			dev_err(dev, "can't register netdev for port MII1");
+			goto netdev_unregister;
+		}
+
+		prueth->registered_netdevs[PRUETH_MAC1] = prueth->emac[PRUETH_MAC1]->ndev;
+		emac_phy_connect(prueth->emac[PRUETH_MAC1]);
+		phy_attached_info(prueth->emac[PRUETH_MAC1]->ndev->phydev);
+	}
+
+	dev_info(dev, "TI PRU ethernet driver initialized: %s EMAC mode\n",
+		 (!eth0_node || !eth1_node) ? "single" : "dual");
+
+	if (eth1_node)
+		of_node_put(eth1_node);
+	if (eth0_node)
+		of_node_put(eth0_node);
+	return 0;
+
+netdev_unregister:
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		if (!prueth->registered_netdevs[i])
+			continue;
+		if (prueth->emac[i]->ndev->phydev) {
+			phy_disconnect(prueth->emac[i]->ndev->phydev);
+			prueth->emac[i]->ndev->phydev = NULL;
+		}
+		unregister_netdev(prueth->registered_netdevs[i]);
+	}
+
+netdev_exit:
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		eth_node = prueth->eth_node[i];
+		if (!eth_node)
+			continue;
+
+		prueth_netdev_exit(prueth, eth_node);
+	}
+
+	gen_pool_free(prueth->sram_pool,
+		      (unsigned long)prueth->msmcram.va, msmc_ram_size);
+
+put_mem:
+	pruss_release_mem_region(prueth->pruss, &prueth->shram);
+	pruss_put(prueth->pruss);
+
+put_cores:
+	if (eth1_node) {
+		prueth_put_cores(prueth, ICSS_SLICE1);
+		of_node_put(eth1_node);
+	}
+
+	if (eth0_node) {
+		prueth_put_cores(prueth, ICSS_SLICE0);
+		of_node_put(eth0_node);
+	}
+
+	return ret;
+}
+
+static void prueth_remove(struct platform_device *pdev)
+{
+	struct prueth *prueth = platform_get_drvdata(pdev);
+	struct device_node *eth_node;
+	int i;
+
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		if (!prueth->registered_netdevs[i])
+			continue;
+		phy_stop(prueth->emac[i]->ndev->phydev);
+		phy_disconnect(prueth->emac[i]->ndev->phydev);
+		prueth->emac[i]->ndev->phydev = NULL;
+		unregister_netdev(prueth->registered_netdevs[i]);
+	}
+
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		eth_node = prueth->eth_node[i];
+		if (!eth_node)
+			continue;
+
+		prueth_netdev_exit(prueth, eth_node);
+	}
+
+	gen_pool_free(prueth->sram_pool,
+		      (unsigned long)prueth->msmcram.va,
+		      MSMC_RAM_SIZE);
+
+	pruss_release_mem_region(prueth->pruss, &prueth->shram);
+
+	pruss_put(prueth->pruss);
+
+	if (prueth->eth_node[PRUETH_MAC1])
+		prueth_put_cores(prueth, ICSS_SLICE1);
+
+	if (prueth->eth_node[PRUETH_MAC0])
+		prueth_put_cores(prueth, ICSS_SLICE0);
+}
+
+static const struct prueth_pdata am654_icssg_pdata = {
+	.fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
+	.quirk_10m_link_issue = 1,
+};
+
+static const struct of_device_id prueth_dt_match[] = {
+	{ .compatible = "ti,am654-icssg-prueth", .data = &am654_icssg_pdata },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, prueth_dt_match);
+
+static struct platform_driver prueth_driver = {
+	.probe = prueth_probe,
+	.remove_new = prueth_remove,
+	.driver = {
+		.name = "icssg-prueth",
+		.of_match_table = prueth_dt_match,
+	},
+};
+module_platform_driver(prueth_driver);
+
+MODULE_AUTHOR("Roger Quadros <rogerq@ti.com>");
+MODULE_AUTHOR("Md Danish Anwar <danishanwar@ti.com>");
+MODULE_DESCRIPTION("PRUSS ICSSG Ethernet Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 42fdf4005010a..b3a923e7a5c9c 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -34,13 +34,42 @@
 
 #include <net/devlink.h>
 
+#include "icssg_config.h"
 #include "icssg_switch_map.h"
 
+#define PRUETH_MAX_MTU          (2000 - ETH_HLEN - ETH_FCS_LEN)
+#define PRUETH_MIN_PKT_SIZE     (VLAN_ETH_ZLEN)
+#define PRUETH_MAX_PKT_SIZE     (PRUETH_MAX_MTU + ETH_HLEN + ETH_FCS_LEN)
+
 #define ICSS_SLICE0	0
 #define ICSS_SLICE1	1
 
+#define ICSS_FW_PRU	0
+#define ICSS_FW_RTU	1
+
 #define ICSSG_MAX_RFLOWS	8	/* per slice */
 
+/* Firmware status codes */
+#define ICSS_HS_FW_READY 0x55555555
+#define ICSS_HS_FW_DEAD 0xDEAD0000	/* lower 16 bits contain error code */
+
+/* Firmware command codes */
+#define ICSS_HS_CMD_BUSY 0x40000000
+#define ICSS_HS_CMD_DONE 0x80000000
+#define ICSS_HS_CMD_CANCEL 0x10000000
+
+/* Firmware commands */
+#define ICSS_CMD_SPAD 0x20
+#define ICSS_CMD_RXTX 0x10
+#define ICSS_CMD_ADD_FDB 0x1
+#define ICSS_CMD_DEL_FDB 0x2
+#define ICSS_CMD_SET_RUN 0x4
+#define ICSS_CMD_GET_FDB_SLOT 0x5
+#define ICSS_CMD_ENABLE_VLAN 0x5
+#define ICSS_CMD_DISABLE_VLAN 0x6
+#define ICSS_CMD_ADD_FILTER 0x7
+#define ICSS_CMD_ADD_MAC 0x8
+
 /* In switch mode there are 3 real ports i.e. 3 mac addrs.
  * however Linux sees only the host side port. The other 2 ports
  * are the switch ports.
@@ -214,4 +243,7 @@ int icssg_queue_pop(struct prueth *prueth, u8 queue);
 void icssg_queue_push(struct prueth *prueth, int queue, u16 addr);
 u32 icssg_queue_level(struct prueth *prueth, int queue);
 
+#define prueth_napi_to_tx_chn(pnapi) \
+	container_of(pnapi, struct prueth_tx_chn, napi_tx)
+
 #endif /* __NET_TI_ICSSG_PRUETH_H */
-- 
GitLab


From c1e10d5dc7a1be8d4eba8560540e20bd03c2be01 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 1 Aug 2023 14:44:25 +0530
Subject: [PATCH 0756/1806] net: ti: icssg-prueth: Add ICSSG Stats

Add icssg_stats.c to help dump, icssg related driver statistics.

ICSSG has hardware registers for providing statistics like total rx bytes,
total tx bytes, etc. These registers are of 32 bits and hence in case of 1G
link, they overflows in around 32 seconds. The behaviour of these registers
is such that they don't roll back to 0 after overflow but rather stay at
UINT_MAX.

These registers support a feature where the value written to them is
subtracted from the register. This feature can be utilized to fix the
overflowing of stats.

This solution uses a Workqueues based solution where a function gets
called before the registers overflow (every 25 seconds in 1G link, 25000
seconds in 100M link), this function saves the register
values in local variables and writes the last read value to the
register. So any update during the read will be taken care of.

Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/Makefile             |   1 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.c |   8 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.h |   8 +
 drivers/net/ethernet/ti/icssg/icssg_stats.c  |  44 ++++++
 drivers/net/ethernet/ti/icssg/icssg_stats.h  | 158 +++++++++++++++++++
 5 files changed, 219 insertions(+)
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_stats.c
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_stats.h

diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index efb050cbb4a8f..03d9b2b36b5ff 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -36,3 +36,4 @@ icssg-prueth-y := k3-cppi-desc-pool.o \
 		  icssg/icssg_queues.o \
 		  icssg/icssg_config.o \
 		  icssg/icssg_mii_cfg.o \
+		  icssg/icssg_stats.o \
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 1869e38f898f1..d0bb4db11b309 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -8,6 +8,7 @@
 
 #include <linux/bitops.h>
 #include <linux/clk.h>
+#include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma/ti-cppi5.h>
 #include <linux/etherdevice.h>
@@ -1090,6 +1091,8 @@ static int emac_ndo_open(struct net_device *ndev)
 
 	prueth->emacs_initialized++;
 
+	queue_work(system_long_wq, &emac->stats_work.work);
+
 	return 0;
 
 reset_tx_chan:
@@ -1164,6 +1167,9 @@ static int emac_ndo_stop(struct net_device *ndev)
 
 	cancel_work_sync(&emac->rx_mode_work);
 
+	/* Destroying the queued work in ndo_stop() */
+	cancel_delayed_work_sync(&emac->stats_work);
+
 	/* stop PRUs */
 	prueth_emac_stop(emac);
 
@@ -1313,6 +1319,8 @@ static int prueth_netdev_init(struct prueth *prueth,
 	}
 	INIT_WORK(&emac->rx_mode_work, emac_ndo_set_rx_mode_work);
 
+	INIT_DELAYED_WORK(&emac->stats_work, emac_stats_work_handler);
+
 	ret = pruss_request_mem_region(prueth->pruss,
 				       port == PRUETH_PORT_MII0 ?
 				       PRUSS_MEM_DRAM0 : PRUSS_MEM_DRAM1,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index b3a923e7a5c9c..f13de0d2e90b5 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -49,6 +49,9 @@
 
 #define ICSSG_MAX_RFLOWS	8	/* per slice */
 
+/* Number of ICSSG related stats */
+#define ICSSG_NUM_STATS 60
+
 /* Firmware status codes */
 #define ICSS_HS_FW_READY 0x55555555
 #define ICSS_HS_FW_DEAD 0xDEAD0000	/* lower 16 bits contain error code */
@@ -153,6 +156,9 @@ struct prueth_emac {
 	struct workqueue_struct	*cmd_wq;
 
 	struct pruss_mem_region dram;
+
+	struct delayed_work stats_work;
+	u64 stats[ICSSG_NUM_STATS];
 };
 
 /**
@@ -246,4 +252,6 @@ u32 icssg_queue_level(struct prueth *prueth, int queue);
 #define prueth_napi_to_tx_chn(pnapi) \
 	container_of(pnapi, struct prueth_tx_chn, napi_tx)
 
+void emac_stats_work_handler(struct work_struct *work);
+void emac_update_hardware_stats(struct prueth_emac *emac);
 #endif /* __NET_TI_ICSSG_PRUETH_H */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
new file mode 100644
index 0000000000000..25deb368a3f03
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Texas Instruments ICSSG Ethernet driver
+ *
+ * Copyright (C) 2018-2021 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#include "icssg_prueth.h"
+#include "icssg_stats.h"
+#include <linux/regmap.h>
+
+static u32 stats_base[] = {	0x54c,	/* Slice 0 stats start */
+				0xb18,	/* Slice 1 stats start */
+};
+
+void emac_update_hardware_stats(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+	u32 base = stats_base[slice];
+	u32 val;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) {
+		regmap_read(prueth->miig_rt,
+			    base + icssg_all_stats[i].offset,
+			    &val);
+		regmap_write(prueth->miig_rt,
+			     base + icssg_all_stats[i].offset,
+			     val);
+
+		emac->stats[i] += val;
+	}
+}
+
+void emac_stats_work_handler(struct work_struct *work)
+{
+	struct prueth_emac *emac = container_of(work, struct prueth_emac,
+						stats_work.work);
+	emac_update_hardware_stats(emac);
+
+	queue_delayed_work(system_long_wq, &emac->stats_work,
+			   msecs_to_jiffies((STATS_TIME_LIMIT_1G_MS * 1000) / emac->speed));
+}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.h b/drivers/net/ethernet/ti/icssg/icssg_stats.h
new file mode 100644
index 0000000000000..999a4a91276c3
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.h
@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Texas Instruments ICSSG Ethernet driver
+ *
+ * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#ifndef __NET_TI_ICSSG_STATS_H
+#define __NET_TI_ICSSG_STATS_H
+
+#include "icssg_prueth.h"
+
+#define STATS_TIME_LIMIT_1G_MS    25000    /* 25 seconds @ 1G */
+
+struct miig_stats_regs {
+	/* Rx */
+	u32 rx_packets;
+	u32 rx_broadcast_frames;
+	u32 rx_multicast_frames;
+	u32 rx_crc_errors;
+	u32 rx_mii_error_frames;
+	u32 rx_odd_nibble_frames;
+	u32 rx_frame_max_size;
+	u32 rx_max_size_error_frames;
+	u32 rx_frame_min_size;
+	u32 rx_min_size_error_frames;
+	u32 rx_over_errors;
+	u32 rx_class0_hits;
+	u32 rx_class1_hits;
+	u32 rx_class2_hits;
+	u32 rx_class3_hits;
+	u32 rx_class4_hits;
+	u32 rx_class5_hits;
+	u32 rx_class6_hits;
+	u32 rx_class7_hits;
+	u32 rx_class8_hits;
+	u32 rx_class9_hits;
+	u32 rx_class10_hits;
+	u32 rx_class11_hits;
+	u32 rx_class12_hits;
+	u32 rx_class13_hits;
+	u32 rx_class14_hits;
+	u32 rx_class15_hits;
+	u32 rx_smd_frags;
+	u32 rx_bucket1_size;
+	u32 rx_bucket2_size;
+	u32 rx_bucket3_size;
+	u32 rx_bucket4_size;
+	u32 rx_64B_frames;
+	u32 rx_bucket1_frames;
+	u32 rx_bucket2_frames;
+	u32 rx_bucket3_frames;
+	u32 rx_bucket4_frames;
+	u32 rx_bucket5_frames;
+	u32 rx_bytes;
+	u32 rx_tx_total_bytes;
+	/* Tx */
+	u32 tx_packets;
+	u32 tx_broadcast_frames;
+	u32 tx_multicast_frames;
+	u32 tx_odd_nibble_frames;
+	u32 tx_underflow_errors;
+	u32 tx_frame_max_size;
+	u32 tx_max_size_error_frames;
+	u32 tx_frame_min_size;
+	u32 tx_min_size_error_frames;
+	u32 tx_bucket1_size;
+	u32 tx_bucket2_size;
+	u32 tx_bucket3_size;
+	u32 tx_bucket4_size;
+	u32 tx_64B_frames;
+	u32 tx_bucket1_frames;
+	u32 tx_bucket2_frames;
+	u32 tx_bucket3_frames;
+	u32 tx_bucket4_frames;
+	u32 tx_bucket5_frames;
+	u32 tx_bytes;
+};
+
+#define ICSSG_STATS(field, stats_type)			\
+{							\
+	#field,						\
+	offsetof(struct miig_stats_regs, field),	\
+	stats_type					\
+}
+
+struct icssg_stats {
+	char name[ETH_GSTRING_LEN];
+	u32 offset;
+	bool standard_stats;
+};
+
+static const struct icssg_stats icssg_all_stats[] = {
+	/* Rx */
+	ICSSG_STATS(rx_packets, true),
+	ICSSG_STATS(rx_broadcast_frames, false),
+	ICSSG_STATS(rx_multicast_frames, true),
+	ICSSG_STATS(rx_crc_errors, true),
+	ICSSG_STATS(rx_mii_error_frames, false),
+	ICSSG_STATS(rx_odd_nibble_frames, false),
+	ICSSG_STATS(rx_frame_max_size, true),
+	ICSSG_STATS(rx_max_size_error_frames, false),
+	ICSSG_STATS(rx_frame_min_size, true),
+	ICSSG_STATS(rx_min_size_error_frames, false),
+	ICSSG_STATS(rx_over_errors, true),
+	ICSSG_STATS(rx_class0_hits, false),
+	ICSSG_STATS(rx_class1_hits, false),
+	ICSSG_STATS(rx_class2_hits, false),
+	ICSSG_STATS(rx_class3_hits, false),
+	ICSSG_STATS(rx_class4_hits, false),
+	ICSSG_STATS(rx_class5_hits, false),
+	ICSSG_STATS(rx_class6_hits, false),
+	ICSSG_STATS(rx_class7_hits, false),
+	ICSSG_STATS(rx_class8_hits, false),
+	ICSSG_STATS(rx_class9_hits, false),
+	ICSSG_STATS(rx_class10_hits, false),
+	ICSSG_STATS(rx_class11_hits, false),
+	ICSSG_STATS(rx_class12_hits, false),
+	ICSSG_STATS(rx_class13_hits, false),
+	ICSSG_STATS(rx_class14_hits, false),
+	ICSSG_STATS(rx_class15_hits, false),
+	ICSSG_STATS(rx_smd_frags, false),
+	ICSSG_STATS(rx_bucket1_size, true),
+	ICSSG_STATS(rx_bucket2_size, true),
+	ICSSG_STATS(rx_bucket3_size, true),
+	ICSSG_STATS(rx_bucket4_size, true),
+	ICSSG_STATS(rx_64B_frames, true),
+	ICSSG_STATS(rx_bucket1_frames, true),
+	ICSSG_STATS(rx_bucket2_frames, true),
+	ICSSG_STATS(rx_bucket3_frames, true),
+	ICSSG_STATS(rx_bucket4_frames, true),
+	ICSSG_STATS(rx_bucket5_frames, true),
+	ICSSG_STATS(rx_bytes, true),
+	ICSSG_STATS(rx_tx_total_bytes, false),
+	/* Tx */
+	ICSSG_STATS(tx_packets, true),
+	ICSSG_STATS(tx_broadcast_frames, false),
+	ICSSG_STATS(tx_multicast_frames, false),
+	ICSSG_STATS(tx_odd_nibble_frames, false),
+	ICSSG_STATS(tx_underflow_errors, false),
+	ICSSG_STATS(tx_frame_max_size, true),
+	ICSSG_STATS(tx_max_size_error_frames, false),
+	ICSSG_STATS(tx_frame_min_size, true),
+	ICSSG_STATS(tx_min_size_error_frames, false),
+	ICSSG_STATS(tx_bucket1_size, true),
+	ICSSG_STATS(tx_bucket2_size, true),
+	ICSSG_STATS(tx_bucket3_size, true),
+	ICSSG_STATS(tx_bucket4_size, true),
+	ICSSG_STATS(tx_64B_frames, true),
+	ICSSG_STATS(tx_bucket1_frames, true),
+	ICSSG_STATS(tx_bucket2_frames, true),
+	ICSSG_STATS(tx_bucket3_frames, true),
+	ICSSG_STATS(tx_bucket4_frames, true),
+	ICSSG_STATS(tx_bucket5_frames, true),
+	ICSSG_STATS(tx_bytes, true),
+};
+
+#endif /* __NET_TI_ICSSG_STATS_H */
-- 
GitLab


From c2f67d192351d33ec884af6bbbbfe77c57f7c397 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 1 Aug 2023 14:44:26 +0530
Subject: [PATCH 0757/1806] net: ti: icssg-prueth: Add Standard network
 staticstics

Implement .ndo_get_stats64 to dump standard network interface
statistics for ICSSG ethernet driver.

Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 22 ++++++++++++++++++++
 drivers/net/ethernet/ti/icssg/icssg_prueth.h |  2 ++
 drivers/net/ethernet/ti/icssg/icssg_stats.c  | 13 ++++++++++++
 3 files changed, 37 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index d0bb4db11b309..e641b6ce94158 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1240,6 +1240,27 @@ static int emac_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
 	return phy_do_ioctl(ndev, ifr, cmd);
 }
 
+static void emac_ndo_get_stats64(struct net_device *ndev,
+				 struct rtnl_link_stats64 *stats)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	emac_update_hardware_stats(emac);
+
+	stats->rx_packets     = emac_get_stat_by_name(emac, "rx_packets");
+	stats->rx_bytes       = emac_get_stat_by_name(emac, "rx_bytes");
+	stats->tx_packets     = emac_get_stat_by_name(emac, "tx_packets");
+	stats->tx_bytes       = emac_get_stat_by_name(emac, "tx_bytes");
+	stats->rx_crc_errors  = emac_get_stat_by_name(emac, "rx_crc_errors");
+	stats->rx_over_errors = emac_get_stat_by_name(emac, "rx_over_errors");
+	stats->multicast      = emac_get_stat_by_name(emac, "rx_multicast_frames");
+
+	stats->rx_errors  = ndev->stats.rx_errors;
+	stats->rx_dropped = ndev->stats.rx_dropped;
+	stats->tx_errors  = ndev->stats.tx_errors;
+	stats->tx_dropped = ndev->stats.tx_dropped;
+}
+
 static const struct net_device_ops emac_netdev_ops = {
 	.ndo_open = emac_ndo_open,
 	.ndo_stop = emac_ndo_stop,
@@ -1249,6 +1270,7 @@ static const struct net_device_ops emac_netdev_ops = {
 	.ndo_tx_timeout = emac_ndo_tx_timeout,
 	.ndo_set_rx_mode = emac_ndo_set_rx_mode,
 	.ndo_eth_ioctl = emac_ndo_ioctl,
+	.ndo_get_stats64 = emac_ndo_get_stats64,
 };
 
 /* get emac_port corresponding to eth_node name */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index f13de0d2e90b5..e58cd8db7ba00 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -51,6 +51,7 @@
 
 /* Number of ICSSG related stats */
 #define ICSSG_NUM_STATS 60
+#define ICSSG_NUM_STANDARD_STATS 31
 
 /* Firmware status codes */
 #define ICSS_HS_FW_READY 0x55555555
@@ -254,4 +255,5 @@ u32 icssg_queue_level(struct prueth *prueth, int queue);
 
 void emac_stats_work_handler(struct work_struct *work);
 void emac_update_hardware_stats(struct prueth_emac *emac);
+int emac_get_stat_by_name(struct prueth_emac *emac, char *stat_name);
 #endif /* __NET_TI_ICSSG_PRUETH_H */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
index 25deb368a3f03..bb0b33927e3b8 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -42,3 +42,16 @@ void emac_stats_work_handler(struct work_struct *work)
 	queue_delayed_work(system_long_wq, &emac->stats_work,
 			   msecs_to_jiffies((STATS_TIME_LIMIT_1G_MS * 1000) / emac->speed));
 }
+
+int emac_get_stat_by_name(struct prueth_emac *emac, char *stat_name)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) {
+		if (!strcmp(icssg_all_stats[i].name, stat_name))
+			return emac->stats[icssg_all_stats[i].offset / sizeof(u32)];
+	}
+
+	netdev_err(emac->ndev, "Invalid stats %s\n", stat_name);
+	return -EINVAL;
+}
-- 
GitLab


From 8fb86b0dcaed2d6bbc33203e7340bff3e68fe339 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 1 Aug 2023 14:44:27 +0530
Subject: [PATCH 0758/1806] net: ti: icssg-prueth: Add ethtool ops for ICSSG
 Ethernet driver

Add icssg_ethtool.c file. This file will be used for dumping statistics
via ethtool for ICSSG ethernet driver.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/Makefile              |   1 +
 drivers/net/ethernet/ti/icssg/icssg_ethtool.c | 188 ++++++++++++++++++
 drivers/net/ethernet/ti/icssg/icssg_prueth.c  |   1 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.h  |   3 +
 4 files changed, 193 insertions(+)
 create mode 100644 drivers/net/ethernet/ti/icssg/icssg_ethtool.c

diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 03d9b2b36b5ff..9176d79c36e1e 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -37,3 +37,4 @@ icssg-prueth-y := k3-cppi-desc-pool.o \
 		  icssg/icssg_config.o \
 		  icssg/icssg_mii_cfg.o \
 		  icssg/icssg_stats.o \
+		  icssg/icssg_ethtool.o
diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
new file mode 100644
index 0000000000000..02c312f01d10f
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Texas Instruments ICSSG Ethernet driver
+ *
+ * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#include "icssg_prueth.h"
+#include "icssg_stats.h"
+
+static void emac_get_drvinfo(struct net_device *ndev,
+			     struct ethtool_drvinfo *info)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+
+	strscpy(info->driver, dev_driver_string(prueth->dev),
+		sizeof(info->driver));
+	strscpy(info->bus_info, dev_name(prueth->dev), sizeof(info->bus_info));
+}
+
+static u32 emac_get_msglevel(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	return emac->msg_enable;
+}
+
+static void emac_set_msglevel(struct net_device *ndev, u32 value)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	emac->msg_enable = value;
+}
+
+static int emac_get_link_ksettings(struct net_device *ndev,
+				   struct ethtool_link_ksettings *ecmd)
+{
+	return phy_ethtool_get_link_ksettings(ndev, ecmd);
+}
+
+static int emac_set_link_ksettings(struct net_device *ndev,
+				   const struct ethtool_link_ksettings *ecmd)
+{
+	return phy_ethtool_set_link_ksettings(ndev, ecmd);
+}
+
+static int emac_get_eee(struct net_device *ndev, struct ethtool_eee *edata)
+{
+	if (!ndev->phydev)
+		return -EOPNOTSUPP;
+
+	return phy_ethtool_get_eee(ndev->phydev, edata);
+}
+
+static int emac_set_eee(struct net_device *ndev, struct ethtool_eee *edata)
+{
+	if (!ndev->phydev)
+		return -EOPNOTSUPP;
+
+	return phy_ethtool_set_eee(ndev->phydev, edata);
+}
+
+static int emac_nway_reset(struct net_device *ndev)
+{
+	return phy_ethtool_nway_reset(ndev);
+}
+
+static int emac_get_sset_count(struct net_device *ndev, int stringset)
+{
+	switch (stringset) {
+	case ETH_SS_STATS:
+		return ICSSG_NUM_ETHTOOL_STATS;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void emac_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+	u8 *p = data;
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) {
+			if (!icssg_all_stats[i].standard_stats) {
+				memcpy(p, icssg_all_stats[i].name,
+				       ETH_GSTRING_LEN);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void emac_get_ethtool_stats(struct net_device *ndev,
+				   struct ethtool_stats *stats, u64 *data)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int i;
+
+	emac_update_hardware_stats(emac);
+
+	for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++)
+		if (!icssg_all_stats[i].standard_stats)
+			*(data++) = emac->stats[i];
+}
+
+static int emac_set_channels(struct net_device *ndev,
+			     struct ethtool_channels *ch)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	/* Check if interface is up. Can change the num queues when
+	 * the interface is down.
+	 */
+	if (netif_running(emac->ndev))
+		return -EBUSY;
+
+	emac->tx_ch_num = ch->tx_count;
+
+	return 0;
+}
+
+static void emac_get_channels(struct net_device *ndev,
+			      struct ethtool_channels *ch)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	ch->max_rx = 1;
+	ch->max_tx = PRUETH_MAX_TX_QUEUES;
+	ch->rx_count = 1;
+	ch->tx_count = emac->tx_ch_num;
+}
+
+static const struct ethtool_rmon_hist_range emac_rmon_ranges[] = {
+	{    0,   64},
+	{   65,  128},
+	{  129,  256},
+	{  257,  512},
+	{  513, PRUETH_MAX_PKT_SIZE},
+	{}
+};
+
+static void emac_get_rmon_stats(struct net_device *ndev,
+				struct ethtool_rmon_stats *rmon_stats,
+				const struct ethtool_rmon_hist_range **ranges)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	*ranges = emac_rmon_ranges;
+
+	rmon_stats->undersize_pkts = emac_get_stat_by_name(emac, "rx_bucket1_frames") -
+				     emac_get_stat_by_name(emac, "rx_64B_frames");
+
+	rmon_stats->hist[0] = emac_get_stat_by_name(emac, "rx_bucket1_frames");
+	rmon_stats->hist[1] = emac_get_stat_by_name(emac, "rx_bucket2_frames");
+	rmon_stats->hist[2] = emac_get_stat_by_name(emac, "rx_bucket3_frames");
+	rmon_stats->hist[3] = emac_get_stat_by_name(emac, "rx_bucket4_frames");
+	rmon_stats->hist[4] = emac_get_stat_by_name(emac, "rx_bucket5_frames");
+
+	rmon_stats->hist_tx[0] = emac_get_stat_by_name(emac, "tx_bucket1_frames");
+	rmon_stats->hist_tx[1] = emac_get_stat_by_name(emac, "tx_bucket2_frames");
+	rmon_stats->hist_tx[2] = emac_get_stat_by_name(emac, "tx_bucket3_frames");
+	rmon_stats->hist_tx[3] = emac_get_stat_by_name(emac, "tx_bucket4_frames");
+	rmon_stats->hist_tx[4] = emac_get_stat_by_name(emac, "tx_bucket5_frames");
+}
+
+const struct ethtool_ops icssg_ethtool_ops = {
+	.get_drvinfo = emac_get_drvinfo,
+	.get_msglevel = emac_get_msglevel,
+	.set_msglevel = emac_set_msglevel,
+	.get_sset_count = emac_get_sset_count,
+	.get_ethtool_stats = emac_get_ethtool_stats,
+	.get_strings = emac_get_strings,
+	.get_channels = emac_get_channels,
+	.set_channels = emac_set_channels,
+	.get_link_ksettings = emac_get_link_ksettings,
+	.set_link_ksettings = emac_set_link_ksettings,
+	.get_link = ethtool_op_get_link,
+	.get_eee = emac_get_eee,
+	.set_eee = emac_set_eee,
+	.nway_reset = emac_nway_reset,
+	.get_rmon_stats = emac_get_rmon_stats,
+};
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index e641b6ce94158..80721d82f6c5f 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1421,6 +1421,7 @@ static int prueth_netdev_init(struct prueth *prueth,
 	ndev->min_mtu = PRUETH_MIN_PKT_SIZE;
 	ndev->max_mtu = PRUETH_MAX_MTU;
 	ndev->netdev_ops = &emac_netdev_ops;
+	ndev->ethtool_ops = &icssg_ethtool_ops;
 	ndev->hw_features = NETIF_F_SG;
 	ndev->features = ndev->hw_features;
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index e58cd8db7ba00..a8ce4d01ef160 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -52,6 +52,7 @@
 /* Number of ICSSG related stats */
 #define ICSSG_NUM_STATS 60
 #define ICSSG_NUM_STANDARD_STATS 31
+#define ICSSG_NUM_ETHTOOL_STATS (ICSSG_NUM_STATS - ICSSG_NUM_STANDARD_STATS)
 
 /* Firmware status codes */
 #define ICSS_HS_FW_READY 0x55555555
@@ -230,6 +231,8 @@ static inline int prueth_emac_slice(struct prueth_emac *emac)
 	}
 }
 
+extern const struct ethtool_ops icssg_ethtool_ops;
+
 /* Classifier helpers */
 void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac);
 void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac);
-- 
GitLab


From a46750a13bb09e2e185bc66c44d9a002dab2d3d5 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Tue, 1 Aug 2023 14:44:28 +0530
Subject: [PATCH 0759/1806] net: ti: icssg-prueth: Add Power management support

Add suspend / resume APIs to support power management in ICSSG ethernet
driver.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 57 ++++++++++++++++++++
 1 file changed, 57 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 80721d82f6c5f..47b941fb0198d 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1813,6 +1813,62 @@ static void prueth_remove(struct platform_device *pdev)
 		prueth_put_cores(prueth, ICSS_SLICE0);
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int prueth_suspend(struct device *dev)
+{
+	struct prueth *prueth = dev_get_drvdata(dev);
+	struct net_device *ndev;
+	int i, ret;
+
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		ndev = prueth->registered_netdevs[i];
+
+		if (!ndev)
+			continue;
+
+		if (netif_running(ndev)) {
+			netif_device_detach(ndev);
+			ret = emac_ndo_stop(ndev);
+			if (ret < 0) {
+				netdev_err(ndev, "failed to stop: %d", ret);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int prueth_resume(struct device *dev)
+{
+	struct prueth *prueth = dev_get_drvdata(dev);
+	struct net_device *ndev;
+	int i, ret;
+
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		ndev = prueth->registered_netdevs[i];
+
+		if (!ndev)
+			continue;
+
+		if (netif_running(ndev)) {
+			ret = emac_ndo_open(ndev);
+			if (ret < 0) {
+				netdev_err(ndev, "failed to start: %d", ret);
+				return ret;
+			}
+			netif_device_attach(ndev);
+		}
+	}
+
+	return 0;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+static const struct dev_pm_ops prueth_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(prueth_suspend, prueth_resume)
+};
+
 static const struct prueth_pdata am654_icssg_pdata = {
 	.fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
 	.quirk_10m_link_issue = 1,
@@ -1830,6 +1886,7 @@ static struct platform_driver prueth_driver = {
 	.driver = {
 		.name = "icssg-prueth",
 		.of_match_table = prueth_dt_match,
+		.pm = &prueth_dev_pm_ops,
 	},
 };
 module_platform_driver(prueth_driver);
-- 
GitLab


From d6b484b5cb2a7d509b36a220911509ddd8b777c4 Mon Sep 17 00:00:00 2001
From: Azeem Shaikh <azeemshaikh38@gmail.com>
Date: Mon, 3 Jul 2023 18:12:56 +0000
Subject: [PATCH 0760/1806] wifi: mt76: Replace strlcpy() with strscpy()

strlcpy() reads the entire source buffer first.
This read may exceed the destination size limit.
This is both inefficient and can lead to linear read
overflows if a source string is not NUL-terminated [1].
In an effort to remove strlcpy() completely [2], replace
strlcpy() here with strscpy().

Direct replacement is safe here since DEV_ASSIGN is only used by
TRACE macros and the return values are ignored.

[1] https://www.kernel.org/doc/html/latest/process/deprecated.html#strlcpy
[2] https://github.com/KSPP/linux/issues/89

Signed-off-by: Azeem Shaikh <azeemshaikh38@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230703181256.3712079-1-azeemshaikh38@gmail.com
---
 drivers/net/wireless/mediatek/mt76/mt7615/mt7615_trace.h | 2 +-
 drivers/net/wireless/mediatek/mt76/mt76x02_trace.h       | 2 +-
 drivers/net/wireless/mediatek/mt76/trace.h               | 2 +-
 drivers/net/wireless/mediatek/mt76/usb_trace.h           | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615_trace.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615_trace.h
index d3eb49d83b98d..9be5a58a4e6dc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615_trace.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615_trace.h
@@ -14,7 +14,7 @@
 
 #define MAXNAME		32
 #define DEV_ENTRY	__array(char, wiphy_name, 32)
-#define DEV_ASSIGN	strlcpy(__entry->wiphy_name,	\
+#define DEV_ASSIGN	strscpy(__entry->wiphy_name,	\
 				wiphy_name(mt76_hw(dev)->wiphy), MAXNAME)
 #define DEV_PR_FMT	"%s"
 #define DEV_PR_ARG	__entry->wiphy_name
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_trace.h b/drivers/net/wireless/mediatek/mt76/mt76x02_trace.h
index 6a98092e996b3..11d119cd0f6fd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_trace.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_trace.h
@@ -14,7 +14,7 @@
 
 #define MAXNAME		32
 #define DEV_ENTRY	__array(char, wiphy_name, 32)
-#define DEV_ASSIGN	strlcpy(__entry->wiphy_name,	\
+#define DEV_ASSIGN	strscpy(__entry->wiphy_name,	\
 				wiphy_name(mt76_hw(dev)->wiphy), MAXNAME)
 #define DEV_PR_FMT	"%s"
 #define DEV_PR_ARG	__entry->wiphy_name
diff --git a/drivers/net/wireless/mediatek/mt76/trace.h b/drivers/net/wireless/mediatek/mt76/trace.h
index c3d0ef8e28903..109a07f9733a8 100644
--- a/drivers/net/wireless/mediatek/mt76/trace.h
+++ b/drivers/net/wireless/mediatek/mt76/trace.h
@@ -14,7 +14,7 @@
 
 #define MAXNAME		32
 #define DEV_ENTRY	__array(char, wiphy_name, 32)
-#define DEVICE_ASSIGN	strlcpy(__entry->wiphy_name,	\
+#define DEVICE_ASSIGN	strscpy(__entry->wiphy_name,	\
 				wiphy_name(dev->hw->wiphy), MAXNAME)
 #define DEV_PR_FMT	"%s"
 #define DEV_PR_ARG	__entry->wiphy_name
diff --git a/drivers/net/wireless/mediatek/mt76/usb_trace.h b/drivers/net/wireless/mediatek/mt76/usb_trace.h
index f5ab3215af800..7b261ddb2ac66 100644
--- a/drivers/net/wireless/mediatek/mt76/usb_trace.h
+++ b/drivers/net/wireless/mediatek/mt76/usb_trace.h
@@ -14,7 +14,7 @@
 
 #define MAXNAME		32
 #define DEV_ENTRY	__array(char, wiphy_name, 32)
-#define DEV_ASSIGN	strlcpy(__entry->wiphy_name,	\
+#define DEV_ASSIGN	strscpy(__entry->wiphy_name,	\
 				wiphy_name(dev->hw->wiphy), MAXNAME)
 #define DEV_PR_FMT	"%s "
 #define DEV_PR_ARG	__entry->wiphy_name
-- 
GitLab


From a9477c12ae54aec11f22ee473938d91f4b1c8536 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Tue, 25 Jul 2023 19:23:45 +0300
Subject: [PATCH 0761/1806] wifi: brcmsmac: remove more unused data types

Remove unused 'struct brcmu_iovar' and 'struct tx_inst_power'. This
follows commit b2090d93d4b6 ("wifi: brcmsmac: remove unused data type").

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230725162400.192357-1-dmantipov@yandex.ru
---
 .../wireless/broadcom/brcm80211/brcmsmac/phy/phy_hal.h   | 5 -----
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/types.h | 9 ---------
 2 files changed, 14 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_hal.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_hal.h
index 2e6a3d454ee87..1efc92fd16717 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_hal.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_hal.h
@@ -141,11 +141,6 @@ struct tx_power {
 	u8 target[WL_TX_POWER_RATES];
 };
 
-struct tx_inst_power {
-	u8 txpwr_est_Pout[2];   /* Latest estimate for 2.4 and 5 Ghz */
-	u8 txpwr_est_Pout_gofdm;        /* Pwr estimate for 2.4 OFDM */
-};
-
 struct brcms_chanvec {
 	u8 vec[MAXCHANNEL / NBBY];
 };
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/types.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/types.h
index 2b0df07ced744..12a0df5b4e98c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/types.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/types.h
@@ -288,15 +288,6 @@ struct tx_status;
 struct d11rxhdr;
 struct txpwr_limits;
 
-/* iovar structure */
-struct brcmu_iovar {
-	const char *name;	/* name for lookup and display */
-	u16 varid;	/* id for switch */
-	u16 flags;	/* driver-specific flag bits */
-	u16 type;	/* base type of argument */
-	u16 minlen;	/* min length for buffer vars */
-};
-
 /* brcm_msg_level is a bit vector with defs in defs.h */
 extern u32 brcm_msg_level;
 
-- 
GitLab


From 0701519fda6fe8390e48a910da4ffb0f178ca332 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Tue, 25 Jul 2023 19:23:46 +0300
Subject: [PATCH 0762/1806] wifi: brcmsmac: cleanup SCB-related data types

Drop unused and set-but-unused fields of 'struct scb_ampdu_tid_ini',
'struct scb_ampdu' and 'struct scb', as well as now unused argument
of 'brcms_c_ampdu_tx_operational()', adjust related code.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230725162400.192357-2-dmantipov@yandex.ru
---
 .../wireless/broadcom/brcm80211/brcmsmac/ampdu.c   |  6 ------
 .../broadcom/brcm80211/brcmsmac/mac80211_if.c      |  8 +++-----
 .../wireless/broadcom/brcm80211/brcmsmac/main.c    |  2 --
 .../net/wireless/broadcom/brcm80211/brcmsmac/pub.h |  2 +-
 .../net/wireless/broadcom/brcm80211/brcmsmac/scb.h | 14 --------------
 5 files changed, 4 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
index e24228e600274..e859075db716b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
@@ -476,11 +476,9 @@ static int brcms_c_ffpld_check_txfunfl(struct brcms_c_info *wlc, int fid)
 
 void
 brcms_c_ampdu_tx_operational(struct brcms_c_info *wlc, u8 tid,
-	u8 ba_wsize,		/* negotiated ba window size (in pdu) */
 	uint max_rx_ampdu_bytes) /* from ht_cap in beacon */
 {
 	struct scb_ampdu *scb_ampdu;
-	struct scb_ampdu_tid_ini *ini;
 	struct ampdu_info *ampdu = wlc->ampdu;
 	struct scb *scb = &wlc->pri_scb;
 	scb_ampdu = &scb->scb_ampdu;
@@ -491,10 +489,6 @@ brcms_c_ampdu_tx_operational(struct brcms_c_info *wlc, u8 tid,
 		return;
 	}
 
-	ini = &scb_ampdu->ini[tid];
-	ini->tid = tid;
-	ini->scb = scb_ampdu->scb;
-	ini->ba_wsize = ba_wsize;
 	scb_ampdu->max_rx_ampdu_bytes = max_rx_ampdu_bytes;
 }
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
index 0bd4e679a3594..543e93ec49d22 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
@@ -810,7 +810,6 @@ brcms_ops_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	brcms_c_init_scb(scb);
 
 	wl->pub->global_ampdu = &(scb->scb_ampdu);
-	wl->pub->global_ampdu->scb = scb;
 	wl->pub->global_ampdu->max_pdu = 16;
 
 	/*
@@ -831,7 +830,6 @@ brcms_ops_ampdu_action(struct ieee80211_hw *hw,
 	struct ieee80211_sta *sta = params->sta;
 	enum ieee80211_ampdu_mlme_action action = params->action;
 	u16 tid = params->tid;
-	u8 buf_size = params->buf_size;
 
 	if (WARN_ON(scb->magic != SCB_MAGIC))
 		return -EIDRM;
@@ -863,11 +861,11 @@ brcms_ops_ampdu_action(struct ieee80211_hw *hw,
 		/*
 		 * BA window size from ADDBA response ('buf_size') defines how
 		 * many outstanding MPDUs are allowed for the BA stream by
-		 * recipient and traffic class. 'ampdu_factor' gives maximum
-		 * AMPDU size.
+		 * recipient and traffic class (this is actually unused by the
+		 * rest of the driver). 'ampdu_factor' gives maximum AMPDU size.
 		 */
 		spin_lock_bh(&wl->lock);
-		brcms_c_ampdu_tx_operational(wl->wlc, tid, buf_size,
+		brcms_c_ampdu_tx_operational(wl->wlc, tid,
 			(1 << (IEEE80211_HT_MAX_AMPDU_FACTOR +
 			 sta->deflink.ht_cap.ampdu_factor)) - 1);
 		spin_unlock_bh(&wl->lock);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
index 11b33e78127c8..b3663c5ef3827 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
@@ -3147,10 +3147,8 @@ void brcms_c_init_scb(struct scb *scb)
 	scb->flags = SCB_WMECAP | SCB_HTCAP;
 	for (i = 0; i < NUMPRIO; i++) {
 		scb->seqnum[i] = 0;
-		scb->seqctl[i] = 0xFFFF;
 	}
 
-	scb->seqctl_nonqos = 0xFFFF;
 	scb->magic = SCB_MAGIC;
 }
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/pub.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/pub.h
index 4da38cb4f3185..bfc63b2f0537f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/pub.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/pub.h
@@ -297,7 +297,7 @@ struct brcms_pub *brcms_c_pub(struct brcms_c_info *wlc);
 void brcms_c_ampdu_flush(struct brcms_c_info *wlc, struct ieee80211_sta *sta,
 			 u16 tid);
 void brcms_c_ampdu_tx_operational(struct brcms_c_info *wlc, u8 tid,
-				  u8 ba_wsize, uint max_rx_ampdu_bytes);
+				  uint max_rx_ampdu_bytes);
 int brcms_c_module_register(struct brcms_pub *pub, const char *name,
 			    struct brcms_info *hdl,
 			    int (*down_fn)(void *handle));
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/scb.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/scb.h
index 3a3d73699f83a..d65561227da00 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/scb.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/scb.h
@@ -36,19 +36,13 @@
 
 /* structure to store per-tid state for the ampdu initiator */
 struct scb_ampdu_tid_ini {
-	u8 tid;		  /* initiator tid for easy lookup */
 	/* tx retry count; indexed by seq modulo */
 	u8 txretry[AMPDU_TX_BA_MAX_WSIZE];
-	struct scb *scb;  /* backptr for easy lookup */
-	u8 ba_wsize;	  /* negotiated ba window size (in pdu) */
 };
 
 struct scb_ampdu {
-	struct scb *scb;	/* back pointer for easy reference */
-	u8 mpdu_density;	/* mpdu density */
 	u8 max_pdu;		/* max pdus allowed in ampdu */
 	u8 release;		/* # of mpdus released at a time */
-	u16 min_len;		/* min mpdu len to support the density */
 	u32 max_rx_ampdu_bytes;	/* max ampdu rcv length; 8k, 16k, 32k, 64k */
 
 	/*
@@ -64,15 +58,7 @@ struct scb_ampdu {
 struct scb {
 	u32 magic;
 	u32 flags;	/* various bit flags as defined below */
-	u32 flags2;	/* various bit flags2 as defined below */
-	u8 state;	/* current state bitfield of auth/assoc process */
-	u8 ea[ETH_ALEN];	/* station address */
-	uint fragresid[NUMPRIO];/* #bytes unused in frag buffer per prio */
-
 	u16 seqctl[NUMPRIO];	/* seqctl of last received frame (for dups) */
-	/* seqctl of last received frame (for dups) for non-QoS data and
-	 * management */
-	u16 seqctl_nonqos;
 	u16 seqnum[NUMPRIO];/* WME: driver maintained sw seqnum per priority */
 
 	struct scb_ampdu scb_ampdu;	/* AMPDU state including per tid info */
-- 
GitLab


From 288c63d5cb4667a51a04668b3e2bb0ea499bc5f4 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Mon, 31 Jul 2023 10:43:07 +0300
Subject: [PATCH 0763/1806] wifi: mwifiex: fix error recovery in PCIE buffer
 descriptor management

Add missing 'kfree_skb()' in 'mwifiex_init_rxq_ring()' and never do
'kfree(card->rxbd_ring_vbase)' because this area is DMAed and should
be released with 'dma_free_coherent()'. The latter is performed in
'mwifiex_pcie_delete_rxbd_ring()', which is now called to recover
from possible errors in 'mwifiex_pcie_create_rxbd_ring()'. Likewise
for 'mwifiex_pcie_init_evt_ring()', 'kfree(card->evtbd_ring_vbase)'
'mwifiex_pcie_delete_evtbd_ring()' and 'mwifiex_pcie_create_rxbd_ring()'.

Fixes: d930faee141b ("mwifiex: add support for Marvell pcie8766 chipset")
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230731074334.56463-1-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/pcie.c | 25 ++++++++++++++-------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c
index 9a698a16a8f38..6697132ecc977 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.c
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.c
@@ -189,6 +189,8 @@ static int mwifiex_pcie_probe_of(struct device *dev)
 }
 
 static void mwifiex_pcie_work(struct work_struct *work);
+static int mwifiex_pcie_delete_rxbd_ring(struct mwifiex_adapter *adapter);
+static int mwifiex_pcie_delete_evtbd_ring(struct mwifiex_adapter *adapter);
 
 static int
 mwifiex_map_pci_memory(struct mwifiex_adapter *adapter, struct sk_buff *skb,
@@ -792,14 +794,15 @@ static int mwifiex_init_rxq_ring(struct mwifiex_adapter *adapter)
 		if (!skb) {
 			mwifiex_dbg(adapter, ERROR,
 				    "Unable to allocate skb for RX ring.\n");
-			kfree(card->rxbd_ring_vbase);
 			return -ENOMEM;
 		}
 
 		if (mwifiex_map_pci_memory(adapter, skb,
 					   MWIFIEX_RX_DATA_BUF_SIZE,
-					   DMA_FROM_DEVICE))
-			return -1;
+					   DMA_FROM_DEVICE)) {
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
 
 		buf_pa = MWIFIEX_SKB_DMA_ADDR(skb);
 
@@ -849,7 +852,6 @@ static int mwifiex_pcie_init_evt_ring(struct mwifiex_adapter *adapter)
 		if (!skb) {
 			mwifiex_dbg(adapter, ERROR,
 				    "Unable to allocate skb for EVENT buf.\n");
-			kfree(card->evtbd_ring_vbase);
 			return -ENOMEM;
 		}
 		skb_put(skb, MAX_EVENT_SIZE);
@@ -857,8 +859,7 @@ static int mwifiex_pcie_init_evt_ring(struct mwifiex_adapter *adapter)
 		if (mwifiex_map_pci_memory(adapter, skb, MAX_EVENT_SIZE,
 					   DMA_FROM_DEVICE)) {
 			kfree_skb(skb);
-			kfree(card->evtbd_ring_vbase);
-			return -1;
+			return -ENOMEM;
 		}
 
 		buf_pa = MWIFIEX_SKB_DMA_ADDR(skb);
@@ -1058,6 +1059,7 @@ static int mwifiex_pcie_delete_txbd_ring(struct mwifiex_adapter *adapter)
  */
 static int mwifiex_pcie_create_rxbd_ring(struct mwifiex_adapter *adapter)
 {
+	int ret;
 	struct pcie_service_card *card = adapter->card;
 	const struct mwifiex_pcie_card_reg *reg = card->pcie.reg;
 
@@ -1096,7 +1098,10 @@ static int mwifiex_pcie_create_rxbd_ring(struct mwifiex_adapter *adapter)
 		    (u32)((u64)card->rxbd_ring_pbase >> 32),
 		    card->rxbd_ring_size);
 
-	return mwifiex_init_rxq_ring(adapter);
+	ret = mwifiex_init_rxq_ring(adapter);
+	if (ret)
+		mwifiex_pcie_delete_rxbd_ring(adapter);
+	return ret;
 }
 
 /*
@@ -1127,6 +1132,7 @@ static int mwifiex_pcie_delete_rxbd_ring(struct mwifiex_adapter *adapter)
  */
 static int mwifiex_pcie_create_evtbd_ring(struct mwifiex_adapter *adapter)
 {
+	int ret;
 	struct pcie_service_card *card = adapter->card;
 	const struct mwifiex_pcie_card_reg *reg = card->pcie.reg;
 
@@ -1161,7 +1167,10 @@ static int mwifiex_pcie_create_evtbd_ring(struct mwifiex_adapter *adapter)
 		    (u32)((u64)card->evtbd_ring_pbase >> 32),
 		    card->evtbd_ring_size);
 
-	return mwifiex_pcie_init_evt_ring(adapter);
+	ret = mwifiex_pcie_init_evt_ring(adapter);
+	if (ret)
+		mwifiex_pcie_delete_evtbd_ring(adapter);
+	return ret;
 }
 
 /*
-- 
GitLab


From bd60438eeb1ebe9415b157398083b4910c7f0aa3 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 31 Jul 2023 14:08:09 -0400
Subject: [PATCH 0764/1806] selftests/net: report rcv_mss in tcp_mmap

tcp_mmap tests TCP_ZEROCOPY_RECEIVE. If 0% of data is received using
mmap, this may be due to mss. Report rcv_mss to identify this cause.

Output of a run failed due to too small mss:

    received 32768 MB (0 % mmap'ed) in 8.40458 s, 32.7057 Gbit
      cpu usage user:0.027922 sys:8.21126, 251.44 usec per MB, 3252 c-switches, rcv_mss 1428

Output on a successful run:

    received 32768 MB (99.9507 % mmap'ed) in 4.69023 s, 58.6064 Gbit
      cpu usage user:0.029172 sys:2.56105, 79.0473 usec per MB, 57591 c-switches, rcv_mss 4096

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tcp_mmap.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 6e59b1461dcce..4fcce5150850d 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -153,6 +153,19 @@ static void *mmap_large_buffer(size_t need, size_t *allocated)
 	return buffer;
 }
 
+static uint32_t tcp_info_get_rcv_mss(int fd)
+{
+	socklen_t sz = sizeof(struct tcp_info);
+	struct tcp_info info;
+
+	if (getsockopt(fd, IPPROTO_TCP, TCP_INFO, &info, &sz)) {
+		fprintf(stderr, "Error fetching TCP_INFO\n");
+		return 0;
+	}
+
+	return info.tcpi_rcv_mss;
+}
+
 void *child_thread(void *arg)
 {
 	unsigned char digest[SHA256_DIGEST_LENGTH];
@@ -288,7 +301,7 @@ end:
 		total_usec = 1000000*ru.ru_utime.tv_sec + ru.ru_utime.tv_usec +
 			     1000000*ru.ru_stime.tv_sec + ru.ru_stime.tv_usec;
 		printf("received %lg MB (%lg %% mmap'ed) in %lg s, %lg Gbit\n"
-		       "  cpu usage user:%lg sys:%lg, %lg usec per MB, %lu c-switches\n",
+		       "  cpu usage user:%lg sys:%lg, %lg usec per MB, %lu c-switches, rcv_mss %u\n",
 				total / (1024.0 * 1024.0),
 				100.0*total_mmap/total,
 				(double)delta_usec / 1000000.0,
@@ -296,7 +309,8 @@ end:
 				(double)ru.ru_utime.tv_sec + (double)ru.ru_utime.tv_usec / 1000000.0,
 				(double)ru.ru_stime.tv_sec + (double)ru.ru_stime.tv_usec / 1000000.0,
 				(double)total_usec/mb,
-				ru.ru_nvcsw);
+				ru.ru_nvcsw,
+				tcp_info_get_rcv_mss(fd));
 	}
 error:
 	munmap(buffer, buffer_sz);
-- 
GitLab


From 34093c9fa05df24558d1e2c5d32f7f93b2c97ee9 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Tue, 1 Aug 2023 08:50:41 +0800
Subject: [PATCH 0765/1806] net: Remove duplicated include in mac.c

./drivers/net/ethernet/freescale/fman/mac.c: linux/of_platform.h is included more than once.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=6039
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fman/mac.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index b6c7c4c0b367d..9767586b4eb32 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -12,7 +12,6 @@
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
 #include <linux/device.h>
-#include <linux/of_platform.h>
 #include <linux/phy.h>
 #include <linux/netdevice.h>
 #include <linux/phy_fixed.h>
-- 
GitLab


From 72c8caf904aed2caed5d6e75233294b6159ddb5d Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Wed, 26 Jul 2023 10:16:24 +0530
Subject: [PATCH 0766/1806] wifi: ath11k: fix band selection for ppdu received
 in channel 177 of 5 GHz

5 GHz band channel 177 support was added with the commit e5e94d10c856 ("wifi:
ath11k: add channel 177 into 5 GHz channel list"). However, during processing
for the received ppdu in ath11k_dp_rx_h_ppdu(), channel number is checked only
till 173. This leads to driver code checking for channel and then fetching the
band from it which is extra effort since firmware has already given the channel
number in the metadata.

Fix this issue by checking the channel number till 177 since we support
it now.

Found via code review. Compile tested only.

Fixes: e5e94d10c856 ("wifi: ath11k: add channel 177 into 5 GHz channel list")
Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230726044624.20507-1-quic_adisi@quicinc.com
---
 drivers/net/wireless/ath/ath11k/dp_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 5c76664ba0dd9..1e488eed282b5 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -2408,7 +2408,7 @@ static void ath11k_dp_rx_h_ppdu(struct ath11k *ar, struct hal_rx_desc *rx_desc,
 		rx_status->freq = center_freq;
 	} else if (channel_num >= 1 && channel_num <= 14) {
 		rx_status->band = NL80211_BAND_2GHZ;
-	} else if (channel_num >= 36 && channel_num <= 173) {
+	} else if (channel_num >= 36 && channel_num <= 177) {
 		rx_status->band = NL80211_BAND_5GHZ;
 	} else {
 		spin_lock_bh(&ar->data_lock);
-- 
GitLab


From 6f092c98dcfa1e4cf37d45f9b8e4d4a3cbeb79d4 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 26 Jul 2023 12:21:02 +0300
Subject: [PATCH 0767/1806] wifi: ath11k: simplify
 ath11k_mac_validate_vht_he_fixed_rate_settings()

In ath11k_mac_validate_vht_he_fixed_rate_settings() ar->ab->peers
list is not altered so list_for_each_entry() should be safe.

Compile tested only.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230726092113.78794-1-dmantipov@yandex.ru
---
 drivers/net/wireless/ath/ath11k/mac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 8c77ade49437f..2aadf2c387b62 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -8255,7 +8255,7 @@ ath11k_mac_validate_vht_he_fixed_rate_settings(struct ath11k *ar, enum nl80211_b
 					       const struct cfg80211_bitrate_mask *mask)
 {
 	bool he_fixed_rate = false, vht_fixed_rate = false;
-	struct ath11k_peer *peer, *tmp;
+	struct ath11k_peer *peer;
 	const u16 *vht_mcs_mask, *he_mcs_mask;
 	struct ieee80211_link_sta *deflink;
 	u8 vht_nss, he_nss;
@@ -8278,7 +8278,7 @@ ath11k_mac_validate_vht_he_fixed_rate_settings(struct ath11k *ar, enum nl80211_b
 
 	rcu_read_lock();
 	spin_lock_bh(&ar->ab->base_lock);
-	list_for_each_entry_safe(peer, tmp, &ar->ab->peers, list) {
+	list_for_each_entry(peer, &ar->ab->peers, list) {
 		if (peer->sta) {
 			deflink = &peer->sta->deflink;
 
-- 
GitLab


From 011e5a3052a22d3758d17442bf0c04c68bf79bea Mon Sep 17 00:00:00 2001
From: Seevalamuthu Mariappan <quic_seevalam@quicinc.com>
Date: Wed, 26 Jul 2023 19:40:30 +0530
Subject: [PATCH 0768/1806] wifi: ath11k: Split coldboot calibration hw_param

QCN9074 enables coldboot calibration only in Factory Test Mode (FTM).
Hence, split cold_boot_calib to two hw_params for mission and FTM
mode.

Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1

Signed-off-by: Seevalamuthu Mariappan <quic_seevalam@quicinc.com>
Signed-off-by: Raj Kumar Bhagat <quic_rajkbhag@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230726141032.3061-2-quic_rajkbhag@quicinc.com
---
 drivers/net/wireless/ath/ath11k/ahb.c  |  3 +--
 drivers/net/wireless/ath/ath11k/core.c | 36 ++++++++++++++++++++------
 drivers/net/wireless/ath/ath11k/core.h |  1 +
 drivers/net/wireless/ath/ath11k/hw.h   |  3 ++-
 drivers/net/wireless/ath/ath11k/qmi.c  |  6 ++---
 5 files changed, 35 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index 1cebba7889d78..56aea2bc97871 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -423,8 +423,7 @@ static int ath11k_ahb_fwreset_from_cold_boot(struct ath11k_base *ab)
 {
 	int timeout;
 
-	if (ath11k_cold_boot_cal == 0 || ab->qmi.cal_done ||
-	    ab->hw_params.cold_boot_calib == 0 ||
+	if (!ath11k_core_coldboot_cal_support(ab) || ab->qmi.cal_done ||
 	    ab->hw_params.cbcal_restart_fw == 0)
 		return 0;
 
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index bebfd342e28b2..d5bf2896d8c59 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -86,7 +86,8 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_shadow_regs = false,
 		.idle_ps = false,
 		.supports_sta_ps = false,
-		.cold_boot_calib = true,
+		.coldboot_cal_mm = true,
+		.coldboot_cal_ftm = true,
 		.cbcal_restart_fw = true,
 		.fw_mem_mode = 0,
 		.num_vdevs = 16 + 1,
@@ -167,7 +168,8 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_shadow_regs = false,
 		.idle_ps = false,
 		.supports_sta_ps = false,
-		.cold_boot_calib = true,
+		.coldboot_cal_mm = true,
+		.coldboot_cal_ftm = true,
 		.cbcal_restart_fw = true,
 		.fw_mem_mode = 0,
 		.num_vdevs = 16 + 1,
@@ -248,7 +250,8 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_shadow_regs = true,
 		.idle_ps = true,
 		.supports_sta_ps = true,
-		.cold_boot_calib = false,
+		.coldboot_cal_mm = false,
+		.coldboot_cal_ftm = false,
 		.cbcal_restart_fw = false,
 		.fw_mem_mode = 0,
 		.num_vdevs = 16 + 1,
@@ -332,7 +335,8 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_shadow_regs = false,
 		.idle_ps = false,
 		.supports_sta_ps = false,
-		.cold_boot_calib = false,
+		.coldboot_cal_mm = false,
+		.coldboot_cal_ftm = false,
 		.cbcal_restart_fw = false,
 		.fw_mem_mode = 2,
 		.num_vdevs = 8,
@@ -413,7 +417,8 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_shadow_regs = true,
 		.idle_ps = true,
 		.supports_sta_ps = true,
-		.cold_boot_calib = false,
+		.coldboot_cal_mm = false,
+		.coldboot_cal_ftm = false,
 		.cbcal_restart_fw = false,
 		.fw_mem_mode = 0,
 		.num_vdevs = 16 + 1,
@@ -495,7 +500,8 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_shadow_regs = true,
 		.idle_ps = true,
 		.supports_sta_ps = true,
-		.cold_boot_calib = false,
+		.coldboot_cal_mm = false,
+		.coldboot_cal_ftm = false,
 		.cbcal_restart_fw = false,
 		.fw_mem_mode = 0,
 		.num_vdevs = 16 + 1,
@@ -578,7 +584,8 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_shadow_regs = true,
 		.idle_ps = true,
 		.supports_sta_ps = true,
-		.cold_boot_calib = true,
+		.coldboot_cal_mm = true,
+		.coldboot_cal_ftm = true,
 		.cbcal_restart_fw = false,
 		.fw_mem_mode = 0,
 		.num_vdevs = 16 + 1,
@@ -667,7 +674,8 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = false,
 		.hal_params = &ath11k_hw_hal_params_ipq8074,
 		.single_pdev_only = false,
-		.cold_boot_calib = true,
+		.coldboot_cal_mm = true,
+		.coldboot_cal_ftm = true,
 		.cbcal_restart_fw = true,
 		.fix_l1ss = true,
 		.supports_dynamic_smps_6ghz = false,
@@ -749,6 +757,18 @@ void ath11k_fw_stats_free(struct ath11k_fw_stats *stats)
 	ath11k_fw_stats_bcn_free(&stats->bcn);
 }
 
+bool ath11k_core_coldboot_cal_support(struct ath11k_base *ab)
+{
+	if (!ath11k_cold_boot_cal)
+		return false;
+
+	if (ath11k_ftm_mode)
+		return ab->hw_params.coldboot_cal_ftm;
+
+	else
+		return ab->hw_params.coldboot_cal_mm;
+}
+
 int ath11k_core_suspend(struct ath11k_base *ab)
 {
 	int ret;
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 9d15b4390b9c8..b044477624837 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -1186,6 +1186,7 @@ void ath11k_core_halt(struct ath11k *ar);
 int ath11k_core_resume(struct ath11k_base *ab);
 int ath11k_core_suspend(struct ath11k_base *ab);
 void ath11k_core_pre_reconfigure_recovery(struct ath11k_base *ab);
+bool ath11k_core_coldboot_cal_support(struct ath11k_base *ab);
 
 const struct firmware *ath11k_core_firmware_request(struct ath11k_base *ab,
 						    const char *filename);
diff --git a/drivers/net/wireless/ath/ath11k/hw.h b/drivers/net/wireless/ath/ath11k/hw.h
index f5533630a7f9d..d51a99669dd6e 100644
--- a/drivers/net/wireless/ath/ath11k/hw.h
+++ b/drivers/net/wireless/ath/ath11k/hw.h
@@ -187,7 +187,8 @@ struct ath11k_hw_params {
 	bool supports_shadow_regs;
 	bool idle_ps;
 	bool supports_sta_ps;
-	bool cold_boot_calib;
+	bool coldboot_cal_mm;
+	bool coldboot_cal_ftm;
 	bool cbcal_restart_fw;
 	int fw_mem_mode;
 	u32 num_vdevs;
diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index d4eaf7d2ba841..91a214caa8b50 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -2079,7 +2079,7 @@ static int ath11k_qmi_assign_target_mem_chunk(struct ath11k_base *ab)
 				return -EINVAL;
 			}
 
-			if (ath11k_cold_boot_cal && ab->hw_params.cold_boot_calib) {
+			if (ath11k_core_coldboot_cal_support(ab)) {
 				if (hremote_node) {
 					ab->qmi.target_mem[idx].paddr =
 							res.start + host_ddr_sz;
@@ -3209,8 +3209,8 @@ static void ath11k_qmi_driver_event_work(struct work_struct *work)
 				break;
 			}
 
-			if (ath11k_cold_boot_cal && ab->qmi.cal_done == 0 &&
-			    ab->hw_params.cold_boot_calib) {
+			if (ab->qmi.cal_done == 0 &&
+			    ath11k_core_coldboot_cal_support(ab)) {
 				ath11k_qmi_process_coldboot_calibration(ab);
 			} else {
 				clear_bit(ATH11K_FLAG_CRASH_FLUSH,
-- 
GitLab


From bdfc967bf5fcd762473a01d39edb81f1165ba290 Mon Sep 17 00:00:00 2001
From: Anilkumar Kolli <quic_akolli@quicinc.com>
Date: Wed, 26 Jul 2023 19:40:31 +0530
Subject: [PATCH 0769/1806] wifi: ath11k: Add coldboot calibration support for
 QCN9074

QCN9074 supports 6 GHz, which has increased number of channels
compared to 5 GHz/2 GHz. So, to support coldboot calibration in
QCN9074 ATH11K_COLD_BOOT_FW_RESET_DELAY extended to 60 seconds. To
avoid code redundancy, fwreset_from_cold_boot moved to QMI and made
common for both ahb and pci. Coldboot calibration is enabled only in
FTM mode for QCN9074. QCN9074 requires firmware restart after coldboot,
hence enable cbcal_restart_fw in hw_params.

This support can be enabled/disabled using hw params for different
hardware. Currently it is not enabled for QCA6390.

Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1

Signed-off-by: Anilkumar Kolli <quic_akolli@quicinc.com>
Signed-off-by: Seevalamuthu Mariappan <quic_seevalam@quicinc.com>
Signed-off-by: Raj Kumar Bhagat <quic_rajkbhag@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230726141032.3061-3-quic_rajkbhag@quicinc.com
---
 drivers/net/wireless/ath/ath11k/ahb.c  | 28 ++------------------------
 drivers/net/wireless/ath/ath11k/core.c |  4 ++--
 drivers/net/wireless/ath/ath11k/pci.c  |  2 ++
 drivers/net/wireless/ath/ath11k/qmi.c  | 28 ++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath11k/qmi.h  |  3 ++-
 5 files changed, 36 insertions(+), 29 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index 56aea2bc97871..b0a40970bada7 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -14,6 +14,7 @@
 #include "ahb.h"
 #include "debug.h"
 #include "hif.h"
+#include "qmi.h"
 #include <linux/remoteproc.h>
 #include "pcic.h"
 #include <linux/soc/qcom/smem.h>
@@ -419,31 +420,6 @@ static void ath11k_ahb_power_down(struct ath11k_base *ab)
 	rproc_shutdown(ab_ahb->tgt_rproc);
 }
 
-static int ath11k_ahb_fwreset_from_cold_boot(struct ath11k_base *ab)
-{
-	int timeout;
-
-	if (!ath11k_core_coldboot_cal_support(ab) || ab->qmi.cal_done ||
-	    ab->hw_params.cbcal_restart_fw == 0)
-		return 0;
-
-	ath11k_dbg(ab, ATH11K_DBG_AHB, "wait for cold boot done\n");
-	timeout = wait_event_timeout(ab->qmi.cold_boot_waitq,
-				     (ab->qmi.cal_done  == 1),
-				     ATH11K_COLD_BOOT_FW_RESET_DELAY);
-	if (timeout <= 0) {
-		ath11k_cold_boot_cal = 0;
-		ath11k_warn(ab, "Coldboot Calibration failed timed out\n");
-	}
-
-	/* reset the firmware */
-	ath11k_ahb_power_down(ab);
-	ath11k_ahb_power_up(ab);
-
-	ath11k_dbg(ab, ATH11K_DBG_AHB, "exited from cold boot mode\n");
-	return 0;
-}
-
 static void ath11k_ahb_init_qmi_ce_config(struct ath11k_base *ab)
 {
 	struct ath11k_qmi_ce_cfg *cfg = &ab->qmi.ce_cfg;
@@ -1226,7 +1202,7 @@ static int ath11k_ahb_probe(struct platform_device *pdev)
 		goto err_ce_free;
 	}
 
-	ath11k_ahb_fwreset_from_cold_boot(ab);
+	ath11k_qmi_fwreset_from_cold_boot(ab);
 
 	return 0;
 
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index d5bf2896d8c59..fc7c4564a715c 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -336,8 +336,8 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.idle_ps = false,
 		.supports_sta_ps = false,
 		.coldboot_cal_mm = false,
-		.coldboot_cal_ftm = false,
-		.cbcal_restart_fw = false,
+		.coldboot_cal_ftm = true,
+		.cbcal_restart_fw = true,
 		.fw_mem_mode = 2,
 		.num_vdevs = 8,
 		.num_peers = 128,
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index 79e2cbe826384..5fd08ffc2a9f6 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -15,6 +15,7 @@
 #include "mhi.h"
 #include "debug.h"
 #include "pcic.h"
+#include "qmi.h"
 
 #define ATH11K_PCI_BAR_NUM		0
 #define ATH11K_PCI_DMA_MASK		32
@@ -897,6 +898,7 @@ unsupported_wcn6855_soc:
 		ath11k_err(ab, "failed to init core: %d\n", ret);
 		goto err_irq_affinity_cleanup;
 	}
+	ath11k_qmi_fwreset_from_cold_boot(ab);
 	return 0;
 
 err_irq_affinity_cleanup:
diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index 91a214caa8b50..c4eab5d7f5c56 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -9,6 +9,7 @@
 #include "qmi.h"
 #include "core.h"
 #include "debug.h"
+#include "hif.h"
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/ioport.h>
@@ -2839,6 +2840,33 @@ int ath11k_qmi_firmware_start(struct ath11k_base *ab,
 	return 0;
 }
 
+int ath11k_qmi_fwreset_from_cold_boot(struct ath11k_base *ab)
+{
+	int timeout;
+
+	if (!ath11k_core_coldboot_cal_support(ab) || ab->qmi.cal_done ||
+	    ab->hw_params.cbcal_restart_fw == 0)
+		return 0;
+
+	ath11k_dbg(ab, ATH11K_DBG_QMI, "wait for cold boot done\n");
+
+	timeout = wait_event_timeout(ab->qmi.cold_boot_waitq,
+				     (ab->qmi.cal_done == 1),
+				     ATH11K_COLD_BOOT_FW_RESET_DELAY);
+
+	if (timeout <= 0) {
+		ath11k_warn(ab, "Coldboot Calibration timed out\n");
+		return -ETIMEDOUT;
+	}
+
+	/* reset the firmware */
+	ath11k_hif_power_down(ab);
+	ath11k_hif_power_up(ab);
+	ath11k_dbg(ab, ATH11K_DBG_QMI, "exit wait for cold boot done\n");
+	return 0;
+}
+EXPORT_SYMBOL(ath11k_qmi_fwreset_from_cold_boot);
+
 static int ath11k_qmi_process_coldboot_calibration(struct ath11k_base *ab)
 {
 	int timeout;
diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h
index 0909d53cefebc..b0407abf90cd9 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.h
+++ b/drivers/net/wireless/ath/ath11k/qmi.h
@@ -37,7 +37,7 @@
 
 #define QMI_WLANFW_MAX_DATA_SIZE_V01		6144
 #define ATH11K_FIRMWARE_MODE_OFF		4
-#define ATH11K_COLD_BOOT_FW_RESET_DELAY		(40 * HZ)
+#define ATH11K_COLD_BOOT_FW_RESET_DELAY		(60 * HZ)
 
 #define ATH11K_QMI_DEVICE_BAR_SIZE		0x200000
 
@@ -519,5 +519,6 @@ void ath11k_qmi_msg_recv_work(struct work_struct *work);
 void ath11k_qmi_deinit_service(struct ath11k_base *ab);
 int ath11k_qmi_init_service(struct ath11k_base *ab);
 void ath11k_qmi_free_resource(struct ath11k_base *ab);
+int ath11k_qmi_fwreset_from_cold_boot(struct ath11k_base *ab);
 
 #endif
-- 
GitLab


From 13329d0cb7212b058bd8451a99d215a8f97645ea Mon Sep 17 00:00:00 2001
From: Seevalamuthu Mariappan <quic_seevalam@quicinc.com>
Date: Wed, 26 Jul 2023 19:40:32 +0530
Subject: [PATCH 0770/1806] wifi: ath11k: Remove cal_done check during probe

In some race conditions, calibration done QMI message is received even
before host wait starts for calibration to be done.
Due to this, resetting firmware was not performed after calibration.

Hence, remove cal_done check in ath11k_qmi_fwreset_from_cold_boot()
as this is called only from probe.

Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1

Signed-off-by: Seevalamuthu Mariappan <quic_seevalam@quicinc.com>
Signed-off-by: Raj Kumar Bhagat <quic_rajkbhag@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230726141032.3061-4-quic_rajkbhag@quicinc.com
---
 drivers/net/wireless/ath/ath11k/qmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index c4eab5d7f5c56..617abb441882b 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -2844,7 +2844,7 @@ int ath11k_qmi_fwreset_from_cold_boot(struct ath11k_base *ab)
 {
 	int timeout;
 
-	if (!ath11k_core_coldboot_cal_support(ab) || ab->qmi.cal_done ||
+	if (!ath11k_core_coldboot_cal_support(ab) ||
 	    ab->hw_params.cbcal_restart_fw == 0)
 		return 0;
 
-- 
GitLab


From 8ad314da54c6dd223a6b6cc85019160aa842f659 Mon Sep 17 00:00:00 2001
From: Wen Gong <quic_wgong@quicinc.com>
Date: Wed, 26 Jul 2023 05:26:25 -0400
Subject: [PATCH 0771/1806] wifi: ath12k: Fix a NULL pointer dereference in
 ath12k_mac_op_hw_scan()

In ath12k_mac_op_hw_scan(), the return value of kzalloc() is directly
used in memcpy(), which may lead to a NULL pointer dereference on
failure of kzalloc().

Fix this bug by adding a check of arg.extraie.ptr.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230726092625.3350-1-quic_wgong@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 1bb9802ef5696..af46b63bb15bc 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -2755,9 +2755,12 @@ static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw,
 	arg.scan_id = ATH12K_SCAN_ID;
 
 	if (req->ie_len) {
+		arg.extraie.ptr = kmemdup(req->ie, req->ie_len, GFP_KERNEL);
+		if (!arg.extraie.ptr) {
+			ret = -ENOMEM;
+			goto exit;
+		}
 		arg.extraie.len = req->ie_len;
-		arg.extraie.ptr = kzalloc(req->ie_len, GFP_KERNEL);
-		memcpy(arg.extraie.ptr, req->ie, req->ie_len);
 	}
 
 	if (req->n_ssids) {
-- 
GitLab


From 15c8441dc1eddb9a19c75a0742edc9f002625931 Mon Sep 17 00:00:00 2001
From: Wen Gong <quic_wgong@quicinc.com>
Date: Wed, 26 Jul 2023 05:38:57 -0400
Subject: [PATCH 0772/1806] wifi: ath12k: correct the data_type from
 QMI_OPT_FLAG to QMI_UNSIGNED_1_BYTE for mlo_capable

Currently, the encoding rule for field mlo_capable in struct
qmi_wlanfw_host_cap_req_msg_v01 defined in array
qmi_wlanfw_host_cap_req_msg_v01_ei uses type QMI_OPT_FLAG.

Unfortunately, all ath12k firmware actually expects this field to be of
type NON QMI_OPT_FLAG such as QMI_UNSIGNED_1_BYTE/QMI_UNSIGNED_8_BYTE...
And as a result, firmware is unable to correctly decode the mlo_capable
field.

Change the ath12k definition as QMI_UNSIGNED_1_BYTE to match the firmware
definition so that firmware can correctly parse the mlo_capable info from
message QMI_WLANFW_HOST_CAP_REQ_V01 at wlan load time.

This is just an accidental typo and that both WCN7850 and QCN9274 firmwares
use QMI_UNSIGNED_1_BYTE.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230726093857.3610-1-quic_wgong@quicinc.com
---
 drivers/net/wireless/ath/ath12k/qmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
index b510c2de1bd43..b2db0436bdde6 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.c
+++ b/drivers/net/wireless/ath/ath12k/qmi.c
@@ -387,7 +387,7 @@ static struct qmi_elem_info qmi_wlanfw_host_cap_req_msg_v01_ei[] = {
 					   mlo_capable_valid),
 	},
 	{
-		.data_type	= QMI_OPT_FLAG,
+		.data_type	= QMI_UNSIGNED_1_BYTE,
 		.elem_len	= 1,
 		.elem_size	= sizeof(u8),
 		.array_type	= NO_ARRAY,
-- 
GitLab


From 603cf6c2fcdcbc38f1daa316794e7268852677a7 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 3 Jul 2023 14:37:29 +0200
Subject: [PATCH 0773/1806] wifi: ath12k: fix memcpy array overflow in
 ath12k_peer_assoc_h_he()

Two memory copies in this function copy from a short array into a longer one,
using the wrong size, which leads to an out-of-bounds access:

include/linux/fortify-string.h:592:4: error: call to '__read_overflow2_field' declared with 'warning' attribute: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror,-Wattribute-warning]
                        __read_overflow2_field(q_size_field, size);
                        ^
include/linux/fortify-string.h:592:4: error: call to '__read_overflow2_field' declared with 'warning' attribute: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror,-Wattribute-warning]
2 errors generated.

Fixes: d889913205cf7 ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230703123737.3420464-1-arnd@kernel.org
---
 drivers/net/wireless/ath/ath12k/mac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index af46b63bb15bc..d165b24094ad5 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -1637,9 +1637,9 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar,
 	arg->peer_nss = min(sta->deflink.rx_nss, max_nss);
 
 	memcpy(&arg->peer_he_cap_macinfo, he_cap->he_cap_elem.mac_cap_info,
-	       sizeof(arg->peer_he_cap_macinfo));
+	       sizeof(he_cap->he_cap_elem.mac_cap_info));
 	memcpy(&arg->peer_he_cap_phyinfo, he_cap->he_cap_elem.phy_cap_info,
-	       sizeof(arg->peer_he_cap_phyinfo));
+	       sizeof(he_cap->he_cap_elem.phy_cap_info));
 	arg->peer_he_ops = vif->bss_conf.he_oper.params;
 
 	/* the top most byte is used to indicate BSS color info */
-- 
GitLab


From 1e9b1363e2de1552ee4e3d74ac8bb43a194f1cb4 Mon Sep 17 00:00:00 2001
From: Wen Gong <quic_wgong@quicinc.com>
Date: Fri, 14 Jul 2023 03:24:05 -0400
Subject: [PATCH 0774/1806] wifi: ath12k: avoid array overflow of hw mode for
 preferred_hw_mode

Currently ath12k define WMI_HOST_HW_MODE_DBS_OR_SBS=5 as max hw mode
for enum wmi_host_hw_mode_config_type, it is also same for the array
ath12k_hw_mode_pri_map.

When tested with new version firmware/board data which support new
hw mode eMLSR mode with hw mode value 8, it leads overflow usage for
array ath12k_hw_mode_pri_map in function ath12k_wmi_hw_mode_caps(),
and then lead preferred_hw_mode changed to 8, and finally function
ath12k_pull_mac_phy_cap_svc_ready_ext() select the capability of hw
mode 8, but the capability of eMLSR mode report from firmware does
not support 2.4 GHz band for WCN7850, so finally 2.4 GHz band is
disabled.

Skip the hw mode which exceeds WMI_HOST_HW_MODE_MAX in function
ath12k_wmi_hw_mode_caps() helps to avoid array overflow, then the 2.4
GHz band will not be disabled.

This is to keep compatibility with newer version firmware/board data
files, this change is still needed after ath12k add eMLSR hw mode 8 in
array ath12k_hw_mode_pri_map and enum wmi_host_hw_mode_config_type,
because more hw mode maybe added in next firmware/board data version
e.g hw mode 9, then it will also lead new array overflow without this
change.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230714072405.28705-1-quic_wgong@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 6512267ae4ca5..e6033ab158255 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -3705,6 +3705,10 @@ static int ath12k_wmi_hw_mode_caps(struct ath12k_base *soc,
 	for (i = 0 ; i < svc_rdy_ext->n_hw_mode_caps; i++) {
 		hw_mode_caps = &svc_rdy_ext->hw_mode_caps[i];
 		mode = le32_to_cpu(hw_mode_caps->hw_mode_id);
+
+		if (mode >= WMI_HOST_HW_MODE_MAX)
+			continue;
+
 		pref = soc->wmi_ab.preferred_hw_mode;
 
 		if (ath12k_hw_mode_pri_map[mode] < ath12k_hw_mode_pri_map[pref]) {
-- 
GitLab


From 7ee027abd4533d53438ccafdd3ba7a68a16aae8d Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Fri, 14 Jul 2023 16:06:58 +0800
Subject: [PATCH 0775/1806] wifi: ath12k: Use pdev_id rather than mac_id to get
 pdev

We are seeing kernel crash in below test scenario:
 1. make DUT connect to an WPA3 encrypted 11ax AP in Ch44 HE80
 2. use "wpa_cli -i <inf> disconnect" to disconnect
 3. wait for DUT to automatically reconnect

Kernel crashes while waiting, below shows the crash stack:
[  755.120868] BUG: kernel NULL pointer dereference, address: 0000000000000000
[  755.120871] #PF: supervisor read access in kernel mode
[  755.120872] #PF: error_code(0x0000) - not-present page
[  755.120873] PGD 0 P4D 0
[  755.120875] Oops: 0000 [#1] PREEMPT SMP NOPTI
[  755.120876] CPU: 7 PID: 0 Comm: swapper/7 Kdump: loaded Not tainted 5.19.0-rc1+ #3
[  755.120878] Hardware name: Intel(R) Client Systems NUC11PHi7/NUC11PHBi7, BIOS PHTGL579.0063.2021.0707.1057 07/07/2021
[  755.120879] RIP: 0010:ath12k_dp_process_rx_err+0x2b6/0x14a0 [ath12k]
[  755.120890] Code: 01 c0 48 c1 e0 05 48 8b 9c 07 b8 b2 00 00 48 c7 c0 61 ff 0e c1 48 85 db 53 48 0f 44 c6 48 c7 c6 80 9d 0f c1 50 e8 1a 25 00 00 <4c> 8b 3b 4d 8b 76 14 41 59 41 5a 41 8b 87 78 43 01 00 4d 85 f6 89
[  755.120891] RSP: 0018:ffff9a93402c8d10 EFLAGS: 00010282
[  755.120892] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000303
[  755.120893] RDX: 0000000000000000 RSI: ffffffff93b7cbe9 RDI: 00000000ffffffff
[  755.120894] RBP: ffff9a93402c8e50 R08: ffffffff93e65360 R09: ffffffff942e044d
[  755.120894] R10: 0000000000000000 R11: 0000000000000063 R12: ffff8dbec5420000
[  755.120895] R13: ffff8dbec5420000 R14: ffff8dbdefe9a0a0 R15: ffff8dbec5420000
[  755.120896] FS:  0000000000000000(0000) GS:ffff8dc2705c0000(0000) knlGS:0000000000000000
[  755.120897] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  755.120898] CR2: 0000000000000000 CR3: 0000000107be4005 CR4: 0000000000770ee0
[  755.120898] PKRU: 55555554
[  755.120899] Call Trace:
[  755.120900]  <IRQ>
[  755.120903]  ? ath12k_pci_write32+0x2e/0x80 [ath12k]
[  755.120910]  ath12k_dp_service_srng+0x214/0x2e0 [ath12k]
[  755.120917]  ath12k_pci_ext_grp_napi_poll+0x26/0x80 [ath12k]
[  755.120923]  __napi_poll+0x2b/0x1c0
[  755.120925]  net_rx_action+0x2a1/0x2f0
[  755.120927]  __do_softirq+0xfa/0x2e9
[  755.120929]  irq_exit_rcu+0xb9/0xd0
[  755.120932]  common_interrupt+0xc1/0xe0
[  755.120934]  </IRQ>
[  755.120934]  <TASK>
[  755.120935]  asm_common_interrupt+0x2c/0x40
[  755.120936] RIP: 0010:cpuidle_enter_state+0xdd/0x3a0
[  755.120938] Code: 00 31 ff e8 45 e2 74 ff 80 7d d7 00 74 16 9c 58 0f 1f 40 00 f6 c4 02 0f 85 a0 02 00 00 31 ff e8 69 79 7b ff fb 0f 1f 44 00 00 <45> 85 ff 0f 88 6d 01 00 00 49 63 d7 4c 2b 6d c8 48 8d 04 52 48 8d
[  755.120939] RSP: 0018:ffff9a934018be50 EFLAGS: 00000246
[  755.120940] RAX: ffff8dc2705c0000 RBX: 0000000000000002 RCX: 000000000000001f
[  755.120941] RDX: 000000afd0b532d3 RSI: ffffffff93b7cbe9 RDI: ffffffff93b8b66e
[  755.120942] RBP: ffff9a934018be88 R08: 0000000000000002 R09: 0000000000030500
[  755.120942] R10: ffff9a934018be18 R11: 0000000000000741 R12: ffffba933fdc0600
[  755.120943] R13: 000000afd0b532d3 R14: ffffffff93fcbc60 R15: 0000000000000002
[  755.120945]  cpuidle_enter+0x2e/0x40
[  755.120946]  call_cpuidle+0x23/0x40
[  755.120948]  do_idle+0x1ff/0x260
[  755.120950]  cpu_startup_entry+0x1d/0x20
[  755.120951]  start_secondary+0x10d/0x130
[  755.120953]  secondary_startup_64_no_verify+0xd3/0xdb
[  755.120956]  </TASK>
[  755.120956] Modules linked in: michael_mic rfcomm cmac algif_hash algif_skcipher af_alg bnep qrtr_mhi intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp coretemp snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio kvm_intel qrtr snd_hda_codec_hdmi kvm irqbypass ath12k snd_hda_intel snd_seq_midi crct10dif_pclmul mhi ghash_clmulni_intel snd_intel_dspcfg snd_seq_midi_event aesni_intel qmi_helpers i915 snd_rawmidi crypto_simd snd_hda_codec cryptd cec intel_cstate snd_hda_core mac80211 rc_core nouveau snd_seq snd_hwdep btusb drm_buddy drm_ttm_helper nls_iso8859_1 snd_pcm ttm btrtl snd_seq_device wmi_bmof mxm_wmi input_leds cfg80211 joydev btbcm drm_display_helper snd_timer btintel mei_me libarc4 drm_kms_helper bluetooth i2c_algo_bit snd fb_sys_fops syscopyarea mei sysfillrect ecdh_generic soundcore sysimgblt ecc acpi_pad mac_hid sch_fq_codel ipmi_devintf ipmi_msghandler msr parport_pc ppdev lp ramoops parport reed_solomon drm efi_pstore ip_tables x_tables autofs4
[  755.120992]  hid_generic usbhid hid ax88179_178a usbnet mii nvme nvme_core rtsx_pci_sdmmc crc32_pclmul i2c_i801 intel_lpss_pci i2c_smbus intel_lpss rtsx_pci idma64 virt_dma vmd wmi video
[  755.121002] CR2: 0000000000000000

The crash is because, for WCN7850, only ab->pdev[0] is initialized, while mac_id here is
misused to retrieve pdev and it is not zero, leading to a NULL pointer access.

Fix this issue by getting pdev_id first and then use it to retrieve pdev.

Also fix some other code snippets which have the same issue.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230714080658.3140-1-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_rx.c | 11 +++++++----
 drivers/net/wireless/ath/ath12k/dp_tx.c |  8 +++++---
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index ffd9a2018610f..67f8c140840fb 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -2539,7 +2539,7 @@ static void ath12k_dp_rx_process_received_packets(struct ath12k_base *ab,
 	struct ath12k_skb_rxcb *rxcb;
 	struct sk_buff *msdu;
 	struct ath12k *ar;
-	u8 mac_id;
+	u8 mac_id, pdev_id;
 	int ret;
 
 	if (skb_queue_empty(msdu_list))
@@ -2550,8 +2550,9 @@ static void ath12k_dp_rx_process_received_packets(struct ath12k_base *ab,
 	while ((msdu = __skb_dequeue(msdu_list))) {
 		rxcb = ATH12K_SKB_RXCB(msdu);
 		mac_id = rxcb->mac_id;
-		ar = ab->pdevs[mac_id].ar;
-		if (!rcu_dereference(ab->pdevs_active[mac_id])) {
+		pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id);
+		ar = ab->pdevs[pdev_id].ar;
+		if (!rcu_dereference(ab->pdevs_active[pdev_id])) {
 			dev_kfree_skb_any(msdu);
 			continue;
 		}
@@ -3385,6 +3386,7 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi,
 	dma_addr_t paddr;
 	bool is_frag;
 	bool drop = false;
+	int pdev_id;
 
 	tot_n_bufs_reaped = 0;
 	quota = budget;
@@ -3440,7 +3442,8 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi,
 			mac_id = le32_get_bits(reo_desc->info0,
 					       HAL_REO_DEST_RING_INFO0_SRC_LINK_ID);
 
-			ar = ab->pdevs[mac_id].ar;
+			pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id);
+			ar = ab->pdevs[pdev_id].ar;
 
 			if (!ath12k_dp_process_rx_err_buf(ar, reo_desc, drop,
 							  msdu_cookies[i]))
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index d3c7c76d6b75e..d661fe586651f 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -347,6 +347,7 @@ static void ath12k_dp_tx_free_txbuf(struct ath12k_base *ab,
 {
 	struct ath12k *ar;
 	struct ath12k_skb_cb *skb_cb;
+	u8 pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id);
 
 	skb_cb = ATH12K_SKB_CB(msdu);
 
@@ -357,7 +358,7 @@ static void ath12k_dp_tx_free_txbuf(struct ath12k_base *ab,
 
 	dev_kfree_skb_any(msdu);
 
-	ar = ab->pdevs[mac_id].ar;
+	ar = ab->pdevs[pdev_id].ar;
 	if (atomic_dec_and_test(&ar->dp.num_tx_pending))
 		wake_up(&ar->dp.tx_empty_waitq);
 }
@@ -536,7 +537,7 @@ void ath12k_dp_tx_completion_handler(struct ath12k_base *ab, int ring_id)
 	struct hal_tx_status ts = { 0 };
 	struct dp_tx_ring *tx_ring = &dp->tx_ring[ring_id];
 	struct hal_wbm_release_ring *desc;
-	u8 mac_id;
+	u8 mac_id, pdev_id;
 	u64 desc_va;
 
 	spin_lock_bh(&status_ring->lock);
@@ -605,7 +606,8 @@ void ath12k_dp_tx_completion_handler(struct ath12k_base *ab, int ring_id)
 			continue;
 		}
 
-		ar = ab->pdevs[mac_id].ar;
+		pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id);
+		ar = ab->pdevs[pdev_id].ar;
 
 		if (atomic_dec_and_test(&ar->dp.num_tx_pending))
 			wake_up(&ar->dp.tx_empty_waitq);
-- 
GitLab


From 68c35cc39b41dca8f6cb54915bdfd60dd7397b01 Mon Sep 17 00:00:00 2001
From: Wen Gong <quic_wgong@quicinc.com>
Date: Fri, 14 Jul 2023 05:25:55 -0400
Subject: [PATCH 0776/1806] wifi: ath12k: trigger station disconnect on
 hardware restart

Currently after the hardware restart triggered from the driver, the
station interface connection remains intact, since a disconnect
trigger is not sent to userspace. This can lead to a problem in
targets where the wifi mac sequence is added by the firmware.

After the target restart, its wifi mac sequence number gets reset to
zero. Hence AP to which our device is connected will receive frames
with a wifi mac sequence number jump to the past, thereby resulting
in the AP dropping all these frames, until the frame arrives with a
wifi mac sequence number which AP was expecting.

To avoid such frame drops, its better to trigger a station disconnect
upon target hardware restart which can be done with API
ieee80211_reconfig_disconnect exposed to mac80211.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230714092555.2018-1-quic_wgong@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index d165b24094ad5..13f477eb4707f 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -6391,6 +6391,7 @@ ath12k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 {
 	struct ath12k *ar = hw->priv;
 	struct ath12k_base *ab = ar->ab;
+	struct ath12k_vif *arvif;
 	int recovery_count;
 
 	if (reconfig_type != IEEE80211_RECONFIG_TYPE_RESTART)
@@ -6419,6 +6420,26 @@ ath12k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 				ath12k_dbg(ab, ATH12K_DBG_BOOT, "reset success\n");
 			}
 		}
+
+		list_for_each_entry(arvif, &ar->arvifs, list) {
+			ath12k_dbg(ab, ATH12K_DBG_BOOT,
+				   "reconfig cipher %d up %d vdev type %d\n",
+				   arvif->key_cipher,
+				   arvif->is_up,
+				   arvif->vdev_type);
+			/* After trigger disconnect, then upper layer will
+			 * trigger connect again, then the PN number of
+			 * upper layer will be reset to keep up with AP
+			 * side, hence PN number mis-match will not happened.
+			 */
+			if (arvif->is_up &&
+			    arvif->vdev_type == WMI_VDEV_TYPE_STA &&
+			    arvif->vdev_subtype == WMI_VDEV_SUBTYPE_NONE) {
+				ieee80211_hw_restart_disconnect(arvif->vif);
+				ath12k_dbg(ab, ATH12K_DBG_BOOT,
+					   "restart disconnect\n");
+			}
+		}
 	}
 
 	mutex_unlock(&ar->conf_mutex);
-- 
GitLab


From 3742928a52d6859731d525f06c09decff87ffa01 Mon Sep 17 00:00:00 2001
From: Wen Gong <quic_wgong@quicinc.com>
Date: Sun, 16 Jul 2023 23:34:31 -0400
Subject: [PATCH 0777/1806] wifi: ath12k: change to use dynamic memory for
 channel list of scan

Currently there are about 60 channels for 6 GHz, then the size of
chan_list in struct scan_req_params which is 40 is not enough to
fill all the channel list of 6 GHz.

Use dynamic memory to save the channel list of scan.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230717033431.21983-1-quic_wgong@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 10 ++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h |  3 +--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 13f477eb4707f..4fa565a115e34 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -2773,6 +2773,14 @@ static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw,
 
 	if (req->n_channels) {
 		arg.num_chan = req->n_channels;
+		arg.chan_list = kcalloc(arg.num_chan, sizeof(*arg.chan_list),
+					GFP_KERNEL);
+
+		if (!arg.chan_list) {
+			ret = -ENOMEM;
+			goto exit;
+		}
+
 		for (i = 0; i < arg.num_chan; i++)
 			arg.chan_list[i] = req->channels[i]->center_freq;
 	}
@@ -2791,6 +2799,8 @@ static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw,
 						      ATH12K_MAC_SCAN_TIMEOUT_MSECS));
 
 exit:
+	kfree(arg.chan_list);
+
 	if (req->ie_len)
 		kfree(arg.extraie.ptr);
 
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index d89c12bfb009f..9b8ba87049047 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -3034,7 +3034,6 @@ enum scan_dwelltime_adaptive_mode {
 
 #define WLAN_SCAN_MAX_NUM_SSID          10
 #define WLAN_SCAN_MAX_NUM_BSSID         10
-#define WLAN_SCAN_MAX_NUM_CHANNELS      40
 
 struct ath12k_wmi_element_info_arg {
 	u32 len;
@@ -3243,7 +3242,7 @@ struct ath12k_wmi_scan_req_arg {
 	u32 num_bssid;
 	u32 num_ssids;
 	u32 n_probes;
-	u32 chan_list[WLAN_SCAN_MAX_NUM_CHANNELS];
+	u32 *chan_list;
 	u32 notify_scan_events;
 	struct cfg80211_ssid ssid[WLAN_SCAN_MAX_NUM_SSID];
 	struct ath12k_wmi_mac_addr_params bssid_list[WLAN_SCAN_MAX_NUM_BSSID];
-- 
GitLab


From ae1d60c41e581be049aa84dd53aca89027101ce1 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Mon, 31 Jul 2023 15:38:58 +0800
Subject: [PATCH 0778/1806] net: hisilicon: fix the return value handle and
 remove redundant netdev_err() for platform_get_irq()

There is no possible for platform_get_irq() to return 0
and the return value of platform_get_irq() is more sensible
to show the error reason.

And there is no need to call the netdev_err() function directly to print
a custom message when handling an error from platform_get_irq() function as
it is going to display an appropriate error message in case of a failure.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/20230731073858.3633193-1-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hip04_eth.c    | 4 ++--
 drivers/net/ethernet/hisilicon/hisi_femac.c   | 4 ++--
 drivers/net/ethernet/hisilicon/hix5hd2_gmac.c | 5 ++---
 3 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index 50c3f5d6611f0..ecf92a5d56bbf 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -960,8 +960,8 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq <= 0) {
-		ret = -EINVAL;
+	if (irq < 0) {
+		ret = irq;
 		goto init_fail;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c
index ce2571c16e431..cb7b0293fe85c 100644
--- a/drivers/net/ethernet/hisilicon/hisi_femac.c
+++ b/drivers/net/ethernet/hisilicon/hisi_femac.c
@@ -862,8 +862,8 @@ static int hisi_femac_drv_probe(struct platform_device *pdev)
 		goto out_disconnect_phy;
 
 	ndev->irq = platform_get_irq(pdev, 0);
-	if (ndev->irq <= 0) {
-		ret = -ENODEV;
+	if (ndev->irq < 0) {
+		ret = ndev->irq;
 		goto out_disconnect_phy;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
index f867e95311173..26d22bb04b879 100644
--- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -1206,9 +1206,8 @@ static int hix5hd2_dev_probe(struct platform_device *pdev)
 	}
 
 	ndev->irq = platform_get_irq(pdev, 0);
-	if (ndev->irq <= 0) {
-		netdev_err(ndev, "No irq resource\n");
-		ret = -EINVAL;
+	if (ndev->irq < 0) {
+		ret = ndev->irq;
 		goto out_phy_node;
 	}
 
-- 
GitLab


From c7606d49e6093e9a66ffd1c5dfb294a4f8836dba Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Tue, 1 Aug 2023 19:26:38 +0800
Subject: [PATCH 0779/1806] octeontx2: Remove unnecessary ternary operators

There are a little ternary operators, the true or false judgement
of which is unnecessary in C language semantics. So remove it
to clean Code.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Sunil Goutham <sgoutham@marvell.com>
Link: https://lore.kernel.org/r/20230801112638.317149-1-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/ptp.c      | 4 ++--
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
index 0ee420a489fc4..c55c2c441a1a7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
@@ -61,12 +61,12 @@ static const struct pci_device_id ptp_id_table[];
 
 static bool is_ptp_dev_cnf10kb(struct ptp *ptp)
 {
-	return (ptp->pdev->subsystem_device == PCI_SUBSYS_DEVID_CNF10K_B_PTP) ? true : false;
+	return ptp->pdev->subsystem_device == PCI_SUBSYS_DEVID_CNF10K_B_PTP;
 }
 
 static bool is_ptp_dev_cn10k(struct ptp *ptp)
 {
-	return (ptp->pdev->device == PCI_DEVID_CN10K_PTP) ? true : false;
+	return ptp->pdev->device == PCI_DEVID_CN10K_PTP;
 }
 
 static bool cn10k_ptp_errata(struct ptp *ptp)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 9551b422622a4..61f62a6ec6627 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -2027,7 +2027,7 @@ u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb,
 #endif
 	int txq;
 
-	qos_enabled = (netdev->real_num_tx_queues > pf->hw.tx_queues) ? true : false;
+	qos_enabled = netdev->real_num_tx_queues > pf->hw.tx_queues;
 	if (unlikely(qos_enabled)) {
 		/* This smp_load_acquire() pairs with smp_store_release() in
 		 * otx2_qos_root_add() called from htb offload root creation
-- 
GitLab


From ae336f30d513c5ccd8a87db02804c7451a061461 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Tue, 1 Aug 2023 19:19:28 +0800
Subject: [PATCH 0780/1806] bnx2x: Remove unnecessary ternary operators

There are a little ternary operators, the true or false judgement
of which is unnecessary in C language semantics.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230801111928.300231-1-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 542c698226494..8e04552d2216c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -890,7 +890,7 @@ static void bnx2x_set_one_mac_e2(struct bnx2x *bp,
 		(struct eth_classify_rules_ramrod_data *)(raw->rdata);
 	int rule_cnt = rule_idx + 1, cmd = elem->cmd_data.vlan_mac.cmd;
 	union eth_classify_rule_cmd *rule_entry = &data->rules[rule_idx];
-	bool add = (cmd == BNX2X_VLAN_MAC_ADD) ? true : false;
+	bool add = cmd == BNX2X_VLAN_MAC_ADD;
 	unsigned long *vlan_mac_flags = &elem->cmd_data.vlan_mac.vlan_mac_flags;
 	u8 *mac = elem->cmd_data.vlan_mac.u.mac.mac;
 
@@ -1075,7 +1075,7 @@ static void bnx2x_set_one_vlan_e2(struct bnx2x *bp,
 	int rule_cnt = rule_idx + 1;
 	union eth_classify_rule_cmd *rule_entry = &data->rules[rule_idx];
 	enum bnx2x_vlan_mac_cmd cmd = elem->cmd_data.vlan_mac.cmd;
-	bool add = (cmd == BNX2X_VLAN_MAC_ADD) ? true : false;
+	bool add = cmd == BNX2X_VLAN_MAC_ADD;
 	u16 vlan = elem->cmd_data.vlan_mac.u.vlan.vlan;
 
 	/* Reset the ramrod data buffer for the first rule */
@@ -1125,7 +1125,7 @@ static void bnx2x_set_one_vlan_mac_e2(struct bnx2x *bp,
 	int rule_cnt = rule_idx + 1;
 	union eth_classify_rule_cmd *rule_entry = &data->rules[rule_idx];
 	enum bnx2x_vlan_mac_cmd cmd = elem->cmd_data.vlan_mac.cmd;
-	bool add = (cmd == BNX2X_VLAN_MAC_ADD) ? true : false;
+	bool add = cmd == BNX2X_VLAN_MAC_ADD;
 	u16 vlan = elem->cmd_data.vlan_mac.u.vlan_mac.vlan;
 	u8 *mac = elem->cmd_data.vlan_mac.u.vlan_mac.mac;
 	u16 inner_mac;
-- 
GitLab


From ae3683a34265381cd4bc006295a091009c7215d1 Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Tue, 1 Aug 2023 15:16:47 +0200
Subject: [PATCH 0781/1806] net: dsa: hellcreek: Replace bogus comment

Replace bogus comment about matching the latched timestamp to one of the
received frames. That comment is probably copied from mv88e6xxx and true for
these switches. However, the hellcreek switch is configured to insert the
timestamp directly into the PTP packets.

While here, remove the other comments regarding the list splicing and locking as
well, because it doesn't add any value.

Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://lore.kernel.org/r/20230801131647.84697-1-kurt@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c
index ffd06cf8c44f0..bd7aacc71a63f 100644
--- a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c
+++ b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c
@@ -298,17 +298,10 @@ static void hellcreek_get_rxts(struct hellcreek *hellcreek,
 	struct sk_buff_head received;
 	unsigned long flags;
 
-	/* The latched timestamp belongs to one of the received frames. */
+	/* Construct Rx timestamps for all received PTP packets. */
 	__skb_queue_head_init(&received);
-
-	/* Lock & disable interrupts */
 	spin_lock_irqsave(&rxq->lock, flags);
-
-	/* Add the reception queue "rxq" to the "received" queue an reintialize
-	 * "rxq".  From now on, we deal with "received" not with "rxq"
-	 */
 	skb_queue_splice_tail_init(rxq, &received);
-
 	spin_unlock_irqrestore(&rxq->lock, flags);
 
 	for (; skb; skb = __skb_dequeue(&received)) {
-- 
GitLab


From 497c3a5fb3ed4a59c4d3c460c70393dd609815dc Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Tue, 1 Aug 2023 21:31:21 +0800
Subject: [PATCH 0782/1806] cirrus: cs89x0: fix the return value handle and
 remove redundant dev_warn() for platform_get_irq()

There is no possible for platform_get_irq() to return 0
and the return value of platform_get_irq() is more sensible
to show the error reason.

And there is no need to call the dev_warn() function directly to print
a custom message when handling an error from platform_get_irq() function as
it is going to display an appropriate error message in case of a failure.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Alex Elder <elder@linaro.org>
Link: https://lore.kernel.org/r/20230801133121.416319-1-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cirrus/cs89x0.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c
index 7c51fd9fc9bee..d323c5c23521f 100644
--- a/drivers/net/ethernet/cirrus/cs89x0.c
+++ b/drivers/net/ethernet/cirrus/cs89x0.c
@@ -1854,9 +1854,8 @@ static int __init cs89x0_platform_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	dev->irq = platform_get_irq(pdev, 0);
-	if (dev->irq <= 0) {
-		dev_warn(&dev->dev, "interrupt resource missing\n");
-		err = -ENXIO;
+	if (dev->irq < 0) {
+		err = dev->irq;
 		goto free;
 	}
 
-- 
GitLab


From 9e63a99c566faf2a4b8f6257ea7fea82106612cc Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 1 Aug 2023 21:39:02 +0800
Subject: [PATCH 0783/1806] udp: Remove unused function declaration
 udp_bpf_get_proto()

commit 8a59f9d1e3d4 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()")
left behind this.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20230801133902.3660-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/udp.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/net/udp.h b/include/net/udp.h
index 4d13424f8f723..5a8421cd90836 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -529,7 +529,6 @@ static inline void udp_post_segment_fix_csum(struct sk_buff *skb)
 
 #ifdef CONFIG_BPF_SYSCALL
 struct sk_psock;
-struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
 int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
 #endif
 
-- 
GitLab


From 2fca1b5ef898b131c430eed6f07b8972fb6c9673 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 1 Aug 2023 22:31:29 +0800
Subject: [PATCH 0784/1806] ila: Remove unnecessary file net/ila.h

Commit 642c2c95585d ("ila: xlat changes") removed ila_xlat_outgoing()
and ila_xlat_incoming() functions, then this file became unnecessary.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230801143129.40652-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ila.h       | 16 ----------------
 net/ipv6/ila/ila_main.c |  1 -
 net/ipv6/ila/ila_xlat.c |  1 -
 3 files changed, 18 deletions(-)
 delete mode 100644 include/net/ila.h

diff --git a/include/net/ila.h b/include/net/ila.h
deleted file mode 100644
index 73ebe5eab2720..0000000000000
--- a/include/net/ila.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * ILA kernel interface
- *
- * Copyright (c) 2015 Tom Herbert <tom@herbertland.com>
- */
-
-#ifndef _NET_ILA_H
-#define _NET_ILA_H
-
-struct sk_buff;
-
-int ila_xlat_outgoing(struct sk_buff *skb);
-int ila_xlat_incoming(struct sk_buff *skb);
-
-#endif /* _NET_ILA_H */
diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c
index 3faf62530d6a4..69caed07315f0 100644
--- a/net/ipv6/ila/ila_main.c
+++ b/net/ipv6/ila/ila_main.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <net/genetlink.h>
-#include <net/ila.h>
 #include <net/netns/generic.h>
 #include <uapi/linux/genetlink.h>
 #include "ila.h"
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index bee45dfeb1874..67e8c9440977a 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -5,7 +5,6 @@
 #include <linux/rhashtable.h>
 #include <linux/vmalloc.h>
 #include <net/genetlink.h>
-#include <net/ila.h>
 #include <net/netns/generic.h>
 #include <uapi/linux/genetlink.h>
 #include "ila.h"
-- 
GitLab


From e12f2a6d1b9e10cfa1a5c520a620cd5c3a7ceba3 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 1 Aug 2023 22:34:53 +0800
Subject: [PATCH 0785/1806] netlabel: Remove unused declaration
 netlbl_cipsov4_doi_free()

Since commit b1edeb102397 ("netlabel: Replace protocol/NetLabel linking with refrerence counts")
this declaration is unused and can be removed.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Link: https://lore.kernel.org/r/20230801143453.24452-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netlabel/netlabel_cipso_v4.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/netlabel/netlabel_cipso_v4.h b/net/netlabel/netlabel_cipso_v4.h
index 85d7ecb057283..9518ab56ec98f 100644
--- a/net/netlabel/netlabel_cipso_v4.h
+++ b/net/netlabel/netlabel_cipso_v4.h
@@ -149,7 +149,4 @@ enum {
 /* NetLabel protocol functions */
 int netlbl_cipsov4_genl_init(void);
 
-/* Free the memory associated with a CIPSOv4 DOI definition */
-void netlbl_cipsov4_doi_free(struct rcu_head *entry);
-
 #endif
-- 
GitLab


From f85b1c7da776d0cb2b4509bdd7f406fe5607930b Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 1 Aug 2023 22:42:09 +0800
Subject: [PATCH 0786/1806] net: switchdev: Remove unused typedef
 switchdev_obj_dump_cb_t()

Commit 29ab586c3d83 ("net: switchdev: Remove bridge bypass support from switchdev")
leave this unused.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230801144209.27512-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/switchdev.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 4d324e2a2eef0..0294cfec9c37c 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -201,8 +201,6 @@ struct switchdev_obj_in_state_mrp {
 #define SWITCHDEV_OBJ_IN_STATE_MRP(OBJ) \
 	container_of((OBJ), struct switchdev_obj_in_state_mrp, obj)
 
-typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj);
-
 struct switchdev_brport {
 	struct net_device *dev;
 	const void *ctx;
-- 
GitLab


From 30ff01ee99bc961e5f278f997e41ffb94785a88b Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Tue, 1 Aug 2023 09:58:33 -0700
Subject: [PATCH 0787/1806] pds_core: Fix documentation for pds_client_register

The documentation above pds_client_register states that it returns 0 on
success and negative on error. However, it actually returns a positive
client ID on success and negative on error. Fix the documentation to
state exactly that.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Link: https://lore.kernel.org/r/20230801165833.1622-1-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/auxbus.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index 561af8e5b3eab..6787a5fae908e 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -11,7 +11,7 @@
  * @pf_pdev:	ptr to the PF driver struct
  * @devname:	name that includes service into, e.g. pds_core.vDPA
  *
- * Return: 0 on success, or
+ * Return: positive client ID (ci) on success, or
  *         negative for error
  */
 int pds_client_register(struct pci_dev *pf_pdev, char *devname)
-- 
GitLab


From 94e38c956b97d3bb3f6cc8215efb13ea851e3a91 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 21 Jul 2023 23:52:36 -0700
Subject: [PATCH 0788/1806] libbpf: fix typos in Makefile

Capitalize ABI (acronym) and fix spelling of "destination".

Fixes: 706819495921 ("libbpf: Improve usability of libbpf Makefile")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: bpf@vger.kernel.org
Cc: Xin Liu <liuxin350@huawei.com>
Link: https://lore.kernel.org/r/20230722065236.17010-1-rdunlap@infradead.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index cf7f02c679680..4be7144e4803d 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -293,11 +293,11 @@ help:
 	@echo '  HINT: use "V=1" to enable verbose build'
 	@echo '  all     - build libraries and pkgconfig'
 	@echo '  clean   - remove all generated files'
-	@echo '  check   - check abi and version info'
+	@echo '  check   - check ABI and version info'
 	@echo ''
 	@echo 'libbpf install targets:'
 	@echo '  HINT: use "prefix"(defaults to "/usr/local") or "DESTDIR" (defaults to "/")'
-	@echo '        to adjust target desitantion, e.g. "make prefix=/usr/local install"'
+	@echo '        to adjust target destination, e.g. "make prefix=/usr/local install"'
 	@echo '  install          - build and install all headers, libraries and pkgconfig'
 	@echo '  install_headers  - install only headers to include/bpf'
 	@echo ''
-- 
GitLab


From 25ad10658dc1068a671553ff10e19a812c2a3783 Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Fri, 21 Jul 2023 18:06:27 +0800
Subject: [PATCH 0789/1806] riscv, bpf: Adapt bpf trampoline to optimized riscv
 ftrace framework
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 6724a76cff85 ("riscv: ftrace: Reduce the detour code size to
half") optimizes the detour code size of kernel functions to half with
T0 register and the upcoming DYNAMIC_FTRACE_WITH_DIRECT_CALLS of riscv
is based on this optimization, we need to adapt riscv bpf trampoline
based on this. One thing to do is to reduce detour code size of bpf
programs, and the second is to deal with the return address after the
execution of bpf trampoline. Meanwhile, we need to construct the frame
of parent function, otherwise we will miss one layer when unwinding.
The related tests have passed.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Link: https://lore.kernel.org/r/20230721100627.2630326-1-pulehui@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/net/bpf_jit_comp64.c | 153 +++++++++++++++++---------------
 1 file changed, 82 insertions(+), 71 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index c648864c8cd1a..0ca4f5c0097c6 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -13,6 +13,8 @@
 #include <asm/patch.h>
 #include "bpf_jit.h"
 
+#define RV_FENTRY_NINSNS 2
+
 #define RV_REG_TCC RV_REG_A6
 #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */
 
@@ -241,7 +243,7 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
 	if (!is_tail_call)
 		emit_mv(RV_REG_A0, RV_REG_A5, ctx);
 	emit_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA,
-		  is_tail_call ? 20 : 0, /* skip reserved nops and TCC init */
+		  is_tail_call ? (RV_FENTRY_NINSNS + 1) * 4 : 0, /* skip reserved nops and TCC init */
 		  ctx);
 }
 
@@ -618,32 +620,7 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	return 0;
 }
 
-static int gen_call_or_nops(void *target, void *ip, u32 *insns)
-{
-	s64 rvoff;
-	int i, ret;
-	struct rv_jit_context ctx;
-
-	ctx.ninsns = 0;
-	ctx.insns = (u16 *)insns;
-
-	if (!target) {
-		for (i = 0; i < 4; i++)
-			emit(rv_nop(), &ctx);
-		return 0;
-	}
-
-	rvoff = (s64)(target - (ip + 4));
-	emit(rv_sd(RV_REG_SP, -8, RV_REG_RA), &ctx);
-	ret = emit_jump_and_link(RV_REG_RA, rvoff, false, &ctx);
-	if (ret)
-		return ret;
-	emit(rv_ld(RV_REG_RA, -8, RV_REG_SP), &ctx);
-
-	return 0;
-}
-
-static int gen_jump_or_nops(void *target, void *ip, u32 *insns)
+static int gen_jump_or_nops(void *target, void *ip, u32 *insns, bool is_call)
 {
 	s64 rvoff;
 	struct rv_jit_context ctx;
@@ -658,38 +635,35 @@ static int gen_jump_or_nops(void *target, void *ip, u32 *insns)
 	}
 
 	rvoff = (s64)(target - ip);
-	return emit_jump_and_link(RV_REG_ZERO, rvoff, false, &ctx);
+	return emit_jump_and_link(is_call ? RV_REG_T0 : RV_REG_ZERO, rvoff, false, &ctx);
 }
 
 int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
 		       void *old_addr, void *new_addr)
 {
-	u32 old_insns[4], new_insns[4];
+	u32 old_insns[RV_FENTRY_NINSNS], new_insns[RV_FENTRY_NINSNS];
 	bool is_call = poke_type == BPF_MOD_CALL;
-	int (*gen_insns)(void *target, void *ip, u32 *insns);
-	int ninsns = is_call ? 4 : 2;
 	int ret;
 
-	if (!is_bpf_text_address((unsigned long)ip))
+	if (!is_kernel_text((unsigned long)ip) &&
+	    !is_bpf_text_address((unsigned long)ip))
 		return -ENOTSUPP;
 
-	gen_insns = is_call ? gen_call_or_nops : gen_jump_or_nops;
-
-	ret = gen_insns(old_addr, ip, old_insns);
+	ret = gen_jump_or_nops(old_addr, ip, old_insns, is_call);
 	if (ret)
 		return ret;
 
-	if (memcmp(ip, old_insns, ninsns * 4))
+	if (memcmp(ip, old_insns, RV_FENTRY_NINSNS * 4))
 		return -EFAULT;
 
-	ret = gen_insns(new_addr, ip, new_insns);
+	ret = gen_jump_or_nops(new_addr, ip, new_insns, is_call);
 	if (ret)
 		return ret;
 
 	cpus_read_lock();
 	mutex_lock(&text_mutex);
-	if (memcmp(ip, new_insns, ninsns * 4))
-		ret = patch_text(ip, new_insns, ninsns);
+	if (memcmp(ip, new_insns, RV_FENTRY_NINSNS * 4))
+		ret = patch_text(ip, new_insns, RV_FENTRY_NINSNS);
 	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
 
@@ -787,8 +761,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	int i, ret, offset;
 	int *branches_off = NULL;
 	int stack_size = 0, nregs = m->nr_args;
-	int retaddr_off, fp_off, retval_off, args_off;
-	int nregs_off, ip_off, run_ctx_off, sreg_off;
+	int retval_off, args_off, nregs_off, ip_off, run_ctx_off, sreg_off;
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
@@ -796,13 +769,27 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	bool save_ret;
 	u32 insn;
 
-	/* Generated trampoline stack layout:
+	/* Two types of generated trampoline stack layout:
+	 *
+	 * 1. trampoline called from function entry
+	 * --------------------------------------
+	 * FP + 8	    [ RA to parent func	] return address to parent
+	 *					  function
+	 * FP + 0	    [ FP of parent func ] frame pointer of parent
+	 *					  function
+	 * FP - 8           [ T0 to traced func ] return address of traced
+	 *					  function
+	 * FP - 16	    [ FP of traced func ] frame pointer of traced
+	 *					  function
+	 * --------------------------------------
 	 *
-	 * FP - 8	    [ RA of parent func	] return address of parent
+	 * 2. trampoline called directly
+	 * --------------------------------------
+	 * FP - 8	    [ RA to caller func ] return address to caller
 	 *					  function
-	 * FP - retaddr_off [ RA of traced func	] return address of traced
+	 * FP - 16	    [ FP of caller func	] frame pointer of caller
 	 *					  function
-	 * FP - fp_off	    [ FP of parent func ]
+	 * --------------------------------------
 	 *
 	 * FP - retval_off  [ return value      ] BPF_TRAMP_F_CALL_ORIG or
 	 *					  BPF_TRAMP_F_RET_FENTRY_RET
@@ -833,14 +820,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	if (nregs > 8)
 		return -ENOTSUPP;
 
-	/* room for parent function return address */
-	stack_size += 8;
-
-	stack_size += 8;
-	retaddr_off = stack_size;
-
-	stack_size += 8;
-	fp_off = stack_size;
+	/* room of trampoline frame to store return address and frame pointer */
+	stack_size += 16;
 
 	save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
 	if (save_ret) {
@@ -867,12 +848,29 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 
 	stack_size = round_up(stack_size, 16);
 
-	emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx);
-
-	emit_sd(RV_REG_SP, stack_size - retaddr_off, RV_REG_RA, ctx);
-	emit_sd(RV_REG_SP, stack_size - fp_off, RV_REG_FP, ctx);
-
-	emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx);
+	if (func_addr) {
+		/* For the trampoline called from function entry,
+		 * the frame of traced function and the frame of
+		 * trampoline need to be considered.
+		 */
+		emit_addi(RV_REG_SP, RV_REG_SP, -16, ctx);
+		emit_sd(RV_REG_SP, 8, RV_REG_RA, ctx);
+		emit_sd(RV_REG_SP, 0, RV_REG_FP, ctx);
+		emit_addi(RV_REG_FP, RV_REG_SP, 16, ctx);
+
+		emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx);
+		emit_sd(RV_REG_SP, stack_size - 8, RV_REG_T0, ctx);
+		emit_sd(RV_REG_SP, stack_size - 16, RV_REG_FP, ctx);
+		emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx);
+	} else {
+		/* For the trampoline called directly, just handle
+		 * the frame of trampoline.
+		 */
+		emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx);
+		emit_sd(RV_REG_SP, stack_size - 8, RV_REG_RA, ctx);
+		emit_sd(RV_REG_SP, stack_size - 16, RV_REG_FP, ctx);
+		emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx);
+	}
 
 	/* callee saved register S1 to pass start time */
 	emit_sd(RV_REG_FP, -sreg_off, RV_REG_S1, ctx);
@@ -890,7 +888,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 
 	/* skip to actual body of traced function */
 	if (flags & BPF_TRAMP_F_SKIP_FRAME)
-		orig_call += 16;
+		orig_call += RV_FENTRY_NINSNS * 4;
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		emit_imm(RV_REG_A0, (const s64)im, ctx);
@@ -967,17 +965,30 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 
 	emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx);
 
-	if (flags & BPF_TRAMP_F_SKIP_FRAME)
-		/* return address of parent function */
-		emit_ld(RV_REG_RA, stack_size - 8, RV_REG_SP, ctx);
-	else
-		/* return address of traced function */
-		emit_ld(RV_REG_RA, stack_size - retaddr_off, RV_REG_SP, ctx);
+	if (func_addr) {
+		/* trampoline called from function entry */
+		emit_ld(RV_REG_T0, stack_size - 8, RV_REG_SP, ctx);
+		emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx);
+		emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx);
 
-	emit_ld(RV_REG_FP, stack_size - fp_off, RV_REG_SP, ctx);
-	emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx);
+		emit_ld(RV_REG_RA, 8, RV_REG_SP, ctx);
+		emit_ld(RV_REG_FP, 0, RV_REG_SP, ctx);
+		emit_addi(RV_REG_SP, RV_REG_SP, 16, ctx);
 
-	emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx);
+		if (flags & BPF_TRAMP_F_SKIP_FRAME)
+			/* return to parent function */
+			emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx);
+		else
+			/* return to traced function */
+			emit_jalr(RV_REG_ZERO, RV_REG_T0, 0, ctx);
+	} else {
+		/* trampoline called directly */
+		emit_ld(RV_REG_RA, stack_size - 8, RV_REG_SP, ctx);
+		emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx);
+		emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx);
+
+		emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx);
+	}
 
 	ret = ctx->ninsns;
 out:
@@ -1691,8 +1702,8 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx)
 
 	store_offset = stack_adjust - 8;
 
-	/* reserve 4 nop insns */
-	for (i = 0; i < 4; i++)
+	/* nops reserved for auipc+jalr pair */
+	for (i = 0; i < RV_FENTRY_NINSNS; i++)
 		emit(rv_nop(), ctx);
 
 	/* First instruction is always setting the tail-call-counter
-- 
GitLab


From 6a5a148aaf14747570cc634f9cdfcb0393f5617f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 1 Aug 2023 13:13:58 +0200
Subject: [PATCH 0790/1806] bpf: fix bpf_probe_read_kernel prototype mismatch

bpf_probe_read_kernel() has a __weak definition in core.c and another
definition with an incompatible prototype in kernel/trace/bpf_trace.c,
when CONFIG_BPF_EVENTS is enabled.

Since the two are incompatible, there cannot be a shared declaration in
a header file, but the lack of a prototype causes a W=1 warning:

kernel/bpf/core.c:1638:12: error: no previous prototype for 'bpf_probe_read_kernel' [-Werror=missing-prototypes]

On 32-bit architectures, the local prototype

u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)

passes arguments in other registers as the one in bpf_trace.c

BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
            const void *, unsafe_ptr)

which uses 64-bit arguments in pairs of registers.

As both versions of the function are fairly simple and only really
differ in one line, just move them into a header file as an inline
function that does not add any overhead for the bpf_trace.c callers
and actually avoids a function call for the other one.

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/ac25cb0f-b804-1649-3afb-1dc6138c2716@iogearbox.net/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230801111449.185301-1-arnd@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h      | 12 ++++++++++++
 kernel/bpf/core.c        | 12 +++---------
 kernel/trace/bpf_trace.c | 11 -----------
 3 files changed, 15 insertions(+), 20 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ceaa8c23287fc..abe75063630b8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2661,6 +2661,18 @@ static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr)
 }
 #endif /* CONFIG_BPF_SYSCALL */
 
+static __always_inline int
+bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
+{
+	int ret = -EFAULT;
+
+	if (IS_ENABLED(CONFIG_BPF_EVENTS))
+		ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
+	if (unlikely(ret < 0))
+		memset(dst, 0, size);
+	return ret;
+}
+
 void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
 			  struct btf_mod_pair *used_btfs, u32 len);
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index baccdec22f199..0f8f036d8bd11 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1650,12 +1650,6 @@ bool bpf_opcode_in_insntable(u8 code)
 }
 
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
-u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
-{
-	memset(dst, 0, size);
-	return -EFAULT;
-}
-
 /**
  *	___bpf_prog_run - run eBPF program on a given context
  *	@regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -2066,8 +2060,8 @@ out:
 		DST = *(SIZE *)(unsigned long) (SRC + insn->off);	\
 		CONT;							\
 	LDX_PROBE_MEM_##SIZEOP:						\
-		bpf_probe_read_kernel(&DST, sizeof(SIZE),		\
-				      (const void *)(long) (SRC + insn->off));	\
+		bpf_probe_read_kernel_common(&DST, sizeof(SIZE),	\
+			      (const void *)(long) (SRC + insn->off));	\
 		DST = *((SIZE *)&DST);					\
 		CONT;
 
@@ -2082,7 +2076,7 @@ out:
 		DST = *(SIZE *)(unsigned long) (SRC + insn->off);	\
 		CONT;							\
 	LDX_PROBE_MEMSX_##SIZEOP:					\
-		bpf_probe_read_kernel(&DST, sizeof(SIZE),		\
+		bpf_probe_read_kernel_common(&DST, sizeof(SIZE),		\
 				      (const void *)(long) (SRC + insn->off));	\
 		DST = *((SIZE *)&DST);					\
 		CONT;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c92eb8c6ff08d..83bde2475ae54 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -223,17 +223,6 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-static __always_inline int
-bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
-{
-	int ret;
-
-	ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
-	if (unlikely(ret < 0))
-		memset(dst, 0, size);
-	return ret;
-}
-
 BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
 	   const void *, unsafe_ptr)
 {
-- 
GitLab


From 416c6d01244ecbf0abfdb898fd091b50ef951b48 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Wed, 2 Aug 2023 08:39:06 +0100
Subject: [PATCH 0791/1806] selftests/bpf: fix static assert compilation issue
 for test_cls_*.c

commit bdeeed3498c7 ("libbpf: fix offsetof() and container_of() to work with CO-RE")

...was backported to stable trees such as 5.15. The problem is that with older
LLVM/clang (14/15) - which is often used for older kernels - we see compilation
failures in BPF selftests now:

In file included from progs/test_cls_redirect_subprogs.c:2:
progs/test_cls_redirect.c:90:2: error: static assertion expression is not an integral constant expression
        sizeof(flow_ports_t) !=
        ^~~~~~~~~~~~~~~~~~~~~~~
progs/test_cls_redirect.c:91:3: note: cast that performs the conversions of a reinterpret_cast is not allowed in a constant expression
                offsetofend(struct bpf_sock_tuple, ipv4.dport) -
                ^
progs/test_cls_redirect.c:32:3: note: expanded from macro 'offsetofend'
        (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER)))
         ^
tools/testing/selftests/bpf/tools/include/bpf/bpf_helpers.h:86:33: note: expanded from macro 'offsetof'
                                 ^
In file included from progs/test_cls_redirect_subprogs.c:2:
progs/test_cls_redirect.c:95:2: error: static assertion expression is not an integral constant expression
        sizeof(flow_ports_t) !=
        ^~~~~~~~~~~~~~~~~~~~~~~
progs/test_cls_redirect.c:96:3: note: cast that performs the conversions of a reinterpret_cast is not allowed in a constant expression
                offsetofend(struct bpf_sock_tuple, ipv6.dport) -
                ^
progs/test_cls_redirect.c:32:3: note: expanded from macro 'offsetofend'
        (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER)))
         ^
tools/testing/selftests/bpf/tools/include/bpf/bpf_helpers.h:86:33: note: expanded from macro 'offsetof'
                                 ^
2 errors generated.
make: *** [Makefile:594: tools/testing/selftests/bpf/test_cls_redirect_subprogs.bpf.o] Error 1

The problem is the new offsetof() does not play nice with static asserts.
Given that the context is a static assert (and CO-RE relocation is not
needed at compile time), offsetof() usage can be replaced by restoring
the original offsetof() definition as __builtin_offsetof().

Fixes: bdeeed3498c7 ("libbpf: fix offsetof() and container_of() to work with CO-RE")
Reported-by: Colm Harrington <colm.harrington@oracle.com>
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Tested-by: Yipeng Zou <zouyipeng@huawei.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230802073906.3197480-1-alan.maguire@oracle.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/test_cls_redirect.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h
index 76eab0aacba0c..233b089d1fbac 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect.h
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h
@@ -12,6 +12,15 @@
 #include <linux/ipv6.h>
 #include <linux/udp.h>
 
+/* offsetof() is used in static asserts, and the libbpf-redefined CO-RE
+ * friendly version breaks compilation for older clang versions <= 15
+ * when invoked in a static assert.  Restore original here.
+ */
+#ifdef offsetof
+#undef offsetof
+#define offsetof(type, member) __builtin_offsetof(type, member)
+#endif
+
 struct gre_base_hdr {
 	uint16_t flags;
 	uint16_t protocol;
-- 
GitLab


From bf4ea1d0b2cb2251f9e5619c81daa98591087c33 Mon Sep 17 00:00:00 2001
From: Leon Hwang <hffilwlqm@gmail.com>
Date: Tue, 1 Aug 2023 22:26:20 +0800
Subject: [PATCH 0792/1806] bpf, xdp: Add tracepoint to xdp attaching failure

When error happens in dev_xdp_attach(), it should have a way to tell
users the error message like the netlink approach.

To avoid breaking uapi, adding a tracepoint in bpf_xdp_link_attach() is
an appropriate way to notify users the error message.

Hence, bpf libraries are able to retrieve the error message by this
tracepoint, and then report the error message to users.

Signed-off-by: Leon Hwang <hffilwlqm@gmail.com>
Link: https://lore.kernel.org/r/20230801142621.7925-2-hffilwlqm@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/trace/events/xdp.h | 17 +++++++++++++++++
 net/core/dev.c             |  5 ++++-
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index c40fc97f94171..cd89f1d5ce7b8 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -404,6 +404,23 @@ TRACE_EVENT(mem_return_failed,
 	)
 );
 
+TRACE_EVENT(bpf_xdp_link_attach_failed,
+
+	TP_PROTO(const char *msg),
+
+	TP_ARGS(msg),
+
+	TP_STRUCT__entry(
+		__string(msg, msg)
+	),
+
+	TP_fast_assign(
+		__assign_str(msg, msg);
+	),
+
+	TP_printk("errmsg=%s", __get_str(msg))
+);
+
 #endif /* _TRACE_XDP_H */
 
 #include <trace/define_trace.h>
diff --git a/net/core/dev.c b/net/core/dev.c
index 8e7d0cb540cdb..002fec07de739 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -133,6 +133,7 @@
 #include <trace/events/net.h>
 #include <trace/events/skb.h>
 #include <trace/events/qdisc.h>
+#include <trace/events/xdp.h>
 #include <linux/inetdevice.h>
 #include <linux/cpu_rmap.h>
 #include <linux/static_key.h>
@@ -9470,6 +9471,7 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
 	struct net *net = current->nsproxy->net_ns;
 	struct bpf_link_primer link_primer;
+	struct netlink_ext_ack extack = {};
 	struct bpf_xdp_link *link;
 	struct net_device *dev;
 	int err, fd;
@@ -9497,12 +9499,13 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 		goto unlock;
 	}
 
-	err = dev_xdp_attach_link(dev, NULL, link);
+	err = dev_xdp_attach_link(dev, &extack, link);
 	rtnl_unlock();
 
 	if (err) {
 		link->dev = NULL;
 		bpf_link_cleanup(&link_primer);
+		trace_bpf_xdp_link_attach_failed(extack._msg);
 		goto out_put_dev;
 	}
 
-- 
GitLab


From 7fedbf32fcc779a07abdba1347e759ad52bded2c Mon Sep 17 00:00:00 2001
From: Leon Hwang <hffilwlqm@gmail.com>
Date: Tue, 1 Aug 2023 22:26:21 +0800
Subject: [PATCH 0793/1806] selftests/bpf: Add testcase for xdp attaching
 failure tracepoint

Add a test case for the tracepoint of xdp attaching failure by bpf
tracepoint when attach XDP to a device with invalid flags option.

The bpf tracepoint retrieves error message from the tracepoint, and
then put the error message to a perf buffer. The testing code receives
error message from perf buffer, and then ASSERT "Invalid XDP flags for
BPF link attachment".

Signed-off-by: Leon Hwang <hffilwlqm@gmail.com>
Link: https://lore.kernel.org/r/20230801142621.7925-3-hffilwlqm@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/xdp_attach.c     | 65 +++++++++++++++++++
 .../bpf/progs/test_xdp_attach_fail.c          | 54 +++++++++++++++
 2 files changed, 119 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
index fa3cac5488f5d..e6bcb6051402d 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "test_xdp_attach_fail.skel.h"
 
 #define IFINDEX_LO 1
 #define XDP_FLAGS_REPLACE		(1U << 4)
@@ -85,10 +86,74 @@ out_1:
 	bpf_object__close(obj1);
 }
 
+#define ERRMSG_LEN 64
+
+struct xdp_errmsg {
+	char msg[ERRMSG_LEN];
+};
+
+static void on_xdp_errmsg(void *ctx, int cpu, void *data, __u32 size)
+{
+	struct xdp_errmsg *ctx_errmg = ctx, *tp_errmsg = data;
+
+	memcpy(&ctx_errmg->msg, &tp_errmsg->msg, ERRMSG_LEN);
+}
+
+static const char tgt_errmsg[] = "Invalid XDP flags for BPF link attachment";
+
+static void test_xdp_attach_fail(const char *file)
+{
+	struct test_xdp_attach_fail *skel = NULL;
+	struct xdp_errmsg errmsg = {};
+	struct perf_buffer *pb = NULL;
+	struct bpf_object *obj = NULL;
+	int err, fd_xdp;
+
+	LIBBPF_OPTS(bpf_link_create_opts, opts);
+
+	skel = test_xdp_attach_fail__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_xdp_attach_fail__open_and_load"))
+		goto out_close;
+
+	err = test_xdp_attach_fail__attach(skel);
+	if (!ASSERT_EQ(err, 0, "test_xdp_attach_fail__attach"))
+		goto out_close;
+
+	/* set up perf buffer */
+	pb = perf_buffer__new(bpf_map__fd(skel->maps.xdp_errmsg_pb), 1,
+			      on_xdp_errmsg, NULL, &errmsg, NULL);
+	if (!ASSERT_OK_PTR(pb, "perf_buffer__new"))
+		goto out_close;
+
+	err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &fd_xdp);
+	if (!ASSERT_EQ(err, 0, "bpf_prog_test_load"))
+		goto out_close;
+
+	opts.flags = 0xFF; // invalid flags to fail to attach XDP prog
+	err = bpf_link_create(fd_xdp, IFINDEX_LO, BPF_XDP, &opts);
+	if (!ASSERT_EQ(err, -EINVAL, "bpf_link_create"))
+		goto out_close;
+
+	/* read perf buffer */
+	err = perf_buffer__poll(pb, 100);
+	if (!ASSERT_GT(err, -1, "perf_buffer__poll"))
+		goto out_close;
+
+	ASSERT_STRNEQ((const char *) errmsg.msg, tgt_errmsg,
+		      42 /* strlen(tgt_errmsg) */, "check error message");
+
+out_close:
+	perf_buffer__free(pb);
+	bpf_object__close(obj);
+	test_xdp_attach_fail__destroy(skel);
+}
+
 void serial_test_xdp_attach(void)
 {
 	if (test__start_subtest("xdp_attach"))
 		test_xdp_attach("./test_xdp.bpf.o");
 	if (test__start_subtest("xdp_attach_dynptr"))
 		test_xdp_attach("./test_xdp_dynptr.bpf.o");
+	if (test__start_subtest("xdp_attach_failed"))
+		test_xdp_attach_fail("./xdp_dummy.bpf.o");
 }
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c b/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c
new file mode 100644
index 0000000000000..2ff1b596e87ea
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Leon Hwang */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define ERRMSG_LEN 64
+
+struct xdp_errmsg {
+	char msg[ERRMSG_LEN];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__type(key, int);
+	__type(value, int);
+} xdp_errmsg_pb SEC(".maps");
+
+struct xdp_attach_error_ctx {
+	unsigned long unused;
+
+	/*
+	 * bpf does not support tracepoint __data_loc directly.
+	 *
+	 * Actually, this field is a 32 bit integer whose value encodes
+	 * information on where to find the actual data. The first 2 bytes is
+	 * the size of the data. The last 2 bytes is the offset from the start
+	 * of the tracepoint struct where the data begins.
+	 * -- https://github.com/iovisor/bpftrace/pull/1542
+	 */
+	__u32 msg; // __data_loc char[] msg;
+};
+
+/*
+ * Catch the error message at the tracepoint.
+ */
+
+SEC("tp/xdp/bpf_xdp_link_attach_failed")
+int tp__xdp__bpf_xdp_link_attach_failed(struct xdp_attach_error_ctx *ctx)
+{
+	char *msg = (void *)(__u64) ((void *) ctx + (__u16) ctx->msg);
+	struct xdp_errmsg errmsg = {};
+
+	bpf_probe_read_kernel_str(&errmsg.msg, ERRMSG_LEN, msg);
+	bpf_perf_event_output(ctx, &xdp_errmsg_pb, BPF_F_CURRENT_CPU, &errmsg,
+			      ERRMSG_LEN);
+	return 0;
+}
+
+/*
+ * Reuse the XDP program in xdp_dummy.c.
+ */
+
+char LICENSE[] SEC("license") = "GPL";
-- 
GitLab


From fbd517549c324049d636de0872ad9d3de63ec015 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:12 +0300
Subject: [PATCH 0794/1806] net/mlx5e: Add function to get IPsec offload
 namespace

Add function to get namespace in different directions. It will be
extended for switchdev mode in later patch, but no functionality change
for now.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/ac2982c34f1ed3288d4670cacfd7e1b87a8c96d9.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 46 +++++++++----------
 1 file changed, 22 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 47baf983147f7..7ec92f0cf1bdb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -814,11 +814,20 @@ static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upsp
 	}
 }
 
-static int setup_modify_header(struct mlx5_core_dev *mdev, u32 val, u8 dir,
+static enum mlx5_flow_namespace_type ipsec_fs_get_ns(struct mlx5e_ipsec *ipsec, u8 dir)
+{
+	if (dir == XFRM_DEV_OFFLOAD_IN)
+		return MLX5_FLOW_NAMESPACE_KERNEL;
+
+	return MLX5_FLOW_NAMESPACE_EGRESS;
+}
+
+static int setup_modify_header(struct mlx5e_ipsec *ipsec, u32 val, u8 dir,
 			       struct mlx5_flow_act *flow_act)
 {
+	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, dir);
 	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
-	enum mlx5_flow_namespace_type ns_type;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_modify_hdr *modify_hdr;
 
 	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
@@ -826,12 +835,10 @@ static int setup_modify_header(struct mlx5_core_dev *mdev, u32 val, u8 dir,
 	case XFRM_DEV_OFFLOAD_IN:
 		MLX5_SET(set_action_in, action, field,
 			 MLX5_ACTION_IN_FIELD_METADATA_REG_B);
-		ns_type = MLX5_FLOW_NAMESPACE_KERNEL;
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
 		MLX5_SET(set_action_in, action, field,
 			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
-		ns_type = MLX5_FLOW_NAMESPACE_EGRESS;
 		break;
 	default:
 		return -EINVAL;
@@ -1024,26 +1031,16 @@ setup_pkt_transport_reformat(struct mlx5_accel_esp_xfrm_attrs *attrs,
 	return 0;
 }
 
-static int setup_pkt_reformat(struct mlx5_core_dev *mdev,
+static int setup_pkt_reformat(struct mlx5e_ipsec *ipsec,
 			      struct mlx5_accel_esp_xfrm_attrs *attrs,
 			      struct mlx5_flow_act *flow_act)
 {
+	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, attrs->dir);
 	struct mlx5_pkt_reformat_params reformat_params = {};
+	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_pkt_reformat *pkt_reformat;
-	enum mlx5_flow_namespace_type ns_type;
 	int ret;
 
-	switch (attrs->dir) {
-	case XFRM_DEV_OFFLOAD_IN:
-		ns_type = MLX5_FLOW_NAMESPACE_KERNEL;
-		break;
-	case XFRM_DEV_OFFLOAD_OUT:
-		ns_type = MLX5_FLOW_NAMESPACE_EGRESS;
-		break;
-	default:
-		return -EINVAL;
-	}
-
 	switch (attrs->mode) {
 	case XFRM_MODE_TRANSPORT:
 		ret = setup_pkt_transport_reformat(attrs, &reformat_params);
@@ -1101,14 +1098,14 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
 
-	err = setup_modify_header(mdev, sa_entry->ipsec_obj_id | BIT(31),
+	err = setup_modify_header(ipsec, sa_entry->ipsec_obj_id | BIT(31),
 				  XFRM_DEV_OFFLOAD_IN, &flow_act);
 	if (err)
 		goto err_mod_header;
 
 	switch (attrs->type) {
 	case XFRM_DEV_OFFLOAD_PACKET:
-		err = setup_pkt_reformat(mdev, attrs, &flow_act);
+		err = setup_pkt_reformat(ipsec, attrs, &flow_act);
 		if (err)
 			goto err_pkt_reformat;
 		break;
@@ -1202,7 +1199,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	case XFRM_DEV_OFFLOAD_PACKET:
 		if (attrs->reqid)
 			setup_fte_reg_c0(spec, attrs->reqid);
-		err = setup_pkt_reformat(mdev, attrs, &flow_act);
+		err = setup_pkt_reformat(ipsec, attrs, &flow_act);
 		if (err)
 			goto err_pkt_reformat;
 		break;
@@ -1259,15 +1256,16 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 {
 	struct mlx5_accel_pol_xfrm_attrs *attrs = &pol_entry->attrs;
 	struct mlx5_core_dev *mdev = mlx5e_ipsec_pol2dev(pol_entry);
-	struct mlx5e_ipsec_tx *tx = pol_entry->ipsec->tx;
+	struct mlx5e_ipsec *ipsec = pol_entry->ipsec;
 	struct mlx5_flow_destination dest[2] = {};
+	struct mlx5e_ipsec_tx *tx = ipsec->tx;
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_table *ft;
 	int err, dstn = 0;
 
-	ft = tx_ft_get_policy(mdev, pol_entry->ipsec, attrs->prio);
+	ft = tx_ft_get_policy(mdev, ipsec, attrs->prio);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 
@@ -1291,7 +1289,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 		if (!attrs->reqid)
 			break;
 
-		err = setup_modify_header(mdev, attrs->reqid,
+		err = setup_modify_header(ipsec, attrs->reqid,
 					  XFRM_DEV_OFFLOAD_OUT, &flow_act);
 		if (err)
 			goto err_mod_header;
@@ -1331,7 +1329,7 @@ err_action:
 err_mod_header:
 	kvfree(spec);
 err_alloc:
-	tx_ft_put_policy(pol_entry->ipsec, attrs->prio);
+	tx_ft_put_policy(ipsec, attrs->prio);
 	return err;
 }
 
-- 
GitLab


From 33b18a0f75cd2278a1ebb585b53be9c10f6f5364 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:13 +0300
Subject: [PATCH 0795/1806] net/mlx5e: Change the parameter of IPsec RX skb
 handle function

Refactor the function to pass in reg B value only.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/3b3c53f64660d464893eaecc41298b1ce49c6baa.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 3 +--
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c               | 3 ++-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index eab5bc718771f..8d6379ac4574e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -309,9 +309,8 @@ enum {
 
 void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct sk_buff *skb,
-				       struct mlx5_cqe64 *cqe)
+				       u32 ipsec_meta_data)
 {
-	u32 ipsec_meta_data = be32_to_cpu(cqe->ft_metadata);
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_ipsec *ipsec = priv->ipsec;
 	struct mlx5e_ipsec_sa_entry *sa_entry;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 1878a70b9031d..436e9a8a32d30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -66,7 +66,7 @@ void mlx5e_ipsec_handle_tx_wqe(struct mlx5e_tx_wqe *wqe,
 			       struct mlx5_wqe_inline_seg *inlseg);
 void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct sk_buff *skb,
-				       struct mlx5_cqe64 *cqe);
+				       u32 ipsec_meta_data);
 static inline unsigned int mlx5e_ipsec_tx_ids_len(struct mlx5e_accel_tx_ipsec_state *ipsec_st)
 {
 	return ipsec_st->tailen;
@@ -145,7 +145,7 @@ mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 static inline
 void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct sk_buff *skb,
-				       struct mlx5_cqe64 *cqe)
+				       u32 ipsec_meta_data)
 {}
 
 static inline bool mlx5e_ipsec_eseg_meta(struct mlx5_wqe_eth_seg *eseg)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 41d37159e027b..f7bb5f4aaaca0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1543,7 +1543,8 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 		mlx5e_ktls_handle_rx_skb(rq, skb, cqe, &cqe_bcnt);
 
 	if (unlikely(mlx5_ipsec_is_rx_flow(cqe)))
-		mlx5e_ipsec_offload_handle_rx_skb(netdev, skb, cqe);
+		mlx5e_ipsec_offload_handle_rx_skb(netdev, skb,
+						  be32_to_cpu(cqe->ft_metadata));
 
 	if (unlikely(mlx5e_macsec_is_rx_flow(cqe)))
 		mlx5e_macsec_offload_handle_rx_skb(netdev, skb, cqe);
-- 
GitLab


From f5c5abc4c04110317dd3e7d5794bd0ca43a013ca Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:14 +0300
Subject: [PATCH 0796/1806] net/mlx5e: Prepare IPsec packet offload for
 switchdev mode

As the uplink representor is created only in switchdev mode, add a local
variable for IPsec to indicate the device is in this mode.
In this mode, IPsec ROCE is disabled, and crypto offload is kept
as it is. However, as the tables for packet offload are created in FDB,
ipsec->rx_esw and ipsec->tx_esw are added.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/ee242398f3b0a18007749fe79ff6ff19445a0280.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec.c       |   2 +
 .../mellanox/mlx5/core/en_accel/ipsec.h       |   3 +
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 262 ++++++++++++------
 3 files changed, 184 insertions(+), 83 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 658b7d8d50c77..a577f0edabe86 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -40,6 +40,7 @@
 #include "en.h"
 #include "ipsec.h"
 #include "ipsec_rxtx.h"
+#include "en_rep.h"
 
 #define MLX5_IPSEC_RESCHED msecs_to_jiffies(1000)
 #define MLX5E_IPSEC_TUNNEL_SA XA_MARK_1
@@ -858,6 +859,7 @@ void mlx5e_ipsec_init(struct mlx5e_priv *priv)
 			goto clear_aso;
 	}
 
+	ipsec->is_uplink_rep = mlx5e_is_uplink_rep(priv);
 	ret = mlx5e_accel_ipsec_fs_init(ipsec);
 	if (ret)
 		goto err_fs_init;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 7a70472636180..e12154276666f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -178,11 +178,14 @@ struct mlx5e_ipsec {
 	struct mlx5e_flow_steering *fs;
 	struct mlx5e_ipsec_rx *rx_ipv4;
 	struct mlx5e_ipsec_rx *rx_ipv6;
+	struct mlx5e_ipsec_rx *rx_esw;
 	struct mlx5e_ipsec_tx *tx;
+	struct mlx5e_ipsec_tx *tx_esw;
 	struct mlx5e_ipsec_aso *aso;
 	struct notifier_block nb;
 	struct notifier_block netevent_nb;
 	struct mlx5_ipsec_fs *roce;
+	u8 is_uplink_rep: 1;
 };
 
 struct mlx5e_ipsec_esn_state {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 7ec92f0cf1bdb..0f0c48f5f6204 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -60,14 +60,25 @@ static enum mlx5_traffic_types family2tt(u32 family)
 	return MLX5_TT_IPV6_IPSEC_ESP;
 }
 
-static struct mlx5e_ipsec_rx *ipsec_rx(struct mlx5e_ipsec *ipsec, u32 family)
+static struct mlx5e_ipsec_rx *ipsec_rx(struct mlx5e_ipsec *ipsec, u32 family, int type)
 {
+	if (ipsec->is_uplink_rep && type == XFRM_DEV_OFFLOAD_PACKET)
+		return ipsec->rx_esw;
+
 	if (family == AF_INET)
 		return ipsec->rx_ipv4;
 
 	return ipsec->rx_ipv6;
 }
 
+static struct mlx5e_ipsec_tx *ipsec_tx(struct mlx5e_ipsec *ipsec, int type)
+{
+	if (ipsec->is_uplink_rep && type == XFRM_DEV_OFFLOAD_PACKET)
+		return ipsec->tx_esw;
+
+	return ipsec->tx;
+}
+
 static struct mlx5_fs_chains *
 ipsec_chains_create(struct mlx5_core_dev *mdev, struct mlx5_flow_table *miss_ft,
 		    enum mlx5_flow_namespace_type ns, int base_prio,
@@ -406,9 +417,10 @@ static void rx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx,
 }
 
 static struct mlx5e_ipsec_rx *rx_ft_get(struct mlx5_core_dev *mdev,
-					struct mlx5e_ipsec *ipsec, u32 family)
+					struct mlx5e_ipsec *ipsec, u32 family,
+					int type)
 {
-	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family);
+	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family, type);
 	int err;
 
 	mutex_lock(&rx->ft.mutex);
@@ -422,9 +434,9 @@ static struct mlx5e_ipsec_rx *rx_ft_get(struct mlx5_core_dev *mdev,
 
 static struct mlx5_flow_table *rx_ft_get_policy(struct mlx5_core_dev *mdev,
 						struct mlx5e_ipsec *ipsec,
-						u32 family, u32 prio)
+						u32 family, u32 prio, int type)
 {
-	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family);
+	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family, type);
 	struct mlx5_flow_table *ft;
 	int err;
 
@@ -449,18 +461,18 @@ err_get:
 	return ERR_PTR(err);
 }
 
-static void rx_ft_put(struct mlx5e_ipsec *ipsec, u32 family)
+static void rx_ft_put(struct mlx5e_ipsec *ipsec, u32 family, int type)
 {
-	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family);
+	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family, type);
 
 	mutex_lock(&rx->ft.mutex);
 	rx_put(ipsec, rx, family);
 	mutex_unlock(&rx->ft.mutex);
 }
 
-static void rx_ft_put_policy(struct mlx5e_ipsec *ipsec, u32 family, u32 prio)
+static void rx_ft_put_policy(struct mlx5e_ipsec *ipsec, u32 family, u32 prio, int type)
 {
-	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family);
+	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family, type);
 
 	mutex_lock(&rx->ft.mutex);
 	if (rx->chains)
@@ -629,9 +641,9 @@ static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
 
 static struct mlx5_flow_table *tx_ft_get_policy(struct mlx5_core_dev *mdev,
 						struct mlx5e_ipsec *ipsec,
-						u32 prio)
+						u32 prio, int type)
 {
-	struct mlx5e_ipsec_tx *tx = ipsec->tx;
+	struct mlx5e_ipsec_tx *tx = ipsec_tx(ipsec, type);
 	struct mlx5_flow_table *ft;
 	int err;
 
@@ -657,9 +669,9 @@ err_get:
 }
 
 static struct mlx5e_ipsec_tx *tx_ft_get(struct mlx5_core_dev *mdev,
-					struct mlx5e_ipsec *ipsec)
+					struct mlx5e_ipsec *ipsec, int type)
 {
-	struct mlx5e_ipsec_tx *tx = ipsec->tx;
+	struct mlx5e_ipsec_tx *tx = ipsec_tx(ipsec, type);
 	int err;
 
 	mutex_lock(&tx->ft.mutex);
@@ -671,18 +683,18 @@ static struct mlx5e_ipsec_tx *tx_ft_get(struct mlx5_core_dev *mdev,
 	return tx;
 }
 
-static void tx_ft_put(struct mlx5e_ipsec *ipsec)
+static void tx_ft_put(struct mlx5e_ipsec *ipsec, int type)
 {
-	struct mlx5e_ipsec_tx *tx = ipsec->tx;
+	struct mlx5e_ipsec_tx *tx = ipsec_tx(ipsec, type);
 
 	mutex_lock(&tx->ft.mutex);
 	tx_put(ipsec, tx);
 	mutex_unlock(&tx->ft.mutex);
 }
 
-static void tx_ft_put_policy(struct mlx5e_ipsec *ipsec, u32 prio)
+static void tx_ft_put_policy(struct mlx5e_ipsec *ipsec, u32 prio, int type)
 {
-	struct mlx5e_ipsec_tx *tx = ipsec->tx;
+	struct mlx5e_ipsec_tx *tx = ipsec_tx(ipsec, type);
 
 	mutex_lock(&tx->ft.mutex);
 	if (tx->chains)
@@ -1079,7 +1091,7 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5_fc *counter;
 	int err;
 
-	rx = rx_ft_get(mdev, ipsec, attrs->family);
+	rx = rx_ft_get(mdev, ipsec, attrs->family, attrs->type);
 	if (IS_ERR(rx))
 		return PTR_ERR(rx);
 
@@ -1155,7 +1167,7 @@ err_pkt_reformat:
 err_mod_header:
 	kvfree(spec);
 err_alloc:
-	rx_ft_put(ipsec, attrs->family);
+	rx_ft_put(ipsec, attrs->family, attrs->type);
 	return err;
 }
 
@@ -1172,7 +1184,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5_fc *counter;
 	int err;
 
-	tx = tx_ft_get(mdev, ipsec);
+	tx = tx_ft_get(mdev, ipsec, attrs->type);
 	if (IS_ERR(tx))
 		return PTR_ERR(tx);
 
@@ -1248,7 +1260,7 @@ err_add_cnt:
 err_pkt_reformat:
 	kvfree(spec);
 err_alloc:
-	tx_ft_put(ipsec);
+	tx_ft_put(ipsec, attrs->type);
 	return err;
 }
 
@@ -1258,14 +1270,14 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	struct mlx5_core_dev *mdev = mlx5e_ipsec_pol2dev(pol_entry);
 	struct mlx5e_ipsec *ipsec = pol_entry->ipsec;
 	struct mlx5_flow_destination dest[2] = {};
-	struct mlx5e_ipsec_tx *tx = ipsec->tx;
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_table *ft;
+	struct mlx5e_ipsec_tx *tx;
 	int err, dstn = 0;
 
-	ft = tx_ft_get_policy(mdev, ipsec, attrs->prio);
+	ft = tx_ft_get_policy(mdev, ipsec, attrs->prio, attrs->type);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 
@@ -1275,6 +1287,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 		goto err_alloc;
 	}
 
+	tx = ipsec_tx(ipsec, attrs->type);
 	if (attrs->family == AF_INET)
 		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
 	else
@@ -1329,7 +1342,7 @@ err_action:
 err_mod_header:
 	kvfree(spec);
 err_alloc:
-	tx_ft_put_policy(ipsec, attrs->prio);
+	tx_ft_put_policy(ipsec, attrs->prio, attrs->type);
 	return err;
 }
 
@@ -1345,11 +1358,12 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	struct mlx5e_ipsec_rx *rx;
 	int err, dstn = 0;
 
-	ft = rx_ft_get_policy(mdev, pol_entry->ipsec, attrs->family, attrs->prio);
+	ft = rx_ft_get_policy(mdev, pol_entry->ipsec, attrs->family, attrs->prio,
+			      attrs->type);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 
-	rx = ipsec_rx(pol_entry->ipsec, attrs->family);
+	rx = ipsec_rx(pol_entry->ipsec, attrs->family, attrs->type);
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec) {
@@ -1398,88 +1412,110 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 err_action:
 	kvfree(spec);
 err_alloc:
-	rx_ft_put_policy(pol_entry->ipsec, attrs->family, attrs->prio);
+	rx_ft_put_policy(pol_entry->ipsec, attrs->family, attrs->prio, attrs->type);
 	return err;
 }
 
+static void ipsec_fs_destroy_single_counter(struct mlx5_core_dev *mdev,
+					    struct mlx5e_ipsec_fc *fc)
+{
+	mlx5_fc_destroy(mdev, fc->drop);
+	mlx5_fc_destroy(mdev, fc->cnt);
+	kfree(fc);
+}
+
 static void ipsec_fs_destroy_counters(struct mlx5e_ipsec *ipsec)
 {
-	struct mlx5e_ipsec_rx *rx_ipv4 = ipsec->rx_ipv4;
 	struct mlx5_core_dev *mdev = ipsec->mdev;
-	struct mlx5e_ipsec_tx *tx = ipsec->tx;
-
-	mlx5_fc_destroy(mdev, tx->fc->drop);
-	mlx5_fc_destroy(mdev, tx->fc->cnt);
-	kfree(tx->fc);
-	mlx5_fc_destroy(mdev, rx_ipv4->fc->drop);
-	mlx5_fc_destroy(mdev, rx_ipv4->fc->cnt);
-	kfree(rx_ipv4->fc);
+
+	ipsec_fs_destroy_single_counter(mdev, ipsec->tx->fc);
+	ipsec_fs_destroy_single_counter(mdev, ipsec->rx_ipv4->fc);
+	if (ipsec->is_uplink_rep) {
+		ipsec_fs_destroy_single_counter(mdev, ipsec->tx_esw->fc);
+		ipsec_fs_destroy_single_counter(mdev, ipsec->rx_esw->fc);
+	}
 }
 
-static int ipsec_fs_init_counters(struct mlx5e_ipsec *ipsec)
+static struct mlx5e_ipsec_fc *ipsec_fs_init_single_counter(struct mlx5_core_dev *mdev)
 {
-	struct mlx5e_ipsec_rx *rx_ipv4 = ipsec->rx_ipv4;
-	struct mlx5e_ipsec_rx *rx_ipv6 = ipsec->rx_ipv6;
-	struct mlx5_core_dev *mdev = ipsec->mdev;
-	struct mlx5e_ipsec_tx *tx = ipsec->tx;
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fc *counter;
 	int err;
 
-	fc = kzalloc(sizeof(*rx_ipv4->fc), GFP_KERNEL);
+	fc = kzalloc(sizeof(*fc), GFP_KERNEL);
 	if (!fc)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
-	/* Both IPv4 and IPv6 point to same flow counters struct. */
-	rx_ipv4->fc = fc;
-	rx_ipv6->fc = fc;
 	counter = mlx5_fc_create(mdev, false);
 	if (IS_ERR(counter)) {
 		err = PTR_ERR(counter);
-		goto err_rx_cnt;
+		goto err_cnt;
 	}
-
 	fc->cnt = counter;
+
 	counter = mlx5_fc_create(mdev, false);
 	if (IS_ERR(counter)) {
 		err = PTR_ERR(counter);
-		goto err_rx_drop;
+		goto err_drop;
 	}
-
 	fc->drop = counter;
-	fc = kzalloc(sizeof(*tx->fc), GFP_KERNEL);
-	if (!fc) {
-		err = -ENOMEM;
-		goto err_tx_fc;
+
+	return fc;
+
+err_drop:
+	mlx5_fc_destroy(mdev, fc->cnt);
+err_cnt:
+	kfree(fc);
+	return ERR_PTR(err);
+}
+
+static int ipsec_fs_init_counters(struct mlx5e_ipsec *ipsec)
+{
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5e_ipsec_fc *fc;
+	int err;
+
+	fc = ipsec_fs_init_single_counter(mdev);
+	if (IS_ERR(fc)) {
+		err = PTR_ERR(fc);
+		goto err_rx_cnt;
 	}
+	ipsec->rx_ipv4->fc = fc;
 
-	tx->fc = fc;
-	counter = mlx5_fc_create(mdev, false);
-	if (IS_ERR(counter)) {
-		err = PTR_ERR(counter);
+	fc = ipsec_fs_init_single_counter(mdev);
+	if (IS_ERR(fc)) {
+		err = PTR_ERR(fc);
 		goto err_tx_cnt;
 	}
+	ipsec->tx->fc = fc;
 
-	fc->cnt = counter;
-	counter = mlx5_fc_create(mdev, false);
-	if (IS_ERR(counter)) {
-		err = PTR_ERR(counter);
-		goto err_tx_drop;
+	if (ipsec->is_uplink_rep) {
+		fc = ipsec_fs_init_single_counter(mdev);
+		if (IS_ERR(fc)) {
+			err = PTR_ERR(fc);
+			goto err_rx_esw_cnt;
+		}
+		ipsec->rx_esw->fc = fc;
+
+		fc = ipsec_fs_init_single_counter(mdev);
+		if (IS_ERR(fc)) {
+			err = PTR_ERR(fc);
+			goto err_tx_esw_cnt;
+		}
+		ipsec->tx_esw->fc = fc;
 	}
 
-	fc->drop = counter;
+	/* Both IPv4 and IPv6 point to same flow counters struct. */
+	ipsec->rx_ipv6->fc = ipsec->rx_ipv4->fc;
 	return 0;
 
-err_tx_drop:
-	mlx5_fc_destroy(mdev, tx->fc->cnt);
+err_tx_esw_cnt:
+	ipsec_fs_destroy_single_counter(mdev, ipsec->rx_esw->fc);
+err_rx_esw_cnt:
+	ipsec_fs_destroy_single_counter(mdev, ipsec->tx->fc);
 err_tx_cnt:
-	kfree(tx->fc);
-err_tx_fc:
-	mlx5_fc_destroy(mdev, rx_ipv4->fc->drop);
-err_rx_drop:
-	mlx5_fc_destroy(mdev, rx_ipv4->fc->cnt);
+	ipsec_fs_destroy_single_counter(mdev, ipsec->rx_ipv4->fc);
 err_rx_cnt:
-	kfree(rx_ipv4->fc);
 	return err;
 }
 
@@ -1489,6 +1525,7 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 	struct mlx5e_ipsec *ipsec = priv->ipsec;
 	struct mlx5e_ipsec_hw_stats *stats;
 	struct mlx5e_ipsec_fc *fc;
+	u64 packets, bytes;
 
 	stats = (struct mlx5e_ipsec_hw_stats *)ipsec_stats;
 
@@ -1510,6 +1547,30 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 	mlx5_fc_query(mdev, fc->cnt, &stats->ipsec_tx_pkts, &stats->ipsec_tx_bytes);
 	mlx5_fc_query(mdev, fc->drop, &stats->ipsec_tx_drop_pkts,
 		      &stats->ipsec_tx_drop_bytes);
+
+	if (ipsec->is_uplink_rep) {
+		fc = ipsec->rx_esw->fc;
+		if (!mlx5_fc_query(mdev, fc->cnt, &packets, &bytes)) {
+			stats->ipsec_rx_pkts += packets;
+			stats->ipsec_rx_bytes += bytes;
+		}
+
+		if (!mlx5_fc_query(mdev, fc->drop, &packets, &bytes)) {
+			stats->ipsec_rx_drop_pkts += packets;
+			stats->ipsec_rx_drop_bytes += bytes;
+		}
+
+		fc = ipsec->tx_esw->fc;
+		if (!mlx5_fc_query(mdev, fc->cnt, &packets, &bytes)) {
+			stats->ipsec_tx_pkts += packets;
+			stats->ipsec_tx_bytes += bytes;
+		}
+
+		if (!mlx5_fc_query(mdev, fc->drop, &packets, &bytes)) {
+			stats->ipsec_tx_drop_pkts += packets;
+			stats->ipsec_tx_drop_bytes += bytes;
+		}
+	}
 }
 
 int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
@@ -1531,12 +1592,12 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		mlx5_packet_reformat_dealloc(mdev, ipsec_rule->pkt_reformat);
 
 	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT) {
-		tx_ft_put(sa_entry->ipsec);
+		tx_ft_put(sa_entry->ipsec, sa_entry->attrs.type);
 		return;
 	}
 
 	mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr);
-	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family);
+	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
 }
 
 int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
@@ -1556,14 +1617,14 @@ void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
 
 	if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) {
 		rx_ft_put_policy(pol_entry->ipsec, pol_entry->attrs.family,
-				 pol_entry->attrs.prio);
+				 pol_entry->attrs.prio, pol_entry->attrs.type);
 		return;
 	}
 
 	if (ipsec_rule->modify_hdr)
 		mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr);
 
-	tx_ft_put_policy(pol_entry->ipsec, pol_entry->attrs.prio);
+	tx_ft_put_policy(pol_entry->ipsec, pol_entry->attrs.prio, pol_entry->attrs.type);
 }
 
 void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
@@ -1571,7 +1632,7 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
 	if (!ipsec->tx)
 		return;
 
-	if (mlx5_ipsec_device_caps(ipsec->mdev) & MLX5_IPSEC_CAP_ROCE)
+	if (ipsec->roce)
 		mlx5_ipsec_fs_roce_cleanup(ipsec->roce);
 
 	ipsec_fs_destroy_counters(ipsec);
@@ -1586,12 +1647,22 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
 	mutex_destroy(&ipsec->rx_ipv6->ft.mutex);
 	WARN_ON(ipsec->rx_ipv6->ft.refcnt);
 	kfree(ipsec->rx_ipv6);
+
+	if (ipsec->is_uplink_rep) {
+		mutex_destroy(&ipsec->tx_esw->ft.mutex);
+		WARN_ON(ipsec->tx_esw->ft.refcnt);
+		kfree(ipsec->tx_esw);
+
+		mutex_destroy(&ipsec->rx_esw->ft.mutex);
+		WARN_ON(ipsec->rx_esw->ft.refcnt);
+		kfree(ipsec->rx_esw);
+	}
 }
 
 int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec)
 {
 	struct mlx5_core_dev *mdev = ipsec->mdev;
-	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_namespace *ns, *ns_esw;
 	int err = -ENOMEM;
 
 	ns = mlx5_get_flow_namespace(ipsec->mdev,
@@ -1599,9 +1670,23 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec)
 	if (!ns)
 		return -EOPNOTSUPP;
 
+	if (ipsec->is_uplink_rep) {
+		ns_esw = mlx5_get_flow_namespace(mdev, MLX5_FLOW_NAMESPACE_FDB);
+		if (!ns_esw)
+			return -EOPNOTSUPP;
+
+		ipsec->tx_esw = kzalloc(sizeof(*ipsec->tx_esw), GFP_KERNEL);
+		if (!ipsec->tx_esw)
+			return -ENOMEM;
+
+		ipsec->rx_esw = kzalloc(sizeof(*ipsec->rx_esw), GFP_KERNEL);
+		if (!ipsec->rx_esw)
+			goto err_rx_esw;
+	}
+
 	ipsec->tx = kzalloc(sizeof(*ipsec->tx), GFP_KERNEL);
 	if (!ipsec->tx)
-		return -ENOMEM;
+		goto err_tx;
 
 	ipsec->rx_ipv4 = kzalloc(sizeof(*ipsec->rx_ipv4), GFP_KERNEL);
 	if (!ipsec->rx_ipv4)
@@ -1620,8 +1705,13 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec)
 	mutex_init(&ipsec->rx_ipv6->ft.mutex);
 	ipsec->tx->ns = ns;
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE)
+	if (ipsec->is_uplink_rep) {
+		mutex_init(&ipsec->tx_esw->ft.mutex);
+		mutex_init(&ipsec->rx_esw->ft.mutex);
+		ipsec->tx_esw->ns = ns_esw;
+	} else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) {
 		ipsec->roce = mlx5_ipsec_fs_roce_init(mdev);
+	}
 
 	return 0;
 
@@ -1631,6 +1721,10 @@ err_rx_ipv6:
 	kfree(ipsec->rx_ipv4);
 err_rx_ipv4:
 	kfree(ipsec->tx);
+err_tx:
+	kfree(ipsec->rx_esw);
+err_rx_esw:
+	kfree(ipsec->tx_esw);
 	return err;
 }
 
@@ -1652,10 +1746,12 @@ void mlx5e_accel_ipsec_fs_modify(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 bool mlx5e_ipsec_fs_tunnel_enabled(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
-	struct mlx5e_ipsec_rx *rx =
-		ipsec_rx(sa_entry->ipsec, sa_entry->attrs.family);
-	struct mlx5e_ipsec_tx *tx = sa_entry->ipsec->tx;
+	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
+	struct mlx5e_ipsec_rx *rx;
+	struct mlx5e_ipsec_tx *tx;
 
+	rx = ipsec_rx(sa_entry->ipsec, attrs->family, attrs->type);
+	tx = ipsec_tx(sa_entry->ipsec, attrs->type);
 	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT)
 		return tx->allow_tunnel_mode;
 
-- 
GitLab


From 6e125265d52d491781e6301b80f885f2453d2e65 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:15 +0300
Subject: [PATCH 0797/1806] net/mlx5e: Refactor IPsec RX tables creation and
 destruction

Add attribute for IPsec RX creation, so rx_create() can be used by
eswitch in later patch. And move the code for TTC dest
connect/disconnect, which are needed only in NIC mode, to individual
functions.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/87478d928479b6a4eee41901204546ea05741815.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec.h       |  11 ++
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 100 ++++++++++++------
 2 files changed, 80 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index e12154276666f..03d83cdf1e207 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -169,6 +169,17 @@ struct mlx5e_ipsec_aso {
 	spinlock_t lock;
 };
 
+struct mlx5e_ipsec_rx_create_attr {
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_ttc_table *ttc;
+	u32 family;
+	int prio;
+	int pol_level;
+	int sa_level;
+	int status_level;
+	enum mlx5_flow_namespace_type chains_ns;
+};
+
 struct mlx5e_ipsec {
 	struct mlx5_core_dev *mdev;
 	struct xarray sadb;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 0f0c48f5f6204..52e382948c134 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -249,13 +249,19 @@ out:
 	return err;
 }
 
+static void ipsec_rx_ft_disconnect(struct mlx5e_ipsec *ipsec, u32 family)
+{
+	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
+
+	mlx5_ttc_fwd_default_dest(ttc, family2tt(family));
+}
+
 static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		       struct mlx5e_ipsec_rx *rx, u32 family)
 {
-	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
 
 	/* disconnect */
-	mlx5_ttc_fwd_default_dest(ttc, family2tt(family));
+	ipsec_rx_ft_disconnect(ipsec, family);
 
 	if (rx->chains) {
 		ipsec_chains_destroy(rx->chains);
@@ -277,41 +283,78 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family);
 }
 
+static void ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				     struct mlx5e_ipsec_rx *rx,
+				     u32 family,
+				     struct mlx5e_ipsec_rx_create_attr *attr)
+{
+	attr->ns = mlx5e_fs_get_ns(ipsec->fs, false);
+	attr->ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
+	attr->family = family;
+	attr->prio = MLX5E_NIC_PRIO;
+	attr->pol_level = MLX5E_ACCEL_FS_POL_FT_LEVEL;
+	attr->sa_level = MLX5E_ACCEL_FS_ESP_FT_LEVEL;
+	attr->status_level = MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL;
+	attr->chains_ns = MLX5_FLOW_NAMESPACE_KERNEL;
+}
+
+static int ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
+					 struct mlx5e_ipsec_rx *rx,
+					 struct mlx5e_ipsec_rx_create_attr *attr,
+					 struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_table *ft;
+	int err;
+
+	*dest = mlx5_ttc_get_default_dest(attr->ttc, family2tt(attr->family));
+	err = mlx5_ipsec_fs_roce_rx_create(ipsec->mdev, ipsec->roce, attr->ns, dest,
+					   attr->family, MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
+					   attr->prio);
+	if (err)
+		return err;
+
+	ft = mlx5_ipsec_fs_roce_ft_get(ipsec->roce, attr->family);
+	if (ft) {
+		dest->type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+		dest->ft = ft;
+	}
+
+	return 0;
+}
+
+static void ipsec_rx_ft_connect(struct mlx5e_ipsec *ipsec,
+				struct mlx5e_ipsec_rx *rx,
+				struct mlx5e_ipsec_rx_create_attr *attr)
+{
+	struct mlx5_flow_destination dest = {};
+
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest.ft = rx->ft.pol;
+	mlx5_ttc_fwd_dest(attr->ttc, family2tt(attr->family), &dest);
+}
+
 static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		     struct mlx5e_ipsec_rx *rx, u32 family)
 {
-	struct mlx5_flow_namespace *ns = mlx5e_fs_get_ns(ipsec->fs, false);
-	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
-	struct mlx5_flow_destination default_dest;
+	struct mlx5e_ipsec_rx_create_attr attr;
 	struct mlx5_flow_destination dest[2];
 	struct mlx5_flow_table *ft;
 	u32 flags = 0;
 	int err;
 
-	default_dest = mlx5_ttc_get_default_dest(ttc, family2tt(family));
-	err = mlx5_ipsec_fs_roce_rx_create(mdev, ipsec->roce, ns, &default_dest,
-					   family, MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
-					   MLX5E_NIC_PRIO);
+	ipsec_rx_create_attr_set(ipsec, rx, family, &attr);
+
+	err = ipsec_rx_status_pass_dest_get(ipsec, rx, &attr, &dest[0]);
 	if (err)
 		return err;
 
-	ft = ipsec_ft_create(ns, MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL,
-			     MLX5E_NIC_PRIO, 1, 0);
+	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 1, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft_status;
 	}
-
 	rx->ft.status = ft;
 
-	ft = mlx5_ipsec_fs_roce_ft_get(ipsec->roce, family);
-	if (ft) {
-		dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-		dest[0].ft = ft;
-	} else {
-		dest[0] = default_dest;
-	}
-
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 	dest[1].counter_id = mlx5_fc_id(rx->fc->cnt);
 	err = ipsec_status_rule(mdev, rx, dest);
@@ -323,8 +366,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (rx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	ft = ipsec_ft_create(ns, MLX5E_ACCEL_FS_ESP_FT_LEVEL, MLX5E_NIC_PRIO, 2,
-			     flags);
+	ft = ipsec_ft_create(attr.ns, attr.sa_level, attr.prio, 2, flags);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft;
@@ -337,9 +379,9 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
 		rx->chains = ipsec_chains_create(mdev, rx->ft.sa,
-						 MLX5_FLOW_NAMESPACE_KERNEL,
-						 MLX5E_NIC_PRIO,
-						 MLX5E_ACCEL_FS_POL_FT_LEVEL,
+						 attr.chains_ns,
+						 attr.prio,
+						 attr.pol_level,
 						 &rx->ft.pol);
 		if (IS_ERR(rx->chains)) {
 			err = PTR_ERR(rx->chains);
@@ -349,8 +391,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		goto connect;
 	}
 
-	ft = ipsec_ft_create(ns, MLX5E_ACCEL_FS_POL_FT_LEVEL, MLX5E_NIC_PRIO,
-			     2, 0);
+	ft = ipsec_ft_create(attr.ns, attr.pol_level, attr.prio, 2, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_pol_ft;
@@ -365,10 +406,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 
 connect:
 	/* connect */
-	memset(dest, 0x00, sizeof(*dest));
-	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest[0].ft = rx->ft.pol;
-	mlx5_ttc_fwd_dest(ttc, family2tt(family), &dest[0]);
+	ipsec_rx_ft_connect(ipsec, rx, &attr);
 	return 0;
 
 err_pol_miss:
-- 
GitLab


From 1762f132d54200ffa008e86f9f6c96ab4ee3fb71 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:16 +0300
Subject: [PATCH 0798/1806] net/mlx5e: Support IPsec packet offload for RX in
 switchdev mode

As decryption must be done first, add new prio for IPsec offload in
FDB, and put it just lower than BYPASS prio and higher than TC prio.
Three levels are added for RX. The first one is for ip xfrm policy. SA
table is created in the second level for ip xfrm state. The status
table is created in the last to check the decryption result. If
success, packets continue with the next process, or dropped otherwise.
For now, the set of reg c1 is removed for swtichdev mode, and the
datapath process will be added in the next patch.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/c91063554cf643fb50b99cf093e8a9bf11729de5.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/Makefile  |   4 +
 .../mellanox/mlx5/core/en_accel/ipsec.h       |  41 +++-
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    |  80 ++++----
 .../mlx5/core/en_accel/ipsec_offload.c        |   5 +-
 .../mellanox/mlx5/core/esw/ipsec_fs.c         | 184 ++++++++++++++++++
 .../mellanox/mlx5/core/esw/ipsec_fs.h         |  39 ++++
 .../net/ethernet/mellanox/mlx5/core/fs_core.c |   6 +
 include/linux/mlx5/fs.h                       |   1 +
 8 files changed, 313 insertions(+), 47 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 35f00700a4d6c..63a2f2bb80a6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -75,6 +75,10 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/acl/helper.o \
 				      esw/acl/egress_lgcy.o esw/acl/egress_ofld.o \
 				      esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o
 
+ifneq ($(CONFIG_MLX5_EN_IPSEC),)
+	mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/ipsec_fs.o
+endif
+
 mlx5_core-$(CONFIG_MLX5_BRIDGE)    += esw/bridge.o esw/bridge_mcast.o esw/bridge_debugfs.o \
 				      en/rep/bridge.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 03d83cdf1e207..578af9d7aef3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -143,7 +143,7 @@ struct mlx5e_ipsec_sw_stats {
 	atomic64_t ipsec_tx_drop_trailer;
 };
 
-struct mlx5e_ipsec_rx;
+struct mlx5e_ipsec_fc;
 struct mlx5e_ipsec_tx;
 
 struct mlx5e_ipsec_work {
@@ -180,6 +180,38 @@ struct mlx5e_ipsec_rx_create_attr {
 	enum mlx5_flow_namespace_type chains_ns;
 };
 
+struct mlx5e_ipsec_ft {
+	struct mutex mutex; /* Protect changes to this struct */
+	struct mlx5_flow_table *pol;
+	struct mlx5_flow_table *sa;
+	struct mlx5_flow_table *status;
+	u32 refcnt;
+};
+
+struct mlx5e_ipsec_rule {
+	struct mlx5_flow_handle *rule;
+	struct mlx5_modify_hdr *modify_hdr;
+	struct mlx5_pkt_reformat *pkt_reformat;
+	struct mlx5_fc *fc;
+};
+
+struct mlx5e_ipsec_miss {
+	struct mlx5_flow_group *group;
+	struct mlx5_flow_handle *rule;
+};
+
+struct mlx5e_ipsec_rx {
+	struct mlx5e_ipsec_ft ft;
+	struct mlx5e_ipsec_miss pol;
+	struct mlx5e_ipsec_miss sa;
+	struct mlx5e_ipsec_rule status;
+	struct mlx5e_ipsec_miss status_drop;
+	struct mlx5_fc *status_drop_cnt;
+	struct mlx5e_ipsec_fc *fc;
+	struct mlx5_fs_chains *chains;
+	u8 allow_tunnel_mode : 1;
+};
+
 struct mlx5e_ipsec {
 	struct mlx5_core_dev *mdev;
 	struct xarray sadb;
@@ -205,13 +237,6 @@ struct mlx5e_ipsec_esn_state {
 	u8 overlap: 1;
 };
 
-struct mlx5e_ipsec_rule {
-	struct mlx5_flow_handle *rule;
-	struct mlx5_modify_hdr *modify_hdr;
-	struct mlx5_pkt_reformat *pkt_reformat;
-	struct mlx5_fc *fc;
-};
-
 struct mlx5e_ipsec_limits {
 	u64 round;
 	u8 soft_limit_hit : 1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 52e382948c134..2db16e49abc10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -9,6 +9,7 @@
 #include "fs_core.h"
 #include "lib/ipsec_fs_roce.h"
 #include "lib/fs_chains.h"
+#include "esw/ipsec_fs.h"
 
 #define NUM_IPSEC_FTE BIT(15)
 #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16
@@ -19,29 +20,6 @@ struct mlx5e_ipsec_fc {
 	struct mlx5_fc *drop;
 };
 
-struct mlx5e_ipsec_ft {
-	struct mutex mutex; /* Protect changes to this struct */
-	struct mlx5_flow_table *pol;
-	struct mlx5_flow_table *sa;
-	struct mlx5_flow_table *status;
-	u32 refcnt;
-};
-
-struct mlx5e_ipsec_miss {
-	struct mlx5_flow_group *group;
-	struct mlx5_flow_handle *rule;
-};
-
-struct mlx5e_ipsec_rx {
-	struct mlx5e_ipsec_ft ft;
-	struct mlx5e_ipsec_miss pol;
-	struct mlx5e_ipsec_miss sa;
-	struct mlx5e_ipsec_rule status;
-	struct mlx5e_ipsec_fc *fc;
-	struct mlx5_fs_chains *chains;
-	u8 allow_tunnel_mode : 1;
-};
-
 struct mlx5e_ipsec_tx {
 	struct mlx5e_ipsec_ft ft;
 	struct mlx5e_ipsec_miss pol;
@@ -259,9 +237,9 @@ static void ipsec_rx_ft_disconnect(struct mlx5e_ipsec *ipsec, u32 family)
 static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		       struct mlx5e_ipsec_rx *rx, u32 family)
 {
-
 	/* disconnect */
-	ipsec_rx_ft_disconnect(ipsec, family);
+	if (rx != ipsec->rx_esw)
+		ipsec_rx_ft_disconnect(ipsec, family);
 
 	if (rx->chains) {
 		ipsec_chains_destroy(rx->chains);
@@ -276,8 +254,12 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_destroy_flow_table(rx->ft.sa);
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-	mlx5_del_flow_rules(rx->status.rule);
-	mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
+	if (rx == ipsec->rx_esw) {
+		mlx5_esw_ipsec_rx_status_destroy(ipsec, rx);
+	} else {
+		mlx5_del_flow_rules(rx->status.rule);
+		mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
+	}
 	mlx5_destroy_flow_table(rx->ft.status);
 
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family);
@@ -288,6 +270,13 @@ static void ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				     u32 family,
 				     struct mlx5e_ipsec_rx_create_attr *attr)
 {
+	if (rx == ipsec->rx_esw) {
+		/* For packet offload in switchdev mode, RX & TX use FDB namespace */
+		attr->ns = ipsec->tx_esw->ns;
+		mlx5_esw_ipsec_rx_create_attr_set(ipsec, attr);
+		return;
+	}
+
 	attr->ns = mlx5e_fs_get_ns(ipsec->fs, false);
 	attr->ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
 	attr->family = family;
@@ -306,6 +295,9 @@ static int ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 	struct mlx5_flow_table *ft;
 	int err;
 
+	if (rx == ipsec->rx_esw)
+		return mlx5_esw_ipsec_rx_status_pass_dest_get(ipsec, dest);
+
 	*dest = mlx5_ttc_get_default_dest(attr->ttc, family2tt(attr->family));
 	err = mlx5_ipsec_fs_roce_rx_create(ipsec->mdev, ipsec->roce, attr->ns, dest,
 					   attr->family, MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
@@ -357,7 +349,10 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 	dest[1].counter_id = mlx5_fc_id(rx->fc->cnt);
-	err = ipsec_status_rule(mdev, rx, dest);
+	if (rx == ipsec->rx_esw)
+		err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest);
+	else
+		err = ipsec_status_rule(mdev, rx, dest);
 	if (err)
 		goto err_add;
 
@@ -406,7 +401,8 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 
 connect:
 	/* connect */
-	ipsec_rx_ft_connect(ipsec, rx, &attr);
+	if (rx != ipsec->rx_esw)
+		ipsec_rx_ft_connect(ipsec, rx, &attr);
 	return 0;
 
 err_pol_miss:
@@ -864,18 +860,22 @@ static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upsp
 	}
 }
 
-static enum mlx5_flow_namespace_type ipsec_fs_get_ns(struct mlx5e_ipsec *ipsec, u8 dir)
+static enum mlx5_flow_namespace_type ipsec_fs_get_ns(struct mlx5e_ipsec *ipsec,
+						     int type, u8 dir)
 {
+	if (ipsec->is_uplink_rep && type == XFRM_DEV_OFFLOAD_PACKET)
+		return MLX5_FLOW_NAMESPACE_FDB;
+
 	if (dir == XFRM_DEV_OFFLOAD_IN)
 		return MLX5_FLOW_NAMESPACE_KERNEL;
 
 	return MLX5_FLOW_NAMESPACE_EGRESS;
 }
 
-static int setup_modify_header(struct mlx5e_ipsec *ipsec, u32 val, u8 dir,
+static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8 dir,
 			       struct mlx5_flow_act *flow_act)
 {
-	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, dir);
+	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, type, dir);
 	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
 	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_modify_hdr *modify_hdr;
@@ -1085,7 +1085,8 @@ static int setup_pkt_reformat(struct mlx5e_ipsec *ipsec,
 			      struct mlx5_accel_esp_xfrm_attrs *attrs,
 			      struct mlx5_flow_act *flow_act)
 {
-	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, attrs->dir);
+	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, attrs->type,
+								attrs->dir);
 	struct mlx5_pkt_reformat_params reformat_params = {};
 	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_pkt_reformat *pkt_reformat;
@@ -1127,7 +1128,7 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5_flow_spec *spec;
 	struct mlx5e_ipsec_rx *rx;
 	struct mlx5_fc *counter;
-	int err;
+	int err = 0;
 
 	rx = rx_ft_get(mdev, ipsec, attrs->family, attrs->type);
 	if (IS_ERR(rx))
@@ -1148,8 +1149,10 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
 
-	err = setup_modify_header(ipsec, sa_entry->ipsec_obj_id | BIT(31),
-				  XFRM_DEV_OFFLOAD_IN, &flow_act);
+	if (rx != ipsec->rx_esw)
+		err = setup_modify_header(ipsec, attrs->type,
+					  sa_entry->ipsec_obj_id | BIT(31),
+					  XFRM_DEV_OFFLOAD_IN, &flow_act);
 	if (err)
 		goto err_mod_header;
 
@@ -1340,7 +1343,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 		if (!attrs->reqid)
 			break;
 
-		err = setup_modify_header(ipsec, attrs->reqid,
+		err = setup_modify_header(ipsec, attrs->type, attrs->reqid,
 					  XFRM_DEV_OFFLOAD_OUT, &flow_act);
 		if (err)
 			goto err_mod_header;
@@ -1388,6 +1391,7 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 {
 	struct mlx5_accel_pol_xfrm_attrs *attrs = &pol_entry->attrs;
 	struct mlx5_core_dev *mdev = mlx5e_ipsec_pol2dev(pol_entry);
+	struct mlx5e_ipsec *ipsec = pol_entry->ipsec;
 	struct mlx5_flow_destination dest[2];
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_handle *rule;
@@ -1433,6 +1437,8 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	}
 
 	flow_act.flags |= FLOW_ACT_NO_APPEND;
+	if (rx == ipsec->rx_esw && rx->chains)
+		flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest[dstn].ft = rx->ft.sa;
 	dstn++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 5ff06263c5bd2..3245d1c9d5392 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -45,8 +45,9 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap))
 			caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD;
 
-		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
-		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level))
+		if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
+		     MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
+		    MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))
 			caps |= MLX5_IPSEC_CAP_PRIO;
 
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
new file mode 100644
index 0000000000000..7df7a8b0a6a09
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+#include "fs_core.h"
+#include "eswitch.h"
+#include "en_accel/ipsec.h"
+#include "esw/ipsec_fs.h"
+
+enum {
+	MLX5_ESW_IPSEC_RX_POL_FT_LEVEL,
+	MLX5_ESW_IPSEC_RX_ESP_FT_LEVEL,
+	MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL,
+};
+
+static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
+					     struct mlx5e_ipsec_rx *rx)
+{
+	mlx5_del_flow_rules(rx->status_drop.rule);
+	mlx5_destroy_flow_group(rx->status_drop.group);
+	mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt);
+}
+
+static void esw_ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
+					     struct mlx5e_ipsec_rx *rx)
+{
+	mlx5_del_flow_rules(rx->status.rule);
+	mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
+}
+
+static int esw_ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec,
+					   struct mlx5e_ipsec_rx *rx)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *flow_counter;
+	struct mlx5_flow_spec *spec;
+	struct mlx5_flow_group *g;
+	u32 *flow_group_in;
+	int err = 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!flow_group_in || !spec) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
+	g = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop flow group, err=%d\n", err);
+		goto err_out;
+	}
+
+	flow_counter = mlx5_fc_create(mdev, false);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule;
+	}
+
+	rx->status_drop.group = g;
+	rx->status_drop.rule = rule;
+	rx->status_drop_cnt = flow_counter;
+
+	kvfree(flow_group_in);
+	kvfree(spec);
+	return 0;
+
+err_rule:
+	mlx5_fc_destroy(mdev, flow_counter);
+err_cnt:
+	mlx5_destroy_flow_group(g);
+err_out:
+	kvfree(flow_group_in);
+	kvfree(spec);
+	return err;
+}
+
+static int esw_ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
+					   struct mlx5e_ipsec_rx *rx,
+					   struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.ipsec_syndrome, 0);
+	spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	flow_act.flags = FLOW_ACT_NO_APPEND;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_warn(ipsec->mdev,
+			       "Failed to add ipsec rx status pass rule, err=%d\n", err);
+		goto err_rule;
+	}
+
+	rx->status.rule = rule;
+	kvfree(spec);
+	return 0;
+
+err_rule:
+	kvfree(spec);
+	return err;
+}
+
+void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
+				      struct mlx5e_ipsec_rx *rx)
+{
+	esw_ipsec_rx_status_pass_destroy(ipsec, rx);
+	esw_ipsec_rx_status_drop_destroy(ipsec, rx);
+}
+
+int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
+				    struct mlx5e_ipsec_rx *rx,
+				    struct mlx5_flow_destination *dest)
+{
+	int err;
+
+	err = esw_ipsec_rx_status_drop_create(ipsec, rx);
+	if (err)
+		return err;
+
+	err = esw_ipsec_rx_status_pass_create(ipsec, rx, dest);
+	if (err)
+		goto err_pass_create;
+
+	return 0;
+
+err_pass_create:
+	esw_ipsec_rx_status_drop_destroy(ipsec, rx);
+	return err;
+}
+
+void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx_create_attr *attr)
+{
+	attr->prio = FDB_CRYPTO_INGRESS;
+	attr->pol_level = MLX5_ESW_IPSEC_RX_POL_FT_LEVEL;
+	attr->sa_level = MLX5_ESW_IPSEC_RX_ESP_FT_LEVEL;
+	attr->status_level = MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL;
+	attr->chains_ns = MLX5_FLOW_NAMESPACE_FDB;
+}
+
+int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
+					   struct mlx5_flow_destination *dest)
+{
+	dest->type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest->ft = mlx5_chains_get_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
new file mode 100644
index 0000000000000..1d6104648d32b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5_ESW_IPSEC_FS_H__
+#define __MLX5_ESW_IPSEC_FS_H__
+
+struct mlx5e_ipsec;
+
+#ifdef CONFIG_MLX5_ESWITCH
+void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
+				      struct mlx5e_ipsec_rx *rx);
+int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
+				    struct mlx5e_ipsec_rx *rx,
+				    struct mlx5_flow_destination *dest);
+void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx_create_attr *attr);
+int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
+					   struct mlx5_flow_destination *dest);
+#else
+static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
+						    struct mlx5e_ipsec_rx *rx) {}
+
+static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
+						  struct mlx5e_ipsec_rx *rx,
+						  struct mlx5_flow_destination *dest)
+{
+	return  -EINVAL;
+}
+
+static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
+						     struct mlx5e_ipsec_rx_create_attr *attr) {}
+
+static inline int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
+							 struct mlx5_flow_destination *dest)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_MLX5_ESWITCH */
+#endif /* __MLX5_ESW_IPSEC_FS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 4ef04aa287719..8ae1854d6b73c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2987,6 +2987,12 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 	if (err)
 		goto out_err;
 
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_CRYPTO_INGRESS, 3);
+	if (IS_ERR(maj_prio)) {
+		err = PTR_ERR(maj_prio);
+		goto out_err;
+	}
+
 	err = create_fdb_fast_path(steering);
 	if (err)
 		goto out_err;
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 2cb404c7ea131..6b1fa94f69c87 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -109,6 +109,7 @@ enum mlx5_flow_namespace_type {
 
 enum {
 	FDB_BYPASS_PATH,
+	FDB_CRYPTO_INGRESS,
 	FDB_TC_OFFLOAD,
 	FDB_FT_OFFLOAD,
 	FDB_TC_MISS,
-- 
GitLab


From 91bafc638ed4128eaca074fe7e88a5444db14325 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:17 +0300
Subject: [PATCH 0799/1806] net/mlx5e: Handle IPsec offload for RX datapath in
 switchdev mode

Reuse tun opts bits in reg c1, to pass IPsec obj id to datapath.
As this is only for RX SA and there are only 11 bits, xarray is used
to map IPsec obj id to an index, which is between 1 and 0x7ff, and
replace obj id to write to reg c1.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/43d60fbcc9cd672a97d7e2a2f7fe6a3d9e9a776d.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/en/rep/tc.c   | 17 ++++-
 .../mellanox/mlx5/core/en_accel/ipsec.h       |  2 +
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    |  7 ++
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.c  | 22 ++++++
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.h  |  2 +
 .../mellanox/mlx5/core/esw/ipsec_fs.c         | 69 +++++++++++++++++++
 .../mellanox/mlx5/core/esw/ipsec_fs.h         | 20 ++++++
 include/linux/mlx5/eswitch.h                  |  3 +
 8 files changed, 139 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index b5c773ffc7632..b12fe3c5a2585 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -715,9 +715,20 @@ void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq,
 	uplink_priv = &uplink_rpriv->uplink_priv;
 	ct_priv = uplink_priv->ct_priv;
 
-	if (!mlx5_ipsec_is_rx_flow(cqe) &&
-	    !mlx5e_tc_update_skb(cqe, skb, mapping_ctx, reg_c0, ct_priv, zone_restore_id, tunnel_id,
-				 &tc_priv))
+#ifdef CONFIG_MLX5_EN_IPSEC
+	if (!(tunnel_id >> ESW_TUN_OPTS_BITS)) {
+		u32 mapped_id;
+		u32 metadata;
+
+		mapped_id = tunnel_id & ESW_IPSEC_RX_MAPPED_ID_MASK;
+		if (mapped_id &&
+		    !mlx5_esw_ipsec_rx_make_metadata(priv, mapped_id, &metadata))
+			mlx5e_ipsec_offload_handle_rx_skb(priv->netdev, skb, metadata);
+	}
+#endif
+
+	if (!mlx5e_tc_update_skb(cqe, skb, mapping_ctx, reg_c0, ct_priv,
+				 zone_restore_id, tunnel_id, &tc_priv))
 		goto free_skb;
 
 forward:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 578af9d7aef3c..168b9600bde31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -210,6 +210,7 @@ struct mlx5e_ipsec_rx {
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fs_chains *chains;
 	u8 allow_tunnel_mode : 1;
+	struct xarray ipsec_obj_id_map;
 };
 
 struct mlx5e_ipsec {
@@ -256,6 +257,7 @@ struct mlx5e_ipsec_sa_entry {
 	struct mlx5e_ipsec_work *work;
 	struct mlx5e_ipsec_dwork *dwork;
 	struct mlx5e_ipsec_limits limits;
+	u32 rx_mapped_id;
 };
 
 struct mlx5_accel_pol_xfrm_attrs {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 2db16e49abc10..84322e85cd23a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -1153,6 +1153,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		err = setup_modify_header(ipsec, attrs->type,
 					  sa_entry->ipsec_obj_id | BIT(31),
 					  XFRM_DEV_OFFLOAD_IN, &flow_act);
+	else
+		err = mlx5_esw_ipsec_rx_setup_modify_header(sa_entry, &flow_act);
+
 	if (err)
 		goto err_mod_header;
 
@@ -1641,6 +1644,7 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	}
 
 	mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr);
+	mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry);
 	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
 }
 
@@ -1693,6 +1697,8 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
 	kfree(ipsec->rx_ipv6);
 
 	if (ipsec->is_uplink_rep) {
+		xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map);
+
 		mutex_destroy(&ipsec->tx_esw->ft.mutex);
 		WARN_ON(ipsec->tx_esw->ft.refcnt);
 		kfree(ipsec->tx_esw);
@@ -1753,6 +1759,7 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec)
 		mutex_init(&ipsec->tx_esw->ft.mutex);
 		mutex_init(&ipsec->rx_esw->ft.mutex);
 		ipsec->tx_esw->ns = ns_esw;
+		xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
 	} else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) {
 		ipsec->roce = mlx5_ipsec_fs_roce_init(mdev);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 8d6379ac4574e..c00fe0d5ea11e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -37,6 +37,7 @@
 #include "ipsec.h"
 #include "ipsec_rxtx.h"
 #include "en.h"
+#include "esw/ipsec_fs.h"
 
 enum {
 	MLX5E_IPSEC_TX_SYNDROME_OFFLOAD = 0x8,
@@ -355,3 +356,24 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 		atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_syndrome);
 	}
 }
+
+int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metadata)
+{
+	struct mlx5e_ipsec *ipsec = priv->ipsec;
+	u32 ipsec_obj_id;
+	int err;
+
+	if (!ipsec || !ipsec->is_uplink_rep)
+		return -EINVAL;
+
+	err = mlx5_esw_ipsec_rx_ipsec_obj_id_search(priv, id, &ipsec_obj_id);
+	if (err) {
+		atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_sadb_miss);
+		return err;
+	}
+
+	*metadata = MLX5_IPSEC_METADATA_CREATE(ipsec_obj_id,
+					       MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 436e9a8a32d30..9ee014a8ad24a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -43,6 +43,7 @@
 #define MLX5_IPSEC_METADATA_MARKER(metadata)  (((metadata) >> 31) & 0x1)
 #define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(5, 0))
 #define MLX5_IPSEC_METADATA_HANDLE(metadata)  ((metadata) & GENMASK(23, 0))
+#define MLX5_IPSEC_METADATA_CREATE(id, syndrome) ((id) | ((syndrome) << 24))
 
 struct mlx5e_accel_tx_ipsec_state {
 	struct xfrm_offload *xo;
@@ -67,6 +68,7 @@ void mlx5e_ipsec_handle_tx_wqe(struct mlx5e_tx_wqe *wqe,
 void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct sk_buff *skb,
 				       u32 ipsec_meta_data);
+int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metadata);
 static inline unsigned int mlx5e_ipsec_tx_ids_len(struct mlx5e_accel_tx_ipsec_state *ipsec_st)
 {
 	return ipsec_st->tailen;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 7df7a8b0a6a09..0675587c1a79f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -182,3 +182,72 @@ int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 
 	return 0;
 }
+
+int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_act *flow_act)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_modify_hdr *modify_hdr;
+	u32 mapped_id;
+	int err;
+
+	err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id,
+			  xa_mk_value(sa_entry->ipsec_obj_id),
+			  XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0);
+	if (err)
+		return err;
+
+	/* reuse tunnel bits for ipsec,
+	 * tun_id is always 0 and tun_opts is mapped to ipsec_obj_id.
+	 */
+	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action, field,
+		 MLX5_ACTION_IN_FIELD_METADATA_REG_C_1);
+	MLX5_SET(set_action_in, action, offset, ESW_ZONE_ID_BITS);
+	MLX5_SET(set_action_in, action, length,
+		 ESW_TUN_ID_BITS + ESW_TUN_OPTS_BITS);
+	MLX5_SET(set_action_in, action, data, mapped_id);
+
+	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_FDB,
+					      1, action);
+	if (IS_ERR(modify_hdr)) {
+		err = PTR_ERR(modify_hdr);
+		goto err_header_alloc;
+	}
+
+	sa_entry->rx_mapped_id = mapped_id;
+	flow_act->modify_hdr = modify_hdr;
+	flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+
+	return 0;
+
+err_header_alloc:
+	xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id);
+	return err;
+}
+
+void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+
+	if (sa_entry->rx_mapped_id)
+		xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map,
+			    sa_entry->rx_mapped_id);
+}
+
+int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
+					  u32 *ipsec_obj_id)
+{
+	struct mlx5e_ipsec *ipsec = priv->ipsec;
+	void *val;
+
+	val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id);
+	if (!val)
+		return -ENOENT;
+
+	*ipsec_obj_id = xa_to_value(val);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index 1d6104648d32b..44df34032d1ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -5,6 +5,7 @@
 #define __MLX5_ESW_IPSEC_FS_H__
 
 struct mlx5e_ipsec;
+struct mlx5e_ipsec_sa_entry;
 
 #ifdef CONFIG_MLX5_ESWITCH
 void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
@@ -16,6 +17,11 @@ void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx_create_attr *attr);
 int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 					   struct mlx5_flow_destination *dest);
+int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_act *flow_act);
+void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry);
+int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
+					  u32 *ipsec_obj_id);
 #else
 static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 						    struct mlx5e_ipsec_rx *rx) {}
@@ -35,5 +41,19 @@ static inline int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ips
 {
 	return -EINVAL;
 }
+
+static inline int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
+							struct mlx5_flow_act *flow_act)
+{
+	return -EINVAL;
+}
+
+static inline void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry) {}
+
+static inline int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
+							u32 *ipsec_obj_id)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index e2701ed0200e2..950d2431a53c8 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -144,6 +144,9 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
 	GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \
 		ESW_TUN_OPTS_OFFSET + 1)
 
+/* reuse tun_opts for the mapped ipsec obj id when tun_id is 0 (invalid) */
+#define ESW_IPSEC_RX_MAPPED_ID_MASK GENMASK(ESW_TUN_OPTS_BITS - 1, 0)
+
 u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev);
 u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);
 struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw);
-- 
GitLab


From f46e92d664fb6a3751e90812419decf5e178e06a Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:18 +0300
Subject: [PATCH 0800/1806] net/mlx5e: Refactor IPsec TX tables creation

Add attribute for IPsec TX creation, pass all needed parameters in it,
so tx_create() can be used by eswitch.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/24d5ab988b0db2d39b7fde321b44ffe885d47828.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec.h       |  8 ++++++
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 26 ++++++++++++++-----
 2 files changed, 28 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 168b9600bde31..9e7c42c2f77b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -213,6 +213,14 @@ struct mlx5e_ipsec_rx {
 	struct xarray ipsec_obj_id_map;
 };
 
+struct mlx5e_ipsec_tx_create_attr {
+	int prio;
+	int pol_level;
+	int sa_level;
+	int cnt_level;
+	enum mlx5_flow_namespace_type chains_ns;
+};
+
 struct mlx5e_ipsec {
 	struct mlx5_core_dev *mdev;
 	struct xarray sadb;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 84322e85cd23a..6d4d2b824b754 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -569,15 +569,29 @@ static void tx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 	mlx5_destroy_flow_table(tx->ft.status);
 }
 
-static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
+static void ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				     struct mlx5e_ipsec_tx *tx,
+				     struct mlx5e_ipsec_tx_create_attr *attr)
+{
+	attr->prio = 0;
+	attr->pol_level = 0;
+	attr->sa_level = 1;
+	attr->cnt_level = 2;
+	attr->chains_ns = MLX5_FLOW_NAMESPACE_EGRESS_IPSEC;
+}
+
+static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		     struct mlx5_ipsec_fs *roce)
 {
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5e_ipsec_tx_create_attr attr;
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_table *ft;
 	u32 flags = 0;
 	int err;
 
-	ft = ipsec_ft_create(tx->ns, 2, 0, 1, 0);
+	ipsec_tx_create_attr_set(ipsec, tx, &attr);
+	ft = ipsec_ft_create(tx->ns, attr.cnt_level, attr.prio, 1, 0);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 	tx->ft.status = ft;
@@ -590,7 +604,7 @@ static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (tx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	ft = ipsec_ft_create(tx->ns, 1, 0, 4, flags);
+	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 4, flags);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_sa_ft;
@@ -599,7 +613,7 @@ static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
 		tx->chains = ipsec_chains_create(
-			mdev, tx->ft.sa, MLX5_FLOW_NAMESPACE_EGRESS_IPSEC, 0, 0,
+			mdev, tx->ft.sa, attr.chains_ns, attr.prio, attr.pol_level,
 			&tx->ft.pol);
 		if (IS_ERR(tx->chains)) {
 			err = PTR_ERR(tx->chains);
@@ -609,7 +623,7 @@ static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 		goto connect_roce;
 	}
 
-	ft = ipsec_ft_create(tx->ns, 0, 0, 2, 0);
+	ft = ipsec_ft_create(tx->ns, attr.pol_level, attr.prio, 2, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_pol_ft;
@@ -656,7 +670,7 @@ static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (tx->ft.refcnt)
 		goto skip;
 
-	err = tx_create(mdev, tx, ipsec->roce);
+	err = tx_create(ipsec, tx, ipsec->roce);
 	if (err)
 		return err;
 
-- 
GitLab


From c6c2bf5db4ea14b316af1fd03cc6c5c61f751f79 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:19 +0300
Subject: [PATCH 0801/1806] net/mlx5e: Support IPsec packet offload for TX in
 switchdev mode

The IPsec encryption is done at the last, so add new prio for IPsec
offload in FDB, and put it just lower than the slow path prio and
higher than the per-vport prio.
Three levels are added for TX. The first one is for ip xfrm policy.
The sa table is created in the second level for ip xfrm state. The
status table is created at the last to count the number of packets
encrypted.
The rules, which forward packets to uplink, are changed to forward
them to IPsec TX tables first. These rules are restored after those
tables are destroyed, which is done immediately when there is no
reference to them, just as what does in legacy mode. The support for
slow path is added here, by refreshing uplink's channels. But, the
handling for TC fast path, which is more complicated, will be added
later. Besides, reg c4 is used instead to match reqid.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/cfd0e6ffaf0b8c55ebaa9fb0649b7c504b6b8ec6.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 70 ++++++++++++++++---
 .../mellanox/mlx5/core/esw/ipsec_fs.c         | 16 +++++
 .../mellanox/mlx5/core/esw/ipsec_fs.h         |  5 ++
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  1 +
 .../mellanox/mlx5/core/eswitch_offloads.c     | 11 +++
 .../net/ethernet/mellanox/mlx5/core/fs_core.c |  6 ++
 include/linux/mlx5/fs.h                       |  1 +
 7 files changed, 101 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 6d4d2b824b754..36704c9fce33d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -10,6 +10,7 @@
 #include "lib/ipsec_fs_roce.h"
 #include "lib/fs_chains.h"
 #include "esw/ipsec_fs.h"
+#include "en_rep.h"
 
 #define NUM_IPSEC_FTE BIT(15)
 #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16
@@ -23,6 +24,7 @@ struct mlx5e_ipsec_fc {
 struct mlx5e_ipsec_tx {
 	struct mlx5e_ipsec_ft ft;
 	struct mlx5e_ipsec_miss pol;
+	struct mlx5e_ipsec_miss sa;
 	struct mlx5e_ipsec_rule status;
 	struct mlx5_flow_namespace *ns;
 	struct mlx5e_ipsec_fc *fc;
@@ -550,7 +552,7 @@ err_rule:
 }
 
 /* IPsec TX flow steering */
-static void tx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
+static void tx_destroy(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		       struct mlx5_ipsec_fs *roce)
 {
 	mlx5_ipsec_fs_roce_tx_destroy(roce);
@@ -562,9 +564,13 @@ static void tx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 		mlx5_destroy_flow_table(tx->ft.pol);
 	}
 
+	if (tx == ipsec->tx_esw) {
+		mlx5_del_flow_rules(tx->sa.rule);
+		mlx5_destroy_flow_group(tx->sa.group);
+	}
 	mlx5_destroy_flow_table(tx->ft.sa);
 	if (tx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
+		mlx5_eswitch_unblock_encap(ipsec->mdev);
 	mlx5_del_flow_rules(tx->status.rule);
 	mlx5_destroy_flow_table(tx->ft.status);
 }
@@ -573,6 +579,11 @@ static void ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				     struct mlx5e_ipsec_tx *tx,
 				     struct mlx5e_ipsec_tx_create_attr *attr)
 {
+	if (tx == ipsec->tx_esw) {
+		mlx5_esw_ipsec_tx_create_attr_set(ipsec, attr);
+		return;
+	}
+
 	attr->prio = 0;
 	attr->pol_level = 0;
 	attr->sa_level = 1;
@@ -611,6 +622,15 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 	}
 	tx->ft.sa = ft;
 
+	if (tx == ipsec->tx_esw) {
+		dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+		dest.vport.num = MLX5_VPORT_UPLINK;
+		err = ipsec_miss_create(mdev, tx->ft.sa, &tx->sa, &dest);
+		if (err)
+			goto err_sa_miss;
+		memset(&dest, 0, sizeof(dest));
+	}
+
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
 		tx->chains = ipsec_chains_create(
 			mdev, tx->ft.sa, attr.chains_ns, attr.prio, attr.pol_level,
@@ -652,6 +672,11 @@ err_roce:
 		mlx5_destroy_flow_table(tx->ft.pol);
 	}
 err_pol_ft:
+	if (tx == ipsec->tx_esw) {
+		mlx5_del_flow_rules(tx->sa.rule);
+		mlx5_destroy_flow_group(tx->sa.group);
+	}
+err_sa_miss:
 	mlx5_destroy_flow_table(tx->ft.sa);
 err_sa_ft:
 	if (tx->allow_tunnel_mode)
@@ -662,6 +687,25 @@ err_status_rule:
 	return err;
 }
 
+static void ipsec_esw_tx_ft_policy_set(struct mlx5_core_dev *mdev,
+				       struct mlx5_flow_table *ft)
+{
+#ifdef CONFIG_MLX5_ESWITCH
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	struct mlx5e_rep_priv *uplink_rpriv;
+	struct mlx5e_priv *priv;
+
+	esw->offloads.ft_ipsec_tx_pol = ft;
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	priv = netdev_priv(uplink_rpriv->netdev);
+	if (!priv->channels.num)
+		return;
+
+	mlx5e_rep_deactivate_channels(priv);
+	mlx5e_rep_activate_channels(priv);
+#endif
+}
+
 static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		  struct mlx5e_ipsec_tx *tx)
 {
@@ -674,6 +718,9 @@ static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
+	if (tx == ipsec->tx_esw)
+		ipsec_esw_tx_ft_policy_set(mdev, tx->ft.pol);
+
 skip:
 	tx->ft.refcnt++;
 	return 0;
@@ -684,7 +731,10 @@ static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
 	if (--tx->ft.refcnt)
 		return;
 
-	tx_destroy(ipsec->mdev, tx, ipsec->roce);
+	if (tx == ipsec->tx_esw)
+		ipsec_esw_tx_ft_policy_set(ipsec->mdev, NULL);
+
+	tx_destroy(ipsec, tx, ipsec->roce);
 }
 
 static struct mlx5_flow_table *tx_ft_get_policy(struct mlx5_core_dev *mdev,
@@ -842,15 +892,15 @@ static void setup_fte_reg_a(struct mlx5_flow_spec *spec)
 		 misc_parameters_2.metadata_reg_a, MLX5_ETH_WQE_FT_META_IPSEC);
 }
 
-static void setup_fte_reg_c0(struct mlx5_flow_spec *spec, u32 reqid)
+static void setup_fte_reg_c4(struct mlx5_flow_spec *spec, u32 reqid)
 {
 	/* Pass policy check before choosing this SA */
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
 
-	MLX5_SET(fte_match_param, spec->match_criteria,
-		 misc_parameters_2.metadata_reg_c_0, reqid);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
 	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.metadata_reg_c_0, reqid);
+		 misc_parameters_2.metadata_reg_c_4, reqid);
 }
 
 static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upspec *upspec)
@@ -902,7 +952,7 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
 		MLX5_SET(set_action_in, action, field,
-			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
+			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
 		break;
 	default:
 		return -EINVAL;
@@ -1268,7 +1318,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		break;
 	case XFRM_DEV_OFFLOAD_PACKET:
 		if (attrs->reqid)
-			setup_fte_reg_c0(spec, attrs->reqid);
+			setup_fte_reg_c4(spec, attrs->reqid);
 		err = setup_pkt_reformat(ipsec, attrs, &flow_act);
 		if (err)
 			goto err_pkt_reformat;
@@ -1379,6 +1429,8 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	}
 
 	flow_act.flags |= FLOW_ACT_NO_APPEND;
+	if (tx == ipsec->tx_esw && tx->chains)
+		flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dest[dstn].ft = tx->ft.sa;
 	dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dstn++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 0675587c1a79f..e60cd3dc1b139 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -12,6 +12,12 @@ enum {
 	MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL,
 };
 
+enum {
+	MLX5_ESW_IPSEC_TX_POL_FT_LEVEL,
+	MLX5_ESW_IPSEC_TX_ESP_FT_LEVEL,
+	MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL,
+};
+
 static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
 					     struct mlx5e_ipsec_rx *rx)
 {
@@ -251,3 +257,13 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 
 	return 0;
 }
+
+void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_tx_create_attr *attr)
+{
+	attr->prio = FDB_CRYPTO_EGRESS;
+	attr->pol_level = MLX5_ESW_IPSEC_TX_POL_FT_LEVEL;
+	attr->sa_level = MLX5_ESW_IPSEC_TX_ESP_FT_LEVEL;
+	attr->cnt_level = MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL;
+	attr->chains_ns = MLX5_FLOW_NAMESPACE_FDB;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index 44df34032d1ee..275684f99ed3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -22,6 +22,8 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
 void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry);
 int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 					  u32 *ipsec_obj_id);
+void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_tx_create_attr *attr);
 #else
 static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 						    struct mlx5e_ipsec_rx *rx) {}
@@ -55,5 +57,8 @@ static inline int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv,
 {
 	return -EINVAL;
 }
+
+static inline void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+						     struct mlx5e_ipsec_tx_create_attr *attr) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 2944c92074870..c7b5faae20a7c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -254,6 +254,7 @@ struct mlx5_esw_offload {
 	struct mlx5_flow_group *vport_rx_group;
 	struct mlx5_flow_group *vport_rx_drop_group;
 	struct mlx5_flow_handle *vport_rx_drop_rule;
+	struct mlx5_flow_table *ft_ipsec_tx_pol;
 	struct xarray vport_reps;
 	struct list_head peer_flows[MLX5_MAX_PORTS];
 	struct mutex peer_mutex;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f83667b4339ec..dc22a7f959e3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -884,6 +884,17 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
+	if (rep->vport == MLX5_VPORT_UPLINK && on_esw->offloads.ft_ipsec_tx_pol) {
+		dest.ft = on_esw->offloads.ft_ipsec_tx_pol;
+		flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL;
+		dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	} else {
+		dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+		dest.vport.num = rep->vport;
+		dest.vport.vhca_id = MLX5_CAP_GEN(rep->esw->dev, vhca_id);
+		dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+	}
+
 	if (MLX5_CAP_ESW_FLOWTABLE(on_esw->dev, flow_source) &&
 	    rep->vport == MLX5_VPORT_UPLINK)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 8ae1854d6b73c..830ff8480fe11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -3015,6 +3015,12 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 		goto out_err;
 	}
 
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_CRYPTO_EGRESS, 3);
+	if (IS_ERR(maj_prio)) {
+		err = PTR_ERR(maj_prio);
+		goto out_err;
+	}
+
 	/* We put this priority last, knowing that nothing will get here
 	 * unless explicitly forwarded to. This is possible because the
 	 * slow path tables have catch all rules and nothing gets passed
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 6b1fa94f69c87..c302ec34255b1 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -115,6 +115,7 @@ enum {
 	FDB_TC_MISS,
 	FDB_BR_OFFLOAD,
 	FDB_SLOW_PATH,
+	FDB_CRYPTO_EGRESS,
 	FDB_PER_VPORT,
 };
 
-- 
GitLab


From 1632649d2dbd6353580273cc37dc269c02ce921f Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:20 +0300
Subject: [PATCH 0802/1806] net/mlx5: Compare with old_dest param to modify
 rule destination

The rule destination must be compared with the old_dest passed in.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/24adc60d05d7492359ba343c6da1ebbe9fe284f6.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 830ff8480fe11..59df6156246e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1066,7 +1066,7 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handle,
 	}
 
 	for (i = 0; i < handle->num_rules; i++) {
-		if (mlx5_flow_dests_cmp(new_dest, &handle->rule[i]->dest_attr))
+		if (mlx5_flow_dests_cmp(old_dest, &handle->rule[i]->dest_attr))
 			return _mlx5_modify_rule_destination(handle->rule[i],
 							     new_dest);
 	}
-- 
GitLab


From 366e46242b8eebfa66cc0dbc85900115cbe6e167 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:21 +0300
Subject: [PATCH 0803/1806] net/mlx5e: Make IPsec offload work together with
 eswitch and TC

The eswitch mode is not allowed to change if there are any IPsec rules.
Besides, by using mlx5_esw_try_lock() to get eswitch mode lock, IPsec
rules are not allowed to be offloaded if there are any TC rules.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/e442b512b21a931fbdfb87d57ae428c37badd58a.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 59 ++++++++++++----
 .../net/ethernet/mellanox/mlx5/core/eswitch.h | 14 ++++
 .../mellanox/mlx5/core/eswitch_offloads.c     | 70 +++++++++++++++++++
 3 files changed, 128 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 36704c9fce33d..7eb926b527daa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -254,8 +254,6 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_del_flow_rules(rx->sa.rule);
 	mlx5_destroy_flow_group(rx->sa.group);
 	mlx5_destroy_flow_table(rx->ft.sa);
-	if (rx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
 	if (rx == ipsec->rx_esw) {
 		mlx5_esw_ipsec_rx_status_destroy(ipsec, rx);
 	} else {
@@ -359,8 +357,6 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		goto err_add;
 
 	/* Create FT */
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
-		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (rx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 	ft = ipsec_ft_create(attr.ns, attr.sa_level, attr.prio, 2, flags);
@@ -415,8 +411,6 @@ err_pol_ft:
 err_fs:
 	mlx5_destroy_flow_table(rx->ft.sa);
 err_fs_ft:
-	if (rx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
 	mlx5_del_flow_rules(rx->status.rule);
 	mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
 err_add:
@@ -434,13 +428,26 @@ static int rx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (rx->ft.refcnt)
 		goto skip;
 
+	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
+		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
+
+	err = mlx5_eswitch_block_mode_trylock(mdev);
+	if (err)
+		goto err_out;
+
 	err = rx_create(mdev, ipsec, rx, family);
+	mlx5_eswitch_block_mode_unlock(mdev, err);
 	if (err)
-		return err;
+		goto err_out;
 
 skip:
 	rx->ft.refcnt++;
 	return 0;
+
+err_out:
+	if (rx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(mdev);
+	return err;
 }
 
 static void rx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx,
@@ -449,7 +456,12 @@ static void rx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx,
 	if (--rx->ft.refcnt)
 		return;
 
+	mlx5_eswitch_unblock_mode_lock(ipsec->mdev);
 	rx_destroy(ipsec->mdev, ipsec, rx, family);
+	mlx5_eswitch_unblock_mode_unlock(ipsec->mdev);
+
+	if (rx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(ipsec->mdev);
 }
 
 static struct mlx5e_ipsec_rx *rx_ft_get(struct mlx5_core_dev *mdev,
@@ -569,8 +581,6 @@ static void tx_destroy(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		mlx5_destroy_flow_group(tx->sa.group);
 	}
 	mlx5_destroy_flow_table(tx->ft.sa);
-	if (tx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(ipsec->mdev);
 	mlx5_del_flow_rules(tx->status.rule);
 	mlx5_destroy_flow_table(tx->ft.status);
 }
@@ -611,8 +621,6 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 	if (err)
 		goto err_status_rule;
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
-		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (tx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 4, flags);
@@ -679,8 +687,6 @@ err_pol_ft:
 err_sa_miss:
 	mlx5_destroy_flow_table(tx->ft.sa);
 err_sa_ft:
-	if (tx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
 	mlx5_del_flow_rules(tx->status.rule);
 err_status_rule:
 	mlx5_destroy_flow_table(tx->ft.status);
@@ -714,16 +720,32 @@ static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (tx->ft.refcnt)
 		goto skip;
 
-	err = tx_create(ipsec, tx, ipsec->roce);
+	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
+		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
+
+	err = mlx5_eswitch_block_mode_trylock(mdev);
 	if (err)
-		return err;
+		goto err_out;
+
+	err = tx_create(ipsec, tx, ipsec->roce);
+	if (err) {
+		mlx5_eswitch_block_mode_unlock(mdev, err);
+		goto err_out;
+	}
 
 	if (tx == ipsec->tx_esw)
 		ipsec_esw_tx_ft_policy_set(mdev, tx->ft.pol);
 
+	mlx5_eswitch_block_mode_unlock(mdev, err);
+
 skip:
 	tx->ft.refcnt++;
 	return 0;
+
+err_out:
+	if (tx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(mdev);
+	return err;
 }
 
 static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
@@ -731,10 +753,17 @@ static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
 	if (--tx->ft.refcnt)
 		return;
 
+	mlx5_eswitch_unblock_mode_lock(ipsec->mdev);
+
 	if (tx == ipsec->tx_esw)
 		ipsec_esw_tx_ft_policy_set(ipsec->mdev, NULL);
 
 	tx_destroy(ipsec, tx, ipsec->roce);
+
+	mlx5_eswitch_unblock_mode_unlock(ipsec->mdev);
+
+	if (tx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(ipsec->mdev);
 }
 
 static struct mlx5_flow_table *tx_ft_get_policy(struct mlx5_core_dev *mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index c7b5faae20a7c..f4b52ab1ff078 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -270,6 +270,7 @@ struct mlx5_esw_offload {
 	u8 inline_mode;
 	atomic64_t num_flows;
 	u64 num_block_encap;
+	u64 num_block_mode;
 	enum devlink_eswitch_encap_mode encap;
 	struct ida vport_metadata_ida;
 	unsigned int host_number; /* ECPF supports one external host */
@@ -784,6 +785,11 @@ int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw);
 bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev);
 void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev);
 
+int mlx5_eswitch_block_mode_trylock(struct mlx5_core_dev *dev);
+void mlx5_eswitch_block_mode_unlock(struct mlx5_core_dev *dev, int err);
+void mlx5_eswitch_unblock_mode_lock(struct mlx5_core_dev *dev);
+void mlx5_eswitch_unblock_mode_unlock(struct mlx5_core_dev *dev);
+
 static inline int mlx5_eswitch_num_vfs(struct mlx5_eswitch *esw)
 {
 	if (mlx5_esw_allowed(esw))
@@ -863,6 +869,14 @@ static inline bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev)
 static inline void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev)
 {
 }
+
+static inline int mlx5_eswitch_block_mode_trylock(struct mlx5_core_dev *dev) { return 0; }
+
+static inline void mlx5_eswitch_block_mode_unlock(struct mlx5_core_dev *dev, int err) {}
+
+static inline void mlx5_eswitch_unblock_mode_lock(struct mlx5_core_dev *dev) {}
+
+static inline void mlx5_eswitch_unblock_mode_unlock(struct mlx5_core_dev *dev) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif /* __MLX5_ESWITCH_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index dc22a7f959e3f..6a7e1955eddf2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3518,6 +3518,69 @@ static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink)
 	return net_eq(devl_net, netdev_net);
 }
 
+int mlx5_eswitch_block_mode_trylock(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	struct mlx5_eswitch *esw;
+	int err;
+
+	devl_lock(devlink);
+	esw = mlx5_devlink_eswitch_get(devlink);
+	if (IS_ERR(esw)) {
+		/* Failure means no eswitch => not possible to change eswitch mode */
+		devl_unlock(devlink);
+		return 0;
+	}
+
+	err = mlx5_esw_try_lock(esw);
+	if (err < 0) {
+		devl_unlock(devlink);
+		return err;
+	}
+
+	return 0;
+}
+
+void mlx5_eswitch_block_mode_unlock(struct mlx5_core_dev *dev, int err)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	struct mlx5_eswitch *esw;
+
+	esw = mlx5_devlink_eswitch_get(devlink);
+	if (IS_ERR(esw))
+		return;
+
+	if (!err)
+		esw->offloads.num_block_mode++;
+	mlx5_esw_unlock(esw);
+	devl_unlock(devlink);
+}
+
+void mlx5_eswitch_unblock_mode_lock(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	struct mlx5_eswitch *esw;
+
+	esw = mlx5_devlink_eswitch_get(devlink);
+	if (IS_ERR(esw))
+		return;
+
+	down_write(&esw->mode_lock);
+}
+
+void mlx5_eswitch_unblock_mode_unlock(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	struct mlx5_eswitch *esw;
+
+	esw = mlx5_devlink_eswitch_get(devlink);
+	if (IS_ERR(esw))
+		return;
+
+	esw->offloads.num_block_mode--;
+	up_write(&esw->mode_lock);
+}
+
 int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 				  struct netlink_ext_ack *extack)
 {
@@ -3551,6 +3614,13 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	if (cur_mlx5_mode == mlx5_mode)
 		goto unlock;
 
+	if (esw->offloads.num_block_mode) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Can't change eswitch mode when IPsec SA and/or policies are configured");
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
 	mlx5_eswitch_disable_locked(esw);
 	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
 		if (mlx5_devlink_trap_get_num_active(esw->dev)) {
-- 
GitLab


From d1569537a837d66620aa7ffc2bddf918e902f227 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:22 +0300
Subject: [PATCH 0804/1806] net/mlx5e: Modify and restore TC rules for IPSec TX
 rules

After IPsec policy/state TX rules are added, any TC flow rule, which
forwards packets to uplink, is modified to forward to IPsec TX tables.
As these tables are destroyed dynamically, whenever there is no
reference to them, the destinations of this kind of rules must be
restored to uplink.

There is a special case for packet encapsulation, as the
packet_reformat_id in the extended destination is used to reformat
packets, but only for the VPORT destination. To forward packet to
IPsec table and do encapsulation in one FTE, move the
packet_reformat_id to flow context, instead of using the extended
destination. As a limitation, multiple encapsulations with table
forwarding, and one together with other VPORT destinations, are not
allowed, so add a check when offloading TC rules.

TC rules are not allowed before IPsec TX rule is added, so only need
to restore TC rules after flush IPSec TX rules. As they are saved in
the vport_rep rhashtables, we walk all the rules in the rhashtables,
and find TC rules with destinations pointing to IPsec tables, and
modify them one by one. To avoid concurrent issue, this handling is
done under the protection of eswitch mode_lock.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/7bcb2c7e2ecf0e0d06b095c8dcc6a37ea7f02faf.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    |  4 +-
 .../mellanox/mlx5/core/esw/ipsec_fs.c         | 56 +++++++++++
 .../mellanox/mlx5/core/esw/ipsec_fs.h         |  3 +
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  2 +
 .../mellanox/mlx5/core/eswitch_offloads.c     | 93 ++++++++++++++++++-
 5 files changed, 154 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 7eb926b527daa..f635b5f6e886f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -755,8 +755,10 @@ static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
 
 	mlx5_eswitch_unblock_mode_lock(ipsec->mdev);
 
-	if (tx == ipsec->tx_esw)
+	if (tx == ipsec->tx_esw) {
+		mlx5_esw_ipsec_restore_dest_uplink(ipsec->mdev);
 		ipsec_esw_tx_ft_policy_set(ipsec->mdev, NULL);
+	}
 
 	tx_destroy(ipsec, tx, ipsec->roce);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index e60cd3dc1b139..455746952260f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -5,6 +5,9 @@
 #include "eswitch.h"
 #include "en_accel/ipsec.h"
 #include "esw/ipsec_fs.h"
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+#include "en/tc_priv.h"
+#endif
 
 enum {
 	MLX5_ESW_IPSEC_RX_POL_FT_LEVEL,
@@ -267,3 +270,56 @@ void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 	attr->cnt_level = MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL;
 	attr->chains_ns = MLX5_FLOW_NAMESPACE_FDB;
 }
+
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+static int mlx5_esw_ipsec_modify_flow_dests(struct mlx5_eswitch *esw,
+					    struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_esw_flow_attr *esw_attr;
+	struct mlx5_flow_attr *attr;
+	int err;
+
+	attr = flow->attr;
+	esw_attr = attr->esw_attr;
+	if (esw_attr->out_count - esw_attr->split_count > 1)
+		return 0;
+
+	err = mlx5_eswitch_restore_ipsec_rule(esw, flow->rule[0], esw_attr,
+					      esw_attr->out_count - 1);
+
+	return err;
+}
+#endif
+
+void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev)
+{
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	struct mlx5_eswitch_rep *rep;
+	struct mlx5e_rep_priv *rpriv;
+	struct rhashtable_iter iter;
+	struct mlx5e_tc_flow *flow;
+	unsigned long i;
+	int err;
+
+	xa_for_each(&esw->offloads.vport_reps, i, rep) {
+		rpriv = rep->rep_data[REP_ETH].priv;
+		if (!rpriv || !rpriv->netdev)
+			continue;
+
+		rhashtable_walk_enter(&rpriv->tc_ht, &iter);
+		rhashtable_walk_start(&iter);
+		while ((flow = rhashtable_walk_next(&iter)) != NULL) {
+			if (IS_ERR(flow))
+				continue;
+
+			err = mlx5_esw_ipsec_modify_flow_dests(esw, flow);
+			if (err)
+				mlx5_core_warn_once(mdev,
+						    "Faided to modify flow dests for IPsec");
+		}
+		rhashtable_walk_stop(&iter);
+		rhashtable_walk_exit(&iter);
+	}
+#endif
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index 275684f99ed3f..0c90f7a8b0d32 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -24,6 +24,7 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 					  u32 *ipsec_obj_id);
 void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_tx_create_attr *attr);
+void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev);
 #else
 static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 						    struct mlx5e_ipsec_rx *rx) {}
@@ -60,5 +61,7 @@ static inline int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv,
 
 static inline void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_tx_create_attr *attr) {}
+
+static inline void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index f4b52ab1ff078..f3a6a1826e00f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -811,6 +811,8 @@ mlx5_eswitch_get_slow_fdb(struct mlx5_eswitch *esw)
 	return esw->fdb_table.offloads.slow_fdb;
 }
 
+int mlx5_eswitch_restore_ipsec_rule(struct mlx5_eswitch *esw, struct mlx5_flow_handle *rule,
+				    struct mlx5_esw_flow_attr *esw_attr, int attr_idx);
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 6a7e1955eddf2..d3bcb632dd443 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -424,10 +424,51 @@ esw_cleanup_chain_dest(struct mlx5_fs_chains *chains, u32 chain, u32 prio, u32 l
 	mlx5_chains_put_table(chains, chain, prio, level);
 }
 
+static bool esw_same_vhca_id(struct mlx5_core_dev *mdev1, struct mlx5_core_dev *mdev2)
+{
+	return MLX5_CAP_GEN(mdev1, vhca_id) == MLX5_CAP_GEN(mdev2, vhca_id);
+}
+
+static bool esw_setup_uplink_fwd_ipsec_needed(struct mlx5_eswitch *esw,
+					      struct mlx5_esw_flow_attr *esw_attr,
+					      int attr_idx)
+{
+	if (esw->offloads.ft_ipsec_tx_pol &&
+	    esw_attr->dests[attr_idx].rep &&
+	    esw_attr->dests[attr_idx].rep->vport == MLX5_VPORT_UPLINK &&
+	    /* To be aligned with software, encryption is needed only for tunnel device */
+	    (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) &&
+	    esw_attr->dests[attr_idx].rep != esw_attr->in_rep &&
+	    esw_same_vhca_id(esw_attr->dests[attr_idx].mdev, esw->dev))
+		return true;
+
+	return false;
+}
+
+static bool esw_flow_dests_fwd_ipsec_check(struct mlx5_eswitch *esw,
+					   struct mlx5_esw_flow_attr *esw_attr)
+{
+	int i;
+
+	if (!esw->offloads.ft_ipsec_tx_pol)
+		return true;
+
+	for (i = 0; i < esw_attr->split_count; i++)
+		if (esw_setup_uplink_fwd_ipsec_needed(esw, esw_attr, i))
+			return false;
+
+	for (i = esw_attr->split_count; i < esw_attr->out_count; i++)
+		if (esw_setup_uplink_fwd_ipsec_needed(esw, esw_attr, i) &&
+		    (esw_attr->out_count - esw_attr->split_count > 1))
+			return false;
+
+	return true;
+}
+
 static void
-esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act,
-		     struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *esw_attr,
-		     int attr_idx, int dest_idx, bool pkt_reformat)
+esw_setup_dest_fwd_vport(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act,
+			 struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *esw_attr,
+			 int attr_idx, int dest_idx, bool pkt_reformat)
 {
 	dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 	dest[dest_idx].vport.num = esw_attr->dests[attr_idx].rep->vport;
@@ -449,6 +490,33 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f
 	}
 }
 
+static void
+esw_setup_dest_fwd_ipsec(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act,
+			 struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *esw_attr,
+			 int attr_idx, int dest_idx, bool pkt_reformat)
+{
+	dest[dest_idx].ft = esw->offloads.ft_ipsec_tx_pol;
+	dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	if (pkt_reformat &&
+	    esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) {
+		flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+		flow_act->pkt_reformat = esw_attr->dests[attr_idx].pkt_reformat;
+	}
+}
+
+static void
+esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act,
+		     struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *esw_attr,
+		     int attr_idx, int dest_idx, bool pkt_reformat)
+{
+	if (esw_setup_uplink_fwd_ipsec_needed(esw, esw_attr, attr_idx))
+		esw_setup_dest_fwd_ipsec(dest, flow_act, esw, esw_attr,
+					 attr_idx, dest_idx, pkt_reformat);
+	else
+		esw_setup_dest_fwd_vport(dest, flow_act, esw, esw_attr,
+					 attr_idx, dest_idx, pkt_reformat);
+}
+
 static int
 esw_setup_vport_dests(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act,
 		      struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *esw_attr,
@@ -575,6 +643,9 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
 		return ERR_PTR(-EOPNOTSUPP);
 
+	if (!esw_flow_dests_fwd_ipsec_check(esw, esw_attr))
+		return ERR_PTR(-EOPNOTSUPP);
+
 	dest = kcalloc(MLX5_MAX_FLOW_FWD_VPORTS + 1, sizeof(*dest), GFP_KERNEL);
 	if (!dest)
 		return ERR_PTR(-ENOMEM);
@@ -4374,3 +4445,19 @@ out:
 	mutex_unlock(&esw->state_lock);
 	return err;
 }
+
+int
+mlx5_eswitch_restore_ipsec_rule(struct mlx5_eswitch *esw, struct mlx5_flow_handle *rule,
+				struct mlx5_esw_flow_attr *esw_attr, int attr_idx)
+{
+	struct mlx5_flow_destination new_dest = {};
+	struct mlx5_flow_destination old_dest = {};
+
+	if (!esw_setup_uplink_fwd_ipsec_needed(esw, esw_attr, attr_idx))
+		return 0;
+
+	esw_setup_dest_fwd_ipsec(&old_dest, NULL, esw, esw_attr, attr_idx, 0, false);
+	esw_setup_dest_fwd_vport(&new_dest, NULL, esw, esw_attr, attr_idx, 0, false);
+
+	return mlx5_modify_rule_destination(rule, &new_dest, &old_dest);
+}
-- 
GitLab


From 6e56ab1c90593630d5e8799831e9dea4850128ea Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:23 +0300
Subject: [PATCH 0805/1806] net/mlx5e: Add get IPsec offload stats for uplink
 representor

As IPsec offload is supported in switchdev mode, HW stats can be can be
obtained from uplink rep.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/b43c91c452f1db9c35c10639a029aa10fd8b7895.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index ca4f57f5064f8..d2fed9615804c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1338,6 +1338,7 @@ static mlx5e_stats_grp_t mlx5e_ul_rep_stats_grps[] = {
 	&MLX5E_STATS_GRP(channels),
 	&MLX5E_STATS_GRP(per_port_buff_congest),
 #ifdef CONFIG_MLX5_EN_IPSEC
+	&MLX5E_STATS_GRP(ipsec_hw),
 	&MLX5E_STATS_GRP(ipsec_sw),
 #endif
 	&MLX5E_STATS_GRP(ptp),
-- 
GitLab


From c8e350e62fc51f3fda28f166fc402f4fb539f528 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:24 +0300
Subject: [PATCH 0806/1806] net/mlx5e: Make TC and IPsec offloads mutually
 exclusive on a netdev

For IPsec packet offload mode, the order of TC offload and IPsec
offload on the same netdevice is not aligned with the order in the
non-offload software. For example, for RX, the software performs TC
first and then IPsec transformation, but the implementation for
offload does that in the opposite way.

To resolve the difference for now, either IPsec offload or TC offload,
not both, is allowed for a specific interface.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/8e2e5e3b0984d785066e8663aaf97b3ba1bb873f.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 84 ++++++++++++++++++-
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 47 +++++++++++
 include/linux/mlx5/driver.h                   |  2 +
 3 files changed, 129 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index f635b5f6e886f..9a5b673442777 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -1717,12 +1717,68 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 	}
 }
 
+#ifdef CONFIG_MLX5_ESWITCH
+static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int err = 0;
+
+	if (esw)
+		down_write(&esw->mode_lock);
+
+	if (mdev->num_block_ipsec) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
+	mdev->num_block_tc++;
+
+unlock:
+	if (esw)
+		up_write(&esw->mode_lock);
+
+	return err;
+}
+#else
+static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
+{
+	if (mdev->num_block_ipsec)
+		return -EBUSY;
+
+	mdev->num_block_tc++;
+	return 0;
+}
+#endif
+
+static void mlx5e_ipsec_unblock_tc_offload(struct mlx5_core_dev *mdev)
+{
+	mdev->num_block_tc++;
+}
+
 int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
+	int err;
+
+	if (sa_entry->attrs.type == XFRM_DEV_OFFLOAD_PACKET) {
+		err = mlx5e_ipsec_block_tc_offload(sa_entry->ipsec->mdev);
+		if (err)
+			return err;
+	}
+
 	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT)
-		return tx_add_rule(sa_entry);
+		err = tx_add_rule(sa_entry);
+	else
+		err = rx_add_rule(sa_entry);
+
+	if (err)
+		goto err_out;
+
+	return 0;
 
-	return rx_add_rule(sa_entry);
+err_out:
+	if (sa_entry->attrs.type == XFRM_DEV_OFFLOAD_PACKET)
+		mlx5e_ipsec_unblock_tc_offload(sa_entry->ipsec->mdev);
+	return err;
 }
 
 void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
@@ -1735,6 +1791,9 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	if (ipsec_rule->pkt_reformat)
 		mlx5_packet_reformat_dealloc(mdev, ipsec_rule->pkt_reformat);
 
+	if (sa_entry->attrs.type == XFRM_DEV_OFFLOAD_PACKET)
+		mlx5e_ipsec_unblock_tc_offload(mdev);
+
 	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT) {
 		tx_ft_put(sa_entry->ipsec, sa_entry->attrs.type);
 		return;
@@ -1747,10 +1806,25 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
 {
+	int err;
+
+	err = mlx5e_ipsec_block_tc_offload(pol_entry->ipsec->mdev);
+	if (err)
+		return err;
+
 	if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT)
-		return tx_add_policy(pol_entry);
+		err = tx_add_policy(pol_entry);
+	else
+		err = rx_add_policy(pol_entry);
+
+	if (err)
+		goto err_out;
+
+	return 0;
 
-	return rx_add_policy(pol_entry);
+err_out:
+	mlx5e_ipsec_unblock_tc_offload(pol_entry->ipsec->mdev);
+	return err;
 }
 
 void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
@@ -1760,6 +1834,8 @@ void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
 
 	mlx5_del_flow_rules(ipsec_rule->rule);
 
+	mlx5e_ipsec_unblock_tc_offload(pol_entry->ipsec->mdev);
+
 	if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) {
 		rx_ft_put_policy(pol_entry->ipsec, pol_entry->attrs.family,
 				 pol_entry->attrs.prio, pol_entry->attrs.type);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dfd282319753f..7d2a029e0932a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4606,6 +4606,46 @@ static bool is_flow_rule_duplicate_allowed(struct net_device *dev,
 	return netif_is_lag_port(dev) && rpriv && rpriv->rep->vport != MLX5_VPORT_UPLINK;
 }
 
+/* As IPsec and TC order is not aligned between software and hardware-offload,
+ * either IPsec offload or TC offload, not both, is allowed for a specific interface.
+ */
+static bool is_tc_ipsec_order_check_needed(struct net_device *filter, struct mlx5e_priv *priv)
+{
+	if (!IS_ENABLED(CONFIG_MLX5_EN_IPSEC))
+		return false;
+
+	if (filter != priv->netdev)
+		return false;
+
+	if (mlx5e_eswitch_vf_rep(priv->netdev))
+		return false;
+
+	return true;
+}
+
+static int mlx5e_tc_block_ipsec_offload(struct net_device *filter, struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	if (!is_tc_ipsec_order_check_needed(filter, priv))
+		return 0;
+
+	if (mdev->num_block_tc)
+		return -EBUSY;
+
+	mdev->num_block_ipsec++;
+
+	return 0;
+}
+
+static void mlx5e_tc_unblock_ipsec_offload(struct net_device *filter, struct mlx5e_priv *priv)
+{
+	if (!is_tc_ipsec_order_check_needed(filter, priv))
+		return;
+
+	priv->mdev->num_block_ipsec--;
+}
+
 int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			   struct flow_cls_offload *f, unsigned long flags)
 {
@@ -4618,6 +4658,10 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	if (!mlx5_esw_hold(priv->mdev))
 		return -EBUSY;
 
+	err = mlx5e_tc_block_ipsec_offload(dev, priv);
+	if (err)
+		goto esw_release;
+
 	mlx5_esw_get(priv->mdev);
 
 	rcu_read_lock();
@@ -4663,7 +4707,9 @@ rcu_unlock:
 err_free:
 	mlx5e_flow_put(priv, flow);
 out:
+	mlx5e_tc_unblock_ipsec_offload(dev, priv);
 	mlx5_esw_put(priv->mdev);
+esw_release:
 	mlx5_esw_release(priv->mdev);
 	return err;
 }
@@ -4704,6 +4750,7 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	trace_mlx5e_delete_flower(f);
 	mlx5e_flow_put(priv, flow);
 
+	mlx5e_tc_unblock_ipsec_offload(dev, priv);
 	mlx5_esw_put(priv->mdev);
 	return 0;
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f21703fb75fde..fa70c25423b21 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -806,6 +806,8 @@ struct mlx5_core_dev {
 	u32                      vsc_addr;
 	struct mlx5_hv_vhca	*hv_vhca;
 	struct mlx5_thermal	*thermal;
+	u64			num_block_tc;
+	u64			num_block_ipsec;
 };
 
 struct mlx5_db {
-- 
GitLab


From 49c467dca39df9a3674854969cc5a8eb7170682d Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 31 Jul 2023 22:10:30 +0800
Subject: [PATCH 0807/1806] sctp: Remove unused function declarations

These declarations are never implemented since beginning of git history.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Xin Long <lucien.xin@gmail.com>
Link: https://lore.kernel.org/r/20230731141030.32772-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sctp/sm.h      | 3 ---
 include/net/sctp/structs.h | 2 --
 2 files changed, 5 deletions(-)

diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index f37c7a558d6dd..64c42bd56bb24 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -156,7 +156,6 @@ sctp_state_fn_t sctp_sf_do_6_2_sack;
 sctp_state_fn_t sctp_sf_autoclose_timer_expire;
 
 /* Prototypes for utility support functions.  */
-__u8 sctp_get_chunk_type(struct sctp_chunk *chunk);
 const struct sctp_sm_table_entry *sctp_sm_lookup_event(
 					struct net *net,
 					enum sctp_event_type event_type,
@@ -166,8 +165,6 @@ int sctp_chunk_iif(const struct sctp_chunk *);
 struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *,
 					     struct sctp_chunk *,
 					     gfp_t gfp);
-__u32 sctp_generate_verification_tag(void);
-void sctp_populate_tie_tags(__u8 *cookie, __u32 curTag, __u32 hisTag);
 
 /* Prototypes for chunk-building functions.  */
 struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 5c72d1864dd6c..5a24d6d8522af 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1122,8 +1122,6 @@ void sctp_outq_free(struct sctp_outq*);
 void sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk, gfp_t);
 int sctp_outq_sack(struct sctp_outq *, struct sctp_chunk *);
 int sctp_outq_is_empty(const struct sctp_outq *);
-void sctp_outq_restart(struct sctp_outq *);
-
 void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport,
 		     enum sctp_retransmit_reason reason);
 void sctp_retransmit_mark(struct sctp_outq *, struct sctp_transport *, __u8);
-- 
GitLab


From 09c2c90705bb64986d499c4a4f3fd659761b637c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Aug 2023 20:52:51 +0000
Subject: [PATCH 0808/1806] net: allow alloc_skb_with_frags() to allocate
 bigger packets

Refactor alloc_skb_with_frags() to allow bigger packets allocations.

Instead of assuming that only order-0 allocations will be attempted,
use the caller supplied max order.

v2: try harder to use high-order pages, per Willem feedback.

Link: https://lore.kernel.org/netdev/CANn89iJQfmc_KeUr3TeXvsLQwo3ZymyoCr7Y6AnHrkWSuz0yAg@mail.gmail.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tahsin Erdogan <trdgn@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20230801205254.400094-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skbuff.c | 56 +++++++++++++++++++++--------------------------
 1 file changed, 25 insertions(+), 31 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a298992060e6e..c6f98245582cd 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6204,7 +6204,7 @@ EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl);
  *
  * @header_len: size of linear part
  * @data_len: needed length in frags
- * @max_page_order: max page order desired.
+ * @order: max page order desired.
  * @errcode: pointer to error code if any
  * @gfp_mask: allocation mask
  *
@@ -6212,21 +6212,17 @@ EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl);
  */
 struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 				     unsigned long data_len,
-				     int max_page_order,
+				     int order,
 				     int *errcode,
 				     gfp_t gfp_mask)
 {
-	int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 	unsigned long chunk;
 	struct sk_buff *skb;
 	struct page *page;
-	int i;
+	int nr_frags = 0;
 
 	*errcode = -EMSGSIZE;
-	/* Note this test could be relaxed, if we succeed to allocate
-	 * high order pages...
-	 */
-	if (npages > MAX_SKB_FRAGS)
+	if (unlikely(data_len > MAX_SKB_FRAGS * (PAGE_SIZE << order)))
 		return NULL;
 
 	*errcode = -ENOBUFS;
@@ -6234,34 +6230,32 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 	if (!skb)
 		return NULL;
 
-	skb->truesize += npages << PAGE_SHIFT;
-
-	for (i = 0; npages > 0; i++) {
-		int order = max_page_order;
-
-		while (order) {
-			if (npages >= 1 << order) {
-				page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
-						   __GFP_COMP |
-						   __GFP_NOWARN,
-						   order);
-				if (page)
-					goto fill_page;
-				/* Do not retry other high order allocations */
-				order = 1;
-				max_page_order = 0;
-			}
+	while (data_len) {
+		if (nr_frags == MAX_SKB_FRAGS - 1)
+			goto failure;
+		while (order && PAGE_ALIGN(data_len) < (PAGE_SIZE << order))
 			order--;
+
+		if (order) {
+			page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
+					   __GFP_COMP |
+					   __GFP_NOWARN,
+					   order);
+			if (!page) {
+				order--;
+				continue;
+			}
+		} else {
+			page = alloc_page(gfp_mask);
+			if (!page)
+				goto failure;
 		}
-		page = alloc_page(gfp_mask);
-		if (!page)
-			goto failure;
-fill_page:
 		chunk = min_t(unsigned long, data_len,
 			      PAGE_SIZE << order);
-		skb_fill_page_desc(skb, i, page, 0, chunk);
+		skb_fill_page_desc(skb, nr_frags, page, 0, chunk);
+		nr_frags++;
+		skb->truesize += (PAGE_SIZE << order);
 		data_len -= chunk;
-		npages -= 1 << order;
 	}
 	return skb;
 
-- 
GitLab


From ce7c7fef147311d0675aa8351ff72e0be1d5b3eb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Aug 2023 20:52:52 +0000
Subject: [PATCH 0809/1806] net: tun: change tun_alloc_skb() to allow bigger
 paged allocations

tun_alloc_skb() is currently calling sock_alloc_send_pskb()
forcing order-0 page allocations.

Switch to PAGE_ALLOC_COSTLY_ORDER, to increase max allocation size by 8x.

Also add logic to increase the linear part if needed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tahsin Erdogan <trdgn@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20230801205254.400094-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tun.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d75456adc62ac..8a48431e8c5b3 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1526,8 +1526,10 @@ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
 	if (prepad + len < PAGE_SIZE || !linear)
 		linear = len;
 
+	if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER);
 	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
-				   &err, 0);
+				   &err, PAGE_ALLOC_COSTLY_ORDER);
 	if (!skb)
 		return ERR_PTR(err);
 
-- 
GitLab


From ae6db08f8b5606ccd95ef2aadd741905d3c13bc0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Aug 2023 20:52:53 +0000
Subject: [PATCH 0810/1806] net/packet: change packet_alloc_skb() to allow
 bigger paged allocations

packet_alloc_skb() is currently calling sock_alloc_send_pskb()
forcing order-0 page allocations.

Switch to PAGE_ALLOC_COSTLY_ORDER, to increase max size by 8x.

Also add logic to increase the linear part if needed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tahsin Erdogan <trdgn@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20230801205254.400094-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/packet/af_packet.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8e3ddec4c3d57..3b77d255d22d6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2927,8 +2927,10 @@ static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad,
 	if (prepad + len < PAGE_SIZE || !linear)
 		linear = len;
 
+	if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER);
 	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
-				   err, 0);
+				   err, PAGE_ALLOC_COSTLY_ORDER);
 	if (!skb)
 		return NULL;
 
-- 
GitLab


From 37dfe5b8ddeb7c0bb97e3643dcfd8f9f1421ad25 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Aug 2023 20:52:54 +0000
Subject: [PATCH 0811/1806] net: tap: change tap_alloc_skb() to allow bigger
 paged allocations

tap_alloc_skb() is currently calling sock_alloc_send_pskb()
forcing order-0 page allocations.

Switch to PAGE_ALLOC_COSTLY_ORDER, to increase max size by 8x.

Also add logic to increase the linear part if needed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tahsin Erdogan <trdgn@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20230801205254.400094-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tap.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 9137fb8c1c420..01574b9d410f0 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -614,8 +614,10 @@ static inline struct sk_buff *tap_alloc_skb(struct sock *sk, size_t prepad,
 	if (prepad + len < PAGE_SIZE || !linear)
 		linear = len;
 
+	if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER);
 	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
-				   err, 0);
+				   err, PAGE_ALLOC_COSTLY_ORDER);
 	if (!skb)
 		return NULL;
 
-- 
GitLab


From 66f7223039c0cef81221e9779520479895995815 Mon Sep 17 00:00:00 2001
From: Maxim Georgiev <glipus@gmail.com>
Date: Tue, 1 Aug 2023 17:28:13 +0300
Subject: [PATCH 0812/1806] net: add NDOs for configuring hardware timestamping

Current hardware timestamping API for NICs requires implementing
.ndo_eth_ioctl() for SIOCGHWTSTAMP and SIOCSHWTSTAMP.

That API has some boilerplate such as request parameter translation
between user and kernel address spaces, handling possible translation
failures correctly, etc. Since it is the same all across the board, it
would be desirable to handle it through generic code.

Here we introduce .ndo_hwtstamp_get() and .ndo_hwtstamp_set(), which
implement that boilerplate and allow drivers to just act upon requests.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Maxim Georgiev <glipus@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-2-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/net_tstamp.h |  8 +++++++
 include/linux/netdevice.h  | 16 +++++++++++++
 net/core/dev_ioctl.c       | 46 ++++++++++++++++++++++++++++++++++++--
 3 files changed, 68 insertions(+), 2 deletions(-)

diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h
index fd67f3cc0c4b5..7c59824f43f51 100644
--- a/include/linux/net_tstamp.h
+++ b/include/linux/net_tstamp.h
@@ -30,4 +30,12 @@ static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kern
 	kernel_cfg->rx_filter = cfg->rx_filter;
 }
 
+static inline void hwtstamp_config_from_kernel(struct hwtstamp_config *cfg,
+					       const struct kernel_hwtstamp_config *kernel_cfg)
+{
+	cfg->flags = kernel_cfg->flags;
+	cfg->tx_type = kernel_cfg->tx_type;
+	cfg->rx_filter = kernel_cfg->rx_filter;
+}
+
 #endif /* _LINUX_NET_TIMESTAMPING_H_ */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 84c36a7f873fd..08a0b8d45dc97 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -57,6 +57,7 @@
 struct netpoll_info;
 struct device;
 struct ethtool_ops;
+struct kernel_hwtstamp_config;
 struct phy_device;
 struct dsa_port;
 struct ip_tunnel_parm;
@@ -1418,6 +1419,16 @@ struct netdev_net_notifier {
  *	Get hardware timestamp based on normal/adjustable time or free running
  *	cycle counter. This function is required if physical clock supports a
  *	free running cycle counter.
+ *
+ * int (*ndo_hwtstamp_get)(struct net_device *dev,
+ *			   struct kernel_hwtstamp_config *kernel_config);
+ *	Get the currently configured hardware timestamping parameters for the
+ *	NIC device.
+ *
+ * int (*ndo_hwtstamp_set)(struct net_device *dev,
+ *			   struct kernel_hwtstamp_config *kernel_config,
+ *			   struct netlink_ext_ack *extack);
+ *	Change the hardware timestamping parameters for NIC device.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1652,6 +1663,11 @@ struct net_device_ops {
 	ktime_t			(*ndo_get_tstamp)(struct net_device *dev,
 						  const struct skb_shared_hwtstamps *hwtstamps,
 						  bool cycles);
+	int			(*ndo_hwtstamp_get)(struct net_device *dev,
+						    struct kernel_hwtstamp_config *kernel_config);
+	int			(*ndo_hwtstamp_set)(struct net_device *dev,
+						    struct kernel_hwtstamp_config *kernel_config,
+						    struct netlink_ext_ack *extack);
 };
 
 struct xdp_metadata_ops {
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 3730945ee2948..10c0e173b38be 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -254,11 +254,32 @@ static int dev_eth_ioctl(struct net_device *dev,
 
 static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 {
-	return dev_eth_ioctl(dev, ifr, SIOCGHWTSTAMP);
+	const struct net_device_ops *ops = dev->netdev_ops;
+	struct kernel_hwtstamp_config kernel_cfg = {};
+	struct hwtstamp_config cfg;
+	int err;
+
+	if (!ops->ndo_hwtstamp_get)
+		return dev_eth_ioctl(dev, ifr, SIOCGHWTSTAMP); /* legacy */
+
+	if (!netif_device_present(dev))
+		return -ENODEV;
+
+	err = ops->ndo_hwtstamp_get(dev, &kernel_cfg);
+	if (err)
+		return err;
+
+	hwtstamp_config_from_kernel(&cfg, &kernel_cfg);
+
+	if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
+		return -EFAULT;
+
+	return 0;
 }
 
 static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 {
+	const struct net_device_ops *ops = dev->netdev_ops;
 	struct kernel_hwtstamp_config kernel_cfg;
 	struct netlink_ext_ack extack = {};
 	struct hwtstamp_config cfg;
@@ -280,7 +301,28 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 		return err;
 	}
 
-	return dev_eth_ioctl(dev, ifr, SIOCSHWTSTAMP);
+	if (!ops->ndo_hwtstamp_set)
+		return dev_eth_ioctl(dev, ifr, SIOCSHWTSTAMP); /* legacy */
+
+	if (!netif_device_present(dev))
+		return -ENODEV;
+
+	err = ops->ndo_hwtstamp_set(dev, &kernel_cfg, &extack);
+	if (err) {
+		if (extack._msg)
+			netdev_err(dev, "%s\n", extack._msg);
+		return err;
+	}
+
+	/* The driver may have modified the configuration, so copy the
+	 * updated version of it back to user space
+	 */
+	hwtstamp_config_from_kernel(&cfg, &kernel_cfg);
+
+	if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
+		return -EFAULT;
+
+	return 0;
 }
 
 static int dev_siocbond(struct net_device *dev,
-- 
GitLab


From e47d01fea663b1fe58d0a493efc9ed667f70242e Mon Sep 17 00:00:00 2001
From: Maxim Georgiev <glipus@gmail.com>
Date: Tue, 1 Aug 2023 17:28:14 +0300
Subject: [PATCH 0813/1806] net: add hwtstamping helpers for stackable net
 devices

The stackable net devices with hwtstamping support (vlan, macvlan,
bonding) only pass the hwtstamping ops to the lower (real) device.

These drivers are the first that need to be converted to the new
timestamping API, because if they aren't prepared to handle that,
then no real device driver cannot be converted to the new API either.

After studying what vlan_dev_ioctl(), macvlan_eth_ioctl() and
bond_eth_ioctl() have in common, here we propose two generic
implementations of ndo_hwtstamp_get() and ndo_hwtstamp_set() which
can be called by those 3 drivers, with "dev" being their lower device.

These helpers cover both cases, when the lower driver is converted to
the new API or unconverted.

We need some hacks in case of an unconverted driver, namely to stuff
some pointers in struct kernel_hwtstamp_config which shouldn't have
been there (since the new API isn't supposed to need it). These will
be removed when all drivers will have been converted to the new API.

Signed-off-by: Maxim Georgiev <glipus@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-3-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/net_tstamp.h |  6 +++
 include/linux/netdevice.h  |  5 +++
 net/core/dev_ioctl.c       | 75 ++++++++++++++++++++++++++++++++++----
 3 files changed, 79 insertions(+), 7 deletions(-)

diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h
index 7c59824f43f51..03e9228148517 100644
--- a/include/linux/net_tstamp.h
+++ b/include/linux/net_tstamp.h
@@ -11,6 +11,10 @@
  * @flags: see struct hwtstamp_config
  * @tx_type: see struct hwtstamp_config
  * @rx_filter: see struct hwtstamp_config
+ * @ifr: pointer to ifreq structure from the original ioctl request, to pass to
+ *	a legacy implementation of a lower driver
+ * @copied_to_user: request was passed to a legacy implementation which already
+ *	copied the ioctl request back to user space
  *
  * Prefer using this structure for in-kernel processing of hardware
  * timestamping configuration, over the inextensible struct hwtstamp_config
@@ -20,6 +24,8 @@ struct kernel_hwtstamp_config {
 	int flags;
 	int tx_type;
 	int rx_filter;
+	struct ifreq *ifr;
+	bool copied_to_user;
 };
 
 static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 08a0b8d45dc97..23e335f245cf7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3950,6 +3950,11 @@ int put_user_ifreq(struct ifreq *ifr, void __user *arg);
 int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
 		void __user *data, bool *need_copyout);
 int dev_ifconf(struct net *net, struct ifconf __user *ifc);
+int generic_hwtstamp_get_lower(struct net_device *dev,
+			       struct kernel_hwtstamp_config *kernel_cfg);
+int generic_hwtstamp_set_lower(struct net_device *dev,
+			       struct kernel_hwtstamp_config *kernel_cfg,
+			       struct netlink_ext_ack *extack);
 int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata);
 unsigned int dev_get_flags(const struct net_device *);
 int __dev_change_flags(struct net_device *dev, unsigned int flags,
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 10c0e173b38be..d0223ecd6f6f4 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -265,14 +265,20 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 	if (!netif_device_present(dev))
 		return -ENODEV;
 
+	kernel_cfg.ifr = ifr;
 	err = ops->ndo_hwtstamp_get(dev, &kernel_cfg);
 	if (err)
 		return err;
 
-	hwtstamp_config_from_kernel(&cfg, &kernel_cfg);
+	/* If the request was resolved through an unconverted driver, omit
+	 * the copy_to_user(), since the implementation has already done that
+	 */
+	if (!kernel_cfg.copied_to_user) {
+		hwtstamp_config_from_kernel(&cfg, &kernel_cfg);
 
-	if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
-		return -EFAULT;
+		if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
+			return -EFAULT;
+	}
 
 	return 0;
 }
@@ -280,7 +286,7 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-	struct kernel_hwtstamp_config kernel_cfg;
+	struct kernel_hwtstamp_config kernel_cfg = {};
 	struct netlink_ext_ack extack = {};
 	struct hwtstamp_config cfg;
 	int err;
@@ -289,6 +295,7 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 		return -EFAULT;
 
 	hwtstamp_config_to_kernel(&kernel_cfg, &cfg);
+	kernel_cfg.ifr = ifr;
 
 	err = net_hwtstamp_validate(&kernel_cfg);
 	if (err)
@@ -317,14 +324,68 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 	/* The driver may have modified the configuration, so copy the
 	 * updated version of it back to user space
 	 */
-	hwtstamp_config_from_kernel(&cfg, &kernel_cfg);
+	if (!kernel_cfg.copied_to_user) {
+		hwtstamp_config_from_kernel(&cfg, &kernel_cfg);
 
-	if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
-		return -EFAULT;
+		if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int generic_hwtstamp_ioctl_lower(struct net_device *dev, int cmd,
+					struct kernel_hwtstamp_config *kernel_cfg)
+{
+	struct ifreq ifrr;
+	int err;
+
+	strscpy_pad(ifrr.ifr_name, dev->name, IFNAMSIZ);
+	ifrr.ifr_ifru = kernel_cfg->ifr->ifr_ifru;
+
+	err = dev_eth_ioctl(dev, &ifrr, cmd);
+	if (err)
+		return err;
+
+	kernel_cfg->ifr->ifr_ifru = ifrr.ifr_ifru;
+	kernel_cfg->copied_to_user = true;
 
 	return 0;
 }
 
+int generic_hwtstamp_get_lower(struct net_device *dev,
+			       struct kernel_hwtstamp_config *kernel_cfg)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!netif_device_present(dev))
+		return -ENODEV;
+
+	if (ops->ndo_hwtstamp_get)
+		return ops->ndo_hwtstamp_get(dev, kernel_cfg);
+
+	/* Legacy path: unconverted lower driver */
+	return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg);
+}
+EXPORT_SYMBOL(generic_hwtstamp_get_lower);
+
+int generic_hwtstamp_set_lower(struct net_device *dev,
+			       struct kernel_hwtstamp_config *kernel_cfg,
+			       struct netlink_ext_ack *extack)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!netif_device_present(dev))
+		return -ENODEV;
+
+	if (ops->ndo_hwtstamp_set)
+		return ops->ndo_hwtstamp_set(dev, kernel_cfg, extack);
+
+	/* Legacy path: unconverted lower driver */
+	return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg);
+}
+EXPORT_SYMBOL(generic_hwtstamp_set_lower);
+
 static int dev_siocbond(struct net_device *dev,
 			struct ifreq *ifr, unsigned int cmd)
 {
-- 
GitLab


From 65c9fde15a651a673637075cc1e9e3aa6aaff203 Mon Sep 17 00:00:00 2001
From: Maxim Georgiev <glipus@gmail.com>
Date: Tue, 1 Aug 2023 17:28:15 +0300
Subject: [PATCH 0814/1806] net: vlan: convert to ndo_hwtstamp_get() /
 ndo_hwtstamp_set()

8021q is one of the stackable net devices which pass the hardware
timestamping ops to the real device through ndo_eth_ioctl(). This
prevents converting any device driver to the new hwtimestamping API
without regressions.

Remove that limitation in the vlan driver by using the newly introduced
helpers for timestamping through lower devices, that handle both the new
and the old driver API.

Signed-off-by: Maxim Georgiev <glipus@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-4-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/8021q/vlan_dev.c | 27 ++++++++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index b90781b9ece64..2a7f1b15714ab 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -354,6 +354,26 @@ out:
 	return 0;
 }
 
+static int vlan_hwtstamp_get(struct net_device *dev,
+			     struct kernel_hwtstamp_config *cfg)
+{
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+
+	return generic_hwtstamp_get_lower(real_dev, cfg);
+}
+
+static int vlan_hwtstamp_set(struct net_device *dev,
+			     struct kernel_hwtstamp_config *cfg,
+			     struct netlink_ext_ack *extack)
+{
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+
+	if (!net_eq(dev_net(dev), dev_net(real_dev)))
+		return -EOPNOTSUPP;
+
+	return generic_hwtstamp_set_lower(real_dev, cfg, extack);
+}
+
 static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
@@ -365,14 +385,9 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	ifrr.ifr_ifru = ifr->ifr_ifru;
 
 	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		if (!net_eq(dev_net(dev), dev_net(real_dev)))
-			break;
-		fallthrough;
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
-	case SIOCGHWTSTAMP:
 		if (netif_device_present(real_dev) && ops->ndo_eth_ioctl)
 			err = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd);
 		break;
@@ -1081,6 +1096,8 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_fix_features	= vlan_dev_fix_features,
 	.ndo_get_iflink		= vlan_dev_get_iflink,
 	.ndo_fill_forward_path	= vlan_dev_fill_forward_path,
+	.ndo_hwtstamp_get	= vlan_hwtstamp_get,
+	.ndo_hwtstamp_set	= vlan_hwtstamp_set,
 };
 
 static void vlan_dev_free(struct net_device *dev)
-- 
GitLab


From 0bca3f7f9acdf755f246b4febb0da59a4cd83638 Mon Sep 17 00:00:00 2001
From: Maxim Georgiev <glipus@gmail.com>
Date: Tue, 1 Aug 2023 17:28:16 +0300
Subject: [PATCH 0815/1806] net: macvlan: convert to ndo_hwtstamp_get() /
 ndo_hwtstamp_set()

macvlan is one of the stackable net devices which pass the hardware
timestamping ops to the real device through ndo_eth_ioctl(). This
prevents converting any device driver to the new hwtimestamping API
without regressions.

Remove that limitation in macvlan by using the newly introduced helpers
for timestamping through lower devices, that handle both the new and the
old driver API.

macvlan only implements ndo_eth_ioctl() for these 2 operations, so
delete that method.

Signed-off-by: Maxim Georgiev <glipus@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-5-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/macvlan.c | 34 ++++++++++++++--------------------
 1 file changed, 14 insertions(+), 20 deletions(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index ed908165a8b4e..02bd201bc7e58 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -868,31 +868,24 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
-static int macvlan_eth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int macvlan_hwtstamp_get(struct net_device *dev,
+				struct kernel_hwtstamp_config *cfg)
 {
 	struct net_device *real_dev = macvlan_dev_real_dev(dev);
-	const struct net_device_ops *ops = real_dev->netdev_ops;
-	struct ifreq ifrr;
-	int err = -EOPNOTSUPP;
 
-	strscpy(ifrr.ifr_name, real_dev->name, IFNAMSIZ);
-	ifrr.ifr_ifru = ifr->ifr_ifru;
+	return generic_hwtstamp_get_lower(real_dev, cfg);
+}
 
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		if (!net_eq(dev_net(dev), &init_net))
-			break;
-		fallthrough;
-	case SIOCGHWTSTAMP:
-		if (netif_device_present(real_dev) && ops->ndo_eth_ioctl)
-			err = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd);
-		break;
-	}
+static int macvlan_hwtstamp_set(struct net_device *dev,
+				struct kernel_hwtstamp_config *cfg,
+				struct netlink_ext_ack *extack)
+{
+	struct net_device *real_dev = macvlan_dev_real_dev(dev);
 
-	if (!err)
-		ifr->ifr_ifru = ifrr.ifr_ifru;
+	if (!net_eq(dev_net(dev), &init_net))
+		return -EOPNOTSUPP;
 
-	return err;
+	return generic_hwtstamp_set_lower(real_dev, cfg, extack);
 }
 
 /*
@@ -1193,7 +1186,6 @@ static const struct net_device_ops macvlan_netdev_ops = {
 	.ndo_stop		= macvlan_stop,
 	.ndo_start_xmit		= macvlan_start_xmit,
 	.ndo_change_mtu		= macvlan_change_mtu,
-	.ndo_eth_ioctl		= macvlan_eth_ioctl,
 	.ndo_fix_features	= macvlan_fix_features,
 	.ndo_change_rx_flags	= macvlan_change_rx_flags,
 	.ndo_set_mac_address	= macvlan_set_mac_address,
@@ -1212,6 +1204,8 @@ static const struct net_device_ops macvlan_netdev_ops = {
 #endif
 	.ndo_get_iflink		= macvlan_dev_get_iflink,
 	.ndo_features_check	= passthru_features_check,
+	.ndo_hwtstamp_get	= macvlan_hwtstamp_get,
+	.ndo_hwtstamp_set	= macvlan_hwtstamp_set,
 };
 
 static void macvlan_dev_free(struct net_device *dev)
-- 
GitLab


From c0dabeb4c666ec952a07e79790606974a3be4303 Mon Sep 17 00:00:00 2001
From: Maxim Georgiev <glipus@gmail.com>
Date: Tue, 1 Aug 2023 17:28:17 +0300
Subject: [PATCH 0816/1806] net: bonding: convert to ndo_hwtstamp_get() /
 ndo_hwtstamp_set()

bonding is one of the stackable net devices which pass the hardware
timestamping ops to the real device through ndo_eth_ioctl(). This
prevents converting any device driver to the new hwtimestamping API
without regressions.

Remove that limitation in bonding by using the newly introduced helpers
for timestamping through lower devices, that handle both the new and the
old driver API.

Signed-off-by: Maxim Georgiev <glipus@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-6-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 105 ++++++++++++++++++++------------
 1 file changed, 65 insertions(+), 40 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 484c9e3e5e825..f04d4f28eb1ab 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4446,11 +4446,6 @@ static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cm
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct mii_ioctl_data *mii = NULL;
-	const struct net_device_ops *ops;
-	struct net_device *real_dev;
-	struct hwtstamp_config cfg;
-	struct ifreq ifrr;
-	int res = 0;
 
 	netdev_dbg(bond_dev, "bond_eth_ioctl: cmd=%d\n", cmd);
 
@@ -4477,44 +4472,11 @@ static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cm
 		}
 
 		break;
-	case SIOCSHWTSTAMP:
-		if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-			return -EFAULT;
-
-		if (!(cfg.flags & HWTSTAMP_FLAG_BONDED_PHC_INDEX))
-			return -EOPNOTSUPP;
-
-		fallthrough;
-	case SIOCGHWTSTAMP:
-		real_dev = bond_option_active_slave_get_rcu(bond);
-		if (!real_dev)
-			return -EOPNOTSUPP;
-
-		strscpy_pad(ifrr.ifr_name, real_dev->name, IFNAMSIZ);
-		ifrr.ifr_ifru = ifr->ifr_ifru;
-
-		ops = real_dev->netdev_ops;
-		if (netif_device_present(real_dev) && ops->ndo_eth_ioctl) {
-			res = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd);
-			if (res)
-				return res;
-
-			ifr->ifr_ifru = ifrr.ifr_ifru;
-			if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-				return -EFAULT;
-
-			/* Set the BOND_PHC_INDEX flag to notify user space */
-			cfg.flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX;
-
-			return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ?
-				-EFAULT : 0;
-		}
-		fallthrough;
 	default:
-		res = -EOPNOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
-	return res;
+	return 0;
 }
 
 static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
@@ -5688,6 +5650,67 @@ static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed)
 	return speed;
 }
 
+/* Set the BOND_PHC_INDEX flag to notify user space */
+static int bond_set_phc_index_flag(struct kernel_hwtstamp_config *kernel_cfg)
+{
+	struct ifreq *ifr = kernel_cfg->ifr;
+	struct hwtstamp_config cfg;
+
+	if (kernel_cfg->copied_to_user) {
+		/* Lower device has a legacy implementation */
+		if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+			return -EFAULT;
+
+		cfg.flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX;
+		if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
+			return -EFAULT;
+	} else {
+		kernel_cfg->flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX;
+	}
+
+	return 0;
+}
+
+static int bond_hwtstamp_get(struct net_device *dev,
+			     struct kernel_hwtstamp_config *cfg)
+{
+	struct bonding *bond = netdev_priv(dev);
+	struct net_device *real_dev;
+	int err;
+
+	real_dev = bond_option_active_slave_get_rcu(bond);
+	if (!real_dev)
+		return -EOPNOTSUPP;
+
+	err = generic_hwtstamp_get_lower(real_dev, cfg);
+	if (err)
+		return err;
+
+	return bond_set_phc_index_flag(cfg);
+}
+
+static int bond_hwtstamp_set(struct net_device *dev,
+			     struct kernel_hwtstamp_config *cfg,
+			     struct netlink_ext_ack *extack)
+{
+	struct bonding *bond = netdev_priv(dev);
+	struct net_device *real_dev;
+	int err;
+
+	if (!(cfg->flags & HWTSTAMP_FLAG_BONDED_PHC_INDEX))
+		return -EOPNOTSUPP;
+
+	real_dev = bond_option_active_slave_get_rcu(bond);
+	if (!real_dev)
+		return -EOPNOTSUPP;
+
+	err = generic_hwtstamp_set_lower(real_dev, cfg, extack);
+	if (err)
+		return err;
+
+	return bond_set_phc_index_flag(cfg);
+}
+
 static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
 					   struct ethtool_link_ksettings *cmd)
 {
@@ -5836,6 +5859,8 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_bpf		= bond_xdp,
 	.ndo_xdp_xmit           = bond_xdp_xmit,
 	.ndo_xdp_get_xmit_slave = bond_xdp_get_xmit_slave,
+	.ndo_hwtstamp_get	= bond_hwtstamp_get,
+	.ndo_hwtstamp_set	= bond_hwtstamp_set,
 };
 
 static const struct device_type bond_type = {
-- 
GitLab


From ef5eb9c5ce45deb4af0898778e2536fda80bc362 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 1 Aug 2023 17:28:18 +0300
Subject: [PATCH 0817/1806] net: fec: convert to ndo_hwtstamp_get() and
 ndo_hwtstamp_set()

The hardware timestamping through ndo_eth_ioctl() is going away.
Convert the FEC driver to the new API before that can be removed.

After removing the timestamping logic from fec_enet_ioctl(), the rest
is equivalent to phy_do_ioctl_running().

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Wei Fang <wei.fang@nxp.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-7-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec.h      |  5 +-
 drivers/net/ethernet/freescale/fec_main.c | 73 ++++++++++++++---------
 drivers/net/ethernet/freescale/fec_ptp.c  | 31 ++++------
 3 files changed, 59 insertions(+), 50 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 8f1edcca96c49..ec64067ca782e 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -699,8 +699,9 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx);
 void fec_ptp_stop(struct platform_device *pdev);
 void fec_ptp_start_cyclecounter(struct net_device *ndev);
 void fec_ptp_disable_hwts(struct net_device *ndev);
-int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr);
-int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr);
+int fec_ptp_set(struct net_device *ndev, struct kernel_hwtstamp_config *config,
+		struct netlink_ext_ack *extack);
+void fec_ptp_get(struct net_device *ndev, struct kernel_hwtstamp_config *config);
 
 /****************************************************************************/
 #endif /* FEC_H */
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 14d0dc7ba3c98..bbd0cc97905a0 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3203,33 +3203,6 @@ static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.self_test		= net_selftest,
 };
 
-static int fec_enet_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
-{
-	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct phy_device *phydev = ndev->phydev;
-
-	if (!netif_running(ndev))
-		return -EINVAL;
-
-	if (!phydev)
-		return -ENODEV;
-
-	if (fep->bufdesc_ex) {
-		bool use_fec_hwts = !phy_has_hwtstamp(phydev);
-
-		if (cmd == SIOCSHWTSTAMP) {
-			if (use_fec_hwts)
-				return fec_ptp_set(ndev, rq);
-			fec_ptp_disable_hwts(ndev);
-		} else if (cmd == SIOCGHWTSTAMP) {
-			if (use_fec_hwts)
-				return fec_ptp_get(ndev, rq);
-		}
-	}
-
-	return phy_mii_ioctl(phydev, rq, cmd);
-}
-
 static void fec_enet_free_buffers(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
@@ -3895,6 +3868,48 @@ static int fec_enet_xdp_xmit(struct net_device *dev,
 	return sent_frames;
 }
 
+static int fec_hwtstamp_get(struct net_device *ndev,
+			    struct kernel_hwtstamp_config *config)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct phy_device *phydev = ndev->phydev;
+
+	if (phy_has_hwtstamp(phydev))
+		return phy_mii_ioctl(phydev, config->ifr, SIOCGHWTSTAMP);
+
+	if (!netif_running(ndev))
+		return -EINVAL;
+
+	if (!fep->bufdesc_ex)
+		return -EOPNOTSUPP;
+
+	fec_ptp_get(ndev, config);
+
+	return 0;
+}
+
+static int fec_hwtstamp_set(struct net_device *ndev,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct phy_device *phydev = ndev->phydev;
+
+	if (phy_has_hwtstamp(phydev)) {
+		fec_ptp_disable_hwts(ndev);
+
+		return phy_mii_ioctl(phydev, config->ifr, SIOCSHWTSTAMP);
+	}
+
+	if (!netif_running(ndev))
+		return -EINVAL;
+
+	if (!fep->bufdesc_ex)
+		return -EOPNOTSUPP;
+
+	return fec_ptp_set(ndev, config, extack);
+}
+
 static const struct net_device_ops fec_netdev_ops = {
 	.ndo_open		= fec_enet_open,
 	.ndo_stop		= fec_enet_close,
@@ -3904,13 +3919,15 @@ static const struct net_device_ops fec_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= fec_timeout,
 	.ndo_set_mac_address	= fec_set_mac_address,
-	.ndo_eth_ioctl		= fec_enet_ioctl,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= fec_poll_controller,
 #endif
 	.ndo_set_features	= fec_set_features,
 	.ndo_bpf		= fec_enet_bpf,
 	.ndo_xdp_xmit		= fec_enet_xdp_xmit,
+	.ndo_hwtstamp_get	= fec_hwtstamp_get,
+	.ndo_hwtstamp_set	= fec_hwtstamp_set,
 };
 
 static const unsigned short offset_des_active_rxq[] = {
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index fc4674cb65be5..befd49b8bd718 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -617,16 +617,12 @@ void fec_ptp_disable_hwts(struct net_device *ndev)
 	fep->hwts_rx_en = 0;
 }
 
-int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr)
+int fec_ptp_set(struct net_device *ndev, struct kernel_hwtstamp_config *config,
+		struct netlink_ext_ack *extack)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
-	struct hwtstamp_config config;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		fep->hwts_tx_en = 0;
 		break;
@@ -637,33 +633,28 @@ int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		fep->hwts_rx_en = 0;
 		break;
 
 	default:
 		fep->hwts_rx_en = 1;
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	}
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-	    -EFAULT : 0;
+	return 0;
 }
 
-int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr)
+void fec_ptp_get(struct net_device *ndev, struct kernel_hwtstamp_config *config)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct hwtstamp_config config;
-
-	config.flags = 0;
-	config.tx_type = fep->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	config.rx_filter = (fep->hwts_rx_en ?
-			    HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE);
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	config->flags = 0;
+	config->tx_type = fep->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	config->rx_filter = (fep->hwts_rx_en ?
+			     HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE);
 }
 
 /*
-- 
GitLab


From 547b006d192261067323efe4b1a12287cf3e4ac2 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 1 Aug 2023 17:28:19 +0300
Subject: [PATCH 0818/1806] net: fec: delete fec_ptp_disable_hwts()

Commit 340746398b67 ("net: fec: fix hardware time stamping by external
devices") was overly cautious with calling fec_ptp_disable_hwts() when
cmd == SIOCSHWTSTAMP and use_fec_hwts == false, because use_fec_hwts is
based on a runtime invariant (phy_has_hwtstamp()). Thus, if use_fec_hwts
is false, then fep->hwts_tx_en and fep->hwts_rx_en cannot be changed at
runtime; their values depend on the initial memory allocation, which
already sets them to zeroes.

If the core will ever gain support for switching timestamping layers,
it will arrange for a more organized calling convention and disable
timestamping in the previous layer as a first step. This means that the
code in the FEC driver is not necessary in any case.

The purpose of this change is to arrange the phy_has_hwtstamp() code in
a way in which it can be refactored away into generic logic.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Wei Fang <wei.fang@nxp.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-8-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec.h      |  1 -
 drivers/net/ethernet/freescale/fec_main.c |  5 +----
 drivers/net/ethernet/freescale/fec_ptp.c  | 12 ------------
 3 files changed, 1 insertion(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index ec64067ca782e..110f2e9f3e3fa 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -698,7 +698,6 @@ struct fec_enet_private {
 void fec_ptp_init(struct platform_device *pdev, int irq_idx);
 void fec_ptp_stop(struct platform_device *pdev);
 void fec_ptp_start_cyclecounter(struct net_device *ndev);
-void fec_ptp_disable_hwts(struct net_device *ndev);
 int fec_ptp_set(struct net_device *ndev, struct kernel_hwtstamp_config *config,
 		struct netlink_ext_ack *extack);
 void fec_ptp_get(struct net_device *ndev, struct kernel_hwtstamp_config *config);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index bbd0cc97905a0..6d81fff0227e5 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3895,11 +3895,8 @@ static int fec_hwtstamp_set(struct net_device *ndev,
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	struct phy_device *phydev = ndev->phydev;
 
-	if (phy_has_hwtstamp(phydev)) {
-		fec_ptp_disable_hwts(ndev);
-
+	if (phy_has_hwtstamp(phydev))
 		return phy_mii_ioctl(phydev, config->ifr, SIOCSHWTSTAMP);
-	}
 
 	if (!netif_running(ndev))
 		return -EINVAL;
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index befd49b8bd718..181d9bfbee220 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -605,18 +605,6 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp,
 	}
 }
 
-/**
- * fec_ptp_disable_hwts - disable hardware time stamping
- * @ndev: pointer to net_device
- */
-void fec_ptp_disable_hwts(struct net_device *ndev)
-{
-	struct fec_enet_private *fep = netdev_priv(ndev);
-
-	fep->hwts_tx_en = 0;
-	fep->hwts_rx_en = 0;
-}
-
 int fec_ptp_set(struct net_device *ndev, struct kernel_hwtstamp_config *config,
 		struct netlink_ext_ack *extack)
 {
-- 
GitLab


From 7bdde44463b2980dac9577604a27ae69c2bbd0a1 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 1 Aug 2023 17:28:20 +0300
Subject: [PATCH 0819/1806] net: sparx5: convert to ndo_hwtstamp_get() and
 ndo_hwtstamp_set()

The hardware timestamping through ndo_eth_ioctl() is going away.
Convert the sparx5 driver to the new API before that can be removed.

After removing the timestamping logic from sparx5_port_ioctl(), the rest
is equivalent to phy_do_ioctl().

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-9-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/microchip/sparx5/sparx5_main.h   |  9 ++--
 .../ethernet/microchip/sparx5/sparx5_netdev.c | 41 +++++++++++++------
 .../ethernet/microchip/sparx5/sparx5_ptp.c    | 24 +++++------
 3 files changed, 46 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index 62c85463b634e..89a9a7afa32c7 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -205,7 +205,7 @@ enum sparx5_core_clockfreq {
 struct sparx5_phc {
 	struct ptp_clock *clock;
 	struct ptp_clock_info info;
-	struct hwtstamp_config hwtstamp_config;
+	struct kernel_hwtstamp_config hwtstamp_config;
 	struct sparx5 *sparx5;
 	u8 index;
 };
@@ -388,8 +388,11 @@ void sparx5_unregister_netdevs(struct sparx5 *sparx5);
 /* sparx5_ptp.c */
 int sparx5_ptp_init(struct sparx5 *sparx5);
 void sparx5_ptp_deinit(struct sparx5 *sparx5);
-int sparx5_ptp_hwtstamp_set(struct sparx5_port *port, struct ifreq *ifr);
-int sparx5_ptp_hwtstamp_get(struct sparx5_port *port, struct ifreq *ifr);
+int sparx5_ptp_hwtstamp_set(struct sparx5_port *port,
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack);
+void sparx5_ptp_hwtstamp_get(struct sparx5_port *port,
+			     struct kernel_hwtstamp_config *cfg);
 void sparx5_ptp_rxtstamp(struct sparx5 *sparx5, struct sk_buff *skb,
 			 u64 timestamp);
 int sparx5_ptp_txtstamp_request(struct sparx5_port *port,
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c
index d078156581d54..e01d3b1e17e00 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c
@@ -210,22 +210,37 @@ static int sparx5_get_port_parent_id(struct net_device *dev,
 	return 0;
 }
 
-static int sparx5_port_ioctl(struct net_device *dev, struct ifreq *ifr,
-			     int cmd)
+static int sparx5_port_hwtstamp_get(struct net_device *dev,
+				    struct kernel_hwtstamp_config *cfg)
 {
 	struct sparx5_port *sparx5_port = netdev_priv(dev);
 	struct sparx5 *sparx5 = sparx5_port->sparx5;
 
-	if (!phy_has_hwtstamp(dev->phydev) && sparx5->ptp) {
-		switch (cmd) {
-		case SIOCSHWTSTAMP:
-			return sparx5_ptp_hwtstamp_set(sparx5_port, ifr);
-		case SIOCGHWTSTAMP:
-			return sparx5_ptp_hwtstamp_get(sparx5_port, ifr);
-		}
-	}
+	if (phy_has_hwtstamp(dev->phydev))
+		return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCGHWTSTAMP);
+
+	if (!sparx5->ptp)
+		return -EOPNOTSUPP;
+
+	sparx5_ptp_hwtstamp_get(sparx5_port, cfg);
+
+	return 0;
+}
+
+static int sparx5_port_hwtstamp_set(struct net_device *dev,
+				    struct kernel_hwtstamp_config *cfg,
+				    struct netlink_ext_ack *extack)
+{
+	struct sparx5_port *sparx5_port = netdev_priv(dev);
+	struct sparx5 *sparx5 = sparx5_port->sparx5;
+
+	if (phy_has_hwtstamp(dev->phydev))
+		return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCSHWTSTAMP);
+
+	if (!sparx5->ptp)
+		return -EOPNOTSUPP;
 
-	return phy_mii_ioctl(dev->phydev, ifr, cmd);
+	return sparx5_ptp_hwtstamp_set(sparx5_port, cfg, extack);
 }
 
 static const struct net_device_ops sparx5_port_netdev_ops = {
@@ -238,8 +253,10 @@ static const struct net_device_ops sparx5_port_netdev_ops = {
 	.ndo_validate_addr      = eth_validate_addr,
 	.ndo_get_stats64        = sparx5_get_stats64,
 	.ndo_get_port_parent_id = sparx5_get_port_parent_id,
-	.ndo_eth_ioctl          = sparx5_port_ioctl,
+	.ndo_eth_ioctl          = phy_do_ioctl,
 	.ndo_setup_tc           = sparx5_port_setup_tc,
+	.ndo_hwtstamp_get       = sparx5_port_hwtstamp_get,
+	.ndo_hwtstamp_set       = sparx5_port_hwtstamp_set,
 };
 
 bool sparx5_netdevice_check(const struct net_device *dev)
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c
index 0edb98cef7e4d..5a932460db581 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c
@@ -74,10 +74,11 @@ static u64 sparx5_ptp_get_nominal_value(struct sparx5 *sparx5)
 	return res;
 }
 
-int sparx5_ptp_hwtstamp_set(struct sparx5_port *port, struct ifreq *ifr)
+int sparx5_ptp_hwtstamp_set(struct sparx5_port *port,
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	struct sparx5 *sparx5 = port->sparx5;
-	struct hwtstamp_config cfg;
 	struct sparx5_phc *phc;
 
 	/* For now don't allow to run ptp on ports that are part of a bridge,
@@ -88,10 +89,7 @@ int sparx5_ptp_hwtstamp_set(struct sparx5_port *port, struct ifreq *ifr)
 	if (test_bit(port->portno, sparx5->bridge_mask))
 		return -EINVAL;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	switch (cfg.tx_type) {
+	switch (cfg->tx_type) {
 	case HWTSTAMP_TX_ON:
 		port->ptp_cmd = IFH_REW_OP_TWO_STEP_PTP;
 		break;
@@ -105,7 +103,7 @@ int sparx5_ptp_hwtstamp_set(struct sparx5_port *port, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
 	case HWTSTAMP_FILTER_ALL:
@@ -122,7 +120,7 @@ int sparx5_ptp_hwtstamp_set(struct sparx5_port *port, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
-		cfg.rx_filter = HWTSTAMP_FILTER_ALL;
+		cfg->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
 		return -ERANGE;
@@ -131,20 +129,20 @@ int sparx5_ptp_hwtstamp_set(struct sparx5_port *port, struct ifreq *ifr)
 	/* Commit back the result & save it */
 	mutex_lock(&sparx5->ptp_lock);
 	phc = &sparx5->phc[SPARX5_PHC_PORT];
-	memcpy(&phc->hwtstamp_config, &cfg, sizeof(cfg));
+	phc->hwtstamp_config = *cfg;
 	mutex_unlock(&sparx5->ptp_lock);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
-int sparx5_ptp_hwtstamp_get(struct sparx5_port *port, struct ifreq *ifr)
+void sparx5_ptp_hwtstamp_get(struct sparx5_port *port,
+			     struct kernel_hwtstamp_config *cfg)
 {
 	struct sparx5 *sparx5 = port->sparx5;
 	struct sparx5_phc *phc;
 
 	phc = &sparx5->phc[SPARX5_PHC_PORT];
-	return copy_to_user(ifr->ifr_data, &phc->hwtstamp_config,
-			    sizeof(phc->hwtstamp_config)) ? -EFAULT : 0;
+	*cfg = phc->hwtstamp_config;
 }
 
 static void sparx5_ptp_classify(struct sparx5_port *port, struct sk_buff *skb,
-- 
GitLab


From 54e1ed69c40a3ea9a82cb59ad88e00af98a6628e Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 1 Aug 2023 17:28:21 +0300
Subject: [PATCH 0820/1806] net: lan966x: convert to ndo_hwtstamp_get() and
 ndo_hwtstamp_set()

The hardware timestamping through ndo_eth_ioctl() is going away.
Convert the lan966x driver to the new API before that can be removed.

After removing the timestamping logic from lan966x_port_ioctl(), the
rest is equivalent to phy_do_ioctl().

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-10-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/microchip/lan966x/lan966x_main.c | 59 +++++++++++--------
 .../ethernet/microchip/lan966x/lan966x_main.h | 12 ++--
 .../ethernet/microchip/lan966x/lan966x_ptp.c  | 34 +++++------
 3 files changed, 55 insertions(+), 50 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 73f20683210ed..1baa94a98fe33 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -450,39 +450,44 @@ static int lan966x_port_get_parent_id(struct net_device *dev,
 	return 0;
 }
 
-static int lan966x_port_ioctl(struct net_device *dev, struct ifreq *ifr,
-			      int cmd)
+static int lan966x_port_hwtstamp_get(struct net_device *dev,
+				     struct kernel_hwtstamp_config *cfg)
 {
 	struct lan966x_port *port = netdev_priv(dev);
-	int err;
 
-	if (cmd == SIOCSHWTSTAMP) {
-		err = lan966x_ptp_setup_traps(port, ifr);
-		if (err)
-			return err;
-	}
+	if (phy_has_hwtstamp(dev->phydev))
+		return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCGHWTSTAMP);
 
-	if (!phy_has_hwtstamp(dev->phydev) && port->lan966x->ptp) {
-		switch (cmd) {
-		case SIOCSHWTSTAMP:
-			err = lan966x_ptp_hwtstamp_set(port, ifr);
-			if (err)
-				lan966x_ptp_del_traps(port);
+	if (!port->lan966x->ptp)
+		return -EOPNOTSUPP;
 
-			return err;
-		case SIOCGHWTSTAMP:
-			return lan966x_ptp_hwtstamp_get(port, ifr);
-		}
-	}
+	lan966x_ptp_hwtstamp_get(port, cfg);
 
-	if (!dev->phydev)
-		return -ENODEV;
+	return 0;
+}
 
-	err = phy_mii_ioctl(dev->phydev, ifr, cmd);
-	if (err && cmd == SIOCSHWTSTAMP)
-		lan966x_ptp_del_traps(port);
+static int lan966x_port_hwtstamp_set(struct net_device *dev,
+				     struct kernel_hwtstamp_config *cfg,
+				     struct netlink_ext_ack *extack)
+{
+	struct lan966x_port *port = netdev_priv(dev);
+	int err;
 
-	return err;
+	err = lan966x_ptp_setup_traps(port, cfg);
+	if (err)
+		return err;
+
+	if (phy_has_hwtstamp(dev->phydev)) {
+		err = phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCSHWTSTAMP);
+		if (err)
+			lan966x_ptp_del_traps(port);
+		return err;
+	}
+
+	if (!port->lan966x->ptp)
+		return -EOPNOTSUPP;
+
+	return lan966x_ptp_hwtstamp_set(port, cfg, extack);
 }
 
 static const struct net_device_ops lan966x_port_netdev_ops = {
@@ -495,10 +500,12 @@ static const struct net_device_ops lan966x_port_netdev_ops = {
 	.ndo_get_stats64		= lan966x_stats_get,
 	.ndo_set_mac_address		= lan966x_port_set_mac_address,
 	.ndo_get_port_parent_id		= lan966x_port_get_parent_id,
-	.ndo_eth_ioctl			= lan966x_port_ioctl,
+	.ndo_eth_ioctl			= phy_do_ioctl,
 	.ndo_setup_tc			= lan966x_tc_setup,
 	.ndo_bpf			= lan966x_xdp,
 	.ndo_xdp_xmit			= lan966x_xdp_xmit,
+	.ndo_hwtstamp_get		= lan966x_port_hwtstamp_get,
+	.ndo_hwtstamp_set		= lan966x_port_hwtstamp_set,
 };
 
 bool lan966x_netdevice_check(const struct net_device *dev)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 27f272831ea5c..b538d496e8d79 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -298,7 +298,7 @@ struct lan966x_phc {
 	struct ptp_clock *clock;
 	struct ptp_clock_info info;
 	struct ptp_pin_desc pins[LAN966X_PHC_PINS_NUM];
-	struct hwtstamp_config hwtstamp_config;
+	struct kernel_hwtstamp_config hwtstamp_config;
 	struct lan966x *lan966x;
 	u8 index;
 };
@@ -578,8 +578,11 @@ void lan966x_mdb_restore_entries(struct lan966x *lan966x);
 
 int lan966x_ptp_init(struct lan966x *lan966x);
 void lan966x_ptp_deinit(struct lan966x *lan966x);
-int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr);
-int lan966x_ptp_hwtstamp_get(struct lan966x_port *port, struct ifreq *ifr);
+int lan966x_ptp_hwtstamp_set(struct lan966x_port *port,
+			     struct kernel_hwtstamp_config *cfg,
+			     struct netlink_ext_ack *extack);
+void lan966x_ptp_hwtstamp_get(struct lan966x_port *port,
+			      struct kernel_hwtstamp_config *cfg);
 void lan966x_ptp_rxtstamp(struct lan966x *lan966x, struct sk_buff *skb,
 			  u64 src_port, u64 timestamp);
 int lan966x_ptp_txtstamp_request(struct lan966x_port *port,
@@ -590,7 +593,8 @@ irqreturn_t lan966x_ptp_irq_handler(int irq, void *args);
 irqreturn_t lan966x_ptp_ext_irq_handler(int irq, void *args);
 u32 lan966x_ptp_get_period_ps(void);
 int lan966x_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts);
-int lan966x_ptp_setup_traps(struct lan966x_port *port, struct ifreq *ifr);
+int lan966x_ptp_setup_traps(struct lan966x_port *port,
+			    struct kernel_hwtstamp_config *cfg);
 int lan966x_ptp_del_traps(struct lan966x_port *port);
 
 int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev);
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
index 266a21a2d1246..60bd0cff66770 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
@@ -248,29 +248,23 @@ int lan966x_ptp_del_traps(struct lan966x_port *port)
 	return err;
 }
 
-int lan966x_ptp_setup_traps(struct lan966x_port *port, struct ifreq *ifr)
+int lan966x_ptp_setup_traps(struct lan966x_port *port,
+			    struct kernel_hwtstamp_config *cfg)
 {
-	struct hwtstamp_config cfg;
-
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	if (cfg.rx_filter == HWTSTAMP_FILTER_NONE)
+	if (cfg->rx_filter == HWTSTAMP_FILTER_NONE)
 		return lan966x_ptp_del_traps(port);
 	else
 		return lan966x_ptp_add_traps(port);
 }
 
-int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr)
+int lan966x_ptp_hwtstamp_set(struct lan966x_port *port,
+			     struct kernel_hwtstamp_config *cfg,
+			     struct netlink_ext_ack *extack)
 {
 	struct lan966x *lan966x = port->lan966x;
-	struct hwtstamp_config cfg;
 	struct lan966x_phc *phc;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	switch (cfg.tx_type) {
+	switch (cfg->tx_type) {
 	case HWTSTAMP_TX_ON:
 		port->ptp_tx_cmd = IFH_REW_OP_TWO_STEP_PTP;
 		break;
@@ -284,7 +278,7 @@ int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		port->ptp_rx_cmd = false;
 		break;
@@ -303,7 +297,7 @@ int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
 		port->ptp_rx_cmd = true;
-		cfg.rx_filter = HWTSTAMP_FILTER_ALL;
+		cfg->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
 		return -ERANGE;
@@ -312,20 +306,20 @@ int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr)
 	/* Commit back the result & save it */
 	mutex_lock(&lan966x->ptp_lock);
 	phc = &lan966x->phc[LAN966X_PHC_PORT];
-	memcpy(&phc->hwtstamp_config, &cfg, sizeof(cfg));
+	phc->hwtstamp_config = *cfg;
 	mutex_unlock(&lan966x->ptp_lock);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
-int lan966x_ptp_hwtstamp_get(struct lan966x_port *port, struct ifreq *ifr)
+void lan966x_ptp_hwtstamp_get(struct lan966x_port *port,
+			      struct kernel_hwtstamp_config *cfg)
 {
 	struct lan966x *lan966x = port->lan966x;
 	struct lan966x_phc *phc;
 
 	phc = &lan966x->phc[LAN966X_PHC_PORT];
-	return copy_to_user(ifr->ifr_data, &phc->hwtstamp_config,
-			    sizeof(phc->hwtstamp_config)) ? -EFAULT : 0;
+	*cfg = phc->hwtstamp_config;
 }
 
 static int lan966x_ptp_classify(struct lan966x_port *port, struct sk_buff *skb)
-- 
GitLab


From 70ef7d87f62a86674c21a99341dabc175c19681a Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 1 Aug 2023 17:28:22 +0300
Subject: [PATCH 0821/1806] net: transfer rtnl_lock() requirement from
 ethtool_set_ethtool_phy_ops() to caller

phy_init() and phy_exit() will have to do more stuff under rtnl_lock()
in a future change. Since rtnl_unlock() -> netdev_run_todo() does a lot
of stuff under the hood, it's a pity to lock and unlock the rtnetlink
mutex twice in a row.

Change the calling convention such that the only caller of
ethtool_set_ethtool_phy_ops(), phy_device.c, provides a context where
the rtnl_mutex is already acquired.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-11-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 7 +++++++
 net/ethtool/common.c         | 3 +--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 61921d4dbb13a..98b8ac28e5a10 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -30,6 +30,7 @@
 #include <linux/phy_led_triggers.h>
 #include <linux/pse-pd/pse.h>
 #include <linux/property.h>
+#include <linux/rtnetlink.h>
 #include <linux/sfp.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
@@ -3451,7 +3452,9 @@ static int __init phy_init(void)
 {
 	int rc;
 
+	rtnl_lock();
 	ethtool_set_ethtool_phy_ops(&phy_ethtool_phy_ops);
+	rtnl_unlock();
 
 	rc = mdio_bus_init();
 	if (rc)
@@ -3474,7 +3477,9 @@ err_c45:
 err_mdio_bus:
 	mdio_bus_exit();
 err_ethtool_phy_ops:
+	rtnl_lock();
 	ethtool_set_ethtool_phy_ops(NULL);
+	rtnl_unlock();
 
 	return rc;
 }
@@ -3484,7 +3489,9 @@ static void __exit phy_exit(void)
 	phy_driver_unregister(&genphy_c45_driver);
 	phy_driver_unregister(&genphy_driver);
 	mdio_bus_exit();
+	rtnl_lock();
 	ethtool_set_ethtool_phy_ops(NULL);
+	rtnl_unlock();
 }
 
 subsys_initcall(phy_init);
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 5fb19050991e0..f5598c5f50de9 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -665,9 +665,8 @@ const struct ethtool_phy_ops *ethtool_phy_ops;
 
 void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops)
 {
-	rtnl_lock();
+	ASSERT_RTNL();
 	ethtool_phy_ops = ops;
-	rtnl_unlock();
 }
 EXPORT_SYMBOL_GPL(ethtool_set_ethtool_phy_ops);
 
-- 
GitLab


From 60495b6622ca67f5180343b89bd932d28d23f63a Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 1 Aug 2023 17:28:23 +0300
Subject: [PATCH 0822/1806] net: phy: provide phylib stubs for hardware
 timestamping operations

net/core/dev_ioctl.c (built-in code) will want to call phy_mii_ioctl()
for hardware timestamping purposes. This is not directly possible,
because phy_mii_ioctl() is a symbol provided under CONFIG_PHYLIB.

Do something similar to what was done in DSA in commit 5a17818682cf
("net: dsa: replace NETDEV_PRE_CHANGE_HWTSTAMP notifier with a stub"),
and arrange some indirect calls to phy_mii_ioctl() through a stub
structure containing function pointers, that's provided by phylib as
built-in even when CONFIG_PHYLIB=m, and which phy_init() populates at
runtime (module insertion).

Note: maybe the ownership of the ethtool_phy_ops singleton is backwards,
and the methods exposed by that should be later merged into phylib_stubs.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-12-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                  |  1 +
 drivers/net/phy/Makefile     |  2 ++
 drivers/net/phy/phy.c        | 34 ++++++++++++++++++
 drivers/net/phy/phy_device.c | 19 ++++++++++
 drivers/net/phy/stubs.c      | 10 ++++++
 include/linux/phy.h          |  7 ++++
 include/linux/phylib_stubs.h | 68 ++++++++++++++++++++++++++++++++++++
 7 files changed, 141 insertions(+)
 create mode 100644 drivers/net/phy/stubs.c
 create mode 100644 include/linux/phylib_stubs.h

diff --git a/MAINTAINERS b/MAINTAINERS
index c4f95a9d03b9e..069e176d607a4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7752,6 +7752,7 @@ F:	include/linux/mii.h
 F:	include/linux/of_net.h
 F:	include/linux/phy.h
 F:	include/linux/phy_fixed.h
+F:	include/linux/phylib_stubs.h
 F:	include/linux/platform_data/mdio-bcm-unimac.h
 F:	include/linux/platform_data/mdio-gpio.h
 F:	include/trace/events/mdio.h
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 35142780fc9da..c945ed9bd14b3 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -14,6 +14,8 @@ endif
 # dedicated loadable module, so we bundle them all together into libphy.ko
 ifdef CONFIG_PHYLIB
 libphy-y			+= $(mdio-bus-y)
+# the stubs are built-in whenever PHYLIB is built-in or module
+obj-y				+= stubs.o
 else
 obj-$(CONFIG_MDIO_DEVICE)	+= mdio-bus.o
 endif
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index bdf00b2b2c1dc..8aec8e83038c5 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -455,6 +455,40 @@ int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL(phy_do_ioctl_running);
 
+/**
+ * __phy_hwtstamp_get - Get hardware timestamping configuration from PHY
+ *
+ * @phydev: the PHY device structure
+ * @config: structure holding the timestamping configuration
+ *
+ * Query the PHY device for its current hardware timestamping configuration.
+ */
+int __phy_hwtstamp_get(struct phy_device *phydev,
+		       struct kernel_hwtstamp_config *config)
+{
+	if (!phydev)
+		return -ENODEV;
+
+	return phy_mii_ioctl(phydev, config->ifr, SIOCGHWTSTAMP);
+}
+
+/**
+ * __phy_hwtstamp_set - Modify PHY hardware timestamping configuration
+ *
+ * @phydev: the PHY device structure
+ * @config: structure holding the timestamping configuration
+ * @extack: netlink extended ack structure, for error reporting
+ */
+int __phy_hwtstamp_set(struct phy_device *phydev,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack)
+{
+	if (!phydev)
+		return -ENODEV;
+
+	return phy_mii_ioctl(phydev, config->ifr, SIOCSHWTSTAMP);
+}
+
 /**
  * phy_queue_state_machine - Trigger the state machine to run soon
  *
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 98b8ac28e5a10..e19c4fee8d229 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -27,6 +27,7 @@
 #include <linux/of.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
+#include <linux/phylib_stubs.h>
 #include <linux/phy_led_triggers.h>
 #include <linux/pse-pd/pse.h>
 #include <linux/property.h>
@@ -3448,12 +3449,28 @@ static const struct ethtool_phy_ops phy_ethtool_phy_ops = {
 	.start_cable_test_tdr	= phy_start_cable_test_tdr,
 };
 
+static const struct phylib_stubs __phylib_stubs = {
+	.hwtstamp_get = __phy_hwtstamp_get,
+	.hwtstamp_set = __phy_hwtstamp_set,
+};
+
+static void phylib_register_stubs(void)
+{
+	phylib_stubs = &__phylib_stubs;
+}
+
+static void phylib_unregister_stubs(void)
+{
+	phylib_stubs = NULL;
+}
+
 static int __init phy_init(void)
 {
 	int rc;
 
 	rtnl_lock();
 	ethtool_set_ethtool_phy_ops(&phy_ethtool_phy_ops);
+	phylib_register_stubs();
 	rtnl_unlock();
 
 	rc = mdio_bus_init();
@@ -3478,6 +3495,7 @@ err_mdio_bus:
 	mdio_bus_exit();
 err_ethtool_phy_ops:
 	rtnl_lock();
+	phylib_unregister_stubs();
 	ethtool_set_ethtool_phy_ops(NULL);
 	rtnl_unlock();
 
@@ -3490,6 +3508,7 @@ static void __exit phy_exit(void)
 	phy_driver_unregister(&genphy_driver);
 	mdio_bus_exit();
 	rtnl_lock();
+	phylib_unregister_stubs();
 	ethtool_set_ethtool_phy_ops(NULL);
 	rtnl_unlock();
 }
diff --git a/drivers/net/phy/stubs.c b/drivers/net/phy/stubs.c
new file mode 100644
index 0000000000000..cfb9f275eb182
--- /dev/null
+++ b/drivers/net/phy/stubs.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Stubs for PHY library functionality called by the core network stack.
+ * These are necessary because CONFIG_PHYLIB can be a module, and built-in
+ * code cannot directly call symbols exported by modules.
+ */
+#include <linux/phylib_stubs.h>
+
+const struct phylib_stubs *phylib_stubs;
+EXPORT_SYMBOL_GPL(phylib_stubs);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index b254848a9c99a..ba08b0e602798 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -298,6 +298,7 @@ static inline const char *phy_modes(phy_interface_t interface)
 #define MII_BUS_ID_SIZE	61
 
 struct device;
+struct kernel_hwtstamp_config;
 struct phylink;
 struct sfp_bus;
 struct sfp_upstream_ops;
@@ -1955,6 +1956,12 @@ int phy_ethtool_set_plca_cfg(struct phy_device *phydev,
 int phy_ethtool_get_plca_status(struct phy_device *phydev,
 				struct phy_plca_status *plca_st);
 
+int __phy_hwtstamp_get(struct phy_device *phydev,
+		       struct kernel_hwtstamp_config *config);
+int __phy_hwtstamp_set(struct phy_device *phydev,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack);
+
 static inline int phy_package_read(struct phy_device *phydev, u32 regnum)
 {
 	struct phy_package_shared *shared = phydev->shared;
diff --git a/include/linux/phylib_stubs.h b/include/linux/phylib_stubs.h
new file mode 100644
index 0000000000000..1279f48c8a707
--- /dev/null
+++ b/include/linux/phylib_stubs.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Stubs for the Network PHY library
+ */
+
+#include <linux/rtnetlink.h>
+
+struct kernel_hwtstamp_config;
+struct netlink_ext_ack;
+struct phy_device;
+
+#if IS_ENABLED(CONFIG_PHYLIB)
+
+extern const struct phylib_stubs *phylib_stubs;
+
+struct phylib_stubs {
+	int (*hwtstamp_get)(struct phy_device *phydev,
+			    struct kernel_hwtstamp_config *config);
+	int (*hwtstamp_set)(struct phy_device *phydev,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack);
+};
+
+static inline int phy_hwtstamp_get(struct phy_device *phydev,
+				   struct kernel_hwtstamp_config *config)
+{
+	/* phylib_register_stubs() and phylib_unregister_stubs()
+	 * also run under rtnl_lock().
+	 */
+	ASSERT_RTNL();
+
+	if (!phylib_stubs)
+		return -EOPNOTSUPP;
+
+	return phylib_stubs->hwtstamp_get(phydev, config);
+}
+
+static inline int phy_hwtstamp_set(struct phy_device *phydev,
+				   struct kernel_hwtstamp_config *config,
+				   struct netlink_ext_ack *extack)
+{
+	/* phylib_register_stubs() and phylib_unregister_stubs()
+	 * also run under rtnl_lock().
+	 */
+	ASSERT_RTNL();
+
+	if (!phylib_stubs)
+		return -EOPNOTSUPP;
+
+	return phylib_stubs->hwtstamp_set(phydev, config, extack);
+}
+
+#else
+
+static inline int phy_hwtstamp_get(struct phy_device *phydev,
+				   struct kernel_hwtstamp_config *config)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int phy_hwtstamp_set(struct phy_device *phydev,
+				   struct kernel_hwtstamp_config *config,
+				   struct netlink_ext_ack *extack)
+{
+	return -EOPNOTSUPP;
+}
+
+#endif
-- 
GitLab


From fd770e856e226f80fe6e1dc9d1861bcb135cdf0b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 1 Aug 2023 17:28:24 +0300
Subject: [PATCH 0823/1806] net: remove phy_has_hwtstamp() -> phy_mii_ioctl()
 decision from converted drivers

It is desirable that the new .ndo_hwtstamp_set() API gives more
uniformity, less overhead and future flexibility w.r.t. the PHY
timestamping behavior.

Currently there are some drivers which allow PHY timestamping through
the procedure mentioned in Documentation/networking/timestamping.rst.
They don't do anything locally if phy_has_hwtstamp() is set, except for
lan966x which installs PTP packet traps.

Centralize that behavior in a new dev_set_hwtstamp_phylib() code
function, which calls either phy_mii_ioctl() for the phylib PHY,
or .ndo_hwtstamp_set() of the netdev, based on a single policy
(currently simplistic: phy_has_hwtstamp()).

Any driver converted to .ndo_hwtstamp_set() will automatically opt into
the centralized phylib timestamping policy. Unconverted drivers still
get to choose whether they let the PHY handle timestamping or not.

Netdev drivers with integrated PHY drivers that don't use phylib
presumably don't set dev->phydev, and those will always see
HWTSTAMP_SOURCE_NETDEV requests even when converted. The timestamping
policy will remain 100% up to them.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Link: https://lore.kernel.org/r/20230801142824.1772134-13-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c     |  8 --
 .../ethernet/microchip/lan966x/lan966x_main.c | 25 ++---
 .../ethernet/microchip/sparx5/sparx5_netdev.c |  6 --
 include/linux/net_tstamp.h                    | 16 ++++
 include/linux/netdevice.h                     |  4 +
 net/core/dev_ioctl.c                          | 91 +++++++++++++++++--
 6 files changed, 117 insertions(+), 33 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 6d81fff0227e5..43f14cec91e93 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3872,10 +3872,6 @@ static int fec_hwtstamp_get(struct net_device *ndev,
 			    struct kernel_hwtstamp_config *config)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct phy_device *phydev = ndev->phydev;
-
-	if (phy_has_hwtstamp(phydev))
-		return phy_mii_ioctl(phydev, config->ifr, SIOCGHWTSTAMP);
 
 	if (!netif_running(ndev))
 		return -EINVAL;
@@ -3893,10 +3889,6 @@ static int fec_hwtstamp_set(struct net_device *ndev,
 			    struct netlink_ext_ack *extack)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct phy_device *phydev = ndev->phydev;
-
-	if (phy_has_hwtstamp(phydev))
-		return phy_mii_ioctl(phydev, config->ifr, SIOCSHWTSTAMP);
 
 	if (!netif_running(ndev))
 		return -EINVAL;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 1baa94a98fe33..4a1acc7234f64 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -455,9 +455,6 @@ static int lan966x_port_hwtstamp_get(struct net_device *dev,
 {
 	struct lan966x_port *port = netdev_priv(dev);
 
-	if (phy_has_hwtstamp(dev->phydev))
-		return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCGHWTSTAMP);
-
 	if (!port->lan966x->ptp)
 		return -EOPNOTSUPP;
 
@@ -473,21 +470,26 @@ static int lan966x_port_hwtstamp_set(struct net_device *dev,
 	struct lan966x_port *port = netdev_priv(dev);
 	int err;
 
+	if (cfg->source != HWTSTAMP_SOURCE_NETDEV &&
+	    cfg->source != HWTSTAMP_SOURCE_PHYLIB)
+		return -EOPNOTSUPP;
+
 	err = lan966x_ptp_setup_traps(port, cfg);
 	if (err)
 		return err;
 
-	if (phy_has_hwtstamp(dev->phydev)) {
-		err = phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCSHWTSTAMP);
-		if (err)
+	if (cfg->source == HWTSTAMP_SOURCE_NETDEV) {
+		if (!port->lan966x->ptp)
+			return -EOPNOTSUPP;
+
+		err = lan966x_ptp_hwtstamp_set(port, cfg, extack);
+		if (err) {
 			lan966x_ptp_del_traps(port);
-		return err;
+			return err;
+		}
 	}
 
-	if (!port->lan966x->ptp)
-		return -EOPNOTSUPP;
-
-	return lan966x_ptp_hwtstamp_set(port, cfg, extack);
+	return 0;
 }
 
 static const struct net_device_ops lan966x_port_netdev_ops = {
@@ -815,6 +817,7 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p,
 			 NETIF_F_HW_VLAN_STAG_TX |
 			 NETIF_F_HW_TC;
 	dev->hw_features |= NETIF_F_HW_TC;
+	dev->priv_flags |= IFF_SEE_ALL_HWTSTAMP_REQUESTS;
 	dev->needed_headroom = IFH_LEN_BYTES;
 
 	eth_hw_addr_gen(dev, lan966x->base_mac, p + 1);
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c
index e01d3b1e17e00..705a004b324fd 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c
@@ -216,9 +216,6 @@ static int sparx5_port_hwtstamp_get(struct net_device *dev,
 	struct sparx5_port *sparx5_port = netdev_priv(dev);
 	struct sparx5 *sparx5 = sparx5_port->sparx5;
 
-	if (phy_has_hwtstamp(dev->phydev))
-		return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCGHWTSTAMP);
-
 	if (!sparx5->ptp)
 		return -EOPNOTSUPP;
 
@@ -234,9 +231,6 @@ static int sparx5_port_hwtstamp_set(struct net_device *dev,
 	struct sparx5_port *sparx5_port = netdev_priv(dev);
 	struct sparx5 *sparx5 = sparx5_port->sparx5;
 
-	if (phy_has_hwtstamp(dev->phydev))
-		return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCSHWTSTAMP);
-
 	if (!sparx5->ptp)
 		return -EOPNOTSUPP;
 
diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h
index 03e9228148517..eb01c37e71e0a 100644
--- a/include/linux/net_tstamp.h
+++ b/include/linux/net_tstamp.h
@@ -5,6 +5,11 @@
 
 #include <uapi/linux/net_tstamp.h>
 
+enum hwtstamp_source {
+	HWTSTAMP_SOURCE_NETDEV,
+	HWTSTAMP_SOURCE_PHYLIB,
+};
+
 /**
  * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config
  *
@@ -15,6 +20,8 @@
  *	a legacy implementation of a lower driver
  * @copied_to_user: request was passed to a legacy implementation which already
  *	copied the ioctl request back to user space
+ * @source: indication whether timestamps should come from the netdev or from
+ *	an attached phylib PHY
  *
  * Prefer using this structure for in-kernel processing of hardware
  * timestamping configuration, over the inextensible struct hwtstamp_config
@@ -26,6 +33,7 @@ struct kernel_hwtstamp_config {
 	int rx_filter;
 	struct ifreq *ifr;
 	bool copied_to_user;
+	enum hwtstamp_source source;
 };
 
 static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg,
@@ -44,4 +52,12 @@ static inline void hwtstamp_config_from_kernel(struct hwtstamp_config *cfg,
 	cfg->rx_filter = kernel_cfg->rx_filter;
 }
 
+static inline bool kernel_hwtstamp_config_changed(const struct kernel_hwtstamp_config *a,
+						  const struct kernel_hwtstamp_config *b)
+{
+	return a->flags != b->flags ||
+	       a->tx_type != b->tx_type ||
+	       a->rx_filter != b->rx_filter;
+}
+
 #endif /* _LINUX_NET_TIMESTAMPING_H_ */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 23e335f245cf7..85d594460c666 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1724,6 +1724,9 @@ struct xdp_metadata_ops {
  * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with
  *	skb_headlen(skb) == 0 (data starts from frag0)
  * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN
+ * @IFF_SEE_ALL_HWTSTAMP_REQUESTS: device wants to see calls to
+ *	ndo_hwtstamp_set() for all timestamp requests regardless of source,
+ *	even if those aren't HWTSTAMP_SOURCE_NETDEV.
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1759,6 +1762,7 @@ enum netdev_priv_flags {
 	IFF_NO_ADDRCONF			= BIT_ULL(30),
 	IFF_TX_SKB_NO_LINEAR		= BIT_ULL(31),
 	IFF_CHANGE_PROTO_DOWN		= BIT_ULL(32),
+	IFF_SEE_ALL_HWTSTAMP_REQUESTS	= BIT_ULL(33),
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index d0223ecd6f6f4..72e0770223483 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -5,6 +5,7 @@
 #include <linux/etherdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/net_tstamp.h>
+#include <linux/phylib_stubs.h>
 #include <linux/wireless.h>
 #include <linux/if_bridge.h>
 #include <net/dsa_stubs.h>
@@ -252,6 +253,30 @@ static int dev_eth_ioctl(struct net_device *dev,
 	return ops->ndo_eth_ioctl(dev, ifr, cmd);
 }
 
+/**
+ * dev_get_hwtstamp_phylib() - Get hardware timestamping settings of NIC
+ *	or of attached phylib PHY
+ * @dev: Network device
+ * @cfg: Timestamping configuration structure
+ *
+ * Helper for enforcing a common policy that phylib timestamping, if available,
+ * should take precedence in front of hardware timestamping provided by the
+ * netdev.
+ *
+ * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), and
+ * there only exists a phydev->mii_ts->hwtstamp() method. So this will return
+ * -EOPNOTSUPP for phylib for now, which is still more accurate than letting
+ * the netdev handle the GET request.
+ */
+static int dev_get_hwtstamp_phylib(struct net_device *dev,
+				   struct kernel_hwtstamp_config *cfg)
+{
+	if (phy_has_hwtstamp(dev->phydev))
+		return phy_hwtstamp_get(dev->phydev, cfg);
+
+	return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg);
+}
+
 static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -266,7 +291,7 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 		return -ENODEV;
 
 	kernel_cfg.ifr = ifr;
-	err = ops->ndo_hwtstamp_get(dev, &kernel_cfg);
+	err = dev_get_hwtstamp_phylib(dev, &kernel_cfg);
 	if (err)
 		return err;
 
@@ -283,6 +308,59 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 	return 0;
 }
 
+/**
+ * dev_set_hwtstamp_phylib() - Change hardware timestamping of NIC
+ *	or of attached phylib PHY
+ * @dev: Network device
+ * @cfg: Timestamping configuration structure
+ * @extack: Netlink extended ack message structure, for error reporting
+ *
+ * Helper for enforcing a common policy that phylib timestamping, if available,
+ * should take precedence in front of hardware timestamping provided by the
+ * netdev. If the netdev driver needs to perform specific actions even for PHY
+ * timestamping to work properly (a switch port must trap the timestamped
+ * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in
+ * dev->priv_flags.
+ */
+static int dev_set_hwtstamp_phylib(struct net_device *dev,
+				   struct kernel_hwtstamp_config *cfg,
+				   struct netlink_ext_ack *extack)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	bool phy_ts = phy_has_hwtstamp(dev->phydev);
+	struct kernel_hwtstamp_config old_cfg = {};
+	bool changed = false;
+	int err;
+
+	cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV;
+
+	if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
+		err = ops->ndo_hwtstamp_get(dev, &old_cfg);
+		if (err)
+			return err;
+
+		err = ops->ndo_hwtstamp_set(dev, cfg, extack);
+		if (err) {
+			if (extack->_msg)
+				netdev_err(dev, "%s\n", extack->_msg);
+			return err;
+		}
+
+		changed = kernel_hwtstamp_config_changed(&old_cfg, cfg);
+	}
+
+	if (phy_ts) {
+		err = phy_hwtstamp_set(dev->phydev, cfg, extack);
+		if (err) {
+			if (changed)
+				ops->ndo_hwtstamp_set(dev, &old_cfg, NULL);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
 static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -314,12 +392,9 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 	if (!netif_device_present(dev))
 		return -ENODEV;
 
-	err = ops->ndo_hwtstamp_set(dev, &kernel_cfg, &extack);
-	if (err) {
-		if (extack._msg)
-			netdev_err(dev, "%s\n", extack._msg);
+	err = dev_set_hwtstamp_phylib(dev, &kernel_cfg, &extack);
+	if (err)
 		return err;
-	}
 
 	/* The driver may have modified the configuration, so copy the
 	 * updated version of it back to user space
@@ -362,7 +437,7 @@ int generic_hwtstamp_get_lower(struct net_device *dev,
 		return -ENODEV;
 
 	if (ops->ndo_hwtstamp_get)
-		return ops->ndo_hwtstamp_get(dev, kernel_cfg);
+		return dev_get_hwtstamp_phylib(dev, kernel_cfg);
 
 	/* Legacy path: unconverted lower driver */
 	return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg);
@@ -379,7 +454,7 @@ int generic_hwtstamp_set_lower(struct net_device *dev,
 		return -ENODEV;
 
 	if (ops->ndo_hwtstamp_set)
-		return ops->ndo_hwtstamp_set(dev, kernel_cfg, extack);
+		return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack);
 
 	/* Legacy path: unconverted lower driver */
 	return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg);
-- 
GitLab


From 80662d9430757302176a4c2e1d7577184eb76adc Mon Sep 17 00:00:00 2001
From: Frank Jungclaus <frank.jungclaus@esd.eu>
Date: Fri, 28 Jul 2023 17:08:57 +0200
Subject: [PATCH 0824/1806] can: esd_usb: Add support for esd CAN-USB/3

Add support for esd CAN-USB/3 and CAN FD to esd_usb.c.

Signed-off-by: Frank Jungclaus <frank.jungclaus@esd.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/all/20230728150857.2374886-2-frank.jungclaus@esd.eu
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/esd_usb.c | 275 ++++++++++++++++++++++++++++++----
 1 file changed, 244 insertions(+), 31 deletions(-)

diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c
index 6201637ac0ff2..41a0e4261d15e 100644
--- a/drivers/net/can/usb/esd_usb.c
+++ b/drivers/net/can/usb/esd_usb.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * CAN driver for esd electronics gmbh CAN-USB/2 and CAN-USB/Micro
+ * CAN driver for esd electronics gmbh CAN-USB/2, CAN-USB/3 and CAN-USB/Micro
  *
  * Copyright (C) 2010-2012 esd electronic system design gmbh, Matthias Fuchs <socketcan@esd.eu>
  * Copyright (C) 2022-2023 esd electronics gmbh, Frank Jungclaus <frank.jungclaus@esd.eu>
@@ -19,17 +19,19 @@
 
 MODULE_AUTHOR("Matthias Fuchs <socketcan@esd.eu>");
 MODULE_AUTHOR("Frank Jungclaus <frank.jungclaus@esd.eu>");
-MODULE_DESCRIPTION("CAN driver for esd electronics gmbh CAN-USB/2 and CAN-USB/Micro interfaces");
+MODULE_DESCRIPTION("CAN driver for esd electronics gmbh CAN-USB/2, CAN-USB/3 and CAN-USB/Micro interfaces");
 MODULE_LICENSE("GPL v2");
 
 /* USB vendor and product ID */
 #define ESD_USB_ESDGMBH_VENDOR_ID	0x0ab4
 #define ESD_USB_CANUSB2_PRODUCT_ID	0x0010
 #define ESD_USB_CANUSBM_PRODUCT_ID	0x0011
+#define ESD_USB_CANUSB3_PRODUCT_ID	0x0014
 
 /* CAN controller clock frequencies */
 #define ESD_USB_2_CAN_CLOCK	(60 * MEGA) /* Hz */
 #define ESD_USB_M_CAN_CLOCK	(36 * MEGA) /* Hz */
+#define ESD_USB_3_CAN_CLOCK	(80 * MEGA) /* Hz */
 
 /* Maximum number of CAN nets */
 #define ESD_USB_MAX_NETS	2
@@ -44,6 +46,9 @@ MODULE_LICENSE("GPL v2");
 
 /* esd CAN message flags - dlc field */
 #define ESD_USB_RTR	BIT(4)
+#define ESD_USB_NO_BRS	BIT(4)
+#define ESD_USB_ESI	BIT(5)
+#define ESD_USB_FD	BIT(7)
 
 /* esd CAN message flags - id field */
 #define ESD_USB_EXTID	BIT(29)
@@ -65,6 +70,9 @@ MODULE_LICENSE("GPL v2");
 #define ESD_USB_M_SJW_SHIFT	24
 #define ESD_USB_TRIPLE_SAMPLES	BIT(23)
 
+/* Transmitter Delay Compensation */
+#define ESD_USB_3_TDC_MODE_AUTO	0
+
 /* esd IDADD message */
 #define ESD_USB_ID_ENABLE	BIT(7)
 #define ESD_USB_MAX_ID_SEGMENT	64
@@ -88,6 +96,21 @@ MODULE_LICENSE("GPL v2");
 #define ESD_USB_MAX_RX_URBS		4
 #define ESD_USB_MAX_TX_URBS		16 /* must be power of 2 */
 
+/* Modes for CAN-USB/3, to be used for esd_usb_3_set_baudrate_msg_x.mode */
+#define ESD_USB_3_BAUDRATE_MODE_DISABLE		0 /* remove from bus */
+#define ESD_USB_3_BAUDRATE_MODE_INDEX		1 /* ESD (CiA) bit rate idx */
+#define ESD_USB_3_BAUDRATE_MODE_BTR_CTRL	2 /* BTR values (controller)*/
+#define ESD_USB_3_BAUDRATE_MODE_BTR_CANONICAL	3 /* BTR values (canonical) */
+#define ESD_USB_3_BAUDRATE_MODE_NUM		4 /* numerical bit rate */
+#define ESD_USB_3_BAUDRATE_MODE_AUTOBAUD	5 /* autobaud */
+
+/* Flags for CAN-USB/3, to be used for esd_usb_3_set_baudrate_msg_x.flags */
+#define ESD_USB_3_BAUDRATE_FLAG_FD	BIT(0) /* enable CAN FD mode */
+#define ESD_USB_3_BAUDRATE_FLAG_LOM	BIT(1) /* enable listen only mode */
+#define ESD_USB_3_BAUDRATE_FLAG_STM	BIT(2) /* enable self test mode */
+#define ESD_USB_3_BAUDRATE_FLAG_TRS	BIT(3) /* enable triple sampling */
+#define ESD_USB_3_BAUDRATE_FLAG_TXP	BIT(4) /* enable transmit pause */
+
 struct esd_usb_header_msg {
 	u8 len; /* total message length in 32bit words */
 	u8 cmd;
@@ -122,6 +145,7 @@ struct esd_usb_rx_msg {
 	__le32 id; /* upper 3 bits contain flags */
 	union {
 		u8 data[CAN_MAX_DLEN];
+		u8 data_fd[CANFD_MAX_DLEN];
 		struct {
 			u8 status; /* CAN Controller Status */
 			u8 ecc;    /* Error Capture Register */
@@ -138,7 +162,10 @@ struct esd_usb_tx_msg {
 	u8 dlc;
 	u32 hnd;	/* opaque handle, not used by device */
 	__le32 id; /* upper 3 bits contain flags */
-	u8 data[CAN_MAX_DLEN];
+	union {
+		u8 data[CAN_MAX_DLEN];
+		u8 data_fd[CANFD_MAX_DLEN];
+	};
 };
 
 struct esd_usb_tx_done_msg {
@@ -166,6 +193,50 @@ struct esd_usb_set_baudrate_msg {
 	__le32 baud;
 };
 
+/* CAN-USB/3 baudrate configuration, used for nominal as well as for data bit rate */
+struct esd_usb_3_baudrate_cfg {
+	__le16 brp;	/* bit rate pre-scaler */
+	__le16 tseg1;	/* time segment before sample point */
+	__le16 tseg2;	/* time segment after sample point */
+	__le16 sjw;	/* synchronization jump Width */
+};
+
+/* In principle, the esd CAN-USB/3 supports Transmitter Delay Compensation (TDC),
+ * but currently only the automatic TDC mode is supported by this driver.
+ * An implementation for manual TDC configuration will follow.
+ *
+ * For information about struct esd_usb_3_tdc_cfg, see
+ * NTCAN Application Developers Manual, 6.2.25 NTCAN_TDC_CFG + related chapters
+ * https://esd.eu/fileadmin/esd/docs/manuals/NTCAN_Part1_Function_API_Manual_en_56.pdf
+ */
+struct esd_usb_3_tdc_cfg {
+	u8 tdc_mode;	/* transmitter delay compensation mode  */
+	u8 ssp_offset;	/* secondary sample point offset in mtq */
+	s8 ssp_shift;	/* secondary sample point shift in mtq */
+	u8 tdc_filter;	/* TDC filter in mtq */
+};
+
+/* Extended version of the above set_baudrate_msg for a CAN-USB/3
+ * to define the CAN bit timing configuration of the CAN controller in
+ * CAN FD mode as well as in Classical CAN mode.
+ *
+ * The payload of this command is a NTCAN_BAUDRATE_X structure according to
+ * esd electronics gmbh, NTCAN Application Developers Manual, 6.2.15 NTCAN_BAUDRATE_X
+ * https://esd.eu/fileadmin/esd/docs/manuals/NTCAN_Part1_Function_API_Manual_en_56.pdf
+ */
+struct esd_usb_3_set_baudrate_msg_x {
+	u8 len;	/* total message length in 32bit words */
+	u8 cmd;
+	u8 net;
+	u8 rsvd;	/*reserved */
+	/* Payload ... */
+	__le16 mode;	/* mode word, see ESD_USB_3_BAUDRATE_MODE_xxx */
+	__le16 flags;	/* control flags, see ESD_USB_3_BAUDRATE_FLAG_xxx */
+	struct esd_usb_3_tdc_cfg tdc;	/* TDC configuration */
+	struct esd_usb_3_baudrate_cfg nom;	/* nominal bit rate */
+	struct esd_usb_3_baudrate_cfg data;	/* data bit rate */
+};
+
 /* Main message type used between library and application */
 union __packed esd_usb_msg {
 	struct esd_usb_header_msg hdr;
@@ -175,12 +246,14 @@ union __packed esd_usb_msg {
 	struct esd_usb_tx_msg tx;
 	struct esd_usb_tx_done_msg txdone;
 	struct esd_usb_set_baudrate_msg setbaud;
+	struct esd_usb_3_set_baudrate_msg_x setbaud_x;
 	struct esd_usb_id_filter_msg filter;
 };
 
 static struct usb_device_id esd_usb_table[] = {
 	{USB_DEVICE(ESD_USB_ESDGMBH_VENDOR_ID, ESD_USB_CANUSB2_PRODUCT_ID)},
 	{USB_DEVICE(ESD_USB_ESDGMBH_VENDOR_ID, ESD_USB_CANUSBM_PRODUCT_ID)},
+	{USB_DEVICE(ESD_USB_ESDGMBH_VENDOR_ID, ESD_USB_CANUSB3_PRODUCT_ID)},
 	{}
 };
 MODULE_DEVICE_TABLE(usb, esd_usb_table);
@@ -321,9 +394,10 @@ static void esd_usb_rx_can_msg(struct esd_usb_net_priv *priv,
 {
 	struct net_device_stats *stats = &priv->netdev->stats;
 	struct can_frame *cf;
+	struct canfd_frame *cfd;
 	struct sk_buff *skb;
-	int i;
 	u32 id;
+	u8 len;
 
 	if (!netif_device_present(priv->netdev))
 		return;
@@ -333,27 +407,42 @@ static void esd_usb_rx_can_msg(struct esd_usb_net_priv *priv,
 	if (id & ESD_USB_EVENT) {
 		esd_usb_rx_event(priv, msg);
 	} else {
-		skb = alloc_can_skb(priv->netdev, &cf);
+		if (msg->rx.dlc & ESD_USB_FD) {
+			skb = alloc_canfd_skb(priv->netdev, &cfd);
+		} else {
+			skb = alloc_can_skb(priv->netdev, &cf);
+			cfd = (struct canfd_frame *)cf;
+		}
+
 		if (skb == NULL) {
 			stats->rx_dropped++;
 			return;
 		}
 
-		cf->can_id = id & ESD_USB_IDMASK;
-		can_frame_set_cc_len(cf, msg->rx.dlc & ~ESD_USB_RTR,
-				     priv->can.ctrlmode);
-
-		if (id & ESD_USB_EXTID)
-			cf->can_id |= CAN_EFF_FLAG;
+		cfd->can_id = id & ESD_USB_IDMASK;
 
-		if (msg->rx.dlc & ESD_USB_RTR) {
-			cf->can_id |= CAN_RTR_FLAG;
+		if (msg->rx.dlc & ESD_USB_FD) {
+			/* masking by 0x0F is already done within can_fd_dlc2len() */
+			cfd->len = can_fd_dlc2len(msg->rx.dlc);
+			len = cfd->len;
+			if ((msg->rx.dlc & ESD_USB_NO_BRS) == 0)
+				cfd->flags |= CANFD_BRS;
+			if (msg->rx.dlc & ESD_USB_ESI)
+				cfd->flags |= CANFD_ESI;
 		} else {
-			for (i = 0; i < cf->len; i++)
-				cf->data[i] = msg->rx.data[i];
-
-			stats->rx_bytes += cf->len;
+			can_frame_set_cc_len(cf, msg->rx.dlc & ~ESD_USB_RTR, priv->can.ctrlmode);
+			len = cf->len;
+			if (msg->rx.dlc & ESD_USB_RTR) {
+				cf->can_id |= CAN_RTR_FLAG;
+				len = 0;
+			}
 		}
+
+		if (id & ESD_USB_EXTID)
+			cfd->can_id |= CAN_EFF_FLAG;
+
+		memcpy(cfd->data, msg->rx.data_fd, len);
+		stats->rx_bytes += len;
 		stats->rx_packets++;
 
 		netif_rx(skb);
@@ -728,7 +817,7 @@ static netdev_tx_t esd_usb_start_xmit(struct sk_buff *skb,
 	struct esd_usb *dev = priv->usb;
 	struct esd_tx_urb_context *context = NULL;
 	struct net_device_stats *stats = &netdev->stats;
-	struct can_frame *cf = (struct can_frame *)skb->data;
+	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 	union esd_usb_msg *msg;
 	struct urb *urb;
 	u8 *buf;
@@ -762,20 +851,29 @@ static netdev_tx_t esd_usb_start_xmit(struct sk_buff *skb,
 	msg->hdr.len = offsetof(struct esd_usb_tx_msg, data) / sizeof(u32);
 	msg->hdr.cmd = ESD_USB_CMD_CAN_TX;
 	msg->tx.net = priv->index;
-	msg->tx.dlc = can_get_cc_dlc(cf, priv->can.ctrlmode);
-	msg->tx.id = cpu_to_le32(cf->can_id & CAN_ERR_MASK);
 
-	if (cf->can_id & CAN_RTR_FLAG)
-		msg->tx.dlc |= ESD_USB_RTR;
+	if (can_is_canfd_skb(skb)) {
+		msg->tx.dlc = can_fd_len2dlc(cfd->len);
+		msg->tx.dlc |= ESD_USB_FD;
+
+		if ((cfd->flags & CANFD_BRS) == 0)
+			msg->tx.dlc |= ESD_USB_NO_BRS;
+	} else {
+		msg->tx.dlc = can_get_cc_dlc((struct can_frame *)cfd, priv->can.ctrlmode);
+
+		if (cfd->can_id & CAN_RTR_FLAG)
+			msg->tx.dlc |= ESD_USB_RTR;
+	}
+
+	msg->tx.id = cpu_to_le32(cfd->can_id & CAN_ERR_MASK);
 
-	if (cf->can_id & CAN_EFF_FLAG)
+	if (cfd->can_id & CAN_EFF_FLAG)
 		msg->tx.id |= cpu_to_le32(ESD_USB_EXTID);
 
-	for (i = 0; i < cf->len; i++)
-		msg->tx.data[i] = cf->data[i];
+	memcpy(msg->tx.data_fd, cfd->data, cfd->len);
 
 	/* round up, then divide by 4 to add the payload length as # of 32bit words */
-	msg->hdr.len += DIV_ROUND_UP(cf->len, sizeof(u32));
+	msg->hdr.len += DIV_ROUND_UP(cfd->len, sizeof(u32));
 
 	for (i = 0; i < ESD_USB_MAX_TX_URBS; i++) {
 		if (priv->tx_contexts[i].echo_index == ESD_USB_MAX_TX_URBS) {
@@ -962,6 +1060,105 @@ static int esd_usb_2_set_bittiming(struct net_device *netdev)
 	return err;
 }
 
+/* Nominal bittiming constants, see
+ * Microchip SAM E70/S70/V70/V71, Data Sheet, Rev. G - 07/2022
+ * 48.6.8 MCAN Nominal Bit Timing and Prescaler Register
+ */
+static const struct can_bittiming_const esd_usb_3_nom_bittiming_const = {
+	.name = "esd_usb_3",
+	.tseg1_min = 2,
+	.tseg1_max = 256,
+	.tseg2_min = 2,
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 1,
+	.brp_max = 512,
+	.brp_inc = 1,
+};
+
+/* Data bittiming constants, see
+ * Microchip SAM E70/S70/V70/V71, Data Sheet, Rev. G - 07/2022
+ * 48.6.4 MCAN Data Bit Timing and Prescaler Register
+ */
+static const struct can_bittiming_const esd_usb_3_data_bittiming_const = {
+	.name = "esd_usb_3",
+	.tseg1_min = 2,
+	.tseg1_max = 32,
+	.tseg2_min = 1,
+	.tseg2_max = 16,
+	.sjw_max = 8,
+	.brp_min = 1,
+	.brp_max = 32,
+	.brp_inc = 1,
+};
+
+static int esd_usb_3_set_bittiming(struct net_device *netdev)
+{
+	const struct can_bittiming_const *nom_btc = &esd_usb_3_nom_bittiming_const;
+	const struct can_bittiming_const *data_btc = &esd_usb_3_data_bittiming_const;
+	struct esd_usb_net_priv *priv = netdev_priv(netdev);
+	struct can_bittiming *nom_bt = &priv->can.bittiming;
+	struct can_bittiming *data_bt = &priv->can.data_bittiming;
+	struct esd_usb_3_set_baudrate_msg_x *baud_x;
+	union esd_usb_msg *msg;
+	u16 flags = 0;
+	int err;
+
+	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	baud_x = &msg->setbaud_x;
+
+	/* Canonical is the most reasonable mode for SocketCAN on CAN-USB/3 ... */
+	baud_x->mode = cpu_to_le16(ESD_USB_3_BAUDRATE_MODE_BTR_CANONICAL);
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		flags |= ESD_USB_3_BAUDRATE_FLAG_LOM;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
+		flags |= ESD_USB_3_BAUDRATE_FLAG_TRS;
+
+	baud_x->nom.brp = cpu_to_le16(nom_bt->brp & (nom_btc->brp_max - 1));
+	baud_x->nom.sjw = cpu_to_le16(nom_bt->sjw & (nom_btc->sjw_max - 1));
+	baud_x->nom.tseg1 = cpu_to_le16((nom_bt->prop_seg + nom_bt->phase_seg1)
+					& (nom_btc->tseg1_max - 1));
+	baud_x->nom.tseg2 = cpu_to_le16(nom_bt->phase_seg2 & (nom_btc->tseg2_max - 1));
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+		baud_x->data.brp = cpu_to_le16(data_bt->brp & (data_btc->brp_max - 1));
+		baud_x->data.sjw = cpu_to_le16(data_bt->sjw & (data_btc->sjw_max - 1));
+		baud_x->data.tseg1 = cpu_to_le16((data_bt->prop_seg + data_bt->phase_seg1)
+						 & (data_btc->tseg1_max - 1));
+		baud_x->data.tseg2 = cpu_to_le16(data_bt->phase_seg2 & (data_btc->tseg2_max - 1));
+		flags |= ESD_USB_3_BAUDRATE_FLAG_FD;
+	}
+
+	/* Currently this driver only supports the automatic TDC mode */
+	baud_x->tdc.tdc_mode = ESD_USB_3_TDC_MODE_AUTO;
+	baud_x->tdc.ssp_offset = 0;
+	baud_x->tdc.ssp_shift = 0;
+	baud_x->tdc.tdc_filter = 0;
+
+	baud_x->flags = cpu_to_le16(flags);
+	baud_x->net = priv->index;
+	baud_x->rsvd = 0;
+
+	/* set len as # of 32bit words */
+	msg->hdr.len = sizeof(struct esd_usb_3_set_baudrate_msg_x) / sizeof(u32);
+	msg->hdr.cmd = ESD_USB_CMD_SETBAUD;
+
+	netdev_dbg(netdev,
+		   "ctrlmode=%#x/%#x, esd-net=%u, esd-mode=%#x, esd-flags=%#x\n",
+		   priv->can.ctrlmode, priv->can.ctrlmode_supported,
+		   priv->index, le16_to_cpu(baud_x->mode), flags);
+
+	err = esd_usb_send_msg(priv->usb, msg);
+
+	kfree(msg);
+	return err;
+}
+
 static int esd_usb_get_berr_counter(const struct net_device *netdev,
 				    struct can_berr_counter *bec)
 {
@@ -1019,16 +1216,32 @@ static int esd_usb_probe_one_net(struct usb_interface *intf, int index)
 		CAN_CTRLMODE_CC_LEN8_DLC |
 		CAN_CTRLMODE_BERR_REPORTING;
 
-	if (le16_to_cpu(dev->udev->descriptor.idProduct) ==
-	    ESD_USB_CANUSBM_PRODUCT_ID)
+	switch (le16_to_cpu(dev->udev->descriptor.idProduct)) {
+	case ESD_USB_CANUSB3_PRODUCT_ID:
+		priv->can.clock.freq = ESD_USB_3_CAN_CLOCK;
+		priv->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
+		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
+		priv->can.bittiming_const = &esd_usb_3_nom_bittiming_const;
+		priv->can.data_bittiming_const = &esd_usb_3_data_bittiming_const;
+		priv->can.do_set_bittiming = esd_usb_3_set_bittiming;
+		priv->can.do_set_data_bittiming = esd_usb_3_set_bittiming;
+		break;
+
+	case ESD_USB_CANUSBM_PRODUCT_ID:
 		priv->can.clock.freq = ESD_USB_M_CAN_CLOCK;
-	else {
+		priv->can.bittiming_const = &esd_usb_2_bittiming_const;
+		priv->can.do_set_bittiming = esd_usb_2_set_bittiming;
+		break;
+
+	case ESD_USB_CANUSB2_PRODUCT_ID:
+	default:
 		priv->can.clock.freq = ESD_USB_2_CAN_CLOCK;
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
+		priv->can.bittiming_const = &esd_usb_2_bittiming_const;
+		priv->can.do_set_bittiming = esd_usb_2_set_bittiming;
+		break;
 	}
 
-	priv->can.bittiming_const = &esd_usb_2_bittiming_const;
-	priv->can.do_set_bittiming = esd_usb_2_set_bittiming;
 	priv->can.do_set_mode = esd_usb_set_mode;
 	priv->can.do_get_berr_counter = esd_usb_get_berr_counter;
 
-- 
GitLab


From f11e5bd159b08976db9e7a9eabbf0318dfe5429d Mon Sep 17 00:00:00 2001
From: Mateusz Kowalski <mko@redhat.com>
Date: Tue, 1 Aug 2023 14:37:50 +0200
Subject: [PATCH 0825/1806] bonding: support balance-alb with openvswitch

Commit d5410ac7b0ba ("net:bonding:support balance-alb interface with
vlan to bridge") introduced a support for balance-alb mode for
interfaces connected to the linux bridge by fixing missing matching of
MAC entry in FDB. In our testing we discovered that it still does not
work when the bond is connected to the OVS bridge as show in diagram
below:

eth1(mac:eth1_mac)--bond0(balance-alb,mac:eth0_mac)--eth0(mac:eth0_mac)
                         |
                       bond0.150(mac:eth0_mac)
                         |
                       ovs_bridge(ip:bridge_ip,mac:eth0_mac)

This patch fixes it by checking not only if the device is a bridge but
also if it is an openvswitch.

Signed-off-by: Mateusz Kowalski <mko@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/9fe7297c-609e-208b-c77b-3ceef6eb51a4@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_alb.c | 2 +-
 include/linux/netdevice.h      | 5 +++++
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index b9dbad3a8af82..cc5049eb25f83 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -668,7 +668,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 
 	dev = ip_dev_find(dev_net(bond->dev), arp->ip_src);
 	if (dev) {
-		if (netif_is_bridge_master(dev)) {
+		if (netif_is_any_bridge_master(dev)) {
 			dev_put(dev);
 			return NULL;
 		}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 85d594460c666..4176a738177be 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5128,6 +5128,11 @@ static inline bool netif_is_ovs_port(const struct net_device *dev)
 	return dev->priv_flags & IFF_OVS_DATAPATH;
 }
 
+static inline bool netif_is_any_bridge_master(const struct net_device *dev)
+{
+	return netif_is_bridge_master(dev) || netif_is_ovs_master(dev);
+}
+
 static inline bool netif_is_any_bridge_port(const struct net_device *dev)
 {
 	return netif_is_bridge_port(dev) || netif_is_ovs_port(dev);
-- 
GitLab


From e22f5b780c691ae2ed0d5e7743ccd6183baf5dc2 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:00 +0300
Subject: [PATCH 0826/1806] wifi: ath12k: rename HE capabilities setup/copy
 functions

Functions ath12k_mac_setup_he_cap() and ath12k_mac_copy_he_cap()
propagate HE and 6GHz capabilities to the userspace using an instance
of struct ieee80211_sband_iftype_data. This structure now has a new
member 'eht_cap' to include EHT capabilities as well.
Rename the above mentioned functions to indicate that their use is not
limited to HE.

Also, replace the local variable 'band' with 'sband' and reuse
'band' for the type enum nl80211_band.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-2-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 58 ++++++++++++++-------------
 1 file changed, 31 insertions(+), 27 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 4fa565a115e34..4d04b6f67043c 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -4222,10 +4222,10 @@ static __le16 ath12k_mac_setup_he_6ghz_cap(struct ath12k_pdev_cap *pcap,
 	return cpu_to_le16(bcap->he_6ghz_capa);
 }
 
-static int ath12k_mac_copy_he_cap(struct ath12k *ar,
-				  struct ath12k_pdev_cap *cap,
-				  struct ieee80211_sband_iftype_data *data,
-				  int band)
+static int ath12k_mac_copy_sband_iftype_data(struct ath12k *ar,
+					     struct ath12k_pdev_cap *cap,
+					     struct ieee80211_sband_iftype_data *data,
+					     int band)
 {
 	int i, idx = 0;
 
@@ -4310,38 +4310,42 @@ static int ath12k_mac_copy_he_cap(struct ath12k *ar,
 	return idx;
 }
 
-static void ath12k_mac_setup_he_cap(struct ath12k *ar,
-				    struct ath12k_pdev_cap *cap)
+static void ath12k_mac_setup_sband_iftype_data(struct ath12k *ar,
+					       struct ath12k_pdev_cap *cap)
 {
-	struct ieee80211_supported_band *band;
+	struct ieee80211_supported_band *sband;
+	enum nl80211_band band;
 	int count;
 
 	if (cap->supported_bands & WMI_HOST_WLAN_2G_CAP) {
-		count = ath12k_mac_copy_he_cap(ar, cap,
-					       ar->mac.iftype[NL80211_BAND_2GHZ],
-					       NL80211_BAND_2GHZ);
-		band = &ar->mac.sbands[NL80211_BAND_2GHZ];
-		band->iftype_data = ar->mac.iftype[NL80211_BAND_2GHZ];
-		band->n_iftype_data = count;
+		band = NL80211_BAND_2GHZ;
+		count = ath12k_mac_copy_sband_iftype_data(ar, cap,
+							  ar->mac.iftype[band],
+							  band);
+		sband = &ar->mac.sbands[band];
+		sband->iftype_data = ar->mac.iftype[band];
+		sband->n_iftype_data = count;
 	}
 
 	if (cap->supported_bands & WMI_HOST_WLAN_5G_CAP) {
-		count = ath12k_mac_copy_he_cap(ar, cap,
-					       ar->mac.iftype[NL80211_BAND_5GHZ],
-					       NL80211_BAND_5GHZ);
-		band = &ar->mac.sbands[NL80211_BAND_5GHZ];
-		band->iftype_data = ar->mac.iftype[NL80211_BAND_5GHZ];
-		band->n_iftype_data = count;
+		band = NL80211_BAND_5GHZ;
+		count = ath12k_mac_copy_sband_iftype_data(ar, cap,
+							  ar->mac.iftype[band],
+							  band);
+		sband = &ar->mac.sbands[band];
+		sband->iftype_data = ar->mac.iftype[band];
+		sband->n_iftype_data = count;
 	}
 
 	if (cap->supported_bands & WMI_HOST_WLAN_5G_CAP &&
 	    ar->supports_6ghz) {
-		count = ath12k_mac_copy_he_cap(ar, cap,
-					       ar->mac.iftype[NL80211_BAND_6GHZ],
-					       NL80211_BAND_6GHZ);
-		band = &ar->mac.sbands[NL80211_BAND_6GHZ];
-		band->iftype_data = ar->mac.iftype[NL80211_BAND_6GHZ];
-		band->n_iftype_data = count;
+		band = NL80211_BAND_6GHZ;
+		count = ath12k_mac_copy_sband_iftype_data(ar, cap,
+							  ar->mac.iftype[band],
+							  band);
+		sband = &ar->mac.sbands[band];
+		sband->iftype_data = ar->mac.iftype[band];
+		sband->n_iftype_data = count;
 	}
 }
 
@@ -4386,7 +4390,7 @@ static int __ath12k_set_antenna(struct ath12k *ar, u32 tx_ant, u32 rx_ant)
 
 	/* Reload HT/VHT/HE capability */
 	ath12k_mac_setup_ht_vht_cap(ar, &ar->pdev->cap, NULL);
-	ath12k_mac_setup_he_cap(ar, &ar->pdev->cap);
+	ath12k_mac_setup_sband_iftype_data(ar, &ar->pdev->cap);
 
 	return 0;
 }
@@ -6888,7 +6892,7 @@ static int __ath12k_mac_register(struct ath12k *ar)
 		goto err;
 
 	ath12k_mac_setup_ht_vht_cap(ar, cap, &ht_cap);
-	ath12k_mac_setup_he_cap(ar, cap);
+	ath12k_mac_setup_sband_iftype_data(ar, cap);
 
 	ret = ath12k_mac_setup_iface_combinations(ar);
 	if (ret) {
-- 
GitLab


From a7a6a45d37fe868b30363255d3a37a44acd1cf37 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:01 +0300
Subject: [PATCH 0827/1806] wifi: ath12k: move HE capabilities processing to a
 new function

The function ath12k_mac_copy_sband_iftype_data() is currently
used HE capabilities propagation but it can be extended to
include EHT data. Move the HE specific functionality from to
ath12k_mac_copy_he_cap() to make EHT additions easier.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-3-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 111 +++++++++++++-------------
 1 file changed, 55 insertions(+), 56 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 4d04b6f67043c..8fedbf4879d6d 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -4222,18 +4222,69 @@ static __le16 ath12k_mac_setup_he_6ghz_cap(struct ath12k_pdev_cap *pcap,
 	return cpu_to_le16(bcap->he_6ghz_capa);
 }
 
+static void ath12k_mac_copy_he_cap(struct ath12k_band_cap *band_cap,
+				   int iftype, u8 num_tx_chains,
+				   struct ieee80211_sta_he_cap *he_cap)
+{
+	struct ieee80211_he_cap_elem *he_cap_elem = &he_cap->he_cap_elem;
+	struct ieee80211_he_mcs_nss_supp *mcs_nss = &he_cap->he_mcs_nss_supp;
+
+	he_cap->has_he = true;
+	memcpy(he_cap_elem->mac_cap_info, band_cap->he_cap_info,
+	       sizeof(he_cap_elem->mac_cap_info));
+	memcpy(he_cap_elem->phy_cap_info, band_cap->he_cap_phy_info,
+	       sizeof(he_cap_elem->phy_cap_info));
+
+	he_cap_elem->mac_cap_info[1] &=
+		IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK;
+
+	he_cap_elem->phy_cap_info[5] &=
+		~IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK;
+	he_cap_elem->phy_cap_info[5] &=
+		~IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK;
+	he_cap_elem->phy_cap_info[5] |= num_tx_chains - 1;
+
+	switch (iftype) {
+	case NL80211_IFTYPE_AP:
+		he_cap_elem->phy_cap_info[3] &=
+			~IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK;
+		he_cap_elem->phy_cap_info[9] |=
+			IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU;
+		break;
+	case NL80211_IFTYPE_STATION:
+		he_cap_elem->mac_cap_info[0] &= ~IEEE80211_HE_MAC_CAP0_TWT_RES;
+		he_cap_elem->mac_cap_info[0] |= IEEE80211_HE_MAC_CAP0_TWT_REQ;
+		he_cap_elem->phy_cap_info[9] |=
+			IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU;
+		break;
+	case NL80211_IFTYPE_MESH_POINT:
+		ath12k_mac_filter_he_cap_mesh(he_cap_elem);
+		break;
+	}
+
+	mcs_nss->rx_mcs_80 = cpu_to_le16(band_cap->he_mcs & 0xffff);
+	mcs_nss->tx_mcs_80 = cpu_to_le16(band_cap->he_mcs & 0xffff);
+	mcs_nss->rx_mcs_160 = cpu_to_le16((band_cap->he_mcs >> 16) & 0xffff);
+	mcs_nss->tx_mcs_160 = cpu_to_le16((band_cap->he_mcs >> 16) & 0xffff);
+	mcs_nss->rx_mcs_80p80 = cpu_to_le16((band_cap->he_mcs >> 16) & 0xffff);
+	mcs_nss->tx_mcs_80p80 = cpu_to_le16((band_cap->he_mcs >> 16) & 0xffff);
+
+	memset(he_cap->ppe_thres, 0, sizeof(he_cap->ppe_thres));
+	if (he_cap_elem->phy_cap_info[6] &
+	    IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT)
+		ath12k_gen_ppe_thresh(&band_cap->he_ppet, he_cap->ppe_thres);
+}
+
 static int ath12k_mac_copy_sband_iftype_data(struct ath12k *ar,
 					     struct ath12k_pdev_cap *cap,
 					     struct ieee80211_sband_iftype_data *data,
 					     int band)
 {
+	struct ath12k_band_cap *band_cap = &cap->band[band];
 	int i, idx = 0;
 
 	for (i = 0; i < NUM_NL80211_IFTYPES; i++) {
 		struct ieee80211_sta_he_cap *he_cap = &data[idx].he_cap;
-		struct ath12k_band_cap *band_cap = &cap->band[band];
-		struct ieee80211_he_cap_elem *he_cap_elem =
-				&he_cap->he_cap_elem;
 
 		switch (i) {
 		case NL80211_IFTYPE_STATION:
@@ -4246,60 +4297,8 @@ static int ath12k_mac_copy_sband_iftype_data(struct ath12k *ar,
 		}
 
 		data[idx].types_mask = BIT(i);
-		he_cap->has_he = true;
-		memcpy(he_cap_elem->mac_cap_info, band_cap->he_cap_info,
-		       sizeof(he_cap_elem->mac_cap_info));
-		memcpy(he_cap_elem->phy_cap_info, band_cap->he_cap_phy_info,
-		       sizeof(he_cap_elem->phy_cap_info));
-
-		he_cap_elem->mac_cap_info[1] &=
-			IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK;
-
-		he_cap_elem->phy_cap_info[5] &=
-			~IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK;
-		he_cap_elem->phy_cap_info[5] &=
-			~IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK;
-		he_cap_elem->phy_cap_info[5] |= ar->num_tx_chains - 1;
-
-		switch (i) {
-		case NL80211_IFTYPE_AP:
-			he_cap_elem->phy_cap_info[3] &=
-				~IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK;
-			he_cap_elem->phy_cap_info[9] |=
-				IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU;
-			break;
-		case NL80211_IFTYPE_STATION:
-			he_cap_elem->mac_cap_info[0] &=
-				~IEEE80211_HE_MAC_CAP0_TWT_RES;
-			he_cap_elem->mac_cap_info[0] |=
-				IEEE80211_HE_MAC_CAP0_TWT_REQ;
-			he_cap_elem->phy_cap_info[9] |=
-				IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU;
-			break;
-		case NL80211_IFTYPE_MESH_POINT:
-			ath12k_mac_filter_he_cap_mesh(he_cap_elem);
-			break;
-		}
-
-		he_cap->he_mcs_nss_supp.rx_mcs_80 =
-			cpu_to_le16(band_cap->he_mcs & 0xffff);
-		he_cap->he_mcs_nss_supp.tx_mcs_80 =
-			cpu_to_le16(band_cap->he_mcs & 0xffff);
-		he_cap->he_mcs_nss_supp.rx_mcs_160 =
-			cpu_to_le16((band_cap->he_mcs >> 16) & 0xffff);
-		he_cap->he_mcs_nss_supp.tx_mcs_160 =
-			cpu_to_le16((band_cap->he_mcs >> 16) & 0xffff);
-		he_cap->he_mcs_nss_supp.rx_mcs_80p80 =
-			cpu_to_le16((band_cap->he_mcs >> 16) & 0xffff);
-		he_cap->he_mcs_nss_supp.tx_mcs_80p80 =
-			cpu_to_le16((band_cap->he_mcs >> 16) & 0xffff);
-
-		memset(he_cap->ppe_thres, 0, sizeof(he_cap->ppe_thres));
-		if (he_cap_elem->phy_cap_info[6] &
-		    IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT)
-			ath12k_gen_ppe_thresh(&band_cap->he_ppet,
-					      he_cap->ppe_thres);
 
+		ath12k_mac_copy_he_cap(band_cap, i, ar->num_tx_chains, he_cap);
 		if (band == NL80211_BAND_6GHZ) {
 			data[idx].he_6ghz_capa.capa =
 				ath12k_mac_setup_he_6ghz_cap(cap, band_cap);
-- 
GitLab


From 1476014fadb6625c6720c4439ff0c4b5b5431137 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:02 +0300
Subject: [PATCH 0828/1806] wifi: ath12k: WMI support to process EHT
 capabilities

Add WMI support to process the EHT capabilities passed by
the firmware. Add required EHT specific definitions in
structures ath12k_band_cap and ath12k_wmi_svc_rdy_ext_parse.

For single_pdev chip such as WCN7850, only one pdev is created
and only one hardware is registered to mac80211. This one pdev
manages both 2.4 GHz radio and 5 GHz/6 GHz radio.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Co-developed-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Co-developed-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-4-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.h |  33 ++++++
 drivers/net/wireless/ath/ath12k/wmi.c  | 147 +++++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h  |  38 +++++++
 3 files changed, 218 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 2f93296db792a..d0b625fea6336 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -580,6 +580,14 @@ struct ath12k_band_cap {
 	u32 he_cap_phy_info[PSOC_HOST_MAX_PHY_SIZE];
 	struct ath12k_wmi_ppe_threshold_arg he_ppet;
 	u16 he_6ghz_capa;
+	u32 eht_cap_mac_info[WMI_MAX_EHTCAP_MAC_SIZE];
+	u32 eht_cap_phy_info[WMI_MAX_EHTCAP_PHY_SIZE];
+	u32 eht_mcs_20_only;
+	u32 eht_mcs_80;
+	u32 eht_mcs_160;
+	u32 eht_mcs_320;
+	struct ath12k_wmi_ppe_threshold_arg eht_ppet;
+	u32 eht_cap_info_internal;
 };
 
 struct ath12k_pdev_cap {
@@ -614,6 +622,12 @@ struct ath12k_pdev {
 	struct mlo_timestamp timestamp;
 };
 
+struct ath12k_fw_pdev {
+	u32 pdev_id;
+	u32 phy_id;
+	u32 supported_bands;
+};
+
 struct ath12k_board_data {
 	const struct firmware *fw;
 	const void *data;
@@ -669,7 +683,26 @@ struct ath12k_base {
 	struct mutex core_lock;
 	/* Protects data like peers */
 	spinlock_t base_lock;
+
+	/* Single pdev device (struct ath12k_hw_params::single_pdev_only):
+	 *
+	 * Firmware maintains data for all bands but advertises a single
+	 * phy to the host which is stored as a single element in this
+	 * array.
+	 *
+	 * Other devices:
+	 *
+	 * This array will contain as many elements as the number of
+	 * radios.
+	 */
 	struct ath12k_pdev pdevs[MAX_RADIOS];
+
+	/* struct ath12k_hw_params::single_pdev_only devices use this to
+	 * store phy specific data
+	 */
+	struct ath12k_fw_pdev fw_pdev[MAX_RADIOS];
+	u8 fw_pdev_count;
+
 	struct ath12k_pdev __rcu *pdevs_active[MAX_RADIOS];
 	struct ath12k_wmi_hal_reg_capabilities_ext_arg hal_reg_cap[MAX_RADIOS];
 	unsigned long long free_vdev_map;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index e6033ab158255..63e6c08c767c8 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -65,6 +65,8 @@ struct ath12k_wmi_svc_rdy_ext_parse {
 struct ath12k_wmi_svc_rdy_ext2_parse {
 	struct ath12k_wmi_dma_ring_caps_parse dma_caps_parse;
 	bool dma_ring_cap_done;
+	bool spectral_bin_scaling_done;
+	bool mac_phy_caps_ext_done;
 };
 
 struct ath12k_wmi_rdy_parse {
@@ -445,8 +447,10 @@ ath12k_pull_mac_phy_cap_svc_ready_ext(struct ath12k_wmi_pdev *wmi_handle,
 	const struct ath12k_wmi_soc_mac_phy_hw_mode_caps_params *hw_caps = svc->hw_caps;
 	const struct ath12k_wmi_hw_mode_cap_params *wmi_hw_mode_caps = svc->hw_mode_caps;
 	const struct ath12k_wmi_mac_phy_caps_params *wmi_mac_phy_caps = svc->mac_phy_caps;
+	struct ath12k_base *ab = wmi_handle->wmi_ab->ab;
 	struct ath12k_band_cap *cap_band;
 	struct ath12k_pdev_cap *pdev_cap = &pdev->cap;
+	struct ath12k_fw_pdev *fw_pdev;
 	u32 phy_map;
 	u32 hw_idx, phy_idx = 0;
 	int i;
@@ -475,6 +479,12 @@ ath12k_pull_mac_phy_cap_svc_ready_ext(struct ath12k_wmi_pdev *wmi_handle,
 	pdev_cap->supported_bands |= le32_to_cpu(mac_caps->supported_bands);
 	pdev_cap->ampdu_density = le32_to_cpu(mac_caps->ampdu_density);
 
+	fw_pdev = &ab->fw_pdev[ab->fw_pdev_count];
+	fw_pdev->supported_bands = le32_to_cpu(mac_caps->supported_bands);
+	fw_pdev->pdev_id = le32_to_cpu(mac_caps->pdev_id);
+	fw_pdev->phy_id = le32_to_cpu(mac_caps->phy_id);
+	ab->fw_pdev_count++;
+
 	/* Take non-zero tx/rx chainmask. If tx/rx chainmask differs from
 	 * band to band for a single radio, need to see how this should be
 	 * handled.
@@ -3815,6 +3825,7 @@ static int ath12k_wmi_ext_soc_hal_reg_caps_parse(struct ath12k_base *soc,
 
 	soc->num_radios = 0;
 	phy_id_map = le32_to_cpu(svc_rdy_ext->pref_hw_mode_caps.phy_id_map);
+	soc->fw_pdev_count = 0;
 
 	while (phy_id_map && soc->num_radios < MAX_RADIOS) {
 		ret = ath12k_pull_mac_phy_cap_svc_ready_ext(wmi_handle,
@@ -4042,6 +4053,125 @@ err:
 	return ret;
 }
 
+static void ath12k_wmi_eht_caps_parse(struct ath12k_pdev *pdev, u32 band,
+				      const __le32 cap_mac_info[],
+				      const __le32 cap_phy_info[],
+				      const __le32 supp_mcs[],
+				      const struct ath12k_wmi_ppe_threshold_params *ppet,
+				       __le32 cap_info_internal)
+{
+	struct ath12k_band_cap *cap_band = &pdev->cap.band[band];
+	u8 i;
+
+	for (i = 0; i < WMI_MAX_EHTCAP_MAC_SIZE; i++)
+		cap_band->eht_cap_mac_info[i] = le32_to_cpu(cap_mac_info[i]);
+
+	for (i = 0; i < WMI_MAX_EHTCAP_PHY_SIZE; i++)
+		cap_band->eht_cap_phy_info[i] = le32_to_cpu(cap_phy_info[i]);
+
+	cap_band->eht_mcs_20_only = le32_to_cpu(supp_mcs[0]);
+	cap_band->eht_mcs_80 = le32_to_cpu(supp_mcs[1]);
+	if (band != NL80211_BAND_2GHZ) {
+		cap_band->eht_mcs_160 = le32_to_cpu(supp_mcs[2]);
+		cap_band->eht_mcs_320 = le32_to_cpu(supp_mcs[3]);
+	}
+
+	cap_band->eht_ppet.numss_m1 = le32_to_cpu(ppet->numss_m1);
+	cap_band->eht_ppet.ru_bit_mask = le32_to_cpu(ppet->ru_info);
+	for (i = 0; i < WMI_MAX_NUM_SS; i++)
+		cap_band->eht_ppet.ppet16_ppet8_ru3_ru0[i] =
+			le32_to_cpu(ppet->ppet16_ppet8_ru3_ru0[i]);
+
+	cap_band->eht_cap_info_internal = le32_to_cpu(cap_info_internal);
+}
+
+static int
+ath12k_wmi_tlv_mac_phy_caps_ext_parse(struct ath12k_base *ab,
+				      const struct ath12k_wmi_caps_ext_params *caps,
+				      struct ath12k_pdev *pdev)
+{
+	u32 bands;
+	int i;
+
+	if (ab->hw_params->single_pdev_only) {
+		for (i = 0; i < ab->fw_pdev_count; i++) {
+			struct ath12k_fw_pdev *fw_pdev = &ab->fw_pdev[i];
+
+			if (fw_pdev->pdev_id == le32_to_cpu(caps->pdev_id) &&
+			    fw_pdev->phy_id == le32_to_cpu(caps->phy_id)) {
+				bands = fw_pdev->supported_bands;
+				break;
+			}
+		}
+
+		if (i == ab->fw_pdev_count)
+			return -EINVAL;
+	} else {
+		bands = pdev->cap.supported_bands;
+	}
+
+	if (bands & WMI_HOST_WLAN_2G_CAP) {
+		ath12k_wmi_eht_caps_parse(pdev, NL80211_BAND_2GHZ,
+					  caps->eht_cap_mac_info_2ghz,
+					  caps->eht_cap_phy_info_2ghz,
+					  caps->eht_supp_mcs_ext_2ghz,
+					  &caps->eht_ppet_2ghz,
+					  caps->eht_cap_info_internal);
+	}
+
+	if (bands & WMI_HOST_WLAN_5G_CAP) {
+		ath12k_wmi_eht_caps_parse(pdev, NL80211_BAND_5GHZ,
+					  caps->eht_cap_mac_info_5ghz,
+					  caps->eht_cap_phy_info_5ghz,
+					  caps->eht_supp_mcs_ext_5ghz,
+					  &caps->eht_ppet_5ghz,
+					  caps->eht_cap_info_internal);
+
+		ath12k_wmi_eht_caps_parse(pdev, NL80211_BAND_6GHZ,
+					  caps->eht_cap_mac_info_5ghz,
+					  caps->eht_cap_phy_info_5ghz,
+					  caps->eht_supp_mcs_ext_5ghz,
+					  &caps->eht_ppet_5ghz,
+					  caps->eht_cap_info_internal);
+	}
+
+	return 0;
+}
+
+static int ath12k_wmi_tlv_mac_phy_caps_ext(struct ath12k_base *ab, u16 tag,
+					   u16 len, const void *ptr,
+					   void *data)
+{
+	const struct ath12k_wmi_caps_ext_params *caps = ptr;
+	int i = 0, ret;
+
+	if (tag != WMI_TAG_MAC_PHY_CAPABILITIES_EXT)
+		return -EPROTO;
+
+	if (ab->hw_params->single_pdev_only) {
+		if (ab->wmi_ab.preferred_hw_mode != le32_to_cpu(caps->hw_mode_id))
+			return 0;
+	} else {
+		for (i = 0; i < ab->num_radios; i++) {
+			if (ab->pdevs[i].pdev_id == le32_to_cpu(caps->pdev_id))
+				break;
+		}
+
+		if (i == ab->num_radios)
+			return -EINVAL;
+	}
+
+	ret = ath12k_wmi_tlv_mac_phy_caps_ext_parse(ab, caps, &ab->pdevs[i]);
+	if (ret) {
+		ath12k_warn(ab,
+			    "failed to parse extended MAC PHY capabilities for pdev %d: %d\n",
+			    ret, ab->pdevs[i].pdev_id);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int ath12k_wmi_svc_rdy_ext2_parse(struct ath12k_base *ab,
 					 u16 tag, u16 len,
 					 const void *ptr, void *data)
@@ -4058,6 +4188,23 @@ static int ath12k_wmi_svc_rdy_ext2_parse(struct ath12k_base *ab,
 				return ret;
 
 			parse->dma_ring_cap_done = true;
+		} else if (!parse->spectral_bin_scaling_done) {
+			/* TODO: This is a place-holder as WMI tag for
+			 * spectral scaling is before
+			 * WMI_TAG_MAC_PHY_CAPABILITIES_EXT
+			 */
+			parse->spectral_bin_scaling_done = true;
+		} else if (!parse->mac_phy_caps_ext_done) {
+			ret = ath12k_wmi_tlv_iter(ab, ptr, len,
+						  ath12k_wmi_tlv_mac_phy_caps_ext,
+						  parse);
+			if (ret) {
+				ath12k_warn(ab, "failed to parse extended MAC PHY capabilities WMI TLV: %d\n",
+					    ret);
+				return ret;
+			}
+
+			parse->mac_phy_caps_ext_done = true;
 		}
 		break;
 	default:
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 9b8ba87049047..bafcaa7f16294 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2581,6 +2581,44 @@ struct ath12k_wmi_soc_hal_reg_caps_params {
 	__le32 num_phy;
 } __packed;
 
+#define WMI_MAX_EHTCAP_MAC_SIZE  2
+#define WMI_MAX_EHTCAP_PHY_SIZE  3
+
+/* Used for EHT MCS-NSS array. Data at each array index follows the format given
+ * in IEEE P802.11be/D2.0, May 20229.4.2.313.4.
+ *
+ * Index interpretation:
+ * 0 - 20 MHz only sta, all 4 bytes valid
+ * 1 - index for bandwidths <= 80 MHz except 20 MHz-only, first 3 bytes valid
+ * 2 - index for 160 MHz, first 3 bytes valid
+ * 3 - index for 320 MHz, first 3 bytes valid
+ */
+#define WMI_MAX_EHT_SUPP_MCS_2G_SIZE  2
+#define WMI_MAX_EHT_SUPP_MCS_5G_SIZE  4
+
+struct ath12k_wmi_caps_ext_params {
+	__le32 hw_mode_id;
+	union {
+		struct {
+			__le16 pdev_id;
+			__le16 hw_link_id;
+		} __packed ath12k_wmi_pdev_to_link_map;
+		__le32 pdev_id;
+	};
+	__le32 phy_id;
+	__le32 wireless_modes_ext;
+	__le32 eht_cap_mac_info_2ghz[WMI_MAX_EHTCAP_MAC_SIZE];
+	__le32 eht_cap_mac_info_5ghz[WMI_MAX_EHTCAP_MAC_SIZE];
+	__le32 rsvd0[2];
+	__le32 eht_cap_phy_info_2ghz[WMI_MAX_EHTCAP_PHY_SIZE];
+	__le32 eht_cap_phy_info_5ghz[WMI_MAX_EHTCAP_PHY_SIZE];
+	struct ath12k_wmi_ppe_threshold_params eht_ppet_2ghz;
+	struct ath12k_wmi_ppe_threshold_params eht_ppet_5ghz;
+	__le32 eht_cap_info_internal;
+	__le32 eht_supp_mcs_ext_2ghz[WMI_MAX_EHT_SUPP_MCS_2G_SIZE];
+	__le32 eht_supp_mcs_ext_5ghz[WMI_MAX_EHT_SUPP_MCS_5G_SIZE];
+} __packed;
+
 /* 2 word representation of MAC addr */
 struct ath12k_wmi_mac_addr_params {
 	u8 addr[ETH_ALEN];
-- 
GitLab


From dbe90679bfa1287651b8bb8304b7ce46b00a5f81 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:02 +0300
Subject: [PATCH 0829/1806] wifi: ath12k: propagate EHT capabilities to
 userspace

Propagate EHT capabilities to the userspace using a new member
'eht_cap' in structure ieee80211_sband_iftype_data.

MCS-NSS capabilities are copied depending on the supported bandwidths
for the given band.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Signed-off-by: Pradeep Kumar Chitrapu<quic_pradeepc@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-5-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 111 ++++++++++++++++++++++++++
 1 file changed, 111 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 8fedbf4879d6d..c64cd8079e20c 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -4275,6 +4275,115 @@ static void ath12k_mac_copy_he_cap(struct ath12k_band_cap *band_cap,
 		ath12k_gen_ppe_thresh(&band_cap->he_ppet, he_cap->ppe_thres);
 }
 
+static void
+ath12k_mac_copy_eht_mcs_nss(struct ath12k_band_cap *band_cap,
+			    struct ieee80211_eht_mcs_nss_supp *mcs_nss,
+			    const struct ieee80211_he_cap_elem *he_cap,
+			    const struct ieee80211_eht_cap_elem_fixed *eht_cap)
+{
+	if ((he_cap->phy_cap_info[0] &
+	     (IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G |
+	      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
+	      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G |
+	      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)) == 0)
+		memcpy(&mcs_nss->only_20mhz, &band_cap->eht_mcs_20_only,
+		       sizeof(struct ieee80211_eht_mcs_nss_supp_20mhz_only));
+
+	if (he_cap->phy_cap_info[0] &
+	    (IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G |
+	     IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G))
+		memcpy(&mcs_nss->bw._80, &band_cap->eht_mcs_80,
+		       sizeof(struct ieee80211_eht_mcs_nss_supp_bw));
+
+	if (he_cap->phy_cap_info[0] &
+	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G)
+		memcpy(&mcs_nss->bw._160, &band_cap->eht_mcs_160,
+		       sizeof(struct ieee80211_eht_mcs_nss_supp_bw));
+
+	if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ)
+		memcpy(&mcs_nss->bw._320, &band_cap->eht_mcs_320,
+		       sizeof(struct ieee80211_eht_mcs_nss_supp_bw));
+}
+
+static void ath12k_mac_copy_eht_ppe_thresh(struct ath12k_wmi_ppe_threshold_arg *fw_ppet,
+					   struct ieee80211_sta_eht_cap *cap)
+{
+	u16 bit = IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE;
+	u8 i, nss, ru, ppet_bit_len_per_ru = IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2;
+
+	u8p_replace_bits(&cap->eht_ppe_thres[0], fw_ppet->numss_m1,
+			 IEEE80211_EHT_PPE_THRES_NSS_MASK);
+
+	u16p_replace_bits((u16 *)&cap->eht_ppe_thres[0], fw_ppet->ru_bit_mask,
+			  IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK);
+
+	for (nss = 0; nss <= fw_ppet->numss_m1; nss++) {
+		for (ru = 0;
+		     ru < hweight16(IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK);
+		     ru++) {
+			u32 val = 0;
+
+			if ((fw_ppet->ru_bit_mask & BIT(ru)) == 0)
+				continue;
+
+			u32p_replace_bits(&val, fw_ppet->ppet16_ppet8_ru3_ru0[nss] >>
+						(ru * ppet_bit_len_per_ru),
+					  GENMASK(ppet_bit_len_per_ru - 1, 0));
+
+			for (i = 0; i < ppet_bit_len_per_ru; i++) {
+				cap->eht_ppe_thres[bit / 8] |=
+					(((val >> i) & 0x1) << ((bit % 8)));
+				bit++;
+			}
+		}
+	}
+}
+
+static void ath12k_mac_copy_eht_cap(struct ath12k_band_cap *band_cap,
+				    struct ieee80211_he_cap_elem *he_cap_elem,
+				    int iftype,
+				    struct ieee80211_sta_eht_cap *eht_cap)
+{
+	struct ieee80211_eht_cap_elem_fixed *eht_cap_elem = &eht_cap->eht_cap_elem;
+
+	memset(eht_cap, 0, sizeof(struct ieee80211_sta_eht_cap));
+	eht_cap->has_eht = true;
+	memcpy(eht_cap_elem->mac_cap_info, band_cap->eht_cap_mac_info,
+	       sizeof(eht_cap_elem->mac_cap_info));
+	memcpy(eht_cap_elem->phy_cap_info, band_cap->eht_cap_phy_info,
+	       sizeof(eht_cap_elem->phy_cap_info));
+
+	switch (iftype) {
+	case NL80211_IFTYPE_AP:
+		eht_cap_elem->phy_cap_info[0] &=
+			~IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ;
+		eht_cap_elem->phy_cap_info[4] &=
+			~IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO;
+		eht_cap_elem->phy_cap_info[5] &=
+			~IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP;
+		break;
+	case NL80211_IFTYPE_STATION:
+		eht_cap_elem->phy_cap_info[7] &=
+			~(IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ |
+			  IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ |
+			  IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ);
+		eht_cap_elem->phy_cap_info[7] &=
+			~(IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ |
+			  IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ |
+			  IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ);
+		break;
+	default:
+		break;
+	}
+
+	ath12k_mac_copy_eht_mcs_nss(band_cap, &eht_cap->eht_mcs_nss_supp,
+				    he_cap_elem, eht_cap_elem);
+
+	if (eht_cap_elem->phy_cap_info[5] &
+	    IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT)
+		ath12k_mac_copy_eht_ppe_thresh(&band_cap->eht_ppet, eht_cap);
+}
+
 static int ath12k_mac_copy_sband_iftype_data(struct ath12k *ar,
 					     struct ath12k_pdev_cap *cap,
 					     struct ieee80211_sband_iftype_data *data,
@@ -4303,6 +4412,8 @@ static int ath12k_mac_copy_sband_iftype_data(struct ath12k *ar,
 			data[idx].he_6ghz_capa.capa =
 				ath12k_mac_setup_he_6ghz_cap(cap, band_cap);
 		}
+		ath12k_mac_copy_eht_cap(band_cap, &he_cap->he_cap_elem, i,
+					&data[idx].eht_cap);
 		idx++;
 	}
 
-- 
GitLab


From 38013653a69734e2bcf84ce951f7a4aee3966320 Mon Sep 17 00:00:00 2001
From: Muna Sinada <quic_msinada@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:03 +0300
Subject: [PATCH 0830/1806] wifi: ath12k: add EHT PHY modes

Add support to retrieve and configure the phy modes supported
by the hardware.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Muna Sinada <quic_msinada@quicinc.com>
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-6-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 101 +++++++++++++++++++++-----
 drivers/net/wireless/ath/ath12k/mac.h |   2 +-
 drivers/net/wireless/ath/ath12k/wmi.h |  13 +++-
 3 files changed, 94 insertions(+), 22 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index c64cd8079e20c..8ea1ac5ab356c 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -182,32 +182,35 @@ ath12k_phymodes[NUM_NL80211_BANDS][ATH12K_CHAN_WIDTH_NUM] = {
 	[NL80211_BAND_2GHZ] = {
 			[NL80211_CHAN_WIDTH_5] = MODE_UNKNOWN,
 			[NL80211_CHAN_WIDTH_10] = MODE_UNKNOWN,
-			[NL80211_CHAN_WIDTH_20_NOHT] = MODE_11AX_HE20_2G,
-			[NL80211_CHAN_WIDTH_20] = MODE_11AX_HE20_2G,
-			[NL80211_CHAN_WIDTH_40] = MODE_11AX_HE40_2G,
-			[NL80211_CHAN_WIDTH_80] = MODE_11AX_HE80_2G,
+			[NL80211_CHAN_WIDTH_20_NOHT] = MODE_11BE_EHT20_2G,
+			[NL80211_CHAN_WIDTH_20] = MODE_11BE_EHT20_2G,
+			[NL80211_CHAN_WIDTH_40] = MODE_11BE_EHT40_2G,
+			[NL80211_CHAN_WIDTH_80] = MODE_UNKNOWN,
 			[NL80211_CHAN_WIDTH_80P80] = MODE_UNKNOWN,
 			[NL80211_CHAN_WIDTH_160] = MODE_UNKNOWN,
+			[NL80211_CHAN_WIDTH_320] = MODE_UNKNOWN,
 	},
 	[NL80211_BAND_5GHZ] = {
 			[NL80211_CHAN_WIDTH_5] = MODE_UNKNOWN,
 			[NL80211_CHAN_WIDTH_10] = MODE_UNKNOWN,
-			[NL80211_CHAN_WIDTH_20_NOHT] = MODE_11AX_HE20,
-			[NL80211_CHAN_WIDTH_20] = MODE_11AX_HE20,
-			[NL80211_CHAN_WIDTH_40] = MODE_11AX_HE40,
-			[NL80211_CHAN_WIDTH_80] = MODE_11AX_HE80,
-			[NL80211_CHAN_WIDTH_160] = MODE_11AX_HE160,
-			[NL80211_CHAN_WIDTH_80P80] = MODE_11AX_HE80_80,
+			[NL80211_CHAN_WIDTH_20_NOHT] = MODE_11BE_EHT20,
+			[NL80211_CHAN_WIDTH_20] = MODE_11BE_EHT20,
+			[NL80211_CHAN_WIDTH_40] = MODE_11BE_EHT40,
+			[NL80211_CHAN_WIDTH_80] = MODE_11BE_EHT80,
+			[NL80211_CHAN_WIDTH_160] = MODE_11BE_EHT160,
+			[NL80211_CHAN_WIDTH_80P80] = MODE_11BE_EHT80_80,
+			[NL80211_CHAN_WIDTH_320] = MODE_11BE_EHT320,
 	},
 	[NL80211_BAND_6GHZ] = {
 			[NL80211_CHAN_WIDTH_5] = MODE_UNKNOWN,
 			[NL80211_CHAN_WIDTH_10] = MODE_UNKNOWN,
-			[NL80211_CHAN_WIDTH_20_NOHT] = MODE_11AX_HE20,
-			[NL80211_CHAN_WIDTH_20] = MODE_11AX_HE20,
-			[NL80211_CHAN_WIDTH_40] = MODE_11AX_HE40,
-			[NL80211_CHAN_WIDTH_80] = MODE_11AX_HE80,
-			[NL80211_CHAN_WIDTH_160] = MODE_11AX_HE160,
-			[NL80211_CHAN_WIDTH_80P80] = MODE_11AX_HE80_80,
+			[NL80211_CHAN_WIDTH_20_NOHT] = MODE_11BE_EHT20,
+			[NL80211_CHAN_WIDTH_20] = MODE_11BE_EHT20,
+			[NL80211_CHAN_WIDTH_40] = MODE_11BE_EHT40,
+			[NL80211_CHAN_WIDTH_80] = MODE_11BE_EHT80,
+			[NL80211_CHAN_WIDTH_160] = MODE_11BE_EHT160,
+			[NL80211_CHAN_WIDTH_80P80] = MODE_11BE_EHT80_80,
+			[NL80211_CHAN_WIDTH_320] = MODE_11BE_EHT320,
 	},
 
 };
@@ -292,6 +295,24 @@ static const char *ath12k_mac_phymode_str(enum wmi_phy_mode mode)
 		return "11ax-he40-2g";
 	case MODE_11AX_HE80_2G:
 		return "11ax-he80-2g";
+	case MODE_11BE_EHT20:
+		return "11be-eht20";
+	case MODE_11BE_EHT40:
+		return "11be-eht40";
+	case MODE_11BE_EHT80:
+		return "11be-eht80";
+	case MODE_11BE_EHT80_80:
+		return "11be-eht80+80";
+	case MODE_11BE_EHT160:
+		return "11be-eht160";
+	case MODE_11BE_EHT160_160:
+		return "11be-eht160+160";
+	case MODE_11BE_EHT320:
+		return "11be-eht320";
+	case MODE_11BE_EHT20_2G:
+		return "11be-eht20-2g";
+	case MODE_11BE_EHT40_2G:
+		return "11be-eht40-2g";
 	case MODE_UNKNOWN:
 		/* skip */
 		break;
@@ -1929,6 +1950,41 @@ static enum wmi_phy_mode ath12k_mac_get_phymode_he(struct ath12k *ar,
 	return MODE_UNKNOWN;
 }
 
+static enum wmi_phy_mode ath12k_mac_get_phymode_eht(struct ath12k *ar,
+						    struct ieee80211_sta *sta)
+{
+	if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_320)
+		if (sta->deflink.eht_cap.eht_cap_elem.phy_cap_info[0] &
+		    IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ)
+			return MODE_11BE_EHT320;
+
+	if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160) {
+		if (sta->deflink.he_cap.he_cap_elem.phy_cap_info[0] &
+		    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G)
+			return MODE_11BE_EHT160;
+
+		if (sta->deflink.he_cap.he_cap_elem.phy_cap_info[0] &
+			 IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)
+			return MODE_11BE_EHT80_80;
+
+		ath12k_warn(ar->ab, "invalid EHT PHY capability info for 160 Mhz: %d\n",
+			    sta->deflink.he_cap.he_cap_elem.phy_cap_info[0]);
+
+		return MODE_11BE_EHT160;
+	}
+
+	if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_80)
+		return MODE_11BE_EHT80;
+
+	if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40)
+		return MODE_11BE_EHT40;
+
+	if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_20)
+		return MODE_11BE_EHT20;
+
+	return MODE_UNKNOWN;
+}
+
 static void ath12k_peer_assoc_h_phymode(struct ath12k *ar,
 					struct ieee80211_vif *vif,
 					struct ieee80211_sta *sta,
@@ -1950,7 +2006,12 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar,
 
 	switch (band) {
 	case NL80211_BAND_2GHZ:
-		if (sta->deflink.he_cap.has_he) {
+		if (sta->deflink.eht_cap.has_eht) {
+			if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40)
+				phymode = MODE_11BE_EHT40_2G;
+			else
+				phymode = MODE_11BE_EHT20_2G;
+		} else if (sta->deflink.he_cap.has_he) {
 			if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_80)
 				phymode = MODE_11AX_HE80_2G;
 			else if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40)
@@ -1977,8 +2038,10 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar,
 		break;
 	case NL80211_BAND_5GHZ:
 	case NL80211_BAND_6GHZ:
-		/* Check HE first */
-		if (sta->deflink.he_cap.has_he) {
+		/* Check EHT first */
+		if (sta->deflink.eht_cap.has_eht) {
+			phymode = ath12k_mac_get_phymode_eht(ar, sta);
+		} else if (sta->deflink.he_cap.has_he) {
 			phymode = ath12k_mac_get_phymode_he(ar, sta);
 		} else if (sta->deflink.vht_cap.vht_supported &&
 		    !ath12k_peer_assoc_h_vht_masked(vht_mcs_mask)) {
diff --git a/drivers/net/wireless/ath/ath12k/mac.h b/drivers/net/wireless/ath/ath12k/mac.h
index 57f4295420bb8..7b16b70df4fa8 100644
--- a/drivers/net/wireless/ath/ath12k/mac.h
+++ b/drivers/net/wireless/ath/ath12k/mac.h
@@ -33,7 +33,7 @@ struct ath12k_generic_iter {
 #define IEEE80211_VHT_MCS_SUPPORT_0_11_MASK	GENMASK(23, 16)
 #define IEEE80211_DISABLE_VHT_MCS_SUPPORT_0_11	BIT(24)
 
-#define ATH12K_CHAN_WIDTH_NUM			8
+#define ATH12K_CHAN_WIDTH_NUM			14
 
 #define ATH12K_TX_POWER_MAX_VAL	70
 #define ATH12K_TX_POWER_MIN_VAL	0
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index bafcaa7f16294..0aa73908a65ff 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2796,8 +2796,17 @@ enum wmi_phy_mode {
 	MODE_11AX_HE20_2G = 21,
 	MODE_11AX_HE40_2G = 22,
 	MODE_11AX_HE80_2G = 23,
-	MODE_UNKNOWN = 24,
-	MODE_MAX = 24
+	MODE_11BE_EHT20 = 24,
+	MODE_11BE_EHT40 = 25,
+	MODE_11BE_EHT80 = 26,
+	MODE_11BE_EHT80_80 = 27,
+	MODE_11BE_EHT160 = 28,
+	MODE_11BE_EHT160_160 = 29,
+	MODE_11BE_EHT320 = 30,
+	MODE_11BE_EHT20_2G = 31,
+	MODE_11BE_EHT40_2G = 32,
+	MODE_UNKNOWN = 33,
+	MODE_MAX = 33,
 };
 
 struct wmi_vdev_start_req_arg {
-- 
GitLab


From 17bbb8aa74fded03527427c25f43a29590c6a9ab Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:04 +0300
Subject: [PATCH 0831/1806] wifi: ath12k: prepare EHT peer assoc parameters

Add new parameters and prepare the association data for an EHT peer.
MCS data uses the format described in IEEE P802.11be/D2.0, May 2022,
9.4.2.313.4, convert it into the format expected by the firmware.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-7-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 144 ++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h |  17 +++
 2 files changed, 161 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 8ea1ac5ab356c..5b7a892e1f79a 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -2067,6 +2067,149 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar,
 	WARN_ON(phymode == MODE_UNKNOWN);
 }
 
+static void ath12k_mac_set_eht_mcs(u8 rx_tx_mcs7, u8 rx_tx_mcs9,
+				   u8 rx_tx_mcs11, u8 rx_tx_mcs13,
+				   u32 *rx_mcs, u32 *tx_mcs)
+{
+	*rx_mcs = 0;
+	u32p_replace_bits(rx_mcs,
+			  u8_get_bits(rx_tx_mcs7, IEEE80211_EHT_MCS_NSS_RX),
+			  WMI_EHT_MCS_NSS_0_7);
+	u32p_replace_bits(rx_mcs,
+			  u8_get_bits(rx_tx_mcs9, IEEE80211_EHT_MCS_NSS_RX),
+			  WMI_EHT_MCS_NSS_8_9);
+	u32p_replace_bits(rx_mcs,
+			  u8_get_bits(rx_tx_mcs11, IEEE80211_EHT_MCS_NSS_RX),
+			  WMI_EHT_MCS_NSS_10_11);
+	u32p_replace_bits(rx_mcs,
+			  u8_get_bits(rx_tx_mcs13, IEEE80211_EHT_MCS_NSS_RX),
+			  WMI_EHT_MCS_NSS_12_13);
+
+	*tx_mcs = 0;
+	u32p_replace_bits(tx_mcs,
+			  u8_get_bits(rx_tx_mcs7, IEEE80211_EHT_MCS_NSS_TX),
+			  WMI_EHT_MCS_NSS_0_7);
+	u32p_replace_bits(tx_mcs,
+			  u8_get_bits(rx_tx_mcs9, IEEE80211_EHT_MCS_NSS_TX),
+			  WMI_EHT_MCS_NSS_8_9);
+	u32p_replace_bits(tx_mcs,
+			  u8_get_bits(rx_tx_mcs11, IEEE80211_EHT_MCS_NSS_TX),
+			  WMI_EHT_MCS_NSS_10_11);
+	u32p_replace_bits(tx_mcs,
+			  u8_get_bits(rx_tx_mcs13, IEEE80211_EHT_MCS_NSS_TX),
+			  WMI_EHT_MCS_NSS_12_13);
+}
+
+static void ath12k_mac_set_eht_ppe_threshold(const u8 *ppe_thres,
+					     struct ath12k_wmi_ppe_threshold_arg *ppet)
+{
+	u32 bit_pos = IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE, val;
+	u8 nss, ru, i;
+	u8 ppet_bit_len_per_ru = IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2;
+
+	ppet->numss_m1 = u8_get_bits(ppe_thres[0], IEEE80211_EHT_PPE_THRES_NSS_MASK);
+	ppet->ru_bit_mask = u16_get_bits(get_unaligned_le16(ppe_thres),
+					 IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK);
+
+	for (nss = 0; nss <= ppet->numss_m1; nss++) {
+		for (ru = 0;
+		     ru < hweight16(IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK);
+		     ru++) {
+			if ((ppet->ru_bit_mask & BIT(ru)) == 0)
+				continue;
+
+			val = 0;
+			for (i = 0; i < ppet_bit_len_per_ru; i++) {
+				val |= (((ppe_thres[bit_pos / 8] >>
+					  (bit_pos % 8)) & 0x1) << i);
+				bit_pos++;
+			}
+			ppet->ppet16_ppet8_ru3_ru0[nss] |=
+					(val << (ru * ppet_bit_len_per_ru));
+		}
+	}
+}
+
+static void ath12k_peer_assoc_h_eht(struct ath12k *ar,
+				    struct ieee80211_vif *vif,
+				    struct ieee80211_sta *sta,
+				    struct ath12k_wmi_peer_assoc_arg *arg)
+{
+	const struct ieee80211_sta_eht_cap *eht_cap = &sta->deflink.eht_cap;
+	const struct ieee80211_sta_he_cap *he_cap = &sta->deflink.he_cap;
+	const struct ieee80211_eht_mcs_nss_supp_20mhz_only *bw_20;
+	const struct ieee80211_eht_mcs_nss_supp_bw *bw;
+	u32 *rx_mcs, *tx_mcs;
+
+	if (!sta->deflink.he_cap.has_he || !eht_cap->has_eht)
+		return;
+
+	arg->eht_flag = true;
+
+	if ((eht_cap->eht_cap_elem.phy_cap_info[5] &
+	     IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) &&
+	    eht_cap->eht_ppe_thres[0] != 0)
+		ath12k_mac_set_eht_ppe_threshold(eht_cap->eht_ppe_thres,
+						 &arg->peer_eht_ppet);
+
+	memcpy(arg->peer_eht_cap_mac, eht_cap->eht_cap_elem.mac_cap_info,
+	       sizeof(eht_cap->eht_cap_elem.mac_cap_info));
+	memcpy(arg->peer_eht_cap_phy, eht_cap->eht_cap_elem.phy_cap_info,
+	       sizeof(eht_cap->eht_cap_elem.phy_cap_info));
+
+	rx_mcs = arg->peer_eht_rx_mcs_set;
+	tx_mcs = arg->peer_eht_tx_mcs_set;
+
+	switch (sta->deflink.bandwidth) {
+	case IEEE80211_STA_RX_BW_320:
+		bw = &eht_cap->eht_mcs_nss_supp.bw._320;
+		ath12k_mac_set_eht_mcs(bw->rx_tx_mcs9_max_nss,
+				       bw->rx_tx_mcs9_max_nss,
+				       bw->rx_tx_mcs11_max_nss,
+				       bw->rx_tx_mcs13_max_nss,
+				       &rx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_320],
+				       &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_320]);
+		arg->peer_eht_mcs_count++;
+		fallthrough;
+	case IEEE80211_STA_RX_BW_160:
+		bw = &eht_cap->eht_mcs_nss_supp.bw._160;
+		ath12k_mac_set_eht_mcs(bw->rx_tx_mcs9_max_nss,
+				       bw->rx_tx_mcs9_max_nss,
+				       bw->rx_tx_mcs11_max_nss,
+				       bw->rx_tx_mcs13_max_nss,
+				       &rx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_160],
+				       &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_160]);
+		arg->peer_eht_mcs_count++;
+		fallthrough;
+	default:
+		if ((he_cap->he_cap_elem.phy_cap_info[0] &
+		     (IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G |
+		      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
+		      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G |
+		      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)) == 0) {
+			bw_20 = &eht_cap->eht_mcs_nss_supp.only_20mhz;
+
+			ath12k_mac_set_eht_mcs(bw_20->rx_tx_mcs7_max_nss,
+					       bw_20->rx_tx_mcs9_max_nss,
+					       bw_20->rx_tx_mcs11_max_nss,
+					       bw_20->rx_tx_mcs13_max_nss,
+					       &rx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_80],
+					       &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_80]);
+		} else {
+			bw = &eht_cap->eht_mcs_nss_supp.bw._80;
+			ath12k_mac_set_eht_mcs(bw->rx_tx_mcs9_max_nss,
+					       bw->rx_tx_mcs9_max_nss,
+					       bw->rx_tx_mcs11_max_nss,
+					       bw->rx_tx_mcs13_max_nss,
+					       &rx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_80],
+					       &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_80]);
+		}
+
+		arg->peer_eht_mcs_count++;
+		break;
+	}
+}
+
 static void ath12k_peer_assoc_prepare(struct ath12k *ar,
 				      struct ieee80211_vif *vif,
 				      struct ieee80211_sta *sta,
@@ -2086,6 +2229,7 @@ static void ath12k_peer_assoc_prepare(struct ath12k *ar,
 	ath12k_peer_assoc_h_ht(ar, vif, sta, arg);
 	ath12k_peer_assoc_h_vht(ar, vif, sta, arg);
 	ath12k_peer_assoc_h_he(ar, vif, sta, arg);
+	ath12k_peer_assoc_h_eht(ar, vif, sta, arg);
 	ath12k_peer_assoc_h_qos(ar, vif, sta, arg);
 	ath12k_peer_assoc_h_phymode(ar, vif, sta, arg);
 	ath12k_peer_assoc_h_smps(sta, arg);
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 0aa73908a65ff..dae895b479c79 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2583,6 +2583,7 @@ struct ath12k_wmi_soc_hal_reg_caps_params {
 
 #define WMI_MAX_EHTCAP_MAC_SIZE  2
 #define WMI_MAX_EHTCAP_PHY_SIZE  3
+#define WMI_MAX_EHTCAP_RATE_SET  3
 
 /* Used for EHT MCS-NSS array. Data at each array index follows the format given
  * in IEEE P802.11be/D2.0, May 20229.4.2.313.4.
@@ -2596,6 +2597,15 @@ struct ath12k_wmi_soc_hal_reg_caps_params {
 #define WMI_MAX_EHT_SUPP_MCS_2G_SIZE  2
 #define WMI_MAX_EHT_SUPP_MCS_5G_SIZE  4
 
+#define WMI_EHTCAP_TXRX_MCS_NSS_IDX_80    0
+#define WMI_EHTCAP_TXRX_MCS_NSS_IDX_160   1
+#define WMI_EHTCAP_TXRX_MCS_NSS_IDX_320   2
+
+#define WMI_EHT_MCS_NSS_0_7    GENMASK(3, 0)
+#define WMI_EHT_MCS_NSS_8_9    GENMASK(7, 4)
+#define WMI_EHT_MCS_NSS_10_11  GENMASK(11, 8)
+#define WMI_EHT_MCS_NSS_12_13  GENMASK(15, 12)
+
 struct ath12k_wmi_caps_ext_params {
 	__le32 hw_mode_id;
 	union {
@@ -3564,6 +3574,13 @@ struct ath12k_wmi_peer_assoc_arg {
 	bool twt_responder;
 	bool twt_requester;
 	struct ath12k_wmi_ppe_threshold_arg peer_ppet;
+	bool eht_flag;
+	u32 peer_eht_cap_mac[WMI_MAX_EHTCAP_MAC_SIZE];
+	u32 peer_eht_cap_phy[WMI_MAX_EHTCAP_PHY_SIZE];
+	u32 peer_eht_mcs_count;
+	u32 peer_eht_rx_mcs_set[WMI_MAX_EHTCAP_RATE_SET];
+	u32 peer_eht_tx_mcs_set[WMI_MAX_EHTCAP_RATE_SET];
+	struct ath12k_wmi_ppe_threshold_arg peer_eht_ppet;
 };
 
 struct wmi_peer_assoc_complete_cmd {
-- 
GitLab


From 5b70ec6036c1c755fd1c1aa80ace3d349d91f3a5 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:04 +0300
Subject: [PATCH 0832/1806] wifi: ath12k: add WMI support for EHT peer

Add new WMI tag and pass the EHT parameters for peer association
to firmware.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-8-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.c | 40 +++++++++++++++++++++++++--
 drivers/net/wireless/ath/ath12k/wmi.h | 20 ++++++++++++++
 2 files changed, 57 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 63e6c08c767c8..b1bc227ad54ed 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1801,6 +1801,7 @@ static void ath12k_wmi_copy_peer_flags(struct wmi_peer_assoc_complete_cmd *cmd,
 				       bool hw_crypto_disabled)
 {
 	cmd->peer_flags = 0;
+	cmd->peer_flags_ext = 0;
 
 	if (arg->is_wme_set) {
 		if (arg->qos_flag)
@@ -1842,6 +1843,8 @@ static void ath12k_wmi_copy_peer_flags(struct wmi_peer_assoc_complete_cmd *cmd,
 			cmd->peer_flags |= cpu_to_le32(WMI_PEER_TWT_REQ);
 		if (arg->twt_responder)
 			cmd->peer_flags |= cpu_to_le32(WMI_PEER_TWT_RESP);
+		if (arg->eht_flag)
+			cmd->peer_flags_ext |= cpu_to_le32(WMI_PEER_EXT_EHT);
 	}
 
 	/* Suppress authorization for all AUTH modes that need 4-way handshake
@@ -1886,6 +1889,7 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 	struct wmi_peer_assoc_complete_cmd *cmd;
 	struct ath12k_wmi_vht_rate_set_params *mcs;
 	struct ath12k_wmi_he_rate_set_params *he_mcs;
+	struct ath12k_wmi_eht_rate_set_params *eht_mcs;
 	struct sk_buff *skb;
 	struct wmi_tlv *tlv;
 	void *ptr;
@@ -1902,7 +1906,8 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 	      TLV_HDR_SIZE + (peer_legacy_rates_align * sizeof(u8)) +
 	      TLV_HDR_SIZE + (peer_ht_rates_align * sizeof(u8)) +
 	      sizeof(*mcs) + TLV_HDR_SIZE +
-	      (sizeof(*he_mcs) * arg->peer_he_mcs_count);
+	      (sizeof(*he_mcs) * arg->peer_he_mcs_count) +
+	      TLV_HDR_SIZE + (sizeof(*eht_mcs) * arg->peer_eht_mcs_count);
 
 	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len);
 	if (!skb)
@@ -1949,6 +1954,16 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 		cmd->peer_ppet.ppet16_ppet8_ru3_ru0[i] =
 			cpu_to_le32(arg->peer_ppet.ppet16_ppet8_ru3_ru0[i]);
 
+	/* Update 11be capabilities */
+	memcpy_and_pad(cmd->peer_eht_cap_mac, sizeof(cmd->peer_eht_cap_mac),
+		       arg->peer_eht_cap_mac, sizeof(arg->peer_eht_cap_mac),
+		       0);
+	memcpy_and_pad(cmd->peer_eht_cap_phy, sizeof(cmd->peer_eht_cap_phy),
+		       arg->peer_eht_cap_phy, sizeof(arg->peer_eht_cap_phy),
+		       0);
+	memcpy_and_pad(&cmd->peer_eht_ppet, sizeof(cmd->peer_eht_ppet),
+		       &arg->peer_eht_ppet, sizeof(arg->peer_eht_ppet), 0);
+
 	/* Update peer legacy rate information */
 	ptr += sizeof(*cmd);
 
@@ -2015,8 +2030,24 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 		ptr += sizeof(*he_mcs);
 	}
 
+	/* Loop through the EHT rate set */
+	len = arg->peer_eht_mcs_count * sizeof(*eht_mcs);
+	tlv = ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT, len);
+	ptr += TLV_HDR_SIZE;
+
+	for (i = 0; i < arg->peer_eht_mcs_count; i++) {
+		eht_mcs = ptr;
+		eht_mcs->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_HE_RATE_SET,
+							     sizeof(*eht_mcs));
+
+		eht_mcs->rx_mcs_set = cpu_to_le32(arg->peer_eht_rx_mcs_set[i]);
+		eht_mcs->tx_mcs_set = cpu_to_le32(arg->peer_eht_tx_mcs_set[i]);
+		ptr += sizeof(*eht_mcs);
+	}
+
 	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
-		   "wmi peer assoc vdev id %d assoc id %d peer mac %pM peer_flags %x rate_caps %x peer_caps %x listen_intval %d ht_caps %x max_mpdu %d nss %d phymode %d peer_mpdu_density %d vht_caps %x he cap_info %x he ops %x he cap_info_ext %x he phy %x %x %x peer_bw_rxnss_override %x\n",
+		   "wmi peer assoc vdev id %d assoc id %d peer mac %pM peer_flags %x rate_caps %x peer_caps %x listen_intval %d ht_caps %x max_mpdu %d nss %d phymode %d peer_mpdu_density %d vht_caps %x he cap_info %x he ops %x he cap_info_ext %x he phy %x %x %x peer_bw_rxnss_override %x peer_flags_ext %x eht mac_cap %x %x eht phy_cap %x %x %x\n",
 		   cmd->vdev_id, cmd->peer_associd, arg->peer_mac,
 		   cmd->peer_flags, cmd->peer_rate_caps, cmd->peer_caps,
 		   cmd->peer_listen_intval, cmd->peer_ht_caps,
@@ -2026,7 +2057,10 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 		   cmd->peer_he_ops, cmd->peer_he_cap_info_ext,
 		   cmd->peer_he_cap_phy[0], cmd->peer_he_cap_phy[1],
 		   cmd->peer_he_cap_phy[2],
-		   cmd->peer_bw_rxnss_override);
+		   cmd->peer_bw_rxnss_override, cmd->peer_flags_ext,
+		   cmd->peer_eht_cap_mac[0], cmd->peer_eht_cap_mac[1],
+		   cmd->peer_eht_cap_phy[0], cmd->peer_eht_cap_phy[1],
+		   cmd->peer_eht_cap_phy[2]);
 
 	ret = ath12k_wmi_cmd_send(wmi, skb, WMI_PEER_ASSOC_CMDID);
 	if (ret) {
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index dae895b479c79..5e8c4a23c6ba0 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -1167,6 +1167,10 @@ enum wmi_tlv_peer_flags {
 
 };
 
+enum wmi_tlv_peer_flags_ext {
+	WMI_PEER_EXT_EHT = BIT(0),
+};
+
 /** Enum list of TLV Tags for each parameter structure type. */
 enum wmi_tlv_tag {
 	WMI_TAG_LAST_RESERVED = 15,
@@ -1924,6 +1928,7 @@ enum wmi_tlv_tag {
 	WMI_TAG_MAC_PHY_CAPABILITIES_EXT = 0x36F,
 	WMI_TAG_REGULATORY_RULE_EXT_STRUCT = 0x3A9,
 	WMI_TAG_REG_CHAN_LIST_CC_EXT_EVENT,
+	WMI_TAG_EHT_RATE_SET = 0x3C4,
 	WMI_TAG_MAX
 };
 
@@ -3612,6 +3617,15 @@ struct wmi_peer_assoc_complete_cmd {
 	__le32 peer_he_cap_info_internal;
 	__le32 min_data_rate;
 	__le32 peer_he_caps_6ghz;
+	__le32 sta_type;
+	__le32 bss_max_idle_option;
+	__le32 auth_mode;
+	__le32 peer_flags_ext;
+	__le32 puncture_20mhz_bitmap;
+	__le32 peer_eht_cap_mac[WMI_MAX_EHTCAP_MAC_SIZE];
+	__le32 peer_eht_cap_phy[WMI_MAX_EHTCAP_PHY_SIZE];
+	__le32 peer_eht_ops;
+	struct ath12k_wmi_ppe_threshold_params peer_eht_ppet;
 } __packed;
 
 struct wmi_stop_scan_cmd {
@@ -3839,6 +3853,12 @@ struct ath12k_wmi_he_rate_set_params {
 	__le32 tx_mcs_set;
 } __packed;
 
+struct ath12k_wmi_eht_rate_set_params {
+	__le32 tlv_header;
+	__le32 rx_mcs_set;
+	__le32 tx_mcs_set;
+} __packed;
+
 #define MAX_REG_RULES 10
 #define REG_ALPHA2_LEN 2
 #define MAX_6G_REG_RULES 5
-- 
GitLab


From 6734cf9b4cc7ae017ec1e9ab44a8ba0d8c512d5d Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:05 +0300
Subject: [PATCH 0833/1806] wifi: ath12k: peer assoc for 320 MHz

Add required peer association definitions and processing if the
bandwidth is 320 MHz.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Signed-off-by: Pradeep Kumar Chitrapu<quic_pradeepc@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-9-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.c | 2 ++
 drivers/net/wireless/ath/ath12k/wmi.h | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index b1bc227ad54ed..6e9b7c5fb0289 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1816,6 +1816,8 @@ static void ath12k_wmi_copy_peer_flags(struct wmi_peer_assoc_complete_cmd *cmd,
 			cmd->peer_flags |= cpu_to_le32(WMI_PEER_80MHZ);
 		if (arg->bw_160)
 			cmd->peer_flags |= cpu_to_le32(WMI_PEER_160MHZ);
+		if (arg->bw_320)
+			cmd->peer_flags |= cpu_to_le32(WMI_PEER_EXT_320MHZ);
 
 		/* Typically if STBC is enabled for VHT it should be enabled
 		 * for HT as well
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 5e8c4a23c6ba0..93a70426df287 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -1169,6 +1169,7 @@ enum wmi_tlv_peer_flags {
 
 enum wmi_tlv_peer_flags_ext {
 	WMI_PEER_EXT_EHT = BIT(0),
+	WMI_PEER_EXT_320MHZ = BIT(1),
 };
 
 /** Enum list of TLV Tags for each parameter structure type. */
@@ -3552,6 +3553,7 @@ struct ath12k_wmi_peer_assoc_arg {
 	bool bw_40;
 	bool bw_80;
 	bool bw_160;
+	bool bw_320;
 	bool stbc_flag;
 	bool ldpc_flag;
 	bool static_mimops_flag;
-- 
GitLab


From 22e1d1166c27ed9099f1312cd2043a480b1bda14 Mon Sep 17 00:00:00 2001
From: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:06 +0300
Subject: [PATCH 0834/1806] wifi: ath12k: add MLO header in peer association

Add tags with length 0 for MLO header and partner links which
are required by the firmware for a successful association.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com>
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-10-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 6e9b7c5fb0289..24f6c1dbd7439 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1909,7 +1909,8 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 	      TLV_HDR_SIZE + (peer_ht_rates_align * sizeof(u8)) +
 	      sizeof(*mcs) + TLV_HDR_SIZE +
 	      (sizeof(*he_mcs) * arg->peer_he_mcs_count) +
-	      TLV_HDR_SIZE + (sizeof(*eht_mcs) * arg->peer_eht_mcs_count);
+	      TLV_HDR_SIZE + (sizeof(*eht_mcs) * arg->peer_eht_mcs_count) +
+	      TLV_HDR_SIZE + TLV_HDR_SIZE;
 
 	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len);
 	if (!skb)
@@ -2032,6 +2033,12 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 		ptr += sizeof(*he_mcs);
 	}
 
+	/* MLO header tag with 0 length */
+	len = 0;
+	tlv = ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT, len);
+	ptr += TLV_HDR_SIZE;
+
 	/* Loop through the EHT rate set */
 	len = arg->peer_eht_mcs_count * sizeof(*eht_mcs);
 	tlv = ptr;
@@ -2048,6 +2055,12 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 		ptr += sizeof(*eht_mcs);
 	}
 
+	/* ML partner links tag with 0 length */
+	len = 0;
+	tlv = ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT, len);
+	ptr += TLV_HDR_SIZE;
+
 	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
 		   "wmi peer assoc vdev id %d assoc id %d peer mac %pM peer_flags %x rate_caps %x peer_caps %x listen_intval %d ht_caps %x max_mpdu %d nss %d phymode %d peer_mpdu_density %d vht_caps %x he cap_info %x he ops %x he cap_info_ext %x he phy %x %x %x peer_bw_rxnss_override %x peer_flags_ext %x eht mac_cap %x %x eht phy_cap %x %x %x\n",
 		   cmd->vdev_id, cmd->peer_associd, arg->peer_mac,
-- 
GitLab


From 9211df5c025a5e50de8b8cb0798c1120f8593d8a Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:06 +0300
Subject: [PATCH 0835/1806] wifi: ath12k: parse WMI service ready ext2 event

Parse WMI service ready ext2 event.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-11-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.c | 48 +++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h | 16 +++++++++
 2 files changed, 64 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 24f6c1dbd7439..35f65b7e23920 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -62,7 +62,23 @@ struct ath12k_wmi_svc_rdy_ext_parse {
 	bool dma_ring_cap_done;
 };
 
+struct ath12k_wmi_svc_rdy_ext2_arg {
+	u32 reg_db_version;
+	u32 hw_min_max_tx_power_2ghz;
+	u32 hw_min_max_tx_power_5ghz;
+	u32 chwidth_num_peer_caps;
+	u32 preamble_puncture_bw;
+	u32 max_user_per_ppdu_ofdma;
+	u32 max_user_per_ppdu_mumimo;
+	u32 target_cap_flags;
+	u32 eht_cap_mac_info[WMI_MAX_EHTCAP_MAC_SIZE];
+	u32 max_num_linkview_peers;
+	u32 max_num_msduq_supported_per_tid;
+	u32 default_num_msduq_supported_per_tid;
+};
+
 struct ath12k_wmi_svc_rdy_ext2_parse {
+	struct ath12k_wmi_svc_rdy_ext2_arg arg;
 	struct ath12k_wmi_dma_ring_caps_parse dma_caps_parse;
 	bool dma_ring_cap_done;
 	bool spectral_bin_scaling_done;
@@ -4102,6 +4118,26 @@ err:
 	return ret;
 }
 
+static int ath12k_pull_svc_ready_ext2(struct ath12k_wmi_pdev *wmi_handle,
+				      const void *ptr,
+				      struct ath12k_wmi_svc_rdy_ext2_arg *arg)
+{
+	const struct wmi_service_ready_ext2_event *ev = ptr;
+
+	if (!ev)
+		return -EINVAL;
+
+	arg->reg_db_version = le32_to_cpu(ev->reg_db_version);
+	arg->hw_min_max_tx_power_2ghz = le32_to_cpu(ev->hw_min_max_tx_power_2ghz);
+	arg->hw_min_max_tx_power_5ghz = le32_to_cpu(ev->hw_min_max_tx_power_5ghz);
+	arg->chwidth_num_peer_caps = le32_to_cpu(ev->chwidth_num_peer_caps);
+	arg->preamble_puncture_bw = le32_to_cpu(ev->preamble_puncture_bw);
+	arg->max_user_per_ppdu_ofdma = le32_to_cpu(ev->max_user_per_ppdu_ofdma);
+	arg->max_user_per_ppdu_mumimo = le32_to_cpu(ev->max_user_per_ppdu_mumimo);
+	arg->target_cap_flags = le32_to_cpu(ev->target_cap_flags);
+	return 0;
+}
+
 static void ath12k_wmi_eht_caps_parse(struct ath12k_pdev *pdev, u32 band,
 				      const __le32 cap_mac_info[],
 				      const __le32 cap_phy_info[],
@@ -4225,10 +4261,22 @@ static int ath12k_wmi_svc_rdy_ext2_parse(struct ath12k_base *ab,
 					 u16 tag, u16 len,
 					 const void *ptr, void *data)
 {
+	struct ath12k_wmi_pdev *wmi_handle = &ab->wmi_ab.wmi[0];
 	struct ath12k_wmi_svc_rdy_ext2_parse *parse = data;
 	int ret;
 
 	switch (tag) {
+	case WMI_TAG_SERVICE_READY_EXT2_EVENT:
+		ret = ath12k_pull_svc_ready_ext2(wmi_handle, ptr,
+						 &parse->arg);
+		if (ret) {
+			ath12k_warn(ab,
+				    "failed to extract wmi service ready ext2 parameters: %d\n",
+				    ret);
+			return ret;
+		}
+		break;
+
 	case WMI_TAG_ARRAY_STRUCT:
 		if (!parse->dma_ring_cap_done) {
 			ret = ath12k_wmi_dma_ring_caps(ab, len, ptr,
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 93a70426df287..fdb79124ad9d3 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -1925,6 +1925,7 @@ enum wmi_tlv_tag {
 	/* TODO add all the missing cmds */
 	WMI_TAG_PDEV_PEER_PKTLOG_FILTER_CMD = 0x301,
 	WMI_TAG_PDEV_PEER_PKTLOG_FILTER_INFO,
+	WMI_TAG_SERVICE_READY_EXT2_EVENT = 0x334,
 	WMI_TAG_FILS_DISCOVERY_TMPL_CMD = 0x344,
 	WMI_TAG_MAC_PHY_CAPABILITIES_EXT = 0x36F,
 	WMI_TAG_REGULATORY_RULE_EXT_STRUCT = 0x3A9,
@@ -2612,6 +2613,21 @@ struct ath12k_wmi_soc_hal_reg_caps_params {
 #define WMI_EHT_MCS_NSS_10_11  GENMASK(11, 8)
 #define WMI_EHT_MCS_NSS_12_13  GENMASK(15, 12)
 
+struct wmi_service_ready_ext2_event {
+	__le32 reg_db_version;
+	__le32 hw_min_max_tx_power_2ghz;
+	__le32 hw_min_max_tx_power_5ghz;
+	__le32 chwidth_num_peer_caps;
+	__le32 preamble_puncture_bw;
+	__le32 max_user_per_ppdu_ofdma;
+	__le32 max_user_per_ppdu_mumimo;
+	__le32 target_cap_flags;
+	__le32 eht_cap_mac_info[WMI_MAX_EHTCAP_MAC_SIZE];
+	__le32 max_num_linkview_peers;
+	__le32 max_num_msduq_supported_per_tid;
+	__le32 default_num_msduq_supported_per_tid;
+} __packed;
+
 struct ath12k_wmi_caps_ext_params {
 	__le32 hw_mode_id;
 	union {
-- 
GitLab


From 07c01b86f21dd499bd487b70c1536f868fede241 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 2 Aug 2023 20:04:07 +0300
Subject: [PATCH 0836/1806] wifi: ath12k: configure puncturing bitmap

Enable the feature flag to indicate the driver support for
preamble puncturing. Firmware will support this feature
by default from IEEE 802.11be onwards.
Configure the bitmap as part of VDEV start/restart and
peer association commands.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Signed-off-by: Muna Sinada <quic_msinada@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230725224034.14045-12-quic_alokad@quicinc.com
---
 drivers/net/wireless/ath/ath12k/core.h |  1 +
 drivers/net/wireless/ath/ath12k/mac.c  | 16 ++++++++++++++--
 drivers/net/wireless/ath/ath12k/wmi.c  |  2 ++
 drivers/net/wireless/ath/ath12k/wmi.h  | 12 +++++++++++-
 4 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index d0b625fea6336..4389ff40b49db 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -238,6 +238,7 @@ struct ath12k_vif {
 	u32 key_cipher;
 	u8 tx_encap_type;
 	u8 vdev_stats_id;
+	u32 punct_bitmap;
 };
 
 struct ath12k_vif_iter {
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 5b7a892e1f79a..48cf3f10a3bcd 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -842,6 +842,7 @@ static int ath12k_mac_monitor_vdev_start(struct ath12k *ar, int vdev_id,
 
 	arg.pref_tx_streams = ar->num_tx_chains;
 	arg.pref_rx_streams = ar->num_rx_chains;
+	arg.punct_bitmap = 0xFFFFFFFF;
 
 	arg.passive |= !!(chandef->chan->flags & IEEE80211_CHAN_NO_IR);
 
@@ -2139,6 +2140,7 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar,
 	const struct ieee80211_sta_he_cap *he_cap = &sta->deflink.he_cap;
 	const struct ieee80211_eht_mcs_nss_supp_20mhz_only *bw_20;
 	const struct ieee80211_eht_mcs_nss_supp_bw *bw;
+	struct ath12k_vif *arvif = (struct ath12k_vif *)vif->drv_priv;
 	u32 *rx_mcs, *tx_mcs;
 
 	if (!sta->deflink.he_cap.has_he || !eht_cap->has_eht)
@@ -2208,6 +2210,8 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar,
 		arg->peer_eht_mcs_count++;
 		break;
 	}
+
+	arg->punct_bitmap = ~arvif->punct_bitmap;
 }
 
 static void ath12k_peer_assoc_prepare(struct ath12k *ar,
@@ -2761,6 +2765,9 @@ static void ath12k_mac_op_bss_info_changed(struct ieee80211_hw *hw,
 	    changed & BSS_CHANGED_UNSOL_BCAST_PROBE_RESP)
 		ath12k_mac_fils_discovery(arvif, info);
 
+	if (changed & BSS_CHANGED_EHT_PUNCTURING)
+		arvif->punct_bitmap = info->eht_puncturing;
+
 	mutex_unlock(&ar->conf_mutex);
 }
 
@@ -5800,6 +5807,7 @@ ath12k_mac_vdev_start_restart(struct ath12k_vif *arvif,
 	arg.vdev_id = arvif->vdev_id;
 	arg.dtim_period = arvif->dtim_period;
 	arg.bcn_intval = arvif->beacon_interval;
+	arg.punct_bitmap = ~arvif->punct_bitmap;
 
 	arg.freq = chandef->chan->center_freq;
 	arg.band_center_freq1 = chandef->center_freq1;
@@ -5842,9 +5850,9 @@ ath12k_mac_vdev_start_restart(struct ath12k_vif *arvif,
 	arg.passive |= !!(chandef->chan->flags & IEEE80211_CHAN_NO_IR);
 
 	ath12k_dbg(ab, ATH12K_DBG_MAC,
-		   "mac vdev %d start center_freq %d phymode %s\n",
+		   "mac vdev %d start center_freq %d phymode %s punct_bitmap 0x%x\n",
 		   arg.vdev_id, arg.freq,
-		   ath12k_mac_phymode_str(arg.mode));
+		   ath12k_mac_phymode_str(arg.mode), arg.punct_bitmap);
 
 	ret = ath12k_wmi_vdev_start(ar, &arg, restart);
 	if (ret) {
@@ -6171,6 +6179,8 @@ ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 		   "mac chanctx assign ptr %pK vdev_id %i\n",
 		   ctx, arvif->vdev_id);
 
+	arvif->punct_bitmap = link_conf->eht_puncturing;
+
 	/* for some targets bss peer must be created before vdev_start */
 	if (ab->hw_params->vdev_start_delay &&
 	    arvif->vdev_type != WMI_VDEV_TYPE_AP &&
@@ -7298,6 +7308,8 @@ static int __ath12k_mac_register(struct ath12k *ar)
 				      NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP);
 	}
 
+	wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_PUNCT);
+
 	ath12k_reg_init(ar);
 
 	if (!test_bit(ATH12K_FLAG_RAW_MODE, &ab->dev_flags)) {
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 35f65b7e23920..c611a19c73645 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1021,6 +1021,7 @@ int ath12k_wmi_vdev_start(struct ath12k *ar, struct wmi_vdev_start_req_arg *arg,
 	cmd->cac_duration_ms = cpu_to_le32(arg->cac_duration_ms);
 	cmd->regdomain = cpu_to_le32(arg->regdomain);
 	cmd->he_ops = cpu_to_le32(arg->he_ops);
+	cmd->punct_bitmap = cpu_to_le32(arg->punct_bitmap);
 
 	if (!restart) {
 		if (arg->ssid) {
@@ -1942,6 +1943,7 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 
 	cmd->peer_new_assoc = cpu_to_le32(arg->peer_new_assoc);
 	cmd->peer_associd = cpu_to_le32(arg->peer_associd);
+	cmd->punct_bitmap = cpu_to_le32(arg->punct_bitmap);
 
 	ath12k_wmi_copy_peer_flags(cmd, arg,
 				   test_bit(ATH12K_FLAG_HW_CRYPTO_DISABLED,
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index fdb79124ad9d3..8c047a9623f9b 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2775,6 +2775,11 @@ struct wmi_vdev_start_request_cmd {
 	__le32 he_ops;
 	__le32 cac_duration_ms;
 	__le32 regdomain;
+	__le32 min_data_rate;
+	__le32 mbssid_flags;
+	__le32 mbssid_tx_vdev_id;
+	__le32 eht_ops;
+	__le32 punct_bitmap;
 } __packed;
 
 #define MGMT_TX_DL_FRM_LEN		     64
@@ -2874,6 +2879,10 @@ struct wmi_vdev_start_req_arg {
 	u32 pref_rx_streams;
 	u32 pref_tx_streams;
 	u32 num_noa_descriptors;
+	u32 min_data_rate;
+	u32 mbssid_flags;
+	u32 mbssid_tx_vdev_id;
+	u32 punct_bitmap;
 };
 
 struct ath12k_wmi_peer_create_arg {
@@ -3604,6 +3613,7 @@ struct ath12k_wmi_peer_assoc_arg {
 	u32 peer_eht_rx_mcs_set[WMI_MAX_EHTCAP_RATE_SET];
 	u32 peer_eht_tx_mcs_set[WMI_MAX_EHTCAP_RATE_SET];
 	struct ath12k_wmi_ppe_threshold_arg peer_eht_ppet;
+	u32 punct_bitmap;
 };
 
 struct wmi_peer_assoc_complete_cmd {
@@ -3639,7 +3649,7 @@ struct wmi_peer_assoc_complete_cmd {
 	__le32 bss_max_idle_option;
 	__le32 auth_mode;
 	__le32 peer_flags_ext;
-	__le32 puncture_20mhz_bitmap;
+	__le32 punct_bitmap;
 	__le32 peer_eht_cap_mac[WMI_MAX_EHTCAP_MAC_SIZE];
 	__le32 peer_eht_cap_phy[WMI_MAX_EHTCAP_PHY_SIZE];
 	__le32 peer_eht_ops;
-- 
GitLab


From 89a9dda1430a71fe95ad2b4f8056e7aa15b4aee7 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 2 Aug 2023 20:04:09 +0300
Subject: [PATCH 0837/1806] wifi: ath12k: relax list iteration in
 ath12k_mac_vif_unref()

In ath12k_mac_vif_unref() dp->tx_desc_used_list[i]
is not altered so list_for_each_entry() should be safe.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230704173718.73462-1-dmantipov@yandex.ru
---
 drivers/net/wireless/ath/ath12k/mac.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 48cf3f10a3bcd..0f2af2f14ef76 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -5542,7 +5542,7 @@ err:
 
 static void ath12k_mac_vif_unref(struct ath12k_dp *dp, struct ieee80211_vif *vif)
 {
-	struct ath12k_tx_desc_info *tx_desc_info, *tmp1;
+	struct ath12k_tx_desc_info *tx_desc_info;
 	struct ath12k_skb_cb *skb_cb;
 	struct sk_buff *skb;
 	int i;
@@ -5550,8 +5550,8 @@ static void ath12k_mac_vif_unref(struct ath12k_dp *dp, struct ieee80211_vif *vif
 	for (i = 0; i < ATH12K_HW_MAX_QUEUES; i++) {
 		spin_lock_bh(&dp->tx_desc_lock[i]);
 
-		list_for_each_entry_safe(tx_desc_info, tmp1, &dp->tx_desc_used_list[i],
-					 list) {
+		list_for_each_entry(tx_desc_info, &dp->tx_desc_used_list[i],
+				    list) {
 			skb = tx_desc_info->skb;
 			if (!skb)
 				continue;
-- 
GitLab


From 9632ea57be659887ab0d28a2a1d7b901dfddd263 Mon Sep 17 00:00:00 2001
From: Wen Gong <quic_wgong@quicinc.com>
Date: Sun, 16 Jul 2023 23:44:57 -0400
Subject: [PATCH 0838/1806] wifi: ath12k: add handler for scan event
 WMI_SCAN_EVENT_DEQUEUED

When wlan interface is up, and 11d scan is sent to the firmware, then
firmware needs to spend couple of seconds to complete the 11d scan. If
normal scan from user space arrives to ath12k at this moment, then the
normal scan request is also sent to the firmware, but the scan started
event will be reported to ath12k until the 11d scan complete. When timed
out for the scan started in ath12k, ath12k stops the normal scan and the
firmware reports WMI_SCAN_EVENT_DEQUEUED to ath12k for the normal scan.
ath12k has no handler for the event and then timed out for the scan
completed in ath12k_scan_stop(), and ath12k prints the following error
message.

[ 1491.604750] ath12k_pci 0000:02:00.0: failed to receive scan abort comple: timed out
[ 1491.604756] ath12k_pci 0000:02:00.0: failed to stop scan: -110
[ 1491.604758] ath12k_pci 0000:02:00.0: failed to start hw scan: -110

Add a handler for WMI_SCAN_EVENT_DEQUEUED and then complete the scan to
get rid of the above error message.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230717034457.22162-1-quic_wgong@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index c611a19c73645..fab4d33c89843 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -5948,6 +5948,8 @@ static void ath12k_scan_event(struct ath12k_base *ab, struct sk_buff *skb)
 		ath12k_wmi_event_scan_start_failed(ar);
 		break;
 	case WMI_SCAN_EVENT_DEQUEUED:
+		__ath12k_mac_scan_finish(ar);
+		break;
 	case WMI_SCAN_EVENT_PREEMPTED:
 	case WMI_SCAN_EVENT_RESTARTED:
 	case WMI_SCAN_EVENT_FOREIGN_CHAN_EXIT:
-- 
GitLab


From 8198950ccb7d311f8b4389441d8dcb597f926340 Mon Sep 17 00:00:00 2001
From: Wen Gong <quic_wgong@quicinc.com>
Date: Mon, 17 Jul 2023 22:47:24 -0400
Subject: [PATCH 0839/1806] wifi: ath12k: avoid deadlock by change
 ieee80211_queue_work for regd_update_work

Deadlock is easily happened while shutdown wlan interface such as run
"ifconfig wlan0 down".

The reason is because when ar->regd_update_work is ran, it will
call wiphy_lock(ar->hw->wiphy) in function ath12k_regd_update() which
is running in workqueue of ieee80211_local queued by ieee80211_queue_work().
Another thread from "ifconfig wlan0 down" will also accuqire the lock
by wiphy_lock(sdata->local->hw.wiphy) in function ieee80211_stop(), and
then it call ieee80211_stop_device() to flush_workqueue(local->workqueue),
this will wait the workqueue of ieee80211_local finished. Then deadlock
will happen easily if the two thread run meanwhile.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230718024724.29120-1-quic_wgong@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index fab4d33c89843..9ed33e2d6da02 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -5473,7 +5473,7 @@ static int ath12k_reg_chan_list_event(struct ath12k_base *ab, struct sk_buff *sk
 		ar = ab->pdevs[pdev_idx].ar;
 		kfree(ab->new_regd[pdev_idx]);
 		ab->new_regd[pdev_idx] = regd;
-		ieee80211_queue_work(ar->hw, &ar->regd_update_work);
+		queue_work(ab->workqueue, &ar->regd_update_work);
 	} else {
 		/* Multiple events for the same *ar is not expected. But we
 		 * can still clear any previously stored default_regd if we
-- 
GitLab


From 571e9c4968875a78495eccfa26901083d0e6f833 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Wed, 2 Aug 2023 04:31:09 +0100
Subject: [PATCH 0840/1806] net: ethernet: mtk_eth_soc: support per-flow
 accounting on MT7988

NETSYS_V3 uses 64 bits for each counters while older SoCs are using
48/40 bits for each counter.
Support reading per-flow byte and package counters on NETSYS_V3.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/37a0928fa8c1253b197884c68ce1f54239421ac5.1690946442.git.daniel@makrotopia.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c  |  1 +
 drivers/net/ethernet/mediatek/mtk_ppe.c      | 21 +++++++++++++-------
 drivers/net/ethernet/mediatek/mtk_ppe_regs.h |  2 ++
 3 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 05be702f19c5e..1b89f800f6dff 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -5064,6 +5064,7 @@ static const struct mtk_soc_data mt7988_data = {
 	.version = 3,
 	.offload_version = 2,
 	.hash_offset = 4,
+	.has_accounting = true,
 	.foe_entry_size = MTK_FOE_ENTRY_V3_SIZE,
 	.txrx = {
 		.txd_size = sizeof(struct mtk_tx_dma_v2),
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c
index bf1ecb0c1c109..86f32f4860437 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.c
@@ -92,7 +92,6 @@ static int mtk_ppe_mib_wait_busy(struct mtk_ppe *ppe)
 
 static int mtk_mib_entry_read(struct mtk_ppe *ppe, u16 index, u64 *bytes, u64 *packets)
 {
-	u32 byte_cnt_low, byte_cnt_high, pkt_cnt_low, pkt_cnt_high;
 	u32 val, cnt_r0, cnt_r1, cnt_r2;
 	int ret;
 
@@ -107,12 +106,20 @@ static int mtk_mib_entry_read(struct mtk_ppe *ppe, u16 index, u64 *bytes, u64 *p
 	cnt_r1 = readl(ppe->base + MTK_PPE_MIB_SER_R1);
 	cnt_r2 = readl(ppe->base + MTK_PPE_MIB_SER_R2);
 
-	byte_cnt_low = FIELD_GET(MTK_PPE_MIB_SER_R0_BYTE_CNT_LOW, cnt_r0);
-	byte_cnt_high = FIELD_GET(MTK_PPE_MIB_SER_R1_BYTE_CNT_HIGH, cnt_r1);
-	pkt_cnt_low = FIELD_GET(MTK_PPE_MIB_SER_R1_PKT_CNT_LOW, cnt_r1);
-	pkt_cnt_high = FIELD_GET(MTK_PPE_MIB_SER_R2_PKT_CNT_HIGH, cnt_r2);
-	*bytes = ((u64)byte_cnt_high << 32) | byte_cnt_low;
-	*packets = (pkt_cnt_high << 16) | pkt_cnt_low;
+	if (mtk_is_netsys_v3_or_greater(ppe->eth)) {
+		/* 64 bit for each counter */
+		u32 cnt_r3 = readl(ppe->base + MTK_PPE_MIB_SER_R3);
+		*bytes = ((u64)cnt_r1 << 32) | cnt_r0;
+		*packets = ((u64)cnt_r3 << 32) | cnt_r2;
+	} else {
+		/* 48 bit byte counter, 40 bit packet counter */
+		u32 byte_cnt_low = FIELD_GET(MTK_PPE_MIB_SER_R0_BYTE_CNT_LOW, cnt_r0);
+		u32 byte_cnt_high = FIELD_GET(MTK_PPE_MIB_SER_R1_BYTE_CNT_HIGH, cnt_r1);
+		u32 pkt_cnt_low = FIELD_GET(MTK_PPE_MIB_SER_R1_PKT_CNT_LOW, cnt_r1);
+		u32 pkt_cnt_high = FIELD_GET(MTK_PPE_MIB_SER_R2_PKT_CNT_HIGH, cnt_r2);
+		*bytes = ((u64)byte_cnt_high << 32) | byte_cnt_low;
+		*packets = ((u64)pkt_cnt_high << 16) | pkt_cnt_low;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_regs.h b/drivers/net/ethernet/mediatek/mtk_ppe_regs.h
index a2e61b3eb006d..3ce088eef0efd 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_regs.h
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_regs.h
@@ -163,6 +163,8 @@ enum {
 #define MTK_PPE_MIB_SER_R2			0x348
 #define MTK_PPE_MIB_SER_R2_PKT_CNT_HIGH		GENMASK(23, 0)
 
+#define MTK_PPE_MIB_SER_R3			0x34c
+
 #define MTK_PPE_MIB_CACHE_CTL			0x350
 #define MTK_PPE_MIB_CACHE_CTL_EN		BIT(0)
 #define MTK_PPE_MIB_CACHE_CTL_FLUSH		BIT(2)
-- 
GitLab


From c956910d5af1e5df0f94fddb1bdae1ecaf74b3c5 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 2 Aug 2023 11:46:59 +0800
Subject: [PATCH 0841/1806] tipc: Remove unused function declarations

Commit d50ccc2d3909 ("tipc: add 128-bit node identifier") declared but never
implemented tipc_node_id2hash().
Also commit 5c216e1d28c8 ("tipc: Allow run-time alteration of default link settings")
never implemented tipc_media_set_priority() and tipc_media_set_window(),
commit cad2929dc432 ("tipc: update a binding service via broadcast") only declared
tipc_named_bcast().

Since commit be07f056396d ("tipc: simplify the finalize work queue")
tipc_sched_net_finalize() is removed and declaration is unused.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230802034659.39840-1-yuehaibing@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/tipc/addr.h       | 1 -
 net/tipc/bearer.h     | 2 --
 net/tipc/name_distr.h | 1 -
 net/tipc/net.h        | 1 -
 4 files changed, 5 deletions(-)

diff --git a/net/tipc/addr.h b/net/tipc/addr.h
index 0772cfadaa0dc..93f82398283d8 100644
--- a/net/tipc/addr.h
+++ b/net/tipc/addr.h
@@ -131,6 +131,5 @@ bool tipc_in_scope(bool legacy_format, u32 domain, u32 addr);
 void tipc_set_node_id(struct net *net, u8 *id);
 void tipc_set_node_addr(struct net *net, u32 addr);
 char *tipc_nodeid2string(char *str, u8 *id);
-u32 tipc_node_id2hash(u8 *id128);
 
 #endif
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 1ee60649bd170..41eac1ee0c091 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -214,8 +214,6 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info);
 int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info);
 int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info);
 
-int tipc_media_set_priority(const char *name, u32 new_value);
-int tipc_media_set_window(const char *name, u32 new_value);
 int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a);
 int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
 			 struct nlattr *attrs[]);
diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h
index e231e6964d611..c677f6f082dfb 100644
--- a/net/tipc/name_distr.h
+++ b/net/tipc/name_distr.h
@@ -67,7 +67,6 @@ struct distr_item {
 	__be32 key;
 };
 
-void tipc_named_bcast(struct net *net, struct sk_buff *skb);
 struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ);
 struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ);
 void tipc_named_node_up(struct net *net, u32 dnode, u16 capabilities);
diff --git a/net/tipc/net.h b/net/tipc/net.h
index d0c91d2df20a6..1cb1e43cf34a4 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -43,7 +43,6 @@ extern const struct nla_policy tipc_nl_net_policy[];
 
 int tipc_net_init(struct net *net, u8 *node_id, u32 addr);
 void tipc_net_finalize_work(struct work_struct *work);
-void tipc_sched_net_finalize(struct net *net, u32 addr);
 void tipc_net_stop(struct net *net);
 int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);
-- 
GitLab


From 0520841960dee1e53449019d4409f0c3c03fb64f Mon Sep 17 00:00:00 2001
From: Chin-Yen Lee <timlee@realtek.com>
Date: Tue, 1 Aug 2023 10:11:20 +0800
Subject: [PATCH 0842/1806] wifi: rtw89: recognize log format from firmware
 file

Firmware log format is an element of multi-firmware file
and used for firmware to provide log with formatted text.
Driver needs to recognize it in advance if it exists.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230801021127.15919-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |  4 ++++
 drivers/net/wireless/realtek/rtw89/fw.c   | 25 +++++++++++++++--------
 2 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index f3f7abddd3c0b..695e8eb5780b0 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3548,6 +3548,7 @@ enum rtw89_fw_type {
 	RTW89_FW_NORMAL = 1,
 	RTW89_FW_WOWLAN = 3,
 	RTW89_FW_NORMAL_CE = 5,
+	RTW89_FW_LOGFMT = 255,
 };
 
 enum rtw89_fw_feature {
@@ -3607,6 +3608,7 @@ struct rtw89_fw_info {
 	u8 c2h_counter;
 	struct rtw89_fw_suit normal;
 	struct rtw89_fw_suit wowlan;
+	struct rtw89_fw_suit logfmt;
 	bool fw_log_enable;
 	u32 feature_map;
 };
@@ -5143,6 +5145,8 @@ static inline struct rtw89_fw_suit *rtw89_fw_suit_get(struct rtw89_dev *rtwdev,
 
 	if (type == RTW89_FW_WOWLAN)
 		return &fw_info->wowlan;
+	else if (type == RTW89_FW_LOGFMT)
+		return &fw_info->logfmt;
 	return &fw_info->normal;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index f8616c178de7e..f27eb09d2bab6 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -178,19 +178,22 @@ int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 
 	for (i = 0; i < mfw_hdr->fw_nr; i++) {
 		mfw_info = &mfw_hdr->info[i];
-		if (mfw_info->cv != rtwdev->hal.cv ||
-		    mfw_info->type != type ||
-		    mfw_info->mp)
-			continue;
-
-		fw_suit->data = mfw + le32_to_cpu(mfw_info->shift);
-		fw_suit->size = le32_to_cpu(mfw_info->size);
-		return 0;
+		if (mfw_info->type == type) {
+			if (mfw_info->cv == rtwdev->hal.cv && !mfw_info->mp)
+				goto found;
+			if (type == RTW89_FW_LOGFMT)
+				goto found;
+		}
 	}
 
 	if (!nowarn)
 		rtw89_err(rtwdev, "no suitable firmware found\n");
 	return -ENOENT;
+
+found:
+	fw_suit->data = mfw + le32_to_cpu(mfw_info->shift);
+	fw_suit->size = le32_to_cpu(mfw_info->size);
+	return 0;
 }
 
 static void rtw89_fw_update_ver(struct rtw89_dev *rtwdev,
@@ -199,6 +202,9 @@ static void rtw89_fw_update_ver(struct rtw89_dev *rtwdev,
 {
 	const struct rtw89_fw_hdr *hdr = (const struct rtw89_fw_hdr *)fw_suit->data;
 
+	if (type == RTW89_FW_LOGFMT)
+		return;
+
 	fw_suit->major_ver = le32_get_bits(hdr->w1, FW_HDR_W1_MAJOR_VERSION);
 	fw_suit->minor_ver = le32_get_bits(hdr->w1, FW_HDR_W1_MINOR_VERSION);
 	fw_suit->sub_ver = le32_get_bits(hdr->w1, FW_HDR_W1_SUBVERSION);
@@ -365,6 +371,9 @@ normal_done:
 	/* It still works if wowlan firmware isn't existing. */
 	__rtw89_fw_recognize(rtwdev, RTW89_FW_WOWLAN, false);
 
+	/* It still works if log format file isn't existing. */
+	__rtw89_fw_recognize(rtwdev, RTW89_FW_LOGFMT, true);
+
 	rtw89_fw_recognize_features(rtwdev);
 
 	rtw89_coex_recognize_ver(rtwdev);
-- 
GitLab


From cad2bd8a136cb1231e8b43996be7133ccf92ef48 Mon Sep 17 00:00:00 2001
From: Chin-Yen Lee <timlee@realtek.com>
Date: Tue, 1 Aug 2023 10:11:21 +0800
Subject: [PATCH 0843/1806] wifi: rtw89: support firmware log with formatted
 text

Original firmware log which is sent via C2H message bloats
code size of firmware and is also length-limited. So we put
some common log into format file, and firmware could use a
log ID and some variables in C2H message to map a formatted
text via pre-designed rule.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230801021127.15919-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c  |   2 +-
 drivers/net/wireless/realtek/rtw89/core.h  |  14 +-
 drivers/net/wireless/realtek/rtw89/debug.c |  14 +-
 drivers/net/wireless/realtek/rtw89/fw.c    | 146 ++++++++++++++++++++-
 drivers/net/wireless/realtek/rtw89/fw.h    |  31 ++++-
 drivers/net/wireless/realtek/rtw89/mac.c   |   3 +-
 6 files changed, 194 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index ec244849e5014..ecdd05b851b75 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -3508,7 +3508,7 @@ int rtw89_core_start(struct rtw89_dev *rtwdev)
 	set_bit(RTW89_FLAG_RUNNING, rtwdev->flags);
 
 	rtw89_btc_ntfy_radio_state(rtwdev, BTC_RFCTRL_WL_ON);
-	rtw89_fw_h2c_fw_log(rtwdev, rtwdev->fw.fw_log_enable);
+	rtw89_fw_h2c_fw_log(rtwdev, rtwdev->fw.log.enable);
 	rtw89_fw_h2c_init_ba_cam(rtwdev);
 
 	return 0;
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 695e8eb5780b0..f05086b27b266 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3599,6 +3599,15 @@ struct rtw89_fw_req_info {
 	struct completion completion;
 };
 
+struct rtw89_fw_log {
+	struct rtw89_fw_suit suit;
+	bool enable;
+	u32 last_fmt_id;
+	u32 fmt_count;
+	const __le32 *fmt_ids;
+	const char *(*fmts)[];
+};
+
 struct rtw89_fw_info {
 	struct rtw89_fw_req_info req;
 	int fw_format;
@@ -3608,8 +3617,7 @@ struct rtw89_fw_info {
 	u8 c2h_counter;
 	struct rtw89_fw_suit normal;
 	struct rtw89_fw_suit wowlan;
-	struct rtw89_fw_suit logfmt;
-	bool fw_log_enable;
+	struct rtw89_fw_log log;
 	u32 feature_map;
 };
 
@@ -5146,7 +5154,7 @@ static inline struct rtw89_fw_suit *rtw89_fw_suit_get(struct rtw89_dev *rtwdev,
 	if (type == RTW89_FW_WOWLAN)
 		return &fw_info->wowlan;
 	else if (type == RTW89_FW_LOGFMT)
-		return &fw_info->logfmt;
+		return &fw_info->log.suit;
 	return &fw_info->normal;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index f67af8aa2358f..f1e5ac4186c2a 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -3204,20 +3204,22 @@ static ssize_t rtw89_debug_priv_btc_manual_set(struct file *filp,
 	return count;
 }
 
-static ssize_t rtw89_debug_fw_log_btc_manual_set(struct file *filp,
-						 const char __user *user_buf,
-						 size_t count, loff_t *loff)
+static ssize_t rtw89_debug_fw_log_manual_set(struct file *filp,
+					     const char __user *user_buf,
+					     size_t count, loff_t *loff)
 {
 	struct rtw89_debugfs_priv *debugfs_priv = filp->private_data;
 	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
-	struct rtw89_fw_info *fw_info = &rtwdev->fw;
+	struct rtw89_fw_log *log = &rtwdev->fw.log;
 	bool fw_log_manual;
 
 	if (kstrtobool_from_user(user_buf, count, &fw_log_manual))
 		goto out;
 
 	mutex_lock(&rtwdev->mutex);
-	fw_info->fw_log_enable = fw_log_manual;
+	log->enable = fw_log_manual;
+	if (log->enable)
+		rtw89_fw_log_prepare(rtwdev);
 	rtw89_fw_h2c_fw_log(rtwdev, fw_log_manual);
 	mutex_unlock(&rtwdev->mutex);
 out:
@@ -3584,7 +3586,7 @@ static struct rtw89_debugfs_priv rtw89_debug_priv_btc_manual = {
 };
 
 static struct rtw89_debugfs_priv rtw89_debug_priv_fw_log_manual = {
-	.cb_write = rtw89_debug_fw_log_btc_manual_set,
+	.cb_write = rtw89_debug_fw_log_manual_set,
 };
 
 static struct rtw89_debugfs_priv rtw89_debug_priv_phy_info = {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index f27eb09d2bab6..cbb0e953fbbfe 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -697,6 +697,150 @@ void rtw89_unload_firmware(struct rtw89_dev *rtwdev)
 		 */
 		fw->req.firmware = NULL;
 	}
+
+	kfree(fw->log.fmts);
+}
+
+static u32 rtw89_fw_log_get_fmt_idx(struct rtw89_dev *rtwdev, u32 fmt_id)
+{
+	struct rtw89_fw_log *fw_log = &rtwdev->fw.log;
+	u32 i;
+
+	if (fmt_id > fw_log->last_fmt_id)
+		return 0;
+
+	for (i = 0; i < fw_log->fmt_count; i++) {
+		if (le32_to_cpu(fw_log->fmt_ids[i]) == fmt_id)
+			return i;
+	}
+	return 0;
+}
+
+static int rtw89_fw_log_create_fmts_dict(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_fw_log *log = &rtwdev->fw.log;
+	const struct rtw89_fw_logsuit_hdr *suit_hdr;
+	struct rtw89_fw_suit *suit = &log->suit;
+	const void *fmts_ptr, *fmts_end_ptr;
+	u32 fmt_count;
+	int i;
+
+	suit_hdr = (const struct rtw89_fw_logsuit_hdr *)suit->data;
+	fmt_count = le32_to_cpu(suit_hdr->count);
+	log->fmt_ids = suit_hdr->ids;
+	fmts_ptr = &suit_hdr->ids[fmt_count];
+	fmts_end_ptr = suit->data + suit->size;
+	log->fmts = kcalloc(fmt_count, sizeof(char *), GFP_KERNEL);
+	if (!log->fmts)
+		return -ENOMEM;
+
+	for (i = 0; i < fmt_count; i++) {
+		fmts_ptr = memchr_inv(fmts_ptr, 0, fmts_end_ptr - fmts_ptr);
+		if (!fmts_ptr)
+			break;
+
+		(*log->fmts)[i] = fmts_ptr;
+		log->last_fmt_id = le32_to_cpu(log->fmt_ids[i]);
+		log->fmt_count++;
+		fmts_ptr += strlen(fmts_ptr);
+	}
+
+	return 0;
+}
+
+int rtw89_fw_log_prepare(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_fw_log *log = &rtwdev->fw.log;
+	struct rtw89_fw_suit *suit = &log->suit;
+
+	if (!suit || !suit->data) {
+		rtw89_debug(rtwdev, RTW89_DBG_FW, "no log format file\n");
+		return -EINVAL;
+	}
+	if (log->fmts)
+		return 0;
+
+	return rtw89_fw_log_create_fmts_dict(rtwdev);
+}
+
+static void rtw89_fw_log_dump_data(struct rtw89_dev *rtwdev,
+				   const struct rtw89_fw_c2h_log_fmt *log_fmt,
+				   u32 fmt_idx, u8 para_int, bool raw_data)
+{
+	const char *(*fmts)[] = rtwdev->fw.log.fmts;
+	char str_buf[RTW89_C2H_FW_LOG_STR_BUF_SIZE];
+	u32 args[RTW89_C2H_FW_LOG_MAX_PARA_NUM] = {0};
+	int i;
+
+	if (log_fmt->argc > RTW89_C2H_FW_LOG_MAX_PARA_NUM) {
+		rtw89_warn(rtwdev, "C2H log: Arg count is unexpected %d\n",
+			   log_fmt->argc);
+		return;
+	}
+
+	if (para_int)
+		for (i = 0 ; i < log_fmt->argc; i++)
+			args[i] = le32_to_cpu(log_fmt->u.argv[i]);
+
+	if (raw_data) {
+		if (para_int)
+			snprintf(str_buf, RTW89_C2H_FW_LOG_STR_BUF_SIZE,
+				 "fw_enc(%d, %d, %d) %*ph", le32_to_cpu(log_fmt->fmt_id),
+				 para_int, log_fmt->argc, (int)sizeof(args), args);
+		else
+			snprintf(str_buf, RTW89_C2H_FW_LOG_STR_BUF_SIZE,
+				 "fw_enc(%d, %d, %d, %s)", le32_to_cpu(log_fmt->fmt_id),
+				 para_int, log_fmt->argc, log_fmt->u.raw);
+	} else {
+		snprintf(str_buf, RTW89_C2H_FW_LOG_STR_BUF_SIZE, (*fmts)[fmt_idx],
+			 args[0x0], args[0x1], args[0x2], args[0x3], args[0x4],
+			 args[0x5], args[0x6], args[0x7], args[0x8], args[0x9],
+			 args[0xa], args[0xb], args[0xc], args[0xd], args[0xe],
+			 args[0xf]);
+	}
+
+	rtw89_info(rtwdev, "C2H log: %s", str_buf);
+}
+
+void rtw89_fw_log_dump(struct rtw89_dev *rtwdev, u8 *buf, u32 len)
+{
+	const struct rtw89_fw_c2h_log_fmt *log_fmt;
+	u8 para_int;
+	u32 fmt_idx;
+
+	if (len < RTW89_C2H_HEADER_LEN) {
+		rtw89_err(rtwdev, "c2h log length is wrong!\n");
+		return;
+	}
+
+	buf += RTW89_C2H_HEADER_LEN;
+	len -= RTW89_C2H_HEADER_LEN;
+	log_fmt = (const struct rtw89_fw_c2h_log_fmt *)buf;
+
+	if (len < RTW89_C2H_FW_FORMATTED_LOG_MIN_LEN)
+		goto plain_log;
+
+	if (log_fmt->signature != cpu_to_le16(RTW89_C2H_FW_LOG_SIGNATURE))
+		goto plain_log;
+
+	if (!rtwdev->fw.log.fmts)
+		return;
+
+	para_int = u8_get_bits(log_fmt->feature, RTW89_C2H_FW_LOG_FEATURE_PARA_INT);
+	fmt_idx = rtw89_fw_log_get_fmt_idx(rtwdev, le32_to_cpu(log_fmt->fmt_id));
+
+	if (!para_int && log_fmt->argc != 0 && fmt_idx != 0)
+		rtw89_info(rtwdev, "C2H log: %s%s",
+			   (*rtwdev->fw.log.fmts)[fmt_idx], log_fmt->u.raw);
+	else if (fmt_idx != 0 && para_int)
+		rtw89_fw_log_dump_data(rtwdev, log_fmt, fmt_idx, para_int, false);
+	else
+		rtw89_fw_log_dump_data(rtwdev, log_fmt, fmt_idx, para_int, true);
+	return;
+
+plain_log:
+	rtw89_info(rtwdev, "C2H log: %*s", len, buf);
+
 }
 
 #define H2C_CAM_LEN 60
@@ -910,7 +1054,7 @@ int rtw89_fw_h2c_fw_log(struct rtw89_dev *rtwdev, bool enable)
 	}
 
 	skb_put(skb, H2C_LOG_CFG_LEN);
-	SET_LOG_CFG_LEVEL(skb->data, RTW89_FW_LOG_LEVEL_SER);
+	SET_LOG_CFG_LEVEL(skb->data, RTW89_FW_LOG_LEVEL_LOUD);
 	SET_LOG_CFG_PATH(skb->data, BIT(RTW89_FW_LOG_LEVEL_C2H));
 	SET_LOG_CFG_COMP(skb->data, comp);
 	SET_LOG_CFG_COMP_EXT(skb->data, 0);
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 49ecf070de712..ad1a621783f90 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -3125,9 +3125,6 @@ static inline struct rtw89_fw_c2h_attr *RTW89_SKB_C2H_CB(struct sk_buff *skb)
 	return (struct rtw89_fw_c2h_attr *)skb->cb;
 }
 
-#define RTW89_GET_C2H_LOG_SRT_PRT(c2h) (char *)((__le32 *)(c2h) + 2)
-#define RTW89_GET_C2H_LOG_LEN(len) ((len) - RTW89_C2H_HEADER_LEN)
-
 struct rtw89_c2h_done_ack {
 	__le32 w0;
 	__le32 w1;
@@ -3149,6 +3146,26 @@ struct rtw89_c2h_done_ack {
 #define RTW89_GET_MAC_C2H_REV_ACK_H2C_SEQ(c2h) \
 	le32_get_bits(*((const __le32 *)(c2h) + 2), GENMASK(23, 16))
 
+struct rtw89_fw_c2h_log_fmt {
+	__le16 signature;
+	u8 feature;
+	u8 syntax;
+	__le32 fmt_id;
+	u8 file_num;
+	__le16 line_num;
+	u8 argc;
+	union {
+		DECLARE_FLEX_ARRAY(u8, raw);
+		DECLARE_FLEX_ARRAY(__le32, argv);
+	} __packed u;
+} __packed;
+
+#define RTW89_C2H_FW_FORMATTED_LOG_MIN_LEN 11
+#define RTW89_C2H_FW_LOG_FEATURE_PARA_INT BIT(2)
+#define RTW89_C2H_FW_LOG_MAX_PARA_NUM 16
+#define RTW89_C2H_FW_LOG_SIGNATURE 0xA5A5
+#define RTW89_C2H_FW_LOG_STR_BUF_SIZE 512
+
 struct rtw89_c2h_mac_bcnfltr_rpt {
 	__le32 w0;
 	__le32 w1;
@@ -3327,6 +3344,12 @@ struct rtw89_mfw_hdr {
 	struct rtw89_mfw_info info[];
 } __packed;
 
+struct rtw89_fw_logsuit_hdr {
+	__le32 rsvd;
+	__le32 count;
+	__le32 ids[];
+} __packed;
+
 struct fwcmd_hdr {
 	__le32 hdr0;
 	__le32 hdr1;
@@ -3517,6 +3540,8 @@ int rtw89_fw_download(struct rtw89_dev *rtwdev, enum rtw89_fw_type type);
 void rtw89_load_firmware_work(struct work_struct *work);
 void rtw89_unload_firmware(struct rtw89_dev *rtwdev);
 int rtw89_wait_firmware_completion(struct rtw89_dev *rtwdev);
+int rtw89_fw_log_prepare(struct rtw89_dev *rtwdev);
+void rtw89_fw_log_dump(struct rtw89_dev *rtwdev, u8 *buf, u32 len);
 void rtw89_h2c_pkt_set_hdr(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 			   u8 type, u8 cat, u8 class, u8 func,
 			   bool rack, bool dack, u32 len);
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index b114babec698c..1efa4da3cebc9 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -4437,8 +4437,7 @@ rtw89_mac_c2h_done_ack(struct rtw89_dev *rtwdev, struct sk_buff *skb_c2h, u32 le
 static void
 rtw89_mac_c2h_log(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
 {
-	rtw89_info(rtwdev, "%*s", RTW89_GET_C2H_LOG_LEN(len),
-		   RTW89_GET_C2H_LOG_SRT_PRT(c2h->data));
+	rtw89_fw_log_dump(rtwdev, c2h->data, len);
 }
 
 static void
-- 
GitLab


From 1b073b350d24b9481f0dffea9e9dec05c838098a Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 1 Aug 2023 10:11:22 +0800
Subject: [PATCH 0844/1806] wifi: rtw89: introduce v1 format of firmware header

New firmware header is used by upcoming WiFi 7 chips to have more
information, so use common field w3[31:24] to determine header version,
and then use corresponding function to read firmware version and commit ID:

rtw89_8852be 0000:03:00.0: Firmware version 0.29.29.1 (799134c3), cmd version 1, type 5
rtw89_8852be 0000:03:00.0: Firmware version 0.29.29.1 (799134c3), cmd version 1, type 3

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230801021127.15919-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |  3 ++
 drivers/net/wireless/realtek/rtw89/fw.c   | 66 ++++++++++++++++++-----
 drivers/net/wireless/realtek/rtw89/fw.h   | 33 ++++++++++++
 3 files changed, 89 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index f05086b27b266..01f79f2a8e2b6 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3563,6 +3563,7 @@ enum rtw89_fw_feature {
 };
 
 struct rtw89_fw_suit {
+	enum rtw89_fw_type type;
 	const u8 *data;
 	u32 size;
 	u8 major_ver;
@@ -3575,6 +3576,8 @@ struct rtw89_fw_suit {
 	u16 build_hour;
 	u16 build_min;
 	u8 cmd_ver;
+	u8 hdr_ver;
+	u32 commitid;
 };
 
 #define RTW89_FW_VER_CODE(major, minor, sub, idx)	\
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index cbb0e953fbbfe..a57d075db74a0 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -196,30 +196,72 @@ found:
 	return 0;
 }
 
-static void rtw89_fw_update_ver(struct rtw89_dev *rtwdev,
-				enum rtw89_fw_type type,
-				struct rtw89_fw_suit *fw_suit)
+static void rtw89_fw_update_ver_v0(struct rtw89_dev *rtwdev,
+				   struct rtw89_fw_suit *fw_suit,
+				   const struct rtw89_fw_hdr *hdr)
 {
-	const struct rtw89_fw_hdr *hdr = (const struct rtw89_fw_hdr *)fw_suit->data;
-
-	if (type == RTW89_FW_LOGFMT)
-		return;
-
 	fw_suit->major_ver = le32_get_bits(hdr->w1, FW_HDR_W1_MAJOR_VERSION);
 	fw_suit->minor_ver = le32_get_bits(hdr->w1, FW_HDR_W1_MINOR_VERSION);
 	fw_suit->sub_ver = le32_get_bits(hdr->w1, FW_HDR_W1_SUBVERSION);
 	fw_suit->sub_idex = le32_get_bits(hdr->w1, FW_HDR_W1_SUBINDEX);
+	fw_suit->commitid = le32_get_bits(hdr->w2, FW_HDR_W2_COMMITID);
 	fw_suit->build_year = le32_get_bits(hdr->w5, FW_HDR_W5_YEAR);
 	fw_suit->build_mon = le32_get_bits(hdr->w4, FW_HDR_W4_MONTH);
 	fw_suit->build_date = le32_get_bits(hdr->w4, FW_HDR_W4_DATE);
 	fw_suit->build_hour = le32_get_bits(hdr->w4, FW_HDR_W4_HOUR);
 	fw_suit->build_min = le32_get_bits(hdr->w4, FW_HDR_W4_MIN);
 	fw_suit->cmd_ver = le32_get_bits(hdr->w7, FW_HDR_W7_CMD_VERSERION);
+}
+
+static void rtw89_fw_update_ver_v1(struct rtw89_dev *rtwdev,
+				   struct rtw89_fw_suit *fw_suit,
+				   const struct rtw89_fw_hdr_v1 *hdr)
+{
+	fw_suit->major_ver = le32_get_bits(hdr->w1, FW_HDR_V1_W1_MAJOR_VERSION);
+	fw_suit->minor_ver = le32_get_bits(hdr->w1, FW_HDR_V1_W1_MINOR_VERSION);
+	fw_suit->sub_ver = le32_get_bits(hdr->w1, FW_HDR_V1_W1_SUBVERSION);
+	fw_suit->sub_idex = le32_get_bits(hdr->w1, FW_HDR_V1_W1_SUBINDEX);
+	fw_suit->commitid = le32_get_bits(hdr->w2, FW_HDR_V1_W2_COMMITID);
+	fw_suit->build_year = le32_get_bits(hdr->w5, FW_HDR_V1_W5_YEAR);
+	fw_suit->build_mon = le32_get_bits(hdr->w4, FW_HDR_V1_W4_MONTH);
+	fw_suit->build_date = le32_get_bits(hdr->w4, FW_HDR_V1_W4_DATE);
+	fw_suit->build_hour = le32_get_bits(hdr->w4, FW_HDR_V1_W4_HOUR);
+	fw_suit->build_min = le32_get_bits(hdr->w4, FW_HDR_V1_W4_MIN);
+	fw_suit->cmd_ver = le32_get_bits(hdr->w7, FW_HDR_V1_W3_CMD_VERSERION);
+}
+
+static int rtw89_fw_update_ver(struct rtw89_dev *rtwdev,
+			       enum rtw89_fw_type type,
+			       struct rtw89_fw_suit *fw_suit)
+{
+	const struct rtw89_fw_hdr *v0 = (const struct rtw89_fw_hdr *)fw_suit->data;
+	const struct rtw89_fw_hdr_v1 *v1 = (const struct rtw89_fw_hdr_v1 *)fw_suit->data;
+
+	if (type == RTW89_FW_LOGFMT)
+		return 0;
+
+	fw_suit->type = type;
+	fw_suit->hdr_ver = le32_get_bits(v0->w3, FW_HDR_W3_HDR_VER);
+
+	switch (fw_suit->hdr_ver) {
+	case 0:
+		rtw89_fw_update_ver_v0(rtwdev, fw_suit, v0);
+		break;
+	case 1:
+		rtw89_fw_update_ver_v1(rtwdev, fw_suit, v1);
+		break;
+	default:
+		rtw89_err(rtwdev, "Unknown firmware header version %u\n",
+			  fw_suit->hdr_ver);
+		return -ENOENT;
+	}
 
 	rtw89_info(rtwdev,
-		   "Firmware version %u.%u.%u.%u, cmd version %u, type %u\n",
+		   "Firmware version %u.%u.%u.%u (%08x), cmd version %u, type %u\n",
 		   fw_suit->major_ver, fw_suit->minor_ver, fw_suit->sub_ver,
-		   fw_suit->sub_idex, fw_suit->cmd_ver, type);
+		   fw_suit->sub_idex, fw_suit->commitid, fw_suit->cmd_ver, type);
+
+	return 0;
 }
 
 static
@@ -233,9 +275,7 @@ int __rtw89_fw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 	if (ret)
 		return ret;
 
-	rtw89_fw_update_ver(rtwdev, type, fw_suit);
-
-	return 0;
+	return rtw89_fw_update_ver(rtwdev, type, fw_suit);
 }
 
 #define __DEF_FW_FEAT_COND(__cond, __op) \
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index ad1a621783f90..366645bcead5f 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -463,7 +463,9 @@ struct rtw89_fw_hdr {
 #define FW_HDR_W1_MINOR_VERSION GENMASK(15, 8)
 #define FW_HDR_W1_SUBVERSION GENMASK(23, 16)
 #define FW_HDR_W1_SUBINDEX GENMASK(31, 24)
+#define FW_HDR_W2_COMMITID GENMASK(31, 0)
 #define FW_HDR_W3_LEN GENMASK(23, 16)
+#define FW_HDR_W3_HDR_VER GENMASK(31, 24)
 #define FW_HDR_W4_MONTH GENMASK(7, 0)
 #define FW_HDR_W4_DATE GENMASK(15, 8)
 #define FW_HDR_W4_HOUR GENMASK(23, 16)
@@ -473,6 +475,37 @@ struct rtw89_fw_hdr {
 #define FW_HDR_W7_DYN_HDR BIT(16)
 #define FW_HDR_W7_CMD_VERSERION GENMASK(31, 24)
 
+struct rtw89_fw_hdr_v1 {
+	__le32 w0;
+	__le32 w1;
+	__le32 w2;
+	__le32 w3;
+	__le32 w4;
+	__le32 w5;
+	__le32 w6;
+	__le32 w7;
+	__le32 w8;
+	__le32 w9;
+	__le32 w10;
+	__le32 w11;
+} __packed;
+
+#define FW_HDR_V1_W1_MAJOR_VERSION GENMASK(7, 0)
+#define FW_HDR_V1_W1_MINOR_VERSION GENMASK(15, 8)
+#define FW_HDR_V1_W1_SUBVERSION GENMASK(23, 16)
+#define FW_HDR_V1_W1_SUBINDEX GENMASK(31, 24)
+#define FW_HDR_V1_W2_COMMITID GENMASK(31, 0)
+#define FW_HDR_V1_W3_CMD_VERSERION GENMASK(23, 16)
+#define FW_HDR_V1_W3_HDR_VER GENMASK(31, 24)
+#define FW_HDR_V1_W4_MONTH GENMASK(7, 0)
+#define FW_HDR_V1_W4_DATE GENMASK(15, 8)
+#define FW_HDR_V1_W4_HOUR GENMASK(23, 16)
+#define FW_HDR_V1_W4_MIN GENMASK(31, 24)
+#define FW_HDR_V1_W5_YEAR GENMASK(15, 0)
+#define FW_HDR_V1_W5_HDR_SIZE GENMASK(31, 16)
+#define FW_HDR_V1_W6_SEC_NUM GENMASK(15, 8)
+#define FW_HDR_V1_W7_DYN_HDR BIT(16)
+
 static inline void SET_FW_HDR_PART_SIZE(void *fwhdr, u32 val)
 {
 	le32p_replace_bits((__le32 *)fwhdr + 7, val, GENMASK(15, 0));
-- 
GitLab


From 12b1a12548eb31812f0a6128a0796d1656e2abb2 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 1 Aug 2023 10:11:23 +0800
Subject: [PATCH 0845/1806] wifi: rtw89: add firmware parser for v1 format

A firmware with v1 format contains many sections to download. Add parser to
read section type, target address, length, checksum and so on, and then
download the section to WiFi CPU with proper location.

The additional dynamic header length named dynamic_hdr_len is used to
skip content of dynamic header containing compiler flags of firmware, which
can help to determine variant firmware build, but currently rtw89 only
use single one variant. So, just skip the content.

The layout of a WiFi CPU firmware with v1 format looks like:

+---------------------------------------+
|      Header (12 words)                |
+---------------------------------------+
|      Section header 1 (4 words)       |
|      Section header 2 (4 words)       |
|      Section header 3 (4 words)       |
|      ...                              |
+---------------------------------------+
|      Dynamic header (variable length) |
+---------------------------------------+
|      Data used & pointed by section   |
|      ...                              |
+---------------------------------------+

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230801021127.15919-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 106 +++++++++++++++++++++---
 drivers/net/wireless/realtek/rtw89/fw.h |  17 ++++
 2 files changed, 111 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index a57d075db74a0..d8bcc51242ffa 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -86,8 +86,8 @@ int rtw89_fw_check_rdy(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int rtw89_fw_hdr_parser(struct rtw89_dev *rtwdev, const u8 *fw, u32 len,
-			       struct rtw89_fw_bin_info *info)
+static int rtw89_fw_hdr_parser_v0(struct rtw89_dev *rtwdev, const u8 *fw, u32 len,
+				  struct rtw89_fw_bin_info *info)
 {
 	const struct rtw89_fw_hdr *fw_hdr = (const struct rtw89_fw_hdr *)fw;
 	struct rtw89_fw_hdr_section_info *section_info;
@@ -154,6 +154,94 @@ static int rtw89_fw_hdr_parser(struct rtw89_dev *rtwdev, const u8 *fw, u32 len,
 	return 0;
 }
 
+static int rtw89_fw_hdr_parser_v1(struct rtw89_dev *rtwdev, const u8 *fw, u32 len,
+				  struct rtw89_fw_bin_info *info)
+{
+	const struct rtw89_fw_hdr_v1 *fw_hdr = (const struct rtw89_fw_hdr_v1 *)fw;
+	struct rtw89_fw_hdr_section_info *section_info;
+	const struct rtw89_fw_dynhdr_hdr *fwdynhdr;
+	const struct rtw89_fw_hdr_section_v1 *section;
+	const u8 *fw_end = fw + len;
+	const u8 *bin;
+	u32 base_hdr_len;
+	u32 mssc_len = 0;
+	u32 i;
+
+	info->section_num = le32_get_bits(fw_hdr->w6, FW_HDR_V1_W6_SEC_NUM);
+	base_hdr_len = struct_size(fw_hdr, sections, info->section_num);
+	info->dynamic_hdr_en = le32_get_bits(fw_hdr->w7, FW_HDR_V1_W7_DYN_HDR);
+
+	if (info->dynamic_hdr_en) {
+		info->hdr_len = le32_get_bits(fw_hdr->w5, FW_HDR_V1_W5_HDR_SIZE);
+		info->dynamic_hdr_len = info->hdr_len - base_hdr_len;
+		fwdynhdr = (const struct rtw89_fw_dynhdr_hdr *)(fw + base_hdr_len);
+		if (le32_to_cpu(fwdynhdr->hdr_len) != info->dynamic_hdr_len) {
+			rtw89_err(rtwdev, "[ERR]invalid fw dynamic header len\n");
+			return -EINVAL;
+		}
+	} else {
+		info->hdr_len = base_hdr_len;
+		info->dynamic_hdr_len = 0;
+	}
+
+	bin = fw + info->hdr_len;
+
+	/* jump to section header */
+	section_info = info->section_info;
+	for (i = 0; i < info->section_num; i++) {
+		section = &fw_hdr->sections[i];
+		section_info->type =
+			le32_get_bits(section->w1, FWSECTION_HDR_V1_W1_SECTIONTYPE);
+		if (section_info->type == FWDL_SECURITY_SECTION_TYPE) {
+			section_info->mssc =
+				le32_get_bits(section->w2, FWSECTION_HDR_V1_W2_MSSC);
+			mssc_len += section_info->mssc * FWDL_SECURITY_SIGLEN;
+		} else {
+			section_info->mssc = 0;
+		}
+
+		section_info->len =
+			le32_get_bits(section->w1, FWSECTION_HDR_V1_W1_SEC_SIZE);
+		if (le32_get_bits(section->w1, FWSECTION_HDR_V1_W1_CHECKSUM))
+			section_info->len += FWDL_SECTION_CHKSUM_LEN;
+		section_info->redl = le32_get_bits(section->w1, FWSECTION_HDR_V1_W1_REDL);
+		section_info->dladdr =
+			le32_get_bits(section->w0, FWSECTION_HDR_V1_W0_DL_ADDR);
+		section_info->addr = bin;
+		bin += section_info->len;
+		section_info++;
+	}
+
+	if (fw_end != bin + mssc_len) {
+		rtw89_err(rtwdev, "[ERR]fw bin size\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rtw89_fw_hdr_parser(struct rtw89_dev *rtwdev,
+			       const struct rtw89_fw_suit *fw_suit,
+			       struct rtw89_fw_bin_info *info)
+{
+	const u8 *fw = fw_suit->data;
+	u32 len = fw_suit->size;
+
+	if (!fw || !len) {
+		rtw89_err(rtwdev, "fw type %d isn't recognized\n", fw_suit->type);
+		return -ENOENT;
+	}
+
+	switch (fw_suit->hdr_ver) {
+	case 0:
+		return rtw89_fw_hdr_parser_v0(rtwdev, fw, len, info);
+	case 1:
+		return rtw89_fw_hdr_parser_v1(rtwdev, fw, len, info);
+	default:
+		return -ENOENT;
+	}
+}
+
 static
 int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 			struct rtw89_fw_suit *fw_suit, bool nowarn)
@@ -621,8 +709,6 @@ int rtw89_fw_download(struct rtw89_dev *rtwdev, enum rtw89_fw_type type)
 	struct rtw89_fw_info *fw_info = &rtwdev->fw;
 	struct rtw89_fw_suit *fw_suit = rtw89_fw_suit_get(rtwdev, type);
 	struct rtw89_fw_bin_info info;
-	const u8 *fw = fw_suit->data;
-	u32 len = fw_suit->size;
 	u8 val;
 	int ret;
 
@@ -631,12 +717,7 @@ int rtw89_fw_download(struct rtw89_dev *rtwdev, enum rtw89_fw_type type)
 	if (ret)
 		return ret;
 
-	if (!fw || !len) {
-		rtw89_err(rtwdev, "fw type %d isn't recognized\n", type);
-		return -ENOENT;
-	}
-
-	ret = rtw89_fw_hdr_parser(rtwdev, fw, len, &info);
+	ret = rtw89_fw_hdr_parser(rtwdev, fw_suit, &info);
 	if (ret) {
 		rtw89_err(rtwdev, "parse fw header fail\n");
 		goto fwdl_err;
@@ -650,13 +731,14 @@ int rtw89_fw_download(struct rtw89_dev *rtwdev, enum rtw89_fw_type type)
 		goto fwdl_err;
 	}
 
-	ret = rtw89_fw_download_hdr(rtwdev, fw, info.hdr_len - info.dynamic_hdr_len);
+	ret = rtw89_fw_download_hdr(rtwdev, fw_suit->data, info.hdr_len -
+							   info.dynamic_hdr_len);
 	if (ret) {
 		ret = -EBUSY;
 		goto fwdl_err;
 	}
 
-	ret = rtw89_fw_download_main(rtwdev, fw, &info);
+	ret = rtw89_fw_download_main(rtwdev, fw_suit->data, &info);
 	if (ret) {
 		ret = -EBUSY;
 		goto fwdl_err;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 366645bcead5f..8961958009dd9 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -475,6 +475,22 @@ struct rtw89_fw_hdr {
 #define FW_HDR_W7_DYN_HDR BIT(16)
 #define FW_HDR_W7_CMD_VERSERION GENMASK(31, 24)
 
+struct rtw89_fw_hdr_section_v1 {
+	__le32 w0;
+	__le32 w1;
+	__le32 w2;
+	__le32 w3;
+} __packed;
+
+#define FWSECTION_HDR_V1_W0_DL_ADDR GENMASK(31, 0)
+#define FWSECTION_HDR_V1_W1_METADATA GENMASK(31, 24)
+#define FWSECTION_HDR_V1_W1_SECTIONTYPE GENMASK(27, 24)
+#define FWSECTION_HDR_V1_W1_SEC_SIZE GENMASK(23, 0)
+#define FWSECTION_HDR_V1_W1_CHECKSUM BIT(28)
+#define FWSECTION_HDR_V1_W1_REDL BIT(29)
+#define FWSECTION_HDR_V1_W2_MSSC GENMASK(7, 0)
+#define FWSECTION_HDR_V1_W2_BBMCU_IDX GENMASK(27, 24)
+
 struct rtw89_fw_hdr_v1 {
 	__le32 w0;
 	__le32 w1;
@@ -488,6 +504,7 @@ struct rtw89_fw_hdr_v1 {
 	__le32 w9;
 	__le32 w10;
 	__le32 w11;
+	struct rtw89_fw_hdr_section_v1 sections[];
 } __packed;
 
 #define FW_HDR_V1_W1_MAJOR_VERSION GENMASK(7, 0)
-- 
GitLab


From 7d112665982b0b78e6bcf4173c8231838c158187 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 1 Aug 2023 10:11:24 +0800
Subject: [PATCH 0846/1806] wifi: rtw89: add firmware suit for BB MCU 0/1

For existing chips, firmware is only for WiFi CPU, but WiFi 7 chips add
new hardware component BB MCU that needs firmware as well. The firmwares of
BB MCU 0/1 are also downloaded via the same path like WiFi CPU firmware,
and use the same firmware header format, so add firmware suits to access
them commonly.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230801021127.15919-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 01f79f2a8e2b6..aaee0733301ac 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3548,6 +3548,8 @@ enum rtw89_fw_type {
 	RTW89_FW_NORMAL = 1,
 	RTW89_FW_WOWLAN = 3,
 	RTW89_FW_NORMAL_CE = 5,
+	RTW89_FW_BBMCU0 = 64,
+	RTW89_FW_BBMCU1 = 65,
 	RTW89_FW_LOGFMT = 255,
 };
 
@@ -3620,6 +3622,8 @@ struct rtw89_fw_info {
 	u8 c2h_counter;
 	struct rtw89_fw_suit normal;
 	struct rtw89_fw_suit wowlan;
+	struct rtw89_fw_suit bbmcu0;
+	struct rtw89_fw_suit bbmcu1;
 	struct rtw89_fw_log log;
 	u32 feature_map;
 };
@@ -5154,10 +5158,19 @@ static inline struct rtw89_fw_suit *rtw89_fw_suit_get(struct rtw89_dev *rtwdev,
 {
 	struct rtw89_fw_info *fw_info = &rtwdev->fw;
 
-	if (type == RTW89_FW_WOWLAN)
+	switch (type) {
+	case RTW89_FW_WOWLAN:
 		return &fw_info->wowlan;
-	else if (type == RTW89_FW_LOGFMT)
+	case RTW89_FW_LOGFMT:
 		return &fw_info->log.suit;
+	case RTW89_FW_BBMCU0:
+		return &fw_info->bbmcu0;
+	case RTW89_FW_BBMCU1:
+		return &fw_info->bbmcu1;
+	default:
+		break;
+	}
+
 	return &fw_info->normal;
 }
 
-- 
GitLab


From a337d4331fd64652a9ad459049713ba5b1f8e0bd Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 1 Aug 2023 10:11:25 +0800
Subject: [PATCH 0847/1806] wifi: rtw89: introduce infrastructure of firmware
 elements

In order to pack more data into firmware file, we introduce firmware
elements and append BB_MCU firmware first. The first part of new firmware
file is still unchanged firmware of WiFi CPU, so the new firmware format
can be backward compatible to old format. The new elements part consists
of ID and size basically, which can append more elements simply. To avoid
unaligned access in certain platform and be easy to read, headers of all
elements start at 16-byte aligned address.

 +===========================================+
 |             original firmware             |
 |                             +-------------+
 |                             |   padding   |
 +===========================================+
 | elm ID 1 | elm size |  other header data  |
 +----------+----------+                     |
 |                                           |
 +-------------------------------------------+
 | content (variable length)                 |
 |                             +-------------+
 |                             |   padding   |
 +===========================================+
 | elm ID 2 | elm size |  other header data  |
 +----------+----------+                     |
 |                                           |
 +-------------------------------------------+
 | content (variable length)                 |
 |                   +-----------------------+
 |                   | (no padding for the last one)
 +===================+

More detail of element header is shown below. The additional fields
'version' and 'element_priv[]' are meta data of elements, so that we can
know element version easily, and element_priv[] provide specific fields
for certain element, such as RF path index for RF parameter tables.

 +===========================================+
 |  elm ID  | elm size | version  |   rsvd0  |
 +----------+----------+----------+----------+
 |        rsvd1/2      |  element_priv[]     |
 +-------------------------------------------+

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230801021127.15919-7-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c |  6 ++
 drivers/net/wireless/realtek/rtw89/fw.c   | 98 +++++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/fw.h   | 31 +++++++
 3 files changed, 135 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index ecdd05b851b75..62c21c09cf92b 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -3779,6 +3779,12 @@ int rtw89_chip_info_setup(struct rtw89_dev *rtwdev)
 		return ret;
 	}
 
+	ret = rtw89_fw_recognize_elements(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to recognize firmware elements\n");
+		return ret;
+	}
+
 	ret = rtw89_chip_efuse_info_setup(rtwdev);
 	if (ret)
 		return ret;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index d8bcc51242ffa..d36fbbb6c5492 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -284,6 +284,26 @@ found:
 	return 0;
 }
 
+static u32 rtw89_mfw_get_size(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_fw_info *fw_info = &rtwdev->fw;
+	const struct firmware *firmware = fw_info->req.firmware;
+	const struct rtw89_mfw_hdr *mfw_hdr =
+		(const struct rtw89_mfw_hdr *)firmware->data;
+	const struct rtw89_mfw_info *mfw_info;
+	u32 size;
+
+	if (mfw_hdr->sig != RTW89_MFW_SIG) {
+		rtw89_warn(rtwdev, "not mfw format\n");
+		return 0;
+	}
+
+	mfw_info = &mfw_hdr->info[mfw_hdr->fw_nr - 1];
+	size = le32_to_cpu(mfw_info->shift) + le32_to_cpu(mfw_info->size);
+
+	return size;
+}
+
 static void rtw89_fw_update_ver_v0(struct rtw89_dev *rtwdev,
 				   struct rtw89_fw_suit *fw_suit,
 				   const struct rtw89_fw_hdr *hdr)
@@ -366,6 +386,21 @@ int __rtw89_fw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 	return rtw89_fw_update_ver(rtwdev, type, fw_suit);
 }
 
+static
+int __rtw89_fw_recognize_from_elm(struct rtw89_dev *rtwdev,
+				  const struct rtw89_fw_element_hdr *elm,
+				  const void *data)
+{
+	enum rtw89_fw_type type = (enum rtw89_fw_type)data;
+	struct rtw89_fw_suit *fw_suit;
+
+	fw_suit = rtw89_fw_suit_get(rtwdev, type);
+	fw_suit->data = elm->u.common.contents;
+	fw_suit->size = le32_to_cpu(elm->size);
+
+	return rtw89_fw_update_ver(rtwdev, type, fw_suit);
+}
+
 #define __DEF_FW_FEAT_COND(__cond, __op) \
 static bool __fw_feat_cond_ ## __cond(u32 suit_ver_code, u32 comp_ver_code) \
 { \
@@ -509,6 +544,69 @@ normal_done:
 	return 0;
 }
 
+struct rtw89_fw_element_handler {
+	int (*fn)(struct rtw89_dev *rtwdev,
+		  const struct rtw89_fw_element_hdr *elm, const void *data);
+	const void *data;
+	const char *name;
+};
+
+static const struct rtw89_fw_element_handler __fw_element_handlers[] = {
+	[RTW89_FW_ELEMENT_ID_BBMCU0] = {__rtw89_fw_recognize_from_elm,
+					(const void *)RTW89_FW_BBMCU0, NULL},
+	[RTW89_FW_ELEMENT_ID_BBMCU1] = {__rtw89_fw_recognize_from_elm,
+					(const void *)RTW89_FW_BBMCU1, NULL},
+};
+
+int rtw89_fw_recognize_elements(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_fw_info *fw_info = &rtwdev->fw;
+	const struct firmware *firmware = fw_info->req.firmware;
+	const struct rtw89_fw_element_handler *handler;
+	const struct rtw89_fw_element_hdr *hdr;
+	u32 elm_size;
+	u32 elem_id;
+	u32 offset;
+	int ret;
+
+	offset = rtw89_mfw_get_size(rtwdev);
+	offset = ALIGN(offset, RTW89_FW_ELEMENT_ALIGN);
+	if (offset == 0)
+		return -EINVAL;
+
+	while (offset + sizeof(*hdr) < firmware->size) {
+		hdr = (const struct rtw89_fw_element_hdr *)(firmware->data + offset);
+
+		elm_size = le32_to_cpu(hdr->size);
+		if (offset + elm_size >= firmware->size) {
+			rtw89_warn(rtwdev, "firmware element size exceeds\n");
+			break;
+		}
+
+		elem_id = le32_to_cpu(hdr->id);
+		if (elem_id >= ARRAY_SIZE(__fw_element_handlers))
+			goto next;
+
+		handler = &__fw_element_handlers[elem_id];
+		if (!handler->fn)
+			goto next;
+
+		ret = handler->fn(rtwdev, hdr, handler->data);
+		if (ret)
+			return ret;
+
+		if (handler->name)
+			rtw89_info(rtwdev, "Firmware element %s version: %4ph\n",
+				   handler->name, hdr->ver);
+
+next:
+		offset += sizeof(*hdr) + elm_size;
+		offset = ALIGN(offset, RTW89_FW_ELEMENT_ALIGN);
+	}
+
+	return 0;
+}
+
 void rtw89_h2c_pkt_set_hdr(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 			   u8 type, u8 cat, u8 class, u8 func,
 			   bool rack, bool dack, u32 len)
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 8961958009dd9..cb9eed8c2f1d8 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -3400,6 +3400,36 @@ struct rtw89_fw_logsuit_hdr {
 	__le32 ids[];
 } __packed;
 
+#define RTW89_FW_ELEMENT_ALIGN 16
+
+enum rtw89_fw_element_id {
+	RTW89_FW_ELEMENT_ID_BBMCU0 = 0,
+	RTW89_FW_ELEMENT_ID_BBMCU1 = 1,
+};
+
+struct rtw89_fw_element_hdr {
+	__le32 id; /* enum rtw89_fw_element_id */
+	__le32 size; /* exclude header size */
+	u8 ver[4];
+	__le32 rsvd0;
+	__le32 rsvd1;
+	__le32 rsvd2;
+	union {
+		struct {
+			u8 priv[8];
+			u8 contents[];
+		} __packed common;
+		struct {
+			u8 idx;
+			u8 rsvd[7];
+			struct {
+				__le32 addr;
+				__le32 data;
+			} __packed regs[];
+		} __packed reg2;
+	} __packed u;
+} __packed;
+
 struct fwcmd_hdr {
 	__le32 hdr0;
 	__le32 hdr1;
@@ -3581,6 +3611,7 @@ struct rtw89_fw_h2c_rf_get_mccch {
 
 int rtw89_fw_check_rdy(struct rtw89_dev *rtwdev);
 int rtw89_fw_recognize(struct rtw89_dev *rtwdev);
+int rtw89_fw_recognize_elements(struct rtw89_dev *rtwdev);
 const struct firmware *
 rtw89_early_fw_feature_recognize(struct device *device,
 				 const struct rtw89_chip_info *chip,
-- 
GitLab


From 894747206893c4a276e82999d1a1ed76c58bb36a Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 1 Aug 2023 10:11:26 +0800
Subject: [PATCH 0848/1806] wifi: rtw89: add to parse firmware elements of BB
 and RF tables

The tables of BB and RF parameters are pairs of {addr, value}. Load them
and convert from little-endian to CPU order, and show the version to clear
which version we are using.

  rtw89_8922ae 0000:03:00.0: Firmware element BB version: 00 04 00 00
  rtw89_8922ae 0000:03:00.0: Firmware element radio A version: 00 13 00 00
  rtw89_8922ae 0000:03:00.0: Firmware element NCTL version: 00 05 00 00

We use tables defined in firmware elements with higher priority than
original static const tables defined in driver, because WiFi 7 chips will
not define the tables in driver, and existing chips can possibly migrate to
the new design one by one.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230801021127.15919-8-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |  8 ++
 drivers/net/wireless/realtek/rtw89/fw.c   | 95 +++++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/fw.h   |  7 ++
 drivers/net/wireless/realtek/rtw89/phy.c  | 15 +++-
 4 files changed, 121 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index aaee0733301ac..bf6d8ef89097c 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3613,6 +3613,13 @@ struct rtw89_fw_log {
 	const char *(*fmts)[];
 };
 
+struct rtw89_fw_elm_info {
+	struct rtw89_phy_table *bb_tbl;
+	struct rtw89_phy_table *bb_gain;
+	struct rtw89_phy_table *rf_radio[RF_PATH_MAX];
+	struct rtw89_phy_table *rf_nctl;
+};
+
 struct rtw89_fw_info {
 	struct rtw89_fw_req_info req;
 	int fw_format;
@@ -3626,6 +3633,7 @@ struct rtw89_fw_info {
 	struct rtw89_fw_suit bbmcu1;
 	struct rtw89_fw_log log;
 	u32 feature_map;
+	struct rtw89_fw_elm_info elm_info;
 };
 
 #define RTW89_CHK_FW_FEATURE(_feat, _fw) \
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index d36fbbb6c5492..1ca99dad2ac0a 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -544,6 +544,68 @@ normal_done:
 	return 0;
 }
 
+static
+int rtw89_build_phy_tbl_from_elm(struct rtw89_dev *rtwdev,
+				 const struct rtw89_fw_element_hdr *elm,
+				 const void *data)
+{
+	struct rtw89_fw_elm_info *elm_info = &rtwdev->fw.elm_info;
+	struct rtw89_phy_table *tbl;
+	struct rtw89_reg2_def *regs;
+	enum rtw89_rf_path rf_path;
+	u32 n_regs, i;
+	u8 idx;
+
+	tbl = kzalloc(sizeof(*tbl), GFP_KERNEL);
+	if (!tbl)
+		return -ENOMEM;
+
+	switch (le32_to_cpu(elm->id)) {
+	case RTW89_FW_ELEMENT_ID_BB_REG:
+		elm_info->bb_tbl = tbl;
+		break;
+	case RTW89_FW_ELEMENT_ID_BB_GAIN:
+		elm_info->bb_gain = tbl;
+		break;
+	case RTW89_FW_ELEMENT_ID_RADIO_A:
+	case RTW89_FW_ELEMENT_ID_RADIO_B:
+	case RTW89_FW_ELEMENT_ID_RADIO_C:
+	case RTW89_FW_ELEMENT_ID_RADIO_D:
+		rf_path = (enum rtw89_rf_path)data;
+		idx = elm->u.reg2.idx;
+
+		elm_info->rf_radio[idx] = tbl;
+		tbl->rf_path = rf_path;
+		tbl->config = rtw89_phy_config_rf_reg_v1;
+		break;
+	case RTW89_FW_ELEMENT_ID_RF_NCTL:
+		elm_info->rf_nctl = tbl;
+		break;
+	default:
+		kfree(tbl);
+		return -ENOENT;
+	}
+
+	n_regs = le32_to_cpu(elm->size) / sizeof(tbl->regs[0]);
+	regs = kcalloc(n_regs, sizeof(tbl->regs[0]), GFP_KERNEL);
+	if (!regs)
+		goto out;
+
+	for (i = 0; i < n_regs; i++) {
+		regs[i].addr = le32_to_cpu(elm->u.reg2.regs[i].addr);
+		regs[i].data = le32_to_cpu(elm->u.reg2.regs[i].data);
+	}
+
+	tbl->n_regs = n_regs;
+	tbl->regs = regs;
+
+	return 0;
+
+out:
+	kfree(tbl);
+	return -ENOMEM;
+}
+
 struct rtw89_fw_element_handler {
 	int (*fn)(struct rtw89_dev *rtwdev,
 		  const struct rtw89_fw_element_hdr *elm, const void *data);
@@ -556,6 +618,17 @@ static const struct rtw89_fw_element_handler __fw_element_handlers[] = {
 					(const void *)RTW89_FW_BBMCU0, NULL},
 	[RTW89_FW_ELEMENT_ID_BBMCU1] = {__rtw89_fw_recognize_from_elm,
 					(const void *)RTW89_FW_BBMCU1, NULL},
+	[RTW89_FW_ELEMENT_ID_BB_REG] = {rtw89_build_phy_tbl_from_elm, NULL, "BB"},
+	[RTW89_FW_ELEMENT_ID_BB_GAIN] = {rtw89_build_phy_tbl_from_elm, NULL, NULL},
+	[RTW89_FW_ELEMENT_ID_RADIO_A] = {rtw89_build_phy_tbl_from_elm,
+					 (const void *)RF_PATH_A, "radio A"},
+	[RTW89_FW_ELEMENT_ID_RADIO_B] = {rtw89_build_phy_tbl_from_elm,
+					 (const void *)RF_PATH_B, NULL},
+	[RTW89_FW_ELEMENT_ID_RADIO_C] = {rtw89_build_phy_tbl_from_elm,
+					 (const void *)RF_PATH_C, NULL},
+	[RTW89_FW_ELEMENT_ID_RADIO_D] = {rtw89_build_phy_tbl_from_elm,
+					 (const void *)RF_PATH_D, NULL},
+	[RTW89_FW_ELEMENT_ID_RF_NCTL] = {rtw89_build_phy_tbl_from_elm, NULL, "NCTL"},
 };
 
 int rtw89_fw_recognize_elements(struct rtw89_dev *rtwdev)
@@ -903,6 +976,27 @@ void rtw89_load_firmware_work(struct work_struct *work)
 	rtw89_load_firmware_req(rtwdev, &rtwdev->fw.req, fw_name, false);
 }
 
+static void rtw89_free_phy_tbl_from_elm(struct rtw89_phy_table *tbl)
+{
+	if (!tbl)
+		return;
+
+	kfree(tbl->regs);
+	kfree(tbl);
+}
+
+static void rtw89_unload_firmware_elements(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_fw_elm_info *elm_info = &rtwdev->fw.elm_info;
+	int i;
+
+	rtw89_free_phy_tbl_from_elm(elm_info->bb_tbl);
+	rtw89_free_phy_tbl_from_elm(elm_info->bb_gain);
+	for (i = 0; i < ARRAY_SIZE(elm_info->rf_radio); i++)
+		rtw89_free_phy_tbl_from_elm(elm_info->rf_radio[i]);
+	rtw89_free_phy_tbl_from_elm(elm_info->rf_nctl);
+}
+
 void rtw89_unload_firmware(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_fw_info *fw = &rtwdev->fw;
@@ -919,6 +1013,7 @@ void rtw89_unload_firmware(struct rtw89_dev *rtwdev)
 	}
 
 	kfree(fw->log.fmts);
+	rtw89_unload_firmware_elements(rtwdev);
 }
 
 static u32 rtw89_fw_log_get_fmt_idx(struct rtw89_dev *rtwdev, u32 fmt_id)
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index cb9eed8c2f1d8..cbb130537e07d 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -3405,6 +3405,13 @@ struct rtw89_fw_logsuit_hdr {
 enum rtw89_fw_element_id {
 	RTW89_FW_ELEMENT_ID_BBMCU0 = 0,
 	RTW89_FW_ELEMENT_ID_BBMCU1 = 1,
+	RTW89_FW_ELEMENT_ID_BB_REG = 2,
+	RTW89_FW_ELEMENT_ID_BB_GAIN = 3,
+	RTW89_FW_ELEMENT_ID_RADIO_A = 4,
+	RTW89_FW_ELEMENT_ID_RADIO_B = 5,
+	RTW89_FW_ELEMENT_ID_RADIO_C = 6,
+	RTW89_FW_ELEMENT_ID_RADIO_D = 7,
+	RTW89_FW_ELEMENT_ID_RF_NCTL = 8,
 };
 
 struct rtw89_fw_element_hdr {
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index abe0f5179a382..c40c4f8c1271c 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -1355,12 +1355,16 @@ static void rtw89_phy_init_reg(struct rtw89_dev *rtwdev,
 
 void rtw89_phy_init_bb_reg(struct rtw89_dev *rtwdev)
 {
+	struct rtw89_fw_elm_info *elm_info = &rtwdev->fw.elm_info;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
-	const struct rtw89_phy_table *bb_table = chip->bb_table;
-	const struct rtw89_phy_table *bb_gain_table = chip->bb_gain_table;
+	const struct rtw89_phy_table *bb_table;
+	const struct rtw89_phy_table *bb_gain_table;
 
+	bb_table = elm_info->bb_tbl ? elm_info->bb_tbl : chip->bb_table;
 	rtw89_phy_init_reg(rtwdev, bb_table, rtw89_phy_config_bb_reg, NULL);
 	rtw89_chip_init_txpwr_unit(rtwdev, RTW89_PHY_0);
+
+	bb_gain_table = elm_info->bb_gain ? elm_info->bb_gain : chip->bb_gain_table;
 	if (bb_gain_table)
 		rtw89_phy_init_reg(rtwdev, bb_gain_table,
 				   rtw89_phy_config_bb_gain, NULL);
@@ -1378,6 +1382,7 @@ void rtw89_phy_init_rf_reg(struct rtw89_dev *rtwdev, bool noio)
 {
 	void (*config)(struct rtw89_dev *rtwdev, const struct rtw89_reg2_def *reg,
 		       enum rtw89_rf_path rf_path, void *data);
+	struct rtw89_fw_elm_info *elm_info = &rtwdev->fw.elm_info;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_phy_table *rf_table;
 	struct rtw89_fw_h2c_rf_reg_info *rf_reg_info;
@@ -1388,7 +1393,8 @@ void rtw89_phy_init_rf_reg(struct rtw89_dev *rtwdev, bool noio)
 		return;
 
 	for (path = RF_PATH_A; path < chip->rf_path_num; path++) {
-		rf_table = chip->rf_table[path];
+		rf_table = elm_info->rf_radio[path] ?
+			   elm_info->rf_radio[path] : chip->rf_table[path];
 		rf_reg_info->rf_path = rf_table->rf_path;
 		if (noio)
 			config = rtw89_phy_config_rf_reg_noio;
@@ -1405,6 +1411,7 @@ void rtw89_phy_init_rf_reg(struct rtw89_dev *rtwdev, bool noio)
 
 static void rtw89_phy_init_rf_nctl(struct rtw89_dev *rtwdev)
 {
+	struct rtw89_fw_elm_info *elm_info = &rtwdev->fw.elm_info;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_phy_table *nctl_table;
 	u32 val;
@@ -1427,7 +1434,7 @@ static void rtw89_phy_init_rf_nctl(struct rtw89_dev *rtwdev)
 	if (ret)
 		rtw89_err(rtwdev, "failed to poll nctl block\n");
 
-	nctl_table = chip->nctl_table;
+	nctl_table = elm_info->rf_nctl ? elm_info->rf_nctl : chip->nctl_table;
 	rtw89_phy_init_reg(rtwdev, nctl_table, rtw89_phy_config_bb_reg, NULL);
 
 	if (chip->nctl_post_table)
-- 
GitLab


From dd59c6a32b7189f51947edc5b15939367729dd85 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 1 Aug 2023 10:11:27 +0800
Subject: [PATCH 0849/1806] wifi: rtw89: return failure if needed firmware
 elements are not recognized

WiFi 7 chips doesn't have static const tables defined in driver. If tables
aren't loaded properly from firmware file, driver can get NULL pointer
access exception. One way is to add the checking statements when trying to
access these tables, but I choose to check them right after loading
firmware elements from firmware file, so I don't need to add error handlers
everywhere.

Currently, the needed firmware elements of WiFi 6 chips are all zero, and
coming WiFi 7 chip will need at least BB MCU, parameters of BB and RF.
We will add them after 8922AE is verified.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230801021127.15919-9-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h     |  1 +
 drivers/net/wireless/realtek/rtw89/fw.c       | 11 +++++++++++
 drivers/net/wireless/realtek/rtw89/fw.h       |  2 ++
 drivers/net/wireless/realtek/rtw89/rtw8851b.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c |  1 +
 7 files changed, 18 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index bf6d8ef89097c..fa4bbc4095ab9 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3382,6 +3382,7 @@ struct rtw89_chip_info {
 	const char *fw_basename;
 	u8 fw_format_max;
 	bool try_ce_fw;
+	u32 needed_fw_elms;
 	u32 fifo_size;
 	bool small_fifo_size;
 	u32 dle_scc_rsvd_size;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 1ca99dad2ac0a..2811a94b5f69a 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -635,6 +635,8 @@ int rtw89_fw_recognize_elements(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_fw_info *fw_info = &rtwdev->fw;
 	const struct firmware *firmware = fw_info->req.firmware;
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	u32 unrecognized_elements = chip->needed_fw_elms;
 	const struct rtw89_fw_element_handler *handler;
 	const struct rtw89_fw_element_hdr *hdr;
 	u32 elm_size;
@@ -642,6 +644,8 @@ int rtw89_fw_recognize_elements(struct rtw89_dev *rtwdev)
 	u32 offset;
 	int ret;
 
+	BUILD_BUG_ON(sizeof(chip->needed_fw_elms) * 8 < RTW89_FW_ELEMENT_ID_NUM);
+
 	offset = rtw89_mfw_get_size(rtwdev);
 	offset = ALIGN(offset, RTW89_FW_ELEMENT_ALIGN);
 	if (offset == 0)
@@ -672,11 +676,18 @@ int rtw89_fw_recognize_elements(struct rtw89_dev *rtwdev)
 			rtw89_info(rtwdev, "Firmware element %s version: %4ph\n",
 				   handler->name, hdr->ver);
 
+		unrecognized_elements &= ~BIT(elem_id);
 next:
 		offset += sizeof(*hdr) + elm_size;
 		offset = ALIGN(offset, RTW89_FW_ELEMENT_ALIGN);
 	}
 
+	if (unrecognized_elements) {
+		rtw89_err(rtwdev, "Firmware elements 0x%08x are unrecognized\n",
+			  unrecognized_elements);
+		return -ENOENT;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index cbb130537e07d..775f4e8fbda4d 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -3412,6 +3412,8 @@ enum rtw89_fw_element_id {
 	RTW89_FW_ELEMENT_ID_RADIO_C = 6,
 	RTW89_FW_ELEMENT_ID_RADIO_D = 7,
 	RTW89_FW_ELEMENT_ID_RF_NCTL = 8,
+
+	RTW89_FW_ELEMENT_ID_NUM,
 };
 
 struct rtw89_fw_element_hdr {
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 456b8369fb068..b5740639e2679 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2339,6 +2339,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.fw_basename		= RTW8851B_FW_BASENAME,
 	.fw_format_max		= RTW8851B_FW_FORMAT_MAX,
 	.try_ce_fw		= true,
+	.needed_fw_elms		= 0,
 	.fifo_size		= 196608,
 	.small_fifo_size	= true,
 	.dle_scc_rsvd_size	= 98304,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 0fc5eb777a4aa..41f05276406d1 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2076,6 +2076,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.fw_basename		= RTW8852A_FW_BASENAME,
 	.fw_format_max		= RTW8852A_FW_FORMAT_MAX,
 	.try_ce_fw		= false,
+	.needed_fw_elms		= 0,
 	.fifo_size		= 458752,
 	.small_fifo_size	= false,
 	.dle_scc_rsvd_size	= 0,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index d76d74cc867ad..eb2210cb7e099 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -2508,6 +2508,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.fw_basename		= RTW8852B_FW_BASENAME,
 	.fw_format_max		= RTW8852B_FW_FORMAT_MAX,
 	.try_ce_fw		= true,
+	.needed_fw_elms		= 0,
 	.fifo_size		= 196608,
 	.small_fifo_size	= true,
 	.dle_scc_rsvd_size	= 98304,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index f269832b2bc6f..b1af72fbf0857 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2807,6 +2807,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.fw_basename		= RTW8852C_FW_BASENAME,
 	.fw_format_max		= RTW8852C_FW_FORMAT_MAX,
 	.try_ce_fw		= false,
+	.needed_fw_elms		= 0,
 	.fifo_size		= 458752,
 	.small_fifo_size	= false,
 	.dle_scc_rsvd_size	= 0,
-- 
GitLab


From c1e9e5e0b9cc25dbfb3a584951e6189b159f869f Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Wed, 2 Aug 2023 17:06:57 +0800
Subject: [PATCH 0850/1806] drivers: net: xgene: Do not check for 0 return
 after calling platform_get_irq()

It is not possible for platform_get_irq() to return 0. Use the
return value from platform_get_irq().

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Link: https://lore.kernel.org/r/20230802090657.969923-1-ruanjinjie@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 390671640388b..41d96f4b23d86 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -1632,7 +1632,7 @@ static int xgene_enet_get_irqs(struct xgene_enet_pdata *pdata)
 
 	for (i = 0; i < max_irqs; i++) {
 		ret = platform_get_irq(pdev, i);
-		if (ret <= 0) {
+		if (ret < 0) {
 			if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) {
 				max_irqs = i;
 				pdata->rxq_cnt = max_irqs / 2;
@@ -1640,7 +1640,7 @@ static int xgene_enet_get_irqs(struct xgene_enet_pdata *pdata)
 				pdata->cq_cnt = max_irqs / 2;
 				break;
 			}
-			return ret ? : -ENXIO;
+			return ret;
 		}
 		pdata->irqs[i] = ret;
 	}
-- 
GitLab


From 6abce66ba953a0f8ed97559709a2a567f95f560a Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Wed, 2 Aug 2023 16:52:16 +0800
Subject: [PATCH 0851/1806] net: gemini: Do not check for 0 return after
 calling platform_get_irq()

It is not possible for platform_get_irq() to return 0. Use the
return value from platform_get_irq().

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Link: https://lore.kernel.org/r/20230802085216.659238-1-ruanjinjie@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cortina/gemini.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 5715b9ab2712e..692cb2d04c1c7 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2415,8 +2415,8 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 
 	/* Interrupt */
 	irq = platform_get_irq(pdev, 0);
-	if (irq <= 0)
-		return irq ? irq : -ENODEV;
+	if (irq < 0)
+		return irq;
 	port->irq = irq;
 
 	/* Clock the port */
-- 
GitLab


From ce650a1663354a6cad7145e7f5131008458b39d4 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 2 Aug 2023 08:36:50 +0100
Subject: [PATCH 0852/1806] udp6: Fix __ip6_append_data()'s handling of
 MSG_SPLICE_PAGES

__ip6_append_data() can has a similar problem to __ip_append_data()[1] when
asked to splice into a partially-built UDP message that has more than the
frag-limit data and up to the MTU limit, but in the ipv6 case, it errors
out with EINVAL.  This can be triggered with something like:

        pipe(pfd);
        sfd = socket(AF_INET6, SOCK_DGRAM, 0);
        connect(sfd, ...);
        send(sfd, buffer, 8137, MSG_CONFIRM|MSG_MORE);
        write(pfd[1], buffer, 8);
        splice(pfd[0], 0, sfd, 0, 0x4ffe0ul, 0);

where the amount of data given to send() is dependent on the MTU size (in
this instance an interface with an MTU of 8192).

The problem is that the calculation of the amount to copy in
__ip6_append_data() goes negative in two places, but a check has been put
in to give an error in this case.

This happens because when pagedlen > 0 (which happens for MSG_ZEROCOPY and
MSG_SPLICE_PAGES), the terms in:

        copy = datalen - transhdrlen - fraggap - pagedlen;

then mostly cancel when pagedlen is substituted for, leaving just -fraggap.

Fix this by:

 (1) Insert a note about the dodgy calculation of 'copy'.

 (2) If MSG_SPLICE_PAGES, clear copy if it is negative from the above
     equation, so that 'offset' isn't regressed and 'length' isn't
     increased, which will mean that length and thus copy should match the
     amount left in the iterator.

 (3) When handling MSG_SPLICE_PAGES, give a warning and return -EIO if
     we're asked to splice more than is in the iterator.  It might be
     better to not give the warning or even just give a 'short' write.

 (4) If MSG_SPLICE_PAGES, override the copy<0 check.

[!] Note that this should also affect MSG_ZEROCOPY, but that will return
-EINVAL for the range of send sizes that requires the skbuff to be split.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: David Ahern <dsahern@kernel.org>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: netdev@vger.kernel.org
Link: https://lore.kernel.org/r/000000000000881d0606004541d1@google.com/ [1]
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/1580952.1690961810@warthog.procyon.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ip6_output.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1e8c90e976080..bc96559bbf0f8 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1693,7 +1693,10 @@ alloc_new_skb:
 			fraglen = datalen + fragheaderlen;
 
 			copy = datalen - transhdrlen - fraggap - pagedlen;
-			if (copy < 0) {
+			/* [!] NOTE: copy may be negative if pagedlen>0
+			 * because then the equation may reduces to -fraggap.
+			 */
+			if (copy < 0 && !(flags & MSG_SPLICE_PAGES)) {
 				err = -EINVAL;
 				goto error;
 			}
@@ -1744,6 +1747,8 @@ alloc_new_skb:
 				err = -EFAULT;
 				kfree_skb(skb);
 				goto error;
+			} else if (flags & MSG_SPLICE_PAGES) {
+				copy = 0;
 			}
 
 			offset += copy;
@@ -1791,6 +1796,10 @@ alloc_new_skb:
 		} else if (flags & MSG_SPLICE_PAGES) {
 			struct msghdr *msg = from;
 
+			err = -EIO;
+			if (WARN_ON_ONCE(copy > msg->msg_iter.count))
+				goto error;
+
 			err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
 						   sk->sk_allocation);
 			if (err < 0)
-- 
GitLab


From 918423fda910380a19a1bcadd858e3e42fb501bb Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@redhat.com>
Date: Tue, 1 Aug 2023 17:22:22 -0400
Subject: [PATCH 0853/1806] selftests: openvswitch: add an initial flow
 programming case

The openvswitch self-tests can test much of the control side of
the module (ie: what a vswitchd implementation would process),
but the actual packet forwarding cases aren't supported, making
the testing of limited value.

Add some flow parsing and an initial ARP based test case using
arping utility.  This lets us display flows, add some basic
output flows with simple matches, and test against a known good
forwarding case.

Signed-off-by: Aaron Conole <aconole@redhat.com>
Reviewed-by: Adrian Moreno <amorenoz@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/net/openvswitch/openvswitch.sh  |  51 +++
 .../selftests/net/openvswitch/ovs-dpctl.py    | 407 ++++++++++++++++++
 2 files changed, 458 insertions(+)

diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index 3117a4be0cd04..5cdacb3c8c925 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -11,6 +11,7 @@ VERBOSE=0
 TRACING=0
 
 tests="
+	arp_ping				eth-arp: Basic arp ping between two NS
 	netlink_checks				ovsnl: validate netlink attrs and settings
 	upcall_interfaces			ovs: test the upcall interfaces"
 
@@ -127,6 +128,16 @@ ovs_add_netns_and_veths () {
 	return 0
 }
 
+ovs_add_flow () {
+	info "Adding flow to DP: sbx:$1 br:$2 flow:$3 act:$4"
+	ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py add-flow "$2" "$3" "$4"
+	if [ $? -ne 0 ]; then
+		echo "Flow [ $3 : $4 ] failed" >> ${ovs_dir}/debug.log
+		return 1
+	fi
+	return 0
+}
+
 usage() {
 	echo
 	echo "$0 [OPTIONS] [TEST]..."
@@ -141,6 +152,46 @@ usage() {
 	exit 1
 }
 
+# arp_ping test
+# - client has 1500 byte MTU
+# - server has 1500 byte MTU
+# - send ARP ping between two ns
+test_arp_ping () {
+
+	which arping >/dev/null 2>&1 || return $ksft_skip
+
+	sbx_add "test_arp_ping" || return $?
+
+	ovs_add_dp "test_arp_ping" arpping || return 1
+
+	info "create namespaces"
+	for ns in client server; do
+		ovs_add_netns_and_veths "test_arp_ping" "arpping" "$ns" \
+		    "${ns:0:1}0" "${ns:0:1}1" || return 1
+	done
+
+	# Setup client namespace
+	ip netns exec client ip addr add 172.31.110.10/24 dev c1
+	ip netns exec client ip link set c1 up
+	HW_CLIENT=`ip netns exec client ip link show dev c1 | grep -E 'link/ether [0-9a-f:]+' | awk '{print $2;}'`
+	info "Client hwaddr: $HW_CLIENT"
+
+	# Setup server namespace
+	ip netns exec server ip addr add 172.31.110.20/24 dev s1
+	ip netns exec server ip link set s1 up
+	HW_SERVER=`ip netns exec server ip link show dev s1 | grep -E 'link/ether [0-9a-f:]+' | awk '{print $2;}'`
+	info "Server hwaddr: $HW_SERVER"
+
+	ovs_add_flow "test_arp_ping" arpping \
+		"in_port(1),eth(),eth_type(0x0806),arp(sip=172.31.110.10,tip=172.31.110.20,sha=$HW_CLIENT,tha=ff:ff:ff:ff:ff:ff)" '2' || return 1
+	ovs_add_flow "test_arp_ping" arpping \
+		"in_port(2),eth(),eth_type(0x0806),arp()" '1' || return 1
+
+	ovs_sbx "test_arp_ping" ip netns exec client arping -I c1 172.31.110.20 -c 1 || return 1
+
+	return 0
+}
+
 # netlink_validation
 # - Create a dp
 # - check no warning with "old version" simulation
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index 1c8b36bc15d48..27e15c636456e 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -9,9 +9,12 @@ import errno
 import ipaddress
 import logging
 import multiprocessing
+import re
 import struct
 import sys
 import time
+import types
+import uuid
 
 try:
     from pyroute2 import NDB
@@ -59,6 +62,104 @@ def macstr(mac):
     return outstr
 
 
+def strspn(str1, str2):
+    tot = 0
+    for char in str1:
+        if str2.find(char) == -1:
+            return tot
+        tot += 1
+    return tot
+
+
+def intparse(statestr, defmask="0xffffffff"):
+    totalparse = strspn(statestr, "0123456789abcdefABCDEFx/")
+    # scan until "/"
+    count = strspn(statestr, "x0123456789abcdefABCDEF")
+
+    firstnum = statestr[:count]
+    if firstnum[-1] == "/":
+        firstnum = firstnum[:-1]
+    k = int(firstnum, 0)
+
+    m = None
+    if defmask is not None:
+        secondnum = defmask
+        if statestr[count] == "/":
+            secondnum = statestr[count + 1 :]  # this is wrong...
+        m = int(secondnum, 0)
+
+    return statestr[totalparse + 1 :], k, m
+
+
+def parse_flags(flag_str, flag_vals):
+    bitResult = 0
+    maskResult = 0
+
+    if len(flag_str) == 0:
+        return flag_str, bitResult, maskResult
+
+    if flag_str[0].isdigit():
+        idx = 0
+        while flag_str[idx].isdigit() or flag_str[idx] == "x":
+            idx += 1
+        digits = flag_str[:idx]
+        flag_str = flag_str[idx:]
+
+        bitResult = int(digits, 0)
+        maskResult = int(digits, 0)
+
+    while len(flag_str) > 0 and (flag_str[0] == "+" or flag_str[0] == "-"):
+        if flag_str[0] == "+":
+            setFlag = True
+        elif flag_str[0] == "-":
+            setFlag = False
+
+        flag_str = flag_str[1:]
+
+        flag_len = 0
+        while (
+            flag_str[flag_len] != "+"
+            and flag_str[flag_len] != "-"
+            and flag_str[flag_len] != ","
+            and flag_str[flag_len] != ")"
+        ):
+            flag_len += 1
+
+        flag = flag_str[0:flag_len]
+
+        if flag in flag_vals:
+            if maskResult & flag_vals[flag]:
+                raise KeyError(
+                    "Flag %s set once, cannot be set in multiples" % flag
+                )
+
+            if setFlag:
+                bitResult |= flag_vals[flag]
+
+            maskResult |= flag_vals[flag]
+        else:
+            raise KeyError("Missing flag value: %s" % flag)
+
+        flag_str = flag_str[flag_len:]
+
+    return flag_str, bitResult, maskResult
+
+
+def parse_ct_state(statestr):
+    ct_flags = {
+        "new": 1 << 0,
+        "est": 1 << 1,
+        "rel": 1 << 2,
+        "rpl": 1 << 3,
+        "inv": 1 << 4,
+        "trk": 1 << 5,
+        "snat": 1 << 6,
+        "dnat": 1 << 7,
+    }
+
+    return parse_flags(statestr, ct_flags)
+
+
 def convert_mac(mac_str, mask=False):
     if mac_str is None or mac_str == "":
         mac_str = "00:00:00:00:00:00"
@@ -79,6 +180,62 @@ def convert_ipv4(ip, mask=False):
     return int(ipaddress.IPv4Address(ip))
 
 
+def parse_starts_block(block_str, scanstr, returnskipped, scanregex=False):
+    if scanregex:
+        m = re.search(scanstr, block_str)
+        if m is None:
+            if returnskipped:
+                return block_str
+            return False
+        if returnskipped:
+            block_str = block_str[len(m.group(0)) :]
+            return block_str
+        return True
+
+    if block_str.startswith(scanstr):
+        if returnskipped:
+            block_str = block_str[len(scanstr) :]
+        else:
+            return True
+
+    if returnskipped:
+        return block_str
+
+    return False
+
+
+def parse_extract_field(
+    block_str, fieldstr, scanfmt, convert, masked=False, defval=None
+):
+    if fieldstr and not block_str.startswith(fieldstr):
+        return block_str, defval
+
+    if fieldstr:
+        str_skiplen = len(fieldstr)
+        str_skipped = block_str[str_skiplen:]
+        if str_skiplen == 0:
+            return str_skipped, defval
+    else:
+        str_skiplen = 0
+        str_skipped = block_str
+
+    m = re.search(scanfmt, str_skipped)
+    if m is None:
+        raise ValueError("Bad fmt string")
+
+    data = m.group(0)
+    if convert:
+        data = convert(m.group(0))
+
+    str_skipped = str_skipped[len(m.group(0)) :]
+    if masked:
+        if str_skipped[0] == "/":
+            raise ValueError("Masking support TBD...")
+
+    str_skipped = str_skipped[strspn(str_skipped, ", ") :]
+    return str_skipped, data
+
+
 class ovs_dp_msg(genlmsg):
     # include the OVS version
     # We need a custom header rather than just being able to rely on
@@ -278,6 +435,50 @@ class ovsactions(nla):
 
         return print_str
 
+    def parse(self, actstr):
+        while len(actstr) != 0:
+            parsed = False
+            if actstr.startswith("drop"):
+                # for now, drops have no explicit action, so we
+                # don't need to set any attributes.  The final
+                # act of the processing chain will just drop the packet
+                return
+
+            elif parse_starts_block(actstr, "^(\d+)", False, True):
+                actstr, output = parse_extract_field(
+                    actstr, None, "(\d+)", lambda x: int(x), False, "0"
+                )
+                self["attrs"].append(["OVS_ACTION_ATTR_OUTPUT", output])
+                parsed = True
+            elif parse_starts_block(actstr, "recirc(", False):
+                actstr, recircid = parse_extract_field(
+                    actstr,
+                    "recirc(",
+                    "([0-9a-fA-Fx]+)",
+                    lambda x: int(x, 0),
+                    False,
+                    0,
+                )
+                self["attrs"].append(["OVS_ACTION_ATTR_RECIRC", recircid])
+                parsed = True
+
+            parse_flat_map = (
+                ("ct_clear", "OVS_ACTION_ATTR_CT_CLEAR"),
+                ("pop_vlan", "OVS_ACTION_ATTR_POP_VLAN"),
+                ("pop_eth", "OVS_ACTION_ATTR_POP_ETH"),
+                ("pop_nsh", "OVS_ACTION_ATTR_POP_NSH"),
+            )
+
+            for flat_act in parse_flat_map:
+                if parse_starts_block(actstr, flat_act[0], False):
+                    actstr += len(flat_act[0])
+                    self["attrs"].append([flat_act[1]])
+                    actstr = actstr[strspn(actstr, ", ") :]
+                    parsed = True
+
+            if not parsed:
+                raise ValueError("Action str: '%s' not supported" % actstr)
+
 
 class ovskey(nla):
     nla_flags = NLA_F_NESTED
@@ -347,6 +548,53 @@ class ovskey(nla):
                 init=init,
             )
 
+        def parse(self, flowstr, typeInst):
+            if not flowstr.startswith(self.proto_str):
+                return None, None
+
+            k = typeInst()
+            m = typeInst()
+
+            flowstr = flowstr[len(self.proto_str) :]
+            if flowstr.startswith("("):
+                flowstr = flowstr[1:]
+
+            keybits = b""
+            maskbits = b""
+            for f in self.fields_map:
+                if flowstr.startswith(f[1]):
+                    # the following assumes that the field looks
+                    # something like 'field.' where '.' is a
+                    # character that we don't exactly care about.
+                    flowstr = flowstr[len(f[1]) + 1 :]
+                    splitchar = 0
+                    for c in flowstr:
+                        if c == "," or c == ")":
+                            break
+                        splitchar += 1
+                    data = flowstr[:splitchar]
+                    flowstr = flowstr[splitchar:]
+                else:
+                    data = None
+
+                if len(f) > 4:
+                    func = f[4]
+                else:
+                    func = f[3]
+                k[f[0]] = func(data)
+                if len(f) > 4:
+                    m[f[0]] = func(data, True)
+                else:
+                    m[f[0]] = func(data)
+
+                flowstr = flowstr[strspn(flowstr, ", ") :]
+                if len(flowstr) == 0:
+                    return flowstr, k, m
+
+            flowstr = flowstr[strspn(flowstr, "), ") :]
+
+            return flowstr, k, m
+
         def dpstr(self, masked=None, more=False):
             outstr = self.proto_str + "("
             first = False
@@ -810,6 +1058,71 @@ class ovskey(nla):
     class ovs_key_mpls(nla):
         fields = (("lse", ">I"),)
 
+    def parse(self, flowstr, mask=None):
+        for field in (
+            ("OVS_KEY_ATTR_PRIORITY", "skb_priority", intparse),
+            ("OVS_KEY_ATTR_SKB_MARK", "skb_mark", intparse),
+            ("OVS_KEY_ATTR_RECIRC_ID", "recirc_id", intparse),
+            ("OVS_KEY_ATTR_DP_HASH", "dp_hash", intparse),
+            ("OVS_KEY_ATTR_CT_STATE", "ct_state", parse_ct_state),
+            ("OVS_KEY_ATTR_CT_ZONE", "ct_zone", intparse),
+            ("OVS_KEY_ATTR_CT_MARK", "ct_mark", intparse),
+            ("OVS_KEY_ATTR_IN_PORT", "in_port", intparse),
+            (
+                "OVS_KEY_ATTR_ETHERNET",
+                "eth",
+                ovskey.ethaddr,
+            ),
+            (
+                "OVS_KEY_ATTR_ETHERTYPE",
+                "eth_type",
+                lambda x: intparse(x, "0xffff"),
+            ),
+            (
+                "OVS_KEY_ATTR_IPV4",
+                "ipv4",
+                ovskey.ovs_key_ipv4,
+            ),
+            (
+                "OVS_KEY_ATTR_IPV6",
+                "ipv6",
+                ovskey.ovs_key_ipv6,
+            ),
+            (
+                "OVS_KEY_ATTR_ARP",
+                "arp",
+                ovskey.ovs_key_arp,
+            ),
+            (
+                "OVS_KEY_ATTR_TCP",
+                "tcp",
+                ovskey.ovs_key_tcp,
+            ),
+            (
+                "OVS_KEY_ATTR_TCP_FLAGS",
+                "tcp_flags",
+                lambda x: parse_flags(x, None),
+            ),
+        ):
+            fld = field[1] + "("
+            if not flowstr.startswith(fld):
+                continue
+
+            if not isinstance(field[2], types.FunctionType):
+                nk = field[2]()
+                flowstr, k, m = nk.parse(flowstr, field[2])
+            else:
+                flowstr = flowstr[len(fld) :]
+                flowstr, k, m = field[2](flowstr)
+
+            if m and mask is not None:
+                mask["attrs"].append([field[0], m])
+            self["attrs"].append([field[0], k])
+
+            flowstr = flowstr[strspn(flowstr, "),") :]
+
+        return flowstr
+
     def dpstr(self, mask=None, more=False):
         print_str = ""
 
@@ -1358,11 +1671,92 @@ class OvsFlow(GenericNetlinkSocket):
 
             return print_str
 
+        def parse(self, flowstr, actstr, dpidx=0):
+            OVS_UFID_F_OMIT_KEY = 1 << 0
+            OVS_UFID_F_OMIT_MASK = 1 << 1
+            OVS_UFID_F_OMIT_ACTIONS = 1 << 2
+
+            self["cmd"] = 0
+            self["version"] = 0
+            self["reserved"] = 0
+            self["dpifindex"] = 0
+
+            if flowstr.startswith("ufid:"):
+                count = 5
+                while flowstr[count] != ",":
+                    count += 1
+                ufidstr = flowstr[5:count]
+                flowstr = flowstr[count + 1 :]
+            else:
+                ufidstr = str(uuid.uuid4())
+            uuidRawObj = uuid.UUID(ufidstr).fields
+
+            self["attrs"].append(
+                [
+                    "OVS_FLOW_ATTR_UFID",
+                    [
+                        uuidRawObj[0],
+                        uuidRawObj[1] << 16 | uuidRawObj[2],
+                        uuidRawObj[3] << 24
+                        | uuidRawObj[4] << 16
+                        | uuidRawObj[5] & (0xFF << 32) >> 32,
+                        uuidRawObj[5] & (0xFFFFFFFF),
+                    ],
+                ]
+            )
+            self["attrs"].append(
+                [
+                    "OVS_FLOW_ATTR_UFID_FLAGS",
+                    int(
+                        OVS_UFID_F_OMIT_KEY
+                        | OVS_UFID_F_OMIT_MASK
+                        | OVS_UFID_F_OMIT_ACTIONS
+                    ),
+                ]
+            )
+
+            k = ovskey()
+            m = ovskey()
+            k.parse(flowstr, m)
+            self["attrs"].append(["OVS_FLOW_ATTR_KEY", k])
+            self["attrs"].append(["OVS_FLOW_ATTR_MASK", m])
+
+            a = ovsactions()
+            a.parse(actstr)
+            self["attrs"].append(["OVS_FLOW_ATTR_ACTIONS", a])
+
     def __init__(self):
         GenericNetlinkSocket.__init__(self)
 
         self.bind(OVS_FLOW_FAMILY, OvsFlow.ovs_flow_msg)
 
+    def add_flow(self, dpifindex, flowmsg):
+        """
+        Send a new flow message to the kernel.
+
+        dpifindex should be a valid datapath obtained by calling
+        into the OvsDatapath lookup
+
+        flowmsg is a flow object obtained by calling a dpparse
+        """
+
+        flowmsg["cmd"] = OVS_FLOW_CMD_NEW
+        flowmsg["version"] = OVS_DATAPATH_VERSION
+        flowmsg["reserved"] = 0
+        flowmsg["dpifindex"] = dpifindex
+
+        try:
+            reply = self.nlm_request(
+                flowmsg,
+                msg_type=self.prid,
+                msg_flags=NLM_F_REQUEST | NLM_F_ACK,
+            )
+            reply = reply[0]
+        except NetlinkError as ne:
+            print(flowmsg)
+            raise ne
+        return reply
+
     def dump(self, dpifindex, flowspec=None):
         """
         Returns a list of messages containing flows.
@@ -1514,6 +1908,11 @@ def main(argv):
     dumpflcmd = subparsers.add_parser("dump-flows")
     dumpflcmd.add_argument("dumpdp", help="Datapath Name")
 
+    addflcmd = subparsers.add_parser("add-flow")
+    addflcmd.add_argument("flbr", help="Datapath name")
+    addflcmd.add_argument("flow", help="Flow specification")
+    addflcmd.add_argument("acts", help="Flow actions")
+
     args = parser.parse_args()
 
     if args.verbose > 0:
@@ -1589,6 +1988,14 @@ def main(argv):
         rep = ovsflow.dump(rep["dpifindex"])
         for flow in rep:
             print(flow.dpstr(True if args.verbose > 0 else False))
+    elif hasattr(args, "flbr"):
+        rep = ovsdp.info(args.flbr, 0)
+        if rep is None:
+            print("DP '%s' not found." % args.flbr)
+            return 1
+        flow = OvsFlow.ovs_flow_msg()
+        flow.parse(args.flow, args.acts, rep["dpifindex"])
+        ovsflow.add_flow(rep["dpifindex"], flow)
 
     return 0
 
-- 
GitLab


From 9f1179fbbd84d5269f57659152e24bd4b03fd095 Mon Sep 17 00:00:00 2001
From: Adrian Moreno <amorenoz@redhat.com>
Date: Tue, 1 Aug 2023 17:22:23 -0400
Subject: [PATCH 0854/1806] selftests: openvswitch: support key masks

The default value for the mask actually depends on the value (e.g: if
the value is non-null, the default is full-mask), so change the convert
functions to accept the full, possibly masked string and let them figure
out how to parse the different values.

Also, implement size-aware int parsing.

With this patch we can now express flows such as the following:
"eth(src=0a:ca:fe:ca:fe:0a/ff:ff:00:00:ff:00)"
"eth(src=0a:ca:fe:ca:fe:0a)" -> mask = ff:ff:ff:ff:ff:ff
"ipv4(src=192.168.1.1)" -> mask = 255.255.255.255
"ipv4(src=192.168.1.1/24)"
"ipv4(src=192.168.1.1/255.255.255.0)"
"tcp(src=8080)" -> mask = 0xffff
"tcp(src=8080/0xf0f0)"

Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Acked-by: Aaron Conole <aconole@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/net/openvswitch/ovs-dpctl.py    | 96 ++++++++++++-------
 1 file changed, 64 insertions(+), 32 deletions(-)

diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index 27e15c636456e..a9b8f52f6bfea 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -160,25 +160,45 @@ def parse_ct_state(statestr):
     return parse_flags(statestr, ct_flags)
 
 
-def convert_mac(mac_str, mask=False):
-    if mac_str is None or mac_str == "":
-        mac_str = "00:00:00:00:00:00"
-    if mask is True and mac_str != "00:00:00:00:00:00":
-        mac_str = "FF:FF:FF:FF:FF:FF"
-    mac_split = mac_str.split(":")
-    ret = bytearray([int(i, 16) for i in mac_split])
-    return bytes(ret)
+def convert_mac(data):
+    def to_bytes(mac):
+        mac_split = mac.split(":")
+        ret = bytearray([int(i, 16) for i in mac_split])
+        return bytes(ret)
 
+    mac_str, _, mask_str = data.partition('/')
 
-def convert_ipv4(ip, mask=False):
-    if ip is None:
-        ip = 0
-    if mask is True:
-        if ip != 0:
-            ip = int(ipaddress.IPv4Address(ip)) & 0xFFFFFFFF
+    if not mac_str:
+        mac_str = mask_str = "00:00:00:00:00:00"
+    elif not mask_str:
+        mask_str = "FF:FF:FF:FF:FF:FF"
 
-    return int(ipaddress.IPv4Address(ip))
+    return to_bytes(mac_str), to_bytes(mask_str)
 
+def convert_ipv4(data):
+    ip, _, mask = data.partition('/')
+
+    if not ip:
+        ip = mask = 0
+    elif not mask:
+        mask = 0xFFFFFFFF
+    elif mask.isdigit():
+        mask = (0xFFFFFFFF << (32 - int(mask))) & 0xFFFFFFFF
+
+    return int(ipaddress.IPv4Address(ip)), int(ipaddress.IPv4Address(mask))
+
+def convert_int(size):
+    def convert_int_sized(data):
+        value, _, mask = data.partition('/')
+
+        if not value:
+            return 0, 0
+        elif not mask:
+            return int(value, 0), pow(2, size) - 1
+        else:
+            return int(value, 0), int(mask, 0)
+
+    return convert_int_sized
 
 def parse_starts_block(block_str, scanstr, returnskipped, scanregex=False):
     if scanregex:
@@ -525,8 +545,10 @@ class ovskey(nla):
         )
 
         fields_map = (
-            ("src", "src", "%d", lambda x: int(x) if x is not None else 0),
-            ("dst", "dst", "%d", lambda x: int(x) if x is not None else 0),
+            ("src", "src", "%d", lambda x: int(x) if x else 0,
+                convert_int(16)),
+            ("dst", "dst", "%d", lambda x: int(x) if x else 0,
+                convert_int(16)),
         )
 
         def __init__(
@@ -575,17 +597,13 @@ class ovskey(nla):
                     data = flowstr[:splitchar]
                     flowstr = flowstr[splitchar:]
                 else:
-                    data = None
+                    data = ""
 
                 if len(f) > 4:
-                    func = f[4]
-                else:
-                    func = f[3]
-                k[f[0]] = func(data)
-                if len(f) > 4:
-                    m[f[0]] = func(data, True)
+                    k[f[0]], m[f[0]] = f[4](data)
                 else:
-                    m[f[0]] = func(data)
+                    k[f[0]] = f[3](data)
+                    m[f[0]] = f[3](data)
 
                 flowstr = flowstr[strspn(flowstr, ", ") :]
                 if len(flowstr) == 0:
@@ -689,10 +707,14 @@ class ovskey(nla):
                 int,
                 convert_ipv4,
             ),
-            ("proto", "proto", "%d", lambda x: int(x) if x is not None else 0),
-            ("tos", "tos", "%d", lambda x: int(x) if x is not None else 0),
-            ("ttl", "ttl", "%d", lambda x: int(x) if x is not None else 0),
-            ("frag", "frag", "%d", lambda x: int(x) if x is not None else 0),
+            ("proto", "proto", "%d", lambda x: int(x) if x else 0,
+                convert_int(8)),
+            ("tos", "tos", "%d", lambda x: int(x) if x else 0,
+                convert_int(8)),
+            ("ttl", "ttl", "%d", lambda x: int(x) if x else 0,
+                convert_int(8)),
+            ("frag", "frag", "%d", lambda x: int(x) if x else 0,
+                convert_int(8)),
         )
 
         def __init__(
@@ -828,8 +850,8 @@ class ovskey(nla):
         )
 
         fields_map = (
-            ("type", "type", "%d", int),
-            ("code", "code", "%d", int),
+            ("type", "type", "%d", lambda x: int(x) if x else 0),
+            ("code", "code", "%d", lambda x: int(x) if x else 0),
         )
 
         def __init__(
@@ -894,7 +916,7 @@ class ovskey(nla):
                 int,
                 convert_ipv4,
             ),
-            ("op", "op", "%d", lambda x: int(x) if x is not None else 0),
+            ("op", "op", "%d", lambda x: int(x) if x else 0),
             (
                 "sha",
                 "sha",
@@ -1098,6 +1120,16 @@ class ovskey(nla):
                 "tcp",
                 ovskey.ovs_key_tcp,
             ),
+            (
+                "OVS_KEY_ATTR_UDP",
+                "udp",
+                ovskey.ovs_key_udp,
+            ),
+            (
+                "OVS_KEY_ATTR_ICMP",
+                "icmp",
+                ovskey.ovs_key_icmp,
+            ),
             (
                 "OVS_KEY_ATTR_TCP_FLAGS",
                 "tcp_flags",
-- 
GitLab


From 05398aa4095360e8bd85a4beb64e0aec47ebfd3e Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@redhat.com>
Date: Tue, 1 Aug 2023 17:22:24 -0400
Subject: [PATCH 0855/1806] selftests: openvswitch: add a test for ipv4
 forwarding

This is a simple ipv4 bidirectional connectivity test.

Signed-off-by: Aaron Conole <aconole@redhat.com>
Reviewed-by: Adrian Moreno <amorenoz@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/net/openvswitch/openvswitch.sh  | 40 +++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index 5cdacb3c8c925..5d60a9466dab3 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -12,6 +12,7 @@ TRACING=0
 
 tests="
 	arp_ping				eth-arp: Basic arp ping between two NS
+	connect_v4				ip4-xon: Basic ipv4 ping between two NS
 	netlink_checks				ovsnl: validate netlink attrs and settings
 	upcall_interfaces			ovs: test the upcall interfaces"
 
@@ -192,6 +193,45 @@ test_arp_ping () {
 	return 0
 }
 
+# connect_v4 test
+#  - client has 1500 byte MTU
+#  - server has 1500 byte MTU
+#  - use ICMP to ping in each direction
+test_connect_v4 () {
+
+	sbx_add "test_connect_v4" || return $?
+
+	ovs_add_dp "test_connect_v4" cv4 || return 1
+
+	info "create namespaces"
+	for ns in client server; do
+		ovs_add_netns_and_veths "test_connect_v4" "cv4" "$ns" \
+		    "${ns:0:1}0" "${ns:0:1}1" || return 1
+	done
+
+
+	ip netns exec client ip addr add 172.31.110.10/24 dev c1
+	ip netns exec client ip link set c1 up
+	ip netns exec server ip addr add 172.31.110.20/24 dev s1
+	ip netns exec server ip link set s1 up
+
+	# Add forwarding for ARP and ip packets - completely wildcarded
+	ovs_add_flow "test_connect_v4" cv4 \
+		'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1
+	ovs_add_flow "test_connect_v4" cv4 \
+		'in_port(2),eth(),eth_type(0x0806),arp()' '1' || return 1
+	ovs_add_flow "test_connect_v4" cv4 \
+		'in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10)' '2' || return 1
+	ovs_add_flow "test_connect_v4" cv4 \
+		'in_port(2),eth(),eth_type(0x0800),ipv4(src=172.31.110.20)' '1' || return 1
+
+	# do a ping
+	ovs_sbx "test_connect_v4" ip netns exec client ping 172.31.110.20 -c 3 || return 1
+
+	info "done..."
+	return 0
+}
+
 # netlink_validation
 # - Create a dp
 # - check no warning with "old version" simulation
-- 
GitLab


From 2893ba9c1d1a4f62b03db77aa8cbc00464fe41c5 Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@redhat.com>
Date: Tue, 1 Aug 2023 17:22:25 -0400
Subject: [PATCH 0856/1806] selftests: openvswitch: add basic ct test case
 parsing

Forwarding via ct() action is an important use case for openvswitch, but
generally would require using a full ovs-vswitchd to get working. Add a
ct action parser for basic ct test case.

Signed-off-by: Aaron Conole <aconole@redhat.com>
Reviewed-by: Adrian Moreno <amorenoz@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/net/openvswitch/openvswitch.sh  | 68 +++++++++++++++++++
 .../selftests/net/openvswitch/ovs-dpctl.py    | 39 +++++++++++
 2 files changed, 107 insertions(+)

diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index 5d60a9466dab3..40a66c72af0f0 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -12,6 +12,7 @@ TRACING=0
 
 tests="
 	arp_ping				eth-arp: Basic arp ping between two NS
+	ct_connect_v4				ip4-ct-xon: Basic ipv4 tcp connection using ct
 	connect_v4				ip4-xon: Basic ipv4 ping between two NS
 	netlink_checks				ovsnl: validate netlink attrs and settings
 	upcall_interfaces			ovs: test the upcall interfaces"
@@ -193,6 +194,73 @@ test_arp_ping () {
 	return 0
 }
 
+# ct_connect_v4 test
+#  - client has 1500 byte MTU
+#  - server has 1500 byte MTU
+#  - use ICMP to ping in each direction
+#  - only allow CT state stuff to pass through new in c -> s
+test_ct_connect_v4 () {
+
+	which nc >/dev/null 2>/dev/null || return $ksft_skip
+
+	sbx_add "test_ct_connect_v4" || return $?
+
+	ovs_add_dp "test_ct_connect_v4" ct4 || return 1
+	info "create namespaces"
+	for ns in client server; do
+		ovs_add_netns_and_veths "test_ct_connect_v4" "ct4" "$ns" \
+		    "${ns:0:1}0" "${ns:0:1}1" || return 1
+	done
+
+	ip netns exec client ip addr add 172.31.110.10/24 dev c1
+	ip netns exec client ip link set c1 up
+	ip netns exec server ip addr add 172.31.110.20/24 dev s1
+	ip netns exec server ip link set s1 up
+
+	# Add forwarding for ARP and ip packets - completely wildcarded
+	ovs_add_flow "test_ct_connect_v4" ct4 \
+		'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1
+	ovs_add_flow "test_ct_connect_v4" ct4 \
+		'in_port(2),eth(),eth_type(0x0806),arp()' '1' || return 1
+	ovs_add_flow "test_ct_connect_v4" ct4 \
+		     'ct_state(-trk),eth(),eth_type(0x0800),ipv4()' \
+		     'ct(commit),recirc(0x1)' || return 1
+	ovs_add_flow "test_ct_connect_v4" ct4 \
+		     'recirc_id(0x1),ct_state(+trk+new),in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10)' \
+		     '2' || return 1
+	ovs_add_flow "test_ct_connect_v4" ct4 \
+		     'recirc_id(0x1),ct_state(+trk+est),in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10)' \
+		     '2' || return 1
+	ovs_add_flow "test_ct_connect_v4" ct4 \
+		     'recirc_id(0x1),ct_state(+trk+est),in_port(2),eth(),eth_type(0x0800),ipv4(dst=172.31.110.10)' \
+		     '1' || return 1
+	ovs_add_flow "test_ct_connect_v4" ct4 \
+		     'recirc_id(0x1),ct_state(+trk+inv),eth(),eth_type(0x0800),ipv4()' 'drop' || \
+		     return 1
+
+	# do a ping
+	ovs_sbx "test_ct_connect_v4" ip netns exec client ping 172.31.110.20 -c 3 || return 1
+
+	# create an echo server in 'server'
+	echo "server" | \
+		ovs_netns_spawn_daemon "test_ct_connect_v4" "server" \
+				nc -lvnp 4443
+	ovs_sbx "test_ct_connect_v4" ip netns exec client nc -i 1 -zv 172.31.110.20 4443 || return 1
+
+	# Now test in the other direction (should fail)
+	echo "client" | \
+		ovs_netns_spawn_daemon "test_ct_connect_v4" "client" \
+				nc -lvnp 4443
+	ovs_sbx "test_ct_connect_v4" ip netns exec client nc -i 1 -zv 172.31.110.10 4443
+	if [ $? == 0 ]; then
+	   info "ct connect to client was successful"
+	   return 1
+	fi
+
+	info "done..."
+	return 0
+}
+
 # connect_v4 test
 #  - client has 1500 byte MTU
 #  - server has 1500 byte MTU
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index a9b8f52f6bfea..1a3dc3762361b 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -62,6 +62,15 @@ def macstr(mac):
     return outstr
 
 
+def strcspn(str1, str2):
+    tot = 0
+    for char in str1:
+        if str2.find(char) != -1:
+            return tot
+        tot += 1
+    return tot
+
+
 def strspn(str1, str2):
     tot = 0
     for char in str1:
@@ -496,6 +505,36 @@ class ovsactions(nla):
                     actstr = actstr[strspn(actstr, ", ") :]
                     parsed = True
 
+            if parse_starts_block(actstr, "ct(", False):
+                actstr = actstr[len("ct(") :]
+                ctact = ovsactions.ctact()
+
+                for scan in (
+                    ("commit", "OVS_CT_ATTR_COMMIT", None),
+                    ("force_commit", "OVS_CT_ATTR_FORCE_COMMIT", None),
+                    ("zone", "OVS_CT_ATTR_ZONE", int),
+                    ("mark", "OVS_CT_ATTR_MARK", int),
+                    ("helper", "OVS_CT_ATTR_HELPER", lambda x, y: str(x)),
+                    ("timeout", "OVS_CT_ATTR_TIMEOUT", lambda x, y: str(x)),
+                ):
+                    if actstr.startswith(scan[0]):
+                        actstr = actstr[len(scan[0]) :]
+                        if scan[2] is not None:
+                            if actstr[0] != "=":
+                                raise ValueError("Invalid ct attr")
+                            actstr = actstr[1:]
+                            pos = strcspn(actstr, ",)")
+                            datum = scan[2](actstr[:pos], 0)
+                            ctact["attrs"].append([scan[1], datum])
+                            actstr = actstr[pos:]
+                        else:
+                            ctact["attrs"].append([scan[1], None])
+                        actstr = actstr[strspn(actstr, ", ") :]
+
+                self["attrs"].append(["OVS_ACTION_ATTR_CT", ctact])
+                parsed = True
+
+            actstr = actstr[strspn(actstr, "), ") :]
             if not parsed:
                 raise ValueError("Action str: '%s' not supported" % actstr)
 
-- 
GitLab


From 60f10077eec6f0255463dc1726c71d5fad1c27ce Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@redhat.com>
Date: Tue, 1 Aug 2023 17:22:26 -0400
Subject: [PATCH 0857/1806] selftests: openvswitch: add ct-nat test case with
 ipv4

Building on the previous work, add a very simplistic NAT case
using ipv4.  This just tests dnat transformation

Signed-off-by: Aaron Conole <aconole@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/net/openvswitch/openvswitch.sh  | 64 +++++++++++++++++++
 .../selftests/net/openvswitch/ovs-dpctl.py    | 62 ++++++++++++++++++
 2 files changed, 126 insertions(+)

diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index 40a66c72af0f0..dced4f612a78c 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -14,6 +14,7 @@ tests="
 	arp_ping				eth-arp: Basic arp ping between two NS
 	ct_connect_v4				ip4-ct-xon: Basic ipv4 tcp connection using ct
 	connect_v4				ip4-xon: Basic ipv4 ping between two NS
+	nat_connect_v4				ip4-nat-xon: Basic ipv4 tcp connection via NAT
 	netlink_checks				ovsnl: validate netlink attrs and settings
 	upcall_interfaces			ovs: test the upcall interfaces"
 
@@ -300,6 +301,69 @@ test_connect_v4 () {
 	return 0
 }
 
+# nat_connect_v4 test
+#  - client has 1500 byte MTU
+#  - server has 1500 byte MTU
+#  - use ICMP to ping in each direction
+#  - only allow CT state stuff to pass through new in c -> s
+test_nat_connect_v4 () {
+	which nc >/dev/null 2>/dev/null || return $ksft_skip
+
+	sbx_add "test_nat_connect_v4" || return $?
+
+	ovs_add_dp "test_nat_connect_v4" nat4 || return 1
+	info "create namespaces"
+	for ns in client server; do
+		ovs_add_netns_and_veths "test_nat_connect_v4" "nat4" "$ns" \
+		    "${ns:0:1}0" "${ns:0:1}1" || return 1
+	done
+
+	ip netns exec client ip addr add 172.31.110.10/24 dev c1
+	ip netns exec client ip link set c1 up
+	ip netns exec server ip addr add 172.31.110.20/24 dev s1
+	ip netns exec server ip link set s1 up
+
+	ip netns exec client ip route add default via 172.31.110.20
+
+	ovs_add_flow "test_nat_connect_v4" nat4 \
+		'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1
+	ovs_add_flow "test_nat_connect_v4" nat4 \
+		'in_port(2),eth(),eth_type(0x0806),arp()' '1' || return 1
+	ovs_add_flow "test_nat_connect_v4" nat4 \
+		"ct_state(-trk),in_port(1),eth(),eth_type(0x0800),ipv4(dst=192.168.0.20)" \
+		"ct(commit,nat(dst=172.31.110.20)),recirc(0x1)"
+	ovs_add_flow "test_nat_connect_v4" nat4 \
+		"ct_state(-trk),in_port(2),eth(),eth_type(0x0800),ipv4()" \
+		"ct(commit,nat),recirc(0x2)"
+
+	ovs_add_flow "test_nat_connect_v4" nat4 \
+		"recirc_id(0x1),ct_state(+trk-inv),in_port(1),eth(),eth_type(0x0800),ipv4()" "2"
+	ovs_add_flow "test_nat_connect_v4" nat4 \
+		"recirc_id(0x2),ct_state(+trk-inv),in_port(2),eth(),eth_type(0x0800),ipv4()" "1"
+
+	# do a ping
+	ovs_sbx "test_nat_connect_v4" ip netns exec client ping 192.168.0.20 -c 3 || return 1
+
+	# create an echo server in 'server'
+	echo "server" | \
+		ovs_netns_spawn_daemon "test_nat_connect_v4" "server" \
+				nc -lvnp 4443
+	ovs_sbx "test_nat_connect_v4" ip netns exec client nc -i 1 -zv 192.168.0.20 4443 || return 1
+
+	# Now test in the other direction (should fail)
+	echo "client" | \
+		ovs_netns_spawn_daemon "test_nat_connect_v4" "client" \
+				nc -lvnp 4443
+	ovs_sbx "test_nat_connect_v4" ip netns exec client nc -i 1 -zv 172.31.110.10 4443
+	if [ $? == 0 ]; then
+	   info "connect to client was successful"
+	   return 1
+	fi
+
+	info "done..."
+	return 0
+}
+
 # netlink_validation
 # - Create a dp
 # - check no warning with "old version" simulation
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index 1a3dc3762361b..fbdac15e31344 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -530,6 +530,68 @@ class ovsactions(nla):
                         else:
                             ctact["attrs"].append([scan[1], None])
                         actstr = actstr[strspn(actstr, ", ") :]
+                    # it seems strange to put this here, but nat() is a complex
+                    # sub-action and this lets it sit anywhere in the ct() action
+                    if actstr.startswith("nat"):
+                        actstr = actstr[3:]
+                        natact = ovsactions.ctact.natattr()
+
+                        if actstr.startswith("("):
+                            t = None
+                            actstr = actstr[1:]
+                            if actstr.startswith("src"):
+                                t = "OVS_NAT_ATTR_SRC"
+                                actstr = actstr[3:]
+                            elif actstr.startswith("dst"):
+                                t = "OVS_NAT_ATTR_DST"
+                                actstr = actstr[3:]
+
+                            actstr, ip_block_min = parse_extract_field(
+                                actstr, "=", "([0-9a-fA-F\.]+)", str, False
+                            )
+                            actstr, ip_block_max = parse_extract_field(
+                                actstr, "-", "([0-9a-fA-F\.]+)", str, False
+                            )
+
+                            actstr, proto_min = parse_extract_field(
+                                actstr, ":", "(\d+)", int, False
+                            )
+                            actstr, proto_max = parse_extract_field(
+                                actstr, "-", "(\d+)", int, False
+                            )
+
+                            if t is not None:
+                                natact["attrs"].append([t, None])
+
+                                if ip_block_min is not None:
+                                    natact["attrs"].append(
+                                        ["OVS_NAT_ATTR_IP_MIN", ip_block_min]
+                                    )
+                                if ip_block_max is not None:
+                                    natact["attrs"].append(
+                                        ["OVS_NAT_ATTR_IP_MAX", ip_block_max]
+                                    )
+                                if proto_min is not None:
+                                    natact["attrs"].append(
+                                        ["OVS_NAT_ATTR_PROTO_MIN", proto_min]
+                                    )
+                                if proto_max is not None:
+                                    natact["attrs"].append(
+                                        ["OVS_NAT_ATTR_PROTO_MAX", proto_max]
+                                    )
+
+                            for natscan in (
+                                ("persistent", "OVS_NAT_ATTR_PERSISTENT"),
+                                ("hash", "OVS_NAT_ATTR_PROTO_HASH"),
+                                ("random", "OVS_NAT_ATTR_PROTO_RANDOM"),
+                            ):
+                                if actstr.startswith(natscan[0]):
+                                    actstr = actstr[len(natscan[0]) :]
+                                    natact["attrs"].append([natscan[1], None])
+                                    actstr = actstr[strspn(actstr, ", ") :]
+
+                        ctact["attrs"].append(["OVS_CT_ATTR_NAT", natact])
+                        actstr = actstr[strspn(actstr, ",) ") :]
 
                 self["attrs"].append(["OVS_ACTION_ATTR_CT", ctact])
                 parsed = True
-- 
GitLab


From 3986892646de95b916f6bf1c22b35dd2a3b3715a Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Wed, 2 Aug 2023 12:00:26 +0800
Subject: [PATCH 0858/1806] net/mlx4: Remove many unnecessary NULL values

The NULL initialization of the pointers assigned by kzalloc() first is
not necessary, because if the kzalloc() failed, the pointers will be
assigned NULL, otherwise it works as usual. so remove it.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230802040026.2588675-1-ruanjinjie@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 10 +++++-----
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c  |  4 ++--
 drivers/net/ethernet/mellanox/mlx4/main.c       |  8 ++++----
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 7d45f1d55f799..164a13272faa2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1467,8 +1467,8 @@ static int add_ip_rule(struct mlx4_en_priv *priv,
 		       struct list_head *list_h)
 {
 	int err;
-	struct mlx4_spec_list *spec_l2 = NULL;
-	struct mlx4_spec_list *spec_l3 = NULL;
+	struct mlx4_spec_list *spec_l2;
+	struct mlx4_spec_list *spec_l3;
 	struct ethtool_usrip4_spec *l3_mask = &cmd->fs.m_u.usr_ip4_spec;
 
 	spec_l3 = kzalloc(sizeof(*spec_l3), GFP_KERNEL);
@@ -1505,9 +1505,9 @@ static int add_tcp_udp_rule(struct mlx4_en_priv *priv,
 			     struct list_head *list_h, int proto)
 {
 	int err;
-	struct mlx4_spec_list *spec_l2 = NULL;
-	struct mlx4_spec_list *spec_l3 = NULL;
-	struct mlx4_spec_list *spec_l4 = NULL;
+	struct mlx4_spec_list *spec_l2;
+	struct mlx4_spec_list *spec_l3;
+	struct mlx4_spec_list *spec_l4;
 	struct ethtool_tcpip4_spec *l4_mask = &cmd->fs.m_u.tcp_ip4_spec;
 
 	spec_l2 = kzalloc(sizeof(*spec_l2), GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index e11bc0ac880e6..403604ceebc8f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -291,7 +291,7 @@ mlx4_en_filter_alloc(struct mlx4_en_priv *priv, int rxq_index, __be32 src_ip,
 		     __be32 dst_ip, u8 ip_proto, __be16 src_port,
 		     __be16 dst_port, u32 flow_id)
 {
-	struct mlx4_en_filter *filter = NULL;
+	struct mlx4_en_filter *filter;
 
 	filter = kzalloc(sizeof(struct mlx4_en_filter), GFP_ATOMIC);
 	if (!filter)
@@ -2935,7 +2935,7 @@ static void mlx4_en_bond_work(struct work_struct *work)
 static int mlx4_en_queue_bond_work(struct mlx4_en_priv *priv, int is_bonded,
 				   u8 v2p_p1, u8 v2p_p2)
 {
-	struct mlx4_en_bond *bond = NULL;
+	struct mlx4_en_bond *bond;
 
 	bond = kzalloc(sizeof(*bond), GFP_ATOMIC);
 	if (!bond)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 61286b0d9b0cb..8a5409b00530f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -864,7 +864,7 @@ static void mlx4_slave_destroy_special_qp_cap(struct mlx4_dev *dev)
 
 static int mlx4_slave_special_qp_cap(struct mlx4_dev *dev)
 {
-	struct mlx4_func_cap *func_cap = NULL;
+	struct mlx4_func_cap *func_cap;
 	struct mlx4_caps *caps = &dev->caps;
 	int i, err = 0;
 
@@ -908,9 +908,9 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 {
 	int			   err;
 	u32			   page_size;
-	struct mlx4_dev_cap	   *dev_cap = NULL;
-	struct mlx4_func_cap	   *func_cap = NULL;
-	struct mlx4_init_hca_param *hca_param = NULL;
+	struct mlx4_dev_cap	   *dev_cap;
+	struct mlx4_func_cap	   *func_cap;
+	struct mlx4_init_hca_param *hca_param;
 
 	hca_param = kzalloc(sizeof(*hca_param), GFP_KERNEL);
 	func_cap = kzalloc(sizeof(*func_cap), GFP_KERNEL);
-- 
GitLab


From 92272ec4107ef4f826b694a1338562c007e09821 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 2 Aug 2023 18:02:28 -0700
Subject: [PATCH 0859/1806] eth: add missing xdp.h includes in drivers

Handful of drivers currently expect to get xdp.h by virtue
of including netdevice.h. This will soon no longer be the case
so add explicit includes.

Reviewed-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20230803010230.1755386-2-kuba@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 drivers/net/bonding/bond_main.c                       | 1 +
 drivers/net/ethernet/amazon/ena/ena_netdev.h          | 1 +
 drivers/net/ethernet/engleder/tsnep.h                 | 1 +
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h      | 1 +
 drivers/net/ethernet/freescale/enetc/enetc.h          | 1 +
 drivers/net/ethernet/freescale/fec.h                  | 1 +
 drivers/net/ethernet/fungible/funeth/funeth_txrx.h    | 1 +
 drivers/net/ethernet/google/gve/gve.h                 | 1 +
 drivers/net/ethernet/intel/igc/igc.h                  | 1 +
 drivers/net/ethernet/microchip/lan966x/lan966x_main.h | 1 +
 drivers/net/ethernet/microsoft/mana/mana_en.c         | 1 +
 drivers/net/ethernet/stmicro/stmmac/stmmac.h          | 1 +
 drivers/net/ethernet/ti/cpsw_priv.h                   | 1 +
 drivers/net/hyperv/hyperv_net.h                       | 1 +
 drivers/net/tap.c                                     | 1 +
 include/net/mana/mana.h                               | 2 ++
 16 files changed, 17 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7a0f25301f7ec..2f21cca4fdaf7 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -90,6 +90,7 @@
 #include <net/tls.h>
 #endif
 #include <net/ip6_route.h>
+#include <net/xdp.h>
 
 #include "bonding_priv.h"
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 248b715b4d68d..33c923e1261a3 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -14,6 +14,7 @@
 #include <linux/interrupt.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <net/xdp.h>
 #include <uapi/linux/bpf.h>
 
 #include "ena_com.h"
diff --git a/drivers/net/ethernet/engleder/tsnep.h b/drivers/net/ethernet/engleder/tsnep.h
index 11b29f56aaf9c..6e14c918e3fb7 100644
--- a/drivers/net/ethernet/engleder/tsnep.h
+++ b/drivers/net/ethernet/engleder/tsnep.h
@@ -14,6 +14,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/miscdevice.h>
+#include <net/xdp.h>
 
 #define TSNEP "tsnep"
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index d56d7a13262ed..bfb6c96c3b2f0 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -12,6 +12,7 @@
 #include <linux/fsl/mc.h>
 #include <linux/net_tstamp.h>
 #include <net/devlink.h>
+#include <net/xdp.h>
 
 #include <soc/fsl/dpaa2-io.h>
 #include <soc/fsl/dpaa2-fd.h>
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 8577cf7699a04..7439739cd81a2 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -11,6 +11,7 @@
 #include <linux/if_vlan.h>
 #include <linux/phylink.h>
 #include <linux/dim.h>
+#include <net/xdp.h>
 
 #include "enetc_hw.h"
 
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 8f1edcca96c49..5a0974e62f994 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -22,6 +22,7 @@
 #include <linux/timecounter.h>
 #include <dt-bindings/firmware/imx/rsrc.h>
 #include <linux/firmware/imx/sci.h>
+#include <net/xdp.h>
 
 #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
     defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
index 53b7e95213a85..5eec552a1f24d 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
+++ b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
@@ -5,6 +5,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
 
 /* Tx descriptor size */
 #define FUNETH_SQE_SIZE 64U
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 4b425bf71ede1..a31256f70348a 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
 
 #include "gve_desc.h"
 #include "gve_desc_dqo.h"
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 9db384f66a8ee..4bffc3cb502f8 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -15,6 +15,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/bitfield.h>
 #include <linux/hrtimer.h>
+#include <net/xdp.h>
 
 #include "igc_hw.h"
 
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 27f272831ea5c..eb7d81b5e9f83 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -14,6 +14,7 @@
 #include <net/pkt_cls.h>
 #include <net/pkt_sched.h>
 #include <net/switchdev.h>
+#include <net/xdp.h>
 
 #include <vcap_api.h>
 #include <vcap_api_client.h>
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index ac2acc9aca9d0..21665f114fe9b 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -11,6 +11,7 @@
 
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
+#include <net/xdp.h>
 
 #include <net/mana/mana.h>
 #include <net/mana/mana_auxiliary.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 4ce5eaaae5135..a6d034968654d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -22,6 +22,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/reset.h>
 #include <net/page_pool.h>
+#include <net/xdp.h>
 #include <uapi/linux/bpf.h>
 
 struct stmmac_resources {
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index 34230145ca0b5..0e27c433098d8 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -6,6 +6,7 @@
 #ifndef DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_
 #define DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_
 
+#include <net/xdp.h>
 #include <uapi/linux/bpf.h>
 
 #include "davinci_cpdma.h"
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index c9dd69dbe1b8f..810977952f950 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -16,6 +16,7 @@
 #include <linux/hyperv.h>
 #include <linux/rndis.h>
 #include <linux/jhash.h>
+#include <net/xdp.h>
 
 /* RSS related */
 #define OID_GEN_RECEIVE_SCALE_CAPABILITIES 0x00010203  /* query only */
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 9137fb8c1c420..b196a2a543556 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -22,6 +22,7 @@
 #include <net/net_namespace.h>
 #include <net/rtnetlink.h>
 #include <net/sock.h>
+#include <net/xdp.h>
 #include <linux/virtio_net.h>
 #include <linux/skb_array.h>
 
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 024ad8ddb27e5..1ccdca03e166e 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -4,6 +4,8 @@
 #ifndef _MANA_H
 #define _MANA_H
 
+#include <net/xdp.h>
+
 #include "gdma.h"
 #include "hw_channel.h"
 
-- 
GitLab


From 49e47a5b6145d86c30022fe0e949bbb24bae28ba Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 2 Aug 2023 18:02:29 -0700
Subject: [PATCH 0860/1806] net: move struct netdev_rx_queue out of netdevice.h

struct netdev_rx_queue is touched in only a few places
and having it defined in netdevice.h brings in the dependency
on xdp.h, because struct xdp_rxq_info gets embedded in
struct netdev_rx_queue.

In prep for removal of xdp.h from netdevice.h move all
the netdev_rx_queue stuff to a new header.

We could technically break the new header up to avoid
the sysfs.h include but it's so rarely included it
doesn't seem to be worth it at this point.

Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20230803010230.1755386-3-kuba@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 drivers/net/virtio_net.c      |  1 +
 include/linux/netdevice.h     | 44 -----------------------------
 include/net/netdev_rx_queue.h | 53 +++++++++++++++++++++++++++++++++++
 net/bpf/test_run.c            |  1 +
 net/core/dev.c                |  1 +
 net/core/net-sysfs.c          |  1 +
 net/xdp/xsk.c                 |  1 +
 7 files changed, 58 insertions(+), 44 deletions(-)
 create mode 100644 include/net/netdev_rx_queue.h

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 0db14f6b87d3e..5bcfd69333eaa 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -22,6 +22,7 @@
 #include <net/route.h>
 #include <net/xdp.h>
 #include <net/net_failover.h>
+#include <net/netdev_rx_queue.h>
 
 static int napi_weight = NAPI_POLL_WEIGHT;
 module_param(napi_weight, int, 0444);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3800d04796984..5563c8a210b54 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -782,32 +782,6 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
 #endif
 #endif /* CONFIG_RPS */
 
-/* This structure contains an instance of an RX queue. */
-struct netdev_rx_queue {
-	struct xdp_rxq_info		xdp_rxq;
-#ifdef CONFIG_RPS
-	struct rps_map __rcu		*rps_map;
-	struct rps_dev_flow_table __rcu	*rps_flow_table;
-#endif
-	struct kobject			kobj;
-	struct net_device		*dev;
-	netdevice_tracker		dev_tracker;
-
-#ifdef CONFIG_XDP_SOCKETS
-	struct xsk_buff_pool            *pool;
-#endif
-} ____cacheline_aligned_in_smp;
-
-/*
- * RX queue sysfs structures and functions.
- */
-struct rx_queue_attribute {
-	struct attribute attr;
-	ssize_t (*show)(struct netdev_rx_queue *queue, char *buf);
-	ssize_t (*store)(struct netdev_rx_queue *queue,
-			 const char *buf, size_t len);
-};
-
 /* XPS map type and offset of the xps map within net_device->xps_maps[]. */
 enum xps_map_type {
 	XPS_CPUS = 0,
@@ -3828,24 +3802,6 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev,
 int netif_set_real_num_queues(struct net_device *dev,
 			      unsigned int txq, unsigned int rxq);
 
-static inline struct netdev_rx_queue *
-__netif_get_rx_queue(struct net_device *dev, unsigned int rxq)
-{
-	return dev->_rx + rxq;
-}
-
-#ifdef CONFIG_SYSFS
-static inline unsigned int get_netdev_rx_queue_index(
-		struct netdev_rx_queue *queue)
-{
-	struct net_device *dev = queue->dev;
-	int index = queue - dev->_rx;
-
-	BUG_ON(index >= dev->num_rx_queues);
-	return index;
-}
-#endif
-
 int netif_get_num_default_rss_queues(void);
 
 void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason);
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
new file mode 100644
index 0000000000000..cdcafb30d4378
--- /dev/null
+++ b/include/net/netdev_rx_queue.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_NETDEV_RX_QUEUE_H
+#define _LINUX_NETDEV_RX_QUEUE_H
+
+#include <linux/kobject.h>
+#include <linux/netdevice.h>
+#include <linux/sysfs.h>
+#include <net/xdp.h>
+
+/* This structure contains an instance of an RX queue. */
+struct netdev_rx_queue {
+	struct xdp_rxq_info		xdp_rxq;
+#ifdef CONFIG_RPS
+	struct rps_map __rcu		*rps_map;
+	struct rps_dev_flow_table __rcu	*rps_flow_table;
+#endif
+	struct kobject			kobj;
+	struct net_device		*dev;
+	netdevice_tracker		dev_tracker;
+
+#ifdef CONFIG_XDP_SOCKETS
+	struct xsk_buff_pool            *pool;
+#endif
+} ____cacheline_aligned_in_smp;
+
+/*
+ * RX queue sysfs structures and functions.
+ */
+struct rx_queue_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct netdev_rx_queue *queue, char *buf);
+	ssize_t (*store)(struct netdev_rx_queue *queue,
+			 const char *buf, size_t len);
+};
+
+static inline struct netdev_rx_queue *
+__netif_get_rx_queue(struct net_device *dev, unsigned int rxq)
+{
+	return dev->_rx + rxq;
+}
+
+#ifdef CONFIG_SYSFS
+static inline unsigned int
+get_netdev_rx_queue_index(struct netdev_rx_queue *queue)
+{
+	struct net_device *dev = queue->dev;
+	int index = queue - dev->_rx;
+
+	BUG_ON(index >= dev->num_rx_queues);
+	return index;
+}
+#endif
+#endif
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 7d47f53f20c10..0aac76c13fd4a 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -20,6 +20,7 @@
 #include <linux/smp.h>
 #include <linux/sock_diag.h>
 #include <linux/netfilter.h>
+#include <net/netdev_rx_queue.h>
 #include <net/xdp.h>
 #include <net/netfilter/nf_bpf_link.h>
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 002fec07de739..1916ec990f58b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -152,6 +152,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/prandom.h>
 #include <linux/once_lite.h>
+#include <net/netdev_rx_queue.h>
 
 #include "dev.h"
 #include "net-sysfs.h"
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 15e3f4606b5f9..fccaa5bac0ed0 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -23,6 +23,7 @@
 #include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/cpu.h>
+#include <net/netdev_rx_queue.h>
 
 #include "dev.h"
 #include "net-sysfs.h"
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 4f1e0599146e2..82aaec1b079fc 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -25,6 +25,7 @@
 #include <linux/vmalloc.h>
 #include <net/xdp_sock_drv.h>
 #include <net/busy_poll.h>
+#include <net/netdev_rx_queue.h>
 #include <net/xdp.h>
 
 #include "xsk_queue.h"
-- 
GitLab


From 680ee0456a5712309db9ec2692e908ea1d6b1644 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 2 Aug 2023 18:02:30 -0700
Subject: [PATCH 0861/1806] net: invert the netdevice.h vs xdp.h dependency

xdp.h is far more specific and is included in only 67 other
files vs netdevice.h's 1538 include sites.
Make xdp.h include netdevice.h, instead of the other way around.
This decreases the incremental allmodconfig builds size when
xdp.h is touched from 5947 to 662 objects.

Move bpf_prog_run_xdp() to xdp.h, seems appropriate and filter.h
is a mega-header in its own right so it's nice to avoid xdp.h
getting included there as well.

The only unfortunate part is that the typedef for xdp_features_t
has to move to netdevice.h, since its embedded in struct netdevice.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20230803010230.1755386-4-kuba@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/filter.h           | 17 -----------------
 include/linux/netdevice.h        | 11 ++++-------
 include/net/busy_poll.h          |  1 +
 include/net/xdp.h                | 29 +++++++++++++++++++++++++----
 include/trace/events/xdp.h       |  1 +
 kernel/bpf/btf.c                 |  1 +
 kernel/bpf/offload.c             |  1 +
 kernel/bpf/verifier.c            |  1 +
 net/netfilter/nf_conntrack_bpf.c |  1 +
 9 files changed, 35 insertions(+), 28 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index f5eabe3fa5e8e..2d6fe30bad5f1 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -774,23 +774,6 @@ DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key);
 
 u32 xdp_master_redirect(struct xdp_buff *xdp);
 
-static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
-					    struct xdp_buff *xdp)
-{
-	/* Driver XDP hooks are invoked within a single NAPI poll cycle and thus
-	 * under local_bh_disable(), which provides the needed RCU protection
-	 * for accessing map entries.
-	 */
-	u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp));
-
-	if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) {
-		if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev))
-			act = xdp_master_redirect(xdp);
-	}
-
-	return act;
-}
-
 void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog);
 
 static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5563c8a210b54..d8ed85183fe43 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -40,7 +40,6 @@
 #include <net/dcbnl.h>
 #endif
 #include <net/netprio_cgroup.h>
-#include <net/xdp.h>
 
 #include <linux/netdev_features.h>
 #include <linux/neighbour.h>
@@ -76,8 +75,12 @@ struct udp_tunnel_nic_info;
 struct udp_tunnel_nic;
 struct bpf_prog;
 struct xdp_buff;
+struct xdp_frame;
+struct xdp_metadata_ops;
 struct xdp_md;
 
+typedef u32 xdp_features_t;
+
 void synchronize_net(void);
 void netdev_set_default_ethtool_ops(struct net_device *dev,
 				    const struct ethtool_ops *ops);
@@ -1628,12 +1631,6 @@ struct net_device_ops {
 						  bool cycles);
 };
 
-struct xdp_metadata_ops {
-	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
-	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
-			       enum xdp_rss_hash_type *rss_type);
-};
-
 /**
  * enum netdev_priv_flags - &struct net_device priv_flags
  *
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index f90f0021f5f2d..4dabeb6c76d31 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -16,6 +16,7 @@
 #include <linux/sched/clock.h>
 #include <linux/sched/signal.h>
 #include <net/ip.h>
+#include <net/xdp.h>
 
 /*		0 - Reserved to indicate value not set
  *     1..NR_CPUS - Reserved for sender_cpu
diff --git a/include/net/xdp.h b/include/net/xdp.h
index d1c5381fc95f2..de08c8e0d1348 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -6,9 +6,10 @@
 #ifndef __LINUX_NET_XDP_H__
 #define __LINUX_NET_XDP_H__
 
-#include <linux/skbuff.h> /* skb_shared_info */
-#include <uapi/linux/netdev.h>
 #include <linux/bitfield.h>
+#include <linux/filter.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h> /* skb_shared_info */
 
 /**
  * DOC: XDP RX-queue information
@@ -45,8 +46,6 @@ enum xdp_mem_type {
 	MEM_TYPE_MAX,
 };
 
-typedef u32 xdp_features_t;
-
 /* XDP flags for ndo_xdp_xmit */
 #define XDP_XMIT_FLUSH		(1U << 0)	/* doorbell signal consumer */
 #define XDP_XMIT_FLAGS_MASK	XDP_XMIT_FLUSH
@@ -443,6 +442,12 @@ enum xdp_rss_hash_type {
 	XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR,
 };
 
+struct xdp_metadata_ops {
+	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
+	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
+			       enum xdp_rss_hash_type *rss_type);
+};
+
 #ifdef CONFIG_NET
 u32 bpf_xdp_metadata_kfunc_id(int id);
 bool bpf_dev_bound_kfunc_id(u32 btf_id);
@@ -474,4 +479,20 @@ static inline void xdp_clear_features_flag(struct net_device *dev)
 	xdp_set_features_flag(dev, 0);
 }
 
+static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
+					    struct xdp_buff *xdp)
+{
+	/* Driver XDP hooks are invoked within a single NAPI poll cycle and thus
+	 * under local_bh_disable(), which provides the needed RCU protection
+	 * for accessing map entries.
+	 */
+	u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp));
+
+	if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) {
+		if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev))
+			act = xdp_master_redirect(xdp);
+	}
+
+	return act;
+}
 #endif /* __LINUX_NET_XDP_H__ */
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index cd89f1d5ce7b8..9adc2bdf2f94a 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -9,6 +9,7 @@
 #include <linux/filter.h>
 #include <linux/tracepoint.h>
 #include <linux/bpf.h>
+#include <net/xdp.h>
 
 #define __XDP_ACT_MAP(FN)	\
 	FN(ABORTED)		\
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index ef9581a580e28..249657c466dd3 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -29,6 +29,7 @@
 #include <net/netfilter/nf_bpf_link.h>
 
 #include <net/sock.h>
+#include <net/xdp.h>
 #include "../tools/lib/bpf/relo_core.h"
 
 /* BTF (BPF Type Format) is the meta data format which describes
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 8a26cd8814c1b..3e4f2ec1af068 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -25,6 +25,7 @@
 #include <linux/rhashtable.h>
 #include <linux/rtnetlink.h>
 #include <linux/rwsem.h>
+#include <net/xdp.h>
 
 /* Protects offdevs, members of bpf_offload_netdev and offload members
  * of all progs.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e7b1af016841f..132f25dab9318 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -26,6 +26,7 @@
 #include <linux/poison.h>
 #include <linux/module.h>
 #include <linux/cpumask.h>
+#include <net/xdp.h>
 
 #include "disasm.h"
 
diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index 0d36d7285e3f0..c7a6114091ae5 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/btf_ids.h>
 #include <linux/net_namespace.h>
+#include <net/xdp.h>
 #include <net/netfilter/nf_conntrack_bpf.h>
 #include <net/netfilter/nf_conntrack_core.h>
 
-- 
GitLab


From e70380650a32e4ccb0bd8a2d7b54e1e4a35b39ba Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 2 Aug 2023 09:18:20 -0700
Subject: [PATCH 0862/1806] docs: net: page_pool: document PP_FLAG_DMA_SYNC_DEV
 parameters

Using PP_FLAG_DMA_SYNC_DEV is a bit confusing. It was perhaps
more obvious when it was introduced but the page pool use
has grown beyond XDP and beyond packet-per-page so now
making the heads and tails out of this feature is not
trivial.

Obviously making the API more user friendly would be
a better fix, but until someone steps up to do that
let's at least document what the parameters are.

Relevant discussion in the first Link.

Link: https://lore.kernel.org/all/20230731114427.0da1f73b@kernel.org/
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Link: https://lore.kernel.org/r/20230802161821.3621985-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/page_pool.rst | 34 ++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst
index 0aa850cf4447c..eb96a592ec6b2 100644
--- a/Documentation/networking/page_pool.rst
+++ b/Documentation/networking/page_pool.rst
@@ -109,6 +109,40 @@ a page will cause no race conditions is enough.
   caller can then report those stats to the user (perhaps via ethtool,
   debugfs, etc.). See below for an example usage of this API.
 
+DMA sync
+--------
+Driver is always responsible for syncing the pages for the CPU.
+Drivers may choose to take care of syncing for the device as well
+or set the ``PP_FLAG_DMA_SYNC_DEV`` flag to request that pages
+allocated from the page pool are already synced for the device.
+
+If ``PP_FLAG_DMA_SYNC_DEV`` is set, the driver must inform the core what portion
+of the buffer has to be synced. This allows the core to avoid syncing the entire
+page when the drivers knows that the device only accessed a portion of the page.
+
+Most drivers will reserve headroom in front of the frame. This part
+of the buffer is not touched by the device, so to avoid syncing
+it drivers can set the ``offset`` field in struct page_pool_params
+appropriately.
+
+For pages recycled on the XDP xmit and skb paths the page pool will
+use the ``max_len`` member of struct page_pool_params to decide how
+much of the page needs to be synced (starting at ``offset``).
+When directly freeing pages in the driver (page_pool_put_page())
+the ``dma_sync_size`` argument specifies how much of the buffer needs
+to be synced.
+
+If in doubt set ``offset`` to 0, ``max_len`` to ``PAGE_SIZE`` and
+pass -1 as ``dma_sync_size``. That combination of arguments is always
+correct.
+
+Note that the syncing parameters are for the entire page.
+This is important to remember when using fragments (``PP_FLAG_PAGE_FRAG``),
+where allocated buffers may be smaller than a full page.
+Unless the driver author really understands page pool internals
+it's recommended to always use ``offset = 0``, ``max_len = PAGE_SIZE``
+with fragmented page pools.
+
 Stats API and structures
 ------------------------
 If the kernel is configured with ``CONFIG_PAGE_POOL_STATS=y``, the API
-- 
GitLab


From 82e896d992fa631cda1f63239fd47b3ab781ffa6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 2 Aug 2023 09:18:21 -0700
Subject: [PATCH 0863/1806] docs: net: page_pool: use kdoc to avoid duplicating
 the information

All struct members of the driver-facing APIs are documented twice,
in the code and under Documentation. This is a bit tedious.

I also get the feeling that a lot of developers will read the header
when coding, rather than the doc. Bring the two a little closer
together by using kdoc for structs and functions.

Using kdoc also gives us links (mentioning a function or struct
in the text gets replaced by a link to its doc).

Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20230802161821.3621985-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/page_pool.rst |  92 ++++-------------
 include/net/page_pool.h                | 134 +++++++++++++++++++------
 net/core/page_pool.c                   |  31 +++++-
 3 files changed, 155 insertions(+), 102 deletions(-)

diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst
index eb96a592ec6b2..53b5448cc0f11 100644
--- a/Documentation/networking/page_pool.rst
+++ b/Documentation/networking/page_pool.rst
@@ -64,50 +64,19 @@ This lockless guarantee naturally comes from running under a NAPI softirq.
 The protection doesn't strictly have to be NAPI, any guarantee that allocating
 a page will cause no race conditions is enough.
 
-* page_pool_create(): Create a pool.
-    * flags:      PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV
-    * order:      2^order pages on allocation
-    * pool_size:  size of the ptr_ring
-    * nid:        preferred NUMA node for allocation
-    * dev:        struct device. Used on DMA operations
-    * dma_dir:    DMA direction
-    * max_len:    max DMA sync memory size
-    * offset:     DMA address offset
-
-* page_pool_put_page(): The outcome of this depends on the page refcnt. If the
-  driver bumps the refcnt > 1 this will unmap the page. If the page refcnt is 1
-  the allocator owns the page and will try to recycle it in one of the pool
-  caches. If PP_FLAG_DMA_SYNC_DEV is set, the page will be synced for_device
-  using dma_sync_single_range_for_device().
-
-* page_pool_put_full_page(): Similar to page_pool_put_page(), but will DMA sync
-  for the entire memory area configured in area pool->max_len.
-
-* page_pool_recycle_direct(): Similar to page_pool_put_full_page() but caller
-  must guarantee safe context (e.g NAPI), since it will recycle the page
-  directly into the pool fast cache.
-
-* page_pool_dev_alloc_pages(): Get a page from the page allocator or page_pool
-  caches.
-
-* page_pool_get_dma_addr(): Retrieve the stored DMA address.
-
-* page_pool_get_dma_dir(): Retrieve the stored DMA direction.
-
-* page_pool_put_page_bulk(): Tries to refill a number of pages into the
-  ptr_ring cache holding ptr_ring producer lock. If the ptr_ring is full,
-  page_pool_put_page_bulk() will release leftover pages to the page allocator.
-  page_pool_put_page_bulk() is suitable to be run inside the driver NAPI tx
-  completion loop for the XDP_REDIRECT use case.
-  Please note the caller must not use data area after running
-  page_pool_put_page_bulk(), as this function overwrites it.
-
-* page_pool_get_stats(): Retrieve statistics about the page_pool. This API
-  is only available if the kernel has been configured with
-  ``CONFIG_PAGE_POOL_STATS=y``. A pointer to a caller allocated ``struct
-  page_pool_stats`` structure is passed to this API which is filled in. The
-  caller can then report those stats to the user (perhaps via ethtool,
-  debugfs, etc.). See below for an example usage of this API.
+.. kernel-doc:: net/core/page_pool.c
+   :identifiers: page_pool_create
+
+.. kernel-doc:: include/net/page_pool.h
+   :identifiers: struct page_pool_params
+
+.. kernel-doc:: include/net/page_pool.h
+   :identifiers: page_pool_put_page page_pool_put_full_page
+		 page_pool_recycle_direct page_pool_dev_alloc_pages
+		 page_pool_get_dma_addr page_pool_get_dma_dir
+
+.. kernel-doc:: net/core/page_pool.c
+   :identifiers: page_pool_put_page_bulk page_pool_get_stats
 
 DMA sync
 --------
@@ -146,36 +115,17 @@ with fragmented page pools.
 Stats API and structures
 ------------------------
 If the kernel is configured with ``CONFIG_PAGE_POOL_STATS=y``, the API
-``page_pool_get_stats()`` and structures described below are available. It
-takes a  pointer to a ``struct page_pool`` and a pointer to a ``struct
-page_pool_stats`` allocated by the caller.
+page_pool_get_stats() and structures described below are available.
+It takes a  pointer to a ``struct page_pool`` and a pointer to a struct
+page_pool_stats allocated by the caller.
 
-The API will fill in the provided ``struct page_pool_stats`` with
+The API will fill in the provided struct page_pool_stats with
 statistics about the page_pool.
 
-The stats structure has the following fields::
-
-    struct page_pool_stats {
-        struct page_pool_alloc_stats alloc_stats;
-        struct page_pool_recycle_stats recycle_stats;
-    };
-
-
-The ``struct page_pool_alloc_stats`` has the following fields:
-  * ``fast``: successful fast path allocations
-  * ``slow``: slow path order-0 allocations
-  * ``slow_high_order``: slow path high order allocations
-  * ``empty``: ptr ring is empty, so a slow path allocation was forced.
-  * ``refill``: an allocation which triggered a refill of the cache
-  * ``waive``: pages obtained from the ptr ring that cannot be added to
-    the cache due to a NUMA mismatch.
-
-The ``struct page_pool_recycle_stats`` has the following fields:
-  * ``cached``: recycling placed page in the page pool cache
-  * ``cache_full``: page pool cache was full
-  * ``ring``: page placed into the ptr ring
-  * ``ring_full``: page released from page pool because the ptr ring was full
-  * ``released_refcnt``: page released (and not recycled) because refcnt > 1
+.. kernel-doc:: include/net/page_pool.h
+   :identifiers: struct page_pool_recycle_stats
+		 struct page_pool_alloc_stats
+		 struct page_pool_stats
 
 Coding examples
 ===============
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index f1d5cc1fa13b1..73d4f786418d5 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -70,47 +70,76 @@ struct pp_alloc_cache {
 	struct page *cache[PP_ALLOC_CACHE_SIZE];
 };
 
+/**
+ * struct page_pool_params - page pool parameters
+ * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_PAGE_FRAG
+ * @order:	2^order pages on allocation
+ * @pool_size:	size of the ptr_ring
+ * @nid:	NUMA node id to allocate from pages from
+ * @dev:	device, for DMA pre-mapping purposes
+ * @napi:	NAPI which is the sole consumer of pages, otherwise NULL
+ * @dma_dir:	DMA mapping direction
+ * @max_len:	max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV
+ * @offset:	DMA sync address offset for PP_FLAG_DMA_SYNC_DEV
+ */
 struct page_pool_params {
 	unsigned int	flags;
 	unsigned int	order;
 	unsigned int	pool_size;
-	int		nid;  /* Numa node id to allocate from pages from */
-	struct device	*dev; /* device, for DMA pre-mapping purposes */
-	struct napi_struct *napi; /* Sole consumer of pages, otherwise NULL */
-	enum dma_data_direction dma_dir; /* DMA mapping direction */
-	unsigned int	max_len; /* max DMA sync memory size */
-	unsigned int	offset;  /* DMA addr offset */
+	int		nid;
+	struct device	*dev;
+	struct napi_struct *napi;
+	enum dma_data_direction dma_dir;
+	unsigned int	max_len;
+	unsigned int	offset;
+/* private: used by test code only */
 	void (*init_callback)(struct page *page, void *arg);
 	void *init_arg;
 };
 
 #ifdef CONFIG_PAGE_POOL_STATS
+/**
+ * struct page_pool_alloc_stats - allocation statistics
+ * @fast:	successful fast path allocations
+ * @slow:	slow path order-0 allocations
+ * @slow_high_order: slow path high order allocations
+ * @empty:	ptr ring is empty, so a slow path allocation was forced
+ * @refill:	an allocation which triggered a refill of the cache
+ * @waive:	pages obtained from the ptr ring that cannot be added to
+ *		the cache due to a NUMA mismatch
+ */
 struct page_pool_alloc_stats {
-	u64 fast; /* fast path allocations */
-	u64 slow; /* slow-path order 0 allocations */
-	u64 slow_high_order; /* slow-path high order allocations */
-	u64 empty; /* failed refills due to empty ptr ring, forcing
-		    * slow path allocation
-		    */
-	u64 refill; /* allocations via successful refill */
-	u64 waive;  /* failed refills due to numa zone mismatch */
+	u64 fast;
+	u64 slow;
+	u64 slow_high_order;
+	u64 empty;
+	u64 refill;
+	u64 waive;
 };
 
+/**
+ * struct page_pool_recycle_stats - recycling (freeing) statistics
+ * @cached:	recycling placed page in the page pool cache
+ * @cache_full:	page pool cache was full
+ * @ring:	page placed into the ptr ring
+ * @ring_full:	page released from page pool because the ptr ring was full
+ * @released_refcnt:	page released (and not recycled) because refcnt > 1
+ */
 struct page_pool_recycle_stats {
-	u64 cached;	/* recycling placed page in the cache. */
-	u64 cache_full; /* cache was full */
-	u64 ring;	/* recycling placed page back into ptr ring */
-	u64 ring_full;	/* page was released from page-pool because
-			 * PTR ring was full.
-			 */
-	u64 released_refcnt; /* page released because of elevated
-			      * refcnt
-			      */
+	u64 cached;
+	u64 cache_full;
+	u64 ring;
+	u64 ring_full;
+	u64 released_refcnt;
 };
 
-/* This struct wraps the above stats structs so users of the
- * page_pool_get_stats API can pass a single argument when requesting the
- * stats for the page pool.
+/**
+ * struct page_pool_stats - combined page pool use statistics
+ * @alloc_stats:	see struct page_pool_alloc_stats
+ * @recycle_stats:	see struct page_pool_recycle_stats
+ *
+ * Wrapper struct for combining page pool stats with different storage
+ * requirements.
  */
 struct page_pool_stats {
 	struct page_pool_alloc_stats alloc_stats;
@@ -211,6 +240,12 @@ struct page_pool {
 
 struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
 
+/**
+ * page_pool_dev_alloc_pages() - allocate a page.
+ * @pool:	pool from which to allocate
+ *
+ * Get a page from the page allocator or page_pool caches.
+ */
 static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool)
 {
 	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
@@ -230,8 +265,12 @@ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool,
 	return page_pool_alloc_frag(pool, offset, size, gfp);
 }
 
-/* get the stored dma direction. A driver might decide to treat this locally and
- * avoid the extra cache line from page_pool to determine the direction
+/**
+ * page_pool_get_dma_dir() - Retrieve the stored DMA direction.
+ * @pool:	pool from which page was allocated
+ *
+ * Get the stored dma direction. A driver might decide to store this locally
+ * and avoid the extra cache line from page_pool to determine the direction.
  */
 static
 inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
@@ -321,6 +360,19 @@ static inline bool page_pool_is_last_frag(struct page_pool *pool,
 	       (page_pool_defrag_page(page, 1) == 0);
 }
 
+/**
+ * page_pool_put_page() - release a reference to a page pool page
+ * @pool:	pool from which page was allocated
+ * @page:	page to release a reference on
+ * @dma_sync_size: how much of the page may have been touched by the device
+ * @allow_direct: released by the consumer, allow lockless caching
+ *
+ * The outcome of this depends on the page refcnt. If the driver bumps
+ * the refcnt > 1 this will unmap the page. If the page refcnt is 1
+ * the allocator owns the page and will try to recycle it in one of the pool
+ * caches. If PP_FLAG_DMA_SYNC_DEV is set, the page will be synced for_device
+ * using dma_sync_single_range_for_device().
+ */
 static inline void page_pool_put_page(struct page_pool *pool,
 				      struct page *page,
 				      unsigned int dma_sync_size,
@@ -337,14 +389,29 @@ static inline void page_pool_put_page(struct page_pool *pool,
 #endif
 }
 
-/* Same as above but will try to sync the entire area pool->max_len */
+/**
+ * page_pool_put_full_page() - release a reference on a page pool page
+ * @pool:	pool from which page was allocated
+ * @page:	page to release a reference on
+ * @allow_direct: released by the consumer, allow lockless caching
+ *
+ * Similar to page_pool_put_page(), but will DMA sync the entire memory area
+ * as configured in &page_pool_params.max_len.
+ */
 static inline void page_pool_put_full_page(struct page_pool *pool,
 					   struct page *page, bool allow_direct)
 {
 	page_pool_put_page(pool, page, -1, allow_direct);
 }
 
-/* Same as above but the caller must guarantee safe context. e.g NAPI */
+/**
+ * page_pool_recycle_direct() - release a reference on a page pool page
+ * @pool:	pool from which page was allocated
+ * @page:	page to release a reference on
+ *
+ * Similar to page_pool_put_full_page() but caller must guarantee safe context
+ * (e.g NAPI), since it will recycle the page directly into the pool fast cache.
+ */
 static inline void page_pool_recycle_direct(struct page_pool *pool,
 					    struct page *page)
 {
@@ -354,6 +421,13 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 #define PAGE_POOL_DMA_USE_PP_FRAG_COUNT	\
 		(sizeof(dma_addr_t) > sizeof(unsigned long))
 
+/**
+ * page_pool_get_dma_addr() - Retrieve the stored DMA address.
+ * @page:	page allocated from a page pool
+ *
+ * Fetch the DMA address of the page. The page pool to which the page belongs
+ * must had been created with PP_FLAG_DMA_MAP.
+ */
 static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
 {
 	dma_addr_t ret = page->dma_addr;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 7ca456bfab71c..5d615a1697187 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -58,6 +58,17 @@ static const char pp_stats[][ETH_GSTRING_LEN] = {
 	"rx_pp_recycle_released_ref",
 };
 
+/**
+ * page_pool_get_stats() - fetch page pool stats
+ * @pool:	pool from which page was allocated
+ * @stats:	struct page_pool_stats to fill in
+ *
+ * Retrieve statistics about the page_pool. This API is only available
+ * if the kernel has been configured with ``CONFIG_PAGE_POOL_STATS=y``.
+ * A pointer to a caller allocated struct page_pool_stats structure
+ * is passed to this API which is filled in. The caller can then report
+ * those stats to the user (perhaps via ethtool, debugfs, etc.).
+ */
 bool page_pool_get_stats(struct page_pool *pool,
 			 struct page_pool_stats *stats)
 {
@@ -224,6 +235,10 @@ static int page_pool_init(struct page_pool *pool,
 	return 0;
 }
 
+/**
+ * page_pool_create() - create a page pool.
+ * @params: parameters, see struct page_pool_params
+ */
 struct page_pool *page_pool_create(const struct page_pool_params *params)
 {
 	struct page_pool *pool;
@@ -626,7 +641,21 @@ void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
 }
 EXPORT_SYMBOL(page_pool_put_defragged_page);
 
-/* Caller must not use data area after call, as this function overwrites it */
+/**
+ * page_pool_put_page_bulk() - release references on multiple pages
+ * @pool:	pool from which pages were allocated
+ * @data:	array holding page pointers
+ * @count:	number of pages in @data
+ *
+ * Tries to refill a number of pages into the ptr_ring cache holding ptr_ring
+ * producer lock. If the ptr_ring is full, page_pool_put_page_bulk()
+ * will release leftover pages to the page allocator.
+ * page_pool_put_page_bulk() is suitable to be run inside the driver NAPI tx
+ * completion loop for the XDP_REDIRECT use case.
+ *
+ * Please note the caller must not use data area after running
+ * page_pool_put_page_bulk(), as this function overwrites it.
+ */
 void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 			     int count)
 {
-- 
GitLab


From 2744cefe03371cb6dda18649635e5dcbbb227ec9 Mon Sep 17 00:00:00 2001
From: Simon Wunderlich <sw@simonwunderlich.de>
Date: Thu, 3 Aug 2023 21:09:39 +0200
Subject: [PATCH 0864/1806] batman-adv: Start new development cycle

This version will contain all the (major or even only minor) changes for
Linux 6.6.

The version number isn't a semantic version number with major and minor
information. It is just encoding the year of the expected publishing as
Linux -rc1 and the number of published versions this year (starting at 0).

Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/main.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 156ed39eded1a..10007c5894a14 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -13,7 +13,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2023.1"
+#define BATADV_SOURCE_VERSION "2023.3"
 #endif
 
 /* B.A.T.M.A.N. parameters */
-- 
GitLab


From bbfb428a0cf6fbce4bcb34510a8eb0cf9b3841a4 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 26 Jul 2023 22:25:25 +0800
Subject: [PATCH 0865/1806] batman-adv: Remove unused declarations

Since commit 335fbe0f5d25 ("batman-adv: tvlv - convert tt query packet to use tvlv unicast packets")
batadv_recv_tt_query() is not used.
And commit 122edaa05940 ("batman-adv: tvlv - convert roaming adv packet to use tvlv unicast packets")
left behind batadv_recv_roam_adv().

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/routing.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h
index 5f387786e9a73..afd15b3879f1c 100644
--- a/net/batman-adv/routing.h
+++ b/net/batman-adv/routing.h
@@ -27,10 +27,6 @@ int batadv_recv_frag_packet(struct sk_buff *skb,
 			    struct batadv_hard_iface *iface);
 int batadv_recv_bcast_packet(struct sk_buff *skb,
 			     struct batadv_hard_iface *recv_if);
-int batadv_recv_tt_query(struct sk_buff *skb,
-			 struct batadv_hard_iface *recv_if);
-int batadv_recv_roam_adv(struct sk_buff *skb,
-			 struct batadv_hard_iface *recv_if);
 int batadv_recv_unicast_tvlv(struct sk_buff *skb,
 			     struct batadv_hard_iface *recv_if);
 int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb,
-- 
GitLab


From e4b817804579624b47823d87e647ec6c3d3ab827 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Thu, 27 Jul 2023 10:13:42 +0200
Subject: [PATCH 0866/1806] batman-adv: Avoid magic value for minimum MTU

The header linux/if_ether.h already defines a constant for the minimum MTU.
So simply use it instead of having a magic constant in the code.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/soft-interface.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index d3fdf82282afe..f7947fad06f25 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -154,7 +154,7 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)
 static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu)
 {
 	/* check ranges */
-	if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev))
+	if (new_mtu < ETH_MIN_MTU || new_mtu > batadv_hardif_min_mtu(dev))
 		return -EINVAL;
 
 	dev->mtu = new_mtu;
-- 
GitLab


From 112cbcb4af90c4b108b120a28089872d2234a350 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Thu, 27 Jul 2023 10:13:43 +0200
Subject: [PATCH 0867/1806] batman-adv: Check hardif MTU against runtime MTU

If the MTU of the soft/mesh interface was already reduced (enough), it is
not necessary to print a warning about a hard interface not having a MTU to
transport ethernet payloads of 1500 bytes.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/hard-interface.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 41c1ad33d009f..5a4ff9a81e743 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -9,6 +9,7 @@
 
 #include <linux/atomic.h>
 #include <linux/byteorder/generic.h>
+#include <linux/compiler.h>
 #include <linux/container_of.h>
 #include <linux/errno.h>
 #include <linux/gfp.h>
@@ -699,9 +700,14 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	struct batadv_priv *bat_priv;
 	__be16 ethertype = htons(ETH_P_BATMAN);
 	int max_header_len = batadv_max_header_len();
+	unsigned int required_mtu;
+	unsigned int hardif_mtu;
 	int ret;
 
-	if (hard_iface->net_dev->mtu < ETH_MIN_MTU + max_header_len)
+	hardif_mtu = READ_ONCE(hard_iface->net_dev->mtu);
+	required_mtu = READ_ONCE(soft_iface->mtu) + max_header_len;
+
+	if (hardif_mtu < ETH_MIN_MTU + max_header_len)
 		return -EINVAL;
 
 	if (hard_iface->if_status != BATADV_IF_NOT_IN_USE)
@@ -734,18 +740,18 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 		    hard_iface->net_dev->name);
 
 	if (atomic_read(&bat_priv->fragmentation) &&
-	    hard_iface->net_dev->mtu < ETH_DATA_LEN + max_header_len)
+	    hardif_mtu < required_mtu)
 		batadv_info(hard_iface->soft_iface,
 			    "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. Packets going over this interface will be fragmented on layer2 which could impact the performance. Setting the MTU to %i would solve the problem.\n",
-			    hard_iface->net_dev->name, hard_iface->net_dev->mtu,
-			    ETH_DATA_LEN + max_header_len);
+			    hard_iface->net_dev->name, hardif_mtu,
+			    required_mtu);
 
 	if (!atomic_read(&bat_priv->fragmentation) &&
-	    hard_iface->net_dev->mtu < ETH_DATA_LEN + max_header_len)
+	    hardif_mtu < required_mtu)
 		batadv_info(hard_iface->soft_iface,
 			    "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. If you experience problems getting traffic through try increasing the MTU to %i.\n",
-			    hard_iface->net_dev->name, hard_iface->net_dev->mtu,
-			    ETH_DATA_LEN + max_header_len);
+			    hard_iface->net_dev->name, hardif_mtu,
+			    required_mtu);
 
 	if (batadv_hardif_is_iface_up(hard_iface))
 		batadv_hardif_activate_interface(hard_iface);
-- 
GitLab


From 6f9bad6b2d7d6b4e11032b944e379974e31c5c8f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 3 Aug 2023 16:00:07 -0700
Subject: [PATCH 0868/1806] eth: dpaa: add missing net/xdp.h include

Add missing include for DPAA (fix aarch64 build).

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308040620.ty8oYNOP-lkp@intel.com/
Fixes: 680ee0456a57 ("net: invert the netdevice.h vs xdp.h dependency")
Reviewed-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20230803230008.362214-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
index 35b8cea7f8866..ac3c8ed57bbe6 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -8,6 +8,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/refcount.h>
+#include <net/xdp.h>
 #include <soc/fsl/qman.h>
 #include <soc/fsl/bman.h>
 
-- 
GitLab


From 5964d1e4594eb1dbfc1e2a34ec89eb48f6b03e75 Mon Sep 17 00:00:00 2001
From: Li kunyu <kunyu@nfschina.com>
Date: Sat, 5 Aug 2023 01:59:29 +0800
Subject: [PATCH 0869/1806] bpf: bpf_struct_ops: Remove unnecessary initial
 values of variables

err and tlinks is assigned first, so it does not need to initialize the
assignment.

Signed-off-by: Li kunyu <kunyu@nfschina.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230804175929.2867-1-kunyu@nfschina.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/bpf_struct_ops.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 116a0ce378ecd..eaff04eefb31e 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -374,9 +374,9 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	struct bpf_struct_ops_value *uvalue, *kvalue;
 	const struct btf_member *member;
 	const struct btf_type *t = st_ops->type;
-	struct bpf_tramp_links *tlinks = NULL;
+	struct bpf_tramp_links *tlinks;
 	void *udata, *kdata;
-	int prog_fd, err = 0;
+	int prog_fd, err;
 	void *image, *image_end;
 	u32 i;
 
@@ -815,7 +815,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 	struct bpf_struct_ops_map *st_map, *old_st_map;
 	struct bpf_map *old_map;
 	struct bpf_struct_ops_link *st_link;
-	int err = 0;
+	int err;
 
 	st_link = container_of(link, struct bpf_struct_ops_link, link);
 	st_map = container_of(new_map, struct bpf_struct_ops_map, map);
-- 
GitLab


From 992725ff32f534eaa13adfa37f933d4fbf1aa040 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 2 Aug 2023 21:07:16 +0800
Subject: [PATCH 0870/1806] net: Space.h: Remove unused function declarations

Commit 5aa83a4c0a15 ("  [PATCH] remove two obsolete net drivers") remove fmv18x_probe().
And commmit 01f4685797a5 ("eth: amd: remove NI6510 support (ni65)") leave ni65_probe().
Commit a10079c66290 ("staging: remove hp100 driver") remove hp100 driver and hp100_probe()
declaration is not used anymore.

sonic_probe() and iph5526_probe() are never implemented since the beginning of git history.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/r/20230802130716.37308-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/Space.h | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/include/net/Space.h b/include/net/Space.h
index 08ca9cef0213b..c29f3d51c0785 100644
--- a/include/net/Space.h
+++ b/include/net/Space.h
@@ -3,18 +3,11 @@
  * ethernet adaptor have the name "eth[0123...]".
  */
 
-struct net_device *hp100_probe(int unit);
 struct net_device *ultra_probe(int unit);
 struct net_device *wd_probe(int unit);
 struct net_device *ne_probe(int unit);
-struct net_device *fmv18x_probe(int unit);
-struct net_device *ni65_probe(int unit);
-struct net_device *sonic_probe(int unit);
 struct net_device *smc_init(int unit);
 struct net_device *cs89x0_probe(int unit);
 struct net_device *tc515_probe(int unit);
 struct net_device *lance_probe(int unit);
 struct net_device *cops_probe(int unit);
-
-/* Fibre Channel adapters */
-int iph5526_probe(struct net_device *dev);
-- 
GitLab


From 58e701264f15a8984136f4997faf99cb22b121f3 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Wed, 2 Aug 2023 17:31:56 +0800
Subject: [PATCH 0871/1806] net: microchip: vcap api: Use ERR_CAST() in
 vcap_decode_rule()

There is a warning reported by coccinelle:

./drivers/net/ethernet/microchip/vcap/vcap_api.c:2399:9-16: WARNING:
ERR_CAST can be used with ri

Use ERR_CAST instead of ERR_PTR + PTR_ERR to simplify the
conversion process.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/vcap/vcap_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c
index a418ad8e8770a..a7b43f99bc808 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_api.c
+++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c
@@ -2396,7 +2396,7 @@ struct vcap_rule *vcap_decode_rule(struct vcap_rule_internal *elem)
 
 	ri = vcap_dup_rule(elem, elem->state == VCAP_RS_DISABLED);
 	if (IS_ERR(ri))
-		return ERR_PTR(PTR_ERR(ri));
+		return ERR_CAST(ri);
 
 	if (ri->state == VCAP_RS_DISABLED)
 		goto out;
-- 
GitLab


From 62c1bff593b7e30041d0273b835af9fd6f5ee737 Mon Sep 17 00:00:00 2001
From: Souradeep Chakrabarti <schakrabarti@linux.microsoft.com>
Date: Wed, 2 Aug 2023 04:07:40 -0700
Subject: [PATCH 0872/1806] net: mana: Configure hwc timeout from hardware

At present hwc timeout value is a fixed value. This patch sets the hwc
timeout from the hardware. It now uses a new hardware capability
GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG to query and set the value
in hwc_timeout.

Signed-off-by: Souradeep Chakrabarti <schakrabarti@linux.microsoft.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/microsoft/mana/gdma_main.c   | 30 ++++++++++++++++++-
 .../net/ethernet/microsoft/mana/hw_channel.c  | 24 ++++++++++++++-
 include/net/mana/gdma.h                       | 20 ++++++++++++-
 include/net/mana/hw_channel.h                 |  5 ++++
 4 files changed, 76 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 3765d3389a9a0..6367de0c2c2e8 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -106,6 +106,25 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
 	return 0;
 }
 
+static int mana_gd_query_hwc_timeout(struct pci_dev *pdev, u32 *timeout_val)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+	struct gdma_query_hwc_timeout_resp resp = {};
+	struct gdma_query_hwc_timeout_req req = {};
+	int err;
+
+	mana_gd_init_req_hdr(&req.hdr, GDMA_QUERY_HWC_TIMEOUT,
+			     sizeof(req), sizeof(resp));
+	req.timeout_ms = *timeout_val;
+	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+	if (err || resp.hdr.status)
+		return err ? err : -EPROTO;
+
+	*timeout_val = resp.timeout_ms;
+
+	return 0;
+}
+
 static int mana_gd_detect_devices(struct pci_dev *pdev)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
@@ -882,8 +901,10 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev)
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 	struct gdma_verify_ver_resp resp = {};
 	struct gdma_verify_ver_req req = {};
+	struct hw_channel_context *hwc;
 	int err;
 
+	hwc = gc->hwc.driver_data;
 	mana_gd_init_req_hdr(&req.hdr, GDMA_VERIFY_VF_DRIVER_VERSION,
 			     sizeof(req), sizeof(resp));
 
@@ -910,7 +931,14 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev)
 			err, resp.hdr.status);
 		return err ? err : -EPROTO;
 	}
-
+	if (resp.pf_cap_flags1 & GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) {
+		err = mana_gd_query_hwc_timeout(pdev, &hwc->hwc_timeout);
+		if (err) {
+			dev_err(gc->dev, "Failed to set the hwc timeout %d\n", err);
+			return err;
+		}
+		dev_dbg(gc->dev, "set the hwc timeout to %u\n", hwc->hwc_timeout);
+	}
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index 2bd1d74021f7c..9d1cd3bfcf662 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -174,7 +174,25 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
 		complete(&hwc->hwc_init_eqe_comp);
 		break;
 
+	case GDMA_EQE_HWC_SOC_RECONFIG_DATA:
+		type_data.as_uint32 = event->details[0];
+		type = type_data.type;
+		val = type_data.value;
+
+		switch (type) {
+		case HWC_DATA_CFG_HWC_TIMEOUT:
+			hwc->hwc_timeout = val;
+			break;
+
+		default:
+			dev_warn(hwc->dev, "Received unknown reconfig type %u\n", type);
+			break;
+		}
+
+		break;
+
 	default:
+		dev_warn(hwc->dev, "Received unknown gdma event %u\n", event->type);
 		/* Ignore unknown events, which should never happen. */
 		break;
 	}
@@ -696,6 +714,7 @@ int mana_hwc_create_channel(struct gdma_context *gc)
 	gd->driver_data = hwc;
 	hwc->gdma_dev = gd;
 	hwc->dev = gc->dev;
+	hwc->hwc_timeout = HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS;
 
 	/* HWC's instance number is always 0. */
 	gd->dev_id.as_uint32 = 0;
@@ -770,6 +789,8 @@ void mana_hwc_destroy_channel(struct gdma_context *gc)
 	hwc->gdma_dev->doorbell = INVALID_DOORBELL;
 	hwc->gdma_dev->pdid = INVALID_PDID;
 
+	hwc->hwc_timeout = 0;
+
 	kfree(hwc);
 	gc->hwc.driver_data = NULL;
 	gc->hwc.gdma_context = NULL;
@@ -825,7 +846,8 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
 		goto out;
 	}
 
-	if (!wait_for_completion_timeout(&ctx->comp_event, 30 * HZ)) {
+	if (!wait_for_completion_timeout(&ctx->comp_event,
+					 (msecs_to_jiffies(hwc->hwc_timeout) * HZ))) {
 		dev_err(hwc->dev, "HWC: Request timed out!\n");
 		err = -ETIMEDOUT;
 		goto out;
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 96c120160f15a..88b6ef7ce1a6e 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -33,6 +33,7 @@ enum gdma_request_type {
 	GDMA_DESTROY_PD			= 30,
 	GDMA_CREATE_MR			= 31,
 	GDMA_DESTROY_MR			= 32,
+	GDMA_QUERY_HWC_TIMEOUT		= 84, /* 0x54 */
 };
 
 #define GDMA_RESOURCE_DOORBELL_PAGE	27
@@ -57,6 +58,8 @@ enum gdma_eqe_type {
 	GDMA_EQE_HWC_INIT_EQ_ID_DB	= 129,
 	GDMA_EQE_HWC_INIT_DATA		= 130,
 	GDMA_EQE_HWC_INIT_DONE		= 131,
+	GDMA_EQE_HWC_SOC_RECONFIG	= 132,
+	GDMA_EQE_HWC_SOC_RECONFIG_DATA	= 133,
 };
 
 enum {
@@ -531,10 +534,12 @@ enum {
  * so the driver is able to reliably support features like busy_poll.
  */
 #define GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX BIT(2)
+#define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3)
 
 #define GDMA_DRV_CAP_FLAGS1 \
 	(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
-	 GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX)
+	 GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \
+	 GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG)
 
 #define GDMA_DRV_CAP_FLAGS2 0
 
@@ -664,6 +669,19 @@ struct gdma_disable_queue_req {
 	u32 alloc_res_id_on_creation;
 }; /* HW DATA */
 
+/* GDMA_QUERY_HWC_TIMEOUT */
+struct gdma_query_hwc_timeout_req {
+	struct gdma_req_hdr hdr;
+	u32 timeout_ms;
+	u32 reserved;
+};
+
+struct gdma_query_hwc_timeout_resp {
+	struct gdma_resp_hdr hdr;
+	u32 timeout_ms;
+	u32 reserved;
+};
+
 enum atb_page_size {
 	ATB_PAGE_SIZE_4K,
 	ATB_PAGE_SIZE_8K,
diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h
index 6a757a6e27326..3d3b5c881bc10 100644
--- a/include/net/mana/hw_channel.h
+++ b/include/net/mana/hw_channel.h
@@ -23,6 +23,10 @@
 #define HWC_INIT_DATA_PF_DEST_RQ_ID	10
 #define HWC_INIT_DATA_PF_DEST_CQ_ID	11
 
+#define HWC_DATA_CFG_HWC_TIMEOUT 1
+
+#define HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS 30000
+
 /* Structures labeled with "HW DATA" are exchanged with the hardware. All of
  * them are naturally aligned and hence don't need __packed.
  */
@@ -182,6 +186,7 @@ struct hw_channel_context {
 
 	u32 pf_dest_vrq_id;
 	u32 pf_dest_vrcq_id;
+	u32 hwc_timeout;
 
 	struct hwc_caller_ctx *caller_ctx;
 };
-- 
GitLab


From 6f5ca184cbef6d2b78772a350a3ed8be696b54a2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 Aug 2023 07:53:34 +0000
Subject: [PATCH 0873/1806] tcp/dccp: cache line align inet_hashinfo

I have seen tcp_hashinfo starting at a non optimal location,
forcing input handlers to pull two cache lines instead of one,
and sharing a cache line that was dirtied more than necessary:

ffffffff83680600 b tcp_orphan_timer
ffffffff83680628 b tcp_orphan_cache
ffffffff8368062c b tcp_enable_tx_delay.__tcp_tx_delay_enabled
ffffffff83680630 B tcp_hashinfo
ffffffff83680680 b tcp_cong_list_lock

After this patch, ehash, ehash_locks, ehash_mask and ehash_locks_mask
are located in a read-only cache line.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 1177effabed35..8435572234143 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -177,7 +177,7 @@ struct inet_hashinfo {
 	struct inet_listen_hashbucket	*lhash2;
 
 	bool				pernet;
-};
+} ____cacheline_aligned_in_smp;
 
 static inline struct inet_hashinfo *tcp_or_dccp_get_hashinfo(const struct sock *sk)
 {
-- 
GitLab


From 7740bb882fdea16b2f3a4d3804827b910f44206c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 Aug 2023 07:14:26 +0000
Subject: [PATCH 0874/1806] net: vlan: update wrong comments

vlan_insert_tag() and friends do not allocate a new skb.
However they might allocate a new skb->head.
Update their comments to better describe their behavior.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 6ba71957851e2..3028af87716e2 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -408,7 +408,7 @@ static inline int __vlan_insert_tag(struct sk_buff *skb,
  * @mac_len: MAC header length including outer vlan headers
  *
  * Inserts the VLAN tag into @skb as part of the payload at offset mac_len
- * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ * Returns a VLAN tagged skb. This might change skb->head.
  *
  * Following the skb_unshare() example, in case of error, the calling function
  * doesn't have to worry about freeing the original skb.
@@ -437,7 +437,7 @@ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb,
  * @vlan_tci: VLAN TCI to insert
  *
  * Inserts the VLAN tag into @skb as part of the payload
- * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ * Returns a VLAN tagged skb. This might change skb->head.
  *
  * Following the skb_unshare() example, in case of error, the calling function
  * doesn't have to worry about freeing the original skb.
@@ -457,7 +457,7 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
  * @vlan_tci: VLAN TCI to insert
  *
  * Inserts the VLAN tag into @skb as part of the payload
- * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ * Returns a VLAN tagged skb. This might change skb->head.
  *
  * Following the skb_unshare() example, in case of error, the calling function
  * doesn't have to worry about freeing the original skb.
-- 
GitLab


From 86b7e033d684a9d4ca20ad8e6f8b9300cf99668f Mon Sep 17 00:00:00 2001
From: Zhu Wang <wangzhu9@huawei.com>
Date: Thu, 3 Aug 2023 16:29:00 +0800
Subject: [PATCH 0875/1806] net: lan966x: Do not check 0 for
 platform_get_irq_byname()

Since platform_get_irq_byname() never returned zero, so it need not to
check whether it returned zero, it returned -EINVAL or -ENXIO when
failed, so we replace the return error code with the result it returned.

Signed-off-by: Zhu Wang <wangzhu9@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan966x/lan966x_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 4a1acc7234f64..0d6e79af24106 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -1119,8 +1119,8 @@ static int lan966x_probe(struct platform_device *pdev)
 
 	/* set irq */
 	lan966x->xtr_irq = platform_get_irq_byname(pdev, "xtr");
-	if (lan966x->xtr_irq <= 0)
-		return -EINVAL;
+	if (lan966x->xtr_irq < 0)
+		return lan966x->xtr_irq;
 
 	err = devm_request_threaded_irq(&pdev->dev, lan966x->xtr_irq, NULL,
 					lan966x_xtr_irq_handler, IRQF_ONESHOT,
-- 
GitLab


From d210f9735e13e9b1ef6ffbb636ee051f615bd109 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Aug 2023 15:11:11 +0200
Subject: [PATCH 0876/1806] bpf: Fix mprog detachment for empty mprog entry

syzbot reported an UBSAN array-index-out-of-bounds access in bpf_mprog_read()
upon bpf_mprog_detach(). While it did not have a reproducer, I was able to
manually reproduce through an empty mprog entry which just has miniq present.

The latter is important given otherwise we get an ENOENT error as tcx detaches
the whole mprog entry. The index 4294967295 was triggered via NULL dtuple.prog
which then attempts to detach from the back. bpf_mprog_fetch() in this case
did hit the idx == total and therefore tried to grab the entry at idx -1.

Fix it by adding an explicit bpf_mprog_total() check in bpf_mprog_detach() and
bail out early with ENOENT.

Fixes: 053c8e1f235d ("bpf: Add generic attach/detach/query API for multi-progs")
Reported-by: syzbot+0c06ba0f831fe07a8f27@syzkaller.appspotmail.com
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20230804131112.11012-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/mprog.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/bpf/mprog.c b/kernel/bpf/mprog.c
index f7816d2bc3e4a..32d2c4829eb8d 100644
--- a/kernel/bpf/mprog.c
+++ b/kernel/bpf/mprog.c
@@ -337,6 +337,8 @@ int bpf_mprog_detach(struct bpf_mprog_entry *entry,
 		return -EINVAL;
 	if (revision && revision != bpf_mprog_revision(entry))
 		return -ESTALE;
+	if (!bpf_mprog_total(entry))
+		return -ENOENT;
 	ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, flags,
 				       prog ? prog->type :
 				       BPF_PROG_TYPE_UNSPEC);
-- 
GitLab


From 21ce6abe178a15a0354eaaf86bea07e302075a20 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Aug 2023 15:11:12 +0200
Subject: [PATCH 0877/1806] selftests/bpf: Add test for detachment on empty
 mprog entry

Add a detachment test case with miniq present to assert that with and
without the miniq we get the same error.

  # ./test_progs -t tc_opts
  #244     tc_opts_after:OK
  #245     tc_opts_append:OK
  #246     tc_opts_basic:OK
  #247     tc_opts_before:OK
  #248     tc_opts_chain_classic:OK
  #249     tc_opts_delete_empty:OK
  #250     tc_opts_demixed:OK
  #251     tc_opts_detach:OK
  #252     tc_opts_detach_after:OK
  #253     tc_opts_detach_before:OK
  #254     tc_opts_dev_cleanup:OK
  #255     tc_opts_invalid:OK
  #256     tc_opts_mixed:OK
  #257     tc_opts_prepend:OK
  #258     tc_opts_replace:OK
  #259     tc_opts_revision:OK
  Summary: 16/0 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20230804131112.11012-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/tc_opts.c        | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
index 7914100f9b469..39bd253e41aa8 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
@@ -2237,3 +2237,34 @@ void serial_test_tc_opts_detach_after(void)
 	test_tc_opts_detach_after_target(BPF_TCX_INGRESS);
 	test_tc_opts_detach_after_target(BPF_TCX_EGRESS);
 }
+
+static void test_tc_opts_delete_empty(int target, bool chain_tc_old)
+{
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	int err;
+
+	assert_mprog_count(target, 0);
+	if (chain_tc_old) {
+		tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+				       BPF_TC_INGRESS : BPF_TC_EGRESS;
+		err = bpf_tc_hook_create(&tc_hook);
+		ASSERT_OK(err, "bpf_tc_hook_create");
+		__assert_mprog_count(target, 0, true, loopback);
+	}
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+	if (chain_tc_old) {
+		tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+		bpf_tc_hook_destroy(&tc_hook);
+	}
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_opts_delete_empty(void)
+{
+	test_tc_opts_delete_empty(BPF_TCX_INGRESS, false);
+	test_tc_opts_delete_empty(BPF_TCX_EGRESS, false);
+	test_tc_opts_delete_empty(BPF_TCX_INGRESS, true);
+	test_tc_opts_delete_empty(BPF_TCX_EGRESS, true);
+}
-- 
GitLab


From 9eab71bd887ae28882c29a82cb0cdb00e1654c54 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Fri, 4 Aug 2023 09:58:31 -0700
Subject: [PATCH 0878/1806] selftests/bpf: fix the incorrect verification of
 port numbers.

Check port numbers before calling htons().

According to Dan Carpenter's report, Smatch identified incorrect port
number checks. It is expected that the returned port number is an integer,
with negative numbers indicating errors. However, the value was mistakenly
verified after being translated by htons().

Major changes from v1:

 - Move the variable 'port' to the same line of 'err'.

Fixes: 539c7e67aa4a ("selftests/bpf: Verify that the cgroup_skb filters receive expected packets.")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/bpf/cafd6585-d5a2-4096-b94f-7556f5aa7737@moroto.mountain/
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20230804165831.173627-1-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
index 95bab61a1e57b..d686ef19f7052 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
@@ -110,11 +110,12 @@ static int connect_client_server_v6(int client_fd, int listen_fd)
 		.sin6_family = AF_INET6,
 		.sin6_addr = IN6ADDR_LOOPBACK_INIT,
 	};
-	int err;
+	int err, port;
 
-	addr.sin6_port = htons(get_sock_port_v6(listen_fd));
-	if (addr.sin6_port < 0)
+	port = get_sock_port_v6(listen_fd);
+	if (port < 0)
 		return -1;
+	addr.sin6_port = htons(port);
 
 	err = connect(client_fd, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0) {
-- 
GitLab


From 78c96d7b7c9a6aa41d109ca9b040c3955db90c88 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:29 +0200
Subject: [PATCH 0879/1806] netlink: specs: add dump-strict flag for
 dont-validate property

Allow user to specify GENL_DONT_VALIDATE_DUMP_STRICT flag for validation
and add this flag to netlink spec schema.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-2-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/genetlink-c.yaml      | 2 +-
 Documentation/netlink/genetlink-legacy.yaml | 2 +-
 Documentation/netlink/genetlink.yaml        | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index 57d1c1c4918f2..4c1f8c22627bb 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -274,7 +274,7 @@ properties:
               description: Kernel attribute validation flags.
               type: array
               items:
-                enum: [ strict, dump ]
+                enum: [ strict, dump, dump-strict ]
             do: &subop-type
               description: Main command handler.
               type: object
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index 43b769c98fb27..196076dfa3096 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -321,7 +321,7 @@ properties:
               description: Kernel attribute validation flags.
               type: array
               items:
-                enum: [ strict, dump ]
+                enum: [ strict, dump, dump-strict ]
             # Start genetlink-legacy
             fixed-header: *fixed-header
             # End genetlink-legacy
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index 1cbb448d2f1c3..3d338c48bf21f 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -243,7 +243,7 @@ properties:
               description: Kernel attribute validation flags.
               type: array
               items:
-                enum: [ strict, dump ]
+                enum: [ strict, dump, dump-strict ]
             do: &subop-type
               description: Main command handler.
               type: object
-- 
GitLab


From dc7b81a828db0d9801e7977edff2735d660937a8 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:30 +0200
Subject: [PATCH 0880/1806] ynl-gen-c.py: filter rendering of validate field
 values for split ops

For split ops, do and dump has different meaningful values in
validate field.

Fix the rendering to allow the values per op type as follows:
do: strict
dump: dump, strict-dump

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-3-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 650be9b8b6937..a3f70ca929fb2 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -1988,9 +1988,17 @@ def print_kernel_op_table(family, cw):
                 cw.block_start()
                 members = [('cmd', op.enum_name)]
                 if 'dont-validate' in op:
+                    dont_validate = []
+                    for x in op['dont-validate']:
+                        if op_mode == 'do' and x in ['dump', 'dump-strict']:
+                            continue
+                        if op_mode == "dump" and x == 'strict':
+                            continue
+                        dont_validate.append(x)
+
                     members.append(('validate',
                                     ' | '.join([c_upper('genl-dont-validate-' + x)
-                                                for x in op['dont-validate']])), )
+                                                for x in dont_validate])), )
                 name = c_lower(f"{family.name}-nl-{op_name}-{op_mode}it")
                 if 'pre' in op[op_mode]:
                     members.append((cb_names[op_mode]['pre'], c_lower(op[op_mode]['pre'])))
-- 
GitLab


From eab7be688b4416588d19ee1fe5edbfa79a639b42 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:31 +0200
Subject: [PATCH 0881/1806] ynl-gen-c.py: allow directional model for kernel
 mode

Directional model limitation is only applicable for uapi mode.
For kernel mode, the code is generated correctly using right cmd values
for do/dump requests. Lift the limitation.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-4-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index a3f70ca929fb2..2ea6af892b682 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -2317,7 +2317,7 @@ def main():
         return
 
     supported_models = ['unified']
-    if args.mode == 'user':
+    if args.mode in ['user', 'kernel']:
         supported_models += ['directional']
     if parsed.msg_id_model not in supported_models:
         print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation')
-- 
GitLab


From fa8ba3502ade9e4a8e447066b0d94261fbbe1906 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:32 +0200
Subject: [PATCH 0882/1806] ynl-gen-c.py: render netlink policies static for
 split ops

When policies are rendered for split ops, they are consumed in the same
file. No need to expose them for user outside, make them static.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-5-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 2ea6af892b682..e64311331726b 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -1843,13 +1843,13 @@ def print_ntf_type_free(ri):
 
 
 def print_req_policy_fwd(cw, struct, ri=None, terminate=True):
-    if terminate and ri and kernel_can_gen_family_struct(struct.family):
+    if terminate and ri and policy_should_be_static(struct.family):
         return
 
     if terminate:
         prefix = 'extern '
     else:
-        if kernel_can_gen_family_struct(struct.family) and ri:
+        if ri and policy_should_be_static(struct.family):
             prefix = 'static '
         else:
             prefix = ''
@@ -1877,6 +1877,10 @@ def kernel_can_gen_family_struct(family):
     return family.proto == 'genetlink'
 
 
+def policy_should_be_static(family):
+    return family.kernel_policy == 'split' or kernel_can_gen_family_struct(family)
+
+
 def print_kernel_op_table_fwd(family, cw, terminate):
     exported = not kernel_can_gen_family_struct(family)
 
-- 
GitLab


From ba0f66c95fa670d99ad40e4a6c1ede425446a291 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:33 +0200
Subject: [PATCH 0883/1806] devlink: rename devlink_nl_ops to
 devlink_nl_small_ops

In order to avoid name collision with the generated split ops array
which is going to be introduced as a follow-up patch, rename
the existing ops array to devlink_nl_small_ops.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-6-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h | 2 +-
 net/devlink/leftover.c      | 2 +-
 net/devlink/netlink.c       | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 62921b2eb0d3f..c67f074641d49 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -119,7 +119,7 @@ struct devlink_cmd {
 			struct netlink_callback *cb);
 };
 
-extern const struct genl_small_ops devlink_nl_ops[56];
+extern const struct genl_small_ops devlink_nl_small_ops[56];
 
 struct devlink *
 devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 5128b9c7eea81..8f42f1f45705b 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -6278,7 +6278,7 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
 	return devlink_trap_policer_set(devlink, policer_item, info);
 }
 
-const struct genl_small_ops devlink_nl_ops[56] = {
+const struct genl_small_ops devlink_nl_small_ops[56] = {
 	{
 		.cmd = DEVLINK_CMD_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 7a332eb70f703..82a3238d5344e 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -243,8 +243,8 @@ struct genl_family devlink_nl_family __ro_after_init = {
 	.pre_doit	= devlink_nl_pre_doit,
 	.post_doit	= devlink_nl_post_doit,
 	.module		= THIS_MODULE,
-	.small_ops	= devlink_nl_ops,
-	.n_small_ops	= ARRAY_SIZE(devlink_nl_ops),
+	.small_ops	= devlink_nl_small_ops,
+	.n_small_ops	= ARRAY_SIZE(devlink_nl_small_ops),
 	.resv_start_op	= DEVLINK_CMD_SELFTESTS_RUN + 1,
 	.mcgrps		= devlink_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(devlink_nl_mcgrps),
-- 
GitLab


From d61aedcf628ef7467d69638c3b3e5e33cafd75aa Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:34 +0200
Subject: [PATCH 0884/1806] devlink: rename couple of doit netlink callbacks to
 match generated names

The generated names of the doit netlink callback are missing "cmd" in
their names. Change names to be ready to switch to generated split ops
header.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-7-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/dev.c           | 4 ++--
 net/devlink/devl_internal.h | 4 ++--
 net/devlink/leftover.c      | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index bf1d6f1bcfc75..2e120b3da2203 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -196,7 +196,7 @@ void devlink_notify(struct devlink *devlink, enum devlink_command cmd)
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
-int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info)
+int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct sk_buff *msg;
@@ -804,7 +804,7 @@ err_cancel_msg:
 	return err;
 }
 
-int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, struct genl_info *info)
+int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct sk_buff *msg;
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index c67f074641d49..d32a32705430a 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -214,11 +214,11 @@ struct devlink_rate *
 devlink_rate_node_get_from_info(struct devlink *devlink,
 				struct genl_info *info);
 /* Devlink nl cmds */
-int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 8f42f1f45705b..094cd0e8224e9 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -6282,7 +6282,7 @@ const struct genl_small_ops devlink_nl_small_ops[56] = {
 	{
 		.cmd = DEVLINK_CMD_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_get_doit,
+		.doit = devlink_nl_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6536,7 +6536,7 @@ const struct genl_small_ops devlink_nl_small_ops[56] = {
 	{
 		.cmd = DEVLINK_CMD_INFO_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_info_get_doit,
+		.doit = devlink_nl_info_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
-- 
GitLab


From 491a24872a64cbb8edf996b6113a97586702e5ca Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:35 +0200
Subject: [PATCH 0885/1806] devlink: introduce couple of dumpit callbacks for
 split ops

Introduce couple of dumpit callbacks for generated split ops. Have them
as a thin wrapper around iteration function and allow to pass dump_one()
function pointer directly without need to store in devlink_cmd structs.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-8-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/dev.c           | 22 ++++++++++++----------
 net/devlink/devl_internal.h | 17 +++++++++++------
 net/devlink/leftover.c      |  4 ++--
 net/devlink/netlink.c       | 21 ++++++++++++---------
 4 files changed, 37 insertions(+), 27 deletions(-)

diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index 2e120b3da2203..5dfba2248b904 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -217,17 +217,18 @@ int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info)
 }
 
 static int
-devlink_nl_cmd_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-			    struct netlink_callback *cb)
+devlink_nl_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+			struct netlink_callback *cb)
 {
 	return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW,
 			       NETLINK_CB(cb->skb).portid,
 			       cb->nlh->nlmsg_seq, NLM_F_MULTI);
 }
 
-const struct devlink_cmd devl_cmd_get = {
-	.dump_one		= devlink_nl_cmd_get_dump_one,
-};
+int devlink_nl_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(msg, cb, devlink_nl_get_dump_one);
+}
 
 static void devlink_reload_failed_set(struct devlink *devlink,
 				      bool reload_failed)
@@ -826,8 +827,8 @@ int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info)
 }
 
 static int
-devlink_nl_cmd_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-				 struct netlink_callback *cb)
+devlink_nl_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+			     struct netlink_callback *cb)
 {
 	int err;
 
@@ -840,9 +841,10 @@ devlink_nl_cmd_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_info_get = {
-	.dump_one		= devlink_nl_cmd_info_get_dump_one,
-};
+int devlink_nl_info_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(msg, cb, devlink_nl_info_get_dump_one);
+}
 
 static int devlink_nl_flash_update_fill(struct sk_buff *msg,
 					struct devlink *devlink,
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index d32a32705430a..7d0a9dd1acebd 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -114,9 +114,12 @@ struct devlink_nl_dump_state {
 	};
 };
 
+typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg,
+				       struct devlink *devlink,
+				       struct netlink_callback *cb);
+
 struct devlink_cmd {
-	int (*dump_one)(struct sk_buff *msg, struct devlink *devlink,
-			struct netlink_callback *cb);
+	devlink_nl_dump_one_func_t *dump_one;
 };
 
 extern const struct genl_small_ops devlink_nl_small_ops[56];
@@ -127,8 +130,9 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs);
 void devlink_notify_unregister(struct devlink *devlink);
 void devlink_notify_register(struct devlink *devlink);
 
-int devlink_nl_instance_iter_dumpit(struct sk_buff *msg,
-				    struct netlink_callback *cb);
+int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
+		      devlink_nl_dump_one_func_t *dump_one);
+int devlink_nl_instance_iter_dumpit(struct sk_buff *msg, struct netlink_callback *cb);
 
 static inline struct devlink_nl_dump_state *
 devlink_dump_state(struct netlink_callback *cb)
@@ -149,7 +153,6 @@ devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
 }
 
 /* Commands */
-extern const struct devlink_cmd devl_cmd_get;
 extern const struct devlink_cmd devl_cmd_port_get;
 extern const struct devlink_cmd devl_cmd_sb_get;
 extern const struct devlink_cmd devl_cmd_sb_pool_get;
@@ -157,7 +160,6 @@ extern const struct devlink_cmd devl_cmd_sb_port_pool_get;
 extern const struct devlink_cmd devl_cmd_sb_tc_pool_bind_get;
 extern const struct devlink_cmd devl_cmd_param_get;
 extern const struct devlink_cmd devl_cmd_region_get;
-extern const struct devlink_cmd devl_cmd_info_get;
 extern const struct devlink_cmd devl_cmd_health_reporter_get;
 extern const struct devlink_cmd devl_cmd_trap_get;
 extern const struct devlink_cmd devl_cmd_trap_group_get;
@@ -215,10 +217,13 @@ devlink_rate_node_get_from_info(struct devlink *devlink,
 				struct genl_info *info);
 /* Devlink nl cmds */
 int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_info_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
 int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 094cd0e8224e9..895b732bed8e8 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -6283,7 +6283,7 @@ const struct genl_small_ops devlink_nl_small_ops[56] = {
 		.cmd = DEVLINK_CMD_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
@@ -6537,7 +6537,7 @@ const struct genl_small_ops devlink_nl_small_ops[56] = {
 		.cmd = DEVLINK_CMD_INFO_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_info_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_info_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 82a3238d5344e..624d0db7e229a 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -178,7 +178,6 @@ static void devlink_nl_post_doit(const struct genl_split_ops *ops,
 }
 
 static const struct devlink_cmd *devl_cmds[] = {
-	[DEVLINK_CMD_GET]		= &devl_cmd_get,
 	[DEVLINK_CMD_PORT_GET]		= &devl_cmd_port_get,
 	[DEVLINK_CMD_SB_GET]		= &devl_cmd_sb_get,
 	[DEVLINK_CMD_SB_POOL_GET]	= &devl_cmd_sb_pool_get,
@@ -186,7 +185,6 @@ static const struct devlink_cmd *devl_cmds[] = {
 	[DEVLINK_CMD_SB_TC_POOL_BIND_GET] = &devl_cmd_sb_tc_pool_bind_get,
 	[DEVLINK_CMD_PARAM_GET]		= &devl_cmd_param_get,
 	[DEVLINK_CMD_REGION_GET]	= &devl_cmd_region_get,
-	[DEVLINK_CMD_INFO_GET]		= &devl_cmd_info_get,
 	[DEVLINK_CMD_HEALTH_REPORTER_GET] = &devl_cmd_health_reporter_get,
 	[DEVLINK_CMD_TRAP_GET]		= &devl_cmd_trap_get,
 	[DEVLINK_CMD_TRAP_GROUP_GET]	= &devl_cmd_trap_group_get,
@@ -196,23 +194,19 @@ static const struct devlink_cmd *devl_cmds[] = {
 	[DEVLINK_CMD_SELFTESTS_GET]	= &devl_cmd_selftests_get,
 };
 
-int devlink_nl_instance_iter_dumpit(struct sk_buff *msg,
-				    struct netlink_callback *cb)
+int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
+		      devlink_nl_dump_one_func_t *dump_one)
 {
-	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	const struct devlink_cmd *cmd;
 	struct devlink *devlink;
 	int err = 0;
 
-	cmd = devl_cmds[info->op.cmd];
-
 	while ((devlink = devlinks_xa_find_get(sock_net(msg->sk),
 					       &state->instance))) {
 		devl_lock(devlink);
 
 		if (devl_is_registered(devlink))
-			err = cmd->dump_one(msg, devlink, cb);
+			err = dump_one(msg, devlink, cb);
 		else
 			err = 0;
 
@@ -233,6 +227,15 @@ int devlink_nl_instance_iter_dumpit(struct sk_buff *msg,
 	return msg->len;
 }
 
+int devlink_nl_instance_iter_dumpit(struct sk_buff *msg,
+				    struct netlink_callback *cb)
+{
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	const struct devlink_cmd *cmd = devl_cmds[info->op.cmd];
+
+	return devlink_nl_dumpit(msg, cb, cmd->dump_one);
+}
+
 struct genl_family devlink_nl_family __ro_after_init = {
 	.name		= DEVLINK_GENL_NAME,
 	.version	= DEVLINK_GENL_VERSION,
-- 
GitLab


From 8300dce542e45c50ef318c4493bbb2e7966a883c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:36 +0200
Subject: [PATCH 0886/1806] devlink: un-static devlink_nl_pre/post_doit()

To be prepared for the follow-up generated split ops addition,
make the functions devlink_nl_pre_doit() and devlink_nl_post_doit()
usable outside of netlink.c. Introduce temporary prototypes which are
going to be removed once the generated header will be included.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-9-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h | 4 ++++
 net/devlink/netlink.c       | 8 ++++----
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 7d0a9dd1acebd..0befa1869fde5 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -216,6 +216,10 @@ struct devlink_rate *
 devlink_rate_node_get_from_info(struct devlink *devlink,
 				struct genl_info *info);
 /* Devlink nl cmds */
+int devlink_nl_pre_doit(const struct genl_split_ops *ops,
+			struct sk_buff *skb, struct genl_info *info);
+void devlink_nl_post_doit(const struct genl_split_ops *ops,
+			  struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 624d0db7e229a..98d5c6b0acd8f 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -109,8 +109,8 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs)
 	return ERR_PTR(-ENODEV);
 }
 
-static int devlink_nl_pre_doit(const struct genl_split_ops *ops,
-			       struct sk_buff *skb, struct genl_info *info)
+int devlink_nl_pre_doit(const struct genl_split_ops *ops,
+			struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink_linecard *linecard;
 	struct devlink_port *devlink_port;
@@ -167,8 +167,8 @@ unlock:
 	return err;
 }
 
-static void devlink_nl_post_doit(const struct genl_split_ops *ops,
-				 struct sk_buff *skb, struct genl_info *info)
+void devlink_nl_post_doit(const struct genl_split_ops *ops,
+			  struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink;
 
-- 
GitLab


From 759f661012d19e61e8d7e8d2bc8d4395ba45a689 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:37 +0200
Subject: [PATCH 0887/1806] netlink: specs: devlink: add info-get dump op

Add missing dump op for info-get command and re-generate related
devlink-user.[ch] code.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-10-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/devlink.yaml |  4 +-
 tools/net/ynl/generated/devlink-user.c   | 53 ++++++++++++++++++++++++
 tools/net/ynl/generated/devlink-user.h   | 10 +++++
 3 files changed, 66 insertions(+), 1 deletion(-)

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 5d46ca9669792..12699b7ce292f 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -194,7 +194,7 @@ operations:
         request:
           value: 51
           attributes: *dev-id-attrs
-        reply:
+        reply: &info-get-reply
           value: 51
           attributes:
             - bus-name
@@ -204,3 +204,5 @@ operations:
             - info-version-fixed
             - info-version-running
             - info-version-stored
+      dump:
+        reply: *info-get-reply
diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c
index 939bd45feacad..8492789433b9e 100644
--- a/tools/net/ynl/generated/devlink-user.c
+++ b/tools/net/ynl/generated/devlink-user.c
@@ -716,6 +716,59 @@ err_free:
 	return NULL;
 }
 
+/* DEVLINK_CMD_INFO_GET - dump */
+void devlink_info_get_list_free(struct devlink_info_get_list *rsp)
+{
+	struct devlink_info_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		unsigned int i;
+
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp->obj.info_driver_name);
+		free(rsp->obj.info_serial_number);
+		for (i = 0; i < rsp->obj.n_info_version_fixed; i++)
+			devlink_dl_info_version_free(&rsp->obj.info_version_fixed[i]);
+		free(rsp->obj.info_version_fixed);
+		for (i = 0; i < rsp->obj.n_info_version_running; i++)
+			devlink_dl_info_version_free(&rsp->obj.info_version_running[i]);
+		free(rsp->obj.info_version_running);
+		for (i = 0; i < rsp->obj.n_info_version_stored; i++)
+			devlink_dl_info_version_free(&rsp->obj.info_version_stored[i]);
+		free(rsp->obj.info_version_stored);
+		free(rsp);
+	}
+}
+
+struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_info_get_list);
+	yds.cb = devlink_info_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_INFO_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_INFO_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_info_get_list_free(yds.first);
+	return NULL;
+}
+
 const struct ynl_family ynl_devlink_family =  {
 	.name		= "devlink",
 };
diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h
index a008b99b6e241..af65e2f2f5295 100644
--- a/tools/net/ynl/generated/devlink-user.h
+++ b/tools/net/ynl/generated/devlink-user.h
@@ -207,4 +207,14 @@ void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp);
 struct devlink_info_get_rsp *
 devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req);
 
+/* DEVLINK_CMD_INFO_GET - dump */
+struct devlink_info_get_list {
+	struct devlink_info_get_list *next;
+	struct devlink_info_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_info_get_list_free(struct devlink_info_get_list *rsp);
+
+struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys);
+
 #endif /* _LINUX_DEVLINK_GEN_H */
-- 
GitLab


From 6b7c486cae8136050df8fca2fbebedb685c49b2d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:38 +0200
Subject: [PATCH 0888/1806] devlink: add split ops generated according to spec

Improve the existing devlink spec in order to serve as a source for
generation of valid devlink split ops for the existing commands.
Add the generated sources.

Node that the policies are narrowed down only to the attributes that
are actually parsed. The dont-validate-strict parsing policy makes sure
that other possibly passed garbage attributes from userspace are
ignored during validation.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-11-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/devlink.yaml | 10 ++++
 net/devlink/Makefile                     |  2 +-
 net/devlink/netlink_gen.c                | 59 ++++++++++++++++++++++++
 net/devlink/netlink_gen.h                | 29 ++++++++++++
 4 files changed, 99 insertions(+), 1 deletion(-)
 create mode 100644 net/devlink/netlink_gen.c
 create mode 100644 net/devlink/netlink_gen.h

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 12699b7ce292f..f6df0b3fd502f 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -165,8 +165,13 @@ operations:
       name: get
       doc: Get devlink instances.
       attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
 
       do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
         request:
           value: 1
           attributes: &dev-id-attrs
@@ -189,8 +194,13 @@ operations:
       name: info-get
       doc: Get device information, like driver name, hardware and firmware versions etc.
       attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
 
       do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
         request:
           value: 51
           attributes: *dev-id-attrs
diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index ef91a76646a33..a087af581847e 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-y := leftover.o core.o netlink.o dev.o health.o
+obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o health.o
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
new file mode 100644
index 0000000000000..32d8cbed0c307
--- /dev/null
+++ b/net/devlink/netlink_gen.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/devlink.yaml */
+/* YNL-GEN kernel source */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "netlink_gen.h"
+
+#include <uapi/linux/devlink.h>
+
+/* DEVLINK_CMD_GET - do */
+static const struct nla_policy devlink_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_INFO_GET - do */
+static const struct nla_policy devlink_info_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* Ops table for devlink */
+const struct genl_split_ops devlink_nl_ops[4] = {
+	{
+		.cmd		= DEVLINK_CMD_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_INFO_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_info_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_info_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_INFO_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_info_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+};
diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h
new file mode 100644
index 0000000000000..11980e04a7186
--- /dev/null
+++ b/net/devlink/netlink_gen.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/devlink.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_DEVLINK_GEN_H
+#define _LINUX_DEVLINK_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/devlink.h>
+
+/* Ops table for devlink */
+extern const struct genl_split_ops devlink_nl_ops[4];
+
+int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+			struct genl_info *info);
+void
+devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		     struct genl_info *info);
+
+int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_info_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+
+#endif /* _LINUX_DEVLINK_GEN_H */
-- 
GitLab


From b2551b1517d86ff5e258e7bc834e5be0e1ce08de Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:39 +0200
Subject: [PATCH 0889/1806] devlink: include the generated netlink header

Put the newly added generated header to the include list. Remove the
duplicated temporary function prototypes.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-12-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 0befa1869fde5..51de0e1fc769c 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -12,6 +12,8 @@
 #include <net/devlink.h>
 #include <net/net_namespace.h>
 
+#include "netlink_gen.h"
+
 #define DEVLINK_REGISTERED XA_MARK_1
 
 #define DEVLINK_RELOAD_STATS_ARRAY_SIZE \
@@ -216,18 +218,9 @@ struct devlink_rate *
 devlink_rate_node_get_from_info(struct devlink *devlink,
 				struct genl_info *info);
 /* Devlink nl cmds */
-int devlink_nl_pre_doit(const struct genl_split_ops *ops,
-			struct sk_buff *skb, struct genl_info *info);
-void devlink_nl_post_doit(const struct genl_split_ops *ops,
-			  struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_info_get_dumpit(struct sk_buff *skb,
-			       struct netlink_callback *cb);
 int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info);
-- 
GitLab


From 6e067d0cab68a64ef3488b5639a66b65e91b146d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 3 Aug 2023 13:13:40 +0200
Subject: [PATCH 0890/1806] devlink: use generated split ops and remove
 duplicated commands from small ops

Do the switch and use generated split ops for get and info_get commands.
Remove those from small ops array.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-13-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h |  2 +-
 net/devlink/leftover.c      | 16 +---------------
 net/devlink/netlink.c       |  2 ++
 3 files changed, 4 insertions(+), 16 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 51de0e1fc769c..7fdd956ff992d 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -124,7 +124,7 @@ struct devlink_cmd {
 	devlink_nl_dump_one_func_t *dump_one;
 };
 
-extern const struct genl_small_ops devlink_nl_small_ops[56];
+extern const struct genl_small_ops devlink_nl_small_ops[54];
 
 struct devlink *
 devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 895b732bed8e8..3bf42f5335ed4 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -6278,14 +6278,7 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
 	return devlink_trap_policer_set(devlink, policer_item, info);
 }
 
-const struct genl_small_ops devlink_nl_small_ops[56] = {
-	{
-		.cmd = DEVLINK_CMD_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_get_doit,
-		.dumpit = devlink_nl_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
+const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_PORT_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -6533,13 +6526,6 @@ const struct genl_small_ops devlink_nl_small_ops[56] = {
 		.dumpit = devlink_nl_cmd_region_read_dumpit,
 		.flags = GENL_ADMIN_PERM,
 	},
-	{
-		.cmd = DEVLINK_CMD_INFO_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_info_get_doit,
-		.dumpit = devlink_nl_info_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 98d5c6b0acd8f..bada2819827bc 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -248,6 +248,8 @@ struct genl_family devlink_nl_family __ro_after_init = {
 	.module		= THIS_MODULE,
 	.small_ops	= devlink_nl_small_ops,
 	.n_small_ops	= ARRAY_SIZE(devlink_nl_small_ops),
+	.split_ops	= devlink_nl_ops,
+	.n_split_ops	= ARRAY_SIZE(devlink_nl_ops),
 	.resv_start_op	= DEVLINK_CMD_SELFTESTS_RUN + 1,
 	.mcgrps		= devlink_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(devlink_nl_mcgrps),
-- 
GitLab


From 8a60a041eada0fbfdc7b6b7a10fdf68ae6a840ce Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 3 Aug 2023 17:51:01 -0700
Subject: [PATCH 0891/1806] bpf: fix inconsistent return types of
 bpf_xdp_copy_buf().

Fix inconsistent return types in two implementations of bpf_xdp_copy_buf().

There are two implementations: one is an empty implementation whose return
type does not match the actual implementation.

Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230804005101.1534505-1-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/filter.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 2d6fe30bad5f1..761af6b3cf2bc 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1572,10 +1572,9 @@ static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len)
 	return NULL;
 }
 
-static inline void *bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf,
-				     unsigned long len, bool flush)
+static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf,
+				    unsigned long len, bool flush)
 {
-	return NULL;
 }
 #endif /* CONFIG_NET */
 
-- 
GitLab


From 5426700e6841bf72e652e34b5cec68eadf442435 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Thu, 3 Aug 2023 16:12:06 -0700
Subject: [PATCH 0892/1806] bpf: fix bpf_dynptr_slice() to stop return an
 ERR_PTR.

Verify if the pointer obtained from bpf_xdp_pointer() is either an error or
NULL before returning it.

The function bpf_dynptr_slice() mistakenly returned an ERR_PTR. Instead of
solely checking for NULL, it should also verify if the pointer returned by
bpf_xdp_pointer() is an error or NULL.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/bpf/d1360219-85c3-4a03-9449-253ea905f9d1@moroto.mountain/
Fixes: 66e3a13e7c2c ("bpf: Add bpf_dynptr_slice and bpf_dynptr_slice_rdwr")
Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230803231206.1060485-1-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/helpers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 56ce5008aedda..eb91cae0612ae 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2270,7 +2270,7 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
 	case BPF_DYNPTR_TYPE_XDP:
 	{
 		void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len);
-		if (xdp_ptr)
+		if (!IS_ERR_OR_NULL(xdp_ptr))
 			return xdp_ptr;
 
 		if (!buffer__opt)
-- 
GitLab


From dde3979bb3451c820b540151f5903bfd2e814f60 Mon Sep 17 00:00:00 2001
From: Sergey Kacheev <s.kacheev@gmail.com>
Date: Wed, 2 Aug 2023 21:22:14 +0300
Subject: [PATCH 0893/1806] libbpf: Use local includes inside the library

In our monrepo, we try to minimize special processing when importing
(aka vendor) third-party source code. Ideally, we try to import
directly from the repositories with the code without changing it, we
try to stick to the source code dependency instead of the artifact
dependency. In the current situation, a patch has to be made for
libbpf to fix the includes in bpf headers so that they work directly
from libbpf/src.

Signed-off-by: Sergey Kacheev <s.kacheev@gmail.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/CAJVhQqUg6OKq6CpVJP5ng04Dg+z=igevPpmuxTqhsR3dKvd9+Q@mail.gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/lib/bpf/bpf_tracing.h | 2 +-
 tools/lib/bpf/usdt.bpf.h    | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index be076a4041ab1..3803479dbe106 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -2,7 +2,7 @@
 #ifndef __BPF_TRACING_H__
 #define __BPF_TRACING_H__
 
-#include <bpf/bpf_helpers.h>
+#include "bpf_helpers.h"
 
 /* Scan the ARCH passed in from ARCH env variable (see Makefile) */
 #if defined(__TARGET_ARCH_x86)
diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h
index 0bd4c135acc21..f6763300b26a4 100644
--- a/tools/lib/bpf/usdt.bpf.h
+++ b/tools/lib/bpf/usdt.bpf.h
@@ -4,8 +4,8 @@
 #define __USDT_BPF_H__
 
 #include <linux/errno.h>
-#include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
+#include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 /* Below types and maps are internal implementation details of libbpf's USDT
  * support and are subjects to change. Also, bpf_usdt_xxx() API helpers should
-- 
GitLab


From 57ecc157b68eac54ee7cdc039e0df8f7f7bd5bc7 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Thu, 3 Aug 2023 21:47:47 +0800
Subject: [PATCH 0894/1806] net: llc: Remove unused function declarations

llc_conn_ac_send_i_rsp_as_ack() and llc_conn_ev_sendack_tmr_exp()
are never implemented since beginning of git history.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230803134747.41512-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/llc_c_ac.h | 1 -
 include/net/llc_c_ev.h | 1 -
 2 files changed, 2 deletions(-)

diff --git a/include/net/llc_c_ac.h b/include/net/llc_c_ac.h
index 3e1f76786d7ba..7620a9196922f 100644
--- a/include/net/llc_c_ac.h
+++ b/include/net/llc_c_ac.h
@@ -175,7 +175,6 @@ int llc_conn_ac_send_ack_if_needed(struct sock *sk, struct sk_buff *skb);
 int llc_conn_ac_adjust_npta_by_rr(struct sock *sk, struct sk_buff *skb);
 int llc_conn_ac_adjust_npta_by_rnr(struct sock *sk, struct sk_buff *skb);
 int llc_conn_ac_rst_sendack_flag(struct sock *sk, struct sk_buff *skb);
-int llc_conn_ac_send_i_rsp_as_ack(struct sock *sk, struct sk_buff *skb);
 int llc_conn_ac_send_i_as_ack(struct sock *sk, struct sk_buff *skb);
 
 void llc_conn_busy_tmr_cb(struct timer_list *t);
diff --git a/include/net/llc_c_ev.h b/include/net/llc_c_ev.h
index 3948cf111dd0d..2418899551579 100644
--- a/include/net/llc_c_ev.h
+++ b/include/net/llc_c_ev.h
@@ -158,7 +158,6 @@ int llc_conn_ev_p_tmr_exp(struct sock *sk, struct sk_buff *skb);
 int llc_conn_ev_ack_tmr_exp(struct sock *sk, struct sk_buff *skb);
 int llc_conn_ev_rej_tmr_exp(struct sock *sk, struct sk_buff *skb);
 int llc_conn_ev_busy_tmr_exp(struct sock *sk, struct sk_buff *skb);
-int llc_conn_ev_sendack_tmr_exp(struct sock *sk, struct sk_buff *skb);
 /* NOT_USED functions and their variations */
 int llc_conn_ev_rx_xxx_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb);
 int llc_conn_ev_rx_xxx_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb);
-- 
GitLab


From faa9039161ef0271bc36c2bf4d01c7897f07524d Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Thu, 3 Aug 2023 21:51:38 +0800
Subject: [PATCH 0895/1806] net: hns3: Remove unused function declarations

Commit 1e6e76101fd9 ("net: hns3: configure promisc mode for VF asynchronously")
left behind hclge_inform_vf_promisc_info() declaration.
And commit 68c0a5c70614 ("net: hns3: Add HNS3 IMP(Integrated Mgmt Proc) Cmd Interface Support")
declared but never implemented hclge_cmd_mdio_write() and hclge_cmd_mdio_read().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230803135138.37456-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h  | 4 ----
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 1 -
 2 files changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 91c173f40701a..0bd858620f27b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -886,8 +886,4 @@ struct hclge_query_wol_supported_cmd {
 
 struct hclge_hw;
 int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num);
-enum hclge_comm_cmd_status hclge_cmd_mdio_write(struct hclge_hw *hw,
-						struct hclge_desc *desc);
-enum hclge_comm_cmd_status hclge_cmd_mdio_read(struct hclge_hw *hw,
-					       struct hclge_desc *desc);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 6a43d1515585f..70b059e6d35f8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1146,7 +1146,6 @@ int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev,
 				struct hclge_desc *desc);
 void hclge_report_hw_error(struct hclge_dev *hdev,
 			   enum hnae3_hw_error_type type);
-void hclge_inform_vf_promisc_info(struct hclge_vport *vport);
 int hclge_dbg_dump_rst_info(struct hclge_dev *hdev, char *buf, int len);
 int hclge_push_vf_link_status(struct hclge_vport *vport);
 int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en);
-- 
GitLab


From c4a6b2da4b59d4819e1d35446ca9363166388051 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 Aug 2023 13:54:16 +0000
Subject: [PATCH 0896/1806] tcp_metrics: hash table allocation cleanup

After commit 098a697b497e ("tcp_metrics: Use a single hash table
for all network namespaces.") we can avoid calling tcp_net_metrics_init()
for each new netns.

Instead, rename tcp_net_metrics_init() to tcp_metrics_hash_alloc(),
and move it to __init section.

Also move tcpmhash_entries to __initdata section.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230803135417.2716879-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_metrics.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 99ac5efe244d3..c196759f1d3bd 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -990,7 +990,7 @@ static struct genl_family tcp_metrics_nl_family __ro_after_init = {
 	.resv_start_op	= TCP_METRICS_CMD_DEL + 1,
 };
 
-static unsigned int tcpmhash_entries;
+static unsigned int tcpmhash_entries __initdata;
 static int __init set_tcpmhash_entries(char *str)
 {
 	ssize_t ret;
@@ -1006,15 +1006,11 @@ static int __init set_tcpmhash_entries(char *str)
 }
 __setup("tcpmhash_entries=", set_tcpmhash_entries);
 
-static int __net_init tcp_net_metrics_init(struct net *net)
+static void __init tcp_metrics_hash_alloc(void)
 {
+	unsigned int slots = tcpmhash_entries;
 	size_t size;
-	unsigned int slots;
 
-	if (!net_eq(net, &init_net))
-		return 0;
-
-	slots = tcpmhash_entries;
 	if (!slots) {
 		if (totalram_pages() >= 128 * 1024)
 			slots = 16 * 1024;
@@ -1027,9 +1023,7 @@ static int __net_init tcp_net_metrics_init(struct net *net)
 
 	tcp_metrics_hash = kvzalloc(size, GFP_KERNEL);
 	if (!tcp_metrics_hash)
-		return -ENOMEM;
-
-	return 0;
+		panic("Could not allocate the tcp_metrics hash table\n");
 }
 
 static void __net_exit tcp_net_metrics_exit_batch(struct list_head *net_exit_list)
@@ -1038,7 +1032,6 @@ static void __net_exit tcp_net_metrics_exit_batch(struct list_head *net_exit_lis
 }
 
 static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
-	.init		=	tcp_net_metrics_init,
 	.exit_batch	=	tcp_net_metrics_exit_batch,
 };
 
@@ -1046,9 +1039,11 @@ void __init tcp_metrics_init(void)
 {
 	int ret;
 
+	tcp_metrics_hash_alloc();
+
 	ret = register_pernet_subsys(&tcp_net_metrics_ops);
 	if (ret < 0)
-		panic("Could not allocate the tcp_metrics hash table\n");
+		panic("Could not register tcp_net_metrics_ops\n");
 
 	ret = genl_register_family(&tcp_metrics_nl_family);
 	if (ret < 0)
-- 
GitLab


From 2f0e807bc2f105435be902997a385ebab86d1a7c Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Thu, 3 Aug 2023 21:54:24 +0800
Subject: [PATCH 0897/1806] net: 802: Remove unused function declarations

Commit d8d9ba8dc9c7 ("net: 802: remove dead leftover after ipx driver removal")
remove these implementations but leave the declarations.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230803135424.41664-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/p8022.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/include/net/p8022.h b/include/net/p8022.h
index b690ffcad66b7..a29e224ac498a 100644
--- a/include/net/p8022.h
+++ b/include/net/p8022.h
@@ -13,7 +13,4 @@ register_8022_client(unsigned char type,
 				 struct packet_type *pt,
 				 struct net_device *orig_dev));
 void unregister_8022_client(struct datalink_proto *proto);
-
-struct datalink_proto *make_8023_client(void);
-void destroy_8023_client(struct datalink_proto *dl);
 #endif
-- 
GitLab


From 781486e415dc701466a25e49fb8bcc28362d80bf Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Thu, 3 Aug 2023 21:45:07 +0800
Subject: [PATCH 0898/1806] af_vsock: Remove unused declaration
 vsock_release_pending()/vsock_init_tap()

Commit d021c344051a ("VSOCK: Introduce VM Sockets") declared but never implemented
vsock_release_pending(). Also vsock_init_tap() never implemented since introduction
in commit 531b374834c8 ("VSOCK: Add vsockmon tap functions").

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://lore.kernel.org/r/20230803134507.22660-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/af_vsock.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 0e7504a42925f..b01cf9ac24371 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -201,7 +201,6 @@ static inline bool __vsock_in_connected_table(struct vsock_sock *vsk)
 	return !list_empty(&vsk->connected_table);
 }
 
-void vsock_release_pending(struct sock *pending);
 void vsock_add_pending(struct sock *listener, struct sock *pending);
 void vsock_remove_pending(struct sock *listener, struct sock *pending);
 void vsock_enqueue_accept(struct sock *listener, struct sock *connected);
@@ -225,7 +224,6 @@ struct vsock_tap {
 	struct list_head list;
 };
 
-int vsock_init_tap(void);
 int vsock_add_tap(struct vsock_tap *vt);
 int vsock_remove_tap(struct vsock_tap *vt);
 void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque);
-- 
GitLab


From 1e8e2efb34023c5113ec679eae3c59ae2cd57b13 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Thu, 3 Aug 2023 10:31:28 +0800
Subject: [PATCH 0899/1806] bpf: change bpf_alu_sign_string and
 bpf_movsx_string to static

The bpf_alu_sign_string and bpf_movsx_string introduced in commit
f835bb622299 ("bpf: Add kernel/bpftool asm support for new instructions")
are only used in disasm.c now, change them to static.

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308050615.wxAn1v2J-lkp@intel.com/
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230803023128.3753323-1-yangyingliang@huawei.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/disasm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index ef7c107c7b8f2..49940c26a2274 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -87,12 +87,12 @@ const char *const bpf_alu_string[16] = {
 	[BPF_END >> 4]  = "endian",
 };
 
-const char *const bpf_alu_sign_string[16] = {
+static const char *const bpf_alu_sign_string[16] = {
 	[BPF_DIV >> 4]  = "s/=",
 	[BPF_MOD >> 4]  = "s%=",
 };
 
-const char *const bpf_movsx_string[4] = {
+static const char *const bpf_movsx_string[4] = {
 	[0] = "(s8)",
 	[1] = "(s16)",
 	[3] = "(s32)",
-- 
GitLab


From f5f2d9bb52f901929c04ea2585160f1b7317071d Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Thu, 3 Aug 2023 22:19:04 +0800
Subject: [PATCH 0900/1806] ixgbevf: Remove unused function declarations

ixgbe_napi_add_all()/ixgbe_napi_del_all() are declared but never implemented in
commit 92915f71201b ("ixgbevf: Driver main and ethool interface module and main header")

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230803141904.15316-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbevf/ixgbevf.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 149c733fcc2b3..130cb868774c4 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -486,9 +486,6 @@ static inline int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring,
 { return 0; }
 #endif /* CONFIG_IXGBEVF_IPSEC */
 
-void ixgbe_napi_add_all(struct ixgbevf_adapter *adapter);
-void ixgbe_napi_del_all(struct ixgbevf_adapter *adapter);
-
 #define ixgbevf_hw_to_netdev(hw) \
 	(((struct ixgbevf_adapter *)(hw)->back)->netdev)
 
-- 
GitLab


From 852c18d5611e5632b8d4456181462896e87b1662 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Thu, 3 Aug 2023 22:20:47 +0800
Subject: [PATCH 0901/1806] mlxsw: spectrum: Remove unused function
 declarations

Commit c3d2ed93b14d ("mlxsw: Remove old parsing depth infrastructure")
left behind mlxsw_sp_nve_inc_parsing_depth_get()/mlxsw_sp_nve_inc_parsing_depth_put().
And commit 532b49e41e64 ("mlxsw: spectrum_span: Derive SBIB from maximum port speed & MTU")
remove mlxsw_sp_span_port_mtu_update()/mlxsw_sp_span_speed_update_work() but leave the
declarations.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://lore.kernel.org/r/20230803142047.42660-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h      | 4 ----
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h | 5 -----
 2 files changed, 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 62151f0531aee..8da7bb04fc3ad 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -1401,10 +1401,6 @@ void mlxsw_sp_port_nve_fini(struct mlxsw_sp_port *mlxsw_sp_port);
 int mlxsw_sp_nve_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_nve_fini(struct mlxsw_sp *mlxsw_sp);
 
-/* spectrum_nve_vxlan.c */
-int mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp);
-void mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp);
-
 /* spectrum_trap.c */
 int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_devlink_traps_fini(struct mlxsw_sp *mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
index 82e711afb02bb..c59b5f11f357f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
@@ -93,13 +93,8 @@ void mlxsw_sp_span_respin(struct mlxsw_sp *mlxsw_sp);
 struct mlxsw_sp_span_entry *
 mlxsw_sp_span_entry_find_by_port(struct mlxsw_sp *mlxsw_sp,
 				 const struct net_device *to_dev);
-
 void mlxsw_sp_span_entry_invalidate(struct mlxsw_sp *mlxsw_sp,
 				    struct mlxsw_sp_span_entry *span_entry);
-
-int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu);
-void mlxsw_sp_span_speed_update_work(struct work_struct *work);
-
 int mlxsw_sp_span_agent_get(struct mlxsw_sp *mlxsw_sp, int *p_span_id,
 			    const struct mlxsw_sp_span_agent_parms *parms);
 void mlxsw_sp_span_agent_put(struct mlxsw_sp *mlxsw_sp, int span_id);
-- 
GitLab


From f4bf467883f210d0bfbe784fffca52887de147fb Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 3 Aug 2023 16:56:24 +0100
Subject: [PATCH 0902/1806] net: phy: move marking PHY on SFP module into SFP
 code

Move marking the PHY as being on a SFP module into the SFP code between
getting the PHY device (and thus initialising the phy_device structure)
and registering the discovered device.

This means that PHY drivers can use phy_on_sfp() in their match and
get_features methods.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qRaga-001vKt-8X@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 2 --
 drivers/net/phy/sfp.c        | 3 +++
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index e19c4fee8d229..3e9909b309385 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1489,8 +1489,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 
 		if (phydev->sfp_bus_attached)
 			dev->sfp_bus = phydev->sfp_bus;
-		else if (dev->sfp_bus)
-			phydev->is_on_sfp_module = true;
 	}
 
 	/* Some Ethernet drivers try to connect to a PHY device before
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index d855a18308d78..4ecfac2278651 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -1763,6 +1763,9 @@ static int sfp_sm_probe_phy(struct sfp *sfp, int addr, bool is_c45)
 		return PTR_ERR(phy);
 	}
 
+	/* Mark this PHY as being on a SFP module */
+	phy->is_on_sfp_module = true;
+
 	err = phy_device_register(phy);
 	if (err) {
 		phy_device_free(phy);
-- 
GitLab


From d0f2b7a9ca0a1a89d65ee145815f89b54b7f977f Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 3 Aug 2023 15:45:51 -0700
Subject: [PATCH 0903/1806] tcp: Disable header prediction for MD5 flow.

TCP socket saves the minimum required header length in tcp_header_len
of struct tcp_sock, and later the value is used in __tcp_fast_path_on()
to generate a part of TCP header in tcp_sock(sk)->pred_flags.

In tcp_rcv_established(), if the incoming packet has the same pattern
with pred_flags, we enter the fast path and skip full option parsing.

The MD5 option is parsed in tcp_v[46]_rcv(), so we need not parse it
again later in tcp_rcv_established() unless other options exist.  We
add TCPOLEN_MD5SIG_ALIGNED to tcp_header_len in two paths to avoid the
slow path.

For passive open connections with MD5, we add TCPOLEN_MD5SIG_ALIGNED
to tcp_header_len in tcp_create_openreq_child() after 3WHS.

On the other hand, we do it in tcp_connect_init() for active open
connections.  However, the value is overwritten while processing
SYN+ACK or crossed SYN in tcp_rcv_synsent_state_process().

These two cases will have the wrong value in pred_flags and never go
into the fast path.

We could update tcp_header_len in tcp_rcv_synsent_state_process(), but
a test with slightly modified netperf which uses MD5 for each flow shows
that the slow path is actually a bit faster than the fast path.

  On c5.4xlarge EC2 instance (16 vCPU, 32 GiB mem)

  $ for i in {1..10}; do
  ./super_netperf $(nproc) -H localhost -l 10 -- -m 256 -M 256;
  done

  Avg of 10
  * 36e68eadd303  : 10.376 Gbps
  * all fast path : 10.374 Gbps (patch v2, See Link)
  * all slow path : 10.394 Gbps

The header prediction is not worth adding complexity for MD5, so let's
disable it for MD5.

Link: https://lore.kernel.org/netdev/20230803042214.38309-1-kuniyu@amazon.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230803224552.69398-2-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_minisocks.c | 2 --
 net/ipv4/tcp_output.c    | 5 -----
 2 files changed, 7 deletions(-)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index c8f2aa0033871..ddba3b67f7c8e 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -570,8 +570,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	newtp->tsoffset = treq->ts_off;
 #ifdef CONFIG_TCP_MD5SIG
 	newtp->md5sig_info = NULL;	/*XXX*/
-	if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req)))
-		newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
 #endif
 	if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
 		newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 51d8638d4b4c6..c5412ee77fc8d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3741,11 +3741,6 @@ static void tcp_connect_init(struct sock *sk)
 	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps))
 		tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED;
 
-#ifdef CONFIG_TCP_MD5SIG
-	if (tp->af_specific->md5_lookup(sk, sk))
-		tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
-#endif
-
 	/* If user gave his TCP_MAXSEG, record it to clamp */
 	if (tp->rx_opt.user_mss)
 		tp->rx_opt.mss_clamp = tp->rx_opt.user_mss;
-- 
GitLab


From b205153689326d22e48b22f21d1ae593df9e85d3 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 3 Aug 2023 15:45:52 -0700
Subject: [PATCH 0904/1806] tcp: Update stale comment for MD5 in
 tcp_parse_options().

Since commit 9ea88a153001 ("tcp: md5: check md5 signature without socket
lock"), the MD5 option is checked in tcp_v[46]_rcv().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230803224552.69398-3-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_input.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 670c3dab24f2b..2995802126e4e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4126,9 +4126,8 @@ void tcp_parse_options(const struct net *net,
 				break;
 #ifdef CONFIG_TCP_MD5SIG
 			case TCPOPT_MD5SIG:
-				/*
-				 * The MD5 Hash has already been
-				 * checked (see tcp_v{4,6}_do_rcv()).
+				/* The MD5 Hash has already been
+				 * checked (see tcp_v{4,6}_rcv()).
 				 */
 				break;
 #endif
-- 
GitLab


From d44fd4a767b3755899f8ad1df3e8eca3961ba708 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Aug 2023 14:46:11 +0000
Subject: [PATCH 0905/1806] tcp: set TCP_SYNCNT locklessly

icsk->icsk_syn_retries can safely be set without locking the socket.

We have to add READ_ONCE() annotations in tcp_fastopen_synack_timer()
and tcp_write_timeout().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c       | 15 ++++++---------
 net/ipv4/tcp_timer.c |  9 ++++++---
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index aca5620cf3ba2..bcbb33a8c152a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3291,9 +3291,7 @@ int tcp_sock_set_syncnt(struct sock *sk, int val)
 	if (val < 1 || val > MAX_TCP_SYNCNT)
 		return -EINVAL;
 
-	lock_sock(sk);
 	WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val);
-	release_sock(sk);
 	return 0;
 }
 EXPORT_SYMBOL(tcp_sock_set_syncnt);
@@ -3462,6 +3460,12 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	if (copy_from_sockptr(&val, optval, sizeof(val)))
 		return -EFAULT;
 
+	/* Handle options that can be set without locking the socket. */
+	switch (optname) {
+	case TCP_SYNCNT:
+		return tcp_sock_set_syncnt(sk, val);
+	}
+
 	sockopt_lock_sock(sk);
 
 	switch (optname) {
@@ -3569,13 +3573,6 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		else
 			WRITE_ONCE(tp->keepalive_probes, val);
 		break;
-	case TCP_SYNCNT:
-		if (val < 1 || val > MAX_TCP_SYNCNT)
-			err = -EINVAL;
-		else
-			WRITE_ONCE(icsk->icsk_syn_retries, val);
-		break;
-
 	case TCP_SAVE_SYN:
 		/* 0: disable, 1: enable, 2: start from ether_header */
 		if (val < 0 || val > 2)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 470f581eedd43..66040ab457d46 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -239,7 +239,8 @@ static int tcp_write_timeout(struct sock *sk)
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits)
 			__dst_negative_advice(sk);
-		retry_until = icsk->icsk_syn_retries ? :
+		/* Paired with WRITE_ONCE() in tcp_sock_set_syncnt() */
+		retry_until = READ_ONCE(icsk->icsk_syn_retries) ? :
 			READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
 
 		max_retransmits = retry_until;
@@ -421,8 +422,10 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 
 	req->rsk_ops->syn_ack_timeout(req);
 
-	/* add one more retry for fastopen */
-	max_retries = icsk->icsk_syn_retries ? :
+	/* Add one more retry for fastopen.
+	 * Paired with WRITE_ONCE() in tcp_sock_set_syncnt()
+	 */
+	max_retries = READ_ONCE(icsk->icsk_syn_retries) ? :
 		READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1;
 
 	if (req->num_timeout >= max_retries) {
-- 
GitLab


From d58f2e15aa0c07f6f03ec71f64d7697ca43d04a1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Aug 2023 14:46:12 +0000
Subject: [PATCH 0906/1806] tcp: set TCP_USER_TIMEOUT locklessly

icsk->icsk_user_timeout can be set locklessly,
if all read sides use READ_ONCE().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h  |  2 +-
 net/ipv4/tcp.c       | 23 ++++++++++-------------
 net/ipv4/tcp_timer.c | 37 ++++++++++++++++++++++---------------
 3 files changed, 33 insertions(+), 29 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index d16abdb3541a6..3c5efeeb024f6 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -564,6 +564,6 @@ void __tcp_sock_set_nodelay(struct sock *sk, bool on);
 void tcp_sock_set_nodelay(struct sock *sk);
 void tcp_sock_set_quickack(struct sock *sk, int val);
 int tcp_sock_set_syncnt(struct sock *sk, int val);
-void tcp_sock_set_user_timeout(struct sock *sk, u32 val);
+int tcp_sock_set_user_timeout(struct sock *sk, int val);
 
 #endif	/* _LINUX_TCP_H */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bcbb33a8c152a..34c2a40b02477 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3296,11 +3296,16 @@ int tcp_sock_set_syncnt(struct sock *sk, int val)
 }
 EXPORT_SYMBOL(tcp_sock_set_syncnt);
 
-void tcp_sock_set_user_timeout(struct sock *sk, u32 val)
+int tcp_sock_set_user_timeout(struct sock *sk, int val)
 {
-	lock_sock(sk);
+	/* Cap the max time in ms TCP will retry or probe the window
+	 * before giving up and aborting (ETIMEDOUT) a connection.
+	 */
+	if (val < 0)
+		return -EINVAL;
+
 	WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val);
-	release_sock(sk);
+	return 0;
 }
 EXPORT_SYMBOL(tcp_sock_set_user_timeout);
 
@@ -3464,6 +3469,8 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	switch (optname) {
 	case TCP_SYNCNT:
 		return tcp_sock_set_syncnt(sk, val);
+	case TCP_USER_TIMEOUT:
+		return tcp_sock_set_user_timeout(sk, val);
 	}
 
 	sockopt_lock_sock(sk);
@@ -3611,16 +3618,6 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
 		break;
 #endif
-	case TCP_USER_TIMEOUT:
-		/* Cap the max time in ms TCP will retry or probe the window
-		 * before giving up and aborting (ETIMEDOUT) a connection.
-		 */
-		if (val < 0)
-			err = -EINVAL;
-		else
-			WRITE_ONCE(icsk->icsk_user_timeout, val);
-		break;
-
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
 		    TCPF_LISTEN))) {
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 66040ab457d46..f99e2d06ae7ca 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -26,14 +26,15 @@
 static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 elapsed, start_ts;
+	u32 elapsed, start_ts, user_timeout;
 	s32 remaining;
 
 	start_ts = tcp_sk(sk)->retrans_stamp;
-	if (!icsk->icsk_user_timeout)
+	user_timeout = READ_ONCE(icsk->icsk_user_timeout);
+	if (!user_timeout)
 		return icsk->icsk_rto;
 	elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts;
-	remaining = icsk->icsk_user_timeout - elapsed;
+	remaining = user_timeout - elapsed;
 	if (remaining <= 0)
 		return 1; /* user timeout has passed; fire ASAP */
 
@@ -43,16 +44,17 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
 u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 remaining;
+	u32 remaining, user_timeout;
 	s32 elapsed;
 
-	if (!icsk->icsk_user_timeout || !icsk->icsk_probes_tstamp)
+	user_timeout = READ_ONCE(icsk->icsk_user_timeout);
+	if (!user_timeout || !icsk->icsk_probes_tstamp)
 		return when;
 
 	elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp;
 	if (unlikely(elapsed < 0))
 		elapsed = 0;
-	remaining = msecs_to_jiffies(icsk->icsk_user_timeout) - elapsed;
+	remaining = msecs_to_jiffies(user_timeout) - elapsed;
 	remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN);
 
 	return min_t(u32, remaining, when);
@@ -270,7 +272,7 @@ static int tcp_write_timeout(struct sock *sk)
 	}
 	if (!expired)
 		expired = retransmits_timed_out(sk, retry_until,
-						icsk->icsk_user_timeout);
+						READ_ONCE(icsk->icsk_user_timeout));
 	tcp_fastopen_active_detect_blackhole(sk, expired);
 
 	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
@@ -384,13 +386,16 @@ static void tcp_probe_timer(struct sock *sk)
 	 * corresponding system limit. We also implement similar policy when
 	 * we use RTO to probe window in tcp_retransmit_timer().
 	 */
-	if (!icsk->icsk_probes_tstamp)
+	if (!icsk->icsk_probes_tstamp) {
 		icsk->icsk_probes_tstamp = tcp_jiffies32;
-	else if (icsk->icsk_user_timeout &&
-		 (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >=
-		 msecs_to_jiffies(icsk->icsk_user_timeout))
-		goto abort;
+	} else {
+		u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
 
+		if (user_timeout &&
+		    (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >=
+		     msecs_to_jiffies(user_timeout))
+		goto abort;
+	}
 	max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2);
 	if (sock_flag(sk, SOCK_DEAD)) {
 		const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
@@ -734,13 +739,15 @@ static void tcp_keepalive_timer (struct timer_list *t)
 	elapsed = keepalive_time_elapsed(tp);
 
 	if (elapsed >= keepalive_time_when(tp)) {
+		u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
+
 		/* If the TCP_USER_TIMEOUT option is enabled, use that
 		 * to determine when to timeout instead.
 		 */
-		if ((icsk->icsk_user_timeout != 0 &&
-		    elapsed >= msecs_to_jiffies(icsk->icsk_user_timeout) &&
+		if ((user_timeout != 0 &&
+		    elapsed >= msecs_to_jiffies(user_timeout) &&
 		    icsk->icsk_probes_out > 0) ||
-		    (icsk->icsk_user_timeout == 0 &&
+		    (user_timeout == 0 &&
 		    icsk->icsk_probes_out >= keepalive_probes(tp))) {
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 			tcp_write_err(sk);
-- 
GitLab


From 6fd70a6b4e6f58482a43da46d12323795bbc5f68 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Aug 2023 14:46:13 +0000
Subject: [PATCH 0907/1806] tcp: set TCP_KEEPINTVL locklessly

tp->keepalive_intvl can be set locklessly, readers
are already taking care of this field being potentially
set by other threads.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 34c2a40b02477..75d6359ee5750 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3348,9 +3348,7 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val)
 	if (val < 1 || val > MAX_TCP_KEEPINTVL)
 		return -EINVAL;
 
-	lock_sock(sk);
 	WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ);
-	release_sock(sk);
 	return 0;
 }
 EXPORT_SYMBOL(tcp_sock_set_keepintvl);
@@ -3471,6 +3469,8 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		return tcp_sock_set_syncnt(sk, val);
 	case TCP_USER_TIMEOUT:
 		return tcp_sock_set_user_timeout(sk, val);
+	case TCP_KEEPINTVL:
+		return tcp_sock_set_keepintvl(sk, val);
 	}
 
 	sockopt_lock_sock(sk);
@@ -3568,12 +3568,6 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	case TCP_KEEPIDLE:
 		err = tcp_sock_set_keepidle_locked(sk, val);
 		break;
-	case TCP_KEEPINTVL:
-		if (val < 1 || val > MAX_TCP_KEEPINTVL)
-			err = -EINVAL;
-		else
-			WRITE_ONCE(tp->keepalive_intvl, val * HZ);
-		break;
 	case TCP_KEEPCNT:
 		if (val < 1 || val > MAX_TCP_KEEPCNT)
 			err = -EINVAL;
-- 
GitLab


From 84485080cbc1e5a011e7549966739df4cec158b1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Aug 2023 14:46:14 +0000
Subject: [PATCH 0908/1806] tcp: set TCP_KEEPCNT locklessly

tp->keepalive_probes can be set locklessly, readers
are already taking care of this field being potentially
set by other threads.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 75d6359ee5750..e74a9593283c9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3358,10 +3358,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val)
 	if (val < 1 || val > MAX_TCP_KEEPCNT)
 		return -EINVAL;
 
-	lock_sock(sk);
 	/* Paired with READ_ONCE() in keepalive_probes() */
 	WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val);
-	release_sock(sk);
 	return 0;
 }
 EXPORT_SYMBOL(tcp_sock_set_keepcnt);
@@ -3471,6 +3469,8 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		return tcp_sock_set_user_timeout(sk, val);
 	case TCP_KEEPINTVL:
 		return tcp_sock_set_keepintvl(sk, val);
+	case TCP_KEEPCNT:
+		return tcp_sock_set_keepcnt(sk, val);
 	}
 
 	sockopt_lock_sock(sk);
@@ -3568,12 +3568,6 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	case TCP_KEEPIDLE:
 		err = tcp_sock_set_keepidle_locked(sk, val);
 		break;
-	case TCP_KEEPCNT:
-		if (val < 1 || val > MAX_TCP_KEEPCNT)
-			err = -EINVAL;
-		else
-			WRITE_ONCE(tp->keepalive_probes, val);
-		break;
 	case TCP_SAVE_SYN:
 		/* 0: disable, 1: enable, 2: start from ether_header */
 		if (val < 0 || val > 2)
-- 
GitLab


From a81722ddd7e4d76c9bbff078d29416e18c6d7f71 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Aug 2023 14:46:15 +0000
Subject: [PATCH 0909/1806] tcp: set TCP_LINGER2 locklessly

tp->linger2 can be set locklessly as long as readers
use READ_ONCE().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c       | 19 +++++++++----------
 net/ipv4/tcp_input.c |  2 +-
 net/ipv4/tcp_timer.c |  2 +-
 3 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e74a9593283c9..5c71b4fe11d1c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2865,7 +2865,7 @@ adjudge_to_death:
 
 	if (sk->sk_state == TCP_FIN_WAIT2) {
 		struct tcp_sock *tp = tcp_sk(sk);
-		if (tp->linger2 < 0) {
+		if (READ_ONCE(tp->linger2) < 0) {
 			tcp_set_state(sk, TCP_CLOSE);
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 			__NET_INC_STATS(sock_net(sk),
@@ -3471,6 +3471,14 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		return tcp_sock_set_keepintvl(sk, val);
 	case TCP_KEEPCNT:
 		return tcp_sock_set_keepcnt(sk, val);
+	case TCP_LINGER2:
+		if (val < 0)
+			WRITE_ONCE(tp->linger2, -1);
+		else if (val > TCP_FIN_TIMEOUT_MAX / HZ)
+			WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX);
+		else
+			WRITE_ONCE(tp->linger2, val * HZ);
+		return 0;
 	}
 
 	sockopt_lock_sock(sk);
@@ -3576,15 +3584,6 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 			tp->save_syn = val;
 		break;
 
-	case TCP_LINGER2:
-		if (val < 0)
-			WRITE_ONCE(tp->linger2, -1);
-		else if (val > TCP_FIN_TIMEOUT_MAX / HZ)
-			WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX);
-		else
-			WRITE_ONCE(tp->linger2, val * HZ);
-		break;
-
 	case TCP_DEFER_ACCEPT:
 		/* Translate value in seconds to number of retransmits */
 		WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2995802126e4e..deac708250e68 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6624,7 +6624,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			break;
 		}
 
-		if (tp->linger2 < 0) {
+		if (READ_ONCE(tp->linger2) < 0) {
 			tcp_done(sk);
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
 			return 1;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index f99e2d06ae7ca..d45c96c7f5a44 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -714,7 +714,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
 
 	tcp_mstamp_refresh(tp);
 	if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) {
-		if (tp->linger2 >= 0) {
+		if (READ_ONCE(tp->linger2) >= 0) {
 			const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN;
 
 			if (tmo > 0) {
-- 
GitLab


From 6e97ba552b8d3dd074a28b8600740b8bed42267b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Aug 2023 14:46:16 +0000
Subject: [PATCH 0910/1806] tcp: set TCP_DEFER_ACCEPT locklessly

rskq_defer_accept field can be read/written without
the need of holding the socket lock.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c           | 13 ++++++-------
 net/ipv4/tcp_input.c     |  2 +-
 net/ipv4/tcp_minisocks.c |  2 +-
 3 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5c71b4fe11d1c..4fbc7ff8c53c0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3479,6 +3479,12 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		else
 			WRITE_ONCE(tp->linger2, val * HZ);
 		return 0;
+	case TCP_DEFER_ACCEPT:
+		/* Translate value in seconds to number of retransmits */
+		WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept,
+			   secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
+					   TCP_RTO_MAX / HZ));
+		return 0;
 	}
 
 	sockopt_lock_sock(sk);
@@ -3584,13 +3590,6 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 			tp->save_syn = val;
 		break;
 
-	case TCP_DEFER_ACCEPT:
-		/* Translate value in seconds to number of retransmits */
-		WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept,
-			   secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
-					   TCP_RTO_MAX / HZ));
-		break;
-
 	case TCP_WINDOW_CLAMP:
 		err = tcp_set_window_clamp(sk, val);
 		break;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index deac708250e68..8e96ebe373d7e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6324,7 +6324,7 @@ consume:
 		if (fastopen_fail)
 			return -1;
 		if (sk->sk_write_pending ||
-		    icsk->icsk_accept_queue.rskq_defer_accept ||
+		    READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept) ||
 		    inet_csk_in_pingpong_mode(sk)) {
 			/* Save one ACK. Data will be ready after
 			 * several ticks, if write_pending is set.
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ddba3b67f7c8e..13ee12983c429 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -792,7 +792,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		return sk;
 
 	/* While TCP_DEFER_ACCEPT is active, drop bare ACK. */
-	if (req->num_timeout < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
+	if (req->num_timeout < READ_ONCE(inet_csk(sk)->icsk_accept_queue.rskq_defer_accept) &&
 	    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
 		inet_rsk(req)->acked = 1;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDEFERACCEPTDROP);
-- 
GitLab


From 66ce8e6b49df401854f0c98bed50a65e4167825b Mon Sep 17 00:00:00 2001
From: Rushil Gupta <rushilg@google.com>
Date: Fri, 4 Aug 2023 21:34:41 +0000
Subject: [PATCH 0911/1806] gve: Control path for DQO-QPL

GVE supports QPL ("queue-page-list") mode where
all data is communicated through a set of pre-registered
pages. Adding this mode to DQO descriptor format.

Add checks, abi-changes and device options to support
QPL mode for DQO in addition to GQI. Also, use
pages-per-qpl supplied by device-option to control the
size of the "queue-page-list".

Signed-off-by: Rushil Gupta <rushilg@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Bailey Forrest <bcf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/google/gve/gve.h        | 29 ++++++-
 drivers/net/ethernet/google/gve/gve_adminq.c | 89 +++++++++++++++++---
 drivers/net/ethernet/google/gve/gve_adminq.h | 10 +++
 drivers/net/ethernet/google/gve/gve_main.c   | 20 +++--
 4 files changed, 128 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index a31256f70348a..3bd6eed7280f1 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -52,6 +52,12 @@
 
 #define GVE_GQ_TX_MIN_PKT_DESC_BYTES 182
 
+#define DQO_QPL_DEFAULT_TX_PAGES 512
+#define DQO_QPL_DEFAULT_RX_PAGES 2048
+
+/* Maximum TSO size supported on DQO */
+#define GVE_DQO_TX_MAX	0x3FFFF
+
 /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */
 struct gve_rx_desc_queue {
 	struct gve_rx_desc *desc_ring; /* the descriptor ring */
@@ -218,6 +224,9 @@ struct gve_rx_ring {
 			 * which cannot be reused yet.
 			 */
 			struct gve_index_list used_buf_states;
+
+			/* qpl assigned to this queue */
+			struct gve_queue_page_list *qpl;
 		} dqo;
 	};
 
@@ -454,6 +463,12 @@ struct gve_tx_ring {
 			s16 num_pending_packets;
 
 			u32 complq_mask; /* complq size is complq_mask + 1 */
+
+			/* QPL fields */
+			struct {
+				/* qpl assigned to this queue */
+				struct gve_queue_page_list *qpl;
+			};
 		} dqo;
 	} ____cacheline_aligned;
 	struct netdev_queue *netdev_txq;
@@ -532,6 +547,7 @@ enum gve_queue_format {
 	GVE_GQI_RDA_FORMAT		= 0x1,
 	GVE_GQI_QPL_FORMAT		= 0x2,
 	GVE_DQO_RDA_FORMAT		= 0x3,
+	GVE_DQO_QPL_FORMAT		= 0x4,
 };
 
 struct gve_priv {
@@ -551,7 +567,8 @@ struct gve_priv {
 	u16 num_event_counters;
 	u16 tx_desc_cnt; /* num desc per ring */
 	u16 rx_desc_cnt; /* num desc per ring */
-	u16 tx_pages_per_qpl; /* tx buffer length */
+	u16 tx_pages_per_qpl; /* Suggested number of pages per qpl for TX queues by NIC */
+	u16 rx_pages_per_qpl; /* Suggested number of pages per qpl for RX queues by NIC */
 	u16 rx_data_slot_cnt; /* rx buffer length */
 	u64 max_registered_pages;
 	u64 num_registered_pages; /* num pages registered with NIC */
@@ -809,11 +826,17 @@ static inline u32 gve_rx_idx_to_ntfy(struct gve_priv *priv, u32 queue_idx)
 	return (priv->num_ntfy_blks / 2) + queue_idx;
 }
 
+static inline bool gve_is_qpl(struct gve_priv *priv)
+{
+	return priv->queue_format == GVE_GQI_QPL_FORMAT ||
+		priv->queue_format == GVE_DQO_QPL_FORMAT;
+}
+
 /* Returns the number of tx queue page lists
  */
 static inline u32 gve_num_tx_qpls(struct gve_priv *priv)
 {
-	if (priv->queue_format != GVE_GQI_QPL_FORMAT)
+	if (!gve_is_qpl(priv))
 		return 0;
 
 	return priv->tx_cfg.num_queues + priv->num_xdp_queues;
@@ -833,7 +856,7 @@ static inline u32 gve_num_xdp_qpls(struct gve_priv *priv)
  */
 static inline u32 gve_num_rx_qpls(struct gve_priv *priv)
 {
-	if (priv->queue_format != GVE_GQI_QPL_FORMAT)
+	if (!gve_is_qpl(priv))
 		return 0;
 
 	return priv->rx_cfg.num_queues;
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index 252974202a3fb..79db7a6d42bc2 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -39,7 +39,8 @@ void gve_parse_device_option(struct gve_priv *priv,
 			     struct gve_device_option_gqi_rda **dev_op_gqi_rda,
 			     struct gve_device_option_gqi_qpl **dev_op_gqi_qpl,
 			     struct gve_device_option_dqo_rda **dev_op_dqo_rda,
-			     struct gve_device_option_jumbo_frames **dev_op_jumbo_frames)
+			     struct gve_device_option_jumbo_frames **dev_op_jumbo_frames,
+			     struct gve_device_option_dqo_qpl **dev_op_dqo_qpl)
 {
 	u32 req_feat_mask = be32_to_cpu(option->required_features_mask);
 	u16 option_length = be16_to_cpu(option->option_length);
@@ -112,6 +113,22 @@ void gve_parse_device_option(struct gve_priv *priv,
 		}
 		*dev_op_dqo_rda = (void *)(option + 1);
 		break;
+	case GVE_DEV_OPT_ID_DQO_QPL:
+		if (option_length < sizeof(**dev_op_dqo_qpl) ||
+		    req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_DQO_QPL) {
+			dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
+				 "DQO QPL", (int)sizeof(**dev_op_dqo_qpl),
+				 GVE_DEV_OPT_REQ_FEAT_MASK_DQO_QPL,
+				 option_length, req_feat_mask);
+			break;
+		}
+
+		if (option_length > sizeof(**dev_op_dqo_qpl)) {
+			dev_warn(&priv->pdev->dev,
+				 GVE_DEVICE_OPTION_TOO_BIG_FMT, "DQO QPL");
+		}
+		*dev_op_dqo_qpl = (void *)(option + 1);
+		break;
 	case GVE_DEV_OPT_ID_JUMBO_FRAMES:
 		if (option_length < sizeof(**dev_op_jumbo_frames) ||
 		    req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_JUMBO_FRAMES) {
@@ -146,7 +163,8 @@ gve_process_device_options(struct gve_priv *priv,
 			   struct gve_device_option_gqi_rda **dev_op_gqi_rda,
 			   struct gve_device_option_gqi_qpl **dev_op_gqi_qpl,
 			   struct gve_device_option_dqo_rda **dev_op_dqo_rda,
-			   struct gve_device_option_jumbo_frames **dev_op_jumbo_frames)
+			   struct gve_device_option_jumbo_frames **dev_op_jumbo_frames,
+			   struct gve_device_option_dqo_qpl **dev_op_dqo_qpl)
 {
 	const int num_options = be16_to_cpu(descriptor->num_device_options);
 	struct gve_device_option *dev_opt;
@@ -166,7 +184,8 @@ gve_process_device_options(struct gve_priv *priv,
 
 		gve_parse_device_option(priv, descriptor, dev_opt,
 					dev_op_gqi_rda, dev_op_gqi_qpl,
-					dev_op_dqo_rda, dev_op_jumbo_frames);
+					dev_op_dqo_rda, dev_op_jumbo_frames,
+					dev_op_dqo_qpl);
 		dev_opt = next_opt;
 	}
 
@@ -505,12 +524,24 @@ static int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index)
 
 		cmd.create_tx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
 	} else {
+		u16 comp_ring_size;
+		u32 qpl_id = 0;
+
+		if (priv->queue_format == GVE_DQO_RDA_FORMAT) {
+			qpl_id = GVE_RAW_ADDRESSING_QPL_ID;
+			comp_ring_size =
+				priv->options_dqo_rda.tx_comp_ring_entries;
+		} else {
+			qpl_id = tx->dqo.qpl->id;
+			comp_ring_size = priv->tx_desc_cnt;
+		}
+		cmd.create_tx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
 		cmd.create_tx_queue.tx_ring_size =
 			cpu_to_be16(priv->tx_desc_cnt);
 		cmd.create_tx_queue.tx_comp_ring_addr =
 			cpu_to_be64(tx->complq_bus_dqo);
 		cmd.create_tx_queue.tx_comp_ring_size =
-			cpu_to_be16(priv->options_dqo_rda.tx_comp_ring_entries);
+			cpu_to_be16(comp_ring_size);
 	}
 
 	return gve_adminq_issue_cmd(priv, &cmd);
@@ -555,6 +586,18 @@ static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index)
 		cmd.create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
 		cmd.create_rx_queue.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size);
 	} else {
+		u16 rx_buff_ring_entries;
+		u32 qpl_id = 0;
+
+		if (priv->queue_format == GVE_DQO_RDA_FORMAT) {
+			qpl_id = GVE_RAW_ADDRESSING_QPL_ID;
+			rx_buff_ring_entries =
+				priv->options_dqo_rda.rx_buff_ring_entries;
+		} else {
+			qpl_id = rx->dqo.qpl->id;
+			rx_buff_ring_entries = priv->rx_desc_cnt;
+		}
+		cmd.create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
 		cmd.create_rx_queue.rx_ring_size =
 			cpu_to_be16(priv->rx_desc_cnt);
 		cmd.create_rx_queue.rx_desc_ring_addr =
@@ -564,7 +607,7 @@ static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index)
 		cmd.create_rx_queue.packet_buffer_size =
 			cpu_to_be16(priv->data_buffer_size_dqo);
 		cmd.create_rx_queue.rx_buff_ring_size =
-			cpu_to_be16(priv->options_dqo_rda.rx_buff_ring_entries);
+			cpu_to_be16(rx_buff_ring_entries);
 		cmd.create_rx_queue.enable_rsc =
 			!!(priv->dev->features & NETIF_F_LRO);
 	}
@@ -675,9 +718,13 @@ gve_set_desc_cnt_dqo(struct gve_priv *priv,
 		     const struct gve_device_option_dqo_rda *dev_op_dqo_rda)
 {
 	priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries);
+	priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries);
+
+	if (priv->queue_format == GVE_DQO_QPL_FORMAT)
+		return 0;
+
 	priv->options_dqo_rda.tx_comp_ring_entries =
 		be16_to_cpu(dev_op_dqo_rda->tx_comp_ring_entries);
-	priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries);
 	priv->options_dqo_rda.rx_buff_ring_entries =
 		be16_to_cpu(dev_op_dqo_rda->rx_buff_ring_entries);
 
@@ -687,7 +734,9 @@ gve_set_desc_cnt_dqo(struct gve_priv *priv,
 static void gve_enable_supported_features(struct gve_priv *priv,
 					  u32 supported_features_mask,
 					  const struct gve_device_option_jumbo_frames
-						  *dev_op_jumbo_frames)
+					  *dev_op_jumbo_frames,
+					  const struct gve_device_option_dqo_qpl
+					  *dev_op_dqo_qpl)
 {
 	/* Before control reaches this point, the page-size-capped max MTU from
 	 * the gve_device_descriptor field has already been stored in
@@ -699,6 +748,18 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 			 "JUMBO FRAMES device option enabled.\n");
 		priv->dev->max_mtu = be16_to_cpu(dev_op_jumbo_frames->max_mtu);
 	}
+
+	/* Override pages for qpl for DQO-QPL */
+	if (dev_op_dqo_qpl) {
+		priv->tx_pages_per_qpl =
+			be16_to_cpu(dev_op_dqo_qpl->tx_pages_per_qpl);
+		priv->rx_pages_per_qpl =
+			be16_to_cpu(dev_op_dqo_qpl->rx_pages_per_qpl);
+		if (priv->tx_pages_per_qpl == 0)
+			priv->tx_pages_per_qpl = DQO_QPL_DEFAULT_TX_PAGES;
+		if (priv->rx_pages_per_qpl == 0)
+			priv->rx_pages_per_qpl = DQO_QPL_DEFAULT_RX_PAGES;
+	}
 }
 
 int gve_adminq_describe_device(struct gve_priv *priv)
@@ -707,6 +768,7 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	struct gve_device_option_gqi_rda *dev_op_gqi_rda = NULL;
 	struct gve_device_option_gqi_qpl *dev_op_gqi_qpl = NULL;
 	struct gve_device_option_dqo_rda *dev_op_dqo_rda = NULL;
+	struct gve_device_option_dqo_qpl *dev_op_dqo_qpl = NULL;
 	struct gve_device_descriptor *descriptor;
 	u32 supported_features_mask = 0;
 	union gve_adminq_command cmd;
@@ -733,13 +795,14 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 
 	err = gve_process_device_options(priv, descriptor, &dev_op_gqi_rda,
 					 &dev_op_gqi_qpl, &dev_op_dqo_rda,
-					 &dev_op_jumbo_frames);
+					 &dev_op_jumbo_frames,
+					 &dev_op_dqo_qpl);
 	if (err)
 		goto free_device_descriptor;
 
 	/* If the GQI_RAW_ADDRESSING option is not enabled and the queue format
 	 * is not set to GqiRda, choose the queue format in a priority order:
-	 * DqoRda, GqiRda, GqiQpl. Use GqiQpl as default.
+	 * DqoRda, DqoQpl, GqiRda, GqiQpl. Use GqiQpl as default.
 	 */
 	if (dev_op_dqo_rda) {
 		priv->queue_format = GVE_DQO_RDA_FORMAT;
@@ -747,7 +810,11 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 			 "Driver is running with DQO RDA queue format.\n");
 		supported_features_mask =
 			be32_to_cpu(dev_op_dqo_rda->supported_features_mask);
-	} else if (dev_op_gqi_rda) {
+	} else if (dev_op_dqo_qpl) {
+		priv->queue_format = GVE_DQO_QPL_FORMAT;
+		supported_features_mask =
+			be32_to_cpu(dev_op_dqo_qpl->supported_features_mask);
+	}  else if (dev_op_gqi_rda) {
 		priv->queue_format = GVE_GQI_RDA_FORMAT;
 		dev_info(&priv->pdev->dev,
 			 "Driver is running with GQI RDA queue format.\n");
@@ -798,7 +865,7 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	priv->default_num_queues = be16_to_cpu(descriptor->default_num_queues);
 
 	gve_enable_supported_features(priv, supported_features_mask,
-				      dev_op_jumbo_frames);
+				      dev_op_jumbo_frames, dev_op_dqo_qpl);
 
 free_device_descriptor:
 	dma_free_coherent(&priv->pdev->dev, PAGE_SIZE, descriptor,
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
index f894beb3deaf7..38a22279e8638 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -109,6 +109,14 @@ struct gve_device_option_dqo_rda {
 
 static_assert(sizeof(struct gve_device_option_dqo_rda) == 8);
 
+struct gve_device_option_dqo_qpl {
+	__be32 supported_features_mask;
+	__be16 tx_pages_per_qpl;
+	__be16 rx_pages_per_qpl;
+};
+
+static_assert(sizeof(struct gve_device_option_dqo_qpl) == 8);
+
 struct gve_device_option_jumbo_frames {
 	__be32 supported_features_mask;
 	__be16 max_mtu;
@@ -130,6 +138,7 @@ enum gve_dev_opt_id {
 	GVE_DEV_OPT_ID_GQI_RDA = 0x2,
 	GVE_DEV_OPT_ID_GQI_QPL = 0x3,
 	GVE_DEV_OPT_ID_DQO_RDA = 0x4,
+	GVE_DEV_OPT_ID_DQO_QPL = 0x7,
 	GVE_DEV_OPT_ID_JUMBO_FRAMES = 0x8,
 };
 
@@ -139,6 +148,7 @@ enum gve_dev_opt_req_feat_mask {
 	GVE_DEV_OPT_REQ_FEAT_MASK_GQI_QPL = 0x0,
 	GVE_DEV_OPT_REQ_FEAT_MASK_DQO_RDA = 0x0,
 	GVE_DEV_OPT_REQ_FEAT_MASK_JUMBO_FRAMES = 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_DQO_QPL = 0x0,
 };
 
 enum gve_sup_feature_mask {
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index e6f1711d9be04..5704b5f57cd0d 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -31,7 +31,6 @@
 
 // Minimum amount of time between queue kicks in msec (10 seconds)
 #define MIN_TX_TIMEOUT_GAP (1000 * 10)
-#define DQO_TX_MAX	0x3FFFF
 
 char gve_driver_name[] = "gve";
 const char gve_version_str[] = GVE_VERSION;
@@ -494,7 +493,7 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 		goto abort_with_stats_report;
 	}
 
-	if (priv->queue_format == GVE_DQO_RDA_FORMAT) {
+	if (!gve_is_gqi(priv)) {
 		priv->ptype_lut_dqo = kvzalloc(sizeof(*priv->ptype_lut_dqo),
 					       GFP_KERNEL);
 		if (!priv->ptype_lut_dqo) {
@@ -1083,11 +1082,12 @@ free_qpls:
 static int gve_alloc_qpls(struct gve_priv *priv)
 {
 	int max_queues = priv->tx_cfg.max_queues + priv->rx_cfg.max_queues;
+	int page_count;
 	int start_id;
 	int i, j;
 	int err;
 
-	if (priv->queue_format != GVE_GQI_QPL_FORMAT)
+	if (!gve_is_qpl(priv))
 		return 0;
 
 	priv->qpls = kvcalloc(max_queues, sizeof(*priv->qpls), GFP_KERNEL);
@@ -1095,17 +1095,25 @@ static int gve_alloc_qpls(struct gve_priv *priv)
 		return -ENOMEM;
 
 	start_id = gve_tx_start_qpl_id(priv);
+	page_count = priv->tx_pages_per_qpl;
 	for (i = start_id; i < start_id + gve_num_tx_qpls(priv); i++) {
 		err = gve_alloc_queue_page_list(priv, i,
-						priv->tx_pages_per_qpl);
+						page_count);
 		if (err)
 			goto free_qpls;
 	}
 
 	start_id = gve_rx_start_qpl_id(priv);
+
+	/* For GQI_QPL number of pages allocated have 1:1 relationship with
+	 * number of descriptors. For DQO, number of pages required are
+	 * more than descriptors (because of out of order completions).
+	 */
+	page_count = priv->queue_format == GVE_GQI_QPL_FORMAT ?
+		priv->rx_data_slot_cnt : priv->rx_pages_per_qpl;
 	for (i = start_id; i < start_id + gve_num_rx_qpls(priv); i++) {
 		err = gve_alloc_queue_page_list(priv, i,
-						priv->rx_data_slot_cnt);
+						page_count);
 		if (err)
 			goto free_qpls;
 	}
@@ -2051,7 +2059,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
 
 	/* Big TCP is only supported on DQ*/
 	if (!gve_is_gqi(priv))
-		netif_set_tso_max_size(priv->dev, DQO_TX_MAX);
+		netif_set_tso_max_size(priv->dev, GVE_DQO_TX_MAX);
 
 	priv->num_registered_pages = 0;
 	priv->rx_copybreak = GVE_DEFAULT_RX_COPYBREAK;
-- 
GitLab


From a6fb8d5a8b6925f1e635818d3dd2d89531d4a058 Mon Sep 17 00:00:00 2001
From: Rushil Gupta <rushilg@google.com>
Date: Fri, 4 Aug 2023 21:34:42 +0000
Subject: [PATCH 0912/1806] gve: Tx path for DQO-QPL

Each QPL page is divided into GVE_TX_BUFS_PER_PAGE_DQO buffers.
When a packet needs to be transmitted, we break the packet into max
GVE_TX_BUF_SIZE_DQO sized chunks and transmit each chunk using a TX
descriptor.
We allocate the TX buffers from the free list in dqo_tx.
We store these TX buffer indices in an array in the pending_packet
structure.

The TX buffers are returned to the free list in dqo_compl after
receiving packet completion or when removing packets from miss
completions list.

Signed-off-by: Rushil Gupta <rushilg@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Bailey Forrest <bcf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/google/gve/gve.h        |  77 +++-
 drivers/net/ethernet/google/gve/gve_tx_dqo.c | 404 +++++++++++++++----
 2 files changed, 398 insertions(+), 83 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 3bd6eed7280f1..2042f79cea1f6 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -58,6 +58,20 @@
 /* Maximum TSO size supported on DQO */
 #define GVE_DQO_TX_MAX	0x3FFFF
 
+#define GVE_TX_BUF_SHIFT_DQO 11
+
+/* 2K buffers for DQO-QPL */
+#define GVE_TX_BUF_SIZE_DQO BIT(GVE_TX_BUF_SHIFT_DQO)
+#define GVE_TX_BUFS_PER_PAGE_DQO (PAGE_SIZE >> GVE_TX_BUF_SHIFT_DQO)
+#define GVE_MAX_TX_BUFS_PER_PKT (DIV_ROUND_UP(GVE_DQO_TX_MAX, GVE_TX_BUF_SIZE_DQO))
+
+/* If number of free/recyclable buffers are less than this threshold; driver
+ * allocs and uses a non-qpl page on the receive path of DQO QPL to free
+ * up buffers.
+ * Value is set big enough to post at least 3 64K LRO packet via 2K buffer to NIC.
+ */
+#define GVE_DQO_QPL_ONDEMAND_ALLOC_THRESHOLD 96
+
 /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */
 struct gve_rx_desc_queue {
 	struct gve_rx_desc *desc_ring; /* the descriptor ring */
@@ -338,8 +352,14 @@ struct gve_tx_pending_packet_dqo {
 	 * All others correspond to `skb`'s frags and should be unmapped with
 	 * `dma_unmap_page`.
 	 */
-	DEFINE_DMA_UNMAP_ADDR(dma[MAX_SKB_FRAGS + 1]);
-	DEFINE_DMA_UNMAP_LEN(len[MAX_SKB_FRAGS + 1]);
+	union {
+		struct {
+			DEFINE_DMA_UNMAP_ADDR(dma[MAX_SKB_FRAGS + 1]);
+			DEFINE_DMA_UNMAP_LEN(len[MAX_SKB_FRAGS + 1]);
+		};
+		s16 tx_qpl_buf_ids[GVE_MAX_TX_BUFS_PER_PKT];
+	};
+
 	u16 num_bufs;
 
 	/* Linked list index to next element in the list, or -1 if none */
@@ -394,6 +414,32 @@ struct gve_tx_ring {
 			 * set.
 			 */
 			u32 last_re_idx;
+
+			/* free running number of packet buf descriptors posted */
+			u16 posted_packet_desc_cnt;
+			/* free running number of packet buf descriptors completed */
+			u16 completed_packet_desc_cnt;
+
+			/* QPL fields */
+			struct {
+			       /* Linked list of gve_tx_buf_dqo. Index into
+				* tx_qpl_buf_next, or -1 if empty.
+				*
+				* This is a consumer list owned by the TX path. When it
+				* runs out, the producer list is stolen from the
+				* completion handling path
+				* (dqo_compl.free_tx_qpl_buf_head).
+				*/
+				s16 free_tx_qpl_buf_head;
+
+			       /* Free running count of the number of QPL tx buffers
+				* allocated
+				*/
+				u32 alloc_tx_qpl_buf_cnt;
+
+				/* Cached value of `dqo_compl.free_tx_qpl_buf_cnt` */
+				u32 free_tx_qpl_buf_cnt;
+			};
 		} dqo_tx;
 	};
 
@@ -437,6 +483,24 @@ struct gve_tx_ring {
 			 * reached a specified timeout.
 			 */
 			struct gve_index_list timed_out_completions;
+
+			/* QPL fields */
+			struct {
+				/* Linked list of gve_tx_buf_dqo. Index into
+				 * tx_qpl_buf_next, or -1 if empty.
+				 *
+				 * This is the producer list, owned by the completion
+				 * handling path. When the consumer list
+				 * (dqo_tx.free_tx_qpl_buf_head) is runs out, this list
+				 * will be stolen.
+				 */
+				atomic_t free_tx_qpl_buf_head;
+
+				/* Free running count of the number of tx buffers
+				 * freed
+				 */
+				atomic_t free_tx_qpl_buf_cnt;
+			};
 		} dqo_compl;
 	} ____cacheline_aligned;
 	u64 pkt_done; /* free-running - total packets completed */
@@ -468,6 +532,15 @@ struct gve_tx_ring {
 			struct {
 				/* qpl assigned to this queue */
 				struct gve_queue_page_list *qpl;
+
+				/* Each QPL page is divided into TX bounce buffers
+				 * of size GVE_TX_BUF_SIZE_DQO. tx_qpl_buf_next is
+				 * an array to manage linked lists of TX buffers.
+				 * An entry j at index i implies that j'th buffer
+				 * is next on the list after i
+				 */
+				s16 *tx_qpl_buf_next;
+				u32 num_tx_qpl_bufs;
 			};
 		} dqo;
 	} ____cacheline_aligned;
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index 3c09e66ba1ab1..1e19b834a6130 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -13,6 +13,89 @@
 #include <linux/slab.h>
 #include <linux/skbuff.h>
 
+/* Returns true if tx_bufs are available. */
+static bool gve_has_free_tx_qpl_bufs(struct gve_tx_ring *tx, int count)
+{
+	int num_avail;
+
+	if (!tx->dqo.qpl)
+		return true;
+
+	num_avail = tx->dqo.num_tx_qpl_bufs -
+		(tx->dqo_tx.alloc_tx_qpl_buf_cnt -
+		 tx->dqo_tx.free_tx_qpl_buf_cnt);
+
+	if (count <= num_avail)
+		return true;
+
+	/* Update cached value from dqo_compl. */
+	tx->dqo_tx.free_tx_qpl_buf_cnt =
+		atomic_read_acquire(&tx->dqo_compl.free_tx_qpl_buf_cnt);
+
+	num_avail = tx->dqo.num_tx_qpl_bufs -
+		(tx->dqo_tx.alloc_tx_qpl_buf_cnt -
+		 tx->dqo_tx.free_tx_qpl_buf_cnt);
+
+	return count <= num_avail;
+}
+
+static s16
+gve_alloc_tx_qpl_buf(struct gve_tx_ring *tx)
+{
+	s16 index;
+
+	index = tx->dqo_tx.free_tx_qpl_buf_head;
+
+	/* No TX buffers available, try to steal the list from the
+	 * completion handler.
+	 */
+	if (unlikely(index == -1)) {
+		tx->dqo_tx.free_tx_qpl_buf_head =
+			atomic_xchg(&tx->dqo_compl.free_tx_qpl_buf_head, -1);
+		index = tx->dqo_tx.free_tx_qpl_buf_head;
+
+		if (unlikely(index == -1))
+			return index;
+	}
+
+	/* Remove TX buf from free list */
+	tx->dqo_tx.free_tx_qpl_buf_head = tx->dqo.tx_qpl_buf_next[index];
+
+	return index;
+}
+
+static void
+gve_free_tx_qpl_bufs(struct gve_tx_ring *tx,
+		     struct gve_tx_pending_packet_dqo *pkt)
+{
+	s16 index;
+	int i;
+
+	if (!pkt->num_bufs)
+		return;
+
+	index = pkt->tx_qpl_buf_ids[0];
+	/* Create a linked list of buffers to be added to the free list */
+	for (i = 1; i < pkt->num_bufs; i++) {
+		tx->dqo.tx_qpl_buf_next[index] = pkt->tx_qpl_buf_ids[i];
+		index = pkt->tx_qpl_buf_ids[i];
+	}
+
+	while (true) {
+		s16 old_head = atomic_read_acquire(&tx->dqo_compl.free_tx_qpl_buf_head);
+
+		tx->dqo.tx_qpl_buf_next[index] = old_head;
+		if (atomic_cmpxchg(&tx->dqo_compl.free_tx_qpl_buf_head,
+				   old_head,
+				   pkt->tx_qpl_buf_ids[0]) == old_head) {
+			break;
+		}
+	}
+
+	atomic_add(pkt->num_bufs, &tx->dqo_compl.free_tx_qpl_buf_cnt);
+	pkt->num_bufs = 0;
+}
+
 /* Returns true if a gve_tx_pending_packet_dqo object is available. */
 static bool gve_has_pending_packet(struct gve_tx_ring *tx)
 {
@@ -136,9 +219,40 @@ static void gve_tx_free_ring_dqo(struct gve_priv *priv, int idx)
 	kvfree(tx->dqo.pending_packets);
 	tx->dqo.pending_packets = NULL;
 
+	kvfree(tx->dqo.tx_qpl_buf_next);
+	tx->dqo.tx_qpl_buf_next = NULL;
+
+	if (tx->dqo.qpl) {
+		gve_unassign_qpl(priv, tx->dqo.qpl->id);
+		tx->dqo.qpl = NULL;
+	}
+
 	netif_dbg(priv, drv, priv->dev, "freed tx queue %d\n", idx);
 }
 
+static int gve_tx_qpl_buf_init(struct gve_tx_ring *tx)
+{
+	int num_tx_qpl_bufs = GVE_TX_BUFS_PER_PAGE_DQO *
+		tx->dqo.qpl->num_entries;
+	int i;
+
+	tx->dqo.tx_qpl_buf_next = kvcalloc(num_tx_qpl_bufs,
+					   sizeof(tx->dqo.tx_qpl_buf_next[0]),
+					   GFP_KERNEL);
+	if (!tx->dqo.tx_qpl_buf_next)
+		return -ENOMEM;
+
+	tx->dqo.num_tx_qpl_bufs = num_tx_qpl_bufs;
+
+	/* Generate free TX buf list */
+	for (i = 0; i < num_tx_qpl_bufs - 1; i++)
+		tx->dqo.tx_qpl_buf_next[i] = i + 1;
+	tx->dqo.tx_qpl_buf_next[num_tx_qpl_bufs - 1] = -1;
+
+	atomic_set_release(&tx->dqo_compl.free_tx_qpl_buf_head, -1);
+	return 0;
+}
+
 static int gve_tx_alloc_ring_dqo(struct gve_priv *priv, int idx)
 {
 	struct gve_tx_ring *tx = &priv->tx[idx];
@@ -155,7 +269,9 @@ static int gve_tx_alloc_ring_dqo(struct gve_priv *priv, int idx)
 
 	/* Queue sizes must be a power of 2 */
 	tx->mask = priv->tx_desc_cnt - 1;
-	tx->dqo.complq_mask = priv->options_dqo_rda.tx_comp_ring_entries - 1;
+	tx->dqo.complq_mask = priv->queue_format == GVE_DQO_RDA_FORMAT ?
+		priv->options_dqo_rda.tx_comp_ring_entries - 1 :
+		tx->mask;
 
 	/* The max number of pending packets determines the maximum number of
 	 * descriptors which maybe written to the completion queue.
@@ -211,6 +327,15 @@ static int gve_tx_alloc_ring_dqo(struct gve_priv *priv, int idx)
 	if (!tx->q_resources)
 		goto err;
 
+	if (gve_is_qpl(priv)) {
+		tx->dqo.qpl = gve_assign_tx_qpl(priv, idx);
+		if (!tx->dqo.qpl)
+			goto err;
+
+		if (gve_tx_qpl_buf_init(tx))
+			goto err;
+	}
+
 	gve_tx_add_to_block(priv, idx);
 
 	return 0;
@@ -267,20 +392,27 @@ static u32 num_avail_tx_slots(const struct gve_tx_ring *tx)
 	return tx->mask - num_used;
 }
 
+static bool gve_has_avail_slots_tx_dqo(struct gve_tx_ring *tx,
+				       int desc_count, int buf_count)
+{
+	return gve_has_pending_packet(tx) &&
+		   num_avail_tx_slots(tx) >= desc_count &&
+		   gve_has_free_tx_qpl_bufs(tx, buf_count);
+}
+
 /* Stops the queue if available descriptors is less than 'count'.
  * Return: 0 if stop is not required.
  */
-static int gve_maybe_stop_tx_dqo(struct gve_tx_ring *tx, int count)
+static int gve_maybe_stop_tx_dqo(struct gve_tx_ring *tx,
+				 int desc_count, int buf_count)
 {
-	if (likely(gve_has_pending_packet(tx) &&
-		   num_avail_tx_slots(tx) >= count))
+	if (likely(gve_has_avail_slots_tx_dqo(tx, desc_count, buf_count)))
 		return 0;
 
 	/* Update cached TX head pointer */
 	tx->dqo_tx.head = atomic_read_acquire(&tx->dqo_compl.hw_tx_head);
 
-	if (likely(gve_has_pending_packet(tx) &&
-		   num_avail_tx_slots(tx) >= count))
+	if (likely(gve_has_avail_slots_tx_dqo(tx, desc_count, buf_count)))
 		return 0;
 
 	/* No space, so stop the queue */
@@ -295,8 +427,7 @@ static int gve_maybe_stop_tx_dqo(struct gve_tx_ring *tx, int count)
 	 */
 	tx->dqo_tx.head = atomic_read_acquire(&tx->dqo_compl.hw_tx_head);
 
-	if (likely(!gve_has_pending_packet(tx) ||
-		   num_avail_tx_slots(tx) < count))
+	if (likely(!gve_has_avail_slots_tx_dqo(tx, desc_count, buf_count)))
 		return -EBUSY;
 
 	netif_tx_start_queue(tx->netdev_txq);
@@ -444,44 +575,16 @@ gve_tx_fill_general_ctx_desc(struct gve_tx_general_context_desc_dqo *desc,
 	};
 }
 
-/* Returns 0 on success, or < 0 on error.
- *
- * Before this function is called, the caller must ensure
- * gve_has_pending_packet(tx) returns true.
- */
 static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
-				      struct sk_buff *skb)
+				      struct sk_buff *skb,
+				      struct gve_tx_pending_packet_dqo *pkt,
+				      s16 completion_tag,
+				      u32 *desc_idx,
+				      bool is_gso)
 {
 	const struct skb_shared_info *shinfo = skb_shinfo(skb);
-	const bool is_gso = skb_is_gso(skb);
-	u32 desc_idx = tx->dqo_tx.tail;
-
-	struct gve_tx_pending_packet_dqo *pkt;
-	struct gve_tx_metadata_dqo metadata;
-	s16 completion_tag;
 	int i;
 
-	pkt = gve_alloc_pending_packet(tx);
-	pkt->skb = skb;
-	pkt->num_bufs = 0;
-	completion_tag = pkt - tx->dqo.pending_packets;
-
-	gve_extract_tx_metadata_dqo(skb, &metadata);
-	if (is_gso) {
-		int header_len = gve_prep_tso(skb);
-
-		if (unlikely(header_len < 0))
-			goto err;
-
-		gve_tx_fill_tso_ctx_desc(&tx->dqo.tx_ring[desc_idx].tso_ctx,
-					 skb, &metadata, header_len);
-		desc_idx = (desc_idx + 1) & tx->mask;
-	}
-
-	gve_tx_fill_general_ctx_desc(&tx->dqo.tx_ring[desc_idx].general_ctx,
-				     &metadata);
-	desc_idx = (desc_idx + 1) & tx->mask;
-
 	/* Note: HW requires that the size of a non-TSO packet be within the
 	 * range of [17, 9728].
 	 *
@@ -490,6 +593,7 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
 	 * - Hypervisor won't allow MTU larger than 9216.
 	 */
 
+	pkt->num_bufs = 0;
 	/* Map the linear portion of skb */
 	{
 		u32 len = skb_headlen(skb);
@@ -503,7 +607,7 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
 		dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr);
 		++pkt->num_bufs;
 
-		gve_tx_fill_pkt_desc_dqo(tx, &desc_idx, skb, len, addr,
+		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, skb, len, addr,
 					 completion_tag,
 					 /*eop=*/shinfo->nr_frags == 0, is_gso);
 	}
@@ -522,10 +626,139 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
 		dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr);
 		++pkt->num_bufs;
 
-		gve_tx_fill_pkt_desc_dqo(tx, &desc_idx, skb, len, addr,
+		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, skb, len, addr,
 					 completion_tag, is_eop, is_gso);
 	}
 
+	return 0;
+err:
+	for (i = 0; i < pkt->num_bufs; i++) {
+		if (i == 0) {
+			dma_unmap_single(tx->dev,
+					 dma_unmap_addr(pkt, dma[i]),
+					 dma_unmap_len(pkt, len[i]),
+					 DMA_TO_DEVICE);
+		} else {
+			dma_unmap_page(tx->dev,
+				       dma_unmap_addr(pkt, dma[i]),
+				       dma_unmap_len(pkt, len[i]),
+				       DMA_TO_DEVICE);
+		}
+	}
+	pkt->num_bufs = 0;
+	return -1;
+}
+
+/* Tx buffer i corresponds to
+ * qpl_page_id = i / GVE_TX_BUFS_PER_PAGE_DQO
+ * qpl_page_offset = (i % GVE_TX_BUFS_PER_PAGE_DQO) * GVE_TX_BUF_SIZE_DQO
+ */
+static void gve_tx_buf_get_addr(struct gve_tx_ring *tx,
+				s16 index,
+				void **va, dma_addr_t *dma_addr)
+{
+	int page_id = index >> (PAGE_SHIFT - GVE_TX_BUF_SHIFT_DQO);
+	int offset = (index & (GVE_TX_BUFS_PER_PAGE_DQO - 1)) << GVE_TX_BUF_SHIFT_DQO;
+
+	*va = page_address(tx->dqo.qpl->pages[page_id]) + offset;
+	*dma_addr = tx->dqo.qpl->page_buses[page_id] + offset;
+}
+
+static int gve_tx_add_skb_copy_dqo(struct gve_tx_ring *tx,
+				   struct sk_buff *skb,
+				   struct gve_tx_pending_packet_dqo *pkt,
+				   s16 completion_tag,
+				   u32 *desc_idx,
+				   bool is_gso)
+{
+	u32 copy_offset = 0;
+	dma_addr_t dma_addr;
+	u32 copy_len;
+	s16 index;
+	void *va;
+
+	/* Break the packet into buffer size chunks */
+	pkt->num_bufs = 0;
+	while (copy_offset < skb->len) {
+		index = gve_alloc_tx_qpl_buf(tx);
+		if (unlikely(index == -1))
+			goto err;
+
+		gve_tx_buf_get_addr(tx, index, &va, &dma_addr);
+		copy_len = min_t(u32, GVE_TX_BUF_SIZE_DQO,
+				 skb->len - copy_offset);
+		skb_copy_bits(skb, copy_offset, va, copy_len);
+
+		copy_offset += copy_len;
+		dma_sync_single_for_device(tx->dev, dma_addr,
+					   copy_len, DMA_TO_DEVICE);
+		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, skb,
+					 copy_len,
+					 dma_addr,
+					 completion_tag,
+					 copy_offset == skb->len,
+					 is_gso);
+
+		pkt->tx_qpl_buf_ids[pkt->num_bufs] = index;
+		++tx->dqo_tx.alloc_tx_qpl_buf_cnt;
+		++pkt->num_bufs;
+	}
+
+	return 0;
+err:
+	/* Should not be here if gve_has_free_tx_qpl_bufs() check is correct */
+	gve_free_tx_qpl_bufs(tx, pkt);
+	return -ENOMEM;
+}
+
+/* Returns 0 on success, or < 0 on error.
+ *
+ * Before this function is called, the caller must ensure
+ * gve_has_pending_packet(tx) returns true.
+ */
+static int gve_tx_add_skb_dqo(struct gve_tx_ring *tx,
+			      struct sk_buff *skb)
+{
+	const bool is_gso = skb_is_gso(skb);
+	u32 desc_idx = tx->dqo_tx.tail;
+	struct gve_tx_pending_packet_dqo *pkt;
+	struct gve_tx_metadata_dqo metadata;
+	s16 completion_tag;
+
+	pkt = gve_alloc_pending_packet(tx);
+	pkt->skb = skb;
+	completion_tag = pkt - tx->dqo.pending_packets;
+
+	gve_extract_tx_metadata_dqo(skb, &metadata);
+	if (is_gso) {
+		int header_len = gve_prep_tso(skb);
+
+		if (unlikely(header_len < 0))
+			goto err;
+
+		gve_tx_fill_tso_ctx_desc(&tx->dqo.tx_ring[desc_idx].tso_ctx,
+					 skb, &metadata, header_len);
+		desc_idx = (desc_idx + 1) & tx->mask;
+	}
+
+	gve_tx_fill_general_ctx_desc(&tx->dqo.tx_ring[desc_idx].general_ctx,
+				     &metadata);
+	desc_idx = (desc_idx + 1) & tx->mask;
+
+	if (tx->dqo.qpl) {
+		if (gve_tx_add_skb_copy_dqo(tx, skb, pkt,
+					    completion_tag,
+					    &desc_idx, is_gso))
+			goto err;
+	}  else {
+		if (gve_tx_add_skb_no_copy_dqo(tx, skb, pkt,
+					       completion_tag,
+					       &desc_idx, is_gso))
+			goto err;
+	}
+
+	tx->dqo_tx.posted_packet_desc_cnt += pkt->num_bufs;
+
 	/* Commit the changes to our state */
 	tx->dqo_tx.tail = desc_idx;
 
@@ -547,22 +780,7 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
 	return 0;
 
 err:
-	for (i = 0; i < pkt->num_bufs; i++) {
-		if (i == 0) {
-			dma_unmap_single(tx->dev,
-					 dma_unmap_addr(pkt, dma[i]),
-					 dma_unmap_len(pkt, len[i]),
-					 DMA_TO_DEVICE);
-		} else {
-			dma_unmap_page(tx->dev,
-				       dma_unmap_addr(pkt, dma[i]),
-				       dma_unmap_len(pkt, len[i]),
-				       DMA_TO_DEVICE);
-		}
-	}
-
 	pkt->skb = NULL;
-	pkt->num_bufs = 0;
 	gve_free_pending_packet(tx, pkt);
 
 	return -1;
@@ -636,40 +854,56 @@ static int gve_try_tx_skb(struct gve_priv *priv, struct gve_tx_ring *tx,
 	int num_buffer_descs;
 	int total_num_descs;
 
-	if (skb_is_gso(skb)) {
-		/* If TSO doesn't meet HW requirements, attempt to linearize the
-		 * packet.
-		 */
-		if (unlikely(!gve_can_send_tso(skb) &&
-			     skb_linearize(skb) < 0)) {
-			net_err_ratelimited("%s: Failed to transmit TSO packet\n",
-					    priv->dev->name);
-			goto drop;
-		}
-
-		if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
-			goto drop;
+	if (tx->dqo.qpl) {
+		if (skb_is_gso(skb))
+			if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
+				goto drop;
 
-		num_buffer_descs = gve_num_buffer_descs_needed(skb);
+		/* We do not need to verify the number of buffers used per
+		 * packet or per segment in case of TSO as with 2K size buffers
+		 * none of the TX packet rules would be violated.
+		 *
+		 * gve_can_send_tso() checks that each TCP segment of gso_size is
+		 * not distributed over more than 9 SKB frags..
+		 */
+		num_buffer_descs = DIV_ROUND_UP(skb->len, GVE_TX_BUF_SIZE_DQO);
 	} else {
-		num_buffer_descs = gve_num_buffer_descs_needed(skb);
+		if (skb_is_gso(skb)) {
+			/* If TSO doesn't meet HW requirements, attempt to linearize the
+			 * packet.
+			 */
+			if (unlikely(!gve_can_send_tso(skb) &&
+				     skb_linearize(skb) < 0)) {
+				net_err_ratelimited("%s: Failed to transmit TSO packet\n",
+						    priv->dev->name);
+				goto drop;
+			}
 
-		if (unlikely(num_buffer_descs > GVE_TX_MAX_DATA_DESCS)) {
-			if (unlikely(skb_linearize(skb) < 0))
+			if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
 				goto drop;
 
-			num_buffer_descs = 1;
+			num_buffer_descs = gve_num_buffer_descs_needed(skb);
+		} else {
+			num_buffer_descs = gve_num_buffer_descs_needed(skb);
+
+			if (unlikely(num_buffer_descs > GVE_TX_MAX_DATA_DESCS)) {
+				if (unlikely(skb_linearize(skb) < 0))
+					goto drop;
+
+				num_buffer_descs = 1;
+			}
 		}
 	}
 
 	/* Metadata + (optional TSO) + data descriptors. */
 	total_num_descs = 1 + skb_is_gso(skb) + num_buffer_descs;
 	if (unlikely(gve_maybe_stop_tx_dqo(tx, total_num_descs +
-			GVE_TX_MIN_DESC_PREVENT_CACHE_OVERLAP))) {
+			GVE_TX_MIN_DESC_PREVENT_CACHE_OVERLAP,
+			num_buffer_descs))) {
 		return -1;
 	}
 
-	if (unlikely(gve_tx_add_skb_no_copy_dqo(tx, skb) < 0))
+	if (unlikely(gve_tx_add_skb_dqo(tx, skb) < 0))
 		goto drop;
 
 	netdev_tx_sent_queue(tx->netdev_txq, skb->len);
@@ -817,7 +1051,11 @@ static void gve_handle_packet_completion(struct gve_priv *priv,
 			return;
 		}
 	}
-	gve_unmap_packet(tx->dev, pending_packet);
+	tx->dqo_tx.completed_packet_desc_cnt += pending_packet->num_bufs;
+	if (tx->dqo.qpl)
+		gve_free_tx_qpl_bufs(tx, pending_packet);
+	else
+		gve_unmap_packet(tx->dev, pending_packet);
 
 	*bytes += pending_packet->skb->len;
 	(*pkts)++;
@@ -875,12 +1113,16 @@ static void remove_miss_completions(struct gve_priv *priv,
 
 		remove_from_list(tx, &tx->dqo_compl.miss_completions,
 				 pending_packet);
-		/* Unmap buffers and free skb but do not unallocate packet i.e.
+		/* Unmap/free TX buffers and free skb but do not unallocate packet i.e.
 		 * the completion tag is not freed to ensure that the driver
 		 * can take appropriate action if a corresponding valid
 		 * completion is received later.
 		 */
-		gve_unmap_packet(tx->dev, pending_packet);
+		if (tx->dqo.qpl)
+			gve_free_tx_qpl_bufs(tx, pending_packet);
+		else
+			gve_unmap_packet(tx->dev, pending_packet);
+
 		/* This indicates the packet was dropped. */
 		dev_kfree_skb_any(pending_packet->skb);
 		pending_packet->skb = NULL;
-- 
GitLab


From e7075ab4fb6b39730dfbfbfa3a5505d678f01d2c Mon Sep 17 00:00:00 2001
From: Rushil Gupta <rushilg@google.com>
Date: Fri, 4 Aug 2023 21:34:43 +0000
Subject: [PATCH 0913/1806] gve: RX path for DQO-QPL

The RX path allocates the QPL page pool at queue creation, and
tries to reuse these pages through page recycling. This patch
ensures that on refill no non-QPL pages are posted to the device.

When the driver is running low on free buffers, an ondemand
allocation step kicks in that allocates a non-qpl page for
SKB business to free up the QPL page in use.

gve_try_recycle_buf was moved to gve_rx_append_frags so that driver does
not attempt to mark buffer as used if a non-qpl page was allocated
ondemand.

Signed-off-by: Rushil Gupta <rushilg@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Bailey Forrest <bcf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/google/gve/gve.h        |   6 +
 drivers/net/ethernet/google/gve/gve_rx_dqo.c | 126 ++++++++++++++++---
 2 files changed, 114 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 2042f79cea1f6..0d1e681be2507 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -241,6 +241,12 @@ struct gve_rx_ring {
 
 			/* qpl assigned to this queue */
 			struct gve_queue_page_list *qpl;
+
+			/* index into queue page list */
+			u32 next_qpl_page_idx;
+
+			/* track number of used buffers */
+			u16 used_buf_states_cnt;
 		} dqo;
 	};
 
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index e57b73eb70f62..ea0e38b4d9e9f 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -22,11 +22,13 @@ static int gve_buf_ref_cnt(struct gve_rx_buf_state_dqo *bs)
 }
 
 static void gve_free_page_dqo(struct gve_priv *priv,
-			      struct gve_rx_buf_state_dqo *bs)
+			      struct gve_rx_buf_state_dqo *bs,
+			      bool free_page)
 {
 	page_ref_sub(bs->page_info.page, bs->page_info.pagecnt_bias - 1);
-	gve_free_page(&priv->pdev->dev, bs->page_info.page, bs->addr,
-		      DMA_FROM_DEVICE);
+	if (free_page)
+		gve_free_page(&priv->pdev->dev, bs->page_info.page, bs->addr,
+			      DMA_FROM_DEVICE);
 	bs->page_info.page = NULL;
 }
 
@@ -130,12 +132,20 @@ gve_get_recycled_buf_state(struct gve_rx_ring *rx)
 	 */
 	for (i = 0; i < 5; i++) {
 		buf_state = gve_dequeue_buf_state(rx, &rx->dqo.used_buf_states);
-		if (gve_buf_ref_cnt(buf_state) == 0)
+		if (gve_buf_ref_cnt(buf_state) == 0) {
+			rx->dqo.used_buf_states_cnt--;
 			return buf_state;
+		}
 
 		gve_enqueue_buf_state(rx, &rx->dqo.used_buf_states, buf_state);
 	}
 
+	/* For QPL, we cannot allocate any new buffers and must
+	 * wait for the existing ones to be available.
+	 */
+	if (rx->dqo.qpl)
+		return NULL;
+
 	/* If there are no free buf states discard an entry from
 	 * `used_buf_states` so it can be used.
 	 */
@@ -144,23 +154,39 @@ gve_get_recycled_buf_state(struct gve_rx_ring *rx)
 		if (gve_buf_ref_cnt(buf_state) == 0)
 			return buf_state;
 
-		gve_free_page_dqo(rx->gve, buf_state);
+		gve_free_page_dqo(rx->gve, buf_state, true);
 		gve_free_buf_state(rx, buf_state);
 	}
 
 	return NULL;
 }
 
-static int gve_alloc_page_dqo(struct gve_priv *priv,
+static int gve_alloc_page_dqo(struct gve_rx_ring *rx,
 			      struct gve_rx_buf_state_dqo *buf_state)
 {
-	int err;
+	struct gve_priv *priv = rx->gve;
+	u32 idx;
 
-	err = gve_alloc_page(priv, &priv->pdev->dev, &buf_state->page_info.page,
-			     &buf_state->addr, DMA_FROM_DEVICE, GFP_ATOMIC);
-	if (err)
-		return err;
+	if (!rx->dqo.qpl) {
+		int err;
 
+		err = gve_alloc_page(priv, &priv->pdev->dev,
+				     &buf_state->page_info.page,
+				     &buf_state->addr,
+				     DMA_FROM_DEVICE, GFP_ATOMIC);
+		if (err)
+			return err;
+	} else {
+		idx = rx->dqo.next_qpl_page_idx;
+		if (idx >= priv->rx_pages_per_qpl) {
+			net_err_ratelimited("%s: Out of QPL pages\n",
+					    priv->dev->name);
+			return -ENOMEM;
+		}
+		buf_state->page_info.page = rx->dqo.qpl->pages[idx];
+		buf_state->addr = rx->dqo.qpl->page_buses[idx];
+		rx->dqo.next_qpl_page_idx++;
+	}
 	buf_state->page_info.page_offset = 0;
 	buf_state->page_info.page_address =
 		page_address(buf_state->page_info.page);
@@ -195,9 +221,13 @@ static void gve_rx_free_ring_dqo(struct gve_priv *priv, int idx)
 
 	for (i = 0; i < rx->dqo.num_buf_states; i++) {
 		struct gve_rx_buf_state_dqo *bs = &rx->dqo.buf_states[i];
-
+		/* Only free page for RDA. QPL pages are freed in gve_main. */
 		if (bs->page_info.page)
-			gve_free_page_dqo(priv, bs);
+			gve_free_page_dqo(priv, bs, !rx->dqo.qpl);
+	}
+	if (rx->dqo.qpl) {
+		gve_unassign_qpl(priv, rx->dqo.qpl->id);
+		rx->dqo.qpl = NULL;
 	}
 
 	if (rx->dqo.bufq.desc_ring) {
@@ -229,7 +259,8 @@ static int gve_rx_alloc_ring_dqo(struct gve_priv *priv, int idx)
 	int i;
 
 	const u32 buffer_queue_slots =
-		priv->options_dqo_rda.rx_buff_ring_entries;
+		priv->queue_format == GVE_DQO_RDA_FORMAT ?
+		priv->options_dqo_rda.rx_buff_ring_entries : priv->rx_desc_cnt;
 	const u32 completion_queue_slots = priv->rx_desc_cnt;
 
 	netif_dbg(priv, drv, priv->dev, "allocating rx ring DQO\n");
@@ -243,7 +274,9 @@ static int gve_rx_alloc_ring_dqo(struct gve_priv *priv, int idx)
 	rx->ctx.skb_head = NULL;
 	rx->ctx.skb_tail = NULL;
 
-	rx->dqo.num_buf_states = min_t(s16, S16_MAX, buffer_queue_slots * 4);
+	rx->dqo.num_buf_states = priv->queue_format == GVE_DQO_RDA_FORMAT ?
+		min_t(s16, S16_MAX, buffer_queue_slots * 4) :
+		priv->rx_pages_per_qpl;
 	rx->dqo.buf_states = kvcalloc(rx->dqo.num_buf_states,
 				      sizeof(rx->dqo.buf_states[0]),
 				      GFP_KERNEL);
@@ -275,6 +308,13 @@ static int gve_rx_alloc_ring_dqo(struct gve_priv *priv, int idx)
 	if (!rx->dqo.bufq.desc_ring)
 		goto err;
 
+	if (priv->queue_format != GVE_DQO_RDA_FORMAT) {
+		rx->dqo.qpl = gve_assign_rx_qpl(priv, rx->q_num);
+		if (!rx->dqo.qpl)
+			goto err;
+		rx->dqo.next_qpl_page_idx = 0;
+	}
+
 	rx->q_resources = dma_alloc_coherent(hdev, sizeof(*rx->q_resources),
 					     &rx->q_resources_bus, GFP_KERNEL);
 	if (!rx->q_resources)
@@ -352,7 +392,7 @@ void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx)
 			if (unlikely(!buf_state))
 				break;
 
-			if (unlikely(gve_alloc_page_dqo(priv, buf_state))) {
+			if (unlikely(gve_alloc_page_dqo(rx, buf_state))) {
 				u64_stats_update_begin(&rx->statss);
 				rx->rx_buf_alloc_fail++;
 				u64_stats_update_end(&rx->statss);
@@ -415,6 +455,7 @@ static void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx,
 
 mark_used:
 	gve_enqueue_buf_state(rx, &rx->dqo.used_buf_states, buf_state);
+	rx->dqo.used_buf_states_cnt++;
 }
 
 static void gve_rx_skb_csum(struct sk_buff *skb,
@@ -475,6 +516,43 @@ static void gve_rx_free_skb(struct gve_rx_ring *rx)
 	rx->ctx.skb_tail = NULL;
 }
 
+static bool gve_rx_should_trigger_copy_ondemand(struct gve_rx_ring *rx)
+{
+	if (!rx->dqo.qpl)
+		return false;
+	if (rx->dqo.used_buf_states_cnt <
+		     (rx->dqo.num_buf_states -
+		     GVE_DQO_QPL_ONDEMAND_ALLOC_THRESHOLD))
+		return false;
+	return true;
+}
+
+static int gve_rx_copy_ondemand(struct gve_rx_ring *rx,
+				struct gve_rx_buf_state_dqo *buf_state,
+				u16 buf_len)
+{
+	struct page *page = alloc_page(GFP_ATOMIC);
+	int num_frags;
+
+	if (!page)
+		return -ENOMEM;
+
+	memcpy(page_address(page),
+	       buf_state->page_info.page_address +
+	       buf_state->page_info.page_offset,
+	       buf_len);
+	num_frags = skb_shinfo(rx->ctx.skb_tail)->nr_frags;
+	skb_add_rx_frag(rx->ctx.skb_tail, num_frags, page,
+			0, buf_len, PAGE_SIZE);
+
+	u64_stats_update_begin(&rx->statss);
+	rx->rx_frag_alloc_cnt++;
+	u64_stats_update_end(&rx->statss);
+	/* Return unused buffer. */
+	gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states, buf_state);
+	return 0;
+}
+
 /* Chains multi skbs for single rx packet.
  * Returns 0 if buffer is appended, -1 otherwise.
  */
@@ -502,12 +580,20 @@ static int gve_rx_append_frags(struct napi_struct *napi,
 		rx->ctx.skb_head->truesize += priv->data_buffer_size_dqo;
 	}
 
+	/* Trigger ondemand page allocation if we are running low on buffers */
+	if (gve_rx_should_trigger_copy_ondemand(rx))
+		return gve_rx_copy_ondemand(rx, buf_state, buf_len);
+
 	skb_add_rx_frag(rx->ctx.skb_tail, num_frags,
 			buf_state->page_info.page,
 			buf_state->page_info.page_offset,
 			buf_len, priv->data_buffer_size_dqo);
 	gve_dec_pagecnt_bias(&buf_state->page_info);
 
+	/* Advances buffer page-offset if page is partially used.
+	 * Marks buffer as used if page is full.
+	 */
+	gve_try_recycle_buf(priv, rx, buf_state);
 	return 0;
 }
 
@@ -561,8 +647,6 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 						 priv)) != 0) {
 			goto error;
 		}
-
-		gve_try_recycle_buf(priv, rx, buf_state);
 		return 0;
 	}
 
@@ -588,6 +672,12 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 		goto error;
 	rx->ctx.skb_tail = rx->ctx.skb_head;
 
+	if (gve_rx_should_trigger_copy_ondemand(rx)) {
+		if (gve_rx_copy_ondemand(rx, buf_state, buf_len) < 0)
+			goto error;
+		return 0;
+	}
+
 	skb_add_rx_frag(rx->ctx.skb_head, 0, buf_state->page_info.page,
 			buf_state->page_info.page_offset, buf_len,
 			priv->data_buffer_size_dqo);
-- 
GitLab


From 5a3f8d1231073fc5f0b6f38ab8337d424ba0cfe4 Mon Sep 17 00:00:00 2001
From: Rushil Gupta <rushilg@google.com>
Date: Fri, 4 Aug 2023 21:34:44 +0000
Subject: [PATCH 0914/1806] gve: update gve.rst

Add a note about QPL and RDA mode

Signed-off-by: Rushil Gupta <rushilg@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Bailey Forrest <bcf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../networking/device_drivers/ethernet/google/gve.rst    | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/networking/device_drivers/ethernet/google/gve.rst b/Documentation/networking/device_drivers/ethernet/google/gve.rst
index 6d73ee78f3d74..31d621bca82ef 100644
--- a/Documentation/networking/device_drivers/ethernet/google/gve.rst
+++ b/Documentation/networking/device_drivers/ethernet/google/gve.rst
@@ -52,6 +52,15 @@ Descriptor Formats
 GVE supports two descriptor formats: GQI and DQO. These two formats have
 entirely different descriptors, which will be described below.
 
+Addressing Mode
+------------------
+GVE supports two addressing modes: QPL and RDA.
+QPL ("queue-page-list") mode communicates data through a set of
+pre-registered pages.
+
+For RDA ("raw DMA addressing") mode, the set of pages is dynamic.
+Therefore, the packet buffers can be anywhere in guest memory.
+
 Registers
 ---------
 All registers are MMIO.
-- 
GitLab


From b1d13f7a3b5396503e6869ed627bb4eeab9b524f Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Fri, 4 Aug 2023 13:33:53 -0700
Subject: [PATCH 0915/1806] net: mana: Add page pool for RX buffers

Add page pool for RX buffers for faster buffer cycle and reduce CPU
usage.

The standard page pool API is used.

With iperf and 128 threads test, this patch improved the throughput
by 12-15%, and decreased the IRQ associated CPU's usage from 99-100% to
10-50%.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 90 +++++++++++++++----
 include/net/mana/mana.h                       |  3 +
 2 files changed, 77 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 21665f114fe9b..a08023c57e25e 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1415,8 +1415,8 @@ static struct sk_buff *mana_build_skb(struct mana_rxq *rxq, void *buf_va,
 	return skb;
 }
 
-static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe,
-			struct mana_rxq *rxq)
+static void mana_rx_skb(void *buf_va, bool from_pool,
+			struct mana_rxcomp_oob *cqe, struct mana_rxq *rxq)
 {
 	struct mana_stats_rx *rx_stats = &rxq->stats;
 	struct net_device *ndev = rxq->ndev;
@@ -1449,6 +1449,9 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe,
 	if (!skb)
 		goto drop;
 
+	if (from_pool)
+		skb_mark_for_recycle(skb);
+
 	skb->dev = napi->dev;
 
 	skb->protocol = eth_type_trans(skb, ndev);
@@ -1499,9 +1502,14 @@ drop_xdp:
 	u64_stats_update_end(&rx_stats->syncp);
 
 drop:
-	WARN_ON_ONCE(rxq->xdp_save_va);
-	/* Save for reuse */
-	rxq->xdp_save_va = buf_va;
+	if (from_pool) {
+		page_pool_recycle_direct(rxq->page_pool,
+					 virt_to_head_page(buf_va));
+	} else {
+		WARN_ON_ONCE(rxq->xdp_save_va);
+		/* Save for reuse */
+		rxq->xdp_save_va = buf_va;
+	}
 
 	++ndev->stats.rx_dropped;
 
@@ -1509,11 +1517,13 @@ drop:
 }
 
 static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
-			     dma_addr_t *da, bool is_napi)
+			     dma_addr_t *da, bool *from_pool, bool is_napi)
 {
 	struct page *page;
 	void *va;
 
+	*from_pool = false;
+
 	/* Reuse XDP dropped page if available */
 	if (rxq->xdp_save_va) {
 		va = rxq->xdp_save_va;
@@ -1534,17 +1544,22 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
 			return NULL;
 		}
 	} else {
-		page = dev_alloc_page();
+		page = page_pool_dev_alloc_pages(rxq->page_pool);
 		if (!page)
 			return NULL;
 
+		*from_pool = true;
 		va = page_to_virt(page);
 	}
 
 	*da = dma_map_single(dev, va + rxq->headroom, rxq->datasize,
 			     DMA_FROM_DEVICE);
 	if (dma_mapping_error(dev, *da)) {
-		put_page(virt_to_head_page(va));
+		if (*from_pool)
+			page_pool_put_full_page(rxq->page_pool, page, false);
+		else
+			put_page(virt_to_head_page(va));
+
 		return NULL;
 	}
 
@@ -1553,21 +1568,25 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
 
 /* Allocate frag for rx buffer, and save the old buf */
 static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq,
-			       struct mana_recv_buf_oob *rxoob, void **old_buf)
+			       struct mana_recv_buf_oob *rxoob, void **old_buf,
+			       bool *old_fp)
 {
+	bool from_pool;
 	dma_addr_t da;
 	void *va;
 
-	va = mana_get_rxfrag(rxq, dev, &da, true);
+	va = mana_get_rxfrag(rxq, dev, &da, &from_pool, true);
 	if (!va)
 		return;
 
 	dma_unmap_single(dev, rxoob->sgl[0].address, rxq->datasize,
 			 DMA_FROM_DEVICE);
 	*old_buf = rxoob->buf_va;
+	*old_fp = rxoob->from_pool;
 
 	rxoob->buf_va = va;
 	rxoob->sgl[0].address = da;
+	rxoob->from_pool = from_pool;
 }
 
 static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
@@ -1581,6 +1600,7 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
 	struct device *dev = gc->dev;
 	void *old_buf = NULL;
 	u32 curr, pktlen;
+	bool old_fp;
 
 	apc = netdev_priv(ndev);
 
@@ -1623,12 +1643,12 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
 	rxbuf_oob = &rxq->rx_oobs[curr];
 	WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1);
 
-	mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf);
+	mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp);
 
 	/* Unsuccessful refill will have old_buf == NULL.
 	 * In this case, mana_rx_skb() will drop the packet.
 	 */
-	mana_rx_skb(old_buf, oob, rxq);
+	mana_rx_skb(old_buf, old_fp, oob, rxq);
 
 drop:
 	mana_move_wq_tail(rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu);
@@ -1888,6 +1908,7 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
 	struct mana_recv_buf_oob *rx_oob;
 	struct device *dev = gc->dev;
 	struct napi_struct *napi;
+	struct page *page;
 	int i;
 
 	if (!rxq)
@@ -1920,10 +1941,18 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
 		dma_unmap_single(dev, rx_oob->sgl[0].address,
 				 rx_oob->sgl[0].size, DMA_FROM_DEVICE);
 
-		put_page(virt_to_head_page(rx_oob->buf_va));
+		page = virt_to_head_page(rx_oob->buf_va);
+
+		if (rx_oob->from_pool)
+			page_pool_put_full_page(rxq->page_pool, page, false);
+		else
+			put_page(page);
+
 		rx_oob->buf_va = NULL;
 	}
 
+	page_pool_destroy(rxq->page_pool);
+
 	if (rxq->gdma_rq)
 		mana_gd_destroy_queue(gc, rxq->gdma_rq);
 
@@ -1934,18 +1963,20 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key,
 			    struct mana_rxq *rxq, struct device *dev)
 {
 	struct mana_port_context *mpc = netdev_priv(rxq->ndev);
+	bool from_pool = false;
 	dma_addr_t da;
 	void *va;
 
 	if (mpc->rxbufs_pre)
 		va = mana_get_rxbuf_pre(rxq, &da);
 	else
-		va = mana_get_rxfrag(rxq, dev, &da, false);
+		va = mana_get_rxfrag(rxq, dev, &da, &from_pool, false);
 
 	if (!va)
 		return -ENOMEM;
 
 	rx_oob->buf_va = va;
+	rx_oob->from_pool = from_pool;
 
 	rx_oob->sgl[0].address = da;
 	rx_oob->sgl[0].size = rxq->datasize;
@@ -2015,6 +2046,26 @@ static int mana_push_wqe(struct mana_rxq *rxq)
 	return 0;
 }
 
+static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
+{
+	struct page_pool_params pprm = {};
+	int ret;
+
+	pprm.pool_size = RX_BUFFERS_PER_QUEUE;
+	pprm.nid = gc->numa_node;
+	pprm.napi = &rxq->rx_cq.napi;
+
+	rxq->page_pool = page_pool_create(&pprm);
+
+	if (IS_ERR(rxq->page_pool)) {
+		ret = PTR_ERR(rxq->page_pool);
+		rxq->page_pool = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
 static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 					u32 rxq_idx, struct mana_eq *eq,
 					struct net_device *ndev)
@@ -2044,6 +2095,13 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 	mana_get_rxbuf_cfg(ndev->mtu, &rxq->datasize, &rxq->alloc_size,
 			   &rxq->headroom);
 
+	/* Create page pool for RX queue */
+	err = mana_create_page_pool(rxq, gc);
+	if (err) {
+		netdev_err(ndev, "Create page pool err:%d\n", err);
+		goto out;
+	}
+
 	err = mana_alloc_rx_wqe(apc, rxq, &rq_size, &cq_size);
 	if (err)
 		goto out;
@@ -2115,8 +2173,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 
 	WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx,
 				 cq->napi.napi_id));
-	WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq,
-					   MEM_TYPE_PAGE_SHARED, NULL));
+	WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, MEM_TYPE_PAGE_POOL,
+					   rxq->page_pool));
 
 	napi_enable(&cq->napi);
 
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 1ccdca03e166e..879990101c9f5 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -282,6 +282,7 @@ struct mana_recv_buf_oob {
 	struct gdma_wqe_request wqe_req;
 
 	void *buf_va;
+	bool from_pool; /* allocated from a page pool */
 
 	/* SGL of the buffer going to be sent has part of the work request. */
 	u32 num_sge;
@@ -332,6 +333,8 @@ struct mana_rxq {
 	bool xdp_flush;
 	int xdp_rc; /* XDP redirect return code */
 
+	struct page_pool *page_pool;
+
 	/* MUST BE THE LAST MEMBER:
 	 * Each receive buffer has an associated mana_recv_buf_oob.
 	 */
-- 
GitLab


From 813f3662c2403f590a3307ea66f4eea699c8d8e4 Mon Sep 17 00:00:00 2001
From: Yu Liao <liaoyu15@huawei.com>
Date: Fri, 4 Aug 2023 17:21:43 +0800
Subject: [PATCH 0916/1806] ibmvnic: remove unused rc variable

gcc with W=1 reports
drivers/net/ethernet/ibm/ibmvnic.c:194:13: warning: variable 'rc' set but not used [-Wunused-but-set-variable]
                                            ^
This variable is not used so remove it.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308040609.zQsSXWXI-lkp@intel.com/
Signed-off-by: Yu Liao <liaoyu15@huawei.com>
Reviewed-by: Nick Child <nnac123@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 763d613adbcc0..01535b03eab6f 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -191,9 +191,8 @@ static void ibmvnic_clean_affinity(struct ibmvnic_adapter *adapter)
 	struct ibmvnic_sub_crq_queue **rxqs;
 	struct ibmvnic_sub_crq_queue **txqs;
 	int num_rxqs, num_txqs;
-	int rc, i;
+	int i;
 
-	rc = 0;
 	rxqs = adapter->rx_scrq;
 	txqs = adapter->tx_scrq;
 	num_txqs = adapter->num_active_tx_scrqs;
-- 
GitLab


From 54024dbec95585243391caeb9f04a2620e630765 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Fri, 4 Aug 2023 17:35:31 +0800
Subject: [PATCH 0917/1806] net: ethernet: adi: adin1110: use
 eth_broadcast_addr() to assign broadcast address

Use eth_broadcast_addr() to assign broadcast address instead
of memset().

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/adi/adin1110.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c
index f5c2d7a9abc10..1c009b485188d 100644
--- a/drivers/net/ethernet/adi/adin1110.c
+++ b/drivers/net/ethernet/adi/adin1110.c
@@ -739,7 +739,7 @@ static int adin1110_broadcasts_filter(struct adin1110_port_priv *port_priv,
 	u32 port_rules = 0;
 	u8 mask[ETH_ALEN];
 
-	memset(mask, 0xFF, ETH_ALEN);
+	eth_broadcast_addr(mask);
 
 	if (accept_broadcast && port_priv->state == BR_STATE_FORWARDING)
 		port_rules = adin1110_port_rules(port_priv, true, true);
@@ -760,7 +760,7 @@ static int adin1110_set_mac_address(struct net_device *netdev,
 		return -EADDRNOTAVAIL;
 
 	eth_hw_addr_set(netdev, dev_addr);
-	memset(mask, 0xFF, ETH_ALEN);
+	eth_broadcast_addr(mask);
 
 	mac_slot = (!port_priv->nr) ?  ADIN_MAC_P1_ADDR_SLOT : ADIN_MAC_P2_ADDR_SLOT;
 	port_rules = adin1110_port_rules(port_priv, true, false);
@@ -1271,7 +1271,7 @@ static int adin1110_port_set_blocking_state(struct adin1110_port_priv *port_priv
 		goto out;
 
 	/* Allow only BPDUs to be passed to the CPU */
-	memset(mask, 0xFF, ETH_ALEN);
+	eth_broadcast_addr(mask);
 	port_rules = adin1110_port_rules(port_priv, true, false);
 	ret = adin1110_write_mac_address(port_priv, mac_slot, mac,
 					 mask, port_rules);
@@ -1386,7 +1386,7 @@ static int adin1110_fdb_add(struct adin1110_port_priv *port_priv,
 
 	other_port = priv->ports[!port_priv->nr];
 	port_rules = adin1110_port_rules(port_priv, false, true);
-	memset(mask, 0xFF, ETH_ALEN);
+	eth_broadcast_addr(mask);
 
 	return adin1110_write_mac_address(other_port, mac_nr, (u8 *)fdb->addr,
 					  mask, port_rules);
-- 
GitLab


From c35e927cbe09d38b2d72183bb215901183927c68 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 4 Aug 2023 16:49:39 +0300
Subject: [PATCH 0918/1806] net: omit ndo_hwtstamp_get() call when possible in
 dev_set_hwtstamp_phylib()

Setting dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS is only legal
for drivers which were converted to ndo_hwtstamp_get() and
ndo_hwtstamp_set(), and it is only there that we call ndo_hwtstamp_set()
for a request that otherwise goes to phylib (for stuff like packet traps,
which need to be undone if phylib failed, hence the old_cfg logic).

The problem is that we end up calling ndo_hwtstamp_get() when we don't
need to (even if the SIOCSHWTSTAMP wasn't intended for phylib, or if it
was, but the driver didn't set IFF_SEE_ALL_HWTSTAMP_REQUESTS). For those
unnecessary conditions, we share a code path with virtual drivers (vlan,
macvlan, bonding) where ndo_hwtstamp_get() is implemented as
generic_hwtstamp_get_lower(), and may be resolved through
generic_hwtstamp_ioctl_lower() if the lower device is unconverted.

I.e. this situation:

$ ip link add link eno0 name eno0.100 type vlan id 100
$ hwstamp_ctl -i eno0.100 -t 1

We are unprepared to deal with this, because if ndo_hwtstamp_get() is
resolved through a legacy ndo_eth_ioctl(SIOCGHWTSTAMP) lower_dev
implementation, that needs a non-NULL old_cfg.ifr pointer, and we don't
have it.

But we don't even need to deal with it either. In the general case,
drivers may not even implement SIOCGHWTSTAMP handling, only SIOCSHWTSTAMP,
so it makes sense to completely avoid a SIOCGHWTSTAMP call if we can.

The solution is to split the single "if" condition into 3 smaller ones,
thus separating the decision to call ndo_hwtstamp_get() from the
decision to call ndo_hwtstamp_set(). The third "if" condition is
identical to the first one, and both are subsets of the second one.
Thus, the "cfg" argument of kernel_hwtstamp_config_changed() is always
valid.

Reported-by: Eric Dumazet <edumazet@google.com>
Closes: https://lore.kernel.org/netdev/CANn89iLOspJsvjPj+y8jikg7erXDomWe8sqHMdfL_2LQSFrPAg@mail.gmail.com/
Fixes: fd770e856e22 ("net: remove phy_has_hwtstamp() -> phy_mii_ioctl() decision from converted drivers")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev_ioctl.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 72e0770223483..b46aedc36939a 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -334,20 +334,23 @@ static int dev_set_hwtstamp_phylib(struct net_device *dev,
 
 	cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV;
 
-	if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
+	if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
 		err = ops->ndo_hwtstamp_get(dev, &old_cfg);
 		if (err)
 			return err;
+	}
 
+	if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
 		err = ops->ndo_hwtstamp_set(dev, cfg, extack);
 		if (err) {
 			if (extack->_msg)
 				netdev_err(dev, "%s\n", extack->_msg);
 			return err;
 		}
+	}
 
+	if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS))
 		changed = kernel_hwtstamp_config_changed(&old_cfg, cfg);
-	}
 
 	if (phy_ts) {
 		err = phy_hwtstamp_set(dev->phydev, cfg, extack);
-- 
GitLab


From 84059a0ef5c6bea71b4f8f87de61d6218c4ddc9c Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 7 Aug 2023 09:28:50 +0200
Subject: [PATCH 0919/1806] Revert "riscv: dts: allwinner: d1: Add CAN
 controller nodes"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turned out the dtsi changes were not quite ready, revert them for
now.

This reverts commit 6ea1ad888f5900953a21853e709fa499fdfcb317.

Link: https://lore.kernel.org/all/2690764.mvXUDI8C0e@jernej-laptop
Suggested-by: Jernej Škrabec <jernej.skrabec@gmail.com>
Link: https://lore.kernel.org/all/20230807-riscv-allwinner-d1-revert-can-controller-nodes-v1-1-eb3f70b435d9@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../boot/dts/allwinner/sunxi-d1s-t113.dtsi    | 30 -------------------
 1 file changed, 30 deletions(-)

diff --git a/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi b/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi
index 4086c0cc0f9da..1bb1e5cae6021 100644
--- a/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi
+++ b/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi
@@ -131,18 +131,6 @@
 				pins = "PB6", "PB7";
 				function = "uart3";
 			};
-
-			/omit-if-no-ref/
-			can0_pins: can0-pins {
-				pins = "PB2", "PB3";
-				function = "can0";
-			};
-
-			/omit-if-no-ref/
-			can1_pins: can1-pins {
-				pins = "PB4", "PB5";
-				function = "can1";
-			};
 		};
 
 		ccu: clock-controller@2001000 {
@@ -891,23 +879,5 @@
 			clock-names = "bus", "hosc", "ahb";
 			#clock-cells = <1>;
 		};
-
-		can0: can@2504000 {
-			compatible = "allwinner,sun20i-d1-can";
-			reg = <0x02504000 0x400>;
-			interrupts = <SOC_PERIPHERAL_IRQ(21) IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&ccu CLK_BUS_CAN0>;
-			resets = <&ccu RST_BUS_CAN0>;
-			status = "disabled";
-		};
-
-		can1: can@2504400 {
-			compatible = "allwinner,sun20i-d1-can";
-			reg = <0x02504400 0x400>;
-			interrupts = <SOC_PERIPHERAL_IRQ(22) IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&ccu CLK_BUS_CAN1>;
-			resets = <&ccu RST_BUS_CAN1>;
-			status = "disabled";
-		};
 	};
 };
-- 
GitLab


From f6ecb68b38a5c23f20160dd49718d1a9d395a86d Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 5 Aug 2023 18:48:11 +0800
Subject: [PATCH 0920/1806] net/tls: Remove unused function declarations

Commit 3c4d7559159b ("tls: kernel TLS support") declared but never implemented
these functions.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/tls/tls.h b/net/tls/tls.h
index 37539ac3ac2ac..164d6a955e26a 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -87,10 +87,6 @@ void tls_ctx_free(struct sock *sk, struct tls_context *ctx);
 void update_sk_prot(struct sock *sk, struct tls_context *ctx);
 
 int wait_on_pending_writer(struct sock *sk, long *timeo);
-int tls_sk_query(struct sock *sk, int optname, char __user *optval,
-		 int __user *optlen);
-int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
-		  unsigned int optlen);
 void tls_err_abort(struct sock *sk, int err);
 
 int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
-- 
GitLab


From 047551cd305ce2f51f8cf16ed5638f1e120f90af Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 5 Aug 2023 18:50:33 +0800
Subject: [PATCH 0921/1806] neighbour: Remove unused function declaration
 pneigh_for_each()

pneigh_for_each() is never implemented since the beginning of git history.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index f6a8ecc6b1fa7..6da68886fabbc 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -394,8 +394,6 @@ void neigh_for_each(struct neigh_table *tbl,
 void __neigh_for_each_release(struct neigh_table *tbl,
 			      int (*cb)(struct neighbour *));
 int neigh_xmit(int fam, struct net_device *, const void *, struct sk_buff *);
-void pneigh_for_each(struct neigh_table *tbl,
-		     void (*cb)(struct pneigh_entry *));
 
 struct neigh_seq_state {
 	struct seq_net_private p;
-- 
GitLab


From 992b47851be9125c1de480c8f34cc0ea7eb58daf Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 5 Aug 2023 18:52:08 +0800
Subject: [PATCH 0922/1806] net: pkt_cls: Remove unused inline helpers

Commit acb674428c3d ("net: sched: introduce per-block callbacks")
implemented these but never used it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 139cd09828af2..f308e8268651e 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -138,19 +138,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 	return NULL;
 }
 
-static inline
-int tc_setup_cb_block_register(struct tcf_block *block, flow_setup_cb_t *cb,
-			       void *cb_priv)
-{
-	return 0;
-}
-
-static inline
-void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb,
-				  void *cb_priv)
-{
-}
-
 static inline int tcf_classify(struct sk_buff *skb,
 			       const struct tcf_block *block,
 			       const struct tcf_proto *tp,
-- 
GitLab


From 2c6af36beb2e7e0066a74bc930e562f66ad88bb6 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 5 Aug 2023 18:53:54 +0800
Subject: [PATCH 0923/1806] ndisc: Remove unused ndisc_ifinfo_sysctl_strategy()
 declaration

Commit f8572d8f2a2b ("sysctl net: Remove unused binary sysctl code")
left behind this declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ndisc.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 52eae09434335..9bbdf6eaa942c 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -488,9 +488,6 @@ void igmp6_event_report(struct sk_buff *skb);
 #ifdef CONFIG_SYSCTL
 int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write,
 			       void *buffer, size_t *lenp, loff_t *ppos);
-int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl,
-				 void __user *oldval, size_t __user *oldlenp,
-				 void __user *newval, size_t newlen);
 #endif
 
 void inet6_ifinfo_notify(int event, struct inet6_dev *idev);
-- 
GitLab


From a6ab5c29b8d2039db885e26058ed8f8853e383ab Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 5 Aug 2023 18:57:40 +0800
Subject: [PATCH 0924/1806] net: sfp: Remove unused function declaration
 sfp_link_configure()

Commit ce0aa27ff3f6 ("sfp: add sfp-bus to bridge between network devices and sfp cages")
declared but never implemented it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/phy/sfp.h b/drivers/net/phy/sfp.h
index c7cb50d100999..1fd097dccb9fc 100644
--- a/drivers/net/phy/sfp.h
+++ b/drivers/net/phy/sfp.h
@@ -37,7 +37,6 @@ int sfp_module_insert(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 void sfp_module_remove(struct sfp_bus *bus);
 int sfp_module_start(struct sfp_bus *bus);
 void sfp_module_stop(struct sfp_bus *bus);
-int sfp_link_configure(struct sfp_bus *bus, const struct sfp_eeprom_id *id);
 struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp,
 				    const struct sfp_socket_ops *ops);
 void sfp_unregister_socket(struct sfp_bus *bus);
-- 
GitLab


From cc97777c80fdfabe12997581131872a03fdcf683 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 5 Aug 2023 19:00:09 +0800
Subject: [PATCH 0925/1806] udp/udplite: Remove unused function declarations
 udp{,lite}_get_port()

Commit 6ba5a3c52da0 ("[UDP]: Make full use of proto.h.udp_hash innovation.")
removed these implementations but leave declarations.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h     | 3 ---
 include/net/udplite.h | 2 --
 2 files changed, 5 deletions(-)

diff --git a/include/net/udp.h b/include/net/udp.h
index 5a8421cd90836..488a6d2babccf 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -273,9 +273,6 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
 
 int udp_v4_early_demux(struct sk_buff *skb);
 bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
-int udp_get_port(struct sock *sk, unsigned short snum,
-		 int (*saddr_cmp)(const struct sock *,
-				  const struct sock *));
 int udp_err(struct sk_buff *, u32);
 int udp_abort(struct sock *sk, int err);
 int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
diff --git a/include/net/udplite.h b/include/net/udplite.h
index 299c14ce2bb94..bd33ff2b8f426 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -81,6 +81,4 @@ static inline __wsum udplite_csum(struct sk_buff *skb)
 }
 
 void udplite4_register(void);
-int udplite_get_port(struct sock *sk, unsigned short snum,
-		     int (*scmp)(const struct sock *, const struct sock *));
 #endif	/* _UDPLITE_H */
-- 
GitLab


From 18cf3d31f8292e3994ec972097419f1c23e0d2ff Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Fri, 9 Jun 2023 15:44:18 +0300
Subject: [PATCH 0926/1806] net/mlx5: Track the current number of completion
 EQs

In preparation to allocate completion EQs, add a counter to track the
number of completion EQs currently allocated. Store the maximum number
of EQs in max_comp_eqs variable.

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 24 ++++++++++++--------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 3db4866d7880f..66257f7879b76 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -58,7 +58,8 @@ struct mlx5_eq_table {
 	struct mlx5_nb          cq_err_nb;
 
 	struct mutex            lock; /* sync async eqs creations */
-	int			num_comp_eqs;
+	int			curr_comp_eqs;
+	int			max_comp_eqs;
 	struct mlx5_irq_table	*irq_table;
 	struct mlx5_irq         **comp_irqs;
 	struct mlx5_irq         *ctrl_irq;
@@ -452,6 +453,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 		ATOMIC_INIT_NOTIFIER_HEAD(&eq_table->nh[i]);
 
 	eq_table->irq_table = mlx5_irq_table_get(dev);
+	eq_table->curr_comp_eqs = 0;
 	return 0;
 }
 
@@ -807,7 +809,7 @@ static void comp_irqs_release_pci(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 
-	mlx5_irqs_release_vectors(table->comp_irqs, table->num_comp_eqs);
+	mlx5_irqs_release_vectors(table->comp_irqs, table->max_comp_eqs);
 }
 
 static int comp_irqs_request_pci(struct mlx5_core_dev *dev)
@@ -821,7 +823,7 @@ static int comp_irqs_request_pci(struct mlx5_core_dev *dev)
 	int cpu;
 	int i;
 
-	ncomp_eqs = table->num_comp_eqs;
+	ncomp_eqs = table->max_comp_eqs;
 	cpus = kcalloc(ncomp_eqs, sizeof(*cpus), GFP_KERNEL);
 	if (!cpus)
 		return -ENOMEM;
@@ -847,13 +849,13 @@ static void comp_irqs_release_sf(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 
-	mlx5_irq_affinity_irqs_release(dev, table->comp_irqs, table->num_comp_eqs);
+	mlx5_irq_affinity_irqs_release(dev, table->comp_irqs, table->max_comp_eqs);
 }
 
 static int comp_irqs_request_sf(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	int ncomp_eqs = table->num_comp_eqs;
+	int ncomp_eqs = table->max_comp_eqs;
 
 	return mlx5_irq_affinity_irqs_request_auto(dev, ncomp_eqs, table->comp_irqs);
 }
@@ -874,7 +876,7 @@ static int comp_irqs_request(struct mlx5_core_dev *dev)
 	int ncomp_eqs;
 	int ret;
 
-	ncomp_eqs = table->num_comp_eqs;
+	ncomp_eqs = table->max_comp_eqs;
 	table->comp_irqs = kcalloc(ncomp_eqs, sizeof(*table->comp_irqs), GFP_KERNEL);
 	if (!table->comp_irqs)
 		return -ENOMEM;
@@ -901,7 +903,7 @@ static int alloc_rmap(struct mlx5_core_dev *mdev)
 	if (mlx5_core_is_sf(mdev))
 		return 0;
 
-	eq_table->rmap = alloc_irq_cpu_rmap(eq_table->num_comp_eqs);
+	eq_table->rmap = alloc_irq_cpu_rmap(eq_table->max_comp_eqs);
 	if (!eq_table->rmap)
 		return -ENOMEM;
 	return 0;
@@ -934,6 +936,7 @@ static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 				       eq->core.eqn);
 		tasklet_disable(&eq->tasklet_ctx.task);
 		kfree(eq);
+		table->curr_comp_eqs--;
 	}
 	comp_irqs_release(dev);
 	free_rmap(dev);
@@ -973,6 +976,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 		goto err_irqs_req;
 	}
 
+	table->max_comp_eqs = ncomp_eqs;
 	INIT_LIST_HEAD(&table->comp_eqs_list);
 	nent = comp_eq_depth_devlink_param_get(dev);
 
@@ -1008,9 +1012,9 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn);
 		/* add tail, to keep the list ordered, for mlx5_vector2eqn to work */
 		list_add_tail(&eq->list, &table->comp_eqs_list);
+		table->curr_comp_eqs++;
 	}
 
-	table->num_comp_eqs = ncomp_eqs;
 	return 0;
 
 clean_eq:
@@ -1057,7 +1061,7 @@ int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn)
 
 unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev)
 {
-	return dev->priv.eq_table->num_comp_eqs;
+	return dev->priv.eq_table->max_comp_eqs;
 }
 EXPORT_SYMBOL(mlx5_comp_vectors_count);
 
@@ -1148,7 +1152,7 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	int err;
 
-	eq_table->num_comp_eqs = get_num_eqs(dev);
+	eq_table->max_comp_eqs = get_num_eqs(dev);
 	err = create_async_eqs(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to create async EQs\n");
-- 
GitLab


From a1772de78d7303e33517d1741e0fce1c7247bec4 Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Sun, 11 Jun 2023 14:35:36 +0300
Subject: [PATCH 0927/1806] net/mlx5: Refactor completion IRQ request/release
 API

Introduce a per-vector completion IRQ request API that requests a
single IRQ for a given vector index instead of multiple IRQs request API.
On driver load, loop over all completion vectors and request an IRQ for
each one via the newly introduced API.

Symmetrically, introduce an IRQ release API per vector. On driver
unload, loop over all vectors and release each completion IRQ via
the new per-vector API.

As IRQ vectors will be requested dynamically later in the patchset,
add a cpumask of the bounded CPUs to avoid the possible mapping of
two IRQs of the same device to the same cpu.

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c  | 36 ++++++--
 .../mellanox/mlx5/core/irq_affinity.c         | 82 +++++++++----------
 .../ethernet/mellanox/mlx5/core/mlx5_irq.h    | 26 +++---
 .../net/ethernet/mellanox/mlx5/core/pci_irq.c | 60 +++++---------
 4 files changed, 101 insertions(+), 103 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 66257f7879b76..268fd61ae8c0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -64,6 +64,7 @@ struct mlx5_eq_table {
 	struct mlx5_irq         **comp_irqs;
 	struct mlx5_irq         *ctrl_irq;
 	struct cpu_rmap		*rmap;
+	struct cpumask          used_cpus;
 };
 
 #define MLX5_ASYNC_EVENT_MASK ((1ull << MLX5_EVENT_TYPE_PATH_MIG)	    | \
@@ -453,6 +454,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 		ATOMIC_INIT_NOTIFIER_HEAD(&eq_table->nh[i]);
 
 	eq_table->irq_table = mlx5_irq_table_get(dev);
+	cpumask_clear(&eq_table->used_cpus);
 	eq_table->curr_comp_eqs = 0;
 	return 0;
 }
@@ -808,8 +810,10 @@ EXPORT_SYMBOL(mlx5_eq_update_ci);
 static void comp_irqs_release_pci(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
+	int i;
 
-	mlx5_irqs_release_vectors(table->comp_irqs, table->max_comp_eqs);
+	for (i = 0; i < table->max_comp_eqs; i++)
+		mlx5_irq_release_vector(table->comp_irqs[i]);
 }
 
 static int comp_irqs_request_pci(struct mlx5_core_dev *dev)
@@ -817,9 +821,9 @@ static int comp_irqs_request_pci(struct mlx5_core_dev *dev)
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	const struct cpumask *prev = cpu_none_mask;
 	const struct cpumask *mask;
+	struct mlx5_irq *irq;
 	int ncomp_eqs;
 	u16 *cpus;
-	int ret;
 	int cpu;
 	int i;
 
@@ -840,24 +844,42 @@ static int comp_irqs_request_pci(struct mlx5_core_dev *dev)
 	}
 spread_done:
 	rcu_read_unlock();
-	ret = mlx5_irqs_request_vectors(dev, cpus, ncomp_eqs, table->comp_irqs, &table->rmap);
+	for (i = 0; i < ncomp_eqs; i++) {
+		irq = mlx5_irq_request_vector(dev, cpus[i], i, &table->rmap);
+		if (IS_ERR(irq))
+			break;
+
+		table->comp_irqs[i] = irq;
+	}
+
 	kfree(cpus);
-	return ret;
+	return i ? i : PTR_ERR(irq);
 }
 
 static void comp_irqs_release_sf(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
+	int i;
 
-	mlx5_irq_affinity_irqs_release(dev, table->comp_irqs, table->max_comp_eqs);
+	for (i = 0; i < table->max_comp_eqs; i++)
+		mlx5_irq_affinity_irq_release(dev, table->comp_irqs[i]);
 }
 
 static int comp_irqs_request_sf(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	int ncomp_eqs = table->max_comp_eqs;
+	struct mlx5_irq *irq;
+	int i;
+
+	for (i = 0; i < table->max_comp_eqs; i++) {
+		irq = mlx5_irq_affinity_irq_request_auto(dev, &table->used_cpus, i);
+		if (IS_ERR(irq))
+			break;
+
+		table->comp_irqs[i] = irq;
+	}
 
-	return mlx5_irq_affinity_irqs_request_auto(dev, ncomp_eqs, table->comp_irqs);
+	return i ? i : PTR_ERR(irq);
 }
 
 static void comp_irqs_release(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index fa467335526e7..ed51800f9f672 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -156,67 +156,61 @@ unlock:
 	return least_loaded_irq;
 }
 
-void mlx5_irq_affinity_irqs_release(struct mlx5_core_dev *dev, struct mlx5_irq **irqs,
-				    int num_irqs)
+void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *irq)
 {
 	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
-	int i;
-
-	for (i = 0; i < num_irqs; i++) {
-		int cpu = cpumask_first(mlx5_irq_get_affinity_mask(irqs[i]));
+	int cpu;
 
-		synchronize_irq(pci_irq_vector(pool->dev->pdev,
-					       mlx5_irq_get_index(irqs[i])));
-		if (mlx5_irq_put(irqs[i]))
-			if (pool->irqs_per_cpu)
-				cpu_put(pool, cpu);
-	}
+	cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq));
+	synchronize_irq(pci_irq_vector(pool->dev->pdev,
+				       mlx5_irq_get_index(irq)));
+	if (mlx5_irq_put(irq))
+		if (pool->irqs_per_cpu)
+			cpu_put(pool, cpu);
 }
 
 /**
- * mlx5_irq_affinity_irqs_request_auto - request one or more IRQs for mlx5 device.
- * @dev: mlx5 device that is requesting the IRQs.
- * @nirqs: number of IRQs to request.
- * @irqs: an output array of IRQs pointers.
+ * mlx5_irq_affinity_irq_request_auto - request one IRQ for mlx5 device.
+ * @dev: mlx5 device that is requesting the IRQ.
+ * @used_cpus: cpumask of bounded cpus by the device
+ * @vecidx: vector index to request an IRQ for.
  *
  * Each IRQ is bounded to at most 1 CPU.
- * This function is requesting IRQs according to the default assignment.
+ * This function is requesting an IRQ according to the default assignment.
  * The default assignment policy is:
- * - in each iteration, request the least loaded IRQ which is not bound to any
+ * - request the least loaded IRQ which is not bound to any
  *   CPU of the previous IRQs requested.
  *
- * This function returns the number of IRQs requested, (which might be smaller than
- * @nirqs), if successful, or a negative error code in case of an error.
+ * On success, this function updates used_cpus mask and returns an irq pointer.
+ * In case of an error, an appropriate error pointer is returned.
  */
-int mlx5_irq_affinity_irqs_request_auto(struct mlx5_core_dev *dev, int nirqs,
-					struct mlx5_irq **irqs)
+struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
+						    struct cpumask *used_cpus, u16 vecidx)
 {
 	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
 	struct irq_affinity_desc af_desc = {};
 	struct mlx5_irq *irq;
-	int i = 0;
 
 	af_desc.is_managed = 1;
 	cpumask_copy(&af_desc.mask, cpu_online_mask);
-	for (i = 0; i < nirqs; i++) {
-		if (mlx5_irq_pool_is_sf_pool(pool))
-			irq = mlx5_irq_affinity_request(pool, &af_desc);
-		else
-			/* In case SF pool doesn't exists, fallback to the PF IRQs.
-			 * The PF IRQs are already allocated and binded to CPU
-			 * at this point. Hence, only an index is needed.
-			 */
-			irq = mlx5_irq_request(dev, i, NULL, NULL);
-		if (IS_ERR(irq))
-			break;
-		irqs[i] = irq;
-		cpumask_clear_cpu(cpumask_first(mlx5_irq_get_affinity_mask(irq)), &af_desc.mask);
-		mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n",
-			      pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)),
-			      cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)),
-			      mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ);
-	}
-	if (!i)
-		return PTR_ERR(irq);
-	return i;
+	cpumask_andnot(&af_desc.mask, &af_desc.mask, used_cpus);
+	if (mlx5_irq_pool_is_sf_pool(pool))
+		irq = mlx5_irq_affinity_request(pool, &af_desc);
+	else
+		/* In case SF pool doesn't exists, fallback to the PF IRQs.
+		 * The PF IRQs are already allocated and binded to CPU
+		 * at this point. Hence, only an index is needed.
+		 */
+		irq = mlx5_irq_request(dev, vecidx, NULL, NULL);
+
+	if (IS_ERR(irq))
+		return irq;
+
+	cpumask_or(used_cpus, used_cpus, mlx5_irq_get_affinity_mask(irq));
+	mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n",
+		      pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)),
+		      cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)),
+		      mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ);
+
+	return irq;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
index aa403a5ea34ed..1088114e905d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
@@ -29,9 +29,9 @@ void mlx5_ctrl_irq_release(struct mlx5_irq *ctrl_irq);
 struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx,
 				  struct irq_affinity_desc *af_desc,
 				  struct cpu_rmap **rmap);
-int mlx5_irqs_request_vectors(struct mlx5_core_dev *dev, u16 *cpus, int nirqs,
-			      struct mlx5_irq **irqs, struct cpu_rmap **rmap);
-void mlx5_irqs_release_vectors(struct mlx5_irq **irqs, int nirqs);
+struct mlx5_irq *mlx5_irq_request_vector(struct mlx5_core_dev *dev, u16 cpu,
+					 u16 vecidx, struct cpu_rmap **rmap);
+void mlx5_irq_release_vector(struct mlx5_irq *irq);
 int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb);
 int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb);
 struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq);
@@ -39,17 +39,17 @@ int mlx5_irq_get_index(struct mlx5_irq *irq);
 
 struct mlx5_irq_pool;
 #ifdef CONFIG_MLX5_SF
-int mlx5_irq_affinity_irqs_request_auto(struct mlx5_core_dev *dev, int nirqs,
-					struct mlx5_irq **irqs);
+struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
+						    struct cpumask *used_cpus, u16 vecidx);
 struct mlx5_irq *mlx5_irq_affinity_request(struct mlx5_irq_pool *pool,
 					   struct irq_affinity_desc *af_desc);
-void mlx5_irq_affinity_irqs_release(struct mlx5_core_dev *dev, struct mlx5_irq **irqs,
-				    int num_irqs);
+void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *irq);
 #else
-static inline int mlx5_irq_affinity_irqs_request_auto(struct mlx5_core_dev *dev, int nirqs,
-						      struct mlx5_irq **irqs)
+static inline
+struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
+						    struct cpumask *used_cpus, u16 vecidx)
 {
-	return -EOPNOTSUPP;
+	return ERR_PTR(-EOPNOTSUPP);
 }
 
 static inline struct mlx5_irq *
@@ -58,7 +58,9 @@ mlx5_irq_affinity_request(struct mlx5_irq_pool *pool, struct irq_affinity_desc *
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
-static inline void mlx5_irq_affinity_irqs_release(struct mlx5_core_dev *dev,
-						  struct mlx5_irq **irqs, int num_irqs) {}
+static inline
+void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *irq)
+{
+}
 #endif
 #endif /* __MLX5_IRQ_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index cba2a4afb5fda..33a133c9918cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -432,19 +432,10 @@ static struct mlx5_irq_pool *ctrl_irq_pool_get(struct mlx5_core_dev *dev)
 	return pool ? pool : irq_table->pcif_pool;
 }
 
-/**
- * mlx5_irqs_release - release one or more IRQs back to the system.
- * @irqs: IRQs to be released.
- * @nirqs: number of IRQs to be released.
- */
-static void mlx5_irqs_release(struct mlx5_irq **irqs, int nirqs)
+static void _mlx5_irq_release(struct mlx5_irq *irq)
 {
-	int i;
-
-	for (i = 0; i < nirqs; i++) {
-		synchronize_irq(irqs[i]->map.virq);
-		mlx5_irq_put(irqs[i]);
-	}
+	synchronize_irq(irq->map.virq);
+	mlx5_irq_put(irq);
 }
 
 /**
@@ -453,7 +444,7 @@ static void mlx5_irqs_release(struct mlx5_irq **irqs, int nirqs)
  */
 void mlx5_ctrl_irq_release(struct mlx5_irq *ctrl_irq)
 {
-	mlx5_irqs_release(&ctrl_irq, 1);
+	_mlx5_irq_release(ctrl_irq);
 }
 
 /**
@@ -569,53 +560,42 @@ void mlx5_msix_free(struct mlx5_core_dev *dev, struct msi_map map)
 EXPORT_SYMBOL(mlx5_msix_free);
 
 /**
- * mlx5_irqs_release_vectors - release one or more IRQs back to the system.
- * @irqs: IRQs to be released.
- * @nirqs: number of IRQs to be released.
+ * mlx5_irq_release_vector - release one IRQ back to the system.
+ * @irq: the irq to release.
  */
-void mlx5_irqs_release_vectors(struct mlx5_irq **irqs, int nirqs)
+void mlx5_irq_release_vector(struct mlx5_irq *irq)
 {
-	mlx5_irqs_release(irqs, nirqs);
+	_mlx5_irq_release(irq);
 }
 
 /**
- * mlx5_irqs_request_vectors - request one or more IRQs for mlx5 device.
- * @dev: mlx5 device that is requesting the IRQs.
- * @cpus: CPUs array for binding the IRQs
- * @nirqs: number of IRQs to request.
- * @irqs: an output array of IRQs pointers.
+ * mlx5_irq_request_vector - request one IRQ for mlx5 device.
+ * @dev: mlx5 device that is requesting the IRQ.
+ * @cpu: CPU to bind the IRQ to.
+ * @vecidx: vector index to request an IRQ for.
  * @rmap: pointer to reverse map pointer for completion interrupts
  *
  * Each IRQ is bound to at most 1 CPU.
- * This function is requests nirqs IRQs, starting from @vecidx.
+ * This function is requests one IRQ, for the given @vecidx.
  *
- * This function returns the number of IRQs requested, (which might be smaller than
- * @nirqs), if successful, or a negative error code in case of an error.
+ * This function returns a pointer to the irq on success, or an error pointer
+ * in case of an error.
  */
-int mlx5_irqs_request_vectors(struct mlx5_core_dev *dev, u16 *cpus, int nirqs,
-			      struct mlx5_irq **irqs, struct cpu_rmap **rmap)
+struct mlx5_irq *mlx5_irq_request_vector(struct mlx5_core_dev *dev, u16 cpu,
+					 u16 vecidx, struct cpu_rmap **rmap)
 {
 	struct mlx5_irq_table *table = mlx5_irq_table_get(dev);
 	struct mlx5_irq_pool *pool = table->pcif_pool;
 	struct irq_affinity_desc af_desc;
-	struct mlx5_irq *irq;
 	int offset = 1;
-	int i;
 
 	if (!pool->xa_num_irqs.max)
 		offset = 0;
 
 	af_desc.is_managed = false;
-	for (i = 0; i < nirqs; i++) {
-		cpumask_clear(&af_desc.mask);
-		cpumask_set_cpu(cpus[i], &af_desc.mask);
-		irq = mlx5_irq_request(dev, i + offset, &af_desc, rmap);
-		if (IS_ERR(irq))
-			break;
-		irqs[i] = irq;
-	}
-
-	return i ? i : PTR_ERR(irq);
+	cpumask_clear(&af_desc.mask);
+	cpumask_set_cpu(cpu, &af_desc.mask);
+	return mlx5_irq_request(dev, vecidx + offset, &af_desc, rmap);
 }
 
 static struct mlx5_irq_pool *
-- 
GitLab


From c8a0245c3937d302a52c9d6b54de44b302e78265 Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Sun, 18 Jun 2023 19:23:24 +0300
Subject: [PATCH 0928/1806] net/mlx5: Use xarray to store and manage completion
 IRQs

Use xarray to store the completion IRQs instead of a fixed-size allocated
array as not all completion IRQs will be requested on driver load, but
rather on demand when an EQ is created. The xarray offers more scalability,
reduced memory overhead, and provides the ability to dynamically resize the
array when needed.

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 61 ++++++++++----------
 1 file changed, 29 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 268fd61ae8c0e..ac22d4d6b94b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -61,7 +61,7 @@ struct mlx5_eq_table {
 	int			curr_comp_eqs;
 	int			max_comp_eqs;
 	struct mlx5_irq_table	*irq_table;
-	struct mlx5_irq         **comp_irqs;
+	struct xarray           comp_irqs;
 	struct mlx5_irq         *ctrl_irq;
 	struct cpu_rmap		*rmap;
 	struct cpumask          used_cpus;
@@ -455,14 +455,18 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 
 	eq_table->irq_table = mlx5_irq_table_get(dev);
 	cpumask_clear(&eq_table->used_cpus);
+	xa_init(&eq_table->comp_irqs);
 	eq_table->curr_comp_eqs = 0;
 	return 0;
 }
 
 void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev)
 {
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+
 	mlx5_eq_debugfs_cleanup(dev);
-	kvfree(dev->priv.eq_table);
+	xa_destroy(&table->comp_irqs);
+	kvfree(table);
 }
 
 /* Async EQs */
@@ -810,10 +814,13 @@ EXPORT_SYMBOL(mlx5_eq_update_ci);
 static void comp_irqs_release_pci(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	int i;
+	struct mlx5_irq *irq;
+	unsigned long index;
 
-	for (i = 0; i < table->max_comp_eqs; i++)
-		mlx5_irq_release_vector(table->comp_irqs[i]);
+	xa_for_each(&table->comp_irqs, index, irq) {
+		xa_erase(&table->comp_irqs, index);
+		mlx5_irq_release_vector(irq);
+	}
 }
 
 static int comp_irqs_request_pci(struct mlx5_core_dev *dev)
@@ -849,7 +856,8 @@ spread_done:
 		if (IS_ERR(irq))
 			break;
 
-		table->comp_irqs[i] = irq;
+		if (xa_err(xa_store(&table->comp_irqs, i, irq, GFP_KERNEL)))
+			break;
 	}
 
 	kfree(cpus);
@@ -859,10 +867,13 @@ spread_done:
 static void comp_irqs_release_sf(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	int i;
+	struct mlx5_irq *irq;
+	unsigned long index;
 
-	for (i = 0; i < table->max_comp_eqs; i++)
-		mlx5_irq_affinity_irq_release(dev, table->comp_irqs[i]);
+	xa_for_each(&table->comp_irqs, index, irq) {
+		xa_erase(&table->comp_irqs, index);
+		mlx5_irq_affinity_irq_release(dev, irq);
+	}
 }
 
 static int comp_irqs_request_sf(struct mlx5_core_dev *dev)
@@ -876,7 +887,8 @@ static int comp_irqs_request_sf(struct mlx5_core_dev *dev)
 		if (IS_ERR(irq))
 			break;
 
-		table->comp_irqs[i] = irq;
+		if (xa_err(xa_store(&table->comp_irqs, i, irq, GFP_KERNEL)))
+			break;
 	}
 
 	return i ? i : PTR_ERR(irq);
@@ -884,31 +896,14 @@ static int comp_irqs_request_sf(struct mlx5_core_dev *dev)
 
 static void comp_irqs_release(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = dev->priv.eq_table;
-
 	mlx5_core_is_sf(dev) ? comp_irqs_release_sf(dev) :
 			       comp_irqs_release_pci(dev);
-
-	kfree(table->comp_irqs);
 }
 
 static int comp_irqs_request(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = dev->priv.eq_table;
-	int ncomp_eqs;
-	int ret;
-
-	ncomp_eqs = table->max_comp_eqs;
-	table->comp_irqs = kcalloc(ncomp_eqs, sizeof(*table->comp_irqs), GFP_KERNEL);
-	if (!table->comp_irqs)
-		return -ENOMEM;
-
-	ret = mlx5_core_is_sf(dev) ? comp_irqs_request_sf(dev) :
-				     comp_irqs_request_pci(dev);
-	if (ret < 0)
-		kfree(table->comp_irqs);
-
-	return ret;
+	return mlx5_core_is_sf(dev) ? comp_irqs_request_sf(dev) :
+				      comp_irqs_request_pci(dev);
 }
 
 #ifdef CONFIG_RFS_ACCEL
@@ -983,10 +978,11 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq_comp *eq;
+	struct mlx5_irq *irq;
+	unsigned long index;
 	int ncomp_eqs;
 	int nent;
 	int err;
-	int i;
 
 	err = alloc_rmap(dev);
 	if (err)
@@ -1002,7 +998,8 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 	INIT_LIST_HEAD(&table->comp_eqs_list);
 	nent = comp_eq_depth_devlink_param_get(dev);
 
-	for (i = 0; i < ncomp_eqs; i++) {
+	xa_for_each(&table->comp_irqs, index, irq)
+	{
 		struct mlx5_eq_param param = {};
 
 		eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, dev->priv.numa_node);
@@ -1018,7 +1015,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 
 		eq->irq_nb.notifier_call = mlx5_eq_comp_int;
 		param = (struct mlx5_eq_param) {
-			.irq = table->comp_irqs[i],
+			.irq = irq,
 			.nent = nent,
 		};
 
-- 
GitLab


From 54b2cf41b853e04ea09a2a075e4a6dc30638c298 Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Mon, 12 Jun 2023 15:34:27 +0300
Subject: [PATCH 0929/1806] net/mlx5: Refactor completion IRQ request/release
 handlers in EQ layer

Break the completion IRQ request/release functions into per-vector
handlers for both PCI devices and SFs in the EQ layer.

On EQ table creation, loop over all vectors and request an IRQ for each
one using the new per-vector functions. Perform the symmetrical change
when releasing IRQs on EQ table cleanup.

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 109 +++++++++----------
 1 file changed, 51 insertions(+), 58 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ac22d4d6b94b2..c01a5d8dbe9bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -811,99 +811,84 @@ void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm)
 }
 EXPORT_SYMBOL(mlx5_eq_update_ci);
 
-static void comp_irqs_release_pci(struct mlx5_core_dev *dev)
+static void comp_irq_release_pci(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_irq *irq;
-	unsigned long index;
 
-	xa_for_each(&table->comp_irqs, index, irq) {
-		xa_erase(&table->comp_irqs, index);
-		mlx5_irq_release_vector(irq);
-	}
+	irq = xa_load(&table->comp_irqs, vecidx);
+	if (!irq)
+		return;
+
+	xa_erase(&table->comp_irqs, vecidx);
+	mlx5_irq_release_vector(irq);
 }
 
-static int comp_irqs_request_pci(struct mlx5_core_dev *dev)
+static int comp_irq_request_pci(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	const struct cpumask *prev = cpu_none_mask;
 	const struct cpumask *mask;
 	struct mlx5_irq *irq;
-	int ncomp_eqs;
-	u16 *cpus;
+	int found_cpu = 0;
+	int i = 0;
 	int cpu;
-	int i;
-
-	ncomp_eqs = table->max_comp_eqs;
-	cpus = kcalloc(ncomp_eqs, sizeof(*cpus), GFP_KERNEL);
-	if (!cpus)
-		return -ENOMEM;
 
-	i = 0;
 	rcu_read_lock();
 	for_each_numa_hop_mask(mask, dev->priv.numa_node) {
 		for_each_cpu_andnot(cpu, mask, prev) {
-			cpus[i] = cpu;
-			if (++i == ncomp_eqs)
+			if (i++ == vecidx) {
+				found_cpu = cpu;
 				goto spread_done;
+			}
 		}
 		prev = mask;
 	}
+
 spread_done:
 	rcu_read_unlock();
-	for (i = 0; i < ncomp_eqs; i++) {
-		irq = mlx5_irq_request_vector(dev, cpus[i], i, &table->rmap);
-		if (IS_ERR(irq))
-			break;
-
-		if (xa_err(xa_store(&table->comp_irqs, i, irq, GFP_KERNEL)))
-			break;
-	}
+	irq = mlx5_irq_request_vector(dev, found_cpu, vecidx, &table->rmap);
+	if (IS_ERR(irq))
+		return PTR_ERR(irq);
 
-	kfree(cpus);
-	return i ? i : PTR_ERR(irq);
+	return xa_err(xa_store(&table->comp_irqs, vecidx, irq, GFP_KERNEL));
 }
 
-static void comp_irqs_release_sf(struct mlx5_core_dev *dev)
+static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_irq *irq;
-	unsigned long index;
 
-	xa_for_each(&table->comp_irqs, index, irq) {
-		xa_erase(&table->comp_irqs, index);
-		mlx5_irq_affinity_irq_release(dev, irq);
-	}
+	irq = xa_load(&table->comp_irqs, vecidx);
+	if (!irq)
+		return;
+
+	xa_erase(&table->comp_irqs, vecidx);
+	mlx5_irq_affinity_irq_release(dev, irq);
 }
 
-static int comp_irqs_request_sf(struct mlx5_core_dev *dev)
+static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_irq *irq;
-	int i;
-
-	for (i = 0; i < table->max_comp_eqs; i++) {
-		irq = mlx5_irq_affinity_irq_request_auto(dev, &table->used_cpus, i);
-		if (IS_ERR(irq))
-			break;
 
-		if (xa_err(xa_store(&table->comp_irqs, i, irq, GFP_KERNEL)))
-			break;
-	}
+	irq = mlx5_irq_affinity_irq_request_auto(dev, &table->used_cpus, vecidx);
+	if (IS_ERR(irq))
+		return PTR_ERR(irq);
 
-	return i ? i : PTR_ERR(irq);
+	return xa_err(xa_store(&table->comp_irqs, vecidx, irq, GFP_KERNEL));
 }
 
-static void comp_irqs_release(struct mlx5_core_dev *dev)
+static void comp_irq_release(struct mlx5_core_dev *dev, u16 vecidx)
 {
-	mlx5_core_is_sf(dev) ? comp_irqs_release_sf(dev) :
-			       comp_irqs_release_pci(dev);
+	mlx5_core_is_sf(dev) ? comp_irq_release_sf(dev, vecidx) :
+			       comp_irq_release_pci(dev, vecidx);
 }
 
-static int comp_irqs_request(struct mlx5_core_dev *dev)
+static int comp_irq_request(struct mlx5_core_dev *dev, u16 vecidx)
 {
-	return mlx5_core_is_sf(dev) ? comp_irqs_request_sf(dev) :
-				      comp_irqs_request_pci(dev);
+	return mlx5_core_is_sf(dev) ? comp_irq_request_sf(dev, vecidx) :
+				      comp_irq_request_pci(dev, vecidx);
 }
 
 #ifdef CONFIG_RFS_ACCEL
@@ -944,6 +929,8 @@ static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq_comp *eq, *n;
+	struct mlx5_irq *irq;
+	unsigned long index;
 
 	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
 		list_del(&eq->list);
@@ -955,7 +942,10 @@ static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 		kfree(eq);
 		table->curr_comp_eqs--;
 	}
-	comp_irqs_release(dev);
+
+	xa_for_each(&table->comp_irqs, index, irq)
+		comp_irq_release(dev, index);
+
 	free_rmap(dev);
 }
 
@@ -980,7 +970,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 	struct mlx5_eq_comp *eq;
 	struct mlx5_irq *irq;
 	unsigned long index;
-	int ncomp_eqs;
+	int vecidx;
 	int nent;
 	int err;
 
@@ -988,13 +978,16 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 	if (err)
 		return err;
 
-	ncomp_eqs = comp_irqs_request(dev);
-	if (ncomp_eqs < 0) {
-		err = ncomp_eqs;
-		goto err_irqs_req;
+	for (vecidx = 0; vecidx < table->max_comp_eqs; vecidx++) {
+		err = comp_irq_request(dev, vecidx);
+		if (err < 0)
+			break;
 	}
 
-	table->max_comp_eqs = ncomp_eqs;
+	if (!vecidx)
+		goto err_irqs_req;
+
+	table->max_comp_eqs = vecidx;
 	INIT_LIST_HEAD(&table->comp_eqs_list);
 	nent = comp_eq_depth_devlink_param_get(dev);
 
-- 
GitLab


From 273c697fdedc65f8b423a652fb248860a3dbf36d Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Mon, 19 Jun 2023 15:01:43 +0300
Subject: [PATCH 0930/1806] net/mlx5: Use xarray to store and manage completion
 EQs

Use xarray to store the completion EQs instead of a linked list.
The xarray offers more scalability, reduced memory overhead, and
facilitates the lookup of a certain EQ given a vector index.

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 50 ++++++++++----------
 1 file changed, 24 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index c01a5d8dbe9bd..b343c0fd621ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -47,7 +47,7 @@ enum {
 static_assert(MLX5_EQ_POLLING_BUDGET <= MLX5_NUM_SPARE_EQE);
 
 struct mlx5_eq_table {
-	struct list_head        comp_eqs_list;
+	struct xarray           comp_eqs;
 	struct mlx5_eq_async    pages_eq;
 	struct mlx5_eq_async    cmd_eq;
 	struct mlx5_eq_async    async_eq;
@@ -455,6 +455,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 
 	eq_table->irq_table = mlx5_irq_table_get(dev);
 	cpumask_clear(&eq_table->used_cpus);
+	xa_init(&eq_table->comp_eqs);
 	xa_init(&eq_table->comp_irqs);
 	eq_table->curr_comp_eqs = 0;
 	return 0;
@@ -466,6 +467,7 @@ void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev)
 
 	mlx5_eq_debugfs_cleanup(dev);
 	xa_destroy(&table->comp_irqs);
+	xa_destroy(&table->comp_eqs);
 	kvfree(table);
 }
 
@@ -928,12 +930,12 @@ static void free_rmap(struct mlx5_core_dev *mdev) {}
 static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_eq_comp *eq, *n;
+	struct mlx5_eq_comp *eq;
 	struct mlx5_irq *irq;
 	unsigned long index;
 
-	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
-		list_del(&eq->list);
+	xa_for_each(&table->comp_eqs, index, eq) {
+		xa_erase(&table->comp_eqs, index);
 		mlx5_eq_disable(dev, &eq->core, &eq->irq_nb);
 		if (destroy_unmap_eq(dev, &eq->core))
 			mlx5_core_warn(dev, "failed to destroy comp EQ 0x%x\n",
@@ -988,7 +990,6 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 		goto err_irqs_req;
 
 	table->max_comp_eqs = vecidx;
-	INIT_LIST_HEAD(&table->comp_eqs_list);
 	nent = comp_eq_depth_devlink_param_get(dev);
 
 	xa_for_each(&table->comp_irqs, index, irq)
@@ -1022,13 +1023,16 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 		}
 
 		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn);
-		/* add tail, to keep the list ordered, for mlx5_vector2eqn to work */
-		list_add_tail(&eq->list, &table->comp_eqs_list);
+		err = xa_err(xa_store(&table->comp_eqs, index, eq, GFP_KERNEL));
+		if (err)
+			goto disable_eq;
 		table->curr_comp_eqs++;
 	}
 
 	return 0;
 
+disable_eq:
+	mlx5_eq_disable(dev, &eq->core, &eq->irq_nb);
 clean_eq:
 	kfree(eq);
 clean:
@@ -1043,21 +1047,16 @@ static int vector2eqnirqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq_comp *eq;
-	int err = -ENOENT;
-	int i = 0;
 
-	list_for_each_entry(eq, &table->comp_eqs_list, list) {
-		if (i++ == vector) {
-			if (irqn)
-				*irqn = eq->core.irqn;
-			if (eqn)
-				*eqn = eq->core.eqn;
-			err = 0;
-			break;
-		}
-	}
+	eq = xa_load(&table->comp_eqs, vector);
+	if (!eq)
+		return -ENOENT;
 
-	return err;
+	if (irqn)
+		*irqn = eq->core.irqn;
+	if (eqn)
+		*eqn = eq->core.eqn;
+	return 0;
 }
 
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn)
@@ -1082,12 +1081,10 @@ mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq_comp *eq;
-	int i = 0;
 
-	list_for_each_entry(eq, &table->comp_eqs_list, list) {
-		if (i++ == vector)
-			return mlx5_irq_get_affinity_mask(eq->core.irq);
-	}
+	eq = xa_load(&table->comp_eqs, vector);
+	if (eq)
+		return mlx5_irq_get_affinity_mask(eq->core.irq);
 
 	WARN_ON_ONCE(1);
 	return NULL;
@@ -1105,8 +1102,9 @@ struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq_comp *eq;
+	unsigned long index;
 
-	list_for_each_entry(eq, &table->comp_eqs_list, list) {
+	xa_for_each(&table->comp_eqs, index, eq) {
 		if (eq->core.eqn == eqn)
 			return eq;
 	}
-- 
GitLab


From e3e56775e91398df95c610bfc9bf4025db7dcf66 Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Sun, 11 Jun 2023 19:55:02 +0300
Subject: [PATCH 0931/1806] net/mlx5: Implement single completion EQ
 create/destroy methods

Currently, create_comp_eqs() function handles the creation of all
completion EQs for all the vectors on driver load. While on driver
unload, destroy_comp_eqs() performs the equivalent job.

In preparation for dynamic EQ creation, replace create_comp_eqs() /
destroy_comp_eqs() with  create_comp_eq() / destroy_comp_eq() functions
which will receive a vector index and allocate/destroy an EQ for that
specific vector. Thus, allowing more flexibility in the management
of completion EQs.

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 137 +++++++++----------
 1 file changed, 66 insertions(+), 71 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index b343c0fd621ea..41fa15757101c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -927,28 +927,19 @@ static int alloc_rmap(struct mlx5_core_dev *mdev) { return 0; }
 static void free_rmap(struct mlx5_core_dev *mdev) {}
 #endif
 
-static void destroy_comp_eqs(struct mlx5_core_dev *dev)
+static void destroy_comp_eq(struct mlx5_core_dev *dev, struct mlx5_eq_comp *eq, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_eq_comp *eq;
-	struct mlx5_irq *irq;
-	unsigned long index;
-
-	xa_for_each(&table->comp_eqs, index, eq) {
-		xa_erase(&table->comp_eqs, index);
-		mlx5_eq_disable(dev, &eq->core, &eq->irq_nb);
-		if (destroy_unmap_eq(dev, &eq->core))
-			mlx5_core_warn(dev, "failed to destroy comp EQ 0x%x\n",
-				       eq->core.eqn);
-		tasklet_disable(&eq->tasklet_ctx.task);
-		kfree(eq);
-		table->curr_comp_eqs--;
-	}
 
-	xa_for_each(&table->comp_irqs, index, irq)
-		comp_irq_release(dev, index);
-
-	free_rmap(dev);
+	xa_erase(&table->comp_eqs, vecidx);
+	mlx5_eq_disable(dev, &eq->core, &eq->irq_nb);
+	if (destroy_unmap_eq(dev, &eq->core))
+		mlx5_core_warn(dev, "failed to destroy comp EQ 0x%x\n",
+			       eq->core.eqn);
+	tasklet_disable(&eq->tasklet_ctx.task);
+	kfree(eq);
+	comp_irq_release(dev, vecidx);
+	table->curr_comp_eqs--;
 }
 
 static u16 comp_eq_depth_devlink_param_get(struct mlx5_core_dev *dev)
@@ -966,79 +957,62 @@ static u16 comp_eq_depth_devlink_param_get(struct mlx5_core_dev *dev)
 	return MLX5_COMP_EQ_SIZE;
 }
 
-static int create_comp_eqs(struct mlx5_core_dev *dev)
+static int create_comp_eq(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_eq_param param = {};
 	struct mlx5_eq_comp *eq;
 	struct mlx5_irq *irq;
-	unsigned long index;
-	int vecidx;
 	int nent;
 	int err;
 
-	err = alloc_rmap(dev);
+	err = comp_irq_request(dev, vecidx);
 	if (err)
 		return err;
 
-	for (vecidx = 0; vecidx < table->max_comp_eqs; vecidx++) {
-		err = comp_irq_request(dev, vecidx);
-		if (err < 0)
-			break;
-	}
-
-	if (!vecidx)
-		goto err_irqs_req;
-
-	table->max_comp_eqs = vecidx;
 	nent = comp_eq_depth_devlink_param_get(dev);
 
-	xa_for_each(&table->comp_irqs, index, irq)
-	{
-		struct mlx5_eq_param param = {};
+	eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, dev->priv.numa_node);
+	if (!eq) {
+		err = -ENOMEM;
+		goto clean_irq;
+	}
 
-		eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, dev->priv.numa_node);
-		if (!eq) {
-			err = -ENOMEM;
-			goto clean;
-		}
+	INIT_LIST_HEAD(&eq->tasklet_ctx.list);
+	INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
+	spin_lock_init(&eq->tasklet_ctx.lock);
+	tasklet_setup(&eq->tasklet_ctx.task, mlx5_cq_tasklet_cb);
 
-		INIT_LIST_HEAD(&eq->tasklet_ctx.list);
-		INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
-		spin_lock_init(&eq->tasklet_ctx.lock);
-		tasklet_setup(&eq->tasklet_ctx.task, mlx5_cq_tasklet_cb);
-
-		eq->irq_nb.notifier_call = mlx5_eq_comp_int;
-		param = (struct mlx5_eq_param) {
-			.irq = irq,
-			.nent = nent,
-		};
-
-		err = create_map_eq(dev, &eq->core, &param);
-		if (err)
-			goto clean_eq;
-		err = mlx5_eq_enable(dev, &eq->core, &eq->irq_nb);
-		if (err) {
-			destroy_unmap_eq(dev, &eq->core);
-			goto clean_eq;
-		}
+	irq = xa_load(&table->comp_irqs, vecidx);
+	eq->irq_nb.notifier_call = mlx5_eq_comp_int;
+	param = (struct mlx5_eq_param) {
+		.irq = irq,
+		.nent = nent,
+	};
 
-		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn);
-		err = xa_err(xa_store(&table->comp_eqs, index, eq, GFP_KERNEL));
-		if (err)
-			goto disable_eq;
-		table->curr_comp_eqs++;
+	err = create_map_eq(dev, &eq->core, &param);
+	if (err)
+		goto clean_eq;
+	err = mlx5_eq_enable(dev, &eq->core, &eq->irq_nb);
+	if (err) {
+		destroy_unmap_eq(dev, &eq->core);
+		goto clean_eq;
 	}
 
+	mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn);
+	err = xa_err(xa_store(&table->comp_eqs, vecidx, eq, GFP_KERNEL));
+	if (err)
+		goto disable_eq;
+
+	table->curr_comp_eqs++;
 	return 0;
 
 disable_eq:
 	mlx5_eq_disable(dev, &eq->core, &eq->irq_nb);
 clean_eq:
 	kfree(eq);
-clean:
-	destroy_comp_eqs(dev);
-err_irqs_req:
-	free_rmap(dev);
+clean_irq:
+	comp_irq_release(dev, vecidx);
 	return err;
 }
 
@@ -1161,6 +1135,7 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	int err;
+	int i;
 
 	eq_table->max_comp_eqs = get_num_eqs(dev);
 	err = create_async_eqs(dev);
@@ -1169,8 +1144,19 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 		goto err_async_eqs;
 	}
 
-	err = create_comp_eqs(dev);
+	err = alloc_rmap(dev);
 	if (err) {
+		mlx5_core_err(dev, "Failed to allocate rmap\n");
+		goto err_rmap;
+	}
+
+	for (i = 0; i < eq_table->max_comp_eqs; i++) {
+		err = create_comp_eq(dev, i);
+		if (err < 0)
+			break;
+	}
+
+	if (!i) {
 		mlx5_core_err(dev, "Failed to create completion EQs\n");
 		goto err_comp_eqs;
 	}
@@ -1178,6 +1164,8 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 	return 0;
 
 err_comp_eqs:
+	free_rmap(dev);
+err_rmap:
 	destroy_async_eqs(dev);
 err_async_eqs:
 	return err;
@@ -1185,7 +1173,14 @@ err_async_eqs:
 
 void mlx5_eq_table_destroy(struct mlx5_core_dev *dev)
 {
-	destroy_comp_eqs(dev);
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_eq_comp *eq;
+	unsigned long index;
+
+	xa_for_each(&table->comp_eqs, index, eq)
+		destroy_comp_eq(dev, eq, index);
+
+	free_rmap(dev);
 	destroy_async_eqs(dev);
 }
 
-- 
GitLab


From ddd2c79da02021153dc8674e5a7e9748e56c1240 Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Mon, 12 Jun 2023 11:50:10 +0300
Subject: [PATCH 0932/1806] net/mlx5: Introduce mlx5_cpumask_default_spread

For better code readability in the completion IRQ request code, define
the cpu lookup per completion vector logic in a separate function.

The new method mlx5_cpumask_default_spread() given a vector index 'n'
will return the 'nth' cpu. This new method will be used also in the next
patch.

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 41fa15757101c..ad654d460d0c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -826,20 +826,18 @@ static void comp_irq_release_pci(struct mlx5_core_dev *dev, u16 vecidx)
 	mlx5_irq_release_vector(irq);
 }
 
-static int comp_irq_request_pci(struct mlx5_core_dev *dev, u16 vecidx)
+static int mlx5_cpumask_default_spread(int numa_node, int index)
 {
-	struct mlx5_eq_table *table = dev->priv.eq_table;
 	const struct cpumask *prev = cpu_none_mask;
 	const struct cpumask *mask;
-	struct mlx5_irq *irq;
 	int found_cpu = 0;
 	int i = 0;
 	int cpu;
 
 	rcu_read_lock();
-	for_each_numa_hop_mask(mask, dev->priv.numa_node) {
+	for_each_numa_hop_mask(mask, numa_node) {
 		for_each_cpu_andnot(cpu, mask, prev) {
-			if (i++ == vecidx) {
+			if (i++ == index) {
 				found_cpu = cpu;
 				goto spread_done;
 			}
@@ -849,7 +847,17 @@ static int comp_irq_request_pci(struct mlx5_core_dev *dev, u16 vecidx)
 
 spread_done:
 	rcu_read_unlock();
-	irq = mlx5_irq_request_vector(dev, found_cpu, vecidx, &table->rmap);
+	return found_cpu;
+}
+
+static int comp_irq_request_pci(struct mlx5_core_dev *dev, u16 vecidx)
+{
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_irq *irq;
+	int cpu;
+
+	cpu = mlx5_cpumask_default_spread(dev->priv.numa_node, vecidx);
+	irq = mlx5_irq_request_vector(dev, cpu, vecidx, &table->rmap);
 	if (IS_ERR(irq))
 		return PTR_ERR(irq);
 
-- 
GitLab


From f3147015fa0769cf1dcbfdb9040ad380cc4daeb5 Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Mon, 12 Jun 2023 11:58:14 +0300
Subject: [PATCH 0933/1806] net/mlx5: Add IRQ vector to CPU lookup function

Currently, once driver load completes, IRQ requests were performed for all
vectors. However, as we move to support dynamic creation of EQs, this will
not be the case as some IRQs will not exist at this stage. Thus, in such
case, use the default CPU to IRQ mapping which is the serial mapping based
on IRQ vector index. Meaning, the n'th vector gets mapped to the n'th CPU.

Introduce an API function mlx5_comp_vector_cpu() that takes an IRQ index and
provides the corresponding CPU mapping. It utilizes the existing IRQ
affinity if defined, or resorts to the default serialized CPU mapping
otherwise.

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/trap.c |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/eq.c  | 19 ++++++++++++++++---
 include/linux/mlx5/driver.h                   |  3 +--
 4 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 201ac7dd338f0..bcf9807a55568 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -128,7 +128,7 @@ static void mlx5e_build_trap_params(struct mlx5_core_dev *mdev,
 
 static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
 {
-	int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, 0));
+	int cpu = mlx5_comp_vector_get_cpu(priv->mdev, 0);
 	struct net_device *netdev = priv->netdev;
 	struct mlx5e_trap *t;
 	int err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1c820119e438f..9ec7b975c5492 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2445,7 +2445,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct xsk_buff_pool *xsk_pool,
 			      struct mlx5e_channel **cp)
 {
-	int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
+	int cpu = mlx5_comp_vector_get_cpu(priv->mdev, ix);
 	struct net_device *netdev = priv->netdev;
 	struct mlx5e_xsk_param xsk;
 	struct mlx5e_channel *c;
@@ -2862,7 +2862,7 @@ static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
 		cpumask_clear(priv->scratchpad.cpumask);
 
 		for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) {
-			int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(mdev, irq));
+			int cpu = mlx5_comp_vector_get_cpu(mdev, irq);
 
 			cpumask_set_cpu(cpu, priv->scratchpad.cpumask);
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ad654d460d0c4..2f5c0d00285f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -1058,7 +1058,7 @@ unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_comp_vectors_count);
 
-struct cpumask *
+static struct cpumask *
 mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
@@ -1068,10 +1068,23 @@ mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
 	if (eq)
 		return mlx5_irq_get_affinity_mask(eq->core.irq);
 
-	WARN_ON_ONCE(1);
 	return NULL;
 }
-EXPORT_SYMBOL(mlx5_comp_irq_get_affinity_mask);
+
+int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector)
+{
+	struct cpumask *mask;
+	int cpu;
+
+	mask = mlx5_comp_irq_get_affinity_mask(dev, vector);
+	if (mask)
+		cpu = cpumask_first(mask);
+	else
+		cpu = mlx5_cpumask_default_spread(dev->priv.numa_node, vector);
+
+	return cpu;
+}
+EXPORT_SYMBOL(mlx5_comp_vector_get_cpu);
 
 #ifdef CONFIG_RFS_ACCEL
 struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index fa70c25423b21..e686722fa4ca4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1109,8 +1109,7 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg,
 void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg);
 
 unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev);
-struct cpumask *
-mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector);
+int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector);
 unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev);
 int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index,
 			   u8 roce_version, u8 roce_l3_type, const u8 *gid,
-- 
GitLab


From 674dd4e2e04e7a62bfacf28129e0808f33395bdf Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Thu, 22 Jun 2023 18:52:44 +0300
Subject: [PATCH 0934/1806] net/mlx5: Rename mlx5_comp_vectors_count() to
 mlx5_comp_vectors_max()

To accurately represent its purpose, rename the function that retrieves
the value of maximum vectors from mlx5_comp_vectors_count() to
mlx5_comp_vectors_max().

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/infiniband/hw/mlx5/main.c                          | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en.h               | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c          | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c               | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c | 2 +-
 drivers/vfio/pci/mlx5/cmd.c                                | 2 +-
 include/linux/mlx5/driver.h                                | 2 +-
 7 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index f0b394ed7452a..3c25b9045f9d5 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3685,7 +3685,7 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	if (mlx5_use_mad_ifc(dev))
 		get_ext_port_caps(dev);
 
-	dev->ib_dev.num_comp_vectors    = mlx5_comp_vectors_count(mdev);
+	dev->ib_dev.num_comp_vectors    = mlx5_comp_vectors_max(mdev);
 
 	mutex_init(&dev->cap_mask_mutex);
 	INIT_LIST_HEAD(&dev->qp_list);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0f8f70b914855..c1deb04ba7e82 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -193,7 +193,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 {
 	return is_kdump_kernel() ?
 		MLX5E_MIN_NUM_CHANNELS :
-		min_t(int, mlx5_comp_vectors_count(mdev), MLX5E_MAX_NUM_CHANNELS);
+		min_t(int, mlx5_comp_vectors_max(mdev), MLX5E_MAX_NUM_CHANNELS);
 }
 
 /* The maximum WQE size can be retrieved by max_wqe_sz_sq in
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9ec7b975c5492..5710d755c2c46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2856,7 +2856,7 @@ static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int num_comp_vectors, ix, irq;
 
-	num_comp_vectors = mlx5_comp_vectors_count(mdev);
+	num_comp_vectors = mlx5_comp_vectors_max(mdev);
 
 	for (ix = 0; ix < params->num_channels; ix++) {
 		cpumask_clear(priv->scratchpad.cpumask);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 2f5c0d00285f8..6272962ea077f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -1052,11 +1052,11 @@ int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn)
 	return vector2eqnirqn(dev, vector, NULL, irqn);
 }
 
-unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev)
+unsigned int mlx5_comp_vectors_max(struct mlx5_core_dev *dev)
 {
 	return dev->priv.eq_table->max_comp_eqs;
 }
-EXPORT_SYMBOL(mlx5_comp_vectors_count);
+EXPORT_SYMBOL(mlx5_comp_vectors_max);
 
 static struct cpumask *
 mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 4a5ae86e2b623..24bb30b5008c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -1096,7 +1096,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	if (!in)
 		goto err_cqwq;
 
-	vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev);
+	vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev);
 	err = mlx5_vector2eqn(mdev, vector, &eqn);
 	if (err) {
 		kvfree(in);
diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index deed156e61656..eee20f04a4697 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -1025,7 +1025,7 @@ static int mlx5vf_create_cq(struct mlx5_core_dev *mdev,
 		goto err_buff;
 	}
 
-	vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev);
+	vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev);
 	err = mlx5_vector2eqn(mdev, vector, &eqn);
 	if (err)
 		goto err_vec;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e686722fa4ca4..43c4fd26c69ad 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1108,7 +1108,7 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg,
 		     bool map_wc, bool fast_path);
 void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg);
 
-unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev);
+unsigned int mlx5_comp_vectors_max(struct mlx5_core_dev *dev);
 int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector);
 unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev);
 int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index,
-- 
GitLab


From 54c5297801f3b9140c751c7f5660770c52dea24e Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Thu, 22 Jun 2023 19:05:46 +0300
Subject: [PATCH 0935/1806] net/mlx5: Handle SF IRQ request in the absence of
 SF IRQ pool

In case the SF IRQ pool is not available due to setup limitations,
SF currently relies on the already allocated PF IRQs to fulfill
its IRQ vector requests.

However, with the dynamic EQ allocation introduced in the next patch,
it is possible that not all IRQs of PF will be allocated after the driver
is loaded. In such case, if a SF requests a completion IRQ without having
its own independent IRQ pool, SF will lack a PF IRQ to utilize.

To address this scenario, allocate an IRQ for the SF from the PF's IRQ pool
on demand. The new IRQ will be shared between the SF and it's PF.

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c  | 24 +++++++++++++++++--
 .../mellanox/mlx5/core/irq_affinity.c         | 12 ++++------
 2 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 6272962ea077f..6e6e0a1c12b59 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -850,14 +850,29 @@ spread_done:
 	return found_cpu;
 }
 
+static struct cpu_rmap *mlx5_eq_table_get_pci_rmap(struct mlx5_core_dev *dev)
+{
+#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_SF
+	if (mlx5_core_is_sf(dev))
+		return dev->priv.parent_mdev->priv.eq_table->rmap;
+#endif
+	return dev->priv.eq_table->rmap;
+#else
+	return NULL;
+#endif
+}
+
 static int comp_irq_request_pci(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct cpu_rmap *rmap;
 	struct mlx5_irq *irq;
 	int cpu;
 
+	rmap = mlx5_eq_table_get_pci_rmap(dev);
 	cpu = mlx5_cpumask_default_spread(dev->priv.numa_node, vecidx);
-	irq = mlx5_irq_request_vector(dev, cpu, vecidx, &table->rmap);
+	irq = mlx5_irq_request_vector(dev, cpu, vecidx, &rmap);
 	if (IS_ERR(irq))
 		return PTR_ERR(irq);
 
@@ -883,8 +898,13 @@ static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
 	struct mlx5_irq *irq;
 
 	irq = mlx5_irq_affinity_irq_request_auto(dev, &table->used_cpus, vecidx);
-	if (IS_ERR(irq))
+	if (IS_ERR(irq)) {
+		/* In case SF irq pool does not exist, fallback to the PF irqs*/
+		if (PTR_ERR(irq) == -ENOENT)
+			return comp_irq_request_pci(dev, vecidx);
+
 		return PTR_ERR(irq);
+	}
 
 	return xa_err(xa_store(&table->comp_irqs, vecidx, irq, GFP_KERNEL));
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index ed51800f9f672..047d5fed5f89e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -191,17 +191,13 @@ struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
 	struct irq_affinity_desc af_desc = {};
 	struct mlx5_irq *irq;
 
+	if (!mlx5_irq_pool_is_sf_pool(pool))
+		return ERR_PTR(-ENOENT);
+
 	af_desc.is_managed = 1;
 	cpumask_copy(&af_desc.mask, cpu_online_mask);
 	cpumask_andnot(&af_desc.mask, &af_desc.mask, used_cpus);
-	if (mlx5_irq_pool_is_sf_pool(pool))
-		irq = mlx5_irq_affinity_request(pool, &af_desc);
-	else
-		/* In case SF pool doesn't exists, fallback to the PF IRQs.
-		 * The PF IRQs are already allocated and binded to CPU
-		 * at this point. Hence, only an index is needed.
-		 */
-		irq = mlx5_irq_request(dev, vecidx, NULL, NULL);
+	irq = mlx5_irq_affinity_request(pool, &af_desc);
 
 	if (IS_ERR(irq))
 		return irq;
-- 
GitLab


From f14c1a14e63227a65faa68237687784a6dd2e922 Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Mon, 12 Jun 2023 10:13:50 +0300
Subject: [PATCH 0936/1806] net/mlx5: Allocate completion EQs dynamically

This commit enables the dynamic allocation of EQs at runtime, allowing
for more flexibility in managing completion EQs and reducing the memory
overhead of driver load. Whenever a CQ is created for a given vector
index, the driver will lookup to see if there is an already mapped
completion EQ for that vector, if so, utilize it. Otherwise, allocate a
new EQ on demand and then utilize it for the CQ completion events.

Add a protection lock to the EQ table to protect from concurrent EQ
creation attempts.

While at it, replace mlx5_vector2irqn()/mlx5_vector2eqn() with
mlx5_comp_eqn_get() and mlx5_comp_irqn_get() which will allocate an
EQ on demand if no EQ is found for the given vector.

Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/infiniband/hw/mlx5/cq.c               |  2 +-
 drivers/infiniband/hw/mlx5/devx.c             |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c |  4 +-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c  | 80 ++++++++++---------
 .../ethernet/mellanox/mlx5/core/fpga/conn.c   |  2 +-
 .../net/ethernet/mellanox/mlx5/core/lib/aso.c |  2 +-
 .../net/ethernet/mellanox/mlx5/core/lib/eq.h  |  2 +-
 .../mellanox/mlx5/core/steering/dr_send.c     |  2 +-
 drivers/vdpa/mlx5/net/mlx5_vnet.c             |  2 +-
 drivers/vfio/pci/mlx5/cmd.c                   |  2 +-
 include/linux/mlx5/driver.h                   |  2 +-
 11 files changed, 54 insertions(+), 48 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index efc9e4a6df04a..9773d2a3d97fb 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -993,7 +993,7 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		INIT_WORK(&cq->notify_work, notify_soft_wc_handler);
 	}
 
-	err = mlx5_vector2eqn(dev->mdev, vector, &eqn);
+	err = mlx5_comp_eqn_get(dev->mdev, vector, &eqn);
 	if (err)
 		goto err_cqb;
 
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index db5fb196c728b..8ba53edf23119 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1002,7 +1002,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_QUERY_EQN)(
 		return PTR_ERR(c);
 	dev = to_mdev(c->ibucontext.device);
 
-	err = mlx5_vector2eqn(dev->mdev, user_vector, &dev_eqn);
+	err = mlx5_comp_eqn_get(dev->mdev, user_vector, &dev_eqn);
 	if (err < 0)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5710d755c2c46..5919b889479f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1989,7 +1989,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	int eqn;
 	int err;
 
-	err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn);
+	err = mlx5_comp_eqn_get(mdev, param->eq_ix, &eqn);
 	if (err)
 		return err;
 
@@ -2452,7 +2452,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	unsigned int irq;
 	int err;
 
-	err = mlx5_vector2irqn(priv->mdev, ix, &irq);
+	err = mlx5_comp_irqn_get(priv->mdev, ix, &irq);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 6e6e0a1c12b59..ea0405e0a43fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -58,6 +58,7 @@ struct mlx5_eq_table {
 	struct mlx5_nb          cq_err_nb;
 
 	struct mutex            lock; /* sync async eqs creations */
+	struct mutex            comp_lock; /* sync comp eqs creations */
 	int			curr_comp_eqs;
 	int			max_comp_eqs;
 	struct mlx5_irq_table	*irq_table;
@@ -457,6 +458,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 	cpumask_clear(&eq_table->used_cpus);
 	xa_init(&eq_table->comp_eqs);
 	xa_init(&eq_table->comp_irqs);
+	mutex_init(&eq_table->comp_lock);
 	eq_table->curr_comp_eqs = 0;
 	return 0;
 }
@@ -985,6 +987,7 @@ static u16 comp_eq_depth_devlink_param_get(struct mlx5_core_dev *dev)
 	return MLX5_COMP_EQ_SIZE;
 }
 
+/* Must be called with EQ table comp_lock held */
 static int create_comp_eq(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
@@ -994,6 +997,13 @@ static int create_comp_eq(struct mlx5_core_dev *dev, u16 vecidx)
 	int nent;
 	int err;
 
+	lockdep_assert_held(&table->comp_lock);
+	if (table->curr_comp_eqs == table->max_comp_eqs) {
+		mlx5_core_err(dev, "maximum number of vectors is allocated, %d\n",
+			      table->max_comp_eqs);
+		return -ENOMEM;
+	}
+
 	err = comp_irq_request(dev, vecidx);
 	if (err)
 		return err;
@@ -1033,7 +1043,7 @@ static int create_comp_eq(struct mlx5_core_dev *dev, u16 vecidx)
 		goto disable_eq;
 
 	table->curr_comp_eqs++;
-	return 0;
+	return eq->core.eqn;
 
 disable_eq:
 	mlx5_eq_disable(dev, &eq->core, &eq->irq_nb);
@@ -1044,32 +1054,47 @@ clean_irq:
 	return err;
 }
 
-static int vector2eqnirqn(struct mlx5_core_dev *dev, int vector, int *eqn,
-			  unsigned int *irqn)
+int mlx5_comp_eqn_get(struct mlx5_core_dev *dev, u16 vecidx, int *eqn)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq_comp *eq;
+	int ret = 0;
 
-	eq = xa_load(&table->comp_eqs, vector);
-	if (!eq)
-		return -ENOENT;
-
-	if (irqn)
-		*irqn = eq->core.irqn;
-	if (eqn)
+	mutex_lock(&table->comp_lock);
+	eq = xa_load(&table->comp_eqs, vecidx);
+	if (eq) {
 		*eqn = eq->core.eqn;
+		goto out;
+	}
+
+	ret = create_comp_eq(dev, vecidx);
+	if (ret < 0) {
+		mutex_unlock(&table->comp_lock);
+		return ret;
+	}
+
+	*eqn = ret;
+out:
+	mutex_unlock(&table->comp_lock);
 	return 0;
 }
+EXPORT_SYMBOL(mlx5_comp_eqn_get);
 
-int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn)
+int mlx5_comp_irqn_get(struct mlx5_core_dev *dev, int vector, unsigned int *irqn)
 {
-	return vector2eqnirqn(dev, vector, eqn, NULL);
-}
-EXPORT_SYMBOL(mlx5_vector2eqn);
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_eq_comp *eq;
+	int eqn;
+	int err;
 
-int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn)
-{
-	return vector2eqnirqn(dev, vector, NULL, irqn);
+	/* Allocate the EQ if not allocated yet */
+	err = mlx5_comp_eqn_get(dev, vector, &eqn);
+	if (err)
+		return err;
+
+	eq = xa_load(&table->comp_eqs, vector);
+	*irqn = eq->core.irqn;
+	return 0;
 }
 
 unsigned int mlx5_comp_vectors_max(struct mlx5_core_dev *dev)
@@ -1119,10 +1144,9 @@ struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn)
 	struct mlx5_eq_comp *eq;
 	unsigned long index;
 
-	xa_for_each(&table->comp_eqs, index, eq) {
+	xa_for_each(&table->comp_eqs, index, eq)
 		if (eq->core.eqn == eqn)
 			return eq;
-	}
 
 	return ERR_PTR(-ENOENT);
 }
@@ -1130,11 +1154,7 @@ struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn)
 /* This function should only be called after mlx5_cmd_force_teardown_hca */
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = dev->priv.eq_table;
-
-	mutex_lock(&table->lock); /* sync with create/destroy_async_eq */
 	mlx5_irq_table_free_irqs(dev);
-	mutex_unlock(&table->lock);
 }
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
@@ -1176,7 +1196,6 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	int err;
-	int i;
 
 	eq_table->max_comp_eqs = get_num_eqs(dev);
 	err = create_async_eqs(dev);
@@ -1191,21 +1210,8 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 		goto err_rmap;
 	}
 
-	for (i = 0; i < eq_table->max_comp_eqs; i++) {
-		err = create_comp_eq(dev, i);
-		if (err < 0)
-			break;
-	}
-
-	if (!i) {
-		mlx5_core_err(dev, "Failed to create completion EQs\n");
-		goto err_comp_eqs;
-	}
-
 	return 0;
 
-err_comp_eqs:
-	free_rmap(dev);
 err_rmap:
 	destroy_async_eqs(dev);
 err_async_eqs:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 12abe991583a8..c4de6bf8d1b65 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -445,7 +445,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 		goto err_cqwq;
 	}
 
-	err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn);
+	err = mlx5_comp_eqn_get(mdev, smp_processor_id(), &eqn);
 	if (err) {
 		kvfree(in);
 		goto err_cqwq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
index 5a80fb7dbbcaa..40c7be1240416 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
@@ -81,7 +81,7 @@ static int create_aso_cq(struct mlx5_aso_cq *cq, void *cqc_data)
 	int inlen, eqn;
 	int err;
 
-	err = mlx5_vector2eqn(mdev, 0, &eqn);
+	err = mlx5_comp_eqn_get(mdev, 0, &eqn);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index d3d628b862f37..69a75459775dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -104,6 +104,6 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
 struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev);
 #endif
 
-int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn);
+int mlx5_comp_irqn_get(struct mlx5_core_dev *dev, int vector, unsigned int *irqn);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 24bb30b5008c9..6fa06ba2d3465 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -1097,7 +1097,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 		goto err_cqwq;
 
 	vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev);
-	err = mlx5_vector2eqn(mdev, vector, &eqn);
+	err = mlx5_comp_eqn_get(mdev, vector, &eqn);
 	if (err) {
 		kvfree(in);
 		goto err_cqwq;
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 9138ef2fb2c85..bece4df7b8dde 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -580,7 +580,7 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent)
 	/* Use vector 0 by default. Consider adding code to choose least used
 	 * vector.
 	 */
-	err = mlx5_vector2eqn(mdev, 0, &eqn);
+	err = mlx5_comp_eqn_get(mdev, 0, &eqn);
 	if (err)
 		goto err_vec;
 
diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index eee20f04a4697..c82c1f4fc5888 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -1026,7 +1026,7 @@ static int mlx5vf_create_cq(struct mlx5_core_dev *mdev,
 	}
 
 	vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev);
-	err = mlx5_vector2eqn(mdev, vector, &eqn);
+	err = mlx5_comp_eqn_get(mdev, vector, &eqn);
 	if (err)
 		goto err_vec;
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 43c4fd26c69ad..3e1017d764b7b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1058,7 +1058,7 @@ void mlx5_unregister_debugfs(void);
 
 void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm);
 void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas);
-int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn);
+int mlx5_comp_eqn_get(struct mlx5_core_dev *dev, u16 vecidx, int *eqn);
 int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
 int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
 
-- 
GitLab


From a0ae00e71e3e652c3bde8dcb61b4c1718618192e Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Fri, 4 Aug 2023 09:43:44 +0800
Subject: [PATCH 0937/1806] net/mlx5: remove many unnecessary NULL values

There are many pointers assigned first, which need not to be
initialized, so remove the NULL assignments.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c   | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
index 39c03dcbd1960..e5c1012921d2c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
@@ -57,7 +57,7 @@ static const char * const mlx5_fpga_qp_error_strings[] = {
 };
 static struct mlx5_fpga_device *mlx5_fpga_device_alloc(void)
 {
-	struct mlx5_fpga_device *fdev = NULL;
+	struct mlx5_fpga_device *fdev;
 
 	fdev = kzalloc(sizeof(*fdev), GFP_KERNEL);
 	if (!fdev)
@@ -252,7 +252,7 @@ out:
 
 int mlx5_fpga_init(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_fpga_device *fdev = NULL;
+	struct mlx5_fpga_device *fdev;
 
 	if (!MLX5_CAP_GEN(mdev, fpga)) {
 		mlx5_core_dbg(mdev, "FPGA capability not present\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c
index 4047629a876b1..30564d9b00e9f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c
@@ -40,7 +40,7 @@ struct mlx5_hv_vhca_agent {
 
 struct mlx5_hv_vhca *mlx5_hv_vhca_create(struct mlx5_core_dev *dev)
 {
-	struct mlx5_hv_vhca *hv_vhca = NULL;
+	struct mlx5_hv_vhca *hv_vhca;
 
 	hv_vhca = kzalloc(sizeof(*hv_vhca), GFP_KERNEL);
 	if (!hv_vhca)
-- 
GitLab


From 58f6d9d04489788d4115bd4bec4193df9e23f45f Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 6 Aug 2023 13:34:59 +0300
Subject: [PATCH 0938/1806] net/mlx5: Fix typo reminder -> remainder

Fix a typo in esw_qos_devlink_rate_to_mbps(): reminder -> remainder.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 7c79476cc5f95..1887a24ee414d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -740,7 +740,7 @@ int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32
 static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char *name,
 					u64 *rate, struct netlink_ext_ack *extack)
 {
-	u32 link_speed_max, reminder;
+	u32 link_speed_max, remainder;
 	u64 value;
 	int err;
 
@@ -750,8 +750,8 @@ static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char *
 		return err;
 	}
 
-	value = div_u64_rem(*rate, MLX5_LINKSPEED_UNIT, &reminder);
-	if (reminder) {
+	value = div_u64_rem(*rate, MLX5_LINKSPEED_UNIT, &remainder);
+	if (remainder) {
 		pr_err("%s rate value %lluBps not in link speed units of 1Mbps.\n",
 		       name, *rate);
 		NL_SET_ERR_MSG_MOD(extack, "TX rate value not in link speed units of 1Mbps");
-- 
GitLab


From d602be220cf97aa581a9b34a7780a889bc3dd25c Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@nvidia.com>
Date: Tue, 11 Jul 2023 09:42:01 +0300
Subject: [PATCH 0939/1806] net/mlx5: E-Switch, Remove redundant arg
 ignore_flow_lvl

The arg is always passed as true and thus redundant.

Signed-off-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 723dff87e6d5e..e391535e1ab11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -375,7 +375,6 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest,
 		      struct mlx5_flow_act *flow_act,
 		      struct mlx5_eswitch *esw,
 		      struct mlx5_flow_attr *attr,
-		      bool ignore_flow_lvl,
 		      int *i)
 {
 	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
@@ -385,8 +384,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest,
 		return -EOPNOTSUPP;
 
 	for (j = esw_attr->split_count; j < esw_attr->out_count; j++, (*i)++) {
-		if (ignore_flow_lvl)
-			flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+		flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 		dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 
 		dest[*i].ft = mlx5_esw_indir_table_get(esw, attr,
@@ -569,7 +567,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 		err = esw_setup_mtu_dest(dest, &attr->meter_attr, *i);
 		(*i)++;
 	} else if (esw_is_indir_table(esw, attr)) {
-		err = esw_setup_indir_table(dest, flow_act, esw, attr, true, i);
+		err = esw_setup_indir_table(dest, flow_act, esw, attr, i);
 	} else if (esw_is_chain_src_port_rewrite(esw, esw_attr)) {
 		err = esw_setup_chain_src_port_rewrite(dest, flow_act, esw, chains, attr, i);
 	} else {
-- 
GitLab


From b56fb19c337951fc4daba646fab2c50bb4c41c58 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@nvidia.com>
Date: Tue, 11 Jul 2023 13:23:27 +0300
Subject: [PATCH 0940/1806] net/mlx5: Bridge, Only handle registered netdev
 bridge events

Don't handle bridge events for a netdev that doesn't belong to
an eswitch that registered for bridge events.

Signed-off-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
index 5608002465734..0fef853eab626 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -77,6 +77,10 @@ mlx5_esw_bridge_rep_vport_num_vhca_id_get(struct net_device *dev, struct mlx5_es
 		return NULL;
 
 	priv = netdev_priv(dev);
+
+	if (!priv->mdev->priv.eswitch->br_offloads)
+		return NULL;
+
 	rpriv = priv->ppriv;
 	*vport_num = rpriv->rep->vport;
 	*esw_owner_vhca_id = MLX5_CAP_GEN(priv->mdev, vhca_id);
-- 
GitLab


From 26cfb838aa002a5c03319f7fce87e9313e794351 Mon Sep 17 00:00:00 2001
From: Johannes Zink <j.zink@pengutronix.de>
Date: Tue, 1 Aug 2023 17:44:29 +0200
Subject: [PATCH 0941/1806] net: stmmac: correct MAC propagation delay

The IEEE1588 Standard specifies that the timestamps of Packets must be
captured when the PTP message timestamp point (leading edge of first
octet after the start of frame delimiter) crosses the boundary between
the node and the network. As the MAC latches the timestamp at an
internal point, the captured timestamp must be corrected for the
additional data transmission latency, as described in the publicly
available datasheet [1].

This patch only corrects for the MAC-Internal delay, which can be read
out from the MAC_Ingress_Timestamp_Latency register on DWMAC version 5,
since the Phy framework currently does not support querying the Phy
ingress and egress latency. The Closs Domain Crossing Circuits errors as
indicated in [1] are already being accounted in the
stmmac_get_tx_hwtstamp() function and are not corrected here.

As the Latency varies for different link speeds and MII
modes of operation, the correction value needs to be updated on each
link state change.

As the delay also causes a phase shift in the timestamp counter compared
to the rest of the network, this correction will also reduce phase error
when generating PPS outputs from the timestamp counter.

Since the correction registers may be unavailable on some hardware and
no feature bits are documented for dynamically detection of the MAC
propagation delay readout, introduce a feature bit to explicitely enable
MAC delay Correction in the gluecode driver.

[1] i.MX8MP Reference Manual, rev.1 Section 11.7.2.5.3 "Timestamp
correction"

Signed-off-by: Johannes Zink <j.zink@pengutronix.de>
Link: https://lore.kernel.org/r/20230719-stmmac_correct_mac_delay-v2-1-3366f38ee9a6@pengutronix.de
Link: https://lore.kernel.org/r/20230719-stmmac_correct_mac_delay-v3-1-61e63427735e@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/hwif.h    |  3 ++
 .../ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 43 +++++++++++++++++++
 .../net/ethernet/stmicro/stmmac/stmmac_main.c |  6 +++
 .../net/ethernet/stmicro/stmmac/stmmac_ptp.h  |  6 +++
 include/linux/stmmac.h                        |  1 +
 5 files changed, 59 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 652af8f6e75ff..238f17c50a1ea 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -532,6 +532,7 @@ struct stmmac_hwtimestamp {
 	void (*get_systime) (void __iomem *ioaddr, u64 *systime);
 	void (*get_ptptime)(void __iomem *ioaddr, u64 *ptp_time);
 	void (*timestamp_interrupt)(struct stmmac_priv *priv);
+	void (*hwtstamp_correct_latency)(struct stmmac_priv *priv);
 };
 
 #define stmmac_config_hw_tstamping(__priv, __args...) \
@@ -550,6 +551,8 @@ struct stmmac_hwtimestamp {
 	stmmac_do_void_callback(__priv, ptp, get_ptptime, __args)
 #define stmmac_timestamp_interrupt(__priv, __args...) \
 	stmmac_do_void_callback(__priv, ptp, timestamp_interrupt, __args)
+#define stmmac_hwtstamp_correct_latency(__priv, __args...) \
+	stmmac_do_void_callback(__priv, ptp, hwtstamp_correct_latency, __args)
 
 struct stmmac_tx_queue;
 struct stmmac_rx_queue;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index fa2c3ba7e9fe7..540f6a4ec0b81 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -60,6 +60,48 @@ static void config_sub_second_increment(void __iomem *ioaddr,
 		*ssinc = data;
 }
 
+static void hwtstamp_correct_latency(struct stmmac_priv *priv)
+{
+	void __iomem *ioaddr = priv->ptpaddr;
+	u32 reg_tsic, reg_tsicsns;
+	u32 reg_tsec, reg_tsecsns;
+	u64 scaled_ns;
+	u32 val;
+
+	/* MAC-internal ingress latency */
+	scaled_ns = readl(ioaddr + PTP_TS_INGR_LAT);
+
+	/* See section 11.7.2.5.3.1 "Ingress Correction" on page 4001 of
+	 * i.MX8MP Applications Processor Reference Manual Rev. 1, 06/2021
+	 */
+	val = readl(ioaddr + PTP_TCR);
+	if (val & PTP_TCR_TSCTRLSSR)
+		/* nanoseconds field is in decimal format with granularity of 1ns/bit */
+		scaled_ns = ((u64)NSEC_PER_SEC << 16) - scaled_ns;
+	else
+		/* nanoseconds field is in binary format with granularity of ~0.466ns/bit */
+		scaled_ns = ((1ULL << 31) << 16) -
+			DIV_U64_ROUND_CLOSEST(scaled_ns * PSEC_PER_NSEC, 466U);
+
+	reg_tsic = scaled_ns >> 16;
+	reg_tsicsns = scaled_ns & 0xff00;
+
+	/* set bit 31 for 2's compliment */
+	reg_tsic |= BIT(31);
+
+	writel(reg_tsic, ioaddr + PTP_TS_INGR_CORR_NS);
+	writel(reg_tsicsns, ioaddr + PTP_TS_INGR_CORR_SNS);
+
+	/* MAC-internal egress latency */
+	scaled_ns = readl(ioaddr + PTP_TS_EGR_LAT);
+
+	reg_tsec = scaled_ns >> 16;
+	reg_tsecsns = scaled_ns & 0xff00;
+
+	writel(reg_tsec, ioaddr + PTP_TS_EGR_CORR_NS);
+	writel(reg_tsecsns, ioaddr + PTP_TS_EGR_CORR_SNS);
+}
+
 static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec)
 {
 	u32 value;
@@ -221,4 +263,5 @@ const struct stmmac_hwtimestamp stmmac_ptp = {
 	.get_systime = get_systime,
 	.get_ptptime = get_ptptime,
 	.timestamp_interrupt = timestamp_interrupt,
+	.hwtstamp_correct_latency = hwtstamp_correct_latency,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index e1f1c034d3259..99aa5360b3ff9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -909,6 +909,9 @@ static int stmmac_init_ptp(struct stmmac_priv *priv)
 	priv->hwts_tx_en = 0;
 	priv->hwts_rx_en = 0;
 
+	if (priv->plat->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY)
+		stmmac_hwtstamp_correct_latency(priv, priv);
+
 	return 0;
 }
 
@@ -1094,6 +1097,9 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 
 	if (priv->dma_cap.fpesel)
 		stmmac_fpe_link_state_handle(priv, true);
+
+	if (priv->plat->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY)
+		stmmac_hwtstamp_correct_latency(priv, priv);
 }
 
 static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
index bf619295d079f..d1fe4b46f1629 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
@@ -26,6 +26,12 @@
 #define	PTP_ACR		0x40	/* Auxiliary Control Reg */
 #define	PTP_ATNR	0x48	/* Auxiliary Timestamp - Nanoseconds Reg */
 #define	PTP_ATSR	0x4c	/* Auxiliary Timestamp - Seconds Reg */
+#define	PTP_TS_INGR_CORR_NS	0x58	/* Ingress timestamp correction nanoseconds */
+#define	PTP_TS_EGR_CORR_NS	0x5C	/* Egress timestamp correction nanoseconds*/
+#define	PTP_TS_INGR_CORR_SNS	0x60	/* Ingress timestamp correction subnanoseconds */
+#define	PTP_TS_EGR_CORR_SNS	0x64	/* Egress timestamp correction subnanoseconds */
+#define	PTP_TS_INGR_LAT	0x68	/* MAC internal Ingress Latency */
+#define	PTP_TS_EGR_LAT	0x6c	/* MAC internal Egress Latency */
 
 #define	PTP_STNSUR_ADDSUB_SHIFT	31
 #define	PTP_DIGITAL_ROLLOVER_MODE	0x3B9ACA00	/* 10e9-1 ns */
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 3d07025102242..652404c03944b 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -218,6 +218,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_INT_SNAPSHOT_EN		BIT(9)
 #define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI		BIT(10)
 #define STMMAC_FLAG_EN_TX_LPI_CLOCKGATING	BIT(11)
+#define STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY	BIT(12)
 
 struct plat_stmmacenet_data {
 	int bus_id;
-- 
GitLab


From 6cb2e613c79653e40814152def7abec32efe0f29 Mon Sep 17 00:00:00 2001
From: Johannes Zink <j.zink@pengutronix.de>
Date: Tue, 1 Aug 2023 17:44:30 +0200
Subject: [PATCH 0942/1806] net: stmmac: dwmac-imx: enable MAC propagation
 delay correction for i.MX8MP

As the i.MX8MP supports reading MAC propagation delay and correcting the
Hardware timestamp counter for additional delays [1], enable the feature
for this SoC.

This reduces phase error of the PPS output from the PTP Hardware Clock
from approx 150ns to 100ns.

[1] i.MX8MP Reference Manual, rev.1 Section 11.7.2.5.3 "Timestamp
correction"

Signed-off-by: Johannes Zink <j.zink@pengutronix.de>
Link: https://lore.kernel.org/r/20230719-stmmac_correct_mac_delay-v3-2-61e63427735e@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 92e06a96757ac..645a9454a4904 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -42,6 +42,7 @@
 
 struct imx_dwmac_ops {
 	u32 addr_width;
+	u32 flags;
 	bool mac_rgmii_txclk_auto_adj;
 
 	int (*fix_soc_reset)(void *priv, void __iomem *ioaddr);
@@ -311,6 +312,9 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 		goto err_parse_dt;
 	}
 
+	if (data->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY)
+		plat_dat->flags |= STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY;
+
 	plat_dat->host_dma_width = dwmac->ops->addr_width;
 	plat_dat->init = imx_dwmac_init;
 	plat_dat->exit = imx_dwmac_exit;
@@ -350,6 +354,7 @@ static struct imx_dwmac_ops imx8mp_dwmac_data = {
 	.addr_width = 34,
 	.mac_rgmii_txclk_auto_adj = false,
 	.set_intf_mode = imx8mp_set_intf_mode,
+	.flags = STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY,
 };
 
 static struct imx_dwmac_ops imx8dxl_dwmac_data = {
-- 
GitLab


From 505a1fdadac1f10b436e8bbf9a63e4e0f7b63077 Mon Sep 17 00:00:00 2001
From: Wojciech Drewek <wojciech.drewek@intel.com>
Date: Thu, 27 Jul 2023 10:35:39 +0200
Subject: [PATCH 0943/1806] ice: Accept LAG netdevs in bridge offloads

Allow LAG interfaces to be used in bridge offload using
netif_is_lag_master. In this case, search for ice netdev in
the list of LAG's lower devices.

Reviewed-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_eswitch_br.c   | 47 +++++++++++++++++--
 1 file changed, 42 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
index cc7357ed6e5fb..67bfd1f61cdd4 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
@@ -20,8 +20,23 @@ static const struct rhashtable_params ice_fdb_ht_params = {
 
 static bool ice_eswitch_br_is_dev_valid(const struct net_device *dev)
 {
-	/* Accept only PF netdev and PRs */
-	return ice_is_port_repr_netdev(dev) || netif_is_ice(dev);
+	/* Accept only PF netdev, PRs and LAG */
+	return ice_is_port_repr_netdev(dev) || netif_is_ice(dev) ||
+		netif_is_lag_master(dev);
+}
+
+static struct net_device *
+ice_eswitch_br_get_uplink_from_lag(struct net_device *lag_dev)
+{
+	struct net_device *lower;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(lag_dev, lower, iter) {
+		if (netif_is_ice(lower))
+			return lower;
+	}
+
+	return NULL;
 }
 
 static struct ice_esw_br_port *
@@ -31,8 +46,19 @@ ice_eswitch_br_netdev_to_port(struct net_device *dev)
 		struct ice_repr *repr = ice_netdev_to_repr(dev);
 
 		return repr->br_port;
-	} else if (netif_is_ice(dev)) {
-		struct ice_pf *pf = ice_netdev_to_pf(dev);
+	} else if (netif_is_ice(dev) || netif_is_lag_master(dev)) {
+		struct net_device *ice_dev;
+		struct ice_pf *pf;
+
+		if (netif_is_lag_master(dev))
+			ice_dev = ice_eswitch_br_get_uplink_from_lag(dev);
+		else
+			ice_dev = dev;
+
+		if (!ice_dev)
+			return NULL;
+
+		pf = ice_netdev_to_pf(ice_dev);
 
 		return pf->br_port;
 	}
@@ -1085,7 +1111,18 @@ ice_eswitch_br_port_link(struct ice_esw_br_offloads *br_offloads,
 		err = ice_eswitch_br_vf_repr_port_init(bridge, repr);
 		trace_ice_eswitch_br_port_link(repr->br_port);
 	} else {
-		struct ice_pf *pf = ice_netdev_to_pf(dev);
+		struct net_device *ice_dev;
+		struct ice_pf *pf;
+
+		if (netif_is_lag_master(dev))
+			ice_dev = ice_eswitch_br_get_uplink_from_lag(dev);
+		else
+			ice_dev = dev;
+
+		if (!ice_dev)
+			return 0;
+
+		pf = ice_netdev_to_pf(ice_dev);
 
 		err = ice_eswitch_br_uplink_port_init(bridge, pf);
 		trace_ice_eswitch_br_port_link(pf->br_port);
-- 
GitLab


From 0960a27bd479fdff21c14ff449dac85f86d7eb4d Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@linux.intel.com>
Date: Thu, 22 Jun 2023 15:35:12 +0200
Subject: [PATCH 0944/1806] ice: Add direction metadata

Currently it is possible to create a filter which breaks TX traffic, e.g.:

tc filter add dev $PF1 ingress protocol ip prio 1 flower ip_proto udp
dst_port $PORT action mirred egress redirect dev $VF1_PR

This adds a rule which might match both TX and RX traffic, and in TX path
the PF will actually receive the traffic, which breaks communication.

To fix this, add a match on direction metadata flag when adding a tc rule.

Because of the way metadata is currently handled, a duplicate lookup word
would appear if VLAN metadata is also added. The lookup would still work
correctly, but one word would be wasted. To prevent it, lookup 0 now always
contains all metadata. When any metadata needs to be added, it is added to
lookup 0 and lookup count is not incremented. This way, two flags residing
in the same word will take up one word, instead of two.

Note: the drop action is also affected, i.e. it will now only work in one
direction.

Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../ethernet/intel/ice/ice_protocol_type.h    |  1 +
 drivers/net/ethernet/intel/ice/ice_switch.c   | 11 ++++--
 drivers/net/ethernet/intel/ice/ice_switch.h   |  1 +
 drivers/net/ethernet/intel/ice/ice_tc_lib.c   | 34 +++++++++----------
 4 files changed, 28 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
index 6a9364761165d..9812b98d107fd 100644
--- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
@@ -287,6 +287,7 @@ struct ice_nvgre_hdr {
  * M = EVLAN (0x8100) - Outer L2 header has EVLAN (ethernet type 0x8100)
  * N = EVLAN (0x9100) - Outer L2 header has EVLAN (ethernet type 0x9100)
  */
+#define ICE_PKT_FROM_NETWORK	BIT(3)
 #define ICE_PKT_VLAN_STAG	BIT(12)
 #define ICE_PKT_VLAN_ITAG	BIT(13)
 #define ICE_PKT_VLAN_EVLAN	(BIT(14) | BIT(15))
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 91bc92f5059b1..dcbb69bc9f5ac 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -6058,14 +6058,21 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw,
 void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup)
 {
 	lkup->type = ICE_HW_METADATA;
-	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_TUNNEL] =
+	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_TUNNEL] |=
 		cpu_to_be16(ICE_PKT_TUNNEL_MASK);
 }
 
+void ice_rule_add_direction_metadata(struct ice_adv_lkup_elem *lkup)
+{
+	lkup->type = ICE_HW_METADATA;
+	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_VLAN] |=
+		cpu_to_be16(ICE_PKT_FROM_NETWORK);
+}
+
 void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup)
 {
 	lkup->type = ICE_HW_METADATA;
-	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_VLAN] =
+	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_VLAN] |=
 		cpu_to_be16(ICE_PKT_VLAN_MASK);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index 250823ac173a9..0bd4320e39dfe 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -359,6 +359,7 @@ int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id);
 
 /* Switch/bridge related commands */
 void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup);
+void ice_rule_add_direction_metadata(struct ice_adv_lkup_elem *lkup);
 void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup);
 void ice_rule_add_src_vsi_metadata(struct ice_adv_lkup_elem *lkup);
 int
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index 38547db1ec4ec..37b54db91df27 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -7,6 +7,8 @@
 #include "ice_lib.h"
 #include "ice_protocol_type.h"
 
+#define ICE_TC_METADATA_LKUP_IDX 0
+
 /**
  * ice_tc_count_lkups - determine lookup count for switch filter
  * @flags: TC-flower flags
@@ -19,7 +21,13 @@ static int
 ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers,
 		   struct ice_tc_flower_fltr *fltr)
 {
-	int lkups_cnt = 0;
+	int lkups_cnt = 1; /* 0th lookup is metadata */
+
+	/* Always add metadata as the 0th lookup. Included elements:
+	 * - Direction flag (always present)
+	 * - ICE_TC_FLWR_FIELD_VLAN_TPID (present if specified)
+	 * - Tunnel flag (present if tunnel)
+	 */
 
 	if (flags & ICE_TC_FLWR_FIELD_TENANT_ID)
 		lkups_cnt++;
@@ -54,10 +62,6 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers,
 	if (flags & (ICE_TC_FLWR_FIELD_VLAN | ICE_TC_FLWR_FIELD_VLAN_PRIO))
 		lkups_cnt++;
 
-	/* is VLAN TPID specified */
-	if (flags & ICE_TC_FLWR_FIELD_VLAN_TPID)
-		lkups_cnt++;
-
 	/* is CVLAN specified? */
 	if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO))
 		lkups_cnt++;
@@ -84,10 +88,6 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers,
 		     ICE_TC_FLWR_FIELD_SRC_L4_PORT))
 		lkups_cnt++;
 
-	/* matching for tunneled packets in metadata */
-	if (fltr->tunnel_type != TNL_LAST)
-		lkups_cnt++;
-
 	return lkups_cnt;
 }
 
@@ -176,10 +176,9 @@ static u16 ice_check_supported_vlan_tpid(u16 vlan_tpid)
 
 static int
 ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr,
-			 struct ice_adv_lkup_elem *list)
+			 struct ice_adv_lkup_elem *list, int i)
 {
 	struct ice_tc_flower_lyr_2_4_hdrs *hdr = &fltr->outer_headers;
-	int i = 0;
 
 	if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) {
 		u32 tenant_id;
@@ -329,8 +328,7 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr,
 	}
 
 	/* always fill matching on tunneled packets in metadata */
-	ice_rule_add_tunnel_metadata(&list[i]);
-	i++;
+	ice_rule_add_tunnel_metadata(&list[ICE_TC_METADATA_LKUP_IDX]);
 
 	return i;
 }
@@ -358,13 +356,16 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags,
 	struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers;
 	bool inner = false;
 	u16 vlan_tpid = 0;
-	int i = 0;
+	int i = 1; /* 0th lookup is metadata */
 
 	rule_info->vlan_type = vlan_tpid;
 
+	/* Always add direction metadata */
+	ice_rule_add_direction_metadata(&list[ICE_TC_METADATA_LKUP_IDX]);
+
 	rule_info->tun_type = ice_sw_type_from_tunnel(tc_fltr->tunnel_type);
 	if (tc_fltr->tunnel_type != TNL_LAST) {
-		i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list);
+		i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i);
 
 		headers = &tc_fltr->inner_headers;
 		inner = true;
@@ -431,8 +432,7 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags,
 		rule_info->vlan_type =
 				ice_check_supported_vlan_tpid(vlan_tpid);
 
-		ice_rule_add_vlan_metadata(&list[i]);
-		i++;
+		ice_rule_add_vlan_metadata(&list[ICE_TC_METADATA_LKUP_IDX]);
 	}
 
 	if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) {
-- 
GitLab


From 41ad9f8ee6b8ec292f46b0a0bfaeace51e82a4eb Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@linux.intel.com>
Date: Thu, 22 Jun 2023 15:35:13 +0200
Subject: [PATCH 0945/1806] ice: Rename enum ice_pkt_flags values

enum ice_pkt_flags contains values such as ICE_PKT_FLAGS_VLAN and
ICE_PKT_FLAGS_TUNNEL, but actually the flags words which they refer to
contain a range of unrelated values - e.g. word 0 (ICE_PKT_FLAGS_VLAN)
contains fields such as from_network and ucast, which have nothing to do
with VLAN. Rename each enum value to ICE_PKT_FLAGS_MDID<number>, so it's
clear in which flags word does some value reside.

Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_protocol_type.h | 8 ++++----
 drivers/net/ethernet/intel/ice/ice_switch.c        | 6 +++---
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
index 9812b98d107fd..f6f27361c3cf7 100644
--- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
@@ -393,10 +393,10 @@ enum ice_hw_metadata_offset {
 };
 
 enum ice_pkt_flags {
-	ICE_PKT_FLAGS_VLAN = 0,
-	ICE_PKT_FLAGS_TUNNEL = 1,
-	ICE_PKT_FLAGS_TCP = 2,
-	ICE_PKT_FLAGS_ERROR = 3,
+	ICE_PKT_FLAGS_MDID20 = 0,
+	ICE_PKT_FLAGS_MDID21 = 1,
+	ICE_PKT_FLAGS_MDID22 = 2,
+	ICE_PKT_FLAGS_MDID23 = 3,
 };
 
 struct ice_hw_metadata {
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index dcbb69bc9f5ac..a7afb612fe32e 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -6058,21 +6058,21 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw,
 void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup)
 {
 	lkup->type = ICE_HW_METADATA;
-	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_TUNNEL] |=
+	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID21] |=
 		cpu_to_be16(ICE_PKT_TUNNEL_MASK);
 }
 
 void ice_rule_add_direction_metadata(struct ice_adv_lkup_elem *lkup)
 {
 	lkup->type = ICE_HW_METADATA;
-	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_VLAN] |=
+	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID20] |=
 		cpu_to_be16(ICE_PKT_FROM_NETWORK);
 }
 
 void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup)
 {
 	lkup->type = ICE_HW_METADATA;
-	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_VLAN] |=
+	lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID20] |=
 		cpu_to_be16(ICE_PKT_VLAN_MASK);
 }
 
-- 
GitLab


From 272ad7944a7bb17ee1060ff887402ce759823640 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Thu, 13 Jul 2023 15:21:23 +0200
Subject: [PATCH 0946/1806] ice: Add get C827 PHY index function

Add a function to find the C827 PHY node handle and return C827 PHY
index for the E810 products.

In order to bring this function to full functionality, some
helpers for this were written by Michal Michalik.

Co-developed-by: Michal Michalik <michal.michalik@intel.com>
Signed-off-by: Michal Michalik <michal.michalik@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_adminq_cmd.h   |  1 +
 drivers/net/ethernet/intel/ice/ice_common.c   | 62 +++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_common.h   |  1 +
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h   |  3 +
 4 files changed, 67 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index c0ad34b425312..1ad92f95d6bd2 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1404,6 +1404,7 @@ struct ice_aqc_get_link_topo {
 	struct ice_aqc_link_topo_addr addr;
 	u8 node_part_num;
 #define ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575	0x21
+#define ICE_AQC_GET_LINK_TOPO_NODE_NR_C827	0x31
 	u8 rsvd[9];
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index dade0a50299c3..ce3f0f2b0e357 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -5,6 +5,7 @@
 #include "ice_sched.h"
 #include "ice_adminq_cmd.h"
 #include "ice_flow.h"
+#include "ice_ptp_hw.h"
 
 #define ICE_PF_RESET_WAIT_COUNT	300
 
@@ -2661,6 +2662,67 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 	ice_recalc_port_limited_caps(hw, &dev_p->common_cap);
 }
 
+/**
+ * ice_aq_get_netlist_node
+ * @hw: pointer to the hw struct
+ * @cmd: get_link_topo AQ structure
+ * @node_part_number: output node part number if node found
+ * @node_handle: output node handle parameter if node found
+ */
+static int
+ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd,
+			u8 *node_part_number, u16 *node_handle)
+{
+	struct ice_aq_desc desc;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
+	desc.params.get_link_topo = *cmd;
+
+	if (ice_aq_send_cmd(hw, &desc, NULL, 0, NULL))
+		return -EIO;
+
+	if (node_handle)
+		*node_handle = le16_to_cpu(desc.params.get_link_topo.addr.handle);
+	if (node_part_number)
+		*node_part_number = desc.params.get_link_topo.node_part_num;
+
+	return 0;
+}
+
+/**
+ * ice_is_pf_c827 - check if pf contains c827 phy
+ * @hw: pointer to the hw struct
+ */
+bool ice_is_pf_c827(struct ice_hw *hw)
+{
+	struct ice_aqc_get_link_topo cmd = {};
+	u8 node_part_number;
+	u16 node_handle;
+	int status;
+
+	if (hw->mac_type != ICE_MAC_E810)
+		return false;
+
+	if (hw->device_id != ICE_DEV_ID_E810C_QSFP)
+		return true;
+
+	cmd.addr.topo_params.node_type_ctx =
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) |
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT);
+	cmd.addr.topo_params.index = 0;
+
+	status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number,
+					 &node_handle);
+
+	if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827)
+		return false;
+
+	if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE)
+		return true;
+
+	return false;
+}
+
 /**
  * ice_aq_list_caps - query function/device capabilities
  * @hw: pointer to the HW struct
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index df12a9d8d28ca..71b82cdf4a6d8 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -93,6 +93,7 @@ int
 ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 		    struct ice_aqc_get_phy_caps_data *caps,
 		    struct ice_sq_cd *cd);
+bool ice_is_pf_c827(struct ice_hw *hw);
 int
 ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count,
 		 enum ice_adminq_opc opc, struct ice_sq_cd *cd);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 3b68cb91bd819..1969425f00848 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -112,6 +112,9 @@ struct ice_cgu_pll_params_e822 {
 extern const struct
 ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ];
 
+#define E810C_QSFP_C827_0_HANDLE 2
+#define E810C_QSFP_C827_1_HANDLE 3
+
 /* Table of constants related to possible TIME_REF sources */
 extern const struct ice_time_ref_info_e822 e822_time_ref[NUM_ICE_TIME_REF_FREQ];
 
-- 
GitLab


From 5708155d902dc881dff7cb3b48098b45ea0847da Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Thu, 13 Jul 2023 15:21:24 +0200
Subject: [PATCH 0947/1806] ice: add FW load wait

As some cards load FW from external sources, we have to wait
to be sure that FW is ready before setting link up.

Add check and wait for FW readiness

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_hw_autogen.h   |  2 +
 drivers/net/ethernet/intel/ice/ice_main.c     | 37 +++++++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index a92dc9a160358..fb590b4c10539 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -335,6 +335,8 @@
 #define VP_MDET_TX_TCLAN_VALID_M		BIT(0)
 #define VP_MDET_TX_TDPU(_VF)			(0x00040000 + ((_VF) * 4))
 #define VP_MDET_TX_TDPU_VALID_M			BIT(0)
+#define GL_MNG_FWSM				0x000B6134
+#define GL_MNG_FWSM_FW_LOADING_M		BIT(30)
 #define GLNVM_FLA				0x000B6108
 #define GLNVM_FLA_LOCKED_M			BIT(6)
 #define GLNVM_GENS				0x000B6100
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 2e80d5cd9f567..0f04347eda39d 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4520,6 +4520,31 @@ static void ice_deinit_eth(struct ice_pf *pf)
 	ice_decfg_netdev(vsi);
 }
 
+/**
+ * ice_wait_for_fw - wait for full FW readiness
+ * @hw: pointer to the hardware structure
+ * @timeout: milliseconds that can elapse before timing out
+ */
+static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout)
+{
+	int fw_loading;
+	u32 elapsed = 0;
+
+	while (elapsed <= timeout) {
+		fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M;
+
+		/* firmware was not yet loaded, we have to wait more */
+		if (fw_loading) {
+			elapsed += 100;
+			msleep(100);
+			continue;
+		}
+		return 0;
+	}
+
+	return -ETIMEDOUT;
+}
+
 static int ice_init_dev(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
@@ -4532,6 +4557,18 @@ static int ice_init_dev(struct ice_pf *pf)
 		return err;
 	}
 
+	/* Some cards require longer initialization times
+	 * due to necessity of loading FW from an external source.
+	 * This can take even half a minute.
+	 */
+	if (ice_is_pf_c827(hw)) {
+		err = ice_wait_for_fw(hw, 30000);
+		if (err) {
+			dev_err(dev, "ice_wait_for_fw timed out");
+			return err;
+		}
+	}
+
 	ice_init_feature_support(pf);
 
 	ice_request_fw(pf);
-- 
GitLab


From b6143c9b073fb321d948b6647065748337918dd8 Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Wed, 7 Jun 2023 09:09:57 -0400
Subject: [PATCH 0948/1806] ice: clean up __ice_aq_get_set_rss_lut()

Refactor __ice_aq_get_set_rss_lut() to improve reader experience and limit
misuse scenarios (undesired LUT size for given LUT type).

Allow only 3 RSS LUT type+size variants:
PF LUT sized 2048, GLOBAL LUT sized 512, and VSI LUT sized 64, which were
used on default flows prior to this commit.

Prior to the change, code was mixing the meaning of @params->lut_size and
@params->lut_type, flag assigning logic was cryptic, while long defines
made everything harder to follow.

Fix that by extracting some code out to separate helpers.
Drop some of "shift by 0" statements that originated from Intel's
internal HW documentation.

Drop some redundant VSI masks (since ice_is_vsi_valid() gives "valid" for
up to 0x300 VSIs).

After sweeping all the defines out of struct ice_aqc_get_set_rss_lut,
it fits into 7 lines.

Finally apply some cleanup to the callsite
(use of the new enums, tmp var for lengthy bit extraction).

Note that flags for 128 and 64 sized VSI LUT are the same,
and 64 is used everywhere in the code (updated to new enum here), it just
happened that there was 128 in flag name.

__ice_aq_get_set_rss_key() uses the same VSI valid bit, make constant
common for it and __ice_aq_get_set_rss_lut().

Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Tested-by: Arpana Arland <arpanax.arland@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_adminq_cmd.h   |  53 +++----
 drivers/net/ethernet/intel/ice/ice_common.c   | 143 +++++++-----------
 .../net/ethernet/intel/ice/ice_hw_autogen.h   |   1 -
 drivers/net/ethernet/intel/ice/ice_lib.c      |  20 +--
 drivers/net/ethernet/intel/ice/ice_type.h     |   9 +-
 drivers/net/ethernet/intel/ice/ice_virtchnl.c |   6 +-
 6 files changed, 99 insertions(+), 133 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 1ad92f95d6bd2..29f7a9852aec6 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1794,11 +1794,10 @@ struct ice_aqc_lldp_filter_ctrl {
 	u8 reserved2[12];
 };
 
+#define ICE_AQC_RSS_VSI_VALID BIT(15)
+
 /* Get/Set RSS key (indirect 0x0B04/0x0B02) */
 struct ice_aqc_get_set_rss_key {
-#define ICE_AQC_GSET_RSS_KEY_VSI_VALID	BIT(15)
-#define ICE_AQC_GSET_RSS_KEY_VSI_ID_S	0
-#define ICE_AQC_GSET_RSS_KEY_VSI_ID_M	(0x3FF << ICE_AQC_GSET_RSS_KEY_VSI_ID_S)
 	__le16 vsi_id;
 	u8 reserved[6];
 	__le32 addr_high;
@@ -1816,35 +1815,33 @@ struct ice_aqc_get_set_rss_keys {
 	u8 extended_hash_key[ICE_AQC_GET_SET_RSS_KEY_DATA_HASH_KEY_SIZE];
 };
 
-/* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */
-struct ice_aqc_get_set_rss_lut {
-#define ICE_AQC_GSET_RSS_LUT_VSI_VALID	BIT(15)
-#define ICE_AQC_GSET_RSS_LUT_VSI_ID_S	0
-#define ICE_AQC_GSET_RSS_LUT_VSI_ID_M	(0x3FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S)
-	__le16 vsi_id;
-#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S	0
-#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M	\
-				(0x3 << ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S)
-
-#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI	 0
-#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF	 1
-#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL	 2
+enum ice_lut_type {
+	ICE_LUT_VSI = 0,
+	ICE_LUT_PF = 1,
+	ICE_LUT_GLOBAL = 2,
+};
 
-#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S	 2
-#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M	 \
-				(0x3 << ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S)
+enum ice_lut_size {
+	ICE_LUT_VSI_SIZE = 64,
+	ICE_LUT_GLOBAL_SIZE = 512,
+	ICE_LUT_PF_SIZE = 2048,
+};
 
-#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128	 128
-#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128_FLAG 0
-#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512	 512
-#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG 1
-#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K	 2048
-#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG	 2
+/* enum ice_aqc_lut_flags combines constants used to fill
+ * &ice_aqc_get_set_rss_lut ::flags, which is an amalgamation of global LUT ID,
+ * LUT size and LUT type, last of which does not need neither shift nor mask.
+ */
+enum ice_aqc_lut_flags {
+	ICE_AQC_LUT_SIZE_SMALL = 0, /* size = 64 or 128 */
+	ICE_AQC_LUT_SIZE_512 = BIT(2),
+	ICE_AQC_LUT_SIZE_2K = BIT(3),
 
-#define ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S	 4
-#define ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_M	 \
-				(0xF << ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S)
+	ICE_AQC_LUT_GLOBAL_IDX = GENMASK(7, 4),
+};
 
+/* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */
+struct ice_aqc_get_set_rss_lut {
+	__le16 vsi_id;
 	__le16 flags;
 	__le32 reserved;
 	__le32 addr_high;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index ce3f0f2b0e357..a86255b529a0c 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -3939,6 +3939,34 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 	return status;
 }
 
+static enum ice_lut_size ice_lut_type_to_size(enum ice_lut_type type)
+{
+	switch (type) {
+	case ICE_LUT_VSI:
+		return ICE_LUT_VSI_SIZE;
+	case ICE_LUT_GLOBAL:
+		return ICE_LUT_GLOBAL_SIZE;
+	case ICE_LUT_PF:
+		return ICE_LUT_PF_SIZE;
+	}
+	WARN_ONCE(1, "incorrect type passed");
+	return ICE_LUT_VSI_SIZE;
+}
+
+static enum ice_aqc_lut_flags ice_lut_size_to_flag(enum ice_lut_size size)
+{
+	switch (size) {
+	case ICE_LUT_VSI_SIZE:
+		return ICE_AQC_LUT_SIZE_SMALL;
+	case ICE_LUT_GLOBAL_SIZE:
+		return ICE_AQC_LUT_SIZE_512;
+	case ICE_LUT_PF_SIZE:
+		return ICE_AQC_LUT_SIZE_2K;
+	}
+	WARN_ONCE(1, "incorrect size passed");
+	return 0;
+}
+
 /**
  * __ice_aq_get_set_rss_lut
  * @hw: pointer to the hardware structure
@@ -3948,95 +3976,44 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
  * Internal function to get (0x0B05) or set (0x0B03) RSS look up table
  */
 static int
-__ice_aq_get_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *params, bool set)
-{
-	u16 flags = 0, vsi_id, lut_type, lut_size, glob_lut_idx, vsi_handle;
-	struct ice_aqc_get_set_rss_lut *cmd_resp;
+__ice_aq_get_set_rss_lut(struct ice_hw *hw,
+			 struct ice_aq_get_set_rss_lut_params *params, bool set)
+{
+	u16 opcode, vsi_id, vsi_handle = params->vsi_handle, glob_lut_idx = 0;
+	enum ice_lut_type lut_type = params->lut_type;
+	struct ice_aqc_get_set_rss_lut *desc_params;
+	enum ice_aqc_lut_flags flags;
+	enum ice_lut_size lut_size;
 	struct ice_aq_desc desc;
-	int status;
-	u8 *lut;
+	u8 *lut = params->lut;
 
-	if (!params)
-		return -EINVAL;
-
-	vsi_handle = params->vsi_handle;
-	lut = params->lut;
 
-	if (!ice_is_vsi_valid(hw, vsi_handle) || !lut)
+	if (!lut || !ice_is_vsi_valid(hw, vsi_handle))
 		return -EINVAL;
 
-	lut_size = params->lut_size;
-	lut_type = params->lut_type;
-	glob_lut_idx = params->global_lut_id;
-	vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
-
-	cmd_resp = &desc.params.get_set_rss_lut;
+	lut_size = ice_lut_type_to_size(lut_type);
+	if (lut_size > params->lut_size)
+		return -EINVAL;
+	else if (set && lut_size != params->lut_size)
+		return -EINVAL;
 
-	if (set) {
-		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_lut);
+	opcode = set ? ice_aqc_opc_set_rss_lut : ice_aqc_opc_get_rss_lut;
+	ice_fill_dflt_direct_cmd_desc(&desc, opcode);
+	if (set)
 		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-	} else {
-		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_lut);
-	}
 
-	cmd_resp->vsi_id = cpu_to_le16(((vsi_id <<
-					 ICE_AQC_GSET_RSS_LUT_VSI_ID_S) &
-					ICE_AQC_GSET_RSS_LUT_VSI_ID_M) |
-				       ICE_AQC_GSET_RSS_LUT_VSI_VALID);
-
-	switch (lut_type) {
-	case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI:
-	case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF:
-	case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL:
-		flags |= ((lut_type << ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S) &
-			  ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M);
-		break;
-	default:
-		status = -EINVAL;
-		goto ice_aq_get_set_rss_lut_exit;
-	}
+	desc_params = &desc.params.get_set_rss_lut;
+	vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
+	desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID);
 
-	if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL) {
-		flags |= ((glob_lut_idx << ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S) &
-			  ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_M);
+	if (lut_type == ICE_LUT_GLOBAL)
+		glob_lut_idx = FIELD_PREP(ICE_AQC_LUT_GLOBAL_IDX,
+					  params->global_lut_id);
 
-		if (!set)
-			goto ice_aq_get_set_rss_lut_send;
-	} else if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF) {
-		if (!set)
-			goto ice_aq_get_set_rss_lut_send;
-	} else {
-		goto ice_aq_get_set_rss_lut_send;
-	}
+	flags = lut_type | glob_lut_idx | ice_lut_size_to_flag(lut_size);
+	desc_params->flags = cpu_to_le16(flags);
 
-	/* LUT size is only valid for Global and PF table types */
-	switch (lut_size) {
-	case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128:
-		break;
-	case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512:
-		flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG <<
-			  ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) &
-			 ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M;
-		break;
-	case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K:
-		if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF) {
-			flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG <<
-				  ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) &
-				 ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M;
-			break;
-		}
-		fallthrough;
-	default:
-		status = -EINVAL;
-		goto ice_aq_get_set_rss_lut_exit;
-	}
-
-ice_aq_get_set_rss_lut_send:
-	cmd_resp->flags = cpu_to_le16(flags);
-	status = ice_aq_send_cmd(hw, &desc, lut, lut_size, NULL);
-
-ice_aq_get_set_rss_lut_exit:
-	return status;
+	return ice_aq_send_cmd(hw, &desc, lut, lut_size, NULL);
 }
 
 /**
@@ -4078,12 +4055,10 @@ static int
 __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id,
 			 struct ice_aqc_get_set_rss_keys *key, bool set)
 {
-	struct ice_aqc_get_set_rss_key *cmd_resp;
+	struct ice_aqc_get_set_rss_key *desc_params;
 	u16 key_size = sizeof(*key);
 	struct ice_aq_desc desc;
 
-	cmd_resp = &desc.params.get_set_rss_key;
-
 	if (set) {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_key);
 		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
@@ -4091,10 +4066,8 @@ __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id,
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_key);
 	}
 
-	cmd_resp->vsi_id = cpu_to_le16(((vsi_id <<
-					 ICE_AQC_GSET_RSS_KEY_VSI_ID_S) &
-					ICE_AQC_GSET_RSS_KEY_VSI_ID_M) |
-				       ICE_AQC_GSET_RSS_KEY_VSI_VALID);
+	desc_params = &desc.params.get_set_rss_key;
+	desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID);
 
 	return ice_aq_send_cmd(hw, &desc, key, key_size, NULL);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index fb590b4c10539..531cc2194741e 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -491,7 +491,6 @@
 #define VSIQF_FD_CNT_FD_BCNT_M			ICE_M(0x3FFF, 16)
 #define VSIQF_FD_SIZE(_VSI)			(0x00462000 + ((_VSI) * 4))
 #define VSIQF_HKEY_MAX_INDEX			12
-#define VSIQF_HLUT_MAX_INDEX			15
 #define PFPM_APM				0x000B8080
 #define PFPM_APM_APME_M				BIT(0)
 #define PFPM_WUFC				0x0009DC00
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 077f2e91ae1a1..927518fcad51c 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -907,6 +907,7 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
 {
 	struct ice_hw_common_caps *cap;
 	struct ice_pf *pf = vsi->back;
+	u16 max_rss_size;
 
 	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
 		vsi->rss_size = 1;
@@ -914,32 +915,31 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
 	}
 
 	cap = &pf->hw.func_caps.common_cap;
+	max_rss_size = BIT(cap->rss_table_entry_width);
 	switch (vsi->type) {
 	case ICE_VSI_CHNL:
 	case ICE_VSI_PF:
 		/* PF VSI will inherit RSS instance of PF */
 		vsi->rss_table_size = (u16)cap->rss_table_size;
 		if (vsi->type == ICE_VSI_CHNL)
-			vsi->rss_size = min_t(u16, vsi->num_rxq,
-					      BIT(cap->rss_table_entry_width));
+			vsi->rss_size = min_t(u16, vsi->num_rxq, max_rss_size);
 		else
 			vsi->rss_size = min_t(u16, num_online_cpus(),
-					      BIT(cap->rss_table_entry_width));
-		vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF;
+					      max_rss_size);
+		vsi->rss_lut_type = ICE_LUT_PF;
 		break;
 	case ICE_VSI_SWITCHDEV_CTRL:
-		vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE;
-		vsi->rss_size = min_t(u16, num_online_cpus(),
-				      BIT(cap->rss_table_entry_width));
-		vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI;
+		vsi->rss_table_size = ICE_LUT_VSI_SIZE;
+		vsi->rss_size = min_t(u16, num_online_cpus(), max_rss_size);
+		vsi->rss_lut_type = ICE_LUT_VSI;
 		break;
 	case ICE_VSI_VF:
 		/* VF VSI will get a small RSS table.
 		 * For VSI_LUT, LUT size should be set to 64 bytes.
 		 */
-		vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE;
+		vsi->rss_table_size = ICE_LUT_VSI_SIZE;
 		vsi->rss_size = ICE_MAX_RSS_QS_PER_VF;
-		vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI;
+		vsi->rss_lut_type = ICE_LUT_VSI;
 		break;
 	case ICE_VSI_LB:
 		break;
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index e82f38c2a9402..5e353b0cbe6f7 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -1040,10 +1040,10 @@ enum ice_sw_fwd_act_type {
 };
 
 struct ice_aq_get_set_rss_lut_params {
-	u16 vsi_handle;		/* software VSI handle */
-	u16 lut_size;		/* size of the LUT buffer */
-	u8 lut_type;		/* type of the LUT (i.e. VSI, PF, Global) */
 	u8 *lut;		/* input RSS LUT for set and output RSS LUT for get */
+	enum ice_lut_size lut_size; /* size of the LUT buffer */
+	enum ice_lut_type lut_type; /* type of the LUT (i.e. VSI, PF, Global) */
+	u16 vsi_handle;		/* software VSI handle */
 	u8 global_lut_id;	/* only valid when lut_type is global */
 };
 
@@ -1145,9 +1145,6 @@ struct ice_aq_get_set_rss_lut_params {
 
 #define ICE_SR_WORDS_IN_1KB		512
 
-/* Hash redirection LUT for VSI - maximum array size */
-#define ICE_VSIQF_HLUT_ARRAY_SIZE	((VSIQF_HLUT_MAX_INDEX + 1) * 4)
-
 /* AQ API version for LLDP_FILTER_CONTROL */
 #define ICE_FW_API_LLDP_FLTR_MAJ	1
 #define ICE_FW_API_LLDP_FLTR_MIN	7
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 625da88e79659..85d9965315021 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -500,7 +500,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	vfres->num_queue_pairs = vsi->num_txq;
 	vfres->max_vectors = vf->pf->vfs.num_msix_per;
 	vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE;
-	vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE;
+	vfres->rss_lut_size = ICE_LUT_VSI_SIZE;
 	vfres->max_mtu = ice_vc_get_max_frame_size(vf);
 
 	vfres->vsi_res[0].vsi_id = vf->lan_vsi_num;
@@ -962,7 +962,7 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
-	if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) {
+	if (vrl->lut_entries != ICE_LUT_VSI_SIZE) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
@@ -978,7 +978,7 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
-	if (ice_set_rss_lut(vsi, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE))
+	if (ice_set_rss_lut(vsi, vrl->lut, ICE_LUT_VSI_SIZE))
 		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
 error_param:
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, v_ret,
-- 
GitLab


From a9ca9f9ceff382b58b488248f0c0da9e157f5d06 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 4 Aug 2023 20:05:24 +0200
Subject: [PATCH 0949/1806] page_pool: split types and declarations from
 page_pool.h

Split types and pure function declarations from page_pool.h
and add them in page_page/types.h, so that C sources can
include page_pool.h and headers should generally only include
page_pool/types.h as suggested by jakub.
Rename page_pool.h to page_pool/helpers.h to have both in
one place.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-2-aleksander.lobakin@intel.com
[Jakub: change microsoft/mana, fix kdoc paths in Documentation]
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/page_pool.rst        |   6 +-
 MAINTAINERS                                   |   2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     |   2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c |   2 +-
 drivers/net/ethernet/engleder/tsnep_main.c    |   1 +
 drivers/net/ethernet/freescale/fec_main.c     |   1 +
 .../net/ethernet/hisilicon/hns3/hns3_enet.c   |   1 +
 .../net/ethernet/hisilicon/hns3/hns3_enet.h   |   2 +-
 drivers/net/ethernet/marvell/mvneta.c         |   2 +-
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h    |   2 +-
 .../net/ethernet/marvell/mvpp2/mvpp2_main.c   |   1 +
 .../marvell/octeontx2/nic/otx2_common.c       |   1 +
 .../ethernet/marvell/octeontx2/nic/otx2_pf.c  |   1 +
 drivers/net/ethernet/mediatek/mtk_eth_soc.c   |   1 +
 drivers/net/ethernet/mediatek/mtk_eth_soc.h   |   2 +-
 .../ethernet/mellanox/mlx5/core/en/params.c   |   1 +
 .../net/ethernet/mellanox/mlx5/core/en/trap.c |   1 -
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c  |   1 +
 .../net/ethernet/mellanox/mlx5/core/en_main.c |   2 +-
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   |   2 +-
 .../ethernet/mellanox/mlx5/core/en_stats.c    |   2 +-
 .../ethernet/microchip/lan966x/lan966x_fdma.c |   1 +
 .../ethernet/microchip/lan966x/lan966x_main.h |   2 +-
 drivers/net/ethernet/microsoft/mana/mana_en.c |   1 +
 drivers/net/ethernet/socionext/netsec.c       |   2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac.h  |   2 +-
 .../net/ethernet/stmicro/stmmac/stmmac_main.c |   1 +
 drivers/net/ethernet/ti/cpsw.c                |   2 +-
 drivers/net/ethernet/ti/cpsw_new.c            |   2 +-
 drivers/net/ethernet/ti/cpsw_priv.c           |   2 +-
 drivers/net/ethernet/wangxun/libwx/wx_lib.c   |   2 +-
 drivers/net/veth.c                            |   2 +-
 drivers/net/wireless/mediatek/mt76/mac80211.c |   1 -
 drivers/net/wireless/mediatek/mt76/mt76.h     |   1 +
 drivers/net/xen-netfront.c                    |   2 +-
 include/linux/skbuff.h                        |   2 +-
 .../net/{page_pool.h => page_pool/helpers.h}  | 242 +-----------------
 include/net/page_pool/types.h                 | 238 +++++++++++++++++
 include/trace/events/page_pool.h              |   2 +-
 net/bpf/test_run.c                            |   2 +-
 net/core/page_pool.c                          |   2 +-
 net/core/skbuff.c                             |   2 +-
 net/core/xdp.c                                |   2 +-
 43 files changed, 284 insertions(+), 267 deletions(-)
 rename include/net/{page_pool.h => page_pool/helpers.h} (51%)
 create mode 100644 include/net/page_pool/types.h

diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst
index 53b5448cc0f11..68b82cea13e43 100644
--- a/Documentation/networking/page_pool.rst
+++ b/Documentation/networking/page_pool.rst
@@ -67,10 +67,10 @@ a page will cause no race conditions is enough.
 .. kernel-doc:: net/core/page_pool.c
    :identifiers: page_pool_create
 
-.. kernel-doc:: include/net/page_pool.h
+.. kernel-doc:: include/net/page_pool/types.h
    :identifiers: struct page_pool_params
 
-.. kernel-doc:: include/net/page_pool.h
+.. kernel-doc:: include/net/page_pool/helpers.h
    :identifiers: page_pool_put_page page_pool_put_full_page
 		 page_pool_recycle_direct page_pool_dev_alloc_pages
 		 page_pool_get_dma_addr page_pool_get_dma_dir
@@ -122,7 +122,7 @@ page_pool_stats allocated by the caller.
 The API will fill in the provided struct page_pool_stats with
 statistics about the page_pool.
 
-.. kernel-doc:: include/net/page_pool.h
+.. kernel-doc:: include/net/page_pool/types.h
    :identifiers: struct page_pool_recycle_stats
 		 struct page_pool_alloc_stats
 		 struct page_pool_stats
diff --git a/MAINTAINERS b/MAINTAINERS
index 5e2bb1059ab67..08bcf3a7c482d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16020,7 +16020,7 @@ M:	Ilias Apalodimas <ilias.apalodimas@linaro.org>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/page_pool.rst
-F:	include/net/page_pool.h
+F:	include/net/page_pool/
 F:	include/trace/events/page_pool.h
 F:	net/core/page_pool.c
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6a643aae78028..eb168ca983b75 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -54,7 +54,7 @@
 #include <net/pkt_cls.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include <linux/align.h>
 #include <net/netdev_queues.h>
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 2ce46d7affe4a..96f5ca778c67d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -15,7 +15,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/filter.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_xdp.h"
diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 079f9f6ae21ae..f61bd89734c58 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -28,6 +28,7 @@
 #include <linux/iopoll.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
+#include <net/page_pool/helpers.h>
 #include <net/xdp_sock_drv.h>
 
 #define TSNEP_RX_OFFSET (max(NET_SKB_PAD, XDP_PACKET_HEADROOM) + NET_IP_ALIGN)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 43f14cec91e93..3bd0bf03aedbf 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -38,6 +38,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <net/ip.h>
+#include <net/page_pool/helpers.h>
 #include <net/selftests.h>
 #include <net/tso.h>
 #include <linux/tcp.h>
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 9f6890059666e..e5e37a33fd819 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -18,6 +18,7 @@
 #include <net/gre.h>
 #include <net/gro.h>
 #include <net/ip6_checksum.h>
+#include <net/page_pool/helpers.h>
 #include <net/pkt_cls.h>
 #include <net/pkt_sched.h>
 #include <net/tcp.h>
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 88af34bbee34b..acd756b0c7c9a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -6,7 +6,7 @@
 
 #include <linux/dim.h>
 #include <linux/if_vlan.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 #include <asm/barrier.h>
 
 #include "hnae3.h"
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index acf4f6ba73a6f..d483b8c00ec0e 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -37,7 +37,7 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/tso.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include <net/pkt_sched.h>
 #include <linux/bpf_trace.h>
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 11e603686a276..e809f91c08fb9 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -16,7 +16,7 @@
 #include <linux/phy.h>
 #include <linux/phylink.h>
 #include <net/flow_offload.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 #include <linux/bpf.h>
 #include <net/xdp.h>
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 9e1b596c8f088..eb74ccddb4409 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -35,6 +35,7 @@
 #include <uapi/linux/ppp_defs.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
+#include <net/page_pool/helpers.h>
 #include <net/tso.h>
 #include <linux/bpf_trace.h>
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 8cdd92dd97628..8336cea16aff0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -7,6 +7,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/pci.h>
+#include <net/page_pool/helpers.h>
 #include <net/tso.h>
 #include <linux/bitfield.h>
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 61f62a6ec6627..70b9065f7d101 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -16,6 +16,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/bitfield.h>
+#include <net/page_pool/types.h>
 
 #include "otx2_reg.h"
 #include "otx2_common.h"
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 1b89f800f6dff..fe05c90202699 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -26,6 +26,7 @@
 #include <linux/bitfield.h>
 #include <net/dsa.h>
 #include <net/dst_metadata.h>
+#include <net/page_pool/helpers.h>
 
 #include "mtk_eth_soc.h"
 #include "mtk_wed.h"
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 80d17729e5578..4a2470fbad2cf 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -18,7 +18,7 @@
 #include <linux/rhashtable.h>
 #include <linux/dim.h>
 #include <linux/bitfield.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 #include <linux/bpf_trace.h>
 #include "mtk_ppe.h"
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 5ce28ff7685fc..e097f336e1c4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -6,6 +6,7 @@
 #include "en/port.h"
 #include "en_accel/en_accel.h"
 #include "en_accel/ipsec.h"
+#include <net/page_pool/types.h>
 #include <net/xdp_sock_drv.h>
 
 static u8 mlx5e_mpwrq_min_page_shift(struct mlx5_core_dev *mdev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 201ac7dd338f0..698647cc8c0f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2020 Mellanox Technologies */
 
-#include <net/page_pool.h>
 #include "en/txrx.h"
 #include "en/params.h"
 #include "en/trap.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 40589cebb7730..12f56d0db0af2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -35,6 +35,7 @@
 #include "en/xdp.h"
 #include "en/params.h"
 #include <linux/bitfield.h>
+#include <net/page_pool/helpers.h>
 
 int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1c820119e438f..c8ec6467d4d16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -38,7 +38,7 @@
 #include <linux/debugfs.h>
 #include <linux/if_bridge.h>
 #include <linux/filter.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 #include <net/pkt_sched.h>
 #include <net/xdp_sock_drv.h>
 #include "eswitch.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index f7bb5f4aaaca0..3fd11b0761e09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -36,7 +36,7 @@
 #include <linux/bitmap.h>
 #include <linux/filter.h>
 #include <net/ip6_checksum.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include <net/inet_ecn.h>
 #include <net/gro.h>
 #include <net/udp.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 4d77055abd4be..07b84d668fcc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -38,7 +38,7 @@
 #include "en/port.h"
 
 #ifdef CONFIG_PAGE_POOL_STATS
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #endif
 
 static unsigned int stats_grps_num(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index bd72fbc2220f3..3960534ac2ad8 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -2,6 +2,7 @@
 
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <net/page_pool/helpers.h>
 
 #include "lan966x_main.h"
 
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index aebc9154693af..caa9e0533c96b 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -10,7 +10,7 @@
 #include <linux/phy.h>
 #include <linux/phylink.h>
 #include <linux/ptp_clock_kernel.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 #include <net/pkt_cls.h>
 #include <net/pkt_sched.h>
 #include <net/switchdev.h>
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index a08023c57e25e..31e2f2c74e15a 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -11,6 +11,7 @@
 
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
+#include <net/page_pool/helpers.h>
 #include <net/xdp.h>
 
 #include <net/mana/mana.h>
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 0dcd6a568b061..f358ea0031936 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -15,7 +15,7 @@
 #include <linux/bpf_trace.h>
 
 #include <net/tcp.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include <net/ip6_checksum.h>
 
 #define NETSEC_REG_SOFT_RST			0x104
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index a6d034968654d..3401e888a9f68 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -21,7 +21,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/net_tstamp.h>
 #include <linux/reset.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 #include <net/xdp.h>
 #include <uapi/linux/bpf.h>
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 99aa5360b3ff9..fcab363d8dfa2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -39,6 +39,7 @@
 #include <linux/phylink.h>
 #include <linux/udp.h>
 #include <linux/bpf_trace.h>
+#include <net/page_pool/helpers.h>
 #include <net/pkt_cls.h>
 #include <net/xdp_sock_drv.h>
 #include "stmmac_ptp.h"
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index f9cd566d1c9b5..ca4d4548f85e3 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -31,7 +31,7 @@
 #include <linux/if_vlan.h>
 #include <linux/kmemleak.h>
 #include <linux/sys_soc.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index c61e4e44a78f0..0e4f526b17532 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -30,7 +30,7 @@
 #include <linux/sys_soc.h>
 
 #include <net/switchdev.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include <net/pkt_cls.h>
 #include <net/devlink.h>
 
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index ae52cdbcf8cc5..0ec85635dfd60 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -18,7 +18,7 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/skbuff.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include <net/pkt_cls.h>
 #include <net/pkt_sched.h>
 
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 2c3f08be8c374..e04d4a5eed7ba 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -3,7 +3,7 @@
 
 #include <linux/etherdevice.h>
 #include <net/ip6_checksum.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include <net/inet_ecn.h>
 #include <linux/iopoll.h>
 #include <linux/sctp.h>
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 614f3e3efab09..953f6d8f8db04 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -26,7 +26,7 @@
 #include <linux/ptr_ring.h>
 #include <linux/bpf_trace.h>
 #include <linux/net_tstamp.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 
 #define DRV_NAME	"veth"
 #define DRV_VERSION	"1.0"
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index c0ff36a98bed3..d158320bc15db 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -4,7 +4,6 @@
  */
 #include <linux/sched.h>
 #include <linux/of.h>
-#include <net/page_pool.h>
 #include "mt76.h"
 
 #define CHAN2G(_idx, _freq) {			\
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 878087257ea7e..e8757865a3d06 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -15,6 +15,7 @@
 #include <linux/average.h>
 #include <linux/soc/mediatek/mtk_wed.h>
 #include <net/mac80211.h>
+#include <net/page_pool/helpers.h>
 #include "util.h"
 #include "testmode.h"
 
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 47d54d8ea59d1..ad29f370034e4 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -45,7 +45,7 @@
 #include <linux/slab.h>
 #include <net/ip.h>
 #include <linux/bpf.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 #include <linux/bpf_trace.h>
 
 #include <xen/xen.h>
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 16a49ba534e4a..888e3d7e74c1f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -32,7 +32,7 @@
 #include <linux/if_packet.h>
 #include <linux/llist.h>
 #include <net/flow.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <linux/netfilter/nf_conntrack_common.h>
 #endif
diff --git a/include/net/page_pool.h b/include/net/page_pool/helpers.h
similarity index 51%
rename from include/net/page_pool.h
rename to include/net/page_pool/helpers.h
index 73d4f786418d5..78df91804c878 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool/helpers.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0
  *
- * page_pool.h
+ * page_pool/helpers.h
  *	Author:	Jesper Dangaard Brouer <netoptimizer@brouer.com>
  *	Copyright (C) 2016 Red Hat, Inc.
  */
@@ -26,126 +26,12 @@
  * will release the DMA mapping and in-flight state accounting.  We
  * hope to lift this requirement in the future.
  */
-#ifndef _NET_PAGE_POOL_H
-#define _NET_PAGE_POOL_H
+#ifndef _NET_PAGE_POOL_HELPERS_H
+#define _NET_PAGE_POOL_HELPERS_H
 
-#include <linux/mm.h> /* Needed by ptr_ring */
-#include <linux/ptr_ring.h>
-#include <linux/dma-direction.h>
-
-#define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
-					* map/unmap
-					*/
-#define PP_FLAG_DMA_SYNC_DEV	BIT(1) /* If set all pages that the driver gets
-					* from page_pool will be
-					* DMA-synced-for-device according to
-					* the length provided by the device
-					* driver.
-					* Please note DMA-sync-for-CPU is still
-					* device driver responsibility
-					*/
-#define PP_FLAG_PAGE_FRAG	BIT(2) /* for page frag feature */
-#define PP_FLAG_ALL		(PP_FLAG_DMA_MAP |\
-				 PP_FLAG_DMA_SYNC_DEV |\
-				 PP_FLAG_PAGE_FRAG)
-
-/*
- * Fast allocation side cache array/stack
- *
- * The cache size and refill watermark is related to the network
- * use-case.  The NAPI budget is 64 packets.  After a NAPI poll the RX
- * ring is usually refilled and the max consumed elements will be 64,
- * thus a natural max size of objects needed in the cache.
- *
- * Keeping room for more objects, is due to XDP_DROP use-case.  As
- * XDP_DROP allows the opportunity to recycle objects directly into
- * this array, as it shares the same softirq/NAPI protection.  If
- * cache is already full (or partly full) then the XDP_DROP recycles
- * would have to take a slower code path.
- */
-#define PP_ALLOC_CACHE_SIZE	128
-#define PP_ALLOC_CACHE_REFILL	64
-struct pp_alloc_cache {
-	u32 count;
-	struct page *cache[PP_ALLOC_CACHE_SIZE];
-};
-
-/**
- * struct page_pool_params - page pool parameters
- * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_PAGE_FRAG
- * @order:	2^order pages on allocation
- * @pool_size:	size of the ptr_ring
- * @nid:	NUMA node id to allocate from pages from
- * @dev:	device, for DMA pre-mapping purposes
- * @napi:	NAPI which is the sole consumer of pages, otherwise NULL
- * @dma_dir:	DMA mapping direction
- * @max_len:	max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV
- * @offset:	DMA sync address offset for PP_FLAG_DMA_SYNC_DEV
- */
-struct page_pool_params {
-	unsigned int	flags;
-	unsigned int	order;
-	unsigned int	pool_size;
-	int		nid;
-	struct device	*dev;
-	struct napi_struct *napi;
-	enum dma_data_direction dma_dir;
-	unsigned int	max_len;
-	unsigned int	offset;
-/* private: used by test code only */
-	void (*init_callback)(struct page *page, void *arg);
-	void *init_arg;
-};
+#include <net/page_pool/types.h>
 
 #ifdef CONFIG_PAGE_POOL_STATS
-/**
- * struct page_pool_alloc_stats - allocation statistics
- * @fast:	successful fast path allocations
- * @slow:	slow path order-0 allocations
- * @slow_high_order: slow path high order allocations
- * @empty:	ptr ring is empty, so a slow path allocation was forced
- * @refill:	an allocation which triggered a refill of the cache
- * @waive:	pages obtained from the ptr ring that cannot be added to
- *		the cache due to a NUMA mismatch
- */
-struct page_pool_alloc_stats {
-	u64 fast;
-	u64 slow;
-	u64 slow_high_order;
-	u64 empty;
-	u64 refill;
-	u64 waive;
-};
-
-/**
- * struct page_pool_recycle_stats - recycling (freeing) statistics
- * @cached:	recycling placed page in the page pool cache
- * @cache_full:	page pool cache was full
- * @ring:	page placed into the ptr ring
- * @ring_full:	page released from page pool because the ptr ring was full
- * @released_refcnt:	page released (and not recycled) because refcnt > 1
- */
-struct page_pool_recycle_stats {
-	u64 cached;
-	u64 cache_full;
-	u64 ring;
-	u64 ring_full;
-	u64 released_refcnt;
-};
-
-/**
- * struct page_pool_stats - combined page pool use statistics
- * @alloc_stats:	see struct page_pool_alloc_stats
- * @recycle_stats:	see struct page_pool_recycle_stats
- *
- * Wrapper struct for combining page pool stats with different storage
- * requirements.
- */
-struct page_pool_stats {
-	struct page_pool_alloc_stats alloc_stats;
-	struct page_pool_recycle_stats recycle_stats;
-};
-
 int page_pool_ethtool_stats_get_count(void);
 u8 *page_pool_ethtool_stats_get_strings(u8 *data);
 u64 *page_pool_ethtool_stats_get(u64 *data, void *stats);
@@ -158,7 +44,6 @@ u64 *page_pool_ethtool_stats_get(u64 *data, void *stats);
 bool page_pool_get_stats(struct page_pool *pool,
 			 struct page_pool_stats *stats);
 #else
-
 static inline int page_pool_ethtool_stats_get_count(void)
 {
 	return 0;
@@ -173,72 +58,7 @@ static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats)
 {
 	return data;
 }
-
-#endif
-
-struct page_pool {
-	struct page_pool_params p;
-
-	struct delayed_work release_dw;
-	void (*disconnect)(void *);
-	unsigned long defer_start;
-	unsigned long defer_warn;
-
-	u32 pages_state_hold_cnt;
-	unsigned int frag_offset;
-	struct page *frag_page;
-	long frag_users;
-
-#ifdef CONFIG_PAGE_POOL_STATS
-	/* these stats are incremented while in softirq context */
-	struct page_pool_alloc_stats alloc_stats;
 #endif
-	u32 xdp_mem_id;
-
-	/*
-	 * Data structure for allocation side
-	 *
-	 * Drivers allocation side usually already perform some kind
-	 * of resource protection.  Piggyback on this protection, and
-	 * require driver to protect allocation side.
-	 *
-	 * For NIC drivers this means, allocate a page_pool per
-	 * RX-queue. As the RX-queue is already protected by
-	 * Softirq/BH scheduling and napi_schedule. NAPI schedule
-	 * guarantee that a single napi_struct will only be scheduled
-	 * on a single CPU (see napi_schedule).
-	 */
-	struct pp_alloc_cache alloc ____cacheline_aligned_in_smp;
-
-	/* Data structure for storing recycled pages.
-	 *
-	 * Returning/freeing pages is more complicated synchronization
-	 * wise, because free's can happen on remote CPUs, with no
-	 * association with allocation resource.
-	 *
-	 * Use ptr_ring, as it separates consumer and producer
-	 * effeciently, it a way that doesn't bounce cache-lines.
-	 *
-	 * TODO: Implement bulk return pages into this structure.
-	 */
-	struct ptr_ring ring;
-
-#ifdef CONFIG_PAGE_POOL_STATS
-	/* recycle stats are per-cpu to avoid locking */
-	struct page_pool_recycle_stats __percpu *recycle_stats;
-#endif
-	atomic_t pages_state_release_cnt;
-
-	/* A page_pool is strictly tied to a single RX-queue being
-	 * protected by NAPI, due to above pp_alloc_cache. This
-	 * refcnt serves purpose is to simplify drivers error handling.
-	 */
-	refcount_t user_cnt;
-
-	u64 destroy_cnt;
-};
-
-struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
 
 /**
  * page_pool_dev_alloc_pages() - allocate a page.
@@ -253,9 +73,6 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool)
 	return page_pool_alloc_pages(pool, gfp);
 }
 
-struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset,
-				  unsigned int size, gfp_t gfp);
-
 static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool,
 						    unsigned int *offset,
 						    unsigned int size)
@@ -278,44 +95,6 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
 	return pool->p.dma_dir;
 }
 
-bool page_pool_return_skb_page(struct page *page, bool napi_safe);
-
-struct page_pool *page_pool_create(const struct page_pool_params *params);
-
-struct xdp_mem_info;
-
-#ifdef CONFIG_PAGE_POOL
-void page_pool_unlink_napi(struct page_pool *pool);
-void page_pool_destroy(struct page_pool *pool);
-void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
-			   struct xdp_mem_info *mem);
-void page_pool_put_page_bulk(struct page_pool *pool, void **data,
-			     int count);
-#else
-static inline void page_pool_unlink_napi(struct page_pool *pool)
-{
-}
-
-static inline void page_pool_destroy(struct page_pool *pool)
-{
-}
-
-static inline void page_pool_use_xdp_mem(struct page_pool *pool,
-					 void (*disconnect)(void *),
-					 struct xdp_mem_info *mem)
-{
-}
-
-static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
-					   int count)
-{
-}
-#endif
-
-void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
-				  unsigned int dma_sync_size,
-				  bool allow_direct);
-
 /* pp_frag_count represents the number of writers who can update the page
  * either by updating skb->data or via DMA mappings for the device.
  * We can't rely on the page refcnt for that as we don't know who might be
@@ -445,26 +224,15 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
 		page->dma_addr_upper = upper_32_bits(addr);
 }
 
-static inline bool is_page_pool_compiled_in(void)
-{
-#ifdef CONFIG_PAGE_POOL
-	return true;
-#else
-	return false;
-#endif
-}
-
 static inline bool page_pool_put(struct page_pool *pool)
 {
 	return refcount_dec_and_test(&pool->user_cnt);
 }
 
-/* Caller must provide appropriate safe context, e.g. NAPI. */
-void page_pool_update_nid(struct page_pool *pool, int new_nid);
 static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid)
 {
 	if (unlikely(pool->p.nid != new_nid))
 		page_pool_update_nid(pool, new_nid);
 }
 
-#endif /* _NET_PAGE_POOL_H */
+#endif /* _NET_PAGE_POOL_HELPERS_H */
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
new file mode 100644
index 0000000000000..9ac39191bed72
--- /dev/null
+++ b/include/net/page_pool/types.h
@@ -0,0 +1,238 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _NET_PAGE_POOL_TYPES_H
+#define _NET_PAGE_POOL_TYPES_H
+
+#include <linux/dma-direction.h>
+#include <linux/ptr_ring.h>
+
+#define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
+					* map/unmap
+					*/
+#define PP_FLAG_DMA_SYNC_DEV	BIT(1) /* If set all pages that the driver gets
+					* from page_pool will be
+					* DMA-synced-for-device according to
+					* the length provided by the device
+					* driver.
+					* Please note DMA-sync-for-CPU is still
+					* device driver responsibility
+					*/
+#define PP_FLAG_PAGE_FRAG	BIT(2) /* for page frag feature */
+#define PP_FLAG_ALL		(PP_FLAG_DMA_MAP |\
+				 PP_FLAG_DMA_SYNC_DEV |\
+				 PP_FLAG_PAGE_FRAG)
+
+/*
+ * Fast allocation side cache array/stack
+ *
+ * The cache size and refill watermark is related to the network
+ * use-case.  The NAPI budget is 64 packets.  After a NAPI poll the RX
+ * ring is usually refilled and the max consumed elements will be 64,
+ * thus a natural max size of objects needed in the cache.
+ *
+ * Keeping room for more objects, is due to XDP_DROP use-case.  As
+ * XDP_DROP allows the opportunity to recycle objects directly into
+ * this array, as it shares the same softirq/NAPI protection.  If
+ * cache is already full (or partly full) then the XDP_DROP recycles
+ * would have to take a slower code path.
+ */
+#define PP_ALLOC_CACHE_SIZE	128
+#define PP_ALLOC_CACHE_REFILL	64
+struct pp_alloc_cache {
+	u32 count;
+	struct page *cache[PP_ALLOC_CACHE_SIZE];
+};
+
+/**
+ * struct page_pool_params - page pool parameters
+ * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_PAGE_FRAG
+ * @order:	2^order pages on allocation
+ * @pool_size:	size of the ptr_ring
+ * @nid:	NUMA node id to allocate from pages from
+ * @dev:	device, for DMA pre-mapping purposes
+ * @napi:	NAPI which is the sole consumer of pages, otherwise NULL
+ * @dma_dir:	DMA mapping direction
+ * @max_len:	max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV
+ * @offset:	DMA sync address offset for PP_FLAG_DMA_SYNC_DEV
+ */
+struct page_pool_params {
+	unsigned int	flags;
+	unsigned int	order;
+	unsigned int	pool_size;
+	int		nid;
+	struct device	*dev;
+	struct napi_struct *napi;
+	enum dma_data_direction dma_dir;
+	unsigned int	max_len;
+	unsigned int	offset;
+/* private: used by test code only */
+	void (*init_callback)(struct page *page, void *arg);
+	void *init_arg;
+};
+
+#ifdef CONFIG_PAGE_POOL_STATS
+/**
+ * struct page_pool_alloc_stats - allocation statistics
+ * @fast:	successful fast path allocations
+ * @slow:	slow path order-0 allocations
+ * @slow_high_order: slow path high order allocations
+ * @empty:	ptr ring is empty, so a slow path allocation was forced
+ * @refill:	an allocation which triggered a refill of the cache
+ * @waive:	pages obtained from the ptr ring that cannot be added to
+ *		the cache due to a NUMA mismatch
+ */
+struct page_pool_alloc_stats {
+	u64 fast;
+	u64 slow;
+	u64 slow_high_order;
+	u64 empty;
+	u64 refill;
+	u64 waive;
+};
+
+/**
+ * struct page_pool_recycle_stats - recycling (freeing) statistics
+ * @cached:	recycling placed page in the page pool cache
+ * @cache_full:	page pool cache was full
+ * @ring:	page placed into the ptr ring
+ * @ring_full:	page released from page pool because the ptr ring was full
+ * @released_refcnt:	page released (and not recycled) because refcnt > 1
+ */
+struct page_pool_recycle_stats {
+	u64 cached;
+	u64 cache_full;
+	u64 ring;
+	u64 ring_full;
+	u64 released_refcnt;
+};
+
+/**
+ * struct page_pool_stats - combined page pool use statistics
+ * @alloc_stats:	see struct page_pool_alloc_stats
+ * @recycle_stats:	see struct page_pool_recycle_stats
+ *
+ * Wrapper struct for combining page pool stats with different storage
+ * requirements.
+ */
+struct page_pool_stats {
+	struct page_pool_alloc_stats alloc_stats;
+	struct page_pool_recycle_stats recycle_stats;
+};
+#endif
+
+struct page_pool {
+	struct page_pool_params p;
+
+	struct delayed_work release_dw;
+	void (*disconnect)(void *pool);
+	unsigned long defer_start;
+	unsigned long defer_warn;
+
+	u32 pages_state_hold_cnt;
+	unsigned int frag_offset;
+	struct page *frag_page;
+	long frag_users;
+
+#ifdef CONFIG_PAGE_POOL_STATS
+	/* these stats are incremented while in softirq context */
+	struct page_pool_alloc_stats alloc_stats;
+#endif
+	u32 xdp_mem_id;
+
+	/*
+	 * Data structure for allocation side
+	 *
+	 * Drivers allocation side usually already perform some kind
+	 * of resource protection.  Piggyback on this protection, and
+	 * require driver to protect allocation side.
+	 *
+	 * For NIC drivers this means, allocate a page_pool per
+	 * RX-queue. As the RX-queue is already protected by
+	 * Softirq/BH scheduling and napi_schedule. NAPI schedule
+	 * guarantee that a single napi_struct will only be scheduled
+	 * on a single CPU (see napi_schedule).
+	 */
+	struct pp_alloc_cache alloc ____cacheline_aligned_in_smp;
+
+	/* Data structure for storing recycled pages.
+	 *
+	 * Returning/freeing pages is more complicated synchronization
+	 * wise, because free's can happen on remote CPUs, with no
+	 * association with allocation resource.
+	 *
+	 * Use ptr_ring, as it separates consumer and producer
+	 * efficiently, it a way that doesn't bounce cache-lines.
+	 *
+	 * TODO: Implement bulk return pages into this structure.
+	 */
+	struct ptr_ring ring;
+
+#ifdef CONFIG_PAGE_POOL_STATS
+	/* recycle stats are per-cpu to avoid locking */
+	struct page_pool_recycle_stats __percpu *recycle_stats;
+#endif
+	atomic_t pages_state_release_cnt;
+
+	/* A page_pool is strictly tied to a single RX-queue being
+	 * protected by NAPI, due to above pp_alloc_cache. This
+	 * refcnt serves purpose is to simplify drivers error handling.
+	 */
+	refcount_t user_cnt;
+
+	u64 destroy_cnt;
+};
+
+struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
+struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset,
+				  unsigned int size, gfp_t gfp);
+bool page_pool_return_skb_page(struct page *page, bool napi_safe);
+
+struct page_pool *page_pool_create(const struct page_pool_params *params);
+
+struct xdp_mem_info;
+
+#ifdef CONFIG_PAGE_POOL
+void page_pool_unlink_napi(struct page_pool *pool);
+void page_pool_destroy(struct page_pool *pool);
+void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
+			   struct xdp_mem_info *mem);
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+			     int count);
+#else
+static inline void page_pool_unlink_napi(struct page_pool *pool)
+{
+}
+
+static inline void page_pool_destroy(struct page_pool *pool)
+{
+}
+
+static inline void page_pool_use_xdp_mem(struct page_pool *pool,
+					 void (*disconnect)(void *),
+					 struct xdp_mem_info *mem)
+{
+}
+
+static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+					   int count)
+{
+}
+#endif
+
+void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
+				  unsigned int dma_sync_size,
+				  bool allow_direct);
+
+static inline bool is_page_pool_compiled_in(void)
+{
+#ifdef CONFIG_PAGE_POOL
+	return true;
+#else
+	return false;
+#endif
+}
+
+/* Caller must provide appropriate safe context, e.g. NAPI. */
+void page_pool_update_nid(struct page_pool *pool, int new_nid);
+
+#endif /* _NET_PAGE_POOL_H */
diff --git a/include/trace/events/page_pool.h b/include/trace/events/page_pool.h
index ca534501158b7..6834356b2d2ae 100644
--- a/include/trace/events/page_pool.h
+++ b/include/trace/events/page_pool.h
@@ -9,7 +9,7 @@
 #include <linux/tracepoint.h>
 
 #include <trace/events/mmflags.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 
 TRACE_EVENT(page_pool_release,
 
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 0aac76c13fd4a..57a7a64b84ede 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -15,7 +15,7 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <net/net_namespace.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include <linux/error-injection.h>
 #include <linux/smp.h>
 #include <linux/sock_diag.h>
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 5d615a1697187..cd28c1f14002b 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/device.h>
 
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 #include <net/xdp.h>
 
 #include <linux/dma-direction.h>
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c6f98245582cd..d3bed964123c9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -73,7 +73,7 @@
 #include <net/mpls.h>
 #include <net/mptcp.h>
 #include <net/mctp.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 #include <net/dropreason.h>
 
 #include <linux/uaccess.h>
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 8362130bf085d..a70670fe9a2dc 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -14,7 +14,7 @@
 #include <linux/idr.h>
 #include <linux/rhashtable.h>
 #include <linux/bug.h>
-#include <net/page_pool.h>
+#include <net/page_pool/helpers.h>
 
 #include <net/xdp.h>
 #include <net/xdp_priv.h> /* struct xdp_mem_allocator */
-- 
GitLab


From 75eaf63ea7afeafd026ffef03bdc69e31f10829b Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Fri, 4 Aug 2023 20:05:25 +0200
Subject: [PATCH 0950/1806] net: skbuff: don't include <net/page_pool/types.h>
 to <linux/skbuff.h>

Currently, touching <net/page_pool/types.h> triggers a rebuild of more
than half of the kernel. That's because it's included in
<linux/skbuff.h>. And each new include to page_pool/types.h adds more
[useless] data for the toolchain to process per each source file from
that pile.

In commit 6a5bcd84e886 ("page_pool: Allow drivers to hint on SKB
recycling"), Matteo included it to be able to call a couple of functions
defined there. Then, in commit 57f05bc2ab24 ("page_pool: keep pp info as
long as page pool owns the page") one of the calls was removed, so only
one was left. It's the call to page_pool_return_skb_page() in
napi_frag_unref(). The function is external and doesn't have any
dependencies. Having very niche page_pool_types.h included only for that
looks like an overkill.

As %PP_SIGNATURE is not local to page_pool.c (was only in the
early submissions), nothing holds this function there. Teleport
page_pool_return_skb_page() to skbuff.c, just next to the main consumer,
skb_pp_recycle(), and rename it to napi_pp_put_page(), as it doesn't
work with skbs at all and the former name tells nothing. The #if guards
here are only to not compile and have it in the vmlinux when not needed
-- both call sites are already guarded.
Now, touching page_pool_types.h only triggers rebuilding of the drivers
using it and a couple of core networking files.

Suggested-by: Jakub Kicinski <kuba@kernel.org> # make skbuff.h less heavy
Suggested-by: Alexander Duyck <alexanderduyck@fb.com> # move to skbuff.c
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-3-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h        |  5 ++--
 include/net/page_pool/types.h |  2 --
 net/core/page_pool.c          | 39 ------------------------------
 net/core/skbuff.c             | 45 +++++++++++++++++++++++++++++++++--
 4 files changed, 46 insertions(+), 45 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 888e3d7e74c1f..aa57e2eca33be 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -32,7 +32,6 @@
 #include <linux/if_packet.h>
 #include <linux/llist.h>
 #include <net/flow.h>
-#include <net/page_pool/types.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <linux/netfilter/nf_conntrack_common.h>
 #endif
@@ -3421,13 +3420,15 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f)
 	__skb_frag_ref(&skb_shinfo(skb)->frags[f]);
 }
 
+bool napi_pp_put_page(struct page *page, bool napi_safe);
+
 static inline void
 napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe)
 {
 	struct page *page = skb_frag_page(frag);
 
 #ifdef CONFIG_PAGE_POOL
-	if (recycle && page_pool_return_skb_page(page, napi_safe))
+	if (recycle && napi_pp_put_page(page, napi_safe))
 		return;
 #endif
 	put_page(page);
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 9ac39191bed72..fcb8465233980 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -185,8 +185,6 @@ struct page_pool {
 struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
 struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset,
 				  unsigned int size, gfp_t gfp);
-bool page_pool_return_skb_page(struct page *page, bool napi_safe);
-
 struct page_pool *page_pool_create(const struct page_pool_params *params);
 
 struct xdp_mem_info;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index cd28c1f14002b..03ad74d259593 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -935,42 +935,3 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid)
 	}
 }
 EXPORT_SYMBOL(page_pool_update_nid);
-
-bool page_pool_return_skb_page(struct page *page, bool napi_safe)
-{
-	struct napi_struct *napi;
-	struct page_pool *pp;
-	bool allow_direct;
-
-	page = compound_head(page);
-
-	/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
-	 * in order to preserve any existing bits, such as bit 0 for the
-	 * head page of compound page and bit 1 for pfmemalloc page, so
-	 * mask those bits for freeing side when doing below checking,
-	 * and page_is_pfmemalloc() is checked in __page_pool_put_page()
-	 * to avoid recycling the pfmemalloc page.
-	 */
-	if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE))
-		return false;
-
-	pp = page->pp;
-
-	/* Allow direct recycle if we have reasons to believe that we are
-	 * in the same context as the consumer would run, so there's
-	 * no possible race.
-	 */
-	napi = READ_ONCE(pp->p.napi);
-	allow_direct = napi_safe && napi &&
-		READ_ONCE(napi->list_owner) == smp_processor_id();
-
-	/* Driver set this to memory recycling info. Reset it on recycle.
-	 * This will *not* work for NIC using a split-page memory model.
-	 * The page will be returned to the pool here regardless of the
-	 * 'flipped' fragment being in use or not.
-	 */
-	page_pool_put_full_page(pp, page, allow_direct);
-
-	return true;
-}
-EXPORT_SYMBOL(page_pool_return_skb_page);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d3bed964123c9..acc5844a0de14 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -73,7 +73,7 @@
 #include <net/mpls.h>
 #include <net/mptcp.h>
 #include <net/mctp.h>
-#include <net/page_pool/types.h>
+#include <net/page_pool/helpers.h>
 #include <net/dropreason.h>
 
 #include <linux/uaccess.h>
@@ -879,11 +879,52 @@ static void skb_clone_fraglist(struct sk_buff *skb)
 		skb_get(list);
 }
 
+#if IS_ENABLED(CONFIG_PAGE_POOL)
+bool napi_pp_put_page(struct page *page, bool napi_safe)
+{
+	struct napi_struct *napi;
+	struct page_pool *pp;
+	bool allow_direct;
+
+	page = compound_head(page);
+
+	/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
+	 * in order to preserve any existing bits, such as bit 0 for the
+	 * head page of compound page and bit 1 for pfmemalloc page, so
+	 * mask those bits for freeing side when doing below checking,
+	 * and page_is_pfmemalloc() is checked in __page_pool_put_page()
+	 * to avoid recycling the pfmemalloc page.
+	 */
+	if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE))
+		return false;
+
+	pp = page->pp;
+
+	/* Allow direct recycle if we have reasons to believe that we are
+	 * in the same context as the consumer would run, so there's
+	 * no possible race.
+	 */
+	napi = READ_ONCE(pp->p.napi);
+	allow_direct = napi_safe && napi &&
+		READ_ONCE(napi->list_owner) == smp_processor_id();
+
+	/* Driver set this to memory recycling info. Reset it on recycle.
+	 * This will *not* work for NIC using a split-page memory model.
+	 * The page will be returned to the pool here regardless of the
+	 * 'flipped' fragment being in use or not.
+	 */
+	page_pool_put_full_page(pp, page, allow_direct);
+
+	return true;
+}
+EXPORT_SYMBOL(napi_pp_put_page);
+#endif
+
 static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe)
 {
 	if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle)
 		return false;
-	return page_pool_return_skb_page(virt_to_page(data), napi_safe);
+	return napi_pp_put_page(virt_to_page(data), napi_safe);
 }
 
 static void skb_kfree_head(void *head, unsigned int end_offset)
-- 
GitLab


From 06d0fbdad612cb8def19065cf1fa14fc34dba9f8 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Fri, 4 Aug 2023 20:05:26 +0200
Subject: [PATCH 0951/1806] page_pool: place frag_* fields in one cacheline

On x86_64, frag_* fields of struct page_pool are scattered across two
cachelines despite the summary size of 24 bytes. All three fields are
used in pretty much the same places, but the last field, ::frag_users,
is pushed out to the next CL, provoking unwanted false-sharing on
hotpath (frags allocation code).
There are some holes and cold members to move around. Move frag_* one
block up, placing them right after &page_pool_params perfectly at the
beginning of CL2. This doesn't do any meaningful to the second block, as
those are some destroy-path cold structures, and doesn't do anything to
::alloc_stats, which still starts at 200-byte offset, 8 bytes after CL3
(still fitting into 1 cacheline).
On my setup, this yields 1-2% of Mpps when using PP frags actively.
When it comes to 32-bit architectures with 32-byte CL: &page_pool_params
plus ::pad is 44 bytes, the block taken care of is 16 bytes within one
CL, so there should be at least no regressions from the actual change.
::pages_state_hold_cnt is not related directly to that triple, but is
paired currently with ::frags_offset and decoupling them would mean
either two 4-byte holes or more invasive layout changes.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-4-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/types.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index fcb8465233980..887e7946a5974 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -123,16 +123,16 @@ struct page_pool_stats {
 struct page_pool {
 	struct page_pool_params p;
 
+	long frag_users;
+	struct page *frag_page;
+	unsigned int frag_offset;
+	u32 pages_state_hold_cnt;
+
 	struct delayed_work release_dw;
 	void (*disconnect)(void *pool);
 	unsigned long defer_start;
 	unsigned long defer_warn;
 
-	u32 pages_state_hold_cnt;
-	unsigned int frag_offset;
-	struct page *frag_page;
-	long frag_users;
-
 #ifdef CONFIG_PAGE_POOL_STATS
 	/* these stats are incremented while in softirq context */
 	struct page_pool_alloc_stats alloc_stats;
-- 
GitLab


From 5b899c33b3b852b9559b724cfee67801324a0886 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Fri, 4 Aug 2023 20:05:27 +0200
Subject: [PATCH 0952/1806] net: skbuff: avoid accessing page_pool if
 !napi_safe when returning page

Currently, pp->p.napi is always read, but the actual variable it gets
assigned to is read-only when @napi_safe is true. For the !napi_safe
cases, which yet is still a pack, it's an unneeded operation.
Moreover, it can lead to premature or even redundant page_pool
cacheline access. For example, when page_pool_is_last_frag() returns
false (with the recent frag improvements).
Thus, read it only when @napi_safe is true. This also allows moving
@napi inside the condition block itself. Constify it while we are
here, because why not.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-5-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skbuff.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index acc5844a0de14..85f82a6a08dc7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -882,9 +882,8 @@ static void skb_clone_fraglist(struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_PAGE_POOL)
 bool napi_pp_put_page(struct page *page, bool napi_safe)
 {
-	struct napi_struct *napi;
+	bool allow_direct = false;
 	struct page_pool *pp;
-	bool allow_direct;
 
 	page = compound_head(page);
 
@@ -904,9 +903,12 @@ bool napi_pp_put_page(struct page *page, bool napi_safe)
 	 * in the same context as the consumer would run, so there's
 	 * no possible race.
 	 */
-	napi = READ_ONCE(pp->p.napi);
-	allow_direct = napi_safe && napi &&
-		READ_ONCE(napi->list_owner) == smp_processor_id();
+	if (napi_safe) {
+		const struct napi_struct *napi = READ_ONCE(pp->p.napi);
+
+		allow_direct = napi &&
+			READ_ONCE(napi->list_owner) == smp_processor_id();
+	}
 
 	/* Driver set this to memory recycling info. Reset it on recycle.
 	 * This will *not* work for NIC using a split-page memory model.
-- 
GitLab


From ff4e538c8c3e675a15e1e49509c55951832e0451 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 4 Aug 2023 20:05:28 +0200
Subject: [PATCH 0953/1806] page_pool: add a lockdep check for recycling in
 hardirq

Page pool use in hardirq is prohibited, add debug checks
to catch misuses. IIRC we previously discussed using
DEBUG_NET_WARN_ON_ONCE() for this, but there were concerns
that people will have DEBUG_NET enabled in perf testing.
I don't think anyone enables lockdep in perf testing,
so use lockdep to avoid pushback and arguing :)

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-6-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/lockdep.h | 7 +++++++
 net/core/page_pool.c    | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 310f85903c91a..dc2844b071c2c 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -625,6 +625,12 @@ do {									\
 	WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirq_context)); \
 } while (0)
 
+#define lockdep_assert_no_hardirq()					\
+do {									\
+	WARN_ON_ONCE(__lockdep_enabled && (this_cpu_read(hardirq_context) || \
+					   !this_cpu_read(hardirqs_enabled))); \
+} while (0)
+
 #define lockdep_assert_preemption_enabled()				\
 do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
@@ -659,6 +665,7 @@ do {									\
 # define lockdep_assert_irqs_enabled() do { } while (0)
 # define lockdep_assert_irqs_disabled() do { } while (0)
 # define lockdep_assert_in_irq() do { } while (0)
+# define lockdep_assert_no_hardirq() do { } while (0)
 
 # define lockdep_assert_preemption_enabled() do { } while (0)
 # define lockdep_assert_preemption_disabled() do { } while (0)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 03ad74d259593..77cb75e63aca1 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -587,6 +587,8 @@ static __always_inline struct page *
 __page_pool_put_page(struct page_pool *pool, struct page *page,
 		     unsigned int dma_sync_size, bool allow_direct)
 {
+	lockdep_assert_no_hardirq();
+
 	/* This allocator is optimized for the XDP mode that uses
 	 * one-frame-per-page, but have fallbacks that act like the
 	 * regular page allocator APIs.
-- 
GitLab


From 4a36d0180c452c3482792e0ff14e2bcf536a9284 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Fri, 4 Aug 2023 20:05:29 +0200
Subject: [PATCH 0954/1806] net: skbuff: always try to recycle PP pages
 directly when in softirq

Commit 8c48eea3adf3 ("page_pool: allow caching from safely localized
NAPI") allowed direct recycling of skb pages to their PP for some cases,
but unfortunately missed a couple of other majors.
For example, %XDP_DROP in skb mode. The netstack just calls kfree_skb(),
which unconditionally passes `false` as @napi_safe. Thus, all pages go
through ptr_ring and locks, although most of time we're actually inside
the NAPI polling this PP is linked with, so that it would be perfectly
safe to recycle pages directly.
Let's address such. If @napi_safe is true, we're fine, don't change
anything for this path. But if it's false, check whether we are in the
softirq context. It will most likely be so and then if ->list_owner
is our current CPU, we're good to use direct recycling, even though
@napi_safe is false -- concurrent access is excluded. in_softirq()
protection is needed mostly due to we can hit this place in the
process context (not the hardirq though).
For the mentioned xdp-drop-skb-mode case, the improvement I got is
3-4% in Mpps. As for page_pool stats, recycle_ring is now 0 and
alloc_slow counter doesn't change most of time, which means the
MM layer is not even called to allocate any new pages.

Suggested-by: Jakub Kicinski <kuba@kernel.org> # in_softirq()
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-7-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skbuff.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 85f82a6a08dc7..33fdf04d4334d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -902,8 +902,10 @@ bool napi_pp_put_page(struct page *page, bool napi_safe)
 	/* Allow direct recycle if we have reasons to believe that we are
 	 * in the same context as the consumer would run, so there's
 	 * no possible race.
+	 * __page_pool_put_page() makes sure we're not in hardirq context
+	 * and interrupts are enabled prior to accessing the cache.
 	 */
-	if (napi_safe) {
+	if (napi_safe || in_softirq()) {
 		const struct napi_struct *napi = READ_ONCE(pp->p.napi);
 
 		allow_direct = napi &&
-- 
GitLab


From 2369e52657d371c58da0b826f8b87f01611cfc59 Mon Sep 17 00:00:00 2001
From: Will Hawkins <hawkinsw@obs.cr>
Date: Mon, 7 Aug 2023 10:06:48 -0400
Subject: [PATCH 0955/1806] bpf, docs: Formalize type notation and function
 semantics in ISA standard

Give a single place where the shorthand for types are defined and the
semantics of helper functions are described.

Signed-off-by: Will Hawkins <hawkinsw@obs.cr>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/r/20230807140651.122484-1-hawkinsw@obs.cr
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../bpf/standardization/instruction-set.rst   | 82 +++++++++++++++++--
 1 file changed, 74 insertions(+), 8 deletions(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 655494ac7af6a..25be958130dc8 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -10,9 +10,71 @@ This document specifies version 1.0 of the eBPF instruction set.
 Documentation conventions
 =========================
 
-For brevity, this document uses the type notion "u64", "u32", etc.
-to mean an unsigned integer whose width is the specified number of bits,
-and "s32", etc. to mean a signed integer of the specified number of bits.
+For brevity and consistency, this document refers to families
+of types using a shorthand syntax and refers to several expository,
+mnemonic functions when describing the semantics of instructions.
+The range of valid values for those types and the semantics of those
+functions are defined in the following subsections.
+
+Types
+-----
+This document refers to integer types with the notation `SN` to specify
+a type's signedness (`S`) and bit width (`N`), respectively.
+
+.. table:: Meaning of signedness notation.
+
+  ==== =========
+  `S`  Meaning
+  ==== =========
+  `u`  unsigned
+  `s`  signed
+  ==== =========
+
+.. table:: Meaning of bit-width notation.
+
+  ===== =========
+  `N`   Bit width
+  ===== =========
+  `8`   8 bits
+  `16`  16 bits
+  `32`  32 bits
+  `64`  64 bits
+  `128` 128 bits
+  ===== =========
+
+For example, `u32` is a type whose valid values are all the 32-bit unsigned
+numbers and `s16` is a types whose valid values are all the 16-bit signed
+numbers.
+
+Functions
+---------
+* `htobe16`: Takes an unsigned 16-bit number in host-endian format and
+  returns the equivalent number as an unsigned 16-bit number in big-endian
+  format.
+* `htobe32`: Takes an unsigned 32-bit number in host-endian format and
+  returns the equivalent number as an unsigned 32-bit number in big-endian
+  format.
+* `htobe64`: Takes an unsigned 64-bit number in host-endian format and
+  returns the equivalent number as an unsigned 64-bit number in big-endian
+  format.
+* `htole16`: Takes an unsigned 16-bit number in host-endian format and
+  returns the equivalent number as an unsigned 16-bit number in little-endian
+  format.
+* `htole32`: Takes an unsigned 32-bit number in host-endian format and
+  returns the equivalent number as an unsigned 32-bit number in little-endian
+  format.
+* `htole64`: Takes an unsigned 64-bit number in host-endian format and
+  returns the equivalent number as an unsigned 64-bit number in little-endian
+  format.
+* `bswap16`: Takes an unsigned 16-bit number in either big- or little-endian
+  format and returns the equivalent number with the same bit width but
+  opposite endianness.
+* `bswap32`: Takes an unsigned 32-bit number in either big- or little-endian
+  format and returns the equivalent number with the same bit width but
+  opposite endianness.
+* `bswap64`: Takes an unsigned 64-bit number in either big- or little-endian
+  format and returns the equivalent number with the same bit width but
+  opposite endianness.
 
 Registers and calling convention
 ================================
@@ -252,19 +314,23 @@ are supported: 16, 32 and 64.
 
 Examples:
 
-``BPF_ALU | BPF_TO_LE | BPF_END`` with imm = 16 means::
+``BPF_ALU | BPF_TO_LE | BPF_END`` with imm = 16/32/64 means::
 
   dst = htole16(dst)
+  dst = htole32(dst)
+  dst = htole64(dst)
 
-``BPF_ALU | BPF_TO_BE | BPF_END`` with imm = 64 means::
+``BPF_ALU | BPF_TO_BE | BPF_END`` with imm = 16/32/64 means::
 
+  dst = htobe16(dst)
+  dst = htobe32(dst)
   dst = htobe64(dst)
 
 ``BPF_ALU64 | BPF_TO_LE | BPF_END`` with imm = 16/32/64 means::
 
-  dst = bswap16 dst
-  dst = bswap32 dst
-  dst = bswap64 dst
+  dst = bswap16(dst)
+  dst = bswap32(dst)
+  dst = bswap64(dst)
 
 Jump instructions
 -----------------
-- 
GitLab


From db2baf82b098aa10ac16f34e44732ec450fb11c7 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Mon, 7 Aug 2023 10:57:21 -0700
Subject: [PATCH 0956/1806] bpf: Fix an incorrect verification success with
 movsx insn

syzbot reports a verifier bug which triggers a runtime panic.
The test bpf program is:
   0: (62) *(u32 *)(r10 -8) = 553656332
   1: (bf) r1 = (s16)r10
   2: (07) r1 += -8
   3: (b7) r2 = 3
   4: (bd) if r2 <= r1 goto pc+0
   5: (85) call bpf_trace_printk#-138320
   6: (b7) r0 = 0
   7: (95) exit

At insn 1, the current implementation keeps 'r1' as a frame pointer,
which caused later bpf_trace_printk helper call crash since frame
pointer address is not valid any more. Note that at insn 4,
the 'pointer vs. scalar' comparison is allowed for privileged
prog run.

To fix the problem with above insn 1, the fix in the patch adopts
similar pattern to existing 'R1 = (u32) R2' handling. For unprivileged
prog run, verification will fail with 'R<num> sign-extension part of pointer'.
For privileged prog run, the dst_reg 'r1' will be marked as
an unknown scalar, so later 'bpf_trace_pointk' helper will complain
since it expected certain pointers.

Reported-by: syzbot+d61b595e9205573133b3@syzkaller.appspotmail.com
Fixes: 8100928c8814 ("bpf: Support new sign-extension mov insns")
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20230807175721.671696-1-yonghong.song@linux.dev
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/verifier.c | 31 ++++++++++++++++++++-----------
 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 132f25dab9318..4ccca1f6c9981 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -13165,17 +13165,26 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 					dst_reg->subreg_def = DEF_NOT_SUBREG;
 				} else {
 					/* case: R1 = (s8, s16 s32)R2 */
-					bool no_sext;
-
-					no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
-					if (no_sext && need_id)
-						src_reg->id = ++env->id_gen;
-					copy_register_state(dst_reg, src_reg);
-					if (!no_sext)
-						dst_reg->id = 0;
-					coerce_reg_to_size_sx(dst_reg, insn->off >> 3);
-					dst_reg->live |= REG_LIVE_WRITTEN;
-					dst_reg->subreg_def = DEF_NOT_SUBREG;
+					if (is_pointer_value(env, insn->src_reg)) {
+						verbose(env,
+							"R%d sign-extension part of pointer\n",
+							insn->src_reg);
+						return -EACCES;
+					} else if (src_reg->type == SCALAR_VALUE) {
+						bool no_sext;
+
+						no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+						if (no_sext && need_id)
+							src_reg->id = ++env->id_gen;
+						copy_register_state(dst_reg, src_reg);
+						if (!no_sext)
+							dst_reg->id = 0;
+						coerce_reg_to_size_sx(dst_reg, insn->off >> 3);
+						dst_reg->live |= REG_LIVE_WRITTEN;
+						dst_reg->subreg_def = DEF_NOT_SUBREG;
+					} else {
+						mark_reg_unknown(env, regs, insn->dst_reg);
+					}
 				}
 			} else {
 				/* R1 = (u32) R2 */
-- 
GitLab


From a5c0a42bd3746091777642d0588102a3a42ac031 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Mon, 7 Aug 2023 10:57:26 -0700
Subject: [PATCH 0957/1806] selftests/bpf: Add a movsx selftest for
 sign-extension of R10

A movsx selftest is added for sign-extension of frame pointer R10.
The verification fails for both privileged and unprivileged
prog runs.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230807175726.672394-1-yonghong.song@linux.dev
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/progs/verifier_movsx.c      | 22 +++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
index 9568089932d78..be6f69a6b6593 100644
--- a/tools/testing/selftests/bpf/progs/verifier_movsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -198,6 +198,28 @@ l0_%=:							\
 	: __clobber_all);
 }
 
+SEC("socket")
+__description("MOV64SX, S16, R10 Sign Extension")
+__failure __msg("R1 type=scalar expected=fp, pkt, pkt_meta, map_key, map_value, mem, ringbuf_mem, buf, trusted_ptr_")
+__failure_unpriv __msg_unpriv("R10 sign-extension part of pointer")
+__naked void mov64sx_s16_r10(void)
+{
+	asm volatile ("					\
+	r1 = 553656332;					\
+	*(u32 *)(r10 - 8) = r1; 			\
+	r1 = (s16)r10;					\
+	r1 += -8;					\
+	r2 = 3;						\
+	if r2 <= r1 goto l0_%=;				\
+l0_%=:							\
+	call %[bpf_trace_printk];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_trace_printk)
+	: __clobber_all);
+}
+
 #else
 
 SEC("socket")
-- 
GitLab


From a3c485a5d8d47af5d2d1a0e5c3b7a1ed223669f9 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 7 Aug 2023 10:59:54 +0200
Subject: [PATCH 0958/1806] bpf: Add support for bpf_get_func_ip helper for
 uprobe program

Adding support for bpf_get_func_ip helper for uprobe program to return
probed address for both uprobe and return uprobe.

We discussed this in [1] and agreed that uprobe can have special use
of bpf_get_func_ip helper that differs from kprobe.

The kprobe bpf_get_func_ip returns:
  - address of the function if probe is attach on function entry
    for both kprobe and return kprobe
  - 0 if the probe is not attach on function entry

The uprobe bpf_get_func_ip returns:
  - address of the probe for both uprobe and return uprobe

The reason for this semantic change is that kernel can't really tell
if the probe user space address is function entry.

The uprobe program is actually kprobe type program attached as uprobe.
One of the consequences of this design is that uprobes do not have its
own set of helpers, but share them with kprobes.

As we need different functionality for bpf_get_func_ip helper for uprobe,
I'm adding the bool value to the bpf_trace_run_ctx, so the helper can
detect that it's executed in uprobe context and call specific code.

The is_uprobe bool is set as true in bpf_prog_run_array_sleepable, which
is currently used only for executing bpf programs in uprobe.

Renaming bpf_prog_run_array_sleepable to bpf_prog_run_array_uprobe
to address that it's only used for uprobes and that it sets the
run_ctx.is_uprobe as suggested by Yafang Shao.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
[1] https://lore.kernel.org/bpf/CAEf4BzZ=xLVkG5eurEuvLU79wAMtwho7ReR+XJAgwhFF4M-7Cg@mail.gmail.com/
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Viktor Malik <vmalik@redhat.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230807085956.2344866-2-jolsa@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/bpf.h            |  9 +++++++--
 include/uapi/linux/bpf.h       |  7 ++++++-
 kernel/trace/bpf_trace.c       | 11 ++++++++++-
 kernel/trace/trace_probe.h     |  5 +++++
 kernel/trace/trace_uprobe.c    |  7 +------
 tools/include/uapi/linux/bpf.h |  7 ++++++-
 6 files changed, 35 insertions(+), 11 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index abe75063630b8..db3fe5a61b058 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1819,6 +1819,7 @@ struct bpf_cg_run_ctx {
 struct bpf_trace_run_ctx {
 	struct bpf_run_ctx run_ctx;
 	u64 bpf_cookie;
+	bool is_uprobe;
 };
 
 struct bpf_tramp_run_ctx {
@@ -1867,6 +1868,8 @@ bpf_prog_run_array(const struct bpf_prog_array *array,
 	if (unlikely(!array))
 		return ret;
 
+	run_ctx.is_uprobe = false;
+
 	migrate_disable();
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 	item = &array->items[0];
@@ -1891,8 +1894,8 @@ bpf_prog_run_array(const struct bpf_prog_array *array,
  * rcu-protected dynamically sized maps.
  */
 static __always_inline u32
-bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu,
-			     const void *ctx, bpf_prog_run_fn run_prog)
+bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
+			  const void *ctx, bpf_prog_run_fn run_prog)
 {
 	const struct bpf_prog_array_item *item;
 	const struct bpf_prog *prog;
@@ -1906,6 +1909,8 @@ bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu,
 	rcu_read_lock_trace();
 	migrate_disable();
 
+	run_ctx.is_uprobe = true;
+
 	array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held());
 	if (unlikely(!array))
 		goto out;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 70da852006952..d21deb46f49f3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5086,9 +5086,14 @@ union bpf_attr {
  * u64 bpf_get_func_ip(void *ctx)
  * 	Description
  * 		Get address of the traced function (for tracing and kprobe programs).
+ *
+ * 		When called for kprobe program attached as uprobe it returns
+ * 		probe address for both entry and return uprobe.
+ *
  * 	Return
- * 		Address of the traced function.
+ * 		Address of the traced function for kprobe.
  * 		0 for kprobes placed within the function (not at the entry).
+ * 		Address of the probe for uprobe and return uprobe.
  *
  * u64 bpf_get_attach_cookie(void *ctx)
  * 	Description
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d6296d51a826a..792445e1f3f04 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1055,7 +1055,16 @@ static unsigned long get_entry_ip(unsigned long fentry_ip)
 
 BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs)
 {
-	struct kprobe *kp = kprobe_running();
+	struct bpf_trace_run_ctx *run_ctx __maybe_unused;
+	struct kprobe *kp;
+
+#ifdef CONFIG_UPROBES
+	run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx);
+	if (run_ctx->is_uprobe)
+		return ((struct uprobe_dispatch_data *)current->utask->vaddr)->bp_addr;
+#endif
+
+	kp = kprobe_running();
 
 	if (!kp || !(kp->flags & KPROBE_FLAG_ON_FUNC_ENTRY))
 		return 0;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 01ea148723de2..7dde806be91ef 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -519,3 +519,8 @@ void __trace_probe_log_err(int offset, int err);
 
 #define trace_probe_log_err(offs, err)	\
 	__trace_probe_log_err(offs, TP_ERR_##err)
+
+struct uprobe_dispatch_data {
+	struct trace_uprobe	*tu;
+	unsigned long		bp_addr;
+};
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 555c223c32321..576b3bcb8ebd3 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -88,11 +88,6 @@ static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev)
 static int register_uprobe_event(struct trace_uprobe *tu);
 static int unregister_uprobe_event(struct trace_uprobe *tu);
 
-struct uprobe_dispatch_data {
-	struct trace_uprobe	*tu;
-	unsigned long		bp_addr;
-};
-
 static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
 static int uretprobe_dispatcher(struct uprobe_consumer *con,
 				unsigned long func, struct pt_regs *regs);
@@ -1352,7 +1347,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 	if (bpf_prog_array_valid(call)) {
 		u32 ret;
 
-		ret = bpf_prog_run_array_sleepable(call->prog_array, regs, bpf_prog_run);
+		ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run);
 		if (!ret)
 			return;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 70da852006952..d21deb46f49f3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5086,9 +5086,14 @@ union bpf_attr {
  * u64 bpf_get_func_ip(void *ctx)
  * 	Description
  * 		Get address of the traced function (for tracing and kprobe programs).
+ *
+ * 		When called for kprobe program attached as uprobe it returns
+ * 		probe address for both entry and return uprobe.
+ *
  * 	Return
- * 		Address of the traced function.
+ * 		Address of the traced function for kprobe.
  * 		0 for kprobes placed within the function (not at the entry).
+ * 		Address of the probe for uprobe and return uprobe.
  *
  * u64 bpf_get_attach_cookie(void *ctx)
  * 	Description
-- 
GitLab


From e43163ed1c0a655083a811404e422f4c045637eb Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 7 Aug 2023 10:59:55 +0200
Subject: [PATCH 0959/1806] selftests/bpf: Add bpf_get_func_ip tests for uprobe
 on function entry

Adding get_func_ip tests for uprobe on function entry that
validates that bpf_get_func_ip returns proper values from
both uprobe and return uprobe.

Tested-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230807085956.2344866-3-jolsa@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../bpf/prog_tests/get_func_ip_test.c         | 11 ++++++++
 .../selftests/bpf/progs/get_func_ip_test.c    | 25 +++++++++++++++++--
 2 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
index fede8ef58b5b0..114cdbc04caf6 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
@@ -1,6 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include "get_func_ip_test.skel.h"
+#include "get_func_ip_uprobe_test.skel.h"
+
+static noinline void uprobe_trigger(void)
+{
+}
 
 static void test_function_entry(void)
 {
@@ -20,6 +25,8 @@ static void test_function_entry(void)
 	if (!ASSERT_OK(err, "get_func_ip_test__attach"))
 		goto cleanup;
 
+	skel->bss->uprobe_trigger = (unsigned long) uprobe_trigger;
+
 	prog_fd = bpf_program__fd(skel->progs.test1);
 	err = bpf_prog_test_run_opts(prog_fd, &topts);
 	ASSERT_OK(err, "test_run");
@@ -30,11 +37,15 @@ static void test_function_entry(void)
 
 	ASSERT_OK(err, "test_run");
 
+	uprobe_trigger();
+
 	ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
 	ASSERT_EQ(skel->bss->test2_result, 1, "test2_result");
 	ASSERT_EQ(skel->bss->test3_result, 1, "test3_result");
 	ASSERT_EQ(skel->bss->test4_result, 1, "test4_result");
 	ASSERT_EQ(skel->bss->test5_result, 1, "test5_result");
+	ASSERT_EQ(skel->bss->test7_result, 1, "test7_result");
+	ASSERT_EQ(skel->bss->test8_result, 1, "test8_result");
 
 cleanup:
 	get_func_ip_test__destroy(skel);
diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
index 8559e698b40d7..8956eb78a2260 100644
--- a/tools/testing/selftests/bpf/progs/get_func_ip_test.c
+++ b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
@@ -1,8 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include <stdbool.h>
 
 char _license[] SEC("license") = "GPL";
 
@@ -83,3 +82,25 @@ int test6(struct pt_regs *ctx)
 	test6_result = (const void *) addr == 0;
 	return 0;
 }
+
+unsigned long uprobe_trigger;
+
+__u64 test7_result = 0;
+SEC("uprobe//proc/self/exe:uprobe_trigger")
+int BPF_UPROBE(test7)
+{
+	__u64 addr = bpf_get_func_ip(ctx);
+
+	test7_result = (const void *) addr == (const void *) uprobe_trigger;
+	return 0;
+}
+
+__u64 test8_result = 0;
+SEC("uretprobe//proc/self/exe:uprobe_trigger")
+int BPF_URETPROBE(test8, int ret)
+{
+	__u64 addr = bpf_get_func_ip(ctx);
+
+	test8_result = (const void *) addr == (const void *) uprobe_trigger;
+	return 0;
+}
-- 
GitLab


From 7febf573a58b55170782985c031dfaf805662297 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 7 Aug 2023 10:59:56 +0200
Subject: [PATCH 0960/1806] selftests/bpf: Add bpf_get_func_ip test for uprobe
 inside function

Adding get_func_ip test for uprobe inside function that validates
the get_func_ip helper returns correct probe address value.

Tested-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230807085956.2344866-4-jolsa@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../bpf/prog_tests/get_func_ip_test.c         | 46 +++++++++++++++++--
 .../bpf/progs/get_func_ip_uprobe_test.c       | 18 ++++++++
 2 files changed, 60 insertions(+), 4 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c

diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
index 114cdbc04caf6..c40242dfa8fb5 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
@@ -51,11 +51,17 @@ cleanup:
 	get_func_ip_test__destroy(skel);
 }
 
-/* test6 is x86_64 specific because of the instruction
- * offset, disabling it for all other archs
- */
 #ifdef __x86_64__
-static void test_function_body(void)
+extern void uprobe_trigger_body(void);
+asm(
+".globl uprobe_trigger_body\n"
+".type uprobe_trigger_body, @function\n"
+"uprobe_trigger_body:\n"
+"	nop\n"
+"	ret\n"
+);
+
+static void test_function_body_kprobe(void)
 {
 	struct get_func_ip_test *skel = NULL;
 	LIBBPF_OPTS(bpf_test_run_opts, topts);
@@ -67,6 +73,9 @@ static void test_function_body(void)
 	if (!ASSERT_OK_PTR(skel, "get_func_ip_test__open"))
 		return;
 
+	/* test6 is x86_64 specific and is disabled by default,
+	 * enable it for body test.
+	 */
 	bpf_program__set_autoload(skel->progs.test6, true);
 
 	err = get_func_ip_test__load(skel);
@@ -90,6 +99,35 @@ cleanup:
 	bpf_link__destroy(link6);
 	get_func_ip_test__destroy(skel);
 }
+
+static void test_function_body_uprobe(void)
+{
+	struct get_func_ip_uprobe_test *skel = NULL;
+	int err;
+
+	skel = get_func_ip_uprobe_test__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "get_func_ip_uprobe_test__open_and_load"))
+		return;
+
+	err = get_func_ip_uprobe_test__attach(skel);
+	if (!ASSERT_OK(err, "get_func_ip_test__attach"))
+		goto cleanup;
+
+	skel->bss->uprobe_trigger_body = (unsigned long) uprobe_trigger_body;
+
+	uprobe_trigger_body();
+
+	ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
+
+cleanup:
+	get_func_ip_uprobe_test__destroy(skel);
+}
+
+static void test_function_body(void)
+{
+	test_function_body_kprobe();
+	test_function_body_uprobe();
+}
 #else
 #define test_function_body()
 #endif
diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c
new file mode 100644
index 0000000000000..052f8a4345a81
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+unsigned long uprobe_trigger_body;
+
+__u64 test1_result = 0;
+SEC("uprobe//proc/self/exe:uprobe_trigger_body+1")
+int BPF_UPROBE(test1)
+{
+	__u64 addr = bpf_get_func_ip(ctx);
+
+	test1_result = (const void *) addr == (const void *) uprobe_trigger_body + 1;
+	return 0;
+}
-- 
GitLab


From aa07a0f421b599c492d2848ab150b0293b487c2b Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Fri, 4 Aug 2023 10:29:34 +0530
Subject: [PATCH 0961/1806] octeontx2-af: Code restructure to handle TC outer
 VLAN offload

Moved the TC outer VLAN offload support to a separate function.
This change is done to handle all VLAN related changes cleanly from
a dedicated function.

Signed-off-by: Suman Ghosh <sumang@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230804045935.3010554-2-sumang@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/marvell/octeontx2/nic/otx2_tc.c  | 93 +++++++++++--------
 1 file changed, 53 insertions(+), 40 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 4bb511e3cbe5a..c535e8170efce 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -439,6 +439,55 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic,
 	return 0;
 }
 
+static int otx2_tc_process_vlan(struct otx2_nic *nic, struct flow_msg *flow_spec,
+				struct flow_msg *flow_mask, struct flow_rule *rule,
+				struct npc_install_flow_req *req, bool is_inner)
+{
+	struct flow_match_vlan match;
+	u16 vlan_tci, vlan_tci_mask;
+
+	if (is_inner)
+		return -EOPNOTSUPP;
+
+	flow_rule_match_vlan(rule, &match);
+	if (ntohs(match.key->vlan_tpid) != ETH_P_8021Q) {
+		netdev_err(nic->netdev, "vlan tpid 0x%x not supported\n",
+			   ntohs(match.key->vlan_tpid));
+		return -EOPNOTSUPP;
+	}
+
+	if (!match.mask->vlan_id) {
+		struct flow_action_entry *act;
+		int i;
+
+		flow_action_for_each(i, act, &rule->action) {
+			if (act->id == FLOW_ACTION_DROP) {
+				netdev_err(nic->netdev,
+					   "vlan tpid 0x%x with vlan_id %d is not supported for DROP rule.\n",
+					   ntohs(match.key->vlan_tpid), match.key->vlan_id);
+				return -EOPNOTSUPP;
+			}
+		}
+	}
+
+	if (match.mask->vlan_id ||
+	    match.mask->vlan_dei ||
+	    match.mask->vlan_priority) {
+		vlan_tci = match.key->vlan_id |
+			   match.key->vlan_dei << 12 |
+			   match.key->vlan_priority << 13;
+
+		vlan_tci_mask = match.mask->vlan_id |
+				match.mask->vlan_dei << 12 |
+				match.mask->vlan_priority << 13;
+		flow_spec->vlan_tci = htons(vlan_tci);
+		flow_mask->vlan_tci = htons(vlan_tci_mask);
+		req->features |= BIT_ULL(NPC_OUTER_VID);
+	}
+
+	return 0;
+}
+
 static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 				struct flow_cls_offload *f,
 				struct npc_install_flow_req *req)
@@ -591,47 +640,11 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_match_vlan match;
-		u16 vlan_tci, vlan_tci_mask;
-
-		flow_rule_match_vlan(rule, &match);
-
-		if (ntohs(match.key->vlan_tpid) != ETH_P_8021Q) {
-			netdev_err(nic->netdev, "vlan tpid 0x%x not supported\n",
-				   ntohs(match.key->vlan_tpid));
-			return -EOPNOTSUPP;
-		}
-
-		if (!match.mask->vlan_id) {
-			struct flow_action_entry *act;
-			int i;
-
-			flow_action_for_each(i, act, &rule->action) {
-				if (act->id == FLOW_ACTION_DROP) {
-					netdev_err(nic->netdev,
-						   "vlan tpid 0x%x with vlan_id %d is not supported for DROP rule.\n",
-						   ntohs(match.key->vlan_tpid),
-						   match.key->vlan_id);
-					return -EOPNOTSUPP;
-				}
-			}
-		}
+		int ret;
 
-		if (match.mask->vlan_id ||
-		    match.mask->vlan_dei ||
-		    match.mask->vlan_priority) {
-			vlan_tci = match.key->vlan_id |
-				   match.key->vlan_dei << 12 |
-				   match.key->vlan_priority << 13;
-
-			vlan_tci_mask = match.mask->vlan_id |
-					match.mask->vlan_dei << 12 |
-					match.mask->vlan_priority << 13;
-
-			flow_spec->vlan_tci = htons(vlan_tci);
-			flow_mask->vlan_tci = htons(vlan_tci_mask);
-			req->features |= BIT_ULL(NPC_OUTER_VID);
-		}
+		ret = otx2_tc_process_vlan(nic, flow_spec, flow_mask, rule, req, false);
+		if (ret)
+			return ret;
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
-- 
GitLab


From 21e748354ec246c9a1a83193cb3f82c05a233b8d Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Fri, 4 Aug 2023 10:29:35 +0530
Subject: [PATCH 0962/1806] octeontx2-af: TC flower offload support for inner
 VLAN

Extend the current TC flower offload support to enable filters matching
inner VLAN, and support offload of those filters to hardware.

Signed-off-by: Suman Ghosh <sumang@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230804045935.3010554-3-sumang@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/marvell/octeontx2/af/mbox.h  |  1 +
 .../net/ethernet/marvell/octeontx2/af/npc.h   |  3 ++
 .../marvell/octeontx2/af/rvu_debugfs.c        |  5 ++++
 .../marvell/octeontx2/af/rvu_npc_fs.c         | 13 +++++++++
 .../ethernet/marvell/octeontx2/nic/otx2_tc.c  | 28 +++++++++++++++----
 5 files changed, 44 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index a8f3c8faf8afa..e2f2b2179eef3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -1465,6 +1465,7 @@ struct flow_msg {
 		u8 ip_flag;
 		u8 next_header;
 	};
+	__be16 vlan_itci;
 };
 
 struct npc_install_flow_req {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index 534f20c0c5df0..de9fbd98dfb76 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -184,6 +184,7 @@ enum key_fields {
 	NPC_VLAN_ETYPE_CTAG, /* 0x8100 */
 	NPC_VLAN_ETYPE_STAG, /* 0x88A8 */
 	NPC_OUTER_VID,
+	NPC_INNER_VID,
 	NPC_TOS,
 	NPC_IPFRAG_IPV4,
 	NPC_SIP_IPV4,
@@ -230,6 +231,8 @@ enum key_fields {
 	NPC_VLAN_TAG1,
 	/* outer vlan tci for double tagged frame */
 	NPC_VLAN_TAG2,
+	/* inner vlan tci for double tagged frame */
+	NPC_VLAN_TAG3,
 	/* other header fields programmed to extract but not of our interest */
 	NPC_UNKNOWN,
 	NPC_KEY_FIELDS_MAX,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 7cd33edca3658..d30e84803481d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -2787,6 +2787,11 @@ static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s,
 			seq_printf(s, "mask 0x%x\n",
 				   ntohs(rule->mask.vlan_tci));
 			break;
+		case NPC_INNER_VID:
+			seq_printf(s, "0x%x ", ntohs(rule->packet.vlan_itci));
+			seq_printf(s, "mask 0x%x\n",
+				   ntohs(rule->mask.vlan_itci));
+			break;
 		case NPC_TOS:
 			seq_printf(s, "%d ", rule->packet.tos);
 			seq_printf(s, "mask 0x%x\n", rule->mask.tos);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index bb715e616fad0..5c8f9fc15ff89 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -20,6 +20,7 @@ static const char * const npc_flow_names[] = {
 	[NPC_VLAN_ETYPE_CTAG] = "vlan ether type ctag",
 	[NPC_VLAN_ETYPE_STAG] = "vlan ether type stag",
 	[NPC_OUTER_VID]	= "outer vlan id",
+	[NPC_INNER_VID]	= "inner vlan id",
 	[NPC_TOS]	= "tos",
 	[NPC_IPFRAG_IPV4] = "fragmented IPv4 header ",
 	[NPC_SIP_IPV4]	= "ipv4 source ip",
@@ -328,6 +329,8 @@ static void npc_handle_multi_layer_fields(struct rvu *rvu, int blkaddr, u8 intf)
 	 */
 	struct npc_key_field *vlan_tag1;
 	struct npc_key_field *vlan_tag2;
+	/* Inner VLAN TCI for double tagged frames */
+	struct npc_key_field *vlan_tag3;
 	u64 *features;
 	u8 start_lid;
 	int i;
@@ -350,6 +353,7 @@ static void npc_handle_multi_layer_fields(struct rvu *rvu, int blkaddr, u8 intf)
 	etype_tag2 = &key_fields[NPC_ETYPE_TAG2];
 	vlan_tag1 = &key_fields[NPC_VLAN_TAG1];
 	vlan_tag2 = &key_fields[NPC_VLAN_TAG2];
+	vlan_tag3 = &key_fields[NPC_VLAN_TAG3];
 
 	/* if key profile programmed does not extract Ethertype at all */
 	if (!etype_ether->nr_kws && !etype_tag1->nr_kws && !etype_tag2->nr_kws) {
@@ -431,6 +435,12 @@ vlan_tci:
 		goto done;
 	}
 	*features |= BIT_ULL(NPC_OUTER_VID);
+
+	/* If key profile extracts inner vlan tci */
+	if (vlan_tag3->nr_kws) {
+		key_fields[NPC_INNER_VID] = *vlan_tag3;
+		*features |= BIT_ULL(NPC_INNER_VID);
+	}
 done:
 	return;
 }
@@ -513,6 +523,7 @@ do {									       \
 	NPC_SCAN_HDR(NPC_ETYPE_TAG2, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 8, 2);
 	NPC_SCAN_HDR(NPC_VLAN_TAG1, NPC_LID_LB, NPC_LT_LB_CTAG, 2, 2);
 	NPC_SCAN_HDR(NPC_VLAN_TAG2, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 2, 2);
+	NPC_SCAN_HDR(NPC_VLAN_TAG3, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 6, 2);
 	NPC_SCAN_HDR(NPC_DMAC, NPC_LID_LA, la_ltype, la_start, 6);
 
 	NPC_SCAN_HDR(NPC_IPSEC_SPI, NPC_LID_LD, NPC_LT_LD_AH, 4, 4);
@@ -943,6 +954,8 @@ do {									      \
 
 	NPC_WRITE_FLOW(NPC_OUTER_VID, vlan_tci, ntohs(pkt->vlan_tci), 0,
 		       ntohs(mask->vlan_tci), 0);
+	NPC_WRITE_FLOW(NPC_INNER_VID, vlan_itci, ntohs(pkt->vlan_itci), 0,
+		       ntohs(mask->vlan_itci), 0);
 
 	NPC_WRITE_FLOW(NPC_IPFRAG_IPV6, next_header, pkt->next_header, 0,
 		       mask->next_header, 0);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index c535e8170efce..fab9d85bfb371 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -447,10 +447,11 @@ static int otx2_tc_process_vlan(struct otx2_nic *nic, struct flow_msg *flow_spec
 	u16 vlan_tci, vlan_tci_mask;
 
 	if (is_inner)
-		return -EOPNOTSUPP;
+		flow_rule_match_cvlan(rule, &match);
+	else
+		flow_rule_match_vlan(rule, &match);
 
-	flow_rule_match_vlan(rule, &match);
-	if (ntohs(match.key->vlan_tpid) != ETH_P_8021Q) {
+	if (!eth_type_vlan(match.key->vlan_tpid)) {
 		netdev_err(nic->netdev, "vlan tpid 0x%x not supported\n",
 			   ntohs(match.key->vlan_tpid));
 		return -EOPNOTSUPP;
@@ -480,9 +481,15 @@ static int otx2_tc_process_vlan(struct otx2_nic *nic, struct flow_msg *flow_spec
 		vlan_tci_mask = match.mask->vlan_id |
 				match.mask->vlan_dei << 12 |
 				match.mask->vlan_priority << 13;
-		flow_spec->vlan_tci = htons(vlan_tci);
-		flow_mask->vlan_tci = htons(vlan_tci_mask);
-		req->features |= BIT_ULL(NPC_OUTER_VID);
+		if (is_inner) {
+			flow_spec->vlan_itci = htons(vlan_tci);
+			flow_mask->vlan_itci = htons(vlan_tci_mask);
+			req->features |= BIT_ULL(NPC_INNER_VID);
+		} else {
+			flow_spec->vlan_tci = htons(vlan_tci);
+			flow_mask->vlan_tci = htons(vlan_tci_mask);
+			req->features |= BIT_ULL(NPC_OUTER_VID);
+		}
 	}
 
 	return 0;
@@ -507,6 +514,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT(FLOW_DISSECTOR_KEY_CVLAN) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
@@ -647,6 +655,14 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 			return ret;
 	}
 
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) {
+		int ret;
+
+		ret = otx2_tc_process_vlan(nic, flow_spec, flow_mask, rule, req, true);
+		if (ret)
+			return ret;
+	}
+
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
 		struct flow_match_ipv4_addrs match;
 
-- 
GitLab


From 43265d3fceebf1c32db07b9515eccdf3d10935d5 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Fri, 4 Aug 2023 17:59:45 +0800
Subject: [PATCH 0963/1806] net: dpaa2-eth: Remove redundant initialization
 owner in dpaa2_eth_driver

The fsl_mc_driver_register() will set "THIS_MODULE" to driver.owner when
register a fsl_mc_driver driver, so it is redundant initialization to set
driver.owner in dpaa2_eth_driver statement. Remove it for clean code.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230804095946.99956-2-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index a9676d0dece8e..15bab41cee48d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -5087,7 +5087,6 @@ MODULE_DEVICE_TABLE(fslmc, dpaa2_eth_match_id_table);
 static struct fsl_mc_driver dpaa2_eth_driver = {
 	.driver = {
 		.name = KBUILD_MODNAME,
-		.owner = THIS_MODULE,
 	},
 	.probe = dpaa2_eth_probe,
 	.remove = dpaa2_eth_remove,
-- 
GitLab


From ca46d207c97210c1fce54b2d81e9f7467ce0db5c Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Fri, 4 Aug 2023 17:59:46 +0800
Subject: [PATCH 0964/1806] net: dpaa2-switch: Remove redundant initialization
 owner in dpaa2_switch_drv

The fsl_mc_driver_register() will set "THIS_MODULE" to driver.owner when
register a fsl_mc_driver driver, so it is redundant initialization to set
driver.owner in dpaa2_switch_drv statement. Remove it for clean code.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230804095946.99956-3-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index 21cc4e52425a9..97d3151076d53 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -3457,7 +3457,6 @@ MODULE_DEVICE_TABLE(fslmc, dpaa2_switch_match_id_table);
 static struct fsl_mc_driver dpaa2_switch_drv = {
 	.driver = {
 		.name = KBUILD_MODNAME,
-		.owner = THIS_MODULE,
 	},
 	.probe = dpaa2_switch_probe,
 	.remove = dpaa2_switch_remove,
-- 
GitLab


From 29cfda963f899da403d6bc5a3abe19d2e0be0cf4 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 2 Aug 2023 21:09:57 +0800
Subject: [PATCH 0965/1806] netfilter: gre: Remove unused function declaration
 nf_ct_gre_keymap_flush()

Commit a23f89a99906 ("netfilter: conntrack: nf_ct_gre_keymap_flush() removal")
leave this unused, remove it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/linux/netfilter/nf_conntrack_proto_gre.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h
index f33aa60213647..34ce5d2f37a2a 100644
--- a/include/linux/netfilter/nf_conntrack_proto_gre.h
+++ b/include/linux/netfilter/nf_conntrack_proto_gre.h
@@ -25,7 +25,6 @@ struct nf_ct_gre_keymap {
 int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir,
 			 struct nf_conntrack_tuple *t);
 
-void nf_ct_gre_keymap_flush(struct net *net);
 /* delete keymap entries */
 void nf_ct_gre_keymap_destroy(struct nf_conn *ct);
 
-- 
GitLab


From 529f63fa11eba5fbe448fbe537b3576edd9fd277 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 2 Aug 2023 21:15:49 +0800
Subject: [PATCH 0966/1806] netfilter: helper: Remove unused function
 declarations

Commit b118509076b3 ("netfilter: remove nf_conntrack_helper sysctl and modparam toggles")
leave these unused declarations.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_conntrack_helper.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index f30b1694b690e..de2f956abf348 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -136,8 +136,6 @@ static inline void *nfct_help_data(const struct nf_conn *ct)
 	return (void *)help->data;
 }
 
-void nf_conntrack_helper_pernet_init(struct net *net);
-
 int nf_conntrack_helper_init(void);
 void nf_conntrack_helper_fini(void);
 
@@ -182,5 +180,4 @@ void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat);
 int nf_nat_helper_try_module_get(const char *name, u16 l3num,
 				 u8 protonum);
 void nf_nat_helper_put(struct nf_conntrack_helper *helper);
-void nf_ct_set_auto_assign_helper_warned(struct net *net);
 #endif /*_NF_CONNTRACK_HELPER_H*/
-- 
GitLab


From 172af3eab05f096122d7c239ab9a11b38b5e5c90 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 4 Aug 2023 21:41:49 +0800
Subject: [PATCH 0967/1806] netfilter: conntrack: Remove unused function
 declarations

Commit 1015c3de23ee ("netfilter: conntrack: remove extension register api")
leave nf_conntrack_acct_fini() and nf_conntrack_labels_init() unused, remove it.
And commit a0ae2562c6c4 ("netfilter: conntrack: remove l3proto abstraction")
leave behind nf_ct_l3proto_try_module_get() and nf_ct_l3proto_module_put().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_conntrack.h        | 4 ----
 include/net/netfilter/nf_conntrack_acct.h   | 2 --
 include/net/netfilter/nf_conntrack_labels.h | 1 -
 3 files changed, 7 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index a72028dbef0c3..4085765c33705 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -190,10 +190,6 @@ static inline void nf_ct_put(struct nf_conn *ct)
 		nf_ct_destroy(&ct->ct_general);
 }
 
-/* Protocol module loading */
-int nf_ct_l3proto_try_module_get(unsigned short l3proto);
-void nf_ct_l3proto_module_put(unsigned short l3proto);
-
 /* load module; enable/disable conntrack in this namespace */
 int nf_ct_netns_get(struct net *net, u8 nfproto);
 void nf_ct_netns_put(struct net *net, u8 nfproto);
diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h
index 4b2b7f8914ea8..a120685cac932 100644
--- a/include/net/netfilter/nf_conntrack_acct.h
+++ b/include/net/netfilter/nf_conntrack_acct.h
@@ -78,6 +78,4 @@ static inline void nf_ct_acct_update(struct nf_conn *ct, u32 dir,
 
 void nf_conntrack_acct_pernet_init(struct net *net);
 
-void nf_conntrack_acct_fini(void);
-
 #endif /* _NF_CONNTRACK_ACCT_H */
diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h
index 66bab6c60d12b..fcb19a4e8f2b2 100644
--- a/include/net/netfilter/nf_conntrack_labels.h
+++ b/include/net/netfilter/nf_conntrack_labels.h
@@ -52,7 +52,6 @@ int nf_connlabels_replace(struct nf_conn *ct,
 			  const u32 *data, const u32 *mask, unsigned int words);
 
 #ifdef CONFIG_NF_CONNTRACK_LABELS
-int nf_conntrack_labels_init(void);
 int nf_connlabels_get(struct net *net, unsigned int bit);
 void nf_connlabels_put(struct net *net);
 #else
-- 
GitLab


From 61e9ab294b39e5e7c040884b65d06f52e06ac40f Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 7 Aug 2023 22:25:26 +0800
Subject: [PATCH 0968/1806] netfilter: h323: Remove unused function
 declarations

Commit f587de0e2feb ("[NETFILTER]: nf_conntrack/nf_nat: add H.323 helper port")
declared but never implemented these.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/linux/netfilter/nf_conntrack_h323.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h
index 9e937f64a1adc..81286c4993252 100644
--- a/include/linux/netfilter/nf_conntrack_h323.h
+++ b/include/linux/netfilter/nf_conntrack_h323.h
@@ -34,10 +34,6 @@ struct nf_ct_h323_master {
 int get_h225_addr(struct nf_conn *ct, unsigned char *data,
 		  TransportAddress *taddr, union nf_inet_addr *addr,
 		  __be16 *port);
-void nf_conntrack_h245_expect(struct nf_conn *new,
-			      struct nf_conntrack_expect *this);
-void nf_conntrack_q931_expect(struct nf_conn *new,
-			      struct nf_conntrack_expect *this);
 
 struct nfct_h323_nat_hooks {
 	int (*set_h245_addr)(struct sk_buff *skb, unsigned int protoff,
-- 
GitLab


From 1d85594fd3e7e39e63b53b1bdc2d89db43b6ecd5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= <maze@google.com>
Date: Tue, 25 Jul 2023 01:54:43 -0700
Subject: [PATCH 0969/1806] netfilter: nfnetlink_log: always add a timestamp
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Compared to all the other work we're already doing to deliver
an skb to userspace this is very cheap - at worse an extra
call to ktime_get_real() - and very useful.

(and indeed it may even be cheaper if we're running from other hooks)

(background: Android occasionally logs packets which
caused wake from sleep/suspend and we'd like to have
timestamps reliably associated with these events)

Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nfnetlink_log.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index e57eb168ee130..53c9e76473ba1 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -470,7 +470,6 @@ __build_packet_message(struct nfnl_log_net *log,
 	sk_buff_data_t old_tail = inst->skb->tail;
 	struct sock *sk;
 	const unsigned char *hwhdrp;
-	ktime_t tstamp;
 
 	nlh = nfnl_msg_put(inst->skb, 0, 0,
 			   nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET),
@@ -599,10 +598,9 @@ __build_packet_message(struct nfnl_log_net *log,
 			goto nla_put_failure;
 	}
 
-	tstamp = skb_tstamp_cond(skb, false);
-	if (hooknum <= NF_INET_FORWARD && tstamp) {
+	if (hooknum <= NF_INET_FORWARD) {
+		struct timespec64 kts = ktime_to_timespec64(skb_tstamp_cond(skb, true));
 		struct nfulnl_msg_packet_timestamp ts;
-		struct timespec64 kts = ktime_to_timespec64(tstamp);
 		ts.sec = cpu_to_be64(kts.tv_sec);
 		ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC);
 
-- 
GitLab


From ac0955f0ccb0c2e710fd6a8c114a6fe8f3cf4dfd Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 4 Aug 2023 20:52:03 +0800
Subject: [PATCH 0970/1806] ixgbe: Remove unused function declarations

Commit dc166e22ede5 ("ixgbe: DCB remove ixgbe_fcoe_getapp routine")
leave ixgbe_fcoe_getapp() unused.
Commit ffed21bcee7a ("ixgbe: Don't bother clearing buffer memory for descriptor rings")
leave ixgbe_unmap_and_free_tx_resource() declaration unused.
And commit 3b3bf3b92b31 ("ixgbe: remove unused fcoe.tc field and fcoe_setapp()")
removed the ixgbe_fcoe_setapp() implementation.

Commit c44ade9ef8ff ("ixgbe: update to latest common code module")
declared but never implemented ixgbe_init_ops_generic().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230804125203.30924-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe.h        | 6 ------
 drivers/net/ethernet/intel/ixgbe/ixgbe_common.h | 1 -
 2 files changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 63d4e32df0295..b6f0376e42f4b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -945,8 +945,6 @@ void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid);
 void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter);
 netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *, struct ixgbe_adapter *,
 				  struct ixgbe_ring *);
-void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *,
-				      struct ixgbe_tx_buffer *);
 void ixgbe_alloc_rx_buffers(struct ixgbe_ring *, u16);
 void ixgbe_write_eitr(struct ixgbe_q_vector *);
 int ixgbe_poll(struct napi_struct *napi, int budget);
@@ -997,10 +995,6 @@ int ixgbe_setup_fcoe_ddp_resources(struct ixgbe_adapter *adapter);
 void ixgbe_free_fcoe_ddp_resources(struct ixgbe_adapter *adapter);
 int ixgbe_fcoe_enable(struct net_device *netdev);
 int ixgbe_fcoe_disable(struct net_device *netdev);
-#ifdef CONFIG_IXGBE_DCB
-u8 ixgbe_fcoe_getapp(struct ixgbe_adapter *adapter);
-u8 ixgbe_fcoe_setapp(struct ixgbe_adapter *adapter, u8 up);
-#endif /* CONFIG_IXGBE_DCB */
 int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type);
 int ixgbe_fcoe_get_hbainfo(struct net_device *netdev,
 			   struct netdev_fcoe_hbainfo *info);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
index 4b531e8ae38ae..34761e691d52d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
@@ -8,7 +8,6 @@
 #include "ixgbe.h"
 
 u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw);
-s32 ixgbe_init_ops_generic(struct ixgbe_hw *hw);
 s32 ixgbe_init_hw_generic(struct ixgbe_hw *hw);
 s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw);
 s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw);
-- 
GitLab


From 2359fd0b8b1f2441ac2c732fba6bb0228189acbc Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 4 Aug 2023 20:55:25 +0800
Subject: [PATCH 0971/1806] i40e: Remove unused function declarations

Commit f62b5060d670 ("i40e: fix mac address checking") left behind
i40e_validate_mac_addr() declaration.
Also the other declarations are declared but never implemented in
commit 56a62fc86895 ("i40e: init code and hardware support").

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230804125525.20244-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/intel/i40e/i40e_prototype.h    | 17 -----------------
 1 file changed, 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index fe845987d99a5..3eeee224f1fb2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -18,7 +18,6 @@
 /* adminq functions */
 int i40e_init_adminq(struct i40e_hw *hw);
 void i40e_shutdown_adminq(struct i40e_hw *hw);
-void i40e_adminq_init_ring_data(struct i40e_hw *hw);
 int i40e_clean_arq_element(struct i40e_hw *hw,
 			   struct i40e_arq_event_info *e,
 			   u16 *events_pending);
@@ -51,7 +50,6 @@ i40e_asq_send_command_atomic_v2(struct i40e_hw *hw,
 void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask,
 		   void *desc, void *buffer, u16 buf_len);
 
-void i40e_idle_aq(struct i40e_hw *hw);
 bool i40e_check_asq_alive(struct i40e_hw *hw);
 int i40e_aq_queue_shutdown(struct i40e_hw *hw, bool unloading);
 const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err);
@@ -117,9 +115,6 @@ int i40e_aq_set_link_restart_an(struct i40e_hw *hw,
 int i40e_aq_get_link_info(struct i40e_hw *hw,
 			  bool enable_lse, struct i40e_link_status *link,
 			  struct i40e_asq_cmd_details *cmd_details);
-int i40e_aq_set_local_advt_reg(struct i40e_hw *hw,
-			       u64 advt_reg,
-			       struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_send_driver_version(struct i40e_hw *hw,
 				struct i40e_driver_version *dv,
 				struct i40e_asq_cmd_details *cmd_details);
@@ -269,9 +264,6 @@ int i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw,
 				struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_dcb_updated(struct i40e_hw *hw,
 			struct i40e_asq_cmd_details *cmd_details);
-int i40e_aq_config_switch_comp_bw_limit(struct i40e_hw *hw,
-					u16 seid, u16 credit, u8 max_bw,
-					struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_config_vsi_tc_bw(struct i40e_hw *hw, u16 seid,
 			     struct i40e_aqc_configure_vsi_tc_bw_data *bw_data,
 			     struct i40e_asq_cmd_details *cmd_details);
@@ -350,7 +342,6 @@ i40e_aq_configure_partition_bw(struct i40e_hw *hw,
 int i40e_get_port_mac_addr(struct i40e_hw *hw, u8 *mac_addr);
 int i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num,
 			 u32 pba_num_size);
-int i40e_validate_mac_addr(u8 *mac_addr);
 void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable);
 /* prototype for functions used for NVM access */
 int i40e_init_nvm(struct i40e_hw *hw);
@@ -425,14 +416,6 @@ i40e_virtchnl_link_speed(enum i40e_aq_link_speed link_speed)
 /* prototype for functions used for SW locks */
 
 /* i40e_common for VF drivers*/
-void i40e_vf_parse_hw_config(struct i40e_hw *hw,
-			     struct virtchnl_vf_resource *msg);
-int i40e_vf_reset(struct i40e_hw *hw);
-int i40e_aq_send_msg_to_pf(struct i40e_hw *hw,
-			   enum virtchnl_ops v_opcode,
-			   int v_retval,
-			   u8 *msg, u16 msglen,
-			   struct i40e_asq_cmd_details *cmd_details);
 int i40e_set_filter_control(struct i40e_hw *hw,
 			    struct i40e_filter_control_settings *settings);
 int i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw,
-- 
GitLab


From 6ff0490cd8100c07d0329d475afccaa9656595b9 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 4 Aug 2023 21:00:48 +0800
Subject: [PATCH 0972/1806] net: hns: Remove unused function declaration
 mac_adjust_link()

Commit 511e6bc071db ("net: add Hisilicon Network Subsystem DSAF support")
declared but never implemented this, remove it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Hao Lan <lanhao@huawei.com>
Link: https://lore.kernel.org/r/20230804130048.39808-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
index e3bb05959ba97..edf0bcf76ac9e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
@@ -422,7 +422,6 @@ void *hns_xgmac_config(struct hns_mac_cb *mac_cb,
 		       struct mac_params *mac_param);
 
 int hns_mac_init(struct dsaf_device *dsaf_dev);
-void mac_adjust_link(struct net_device *net_dev);
 bool hns_mac_need_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex);
 void hns_mac_get_link_status(struct hns_mac_cb *mac_cb,	u32 *link_status);
 int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, u32 vmid,
-- 
GitLab


From 78d3902795f0d6a688407e032dfad89bc7933886 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 4 Aug 2023 15:30:11 +0200
Subject: [PATCH 0973/1806] net: fs_enet: Remove set but not used variable

CC      drivers/net/ethernet/freescale/fs_enet/fs_enet-main.o
drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c: In function 'fs_enet_interrupt':
drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c:321:40: warning: variable 'fpi' set but not used [-Wunused-but-set-variable]

Remove that variable.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/90b72c1708bb8ba2b7a1a688e8259e428968364d.1691155346.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index f9f5b28cc72e8..a6dfc8807d3dd 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -318,14 +318,12 @@ fs_enet_interrupt(int irq, void *dev_id)
 {
 	struct net_device *dev = dev_id;
 	struct fs_enet_private *fep;
-	const struct fs_platform_info *fpi;
 	u32 int_events;
 	u32 int_clr_events;
 	int nr, napi_ok;
 	int handled;
 
 	fep = netdev_priv(dev);
-	fpi = fep->fpi;
 
 	nr = 0;
 	while ((int_events = (*fep->ops->get_int_events)(dev)) != 0) {
-- 
GitLab


From ae9e78a9dc88be8014c3c5116423ce6e58fdbcb8 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 4 Aug 2023 15:30:12 +0200
Subject: [PATCH 0974/1806] net: fs_enet: Fix address space and base types
 mismatches

CHECK   drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
drivers/net/ethernet/freescale/fs_enet/mac-fcc.c:550:9: warning: cast removes address space '__iomem' of expression
drivers/net/ethernet/freescale/fs_enet/mac-fcc.c:550:9: error: subtraction of different types can't work (different address spaces)
  CC      drivers/net/ethernet/freescale/fs_enet/mii-bitbang.o
  CHECK   drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c:95:31: warning: incorrect type in argument 1 (different base types)
drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c:95:31:    expected unsigned int [noderef] [usertype] __iomem *p
drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c:95:31:    got restricted __be32 [noderef] [usertype] __iomem *dat
...
drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c:63:31: warning: incorrect type in argument 1 (different base types)
drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c:63:31:    expected unsigned int [noderef] [usertype] __iomem *p
drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c:63:31:    got restricted __be32 [noderef] [usertype] __iomem *dir
...

Fix those address space and base type mismatches reported by sparse.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/25c7965e6aeeb6bbe1b6be5a3c2c7125182fcb02.1691155346.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fs_enet/mac-fcc.c     | 2 +-
 drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index 925428f1b0c85..ce63fd56df89f 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -547,7 +547,7 @@ static void tx_restart(struct net_device *dev)
 	}
 	/* Now update the TBPTR and dirty flag to the current buffer */
 	W32(ep, fen_genfcc.fcc_tbptr,
-		(uint) (((void *)recheck_bd - fep->ring_base) +
+		(uint)(((void __iomem *)recheck_bd - fep->ring_base) +
 		fep->ring_mem_addr));
 	fep->dirty_tx = recheck_bd;
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
index 91a69fc2f7c2d..f965a2329055e 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
@@ -29,8 +29,8 @@
 
 struct bb_info {
 	struct mdiobb_ctrl ctrl;
-	__be32 __iomem *dir;
-	__be32 __iomem *dat;
+	u32 __iomem *dir;
+	u32 __iomem *dat;
 	u32 mdio_msk;
 	u32 mdc_msk;
 };
-- 
GitLab


From 26bbbef8ff4047f857ac2d7353eb19e46100ce18 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 4 Aug 2023 15:30:13 +0200
Subject: [PATCH 0975/1806] net: fs_enet: Remove fs_get_id()

fs_get_id() hasn't been used since commit b219108cbace ("fs_enet:
Remove !CONFIG_PPC_CPM_NEW_BINDING code")

Remove it.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/7a53b88cc40302fcbea59554f5e7067e3594ad53.1691155346.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/fs_enet_pd.h | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h
index 77d783f71527f..2351c3d9404da 100644
--- a/include/linux/fs_enet_pd.h
+++ b/include/linux/fs_enet_pd.h
@@ -151,15 +151,4 @@ struct fs_mii_fec_platform_info {
 	u32 mii_speed;
 };
 
-static inline int fs_get_id(struct fs_platform_info *fpi)
-{
-	if(strstr(fpi->fs_type, "SCC"))
-		return fs_scc_index2id(fpi->fs_no);
-	if(strstr(fpi->fs_type, "FCC"))
-		return fs_fcc_index2id(fpi->fs_no);
-	if(strstr(fpi->fs_type, "FEC"))
-		return fs_fec_index2id(fpi->fs_no);
-	return fpi->fs_no;
-}
-
 #endif
-- 
GitLab


From caaf482e265415778de74e262a6f153dd2f18fa4 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 4 Aug 2023 15:30:14 +0200
Subject: [PATCH 0976/1806] net: fs_enet: Remove unused fields in
 fs_platform_info struct

Since commit 3dd82a1ea724 ("[POWERPC] CPM: Always use new binding.")
many fields of fs_platform_info structure are not used anymore.

Remove them.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/2e584fcd75e21a0f7e7d5f942eebdc067b2f82f9.1691155346.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/fs_enet_pd.h | 19 -------------------
 1 file changed, 19 deletions(-)

diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h
index 2351c3d9404da..a1905e41c1677 100644
--- a/include/linux/fs_enet_pd.h
+++ b/include/linux/fs_enet_pd.h
@@ -111,33 +111,14 @@ struct fs_mii_bb_platform_info {
 };
 
 struct fs_platform_info {
-
-	void(*init_ioports)(struct fs_platform_info *);
 	/* device specific information */
-	int fs_no;		/* controller index            */
-	char fs_type[4];	/* controller type             */
-
-	u32 cp_page;		/* CPM page */
-	u32 cp_block;		/* CPM sblock */
 	u32 cp_command;		/* CPM page/sblock/mcn */
 
-	u32 clk_trx;		/* some stuff for pins & mux configuration*/
-	u32 clk_rx;
-	u32 clk_tx;
-	u32 clk_route;
-	u32 clk_mask;
-
-	u32 mem_offset;
 	u32 dpram_offset;
-	u32 fcc_regs_c;
 	
-	u32 device_flags;
-
 	struct device_node *phy_node;
-	const struct fs_mii_bus_info *bus_info;
 
 	int rx_ring, tx_ring;	/* number of buffers on rx     */
-	__u8 macaddr[ETH_ALEN];	/* mac address                 */
 	int rx_copybreak;	/* limit we copy small frames  */
 	int napi_weight;	/* NAPI weight                 */
 
-- 
GitLab


From 9359a48c65a3c2723d469ba11889c56387e4395a Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 4 Aug 2023 15:30:15 +0200
Subject: [PATCH 0977/1806] net: fs_enet: Remove has_phy field in
 fs_platform_info struct

Since commit 3dd82a1ea724 ("[POWERPC] CPM: Always use new binding.")
has_phy field is never set.

Remove dead code and remove the field.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/bb5264e09e18f0ce8a0dbee399926a59f33cb248.1691155346.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fs_enet/mac-fec.c | 14 --------------
 include/linux/fs_enet_pd.h                       |  1 -
 2 files changed, 15 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index f609dc112458c..cdc89d83cf075 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -339,11 +339,7 @@ static void restart(struct net_device *dev)
 static void stop(struct net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
-	const struct fs_platform_info *fpi = fep->fpi;
 	struct fec __iomem *fecp = fep->fec.fecp;
-
-	struct fec_info *feci = dev->phydev->mdio.bus->priv;
-
 	int i;
 
 	if ((FR(fecp, ecntrl) & FEC_ECNTRL_ETHER_EN) == 0)
@@ -363,16 +359,6 @@ static void stop(struct net_device *dev)
 	FC(fecp, ecntrl, FEC_ECNTRL_ETHER_EN);
 
 	fs_cleanup_bds(dev);
-
-	/* shut down FEC1? that's where the mii bus is */
-	if (fpi->has_phy) {
-		FS(fecp, r_cntrl, fpi->use_rmii ?
-				FEC_RCNTRL_RMII_MODE :
-				FEC_RCNTRL_MII_MODE);	/* MII/RMII enable */
-		FS(fecp, ecntrl, FEC_ECNTRL_PINMUX | FEC_ECNTRL_ETHER_EN);
-		FW(fecp, ievent, FEC_ENET_MII);
-		FW(fecp, mii_speed, feci->mii_speed);
-	}
 }
 
 static void napi_clear_event_fs(struct net_device *dev)
diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h
index a1905e41c1677..2b351b676467c 100644
--- a/include/linux/fs_enet_pd.h
+++ b/include/linux/fs_enet_pd.h
@@ -123,7 +123,6 @@ struct fs_platform_info {
 	int napi_weight;	/* NAPI weight                 */
 
 	int use_rmii;		/* use RMII mode 	       */
-	int has_phy;            /* if the network is phy container as well...*/
 
 	struct clk *clk_per;	/* 'per' clock for register access */
 };
-- 
GitLab


From 62e106c802c555801b341885067dd8ffbf96835d Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 4 Aug 2023 15:30:16 +0200
Subject: [PATCH 0978/1806] net: fs_enet: Remove stale prototypes from
 fsl_soc.c

Commit 3dd82a1ea724 ("[POWERPC] CPM: Always use new binding.")
removed last use of init_fec_ioports() and init_fcc_ioports().

Remove stale prototypes then don't include anymore fs_enet_pd.h
which was only included to provide fs_platform_info structure
for the prototypes.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/f2f2db5dce3242eaa4a2aad6c226ba587fb0f513.1691155347.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 arch/powerpc/sysdev/fsl_soc.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index 68709743450e3..c11771542bec2 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -23,7 +23,6 @@
 #include <linux/phy.h>
 #include <linux/spi/spi.h>
 #include <linux/fsl_devices.h>
-#include <linux/fs_enet_pd.h>
 #include <linux/fs_uart_pd.h>
 #include <linux/reboot.h>
 
@@ -37,8 +36,6 @@
 #include <asm/cpm2.h>
 #include <asm/fsl_hcalls.h>	/* For the Freescale hypervisor */
 
-extern void init_fcc_ioports(struct fs_platform_info*);
-extern void init_fec_ioports(struct fs_platform_info*);
 extern void init_smc_ioports(struct fs_uart_platform_info*);
 static phys_addr_t immrbase = -1;
 
-- 
GitLab


From 7a76918371fe04667528142554a3f26a8879e8ab Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 4 Aug 2023 15:30:17 +0200
Subject: [PATCH 0979/1806] net: fs_enet: Move struct fs_platform_info into
 fs_enet.h

struct fs_platform_info is only used in fs_enet ethernet driver since
commit 3dd82a1ea724 ("[POWERPC] CPM: Always use new binding.").

Stale prototypes using fs_platform_info were left over in
arch/powerpc/sysdev/fsl_soc.c but they are now removed by
previous patch.

Move struct fs_platform_info into fs_enet.h

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/f882d6b0b7075d0d8435310634ceaa2cc8e9938f.1691155347.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/freescale/fs_enet/fs_enet.h  | 19 ++++++++++++++++++-
 .../net/ethernet/freescale/fs_enet/mii-fec.c  |  1 +
 include/linux/fs_enet_pd.h                    | 16 ----------------
 3 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
index cb419aef8d1b8..d371072fff608 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
@@ -2,6 +2,7 @@
 #ifndef FS_ENET_H
 #define FS_ENET_H
 
+#include <linux/clk.h>
 #include <linux/mii.h>
 #include <linux/netdevice.h>
 #include <linux/types.h>
@@ -9,7 +10,6 @@
 #include <linux/phy.h>
 #include <linux/dma-mapping.h>
 
-#include <linux/fs_enet_pd.h>
 #include <asm/fs_pd.h>
 
 #ifdef CONFIG_CPM1
@@ -118,6 +118,23 @@ struct phy_info {
 #define ENET_RX_ALIGN  16
 #define ENET_RX_FRSIZE L1_CACHE_ALIGN(PKT_MAXBUF_SIZE + ENET_RX_ALIGN - 1)
 
+struct fs_platform_info {
+	/* device specific information */
+	u32 cp_command;		/* CPM page/sblock/mcn */
+
+	u32 dpram_offset;
+
+	struct device_node *phy_node;
+
+	int rx_ring, tx_ring;	/* number of buffers on rx	*/
+	int rx_copybreak;	/* limit we copy small frames	*/
+	int napi_weight;	/* NAPI weight			*/
+
+	int use_rmii;		/* use RMII mode		*/
+
+	struct clk *clk_per;	/* 'per' clock for register access */
+};
+
 struct fs_enet_private {
 	struct napi_struct napi;
 	struct device *dev;	/* pointer back to the device (must be initialized first) */
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
index 1910df250c33e..a1e777a4b75f6 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
@@ -31,6 +31,7 @@
 #include <linux/bitops.h>
 #include <linux/platform_device.h>
 #include <linux/of_address.h>
+#include <linux/of_mdio.h>
 #include <linux/of_platform.h>
 #include <linux/pgtable.h>
 
diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h
index 2b351b676467c..7c9897dab558d 100644
--- a/include/linux/fs_enet_pd.h
+++ b/include/linux/fs_enet_pd.h
@@ -110,22 +110,6 @@ struct fs_mii_bb_platform_info {
 	int irq[32]; 	/* irqs per phy's */
 };
 
-struct fs_platform_info {
-	/* device specific information */
-	u32 cp_command;		/* CPM page/sblock/mcn */
-
-	u32 dpram_offset;
-	
-	struct device_node *phy_node;
-
-	int rx_ring, tx_ring;	/* number of buffers on rx     */
-	int rx_copybreak;	/* limit we copy small frames  */
-	int napi_weight;	/* NAPI weight                 */
-
-	int use_rmii;		/* use RMII mode 	       */
-
-	struct clk *clk_per;	/* 'per' clock for register access */
-};
 struct fs_mii_fec_platform_info {
 	u32 irq[32];
 	u32 mii_speed;
-- 
GitLab


From 33deffc9f19f292f183a3d4f5632aba692a3a555 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 4 Aug 2023 15:30:18 +0200
Subject: [PATCH 0980/1806] net: fs_enet: Don't include fs_enet_pd.h when not
 needed

Three platforms in arch/powerpc/platforms/8xx/ include fs_enet_pd.h
but don't use anything from it.

Remove the includes.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/de62ad1261a801c4a8ae4238bd4842ff278d2ddf.1691155347.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 arch/powerpc/platforms/8xx/adder875.c        | 1 -
 arch/powerpc/platforms/8xx/mpc885ads_setup.c | 1 -
 arch/powerpc/platforms/8xx/tqm8xx_setup.c    | 1 -
 3 files changed, 3 deletions(-)

diff --git a/arch/powerpc/platforms/8xx/adder875.c b/arch/powerpc/platforms/8xx/adder875.c
index 7e83eb6746f4a..f6bd232f83230 100644
--- a/arch/powerpc/platforms/8xx/adder875.c
+++ b/arch/powerpc/platforms/8xx/adder875.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/init.h>
-#include <linux/fs_enet_pd.h>
 #include <linux/of_platform.h>
 
 #include <asm/time.h>
diff --git a/arch/powerpc/platforms/8xx/mpc885ads_setup.c b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
index 2fc7cacbcd968..c7c4f082b8386 100644
--- a/arch/powerpc/platforms/8xx/mpc885ads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
@@ -21,7 +21,6 @@
 #include <linux/device.h>
 #include <linux/delay.h>
 
-#include <linux/fs_enet_pd.h>
 #include <linux/fs_uart_pd.h>
 #include <linux/fsl_devices.h>
 #include <linux/mii.h>
diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
index 7d8eb50bb9cd3..6e56be852b2c7 100644
--- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
@@ -24,7 +24,6 @@
 #include <linux/device.h>
 #include <linux/delay.h>
 
-#include <linux/fs_enet_pd.h>
 #include <linux/fs_uart_pd.h>
 #include <linux/fsl_devices.h>
 #include <linux/mii.h>
-- 
GitLab


From 7149b38dc7cbc77548afd65e4bb4d4b11dca8670 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 4 Aug 2023 15:30:19 +0200
Subject: [PATCH 0981/1806] net: fs_enet: Remove linux/fs_enet_pd.h

linux/fs_enet_pd.h is not used anymore.

Remove it.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/5be102791c987792ad127b15543ee6715394cf67.1691155347.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                |   1 -
 include/linux/fs_enet_pd.h | 118 -------------------------------------
 2 files changed, 119 deletions(-)
 delete mode 100644 include/linux/fs_enet_pd.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 08bcf3a7c482d..6efcd87136829 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8371,7 +8371,6 @@ L:	linuxppc-dev@lists.ozlabs.org
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/freescale/fs_enet/
-F:	include/linux/fs_enet_pd.h
 
 FREESCALE SOC SOUND DRIVERS
 M:	Shengjiu Wang <shengjiu.wang@gmail.com>
diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h
deleted file mode 100644
index 7c9897dab558d..0000000000000
--- a/include/linux/fs_enet_pd.h
+++ /dev/null
@@ -1,118 +0,0 @@
-/*
- * Platform information definitions for the
- * universal Freescale Ethernet driver.
- *
- * Copyright (c) 2003 Intracom S.A. 
- *  by Pantelis Antoniou <panto@intracom.gr>
- *
- * 2005 (c) MontaVista Software, Inc. 
- * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License 
- * version 2. This program is licensed "as is" without any warranty of any 
- * kind, whether express or implied.
- */
-
-#ifndef FS_ENET_PD_H
-#define FS_ENET_PD_H
-
-#include <linux/clk.h>
-#include <linux/string.h>
-#include <linux/of_mdio.h>
-#include <linux/if_ether.h>
-#include <asm/types.h>
-
-#define FS_ENET_NAME	"fs_enet"
-
-enum fs_id {
-	fsid_fec1,
-	fsid_fec2,
-	fsid_fcc1,
-	fsid_fcc2,
-	fsid_fcc3,
-	fsid_scc1,
-	fsid_scc2,
-	fsid_scc3,
-	fsid_scc4,
-};
-
-#define FS_MAX_INDEX	9
-
-static inline int fs_get_fec_index(enum fs_id id)
-{
-	if (id >= fsid_fec1 && id <= fsid_fec2)
-		return id - fsid_fec1;
-	return -1;
-}
-
-static inline int fs_get_fcc_index(enum fs_id id)
-{
-	if (id >= fsid_fcc1 && id <= fsid_fcc3)
-		return id - fsid_fcc1;
-	return -1;
-}
-
-static inline int fs_get_scc_index(enum fs_id id)
-{
-	if (id >= fsid_scc1 && id <= fsid_scc4)
-		return id - fsid_scc1;
-	return -1;
-}
-
-static inline int fs_fec_index2id(int index)
-{
-	int id = fsid_fec1 + index - 1;
-	if (id >= fsid_fec1 && id <= fsid_fec2)
-		return id;
-	return FS_MAX_INDEX;
-		}
-
-static inline int fs_fcc_index2id(int index)
-{
-	int id = fsid_fcc1 + index - 1;
-	if (id >= fsid_fcc1 && id <= fsid_fcc3)
-		return id;
-	return FS_MAX_INDEX;
-}
-
-static inline int fs_scc_index2id(int index)
-{
-	int id = fsid_scc1 + index - 1;
-	if (id >= fsid_scc1 && id <= fsid_scc4)
-		return id;
-	return FS_MAX_INDEX;
-}
-
-enum fs_mii_method {
-	fsmii_fixed,
-	fsmii_fec,
-	fsmii_bitbang,
-};
-
-enum fs_ioport {
-	fsiop_porta,
-	fsiop_portb,
-	fsiop_portc,
-	fsiop_portd,
-	fsiop_porte,
-};
-
-struct fs_mii_bit {
-	u32 offset;
-	u8 bit;
-	u8 polarity;
-};
-struct fs_mii_bb_platform_info {
-	struct fs_mii_bit 	mdio_dir;
-	struct fs_mii_bit 	mdio_dat;
-	struct fs_mii_bit	mdc_dat;
-	int delay;	/* delay in us         */
-	int irq[32]; 	/* irqs per phy's */
-};
-
-struct fs_mii_fec_platform_info {
-	u32 irq[32];
-	u32 mii_speed;
-};
-
-#endif
-- 
GitLab


From 5e6cb39a256dd5a30e657d57e93f2e009f34ec4e Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 4 Aug 2023 15:30:20 +0200
Subject: [PATCH 0982/1806] net: fs_enet: Use cpm_muram_xxx() functions instead
 of cpm_dpxxx() macros

cpm_dpxxx() macros are now always referring to cpm_muram_xxx() functions
directly since commit 3dd82a1ea724 ("[POWERPC] CPM: Always use new
binding.")

Use cpm_muram_xxx() functions directly so that the cpm_dpxxx() macros
can be removed in the near future.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/2400b3156891adb653dc387fff6393de10cf2b24.1691155347.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fs_enet/mac-fcc.c | 2 +-
 drivers/net/ethernet/freescale/fs_enet/mac-scc.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index ce63fd56df89f..d903a9012db0f 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -105,7 +105,7 @@ static int do_pd_setup(struct fs_enet_private *fep)
 		goto out_ep;
 
 	fep->fcc.mem = (void __iomem *)cpm2_immr;
-	fpi->dpram_offset = cpm_dpalloc(128, 32);
+	fpi->dpram_offset = cpm_muram_alloc(128, 32);
 	if (IS_ERR_VALUE(fpi->dpram_offset)) {
 		ret = fpi->dpram_offset;
 		goto out_fcccp;
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index 66d40da5cde00..a64cb6270515a 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -133,13 +133,13 @@ static int allocate_bd(struct net_device *dev)
 	struct fs_enet_private *fep = netdev_priv(dev);
 	const struct fs_platform_info *fpi = fep->fpi;
 
-	fep->ring_mem_addr = cpm_dpalloc((fpi->tx_ring + fpi->rx_ring) *
-					 sizeof(cbd_t), 8);
+	fep->ring_mem_addr = cpm_muram_alloc((fpi->tx_ring + fpi->rx_ring) *
+					     sizeof(cbd_t), 8);
 	if (IS_ERR_VALUE(fep->ring_mem_addr))
 		return -ENOMEM;
 
 	fep->ring_base = (void __iomem __force*)
-		cpm_dpram_addr(fep->ring_mem_addr);
+		cpm_muram_addr(fep->ring_mem_addr);
 
 	return 0;
 }
@@ -149,7 +149,7 @@ static void free_bd(struct net_device *dev)
 	struct fs_enet_private *fep = netdev_priv(dev);
 
 	if (fep->ring_base)
-		cpm_dpfree(fep->ring_mem_addr);
+		cpm_muram_free(fep->ring_mem_addr);
 }
 
 static void cleanup_data(struct net_device *dev)
-- 
GitLab


From 8958ef511a01d395234638c68a77a226cf3f541f Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Mon, 7 Aug 2023 09:25:52 +0800
Subject: [PATCH 0983/1806] team: add __exit modifier to team_nl_fini()

team_nl_fini is only called when the module exits, so add the __exit
modifier to it.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230807012556.3146071-2-shaozhengchao@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/team/team.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index bc50fc3f69135..e4fe70a71b400 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2892,7 +2892,7 @@ static int __init team_nl_init(void)
 	return genl_register_family(&team_nl_family);
 }
 
-static void team_nl_fini(void)
+static void __exit team_nl_fini(void)
 {
 	genl_unregister_family(&team_nl_family);
 }
-- 
GitLab


From adac119421c30666623c4849bd93731992a0f123 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Mon, 7 Aug 2023 09:25:53 +0800
Subject: [PATCH 0984/1806] team: remove unreferenced header in broadcast and
 roundrobin files

Because linux/errno.h is unreferenced in broadcast and roundrobin
files, so remove it.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230807012556.3146071-3-shaozhengchao@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/team/team_mode_broadcast.c  | 1 -
 drivers/net/team/team_mode_roundrobin.c | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/net/team/team_mode_broadcast.c b/drivers/net/team/team_mode_broadcast.c
index 313a3e2d68bf6..61d7d79f0c363 100644
--- a/drivers/net/team/team_mode_broadcast.c
+++ b/drivers/net/team/team_mode_broadcast.c
@@ -8,7 +8,6 @@
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/errno.h>
 #include <linux/netdevice.h>
 #include <linux/if_team.h>
 
diff --git a/drivers/net/team/team_mode_roundrobin.c b/drivers/net/team/team_mode_roundrobin.c
index 3ec63de97ae31..dd405d82c6ac5 100644
--- a/drivers/net/team/team_mode_roundrobin.c
+++ b/drivers/net/team/team_mode_roundrobin.c
@@ -8,7 +8,6 @@
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/errno.h>
 #include <linux/netdevice.h>
 #include <linux/if_team.h>
 
-- 
GitLab


From de3ecc4fd8bf201c5cd02dc49687fb1506cebb45 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Mon, 7 Aug 2023 09:25:54 +0800
Subject: [PATCH 0985/1806] team: change the init function in the team_option
 structure to void

Because the init function in the team_option structure always returns 0,
so change the init function to void and remove redundant code.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230807012556.3146071-4-shaozhengchao@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/team/team.c                   |  8 ++------
 drivers/net/team/team_mode_activebackup.c |  5 ++---
 drivers/net/team/team_mode_loadbalance.c  | 15 ++++++---------
 include/linux/if_team.h                   |  2 +-
 4 files changed, 11 insertions(+), 19 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index e4fe70a71b400..b88e1c451e074 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -149,7 +149,6 @@ static int __team_option_inst_add(struct team *team, struct team_option *option,
 	struct team_option_inst *opt_inst;
 	unsigned int array_size;
 	unsigned int i;
-	int err;
 
 	array_size = option->array_size;
 	if (!array_size)
@@ -165,11 +164,8 @@ static int __team_option_inst_add(struct team *team, struct team_option *option,
 		opt_inst->changed = true;
 		opt_inst->removed = false;
 		list_add_tail(&opt_inst->list, &team->option_inst_list);
-		if (option->init) {
-			err = option->init(team, &opt_inst->info);
-			if (err)
-				return err;
-		}
+		if (option->init)
+			option->init(team, &opt_inst->info);
 
 	}
 	return 0;
diff --git a/drivers/net/team/team_mode_activebackup.c b/drivers/net/team/team_mode_activebackup.c
index 3147a4fdf8d96..44d604f1c5126 100644
--- a/drivers/net/team/team_mode_activebackup.c
+++ b/drivers/net/team/team_mode_activebackup.c
@@ -57,11 +57,10 @@ static void ab_port_leave(struct team *team, struct team_port *port)
 	}
 }
 
-static int ab_active_port_init(struct team *team,
-			       struct team_option_inst_info *info)
+static void ab_active_port_init(struct team *team,
+				struct team_option_inst_info *info)
 {
 	ab_priv(team)->ap_opt_inst_info = info;
-	return 0;
 }
 
 static int ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx)
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index 18d99fda997cf..50c015cd06820 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -361,14 +361,13 @@ static int lb_tx_method_set(struct team *team, struct team_gsetter_ctx *ctx)
 	return 0;
 }
 
-static int lb_tx_hash_to_port_mapping_init(struct team *team,
-					   struct team_option_inst_info *info)
+static void lb_tx_hash_to_port_mapping_init(struct team *team,
+					    struct team_option_inst_info *info)
 {
 	struct lb_priv *lb_priv = get_lb_priv(team);
 	unsigned char hash = info->array_index;
 
 	LB_HTPM_OPT_INST_INFO_BY_HASH(lb_priv, hash) = info;
-	return 0;
 }
 
 static int lb_tx_hash_to_port_mapping_get(struct team *team,
@@ -401,14 +400,13 @@ static int lb_tx_hash_to_port_mapping_set(struct team *team,
 	return -ENODEV;
 }
 
-static int lb_hash_stats_init(struct team *team,
-			      struct team_option_inst_info *info)
+static void lb_hash_stats_init(struct team *team,
+			       struct team_option_inst_info *info)
 {
 	struct lb_priv *lb_priv = get_lb_priv(team);
 	unsigned char hash = info->array_index;
 
 	lb_priv->ex->stats.info[hash].opt_inst_info = info;
-	return 0;
 }
 
 static int lb_hash_stats_get(struct team *team, struct team_gsetter_ctx *ctx)
@@ -421,14 +419,13 @@ static int lb_hash_stats_get(struct team *team, struct team_gsetter_ctx *ctx)
 	return 0;
 }
 
-static int lb_port_stats_init(struct team *team,
-			      struct team_option_inst_info *info)
+static void lb_port_stats_init(struct team *team,
+			       struct team_option_inst_info *info)
 {
 	struct team_port *port = info->port;
 	struct lb_port_priv *lb_port_priv = get_lb_port_priv(port);
 
 	lb_port_priv->stats_info.opt_inst_info = info;
-	return 0;
 }
 
 static int lb_port_stats_get(struct team *team, struct team_gsetter_ctx *ctx)
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index 8de6b6e678295..fc01c3cfe86d6 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -162,7 +162,7 @@ struct team_option {
 	bool per_port;
 	unsigned int array_size; /* != 0 means the option is array */
 	enum team_option_type type;
-	int (*init)(struct team *team, struct team_option_inst_info *info);
+	void (*init)(struct team *team, struct team_option_inst_info *info);
 	int (*getter)(struct team *team, struct team_gsetter_ctx *ctx);
 	int (*setter)(struct team *team, struct team_gsetter_ctx *ctx);
 };
-- 
GitLab


From c3b41f4c7b7ce573f379c0053e3c86e722562659 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Mon, 7 Aug 2023 09:25:55 +0800
Subject: [PATCH 0986/1806] team: change the getter function in the team_option
 structure to void

Because the getter function in the team_option structure always returns 0,
so change the getter function to void and remove redundant code.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230807012556.3146071-5-shaozhengchao@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/team/team.c                   | 52 ++++++++++-------------
 drivers/net/team/team_mode_activebackup.c |  3 +-
 drivers/net/team/team_mode_loadbalance.c  | 24 ++++-------
 include/linux/if_team.h                   |  2 +-
 4 files changed, 33 insertions(+), 48 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index b88e1c451e074..8243563a40f0a 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -358,7 +358,9 @@ static int team_option_get(struct team *team,
 {
 	if (!opt_inst->option->getter)
 		return -EOPNOTSUPP;
-	return opt_inst->option->getter(team, ctx);
+
+	opt_inst->option->getter(team, ctx);
+	return 0;
 }
 
 static int team_option_set(struct team *team,
@@ -1373,10 +1375,9 @@ static int team_port_del(struct team *team, struct net_device *port_dev)
  * Net device ops
  *****************/
 
-static int team_mode_option_get(struct team *team, struct team_gsetter_ctx *ctx)
+static void team_mode_option_get(struct team *team, struct team_gsetter_ctx *ctx)
 {
 	ctx->data.str_val = team->mode->kind;
-	return 0;
 }
 
 static int team_mode_option_set(struct team *team, struct team_gsetter_ctx *ctx)
@@ -1384,11 +1385,10 @@ static int team_mode_option_set(struct team *team, struct team_gsetter_ctx *ctx)
 	return team_change_mode(team, ctx->data.str_val);
 }
 
-static int team_notify_peers_count_get(struct team *team,
-				       struct team_gsetter_ctx *ctx)
+static void team_notify_peers_count_get(struct team *team,
+					struct team_gsetter_ctx *ctx)
 {
 	ctx->data.u32_val = team->notify_peers.count;
-	return 0;
 }
 
 static int team_notify_peers_count_set(struct team *team,
@@ -1398,11 +1398,10 @@ static int team_notify_peers_count_set(struct team *team,
 	return 0;
 }
 
-static int team_notify_peers_interval_get(struct team *team,
-					  struct team_gsetter_ctx *ctx)
+static void team_notify_peers_interval_get(struct team *team,
+					   struct team_gsetter_ctx *ctx)
 {
 	ctx->data.u32_val = team->notify_peers.interval;
-	return 0;
 }
 
 static int team_notify_peers_interval_set(struct team *team,
@@ -1412,11 +1411,10 @@ static int team_notify_peers_interval_set(struct team *team,
 	return 0;
 }
 
-static int team_mcast_rejoin_count_get(struct team *team,
-				       struct team_gsetter_ctx *ctx)
+static void team_mcast_rejoin_count_get(struct team *team,
+					struct team_gsetter_ctx *ctx)
 {
 	ctx->data.u32_val = team->mcast_rejoin.count;
-	return 0;
 }
 
 static int team_mcast_rejoin_count_set(struct team *team,
@@ -1426,11 +1424,10 @@ static int team_mcast_rejoin_count_set(struct team *team,
 	return 0;
 }
 
-static int team_mcast_rejoin_interval_get(struct team *team,
-					  struct team_gsetter_ctx *ctx)
+static void team_mcast_rejoin_interval_get(struct team *team,
+					   struct team_gsetter_ctx *ctx)
 {
 	ctx->data.u32_val = team->mcast_rejoin.interval;
-	return 0;
 }
 
 static int team_mcast_rejoin_interval_set(struct team *team,
@@ -1440,13 +1437,12 @@ static int team_mcast_rejoin_interval_set(struct team *team,
 	return 0;
 }
 
-static int team_port_en_option_get(struct team *team,
-				   struct team_gsetter_ctx *ctx)
+static void team_port_en_option_get(struct team *team,
+				    struct team_gsetter_ctx *ctx)
 {
 	struct team_port *port = ctx->info->port;
 
 	ctx->data.bool_val = team_port_enabled(port);
-	return 0;
 }
 
 static int team_port_en_option_set(struct team *team,
@@ -1461,13 +1457,12 @@ static int team_port_en_option_set(struct team *team,
 	return 0;
 }
 
-static int team_user_linkup_option_get(struct team *team,
-				       struct team_gsetter_ctx *ctx)
+static void team_user_linkup_option_get(struct team *team,
+					struct team_gsetter_ctx *ctx)
 {
 	struct team_port *port = ctx->info->port;
 
 	ctx->data.bool_val = port->user.linkup;
-	return 0;
 }
 
 static void __team_carrier_check(struct team *team);
@@ -1483,13 +1478,12 @@ static int team_user_linkup_option_set(struct team *team,
 	return 0;
 }
 
-static int team_user_linkup_en_option_get(struct team *team,
-					  struct team_gsetter_ctx *ctx)
+static void team_user_linkup_en_option_get(struct team *team,
+					   struct team_gsetter_ctx *ctx)
 {
 	struct team_port *port = ctx->info->port;
 
 	ctx->data.bool_val = port->user.linkup_enabled;
-	return 0;
 }
 
 static int team_user_linkup_en_option_set(struct team *team,
@@ -1503,13 +1497,12 @@ static int team_user_linkup_en_option_set(struct team *team,
 	return 0;
 }
 
-static int team_priority_option_get(struct team *team,
-				    struct team_gsetter_ctx *ctx)
+static void team_priority_option_get(struct team *team,
+				     struct team_gsetter_ctx *ctx)
 {
 	struct team_port *port = ctx->info->port;
 
 	ctx->data.s32_val = port->priority;
-	return 0;
 }
 
 static int team_priority_option_set(struct team *team,
@@ -1525,13 +1518,12 @@ static int team_priority_option_set(struct team *team,
 	return 0;
 }
 
-static int team_queue_id_option_get(struct team *team,
-				    struct team_gsetter_ctx *ctx)
+static void team_queue_id_option_get(struct team *team,
+				     struct team_gsetter_ctx *ctx)
 {
 	struct team_port *port = ctx->info->port;
 
 	ctx->data.u32_val = port->queue_id;
-	return 0;
 }
 
 static int team_queue_id_option_set(struct team *team,
diff --git a/drivers/net/team/team_mode_activebackup.c b/drivers/net/team/team_mode_activebackup.c
index 44d604f1c5126..e0f599e2a51dd 100644
--- a/drivers/net/team/team_mode_activebackup.c
+++ b/drivers/net/team/team_mode_activebackup.c
@@ -63,7 +63,7 @@ static void ab_active_port_init(struct team *team,
 	ab_priv(team)->ap_opt_inst_info = info;
 }
 
-static int ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx)
+static void ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx)
 {
 	struct team_port *active_port;
 
@@ -73,7 +73,6 @@ static int ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx)
 		ctx->data.u32_val = active_port->dev->ifindex;
 	else
 		ctx->data.u32_val = 0;
-	return 0;
 }
 
 static int ab_active_port_set(struct team *team, struct team_gsetter_ctx *ctx)
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index 50c015cd06820..2f1573f253ecd 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -242,19 +242,18 @@ drop:
 	return false;
 }
 
-static int lb_bpf_func_get(struct team *team, struct team_gsetter_ctx *ctx)
+static void lb_bpf_func_get(struct team *team, struct team_gsetter_ctx *ctx)
 {
 	struct lb_priv *lb_priv = get_lb_priv(team);
 
 	if (!lb_priv->ex->orig_fprog) {
 		ctx->data.bin_val.len = 0;
 		ctx->data.bin_val.ptr = NULL;
-		return 0;
+		return;
 	}
 	ctx->data.bin_val.len = lb_priv->ex->orig_fprog->len *
 				sizeof(struct sock_filter);
 	ctx->data.bin_val.ptr = lb_priv->ex->orig_fprog->filter;
-	return 0;
 }
 
 static int __fprog_create(struct sock_fprog_kern **pfprog, u32 data_len,
@@ -335,7 +334,7 @@ static void lb_bpf_func_free(struct team *team)
 	bpf_prog_destroy(fp);
 }
 
-static int lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx)
+static void lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx)
 {
 	struct lb_priv *lb_priv = get_lb_priv(team);
 	lb_select_tx_port_func_t *func;
@@ -346,7 +345,6 @@ static int lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx)
 	name = lb_select_tx_port_get_name(func);
 	BUG_ON(!name);
 	ctx->data.str_val = name;
-	return 0;
 }
 
 static int lb_tx_method_set(struct team *team, struct team_gsetter_ctx *ctx)
@@ -370,8 +368,8 @@ static void lb_tx_hash_to_port_mapping_init(struct team *team,
 	LB_HTPM_OPT_INST_INFO_BY_HASH(lb_priv, hash) = info;
 }
 
-static int lb_tx_hash_to_port_mapping_get(struct team *team,
-					  struct team_gsetter_ctx *ctx)
+static void lb_tx_hash_to_port_mapping_get(struct team *team,
+					   struct team_gsetter_ctx *ctx)
 {
 	struct lb_priv *lb_priv = get_lb_priv(team);
 	struct team_port *port;
@@ -379,7 +377,6 @@ static int lb_tx_hash_to_port_mapping_get(struct team *team,
 
 	port = LB_HTPM_PORT_BY_HASH(lb_priv, hash);
 	ctx->data.u32_val = port ? port->dev->ifindex : 0;
-	return 0;
 }
 
 static int lb_tx_hash_to_port_mapping_set(struct team *team,
@@ -409,14 +406,13 @@ static void lb_hash_stats_init(struct team *team,
 	lb_priv->ex->stats.info[hash].opt_inst_info = info;
 }
 
-static int lb_hash_stats_get(struct team *team, struct team_gsetter_ctx *ctx)
+static void lb_hash_stats_get(struct team *team, struct team_gsetter_ctx *ctx)
 {
 	struct lb_priv *lb_priv = get_lb_priv(team);
 	unsigned char hash = ctx->info->array_index;
 
 	ctx->data.bin_val.ptr = &lb_priv->ex->stats.info[hash].stats;
 	ctx->data.bin_val.len = sizeof(struct lb_stats);
-	return 0;
 }
 
 static void lb_port_stats_init(struct team *team,
@@ -428,14 +424,13 @@ static void lb_port_stats_init(struct team *team,
 	lb_port_priv->stats_info.opt_inst_info = info;
 }
 
-static int lb_port_stats_get(struct team *team, struct team_gsetter_ctx *ctx)
+static void lb_port_stats_get(struct team *team, struct team_gsetter_ctx *ctx)
 {
 	struct team_port *port = ctx->info->port;
 	struct lb_port_priv *lb_port_priv = get_lb_port_priv(port);
 
 	ctx->data.bin_val.ptr = &lb_port_priv->stats_info.stats;
 	ctx->data.bin_val.len = sizeof(struct lb_stats);
-	return 0;
 }
 
 static void __lb_stats_info_refresh_prepare(struct lb_stats_info *s_info)
@@ -528,13 +523,12 @@ static void lb_stats_refresh(struct work_struct *work)
 	mutex_unlock(&team->lock);
 }
 
-static int lb_stats_refresh_interval_get(struct team *team,
-					 struct team_gsetter_ctx *ctx)
+static void lb_stats_refresh_interval_get(struct team *team,
+					  struct team_gsetter_ctx *ctx)
 {
 	struct lb_priv *lb_priv = get_lb_priv(team);
 
 	ctx->data.u32_val = lb_priv->ex->stats.refresh_interval;
-	return 0;
 }
 
 static int lb_stats_refresh_interval_set(struct team *team,
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index fc01c3cfe86d6..1b9b15a492fae 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -163,7 +163,7 @@ struct team_option {
 	unsigned int array_size; /* != 0 means the option is array */
 	enum team_option_type type;
 	void (*init)(struct team *team, struct team_option_inst_info *info);
-	int (*getter)(struct team *team, struct team_gsetter_ctx *ctx);
+	void (*getter)(struct team *team, struct team_gsetter_ctx *ctx);
 	int (*setter)(struct team *team, struct team_gsetter_ctx *ctx);
 };
 
-- 
GitLab


From 7790eaeb688f9ded41d90abafda98f0389008e03 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Mon, 7 Aug 2023 09:25:56 +0800
Subject: [PATCH 0987/1806] team: remove unused input parameters in
 lb_htpm_select_tx_port and lb_hash_select_tx_port

The input parameters "lb_priv" and "skb" in lb_htpm_select_tx_port and
lb_hash_select_tx_port are unused, so remove them.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230807012556.3146071-6-shaozhengchao@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/team/team_mode_loadbalance.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index 2f1573f253ecd..00f8989c29c0f 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -30,8 +30,6 @@ static rx_handler_result_t lb_receive(struct team *team, struct team_port *port,
 struct lb_priv;
 
 typedef struct team_port *lb_select_tx_port_func_t(struct team *,
-						   struct lb_priv *,
-						   struct sk_buff *,
 						   unsigned char);
 
 #define LB_TX_HASHTABLE_SIZE 256 /* hash is a char */
@@ -118,8 +116,6 @@ static void lb_tx_hash_to_port_mapping_null_port(struct team *team,
 
 /* Basic tx selection based solely by hash */
 static struct team_port *lb_hash_select_tx_port(struct team *team,
-						struct lb_priv *lb_priv,
-						struct sk_buff *skb,
 						unsigned char hash)
 {
 	int port_index = team_num_to_port_index(team, hash);
@@ -129,17 +125,16 @@ static struct team_port *lb_hash_select_tx_port(struct team *team,
 
 /* Hash to port mapping select tx port */
 static struct team_port *lb_htpm_select_tx_port(struct team *team,
-						struct lb_priv *lb_priv,
-						struct sk_buff *skb,
 						unsigned char hash)
 {
+	struct lb_priv *lb_priv = get_lb_priv(team);
 	struct team_port *port;
 
 	port = rcu_dereference_bh(LB_HTPM_PORT_BY_HASH(lb_priv, hash));
 	if (likely(port))
 		return port;
 	/* If no valid port in the table, fall back to simple hash */
-	return lb_hash_select_tx_port(team, lb_priv, skb, hash);
+	return lb_hash_select_tx_port(team, hash);
 }
 
 struct lb_select_tx_port {
@@ -229,7 +224,7 @@ static bool lb_transmit(struct team *team, struct sk_buff *skb)
 
 	hash = lb_get_skb_hash(lb_priv, skb);
 	select_tx_port_func = rcu_dereference_bh(lb_priv->select_tx_port_func);
-	port = select_tx_port_func(team, lb_priv, skb, hash);
+	port = select_tx_port_func(team, hash);
 	if (unlikely(!port))
 		goto drop;
 	if (team_dev_queue_xmit(team, port, skb))
-- 
GitLab


From 48d17c517a7af933346bd095e8ccc52b8477b274 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 7 Aug 2023 16:01:53 +0300
Subject: [PATCH 0988/1806] net: bcmasp: Prevent array undereflow in
 bcmasp_netfilt_get_init()

The "loc" value comes from the user and it can be negative leading to an
an array underflow when we check "priv->net_filters[loc].claimed".  Fix
this by changing the type to u32.

Fixes: c5d511c49587 ("net: bcmasp: Add support for wake on net filters")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Justin Chen <justin.chen@broadcom.com>
Link: https://lore.kernel.org/r/b3b47b25-01fc-4d9f-a6c3-e037ad4d71d7@moroto.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.c | 2 +-
 drivers/net/ethernet/broadcom/asp2/bcmasp.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index eb35ced1c8ba7..d63d321f3e7b0 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -640,7 +640,7 @@ bool bcmasp_netfilt_check_dup(struct bcmasp_intf *intf,
  * If no more open filters return NULL
  */
 struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf,
-						  int loc, bool wake_filter,
+						  u32 loc, bool wake_filter,
 						  bool init)
 {
 	struct bcmasp_net_filter *nfilter = NULL;
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
index 6bfcaa7f95a83..5b512f7f5e949 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
@@ -566,7 +566,7 @@ void bcmasp_disable_all_filters(struct bcmasp_intf *intf);
 void bcmasp_core_clock_set_intf(struct bcmasp_intf *intf, bool en);
 
 struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf,
-						  int loc, bool wake_filter,
+						  u32 loc, bool wake_filter,
 						  bool init);
 
 bool bcmasp_netfilt_check_dup(struct bcmasp_intf *intf,
-- 
GitLab


From ac1b8c978a7acce25a530b02e7b3f0e74ac931c8 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 7 Aug 2023 07:57:19 -0700
Subject: [PATCH 0989/1806] bnxt_en: Fix W=1 warning in bnxt_dcb.c from fortify
 memcpy()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following warning:

inlined from ‘bnxt_hwrm_queue_cos2bw_qcfg’ at drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c:165:3,
./include/linux/fortify-string.h:592:4: error: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror]
    __read_overflow2_field(q_size_field, size);
    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Modify the FW interface defintion of struct hwrm_queue_cos2bw_qcfg_output
to use an array of sub struct for the queue1 to queue7 fields.  Note that
the layout of the queue0 fields are different and these are not part of
the array.  This makes the code much cleaner by removing the pointer
arithmetic for memcpy().

Link: https://lore.kernel.org/netdev/20230727190726.1859515-2-kuba@kernel.org/
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20230807145720.159645-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c |  15 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 322 +++---------------
 2 files changed, 52 insertions(+), 285 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 31f85f3e23641..052a0821153e8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -144,7 +144,6 @@ static int bnxt_hwrm_queue_cos2bw_qcfg(struct bnxt *bp, struct ieee_ets *ets)
 	struct hwrm_queue_cos2bw_qcfg_output *resp;
 	struct hwrm_queue_cos2bw_qcfg_input *req;
 	struct bnxt_cos2bw_cfg cos2bw;
-	void *data;
 	int rc, i;
 
 	rc = hwrm_req_init(bp, req, HWRM_QUEUE_COS2BW_QCFG);
@@ -158,13 +157,19 @@ static int bnxt_hwrm_queue_cos2bw_qcfg(struct bnxt *bp, struct ieee_ets *ets)
 		return rc;
 	}
 
-	data = &resp->queue_id0 + offsetof(struct bnxt_cos2bw_cfg, queue_id);
-	for (i = 0; i < bp->max_tc; i++, data += sizeof(cos2bw.cfg)) {
+	for (i = 0; i < bp->max_tc; i++) {
 		int tc;
 
-		memcpy(&cos2bw.cfg, data, sizeof(cos2bw.cfg));
-		if (i == 0)
+		if (i == 0) {
 			cos2bw.queue_id = resp->queue_id0;
+			cos2bw.min_bw = resp->queue_id0_min_bw;
+			cos2bw.max_bw = resp->queue_id0_max_bw;
+			cos2bw.tsa = resp->queue_id0_tsa_assign;
+			cos2bw.pri_lvl = resp->queue_id0_pri_lvl;
+			cos2bw.bw_weight = resp->queue_id0_bw_weight;
+		} else {
+			memcpy(&cos2bw.cfg, &resp->cfg[i - 1], sizeof(cos2bw.cfg));
+		}
 
 		tc = bnxt_queue_to_tc(bp, cos2bw.queue_id);
 		if (tc < 0)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index b31de4cf6534b..fd38d5dcbc259 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -5739,286 +5739,48 @@ struct hwrm_queue_cos2bw_qcfg_output {
 	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST  0xffUL
 	u8	queue_id0_pri_lvl;
 	u8	queue_id0_bw_weight;
-	u8	queue_id1;
-	__le32	queue_id1_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id1_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id1_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID1_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id1_pri_lvl;
-	u8	queue_id1_bw_weight;
-	u8	queue_id2;
-	__le32	queue_id2_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id2_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id2_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID2_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id2_pri_lvl;
-	u8	queue_id2_bw_weight;
-	u8	queue_id3;
-	__le32	queue_id3_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id3_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id3_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID3_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id3_pri_lvl;
-	u8	queue_id3_bw_weight;
-	u8	queue_id4;
-	__le32	queue_id4_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id4_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id4_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID4_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id4_pri_lvl;
-	u8	queue_id4_bw_weight;
-	u8	queue_id5;
-	__le32	queue_id5_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id5_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id5_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID5_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id5_pri_lvl;
-	u8	queue_id5_bw_weight;
-	u8	queue_id6;
-	__le32	queue_id6_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id6_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id6_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID6_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id6_pri_lvl;
-	u8	queue_id6_bw_weight;
-	u8	queue_id7;
-	__le32	queue_id7_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id7_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id7_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID7_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id7_pri_lvl;
-	u8	queue_id7_bw_weight;
+	struct {
+		u8	queue_id;
+		__le32	queue_id_min_bw;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID
+		__le32	queue_id_max_bw;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID
+		u8	queue_id_tsa_assign;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_SP             0x0UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_ETS            0x1UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_RESERVED_FIRST 0x2UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_RESERVED_LAST  0xffUL
+		u8	queue_id_pri_lvl;
+		u8	queue_id_bw_weight;
+	} __packed cfg[7];
 	u8	unused_2[4];
 	u8	valid;
 };
-- 
GitLab


From 3d5ecada049f4afdad71be09295c4cd0bbf105c3 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 7 Aug 2023 07:57:20 -0700
Subject: [PATCH 0990/1806] bnxt_en: Fix W=stringop-overflow warning in
 bnxt_dcb.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following warning:

drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c: In function ‘bnxt_hwrm_queue_cos2bw_cfg’:
cc1: error: writing 12 bytes into a region of size 1 [-Werror=stringop-overflow ]
In file included from drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c:19:
drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h:6045:17: note: destination object ‘unused_0’ of size 1
 6045 |         u8      unused_0;

Fix it by modifying struct hwrm_queue_cos2bw_cfg_input to use an array
of sub struct similar to the previous patch.  This will eliminate the
pointer arithmetc to calculate the destination pointer passed to
memcpy().

Link: https://lore.kernel.org/netdev/CACKFLinikvXmKcxr4kjWO9TPYxTd2cb5agT1j=w9Qyj5-24s5A@mail.gmail.com/
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20230807145720.159645-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c |  11 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 322 +++---------------
 2 files changed, 49 insertions(+), 284 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 052a0821153e8..63e0670383852 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -98,7 +98,6 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets,
 {
 	struct hwrm_queue_cos2bw_cfg_input *req;
 	struct bnxt_cos2bw_cfg cos2bw;
-	void *data;
 	int rc, i;
 
 	rc = hwrm_req_init(bp, req, HWRM_QUEUE_COS2BW_CFG);
@@ -129,11 +128,15 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets,
 				cpu_to_le32((ets->tc_tx_bw[i] * 100) |
 					    BW_VALUE_UNIT_PERCENT1_100);
 		}
-		data = &req->unused_0 + qidx * (sizeof(cos2bw) - 4);
-		memcpy(data, &cos2bw.cfg, sizeof(cos2bw) - 4);
 		if (qidx == 0) {
 			req->queue_id0 = cos2bw.queue_id;
-			req->unused_0 = 0;
+			req->queue_id0_min_bw = cos2bw.min_bw;
+			req->queue_id0_max_bw = cos2bw.max_bw;
+			req->queue_id0_tsa_assign = cos2bw.tsa;
+			req->queue_id0_pri_lvl = cos2bw.pri_lvl;
+			req->queue_id0_bw_weight = cos2bw.bw_weight;
+		} else {
+			memcpy(&req->cfg[i - 1], &cos2bw.cfg, sizeof(cos2bw.cfg));
 		}
 	}
 	return hwrm_req_send(bp, req);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index fd38d5dcbc259..f178ed9899a9e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -5844,286 +5844,48 @@ struct hwrm_queue_cos2bw_cfg_input {
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST  0xffUL
 	u8	queue_id0_pri_lvl;
 	u8	queue_id0_bw_weight;
-	u8	queue_id1;
-	__le32	queue_id1_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id1_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id1_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id1_pri_lvl;
-	u8	queue_id1_bw_weight;
-	u8	queue_id2;
-	__le32	queue_id2_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id2_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id2_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id2_pri_lvl;
-	u8	queue_id2_bw_weight;
-	u8	queue_id3;
-	__le32	queue_id3_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id3_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id3_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id3_pri_lvl;
-	u8	queue_id3_bw_weight;
-	u8	queue_id4;
-	__le32	queue_id4_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id4_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id4_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id4_pri_lvl;
-	u8	queue_id4_bw_weight;
-	u8	queue_id5;
-	__le32	queue_id5_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id5_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id5_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id5_pri_lvl;
-	u8	queue_id5_bw_weight;
-	u8	queue_id6;
-	__le32	queue_id6_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id6_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id6_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id6_pri_lvl;
-	u8	queue_id6_bw_weight;
-	u8	queue_id7;
-	__le32	queue_id7_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id7_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id7_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id7_pri_lvl;
-	u8	queue_id7_bw_weight;
+	struct {
+		u8	queue_id;
+		__le32	queue_id_min_bw;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID
+		__le32	queue_id_max_bw;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID
+		u8	queue_id_tsa_assign;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_SP             0x0UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_ETS            0x1UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_RESERVED_FIRST 0x2UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_RESERVED_LAST  0xffUL
+		u8	queue_id_pri_lvl;
+		u8	queue_id_bw_weight;
+	} __packed cfg[7];
 	u8	unused_1[5];
 };
 
-- 
GitLab


From f1d152eb66a30aecd19f22ff2676a7cb2584a920 Mon Sep 17 00:00:00 2001
From: Lin Ma <linma@zju.edu.cn>
Date: Mon, 7 Aug 2023 17:13:47 +0800
Subject: [PATCH 0991/1806] rtnetlink: remove redundant checks for nlattr
 IFLA_BRIDGE_MODE

The commit d73ef2d69c0d ("rtnetlink: let rtnl_bridge_setlink checks
IFLA_BRIDGE_MODE length") added the nla_len check in rtnl_bridge_setlink,
which is the only caller for ndo_bridge_setlink handlers defined in
low-level driver codes. Hence, this patch cleanups the redundant checks in
each ndo_bridge_setlink handler function.

Suggested-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Lin Ma <linma@zju.edu.cn>
Acked-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230807091347.3804523-1-linma@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c           | 3 ---
 drivers/net/ethernet/emulex/benet/be_main.c         | 3 ---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c       | 3 ---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c   | 3 ---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 3 ---
 5 files changed, 15 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index eb168ca983b75..7be917a8da482 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -13132,9 +13132,6 @@ static int bnxt_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 		if (nla_type(attr) != IFLA_BRIDGE_MODE)
 			continue;
 
-		if (nla_len(attr) < sizeof(mode))
-			return -EINVAL;
-
 		mode = nla_get_u16(attr);
 		if (mode == bp->br_mode)
 			break;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 0616b5fe241cb..ad862ed7888ac 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4986,9 +4986,6 @@ static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 		if (nla_type(attr) != IFLA_BRIDGE_MODE)
 			continue;
 
-		if (nla_len(attr) < sizeof(mode))
-			return -EINVAL;
-
 		mode = nla_get_u16(attr);
 		if (BE3_chip(adapter) && mode == BRIDGE_MODE_VEPA)
 			return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 8eb9839a3ca69..dd03b017dfc51 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10042,9 +10042,6 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
 		if (nla_type(attr) != IFLA_BRIDGE_MODE)
 			continue;
 
-		if (nla_len(attr) < sizeof(mode))
-			return -EINVAL;
-
 		mode = nla_get_u16(attr);
 		status = ixgbe_configure_bridge_mode(adapter, mode);
 		if (status)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c8ec6467d4d16..ca80c220e4b0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4896,9 +4896,6 @@ static int mlx5e_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 		if (nla_type(attr) != IFLA_BRIDGE_MODE)
 			continue;
 
-		if (nla_len(attr) < sizeof(mode))
-			return -EINVAL;
-
 		mode = nla_get_u16(attr);
 		if (mode > BRIDGE_MODE_VEPA)
 			return -EINVAL;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index f18c791cf698f..de0a5d5ded305 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2108,9 +2108,6 @@ static int nfp_net_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 		if (nla_type(attr) != IFLA_BRIDGE_MODE)
 			continue;
 
-		if (nla_len(attr) < sizeof(mode))
-			return -EINVAL;
-
 		new_ctrl = nn->dp.ctrl;
 		mode = nla_get_u16(attr);
 		if (mode == BRIDGE_MODE_VEPA)
-- 
GitLab


From c009b903f8ccfce5844c91f005b0f152a5518526 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Mon, 7 Aug 2023 09:32:30 +0900
Subject: [PATCH 0992/1806] net: renesas: rswitch: Add runtime speed change
 support

The latest SoC version can support runtime speed change. So,
add detect SoC version by using soc_device_match() and then
reconfigure the hardware of this and SerDes if needed.

Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230807003231.1552062-2-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/renesas/rswitch.c | 27 +++++++++++++++++++++++---
 drivers/net/ethernet/renesas/rswitch.h |  1 +
 2 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 0ba7fb75d5893..fd3668b958345 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -20,6 +20,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/sys_soc.h>
 
 #include "rswitch.h"
 
@@ -1243,7 +1244,6 @@ static void rswitch_adjust_link(struct net_device *ndev)
 	struct rswitch_device *rdev = netdev_priv(ndev);
 	struct phy_device *phydev = ndev->phydev;
 
-	/* Current hardware has a restriction not to change speed at runtime */
 	if (phydev->link != rdev->etha->link) {
 		phy_print_status(phydev);
 		if (phydev->link)
@@ -1252,13 +1252,23 @@ static void rswitch_adjust_link(struct net_device *ndev)
 			phy_power_off(rdev->serdes);
 
 		rdev->etha->link = phydev->link;
+
+		if (!rdev->priv->etha_no_runtime_change &&
+		    phydev->speed != rdev->etha->speed) {
+			rdev->etha->speed = phydev->speed;
+
+			rswitch_etha_hw_init(rdev->etha, rdev->ndev->dev_addr);
+			phy_set_speed(rdev->serdes, rdev->etha->speed);
+		}
 	}
 }
 
 static void rswitch_phy_remove_link_mode(struct rswitch_device *rdev,
 					 struct phy_device *phydev)
 {
-	/* Current hardware has a restriction not to change speed at runtime */
+	if (!rdev->priv->etha_no_runtime_change)
+		return;
+
 	switch (rdev->etha->speed) {
 	case SPEED_2500:
 		phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Full_BIT);
@@ -1347,7 +1357,8 @@ static int rswitch_ether_port_init_one(struct rswitch_device *rdev)
 		err = rswitch_etha_hw_init(rdev->etha, rdev->ndev->dev_addr);
 		if (err < 0)
 			return err;
-		rdev->etha->operated = true;
+		if (rdev->priv->etha_no_runtime_change)
+			rdev->etha->operated = true;
 	}
 
 	err = rswitch_mii_register(rdev);
@@ -1853,8 +1864,14 @@ err_ts_queue_alloc:
 	return err;
 }
 
+static const struct soc_device_attribute rswitch_soc_no_speed_change[]  = {
+	{ .soc_id = "r8a779f0", .revision = "ES1.0" },
+	{ /* Sentinel */ }
+};
+
 static int renesas_eth_sw_probe(struct platform_device *pdev)
 {
+	const struct soc_device_attribute *attr;
 	struct rswitch_private *priv;
 	struct resource *res;
 	int ret;
@@ -1869,6 +1886,10 @@ static int renesas_eth_sw_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
+	attr = soc_device_match(rswitch_soc_no_speed_change);
+	if (attr)
+		priv->etha_no_runtime_change = true;
+
 	priv->ptp_priv = rcar_gen4_ptp_alloc(pdev);
 	if (!priv->ptp_priv)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h
index bb9ed971a97ca..54f397effbc6b 100644
--- a/drivers/net/ethernet/renesas/rswitch.h
+++ b/drivers/net/ethernet/renesas/rswitch.h
@@ -1011,6 +1011,7 @@ struct rswitch_private {
 	struct rswitch_etha etha[RSWITCH_NUM_PORTS];
 	struct rswitch_mfwd mfwd;
 
+	bool etha_no_runtime_change;
 	bool gwca_halt;
 };
 
-- 
GitLab


From 20f8be6b24da814912c09cdb5b3457f0a3ecf505 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Mon, 7 Aug 2023 09:32:31 +0900
Subject: [PATCH 0993/1806] net: renesas: rswitch: Add .[gs]et_link_ksettings
 support

Add .[gs]et_link_ksettings support by using
phy_ethtool_[gs]et_link_ksettings() functions.

Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230807003231.1552062-3-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/renesas/rswitch.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index fd3668b958345..6083b1c8e4fb9 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -1664,6 +1664,8 @@ static int rswitch_get_ts_info(struct net_device *ndev, struct ethtool_ts_info *
 
 static const struct ethtool_ops rswitch_ethtool_ops = {
 	.get_ts_info = rswitch_get_ts_info,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 static const struct of_device_id renesas_eth_sw_of_table[] = {
-- 
GitLab


From c67180efc507e04a87f22aa68bd7dd832db006b7 Mon Sep 17 00:00:00 2001
From: xu xin <xu.xin16@zte.com.cn>
Date: Mon, 7 Aug 2023 01:54:08 +0000
Subject: [PATCH 0994/1806] net/ipv4: return the real errno instead of -EINVAL

For now, No matter what error pointer ip_neigh_for_gw() returns,
ip_finish_output2() always return -EINVAL, which may mislead the upper
users.

For exemple, an application uses sendto to send an UDP packet, but when the
neighbor table overflows, sendto() will get a value of -EINVAL, and it will
cause users to waste a lot of time checking parameters for errors.

Return the real errno instead of -EINVAL.

Signed-off-by: xu xin <xu.xin16@zte.com.cn>
Reviewed-by: Yang Yang <yang.yang29@zte.com.cn>
Cc: Si Hao <si.hao@zte.com.cn>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://lore.kernel.org/r/20230807015408.248237-1-xu.xin16@zte.com.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ip_output.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6ba1a0fafbaab..f28c87533a465 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -236,7 +236,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
 	net_dbg_ratelimited("%s: No header cache and no neighbour!\n",
 			    __func__);
 	kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL);
-	return -EINVAL;
+	return PTR_ERR(neigh);
 }
 
 static int ip_finish_output_gso(struct net *net, struct sock *sk,
-- 
GitLab


From 794529c448008d8bc24d6e06c7528b7dbec99dfd Mon Sep 17 00:00:00 2001
From: Ziyang Xuan <william.xuanziyang@huawei.com>
Date: Mon, 7 Aug 2023 10:09:47 +0800
Subject: [PATCH 0995/1806] ipv6: exthdrs: Replace opencoded swap()
 implementation

Get a coccinelle warning as follows:
net/ipv6/exthdrs.c:800:29-30: WARNING opportunity for swap()

Use swap() to replace opencoded implementation.

Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230807020947.1991716-1-william.xuanziyang@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/exthdrs.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index f4bfccae003cc..4952ae7924505 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -648,7 +648,6 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb)
 	struct inet6_dev *idev = __in6_dev_get(skb->dev);
 	struct inet6_skb_parm *opt = IP6CB(skb);
 	struct in6_addr *addr = NULL;
-	struct in6_addr daddr;
 	int n, i;
 	struct ipv6_rt_hdr *hdr;
 	struct rt0_hdr *rthdr;
@@ -796,9 +795,7 @@ looped_back:
 		return -1;
 	}
 
-	daddr = *addr;
-	*addr = ipv6_hdr(skb)->daddr;
-	ipv6_hdr(skb)->daddr = daddr;
+	swap(*addr, ipv6_hdr(skb)->daddr);
 
 	ip6_route_input(skb);
 	if (skb_dst(skb)->error) {
-- 
GitLab


From ba4a734e1aa073b06412fc80ad81b54c4644d093 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Mon, 7 Aug 2023 09:10:22 +0200
Subject: [PATCH 0996/1806] net/tls: avoid TCP window full during ->read_sock()

When flushing the backlog after decoding a record we don't really
know how much data the caller want us to evaluate, so use INT_MAX
and 0 as arguments to tls_read_flush_backlog() to ensure we flush
at 128k of data. Otherwise we might be reading too much data and
trigger a TCP window full.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Link: https://lore.kernel.org/r/20230807071022.10091-1-hare@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 9c1f13541708d..5c122d7bb7847 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2240,7 +2240,6 @@ int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
 			tlm = tls_msg(skb);
 		} else {
 			struct tls_decrypt_arg darg;
-			int to_decrypt;
 
 			err = tls_rx_rec_wait(sk, NULL, true, released);
 			if (err <= 0)
@@ -2248,20 +2247,18 @@ int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
 
 			memset(&darg.inargs, 0, sizeof(darg.inargs));
 
-			rxm = strp_msg(tls_strp_msg(ctx));
-			tlm = tls_msg(tls_strp_msg(ctx));
-
-			to_decrypt = rxm->full_len - prot->overhead_size;
-
 			err = tls_rx_one_record(sk, NULL, &darg);
 			if (err < 0) {
 				tls_err_abort(sk, -EBADMSG);
 				goto read_sock_end;
 			}
 
-			released = tls_read_flush_backlog(sk, prot, rxm->full_len, to_decrypt,
-							  decrypted, &flushed_at);
+			released = tls_read_flush_backlog(sk, prot, INT_MAX,
+							  0, decrypted,
+							  &flushed_at);
 			skb = darg.skb;
+			rxm = strp_msg(skb);
+			tlm = tls_msg(skb);
 			decrypted += rxm->full_len;
 
 			tls_rx_rec_done(ctx);
-- 
GitLab


From 209bccbac9e6baa68308e1e236992ae3873e49dc Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 7 Aug 2023 22:21:11 +0800
Subject: [PATCH 0997/1806] net: fq: Remove unused typedef
 fq_flow_get_default_t

Commitbf9009bf21b5 ("net/fq_impl: drop get_default_func, move default flow to fq_tin")
remove its last user, so can remove it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230807142111.33524-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/fq.h | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/include/net/fq.h b/include/net/fq.h
index 07b5aff6ec583..99fbe4127b951 100644
--- a/include/net/fq.h
+++ b/include/net/fq.h
@@ -98,9 +98,4 @@ typedef bool fq_skb_filter_t(struct fq *,
 			     struct sk_buff *,
 			     void *);
 
-typedef struct fq_flow *fq_flow_get_default_t(struct fq *,
-					      struct fq_tin *,
-					      int idx,
-					      struct sk_buff *);
-
 #endif
-- 
GitLab


From b876b71a6ac24265848cff4f208e96bf82c32b29 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 7 Aug 2023 22:32:14 +0800
Subject: [PATCH 0998/1806] devlink: Remove unused
 devlink_dpipe_table_resource_set() declaration

Commit f655dacb59ac ("net: devlink: remove unused locked functions")
removed this but leave the declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230807143214.46648-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/devlink.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index a1a8e1b6e7dfc..f7fec0791acc2 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1743,9 +1743,6 @@ int devl_resource_size_get(struct devlink *devlink,
 int devl_dpipe_table_resource_set(struct devlink *devlink,
 				  const char *table_name, u64 resource_id,
 				  u64 resource_units);
-int devlink_dpipe_table_resource_set(struct devlink *devlink,
-				     const char *table_name, u64 resource_id,
-				     u64 resource_units);
 void devl_resource_occ_get_register(struct devlink *devlink,
 				    u64 resource_id,
 				    devlink_resource_occ_get_t *occ_get,
-- 
GitLab


From 2c2b88748fd5028a7771a864d46b1b78fb436a07 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 7 Aug 2023 14:00:51 -0700
Subject: [PATCH 0999/1806] docs: net: page_pool: de-duplicate the intro
 comment

In commit 82e896d992fa ("docs: net: page_pool: use kdoc to avoid
duplicating the information") I shied away from using the DOC:
comments when moving to kdoc for documenting page_pool API,
because I wasn't sure how familiar people are with it.

Turns out there is already a DOC: comment for the intro, which
is the same in both places, modulo what looks like minor rewording.
Use the version from Documentation/ but keep the contents with
the code.

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20230807210051.1014580-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/page_pool.rst | 18 ++----------------
 include/net/page_pool/helpers.h        | 24 ++++++++++++------------
 2 files changed, 14 insertions(+), 28 deletions(-)

diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst
index 68b82cea13e43..215ebc92752ca 100644
--- a/Documentation/networking/page_pool.rst
+++ b/Documentation/networking/page_pool.rst
@@ -4,22 +4,8 @@
 Page Pool API
 =============
 
-The page_pool allocator is optimized for the XDP mode that uses one frame
-per-page, but it can fallback on the regular page allocator APIs.
-
-Basic use involves replacing alloc_pages() calls with the
-page_pool_alloc_pages() call.  Drivers should use page_pool_dev_alloc_pages()
-replacing dev_alloc_pages().
-
-API keeps track of in-flight pages, in order to let API user know
-when it is safe to free a page_pool object.  Thus, API users
-must call page_pool_put_page() to free the page, or attach
-the page to a page_pool-aware objects like skbs marked with
-skb_mark_for_recycle().
-
-API user must call page_pool_put_page() once on a page, as it
-will either recycle the page, or in case of refcnt > 1, it will
-release the DMA mapping and in-flight state accounting.
+.. kernel-doc:: include/net/page_pool/helpers.h
+   :doc: page_pool allocator
 
 Architecture overview
 =====================
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 78df91804c878..94231533a3696 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -8,23 +8,23 @@
 /**
  * DOC: page_pool allocator
  *
- * This page_pool allocator is optimized for the XDP mode that
- * uses one-frame-per-page, but have fallbacks that act like the
+ * The page_pool allocator is optimized for the XDP mode that
+ * uses one frame per-page, but it can fallback on the
  * regular page allocator APIs.
  *
- * Basic use involve replacing alloc_pages() calls with the
- * page_pool_alloc_pages() call.  Drivers should likely use
+ * Basic use involves replacing alloc_pages() calls with the
+ * page_pool_alloc_pages() call.  Drivers should use
  * page_pool_dev_alloc_pages() replacing dev_alloc_pages().
  *
- * API keeps track of in-flight pages, in-order to let API user know
- * when it is safe to dealloactor page_pool object.  Thus, API users
- * must call page_pool_put_page() where appropriate and only attach
- * the page to a page_pool-aware objects, like skbs marked for recycling.
+ * API keeps track of in-flight pages, in order to let API user know
+ * when it is safe to free a page_pool object.  Thus, API users
+ * must call page_pool_put_page() to free the page, or attach
+ * the page to a page_pool-aware objects like skbs marked with
+ * skb_mark_for_recycle().
  *
- * API user must only call page_pool_put_page() once on a page, as it
- * will either recycle the page, or in case of elevated refcnt, it
- * will release the DMA mapping and in-flight state accounting.  We
- * hope to lift this requirement in the future.
+ * API user must call page_pool_put_page() once on a page, as it
+ * will either recycle the page, or in case of refcnt > 1, it will
+ * release the DMA mapping and in-flight state accounting.
  */
 #ifndef _NET_PAGE_POOL_HELPERS_H
 #define _NET_PAGE_POOL_HELPERS_H
-- 
GitLab


From e546a119801f732f5c5c620d59be2e85aa732a8b Mon Sep 17 00:00:00 2001
From: Will Hawkins <hawkinsw@obs.cr>
Date: Tue, 8 Aug 2023 17:25:01 -0400
Subject: [PATCH 1000/1806] bpf, docs: Fix small typo and define semantics of
 sign extension

Add additional precision on the semantics of the sign extension
operations in BPF. In addition, fix a very minor typo.

Signed-off-by: Will Hawkins <hawkinsw@obs.cr>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/r/20230808212503.197834-1-hawkinsw@obs.cr
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../bpf/standardization/instruction-set.rst   | 39 ++++++++++++++-----
 1 file changed, 30 insertions(+), 9 deletions(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 25be958130dc8..4f73e9dc8d9ee 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -76,6 +76,27 @@ Functions
   format and returns the equivalent number with the same bit width but
   opposite endianness.
 
+
+Definitions
+-----------
+
+.. glossary::
+
+  Sign Extend
+    To `sign extend an` ``X`` `-bit number, A, to a` ``Y`` `-bit number, B  ,` means to
+
+    #. Copy all ``X`` bits from `A` to the lower ``X`` bits of `B`.
+    #. Set the value of the remaining ``Y`` - ``X`` bits of `B` to the value of
+       the  most-significant bit of `A`.
+
+.. admonition:: Example
+
+  Sign extend an 8-bit number ``A`` to a 16-bit number ``B`` on a big-endian platform:
+  ::
+
+    A:          10000110
+    B: 11111111 10000110
+
 Registers and calling convention
 ================================
 
@@ -234,7 +255,7 @@ BPF_SMOD   0x90   1        dst = (src != 0) ? (dst s% src) : dst
 BPF_XOR    0xa0   0        dst ^= src
 BPF_MOV    0xb0   0        dst = src
 BPF_MOVSX  0xb0   8/16/32  dst = (s8,s16,s32)src
-BPF_ARSH   0xc0   0        sign extending dst >>= (src & mask)
+BPF_ARSH   0xc0   0        :term:`sign extending<Sign Extend>` dst >>= (src & mask)
 BPF_END    0xd0   0        byte swap operations (see `Byte swap instructions`_ below)
 =========  =====  =======  ==========================================================
 
@@ -266,22 +287,22 @@ where '(u32)' indicates that the upper 32 bits are zeroed.
 Note that most instructions have instruction offset of 0. Only three instructions
 (``BPF_SDIV``, ``BPF_SMOD``, ``BPF_MOVSX``) have a non-zero offset.
 
-The devision and modulo operations support both unsigned and signed flavors.
+The division and modulo operations support both unsigned and signed flavors.
 
 For unsigned operations (``BPF_DIV`` and ``BPF_MOD``), for ``BPF_ALU``,
 'imm' is interpreted as a 32-bit unsigned value. For ``BPF_ALU64``,
-'imm' is first sign extended from 32 to 64 bits, and then interpreted as
-a 64-bit unsigned value.
+'imm' is first :term:`sign extended<Sign Extend>` from 32 to 64 bits, and then
+interpreted as a 64-bit unsigned value.
 
 For signed operations (``BPF_SDIV`` and ``BPF_SMOD``), for ``BPF_ALU``,
 'imm' is interpreted as a 32-bit signed value. For ``BPF_ALU64``, 'imm'
-is first sign extended from 32 to 64 bits, and then interpreted as a
-64-bit signed value.
+is first :term:`sign extended<Sign Extend>` from 32 to 64 bits, and then
+interpreted as a 64-bit signed value.
 
 The ``BPF_MOVSX`` instruction does a move operation with sign extension.
-``BPF_ALU | BPF_MOVSX`` sign extends 8-bit and 16-bit operands into 32
+``BPF_ALU | BPF_MOVSX`` :term:`sign extends<Sign Extend>` 8-bit and 16-bit operands into 32
 bit operands, and zeroes the remaining upper 32 bits.
-``BPF_ALU64 | BPF_MOVSX`` sign extends 8-bit, 16-bit, and 32-bit
+``BPF_ALU64 | BPF_MOVSX`` :term:`sign extends<Sign Extend>` 8-bit, 16-bit, and 32-bit
 operands into 64 bit operands.
 
 Shift operations use a mask of 0x3F (63) for 64-bit operations and 0x1F (31)
@@ -466,7 +487,7 @@ Where size is one of: ``BPF_B``, ``BPF_H``, ``BPF_W``, or ``BPF_DW`` and
 Sign-extension load operations
 ------------------------------
 
-The ``BPF_MEMSX`` mode modifier is used to encode sign-extension load
+The ``BPF_MEMSX`` mode modifier is used to encode :term:`sign-extension<Sign Extend>` load
 instructions that transfer data between a register and memory.
 
 ``BPF_MEMSX | <size> | BPF_LDX`` means::
-- 
GitLab


From 96ead1e702902c21513354174942415eed0958f3 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Tue, 8 Aug 2023 09:28:58 -0700
Subject: [PATCH 1001/1806] selftests/bpf: remove duplicated functions

The file cgroup_tcp_skb.c contains redundant implementations of the similar
functions (create_server_sock_v6(), connect_client_server_v6() and
get_sock_port_v6()) found in network_helpers.c. Let's eliminate these
duplicated functions.

Changes from v1:

 - Remove get_sock_port_v6() as well.

v1: https://lore.kernel.org/all/20230807193840.567962-1-thinker.li@gmail.com/

Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20230808162858.326871-1-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/cgroup_tcp_skb.c | 93 ++++---------------
 1 file changed, 17 insertions(+), 76 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
index d686ef19f7052..a1542faf7873b 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
@@ -9,6 +9,7 @@
 #include "testing_helpers.h"
 #include "cgroup_tcp_skb.skel.h"
 #include "cgroup_tcp_skb.h"
+#include "network_helpers.h"
 
 #define CGROUP_TCP_SKB_PATH "/test_cgroup_tcp_skb"
 
@@ -58,80 +59,13 @@ static int create_client_sock_v6(void)
 	return fd;
 }
 
-static int create_server_sock_v6(void)
-{
-	struct sockaddr_in6 addr = {
-		.sin6_family = AF_INET6,
-		.sin6_port = htons(0),
-		.sin6_addr = IN6ADDR_LOOPBACK_INIT,
-	};
-	int fd, err;
-
-	fd = socket(AF_INET6, SOCK_STREAM, 0);
-	if (fd < 0) {
-		perror("socket");
-		return -1;
-	}
-
-	err = bind(fd, (struct sockaddr *)&addr, sizeof(addr));
-	if (err < 0) {
-		perror("bind");
-		return -1;
-	}
-
-	err = listen(fd, 1);
-	if (err < 0) {
-		perror("listen");
-		return -1;
-	}
-
-	return fd;
-}
-
-static int get_sock_port_v6(int fd)
-{
-	struct sockaddr_in6 addr;
-	socklen_t len;
-	int err;
-
-	len = sizeof(addr);
-	err = getsockname(fd, (struct sockaddr *)&addr, &len);
-	if (err < 0) {
-		perror("getsockname");
-		return -1;
-	}
-
-	return ntohs(addr.sin6_port);
-}
-
-static int connect_client_server_v6(int client_fd, int listen_fd)
-{
-	struct sockaddr_in6 addr = {
-		.sin6_family = AF_INET6,
-		.sin6_addr = IN6ADDR_LOOPBACK_INIT,
-	};
-	int err, port;
-
-	port = get_sock_port_v6(listen_fd);
-	if (port < 0)
-		return -1;
-	addr.sin6_port = htons(port);
-
-	err = connect(client_fd, (struct sockaddr *)&addr, sizeof(addr));
-	if (err < 0) {
-		perror("connect");
-		return -1;
-	}
-
-	return 0;
-}
-
 /* Connect to the server in a cgroup from the outside of the cgroup. */
 static int talk_to_cgroup(int *client_fd, int *listen_fd, int *service_fd,
 			  struct cgroup_tcp_skb *skel)
 {
 	int err, cp;
 	char buf[5];
+	int port;
 
 	/* Create client & server socket */
 	err = join_root_cgroup();
@@ -143,14 +77,17 @@ static int talk_to_cgroup(int *client_fd, int *listen_fd, int *service_fd,
 	err = join_cgroup(CGROUP_TCP_SKB_PATH);
 	if (!ASSERT_OK(err, "join_cgroup"))
 		return -1;
-	*listen_fd = create_server_sock_v6();
+	*listen_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
 	if (!ASSERT_GE(*listen_fd, 0, "listen_fd"))
 		return -1;
-	skel->bss->g_sock_port = get_sock_port_v6(*listen_fd);
+	port = get_socket_local_port(*listen_fd);
+	if (!ASSERT_GE(port, 0, "get_socket_local_port"))
+		return -1;
+	skel->bss->g_sock_port = ntohs(port);
 
 	/* Connect client to server */
-	err = connect_client_server_v6(*client_fd, *listen_fd);
-	if (!ASSERT_OK(err, "connect_client_server_v6"))
+	err = connect_fd_to_fd(*client_fd, *listen_fd, 0);
+	if (!ASSERT_OK(err, "connect_fd_to_fd"))
 		return -1;
 	*service_fd = accept(*listen_fd, NULL, NULL);
 	if (!ASSERT_GE(*service_fd, 0, "service_fd"))
@@ -175,12 +112,13 @@ static int talk_to_outside(int *client_fd, int *listen_fd, int *service_fd,
 {
 	int err, cp;
 	char buf[5];
+	int port;
 
 	/* Create client & server socket */
 	err = join_root_cgroup();
 	if (!ASSERT_OK(err, "join_root_cgroup"))
 		return -1;
-	*listen_fd = create_server_sock_v6();
+	*listen_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
 	if (!ASSERT_GE(*listen_fd, 0, "listen_fd"))
 		return -1;
 	err = join_cgroup(CGROUP_TCP_SKB_PATH);
@@ -192,11 +130,14 @@ static int talk_to_outside(int *client_fd, int *listen_fd, int *service_fd,
 	err = join_root_cgroup();
 	if (!ASSERT_OK(err, "join_root_cgroup"))
 		return -1;
-	skel->bss->g_sock_port = get_sock_port_v6(*listen_fd);
+	port = get_socket_local_port(*listen_fd);
+	if (!ASSERT_GE(port, 0, "get_socket_local_port"))
+		return -1;
+	skel->bss->g_sock_port = ntohs(port);
 
 	/* Connect client to server */
-	err = connect_client_server_v6(*client_fd, *listen_fd);
-	if (!ASSERT_OK(err, "connect_client_server_v6"))
+	err = connect_fd_to_fd(*client_fd, *listen_fd, 0);
+	if (!ASSERT_OK(err, "connect_fd_to_fd"))
 		return -1;
 	*service_fd = accept(*listen_fd, NULL, NULL);
 	if (!ASSERT_GE(*service_fd, 0, "service_fd"))
-- 
GitLab


From 898f55f50a00f56dac1ef55f5478c10a7511d0a6 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Tue, 8 Aug 2023 19:27:55 +0300
Subject: [PATCH 1002/1806] selftests/bpf: relax expected log messages to allow
 emitting BPF_ST

Update [1] to LLVM BPF backend seeks to enable generation of BPF_ST
instruction when CPUv4 is selected. This affects expected log messages
for the following selftests:
- log_fixup/missing_map
- spin_lock/lock_id_mapval_preserve
- spin_lock/lock_id_innermapval_preserve

Expected messages in these tests hard-code instruction numbers for BPF
programs compiled from C. These instruction numbers change when
BPF_ST is allowed because single BPF_ST instruction replaces a pair of
BPF_MOV/BPF_STX instructions, e.g.:

    r1 = 42;
    *(u32 *)(r10 - 8) = r1;  --->  *(u32 *)(r10 - 8) = 42;

This commit updates expected log messages to avoid matching specific
instruction numbers (program position still could be uniquely
identified).

[1] https://reviews.llvm.org/D140804
    "[BPF] support for BPF_ST instruction in codegen"

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230808162755.392606-1-eddyz87@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/log_fixup.c      |  2 +-
 .../selftests/bpf/prog_tests/spin_lock.c      | 37 ++++++++++++++++---
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/log_fixup.c b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
index dba71d98a2279..effd78b2a6573 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_fixup.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
@@ -124,7 +124,7 @@ static void missing_map(void)
 	ASSERT_FALSE(bpf_map__autocreate(skel->maps.missing_map), "missing_map_autocreate");
 
 	ASSERT_HAS_SUBSTR(log_buf,
-			  "8: <invalid BPF map reference>\n"
+			  ": <invalid BPF map reference>\n"
 			  "BPF map 'missing_map' is referenced but wasn't created\n",
 			  "log_buf");
 
diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
index d9270bd3d9207..f29c08d93beb1 100644
--- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <regex.h>
 #include <test_progs.h>
 #include <network_helpers.h>
 
@@ -19,12 +20,16 @@ static struct {
 	  "; R1_w=map_value(off=0,ks=4,vs=4,imm=0)\n2: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_mapval_preserve",
-	  "8: (bf) r1 = r0                       ; R0_w=map_value(id=1,off=0,ks=4,vs=8,imm=0) "
-	  "R1_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)\n9: (85) call bpf_this_cpu_ptr#154\n"
+	  "[0-9]\\+: (bf) r1 = r0                       ;"
+	  " R0_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)"
+	  " R1_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)\n"
+	  "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_innermapval_preserve",
-	  "13: (bf) r1 = r0                      ; R0=map_value(id=2,off=0,ks=4,vs=8,imm=0) "
-	  "R1_w=map_value(id=2,off=0,ks=4,vs=8,imm=0)\n14: (85) call bpf_this_cpu_ptr#154\n"
+	  "[0-9]\\+: (bf) r1 = r0                      ;"
+	  " R0=map_value(id=2,off=0,ks=4,vs=8,imm=0)"
+	  " R1_w=map_value(id=2,off=0,ks=4,vs=8,imm=0)\n"
+	  "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_mismatch_kptr_kptr", "bpf_spin_unlock of different lock" },
 	{ "lock_id_mismatch_kptr_global", "bpf_spin_unlock of different lock" },
@@ -45,6 +50,24 @@ static struct {
 	{ "lock_id_mismatch_innermapval_mapval", "bpf_spin_unlock of different lock" },
 };
 
+static int match_regex(const char *pattern, const char *string)
+{
+	int err, rc;
+	regex_t re;
+
+	err = regcomp(&re, pattern, REG_NOSUB);
+	if (err) {
+		char errbuf[512];
+
+		regerror(err, &re, errbuf, sizeof(errbuf));
+		PRINT_FAIL("Can't compile regex: %s\n", errbuf);
+		return -1;
+	}
+	rc = regexec(&re, string, 0, NULL, 0);
+	regfree(&re);
+	return rc == 0 ? 1 : 0;
+}
+
 static void test_spin_lock_fail_prog(const char *prog_name, const char *err_msg)
 {
 	LIBBPF_OPTS(bpf_object_open_opts, opts, .kernel_log_buf = log_buf,
@@ -74,7 +97,11 @@ static void test_spin_lock_fail_prog(const char *prog_name, const char *err_msg)
 		goto end;
 	}
 
-	if (!ASSERT_OK_PTR(strstr(log_buf, err_msg), "expected error message")) {
+	ret = match_regex(err_msg, log_buf);
+	if (!ASSERT_GE(ret, 0, "match_regex"))
+		goto end;
+
+	if (!ASSERT_TRUE(ret, "no match for expected error message")) {
 		fprintf(stderr, "Expected: %s\n", err_msg);
 		fprintf(stderr, "Verifier: %s\n", log_buf);
 	}
-- 
GitLab


From 526bc5ba19e8701a2b03fdbd2c01e684f0cf9010 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 8 Aug 2023 22:55:31 +0800
Subject: [PATCH 1003/1806] bpf: lru: Remove unused declaration
 bpf_lru_promote()

Commit 3a08c2fd7634 ("bpf: LRU List") declared but never implemented this.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/r/20230808145531.19692-1-yuehaibing@huawei.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/bpf_lru_list.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
index 8f3c8b2b4490e..cbd8d3720c2bb 100644
--- a/kernel/bpf/bpf_lru_list.h
+++ b/kernel/bpf/bpf_lru_list.h
@@ -75,6 +75,5 @@ void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset,
 void bpf_lru_destroy(struct bpf_lru *lru);
 struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash);
 void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node);
-void bpf_lru_promote(struct bpf_lru *lru, struct bpf_lru_node *node);
 
 #endif
-- 
GitLab


From 2adbb7637fd1fcec93f4680ddb5ddbbd1a91aefb Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 8 Aug 2023 22:57:41 +0800
Subject: [PATCH 1004/1806] bpf: btf: Remove two unused function declarations

Commit db559117828d ("bpf: Consolidate spin_lock, timer management into btf_record")
removed the implementations but leave declarations.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/r/20230808145741.33292-1-yuehaibing@huawei.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/btf.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/btf.h b/include/linux/btf.h
index cac9f304e27a2..df64cc6420741 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -204,8 +204,6 @@ u32 btf_nr_types(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
-int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
-int btf_find_timer(const struct btf *btf, const struct btf_type *t);
 struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t,
 				    u32 field_mask, u32 value_size);
 int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec);
-- 
GitLab


From 3bf969e88ada7265ed6ef6f4b52a0c7d1d35c0b6 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 7 Aug 2023 14:48:05 +0100
Subject: [PATCH 1005/1806] sfc: add MAE table machinery for conntrack table

Access to the connection tracking table in EF100 hardware is through
 a "generic" table mechanism, whereby a firmware call at probe time
 gives the driver a description of the field widths and offsets, so
 that the driver can then construct key and response bitstrings at
 runtime.
Probe the NIC for this information and populate the needed metadata
 into a new meta_ct field of struct efx_tc_state.

Reviewed-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/mae.c  | 250 ++++++++++++++++++++++++++++++++
 drivers/net/ethernet/sfc/mae.h  |   3 +
 drivers/net/ethernet/sfc/mcdi.h |   3 +
 drivers/net/ethernet/sfc/tc.c   |   9 +-
 drivers/net/ethernet/sfc/tc.h   |  44 ++++++
 5 files changed, 308 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c
index 0cab508f2f9d1..33ae2c852b447 100644
--- a/drivers/net/ethernet/sfc/mae.c
+++ b/drivers/net/ethernet/sfc/mae.c
@@ -227,6 +227,256 @@ void efx_mae_counters_grant_credits(struct work_struct *work)
 		rx_queue->granted_count += credits;
 }
 
+static int efx_mae_table_get_desc(struct efx_nic *efx,
+				  struct efx_tc_table_desc *desc,
+				  u32 table_id)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_TABLE_DESCRIPTOR_OUT_LEN(16));
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_TABLE_DESCRIPTOR_IN_LEN);
+	unsigned int offset = 0, i;
+	size_t outlen;
+	int rc;
+
+	memset(desc, 0, sizeof(*desc));
+
+	MCDI_SET_DWORD(inbuf, TABLE_DESCRIPTOR_IN_TABLE_ID, table_id);
+more:
+	MCDI_SET_DWORD(inbuf, TABLE_DESCRIPTOR_IN_FIRST_FIELDS_INDEX, offset);
+	rc = efx_mcdi_rpc(efx, MC_CMD_TABLE_DESCRIPTOR, inbuf, sizeof(inbuf),
+			  outbuf, sizeof(outbuf), &outlen);
+	if (rc)
+		goto fail;
+	if (outlen < MC_CMD_TABLE_DESCRIPTOR_OUT_LEN(1)) {
+		rc = -EIO;
+		goto fail;
+	}
+	if (!offset) { /* first iteration: get metadata */
+		desc->type = MCDI_WORD(outbuf, TABLE_DESCRIPTOR_OUT_TYPE);
+		desc->key_width = MCDI_WORD(outbuf, TABLE_DESCRIPTOR_OUT_KEY_WIDTH);
+		desc->resp_width = MCDI_WORD(outbuf, TABLE_DESCRIPTOR_OUT_RESP_WIDTH);
+		desc->n_keys = MCDI_WORD(outbuf, TABLE_DESCRIPTOR_OUT_N_KEY_FIELDS);
+		desc->n_resps = MCDI_WORD(outbuf, TABLE_DESCRIPTOR_OUT_N_RESP_FIELDS);
+		desc->n_prios = MCDI_WORD(outbuf, TABLE_DESCRIPTOR_OUT_N_PRIORITIES);
+		desc->flags = MCDI_BYTE(outbuf, TABLE_DESCRIPTOR_OUT_FLAGS);
+		rc = -EOPNOTSUPP;
+		if (desc->flags)
+			goto fail;
+		desc->scheme = MCDI_BYTE(outbuf, TABLE_DESCRIPTOR_OUT_SCHEME);
+		if (desc->scheme)
+			goto fail;
+		rc = -ENOMEM;
+		desc->keys = kcalloc(desc->n_keys,
+				     sizeof(struct efx_tc_table_field_fmt),
+				     GFP_KERNEL);
+		if (!desc->keys)
+			goto fail;
+		desc->resps = kcalloc(desc->n_resps,
+				      sizeof(struct efx_tc_table_field_fmt),
+				      GFP_KERNEL);
+		if (!desc->resps)
+			goto fail;
+	}
+	/* FW could have returned more than the 16 field_descrs we
+	 * made room for in our outbuf
+	 */
+	outlen = min(outlen, sizeof(outbuf));
+	for (i = 0; i + offset < desc->n_keys + desc->n_resps; i++) {
+		struct efx_tc_table_field_fmt *field;
+		MCDI_DECLARE_STRUCT_PTR(fdesc);
+
+		if (outlen < MC_CMD_TABLE_DESCRIPTOR_OUT_LEN(i + 1)) {
+			offset += i;
+			goto more;
+		}
+		if (i + offset < desc->n_keys)
+			field = desc->keys + i + offset;
+		else
+			field = desc->resps + (i + offset - desc->n_keys);
+		fdesc = MCDI_ARRAY_STRUCT_PTR(outbuf,
+					      TABLE_DESCRIPTOR_OUT_FIELDS, i);
+		field->field_id = MCDI_STRUCT_WORD(fdesc,
+						   TABLE_FIELD_DESCR_FIELD_ID);
+		field->lbn = MCDI_STRUCT_WORD(fdesc, TABLE_FIELD_DESCR_LBN);
+		field->width = MCDI_STRUCT_WORD(fdesc, TABLE_FIELD_DESCR_WIDTH);
+		field->masking = MCDI_STRUCT_BYTE(fdesc, TABLE_FIELD_DESCR_MASK_TYPE);
+		field->scheme = MCDI_STRUCT_BYTE(fdesc, TABLE_FIELD_DESCR_SCHEME);
+	}
+	return 0;
+
+fail:
+	kfree(desc->keys);
+	kfree(desc->resps);
+	return rc;
+}
+
+static int efx_mae_table_hook_find(u16 n_fields,
+				   struct efx_tc_table_field_fmt *fields,
+				   u16 field_id)
+{
+	unsigned int i;
+
+	for (i = 0; i < n_fields; i++) {
+		if (fields[i].field_id == field_id)
+			return i;
+	}
+	return -EPROTO;
+}
+
+#define TABLE_FIND_KEY(_desc, _id)	\
+	efx_mae_table_hook_find((_desc)->n_keys, (_desc)->keys, _id)
+#define TABLE_FIND_RESP(_desc, _id)	\
+	efx_mae_table_hook_find((_desc)->n_resps, (_desc)->resps, _id)
+
+#define TABLE_HOOK_KEY(_meta, _name, _mcdi_name)	({			\
+	int _rc = TABLE_FIND_KEY(&_meta->desc, TABLE_FIELD_ID_##_mcdi_name);	\
+										\
+	if (_rc > U8_MAX)							\
+		_rc = -EOPNOTSUPP;						\
+	if (_rc >= 0) {								\
+		_meta->keys._name##_idx = _rc;					\
+		_rc = 0;							\
+	}									\
+	_rc;									\
+})
+#define TABLE_HOOK_RESP(_meta, _name, _mcdi_name)	({			\
+	int _rc = TABLE_FIND_RESP(&_meta->desc, TABLE_FIELD_ID_##_mcdi_name);	\
+										\
+	if (_rc > U8_MAX)							\
+		_rc = -EOPNOTSUPP;						\
+	if (_rc >= 0) {								\
+		_meta->resps._name##_idx = _rc;					\
+		_rc = 0;							\
+	}									\
+	_rc;									\
+})
+
+static int efx_mae_table_hook_ct(struct efx_nic *efx,
+				 struct efx_tc_table_ct *meta_ct)
+{
+	int rc;
+
+	rc = TABLE_HOOK_KEY(meta_ct, eth_proto, ETHER_TYPE);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_KEY(meta_ct, ip_proto, IP_PROTO);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_KEY(meta_ct, src_ip, SRC_IP);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_KEY(meta_ct, dst_ip, DST_IP);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_KEY(meta_ct, l4_sport, SRC_PORT);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_KEY(meta_ct, l4_dport, DST_PORT);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_KEY(meta_ct, zone, DOMAIN);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_RESP(meta_ct, dnat, NAT_DIR);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_RESP(meta_ct, nat_ip, NAT_IP);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_RESP(meta_ct, l4_natport, NAT_PORT);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_RESP(meta_ct, mark, CT_MARK);
+	if (rc)
+		return rc;
+	rc = TABLE_HOOK_RESP(meta_ct, counter_id, COUNTER_ID);
+	if (rc)
+		return rc;
+	meta_ct->hooked = true;
+	return 0;
+}
+
+static void efx_mae_table_free_desc(struct efx_tc_table_desc *desc)
+{
+	kfree(desc->keys);
+	kfree(desc->resps);
+	memset(desc, 0, sizeof(*desc));
+}
+
+static bool efx_mae_check_table_exists(struct efx_nic *efx, u32 tbl_req)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_TABLE_LIST_OUT_LEN(16));
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_TABLE_LIST_IN_LEN);
+	u32 tbl_id, tbl_total, tbl_cnt, pos = 0;
+	size_t outlen, msg_max;
+	bool ct_tbl = false;
+	int rc, idx;
+
+	msg_max = sizeof(outbuf);
+	efx->tc->meta_ct.hooked = false;
+more:
+	memset(outbuf, 0, sizeof(*outbuf));
+	MCDI_SET_DWORD(inbuf, TABLE_LIST_IN_FIRST_TABLE_ID_INDEX, pos);
+	rc = efx_mcdi_rpc(efx, MC_CMD_TABLE_LIST, inbuf, sizeof(inbuf), outbuf,
+			  msg_max, &outlen);
+	if (rc)
+		return false;
+
+	if (outlen < MC_CMD_TABLE_LIST_OUT_LEN(1))
+		return false;
+
+	tbl_total = MCDI_DWORD(outbuf, TABLE_LIST_OUT_N_TABLES);
+	tbl_cnt = MC_CMD_TABLE_LIST_OUT_TABLE_ID_NUM(min(outlen, msg_max));
+
+	for (idx = 0; idx < tbl_cnt; idx++) {
+		tbl_id = MCDI_ARRAY_DWORD(outbuf, TABLE_LIST_OUT_TABLE_ID, idx);
+		if (tbl_id == tbl_req) {
+			ct_tbl = true;
+			break;
+		}
+	}
+
+	pos += tbl_cnt;
+	if (!ct_tbl && pos < tbl_total)
+		goto more;
+
+	return ct_tbl;
+}
+
+int efx_mae_get_tables(struct efx_nic *efx)
+{
+	int rc;
+
+	efx->tc->meta_ct.hooked = false;
+	if (efx_mae_check_table_exists(efx, TABLE_ID_CONNTRACK_TABLE)) {
+		rc = efx_mae_table_get_desc(efx, &efx->tc->meta_ct.desc,
+					    TABLE_ID_CONNTRACK_TABLE);
+		if (rc) {
+			pci_info(efx->pci_dev,
+				 "FW does not support conntrack desc rc %d\n",
+				 rc);
+			return 0;
+		}
+
+		rc = efx_mae_table_hook_ct(efx, &efx->tc->meta_ct);
+		if (rc) {
+			pci_info(efx->pci_dev,
+				 "FW does not support conntrack hook rc %d\n",
+				 rc);
+			return 0;
+		}
+	} else {
+		pci_info(efx->pci_dev,
+			 "FW does not support conntrack table\n");
+	}
+	return 0;
+}
+
+void efx_mae_free_tables(struct efx_nic *efx)
+{
+	efx_mae_table_free_desc(&efx->tc->meta_ct.desc);
+	efx->tc->meta_ct.hooked = false;
+}
+
 static int efx_mae_get_basic_caps(struct efx_nic *efx, struct mae_caps *caps)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_GET_CAPS_OUT_LEN);
diff --git a/drivers/net/ethernet/sfc/mae.h b/drivers/net/ethernet/sfc/mae.h
index 24abfe5096909..afdf738254b2f 100644
--- a/drivers/net/ethernet/sfc/mae.h
+++ b/drivers/net/ethernet/sfc/mae.h
@@ -66,6 +66,9 @@ int efx_mae_start_counters(struct efx_nic *efx, struct efx_rx_queue *rx_queue);
 int efx_mae_stop_counters(struct efx_nic *efx, struct efx_rx_queue *rx_queue);
 void efx_mae_counters_grant_credits(struct work_struct *work);
 
+int efx_mae_get_tables(struct efx_nic *efx);
+void efx_mae_free_tables(struct efx_nic *efx);
+
 #define MAE_NUM_FIELDS	(MAE_FIELD_ENC_VNET_ID + 1)
 
 struct mae_caps {
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index 454e9d51a4c2c..995a26686fd82 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -221,6 +221,9 @@ void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev);
 #define MCDI_BYTE(_buf, _field)						\
 	((void)BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 1),	\
 	 *MCDI_PTR(_buf, _field))
+#define MCDI_STRUCT_BYTE(_buf, _field)					\
+	((void)BUILD_BUG_ON_ZERO(_field ## _LEN != 1),			\
+	 *MCDI_STRUCT_PTR(_buf, _field))
 #define MCDI_SET_WORD(_buf, _field, _value) do {			\
 	BUILD_BUG_ON(MC_CMD_ ## _field ## _LEN != 2);			\
 	BUILD_BUG_ON(MC_CMD_ ## _field ## _OFST & 1);			\
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 4dc8811592461..4dc979fdc9688 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -1658,13 +1658,19 @@ int efx_init_tc(struct efx_nic *efx)
 	if (rc)
 		return rc;
 	rc = efx_tc_configure_fallback_acts_reps(efx);
+	if (rc)
+		return rc;
+	rc = efx_mae_get_tables(efx);
 	if (rc)
 		return rc;
 	efx->tc->up = true;
 	rc = flow_indr_dev_register(efx_tc_indr_setup_cb, efx);
 	if (rc)
-		return rc;
+		goto out_free;
 	return 0;
+out_free:
+	efx_mae_free_tables(efx);
+	return rc;
 }
 
 void efx_fini_tc(struct efx_nic *efx)
@@ -1680,6 +1686,7 @@ void efx_fini_tc(struct efx_nic *efx)
 	efx_tc_deconfigure_fallback_acts(efx, &efx->tc->facts.pf);
 	efx_tc_deconfigure_fallback_acts(efx, &efx->tc->facts.reps);
 	efx->tc->up = false;
+	efx_mae_free_tables(efx);
 }
 
 /* At teardown time, all TC filter rules (and thus all resources they created)
diff --git a/drivers/net/ethernet/sfc/tc.h b/drivers/net/ethernet/sfc/tc.h
index 1549c3df43bbe..27592f10b5365 100644
--- a/drivers/net/ethernet/sfc/tc.h
+++ b/drivers/net/ethernet/sfc/tc.h
@@ -143,6 +143,48 @@ enum efx_tc_rule_prios {
 	EFX_TC_PRIO__NUM
 };
 
+struct efx_tc_table_field_fmt {
+	u16 field_id;
+	u16 lbn;
+	u16 width;
+	u8 masking;
+	u8 scheme;
+};
+
+struct efx_tc_table_desc {
+	u16 type;
+	u16 key_width;
+	u16 resp_width;
+	u16 n_keys;
+	u16 n_resps;
+	u16 n_prios;
+	u8 flags;
+	u8 scheme;
+	struct efx_tc_table_field_fmt *keys;
+	struct efx_tc_table_field_fmt *resps;
+};
+
+struct efx_tc_table_ct { /* TABLE_ID_CONNTRACK_TABLE */
+	struct efx_tc_table_desc desc;
+	bool hooked;
+	struct { /* indices of named fields within @desc.keys */
+		u8 eth_proto_idx;
+		u8 ip_proto_idx;
+		u8 src_ip_idx; /* either v4 or v6 */
+		u8 dst_ip_idx;
+		u8 l4_sport_idx;
+		u8 l4_dport_idx;
+		u8 zone_idx; /* for TABLE_FIELD_ID_DOMAIN */
+	} keys;
+	struct { /* indices of named fields within @desc.resps */
+		u8 dnat_idx;
+		u8 nat_ip_idx;
+		u8 l4_natport_idx;
+		u8 mark_idx;
+		u8 counter_id_idx;
+	} resps;
+};
+
 /**
  * struct efx_tc_state - control plane data for TC offload
  *
@@ -155,6 +197,7 @@ enum efx_tc_rule_prios {
  * @encap_match_ht: Hashtable of TC encap matches
  * @match_action_ht: Hashtable of TC match-action rules
  * @neigh_ht: Hashtable of neighbour watches (&struct efx_neigh_binder)
+ * @meta_ct: MAE table layout for conntrack table
  * @reps_mport_id: MAE port allocated for representor RX
  * @reps_filter_uc: VNIC filter for representor unicast RX (promisc)
  * @reps_filter_mc: VNIC filter for representor multicast RX (allmulti)
@@ -186,6 +229,7 @@ struct efx_tc_state {
 	struct rhashtable encap_match_ht;
 	struct rhashtable match_action_ht;
 	struct rhashtable neigh_ht;
+	struct efx_tc_table_ct meta_ct;
 	u32 reps_mport_id, reps_mport_vport_id;
 	s32 reps_filter_uc, reps_filter_mc;
 	bool flush_counters;
-- 
GitLab


From c3bb5c6acd4e0104522f6b1a22f7d62e37e8fa02 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 7 Aug 2023 14:48:06 +0100
Subject: [PATCH 1006/1806] sfc: functions to register for conntrack zone
 offload

Bind a stub callback to the netfilter flow table.

Reviewed-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/Makefile       |   2 +-
 drivers/net/ethernet/sfc/tc.c           |   7 ++
 drivers/net/ethernet/sfc/tc.h           |   2 +
 drivers/net/ethernet/sfc/tc_conntrack.c | 109 ++++++++++++++++++++++++
 drivers/net/ethernet/sfc/tc_conntrack.h |  37 ++++++++
 5 files changed, 156 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/sfc/tc_conntrack.c
 create mode 100644 drivers/net/ethernet/sfc/tc_conntrack.h

diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index 16293b58e0a89..8f446b9bd5ee3 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -11,7 +11,7 @@ sfc-y			+= efx.o efx_common.o efx_channels.o nic.o \
 sfc-$(CONFIG_SFC_MTD)	+= mtd.o
 sfc-$(CONFIG_SFC_SRIOV)	+= sriov.o ef10_sriov.o ef100_sriov.o ef100_rep.o \
                            mae.o tc.o tc_bindings.o tc_counters.o \
-                           tc_encap_actions.o
+                           tc_encap_actions.o tc_conntrack.o
 
 obj-$(CONFIG_SFC)	+= sfc.o
 
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 4dc979fdc9688..44a6fc30b7224 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -15,6 +15,7 @@
 #include "tc.h"
 #include "tc_bindings.h"
 #include "tc_encap_actions.h"
+#include "tc_conntrack.h"
 #include "mae.h"
 #include "ef100_rep.h"
 #include "efx.h"
@@ -1747,6 +1748,9 @@ int efx_init_struct_tc(struct efx_nic *efx)
 	rc = rhashtable_init(&efx->tc->match_action_ht, &efx_tc_match_action_ht_params);
 	if (rc < 0)
 		goto fail_match_action_ht;
+	rc = efx_tc_init_conntrack(efx);
+	if (rc < 0)
+		goto fail_conntrack;
 	efx->tc->reps_filter_uc = -1;
 	efx->tc->reps_filter_mc = -1;
 	INIT_LIST_HEAD(&efx->tc->dflt.pf.acts.list);
@@ -1759,6 +1763,8 @@ int efx_init_struct_tc(struct efx_nic *efx)
 	efx->tc->facts.reps.fw_id = MC_CMD_MAE_ACTION_SET_ALLOC_OUT_ACTION_SET_ID_NULL;
 	efx->extra_channel_type[EFX_EXTRA_CHANNEL_TC] = &efx_tc_channel_type;
 	return 0;
+fail_conntrack:
+	rhashtable_destroy(&efx->tc->match_action_ht);
 fail_match_action_ht:
 	rhashtable_destroy(&efx->tc->encap_match_ht);
 fail_encap_match_ht:
@@ -1792,6 +1798,7 @@ void efx_fini_struct_tc(struct efx_nic *efx)
 				    efx);
 	rhashtable_free_and_destroy(&efx->tc->encap_match_ht,
 				    efx_tc_encap_match_free, NULL);
+	efx_tc_fini_conntrack(efx);
 	efx_tc_fini_counters(efx);
 	efx_tc_fini_encap_actions(efx);
 	mutex_unlock(&efx->tc->mutex);
diff --git a/drivers/net/ethernet/sfc/tc.h b/drivers/net/ethernet/sfc/tc.h
index 27592f10b5365..fc196eb897af2 100644
--- a/drivers/net/ethernet/sfc/tc.h
+++ b/drivers/net/ethernet/sfc/tc.h
@@ -196,6 +196,7 @@ struct efx_tc_table_ct { /* TABLE_ID_CONNTRACK_TABLE */
  * @encap_ht: Hashtable of TC encap actions
  * @encap_match_ht: Hashtable of TC encap matches
  * @match_action_ht: Hashtable of TC match-action rules
+ * @ct_zone_ht: Hashtable of TC conntrack flowtable bindings
  * @neigh_ht: Hashtable of neighbour watches (&struct efx_neigh_binder)
  * @meta_ct: MAE table layout for conntrack table
  * @reps_mport_id: MAE port allocated for representor RX
@@ -228,6 +229,7 @@ struct efx_tc_state {
 	struct rhashtable encap_ht;
 	struct rhashtable encap_match_ht;
 	struct rhashtable match_action_ht;
+	struct rhashtable ct_zone_ht;
 	struct rhashtable neigh_ht;
 	struct efx_tc_table_ct meta_ct;
 	u32 reps_mport_id, reps_mport_vport_id;
diff --git a/drivers/net/ethernet/sfc/tc_conntrack.c b/drivers/net/ethernet/sfc/tc_conntrack.c
new file mode 100644
index 0000000000000..d67302715ec36
--- /dev/null
+++ b/drivers/net/ethernet/sfc/tc_conntrack.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2023, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include "tc_conntrack.h"
+#include "tc.h"
+#include "mae.h"
+
+static int efx_tc_flow_block(enum tc_setup_type type, void *type_data,
+			     void *cb_priv);
+
+static const struct rhashtable_params efx_tc_ct_zone_ht_params = {
+	.key_len	= offsetof(struct efx_tc_ct_zone, linkage),
+	.key_offset	= 0,
+	.head_offset	= offsetof(struct efx_tc_ct_zone, linkage),
+};
+
+static void efx_tc_ct_zone_free(void *ptr, void *arg)
+{
+	struct efx_tc_ct_zone *zone = ptr;
+	struct efx_nic *efx = zone->efx;
+
+	netif_err(efx, drv, efx->net_dev,
+		  "tc ct_zone %u still present at teardown, removing\n",
+		  zone->zone);
+
+	nf_flow_table_offload_del_cb(zone->nf_ft, efx_tc_flow_block, zone);
+	kfree(zone);
+}
+
+int efx_tc_init_conntrack(struct efx_nic *efx)
+{
+	int rc;
+
+	rc = rhashtable_init(&efx->tc->ct_zone_ht, &efx_tc_ct_zone_ht_params);
+	if (rc < 0)
+		return rc;
+	return 0;
+}
+
+void efx_tc_fini_conntrack(struct efx_nic *efx)
+{
+	rhashtable_free_and_destroy(&efx->tc->ct_zone_ht, efx_tc_ct_zone_free, NULL);
+}
+
+static int efx_tc_flow_block(enum tc_setup_type type, void *type_data,
+			     void *cb_priv)
+{
+	return -EOPNOTSUPP;
+}
+
+struct efx_tc_ct_zone *efx_tc_ct_register_zone(struct efx_nic *efx, u16 zone,
+					       struct nf_flowtable *ct_ft)
+{
+	struct efx_tc_ct_zone *ct_zone, *old;
+	int rc;
+
+	ct_zone = kzalloc(sizeof(*ct_zone), GFP_USER);
+	if (!ct_zone)
+		return ERR_PTR(-ENOMEM);
+	ct_zone->zone = zone;
+	old = rhashtable_lookup_get_insert_fast(&efx->tc->ct_zone_ht,
+						&ct_zone->linkage,
+						efx_tc_ct_zone_ht_params);
+	if (old) {
+		/* don't need our new entry */
+		kfree(ct_zone);
+		if (!refcount_inc_not_zero(&old->ref))
+			return ERR_PTR(-EAGAIN);
+		/* existing entry found */
+		WARN_ON_ONCE(old->nf_ft != ct_ft);
+		netif_dbg(efx, drv, efx->net_dev,
+			  "Found existing ct_zone for %u\n", zone);
+		return old;
+	}
+	ct_zone->nf_ft = ct_ft;
+	ct_zone->efx = efx;
+	rc = nf_flow_table_offload_add_cb(ct_ft, efx_tc_flow_block, ct_zone);
+	netif_dbg(efx, drv, efx->net_dev, "Adding new ct_zone for %u, rc %d\n",
+		  zone, rc);
+	if (rc < 0)
+		goto fail;
+	refcount_set(&ct_zone->ref, 1);
+	return ct_zone;
+fail:
+	rhashtable_remove_fast(&efx->tc->ct_zone_ht, &ct_zone->linkage,
+			       efx_tc_ct_zone_ht_params);
+	kfree(ct_zone);
+	return ERR_PTR(rc);
+}
+
+void efx_tc_ct_unregister_zone(struct efx_nic *efx,
+			       struct efx_tc_ct_zone *ct_zone)
+{
+	if (!refcount_dec_and_test(&ct_zone->ref))
+		return; /* still in use */
+	nf_flow_table_offload_del_cb(ct_zone->nf_ft, efx_tc_flow_block, ct_zone);
+	rhashtable_remove_fast(&efx->tc->ct_zone_ht, &ct_zone->linkage,
+			       efx_tc_ct_zone_ht_params);
+	netif_dbg(efx, drv, efx->net_dev, "Removed ct_zone for %u\n",
+		  ct_zone->zone);
+	kfree(ct_zone);
+}
diff --git a/drivers/net/ethernet/sfc/tc_conntrack.h b/drivers/net/ethernet/sfc/tc_conntrack.h
new file mode 100644
index 0000000000000..f1e5fb74a73f2
--- /dev/null
+++ b/drivers/net/ethernet/sfc/tc_conntrack.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2023, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EFX_TC_CONNTRACK_H
+#define EFX_TC_CONNTRACK_H
+#include "net_driver.h"
+
+#if IS_ENABLED(CONFIG_SFC_SRIOV)
+#include <linux/refcount.h>
+#include <net/netfilter/nf_flow_table.h>
+
+struct efx_tc_ct_zone {
+	u16 zone;
+	struct rhash_head linkage;
+	refcount_t ref;
+	struct nf_flowtable *nf_ft;
+	struct efx_nic *efx;
+};
+
+/* create/teardown hashtables */
+int efx_tc_init_conntrack(struct efx_nic *efx);
+void efx_tc_fini_conntrack(struct efx_nic *efx);
+
+struct efx_tc_ct_zone *efx_tc_ct_register_zone(struct efx_nic *efx, u16 zone,
+					       struct nf_flowtable *ct_ft);
+void efx_tc_ct_unregister_zone(struct efx_nic *efx,
+			       struct efx_tc_ct_zone *ct_zone);
+
+#endif /* CONFIG_SFC_SRIOV */
+#endif /* EFX_TC_CONNTRACK_H */
-- 
GitLab


From 94aa05bdc77731043b6239a7b810c586be2dce46 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 7 Aug 2023 14:48:07 +0100
Subject: [PATCH 1007/1806] sfc: functions to insert/remove conntrack entries
 to MAE hardware

Translate from software struct efx_tc_ct_entry objects to the key
 and response bitstrings, and implement insertion and removal of
 these entries from the hardware table.
Callers of these functions will be added in subsequent patches.

Reviewed-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/mae.c          | 257 ++++++++++++++++++++++++
 drivers/net/ethernet/sfc/mae.h          |   3 +
 drivers/net/ethernet/sfc/tc_conntrack.h |  14 ++
 3 files changed, 274 insertions(+)

diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c
index 33ae2c852b447..8ebf71a54bf99 100644
--- a/drivers/net/ethernet/sfc/mae.c
+++ b/drivers/net/ethernet/sfc/mae.c
@@ -16,6 +16,7 @@
 #include "mcdi_pcol.h"
 #include "mcdi_pcol_mae.h"
 #include "tc_encap_actions.h"
+#include "tc_conntrack.h"
 
 int efx_mae_allocate_mport(struct efx_nic *efx, u32 *id, u32 *label)
 {
@@ -1403,6 +1404,262 @@ int efx_mae_unregister_encap_match(struct efx_nic *efx,
 	return 0;
 }
 
+/* Populating is done by taking each byte of @value in turn and storing
+ * it in the appropriate bits of @row.  @value must be big-endian; we
+ * convert it to little-endianness as we go.
+ */
+static int efx_mae_table_populate(struct efx_tc_table_field_fmt field,
+				  __le32 *row, size_t row_bits,
+				  void *value, size_t value_size)
+{
+	unsigned int i;
+
+	/* For now only scheme 0 is supported for any field, so we check here
+	 * (rather than, say, in calling code, which knows the semantics and
+	 * could in principle encode for other schemes).
+	 */
+	if (field.scheme)
+		return -EOPNOTSUPP;
+	if (DIV_ROUND_UP(field.width, 8) != value_size)
+		return -EINVAL;
+	if (field.lbn + field.width > row_bits)
+		return -EINVAL;
+	for (i = 0; i < value_size; i++) {
+		unsigned int bn = field.lbn + i * 8;
+		unsigned int wn = bn / 32;
+		u64 v;
+
+		v = ((u8 *)value)[value_size - i - 1];
+		v <<= (bn % 32);
+		row[wn] |= cpu_to_le32(v & 0xffffffff);
+		if (wn * 32 < row_bits)
+			row[wn + 1] |= cpu_to_le32(v >> 32);
+	}
+	return 0;
+}
+
+static int efx_mae_table_populate_bool(struct efx_tc_table_field_fmt field,
+				       __le32 *row, size_t row_bits, bool value)
+{
+	u8 v = value ? 1 : 0;
+
+	if (field.width != 1)
+		return -EINVAL;
+	return efx_mae_table_populate(field, row, row_bits, &v, 1);
+}
+
+static int efx_mae_table_populate_ipv4(struct efx_tc_table_field_fmt field,
+				       __le32 *row, size_t row_bits, __be32 value)
+{
+	/* IPv4 is placed in the first 4 bytes of an IPv6-sized field */
+	struct in6_addr v = {};
+
+	if (field.width != 128)
+		return -EINVAL;
+	v.s6_addr32[0] = value;
+	return efx_mae_table_populate(field, row, row_bits, &v, sizeof(v));
+}
+
+static int efx_mae_table_populate_u24(struct efx_tc_table_field_fmt field,
+				      __le32 *row, size_t row_bits, u32 value)
+{
+	__be32 v = cpu_to_be32(value);
+
+	/* We adjust value_size here since just 3 bytes will be copied, and
+	 * the pointer to the value is set discarding the first byte which is
+	 * the most significant byte for a big-endian 4-bytes value.
+	 */
+	return efx_mae_table_populate(field, row, row_bits, ((void *)&v) + 1,
+				      sizeof(v) - 1);
+}
+
+#define _TABLE_POPULATE(dst, dw, _field, _value) ({	\
+	typeof(_value) _v = _value;			\
+							\
+	(_field.width == sizeof(_value) * 8) ?		\
+	 efx_mae_table_populate(_field, dst, dw, &_v,	\
+				sizeof(_v)) : -EINVAL;	\
+})
+#define TABLE_POPULATE_KEY_IPV4(dst, _table, _field, _value)		       \
+	efx_mae_table_populate_ipv4(efx->tc->meta_##_table.desc.keys	       \
+				    [efx->tc->meta_##_table.keys._field##_idx],\
+				    dst, efx->tc->meta_##_table.desc.key_width,\
+				    _value)
+#define TABLE_POPULATE_KEY(dst, _table, _field, _value)			\
+	_TABLE_POPULATE(dst, efx->tc->meta_##_table.desc.key_width,	\
+			efx->tc->meta_##_table.desc.keys		\
+			[efx->tc->meta_##_table.keys._field##_idx],	\
+			_value)
+
+#define TABLE_POPULATE_RESP_BOOL(dst, _table, _field, _value)			\
+	efx_mae_table_populate_bool(efx->tc->meta_##_table.desc.resps		\
+				    [efx->tc->meta_##_table.resps._field##_idx],\
+				    dst, efx->tc->meta_##_table.desc.resp_width,\
+				    _value)
+#define TABLE_POPULATE_RESP(dst, _table, _field, _value)		\
+	_TABLE_POPULATE(dst, efx->tc->meta_##_table.desc.resp_width,	\
+			efx->tc->meta_##_table.desc.resps		\
+			[efx->tc->meta_##_table.resps._field##_idx],	\
+			_value)
+
+#define TABLE_POPULATE_RESP_U24(dst, _table, _field, _value)		       \
+	efx_mae_table_populate_u24(efx->tc->meta_##_table.desc.resps	       \
+				   [efx->tc->meta_##_table.resps._field##_idx],\
+				   dst, efx->tc->meta_##_table.desc.resp_width,\
+				   _value)
+
+static int efx_mae_populate_ct_key(struct efx_nic *efx, __le32 *key, size_t kw,
+				   struct efx_tc_ct_entry *conn)
+{
+	bool ipv6 = conn->eth_proto == htons(ETH_P_IPV6);
+	int rc;
+
+	rc = TABLE_POPULATE_KEY(key, ct, eth_proto, conn->eth_proto);
+	if (rc)
+		return rc;
+	rc = TABLE_POPULATE_KEY(key, ct, ip_proto, conn->ip_proto);
+	if (rc)
+		return rc;
+	if (ipv6)
+		rc = TABLE_POPULATE_KEY(key, ct, src_ip, conn->src_ip6);
+	else
+		rc = TABLE_POPULATE_KEY_IPV4(key, ct, src_ip, conn->src_ip);
+	if (rc)
+		return rc;
+	if (ipv6)
+		rc = TABLE_POPULATE_KEY(key, ct, dst_ip, conn->dst_ip6);
+	else
+		rc = TABLE_POPULATE_KEY_IPV4(key, ct, dst_ip, conn->dst_ip);
+	if (rc)
+		return rc;
+	rc = TABLE_POPULATE_KEY(key, ct, l4_sport, conn->l4_sport);
+	if (rc)
+		return rc;
+	rc = TABLE_POPULATE_KEY(key, ct, l4_dport, conn->l4_dport);
+	if (rc)
+		return rc;
+	return TABLE_POPULATE_KEY(key, ct, zone, cpu_to_be16(conn->zone->zone));
+}
+
+int efx_mae_insert_ct(struct efx_nic *efx, struct efx_tc_ct_entry *conn)
+{
+	bool ipv6 = conn->eth_proto == htons(ETH_P_IPV6);
+	__le32 *key = NULL, *resp = NULL;
+	size_t inlen, kw, rw;
+	efx_dword_t *inbuf;
+	int rc = -ENOMEM;
+
+	/* Check table access is supported */
+	if (!efx->tc->meta_ct.hooked)
+		return -EOPNOTSUPP;
+
+	/* key/resp widths are in bits; convert to dwords for IN_LEN */
+	kw = DIV_ROUND_UP(efx->tc->meta_ct.desc.key_width, 32);
+	rw = DIV_ROUND_UP(efx->tc->meta_ct.desc.resp_width, 32);
+	BUILD_BUG_ON(sizeof(__le32) != MC_CMD_TABLE_INSERT_IN_DATA_LEN);
+	inlen = MC_CMD_TABLE_INSERT_IN_LEN(kw + rw);
+	if (inlen > MC_CMD_TABLE_INSERT_IN_LENMAX_MCDI2)
+		return -E2BIG;
+	inbuf = kzalloc(inlen, GFP_KERNEL);
+	if (!inbuf)
+		return -ENOMEM;
+
+	key = kcalloc(kw, sizeof(__le32), GFP_KERNEL);
+	if (!key)
+		goto out_free;
+	resp = kcalloc(rw, sizeof(__le32), GFP_KERNEL);
+	if (!resp)
+		goto out_free;
+
+	rc = efx_mae_populate_ct_key(efx, key, kw, conn);
+	if (rc)
+		goto out_free;
+
+	rc = TABLE_POPULATE_RESP_BOOL(resp, ct, dnat, conn->dnat);
+	if (rc)
+		goto out_free;
+	/* No support in hw for IPv6 NAT; field is only 32 bits */
+	if (!ipv6)
+		rc = TABLE_POPULATE_RESP(resp, ct, nat_ip, conn->nat_ip);
+	if (rc)
+		goto out_free;
+	rc = TABLE_POPULATE_RESP(resp, ct, l4_natport, conn->l4_natport);
+	if (rc)
+		goto out_free;
+	rc = TABLE_POPULATE_RESP(resp, ct, mark, cpu_to_be32(conn->mark));
+	if (rc)
+		goto out_free;
+	rc = TABLE_POPULATE_RESP_U24(resp, ct, counter_id, conn->cnt->fw_id);
+	if (rc)
+		goto out_free;
+
+	MCDI_SET_DWORD(inbuf, TABLE_INSERT_IN_TABLE_ID, TABLE_ID_CONNTRACK_TABLE);
+	MCDI_SET_WORD(inbuf, TABLE_INSERT_IN_KEY_WIDTH,
+		      efx->tc->meta_ct.desc.key_width);
+	/* MASK_WIDTH is zero as CT is a BCAM */
+	MCDI_SET_WORD(inbuf, TABLE_INSERT_IN_RESP_WIDTH,
+		      efx->tc->meta_ct.desc.resp_width);
+	memcpy(MCDI_PTR(inbuf, TABLE_INSERT_IN_DATA), key, kw * sizeof(__le32));
+	memcpy(MCDI_PTR(inbuf, TABLE_INSERT_IN_DATA) + kw * sizeof(__le32),
+	       resp, rw * sizeof(__le32));
+
+	BUILD_BUG_ON(MC_CMD_TABLE_INSERT_OUT_LEN);
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_TABLE_INSERT, inbuf, inlen, NULL, 0, NULL);
+
+out_free:
+	kfree(resp);
+	kfree(key);
+	kfree(inbuf);
+	return rc;
+}
+
+int efx_mae_remove_ct(struct efx_nic *efx, struct efx_tc_ct_entry *conn)
+{
+	__le32 *key = NULL;
+	efx_dword_t *inbuf;
+	size_t inlen, kw;
+	int rc = -ENOMEM;
+
+	/* Check table access is supported */
+	if (!efx->tc->meta_ct.hooked)
+		return -EOPNOTSUPP;
+
+	/* key width is in bits; convert to dwords for IN_LEN */
+	kw = DIV_ROUND_UP(efx->tc->meta_ct.desc.key_width, 32);
+	BUILD_BUG_ON(sizeof(__le32) != MC_CMD_TABLE_DELETE_IN_DATA_LEN);
+	inlen = MC_CMD_TABLE_DELETE_IN_LEN(kw);
+	if (inlen > MC_CMD_TABLE_DELETE_IN_LENMAX_MCDI2)
+		return -E2BIG;
+	inbuf = kzalloc(inlen, GFP_KERNEL);
+	if (!inbuf)
+		return -ENOMEM;
+
+	key = kcalloc(kw, sizeof(__le32), GFP_KERNEL);
+	if (!key)
+		goto out_free;
+
+	rc = efx_mae_populate_ct_key(efx, key, kw, conn);
+	if (rc)
+		goto out_free;
+
+	MCDI_SET_DWORD(inbuf, TABLE_DELETE_IN_TABLE_ID, TABLE_ID_CONNTRACK_TABLE);
+	MCDI_SET_WORD(inbuf, TABLE_DELETE_IN_KEY_WIDTH,
+		      efx->tc->meta_ct.desc.key_width);
+	/* MASK_WIDTH is zero as CT is a BCAM */
+	/* RESP_WIDTH is zero for DELETE */
+	memcpy(MCDI_PTR(inbuf, TABLE_DELETE_IN_DATA), key, kw * sizeof(__le32));
+
+	BUILD_BUG_ON(MC_CMD_TABLE_DELETE_OUT_LEN);
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_TABLE_DELETE, inbuf, inlen, NULL, 0, NULL);
+
+out_free:
+	kfree(key);
+	kfree(inbuf);
+	return rc;
+}
+
 static int efx_mae_populate_match_criteria(MCDI_DECLARE_STRUCT_PTR(match_crit),
 					   const struct efx_tc_match *match)
 {
diff --git a/drivers/net/ethernet/sfc/mae.h b/drivers/net/ethernet/sfc/mae.h
index afdf738254b2f..24f29a4fc0e10 100644
--- a/drivers/net/ethernet/sfc/mae.h
+++ b/drivers/net/ethernet/sfc/mae.h
@@ -112,6 +112,9 @@ int efx_mae_register_encap_match(struct efx_nic *efx,
 				 struct efx_tc_encap_match *encap);
 int efx_mae_unregister_encap_match(struct efx_nic *efx,
 				   struct efx_tc_encap_match *encap);
+struct efx_tc_ct_entry; /* see tc_conntrack.h */
+int efx_mae_insert_ct(struct efx_nic *efx, struct efx_tc_ct_entry *conn);
+int efx_mae_remove_ct(struct efx_nic *efx, struct efx_tc_ct_entry *conn);
 
 int efx_mae_insert_rule(struct efx_nic *efx, const struct efx_tc_match *match,
 			u32 prio, u32 acts_id, u32 *id);
diff --git a/drivers/net/ethernet/sfc/tc_conntrack.h b/drivers/net/ethernet/sfc/tc_conntrack.h
index f1e5fb74a73f2..a3e518344cbc5 100644
--- a/drivers/net/ethernet/sfc/tc_conntrack.h
+++ b/drivers/net/ethernet/sfc/tc_conntrack.h
@@ -33,5 +33,19 @@ struct efx_tc_ct_zone *efx_tc_ct_register_zone(struct efx_nic *efx, u16 zone,
 void efx_tc_ct_unregister_zone(struct efx_nic *efx,
 			       struct efx_tc_ct_zone *ct_zone);
 
+struct efx_tc_ct_entry {
+	unsigned long cookie;
+	struct rhash_head linkage;
+	__be16 eth_proto;
+	u8 ip_proto;
+	bool dnat;
+	__be32 src_ip, dst_ip, nat_ip;
+	struct in6_addr src_ip6, dst_ip6;
+	__be16 l4_sport, l4_dport, l4_natport; /* Ports (UDP, TCP) */
+	struct efx_tc_ct_zone *zone;
+	u32 mark;
+	struct efx_tc_counter *cnt;
+};
+
 #endif /* CONFIG_SFC_SRIOV */
 #endif /* EFX_TC_CONNTRACK_H */
-- 
GitLab


From 1909387fcfcfc9197a0adcaa9702967e5c18f812 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 7 Aug 2023 14:48:08 +0100
Subject: [PATCH 1008/1806] sfc: offload conntrack flow entries (match only)
 from CT zones

No handling yet for FLOW_ACTION_MANGLE (NAT or NAPT) actions.

Reviewed-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/tc.h           |   4 +-
 drivers/net/ethernet/sfc/tc_conntrack.c | 417 +++++++++++++++++++++++-
 drivers/net/ethernet/sfc/tc_conntrack.h |   3 +
 drivers/net/ethernet/sfc/tc_counters.c  |   8 +-
 drivers/net/ethernet/sfc/tc_counters.h  |   4 +
 5 files changed, 429 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/sfc/tc.h b/drivers/net/ethernet/sfc/tc.h
index fc196eb897af2..2aba9ca006185 100644
--- a/drivers/net/ethernet/sfc/tc.h
+++ b/drivers/net/ethernet/sfc/tc.h
@@ -18,12 +18,10 @@
 
 #define IS_ALL_ONES(v)	(!(typeof (v))~(v))
 
-#ifdef CONFIG_IPV6
 static inline bool efx_ipv6_addr_all_ones(struct in6_addr *addr)
 {
 	return !memchr_inv(addr, 0xff, sizeof(*addr));
 }
-#endif
 
 struct efx_tc_encap_action; /* see tc_encap_actions.h */
 
@@ -197,6 +195,7 @@ struct efx_tc_table_ct { /* TABLE_ID_CONNTRACK_TABLE */
  * @encap_match_ht: Hashtable of TC encap matches
  * @match_action_ht: Hashtable of TC match-action rules
  * @ct_zone_ht: Hashtable of TC conntrack flowtable bindings
+ * @ct_ht: Hashtable of TC conntrack flow entries
  * @neigh_ht: Hashtable of neighbour watches (&struct efx_neigh_binder)
  * @meta_ct: MAE table layout for conntrack table
  * @reps_mport_id: MAE port allocated for representor RX
@@ -230,6 +229,7 @@ struct efx_tc_state {
 	struct rhashtable encap_match_ht;
 	struct rhashtable match_action_ht;
 	struct rhashtable ct_zone_ht;
+	struct rhashtable ct_ht;
 	struct rhashtable neigh_ht;
 	struct efx_tc_table_ct meta_ct;
 	u32 reps_mport_id, reps_mport_vport_id;
diff --git a/drivers/net/ethernet/sfc/tc_conntrack.c b/drivers/net/ethernet/sfc/tc_conntrack.c
index d67302715ec36..6729b3796a8b8 100644
--- a/drivers/net/ethernet/sfc/tc_conntrack.c
+++ b/drivers/net/ethernet/sfc/tc_conntrack.c
@@ -21,6 +21,12 @@ static const struct rhashtable_params efx_tc_ct_zone_ht_params = {
 	.head_offset	= offsetof(struct efx_tc_ct_zone, linkage),
 };
 
+static const struct rhashtable_params efx_tc_ct_ht_params = {
+	.key_len	= offsetof(struct efx_tc_ct_entry, linkage),
+	.key_offset	= 0,
+	.head_offset	= offsetof(struct efx_tc_ct_entry, linkage),
+};
+
 static void efx_tc_ct_zone_free(void *ptr, void *arg)
 {
 	struct efx_tc_ct_zone *zone = ptr;
@@ -34,24 +40,420 @@ static void efx_tc_ct_zone_free(void *ptr, void *arg)
 	kfree(zone);
 }
 
+static void efx_tc_ct_free(void *ptr, void *arg)
+{
+	struct efx_tc_ct_entry *conn = ptr;
+	struct efx_nic *efx = arg;
+
+	netif_err(efx, drv, efx->net_dev,
+		  "tc ct_entry %lx still present at teardown\n",
+		  conn->cookie);
+
+	/* We can release the counter, but we can't remove the CT itself
+	 * from hardware because the table meta is already gone.
+	 */
+	efx_tc_flower_release_counter(efx, conn->cnt);
+	kfree(conn);
+}
+
 int efx_tc_init_conntrack(struct efx_nic *efx)
 {
 	int rc;
 
 	rc = rhashtable_init(&efx->tc->ct_zone_ht, &efx_tc_ct_zone_ht_params);
 	if (rc < 0)
-		return rc;
+		goto fail_ct_zone_ht;
+	rc = rhashtable_init(&efx->tc->ct_ht, &efx_tc_ct_ht_params);
+	if (rc < 0)
+		goto fail_ct_ht;
 	return 0;
+fail_ct_ht:
+	rhashtable_destroy(&efx->tc->ct_zone_ht);
+fail_ct_zone_ht:
+	return rc;
 }
 
 void efx_tc_fini_conntrack(struct efx_nic *efx)
 {
 	rhashtable_free_and_destroy(&efx->tc->ct_zone_ht, efx_tc_ct_zone_free, NULL);
+	rhashtable_free_and_destroy(&efx->tc->ct_ht, efx_tc_ct_free, efx);
+}
+
+#define EFX_NF_TCP_FLAG(flg)	cpu_to_be16(be32_to_cpu(TCP_FLAG_##flg) >> 16)
+
+static int efx_tc_ct_parse_match(struct efx_nic *efx, struct flow_rule *fr,
+				 struct efx_tc_ct_entry *conn)
+{
+	struct flow_dissector *dissector = fr->match.dissector;
+	unsigned char ipv = 0;
+	bool tcp = false;
+
+	if (flow_rule_match_key(fr, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control fm;
+
+		flow_rule_match_control(fr, &fm);
+		if (IS_ALL_ONES(fm.mask->addr_type))
+			switch (fm.key->addr_type) {
+			case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+				ipv = 4;
+				break;
+			case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+				ipv = 6;
+				break;
+			default:
+				break;
+			}
+	}
+
+	if (!ipv) {
+		netif_dbg(efx, drv, efx->net_dev,
+			  "Conntrack missing ipv specification\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (dissector->used_keys &
+	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_TCP) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_META))) {
+		netif_dbg(efx, drv, efx->net_dev,
+			  "Unsupported conntrack keys %#llx\n",
+			  dissector->used_keys);
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(fr, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic fm;
+
+		flow_rule_match_basic(fr, &fm);
+		if (!IS_ALL_ONES(fm.mask->n_proto)) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack eth_proto is not exact-match; mask %04x\n",
+				   ntohs(fm.mask->n_proto));
+			return -EOPNOTSUPP;
+		}
+		conn->eth_proto = fm.key->n_proto;
+		if (conn->eth_proto != (ipv == 4 ? htons(ETH_P_IP)
+						 : htons(ETH_P_IPV6))) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack eth_proto is not IPv%u, is %04x\n",
+				   ipv, ntohs(conn->eth_proto));
+			return -EOPNOTSUPP;
+		}
+		if (!IS_ALL_ONES(fm.mask->ip_proto)) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack ip_proto is not exact-match; mask %02x\n",
+				   fm.mask->ip_proto);
+			return -EOPNOTSUPP;
+		}
+		conn->ip_proto = fm.key->ip_proto;
+		switch (conn->ip_proto) {
+		case IPPROTO_TCP:
+			tcp = true;
+			break;
+		case IPPROTO_UDP:
+			break;
+		default:
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack ip_proto not TCP or UDP, is %02x\n",
+				   conn->ip_proto);
+			return -EOPNOTSUPP;
+		}
+	} else {
+		netif_dbg(efx, drv, efx->net_dev,
+			  "Conntrack missing eth_proto, ip_proto\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (ipv == 4 && flow_rule_match_key(fr, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs fm;
+
+		flow_rule_match_ipv4_addrs(fr, &fm);
+		if (!IS_ALL_ONES(fm.mask->src)) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack ipv4.src is not exact-match; mask %08x\n",
+				   ntohl(fm.mask->src));
+			return -EOPNOTSUPP;
+		}
+		conn->src_ip = fm.key->src;
+		if (!IS_ALL_ONES(fm.mask->dst)) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack ipv4.dst is not exact-match; mask %08x\n",
+				   ntohl(fm.mask->dst));
+			return -EOPNOTSUPP;
+		}
+		conn->dst_ip = fm.key->dst;
+	} else if (ipv == 6 && flow_rule_match_key(fr, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_match_ipv6_addrs fm;
+
+		flow_rule_match_ipv6_addrs(fr, &fm);
+		if (!efx_ipv6_addr_all_ones(&fm.mask->src)) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack ipv6.src is not exact-match; mask %pI6\n",
+				   &fm.mask->src);
+			return -EOPNOTSUPP;
+		}
+		conn->src_ip6 = fm.key->src;
+		if (!efx_ipv6_addr_all_ones(&fm.mask->dst)) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack ipv6.dst is not exact-match; mask %pI6\n",
+				   &fm.mask->dst);
+			return -EOPNOTSUPP;
+		}
+		conn->dst_ip6 = fm.key->dst;
+	} else {
+		netif_dbg(efx, drv, efx->net_dev,
+			  "Conntrack missing IPv%u addrs\n", ipv);
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(fr, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports fm;
+
+		flow_rule_match_ports(fr, &fm);
+		if (!IS_ALL_ONES(fm.mask->src)) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack ports.src is not exact-match; mask %04x\n",
+				   ntohs(fm.mask->src));
+			return -EOPNOTSUPP;
+		}
+		conn->l4_sport = fm.key->src;
+		if (!IS_ALL_ONES(fm.mask->dst)) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack ports.dst is not exact-match; mask %04x\n",
+				   ntohs(fm.mask->dst));
+			return -EOPNOTSUPP;
+		}
+		conn->l4_dport = fm.key->dst;
+	} else {
+		netif_dbg(efx, drv, efx->net_dev, "Conntrack missing L4 ports\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(fr, FLOW_DISSECTOR_KEY_TCP)) {
+		__be16 tcp_interesting_flags;
+		struct flow_match_tcp fm;
+
+		if (!tcp) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Conntrack matching on TCP keys but ipproto is not tcp\n");
+			return -EOPNOTSUPP;
+		}
+		flow_rule_match_tcp(fr, &fm);
+		tcp_interesting_flags = EFX_NF_TCP_FLAG(SYN) |
+					EFX_NF_TCP_FLAG(RST) |
+					EFX_NF_TCP_FLAG(FIN);
+		/* If any of the tcp_interesting_flags is set, we always
+		 * inhibit CT lookup in LHS (so SW can update CT table).
+		 */
+		if (fm.key->flags & tcp_interesting_flags) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Unsupported conntrack tcp.flags %04x/%04x\n",
+				   ntohs(fm.key->flags), ntohs(fm.mask->flags));
+			return -EOPNOTSUPP;
+		}
+		/* Other TCP flags cannot be filtered at CT */
+		if (fm.mask->flags & ~tcp_interesting_flags) {
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Unsupported conntrack tcp.flags %04x/%04x\n",
+				   ntohs(fm.key->flags), ntohs(fm.mask->flags));
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static int efx_tc_ct_replace(struct efx_tc_ct_zone *ct_zone,
+			     struct flow_cls_offload *tc)
+{
+	struct flow_rule *fr = flow_cls_offload_flow_rule(tc);
+	struct efx_tc_ct_entry *conn, *old;
+	struct efx_nic *efx = ct_zone->efx;
+	const struct flow_action_entry *fa;
+	struct efx_tc_counter *cnt;
+	int rc, i;
+
+	if (WARN_ON(!efx->tc))
+		return -ENETDOWN;
+	if (WARN_ON(!efx->tc->up))
+		return -ENETDOWN;
+
+	conn = kzalloc(sizeof(*conn), GFP_USER);
+	if (!conn)
+		return -ENOMEM;
+	conn->cookie = tc->cookie;
+	old = rhashtable_lookup_get_insert_fast(&efx->tc->ct_ht,
+						&conn->linkage,
+						efx_tc_ct_ht_params);
+	if (old) {
+		netif_dbg(efx, drv, efx->net_dev,
+			  "Already offloaded conntrack (cookie %lx)\n", tc->cookie);
+		rc = -EEXIST;
+		goto release;
+	}
+
+	/* Parse match */
+	conn->zone = ct_zone;
+	rc = efx_tc_ct_parse_match(efx, fr, conn);
+	if (rc)
+		goto release;
+
+	/* Parse actions */
+	flow_action_for_each(i, fa, &fr->action) {
+		switch (fa->id) {
+		case FLOW_ACTION_CT_METADATA:
+			conn->mark = fa->ct_metadata.mark;
+			if (memchr_inv(fa->ct_metadata.labels, 0, sizeof(fa->ct_metadata.labels))) {
+				netif_dbg(efx, drv, efx->net_dev,
+					  "Setting CT label not supported\n");
+				rc = -EOPNOTSUPP;
+				goto release;
+			}
+			break;
+		default:
+			netif_dbg(efx, drv, efx->net_dev,
+				  "Unhandled action %u for conntrack\n", fa->id);
+			rc = -EOPNOTSUPP;
+			goto release;
+		}
+	}
+
+	/* fill in defaults for unmangled values */
+	conn->nat_ip = conn->dnat ? conn->dst_ip : conn->src_ip;
+	conn->l4_natport = conn->dnat ? conn->l4_dport : conn->l4_sport;
+
+	cnt = efx_tc_flower_allocate_counter(efx, EFX_TC_COUNTER_TYPE_CT);
+	if (IS_ERR(cnt)) {
+		rc = PTR_ERR(cnt);
+		goto release;
+	}
+	conn->cnt = cnt;
+
+	rc = efx_mae_insert_ct(efx, conn);
+	if (rc) {
+		netif_dbg(efx, drv, efx->net_dev,
+			  "Failed to insert conntrack, %d\n", rc);
+		goto release;
+	}
+	mutex_lock(&ct_zone->mutex);
+	list_add_tail(&conn->list, &ct_zone->cts);
+	mutex_unlock(&ct_zone->mutex);
+	return 0;
+release:
+	if (conn->cnt)
+		efx_tc_flower_release_counter(efx, conn->cnt);
+	if (!old)
+		rhashtable_remove_fast(&efx->tc->ct_ht, &conn->linkage,
+				       efx_tc_ct_ht_params);
+	kfree(conn);
+	return rc;
+}
+
+/* Caller must follow with efx_tc_ct_remove_finish() after RCU grace period! */
+static void efx_tc_ct_remove(struct efx_nic *efx, struct efx_tc_ct_entry *conn)
+{
+	int rc;
+
+	/* Remove it from HW */
+	rc = efx_mae_remove_ct(efx, conn);
+	/* Delete it from SW */
+	rhashtable_remove_fast(&efx->tc->ct_ht, &conn->linkage,
+			       efx_tc_ct_ht_params);
+	if (rc) {
+		netif_err(efx, drv, efx->net_dev,
+			  "Failed to remove conntrack %lx from hw, rc %d\n",
+			  conn->cookie, rc);
+	} else {
+		netif_dbg(efx, drv, efx->net_dev, "Removed conntrack %lx\n",
+			  conn->cookie);
+	}
+}
+
+static void efx_tc_ct_remove_finish(struct efx_nic *efx, struct efx_tc_ct_entry *conn)
+{
+	/* Remove related CT counter.  This is delayed after the conn object we
+	 * are working with has been successfully removed.  This protects the
+	 * counter from being used-after-free inside efx_tc_ct_stats.
+	 */
+	efx_tc_flower_release_counter(efx, conn->cnt);
+	kfree(conn);
+}
+
+static int efx_tc_ct_destroy(struct efx_tc_ct_zone *ct_zone,
+			     struct flow_cls_offload *tc)
+{
+	struct efx_nic *efx = ct_zone->efx;
+	struct efx_tc_ct_entry *conn;
+
+	conn = rhashtable_lookup_fast(&efx->tc->ct_ht, &tc->cookie,
+				      efx_tc_ct_ht_params);
+	if (!conn) {
+		netif_warn(efx, drv, efx->net_dev,
+			   "Conntrack %lx not found to remove\n", tc->cookie);
+		return -ENOENT;
+	}
+
+	mutex_lock(&ct_zone->mutex);
+	list_del(&conn->list);
+	efx_tc_ct_remove(efx, conn);
+	mutex_unlock(&ct_zone->mutex);
+	synchronize_rcu();
+	efx_tc_ct_remove_finish(efx, conn);
+	return 0;
+}
+
+static int efx_tc_ct_stats(struct efx_tc_ct_zone *ct_zone,
+			   struct flow_cls_offload *tc)
+{
+	struct efx_nic *efx = ct_zone->efx;
+	struct efx_tc_ct_entry *conn;
+	struct efx_tc_counter *cnt;
+
+	rcu_read_lock();
+	conn = rhashtable_lookup_fast(&efx->tc->ct_ht, &tc->cookie,
+				      efx_tc_ct_ht_params);
+	if (!conn) {
+		netif_warn(efx, drv, efx->net_dev,
+			   "Conntrack %lx not found for stats\n", tc->cookie);
+		rcu_read_unlock();
+		return -ENOENT;
+	}
+
+	cnt = conn->cnt;
+	spin_lock_bh(&cnt->lock);
+	/* Report only last use */
+	flow_stats_update(&tc->stats, 0, 0, 0, cnt->touched,
+			  FLOW_ACTION_HW_STATS_DELAYED);
+	spin_unlock_bh(&cnt->lock);
+	rcu_read_unlock();
+
+	return 0;
 }
 
 static int efx_tc_flow_block(enum tc_setup_type type, void *type_data,
 			     void *cb_priv)
 {
+	struct flow_cls_offload *tcb = type_data;
+	struct efx_tc_ct_zone *ct_zone = cb_priv;
+
+	if (type != TC_SETUP_CLSFLOWER)
+		return -EOPNOTSUPP;
+
+	switch (tcb->command) {
+	case FLOW_CLS_REPLACE:
+		return efx_tc_ct_replace(ct_zone, tcb);
+	case FLOW_CLS_DESTROY:
+		return efx_tc_ct_destroy(ct_zone, tcb);
+	case FLOW_CLS_STATS:
+		return efx_tc_ct_stats(ct_zone, tcb);
+	default:
+		break;
+	};
+
 	return -EOPNOTSUPP;
 }
 
@@ -81,6 +483,8 @@ struct efx_tc_ct_zone *efx_tc_ct_register_zone(struct efx_nic *efx, u16 zone,
 	}
 	ct_zone->nf_ft = ct_ft;
 	ct_zone->efx = efx;
+	INIT_LIST_HEAD(&ct_zone->cts);
+	mutex_init(&ct_zone->mutex);
 	rc = nf_flow_table_offload_add_cb(ct_ft, efx_tc_flow_block, ct_zone);
 	netif_dbg(efx, drv, efx->net_dev, "Adding new ct_zone for %u, rc %d\n",
 		  zone, rc);
@@ -98,11 +502,22 @@ fail:
 void efx_tc_ct_unregister_zone(struct efx_nic *efx,
 			       struct efx_tc_ct_zone *ct_zone)
 {
+	struct efx_tc_ct_entry *conn, *next;
+
 	if (!refcount_dec_and_test(&ct_zone->ref))
 		return; /* still in use */
 	nf_flow_table_offload_del_cb(ct_zone->nf_ft, efx_tc_flow_block, ct_zone);
 	rhashtable_remove_fast(&efx->tc->ct_zone_ht, &ct_zone->linkage,
 			       efx_tc_ct_zone_ht_params);
+	mutex_lock(&ct_zone->mutex);
+	list_for_each_entry(conn, &ct_zone->cts, list)
+		efx_tc_ct_remove(efx, conn);
+	synchronize_rcu();
+	/* need to use _safe because efx_tc_ct_remove_finish() frees conn */
+	list_for_each_entry_safe(conn, next, &ct_zone->cts, list)
+		efx_tc_ct_remove_finish(efx, conn);
+	mutex_unlock(&ct_zone->mutex);
+	mutex_destroy(&ct_zone->mutex);
 	netif_dbg(efx, drv, efx->net_dev, "Removed ct_zone for %u\n",
 		  ct_zone->zone);
 	kfree(ct_zone);
diff --git a/drivers/net/ethernet/sfc/tc_conntrack.h b/drivers/net/ethernet/sfc/tc_conntrack.h
index a3e518344cbc5..ef5cf96c06490 100644
--- a/drivers/net/ethernet/sfc/tc_conntrack.h
+++ b/drivers/net/ethernet/sfc/tc_conntrack.h
@@ -22,6 +22,8 @@ struct efx_tc_ct_zone {
 	refcount_t ref;
 	struct nf_flowtable *nf_ft;
 	struct efx_nic *efx;
+	struct mutex mutex; /* protects cts list */
+	struct list_head cts; /* list of efx_tc_ct_entry in this zone */
 };
 
 /* create/teardown hashtables */
@@ -45,6 +47,7 @@ struct efx_tc_ct_entry {
 	struct efx_tc_ct_zone *zone;
 	u32 mark;
 	struct efx_tc_counter *cnt;
+	struct list_head list; /* entry on zone->cts */
 };
 
 #endif /* CONFIG_SFC_SRIOV */
diff --git a/drivers/net/ethernet/sfc/tc_counters.c b/drivers/net/ethernet/sfc/tc_counters.c
index 979f49058a0c0..0fafb47ea0824 100644
--- a/drivers/net/ethernet/sfc/tc_counters.c
+++ b/drivers/net/ethernet/sfc/tc_counters.c
@@ -129,8 +129,8 @@ static void efx_tc_counter_work(struct work_struct *work)
 
 /* Counter allocation */
 
-static struct efx_tc_counter *efx_tc_flower_allocate_counter(struct efx_nic *efx,
-							     int type)
+struct efx_tc_counter *efx_tc_flower_allocate_counter(struct efx_nic *efx,
+						      int type)
 {
 	struct efx_tc_counter *cnt;
 	int rc, rc2;
@@ -169,8 +169,8 @@ fail1:
 	return ERR_PTR(rc > 0 ? -EIO : rc);
 }
 
-static void efx_tc_flower_release_counter(struct efx_nic *efx,
-					  struct efx_tc_counter *cnt)
+void efx_tc_flower_release_counter(struct efx_nic *efx,
+				   struct efx_tc_counter *cnt)
 {
 	int rc;
 
diff --git a/drivers/net/ethernet/sfc/tc_counters.h b/drivers/net/ethernet/sfc/tc_counters.h
index 41e57f34b763a..f18d71c136005 100644
--- a/drivers/net/ethernet/sfc/tc_counters.h
+++ b/drivers/net/ethernet/sfc/tc_counters.h
@@ -49,6 +49,10 @@ int efx_tc_init_counters(struct efx_nic *efx);
 void efx_tc_destroy_counters(struct efx_nic *efx);
 void efx_tc_fini_counters(struct efx_nic *efx);
 
+struct efx_tc_counter *efx_tc_flower_allocate_counter(struct efx_nic *efx,
+						      int type);
+void efx_tc_flower_release_counter(struct efx_nic *efx,
+				   struct efx_tc_counter *cnt);
 struct efx_tc_counter_index *efx_tc_flower_get_counter_index(
 				struct efx_nic *efx, unsigned long cookie,
 				enum efx_tc_counter_type type);
-- 
GitLab


From 29416025185383aba51d863b9e9eff234b54d855 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 7 Aug 2023 14:48:09 +0100
Subject: [PATCH 1009/1806] sfc: handle non-zero chain_index on TC rules

Map it to an 8-bit recirc_id for use by the hardware.
Currently nothing in the driver is offloading 'goto chain' actions,
 so these rules cannot yet be hit.

Reviewed-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/tc.c           | 169 ++++++++++++++++++++----
 drivers/net/ethernet/sfc/tc.h           |  15 ++-
 drivers/net/ethernet/sfc/tc_conntrack.c |   9 ++
 drivers/net/ethernet/sfc/tc_conntrack.h |   3 +-
 4 files changed, 170 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 44a6fc30b7224..181636d07024a 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -97,6 +97,12 @@ static const struct rhashtable_params efx_tc_match_action_ht_params = {
 	.head_offset	= offsetof(struct efx_tc_flow_rule, linkage),
 };
 
+static const struct rhashtable_params efx_tc_recirc_ht_params = {
+	.key_len	= offsetof(struct efx_tc_recirc_id, linkage),
+	.key_offset	= 0,
+	.head_offset	= offsetof(struct efx_tc_recirc_id, linkage),
+};
+
 static void efx_tc_free_action_set(struct efx_nic *efx,
 				   struct efx_tc_action_set *act, bool in_hw)
 {
@@ -576,12 +582,65 @@ fail_pseudo:
 	return rc;
 }
 
+static struct efx_tc_recirc_id *efx_tc_get_recirc_id(struct efx_nic *efx,
+						     u32 chain_index,
+						     struct net_device *net_dev)
+{
+	struct efx_tc_recirc_id *rid, *old;
+	int rc;
+
+	rid = kzalloc(sizeof(*rid), GFP_USER);
+	if (!rid)
+		return ERR_PTR(-ENOMEM);
+	rid->chain_index = chain_index;
+	/* We don't take a reference here, because it's implied - if there's
+	 * a rule on the net_dev that's been offloaded to us, then the net_dev
+	 * can't go away until the rule has been deoffloaded.
+	 */
+	rid->net_dev = net_dev;
+	old = rhashtable_lookup_get_insert_fast(&efx->tc->recirc_ht,
+						&rid->linkage,
+						efx_tc_recirc_ht_params);
+	if (old) {
+		/* don't need our new entry */
+		kfree(rid);
+		if (!refcount_inc_not_zero(&old->ref))
+			return ERR_PTR(-EAGAIN);
+		/* existing entry found */
+		rid = old;
+	} else {
+		rc = ida_alloc_range(&efx->tc->recirc_ida, 1, U8_MAX, GFP_USER);
+		if (rc < 0) {
+			rhashtable_remove_fast(&efx->tc->recirc_ht,
+					       &rid->linkage,
+					       efx_tc_recirc_ht_params);
+			kfree(rid);
+			return ERR_PTR(rc);
+		}
+		rid->fw_id = rc;
+		refcount_set(&rid->ref, 1);
+	}
+	return rid;
+}
+
+static void efx_tc_put_recirc_id(struct efx_nic *efx, struct efx_tc_recirc_id *rid)
+{
+	if (!refcount_dec_and_test(&rid->ref))
+		return; /* still in use */
+	rhashtable_remove_fast(&efx->tc->recirc_ht, &rid->linkage,
+			       efx_tc_recirc_ht_params);
+	ida_free(&efx->tc->recirc_ida, rid->fw_id);
+	kfree(rid);
+}
+
 static void efx_tc_delete_rule(struct efx_nic *efx, struct efx_tc_flow_rule *rule)
 {
 	efx_mae_delete_rule(efx, rule->fw_id);
 
 	/* Release entries in subsidiary tables */
 	efx_tc_free_action_set_list(efx, &rule->acts, true);
+	if (rule->match.rid)
+		efx_tc_put_recirc_id(efx, rule->match.rid);
 	if (rule->match.encap)
 		efx_tc_flower_release_encap_match(efx, rule->match.encap);
 	rule->fw_id = MC_CMD_MAE_ACTION_RULE_INSERT_OUT_ACTION_RULE_ID_NULL;
@@ -685,8 +744,17 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 	match.mask.ingress_port = ~0;
 
 	if (tc->common.chain_index) {
-		NL_SET_ERR_MSG_MOD(extack, "No support for nonzero chain_index");
-		return -EOPNOTSUPP;
+		struct efx_tc_recirc_id *rid;
+
+		rid = efx_tc_get_recirc_id(efx, tc->common.chain_index, net_dev);
+		if (IS_ERR(rid)) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Failed to allocate a hardware recirculation ID for chain_index %u",
+					       tc->common.chain_index);
+			return PTR_ERR(rid);
+		}
+		match.rid = rid;
+		match.value.recirc_id = rid->fw_id;
 	}
 	match.mask.recirc_id = 0xff;
 
@@ -706,12 +774,13 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 	if (!found) { /* We don't care. */
 		netif_dbg(efx, drv, efx->net_dev,
 			  "Ignoring foreign filter that doesn't egdev us\n");
-		return -EOPNOTSUPP;
+		rc = -EOPNOTSUPP;
+		goto release;
 	}
 
 	rc = efx_mae_match_check_caps(efx, &match.mask, NULL);
 	if (rc)
-		return rc;
+		goto release;
 
 	if (efx_tc_match_is_encap(&match.mask)) {
 		enum efx_encap_type type;
@@ -720,7 +789,8 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 		if (type == EFX_ENCAP_TYPE_NONE) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Egress encap match on unsupported tunnel device");
-			return -EOPNOTSUPP;
+			rc = -EOPNOTSUPP;
+			goto release;
 		}
 
 		rc = efx_mae_check_encap_type_supported(efx, type);
@@ -728,25 +798,26 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 			NL_SET_ERR_MSG_FMT_MOD(extack,
 					       "Firmware reports no support for %s encap match",
 					       efx_tc_encap_type_name(type));
-			return rc;
+			goto release;
 		}
 
 		rc = efx_tc_flower_record_encap_match(efx, &match, type,
 						      EFX_TC_EM_DIRECT, 0, 0,
 						      extack);
 		if (rc)
-			return rc;
+			goto release;
 	} else {
 		/* This is not a tunnel decap rule, ignore it */
 		netif_dbg(efx, drv, efx->net_dev,
 			  "Ignoring foreign filter without encap match\n");
-		return -EOPNOTSUPP;
+		rc = -EOPNOTSUPP;
+		goto release;
 	}
 
 	rule = kzalloc(sizeof(*rule), GFP_USER);
 	if (!rule) {
 		rc = -ENOMEM;
-		goto out_free;
+		goto release;
 	}
 	INIT_LIST_HEAD(&rule->acts.list);
 	rule->cookie = tc->cookie;
@@ -758,7 +829,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 			  "Ignoring already-offloaded rule (cookie %lx)\n",
 			  tc->cookie);
 		rc = -EEXIST;
-		goto out_free;
+		goto release;
 	}
 
 	act = kzalloc(sizeof(*act), GFP_USER);
@@ -916,15 +987,17 @@ release:
 	/* We failed to insert the rule, so free up any entries we created in
 	 * subsidiary tables.
 	 */
+	if (match.rid)
+		efx_tc_put_recirc_id(efx, match.rid);
 	if (act)
 		efx_tc_free_action_set(efx, act, false);
 	if (rule) {
-		rhashtable_remove_fast(&efx->tc->match_action_ht,
-				       &rule->linkage,
-				       efx_tc_match_action_ht_params);
+		if (!old)
+			rhashtable_remove_fast(&efx->tc->match_action_ht,
+					       &rule->linkage,
+					       efx_tc_match_action_ht_params);
 		efx_tc_free_action_set_list(efx, &rule->acts, false);
 	}
-out_free:
 	kfree(rule);
 	if (match.encap)
 		efx_tc_flower_release_encap_match(efx, match.encap);
@@ -986,19 +1059,45 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 		return -EOPNOTSUPP;
 	}
 
+	/* chain_index 0 is always recirc_id 0 (and does not appear in recirc_ht).
+	 * Conveniently, match.rid == NULL and match.value.recirc_id == 0 owing
+	 * to the initial memset(), so we don't need to do anything in that case.
+	 */
 	if (tc->common.chain_index) {
-		NL_SET_ERR_MSG_MOD(extack, "No support for nonzero chain_index");
-		return -EOPNOTSUPP;
+		struct efx_tc_recirc_id *rid;
+
+		/* Note regarding passed net_dev:
+		 * VFreps and PF can share chain namespace, as they have
+		 * distinct ingress_mports.  So we don't need to burn an
+		 * extra recirc_id if both use the same chain_index.
+		 * (Strictly speaking, we could give each VFrep its own
+		 * recirc_id namespace that doesn't take IDs away from the
+		 * PF, but that would require a bunch of additional IDAs -
+		 * one for each representor - and that's not likely to be
+		 * the main cause of recirc_id exhaustion anyway.)
+		 */
+		rid = efx_tc_get_recirc_id(efx, tc->common.chain_index,
+					   efx->net_dev);
+		if (IS_ERR(rid)) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Failed to allocate a hardware recirculation ID for chain_index %u",
+					       tc->common.chain_index);
+			return PTR_ERR(rid);
+		}
+		match.rid = rid;
+		match.value.recirc_id = rid->fw_id;
 	}
 	match.mask.recirc_id = 0xff;
 
 	rc = efx_mae_match_check_caps(efx, &match.mask, extack);
 	if (rc)
-		return rc;
+		goto release;
 
 	rule = kzalloc(sizeof(*rule), GFP_USER);
-	if (!rule)
-		return -ENOMEM;
+	if (!rule) {
+		rc = -ENOMEM;
+		goto release;
+	}
 	INIT_LIST_HEAD(&rule->acts.list);
 	rule->cookie = tc->cookie;
 	old = rhashtable_lookup_get_insert_fast(&efx->tc->match_action_ht,
@@ -1008,8 +1107,8 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 		netif_dbg(efx, drv, efx->net_dev,
 			  "Already offloaded rule (cookie %lx)\n", tc->cookie);
 		NL_SET_ERR_MSG_MOD(extack, "Rule already offloaded");
-		kfree(rule);
-		return -EEXIST;
+		rc = -EEXIST;
+		goto release;
 	}
 
 	/* Parse actions */
@@ -1327,12 +1426,15 @@ release:
 	/* We failed to insert the rule, so free up any entries we created in
 	 * subsidiary tables.
 	 */
+	if (match.rid)
+		efx_tc_put_recirc_id(efx, match.rid);
 	if (act)
 		efx_tc_free_action_set(efx, act, false);
 	if (rule) {
-		rhashtable_remove_fast(&efx->tc->match_action_ht,
-				       &rule->linkage,
-				       efx_tc_match_action_ht_params);
+		if (!old)
+			rhashtable_remove_fast(&efx->tc->match_action_ht,
+					       &rule->linkage,
+					       efx_tc_match_action_ht_params);
 		efx_tc_free_action_set_list(efx, &rule->acts, false);
 	}
 	kfree(rule);
@@ -1702,6 +1804,16 @@ static void efx_tc_encap_match_free(void *ptr, void *__unused)
 	kfree(encap);
 }
 
+static void efx_tc_recirc_free(void *ptr, void *arg)
+{
+	struct efx_tc_recirc_id *rid = ptr;
+	struct efx_nic *efx = arg;
+
+	WARN_ON(refcount_read(&rid->ref));
+	ida_free(&efx->tc->recirc_ida, rid->fw_id);
+	kfree(rid);
+}
+
 static void efx_tc_flow_free(void *ptr, void *arg)
 {
 	struct efx_tc_flow_rule *rule = ptr;
@@ -1751,6 +1863,10 @@ int efx_init_struct_tc(struct efx_nic *efx)
 	rc = efx_tc_init_conntrack(efx);
 	if (rc < 0)
 		goto fail_conntrack;
+	rc = rhashtable_init(&efx->tc->recirc_ht, &efx_tc_recirc_ht_params);
+	if (rc < 0)
+		goto fail_recirc_ht;
+	ida_init(&efx->tc->recirc_ida);
 	efx->tc->reps_filter_uc = -1;
 	efx->tc->reps_filter_mc = -1;
 	INIT_LIST_HEAD(&efx->tc->dflt.pf.acts.list);
@@ -1763,6 +1879,8 @@ int efx_init_struct_tc(struct efx_nic *efx)
 	efx->tc->facts.reps.fw_id = MC_CMD_MAE_ACTION_SET_ALLOC_OUT_ACTION_SET_ID_NULL;
 	efx->extra_channel_type[EFX_EXTRA_CHANNEL_TC] = &efx_tc_channel_type;
 	return 0;
+fail_recirc_ht:
+	efx_tc_destroy_conntrack(efx);
 fail_conntrack:
 	rhashtable_destroy(&efx->tc->match_action_ht);
 fail_match_action_ht:
@@ -1799,6 +1917,9 @@ void efx_fini_struct_tc(struct efx_nic *efx)
 	rhashtable_free_and_destroy(&efx->tc->encap_match_ht,
 				    efx_tc_encap_match_free, NULL);
 	efx_tc_fini_conntrack(efx);
+	rhashtable_free_and_destroy(&efx->tc->recirc_ht, efx_tc_recirc_free, efx);
+	WARN_ON(!ida_is_empty(&efx->tc->recirc_ida));
+	ida_destroy(&efx->tc->recirc_ida);
 	efx_tc_fini_counters(efx);
 	efx_tc_fini_encap_actions(efx);
 	mutex_unlock(&efx->tc->mutex);
diff --git a/drivers/net/ethernet/sfc/tc.h b/drivers/net/ethernet/sfc/tc.h
index 2aba9ca006185..af15020c8da7e 100644
--- a/drivers/net/ethernet/sfc/tc.h
+++ b/drivers/net/ethernet/sfc/tc.h
@@ -45,7 +45,7 @@ struct efx_tc_action_set {
 struct efx_tc_match_fields {
 	/* L1 */
 	u32 ingress_port;
-	u8 recirc_id;
+	u8 recirc_id; /* mapped from (u32) TC chain_index to smaller space */
 	/* L2 (inner when encap) */
 	__be16 eth_proto;
 	__be16 vlan_tci[2], vlan_proto[2];
@@ -115,10 +115,19 @@ struct efx_tc_encap_match {
 	struct efx_tc_encap_match *pseudo; /* Referenced pseudo EM if needed */
 };
 
+struct efx_tc_recirc_id {
+	u32 chain_index;
+	struct net_device *net_dev;
+	struct rhash_head linkage;
+	refcount_t ref;
+	u8 fw_id; /* index allocated for use in the MAE */
+};
+
 struct efx_tc_match {
 	struct efx_tc_match_fields value;
 	struct efx_tc_match_fields mask;
 	struct efx_tc_encap_match *encap;
+	struct efx_tc_recirc_id *rid;
 };
 
 struct efx_tc_action_set_list {
@@ -197,6 +206,8 @@ struct efx_tc_table_ct { /* TABLE_ID_CONNTRACK_TABLE */
  * @ct_zone_ht: Hashtable of TC conntrack flowtable bindings
  * @ct_ht: Hashtable of TC conntrack flow entries
  * @neigh_ht: Hashtable of neighbour watches (&struct efx_neigh_binder)
+ * @recirc_ht: Hashtable of recirculation ID mappings (&struct efx_tc_recirc_id)
+ * @recirc_ida: Recirculation ID allocator
  * @meta_ct: MAE table layout for conntrack table
  * @reps_mport_id: MAE port allocated for representor RX
  * @reps_filter_uc: VNIC filter for representor unicast RX (promisc)
@@ -231,6 +242,8 @@ struct efx_tc_state {
 	struct rhashtable ct_zone_ht;
 	struct rhashtable ct_ht;
 	struct rhashtable neigh_ht;
+	struct rhashtable recirc_ht;
+	struct ida recirc_ida;
 	struct efx_tc_table_ct meta_ct;
 	u32 reps_mport_id, reps_mport_vport_id;
 	s32 reps_filter_uc, reps_filter_mc;
diff --git a/drivers/net/ethernet/sfc/tc_conntrack.c b/drivers/net/ethernet/sfc/tc_conntrack.c
index 6729b3796a8b8..54ed288543d03 100644
--- a/drivers/net/ethernet/sfc/tc_conntrack.c
+++ b/drivers/net/ethernet/sfc/tc_conntrack.c
@@ -73,6 +73,15 @@ fail_ct_zone_ht:
 	return rc;
 }
 
+/* Only call this in init failure teardown.
+ * Normal exit should fini instead as there may be entries in the table.
+ */
+void efx_tc_destroy_conntrack(struct efx_nic *efx)
+{
+	rhashtable_destroy(&efx->tc->ct_ht);
+	rhashtable_destroy(&efx->tc->ct_zone_ht);
+}
+
 void efx_tc_fini_conntrack(struct efx_nic *efx)
 {
 	rhashtable_free_and_destroy(&efx->tc->ct_zone_ht, efx_tc_ct_zone_free, NULL);
diff --git a/drivers/net/ethernet/sfc/tc_conntrack.h b/drivers/net/ethernet/sfc/tc_conntrack.h
index ef5cf96c06490..e75c8eb1965d9 100644
--- a/drivers/net/ethernet/sfc/tc_conntrack.h
+++ b/drivers/net/ethernet/sfc/tc_conntrack.h
@@ -26,8 +26,9 @@ struct efx_tc_ct_zone {
 	struct list_head cts; /* list of efx_tc_ct_entry in this zone */
 };
 
-/* create/teardown hashtables */
+/* create/uncreate/teardown hashtables */
 int efx_tc_init_conntrack(struct efx_nic *efx);
+void efx_tc_destroy_conntrack(struct efx_nic *efx);
 void efx_tc_fini_conntrack(struct efx_nic *efx);
 
 struct efx_tc_ct_zone *efx_tc_ct_register_zone(struct efx_nic *efx, u16 zone,
-- 
GitLab


From 1dfc29be4d743bba9c249b50acf8e44cb5477624 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 7 Aug 2023 14:48:10 +0100
Subject: [PATCH 1010/1806] sfc: conntrack state matches in TC rules

Parse ct_state trk/est, mark and zone out of flower keys, and plumb
 them through to the hardware, performing some minor translations.
Nothing can actually hit them yet as we're not offloading any DO_CT
 actions.

Reviewed-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/mae.c  | 33 +++++++++++++++--
 drivers/net/ethernet/sfc/mcdi.h |  5 +++
 drivers/net/ethernet/sfc/tc.c   | 66 +++++++++++++++++++++++++++++++++
 drivers/net/ethernet/sfc/tc.h   |  5 +++
 4 files changed, 105 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c
index 8ebf71a54bf99..1fa0958d52628 100644
--- a/drivers/net/ethernet/sfc/mae.c
+++ b/drivers/net/ethernet/sfc/mae.c
@@ -695,8 +695,13 @@ int efx_mae_match_check_caps(struct efx_nic *efx,
 	    CHECK(L4_SPORT, l4_sport) ||
 	    CHECK(L4_DPORT, l4_dport) ||
 	    CHECK(TCP_FLAGS, tcp_flags) ||
+	    CHECK_BIT(TCP_SYN_FIN_RST, tcp_syn_fin_rst) ||
 	    CHECK_BIT(IS_IP_FRAG, ip_frag) ||
 	    CHECK_BIT(IP_FIRST_FRAG, ip_firstfrag) ||
+	    CHECK_BIT(DO_CT, ct_state_trk) ||
+	    CHECK_BIT(CT_HIT, ct_state_est) ||
+	    CHECK(CT_MARK, ct_mark) ||
+	    CHECK(CT_DOMAIN, ct_zone) ||
 	    CHECK(RECIRC_ID, recirc_id))
 		return rc;
 	/* Matches on outer fields are done in a separate hardware table,
@@ -1672,20 +1677,40 @@ static int efx_mae_populate_match_criteria(MCDI_DECLARE_STRUCT_PTR(match_crit),
 	}
 	MCDI_STRUCT_SET_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_INGRESS_MPORT_SELECTOR_MASK,
 			      match->mask.ingress_port);
-	EFX_POPULATE_DWORD_2(*_MCDI_STRUCT_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_FLAGS),
+	EFX_POPULATE_DWORD_5(*_MCDI_STRUCT_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_FLAGS),
+			     MAE_FIELD_MASK_VALUE_PAIRS_V2_DO_CT,
+			     match->value.ct_state_trk,
+			     MAE_FIELD_MASK_VALUE_PAIRS_V2_CT_HIT,
+			     match->value.ct_state_est,
 			     MAE_FIELD_MASK_VALUE_PAIRS_V2_IS_IP_FRAG,
 			     match->value.ip_frag,
 			     MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_FIRST_FRAG,
-			     match->value.ip_firstfrag);
-	EFX_POPULATE_DWORD_2(*_MCDI_STRUCT_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_FLAGS_MASK),
+			     match->value.ip_firstfrag,
+			     MAE_FIELD_MASK_VALUE_PAIRS_V2_TCP_SYN_FIN_RST,
+			     match->value.tcp_syn_fin_rst);
+	EFX_POPULATE_DWORD_5(*_MCDI_STRUCT_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_FLAGS_MASK),
+			     MAE_FIELD_MASK_VALUE_PAIRS_V2_DO_CT,
+			     match->mask.ct_state_trk,
+			     MAE_FIELD_MASK_VALUE_PAIRS_V2_CT_HIT,
+			     match->mask.ct_state_est,
 			     MAE_FIELD_MASK_VALUE_PAIRS_V2_IS_IP_FRAG,
 			     match->mask.ip_frag,
 			     MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_FIRST_FRAG,
-			     match->mask.ip_firstfrag);
+			     match->mask.ip_firstfrag,
+			     MAE_FIELD_MASK_VALUE_PAIRS_V2_TCP_SYN_FIN_RST,
+			     match->mask.tcp_syn_fin_rst);
 	MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_RECIRC_ID,
 			     match->value.recirc_id);
 	MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_RECIRC_ID_MASK,
 			     match->mask.recirc_id);
+	MCDI_STRUCT_SET_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_CT_MARK,
+			      match->value.ct_mark);
+	MCDI_STRUCT_SET_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_CT_MARK_MASK,
+			      match->mask.ct_mark);
+	MCDI_STRUCT_SET_WORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_CT_DOMAIN,
+			     match->value.ct_zone);
+	MCDI_STRUCT_SET_WORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_CT_DOMAIN_MASK,
+			     match->mask.ct_zone);
 	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETHER_TYPE_BE,
 				match->value.eth_proto);
 	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETHER_TYPE_BE_MASK,
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index 995a26686fd82..700d0252aebdc 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -229,6 +229,11 @@ void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev);
 	BUILD_BUG_ON(MC_CMD_ ## _field ## _OFST & 1);			\
 	*(__force __le16 *)MCDI_PTR(_buf, _field) = cpu_to_le16(_value);\
 	} while (0)
+#define MCDI_STRUCT_SET_WORD(_buf, _field, _value) do {			\
+	BUILD_BUG_ON(_field ## _LEN != 2);				\
+	BUILD_BUG_ON(_field ## _OFST & 1);				\
+	*(__force __le16 *)MCDI_STRUCT_PTR(_buf, _field) = cpu_to_le16(_value);\
+	} while (0)
 #define MCDI_WORD(_buf, _field)						\
 	((u16)BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 2) +	\
 	 le16_to_cpu(*(__force const __le16 *)MCDI_PTR(_buf, _field)))
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 181636d07024a..a9f4bfaacac31 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -222,6 +222,7 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx,
 	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_CT) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_TCP) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_IP))) {
 		NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported flower keys %#llx",
@@ -363,6 +364,31 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx,
 				       dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CT)) {
+		struct flow_match_ct fm;
+
+		flow_rule_match_ct(rule, &fm);
+		match->value.ct_state_trk = !!(fm.key->ct_state & TCA_FLOWER_KEY_CT_FLAGS_TRACKED);
+		match->mask.ct_state_trk = !!(fm.mask->ct_state & TCA_FLOWER_KEY_CT_FLAGS_TRACKED);
+		match->value.ct_state_est = !!(fm.key->ct_state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED);
+		match->mask.ct_state_est = !!(fm.mask->ct_state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED);
+		if (fm.mask->ct_state & ~(TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+					  TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED)) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Unsupported ct_state match %#x",
+					       fm.mask->ct_state);
+			return -EOPNOTSUPP;
+		}
+		match->value.ct_mark = fm.key->ct_mark;
+		match->mask.ct_mark = fm.mask->ct_mark;
+		match->value.ct_zone = fm.key->ct_zone;
+		match->mask.ct_zone = fm.mask->ct_zone;
+
+		if (memchr_inv(fm.mask->ct_labels, 0, sizeof(fm.mask->ct_labels))) {
+			NL_SET_ERR_MSG_MOD(extack, "Matching on ct_label not supported");
+			return -EOPNOTSUPP;
+		}
+	}
 
 	return 0;
 }
@@ -758,6 +784,26 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 	}
 	match.mask.recirc_id = 0xff;
 
+	/* AR table can't match on DO_CT (+trk).  But a commonly used pattern is
+	 * +trk+est, which is strictly implied by +est, so rewrite it to that.
+	 */
+	if (match.mask.ct_state_trk && match.value.ct_state_trk &&
+	    match.mask.ct_state_est && match.value.ct_state_est)
+		match.mask.ct_state_trk = 0;
+	/* Thanks to CT_TCP_FLAGS_INHIBIT, packets with interesting flags could
+	 * match +trk-est (CT_HIT=0) despite being on an established connection.
+	 * So make -est imply -tcp_syn_fin_rst match to ensure these packets
+	 * still hit the software path.
+	 */
+	if (match.mask.ct_state_est && !match.value.ct_state_est) {
+		if (match.value.tcp_syn_fin_rst) {
+			/* Can't offload this combination */
+			rc = -EOPNOTSUPP;
+			goto release;
+		}
+		match.mask.tcp_syn_fin_rst = true;
+	}
+
 	flow_action_for_each(i, fa, &fr->action) {
 		switch (fa->id) {
 		case FLOW_ACTION_REDIRECT:
@@ -1089,6 +1135,26 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 	}
 	match.mask.recirc_id = 0xff;
 
+	/* AR table can't match on DO_CT (+trk).  But a commonly used pattern is
+	 * +trk+est, which is strictly implied by +est, so rewrite it to that.
+	 */
+	if (match.mask.ct_state_trk && match.value.ct_state_trk &&
+	    match.mask.ct_state_est && match.value.ct_state_est)
+		match.mask.ct_state_trk = 0;
+	/* Thanks to CT_TCP_FLAGS_INHIBIT, packets with interesting flags could
+	 * match +trk-est (CT_HIT=0) despite being on an established connection.
+	 * So make -est imply -tcp_syn_fin_rst match to ensure these packets
+	 * still hit the software path.
+	 */
+	if (match.mask.ct_state_est && !match.value.ct_state_est) {
+		if (match.value.tcp_syn_fin_rst) {
+			/* Can't offload this combination */
+			rc = -EOPNOTSUPP;
+			goto release;
+		}
+		match.mask.tcp_syn_fin_rst = true;
+	}
+
 	rc = efx_mae_match_check_caps(efx, &match.mask, extack);
 	if (rc)
 		goto release;
diff --git a/drivers/net/ethernet/sfc/tc.h b/drivers/net/ethernet/sfc/tc.h
index af15020c8da7e..ce8e30743a3a9 100644
--- a/drivers/net/ethernet/sfc/tc.h
+++ b/drivers/net/ethernet/sfc/tc.h
@@ -60,6 +60,7 @@ struct efx_tc_match_fields {
 	/* L4 */
 	__be16 l4_sport, l4_dport; /* Ports (UDP, TCP) */
 	__be16 tcp_flags;
+	bool tcp_syn_fin_rst; /* true if ANY of SYN/FIN/RST are set */
 	/* Encap.  The following are *outer* fields.  Note that there are no
 	 * outer eth (L2) fields; this is because TC doesn't have them.
 	 */
@@ -68,6 +69,10 @@ struct efx_tc_match_fields {
 	u8 enc_ip_tos, enc_ip_ttl;
 	__be16 enc_sport, enc_dport;
 	__be32 enc_keyid; /* e.g. VNI, VSID */
+	/* Conntrack. */
+	u16 ct_state_trk:1, ct_state_est:1;
+	u32 ct_mark;
+	u16 ct_zone;
 };
 
 static inline bool efx_tc_match_is_encap(const struct efx_tc_match_fields *mask)
-- 
GitLab


From 01ad088fb05cb69bb2e061dc2ebddb67c62aeaf4 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 7 Aug 2023 14:48:11 +0100
Subject: [PATCH 1011/1806] sfc: offload left-hand side rules for conntrack

Handle the (comparatively) simple case of a -trk rule on an efx netdev
 (i.e. not a tunnel decap rule) with ct and goto chain actions.

Reviewed-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/bitfield.h |   2 +
 drivers/net/ethernet/sfc/mae.c      | 287 ++++++++++++++++++++++++++++
 drivers/net/ethernet/sfc/mae.h      |   6 +
 drivers/net/ethernet/sfc/mcdi.h     |   6 +
 drivers/net/ethernet/sfc/tc.c       | 282 +++++++++++++++++++++++++++
 drivers/net/ethernet/sfc/tc.h       |  16 ++
 6 files changed, 599 insertions(+)

diff --git a/drivers/net/ethernet/sfc/bitfield.h b/drivers/net/ethernet/sfc/bitfield.h
index 1f981dfe4bdc1..89665fc9b8d0c 100644
--- a/drivers/net/ethernet/sfc/bitfield.h
+++ b/drivers/net/ethernet/sfc/bitfield.h
@@ -26,6 +26,8 @@
 /* Lowest bit numbers and widths */
 #define EFX_DUMMY_FIELD_LBN 0
 #define EFX_DUMMY_FIELD_WIDTH 0
+#define EFX_BYTE_0_LBN 0
+#define EFX_BYTE_0_WIDTH 8
 #define EFX_WORD_0_LBN 0
 #define EFX_WORD_0_WIDTH 16
 #define EFX_WORD_1_LBN 16
diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c
index 1fa0958d52628..3b8780c76b6e2 100644
--- a/drivers/net/ethernet/sfc/mae.c
+++ b/drivers/net/ethernet/sfc/mae.c
@@ -727,6 +727,90 @@ int efx_mae_match_check_caps(struct efx_nic *efx,
 	}
 	return 0;
 }
+
+/* Checks for match fields not supported in LHS Outer Rules */
+#define UNSUPPORTED(_field)	({					       \
+	enum mask_type typ = classify_mask((const u8 *)&mask->_field,	       \
+					   sizeof(mask->_field));	       \
+									       \
+	if (typ != MASK_ZEROES) {					       \
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported match field " #_field);\
+		rc = -EOPNOTSUPP;					       \
+	}								       \
+	rc;								       \
+})
+#define UNSUPPORTED_BIT(_field)	({					       \
+	if (mask->_field) {						       \
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported match field " #_field);\
+		rc = -EOPNOTSUPP;					       \
+	}								       \
+	rc;								       \
+})
+
+/* LHS rules are (normally) inserted in the Outer Rule table, which means
+ * they use ENC_ fields in hardware to match regular (not enc_) fields from
+ * &struct efx_tc_match_fields.
+ */
+int efx_mae_match_check_caps_lhs(struct efx_nic *efx,
+				 const struct efx_tc_match_fields *mask,
+				 struct netlink_ext_ack *extack)
+{
+	const u8 *supported_fields = efx->tc->caps->outer_rule_fields;
+	__be32 ingress_port = cpu_to_be32(mask->ingress_port);
+	enum mask_type ingress_port_mask_type;
+	int rc;
+
+	/* Check for _PREFIX assumes big-endian, so we need to convert */
+	ingress_port_mask_type = classify_mask((const u8 *)&ingress_port,
+					       sizeof(ingress_port));
+	rc = efx_mae_match_check_cap_typ(supported_fields[MAE_FIELD_INGRESS_PORT],
+					 ingress_port_mask_type);
+	if (rc) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "No support for %s mask in field %s\n",
+				       mask_type_name(ingress_port_mask_type),
+				       "ingress_port");
+		return rc;
+	}
+	if (CHECK(ENC_ETHER_TYPE, eth_proto) ||
+	    CHECK(ENC_VLAN0_TCI, vlan_tci[0]) ||
+	    CHECK(ENC_VLAN0_PROTO, vlan_proto[0]) ||
+	    CHECK(ENC_VLAN1_TCI, vlan_tci[1]) ||
+	    CHECK(ENC_VLAN1_PROTO, vlan_proto[1]) ||
+	    CHECK(ENC_ETH_SADDR, eth_saddr) ||
+	    CHECK(ENC_ETH_DADDR, eth_daddr) ||
+	    CHECK(ENC_IP_PROTO, ip_proto) ||
+	    CHECK(ENC_IP_TOS, ip_tos) ||
+	    CHECK(ENC_IP_TTL, ip_ttl) ||
+	    CHECK_BIT(ENC_IP_FRAG, ip_frag) ||
+	    UNSUPPORTED_BIT(ip_firstfrag) ||
+	    CHECK(ENC_SRC_IP4, src_ip) ||
+	    CHECK(ENC_DST_IP4, dst_ip) ||
+#ifdef CONFIG_IPV6
+	    CHECK(ENC_SRC_IP6, src_ip6) ||
+	    CHECK(ENC_DST_IP6, dst_ip6) ||
+#endif
+	    CHECK(ENC_L4_SPORT, l4_sport) ||
+	    CHECK(ENC_L4_DPORT, l4_dport) ||
+	    UNSUPPORTED(tcp_flags) ||
+	    CHECK_BIT(TCP_SYN_FIN_RST, tcp_syn_fin_rst))
+		return rc;
+	if (efx_tc_match_is_encap(mask)) {
+		/* can't happen; disallowed for local rules, translated
+		 * for foreign rules.
+		 */
+		NL_SET_ERR_MSG_MOD(extack, "Unexpected encap match in LHS rule");
+		return -EOPNOTSUPP;
+	}
+	if (UNSUPPORTED(enc_keyid) ||
+	    /* Can't filter on conntrack in LHS rules */
+	    UNSUPPORTED_BIT(ct_state_trk) ||
+	    UNSUPPORTED_BIT(ct_state_est) ||
+	    UNSUPPORTED(ct_mark) ||
+	    UNSUPPORTED(recirc_id))
+		return rc;
+	return 0;
+}
+#undef UNSUPPORTED
 #undef CHECK_BIT
 #undef CHECK
 
@@ -1409,6 +1493,209 @@ int efx_mae_unregister_encap_match(struct efx_nic *efx,
 	return 0;
 }
 
+static int efx_mae_populate_lhs_match_criteria(MCDI_DECLARE_STRUCT_PTR(match_crit),
+					       const struct efx_tc_match *match)
+{
+	if (match->mask.ingress_port) {
+		if (~match->mask.ingress_port)
+			return -EOPNOTSUPP;
+		MCDI_STRUCT_SET_DWORD(match_crit,
+				      MAE_ENC_FIELD_PAIRS_INGRESS_MPORT_SELECTOR,
+				      match->value.ingress_port);
+	}
+	MCDI_STRUCT_SET_DWORD(match_crit, MAE_ENC_FIELD_PAIRS_INGRESS_MPORT_SELECTOR_MASK,
+			      match->mask.ingress_port);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_ETHER_TYPE_BE,
+				match->value.eth_proto);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_ETHER_TYPE_BE_MASK,
+				match->mask.eth_proto);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_VLAN0_TCI_BE,
+				match->value.vlan_tci[0]);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_VLAN0_TCI_BE_MASK,
+				match->mask.vlan_tci[0]);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_VLAN0_PROTO_BE,
+				match->value.vlan_proto[0]);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_VLAN0_PROTO_BE_MASK,
+				match->mask.vlan_proto[0]);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_VLAN1_TCI_BE,
+				match->value.vlan_tci[1]);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_VLAN1_TCI_BE_MASK,
+				match->mask.vlan_tci[1]);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_VLAN1_PROTO_BE,
+				match->value.vlan_proto[1]);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_VLAN1_PROTO_BE_MASK,
+				match->mask.vlan_proto[1]);
+	memcpy(MCDI_STRUCT_PTR(match_crit, MAE_ENC_FIELD_PAIRS_ENC_ETH_SADDR_BE),
+	       match->value.eth_saddr, ETH_ALEN);
+	memcpy(MCDI_STRUCT_PTR(match_crit, MAE_ENC_FIELD_PAIRS_ENC_ETH_SADDR_BE_MASK),
+	       match->mask.eth_saddr, ETH_ALEN);
+	memcpy(MCDI_STRUCT_PTR(match_crit, MAE_ENC_FIELD_PAIRS_ENC_ETH_DADDR_BE),
+	       match->value.eth_daddr, ETH_ALEN);
+	memcpy(MCDI_STRUCT_PTR(match_crit, MAE_ENC_FIELD_PAIRS_ENC_ETH_DADDR_BE_MASK),
+	       match->mask.eth_daddr, ETH_ALEN);
+	MCDI_STRUCT_SET_BYTE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_IP_PROTO,
+			     match->value.ip_proto);
+	MCDI_STRUCT_SET_BYTE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_IP_PROTO_MASK,
+			     match->mask.ip_proto);
+	MCDI_STRUCT_SET_BYTE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_IP_TOS,
+			     match->value.ip_tos);
+	MCDI_STRUCT_SET_BYTE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_IP_TOS_MASK,
+			     match->mask.ip_tos);
+	MCDI_STRUCT_SET_BYTE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_IP_TTL,
+			     match->value.ip_ttl);
+	MCDI_STRUCT_SET_BYTE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_IP_TTL_MASK,
+			     match->mask.ip_ttl);
+	MCDI_STRUCT_POPULATE_BYTE_1(match_crit,
+				    MAE_ENC_FIELD_PAIRS_ENC_VLAN_FLAGS,
+				    MAE_ENC_FIELD_PAIRS_ENC_IP_FRAG,
+				    match->value.ip_frag);
+	MCDI_STRUCT_POPULATE_BYTE_1(match_crit,
+				    MAE_ENC_FIELD_PAIRS_ENC_VLAN_FLAGS_MASK,
+				    MAE_ENC_FIELD_PAIRS_ENC_IP_FRAG_MASK,
+				    match->mask.ip_frag);
+	MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_SRC_IP4_BE,
+				 match->value.src_ip);
+	MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_SRC_IP4_BE_MASK,
+				 match->mask.src_ip);
+	MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_DST_IP4_BE,
+				 match->value.dst_ip);
+	MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_DST_IP4_BE_MASK,
+				 match->mask.dst_ip);
+#ifdef CONFIG_IPV6
+	memcpy(MCDI_STRUCT_PTR(match_crit, MAE_ENC_FIELD_PAIRS_ENC_SRC_IP6_BE),
+	       &match->value.src_ip6, sizeof(struct in6_addr));
+	memcpy(MCDI_STRUCT_PTR(match_crit, MAE_ENC_FIELD_PAIRS_ENC_SRC_IP6_BE_MASK),
+	       &match->mask.src_ip6, sizeof(struct in6_addr));
+	memcpy(MCDI_STRUCT_PTR(match_crit, MAE_ENC_FIELD_PAIRS_ENC_DST_IP6_BE),
+	       &match->value.dst_ip6, sizeof(struct in6_addr));
+	memcpy(MCDI_STRUCT_PTR(match_crit, MAE_ENC_FIELD_PAIRS_ENC_DST_IP6_BE_MASK),
+	       &match->mask.dst_ip6, sizeof(struct in6_addr));
+#endif
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_L4_SPORT_BE,
+				match->value.l4_sport);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_L4_SPORT_BE_MASK,
+				match->mask.l4_sport);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_L4_DPORT_BE,
+				match->value.l4_dport);
+	MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_ENC_FIELD_PAIRS_ENC_L4_DPORT_BE_MASK,
+				match->mask.l4_dport);
+	/* No enc-keys in LHS rules.  Caps check should have caught this; any
+	 * enc-keys from an fLHS should have been translated to regular keys
+	 * and any EM should be a pseudo (we're an OR so can't have a direct
+	 * EM with another OR).
+	 */
+	if (WARN_ON_ONCE(match->encap && !match->encap->type))
+		return -EOPNOTSUPP;
+	if (WARN_ON_ONCE(match->mask.enc_src_ip))
+		return -EOPNOTSUPP;
+	if (WARN_ON_ONCE(match->mask.enc_dst_ip))
+		return -EOPNOTSUPP;
+#ifdef CONFIG_IPV6
+	if (WARN_ON_ONCE(!ipv6_addr_any(&match->mask.enc_src_ip6)))
+		return -EOPNOTSUPP;
+	if (WARN_ON_ONCE(!ipv6_addr_any(&match->mask.enc_dst_ip6)))
+		return -EOPNOTSUPP;
+#endif
+	if (WARN_ON_ONCE(match->mask.enc_ip_tos))
+		return -EOPNOTSUPP;
+	if (WARN_ON_ONCE(match->mask.enc_ip_ttl))
+		return -EOPNOTSUPP;
+	if (WARN_ON_ONCE(match->mask.enc_sport))
+		return -EOPNOTSUPP;
+	if (WARN_ON_ONCE(match->mask.enc_dport))
+		return -EOPNOTSUPP;
+	if (WARN_ON_ONCE(match->mask.enc_keyid))
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static int efx_mae_insert_lhs_outer_rule(struct efx_nic *efx,
+					 struct efx_tc_lhs_rule *rule, u32 prio)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_OUTER_RULE_INSERT_IN_LEN(MAE_ENC_FIELD_PAIRS_LEN));
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_OUTER_RULE_INSERT_OUT_LEN);
+	MCDI_DECLARE_STRUCT_PTR(match_crit);
+	const struct efx_tc_lhs_action *act;
+	size_t outlen;
+	int rc;
+
+	MCDI_SET_DWORD(inbuf, MAE_OUTER_RULE_INSERT_IN_PRIO, prio);
+	/* match */
+	match_crit = _MCDI_DWORD(inbuf, MAE_OUTER_RULE_INSERT_IN_FIELD_MATCH_CRITERIA);
+	rc = efx_mae_populate_lhs_match_criteria(match_crit, &rule->match);
+	if (rc)
+		return rc;
+
+	/* action */
+	act = &rule->lhs_act;
+	MCDI_SET_DWORD(inbuf, MAE_OUTER_RULE_INSERT_IN_ENCAP_TYPE,
+		       MAE_MCDI_ENCAP_TYPE_NONE);
+	/* We always inhibit CT lookup on TCP_INTERESTING_FLAGS, since the
+	 * SW path needs to process the packet to update the conntrack tables
+	 * on connection establishment (SYN) or termination (FIN, RST).
+	 */
+	MCDI_POPULATE_DWORD_6(inbuf, MAE_OUTER_RULE_INSERT_IN_LOOKUP_CONTROL,
+			      MAE_OUTER_RULE_INSERT_IN_DO_CT, !!act->zone,
+			      MAE_OUTER_RULE_INSERT_IN_CT_TCP_FLAGS_INHIBIT, 1,
+			      MAE_OUTER_RULE_INSERT_IN_CT_DOMAIN,
+			      act->zone ? act->zone->zone : 0,
+			      MAE_OUTER_RULE_INSERT_IN_CT_VNI_MODE,
+			      MAE_CT_VNI_MODE_ZERO,
+			      MAE_OUTER_RULE_INSERT_IN_DO_COUNT, !!act->count,
+			      MAE_OUTER_RULE_INSERT_IN_RECIRC_ID,
+			      act->rid ? act->rid->fw_id : 0);
+	if (act->count)
+		MCDI_SET_DWORD(inbuf, MAE_OUTER_RULE_INSERT_IN_COUNTER_ID,
+			       act->count->cnt->fw_id);
+	rc = efx_mcdi_rpc(efx, MC_CMD_MAE_OUTER_RULE_INSERT, inbuf,
+			  sizeof(inbuf), outbuf, sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < sizeof(outbuf))
+		return -EIO;
+	rule->fw_id = MCDI_DWORD(outbuf, MAE_OUTER_RULE_INSERT_OUT_OR_ID);
+	return 0;
+}
+
+int efx_mae_insert_lhs_rule(struct efx_nic *efx, struct efx_tc_lhs_rule *rule,
+			    u32 prio)
+{
+	return efx_mae_insert_lhs_outer_rule(efx, rule, prio);
+}
+
+static int efx_mae_remove_lhs_outer_rule(struct efx_nic *efx,
+					 struct efx_tc_lhs_rule *rule)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_OUTER_RULE_REMOVE_OUT_LEN(1));
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_OUTER_RULE_REMOVE_IN_LEN(1));
+	size_t outlen;
+	int rc;
+
+	MCDI_SET_DWORD(inbuf, MAE_OUTER_RULE_REMOVE_IN_OR_ID, rule->fw_id);
+	rc = efx_mcdi_rpc(efx, MC_CMD_MAE_OUTER_RULE_REMOVE, inbuf,
+			  sizeof(inbuf), outbuf, sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < sizeof(outbuf))
+		return -EIO;
+	/* FW freed a different ID than we asked for, should also never happen.
+	 * Warn because it means we've now got a different idea to the FW of
+	 * what encap_mds exist, which could cause mayhem later.
+	 */
+	if (WARN_ON(MCDI_DWORD(outbuf, MAE_OUTER_RULE_REMOVE_OUT_REMOVED_OR_ID) != rule->fw_id))
+		return -EIO;
+	/* We're probably about to free @rule, but let's just make sure its
+	 * fw_id is blatted so that it won't look valid if it leaks out.
+	 */
+	rule->fw_id = MC_CMD_MAE_OUTER_RULE_INSERT_OUT_OUTER_RULE_ID_NULL;
+	return 0;
+}
+
+int efx_mae_remove_lhs_rule(struct efx_nic *efx, struct efx_tc_lhs_rule *rule)
+{
+	return efx_mae_remove_lhs_outer_rule(efx, rule);
+}
+
 /* Populating is done by taking each byte of @value in turn and storing
  * it in the appropriate bits of @row.  @value must be big-endian; we
  * convert it to little-endianness as we go.
diff --git a/drivers/net/ethernet/sfc/mae.h b/drivers/net/ethernet/sfc/mae.h
index 24f29a4fc0e10..e88e80574f155 100644
--- a/drivers/net/ethernet/sfc/mae.h
+++ b/drivers/net/ethernet/sfc/mae.h
@@ -84,6 +84,9 @@ int efx_mae_get_caps(struct efx_nic *efx, struct mae_caps *caps);
 int efx_mae_match_check_caps(struct efx_nic *efx,
 			     const struct efx_tc_match_fields *mask,
 			     struct netlink_ext_ack *extack);
+int efx_mae_match_check_caps_lhs(struct efx_nic *efx,
+				 const struct efx_tc_match_fields *mask,
+				 struct netlink_ext_ack *extack);
 int efx_mae_check_encap_match_caps(struct efx_nic *efx, bool ipv6,
 				   u8 ip_tos_mask, __be16 udp_sport_mask,
 				   struct netlink_ext_ack *extack);
@@ -112,6 +115,9 @@ int efx_mae_register_encap_match(struct efx_nic *efx,
 				 struct efx_tc_encap_match *encap);
 int efx_mae_unregister_encap_match(struct efx_nic *efx,
 				   struct efx_tc_encap_match *encap);
+int efx_mae_insert_lhs_rule(struct efx_nic *efx, struct efx_tc_lhs_rule *rule,
+			    u32 prio);
+int efx_mae_remove_lhs_rule(struct efx_nic *efx, struct efx_tc_lhs_rule *rule);
 struct efx_tc_ct_entry; /* see tc_conntrack.h */
 int efx_mae_insert_ct(struct efx_nic *efx, struct efx_tc_ct_entry *conn);
 int efx_mae_remove_ct(struct efx_nic *efx, struct efx_tc_ct_entry *conn);
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index 700d0252aebdc..ea612c6198742 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -218,6 +218,12 @@ void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev);
 	BUILD_BUG_ON(_field ## _LEN != 1);				\
 	*(u8 *)MCDI_STRUCT_PTR(_buf, _field) = _value;			\
 	} while (0)
+#define MCDI_STRUCT_POPULATE_BYTE_1(_buf, _field, _name, _value) do {	\
+	efx_dword_t _temp;						\
+	EFX_POPULATE_DWORD_1(_temp, _name, _value);			\
+	MCDI_STRUCT_SET_BYTE(_buf, _field,				\
+			     EFX_DWORD_FIELD(_temp, EFX_BYTE_0));	\
+	} while (0)
 #define MCDI_BYTE(_buf, _field)						\
 	((void)BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 1),	\
 	 *MCDI_PTR(_buf, _field))
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index a9f4bfaacac31..2466572229589 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -12,6 +12,7 @@
 #include <net/pkt_cls.h>
 #include <net/vxlan.h>
 #include <net/geneve.h>
+#include <net/tc_act/tc_ct.h>
 #include "tc.h"
 #include "tc_bindings.h"
 #include "tc_encap_actions.h"
@@ -97,6 +98,12 @@ static const struct rhashtable_params efx_tc_match_action_ht_params = {
 	.head_offset	= offsetof(struct efx_tc_flow_rule, linkage),
 };
 
+static const struct rhashtable_params efx_tc_lhs_rule_ht_params = {
+	.key_len	= sizeof(unsigned long),
+	.key_offset	= offsetof(struct efx_tc_lhs_rule, cookie),
+	.head_offset	= offsetof(struct efx_tc_lhs_rule, linkage),
+};
+
 static const struct rhashtable_params efx_tc_recirc_ht_params = {
 	.key_len	= offsetof(struct efx_tc_recirc_id, linkage),
 	.key_offset	= 0,
@@ -736,6 +743,163 @@ static bool efx_tc_flower_action_order_ok(const struct efx_tc_action_set *act,
 	}
 }
 
+/**
+ * DOC: TC conntrack sequences
+ *
+ * The MAE hardware can handle at most two rounds of action rule matching,
+ * consequently we support conntrack through the notion of a "left-hand side
+ * rule".  This is a rule which typically contains only the actions "ct" and
+ * "goto chain N", and corresponds to one or more "right-hand side rules" in
+ * chain N, which typically match on +trk+est, and may perform ct(nat) actions.
+ * RHS rules go in the Action Rule table as normal but with a nonzero recirc_id
+ * (the hardware equivalent of chain_index), while LHS rules may go in either
+ * the Action Rule or the Outer Rule table, the latter being preferred for
+ * performance reasons, and set both DO_CT and a recirc_id in their response.
+ *
+ * Besides the RHS rules, there are often also similar rules matching on
+ * +trk+new which perform the ct(commit) action.  These are not offloaded.
+ */
+
+static bool efx_tc_rule_is_lhs_rule(struct flow_rule *fr,
+				    struct efx_tc_match *match)
+{
+	const struct flow_action_entry *fa;
+	int i;
+
+	flow_action_for_each(i, fa, &fr->action) {
+		switch (fa->id) {
+		case FLOW_ACTION_GOTO:
+			return true;
+		case FLOW_ACTION_CT:
+			/* If rule is -trk, or doesn't mention trk at all, then
+			 * a CT action implies a conntrack lookup (hence it's an
+			 * LHS rule).  If rule is +trk, then a CT action could
+			 * just be ct(nat) or even ct(commit) (though the latter
+			 * can't be offloaded).
+			 */
+			if (!match->mask.ct_state_trk || !match->value.ct_state_trk)
+				return true;
+			break;
+		default:
+			break;
+		}
+	}
+	return false;
+}
+
+static int efx_tc_flower_handle_lhs_actions(struct efx_nic *efx,
+					    struct flow_cls_offload *tc,
+					    struct flow_rule *fr,
+					    struct net_device *net_dev,
+					    struct efx_tc_lhs_rule *rule)
+
+{
+	struct netlink_ext_ack *extack = tc->common.extack;
+	struct efx_tc_lhs_action *act = &rule->lhs_act;
+	const struct flow_action_entry *fa;
+	bool pipe = true;
+	int i;
+
+	flow_action_for_each(i, fa, &fr->action) {
+		struct efx_tc_ct_zone *ct_zone;
+		struct efx_tc_recirc_id *rid;
+
+		if (!pipe) {
+			/* more actions after a non-pipe action */
+			NL_SET_ERR_MSG_MOD(extack, "Action follows non-pipe action");
+			return -EINVAL;
+		}
+		switch (fa->id) {
+		case FLOW_ACTION_GOTO:
+			if (!fa->chain_index) {
+				NL_SET_ERR_MSG_MOD(extack, "Can't goto chain 0, no looping in hw");
+				return -EOPNOTSUPP;
+			}
+			rid = efx_tc_get_recirc_id(efx, fa->chain_index,
+						   net_dev);
+			if (IS_ERR(rid)) {
+				NL_SET_ERR_MSG_MOD(extack, "Failed to allocate a hardware recirculation ID for this chain_index");
+				return PTR_ERR(rid);
+			}
+			act->rid = rid;
+			if (fa->hw_stats) {
+				struct efx_tc_counter_index *cnt;
+
+				if (!(fa->hw_stats & FLOW_ACTION_HW_STATS_DELAYED)) {
+					NL_SET_ERR_MSG_FMT_MOD(extack,
+							       "hw_stats_type %u not supported (only 'delayed')",
+							       fa->hw_stats);
+					return -EOPNOTSUPP;
+				}
+				cnt = efx_tc_flower_get_counter_index(efx, tc->cookie,
+								      EFX_TC_COUNTER_TYPE_OR);
+				if (IS_ERR(cnt)) {
+					NL_SET_ERR_MSG_MOD(extack, "Failed to obtain a counter");
+					return PTR_ERR(cnt);
+				}
+				WARN_ON(act->count); /* can't happen */
+				act->count = cnt;
+			}
+			pipe = false;
+			break;
+		case FLOW_ACTION_CT:
+			if (act->zone) {
+				NL_SET_ERR_MSG_MOD(extack, "Can't offload multiple ct actions");
+				return -EOPNOTSUPP;
+			}
+			if (fa->ct.action & (TCA_CT_ACT_COMMIT |
+					     TCA_CT_ACT_FORCE)) {
+				NL_SET_ERR_MSG_MOD(extack, "Can't offload ct commit/force");
+				return -EOPNOTSUPP;
+			}
+			if (fa->ct.action & TCA_CT_ACT_CLEAR) {
+				NL_SET_ERR_MSG_MOD(extack, "Can't clear ct in LHS rule");
+				return -EOPNOTSUPP;
+			}
+			if (fa->ct.action & (TCA_CT_ACT_NAT |
+					     TCA_CT_ACT_NAT_SRC |
+					     TCA_CT_ACT_NAT_DST)) {
+				NL_SET_ERR_MSG_MOD(extack, "Can't perform NAT in LHS rule - packet isn't conntracked yet");
+				return -EOPNOTSUPP;
+			}
+			if (fa->ct.action) {
+				NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled ct.action %u for LHS rule\n",
+						       fa->ct.action);
+				return -EOPNOTSUPP;
+			}
+			ct_zone = efx_tc_ct_register_zone(efx, fa->ct.zone,
+							  fa->ct.flow_table);
+			if (IS_ERR(ct_zone)) {
+				NL_SET_ERR_MSG_MOD(extack, "Failed to register for CT updates");
+				return PTR_ERR(ct_zone);
+			}
+			act->zone = ct_zone;
+			break;
+		default:
+			NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled action %u for LHS rule\n",
+					       fa->id);
+			return -EOPNOTSUPP;
+		}
+	}
+
+	if (pipe) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing goto chain in LHS rule");
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static void efx_tc_flower_release_lhs_actions(struct efx_nic *efx,
+					      struct efx_tc_lhs_action *act)
+{
+	if (act->rid)
+		efx_tc_put_recirc_id(efx, act->rid);
+	if (act->zone)
+		efx_tc_ct_unregister_zone(efx, act->zone);
+	if (act->count)
+		efx_tc_flower_put_counter_index(efx, act->count);
+}
+
 static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 					 struct net_device *net_dev,
 					 struct flow_cls_offload *tc)
@@ -1050,6 +1214,78 @@ release:
 	return rc;
 }
 
+static int efx_tc_flower_replace_lhs(struct efx_nic *efx,
+				     struct flow_cls_offload *tc,
+				     struct flow_rule *fr,
+				     struct efx_tc_match *match,
+				     struct efx_rep *efv,
+				     struct net_device *net_dev)
+{
+	struct netlink_ext_ack *extack = tc->common.extack;
+	struct efx_tc_lhs_rule *rule, *old;
+	int rc;
+
+	if (tc->common.chain_index) {
+		NL_SET_ERR_MSG_MOD(extack, "LHS rule only allowed in chain 0");
+		return -EOPNOTSUPP;
+	}
+
+	if (match->mask.ct_state_trk && match->value.ct_state_trk) {
+		NL_SET_ERR_MSG_MOD(extack, "LHS rule can never match +trk");
+		return -EOPNOTSUPP;
+	}
+	/* LHS rules are always -trk, so we don't need to match on that */
+	match->mask.ct_state_trk = 0;
+	match->value.ct_state_trk = 0;
+
+	rc = efx_mae_match_check_caps_lhs(efx, &match->mask, extack);
+	if (rc)
+		return rc;
+
+	rule = kzalloc(sizeof(*rule), GFP_USER);
+	if (!rule)
+		return -ENOMEM;
+	rule->cookie = tc->cookie;
+	old = rhashtable_lookup_get_insert_fast(&efx->tc->lhs_rule_ht,
+						&rule->linkage,
+						efx_tc_lhs_rule_ht_params);
+	if (old) {
+		netif_dbg(efx, drv, efx->net_dev,
+			  "Already offloaded rule (cookie %lx)\n", tc->cookie);
+		rc = -EEXIST;
+		NL_SET_ERR_MSG_MOD(extack, "Rule already offloaded");
+		goto release;
+	}
+
+	/* Parse actions */
+	/* See note in efx_tc_flower_replace() regarding passed net_dev
+	 * (used for efx_tc_get_recirc_id()).
+	 */
+	rc = efx_tc_flower_handle_lhs_actions(efx, tc, fr, efx->net_dev, rule);
+	if (rc)
+		goto release;
+
+	rule->match = *match;
+
+	rc = efx_mae_insert_lhs_rule(efx, rule, EFX_TC_PRIO_TC);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to insert rule in hw");
+		goto release;
+	}
+	netif_dbg(efx, drv, efx->net_dev,
+		  "Successfully parsed lhs rule (cookie %lx)\n",
+		  tc->cookie);
+	return 0;
+
+release:
+	efx_tc_flower_release_lhs_actions(efx, &rule->lhs_act);
+	if (!old)
+		rhashtable_remove_fast(&efx->tc->lhs_rule_ht, &rule->linkage,
+				       efx_tc_lhs_rule_ht_params);
+	kfree(rule);
+	return rc;
+}
+
 static int efx_tc_flower_replace(struct efx_nic *efx,
 				 struct net_device *net_dev,
 				 struct flow_cls_offload *tc,
@@ -1105,6 +1341,10 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 		return -EOPNOTSUPP;
 	}
 
+	if (efx_tc_rule_is_lhs_rule(fr, &match))
+		return efx_tc_flower_replace_lhs(efx, tc, fr, &match, efv,
+						 net_dev);
+
 	/* chain_index 0 is always recirc_id 0 (and does not appear in recirc_ht).
 	 * Conveniently, match.rid == NULL and match.value.recirc_id == 0 owing
 	 * to the initial memset(), so we don't need to do anything in that case.
@@ -1512,8 +1752,26 @@ static int efx_tc_flower_destroy(struct efx_nic *efx,
 				 struct flow_cls_offload *tc)
 {
 	struct netlink_ext_ack *extack = tc->common.extack;
+	struct efx_tc_lhs_rule *lhs_rule;
 	struct efx_tc_flow_rule *rule;
 
+	lhs_rule = rhashtable_lookup_fast(&efx->tc->lhs_rule_ht, &tc->cookie,
+					  efx_tc_lhs_rule_ht_params);
+	if (lhs_rule) {
+		/* Remove it from HW */
+		efx_mae_remove_lhs_rule(efx, lhs_rule);
+		/* Delete it from SW */
+		efx_tc_flower_release_lhs_actions(efx, &lhs_rule->lhs_act);
+		rhashtable_remove_fast(&efx->tc->lhs_rule_ht, &lhs_rule->linkage,
+				       efx_tc_lhs_rule_ht_params);
+		if (lhs_rule->match.encap)
+			efx_tc_flower_release_encap_match(efx, lhs_rule->match.encap);
+		netif_dbg(efx, drv, efx->net_dev, "Removed (lhs) filter %lx\n",
+			  lhs_rule->cookie);
+		kfree(lhs_rule);
+		return 0;
+	}
+
 	rule = rhashtable_lookup_fast(&efx->tc->match_action_ht, &tc->cookie,
 				      efx_tc_match_action_ht_params);
 	if (!rule) {
@@ -1880,6 +2138,24 @@ static void efx_tc_recirc_free(void *ptr, void *arg)
 	kfree(rid);
 }
 
+static void efx_tc_lhs_free(void *ptr, void *arg)
+{
+	struct efx_tc_lhs_rule *rule = ptr;
+	struct efx_nic *efx = arg;
+
+	netif_err(efx, drv, efx->net_dev,
+		  "tc lhs_rule %lx still present at teardown, removing\n",
+		  rule->cookie);
+
+	if (rule->lhs_act.zone)
+		efx_tc_ct_unregister_zone(efx, rule->lhs_act.zone);
+	if (rule->lhs_act.count)
+		efx_tc_flower_put_counter_index(efx, rule->lhs_act.count);
+	efx_mae_remove_lhs_rule(efx, rule);
+
+	kfree(rule);
+}
+
 static void efx_tc_flow_free(void *ptr, void *arg)
 {
 	struct efx_tc_flow_rule *rule = ptr;
@@ -1926,6 +2202,9 @@ int efx_init_struct_tc(struct efx_nic *efx)
 	rc = rhashtable_init(&efx->tc->match_action_ht, &efx_tc_match_action_ht_params);
 	if (rc < 0)
 		goto fail_match_action_ht;
+	rc = rhashtable_init(&efx->tc->lhs_rule_ht, &efx_tc_lhs_rule_ht_params);
+	if (rc < 0)
+		goto fail_lhs_rule_ht;
 	rc = efx_tc_init_conntrack(efx);
 	if (rc < 0)
 		goto fail_conntrack;
@@ -1948,6 +2227,8 @@ int efx_init_struct_tc(struct efx_nic *efx)
 fail_recirc_ht:
 	efx_tc_destroy_conntrack(efx);
 fail_conntrack:
+	rhashtable_destroy(&efx->tc->lhs_rule_ht);
+fail_lhs_rule_ht:
 	rhashtable_destroy(&efx->tc->match_action_ht);
 fail_match_action_ht:
 	rhashtable_destroy(&efx->tc->encap_match_ht);
@@ -1978,6 +2259,7 @@ void efx_fini_struct_tc(struct efx_nic *efx)
 			     MC_CMD_MAE_ACTION_SET_LIST_ALLOC_OUT_ACTION_SET_LIST_ID_NULL);
 	EFX_WARN_ON_PARANOID(efx->tc->facts.reps.fw_id !=
 			     MC_CMD_MAE_ACTION_SET_LIST_ALLOC_OUT_ACTION_SET_LIST_ID_NULL);
+	rhashtable_free_and_destroy(&efx->tc->lhs_rule_ht, efx_tc_lhs_free, efx);
 	rhashtable_free_and_destroy(&efx->tc->match_action_ht, efx_tc_flow_free,
 				    efx);
 	rhashtable_free_and_destroy(&efx->tc->encap_match_ht,
diff --git a/drivers/net/ethernet/sfc/tc.h b/drivers/net/ethernet/sfc/tc.h
index ce8e30743a3a9..40d2c803fca82 100644
--- a/drivers/net/ethernet/sfc/tc.h
+++ b/drivers/net/ethernet/sfc/tc.h
@@ -140,6 +140,12 @@ struct efx_tc_action_set_list {
 	u32 fw_id;
 };
 
+struct efx_tc_lhs_action {
+	struct efx_tc_recirc_id *rid;
+	struct efx_tc_ct_zone *zone;
+	struct efx_tc_counter_index *count;
+};
+
 struct efx_tc_flow_rule {
 	unsigned long cookie;
 	struct rhash_head linkage;
@@ -149,6 +155,14 @@ struct efx_tc_flow_rule {
 	u32 fw_id;
 };
 
+struct efx_tc_lhs_rule {
+	unsigned long cookie;
+	struct efx_tc_match match;
+	struct efx_tc_lhs_action lhs_act;
+	struct rhash_head linkage;
+	u32 fw_id;
+};
+
 enum efx_tc_rule_prios {
 	EFX_TC_PRIO_TC, /* Rule inserted by TC */
 	EFX_TC_PRIO_DFLT, /* Default switch rule; one of efx_tc_default_rules */
@@ -208,6 +222,7 @@ struct efx_tc_table_ct { /* TABLE_ID_CONNTRACK_TABLE */
  * @encap_ht: Hashtable of TC encap actions
  * @encap_match_ht: Hashtable of TC encap matches
  * @match_action_ht: Hashtable of TC match-action rules
+ * @lhs_rule_ht: Hashtable of TC left-hand (act ct & goto chain) rules
  * @ct_zone_ht: Hashtable of TC conntrack flowtable bindings
  * @ct_ht: Hashtable of TC conntrack flow entries
  * @neigh_ht: Hashtable of neighbour watches (&struct efx_neigh_binder)
@@ -244,6 +259,7 @@ struct efx_tc_state {
 	struct rhashtable encap_ht;
 	struct rhashtable encap_match_ht;
 	struct rhashtable match_action_ht;
+	struct rhashtable lhs_rule_ht;
 	struct rhashtable ct_zone_ht;
 	struct rhashtable ct_ht;
 	struct rhashtable neigh_ht;
-- 
GitLab


From b9b05381e5d76a5ad05aedf5357c585d4a1f78cd Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Sat, 5 Aug 2023 15:45:36 +0100
Subject: [PATCH 1012/1806] net: dsa: mt7530: improve and relax PHY driver
 dependency

Different MT7530 variants require different PHY drivers.
Use 'imply' instead of 'select' to relax the dependency on the PHY
driver, and choose the appropriate driver.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 3ed5391bb18d6..f8c1d73b251d0 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -37,7 +37,6 @@ config NET_DSA_LANTIQ_GSWIP
 config NET_DSA_MT7530
 	tristate "MediaTek MT7530 and MT7531 Ethernet switch support"
 	select NET_DSA_TAG_MTK
-	select MEDIATEK_GE_PHY
 	imply NET_DSA_MT7530_MDIO
 	imply NET_DSA_MT7530_MMIO
 	help
@@ -49,6 +48,7 @@ config NET_DSA_MT7530
 config NET_DSA_MT7530_MDIO
 	tristate "MediaTek MT7530 MDIO interface driver"
 	depends on NET_DSA_MT7530
+	imply MEDIATEK_GE_PHY
 	select PCS_MTK_LYNXI
 	help
 	  This enables support for the MediaTek MT7530 and MT7531 switch
@@ -60,6 +60,7 @@ config NET_DSA_MT7530_MMIO
 	tristate "MediaTek MT7530 MMIO interface driver"
 	depends on NET_DSA_MT7530
 	depends on HAS_IOMEM
+	imply MEDIATEK_GE_SOC_PHY
 	help
 	  This enables support for the built-in Ethernet switch found
 	  in the MediaTek MT7988 SoC.
-- 
GitLab


From ca76b386d46fdcdf2d8829f008744e57f819a581 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 7 Aug 2023 22:29:26 +0800
Subject: [PATCH 1013/1806] tipc: Remove unused declaration
 tipc_link_build_bc_sync_msg()

Commit 526669866140 ("tipc: let broadcast packet reception use new link receive function")
declared but never implemented this.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230807142926.45752-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/link.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/tipc/link.h b/net/tipc/link.h
index a16f401fdabda..d80f5649b3953 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -148,8 +148,6 @@ int tipc_link_bc_ack_rcv(struct tipc_link *l, u16 acked, u16 gap,
 			 struct tipc_gap_ack_blks *ga,
 			 struct sk_buff_head *xmitq,
 			 struct sk_buff_head *retrq);
-void tipc_link_build_bc_sync_msg(struct tipc_link *l,
-				 struct sk_buff_head *xmitq);
 void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr);
 int tipc_link_bc_sync_rcv(struct tipc_link *l,   struct tipc_msg *hdr,
 			  struct sk_buff_head *xmitq);
-- 
GitLab


From 09c80167dbec3c742ed0d0218eef13be648b47ed Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 8 Aug 2023 09:47:02 +0800
Subject: [PATCH 1014/1806] bcm63xx_enet: Remove redundant initialization owner

The platform_register_drivers() will set "THIS_MODULE" to driver.owner when
register a platform_driver driver, so it is redundant initialization to set
driver.owner in the statement. Remove it for clean code.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://lore.kernel.org/r/20230808014702.2712699-1-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bcm63xx_enet.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 2cf96892e5650..a741070f1f9a0 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1940,7 +1940,6 @@ static struct platform_driver bcm63xx_enet_driver = {
 	.remove	= bcm_enet_remove,
 	.driver	= {
 		.name	= "bcm63xx_enet",
-		.owner  = THIS_MODULE,
 	},
 };
 
@@ -2761,7 +2760,6 @@ static struct platform_driver bcm63xx_enetsw_driver = {
 	.remove	= bcm_enetsw_remove,
 	.driver	= {
 		.name	= "bcm63xx_enetsw",
-		.owner  = THIS_MODULE,
 	},
 };
 
@@ -2791,7 +2789,6 @@ struct platform_driver bcm63xx_enet_shared_driver = {
 	.probe	= bcm_enet_shared_probe,
 	.driver	= {
 		.name	= "bcm63xx_enet_shared",
-		.owner  = THIS_MODULE,
 	},
 };
 
-- 
GitLab


From d8c21ef7b2b147a7e0d0497da120a3bc73be7fbe Mon Sep 17 00:00:00 2001
From: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Date: Tue, 8 Aug 2023 10:49:31 +0800
Subject: [PATCH 1015/1806] net: txgbe: Use pci_dev_id() to simplify the code

PCI core API pci_dev_id() can be used to get the BDF number for a pci
device. We don't need to compose it manually. Use pci_dev_id() to
simplify the code a little bit.

Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Reviewed-by: Yang Yingliang <yangyingliang@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230808024931.147048-1-wangxiongfeng2@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 8779645a54be4..819d1db346433 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -26,7 +26,7 @@ static int txgbe_swnodes_register(struct txgbe *txgbe)
 	struct software_node *swnodes;
 	u32 id;
 
-	id = (pdev->bus->number << 8) | pdev->devfn;
+	id = pci_dev_id(pdev);
 
 	snprintf(nodes->gpio_name, sizeof(nodes->gpio_name), "txgbe_gpio-%x", id);
 	snprintf(nodes->i2c_name, sizeof(nodes->i2c_name), "txgbe_i2c-%x", id);
@@ -140,7 +140,7 @@ static int txgbe_mdio_pcs_init(struct txgbe *txgbe)
 	mii_bus->phy_mask = ~0;
 	mii_bus->priv = wx;
 	snprintf(mii_bus->id, MII_BUS_ID_SIZE, "txgbe_pcs-%x",
-		 (pdev->bus->number << 8) | pdev->devfn);
+		 pci_dev_id(pdev));
 
 	ret = devm_mdiobus_register(&pdev->dev, mii_bus);
 	if (ret)
@@ -459,7 +459,7 @@ static int txgbe_gpio_init(struct txgbe *txgbe)
 		return -ENOMEM;
 
 	gc->label = devm_kasprintf(dev, GFP_KERNEL, "txgbe_gpio-%x",
-				   (wx->pdev->bus->number << 8) | wx->pdev->devfn);
+				   pci_dev_id(wx->pdev));
 	if (!gc->label)
 		return -ENOMEM;
 
@@ -503,7 +503,7 @@ static int txgbe_clock_register(struct txgbe *txgbe)
 	struct clk *clk;
 
 	snprintf(clk_name, sizeof(clk_name), "i2c_designware.%d",
-		 (pdev->bus->number << 8) | pdev->devfn);
+		 pci_dev_id(pdev));
 
 	clk = clk_register_fixed_rate(NULL, clk_name, NULL, 0, 156250000);
 	if (IS_ERR(clk))
@@ -566,7 +566,7 @@ static int txgbe_i2c_register(struct txgbe *txgbe)
 	info.parent = &pdev->dev;
 	info.fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_I2C]);
 	info.name = "i2c_designware";
-	info.id = (pdev->bus->number << 8) | pdev->devfn;
+	info.id = pci_dev_id(pdev);
 
 	info.res = &DEFINE_RES_IRQ(pdev->irq);
 	info.num_res = 1;
@@ -588,7 +588,7 @@ static int txgbe_sfp_register(struct txgbe *txgbe)
 	info.parent = &pdev->dev;
 	info.fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_SFP]);
 	info.name = "sfp";
-	info.id = (pdev->bus->number << 8) | pdev->devfn;
+	info.id = pci_dev_id(pdev);
 	sfp_dev = platform_device_register_full(&info);
 	if (IS_ERR(sfp_dev))
 		return PTR_ERR(sfp_dev);
-- 
GitLab


From 2c0e9f3806c46976e9d34130dcb4550ac114293a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Tue, 8 Aug 2023 11:03:44 +0200
Subject: [PATCH 1016/1806] tools: ynl-gen: avoid rendering empty validate
 field

When dont-validate flags are filtered out for do/dump op, the list may
be empty. In that case, avoid rendering the validate field.

Fixes: fa8ba3502ade ("ynl-gen-c.py: render netlink policies static for split ops")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230808090344.1368874-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index e64311331726b..6b9d9380a6ab4 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -2000,9 +2000,10 @@ def print_kernel_op_table(family, cw):
                             continue
                         dont_validate.append(x)
 
-                    members.append(('validate',
-                                    ' | '.join([c_upper('genl-dont-validate-' + x)
-                                                for x in dont_validate])), )
+                    if dont_validate:
+                        members.append(('validate',
+                                        ' | '.join([c_upper('genl-dont-validate-' + x)
+                                                    for x in dont_validate])), )
                 name = c_lower(f"{family.name}-nl-{op_name}-{op_mode}it")
                 if 'pre' in op[op_mode]:
                     members.append((cb_names[op_mode]['pre'], c_lower(op[op_mode]['pre'])))
-- 
GitLab


From 832140804e3b3ad19d73adebd25f69ed98778c58 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Tue, 8 Aug 2023 10:20:20 +0200
Subject: [PATCH 1017/1806] devlink: clear flag on port register error path

When xarray insertion fails, clear the flag.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230808082020.1363497-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/leftover.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 3bf42f5335ed4..e7900d9fa205a 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -6829,8 +6829,10 @@ int devl_port_register_with_ops(struct devlink *devlink,
 	spin_lock_init(&devlink_port->type_lock);
 	INIT_LIST_HEAD(&devlink_port->reporter_list);
 	err = xa_insert(&devlink->ports, port_index, devlink_port, GFP_KERNEL);
-	if (err)
+	if (err) {
+		devlink_port->registered = false;
 		return err;
+	}
 
 	INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn);
 	devlink_port_type_warn_schedule(devlink_port);
-- 
GitLab


From 145622771d22a7ad5061278eb6fb16396c29d308 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 8 Aug 2023 12:12:16 +0100
Subject: [PATCH 1018/1806] net: dsa: mark parsed interface mode for legacy
 switch drivers

If we successfully parsed an interface mode with a legacy switch
driver, populate that mode into phylink's supported interfaces rather
than defaulting to the internal and gmii interfaces.

This hasn't caused an issue so far, because when the interface doesn't
match a supported one, phylink_validate() doesn't clear the supported
mask, but instead returns -EINVAL. phylink_parse_fixedlink() doesn't
check this return value, and merely relies on the supported ethtool
link modes mask being cleared. Therefore, the fixed link settings end
up being allowed despite validation failing.

Before this causes a problem, arrange for DSA to more accurately
populate phylink's supported interfaces mask so validation can
correctly succeed.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://lore.kernel.org/r/E1qTKdM-003Cpx-Eh@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/dsa/port.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/dsa/port.c b/net/dsa/port.c
index 24015e11255f0..37ab238e83042 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -1690,10 +1690,14 @@ int dsa_port_phylink_create(struct dsa_port *dp)
 		ds->ops->phylink_get_caps(ds, dp->index, &dp->pl_config);
 	} else {
 		/* For legacy drivers */
-		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
-			  dp->pl_config.supported_interfaces);
-		__set_bit(PHY_INTERFACE_MODE_GMII,
-			  dp->pl_config.supported_interfaces);
+		if (mode != PHY_INTERFACE_MODE_NA) {
+			__set_bit(mode, dp->pl_config.supported_interfaces);
+		} else {
+			__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+				  dp->pl_config.supported_interfaces);
+			__set_bit(PHY_INTERFACE_MODE_GMII,
+				  dp->pl_config.supported_interfaces);
+		}
 	}
 
 	pl = phylink_create(&dp->pl_config, of_fwnode_handle(dp->dn),
-- 
GitLab


From 90ed8d3dc34bb36b5fb59671924d1ac35f01e75d Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 8 Aug 2023 22:46:10 +0800
Subject: [PATCH 1019/1806] net: phy: Remove two unused function declarations

Commit 1e2dc14509fd ("net: ethtool: Add helpers for reporting test results")
declared but never implemented these function.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230808144610.19096-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/phy.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/include/linux/phy.h b/include/linux/phy.h
index ba08b0e602798..b963ce22e7c75 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1732,10 +1732,6 @@ int phy_start_cable_test_tdr(struct phy_device *phydev,
 }
 #endif
 
-int phy_cable_test_result(struct phy_device *phydev, u8 pair, u16 result);
-int phy_cable_test_fault_length(struct phy_device *phydev, u8 pair,
-				u16 cm);
-
 static inline void phy_device_reset(struct phy_device *phydev, int value)
 {
 	mdio_device_reset(&phydev->mdio, value);
-- 
GitLab


From 98261be155f8de38f11b6542d4a8935e5532687b Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 8 Aug 2023 22:52:49 +0800
Subject: [PATCH 1020/1806] mlxbf_gige: Remove two unused function declarations

Commit f92e1869d74e ("Add Mellanox BlueField Gigabit Ethernet driver")
declared but never implemented these.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Asmaa Mnebhi <asmaa@nvidia.com>
Link: https://lore.kernel.org/r/20230808145249.41596-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
index a453b9cd90330..bc94e75a7aebd 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
@@ -175,9 +175,6 @@ enum mlxbf_gige_res {
 int mlxbf_gige_mdio_probe(struct platform_device *pdev,
 			  struct mlxbf_gige *priv);
 void mlxbf_gige_mdio_remove(struct mlxbf_gige *priv);
-irqreturn_t mlxbf_gige_mdio_handle_phy_interrupt(int irq, void *dev_id);
-void mlxbf_gige_mdio_enable_phy_int(struct mlxbf_gige *priv);
-
 void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv,
 				  unsigned int index, u64 dmac);
 void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv,
-- 
GitLab


From a76728719c85eaa8440c353490c639655d60d28f Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 8 Aug 2023 22:59:55 +0800
Subject: [PATCH 1021/1806] net: switchdev: Remove unused declaration
 switchdev_port_fwd_mark_set()

Commit 6bc506b4fb06 ("bridge: switchdev: Add forward mark support for stacked devices")
removed the implementation but leave declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/20230808145955.2176-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/switchdev.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 0294cfec9c37c..a43062d4c734b 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -326,10 +326,6 @@ int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev,
 				      struct switchdev_notifier_info *info,
 				      struct netlink_ext_ack *extack);
 
-void switchdev_port_fwd_mark_set(struct net_device *dev,
-				 struct net_device *group_dev,
-				 bool joining);
-
 int switchdev_handle_fdb_event_to_device(struct net_device *dev, unsigned long event,
 		const struct switchdev_notifier_fdb_info *fdb_info,
 		bool (*check_cb)(const struct net_device *dev),
-- 
GitLab


From cd3112ebbaf44b13993569d37acc12c02fffb1b3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 8 Aug 2023 13:09:07 -0700
Subject: [PATCH 1022/1806] tools: ynl-gen: add missing empty line between
 policies

We're missing empty line between policies.
DPLL will need this.

Tested-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://lore.kernel.org/r/20230808200907.1290647-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 6b9d9380a6ab4..5f39d24906551 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -1871,6 +1871,7 @@ def print_req_policy(cw, struct, ri=None):
     for _, arg in struct.member_list():
         arg.attr_policy(cw)
     cw.p("};")
+    cw.nl()
 
 
 def kernel_can_gen_family_struct(family):
-- 
GitLab


From 99ecd6d065270c0447e33b7a14acf990fe6a2668 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Tue, 8 Aug 2023 21:35:28 +0800
Subject: [PATCH 1023/1806] mlxsw: spectrum_switchdev: Use is_zero_ether_addr()
 instead of ether_addr_equal()

Use is_zero_ether_addr() instead of ether_addr_equal()
to check if the ethernet address is all zeros.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://lore.kernel.org/r/20230808133528.4083501-1-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 5376d4af5f912..efacb057d1d4f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -3549,7 +3549,6 @@ mlxsw_sp_switchdev_vxlan_fdb_add(struct mlxsw_sp *mlxsw_sp,
 	struct switchdev_notifier_vxlan_fdb_info *vxlan_fdb_info;
 	struct mlxsw_sp_bridge_device *bridge_device;
 	struct net_device *dev = switchdev_work->dev;
-	u8 all_zeros_mac[ETH_ALEN] = { 0 };
 	enum mlxsw_sp_l3proto proto;
 	union mlxsw_sp_l3addr addr;
 	struct net_device *br_dev;
@@ -3571,7 +3570,7 @@ mlxsw_sp_switchdev_vxlan_fdb_add(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_switchdev_vxlan_addr_convert(&vxlan_fdb_info->remote_ip,
 					      &proto, &addr);
 
-	if (ether_addr_equal(vxlan_fdb_info->eth_addr, all_zeros_mac)) {
+	if (is_zero_ether_addr(vxlan_fdb_info->eth_addr)) {
 		err = mlxsw_sp_nve_flood_ip_add(mlxsw_sp, fid, proto, &addr);
 		if (err) {
 			mlxsw_sp_fid_put(fid);
@@ -3623,7 +3622,6 @@ mlxsw_sp_switchdev_vxlan_fdb_del(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_bridge_device *bridge_device;
 	struct net_device *dev = switchdev_work->dev;
 	struct net_device *br_dev = netdev_master_upper_dev_get(dev);
-	u8 all_zeros_mac[ETH_ALEN] = { 0 };
 	enum mlxsw_sp_l3proto proto;
 	union mlxsw_sp_l3addr addr;
 	struct mlxsw_sp_fid *fid;
@@ -3644,7 +3642,7 @@ mlxsw_sp_switchdev_vxlan_fdb_del(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_switchdev_vxlan_addr_convert(&vxlan_fdb_info->remote_ip,
 					      &proto, &addr);
 
-	if (ether_addr_equal(vxlan_fdb_info->eth_addr, all_zeros_mac)) {
+	if (is_zero_ether_addr(vxlan_fdb_info->eth_addr)) {
 		mlxsw_sp_nve_flood_ip_del(mlxsw_sp, fid, proto, &addr);
 		mlxsw_sp_fid_put(fid);
 		return;
-- 
GitLab


From b77049f04ed16cb0ab89b1cca689cd16a3071fd2 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 8 Aug 2023 19:38:49 +0800
Subject: [PATCH 1024/1806] ethernet: s2io: Use ether_addr_to_u64() to convert
 ethernet address

Use ether_addr_to_u64() to convert an Ethernet address into a u64 value,
instead of directly calculating, as this is exactly what
this function does.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230808113849.4033657-1-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/neterion/s2io.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 700c05fb05b97..61d8bfd12d5fd 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -5091,13 +5091,10 @@ static void do_s2io_restore_unicast_mc(struct s2io_nic *sp)
 static int do_s2io_add_mc(struct s2io_nic *sp, u8 *addr)
 {
 	int i;
-	u64 mac_addr = 0;
+	u64 mac_addr;
 	struct config_param *config = &sp->config;
 
-	for (i = 0; i < ETH_ALEN; i++) {
-		mac_addr <<= 8;
-		mac_addr |= addr[i];
-	}
+	mac_addr = ether_addr_to_u64(addr);
 	if ((0ULL == mac_addr) || (mac_addr == S2IO_DISABLE_MAC_ENTRY))
 		return SUCCESS;
 
@@ -5220,7 +5217,7 @@ static int s2io_set_mac_addr(struct net_device *dev, void *p)
 static int do_s2io_prog_unicast(struct net_device *dev, const u8 *addr)
 {
 	struct s2io_nic *sp = netdev_priv(dev);
-	register u64 mac_addr = 0, perm_addr = 0;
+	register u64 mac_addr, perm_addr;
 	int i;
 	u64 tmp64;
 	struct config_param *config = &sp->config;
@@ -5230,12 +5227,8 @@ static int do_s2io_prog_unicast(struct net_device *dev, const u8 *addr)
 	 * change on the device address registered with the OS. It will be
 	 * at offset 0.
 	 */
-	for (i = 0; i < ETH_ALEN; i++) {
-		mac_addr <<= 8;
-		mac_addr |= addr[i];
-		perm_addr <<= 8;
-		perm_addr |= sp->def_mac_addr[0].mac_addr[i];
-	}
+	mac_addr = ether_addr_to_u64(addr);
+	perm_addr = ether_addr_to_u64(sp->def_mac_addr[0].mac_addr);
 
 	/* check if the dev_addr is different than perm_addr */
 	if (mac_addr == perm_addr)
-- 
GitLab


From a76ca8afd45af103fc61217eebe90cae7c02cf6c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Tue, 8 Aug 2023 15:18:15 +0200
Subject: [PATCH 1025/1806] mlxsw: Set port STP state on bridge enslavement

When the first port joins a LAG that already has a bridge upper, an
instance of struct mlxsw_sp_bridge_port is created for the LAG to keep
track of it as a bridge port. The bridge_port's STP state is initialized to
BR_STATE_DISABLED. This made sense previously, because mlxsw would only
ever allow a port to join a LAG if the LAG had no uppers. Thus if a
bridge_port was instantiated, it must have been because the LAG as such is
joining a bridge, and the STP state is correspondingly disabled.

However as of commit 2c5ffe8d7226 ("mlxsw: spectrum: Permit enslavement to
netdevices with uppers"), mlxsw allows a port to join a LAG that is already
a member of a bridge. The STP state may be different than disabled in that
case. Initialize it properly by querying the actual state.

This bug may cause an issue as traffic on ports attached to a bridged LAG
gets dropped on ingress with discard_ingress_general counter bumped.

Fixes: c6514f3627a0 ("Merge branch 'mlxsw-enslavement'")
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/39f4a5781050866b4132f350d7d8cf7ab23ea070.1691498735.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index efacb057d1d4f..3662b9da54890 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -490,7 +490,7 @@ mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device,
 		bridge_port->system_port = mlxsw_sp_port->local_port;
 	bridge_port->dev = brport_dev;
 	bridge_port->bridge_device = bridge_device;
-	bridge_port->stp_state = BR_STATE_DISABLED;
+	bridge_port->stp_state = br_port_get_stp_state(brport_dev);
 	bridge_port->flags = BR_LEARNING | BR_FLOOD | BR_LEARNING_SYNC |
 			     BR_MCAST_FLOOD;
 	INIT_LIST_HEAD(&bridge_port->vlans_list);
-- 
GitLab


From aae5bb8d18d8ca00d658720710a490eebaf9087d Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Tue, 8 Aug 2023 15:18:16 +0200
Subject: [PATCH 1026/1806] selftests: mlxsw: router_bridge_lag: Add a new
 selftest

Add a selftest to verify enslavement to a LAG with upper after fresh
devlink reload.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/373a7754daa4dac32759a45095f47b08a2a869c8.1691498735.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../drivers/net/mlxsw/router_bridge_lag.sh    | 50 +++++++++++++++++++
 1 file changed, 50 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/router_bridge_lag.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_bridge_lag.sh b/tools/testing/selftests/drivers/net/mlxsw/router_bridge_lag.sh
new file mode 100755
index 0000000000000..6ce317cfaf9bf
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/router_bridge_lag.sh
@@ -0,0 +1,50 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test enslavement to LAG with a clean slate.
+# See $lib_dir/router_bridge_lag.sh for further details.
+
+ALL_TESTS="
+	config_devlink_reload
+	config_enslave_h1
+	config_enslave_h2
+	config_enslave_h3
+	config_enslave_h4
+	config_enslave_swp1
+	config_enslave_swp2
+	config_enslave_swp3
+	config_enslave_swp4
+	config_wait
+	ping_ipv4
+	ping_ipv6
+"
+
+config_devlink_reload()
+{
+	log_info "Devlink reload"
+	devlink_reload
+}
+
+config_enslave_h1()
+{
+	config_enslave $h1 lag1
+}
+
+config_enslave_h2()
+{
+	config_enslave $h2 lag4
+}
+
+config_enslave_h3()
+{
+	config_enslave $h3 lag4
+}
+
+config_enslave_h4()
+{
+	config_enslave $h4 lag1
+}
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+EXTRA_SOURCE="source $lib_dir/devlink_lib.sh"
+source $lib_dir/router_bridge_lag.sh
-- 
GitLab


From 7d0bc2602308ec0a183241914b0646d99d0fb541 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 8 Aug 2023 19:45:02 +0800
Subject: [PATCH 1027/1806] octeontx2-af: Remove redundant functions mac2u64()
 and cfg2mac()

The mac2u64() is used to convert an Ethernet MAC address into a u64 value,
as this is exactly what ether_addr_to_u64() does. Similarly, the cfg2mac()
is also the case. Use ether_addr_to_u64() and u64_to_ether_addr() instead
of these two.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Acked-by: Geethasowjanya Akula <gakula@marvell.com>
Link: https://lore.kernel.org/r/20230808114504.4036008-2-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/marvell/octeontx2/af/cgx.c   | 26 +++----------------
 1 file changed, 4 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 592037f4e55b6..988383e20bb8a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -223,24 +223,6 @@ int cgx_get_link_info(void *cgxd, int lmac_id,
 	return 0;
 }
 
-static u64 mac2u64 (u8 *mac_addr)
-{
-	u64 mac = 0;
-	int index;
-
-	for (index = ETH_ALEN - 1; index >= 0; index--)
-		mac |= ((u64)*mac_addr++) << (8 * index);
-	return mac;
-}
-
-static void cfg2mac(u64 cfg, u8 *mac_addr)
-{
-	int i, index = 0;
-
-	for (i = ETH_ALEN - 1; i >= 0; i--, index++)
-		mac_addr[i] = (cfg >> (8 * index)) & 0xFF;
-}
-
 int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr)
 {
 	struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
@@ -255,7 +237,7 @@ int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr)
 	/* copy 6bytes from macaddr */
 	/* memcpy(&cfg, mac_addr, 6); */
 
-	cfg = mac2u64 (mac_addr);
+	cfg = ether_addr_to_u64(mac_addr);
 
 	id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
 
@@ -322,7 +304,7 @@ int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr)
 
 	index = id * lmac->mac_to_index_bmap.max + idx;
 
-	cfg = mac2u64 (mac_addr);
+	cfg = ether_addr_to_u64(mac_addr);
 	cfg |= CGX_DMAC_CAM_ADDR_ENABLE;
 	cfg |= ((u64)lmac_id << 49);
 	cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg);
@@ -405,7 +387,7 @@ int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index)
 
 	cfg = cgx_read(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)));
 	cfg &= ~CGX_RX_DMAC_ADR_MASK;
-	cfg |= mac2u64 (mac_addr);
+	cfg |= ether_addr_to_u64(mac_addr);
 
 	cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg);
 	return 0;
@@ -441,7 +423,7 @@ int cgx_lmac_addr_del(u8 cgx_id, u8 lmac_id, u8 index)
 	/* Read MAC address to check whether it is ucast or mcast */
 	cfg = cgx_read(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)));
 
-	cfg2mac(cfg, mac);
+	u64_to_ether_addr(cfg, mac);
 	if (is_multicast_ether_addr(mac))
 		lmac->mcast_filters_count--;
 
-- 
GitLab


From e62c7adfd4acc394c448870ba63d4315e7a662f6 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 8 Aug 2023 19:45:03 +0800
Subject: [PATCH 1028/1806] octeontx2-af: Use u64_to_ether_addr() to convert
 ethernet address

Use u64_to_ether_addr() to convert a u64 value to an Ethernet MAC address,
instead of directly calculating, as this is exactly what this
function does.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Acked-by: Geethasowjanya Akula <gakula@marvell.com>
Link: https://lore.kernel.org/r/20230808114504.4036008-3-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 095b2cc4a6999..b3f766b970ca8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -686,7 +686,7 @@ int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu,
 {
 	int pf = rvu_get_pf(req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
-	int rc = 0, i;
+	int rc = 0;
 	u64 cfg;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -697,8 +697,7 @@ int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu,
 	rsp->hdr.rc = rc;
 	cfg = cgx_lmac_addr_get(cgx_id, lmac_id);
 	/* copy 48 bit mac address to req->mac_addr */
-	for (i = 0; i < ETH_ALEN; i++)
-		rsp->mac_addr[i] = cfg >> (ETH_ALEN - 1 - i) * 8;
+	u64_to_ether_addr(cfg, rsp->mac_addr);
 	return 0;
 }
 
-- 
GitLab


From 47f8dc0938e95fc98bd1a61d49717c892eb5f9f7 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 8 Aug 2023 19:45:04 +0800
Subject: [PATCH 1029/1806] octeontx2-af: Remove redundant functions
 rvu_npc_exact_mac2u64()

The rvu_npc_exact_mac2u64() is used to convert an Ethernet MAC address
into a u64 value, as this is exactly what ether_addr_to_u64() does.
Use ether_addr_to_u64() to replace the rvu_npc_exact_mac2u64().

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Acked-by: Geethasowjanya Akula <gakula@marvell.com>
Link: https://lore.kernel.org/r/20230808114504.4036008-4-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../marvell/octeontx2/af/rvu_npc_hash.c       | 20 ++-----------------
 1 file changed, 2 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
index 7e20282c12d00..d2661e7fabdb4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
@@ -390,22 +390,6 @@ int rvu_mbox_handler_npc_get_field_hash_info(struct rvu *rvu,
 	return 0;
 }
 
-/**
- *	rvu_npc_exact_mac2u64 - utility function to convert mac address to u64.
- *	@mac_addr: MAC address.
- *	Return: mdata for exact match table.
- */
-static u64 rvu_npc_exact_mac2u64(u8 *mac_addr)
-{
-	u64 mac = 0;
-	int index;
-
-	for (index = ETH_ALEN - 1; index >= 0; index--)
-		mac |= ((u64)*mac_addr++) << (8 * index);
-
-	return mac;
-}
-
 /**
  *	rvu_exact_prepare_mdata - Make mdata for mcam entry
  *	@mac: MAC address
@@ -416,7 +400,7 @@ static u64 rvu_npc_exact_mac2u64(u8 *mac_addr)
  */
 static u64 rvu_exact_prepare_mdata(u8 *mac, u16 chan, u16 ctype, u64 mask)
 {
-	u64 ldata = rvu_npc_exact_mac2u64(mac);
+	u64 ldata = ether_addr_to_u64(mac);
 
 	/* Please note that mask is 48bit which excludes chan and ctype.
 	 * Increase mask bits if we need to include them as well.
@@ -604,7 +588,7 @@ static u64 rvu_exact_prepare_table_entry(struct rvu *rvu, bool enable,
 					 u8 ctype, u16 chan, u8 *mac_addr)
 
 {
-	u64 ldata = rvu_npc_exact_mac2u64(mac_addr);
+	u64 ldata = ether_addr_to_u64(mac_addr);
 
 	/* Enable or disable */
 	u64 mdata = FIELD_PREP(GENMASK_ULL(63, 63), enable ? 1 : 0);
-- 
GitLab


From 1ded5e5a5931bb8b31e15b63b655fe232e3416b2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 8 Aug 2023 13:58:09 +0000
Subject: [PATCH 1030/1806] net: annotate data-races around sock->ops

IPV6_ADDRFORM socket option is evil, because it can change sock->ops
while other threads might read it. Same issue for sk->sk_family
being set to AF_INET.

Adding READ_ONCE() over sock->ops reads is needed for sockets
that might be impacted by IPV6_ADDRFORM.

Note that mptcp_is_tcpsk() can also overwrite sock->ops.

Adding annotations for all sk->sk_family reads will require
more patches :/

BUG: KCSAN: data-race in ____sys_sendmsg / do_ipv6_setsockopt

write to 0xffff888109f24ca0 of 8 bytes by task 4470 on cpu 0:
do_ipv6_setsockopt+0x2c5e/0x2ce0 net/ipv6/ipv6_sockglue.c:491
ipv6_setsockopt+0x57/0x130 net/ipv6/ipv6_sockglue.c:1012
udpv6_setsockopt+0x95/0xa0 net/ipv6/udp.c:1690
sock_common_setsockopt+0x61/0x70 net/core/sock.c:3663
__sys_setsockopt+0x1c3/0x230 net/socket.c:2273
__do_sys_setsockopt net/socket.c:2284 [inline]
__se_sys_setsockopt net/socket.c:2281 [inline]
__x64_sys_setsockopt+0x66/0x80 net/socket.c:2281
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

read to 0xffff888109f24ca0 of 8 bytes by task 4469 on cpu 1:
sock_sendmsg_nosec net/socket.c:724 [inline]
sock_sendmsg net/socket.c:747 [inline]
____sys_sendmsg+0x349/0x4c0 net/socket.c:2503
___sys_sendmsg net/socket.c:2557 [inline]
__sys_sendmmsg+0x263/0x500 net/socket.c:2643
__do_sys_sendmmsg net/socket.c:2672 [inline]
__se_sys_sendmmsg net/socket.c:2669 [inline]
__x64_sys_sendmmsg+0x57/0x60 net/socket.c:2669
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0xffffffff850e32b8 -> 0xffffffff850da890

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 4469 Comm: syz-executor.1 Not tainted 6.4.0-rc5-syzkaller-00313-g4c605260bc60 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230808135809.2300241-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/net.h      |   2 +-
 net/9p/trans_fd.c        |   4 +-
 net/core/scm.c           |   3 +-
 net/core/skmsg.c         |   8 ++-
 net/core/sock.c          |  24 +++++--
 net/ipv6/ipv6_sockglue.c |   8 +--
 net/mptcp/protocol.c     |   8 +--
 net/socket.c             | 136 +++++++++++++++++++++++----------------
 net/unix/scm.c           |   3 +-
 9 files changed, 118 insertions(+), 78 deletions(-)

diff --git a/include/linux/net.h b/include/linux/net.h
index 41c608c1b02c2..c9b4a63791a45 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -123,7 +123,7 @@ struct socket {
 
 	struct file		*file;
 	struct sock		*sk;
-	const struct proto_ops	*ops;
+	const struct proto_ops	*ops; /* Might change with IPV6_ADDRFORM or MPTCP. */
 
 	struct socket_wq	wq;
 };
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 00b684616e8d9..c4015f30f9fa7 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -1019,7 +1019,7 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args)
 		}
 	}
 
-	err = csocket->ops->connect(csocket,
+	err = READ_ONCE(csocket->ops)->connect(csocket,
 				    (struct sockaddr *)&sin_server,
 				    sizeof(struct sockaddr_in), 0);
 	if (err < 0) {
@@ -1060,7 +1060,7 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args)
 
 		return err;
 	}
-	err = csocket->ops->connect(csocket, (struct sockaddr *)&sun_server,
+	err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr *)&sun_server,
 			sizeof(struct sockaddr_un) - 1, 0);
 	if (err < 0) {
 		pr_err("%s (%d): problem connecting socket: %s: %d\n",
diff --git a/net/core/scm.c b/net/core/scm.c
index 3cd7dd377e53f..880027ecf5165 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -130,6 +130,7 @@ EXPORT_SYMBOL(__scm_destroy);
 
 int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
 {
+	const struct proto_ops *ops = READ_ONCE(sock->ops);
 	struct cmsghdr *cmsg;
 	int err;
 
@@ -153,7 +154,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
 		switch (cmsg->cmsg_type)
 		{
 		case SCM_RIGHTS:
-			if (!sock->ops || sock->ops->family != PF_UNIX)
+			if (!ops || ops->family != PF_UNIX)
 				goto error;
 			err=scm_fp_copy(cmsg, &p->fp);
 			if (err<0)
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index a29508e1ff356..e6dfc846018f9 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1198,13 +1198,17 @@ out:
 static void sk_psock_verdict_data_ready(struct sock *sk)
 {
 	struct socket *sock = sk->sk_socket;
+	const struct proto_ops *ops;
 	int copied;
 
 	trace_sk_data_ready(sk);
 
-	if (unlikely(!sock || !sock->ops || !sock->ops->read_skb))
+	if (unlikely(!sock))
 		return;
-	copied = sock->ops->read_skb(sk, sk_psock_verdict_recv);
+	ops = READ_ONCE(sock->ops);
+	if (!ops || !ops->read_skb)
+		return;
+	copied = ops->read_skb(sk, sk_psock_verdict_recv);
 	if (copied >= 0) {
 		struct sk_psock *psock;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 49915801d53a3..51f7d94eccf7c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1277,14 +1277,19 @@ set_sndbuf:
 		break;
 
 	case SO_RCVLOWAT:
+		{
+		int (*set_rcvlowat)(struct sock *sk, int val) = NULL;
+
 		if (val < 0)
 			val = INT_MAX;
-		if (sock && sock->ops->set_rcvlowat)
-			ret = sock->ops->set_rcvlowat(sk, val);
+		if (sock)
+			set_rcvlowat = READ_ONCE(sock->ops)->set_rcvlowat;
+		if (set_rcvlowat)
+			ret = set_rcvlowat(sk, val);
 		else
 			WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 		break;
-
+		}
 	case SO_RCVTIMEO_OLD:
 	case SO_RCVTIMEO_NEW:
 		ret = sock_set_timeout(&sk->sk_rcvtimeo, optval,
@@ -1379,11 +1384,16 @@ set_sndbuf:
 		break;
 
 	case SO_PEEK_OFF:
-		if (sock->ops->set_peek_off)
-			ret = sock->ops->set_peek_off(sk, val);
+		{
+		int (*set_peek_off)(struct sock *sk, int val);
+
+		set_peek_off = READ_ONCE(sock->ops)->set_peek_off;
+		if (set_peek_off)
+			ret = set_peek_off(sk, val);
 		else
 			ret = -EOPNOTSUPP;
 		break;
+		}
 
 	case SO_NOFCS:
 		sock_valbool_flag(sk, SOCK_NOFCS, valbool);
@@ -1816,7 +1826,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 	{
 		struct sockaddr_storage address;
 
-		lv = sock->ops->getname(sock, (struct sockaddr *)&address, 2);
+		lv = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 2);
 		if (lv < 0)
 			return -ENOTCONN;
 		if (lv < len)
@@ -1858,7 +1868,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_PEEK_OFF:
-		if (!sock->ops->set_peek_off)
+		if (!READ_ONCE(sock->ops)->set_peek_off)
 			return -EOPNOTSUPP;
 
 		v.val = READ_ONCE(sk->sk_peek_off);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index ae818ff462248..ca377159967c8 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -474,8 +474,8 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 				WRITE_ONCE(sk->sk_prot, &tcp_prot);
 				/* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
 				WRITE_ONCE(icsk->icsk_af_ops, &ipv4_specific);
-				sk->sk_socket->ops = &inet_stream_ops;
-				sk->sk_family = PF_INET;
+				WRITE_ONCE(sk->sk_socket->ops, &inet_stream_ops);
+				WRITE_ONCE(sk->sk_family, PF_INET);
 				tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 			} else {
 				struct proto *prot = &udp_prot;
@@ -488,8 +488,8 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 
 				/* Paired with READ_ONCE(sk->sk_prot) in inet6_dgram_ops */
 				WRITE_ONCE(sk->sk_prot, prot);
-				sk->sk_socket->ops = &inet_dgram_ops;
-				sk->sk_family = PF_INET;
+				WRITE_ONCE(sk->sk_socket->ops, &inet_dgram_ops);
+				WRITE_ONCE(sk->sk_family, PF_INET);
 			}
 
 			/* Disable all options not to allocate memory anymore,
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 65ee949a8a445..1c079e83481ea 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -67,11 +67,11 @@ static bool mptcp_is_tcpsk(struct sock *sk)
 		 * Hand the socket over to tcp so all further socket ops
 		 * bypass mptcp.
 		 */
-		sock->ops = &inet_stream_ops;
+		WRITE_ONCE(sock->ops, &inet_stream_ops);
 		return true;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	} else if (unlikely(sk->sk_prot == &tcpv6_prot)) {
-		sock->ops = &inet6_stream_ops;
+		WRITE_ONCE(sock->ops, &inet6_stream_ops);
 		return true;
 #endif
 	}
@@ -3683,7 +3683,7 @@ static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto unlock;
 	}
 
-	err = ssock->ops->bind(ssock, uaddr, addr_len);
+	err = READ_ONCE(ssock->ops)->bind(ssock, uaddr, addr_len);
 	if (!err)
 		mptcp_copy_inaddrs(sock->sk, ssock->sk);
 
@@ -3717,7 +3717,7 @@ static int mptcp_listen(struct socket *sock, int backlog)
 	inet_sk_state_store(sk, TCP_LISTEN);
 	sock_set_flag(sk, SOCK_RCU_FREE);
 
-	err = ssock->ops->listen(ssock, backlog);
+	err = READ_ONCE(ssock->ops)->listen(ssock, backlog);
 	inet_sk_state_store(sk, inet_sk_state_load(ssock->sk));
 	if (!err) {
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
diff --git a/net/socket.c b/net/socket.c
index 2b0e54b2405c8..5d4e37595e9aa 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -136,9 +136,10 @@ static void sock_splice_eof(struct file *file);
 static void sock_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct socket *sock = f->private_data;
+	const struct proto_ops *ops = READ_ONCE(sock->ops);
 
-	if (sock->ops->show_fdinfo)
-		sock->ops->show_fdinfo(m, sock);
+	if (ops->show_fdinfo)
+		ops->show_fdinfo(m, sock);
 }
 #else
 #define sock_show_fdinfo NULL
@@ -646,12 +647,14 @@ EXPORT_SYMBOL(sock_alloc);
 
 static void __sock_release(struct socket *sock, struct inode *inode)
 {
-	if (sock->ops) {
-		struct module *owner = sock->ops->owner;
+	const struct proto_ops *ops = READ_ONCE(sock->ops);
+
+	if (ops) {
+		struct module *owner = ops->owner;
 
 		if (inode)
 			inode_lock(inode);
-		sock->ops->release(sock);
+		ops->release(sock);
 		sock->sk = NULL;
 		if (inode)
 			inode_unlock(inode);
@@ -722,7 +725,7 @@ static noinline void call_trace_sock_send_length(struct sock *sk, int ret,
 
 static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
 {
-	int ret = INDIRECT_CALL_INET(sock->ops->sendmsg, inet6_sendmsg,
+	int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->sendmsg, inet6_sendmsg,
 				     inet_sendmsg, sock, msg,
 				     msg_data_left(msg));
 	BUG_ON(ret == -EIOCBQUEUED);
@@ -786,13 +789,14 @@ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 			  struct kvec *vec, size_t num, size_t size)
 {
 	struct socket *sock = sk->sk_socket;
+	const struct proto_ops *ops = READ_ONCE(sock->ops);
 
-	if (!sock->ops->sendmsg_locked)
+	if (!ops->sendmsg_locked)
 		return sock_no_sendmsg_locked(sk, msg, size);
 
 	iov_iter_kvec(&msg->msg_iter, ITER_SOURCE, vec, num, size);
 
-	return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg));
+	return ops->sendmsg_locked(sk, msg, msg_data_left(msg));
 }
 EXPORT_SYMBOL(kernel_sendmsg_locked);
 
@@ -1017,7 +1021,8 @@ static noinline void call_trace_sock_recv_length(struct sock *sk, int ret, int f
 static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
 				     int flags)
 {
-	int ret = INDIRECT_CALL_INET(sock->ops->recvmsg, inet6_recvmsg,
+	int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->recvmsg,
+				     inet6_recvmsg,
 				     inet_recvmsg, sock, msg,
 				     msg_data_left(msg), flags);
 	if (trace_sock_recv_length_enabled())
@@ -1072,19 +1077,23 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 				unsigned int flags)
 {
 	struct socket *sock = file->private_data;
+	const struct proto_ops *ops;
 
-	if (unlikely(!sock->ops->splice_read))
+	ops = READ_ONCE(sock->ops);
+	if (unlikely(!ops->splice_read))
 		return copy_splice_read(file, ppos, pipe, len, flags);
 
-	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
+	return ops->splice_read(sock, ppos, pipe, len, flags);
 }
 
 static void sock_splice_eof(struct file *file)
 {
 	struct socket *sock = file->private_data;
+	const struct proto_ops *ops;
 
-	if (sock->ops->splice_eof)
-		sock->ops->splice_eof(sock);
+	ops = READ_ONCE(sock->ops);
+	if (ops->splice_eof)
+		ops->splice_eof(sock);
 }
 
 static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -1181,13 +1190,14 @@ EXPORT_SYMBOL(vlan_ioctl_set);
 static long sock_do_ioctl(struct net *net, struct socket *sock,
 			  unsigned int cmd, unsigned long arg)
 {
+	const struct proto_ops *ops = READ_ONCE(sock->ops);
 	struct ifreq ifr;
 	bool need_copyout;
 	int err;
 	void __user *argp = (void __user *)arg;
 	void __user *data;
 
-	err = sock->ops->ioctl(sock, cmd, arg);
+	err = ops->ioctl(sock, cmd, arg);
 
 	/*
 	 * If this ioctl is unknown try to hand it down
@@ -1216,6 +1226,7 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
 
 static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
+	const struct proto_ops  *ops;
 	struct socket *sock;
 	struct sock *sk;
 	void __user *argp = (void __user *)arg;
@@ -1223,6 +1234,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	struct net *net;
 
 	sock = file->private_data;
+	ops = READ_ONCE(sock->ops);
 	sk = sock->sk;
 	net = sock_net(sk);
 	if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) {
@@ -1280,23 +1292,23 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			break;
 		case SIOCGSTAMP_OLD:
 		case SIOCGSTAMPNS_OLD:
-			if (!sock->ops->gettstamp) {
+			if (!ops->gettstamp) {
 				err = -ENOIOCTLCMD;
 				break;
 			}
-			err = sock->ops->gettstamp(sock, argp,
-						   cmd == SIOCGSTAMP_OLD,
-						   !IS_ENABLED(CONFIG_64BIT));
+			err = ops->gettstamp(sock, argp,
+					     cmd == SIOCGSTAMP_OLD,
+					     !IS_ENABLED(CONFIG_64BIT));
 			break;
 		case SIOCGSTAMP_NEW:
 		case SIOCGSTAMPNS_NEW:
-			if (!sock->ops->gettstamp) {
+			if (!ops->gettstamp) {
 				err = -ENOIOCTLCMD;
 				break;
 			}
-			err = sock->ops->gettstamp(sock, argp,
-						   cmd == SIOCGSTAMP_NEW,
-						   false);
+			err = ops->gettstamp(sock, argp,
+					     cmd == SIOCGSTAMP_NEW,
+					     false);
 			break;
 
 		case SIOCGIFCONF:
@@ -1357,9 +1369,10 @@ EXPORT_SYMBOL(sock_create_lite);
 static __poll_t sock_poll(struct file *file, poll_table *wait)
 {
 	struct socket *sock = file->private_data;
+	const struct proto_ops *ops = READ_ONCE(sock->ops);
 	__poll_t events = poll_requested_events(wait), flag = 0;
 
-	if (!sock->ops->poll)
+	if (!ops->poll)
 		return 0;
 
 	if (sk_can_busy_loop(sock->sk)) {
@@ -1371,14 +1384,14 @@ static __poll_t sock_poll(struct file *file, poll_table *wait)
 		flag = POLL_BUSY_LOOP;
 	}
 
-	return sock->ops->poll(file, sock, wait) | flag;
+	return ops->poll(file, sock, wait) | flag;
 }
 
 static int sock_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct socket *sock = file->private_data;
 
-	return sock->ops->mmap(file, sock, vma);
+	return READ_ONCE(sock->ops)->mmap(file, sock, vma);
 }
 
 static int sock_close(struct inode *inode, struct file *filp)
@@ -1728,7 +1741,7 @@ int __sys_socketpair(int family, int type, int protocol, int __user *usockvec)
 		goto out;
 	}
 
-	err = sock1->ops->socketpair(sock1, sock2);
+	err = READ_ONCE(sock1->ops)->socketpair(sock1, sock2);
 	if (unlikely(err < 0)) {
 		sock_release(sock2);
 		sock_release(sock1);
@@ -1789,7 +1802,7 @@ int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen)
 						   (struct sockaddr *)&address,
 						   addrlen);
 			if (!err)
-				err = sock->ops->bind(sock,
+				err = READ_ONCE(sock->ops)->bind(sock,
 						      (struct sockaddr *)
 						      &address, addrlen);
 		}
@@ -1823,7 +1836,7 @@ int __sys_listen(int fd, int backlog)
 
 		err = security_socket_listen(sock, backlog);
 		if (!err)
-			err = sock->ops->listen(sock, backlog);
+			err = READ_ONCE(sock->ops)->listen(sock, backlog);
 
 		fput_light(sock->file, fput_needed);
 	}
@@ -1843,6 +1856,7 @@ struct file *do_accept(struct file *file, unsigned file_flags,
 	struct file *newfile;
 	int err, len;
 	struct sockaddr_storage address;
+	const struct proto_ops *ops;
 
 	sock = sock_from_file(file);
 	if (!sock)
@@ -1851,15 +1865,16 @@ struct file *do_accept(struct file *file, unsigned file_flags,
 	newsock = sock_alloc();
 	if (!newsock)
 		return ERR_PTR(-ENFILE);
+	ops = READ_ONCE(sock->ops);
 
 	newsock->type = sock->type;
-	newsock->ops = sock->ops;
+	newsock->ops = ops;
 
 	/*
 	 * We don't need try_module_get here, as the listening socket (sock)
 	 * has the protocol module (sock->ops->owner) held.
 	 */
-	__module_get(newsock->ops->owner);
+	__module_get(ops->owner);
 
 	newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name);
 	if (IS_ERR(newfile))
@@ -1869,14 +1884,13 @@ struct file *do_accept(struct file *file, unsigned file_flags,
 	if (err)
 		goto out_fd;
 
-	err = sock->ops->accept(sock, newsock, sock->file->f_flags | file_flags,
+	err = ops->accept(sock, newsock, sock->file->f_flags | file_flags,
 					false);
 	if (err < 0)
 		goto out_fd;
 
 	if (upeer_sockaddr) {
-		len = newsock->ops->getname(newsock,
-					(struct sockaddr *)&address, 2);
+		len = ops->getname(newsock, (struct sockaddr *)&address, 2);
 		if (len < 0) {
 			err = -ECONNABORTED;
 			goto out_fd;
@@ -1989,8 +2003,8 @@ int __sys_connect_file(struct file *file, struct sockaddr_storage *address,
 	if (err)
 		goto out;
 
-	err = sock->ops->connect(sock, (struct sockaddr *)address, addrlen,
-				 sock->file->f_flags | file_flags);
+	err = READ_ONCE(sock->ops)->connect(sock, (struct sockaddr *)address,
+				addrlen, sock->file->f_flags | file_flags);
 out:
 	return err;
 }
@@ -2039,7 +2053,7 @@ int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
 	if (err)
 		goto out_put;
 
-	err = sock->ops->getname(sock, (struct sockaddr *)&address, 0);
+	err = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 0);
 	if (err < 0)
 		goto out_put;
 	/* "err" is actually length in this case */
@@ -2071,13 +2085,15 @@ int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (sock != NULL) {
+		const struct proto_ops *ops = READ_ONCE(sock->ops);
+
 		err = security_socket_getpeername(sock);
 		if (err) {
 			fput_light(sock->file, fput_needed);
 			return err;
 		}
 
-		err = sock->ops->getname(sock, (struct sockaddr *)&address, 1);
+		err = ops->getname(sock, (struct sockaddr *)&address, 1);
 		if (err >= 0)
 			/* "err" is actually length in this case */
 			err = move_addr_to_user(&address, err, usockaddr,
@@ -2227,6 +2243,7 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 		int optlen)
 {
 	sockptr_t optval = USER_SOCKPTR(user_optval);
+	const struct proto_ops *ops;
 	char *kernel_optval = NULL;
 	int err, fput_needed;
 	struct socket *sock;
@@ -2255,12 +2272,13 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 
 	if (kernel_optval)
 		optval = KERNEL_SOCKPTR(kernel_optval);
+	ops = READ_ONCE(sock->ops);
 	if (level == SOL_SOCKET && !sock_use_custom_sol_socket(sock))
 		err = sock_setsockopt(sock, level, optname, optval, optlen);
-	else if (unlikely(!sock->ops->setsockopt))
+	else if (unlikely(!ops->setsockopt))
 		err = -EOPNOTSUPP;
 	else
-		err = sock->ops->setsockopt(sock, level, optname, optval,
+		err = ops->setsockopt(sock, level, optname, optval,
 					    optlen);
 	kfree(kernel_optval);
 out_put:
@@ -2285,6 +2303,7 @@ int __sys_getsockopt(int fd, int level, int optname, char __user *optval,
 		int __user *optlen)
 {
 	int max_optlen __maybe_unused;
+	const struct proto_ops *ops;
 	int err, fput_needed;
 	struct socket *sock;
 
@@ -2299,12 +2318,13 @@ int __sys_getsockopt(int fd, int level, int optname, char __user *optval,
 	if (!in_compat_syscall())
 		max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
 
+	ops = READ_ONCE(sock->ops);
 	if (level == SOL_SOCKET)
 		err = sock_getsockopt(sock, level, optname, optval, optlen);
-	else if (unlikely(!sock->ops->getsockopt))
+	else if (unlikely(!ops->getsockopt))
 		err = -EOPNOTSUPP;
 	else
-		err = sock->ops->getsockopt(sock, level, optname, optval,
+		err = ops->getsockopt(sock, level, optname, optval,
 					    optlen);
 
 	if (!in_compat_syscall())
@@ -2332,7 +2352,7 @@ int __sys_shutdown_sock(struct socket *sock, int how)
 
 	err = security_socket_shutdown(sock, how);
 	if (!err)
-		err = sock->ops->shutdown(sock, how);
+		err = READ_ONCE(sock->ops)->shutdown(sock, how);
 
 	return err;
 }
@@ -3324,6 +3344,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	void __user *argp = compat_ptr(arg);
 	struct sock *sk = sock->sk;
 	struct net *net = sock_net(sk);
+	const struct proto_ops *ops;
 
 	if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))
 		return sock_ioctl(file, cmd, (unsigned long)argp);
@@ -3333,10 +3354,11 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 		return compat_siocwandev(net, argp);
 	case SIOCGSTAMP_OLD:
 	case SIOCGSTAMPNS_OLD:
-		if (!sock->ops->gettstamp)
+		ops = READ_ONCE(sock->ops);
+		if (!ops->gettstamp)
 			return -ENOIOCTLCMD;
-		return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD,
-					    !COMPAT_USE_64BIT_TIME);
+		return ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD,
+				      !COMPAT_USE_64BIT_TIME);
 
 	case SIOCETHTOOL:
 	case SIOCBONDSLAVEINFOQUERY:
@@ -3417,6 +3439,7 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd,
 			      unsigned long arg)
 {
 	struct socket *sock = file->private_data;
+	const struct proto_ops *ops = READ_ONCE(sock->ops);
 	int ret = -ENOIOCTLCMD;
 	struct sock *sk;
 	struct net *net;
@@ -3424,8 +3447,8 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd,
 	sk = sock->sk;
 	net = sock_net(sk);
 
-	if (sock->ops->compat_ioctl)
-		ret = sock->ops->compat_ioctl(sock, cmd, arg);
+	if (ops->compat_ioctl)
+		ret = ops->compat_ioctl(sock, cmd, arg);
 
 	if (ret == -ENOIOCTLCMD &&
 	    (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST))
@@ -3449,7 +3472,7 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd,
 
 int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen)
 {
-	return sock->ops->bind(sock, addr, addrlen);
+	return READ_ONCE(sock->ops)->bind(sock, addr, addrlen);
 }
 EXPORT_SYMBOL(kernel_bind);
 
@@ -3463,7 +3486,7 @@ EXPORT_SYMBOL(kernel_bind);
 
 int kernel_listen(struct socket *sock, int backlog)
 {
-	return sock->ops->listen(sock, backlog);
+	return READ_ONCE(sock->ops)->listen(sock, backlog);
 }
 EXPORT_SYMBOL(kernel_listen);
 
@@ -3481,6 +3504,7 @@ EXPORT_SYMBOL(kernel_listen);
 int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
 {
 	struct sock *sk = sock->sk;
+	const struct proto_ops *ops = READ_ONCE(sock->ops);
 	int err;
 
 	err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol,
@@ -3488,15 +3512,15 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
 	if (err < 0)
 		goto done;
 
-	err = sock->ops->accept(sock, *newsock, flags, true);
+	err = ops->accept(sock, *newsock, flags, true);
 	if (err < 0) {
 		sock_release(*newsock);
 		*newsock = NULL;
 		goto done;
 	}
 
-	(*newsock)->ops = sock->ops;
-	__module_get((*newsock)->ops->owner);
+	(*newsock)->ops = ops;
+	__module_get(ops->owner);
 
 done:
 	return err;
@@ -3519,7 +3543,7 @@ EXPORT_SYMBOL(kernel_accept);
 int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
 		   int flags)
 {
-	return sock->ops->connect(sock, addr, addrlen, flags);
+	return READ_ONCE(sock->ops)->connect(sock, addr, addrlen, flags);
 }
 EXPORT_SYMBOL(kernel_connect);
 
@@ -3534,7 +3558,7 @@ EXPORT_SYMBOL(kernel_connect);
 
 int kernel_getsockname(struct socket *sock, struct sockaddr *addr)
 {
-	return sock->ops->getname(sock, addr, 0);
+	return READ_ONCE(sock->ops)->getname(sock, addr, 0);
 }
 EXPORT_SYMBOL(kernel_getsockname);
 
@@ -3549,7 +3573,7 @@ EXPORT_SYMBOL(kernel_getsockname);
 
 int kernel_getpeername(struct socket *sock, struct sockaddr *addr)
 {
-	return sock->ops->getname(sock, addr, 1);
+	return READ_ONCE(sock->ops)->getname(sock, addr, 1);
 }
 EXPORT_SYMBOL(kernel_getpeername);
 
@@ -3563,7 +3587,7 @@ EXPORT_SYMBOL(kernel_getpeername);
 
 int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how)
 {
-	return sock->ops->shutdown(sock, how);
+	return READ_ONCE(sock->ops)->shutdown(sock, how);
 }
 EXPORT_SYMBOL(kernel_sock_shutdown);
 
diff --git a/net/unix/scm.c b/net/unix/scm.c
index f9152881d77f6..e9dde7176c8a3 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -29,10 +29,11 @@ struct sock *unix_get_socket(struct file *filp)
 	/* Socket ? */
 	if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
 		struct socket *sock = SOCKET_I(inode);
+		const struct proto_ops *ops = READ_ONCE(sock->ops);
 		struct sock *s = sock->sk;
 
 		/* PF_UNIX ? */
-		if (s && sock->ops && sock->ops->family == PF_UNIX)
+		if (s && ops && ops->family == PF_UNIX)
 			u_sock = s;
 	} else {
 		/* Could be an io_uring instance */
-- 
GitLab


From fa1891aeb7620b51992d0db86c72c0cd3cf114ab Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 8 Aug 2023 09:43:09 -0700
Subject: [PATCH 1031/1806] net/llc/llc_conn.c: fix 4 instances of
 -Wmissing-variable-declarations

I'm looking to enable -Wmissing-variable-declarations behind W=1. 0day
bot spotted the following instances:

  net/llc/llc_conn.c:44:5: warning: no previous extern declaration for
  non-static variable 'sysctl_llc2_ack_timeout'
  [-Wmissing-variable-declarations]
  44 | int sysctl_llc2_ack_timeout = LLC2_ACK_TIME * HZ;
     |     ^
  net/llc/llc_conn.c:44:1: note: declare 'static' if the variable is not
  intended to be used outside of this translation unit
  44 | int sysctl_llc2_ack_timeout = LLC2_ACK_TIME * HZ;
     | ^
  net/llc/llc_conn.c:45:5: warning: no previous extern declaration for
  non-static variable 'sysctl_llc2_p_timeout'
  [-Wmissing-variable-declarations]
  45 | int sysctl_llc2_p_timeout = LLC2_P_TIME * HZ;
     |     ^
  net/llc/llc_conn.c:45:1: note: declare 'static' if the variable is not
  intended to be used outside of this translation unit
  45 | int sysctl_llc2_p_timeout = LLC2_P_TIME * HZ;
     | ^
  net/llc/llc_conn.c:46:5: warning: no previous extern declaration for
  non-static variable 'sysctl_llc2_rej_timeout'
  [-Wmissing-variable-declarations]
  46 | int sysctl_llc2_rej_timeout = LLC2_REJ_TIME * HZ;
     |     ^
  net/llc/llc_conn.c:46:1: note: declare 'static' if the variable is not
  intended to be used outside of this translation unit
  46 | int sysctl_llc2_rej_timeout = LLC2_REJ_TIME * HZ;
     | ^
  net/llc/llc_conn.c:47:5: warning: no previous extern declaration for
  non-static variable 'sysctl_llc2_busy_timeout'
  [-Wmissing-variable-declarations]
  47 | int sysctl_llc2_busy_timeout = LLC2_BUSY_TIME * HZ;
     |     ^
  net/llc/llc_conn.c:47:1: note: declare 'static' if the variable is not
  intended to be used outside of this translation unit
  47 | int sysctl_llc2_busy_timeout = LLC2_BUSY_TIME * HZ;
     | ^

These symbols are referenced by more than one translation unit, so make
include the correct header for their declarations. Finally, sort the
list of includes to help keep them tidy.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/llvm/202308081000.tTL1ElTr-lkp@intel.com/
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230808-llc_static-v1-1-c140c4c297e4@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/llc/llc_conn.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index d037009ee10f3..0a3f5e0bec00c 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -14,14 +14,15 @@
 
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <net/llc_sap.h>
-#include <net/llc_conn.h>
-#include <net/sock.h>
-#include <net/tcp_states.h>
-#include <net/llc_c_ev.h>
+#include <net/llc.h>
 #include <net/llc_c_ac.h>
+#include <net/llc_c_ev.h>
 #include <net/llc_c_st.h>
+#include <net/llc_conn.h>
 #include <net/llc_pdu.h>
+#include <net/llc_sap.h>
+#include <net/sock.h>
+#include <net/tcp_states.h>
 
 #if 0
 #define dprintk(args...) printk(KERN_DEBUG args)
-- 
GitLab


From 383a4de3b44744b194848089db9e13ec98af2881 Mon Sep 17 00:00:00 2001
From: Adham Faris <afaris@nvidia.com>
Date: Mon, 7 Aug 2023 11:05:06 -0700
Subject: [PATCH 1032/1806] net/mlx5: Expose port.c/mlx5_query_module_num()
 function

Make mlx5_query_module_num() defined in port.c, a non-static, so it can
be used by other files.

CC: Jean Delvare <jdelvare@suse.com>
CC: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Adham Faris <afaris@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230807180507.22984-2-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/port.c      | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 43b0144121ca2..d54afb07d9720 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -176,6 +176,7 @@ static inline int mlx5_flexible_inlen(struct mlx5_core_dev *dev, size_t fixed,
 
 int mlx5_query_hca_caps(struct mlx5_core_dev *dev);
 int mlx5_query_board_id(struct mlx5_core_dev *dev);
+int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num);
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
 int mlx5_cmd_enable(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 0daeb4b72cca7..be70d1f23a5da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -271,7 +271,7 @@ void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_oper_mtu);
 
-static int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num)
+int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num)
 {
 	u32 in[MLX5_ST_SZ_DW(pmlp_reg)] = {0};
 	u32 out[MLX5_ST_SZ_DW(pmlp_reg)];
-- 
GitLab


From 1f507e80c700e31e358bf4213dc7e4dd614c7c72 Mon Sep 17 00:00:00 2001
From: Adham Faris <afaris@nvidia.com>
Date: Mon, 7 Aug 2023 11:05:07 -0700
Subject: [PATCH 1033/1806] net/mlx5: Expose NIC temperature via hardware
 monitoring kernel API
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Expose NIC temperature by implementing hwmon kernel API, which turns
current thermal zone kernel API to redundant.

For each one of the supported and exposed thermal diode sensors, expose
the following attributes:
1) Input temperature.
2) Highest temperature.
3) Temperature label:
   Depends on the firmware capability, if firmware doesn't support
   sensors naming, the fallback naming convention would be: "sensorX",
   where X is the HW spec (MTMP register) sensor index.
4) Temperature critical max value:
   refers to the high threshold of Warning Event. Will be exposed as
   `tempY_crit` hwmon attribute (RO attribute). For example for
   ConnectX5 HCA's this temperature value will be 105 Celsius, 10
   degrees lower than the HW shutdown temperature).
5) Temperature reset history: resets highest temperature.

For example, for dualport ConnectX5 NIC with a single IC thermal diode
sensor will have 2 hwmon directories (one for each PCI function)
under "/sys/class/hwmon/hwmon[X,Y]".

Listing one of the directories above (hwmonX/Y) generates the
corresponding output below:

$ grep -H -d skip . /sys/class/hwmon/hwmon0/*

Output
=======================================================================
/sys/class/hwmon/hwmon0/name:mlx5
/sys/class/hwmon/hwmon0/temp1_crit:105000
/sys/class/hwmon/hwmon0/temp1_highest:48000
/sys/class/hwmon/hwmon0/temp1_input:46000
/sys/class/hwmon/hwmon0/temp1_label:asic
grep: /sys/class/hwmon/hwmon0/temp1_reset_history: Permission denied

In addition, displaying the sensors data via lm_sensors generates the
corresponding output below:

$ sensors

Output
=======================================================================
mlx5-pci-0800
Adapter: PCI adapter
asic:         +46.0°C  (crit = +105.0°C, highest = +48.0°C)

mlx5-pci-0801
Adapter: PCI adapter
asic:         +46.0°C  (crit = +105.0°C, highest = +48.0°C)

CC: Jean Delvare <jdelvare@suse.com>
Signed-off-by: Adham Faris <afaris@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230807180507.22984-3-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/Kconfig   |   1 +
 .../net/ethernet/mellanox/mlx5/core/Makefile  |   2 +-
 .../net/ethernet/mellanox/mlx5/core/hwmon.c   | 418 ++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/hwmon.h   |  24 +
 .../net/ethernet/mellanox/mlx5/core/main.c    |   8 +-
 .../net/ethernet/mellanox/mlx5/core/thermal.c | 114 -----
 .../net/ethernet/mellanox/mlx5/core/thermal.h |  20 -
 include/linux/mlx5/driver.h                   |   3 +-
 include/linux/mlx5/mlx5_ifc.h                 |  14 +-
 9 files changed, 463 insertions(+), 141 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/thermal.c
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/thermal.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index bb1d7b039a7e5..d537d517cabef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -12,6 +12,7 @@ config MLX5_CORE
 	depends on MLXFW || !MLXFW
 	depends on PTP_1588_CLOCK_OPTIONAL
 	depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE
+	depends on HWMON || !HWMON
 	help
 	  Core driver for low level functionality of the ConnectX-4 and
 	  Connect-IB cards by Mellanox Technologies.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 63a2f2bb80a6b..9463103906590 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -82,7 +82,7 @@ endif
 mlx5_core-$(CONFIG_MLX5_BRIDGE)    += esw/bridge.o esw/bridge_mcast.o esw/bridge_debugfs.o \
 				      en/rep/bridge.o
 
-mlx5_core-$(CONFIG_THERMAL)        += thermal.o
+mlx5_core-$(CONFIG_HWMON)          += hwmon.o
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
new file mode 100644
index 0000000000000..353f81dccd1ce
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
@@ -0,0 +1,418 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+
+#include <linux/hwmon.h>
+#include <linux/bitmap.h>
+#include <linux/mlx5/device.h>
+#include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/port.h>
+#include "mlx5_core.h"
+#include "hwmon.h"
+
+#define CHANNELS_TYPE_NUM 2 /* chip channel and temp channel */
+#define CHIP_CONFIG_NUM 1
+
+/* module 0 is mapped to sensor_index 64 in MTMP register */
+#define to_mtmp_module_sensor_idx(idx) (64 + (idx))
+
+/* All temperatures retrieved in units of 0.125C. hwmon framework expect
+ * it in units of millidegrees C. Hence multiply values by 125.
+ */
+#define mtmp_temp_to_mdeg(temp) ((temp) * 125)
+
+struct temp_channel_desc {
+	u32 sensor_index;
+	char sensor_name[32];
+};
+
+/* chip_channel_config and channel_info arrays must be 0-terminated, hence + 1 */
+struct mlx5_hwmon {
+	struct mlx5_core_dev *mdev;
+	struct device *hwmon_dev;
+	struct hwmon_channel_info chip_info;
+	u32 chip_channel_config[CHIP_CONFIG_NUM + 1];
+	struct hwmon_channel_info temp_info;
+	u32 *temp_channel_config;
+	const struct hwmon_channel_info *channel_info[CHANNELS_TYPE_NUM + 1];
+	struct hwmon_chip_info chip;
+	struct temp_channel_desc *temp_channel_desc;
+	u32 asic_platform_scount;
+	u32 module_scount;
+};
+
+static int mlx5_hwmon_query_mtmp(struct mlx5_core_dev *mdev, u32 sensor_index, u32 *mtmp_out)
+{
+	u32 mtmp_in[MLX5_ST_SZ_DW(mtmp_reg)] = {};
+
+	MLX5_SET(mtmp_reg, mtmp_in, sensor_index, sensor_index);
+
+	return mlx5_core_access_reg(mdev, mtmp_in,  sizeof(mtmp_in),
+				    mtmp_out, MLX5_ST_SZ_BYTES(mtmp_reg),
+				    MLX5_REG_MTMP, 0, 0);
+}
+
+static int mlx5_hwmon_reset_max_temp(struct mlx5_core_dev *mdev, int sensor_index)
+{
+	u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)] = {};
+	u32 mtmp_in[MLX5_ST_SZ_DW(mtmp_reg)] = {};
+
+	MLX5_SET(mtmp_reg, mtmp_in, sensor_index, sensor_index);
+	MLX5_SET(mtmp_reg, mtmp_in, mtr, 1);
+
+	return mlx5_core_access_reg(mdev, mtmp_in,  sizeof(mtmp_in),
+				    mtmp_out, sizeof(mtmp_out),
+				    MLX5_REG_MTMP, 0, 0);
+}
+
+static int mlx5_hwmon_enable_max_temp(struct mlx5_core_dev *mdev, int sensor_index)
+{
+	u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)] = {};
+	u32 mtmp_in[MLX5_ST_SZ_DW(mtmp_reg)] = {};
+	int err;
+
+	err = mlx5_hwmon_query_mtmp(mdev, sensor_index, mtmp_in);
+	if (err)
+		return err;
+
+	MLX5_SET(mtmp_reg, mtmp_in, mte, 1);
+	return mlx5_core_access_reg(mdev, mtmp_in,  sizeof(mtmp_in),
+				    mtmp_out, sizeof(mtmp_out),
+				    MLX5_REG_MTMP, 0, 1);
+}
+
+static int mlx5_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+			   int channel, long *val)
+{
+	struct mlx5_hwmon *hwmon = dev_get_drvdata(dev);
+	u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)] = {};
+	int err;
+
+	if (type != hwmon_temp)
+		return -EOPNOTSUPP;
+
+	err = mlx5_hwmon_query_mtmp(hwmon->mdev, hwmon->temp_channel_desc[channel].sensor_index,
+				    mtmp_out);
+	if (err)
+		return err;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		*val = mtmp_temp_to_mdeg(MLX5_GET(mtmp_reg, mtmp_out, temperature));
+		return 0;
+	case hwmon_temp_highest:
+		*val = mtmp_temp_to_mdeg(MLX5_GET(mtmp_reg, mtmp_out, max_temperature));
+		return 0;
+	case hwmon_temp_crit:
+		*val = mtmp_temp_to_mdeg(MLX5_GET(mtmp_reg, mtmp_out, temp_threshold_hi));
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5_hwmon_write(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+			    int channel, long val)
+{
+	struct mlx5_hwmon *hwmon = dev_get_drvdata(dev);
+
+	if (type != hwmon_temp || attr != hwmon_temp_reset_history)
+		return -EOPNOTSUPP;
+
+	return mlx5_hwmon_reset_max_temp(hwmon->mdev,
+				hwmon->temp_channel_desc[channel].sensor_index);
+}
+
+static umode_t mlx5_hwmon_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr,
+				     int channel)
+{
+	if (type != hwmon_temp)
+		return 0;
+
+	switch (attr) {
+	case hwmon_temp_input:
+	case hwmon_temp_highest:
+	case hwmon_temp_crit:
+	case hwmon_temp_label:
+		return 0444;
+	case hwmon_temp_reset_history:
+		return 0200;
+	default:
+		return 0;
+	}
+}
+
+static int mlx5_hwmon_read_string(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+				  int channel, const char **str)
+{
+	struct mlx5_hwmon *hwmon = dev_get_drvdata(dev);
+
+	if (type != hwmon_temp || attr != hwmon_temp_label)
+		return -EOPNOTSUPP;
+
+	*str = (const char *)hwmon->temp_channel_desc[channel].sensor_name;
+	return 0;
+}
+
+static const struct hwmon_ops mlx5_hwmon_ops = {
+	.read = mlx5_hwmon_read,
+	.read_string = mlx5_hwmon_read_string,
+	.is_visible = mlx5_hwmon_is_visible,
+	.write = mlx5_hwmon_write,
+};
+
+static int mlx5_hwmon_init_channels_names(struct mlx5_hwmon *hwmon)
+{
+	u32 i;
+
+	for (i = 0; i < hwmon->asic_platform_scount + hwmon->module_scount; i++) {
+		u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)] = {};
+		char *sensor_name;
+		int err;
+
+		err = mlx5_hwmon_query_mtmp(hwmon->mdev, hwmon->temp_channel_desc[i].sensor_index,
+					    mtmp_out);
+		if (err)
+			return err;
+
+		sensor_name = MLX5_ADDR_OF(mtmp_reg, mtmp_out, sensor_name_hi);
+		if (!*sensor_name) {
+			snprintf(hwmon->temp_channel_desc[i].sensor_name,
+				 sizeof(hwmon->temp_channel_desc[i].sensor_name), "sensor%u",
+				 hwmon->temp_channel_desc[i].sensor_index);
+			continue;
+		}
+
+		memcpy(&hwmon->temp_channel_desc[i].sensor_name, sensor_name,
+		       MLX5_FLD_SZ_BYTES(mtmp_reg, sensor_name_hi) +
+		       MLX5_FLD_SZ_BYTES(mtmp_reg, sensor_name_lo));
+	}
+
+	return 0;
+}
+
+static int mlx5_hwmon_get_module_sensor_index(struct mlx5_core_dev *mdev, u32 *module_index)
+{
+	int module_num;
+	int err;
+
+	err = mlx5_query_module_num(mdev, &module_num);
+	if (err)
+		return err;
+
+	*module_index = to_mtmp_module_sensor_idx(module_num);
+
+	return 0;
+}
+
+static int mlx5_hwmon_init_sensors_indexes(struct mlx5_hwmon *hwmon, u64 sensor_map)
+{
+	DECLARE_BITMAP(smap, BITS_PER_TYPE(sensor_map));
+	unsigned long bit_pos;
+	int err = 0;
+	int i = 0;
+
+	bitmap_from_u64(smap, sensor_map);
+
+	for_each_set_bit(bit_pos, smap, BITS_PER_TYPE(sensor_map)) {
+		hwmon->temp_channel_desc[i].sensor_index = bit_pos;
+		i++;
+	}
+
+	if (hwmon->module_scount)
+		err = mlx5_hwmon_get_module_sensor_index(hwmon->mdev,
+							 &hwmon->temp_channel_desc[i].sensor_index);
+
+	return err;
+}
+
+static void mlx5_hwmon_channel_info_init(struct mlx5_hwmon *hwmon)
+{
+	int i;
+
+	hwmon->channel_info[0] = &hwmon->chip_info;
+	hwmon->channel_info[1] = &hwmon->temp_info;
+
+	hwmon->chip_channel_config[0] = HWMON_C_REGISTER_TZ;
+	hwmon->chip_info.config = (const u32 *)hwmon->chip_channel_config;
+	hwmon->chip_info.type = hwmon_chip;
+
+	for (i = 0; i < hwmon->asic_platform_scount + hwmon->module_scount; i++)
+		hwmon->temp_channel_config[i] = HWMON_T_INPUT | HWMON_T_HIGHEST | HWMON_T_CRIT |
+					     HWMON_T_RESET_HISTORY | HWMON_T_LABEL;
+
+	hwmon->temp_info.config = (const u32 *)hwmon->temp_channel_config;
+	hwmon->temp_info.type = hwmon_temp;
+}
+
+static int mlx5_hwmon_is_module_mon_cap(struct mlx5_core_dev *mdev, bool *mon_cap)
+{
+	u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)];
+	u32 module_index;
+	int err;
+
+	err = mlx5_hwmon_get_module_sensor_index(mdev, &module_index);
+	if (err)
+		return err;
+
+	err = mlx5_hwmon_query_mtmp(mdev, module_index, mtmp_out);
+	if (err)
+		return err;
+
+	if (MLX5_GET(mtmp_reg, mtmp_out, temperature))
+		*mon_cap = true;
+
+	return 0;
+}
+
+static int mlx5_hwmon_get_sensors_count(struct mlx5_core_dev *mdev, u32 *asic_platform_scount)
+{
+	u32 mtcap_out[MLX5_ST_SZ_DW(mtcap_reg)] = {};
+	u32 mtcap_in[MLX5_ST_SZ_DW(mtcap_reg)] = {};
+	int err;
+
+	err = mlx5_core_access_reg(mdev, mtcap_in,  sizeof(mtcap_in),
+				   mtcap_out, sizeof(mtcap_out),
+				   MLX5_REG_MTCAP, 0, 0);
+	if (err)
+		return err;
+
+	*asic_platform_scount = MLX5_GET(mtcap_reg, mtcap_out, sensor_count);
+
+	return 0;
+}
+
+static void mlx5_hwmon_free(struct mlx5_hwmon *hwmon)
+{
+	if (!hwmon)
+		return;
+
+	kfree(hwmon->temp_channel_config);
+	kfree(hwmon->temp_channel_desc);
+	kfree(hwmon);
+}
+
+static struct mlx5_hwmon *mlx5_hwmon_alloc(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_hwmon *hwmon;
+	bool mon_cap = false;
+	u32 sensors_count;
+	int err;
+
+	hwmon = kzalloc(sizeof(*mdev->hwmon), GFP_KERNEL);
+	if (!hwmon)
+		return ERR_PTR(-ENOMEM);
+
+	err = mlx5_hwmon_get_sensors_count(mdev, &hwmon->asic_platform_scount);
+	if (err)
+		goto err_free_hwmon;
+
+	/* check if module sensor has thermal mon cap. if yes, allocate channel desc for it */
+	err = mlx5_hwmon_is_module_mon_cap(mdev, &mon_cap);
+	if (err)
+		goto err_free_hwmon;
+
+	hwmon->module_scount = mon_cap ? 1 : 0;
+	sensors_count = hwmon->asic_platform_scount + hwmon->module_scount;
+	hwmon->temp_channel_desc = kcalloc(sensors_count, sizeof(*hwmon->temp_channel_desc),
+					   GFP_KERNEL);
+	if (!hwmon->temp_channel_desc) {
+		err = -ENOMEM;
+		goto err_free_hwmon;
+	}
+
+	/* sensors configuration values array, must be 0-terminated hence, + 1 */
+	hwmon->temp_channel_config = kcalloc(sensors_count + 1, sizeof(*hwmon->temp_channel_config),
+					     GFP_KERNEL);
+	if (!hwmon->temp_channel_config) {
+		err = -ENOMEM;
+		goto err_free_temp_channel_desc;
+	}
+
+	hwmon->mdev = mdev;
+
+	return hwmon;
+
+err_free_temp_channel_desc:
+	kfree(hwmon->temp_channel_desc);
+err_free_hwmon:
+	kfree(hwmon);
+	return ERR_PTR(err);
+}
+
+static int mlx5_hwmon_dev_init(struct mlx5_hwmon *hwmon)
+{
+	u32 mtcap_out[MLX5_ST_SZ_DW(mtcap_reg)] = {};
+	u32 mtcap_in[MLX5_ST_SZ_DW(mtcap_reg)] = {};
+	int err;
+	int i;
+
+	err =  mlx5_core_access_reg(hwmon->mdev, mtcap_in,  sizeof(mtcap_in),
+				    mtcap_out, sizeof(mtcap_out),
+				    MLX5_REG_MTCAP, 0, 0);
+	if (err)
+		return err;
+
+	mlx5_hwmon_channel_info_init(hwmon);
+	mlx5_hwmon_init_sensors_indexes(hwmon, MLX5_GET64(mtcap_reg, mtcap_out, sensor_map));
+	err = mlx5_hwmon_init_channels_names(hwmon);
+	if (err)
+		return err;
+
+	for (i = 0; i < hwmon->asic_platform_scount + hwmon->module_scount; i++) {
+		err = mlx5_hwmon_enable_max_temp(hwmon->mdev,
+						 hwmon->temp_channel_desc[i].sensor_index);
+		if (err)
+			return err;
+	}
+
+	hwmon->chip.ops = &mlx5_hwmon_ops;
+	hwmon->chip.info = (const struct hwmon_channel_info **)hwmon->channel_info;
+
+	return 0;
+}
+
+int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev)
+{
+	struct device *dev = mdev->device;
+	struct mlx5_hwmon *hwmon;
+	int err;
+
+	if (!MLX5_CAP_MCAM_REG(mdev, mtmp))
+		return 0;
+
+	hwmon = mlx5_hwmon_alloc(mdev);
+	if (IS_ERR(hwmon))
+		return PTR_ERR(hwmon);
+
+	err = mlx5_hwmon_dev_init(hwmon);
+	if (err)
+		goto err_free_hwmon;
+
+	hwmon->hwmon_dev = hwmon_device_register_with_info(dev, "mlx5",
+							   hwmon,
+							   &hwmon->chip,
+							   NULL);
+	if (IS_ERR(hwmon->hwmon_dev)) {
+		err = PTR_ERR(hwmon->hwmon_dev);
+		goto err_free_hwmon;
+	}
+
+	mdev->hwmon = hwmon;
+	return 0;
+
+err_free_hwmon:
+	mlx5_hwmon_free(hwmon);
+	return err;
+}
+
+void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_hwmon *hwmon = mdev->hwmon;
+
+	if (!hwmon)
+		return;
+
+	hwmon_device_unregister(hwmon->hwmon_dev);
+	mlx5_hwmon_free(hwmon);
+	mdev->hwmon = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
new file mode 100644
index 0000000000000..999654a9b9da5
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+#ifndef __MLX5_HWMON_H__
+#define __MLX5_HWMON_H__
+
+#include <linux/mlx5/driver.h>
+
+#if IS_ENABLED(CONFIG_HWMON)
+
+int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev);
+void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev);
+
+#else
+static inline int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev)
+{
+	return 0;
+}
+
+static inline void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev) {}
+
+#endif
+
+#endif /* __MLX5_HWMON_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index db2e8e4f848db..0389e84f98156 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -49,7 +49,6 @@
 #include <linux/version.h>
 #include <net/devlink.h>
 #include "mlx5_core.h"
-#include "thermal.h"
 #include "lib/eq.h"
 #include "fs_core.h"
 #include "lib/mpfs.h"
@@ -73,6 +72,7 @@
 #include "sf/dev/dev.h"
 #include "sf/sf.h"
 #include "mlx5_irq.h"
+#include "hwmon.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -1930,9 +1930,9 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
 
-	err = mlx5_thermal_init(dev);
+	err = mlx5_hwmon_dev_register(dev);
 	if (err)
-		dev_err(&pdev->dev, "mlx5_thermal_init failed with error code %d\n", err);
+		mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err);
 
 	pci_save_state(pdev);
 	devlink_register(devlink);
@@ -1964,7 +1964,7 @@ static void remove_one(struct pci_dev *pdev)
 	mlx5_drain_health_wq(dev);
 	devlink_unregister(devlink);
 	mlx5_sriov_disable(pdev, false);
-	mlx5_thermal_uninit(dev);
+	mlx5_hwmon_dev_unregister(dev);
 	mlx5_crdump_disable(dev);
 	mlx5_uninit_one(dev);
 	mlx5_pci_close(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c b/drivers/net/ethernet/mellanox/mlx5/core/thermal.c
deleted file mode 100644
index 52199d39657ed..0000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c
+++ /dev/null
@@ -1,114 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
-// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES.
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/device.h>
-#include <linux/thermal.h>
-#include <linux/err.h>
-#include <linux/mlx5/driver.h>
-#include "mlx5_core.h"
-#include "thermal.h"
-
-#define MLX5_THERMAL_POLL_INT_MSEC	1000
-#define MLX5_THERMAL_NUM_TRIPS		0
-#define MLX5_THERMAL_ASIC_SENSOR_INDEX	0
-
-/* Bit string indicating the writeablility of trip points if any */
-#define MLX5_THERMAL_TRIP_MASK	(BIT(MLX5_THERMAL_NUM_TRIPS) - 1)
-
-struct mlx5_thermal {
-	struct mlx5_core_dev *mdev;
-	struct thermal_zone_device *tzdev;
-};
-
-static int mlx5_thermal_get_mtmp_temp(struct mlx5_core_dev *mdev, u32 id, int *p_temp)
-{
-	u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)] = {};
-	u32 mtmp_in[MLX5_ST_SZ_DW(mtmp_reg)] = {};
-	int err;
-
-	MLX5_SET(mtmp_reg, mtmp_in, sensor_index, id);
-
-	err = mlx5_core_access_reg(mdev, mtmp_in,  sizeof(mtmp_in),
-				   mtmp_out, sizeof(mtmp_out),
-				   MLX5_REG_MTMP, 0, 0);
-
-	if (err)
-		return err;
-
-	*p_temp = MLX5_GET(mtmp_reg, mtmp_out, temperature);
-
-	return 0;
-}
-
-static int mlx5_thermal_get_temp(struct thermal_zone_device *tzdev,
-				 int *p_temp)
-{
-	struct mlx5_thermal *thermal = thermal_zone_device_priv(tzdev);
-	struct mlx5_core_dev *mdev = thermal->mdev;
-	int err;
-
-	err = mlx5_thermal_get_mtmp_temp(mdev, MLX5_THERMAL_ASIC_SENSOR_INDEX, p_temp);
-
-	if (err)
-		return err;
-
-	/* The unit of temp returned is in 0.125 C. The thermal
-	 * framework expects the value in 0.001 C.
-	 */
-	*p_temp *= 125;
-
-	return 0;
-}
-
-static struct thermal_zone_device_ops mlx5_thermal_ops = {
-	.get_temp = mlx5_thermal_get_temp,
-};
-
-int mlx5_thermal_init(struct mlx5_core_dev *mdev)
-{
-	char data[THERMAL_NAME_LENGTH];
-	struct mlx5_thermal *thermal;
-	int err;
-
-	if (!mlx5_core_is_pf(mdev) && !mlx5_core_is_ecpf(mdev))
-		return 0;
-
-	err = snprintf(data, sizeof(data), "mlx5_%s", dev_name(mdev->device));
-	if (err < 0 || err >= sizeof(data)) {
-		mlx5_core_err(mdev, "Failed to setup thermal zone name, %d\n", err);
-		return -EINVAL;
-	}
-
-	thermal = kzalloc(sizeof(*thermal), GFP_KERNEL);
-	if (!thermal)
-		return -ENOMEM;
-
-	thermal->mdev = mdev;
-	thermal->tzdev = thermal_zone_device_register_with_trips(data,
-								 NULL,
-								 MLX5_THERMAL_NUM_TRIPS,
-								 MLX5_THERMAL_TRIP_MASK,
-								 thermal,
-								 &mlx5_thermal_ops,
-								 NULL, 0, MLX5_THERMAL_POLL_INT_MSEC);
-	if (IS_ERR(thermal->tzdev)) {
-		err = PTR_ERR(thermal->tzdev);
-		mlx5_core_err(mdev, "Failed to register thermal zone device (%s) %d\n", data, err);
-		kfree(thermal);
-		return err;
-	}
-
-	mdev->thermal = thermal;
-	return 0;
-}
-
-void mlx5_thermal_uninit(struct mlx5_core_dev *mdev)
-{
-	if (!mdev->thermal)
-		return;
-
-	thermal_zone_device_unregister(mdev->thermal->tzdev);
-	kfree(mdev->thermal);
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/thermal.h b/drivers/net/ethernet/mellanox/mlx5/core/thermal.h
deleted file mode 100644
index 7d752c1221922..0000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/thermal.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
- * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES.
- */
-#ifndef __MLX5_THERMAL_DRIVER_H
-#define __MLX5_THERMAL_DRIVER_H
-
-#if IS_ENABLED(CONFIG_THERMAL)
-int mlx5_thermal_init(struct mlx5_core_dev *mdev);
-void mlx5_thermal_uninit(struct mlx5_core_dev *mdev);
-#else
-static inline int mlx5_thermal_init(struct mlx5_core_dev *mdev)
-{
-	mdev->thermal = NULL;
-	return 0;
-}
-
-static inline void mlx5_thermal_uninit(struct mlx5_core_dev *mdev) { }
-#endif
-
-#endif /* __MLX5_THERMAL_DRIVER_H */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 3e1017d764b7b..e1c7e502a4fc0 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -134,6 +134,7 @@ enum {
 	MLX5_REG_PCAM		 = 0x507f,
 	MLX5_REG_NODE_DESC	 = 0x6001,
 	MLX5_REG_HOST_ENDIANNESS = 0x7004,
+	MLX5_REG_MTCAP		 = 0x9009,
 	MLX5_REG_MTMP		 = 0x900A,
 	MLX5_REG_MCIA		 = 0x9014,
 	MLX5_REG_MFRL		 = 0x9028,
@@ -805,7 +806,7 @@ struct mlx5_core_dev {
 	struct mlx5_rsc_dump    *rsc_dump;
 	u32                      vsc_addr;
 	struct mlx5_hv_vhca	*hv_vhca;
-	struct mlx5_thermal	*thermal;
+	struct mlx5_hwmon	*hwmon;
 	u64			num_block_tc;
 	u64			num_block_ipsec;
 };
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index b3ad6b9852ecb..87fd6f9ed82cd 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10196,7 +10196,9 @@ struct mlx5_ifc_mcam_access_reg_bits {
 	u8         mrtc[0x1];
 	u8         regs_44_to_32[0xd];
 
-	u8         regs_31_to_0[0x20];
+	u8         regs_31_to_10[0x16];
+	u8         mtmp[0x1];
+	u8         regs_8_to_0[0x9];
 };
 
 struct mlx5_ifc_mcam_access_reg_bits1 {
@@ -10949,6 +10951,15 @@ struct mlx5_ifc_mrtc_reg_bits {
 	u8         time_l[0x20];
 };
 
+struct mlx5_ifc_mtcap_reg_bits {
+	u8         reserved_at_0[0x19];
+	u8         sensor_count[0x7];
+
+	u8         reserved_at_20[0x20];
+
+	u8         sensor_map[0x40];
+};
+
 struct mlx5_ifc_mtmp_reg_bits {
 	u8         reserved_at_0[0x14];
 	u8         sensor_index[0xc];
@@ -11036,6 +11047,7 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_mfrl_reg_bits mfrl_reg;
 	struct mlx5_ifc_mtutc_reg_bits mtutc_reg;
 	struct mlx5_ifc_mrtc_reg_bits mrtc_reg;
+	struct mlx5_ifc_mtcap_reg_bits mtcap_reg;
 	struct mlx5_ifc_mtmp_reg_bits mtmp_reg;
 	u8         reserved_at_0[0x60e0];
 };
-- 
GitLab


From 09e0c3bbde901f17837ad5088a13c3985534b860 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:14 +0300
Subject: [PATCH 1034/1806] net/sched: taprio: don't access q->qdiscs[] in
 unoffloaded mode during attach()

This is a simple code transformation with no intended behavior change,
just to make it absolutely clear that q->qdiscs[] is only attached to
the child taprio classes in full offload mode.

Right now we use the q->qdiscs[] variable in taprio_attach() for
software mode too, but that is quite confusing and avoidable. We use
it only to reach the netdev TX queue, but we could as well just use
netdev_get_tx_queue() for that.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-2-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_taprio.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 8c9cfff7fd05c..1cbc7fcd56c0a 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -2145,14 +2145,20 @@ static void taprio_attach(struct Qdisc *sch)
 
 	/* Attach underlying qdisc */
 	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
-		struct Qdisc *qdisc = q->qdiscs[ntx];
+		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx);
 		struct Qdisc *old;
 
 		if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
+			struct Qdisc *qdisc = q->qdiscs[ntx];
+
 			qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
-			old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
+			old = dev_graft_qdisc(dev_queue, qdisc);
 		} else {
-			old = dev_graft_qdisc(qdisc->dev_queue, sch);
+			/* In software mode, attach the root taprio qdisc
+			 * to all netdev TX queues, so that dev_qdisc_enqueue()
+			 * goes through taprio_enqueue().
+			 */
+			old = dev_graft_qdisc(dev_queue, sch);
 			qdisc_refcount_inc(sch);
 		}
 		if (old)
-- 
GitLab


From 25b0d4e4e41fcf0d2f43c431a82d344149e91258 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:15 +0300
Subject: [PATCH 1035/1806] net/sched: taprio: keep child Qdisc refcount
 elevated at 2 in offload mode

Normally, Qdiscs have one reference on them held by their owner and one
held for each TXQ to which they are attached, however this is not the
case with the children of an offloaded taprio. Instead, the taprio qdisc
currently lives in the following fragile equilibrium.

In the software scheduling case, taprio attaches itself (the root Qdisc)
to all TXQs, thus having a refcount of 1 + the number of TX queues. In
this mode, the q->qdiscs[] children are not visible directly to the
Qdisc API. The lifetime of the Qdiscs from this private array lasts
until qdisc_destroy() -> taprio_destroy().

In the fully offloaded case, the root taprio has a refcount of 1, and
all child q->qdiscs[] also have a refcount of 1. The child q->qdiscs[]
are attached to the netdev TXQs directly and thus are visible to the
Qdisc API, however taprio loses a reference to them very early - during
qdisc_graft(parent==NULL) -> taprio_attach(). At that time, taprio frees
the q->qdiscs[] array to not leak memory, but interestingly, it does not
release a reference on these qdiscs because it doesn't effectively own
them - they are created by taprio but owned by the Qdisc core, and will
be freed by qdisc_graft(parent==NULL, new==NULL) -> qdisc_put(old) when
the Qdisc is deleted or when the child Qdisc is replaced with something
else.

My interest is to change this equilibrium such that taprio also owns a
reference on the q->qdiscs[] child Qdiscs for the lifetime of the root
Qdisc, including in full offload mode. I want this because I would like
taprio_leaf(), taprio_dump_class(), taprio_dump_class_stats() to have
insight into q->qdiscs[] for the software scheduling mode - currently
they look at dev_queue->qdisc_sleeping, which is, as mentioned, the same
as the root taprio.

The following set of changes is necessary:
- don't free q->qdiscs[] early in taprio_attach(), free it late in
  taprio_destroy() for consistency with software mode. But:
- currently that's not possible, because taprio doesn't own a reference
  on q->qdiscs[]. So hold that reference - once during the initial
  attach() and once during subsequent graft() calls when the child is
  changed.
- always keep track of the current child in q->qdiscs[], even for full
  offload mode, so that we free in taprio_destroy() what we should, and
  not something stale.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-3-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_taprio.c | 39 +++++++++++++++++++++++++--------------
 1 file changed, 25 insertions(+), 14 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 1cbc7fcd56c0a..7c1fc3dc3e55f 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -2146,30 +2146,31 @@ static void taprio_attach(struct Qdisc *sch)
 	/* Attach underlying qdisc */
 	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
 		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx);
-		struct Qdisc *old;
+		struct Qdisc *old, *dev_queue_qdisc;
 
 		if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
 			struct Qdisc *qdisc = q->qdiscs[ntx];
 
+			/* In offload mode, the root taprio qdisc is bypassed
+			 * and the netdev TX queues see the children directly
+			 */
 			qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
-			old = dev_graft_qdisc(dev_queue, qdisc);
+			dev_queue_qdisc = qdisc;
 		} else {
 			/* In software mode, attach the root taprio qdisc
 			 * to all netdev TX queues, so that dev_qdisc_enqueue()
 			 * goes through taprio_enqueue().
 			 */
-			old = dev_graft_qdisc(dev_queue, sch);
-			qdisc_refcount_inc(sch);
+			dev_queue_qdisc = sch;
 		}
+		old = dev_graft_qdisc(dev_queue, dev_queue_qdisc);
+		/* The qdisc's refcount requires to be elevated once
+		 * for each netdev TX queue it is grafted onto
+		 */
+		qdisc_refcount_inc(dev_queue_qdisc);
 		if (old)
 			qdisc_put(old);
 	}
-
-	/* access to the child qdiscs is not needed in offload mode */
-	if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
-		kfree(q->qdiscs);
-		q->qdiscs = NULL;
-	}
 }
 
 static struct netdev_queue *taprio_queue_get(struct Qdisc *sch,
@@ -2198,13 +2199,23 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl,
 	if (dev->flags & IFF_UP)
 		dev_deactivate(dev);
 
+	/* In offload mode, the child Qdisc is directly attached to the netdev
+	 * TX queue, and thus, we need to keep its refcount elevated in order
+	 * to counteract qdisc_graft()'s call to qdisc_put() once per TX queue.
+	 * However, save the reference to the new qdisc in the private array in
+	 * both software and offload cases, to have an up-to-date reference to
+	 * our children.
+	 */
+	*old = q->qdiscs[cl - 1];
 	if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
-		*old = dev_graft_qdisc(dev_queue, new);
-	} else {
-		*old = q->qdiscs[cl - 1];
-		q->qdiscs[cl - 1] = new;
+		WARN_ON_ONCE(dev_graft_qdisc(dev_queue, new) != *old);
+		if (new)
+			qdisc_refcount_inc(new);
+		if (*old)
+			qdisc_put(*old);
 	}
 
+	q->qdiscs[cl - 1] = new;
 	if (new)
 		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 
-- 
GitLab


From 98766add2d55194be9f7d88628a058ceab3b06e6 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:16 +0300
Subject: [PATCH 1036/1806] net/sched: taprio: try again to report q->qdiscs[]
 to qdisc_leaf()

This is another stab at commit 1461d212ab27 ("net/sched: taprio: make
qdisc_leaf() see the per-netdev-queue pfifo child qdiscs"), later
reverted in commit af7b29b1deaa ("Revert "net/sched: taprio: make
qdisc_leaf() see the per-netdev-queue pfifo child qdiscs"").

I believe that the problems that caused the revert were fixed, and thus,
this change is identical to the original patch.

Its purpose is to properly reject attaching a software taprio child
qdisc to a software taprio parent. Because unoffloaded taprio currently
reports itself (the root Qdisc) as the return value from qdisc_leaf(),
then the process of attaching another taprio as child to a Qdisc class
of the root will just result in a Qdisc_ops :: change() call for the
root. Whereas that's not we want. We want Qdisc_ops :: init() to be
called for the taprio child, in order to give the taprio child a chance
to check whether its sch->parent is TC_H_ROOT or not (and reject this
configuration).

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-4-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_taprio.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 7c1fc3dc3e55f..831e6f3fda2a0 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -2453,12 +2453,14 @@ start_error:
 
 static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl)
 {
-	struct netdev_queue *dev_queue = taprio_queue_get(sch, cl);
+	struct taprio_sched *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned int ntx = cl - 1;
 
-	if (!dev_queue)
+	if (ntx >= dev->num_tx_queues)
 		return NULL;
 
-	return rtnl_dereference(dev_queue->qdisc_sleeping);
+	return q->qdiscs[ntx];
 }
 
 static unsigned long taprio_find(struct Qdisc *sch, u32 classid)
-- 
GitLab


From 6e0ec800c1740372a6bbada0d98e78c2e69ba4a8 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:17 +0300
Subject: [PATCH 1037/1806] net/sched: taprio: delete misleading comment about
 preallocating child qdiscs

As mentioned in commit af7b29b1deaa ("Revert "net/sched: taprio: make
qdisc_leaf() see the per-netdev-queue pfifo child qdiscs"") - unlike
mqprio, taprio doesn't use q->qdiscs[] only as a temporary transport
between Qdisc_ops :: init() and Qdisc_ops :: attach().

Delete the comment, which is just stolen from mqprio, but there, the
usage patterns are a lot different, and this is nothing but confusing.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-5-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_taprio.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 831e6f3fda2a0..d5693bd52e930 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -2099,11 +2099,8 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 		return -EOPNOTSUPP;
 	}
 
-	/* pre-allocate qdisc, attachment can't fail */
-	q->qdiscs = kcalloc(dev->num_tx_queues,
-			    sizeof(q->qdiscs[0]),
+	q->qdiscs = kcalloc(dev->num_tx_queues, sizeof(q->qdiscs[0]),
 			    GFP_KERNEL);
-
 	if (!q->qdiscs)
 		return -ENOMEM;
 
-- 
GitLab


From 665338b2a7a0139337d1f85be65ed16e487f84c1 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:18 +0300
Subject: [PATCH 1038/1806] net/sched: taprio: dump class stats for the actual
 q->qdiscs[]

This makes a difference for the software scheduling mode, where
dev_queue->qdisc_sleeping is the same as the taprio root Qdisc itself,
but when we're talking about what Qdisc and stats get reported for a
traffic class, the root taprio isn't what comes to mind, but q->qdiscs[]
is.

To understand the difference, I've attempted to send 100 packets in
software mode through class 8001:5, and recorded the stats before and
after the change.

Here is before:

$ tc -s class show dev eth0
class taprio 8001:1 root leaf 8001:
 Sent 9400 bytes 100 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:2 root leaf 8001:
 Sent 9400 bytes 100 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:3 root leaf 8001:
 Sent 9400 bytes 100 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:4 root leaf 8001:
 Sent 9400 bytes 100 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:5 root leaf 8001:
 Sent 9400 bytes 100 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:6 root leaf 8001:
 Sent 9400 bytes 100 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:7 root leaf 8001:
 Sent 9400 bytes 100 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:8 root leaf 8001:
 Sent 9400 bytes 100 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0

and here is after:

class taprio 8001:1 root
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:2 root
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:3 root
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:4 root
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:5 root
 Sent 9400 bytes 100 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:6 root
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:7 root
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0
class taprio 8001:8 root leaf 800d:
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
 window_drops 0

The most glaring (and expected) difference is that before, all class
stats reported the global stats, whereas now, they really report just
the counters for that traffic class.

Finally, Pedro Tammela points out that there is a tc selftest which
checks specifically which handle do the child Qdiscs corresponding to
each class have. That's changing here - taprio no longer reports
tcm->tcm_info as the same handle "1:" as itself (the root Qdisc), but 0
(the handle of the default pfifo child Qdiscs). Since iproute2 does not
print a child Qdisc handle of 0, adjust the test's expected output.

Link: https://lore.kernel.org/netdev/3b83fcf6-a5e8-26fb-8c8a-ec34ec4c3342@mojatatu.com/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-6-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_taprio.c                                    | 8 +++-----
 .../selftests/tc-testing/tc-tests/qdiscs/taprio.json      | 2 +-
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index d5693bd52e930..1cb5e41c0ec72 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -2472,11 +2472,11 @@ static unsigned long taprio_find(struct Qdisc *sch, u32 classid)
 static int taprio_dump_class(struct Qdisc *sch, unsigned long cl,
 			     struct sk_buff *skb, struct tcmsg *tcm)
 {
-	struct netdev_queue *dev_queue = taprio_queue_get(sch, cl);
+	struct Qdisc *child = taprio_leaf(sch, cl);
 
 	tcm->tcm_parent = TC_H_ROOT;
 	tcm->tcm_handle |= TC_H_MIN(cl);
-	tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle;
+	tcm->tcm_info = child->handle;
 
 	return 0;
 }
@@ -2486,16 +2486,14 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	__releases(d->lock)
 	__acquires(d->lock)
 {
-	struct netdev_queue *dev_queue = taprio_queue_get(sch, cl);
+	struct Qdisc *child = taprio_leaf(sch, cl);
 	struct tc_taprio_qopt_offload offload = {
 		.cmd = TAPRIO_CMD_QUEUE_STATS,
 		.queue_stats = {
 			.queue = cl - 1,
 		},
 	};
-	struct Qdisc *child;
 
-	child = rtnl_dereference(dev_queue->qdisc_sleeping);
 	if (gnet_stats_copy_basic(d, NULL, &child->bstats, true) < 0 ||
 	    qdisc_qstats_copy(d, child) < 0)
 		return -1;
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
index 08d4861c2e782..860b55df0d6df 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
@@ -104,7 +104,7 @@
         "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 3 map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@0 1@0 base-time 1000000000 sched-entry S 01 300000 flags 0x1 clockid CLOCK_TAI",
         "expExitCode": "0",
         "verifyCmd": "$TC class show dev $ETH",
-        "matchPattern": "class taprio 1:[0-9]+ root leaf 1:",
+        "matchPattern": "class taprio 1:[0-9]+ root",
         "matchCount": "8",
         "teardown": [
             "echo \"1\" > /sys/bus/netdevsim/del_device"
-- 
GitLab


From 40b0425f8ba17c32cf7182975032a3999c364dfc Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:19 +0300
Subject: [PATCH 1039/1806] net: ptp: create a mock-up PTP Hardware Clock
 driver

There are several cases where virtual net devices may benefit from
having a PTP clock, and these have to do with testing. I can see at
least netdevsim and veth as potential users of a common mock-up PTP
hardware clock driver.

The proposed idea is to create an object which emulates PTP clock
operations on top of the unadjustable CLOCK_MONOTONIC_RAW plus a
software-controlled time domain via a timecounter/cyclecounter and then
link that PHC to the netdevsim device.

The driver is fully functional for its intended purpose, and it
successfully passes the PTP selftests.

$ cd tools/testing/selftests/ptp/
$ ./phc.sh /dev/ptp2
TEST: settime                          [ OK ]
TEST: adjtime                          [ OK ]
TEST: adjfreq                          [ OK ]

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-7-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS              |   7 ++
 drivers/ptp/Kconfig      |  11 +++
 drivers/ptp/Makefile     |   1 +
 drivers/ptp/ptp_mock.c   | 175 +++++++++++++++++++++++++++++++++++++++
 include/linux/ptp_mock.h |  38 +++++++++
 5 files changed, 232 insertions(+)
 create mode 100644 drivers/ptp/ptp_mock.c
 create mode 100644 include/linux/ptp_mock.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 6efcd87136829..49f032556cf16 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17170,6 +17170,13 @@ F:	drivers/ptp/*
 F:	include/linux/ptp_cl*
 K:	(?:\b|_)ptp(?:\b|_)
 
+PTP MOCKUP CLOCK SUPPORT
+M:	Vladimir Oltean <vladimir.oltean@nxp.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/ptp/ptp_mock.c
+F:	include/linux/ptp_mock.h
+
 PTP VIRTUAL CLOCK SUPPORT
 M:	Yangbo Lu <yangbo.lu@nxp.com>
 L:	netdev@vger.kernel.org
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 32dff1b4f891b..ed9d97a032f1c 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -155,6 +155,17 @@ config PTP_1588_CLOCK_IDTCM
 	  To compile this driver as a module, choose M here: the module
 	  will be called ptp_clockmatrix.
 
+config PTP_1588_CLOCK_MOCK
+	tristate "Mock-up PTP clock"
+	depends on PTP_1588_CLOCK
+	help
+	  This driver offers a set of PTP clock manipulation operations over
+	  the system monotonic time. It can be used by virtual network device
+	  drivers to emulate PTP capabilities.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called ptp_mock.
+
 config PTP_1588_CLOCK_VMW
 	tristate "VMware virtual PTP clock"
 	depends on ACPI && HYPERVISOR_GUEST && X86
diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile
index 553f18bf3c835..dea0cebd2303e 100644
--- a/drivers/ptp/Makefile
+++ b/drivers/ptp/Makefile
@@ -16,6 +16,7 @@ ptp-qoriq-y				+= ptp_qoriq.o
 ptp-qoriq-$(CONFIG_DEBUG_FS)		+= ptp_qoriq_debugfs.o
 obj-$(CONFIG_PTP_1588_CLOCK_IDTCM)	+= ptp_clockmatrix.o
 obj-$(CONFIG_PTP_1588_CLOCK_IDT82P33)	+= ptp_idt82p33.o
+obj-$(CONFIG_PTP_1588_CLOCK_MOCK)	+= ptp_mock.o
 obj-$(CONFIG_PTP_1588_CLOCK_VMW)	+= ptp_vmw.o
 obj-$(CONFIG_PTP_1588_CLOCK_OCP)	+= ptp_ocp.o
 obj-$(CONFIG_PTP_DFL_TOD)		+= ptp_dfl_tod.o
diff --git a/drivers/ptp/ptp_mock.c b/drivers/ptp/ptp_mock.c
new file mode 100644
index 0000000000000..e7b459c846a2c
--- /dev/null
+++ b/drivers/ptp/ptp_mock.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2023 NXP
+ *
+ * Mock-up PTP Hardware Clock driver for virtual network devices
+ *
+ * Create a PTP clock which offers PTP time manipulation operations
+ * using a timecounter/cyclecounter on top of CLOCK_MONOTONIC_RAW.
+ */
+
+#include <linux/ptp_clock_kernel.h>
+#include <linux/ptp_mock.h>
+#include <linux/timecounter.h>
+
+/* Clamp scaled_ppm between -2,097,152,000 and 2,097,152,000,
+ * and thus "adj" between -68,719,476 and 68,719,476
+ */
+#define MOCK_PHC_MAX_ADJ_PPB		32000000
+/* Timestamps from ktime_get_raw() have 1 ns resolution, so the scale factor
+ * (MULT >> SHIFT) needs to be 1. Pick SHIFT as 31 bits, which translates
+ * MULT(freq 0) into 0x80000000.
+ */
+#define MOCK_PHC_CC_SHIFT		31
+#define MOCK_PHC_CC_MULT		(1 << MOCK_PHC_CC_SHIFT)
+#define MOCK_PHC_FADJ_SHIFT		9
+#define MOCK_PHC_FADJ_DENOMINATOR	15625ULL
+
+/* The largest cycle_delta that timecounter_read_delta() can handle without a
+ * 64-bit overflow during the multiplication with cc->mult, given the max "adj"
+ * we permit, is ~8.3 seconds. Make sure readouts are more frequent than that.
+ */
+#define MOCK_PHC_REFRESH_INTERVAL	(HZ * 5)
+
+#define info_to_phc(d) container_of((d), struct mock_phc, info)
+
+struct mock_phc {
+	struct ptp_clock_info info;
+	struct ptp_clock *clock;
+	struct timecounter tc;
+	struct cyclecounter cc;
+	spinlock_t lock;
+};
+
+static u64 mock_phc_cc_read(const struct cyclecounter *cc)
+{
+	return ktime_get_raw_ns();
+}
+
+static int mock_phc_adjfine(struct ptp_clock_info *info, long scaled_ppm)
+{
+	struct mock_phc *phc = info_to_phc(info);
+	s64 adj;
+
+	adj = (s64)scaled_ppm << MOCK_PHC_FADJ_SHIFT;
+	adj = div_s64(adj, MOCK_PHC_FADJ_DENOMINATOR);
+
+	spin_lock(&phc->lock);
+	timecounter_read(&phc->tc);
+	phc->cc.mult = MOCK_PHC_CC_MULT + adj;
+	spin_unlock(&phc->lock);
+
+	return 0;
+}
+
+static int mock_phc_adjtime(struct ptp_clock_info *info, s64 delta)
+{
+	struct mock_phc *phc = info_to_phc(info);
+
+	spin_lock(&phc->lock);
+	timecounter_adjtime(&phc->tc, delta);
+	spin_unlock(&phc->lock);
+
+	return 0;
+}
+
+static int mock_phc_settime64(struct ptp_clock_info *info,
+			      const struct timespec64 *ts)
+{
+	struct mock_phc *phc = info_to_phc(info);
+	u64 ns = timespec64_to_ns(ts);
+
+	spin_lock(&phc->lock);
+	timecounter_init(&phc->tc, &phc->cc, ns);
+	spin_unlock(&phc->lock);
+
+	return 0;
+}
+
+static int mock_phc_gettime64(struct ptp_clock_info *info, struct timespec64 *ts)
+{
+	struct mock_phc *phc = info_to_phc(info);
+	u64 ns;
+
+	spin_lock(&phc->lock);
+	ns = timecounter_read(&phc->tc);
+	spin_unlock(&phc->lock);
+
+	*ts = ns_to_timespec64(ns);
+
+	return 0;
+}
+
+static long mock_phc_refresh(struct ptp_clock_info *info)
+{
+	struct timespec64 ts;
+
+	mock_phc_gettime64(info, &ts);
+
+	return MOCK_PHC_REFRESH_INTERVAL;
+}
+
+int mock_phc_index(struct mock_phc *phc)
+{
+	return ptp_clock_index(phc->clock);
+}
+EXPORT_SYMBOL_GPL(mock_phc_index);
+
+struct mock_phc *mock_phc_create(struct device *dev)
+{
+	struct mock_phc *phc;
+	int err;
+
+	phc = kzalloc(sizeof(*phc), GFP_KERNEL);
+	if (!phc) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	phc->info = (struct ptp_clock_info) {
+		.owner		= THIS_MODULE,
+		.name		= "Mock-up PTP clock",
+		.max_adj	= MOCK_PHC_MAX_ADJ_PPB,
+		.adjfine	= mock_phc_adjfine,
+		.adjtime	= mock_phc_adjtime,
+		.gettime64	= mock_phc_gettime64,
+		.settime64	= mock_phc_settime64,
+		.do_aux_work	= mock_phc_refresh,
+	};
+
+	phc->cc = (struct cyclecounter) {
+		.read	= mock_phc_cc_read,
+		.mask	= CYCLECOUNTER_MASK(64),
+		.mult	= MOCK_PHC_CC_MULT,
+		.shift	= MOCK_PHC_CC_SHIFT,
+	};
+
+	spin_lock_init(&phc->lock);
+	timecounter_init(&phc->tc, &phc->cc, 0);
+
+	phc->clock = ptp_clock_register(&phc->info, dev);
+	if (IS_ERR(phc->clock)) {
+		err = PTR_ERR(phc->clock);
+		goto out_free_phc;
+	}
+
+	ptp_schedule_worker(phc->clock, MOCK_PHC_REFRESH_INTERVAL);
+
+	return phc;
+
+out_free_phc:
+	kfree(phc);
+out:
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(mock_phc_create);
+
+void mock_phc_destroy(struct mock_phc *phc)
+{
+	ptp_clock_unregister(phc->clock);
+	kfree(phc);
+}
+EXPORT_SYMBOL_GPL(mock_phc_destroy);
+
+MODULE_DESCRIPTION("Mock-up PTP Hardware Clock driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/ptp_mock.h b/include/linux/ptp_mock.h
new file mode 100644
index 0000000000000..72eb401034d93
--- /dev/null
+++ b/include/linux/ptp_mock.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Mock-up PTP Hardware Clock driver for virtual network devices
+ *
+ * Copyright 2023 NXP
+ */
+
+#ifndef _PTP_MOCK_H_
+#define _PTP_MOCK_H_
+
+struct device;
+struct mock_phc;
+
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK_MOCK)
+
+struct mock_phc *mock_phc_create(struct device *dev);
+void mock_phc_destroy(struct mock_phc *phc);
+int mock_phc_index(struct mock_phc *phc);
+
+#else
+
+static inline struct mock_phc *mock_phc_create(struct device *dev)
+{
+	return NULL;
+}
+
+static inline void mock_phc_destroy(struct mock_phc *phc)
+{
+}
+
+static inline int mock_phc_index(struct mock_phc *phc)
+{
+	return -1;
+}
+
+#endif
+
+#endif /* _PTP_MOCK_H_ */
-- 
GitLab


From b63e78fca889e07931ec8f259701718a24e5052e Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:20 +0300
Subject: [PATCH 1040/1806] net: netdevsim: use mock PHC driver

I'd like to make netdevsim offload tc-taprio, but currently, this Qdisc
emits a ETHTOOL_GET_TS_INFO call to the driver to make sure that it has
a PTP clock, so that it is reasonably capable of offloading the schedule.

By using the mock PHC driver, that becomes possible.

Hardware timestamping is not necessary, and netdevsim does not support
packet I/O anyway.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-8-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/Kconfig               |  1 +
 drivers/net/netdevsim/ethtool.c   | 11 +++++++++++
 drivers/net/netdevsim/netdev.c    | 11 ++++++++++-
 drivers/net/netdevsim/netdevsim.h |  2 ++
 4 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 368c6f5b327e8..4953c14947234 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -592,6 +592,7 @@ config NETDEVSIM
 	depends on INET
 	depends on IPV6 || IPV6=n
 	depends on PSAMPLE || PSAMPLE=n
+	depends on PTP_1588_CLOCK_MOCK || PTP_1588_CLOCK_MOCK=n
 	select NET_DEVLINK
 	help
 	  This driver is a developer testing tool and software model that can
diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c
index ffd9f84b66443..bd546d4d26c68 100644
--- a/drivers/net/netdevsim/ethtool.c
+++ b/drivers/net/netdevsim/ethtool.c
@@ -140,6 +140,16 @@ nsim_set_fecparam(struct net_device *dev, struct ethtool_fecparam *fecparam)
 	return 0;
 }
 
+static int nsim_get_ts_info(struct net_device *dev,
+			    struct ethtool_ts_info *info)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	info->phc_index = mock_phc_index(ns->phc);
+
+	return 0;
+}
+
 static const struct ethtool_ops nsim_ethtool_ops = {
 	.supported_coalesce_params	= ETHTOOL_COALESCE_ALL_PARAMS,
 	.get_pause_stats	        = nsim_get_pause_stats,
@@ -153,6 +163,7 @@ static const struct ethtool_ops nsim_ethtool_ops = {
 	.set_channels			= nsim_set_channels,
 	.get_fecparam			= nsim_get_fecparam,
 	.set_fecparam			= nsim_set_fecparam,
+	.get_ts_info			= nsim_get_ts_info,
 };
 
 static void nsim_ethtool_ring_init(struct netdevsim *ns)
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 0c8daeb0d62b9..2a4a0c4065cf4 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -291,13 +291,19 @@ static void nsim_setup(struct net_device *dev)
 
 static int nsim_init_netdevsim(struct netdevsim *ns)
 {
+	struct mock_phc *phc;
 	int err;
 
+	phc = mock_phc_create(&ns->nsim_bus_dev->dev);
+	if (IS_ERR(phc))
+		return PTR_ERR(phc);
+
+	ns->phc = phc;
 	ns->netdev->netdev_ops = &nsim_netdev_ops;
 
 	err = nsim_udp_tunnels_info_create(ns->nsim_dev, ns->netdev);
 	if (err)
-		return err;
+		goto err_phc_destroy;
 
 	rtnl_lock();
 	err = nsim_bpf_init(ns);
@@ -320,6 +326,8 @@ err_ipsec_teardown:
 err_utn_destroy:
 	rtnl_unlock();
 	nsim_udp_tunnels_info_destroy(ns->netdev);
+err_phc_destroy:
+	mock_phc_destroy(ns->phc);
 	return err;
 }
 
@@ -383,6 +391,7 @@ void nsim_destroy(struct netdevsim *ns)
 	rtnl_unlock();
 	if (nsim_dev_port_is_pf(ns->nsim_dev_port))
 		nsim_udp_tunnels_info_destroy(dev);
+	mock_phc_destroy(ns->phc);
 	free_netdev(dev);
 }
 
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 7be98b7dcca96..028c825b86db1 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/netdevice.h>
+#include <linux/ptp_mock.h>
 #include <linux/u64_stats_sync.h>
 #include <net/devlink.h>
 #include <net/udp_tunnel.h>
@@ -93,6 +94,7 @@ struct netdevsim {
 	struct net_device *netdev;
 	struct nsim_dev *nsim_dev;
 	struct nsim_dev_port *nsim_dev_port;
+	struct mock_phc *phc;
 
 	u64 tx_packets;
 	u64 tx_bytes;
-- 
GitLab


From 35da47fe1c4766451def03a1b4f59c6b13a9373c Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:21 +0300
Subject: [PATCH 1041/1806] net: netdevsim: mimic tc-taprio offload

To be able to use netdevsim for tc-testing with an offloaded tc-taprio
schedule, it needs to report a PTP clock (which it now does), and to
accept ndo_setup_tc(TC_SETUP_QDISC_TAPRIO) calls.

Since netdevsim has no packet I/O, this doesn't do anything intelligent,
it only allows taprio offload code paths to go through some level of
automated testing.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-9-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/netdev.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 2a4a0c4065cf4..2eac92f49631f 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -209,6 +209,31 @@ static int nsim_set_vf_link_state(struct net_device *dev, int vf, int state)
 	return 0;
 }
 
+static void nsim_taprio_stats(struct tc_taprio_qopt_stats *stats)
+{
+	stats->window_drops = 0;
+	stats->tx_overruns = 0;
+}
+
+static int nsim_setup_tc_taprio(struct net_device *dev,
+				struct tc_taprio_qopt_offload *offload)
+{
+	int err = 0;
+
+	switch (offload->cmd) {
+	case TAPRIO_CMD_REPLACE:
+	case TAPRIO_CMD_DESTROY:
+		break;
+	case TAPRIO_CMD_STATS:
+		nsim_taprio_stats(&offload->stats);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
 static LIST_HEAD(nsim_block_cb_list);
 
 static int
@@ -217,6 +242,8 @@ nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data)
 	struct netdevsim *ns = netdev_priv(dev);
 
 	switch (type) {
+	case TC_SETUP_QDISC_TAPRIO:
+		return nsim_setup_tc_taprio(dev, type_data);
 	case TC_SETUP_BLOCK:
 		return flow_block_cb_setup_simple(type_data,
 						  &nsim_block_cb_list,
-- 
GitLab


From 355adce3010b9e91a29fc675520fee919639d6ee Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:22 +0300
Subject: [PATCH 1042/1806] selftests/tc-testing: add ptp_mock Kconfig
 dependency

For offloaded tc-taprio testing with netdevsim, the mock-up PHC driver
is used.

Suggested-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-10-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/tc-testing/config | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
index 71706197ba0f8..5aa8705751f0f 100644
--- a/tools/testing/selftests/tc-testing/config
+++ b/tools/testing/selftests/tc-testing/config
@@ -96,10 +96,11 @@ CONFIG_NET_SCH_FIFO=y
 CONFIG_NET_SCH_ETS=m
 CONFIG_NET_SCH_RED=m
 CONFIG_NET_SCH_FQ_PIE=m
-CONFIG_NETDEVSIM=m
 
 #
 ## Network testing
 #
 CONFIG_CAN=m
 CONFIG_ATM=y
+CONFIG_NETDEVSIM=m
+CONFIG_PTP_1588_CLOCK_MOCK=m
-- 
GitLab


From 1890cf08bd9992558bfbe710a008a12209389c9b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:23 +0300
Subject: [PATCH 1043/1806] selftests/tc-testing: test that taprio can only be
 attached as root

Check that the "Can only be attached as root qdisc" error message from
taprio is effective by attempting to attach it to a class of another
taprio qdisc. That operation should fail.

In the bug that was squashed by change "net/sched: taprio: try again to
report q->qdiscs[] to qdisc_leaf()", grafting a child taprio to a root
software taprio would be misinterpreted as a change() to the root
taprio. Catch this by looking at whether the base-time of the root
taprio has changed to follow the base-time of the child taprio,
something which should have absolutely never happened assuming correct
semantics.

Vinicius points out that looking at "base_time" in the tc qdisc show
output is unreliable because user space is in a race with the kernel
applying the setting. So we create a helper bash script which waits
while there is any pending schedule.

Link: https://lore.kernel.org/netdev/87il9w0xx7.fsf@intel.com/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Pedro Tammela <pctammela@mojatatu.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-11-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../tc-testing/taprio_wait_for_admin.sh       | 16 ++++++
 .../tc-testing/tc-tests/qdiscs/taprio.json    | 50 +++++++++++++++++++
 2 files changed, 66 insertions(+)
 create mode 100755 tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh

diff --git a/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh b/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh
new file mode 100755
index 0000000000000..f5335e8ad6b4a
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh
@@ -0,0 +1,16 @@
+#!/bin/bash
+
+TC="$1"; shift
+ETH="$1"; shift
+
+# The taprio architecture changes the admin schedule from a hrtimer and not
+# from process context, so we need to wait in order to make sure that any
+# schedule change actually took place.
+while :; do
+	has_admin="$($TC -j qdisc show dev $ETH root | jq '.[].options | has("admin")')"
+	if [ "$has_admin" = "false" ]; then
+		break;
+	fi
+
+	sleep 1
+done
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
index 860b55df0d6df..f475967c509fb 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
@@ -156,5 +156,55 @@
         "teardown": [
             "echo \"1\" > /sys/bus/netdevsim/del_device"
         ]
+    },
+    {
+        "id": "39b4",
+        "name": "Reject grafting taprio as child qdisc of software taprio",
+        "category": [
+            "qdisc",
+            "taprio"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 8\" > /sys/bus/netdevsim/new_device",
+            "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 clockid CLOCK_TAI",
+            "./taprio_wait_for_admin.sh $TC $ETH"
+        ],
+        "cmdUnderTest": "$TC qdisc replace dev $ETH parent 8001:7 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 200 sched-entry S ff 20000000 clockid CLOCK_TAI",
+        "expExitCode": "2",
+        "verifyCmd": "bash -c \"./taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"",
+        "matchPattern": "0",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $ETH root",
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
+    {
+        "id": "e8a1",
+        "name": "Reject grafting taprio as child qdisc of offloaded taprio",
+        "category": [
+            "qdisc",
+            "taprio"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 8\" > /sys/bus/netdevsim/new_device",
+            "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 flags 0x2",
+            "./taprio_wait_for_admin.sh $TC $ETH"
+        ],
+        "cmdUnderTest": "$TC qdisc replace dev $ETH parent 8001:7 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 200 sched-entry S ff 20000000 flags 0x2",
+        "expExitCode": "2",
+        "verifyCmd": "bash -c \"./taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"",
+        "matchPattern": "0",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $ETH root",
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
     }
 ]
-- 
GitLab


From 29c298d2bc82ccdbd23bf08bbafeb4e874832946 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 7 Aug 2023 22:33:24 +0300
Subject: [PATCH 1044/1806] selftests/tc-testing: verify that a qdisc can be
 grafted onto a taprio class

The reason behind commit af7b29b1deaa ("Revert "net/sched: taprio: make
qdisc_leaf() see the per-netdev-queue pfifo child qdiscs"") was that the
patch it reverted caused a crash when attaching a CBS shaper to one of
the taprio classes. Prevent that from happening again by adding a test
case for it, which now passes correctly in both offload and software
modes.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Pedro Tammela <pctammela@mojatatu.com>
Link: https://lore.kernel.org/r/20230807193324.4128292-12-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../tc-testing/tc-tests/qdiscs/taprio.json    | 50 +++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
index f475967c509fb..0599635c4bc65 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
@@ -206,5 +206,55 @@
             "$TC qdisc del dev $ETH root",
             "echo \"1\" > /sys/bus/netdevsim/del_device"
         ]
+    },
+    {
+        "id": "a7bf",
+        "name": "Graft cbs as child of software taprio",
+        "category": [
+            "qdisc",
+            "taprio",
+            "cbs"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 8\" > /sys/bus/netdevsim/new_device",
+            "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 clockid CLOCK_TAI"
+        ],
+        "cmdUnderTest": "$TC qdisc replace dev $ETH handle 8002: parent 8001:8 cbs idleslope 20000 sendslope -980000 hicredit 30 locredit -1470",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -d qdisc show dev $ETH",
+        "matchPattern": "qdisc cbs 8002: parent 8001:8 hicredit 30 locredit -1470 sendslope -980000 idleslope 20000 offload 0",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $ETH root",
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
+    {
+        "id": "6a83",
+        "name": "Graft cbs as child of offloaded taprio",
+        "category": [
+            "qdisc",
+            "taprio",
+            "cbs"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 8\" > /sys/bus/netdevsim/new_device",
+            "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 flags 0x2"
+        ],
+        "cmdUnderTest": "$TC qdisc replace dev $ETH handle 8002: parent 8001:8 cbs idleslope 20000 sendslope -980000 hicredit 30 locredit -1470",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -d qdisc show dev $ETH",
+        "matchPattern": "qdisc cbs 8002: parent 8001:8 refcnt 2 hicredit 30 locredit -1470 sendslope -980000 idleslope 20000 offload 0",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $ETH root",
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
     }
 ]
-- 
GitLab


From e55c50eac36a704e9e867257f50cd482e8256755 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 1 Aug 2023 23:05:31 -0600
Subject: [PATCH 1045/1806] i40e: Replace one-element array with flex-array
 member in struct i40e_package_header

One-element and zero-length arrays are deprecated. So, replace
one-element array in struct i40e_package_header with flexible-array
member.

The `+ sizeof(u32)` adjustments ensure that there are no differences
in binary output.

Link: https://github.com/KSPP/linux/issues/335
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ddp.c  | 4 ++--
 drivers/net/ethernet/intel/i40e/i40e_type.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
index 969120587cad8..0e72abd178ae3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
@@ -220,7 +220,7 @@ static bool i40e_ddp_is_pkg_hdr_valid(struct net_device *netdev,
 		netdev_err(netdev, "Invalid DDP profile - size is bigger than 4G");
 		return false;
 	}
-	if (size < (sizeof(struct i40e_package_header) +
+	if (size < (sizeof(struct i40e_package_header) + sizeof(u32) +
 		sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) {
 		netdev_err(netdev, "Invalid DDP profile - size is too small.");
 		return false;
@@ -281,7 +281,7 @@ int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size,
 	if (!i40e_ddp_is_pkg_hdr_valid(netdev, pkg_hdr, size))
 		return -EINVAL;
 
-	if (size < (sizeof(struct i40e_package_header) +
+	if (size < (sizeof(struct i40e_package_header) + sizeof(u32) +
 		    sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) {
 		netdev_err(netdev, "Invalid DDP recipe size.");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 5f61546f50d8f..08ad83ee4a439 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1455,7 +1455,7 @@ struct i40e_ddp_version {
 struct i40e_package_header {
 	struct i40e_ddp_version version;
 	u32 segment_count;
-	u32 segment_offset[1];
+	u32 segment_offset[];
 };
 
 /* Generic segment header */
-- 
GitLab


From fbfa49f92484a63574b692069f09cfe9b79ec565 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 1 Aug 2023 23:05:59 -0600
Subject: [PATCH 1046/1806] i40e: Replace one-element array with flex-array
 member in struct i40e_profile_segment

One-element and zero-length arrays are deprecated. So, replace
one-element array in struct i40e_profile_segment with flexible-array
member.

This results in no differences in binary output.

Link: https://github.com/KSPP/linux/issues/335
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Tested-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_type.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 08ad83ee4a439..6cbc3dbf9b03c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1486,7 +1486,7 @@ struct i40e_profile_segment {
 	struct i40e_ddp_version version;
 	char name[I40E_DDP_NAME_SIZE];
 	u32 device_table_count;
-	struct i40e_device_id_entry device_table[1];
+	struct i40e_device_id_entry device_table[];
 };
 
 struct i40e_section_table {
-- 
GitLab


From ff1a724c4f6a693d5e829903d80a13e48cd3e64f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 1 Aug 2023 23:06:30 -0600
Subject: [PATCH 1047/1806] i40e: Replace one-element array with flex-array
 member in struct i40e_section_table

One-element and zero-length arrays are deprecated. So, replace
one-element array in struct i40e_section_table with flexible-array
member.

This results in no differences in binary output.

Link: https://github.com/KSPP/linux/issues/335
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_type.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 6cbc3dbf9b03c..8ad878ff02cf9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1491,7 +1491,7 @@ struct i40e_profile_segment {
 
 struct i40e_section_table {
 	u32 section_count;
-	u32 section_offset[1];
+	u32 section_offset[];
 };
 
 struct i40e_profile_section_header {
-- 
GitLab


From 4bb28b27040bb070477ce9610173e7360b02ba9b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 1 Aug 2023 23:07:06 -0600
Subject: [PATCH 1048/1806] i40e: Replace one-element array with flex-array
 member in struct i40e_profile_aq_section

One-element and zero-length arrays are deprecated. So, replace
one-element array in struct i40e_profile_aq_section with
flexible-array member.

This results in no differences in binary output.

Link: https://github.com/KSPP/linux/issues/335
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_type.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 8ad878ff02cf9..232131bedc3e7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1523,7 +1523,7 @@ struct i40e_profile_aq_section {
 	u16 flags;
 	u8  param[16];
 	u16 datalen;
-	u8  data[1];
+	u8  data[];
 };
 
 struct i40e_profile_info {
-- 
GitLab


From 1fc04a0b973392df5975901f56addc913d2c8f4d Mon Sep 17 00:00:00 2001
From: Shenwei Wang <shenwei.wang@nxp.com>
Date: Mon, 7 Aug 2023 11:07:15 -0500
Subject: [PATCH 1049/1806] net: stmmac: add new mode parameter for
 fix_mac_speed

A mode parameter has been added to the callback function of fix_mac_speed
to indicate the physical layer type.

The mode can be one the following:
	MLO_AN_PHY	- Conventional PHY
	MLO_AN_FIXED	- Fixed-link mode
	MLO_AN_INBAND	- In-band protocol

Signed-off-by: Shenwei Wang <shenwei.wang@nxp.com>
Link: https://lore.kernel.org/r/20230807160716.259072-2-shenwei.wang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c         | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c  | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c     | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c       | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c          | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c     | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c    | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c         | 8 ++++----
 drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c       | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c    | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c       | 2 +-
 include/linux/stmmac.h                                  | 2 +-
 14 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 74c10373cc399..61ebf36da13de 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -178,7 +178,7 @@ static void dwc_qos_remove(struct platform_device *pdev)
 #define AUTO_CAL_STATUS 0x880c
 #define  AUTO_CAL_STATUS_ACTIVE BIT(31)
 
-static void tegra_eqos_fix_speed(void *priv, unsigned int speed)
+static void tegra_eqos_fix_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct tegra_eqos *eqos = priv;
 	unsigned long rate = 125000000;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 645a9454a4904..7c4f3ad88bdcd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -178,7 +178,7 @@ static void imx_dwmac_exit(struct platform_device *pdev, void *priv)
 	/* nothing to do now */
 }
 
-static void imx_dwmac_fix_speed(void *priv, unsigned int speed)
+static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct plat_stmmacenet_data *plat_dat;
 	struct imx_priv_data *dwmac = priv;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
index a5e639ab0b9e7..d352a14f9d483 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
@@ -22,13 +22,13 @@ struct intel_dwmac {
 };
 
 struct intel_dwmac_data {
-	void (*fix_mac_speed)(void *priv, unsigned int speed);
+	void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode);
 	unsigned long ptp_ref_clk_rate;
 	unsigned long tx_clk_rate;
 	bool tx_clk_en;
 };
 
-static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed)
+static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct intel_dwmac *dwmac = priv;
 	unsigned long rate;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index e39406df8516f..9b02007491094 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -257,7 +257,7 @@ static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac)
 	return PTR_ERR_OR_ZERO(gmac->qsgmii_csr);
 }
 
-static void ipq806x_gmac_fix_mac_speed(void *priv, unsigned int speed)
+static void ipq806x_gmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct ipq806x_gmac *gmac = priv;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
index 7aa5e6bc04eba..959f88c6da16f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
@@ -22,7 +22,7 @@ struct meson_dwmac {
 	void __iomem	*reg;
 };
 
-static void meson6_dwmac_fix_mac_speed(void *priv, unsigned int speed)
+static void meson6_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct meson_dwmac *dwmac = priv;
 	unsigned int val;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 5b3df27035ec9..d3bf42d0fceb6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -630,7 +630,7 @@ static int ethqos_configure(struct qcom_ethqos *ethqos)
 	return ethqos->configure_func(ethqos);
 }
 
-static void ethqos_fix_mac_speed(void *priv, unsigned int speed)
+static void ethqos_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct qcom_ethqos *ethqos = priv;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 35789cb549f72..d920a50dd16c7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1785,7 +1785,7 @@ static void rk_gmac_powerdown(struct rk_priv_data *gmac)
 	gmac_clk_enable(gmac, false);
 }
 
-static void rk_fix_speed(void *priv, unsigned int speed)
+static void rk_fix_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct rk_priv_data *bsp_priv = priv;
 	struct device *dev = &bsp_priv->pdev->dev;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 6267bcb60206b..7db176e8691f8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -61,7 +61,7 @@ struct socfpga_dwmac {
 	struct mdio_device *pcs_mdiodev;
 };
 
-static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed)
+static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)priv;
 	void __iomem *splitter_base = dwmac->splitter_base;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
index b1c5f2527c0d0..8926125646945 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
@@ -24,7 +24,7 @@ struct starfive_dwmac {
 	struct clk *clk_tx;
 };
 
-static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed)
+static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct starfive_dwmac *dwmac = priv;
 	unsigned long rate;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index ef03e46694918..0d653bbb931bd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -103,11 +103,11 @@ struct sti_dwmac {
 	struct regmap *regmap;
 	bool gmac_en;
 	u32 speed;
-	void (*fix_retime_src)(void *priv, unsigned int speed);
+	void (*fix_retime_src)(void *priv, unsigned int speed, unsigned int mode);
 };
 
 struct sti_dwmac_of_data {
-	void (*fix_retime_src)(void *priv, unsigned int speed);
+	void (*fix_retime_src)(void *priv, unsigned int speed, unsigned int mode);
 };
 
 static u32 phy_intf_sels[] = {
@@ -135,7 +135,7 @@ static u32 stih4xx_tx_retime_val[] = {
 				 | STIH4XX_ETH_SEL_INTERNAL_NOTEXT_PHYCLK,
 };
 
-static void stih4xx_fix_retime_src(void *priv, u32 spd)
+static void stih4xx_fix_retime_src(void *priv, u32 spd, unsigned int mode)
 {
 	struct sti_dwmac *dwmac = priv;
 	u32 src = dwmac->tx_retime_src;
@@ -187,7 +187,7 @@ static int sti_dwmac_set_mode(struct sti_dwmac *dwmac)
 	val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII;
 	regmap_update_bits(regmap, reg, ENMII_MASK, val);
 
-	dwmac->fix_retime_src(dwmac, dwmac->speed);
+	dwmac->fix_retime_src(dwmac, dwmac->speed, 0);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 50963e91c347a..beceeae579bf1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -72,7 +72,7 @@ static void sun7i_gmac_exit(struct platform_device *pdev, void *priv)
 		regulator_disable(gmac->regulator);
 }
 
-static void sun7i_fix_speed(void *priv, unsigned int speed)
+static void sun7i_fix_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct sunxi_priv_data *gmac = priv;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
index a8731ce0fff09..22d113fb8e09c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
@@ -54,7 +54,7 @@ struct visconti_eth {
 	spinlock_t lock; /* lock to protect register update */
 };
 
-static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed)
+static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
 {
 	struct visconti_eth *dwmac = priv;
 	struct net_device *netdev = dev_get_drvdata(dwmac->dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fcab363d8dfa2..351eca6109e01 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1064,7 +1064,7 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 	priv->speed = speed;
 
 	if (priv->plat->fix_mac_speed)
-		priv->plat->fix_mac_speed(priv->plat->bsp_priv, speed);
+		priv->plat->fix_mac_speed(priv->plat->bsp_priv, speed, mode);
 
 	if (!duplex)
 		ctrl &= ~priv->hw->link.duplex;
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 652404c03944b..784277d666eb5 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -256,7 +256,7 @@ struct plat_stmmacenet_data {
 	u8 tx_sched_algorithm;
 	struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
 	struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES];
-	void (*fix_mac_speed)(void *priv, unsigned int speed);
+	void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode);
 	int (*fix_soc_reset)(void *priv, void __iomem *ioaddr);
 	int (*serdes_powerup)(struct net_device *ndev, void *priv);
 	void (*serdes_powerdown)(struct net_device *ndev, void *priv);
-- 
GitLab


From 4fa6c976158b20eb7da94d35dfe34deec4b2a504 Mon Sep 17 00:00:00 2001
From: Shenwei Wang <shenwei.wang@nxp.com>
Date: Mon, 7 Aug 2023 11:07:16 -0500
Subject: [PATCH 1050/1806] net: stmmac: dwmac-imx: pause the TXC clock in
 fixed-link

When using a fixed-link setup, certain devices like the SJA1105 require a
small pause in the TXC clock line to enable their internal tunable
delay line (TDL).

To satisfy this requirement, this patch temporarily disables the TX clock,
and restarts it after a required period. This provides the required
silent interval on the clock line for SJA1105 to complete the frequency
transition and enable the internal TDLs. This action occurs before the link
is built up, so it does not impact a normal device too. There is no
need to identify if the connected device is an SJA1105 alike or not during
the implementation.

So far we have only enabled this feature on the i.MX93 platform.

Signed-off-by: Shenwei Wang <shenwei.wang@nxp.com>
Reviewed-by: Frank Li <frank.li@nxp.com>
Link: https://lore.kernel.org/r/20230807160716.259072-3-shenwei.wang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwmac-imx.c   | 43 +++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 7c4f3ad88bdcd..535856fffaea9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -31,6 +31,7 @@
 #define GPR_ENET_QOS_RGMII_EN		(0x1 << 21)
 
 #define MX93_GPR_ENET_QOS_INTF_MODE_MASK	GENMASK(3, 0)
+#define MX93_GPR_ENET_QOS_INTF_MASK		GENMASK(3, 1)
 #define MX93_GPR_ENET_QOS_INTF_SEL_MII		(0x0 << 1)
 #define MX93_GPR_ENET_QOS_INTF_SEL_RMII		(0x4 << 1)
 #define MX93_GPR_ENET_QOS_INTF_SEL_RGMII	(0x1 << 1)
@@ -39,6 +40,7 @@
 #define DMA_BUS_MODE			0x00001000
 #define DMA_BUS_MODE_SFT_RESET		(0x1 << 0)
 #define RMII_RESET_SPEED		(0x3 << 14)
+#define CTRL_SPEED_MASK			GENMASK(15, 14)
 
 struct imx_dwmac_ops {
 	u32 addr_width;
@@ -47,6 +49,7 @@ struct imx_dwmac_ops {
 
 	int (*fix_soc_reset)(void *priv, void __iomem *ioaddr);
 	int (*set_intf_mode)(struct plat_stmmacenet_data *plat_dat);
+	void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode);
 };
 
 struct imx_priv_data {
@@ -56,6 +59,7 @@ struct imx_priv_data {
 	struct regmap *intf_regmap;
 	u32 intf_reg_off;
 	bool rmii_refclk_ext;
+	void __iomem *base_addr;
 
 	const struct imx_dwmac_ops *ops;
 	struct plat_stmmacenet_data *plat_dat;
@@ -212,6 +216,41 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod
 		dev_err(dwmac->dev, "failed to set tx rate %lu\n", rate);
 }
 
+static void imx93_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+{
+	struct imx_priv_data *dwmac = priv;
+	unsigned int iface;
+	int ctrl, old_ctrl;
+
+	imx_dwmac_fix_speed(priv, speed, mode);
+
+	if (!dwmac || mode != MLO_AN_FIXED)
+		return;
+
+	if (regmap_read(dwmac->intf_regmap, dwmac->intf_reg_off, &iface))
+		return;
+
+	iface &= MX93_GPR_ENET_QOS_INTF_MASK;
+	if (iface != MX93_GPR_ENET_QOS_INTF_SEL_RGMII)
+		return;
+
+	old_ctrl = readl(dwmac->base_addr + MAC_CTRL_REG);
+	ctrl = old_ctrl & ~CTRL_SPEED_MASK;
+	regmap_update_bits(dwmac->intf_regmap, dwmac->intf_reg_off,
+			   MX93_GPR_ENET_QOS_INTF_MODE_MASK, 0);
+	writel(ctrl, dwmac->base_addr + MAC_CTRL_REG);
+
+	 /* Ensure the settings for CTRL are applied. */
+	readl(dwmac->base_addr + MAC_CTRL_REG);
+
+	usleep_range(10, 20);
+	iface |= MX93_GPR_ENET_QOS_CLK_GEN_EN;
+	regmap_update_bits(dwmac->intf_regmap, dwmac->intf_reg_off,
+			   MX93_GPR_ENET_QOS_INTF_MODE_MASK, iface);
+
+	writel(old_ctrl, dwmac->base_addr + MAC_CTRL_REG);
+}
+
 static int imx_dwmac_mx93_reset(void *priv, void __iomem *ioaddr)
 {
 	struct plat_stmmacenet_data *plat_dat = priv;
@@ -322,6 +361,7 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	plat_dat->fix_mac_speed = imx_dwmac_fix_speed;
 	plat_dat->bsp_priv = dwmac;
 	dwmac->plat_dat = plat_dat;
+	dwmac->base_addr = stmmac_res.addr;
 
 	ret = imx_dwmac_clks_config(dwmac, true);
 	if (ret)
@@ -331,6 +371,8 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_dwmac_init;
 
+	if (dwmac->ops->fix_mac_speed)
+		plat_dat->fix_mac_speed = dwmac->ops->fix_mac_speed;
 	dwmac->plat_dat->fix_soc_reset = dwmac->ops->fix_soc_reset;
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
@@ -368,6 +410,7 @@ static struct imx_dwmac_ops imx93_dwmac_data = {
 	.mac_rgmii_txclk_auto_adj = true,
 	.set_intf_mode = imx93_set_intf_mode,
 	.fix_soc_reset = imx_dwmac_mx93_reset,
+	.fix_mac_speed = imx93_dwmac_fix_speed,
 };
 
 static const struct of_device_id imx_dwmac_match[] = {
-- 
GitLab


From 215c44fa69d7a873e058b2e1c451c12025d94bee Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 8 Aug 2023 10:12:38 +0800
Subject: [PATCH 1051/1806] net: mhi: Remove redundant initialization owner in
 mhi_net_driver

The module_mhi_driver() will set "THIS_MODULE" to driver.owner when
register a mhi_driver driver, so it is redundant initialization to set
driver.owner in the statement. Remove it for clean code.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230808021238.2975585-1-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mhi_net.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/mhi_net.c b/drivers/net/mhi_net.c
index 3d322ac4f6a59..ae169929a9d8e 100644
--- a/drivers/net/mhi_net.c
+++ b/drivers/net/mhi_net.c
@@ -403,7 +403,6 @@ static struct mhi_driver mhi_net_driver = {
 	.id_table = mhi_net_id_table,
 	.driver = {
 		.name = "mhi_net",
-		.owner = THIS_MODULE,
 	},
 };
 
-- 
GitLab


From 7df1f14c04cbb1950e79c19793420f87227c3e80 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 8 Aug 2023 23:04:33 +0200
Subject: [PATCH 1052/1806] led: trig: netdev: Fix requesting offload device

When the netdev trigger is activates, it tries to determine what
device the LED blinks for, and what the current blink mode is.

The documentation for hw_control_get() says:

	 * Return 0 on success, a negative error number on failing parsing the
	 * initial mode. Error from this function is NOT FATAL as the device
	 * may be in a not supported initial state by the attached LED trigger.
	 */

For the Marvell PHY and the Armada 370-rd board, the initial LED blink
mode is not supported by the trigger, so it returns an error. This
resulted in not getting the device the LED is blinking for. As a
result, the device is unknown and offloaded is never performed.

Change to condition to always get the device if offloading is
supported, and reduce the scope of testing for an error from
hw_control_get() to skip setting trigger internal state if there is an
error.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/20230808210436.838995-2-andrew@lunn.ch
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/leds/trigger/ledtrig-netdev.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index c9bc5a91ec832..3d215a556e20a 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -564,15 +564,17 @@ static int netdev_trig_activate(struct led_classdev *led_cdev)
 	/* Check if hw control is active by default on the LED.
 	 * Init already enabled mode in hw control.
 	 */
-	if (supports_hw_control(led_cdev) &&
-	    !led_cdev->hw_control_get(led_cdev, &mode)) {
+	if (supports_hw_control(led_cdev)) {
 		dev = led_cdev->hw_control_get_device(led_cdev);
 		if (dev) {
 			const char *name = dev_name(dev);
 
 			set_device_name(trigger_data, name, strlen(name));
 			trigger_data->hw_control = true;
-			trigger_data->mode = mode;
+
+			rc = led_cdev->hw_control_get(led_cdev, &mode);
+			if (!rc)
+				trigger_data->mode = mode;
 		}
 	}
 
-- 
GitLab


From 1dcc03c9a7a824a31eaaecdfaa03542fb25feb6c Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 8 Aug 2023 23:04:34 +0200
Subject: [PATCH 1053/1806] net: phy: phy_device: Call into the PHY driver to
 set LED offload

Linux LEDs can be requested to perform hardware accelerated blinking
to indicate link, RX, TX etc. Pass the rules for blinking to the PHY
driver, if it implements the ops needed to determine if a given
pattern can be offloaded, to offload it, and what the current offload
is. Additionally implement the op needed to get what device the LED is
for.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/20230808210436.838995-3-andrew@lunn.ch
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 68 ++++++++++++++++++++++++++++++++++++
 include/linux/phy.h          | 33 +++++++++++++++++
 2 files changed, 101 insertions(+)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 3e9909b309385..17cb3e07216ac 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -3020,6 +3020,61 @@ static int phy_led_blink_set(struct led_classdev *led_cdev,
 	return err;
 }
 
+static __maybe_unused struct device *
+phy_led_hw_control_get_device(struct led_classdev *led_cdev)
+{
+	struct phy_led *phyled = to_phy_led(led_cdev);
+	struct phy_device *phydev = phyled->phydev;
+
+	if (phydev->attached_dev)
+		return &phydev->attached_dev->dev;
+	return NULL;
+}
+
+static int __maybe_unused
+phy_led_hw_control_get(struct led_classdev *led_cdev,
+		       unsigned long *rules)
+{
+	struct phy_led *phyled = to_phy_led(led_cdev);
+	struct phy_device *phydev = phyled->phydev;
+	int err;
+
+	mutex_lock(&phydev->lock);
+	err = phydev->drv->led_hw_control_get(phydev, phyled->index, rules);
+	mutex_unlock(&phydev->lock);
+
+	return err;
+}
+
+static int __maybe_unused
+phy_led_hw_control_set(struct led_classdev *led_cdev,
+		       unsigned long rules)
+{
+	struct phy_led *phyled = to_phy_led(led_cdev);
+	struct phy_device *phydev = phyled->phydev;
+	int err;
+
+	mutex_lock(&phydev->lock);
+	err = phydev->drv->led_hw_control_set(phydev, phyled->index, rules);
+	mutex_unlock(&phydev->lock);
+
+	return err;
+}
+
+static __maybe_unused int phy_led_hw_is_supported(struct led_classdev *led_cdev,
+						  unsigned long rules)
+{
+	struct phy_led *phyled = to_phy_led(led_cdev);
+	struct phy_device *phydev = phyled->phydev;
+	int err;
+
+	mutex_lock(&phydev->lock);
+	err = phydev->drv->led_hw_is_supported(phydev, phyled->index, rules);
+	mutex_unlock(&phydev->lock);
+
+	return err;
+}
+
 static void phy_leds_unregister(struct phy_device *phydev)
 {
 	struct phy_led *phyled;
@@ -3057,6 +3112,19 @@ static int of_phy_led(struct phy_device *phydev,
 		cdev->brightness_set_blocking = phy_led_set_brightness;
 	if (phydev->drv->led_blink_set)
 		cdev->blink_set = phy_led_blink_set;
+
+#ifdef CONFIG_LEDS_TRIGGERS
+	if (phydev->drv->led_hw_is_supported &&
+	    phydev->drv->led_hw_control_set &&
+	    phydev->drv->led_hw_control_get) {
+		cdev->hw_control_is_supported = phy_led_hw_is_supported;
+		cdev->hw_control_set = phy_led_hw_control_set;
+		cdev->hw_control_get = phy_led_hw_control_get;
+		cdev->hw_control_trigger = "netdev";
+	}
+
+	cdev->hw_control_get_device = phy_led_hw_control_get_device;
+#endif
 	cdev->max_brightness = 1;
 	init_data.devicename = dev_name(&phydev->mdio.dev);
 	init_data.fwnode = of_fwnode_handle(led);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index b963ce22e7c75..3c1ceedd1b771 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1105,6 +1105,39 @@ struct phy_driver {
 	int (*led_blink_set)(struct phy_device *dev, u8 index,
 			     unsigned long *delay_on,
 			     unsigned long *delay_off);
+	/**
+	 * @led_hw_is_supported: Can the HW support the given rules.
+	 * @dev: PHY device which has the LED
+	 * @index: Which LED of the PHY device
+	 * @rules The core is interested in these rules
+	 *
+	 * Return 0 if yes,  -EOPNOTSUPP if not, or an error code.
+	 */
+	int (*led_hw_is_supported)(struct phy_device *dev, u8 index,
+				   unsigned long rules);
+	/**
+	 * @led_hw_control_set: Set the HW to control the LED
+	 * @dev: PHY device which has the LED
+	 * @index: Which LED of the PHY device
+	 * @rules The rules used to control the LED
+	 *
+	 * Returns 0, or a an error code.
+	 */
+	int (*led_hw_control_set)(struct phy_device *dev, u8 index,
+				  unsigned long rules);
+	/**
+	 * @led_hw_control_get: Get how the HW is controlling the LED
+	 * @dev: PHY device which has the LED
+	 * @index: Which LED of the PHY device
+	 * @rules Pointer to the rules used to control the LED
+	 *
+	 * Set *@rules to how the HW is currently blinking. Returns 0
+	 * on success, or a error code if the current blinking cannot
+	 * be represented in rules, or some other error happens.
+	 */
+	int (*led_hw_control_get)(struct phy_device *dev, u8 index,
+				  unsigned long *rules);
+
 };
 #define to_phy_driver(d) container_of(to_mdio_common_driver(d),		\
 				      struct phy_driver, mdiodrv)
-- 
GitLab


From 460b0b648fab24f576c481424e0de5479ffb9786 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 8 Aug 2023 23:04:35 +0200
Subject: [PATCH 1054/1806] net: phy: marvell: Add support for offloading LED
 blinking

Add the code needed to indicate if a given blinking pattern can be
offloaded, to offload a pattern and to try to return the current
pattern.

Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/20230808210436.838995-4-andrew@lunn.ch
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/marvell.c | 281 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 281 insertions(+)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 43b6cb7255511..eba652a4c1d88 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -2893,6 +2893,272 @@ static int m88e1318_led_blink_set(struct phy_device *phydev, u8 index,
 			       MII_88E1318S_PHY_LED_FUNC, reg);
 }
 
+struct marvell_led_rules {
+	int mode;
+	unsigned long rules;
+};
+
+static const struct marvell_led_rules marvell_led0[] = {
+	{
+		.mode = 0,
+		.rules = BIT(TRIGGER_NETDEV_LINK),
+	},
+	{
+		.mode = 1,
+		.rules = (BIT(TRIGGER_NETDEV_LINK) |
+			  BIT(TRIGGER_NETDEV_RX) |
+			  BIT(TRIGGER_NETDEV_TX)),
+	},
+	{
+		.mode = 3,
+		.rules = (BIT(TRIGGER_NETDEV_RX) |
+			  BIT(TRIGGER_NETDEV_TX)),
+	},
+	{
+		.mode = 4,
+		.rules = (BIT(TRIGGER_NETDEV_RX) |
+			  BIT(TRIGGER_NETDEV_TX)),
+	},
+	{
+		.mode = 5,
+		.rules = BIT(TRIGGER_NETDEV_TX),
+	},
+	{
+		.mode = 6,
+		.rules = BIT(TRIGGER_NETDEV_LINK),
+	},
+	{
+		.mode = 7,
+		.rules = BIT(TRIGGER_NETDEV_LINK_1000),
+	},
+	{
+		.mode = 8,
+		.rules = 0,
+	},
+};
+
+static const struct marvell_led_rules marvell_led1[] = {
+	{
+		.mode = 1,
+		.rules = (BIT(TRIGGER_NETDEV_LINK) |
+			  BIT(TRIGGER_NETDEV_RX) |
+			  BIT(TRIGGER_NETDEV_TX)),
+	},
+	{
+		.mode = 2,
+		.rules = (BIT(TRIGGER_NETDEV_LINK) |
+			  BIT(TRIGGER_NETDEV_RX)),
+	},
+	{
+		.mode = 3,
+		.rules = (BIT(TRIGGER_NETDEV_RX) |
+			  BIT(TRIGGER_NETDEV_TX)),
+	},
+	{
+		.mode = 4,
+		.rules = (BIT(TRIGGER_NETDEV_RX) |
+			  BIT(TRIGGER_NETDEV_TX)),
+	},
+	{
+		.mode = 6,
+		.rules = (BIT(TRIGGER_NETDEV_LINK_100) |
+			  BIT(TRIGGER_NETDEV_LINK_1000)),
+	},
+	{
+		.mode = 7,
+		.rules = BIT(TRIGGER_NETDEV_LINK_100),
+	},
+	{
+		.mode = 8,
+		.rules = 0,
+	},
+};
+
+static const struct marvell_led_rules marvell_led2[] = {
+	{
+		.mode = 0,
+		.rules = BIT(TRIGGER_NETDEV_LINK),
+	},
+	{
+		.mode = 1,
+		.rules = (BIT(TRIGGER_NETDEV_LINK) |
+			  BIT(TRIGGER_NETDEV_RX) |
+			  BIT(TRIGGER_NETDEV_TX)),
+	},
+	{
+		.mode = 3,
+		.rules = (BIT(TRIGGER_NETDEV_RX) |
+			  BIT(TRIGGER_NETDEV_TX)),
+	},
+	{
+		.mode = 4,
+		.rules = (BIT(TRIGGER_NETDEV_RX) |
+			  BIT(TRIGGER_NETDEV_TX)),
+	},
+	{
+		.mode = 5,
+		.rules = BIT(TRIGGER_NETDEV_TX),
+	},
+	{
+		.mode = 6,
+		.rules = (BIT(TRIGGER_NETDEV_LINK_10) |
+			  BIT(TRIGGER_NETDEV_LINK_1000)),
+	},
+	{
+		.mode = 7,
+		.rules = BIT(TRIGGER_NETDEV_LINK_10),
+	},
+	{
+		.mode = 8,
+		.rules = 0,
+	},
+};
+
+static int marvell_find_led_mode(unsigned long rules,
+				 const struct marvell_led_rules *marvell_rules,
+				 int count,
+				 int *mode)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		if (marvell_rules[i].rules == rules) {
+			*mode = marvell_rules[i].mode;
+			return 0;
+		}
+	}
+	return -EOPNOTSUPP;
+}
+
+static int marvell_get_led_mode(u8 index, unsigned long rules, int *mode)
+{
+	int ret;
+
+	switch (index) {
+	case 0:
+		ret = marvell_find_led_mode(rules, marvell_led0,
+					    ARRAY_SIZE(marvell_led0), mode);
+		break;
+	case 1:
+		ret = marvell_find_led_mode(rules, marvell_led1,
+					    ARRAY_SIZE(marvell_led1), mode);
+		break;
+	case 2:
+		ret = marvell_find_led_mode(rules, marvell_led2,
+					    ARRAY_SIZE(marvell_led2), mode);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int marvell_find_led_rules(unsigned long *rules,
+				  const struct marvell_led_rules *marvell_rules,
+				  int count,
+				  int mode)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		if (marvell_rules[i].mode == mode) {
+			*rules = marvell_rules[i].rules;
+			return 0;
+		}
+	}
+	return -EOPNOTSUPP;
+}
+
+static int marvell_get_led_rules(u8 index, unsigned long *rules, int mode)
+{
+	int ret;
+
+	switch (index) {
+	case 0:
+		ret = marvell_find_led_rules(rules, marvell_led0,
+					     ARRAY_SIZE(marvell_led0), mode);
+		break;
+	case 1:
+		ret = marvell_find_led_rules(rules, marvell_led1,
+					     ARRAY_SIZE(marvell_led1), mode);
+		break;
+	case 2:
+		ret = marvell_find_led_rules(rules, marvell_led2,
+					     ARRAY_SIZE(marvell_led2), mode);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+static int m88e1318_led_hw_is_supported(struct phy_device *phydev, u8 index,
+					unsigned long rules)
+{
+	int mode, ret;
+
+	switch (index) {
+	case 0:
+	case 1:
+	case 2:
+		ret = marvell_get_led_mode(index, rules, &mode);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int m88e1318_led_hw_control_set(struct phy_device *phydev, u8 index,
+				       unsigned long rules)
+{
+	int mode, ret, reg;
+
+	switch (index) {
+	case 0:
+	case 1:
+	case 2:
+		ret = marvell_get_led_mode(index, rules, &mode);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	reg = phy_read_paged(phydev, MII_MARVELL_LED_PAGE,
+			     MII_88E1318S_PHY_LED_FUNC);
+	if (reg < 0)
+		return reg;
+
+	reg &= ~(0xf << (4 * index));
+	reg |= mode << (4 * index);
+	return phy_write_paged(phydev, MII_MARVELL_LED_PAGE,
+			       MII_88E1318S_PHY_LED_FUNC, reg);
+}
+
+static int m88e1318_led_hw_control_get(struct phy_device *phydev, u8 index,
+				       unsigned long *rules)
+{
+	int mode, reg;
+
+	if (index > 2)
+		return -EINVAL;
+
+	reg = phy_read_paged(phydev, MII_MARVELL_LED_PAGE,
+			     MII_88E1318S_PHY_LED_FUNC);
+	if (reg < 0)
+		return reg;
+
+	mode = (reg >> (4 * index)) & 0xf;
+
+	return marvell_get_led_rules(index, rules, mode);
+}
+
 static int marvell_probe(struct phy_device *phydev)
 {
 	struct marvell_priv *priv;
@@ -3144,6 +3410,9 @@ static struct phy_driver marvell_drivers[] = {
 		.get_stats = marvell_get_stats,
 		.led_brightness_set = m88e1318_led_brightness_set,
 		.led_blink_set = m88e1318_led_blink_set,
+		.led_hw_is_supported = m88e1318_led_hw_is_supported,
+		.led_hw_control_set = m88e1318_led_hw_control_set,
+		.led_hw_control_get = m88e1318_led_hw_control_get,
 	},
 	{
 		.phy_id = MARVELL_PHY_ID_88E1145,
@@ -3252,6 +3521,9 @@ static struct phy_driver marvell_drivers[] = {
 		.cable_test_get_status = marvell_vct7_cable_test_get_status,
 		.led_brightness_set = m88e1318_led_brightness_set,
 		.led_blink_set = m88e1318_led_blink_set,
+		.led_hw_is_supported = m88e1318_led_hw_is_supported,
+		.led_hw_control_set = m88e1318_led_hw_control_set,
+		.led_hw_control_get = m88e1318_led_hw_control_get,
 	},
 	{
 		.phy_id = MARVELL_PHY_ID_88E1540,
@@ -3280,6 +3552,9 @@ static struct phy_driver marvell_drivers[] = {
 		.cable_test_get_status = marvell_vct7_cable_test_get_status,
 		.led_brightness_set = m88e1318_led_brightness_set,
 		.led_blink_set = m88e1318_led_blink_set,
+		.led_hw_is_supported = m88e1318_led_hw_is_supported,
+		.led_hw_control_set = m88e1318_led_hw_control_set,
+		.led_hw_control_get = m88e1318_led_hw_control_get,
 	},
 	{
 		.phy_id = MARVELL_PHY_ID_88E1545,
@@ -3308,6 +3583,9 @@ static struct phy_driver marvell_drivers[] = {
 		.cable_test_get_status = marvell_vct7_cable_test_get_status,
 		.led_brightness_set = m88e1318_led_brightness_set,
 		.led_blink_set = m88e1318_led_blink_set,
+		.led_hw_is_supported = m88e1318_led_hw_is_supported,
+		.led_hw_control_set = m88e1318_led_hw_control_set,
+		.led_hw_control_get = m88e1318_led_hw_control_get,
 	},
 	{
 		.phy_id = MARVELL_PHY_ID_88E3016,
@@ -3451,6 +3729,9 @@ static struct phy_driver marvell_drivers[] = {
 		.set_tunable = m88e1540_set_tunable,
 		.led_brightness_set = m88e1318_led_brightness_set,
 		.led_blink_set = m88e1318_led_blink_set,
+		.led_hw_is_supported = m88e1318_led_hw_is_supported,
+		.led_hw_control_set = m88e1318_led_hw_control_set,
+		.led_hw_control_get = m88e1318_led_hw_control_get,
 	},
 };
 
-- 
GitLab


From e8fbcc47a8e935f36f044d85f21a99acecbd7bfb Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 8 Aug 2023 23:04:36 +0200
Subject: [PATCH 1055/1806] leds: trig-netdev: Disable offload on deactivation
 of trigger

Ensure that the offloading of blinking is stopped when the trigger is
deactivated. Calling led_set_brightness() is documented as stopping
offload and setting the LED to a constant brightness.

Suggested-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/20230808210436.838995-5-andrew@lunn.ch
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/leds/trigger/ledtrig-netdev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index 3d215a556e20a..42f758880ef8a 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -595,6 +595,8 @@ static void netdev_trig_deactivate(struct led_classdev *led_cdev)
 
 	cancel_delayed_work_sync(&trigger_data->work);
 
+	led_set_brightness(led_cdev, LED_OFF);
+
 	dev_put(trigger_data->net_dev);
 
 	kfree(trigger_data);
-- 
GitLab


From 0c2910ae7fa0caa0f1adc6fed73c23e5593b307b Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Wed, 9 Aug 2023 10:02:38 +0800
Subject: [PATCH 1056/1806] net: stmmac: xgmac: RX queue routing configuration

Commit abe80fdc6ee6 ("net: stmmac: RX queue routing configuration")
introduced RX queue routing to DWMAC4 core.
This patch extend the support to XGMAC2 core.

Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230809020238.1136732-1-0x1207@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwxgmac2.h    | 12 +++++++
 .../ethernet/stmicro/stmmac/dwxgmac2_core.c   | 34 +++++++++++++++++--
 2 files changed, 44 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 153321fe42c31..ce67b178c2d53 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -74,8 +74,20 @@
 #define XGMAC_RXQEN(x)			GENMASK((x) * 2 + 1, (x) * 2)
 #define XGMAC_RXQEN_SHIFT(x)		((x) * 2)
 #define XGMAC_RXQ_CTRL1			0x000000a4
+#define XGMAC_AVCPQ			GENMASK(31, 28)
+#define XGMAC_AVCPQ_SHIFT		28
+#define XGMAC_PTPQ			GENMASK(27, 24)
+#define XGMAC_PTPQ_SHIFT		24
+#define XGMAC_TACPQE			BIT(23)
+#define XGMAC_DCBCPQ			GENMASK(19, 16)
+#define XGMAC_DCBCPQ_SHIFT		16
+#define XGMAC_MCBCQEN			BIT(15)
+#define XGMAC_MCBCQ			GENMASK(11, 8)
+#define XGMAC_MCBCQ_SHIFT		8
 #define XGMAC_RQ			GENMASK(7, 4)
 #define XGMAC_RQ_SHIFT			4
+#define XGMAC_UPQ			GENMASK(3, 0)
+#define XGMAC_UPQ_SHIFT			0
 #define XGMAC_RXQ_CTRL2			0x000000a8
 #define XGMAC_RXQ_CTRL3			0x000000ac
 #define XGMAC_PSRQ(x)			GENMASK((x) * 8 + 7, (x) * 8)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index a0c2ef8bb0ac8..38782662ff986 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -127,6 +127,36 @@ static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio,
 	writel(value, ioaddr + reg);
 }
 
+static void dwxgmac2_rx_queue_routing(struct mac_device_info *hw,
+				      u8 packet, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	static const struct stmmac_rx_routing dwxgmac2_route_possibilities[] = {
+		{ XGMAC_AVCPQ, XGMAC_AVCPQ_SHIFT },
+		{ XGMAC_PTPQ, XGMAC_PTPQ_SHIFT },
+		{ XGMAC_DCBCPQ, XGMAC_DCBCPQ_SHIFT },
+		{ XGMAC_UPQ, XGMAC_UPQ_SHIFT },
+		{ XGMAC_MCBCQ, XGMAC_MCBCQ_SHIFT },
+	};
+
+	value = readl(ioaddr + XGMAC_RXQ_CTRL1);
+
+	/* routing configuration */
+	value &= ~dwxgmac2_route_possibilities[packet - 1].reg_mask;
+	value |= (queue << dwxgmac2_route_possibilities[packet - 1].reg_shift) &
+		 dwxgmac2_route_possibilities[packet - 1].reg_mask;
+
+	/* some packets require extra ops */
+	if (packet == PACKET_AVCPQ)
+		value |= FIELD_PREP(XGMAC_TACPQE, 1);
+	else if (packet == PACKET_MCBCQ)
+		value |= FIELD_PREP(XGMAC_MCBCQEN, 1);
+
+	writel(value, ioaddr + XGMAC_RXQ_CTRL1);
+}
+
 static void dwxgmac2_prog_mtl_rx_algorithms(struct mac_device_info *hw,
 					    u32 rx_alg)
 {
@@ -1463,7 +1493,7 @@ const struct stmmac_ops dwxgmac210_ops = {
 	.rx_queue_enable = dwxgmac2_rx_queue_enable,
 	.rx_queue_prio = dwxgmac2_rx_queue_prio,
 	.tx_queue_prio = dwxgmac2_tx_queue_prio,
-	.rx_queue_routing = NULL,
+	.rx_queue_routing = dwxgmac2_rx_queue_routing,
 	.prog_mtl_rx_algorithms = dwxgmac2_prog_mtl_rx_algorithms,
 	.prog_mtl_tx_algorithms = dwxgmac2_prog_mtl_tx_algorithms,
 	.set_mtl_tx_queue_weight = dwxgmac2_set_mtl_tx_queue_weight,
@@ -1524,7 +1554,7 @@ const struct stmmac_ops dwxlgmac2_ops = {
 	.rx_queue_enable = dwxlgmac2_rx_queue_enable,
 	.rx_queue_prio = dwxgmac2_rx_queue_prio,
 	.tx_queue_prio = dwxgmac2_tx_queue_prio,
-	.rx_queue_routing = NULL,
+	.rx_queue_routing = dwxgmac2_rx_queue_routing,
 	.prog_mtl_rx_algorithms = dwxgmac2_prog_mtl_rx_algorithms,
 	.prog_mtl_tx_algorithms = dwxgmac2_prog_mtl_tx_algorithms,
 	.set_mtl_tx_queue_weight = dwxgmac2_set_mtl_tx_queue_weight,
-- 
GitLab


From 4a8d287909c905107d88a9835141ad592aedae75 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 9 Aug 2023 21:49:43 +0800
Subject: [PATCH 1057/1806] net: caif: Remove unused declaration
 cfsrvl_ctrlcmd()

Commit 43e369210108 ("caif: Move refcount from service layer to sock and dev.")
declared but never implemented this.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230809134943.37844-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/caif/cfsrvl.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/include/net/caif/cfsrvl.h b/include/net/caif/cfsrvl.h
index bd5440977f7f6..5ee7b322e18b4 100644
--- a/include/net/caif/cfsrvl.h
+++ b/include/net/caif/cfsrvl.h
@@ -33,9 +33,6 @@ struct cflayer *cfrfml_create(u8 linkid, struct dev_info *dev_info,
 				int mtu_size);
 struct cflayer *cfdbgl_create(u8 linkid, struct dev_info *dev_info);
 
-void cfsrvl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
-		     int phyid);
-
 bool cfsrvl_phyid_match(struct cflayer *layer, int phyid);
 
 void cfsrvl_init(struct cfsrvl *service,
-- 
GitLab


From afa2420cff5448eb225e88543e01b0b34b9a43cd Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 9 Aug 2023 22:23:23 +0800
Subject: [PATCH 1058/1806] sctp: Remove unused declaration
 sctp_backlog_migrate()

Commit 61c9fed41638 ("[SCTP]: A better solution to fix the race between sctp_peeloff()
and sctp_rcv().") removed the implementation but left declaration in place. Remove it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Acked-by: Xin Long <lucien.xin@gmail.com>
Link: https://lore.kernel.org/r/20230809142323.9428-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sctp/sctp.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 2a67100b2a178..a2310fa995f64 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -148,8 +148,6 @@ void sctp_icmp_redirect(struct sock *, struct sctp_transport *,
 void sctp_icmp_proto_unreachable(struct sock *sk,
 				 struct sctp_association *asoc,
 				 struct sctp_transport *t);
-void sctp_backlog_migrate(struct sctp_association *assoc,
-			  struct sock *oldsk, struct sock *newsk);
 int sctp_transport_hashtable_init(void);
 void sctp_transport_hashtable_destroy(void);
 int sctp_hash_transport(struct sctp_transport *t);
-- 
GitLab


From 5604ac35cb6ec34ad608008ba851568c385fd3f4 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Thu, 10 Aug 2023 09:46:33 +0800
Subject: [PATCH 1059/1806] net: ethernet: 8390: ne2k-pci: use
 module_pci_driver() macro

The driver init/exit() function don't do anything special, it
can use the module_pci_driver() macro to eliminate boilerplate
code.

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Link: https://lore.kernel.org/r/20230810014633.3084355-1-yangyingliang@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/8390/ne2k-pci.c | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/8390/ne2k-pci.c b/drivers/net/ethernet/8390/ne2k-pci.c
index 2c6bd36d2f313..65f56a98c0a06 100644
--- a/drivers/net/ethernet/8390/ne2k-pci.c
+++ b/drivers/net/ethernet/8390/ne2k-pci.c
@@ -731,18 +731,4 @@ static struct pci_driver ne2k_driver = {
 	.id_table	= ne2k_pci_tbl,
 	.driver.pm	= &ne2k_pci_pm_ops,
 };
-
-
-static int __init ne2k_pci_init(void)
-{
-	return pci_register_driver(&ne2k_driver);
-}
-
-
-static void __exit ne2k_pci_cleanup(void)
-{
-	pci_unregister_driver(&ne2k_driver);
-}
-
-module_init(ne2k_pci_init);
-module_exit(ne2k_pci_cleanup);
+module_pci_driver(ne2k_driver);
-- 
GitLab


From 6231e47b6fadf42da2e7a45b8272e80aed53c444 Mon Sep 17 00:00:00 2001
From: Tahsin Erdogan <trdgn@amazon.com>
Date: Wed, 9 Aug 2023 09:47:52 -0700
Subject: [PATCH 1060/1806] tun: avoid high-order page allocation for packet
 header

When gso.hdr_len is zero and a packet is transmitted via write() or
writev(), all payload is treated as header which requires a contiguous
memory allocation. This allocation request is harder to satisfy, and may
even fail if there is enough fragmentation.

Note that sendmsg() code path limits the linear copy length, so this change
makes write()/writev() and sendmsg() paths more consistent.

Signed-off-by: Tahsin Erdogan <trdgn@amazon.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20230809164753.2247594-1-trdgn@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tun.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a057654488031..d4bd76297a2aa 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1523,7 +1523,7 @@ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
 	int err;
 
 	/* Under a page?  Don't bother with paged skb. */
-	if (prepad + len < PAGE_SIZE || !linear)
+	if (prepad + len < PAGE_SIZE)
 		linear = len;
 
 	if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
@@ -1840,6 +1840,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			 */
 			zerocopy = false;
 		} else {
+			if (!linear)
+				linear = min_t(size_t, good_linear, copylen);
+
 			skb = tun_alloc_skb(tfile, align, copylen, linear,
 					    noblock);
 		}
-- 
GitLab


From 7a1c38215820edfcd7c3a2523f4fd385f4e482d6 Mon Sep 17 00:00:00 2001
From: Sergei Antonov <saproj@gmail.com>
Date: Tue, 8 Aug 2023 15:43:07 +0300
Subject: [PATCH 1061/1806] net: ftmac100: add multicast filtering possibility

If netdev_mc_count() is not zero and not IFF_ALLMULTI, filter
incoming multicast packets. The chip has a Multicast Address Hash Table
for allowed multicast addresses, so we fill it.

Implement .ndo_set_rx_mode and recalculate multicast hash table. Also
observe change of IFF_PROMISC and IFF_ALLMULTI netdev flags.

Signed-off-by: Sergei Antonov <saproj@gmail.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/faraday/ftmac100.c | 50 ++++++++++++++++++++++---
 1 file changed, 45 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c
index 139fe66f8bcd2..183069581bc02 100644
--- a/drivers/net/ethernet/faraday/ftmac100.c
+++ b/drivers/net/ethernet/faraday/ftmac100.c
@@ -149,6 +149,40 @@ static void ftmac100_set_mac(struct ftmac100 *priv, const unsigned char *mac)
 	iowrite32(laddr, priv->base + FTMAC100_OFFSET_MAC_LADR);
 }
 
+static void ftmac100_setup_mc_ht(struct ftmac100 *priv)
+{
+	struct netdev_hw_addr *ha;
+	u64 maht = 0; /* Multicast Address Hash Table */
+
+	netdev_for_each_mc_addr(ha, priv->netdev) {
+		u32 hash = ether_crc(ETH_ALEN, ha->addr) >> 26;
+
+		maht |= BIT_ULL(hash);
+	}
+
+	iowrite32(lower_32_bits(maht), priv->base + FTMAC100_OFFSET_MAHT0);
+	iowrite32(upper_32_bits(maht), priv->base + FTMAC100_OFFSET_MAHT1);
+}
+
+static void ftmac100_set_rx_bits(struct ftmac100 *priv, unsigned int *maccr)
+{
+	struct net_device *netdev = priv->netdev;
+
+	/* Clear all */
+	*maccr &= ~(FTMAC100_MACCR_RCV_ALL | FTMAC100_MACCR_RX_MULTIPKT |
+		   FTMAC100_MACCR_HT_MULTI_EN);
+
+	/* Set the requested bits */
+	if (netdev->flags & IFF_PROMISC)
+		*maccr |= FTMAC100_MACCR_RCV_ALL;
+	if (netdev->flags & IFF_ALLMULTI)
+		*maccr |= FTMAC100_MACCR_RX_MULTIPKT;
+	else if (netdev_mc_count(netdev)) {
+		*maccr |= FTMAC100_MACCR_HT_MULTI_EN;
+		ftmac100_setup_mc_ht(priv);
+	}
+}
+
 #define MACCR_ENABLE_ALL	(FTMAC100_MACCR_XMT_EN	| \
 				 FTMAC100_MACCR_RCV_EN	| \
 				 FTMAC100_MACCR_XDMA_EN	| \
@@ -182,11 +216,7 @@ static int ftmac100_start_hw(struct ftmac100 *priv)
 	if (netdev->mtu > ETH_DATA_LEN)
 		maccr |= FTMAC100_MACCR_RX_FTL;
 
-	/* Add other bits as needed */
-	if (netdev->flags & IFF_PROMISC)
-		maccr |= FTMAC100_MACCR_RCV_ALL;
-	if (netdev->flags & IFF_ALLMULTI)
-		maccr |= FTMAC100_MACCR_RX_MULTIPKT;
+	ftmac100_set_rx_bits(priv, &maccr);
 
 	iowrite32(maccr, priv->base + FTMAC100_OFFSET_MACCR);
 	return 0;
@@ -1067,6 +1097,15 @@ static int ftmac100_change_mtu(struct net_device *netdev, int mtu)
 	return 0;
 }
 
+static void ftmac100_set_rx_mode(struct net_device *netdev)
+{
+	struct ftmac100 *priv = netdev_priv(netdev);
+	unsigned int maccr = ioread32(priv->base + FTMAC100_OFFSET_MACCR);
+
+	ftmac100_set_rx_bits(priv, &maccr);
+	iowrite32(maccr, priv->base + FTMAC100_OFFSET_MACCR);
+}
+
 static const struct net_device_ops ftmac100_netdev_ops = {
 	.ndo_open		= ftmac100_open,
 	.ndo_stop		= ftmac100_stop,
@@ -1075,6 +1114,7 @@ static const struct net_device_ops ftmac100_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_eth_ioctl		= ftmac100_do_ioctl,
 	.ndo_change_mtu		= ftmac100_change_mtu,
+	.ndo_set_rx_mode	= ftmac100_set_rx_mode,
 };
 
 /******************************************************************************
-- 
GitLab


From 12aa0a3b93f3adf61b6f7937c3aac8585ced3fca Mon Sep 17 00:00:00 2001
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: Wed, 9 Aug 2023 12:10:39 +0530
Subject: [PATCH 1062/1806] octeontx2-af: Harden rule validation.

Accept TC offload classifier rule only if SPI field
can be extracted by HW.

Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index 5c8f9fc15ff89..237f82082ebe5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -580,7 +580,9 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf)
 		if (!npc_check_field(rvu, blkaddr, NPC_LB, intf))
 			*features &= ~BIT_ULL(NPC_OUTER_VID);
 
-	if (*features & (BIT_ULL(NPC_IPPROTO_AH) | BIT_ULL(NPC_IPPROTO_ESP)))
+	/* Set SPI flag only if AH/ESP and IPSEC_SPI are in the key */
+	if (npc_check_field(rvu, blkaddr, NPC_IPSEC_SPI, intf) &&
+	    (*features & (BIT_ULL(NPC_IPPROTO_ESP) | BIT_ULL(NPC_IPPROTO_AH))))
 		*features |= BIT_ULL(NPC_IPSEC_SPI);
 
 	/* for vlan ethertypes corresponding layer type should be in the key */
-- 
GitLab


From a20b4c5f3a0ed257b9c0642bb935e3de2e23bce8 Mon Sep 17 00:00:00 2001
From: Sathesh Edara <sedara@marvell.com>
Date: Wed, 9 Aug 2023 04:29:33 -0700
Subject: [PATCH 1063/1806] octeon_ep: Add control plane host and firmware
 versions.

Implement control plane mailbox versions for host and firmware.
Versions are published in info area of control mailbox bar4
memory structure.Firmware will publish minimum and maximum
supported versions.Control plane mailbox apis will check for
firmware version before sending any control commands to firmware.
Notifications from firmware will similarly be checked for host
version compatibility.

Signed-off-by: Sathesh Edara <sedara@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../marvell/octeon_ep/octep_cp_version.h      | 11 ++++++
 .../marvell/octeon_ep/octep_ctrl_mbox.c       |  9 ++++-
 .../marvell/octeon_ep/octep_ctrl_mbox.h       |  6 +++
 .../marvell/octeon_ep/octep_ctrl_net.c        | 37 ++++++++++++++++++-
 .../marvell/octeon_ep/octep_ctrl_net.h        |  4 ++
 5 files changed, 64 insertions(+), 3 deletions(-)
 create mode 100644 drivers/net/ethernet/marvell/octeon_ep/octep_cp_version.h

diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_cp_version.h b/drivers/net/ethernet/marvell/octeon_ep/octep_cp_version.h
new file mode 100644
index 0000000000000..0c741e752db65
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_cp_version.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2022 Marvell.
+ */
+#ifndef __OCTEP_CP_VERSION_H__
+#define __OCTEP_CP_VERSION_H__
+
+#define OCTEP_CP_VERSION(a, b, c)	((((a) & 0xff) << 16) + \
+					 (((b) & 0xff) << 8) + \
+					  ((c) & 0xff))
+
+#endif /* __OCTEP_CP_VERSION_H__ */
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c
index dab61cc1acb57..9d53c1402cb4c 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c
@@ -37,7 +37,9 @@
 
 #define OCTEP_CTRL_MBOX_INFO_MAGIC_NUM(m)	(m)
 #define OCTEP_CTRL_MBOX_INFO_BARMEM_SZ(m)	((m) + 8)
+#define OCTEP_CTRL_MBOX_INFO_HOST_VERSION(m)   ((m) + 16)
 #define OCTEP_CTRL_MBOX_INFO_HOST_STATUS(m)	((m) + 24)
+#define OCTEP_CTRL_MBOX_INFO_FW_VERSION(m)     ((m) + 136)
 #define OCTEP_CTRL_MBOX_INFO_FW_STATUS(m)	((m) + 144)
 
 #define OCTEP_CTRL_MBOX_H2FQ_INFO(m)	((m) + OCTEP_CTRL_MBOX_INFO_SZ)
@@ -71,7 +73,7 @@ static u32 octep_ctrl_mbox_circq_depth(u32 pi, u32 ci, u32 sz)
 
 int octep_ctrl_mbox_init(struct octep_ctrl_mbox *mbox)
 {
-	u64 magic_num, status;
+	u64 magic_num, status, fw_versions;
 
 	if (!mbox)
 		return -EINVAL;
@@ -93,6 +95,9 @@ int octep_ctrl_mbox_init(struct octep_ctrl_mbox *mbox)
 		return -EINVAL;
 	}
 
+	fw_versions = readq(OCTEP_CTRL_MBOX_INFO_FW_VERSION(mbox->barmem));
+	mbox->min_fw_version = ((fw_versions & 0xffffffff00000000ull) >> 32);
+	mbox->max_fw_version = (fw_versions & 0xffffffff);
 	mbox->barmem_sz = readl(OCTEP_CTRL_MBOX_INFO_BARMEM_SZ(mbox->barmem));
 
 	writeq(OCTEP_CTRL_MBOX_STATUS_INIT,
@@ -113,6 +118,7 @@ int octep_ctrl_mbox_init(struct octep_ctrl_mbox *mbox)
 			  OCTEP_CTRL_MBOX_TOTAL_INFO_SZ +
 			  mbox->h2fq.sz;
 
+	writeq(mbox->version, OCTEP_CTRL_MBOX_INFO_HOST_VERSION(mbox->barmem));
 	/* ensure ready state is seen after everything is initialized */
 	wmb();
 	writeq(OCTEP_CTRL_MBOX_STATUS_READY,
@@ -258,6 +264,7 @@ int octep_ctrl_mbox_uninit(struct octep_ctrl_mbox *mbox)
 	if (!mbox->barmem)
 		return -EINVAL;
 
+	writeq(0, OCTEP_CTRL_MBOX_INFO_HOST_VERSION(mbox->barmem));
 	writeq(OCTEP_CTRL_MBOX_STATUS_INVALID,
 	       OCTEP_CTRL_MBOX_INFO_HOST_STATUS(mbox->barmem));
 	/* ensure uninit state is written before uninitialization */
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h
index 9c4ff0fba6a05..7f8135788efcd 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h
@@ -121,6 +121,8 @@ struct octep_ctrl_mbox_q {
 };
 
 struct octep_ctrl_mbox {
+	/* control plane version */
+	u64 version;
 	/* size of bar memory */
 	u32 barmem_sz;
 	/* pointer to BAR memory */
@@ -133,6 +135,10 @@ struct octep_ctrl_mbox {
 	struct mutex h2fq_lock;
 	/* lock for f2hq */
 	struct mutex f2hq_lock;
+	/* Min control plane version supported by firmware */
+	u32 min_fw_version;
+	/* Max control plane version supported by firmware */
+	u32 max_fw_version;
 };
 
 /* Initialize control mbox.
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c
index 1cc6af2feb38a..4c6d91a8c83e7 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c
@@ -14,6 +14,9 @@
 #include "octep_main.h"
 #include "octep_ctrl_net.h"
 
+/* Control plane version */
+#define OCTEP_CP_VERSION_CURRENT	OCTEP_CP_VERSION(1, 0, 0)
+
 static const u32 req_hdr_sz = sizeof(union octep_ctrl_net_req_hdr);
 static const u32 mtu_sz = sizeof(struct octep_ctrl_net_h2f_req_cmd_mtu);
 static const u32 mac_sz = sizeof(struct octep_ctrl_net_h2f_req_cmd_mac);
@@ -21,6 +24,18 @@ static const u32 state_sz = sizeof(struct octep_ctrl_net_h2f_req_cmd_state);
 static const u32 link_info_sz = sizeof(struct octep_ctrl_net_link_info);
 static atomic_t ctrl_net_msg_id;
 
+/* Control plane version in which OCTEP_CTRL_NET_H2F_CMD was added */
+static const u32 octep_ctrl_net_h2f_cmd_versions[OCTEP_CTRL_NET_H2F_CMD_MAX] = {
+	[OCTEP_CTRL_NET_H2F_CMD_INVALID ... OCTEP_CTRL_NET_H2F_CMD_LINK_INFO] =
+	 OCTEP_CP_VERSION(1, 0, 0)
+};
+
+/* Control plane version in which OCTEP_CTRL_NET_F2H_CMD was added */
+static const u32 octep_ctrl_net_f2h_cmd_versions[OCTEP_CTRL_NET_F2H_CMD_MAX] = {
+	[OCTEP_CTRL_NET_F2H_CMD_INVALID ... OCTEP_CTRL_NET_F2H_CMD_LINK_STATUS] =
+	 OCTEP_CP_VERSION(1, 0, 0)
+};
+
 static void init_send_req(struct octep_ctrl_mbox_msg *msg, void *buf,
 			  u16 sz, int vfid)
 {
@@ -41,7 +56,13 @@ static int octep_send_mbox_req(struct octep_device *oct,
 			       struct octep_ctrl_net_wait_data *d,
 			       bool wait_for_response)
 {
-	int err, ret;
+	int err, ret, cmd;
+
+	/* check if firmware is compatible for this request */
+	cmd = d->data.req.hdr.s.cmd;
+	if (octep_ctrl_net_h2f_cmd_versions[cmd] > oct->ctrl_mbox.max_fw_version ||
+	    octep_ctrl_net_h2f_cmd_versions[cmd] < oct->ctrl_mbox.min_fw_version)
+		return -EOPNOTSUPP;
 
 	err = octep_ctrl_mbox_send(&oct->ctrl_mbox, &d->msg);
 	if (err < 0)
@@ -84,12 +105,16 @@ int octep_ctrl_net_init(struct octep_device *oct)
 
 	/* Initialize control mbox */
 	ctrl_mbox = &oct->ctrl_mbox;
+	ctrl_mbox->version = OCTEP_CP_VERSION_CURRENT;
 	ctrl_mbox->barmem = CFG_GET_CTRL_MBOX_MEM_ADDR(oct->conf);
 	ret = octep_ctrl_mbox_init(ctrl_mbox);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to initialize control mbox\n");
 		return ret;
 	}
+	dev_info(&pdev->dev, "Control plane versions host: %llx, firmware: %x:%x\n",
+		 ctrl_mbox->version, ctrl_mbox->min_fw_version,
+		 ctrl_mbox->max_fw_version);
 	oct->ctrl_mbox_ifstats_offset = ctrl_mbox->barmem_sz;
 
 	return 0;
@@ -273,9 +298,17 @@ static int process_mbox_notify(struct octep_device *oct,
 {
 	struct net_device *netdev = oct->netdev;
 	struct octep_ctrl_net_f2h_req *req;
+	int cmd;
 
 	req = (struct octep_ctrl_net_f2h_req *)msg->sg_list[0].msg;
-	switch (req->hdr.s.cmd) {
+	cmd = req->hdr.s.cmd;
+
+	/* check if we support this command */
+	if (octep_ctrl_net_f2h_cmd_versions[cmd] > OCTEP_CP_VERSION_CURRENT ||
+	    octep_ctrl_net_f2h_cmd_versions[cmd] < OCTEP_CP_VERSION_CURRENT)
+		return -EOPNOTSUPP;
+
+	switch (cmd) {
 	case OCTEP_CTRL_NET_F2H_CMD_LINK_STATUS:
 		if (netif_running(netdev)) {
 			if (req->link.state) {
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h
index 37880dd791164..1c2ef4ee31d91 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h
@@ -7,6 +7,8 @@
 #ifndef __OCTEP_CTRL_NET_H__
 #define __OCTEP_CTRL_NET_H__
 
+#include "octep_cp_version.h"
+
 #define OCTEP_CTRL_NET_INVALID_VFID	(-1)
 
 /* Supported commands */
@@ -39,12 +41,14 @@ enum octep_ctrl_net_h2f_cmd {
 	OCTEP_CTRL_NET_H2F_CMD_LINK_STATUS,
 	OCTEP_CTRL_NET_H2F_CMD_RX_STATE,
 	OCTEP_CTRL_NET_H2F_CMD_LINK_INFO,
+	OCTEP_CTRL_NET_H2F_CMD_MAX
 };
 
 /* Supported fw to host commands */
 enum octep_ctrl_net_f2h_cmd {
 	OCTEP_CTRL_NET_F2H_CMD_INVALID = 0,
 	OCTEP_CTRL_NET_F2H_CMD_LINK_STATUS,
+	OCTEP_CTRL_NET_F2H_CMD_MAX
 };
 
 union octep_ctrl_net_req_hdr {
-- 
GitLab


From ac3899c6229649737b9d5cb86e417c98243883dc Mon Sep 17 00:00:00 2001
From: Shradha Gupta <shradhagupta@linux.microsoft.com>
Date: Wed, 9 Aug 2023 21:15:22 -0700
Subject: [PATCH 1064/1806] net: mana: Add gdma stats to ethtool output for
 mana

Extended performance counter stats in 'ethtool -S <interface>'
for MANA VF to include GDMA tx LSO packets and bytes count.

Tested-on: Ubuntu22
Testcases:
1. LISA testcase:
PERF-NETWORK-TCP-THROUGHPUT-MULTICONNECTION-NTTTCP-Synthetic
2. LISA testcase:
PERF-NETWORK-TCP-THROUGHPUT-MULTICONNECTION-NTTTCP-SRIOV
3. Validated the GDMA stat packets and byte counters
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 40 +++++++++
 .../ethernet/microsoft/mana/mana_ethtool.c    | 15 ++++
 include/net/mana/mana.h                       | 87 +++++++++++++++++++
 3 files changed, 142 insertions(+)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 48f330d592846..4a16ebff3d1d5 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -2295,6 +2295,46 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx,
 	return 0;
 }
 
+void mana_query_gf_stats(struct mana_port_context *apc)
+{
+	struct mana_query_gf_stat_resp resp = {};
+	struct mana_query_gf_stat_req req = {};
+	struct net_device *ndev = apc->ndev;
+	int err;
+
+	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT,
+			     sizeof(req), sizeof(resp));
+	req.req_stats = STATISTICS_FLAGS_HC_TX_BYTES |
+			STATISTICS_FLAGS_HC_TX_UCAST_PACKETS |
+			STATISTICS_FLAGS_HC_TX_UCAST_BYTES |
+			STATISTICS_FLAGS_HC_TX_MCAST_PACKETS |
+			STATISTICS_FLAGS_HC_TX_MCAST_BYTES |
+			STATISTICS_FLAGS_HC_TX_BCAST_PACKETS |
+			STATISTICS_FLAGS_HC_TX_BCAST_BYTES;
+
+	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
+				sizeof(resp));
+	if (err) {
+		netdev_err(ndev, "Failed to query GF stats: %d\n", err);
+		return;
+	}
+	err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT,
+				   sizeof(resp));
+	if (err || resp.hdr.status) {
+		netdev_err(ndev, "Failed to query GF stats: %d, 0x%x\n", err,
+			   resp.hdr.status);
+		return;
+	}
+
+	apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes;
+	apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts;
+	apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes;
+	apc->eth_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts;
+	apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes;
+	apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts;
+	apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes;
+}
+
 static int mana_init_port(struct net_device *ndev)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 0dc78679f6209..607150165ab4b 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -13,6 +13,19 @@ static const struct {
 } mana_eth_stats[] = {
 	{"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)},
 	{"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)},
+	{"hc_tx_bytes", offsetof(struct mana_ethtool_stats, hc_tx_bytes)},
+	{"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_stats,
+					hc_tx_ucast_pkts)},
+	{"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_stats,
+					hc_tx_ucast_bytes)},
+	{"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_stats,
+					hc_tx_bcast_pkts)},
+	{"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_stats,
+					hc_tx_bcast_bytes)},
+	{"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_stats,
+					hc_tx_mcast_pkts)},
+	{"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_stats,
+					hc_tx_mcast_bytes)},
 	{"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)},
 	{"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
 					tx_cqe_unknown_type)},
@@ -114,6 +127,8 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
 
 	if (!apc->port_is_up)
 		return;
+	/* we call mana function to update stats from GDMA */
+	mana_query_gf_stats(apc);
 
 	for (q = 0; q < ARRAY_SIZE(mana_eth_stats); q++)
 		data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset);
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 879990101c9f5..9f70b43322383 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -352,6 +352,13 @@ struct mana_tx_qp {
 struct mana_ethtool_stats {
 	u64 stop_queue;
 	u64 wake_queue;
+	u64 hc_tx_bytes;
+	u64 hc_tx_ucast_pkts;
+	u64 hc_tx_ucast_bytes;
+	u64 hc_tx_bcast_pkts;
+	u64 hc_tx_bcast_bytes;
+	u64 hc_tx_mcast_pkts;
+	u64 hc_tx_mcast_bytes;
 	u64 tx_cqe_err;
 	u64 tx_cqe_unknown_type;
 	u64 rx_coalesced_err;
@@ -442,6 +449,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq,
 struct bpf_prog *mana_xdp_get(struct mana_port_context *apc);
 void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog);
 int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
+void mana_query_gf_stats(struct mana_port_context *apc);
 
 extern const struct ethtool_ops mana_ethtool_ops;
 
@@ -583,6 +591,49 @@ struct mana_fence_rq_resp {
 	struct gdma_resp_hdr hdr;
 }; /* HW DATA */
 
+/* Query stats RQ */
+struct mana_query_gf_stat_req {
+	struct gdma_req_hdr hdr;
+	u64 req_stats;
+}; /* HW DATA */
+
+struct mana_query_gf_stat_resp {
+	struct gdma_resp_hdr hdr;
+	u64 reported_stats;
+	/* rx errors/discards */
+	u64 discard_rx_nowqe;
+	u64 err_rx_vport_disabled;
+	/* rx bytes/packets */
+	u64 hc_rx_bytes;
+	u64 hc_rx_ucast_pkts;
+	u64 hc_rx_ucast_bytes;
+	u64 hc_rx_bcast_pkts;
+	u64 hc_rx_bcast_bytes;
+	u64 hc_rx_mcast_pkts;
+	u64 hc_rx_mcast_bytes;
+	/* tx errors */
+	u64 err_tx_gf_disabled;
+	u64 err_tx_vport_disabled;
+	u64 err_tx_inval_vport_offset_pkt;
+	u64 err_tx_vlan_enforcement;
+	u64 err_tx_ethtype_enforcement;
+	u64 err_tx_SA_enforecement;
+	u64 err_tx_SQPDID_enforcement;
+	u64 err_tx_CQPDID_enforcement;
+	u64 err_tx_mtu_violation;
+	u64 err_tx_inval_oob;
+	/* tx bytes/packets */
+	u64 hc_tx_bytes;
+	u64 hc_tx_ucast_pkts;
+	u64 hc_tx_ucast_bytes;
+	u64 hc_tx_bcast_pkts;
+	u64 hc_tx_bcast_bytes;
+	u64 hc_tx_mcast_pkts;
+	u64 hc_tx_mcast_bytes;
+	/* tx error */
+	u64 err_tx_gdma;
+}; /* HW DATA */
+
 /* Configure vPort Rx Steering */
 struct mana_cfg_rx_steer_req_v2 {
 	struct gdma_req_hdr hdr;
@@ -662,6 +713,42 @@ struct mana_deregister_filter_resp {
 	struct gdma_resp_hdr hdr;
 }; /* HW DATA */
 
+/* Requested GF stats Flags */
+/* Rx discards/Errors */
+#define STATISTICS_FLAGS_RX_DISCARDS_NO_WQE		0x0000000000000001
+#define STATISTICS_FLAGS_RX_ERRORS_VPORT_DISABLED	0x0000000000000002
+/* Rx bytes/pkts */
+#define STATISTICS_FLAGS_HC_RX_BYTES			0x0000000000000004
+#define STATISTICS_FLAGS_HC_RX_UCAST_PACKETS		0x0000000000000008
+#define STATISTICS_FLAGS_HC_RX_UCAST_BYTES		0x0000000000000010
+#define STATISTICS_FLAGS_HC_RX_MCAST_PACKETS		0x0000000000000020
+#define STATISTICS_FLAGS_HC_RX_MCAST_BYTES		0x0000000000000040
+#define STATISTICS_FLAGS_HC_RX_BCAST_PACKETS		0x0000000000000080
+#define STATISTICS_FLAGS_HC_RX_BCAST_BYTES		0x0000000000000100
+/* Tx errors */
+#define STATISTICS_FLAGS_TX_ERRORS_GF_DISABLED		0x0000000000000200
+#define STATISTICS_FLAGS_TX_ERRORS_VPORT_DISABLED	0x0000000000000400
+#define STATISTICS_FLAGS_TX_ERRORS_INVAL_VPORT_OFFSET_PACKETS		\
+							0x0000000000000800
+#define STATISTICS_FLAGS_TX_ERRORS_VLAN_ENFORCEMENT	0x0000000000001000
+#define STATISTICS_FLAGS_TX_ERRORS_ETH_TYPE_ENFORCEMENT			\
+							0x0000000000002000
+#define STATISTICS_FLAGS_TX_ERRORS_SA_ENFORCEMENT	0x0000000000004000
+#define STATISTICS_FLAGS_TX_ERRORS_SQPDID_ENFORCEMENT	0x0000000000008000
+#define STATISTICS_FLAGS_TX_ERRORS_CQPDID_ENFORCEMENT	0x0000000000010000
+#define STATISTICS_FLAGS_TX_ERRORS_MTU_VIOLATION	0x0000000000020000
+#define STATISTICS_FLAGS_TX_ERRORS_INVALID_OOB		0x0000000000040000
+/* Tx bytes/pkts */
+#define STATISTICS_FLAGS_HC_TX_BYTES			0x0000000000080000
+#define STATISTICS_FLAGS_HC_TX_UCAST_PACKETS		0x0000000000100000
+#define STATISTICS_FLAGS_HC_TX_UCAST_BYTES		0x0000000000200000
+#define STATISTICS_FLAGS_HC_TX_MCAST_PACKETS		0x0000000000400000
+#define STATISTICS_FLAGS_HC_TX_MCAST_BYTES		0x0000000000800000
+#define STATISTICS_FLAGS_HC_TX_BCAST_PACKETS		0x0000000001000000
+#define STATISTICS_FLAGS_HC_TX_BCAST_BYTES		0x0000000002000000
+/* Tx error */
+#define STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR		0x0000000004000000
+
 #define MANA_MAX_NUM_QUEUES 64
 
 #define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1)
-- 
GitLab


From c5b0c34fae1ef234982d55445b8aa482f0b05ba6 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Aug 2023 12:39:22 +0200
Subject: [PATCH 1065/1806] net/xgene: fix Wvoid-pointer-to-enum-cast warning

'enet_id' is an enum, thus cast of pointer on 64-bit compile test with
W=1 causes:

  xgene_enet_main.c:2044:20: error: cast to smaller integer type 'enum xgene_enet_id' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast]

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Simon Horman <horms@kernel.org> # build-tested
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 41d96f4b23d86..4d4140b7c4509 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -2041,7 +2041,7 @@ static int xgene_enet_probe(struct platform_device *pdev)
 
 	of_id = of_match_device(xgene_enet_of_match, &pdev->dev);
 	if (of_id) {
-		pdata->enet_id = (enum xgene_enet_id)of_id->data;
+		pdata->enet_id = (uintptr_t)of_id->data;
 	}
 #ifdef CONFIG_ACPI
 	else {
-- 
GitLab


From e5cd429e79286a17b345f9f9153d3970a46359f2 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Aug 2023 12:39:23 +0200
Subject: [PATCH 1066/1806] net/marvell: fix Wvoid-pointer-to-enum-cast warning

'type' is an enum, thus cast of pointer on 64-bit compile test with
W=1 causes:

  mvmdio.c:272:9: error: cast to smaller integer type 'enum orion_mdio_bus_type' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast]

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Simon Horman <horms@kernel.org> # build-tested
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvmdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index a1a80f13b1e89..674913184ebf5 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -269,7 +269,7 @@ static int orion_mdio_probe(struct platform_device *pdev)
 	struct orion_mdio_dev *dev;
 	int i, ret;
 
-	type = (enum orion_mdio_bus_type)device_get_match_data(&pdev->dev);
+	type = (uintptr_t)device_get_match_data(&pdev->dev);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!r) {
-- 
GitLab


From e08190ef514fd3c7e45826cd0d427d4133361192 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Thu, 10 Aug 2023 21:50:03 +0800
Subject: [PATCH 1067/1806] bonding: add modifier to initialization function
 and exit function

Some functions are only used in initialization and exit functions, so add
the __init/__net_init and __net_exit modifiers to these functions.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_debugfs.c | 4 ++--
 drivers/net/bonding/bond_main.c    | 2 +-
 drivers/net/bonding/bond_sysfs.c   | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index 5940945266489..94c2f35e3bfcd 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -84,7 +84,7 @@ void bond_debug_reregister(struct bonding *bond)
 	}
 }
 
-void bond_create_debugfs(void)
+void __init bond_create_debugfs(void)
 {
 	bonding_debug_root = debugfs_create_dir("bonding", NULL);
 
@@ -113,7 +113,7 @@ void bond_debug_reregister(struct bonding *bond)
 {
 }
 
-void bond_create_debugfs(void)
+void __init bond_create_debugfs(void)
 {
 }
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index d26c69d84c1e1..6636638f5d975 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5981,7 +5981,7 @@ static void bond_uninit(struct net_device *bond_dev)
 
 /*------------------------- Module initialization ---------------------------*/
 
-static int bond_check_params(struct bond_params *params)
+static int __init bond_check_params(struct bond_params *params)
 {
 	int arp_validate_value, fail_over_mac_value, primary_reselect_value, i;
 	struct bond_opt_value newval;
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 0bb59da249224..2805135a7205b 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -803,7 +803,7 @@ static const struct attribute_group bonding_group = {
 /* Initialize sysfs.  This sets up the bonding_masters file in
  * /sys/class/net.
  */
-int bond_create_sysfs(struct bond_net *bn)
+int __net_init bond_create_sysfs(struct bond_net *bn)
 {
 	int ret;
 
@@ -836,7 +836,7 @@ int bond_create_sysfs(struct bond_net *bn)
 }
 
 /* Remove /sys/class/net/bonding_masters. */
-void bond_destroy_sysfs(struct bond_net *bn)
+void __net_exit bond_destroy_sysfs(struct bond_net *bn)
 {
 	netdev_class_remove_file_ns(&bn->class_attr_bonding_masters, bn->net);
 }
-- 
GitLab


From 57647e6fdf174e3c84072a39d901036f867e4192 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Thu, 10 Aug 2023 21:50:04 +0800
Subject: [PATCH 1068/1806] bonding: use IS_ERR instead of NULL check in
 bond_create_debugfs

Because debugfs_create_dir returns ERR_PTR, so IS_ERR should be used to
check whether the directory is successfully created.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_debugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index 94c2f35e3bfcd..50e48136c6977 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -88,7 +88,7 @@ void __init bond_create_debugfs(void)
 {
 	bonding_debug_root = debugfs_create_dir("bonding", NULL);
 
-	if (!bonding_debug_root)
+	if (IS_ERR(bonding_debug_root))
 		pr_warn("Warning: Cannot create bonding directory in debugfs\n");
 }
 
-- 
GitLab


From cc317ea3d9272fab4f6fef527c865f30ca479394 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Thu, 10 Aug 2023 21:50:05 +0800
Subject: [PATCH 1069/1806] bonding: remove redundant NULL check in debugfs
 function

Because debugfs_create_dir returns ERR_PTR, so bonding_debug_root will
never be NULL. Remove redundant NULL check for bonding_debug_root in
debugfs function. The later debugfs_create_dir/debugfs_remove_recursive
/debugfs_remove_recursive functions will check the dentry with IS_ERR().

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_debugfs.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index 50e48136c6977..b19492a7f6ad1 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -49,9 +49,6 @@ DEFINE_SHOW_ATTRIBUTE(bond_debug_rlb_hash);
 
 void bond_debug_register(struct bonding *bond)
 {
-	if (!bonding_debug_root)
-		return;
-
 	bond->debug_dir =
 		debugfs_create_dir(bond->dev->name, bonding_debug_root);
 
@@ -61,9 +58,6 @@ void bond_debug_register(struct bonding *bond)
 
 void bond_debug_unregister(struct bonding *bond)
 {
-	if (!bonding_debug_root)
-		return;
-
 	debugfs_remove_recursive(bond->debug_dir);
 }
 
@@ -71,9 +65,6 @@ void bond_debug_reregister(struct bonding *bond)
 {
 	struct dentry *d;
 
-	if (!bonding_debug_root)
-		return;
-
 	d = debugfs_rename(bonding_debug_root, bond->debug_dir,
 			   bonding_debug_root, bond->dev->name);
 	if (!IS_ERR(d)) {
-- 
GitLab


From a8f3f4b448458a117465b9404d18994469c01957 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Thu, 10 Aug 2023 21:50:06 +0800
Subject: [PATCH 1070/1806] bonding: use bond_set_slave_arr to simplify code

In bond_reset_slave_arr(), values are assigned and memory is released only
when the variables "usable" and "all" are not NULL. But even if the
"usable" and "all" variables are NULL, they can still work, because value
will be checked in kfree_rcu. Therefore, use bond_set_slave_arr() and set
the input parameters "usable_slaves" and "all_slaves" to NULL to simplify
the code in bond_reset_slave_arr(). And the same to bond_uninit().

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 27 ++-------------------------
 1 file changed, 2 insertions(+), 25 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 6636638f5d975..de3ae9c57da07 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5046,19 +5046,7 @@ static void bond_set_slave_arr(struct bonding *bond,
 
 static void bond_reset_slave_arr(struct bonding *bond)
 {
-	struct bond_up_slave *usable, *all;
-
-	usable = rtnl_dereference(bond->usable_slaves);
-	if (usable) {
-		RCU_INIT_POINTER(bond->usable_slaves, NULL);
-		kfree_rcu(usable, rcu);
-	}
-
-	all = rtnl_dereference(bond->all_slaves);
-	if (all) {
-		RCU_INIT_POINTER(bond->all_slaves, NULL);
-		kfree_rcu(all, rcu);
-	}
+	bond_set_slave_arr(bond, NULL, NULL);
 }
 
 /* Build the usable slaves array in control path for modes that use xmit-hash
@@ -5951,7 +5939,6 @@ void bond_setup(struct net_device *bond_dev)
 static void bond_uninit(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct bond_up_slave *usable, *all;
 	struct list_head *iter;
 	struct slave *slave;
 
@@ -5962,17 +5949,7 @@ static void bond_uninit(struct net_device *bond_dev)
 		__bond_release_one(bond_dev, slave->dev, true, true);
 	netdev_info(bond_dev, "Released all slaves\n");
 
-	usable = rtnl_dereference(bond->usable_slaves);
-	if (usable) {
-		RCU_INIT_POINTER(bond->usable_slaves, NULL);
-		kfree_rcu(usable, rcu);
-	}
-
-	all = rtnl_dereference(bond->all_slaves);
-	if (all) {
-		RCU_INIT_POINTER(bond->all_slaves, NULL);
-		kfree_rcu(all, rcu);
-	}
+	bond_set_slave_arr(bond, NULL, NULL);
 
 	list_del(&bond->bond_list);
 
-- 
GitLab


From f5370ba3590d1e141c288eed2c0e53618b91356d Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Thu, 10 Aug 2023 21:50:07 +0800
Subject: [PATCH 1071/1806] bonding: remove unnecessary NULL check in
 bond_destructor

The free_percpu function also could check whether "rr_tx_counter"
parameter is NULL. Therefore, remove NULL check in bond_destructor.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index de3ae9c57da07..f398bec784574 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5863,8 +5863,7 @@ static void bond_destructor(struct net_device *bond_dev)
 	if (bond->wq)
 		destroy_workqueue(bond->wq);
 
-	if (bond->rr_tx_counter)
-		free_percpu(bond->rr_tx_counter);
+	free_percpu(bond->rr_tx_counter);
 }
 
 void bond_setup(struct net_device *bond_dev)
-- 
GitLab


From 61f98da4698407d042128396297d7f724cfa1424 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Thu, 10 Aug 2023 22:41:19 +0530
Subject: [PATCH 1072/1806] octeontx2-pf: Allow both ntuple and TC features on
 the interface

The current implementation does not allow the user to enable both
hw-tc-offload and ntuple features on the interface. These checks
are added as TC flower offload and ntuple features internally configures
the same hardware resource MCAM. But TC HTB offload configures the
transmit scheduler which can be safely enabled on the interface with
ntuple feature.

This patch adds the same and ensures only TC flower offload and ntuple
features are mutually exclusive.

Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../marvell/octeontx2/nic/otx2_common.c       | 21 +++----------------
 .../marvell/octeontx2/nic/otx2_common.h       |  9 ++++++++
 2 files changed, 12 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 8336cea16aff0..dce3cea00032a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1905,31 +1905,16 @@ int otx2_handle_ntuple_tc_features(struct net_device *netdev, netdev_features_t
 		}
 	}
 
-	if ((changed & NETIF_F_HW_TC) && tc) {
-		if (!pfvf->flow_cfg->max_flows) {
-			netdev_err(netdev,
-				   "Can't enable TC, MCAM entries not allocated\n");
-			return -EINVAL;
-		}
-	}
-
 	if ((changed & NETIF_F_HW_TC) && !tc &&
-	    pfvf->flow_cfg && pfvf->flow_cfg->nr_flows) {
+	    otx2_tc_flower_rule_cnt(pfvf)) {
 		netdev_err(netdev, "Can't disable TC hardware offload while flows are active\n");
 		return -EBUSY;
 	}
 
 	if ((changed & NETIF_F_NTUPLE) && ntuple &&
-	    (netdev->features & NETIF_F_HW_TC) && !(changed & NETIF_F_HW_TC)) {
-		netdev_err(netdev,
-			   "Can't enable NTUPLE when TC is active, disable TC and retry\n");
-		return -EINVAL;
-	}
-
-	if ((changed & NETIF_F_HW_TC) && tc &&
-	    (netdev->features & NETIF_F_NTUPLE) && !(changed & NETIF_F_NTUPLE)) {
+	    otx2_tc_flower_rule_cnt(pfvf) && !(changed & NETIF_F_HW_TC)) {
 		netdev_err(netdev,
-			   "Can't enable TC when NTUPLE is active, disable NTUPLE and retry\n");
+			   "Can't enable NTUPLE when TC flower offload is active, disable TC rules and retry\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 25e99fd2e3fd3..5fd05d94de7c8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -940,6 +940,15 @@ static inline u64 otx2_convert_rate(u64 rate)
 	return converted_rate;
 }
 
+static inline int otx2_tc_flower_rule_cnt(struct otx2_nic *pfvf)
+{
+	/* return here if MCAM entries not allocated */
+	if (!pfvf->flow_cfg)
+		return 0;
+
+	return pfvf->flow_cfg->nr_flows;
+}
+
 /* MSI-X APIs */
 void otx2_free_cints(struct otx2_nic *pfvf, int n);
 void otx2_set_cints_affinity(struct otx2_nic *pfvf);
-- 
GitLab


From 6cf30fdd7b06515db9188ace84d2497f390f4c37 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <clement.leger@bootlin.com>
Date: Thu, 10 Aug 2023 11:36:49 +0200
Subject: [PATCH 1073/1806] net: dsa: rzn1-a5psw: use a5psw_reg_rmw() to modify
 flooding resolution
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

.port_bridge_flags will be added and allows to modify the flood mask
independently for each port. Keeping the existing bridged_ports write
in a5psw_flooding_set_resolution() would potentially messed up this.
Use a read-modify-write to set that value and move bridged_ports
handling in bridge_port_join/leave.

Signed-off-by: Clément Léger <clement.leger@bootlin.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rzn1_a5psw.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c
index c37d2e5372302..302529edb4e0f 100644
--- a/drivers/net/dsa/rzn1_a5psw.c
+++ b/drivers/net/dsa/rzn1_a5psw.c
@@ -331,13 +331,9 @@ static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port,
 			A5PSW_MCAST_DEF_MASK};
 	int i;
 
-	if (set)
-		a5psw->bridged_ports |= BIT(port);
-	else
-		a5psw->bridged_ports &= ~BIT(port);
-
 	for (i = 0; i < ARRAY_SIZE(offsets); i++)
-		a5psw_reg_writel(a5psw, offsets[i], a5psw->bridged_ports);
+		a5psw_reg_rmw(a5psw, offsets[i], BIT(port),
+			      set ? BIT(port) : 0);
 }
 
 static void a5psw_port_set_standalone(struct a5psw *a5psw, int port,
@@ -365,6 +361,8 @@ static int a5psw_port_bridge_join(struct dsa_switch *ds, int port,
 	a5psw->br_dev = bridge.dev;
 	a5psw_port_set_standalone(a5psw, port, false);
 
+	a5psw->bridged_ports |= BIT(port);
+
 	return 0;
 }
 
@@ -373,6 +371,8 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port,
 {
 	struct a5psw *a5psw = ds->priv;
 
+	a5psw->bridged_ports &= ~BIT(port);
+
 	a5psw_port_set_standalone(a5psw, port, true);
 
 	/* No more ports bridged */
@@ -992,6 +992,8 @@ static int a5psw_probe(struct platform_device *pdev)
 	if (IS_ERR(a5psw->base))
 		return PTR_ERR(a5psw->base);
 
+	a5psw->bridged_ports = BIT(A5PSW_CPU_PORT);
+
 	ret = a5psw_pcs_get(a5psw);
 	if (ret)
 		return ret;
-- 
GitLab


From 0d37f839836b4f61493ff3ff0397abd19f540494 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <clement.leger@bootlin.com>
Date: Thu, 10 Aug 2023 11:36:50 +0200
Subject: [PATCH 1074/1806] net: dsa: rzn1-a5psw: add support for
 .port_bridge_flags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When running vlan test (bridge_vlan_aware/unaware.sh), there were some
failure due to the lack .port_bridge_flag function to disable port
flooding. Implement this operation for BR_LEARNING, BR_FLOOD,
BR_MCAST_FLOOD and BR_BCAST_FLOOD.

Since .port_bridge_flags affects the bits disabling learning for a port,
ensure that any other modification on the same register done by
a5psw_port_stp_state_set is in sync by using the port learning state to
enable/disable learning on the port.

Signed-off-by: Clément Léger <clement.leger@bootlin.com>
Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rzn1_a5psw.c | 60 ++++++++++++++++++++++++++++++++++--
 1 file changed, 58 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c
index 302529edb4e0f..e4a93dad1d58e 100644
--- a/drivers/net/dsa/rzn1_a5psw.c
+++ b/drivers/net/dsa/rzn1_a5psw.c
@@ -380,9 +380,63 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port,
 		a5psw->br_dev = NULL;
 }
 
+static int a5psw_port_pre_bridge_flags(struct dsa_switch *ds, int port,
+				       struct switchdev_brport_flags flags,
+				       struct netlink_ext_ack *extack)
+{
+	if (flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD |
+			   BR_BCAST_FLOOD))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int
+a5psw_port_bridge_flags(struct dsa_switch *ds, int port,
+			struct switchdev_brport_flags flags,
+			struct netlink_ext_ack *extack)
+{
+	struct a5psw *a5psw = ds->priv;
+	u32 val;
+
+	/* If a port is set as standalone, we do not want to be able to
+	 * configure flooding nor learning which would result in joining the
+	 * unique bridge. This can happen when a port leaves the bridge, in
+	 * which case the DSA core will try to "clear" all flags for the
+	 * standalone port (ie enable flooding, disable learning). In that case
+	 * do not fail but do not apply the flags.
+	 */
+	if (!(a5psw->bridged_ports & BIT(port)))
+		return 0;
+
+	if (flags.mask & BR_LEARNING) {
+		val = flags.val & BR_LEARNING ? 0 : A5PSW_INPUT_LEARN_DIS(port);
+		a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN,
+			      A5PSW_INPUT_LEARN_DIS(port), val);
+	}
+
+	if (flags.mask & BR_FLOOD) {
+		val = flags.val & BR_FLOOD ? BIT(port) : 0;
+		a5psw_reg_rmw(a5psw, A5PSW_UCAST_DEF_MASK, BIT(port), val);
+	}
+
+	if (flags.mask & BR_MCAST_FLOOD) {
+		val = flags.val & BR_MCAST_FLOOD ? BIT(port) : 0;
+		a5psw_reg_rmw(a5psw, A5PSW_MCAST_DEF_MASK, BIT(port), val);
+	}
+
+	if (flags.mask & BR_BCAST_FLOOD) {
+		val = flags.val & BR_BCAST_FLOOD ? BIT(port) : 0;
+		a5psw_reg_rmw(a5psw, A5PSW_BCAST_DEF_MASK, BIT(port), val);
+	}
+
+	return 0;
+}
+
 static void a5psw_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 {
 	bool learning_enabled, rx_enabled, tx_enabled;
+	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct a5psw *a5psw = ds->priv;
 
 	switch (state) {
@@ -396,12 +450,12 @@ static void a5psw_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 	case BR_STATE_LEARNING:
 		rx_enabled = false;
 		tx_enabled = false;
-		learning_enabled = true;
+		learning_enabled = dp->learning;
 		break;
 	case BR_STATE_FORWARDING:
 		rx_enabled = true;
 		tx_enabled = true;
-		learning_enabled = true;
+		learning_enabled = dp->learning;
 		break;
 	default:
 		dev_err(ds->dev, "invalid STP state: %d\n", state);
@@ -801,6 +855,8 @@ static const struct dsa_switch_ops a5psw_switch_ops = {
 	.set_ageing_time = a5psw_set_ageing_time,
 	.port_bridge_join = a5psw_port_bridge_join,
 	.port_bridge_leave = a5psw_port_bridge_leave,
+	.port_pre_bridge_flags = a5psw_port_pre_bridge_flags,
+	.port_bridge_flags = a5psw_port_bridge_flags,
 	.port_stp_state_set = a5psw_port_stp_state_set,
 	.port_fast_age = a5psw_port_fast_age,
 	.port_fdb_add = a5psw_port_fdb_add,
-- 
GitLab


From 7b3f77c428ad7d3ae66ed8c98b072a0cdca2f0ba Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <clement.leger@bootlin.com>
Date: Thu, 10 Aug 2023 11:36:51 +0200
Subject: [PATCH 1075/1806] net: dsa: rzn1-a5psw: add vlan support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for vlan operation (add, del, filtering) on the RZN1
driver. The a5psw switch supports up to 32 VLAN IDs with filtering,
tagged/untagged VLANs and PVID for each ports.

Signed-off-by: Clément Léger <clement.leger@bootlin.com>
Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rzn1_a5psw.c | 166 +++++++++++++++++++++++++++++++++++
 drivers/net/dsa/rzn1_a5psw.h |   8 +-
 2 files changed, 171 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c
index e4a93dad1d58e..2bb458f2c1f88 100644
--- a/drivers/net/dsa/rzn1_a5psw.c
+++ b/drivers/net/dsa/rzn1_a5psw.c
@@ -639,6 +639,146 @@ out_unlock:
 	return ret;
 }
 
+static int a5psw_port_vlan_filtering(struct dsa_switch *ds, int port,
+				     bool vlan_filtering,
+				     struct netlink_ext_ack *extack)
+{
+	u32 mask = BIT(port + A5PSW_VLAN_VERI_SHIFT) |
+		   BIT(port + A5PSW_VLAN_DISC_SHIFT);
+	u32 val = vlan_filtering ? mask : 0;
+	struct a5psw *a5psw = ds->priv;
+
+	/* Disable/enable vlan tagging */
+	a5psw_reg_rmw(a5psw, A5PSW_VLAN_IN_MODE_ENA, BIT(port),
+		      vlan_filtering ? BIT(port) : 0);
+
+	/* Disable/enable vlan input filtering */
+	a5psw_reg_rmw(a5psw, A5PSW_VLAN_VERIFY, mask, val);
+
+	return 0;
+}
+
+static int a5psw_find_vlan_entry(struct a5psw *a5psw, u16 vid)
+{
+	u32 vlan_res;
+	int i;
+
+	/* Find vlan for this port */
+	for (i = 0; i < A5PSW_VLAN_COUNT; i++) {
+		vlan_res = a5psw_reg_readl(a5psw, A5PSW_VLAN_RES(i));
+		if (FIELD_GET(A5PSW_VLAN_RES_VLANID, vlan_res) == vid)
+			return i;
+	}
+
+	return -1;
+}
+
+static int a5psw_new_vlan_res_entry(struct a5psw *a5psw, u16 newvid)
+{
+	u32 vlan_res;
+	int i;
+
+	/* Find a free VLAN entry */
+	for (i = 0; i < A5PSW_VLAN_COUNT; i++) {
+		vlan_res = a5psw_reg_readl(a5psw, A5PSW_VLAN_RES(i));
+		if (!(FIELD_GET(A5PSW_VLAN_RES_PORTMASK, vlan_res))) {
+			vlan_res = FIELD_PREP(A5PSW_VLAN_RES_VLANID, newvid);
+			a5psw_reg_writel(a5psw, A5PSW_VLAN_RES(i), vlan_res);
+			return i;
+		}
+	}
+
+	return -1;
+}
+
+static void a5psw_port_vlan_tagged_cfg(struct a5psw *a5psw,
+				       unsigned int vlan_res_id, int port,
+				       bool set)
+{
+	u32 mask = A5PSW_VLAN_RES_WR_PORTMASK | A5PSW_VLAN_RES_RD_TAGMASK |
+		   BIT(port);
+	u32 vlan_res_off = A5PSW_VLAN_RES(vlan_res_id);
+	u32 val = A5PSW_VLAN_RES_WR_TAGMASK, reg;
+
+	if (set)
+		val |= BIT(port);
+
+	/* Toggle tag mask read */
+	a5psw_reg_writel(a5psw, vlan_res_off, A5PSW_VLAN_RES_RD_TAGMASK);
+	reg = a5psw_reg_readl(a5psw, vlan_res_off);
+	a5psw_reg_writel(a5psw, vlan_res_off, A5PSW_VLAN_RES_RD_TAGMASK);
+
+	reg &= ~mask;
+	reg |= val;
+	a5psw_reg_writel(a5psw, vlan_res_off, reg);
+}
+
+static void a5psw_port_vlan_cfg(struct a5psw *a5psw, unsigned int vlan_res_id,
+				int port, bool set)
+{
+	u32 mask = A5PSW_VLAN_RES_WR_TAGMASK | BIT(port);
+	u32 reg = A5PSW_VLAN_RES_WR_PORTMASK;
+
+	if (set)
+		reg |= BIT(port);
+
+	a5psw_reg_rmw(a5psw, A5PSW_VLAN_RES(vlan_res_id), mask, reg);
+}
+
+static int a5psw_port_vlan_add(struct dsa_switch *ds, int port,
+			       const struct switchdev_obj_port_vlan *vlan,
+			       struct netlink_ext_ack *extack)
+{
+	bool tagged = !(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	struct a5psw *a5psw = ds->priv;
+	u16 vid = vlan->vid;
+	int vlan_res_id;
+
+	dev_dbg(a5psw->dev, "Add VLAN %d on port %d, %s, %s\n",
+		vid, port, tagged ? "tagged" : "untagged",
+		pvid ? "PVID" : "no PVID");
+
+	vlan_res_id = a5psw_find_vlan_entry(a5psw, vid);
+	if (vlan_res_id < 0) {
+		vlan_res_id = a5psw_new_vlan_res_entry(a5psw, vid);
+		if (vlan_res_id < 0)
+			return -ENOSPC;
+	}
+
+	a5psw_port_vlan_cfg(a5psw, vlan_res_id, port, true);
+	if (tagged)
+		a5psw_port_vlan_tagged_cfg(a5psw, vlan_res_id, port, true);
+
+	/* Configure port to tag with corresponding VID, but do not enable it
+	 * yet: wait for vlan filtering to be enabled to enable vlan port
+	 * tagging
+	 */
+	if (pvid)
+		a5psw_reg_writel(a5psw, A5PSW_SYSTEM_TAGINFO(port), vid);
+
+	return 0;
+}
+
+static int a5psw_port_vlan_del(struct dsa_switch *ds, int port,
+			       const struct switchdev_obj_port_vlan *vlan)
+{
+	struct a5psw *a5psw = ds->priv;
+	u16 vid = vlan->vid;
+	int vlan_res_id;
+
+	dev_dbg(a5psw->dev, "Removing VLAN %d on port %d\n", vid, port);
+
+	vlan_res_id = a5psw_find_vlan_entry(a5psw, vid);
+	if (vlan_res_id < 0)
+		return -EINVAL;
+
+	a5psw_port_vlan_cfg(a5psw, vlan_res_id, port, false);
+	a5psw_port_vlan_tagged_cfg(a5psw, vlan_res_id, port, false);
+
+	return 0;
+}
+
 static u64 a5psw_read_stat(struct a5psw *a5psw, u32 offset, int port)
 {
 	u32 reg_lo, reg_hi;
@@ -756,6 +896,27 @@ static void a5psw_get_eth_ctrl_stats(struct dsa_switch *ds, int port,
 	ctrl_stats->MACControlFramesReceived = stat;
 }
 
+static void a5psw_vlan_setup(struct a5psw *a5psw, int port)
+{
+	u32 reg;
+
+	/* Enable TAG always mode for the port, this is actually controlled
+	 * by VLAN_IN_MODE_ENA field which will be used for PVID insertion
+	 */
+	reg = A5PSW_VLAN_IN_MODE_TAG_ALWAYS;
+	reg <<= A5PSW_VLAN_IN_MODE_PORT_SHIFT(port);
+	a5psw_reg_rmw(a5psw, A5PSW_VLAN_IN_MODE, A5PSW_VLAN_IN_MODE_PORT(port),
+		      reg);
+
+	/* Set transparent mode for output frame manipulation, this will depend
+	 * on the VLAN_RES configuration mode
+	 */
+	reg = A5PSW_VLAN_OUT_MODE_TRANSPARENT;
+	reg <<= A5PSW_VLAN_OUT_MODE_PORT_SHIFT(port);
+	a5psw_reg_rmw(a5psw, A5PSW_VLAN_OUT_MODE,
+		      A5PSW_VLAN_OUT_MODE_PORT(port), reg);
+}
+
 static int a5psw_setup(struct dsa_switch *ds)
 {
 	struct a5psw *a5psw = ds->priv;
@@ -830,6 +991,8 @@ static int a5psw_setup(struct dsa_switch *ds)
 		/* Enable standalone mode for user ports */
 		if (dsa_port_is_user(dp))
 			a5psw_port_set_standalone(a5psw, port, true);
+
+		a5psw_vlan_setup(a5psw, port);
 	}
 
 	return 0;
@@ -859,6 +1022,9 @@ static const struct dsa_switch_ops a5psw_switch_ops = {
 	.port_bridge_flags = a5psw_port_bridge_flags,
 	.port_stp_state_set = a5psw_port_stp_state_set,
 	.port_fast_age = a5psw_port_fast_age,
+	.port_vlan_filtering = a5psw_port_vlan_filtering,
+	.port_vlan_add = a5psw_port_vlan_add,
+	.port_vlan_del = a5psw_port_vlan_del,
 	.port_fdb_add = a5psw_port_fdb_add,
 	.port_fdb_del = a5psw_port_fdb_del,
 	.port_fdb_dump = a5psw_port_fdb_dump,
diff --git a/drivers/net/dsa/rzn1_a5psw.h b/drivers/net/dsa/rzn1_a5psw.h
index b869192eef3f7..d54acedac1947 100644
--- a/drivers/net/dsa/rzn1_a5psw.h
+++ b/drivers/net/dsa/rzn1_a5psw.h
@@ -51,7 +51,9 @@
 #define A5PSW_VLAN_IN_MODE_TAG_ALWAYS		0x2
 
 #define A5PSW_VLAN_OUT_MODE		0x2C
-#define A5PSW_VLAN_OUT_MODE_PORT(port)	(GENMASK(1, 0) << ((port) * 2))
+#define A5PSW_VLAN_OUT_MODE_PORT_SHIFT(port)	((port) * 2)
+#define A5PSW_VLAN_OUT_MODE_PORT(port)	(GENMASK(1, 0) << \
+					A5PSW_VLAN_OUT_MODE_PORT_SHIFT(port))
 #define A5PSW_VLAN_OUT_MODE_DIS		0x0
 #define A5PSW_VLAN_OUT_MODE_STRIP	0x1
 #define A5PSW_VLAN_OUT_MODE_TAG_THROUGH	0x2
@@ -60,7 +62,7 @@
 #define A5PSW_VLAN_IN_MODE_ENA		0x30
 #define A5PSW_VLAN_TAG_ID		0x34
 
-#define A5PSW_SYSTEM_TAGINFO(port)	(0x200 + A5PSW_PORT_OFFSET(port))
+#define A5PSW_SYSTEM_TAGINFO(port)	(0x200 + 4 * (port))
 
 #define A5PSW_AUTH_PORT(port)		(0x240 + 4 * (port))
 #define A5PSW_AUTH_PORT_AUTHORIZED	BIT(0)
@@ -69,7 +71,7 @@
 #define A5PSW_VLAN_RES_WR_PORTMASK	BIT(30)
 #define A5PSW_VLAN_RES_WR_TAGMASK	BIT(29)
 #define A5PSW_VLAN_RES_RD_TAGMASK	BIT(28)
-#define A5PSW_VLAN_RES_ID		GENMASK(16, 5)
+#define A5PSW_VLAN_RES_VLANID		GENMASK(16, 5)
 #define A5PSW_VLAN_RES_PORTMASK		GENMASK(4, 0)
 
 #define A5PSW_RXMATCH_CONFIG(port)	(0x3e80 + 4 * (port))
-- 
GitLab


From ae75336131337f926d61b7fd86a0cca3146a7620 Mon Sep 17 00:00:00 2001
From: Claudia Draghicescu <claudia.rosu@nxp.com>
Date: Wed, 10 May 2023 16:45:57 +0300
Subject: [PATCH 1076/1806] Bluetooth: Check for ISO support in controller

This patch checks for ISO_BROADCASTER and ISO_SYNC_RECEIVER in
controller.

Signed-off-by: Claudia Draghicescu <claudia.rosu@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci.h      | 1 +
 include/net/bluetooth/hci_core.h | 1 +
 include/net/bluetooth/mgmt.h     | 2 ++
 net/bluetooth/mgmt.c             | 6 ++++++
 4 files changed, 10 insertions(+)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 872dcb91a540e..ab2f8f1817cf1 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -577,6 +577,7 @@ enum {
 #define HCI_LE_CIS_CENTRAL		0x10
 #define HCI_LE_CIS_PERIPHERAL		0x20
 #define HCI_LE_ISO_BROADCASTER		0x40
+#define HCI_LE_ISO_SYNC_RECEIVER	0x80
 
 /* Connection modes */
 #define HCI_CM_ACTIVE	0x0000
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index e01d52cb668c0..da871581ef87b 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1765,6 +1765,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define cis_peripheral_capable(dev) \
 	((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL)
 #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER)
+#define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER)
 
 #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \
 	(!test_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &(dev)->quirks)))
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 5e68b3dd44222..d382679efd2b1 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -111,6 +111,8 @@ struct mgmt_rp_read_index_list {
 #define MGMT_SETTING_WIDEBAND_SPEECH	BIT(17)
 #define MGMT_SETTING_CIS_CENTRAL	BIT(18)
 #define MGMT_SETTING_CIS_PERIPHERAL	BIT(19)
+#define MGMT_SETTING_ISO_BROADCASTER	BIT(20)
+#define MGMT_SETTING_ISO_SYNC_RECEIVER	BIT(21)
 
 #define MGMT_OP_READ_INFO		0x0004
 #define MGMT_READ_INFO_SIZE		0
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index d4498037fadc6..4c352abe063b9 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -944,6 +944,12 @@ static u32 get_current_settings(struct hci_dev *hdev)
 	if (cis_peripheral_capable(hdev))
 		settings |= MGMT_SETTING_CIS_PERIPHERAL;
 
+	if (bis_capable(hdev))
+		settings |= MGMT_SETTING_ISO_BROADCASTER;
+
+	if (sync_recv_capable(hdev))
+		settings |= MGMT_SETTING_ISO_SYNC_RECEIVER;
+
 	return settings;
 }
 
-- 
GitLab


From 044014ce85a17c0b7fab8e5df0925792010c29b2 Mon Sep 17 00:00:00 2001
From: Hilda Wu <hildawu@realtek.com>
Date: Thu, 27 Apr 2023 11:27:55 +0800
Subject: [PATCH 1077/1806] Bluetooth: btrtl: Add Realtek devcoredump support

Catch debug exception from controller and driver, and trigger a
devcoredump using hci devcoredump APIs. The debug exception data
will be parsed in userspace.

Signed-off-by: Alex Lu <alex_lu@realsil.com.cn>
Signed-off-by: Hilda Wu <hildawu@realtek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btrtl.c | 145 +++++++++++++++++++++++++++++++-------
 drivers/bluetooth/btrtl.h |  13 ++++
 drivers/bluetooth/btusb.c |  74 +++++++++++++++++++
 3 files changed, 205 insertions(+), 27 deletions(-)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index d978e7cea8731..9a6ae8a2adfc8 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -32,6 +32,8 @@
 #define RTL_ROM_LMP_8851B	0x8851
 #define RTL_CONFIG_MAGIC	0x8723ab55
 
+#define RTL_VSC_OP_COREDUMP	0xfcff
+
 #define IC_MATCH_FL_LMPSUBV	(1 << 0)
 #define IC_MATCH_FL_HCIREV	(1 << 1)
 #define IC_MATCH_FL_HCIVER	(1 << 2)
@@ -81,6 +83,7 @@ struct id_table {
 	bool has_msft_ext;
 	char *fw_name;
 	char *cfg_name;
+	char *hw_info;
 };
 
 struct btrtl_device_info {
@@ -102,21 +105,24 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = false,
 	  .has_rom_version = false,
 	  .fw_name = "rtl_bt/rtl8723a_fw.bin",
-	  .cfg_name = NULL },
+	  .cfg_name = NULL,
+	  .hw_info = "rtl8723au" },
 
 	/* 8723BS */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xb, 0x6, HCI_UART),
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723bs_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723bs_config" },
+	  .cfg_name = "rtl_bt/rtl8723bs_config",
+	  .hw_info  = "rtl8723bs" },
 
 	/* 8723B */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xb, 0x6, HCI_USB),
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723b_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723b_config" },
+	  .cfg_name = "rtl_bt/rtl8723b_config",
+	  .hw_info  = "rtl8723bu" },
 
 	/* 8723CS-CG */
 	{ .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_CHIP_TYPE |
@@ -127,7 +133,8 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723cs_cg_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723cs_cg_config" },
+	  .cfg_name = "rtl_bt/rtl8723cs_cg_config",
+	  .hw_info  = "rtl8723cs-cg" },
 
 	/* 8723CS-VF */
 	{ .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_CHIP_TYPE |
@@ -138,7 +145,8 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723cs_vf_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723cs_vf_config" },
+	  .cfg_name = "rtl_bt/rtl8723cs_vf_config",
+	  .hw_info  = "rtl8723cs-vf" },
 
 	/* 8723CS-XX */
 	{ .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_CHIP_TYPE |
@@ -149,28 +157,32 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723cs_xx_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723cs_xx_config" },
+	  .cfg_name = "rtl_bt/rtl8723cs_xx_config",
+	  .hw_info  = "rtl8723cs" },
 
 	/* 8723D */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xd, 0x8, HCI_USB),
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723d_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723d_config" },
+	  .cfg_name = "rtl_bt/rtl8723d_config",
+	  .hw_info  = "rtl8723du" },
 
 	/* 8723DS */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xd, 0x8, HCI_UART),
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723ds_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723ds_config" },
+	  .cfg_name = "rtl_bt/rtl8723ds_config",
+	  .hw_info  = "rtl8723ds" },
 
 	/* 8821A */
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xa, 0x6, HCI_USB),
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8821a_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8821a_config" },
+	  .cfg_name = "rtl_bt/rtl8821a_config",
+	  .hw_info  = "rtl8821au" },
 
 	/* 8821C */
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xc, 0x8, HCI_USB),
@@ -178,7 +190,8 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8821c_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8821c_config" },
+	  .cfg_name = "rtl_bt/rtl8821c_config",
+	  .hw_info  = "rtl8821cu" },
 
 	/* 8821CS */
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xc, 0x8, HCI_UART),
@@ -186,14 +199,16 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8821cs_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8821cs_config" },
+	  .cfg_name = "rtl_bt/rtl8821cs_config",
+	  .hw_info  = "rtl8821cs" },
 
 	/* 8761A */
 	{ IC_INFO(RTL_ROM_LMP_8761A, 0xa, 0x6, HCI_USB),
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8761a_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8761a_config" },
+	  .cfg_name = "rtl_bt/rtl8761a_config",
+	  .hw_info  = "rtl8761au" },
 
 	/* 8761B */
 	{ IC_INFO(RTL_ROM_LMP_8761A, 0xb, 0xa, HCI_UART),
@@ -201,14 +216,16 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8761b_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8761b_config" },
+	  .cfg_name = "rtl_bt/rtl8761b_config",
+	  .hw_info  = "rtl8761btv" },
 
 	/* 8761BU */
 	{ IC_INFO(RTL_ROM_LMP_8761A, 0xb, 0xa, HCI_USB),
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8761bu_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8761bu_config" },
+	  .cfg_name = "rtl_bt/rtl8761bu_config",
+	  .hw_info  = "rtl8761bu" },
 
 	/* 8822C with UART interface */
 	{ IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0x8, HCI_UART),
@@ -216,7 +233,8 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8822cs_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8822cs_config" },
+	  .cfg_name = "rtl_bt/rtl8822cs_config",
+	  .hw_info  = "rtl8822cs" },
 
 	/* 8822C with UART interface */
 	{ IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0xa, HCI_UART),
@@ -224,7 +242,8 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8822cs_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8822cs_config" },
+	  .cfg_name = "rtl_bt/rtl8822cs_config",
+	  .hw_info  = "rtl8822cs" },
 
 	/* 8822C with USB interface */
 	{ IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0xa, HCI_USB),
@@ -232,7 +251,8 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8822cu_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8822cu_config" },
+	  .cfg_name = "rtl_bt/rtl8822cu_config",
+	  .hw_info  = "rtl8822cu" },
 
 	/* 8822B */
 	{ IC_INFO(RTL_ROM_LMP_8822B, 0xb, 0x7, HCI_USB),
@@ -240,7 +260,8 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8822b_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8822b_config" },
+	  .cfg_name = "rtl_bt/rtl8822b_config",
+	  .hw_info  = "rtl8822bu" },
 
 	/* 8852A */
 	{ IC_INFO(RTL_ROM_LMP_8852A, 0xa, 0xb, HCI_USB),
@@ -248,7 +269,8 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8852au_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8852au_config" },
+	  .cfg_name = "rtl_bt/rtl8852au_config",
+	  .hw_info  = "rtl8852au" },
 
 	/* 8852B with UART interface */
 	{ IC_INFO(RTL_ROM_LMP_8852A, 0xb, 0xb, HCI_UART),
@@ -256,7 +278,8 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8852bs_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8852bs_config" },
+	  .cfg_name = "rtl_bt/rtl8852bs_config",
+	  .hw_info  = "rtl8852bs" },
 
 	/* 8852B */
 	{ IC_INFO(RTL_ROM_LMP_8852A, 0xb, 0xb, HCI_USB),
@@ -264,7 +287,8 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8852bu_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8852bu_config" },
+	  .cfg_name = "rtl_bt/rtl8852bu_config",
+	  .hw_info  = "rtl8852bu" },
 
 	/* 8852C */
 	{ IC_INFO(RTL_ROM_LMP_8852A, 0xc, 0xc, HCI_USB),
@@ -272,7 +296,8 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
 	  .fw_name  = "rtl_bt/rtl8852cu_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8852cu_config" },
+	  .cfg_name = "rtl_bt/rtl8852cu_config",
+	  .hw_info  = "rtl8852cu" },
 
 	/* 8851B */
 	{ IC_INFO(RTL_ROM_LMP_8851B, 0xb, 0xc, HCI_USB),
@@ -280,7 +305,8 @@ static const struct id_table ic_id_table[] = {
 	  .has_rom_version = true,
 	  .has_msft_ext = false,
 	  .fw_name  = "rtl_bt/rtl8851bu_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8851bu_config" },
+	  .cfg_name = "rtl_bt/rtl8851bu_config",
+	  .hw_info  = "rtl8851bu" },
 	};
 
 static const struct id_table *btrtl_match_ic(u16 lmp_subver, u16 hci_rev,
@@ -590,6 +616,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev,
 				unsigned char **_buf)
 {
 	static const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 };
+	struct btrealtek_data *coredump_info = hci_get_priv(hdev);
 	struct rtl_epatch_header *epatch_info;
 	unsigned char *buf;
 	int i, len;
@@ -705,8 +732,10 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev,
 
 	epatch_info = (struct rtl_epatch_header *)btrtl_dev->fw_data;
 	num_patches = le16_to_cpu(epatch_info->num_patches);
+
 	BT_DBG("fw_version=%x, num_patches=%d",
 	       le32_to_cpu(epatch_info->fw_version), num_patches);
+	coredump_info->rtl_dump.fw_version = le32_to_cpu(epatch_info->fw_version);
 
 	/* After the rtl_epatch_header there is a funky patch metadata section.
 	 * Assuming 2 patches, the layout is:
@@ -903,6 +932,53 @@ out:
 	return ret;
 }
 
+static void btrtl_coredump(struct hci_dev *hdev)
+{
+	static const u8 param[] = { 0x00, 0x00 };
+
+	__hci_cmd_send(hdev, RTL_VSC_OP_COREDUMP, sizeof(param), param);
+}
+
+static void btrtl_dmp_hdr(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct btrealtek_data *coredump_info = hci_get_priv(hdev);
+	char buf[80];
+
+	if (coredump_info->rtl_dump.controller)
+		snprintf(buf, sizeof(buf), "Controller Name: %s\n",
+			 coredump_info->rtl_dump.controller);
+	else
+		snprintf(buf, sizeof(buf), "Controller Name: Unknown\n");
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Firmware Version: 0x%X\n",
+		 coredump_info->rtl_dump.fw_version);
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Driver: %s\n", coredump_info->rtl_dump.driver_name);
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Vendor: Realtek\n");
+	skb_put_data(skb, buf, strlen(buf));
+}
+
+static int btrtl_register_devcoredump_support(struct hci_dev *hdev)
+{
+	int err;
+
+	err = hci_devcd_register(hdev, btrtl_coredump, btrtl_dmp_hdr, NULL);
+
+	return err;
+}
+
+void btrtl_set_driver_name(struct hci_dev *hdev, const char *driver_name)
+{
+	struct btrealtek_data *coredump_info = hci_get_priv(hdev);
+
+	coredump_info->rtl_dump.driver_name = driver_name;
+}
+EXPORT_SYMBOL_GPL(btrtl_set_driver_name);
+
 static bool rtl_has_chip_type(u16 lmp_subver)
 {
 	switch (lmp_subver) {
@@ -964,6 +1040,7 @@ EXPORT_SYMBOL_GPL(btrtl_free);
 struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev,
 					   const char *postfix)
 {
+	struct btrealtek_data *coredump_info = hci_get_priv(hdev);
 	struct btrtl_device_info *btrtl_dev;
 	struct sk_buff *skb;
 	struct hci_rp_read_local_version *resp;
@@ -1113,6 +1190,9 @@ next:
 	if (btrtl_dev->ic_info->has_msft_ext)
 		hci_set_msft_opcode(hdev, 0xFCF0);
 
+	if (btrtl_dev->ic_info)
+		coredump_info->rtl_dump.controller = btrtl_dev->ic_info->hw_info;
+
 	return btrtl_dev;
 
 err_free:
@@ -1125,6 +1205,8 @@ EXPORT_SYMBOL_GPL(btrtl_initialize);
 int btrtl_download_firmware(struct hci_dev *hdev,
 			    struct btrtl_device_info *btrtl_dev)
 {
+	int err = 0;
+
 	/* Match a set of subver values that correspond to stock firmware,
 	 * which is not compatible with standard btusb.
 	 * If matched, upload an alternative firmware that does conform to
@@ -1133,12 +1215,14 @@ int btrtl_download_firmware(struct hci_dev *hdev,
 	 */
 	if (!btrtl_dev->ic_info) {
 		rtl_dev_info(hdev, "assuming no firmware upload needed");
-		return 0;
+		err = 0;
+		goto done;
 	}
 
 	switch (btrtl_dev->ic_info->lmp_subver) {
 	case RTL_ROM_LMP_8723A:
-		return btrtl_setup_rtl8723a(hdev, btrtl_dev);
+		err = btrtl_setup_rtl8723a(hdev, btrtl_dev);
+		break;
 	case RTL_ROM_LMP_8723B:
 	case RTL_ROM_LMP_8821A:
 	case RTL_ROM_LMP_8761A:
@@ -1146,11 +1230,18 @@ int btrtl_download_firmware(struct hci_dev *hdev,
 	case RTL_ROM_LMP_8852A:
 	case RTL_ROM_LMP_8703B:
 	case RTL_ROM_LMP_8851B:
-		return btrtl_setup_rtl8723b(hdev, btrtl_dev);
+		err = btrtl_setup_rtl8723b(hdev, btrtl_dev);
+		break;
 	default:
 		rtl_dev_info(hdev, "assuming no firmware upload needed");
-		return 0;
+		break;
 	}
+
+done:
+	if (!err)
+		err = btrtl_register_devcoredump_support(hdev);
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(btrtl_download_firmware);
 
diff --git a/drivers/bluetooth/btrtl.h b/drivers/bluetooth/btrtl.h
index adb4c2c9abc50..a2d9d34f9fb08 100644
--- a/drivers/bluetooth/btrtl.h
+++ b/drivers/bluetooth/btrtl.h
@@ -109,8 +109,16 @@ enum {
 	__REALTEK_NUM_FLAGS,
 };
 
+struct rtl_dump_info {
+	const char *driver_name;
+	char *controller;
+	u32  fw_version;
+};
+
 struct btrealtek_data {
 	DECLARE_BITMAP(flags, __REALTEK_NUM_FLAGS);
+
+	struct rtl_dump_info rtl_dump;
 };
 
 #define btrealtek_set_flag(hdev, nr)					\
@@ -139,6 +147,7 @@ int btrtl_get_uart_settings(struct hci_dev *hdev,
 			    struct btrtl_device_info *btrtl_dev,
 			    unsigned int *controller_baudrate,
 			    u32 *device_baudrate, bool *flow_control);
+void btrtl_set_driver_name(struct hci_dev *hdev, const char *driver_name);
 
 #else
 
@@ -182,4 +191,8 @@ static inline int btrtl_get_uart_settings(struct hci_dev *hdev,
 	return -ENOENT;
 }
 
+static inline void btrtl_set_driver_name(struct hci_dev *hdev, const char *driver_name)
+{
+}
+
 #endif
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 764d176e97351..711beaa0ac562 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -887,10 +887,49 @@ static void btusb_intel_cmd_timeout(struct hci_dev *hdev)
 	gpiod_set_value_cansleep(reset_gpio, 0);
 }
 
+#define RTK_DEVCOREDUMP_CODE_MEMDUMP		0x01
+#define RTK_DEVCOREDUMP_CODE_HW_ERR		0x02
+#define RTK_DEVCOREDUMP_CODE_CMD_TIMEOUT	0x03
+
+#define RTK_SUB_EVENT_CODE_COREDUMP		0x34
+
+struct rtk_dev_coredump_hdr {
+	u8 type;
+	u8 code;
+	u8 reserved[2];
+} __packed;
+
+static inline void btusb_rtl_alloc_devcoredump(struct hci_dev *hdev,
+		struct rtk_dev_coredump_hdr *hdr, u8 *buf, u32 len)
+{
+	struct sk_buff *skb;
+
+	skb = alloc_skb(len + sizeof(*hdr), GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	skb_put_data(skb, hdr, sizeof(*hdr));
+	if (len)
+		skb_put_data(skb, buf, len);
+
+	if (!hci_devcd_init(hdev, skb->len)) {
+		hci_devcd_append(hdev, skb);
+		hci_devcd_complete(hdev);
+	} else {
+		bt_dev_err(hdev, "RTL: Failed to generate devcoredump");
+		kfree_skb(skb);
+	}
+}
+
 static void btusb_rtl_cmd_timeout(struct hci_dev *hdev)
 {
 	struct btusb_data *data = hci_get_drvdata(hdev);
 	struct gpio_desc *reset_gpio = data->reset_gpio;
+	struct rtk_dev_coredump_hdr hdr = {
+		.type = RTK_DEVCOREDUMP_CODE_CMD_TIMEOUT,
+	};
+
+	btusb_rtl_alloc_devcoredump(hdev, &hdr, NULL, 0);
 
 	if (++data->cmd_timeout_cnt < 5)
 		return;
@@ -917,6 +956,18 @@ static void btusb_rtl_cmd_timeout(struct hci_dev *hdev)
 	gpiod_set_value_cansleep(reset_gpio, 0);
 }
 
+static void btusb_rtl_hw_error(struct hci_dev *hdev, u8 code)
+{
+	struct rtk_dev_coredump_hdr hdr = {
+		.type = RTK_DEVCOREDUMP_CODE_HW_ERR,
+		.code = code,
+	};
+
+	bt_dev_err(hdev, "RTL: hw err, trigger devcoredump (%d)", code);
+
+	btusb_rtl_alloc_devcoredump(hdev, &hdr, NULL, 0);
+}
+
 static void btusb_qca_cmd_timeout(struct hci_dev *hdev)
 {
 	struct btusb_data *data = hci_get_drvdata(hdev);
@@ -2562,6 +2613,25 @@ static int btusb_setup_realtek(struct hci_dev *hdev)
 	return ret;
 }
 
+static int btusb_recv_event_realtek(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	if (skb->data[0] == HCI_VENDOR_PKT && skb->data[2] == RTK_SUB_EVENT_CODE_COREDUMP) {
+		struct rtk_dev_coredump_hdr hdr = {
+			.code = RTK_DEVCOREDUMP_CODE_MEMDUMP,
+		};
+
+		bt_dev_dbg(hdev, "RTL: received coredump vendor evt, len %u",
+			skb->len);
+
+		btusb_rtl_alloc_devcoredump(hdev, &hdr, skb->data, skb->len);
+		kfree_skb(skb);
+
+		return 0;
+	}
+
+	return hci_recv_frame(hdev, skb);
+}
+
 /* UHW CR mapping */
 #define MTK_BT_MISC		0x70002510
 #define MTK_BT_SUBSYS_RST	0x70002610
@@ -4201,6 +4271,8 @@ static int btusb_probe(struct usb_interface *intf,
 	} else if (id->driver_info & BTUSB_REALTEK) {
 		/* Allocate extra space for Realtek device */
 		priv_size += sizeof(struct btrealtek_data);
+
+		data->recv_event = btusb_recv_event_realtek;
 	}
 
 	data->recv_acl = hci_recv_frame;
@@ -4364,9 +4436,11 @@ static int btusb_probe(struct usb_interface *intf,
 
 	if (IS_ENABLED(CONFIG_BT_HCIBTUSB_RTL) &&
 	    (id->driver_info & BTUSB_REALTEK)) {
+		btrtl_set_driver_name(hdev, btusb_driver.name);
 		hdev->setup = btusb_setup_realtek;
 		hdev->shutdown = btrtl_shutdown_realtek;
 		hdev->cmd_timeout = btusb_rtl_cmd_timeout;
+		hdev->hw_error = btusb_rtl_hw_error;
 
 		/* Realtek devices need to set remote wakeup on auto-suspend */
 		set_bit(BTUSB_WAKEUP_AUTOSUSPEND, &data->flags);
-- 
GitLab


From a0bfde167b506423111ddb8cd71930497a40fc54 Mon Sep 17 00:00:00 2001
From: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Date: Tue, 30 May 2023 17:21:59 +0300
Subject: [PATCH 1078/1806] Bluetooth: ISO: Add support for connecting multiple
 BISes

It is required for some configurations to have multiple BISes as part
of the same BIG.

Similar to the flow implemented for unicast, DEFER_SETUP will also be
used to bind multiple BISes for the same BIG, before starting Periodic
Advertising and creating the BIG.

The user will have to open a new socket for each BIS. By setting the
BT_DEFER_SETUP socket option and calling connect, a new connection
will be added for the BIG and advertising handle set by the socket
QoS parameters. Since all BISes will be bound for the same BIG and
advertising handle, the socket QoS options and base parameters should
match for all connections.

By calling connect on a socket that does not have the BT_DEFER_SETUP
option set, periodic advertising will be started and the BIG will
be created, with a BIS for each previously bound connection. Since
a BIG cannot be reconfigured with additional BISes after creation,
no more connections can be bound for the BIG after the start periodic
advertising and create BIG commands have been queued.

The bis_cleanup function has also been updated, so that the advertising
set and the BIG will not be terminated unless there are no more
bound or connected BISes.

The HCI_CONN_BIG_CREATED connection flag has been added to indicate
that the BIG has been successfully created. This flag is checked at
bis_cleanup, so that the BIG is only terminated if the
HCI_LE_Create_BIG_Complete has been received.

This implementation has been tested on hardware, using the "isotest"
tool with an additional command line option, to specify the number of
BISes to create as part of the desired BIG:

    tools/isotest -i hci0 -s 00:00:00:00:00:00 -N 2 -G 1 -T 1

The btmon log shows that a BIG containing 2 BISes has been created:

< HCI Command: LE Create Broadcast Isochronous Group (0x08|0x0068) plen 31
        Handle: 0x01
        Advertising Handle: 0x01
        Number of BIS: 2
        SDU Interval: 10000 us (0x002710)
        Maximum SDU size: 40
        Maximum Latency: 10 ms (0x000a)
        RTN: 0x02
        PHY: LE 2M (0x02)
        Packing: Sequential (0x00)
        Framing: Unframed (0x00)
        Encryption: 0x00
        Broadcast Code: 00000000000000000000000000000000

> HCI Event: Command Status (0x0f) plen 4
      LE Create Broadcast Isochronous Group (0x08|0x0068) ncmd 1
        Status: Success (0x00)

> HCI Event: LE Meta Event (0x3e) plen 23
      LE Broadcast Isochronous Group Complete (0x1b)
        Status: Success (0x00)
        Handle: 0x01
        BIG Synchronization Delay: 1974 us (0x0007b6)
        Transport Latency: 1974 us (0x0007b6)
        PHY: LE 2M (0x02)
        NSE: 3
        BN: 1
        PTO: 1
        IRC: 3
        Maximum PDU: 40
        ISO Interval: 10.00 msec (0x0008)
        Connection Handle #0: 10
        Connection Handle #1: 11

< HCI Command: LE Setup Isochronous Data Path (0x08|0x006e) plen 13
        Handle: 10
        Data Path Direction: Input (Host to Controller) (0x00)
        Data Path: HCI (0x00)
        Coding Format: Transparent (0x03)
        Company Codec ID: Ericsson Technology Licensing (0)
        Vendor Codec ID: 0
        Controller Delay: 0 us (0x000000)
        Codec Configuration Length: 0
        Codec Configuration:

> HCI Event: Command Complete (0x0e) plen 6
      LE Setup Isochronous Data Path (0x08|0x006e) ncmd 1
        Status: Success (0x00)
        Handle: 10

< HCI Command: LE Setup Isochronous Data Path (0x08|0x006e) plen 13
        Handle: 11
        Data Path Direction: Input (Host to Controller) (0x00)
        Data Path: HCI (0x00)
        Coding Format: Transparent (0x03)
        Company Codec ID: Ericsson Technology Licensing (0)
        Vendor Codec ID: 0
        Controller Delay: 0 us (0x000000)
        Codec Configuration Length: 0
        Codec Configuration:

> HCI Event: Command Complete (0x0e) plen 6
      LE Setup Isochronous Data Path (0x08|0x006e) ncmd 1
        Status: Success (0x00)
        Handle: 11

< ISO Data TX: Handle 10 flags 0x02 dlen 44

< ISO Data TX: Handle 11 flags 0x02 dlen 44

> HCI Event: Number of Completed Packets (0x13) plen 5
        Num handles: 1
        Handle: 10
        Count: 1

> HCI Event: Number of Completed Packets (0x13) plen 5
        Num handles: 1
        Handle: 11
        Count: 1

Signed-off-by: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  30 ++++++
 net/bluetooth/hci_conn.c         | 152 +++++++++++++++++++++----------
 net/bluetooth/hci_event.c        |  52 +++++++----
 net/bluetooth/iso.c              |  28 ++++--
 4 files changed, 189 insertions(+), 73 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index da871581ef87b..c0bb58f1e86f8 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -974,6 +974,7 @@ enum {
 	HCI_CONN_SCANNING,
 	HCI_CONN_AUTH_FAILURE,
 	HCI_CONN_PER_ADV,
+	HCI_CONN_BIG_CREATED,
 };
 
 static inline bool hci_conn_ssp_enabled(struct hci_conn *conn)
@@ -1115,6 +1116,32 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev,
 	return NULL;
 }
 
+static inline struct hci_conn *
+hci_conn_hash_lookup_per_adv_bis(struct hci_dev *hdev,
+				 bdaddr_t *ba,
+				 __u8 big, __u8 bis)
+{
+	struct hci_conn_hash *h = &hdev->conn_hash;
+	struct hci_conn  *c;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(c, &h->list, list) {
+		if (bacmp(&c->dst, ba) || c->type != ISO_LINK ||
+			!test_bit(HCI_CONN_PER_ADV, &c->flags))
+			continue;
+
+		if (c->iso_qos.bcast.big == big &&
+		    c->iso_qos.bcast.bis == bis) {
+			rcu_read_unlock();
+			return c;
+		}
+	}
+	rcu_read_unlock();
+
+	return NULL;
+}
+
 static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev,
 								__u16 handle)
 {
@@ -1351,6 +1378,9 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst,
 				 __u16 setting, struct bt_codec *codec);
 struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst,
 			      __u8 dst_type, struct bt_iso_qos *qos);
+struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
+			      struct bt_iso_qos *qos,
+			      __u8 base_len, __u8 *base);
 struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst,
 				 __u8 dst_type, struct bt_iso_qos *qos);
 struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 76222565e2df0..13c266dbee671 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -792,6 +792,7 @@ struct iso_list_data {
 	};
 	int count;
 	struct iso_cig_params pdu;
+	bool big_term;
 };
 
 static void bis_list(struct hci_conn *conn, void *data)
@@ -828,11 +829,8 @@ static int terminate_big_sync(struct hci_dev *hdev, void *data)
 
 	hci_remove_ext_adv_instance_sync(hdev, d->bis, NULL);
 
-	/* Check if ISO connection is a BIS and terminate BIG if there are
-	 * no other connections using it.
-	 */
-	hci_conn_hash_list_state(hdev, find_bis, ISO_LINK, BT_CONNECTED, d);
-	if (d->count)
+	/* Only terminate BIG if it has been created */
+	if (!d->big_term)
 		return 0;
 
 	return hci_le_terminate_big_sync(hdev, d->big,
@@ -844,19 +842,21 @@ static void terminate_big_destroy(struct hci_dev *hdev, void *data, int err)
 	kfree(data);
 }
 
-static int hci_le_terminate_big(struct hci_dev *hdev, u8 big, u8 bis)
+static int hci_le_terminate_big(struct hci_dev *hdev, struct hci_conn *conn)
 {
 	struct iso_list_data *d;
 	int ret;
 
-	bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", big, bis);
+	bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", conn->iso_qos.bcast.big,
+		   conn->iso_qos.bcast.bis);
 
 	d = kzalloc(sizeof(*d), GFP_KERNEL);
 	if (!d)
 		return -ENOMEM;
 
-	d->big = big;
-	d->bis = bis;
+	d->big = conn->iso_qos.bcast.big;
+	d->bis = conn->iso_qos.bcast.bis;
+	d->big_term = test_and_clear_bit(HCI_CONN_BIG_CREATED, &conn->flags);
 
 	ret = hci_cmd_sync_queue(hdev, terminate_big_sync, d,
 				 terminate_big_destroy);
@@ -916,6 +916,7 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle)
 static void bis_cleanup(struct hci_conn *conn)
 {
 	struct hci_dev *hdev = conn->hdev;
+	struct hci_conn *bis;
 
 	bt_dev_dbg(hdev, "conn %p", conn);
 
@@ -923,8 +924,16 @@ static void bis_cleanup(struct hci_conn *conn)
 		if (!test_and_clear_bit(HCI_CONN_PER_ADV, &conn->flags))
 			return;
 
-		hci_le_terminate_big(hdev, conn->iso_qos.bcast.big,
-				     conn->iso_qos.bcast.bis);
+		/* Check if ISO connection is a BIS and terminate advertising
+		 * set and BIG if there are no other connections using it.
+		 */
+		bis = hci_conn_hash_lookup_bis(hdev, BDADDR_ANY,
+					       conn->iso_qos.bcast.big,
+					       conn->iso_qos.bcast.bis);
+		if (bis)
+			return;
+
+		hci_le_terminate_big(hdev, conn);
 	} else {
 		hci_le_big_terminate(hdev, conn->iso_qos.bcast.big,
 				     conn->sync_handle);
@@ -1495,10 +1504,10 @@ static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos)
 
 /* This function requires the caller holds hdev->lock */
 static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst,
-				    struct bt_iso_qos *qos)
+				    struct bt_iso_qos *qos, __u8 base_len,
+				    __u8 *base)
 {
 	struct hci_conn *conn;
-	struct iso_list_data data;
 	int err;
 
 	/* Let's make sure that le is enabled.*/
@@ -1516,24 +1525,27 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst,
 	if (err)
 		return ERR_PTR(err);
 
-	data.big = qos->bcast.big;
-	data.bis = qos->bcast.bis;
-	data.count = 0;
-
-	/* Check if there is already a matching BIG/BIS */
-	hci_conn_hash_list_state(hdev, bis_list, ISO_LINK, BT_BOUND, &data);
-	if (data.count)
+	/* Check if the LE Create BIG command has already been sent */
+	conn = hci_conn_hash_lookup_per_adv_bis(hdev, dst, qos->bcast.big,
+						qos->bcast.big);
+	if (conn)
 		return ERR_PTR(-EADDRINUSE);
 
-	conn = hci_conn_hash_lookup_bis(hdev, dst, qos->bcast.big, qos->bcast.bis);
-	if (conn)
+	/* Check BIS settings against other bound BISes, since all
+	 * BISes in a BIG must have the same value for all parameters
+	 */
+	conn = hci_conn_hash_lookup_bis(hdev, dst, qos->bcast.big,
+					qos->bcast.bis);
+
+	if (conn && (memcmp(qos, &conn->iso_qos, sizeof(*qos)) ||
+		     base_len != conn->le_per_adv_data_len ||
+		     memcmp(conn->le_per_adv_data, base, base_len)))
 		return ERR_PTR(-EADDRINUSE);
 
 	conn = hci_conn_add(hdev, ISO_LINK, dst, HCI_ROLE_MASTER);
 	if (!conn)
 		return ERR_PTR(-ENOMEM);
 
-	set_bit(HCI_CONN_PER_ADV, &conn->flags);
 	conn->state = BT_CONNECT;
 
 	hci_conn_hold(conn);
@@ -1747,12 +1759,21 @@ static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos)
 {
 	struct hci_dev *hdev = conn->hdev;
 	struct hci_cp_le_create_big cp;
+	struct iso_list_data data;
 
 	memset(&cp, 0, sizeof(cp));
 
+	data.big = qos->bcast.big;
+	data.bis = qos->bcast.bis;
+	data.count = 0;
+
+	/* Create a BIS for each bound connection */
+	hci_conn_hash_list_state(hdev, bis_list, ISO_LINK,
+				 BT_BOUND, &data);
+
 	cp.handle = qos->bcast.big;
 	cp.adv_handle = qos->bcast.bis;
-	cp.num_bis  = 0x01;
+	cp.num_bis  = data.count;
 	hci_cpu_to_le24(qos->bcast.out.interval, cp.bis.sdu_interval);
 	cp.bis.sdu = cpu_to_le16(qos->bcast.out.sdu);
 	cp.bis.latency =  cpu_to_le16(qos->bcast.out.latency);
@@ -2051,16 +2072,6 @@ static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn,
 		qos->latency = conn->le_conn_latency;
 }
 
-static void hci_bind_bis(struct hci_conn *conn,
-			 struct bt_iso_qos *qos)
-{
-	/* Update LINK PHYs according to QoS preference */
-	conn->le_tx_phy = qos->bcast.out.phy;
-	conn->le_tx_phy = qos->bcast.out.phy;
-	conn->iso_qos = *qos;
-	conn->state = BT_BOUND;
-}
-
 static int create_big_sync(struct hci_dev *hdev, void *data)
 {
 	struct hci_conn *conn = data;
@@ -2183,27 +2194,80 @@ static void create_big_complete(struct hci_dev *hdev, void *data, int err)
 	}
 }
 
-struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
-				 __u8 dst_type, struct bt_iso_qos *qos,
-				 __u8 base_len, __u8 *base)
+struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
+			      struct bt_iso_qos *qos,
+			      __u8 base_len, __u8 *base)
 {
 	struct hci_conn *conn;
-	int err;
+	__u8 eir[HCI_MAX_PER_AD_LENGTH];
+
+	if (base_len && base)
+		base_len = eir_append_service_data(eir, 0,  0x1851,
+						   base, base_len);
 
 	/* We need hci_conn object using the BDADDR_ANY as dst */
-	conn = hci_add_bis(hdev, dst, qos);
+	conn = hci_add_bis(hdev, dst, qos, base_len, eir);
 	if (IS_ERR(conn))
 		return conn;
 
-	hci_bind_bis(conn, qos);
+	/* Update LINK PHYs according to QoS preference */
+	conn->le_tx_phy = qos->bcast.out.phy;
+	conn->le_tx_phy = qos->bcast.out.phy;
 
 	/* Add Basic Announcement into Peridic Adv Data if BASE is set */
 	if (base_len && base) {
-		base_len = eir_append_service_data(conn->le_per_adv_data, 0,
-						   0x1851, base, base_len);
+		memcpy(conn->le_per_adv_data,  eir, sizeof(eir));
 		conn->le_per_adv_data_len = base_len;
 	}
 
+	hci_iso_qos_setup(hdev, conn, &qos->bcast.out,
+			  conn->le_tx_phy ? conn->le_tx_phy :
+			  hdev->le_tx_def_phys);
+
+	conn->iso_qos = *qos;
+	conn->state = BT_BOUND;
+
+	return conn;
+}
+
+static void bis_mark_per_adv(struct hci_conn *conn, void *data)
+{
+	struct iso_list_data *d = data;
+
+	/* Skip if not broadcast/ANY address */
+	if (bacmp(&conn->dst, BDADDR_ANY))
+		return;
+
+	if (d->big != conn->iso_qos.bcast.big ||
+	    d->bis == BT_ISO_QOS_BIS_UNSET ||
+	    d->bis != conn->iso_qos.bcast.bis)
+		return;
+
+	set_bit(HCI_CONN_PER_ADV, &conn->flags);
+}
+
+struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
+				 __u8 dst_type, struct bt_iso_qos *qos,
+				 __u8 base_len, __u8 *base)
+{
+	struct hci_conn *conn;
+	int err;
+	struct iso_list_data data;
+
+	conn = hci_bind_bis(hdev, dst, qos, base_len, base);
+	if (IS_ERR(conn))
+		return conn;
+
+	data.big = qos->bcast.big;
+	data.bis = qos->bcast.bis;
+
+	/* Set HCI_CONN_PER_ADV for all bound connections, to mark that
+	 * the start periodic advertising and create BIG commands have
+	 * been queued
+	 */
+	hci_conn_hash_list_state(hdev, bis_mark_per_adv, ISO_LINK,
+				 BT_BOUND, &data);
+
 	/* Queue start periodic advertising and create BIG */
 	err = hci_cmd_sync_queue(hdev, create_big_sync, conn,
 				 create_big_complete);
@@ -2212,10 +2276,6 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
 		return ERR_PTR(err);
 	}
 
-	hci_iso_qos_setup(hdev, conn, &qos->bcast.out,
-			  conn->le_tx_phy ? conn->le_tx_phy :
-			  hdev->le_tx_def_phys);
-
 	return conn;
 }
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 31ca320ce38d3..86a7e4b3b98da 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6936,6 +6936,7 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data,
 {
 	struct hci_evt_le_create_big_complete *ev = data;
 	struct hci_conn *conn;
+	__u8 bis_idx = 0;
 
 	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
 
@@ -6944,33 +6945,44 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data,
 		return;
 
 	hci_dev_lock(hdev);
+	rcu_read_lock();
 
-	conn = hci_conn_hash_lookup_big(hdev, ev->handle);
-	if (!conn)
-		goto unlock;
+	/* Connect all BISes that are bound to the BIG */
+	list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
+		if (bacmp(&conn->dst, BDADDR_ANY) ||
+		    conn->type != ISO_LINK ||
+		    conn->iso_qos.bcast.big != ev->handle)
+			continue;
 
-	if (conn->type != ISO_LINK) {
-		bt_dev_err(hdev,
-			   "Invalid connection link type handle 0x%2.2x",
-			   ev->handle);
-		goto unlock;
-	}
+		conn->handle = __le16_to_cpu(ev->bis_handle[bis_idx++]);
 
-	if (ev->num_bis)
-		conn->handle = __le16_to_cpu(ev->bis_handle[0]);
+		if (!ev->status) {
+			conn->state = BT_CONNECTED;
+			set_bit(HCI_CONN_BIG_CREATED, &conn->flags);
+			rcu_read_unlock();
+			hci_debugfs_create_conn(conn);
+			hci_conn_add_sysfs(conn);
+			hci_iso_setup_path(conn);
+			rcu_read_lock();
+			continue;
+		}
 
-	if (!ev->status) {
-		conn->state = BT_CONNECTED;
-		hci_debugfs_create_conn(conn);
-		hci_conn_add_sysfs(conn);
-		hci_iso_setup_path(conn);
-		goto unlock;
+		hci_connect_cfm(conn, ev->status);
+		rcu_read_unlock();
+		hci_conn_del(conn);
+		rcu_read_lock();
 	}
 
-	hci_connect_cfm(conn, ev->status);
-	hci_conn_del(conn);
+	if (!ev->status && !bis_idx)
+		/* If no BISes have been connected for the BIG,
+		 * terminate. This is in case all bound connections
+		 * have been closed before the BIG creation
+		 * has completed.
+		 */
+		hci_le_terminate_big_sync(hdev, ev->handle,
+					  HCI_ERROR_LOCAL_HOST_TERM);
 
-unlock:
+	rcu_read_unlock();
 	hci_dev_unlock(hdev);
 }
 
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 505d622472688..5808d57c1d7ba 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -287,13 +287,24 @@ static int iso_connect_bis(struct sock *sk)
 		goto unlock;
 	}
 
-	hcon = hci_connect_bis(hdev, &iso_pi(sk)->dst,
-			       le_addr_type(iso_pi(sk)->dst_type),
-			       &iso_pi(sk)->qos, iso_pi(sk)->base_len,
-			       iso_pi(sk)->base);
-	if (IS_ERR(hcon)) {
-		err = PTR_ERR(hcon);
-		goto unlock;
+	/* Just bind if DEFER_SETUP has been set */
+	if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
+		hcon = hci_bind_bis(hdev, &iso_pi(sk)->dst,
+				    &iso_pi(sk)->qos, iso_pi(sk)->base_len,
+				    iso_pi(sk)->base);
+		if (IS_ERR(hcon)) {
+			err = PTR_ERR(hcon);
+			goto unlock;
+		}
+	} else {
+		hcon = hci_connect_bis(hdev, &iso_pi(sk)->dst,
+				       le_addr_type(iso_pi(sk)->dst_type),
+				       &iso_pi(sk)->qos, iso_pi(sk)->base_len,
+				       iso_pi(sk)->base);
+		if (IS_ERR(hcon)) {
+			err = PTR_ERR(hcon);
+			goto unlock;
+		}
 	}
 
 	conn = iso_conn_add(hcon);
@@ -317,6 +328,9 @@ static int iso_connect_bis(struct sock *sk)
 	if (hcon->state == BT_CONNECTED) {
 		iso_sock_clear_timer(sk);
 		sk->sk_state = BT_CONNECTED;
+	} else if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
+		iso_sock_clear_timer(sk);
+		sk->sk_state = BT_CONNECT;
 	} else {
 		sk->sk_state = BT_CONNECT;
 		iso_sock_set_timer(sk, sk->sk_sndtimeo);
-- 
GitLab


From 7f74563e6140e42b4ffae62adbef7a65967a3f98 Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Thu, 1 Jun 2023 09:34:46 +0300
Subject: [PATCH 1079/1806] Bluetooth: ISO: do not emit new LE Create CIS if
 previous is pending

LE Create CIS command shall not be sent before all CIS Established
events from its previous invocation have been processed. Currently it is
sent via hci_sync but that only waits for the first event, but there can
be multiple.

Make it wait for all events, and simplify the CIS creation as follows:

Add new flag HCI_CONN_CREATE_CIS, which is set if Create CIS has been
sent for the connection but it is not yet completed.

Make BT_CONNECT state to mean the connection wants Create CIS.

On events after which new Create CIS may need to be sent, send it if
possible and some connections need it. These events are:
hci_connect_cis, iso_connect_cfm, hci_cs_le_create_cis,
hci_le_cis_estabilished_evt.

The Create CIS status/completion events shall queue new Create CIS only
if at least one of the connections transitions away from BT_CONNECT, so
that we don't loop if controller is sending bogus events.

This fixes sending multiple CIS Create for the same CIS in the
"ISO AC 6(i) - Success" BlueZ test case:

< HCI Command: LE Create Co.. (0x08|0x0064) plen 9  #129 [hci0]
        Number of CIS: 2
        CIS Handle: 257
        ACL Handle: 42
        CIS Handle: 258
        ACL Handle: 42
> HCI Event: Command Status (0x0f) plen 4           #130 [hci0]
      LE Create Connected Isochronous Stream (0x08|0x0064) ncmd 1
        Status: Success (0x00)
> HCI Event: LE Meta Event (0x3e) plen 29           #131 [hci0]
      LE Connected Isochronous Stream Established (0x19)
        Status: Success (0x00)
        Connection Handle: 257
        ...
< HCI Command: LE Setup Is.. (0x08|0x006e) plen 13  #132 [hci0]
        ...
> HCI Event: Command Complete (0x0e) plen 6         #133 [hci0]
      LE Setup Isochronous Data Path (0x08|0x006e) ncmd 1
        ...
< HCI Command: LE Create Co.. (0x08|0x0064) plen 5  #134 [hci0]
        Number of CIS: 1
        CIS Handle: 258
        ACL Handle: 42
> HCI Event: Command Status (0x0f) plen 4           #135 [hci0]
      LE Create Connected Isochronous Stream (0x08|0x0064) ncmd 1
        Status: ACL Connection Already Exists (0x0b)
> HCI Event: LE Meta Event (0x3e) plen 29           #136 [hci0]
      LE Connected Isochronous Stream Established (0x19)
        Status: Success (0x00)
        Connection Handle: 258
        ...

Fixes: c09b80be6ffc ("Bluetooth: hci_conn: Fix not waiting for HCI_EVT_LE_CIS_ESTABLISHED")
Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  4 +-
 include/net/bluetooth/hci_sync.h |  2 +-
 net/bluetooth/hci_conn.c         | 74 +++++++++++---------------
 net/bluetooth/hci_event.c        | 25 +++++++--
 net/bluetooth/hci_sync.c         | 90 ++++++++++++++++++++++----------
 net/bluetooth/iso.c              |  2 +-
 6 files changed, 119 insertions(+), 78 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index c0bb58f1e86f8..ad39d09e9bd66 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -975,6 +975,7 @@ enum {
 	HCI_CONN_AUTH_FAILURE,
 	HCI_CONN_PER_ADV,
 	HCI_CONN_BIG_CREATED,
+	HCI_CONN_CREATE_CIS,
 };
 
 static inline bool hci_conn_ssp_enabled(struct hci_conn *conn)
@@ -1351,7 +1352,8 @@ int hci_disconnect(struct hci_conn *conn, __u8 reason);
 bool hci_setup_sync(struct hci_conn *conn, __u16 handle);
 void hci_sco_setup(struct hci_conn *conn, __u8 status);
 bool hci_iso_setup_path(struct hci_conn *conn);
-int hci_le_create_cis(struct hci_conn *conn);
+int hci_le_create_cis_pending(struct hci_dev *hdev);
+int hci_conn_check_create_cis(struct hci_conn *conn);
 
 struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst,
 			      u8 role);
diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index 2495be4d8b828..b516a0f4a55b8 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -124,7 +124,7 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason);
 
 int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn);
 
-int hci_le_create_cis_sync(struct hci_dev *hdev, struct hci_conn *conn);
+int hci_le_create_cis_sync(struct hci_dev *hdev);
 
 int hci_le_remove_cig_sync(struct hci_dev *hdev, u8 handle);
 
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 13c266dbee671..4b5223e62141c 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1990,59 +1990,47 @@ bool hci_iso_setup_path(struct hci_conn *conn)
 	return true;
 }
 
-static int hci_create_cis_sync(struct hci_dev *hdev, void *data)
+int hci_conn_check_create_cis(struct hci_conn *conn)
 {
-	return hci_le_create_cis_sync(hdev, data);
-}
+	if (conn->type != ISO_LINK || !bacmp(&conn->dst, BDADDR_ANY))
+		return -EINVAL;
 
-int hci_le_create_cis(struct hci_conn *conn)
-{
-	struct hci_conn *cis;
-	struct hci_link *link, *t;
-	struct hci_dev *hdev = conn->hdev;
-	int err;
+	if (!conn->parent || conn->parent->state != BT_CONNECTED ||
+	    conn->state != BT_CONNECT || conn->handle == HCI_CONN_HANDLE_UNSET)
+		return 1;
 
-	bt_dev_dbg(hdev, "hcon %p", conn);
+	return 0;
+}
 
-	switch (conn->type) {
-	case LE_LINK:
-		if (conn->state != BT_CONNECTED || list_empty(&conn->link_list))
-			return -EINVAL;
+static int hci_create_cis_sync(struct hci_dev *hdev, void *data)
+{
+	return hci_le_create_cis_sync(hdev);
+}
 
-		cis = NULL;
+int hci_le_create_cis_pending(struct hci_dev *hdev)
+{
+	struct hci_conn *conn;
+	bool pending = false;
 
-		/* hci_conn_link uses list_add_tail_rcu so the list is in
-		 * the same order as the connections are requested.
-		 */
-		list_for_each_entry_safe(link, t, &conn->link_list, list) {
-			if (link->conn->state == BT_BOUND) {
-				err = hci_le_create_cis(link->conn);
-				if (err)
-					return err;
+	rcu_read_lock();
 
-				cis = link->conn;
-			}
+	list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
+		if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) {
+			rcu_read_unlock();
+			return -EBUSY;
 		}
 
-		return cis ? 0 : -EINVAL;
-	case ISO_LINK:
-		cis = conn;
-		break;
-	default:
-		return -EINVAL;
+		if (!hci_conn_check_create_cis(conn))
+			pending = true;
 	}
 
-	if (cis->state == BT_CONNECT)
+	rcu_read_unlock();
+
+	if (!pending)
 		return 0;
 
 	/* Queue Create CIS */
-	err = hci_cmd_sync_queue(hdev, hci_create_cis_sync, cis, NULL);
-	if (err)
-		return err;
-
-	cis->state = BT_CONNECT;
-
-	return 0;
+	return hci_cmd_sync_queue(hdev, hci_create_cis_sync, NULL, NULL);
 }
 
 static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn,
@@ -2317,11 +2305,9 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst,
 		return ERR_PTR(-ENOLINK);
 	}
 
-	/* If LE is already connected and CIS handle is already set proceed to
-	 * Create CIS immediately.
-	 */
-	if (le->state == BT_CONNECTED && cis->handle != HCI_CONN_HANDLE_UNSET)
-		hci_le_create_cis(cis);
+	cis->state = BT_CONNECT;
+
+	hci_le_create_cis_pending(hdev);
 
 	return cis;
 }
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 86a7e4b3b98da..e7249ed3f5f2e 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3810,6 +3810,7 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data,
 	struct hci_cp_le_set_cig_params *cp;
 	struct hci_conn *conn;
 	u8 status = rp->status;
+	bool pending = false;
 	int i;
 
 	bt_dev_dbg(hdev, "status 0x%2.2x", rp->status);
@@ -3852,13 +3853,15 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data,
 
 		bt_dev_dbg(hdev, "%p handle 0x%4.4x parent %p", conn,
 			   conn->handle, conn->parent);
-
-		/* Create CIS if LE is already connected */
-		if (conn->parent && conn->parent->state == BT_CONNECTED)
-			hci_le_create_cis(conn);
+		
+		if (conn->state == BT_CONNECT)
+			pending = true;
 	}
 
 unlock:
+	if (pending)
+		hci_le_create_cis_pending(hdev);
+
 	hci_dev_unlock(hdev);
 
 	return rp->status;
@@ -4224,6 +4227,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, void *data,
 static void hci_cs_le_create_cis(struct hci_dev *hdev, u8 status)
 {
 	struct hci_cp_le_create_cis *cp;
+	bool pending = false;
 	int i;
 
 	bt_dev_dbg(hdev, "status 0x%2.2x", status);
@@ -4246,12 +4250,18 @@ static void hci_cs_le_create_cis(struct hci_dev *hdev, u8 status)
 
 		conn = hci_conn_hash_lookup_handle(hdev, handle);
 		if (conn) {
+			if (test_and_clear_bit(HCI_CONN_CREATE_CIS,
+					       &conn->flags))
+				pending = true;
 			conn->state = BT_CLOSED;
 			hci_connect_cfm(conn, status);
 			hci_conn_del(conn);
 		}
 	}
 
+	if (pending)
+		hci_le_create_cis_pending(hdev);
+
 	hci_dev_unlock(hdev);
 }
 
@@ -6790,6 +6800,7 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data,
 	struct hci_evt_le_cis_established *ev = data;
 	struct hci_conn *conn;
 	struct bt_iso_qos *qos;
+	bool pending = false;
 	u16 handle = __le16_to_cpu(ev->handle);
 
 	bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
@@ -6813,6 +6824,8 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data,
 
 	qos = &conn->iso_qos;
 
+	pending = test_and_clear_bit(HCI_CONN_CREATE_CIS, &conn->flags);
+
 	/* Convert ISO Interval (1.25 ms slots) to SDU Interval (us) */
 	qos->ucast.in.interval = le16_to_cpu(ev->interval) * 1250;
 	qos->ucast.out.interval = qos->ucast.in.interval;
@@ -6854,10 +6867,14 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data,
 		goto unlock;
 	}
 
+	conn->state = BT_CLOSED;
 	hci_connect_cfm(conn, ev->status);
 	hci_conn_del(conn);
 
 unlock:
+	if (pending)
+		hci_le_create_cis_pending(hdev);
+
 	hci_dev_unlock(hdev);
 }
 
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 4d1e32bb6a9c6..b617d1dd247a5 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -6260,56 +6260,92 @@ done:
 	return err;
 }
 
-int hci_le_create_cis_sync(struct hci_dev *hdev, struct hci_conn *conn)
+int hci_le_create_cis_sync(struct hci_dev *hdev)
 {
 	struct {
 		struct hci_cp_le_create_cis cp;
 		struct hci_cis cis[0x1f];
 	} cmd;
-	u8 cig;
-	struct hci_conn *hcon = conn;
+	struct hci_conn *conn;
+	u8 cig = BT_ISO_QOS_CIG_UNSET;
+
+	/* The spec allows only one pending LE Create CIS command at a time. If
+	 * the command is pending now, don't do anything. We check for pending
+	 * connections after each CIS Established event.
+	 *
+	 * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
+	 * page 2566:
+	 *
+	 * If the Host issues this command before all the
+	 * HCI_LE_CIS_Established events from the previous use of the
+	 * command have been generated, the Controller shall return the
+	 * error code Command Disallowed (0x0C).
+	 *
+	 * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
+	 * page 2567:
+	 *
+	 * When the Controller receives the HCI_LE_Create_CIS command, the
+	 * Controller sends the HCI_Command_Status event to the Host. An
+	 * HCI_LE_CIS_Established event will be generated for each CIS when it
+	 * is established or if it is disconnected or considered lost before
+	 * being established; until all the events are generated, the command
+	 * remains pending.
+	 */
 
 	memset(&cmd, 0, sizeof(cmd));
-	cmd.cis[0].acl_handle = cpu_to_le16(conn->parent->handle);
-	cmd.cis[0].cis_handle = cpu_to_le16(conn->handle);
-	cmd.cp.num_cis++;
-	cig = conn->iso_qos.ucast.cig;
 
 	hci_dev_lock(hdev);
 
 	rcu_read_lock();
 
+	/* Wait until previous Create CIS has completed */
 	list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
-		struct hci_cis *cis = &cmd.cis[cmd.cp.num_cis];
+		if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags))
+			goto done;
+	}
 
-		if (conn == hcon || conn->type != ISO_LINK ||
-		    conn->state == BT_CONNECTED ||
-		    conn->iso_qos.ucast.cig != cig)
+	/* Find CIG with all CIS ready */
+	list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
+		struct hci_conn *link;
+
+		if (hci_conn_check_create_cis(conn))
 			continue;
 
-		/* Check if all CIS(s) belonging to a CIG are ready */
-		if (!conn->parent || conn->parent->state != BT_CONNECTED ||
-		    conn->state != BT_CONNECT) {
-			cmd.cp.num_cis = 0;
-			break;
+		cig = conn->iso_qos.ucast.cig;
+
+		list_for_each_entry_rcu(link, &hdev->conn_hash.list, list) {
+			if (hci_conn_check_create_cis(link) > 0 &&
+			    link->iso_qos.ucast.cig == cig &&
+			    link->state != BT_CONNECTED) {
+				cig = BT_ISO_QOS_CIG_UNSET;
+				break;
+			}
 		}
 
-		/* Group all CIS with state BT_CONNECT since the spec don't
-		 * allow to send them individually:
-		 *
-		 * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
-		 * page 2566:
-		 *
-		 * If the Host issues this command before all the
-		 * HCI_LE_CIS_Established events from the previous use of the
-		 * command have been generated, the Controller shall return the
-		 * error code Command Disallowed (0x0C).
-		 */
+		if (cig != BT_ISO_QOS_CIG_UNSET)
+			break;
+	}
+
+	if (cig == BT_ISO_QOS_CIG_UNSET)
+		goto done;
+
+	list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
+		struct hci_cis *cis = &cmd.cis[cmd.cp.num_cis];
+
+		if (hci_conn_check_create_cis(conn) ||
+		    conn->iso_qos.ucast.cig != cig)
+			continue;
+
+		set_bit(HCI_CONN_CREATE_CIS, &conn->flags);
 		cis->acl_handle = cpu_to_le16(conn->parent->handle);
 		cis->cis_handle = cpu_to_le16(conn->handle);
 		cmd.cp.num_cis++;
+
+		if (cmd.cp.num_cis >= ARRAY_SIZE(cmd.cis))
+			break;
 	}
 
+done:
 	rcu_read_unlock();
 
 	hci_dev_unlock(hdev);
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 5808d57c1d7ba..5db4d68c96d5c 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1690,7 +1690,7 @@ static void iso_connect_cfm(struct hci_conn *hcon, __u8 status)
 		}
 
 		/* Create CIS if pending */
-		hci_le_create_cis(hcon);
+		hci_le_create_cis_pending(hcon->hdev);
 		return;
 	}
 
-- 
GitLab


From 6b42f04e241732158592aac6241822cd6b4a7aae Mon Sep 17 00:00:00 2001
From: Max Chou <max.chou@realtek.com>
Date: Tue, 30 May 2023 16:34:20 +0800
Subject: [PATCH 1080/1806] Bluetooth: btrtl: Correct the length of the HCI
 command for drop fw

The original code did not determine the length value of the HCI command
for drop fw even there's no parameter needed. In this commit, use struct
hci_command_hdr to manage opcode and length. It would be more regular and
more readable.

Suggested-by: Alex Lu <alex_lu@realsil.com.cn>
Signed-off-by: Max Chou <max.chou@realtek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btrtl.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index 9a6ae8a2adfc8..04399b3c39a0b 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -1044,12 +1044,11 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev,
 	struct btrtl_device_info *btrtl_dev;
 	struct sk_buff *skb;
 	struct hci_rp_read_local_version *resp;
+	struct hci_command_hdr *cmd;
 	char cfg_name[40];
 	u16 hci_rev, lmp_subver;
 	u8 hci_ver, lmp_ver, chip_type = 0;
 	int ret;
-	u16 opcode;
-	u8 cmd[2];
 	u8 reg_val[2];
 
 	btrtl_dev = kzalloc(sizeof(*btrtl_dev), GFP_KERNEL);
@@ -1118,15 +1117,14 @@ next:
 		btrtl_dev->drop_fw = false;
 
 	if (btrtl_dev->drop_fw) {
-		opcode = hci_opcode_pack(0x3f, 0x66);
-		cmd[0] = opcode & 0xff;
-		cmd[1] = opcode >> 8;
-
-		skb = bt_skb_alloc(sizeof(cmd), GFP_KERNEL);
+		skb = bt_skb_alloc(sizeof(*cmd), GFP_KERNEL);
 		if (!skb)
 			goto err_free;
 
-		skb_put_data(skb, cmd, sizeof(cmd));
+		cmd = skb_put(skb, HCI_COMMAND_HDR_SIZE);
+		cmd->opcode = cpu_to_le16(0xfc66);
+		cmd->plen = 0;
+
 		hci_skb_pkt_type(skb) = HCI_COMMAND_PKT;
 
 		ret = hdev->send(hdev, skb);
-- 
GitLab


From 6bfa273e533d7b25eee3d74e28a7fe8e6a8e7a93 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 25 May 2023 16:46:41 -0700
Subject: [PATCH 1081/1806] Bluetooth: Consolidate code around sk_alloc into a
 helper function

This consolidates code around sk_alloc into bt_sock_alloc which does
take care of common initialization.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/bluetooth.h |  2 ++
 net/bluetooth/af_bluetooth.c      | 21 +++++++++++++++++++++
 net/bluetooth/bnep/sock.c         | 10 +---------
 net/bluetooth/hci_sock.c          | 10 ++--------
 net/bluetooth/iso.c               | 10 +---------
 net/bluetooth/l2cap_sock.c        | 10 +---------
 net/bluetooth/rfcomm/sock.c       | 13 +++----------
 net/bluetooth/sco.c               | 10 +---------
 8 files changed, 32 insertions(+), 54 deletions(-)

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index af729859385ed..60689a07b82cb 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -400,6 +400,8 @@ int  bt_sock_register(int proto, const struct net_proto_family *ops);
 void bt_sock_unregister(int proto);
 void bt_sock_link(struct bt_sock_list *l, struct sock *s);
 void bt_sock_unlink(struct bt_sock_list *l, struct sock *s);
+struct sock *bt_sock_alloc(struct net *net, struct socket *sock,
+			   struct proto *prot, int proto, gfp_t prio, int kern);
 int  bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		     int flags);
 int  bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg,
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 1c3c7ff5c3c66..6035422e13da5 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -140,6 +140,27 @@ static int bt_sock_create(struct net *net, struct socket *sock, int proto,
 	return err;
 }
 
+struct sock *bt_sock_alloc(struct net *net, struct socket *sock,
+			   struct proto *prot, int proto, gfp_t prio, int kern)
+{
+	struct sock *sk;
+
+	sk = sk_alloc(net, PF_BLUETOOTH, prio, prot, kern);
+	if (!sk)
+		return NULL;
+
+	sock_init_data(sock, sk);
+	INIT_LIST_HEAD(&bt_sk(sk)->accept_q);
+
+	sock_reset_flag(sk, SOCK_ZAPPED);
+
+	sk->sk_protocol = proto;
+	sk->sk_state    = BT_OPEN;
+
+	return sk;
+}
+EXPORT_SYMBOL(bt_sock_alloc);
+
 void bt_sock_link(struct bt_sock_list *l, struct sock *sk)
 {
 	write_lock(&l->lock);
diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c
index 57d509d77cb46..00d47bcf4d7dc 100644
--- a/net/bluetooth/bnep/sock.c
+++ b/net/bluetooth/bnep/sock.c
@@ -205,21 +205,13 @@ static int bnep_sock_create(struct net *net, struct socket *sock, int protocol,
 	if (sock->type != SOCK_RAW)
 		return -ESOCKTNOSUPPORT;
 
-	sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &bnep_proto, kern);
+	sk = bt_sock_alloc(net, sock, &bnep_proto, protocol, GFP_ATOMIC, kern);
 	if (!sk)
 		return -ENOMEM;
 
-	sock_init_data(sock, sk);
-
 	sock->ops = &bnep_sock_ops;
-
 	sock->state = SS_UNCONNECTED;
 
-	sock_reset_flag(sk, SOCK_ZAPPED);
-
-	sk->sk_protocol = protocol;
-	sk->sk_state	= BT_OPEN;
-
 	bt_sock_link(&bnep_sk_list, sk);
 	return 0;
 }
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 1d249d839819d..9c45586f58189 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -2143,18 +2143,12 @@ static int hci_sock_create(struct net *net, struct socket *sock, int protocol,
 
 	sock->ops = &hci_sock_ops;
 
-	sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hci_sk_proto, kern);
+	sk = bt_sock_alloc(net, sock, &hci_sk_proto, protocol, GFP_ATOMIC,
+			   kern);
 	if (!sk)
 		return -ENOMEM;
 
-	sock_init_data(sock, sk);
-
-	sock_reset_flag(sk, SOCK_ZAPPED);
-
-	sk->sk_protocol = protocol;
-
 	sock->state = SS_UNCONNECTED;
-	sk->sk_state = BT_OPEN;
 	sk->sk_destruct = hci_sock_destruct;
 
 	bt_sock_link(&hci_sk_list, sk);
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 5db4d68c96d5c..84d238d0639a6 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -738,21 +738,13 @@ static struct sock *iso_sock_alloc(struct net *net, struct socket *sock,
 {
 	struct sock *sk;
 
-	sk = sk_alloc(net, PF_BLUETOOTH, prio, &iso_proto, kern);
+	sk = bt_sock_alloc(net, sock, &iso_proto, proto, prio, kern);
 	if (!sk)
 		return NULL;
 
-	sock_init_data(sock, sk);
-	INIT_LIST_HEAD(&bt_sk(sk)->accept_q);
-
 	sk->sk_destruct = iso_sock_destruct;
 	sk->sk_sndtimeo = ISO_CONN_TIMEOUT;
 
-	sock_reset_flag(sk, SOCK_ZAPPED);
-
-	sk->sk_protocol = proto;
-	sk->sk_state    = BT_OPEN;
-
 	/* Set address type as public as default src address is BDADDR_ANY */
 	iso_pi(sk)->src_type = BDADDR_LE_PUBLIC;
 
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 947ca580bb9a2..9ef936f27a6a8 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1858,21 +1858,13 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 	struct sock *sk;
 	struct l2cap_chan *chan;
 
-	sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto, kern);
+	sk = bt_sock_alloc(net, sock, &l2cap_proto, proto, prio, kern);
 	if (!sk)
 		return NULL;
 
-	sock_init_data(sock, sk);
-	INIT_LIST_HEAD(&bt_sk(sk)->accept_q);
-
 	sk->sk_destruct = l2cap_sock_destruct;
 	sk->sk_sndtimeo = L2CAP_CONN_TIMEOUT;
 
-	sock_reset_flag(sk, SOCK_ZAPPED);
-
-	sk->sk_protocol = proto;
-	sk->sk_state = BT_OPEN;
-
 	chan = l2cap_chan_create();
 	if (!chan) {
 		sk_free(sk);
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 4397e14ff560f..b54e8a530f55a 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -268,18 +268,16 @@ static struct proto rfcomm_proto = {
 	.obj_size	= sizeof(struct rfcomm_pinfo)
 };
 
-static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern)
+static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock,
+				      int proto, gfp_t prio, int kern)
 {
 	struct rfcomm_dlc *d;
 	struct sock *sk;
 
-	sk = sk_alloc(net, PF_BLUETOOTH, prio, &rfcomm_proto, kern);
+	sk = bt_sock_alloc(net, sock, &rfcomm_proto, proto, prio, kern);
 	if (!sk)
 		return NULL;
 
-	sock_init_data(sock, sk);
-	INIT_LIST_HEAD(&bt_sk(sk)->accept_q);
-
 	d = rfcomm_dlc_alloc(prio);
 	if (!d) {
 		sk_free(sk);
@@ -298,11 +296,6 @@ static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int
 	sk->sk_sndbuf = RFCOMM_MAX_CREDITS * RFCOMM_DEFAULT_MTU * 10;
 	sk->sk_rcvbuf = RFCOMM_MAX_CREDITS * RFCOMM_DEFAULT_MTU * 10;
 
-	sock_reset_flag(sk, SOCK_ZAPPED);
-
-	sk->sk_protocol = proto;
-	sk->sk_state    = BT_OPEN;
-
 	bt_sock_link(&rfcomm_sk_list, sk);
 
 	BT_DBG("sk %p", sk);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 7762604ddfc05..ec6dce488a400 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -504,21 +504,13 @@ static struct sock *sco_sock_alloc(struct net *net, struct socket *sock,
 {
 	struct sock *sk;
 
-	sk = sk_alloc(net, PF_BLUETOOTH, prio, &sco_proto, kern);
+	sk = bt_sock_alloc(net, sock, &sco_proto, proto, prio, kern);
 	if (!sk)
 		return NULL;
 
-	sock_init_data(sock, sk);
-	INIT_LIST_HEAD(&bt_sk(sk)->accept_q);
-
 	sk->sk_destruct = sco_sock_destruct;
 	sk->sk_sndtimeo = SCO_CONN_TIMEOUT;
 
-	sock_reset_flag(sk, SOCK_ZAPPED);
-
-	sk->sk_protocol = proto;
-	sk->sk_state    = BT_OPEN;
-
 	sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT;
 	sco_pi(sk)->codec.id = BT_CODEC_CVSD;
 	sco_pi(sk)->codec.cid = 0xffff;
-- 
GitLab


From 464c702fb9374ff8f3f816f24fb7ac719dd20e1e Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 25 May 2023 16:46:42 -0700
Subject: [PATCH 1082/1806] Bluetooth: Init sk_peer_* on bt_sock_alloc

This makes sure peer information is always available via sock when using
bt_sock_alloc.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/af_bluetooth.c | 24 ++++++++++++++++++++++++
 net/bluetooth/hidp/sock.c    | 10 +---------
 net/bluetooth/l2cap_sock.c   | 19 -------------------
 3 files changed, 25 insertions(+), 28 deletions(-)

diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 6035422e13da5..647afb1871476 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -157,6 +157,14 @@ struct sock *bt_sock_alloc(struct net *net, struct socket *sock,
 	sk->sk_protocol = proto;
 	sk->sk_state    = BT_OPEN;
 
+	/* Init peer information so it can be properly monitored */
+	if (!kern) {
+		spin_lock(&sk->sk_peer_lock);
+		sk->sk_peer_pid  = get_pid(task_tgid(current));
+		sk->sk_peer_cred = get_current_cred();
+		spin_unlock(&sk->sk_peer_lock);
+	}
+
 	return sk;
 }
 EXPORT_SYMBOL(bt_sock_alloc);
@@ -179,6 +187,9 @@ EXPORT_SYMBOL(bt_sock_unlink);
 
 void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh)
 {
+	const struct cred *old_cred;
+	struct pid *old_pid;
+
 	BT_DBG("parent %p, sk %p", parent, sk);
 
 	sock_hold(sk);
@@ -191,6 +202,19 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh)
 	list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q);
 	bt_sk(sk)->parent = parent;
 
+	/* Copy credentials from parent since for incoming connections the
+	 * socket is allocated by the kernel.
+	 */
+	spin_lock(&sk->sk_peer_lock);
+	old_pid = sk->sk_peer_pid;
+	old_cred = sk->sk_peer_cred;
+	sk->sk_peer_pid = get_pid(parent->sk_peer_pid);
+	sk->sk_peer_cred = get_cred(parent->sk_peer_cred);
+	spin_unlock(&sk->sk_peer_lock);
+
+	put_pid(old_pid);
+	put_cred(old_cred);
+
 	if (bh)
 		bh_unlock_sock(sk);
 	else
diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c
index 369ed92dac997..c93aaeb3a3fad 100644
--- a/net/bluetooth/hidp/sock.c
+++ b/net/bluetooth/hidp/sock.c
@@ -256,21 +256,13 @@ static int hidp_sock_create(struct net *net, struct socket *sock, int protocol,
 	if (sock->type != SOCK_RAW)
 		return -ESOCKTNOSUPPORT;
 
-	sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hidp_proto, kern);
+	sk = bt_sock_alloc(net, sock, &hidp_proto, protocol, GFP_ATOMIC, kern);
 	if (!sk)
 		return -ENOMEM;
 
-	sock_init_data(sock, sk);
-
 	sock->ops = &hidp_sock_ops;
-
 	sock->state = SS_UNCONNECTED;
 
-	sock_reset_flag(sk, SOCK_ZAPPED);
-
-	sk->sk_protocol = protocol;
-	sk->sk_state	= BT_OPEN;
-
 	bt_sock_link(&hidp_sk_list, sk);
 
 	return 0;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 9ef936f27a6a8..3bdfc3f1e73d0 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -178,21 +178,6 @@ done:
 	return err;
 }
 
-static void l2cap_sock_init_pid(struct sock *sk)
-{
-	struct l2cap_chan *chan = l2cap_pi(sk)->chan;
-
-	/* Only L2CAP_MODE_EXT_FLOWCTL ever need to access the PID in order to
-	 * group the channels being requested.
-	 */
-	if (chan->mode != L2CAP_MODE_EXT_FLOWCTL)
-		return;
-
-	spin_lock(&sk->sk_peer_lock);
-	sk->sk_peer_pid = get_pid(task_tgid(current));
-	spin_unlock(&sk->sk_peer_lock);
-}
-
 static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr,
 			      int alen, int flags)
 {
@@ -268,8 +253,6 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr,
 	    chan->mode != L2CAP_MODE_EXT_FLOWCTL)
 		chan->mode = L2CAP_MODE_LE_FLOWCTL;
 
-	l2cap_sock_init_pid(sk);
-
 	err = l2cap_chan_connect(chan, la.l2_psm, __le16_to_cpu(la.l2_cid),
 				 &la.l2_bdaddr, la.l2_bdaddr_type);
 	if (err)
@@ -325,8 +308,6 @@ static int l2cap_sock_listen(struct socket *sock, int backlog)
 		goto done;
 	}
 
-	l2cap_sock_init_pid(sk);
-
 	sk->sk_max_ack_backlog = backlog;
 	sk->sk_ack_backlog = 0;
 
-- 
GitLab


From 69ae5065061c53ded4f49e821646b9bc60ab302a Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 25 May 2023 16:46:43 -0700
Subject: [PATCH 1083/1806] Bluetooth: hci_sock: Forward credentials to monitor

This stores scm_creds into hci_skb_cb so they can be properly forwarded
to the likes of btmon which is then able to print information about the
process who is originating the traffic:

bluetoothd[35]: @ MGMT Command: Rea.. (0x0001) plen 0  {0x0001}
@ MGMT Event: Command Complete (0x0001) plen 6         {0x0001}
      Read Management Version Information (0x0001) plen 3

bluetoothd[35]: < ACL Data T.. flags 0x00 dlen 41
      ATT: Write Command (0x52) len 36
        Handle: 0x0043 Type: ASE Control Point (0x2bc6)
          Data: 020203000110270000022800020a00409c0001000110270000022800020a00409c00
            Opcode: QoS Configuration (0x02)
            Number of ASE(s): 2
            ASE: #0
            ASE ID: 0x03
            CIG ID: 0x00
            CIS ID: 0x01
            SDU Interval: 10000 usec
            Framing: Unframed (0x00)
            PHY: 0x02
            LE 2M PHY (0x02)
            Max SDU: 40
            RTN: 2
            Max Transport Latency: 10
            Presentation Delay: 40000 us
            ASE: #1
            ASE ID: 0x01
            CIG ID: 0x00
            CIS ID: 0x01
            SDU Interval: 10000 usec
            Framing: Unframed (0x00)
            PHY: 0x02
            LE 2M PHY (0x02)
            Max SDU: 40
            RTN: 2
            Max Transport Latency: 10
            Presentation Delay: 40000 us

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/bluetooth.h |  1 +
 net/bluetooth/hci_sock.c          | 67 ++++++++++++++++++++++++++++++-
 2 files changed, 66 insertions(+), 2 deletions(-)

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 60689a07b82cb..34998ae8ed78d 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -471,6 +471,7 @@ struct bt_skb_cb {
 		struct sco_ctrl sco;
 		struct hci_ctrl hci;
 		struct mgmt_ctrl mgmt;
+		struct scm_creds creds;
 	};
 };
 #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb))
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 9c45586f58189..5e4f718073b7e 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -264,6 +264,53 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
 	kfree_skb(skb_copy);
 }
 
+static void hci_sock_copy_creds(struct sock *sk, struct sk_buff *skb)
+{
+	struct scm_creds *creds;
+
+	if (!sk || WARN_ON(!skb))
+		return;
+
+	creds = &bt_cb(skb)->creds;
+
+	/* Check if peer credentials is set */
+	if (!sk->sk_peer_pid) {
+		/* Check if parent peer credentials is set */
+		if (bt_sk(sk)->parent && bt_sk(sk)->parent->sk_peer_pid)
+			sk = bt_sk(sk)->parent;
+		else
+			return;
+	}
+
+	/* Check if scm_creds already set */
+	if (creds->pid == pid_vnr(sk->sk_peer_pid))
+		return;
+
+	memset(creds, 0, sizeof(*creds));
+
+	creds->pid = pid_vnr(sk->sk_peer_pid);
+	if (sk->sk_peer_cred) {
+		creds->uid = sk->sk_peer_cred->uid;
+		creds->gid = sk->sk_peer_cred->gid;
+	}
+}
+
+static struct sk_buff *hci_skb_clone(struct sk_buff *skb)
+{
+	struct sk_buff *nskb;
+
+	if (!skb)
+		return NULL;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return NULL;
+
+	hci_sock_copy_creds(skb->sk, nskb);
+
+	return nskb;
+}
+
 /* Send frame to sockets with specific channel */
 static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
 				  int flag, struct sock *skip_sk)
@@ -289,7 +336,7 @@ static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
 		if (hci_pi(sk)->channel != channel)
 			continue;
 
-		nskb = skb_clone(skb, GFP_ATOMIC);
+		nskb = hci_skb_clone(skb);
 		if (!nskb)
 			continue;
 
@@ -356,6 +403,8 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!skb_copy)
 		return;
 
+	hci_sock_copy_creds(skb->sk, skb_copy);
+
 	/* Put header before the data */
 	hdr = skb_push(skb_copy, HCI_MON_HDR_SIZE);
 	hdr->opcode = opcode;
@@ -531,10 +580,12 @@ static struct sk_buff *create_monitor_ctrl_open(struct sock *sk)
 		return NULL;
 	}
 
-	skb = bt_skb_alloc(14 + TASK_COMM_LEN , GFP_ATOMIC);
+	skb = bt_skb_alloc(14 + TASK_COMM_LEN, GFP_ATOMIC);
 	if (!skb)
 		return NULL;
 
+	hci_sock_copy_creds(sk, skb);
+
 	flags = hci_sock_test_flag(sk, HCI_SOCK_TRUSTED) ? 0x1 : 0x0;
 
 	put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4));
@@ -580,6 +631,8 @@ static struct sk_buff *create_monitor_ctrl_close(struct sock *sk)
 	if (!skb)
 		return NULL;
 
+	hci_sock_copy_creds(sk, skb);
+
 	put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4));
 
 	__net_timestamp(skb);
@@ -606,6 +659,8 @@ static struct sk_buff *create_monitor_ctrl_command(struct sock *sk, u16 index,
 	if (!skb)
 		return NULL;
 
+	hci_sock_copy_creds(sk, skb);
+
 	put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4));
 	put_unaligned_le16(opcode, skb_put(skb, 2));
 
@@ -638,6 +693,8 @@ send_monitor_note(struct sock *sk, const char *fmt, ...)
 	if (!skb)
 		return;
 
+	hci_sock_copy_creds(sk, skb);
+
 	va_start(args, fmt);
 	vsprintf(skb_put(skb, len), fmt, args);
 	*(u8 *)skb_put(skb, 1) = 0;
@@ -1494,6 +1551,7 @@ static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg,
 static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 			    size_t len, int flags)
 {
+	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int copied, err;
@@ -1538,11 +1596,16 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 		break;
 	}
 
+	memset(&scm, 0, sizeof(scm));
+	scm.creds = bt_cb(skb)->creds;
+
 	skb_free_datagram(sk, skb);
 
 	if (flags & MSG_TRUNC)
 		copied = skblen;
 
+	scm_recv(sock, msg, &scm, flags);
+
 	return err ? : copied;
 }
 
-- 
GitLab


From 6a42e9bfd17f7135d59701f93942a3392da482f4 Mon Sep 17 00:00:00 2001
From: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Date: Mon, 19 Jun 2023 17:53:16 +0300
Subject: [PATCH 1084/1806] Bluetooth: ISO: Support multiple BIGs

This adds support for creating multiple BIGs. According to
spec, each BIG shall have an unique handle, and each BIG should
be associated with a different advertising handle. Otherwise,
the LE Create BIG command will fail, with error code
Command Disallowed (for reusing a BIG handle), or
Unknown Advertising Identifier (for reusing an advertising
handle).

The btmon snippet below shows an exercise for creating two BIGs
for the same controller, by opening two isotest instances with
the following command:
    tools/isotest -i hci0 -s 00:00:00:00:00:00

< HCI Command: LE Create Broadcast Isochronous Group (0x08|0x0068) plen 31
        Handle: 0x00
        Advertising Handle: 0x01
        Number of BIS: 1
        SDU Interval: 10000 us (0x002710)
        Maximum SDU size: 40
        Maximum Latency: 10 ms (0x000a)
        RTN: 0x02
        PHY: LE 2M (0x02)
        Packing: Sequential (0x00)
        Framing: Unframed (0x00)
        Encryption: 0x00
        Broadcast Code: 00000000000000000000000000000000

> HCI Event: Command Status (0x0f) plen 4
      LE Create Broadcast Isochronous Group (0x08|0x0068) ncmd 1
        Status: Success (0x00)

> HCI Event: LE Meta Event (0x3e) plen 21
      LE Broadcast Isochronous Group Complete (0x1b)
        Status: Success (0x00)
        Handle: 0x00
        BIG Synchronization Delay: 912 us (0x000390)
        Transport Latency: 912 us (0x000390)
        PHY: LE 2M (0x02)
        NSE: 3
        BN: 1
        PTO: 1
        IRC: 3
        Maximum PDU: 40
        ISO Interval: 10.00 msec (0x0008)
        Connection Handle #0: 10

< HCI Command: LE Create Broadcast Isochronous Group (0x08|0x0068)
        Handle: 0x01
        Advertising Handle: 0x02
        Number of BIS: 1
        SDU Interval: 10000 us (0x002710)
        Maximum SDU size: 40
        Maximum Latency: 10 ms (0x000a)
        RTN: 0x02
        PHY: LE 2M (0x02)
        Packing: Sequential (0x00)
        Framing: Unframed (0x00)
        Encryption: 0x00
        Broadcast Code: 00000000000000000000000000000000

> HCI Event: Command Status (0x0f) plen 4
      LE Create Broadcast Isochronous Group (0x08|0x0068) ncmd 1
        Status: Success (0x00)

Signed-off-by: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  5 ++--
 net/bluetooth/hci_conn.c         | 40 ++++++++++++++------------------
 net/bluetooth/hci_event.c        | 35 +++++++++++++++++++++++-----
 net/bluetooth/hci_sync.c         | 28 +++++++++++-----------
 4 files changed, 63 insertions(+), 45 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ad39d09e9bd66..9140d4a80e38e 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1095,8 +1095,7 @@ static inline __u8 hci_conn_lookup_type(struct hci_dev *hdev, __u16 handle)
 }
 
 static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev,
-							bdaddr_t *ba,
-							__u8 big, __u8 bis)
+							bdaddr_t *ba, __u8 bis)
 {
 	struct hci_conn_hash *h = &hdev->conn_hash;
 	struct hci_conn  *c;
@@ -1107,7 +1106,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev,
 		if (bacmp(&c->dst, ba) || c->type != ISO_LINK)
 			continue;
 
-		if (c->iso_qos.bcast.big == big && c->iso_qos.bcast.bis == bis) {
+		if (c->iso_qos.bcast.bis == bis) {
 			rcu_read_unlock();
 			return c;
 		}
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 4b5223e62141c..0f89daafe194d 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -927,9 +927,7 @@ static void bis_cleanup(struct hci_conn *conn)
 		/* Check if ISO connection is a BIS and terminate advertising
 		 * set and BIG if there are no other connections using it.
 		 */
-		bis = hci_conn_hash_lookup_bis(hdev, BDADDR_ANY,
-					       conn->iso_qos.bcast.big,
-					       conn->iso_qos.bcast.bis);
+		bis = hci_conn_hash_lookup_big(hdev, conn->iso_qos.bcast.big);
 		if (bis)
 			return;
 
@@ -1449,25 +1447,23 @@ static int hci_explicit_conn_params_set(struct hci_dev *hdev,
 
 static int qos_set_big(struct hci_dev *hdev, struct bt_iso_qos *qos)
 {
-	struct iso_list_data data;
+	struct hci_conn *conn;
+	u8  big;
 
 	/* Allocate a BIG if not set */
 	if (qos->bcast.big == BT_ISO_QOS_BIG_UNSET) {
-		for (data.big = 0x00; data.big < 0xef; data.big++) {
-			data.count = 0;
-			data.bis = 0xff;
+		for (big = 0x00; big < 0xef; big++) {
 
-			hci_conn_hash_list_state(hdev, bis_list, ISO_LINK,
-						 BT_BOUND, &data);
-			if (!data.count)
+			conn = hci_conn_hash_lookup_big(hdev, big);
+			if (!conn)
 				break;
 		}
 
-		if (data.big == 0xef)
+		if (big == 0xef)
 			return -EADDRNOTAVAIL;
 
 		/* Update BIG */
-		qos->bcast.big = data.big;
+		qos->bcast.big = big;
 	}
 
 	return 0;
@@ -1475,28 +1471,27 @@ static int qos_set_big(struct hci_dev *hdev, struct bt_iso_qos *qos)
 
 static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos)
 {
-	struct iso_list_data data;
+	struct hci_conn *conn;
+	u8  bis;
 
 	/* Allocate BIS if not set */
 	if (qos->bcast.bis == BT_ISO_QOS_BIS_UNSET) {
 		/* Find an unused adv set to advertise BIS, skip instance 0x00
 		 * since it is reserved as general purpose set.
 		 */
-		for (data.bis = 0x01; data.bis < hdev->le_num_of_adv_sets;
-		     data.bis++) {
-			data.count = 0;
+		for (bis = 0x01; bis < hdev->le_num_of_adv_sets;
+		     bis++) {
 
-			hci_conn_hash_list_state(hdev, bis_list, ISO_LINK,
-						 BT_BOUND, &data);
-			if (!data.count)
+			conn = hci_conn_hash_lookup_bis(hdev, BDADDR_ANY, bis);
+			if (!conn)
 				break;
 		}
 
-		if (data.bis == hdev->le_num_of_adv_sets)
+		if (bis == hdev->le_num_of_adv_sets)
 			return -EADDRNOTAVAIL;
 
 		/* Update BIS */
-		qos->bcast.bis = data.bis;
+		qos->bcast.bis = bis;
 	}
 
 	return 0;
@@ -1534,8 +1529,7 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst,
 	/* Check BIS settings against other bound BISes, since all
 	 * BISes in a BIG must have the same value for all parameters
 	 */
-	conn = hci_conn_hash_lookup_bis(hdev, dst, qos->bcast.big,
-					qos->bcast.bis);
+	conn = hci_conn_hash_lookup_big(hdev, qos->bcast.big);
 
 	if (conn && (memcmp(qos, &conn->iso_qos, sizeof(*qos)) ||
 		     base_len != conn->le_per_adv_data_len ||
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index e7249ed3f5f2e..c67612c99f89f 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1639,7 +1639,7 @@ static u8 hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, void *data,
 
 		hci_dev_set_flag(hdev, HCI_LE_ADV);
 
-		if (adv)
+		if (adv && !adv->periodic)
 			adv->enabled = true;
 
 		conn = hci_lookup_le_connect(hdev);
@@ -3941,24 +3941,47 @@ static u8 hci_cc_le_set_per_adv_enable(struct hci_dev *hdev, void *data,
 				       struct sk_buff *skb)
 {
 	struct hci_ev_status *rp = data;
-	__u8 *sent;
+	struct hci_cp_le_set_per_adv_enable *cp;
+	struct adv_info *adv = NULL, *n;
+	u8 per_adv_cnt = 0;
 
 	bt_dev_dbg(hdev, "status 0x%2.2x", rp->status);
 
 	if (rp->status)
 		return rp->status;
 
-	sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_PER_ADV_ENABLE);
-	if (!sent)
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_PER_ADV_ENABLE);
+	if (!cp)
 		return rp->status;
 
 	hci_dev_lock(hdev);
 
-	if (*sent)
+	adv = hci_find_adv_instance(hdev, cp->handle);
+
+	if (cp->enable) {
 		hci_dev_set_flag(hdev, HCI_LE_PER_ADV);
-	else
+
+		if (adv)
+			adv->enabled = true;
+	} else {
+		/* If just one instance was disabled check if there are
+		 * any other instance enabled before clearing HCI_LE_PER_ADV.
+		 * The current periodic adv instance will be marked as
+		 * disabled once extended advertising is also disabled.
+		 */
+		list_for_each_entry_safe(adv, n, &hdev->adv_instances,
+					 list) {
+			if (adv->periodic && adv->enabled)
+				per_adv_cnt++;
+		}
+
+		if (per_adv_cnt > 1)
+			goto unlock;
+
 		hci_dev_clear_flag(hdev, HCI_LE_PER_ADV);
+	}
 
+unlock:
 	hci_dev_unlock(hdev);
 
 	return rp->status;
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index b617d1dd247a5..afb8e970e62cc 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3,6 +3,7 @@
  * BlueZ - Bluetooth protocol stack for Linux
  *
  * Copyright (C) 2021 Intel Corporation
+ * Copyright 2023 NXP
  */
 
 #include <linux/property.h>
@@ -1319,9 +1320,11 @@ int hci_start_ext_adv_sync(struct hci_dev *hdev, u8 instance)
 static int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance)
 {
 	struct hci_cp_le_set_per_adv_enable cp;
+	struct adv_info *adv = NULL;
 
 	/* If periodic advertising already disabled there is nothing to do. */
-	if (!hci_dev_test_flag(hdev, HCI_LE_PER_ADV))
+	adv = hci_find_adv_instance(hdev, instance);
+	if (!adv || !adv->periodic || !adv->enabled)
 		return 0;
 
 	memset(&cp, 0, sizeof(cp));
@@ -1386,9 +1389,11 @@ static int hci_set_per_adv_data_sync(struct hci_dev *hdev, u8 instance)
 static int hci_enable_per_advertising_sync(struct hci_dev *hdev, u8 instance)
 {
 	struct hci_cp_le_set_per_adv_enable cp;
+	struct adv_info *adv = NULL;
 
 	/* If periodic advertising already enabled there is nothing to do. */
-	if (hci_dev_test_flag(hdev, HCI_LE_PER_ADV))
+	adv = hci_find_adv_instance(hdev, instance);
+	if (adv && adv->periodic && adv->enabled)
 		return 0;
 
 	memset(&cp, 0, sizeof(cp));
@@ -1458,22 +1463,19 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len,
 						   sync_interval);
 			if (IS_ERR(adv))
 				return PTR_ERR(adv);
+			adv->pending = false;
 			added = true;
 		}
 	}
 
-	/* Only start advertising if instance 0 or if a dedicated instance has
-	 * been added.
-	 */
-	if (!adv || added) {
-		err = hci_start_ext_adv_sync(hdev, instance);
-		if (err < 0)
-			goto fail;
+	/* Start advertising */
+	err = hci_start_ext_adv_sync(hdev, instance);
+	if (err < 0)
+		goto fail;
 
-		err = hci_adv_bcast_annoucement(hdev, adv);
-		if (err < 0)
-			goto fail;
-	}
+	err = hci_adv_bcast_annoucement(hdev, adv);
+	if (err < 0)
+		goto fail;
 
 	err = hci_set_per_adv_params_sync(hdev, instance, min_interval,
 					  max_interval);
-- 
GitLab


From 6ce95a304c816a4cd71329e22e3aaeefe5173fdf Mon Sep 17 00:00:00 2001
From: Sai Teja Aluvala <quic_saluvala@quicinc.com>
Date: Wed, 14 Jun 2023 10:28:15 +0530
Subject: [PATCH 1085/1806] Bluetooth: hci_qca: Add qcom devcoredump sysfs
 support

This patch implements the hci_qca driver side .coredump() callback to
trigger a devcoredump via sysfs.

Signed-off-by: Sai Teja Aluvala <quic_saluvala@quicinc.com>

v2 -> V3:
--------
Updated commit text

v1 -> V2:
--------
Updated to work with the updated HCI devcoredump API.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_qca.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index e30c979535b1d..1ee5323ada7df 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2384,6 +2384,18 @@ static const struct acpi_device_id qca_bluetooth_acpi_match[] = {
 MODULE_DEVICE_TABLE(acpi, qca_bluetooth_acpi_match);
 #endif
 
+#ifdef CONFIG_DEV_COREDUMP
+static void hciqca_coredump(struct device *dev)
+{
+	struct serdev_device *serdev = to_serdev_device(dev);
+	struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev);
+	struct hci_uart *hu = &qcadev->serdev_hu;
+	struct hci_dev  *hdev = hu->hdev;
+
+	if (hdev->dump.coredump)
+		hdev->dump.coredump(hdev);
+}
+#endif
 
 static struct serdev_device_driver qca_serdev_driver = {
 	.probe = qca_serdev_probe,
@@ -2394,6 +2406,9 @@ static struct serdev_device_driver qca_serdev_driver = {
 		.acpi_match_table = ACPI_PTR(qca_bluetooth_acpi_match),
 		.shutdown = qca_serdev_shutdown,
 		.pm = &qca_pm_ops,
+#ifdef CONFIG_DEV_COREDUMP
+		.coredump = hciqca_coredump,
+#endif
 	},
 };
 
-- 
GitLab


From 06d3fdfcdf5cefb06f2024b9d3dad356779399cf Mon Sep 17 00:00:00 2001
From: Sai Teja Aluvala <quic_saluvala@quicinc.com>
Date: Wed, 14 Jun 2023 10:29:10 +0530
Subject: [PATCH 1086/1806] Bluetooth: hci_qca: Add qcom devcoredump support

Intercept debug exception events from QCA controller and put them into
a devcoredump using hci devcoredump APIs of hci_core

Signed-off-by: Sai Teja Aluvala <quic_saluvala@quicinc.com>

V2 -> V3:
---------
changed hci_coredump_qca function

V1 -> V2:
---------
Updated to work with the updated HCI devcoredump API.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_qca.c | 135 +++++++++++++++++++++++-------------
 1 file changed, 85 insertions(+), 50 deletions(-)

diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 1ee5323ada7df..87a7325c75b16 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -117,9 +117,7 @@ enum qca_memdump_states {
 	QCA_MEMDUMP_TIMEOUT,
 };
 
-struct qca_memdump_data {
-	char *memdump_buf_head;
-	char *memdump_buf_tail;
+struct qca_memdump_info {
 	u32 current_seq_no;
 	u32 received_dump;
 	u32 ram_dump_size;
@@ -160,13 +158,15 @@ struct qca_data {
 	struct work_struct ws_tx_vote_off;
 	struct work_struct ctrl_memdump_evt;
 	struct delayed_work ctrl_memdump_timeout;
-	struct qca_memdump_data *qca_memdump;
+	struct qca_memdump_info *qca_memdump;
 	unsigned long flags;
 	struct completion drop_ev_comp;
 	wait_queue_head_t suspend_wait_q;
 	enum qca_memdump_states memdump_state;
 	struct mutex hci_memdump_lock;
 
+	u16 fw_version;
+	u16 controller_id;
 	/* For debugging purpose */
 	u64 ibs_sent_wacks;
 	u64 ibs_sent_slps;
@@ -233,6 +233,7 @@ static void qca_regulator_disable(struct qca_serdev *qcadev);
 static void qca_power_shutdown(struct hci_uart *hu);
 static int qca_power_off(struct hci_dev *hdev);
 static void qca_controller_memdump(struct work_struct *work);
+static void qca_dmp_hdr(struct hci_dev *hdev, struct sk_buff *skb);
 
 static enum qca_btsoc_type qca_soc_type(struct hci_uart *hu)
 {
@@ -980,6 +981,28 @@ static int qca_recv_acl_data(struct hci_dev *hdev, struct sk_buff *skb)
 	return hci_recv_frame(hdev, skb);
 }
 
+static void qca_dmp_hdr(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	struct qca_data *qca = hu->priv;
+	char buf[80];
+
+	snprintf(buf, sizeof(buf), "Controller Name: 0x%x\n",
+		qca->controller_id);
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Firmware Version: 0x%x\n",
+		qca->fw_version);
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Vendor:Qualcomm\n");
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Driver: %s\n",
+		hu->serdev->dev.driver->name);
+	skb_put_data(skb, buf, strlen(buf));
+}
+
 static void qca_controller_memdump(struct work_struct *work)
 {
 	struct qca_data *qca = container_of(work, struct qca_data,
@@ -987,13 +1010,11 @@ static void qca_controller_memdump(struct work_struct *work)
 	struct hci_uart *hu = qca->hu;
 	struct sk_buff *skb;
 	struct qca_memdump_event_hdr *cmd_hdr;
-	struct qca_memdump_data *qca_memdump = qca->qca_memdump;
+	struct qca_memdump_info *qca_memdump = qca->qca_memdump;
 	struct qca_dump_size *dump;
-	char *memdump_buf;
-	char nullBuff[QCA_DUMP_PACKET_SIZE] = { 0 };
 	u16 seq_no;
-	u32 dump_size;
 	u32 rx_size;
+	int ret = 0;
 	enum qca_btsoc_type soc_type = qca_soc_type(hu);
 
 	while ((skb = skb_dequeue(&qca->rx_memdump_q))) {
@@ -1009,7 +1030,7 @@ static void qca_controller_memdump(struct work_struct *work)
 		}
 
 		if (!qca_memdump) {
-			qca_memdump = kzalloc(sizeof(struct qca_memdump_data),
+			qca_memdump = kzalloc(sizeof(struct qca_memdump_info),
 					      GFP_ATOMIC);
 			if (!qca_memdump) {
 				mutex_unlock(&qca->hci_memdump_lock);
@@ -1035,44 +1056,49 @@ static void qca_controller_memdump(struct work_struct *work)
 			set_bit(QCA_IBS_DISABLED, &qca->flags);
 			set_bit(QCA_MEMDUMP_COLLECTION, &qca->flags);
 			dump = (void *) skb->data;
-			dump_size = __le32_to_cpu(dump->dump_size);
-			if (!(dump_size)) {
+			qca_memdump->ram_dump_size = __le32_to_cpu(dump->dump_size);
+			if (!(qca_memdump->ram_dump_size)) {
 				bt_dev_err(hu->hdev, "Rx invalid memdump size");
 				kfree(qca_memdump);
 				kfree_skb(skb);
-				qca->qca_memdump = NULL;
 				mutex_unlock(&qca->hci_memdump_lock);
 				return;
 			}
 
-			bt_dev_info(hu->hdev, "QCA collecting dump of size:%u",
-				    dump_size);
 			queue_delayed_work(qca->workqueue,
 					   &qca->ctrl_memdump_timeout,
-					   msecs_to_jiffies(MEMDUMP_TIMEOUT_MS)
-					  );
-
-			skb_pull(skb, sizeof(dump_size));
-			memdump_buf = vmalloc(dump_size);
-			qca_memdump->ram_dump_size = dump_size;
-			qca_memdump->memdump_buf_head = memdump_buf;
-			qca_memdump->memdump_buf_tail = memdump_buf;
-		}
+					   msecs_to_jiffies(MEMDUMP_TIMEOUT_MS));
+			skb_pull(skb, sizeof(qca_memdump->ram_dump_size));
+			qca_memdump->current_seq_no = 0;
+			qca_memdump->received_dump = 0;
+			ret = hci_devcd_init(hu->hdev, qca_memdump->ram_dump_size);
+			bt_dev_info(hu->hdev, "hci_devcd_init Return:%d",
+				    ret);
+			if (ret < 0) {
+				kfree(qca->qca_memdump);
+				qca->qca_memdump = NULL;
+				qca->memdump_state = QCA_MEMDUMP_COLLECTED;
+				cancel_delayed_work(&qca->ctrl_memdump_timeout);
+				clear_bit(QCA_MEMDUMP_COLLECTION, &qca->flags);
+				mutex_unlock(&qca->hci_memdump_lock);
+				return;
+			}
 
-		memdump_buf = qca_memdump->memdump_buf_tail;
+			bt_dev_info(hu->hdev, "QCA collecting dump of size:%u",
+				    qca_memdump->ram_dump_size);
+
+		}
 
 		/* If sequence no 0 is missed then there is no point in
 		 * accepting the other sequences.
 		 */
-		if (!memdump_buf) {
+		if (!test_bit(QCA_MEMDUMP_COLLECTION, &qca->flags)) {
 			bt_dev_err(hu->hdev, "QCA: Discarding other packets");
 			kfree(qca_memdump);
 			kfree_skb(skb);
-			qca->qca_memdump = NULL;
 			mutex_unlock(&qca->hci_memdump_lock);
 			return;
 		}
-
 		/* There could be chance of missing some packets from
 		 * the controller. In such cases let us store the dummy
 		 * packets in the buffer.
@@ -1082,8 +1108,8 @@ static void qca_controller_memdump(struct work_struct *work)
 		 * bits, so skip this checking for missing packet.
 		 */
 		while ((seq_no > qca_memdump->current_seq_no + 1) &&
-		       (soc_type != QCA_QCA6390) &&
-		       seq_no != QCA_LAST_SEQUENCE_NUM) {
+			(soc_type != QCA_QCA6390) &&
+			seq_no != QCA_LAST_SEQUENCE_NUM) {
 			bt_dev_err(hu->hdev, "QCA controller missed packet:%d",
 				   qca_memdump->current_seq_no);
 			rx_size = qca_memdump->received_dump;
@@ -1094,43 +1120,38 @@ static void qca_controller_memdump(struct work_struct *work)
 					   qca_memdump->received_dump);
 				break;
 			}
-			memcpy(memdump_buf, nullBuff, QCA_DUMP_PACKET_SIZE);
-			memdump_buf = memdump_buf + QCA_DUMP_PACKET_SIZE;
+			hci_devcd_append_pattern(hu->hdev, 0x00,
+				QCA_DUMP_PACKET_SIZE);
 			qca_memdump->received_dump += QCA_DUMP_PACKET_SIZE;
 			qca_memdump->current_seq_no++;
 		}
 
-		rx_size = qca_memdump->received_dump + skb->len;
+		rx_size = qca_memdump->received_dump  + skb->len;
 		if (rx_size <= qca_memdump->ram_dump_size) {
 			if ((seq_no != QCA_LAST_SEQUENCE_NUM) &&
-			    (seq_no != qca_memdump->current_seq_no))
+			    (seq_no != qca_memdump->current_seq_no)) {
 				bt_dev_err(hu->hdev,
 					   "QCA memdump unexpected packet %d",
 					   seq_no);
+			}
 			bt_dev_dbg(hu->hdev,
 				   "QCA memdump packet %d with length %d",
 				   seq_no, skb->len);
-			memcpy(memdump_buf, (unsigned char *)skb->data,
-			       skb->len);
-			memdump_buf = memdump_buf + skb->len;
-			qca_memdump->memdump_buf_tail = memdump_buf;
-			qca_memdump->current_seq_no = seq_no + 1;
-			qca_memdump->received_dump += skb->len;
+			hci_devcd_append(hu->hdev, skb);
+			qca_memdump->current_seq_no += 1;
+			qca_memdump->received_dump = rx_size;
 		} else {
 			bt_dev_err(hu->hdev,
-				   "QCA memdump received %d, no space for packet %d",
-				   qca_memdump->received_dump, seq_no);
+				   "QCA memdump received no space for packet %d",
+				    qca_memdump->current_seq_no);
 		}
-		qca->qca_memdump = qca_memdump;
-		kfree_skb(skb);
+
 		if (seq_no == QCA_LAST_SEQUENCE_NUM) {
 			bt_dev_info(hu->hdev,
-				    "QCA memdump Done, received %d, total %d",
-				    qca_memdump->received_dump,
-				    qca_memdump->ram_dump_size);
-			memdump_buf = qca_memdump->memdump_buf_head;
-			dev_coredumpv(&hu->serdev->dev, memdump_buf,
-				      qca_memdump->received_dump, GFP_KERNEL);
+				"QCA memdump Done, received %d, total %d",
+				qca_memdump->received_dump,
+				qca_memdump->ram_dump_size);
+			hci_devcd_complete(hu->hdev);
 			cancel_delayed_work(&qca->ctrl_memdump_timeout);
 			kfree(qca->qca_memdump);
 			qca->qca_memdump = NULL;
@@ -1541,8 +1562,8 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code)
 	mutex_lock(&qca->hci_memdump_lock);
 	if (qca->memdump_state != QCA_MEMDUMP_COLLECTED) {
 		bt_dev_err(hu->hdev, "clearing allocated memory due to memdump timeout");
+		hci_devcd_abort(hu->hdev);
 		if (qca->qca_memdump) {
-			vfree(qca->qca_memdump->memdump_buf_head);
 			kfree(qca->qca_memdump);
 			qca->qca_memdump = NULL;
 		}
@@ -1706,6 +1727,17 @@ static int qca_power_on(struct hci_dev *hdev)
 	return ret;
 }
 
+static void hci_coredump_qca(struct hci_dev *hdev)
+{
+	static const u8 param[] = { 0x26 };
+	struct sk_buff *skb;
+
+	skb = __hci_cmd_sync(hdev, 0xfc0c, 1, param, HCI_CMD_TIMEOUT);
+	if (IS_ERR(skb))
+		bt_dev_err(hdev, "%s: trigger crash failed (%ld)", __func__, PTR_ERR(skb));
+	kfree_skb(skb);
+}
+
 static int qca_setup(struct hci_uart *hu)
 {
 	struct hci_dev *hdev = hu->hdev;
@@ -1820,6 +1852,9 @@ out:
 		hu->hdev->set_bdaddr = qca_set_bdaddr_rome;
 	else
 		hu->hdev->set_bdaddr = qca_set_bdaddr;
+	qca->fw_version = le16_to_cpu(ver.patch_ver);
+	qca->controller_id = le16_to_cpu(ver.rom_ver);
+	hci_devcd_register(hdev, hci_coredump_qca, qca_dmp_hdr, NULL);
 
 	return ret;
 }
-- 
GitLab


From 8f0a3786f56d9fa4b308bdbd54757a51145dbb7a Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Sun, 11 Jun 2023 12:13:42 +0530
Subject: [PATCH 1087/1806] Bluetooth: btintel: Add support to reset bluetooth
 via ACPI DSM

New Intel platforms supports reset of Bluetooth device  via ACPI DSM
methods. The legacy reset mechanism via GPIO will be deprecated in
future. This patch checks the platform support for reset methods and if
supported uses the same instead of legacy GPIO toggling method.

ACPI firmware supports two types of reset method based on NIC card.
(Discrete or Integrated).

1. VSEC Type - Vendor Specific Extended Capability. Here  BT_EN and
   BT_IF_SELECT lines are driven by a register in PCH cluster. This
   interface is supported on discrete BT solution.

2. WDISABLE2 - In this soluton, W_DISABLE2 pin in M.2 is connected to
   physical GPIO from PCH. The DSM interface shall toggle this to recover
   from  error.

Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.c | 121 ++++++++++++++++++++++++++++++++++++
 drivers/bluetooth/btintel.h |   2 +
 drivers/bluetooth/btusb.c   |  16 +++++
 3 files changed, 139 insertions(+)

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index d9349ba48281e..dd1e48808ee2c 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -10,6 +10,7 @@
 #include <linux/firmware.h>
 #include <linux/regmap.h>
 #include <linux/acpi.h>
+#include <acpi/acpi_bus.h>
 #include <asm/unaligned.h>
 
 #include <net/bluetooth/bluetooth.h>
@@ -27,6 +28,11 @@
 
 #define BTINTEL_PPAG_NAME   "PPAG"
 
+enum {
+	DSM_SET_WDISABLE2_DELAY = 1,
+	DSM_SET_RESET_METHOD = 3,
+};
+
 /* structure to store the PPAG data read from ACPI table */
 struct btintel_ppag {
 	u32	domain;
@@ -49,6 +55,10 @@ static struct {
 	u32        fw_build_num;
 } coredump_info;
 
+static const guid_t btintel_guid_dsm =
+	GUID_INIT(0xaa10f4e0, 0x81ac, 0x4233,
+		  0xab, 0xf6, 0x3b, 0x2a, 0xc5, 0x0e, 0x28, 0xd9);
+
 int btintel_check_bdaddr(struct hci_dev *hdev)
 {
 	struct hci_rp_read_bd_addr *bda;
@@ -2444,6 +2454,116 @@ static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver
 	kfree_skb(skb);
 }
 
+static int btintel_acpi_reset_method(struct hci_dev *hdev)
+{
+	int ret = 0;
+	acpi_status status;
+	union acpi_object *p, *ref;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+
+	status = acpi_evaluate_object(ACPI_HANDLE(GET_HCIDEV_DEV(hdev)), "_PRR", NULL, &buffer);
+	if (ACPI_FAILURE(status)) {
+		bt_dev_err(hdev, "Failed to run _PRR method");
+		ret = -ENODEV;
+		return ret;
+	}
+	p = buffer.pointer;
+
+	if (p->package.count != 1 || p->type != ACPI_TYPE_PACKAGE) {
+		bt_dev_err(hdev, "Invalid arguments");
+		ret = -EINVAL;
+		goto exit_on_error;
+	}
+
+	ref = &p->package.elements[0];
+	if (ref->type != ACPI_TYPE_LOCAL_REFERENCE) {
+		bt_dev_err(hdev, "Invalid object type: 0x%x", ref->type);
+		ret = -EINVAL;
+		goto exit_on_error;
+	}
+
+	status = acpi_evaluate_object(ref->reference.handle, "_RST", NULL, NULL);
+	if (ACPI_FAILURE(status)) {
+		bt_dev_err(hdev, "Failed to run_RST method");
+		ret = -ENODEV;
+		goto exit_on_error;
+	}
+
+exit_on_error:
+	kfree(buffer.pointer);
+	return ret;
+}
+
+static void btintel_set_dsm_reset_method(struct hci_dev *hdev,
+					 struct intel_version_tlv *ver_tlv)
+{
+	struct btintel_data *data = hci_get_priv(hdev);
+	acpi_handle handle = ACPI_HANDLE(GET_HCIDEV_DEV(hdev));
+	u8 reset_payload[4] = {0x01, 0x00, 0x01, 0x00};
+	union acpi_object *obj, argv4;
+	enum {
+		RESET_TYPE_WDISABLE2,
+		RESET_TYPE_VSEC
+	};
+
+	handle = ACPI_HANDLE(GET_HCIDEV_DEV(hdev));
+
+	if (!handle) {
+		bt_dev_dbg(hdev, "No support for bluetooth device in ACPI firmware");
+		return;
+	}
+
+	if (!acpi_has_method(handle, "_PRR")) {
+		bt_dev_err(hdev, "No support for _PRR ACPI method");
+		return;
+	}
+
+	switch (ver_tlv->cnvi_top & 0xfff) {
+	case 0x910: /* GalePeak2 */
+		reset_payload[2] = RESET_TYPE_VSEC;
+		break;
+	default:
+		/* WDISABLE2 is the default reset method */
+		reset_payload[2] = RESET_TYPE_WDISABLE2;
+
+		if (!acpi_check_dsm(handle, &btintel_guid_dsm, 0,
+				    BIT(DSM_SET_WDISABLE2_DELAY))) {
+			bt_dev_err(hdev, "No dsm support to set reset delay");
+			return;
+		}
+		argv4.integer.type = ACPI_TYPE_INTEGER;
+		/* delay required to toggle BT power */
+		argv4.integer.value = 160;
+		obj = acpi_evaluate_dsm(handle, &btintel_guid_dsm, 0,
+					DSM_SET_WDISABLE2_DELAY, &argv4);
+		if (!obj) {
+			bt_dev_err(hdev, "Failed to call dsm to set reset delay");
+			return;
+		}
+		ACPI_FREE(obj);
+	}
+
+	bt_dev_info(hdev, "DSM reset method type: 0x%02x", reset_payload[2]);
+
+	if (!acpi_check_dsm(handle, &btintel_guid_dsm, 0,
+			    DSM_SET_RESET_METHOD)) {
+		bt_dev_warn(hdev, "No support for dsm to set reset method");
+		return;
+	}
+	argv4.buffer.type = ACPI_TYPE_BUFFER;
+	argv4.buffer.length = sizeof(reset_payload);
+	argv4.buffer.pointer = reset_payload;
+
+	obj = acpi_evaluate_dsm(handle, &btintel_guid_dsm, 0,
+				DSM_SET_RESET_METHOD, &argv4);
+	if (!obj) {
+		bt_dev_err(hdev, "Failed to call dsm to set reset method");
+		return;
+	}
+	ACPI_FREE(obj);
+	data->acpi_reset_method = btintel_acpi_reset_method;
+}
+
 static int btintel_bootloader_setup_tlv(struct hci_dev *hdev,
 					struct intel_version_tlv *ver)
 {
@@ -2757,6 +2877,7 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 		/* Setup MSFT Extension support */
 		btintel_set_msft_opcode(hdev,
 					INTEL_HW_VARIANT(ver_tlv.cnvi_bt));
+		btintel_set_dsm_reset_method(hdev, &ver_tlv);
 
 		err = btintel_bootloader_setup_tlv(hdev, &ver_tlv);
 		btintel_register_devcoredump_support(hdev);
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index d6a1dc8d8a828..7fd29ef038bd6 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -166,12 +166,14 @@ enum {
 	INTEL_BROKEN_SHUTDOWN_LED,
 	INTEL_ROM_LEGACY,
 	INTEL_ROM_LEGACY_NO_WBS_SUPPORT,
+	INTEL_ACPI_RESET_ACTIVE,
 
 	__INTEL_NUM_FLAGS,
 };
 
 struct btintel_data {
 	DECLARE_BITMAP(flags, __INTEL_NUM_FLAGS);
+	int (*acpi_reset_method)(struct hci_dev *hdev);
 };
 
 #define btintel_set_flag(hdev, nr)					\
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 711beaa0ac562..f99ce34abb9fd 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -860,10 +860,26 @@ static void btusb_intel_cmd_timeout(struct hci_dev *hdev)
 {
 	struct btusb_data *data = hci_get_drvdata(hdev);
 	struct gpio_desc *reset_gpio = data->reset_gpio;
+	struct btintel_data *intel_data = hci_get_priv(hdev);
 
 	if (++data->cmd_timeout_cnt < 5)
 		return;
 
+	if (intel_data->acpi_reset_method) {
+		if (test_and_set_bit(INTEL_ACPI_RESET_ACTIVE, intel_data->flags)) {
+			bt_dev_err(hdev, "acpi: last reset failed ? Not resetting again");
+			return;
+		}
+
+		bt_dev_err(hdev, "Initiating acpi reset method");
+		/* If ACPI reset method fails, lets try with legacy GPIO
+		 * toggling
+		 */
+		if (!intel_data->acpi_reset_method(hdev)) {
+			return;
+		}
+	}
+
 	if (!reset_gpio) {
 		btusb_reset(hdev);
 		return;
-- 
GitLab


From 4c92ae75ea7d41b6bafe10ee6f4c12ec12624786 Mon Sep 17 00:00:00 2001
From: Peter Tsao <peter.tsao@mediatek.com>
Date: Tue, 20 Jun 2023 16:27:50 +0800
Subject: [PATCH 1088/1806] Bluetooth: btusb: Add support Mediatek MT7925

This patch is added support Mediatek MT7925.
1. The firmware location of MT7925 will set to
/lib/firmware/mediatek/mt7925
2. Add Mediatek private data in hdev
to record the device for handle MT7925 flow.
3. Use the recoreded dev_id to condition chip reset flow.

The information in /sys/kernel/debug/usb/devices about the MT7925U
Bluetooth device is listed as the below

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 27 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0e8d ProdID=7925 Rev= 1.00
S:  Manufacturer=MediaTek Inc.
S:  Product=Wireless_Device
S:  SerialNumber=000000000
C:* #Ifs= 4 Cfg#= 1 Atr=e0 MxPwr=100mA
A:  FirstIf#= 0 IfCount= 3 Cls=e0(wlcon) Sub=01 Prot=01
I:* If#= 0 Alt= 0 #EPs= 5 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=125us
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8f(I) Atr=03(Int.) MxPS=   2 Ivl=125us
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS=  64 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS=  64 Ivl=125us
I:  If#= 2 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS= 512 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS= 512 Ivl=125us
I:* If#= 3 Alt= 0 #EPs= 9 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=08(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=09(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=   2 Ivl=125us

Signed-off-by: Peter Tsao <peter.tsao@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btmtk.c |  1 +
 drivers/bluetooth/btmtk.h |  5 +++
 drivers/bluetooth/btusb.c | 78 +++++++++++++++++++++++++++++----------
 3 files changed, 64 insertions(+), 20 deletions(-)

diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index 809762d64fc65..9482401d97fab 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -289,3 +289,4 @@ MODULE_FIRMWARE(FIRMWARE_MT7622);
 MODULE_FIRMWARE(FIRMWARE_MT7663);
 MODULE_FIRMWARE(FIRMWARE_MT7668);
 MODULE_FIRMWARE(FIRMWARE_MT7961);
+MODULE_FIRMWARE(FIRMWARE_MT7925);
diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h
index 2a88ea8e475e8..fadc1a5206522 100644
--- a/drivers/bluetooth/btmtk.h
+++ b/drivers/bluetooth/btmtk.h
@@ -5,6 +5,7 @@
 #define FIRMWARE_MT7663		"mediatek/mt7663pr2h.bin"
 #define FIRMWARE_MT7668		"mediatek/mt7668pr2h.bin"
 #define FIRMWARE_MT7961		"mediatek/BT_RAM_CODE_MT7961_1_2_hdr.bin"
+#define FIRMWARE_MT7925		"mediatek/mt7925/BT_RAM_CODE_MT7925_1_1_hdr.bin"
 
 #define HCI_EV_WMT 0xe4
 #define HCI_WMT_MAX_EVENT_SIZE		64
@@ -119,6 +120,10 @@ struct btmtk_hci_wmt_params {
 	u32 *status;
 };
 
+struct btmediatek_data {
+	u32 dev_id;
+};
+
 typedef int (*wmt_cmd_sync_func_t)(struct hci_dev *,
 				   struct btmtk_hci_wmt_params *);
 
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index f99ce34abb9fd..e1e271e0437d6 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2659,6 +2659,9 @@ static int btusb_recv_event_realtek(struct hci_dev *hdev, struct sk_buff *skb)
 #define MTK_BT_RST_DONE		0x00000100
 #define MTK_BT_RESET_WAIT_MS	100
 #define MTK_BT_RESET_NUM_TRIES	10
+#define MTK_BT_RESET_REG_CONNV3	0x70028610
+#define MTK_BT_READ_DEV_ID	0x70010200
+
 
 static void btusb_mtk_wmt_recv(struct urb *urb)
 {
@@ -3039,10 +3042,11 @@ static int btusb_mtk_setup(struct hci_dev *hdev)
 	struct sk_buff *skb;
 	const char *fwname;
 	int err, status;
-	u32 dev_id;
+	u32 dev_id = 0;
 	char fw_bin_name[64];
 	u32 fw_version = 0;
 	u8 param;
+	struct btmediatek_data *mediatek;
 
 	calltime = ktime_get();
 
@@ -3052,7 +3056,7 @@ static int btusb_mtk_setup(struct hci_dev *hdev)
 		return err;
 	}
 
-	if (!dev_id) {
+	if (!dev_id || dev_id != 0x7663) {
 		err = btusb_mtk_id_get(data, 0x70010200, &dev_id);
 		if (err < 0) {
 			bt_dev_err(hdev, "Failed to get device id (%d)", err);
@@ -3065,6 +3069,9 @@ static int btusb_mtk_setup(struct hci_dev *hdev)
 		}
 	}
 
+	mediatek = hci_get_priv(hdev);
+	mediatek->dev_id = dev_id;
+
 	switch (dev_id) {
 	case 0x7663:
 		fwname = FIRMWARE_MT7663;
@@ -3074,9 +3081,16 @@ static int btusb_mtk_setup(struct hci_dev *hdev)
 		break;
 	case 0x7922:
 	case 0x7961:
-		snprintf(fw_bin_name, sizeof(fw_bin_name),
-			"mediatek/BT_RAM_CODE_MT%04x_1_%x_hdr.bin",
-			 dev_id & 0xffff, (fw_version & 0xff) + 1);
+	case 0x7925:
+		if (dev_id == 0x7925)
+			snprintf(fw_bin_name, sizeof(fw_bin_name),
+				 "mediatek/mt%04x/BT_RAM_CODE_MT%04x_1_%x_hdr.bin",
+				 dev_id & 0xffff, dev_id & 0xffff, (fw_version & 0xff) + 1);
+		else
+			snprintf(fw_bin_name, sizeof(fw_bin_name),
+				 "mediatek/BT_RAM_CODE_MT%04x_1_%x_hdr.bin",
+				 dev_id & 0xffff, (fw_version & 0xff) + 1);
+
 		err = btmtk_setup_firmware_79xx(hdev, fw_bin_name,
 						btusb_mtk_hci_wmt_sync);
 		if (err < 0) {
@@ -3219,6 +3233,7 @@ static void btusb_mtk_cmd_timeout(struct hci_dev *hdev)
 	struct btusb_data *data = hci_get_drvdata(hdev);
 	u32 val;
 	int err, retry = 0;
+	struct btmediatek_data *mediatek;
 
 	/* It's MediaTek specific bluetooth reset mechanism via USB */
 	if (test_and_set_bit(BTUSB_HW_RESET_ACTIVE, &data->flags)) {
@@ -3232,22 +3247,42 @@ static void btusb_mtk_cmd_timeout(struct hci_dev *hdev)
 
 	btusb_stop_traffic(data);
 	usb_kill_anchored_urbs(&data->tx_anchor);
+	mediatek = hci_get_priv(hdev);
+
+	if (mediatek->dev_id == 0x7925) {
+		btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val);
+		val |= (1 << 5);
+		btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val);
+		btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val);
+		val &= 0xFFFF00FF;
+		val |= (1 << 13);
+		btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val);
+		btusb_mtk_uhw_reg_write(data, MTK_EP_RST_OPT, 0x00010001);
+		btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val);
+		val |= (1 << 0);
+		btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val);
+		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT, 0x000000FF);
+		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT, &val);
+		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT1, 0x000000FF);
+		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT1, &val);
+		msleep(100);
+	} else {
+		/* It's Device EndPoint Reset Option Register */
+		bt_dev_dbg(hdev, "Initiating reset mechanism via uhw");
+		btusb_mtk_uhw_reg_write(data, MTK_EP_RST_OPT, MTK_EP_RST_IN_OUT_OPT);
+		btusb_mtk_uhw_reg_read(data, MTK_BT_WDT_STATUS, &val);
 
-	/* It's Device EndPoint Reset Option Register */
-	bt_dev_dbg(hdev, "Initiating reset mechanism via uhw");
-	btusb_mtk_uhw_reg_write(data, MTK_EP_RST_OPT, MTK_EP_RST_IN_OUT_OPT);
-	btusb_mtk_uhw_reg_read(data, MTK_BT_WDT_STATUS, &val);
-
-	/* Reset the bluetooth chip via USB interface. */
-	btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 1);
-	btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT, 0x000000FF);
-	btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT, &val);
-	btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT1, 0x000000FF);
-	btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT1, &val);
-	/* MT7921 need to delay 20ms between toggle reset bit */
-	msleep(20);
-	btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 0);
-	btusb_mtk_uhw_reg_read(data, MTK_BT_SUBSYS_RST, &val);
+		/* Reset the bluetooth chip via USB interface. */
+		btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 1);
+		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT, 0x000000FF);
+		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT, &val);
+		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT1, 0x000000FF);
+		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT1, &val);
+		/* MT7921 need to delay 20ms between toggle reset bit */
+		msleep(20);
+		btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 0);
+		btusb_mtk_uhw_reg_read(data, MTK_BT_SUBSYS_RST, &val);
+	}
 
 	/* Poll the register until reset is completed */
 	do {
@@ -4289,6 +4324,9 @@ static int btusb_probe(struct usb_interface *intf,
 		priv_size += sizeof(struct btrealtek_data);
 
 		data->recv_event = btusb_recv_event_realtek;
+	} else if (id->driver_info & BTUSB_MEDIATEK) {
+		/* Allocate extra space for Mediatek device */
+		priv_size += sizeof(struct btmediatek_data);
 	}
 
 	data->recv_acl = hci_recv_frame;
-- 
GitLab


From 9e14606d8f38ea52a38c27692a9c1513c987a5da Mon Sep 17 00:00:00 2001
From: Hilda Wu <hildawu@realtek.com>
Date: Wed, 21 Jun 2023 18:00:31 +0800
Subject: [PATCH 1089/1806] Bluetooth: msft: Extended monitor tracking by
 address filter

Since limited tracking device per condition, this feature is to support
tracking multiple devices concurrently.
When a pattern monitor detects the device, this feature issues an address
monitor for tracking that device. Let pattern monitor can keep monitor
new devices.
This feature adds an address filter when receiving a LE monitor device
event which monitor handle is for a pattern, and the controller started
monitoring the device. And this feature also has cancelled the monitor
advertisement from address filters when receiving a LE monitor device
event when the controller stopped monitoring the device specified by an
address and monitor handle.

Below is an example to know the feature adds the address filter.

//Add MSFT pattern monitor
< HCI Command: Vendor (0x3f|0x00f0) plen 14          #142 [hci0] 55.552420
        03 b8 a4 03 ff 01 01 06 09 05 5f 52 45 46        .........._REF
> HCI Event: Command Complete (0x0e) plen 6          #143 [hci0] 55.653960
      Vendor (0x3f|0x00f0) ncmd 2
        Status: Success (0x00)
        03 00

//Got event from the pattern monitor
> HCI Event: Vendor (0xff) plen 18                   #148 [hci0] 58.384953
        23 79 54 33 77 88 97 68 02 00 fb c1 29 eb 27 b8  #yT3w..h....).'.
        00 01                                            ..

//Add MSFT address monitor (Sample address: B8:27:EB:29:C1:FB)
< HCI Command: Vendor (0x3f|0x00f0) plen 13          #149 [hci0] 58.385067
        03 b8 a4 03 ff 04 00 fb c1 29 eb 27 b8           .........).'.

//Report to userspace about found device (ADV Monitor Device Found)
@ MGMT Event: Unknown (0x002f) plen 38           {0x0003} [hci0] 58.680042
        01 00 fb c1 29 eb 27 b8 01 ce 00 00 00 00 16 00  ....).'.........
        0a 09 4b 45 59 42 44 5f 52 45 46 02 01 06 03 19  ..KEYBD_REF.....
        c1 03 03 03 12 18                                ......

//Got event from address monitor
> HCI Event: Vendor (0xff) plen 18                   #152 [hci0] 58.672956
        23 79 54 33 77 88 97 68 02 00 fb c1 29 eb 27 b8  #yT3w..h....).'.
        01 01

Signed-off-by: Alex Lu <alex_lu@realsil.com.cn>
Signed-off-by: Hilda Wu <hildawu@realtek.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btrtl.c   |   4 +
 include/net/bluetooth/hci.h |  10 +
 net/bluetooth/msft.c        | 412 ++++++++++++++++++++++++++++++++++--
 3 files changed, 411 insertions(+), 15 deletions(-)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index 04399b3c39a0b..ddae6524106d1 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -1269,6 +1269,10 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev)
 		if (btrtl_dev->project_id == CHIP_ID_8852C)
 			btrealtek_set_flag(hdev, REALTEK_ALT6_CONTINUOUS_TX_CHIP);
 
+		if (btrtl_dev->project_id == CHIP_ID_8852A ||
+		    btrtl_dev->project_id == CHIP_ID_8852C)
+			set_bit(HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, &hdev->quirks);
+
 		hci_set_aosp_capable(hdev);
 		break;
 	default:
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index ab2f8f1817cf1..5723405b833e9 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -309,6 +309,16 @@ enum {
 	 * to support it.
 	 */
 	HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT,
+
+	/* When this quirk is set, MSFT extension monitor tracking by
+	 * address filter is supported. Since tracking quantity of each
+	 * pattern is limited, this feature supports tracking multiple
+	 * devices concurrently if controller supports multiple
+	 * address filters.
+	 *
+	 * This quirk must be set before hci_register_dev is called.
+	 */
+	HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER,
 };
 
 /* HCI device flags */
diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c
index bf5cee48916c7..b80a2162a5c33 100644
--- a/net/bluetooth/msft.c
+++ b/net/bluetooth/msft.c
@@ -91,6 +91,33 @@ struct msft_ev_le_monitor_device {
 struct msft_monitor_advertisement_handle_data {
 	__u8  msft_handle;
 	__u16 mgmt_handle;
+	__s8 rssi_high;
+	__s8 rssi_low;
+	__u8 rssi_low_interval;
+	__u8 rssi_sampling_period;
+	__u8 cond_type;
+	struct list_head list;
+};
+
+enum monitor_addr_filter_state {
+	AF_STATE_IDLE,
+	AF_STATE_ADDING,
+	AF_STATE_ADDED,
+	AF_STATE_REMOVING,
+};
+
+#define MSFT_MONITOR_ADVERTISEMENT_TYPE_ADDR	0x04
+struct msft_monitor_addr_filter_data {
+	__u8     msft_handle;
+	__u8     pattern_handle; /* address filters pertain to */
+	__u16    mgmt_handle;
+	int      state;
+	__s8     rssi_high;
+	__s8     rssi_low;
+	__u8     rssi_low_interval;
+	__u8     rssi_sampling_period;
+	__u8     addr_type;
+	bdaddr_t bdaddr;
 	struct list_head list;
 };
 
@@ -99,9 +126,12 @@ struct msft_data {
 	__u8  evt_prefix_len;
 	__u8  *evt_prefix;
 	struct list_head handle_map;
+	struct list_head address_filters;
 	__u8 resuming;
 	__u8 suspending;
 	__u8 filter_enabled;
+	/* To synchronize add/remove address filter and monitor device event.*/
+	struct mutex filter_lock;
 };
 
 bool msft_monitor_supported(struct hci_dev *hdev)
@@ -180,6 +210,24 @@ static struct msft_monitor_advertisement_handle_data *msft_find_handle_data
 	return NULL;
 }
 
+/* This function requires the caller holds msft->filter_lock */
+static struct msft_monitor_addr_filter_data *msft_find_address_data
+			(struct hci_dev *hdev, u8 addr_type, bdaddr_t *addr,
+			 u8 pattern_handle)
+{
+	struct msft_monitor_addr_filter_data *entry;
+	struct msft_data *msft = hdev->msft_data;
+
+	list_for_each_entry(entry, &msft->address_filters, list) {
+		if (entry->pattern_handle == pattern_handle &&
+		    addr_type == entry->addr_type &&
+		    !bacmp(addr, &entry->bdaddr))
+			return entry;
+	}
+
+	return NULL;
+}
+
 /* This function requires the caller holds hdev->lock */
 static int msft_monitor_device_del(struct hci_dev *hdev, __u16 mgmt_handle,
 				   bdaddr_t *bdaddr, __u8 addr_type,
@@ -240,6 +288,7 @@ static int msft_le_monitor_advertisement_cb(struct hci_dev *hdev, u16 opcode,
 
 	handle_data->mgmt_handle = monitor->handle;
 	handle_data->msft_handle = rp->handle;
+	handle_data->cond_type   = MSFT_MONITOR_ADVERTISEMENT_TYPE_PATTERN;
 	INIT_LIST_HEAD(&handle_data->list);
 	list_add(&handle_data->list, &msft->handle_map);
 
@@ -254,6 +303,70 @@ unlock:
 	return status;
 }
 
+/* This function requires the caller holds hci_req_sync_lock */
+static void msft_remove_addr_filters_sync(struct hci_dev *hdev, u8 handle)
+{
+	struct msft_monitor_addr_filter_data *address_filter, *n;
+	struct msft_cp_le_cancel_monitor_advertisement cp;
+	struct msft_data *msft = hdev->msft_data;
+	struct list_head head;
+	struct sk_buff *skb;
+
+	INIT_LIST_HEAD(&head);
+
+	/* Cancel all corresponding address monitors */
+	mutex_lock(&msft->filter_lock);
+
+	list_for_each_entry_safe(address_filter, n, &msft->address_filters,
+				 list) {
+		if (address_filter->pattern_handle != handle)
+			continue;
+
+		list_del(&address_filter->list);
+
+		/* Keep the address filter and let
+		 * msft_add_address_filter_sync() remove and free the address
+		 * filter.
+		 */
+		if (address_filter->state == AF_STATE_ADDING) {
+			address_filter->state = AF_STATE_REMOVING;
+			continue;
+		}
+
+		/* Keep the address filter and let
+		 * msft_cancel_address_filter_sync() remove and free the address
+		 * filter
+		 */
+		if (address_filter->state == AF_STATE_REMOVING)
+			continue;
+
+		list_add_tail(&address_filter->list, &head);
+	}
+
+	mutex_unlock(&msft->filter_lock);
+
+	list_for_each_entry_safe(address_filter, n, &head, list) {
+		list_del(&address_filter->list);
+
+		cp.sub_opcode = MSFT_OP_LE_CANCEL_MONITOR_ADVERTISEMENT;
+		cp.handle = address_filter->msft_handle;
+
+		skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp,
+				     HCI_CMD_TIMEOUT);
+		if (IS_ERR_OR_NULL(skb)) {
+			kfree(address_filter);
+			continue;
+		}
+
+		kfree_skb(skb);
+
+		bt_dev_dbg(hdev, "MSFT: Canceled device %pMR address filter",
+			   &address_filter->bdaddr);
+
+		kfree(address_filter);
+	}
+}
+
 static int msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev,
 						   u16 opcode,
 						   struct adv_monitor *monitor,
@@ -263,6 +376,7 @@ static int msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev,
 	struct msft_monitor_advertisement_handle_data *handle_data;
 	struct msft_data *msft = hdev->msft_data;
 	int status = 0;
+	u8 msft_handle;
 
 	rp = (struct msft_rp_le_cancel_monitor_advertisement *)skb->data;
 	if (skb->len < sizeof(*rp)) {
@@ -293,11 +407,17 @@ static int msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev,
 						NULL, 0, false);
 		}
 
+		msft_handle = handle_data->msft_handle;
+
 		list_del(&handle_data->list);
 		kfree(handle_data);
-	}
 
-	hci_dev_unlock(hdev);
+		hci_dev_unlock(hdev);
+
+		msft_remove_addr_filters_sync(hdev, msft_handle);
+	} else {
+		hci_dev_unlock(hdev);
+	}
 
 done:
 	return status;
@@ -394,12 +514,14 @@ static int msft_add_monitor_sync(struct hci_dev *hdev,
 {
 	struct msft_cp_le_monitor_advertisement *cp;
 	struct msft_le_monitor_advertisement_pattern_data *pattern_data;
+	struct msft_monitor_advertisement_handle_data *handle_data;
 	struct msft_le_monitor_advertisement_pattern *pattern;
 	struct adv_pattern *entry;
 	size_t total_size = sizeof(*cp) + sizeof(*pattern_data);
 	ptrdiff_t offset = 0;
 	u8 pattern_count = 0;
 	struct sk_buff *skb;
+	int err;
 
 	if (!msft_monitor_pattern_valid(monitor))
 		return -EINVAL;
@@ -436,16 +558,31 @@ static int msft_add_monitor_sync(struct hci_dev *hdev,
 
 	skb = __hci_cmd_sync(hdev, hdev->msft_opcode, total_size, cp,
 			     HCI_CMD_TIMEOUT);
-	kfree(cp);
 
 	if (IS_ERR_OR_NULL(skb)) {
-		if (!skb)
-			return -EIO;
-		return PTR_ERR(skb);
+		err = PTR_ERR(skb);
+		goto out_free;
 	}
 
-	return msft_le_monitor_advertisement_cb(hdev, hdev->msft_opcode,
-						monitor, skb);
+	err = msft_le_monitor_advertisement_cb(hdev, hdev->msft_opcode,
+					       monitor, skb);
+	if (err)
+		goto out_free;
+
+	handle_data = msft_find_handle_data(hdev, monitor->handle, true);
+	if (!handle_data) {
+		err = -ENODATA;
+		goto out_free;
+	}
+
+	handle_data->rssi_high	= cp->rssi_high;
+	handle_data->rssi_low	= cp->rssi_low;
+	handle_data->rssi_low_interval	  = cp->rssi_low_interval;
+	handle_data->rssi_sampling_period = cp->rssi_sampling_period;
+
+out_free:
+	kfree(cp);
+	return err;
 }
 
 /* This function requires the caller holds hci_req_sync_lock */
@@ -538,6 +675,7 @@ void msft_do_close(struct hci_dev *hdev)
 {
 	struct msft_data *msft = hdev->msft_data;
 	struct msft_monitor_advertisement_handle_data *handle_data, *tmp;
+	struct msft_monitor_addr_filter_data *address_filter, *n;
 	struct adv_monitor *monitor;
 
 	if (!msft)
@@ -559,6 +697,14 @@ void msft_do_close(struct hci_dev *hdev)
 		kfree(handle_data);
 	}
 
+	mutex_lock(&msft->filter_lock);
+	list_for_each_entry_safe(address_filter, n, &msft->address_filters,
+				 list) {
+		list_del(&address_filter->list);
+		kfree(address_filter);
+	}
+	mutex_unlock(&msft->filter_lock);
+
 	hci_dev_lock(hdev);
 
 	/* Clear any devices that are being monitored and notify device lost */
@@ -568,6 +714,49 @@ void msft_do_close(struct hci_dev *hdev)
 	hci_dev_unlock(hdev);
 }
 
+static int msft_cancel_address_filter_sync(struct hci_dev *hdev, void *data)
+{
+	struct msft_monitor_addr_filter_data *address_filter = data;
+	struct msft_cp_le_cancel_monitor_advertisement cp;
+	struct msft_data *msft = hdev->msft_data;
+	struct sk_buff *skb;
+	int err = 0;
+
+	if (!msft) {
+		bt_dev_err(hdev, "MSFT: msft data is freed");
+		return -EINVAL;
+	}
+
+	/* The address filter has been removed by hci dev close */
+	if (!test_bit(HCI_UP, &hdev->flags))
+		return 0;
+
+	mutex_lock(&msft->filter_lock);
+	list_del(&address_filter->list);
+	mutex_unlock(&msft->filter_lock);
+
+	cp.sub_opcode = MSFT_OP_LE_CANCEL_MONITOR_ADVERTISEMENT;
+	cp.handle = address_filter->msft_handle;
+
+	skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp,
+			     HCI_CMD_TIMEOUT);
+	if (IS_ERR_OR_NULL(skb)) {
+		bt_dev_err(hdev, "MSFT: Failed to cancel address (%pMR) filter",
+			   &address_filter->bdaddr);
+		err = EIO;
+		goto done;
+	}
+	kfree_skb(skb);
+
+	bt_dev_dbg(hdev, "MSFT: Canceled device %pMR address filter",
+		   &address_filter->bdaddr);
+
+done:
+	kfree(address_filter);
+
+	return err;
+}
+
 void msft_register(struct hci_dev *hdev)
 {
 	struct msft_data *msft = NULL;
@@ -581,7 +770,9 @@ void msft_register(struct hci_dev *hdev)
 	}
 
 	INIT_LIST_HEAD(&msft->handle_map);
+	INIT_LIST_HEAD(&msft->address_filters);
 	hdev->msft_data = msft;
+	mutex_init(&msft->filter_lock);
 }
 
 void msft_unregister(struct hci_dev *hdev)
@@ -596,6 +787,7 @@ void msft_unregister(struct hci_dev *hdev)
 	hdev->msft_data = NULL;
 
 	kfree(msft->evt_prefix);
+	mutex_destroy(&msft->filter_lock);
 	kfree(msft);
 }
 
@@ -645,11 +837,149 @@ static void *msft_skb_pull(struct hci_dev *hdev, struct sk_buff *skb,
 	return data;
 }
 
+static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data)
+{
+	struct msft_monitor_addr_filter_data *address_filter = data;
+	struct msft_rp_le_monitor_advertisement *rp;
+	struct msft_cp_le_monitor_advertisement *cp;
+	struct msft_data *msft = hdev->msft_data;
+	struct sk_buff *skb = NULL;
+	bool remove = false;
+	size_t size;
+
+	if (!msft) {
+		bt_dev_err(hdev, "MSFT: msft data is freed");
+		return -EINVAL;
+	}
+
+	/* The address filter has been removed by hci dev close */
+	if (!test_bit(HCI_UP, &hdev->flags))
+		return -ENODEV;
+
+	/* We are safe to use the address filter from now on.
+	 * msft_monitor_device_evt() wouldn't delete this filter because it's
+	 * not been added by now.
+	 * And all other functions that requiring hci_req_sync_lock wouldn't
+	 * touch this filter before this func completes because it's protected
+	 * by hci_req_sync_lock.
+	 */
+
+	if (address_filter->state == AF_STATE_REMOVING) {
+		mutex_lock(&msft->filter_lock);
+		list_del(&address_filter->list);
+		mutex_unlock(&msft->filter_lock);
+		kfree(address_filter);
+		return 0;
+	}
+
+	size = sizeof(*cp) +
+	       sizeof(address_filter->addr_type) +
+	       sizeof(address_filter->bdaddr);
+	cp = kzalloc(size, GFP_KERNEL);
+	if (!cp) {
+		bt_dev_err(hdev, "MSFT: Alloc cmd param err");
+		remove = true;
+		goto done;
+	}
+	cp->sub_opcode           = MSFT_OP_LE_MONITOR_ADVERTISEMENT;
+	cp->rssi_high		 = address_filter->rssi_high;
+	cp->rssi_low		 = address_filter->rssi_low;
+	cp->rssi_low_interval    = address_filter->rssi_low_interval;
+	cp->rssi_sampling_period = address_filter->rssi_sampling_period;
+	cp->cond_type            = MSFT_MONITOR_ADVERTISEMENT_TYPE_ADDR;
+	cp->data[0]              = address_filter->addr_type;
+	memcpy(&cp->data[1], &address_filter->bdaddr,
+	       sizeof(address_filter->bdaddr));
+
+	skb = __hci_cmd_sync(hdev, hdev->msft_opcode, size, cp,
+			     HCI_CMD_TIMEOUT);
+	if (IS_ERR_OR_NULL(skb)) {
+		bt_dev_err(hdev, "Failed to enable address %pMR filter",
+			   &address_filter->bdaddr);
+		skb = NULL;
+		remove = true;
+		goto done;
+	}
+
+	rp = skb_pull_data(skb, sizeof(*rp));
+	if (!rp || rp->sub_opcode != MSFT_OP_LE_MONITOR_ADVERTISEMENT ||
+	    rp->status)
+		remove = true;
+
+done:
+	mutex_lock(&msft->filter_lock);
+
+	if (remove) {
+		bt_dev_warn(hdev, "MSFT: Remove address (%pMR) filter",
+			    &address_filter->bdaddr);
+		list_del(&address_filter->list);
+		kfree(address_filter);
+	} else {
+		address_filter->state = AF_STATE_ADDED;
+		address_filter->msft_handle = rp->handle;
+		bt_dev_dbg(hdev, "MSFT: Address %pMR filter enabled",
+			   &address_filter->bdaddr);
+	}
+	mutex_unlock(&msft->filter_lock);
+
+	kfree_skb(skb);
+
+	return 0;
+}
+
+/* This function requires the caller holds msft->filter_lock */
+static struct msft_monitor_addr_filter_data *msft_add_address_filter
+		(struct hci_dev *hdev, u8 addr_type, bdaddr_t *bdaddr,
+		 struct msft_monitor_advertisement_handle_data *handle_data)
+{
+	struct msft_monitor_addr_filter_data *address_filter = NULL;
+	struct msft_data *msft = hdev->msft_data;
+	int err;
+
+	address_filter = kzalloc(sizeof(*address_filter), GFP_KERNEL);
+	if (!address_filter)
+		return NULL;
+
+	address_filter->state             = AF_STATE_ADDING;
+	address_filter->msft_handle       = 0xff;
+	address_filter->pattern_handle    = handle_data->msft_handle;
+	address_filter->mgmt_handle       = handle_data->mgmt_handle;
+	address_filter->rssi_high         = handle_data->rssi_high;
+	address_filter->rssi_low          = handle_data->rssi_low;
+	address_filter->rssi_low_interval = handle_data->rssi_low_interval;
+	address_filter->rssi_sampling_period = handle_data->rssi_sampling_period;
+	address_filter->addr_type            = addr_type;
+	bacpy(&address_filter->bdaddr, bdaddr);
+
+	/* With the above AF_STATE_ADDING, duplicated address filter can be
+	 * avoided when receiving monitor device event (found/lost) frequently
+	 * for the same device.
+	 */
+	list_add_tail(&address_filter->list, &msft->address_filters);
+
+	err = hci_cmd_sync_queue(hdev, msft_add_address_filter_sync,
+				 address_filter, NULL);
+	if (err < 0) {
+		bt_dev_err(hdev, "MSFT: Add address %pMR filter err", bdaddr);
+		list_del(&address_filter->list);
+		kfree(address_filter);
+		return NULL;
+	}
+
+	bt_dev_dbg(hdev, "MSFT: Add device %pMR address filter",
+		   &address_filter->bdaddr);
+
+	return address_filter;
+}
+
 /* This function requires the caller holds hdev->lock */
 static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
+	struct msft_monitor_addr_filter_data *n, *address_filter = NULL;
 	struct msft_ev_le_monitor_device *ev;
 	struct msft_monitor_advertisement_handle_data *handle_data;
+	struct msft_data *msft = hdev->msft_data;
+	u16 mgmt_handle = 0xffff;
 	u8 addr_type;
 
 	ev = msft_skb_pull(hdev, skb, MSFT_EV_LE_MONITOR_DEVICE, sizeof(*ev));
@@ -662,9 +992,53 @@ static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		   ev->monitor_state, &ev->bdaddr);
 
 	handle_data = msft_find_handle_data(hdev, ev->monitor_handle, false);
-	if (!handle_data)
+
+	if (!test_bit(HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, &hdev->quirks)) {
+		if (!handle_data)
+			return;
+		mgmt_handle = handle_data->mgmt_handle;
+		goto report_state;
+	}
+
+	if (handle_data) {
+		/* Don't report any device found/lost event from pattern
+		 * monitors. Pattern monitor always has its address filters for
+		 * tracking devices.
+		 */
+
+		address_filter = msft_find_address_data(hdev, ev->addr_type,
+							&ev->bdaddr,
+							handle_data->msft_handle);
+		if (address_filter)
+			return;
+
+		if (ev->monitor_state && handle_data->cond_type ==
+				MSFT_MONITOR_ADVERTISEMENT_TYPE_PATTERN)
+			msft_add_address_filter(hdev, ev->addr_type,
+						&ev->bdaddr, handle_data);
+
 		return;
+	}
 
+	/* This device event is not from pattern monitor.
+	 * Report it if there is a corresponding address_filter for it.
+	 */
+	list_for_each_entry(n, &msft->address_filters, list) {
+		if (n->state == AF_STATE_ADDED &&
+		    n->msft_handle == ev->monitor_handle) {
+			mgmt_handle = n->mgmt_handle;
+			address_filter = n;
+			break;
+		}
+	}
+
+	if (!address_filter) {
+		bt_dev_warn(hdev, "MSFT: Unexpected device event %pMR, %u, %u",
+			    &ev->bdaddr, ev->monitor_handle, ev->monitor_state);
+		return;
+	}
+
+report_state:
 	switch (ev->addr_type) {
 	case ADDR_LE_DEV_PUBLIC:
 		addr_type = BDADDR_LE_PUBLIC;
@@ -681,12 +1055,18 @@ static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		return;
 	}
 
-	if (ev->monitor_state)
-		msft_device_found(hdev, &ev->bdaddr, addr_type,
-				  handle_data->mgmt_handle);
-	else
-		msft_device_lost(hdev, &ev->bdaddr, addr_type,
-				 handle_data->mgmt_handle);
+	if (ev->monitor_state) {
+		msft_device_found(hdev, &ev->bdaddr, addr_type, mgmt_handle);
+	} else {
+		if (address_filter && address_filter->state == AF_STATE_ADDED) {
+			address_filter->state = AF_STATE_REMOVING;
+			hci_cmd_sync_queue(hdev,
+					   msft_cancel_address_filter_sync,
+					   address_filter,
+					   NULL);
+		}
+		msft_device_lost(hdev, &ev->bdaddr, addr_type, mgmt_handle);
+	}
 }
 
 void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb)
@@ -724,7 +1104,9 @@ void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb)
 
 	switch (*evt) {
 	case MSFT_EV_LE_MONITOR_DEVICE:
+		mutex_lock(&msft->filter_lock);
 		msft_monitor_device_evt(hdev, skb);
+		mutex_unlock(&msft->filter_lock);
 		break;
 
 	default:
-- 
GitLab


From c33362a528d968ed7fce21e6a9d4b1334bbbb25c Mon Sep 17 00:00:00 2001
From: Claudia Draghicescu <claudia.rosu@nxp.com>
Date: Thu, 29 Jun 2023 16:45:18 +0300
Subject: [PATCH 1090/1806] Bluetooth: hci_sync: Enable events for BIS capable
 devices

In the case of a Synchronized Receiver capable device, enable at start-up the
events for PA reports, PA Sync Established and Big Info Adv reports.

Signed-off-by: Claudia Draghicescu <claudia.rosu@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index afb8e970e62cc..73b49d0c1e110 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4135,10 +4135,13 @@ static int hci_le_set_event_mask_sync(struct hci_dev *hdev)
 	}
 
 	if (bis_capable(hdev)) {
+		events[1] |= 0x20;	/* LE PA Report */
+		events[1] |= 0x40;	/* LE PA Sync Established */
 		events[3] |= 0x04;	/* LE Create BIG Complete */
 		events[3] |= 0x08;	/* LE Terminate BIG Complete */
 		events[3] |= 0x10;	/* LE BIG Sync Established */
 		events[3] |= 0x20;	/* LE BIG Sync Loss */
+		events[4] |= 0x02;	/* LE BIG Info Advertising Report */
 	}
 
 	return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EVENT_MASK,
-- 
GitLab


From bb925bf9fbc1945eafaebc43ad39fb8a096af995 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Wed, 28 Jun 2023 17:48:31 +0530
Subject: [PATCH 1091/1806] Bluetooth: btintel: Add support for Gale Peak

Add hardware variant(0x1c) for Gale Peak core (CNVi).

Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index dd1e48808ee2c..b32277cb045d6 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -480,6 +480,7 @@ static int btintel_version_info_tlv(struct hci_dev *hdev,
 	case 0x18:	/* Slr */
 	case 0x19:	/* Slr-F */
 	case 0x1b:      /* Mgr */
+	case 0x1c:	/* Gale Peak (GaP) */
 		break;
 	default:
 		bt_dev_err(hdev, "Unsupported Intel hardware variant (0x%x)",
@@ -2648,6 +2649,7 @@ static void btintel_set_msft_opcode(struct hci_dev *hdev, u8 hw_variant)
 	case 0x18:
 	case 0x19:
 	case 0x1b:
+	case 0x1c:
 		hci_set_msft_opcode(hdev, 0xFC1E);
 		break;
 	default:
@@ -2862,6 +2864,7 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 	case 0x18:
 	case 0x19:
 	case 0x1b:
+	case 0x1c:
 		/* Display version information of TLV type */
 		btintel_version_info_tlv(hdev, &ver_tlv);
 
-- 
GitLab


From 3e0635181fccb01f3e6bef148da718226fc0b1db Mon Sep 17 00:00:00 2001
From: Chris Lu <chris.lu@mediatek.com>
Date: Thu, 29 Jun 2023 06:20:03 +0800
Subject: [PATCH 1092/1806] Bluetooth: btmtk: add printing firmware information

Add printing firmware information part when driver loading firmware that
user can get mediatek bluetooth information.

Co-developed-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Chris Lu <chris.lu@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btmtk.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index 9482401d97fab..8490d59502a52 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -57,6 +57,7 @@ int btmtk_setup_firmware_79xx(struct hci_dev *hdev, const char *fwname,
 			      wmt_cmd_sync_func_t wmt_cmd_sync)
 {
 	struct btmtk_hci_wmt_params wmt_params;
+	struct btmtk_patch_header *hdr;
 	struct btmtk_global_desc *globaldesc = NULL;
 	struct btmtk_section_map *sectionmap;
 	const struct firmware *fw;
@@ -75,9 +76,13 @@ int btmtk_setup_firmware_79xx(struct hci_dev *hdev, const char *fwname,
 
 	fw_ptr = fw->data;
 	fw_bin_ptr = fw_ptr;
+	hdr = (struct btmtk_patch_header *)fw_ptr;
 	globaldesc = (struct btmtk_global_desc *)(fw_ptr + MTK_FW_ROM_PATCH_HEADER_SIZE);
 	section_num = le32_to_cpu(globaldesc->section_num);
 
+	bt_dev_info(hdev, "HW/SW Version: 0x%04x%04x, Build Time: %s",
+		    le16_to_cpu(hdr->hwver), le16_to_cpu(hdr->swver), hdr->datetime);
+
 	for (i = 0; i < section_num; i++) {
 		first_block = 1;
 		fw_ptr = fw_bin_ptr;
-- 
GitLab


From ca58330c0b68c5597606f329c75e3c1edadc0f81 Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Thu, 29 Jun 2023 06:54:55 +0800
Subject: [PATCH 1093/1806] Bluetooth: btusb: mediatek: readx_poll_timeout
 replaces open coding

Use readx_poll_timeout instead of open coding to poll the hardware reset
status until it is done.

Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index e1e271e0437d6..2122e86f13cfd 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2657,8 +2657,6 @@ static int btusb_recv_event_realtek(struct hci_dev *hdev, struct sk_buff *skb)
 #define MTK_EP_RST_OPT		0x74011890
 #define MTK_EP_RST_IN_OUT_OPT	0x00010001
 #define MTK_BT_RST_DONE		0x00000100
-#define MTK_BT_RESET_WAIT_MS	100
-#define MTK_BT_RESET_NUM_TRIES	10
 #define MTK_BT_RESET_REG_CONNV3	0x70028610
 #define MTK_BT_READ_DEV_ID	0x70010200
 
@@ -3032,6 +3030,16 @@ static int btusb_mtk_id_get(struct btusb_data *data, u32 reg, u32 *id)
 	return btusb_mtk_reg_read(data, reg, id);
 }
 
+static u32 btusb_mtk_reset_done(struct hci_dev *hdev)
+{
+	struct btusb_data *data = hci_get_drvdata(hdev);
+	u32 val = 0;
+
+	btusb_mtk_uhw_reg_read(data, MTK_BT_MISC, &val);
+
+	return val & MTK_BT_RST_DONE;
+}
+
 static int btusb_mtk_setup(struct hci_dev *hdev)
 {
 	struct btusb_data *data = hci_get_drvdata(hdev);
@@ -3232,7 +3240,7 @@ static void btusb_mtk_cmd_timeout(struct hci_dev *hdev)
 {
 	struct btusb_data *data = hci_get_drvdata(hdev);
 	u32 val;
-	int err, retry = 0;
+	int err;
 	struct btmediatek_data *mediatek;
 
 	/* It's MediaTek specific bluetooth reset mechanism via USB */
@@ -3284,18 +3292,10 @@ static void btusb_mtk_cmd_timeout(struct hci_dev *hdev)
 		btusb_mtk_uhw_reg_read(data, MTK_BT_SUBSYS_RST, &val);
 	}
 
-	/* Poll the register until reset is completed */
-	do {
-		btusb_mtk_uhw_reg_read(data, MTK_BT_MISC, &val);
-		if (val & MTK_BT_RST_DONE) {
-			bt_dev_dbg(hdev, "Bluetooth Reset Successfully");
-			break;
-		}
-
-		bt_dev_dbg(hdev, "Polling Bluetooth Reset CR");
-		retry++;
-		msleep(MTK_BT_RESET_WAIT_MS);
-	} while (retry < MTK_BT_RESET_NUM_TRIES);
+	err = readx_poll_timeout(btusb_mtk_reset_done, hdev, val,
+				 val & MTK_BT_RST_DONE, 20000, 1000000);
+	if (err < 0)
+		bt_dev_err(hdev, "Reset timeout");
 
 	btusb_mtk_id_get(data, 0x70010200, &val);
 	if (!val)
-- 
GitLab


From 25b6d7593a3af75a00374c9afe548a72794e5af0 Mon Sep 17 00:00:00 2001
From: Jing Cai <jing.cai@mediatek.com>
Date: Thu, 29 Jun 2023 06:54:56 +0800
Subject: [PATCH 1094/1806] Bluetooth: btmtk: introduce btmtk reset work

Introduce btmtk_reset_work which can be called whenever the firmware abort,
HCI command timeout, other fatal error happen.

Co-developed-by: Chris Lu <chris.lu@mediatek.com>
Signed-off-by: Chris Lu <chris.lu@mediatek.com>
Co-developed-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Jing Cai <jing.cai@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btmtk.c |  15 ++++
 drivers/bluetooth/btmtk.h |   8 +++
 drivers/bluetooth/btusb.c | 145 +++++++++++++++++++-------------------
 3 files changed, 97 insertions(+), 71 deletions(-)

diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index 8490d59502a52..c83ea3fd524fc 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -285,6 +285,21 @@ int btmtk_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 }
 EXPORT_SYMBOL_GPL(btmtk_set_bdaddr);
 
+void btmtk_reset_sync(struct hci_dev *hdev)
+{
+	struct btmediatek_data *reset_work = hci_get_priv(hdev);
+	int err;
+
+	hci_dev_lock(hdev);
+
+	err = hci_cmd_sync_queue(hdev, reset_work->reset_sync, NULL, NULL);
+	if (err)
+		bt_dev_err(hdev, "failed to reset (%d)", err);
+
+	hci_dev_unlock(hdev);
+}
+EXPORT_SYMBOL_GPL(btmtk_reset_sync);
+
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Mark Chen <mark-yw.chen@mediatek.com>");
 MODULE_DESCRIPTION("Bluetooth support for MediaTek devices ver " VERSION);
diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h
index fadc1a5206522..75d8e71efcd3c 100644
--- a/drivers/bluetooth/btmtk.h
+++ b/drivers/bluetooth/btmtk.h
@@ -120,8 +120,11 @@ struct btmtk_hci_wmt_params {
 	u32 *status;
 };
 
+typedef int (*btmtk_reset_sync_func_t)(struct hci_dev *, void *);
+
 struct btmediatek_data {
 	u32 dev_id;
+	btmtk_reset_sync_func_t reset_sync;
 };
 
 typedef int (*wmt_cmd_sync_func_t)(struct hci_dev *,
@@ -136,6 +139,8 @@ int btmtk_setup_firmware_79xx(struct hci_dev *hdev, const char *fwname,
 
 int btmtk_setup_firmware(struct hci_dev *hdev, const char *fwname,
 			 wmt_cmd_sync_func_t wmt_cmd_sync);
+
+void btmtk_reset_sync(struct hci_dev *hdev);
 #else
 
 static inline int btmtk_set_bdaddr(struct hci_dev *hdev,
@@ -156,4 +161,7 @@ static int btmtk_setup_firmware(struct hci_dev *hdev, const char *fwname,
 	return -EOPNOTSUPP;
 }
 
+static void btmtk_reset_sync(struct hci_dev *hdev)
+{
+}
 #endif
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 2122e86f13cfd..2d3e2cb7963f6 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -3040,6 +3040,78 @@ static u32 btusb_mtk_reset_done(struct hci_dev *hdev)
 	return val & MTK_BT_RST_DONE;
 }
 
+static int btusb_mtk_reset(struct hci_dev *hdev, void *rst_data)
+{
+	struct btusb_data *data = hci_get_drvdata(hdev);
+	struct btmediatek_data *mediatek;
+	u32 val;
+	int err;
+
+	/* It's MediaTek specific bluetooth reset mechanism via USB */
+	if (test_and_set_bit(BTUSB_HW_RESET_ACTIVE, &data->flags)) {
+		bt_dev_err(hdev, "last reset failed? Not resetting again");
+		return -EBUSY;
+	}
+
+	err = usb_autopm_get_interface(data->intf);
+	if (err < 0)
+		return err;
+
+	btusb_stop_traffic(data);
+	usb_kill_anchored_urbs(&data->tx_anchor);
+	mediatek = hci_get_priv(hdev);
+
+	if (mediatek->dev_id == 0x7925) {
+		btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val);
+		val |= (1 << 5);
+		btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val);
+		btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val);
+		val &= 0xFFFF00FF;
+		val |= (1 << 13);
+		btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val);
+		btusb_mtk_uhw_reg_write(data, MTK_EP_RST_OPT, 0x00010001);
+		btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val);
+		val |= (1 << 0);
+		btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val);
+		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT, 0x000000FF);
+		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT, &val);
+		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT1, 0x000000FF);
+		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT1, &val);
+		msleep(100);
+	} else {
+		/* It's Device EndPoint Reset Option Register */
+		bt_dev_dbg(hdev, "Initiating reset mechanism via uhw");
+		btusb_mtk_uhw_reg_write(data, MTK_EP_RST_OPT, MTK_EP_RST_IN_OUT_OPT);
+		btusb_mtk_uhw_reg_read(data, MTK_BT_WDT_STATUS, &val);
+
+		/* Reset the bluetooth chip via USB interface. */
+		btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 1);
+		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT, 0x000000FF);
+		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT, &val);
+		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT1, 0x000000FF);
+		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT1, &val);
+		/* MT7921 need to delay 20ms between toggle reset bit */
+		msleep(20);
+		btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 0);
+		btusb_mtk_uhw_reg_read(data, MTK_BT_SUBSYS_RST, &val);
+	}
+
+	err = readx_poll_timeout(btusb_mtk_reset_done, hdev, val,
+				 val & MTK_BT_RST_DONE, 20000, 1000000);
+	if (err < 0)
+		bt_dev_err(hdev, "Reset timeout");
+
+	btusb_mtk_id_get(data, 0x70010200, &val);
+	if (!val)
+		bt_dev_err(hdev, "Can't get device id, subsys reset fail.");
+
+	usb_queue_reset_device(data->intf);
+
+	clear_bit(BTUSB_HW_RESET_ACTIVE, &data->flags);
+
+	return err;
+}
+
 static int btusb_mtk_setup(struct hci_dev *hdev)
 {
 	struct btusb_data *data = hci_get_drvdata(hdev);
@@ -3079,6 +3151,7 @@ static int btusb_mtk_setup(struct hci_dev *hdev)
 
 	mediatek = hci_get_priv(hdev);
 	mediatek->dev_id = dev_id;
+	mediatek->reset_sync = btusb_mtk_reset;
 
 	switch (dev_id) {
 	case 0x7663:
@@ -3236,76 +3309,6 @@ static int btusb_mtk_shutdown(struct hci_dev *hdev)
 	return 0;
 }
 
-static void btusb_mtk_cmd_timeout(struct hci_dev *hdev)
-{
-	struct btusb_data *data = hci_get_drvdata(hdev);
-	u32 val;
-	int err;
-	struct btmediatek_data *mediatek;
-
-	/* It's MediaTek specific bluetooth reset mechanism via USB */
-	if (test_and_set_bit(BTUSB_HW_RESET_ACTIVE, &data->flags)) {
-		bt_dev_err(hdev, "last reset failed? Not resetting again");
-		return;
-	}
-
-	err = usb_autopm_get_interface(data->intf);
-	if (err < 0)
-		return;
-
-	btusb_stop_traffic(data);
-	usb_kill_anchored_urbs(&data->tx_anchor);
-	mediatek = hci_get_priv(hdev);
-
-	if (mediatek->dev_id == 0x7925) {
-		btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val);
-		val |= (1 << 5);
-		btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val);
-		btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val);
-		val &= 0xFFFF00FF;
-		val |= (1 << 13);
-		btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val);
-		btusb_mtk_uhw_reg_write(data, MTK_EP_RST_OPT, 0x00010001);
-		btusb_mtk_uhw_reg_read(data, MTK_BT_RESET_REG_CONNV3, &val);
-		val |= (1 << 0);
-		btusb_mtk_uhw_reg_write(data, MTK_BT_RESET_REG_CONNV3, val);
-		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT, 0x000000FF);
-		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT, &val);
-		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT1, 0x000000FF);
-		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT1, &val);
-		msleep(100);
-	} else {
-		/* It's Device EndPoint Reset Option Register */
-		bt_dev_dbg(hdev, "Initiating reset mechanism via uhw");
-		btusb_mtk_uhw_reg_write(data, MTK_EP_RST_OPT, MTK_EP_RST_IN_OUT_OPT);
-		btusb_mtk_uhw_reg_read(data, MTK_BT_WDT_STATUS, &val);
-
-		/* Reset the bluetooth chip via USB interface. */
-		btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 1);
-		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT, 0x000000FF);
-		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT, &val);
-		btusb_mtk_uhw_reg_write(data, MTK_UDMA_INT_STA_BT1, 0x000000FF);
-		btusb_mtk_uhw_reg_read(data, MTK_UDMA_INT_STA_BT1, &val);
-		/* MT7921 need to delay 20ms between toggle reset bit */
-		msleep(20);
-		btusb_mtk_uhw_reg_write(data, MTK_BT_SUBSYS_RST, 0);
-		btusb_mtk_uhw_reg_read(data, MTK_BT_SUBSYS_RST, &val);
-	}
-
-	err = readx_poll_timeout(btusb_mtk_reset_done, hdev, val,
-				 val & MTK_BT_RST_DONE, 20000, 1000000);
-	if (err < 0)
-		bt_dev_err(hdev, "Reset timeout");
-
-	btusb_mtk_id_get(data, 0x70010200, &val);
-	if (!val)
-		bt_dev_err(hdev, "Can't get device id, subsys reset fail.");
-
-	usb_queue_reset_device(data->intf);
-
-	clear_bit(BTUSB_HW_RESET_ACTIVE, &data->flags);
-}
-
 static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct btusb_data *data = hci_get_drvdata(hdev);
@@ -4433,7 +4436,7 @@ static int btusb_probe(struct usb_interface *intf,
 		hdev->setup = btusb_mtk_setup;
 		hdev->shutdown = btusb_mtk_shutdown;
 		hdev->manufacturer = 70;
-		hdev->cmd_timeout = btusb_mtk_cmd_timeout;
+		hdev->cmd_timeout = btmtk_reset_sync;
 		hdev->set_bdaddr = btmtk_set_bdaddr;
 		set_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &hdev->quirks);
 		set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks);
-- 
GitLab


From 0b70151328781a89c89e4cf3fae21fc0e98d869e Mon Sep 17 00:00:00 2001
From: Jing Cai <jing.cai@mediatek.com>
Date: Thu, 29 Jun 2023 06:54:57 +0800
Subject: [PATCH 1095/1806] Bluetooth: btusb: mediatek: add MediaTek
 devcoredump support

This patch implement function .coredump() and dmp_hdr() in btusb
driver for MediaTek controller.  FW core dump was triggered by FW
specific event to show something unexpected happened in the controller.

The driver would be responsible for collecting and uploading the device
core dump pieces in hci driver using core dump API. Once we finished
the whole process, the driver would reset the controller to recover the
kind of fatal error.

Co-developed-by: Chris Lu <chris.lu@mediatek.com>
Signed-off-by: Chris Lu <chris.lu@mediatek.com>
Co-developed-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Jing Cai <jing.cai@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btmtk.c | 112 ++++++++++++++++++++++++++++++++++++++
 drivers/bluetooth/btmtk.h |  28 ++++++++++
 drivers/bluetooth/btusb.c |  14 +++++
 3 files changed, 154 insertions(+)

diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index c83ea3fd524fc..786f775196ae5 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -53,6 +53,56 @@ struct btmtk_section_map {
 	};
 } __packed;
 
+static void btmtk_coredump(struct hci_dev *hdev)
+{
+	int err;
+
+	err = __hci_cmd_send(hdev, 0xfd5b, 0, NULL);
+	if (err < 0)
+		bt_dev_err(hdev, "Coredump failed (%d)", err);
+}
+
+static void btmtk_coredump_hdr(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct btmediatek_data *data = hci_get_priv(hdev);
+	char buf[80];
+
+	snprintf(buf, sizeof(buf), "Controller Name: 0x%X\n",
+		 data->dev_id);
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Firmware Version: 0x%X\n",
+		 data->cd_info.fw_version);
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Driver: %s\n",
+		 data->cd_info.driver_name);
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Vendor: MediaTek\n");
+	skb_put_data(skb, buf, strlen(buf));
+}
+
+static void btmtk_coredump_notify(struct hci_dev *hdev, int state)
+{
+	struct btmediatek_data *data = hci_get_priv(hdev);
+
+	switch (state) {
+	case HCI_DEVCOREDUMP_IDLE:
+		data->cd_info.state = HCI_DEVCOREDUMP_IDLE;
+		break;
+	case HCI_DEVCOREDUMP_ACTIVE:
+		data->cd_info.state = HCI_DEVCOREDUMP_ACTIVE;
+		break;
+	case HCI_DEVCOREDUMP_TIMEOUT:
+	case HCI_DEVCOREDUMP_ABORT:
+	case HCI_DEVCOREDUMP_DONE:
+		data->cd_info.state = HCI_DEVCOREDUMP_IDLE;
+		btmtk_reset_sync(hdev);
+		break;
+	}
+}
+
 int btmtk_setup_firmware_79xx(struct hci_dev *hdev, const char *fwname,
 			      wmt_cmd_sync_func_t wmt_cmd_sync)
 {
@@ -300,6 +350,68 @@ void btmtk_reset_sync(struct hci_dev *hdev)
 }
 EXPORT_SYMBOL_GPL(btmtk_reset_sync);
 
+int btmtk_register_coredump(struct hci_dev *hdev, const char *name,
+			    u32 fw_version)
+{
+	struct btmediatek_data *data = hci_get_priv(hdev);
+
+	if (!IS_ENABLED(CONFIG_DEV_COREDUMP))
+		return -EOPNOTSUPP;
+
+	data->cd_info.fw_version = fw_version;
+	data->cd_info.state = HCI_DEVCOREDUMP_IDLE;
+	data->cd_info.driver_name = name;
+
+	return hci_devcd_register(hdev, btmtk_coredump, btmtk_coredump_hdr,
+				  btmtk_coredump_notify);
+}
+EXPORT_SYMBOL_GPL(btmtk_register_coredump);
+
+int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct btmediatek_data *data = hci_get_priv(hdev);
+	int err;
+
+	if (!IS_ENABLED(CONFIG_DEV_COREDUMP))
+		return 0;
+
+	switch (data->cd_info.state) {
+	case HCI_DEVCOREDUMP_IDLE:
+		err = hci_devcd_init(hdev, MTK_COREDUMP_SIZE);
+		if (err < 0)
+			break;
+		data->cd_info.cnt = 0;
+
+		/* It is supposed coredump can be done within 5 seconds */
+		schedule_delayed_work(&hdev->dump.dump_timeout,
+				      msecs_to_jiffies(5000));
+		fallthrough;
+	case HCI_DEVCOREDUMP_ACTIVE:
+	default:
+		err = hci_devcd_append(hdev, skb);
+		if (err < 0)
+			break;
+		data->cd_info.cnt++;
+
+		/* Mediatek coredump data would be more than MTK_COREDUMP_NUM */
+		if (data->cd_info.cnt > MTK_COREDUMP_NUM &&
+		    skb->len > sizeof(MTK_COREDUMP_END) &&
+		    !memcmp((char *)&skb->data[skb->len - sizeof(MTK_COREDUMP_END)],
+			    MTK_COREDUMP_END, sizeof(MTK_COREDUMP_END) - 1)) {
+			bt_dev_info(hdev, "Mediatek coredump end");
+			hci_devcd_complete(hdev);
+		}
+
+		break;
+	}
+
+	if (err < 0)
+		kfree_skb(skb);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(btmtk_process_coredump);
+
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Mark Chen <mark-yw.chen@mediatek.com>");
 MODULE_DESCRIPTION("Bluetooth support for MediaTek devices ver " VERSION);
diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h
index 75d8e71efcd3c..68309dfe076af 100644
--- a/drivers/bluetooth/btmtk.h
+++ b/drivers/bluetooth/btmtk.h
@@ -22,6 +22,10 @@
 #define MT7921_DLSTATUS 0x7c053c10
 #define BT_DL_STATE BIT(1)
 
+#define MTK_COREDUMP_SIZE		(1024 * 1000)
+#define MTK_COREDUMP_END		"coredump end"
+#define MTK_COREDUMP_NUM		255
+
 enum {
 	BTMTK_WMT_PATCH_DWNLD = 0x1,
 	BTMTK_WMT_TEST = 0x2,
@@ -122,9 +126,17 @@ struct btmtk_hci_wmt_params {
 
 typedef int (*btmtk_reset_sync_func_t)(struct hci_dev *, void *);
 
+struct btmtk_coredump_info {
+	const char *driver_name;
+	u32 fw_version;
+	u16 cnt;
+	int state;
+};
+
 struct btmediatek_data {
 	u32 dev_id;
 	btmtk_reset_sync_func_t reset_sync;
+	struct btmtk_coredump_info cd_info;
 };
 
 typedef int (*wmt_cmd_sync_func_t)(struct hci_dev *,
@@ -141,6 +153,11 @@ int btmtk_setup_firmware(struct hci_dev *hdev, const char *fwname,
 			 wmt_cmd_sync_func_t wmt_cmd_sync);
 
 void btmtk_reset_sync(struct hci_dev *hdev);
+
+int btmtk_register_coredump(struct hci_dev *hdev, const char *name,
+			    u32 fw_version);
+
+int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb);
 #else
 
 static inline int btmtk_set_bdaddr(struct hci_dev *hdev,
@@ -164,4 +181,15 @@ static int btmtk_setup_firmware(struct hci_dev *hdev, const char *fwname,
 static void btmtk_reset_sync(struct hci_dev *hdev)
 {
 }
+
+static int btmtk_register_coredump(struct hci_dev *hdev, const char *name,
+				   u32 fw_version)
+{
+	return -EOPNOTSUPP;
+}
+
+static int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	return -EOPNOTSUPP;
+}
 #endif
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 2d3e2cb7963f6..2bd819bf6d104 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -3153,6 +3153,10 @@ static int btusb_mtk_setup(struct hci_dev *hdev)
 	mediatek->dev_id = dev_id;
 	mediatek->reset_sync = btusb_mtk_reset;
 
+	err = btmtk_register_coredump(hdev, btusb_driver.name, fw_version);
+	if (err < 0)
+		bt_dev_err(hdev, "Failed to register coredump (%d)", err);
+
 	switch (dev_id) {
 	case 0x7663:
 		fwname = FIRMWARE_MT7663;
@@ -3313,6 +3317,7 @@ static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct btusb_data *data = hci_get_drvdata(hdev);
 	u16 handle = le16_to_cpu(hci_acl_hdr(skb)->handle);
+	struct sk_buff *skb_cd;
 
 	switch (handle) {
 	case 0xfc6f:		/* Firmware dump from device */
@@ -3320,6 +3325,15 @@ static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb)
 		 * suspend and thus disable auto-suspend.
 		 */
 		usb_disable_autosuspend(data->udev);
+
+		/* We need to forward the diagnostic packet to userspace daemon
+		 * for backward compatibility, so we have to clone the packet
+		 * extraly for the in-kernel coredump support.
+		 */
+		skb_cd = skb_clone(skb, GFP_ATOMIC);
+		if (skb_cd)
+			btmtk_process_coredump(hdev, skb_cd);
+
 		fallthrough;
 	case 0x05ff:		/* Firmware debug logging 1 */
 	case 0x05fe:		/* Firmware debug logging 2 */
-- 
GitLab


From a13f316e90fdb1fb6df6582e845aa9b3270f3581 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 26 Jun 2023 17:25:06 -0700
Subject: [PATCH 1096/1806] Bluetooth: hci_conn: Consolidate code for aborting
 connections

This consolidates code for aborting connections using
hci_cmd_sync_queue so it is synchronized with other threads, but
because of the fact that some commands may block the cmd_sync_queue
while waiting specific events this attempt to cancel those requests by
using hci_cmd_sync_cancel.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |   2 +-
 net/bluetooth/hci_conn.c         | 154 ++++++-------------------------
 net/bluetooth/hci_sync.c         |  23 +++--
 net/bluetooth/mgmt.c             |  15 +--
 4 files changed, 47 insertions(+), 147 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 9140d4a80e38e..2dd59e3a51b36 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -739,6 +739,7 @@ struct hci_conn {
 	unsigned long	flags;
 
 	enum conn_reasons conn_reason;
+	__u8		abort_reason;
 
 	__u32		clock;
 	__u16		clock_accuracy;
@@ -758,7 +759,6 @@ struct hci_conn {
 	struct delayed_work auto_accept_work;
 	struct delayed_work idle_work;
 	struct delayed_work le_conn_timeout;
-	struct work_struct  le_scan_cleanup;
 
 	struct device	dev;
 	struct dentry	*debugfs;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 0f89daafe194d..fa9236dfba3eb 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -178,57 +178,6 @@ static void hci_conn_cleanup(struct hci_conn *conn)
 	hci_conn_put(conn);
 }
 
-static void le_scan_cleanup(struct work_struct *work)
-{
-	struct hci_conn *conn = container_of(work, struct hci_conn,
-					     le_scan_cleanup);
-	struct hci_dev *hdev = conn->hdev;
-	struct hci_conn *c = NULL;
-
-	BT_DBG("%s hcon %p", hdev->name, conn);
-
-	hci_dev_lock(hdev);
-
-	/* Check that the hci_conn is still around */
-	rcu_read_lock();
-	list_for_each_entry_rcu(c, &hdev->conn_hash.list, list) {
-		if (c == conn)
-			break;
-	}
-	rcu_read_unlock();
-
-	if (c == conn) {
-		hci_connect_le_scan_cleanup(conn, 0x00);
-		hci_conn_cleanup(conn);
-	}
-
-	hci_dev_unlock(hdev);
-	hci_dev_put(hdev);
-	hci_conn_put(conn);
-}
-
-static void hci_connect_le_scan_remove(struct hci_conn *conn)
-{
-	BT_DBG("%s hcon %p", conn->hdev->name, conn);
-
-	/* We can't call hci_conn_del/hci_conn_cleanup here since that
-	 * could deadlock with another hci_conn_del() call that's holding
-	 * hci_dev_lock and doing cancel_delayed_work_sync(&conn->disc_work).
-	 * Instead, grab temporary extra references to the hci_dev and
-	 * hci_conn and perform the necessary cleanup in a separate work
-	 * callback.
-	 */
-
-	hci_dev_hold(conn->hdev);
-	hci_conn_get(conn);
-
-	/* Even though we hold a reference to the hdev, many other
-	 * things might get cleaned up meanwhile, including the hdev's
-	 * own workqueue, so we can't use that for scheduling.
-	 */
-	schedule_work(&conn->le_scan_cleanup);
-}
-
 static void hci_acl_create_connection(struct hci_conn *conn)
 {
 	struct hci_dev *hdev = conn->hdev;
@@ -679,13 +628,6 @@ static void hci_conn_timeout(struct work_struct *work)
 	if (refcnt > 0)
 		return;
 
-	/* LE connections in scanning state need special handling */
-	if (conn->state == BT_CONNECT && conn->type == LE_LINK &&
-	    test_bit(HCI_CONN_SCANNING, &conn->flags)) {
-		hci_connect_le_scan_remove(conn);
-		return;
-	}
-
 	hci_abort_conn(conn, hci_proto_disconn_ind(conn));
 }
 
@@ -1066,7 +1008,6 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst,
 	INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept);
 	INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle);
 	INIT_DELAYED_WORK(&conn->le_conn_timeout, le_conn_timeout);
-	INIT_WORK(&conn->le_scan_cleanup, le_scan_cleanup);
 
 	atomic_set(&conn->refcnt, 0);
 
@@ -2888,81 +2829,46 @@ u32 hci_conn_get_phy(struct hci_conn *conn)
 	return phys;
 }
 
-int hci_abort_conn(struct hci_conn *conn, u8 reason)
+static int abort_conn_sync(struct hci_dev *hdev, void *data)
 {
-	int r = 0;
+	struct hci_conn *conn;
+	u16 handle = PTR_ERR(data);
 
-	if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags))
+	conn = hci_conn_hash_lookup_handle(hdev, handle);
+	if (!conn)
 		return 0;
 
-	switch (conn->state) {
-	case BT_CONNECTED:
-	case BT_CONFIG:
-		if (conn->type == AMP_LINK) {
-			struct hci_cp_disconn_phy_link cp;
+	return hci_abort_conn_sync(hdev, conn, conn->abort_reason);
+}
 
-			cp.phy_handle = HCI_PHY_HANDLE(conn->handle);
-			cp.reason = reason;
-			r = hci_send_cmd(conn->hdev, HCI_OP_DISCONN_PHY_LINK,
-					 sizeof(cp), &cp);
-		} else {
-			struct hci_cp_disconnect dc;
+int hci_abort_conn(struct hci_conn *conn, u8 reason)
+{
+	struct hci_dev *hdev = conn->hdev;
 
-			dc.handle = cpu_to_le16(conn->handle);
-			dc.reason = reason;
-			r = hci_send_cmd(conn->hdev, HCI_OP_DISCONNECT,
-					 sizeof(dc), &dc);
-		}
+	/* If abort_reason has already been set it means the connection is
+	 * already being aborted so don't attempt to overwrite it.
+	 */
+	if (conn->abort_reason)
+		return 0;
 
-		conn->state = BT_DISCONN;
+	bt_dev_dbg(hdev, "handle 0x%2.2x reason 0x%2.2x", conn->handle, reason);
 
-		break;
-	case BT_CONNECT:
-		if (conn->type == LE_LINK) {
-			if (test_bit(HCI_CONN_SCANNING, &conn->flags))
-				break;
-			r = hci_send_cmd(conn->hdev,
-					 HCI_OP_LE_CREATE_CONN_CANCEL, 0, NULL);
-		} else if (conn->type == ACL_LINK) {
-			if (conn->hdev->hci_ver < BLUETOOTH_VER_1_2)
-				break;
-			r = hci_send_cmd(conn->hdev,
-					 HCI_OP_CREATE_CONN_CANCEL,
-					 6, &conn->dst);
-		}
-		break;
-	case BT_CONNECT2:
-		if (conn->type == ACL_LINK) {
-			struct hci_cp_reject_conn_req rej;
-
-			bacpy(&rej.bdaddr, &conn->dst);
-			rej.reason = reason;
-
-			r = hci_send_cmd(conn->hdev,
-					 HCI_OP_REJECT_CONN_REQ,
-					 sizeof(rej), &rej);
-		} else if (conn->type == SCO_LINK || conn->type == ESCO_LINK) {
-			struct hci_cp_reject_sync_conn_req rej;
-
-			bacpy(&rej.bdaddr, &conn->dst);
-
-			/* SCO rejection has its own limited set of
-			 * allowed error values (0x0D-0x0F) which isn't
-			 * compatible with most values passed to this
-			 * function. To be safe hard-code one of the
-			 * values that's suitable for SCO.
-			 */
-			rej.reason = HCI_ERROR_REJ_LIMITED_RESOURCES;
+	conn->abort_reason = reason;
 
-			r = hci_send_cmd(conn->hdev,
-					 HCI_OP_REJECT_SYNC_CONN_REQ,
-					 sizeof(rej), &rej);
+	/* If the connection is pending check the command opcode since that
+	 * might be blocking on hci_cmd_sync_work while waiting its respective
+	 * event so we need to hci_cmd_sync_cancel to cancel it.
+	 */
+	if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) {
+		switch (hci_skb_event(hdev->sent_cmd)) {
+		case HCI_EV_LE_CONN_COMPLETE:
+		case HCI_EV_LE_ENHANCED_CONN_COMPLETE:
+		case HCI_EVT_LE_CIS_ESTABLISHED:
+			hci_cmd_sync_cancel(hdev, -ECANCELED);
+			break;
 		}
-		break;
-	default:
-		conn->state = BT_CLOSED;
-		break;
 	}
 
-	return r;
+	return hci_cmd_sync_queue(hdev, abort_conn_sync, ERR_PTR(conn->handle),
+				  NULL);
 }
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 73b49d0c1e110..5f7a901709b52 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5274,22 +5274,27 @@ static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn,
 }
 
 static int hci_le_connect_cancel_sync(struct hci_dev *hdev,
-				      struct hci_conn *conn)
+				      struct hci_conn *conn, u8 reason)
 {
+	/* Return reason if scanning since the connection shall probably be
+	 * cleanup directly.
+	 */
 	if (test_bit(HCI_CONN_SCANNING, &conn->flags))
-		return 0;
+		return reason;
 
-	if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags))
+	if (conn->role == HCI_ROLE_SLAVE ||
+	    test_and_set_bit(HCI_CONN_CANCEL, &conn->flags))
 		return 0;
 
 	return __hci_cmd_sync_status(hdev, HCI_OP_LE_CREATE_CONN_CANCEL,
 				     0, NULL, HCI_CMD_TIMEOUT);
 }
 
-static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn)
+static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn,
+				   u8 reason)
 {
 	if (conn->type == LE_LINK)
-		return hci_le_connect_cancel_sync(hdev, conn);
+		return hci_le_connect_cancel_sync(hdev, conn, reason);
 
 	if (hdev->hci_ver < BLUETOOTH_VER_1_2)
 		return 0;
@@ -5342,9 +5347,11 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
 	case BT_CONFIG:
 		return hci_disconnect_sync(hdev, conn, reason);
 	case BT_CONNECT:
-		err = hci_connect_cancel_sync(hdev, conn);
+		err = hci_connect_cancel_sync(hdev, conn, reason);
 		/* Cleanup hci_conn object if it cannot be cancelled as it
-		 * likelly means the controller and host stack are out of sync.
+		 * likelly means the controller and host stack are out of sync
+		 * or in case of LE it was still scanning so it can be cleanup
+		 * safely.
 		 */
 		if (err) {
 			hci_dev_lock(hdev);
@@ -6258,7 +6265,7 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn)
 
 done:
 	if (err == -ETIMEDOUT)
-		hci_le_connect_cancel_sync(hdev, conn);
+		hci_le_connect_cancel_sync(hdev, conn, 0x00);
 
 	/* Re-enable advertising after the connection attempt is finished. */
 	hci_resume_advertising_sync(hdev);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 4c352abe063b9..5707ff4688423 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3586,18 +3586,6 @@ unlock:
 	return err;
 }
 
-static int abort_conn_sync(struct hci_dev *hdev, void *data)
-{
-	struct hci_conn *conn;
-	u16 handle = PTR_ERR(data);
-
-	conn = hci_conn_hash_lookup_handle(hdev, handle);
-	if (!conn)
-		return 0;
-
-	return hci_abort_conn_sync(hdev, conn, HCI_ERROR_REMOTE_USER_TERM);
-}
-
 static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 			      u16 len)
 {
@@ -3648,8 +3636,7 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 					      le_addr_type(addr->type));
 
 	if (conn->conn_reason == CONN_REASON_PAIR_DEVICE)
-		hci_cmd_sync_queue(hdev, abort_conn_sync, ERR_PTR(conn->handle),
-				   NULL);
+		hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM);
 
 unlock:
 	hci_dev_unlock(hdev);
-- 
GitLab


From 04a51d616929eb96b7a3e547bc11d3bb46af2c9f Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 27 Jun 2023 15:55:47 -0700
Subject: [PATCH 1097/1806] Bluetooth: hci_sync: Fix not handling ISO_LINK in
 hci_abort_conn_sync

ISO_LINK connections where not being handled properly on
hci_abort_conn_sync which sometimes resulted in sending the wrong
commands, or in case of having the reject command being sent by the
socket code (iso.c) which is sort of a layer violation.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 23 +++++++++++++++++++----
 net/bluetooth/hci_sync.c | 34 ++++++++++++++++++++++++++++++++++
 net/bluetooth/iso.c      | 14 --------------
 3 files changed, 53 insertions(+), 18 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index fa9236dfba3eb..a0ffe7db412bf 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1223,7 +1223,12 @@ void hci_conn_failed(struct hci_conn *conn, u8 status)
 
 static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err)
 {
-	struct hci_conn *conn = data;
+	struct hci_conn *conn;
+	u16 handle = PTR_ERR(data);
+
+	conn = hci_conn_hash_lookup_handle(hdev, handle);
+	if (!conn)
+		return;
 
 	bt_dev_dbg(hdev, "err %d", err);
 
@@ -1248,10 +1253,17 @@ done:
 
 static int hci_connect_le_sync(struct hci_dev *hdev, void *data)
 {
-	struct hci_conn *conn = data;
+	struct hci_conn *conn;
+	u16 handle = PTR_ERR(data);
+
+	conn = hci_conn_hash_lookup_handle(hdev, handle);
+	if (!conn)
+		return 0;
 
 	bt_dev_dbg(hdev, "conn %p", conn);
 
+	conn->state = BT_CONNECT;
+
 	return hci_le_create_conn_sync(hdev, conn);
 }
 
@@ -1321,10 +1333,10 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	conn->sec_level = BT_SECURITY_LOW;
 	conn->conn_timeout = conn_timeout;
 
-	conn->state = BT_CONNECT;
 	clear_bit(HCI_CONN_SCANNING, &conn->flags);
 
-	err = hci_cmd_sync_queue(hdev, hci_connect_le_sync, conn,
+	err = hci_cmd_sync_queue(hdev, hci_connect_le_sync,
+				 ERR_PTR(conn->handle),
 				 create_le_conn_complete);
 	if (err) {
 		hci_conn_del(conn);
@@ -2858,6 +2870,9 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason)
 	/* If the connection is pending check the command opcode since that
 	 * might be blocking on hci_cmd_sync_work while waiting its respective
 	 * event so we need to hci_cmd_sync_cancel to cancel it.
+	 *
+	 * hci_connect_le serializes the connection attempts so only one
+	 * connection can be in BT_CONNECT at time.
 	 */
 	if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) {
 		switch (hci_skb_event(hdev->sent_cmd)) {
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 5f7a901709b52..c085b54d158bc 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5296,6 +5296,24 @@ static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn,
 	if (conn->type == LE_LINK)
 		return hci_le_connect_cancel_sync(hdev, conn, reason);
 
+	if (conn->type == ISO_LINK) {
+		/* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
+		 * page 1857:
+		 *
+		 * If this command is issued for a CIS on the Central and the
+		 * CIS is successfully terminated before being established,
+		 * then an HCI_LE_CIS_Established event shall also be sent for
+		 * this CIS with the Status Operation Cancelled by Host (0x44).
+		 */
+		if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags))
+			return hci_disconnect_sync(hdev, conn, reason);
+
+		/* There is no way to cancel a BIS without terminating the BIG
+		 * which is done later on connection cleanup.
+		 */
+		return 0;
+	}
+
 	if (hdev->hci_ver < BLUETOOTH_VER_1_2)
 		return 0;
 
@@ -5322,11 +5340,27 @@ static int hci_reject_sco_sync(struct hci_dev *hdev, struct hci_conn *conn,
 				     sizeof(cp), &cp, HCI_CMD_TIMEOUT);
 }
 
+static int hci_le_reject_cis_sync(struct hci_dev *hdev, struct hci_conn *conn,
+				  u8 reason)
+{
+	struct hci_cp_le_reject_cis cp;
+
+	memset(&cp, 0, sizeof(cp));
+	cp.handle = cpu_to_le16(conn->handle);
+	cp.reason = reason;
+
+	return __hci_cmd_sync_status(hdev, HCI_OP_LE_REJECT_CIS,
+				     sizeof(cp), &cp, HCI_CMD_TIMEOUT);
+}
+
 static int hci_reject_conn_sync(struct hci_dev *hdev, struct hci_conn *conn,
 				u8 reason)
 {
 	struct hci_cp_reject_conn_req cp;
 
+	if (conn->type == ISO_LINK)
+		return hci_le_reject_cis_sync(hdev, conn, reason);
+
 	if (conn->type == SCO_LINK || conn->type == ESCO_LINK)
 		return hci_reject_sco_sync(hdev, conn, reason);
 
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 84d238d0639a6..9c41af55f2c73 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -614,18 +614,6 @@ static void iso_sock_kill(struct sock *sk)
 	sock_put(sk);
 }
 
-static void iso_conn_defer_reject(struct hci_conn *conn)
-{
-	struct hci_cp_le_reject_cis cp;
-
-	BT_DBG("conn %p", conn);
-
-	memset(&cp, 0, sizeof(cp));
-	cp.handle = cpu_to_le16(conn->handle);
-	cp.reason = HCI_ERROR_REJ_BAD_ADDR;
-	hci_send_cmd(conn->hdev, HCI_OP_LE_REJECT_CIS, sizeof(cp), &cp);
-}
-
 static void __iso_sock_close(struct sock *sk)
 {
 	BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket);
@@ -650,8 +638,6 @@ static void __iso_sock_close(struct sock *sk)
 		break;
 
 	case BT_CONNECT2:
-		if (iso_pi(sk)->conn->hcon)
-			iso_conn_defer_reject(iso_pi(sk)->conn->hcon);
 		iso_chan_del(sk, ECONNRESET);
 		break;
 	case BT_CONNECT:
-- 
GitLab


From 9f78191cc9f1b34c2e2afd7b554a83bf034092dd Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 28 Jun 2023 12:15:53 -0700
Subject: [PATCH 1098/1806] Bluetooth: hci_conn: Always allocate unique handles

This attempts to always allocate a unique handle for connections so they
can be properly aborted by the likes of hci_abort_conn, so this uses the
invalid range as a pool of unset handles that way if userspace is trying
to create multiple connections at once each will be given a unique
handle which will be considered unset.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  2 +-
 net/bluetooth/hci_conn.c         | 25 ++++++++++++++++++++++---
 net/bluetooth/hci_event.c        |  6 +++---
 3 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2dd59e3a51b36..491ab83ccafc9 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -321,8 +321,8 @@ struct adv_monitor {
 
 #define HCI_MAX_SHORT_NAME_LENGTH	10
 
-#define HCI_CONN_HANDLE_UNSET		0xffff
 #define HCI_CONN_HANDLE_MAX		0x0eff
+#define HCI_CONN_HANDLE_UNSET(_handle)	(_handle > HCI_CONN_HANDLE_MAX)
 
 /* Min encryption key size to match with SMP */
 #define HCI_MIN_ENC_KEY_SIZE		7
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index a0ffe7db412bf..af7dc8131a8c4 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -932,6 +932,25 @@ static void cis_cleanup(struct hci_conn *conn)
 	hci_le_remove_cig(hdev, conn->iso_qos.ucast.cig);
 }
 
+static u16 hci_conn_hash_alloc_unset(struct hci_dev *hdev)
+{
+	struct hci_conn_hash *h = &hdev->conn_hash;
+	struct hci_conn  *c;
+	u16 handle = HCI_CONN_HANDLE_MAX + 1;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(c, &h->list, list) {
+		/* Find the first unused handle */
+		if (handle == 0xffff || c->handle != handle)
+			break;
+		handle++;
+	}
+	rcu_read_unlock();
+
+	return handle;
+}
+
 struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst,
 			      u8 role)
 {
@@ -945,7 +964,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst,
 
 	bacpy(&conn->dst, dst);
 	bacpy(&conn->src, &hdev->bdaddr);
-	conn->handle = HCI_CONN_HANDLE_UNSET;
+	conn->handle = hci_conn_hash_alloc_unset(hdev);
 	conn->hdev  = hdev;
 	conn->type  = type;
 	conn->role  = role;
@@ -1057,7 +1076,7 @@ static void hci_conn_unlink(struct hci_conn *conn)
 			 */
 			if ((child->type == SCO_LINK ||
 			     child->type == ESCO_LINK) &&
-			    child->handle == HCI_CONN_HANDLE_UNSET)
+			    HCI_CONN_HANDLE_UNSET(child->handle))
 				hci_conn_del(child);
 		}
 
@@ -1943,7 +1962,7 @@ int hci_conn_check_create_cis(struct hci_conn *conn)
 		return -EINVAL;
 
 	if (!conn->parent || conn->parent->state != BT_CONNECTED ||
-	    conn->state != BT_CONNECT || conn->handle == HCI_CONN_HANDLE_UNSET)
+	    conn->state != BT_CONNECT || HCI_CONN_HANDLE_UNSET(conn->handle))
 		return 1;
 
 	return 0;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index c67612c99f89f..90cfd30616f51 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3173,7 +3173,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data,
 	 * As the connection handle is set here for the first time, it indicates
 	 * whether the connection is already set up.
 	 */
-	if (conn->handle != HCI_CONN_HANDLE_UNSET) {
+	if (!HCI_CONN_HANDLE_UNSET(conn->handle)) {
 		bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection");
 		goto unlock;
 	}
@@ -5032,7 +5032,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data,
 	 * As the connection handle is set here for the first time, it indicates
 	 * whether the connection is already set up.
 	 */
-	if (conn->handle != HCI_CONN_HANDLE_UNSET) {
+	if (!HCI_CONN_HANDLE_UNSET(conn->handle)) {
 		bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete event for existing connection");
 		goto unlock;
 	}
@@ -5896,7 +5896,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
 	 * As the connection handle is set here for the first time, it indicates
 	 * whether the connection is already set up.
 	 */
-	if (conn->handle != HCI_CONN_HANDLE_UNSET) {
+	if (!HCI_CONN_HANDLE_UNSET(conn->handle)) {
 		bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection");
 		goto unlock;
 	}
-- 
GitLab


From e160a8f4e920e5cf4e16a17f57367954c9436aea Mon Sep 17 00:00:00 2001
From: Valentin David <valentin.david@gmail.com>
Date: Sun, 2 Jul 2023 23:01:38 +0200
Subject: [PATCH 1099/1806] Bluetooth: btusb: Add device 0489:e0f5 as MT7922
 device

Asus ROG Ally gaming computer has a MediaTek MT7922 chip that uses USB id
0489:e0f5 and needs to be added to the table. Without this, the device is
not usable and gives the following error:

Bluetooth: hci0: Opcode 0x c03 failed: -110

Output from /sys/kernel/debug/usb/devices:

T:  Bus=01 Lev=01 Prnt=01 Port=03 Cnt=03 Dev#=  4 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0489 ProdID=e0f5 Rev= 1.00
S:  Manufacturer=MediaTek Inc.
S:  Product=Wireless_Device
S:  SerialNumber=000000000
C:* #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=100mA
A:  FirstIf#= 0 IfCount= 3 Cls=e0(wlcon) Sub=01 Prot=01
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=125us
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS=  64 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS=  64 Ivl=125us
I:  If#= 2 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS= 512 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS= 512 Ivl=125us

Signed-off-by: Valentin David <valentin.david@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 2bd819bf6d104..63c4b7a3319e5 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -628,6 +628,9 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe0f2), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH |
 						     BTUSB_VALID_LE_STATES },
+	{ USB_DEVICE(0x0489, 0xe0f5), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH |
+						     BTUSB_VALID_LE_STATES },
 
 	/* Additional Realtek 8723AE Bluetooth devices */
 	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
-- 
GitLab


From f777d88278170410b06a1f6633f3b9375a4ddd6b Mon Sep 17 00:00:00 2001
From: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Date: Mon, 3 Jul 2023 10:02:38 +0300
Subject: [PATCH 1100/1806] Bluetooth: ISO: Notify user space about failed bis
 connections

Some use cases require the user to be informed if BIG synchronization
fails. This commit makes it so that even if the BIG sync established
event arrives with error status, a new hconn is added for each BIS,
and the iso layer is notified about the failed connections.

Unsuccesful bis connections will be marked using the
HCI_CONN_BIG_SYNC_FAILED flag. From the iso layer, the POLLERR event
is triggered on the newly allocated bis sockets, before adding them
to the accept list of the parent socket.

From user space, a new fd for each failed bis connection will be
obtained by calling accept. The user should check for the POLLERR
event on the new socket, to determine if the connection was successful
or not.

The HCI_CONN_BIG_SYNC flag has been added to mark whether the BIG sync
has been successfully established. This flag is checked at bis cleanup,
so the HCI LE BIG Terminate Sync command is only issued if needed.

The BT_SK_BIG_SYNC flag indicates if BIG create sync has been called
for a listening socket, to avoid issuing the command everytime a BIGInfo
advertising report is received.

Signed-off-by: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h | 25 ++++++++++++++++++++
 net/bluetooth/hci_conn.c         | 37 +++++++++++------------------
 net/bluetooth/hci_event.c        | 21 +++++++++++++----
 net/bluetooth/hci_sync.c         |  8 +++++++
 net/bluetooth/iso.c              | 40 +++++++++++++++++++++++---------
 5 files changed, 93 insertions(+), 38 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 491ab83ccafc9..105c1c394f82b 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -976,6 +976,8 @@ enum {
 	HCI_CONN_PER_ADV,
 	HCI_CONN_BIG_CREATED,
 	HCI_CONN_CREATE_CIS,
+	HCI_CONN_BIG_SYNC,
+	HCI_CONN_BIG_SYNC_FAILED,
 };
 
 static inline bool hci_conn_ssp_enabled(struct hci_conn *conn)
@@ -1286,6 +1288,29 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev,
 	return NULL;
 }
 
+static inline struct hci_conn *hci_conn_hash_lookup_big_any_dst(struct hci_dev *hdev,
+							__u8 handle)
+{
+	struct hci_conn_hash *h = &hdev->conn_hash;
+	struct hci_conn  *c;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(c, &h->list, list) {
+		if (c->type != ISO_LINK)
+			continue;
+
+		if (handle == c->iso_qos.bcast.big) {
+			rcu_read_unlock();
+			return c;
+		}
+	}
+
+	rcu_read_unlock();
+
+	return NULL;
+}
+
 static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev,
 							__u8 type, __u16 state)
 {
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index af7dc8131a8c4..cccc2b8b60a81 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -735,6 +735,7 @@ struct iso_list_data {
 	int count;
 	struct iso_cig_params pdu;
 	bool big_term;
+	bool big_sync_term;
 };
 
 static void bis_list(struct hci_conn *conn, void *data)
@@ -752,17 +753,6 @@ static void bis_list(struct hci_conn *conn, void *data)
 	d->count++;
 }
 
-static void find_bis(struct hci_conn *conn, void *data)
-{
-	struct iso_list_data *d = data;
-
-	/* Ignore unicast */
-	if (bacmp(&conn->dst, BDADDR_ANY))
-		return;
-
-	d->count++;
-}
-
 static int terminate_big_sync(struct hci_dev *hdev, void *data)
 {
 	struct iso_list_data *d = data;
@@ -815,31 +805,26 @@ static int big_terminate_sync(struct hci_dev *hdev, void *data)
 	bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", d->big,
 		   d->sync_handle);
 
-	/* Check if ISO connection is a BIS and terminate BIG if there are
-	 * no other connections using it.
-	 */
-	hci_conn_hash_list_state(hdev, find_bis, ISO_LINK, BT_CONNECTED, d);
-	if (d->count)
-		return 0;
-
-	hci_le_big_terminate_sync(hdev, d->big);
+	if (d->big_sync_term)
+		hci_le_big_terminate_sync(hdev, d->big);
 
 	return hci_le_pa_terminate_sync(hdev, d->sync_handle);
 }
 
-static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle)
+static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn)
 {
 	struct iso_list_data *d;
 	int ret;
 
-	bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, sync_handle);
+	bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, conn->sync_handle);
 
 	d = kzalloc(sizeof(*d), GFP_KERNEL);
 	if (!d)
 		return -ENOMEM;
 
 	d->big = big;
-	d->sync_handle = sync_handle;
+	d->sync_handle = conn->sync_handle;
+	d->big_sync_term = test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags);
 
 	ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d,
 				 terminate_big_destroy);
@@ -875,8 +860,14 @@ static void bis_cleanup(struct hci_conn *conn)
 
 		hci_le_terminate_big(hdev, conn);
 	} else {
+		bis = hci_conn_hash_lookup_big_any_dst(hdev,
+						       conn->iso_qos.bcast.big);
+
+		if (bis)
+			return;
+
 		hci_le_big_terminate(hdev, conn->iso_qos.bcast.big,
-				     conn->sync_handle);
+				     conn);
 	}
 }
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 90cfd30616f51..c29eece88d2c4 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -7039,9 +7039,6 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
 				flex_array_size(ev, bis, ev->num_bis)))
 		return;
 
-	if (ev->status)
-		return;
-
 	hci_dev_lock(hdev);
 
 	for (i = 0; i < ev->num_bis; i++) {
@@ -7065,9 +7062,25 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
 		bis->iso_qos.bcast.in.latency = le16_to_cpu(ev->interval) * 125 / 100;
 		bis->iso_qos.bcast.in.sdu = le16_to_cpu(ev->max_pdu);
 
-		hci_iso_setup_path(bis);
+		if (!ev->status) {
+			set_bit(HCI_CONN_BIG_SYNC, &bis->flags);
+			hci_iso_setup_path(bis);
+		}
 	}
 
+	/* In case BIG sync failed, notify each failed connection to
+	 * the user after all hci connections have been added
+	 */
+	if (ev->status)
+		for (i = 0; i < ev->num_bis; i++) {
+			u16 handle = le16_to_cpu(ev->bis[i]);
+
+			bis = hci_conn_hash_lookup_handle(hdev, handle);
+
+			set_bit(HCI_CONN_BIG_SYNC_FAILED, &bis->flags);
+			hci_connect_cfm(bis, ev->status);
+		}
+
 	hci_dev_unlock(hdev);
 }
 
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index c085b54d158bc..3348a1b0e3f7d 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5395,6 +5395,14 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
 		return err;
 	case BT_CONNECT2:
 		return hci_reject_conn_sync(hdev, conn, reason);
+	case BT_OPEN:
+		/* Cleanup bises that failed to be established */
+		if (test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags)) {
+			hci_dev_lock(hdev);
+			hci_conn_failed(conn, reason);
+			hci_dev_unlock(hdev);
+		}
+		break;
 	default:
 		conn->state = BT_CLOSED;
 		break;
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 9c41af55f2c73..efac284badbc5 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -48,6 +48,11 @@ static void iso_sock_kill(struct sock *sk);
 #define EIR_SERVICE_DATA_LENGTH 4
 #define BASE_MAX_LENGTH (HCI_MAX_PER_AD_LENGTH - EIR_SERVICE_DATA_LENGTH)
 
+/* iso_pinfo flags values */
+enum {
+	BT_SK_BIG_SYNC,
+};
+
 struct iso_pinfo {
 	struct bt_sock		bt;
 	bdaddr_t		src;
@@ -58,7 +63,7 @@ struct iso_pinfo {
 	__u8			bc_num_bis;
 	__u8			bc_bis[ISO_MAX_NUM_BIS];
 	__u16			sync_handle;
-	__u32			flags;
+	unsigned long		flags;
 	struct bt_iso_qos	qos;
 	bool			qos_user_set;
 	__u8			base_len;
@@ -1555,6 +1560,12 @@ static void iso_conn_ready(struct iso_conn *conn)
 		hci_conn_hold(hcon);
 		iso_chan_add(conn, sk, parent);
 
+		if (ev && ((struct hci_evt_le_big_sync_estabilished *)ev)->status) {
+			/* Trigger error signal on child socket */
+			sk->sk_err = ECONNREFUSED;
+			sk->sk_error_report(sk);
+		}
+
 		if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags))
 			sk->sk_state = BT_CONNECT2;
 		else
@@ -1623,15 +1634,17 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 			if (ev2->num_bis < iso_pi(sk)->bc_num_bis)
 				iso_pi(sk)->bc_num_bis = ev2->num_bis;
 
-			err = hci_le_big_create_sync(hdev,
-						     &iso_pi(sk)->qos,
-						     iso_pi(sk)->sync_handle,
-						     iso_pi(sk)->bc_num_bis,
-						     iso_pi(sk)->bc_bis);
-			if (err) {
-				bt_dev_err(hdev, "hci_le_big_create_sync: %d",
-					   err);
-				sk = NULL;
+			if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) {
+				err = hci_le_big_create_sync(hdev,
+							     &iso_pi(sk)->qos,
+							     iso_pi(sk)->sync_handle,
+							     iso_pi(sk)->bc_num_bis,
+							     iso_pi(sk)->bc_bis);
+				if (err) {
+					bt_dev_err(hdev, "hci_le_big_create_sync: %d",
+						   err);
+					sk = NULL;
+				}
 			}
 		}
 	} else {
@@ -1674,7 +1687,12 @@ static void iso_connect_cfm(struct hci_conn *hcon, __u8 status)
 
 	BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status);
 
-	if (!status) {
+	/* Similar to the success case, if HCI_CONN_BIG_SYNC_FAILED is set,
+	 * queue the failed bis connection into the accept queue of the
+	 * listening socket and wake up userspace, to inform the user about
+	 * the BIG sync failed event.
+	 */
+	if (!status || test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) {
 		struct iso_conn *conn;
 
 		conn = iso_conn_add(hcon);
-- 
GitLab


From 528b2acf434bf4a0fb2969e5222fbe790b95f422 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 3 Jul 2023 17:17:16 +0300
Subject: [PATCH 1101/1806] Bluetooth: msft: Fix error code in
 msft_cancel_address_filter_sync()

Return negative -EIO instead of positive EIO.

Fixes: 926df8962f3f ("Bluetooth: msft: Extended monitor tracking by address filter")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/msft.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c
index b80a2162a5c33..abbafa6194ca1 100644
--- a/net/bluetooth/msft.c
+++ b/net/bluetooth/msft.c
@@ -743,7 +743,7 @@ static int msft_cancel_address_filter_sync(struct hci_dev *hdev, void *data)
 	if (IS_ERR_OR_NULL(skb)) {
 		bt_dev_err(hdev, "MSFT: Failed to cancel address (%pMR) filter",
 			   &address_filter->bdaddr);
-		err = EIO;
+		err = -EIO;
 		goto done;
 	}
 	kfree_skb(skb);
-- 
GitLab


From b6cfa1c29afb6d527652938b0eb8db17b194bddc Mon Sep 17 00:00:00 2001
From: Chris Lu <chris.lu@mediatek.com>
Date: Fri, 30 Jun 2023 21:32:30 +0800
Subject: [PATCH 1102/1806] Bluetooth: btusb: Add a new VID/PID 0489/e0f6 for
 MT7922

Add VID/PID 0489/e0f6 for MediaTek MT7922 USB Bluetooth chip.

The information in /sys/kernel/debug/usb/devices about the Bluetooth
device is listed as the below.

T:  Bus=01 Lev=01 Prnt=01 Port=04 Cnt=03 Dev#=  4 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0489 ProdID=e0f6 Rev= 1.00
S:  Manufacturer=MediaTek Inc.
S:  Product=Wireless_Device
S:  SerialNumber=000000000
C:* #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=100mA
A:  FirstIf#= 0 IfCount= 3 Cls=e0(wlcon) Sub=01 Prot=01
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=125us
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS=  64 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS=  64 Ivl=125us
I:  If#= 2 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS= 512 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS= 512 Ivl=125us

Signed-off-by: Chris Lu <chris.lu@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 63c4b7a3319e5..5f120c3461a26 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -631,6 +631,9 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe0f5), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH |
 						     BTUSB_VALID_LE_STATES },
+	{ USB_DEVICE(0x0489, 0xe0f6), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH |
+						     BTUSB_VALID_LE_STATES },
 
 	/* Additional Realtek 8723AE Bluetooth devices */
 	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
-- 
GitLab


From 999a8a6b2e6ae73d293ff9ca69ec1715e34d6219 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Tue, 4 Jul 2023 13:46:51 +0530
Subject: [PATCH 1103/1806] Bluetooth: Add support for Gale Peak (8087:0036)

Devices from /sys/kernel/debug/usb/devices:

T:  Bus=09 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12   MxCh= 0
D:  Ver= 2.01 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=8087 ProdID=0036 Rev= 0.00
C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=1ms
E:  Ad=02(O) Atr=02(Bulk) MxPS=  64 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS=  64 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms

Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 5f120c3461a26..d51ffff827e2b 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -476,6 +476,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x8087, 0x0032), .driver_info = BTUSB_INTEL_COMBINED },
 	{ USB_DEVICE(0x8087, 0x0033), .driver_info = BTUSB_INTEL_COMBINED },
 	{ USB_DEVICE(0x8087, 0x0035), .driver_info = BTUSB_INTEL_COMBINED },
+	{ USB_DEVICE(0x8087, 0x0036), .driver_info = BTUSB_INTEL_COMBINED },
 	{ USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR },
 	{ USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL_COMBINED |
 						     BTUSB_INTEL_NO_WBS_SUPPORT |
-- 
GitLab


From 6f55eea116ba3646fb5fbb31de703f8cf79d8214 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Fri, 30 Jun 2023 15:33:15 -0700
Subject: [PATCH 1104/1806] Bluetooth: hci_sync: Don't double print name in
 add/remove adv_monitor

The hci_add_adv_monitor() hci_remove_adv_monitor() functions call
bt_dev_dbg() to print some debug statements. The bt_dev_dbg() macro
automatically adds in the device's name. That means that we shouldn't
include the name in the bt_dev_dbg() calls.

Suggested-by: Luiz Augusto von Dentz <luiz.dentz@gmail.com>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_core.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 1ec83985f1ab0..821ae737e85b2 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1949,14 +1949,14 @@ int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor)
 
 	switch (hci_get_adv_monitor_offload_ext(hdev)) {
 	case HCI_ADV_MONITOR_EXT_NONE:
-		bt_dev_dbg(hdev, "%s add monitor %d status %d", hdev->name,
+		bt_dev_dbg(hdev, "add monitor %d status %d",
 			   monitor->handle, status);
 		/* Message was not forwarded to controller - not an error */
 		break;
 
 	case HCI_ADV_MONITOR_EXT_MSFT:
 		status = msft_add_monitor_pattern(hdev, monitor);
-		bt_dev_dbg(hdev, "%s add monitor %d msft status %d", hdev->name,
+		bt_dev_dbg(hdev, "add monitor %d msft status %d",
 			   monitor->handle, status);
 		break;
 	}
@@ -1976,15 +1976,15 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev,
 
 	switch (hci_get_adv_monitor_offload_ext(hdev)) {
 	case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */
-		bt_dev_dbg(hdev, "%s remove monitor %d status %d", hdev->name,
+		bt_dev_dbg(hdev, "remove monitor %d status %d",
 			   monitor->handle, status);
 		goto free_monitor;
 
 	case HCI_ADV_MONITOR_EXT_MSFT:
 		handle = monitor->handle;
 		status = msft_remove_monitor(hdev, monitor);
-		bt_dev_dbg(hdev, "%s remove monitor %d msft status %d",
-			   hdev->name, handle, status);
+		bt_dev_dbg(hdev, "remove monitor %d msft status %d",
+			   handle, status);
 		break;
 	}
 
-- 
GitLab


From 112b5090c21905531314fee41f691f0317bbf4f6 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 6 Jul 2023 12:06:32 -0700
Subject: [PATCH 1105/1806] Bluetooth: MGMT: Fix always using HCI_MAX_AD_LENGTH

HCI_MAX_AD_LENGTH shall only be used if the controller doesn't support
extended advertising, otherwise HCI_MAX_EXT_AD_LENGTH shall be used
instead.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  4 ++++
 net/bluetooth/hci_event.c        | 12 +++++++-----
 net/bluetooth/mgmt.c             |  6 +++---
 3 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 105c1c394f82b..8200a6689b397 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1801,6 +1801,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 /* Extended advertising support */
 #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV))
 
+/* Maximum advertising length */
+#define max_adv_len(dev) \
+	(ext_adv_capable(dev) ? HCI_MAX_EXT_AD_LENGTH : HCI_MAX_AD_LENGTH)
+
 /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 1789:
  *
  * C24: Mandatory if the LE Controller supports Connection State and either
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index c29eece88d2c4..f1fcece29e7d8 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1747,7 +1747,7 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr,
 {
 	struct discovery_state *d = &hdev->discovery;
 
-	if (len > HCI_MAX_AD_LENGTH)
+	if (len > max_adv_len(hdev))
 		return;
 
 	bacpy(&d->last_adv_addr, bdaddr);
@@ -6249,8 +6249,9 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 		return;
 	}
 
-	if (!ext_adv && len > HCI_MAX_AD_LENGTH) {
-		bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes");
+	if (len > max_adv_len(hdev)) {
+		bt_dev_err_ratelimited(hdev,
+				       "adv larger than maximum supported");
 		return;
 	}
 
@@ -6315,7 +6316,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 	 */
 	conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, bdaddr_resolved,
 				     type);
-	if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) {
+	if (!ext_adv && conn && type == LE_ADV_IND &&
+	    len <= max_adv_len(hdev)) {
 		/* Store report for later inclusion by
 		 * mgmt_device_connected
 		 */
@@ -6456,7 +6458,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data,
 					info->length + 1))
 			break;
 
-		if (info->length <= HCI_MAX_AD_LENGTH) {
+		if (info->length <= max_adv_len(hdev)) {
 			rssi = info->data[info->length];
 			process_adv_report(hdev, info->type, &info->bdaddr,
 					   info->bdaddr_type, NULL, 0, rssi,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 5707ff4688423..d6c9b7bc85929 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -8428,8 +8428,8 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev,
 	supported_flags = get_supported_adv_flags(hdev);
 
 	rp->supported_flags = cpu_to_le32(supported_flags);
-	rp->max_adv_data_len = HCI_MAX_AD_LENGTH;
-	rp->max_scan_rsp_len = HCI_MAX_AD_LENGTH;
+	rp->max_adv_data_len = max_adv_len(hdev);
+	rp->max_scan_rsp_len = max_adv_len(hdev);
 	rp->max_instances = hdev->le_num_of_adv_sets;
 	rp->num_instances = hdev->adv_instance_cnt;
 
@@ -8465,7 +8465,7 @@ static u8 calculate_name_len(struct hci_dev *hdev)
 static u8 tlv_data_max_len(struct hci_dev *hdev, u32 adv_flags,
 			   bool is_adv_data)
 {
-	u8 max_len = HCI_MAX_AD_LENGTH;
+	u8 max_len = max_adv_len(hdev);
 
 	if (is_adv_data) {
 		if (adv_flags & (MGMT_ADV_FLAG_DISCOV |
-- 
GitLab


From bf809efdcc4df4132c8c261fbba7121909dc6211 Mon Sep 17 00:00:00 2001
From: Chris Lu <chris.lu@mediatek.com>
Date: Fri, 7 Jul 2023 14:29:58 +0800
Subject: [PATCH 1106/1806] Bluetooth: btusb: Add new VID/PID 0489/e102 for
 MT7922

Add VID 0489 & PID e102 for MediaTek MT7922 USB Bluetooth chip.

The information in /sys/kernel/debug/usb/devices about the Bluetooth
device is listed as the below.

T:  Bus=05 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0489 ProdID=e102 Rev= 1.00
S:  Manufacturer=MediaTek Inc.
S:  Product=Wireless_Device
S:  SerialNumber=000000000
C:* #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=100mA
A:  FirstIf#= 0 IfCount= 3 Cls=e0(wlcon) Sub=01 Prot=01
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=125us
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS=  64 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS=  64 Ivl=125us
I:  If#= 2 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS= 512 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS= 512 Ivl=125us

Signed-off-by: Chris Lu <chris.lu@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index d51ffff827e2b..1b572b11ad474 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -635,6 +635,9 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe0f6), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH |
 						     BTUSB_VALID_LE_STATES },
+	{ USB_DEVICE(0x0489, 0xe102), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH |
+						     BTUSB_VALID_LE_STATES },
 
 	/* Additional Realtek 8723AE Bluetooth devices */
 	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
-- 
GitLab


From 59be4be82bd3639cd9dbfb92df0f6263ab2c2e28 Mon Sep 17 00:00:00 2001
From: Chris Lu <chris.lu@mediatek.com>
Date: Fri, 7 Jul 2023 14:29:59 +0800
Subject: [PATCH 1107/1806] Bluetooth: btusb: Add new VID/PID 04ca/3804 for
 MT7922

Add VID 04ca & PID 3804 for MediaTek MT7922 USB Bluetooth chip.

The information in /sys/kernel/debug/usb/devices about the Bluetooth
device is listed as the below.

T:  Bus=05 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=04ca ProdID=3804 Rev= 1.00
S:  Manufacturer=MediaTek Inc.
S:  Product=Wireless_Device
S:  SerialNumber=000000000
C:* #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=100mA
A:  FirstIf#= 0 IfCount= 3 Cls=e0(wlcon) Sub=01 Prot=01
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=125us
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS=  64 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS=  64 Ivl=125us
I:  If#= 2 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS= 512 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS= 512 Ivl=125us

Signed-off-by: Chris Lu <chris.lu@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 1b572b11ad474..b93087998f54c 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -638,6 +638,9 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe102), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH |
 						     BTUSB_VALID_LE_STATES },
+	{ USB_DEVICE(0x04ca, 0x3804), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH |
+						     BTUSB_VALID_LE_STATES },
 
 	/* Additional Realtek 8723AE Bluetooth devices */
 	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
-- 
GitLab


From 82eae9dc438cd7932b5a1c79057378839f1e61e0 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 11 Jul 2023 19:41:10 +0200
Subject: [PATCH 1108/1806] Bluetooth: hci_debugfs: Use kstrtobool() instead of
 strtobool()

strtobool() is the same as kstrtobool().
However, the latter is more used within the kernel.

In order to remove strtobool() and slightly simplify kstrtox.h, switch to
the other function name.

While at it, include the corresponding header file (<linux/kstrtox.h>)

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_debugfs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index ec0df2f9188ed..6b7741f6e95b2 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -22,6 +22,7 @@
 */
 
 #include <linux/debugfs.h>
+#include <linux/kstrtox.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -1152,7 +1153,7 @@ static ssize_t force_no_mitm_write(struct file *file,
 		return -EFAULT;
 
 	buf[buf_size] = '\0';
-	if (strtobool(buf, &enable))
+	if (kstrtobool(buf, &enable))
 		return -EINVAL;
 
 	if (enable == hci_dev_test_flag(hdev, HCI_FORCE_NO_MITM))
-- 
GitLab


From 9c33663af9ad115f90c076a1828129a3fbadea98 Mon Sep 17 00:00:00 2001
From: "Lee, Chun-Yi" <joeyli.kernel@gmail.com>
Date: Mon, 10 Jul 2023 23:17:23 +0800
Subject: [PATCH 1109/1806] Bluetooth: hci_ldisc: check HCI_UART_PROTO_READY
 flag in HCIUARTGETPROTO

This patch adds code to check HCI_UART_PROTO_READY flag before
accessing hci_uart->proto. It fixes the race condition in
hci_uart_tty_ioctl() between HCIUARTSETPROTO and HCIUARTGETPROTO.
This issue bug found by Yu Hao and Weiteng Chen:

BUG: general protection fault in hci_uart_tty_ioctl [1]

The information of C reproducer can also reference the link [2]

Reported-by: Yu Hao <yhao016@ucr.edu>
Closes: https://lore.kernel.org/all/CA+UBctC3p49aTgzbVgkSZ2+TQcqq4fPDO7yZitFT5uBPDeCO2g@mail.gmail.com/ [1]
Reported-by: Weiteng Chen <wchen130@ucr.edu>
Closes: https://lore.kernel.org/lkml/CA+UBctDPEvHdkHMwD340=n02rh+jNRJNNQ5LBZNA+Wm4Keh2ow@mail.gmail.com/T/ [2]
Signed-off-by: "Lee, Chun-Yi" <jlee@suse.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_ldisc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index efdda2c3fce8c..a76eb98c0047a 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -770,7 +770,8 @@ static int hci_uart_tty_ioctl(struct tty_struct *tty, unsigned int cmd,
 		break;
 
 	case HCIUARTGETPROTO:
-		if (test_bit(HCI_UART_PROTO_SET, &hu->flags))
+		if (test_bit(HCI_UART_PROTO_SET, &hu->flags) &&
+		    test_bit(HCI_UART_PROTO_READY, &hu->flags))
 			err = hu->proto->id;
 		else
 			err = -EUNATCH;
-- 
GitLab


From 573ebae162111063eedc6c838a659ba628f66a0f Mon Sep 17 00:00:00 2001
From: Ying Hsu <yinghsu@chromium.org>
Date: Wed, 5 Jul 2023 21:06:47 +0000
Subject: [PATCH 1110/1806] Bluetooth: Fix hci_suspend_sync crash

If hci_unregister_dev() frees the hci_dev object but hci_suspend_notifier
may still be accessing it, it can cause the program to crash.
Here's the call trace:
  <4>[102152.653246] Call Trace:
  <4>[102152.653254]  hci_suspend_sync+0x109/0x301 [bluetooth]
  <4>[102152.653259]  hci_suspend_dev+0x78/0xcd [bluetooth]
  <4>[102152.653263]  hci_suspend_notifier+0x42/0x7a [bluetooth]
  <4>[102152.653268]  notifier_call_chain+0x43/0x6b
  <4>[102152.653271]  __blocking_notifier_call_chain+0x48/0x69
  <4>[102152.653273]  __pm_notifier_call_chain+0x22/0x39
  <4>[102152.653276]  pm_suspend+0x287/0x57c
  <4>[102152.653278]  state_store+0xae/0xe5
  <4>[102152.653281]  kernfs_fop_write+0x109/0x173
  <4>[102152.653284]  __vfs_write+0x16f/0x1a2
  <4>[102152.653287]  ? selinux_file_permission+0xca/0x16f
  <4>[102152.653289]  ? security_file_permission+0x36/0x109
  <4>[102152.653291]  vfs_write+0x114/0x21d
  <4>[102152.653293]  __x64_sys_write+0x7b/0xdb
  <4>[102152.653296]  do_syscall_64+0x59/0x194
  <4>[102152.653299]  entry_SYSCALL_64_after_hwframe+0x5c/0xc1

This patch holds the reference count of the hci_dev object while
processing it in hci_suspend_notifier to avoid potential crash
caused by the race condition.

Signed-off-by: Ying Hsu <yinghsu@chromium.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 821ae737e85b2..bd90caad48049 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2436,6 +2436,9 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action,
 	if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL))
 		return NOTIFY_DONE;
 
+	/* To avoid a potential race with hci_unregister_dev. */
+	hci_dev_hold(hdev);
+
 	if (action == PM_SUSPEND_PREPARE)
 		ret = hci_suspend_dev(hdev);
 	else if (action == PM_POST_SUSPEND)
@@ -2445,6 +2448,7 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action,
 		bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d",
 			   action, ret);
 
+	hci_dev_put(hdev);
 	return NOTIFY_DONE;
 }
 
-- 
GitLab


From 0cefdaed944d1617852762ff1f66364199cf5d7d Mon Sep 17 00:00:00 2001
From: Roger Gammans <rgammans@gammascience.co.uk>
Date: Wed, 12 Jul 2023 22:36:02 +0100
Subject: [PATCH 1111/1806] Bluetooth: btusb: Add support for another MediaTek
 7922 VID/PID

This one is found on the Dell Inspiron 2-in-1 7435

The information in /sys/kernel/debug/usb/devices about the Bluetooth
device is listed as the below.

T:  Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#=  2 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0489 ProdID=e0f1 Rev= 1.00
S:  Manufacturer=MediaTek Inc.
S:  Product=Wireless_Device
S:  SerialNumber=000000000
C:* #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=100mA
A:  FirstIf#= 0 IfCount= 3 Cls=e0(wlcon) Sub=01 Prot=01
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=125us
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS=  64 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS=  64 Ivl=125us
I:  If#= 2 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS= 512 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS= 512 Ivl=125us

Signed-off-by: Roger Gammans <rgammans@gammascience.co.uk>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index b93087998f54c..48dd18c9bd1ab 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -626,6 +626,9 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe0e4), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH |
 						     BTUSB_VALID_LE_STATES },
+	{ USB_DEVICE(0x0489, 0xe0f1), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH |
+						     BTUSB_VALID_LE_STATES },
 	{ USB_DEVICE(0x0489, 0xe0f2), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH |
 						     BTUSB_VALID_LE_STATES },
-- 
GitLab


From 0e72e3b12c1ee73e8cb180f0bff204a9eb51621a Mon Sep 17 00:00:00 2001
From: Chris Lu <chris.lu@mediatek.com>
Date: Thu, 13 Jul 2023 15:11:06 +0800
Subject: [PATCH 1112/1806] Bluetooth: btmtk: Fix kernel crash when processing
 coredump

There may be a potential kernel crash risk if 'skb->len
- MTK_COREDUMP_END_LEN' value is less than 0 when doing
memcmp in btmtk_process_coredump().
Check the value is valid before doing memcmp.

[215.021695] Unable to handle kernel paging request at
             virtual address ffffff939fffd3c5
[215.021781] Mem abort info:
[215.021805]   ESR = 0x96000005
[215.021833]   EC = 0x25: DABT (current EL), IL = 32 bits
[215.021861]   SET = 0, FnV = 0
[215.021875]   EA = 0, S1PTW = 0
[215.021886] Data abort info:
[215.021899]   ISV = 0, ISS = 0x00000005
[215.021912]   CM = 0, WnR = 0
[215.021929] swapper pgtable: 4k pages, 39-bit VAs,
             pgdp=00000000410de000
[215.021943] [ffffff939fffd3c5] pgd=0000000000000000,
             p4d=0000000000000000, pud=0000000000000000
[215.021979] Internal error: Oops: 96000005 [#1] PREEMPT SMP
[215.022496] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.10.186#3
             (HASH:ad23 4)
[215.022511] Hardware name: MediaTek Tomato board (DT)
[215.022530] pstate: 80400009 (Nzcv daif +PAN -UAO -TCO BTYPE=--)
[215.022556] pc : __pi_memcmp+0xd0/0x1b8
[215.022579] lr : btmtk_process_coredump+0xb0/0x5f8 [btmtk]
[215.022593] sp : ffffffc010003d40
[215.022607] x29: ffffffc010003d40 x28: 0000000000000006
[215.022633] x27: ffffffda696350c0 x26: 0000000000000002
[215.022659] x25: 00000000000003ff x24: ffffff9360cca804
[215.022685] x23: 0000000000000000 x22: ffffff9365638500
[215.022710] x21: ffffff9365638700 x20: 0000000000000000
[215.022736] x19: ffffff936002e000 x18: 0000000000000000
[215.022761] x17: 0000000000000180 x16: ffffffda6881b8b4
[215.022787] x15: 0000000000000001 x14: 0000000000002d00
[215.022812] x13: 0000000000060000 x12: 0000000000000181
[215.022837] x11: 0000000000000006 x10: fffffffffffffffd
[215.022862] x9 : 0000000000000006 x8 : 0000000000000003
[215.022887] x7 : 0000000000000000 x6 : 0000000000000000
[215.022913] x5 : ffffff93656387b8 x4 : 0000000000000000
[215.022938] x3 : ffffffc010003c18 x2 : 0000000000000006
[215.022963] x1 : ffffffda09d4124a x0 : ffffff939fffd3c5
[215.022989] Call trace:
[215.023012]  __pi_memcmp+0xd0/0x1b8
[215.023053]  btusb_recv_acl_mtk+0x64/0x90 [btusb (HASH:dc6b 5)]
[215.023087]  btusb_recv_bulk+0x118/0x170 [btusb (HASH:dc6b 5)]
[215.023121]  btusb_bulk_complete+0x8c/0x148 [btusb (HASH:dc6b 5)]
[215.023144]  __usb_hcd_giveback_urb+0xbc/0x148
[215.023164]  usb_giveback_urb_bh+0xb4/0x190
[215.023184]  tasklet_action_common+0x98/0x1a0
[215.023201]  tasklet_action+0x2c/0x38
[215.023220]  __do_softirq+0xe0/0x38c
[215.023241]  invoke_softirq+0x34/0x6c
[215.023258]  irq_exit+0x6c/0xb0
[215.023279]  __handle_domain_irq+0x98/0xd4
[215.023296]  gic_handle_irq+0x5c/0x11c
[215.023313]  el1_irq+0xd0/0x180
[215.023332]  cpuidle_enter_state+0xac/0x338
[215.023349]  cpuidle_enter+0x40/0x70
[215.023366]  do_idle+0x150/0x278
[215.023384]  cpu_startup_entry+0x2c/0x58
[215.023401]  rest_init+0xdc/0xec
[215.023419]  arch_call_rest_init+0x18/0x24
[215.023435]  start_kernel+0x334/0x400
[215.023460] Code: 91002129 eb09010a 9a89810b cb0b0042 (38401403)
[215.023478] ---[ end trace 28668fd20c7a90cd ]

Fixes: 2822cd0173ad ("Bluetooth: btusb: mediatek: add MediaTek devcoredump support")
Signed-off-by: Chris Lu <chris.lu@mediatek.com>
Co-developed-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btmtk.c | 12 ++++++------
 drivers/bluetooth/btmtk.h |  1 +
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index 786f775196ae5..aaabb732082cd 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -395,12 +395,12 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb)
 
 		/* Mediatek coredump data would be more than MTK_COREDUMP_NUM */
 		if (data->cd_info.cnt > MTK_COREDUMP_NUM &&
-		    skb->len > sizeof(MTK_COREDUMP_END) &&
-		    !memcmp((char *)&skb->data[skb->len - sizeof(MTK_COREDUMP_END)],
-			    MTK_COREDUMP_END, sizeof(MTK_COREDUMP_END) - 1)) {
-			bt_dev_info(hdev, "Mediatek coredump end");
-			hci_devcd_complete(hdev);
-		}
+		    skb->len > MTK_COREDUMP_END_LEN)
+			if (!memcmp((char *)&skb->data[skb->len - MTK_COREDUMP_END_LEN],
+				    MTK_COREDUMP_END, MTK_COREDUMP_END_LEN - 1)) {
+				bt_dev_info(hdev, "Mediatek coredump end");
+				hci_devcd_complete(hdev);
+			}
 
 		break;
 	}
diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h
index 68309dfe076af..56f5502baadf9 100644
--- a/drivers/bluetooth/btmtk.h
+++ b/drivers/bluetooth/btmtk.h
@@ -24,6 +24,7 @@
 
 #define MTK_COREDUMP_SIZE		(1024 * 1000)
 #define MTK_COREDUMP_END		"coredump end"
+#define MTK_COREDUMP_END_LEN		(sizeof(MTK_COREDUMP_END))
 #define MTK_COREDUMP_NUM		255
 
 enum {
-- 
GitLab


From 3f19ffb2f924db5b0925c77818d18ac1f6f08a44 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 13 Jul 2023 13:41:31 -0700
Subject: [PATCH 1113/1806] Bluetooth: af_bluetooth: Make BT_PKT_STATUS generic

This makes the handling of BT_PKT_STATUS more generic so it can be
reused by sockets other than SCO like BT_DEFER_SETUP, etc.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/bluetooth.h |  8 +++-----
 include/net/bluetooth/sco.h       |  2 --
 net/bluetooth/af_bluetooth.c      |  8 ++++++--
 net/bluetooth/hci_core.c          |  2 +-
 net/bluetooth/sco.c               | 22 ++++------------------
 5 files changed, 14 insertions(+), 28 deletions(-)

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 34998ae8ed78d..aa90adc3b2a4d 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -386,6 +386,7 @@ struct bt_sock {
 enum {
 	BT_SK_DEFER_SETUP,
 	BT_SK_SUSPEND,
+	BT_SK_PKT_STATUS
 };
 
 struct bt_sock_list {
@@ -432,10 +433,6 @@ struct l2cap_ctrl {
 	struct l2cap_chan *chan;
 };
 
-struct sco_ctrl {
-	u8	pkt_status;
-};
-
 struct hci_dev;
 
 typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode);
@@ -466,9 +463,9 @@ struct bt_skb_cb {
 	u8 force_active;
 	u16 expect;
 	u8 incoming:1;
+	u8 pkt_status:2;
 	union {
 		struct l2cap_ctrl l2cap;
-		struct sco_ctrl sco;
 		struct hci_ctrl hci;
 		struct mgmt_ctrl mgmt;
 		struct scm_creds creds;
@@ -477,6 +474,7 @@ struct bt_skb_cb {
 #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb))
 
 #define hci_skb_pkt_type(skb) bt_cb((skb))->pkt_type
+#define hci_skb_pkt_status(skb) bt_cb((skb))->pkt_status
 #define hci_skb_expect(skb) bt_cb((skb))->expect
 #define hci_skb_opcode(skb) bt_cb((skb))->hci.opcode
 #define hci_skb_event(skb) bt_cb((skb))->hci.req_event
diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h
index 1aa2e14b6c94e..f40ddb4264fc3 100644
--- a/include/net/bluetooth/sco.h
+++ b/include/net/bluetooth/sco.h
@@ -46,6 +46,4 @@ struct sco_conninfo {
 	__u8  dev_class[3];
 };
 
-#define SCO_CMSG_PKT_STATUS	0x01
-
 #endif /* __SCO_H */
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 647afb1871476..336a761654546 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -333,8 +333,12 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			bt_sk(sk)->skb_msg_name(skb, msg->msg_name,
 						&msg->msg_namelen);
 
-		if (bt_sk(sk)->skb_put_cmsg)
-			bt_sk(sk)->skb_put_cmsg(skb, msg, sk);
+		if (test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags)) {
+			u8 pkt_status = hci_skb_pkt_status(skb);
+
+			put_cmsg(msg, SOL_BLUETOOTH, BT_SCM_PKT_STATUS,
+				 sizeof(pkt_status), &pkt_status);
+		}
 	}
 
 	skb_free_datagram(sk, skb);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index bd90caad48049..0fefa6788911b 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3895,7 +3895,7 @@ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb)
 
 	if (conn) {
 		/* Send to upper protocol */
-		bt_cb(skb)->sco.pkt_status = flags & 0x03;
+		hci_skb_pkt_status(skb) = flags & 0x03;
 		sco_recv_scodata(conn, skb);
 		return;
 	} else {
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index ec6dce488a400..50ad5935ae47a 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -68,7 +68,6 @@ struct sco_pinfo {
 	bdaddr_t	dst;
 	__u32		flags;
 	__u16		setting;
-	__u8		cmsg_mask;
 	struct bt_codec codec;
 	struct sco_conn	*conn;
 };
@@ -471,15 +470,6 @@ static void sco_sock_close(struct sock *sk)
 	release_sock(sk);
 }
 
-static void sco_skb_put_cmsg(struct sk_buff *skb, struct msghdr *msg,
-			     struct sock *sk)
-{
-	if (sco_pi(sk)->cmsg_mask & SCO_CMSG_PKT_STATUS)
-		put_cmsg(msg, SOL_BLUETOOTH, BT_SCM_PKT_STATUS,
-			 sizeof(bt_cb(skb)->sco.pkt_status),
-			 &bt_cb(skb)->sco.pkt_status);
-}
-
 static void sco_sock_init(struct sock *sk, struct sock *parent)
 {
 	BT_DBG("sk %p", sk);
@@ -488,8 +478,6 @@ static void sco_sock_init(struct sock *sk, struct sock *parent)
 		sk->sk_type = parent->sk_type;
 		bt_sk(sk)->flags = bt_sk(parent)->flags;
 		security_sk_clone(parent, sk);
-	} else {
-		bt_sk(sk)->skb_put_cmsg = sco_skb_put_cmsg;
 	}
 }
 
@@ -907,9 +895,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
 		}
 
 		if (opt)
-			sco_pi(sk)->cmsg_mask |= SCO_CMSG_PKT_STATUS;
+			set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags);
 		else
-			sco_pi(sk)->cmsg_mask &= SCO_CMSG_PKT_STATUS;
+			clear_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags);
 		break;
 
 	case BT_CODEC:
@@ -1040,7 +1028,6 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname,
 	int len, err = 0;
 	struct bt_voice voice;
 	u32 phys;
-	int pkt_status;
 	int buf_len;
 	struct codec_list *c;
 	u8 num_codecs, i, __user *ptr;
@@ -1094,9 +1081,8 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case BT_PKT_STATUS:
-		pkt_status = (sco_pi(sk)->cmsg_mask & SCO_CMSG_PKT_STATUS);
-
-		if (put_user(pkt_status, (int __user *)optval))
+		if (put_user(test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags),
+			     (int __user *)optval))
 			err = -EFAULT;
 		break;
 
-- 
GitLab


From 0731c5ab4d510501a6a2da491ac68aea858bf834 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 13 Jul 2023 14:02:37 -0700
Subject: [PATCH 1114/1806] Bluetooth: ISO: Add support for BT_PKT_STATUS

This adds support for BT_PKT_STATUS socketopt by setting
BT_SK_PKT_STATUS. Then upon receiving an ISO packet the code would
attempt to store the Packet_Status_Flag to hci_skb_pkt_status which
is then forward to userspace in the form of BT_SCM_PKT_STATUS whenever
BT_PKT_STATUS has been enabled/set.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/iso.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index efac284badbc5..cbe3299b4a415 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1288,6 +1288,18 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname,
 			clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
 		break;
 
+	case BT_PKT_STATUS:
+		if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
+			err = -EFAULT;
+			break;
+		}
+
+		if (opt)
+			set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags);
+		else
+			clear_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags);
+		break;
+
 	case BT_ISO_QOS:
 		if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND &&
 		    sk->sk_state != BT_CONNECT2) {
@@ -1373,6 +1385,12 @@ static int iso_sock_getsockopt(struct socket *sock, int level, int optname,
 
 		break;
 
+	case BT_PKT_STATUS:
+		if (put_user(test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags),
+			     (int __user *)optval))
+			err = -EFAULT;
+		break;
+
 	case BT_ISO_QOS:
 		qos = iso_sock_get_qos(sk);
 
@@ -1767,6 +1785,7 @@ void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
 
 		if (len == skb->len) {
 			/* Complete frame received */
+			hci_skb_pkt_status(skb) = flags & 0x03;
 			iso_recv_frame(conn, skb);
 			return;
 		}
@@ -1788,6 +1807,7 @@ void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
 		if (!conn->rx_skb)
 			goto drop;
 
+		hci_skb_pkt_status(conn->rx_skb) = flags & 0x03;
 		skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len),
 					  skb->len);
 		conn->rx_len = len - skb->len;
-- 
GitLab


From 47e90f6b04a4c16faefd3d4a44989b00cf5674c2 Mon Sep 17 00:00:00 2001
From: Mans Rullgard <mans@mansr.com>
Date: Sat, 15 Jul 2023 17:41:59 +0100
Subject: [PATCH 1115/1806] Bluetooth: btbcm: add default address for
 BCM43430A1

The BCM43430A1 has a default MAC address of AA:AA:AA:AA:AA:AA.
Although, unlike some other entries, this does not include the
chip name, it is clearly not a real address. This was found in
AzureWave AW-NB197SM and AW-NM372SM modules.

Signed-off-by: Mans Rullgard <mans@mansr.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btbcm.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index de2ea589aa49b..0a5445ac5e1b7 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -24,6 +24,7 @@
 #define BDADDR_BCM20702A1 (&(bdaddr_t) {{0x00, 0x00, 0xa0, 0x02, 0x70, 0x20}})
 #define BDADDR_BCM2076B1 (&(bdaddr_t) {{0x79, 0x56, 0x00, 0xa0, 0x76, 0x20}})
 #define BDADDR_BCM43430A0 (&(bdaddr_t) {{0xac, 0x1f, 0x12, 0xa0, 0x43, 0x43}})
+#define BDADDR_BCM43430A1 (&(bdaddr_t) {{0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa}})
 #define BDADDR_BCM4324B3 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb3, 0x24, 0x43}})
 #define BDADDR_BCM4330B1 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb1, 0x30, 0x43}})
 #define BDADDR_BCM4334B0 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb0, 0x34, 0x43}})
@@ -115,6 +116,9 @@ int btbcm_check_bdaddr(struct hci_dev *hdev)
 	 *
 	 * The address 43:43:A0:12:1F:AC indicates a BCM43430A0 controller
 	 * with no configured address.
+	 *
+	 * The address AA:AA:AA:AA:AA:AA indicates a BCM43430A1 controller
+	 * with no configured address.
 	 */
 	if (!bacmp(&bda->bdaddr, BDADDR_BCM20702A0) ||
 	    !bacmp(&bda->bdaddr, BDADDR_BCM20702A1) ||
@@ -124,6 +128,7 @@ int btbcm_check_bdaddr(struct hci_dev *hdev)
 	    !bacmp(&bda->bdaddr, BDADDR_BCM4334B0) ||
 	    !bacmp(&bda->bdaddr, BDADDR_BCM4345C5) ||
 	    !bacmp(&bda->bdaddr, BDADDR_BCM43430A0) ||
+	    !bacmp(&bda->bdaddr, BDADDR_BCM43430A1) ||
 	    !bacmp(&bda->bdaddr, BDADDR_BCM43341B)) {
 		/* Try falling back to BDADDR EFI variable */
 		if (btbcm_set_bdaddr_from_efi(hdev) != 0) {
-- 
GitLab


From e15f44fb9cb26168a1171a3e8f7f44d11a2727b8 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 14 Jul 2023 11:40:57 -0600
Subject: [PATCH 1116/1806] bluetooth: Explicitly include correct DT includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btmtkuart.c | 1 -
 drivers/bluetooth/hci_h5.c    | 2 +-
 drivers/bluetooth/hci_qca.c   | 2 +-
 3 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c
index 7680c67cdb35c..935feab815d97 100644
--- a/drivers/bluetooth/btmtkuart.c
+++ b/drivers/bluetooth/btmtkuart.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index fefc37b98b4ac..71e748a9477e4 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -11,7 +11,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/kernel.h>
 #include <linux/mod_devicetable.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/pm_runtime.h>
 #include <linux/serdev.h>
 #include <linux/skbuff.h>
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 87a7325c75b16..9b785c947d96a 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -25,7 +25,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/acpi.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
-- 
GitLab


From e8b5aed31355072faac8092ead4938ddec3111fd Mon Sep 17 00:00:00 2001
From: Yuanjun Gong <ruc_gongyuanjun@163.com>
Date: Wed, 26 Jul 2023 21:30:00 +0800
Subject: [PATCH 1117/1806] Bluetooth: nokia: fix value check in
 nokia_bluetooth_serdev_probe()

in nokia_bluetooth_serdev_probe(), check the return value of
clk_prepare_enable() and return the error code if
clk_prepare_enable() returns an unexpected value.

Fixes: 7bb318680e86 ("Bluetooth: add nokia driver")
Signed-off-by: Yuanjun Gong <ruc_gongyuanjun@163.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_nokia.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/hci_nokia.c b/drivers/bluetooth/hci_nokia.c
index 05f7f6de6863d..97da0b2bfd17e 100644
--- a/drivers/bluetooth/hci_nokia.c
+++ b/drivers/bluetooth/hci_nokia.c
@@ -734,7 +734,11 @@ static int nokia_bluetooth_serdev_probe(struct serdev_device *serdev)
 		return err;
 	}
 
-	clk_prepare_enable(sysclk);
+	err = clk_prepare_enable(sysclk);
+	if (err) {
+		dev_err(dev, "could not enable sysclk: %d", err);
+		return err;
+	}
 	btdev->sysclk_speed = clk_get_rate(sysclk);
 	clk_disable_unprepare(sysclk);
 
-- 
GitLab


From c55c8a7cfafe41c71b87b3f7baf16249ce4fbd3d Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Thu, 27 Jul 2023 19:03:17 +0530
Subject: [PATCH 1118/1806] Bluetooth: btnxpuart: Add support for AW693 chipset

This adds support for NXP AW693 chipset in btnxpuart driver
by adding FW name and bootloader signature. Based on the
loader version bits 7:6 of the bootloader signature, the
driver can choose between selecting secure and non-secure
FW files.

Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 39 ++++++++++++++++++++++++++++-------
 1 file changed, 31 insertions(+), 8 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 52ef44688d38a..ee6f6c872a34e 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -29,16 +29,25 @@
 #define BTNXPUART_CHECK_BOOT_SIGNATURE	3
 #define BTNXPUART_SERDEV_OPEN		4
 
-#define FIRMWARE_W8987	"nxp/uartuart8987_bt.bin"
-#define FIRMWARE_W8997	"nxp/uartuart8997_bt_v4.bin"
-#define FIRMWARE_W9098	"nxp/uartuart9098_bt_v1.bin"
-#define FIRMWARE_IW416	"nxp/uartiw416_bt_v0.bin"
-#define FIRMWARE_IW612	"nxp/uartspi_n61x_v1.bin.se"
-#define FIRMWARE_HELPER	"nxp/helper_uart_3000000.bin"
+#define FIRMWARE_W8987		"nxp/uartuart8987_bt.bin"
+#define FIRMWARE_W8997		"nxp/uartuart8997_bt_v4.bin"
+#define FIRMWARE_W9098		"nxp/uartuart9098_bt_v1.bin"
+#define FIRMWARE_IW416		"nxp/uartiw416_bt_v0.bin"
+#define FIRMWARE_IW612		"nxp/uartspi_n61x_v1.bin.se"
+#define FIRMWARE_AW693		"nxp/uartaw693_bt.bin"
+#define FIRMWARE_SECURE_AW693	"nxp/uartaw693_bt.bin.se"
+#define FIRMWARE_HELPER		"nxp/helper_uart_3000000.bin"
 
 #define CHIP_ID_W9098		0x5c03
 #define CHIP_ID_IW416		0x7201
 #define CHIP_ID_IW612		0x7601
+#define CHIP_ID_AW693		0x8200
+
+#define FW_SECURE_MASK		0xc0
+#define FW_OPEN			0x00
+#define FW_AUTH_ILLEGAL		0x40
+#define FW_AUTH_PLAIN		0x80
+#define FW_AUTH_ENC		0xc0
 
 #define HCI_NXP_PRI_BAUDRATE	115200
 #define HCI_NXP_SEC_BAUDRATE	3000000
@@ -665,6 +674,9 @@ static int nxp_request_firmware(struct hci_dev *hdev, const char *fw_name)
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
 	int err = 0;
 
+	if (!fw_name)
+		return -ENOENT;
+
 	if (!strlen(nxpdev->fw_name)) {
 		snprintf(nxpdev->fw_name, MAX_FW_FILE_NAME_LEN, "%s", fw_name);
 
@@ -812,7 +824,8 @@ free_skb:
 	return 0;
 }
 
-static char *nxp_get_fw_name_from_chipid(struct hci_dev *hdev, u16 chipid)
+static char *nxp_get_fw_name_from_chipid(struct hci_dev *hdev, u16 chipid,
+					 u8 loader_ver)
 {
 	char *fw_name = NULL;
 
@@ -826,6 +839,14 @@ static char *nxp_get_fw_name_from_chipid(struct hci_dev *hdev, u16 chipid)
 	case CHIP_ID_IW612:
 		fw_name = FIRMWARE_IW612;
 		break;
+	case CHIP_ID_AW693:
+		if ((loader_ver & FW_SECURE_MASK) == FW_OPEN)
+			fw_name = FIRMWARE_AW693;
+		else if ((loader_ver & FW_SECURE_MASK) != FW_AUTH_ILLEGAL)
+			fw_name = FIRMWARE_SECURE_AW693;
+		else
+			bt_dev_err(hdev, "Illegal loader version %02x", loader_ver);
+		break;
 	default:
 		bt_dev_err(hdev, "Unknown chip signature %04x", chipid);
 		break;
@@ -838,13 +859,15 @@ static int nxp_recv_chip_ver_v3(struct hci_dev *hdev, struct sk_buff *skb)
 	struct v3_start_ind *req = skb_pull_data(skb, sizeof(*req));
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
 	u16 chip_id;
+	u8 loader_ver;
 
 	if (!process_boot_signature(nxpdev))
 		goto free_skb;
 
 	chip_id = le16_to_cpu(req->chip_id);
+	loader_ver = req->loader_ver;
 	if (!nxp_request_firmware(hdev, nxp_get_fw_name_from_chipid(hdev,
-								    chip_id)))
+								    chip_id, loader_ver)))
 		nxp_send_ack(NXP_ACK_V3, hdev);
 
 free_skb:
-- 
GitLab


From 606a8bff3cbdb4ae7b6374e77da58028880c9531 Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Wed, 2 Aug 2023 08:56:28 +0200
Subject: [PATCH 1119/1806] dt-bindings: net: qualcomm: Add WCN3988

Add the compatible for the Bluetooth part of the Qualcomm WCN3988
chipset.

Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 .../devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml   | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
index 56cbb42b5aeaa..2735c6a4f336d 100644
--- a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
+++ b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
@@ -19,6 +19,7 @@ properties:
       - qcom,qca2066-bt
       - qcom,qca6174-bt
       - qcom,qca9377-bt
+      - qcom,wcn3988-bt
       - qcom,wcn3990-bt
       - qcom,wcn3991-bt
       - qcom,wcn3998-bt
@@ -111,6 +112,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,wcn3988-bt
               - qcom,wcn3990-bt
               - qcom,wcn3991-bt
               - qcom,wcn3998-bt
-- 
GitLab


From f904feefe60c28b6852d5625adc4a2c39426a2d9 Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Wed, 2 Aug 2023 08:56:29 +0200
Subject: [PATCH 1120/1806] Bluetooth: btqca: Add WCN3988 support

Add support for the Bluetooth chip codenamed APACHE which is part of
WCN3988.

The firmware for this chip has a slightly different naming scheme
compared to most others. For ROM Version 0x0200 we need to use
apbtfw10.tlv + apnv10.bin and for ROM version 0x201 apbtfw11.tlv +
apnv11.bin

Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btqca.c   | 13 +++++++++++--
 drivers/bluetooth/btqca.h   | 12 ++++++++++--
 drivers/bluetooth/hci_qca.c | 12 ++++++++++++
 3 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index e7e58a956d154..6f2187fab55f5 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -594,14 +594,20 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	/* Firmware files to download are based on ROM version.
 	 * ROM version is derived from last two bytes of soc_ver.
 	 */
-	rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f);
+	if (soc_type == QCA_WCN3988)
+		rom_ver = ((soc_ver & 0x00000f00) >> 0x05) | (soc_ver & 0x0000000f);
+	else
+		rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f);
 
 	if (soc_type == QCA_WCN6750)
 		qca_send_patch_config_cmd(hdev);
 
 	/* Download rampatch file */
 	config.type = TLV_TYPE_PATCH;
-	if (qca_is_wcn399x(soc_type)) {
+	if (soc_type == QCA_WCN3988) {
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/apbtfw%02x.tlv", rom_ver);
+	} else if (qca_is_wcn399x(soc_type)) {
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/crbtfw%02x.tlv", rom_ver);
 	} else if (soc_type == QCA_QCA6390) {
@@ -636,6 +642,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	if (firmware_name)
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/%s", firmware_name);
+	else if (soc_type == QCA_WCN3988)
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/apnv%02x.bin", rom_ver);
 	else if (qca_is_wcn399x(soc_type)) {
 		if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) {
 			snprintf(config.fwname, sizeof(config.fwname),
diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h
index b884095bcd9d0..fc6cf314eb0ef 100644
--- a/drivers/bluetooth/btqca.h
+++ b/drivers/bluetooth/btqca.h
@@ -142,6 +142,7 @@ enum qca_btsoc_type {
 	QCA_INVALID = -1,
 	QCA_AR3002,
 	QCA_ROME,
+	QCA_WCN3988,
 	QCA_WCN3990,
 	QCA_WCN3998,
 	QCA_WCN3991,
@@ -162,8 +163,15 @@ int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr);
 int qca_send_pre_shutdown_cmd(struct hci_dev *hdev);
 static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type)
 {
-	return soc_type == QCA_WCN3990 || soc_type == QCA_WCN3991 ||
-	       soc_type == QCA_WCN3998;
+	switch (soc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
+		return true;
+	default:
+		return false;
+	}
 }
 static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type)
 {
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 9b785c947d96a..0118225196021 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -1874,6 +1874,17 @@ static const struct hci_uart_proto qca_proto = {
 	.dequeue	= qca_dequeue,
 };
 
+static const struct qca_device_data qca_soc_data_wcn3988 __maybe_unused = {
+	.soc_type = QCA_WCN3988,
+	.vregs = (struct qca_vreg []) {
+		{ "vddio", 15000  },
+		{ "vddxo", 80000  },
+		{ "vddrf", 300000 },
+		{ "vddch0", 450000 },
+	},
+	.num_vregs = 4,
+};
+
 static const struct qca_device_data qca_soc_data_wcn3990 __maybe_unused = {
 	.soc_type = QCA_WCN3990,
 	.vregs = (struct qca_vreg []) {
@@ -2398,6 +2409,7 @@ static const struct of_device_id qca_bluetooth_of_match[] = {
 	{ .compatible = "qcom,qca6174-bt" },
 	{ .compatible = "qcom,qca6390-bt", .data = &qca_soc_data_qca6390},
 	{ .compatible = "qcom,qca9377-bt" },
+	{ .compatible = "qcom,wcn3988-bt", .data = &qca_soc_data_wcn3988},
 	{ .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data_wcn3990},
 	{ .compatible = "qcom,wcn3991-bt", .data = &qca_soc_data_wcn3991},
 	{ .compatible = "qcom,wcn3998-bt", .data = &qca_soc_data_wcn3998},
-- 
GitLab


From 123c26311859b1b1848b1cfe80feac228fd5afb5 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 20 Jul 2023 15:16:32 -0700
Subject: [PATCH 1121/1806] Bluetooth: btusb: Move btusb_recv_event_intel to
 btintel

btusb_recv_event_intel is specific to Intel controllers therefore it
shall be placed inside btintel.c so btusb don't have a mix of vendor
specific code with the generic parts.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.c | 74 ++++++++++++++++++++++++++++++++++++
 drivers/bluetooth/btintel.h |  1 +
 drivers/bluetooth/btusb.c   | 75 +------------------------------------
 3 files changed, 76 insertions(+), 74 deletions(-)

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index b32277cb045d6..633e8d9bf58f9 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -2948,6 +2948,80 @@ int btintel_configure_setup(struct hci_dev *hdev, const char *driver_name)
 }
 EXPORT_SYMBOL_GPL(btintel_configure_setup);
 
+static int btintel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct intel_tlv *tlv = (void *)&skb->data[5];
+
+	/* The first event is always an event type TLV */
+	if (tlv->type != INTEL_TLV_TYPE_ID)
+		goto recv_frame;
+
+	switch (tlv->val[0]) {
+	case INTEL_TLV_SYSTEM_EXCEPTION:
+	case INTEL_TLV_FATAL_EXCEPTION:
+	case INTEL_TLV_DEBUG_EXCEPTION:
+	case INTEL_TLV_TEST_EXCEPTION:
+		/* Generate devcoredump from exception */
+		if (!hci_devcd_init(hdev, skb->len)) {
+			hci_devcd_append(hdev, skb);
+			hci_devcd_complete(hdev);
+		} else {
+			bt_dev_err(hdev, "Failed to generate devcoredump");
+			kfree_skb(skb);
+		}
+		return 0;
+	default:
+		bt_dev_err(hdev, "Invalid exception type %02X", tlv->val[0]);
+	}
+
+recv_frame:
+	return hci_recv_frame(hdev, skb);
+}
+
+int btintel_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_event_hdr *hdr = (void *)skb->data;
+	const char diagnostics_hdr[] = { 0x87, 0x80, 0x03 };
+
+	if (skb->len > HCI_EVENT_HDR_SIZE && hdr->evt == 0xff &&
+	    hdr->plen > 0) {
+		const void *ptr = skb->data + HCI_EVENT_HDR_SIZE + 1;
+		unsigned int len = skb->len - HCI_EVENT_HDR_SIZE - 1;
+
+		if (btintel_test_flag(hdev, INTEL_BOOTLOADER)) {
+			switch (skb->data[2]) {
+			case 0x02:
+				/* When switching to the operational firmware
+				 * the device sends a vendor specific event
+				 * indicating that the bootup completed.
+				 */
+				btintel_bootup(hdev, ptr, len);
+				break;
+			case 0x06:
+				/* When the firmware loading completes the
+				 * device sends out a vendor specific event
+				 * indicating the result of the firmware
+				 * loading.
+				 */
+				btintel_secure_send_result(hdev, ptr, len);
+				break;
+			}
+		}
+
+		/* Handle all diagnostics events separately. May still call
+		 * hci_recv_frame.
+		 */
+		if (len >= sizeof(diagnostics_hdr) &&
+		    memcmp(&skb->data[2], diagnostics_hdr,
+			   sizeof(diagnostics_hdr)) == 0) {
+			return btintel_diagnostics(hdev, skb);
+		}
+	}
+
+	return hci_recv_frame(hdev, skb);
+}
+EXPORT_SYMBOL_GPL(btintel_recv_event);
+
 void btintel_bootup(struct hci_dev *hdev, const void *ptr, unsigned int len)
 {
 	const struct intel_bootup *evt = ptr;
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 7fd29ef038bd6..2ed646609deec 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -222,6 +222,7 @@ int btintel_read_boot_params(struct hci_dev *hdev,
 int btintel_download_firmware(struct hci_dev *dev, struct intel_version *ver,
 			      const struct firmware *fw, u32 *boot_param);
 int btintel_configure_setup(struct hci_dev *hdev, const char *driver_name);
+int btintel_recv_event(struct hci_dev *hdev, struct sk_buff *skb);
 void btintel_bootup(struct hci_dev *hdev, const void *ptr, unsigned int len);
 void btintel_secure_send_result(struct hci_dev *hdev,
 				const void *ptr, unsigned int len);
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 48dd18c9bd1ab..1bb3b09013b07 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2492,79 +2492,6 @@ static int btusb_recv_bulk_intel(struct btusb_data *data, void *buffer,
 	return btusb_recv_bulk(data, buffer, count);
 }
 
-static int btusb_intel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb)
-{
-	struct intel_tlv *tlv = (void *)&skb->data[5];
-
-	/* The first event is always an event type TLV */
-	if (tlv->type != INTEL_TLV_TYPE_ID)
-		goto recv_frame;
-
-	switch (tlv->val[0]) {
-	case INTEL_TLV_SYSTEM_EXCEPTION:
-	case INTEL_TLV_FATAL_EXCEPTION:
-	case INTEL_TLV_DEBUG_EXCEPTION:
-	case INTEL_TLV_TEST_EXCEPTION:
-		/* Generate devcoredump from exception */
-		if (!hci_devcd_init(hdev, skb->len)) {
-			hci_devcd_append(hdev, skb);
-			hci_devcd_complete(hdev);
-		} else {
-			bt_dev_err(hdev, "Failed to generate devcoredump");
-			kfree_skb(skb);
-		}
-		return 0;
-	default:
-		bt_dev_err(hdev, "Invalid exception type %02X", tlv->val[0]);
-	}
-
-recv_frame:
-	return hci_recv_frame(hdev, skb);
-}
-
-static int btusb_recv_event_intel(struct hci_dev *hdev, struct sk_buff *skb)
-{
-	struct hci_event_hdr *hdr = (void *)skb->data;
-	const char diagnostics_hdr[] = { 0x87, 0x80, 0x03 };
-
-	if (skb->len > HCI_EVENT_HDR_SIZE && hdr->evt == 0xff &&
-	    hdr->plen > 0) {
-		const void *ptr = skb->data + HCI_EVENT_HDR_SIZE + 1;
-		unsigned int len = skb->len - HCI_EVENT_HDR_SIZE - 1;
-
-		if (btintel_test_flag(hdev, INTEL_BOOTLOADER)) {
-			switch (skb->data[2]) {
-			case 0x02:
-				/* When switching to the operational firmware
-				 * the device sends a vendor specific event
-				 * indicating that the bootup completed.
-				 */
-				btintel_bootup(hdev, ptr, len);
-				break;
-			case 0x06:
-				/* When the firmware loading completes the
-				 * device sends out a vendor specific event
-				 * indicating the result of the firmware
-				 * loading.
-				 */
-				btintel_secure_send_result(hdev, ptr, len);
-				break;
-			}
-		}
-
-		/* Handle all diagnostics events separately. May still call
-		 * hci_recv_frame.
-		 */
-		if (len >= sizeof(diagnostics_hdr) &&
-		    memcmp(&skb->data[2], diagnostics_hdr,
-			   sizeof(diagnostics_hdr)) == 0) {
-			return btusb_intel_diagnostics(hdev, skb);
-		}
-	}
-
-	return hci_recv_frame(hdev, skb);
-}
-
 static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct urb *urb;
@@ -4350,7 +4277,7 @@ static int btusb_probe(struct usb_interface *intf,
 		priv_size += sizeof(struct btintel_data);
 
 		/* Override the rx handlers */
-		data->recv_event = btusb_recv_event_intel;
+		data->recv_event = btintel_recv_event;
 		data->recv_bulk = btusb_recv_bulk_intel;
 	} else if (id->driver_info & BTUSB_REALTEK) {
 		/* Allocate extra space for Realtek device */
-- 
GitLab


From 90005880a68cc8908885f5c9c9e2e60deaf78700 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 28 Jul 2023 11:30:11 +0800
Subject: [PATCH 1122/1806] Bluetooth: Remove unused declaration
 amp_read_loc_info()

This is introduced in commit 903e45411099 but was never implemented.

Fixes: 903e45411099 ("Bluetooth: AMP: Use HCI cmd to Read Loc AMP Assoc")
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/amp.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/bluetooth/amp.h b/net/bluetooth/amp.h
index 832764dfbfb3e..97c87abd129f6 100644
--- a/net/bluetooth/amp.h
+++ b/net/bluetooth/amp.h
@@ -28,7 +28,6 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
 
 int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type);
 
-void amp_read_loc_info(struct hci_dev *hdev, struct amp_mgr *mgr);
 void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle);
 void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr);
 void amp_read_loc_assoc_final_data(struct hci_dev *hdev,
-- 
GitLab


From 69997d50ec574be816b4ee8f9cee52ebbd53f8bd Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Thu, 27 Jul 2023 00:25:26 +0300
Subject: [PATCH 1123/1806] Bluetooth: ISO: handle bound CIS cleanup via
 hci_conn

Calling hci_conn_del in __iso_sock_close is invalid. It needs
hdev->lock, but it cannot be acquired there due to lock ordering.

Fix this by doing cleanup via hci_conn_drop.

Return hci_conn with refcount 1 from hci_bind_cis and hci_connect_cis,
so that the iso_conn always holds one reference.  This also fixes
refcounting when error handling.

Since hci_conn_abort shall handle termination of connections in any
state properly, we can handle BT_CONNECT socket state in the same way as
BT_CONNECTED.

Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c |  5 +++++
 net/bluetooth/iso.c      | 14 +-------------
 2 files changed, 6 insertions(+), 13 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index cccc2b8b60a81..923bb7e7be2bc 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1909,6 +1909,8 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst,
 		return ERR_PTR(-EINVAL);
 	}
 
+	hci_conn_hold(cis);
+
 	cis->iso_qos = *qos;
 	cis->state = BT_BOUND;
 
@@ -2262,6 +2264,9 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst,
 		return ERR_PTR(-ENOLINK);
 	}
 
+	/* Link takes the refcount */
+	hci_conn_drop(cis);
+
 	cis->state = BT_CONNECT;
 
 	hci_le_create_cis_pending(hdev);
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index cbe3299b4a415..358954bfbb32b 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -628,6 +628,7 @@ static void __iso_sock_close(struct sock *sk)
 		iso_sock_cleanup_listen(sk);
 		break;
 
+	case BT_CONNECT:
 	case BT_CONNECTED:
 	case BT_CONFIG:
 		if (iso_pi(sk)->conn->hcon) {
@@ -643,19 +644,6 @@ static void __iso_sock_close(struct sock *sk)
 		break;
 
 	case BT_CONNECT2:
-		iso_chan_del(sk, ECONNRESET);
-		break;
-	case BT_CONNECT:
-		/* In case of DEFER_SETUP the hcon would be bound to CIG which
-		 * needs to be removed so just call hci_conn_del so the cleanup
-		 * callback do what is needed.
-		 */
-		if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) &&
-		    iso_pi(sk)->conn->hcon) {
-			hci_conn_del(iso_pi(sk)->conn->hcon);
-			iso_pi(sk)->conn->hcon = NULL;
-		}
-
 		iso_chan_del(sk, ECONNRESET);
 		break;
 	case BT_DISCONN:
-- 
GitLab


From 2889bdd0a9a195533c2103e7b39ab0de844d72f6 Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Thu, 27 Jul 2023 00:25:25 +0300
Subject: [PATCH 1124/1806] Bluetooth: hci_sync: delete CIS in
 BT_OPEN/CONNECT/BOUND when aborting

Dropped CIS that are in state BT_OPEN/BT_BOUND, and in state BT_CONNECT
with HCI_CONN_CREATE_CIS unset, should be cleaned up immediately.
Closing CIS ISO sockets should result to the hci_conn be deleted, so
that potentially pending CIG removal can run.

hci_abort_conn cannot refer to them by handle, since their handle is
still unset if Set CIG Parameters has not yet completed.

This fixes CIS not being terminated if the socket is shut down
immediately after connection, so that the hci_abort_conn runs before Set
CIG Parameters completes. See new BlueZ test "ISO Connect Close - Success"

Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 3348a1b0e3f7d..e114409628d1c 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5308,6 +5308,10 @@ static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn,
 		if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags))
 			return hci_disconnect_sync(hdev, conn, reason);
 
+		/* CIS with no Create CIS sent have nothing to cancel */
+		if (bacmp(&conn->dst, BDADDR_ANY))
+			return HCI_ERROR_LOCAL_HOST_TERM;
+
 		/* There is no way to cancel a BIS without terminating the BIG
 		 * which is done later on connection cleanup.
 		 */
@@ -5396,13 +5400,11 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
 	case BT_CONNECT2:
 		return hci_reject_conn_sync(hdev, conn, reason);
 	case BT_OPEN:
-		/* Cleanup bises that failed to be established */
-		if (test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags)) {
-			hci_dev_lock(hdev);
-			hci_conn_failed(conn, reason);
-			hci_dev_unlock(hdev);
-		}
-		break;
+	case BT_BOUND:
+		hci_dev_lock(hdev);
+		hci_conn_failed(conn, reason);
+		hci_dev_unlock(hdev);
+		return 0;
 	default:
 		conn->state = BT_CLOSED;
 		break;
-- 
GitLab


From 094e3639623ee3b8a043e2b5285498b036a4dc09 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 2 Aug 2023 21:08:53 -0700
Subject: [PATCH 1125/1806] Bluetooth: hci_sync: Fix handling of
 HCI_OP_CREATE_CONN_CANCEL

When sending HCI_OP_CREATE_CONN_CANCEL it shall Wait for
HCI_EV_CONN_COMPLETE, not HCI_EV_CMD_STATUS, when the reason is
anything but HCI_ERROR_REMOTE_POWER_OFF. This reason is used when
suspending or powering off, where we don't want to wait for the peer's
response.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index e114409628d1c..a9b048d7b419b 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5321,6 +5321,17 @@ static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn,
 	if (hdev->hci_ver < BLUETOOTH_VER_1_2)
 		return 0;
 
+	/* Wait for HCI_EV_CONN_COMPLETE, not HCI_EV_CMD_STATUS, when the
+	 * reason is anything but HCI_ERROR_REMOTE_POWER_OFF. This reason is
+	 * used when suspending or powering off, where we don't want to wait
+	 * for the peer's response.
+	 */
+	if (reason != HCI_ERROR_REMOTE_POWER_OFF)
+		return __hci_cmd_sync_status_sk(hdev, HCI_OP_CREATE_CONN_CANCEL,
+						6, &conn->dst,
+						HCI_EV_CONN_COMPLETE,
+						HCI_CMD_TIMEOUT, NULL);
+
 	return __hci_cmd_sync_status(hdev, HCI_OP_CREATE_CONN_CANCEL,
 				     6, &conn->dst, HCI_CMD_TIMEOUT);
 }
-- 
GitLab


From 5af1f84ed13a416297ab9ced7537f4d5ae7f329a Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 3 Aug 2023 11:04:51 -0700
Subject: [PATCH 1126/1806] Bluetooth: hci_sync: Fix UAF on hci_abort_conn_sync

Connections may be cleanup while waiting for the commands to complete so
this attempts to check if the connection handle remains valid in case of
errors that would lead to call hci_conn_failed:

BUG: KASAN: slab-use-after-free in hci_conn_failed+0x1f/0x160
Read of size 8 at addr ffff888001376958 by task kworker/u3:0/52

CPU: 0 PID: 52 Comm: kworker/u3:0 Not tainted
6.5.0-rc1-00527-g2dfe76d58d3a #5615
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
1.16.2-1.fc38 04/01/2014
Workqueue: hci0 hci_cmd_sync_work
Call Trace:
 <TASK>
 dump_stack_lvl+0x1d/0x70
 print_report+0xce/0x620
 ? __virt_addr_valid+0xd4/0x150
 ? hci_conn_failed+0x1f/0x160
 kasan_report+0xd1/0x100
 ? hci_conn_failed+0x1f/0x160
 hci_conn_failed+0x1f/0x160
 hci_abort_conn_sync+0x237/0x360

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 45 ++++++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 16 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index a9b048d7b419b..ec8929e79502f 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5389,27 +5389,20 @@ static int hci_reject_conn_sync(struct hci_dev *hdev, struct hci_conn *conn,
 
 int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
 {
-	int err;
+	int err = 0;
+	u16 handle = conn->handle;
 
 	switch (conn->state) {
 	case BT_CONNECTED:
 	case BT_CONFIG:
-		return hci_disconnect_sync(hdev, conn, reason);
+		err = hci_disconnect_sync(hdev, conn, reason);
+		break;
 	case BT_CONNECT:
 		err = hci_connect_cancel_sync(hdev, conn, reason);
-		/* Cleanup hci_conn object if it cannot be cancelled as it
-		 * likelly means the controller and host stack are out of sync
-		 * or in case of LE it was still scanning so it can be cleanup
-		 * safely.
-		 */
-		if (err) {
-			hci_dev_lock(hdev);
-			hci_conn_failed(conn, err);
-			hci_dev_unlock(hdev);
-		}
-		return err;
+		break;
 	case BT_CONNECT2:
-		return hci_reject_conn_sync(hdev, conn, reason);
+		err = hci_reject_conn_sync(hdev, conn, reason);
+		break;
 	case BT_OPEN:
 	case BT_BOUND:
 		hci_dev_lock(hdev);
@@ -5418,10 +5411,30 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
 		return 0;
 	default:
 		conn->state = BT_CLOSED;
-		break;
+		return 0;
 	}
 
-	return 0;
+	/* Cleanup hci_conn object if it cannot be cancelled as it
+	 * likelly means the controller and host stack are out of sync
+	 * or in case of LE it was still scanning so it can be cleanup
+	 * safely.
+	 */
+	if (err) {
+		struct hci_conn *c;
+
+		/* Check if the connection hasn't been cleanup while waiting
+		 * commands to complete.
+		 */
+		c = hci_conn_hash_lookup_handle(hdev, handle);
+		if (!c || c != conn)
+			return 0;
+
+		hci_dev_lock(hdev);
+		hci_conn_failed(conn, err);
+		hci_dev_unlock(hdev);
+	}
+
+	return err;
 }
 
 static int hci_disconnect_all_sync(struct hci_dev *hdev, u8 reason)
-- 
GitLab


From b7f923b1ef6a2e76013089d30c9552257056360a Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 3 Aug 2023 14:41:46 -0700
Subject: [PATCH 1127/1806] Bluetooth: ISO: Fix not checking for valid CIG/CIS
 IDs

Valid range of CIG/CIS are 0x00 to 0xEF, so this checks they are
properly checked before attempting to use HCI_OP_LE_SET_CIG_PARAMS.

Fixes: ccf74f2390d6 ("Bluetooth: Add BTPROTO_ISO socket type")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/iso.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 358954bfbb32b..6b66d6a88b9a2 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1187,6 +1187,12 @@ static bool check_io_qos(struct bt_iso_io_qos *qos)
 
 static bool check_ucast_qos(struct bt_iso_qos *qos)
 {
+	if (qos->ucast.cig > 0xef && qos->ucast.cig != BT_ISO_QOS_CIG_UNSET)
+		return false;
+
+	if (qos->ucast.cis > 0xef && qos->ucast.cis != BT_ISO_QOS_CIS_UNSET)
+		return false;
+
 	if (qos->ucast.sca > 0x07)
 		return false;
 
-- 
GitLab


From 16e3b6429159795a87add7584eb100b19aa1d70b Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 3 Aug 2023 14:49:14 -0700
Subject: [PATCH 1128/1806] Bluetooth: hci_conn: Fix modifying handle while
 aborting

This introduces hci_conn_set_handle which takes care of verifying the
conditions where the hci_conn handle can be modified, including when
hci_conn_abort has been called and also checks that the handles is
valid as well.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_conn.c         | 27 +++++++++++++++++++++++++++
 net/bluetooth/hci_event.c        | 29 +++++++++++------------------
 3 files changed, 39 insertions(+), 18 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 8200a6689b397..d2a3a2a9fd7d6 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1425,6 +1425,7 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role);
 void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active);
 
 void hci_conn_failed(struct hci_conn *conn, u8 status);
+u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle);
 
 /*
  * hci_conn_get() and hci_conn_put() are used to control the life-time of an
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 923bb7e7be2bc..6132eed7e8dcd 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1231,6 +1231,33 @@ void hci_conn_failed(struct hci_conn *conn, u8 status)
 	hci_conn_del(conn);
 }
 
+/* This function requires the caller holds hdev->lock */
+u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle)
+{
+	struct hci_dev *hdev = conn->hdev;
+
+	bt_dev_dbg(hdev, "hcon %p handle 0x%4.4x", conn, handle);
+
+	if (conn->handle == handle)
+		return 0;
+
+	if (handle > HCI_CONN_HANDLE_MAX) {
+		bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x",
+			   handle, HCI_CONN_HANDLE_MAX);
+		return HCI_ERROR_INVALID_PARAMETERS;
+	}
+
+	/* If abort_reason has been sent it means the connection is being
+	 * aborted and the handle shall not be changed.
+	 */
+	if (conn->abort_reason)
+		return conn->abort_reason;
+
+	conn->handle = handle;
+
+	return 0;
+}
+
 static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err)
 {
 	struct hci_conn *conn;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index f1fcece29e7d8..218da9b0fe8f1 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3179,13 +3179,9 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data,
 	}
 
 	if (!status) {
-		conn->handle = __le16_to_cpu(ev->handle);
-		if (conn->handle > HCI_CONN_HANDLE_MAX) {
-			bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x",
-				   conn->handle, HCI_CONN_HANDLE_MAX);
-			status = HCI_ERROR_INVALID_PARAMETERS;
+		status = hci_conn_set_handle(conn, __le16_to_cpu(ev->handle));
+		if (status)
 			goto done;
-		}
 
 		if (conn->type == ACL_LINK) {
 			conn->state = BT_CONFIG;
@@ -3849,11 +3845,9 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data,
 		if (conn->state != BT_BOUND && conn->state != BT_CONNECT)
 			continue;
 
-		conn->handle = __le16_to_cpu(rp->handle[i]);
+		if (hci_conn_set_handle(conn, __le16_to_cpu(rp->handle[i])))
+			continue;
 
-		bt_dev_dbg(hdev, "%p handle 0x%4.4x parent %p", conn,
-			   conn->handle, conn->parent);
-		
 		if (conn->state == BT_CONNECT)
 			pending = true;
 	}
@@ -5039,11 +5033,8 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data,
 
 	switch (status) {
 	case 0x00:
-		conn->handle = __le16_to_cpu(ev->handle);
-		if (conn->handle > HCI_CONN_HANDLE_MAX) {
-			bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x",
-				   conn->handle, HCI_CONN_HANDLE_MAX);
-			status = HCI_ERROR_INVALID_PARAMETERS;
+		status = hci_conn_set_handle(conn, __le16_to_cpu(ev->handle));
+		if (status) {
 			conn->state = BT_CLOSED;
 			break;
 		}
@@ -6978,7 +6969,7 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data,
 {
 	struct hci_evt_le_create_big_complete *ev = data;
 	struct hci_conn *conn;
-	__u8 bis_idx = 0;
+	__u8 i = 0;
 
 	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
 
@@ -6996,7 +6987,9 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data,
 		    conn->iso_qos.bcast.big != ev->handle)
 			continue;
 
-		conn->handle = __le16_to_cpu(ev->bis_handle[bis_idx++]);
+		if (hci_conn_set_handle(conn,
+					__le16_to_cpu(ev->bis_handle[i++])))
+			continue;
 
 		if (!ev->status) {
 			conn->state = BT_CONNECTED;
@@ -7015,7 +7008,7 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data,
 		rcu_read_lock();
 	}
 
-	if (!ev->status && !bis_idx)
+	if (!ev->status && !i)
 		/* If no BISes have been connected for the BIG,
 		 * terminate. This is in case all bound connections
 		 * have been closed before the BIG creation
-- 
GitLab


From f2f84a70f9d0c9a3263194ca9d82e7bc6027d356 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 3 Aug 2023 16:41:34 -0700
Subject: [PATCH 1129/1806] Bluetooth: hci_conn: Fix not allowing valid CIS ID

Only the number of CIS shall be limited to 0x1f, the CIS ID in the
other hand is up to 0xef.

Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 6132eed7e8dcd..71e5a4c2e5230 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1846,9 +1846,12 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos)
 		cis_add(&data, qos);
 	}
 
-	/* Reprogram all CIS(s) with the same CIG */
-	for (data.cig = qos->ucast.cig, data.cis = 0x00; data.cis < 0x11;
-	     data.cis++) {
+	/* Reprogram all CIS(s) with the same CIG, valid range are:
+	 * num_cis: 0x00 to 0x1F
+	 * cis_id: 0x00 to 0xEF
+	 */
+	for (data.cig = qos->ucast.cig, data.cis = 0x00; data.cis < 0xf0 &&
+	     data.pdu.cp.num_cis < ARRAY_SIZE(data.pdu.cis); data.cis++) {
 		data.count = 0;
 
 		hci_conn_hash_list_state(hdev, cis_list, ISO_LINK, BT_BOUND,
-- 
GitLab


From f88670161eb205f842989df555d0dd2f9fe2d4b5 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 4 Aug 2023 11:03:43 -0700
Subject: [PATCH 1130/1806] Bluetooth: hci_core: Make hci_is_le_conn_scanning
 public

This moves hci_is_le_conn_scanning to hci_core.h so it can be used by
different files without having to duplicate its code.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h | 21 +++++++++++++++++++++
 net/bluetooth/hci_request.c      | 21 ---------------------
 net/bluetooth/hci_sync.c         | 21 ---------------------
 3 files changed, 21 insertions(+), 42 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d2a3a2a9fd7d6..f4462c325e2ab 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1372,6 +1372,27 @@ static inline struct hci_conn *hci_lookup_le_connect(struct hci_dev *hdev)
 	return NULL;
 }
 
+/* Returns true if an le connection is in the scanning state */
+static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev)
+{
+	struct hci_conn_hash *h = &hdev->conn_hash;
+	struct hci_conn  *c;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(c, &h->list, list) {
+		if (c->type == LE_LINK && c->state == BT_CONNECT &&
+		    test_bit(HCI_CONN_SCANNING, &c->flags)) {
+			rcu_read_unlock();
+			return true;
+		}
+	}
+
+	rcu_read_unlock();
+
+	return false;
+}
+
 int hci_disconnect(struct hci_conn *conn, __u8 reason);
 bool hci_setup_sync(struct hci_conn *conn, __u16 handle);
 void hci_sco_setup(struct hci_conn *conn, __u8 status);
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index f7e006a363829..6e023b0104b03 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -629,27 +629,6 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval,
 	}
 }
 
-/* Returns true if an le connection is in the scanning state */
-static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev)
-{
-	struct hci_conn_hash *h = &hdev->conn_hash;
-	struct hci_conn  *c;
-
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type == LE_LINK && c->state == BT_CONNECT &&
-		    test_bit(HCI_CONN_SCANNING, &c->flags)) {
-			rcu_read_unlock();
-			return true;
-		}
-	}
-
-	rcu_read_unlock();
-
-	return false;
-}
-
 static void set_random_addr(struct hci_request *req, bdaddr_t *rpa);
 static int hci_update_random_address(struct hci_request *req,
 				     bool require_privacy, bool use_rpa,
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index ec8929e79502f..41a8e57d82672 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2672,27 +2672,6 @@ done:
 	return filter_policy;
 }
 
-/* Returns true if an le connection is in the scanning state */
-static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev)
-{
-	struct hci_conn_hash *h = &hdev->conn_hash;
-	struct hci_conn  *c;
-
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type == LE_LINK && c->state == BT_CONNECT &&
-		    test_bit(HCI_CONN_SCANNING, &c->flags)) {
-			rcu_read_unlock();
-			return true;
-		}
-	}
-
-	rcu_read_unlock();
-
-	return false;
-}
-
 static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type,
 					  u16 interval, u16 window,
 					  u8 own_addr_type, u8 filter_policy)
-- 
GitLab


From a091289218202bc09d9b9caa8afcde1018584aec Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 4 Aug 2023 14:54:09 -0700
Subject: [PATCH 1131/1806] Bluetooth: hci_conn: Fix hci_le_set_cig_params

When running with concurrent task only one CIS was being assigned so
this attempts to rework the way the PDU is constructed so it is handled
later at the callback instead of in place.

Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 157 ++++++++++++++++-----------------------
 1 file changed, 63 insertions(+), 94 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 71e5a4c2e5230..ae206eb551f76 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -733,7 +733,6 @@ struct iso_list_data {
 		u16 sync_handle;
 	};
 	int count;
-	struct iso_cig_params pdu;
 	bool big_term;
 	bool big_sync_term;
 };
@@ -1703,42 +1702,6 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst,
 	return sco;
 }
 
-static void cis_add(struct iso_list_data *d, struct bt_iso_qos *qos)
-{
-	struct hci_cis_params *cis = &d->pdu.cis[d->pdu.cp.num_cis];
-
-	cis->cis_id = qos->ucast.cis;
-	cis->c_sdu  = cpu_to_le16(qos->ucast.out.sdu);
-	cis->p_sdu  = cpu_to_le16(qos->ucast.in.sdu);
-	cis->c_phy  = qos->ucast.out.phy ? qos->ucast.out.phy : qos->ucast.in.phy;
-	cis->p_phy  = qos->ucast.in.phy ? qos->ucast.in.phy : qos->ucast.out.phy;
-	cis->c_rtn  = qos->ucast.out.rtn;
-	cis->p_rtn  = qos->ucast.in.rtn;
-
-	d->pdu.cp.num_cis++;
-}
-
-static void cis_list(struct hci_conn *conn, void *data)
-{
-	struct iso_list_data *d = data;
-
-	/* Skip if broadcast/ANY address */
-	if (!bacmp(&conn->dst, BDADDR_ANY))
-		return;
-
-	if (d->cig != conn->iso_qos.ucast.cig || d->cis == BT_ISO_QOS_CIS_UNSET ||
-	    d->cis != conn->iso_qos.ucast.cis)
-		return;
-
-	d->count++;
-
-	if (d->pdu.cp.cig_id == BT_ISO_QOS_CIG_UNSET ||
-	    d->count >= ARRAY_SIZE(d->pdu.cis))
-		return;
-
-	cis_add(d, &conn->iso_qos);
-}
-
 static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos)
 {
 	struct hci_dev *hdev = conn->hdev;
@@ -1771,25 +1734,62 @@ static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos)
 	return hci_send_cmd(hdev, HCI_OP_LE_CREATE_BIG, sizeof(cp), &cp);
 }
 
-static void set_cig_params_complete(struct hci_dev *hdev, void *data, int err)
+static int set_cig_params_sync(struct hci_dev *hdev, void *data)
 {
-	struct iso_cig_params *pdu = data;
+	u8 cig_id = PTR_ERR(data);
+	struct hci_conn *conn;
+	struct bt_iso_qos *qos;
+	struct iso_cig_params pdu;
+	u8 cis_id;
 
-	bt_dev_dbg(hdev, "");
+	conn = hci_conn_hash_lookup_cig(hdev, cig_id);
+	if (!conn)
+		return 0;
 
-	if (err)
-		bt_dev_err(hdev, "Unable to set CIG parameters: %d", err);
+	memset(&pdu, 0, sizeof(pdu));
 
-	kfree(pdu);
-}
+	qos = &conn->iso_qos;
+	pdu.cp.cig_id = cig_id;
+	hci_cpu_to_le24(qos->ucast.out.interval, pdu.cp.c_interval);
+	hci_cpu_to_le24(qos->ucast.in.interval, pdu.cp.p_interval);
+	pdu.cp.sca = qos->ucast.sca;
+	pdu.cp.packing = qos->ucast.packing;
+	pdu.cp.framing = qos->ucast.framing;
+	pdu.cp.c_latency = cpu_to_le16(qos->ucast.out.latency);
+	pdu.cp.p_latency = cpu_to_le16(qos->ucast.in.latency);
 
-static int set_cig_params_sync(struct hci_dev *hdev, void *data)
-{
-	struct iso_cig_params *pdu = data;
-	u32 plen;
+	/* Reprogram all CIS(s) with the same CIG, valid range are:
+	 * num_cis: 0x00 to 0x1F
+	 * cis_id: 0x00 to 0xEF
+	 */
+	for (cis_id = 0x00; cis_id < 0xf0 &&
+	     pdu.cp.num_cis < ARRAY_SIZE(pdu.cis); cis_id++) {
+		struct hci_cis_params *cis;
+
+		conn = hci_conn_hash_lookup_cis(hdev, NULL, 0, cig_id, cis_id);
+		if (!conn)
+			continue;
 
-	plen = sizeof(pdu->cp) + pdu->cp.num_cis * sizeof(pdu->cis[0]);
-	return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_CIG_PARAMS, plen, pdu,
+		qos = &conn->iso_qos;
+
+		cis = &pdu.cis[pdu.cp.num_cis++];
+		cis->cis_id = cis_id;
+		cis->c_sdu  = cpu_to_le16(conn->iso_qos.ucast.out.sdu);
+		cis->p_sdu  = cpu_to_le16(conn->iso_qos.ucast.in.sdu);
+		cis->c_phy  = qos->ucast.out.phy ? qos->ucast.out.phy :
+			      qos->ucast.in.phy;
+		cis->p_phy  = qos->ucast.in.phy ? qos->ucast.in.phy :
+			      qos->ucast.out.phy;
+		cis->c_rtn  = qos->ucast.out.rtn;
+		cis->p_rtn  = qos->ucast.in.rtn;
+	}
+
+	if (!pdu.cp.num_cis)
+		return 0;
+
+	return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_CIG_PARAMS,
+				     sizeof(pdu.cp) +
+				     pdu.cp.num_cis * sizeof(pdu.cis[0]), &pdu,
 				     HCI_CMD_TIMEOUT);
 }
 
@@ -1797,7 +1797,6 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos)
 {
 	struct hci_dev *hdev = conn->hdev;
 	struct iso_list_data data;
-	struct iso_cig_params *pdu;
 
 	memset(&data, 0, sizeof(data));
 
@@ -1824,61 +1823,31 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos)
 		qos->ucast.cig = data.cig;
 	}
 
-	data.pdu.cp.cig_id = qos->ucast.cig;
-	hci_cpu_to_le24(qos->ucast.out.interval, data.pdu.cp.c_interval);
-	hci_cpu_to_le24(qos->ucast.in.interval, data.pdu.cp.p_interval);
-	data.pdu.cp.sca = qos->ucast.sca;
-	data.pdu.cp.packing = qos->ucast.packing;
-	data.pdu.cp.framing = qos->ucast.framing;
-	data.pdu.cp.c_latency = cpu_to_le16(qos->ucast.out.latency);
-	data.pdu.cp.p_latency = cpu_to_le16(qos->ucast.in.latency);
-
 	if (qos->ucast.cis != BT_ISO_QOS_CIS_UNSET) {
-		data.count = 0;
-		data.cig = qos->ucast.cig;
-		data.cis = qos->ucast.cis;
-
-		hci_conn_hash_list_state(hdev, cis_list, ISO_LINK, BT_BOUND,
-					 &data);
-		if (data.count)
+		if (hci_conn_hash_lookup_cis(hdev, NULL, 0, qos->ucast.cig,
+					     qos->ucast.cis))
 			return false;
-
-		cis_add(&data, qos);
+		goto done;
 	}
 
-	/* Reprogram all CIS(s) with the same CIG, valid range are:
-	 * num_cis: 0x00 to 0x1F
-	 * cis_id: 0x00 to 0xEF
-	 */
-	for (data.cig = qos->ucast.cig, data.cis = 0x00; data.cis < 0xf0 &&
-	     data.pdu.cp.num_cis < ARRAY_SIZE(data.pdu.cis); data.cis++) {
-		data.count = 0;
-
-		hci_conn_hash_list_state(hdev, cis_list, ISO_LINK, BT_BOUND,
-					 &data);
-		if (data.count)
-			continue;
-
-		/* Allocate a CIS if not set */
-		if (qos->ucast.cis == BT_ISO_QOS_CIS_UNSET) {
+	/* Allocate first available CIS if not set */
+	for (data.cig = qos->ucast.cig, data.cis = 0x00; data.cis < 0xf0;
+	     data.cis++) {
+		if (!hci_conn_hash_lookup_cis(hdev, NULL, 0, data.cig,
+					      data.cis)) {
 			/* Update CIS */
 			qos->ucast.cis = data.cis;
-			cis_add(&data, qos);
+			break;
 		}
 	}
 
-	if (qos->ucast.cis == BT_ISO_QOS_CIS_UNSET || !data.pdu.cp.num_cis)
+	if (qos->ucast.cis == BT_ISO_QOS_CIS_UNSET)
 		return false;
 
-	pdu = kmemdup(&data.pdu, sizeof(*pdu), GFP_KERNEL);
-	if (!pdu)
-		return false;
-
-	if (hci_cmd_sync_queue(hdev, set_cig_params_sync, pdu,
-			       set_cig_params_complete) < 0) {
-		kfree(pdu);
+done:
+	if (hci_cmd_sync_queue(hdev, set_cig_params_sync,
+			       ERR_PTR(qos->ucast.cig), NULL) < 0)
 		return false;
-	}
 
 	return true;
 }
-- 
GitLab


From a1f6c3aef13c9e7f8d459bd464e9e34da1342c0c Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 4 Aug 2023 16:23:41 -0700
Subject: [PATCH 1132/1806] Bluetooth: hci_sync: Introduce PTR_UINT/UINT_PTR
 macros

This introduces PTR_UINT/UINT_PTR macros and replace the use of
PTR_ERR/ERR_PTR.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_sync.h |  3 +++
 net/bluetooth/hci_conn.c         | 19 ++++++++++---------
 net/bluetooth/hci_sync.c         |  4 ++--
 3 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index b516a0f4a55b8..57eeb07aeb251 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -5,6 +5,9 @@
  * Copyright (C) 2021 Intel Corporation
  */
 
+#define UINT_PTR(_handle)		((void *)((uintptr_t)_handle))
+#define PTR_UINT(_ptr)			((uintptr_t)((void *)_ptr))
+
 typedef int (*hci_cmd_sync_work_func_t)(struct hci_dev *hdev, void *data);
 typedef void (*hci_cmd_sync_work_destroy_t)(struct hci_dev *hdev, void *data,
 					    int err);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index ae206eb551f76..4ad6af4e31450 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -872,7 +872,7 @@ static void bis_cleanup(struct hci_conn *conn)
 
 static int remove_cig_sync(struct hci_dev *hdev, void *data)
 {
-	u8 handle = PTR_ERR(data);
+	u8 handle = PTR_UINT(data);
 
 	return hci_le_remove_cig_sync(hdev, handle);
 }
@@ -881,7 +881,8 @@ static int hci_le_remove_cig(struct hci_dev *hdev, u8 handle)
 {
 	bt_dev_dbg(hdev, "handle 0x%2.2x", handle);
 
-	return hci_cmd_sync_queue(hdev, remove_cig_sync, ERR_PTR(handle), NULL);
+	return hci_cmd_sync_queue(hdev, remove_cig_sync, UINT_PTR(handle),
+				  NULL);
 }
 
 static void find_cis(struct hci_conn *conn, void *data)
@@ -1260,7 +1261,7 @@ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle)
 static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err)
 {
 	struct hci_conn *conn;
-	u16 handle = PTR_ERR(data);
+	u16 handle = PTR_UINT(data);
 
 	conn = hci_conn_hash_lookup_handle(hdev, handle);
 	if (!conn)
@@ -1290,7 +1291,7 @@ done:
 static int hci_connect_le_sync(struct hci_dev *hdev, void *data)
 {
 	struct hci_conn *conn;
-	u16 handle = PTR_ERR(data);
+	u16 handle = PTR_UINT(data);
 
 	conn = hci_conn_hash_lookup_handle(hdev, handle);
 	if (!conn)
@@ -1372,7 +1373,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	clear_bit(HCI_CONN_SCANNING, &conn->flags);
 
 	err = hci_cmd_sync_queue(hdev, hci_connect_le_sync,
-				 ERR_PTR(conn->handle),
+				 UINT_PTR(conn->handle),
 				 create_le_conn_complete);
 	if (err) {
 		hci_conn_del(conn);
@@ -1736,7 +1737,7 @@ static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos)
 
 static int set_cig_params_sync(struct hci_dev *hdev, void *data)
 {
-	u8 cig_id = PTR_ERR(data);
+	u8 cig_id = PTR_UINT(data);
 	struct hci_conn *conn;
 	struct bt_iso_qos *qos;
 	struct iso_cig_params pdu;
@@ -1846,7 +1847,7 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos)
 
 done:
 	if (hci_cmd_sync_queue(hdev, set_cig_params_sync,
-			       ERR_PTR(qos->ucast.cig), NULL) < 0)
+			       UINT_PTR(qos->ucast.cig), NULL) < 0)
 		return false;
 
 	return true;
@@ -2858,7 +2859,7 @@ u32 hci_conn_get_phy(struct hci_conn *conn)
 static int abort_conn_sync(struct hci_dev *hdev, void *data)
 {
 	struct hci_conn *conn;
-	u16 handle = PTR_ERR(data);
+	u16 handle = PTR_UINT(data);
 
 	conn = hci_conn_hash_lookup_handle(hdev, handle);
 	if (!conn)
@@ -2898,6 +2899,6 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason)
 		}
 	}
 
-	return hci_cmd_sync_queue(hdev, abort_conn_sync, ERR_PTR(conn->handle),
+	return hci_cmd_sync_queue(hdev, abort_conn_sync, UINT_PTR(conn->handle),
 				  NULL);
 }
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 41a8e57d82672..5eb30ba213708 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -6528,7 +6528,7 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy,
 
 static int _update_adv_data_sync(struct hci_dev *hdev, void *data)
 {
-	u8 instance = PTR_ERR(data);
+	u8 instance = PTR_UINT(data);
 
 	return hci_update_adv_data_sync(hdev, instance);
 }
@@ -6536,5 +6536,5 @@ static int _update_adv_data_sync(struct hci_dev *hdev, void *data)
 int hci_update_adv_data(struct hci_dev *hdev, u8 instance)
 {
 	return hci_cmd_sync_queue(hdev, _update_adv_data_sync,
-				  ERR_PTR(instance), NULL);
+				  UINT_PTR(instance), NULL);
 }
-- 
GitLab


From 3673952cf0c6cf81b06c66a0b788abeeb02ff3ae Mon Sep 17 00:00:00 2001
From: Min Li <lm0963hack@gmail.com>
Date: Mon, 7 Aug 2023 19:07:41 +0800
Subject: [PATCH 1133/1806] Bluetooth: Fix potential use-after-free when clear
 keys

Similar to commit c5d2b6fa26b5 ("Bluetooth: Fix use-after-free in
hci_remove_ltk/hci_remove_irk"). We can not access k after kfree_rcu()
call.

Fixes: d7d41682efc2 ("Bluetooth: Fix Suspicious RCU usage warnings")
Signed-off-by: Min Li <lm0963hack@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_core.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 0fefa6788911b..d7552b394ac22 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1074,9 +1074,9 @@ void hci_uuids_clear(struct hci_dev *hdev)
 
 void hci_link_keys_clear(struct hci_dev *hdev)
 {
-	struct link_key *key;
+	struct link_key *key, *tmp;
 
-	list_for_each_entry(key, &hdev->link_keys, list) {
+	list_for_each_entry_safe(key, tmp, &hdev->link_keys, list) {
 		list_del_rcu(&key->list);
 		kfree_rcu(key, rcu);
 	}
@@ -1084,9 +1084,9 @@ void hci_link_keys_clear(struct hci_dev *hdev)
 
 void hci_smp_ltks_clear(struct hci_dev *hdev)
 {
-	struct smp_ltk *k;
+	struct smp_ltk *k, *tmp;
 
-	list_for_each_entry(k, &hdev->long_term_keys, list) {
+	list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) {
 		list_del_rcu(&k->list);
 		kfree_rcu(k, rcu);
 	}
@@ -1094,9 +1094,9 @@ void hci_smp_ltks_clear(struct hci_dev *hdev)
 
 void hci_smp_irks_clear(struct hci_dev *hdev)
 {
-	struct smp_irk *k;
+	struct smp_irk *k, *tmp;
 
-	list_for_each_entry(k, &hdev->identity_resolving_keys, list) {
+	list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) {
 		list_del_rcu(&k->list);
 		kfree_rcu(k, rcu);
 	}
@@ -1104,9 +1104,9 @@ void hci_smp_irks_clear(struct hci_dev *hdev)
 
 void hci_blocked_keys_clear(struct hci_dev *hdev)
 {
-	struct blocked_key *b;
+	struct blocked_key *b, *tmp;
 
-	list_for_each_entry(b, &hdev->blocked_keys, list) {
+	list_for_each_entry_safe(b, tmp, &hdev->blocked_keys, list) {
 		list_del_rcu(&b->list);
 		kfree_rcu(b, rcu);
 	}
-- 
GitLab


From a2bcd2b63271a93a695fabbfbf459c603d956d48 Mon Sep 17 00:00:00 2001
From: Manish Mandlik <mmandlik@google.com>
Date: Fri, 4 Aug 2023 11:14:45 -0700
Subject: [PATCH 1134/1806] Bluetooth: hci_sync: Avoid use-after-free in dbg
 for hci_add_adv_monitor()

KSAN reports use-after-free in hci_add_adv_monitor().

While adding an adv monitor,
    hci_add_adv_monitor() calls ->
    msft_add_monitor_pattern() calls ->
    msft_add_monitor_sync() calls ->
    msft_le_monitor_advertisement_cb() calls in an error case ->
    hci_free_adv_monitor() which frees the *moniter.

This is referenced by bt_dev_dbg() in hci_add_adv_monitor().

Fix the bt_dev_dbg() by using handle instead of monitor->handle.

Fixes: b747a83690c8 ("Bluetooth: hci_sync: Refactor add Adv Monitor")
Signed-off-by: Manish Mandlik <mmandlik@google.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index d7552b394ac22..a5992f1b3c9b7 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1957,7 +1957,7 @@ int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor)
 	case HCI_ADV_MONITOR_EXT_MSFT:
 		status = msft_add_monitor_pattern(hdev, monitor);
 		bt_dev_dbg(hdev, "add monitor %d msft status %d",
-			   monitor->handle, status);
+			   handle, status);
 		break;
 	}
 
-- 
GitLab


From 3cd43dd15f9dbfb67a60889992bf03b92370b202 Mon Sep 17 00:00:00 2001
From: Ziyang Xuan <william.xuanziyang@huawei.com>
Date: Mon, 7 Aug 2023 10:32:06 +0800
Subject: [PATCH 1135/1806] Bluetooth: Remove unnecessary NULL check before
 vfree()

Remove unnecessary NULL check which causes coccinelle warning:

net/bluetooth/coredump.c:104:2-7: WARNING: NULL check before some
freeing functions is not needed.

Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/coredump.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/bluetooth/coredump.c b/net/bluetooth/coredump.c
index d2d2624ec708f..ec97a4bab1c9f 100644
--- a/net/bluetooth/coredump.c
+++ b/net/bluetooth/coredump.c
@@ -100,8 +100,7 @@ void hci_devcd_reset(struct hci_dev *hdev)
 /* Call with hci_dev_lock only. */
 static void hci_devcd_free(struct hci_dev *hdev)
 {
-	if (hdev->dump.head)
-		vfree(hdev->dump.head);
+	vfree(hdev->dump.head);
 
 	hci_devcd_reset(hdev);
 }
-- 
GitLab


From bd003fb338afee97c76f13c3e9144a7e4ad37179 Mon Sep 17 00:00:00 2001
From: Max Chou <max.chou@realtek.com>
Date: Mon, 7 Aug 2023 19:42:59 +0800
Subject: [PATCH 1136/1806] Bluetooth: btrtl: Load FW v2 otherwise FW v1 for
 RTL8852C

In this commit, prefer to load FW v2 if available. Fallback to FW v1
otherwise. This behavior is only for RTL8852C.

Fixes: 9a24ce5e29b1 ("Bluetooth: btrtl: Firmware format v2 support")
Cc: stable@vger.kernel.org
Suggested-by: Juerg Haefliger <juerg.haefliger@canonical.com>
Tested-by: Hilda Wu <hildawu@realtek.com>
Signed-off-by: Max Chou <max.chou@realtek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btrtl.c | 70 +++++++++++++++++++++++++--------------
 1 file changed, 45 insertions(+), 25 deletions(-)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index ddae6524106d1..84c2c2e1122fb 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -104,7 +104,7 @@ static const struct id_table ic_id_table[] = {
 	{ IC_INFO(RTL_ROM_LMP_8723A, 0xb, 0x6, HCI_USB),
 	  .config_needed = false,
 	  .has_rom_version = false,
-	  .fw_name = "rtl_bt/rtl8723a_fw.bin",
+	  .fw_name = "rtl_bt/rtl8723a_fw",
 	  .cfg_name = NULL,
 	  .hw_info = "rtl8723au" },
 
@@ -112,7 +112,7 @@ static const struct id_table ic_id_table[] = {
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xb, 0x6, HCI_UART),
 	  .config_needed = true,
 	  .has_rom_version = true,
-	  .fw_name  = "rtl_bt/rtl8723bs_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8723bs_fw",
 	  .cfg_name = "rtl_bt/rtl8723bs_config",
 	  .hw_info  = "rtl8723bs" },
 
@@ -120,7 +120,7 @@ static const struct id_table ic_id_table[] = {
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xb, 0x6, HCI_USB),
 	  .config_needed = false,
 	  .has_rom_version = true,
-	  .fw_name  = "rtl_bt/rtl8723b_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8723b_fw",
 	  .cfg_name = "rtl_bt/rtl8723b_config",
 	  .hw_info  = "rtl8723bu" },
 
@@ -132,7 +132,7 @@ static const struct id_table ic_id_table[] = {
 	  .hci_bus = HCI_UART,
 	  .config_needed = true,
 	  .has_rom_version = true,
-	  .fw_name  = "rtl_bt/rtl8723cs_cg_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8723cs_cg_fw",
 	  .cfg_name = "rtl_bt/rtl8723cs_cg_config",
 	  .hw_info  = "rtl8723cs-cg" },
 
@@ -144,7 +144,7 @@ static const struct id_table ic_id_table[] = {
 	  .hci_bus = HCI_UART,
 	  .config_needed = true,
 	  .has_rom_version = true,
-	  .fw_name  = "rtl_bt/rtl8723cs_vf_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8723cs_vf_fw",
 	  .cfg_name = "rtl_bt/rtl8723cs_vf_config",
 	  .hw_info  = "rtl8723cs-vf" },
 
@@ -156,7 +156,7 @@ static const struct id_table ic_id_table[] = {
 	  .hci_bus = HCI_UART,
 	  .config_needed = true,
 	  .has_rom_version = true,
-	  .fw_name  = "rtl_bt/rtl8723cs_xx_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8723cs_xx_fw",
 	  .cfg_name = "rtl_bt/rtl8723cs_xx_config",
 	  .hw_info  = "rtl8723cs" },
 
@@ -164,7 +164,7 @@ static const struct id_table ic_id_table[] = {
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xd, 0x8, HCI_USB),
 	  .config_needed = true,
 	  .has_rom_version = true,
-	  .fw_name  = "rtl_bt/rtl8723d_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8723d_fw",
 	  .cfg_name = "rtl_bt/rtl8723d_config",
 	  .hw_info  = "rtl8723du" },
 
@@ -172,7 +172,7 @@ static const struct id_table ic_id_table[] = {
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xd, 0x8, HCI_UART),
 	  .config_needed = true,
 	  .has_rom_version = true,
-	  .fw_name  = "rtl_bt/rtl8723ds_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8723ds_fw",
 	  .cfg_name = "rtl_bt/rtl8723ds_config",
 	  .hw_info  = "rtl8723ds" },
 
@@ -180,7 +180,7 @@ static const struct id_table ic_id_table[] = {
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xa, 0x6, HCI_USB),
 	  .config_needed = false,
 	  .has_rom_version = true,
-	  .fw_name  = "rtl_bt/rtl8821a_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8821a_fw",
 	  .cfg_name = "rtl_bt/rtl8821a_config",
 	  .hw_info  = "rtl8821au" },
 
@@ -189,7 +189,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8821c_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8821c_fw",
 	  .cfg_name = "rtl_bt/rtl8821c_config",
 	  .hw_info  = "rtl8821cu" },
 
@@ -198,7 +198,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8821cs_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8821cs_fw",
 	  .cfg_name = "rtl_bt/rtl8821cs_config",
 	  .hw_info  = "rtl8821cs" },
 
@@ -206,7 +206,7 @@ static const struct id_table ic_id_table[] = {
 	{ IC_INFO(RTL_ROM_LMP_8761A, 0xa, 0x6, HCI_USB),
 	  .config_needed = false,
 	  .has_rom_version = true,
-	  .fw_name  = "rtl_bt/rtl8761a_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8761a_fw",
 	  .cfg_name = "rtl_bt/rtl8761a_config",
 	  .hw_info  = "rtl8761au" },
 
@@ -215,7 +215,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8761b_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8761b_fw",
 	  .cfg_name = "rtl_bt/rtl8761b_config",
 	  .hw_info  = "rtl8761btv" },
 
@@ -223,7 +223,7 @@ static const struct id_table ic_id_table[] = {
 	{ IC_INFO(RTL_ROM_LMP_8761A, 0xb, 0xa, HCI_USB),
 	  .config_needed = false,
 	  .has_rom_version = true,
-	  .fw_name  = "rtl_bt/rtl8761bu_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8761bu_fw",
 	  .cfg_name = "rtl_bt/rtl8761bu_config",
 	  .hw_info  = "rtl8761bu" },
 
@@ -232,7 +232,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8822cs_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8822cs_fw",
 	  .cfg_name = "rtl_bt/rtl8822cs_config",
 	  .hw_info  = "rtl8822cs" },
 
@@ -241,7 +241,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8822cs_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8822cs_fw",
 	  .cfg_name = "rtl_bt/rtl8822cs_config",
 	  .hw_info  = "rtl8822cs" },
 
@@ -250,7 +250,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8822cu_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8822cu_fw",
 	  .cfg_name = "rtl_bt/rtl8822cu_config",
 	  .hw_info  = "rtl8822cu" },
 
@@ -259,7 +259,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8822b_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8822b_fw",
 	  .cfg_name = "rtl_bt/rtl8822b_config",
 	  .hw_info  = "rtl8822bu" },
 
@@ -268,7 +268,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8852au_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8852au_fw",
 	  .cfg_name = "rtl_bt/rtl8852au_config",
 	  .hw_info  = "rtl8852au" },
 
@@ -277,7 +277,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8852bs_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8852bs_fw",
 	  .cfg_name = "rtl_bt/rtl8852bs_config",
 	  .hw_info  = "rtl8852bs" },
 
@@ -286,7 +286,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8852bu_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8852bu_fw",
 	  .cfg_name = "rtl_bt/rtl8852bu_config",
 	  .hw_info  = "rtl8852bu" },
 
@@ -295,7 +295,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .has_msft_ext = true,
-	  .fw_name  = "rtl_bt/rtl8852cu_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8852cu_fw",
 	  .cfg_name = "rtl_bt/rtl8852cu_config",
 	  .hw_info  = "rtl8852cu" },
 
@@ -304,7 +304,7 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .has_msft_ext = false,
-	  .fw_name  = "rtl_bt/rtl8851bu_fw.bin",
+	  .fw_name  = "rtl_bt/rtl8851bu_fw",
 	  .cfg_name = "rtl_bt/rtl8851bu_config",
 	  .hw_info  = "rtl8851bu" },
 	};
@@ -1045,6 +1045,7 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev,
 	struct sk_buff *skb;
 	struct hci_rp_read_local_version *resp;
 	struct hci_command_hdr *cmd;
+	char fw_name[40];
 	char cfg_name[40];
 	u16 hci_rev, lmp_subver;
 	u8 hci_ver, lmp_ver, chip_type = 0;
@@ -1154,8 +1155,26 @@ next:
 			goto err_free;
 	}
 
-	btrtl_dev->fw_len = rtl_load_file(hdev, btrtl_dev->ic_info->fw_name,
-					  &btrtl_dev->fw_data);
+	if (!btrtl_dev->ic_info->fw_name) {
+		ret = -ENOMEM;
+		goto err_free;
+	}
+
+	btrtl_dev->fw_len = -EIO;
+	if (lmp_subver == RTL_ROM_LMP_8852A && hci_rev == 0x000c) {
+		snprintf(fw_name, sizeof(fw_name), "%s_v2.bin",
+				btrtl_dev->ic_info->fw_name);
+		btrtl_dev->fw_len = rtl_load_file(hdev, fw_name,
+				&btrtl_dev->fw_data);
+	}
+
+	if (btrtl_dev->fw_len < 0) {
+		snprintf(fw_name, sizeof(fw_name), "%s.bin",
+				btrtl_dev->ic_info->fw_name);
+		btrtl_dev->fw_len = rtl_load_file(hdev, fw_name,
+				&btrtl_dev->fw_data);
+	}
+
 	if (btrtl_dev->fw_len < 0) {
 		rtl_dev_err(hdev, "firmware file %s not found",
 			    btrtl_dev->ic_info->fw_name);
@@ -1491,4 +1510,5 @@ MODULE_FIRMWARE("rtl_bt/rtl8852bs_config.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8852bu_fw.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8852bu_config.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8852cu_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8852cu_fw_v2.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8852cu_config.bin");
-- 
GitLab


From 66dee21524d9ac6461ec3052652b7bc0603ee0c5 Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Sat, 5 Aug 2023 19:08:41 +0300
Subject: [PATCH 1137/1806] Bluetooth: hci_event: drop only unbound CIS if Set
 CIG Parameters fails

When user tries to connect a new CIS when its CIG is not configurable,
that connection shall fail, but pre-existing connections shall not be
affected.  However, currently hci_cc_le_set_cig_params deletes all CIS
of the CIG on error so it doesn't work, even though controller shall not
change CIG/CIS configuration if the command fails.

Fix by failing on command error only the connections that are not yet
bound, so that we keep the previous CIS configuration like the
controller does.

Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections")
Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 218da9b0fe8f1..559b6080706ce 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3799,6 +3799,22 @@ static u8 hci_cc_le_read_buffer_size_v2(struct hci_dev *hdev, void *data,
 	return rp->status;
 }
 
+static void hci_unbound_cis_failed(struct hci_dev *hdev, u8 cig, u8 status)
+{
+	struct hci_conn *conn, *tmp;
+
+	lockdep_assert_held(&hdev->lock);
+
+	list_for_each_entry_safe(conn, tmp, &hdev->conn_hash.list, list) {
+		if (conn->type != ISO_LINK || !bacmp(&conn->dst, BDADDR_ANY) ||
+		    conn->state == BT_OPEN || conn->iso_qos.ucast.cig != cig)
+			continue;
+
+		if (HCI_CONN_HANDLE_UNSET(conn->handle))
+			hci_conn_failed(conn, status);
+	}
+}
+
 static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data,
 				   struct sk_buff *skb)
 {
@@ -3820,12 +3836,15 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data,
 
 	hci_dev_lock(hdev);
 
+	/* BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 4, Part E page 2554
+	 *
+	 * If the Status return parameter is non-zero, then the state of the CIG
+	 * and its CIS configurations shall not be changed by the command. If
+	 * the CIG did not already exist, it shall not be created.
+	 */
 	if (status) {
-		while ((conn = hci_conn_hash_lookup_cig(hdev, rp->cig_id))) {
-			conn->state = BT_CLOSED;
-			hci_connect_cfm(conn, status);
-			hci_conn_del(conn);
-		}
+		/* Keep current configuration, fail only the unbound CIS */
+		hci_unbound_cis_failed(hdev, rp->cig_id, status);
 		goto unlock;
 	}
 
-- 
GitLab


From b5793de3cfaefef34a1fc9305c9fe3dbcd0ac792 Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Sat, 5 Aug 2023 19:08:42 +0300
Subject: [PATCH 1138/1806] Bluetooth: hci_conn: avoid checking uninitialized
 CIG/CIS ids

The CIS/CIG ids of ISO connections are defined only when the connection
is unicast.

Fix the lookup functions to check for unicast first. Ensure CIG/CIS
IDs have valid value also in state BT_OPEN.

Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h | 4 ++--
 net/bluetooth/hci_conn.c         | 2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index f4462c325e2ab..c53d74236e3a1 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1219,7 +1219,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != ISO_LINK)
+		if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY))
 			continue;
 
 		/* Match CIG ID if set */
@@ -1251,7 +1251,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_cig(struct hci_dev *hdev,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != ISO_LINK)
+		if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY))
 			continue;
 
 		if (handle == c->iso_qos.ucast.cig) {
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 4ad6af4e31450..234746721047f 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1866,6 +1866,8 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst,
 			return ERR_PTR(-ENOMEM);
 		cis->cleanup = cis_cleanup;
 		cis->dst_type = dst_type;
+		cis->iso_qos.ucast.cig = BT_ISO_QOS_CIG_UNSET;
+		cis->iso_qos.ucast.cis = BT_ISO_QOS_CIS_UNSET;
 	}
 
 	if (cis->state == BT_CONNECTED)
-- 
GitLab


From ea6f782fe5841249456c4b64c38b9c4508e05529 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 10 Aug 2023 14:25:15 +0200
Subject: [PATCH 1139/1806] ethernet: ldmvsw: mark ldmvsw_open() static

The function is exported for no reason and should just be static:

drivers/net/ethernet/sun/ldmvsw.c:127:5: error: no previous prototype for 'ldmvsw_open' [-Werror=missing-prototypes]

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Simon Horman <horms@kernel.org> # build-tested
Link: https://lore.kernel.org/r/20230810122528.1220434-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sun/ldmvsw.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index 734a817d3c945..a9a6670b5ff1f 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -124,7 +124,7 @@ static void vsw_set_rx_mode(struct net_device *dev)
 	return sunvnet_set_rx_mode_common(dev, port->vp);
 }
 
-int ldmvsw_open(struct net_device *dev)
+static int ldmvsw_open(struct net_device *dev)
 {
 	struct vnet_port *port = netdev_priv(dev);
 	struct vio_driver_state *vio = &port->vio;
@@ -136,7 +136,6 @@ int ldmvsw_open(struct net_device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ldmvsw_open);
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void vsw_poll_controller(struct net_device *dev)
-- 
GitLab


From 7191c140faa2631dd28d382ec53fb94d47c170cc Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 10 Aug 2023 14:25:16 +0200
Subject: [PATCH 1140/1806] ethernet: atarilance: mark init function static

The init function is only referenced locally, so it should be static to
avoid this warning:

drivers/net/ethernet/amd/atarilance.c:370:28: error: no previous prototype for 'atarilance_probe' [-Werror=missing-prototypes]

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Yang Yingliang <yangyingliang@huawei.com>
Link: https://lore.kernel.org/r/20230810122528.1220434-2-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/atarilance.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c
index ec704222925d8..751454d305c64 100644
--- a/drivers/net/ethernet/amd/atarilance.c
+++ b/drivers/net/ethernet/amd/atarilance.c
@@ -367,7 +367,7 @@ static void *slow_memcpy( void *dst, const void *src, size_t len )
 }
 
 
-struct net_device * __init atarilance_probe(void)
+static struct net_device * __init atarilance_probe(void)
 {
 	int i;
 	static int found;
-- 
GitLab


From 01b8539655635288dcd46366806abfacbb9b1f6c Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 9 Aug 2023 22:05:56 +0800
Subject: [PATCH 1141/1806] bpf: Remove unused declaration bpf_link_new_file()

Commit a3b80e107894 ("bpf: Allocate ID for bpf_link")
removed the implementation but not the declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/r/20230809140556.45836-1-yuehaibing@huawei.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/bpf.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index db3fe5a61b058..cfabbcf47bdb8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2120,7 +2120,6 @@ void bpf_link_cleanup(struct bpf_link_primer *primer);
 void bpf_link_inc(struct bpf_link *link);
 void bpf_link_put(struct bpf_link *link);
 int bpf_link_new_fd(struct bpf_link *link);
-struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd);
 struct bpf_link *bpf_link_get_from_fd(u32 ufd);
 struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
 
-- 
GitLab


From 6da4fea89d258ff4816e53345fcbc593104f98ec Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 11 Aug 2023 21:16:03 +0900
Subject: [PATCH 1142/1806] bpftool: fix perf help message

Currently, bpftool perf subcommand has typo with the help message.

    $ tools/bpf/bpftool/bpftool perf help
    Usage: bpftool perf { show | list }
           bpftool perf help }

Since this bpftool perf subcommand help message has the extra bracket,
this commit fix the typo by removing the extra bracket.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/r/20230811121603.17429-1-danieltimlee@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/bpf/bpftool/perf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c
index 91743445e4c7c..80de2874dabe4 100644
--- a/tools/bpf/bpftool/perf.c
+++ b/tools/bpf/bpftool/perf.c
@@ -236,7 +236,7 @@ static int do_help(int argc, char **argv)
 {
 	fprintf(stderr,
 		"Usage: %1$s %2$s { show | list }\n"
-		"       %1$s %2$s help }\n"
+		"       %1$s %2$s help\n"
 		"\n"
 		"       " HELP_SPEC_OPTIONS " }\n"
 		"",
-- 
GitLab


From e2142825c120d4317abf7160a0fc34b3de532586 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Fri, 11 Aug 2023 10:55:27 +0800
Subject: [PATCH 1143/1806] net: tcp: send zero-window ACK when no memory

For now, skb will be dropped when no memory, which makes client keep
retrans util timeout and it's not friendly to the users.

In this patch, we reply an ACK with zero-window in this case to update
the snd_wnd of the sender to 0. Therefore, the sender won't timeout the
connection and will probe the zero-window with the retransmits.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h |  3 ++-
 net/ipv4/tcp_input.c               | 18 ++++++++++++------
 net/ipv4/tcp_output.c              | 14 +++++++++++---
 3 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c2b15f7e55161..be3c858a2ebb7 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -164,7 +164,8 @@ enum inet_csk_ack_state_t {
 	ICSK_ACK_TIMER  = 2,
 	ICSK_ACK_PUSHED = 4,
 	ICSK_ACK_PUSHED2 = 8,
-	ICSK_ACK_NOW = 16	/* Send the next ACK immediately (once) */
+	ICSK_ACK_NOW = 16,	/* Send the next ACK immediately (once) */
+	ICSK_ACK_NOMEM = 32,
 };
 
 void inet_csk_init_xmit_timers(struct sock *sk,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8e96ebe373d7e..2ac0594834101 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5059,13 +5059,19 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 
 		/* Ok. In sequence. In window. */
 queue_and_out:
-		if (skb_queue_len(&sk->sk_receive_queue) == 0)
-			sk_forced_mem_schedule(sk, skb->truesize);
-		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
-			reason = SKB_DROP_REASON_PROTO_MEM;
-			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
+		if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+			/* TODO: maybe ratelimit these WIN 0 ACK ? */
+			inet_csk(sk)->icsk_ack.pending |=
+					(ICSK_ACK_NOMEM | ICSK_ACK_NOW);
+			inet_csk_schedule_ack(sk);
 			sk->sk_data_ready(sk);
-			goto drop;
+
+			if (skb_queue_len(&sk->sk_receive_queue)) {
+				reason = SKB_DROP_REASON_PROTO_MEM;
+				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
+				goto drop;
+			}
+			sk_forced_mem_schedule(sk, skb->truesize);
 		}
 
 		eaten = tcp_queue_rcv(sk, skb, &fragstolen);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c5412ee77fc8d..769a558159ee1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -257,11 +257,19 @@ EXPORT_SYMBOL(tcp_select_initial_window);
 static u16 tcp_select_window(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 old_win = tp->rcv_wnd;
-	u32 cur_win = tcp_receive_window(tp);
-	u32 new_win = __tcp_select_window(sk);
 	struct net *net = sock_net(sk);
+	u32 old_win = tp->rcv_wnd;
+	u32 cur_win, new_win;
+
+	/* Make the window 0 if we failed to queue the data because we
+	 * are out of memory. The window is temporary, so we don't store
+	 * it on the socket.
+	 */
+	if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM))
+		return 0;
 
+	cur_win = tcp_receive_window(tp);
+	new_win = __tcp_select_window(sk);
 	if (new_win < cur_win) {
 		/* Danger Will Robinson!
 		 * Don't update rcv_wup/rcv_wnd here or else
-- 
GitLab


From 800a666141de75baebb59b347b9c9e43d963e4da Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Fri, 11 Aug 2023 10:55:28 +0800
Subject: [PATCH 1144/1806] net: tcp: allow zero-window ACK update the window

Fow now, an ACK can update the window in following case, according to
the tcp_may_update_window():

1. the ACK acknowledged new data
2. the ACK has new data
3. the ACK expand the window and the seq of it is valid

Now, we allow the ACK update the window if the window is 0, and the
seq/ack of it is valid. This is for the case that the receiver replies
an zero-window ACK when it is under memory stress and can't queue the new
data.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2ac0594834101..d34d52fdfdb1e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3525,7 +3525,7 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp,
 {
 	return	after(ack, tp->snd_una) ||
 		after(ack_seq, tp->snd_wl1) ||
-		(ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd);
+		(ack_seq == tp->snd_wl1 && (nwin > tp->snd_wnd || !nwin));
 }
 
 /* If we update tp->snd_una, also update tp->bytes_acked */
-- 
GitLab


From e89688e3e97868451a5d05b38a9d2633d6785cd4 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Fri, 11 Aug 2023 10:55:29 +0800
Subject: [PATCH 1145/1806] net: tcp: fix unexcepted socket die when snd_wnd is
 0

In tcp_retransmit_timer(), a window shrunk connection will be regarded
as timeout if 'tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX'. This is not
right all the time.

The retransmits will become zero-window probes in tcp_retransmit_timer()
if the 'snd_wnd==0'. Therefore, the icsk->icsk_rto will come up to
TCP_RTO_MAX sooner or later.

However, the timer can be delayed and be triggered after 122877ms, not
TCP_RTO_MAX, as I tested.

Therefore, 'tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX' is always true
once the RTO come up to TCP_RTO_MAX, and the socket will die.

Fix this by replacing the 'tcp_jiffies32' with '(u32)icsk->icsk_timeout',
which is exact the timestamp of the timeout.

However, "tp->rcv_tstamp" can restart from idle, then tp->rcv_tstamp
could already be a long time (minutes or hours) in the past even on the
first RTO. So we double check the timeout with the duration of the
retransmission.

Meanwhile, making "2 * TCP_RTO_MAX" as the timeout to avoid the socket
dying too soon.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Link: https://lore.kernel.org/netdev/CADxym3YyMiO+zMD4zj03YPM3FBi-1LHi6gSD2XT8pyAMM096pg@mail.gmail.com/
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index d45c96c7f5a44..f2a52c11e044e 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -454,6 +454,22 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 			  req->timeout << req->num_timeout, TCP_RTO_MAX);
 }
 
+static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
+				     const struct sk_buff *skb)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	const int timeout = TCP_RTO_MAX * 2;
+	u32 rcv_delta, rtx_delta;
+
+	rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp;
+	if (rcv_delta <= timeout)
+		return false;
+
+	rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) -
+			(tp->retrans_stamp ?: tcp_skb_timestamp(skb)));
+
+	return rtx_delta > timeout;
+}
 
 /**
  *  tcp_retransmit_timer() - The TCP retransmit timeout handler
@@ -519,7 +535,7 @@ void tcp_retransmit_timer(struct sock *sk)
 					    tp->snd_una, tp->snd_nxt);
 		}
 #endif
-		if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) {
+		if (tcp_rtx_probe0_timed_out(sk, skb)) {
 			tcp_write_err(sk);
 			goto out;
 		}
-- 
GitLab


From 031c44b7527aec2f22ddaae4bcd8b085ff810ec4 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Fri, 11 Aug 2023 10:55:30 +0800
Subject: [PATCH 1146/1806] net: tcp: refactor the dbg message in
 tcp_retransmit_timer()

The debug message in tcp_retransmit_timer() is slightly wrong, because
they could be printed even if we did not receive a new ACK packet from
the remote peer.

Change it to probing zero-window, as it is a expected case now. The
description may be not correct.

Adding the duration since the last ACK we received, and the duration of
the retransmission, which are useful for debugging.

And the message now like this:

Probing zero-window on 127.0.0.1:9999/46946, seq=3737778959:3737791503, recv 209ms ago, lasting 209ms
Probing zero-window on 127.0.0.1:9999/46946, seq=3737778959:3737791503, recv 404ms ago, lasting 408ms
Probing zero-window on 127.0.0.1:9999/46946, seq=3737778959:3737791503, recv 812ms ago, lasting 1224ms

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index f2a52c11e044e..74c70fc1003c6 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -519,20 +519,23 @@ void tcp_retransmit_timer(struct sock *sk)
 		 * we cannot allow such beasts to hang infinitely.
 		 */
 		struct inet_sock *inet = inet_sk(sk);
+		u32 rtx_delta;
+
+		rtx_delta = tcp_time_stamp(tp) - (tp->retrans_stamp ?: tcp_skb_timestamp(skb));
 		if (sk->sk_family == AF_INET) {
-			net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
-					    &inet->inet_daddr,
-					    ntohs(inet->inet_dport),
-					    inet->inet_num,
-					    tp->snd_una, tp->snd_nxt);
+			net_dbg_ratelimited("Probing zero-window on %pI4:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n",
+				&inet->inet_daddr, ntohs(inet->inet_dport),
+				inet->inet_num, tp->snd_una, tp->snd_nxt,
+				jiffies_to_msecs(jiffies - tp->rcv_tstamp),
+				rtx_delta);
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (sk->sk_family == AF_INET6) {
-			net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
-					    &sk->sk_v6_daddr,
-					    ntohs(inet->inet_dport),
-					    inet->inet_num,
-					    tp->snd_una, tp->snd_nxt);
+			net_dbg_ratelimited("Probing zero-window on %pI6:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n",
+				&sk->sk_v6_daddr, ntohs(inet->inet_dport),
+				inet->inet_num, tp->snd_una, tp->snd_nxt,
+				jiffies_to_msecs(jiffies - tp->rcv_tstamp),
+				rtx_delta);
 		}
 #endif
 		if (tcp_rtx_probe0_timed_out(sk, skb)) {
-- 
GitLab


From 8fe08d70a2b61b35a0a1235c78cf321e7528351f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 11 Aug 2023 07:22:26 +0000
Subject: [PATCH 1147/1806] netlink: convert nlk->flags to atomic flags

sk_diag_put_flags(), netlink_setsockopt(), netlink_getsockopt()
and others use nlk->flags without correct locking.

Use set_bit(), clear_bit(), test_bit(), assign_bit() to remove
data-races.

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 90 ++++++++++++++--------------------------
 net/netlink/af_netlink.h | 22 ++++++----
 net/netlink/diag.c       | 10 ++---
 3 files changed, 48 insertions(+), 74 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 96c605e452358..642b9d382fb46 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -84,7 +84,7 @@ struct listeners {
 
 static inline int netlink_is_kernel(struct sock *sk)
 {
-	return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET;
+	return nlk_test_bit(KERNEL_SOCKET, sk);
 }
 
 struct netlink_table *nl_table __read_mostly;
@@ -349,9 +349,7 @@ static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src,
 
 static void netlink_overrun(struct sock *sk)
 {
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (!(nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)) {
+	if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) {
 		if (!test_and_set_bit(NETLINK_S_CONGESTED,
 				      &nlk_sk(sk)->state)) {
 			sk->sk_err = ENOBUFS;
@@ -1407,9 +1405,7 @@ EXPORT_SYMBOL_GPL(netlink_has_listeners);
 
 bool netlink_strict_get_check(struct sk_buff *skb)
 {
-	const struct netlink_sock *nlk = nlk_sk(NETLINK_CB(skb).sk);
-
-	return nlk->flags & NETLINK_F_STRICT_CHK;
+	return nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk);
 }
 EXPORT_SYMBOL_GPL(netlink_strict_get_check);
 
@@ -1455,7 +1451,7 @@ static void do_one_broadcast(struct sock *sk,
 		return;
 
 	if (!net_eq(sock_net(sk), p->net)) {
-		if (!(nlk->flags & NETLINK_F_LISTEN_ALL_NSID))
+		if (!nlk_test_bit(LISTEN_ALL_NSID, sk))
 			return;
 
 		if (!peernet_has_id(sock_net(sk), p->net))
@@ -1488,7 +1484,7 @@ static void do_one_broadcast(struct sock *sk,
 		netlink_overrun(sk);
 		/* Clone failed. Notify ALL listeners. */
 		p->failure = 1;
-		if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
+		if (nlk_test_bit(BROADCAST_SEND_ERROR, sk))
 			p->delivery_failure = 1;
 		goto out;
 	}
@@ -1510,7 +1506,7 @@ static void do_one_broadcast(struct sock *sk,
 	val = netlink_broadcast_deliver(sk, p->skb2);
 	if (val < 0) {
 		netlink_overrun(sk);
-		if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
+		if (nlk_test_bit(BROADCAST_SEND_ERROR, sk))
 			p->delivery_failure = 1;
 	} else {
 		p->congested |= val;
@@ -1604,7 +1600,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p)
 	    !test_bit(p->group - 1, nlk->groups))
 		goto out;
 
-	if (p->code == ENOBUFS && nlk->flags & NETLINK_F_RECV_NO_ENOBUFS) {
+	if (p->code == ENOBUFS && nlk_test_bit(RECV_NO_ENOBUFS, sk)) {
 		ret = 1;
 		goto out;
 	}
@@ -1668,7 +1664,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
 	unsigned int val = 0;
-	int err;
+	int nr = -1;
 
 	if (level != SOL_NETLINK)
 		return -ENOPROTOOPT;
@@ -1679,14 +1675,12 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 
 	switch (optname) {
 	case NETLINK_PKTINFO:
-		if (val)
-			nlk->flags |= NETLINK_F_RECV_PKTINFO;
-		else
-			nlk->flags &= ~NETLINK_F_RECV_PKTINFO;
-		err = 0;
+		nr = NETLINK_F_RECV_PKTINFO;
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
 	case NETLINK_DROP_MEMBERSHIP: {
+		int err;
+
 		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
@@ -1706,61 +1700,38 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind)
 			nlk->netlink_unbind(sock_net(sk), val);
 
-		err = 0;
 		break;
 	}
 	case NETLINK_BROADCAST_ERROR:
-		if (val)
-			nlk->flags |= NETLINK_F_BROADCAST_SEND_ERROR;
-		else
-			nlk->flags &= ~NETLINK_F_BROADCAST_SEND_ERROR;
-		err = 0;
+		nr = NETLINK_F_BROADCAST_SEND_ERROR;
 		break;
 	case NETLINK_NO_ENOBUFS:
+		assign_bit(NETLINK_F_RECV_NO_ENOBUFS, &nlk->flags, val);
 		if (val) {
-			nlk->flags |= NETLINK_F_RECV_NO_ENOBUFS;
 			clear_bit(NETLINK_S_CONGESTED, &nlk->state);
 			wake_up_interruptible(&nlk->wait);
-		} else {
-			nlk->flags &= ~NETLINK_F_RECV_NO_ENOBUFS;
 		}
-		err = 0;
 		break;
 	case NETLINK_LISTEN_ALL_NSID:
 		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST))
 			return -EPERM;
-
-		if (val)
-			nlk->flags |= NETLINK_F_LISTEN_ALL_NSID;
-		else
-			nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID;
-		err = 0;
+		nr = NETLINK_F_LISTEN_ALL_NSID;
 		break;
 	case NETLINK_CAP_ACK:
-		if (val)
-			nlk->flags |= NETLINK_F_CAP_ACK;
-		else
-			nlk->flags &= ~NETLINK_F_CAP_ACK;
-		err = 0;
+		nr = NETLINK_F_CAP_ACK;
 		break;
 	case NETLINK_EXT_ACK:
-		if (val)
-			nlk->flags |= NETLINK_F_EXT_ACK;
-		else
-			nlk->flags &= ~NETLINK_F_EXT_ACK;
-		err = 0;
+		nr = NETLINK_F_EXT_ACK;
 		break;
 	case NETLINK_GET_STRICT_CHK:
-		if (val)
-			nlk->flags |= NETLINK_F_STRICT_CHK;
-		else
-			nlk->flags &= ~NETLINK_F_STRICT_CHK;
-		err = 0;
+		nr = NETLINK_F_STRICT_CHK;
 		break;
 	default:
-		err = -ENOPROTOOPT;
+		return -ENOPROTOOPT;
 	}
-	return err;
+	if (nr >= 0)
+		assign_bit(nr, &nlk->flags, val);
+	return 0;
 }
 
 static int netlink_getsockopt(struct socket *sock, int level, int optname,
@@ -1827,7 +1798,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		return -EINVAL;
 
 	len = sizeof(int);
-	val = nlk->flags & flag ? 1 : 0;
+	val = test_bit(flag, &nlk->flags);
 
 	if (put_user(len, optlen) ||
 	    copy_to_user(optval, &val, len))
@@ -2004,9 +1975,9 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		msg->msg_namelen = sizeof(*addr);
 	}
 
-	if (nlk->flags & NETLINK_F_RECV_PKTINFO)
+	if (nlk_test_bit(RECV_PKTINFO, sk))
 		netlink_cmsg_recv_pktinfo(msg, skb);
-	if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID)
+	if (nlk_test_bit(LISTEN_ALL_NSID, sk))
 		netlink_cmsg_listen_all_nsid(sk, msg, skb);
 
 	memset(&scm, 0, sizeof(scm));
@@ -2083,7 +2054,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 		goto out_sock_release;
 
 	nlk = nlk_sk(sk);
-	nlk->flags |= NETLINK_F_KERNEL_SOCKET;
+	set_bit(NETLINK_F_KERNEL_SOCKET, &nlk->flags);
 
 	netlink_table_grab();
 	if (!nl_table[unit].registered) {
@@ -2218,7 +2189,7 @@ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb,
 	nl_dump_check_consistent(cb, nlh);
 	memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno));
 
-	if (extack->_msg && nlk->flags & NETLINK_F_EXT_ACK) {
+	if (extack->_msg && test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) {
 		nlh->nlmsg_flags |= NLM_F_ACK_TLVS;
 		if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg))
 			nlmsg_end(skb, nlh);
@@ -2347,8 +2318,8 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 			 const struct nlmsghdr *nlh,
 			 struct netlink_dump_control *control)
 {
-	struct netlink_sock *nlk, *nlk2;
 	struct netlink_callback *cb;
+	struct netlink_sock *nlk;
 	struct sock *sk;
 	int ret;
 
@@ -2383,8 +2354,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	cb->min_dump_alloc = control->min_dump_alloc;
 	cb->skb = skb;
 
-	nlk2 = nlk_sk(NETLINK_CB(skb).sk);
-	cb->strict_check = !!(nlk2->flags & NETLINK_F_STRICT_CHK);
+	cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk);
 
 	if (control->start) {
 		cb->extack = control->extack;
@@ -2428,7 +2398,7 @@ netlink_ack_tlv_len(struct netlink_sock *nlk, int err,
 {
 	size_t tlvlen;
 
-	if (!extack || !(nlk->flags & NETLINK_F_EXT_ACK))
+	if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags))
 		return 0;
 
 	tlvlen = 0;
@@ -2500,7 +2470,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 	 * requests to cap the error message, and get extra error data if
 	 * requested.
 	 */
-	if (err && !(nlk->flags & NETLINK_F_CAP_ACK))
+	if (err && !test_bit(NETLINK_F_CAP_ACK, &nlk->flags))
 		payload += nlmsg_len(nlh);
 	else
 		flags |= NLM_F_CAPPED;
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index fd424cd63f31c..2145979b9986a 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -8,14 +8,16 @@
 #include <net/sock.h>
 
 /* flags */
-#define NETLINK_F_KERNEL_SOCKET		0x1
-#define NETLINK_F_RECV_PKTINFO		0x2
-#define NETLINK_F_BROADCAST_SEND_ERROR	0x4
-#define NETLINK_F_RECV_NO_ENOBUFS	0x8
-#define NETLINK_F_LISTEN_ALL_NSID	0x10
-#define NETLINK_F_CAP_ACK		0x20
-#define NETLINK_F_EXT_ACK		0x40
-#define NETLINK_F_STRICT_CHK		0x80
+enum {
+	NETLINK_F_KERNEL_SOCKET,
+	NETLINK_F_RECV_PKTINFO,
+	NETLINK_F_BROADCAST_SEND_ERROR,
+	NETLINK_F_RECV_NO_ENOBUFS,
+	NETLINK_F_LISTEN_ALL_NSID,
+	NETLINK_F_CAP_ACK,
+	NETLINK_F_EXT_ACK,
+	NETLINK_F_STRICT_CHK,
+};
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
 #define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
@@ -23,10 +25,10 @@
 struct netlink_sock {
 	/* struct sock has to be the first member of netlink_sock */
 	struct sock		sk;
+	unsigned long		flags;
 	u32			portid;
 	u32			dst_portid;
 	u32			dst_group;
-	u32			flags;
 	u32			subscriptions;
 	u32			ngroups;
 	unsigned long		*groups;
@@ -56,6 +58,8 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk)
 	return container_of(sk, struct netlink_sock, sk);
 }
 
+#define nlk_test_bit(nr, sk) test_bit(NETLINK_F_##nr, &nlk_sk(sk)->flags)
+
 struct netlink_table {
 	struct rhashtable	hash;
 	struct hlist_head	mc_list;
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index e4f21b1067bcc..9c4f231be2757 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -27,15 +27,15 @@ static int sk_diag_put_flags(struct sock *sk, struct sk_buff *skb)
 
 	if (nlk->cb_running)
 		flags |= NDIAG_FLAG_CB_RUNNING;
-	if (nlk->flags & NETLINK_F_RECV_PKTINFO)
+	if (nlk_test_bit(RECV_PKTINFO, sk))
 		flags |= NDIAG_FLAG_PKTINFO;
-	if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
+	if (nlk_test_bit(BROADCAST_SEND_ERROR, sk))
 		flags |= NDIAG_FLAG_BROADCAST_ERROR;
-	if (nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)
+	if (nlk_test_bit(RECV_NO_ENOBUFS, sk))
 		flags |= NDIAG_FLAG_NO_ENOBUFS;
-	if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID)
+	if (nlk_test_bit(LISTEN_ALL_NSID, sk))
 		flags |= NDIAG_FLAG_LISTEN_ALL_NSID;
-	if (nlk->flags & NETLINK_F_CAP_ACK)
+	if (nlk_test_bit(CAP_ACK, sk))
 		flags |= NDIAG_FLAG_CAP_ACK;
 
 	return nla_put_u32(skb, NETLINK_DIAG_FLAGS, flags);
-- 
GitLab


From 2b8893b639e4ad38fa0a941d665e827963ede727 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 11 Aug 2023 17:50:10 +0800
Subject: [PATCH 1148/1806] net/rds: Remove unused function declarations

Commit 39de8281791c ("RDS: Main header file") declared but never implemented
rds_trans_init() and rds_trans_exit(), remove it.
Commit d37c9359056f ("RDS: Move loop-only function to loop.c") removed the
implementation rds_message_inc_free() but not the declaration.

Since commit 55b7ed0b582f ("RDS: Common RDMA transport code")
rds_rdma_conn_connect() is never implemented and used.
rds_tcp_map_seq() is never implemented and used since
commit 70041088e3b9 ("RDS: Add TCP transport to RDS").

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/rdma_transport.h | 1 -
 net/rds/rds.h            | 3 ---
 net/rds/tcp.h            | 1 -
 3 files changed, 5 deletions(-)

diff --git a/net/rds/rdma_transport.h b/net/rds/rdma_transport.h
index ca4c3a6670910..d2fdb15295856 100644
--- a/net/rds/rdma_transport.h
+++ b/net/rds/rdma_transport.h
@@ -17,7 +17,6 @@
  */
 #define RDS_RDMA_REJ_INCOMPAT		1
 
-int rds_rdma_conn_connect(struct rds_connection *conn);
 int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
 			      struct rdma_cm_event *event);
 int rds6_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
diff --git a/net/rds/rds.h b/net/rds/rds.h
index d35d1fc398076..dc360252c5157 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -863,7 +863,6 @@ int rds_message_next_extension(struct rds_header *hdr,
 			       unsigned int *pos, void *buf, unsigned int *buflen);
 int rds_message_add_rdma_dest_extension(struct rds_header *hdr, u32 r_key, u32 offset);
 int rds_message_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
-void rds_message_inc_free(struct rds_incoming *inc);
 void rds_message_addref(struct rds_message *rm);
 void rds_message_put(struct rds_message *rm);
 void rds_message_wait(struct rds_message *rm);
@@ -1013,7 +1012,5 @@ void rds_trans_put(struct rds_transport *trans);
 unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter,
 				       unsigned int avail);
 struct rds_transport *rds_trans_get(int t_type);
-int rds_trans_init(void);
-void rds_trans_exit(void);
 
 #endif
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index f8b5930d7b343..053aa7da87efa 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -56,7 +56,6 @@ void rds_tcp_restore_callbacks(struct socket *sock,
 			       struct rds_tcp_connection *tc);
 u32 rds_tcp_write_seq(struct rds_tcp_connection *tc);
 u32 rds_tcp_snd_una(struct rds_tcp_connection *tc);
-u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq);
 extern struct rds_transport rds_tcp_transport;
 void rds_tcp_accept_work(struct sock *sk);
 int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
-- 
GitLab


From 2045b3938ffad5bc986f68b9bb44acb188c73792 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 11 Aug 2023 18:50:05 +0800
Subject: [PATCH 1149/1806] net: e1000: Remove unused declarations

Commit 675ad47375c7 ("e1000: Use netdev_<level>, pr_<level> and dev_<level>")
declared but never implemented e1000_get_hw_dev_name().
Commit 1532ecea1deb ("e1000: drop dead pcie code from e1000")
removed e1000_check_mng_mode()/e1000_blink_led_start() but not the declarations.
Commit c46b59b241ec ("e1000: Remove unused function e1000_mta_set.")
removed e1000_mta_set() but not its declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/e1000/e1000.h    | 1 -
 drivers/net/ethernet/intel/e1000/e1000_hw.h | 3 ---
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000/e1000.h b/drivers/net/ethernet/intel/e1000/e1000.h
index 4817eb13ca6f8..75f3fd1d8d6ee 100644
--- a/drivers/net/ethernet/intel/e1000/e1000.h
+++ b/drivers/net/ethernet/intel/e1000/e1000.h
@@ -347,6 +347,5 @@ bool e1000_has_link(struct e1000_adapter *adapter);
 void e1000_power_up_phy(struct e1000_adapter *);
 void e1000_set_ethtool_ops(struct net_device *netdev);
 void e1000_check_options(struct e1000_adapter *adapter);
-char *e1000_get_hw_dev_name(struct e1000_hw *hw);
 
 #endif /* _E1000_H_ */
diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.h b/drivers/net/ethernet/intel/e1000/e1000_hw.h
index b57a04954ccfb..95cdd17134e5e 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_hw.h
+++ b/drivers/net/ethernet/intel/e1000/e1000_hw.h
@@ -343,7 +343,6 @@ struct e1000_host_mng_dhcp_cookie {
 };
 #endif
 
-bool e1000_check_mng_mode(struct e1000_hw *hw);
 s32 e1000_read_eeprom(struct e1000_hw *hw, u16 reg, u16 words, u16 * data);
 s32 e1000_validate_eeprom_checksum(struct e1000_hw *hw);
 s32 e1000_update_eeprom_checksum(struct e1000_hw *hw);
@@ -352,7 +351,6 @@ s32 e1000_read_mac_addr(struct e1000_hw *hw);
 
 /* Filters (multicast, vlan, receive) */
 u32 e1000_hash_mc_addr(struct e1000_hw *hw, u8 * mc_addr);
-void e1000_mta_set(struct e1000_hw *hw, u32 hash_value);
 void e1000_rar_set(struct e1000_hw *hw, u8 * mc_addr, u32 rar_index);
 void e1000_write_vfta(struct e1000_hw *hw, u32 offset, u32 value);
 
@@ -361,7 +359,6 @@ s32 e1000_setup_led(struct e1000_hw *hw);
 s32 e1000_cleanup_led(struct e1000_hw *hw);
 s32 e1000_led_on(struct e1000_hw *hw);
 s32 e1000_led_off(struct e1000_hw *hw);
-s32 e1000_blink_led_start(struct e1000_hw *hw);
 
 /* Adaptive IFS Functions */
 
-- 
GitLab


From fcbb797458e123b3f304606199ded27b042118b1 Mon Sep 17 00:00:00 2001
From: Zheng Zengkai <zhengzengkai@huawei.com>
Date: Fri, 11 Aug 2023 19:06:58 +0800
Subject: [PATCH 1150/1806] et131x: Use pci_dev_id() to simplify the code

PCI core API pci_dev_id() can be used to get the BDF number for a pci
device. We don't need to compose it manually. Use pci_dev_id() to
simplify the code a little bit.

Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/agere/et131x.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 5fab589b3ddf6..3d9220f9c9fe7 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -3982,8 +3982,7 @@ static int et131x_pci_setup(struct pci_dev *pdev,
 	}
 
 	adapter->mii_bus->name = "et131x_eth_mii";
-	snprintf(adapter->mii_bus->id, MII_BUS_ID_SIZE, "%x",
-		 (adapter->pdev->bus->number << 8) | adapter->pdev->devfn);
+	snprintf(adapter->mii_bus->id, MII_BUS_ID_SIZE, "%x", pci_dev_id(adapter->pdev));
 	adapter->mii_bus->priv = netdev;
 	adapter->mii_bus->read = et131x_mdio_read;
 	adapter->mii_bus->write = et131x_mdio_write;
-- 
GitLab


From 6ecb2ced346f6d2209428ef86cae83269af2d744 Mon Sep 17 00:00:00 2001
From: Zheng Zengkai <zhengzengkai@huawei.com>
Date: Fri, 11 Aug 2023 19:06:59 +0800
Subject: [PATCH 1151/1806] tg3: Use pci_dev_id() to simplify the code

PCI core API pci_dev_id() can be used to get the BDF number for a pci
device. We don't need to compose it manually. Use pci_dev_id() to
simplify the code a little bit.

Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 5ef073a79ce94..7f956cf36337e 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -1539,8 +1539,7 @@ static int tg3_mdio_init(struct tg3 *tp)
 		return -ENOMEM;
 
 	tp->mdio_bus->name     = "tg3 mdio bus";
-	snprintf(tp->mdio_bus->id, MII_BUS_ID_SIZE, "%x",
-		 (tp->pdev->bus->number << 8) | tp->pdev->devfn);
+	snprintf(tp->mdio_bus->id, MII_BUS_ID_SIZE, "%x", pci_dev_id(tp->pdev));
 	tp->mdio_bus->priv     = tp;
 	tp->mdio_bus->parent   = &tp->pdev->dev;
 	tp->mdio_bus->read     = &tg3_mdio_read;
-- 
GitLab


From adc4d18538ec5e7ae44323130257c2ba47da2d57 Mon Sep 17 00:00:00 2001
From: Zheng Zengkai <zhengzengkai@huawei.com>
Date: Fri, 11 Aug 2023 19:07:00 +0800
Subject: [PATCH 1152/1806] net: smsc: Use pci_dev_id() to simplify the code

PCI core API pci_dev_id() can be used to get the BDF number for a pci
device. We don't need to compose it manually. Use pci_dev_id() to
simplify the code a little bit.

Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/smsc/smsc9420.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c
index 3b26f1d86beba..e1c4a11c1f181 100644
--- a/drivers/net/ethernet/smsc/smsc9420.c
+++ b/drivers/net/ethernet/smsc/smsc9420.c
@@ -1144,8 +1144,7 @@ static int smsc9420_mii_init(struct net_device *dev)
 		goto err_out_1;
 	}
 	pd->mii_bus->name = DRV_MDIONAME;
-	snprintf(pd->mii_bus->id, MII_BUS_ID_SIZE, "%x",
-		(pd->pdev->bus->number << 8) | pd->pdev->devfn);
+	snprintf(pd->mii_bus->id, MII_BUS_ID_SIZE, "%x", pci_dev_id(pd->pdev));
 	pd->mii_bus->priv = pd;
 	pd->mii_bus->read = smsc9420_mii_read;
 	pd->mii_bus->write = smsc9420_mii_write;
-- 
GitLab


From ca51d1356071e40d48169a308e996be779be56d4 Mon Sep 17 00:00:00 2001
From: Zheng Zengkai <zhengzengkai@huawei.com>
Date: Fri, 11 Aug 2023 19:07:01 +0800
Subject: [PATCH 1153/1806] net: tc35815: Use pci_dev_id() to simplify the code

PCI core API pci_dev_id() can be used to get the BDF number for a pci
device. We don't need to compose it manually. Use pci_dev_id() to
simplify the code a little bit.

Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/toshiba/tc35815.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index b50be67b398b1..14cf6ecf6d0df 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -667,8 +667,7 @@ static int tc_mii_init(struct net_device *dev)
 	lp->mii_bus->name = "tc35815_mii_bus";
 	lp->mii_bus->read = tc_mdio_read;
 	lp->mii_bus->write = tc_mdio_write;
-	snprintf(lp->mii_bus->id, MII_BUS_ID_SIZE, "%x",
-		 (lp->pci_dev->bus->number << 8) | lp->pci_dev->devfn);
+	snprintf(lp->mii_bus->id, MII_BUS_ID_SIZE, "%x", pci_dev_id(lp->pci_dev));
 	lp->mii_bus->priv = dev;
 	lp->mii_bus->parent = &lp->pci_dev->dev;
 	err = mdiobus_register(lp->mii_bus);
-- 
GitLab


From cf9b107f5fdddcd73b77169c30949d5e12e56eae Mon Sep 17 00:00:00 2001
From: Zheng Zengkai <zhengzengkai@huawei.com>
Date: Fri, 11 Aug 2023 19:07:02 +0800
Subject: [PATCH 1154/1806] net: ngbe: use pci_dev_id() to simplify the code

PCI core API pci_dev_id() can be used to get the BDF number for a pci
device. We don't need to compose it manually. Use pci_dev_id() to
simplify the code a little bit.

Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
index cc2f325a52f78..fe20f02ecb3aa 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
@@ -266,8 +266,7 @@ int ngbe_mdio_init(struct wx *wx)
 		mii_bus->write_c45 = ngbe_phy_write_reg_mdi_c45;
 	}
 
-	snprintf(mii_bus->id, MII_BUS_ID_SIZE, "ngbe-%x",
-		 (pdev->bus->number << 8) | pdev->devfn);
+	snprintf(mii_bus->id, MII_BUS_ID_SIZE, "ngbe-%x", pci_dev_id(pdev));
 	ret = devm_mdiobus_register(&pdev->dev, mii_bus);
 	if (ret)
 		return ret;
-- 
GitLab


From 2f4503f94c5d81d1589842bfb457be466c8c670b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 11 Aug 2023 14:53:52 +0300
Subject: [PATCH 1155/1806] net: pcs: lynx: fix lynx_pcs_link_up_sgmii() not
 doing anything in fixed-link mode

lynx_pcs_link_up_sgmii() is supposed to update the PCS speed and duplex
for the non-inband operating modes, and prior to the blamed commit, it
did just that, but a mistake sneaked into the conversion and reversed
the condition.

It is easy for this to go undetected on platforms that also initialize
the PCS in the bootloader, because Linux doesn't reset it (although
maybe it should). The nature of the bug is that phylink will not touch
the IF_MODE_HALF_DUPLEX | IF_MODE_SPEED_MSK fields when it should, and
it will apparently keep working if the previous values set by the
bootloader were correct.

Fixes: c689a6528c22 ("net: pcs: lynx: update PCS driver to use neg_mode")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/pcs/pcs-lynx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c
index 9021b96d4f9df..dc3962b2aa6b0 100644
--- a/drivers/net/pcs/pcs-lynx.c
+++ b/drivers/net/pcs/pcs-lynx.c
@@ -216,7 +216,7 @@ static void lynx_pcs_link_up_sgmii(struct mdio_device *pcs,
 	/* The PCS needs to be configured manually only
 	 * when not operating on in-band mode
 	 */
-	if (neg_mode != PHYLINK_PCS_NEG_INBAND_ENABLED)
+	if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED)
 		return;
 
 	if (duplex == DUPLEX_HALF)
-- 
GitLab


From f614a29d6ca6962139b0eb36b985e3dda80258a6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=B6rn-Thorben=20Hinz?= <jthinz@mailbox.tu-berlin.de>
Date: Fri, 11 Aug 2023 19:33:57 +0200
Subject: [PATCH 1156/1806] net: Remove leftover include from nftables.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit db3685b4046f ("net: remove obsolete members from struct net")
removed the uses of struct list_head from this header, without removing
the corresponding included header.

Signed-off-by: Jörn-Thorben Hinz <jthinz@mailbox.tu-berlin.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/nftables.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index 8c77832d02404..cc8060c017d5f 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -2,8 +2,6 @@
 #ifndef _NETNS_NFTABLES_H_
 #define _NETNS_NFTABLES_H_
 
-#include <linux/list.h>
-
 struct netns_nftables {
 	u8			gencursor;
 };
-- 
GitLab


From 131a627751e3474bc8e33009c032feecfe8d879f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:14 +0200
Subject: [PATCH 1157/1806] mptcp: avoid unneeded mptcp_token_destroy() calls

The MPTCP protocol currently clears the msk token both at connect() and
listen() time. That is needed to deal with failing connect() calls that
can create a new token while leaving the sk in TCP_CLOSE,SS_UNCONNECTED
status and thus allowing later connect() and/or listen() calls.

Let's deal with such failures explicitly, cleaning the token in a timely
manner and avoid the confusing early mptcp_token_destroy().

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 48e649fe2360d..abb310548c37b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3594,7 +3594,6 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (IS_ERR(ssock))
 		return PTR_ERR(ssock);
 
-	mptcp_token_destroy(msk);
 	inet_sk_state_store(sk, TCP_SYN_SENT);
 	subflow = mptcp_subflow_ctx(ssock->sk);
 #ifdef CONFIG_TCP_MD5SIG
@@ -3624,6 +3623,8 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	 * subflow_finish_connect()
 	 */
 	if (unlikely(err && err != -EINPROGRESS)) {
+		/* avoid leaving a dangling token in an unconnected socket */
+		mptcp_token_destroy(msk);
 		inet_sk_state_store(sk, inet_sk_state_load(ssock->sk));
 		return err;
 	}
@@ -3713,7 +3714,6 @@ static int mptcp_listen(struct socket *sock, int backlog)
 		goto unlock;
 	}
 
-	mptcp_token_destroy(msk);
 	inet_sk_state_store(sk, TCP_LISTEN);
 	sock_set_flag(sk, SOCK_RCU_FREE);
 
-- 
GitLab


From ccae357c1c6a76c3b46f12ae18d7679d871c9390 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:15 +0200
Subject: [PATCH 1158/1806] mptcp: avoid additional __inet_stream_connect()
 call

The mptcp protocol maintains an additional socket just to easily
invoke a few stream operations on the first subflow. One of them is
__inet_stream_connect().

We are going to remove the first subflow socket soon, so avoid
the additional indirection via at connect time, calling directly
into the sock-level connect() ops.

The sk-level connect never return -EINPROGRESS, cleanup the error
path accordingly. Additionally, the ssk status on error is always
TCP_CLOSE. Avoid unneeded access to the subflow sk state.

No functional change intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 49 +++++++++++++++++++++++++++++---------------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index abb310548c37b..b888d6339c805 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3589,22 +3589,24 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct socket *ssock;
 	int err = -EINVAL;
+	struct sock *ssk;
 
 	ssock = __mptcp_nmpc_socket(msk);
 	if (IS_ERR(ssock))
 		return PTR_ERR(ssock);
 
 	inet_sk_state_store(sk, TCP_SYN_SENT);
-	subflow = mptcp_subflow_ctx(ssock->sk);
+	ssk = msk->first;
+	subflow = mptcp_subflow_ctx(ssk);
 #ifdef CONFIG_TCP_MD5SIG
 	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
 	 * TCP option space.
 	 */
-	if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info))
+	if (rcu_access_pointer(tcp_sk(ssk)->md5sig_info))
 		mptcp_subflow_early_fallback(msk, subflow);
 #endif
-	if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) {
-		MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT);
+	if (subflow->request_mptcp && mptcp_token_new_connect(ssk)) {
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT);
 		mptcp_subflow_early_fallback(msk, subflow);
 	}
 	if (likely(!__mptcp_check_fallback(msk)))
@@ -3613,27 +3615,42 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	/* if reaching here via the fastopen/sendmsg path, the caller already
 	 * acquired the subflow socket lock, too.
 	 */
-	if (msk->fastopening)
-		err = __inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK, 1);
-	else
-		err = inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK);
-	inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect;
+	if (!msk->fastopening)
+		lock_sock(ssk);
+
+	/* the following mirrors closely a very small chunk of code from
+	 * __inet_stream_connect()
+	 */
+	if (ssk->sk_state != TCP_CLOSE)
+		goto out;
+
+	if (BPF_CGROUP_PRE_CONNECT_ENABLED(ssk)) {
+		err = ssk->sk_prot->pre_connect(ssk, uaddr, addr_len);
+		if (err)
+			goto out;
+	}
+
+	err = ssk->sk_prot->connect(ssk, uaddr, addr_len);
+	if (err < 0)
+		goto out;
+
+	inet_sk(sk)->defer_connect = inet_sk(ssk)->defer_connect;
+
+out:
+	if (!msk->fastopening)
+		release_sock(ssk);
 
 	/* on successful connect, the msk state will be moved to established by
 	 * subflow_finish_connect()
 	 */
-	if (unlikely(err && err != -EINPROGRESS)) {
+	if (unlikely(err)) {
 		/* avoid leaving a dangling token in an unconnected socket */
 		mptcp_token_destroy(msk);
-		inet_sk_state_store(sk, inet_sk_state_load(ssock->sk));
+		inet_sk_state_store(sk, TCP_CLOSE);
 		return err;
 	}
 
-	mptcp_copy_inaddrs(sk, ssock->sk);
-
-	/* silence EINPROGRESS and let the caller inet_stream_connect
-	 * handle the connection in progress
-	 */
+	mptcp_copy_inaddrs(sk, ssk);
 	return 0;
 }
 
-- 
GitLab


From cfb63e50d319ee5d11254c83d3ad2b135b8735db Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:16 +0200
Subject: [PATCH 1159/1806] mptcp: avoid subflow socket usage in
 mptcp_get_port()

We are going to remove the first subflow socket soon, so avoid
accessing it in mptcp_get_port(). Instead, access directly the
first subflow sock.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index b888d6339c805..891f49722263f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3405,14 +3405,12 @@ static void mptcp_unhash(struct sock *sk)
 static int mptcp_get_port(struct sock *sk, unsigned short snum)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct socket *ssock;
 
-	ssock = msk->subflow;
-	pr_debug("msk=%p, subflow=%p", msk, ssock);
-	if (WARN_ON_ONCE(!ssock))
+	pr_debug("msk=%p, ssk=%p", msk, msk->first);
+	if (WARN_ON_ONCE(!msk->first))
 		return -EINVAL;
 
-	return inet_csk_get_port(ssock->sk, snum);
+	return inet_csk_get_port(msk->first, snum);
 }
 
 void mptcp_finish_connect(struct sock *ssk)
-- 
GitLab


From e6d360ff87f005e5b28edc26cb43718244ae7e73 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:17 +0200
Subject: [PATCH 1160/1806] net: factor out inet{,6}_bind_sk helpers

The mptcp protocol maintains an additional socket just to easily
invoke a few stream operations on the first subflow. One of
them is bind().

Factor out the helpers operating directly on the struct sock, to
allow get rid of the above dependency in the next patch without
duplicating the existing code.

No functional changes intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_common.h |  1 +
 include/net/ipv6.h        |  1 +
 net/ipv4/af_inet.c        |  8 ++++++--
 net/ipv6/af_inet6.c       | 10 +++++++---
 4 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index b86b8e21de7f7..8e97de7009918 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -42,6 +42,7 @@ int inet_shutdown(struct socket *sock, int how);
 int inet_listen(struct socket *sock, int backlog);
 void inet_sock_destruct(struct sock *sk);
 int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
+int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 /* Don't allocate port at this moment, defer to connect. */
 #define BIND_FORCE_ADDRESS_NO_PORT	(1 << 0)
 /* Grab and release socket lock. */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 2acc4c808d45d..22643ffc2df8c 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1216,6 +1216,7 @@ void inet6_cleanup_sock(struct sock *sk);
 void inet6_sock_destruct(struct sock *sk);
 int inet6_release(struct socket *sock);
 int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
+int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 		  int peer);
 int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9b2ca2fcc5a11..2fd23437c1d2e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -431,9 +431,8 @@ int inet_release(struct socket *sock)
 }
 EXPORT_SYMBOL(inet_release);
 
-int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
-	struct sock *sk = sock->sk;
 	u32 flags = BIND_WITH_LOCK;
 	int err;
 
@@ -454,6 +453,11 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	return __inet_bind(sk, uaddr, addr_len, flags);
 }
+
+int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+{
+	return inet_bind_sk(sock->sk, uaddr, addr_len);
+}
 EXPORT_SYMBOL(inet_bind);
 
 int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 9f9c4b838664a..3ec0359d5c1f1 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -435,10 +435,8 @@ out_unlock:
 	goto out;
 }
 
-/* bind for INET6 API */
-int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
-	struct sock *sk = sock->sk;
 	u32 flags = BIND_WITH_LOCK;
 	const struct proto *prot;
 	int err = 0;
@@ -462,6 +460,12 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	return __inet6_bind(sk, uaddr, addr_len, flags);
 }
+
+/* bind for INET6 API */
+int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+{
+	return inet6_bind_sk(sock->sk, uaddr, addr_len);
+}
 EXPORT_SYMBOL(inet6_bind);
 
 int inet6_release(struct socket *sock)
-- 
GitLab


From 8cf2ebdc0078a841fd54fcd50574bae1ae910d94 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:18 +0200
Subject: [PATCH 1161/1806] mptcp: mptcp: avoid additional indirection in
 mptcp_bind()

We are going to remove the first subflow socket soon, so avoid
the additional indirection via at bind() time. Instead call directly
the recently introduced helpers on the first subflow sock.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 891f49722263f..5b4d6f0628a7e 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3689,22 +3689,29 @@ static struct proto mptcp_prot = {
 static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct mptcp_sock *msk = mptcp_sk(sock->sk);
+	struct sock *ssk, *sk = sock->sk;
 	struct socket *ssock;
-	int err;
+	int err = -EINVAL;
 
-	lock_sock(sock->sk);
+	lock_sock(sk);
 	ssock = __mptcp_nmpc_socket(msk);
 	if (IS_ERR(ssock)) {
 		err = PTR_ERR(ssock);
 		goto unlock;
 	}
 
-	err = READ_ONCE(ssock->ops)->bind(ssock, uaddr, addr_len);
+	ssk = msk->first;
+	if (sk->sk_family == AF_INET)
+		err = inet_bind_sk(ssk, uaddr, addr_len);
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	else if (sk->sk_family == AF_INET6)
+		err = inet6_bind_sk(ssk, uaddr, addr_len);
+#endif
 	if (!err)
-		mptcp_copy_inaddrs(sock->sk, ssock->sk);
+		mptcp_copy_inaddrs(sk, ssk);
 
 unlock:
-	release_sock(sock->sk);
+	release_sock(sk);
 	return err;
 }
 
-- 
GitLab


From 71a9a874cd6beb074896519f762741fbc448f5be Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:19 +0200
Subject: [PATCH 1162/1806] net: factor out __inet_listen_sk() helper

The mptcp protocol maintains an additional socket just to easily
invoke a few stream operations on the first subflow. One of them
is inet_listen().

Factor out an helper operating directly on the (locked) struct sock,
to allow get rid of the above dependency in the next patch without
duplicating the existing code.

No functional changes intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_common.h |  1 +
 net/ipv4/af_inet.c        | 38 ++++++++++++++++++++++----------------
 2 files changed, 23 insertions(+), 16 deletions(-)

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 8e97de7009918..f50a644d87a98 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -40,6 +40,7 @@ int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		 int flags);
 int inet_shutdown(struct socket *sock, int how);
 int inet_listen(struct socket *sock, int backlog);
+int __inet_listen_sk(struct sock *sk, int backlog);
 void inet_sock_destruct(struct sock *sk);
 int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
 int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 2fd23437c1d2e..c59da65f19d23 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -187,24 +187,13 @@ static int inet_autobind(struct sock *sk)
 	return 0;
 }
 
-/*
- *	Move a socket into listening state.
- */
-int inet_listen(struct socket *sock, int backlog)
+int __inet_listen_sk(struct sock *sk, int backlog)
 {
-	struct sock *sk = sock->sk;
-	unsigned char old_state;
+	unsigned char old_state = sk->sk_state;
 	int err, tcp_fastopen;
 
-	lock_sock(sk);
-
-	err = -EINVAL;
-	if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM)
-		goto out;
-
-	old_state = sk->sk_state;
 	if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN)))
-		goto out;
+		return -EINVAL;
 
 	WRITE_ONCE(sk->sk_max_ack_backlog, backlog);
 	/* Really, if the socket is already in listen state
@@ -227,10 +216,27 @@ int inet_listen(struct socket *sock, int backlog)
 
 		err = inet_csk_listen_start(sk);
 		if (err)
-			goto out;
+			return err;
+
 		tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL);
 	}
-	err = 0;
+	return 0;
+}
+
+/*
+ *	Move a socket into listening state.
+ */
+int inet_listen(struct socket *sock, int backlog)
+{
+	struct sock *sk = sock->sk;
+	int err = -EINVAL;
+
+	lock_sock(sk);
+
+	if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM)
+		goto out;
+
+	err = __inet_listen_sk(sk, backlog);
 
 out:
 	release_sock(sk);
-- 
GitLab


From 40f56d0c7043d16e9d49d1df6c02804c09ed5cd6 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:20 +0200
Subject: [PATCH 1163/1806] mptcp: avoid additional indirection in
 mptcp_listen()

We are going to remove the first subflow socket soon, so avoid
the additional indirection via at listen() time. Instead call
directly the recently introduced helper on the first subflow sock.

No functional changes intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5b4d6f0628a7e..d8b75fbc4f248 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3720,6 +3720,7 @@ static int mptcp_listen(struct socket *sock, int backlog)
 	struct mptcp_sock *msk = mptcp_sk(sock->sk);
 	struct sock *sk = sock->sk;
 	struct socket *ssock;
+	struct sock *ssk;
 	int err;
 
 	pr_debug("msk=%p", msk);
@@ -3736,15 +3737,19 @@ static int mptcp_listen(struct socket *sock, int backlog)
 		goto unlock;
 	}
 
+	ssk = msk->first;
 	inet_sk_state_store(sk, TCP_LISTEN);
 	sock_set_flag(sk, SOCK_RCU_FREE);
 
-	err = READ_ONCE(ssock->ops)->listen(ssock, backlog);
-	inet_sk_state_store(sk, inet_sk_state_load(ssock->sk));
+	lock_sock(ssk);
+	err = __inet_listen_sk(ssk, backlog);
+	release_sock(ssk);
+	inet_sk_state_store(sk, inet_sk_state_load(ssk));
+
 	if (!err) {
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
-		mptcp_copy_inaddrs(sk, ssock->sk);
-		mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED);
+		mptcp_copy_inaddrs(sk, ssk);
+		mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED);
 	}
 
 unlock:
-- 
GitLab


From 5426a4ef6455c93e76a553eda0a1811bb0bbd214 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:21 +0200
Subject: [PATCH 1164/1806] mptcp: avoid additional indirection in mptcp_poll()

We are going to remove the first subflow socket soon, so avoid
the additional indirection at poll() time. Instead access
directly the first subflow sock.

No functional changes intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index d8b75fbc4f248..e89d1bf44f77b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3844,12 +3844,12 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	state = inet_sk_state_load(sk);
 	pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
 	if (state == TCP_LISTEN) {
-		struct socket *ssock = READ_ONCE(msk->subflow);
+		struct sock *ssk = READ_ONCE(msk->first);
 
-		if (WARN_ON_ONCE(!ssock || !ssock->sk))
+		if (WARN_ON_ONCE(!ssk))
 			return 0;
 
-		return inet_csk_listen_poll(ssock->sk);
+		return inet_csk_listen_poll(ssk);
 	}
 
 	shutdown = READ_ONCE(sk->sk_shutdown);
-- 
GitLab


From 1f6610b92ac3c4cd4b7904b1d00b776f9bf08ed3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:22 +0200
Subject: [PATCH 1165/1806] mptcp: avoid unneeded indirection in
 mptcp_stream_accept()

We are going to remove the first subflow socket soon, so avoid
the additional indirection at accept() time. Instead access
directly the first subflow sock, and update mptcp_accept() to
operate on it. This allows dropping a duplicated check in
mptcp_accept().

No functional changes intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 29 ++++++++++-------------------
 1 file changed, 10 insertions(+), 19 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e89d1bf44f77b..e5ebd170d3165 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3174,25 +3174,17 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
 }
 
-static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
+static struct sock *mptcp_accept(struct sock *ssk, int flags, int *err,
 				 bool kern)
 {
-	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct socket *listener;
 	struct sock *newsk;
 
-	listener = READ_ONCE(msk->subflow);
-	if (WARN_ON_ONCE(!listener)) {
-		*err = -EINVAL;
-		return NULL;
-	}
-
-	pr_debug("msk=%p, listener=%p", msk, mptcp_subflow_ctx(listener->sk));
-	newsk = inet_csk_accept(listener->sk, flags, err, kern);
+	pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
+	newsk = inet_csk_accept(ssk, flags, err, kern);
 	if (!newsk)
 		return NULL;
 
-	pr_debug("msk=%p, subflow is mptcp=%d", msk, sk_is_mptcp(newsk));
+	pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
 	if (sk_is_mptcp(newsk)) {
 		struct mptcp_subflow_context *subflow;
 		struct sock *new_mptcp_sock;
@@ -3209,9 +3201,9 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 		}
 
 		newsk = new_mptcp_sock;
-		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
 	} else {
-		MPTCP_INC_STATS(sock_net(sk),
+		MPTCP_INC_STATS(sock_net(ssk),
 				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
 	}
 
@@ -3761,8 +3753,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			       int flags, bool kern)
 {
 	struct mptcp_sock *msk = mptcp_sk(sock->sk);
-	struct socket *ssock;
-	struct sock *newsk;
+	struct sock *ssk, *newsk;
 	int err;
 
 	pr_debug("msk=%p", msk);
@@ -3770,11 +3761,11 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 	/* Buggy applications can call accept on socket states other then LISTEN
 	 * but no need to allocate the first subflow just to error out.
 	 */
-	ssock = READ_ONCE(msk->subflow);
-	if (!ssock)
+	ssk = READ_ONCE(msk->first);
+	if (!ssk)
 		return -EINVAL;
 
-	newsk = mptcp_accept(sock->sk, flags, &err, kern);
+	newsk = mptcp_accept(ssk, flags, &err, kern);
 	if (!newsk)
 		return err;
 
-- 
GitLab


From f0bc514bd5c1396d1f189e4aafd2c24372ce535a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:23 +0200
Subject: [PATCH 1166/1806] mptcp: avoid additional indirection in sockopt

The mptcp sockopt infrastructure unneedly uses the first subflow
socket struct in a few spots. We are going to remove such field
soon, so use directly the first subflow sock instead.

No functional changes intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/sockopt.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index a3f1fe810cc96..6661852f8d974 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -293,6 +293,7 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
 {
 	struct sock *sk = (struct sock *)msk;
 	struct socket *ssock;
+	struct sock *ssk;
 	int ret;
 
 	switch (optname) {
@@ -307,16 +308,17 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
 			return PTR_ERR(ssock);
 		}
 
-		ret = sock_setsockopt(ssock, SOL_SOCKET, optname, optval, optlen);
+		ssk = msk->first;
+		ret = sk_setsockopt(ssk, SOL_SOCKET, optname, optval, optlen);
 		if (ret == 0) {
 			if (optname == SO_REUSEPORT)
-				sk->sk_reuseport = ssock->sk->sk_reuseport;
+				sk->sk_reuseport = ssk->sk_reuseport;
 			else if (optname == SO_REUSEADDR)
-				sk->sk_reuse = ssock->sk->sk_reuse;
+				sk->sk_reuse = ssk->sk_reuse;
 			else if (optname == SO_BINDTODEVICE)
-				sk->sk_bound_dev_if = ssock->sk->sk_bound_dev_if;
+				sk->sk_bound_dev_if = ssk->sk_bound_dev_if;
 			else if (optname == SO_BINDTOIFINDEX)
-				sk->sk_bound_dev_if = ssock->sk->sk_bound_dev_if;
+				sk->sk_bound_dev_if = ssk->sk_bound_dev_if;
 		}
 		release_sock(sk);
 		return ret;
@@ -391,6 +393,7 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 	struct sock *sk = (struct sock *)msk;
 	int ret = -EOPNOTSUPP;
 	struct socket *ssock;
+	struct sock *ssk;
 
 	switch (optname) {
 	case IPV6_V6ONLY:
@@ -403,7 +406,8 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 			return PTR_ERR(ssock);
 		}
 
-		ret = tcp_setsockopt(ssock->sk, SOL_IPV6, optname, optval, optlen);
+		ssk = msk->first;
+		ret = tcp_setsockopt(ssk, SOL_IPV6, optname, optval, optlen);
 		if (ret != 0) {
 			release_sock(sk);
 			return ret;
@@ -413,13 +417,13 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 
 		switch (optname) {
 		case IPV6_V6ONLY:
-			sk->sk_ipv6only = ssock->sk->sk_ipv6only;
+			sk->sk_ipv6only = ssk->sk_ipv6only;
 			break;
 		case IPV6_TRANSPARENT:
-			inet_sk(sk)->transparent = inet_sk(ssock->sk)->transparent;
+			inet_sk(sk)->transparent = inet_sk(ssk)->transparent;
 			break;
 		case IPV6_FREEBIND:
-			inet_sk(sk)->freebind = inet_sk(ssock->sk)->freebind;
+			inet_sk(sk)->freebind = inet_sk(ssk)->freebind;
 			break;
 		}
 
@@ -700,7 +704,7 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o
 		return PTR_ERR(ssock);
 	}
 
-	issk = inet_sk(ssock->sk);
+	issk = inet_sk(msk->first);
 
 	switch (optname) {
 	case IP_FREEBIND:
@@ -865,8 +869,8 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int
 {
 	struct sock *sk = (struct sock *)msk;
 	struct socket *ssock;
-	int ret;
 	struct sock *ssk;
+	int ret;
 
 	lock_sock(sk);
 	ssk = msk->first;
@@ -881,7 +885,7 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int
 		goto out;
 	}
 
-	ret = tcp_getsockopt(ssock->sk, level, optname, optval, optlen);
+	ret = tcp_getsockopt(ssk, level, optname, optval, optlen);
 
 out:
 	release_sock(sk);
-- 
GitLab


From 3aa362494170142406228e45860d6f4e48595d54 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:24 +0200
Subject: [PATCH 1167/1806] mptcp: avoid ssock usage in
 mptcp_pm_nl_create_listen_socket()

This is one of the few remaining spots actually manipulating the
first subflow socket. We can leverage the recently introduced
inet helpers to get rid of ssock there.

No functional changes intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/pm_netlink.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 5692daf57a4d8..ae36155ff1286 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -9,6 +9,7 @@
 #include <linux/inet.h>
 #include <linux/kernel.h>
 #include <net/tcp.h>
+#include <net/inet_common.h>
 #include <net/netns/generic.h>
 #include <net/mptcp.h>
 #include <net/genetlink.h>
@@ -1005,8 +1006,8 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	bool is_ipv6 = sk->sk_family == AF_INET6;
 	int addrlen = sizeof(struct sockaddr_in);
 	struct sockaddr_storage addr;
+	struct sock *newsk, *ssk;
 	struct socket *ssock;
-	struct sock *newsk;
 	int backlog = 1024;
 	int err;
 
@@ -1042,18 +1043,23 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	if (entry->addr.family == AF_INET6)
 		addrlen = sizeof(struct sockaddr_in6);
 #endif
-	err = kernel_bind(ssock, (struct sockaddr *)&addr, addrlen);
+	ssk = mptcp_sk(newsk)->first;
+	if (ssk->sk_family == AF_INET)
+		err = inet_bind_sk(ssk, (struct sockaddr *)&addr, addrlen);
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	else if (ssk->sk_family == AF_INET6)
+		err = inet6_bind_sk(ssk, (struct sockaddr *)&addr, addrlen);
+#endif
 	if (err)
 		return err;
 
 	inet_sk_state_store(newsk, TCP_LISTEN);
-	err = kernel_listen(ssock, backlog);
-	if (err)
-		return err;
-
-	mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED);
-
-	return 0;
+	lock_sock(ssk);
+	err = __inet_listen_sk(ssk, backlog);
+	if (!err)
+		mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED);
+	release_sock(ssk);
+	return err;
 }
 
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
-- 
GitLab


From 3f326a821b99812edb6d3c24bcb78377cae6e432 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:25 +0200
Subject: [PATCH 1168/1806] mptcp: change the mpc check helper to return a sk

After the previous patch the __mptcp_nmpc_socket helper is used
only to ensure that the MPTCP socket is a suitable status - that
is, the mptcp capable handshake is not started yet.

Change the return value to the relevant subflow sock, to finally
remove the last references to first subflow socket in the MPTCP stack.

As a bonus, we can get rid of a few local variables in different
functions.

No functional change intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/pm_netlink.c |  8 +++-----
 net/mptcp/protocol.c   | 40 +++++++++++++++------------------------
 net/mptcp/protocol.h   |  2 +-
 net/mptcp/sockopt.c    | 43 +++++++++++++++++++-----------------------
 4 files changed, 38 insertions(+), 55 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index ae36155ff1286..c75d9d88a053d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1007,7 +1007,6 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	int addrlen = sizeof(struct sockaddr_in);
 	struct sockaddr_storage addr;
 	struct sock *newsk, *ssk;
-	struct socket *ssock;
 	int backlog = 1024;
 	int err;
 
@@ -1033,17 +1032,16 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 				      &mptcp_keys[is_ipv6]);
 
 	lock_sock(newsk);
-	ssock = __mptcp_nmpc_socket(mptcp_sk(newsk));
+	ssk = __mptcp_nmpc_sk(mptcp_sk(newsk));
 	release_sock(newsk);
-	if (IS_ERR(ssock))
-		return PTR_ERR(ssock);
+	if (IS_ERR(ssk))
+		return PTR_ERR(ssk);
 
 	mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family);
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	if (entry->addr.family == AF_INET6)
 		addrlen = sizeof(struct sockaddr_in6);
 #endif
-	ssk = mptcp_sk(newsk)->first;
 	if (ssk->sk_family == AF_INET)
 		err = inet_bind_sk(ssk, (struct sockaddr *)&addr, addrlen);
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e5ebd170d3165..fafa83ee4a729 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -109,7 +109,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 /* If the MPC handshake is not started, returns the first subflow,
  * eventually allocating it.
  */
-struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk)
+struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk)
 {
 	struct sock *sk = (struct sock *)msk;
 	int ret;
@@ -117,10 +117,7 @@ struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk)
 	if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		return ERR_PTR(-EINVAL);
 
-	if (!msk->subflow) {
-		if (msk->first)
-			return ERR_PTR(-EINVAL);
-
+	if (!msk->first) {
 		ret = __mptcp_socket_create(msk);
 		if (ret)
 			return ERR_PTR(ret);
@@ -128,7 +125,7 @@ struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk)
 		mptcp_sockopt_sync(msk, msk->first);
 	}
 
-	return msk->subflow;
+	return msk->first;
 }
 
 static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
@@ -1643,7 +1640,6 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 {
 	unsigned int saved_flags = msg->msg_flags;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct socket *ssock;
 	struct sock *ssk;
 	int ret;
 
@@ -1654,9 +1650,9 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	 * fastopen attempt, no need to check for additional subflow status.
 	 */
 	if (msg->msg_flags & MSG_FASTOPEN) {
-		ssock = __mptcp_nmpc_socket(msk);
-		if (IS_ERR(ssock))
-			return PTR_ERR(ssock);
+		ssk = __mptcp_nmpc_sk(msk);
+		if (IS_ERR(ssk))
+			return PTR_ERR(ssk);
 	}
 	if (!msk->first)
 		return -EINVAL;
@@ -3577,16 +3573,14 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct socket *ssock;
 	int err = -EINVAL;
 	struct sock *ssk;
 
-	ssock = __mptcp_nmpc_socket(msk);
-	if (IS_ERR(ssock))
-		return PTR_ERR(ssock);
+	ssk = __mptcp_nmpc_sk(msk);
+	if (IS_ERR(ssk))
+		return PTR_ERR(ssk);
 
 	inet_sk_state_store(sk, TCP_SYN_SENT);
-	ssk = msk->first;
 	subflow = mptcp_subflow_ctx(ssk);
 #ifdef CONFIG_TCP_MD5SIG
 	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
@@ -3682,17 +3676,15 @@ static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct mptcp_sock *msk = mptcp_sk(sock->sk);
 	struct sock *ssk, *sk = sock->sk;
-	struct socket *ssock;
 	int err = -EINVAL;
 
 	lock_sock(sk);
-	ssock = __mptcp_nmpc_socket(msk);
-	if (IS_ERR(ssock)) {
-		err = PTR_ERR(ssock);
+	ssk = __mptcp_nmpc_sk(msk);
+	if (IS_ERR(ssk)) {
+		err = PTR_ERR(ssk);
 		goto unlock;
 	}
 
-	ssk = msk->first;
 	if (sk->sk_family == AF_INET)
 		err = inet_bind_sk(ssk, uaddr, addr_len);
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
@@ -3711,7 +3703,6 @@ static int mptcp_listen(struct socket *sock, int backlog)
 {
 	struct mptcp_sock *msk = mptcp_sk(sock->sk);
 	struct sock *sk = sock->sk;
-	struct socket *ssock;
 	struct sock *ssk;
 	int err;
 
@@ -3723,13 +3714,12 @@ static int mptcp_listen(struct socket *sock, int backlog)
 	if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM)
 		goto unlock;
 
-	ssock = __mptcp_nmpc_socket(msk);
-	if (IS_ERR(ssock)) {
-		err = PTR_ERR(ssock);
+	ssk = __mptcp_nmpc_sk(msk);
+	if (IS_ERR(ssk)) {
+		err = PTR_ERR(ssk);
 		goto unlock;
 	}
 
-	ssk = msk->first;
 	inet_sk_state_store(sk, TCP_LISTEN);
 	sock_set_flag(sk, SOCK_RCU_FREE);
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 79fc5cdb67bc0..dccc96dc2d6b4 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -640,7 +640,7 @@ void __mptcp_subflow_send_ack(struct sock *ssk);
 void mptcp_subflow_reset(struct sock *ssk);
 void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
 void mptcp_sock_graft(struct sock *sk, struct socket *parent);
-struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk);
+struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk);
 bool __mptcp_close(struct sock *sk, long timeout);
 void mptcp_cancel_work(struct sock *sk);
 void __mptcp_unaccepted_force_close(struct sock *sk);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 6661852f8d974..21bc46acbe38e 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -292,7 +292,6 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
 				       sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = (struct sock *)msk;
-	struct socket *ssock;
 	struct sock *ssk;
 	int ret;
 
@@ -302,13 +301,12 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
 	case SO_BINDTODEVICE:
 	case SO_BINDTOIFINDEX:
 		lock_sock(sk);
-		ssock = __mptcp_nmpc_socket(msk);
-		if (IS_ERR(ssock)) {
+		ssk = __mptcp_nmpc_sk(msk);
+		if (IS_ERR(ssk)) {
 			release_sock(sk);
-			return PTR_ERR(ssock);
+			return PTR_ERR(ssk);
 		}
 
-		ssk = msk->first;
 		ret = sk_setsockopt(ssk, SOL_SOCKET, optname, optval, optlen);
 		if (ret == 0) {
 			if (optname == SO_REUSEPORT)
@@ -392,7 +390,6 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 {
 	struct sock *sk = (struct sock *)msk;
 	int ret = -EOPNOTSUPP;
-	struct socket *ssock;
 	struct sock *ssk;
 
 	switch (optname) {
@@ -400,13 +397,12 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 	case IPV6_TRANSPARENT:
 	case IPV6_FREEBIND:
 		lock_sock(sk);
-		ssock = __mptcp_nmpc_socket(msk);
-		if (IS_ERR(ssock)) {
+		ssk = __mptcp_nmpc_sk(msk);
+		if (IS_ERR(ssk)) {
 			release_sock(sk);
-			return PTR_ERR(ssock);
+			return PTR_ERR(ssk);
 		}
 
-		ssk = msk->first;
 		ret = tcp_setsockopt(ssk, SOL_IPV6, optname, optval, optlen);
 		if (ret != 0) {
 			release_sock(sk);
@@ -689,7 +685,7 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o
 {
 	struct sock *sk = (struct sock *)msk;
 	struct inet_sock *issk;
-	struct socket *ssock;
+	struct sock *ssk;
 	int err;
 
 	err = ip_setsockopt(sk, SOL_IP, optname, optval, optlen);
@@ -698,13 +694,13 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o
 
 	lock_sock(sk);
 
-	ssock = __mptcp_nmpc_socket(msk);
-	if (IS_ERR(ssock)) {
+	ssk = __mptcp_nmpc_sk(msk);
+	if (IS_ERR(ssk)) {
 		release_sock(sk);
-		return PTR_ERR(ssock);
+		return PTR_ERR(ssk);
 	}
 
-	issk = inet_sk(msk->first);
+	issk = inet_sk(ssk);
 
 	switch (optname) {
 	case IP_FREEBIND:
@@ -767,18 +763,18 @@ static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int
 					  sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = (struct sock *)msk;
-	struct socket *sock;
+	struct sock *ssk;
 	int ret;
 
 	/* Limit to first subflow, before the connection establishment */
 	lock_sock(sk);
-	sock = __mptcp_nmpc_socket(msk);
-	if (IS_ERR(sock)) {
-		ret = PTR_ERR(sock);
+	ssk = __mptcp_nmpc_sk(msk);
+	if (IS_ERR(ssk)) {
+		ret = PTR_ERR(ssk);
 		goto unlock;
 	}
 
-	ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen);
+	ret = tcp_setsockopt(ssk, level, optname, optval, optlen);
 
 unlock:
 	release_sock(sk);
@@ -868,7 +864,6 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int
 					  char __user *optval, int __user *optlen)
 {
 	struct sock *sk = (struct sock *)msk;
-	struct socket *ssock;
 	struct sock *ssk;
 	int ret;
 
@@ -879,9 +874,9 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int
 		goto out;
 	}
 
-	ssock = __mptcp_nmpc_socket(msk);
-	if (IS_ERR(ssock)) {
-		ret = PTR_ERR(ssock);
+	ssk = __mptcp_nmpc_sk(msk);
+	if (IS_ERR(ssk)) {
+		ret = PTR_ERR(ssk);
 		goto out;
 	}
 
-- 
GitLab


From 39880bd808ad2ddfb9b7fee129568c3b814f0609 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 11 Aug 2023 17:57:26 +0200
Subject: [PATCH 1169/1806] mptcp: get rid of msk->subflow

Such field is now unused just as a flag to control the first subflow
deletion at close() time. Introduce a new bit flag for that and finally
drop the mentioned field.

As an intended side effect, now the first subflow sock is not freed
before close() even for passive sockets. The msk has no open/active
subflows if the first one is closed and the subflow list is singular,
update accordingly the state check in mptcp_stream_accept().

Among other benefits, the subflow removal, reduces the amount of memory
used on the client side for each mptcp connection, allows passive sockets
to go through successful accept()/disconnect()/connect() and makes return
error code consistent for failing both passive and active sockets.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/290
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 25 ++++++-------------------
 net/mptcp/protocol.h | 13 ++++++-------
 2 files changed, 12 insertions(+), 26 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index fafa83ee4a729..e715771ded7cb 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -92,7 +92,6 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 
 	msk->scaling_ratio = tcp_sk(ssock->sk)->scaling_ratio;
 	WRITE_ONCE(msk->first, ssock->sk);
-	WRITE_ONCE(msk->subflow, ssock);
 	subflow = mptcp_subflow_ctx(ssock->sk);
 	list_add(&subflow->node, &msk->conn_list);
 	sock_hold(ssock->sk);
@@ -102,6 +101,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	/* This is the first subflow, always with id 0 */
 	subflow->local_id_valid = 1;
 	mptcp_sock_graft(msk->first, sk->sk_socket);
+	iput(SOCK_INODE(ssock));
 
 	return 0;
 }
@@ -2238,14 +2238,6 @@ static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
 	return min_stale_count > 1 ? backup : NULL;
 }
 
-static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk)
-{
-	if (msk->subflow) {
-		iput(SOCK_INODE(msk->subflow));
-		WRITE_ONCE(msk->subflow, NULL);
-	}
-}
-
 bool __mptcp_retransmit_pending_data(struct sock *sk)
 {
 	struct mptcp_data_frag *cur, *rtx_head;
@@ -2324,7 +2316,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		goto out_release;
 	}
 
-	dispose_it = !msk->subflow || ssk != msk->subflow->sk;
+	dispose_it = msk->free_first || ssk != msk->first;
 	if (dispose_it)
 		list_del(&subflow->node);
 
@@ -2345,7 +2337,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		 * disconnect should never fail
 		 */
 		WARN_ON_ONCE(tcp_disconnect(ssk, 0));
-		msk->subflow->state = SS_UNCONNECTED;
 		mptcp_subflow_ctx_reset(subflow);
 		release_sock(ssk);
 
@@ -3106,7 +3097,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	msk = mptcp_sk(nsk);
 	msk->local_key = subflow_req->local_key;
 	msk->token = subflow_req->token;
-	WRITE_ONCE(msk->subflow, NULL);
 	msk->in_accept_queue = 1;
 	WRITE_ONCE(msk->fully_established, false);
 	if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD)
@@ -3240,10 +3230,8 @@ static void mptcp_destroy(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	/* clears msk->subflow, allowing the following to close
-	 * even the initial subflow
-	 */
-	mptcp_dispose_initial_subflow(msk);
+	/* allow the following to close even the initial subflow */
+	msk->free_first = 1;
 	mptcp_destroy_common(msk, 0);
 	sk_sockets_allocated_dec(sk);
 }
@@ -3782,11 +3770,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 		/* Do late cleanup for the first subflow as necessary. Also
 		 * deal with bad peers not doing a complete shutdown.
 		 */
-		if (msk->first &&
-		    unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) {
+		if (unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) {
 			__mptcp_close_ssk(newsk, msk->first,
 					  mptcp_subflow_ctx(msk->first), 0);
-			if (unlikely(list_empty(&msk->conn_list)))
+			if (unlikely(list_is_singular(&msk->conn_list)))
 				inet_sk_state_store(newsk, TCP_CLOSE);
 		}
 	}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index dccc96dc2d6b4..38c7ea0133610 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -299,7 +299,8 @@ struct mptcp_sock {
 			cork:1,
 			nodelay:1,
 			fastopening:1,
-			in_accept_queue:1;
+			in_accept_queue:1,
+			free_first:1;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
@@ -308,12 +309,10 @@ struct mptcp_sock {
 	struct list_head rtx_queue;
 	struct mptcp_data_frag *first_pending;
 	struct list_head join_list;
-	struct socket	*subflow; /* outgoing connect/listener/!mp_capable
-				   * The mptcp ops can safely dereference, using suitable
-				   * ONCE annotation, the subflow outside the socket
-				   * lock as such sock is freed after close().
-				   */
-	struct sock	*first;
+	struct sock	*first; /* The mptcp ops can safely dereference, using suitable
+				 * ONCE annotation, the subflow outside the socket
+				 * lock as such sock is freed after close().
+				 */
 	struct mptcp_pm_data	pm;
 	struct {
 		u32	space;	/* bytes copied in last measurement window */
-- 
GitLab


From e263691773cd67d7c824eeee8b802f50c6e0c118 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 11 Aug 2023 17:57:27 +0200
Subject: [PATCH 1170/1806] mptcp: Remove unnecessary test for
 __mptcp_init_sock()

__mptcp_init_sock() always returns 0 because mptcp_init_sock() used
to return the value directly.

But after commit 18b683bff89d ("mptcp: queue data for mptcp level
retransmission"), __mptcp_init_sock() need not return value anymore.

Let's remove the unnecessary test for __mptcp_init_sock() and make
it return void.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e715771ded7cb..6ea0a1da80685 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2649,7 +2649,7 @@ unlock:
 	sock_put(sk);
 }
 
-static int __mptcp_init_sock(struct sock *sk)
+static void __mptcp_init_sock(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
@@ -2676,8 +2676,6 @@ static int __mptcp_init_sock(struct sock *sk)
 	/* re-use the csk retrans timer for MPTCP-level retrans */
 	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
 	timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
-
-	return 0;
 }
 
 static void mptcp_ca_reset(struct sock *sk)
@@ -2695,11 +2693,8 @@ static void mptcp_ca_reset(struct sock *sk)
 static int mptcp_init_sock(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
-	int ret;
 
-	ret = __mptcp_init_sock(sk);
-	if (ret)
-		return ret;
+	__mptcp_init_sock(sk);
 
 	if (!mptcp_is_enabled(net))
 		return -ENOPROTOOPT;
-- 
GitLab


From 9d802da40b7c820deb9c60fc394457ea565cafc8 Mon Sep 17 00:00:00 2001
From: Adrian Moreno <amorenoz@redhat.com>
Date: Fri, 11 Aug 2023 16:12:48 +0200
Subject: [PATCH 1171/1806] net: openvswitch: add last-action drop reason

Create a new drop reason subsystem for openvswitch and add the first
drop reason to represent last-action drops.

Last-action drops happen when a flow has an empty action list or there
is no action that consumes the packet (output, userspace, recirc, etc).
It is the most common way in which OVS drops packets.

Implementation-wise, most of these skb-consuming actions already call
"consume_skb" internally and return directly from within the
do_execute_actions() loop so with minimal changes we can assume that
any skb that exits the loop normally is a packet drop.

Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dropreason.h   |  6 ++++++
 net/openvswitch/actions.c  | 12 ++++++++++--
 net/openvswitch/datapath.c | 16 ++++++++++++++++
 net/openvswitch/drop.h     | 31 +++++++++++++++++++++++++++++++
 4 files changed, 63 insertions(+), 2 deletions(-)
 create mode 100644 net/openvswitch/drop.h

diff --git a/include/net/dropreason.h b/include/net/dropreason.h
index 685fb37df8e8e..56cb7be92244c 100644
--- a/include/net/dropreason.h
+++ b/include/net/dropreason.h
@@ -23,6 +23,12 @@ enum skb_drop_reason_subsys {
 	 */
 	SKB_DROP_REASON_SUBSYS_MAC80211_MONITOR,
 
+	/**
+	 * @SKB_DROP_REASON_SUBSYS_OPENVSWITCH: openvswitch drop reasons,
+	 * see net/openvswitch/drop.h
+	 */
+	SKB_DROP_REASON_SUBSYS_OPENVSWITCH,
+
 	/** @SKB_DROP_REASON_SUBSYS_NUM: number of subsystems defined */
 	SKB_DROP_REASON_SUBSYS_NUM
 };
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index cab1e02b63e05..8c8a7a82f76ff 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -27,6 +27,7 @@
 #include <net/sctp/checksum.h>
 
 #include "datapath.h"
+#include "drop.h"
 #include "flow.h"
 #include "conntrack.h"
 #include "vport.h"
@@ -1036,7 +1037,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 	if ((arg->probability != U32_MAX) &&
 	    (!arg->probability || get_random_u32() > arg->probability)) {
 		if (last)
-			consume_skb(skb);
+			ovs_kfree_skb_reason(skb, OVS_DROP_LAST_ACTION);
 		return 0;
 	}
 
@@ -1297,6 +1298,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 		if (trace_ovs_do_execute_action_enabled())
 			trace_ovs_do_execute_action(dp, skb, key, a, rem);
 
+		/* Actions that rightfully have to consume the skb should do it
+		 * and return directly.
+		 */
 		switch (nla_type(a)) {
 		case OVS_ACTION_ATTR_OUTPUT: {
 			int port = nla_get_u32(a);
@@ -1332,6 +1336,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			output_userspace(dp, skb, key, a, attr,
 						     len, OVS_CB(skb)->cutlen);
 			OVS_CB(skb)->cutlen = 0;
+			if (nla_is_last(a, rem)) {
+				consume_skb(skb);
+				return 0;
+			}
 			break;
 
 		case OVS_ACTION_ATTR_HASH:
@@ -1485,7 +1493,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 		}
 	}
 
-	consume_skb(skb);
+	ovs_kfree_skb_reason(skb, OVS_DROP_LAST_ACTION);
 	return 0;
 }
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index a6d2a0b1aa21e..d33cb739883f7 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -41,6 +41,7 @@
 #include <net/pkt_cls.h>
 
 #include "datapath.h"
+#include "drop.h"
 #include "flow.h"
 #include "flow_table.h"
 #include "flow_netlink.h"
@@ -2702,6 +2703,17 @@ static struct pernet_operations ovs_net_ops = {
 	.size = sizeof(struct ovs_net),
 };
 
+static const char * const ovs_drop_reasons[] = {
+#define S(x)	(#x),
+	OVS_DROP_REASONS(S)
+#undef S
+};
+
+static struct drop_reason_list drop_reason_list_ovs = {
+	.reasons = ovs_drop_reasons,
+	.n_reasons = ARRAY_SIZE(ovs_drop_reasons),
+};
+
 static int __init dp_init(void)
 {
 	int err;
@@ -2743,6 +2755,9 @@ static int __init dp_init(void)
 	if (err < 0)
 		goto error_unreg_netdev;
 
+	drop_reasons_register_subsys(SKB_DROP_REASON_SUBSYS_OPENVSWITCH,
+				     &drop_reason_list_ovs);
+
 	return 0;
 
 error_unreg_netdev:
@@ -2769,6 +2784,7 @@ static void dp_cleanup(void)
 	ovs_netdev_exit();
 	unregister_netdevice_notifier(&ovs_dp_device_notifier);
 	unregister_pernet_device(&ovs_net_ops);
+	drop_reasons_unregister_subsys(SKB_DROP_REASON_SUBSYS_OPENVSWITCH);
 	rcu_barrier();
 	ovs_vport_exit();
 	ovs_flow_exit();
diff --git a/net/openvswitch/drop.h b/net/openvswitch/drop.h
new file mode 100644
index 0000000000000..a5b2b901249bc
--- /dev/null
+++ b/net/openvswitch/drop.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * OpenvSwitch drop reason list.
+ */
+
+#ifndef OPENVSWITCH_DROP_H
+#define OPENVSWITCH_DROP_H
+#include <linux/skbuff.h>
+#include <net/dropreason.h>
+
+#define OVS_DROP_REASONS(R)			\
+	R(OVS_DROP_LAST_ACTION)		        \
+	/* deliberate comment for trailing \ */
+
+enum ovs_drop_reason {
+	__OVS_DROP_REASON = SKB_DROP_REASON_SUBSYS_OPENVSWITCH <<
+				SKB_DROP_REASON_SUBSYS_SHIFT,
+#define ENUM(x) x,
+	OVS_DROP_REASONS(ENUM)
+#undef ENUM
+
+	OVS_DROP_MAX,
+};
+
+static inline void
+ovs_kfree_skb_reason(struct sk_buff *skb, enum ovs_drop_reason reason)
+{
+	kfree_skb_reason(skb, (u32)reason);
+}
+
+#endif /* OPENVSWITCH_DROP_H */
-- 
GitLab


From ec7bfb5e5a054f1178e8bdbf4f145fdafa5bf804 Mon Sep 17 00:00:00 2001
From: Adrian Moreno <amorenoz@redhat.com>
Date: Fri, 11 Aug 2023 16:12:49 +0200
Subject: [PATCH 1172/1806] net: openvswitch: add action error drop reason

Add a drop reason for packets that are dropped because an action
returns a non-zero error code.

Acked-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c | 2 +-
 net/openvswitch/drop.h    | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 8c8a7a82f76ff..bb7aa181da307 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1488,7 +1488,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 		}
 
 		if (unlikely(err)) {
-			kfree_skb(skb);
+			ovs_kfree_skb_reason(skb, OVS_DROP_ACTION_ERROR);
 			return err;
 		}
 	}
diff --git a/net/openvswitch/drop.h b/net/openvswitch/drop.h
index a5b2b901249bc..b87613ced7132 100644
--- a/net/openvswitch/drop.h
+++ b/net/openvswitch/drop.h
@@ -10,6 +10,7 @@
 
 #define OVS_DROP_REASONS(R)			\
 	R(OVS_DROP_LAST_ACTION)		        \
+	R(OVS_DROP_ACTION_ERROR)		\
 	/* deliberate comment for trailing \ */
 
 enum ovs_drop_reason {
-- 
GitLab


From e7bc7db9ba463e763ac6113279cade19da9cb939 Mon Sep 17 00:00:00 2001
From: Eric Garver <eric@garver.life>
Date: Fri, 11 Aug 2023 16:12:50 +0200
Subject: [PATCH 1173/1806] net: openvswitch: add explicit drop action

From: Eric Garver <eric@garver.life>

This adds an explicit drop action. This is used by OVS to drop packets
for which it cannot determine what to do. An explicit action in the
kernel allows passing the reason _why_ the packet is being dropped or
zero to indicate no particular error happened (i.e: OVS intentionally
dropped the packet).

Since the error codes coming from userspace mean nothing for the kernel,
we squash all of them into only two drop reasons:
- OVS_DROP_EXPLICIT_WITH_ERROR to indicate a non-zero value was passed
- OVS_DROP_EXPLICIT to indicate a zero value was passed (no error)

e.g. trace all OVS dropped skbs

 # perf trace -e skb:kfree_skb --filter="reason >= 0x30000"
 [..]
 106.023 ping/2465 skb:kfree_skb(skbaddr: 0xffffa0e8765f2000, \
  location:0xffffffffc0d9b462, protocol: 2048, reason: 196611)

reason: 196611 --> 0x30003 (OVS_DROP_EXPLICIT)

Also, this patch allows ovs-dpctl.py to add explicit drop actions as:
  "drop"     -> implicit empty-action drop
  "drop(0)"  -> explicit non-error action drop
  "drop(42)" -> explicit error action drop

Signed-off-by: Eric Garver <eric@garver.life>
Co-developed-by: Adrian Moreno <amorenoz@redhat.com>
Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/openvswitch.h              |  2 ++
 net/openvswitch/actions.c                     |  9 ++++++++
 net/openvswitch/drop.h                        |  2 ++
 net/openvswitch/flow_netlink.c                | 10 ++++++++-
 .../selftests/net/openvswitch/ovs-dpctl.py    | 22 +++++++++++++++----
 5 files changed, 40 insertions(+), 5 deletions(-)

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index e94870e77ee96..efc82c318fa2a 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -965,6 +965,7 @@ struct check_pkt_len_arg {
  * start of the packet or at the start of the l3 header depending on the value
  * of l3 tunnel flag in the tun_flags field of OVS_ACTION_ATTR_ADD_MPLS
  * argument.
+ * @OVS_ACTION_ATTR_DROP: Explicit drop action.
  *
  * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
  * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
@@ -1002,6 +1003,7 @@ enum ovs_action_attr {
 	OVS_ACTION_ATTR_CHECK_PKT_LEN, /* Nested OVS_CHECK_PKT_LEN_ATTR_*. */
 	OVS_ACTION_ATTR_ADD_MPLS,     /* struct ovs_action_add_mpls. */
 	OVS_ACTION_ATTR_DEC_TTL,      /* Nested OVS_DEC_TTL_ATTR_*. */
+	OVS_ACTION_ATTR_DROP,         /* u32 error code. */
 
 	__OVS_ACTION_ATTR_MAX,	      /* Nothing past this will be accepted
 				       * from userspace. */
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index bb7aa181da307..e188f32ea96fb 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1485,6 +1485,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 				return dec_ttl_exception_handler(dp, skb,
 								 key, a);
 			break;
+
+		case OVS_ACTION_ATTR_DROP: {
+			enum ovs_drop_reason reason = nla_get_u32(a)
+				? OVS_DROP_EXPLICIT_WITH_ERROR
+				: OVS_DROP_EXPLICIT;
+
+			ovs_kfree_skb_reason(skb, reason);
+			return 0;
+		}
 		}
 
 		if (unlikely(err)) {
diff --git a/net/openvswitch/drop.h b/net/openvswitch/drop.h
index b87613ced7132..22e66d28c0ca4 100644
--- a/net/openvswitch/drop.h
+++ b/net/openvswitch/drop.h
@@ -11,6 +11,8 @@
 #define OVS_DROP_REASONS(R)			\
 	R(OVS_DROP_LAST_ACTION)		        \
 	R(OVS_DROP_ACTION_ERROR)		\
+	R(OVS_DROP_EXPLICIT)			\
+	R(OVS_DROP_EXPLICIT_WITH_ERROR)		\
 	/* deliberate comment for trailing \ */
 
 enum ovs_drop_reason {
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 41116361433da..88965e2068ac6 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -38,6 +38,7 @@
 #include <net/tun_proto.h>
 #include <net/erspan.h>
 
+#include "drop.h"
 #include "flow_netlink.h"
 
 struct ovs_len_tbl {
@@ -61,6 +62,7 @@ static bool actions_may_change_flow(const struct nlattr *actions)
 		case OVS_ACTION_ATTR_RECIRC:
 		case OVS_ACTION_ATTR_TRUNC:
 		case OVS_ACTION_ATTR_USERSPACE:
+		case OVS_ACTION_ATTR_DROP:
 			break;
 
 		case OVS_ACTION_ATTR_CT:
@@ -2394,7 +2396,7 @@ static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len)
 	/* Whenever new actions are added, the need to update this
 	 * function should be considered.
 	 */
-	BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23);
+	BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 24);
 
 	if (!actions)
 		return;
@@ -3182,6 +3184,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			[OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1,
 			[OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls),
 			[OVS_ACTION_ATTR_DEC_TTL] = (u32)-1,
+			[OVS_ACTION_ATTR_DROP] = sizeof(u32),
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
@@ -3453,6 +3456,11 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			skip_copy = true;
 			break;
 
+		case OVS_ACTION_ATTR_DROP:
+			if (!nla_is_last(a, rem))
+				return -EINVAL;
+			break;
+
 		default:
 			OVS_NLERR(log, "Unknown Action type %d", type);
 			return -EINVAL;
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index fbdac15e31344..912dc8c490858 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -301,6 +301,7 @@ class ovsactions(nla):
         ("OVS_ACTION_ATTR_CHECK_PKT_LEN", "none"),
         ("OVS_ACTION_ATTR_ADD_MPLS", "none"),
         ("OVS_ACTION_ATTR_DEC_TTL", "none"),
+        ("OVS_ACTION_ATTR_DROP", "uint32"),
     )
 
     class ctact(nla):
@@ -447,6 +448,8 @@ class ovsactions(nla):
                     print_str += "recirc(0x%x)" % int(self.get_attr(field[0]))
                 elif field[0] == "OVS_ACTION_ATTR_TRUNC":
                     print_str += "trunc(%d)" % int(self.get_attr(field[0]))
+                elif field[0] == "OVS_ACTION_ATTR_DROP":
+                    print_str += "drop(%d)" % int(self.get_attr(field[0]))
             elif field[1] == "flag":
                 if field[0] == "OVS_ACTION_ATTR_CT_CLEAR":
                     print_str += "ct_clear"
@@ -468,10 +471,21 @@ class ovsactions(nla):
         while len(actstr) != 0:
             parsed = False
             if actstr.startswith("drop"):
-                # for now, drops have no explicit action, so we
-                # don't need to set any attributes.  The final
-                # act of the processing chain will just drop the packet
-                return
+                # If no reason is provided, the implicit drop is used (i.e no
+                # action). If some reason is given, an explicit action is used.
+                actstr, reason = parse_extract_field(
+                    actstr,
+                    "drop(",
+                    "([0-9]+)",
+                    lambda x: int(x, 0),
+                    False,
+                    None,
+                )
+                if reason is not None:
+                    self["attrs"].append(["OVS_ACTION_ATTR_DROP", reason])
+                    parsed = True
+                else:
+                    return
 
             elif parse_starts_block(actstr, "^(\d+)", False, True):
                 actstr, output = parse_extract_field(
-- 
GitLab


From f329d1bc1a4580e0f8a402b14a6fd024ec8e5c7b Mon Sep 17 00:00:00 2001
From: Adrian Moreno <amorenoz@redhat.com>
Date: Fri, 11 Aug 2023 16:12:51 +0200
Subject: [PATCH 1174/1806] net: openvswitch: add meter drop reason

By using an independent drop reason it makes it easy to distinguish
between QoS-triggered or flow-triggered drop.

Acked-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c | 2 +-
 net/openvswitch/drop.h    | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index e188f32ea96fb..1222114786067 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1454,7 +1454,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 		case OVS_ACTION_ATTR_METER:
 			if (ovs_meter_execute(dp, skb, key, nla_get_u32(a))) {
-				consume_skb(skb);
+				ovs_kfree_skb_reason(skb, OVS_DROP_METER);
 				return 0;
 			}
 			break;
diff --git a/net/openvswitch/drop.h b/net/openvswitch/drop.h
index 22e66d28c0ca4..a35e63d710947 100644
--- a/net/openvswitch/drop.h
+++ b/net/openvswitch/drop.h
@@ -13,6 +13,7 @@
 	R(OVS_DROP_ACTION_ERROR)		\
 	R(OVS_DROP_EXPLICIT)			\
 	R(OVS_DROP_EXPLICIT_WITH_ERROR)		\
+	R(OVS_DROP_METER)			\
 	/* deliberate comment for trailing \ */
 
 enum ovs_drop_reason {
-- 
GitLab


From 43d95b30cf5793cdd3c7b1c1cd5fead9b469bd60 Mon Sep 17 00:00:00 2001
From: Adrian Moreno <amorenoz@redhat.com>
Date: Fri, 11 Aug 2023 16:12:52 +0200
Subject: [PATCH 1175/1806] net: openvswitch: add misc error drop reasons

Use drop reasons from include/net/dropreason-core.h when a reasonable
candidate exists.

Acked-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c   | 17 ++++++++++-------
 net/openvswitch/conntrack.c |  3 ++-
 net/openvswitch/drop.h      |  6 ++++++
 3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 1222114786067..fd66014d8a76a 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -782,7 +782,7 @@ static int ovs_vport_output(struct net *net, struct sock *sk,
 	struct vport *vport = data->vport;
 
 	if (skb_cow_head(skb, data->l2_len) < 0) {
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM);
 		return -ENOMEM;
 	}
 
@@ -853,6 +853,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 			 struct sk_buff *skb, u16 mru,
 			 struct sw_flow_key *key)
 {
+	enum ovs_drop_reason reason;
 	u16 orig_network_offset = 0;
 
 	if (eth_p_mpls(skb->protocol)) {
@@ -862,6 +863,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 
 	if (skb_network_offset(skb) > MAX_L2_LEN) {
 		OVS_NLERR(1, "L2 header too long to fragment");
+		reason = OVS_DROP_FRAG_L2_TOO_LONG;
 		goto err;
 	}
 
@@ -902,12 +904,13 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 		WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
 			  ovs_vport_name(vport), ntohs(key->eth.type), mru,
 			  vport->dev->mtu);
+		reason = OVS_DROP_FRAG_INVALID_PROTO;
 		goto err;
 	}
 
 	return;
 err:
-	kfree_skb(skb);
+	ovs_kfree_skb_reason(skb, reason);
 }
 
 static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
@@ -934,10 +937,10 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 
 			ovs_fragment(net, vport, skb, mru, key);
 		} else {
-			kfree_skb(skb);
+			kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
 		}
 	} else {
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_DEV_READY);
 	}
 }
 
@@ -1011,7 +1014,7 @@ static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb,
 		return clone_execute(dp, skb, key, 0, nla_data(actions),
 				     nla_len(actions), true, false);
 
-	consume_skb(skb);
+	ovs_kfree_skb_reason(skb, OVS_DROP_IP_TTL);
 	return 0;
 }
 
@@ -1564,7 +1567,7 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 		/* Out of per CPU action FIFO space. Drop the 'skb' and
 		 * log an error.
 		 */
-		kfree_skb(skb);
+		ovs_kfree_skb_reason(skb, OVS_DROP_DEFERRED_LIMIT);
 
 		if (net_ratelimit()) {
 			if (actions) { /* Sample action */
@@ -1616,7 +1619,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	if (unlikely(level > OVS_RECURSION_LIMIT)) {
 		net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n",
 				     ovs_dp_name(dp));
-		kfree_skb(skb);
+		ovs_kfree_skb_reason(skb, OVS_DROP_RECURSION_LIMIT);
 		err = -ENETDOWN;
 		goto out;
 	}
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index fa955e892210f..0cfa1e9482e63 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -29,6 +29,7 @@
 #include <net/netfilter/nf_conntrack_act_ct.h>
 
 #include "datapath.h"
+#include "drop.h"
 #include "conntrack.h"
 #include "flow.h"
 #include "flow_netlink.h"
@@ -1035,7 +1036,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 
 	skb_push_rcsum(skb, nh_ofs);
 	if (err)
-		kfree_skb(skb);
+		ovs_kfree_skb_reason(skb, OVS_DROP_CONNTRACK);
 	return err;
 }
 
diff --git a/net/openvswitch/drop.h b/net/openvswitch/drop.h
index a35e63d710947..cedf9b7b57962 100644
--- a/net/openvswitch/drop.h
+++ b/net/openvswitch/drop.h
@@ -14,6 +14,12 @@
 	R(OVS_DROP_EXPLICIT)			\
 	R(OVS_DROP_EXPLICIT_WITH_ERROR)		\
 	R(OVS_DROP_METER)			\
+	R(OVS_DROP_RECURSION_LIMIT)		\
+	R(OVS_DROP_DEFERRED_LIMIT)		\
+	R(OVS_DROP_FRAG_L2_TOO_LONG)		\
+	R(OVS_DROP_FRAG_INVALID_PROTO)		\
+	R(OVS_DROP_CONNTRACK)			\
+	R(OVS_DROP_IP_TTL)			\
 	/* deliberate comment for trailing \ */
 
 enum ovs_drop_reason {
-- 
GitLab


From aab1272f5daccceeeb71874ce75f60ae2ac21565 Mon Sep 17 00:00:00 2001
From: Adrian Moreno <amorenoz@redhat.com>
Date: Fri, 11 Aug 2023 16:12:53 +0200
Subject: [PATCH 1176/1806] selftests: openvswitch: add drop reason testcase

Test if the correct drop reason is reported when OVS drops a packet due
to an explicit flow.

Acked-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/openvswitch/openvswitch.sh  | 67 ++++++++++++++++++-
 1 file changed, 66 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index dced4f612a78c..a10c345f40ef2 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -16,7 +16,8 @@ tests="
 	connect_v4				ip4-xon: Basic ipv4 ping between two NS
 	nat_connect_v4				ip4-nat-xon: Basic ipv4 tcp connection via NAT
 	netlink_checks				ovsnl: validate netlink attrs and settings
-	upcall_interfaces			ovs: test the upcall interfaces"
+	upcall_interfaces			ovs: test the upcall interfaces
+	drop_reason				drop: test drop reasons are emitted"
 
 info() {
     [ $VERBOSE = 0 ] || echo $*
@@ -141,6 +142,25 @@ ovs_add_flow () {
 	return 0
 }
 
+ovs_drop_record_and_run () {
+	local sbx=$1
+	shift
+
+	perf record -a -q -e skb:kfree_skb -o ${ovs_dir}/perf.data $* \
+		>> ${ovs_dir}/stdout 2>> ${ovs_dir}/stderr
+	return $?
+}
+
+ovs_drop_reason_count()
+{
+	local reason=$1
+
+	local perf_output=`perf script -i ${ovs_dir}/perf.data -F trace:event,trace`
+	local pattern="skb:kfree_skb:.*reason: $reason"
+
+	return `echo "$perf_output" | grep "$pattern" | wc -l`
+}
+
 usage() {
 	echo
 	echo "$0 [OPTIONS] [TEST]..."
@@ -155,6 +175,51 @@ usage() {
 	exit 1
 }
 
+# drop_reason test
+# - drop packets and verify the right drop reason is reported
+test_drop_reason() {
+	which perf >/dev/null 2>&1 || return $ksft_skip
+
+	sbx_add "test_drop_reason" || return $?
+
+	ovs_add_dp "test_drop_reason" dropreason || return 1
+
+	info "create namespaces"
+	for ns in client server; do
+		ovs_add_netns_and_veths "test_drop_reason" "dropreason" "$ns" \
+			"${ns:0:1}0" "${ns:0:1}1" || return 1
+	done
+
+	# Setup client namespace
+	ip netns exec client ip addr add 172.31.110.10/24 dev c1
+	ip netns exec client ip link set c1 up
+
+	# Setup server namespace
+	ip netns exec server ip addr add 172.31.110.20/24 dev s1
+	ip netns exec server ip link set s1 up
+
+	# Allow ARP
+	ovs_add_flow "test_drop_reason" dropreason \
+		'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1
+	ovs_add_flow "test_drop_reason" dropreason \
+		'in_port(2),eth(),eth_type(0x0806),arp()' '1' || return 1
+
+	# Allow client ICMP traffic but drop return path
+	ovs_add_flow "test_drop_reason" dropreason \
+		"in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10,proto=1),icmp()" '2'
+	ovs_add_flow "test_drop_reason" dropreason \
+		"in_port(2),eth(),eth_type(0x0800),ipv4(src=172.31.110.20,proto=1),icmp()" 'drop'
+
+	ovs_drop_record_and_run "test_drop_reason" ip netns exec client ping -c 2 172.31.110.20
+	ovs_drop_reason_count 0x30001 # OVS_DROP_FLOW_ACTION
+	if [[ "$?" -ne "2" ]]; then
+		info "Did not detect expected drops: $?"
+		return 1
+	fi
+
+	return 0
+}
+
 # arp_ping test
 # - client has 1500 byte MTU
 # - server has 1500 byte MTU
-- 
GitLab


From 4242029164d6e675d4695e3420399eece29ec599 Mon Sep 17 00:00:00 2001
From: Adrian Moreno <amorenoz@redhat.com>
Date: Fri, 11 Aug 2023 16:12:54 +0200
Subject: [PATCH 1177/1806] selftests: openvswitch: add explicit drop testcase

Test explicit drops generate the right drop reason. Also, verify that
the kernel rejects flows with actions following an explicit drop.

Acked-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/openvswitch/openvswitch.sh  | 35 +++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index a10c345f40ef2..9c2012d70b08e 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -217,6 +217,31 @@ test_drop_reason() {
 		return 1
 	fi
 
+	# Drop UDP 6000 traffic with an explicit action and an error code.
+	ovs_add_flow "test_drop_reason" dropreason \
+		"in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10,proto=17),udp(dst=6000)" \
+                'drop(42)'
+	# Drop UDP 7000 traffic with an explicit action with no error code.
+	ovs_add_flow "test_drop_reason" dropreason \
+		"in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10,proto=17),udp(dst=7000)" \
+                'drop(0)'
+
+	ovs_drop_record_and_run \
+            "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 6000
+	ovs_drop_reason_count 0x30004 # OVS_DROP_EXPLICIT_ACTION_ERROR
+	if [[ "$?" -ne "1" ]]; then
+		info "Did not detect expected explicit error drops: $?"
+		return 1
+	fi
+
+	ovs_drop_record_and_run \
+            "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 7000
+	ovs_drop_reason_count 0x30003 # OVS_DROP_EXPLICIT_ACTION
+	if [[ "$?" -ne "1" ]]; then
+		info "Did not detect expected explicit drops: $?"
+		return 1
+	fi
+
 	return 0
 }
 
@@ -458,6 +483,16 @@ test_netlink_checks () {
 	    wc -l) == 2 ] || \
 	      return 1
 
+	ERR_MSG="Flow actions may not be safe on all matching packets"
+	PRE_TEST=$(dmesg | grep -c "${ERR_MSG}")
+	ovs_add_flow "test_netlink_checks" nv0 \
+		'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(0),2' \
+		&> /dev/null && return 1
+	POST_TEST=$(dmesg | grep -c "${ERR_MSG}")
+	if [ "$PRE_TEST" == "$POST_TEST" ]; then
+		info "failed - error not generated"
+		return 1
+	fi
 	return 0
 }
 
-- 
GitLab


From 54f00cce11786742bd11e5e68c3bf85e6dc048c9 Mon Sep 17 00:00:00 2001
From: William Tu <u9012063@gmail.com>
Date: Wed, 9 Aug 2023 21:13:04 -0700
Subject: [PATCH 1178/1806] vmxnet3: Add XDP support.

The patch adds native-mode XDP support: XDP DROP, PASS, TX, and REDIRECT.

Background:
The vmxnet3 rx consists of three rings: ring0, ring1, and dataring.
For r0 and r1, buffers at r0 are allocated using alloc_skb APIs and dma
mapped to the ring's descriptor. If LRO is enabled and packet size larger
than 3K, VMXNET3_MAX_SKB_BUF_SIZE, then r1 is used to mapped the rest of
the buffer larger than VMXNET3_MAX_SKB_BUF_SIZE. Each buffer in r1 is
allocated using alloc_page. So for LRO packets, the payload will be in one
buffer from r0 and multiple from r1, for non-LRO packets, only one
descriptor in r0 is used for packet size less than 3k.

When receiving a packet, the first descriptor will have the sop (start of
packet) bit set, and the last descriptor will have the eop (end of packet)
bit set. Non-LRO packets will have only one descriptor with both sop and
eop set.

Other than r0 and r1, vmxnet3 dataring is specifically designed for
handling packets with small size, usually 128 bytes, defined in
VMXNET3_DEF_RXDATA_DESC_SIZE, by simply copying the packet from the backend
driver in ESXi to the ring's memory region at front-end vmxnet3 driver, in
order to avoid memory mapping/unmapping overhead. In summary, packet size:
    A. < 128B: use dataring
    B. 128B - 3K: use ring0 (VMXNET3_RX_BUF_SKB)
    C. > 3K: use ring0 and ring1 (VMXNET3_RX_BUF_SKB + VMXNET3_RX_BUF_PAGE)
As a result, the patch adds XDP support for packets using dataring
and r0 (case A and B), not the large packet size when LRO is enabled.

XDP Implementation:
When user loads and XDP prog, vmxnet3 driver checks configurations, such
as mtu, lro, and re-allocate the rx buffer size for reserving the extra
headroom, XDP_PACKET_HEADROOM, for XDP frame. The XDP prog will then be
associated with every rx queue of the device. Note that when using dataring
for small packet size, vmxnet3 (front-end driver) doesn't control the
buffer allocation, as a result we allocate a new page and copy packet
from the dataring to XDP frame.

The receive side of XDP is implemented for case A and B, by invoking the
bpf program at vmxnet3_rq_rx_complete and handle its returned action.
The vmxnet3_process_xdp(), vmxnet3_process_xdp_small() function handles
the ring0 and dataring case separately, and decides the next journey of
the packet afterward.

For TX, vmxnet3 has split header design. Outgoing packets are parsed
first and protocol headers (L2/L3/L4) are copied to the backend. The
rest of the payload are dma mapped. Since XDP_TX does not parse the
packet protocol, the entire XDP frame is dma mapped for transmission
and transmitted in a batch. Later on, the frame is freed and recycled
back to the memory pool.

Performance:
Tested using two VMs inside one ESXi vSphere 7.0 machine, using single
core on each vmxnet3 device, sender using DPDK testpmd tx-mode attached
to vmxnet3 device, sending 64B or 512B UDP packet.

VM1 txgen:
$ dpdk-testpmd -l 0-3 -n 1 -- -i --nb-cores=3 \
--forward-mode=txonly --eth-peer=0,<mac addr of vm2>
option: add "--txonly-multi-flow"
option: use --txpkts=512 or 64 byte

VM2 running XDP:
$ ./samples/bpf/xdp_rxq_info -d ens160 -a <options> --skb-mode
$ ./samples/bpf/xdp_rxq_info -d ens160 -a <options>
options: XDP_DROP, XDP_PASS, XDP_TX

To test REDIRECT to cpu 0, use
$ ./samples/bpf/xdp_redirect_cpu -d ens160 -c 0 -e drop

Single core performance comparison with skb-mode.
64B:      skb-mode -> native-mode
XDP_DROP: 1.6Mpps -> 2.4Mpps
XDP_PASS: 338Kpps -> 367Kpps
XDP_TX:   1.1Mpps -> 2.3Mpps
REDIRECT-drop: 1.3Mpps -> 2.3Mpps

512B:     skb-mode -> native-mode
XDP_DROP: 863Kpps -> 1.3Mpps
XDP_PASS: 275Kpps -> 376Kpps
XDP_TX:   554Kpps -> 1.2Mpps
REDIRECT-drop: 659Kpps -> 1.2Mpps

Demo: https://youtu.be/4lm1CSCi78Q

Future work:
- XDP frag support
- use napi_consume_skb() instead of dev_kfree_skb_any at unmap
- stats using u64_stats_t
- using bitfield macro BIT()
- optimization for DMA synchronization using actual frame length,
  instead of always max_len

Signed-off-by: William Tu <u9012063@gmail.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/Kconfig                   |   1 +
 drivers/net/vmxnet3/Makefile          |   2 +-
 drivers/net/vmxnet3/vmxnet3_drv.c     | 236 +++++++++++++--
 drivers/net/vmxnet3/vmxnet3_ethtool.c |  23 ++
 drivers/net/vmxnet3/vmxnet3_int.h     |  43 ++-
 drivers/net/vmxnet3/vmxnet3_xdp.c     | 419 ++++++++++++++++++++++++++
 drivers/net/vmxnet3/vmxnet3_xdp.h     |  47 +++
 7 files changed, 729 insertions(+), 42 deletions(-)
 create mode 100644 drivers/net/vmxnet3/vmxnet3_xdp.c
 create mode 100644 drivers/net/vmxnet3/vmxnet3_xdp.h

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 4953c14947234..be43cd08027b5 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -571,6 +571,7 @@ config VMXNET3
 	tristate "VMware VMXNET3 ethernet driver"
 	depends on PCI && INET
 	depends on PAGE_SIZE_LESS_THAN_64KB
+	select PAGE_POOL
 	help
 	  This driver supports VMware's vmxnet3 virtual ethernet NIC.
 	  To compile this driver as a module, choose M here: the
diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile
index a666a88ac1ffa..f82870c10205a 100644
--- a/drivers/net/vmxnet3/Makefile
+++ b/drivers/net/vmxnet3/Makefile
@@ -32,4 +32,4 @@
 
 obj-$(CONFIG_VMXNET3) += vmxnet3.o
 
-vmxnet3-objs := vmxnet3_drv.o vmxnet3_ethtool.o
+vmxnet3-objs := vmxnet3_drv.o vmxnet3_ethtool.o vmxnet3_xdp.o
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 7fa74b8b21001..0578864792b60 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -28,6 +28,7 @@
 #include <net/ip6_checksum.h>
 
 #include "vmxnet3_int.h"
+#include "vmxnet3_xdp.h"
 
 char vmxnet3_driver_name[] = "vmxnet3";
 #define VMXNET3_DRIVER_DESC "VMware vmxnet3 virtual NIC driver"
@@ -338,14 +339,16 @@ static void
 vmxnet3_unmap_tx_buf(struct vmxnet3_tx_buf_info *tbi,
 		     struct pci_dev *pdev)
 {
-	if (tbi->map_type == VMXNET3_MAP_SINGLE)
+	u32 map_type = tbi->map_type;
+
+	if (map_type & VMXNET3_MAP_SINGLE)
 		dma_unmap_single(&pdev->dev, tbi->dma_addr, tbi->len,
 				 DMA_TO_DEVICE);
-	else if (tbi->map_type == VMXNET3_MAP_PAGE)
+	else if (map_type & VMXNET3_MAP_PAGE)
 		dma_unmap_page(&pdev->dev, tbi->dma_addr, tbi->len,
 			       DMA_TO_DEVICE);
 	else
-		BUG_ON(tbi->map_type != VMXNET3_MAP_NONE);
+		BUG_ON(map_type & ~VMXNET3_MAP_XDP);
 
 	tbi->map_type = VMXNET3_MAP_NONE; /* to help debugging */
 }
@@ -353,19 +356,20 @@ vmxnet3_unmap_tx_buf(struct vmxnet3_tx_buf_info *tbi,
 
 static int
 vmxnet3_unmap_pkt(u32 eop_idx, struct vmxnet3_tx_queue *tq,
-		  struct pci_dev *pdev,	struct vmxnet3_adapter *adapter)
+		  struct pci_dev *pdev,	struct vmxnet3_adapter *adapter,
+		  struct xdp_frame_bulk *bq)
 {
-	struct sk_buff *skb;
+	struct vmxnet3_tx_buf_info *tbi;
 	int entries = 0;
+	u32 map_type;
 
 	/* no out of order completion */
 	BUG_ON(tq->buf_info[eop_idx].sop_idx != tq->tx_ring.next2comp);
 	BUG_ON(VMXNET3_TXDESC_GET_EOP(&(tq->tx_ring.base[eop_idx].txd)) != 1);
 
-	skb = tq->buf_info[eop_idx].skb;
-	BUG_ON(skb == NULL);
-	tq->buf_info[eop_idx].skb = NULL;
-
+	tbi = &tq->buf_info[eop_idx];
+	BUG_ON(!tbi->skb);
+	map_type = tbi->map_type;
 	VMXNET3_INC_RING_IDX_ONLY(eop_idx, tq->tx_ring.size);
 
 	while (tq->tx_ring.next2comp != eop_idx) {
@@ -381,7 +385,14 @@ vmxnet3_unmap_pkt(u32 eop_idx, struct vmxnet3_tx_queue *tq,
 		entries++;
 	}
 
-	dev_kfree_skb_any(skb);
+	if (map_type & VMXNET3_MAP_XDP)
+		xdp_return_frame_bulk(tbi->xdpf, bq);
+	else
+		dev_kfree_skb_any(tbi->skb);
+
+	/* xdpf and skb are in an anonymous union. */
+	tbi->skb = NULL;
+
 	return entries;
 }
 
@@ -390,8 +401,12 @@ static int
 vmxnet3_tq_tx_complete(struct vmxnet3_tx_queue *tq,
 			struct vmxnet3_adapter *adapter)
 {
-	int completed = 0;
 	union Vmxnet3_GenericDesc *gdesc;
+	struct xdp_frame_bulk bq;
+	int completed = 0;
+
+	xdp_frame_bulk_init(&bq);
+	rcu_read_lock();
 
 	gdesc = tq->comp_ring.base + tq->comp_ring.next2proc;
 	while (VMXNET3_TCD_GET_GEN(&gdesc->tcd) == tq->comp_ring.gen) {
@@ -402,11 +417,13 @@ vmxnet3_tq_tx_complete(struct vmxnet3_tx_queue *tq,
 
 		completed += vmxnet3_unmap_pkt(VMXNET3_TCD_GET_TXIDX(
 					       &gdesc->tcd), tq, adapter->pdev,
-					       adapter);
+					       adapter, &bq);
 
 		vmxnet3_comp_ring_adv_next2proc(&tq->comp_ring);
 		gdesc = tq->comp_ring.base + tq->comp_ring.next2proc;
 	}
+	xdp_flush_frame_bulk(&bq);
+	rcu_read_unlock();
 
 	if (completed) {
 		spin_lock(&tq->tx_lock);
@@ -426,26 +443,36 @@ static void
 vmxnet3_tq_cleanup(struct vmxnet3_tx_queue *tq,
 		   struct vmxnet3_adapter *adapter)
 {
+	struct xdp_frame_bulk bq;
+	u32 map_type;
 	int i;
 
+	xdp_frame_bulk_init(&bq);
+	rcu_read_lock();
+
 	while (tq->tx_ring.next2comp != tq->tx_ring.next2fill) {
 		struct vmxnet3_tx_buf_info *tbi;
 
 		tbi = tq->buf_info + tq->tx_ring.next2comp;
+		map_type = tbi->map_type;
 
 		vmxnet3_unmap_tx_buf(tbi, adapter->pdev);
 		if (tbi->skb) {
-			dev_kfree_skb_any(tbi->skb);
+			if (map_type & VMXNET3_MAP_XDP)
+				xdp_return_frame_bulk(tbi->xdpf, &bq);
+			else
+				dev_kfree_skb_any(tbi->skb);
 			tbi->skb = NULL;
 		}
 		vmxnet3_cmd_ring_adv_next2comp(&tq->tx_ring);
 	}
 
-	/* sanity check, verify all buffers are indeed unmapped and freed */
-	for (i = 0; i < tq->tx_ring.size; i++) {
-		BUG_ON(tq->buf_info[i].skb != NULL ||
-		       tq->buf_info[i].map_type != VMXNET3_MAP_NONE);
-	}
+	xdp_flush_frame_bulk(&bq);
+	rcu_read_unlock();
+
+	/* sanity check, verify all buffers are indeed unmapped */
+	for (i = 0; i < tq->tx_ring.size; i++)
+		BUG_ON(tq->buf_info[i].map_type != VMXNET3_MAP_NONE);
 
 	tq->tx_ring.gen = VMXNET3_INIT_GEN;
 	tq->tx_ring.next2fill = tq->tx_ring.next2comp = 0;
@@ -599,7 +626,17 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
 		gd = ring->base + ring->next2fill;
 		rbi->comp_state = VMXNET3_RXD_COMP_PENDING;
 
-		if (rbi->buf_type == VMXNET3_RX_BUF_SKB) {
+		if (rbi->buf_type == VMXNET3_RX_BUF_XDP) {
+			void *data = vmxnet3_pp_get_buff(rq->page_pool,
+							 &rbi->dma_addr,
+							 GFP_KERNEL);
+			if (!data) {
+				rq->stats.rx_buf_alloc_failure++;
+				break;
+			}
+			rbi->page = virt_to_page(data);
+			val = VMXNET3_RXD_BTYPE_HEAD << VMXNET3_RXD_BTYPE_SHIFT;
+		} else if (rbi->buf_type == VMXNET3_RX_BUF_SKB) {
 			if (rbi->skb == NULL) {
 				rbi->skb = __netdev_alloc_skb_ip_align(adapter->netdev,
 								       rbi->len,
@@ -1263,6 +1300,63 @@ drop_pkt:
 	return NETDEV_TX_OK;
 }
 
+static int
+vmxnet3_create_pp(struct vmxnet3_adapter *adapter,
+		  struct vmxnet3_rx_queue *rq, int size)
+{
+	bool xdp_prog = vmxnet3_xdp_enabled(adapter);
+	const struct page_pool_params pp_params = {
+		.order = 0,
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+		.pool_size = size,
+		.nid = NUMA_NO_NODE,
+		.dev = &adapter->pdev->dev,
+		.offset = VMXNET3_XDP_RX_OFFSET,
+		.max_len = VMXNET3_XDP_MAX_FRSIZE,
+		.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
+	};
+	struct page_pool *pp;
+	int err;
+
+	pp = page_pool_create(&pp_params);
+	if (IS_ERR(pp))
+		return PTR_ERR(pp);
+
+	err = xdp_rxq_info_reg(&rq->xdp_rxq, adapter->netdev, rq->qid,
+			       rq->napi.napi_id);
+	if (err < 0)
+		goto err_free_pp;
+
+	err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_POOL, pp);
+	if (err)
+		goto err_unregister_rxq;
+
+	rq->page_pool = pp;
+
+	return 0;
+
+err_unregister_rxq:
+	xdp_rxq_info_unreg(&rq->xdp_rxq);
+err_free_pp:
+	page_pool_destroy(pp);
+
+	return err;
+}
+
+void *
+vmxnet3_pp_get_buff(struct page_pool *pp, dma_addr_t *dma_addr,
+		    gfp_t gfp_mask)
+{
+	struct page *page;
+
+	page = page_pool_alloc_pages(pp, gfp_mask | __GFP_NOWARN);
+	if (unlikely(!page))
+		return NULL;
+
+	*dma_addr = page_pool_get_dma_addr(page) + pp->p.offset;
+
+	return page_address(page);
+}
 
 static netdev_tx_t
 vmxnet3_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
@@ -1423,6 +1517,8 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 	struct Vmxnet3_RxDesc rxCmdDesc;
 	struct Vmxnet3_RxCompDesc rxComp;
 #endif
+	bool need_flush = false;
+
 	vmxnet3_getRxComp(rcd, &rq->comp_ring.base[rq->comp_ring.next2proc].rcd,
 			  &rxComp);
 	while (rcd->gen == rq->comp_ring.gen) {
@@ -1463,6 +1559,31 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 			goto rcd_done;
 		}
 
+		if (rcd->sop && rcd->eop && vmxnet3_xdp_enabled(adapter)) {
+			struct sk_buff *skb_xdp_pass;
+			int act;
+
+			if (VMXNET3_RX_DATA_RING(adapter, rcd->rqID)) {
+				ctx->skb = NULL;
+				goto skip_xdp; /* Handle it later. */
+			}
+
+			if (rbi->buf_type != VMXNET3_RX_BUF_XDP)
+				goto rcd_done;
+
+			act = vmxnet3_process_xdp(adapter, rq, rcd, rbi, rxd,
+						  &skb_xdp_pass);
+			if (act == XDP_PASS) {
+				ctx->skb = skb_xdp_pass;
+				goto sop_done;
+			}
+			ctx->skb = NULL;
+			need_flush |= act == XDP_REDIRECT;
+
+			goto rcd_done;
+		}
+skip_xdp:
+
 		if (rcd->sop) { /* first buf of the pkt */
 			bool rxDataRingUsed;
 			u16 len;
@@ -1471,7 +1592,8 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 			       (rcd->rqID != rq->qid &&
 				rcd->rqID != rq->dataRingQid));
 
-			BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_SKB);
+			BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_SKB &&
+			       rbi->buf_type != VMXNET3_RX_BUF_XDP);
 			BUG_ON(ctx->skb != NULL || rbi->skb == NULL);
 
 			if (unlikely(rcd->len == 0)) {
@@ -1489,6 +1611,25 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 			rxDataRingUsed =
 				VMXNET3_RX_DATA_RING(adapter, rcd->rqID);
 			len = rxDataRingUsed ? rcd->len : rbi->len;
+
+			if (rxDataRingUsed && vmxnet3_xdp_enabled(adapter)) {
+				struct sk_buff *skb_xdp_pass;
+				size_t sz;
+				int act;
+
+				sz = rcd->rxdIdx * rq->data_ring.desc_size;
+				act = vmxnet3_process_xdp_small(adapter, rq,
+								&rq->data_ring.base[sz],
+								rcd->len,
+								&skb_xdp_pass);
+				if (act == XDP_PASS) {
+					ctx->skb = skb_xdp_pass;
+					goto sop_done;
+				}
+				need_flush |= act == XDP_REDIRECT;
+
+				goto rcd_done;
+			}
 			new_skb = netdev_alloc_skb_ip_align(adapter->netdev,
 							    len);
 			if (new_skb == NULL) {
@@ -1621,6 +1762,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 		}
 
 
+sop_done:
 		skb = ctx->skb;
 		if (rcd->eop) {
 			u32 mtu = adapter->netdev->mtu;
@@ -1757,6 +1899,8 @@ refill_buf:
 		vmxnet3_getRxComp(rcd,
 				  &rq->comp_ring.base[rq->comp_ring.next2proc].rcd, &rxComp);
 	}
+	if (need_flush)
+		xdp_do_flush();
 
 	return num_pkts;
 }
@@ -1775,24 +1919,32 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq,
 
 	for (ring_idx = 0; ring_idx < 2; ring_idx++) {
 		for (i = 0; i < rq->rx_ring[ring_idx].size; i++) {
+			struct vmxnet3_rx_buf_info *rbi;
 #ifdef __BIG_ENDIAN_BITFIELD
 			struct Vmxnet3_RxDesc rxDesc;
 #endif
+
+			rbi = &rq->buf_info[ring_idx][i];
 			vmxnet3_getRxDesc(rxd,
 				&rq->rx_ring[ring_idx].base[i].rxd, &rxDesc);
 
 			if (rxd->btype == VMXNET3_RXD_BTYPE_HEAD &&
-					rq->buf_info[ring_idx][i].skb) {
+			    rbi->page && rbi->buf_type == VMXNET3_RX_BUF_XDP) {
+				page_pool_recycle_direct(rq->page_pool,
+							 rbi->page);
+				rbi->page = NULL;
+			} else if (rxd->btype == VMXNET3_RXD_BTYPE_HEAD &&
+				   rbi->skb) {
 				dma_unmap_single(&adapter->pdev->dev, rxd->addr,
 						 rxd->len, DMA_FROM_DEVICE);
-				dev_kfree_skb(rq->buf_info[ring_idx][i].skb);
-				rq->buf_info[ring_idx][i].skb = NULL;
+				dev_kfree_skb(rbi->skb);
+				rbi->skb = NULL;
 			} else if (rxd->btype == VMXNET3_RXD_BTYPE_BODY &&
-					rq->buf_info[ring_idx][i].page) {
+				   rbi->page) {
 				dma_unmap_page(&adapter->pdev->dev, rxd->addr,
 					       rxd->len, DMA_FROM_DEVICE);
-				put_page(rq->buf_info[ring_idx][i].page);
-				rq->buf_info[ring_idx][i].page = NULL;
+				put_page(rbi->page);
+				rbi->page = NULL;
 			}
 		}
 
@@ -1813,6 +1965,7 @@ vmxnet3_rq_cleanup_all(struct vmxnet3_adapter *adapter)
 
 	for (i = 0; i < adapter->num_rx_queues; i++)
 		vmxnet3_rq_cleanup(&adapter->rx_queue[i], adapter);
+	rcu_assign_pointer(adapter->xdp_bpf_prog, NULL);
 }
 
 
@@ -1842,6 +1995,11 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 		}
 	}
 
+	if (xdp_rxq_info_is_reg(&rq->xdp_rxq))
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
+	page_pool_destroy(rq->page_pool);
+	rq->page_pool = NULL;
+
 	if (rq->data_ring.base) {
 		dma_free_coherent(&adapter->pdev->dev,
 				  rq->rx_ring[0].size * rq->data_ring.desc_size,
@@ -1885,14 +2043,16 @@ static int
 vmxnet3_rq_init(struct vmxnet3_rx_queue *rq,
 		struct vmxnet3_adapter  *adapter)
 {
-	int i;
+	int i, err;
 
 	/* initialize buf_info */
 	for (i = 0; i < rq->rx_ring[0].size; i++) {
 
-		/* 1st buf for a pkt is skbuff */
+		/* 1st buf for a pkt is skbuff or xdp page */
 		if (i % adapter->rx_buf_per_pkt == 0) {
-			rq->buf_info[0][i].buf_type = VMXNET3_RX_BUF_SKB;
+			rq->buf_info[0][i].buf_type = vmxnet3_xdp_enabled(adapter) ?
+						      VMXNET3_RX_BUF_XDP :
+						      VMXNET3_RX_BUF_SKB;
 			rq->buf_info[0][i].len = adapter->skb_buf_size;
 		} else { /* subsequent bufs for a pkt is frag */
 			rq->buf_info[0][i].buf_type = VMXNET3_RX_BUF_PAGE;
@@ -1913,8 +2073,18 @@ vmxnet3_rq_init(struct vmxnet3_rx_queue *rq,
 		rq->rx_ring[i].gen = VMXNET3_INIT_GEN;
 		rq->rx_ring[i].isOutOfOrder = 0;
 	}
+
+	err = vmxnet3_create_pp(adapter, rq,
+				rq->rx_ring[0].size + rq->rx_ring[1].size);
+	if (err)
+		return err;
+
 	if (vmxnet3_rq_alloc_rx_buf(rq, 0, rq->rx_ring[0].size - 1,
 				    adapter) == 0) {
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
+		page_pool_destroy(rq->page_pool);
+		rq->page_pool = NULL;
+
 		/* at least has 1 rx buffer for the 1st ring */
 		return -ENOMEM;
 	}
@@ -2016,7 +2186,7 @@ err:
 }
 
 
-static int
+int
 vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter)
 {
 	int i, err = 0;
@@ -3053,7 +3223,7 @@ vmxnet3_free_pci_resources(struct vmxnet3_adapter *adapter)
 }
 
 
-static void
+void
 vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter)
 {
 	size_t sz, i, ring0_size, ring1_size, comp_size;
@@ -3612,6 +3782,8 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 		.ndo_poll_controller = vmxnet3_netpoll,
 #endif
+		.ndo_bpf = vmxnet3_xdp,
+		.ndo_xdp_xmit = vmxnet3_xdp_xmit,
 	};
 	int err;
 	u32 ver;
@@ -3864,6 +4036,8 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 	vmxnet3_declare_features(adapter);
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_NDO_XMIT;
 
 	adapter->rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ?
 		VMXNET3_DEF_RXDATA_DESC_SIZE : 0;
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 18cf7c7232010..98c22d7d87a2a 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -28,6 +28,7 @@
 #include "vmxnet3_int.h"
 #include <net/vxlan.h>
 #include <net/geneve.h>
+#include "vmxnet3_xdp.h"
 
 #define VXLAN_UDP_PORT 8472
 
@@ -76,6 +77,10 @@ vmxnet3_tq_driver_stats[] = {
 					 copy_skb_header) },
 	{ "  giant hdr",	offsetof(struct vmxnet3_tq_driver_stats,
 					 oversized_hdr) },
+	{ "  xdp xmit",		offsetof(struct vmxnet3_tq_driver_stats,
+					 xdp_xmit) },
+	{ "  xdp xmit err",	offsetof(struct vmxnet3_tq_driver_stats,
+					 xdp_xmit_err) },
 };
 
 /* per rq stats maintained by the device */
@@ -106,6 +111,16 @@ vmxnet3_rq_driver_stats[] = {
 					 drop_fcs) },
 	{ "  rx buf alloc fail", offsetof(struct vmxnet3_rq_driver_stats,
 					  rx_buf_alloc_failure) },
+	{ "     xdp packets", offsetof(struct vmxnet3_rq_driver_stats,
+				       xdp_packets) },
+	{ "     xdp tx", offsetof(struct vmxnet3_rq_driver_stats,
+				  xdp_tx) },
+	{ "     xdp redirects", offsetof(struct vmxnet3_rq_driver_stats,
+					 xdp_redirects) },
+	{ "     xdp drops", offsetof(struct vmxnet3_rq_driver_stats,
+				     xdp_drops) },
+	{ "     xdp aborted", offsetof(struct vmxnet3_rq_driver_stats,
+				       xdp_aborted) },
 };
 
 /* global stats maintained by the driver */
@@ -249,10 +264,18 @@ vmxnet3_get_strings(struct net_device *netdev, u32 stringset, u8 *buf)
 netdev_features_t vmxnet3_fix_features(struct net_device *netdev,
 				       netdev_features_t features)
 {
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+
 	/* If Rx checksum is disabled, then LRO should also be disabled */
 	if (!(features & NETIF_F_RXCSUM))
 		features &= ~NETIF_F_LRO;
 
+	/* If XDP is enabled, then LRO should not be enabled */
+	if (vmxnet3_xdp_enabled(adapter) && (features & NETIF_F_LRO)) {
+		netdev_err(netdev, "LRO is not supported with XDP");
+		features &= ~NETIF_F_LRO;
+	}
+
 	return features;
 }
 
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 3367db23aa13c..915aaf18c4094 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -56,6 +56,9 @@
 #include <linux/if_arp.h>
 #include <linux/inetdevice.h>
 #include <linux/log2.h>
+#include <linux/bpf.h>
+#include <net/page_pool/helpers.h>
+#include <net/xdp.h>
 
 #include "vmxnet3_defs.h"
 
@@ -188,19 +191,20 @@ struct vmxnet3_tx_data_ring {
 	dma_addr_t          basePA;
 };
 
-enum vmxnet3_buf_map_type {
-	VMXNET3_MAP_INVALID = 0,
-	VMXNET3_MAP_NONE,
-	VMXNET3_MAP_SINGLE,
-	VMXNET3_MAP_PAGE,
-};
+#define VMXNET3_MAP_NONE	0
+#define VMXNET3_MAP_SINGLE	BIT(0)
+#define VMXNET3_MAP_PAGE	BIT(1)
+#define VMXNET3_MAP_XDP		BIT(2)
 
 struct vmxnet3_tx_buf_info {
 	u32      map_type;
 	u16      len;
 	u16      sop_idx;
 	dma_addr_t  dma_addr;
-	struct sk_buff *skb;
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdpf;
+	};
 };
 
 struct vmxnet3_tq_driver_stats {
@@ -217,6 +221,9 @@ struct vmxnet3_tq_driver_stats {
 	u64 linearized;         /* # of pkts linearized */
 	u64 copy_skb_header;    /* # of times we have to copy skb header */
 	u64 oversized_hdr;
+
+	u64 xdp_xmit;
+	u64 xdp_xmit_err;
 };
 
 struct vmxnet3_tx_ctx {
@@ -253,12 +260,13 @@ struct vmxnet3_tx_queue {
 						    * stopped */
 	int				qid;
 	u16				txdata_desc_size;
-} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+} ____cacheline_aligned;
 
 enum vmxnet3_rx_buf_type {
 	VMXNET3_RX_BUF_NONE = 0,
 	VMXNET3_RX_BUF_SKB = 1,
-	VMXNET3_RX_BUF_PAGE = 2
+	VMXNET3_RX_BUF_PAGE = 2,
+	VMXNET3_RX_BUF_XDP = 3,
 };
 
 #define VMXNET3_RXD_COMP_PENDING        0
@@ -285,6 +293,12 @@ struct vmxnet3_rq_driver_stats {
 	u64 drop_err;
 	u64 drop_fcs;
 	u64 rx_buf_alloc_failure;
+
+	u64 xdp_packets;	/* Total packets processed by XDP. */
+	u64 xdp_tx;
+	u64 xdp_redirects;
+	u64 xdp_drops;
+	u64 xdp_aborted;
 };
 
 struct vmxnet3_rx_data_ring {
@@ -307,7 +321,9 @@ struct vmxnet3_rx_queue {
 	struct vmxnet3_rx_buf_info     *buf_info[2];
 	struct Vmxnet3_RxQueueCtrl            *shared;
 	struct vmxnet3_rq_driver_stats  stats;
-} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+	struct page_pool *page_pool;
+	struct xdp_rxq_info xdp_rxq;
+} ____cacheline_aligned;
 
 #define VMXNET3_DEVICE_MAX_TX_QUEUES 32
 #define VMXNET3_DEVICE_MAX_RX_QUEUES 32   /* Keep this value as a power of 2 */
@@ -415,6 +431,7 @@ struct vmxnet3_adapter {
 	u16    tx_prod_offset;
 	u16    rx_prod_offset;
 	u16    rx_prod2_offset;
+	struct bpf_prog __rcu *xdp_bpf_prog;
 };
 
 #define VMXNET3_WRITE_BAR0_REG(adapter, reg, val)  \
@@ -490,6 +507,12 @@ vmxnet3_tq_destroy_all(struct vmxnet3_adapter *adapter);
 void
 vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter);
 
+int
+vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter);
+
+void
+vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter);
+
 netdev_features_t
 vmxnet3_fix_features(struct net_device *netdev, netdev_features_t features);
 
diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c
new file mode 100644
index 0000000000000..80ddaff759d47
--- /dev/null
+++ b/drivers/net/vmxnet3/vmxnet3_xdp.c
@@ -0,0 +1,419 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Linux driver for VMware's vmxnet3 ethernet NIC.
+ * Copyright (C) 2008-2023, VMware, Inc. All Rights Reserved.
+ * Maintained by: pv-drivers@vmware.com
+ *
+ */
+
+#include "vmxnet3_int.h"
+#include "vmxnet3_xdp.h"
+
+static void
+vmxnet3_xdp_exchange_program(struct vmxnet3_adapter *adapter,
+			     struct bpf_prog *prog)
+{
+	rcu_assign_pointer(adapter->xdp_bpf_prog, prog);
+}
+
+static inline struct vmxnet3_tx_queue *
+vmxnet3_xdp_get_tq(struct vmxnet3_adapter *adapter)
+{
+	struct vmxnet3_tx_queue *tq;
+	int tq_number;
+	int cpu;
+
+	tq_number = adapter->num_tx_queues;
+	cpu = smp_processor_id();
+	if (likely(cpu < tq_number))
+		tq = &adapter->tx_queue[cpu];
+	else
+		tq = &adapter->tx_queue[reciprocal_scale(cpu, tq_number)];
+
+	return tq;
+}
+
+static int
+vmxnet3_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf,
+		struct netlink_ext_ack *extack)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	struct bpf_prog *new_bpf_prog = bpf->prog;
+	struct bpf_prog *old_bpf_prog;
+	bool need_update;
+	bool running;
+	int err;
+
+	if (new_bpf_prog && netdev->mtu > VMXNET3_XDP_MAX_MTU) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "MTU %u too large for XDP",
+				       netdev->mtu);
+		return -EOPNOTSUPP;
+	}
+
+	if (adapter->netdev->features & NETIF_F_LRO) {
+		NL_SET_ERR_MSG_MOD(extack, "LRO is not supported with XDP");
+		adapter->netdev->features &= ~NETIF_F_LRO;
+	}
+
+	old_bpf_prog = rcu_dereference(adapter->xdp_bpf_prog);
+	if (!new_bpf_prog && !old_bpf_prog)
+		return 0;
+
+	running = netif_running(netdev);
+	need_update = !!old_bpf_prog != !!new_bpf_prog;
+
+	if (running && need_update)
+		vmxnet3_quiesce_dev(adapter);
+
+	vmxnet3_xdp_exchange_program(adapter, new_bpf_prog);
+	if (old_bpf_prog)
+		bpf_prog_put(old_bpf_prog);
+
+	if (!running || !need_update)
+		return 0;
+
+	if (new_bpf_prog)
+		xdp_features_set_redirect_target(netdev, false);
+	else
+		xdp_features_clear_redirect_target(netdev);
+
+	vmxnet3_reset_dev(adapter);
+	vmxnet3_rq_destroy_all(adapter);
+	vmxnet3_adjust_rx_ring_size(adapter);
+	err = vmxnet3_rq_create_all(adapter);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "failed to re-create rx queues for XDP.");
+		return -EOPNOTSUPP;
+	}
+	err = vmxnet3_activate_dev(adapter);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "failed to activate device for XDP.");
+		return -EOPNOTSUPP;
+	}
+	clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
+
+	return 0;
+}
+
+/* This is the main xdp call used by kernel to set/unset eBPF program. */
+int
+vmxnet3_xdp(struct net_device *netdev, struct netdev_bpf *bpf)
+{
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		return vmxnet3_xdp_set(netdev, bpf, bpf->extack);
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
+		       struct xdp_frame *xdpf,
+		       struct vmxnet3_tx_queue *tq, bool dma_map)
+{
+	struct vmxnet3_tx_buf_info *tbi = NULL;
+	union Vmxnet3_GenericDesc *gdesc;
+	struct vmxnet3_tx_ctx ctx;
+	int tx_num_deferred;
+	struct page *page;
+	u32 buf_size;
+	u32 dw2;
+
+	dw2 = (tq->tx_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT;
+	dw2 |= xdpf->len;
+	ctx.sop_txd = tq->tx_ring.base + tq->tx_ring.next2fill;
+	gdesc = ctx.sop_txd;
+
+	buf_size = xdpf->len;
+	tbi = tq->buf_info + tq->tx_ring.next2fill;
+
+	if (vmxnet3_cmd_ring_desc_avail(&tq->tx_ring) == 0) {
+		tq->stats.tx_ring_full++;
+		return -ENOSPC;
+	}
+
+	tbi->map_type = VMXNET3_MAP_XDP;
+	if (dma_map) { /* ndo_xdp_xmit */
+		tbi->dma_addr = dma_map_single(&adapter->pdev->dev,
+					       xdpf->data, buf_size,
+					       DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+			return -EFAULT;
+		tbi->map_type |= VMXNET3_MAP_SINGLE;
+	} else { /* XDP buffer from page pool */
+		page = virt_to_page(xdpf->data);
+		tbi->dma_addr = page_pool_get_dma_addr(page) +
+				VMXNET3_XDP_HEADROOM;
+		dma_sync_single_for_device(&adapter->pdev->dev,
+					   tbi->dma_addr, buf_size,
+					   DMA_TO_DEVICE);
+	}
+	tbi->xdpf = xdpf;
+	tbi->len = buf_size;
+
+	gdesc = tq->tx_ring.base + tq->tx_ring.next2fill;
+	WARN_ON_ONCE(gdesc->txd.gen == tq->tx_ring.gen);
+
+	gdesc->txd.addr = cpu_to_le64(tbi->dma_addr);
+	gdesc->dword[2] = cpu_to_le32(dw2);
+
+	/* Setup the EOP desc */
+	gdesc->dword[3] = cpu_to_le32(VMXNET3_TXD_CQ | VMXNET3_TXD_EOP);
+
+	gdesc->txd.om = 0;
+	gdesc->txd.msscof = 0;
+	gdesc->txd.hlen = 0;
+	gdesc->txd.ti = 0;
+
+	tx_num_deferred = le32_to_cpu(tq->shared->txNumDeferred);
+	le32_add_cpu(&tq->shared->txNumDeferred, 1);
+	tx_num_deferred++;
+
+	vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring);
+
+	/* set the last buf_info for the pkt */
+	tbi->sop_idx = ctx.sop_txd - tq->tx_ring.base;
+
+	dma_wmb();
+	gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
+						  VMXNET3_TXD_GEN);
+
+	/* No need to handle the case when tx_num_deferred doesn't reach
+	 * threshold. Backend driver at hypervisor side will poll and reset
+	 * tq->shared->txNumDeferred to 0.
+	 */
+	if (tx_num_deferred >= le32_to_cpu(tq->shared->txThreshold)) {
+		tq->shared->txNumDeferred = 0;
+		VMXNET3_WRITE_BAR0_REG(adapter,
+				       VMXNET3_REG_TXPROD + tq->qid * 8,
+				       tq->tx_ring.next2fill);
+	}
+
+	return 0;
+}
+
+static int
+vmxnet3_xdp_xmit_back(struct vmxnet3_adapter *adapter,
+		      struct xdp_frame *xdpf)
+{
+	struct vmxnet3_tx_queue *tq;
+	struct netdev_queue *nq;
+	int err;
+
+	tq = vmxnet3_xdp_get_tq(adapter);
+	if (tq->stopped)
+		return -ENETDOWN;
+
+	nq = netdev_get_tx_queue(adapter->netdev, tq->qid);
+
+	__netif_tx_lock(nq, smp_processor_id());
+	err = vmxnet3_xdp_xmit_frame(adapter, xdpf, tq, false);
+	__netif_tx_unlock(nq);
+
+	return err;
+}
+
+/* ndo_xdp_xmit */
+int
+vmxnet3_xdp_xmit(struct net_device *dev,
+		 int n, struct xdp_frame **frames, u32 flags)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(dev);
+	struct vmxnet3_tx_queue *tq;
+	int i;
+
+	if (unlikely(test_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state)))
+		return -ENETDOWN;
+	if (unlikely(test_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)))
+		return -EINVAL;
+
+	tq = vmxnet3_xdp_get_tq(adapter);
+	if (tq->stopped)
+		return -ENETDOWN;
+
+	for (i = 0; i < n; i++) {
+		if (vmxnet3_xdp_xmit_frame(adapter, frames[i], tq, true)) {
+			tq->stats.xdp_xmit_err++;
+			break;
+		}
+	}
+	tq->stats.xdp_xmit += i;
+
+	return i;
+}
+
+static int
+vmxnet3_run_xdp(struct vmxnet3_rx_queue *rq, struct xdp_buff *xdp,
+		struct bpf_prog *prog)
+{
+	struct xdp_frame *xdpf;
+	struct page *page;
+	int err;
+	u32 act;
+
+	rq->stats.xdp_packets++;
+	act = bpf_prog_run_xdp(prog, xdp);
+	page = virt_to_page(xdp->data_hard_start);
+
+	switch (act) {
+	case XDP_PASS:
+		return act;
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(rq->adapter->netdev, xdp, prog);
+		if (!err) {
+			rq->stats.xdp_redirects++;
+		} else {
+			rq->stats.xdp_drops++;
+			page_pool_recycle_direct(rq->page_pool, page);
+		}
+		return act;
+	case XDP_TX:
+		xdpf = xdp_convert_buff_to_frame(xdp);
+		if (unlikely(!xdpf ||
+			     vmxnet3_xdp_xmit_back(rq->adapter, xdpf))) {
+			rq->stats.xdp_drops++;
+			page_pool_recycle_direct(rq->page_pool, page);
+		} else {
+			rq->stats.xdp_tx++;
+		}
+		return act;
+	default:
+		bpf_warn_invalid_xdp_action(rq->adapter->netdev, prog, act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(rq->adapter->netdev, prog, act);
+		rq->stats.xdp_aborted++;
+		break;
+	case XDP_DROP:
+		rq->stats.xdp_drops++;
+		break;
+	}
+
+	page_pool_recycle_direct(rq->page_pool, page);
+
+	return act;
+}
+
+static struct sk_buff *
+vmxnet3_build_skb(struct vmxnet3_rx_queue *rq, struct page *page,
+		  const struct xdp_buff *xdp)
+{
+	struct sk_buff *skb;
+
+	skb = build_skb(page_address(page), PAGE_SIZE);
+	if (unlikely(!skb)) {
+		page_pool_recycle_direct(rq->page_pool, page);
+		rq->stats.rx_buf_alloc_failure++;
+		return NULL;
+	}
+
+	/* bpf prog might change len and data position. */
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
+	skb_put(skb, xdp->data_end - xdp->data);
+	skb_mark_for_recycle(skb);
+
+	return skb;
+}
+
+/* Handle packets from DataRing. */
+int
+vmxnet3_process_xdp_small(struct vmxnet3_adapter *adapter,
+			  struct vmxnet3_rx_queue *rq,
+			  void *data, int len,
+			  struct sk_buff **skb_xdp_pass)
+{
+	struct bpf_prog *xdp_prog;
+	struct xdp_buff xdp;
+	struct page *page;
+	int act;
+
+	page = page_pool_alloc_pages(rq->page_pool, GFP_ATOMIC);
+	if (unlikely(!page)) {
+		rq->stats.rx_buf_alloc_failure++;
+		return XDP_DROP;
+	}
+
+	xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq);
+	xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset,
+			 len, false);
+	xdp_buff_clear_frags_flag(&xdp);
+
+	/* Must copy the data because it's at dataring. */
+	memcpy(xdp.data, data, len);
+
+	xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog);
+	if (!xdp_prog) {
+		act = XDP_PASS;
+		goto out_skb;
+	}
+	act = vmxnet3_run_xdp(rq, &xdp, xdp_prog);
+	if (act != XDP_PASS)
+		return act;
+
+out_skb:
+	*skb_xdp_pass = vmxnet3_build_skb(rq, page, &xdp);
+	if (!*skb_xdp_pass)
+		return XDP_DROP;
+
+	/* No need to refill. */
+	return likely(*skb_xdp_pass) ? act : XDP_DROP;
+}
+
+int
+vmxnet3_process_xdp(struct vmxnet3_adapter *adapter,
+		    struct vmxnet3_rx_queue *rq,
+		    struct Vmxnet3_RxCompDesc *rcd,
+		    struct vmxnet3_rx_buf_info *rbi,
+		    struct Vmxnet3_RxDesc *rxd,
+		    struct sk_buff **skb_xdp_pass)
+{
+	struct bpf_prog *xdp_prog;
+	dma_addr_t new_dma_addr;
+	struct xdp_buff xdp;
+	struct page *page;
+	void *new_data;
+	int act;
+
+	page = rbi->page;
+	dma_sync_single_for_cpu(&adapter->pdev->dev,
+				page_pool_get_dma_addr(page) +
+				rq->page_pool->p.offset, rcd->len,
+				page_pool_get_dma_dir(rq->page_pool));
+
+	xdp_init_buff(&xdp, rbi->len, &rq->xdp_rxq);
+	xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset,
+			 rcd->len, false);
+	xdp_buff_clear_frags_flag(&xdp);
+
+	xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog);
+	if (!xdp_prog) {
+		act = XDP_PASS;
+		goto out_skb;
+	}
+	act = vmxnet3_run_xdp(rq, &xdp, xdp_prog);
+
+	if (act == XDP_PASS) {
+out_skb:
+		*skb_xdp_pass = vmxnet3_build_skb(rq, page, &xdp);
+		if (!*skb_xdp_pass)
+			act = XDP_DROP;
+	}
+
+	new_data = vmxnet3_pp_get_buff(rq->page_pool, &new_dma_addr,
+				       GFP_ATOMIC);
+	if (!new_data) {
+		rq->stats.rx_buf_alloc_failure++;
+		return XDP_DROP;
+	}
+	rbi->page = virt_to_page(new_data);
+	rbi->dma_addr = new_dma_addr;
+	rxd->addr = cpu_to_le64(rbi->dma_addr);
+	rxd->len = rbi->len;
+
+	return act;
+}
diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.h b/drivers/net/vmxnet3/vmxnet3_xdp.h
new file mode 100644
index 0000000000000..f9d843e060a32
--- /dev/null
+++ b/drivers/net/vmxnet3/vmxnet3_xdp.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * Linux driver for VMware's vmxnet3 ethernet NIC.
+ * Copyright (C) 2008-2023, VMware, Inc. All Rights Reserved.
+ * Maintained by: pv-drivers@vmware.com
+ *
+ */
+
+#ifndef _VMXNET3_XDP_H
+#define _VMXNET3_XDP_H
+
+#include <linux/filter.h>
+#include <linux/bpf_trace.h>
+#include <linux/netlink.h>
+
+#include "vmxnet3_int.h"
+
+#define VMXNET3_XDP_HEADROOM	(XDP_PACKET_HEADROOM + NET_IP_ALIGN)
+#define VMXNET3_XDP_RX_TAILROOM	SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
+#define VMXNET3_XDP_RX_OFFSET	VMXNET3_XDP_HEADROOM
+#define VMXNET3_XDP_MAX_FRSIZE	(PAGE_SIZE - VMXNET3_XDP_HEADROOM - \
+				 VMXNET3_XDP_RX_TAILROOM)
+#define VMXNET3_XDP_MAX_MTU	(VMXNET3_XDP_MAX_FRSIZE - ETH_HLEN - \
+				 2 * VLAN_HLEN - ETH_FCS_LEN)
+
+int vmxnet3_xdp(struct net_device *netdev, struct netdev_bpf *bpf);
+int vmxnet3_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+		     u32 flags);
+int vmxnet3_process_xdp(struct vmxnet3_adapter *adapter,
+			struct vmxnet3_rx_queue *rq,
+			struct Vmxnet3_RxCompDesc *rcd,
+			struct vmxnet3_rx_buf_info *rbi,
+			struct Vmxnet3_RxDesc *rxd,
+			struct sk_buff **skb_xdp_pass);
+int vmxnet3_process_xdp_small(struct vmxnet3_adapter *adapter,
+			      struct vmxnet3_rx_queue *rq,
+			      void *data, int len,
+			      struct sk_buff **skb_xdp_pass);
+void *vmxnet3_pp_get_buff(struct page_pool *pp, dma_addr_t *dma_addr,
+			  gfp_t gfp_mask);
+
+static inline bool vmxnet3_xdp_enabled(struct vmxnet3_adapter *adapter)
+{
+	return !!rcu_access_pointer(adapter->xdp_bpf_prog);
+}
+
+#endif
-- 
GitLab


From bf98bbe985539ffb61898bd4d855df727b1a80c7 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 10 Aug 2023 16:56:41 +0800
Subject: [PATCH 1179/1806] net: macsec: Use helper functions to update stats

Use the helper functions dev_sw_netstats_rx_add() and
dev_sw_netstats_tx_add() to update stats, which helps to
provide code readability.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 17 +++--------------
 1 file changed, 3 insertions(+), 14 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 144ec756c796a..ae60817ec5c2d 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -518,14 +518,8 @@ static void macsec_count_tx(struct sk_buff *skb, struct macsec_tx_sc *tx_sc,
 
 static void count_tx(struct net_device *dev, int ret, int len)
 {
-	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
-		struct pcpu_sw_netstats *stats = this_cpu_ptr(dev->tstats);
-
-		u64_stats_update_begin(&stats->syncp);
-		u64_stats_inc(&stats->tx_packets);
-		u64_stats_add(&stats->tx_bytes, len);
-		u64_stats_update_end(&stats->syncp);
-	}
+	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN))
+		dev_sw_netstats_tx_add(dev, 1, len);
 }
 
 static void macsec_encrypt_done(void *data, int err)
@@ -827,12 +821,7 @@ static void macsec_finalize_skb(struct sk_buff *skb, u8 icv_len, u8 hdr_len)
 
 static void count_rx(struct net_device *dev, int len)
 {
-	struct pcpu_sw_netstats *stats = this_cpu_ptr(dev->tstats);
-
-	u64_stats_update_begin(&stats->syncp);
-	u64_stats_inc(&stats->rx_packets);
-	u64_stats_add(&stats->rx_bytes, len);
-	u64_stats_update_end(&stats->syncp);
+	dev_sw_netstats_rx_add(dev, len);
 }
 
 static void macsec_decrypt_done(void *data, int err)
-- 
GitLab


From 3c0930b491f8995de974f459648e4aad4ca996ff Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 10 Aug 2023 16:56:42 +0800
Subject: [PATCH 1180/1806] vxlan: Use helper functions to update stats

Use the helper functions dev_sw_netstats_rx_add() and
dev_sw_netstats_tx_add() to update stats, which helps to
provide code readability.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan/vxlan_core.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 2bddcdf482a74..e463f59e95c25 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2328,14 +2328,11 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 			       struct vxlan_dev *dst_vxlan, __be32 vni,
 			       bool snoop)
 {
-	struct pcpu_sw_netstats *tx_stats, *rx_stats;
 	union vxlan_addr loopback;
 	union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
 	struct net_device *dev;
 	int len = skb->len;
 
-	tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
-	rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
 	skb->pkt_type = PACKET_HOST;
 	skb->encapsulation = 0;
 	skb->dev = dst_vxlan->dev;
@@ -2361,17 +2358,11 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 	if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop)
 		vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni);
 
-	u64_stats_update_begin(&tx_stats->syncp);
-	u64_stats_inc(&tx_stats->tx_packets);
-	u64_stats_add(&tx_stats->tx_bytes, len);
-	u64_stats_update_end(&tx_stats->syncp);
+	dev_sw_netstats_tx_add(src_vxlan->dev, 1, len);
 	vxlan_vnifilter_count(src_vxlan, vni, NULL, VXLAN_VNI_STATS_TX, len);
 
 	if (__netif_rx(skb) == NET_RX_SUCCESS) {
-		u64_stats_update_begin(&rx_stats->syncp);
-		u64_stats_inc(&rx_stats->rx_packets);
-		u64_stats_add(&rx_stats->rx_bytes, len);
-		u64_stats_update_end(&rx_stats->syncp);
+		dev_sw_netstats_rx_add(dst_vxlan->dev, len);
 		vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX,
 				      len);
 	} else {
-- 
GitLab


From 58c1e0bace590715fe22489c06dd4610c1ba50ba Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Fri, 11 Aug 2023 20:51:39 +0800
Subject: [PATCH 1181/1806] net: stmmac: xgmac: show more MAC HW features in
 debugfs

1. Show TSSTSSEL(Timestamp System Time Source),
ADDMACADRSEL(additional MAC addresses), SMASEL(SMA/MDIO Interface),
HDSEL(Half-duplex Support) in debugfs.
2. Show exact number of additional MAC address registers for XGMAC2 core.
3. XGMAC2 core does not have different IP checksum offload types, so just
show rx_coe instead of rx_coe_type1 or rx_coe_type2.
4. XGMAC2 core does not have rxfifo_over_2048 definition, skip it.

Signed-off-by: Furong Xu <0x1207@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h  |  2 ++
 .../net/ethernet/stmicro/stmmac/dwxgmac2.h    |  4 +++
 .../ethernet/stmicro/stmmac/dwxgmac2_dma.c    |  6 ++++-
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 25 +++++++++++++++----
 4 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index c67171975d5c7..1f5293c8cc047 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -438,6 +438,8 @@ struct dma_features {
 	unsigned int tbssel;
 	/* Numbers of Auxiliary Snapshot Inputs */
 	unsigned int aux_snapshot_n;
+	/* Timestamp System Time Source */
+	unsigned int tssrc;
 };
 
 /* RX Buffer size must be multiple of 4/8/16 bytes */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index ce67b178c2d53..7f68bef456b7f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -123,6 +123,8 @@
 #define XGMAC_LPI_TIMER_CTRL		0x000000d4
 #define XGMAC_HW_FEATURE0		0x0000011c
 #define XGMAC_HWFEAT_SAVLANINS		BIT(27)
+#define XGMAC_HWFEAT_TSSTSSEL		GENMASK(26, 25)
+#define XGMAC_HWFEAT_ADDMACADRSEL	GENMASK(22, 18)
 #define XGMAC_HWFEAT_RXCOESEL		BIT(16)
 #define XGMAC_HWFEAT_TXCOESEL		BIT(14)
 #define XGMAC_HWFEAT_EEESEL		BIT(13)
@@ -133,7 +135,9 @@
 #define XGMAC_HWFEAT_MMCSEL		BIT(8)
 #define XGMAC_HWFEAT_MGKSEL		BIT(7)
 #define XGMAC_HWFEAT_RWKSEL		BIT(6)
+#define XGMAC_HWFEAT_SMASEL		BIT(5)
 #define XGMAC_HWFEAT_VLHASH		BIT(4)
+#define XGMAC_HWFEAT_HDSEL		BIT(3)
 #define XGMAC_HWFEAT_GMIISEL		BIT(1)
 #define XGMAC_HW_FEATURE1		0x00000120
 #define XGMAC_HWFEAT_L3L4FNUM		GENMASK(30, 27)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index b09395f5edcb1..3aacf791efebc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -391,9 +391,11 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 {
 	u32 hw_cap;
 
-	/*  MAC HW feature 0 */
+	/* MAC HW feature 0 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE0);
 	dma_cap->vlins = (hw_cap & XGMAC_HWFEAT_SAVLANINS) >> 27;
+	dma_cap->tssrc = (hw_cap & XGMAC_HWFEAT_TSSTSSEL) >> 25;
+	dma_cap->multi_addr = (hw_cap & XGMAC_HWFEAT_ADDMACADRSEL) >> 18;
 	dma_cap->rx_coe = (hw_cap & XGMAC_HWFEAT_RXCOESEL) >> 16;
 	dma_cap->tx_coe = (hw_cap & XGMAC_HWFEAT_TXCOESEL) >> 14;
 	dma_cap->eee = (hw_cap & XGMAC_HWFEAT_EEESEL) >> 13;
@@ -404,7 +406,9 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 	dma_cap->rmon = (hw_cap & XGMAC_HWFEAT_MMCSEL) >> 8;
 	dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7;
 	dma_cap->pmt_remote_wake_up = (hw_cap & XGMAC_HWFEAT_RWKSEL) >> 6;
+	dma_cap->sma_mdio = (hw_cap & XGMAC_HWFEAT_SMASEL) >> 5;
 	dma_cap->vlhash = (hw_cap & XGMAC_HWFEAT_VLHASH) >> 4;
+	dma_cap->half_duplex = (hw_cap & XGMAC_HWFEAT_HDSEL) >> 3;
 	dma_cap->mbps_1000 = (hw_cap & XGMAC_HWFEAT_GMIISEL) >> 1;
 
 	/* MAC HW feature 1 */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 351eca6109e01..733b5e9008173 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6237,6 +6237,12 @@ DEFINE_SHOW_ATTRIBUTE(stmmac_rings_status);
 
 static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 {
+	static const char * const dwxgmac_timestamp_source[] = {
+		"None",
+		"Internal",
+		"External",
+		"Both",
+	};
 	struct net_device *dev = seq->private;
 	struct stmmac_priv *priv = netdev_priv(dev);
 
@@ -6257,8 +6263,13 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 		   (priv->dma_cap.half_duplex) ? "Y" : "N");
 	seq_printf(seq, "\tHash Filter: %s\n",
 		   (priv->dma_cap.hash_filter) ? "Y" : "N");
-	seq_printf(seq, "\tMultiple MAC address registers: %s\n",
-		   (priv->dma_cap.multi_addr) ? "Y" : "N");
+	if (priv->plat->has_xgmac)
+		seq_printf(seq,
+			   "\tNumber of Additional MAC address registers: %d\n",
+			   priv->dma_cap.multi_addr);
+	else
+		seq_printf(seq, "\tMultiple MAC address registers: %s\n",
+			   (priv->dma_cap.multi_addr) ? "Y" : "N");
 	seq_printf(seq, "\tPCS (TBI/SGMII/RTBI PHY interfaces): %s\n",
 		   (priv->dma_cap.pcs) ? "Y" : "N");
 	seq_printf(seq, "\tSMA (MDIO) Interface: %s\n",
@@ -6273,12 +6284,16 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 		   (priv->dma_cap.time_stamp) ? "Y" : "N");
 	seq_printf(seq, "\tIEEE 1588-2008 Advanced Time Stamp: %s\n",
 		   (priv->dma_cap.atime_stamp) ? "Y" : "N");
+	if (priv->plat->has_xgmac)
+		seq_printf(seq, "\tTimestamp System Time Source: %s\n",
+			   dwxgmac_timestamp_source[priv->dma_cap.tssrc]);
 	seq_printf(seq, "\t802.3az - Energy-Efficient Ethernet (EEE): %s\n",
 		   (priv->dma_cap.eee) ? "Y" : "N");
 	seq_printf(seq, "\tAV features: %s\n", (priv->dma_cap.av) ? "Y" : "N");
 	seq_printf(seq, "\tChecksum Offload in TX: %s\n",
 		   (priv->dma_cap.tx_coe) ? "Y" : "N");
-	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+	if (priv->synopsys_id >= DWMAC_CORE_4_00 ||
+	    priv->plat->has_xgmac) {
 		seq_printf(seq, "\tIP Checksum Offload in RX: %s\n",
 			   (priv->dma_cap.rx_coe) ? "Y" : "N");
 	} else {
@@ -6286,9 +6301,9 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 			   (priv->dma_cap.rx_coe_type1) ? "Y" : "N");
 		seq_printf(seq, "\tIP Checksum Offload (type2) in RX: %s\n",
 			   (priv->dma_cap.rx_coe_type2) ? "Y" : "N");
+		seq_printf(seq, "\tRXFIFO > 2048bytes: %s\n",
+			   (priv->dma_cap.rxfifo_over_2048) ? "Y" : "N");
 	}
-	seq_printf(seq, "\tRXFIFO > 2048bytes: %s\n",
-		   (priv->dma_cap.rxfifo_over_2048) ? "Y" : "N");
 	seq_printf(seq, "\tNumber of Additional RX channel: %d\n",
 		   priv->dma_cap.number_rx_channel);
 	seq_printf(seq, "\tNumber of Additional TX channel: %d\n",
-- 
GitLab


From d0d449c747649dd38e7a1fb66a5e29f10284e287 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 11 Aug 2023 17:13:55 +0200
Subject: [PATCH 1182/1806] mlxsw: core_acl_flex_actions: Add IGNORE_ACTION

Add the IGNORE_ACTION which is used to ignore basic switching functions
such as learning on a per-packet basis.

The action will be prepended to the FORWARDING_ACTION in subsequent
patches.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlxsw/core_acl_flex_actions.c    | 40 +++++++++++++++++++
 .../mellanox/mlxsw/core_acl_flex_actions.h    |  2 +
 2 files changed, 42 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 9dfe7148199f9..faa63ea9b83e1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -1887,6 +1887,46 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid,
 }
 EXPORT_SYMBOL(mlxsw_afa_block_append_fid_set);
 
+/* Ignore Action
+ * -------------
+ * The ignore action is used to ignore basic switching functions such as
+ * learning on a per-packet basis.
+ */
+
+#define MLXSW_AFA_IGNORE_CODE 0x0F
+#define MLXSW_AFA_IGNORE_SIZE 1
+
+/* afa_ignore_disable_learning
+ * Disable learning on ingress.
+ */
+MLXSW_ITEM32(afa, ignore, disable_learning, 0x00, 29, 1);
+
+/* afa_ignore_disable_security
+ * Disable security lookup on ingress.
+ * Reserved when Spectrum-1.
+ */
+MLXSW_ITEM32(afa, ignore, disable_security, 0x00, 28, 1);
+
+static void mlxsw_afa_ignore_pack(char *payload, bool disable_learning,
+				  bool disable_security)
+{
+	mlxsw_afa_ignore_disable_learning_set(payload, disable_learning);
+	mlxsw_afa_ignore_disable_security_set(payload, disable_security);
+}
+
+int mlxsw_afa_block_append_ignore(struct mlxsw_afa_block *block,
+				  bool disable_learning, bool disable_security)
+{
+	char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_IGNORE_CODE,
+						  MLXSW_AFA_IGNORE_SIZE);
+
+	if (IS_ERR(act))
+		return PTR_ERR(act);
+	mlxsw_afa_ignore_pack(act, disable_learning, disable_security);
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_ignore);
+
 /* MC Routing Action
  * -----------------
  * The Multicast router action. Can be used by RMFT_V2 - Router Multicast
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index db58037be46ef..0ead3a212de8c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -89,6 +89,8 @@ int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
 				   struct netlink_ext_ack *extack);
 int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid,
 				   struct netlink_ext_ack *extack);
+int mlxsw_afa_block_append_ignore(struct mlxsw_afa_block *block,
+				  bool disable_learning, bool disable_security);
 int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block,
 				    u16 expected_irif, u16 min_mtu,
 				    bool rmid_valid, u32 kvdl_index);
-- 
GitLab


From 0433670e136ad879d2d52b3e05ee342a9bb052d8 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 11 Aug 2023 17:13:56 +0200
Subject: [PATCH 1183/1806] mlxsw: spectrum_flower: Disable learning and
 security lookup when redirecting

It is possible to add a filter that redirects traffic from the ingress
of a bridge port that is locked (i.e., performs security / SMAC lookup)
and has learning enabled. For example:

 # ip link add name br0 type bridge
 # ip link set dev swp1 master br0
 # bridge link set dev swp1 learning on locked on mab on
 # tc qdisc add dev swp1 clsact
 # tc filter add dev swp1 ingress pref 1 proto ip flower skip_sw src_ip 192.0.2.1 action mirred egress redirect dev swp2

In the kernel's Rx path, this filter is evaluated before the Rx handler
of the bridge, which means that redirected traffic should not be
affected by bridge port configuration such as learning.

However, the hardware data path is a bit different and the redirect
action (FORWARDING_ACTION in hardware) merely attaches a pointer to the
packet, which is later used by the L2 lookup stage to understand how to
forward the packet. Between both stages - ingress ACL and L2 lookup -
learning and security lookup are performed, which means that redirected
traffic is affected by bridge port configuration, unlike in the kernel's
data path.

The learning discrepancy was handled in commit 577fa14d2100 ("mlxsw:
spectrum: Do not process learned records with a dummy FID") by simply
ignoring learning notifications generated by the redirected traffic. A
similar solution is not possible for the security / SMAC lookup since
- unlike learning - the CPU is not involved and packets that failed the
lookup are dropped by the device.

Instead, solve this by prepending the ignore action to the redirect
action and use it to instruct the device to disable both learning and
the security / SMAC lookup for redirected traffic.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h        |  3 +++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c    |  9 +++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 10 ++++++++++
 3 files changed, 22 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 8da7bb04fc3ad..2fed55bcfd635 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -1050,6 +1050,9 @@ int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
 int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_rule_info *rulei,
 				   u16 fid, struct netlink_ext_ack *extack);
+int mlxsw_sp_acl_rulei_act_ignore(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_rule_info *rulei,
+				  bool disable_learning, bool disable_security);
 int mlxsw_sp_acl_rulei_act_sample(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_rule_info *rulei,
 				  struct mlxsw_sp_flow_block *block,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 186161a3459dd..7c59c8a135840 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -775,6 +775,15 @@ int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_afa_block_append_fid_set(rulei->act_block, fid, extack);
 }
 
+int mlxsw_sp_acl_rulei_act_ignore(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_rule_info *rulei,
+				  bool disable_learning, bool disable_security)
+{
+	return mlxsw_afa_block_append_ignore(rulei->act_block,
+					     disable_learning,
+					     disable_security);
+}
+
 int mlxsw_sp_acl_rulei_act_sample(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_rule_info *rulei,
 				  struct mlxsw_sp_flow_block *block,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index af3f57d017ec0..9fd1ca0792584 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -160,6 +160,16 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 			 */
 			rulei->egress_bind_blocker = 1;
 
+			/* Ignore learning and security lookup as redirection
+			 * using ingress filters happens before the bridge.
+			 */
+			err = mlxsw_sp_acl_rulei_act_ignore(mlxsw_sp, rulei,
+							    true, true);
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Cannot append ignore action");
+				return err;
+			}
+
 			fid = mlxsw_sp_acl_dummy_fid(mlxsw_sp);
 			fid_index = mlxsw_sp_fid_index(fid);
 			err = mlxsw_sp_acl_rulei_act_fid_set(mlxsw_sp, rulei,
-- 
GitLab


From 9793a5a9c493a66871de4c6f27e26e9ca90699cc Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 11 Aug 2023 17:13:57 +0200
Subject: [PATCH 1184/1806] mlxsw: spectrum: Stop ignoring learning
 notifications from redirected traffic

As explained in the previous patch, with the ignore action prepended to
the redirect action, it is not longer possible for redirected traffic to
generate learning notifications.

Therefore, remove the workaround that was added in commit 577fa14d2100
("mlxsw: spectrum: Do not process learned records with a dummy FID") as
it is no longer needed.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h         |  1 -
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c     | 10 ----------
 .../net/ethernet/mellanox/mlxsw/spectrum_switchdev.c   |  6 ------
 3 files changed, 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 2fed55bcfd635..02ca2871b6f9f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -1271,7 +1271,6 @@ int mlxsw_sp_setup_tc_block_qevent_mark(struct mlxsw_sp_port *mlxsw_sp_port,
 					struct flow_block_offload *f);
 
 /* spectrum_fid.c */
-bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index);
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
 						  u16 fid_index);
 int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index b6ee2d658b0c4..9df098474743d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -137,16 +137,6 @@ static const int *mlxsw_sp_packet_type_sfgc_types[] = {
 	[MLXSW_SP_FLOOD_TYPE_MC]	= mlxsw_sp_sfgc_mc_packet_types,
 };
 
-bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index)
-{
-	enum mlxsw_sp_fid_type fid_type = MLXSW_SP_FID_TYPE_DUMMY;
-	struct mlxsw_sp_fid_family *fid_family;
-
-	fid_family = mlxsw_sp->fid_core->fid_family_arr[fid_type];
-
-	return fid_family->start_index == fid_index;
-}
-
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
 						  u16 fid_index)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 3662b9da54890..6c749c148148d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -3066,9 +3066,6 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
 		goto just_remove;
 	}
 
-	if (mlxsw_sp_fid_is_dummy(mlxsw_sp, fid))
-		goto just_remove;
-
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_fid(mlxsw_sp_port, fid);
 	if (!mlxsw_sp_port_vlan) {
 		netdev_err(mlxsw_sp_port->dev, "Failed to find a matching {Port, VID} following FDB notification\n");
@@ -3136,9 +3133,6 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp,
 		goto just_remove;
 	}
 
-	if (mlxsw_sp_fid_is_dummy(mlxsw_sp, fid))
-		goto just_remove;
-
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_fid(mlxsw_sp_port, fid);
 	if (!mlxsw_sp_port_vlan) {
 		netdev_err(mlxsw_sp_port->dev, "Failed to find a matching {Port, VID} following FDB notification\n");
-- 
GitLab


From 38c43a1ce758674dc8da07b3e31489d1d13742a4 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 11 Aug 2023 17:13:58 +0200
Subject: [PATCH 1185/1806] selftests: forwarding: Add test case for traffic
 redirection from a locked port

Check that traffic can be redirected from a locked bridge port and that
it does not create locked FDB entries.

Cc: Hans J. Schultz <netdev@kapio-technology.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/bridge_locked_port.sh      | 36 +++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
index dc92d32464f60..9af9f6964808b 100755
--- a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
@@ -9,6 +9,7 @@ ALL_TESTS="
 	locked_port_mab_roam
 	locked_port_mab_config
 	locked_port_mab_flush
+	locked_port_mab_redirect
 "
 
 NUM_NETIFS=4
@@ -319,6 +320,41 @@ locked_port_mab_flush()
 	log_test "Locked port MAB FDB flush"
 }
 
+# Check that traffic can be redirected from a locked bridge port and that it
+# does not create locked FDB entries.
+locked_port_mab_redirect()
+{
+	RET=0
+	check_port_mab_support || return 0
+
+	bridge link set dev $swp1 learning on locked on mab on
+	tc qdisc add dev $swp1 clsact
+	tc filter add dev $swp1 ingress protocol all pref 1 handle 101 flower \
+		action mirred egress redirect dev $swp2
+
+	ping_do $h1 192.0.2.2
+	check_err $? "Ping did not work with redirection"
+
+	bridge fdb get `mac_get $h1` br br0 vlan 1 2> /dev/null | \
+		grep "dev $swp1" | grep -q "locked"
+	check_fail $? "Locked entry created for redirected traffic"
+
+	tc filter del dev $swp1 ingress protocol all pref 1 handle 101 flower
+
+	ping_do $h1 192.0.2.2
+	check_fail $? "Ping worked without redirection"
+
+	bridge fdb get `mac_get $h1` br br0 vlan 1 2> /dev/null | \
+		grep "dev $swp1" | grep -q "locked"
+	check_err $? "Locked entry not created after deleting filter"
+
+	bridge fdb del `mac_get $h1` vlan 1 dev $swp1 master
+	tc qdisc del dev $swp1 clsact
+	bridge link set dev $swp1 learning off locked off mab off
+
+	log_test "Locked port MAB redirect"
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
GitLab


From de875d35e0b07961657d41d0e1e05004fbb66664 Mon Sep 17 00:00:00 2001
From: Robert Marko <robert.marko@sartura.hr>
Date: Fri, 11 Aug 2023 13:10:06 +0200
Subject: [PATCH 1186/1806] dt-bindings: net: ethernet-controller: add PSGMII
 mode

Add a new PSGMII mode which is similar to QSGMII with the difference being
that it combines 5 SGMII lines into a single link compared to 4 on QSGMII.

It is commonly used by Qualcomm on their QCA807x PHY series.

Signed-off-by: Robert Marko <robert.marko@sartura.hr>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/ethernet-controller.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 6b0d359367daa..9f6a5ccbcefef 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -66,6 +66,7 @@ properties:
       - mii
       - gmii
       - sgmii
+      - psgmii
       - qsgmii
       - qusgmii
       - tbi
-- 
GitLab


From 83b5f0253b1ef352f4333c4fb2d24eff23045f6b Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Fri, 11 Aug 2023 13:10:07 +0200
Subject: [PATCH 1187/1806] net: phy: Introduce PSGMII PHY interface mode

The PSGMII interface is similar to QSGMII. The main difference
is that the PSGMII interface combines five SGMII lines into a
single link while in QSGMII only four lines are combined.

Similarly to the QSGMII, this interface mode might also needs
special handling within the MAC driver.

It is commonly used by Qualcomm with their QCA807x PHY series and
modern WiSoC-s.

Add definitions for the PHY layer to allow to express this type
of connection between the MAC and PHY.

Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Signed-off-by: Robert Marko <robert.marko@sartura.hr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/phy.rst | 4 ++++
 drivers/net/phy/phy-core.c       | 2 ++
 drivers/net/phy/phylink.c        | 3 +++
 include/linux/phy.h              | 4 ++++
 4 files changed, 13 insertions(+)

diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst
index b7ac4c64cf679..1283240d7620b 100644
--- a/Documentation/networking/phy.rst
+++ b/Documentation/networking/phy.rst
@@ -323,6 +323,10 @@ Some of the interface modes are described below:
     contrast with the 1000BASE-X phy mode used for Clause 38 and 39 PMDs, this
     interface mode has different autonegotiation and only supports full duplex.
 
+``PHY_INTERFACE_MODE_PSGMII``
+    This is the Penta SGMII mode, it is similar to QSGMII but it combines 5
+    SGMII lines into a single link compared to 4 on QSGMII.
+
 Pause frames / flow control
 ===========================
 
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index a64186dc53f8b..966c93cbe6164 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -142,6 +142,8 @@ int phy_interface_num_ports(phy_interface_t interface)
 	case PHY_INTERFACE_MODE_QSGMII:
 	case PHY_INTERFACE_MODE_QUSGMII:
 		return 4;
+	case PHY_INTERFACE_MODE_PSGMII:
+		return 5;
 	case PHY_INTERFACE_MODE_MAX:
 		WARN_ONCE(1, "PHY_INTERFACE_MODE_MAX isn't a valid interface mode");
 		return 0;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 4f1c8bb199e9f..160bce608c343 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -210,6 +210,7 @@ static int phylink_interface_max_speed(phy_interface_t interface)
 	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_PSGMII:
 	case PHY_INTERFACE_MODE_QSGMII:
 	case PHY_INTERFACE_MODE_QUSGMII:
 	case PHY_INTERFACE_MODE_SGMII:
@@ -475,6 +476,7 @@ unsigned long phylink_get_capabilities(phy_interface_t interface,
 	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_PSGMII:
 	case PHY_INTERFACE_MODE_QSGMII:
 	case PHY_INTERFACE_MODE_QUSGMII:
 	case PHY_INTERFACE_MODE_SGMII:
@@ -868,6 +870,7 @@ static int phylink_parse_mode(struct phylink *pl,
 
 		switch (pl->link_config.interface) {
 		case PHY_INTERFACE_MODE_SGMII:
+		case PHY_INTERFACE_MODE_PSGMII:
 		case PHY_INTERFACE_MODE_QSGMII:
 		case PHY_INTERFACE_MODE_QUSGMII:
 		case PHY_INTERFACE_MODE_RGMII:
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3c1ceedd1b771..1351b802ffcff 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -110,6 +110,7 @@ extern const int phy_10gbit_features_array[1];
  * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface
  * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface
  * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax
+ * @PHY_INTERFACE_MODE_PSGMII: Penta SGMII
  * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII
  * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII
  * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX
@@ -147,6 +148,7 @@ typedef enum {
 	PHY_INTERFACE_MODE_XGMII,
 	PHY_INTERFACE_MODE_XLGMII,
 	PHY_INTERFACE_MODE_MOCA,
+	PHY_INTERFACE_MODE_PSGMII,
 	PHY_INTERFACE_MODE_QSGMII,
 	PHY_INTERFACE_MODE_TRGMII,
 	PHY_INTERFACE_MODE_100BASEX,
@@ -254,6 +256,8 @@ static inline const char *phy_modes(phy_interface_t interface)
 		return "xlgmii";
 	case PHY_INTERFACE_MODE_MOCA:
 		return "moca";
+	case PHY_INTERFACE_MODE_PSGMII:
+		return "psgmii";
 	case PHY_INTERFACE_MODE_QSGMII:
 		return "qsgmii";
 	case PHY_INTERFACE_MODE_TRGMII:
-- 
GitLab


From 8e50750f122e59ea4cab4b4f696ef22b391bedc9 Mon Sep 17 00:00:00 2001
From: Marco Vedovati <marco.vedovati@crowdstrike.com>
Date: Thu, 10 Aug 2023 14:43:53 -0700
Subject: [PATCH 1188/1806] libbpf: Set close-on-exec flag on gzopen

Enable the close-on-exec flag when using gzopen. This is especially important
for multithreaded programs making use of libbpf, where a fork + exec could
race with libbpf library calls, potentially resulting in a file descriptor
leaked to the new process. This got missed in 59842c5451fe ("libbpf: Ensure
libbpf always opens files with O_CLOEXEC").

Fixes: 59842c5451fe ("libbpf: Ensure libbpf always opens files with O_CLOEXEC")
Signed-off-by: Marco Vedovati <marco.vedovati@crowdstrike.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230810214350.106301-1-martin.kelly@crowdstrike.com
---
 tools/lib/bpf/libbpf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 17883f5a44b97..b14a4376a86e6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1978,9 +1978,9 @@ static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data)
 		return -ENAMETOOLONG;
 
 	/* gzopen also accepts uncompressed files. */
-	file = gzopen(buf, "r");
+	file = gzopen(buf, "re");
 	if (!file)
-		file = gzopen("/proc/config.gz", "r");
+		file = gzopen("/proc/config.gz", "re");
 
 	if (!file) {
 		pr_warn("failed to open system Kconfig\n");
-- 
GitLab


From 950c92bbaa8f16fc71485f4d564d429a9e4cc9fd Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Wed, 2 Aug 2023 10:16:49 +0200
Subject: [PATCH 1189/1806] batman-adv: Drop unused function
 batadv_gw_bandwidth_set

This function is no longer used since the sysfs support was removed from
batman-adv.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/gateway_common.c | 88 ---------------------------------
 net/batman-adv/gateway_common.h |  2 -
 2 files changed, 90 deletions(-)

diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 6a964a773f57c..d9632607f92b6 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -9,7 +9,6 @@
 
 #include <linux/atomic.h>
 #include <linux/byteorder/generic.h>
-#include <linux/errno.h>
 #include <linux/kstrtox.h>
 #include <linux/limits.h>
 #include <linux/math64.h>
@@ -90,42 +89,6 @@ bool batadv_parse_throughput(struct net_device *net_dev, char *buff,
 	return true;
 }
 
-/**
- * batadv_parse_gw_bandwidth() - parse supplied string buffer to extract
- *  download and upload bandwidth information
- * @net_dev: the soft interface net device
- * @buff: string buffer to parse
- * @down: pointer holding the returned download bandwidth information
- * @up: pointer holding the returned upload bandwidth information
- *
- * Return: false on parse error and true otherwise.
- */
-static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff,
-				      u32 *down, u32 *up)
-{
-	char *slash_ptr;
-	bool ret;
-
-	slash_ptr = strchr(buff, '/');
-	if (slash_ptr)
-		*slash_ptr = 0;
-
-	ret = batadv_parse_throughput(net_dev, buff, "download gateway speed",
-				      down);
-	if (!ret)
-		return false;
-
-	/* we also got some upload info */
-	if (slash_ptr) {
-		ret = batadv_parse_throughput(net_dev, slash_ptr + 1,
-					      "upload gateway speed", up);
-		if (!ret)
-			return false;
-	}
-
-	return true;
-}
-
 /**
  * batadv_gw_tvlv_container_update() - update the gw tvlv container after
  *  gateway setting change
@@ -155,57 +118,6 @@ void batadv_gw_tvlv_container_update(struct batadv_priv *bat_priv)
 	}
 }
 
-/**
- * batadv_gw_bandwidth_set() - Parse and set download/upload gateway bandwidth
- *  from supplied string buffer
- * @net_dev: netdev struct of the soft interface
- * @buff: the buffer containing the user data
- * @count: number of bytes in the buffer
- *
- * Return: 'count' on success or a negative error code in case of failure
- */
-ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff,
-				size_t count)
-{
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	u32 down_curr;
-	u32 up_curr;
-	u32 down_new = 0;
-	u32 up_new = 0;
-	bool ret;
-
-	down_curr = (unsigned int)atomic_read(&bat_priv->gw.bandwidth_down);
-	up_curr = (unsigned int)atomic_read(&bat_priv->gw.bandwidth_up);
-
-	ret = batadv_parse_gw_bandwidth(net_dev, buff, &down_new, &up_new);
-	if (!ret)
-		return -EINVAL;
-
-	if (!down_new)
-		down_new = 1;
-
-	if (!up_new)
-		up_new = down_new / 5;
-
-	if (!up_new)
-		up_new = 1;
-
-	if (down_curr == down_new && up_curr == up_new)
-		return count;
-
-	batadv_gw_reselect(bat_priv);
-	batadv_info(net_dev,
-		    "Changing gateway bandwidth from: '%u.%u/%u.%u MBit' to: '%u.%u/%u.%u MBit'\n",
-		    down_curr / 10, down_curr % 10, up_curr / 10, up_curr % 10,
-		    down_new / 10, down_new % 10, up_new / 10, up_new % 10);
-
-	atomic_set(&bat_priv->gw.bandwidth_down, down_new);
-	atomic_set(&bat_priv->gw.bandwidth_up, up_new);
-	batadv_gw_tvlv_container_update(bat_priv);
-
-	return count;
-}
-
 /**
  * batadv_gw_tvlv_ogm_handler_v1() - process incoming gateway tvlv container
  * @bat_priv: the bat priv with all the soft interface information
diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h
index 87c37f9072614..cb2e72d7ab141 100644
--- a/net/batman-adv/gateway_common.h
+++ b/net/batman-adv/gateway_common.h
@@ -27,8 +27,6 @@ enum batadv_bandwidth_units {
 #define BATADV_GW_MODE_CLIENT_NAME	"client"
 #define BATADV_GW_MODE_SERVER_NAME	"server"
 
-ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff,
-				size_t count);
 void batadv_gw_tvlv_container_update(struct batadv_priv *bat_priv);
 void batadv_gw_init(struct batadv_priv *bat_priv);
 void batadv_gw_free(struct batadv_priv *bat_priv);
-- 
GitLab


From 02e61f06a97e7ba73fa44046d6da097e5c2aacc8 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Wed, 2 Aug 2023 10:24:20 +0200
Subject: [PATCH 1190/1806] batman-adv: Keep batadv_netlink_notify_* static

The batadv_netlink_notify_*() functions are not used by any other source
file. Just keep them local to netlink.c to get informed by the compiler
when they are not used anymore.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/netlink.c | 10 +++++-----
 net/batman-adv/netlink.h |  6 ------
 2 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index ad5714f737be2..b6c512ce67043 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -377,7 +377,7 @@ nla_put_failure:
  *
  * Return: 0 on success, < 0 on error
  */
-int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv)
+static int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv)
 {
 	struct sk_buff *msg;
 	int ret;
@@ -858,8 +858,8 @@ nla_put_failure:
  *
  * Return: 0 on success, < 0 on error
  */
-int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv,
-				 struct batadv_hard_iface *hard_iface)
+static int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv,
+					struct batadv_hard_iface *hard_iface)
 {
 	struct sk_buff *msg;
 	int ret;
@@ -1073,8 +1073,8 @@ nla_put_failure:
  *
  * Return: 0 on success, < 0 on error
  */
-int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv,
-			       struct batadv_softif_vlan *vlan)
+static int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv,
+				      struct batadv_softif_vlan *vlan)
 {
 	struct sk_buff *msg;
 	int ret;
diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h
index 48102cc7490c7..876d2806a67d2 100644
--- a/net/batman-adv/netlink.h
+++ b/net/batman-adv/netlink.h
@@ -21,12 +21,6 @@ int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst,
 				  u8 result, u32 test_time, u64 total_bytes,
 				  u32 cookie);
 
-int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv);
-int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv,
-				 struct batadv_hard_iface *hard_iface);
-int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv,
-			       struct batadv_softif_vlan *vlan);
-
 extern struct genl_family batadv_netlink_family;
 
 #endif /* _NET_BATMAN_ADV_NETLINK_H_ */
-- 
GitLab


From 6f96d46f9a1ad1c02589b598c56ea881094129d8 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Wed, 2 Aug 2023 10:39:28 +0200
Subject: [PATCH 1191/1806] batman-adv: Drop per algo GW section class code

This code was  only used in the past for the sysfs interface. But since
this was replace with netlink, it was never executed. The function pointer
was only checked to figure out whether the limit 255 (B.A.T.M.A.N. IV) or
2**32-1 (B.A.T.M.A.N. V) should be used as limit.

So instead of keeping the function pointer, just store the limits directly
in struct batadv_algo_gw_ops.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_iv_ogm.c     |  1 +
 net/batman-adv/bat_v.c          | 23 +---------
 net/batman-adv/gateway_common.c | 74 +--------------------------------
 net/batman-adv/gateway_common.h |  5 ---
 net/batman-adv/netlink.c        |  5 +--
 net/batman-adv/types.h          |  7 ++--
 6 files changed, 8 insertions(+), 107 deletions(-)

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 828fb393ee94a..74b49c35ddc14 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -2516,6 +2516,7 @@ static struct batadv_algo_ops batadv_batman_iv __read_mostly = {
 	},
 	.gw = {
 		.init_sel_class = batadv_iv_init_sel_class,
+		.sel_class_max = BATADV_TQ_MAX_VALUE,
 		.get_best_gw_node = batadv_iv_gw_get_best_gw_node,
 		.is_eligible = batadv_iv_gw_is_eligible,
 		.dump = batadv_iv_gw_dump,
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 54e41fc709c37..ac11f1f08db0f 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/jiffies.h>
 #include <linux/kref.h>
+#include <linux/limits.h>
 #include <linux/list.h>
 #include <linux/minmax.h>
 #include <linux/netdevice.h>
@@ -34,7 +35,6 @@
 #include "bat_v_elp.h"
 #include "bat_v_ogm.h"
 #include "gateway_client.h"
-#include "gateway_common.h"
 #include "hard-interface.h"
 #include "hash.h"
 #include "log.h"
@@ -512,25 +512,6 @@ static void batadv_v_init_sel_class(struct batadv_priv *bat_priv)
 	atomic_set(&bat_priv->gw.sel_class, 50);
 }
 
-static ssize_t batadv_v_store_sel_class(struct batadv_priv *bat_priv,
-					char *buff, size_t count)
-{
-	u32 old_class, class;
-
-	if (!batadv_parse_throughput(bat_priv->soft_iface, buff,
-				     "B.A.T.M.A.N. V GW selection class",
-				     &class))
-		return -EINVAL;
-
-	old_class = atomic_read(&bat_priv->gw.sel_class);
-	atomic_set(&bat_priv->gw.sel_class, class);
-
-	if (old_class != class)
-		batadv_gw_reselect(bat_priv);
-
-	return count;
-}
-
 /**
  * batadv_v_gw_throughput_get() - retrieve the GW-bandwidth for a given GW
  * @gw_node: the GW to retrieve the metric for
@@ -818,7 +799,7 @@ static struct batadv_algo_ops batadv_batman_v __read_mostly = {
 	},
 	.gw = {
 		.init_sel_class = batadv_v_init_sel_class,
-		.store_sel_class = batadv_v_store_sel_class,
+		.sel_class_max = U32_MAX,
 		.get_best_gw_node = batadv_v_gw_get_best_gw_node,
 		.is_eligible = batadv_v_gw_is_eligible,
 		.dump = batadv_v_gw_dump,
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index d9632607f92b6..2dd36ef03c841 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -9,86 +9,14 @@
 
 #include <linux/atomic.h>
 #include <linux/byteorder/generic.h>
-#include <linux/kstrtox.h>
-#include <linux/limits.h>
-#include <linux/math64.h>
-#include <linux/netdevice.h>
 #include <linux/stddef.h>
-#include <linux/string.h>
+#include <linux/types.h>
 #include <uapi/linux/batadv_packet.h>
 #include <uapi/linux/batman_adv.h>
 
 #include "gateway_client.h"
-#include "log.h"
 #include "tvlv.h"
 
-/**
- * batadv_parse_throughput() - parse supplied string buffer to extract
- *  throughput information
- * @net_dev: the soft interface net device
- * @buff: string buffer to parse
- * @description: text shown when throughput string cannot be parsed
- * @throughput: pointer holding the returned throughput information
- *
- * Return: false on parse error and true otherwise.
- */
-bool batadv_parse_throughput(struct net_device *net_dev, char *buff,
-			     const char *description, u32 *throughput)
-{
-	enum batadv_bandwidth_units bw_unit_type = BATADV_BW_UNIT_KBIT;
-	u64 lthroughput;
-	char *tmp_ptr;
-	int ret;
-
-	if (strlen(buff) > 4) {
-		tmp_ptr = buff + strlen(buff) - 4;
-
-		if (strncasecmp(tmp_ptr, "mbit", 4) == 0)
-			bw_unit_type = BATADV_BW_UNIT_MBIT;
-
-		if (strncasecmp(tmp_ptr, "kbit", 4) == 0 ||
-		    bw_unit_type == BATADV_BW_UNIT_MBIT)
-			*tmp_ptr = '\0';
-	}
-
-	ret = kstrtou64(buff, 10, &lthroughput);
-	if (ret) {
-		batadv_err(net_dev,
-			   "Invalid throughput speed for %s: %s\n",
-			   description, buff);
-		return false;
-	}
-
-	switch (bw_unit_type) {
-	case BATADV_BW_UNIT_MBIT:
-		/* prevent overflow */
-		if (U64_MAX / 10 < lthroughput) {
-			batadv_err(net_dev,
-				   "Throughput speed for %s too large: %s\n",
-				   description, buff);
-			return false;
-		}
-
-		lthroughput *= 10;
-		break;
-	case BATADV_BW_UNIT_KBIT:
-	default:
-		lthroughput = div_u64(lthroughput, 100);
-		break;
-	}
-
-	if (lthroughput > U32_MAX) {
-		batadv_err(net_dev,
-			   "Throughput speed for %s too large: %s\n",
-			   description, buff);
-		return false;
-	}
-
-	*throughput = lthroughput;
-
-	return true;
-}
-
 /**
  * batadv_gw_tvlv_container_update() - update the gw tvlv container after
  *  gateway setting change
diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h
index cb2e72d7ab141..5d097d6a1dd95 100644
--- a/net/batman-adv/gateway_common.h
+++ b/net/batman-adv/gateway_common.h
@@ -9,9 +9,6 @@
 
 #include "main.h"
 
-#include <linux/netdevice.h>
-#include <linux/types.h>
-
 /**
  * enum batadv_bandwidth_units - bandwidth unit types
  */
@@ -30,7 +27,5 @@ enum batadv_bandwidth_units {
 void batadv_gw_tvlv_container_update(struct batadv_priv *bat_priv);
 void batadv_gw_init(struct batadv_priv *bat_priv);
 void batadv_gw_free(struct batadv_priv *bat_priv);
-bool batadv_parse_throughput(struct net_device *net_dev, char *buff,
-			     const char *description, u32 *throughput);
 
 #endif /* _NET_BATMAN_ADV_GATEWAY_COMMON_H_ */
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index b6c512ce67043..d37872b34281d 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -548,15 +548,12 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info)
 		 * algorithm in use implements the GW API
 		 */
 
-		u32 sel_class_max = 0xffffffffu;
+		u32 sel_class_max = bat_priv->algo_ops->gw.sel_class_max;
 		u32 sel_class;
 
 		attr = info->attrs[BATADV_ATTR_GW_SEL_CLASS];
 		sel_class = nla_get_u32(attr);
 
-		if (!bat_priv->algo_ops->gw.store_sel_class)
-			sel_class_max = BATADV_TQ_MAX_VALUE;
-
 		if (sel_class >= 1 && sel_class <= sel_class_max) {
 			atomic_set(&bat_priv->gw.sel_class, sel_class);
 			batadv_gw_reselect(bat_priv);
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index ca9449ec9836a..54c2b8fa48ccd 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -2191,11 +2191,10 @@ struct batadv_algo_gw_ops {
 	void (*init_sel_class)(struct batadv_priv *bat_priv);
 
 	/**
-	 * @store_sel_class: parse and stores a new GW selection class
-	 *  (optional)
+	 * @sel_class_max: maximum allowed GW selection class
 	 */
-	ssize_t (*store_sel_class)(struct batadv_priv *bat_priv, char *buff,
-				   size_t count);
+	u32 sel_class_max;
+
 	/**
 	 * @get_best_gw_node: select the best GW from the list of available
 	 *  nodes (optional)
-- 
GitLab


From 811915db674f8daf19bb4fcb67da9017235ce26d Mon Sep 17 00:00:00 2001
From: Yipeng Zou <zouyipeng@huawei.com>
Date: Mon, 14 Aug 2023 11:14:34 +0800
Subject: [PATCH 1192/1806] selftests/bpf: Fix repeat option when kfunc_call
 verification fails

There is no way where topts.repeat can be set to 1 when tc_test fails.
Fix the typo where the break statement slipped by one line.

Fixes: fb66223a244f ("selftests/bpf: add test for accessing ctx from syscall program type")
Signed-off-by: Yipeng Zou <zouyipeng@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Li Zetao <lizetao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230814031434.3077944-1-zouyipeng@huawei.com
---
 tools/testing/selftests/bpf/prog_tests/kfunc_call.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
index a543742cd7bd1..2eb71559713c9 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -173,8 +173,8 @@ static void verify_fail(struct kfunc_test_params *param)
 	case tc_test:
 		topts.data_in = &pkt_v4;
 		topts.data_size_in = sizeof(pkt_v4);
-		break;
 		topts.repeat = 1;
+		break;
 	}
 
 	skel = kfunc_call_fail__open_opts(&opts);
-- 
GitLab


From 83a89c4b6ae93481d3f618aba6a29d89208d26ed Mon Sep 17 00:00:00 2001
From: Yipeng Zou <zouyipeng@huawei.com>
Date: Mon, 14 Aug 2023 11:07:27 +0800
Subject: [PATCH 1193/1806] selftests/bpf: Clean up fmod_ret in bench_rename
 test script
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Running the bench_rename test script, the following error occurs:

  # ./benchs/run_bench_rename.sh
  base      :    0.819 ± 0.012M/s
  kprobe    :    0.538 ± 0.009M/s
  kretprobe :    0.503 ± 0.004M/s
  rawtp     :    0.779 ± 0.020M/s
  fentry    :    0.726 ± 0.007M/s
  fexit     :    0.691 ± 0.007M/s
  benchmark 'rename-fmodret' not found

The bench_rename_fmodret has been removed in commit b000def2e052
("selftests: Remove fmod_ret from test_overhead"), thus remove it
from the runners in the test script.

Fixes: b000def2e052 ("selftests: Remove fmod_ret from test_overhead")
Signed-off-by: Yipeng Zou <zouyipeng@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230814030727.3010390-1-zouyipeng@huawei.com
---
 tools/testing/selftests/bpf/benchs/run_bench_rename.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh
index 16f774b1cdbed..7b281dbe41656 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh
@@ -2,7 +2,7 @@
 
 set -eufo pipefail
 
-for i in base kprobe kretprobe rawtp fentry fexit fmodret
+for i in base kprobe kretprobe rawtp fentry fexit
 do
 	summary=$(sudo ./bench -w2 -d5 -a rename-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
 	printf "%-10s: %s\n" $i "$summary"
-- 
GitLab


From 63618463cb94bda3ee68dc2ada998c0ef3c00e67 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:02 +0200
Subject: [PATCH 1194/1806] devlink: parse linecard attr in doit() callbacks

No need to give the linecards any special treatment in netlink attribute
parsing, as unlike for ports, there is only a couple of commands
benefiting from that.

Remove DEVLINK_NL_FLAG_NEED_LINECARD, make pre_doit() callback simpler
by moving the linecard attribute parsing to linecard_[gs]et_doit() ops.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-2-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h |  7 -------
 net/devlink/leftover.c      | 19 +++++++++++++------
 net/devlink/netlink.c       |  8 --------
 3 files changed, 13 insertions(+), 21 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 7fdd956ff992d..3bbecebf192dc 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -94,7 +94,6 @@ static inline bool devl_is_registered(struct devlink *devlink)
 #define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
 #define DEVLINK_NL_FLAG_NEED_RATE		BIT(2)
 #define DEVLINK_NL_FLAG_NEED_RATE_NODE		BIT(3)
-#define DEVLINK_NL_FLAG_NEED_LINECARD		BIT(4)
 
 enum devlink_multicast_groups {
 	DEVLINK_MCGRP_CONFIG,
@@ -203,12 +202,6 @@ int devlink_resources_validate(struct devlink *devlink,
 			       struct devlink_resource *resource,
 			       struct genl_info *info);
 
-/* Line cards */
-struct devlink_linecard;
-
-struct devlink_linecard *
-devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info);
-
 /* Rates */
 int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
 			     struct netlink_ext_ack *extack);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index e7900d9fa205a..46cdd5d88583c 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -285,7 +285,7 @@ devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
 	return ERR_PTR(-EINVAL);
 }
 
-struct devlink_linecard *
+static struct devlink_linecard *
 devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info)
 {
 	return devlink_linecard_get_from_attrs(devlink, info->attrs);
@@ -1814,11 +1814,15 @@ static void devlink_linecard_notify(struct devlink_linecard *linecard,
 static int devlink_nl_cmd_linecard_get_doit(struct sk_buff *skb,
 					    struct genl_info *info)
 {
-	struct devlink_linecard *linecard = info->user_ptr[1];
-	struct devlink *devlink = linecard->devlink;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_linecard *linecard;
 	struct sk_buff *msg;
 	int err;
 
+	linecard = devlink_linecard_get_from_info(devlink, info);
+	if (IS_ERR(linecard))
+		return PTR_ERR(linecard);
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
@@ -2008,10 +2012,15 @@ out:
 static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb,
 					    struct genl_info *info)
 {
-	struct devlink_linecard *linecard = info->user_ptr[1];
 	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_linecard *linecard;
 	int err;
 
+	linecard = devlink_linecard_get_from_info(devlink, info);
+	if (IS_ERR(linecard))
+		return PTR_ERR(linecard);
+
 	if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) {
 		const char *type;
 
@@ -6347,14 +6356,12 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.cmd = DEVLINK_CMD_LINECARD_GET,
 		.doit = devlink_nl_cmd_linecard_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_LINECARD_SET,
 		.doit = devlink_nl_cmd_linecard_set_doit,
 		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD,
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_GET,
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index bada2819827bc..9fd683f38a53e 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -112,7 +112,6 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs)
 int devlink_nl_pre_doit(const struct genl_split_ops *ops,
 			struct sk_buff *skb, struct genl_info *info)
 {
-	struct devlink_linecard *linecard;
 	struct devlink_port *devlink_port;
 	struct devlink *devlink;
 	int err;
@@ -151,13 +150,6 @@ int devlink_nl_pre_doit(const struct genl_split_ops *ops,
 			goto unlock;
 		}
 		info->user_ptr[1] = rate_node;
-	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) {
-		linecard = devlink_linecard_get_from_info(devlink, info);
-		if (IS_ERR(linecard)) {
-			err = PTR_ERR(linecard);
-			goto unlock;
-		}
-		info->user_ptr[1] = linecard;
 	}
 	return 0;
 
-- 
GitLab


From 41a1d4d1399af0f4ba9754086b23f7b9576eb25f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:03 +0200
Subject: [PATCH 1195/1806] devlink: parse rate attrs in doit() callbacks

No need to give the rate any special treatment in netlink attributes
parsing, as unlike for ports, there is only a couple of commands
benefiting from that.

Remove DEVLINK_NL_FLAG_NEED_RATE*, make pre_doit() callback simpler
by moving the rate attributes parsing to rate_*_doit() ops.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-3-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h |  8 +-------
 net/devlink/leftover.c      | 37 ++++++++++++++++++++++++-------------
 net/devlink/netlink.c       | 18 ------------------
 3 files changed, 25 insertions(+), 38 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 3bbecebf192dc..ca04e4ee94277 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -92,8 +92,6 @@ static inline bool devl_is_registered(struct devlink *devlink)
 /* Netlink */
 #define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
 #define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
-#define DEVLINK_NL_FLAG_NEED_RATE		BIT(2)
-#define DEVLINK_NL_FLAG_NEED_RATE_NODE		BIT(3)
 
 enum devlink_multicast_groups {
 	DEVLINK_MCGRP_CONFIG,
@@ -205,11 +203,7 @@ int devlink_resources_validate(struct devlink *devlink,
 /* Rates */
 int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
 			     struct netlink_ext_ack *extack);
-struct devlink_rate *
-devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info);
-struct devlink_rate *
-devlink_rate_node_get_from_info(struct devlink *devlink,
-				struct genl_info *info);
+
 /* Devlink nl cmds */
 int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 46cdd5d88583c..b7b6850e26d81 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -232,13 +232,13 @@ devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
 	return devlink_rate_node_get_by_name(devlink, rate_node_name);
 }
 
-struct devlink_rate *
+static struct devlink_rate *
 devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info)
 {
 	return devlink_rate_node_get_from_attrs(devlink, info->attrs);
 }
 
-struct devlink_rate *
+static struct devlink_rate *
 devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info)
 {
 	struct nlattr **attrs = info->attrs;
@@ -1041,10 +1041,15 @@ const struct devlink_cmd devl_cmd_rate_get = {
 static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb,
 					struct genl_info *info)
 {
-	struct devlink_rate *devlink_rate = info->user_ptr[1];
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_rate *devlink_rate;
 	struct sk_buff *msg;
 	int err;
 
+	devlink_rate = devlink_rate_get_from_info(devlink, info);
+	if (IS_ERR(devlink_rate))
+		return PTR_ERR(devlink_rate);
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
@@ -1629,11 +1634,16 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops,
 static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb,
 					struct genl_info *info)
 {
-	struct devlink_rate *devlink_rate = info->user_ptr[1];
-	struct devlink *devlink = devlink_rate->devlink;
-	const struct devlink_ops *ops = devlink->ops;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_rate *devlink_rate;
+	const struct devlink_ops *ops;
 	int err;
 
+	devlink_rate = devlink_rate_get_from_info(devlink, info);
+	if (IS_ERR(devlink_rate))
+		return PTR_ERR(devlink_rate);
+
+	ops = devlink->ops;
 	if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type))
 		return -EOPNOTSUPP;
 
@@ -1704,18 +1714,22 @@ err_strdup:
 static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb,
 					struct genl_info *info)
 {
-	struct devlink_rate *rate_node = info->user_ptr[1];
-	struct devlink *devlink = rate_node->devlink;
-	const struct devlink_ops *ops = devlink->ops;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_rate *rate_node;
 	int err;
 
+	rate_node = devlink_rate_node_get_from_info(devlink, info);
+	if (IS_ERR(rate_node))
+		return PTR_ERR(rate_node);
+
 	if (refcount_read(&rate_node->refcnt) > 1) {
 		NL_SET_ERR_MSG(info->extack, "Node has children. Cannot delete node.");
 		return -EBUSY;
 	}
 
 	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
-	err = ops->rate_node_del(rate_node, rate_node->priv, info->extack);
+	err = devlink->ops->rate_node_del(rate_node, rate_node->priv,
+					  info->extack);
 	if (rate_node->parent)
 		refcount_dec(&rate_node->parent->refcnt);
 	list_del(&rate_node->list);
@@ -6307,14 +6321,12 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.cmd = DEVLINK_CMD_RATE_GET,
 		.doit = devlink_nl_cmd_rate_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_RATE,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_RATE_SET,
 		.doit = devlink_nl_cmd_rate_set_doit,
 		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_RATE,
 	},
 	{
 		.cmd = DEVLINK_CMD_RATE_NEW,
@@ -6325,7 +6337,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.cmd = DEVLINK_CMD_RATE_DEL,
 		.doit = devlink_nl_cmd_rate_del_doit,
 		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_RATE_NODE,
 	},
 	{
 		.cmd = DEVLINK_CMD_PORT_SPLIT,
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 9fd683f38a53e..96cf8a1b8bced 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -132,24 +132,6 @@ int devlink_nl_pre_doit(const struct genl_split_ops *ops,
 		devlink_port = devlink_port_get_from_info(devlink, info);
 		if (!IS_ERR(devlink_port))
 			info->user_ptr[1] = devlink_port;
-	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) {
-		struct devlink_rate *devlink_rate;
-
-		devlink_rate = devlink_rate_get_from_info(devlink, info);
-		if (IS_ERR(devlink_rate)) {
-			err = PTR_ERR(devlink_rate);
-			goto unlock;
-		}
-		info->user_ptr[1] = devlink_rate;
-	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) {
-		struct devlink_rate *rate_node;
-
-		rate_node = devlink_rate_node_get_from_info(devlink, info);
-		if (IS_ERR(rate_node)) {
-			err = PTR_ERR(rate_node);
-			goto unlock;
-		}
-		info->user_ptr[1] = rate_node;
 	}
 	return 0;
 
-- 
GitLab


From ee6d78ac28c708c62fd83595e9366b0eb0deb014 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:04 +0200
Subject: [PATCH 1196/1806] devlink: introduce devlink_nl_pre_doit_port*()
 helper functions

Define port handling helpers what don't rely on internal_flags.
Have __devlink_nl_pre_doit() to accept the flags as a function arg and
make devlink_nl_pre_doit() a wrapper helper function calling it.
Introduce new helpers devlink_nl_pre_doit_port() and
devlink_nl_pre_doit_port_optional() to be used by split ops in follow-up
patch.

Note that the function prototypes are temporary until the generated ones
will replace them in a follow-up patch.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-4-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h |  5 +++++
 net/devlink/netlink.c       | 27 +++++++++++++++++++++++----
 2 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index ca04e4ee94277..9851fd48ab592 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -205,6 +205,11 @@ int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
 			     struct netlink_ext_ack *extack);
 
 /* Devlink nl cmds */
+int devlink_nl_pre_doit_port(const struct genl_split_ops *ops,
+			     struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
+				      struct sk_buff *skb,
+				      struct genl_info *info);
 int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 96cf8a1b8bced..3c59b9c491502 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -109,8 +109,8 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs)
 	return ERR_PTR(-ENODEV);
 }
 
-int devlink_nl_pre_doit(const struct genl_split_ops *ops,
-			struct sk_buff *skb, struct genl_info *info)
+static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info,
+				 u8 flags)
 {
 	struct devlink_port *devlink_port;
 	struct devlink *devlink;
@@ -121,14 +121,14 @@ int devlink_nl_pre_doit(const struct genl_split_ops *ops,
 		return PTR_ERR(devlink);
 
 	info->user_ptr[0] = devlink;
-	if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) {
+	if (flags & DEVLINK_NL_FLAG_NEED_PORT) {
 		devlink_port = devlink_port_get_from_info(devlink, info);
 		if (IS_ERR(devlink_port)) {
 			err = PTR_ERR(devlink_port);
 			goto unlock;
 		}
 		info->user_ptr[1] = devlink_port;
-	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) {
+	} else if (flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) {
 		devlink_port = devlink_port_get_from_info(devlink, info);
 		if (!IS_ERR(devlink_port))
 			info->user_ptr[1] = devlink_port;
@@ -141,6 +141,25 @@ unlock:
 	return err;
 }
 
+int devlink_nl_pre_doit(const struct genl_split_ops *ops,
+			struct sk_buff *skb, struct genl_info *info)
+{
+	return __devlink_nl_pre_doit(skb, info, ops->internal_flags);
+}
+
+int devlink_nl_pre_doit_port(const struct genl_split_ops *ops,
+			     struct sk_buff *skb, struct genl_info *info)
+{
+	return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_PORT);
+}
+
+int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
+				      struct sk_buff *skb,
+				      struct genl_info *info)
+{
+	return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT);
+}
+
 void devlink_nl_post_doit(const struct genl_split_ops *ops,
 			  struct sk_buff *skb, struct genl_info *info)
 {
-- 
GitLab


From 8fa995ad1f7f8f615b479edcf540cc12fe7b87ba Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:05 +0200
Subject: [PATCH 1197/1806] devlink: rename doit callbacks for per-instance
 dump commands

Rename netlink doit callback functions for the commands that do
implement per-instance dump to match the generated names that are going
to be introduce in the follow-up patch.

Note that the function prototypes are temporary until the generated ones
will replace them in a follow-up patch.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-5-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/dev.c           |  3 +-
 net/devlink/devl_internal.h | 22 ++++++++++--
 net/devlink/health.c        |  4 +--
 net/devlink/leftover.c      | 68 ++++++++++++++++---------------------
 4 files changed, 52 insertions(+), 45 deletions(-)

diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index 5dfba2248b904..167fe6188d21b 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -1206,8 +1206,7 @@ err_cancel_msg:
 	return err;
 }
 
-int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb,
-				      struct genl_info *info)
+int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct sk_buff *msg;
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 9851fd48ab592..f29ec0bfc5595 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -214,10 +214,22 @@ int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb,
-					    struct genl_info *info);
+int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_param_get_doit(struct sk_buff *skb,
+			      struct genl_info *info);
+int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_health_reporter_get_doit(struct sk_buff *skb,
+					struct genl_info *info);
 int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 					    struct genl_info *info);
 int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
@@ -230,3 +242,7 @@ int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb,
 						   struct genl_info *info);
 int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb,
 					     struct genl_info *info);
+int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_policer_get_doit(struct sk_buff *skb,
+				     struct genl_info *info);
diff --git a/net/devlink/health.c b/net/devlink/health.c
index 194340a8bb863..6df4e343d8c26 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -356,8 +356,8 @@ devlink_health_reporter_get_from_info(struct devlink *devlink,
 	return devlink_health_reporter_get_from_attrs(devlink, info->attrs);
 }
 
-int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb,
-					    struct genl_info *info)
+int devlink_nl_health_reporter_get_doit(struct sk_buff *skb,
+					struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_health_reporter *reporter;
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index b7b6850e26d81..bd8fa2f9a05bb 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -1038,8 +1038,7 @@ const struct devlink_cmd devl_cmd_rate_get = {
 	.dump_one		= devlink_nl_cmd_rate_get_dump_one,
 };
 
-static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb,
-					struct genl_info *info)
+int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_rate *devlink_rate;
@@ -1077,8 +1076,7 @@ devlink_rate_is_parent_node(struct devlink_rate *devlink_rate,
 	return false;
 }
 
-static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb,
-					struct genl_info *info)
+int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink_port *devlink_port = info->user_ptr[1];
 	struct sk_buff *msg;
@@ -1825,8 +1823,7 @@ static void devlink_linecard_notify(struct devlink_linecard *linecard,
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
-static int devlink_nl_cmd_linecard_get_doit(struct sk_buff *skb,
-					    struct genl_info *info)
+int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_linecard *linecard;
@@ -2091,8 +2088,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int devlink_nl_cmd_sb_get_doit(struct sk_buff *skb,
-				      struct genl_info *info)
+int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_sb *devlink_sb;
@@ -2194,8 +2190,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int devlink_nl_cmd_sb_pool_get_doit(struct sk_buff *skb,
-					   struct genl_info *info)
+int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_sb *devlink_sb;
@@ -2394,8 +2389,8 @@ sb_occ_get_failure:
 	return err;
 }
 
-static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb,
-						struct genl_info *info)
+int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
+				     struct genl_info *info)
 {
 	struct devlink_port *devlink_port = info->user_ptr[1];
 	struct devlink *devlink = devlink_port->devlink;
@@ -2603,8 +2598,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int devlink_nl_cmd_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
-						   struct genl_info *info)
+int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
+					struct genl_info *info)
 {
 	struct devlink_port *devlink_port = info->user_ptr[1];
 	struct devlink *devlink = devlink_port->devlink;
@@ -4295,8 +4290,8 @@ devlink_param_get_from_info(struct xarray *params, struct genl_info *info)
 	return devlink_param_find_by_name(params, param_name);
 }
 
-static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb,
-					 struct genl_info *info)
+int devlink_nl_param_get_doit(struct sk_buff *skb,
+			      struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_param_item *param_item;
@@ -4793,8 +4788,7 @@ static void devlink_region_snapshot_del(struct devlink_region *region,
 	kfree(snapshot);
 }
 
-static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb,
-					  struct genl_info *info)
+int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_port *port = NULL;
@@ -5655,8 +5649,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int devlink_nl_cmd_trap_get_doit(struct sk_buff *skb,
-					struct genl_info *info)
+int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct netlink_ext_ack *extack = info->extack;
 	struct devlink *devlink = info->user_ptr[0];
@@ -5866,8 +5859,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int devlink_nl_cmd_trap_group_get_doit(struct sk_buff *skb,
-					      struct genl_info *info)
+int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct netlink_ext_ack *extack = info->extack;
 	struct devlink *devlink = info->user_ptr[0];
@@ -6160,8 +6152,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int devlink_nl_cmd_trap_policer_get_doit(struct sk_buff *skb,
-						struct genl_info *info)
+int devlink_nl_trap_policer_get_doit(struct sk_buff *skb,
+				     struct genl_info *info)
 {
 	struct devlink_trap_policer_item *policer_item;
 	struct netlink_ext_ack *extack = info->extack;
@@ -6305,7 +6297,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_PORT_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_get_doit,
+		.doit = devlink_nl_port_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 		/* can be retrieved by unprivileged users */
@@ -6319,7 +6311,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_RATE_GET,
-		.doit = devlink_nl_cmd_rate_get_doit,
+		.doit = devlink_nl_rate_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6365,7 +6357,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_LINECARD_GET,
-		.doit = devlink_nl_cmd_linecard_get_doit,
+		.doit = devlink_nl_linecard_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6377,14 +6369,14 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_SB_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_get_doit,
+		.doit = devlink_nl_sb_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_POOL_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_pool_get_doit,
+		.doit = devlink_nl_sb_pool_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6397,7 +6389,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_SB_PORT_POOL_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_port_pool_get_doit,
+		.doit = devlink_nl_sb_port_pool_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 		/* can be retrieved by unprivileged users */
@@ -6412,7 +6404,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit,
+		.doit = devlink_nl_sb_tc_pool_bind_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 		/* can be retrieved by unprivileged users */
@@ -6493,7 +6485,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_PARAM_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_param_get_doit,
+		.doit = devlink_nl_param_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6521,7 +6513,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_REGION_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_region_get_doit,
+		.doit = devlink_nl_region_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		.flags = GENL_ADMIN_PERM,
 	},
@@ -6547,7 +6539,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_get_doit,
+		.doit = devlink_nl_health_reporter_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
 		/* can be retrieved by unprivileged users */
@@ -6602,7 +6594,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_TRAP_GET,
-		.doit = devlink_nl_cmd_trap_get_doit,
+		.doit = devlink_nl_trap_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6613,7 +6605,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_TRAP_GROUP_GET,
-		.doit = devlink_nl_cmd_trap_group_get_doit,
+		.doit = devlink_nl_trap_group_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6624,7 +6616,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_TRAP_POLICER_GET,
-		.doit = devlink_nl_cmd_trap_policer_get_doit,
+		.doit = devlink_nl_trap_policer_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6635,7 +6627,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_SELFTESTS_GET,
-		.doit = devlink_nl_cmd_selftests_get_doit,
+		.doit = devlink_nl_selftests_get_doit,
 		.dumpit = devlink_nl_instance_iter_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
-- 
GitLab


From 24c8e56d4f983527cc5e1f6d771fef8ec7ce352e Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:06 +0200
Subject: [PATCH 1198/1806] devlink: introduce dumpit callbacks for split ops

Introduce dumpit callbacks for generated split ops. Have them
as a thin wrapper around iteration function and allow to pass dump_one()
function pointer directly without need to store in devlink_cmd structs.

Note that the function prototypes are temporary until the generated ones
will replace them in a follow-up patch.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-6-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/dev.c           |  15 +--
 net/devlink/devl_internal.h |  45 +++++----
 net/devlink/health.c        |  16 +--
 net/devlink/leftover.c      | 189 ++++++++++++++++++++----------------
 net/devlink/netlink.c       |  26 -----
 5 files changed, 144 insertions(+), 147 deletions(-)

diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index 167fe6188d21b..22e8ab3eaaa21 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -1229,10 +1229,9 @@ int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info)
 	return genlmsg_reply(msg, info);
 }
 
-static int
-devlink_nl_cmd_selftests_get_dump_one(struct sk_buff *msg,
-				      struct devlink *devlink,
-				      struct netlink_callback *cb)
+static int devlink_nl_selftests_get_dump_one(struct sk_buff *msg,
+					     struct devlink *devlink,
+					     struct netlink_callback *cb)
 {
 	if (!devlink->ops->selftest_check)
 		return 0;
@@ -1243,9 +1242,11 @@ devlink_nl_cmd_selftests_get_dump_one(struct sk_buff *msg,
 					 cb->extack);
 }
 
-const struct devlink_cmd devl_cmd_selftests_get = {
-	.dump_one		= devlink_nl_cmd_selftests_get_dump_one,
-};
+int devlink_nl_selftests_get_dumpit(struct sk_buff *skb,
+				    struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_selftests_get_dump_one);
+}
 
 static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id,
 				       enum devlink_selftest_status test_status)
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index f29ec0bfc5595..500c91c61b2d3 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -117,10 +117,6 @@ typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg,
 				       struct devlink *devlink,
 				       struct netlink_callback *cb);
 
-struct devlink_cmd {
-	devlink_nl_dump_one_func_t *dump_one;
-};
-
 extern const struct genl_small_ops devlink_nl_small_ops[54];
 
 struct devlink *
@@ -131,7 +127,6 @@ void devlink_notify_register(struct devlink *devlink);
 
 int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 		      devlink_nl_dump_one_func_t *dump_one);
-int devlink_nl_instance_iter_dumpit(struct sk_buff *msg, struct netlink_callback *cb);
 
 static inline struct devlink_nl_dump_state *
 devlink_dump_state(struct netlink_callback *cb)
@@ -151,22 +146,6 @@ devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
 	return 0;
 }
 
-/* Commands */
-extern const struct devlink_cmd devl_cmd_port_get;
-extern const struct devlink_cmd devl_cmd_sb_get;
-extern const struct devlink_cmd devl_cmd_sb_pool_get;
-extern const struct devlink_cmd devl_cmd_sb_port_pool_get;
-extern const struct devlink_cmd devl_cmd_sb_tc_pool_bind_get;
-extern const struct devlink_cmd devl_cmd_param_get;
-extern const struct devlink_cmd devl_cmd_region_get;
-extern const struct devlink_cmd devl_cmd_health_reporter_get;
-extern const struct devlink_cmd devl_cmd_trap_get;
-extern const struct devlink_cmd devl_cmd_trap_group_get;
-extern const struct devlink_cmd devl_cmd_trap_policer_get;
-extern const struct devlink_cmd devl_cmd_rate_get;
-extern const struct devlink_cmd devl_cmd_linecard_get;
-extern const struct devlink_cmd devl_cmd_selftests_get;
-
 /* Notify */
 void devlink_notify(struct devlink *devlink, enum devlink_command cmd);
 
@@ -215,21 +194,40 @@ int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info)
 int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_selftests_get_dumpit(struct sk_buff *skb,
+				    struct netlink_callback *cb);
 int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb);
 int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb);
 int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
 				     struct genl_info *info);
+int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb);
 int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
 					struct genl_info *info);
+int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb);
 int devlink_nl_param_get_doit(struct sk_buff *skb,
 			      struct genl_info *info);
+int devlink_nl_param_get_dumpit(struct sk_buff *skb,
+				struct netlink_callback *cb);
 int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb);
 int devlink_nl_health_reporter_get_doit(struct sk_buff *skb,
 					struct genl_info *info);
+int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb);
 int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 					    struct genl_info *info);
 int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
@@ -243,6 +241,11 @@ int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb,
 int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb,
 					     struct genl_info *info);
 int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb);
 int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_trap_policer_get_doit(struct sk_buff *skb,
 				     struct genl_info *info);
+int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb);
diff --git a/net/devlink/health.c b/net/devlink/health.c
index 6df4e343d8c26..dbe2d6a1df3bd 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -384,10 +384,9 @@ int devlink_nl_health_reporter_get_doit(struct sk_buff *skb,
 	return genlmsg_reply(msg, info);
 }
 
-static int
-devlink_nl_cmd_health_reporter_get_dump_one(struct sk_buff *msg,
-					    struct devlink *devlink,
-					    struct netlink_callback *cb)
+static int devlink_nl_health_reporter_get_dump_one(struct sk_buff *msg,
+						   struct devlink *devlink,
+						   struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_health_reporter *reporter;
@@ -434,9 +433,12 @@ devlink_nl_cmd_health_reporter_get_dump_one(struct sk_buff *msg,
 	return 0;
 }
 
-const struct devlink_cmd devl_cmd_health_reporter_get = {
-	.dump_one		= devlink_nl_cmd_health_reporter_get_dump_one,
-};
+int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb,
+				 devlink_nl_health_reporter_get_dump_one);
+}
 
 int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 					    struct genl_info *info)
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index bd8fa2f9a05bb..21f1058ef14d4 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -1005,8 +1005,8 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate,
 }
 
 static int
-devlink_nl_cmd_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-				 struct netlink_callback *cb)
+devlink_nl_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+			     struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_rate *devlink_rate;
@@ -1034,9 +1034,10 @@ devlink_nl_cmd_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_rate_get = {
-	.dump_one		= devlink_nl_cmd_rate_get_dump_one,
-};
+int devlink_nl_rate_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_rate_get_dump_one);
+}
 
 int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
@@ -1098,8 +1099,8 @@ int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info)
 }
 
 static int
-devlink_nl_cmd_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-				 struct netlink_callback *cb)
+devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+			     struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_port *devlink_port;
@@ -1121,9 +1122,10 @@ devlink_nl_cmd_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_port_get = {
-	.dump_one		= devlink_nl_cmd_port_get_dump_one,
-};
+int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_port_get_dump_one);
+}
 
 static int devlink_port_type_set(struct devlink_port *devlink_port,
 				 enum devlink_port_type port_type)
@@ -1852,9 +1854,9 @@ int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info)
 	return genlmsg_reply(msg, info);
 }
 
-static int devlink_nl_cmd_linecard_get_dump_one(struct sk_buff *msg,
-						struct devlink *devlink,
-						struct netlink_callback *cb)
+static int devlink_nl_linecard_get_dump_one(struct sk_buff *msg,
+					    struct devlink *devlink,
+					    struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_linecard *linecard;
@@ -1884,9 +1886,11 @@ static int devlink_nl_cmd_linecard_get_dump_one(struct sk_buff *msg,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_linecard_get = {
-	.dump_one		= devlink_nl_cmd_linecard_get_dump_one,
-};
+int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_linecard_get_dump_one);
+}
 
 static struct devlink_linecard_type *
 devlink_linecard_type_lookup(struct devlink_linecard *linecard,
@@ -2115,8 +2119,8 @@ int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info)
 }
 
 static int
-devlink_nl_cmd_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-			       struct netlink_callback *cb)
+devlink_nl_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+			   struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_sb *devlink_sb;
@@ -2143,9 +2147,10 @@ devlink_nl_cmd_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_sb_get = {
-	.dump_one		= devlink_nl_cmd_sb_get_dump_one,
-};
+int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_get_dump_one);
+}
 
 static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink,
 				   struct devlink_sb *devlink_sb,
@@ -2252,9 +2257,8 @@ static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
 }
 
 static int
-devlink_nl_cmd_sb_pool_get_dump_one(struct sk_buff *msg,
-				    struct devlink *devlink,
-				    struct netlink_callback *cb)
+devlink_nl_sb_pool_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+				struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_sb *devlink_sb;
@@ -2280,9 +2284,11 @@ devlink_nl_cmd_sb_pool_get_dump_one(struct sk_buff *msg,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_sb_pool_get = {
-	.dump_one		= devlink_nl_cmd_sb_pool_get_dump_one,
-};
+int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_pool_get_dump_one);
+}
 
 static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index,
 			       u16 pool_index, u32 size,
@@ -2460,9 +2466,9 @@ static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
 }
 
 static int
-devlink_nl_cmd_sb_port_pool_get_dump_one(struct sk_buff *msg,
-					 struct devlink *devlink,
-					 struct netlink_callback *cb)
+devlink_nl_sb_port_pool_get_dump_one(struct sk_buff *msg,
+				     struct devlink *devlink,
+				     struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_sb *devlink_sb;
@@ -2488,9 +2494,11 @@ devlink_nl_cmd_sb_port_pool_get_dump_one(struct sk_buff *msg,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_sb_port_pool_get = {
-	.dump_one		= devlink_nl_cmd_sb_port_pool_get_dump_one,
-};
+int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_port_pool_get_dump_one);
+}
 
 static int devlink_sb_port_pool_set(struct devlink_port *devlink_port,
 				    unsigned int sb_index, u16 pool_index,
@@ -2694,10 +2702,9 @@ static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
 	return 0;
 }
 
-static int
-devlink_nl_cmd_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg,
-					    struct devlink *devlink,
-					    struct netlink_callback *cb)
+static int devlink_nl_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg,
+						   struct devlink *devlink,
+						   struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_sb *devlink_sb;
@@ -2723,9 +2730,12 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_sb_tc_pool_bind_get = {
-	.dump_one		= devlink_nl_cmd_sb_tc_pool_bind_get_dump_one,
-};
+int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb,
+				 devlink_nl_sb_tc_pool_bind_get_dump_one);
+}
 
 static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
 				       unsigned int sb_index, u16 tc_index,
@@ -4173,9 +4183,9 @@ static void devlink_param_notify(struct devlink *devlink,
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
-static int
-devlink_nl_cmd_param_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-				  struct netlink_callback *cb)
+static int devlink_nl_param_get_dump_one(struct sk_buff *msg,
+					 struct devlink *devlink,
+					 struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_param_item *param_item;
@@ -4199,9 +4209,11 @@ devlink_nl_cmd_param_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_param_get = {
-	.dump_one		= devlink_nl_cmd_param_get_dump_one,
-};
+int devlink_nl_param_get_dumpit(struct sk_buff *skb,
+				struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_param_get_dump_one);
+}
 
 static int
 devlink_param_type_get_from_info(struct genl_info *info,
@@ -4861,9 +4873,9 @@ out:
 	return err;
 }
 
-static int
-devlink_nl_cmd_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-				   struct netlink_callback *cb)
+static int devlink_nl_region_get_dump_one(struct sk_buff *msg,
+					  struct devlink *devlink,
+					  struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_region *region;
@@ -4901,9 +4913,11 @@ devlink_nl_cmd_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 	return 0;
 }
 
-const struct devlink_cmd devl_cmd_region_get = {
-	.dump_one		= devlink_nl_cmd_region_get_dump_one,
-};
+int devlink_nl_region_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_region_get_dump_one);
+}
 
 static int devlink_nl_cmd_region_del(struct sk_buff *skb,
 				     struct genl_info *info)
@@ -5683,9 +5697,9 @@ err_trap_fill:
 	return err;
 }
 
-static int
-devlink_nl_cmd_trap_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-				 struct netlink_callback *cb)
+static int devlink_nl_trap_get_dump_one(struct sk_buff *msg,
+					struct devlink *devlink,
+					struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_trap_item *trap_item;
@@ -5712,9 +5726,10 @@ devlink_nl_cmd_trap_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_trap_get = {
-	.dump_one		= devlink_nl_cmd_trap_get_dump_one,
-};
+int devlink_nl_trap_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_trap_get_dump_one);
+}
 
 static int __devlink_trap_action_set(struct devlink *devlink,
 				     struct devlink_trap_item *trap_item,
@@ -5893,10 +5908,9 @@ err_trap_group_fill:
 	return err;
 }
 
-static int
-devlink_nl_cmd_trap_group_get_dump_one(struct sk_buff *msg,
-				       struct devlink *devlink,
-				       struct netlink_callback *cb)
+static int devlink_nl_trap_group_get_dump_one(struct sk_buff *msg,
+					      struct devlink *devlink,
+					      struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_trap_group_item *group_item;
@@ -5924,9 +5938,11 @@ devlink_nl_cmd_trap_group_get_dump_one(struct sk_buff *msg,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_trap_group_get = {
-	.dump_one		= devlink_nl_cmd_trap_group_get_dump_one,
-};
+int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_trap_group_get_dump_one);
+}
 
 static int
 __devlink_trap_group_action_set(struct devlink *devlink,
@@ -6187,10 +6203,9 @@ err_trap_policer_fill:
 	return err;
 }
 
-static int
-devlink_nl_cmd_trap_policer_get_dump_one(struct sk_buff *msg,
-					 struct devlink *devlink,
-					 struct netlink_callback *cb)
+static int devlink_nl_trap_policer_get_dump_one(struct sk_buff *msg,
+						struct devlink *devlink,
+						struct netlink_callback *cb)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_trap_policer_item *policer_item;
@@ -6217,9 +6232,11 @@ devlink_nl_cmd_trap_policer_get_dump_one(struct sk_buff *msg,
 	return err;
 }
 
-const struct devlink_cmd devl_cmd_trap_policer_get = {
-	.dump_one		= devlink_nl_cmd_trap_policer_get_dump_one,
-};
+int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_trap_policer_get_dump_one);
+}
 
 static int
 devlink_trap_policer_set(struct devlink *devlink,
@@ -6298,7 +6315,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.cmd = DEVLINK_CMD_PORT_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_port_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_port_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6312,7 +6329,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_RATE_GET,
 		.doit = devlink_nl_rate_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_rate_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
@@ -6358,7 +6375,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_LINECARD_GET,
 		.doit = devlink_nl_linecard_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_linecard_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
@@ -6370,14 +6387,14 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.cmd = DEVLINK_CMD_SB_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_sb_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_sb_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_POOL_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_sb_pool_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_sb_pool_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
@@ -6390,7 +6407,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.cmd = DEVLINK_CMD_SB_PORT_POOL_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_sb_port_pool_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_sb_port_pool_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6405,7 +6422,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_sb_tc_pool_bind_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_sb_tc_pool_bind_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6486,7 +6503,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.cmd = DEVLINK_CMD_PARAM_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_param_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_param_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
@@ -6514,7 +6531,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.cmd = DEVLINK_CMD_REGION_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_region_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_region_get_dumpit,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
@@ -6540,7 +6557,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_health_reporter_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_health_reporter_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
 		/* can be retrieved by unprivileged users */
 	},
@@ -6595,7 +6612,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_TRAP_GET,
 		.doit = devlink_nl_trap_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_trap_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
@@ -6606,7 +6623,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_TRAP_GROUP_GET,
 		.doit = devlink_nl_trap_group_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_trap_group_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
@@ -6617,7 +6634,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_TRAP_POLICER_GET,
 		.doit = devlink_nl_trap_policer_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_trap_policer_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
@@ -6628,7 +6645,7 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 	{
 		.cmd = DEVLINK_CMD_SELFTESTS_GET,
 		.doit = devlink_nl_selftests_get_doit,
-		.dumpit = devlink_nl_instance_iter_dumpit,
+		.dumpit = devlink_nl_selftests_get_dumpit,
 		/* can be retrieved by unprivileged users */
 	},
 	{
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 3c59b9c491502..13388665f319d 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -170,23 +170,6 @@ void devlink_nl_post_doit(const struct genl_split_ops *ops,
 	devlink_put(devlink);
 }
 
-static const struct devlink_cmd *devl_cmds[] = {
-	[DEVLINK_CMD_PORT_GET]		= &devl_cmd_port_get,
-	[DEVLINK_CMD_SB_GET]		= &devl_cmd_sb_get,
-	[DEVLINK_CMD_SB_POOL_GET]	= &devl_cmd_sb_pool_get,
-	[DEVLINK_CMD_SB_PORT_POOL_GET]	= &devl_cmd_sb_port_pool_get,
-	[DEVLINK_CMD_SB_TC_POOL_BIND_GET] = &devl_cmd_sb_tc_pool_bind_get,
-	[DEVLINK_CMD_PARAM_GET]		= &devl_cmd_param_get,
-	[DEVLINK_CMD_REGION_GET]	= &devl_cmd_region_get,
-	[DEVLINK_CMD_HEALTH_REPORTER_GET] = &devl_cmd_health_reporter_get,
-	[DEVLINK_CMD_TRAP_GET]		= &devl_cmd_trap_get,
-	[DEVLINK_CMD_TRAP_GROUP_GET]	= &devl_cmd_trap_group_get,
-	[DEVLINK_CMD_TRAP_POLICER_GET]	= &devl_cmd_trap_policer_get,
-	[DEVLINK_CMD_RATE_GET]		= &devl_cmd_rate_get,
-	[DEVLINK_CMD_LINECARD_GET]	= &devl_cmd_linecard_get,
-	[DEVLINK_CMD_SELFTESTS_GET]	= &devl_cmd_selftests_get,
-};
-
 int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 		      devlink_nl_dump_one_func_t *dump_one)
 {
@@ -220,15 +203,6 @@ int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 	return msg->len;
 }
 
-int devlink_nl_instance_iter_dumpit(struct sk_buff *msg,
-				    struct netlink_callback *cb)
-{
-	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	const struct devlink_cmd *cmd = devl_cmds[info->op.cmd];
-
-	return devlink_nl_dumpit(msg, cb, cmd->dump_one);
-}
-
 struct genl_family devlink_nl_family __ro_after_init = {
 	.name		= DEVLINK_GENL_NAME,
 	.version	= DEVLINK_GENL_VERSION,
-- 
GitLab


From 7d3c6fec6135e10842587f38a15d7d06fd02c21f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:07 +0200
Subject: [PATCH 1199/1806] devlink: pass flags as an arg of dump_one()
 callback

In order to easily set NLM_F_DUMP_FILTERED for partial dumps, pass the
flags as an arg of dump_one() callback. Currently, it is always
NLM_F_MULTI.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-7-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/dev.c           | 13 +++---
 net/devlink/devl_internal.h |  3 +-
 net/devlink/health.c        |  7 +--
 net/devlink/leftover.c      | 87 ++++++++++++++++++-------------------
 net/devlink/netlink.c       |  2 +-
 5 files changed, 56 insertions(+), 56 deletions(-)

diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index 22e8ab3eaaa21..abf3393a7a175 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -218,11 +218,11 @@ int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info)
 
 static int
 devlink_nl_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-			struct netlink_callback *cb)
+			struct netlink_callback *cb, int flags)
 {
 	return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW,
 			       NETLINK_CB(cb->skb).portid,
-			       cb->nlh->nlmsg_seq, NLM_F_MULTI);
+			       cb->nlh->nlmsg_seq, flags);
 }
 
 int devlink_nl_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb)
@@ -828,13 +828,13 @@ int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info)
 
 static int
 devlink_nl_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-			     struct netlink_callback *cb)
+			     struct netlink_callback *cb, int flags)
 {
 	int err;
 
 	err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET,
 				   NETLINK_CB(cb->skb).portid,
-				   cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				   cb->nlh->nlmsg_seq, flags,
 				   cb->extack);
 	if (err == -EOPNOTSUPP)
 		err = 0;
@@ -1231,14 +1231,15 @@ int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info)
 
 static int devlink_nl_selftests_get_dump_one(struct sk_buff *msg,
 					     struct devlink *devlink,
-					     struct netlink_callback *cb)
+					     struct netlink_callback *cb,
+					     int flags)
 {
 	if (!devlink->ops->selftest_check)
 		return 0;
 
 	return devlink_nl_selftests_fill(msg, devlink,
 					 NETLINK_CB(cb->skb).portid,
-					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
+					 cb->nlh->nlmsg_seq, flags,
 					 cb->extack);
 }
 
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 500c91c61b2d3..f8af6ffdbb3ad 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -115,7 +115,8 @@ struct devlink_nl_dump_state {
 
 typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg,
 				       struct devlink *devlink,
-				       struct netlink_callback *cb);
+				       struct netlink_callback *cb,
+				       int flags);
 
 extern const struct genl_small_ops devlink_nl_small_ops[54];
 
diff --git a/net/devlink/health.c b/net/devlink/health.c
index dbe2d6a1df3bd..b9b3e68d90430 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -386,7 +386,8 @@ int devlink_nl_health_reporter_get_doit(struct sk_buff *skb,
 
 static int devlink_nl_health_reporter_get_dump_one(struct sk_buff *msg,
 						   struct devlink *devlink,
-						   struct netlink_callback *cb)
+						   struct netlink_callback *cb,
+						   int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_health_reporter *reporter;
@@ -404,7 +405,7 @@ static int devlink_nl_health_reporter_get_dump_one(struct sk_buff *msg,
 						      DEVLINK_CMD_HEALTH_REPORTER_GET,
 						      NETLINK_CB(cb->skb).portid,
 						      cb->nlh->nlmsg_seq,
-						      NLM_F_MULTI);
+						      flags);
 		if (err) {
 			state->idx = idx;
 			return err;
@@ -421,7 +422,7 @@ static int devlink_nl_health_reporter_get_dump_one(struct sk_buff *msg,
 							      DEVLINK_CMD_HEALTH_REPORTER_GET,
 							      NETLINK_CB(cb->skb).portid,
 							      cb->nlh->nlmsg_seq,
-							      NLM_F_MULTI);
+							      flags);
 			if (err) {
 				state->idx = idx;
 				return err;
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 21f1058ef14d4..883c65545d263 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -1006,7 +1006,7 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate,
 
 static int
 devlink_nl_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-			     struct netlink_callback *cb)
+			     struct netlink_callback *cb, int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_rate *devlink_rate;
@@ -1022,8 +1022,7 @@ devlink_nl_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 			continue;
 		}
 		err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id,
-					   cb->nlh->nlmsg_seq,
-					   NLM_F_MULTI, NULL);
+					   cb->nlh->nlmsg_seq, flags, NULL);
 		if (err) {
 			state->idx = idx;
 			break;
@@ -1100,7 +1099,7 @@ int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info)
 
 static int
 devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-			     struct netlink_callback *cb)
+			     struct netlink_callback *cb, int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_port *devlink_port;
@@ -1111,8 +1110,8 @@ devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 		err = devlink_nl_port_fill(msg, devlink_port,
 					   DEVLINK_CMD_NEW,
 					   NETLINK_CB(cb->skb).portid,
-					   cb->nlh->nlmsg_seq,
-					   NLM_F_MULTI, cb->extack);
+					   cb->nlh->nlmsg_seq, flags,
+					   cb->extack);
 		if (err) {
 			state->idx = port_index;
 			break;
@@ -1856,7 +1855,8 @@ int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info)
 
 static int devlink_nl_linecard_get_dump_one(struct sk_buff *msg,
 					    struct devlink *devlink,
-					    struct netlink_callback *cb)
+					    struct netlink_callback *cb,
+					    int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_linecard *linecard;
@@ -1872,8 +1872,7 @@ static int devlink_nl_linecard_get_dump_one(struct sk_buff *msg,
 		err = devlink_nl_linecard_fill(msg, devlink, linecard,
 					       DEVLINK_CMD_LINECARD_NEW,
 					       NETLINK_CB(cb->skb).portid,
-					       cb->nlh->nlmsg_seq,
-					       NLM_F_MULTI,
+					       cb->nlh->nlmsg_seq, flags,
 					       cb->extack);
 		mutex_unlock(&linecard->state_lock);
 		if (err) {
@@ -2120,7 +2119,7 @@ int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info)
 
 static int
 devlink_nl_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-			   struct netlink_callback *cb)
+			   struct netlink_callback *cb, int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_sb *devlink_sb;
@@ -2135,8 +2134,7 @@ devlink_nl_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 		err = devlink_nl_sb_fill(msg, devlink, devlink_sb,
 					 DEVLINK_CMD_SB_NEW,
 					 NETLINK_CB(cb->skb).portid,
-					 cb->nlh->nlmsg_seq,
-					 NLM_F_MULTI);
+					 cb->nlh->nlmsg_seq, flags);
 		if (err) {
 			state->idx = idx;
 			break;
@@ -2233,7 +2231,7 @@ int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info)
 static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
 				struct devlink *devlink,
 				struct devlink_sb *devlink_sb,
-				u32 portid, u32 seq)
+				u32 portid, u32 seq, int flags)
 {
 	u16 pool_count = devlink_sb_pool_count(devlink_sb);
 	u16 pool_index;
@@ -2248,7 +2246,7 @@ static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
 					      devlink_sb,
 					      pool_index,
 					      DEVLINK_CMD_SB_POOL_NEW,
-					      portid, seq, NLM_F_MULTI);
+					      portid, seq, flags);
 		if (err)
 			return err;
 		(*p_idx)++;
@@ -2258,7 +2256,7 @@ static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
 
 static int
 devlink_nl_sb_pool_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-				struct netlink_callback *cb)
+				struct netlink_callback *cb, int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_sb *devlink_sb;
@@ -2272,7 +2270,7 @@ devlink_nl_sb_pool_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 		err = __sb_pool_get_dumpit(msg, state->idx, &idx,
 					   devlink, devlink_sb,
 					   NETLINK_CB(cb->skb).portid,
-					   cb->nlh->nlmsg_seq);
+					   cb->nlh->nlmsg_seq, flags);
 		if (err == -EOPNOTSUPP) {
 			err = 0;
 		} else if (err) {
@@ -2436,7 +2434,7 @@ int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
 static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
 				     struct devlink *devlink,
 				     struct devlink_sb *devlink_sb,
-				     u32 portid, u32 seq)
+				     u32 portid, u32 seq, int flags)
 {
 	struct devlink_port *devlink_port;
 	u16 pool_count = devlink_sb_pool_count(devlink_sb);
@@ -2455,8 +2453,7 @@ static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
 							   devlink_sb,
 							   pool_index,
 							   DEVLINK_CMD_SB_PORT_POOL_NEW,
-							   portid, seq,
-							   NLM_F_MULTI);
+							   portid, seq, flags);
 			if (err)
 				return err;
 			(*p_idx)++;
@@ -2468,7 +2465,7 @@ static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
 static int
 devlink_nl_sb_port_pool_get_dump_one(struct sk_buff *msg,
 				     struct devlink *devlink,
-				     struct netlink_callback *cb)
+				     struct netlink_callback *cb, int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_sb *devlink_sb;
@@ -2482,7 +2479,7 @@ devlink_nl_sb_port_pool_get_dump_one(struct sk_buff *msg,
 		err = __sb_port_pool_get_dumpit(msg, state->idx, &idx,
 						devlink, devlink_sb,
 						NETLINK_CB(cb->skb).portid,
-						cb->nlh->nlmsg_seq);
+						cb->nlh->nlmsg_seq, flags);
 		if (err == -EOPNOTSUPP) {
 			err = 0;
 		} else if (err) {
@@ -2654,7 +2651,7 @@ static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
 					int start, int *p_idx,
 					struct devlink *devlink,
 					struct devlink_sb *devlink_sb,
-					u32 portid, u32 seq)
+					u32 portid, u32 seq, int flags)
 {
 	struct devlink_port *devlink_port;
 	unsigned long port_index;
@@ -2675,7 +2672,7 @@ static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
 							      DEVLINK_SB_POOL_TYPE_INGRESS,
 							      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
 							      portid, seq,
-							      NLM_F_MULTI);
+							      flags);
 			if (err)
 				return err;
 			(*p_idx)++;
@@ -2693,7 +2690,7 @@ static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
 							      DEVLINK_SB_POOL_TYPE_EGRESS,
 							      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
 							      portid, seq,
-							      NLM_F_MULTI);
+							      flags);
 			if (err)
 				return err;
 			(*p_idx)++;
@@ -2704,7 +2701,8 @@ static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
 
 static int devlink_nl_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg,
 						   struct devlink *devlink,
-						   struct netlink_callback *cb)
+						   struct netlink_callback *cb,
+						   int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_sb *devlink_sb;
@@ -2718,7 +2716,7 @@ static int devlink_nl_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg,
 		err = __sb_tc_pool_bind_get_dumpit(msg, state->idx, &idx,
 						   devlink, devlink_sb,
 						   NETLINK_CB(cb->skb).portid,
-						   cb->nlh->nlmsg_seq);
+						   cb->nlh->nlmsg_seq, flags);
 		if (err == -EOPNOTSUPP) {
 			err = 0;
 		} else if (err) {
@@ -4185,7 +4183,8 @@ static void devlink_param_notify(struct devlink *devlink,
 
 static int devlink_nl_param_get_dump_one(struct sk_buff *msg,
 					 struct devlink *devlink,
-					 struct netlink_callback *cb)
+					 struct netlink_callback *cb,
+					 int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_param_item *param_item;
@@ -4196,8 +4195,7 @@ static int devlink_nl_param_get_dump_one(struct sk_buff *msg,
 		err = devlink_nl_param_fill(msg, devlink, 0, param_item,
 					    DEVLINK_CMD_PARAM_GET,
 					    NETLINK_CB(cb->skb).portid,
-					    cb->nlh->nlmsg_seq,
-					    NLM_F_MULTI);
+					    cb->nlh->nlmsg_seq, flags);
 		if (err == -EOPNOTSUPP) {
 			err = 0;
 		} else if (err) {
@@ -4848,8 +4846,7 @@ int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info)
 static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg,
 						 struct netlink_callback *cb,
 						 struct devlink_port *port,
-						 int *idx,
-						 int start)
+						 int *idx, int start, int flags)
 {
 	struct devlink_region *region;
 	int err = 0;
@@ -4863,7 +4860,7 @@ static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg,
 					     DEVLINK_CMD_REGION_GET,
 					     NETLINK_CB(cb->skb).portid,
 					     cb->nlh->nlmsg_seq,
-					     NLM_F_MULTI, region);
+					     flags, region);
 		if (err)
 			goto out;
 		(*idx)++;
@@ -4875,7 +4872,8 @@ out:
 
 static int devlink_nl_region_get_dump_one(struct sk_buff *msg,
 					  struct devlink *devlink,
-					  struct netlink_callback *cb)
+					  struct netlink_callback *cb,
+					  int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_region *region;
@@ -4892,8 +4890,8 @@ static int devlink_nl_region_get_dump_one(struct sk_buff *msg,
 		err = devlink_nl_region_fill(msg, devlink,
 					     DEVLINK_CMD_REGION_GET,
 					     NETLINK_CB(cb->skb).portid,
-					     cb->nlh->nlmsg_seq,
-					     NLM_F_MULTI, region);
+					     cb->nlh->nlmsg_seq, flags,
+					     region);
 		if (err) {
 			state->idx = idx;
 			return err;
@@ -4903,7 +4901,7 @@ static int devlink_nl_region_get_dump_one(struct sk_buff *msg,
 
 	xa_for_each(&devlink->ports, port_index, port) {
 		err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, &idx,
-							    state->idx);
+							    state->idx, flags);
 		if (err) {
 			state->idx = idx;
 			return err;
@@ -5699,7 +5697,7 @@ err_trap_fill:
 
 static int devlink_nl_trap_get_dump_one(struct sk_buff *msg,
 					struct devlink *devlink,
-					struct netlink_callback *cb)
+					struct netlink_callback *cb, int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_trap_item *trap_item;
@@ -5714,8 +5712,7 @@ static int devlink_nl_trap_get_dump_one(struct sk_buff *msg,
 		err = devlink_nl_trap_fill(msg, devlink, trap_item,
 					   DEVLINK_CMD_TRAP_NEW,
 					   NETLINK_CB(cb->skb).portid,
-					   cb->nlh->nlmsg_seq,
-					   NLM_F_MULTI);
+					   cb->nlh->nlmsg_seq, flags);
 		if (err) {
 			state->idx = idx;
 			break;
@@ -5910,7 +5907,8 @@ err_trap_group_fill:
 
 static int devlink_nl_trap_group_get_dump_one(struct sk_buff *msg,
 					      struct devlink *devlink,
-					      struct netlink_callback *cb)
+					      struct netlink_callback *cb,
+					      int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_trap_group_item *group_item;
@@ -5926,8 +5924,7 @@ static int devlink_nl_trap_group_get_dump_one(struct sk_buff *msg,
 		err = devlink_nl_trap_group_fill(msg, devlink, group_item,
 						 DEVLINK_CMD_TRAP_GROUP_NEW,
 						 NETLINK_CB(cb->skb).portid,
-						 cb->nlh->nlmsg_seq,
-						 NLM_F_MULTI);
+						 cb->nlh->nlmsg_seq, flags);
 		if (err) {
 			state->idx = idx;
 			break;
@@ -6205,7 +6202,8 @@ err_trap_policer_fill:
 
 static int devlink_nl_trap_policer_get_dump_one(struct sk_buff *msg,
 						struct devlink *devlink,
-						struct netlink_callback *cb)
+						struct netlink_callback *cb,
+						int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink_trap_policer_item *policer_item;
@@ -6220,8 +6218,7 @@ static int devlink_nl_trap_policer_get_dump_one(struct sk_buff *msg,
 		err = devlink_nl_trap_policer_fill(msg, devlink, policer_item,
 						   DEVLINK_CMD_TRAP_POLICER_NEW,
 						   NETLINK_CB(cb->skb).portid,
-						   cb->nlh->nlmsg_seq,
-						   NLM_F_MULTI);
+						   cb->nlh->nlmsg_seq, flags);
 		if (err) {
 			state->idx = idx;
 			break;
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 13388665f319d..47e44fb45815f 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -182,7 +182,7 @@ int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 		devl_lock(devlink);
 
 		if (devl_is_registered(devlink))
-			err = dump_one(msg, devlink, cb);
+			err = dump_one(msg, devlink, cb, NLM_F_MULTI);
 		else
 			err = 0;
 
-- 
GitLab


From 7199c86247e9618981a2916900d3fcb83e5df157 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:08 +0200
Subject: [PATCH 1200/1806] netlink: specs: devlink: add commands that do
 per-instance dump

Add the definitions for the commands that do per-instance dump
and re-generate the related code.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-8-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/devlink.yaml |  444 +++-
 net/devlink/netlink_gen.c                |  332 ++-
 net/devlink/netlink_gen.h                |   52 +-
 tools/net/ynl/generated/devlink-user.c   | 2341 ++++++++++++++++++++--
 tools/net/ynl/generated/devlink-user.h   | 1295 +++++++++++-
 5 files changed, 4319 insertions(+), 145 deletions(-)

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index f6df0b3fd502f..4f2aa48017a70 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -6,6 +6,16 @@ protocol: genetlink-legacy
 
 doc: Partial family for Devlink.
 
+definitions:
+  -
+    type: enum
+    name: sb-pool-type
+    entries:
+      -
+        name: ingress
+      -
+        name: egress
+
 attribute-sets:
   -
     name: devlink
@@ -24,6 +34,46 @@ attribute-sets:
 
       # TODO: fill in the attributes in between
 
+      -
+        name: sb-index
+        type: u32
+        value: 11
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: sb-pool-index
+        type: u16
+        value: 17
+
+      -
+        name: sb-pool-type
+        type: u8
+        enum: sb-pool-type
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: sb-tc-index
+        type: u16
+        value: 22
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: param-name
+        type: string
+        value: 81
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: region-name
+        type: string
+        value: 88
+
+      # TODO: fill in the attributes in between
+
       -
         name: info-driver-name
         type: string
@@ -55,10 +105,35 @@ attribute-sets:
 
       # TODO: fill in the attributes in between
 
+      -
+        name: health-reporter-name
+        type: string
+        value: 115
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: trap-name
+        type: string
+        value: 130
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: trap-group-name
+        type: string
+        value: 135
+
       -
         name: reload-failed
         type: u8
-        value: 136
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: trap-policer-id
+        type: u32
+        value: 142
 
       # TODO: fill in the attributes in between
 
@@ -103,6 +178,21 @@ attribute-sets:
         type: nest
         multi-attr: true
         nested-attributes: dl-reload-act-stats
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: rate-node-name
+        type: string
+        value: 168
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: linecard-index
+        type: u32
+        value: 171
+
   -
     name: dl-dev-stats
     subset-of: devlink
@@ -188,6 +278,188 @@ operations:
       dump:
         reply: *get-reply
 
+    -
+      name: port-get
+      doc: Get devlink port instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          value: 5
+          attributes: &port-id-attrs
+            - bus-name
+            - dev-name
+            - port-index
+        reply:
+          value: 7
+          attributes: *port-id-attrs
+      dump:
+        reply:
+          value: 3  # due to a bug, port dump returns DEVLINK_CMD_NEW
+          attributes: *port-id-attrs
+
+      # TODO: fill in the operations in between
+
+    -
+      name: sb-get
+      doc: Get shared buffer instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          value: 11
+          attributes: &sb-id-attrs
+            - bus-name
+            - dev-name
+            - sb-index
+        reply: &sb-get-reply
+          value: 11
+          attributes: *sb-id-attrs
+      dump:
+        reply: *sb-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: sb-pool-get
+      doc: Get shared buffer pool instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          value: 15
+          attributes: &sb-pool-id-attrs
+            - bus-name
+            - dev-name
+            - sb-index
+            - sb-pool-index
+        reply: &sb-pool-get-reply
+          value: 15
+          attributes: *sb-pool-id-attrs
+      dump:
+        reply: *sb-pool-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: sb-port-pool-get
+      doc: Get shared buffer port-pool combinations and threshold.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          value: 19
+          attributes: &sb-port-pool-id-attrs
+            - bus-name
+            - dev-name
+            - port-index
+            - sb-index
+            - sb-pool-index
+        reply: &sb-port-pool-get-reply
+          value: 19
+          attributes: *sb-port-pool-id-attrs
+      dump:
+        reply: *sb-port-pool-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: sb-tc-pool-bind-get
+      doc: Get shared buffer port-TC to pool bindings and threshold.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          value: 23
+          attributes: &sb-tc-pool-bind-id-attrs
+            - bus-name
+            - dev-name
+            - port-index
+            - sb-index
+            - sb-pool-type
+            - sb-tc-index
+        reply: &sb-tc-pool-bind-get-reply
+          value: 23
+          attributes: *sb-tc-pool-bind-id-attrs
+      dump:
+        reply: *sb-tc-pool-bind-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: param-get
+      doc: Get param instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          value: 38
+          attributes: &param-id-attrs
+            - bus-name
+            - dev-name
+            - param-name
+        reply: &param-get-reply
+          value: 38
+          attributes: *param-id-attrs
+      dump:
+        reply: *param-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: region-get
+      doc: Get region instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit-port-optional
+        post: devlink-nl-post-doit
+        request:
+          value: 42
+          attributes: &region-id-attrs
+            - bus-name
+            - dev-name
+            - port-index
+            - region-name
+        reply: &region-get-reply
+          value: 42
+          attributes: *region-id-attrs
+      dump:
+        reply: *region-get-reply
+
       # TODO: fill in the operations in between
 
     -
@@ -216,3 +488,173 @@ operations:
             - info-version-stored
       dump:
         reply: *info-get-reply
+
+    -
+      name: health-reporter-get
+      doc: Get health reporter instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit-port-optional
+        post: devlink-nl-post-doit
+        request:
+          attributes: &health-reporter-id-attrs
+            - bus-name
+            - dev-name
+            - port-index
+            - health-reporter-name
+        reply: &health-reporter-get-reply
+          attributes: *health-reporter-id-attrs
+      dump:
+        reply: *health-reporter-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: trap-get
+      doc: Get trap instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          value: 61
+          attributes: &trap-id-attrs
+            - bus-name
+            - dev-name
+            - trap-name
+        reply: &trap-get-reply
+          value: 61
+          attributes: *trap-id-attrs
+      dump:
+        reply: *trap-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: trap-group-get
+      doc: Get trap group instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          value: 65
+          attributes: &trap-group-id-attrs
+            - bus-name
+            - dev-name
+            - trap-group-name
+        reply: &trap-group-get-reply
+          value: 65
+          attributes: *trap-group-id-attrs
+      dump:
+        reply: *trap-group-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: trap-policer-get
+      doc: Get trap policer instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          value: 69
+          attributes: &trap-policer-id-attrs
+            - bus-name
+            - dev-name
+            - trap-policer-id
+        reply: &trap-policer-get-reply
+          value: 69
+          attributes: *trap-policer-id-attrs
+      dump:
+        reply: *trap-policer-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: rate-get
+      doc: Get rate instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          value: 74
+          attributes: &rate-id-attrs
+            - bus-name
+            - dev-name
+            - port-index
+            - rate-node-name
+        reply: &rate-get-reply
+          value: 74
+          attributes: *rate-id-attrs
+      dump:
+        reply: *rate-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: linecard-get
+      doc: Get line card instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          value: 78
+          attributes: &linecard-id-attrs
+            - bus-name
+            - dev-name
+            - linecard-index
+        reply: &linecard-get-reply
+          value: 78
+          attributes: *linecard-id-attrs
+      dump:
+        reply: *linecard-get-reply
+
+      # TODO: fill in the operations in between
+
+    -
+      name: selftests-get
+      doc: Get device selftest instances.
+      attribute-set: devlink
+      dont-validate:
+        - strict
+        - dump
+
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          value: 82
+          attributes: *dev-id-attrs
+        reply: &selftests-get-reply
+          value: 82
+          attributes: *dev-id-attrs
+      dump:
+        reply: *selftests-get-reply
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
index 32d8cbed0c307..e384b91b2e3ba 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -16,14 +16,120 @@ static const struct nla_policy devlink_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1]
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_PORT_GET - do */
+static const struct nla_policy devlink_port_get_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_SB_GET - do */
+static const struct nla_policy devlink_sb_get_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_SB_POOL_GET - do */
+static const struct nla_policy devlink_sb_pool_get_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, },
+};
+
+/* DEVLINK_CMD_SB_PORT_POOL_GET - do */
+static const struct nla_policy devlink_sb_port_pool_get_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, },
+};
+
+/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
+static const struct nla_policy devlink_sb_tc_pool_bind_get_nl_policy[DEVLINK_ATTR_SB_TC_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_SB_POOL_TYPE] = NLA_POLICY_MAX(NLA_U8, 1),
+	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16, },
+};
+
+/* DEVLINK_CMD_PARAM_GET - do */
+static const struct nla_policy devlink_param_get_nl_policy[DEVLINK_ATTR_PARAM_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_REGION_GET - do */
+static const struct nla_policy devlink_region_get_nl_policy[DEVLINK_ATTR_REGION_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_INFO_GET - do */
 static const struct nla_policy devlink_info_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */
+static const struct nla_policy devlink_health_reporter_get_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_TRAP_GET - do */
+static const struct nla_policy devlink_trap_get_nl_policy[DEVLINK_ATTR_TRAP_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_TRAP_GROUP_GET - do */
+static const struct nla_policy devlink_trap_group_get_nl_policy[DEVLINK_ATTR_TRAP_GROUP_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_TRAP_POLICER_GET - do */
+static const struct nla_policy devlink_trap_policer_get_nl_policy[DEVLINK_ATTR_TRAP_POLICER_ID + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_RATE_GET - do */
+static const struct nla_policy devlink_rate_get_nl_policy[DEVLINK_ATTR_RATE_NODE_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_LINECARD_GET - do */
+static const struct nla_policy devlink_linecard_get_nl_policy[DEVLINK_ATTR_LINECARD_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_SELFTESTS_GET - do */
+static const struct nla_policy devlink_selftests_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* Ops table for devlink */
-const struct genl_split_ops devlink_nl_ops[4] = {
+const struct genl_split_ops devlink_nl_ops[32] = {
 	{
 		.cmd		= DEVLINK_CMD_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -40,6 +146,118 @@ const struct genl_split_ops devlink_nl_ops[4] = {
 		.dumpit		= devlink_nl_get_dumpit,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_PORT_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_port_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_port_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PORT_INDEX,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_PORT_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_port_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SB_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_sb_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_sb_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_SB_INDEX,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SB_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_sb_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SB_POOL_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_sb_pool_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_sb_pool_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_SB_POOL_INDEX,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SB_POOL_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_sb_pool_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SB_PORT_POOL_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_sb_port_pool_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_sb_port_pool_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_SB_POOL_INDEX,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SB_PORT_POOL_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_sb_port_pool_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SB_TC_POOL_BIND_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_sb_tc_pool_bind_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_sb_tc_pool_bind_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_SB_TC_INDEX,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SB_TC_POOL_BIND_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_sb_tc_pool_bind_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_PARAM_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_param_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_param_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PARAM_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_PARAM_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_param_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_REGION_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port_optional,
+		.doit		= devlink_nl_region_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_region_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_REGION_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_REGION_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_region_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
 	{
 		.cmd		= DEVLINK_CMD_INFO_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -56,4 +274,116 @@ const struct genl_split_ops devlink_nl_ops[4] = {
 		.dumpit		= devlink_nl_info_get_dumpit,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_HEALTH_REPORTER_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port_optional,
+		.doit		= devlink_nl_health_reporter_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_health_reporter_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_HEALTH_REPORTER_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_HEALTH_REPORTER_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_health_reporter_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_TRAP_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_trap_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_trap_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_TRAP_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_TRAP_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_trap_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_TRAP_GROUP_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_trap_group_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_trap_group_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_TRAP_GROUP_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_TRAP_GROUP_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_trap_group_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_TRAP_POLICER_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_trap_policer_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_trap_policer_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_TRAP_POLICER_ID,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_TRAP_POLICER_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_trap_policer_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_RATE_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_rate_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_rate_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_RATE_NODE_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_RATE_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_rate_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_LINECARD_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_linecard_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_linecard_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_LINECARD_INDEX,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_LINECARD_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_linecard_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SELFTESTS_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_selftests_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_selftests_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SELFTESTS_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.dumpit		= devlink_nl_selftests_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
 };
diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h
index 11980e04a7186..f8bbc93e39be7 100644
--- a/net/devlink/netlink_gen.h
+++ b/net/devlink/netlink_gen.h
@@ -12,18 +12,68 @@
 #include <uapi/linux/devlink.h>
 
 /* Ops table for devlink */
-extern const struct genl_split_ops devlink_nl_ops[4];
+extern const struct genl_split_ops devlink_nl_ops[32];
 
 int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 			struct genl_info *info);
+int devlink_nl_pre_doit_port(const struct genl_split_ops *ops,
+			     struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
+				      struct sk_buff *skb,
+				      struct genl_info *info);
 void
 devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 		     struct genl_info *info);
 
 int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb);
+int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb);
+int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb);
+int devlink_nl_param_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_param_get_dumpit(struct sk_buff *skb,
+				struct netlink_callback *cb);
+int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb);
 int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_info_get_dumpit(struct sk_buff *skb,
 			       struct netlink_callback *cb);
+int devlink_nl_health_reporter_get_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb);
+int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb);
+int devlink_nl_trap_policer_get_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb);
+int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb);
+int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_selftests_get_dumpit(struct sk_buff *skb,
+				    struct netlink_callback *cb);
 
 #endif /* _LINUX_DEVLINK_GEN_H */
diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c
index 8492789433b9e..e9ab98b5ffe32 100644
--- a/tools/net/ynl/generated/devlink-user.c
+++ b/tools/net/ynl/generated/devlink-user.c
@@ -15,7 +15,21 @@
 /* Enums */
 static const char * const devlink_op_strmap[] = {
 	[3] = "get",
+	[7] = "port-get",
+	[DEVLINK_CMD_SB_GET] = "sb-get",
+	[DEVLINK_CMD_SB_POOL_GET] = "sb-pool-get",
+	[DEVLINK_CMD_SB_PORT_POOL_GET] = "sb-port-pool-get",
+	[DEVLINK_CMD_SB_TC_POOL_BIND_GET] = "sb-tc-pool-bind-get",
+	[DEVLINK_CMD_PARAM_GET] = "param-get",
+	[DEVLINK_CMD_REGION_GET] = "region-get",
 	[DEVLINK_CMD_INFO_GET] = "info-get",
+	[DEVLINK_CMD_HEALTH_REPORTER_GET] = "health-reporter-get",
+	[DEVLINK_CMD_TRAP_GET] = "trap-get",
+	[DEVLINK_CMD_TRAP_GROUP_GET] = "trap-group-get",
+	[DEVLINK_CMD_TRAP_POLICER_GET] = "trap-policer-get",
+	[DEVLINK_CMD_RATE_GET] = "rate-get",
+	[DEVLINK_CMD_LINECARD_GET] = "linecard-get",
+	[DEVLINK_CMD_SELFTESTS_GET] = "selftests-get",
 };
 
 const char *devlink_op_str(int op)
@@ -25,6 +39,18 @@ const char *devlink_op_str(int op)
 	return devlink_op_strmap[op];
 }
 
+static const char * const devlink_sb_pool_type_strmap[] = {
+	[0] = "ingress",
+	[1] = "egress",
+};
+
+const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_sb_pool_type_strmap))
+		return NULL;
+	return devlink_sb_pool_type_strmap[value];
+}
+
 /* Policies */
 struct ynl_policy_attr devlink_dl_info_version_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, },
@@ -88,6 +114,12 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .name = "bus-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_DEV_NAME] = { .name = "dev-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_PORT_INDEX] = { .name = "port-index", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_SB_INDEX] = { .name = "sb-index", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_SB_POOL_INDEX] = { .name = "sb-pool-index", .type = YNL_PT_U16, },
+	[DEVLINK_ATTR_SB_POOL_TYPE] = { .name = "sb-pool-type", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_SB_TC_INDEX] = { .name = "sb-tc-index", .type = YNL_PT_U16, },
+	[DEVLINK_ATTR_PARAM_NAME] = { .name = "param-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_REGION_NAME] = { .name = "region-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_INFO_DRIVER_NAME] = { .name = "info-driver-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_INFO_SERIAL_NUMBER] = { .name = "info-serial-number", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_INFO_VERSION_FIXED] = { .name = "info-version-fixed", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, },
@@ -95,7 +127,11 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_INFO_VERSION_STORED] = { .name = "info-version-stored", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, },
 	[DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .name = "health-reporter-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_TRAP_NAME] = { .name = "trap-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .name = "trap-group-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_RELOAD_FAILED] = { .name = "reload-failed", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_TRAP_POLICER_ID] = { .name = "trap-policer-id", .type = YNL_PT_U32, },
 	[DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, },
 	[DEVLINK_ATTR_DEV_STATS] = { .name = "dev-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_dev_stats_nest, },
 	[DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, },
@@ -105,6 +141,8 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, },
 	[DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, },
 	[DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, },
+	[DEVLINK_ATTR_RATE_NODE_NAME] = { .name = "rate-node-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_LINECARD_INDEX] = { .name = "linecard-index", .type = YNL_PT_U32, },
 };
 
 struct ynl_policy_nest devlink_nest = {
@@ -531,55 +569,29 @@ free_list:
 	return NULL;
 }
 
-/* ============== DEVLINK_CMD_INFO_GET ============== */
-/* DEVLINK_CMD_INFO_GET - do */
-void devlink_info_get_req_free(struct devlink_info_get_req *req)
+/* ============== DEVLINK_CMD_PORT_GET ============== */
+/* DEVLINK_CMD_PORT_GET - do */
+void devlink_port_get_req_free(struct devlink_port_get_req *req)
 {
 	free(req->bus_name);
 	free(req->dev_name);
 	free(req);
 }
 
-void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp)
+void devlink_port_get_rsp_free(struct devlink_port_get_rsp *rsp)
 {
-	unsigned int i;
-
 	free(rsp->bus_name);
 	free(rsp->dev_name);
-	free(rsp->info_driver_name);
-	free(rsp->info_serial_number);
-	for (i = 0; i < rsp->n_info_version_fixed; i++)
-		devlink_dl_info_version_free(&rsp->info_version_fixed[i]);
-	free(rsp->info_version_fixed);
-	for (i = 0; i < rsp->n_info_version_running; i++)
-		devlink_dl_info_version_free(&rsp->info_version_running[i]);
-	free(rsp->info_version_running);
-	for (i = 0; i < rsp->n_info_version_stored; i++)
-		devlink_dl_info_version_free(&rsp->info_version_stored[i]);
-	free(rsp->info_version_stored);
 	free(rsp);
 }
 
-int devlink_info_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+int devlink_port_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 {
-	unsigned int n_info_version_running = 0;
-	unsigned int n_info_version_stored = 0;
-	unsigned int n_info_version_fixed = 0;
 	struct ynl_parse_arg *yarg = data;
-	struct devlink_info_get_rsp *dst;
+	struct devlink_port_get_rsp *dst;
 	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
 
 	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	if (dst->info_version_fixed)
-		return ynl_error_parse(yarg, "attribute already present (devlink.info-version-fixed)");
-	if (dst->info_version_running)
-		return ynl_error_parse(yarg, "attribute already present (devlink.info-version-running)");
-	if (dst->info_version_stored)
-		return ynl_error_parse(yarg, "attribute already present (devlink.info-version-stored)");
 
 	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
 		unsigned int type = mnl_attr_get_type(attr);
@@ -606,92 +618,205 @@ int devlink_info_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 			dst->dev_name = malloc(len + 1);
 			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
 			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_INFO_DRIVER_NAME) {
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_port_get_rsp *
+devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_port_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_port_get_rsp_parse;
+	yrs.rsp_cmd = 7;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_port_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_PORT_GET - dump */
+int devlink_port_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_port_get_rsp_dump *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
 			unsigned int len;
 
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
 
 			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.info_driver_name_len = len;
-			dst->info_driver_name = malloc(len + 1);
-			memcpy(dst->info_driver_name, mnl_attr_get_str(attr), len);
-			dst->info_driver_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_INFO_SERIAL_NUMBER) {
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
 			unsigned int len;
 
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
 
 			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.info_serial_number_len = len;
-			dst->info_serial_number = malloc(len + 1);
-			memcpy(dst->info_serial_number, mnl_attr_get_str(attr), len);
-			dst->info_serial_number[len] = 0;
-		} else if (type == DEVLINK_ATTR_INFO_VERSION_FIXED) {
-			n_info_version_fixed++;
-		} else if (type == DEVLINK_ATTR_INFO_VERSION_RUNNING) {
-			n_info_version_running++;
-		} else if (type == DEVLINK_ATTR_INFO_VERSION_STORED) {
-			n_info_version_stored++;
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
 		}
 	}
 
-	if (n_info_version_fixed) {
-		dst->info_version_fixed = calloc(n_info_version_fixed, sizeof(*dst->info_version_fixed));
-		dst->n_info_version_fixed = n_info_version_fixed;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_info_version_nest;
-		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_FIXED) {
-				parg.data = &dst->info_version_fixed[i];
-				if (devlink_dl_info_version_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-	if (n_info_version_running) {
-		dst->info_version_running = calloc(n_info_version_running, sizeof(*dst->info_version_running));
-		dst->n_info_version_running = n_info_version_running;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_info_version_nest;
-		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_RUNNING) {
-				parg.data = &dst->info_version_running[i];
-				if (devlink_dl_info_version_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
+	return MNL_CB_OK;
+}
+
+void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp)
+{
+	struct devlink_port_get_rsp_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
 	}
-	if (n_info_version_stored) {
-		dst->info_version_stored = calloc(n_info_version_stored, sizeof(*dst->info_version_stored));
-		dst->n_info_version_stored = n_info_version_stored;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_info_version_nest;
-		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_STORED) {
-				parg.data = &dst->info_version_stored[i];
-				if (devlink_dl_info_version_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
+}
+
+struct devlink_port_get_rsp_list *devlink_port_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_port_get_rsp_list);
+	yds.cb = devlink_port_get_rsp_dump_parse;
+	yds.rsp_cmd = 7;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_port_get_rsp_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_SB_GET ============== */
+/* DEVLINK_CMD_SB_GET - do */
+void devlink_sb_get_req_free(struct devlink_sb_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_sb_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct ynl_parse_arg *yarg = data;
+	struct devlink_sb_get_rsp *dst;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_SB_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_index = 1;
+			dst->sb_index = mnl_attr_get_u32(attr);
 		}
 	}
 
 	return MNL_CB_OK;
 }
 
-struct devlink_info_get_rsp *
-devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req)
+struct devlink_sb_get_rsp *
+devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req)
 {
 	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_info_get_rsp *rsp;
+	struct devlink_sb_get_rsp *rsp;
 	struct nlmsghdr *nlh;
 	int err;
 
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_INFO_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1);
 	ys->req_policy = &devlink_nest;
 	yrs.yarg.rsp_policy = &devlink_nest;
 
@@ -699,11 +824,13 @@ devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
 	if (req->_present.dev_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
 
 	rsp = calloc(1, sizeof(*rsp));
 	yrs.yarg.data = rsp;
-	yrs.cb = devlink_info_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_INFO_GET;
+	yrs.cb = devlink_sb_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_SB_GET;
 
 	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
@@ -712,51 +839,38 @@ devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req)
 	return rsp;
 
 err_free:
-	devlink_info_get_rsp_free(rsp);
+	devlink_sb_get_rsp_free(rsp);
 	return NULL;
 }
 
-/* DEVLINK_CMD_INFO_GET - dump */
-void devlink_info_get_list_free(struct devlink_info_get_list *rsp)
+/* DEVLINK_CMD_SB_GET - dump */
+void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp)
 {
-	struct devlink_info_get_list *next = rsp;
+	struct devlink_sb_get_list *next = rsp;
 
 	while ((void *)next != YNL_LIST_END) {
-		unsigned int i;
-
 		rsp = next;
 		next = rsp->next;
 
 		free(rsp->obj.bus_name);
 		free(rsp->obj.dev_name);
-		free(rsp->obj.info_driver_name);
-		free(rsp->obj.info_serial_number);
-		for (i = 0; i < rsp->obj.n_info_version_fixed; i++)
-			devlink_dl_info_version_free(&rsp->obj.info_version_fixed[i]);
-		free(rsp->obj.info_version_fixed);
-		for (i = 0; i < rsp->obj.n_info_version_running; i++)
-			devlink_dl_info_version_free(&rsp->obj.info_version_running[i]);
-		free(rsp->obj.info_version_running);
-		for (i = 0; i < rsp->obj.n_info_version_stored; i++)
-			devlink_dl_info_version_free(&rsp->obj.info_version_stored[i]);
-		free(rsp->obj.info_version_stored);
 		free(rsp);
 	}
 }
 
-struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys)
+struct devlink_sb_get_list *devlink_sb_get_dump(struct ynl_sock *ys)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
 	int err;
 
 	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_info_get_list);
-	yds.cb = devlink_info_get_rsp_parse;
-	yds.rsp_cmd = DEVLINK_CMD_INFO_GET;
+	yds.alloc_sz = sizeof(struct devlink_sb_get_list);
+	yds.cb = devlink_sb_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_SB_GET;
 	yds.rsp_policy = &devlink_nest;
 
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_INFO_GET, 1);
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -765,7 +879,2002 @@ struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys)
 	return yds.first;
 
 free_list:
-	devlink_info_get_list_free(yds.first);
+	devlink_sb_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_SB_POOL_GET ============== */
+/* DEVLINK_CMD_SB_POOL_GET - do */
+void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_sb_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_sb_pool_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_SB_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_index = 1;
+			dst->sb_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_SB_POOL_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_pool_index = 1;
+			dst->sb_pool_index = mnl_attr_get_u16(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_sb_pool_get_rsp *
+devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_sb_pool_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+	if (req->_present.sb_pool_index)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_sb_pool_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_SB_POOL_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_sb_pool_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_SB_POOL_GET - dump */
+void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp)
+{
+	struct devlink_sb_pool_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_sb_pool_get_list *devlink_sb_pool_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_sb_pool_get_list);
+	yds.cb = devlink_sb_pool_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_SB_POOL_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_sb_pool_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */
+/* DEVLINK_CMD_SB_PORT_POOL_GET - do */
+void
+devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void
+devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_sb_port_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_sb_port_pool_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_SB_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_index = 1;
+			dst->sb_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_SB_POOL_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_pool_index = 1;
+			dst->sb_pool_index = mnl_attr_get_u16(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_sb_port_pool_get_rsp *
+devlink_sb_port_pool_get(struct ynl_sock *ys,
+			 struct devlink_sb_port_pool_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_sb_port_pool_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+	if (req->_present.sb_pool_index)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_sb_port_pool_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_SB_PORT_POOL_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_sb_port_pool_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */
+void
+devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp)
+{
+	struct devlink_sb_port_pool_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_sb_port_pool_get_list *
+devlink_sb_port_pool_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_sb_port_pool_get_list);
+	yds.cb = devlink_sb_port_pool_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_SB_PORT_POOL_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_sb_port_pool_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */
+/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
+void
+devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void
+devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_sb_tc_pool_bind_get_rsp_parse(const struct nlmsghdr *nlh,
+					  void *data)
+{
+	struct devlink_sb_tc_pool_bind_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_SB_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_index = 1;
+			dst->sb_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_SB_POOL_TYPE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_pool_type = 1;
+			dst->sb_pool_type = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_SB_TC_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_tc_index = 1;
+			dst->sb_tc_index = mnl_attr_get_u16(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_sb_tc_pool_bind_get_rsp *
+devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
+			    struct devlink_sb_tc_pool_bind_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_sb_tc_pool_bind_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+	if (req->_present.sb_pool_type)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_TYPE, req->sb_pool_type);
+	if (req->_present.sb_tc_index)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_TC_INDEX, req->sb_tc_index);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_sb_tc_pool_bind_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_sb_tc_pool_bind_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */
+void
+devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp)
+{
+	struct devlink_sb_tc_pool_bind_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_sb_tc_pool_bind_get_list *
+devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_sb_tc_pool_bind_get_list);
+	yds.cb = devlink_sb_tc_pool_bind_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_sb_tc_pool_bind_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_PARAM_GET ============== */
+/* DEVLINK_CMD_PARAM_GET - do */
+void devlink_param_get_req_free(struct devlink_param_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->param_name);
+	free(req);
+}
+
+void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp->param_name);
+	free(rsp);
+}
+
+int devlink_param_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_param_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PARAM_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.param_name_len = len;
+			dst->param_name = malloc(len + 1);
+			memcpy(dst->param_name, mnl_attr_get_str(attr), len);
+			dst->param_name[len] = 0;
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_param_get_rsp *
+devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_param_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.param_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_PARAM_NAME, req->param_name);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_param_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_PARAM_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_param_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_PARAM_GET - dump */
+void devlink_param_get_list_free(struct devlink_param_get_list *rsp)
+{
+	struct devlink_param_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp->obj.param_name);
+		free(rsp);
+	}
+}
+
+struct devlink_param_get_list *devlink_param_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_param_get_list);
+	yds.cb = devlink_param_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_PARAM_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_param_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_REGION_GET ============== */
+/* DEVLINK_CMD_REGION_GET - do */
+void devlink_region_get_req_free(struct devlink_region_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->region_name);
+	free(req);
+}
+
+void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp->region_name);
+	free(rsp);
+}
+
+int devlink_region_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_region_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_REGION_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.region_name_len = len;
+			dst->region_name = malloc(len + 1);
+			memcpy(dst->region_name, mnl_attr_get_str(attr), len);
+			dst->region_name[len] = 0;
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_region_get_rsp *
+devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_region_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.region_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_region_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_REGION_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_region_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_REGION_GET - dump */
+void devlink_region_get_list_free(struct devlink_region_get_list *rsp)
+{
+	struct devlink_region_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp->obj.region_name);
+		free(rsp);
+	}
+}
+
+struct devlink_region_get_list *devlink_region_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_region_get_list);
+	yds.cb = devlink_region_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_REGION_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_region_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_INFO_GET ============== */
+/* DEVLINK_CMD_INFO_GET - do */
+void devlink_info_get_req_free(struct devlink_info_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp)
+{
+	unsigned int i;
+
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp->info_driver_name);
+	free(rsp->info_serial_number);
+	for (i = 0; i < rsp->n_info_version_fixed; i++)
+		devlink_dl_info_version_free(&rsp->info_version_fixed[i]);
+	free(rsp->info_version_fixed);
+	for (i = 0; i < rsp->n_info_version_running; i++)
+		devlink_dl_info_version_free(&rsp->info_version_running[i]);
+	free(rsp->info_version_running);
+	for (i = 0; i < rsp->n_info_version_stored; i++)
+		devlink_dl_info_version_free(&rsp->info_version_stored[i]);
+	free(rsp->info_version_stored);
+	free(rsp);
+}
+
+int devlink_info_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	unsigned int n_info_version_running = 0;
+	unsigned int n_info_version_stored = 0;
+	unsigned int n_info_version_fixed = 0;
+	struct ynl_parse_arg *yarg = data;
+	struct devlink_info_get_rsp *dst;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	dst = yarg->data;
+	parg.ys = yarg->ys;
+
+	if (dst->info_version_fixed)
+		return ynl_error_parse(yarg, "attribute already present (devlink.info-version-fixed)");
+	if (dst->info_version_running)
+		return ynl_error_parse(yarg, "attribute already present (devlink.info-version-running)");
+	if (dst->info_version_stored)
+		return ynl_error_parse(yarg, "attribute already present (devlink.info-version-stored)");
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_INFO_DRIVER_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.info_driver_name_len = len;
+			dst->info_driver_name = malloc(len + 1);
+			memcpy(dst->info_driver_name, mnl_attr_get_str(attr), len);
+			dst->info_driver_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_INFO_SERIAL_NUMBER) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.info_serial_number_len = len;
+			dst->info_serial_number = malloc(len + 1);
+			memcpy(dst->info_serial_number, mnl_attr_get_str(attr), len);
+			dst->info_serial_number[len] = 0;
+		} else if (type == DEVLINK_ATTR_INFO_VERSION_FIXED) {
+			n_info_version_fixed++;
+		} else if (type == DEVLINK_ATTR_INFO_VERSION_RUNNING) {
+			n_info_version_running++;
+		} else if (type == DEVLINK_ATTR_INFO_VERSION_STORED) {
+			n_info_version_stored++;
+		}
+	}
+
+	if (n_info_version_fixed) {
+		dst->info_version_fixed = calloc(n_info_version_fixed, sizeof(*dst->info_version_fixed));
+		dst->n_info_version_fixed = n_info_version_fixed;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_info_version_nest;
+		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_FIXED) {
+				parg.data = &dst->info_version_fixed[i];
+				if (devlink_dl_info_version_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+	if (n_info_version_running) {
+		dst->info_version_running = calloc(n_info_version_running, sizeof(*dst->info_version_running));
+		dst->n_info_version_running = n_info_version_running;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_info_version_nest;
+		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_RUNNING) {
+				parg.data = &dst->info_version_running[i];
+				if (devlink_dl_info_version_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+	if (n_info_version_stored) {
+		dst->info_version_stored = calloc(n_info_version_stored, sizeof(*dst->info_version_stored));
+		dst->n_info_version_stored = n_info_version_stored;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_info_version_nest;
+		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_STORED) {
+				parg.data = &dst->info_version_stored[i];
+				if (devlink_dl_info_version_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_info_get_rsp *
+devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_info_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_INFO_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_info_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_INFO_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_info_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_INFO_GET - dump */
+void devlink_info_get_list_free(struct devlink_info_get_list *rsp)
+{
+	struct devlink_info_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		unsigned int i;
+
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp->obj.info_driver_name);
+		free(rsp->obj.info_serial_number);
+		for (i = 0; i < rsp->obj.n_info_version_fixed; i++)
+			devlink_dl_info_version_free(&rsp->obj.info_version_fixed[i]);
+		free(rsp->obj.info_version_fixed);
+		for (i = 0; i < rsp->obj.n_info_version_running; i++)
+			devlink_dl_info_version_free(&rsp->obj.info_version_running[i]);
+		free(rsp->obj.info_version_running);
+		for (i = 0; i < rsp->obj.n_info_version_stored; i++)
+			devlink_dl_info_version_free(&rsp->obj.info_version_stored[i]);
+		free(rsp->obj.info_version_stored);
+		free(rsp);
+	}
+}
+
+struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_info_get_list);
+	yds.cb = devlink_info_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_INFO_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_INFO_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_info_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_GET ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */
+void
+devlink_health_reporter_get_req_free(struct devlink_health_reporter_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->health_reporter_name);
+	free(req);
+}
+
+void
+devlink_health_reporter_get_rsp_free(struct devlink_health_reporter_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp->health_reporter_name);
+	free(rsp);
+}
+
+int devlink_health_reporter_get_rsp_parse(const struct nlmsghdr *nlh,
+					  void *data)
+{
+	struct devlink_health_reporter_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_HEALTH_REPORTER_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.health_reporter_name_len = len;
+			dst->health_reporter_name = malloc(len + 1);
+			memcpy(dst->health_reporter_name, mnl_attr_get_str(attr), len);
+			dst->health_reporter_name[len] = 0;
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_health_reporter_get_rsp *
+devlink_health_reporter_get(struct ynl_sock *ys,
+			    struct devlink_health_reporter_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_health_reporter_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.health_reporter_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_health_reporter_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_health_reporter_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */
+void
+devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp)
+{
+	struct devlink_health_reporter_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp->obj.health_reporter_name);
+		free(rsp);
+	}
+}
+
+struct devlink_health_reporter_get_list *
+devlink_health_reporter_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_health_reporter_get_list);
+	yds.cb = devlink_health_reporter_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_health_reporter_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_TRAP_GET ============== */
+/* DEVLINK_CMD_TRAP_GET - do */
+void devlink_trap_get_req_free(struct devlink_trap_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->trap_name);
+	free(req);
+}
+
+void devlink_trap_get_rsp_free(struct devlink_trap_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp->trap_name);
+	free(rsp);
+}
+
+int devlink_trap_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct ynl_parse_arg *yarg = data;
+	struct devlink_trap_get_rsp *dst;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_TRAP_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.trap_name_len = len;
+			dst->trap_name = malloc(len + 1);
+			memcpy(dst->trap_name, mnl_attr_get_str(attr), len);
+			dst->trap_name[len] = 0;
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_trap_get_rsp *
+devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_trap_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.trap_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_NAME, req->trap_name);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_trap_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_TRAP_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_trap_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_TRAP_GET - dump */
+void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp)
+{
+	struct devlink_trap_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp->obj.trap_name);
+		free(rsp);
+	}
+}
+
+struct devlink_trap_get_list *devlink_trap_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_trap_get_list);
+	yds.cb = devlink_trap_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_TRAP_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_trap_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */
+/* DEVLINK_CMD_TRAP_GROUP_GET - do */
+void devlink_trap_group_get_req_free(struct devlink_trap_group_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->trap_group_name);
+	free(req);
+}
+
+void devlink_trap_group_get_rsp_free(struct devlink_trap_group_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp->trap_group_name);
+	free(rsp);
+}
+
+int devlink_trap_group_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_trap_group_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_TRAP_GROUP_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.trap_group_name_len = len;
+			dst->trap_group_name = malloc(len + 1);
+			memcpy(dst->trap_group_name, mnl_attr_get_str(attr), len);
+			dst->trap_group_name[len] = 0;
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_trap_group_get_rsp *
+devlink_trap_group_get(struct ynl_sock *ys,
+		       struct devlink_trap_group_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_trap_group_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.trap_group_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_GROUP_NAME, req->trap_group_name);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_trap_group_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_TRAP_GROUP_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_trap_group_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_TRAP_GROUP_GET - dump */
+void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp)
+{
+	struct devlink_trap_group_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp->obj.trap_group_name);
+		free(rsp);
+	}
+}
+
+struct devlink_trap_group_get_list *
+devlink_trap_group_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_trap_group_get_list);
+	yds.cb = devlink_trap_group_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_TRAP_GROUP_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_trap_group_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */
+/* DEVLINK_CMD_TRAP_POLICER_GET - do */
+void
+devlink_trap_policer_get_req_free(struct devlink_trap_policer_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void
+devlink_trap_policer_get_rsp_free(struct devlink_trap_policer_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_trap_policer_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_trap_policer_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_TRAP_POLICER_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.trap_policer_id = 1;
+			dst->trap_policer_id = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_trap_policer_get_rsp *
+devlink_trap_policer_get(struct ynl_sock *ys,
+			 struct devlink_trap_policer_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_trap_policer_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.trap_policer_id)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_trap_policer_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_TRAP_POLICER_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_trap_policer_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_TRAP_POLICER_GET - dump */
+void
+devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp)
+{
+	struct devlink_trap_policer_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_trap_policer_get_list *
+devlink_trap_policer_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_trap_policer_get_list);
+	yds.cb = devlink_trap_policer_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_TRAP_POLICER_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_trap_policer_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_RATE_GET ============== */
+/* DEVLINK_CMD_RATE_GET - do */
+void devlink_rate_get_req_free(struct devlink_rate_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->rate_node_name);
+	free(req);
+}
+
+void devlink_rate_get_rsp_free(struct devlink_rate_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp->rate_node_name);
+	free(rsp);
+}
+
+int devlink_rate_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct ynl_parse_arg *yarg = data;
+	struct devlink_rate_get_rsp *dst;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_RATE_NODE_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.rate_node_name_len = len;
+			dst->rate_node_name = malloc(len + 1);
+			memcpy(dst->rate_node_name, mnl_attr_get_str(attr), len);
+			dst->rate_node_name[len] = 0;
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_rate_get_rsp *
+devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_rate_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.rate_node_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_rate_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_RATE_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_rate_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_RATE_GET - dump */
+void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp)
+{
+	struct devlink_rate_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp->obj.rate_node_name);
+		free(rsp);
+	}
+}
+
+struct devlink_rate_get_list *devlink_rate_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_rate_get_list);
+	yds.cb = devlink_rate_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_RATE_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_rate_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_LINECARD_GET ============== */
+/* DEVLINK_CMD_LINECARD_GET - do */
+void devlink_linecard_get_req_free(struct devlink_linecard_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_linecard_get_rsp_free(struct devlink_linecard_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_linecard_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_linecard_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_LINECARD_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.linecard_index = 1;
+			dst->linecard_index = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_linecard_get_rsp *
+devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_linecard_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.linecard_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_LINECARD_INDEX, req->linecard_index);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_linecard_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_LINECARD_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_linecard_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_LINECARD_GET - dump */
+void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp)
+{
+	struct devlink_linecard_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_linecard_get_list *
+devlink_linecard_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_linecard_get_list);
+	yds.cb = devlink_linecard_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_LINECARD_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_linecard_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_SELFTESTS_GET ============== */
+/* DEVLINK_CMD_SELFTESTS_GET - do */
+void devlink_selftests_get_req_free(struct devlink_selftests_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_selftests_get_rsp_free(struct devlink_selftests_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_selftests_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_selftests_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_selftests_get_rsp *
+devlink_selftests_get(struct ynl_sock *ys,
+		      struct devlink_selftests_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_selftests_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_selftests_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_SELFTESTS_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_selftests_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_SELFTESTS_GET - dump */
+void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp)
+{
+	struct devlink_selftests_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_selftests_get_list *
+devlink_selftests_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_selftests_get_list);
+	yds.cb = devlink_selftests_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_SELFTESTS_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_selftests_get_list_free(yds.first);
 	return NULL;
 }
 
diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h
index af65e2f2f5295..f6ec5b6e5d26e 100644
--- a/tools/net/ynl/generated/devlink-user.h
+++ b/tools/net/ynl/generated/devlink-user.h
@@ -17,6 +17,7 @@ extern const struct ynl_family ynl_devlink_family;
 
 /* Enums */
 const char *devlink_op_str(int op);
+const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value);
 
 /* Common nested types */
 struct devlink_dl_info_version {
@@ -140,6 +141,659 @@ void devlink_get_list_free(struct devlink_get_list *rsp);
 
 struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys);
 
+/* ============== DEVLINK_CMD_PORT_GET ============== */
+/* DEVLINK_CMD_PORT_GET - do */
+struct devlink_port_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+};
+
+static inline struct devlink_port_get_req *devlink_port_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_port_get_req));
+}
+void devlink_port_get_req_free(struct devlink_port_get_req *req);
+
+static inline void
+devlink_port_get_req_set_bus_name(struct devlink_port_get_req *req,
+				  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_port_get_req_set_dev_name(struct devlink_port_get_req *req,
+				  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_port_get_req_set_port_index(struct devlink_port_get_req *req,
+				    __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+
+struct devlink_port_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+};
+
+void devlink_port_get_rsp_free(struct devlink_port_get_rsp *rsp);
+
+/*
+ * Get devlink port instances.
+ */
+struct devlink_port_get_rsp *
+devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req);
+
+/* DEVLINK_CMD_PORT_GET - dump */
+struct devlink_port_get_rsp_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+};
+
+struct devlink_port_get_rsp_list {
+	struct devlink_port_get_rsp_list *next;
+	struct devlink_port_get_rsp_dump obj __attribute__ ((aligned (8)));
+};
+
+void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp);
+
+struct devlink_port_get_rsp_list *devlink_port_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_SB_GET ============== */
+/* DEVLINK_CMD_SB_GET - do */
+struct devlink_sb_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 sb_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 sb_index;
+};
+
+static inline struct devlink_sb_get_req *devlink_sb_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_get_req));
+}
+void devlink_sb_get_req_free(struct devlink_sb_get_req *req);
+
+static inline void
+devlink_sb_get_req_set_bus_name(struct devlink_sb_get_req *req,
+				const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_get_req_set_dev_name(struct devlink_sb_get_req *req,
+				const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_get_req_set_sb_index(struct devlink_sb_get_req *req, __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+
+struct devlink_sb_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 sb_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 sb_index;
+};
+
+void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp);
+
+/*
+ * Get shared buffer instances.
+ */
+struct devlink_sb_get_rsp *
+devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req);
+
+/* DEVLINK_CMD_SB_GET - dump */
+struct devlink_sb_get_list {
+	struct devlink_sb_get_list *next;
+	struct devlink_sb_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp);
+
+struct devlink_sb_get_list *devlink_sb_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_SB_POOL_GET ============== */
+/* DEVLINK_CMD_SB_POOL_GET - do */
+struct devlink_sb_pool_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 sb_index;
+	__u16 sb_pool_index;
+};
+
+static inline struct devlink_sb_pool_get_req *
+devlink_sb_pool_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_pool_get_req));
+}
+void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req);
+
+static inline void
+devlink_sb_pool_get_req_set_bus_name(struct devlink_sb_pool_get_req *req,
+				     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_pool_get_req_set_dev_name(struct devlink_sb_pool_get_req *req,
+				     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_pool_get_req_set_sb_index(struct devlink_sb_pool_get_req *req,
+				     __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+static inline void
+devlink_sb_pool_get_req_set_sb_pool_index(struct devlink_sb_pool_get_req *req,
+					  __u16 sb_pool_index)
+{
+	req->_present.sb_pool_index = 1;
+	req->sb_pool_index = sb_pool_index;
+}
+
+struct devlink_sb_pool_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 sb_index;
+	__u16 sb_pool_index;
+};
+
+void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp);
+
+/*
+ * Get shared buffer pool instances.
+ */
+struct devlink_sb_pool_get_rsp *
+devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req);
+
+/* DEVLINK_CMD_SB_POOL_GET - dump */
+struct devlink_sb_pool_get_list {
+	struct devlink_sb_pool_get_list *next;
+	struct devlink_sb_pool_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp);
+
+struct devlink_sb_pool_get_list *devlink_sb_pool_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */
+/* DEVLINK_CMD_SB_PORT_POOL_GET - do */
+struct devlink_sb_port_pool_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	__u32 sb_index;
+	__u16 sb_pool_index;
+};
+
+static inline struct devlink_sb_port_pool_get_req *
+devlink_sb_port_pool_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_port_pool_get_req));
+}
+void
+devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req);
+
+static inline void
+devlink_sb_port_pool_get_req_set_bus_name(struct devlink_sb_port_pool_get_req *req,
+					  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_port_pool_get_req_set_dev_name(struct devlink_sb_port_pool_get_req *req,
+					  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_port_pool_get_req_set_port_index(struct devlink_sb_port_pool_get_req *req,
+					    __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_sb_port_pool_get_req_set_sb_index(struct devlink_sb_port_pool_get_req *req,
+					  __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+static inline void
+devlink_sb_port_pool_get_req_set_sb_pool_index(struct devlink_sb_port_pool_get_req *req,
+					       __u16 sb_pool_index)
+{
+	req->_present.sb_pool_index = 1;
+	req->sb_pool_index = sb_pool_index;
+}
+
+struct devlink_sb_port_pool_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	__u32 sb_index;
+	__u16 sb_pool_index;
+};
+
+void
+devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp);
+
+/*
+ * Get shared buffer port-pool combinations and threshold.
+ */
+struct devlink_sb_port_pool_get_rsp *
+devlink_sb_port_pool_get(struct ynl_sock *ys,
+			 struct devlink_sb_port_pool_get_req *req);
+
+/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */
+struct devlink_sb_port_pool_get_list {
+	struct devlink_sb_port_pool_get_list *next;
+	struct devlink_sb_port_pool_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void
+devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp);
+
+struct devlink_sb_port_pool_get_list *
+devlink_sb_port_pool_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */
+/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
+struct devlink_sb_tc_pool_bind_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 sb_index:1;
+		__u32 sb_pool_type:1;
+		__u32 sb_tc_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	__u32 sb_index;
+	enum devlink_sb_pool_type sb_pool_type;
+	__u16 sb_tc_index;
+};
+
+static inline struct devlink_sb_tc_pool_bind_get_req *
+devlink_sb_tc_pool_bind_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req));
+}
+void
+devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req);
+
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_bus_name(struct devlink_sb_tc_pool_bind_get_req *req,
+					     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_dev_name(struct devlink_sb_tc_pool_bind_get_req *req,
+					     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_port_index(struct devlink_sb_tc_pool_bind_get_req *req,
+					       __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_sb_index(struct devlink_sb_tc_pool_bind_get_req *req,
+					     __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_sb_pool_type(struct devlink_sb_tc_pool_bind_get_req *req,
+						 enum devlink_sb_pool_type sb_pool_type)
+{
+	req->_present.sb_pool_type = 1;
+	req->sb_pool_type = sb_pool_type;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_sb_tc_index(struct devlink_sb_tc_pool_bind_get_req *req,
+						__u16 sb_tc_index)
+{
+	req->_present.sb_tc_index = 1;
+	req->sb_tc_index = sb_tc_index;
+}
+
+struct devlink_sb_tc_pool_bind_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 sb_index:1;
+		__u32 sb_pool_type:1;
+		__u32 sb_tc_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	__u32 sb_index;
+	enum devlink_sb_pool_type sb_pool_type;
+	__u16 sb_tc_index;
+};
+
+void
+devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp);
+
+/*
+ * Get shared buffer port-TC to pool bindings and threshold.
+ */
+struct devlink_sb_tc_pool_bind_get_rsp *
+devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
+			    struct devlink_sb_tc_pool_bind_get_req *req);
+
+/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */
+struct devlink_sb_tc_pool_bind_get_list {
+	struct devlink_sb_tc_pool_bind_get_list *next;
+	struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void
+devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp);
+
+struct devlink_sb_tc_pool_bind_get_list *
+devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_PARAM_GET ============== */
+/* DEVLINK_CMD_PARAM_GET - do */
+struct devlink_param_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 param_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *param_name;
+};
+
+static inline struct devlink_param_get_req *devlink_param_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_param_get_req));
+}
+void devlink_param_get_req_free(struct devlink_param_get_req *req);
+
+static inline void
+devlink_param_get_req_set_bus_name(struct devlink_param_get_req *req,
+				   const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_param_get_req_set_dev_name(struct devlink_param_get_req *req,
+				   const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_param_get_req_set_param_name(struct devlink_param_get_req *req,
+				     const char *param_name)
+{
+	free(req->param_name);
+	req->_present.param_name_len = strlen(param_name);
+	req->param_name = malloc(req->_present.param_name_len + 1);
+	memcpy(req->param_name, param_name, req->_present.param_name_len);
+	req->param_name[req->_present.param_name_len] = 0;
+}
+
+struct devlink_param_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 param_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *param_name;
+};
+
+void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp);
+
+/*
+ * Get param instances.
+ */
+struct devlink_param_get_rsp *
+devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req);
+
+/* DEVLINK_CMD_PARAM_GET - dump */
+struct devlink_param_get_list {
+	struct devlink_param_get_list *next;
+	struct devlink_param_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_param_get_list_free(struct devlink_param_get_list *rsp);
+
+struct devlink_param_get_list *devlink_param_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_REGION_GET ============== */
+/* DEVLINK_CMD_REGION_GET - do */
+struct devlink_region_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 region_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *region_name;
+};
+
+static inline struct devlink_region_get_req *devlink_region_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_region_get_req));
+}
+void devlink_region_get_req_free(struct devlink_region_get_req *req);
+
+static inline void
+devlink_region_get_req_set_bus_name(struct devlink_region_get_req *req,
+				    const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_region_get_req_set_dev_name(struct devlink_region_get_req *req,
+				    const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_region_get_req_set_port_index(struct devlink_region_get_req *req,
+				      __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_region_get_req_set_region_name(struct devlink_region_get_req *req,
+				       const char *region_name)
+{
+	free(req->region_name);
+	req->_present.region_name_len = strlen(region_name);
+	req->region_name = malloc(req->_present.region_name_len + 1);
+	memcpy(req->region_name, region_name, req->_present.region_name_len);
+	req->region_name[req->_present.region_name_len] = 0;
+}
+
+struct devlink_region_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 region_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *region_name;
+};
+
+void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp);
+
+/*
+ * Get region instances.
+ */
+struct devlink_region_get_rsp *
+devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req);
+
+/* DEVLINK_CMD_REGION_GET - dump */
+struct devlink_region_get_list {
+	struct devlink_region_get_list *next;
+	struct devlink_region_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_region_get_list_free(struct devlink_region_get_list *rsp);
+
+struct devlink_region_get_list *devlink_region_get_dump(struct ynl_sock *ys);
+
 /* ============== DEVLINK_CMD_INFO_GET ============== */
 /* DEVLINK_CMD_INFO_GET - do */
 struct devlink_info_get_req {
@@ -152,14 +806,442 @@ struct devlink_info_get_req {
 	char *dev_name;
 };
 
-static inline struct devlink_info_get_req *devlink_info_get_req_alloc(void)
+static inline struct devlink_info_get_req *devlink_info_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_info_get_req));
+}
+void devlink_info_get_req_free(struct devlink_info_get_req *req);
+
+static inline void
+devlink_info_get_req_set_bus_name(struct devlink_info_get_req *req,
+				  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_info_get_req_set_dev_name(struct devlink_info_get_req *req,
+				  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_info_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 info_driver_name_len;
+		__u32 info_serial_number_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *info_driver_name;
+	char *info_serial_number;
+	unsigned int n_info_version_fixed;
+	struct devlink_dl_info_version *info_version_fixed;
+	unsigned int n_info_version_running;
+	struct devlink_dl_info_version *info_version_running;
+	unsigned int n_info_version_stored;
+	struct devlink_dl_info_version *info_version_stored;
+};
+
+void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp);
+
+/*
+ * Get device information, like driver name, hardware and firmware versions etc.
+ */
+struct devlink_info_get_rsp *
+devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req);
+
+/* DEVLINK_CMD_INFO_GET - dump */
+struct devlink_info_get_list {
+	struct devlink_info_get_list *next;
+	struct devlink_info_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_info_get_list_free(struct devlink_info_get_list *rsp);
+
+struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_GET ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */
+struct devlink_health_reporter_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 health_reporter_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *health_reporter_name;
+};
+
+static inline struct devlink_health_reporter_get_req *
+devlink_health_reporter_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_health_reporter_get_req));
+}
+void
+devlink_health_reporter_get_req_free(struct devlink_health_reporter_get_req *req);
+
+static inline void
+devlink_health_reporter_get_req_set_bus_name(struct devlink_health_reporter_get_req *req,
+					     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_health_reporter_get_req_set_dev_name(struct devlink_health_reporter_get_req *req,
+					     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_health_reporter_get_req_set_port_index(struct devlink_health_reporter_get_req *req,
+					       __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_health_reporter_get_req_set_health_reporter_name(struct devlink_health_reporter_get_req *req,
+							 const char *health_reporter_name)
+{
+	free(req->health_reporter_name);
+	req->_present.health_reporter_name_len = strlen(health_reporter_name);
+	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
+	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
+	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
+}
+
+struct devlink_health_reporter_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 health_reporter_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *health_reporter_name;
+};
+
+void
+devlink_health_reporter_get_rsp_free(struct devlink_health_reporter_get_rsp *rsp);
+
+/*
+ * Get health reporter instances.
+ */
+struct devlink_health_reporter_get_rsp *
+devlink_health_reporter_get(struct ynl_sock *ys,
+			    struct devlink_health_reporter_get_req *req);
+
+/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */
+struct devlink_health_reporter_get_list {
+	struct devlink_health_reporter_get_list *next;
+	struct devlink_health_reporter_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void
+devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp);
+
+struct devlink_health_reporter_get_list *
+devlink_health_reporter_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_TRAP_GET ============== */
+/* DEVLINK_CMD_TRAP_GET - do */
+struct devlink_trap_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 trap_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *trap_name;
+};
+
+static inline struct devlink_trap_get_req *devlink_trap_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_trap_get_req));
+}
+void devlink_trap_get_req_free(struct devlink_trap_get_req *req);
+
+static inline void
+devlink_trap_get_req_set_bus_name(struct devlink_trap_get_req *req,
+				  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_trap_get_req_set_dev_name(struct devlink_trap_get_req *req,
+				  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_trap_get_req_set_trap_name(struct devlink_trap_get_req *req,
+				   const char *trap_name)
+{
+	free(req->trap_name);
+	req->_present.trap_name_len = strlen(trap_name);
+	req->trap_name = malloc(req->_present.trap_name_len + 1);
+	memcpy(req->trap_name, trap_name, req->_present.trap_name_len);
+	req->trap_name[req->_present.trap_name_len] = 0;
+}
+
+struct devlink_trap_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 trap_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *trap_name;
+};
+
+void devlink_trap_get_rsp_free(struct devlink_trap_get_rsp *rsp);
+
+/*
+ * Get trap instances.
+ */
+struct devlink_trap_get_rsp *
+devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req);
+
+/* DEVLINK_CMD_TRAP_GET - dump */
+struct devlink_trap_get_list {
+	struct devlink_trap_get_list *next;
+	struct devlink_trap_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp);
+
+struct devlink_trap_get_list *devlink_trap_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */
+/* DEVLINK_CMD_TRAP_GROUP_GET - do */
+struct devlink_trap_group_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 trap_group_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *trap_group_name;
+};
+
+static inline struct devlink_trap_group_get_req *
+devlink_trap_group_get_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_info_get_req));
+	return calloc(1, sizeof(struct devlink_trap_group_get_req));
 }
-void devlink_info_get_req_free(struct devlink_info_get_req *req);
+void devlink_trap_group_get_req_free(struct devlink_trap_group_get_req *req);
 
 static inline void
-devlink_info_get_req_set_bus_name(struct devlink_info_get_req *req,
+devlink_trap_group_get_req_set_bus_name(struct devlink_trap_group_get_req *req,
+					const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_trap_group_get_req_set_dev_name(struct devlink_trap_group_get_req *req,
+					const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_trap_group_get_req_set_trap_group_name(struct devlink_trap_group_get_req *req,
+					       const char *trap_group_name)
+{
+	free(req->trap_group_name);
+	req->_present.trap_group_name_len = strlen(trap_group_name);
+	req->trap_group_name = malloc(req->_present.trap_group_name_len + 1);
+	memcpy(req->trap_group_name, trap_group_name, req->_present.trap_group_name_len);
+	req->trap_group_name[req->_present.trap_group_name_len] = 0;
+}
+
+struct devlink_trap_group_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 trap_group_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *trap_group_name;
+};
+
+void devlink_trap_group_get_rsp_free(struct devlink_trap_group_get_rsp *rsp);
+
+/*
+ * Get trap group instances.
+ */
+struct devlink_trap_group_get_rsp *
+devlink_trap_group_get(struct ynl_sock *ys,
+		       struct devlink_trap_group_get_req *req);
+
+/* DEVLINK_CMD_TRAP_GROUP_GET - dump */
+struct devlink_trap_group_get_list {
+	struct devlink_trap_group_get_list *next;
+	struct devlink_trap_group_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp);
+
+struct devlink_trap_group_get_list *
+devlink_trap_group_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */
+/* DEVLINK_CMD_TRAP_POLICER_GET - do */
+struct devlink_trap_policer_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 trap_policer_id:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 trap_policer_id;
+};
+
+static inline struct devlink_trap_policer_get_req *
+devlink_trap_policer_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_trap_policer_get_req));
+}
+void
+devlink_trap_policer_get_req_free(struct devlink_trap_policer_get_req *req);
+
+static inline void
+devlink_trap_policer_get_req_set_bus_name(struct devlink_trap_policer_get_req *req,
+					  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_trap_policer_get_req_set_dev_name(struct devlink_trap_policer_get_req *req,
+					  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_trap_policer_get_req_set_trap_policer_id(struct devlink_trap_policer_get_req *req,
+						 __u32 trap_policer_id)
+{
+	req->_present.trap_policer_id = 1;
+	req->trap_policer_id = trap_policer_id;
+}
+
+struct devlink_trap_policer_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 trap_policer_id:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 trap_policer_id;
+};
+
+void
+devlink_trap_policer_get_rsp_free(struct devlink_trap_policer_get_rsp *rsp);
+
+/*
+ * Get trap policer instances.
+ */
+struct devlink_trap_policer_get_rsp *
+devlink_trap_policer_get(struct ynl_sock *ys,
+			 struct devlink_trap_policer_get_req *req);
+
+/* DEVLINK_CMD_TRAP_POLICER_GET - dump */
+struct devlink_trap_policer_get_list {
+	struct devlink_trap_policer_get_list *next;
+	struct devlink_trap_policer_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void
+devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp);
+
+struct devlink_trap_policer_get_list *
+devlink_trap_policer_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_RATE_GET ============== */
+/* DEVLINK_CMD_RATE_GET - do */
+struct devlink_rate_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 rate_node_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *rate_node_name;
+};
+
+static inline struct devlink_rate_get_req *devlink_rate_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_rate_get_req));
+}
+void devlink_rate_get_req_free(struct devlink_rate_get_req *req);
+
+static inline void
+devlink_rate_get_req_set_bus_name(struct devlink_rate_get_req *req,
 				  const char *bus_name)
 {
 	free(req->bus_name);
@@ -169,7 +1251,7 @@ devlink_info_get_req_set_bus_name(struct devlink_info_get_req *req,
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_info_get_req_set_dev_name(struct devlink_info_get_req *req,
+devlink_rate_get_req_set_dev_name(struct devlink_rate_get_req *req,
 				  const char *dev_name)
 {
 	free(req->dev_name);
@@ -178,43 +1260,204 @@ devlink_info_get_req_set_dev_name(struct devlink_info_get_req *req,
 	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
+static inline void
+devlink_rate_get_req_set_port_index(struct devlink_rate_get_req *req,
+				    __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_rate_get_req_set_rate_node_name(struct devlink_rate_get_req *req,
+					const char *rate_node_name)
+{
+	free(req->rate_node_name);
+	req->_present.rate_node_name_len = strlen(rate_node_name);
+	req->rate_node_name = malloc(req->_present.rate_node_name_len + 1);
+	memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len);
+	req->rate_node_name[req->_present.rate_node_name_len] = 0;
+}
 
-struct devlink_info_get_rsp {
+struct devlink_rate_get_rsp {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
-		__u32 info_driver_name_len;
-		__u32 info_serial_number_len;
+		__u32 port_index:1;
+		__u32 rate_node_name_len;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
-	char *info_driver_name;
-	char *info_serial_number;
-	unsigned int n_info_version_fixed;
-	struct devlink_dl_info_version *info_version_fixed;
-	unsigned int n_info_version_running;
-	struct devlink_dl_info_version *info_version_running;
-	unsigned int n_info_version_stored;
-	struct devlink_dl_info_version *info_version_stored;
+	__u32 port_index;
+	char *rate_node_name;
 };
 
-void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp);
+void devlink_rate_get_rsp_free(struct devlink_rate_get_rsp *rsp);
 
 /*
- * Get device information, like driver name, hardware and firmware versions etc.
+ * Get rate instances.
  */
-struct devlink_info_get_rsp *
-devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req);
+struct devlink_rate_get_rsp *
+devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req);
 
-/* DEVLINK_CMD_INFO_GET - dump */
-struct devlink_info_get_list {
-	struct devlink_info_get_list *next;
-	struct devlink_info_get_rsp obj __attribute__ ((aligned (8)));
+/* DEVLINK_CMD_RATE_GET - dump */
+struct devlink_rate_get_list {
+	struct devlink_rate_get_list *next;
+	struct devlink_rate_get_rsp obj __attribute__ ((aligned (8)));
 };
 
-void devlink_info_get_list_free(struct devlink_info_get_list *rsp);
+void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp);
 
-struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys);
+struct devlink_rate_get_list *devlink_rate_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_LINECARD_GET ============== */
+/* DEVLINK_CMD_LINECARD_GET - do */
+struct devlink_linecard_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 linecard_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 linecard_index;
+};
+
+static inline struct devlink_linecard_get_req *
+devlink_linecard_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_linecard_get_req));
+}
+void devlink_linecard_get_req_free(struct devlink_linecard_get_req *req);
+
+static inline void
+devlink_linecard_get_req_set_bus_name(struct devlink_linecard_get_req *req,
+				      const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_linecard_get_req_set_dev_name(struct devlink_linecard_get_req *req,
+				      const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_linecard_get_req_set_linecard_index(struct devlink_linecard_get_req *req,
+					    __u32 linecard_index)
+{
+	req->_present.linecard_index = 1;
+	req->linecard_index = linecard_index;
+}
+
+struct devlink_linecard_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 linecard_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 linecard_index;
+};
+
+void devlink_linecard_get_rsp_free(struct devlink_linecard_get_rsp *rsp);
+
+/*
+ * Get line card instances.
+ */
+struct devlink_linecard_get_rsp *
+devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req);
+
+/* DEVLINK_CMD_LINECARD_GET - dump */
+struct devlink_linecard_get_list {
+	struct devlink_linecard_get_list *next;
+	struct devlink_linecard_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp);
+
+struct devlink_linecard_get_list *
+devlink_linecard_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_SELFTESTS_GET ============== */
+/* DEVLINK_CMD_SELFTESTS_GET - do */
+struct devlink_selftests_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_selftests_get_req *
+devlink_selftests_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_selftests_get_req));
+}
+void devlink_selftests_get_req_free(struct devlink_selftests_get_req *req);
+
+static inline void
+devlink_selftests_get_req_set_bus_name(struct devlink_selftests_get_req *req,
+				       const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_selftests_get_req_set_dev_name(struct devlink_selftests_get_req *req,
+				       const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_selftests_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+void devlink_selftests_get_rsp_free(struct devlink_selftests_get_rsp *rsp);
+
+/*
+ * Get device selftest instances.
+ */
+struct devlink_selftests_get_rsp *
+devlink_selftests_get(struct ynl_sock *ys,
+		      struct devlink_selftests_get_req *req);
+
+/* DEVLINK_CMD_SELFTESTS_GET - dump */
+struct devlink_selftests_get_list {
+	struct devlink_selftests_get_list *next;
+	struct devlink_selftests_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp);
+
+struct devlink_selftests_get_list *
+devlink_selftests_get_dump(struct ynl_sock *ys);
 
 #endif /* _LINUX_DEVLINK_GEN_H */
-- 
GitLab


From ddff283280ba0a6b84929f357859f7ea74cecfbe Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:09 +0200
Subject: [PATCH 1201/1806] devlink: remove duplicate temporary netlink
 callback prototypes

Remove the duplicate temporary netlink callback prototype as the
generated ones are already in place.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-9-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h | 48 -------------------------------------
 1 file changed, 48 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index f8af6ffdbb3ad..7caa385703de7 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -185,50 +185,11 @@ int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
 			     struct netlink_ext_ack *extack);
 
 /* Devlink nl cmds */
-int devlink_nl_pre_doit_port(const struct genl_split_ops *ops,
-			     struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
-				      struct sk_buff *skb,
-				      struct genl_info *info);
 int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_selftests_get_dumpit(struct sk_buff *skb,
-				    struct netlink_callback *cb);
 int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
-int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_rate_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
-int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
-				   struct netlink_callback *cb);
-int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
-int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb,
-				  struct netlink_callback *cb);
-int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
-				     struct genl_info *info);
-int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb,
-				       struct netlink_callback *cb);
-int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
-					struct genl_info *info);
-int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb,
-					  struct netlink_callback *cb);
-int devlink_nl_param_get_doit(struct sk_buff *skb,
-			      struct genl_info *info);
-int devlink_nl_param_get_dumpit(struct sk_buff *skb,
-				struct netlink_callback *cb);
-int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_region_get_dumpit(struct sk_buff *skb,
-				 struct netlink_callback *cb);
-int devlink_nl_health_reporter_get_doit(struct sk_buff *skb,
-					struct genl_info *info);
-int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb,
-					  struct netlink_callback *cb);
 int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 					    struct genl_info *info);
 int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
@@ -241,12 +202,3 @@ int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb,
 						   struct genl_info *info);
 int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb,
 					     struct genl_info *info);
-int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_trap_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
-int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb,
-				     struct netlink_callback *cb);
-int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info);
-int devlink_nl_trap_policer_get_doit(struct sk_buff *skb,
-				     struct genl_info *info);
-int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb,
-				       struct netlink_callback *cb);
-- 
GitLab


From 833e479d330c29aa4cfd35b8647d5993d5a78643 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:10 +0200
Subject: [PATCH 1202/1806] devlink: remove converted commands from small ops

As the commands are already defined in split ops, remove them
from small ops.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-10-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h |  2 +-
 net/devlink/leftover.c      | 99 +------------------------------------
 2 files changed, 3 insertions(+), 98 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 7caa385703de7..eb1d5066c73fe 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -118,7 +118,7 @@ typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg,
 				       struct netlink_callback *cb,
 				       int flags);
 
-extern const struct genl_small_ops devlink_nl_small_ops[54];
+extern const struct genl_small_ops devlink_nl_small_ops[40];
 
 struct devlink *
 devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 883c65545d263..3883a90d32bb2 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -6307,15 +6307,7 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
 	return devlink_trap_policer_set(devlink, policer_item, info);
 }
 
-const struct genl_small_ops devlink_nl_small_ops[54] = {
-	{
-		.cmd = DEVLINK_CMD_PORT_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_port_get_doit,
-		.dumpit = devlink_nl_port_get_dumpit,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-		/* can be retrieved by unprivileged users */
-	},
+const struct genl_small_ops devlink_nl_small_ops[40] = {
 	{
 		.cmd = DEVLINK_CMD_PORT_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -6323,12 +6315,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
-	{
-		.cmd = DEVLINK_CMD_RATE_GET,
-		.doit = devlink_nl_rate_get_doit,
-		.dumpit = devlink_nl_rate_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_RATE_SET,
 		.doit = devlink_nl_cmd_rate_set_doit,
@@ -6369,45 +6355,18 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
-	{
-		.cmd = DEVLINK_CMD_LINECARD_GET,
-		.doit = devlink_nl_linecard_get_doit,
-		.dumpit = devlink_nl_linecard_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
+
 	{
 		.cmd = DEVLINK_CMD_LINECARD_SET,
 		.doit = devlink_nl_cmd_linecard_set_doit,
 		.flags = GENL_ADMIN_PERM,
 	},
-	{
-		.cmd = DEVLINK_CMD_SB_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_sb_get_doit,
-		.dumpit = devlink_nl_sb_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_POOL_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_sb_pool_get_doit,
-		.dumpit = devlink_nl_sb_pool_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_SB_POOL_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_sb_pool_set_doit,
 		.flags = GENL_ADMIN_PERM,
 	},
-	{
-		.cmd = DEVLINK_CMD_SB_PORT_POOL_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_sb_port_pool_get_doit,
-		.dumpit = devlink_nl_sb_port_pool_get_dumpit,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_SB_PORT_POOL_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -6415,14 +6374,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
-	{
-		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_sb_tc_pool_bind_get_doit,
-		.dumpit = devlink_nl_sb_tc_pool_bind_get_dumpit,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -6496,13 +6447,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.doit = devlink_nl_cmd_reload,
 		.flags = GENL_ADMIN_PERM,
 	},
-	{
-		.cmd = DEVLINK_CMD_PARAM_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_param_get_doit,
-		.dumpit = devlink_nl_param_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_PARAM_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -6524,13 +6468,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
-	{
-		.cmd = DEVLINK_CMD_REGION_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_region_get_doit,
-		.dumpit = devlink_nl_region_get_dumpit,
-		.flags = GENL_ADMIN_PERM,
-	},
 	{
 		.cmd = DEVLINK_CMD_REGION_NEW,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -6550,14 +6487,6 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.dumpit = devlink_nl_cmd_region_read_dumpit,
 		.flags = GENL_ADMIN_PERM,
 	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_health_reporter_get_doit,
-		.dumpit = devlink_nl_health_reporter_get_dumpit,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -6606,45 +6535,21 @@ const struct genl_small_ops devlink_nl_small_ops[54] = {
 		.doit = devlink_nl_cmd_flash_update,
 		.flags = GENL_ADMIN_PERM,
 	},
-	{
-		.cmd = DEVLINK_CMD_TRAP_GET,
-		.doit = devlink_nl_trap_get_doit,
-		.dumpit = devlink_nl_trap_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_TRAP_SET,
 		.doit = devlink_nl_cmd_trap_set_doit,
 		.flags = GENL_ADMIN_PERM,
 	},
-	{
-		.cmd = DEVLINK_CMD_TRAP_GROUP_GET,
-		.doit = devlink_nl_trap_group_get_doit,
-		.dumpit = devlink_nl_trap_group_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_TRAP_GROUP_SET,
 		.doit = devlink_nl_cmd_trap_group_set_doit,
 		.flags = GENL_ADMIN_PERM,
 	},
-	{
-		.cmd = DEVLINK_CMD_TRAP_POLICER_GET,
-		.doit = devlink_nl_trap_policer_get_doit,
-		.dumpit = devlink_nl_trap_policer_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_TRAP_POLICER_SET,
 		.doit = devlink_nl_cmd_trap_policer_set_doit,
 		.flags = GENL_ADMIN_PERM,
 	},
-	{
-		.cmd = DEVLINK_CMD_SELFTESTS_GET,
-		.doit = devlink_nl_selftests_get_doit,
-		.dumpit = devlink_nl_selftests_get_dumpit,
-		/* can be retrieved by unprivileged users */
-	},
 	{
 		.cmd = DEVLINK_CMD_SELFTESTS_RUN,
 		.doit = devlink_nl_cmd_selftests_run,
-- 
GitLab


From 4a1b5aa8b5c7433ad6e0c8b52469980ae94a4398 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:11 +0200
Subject: [PATCH 1203/1806] devlink: allow user to narrow per-instance dumps by
 passing handle attrs

For SFs, one devlink instance per SF is created. There might be
thousands of these on a single host. When a user needs to know port
handle for specific SF, he needs to dump all devlink ports on the host
which does not scale good.

Allow user to pass devlink handle attributes alongside the dump command
and dump only objects which are under selected devlink instance.

Example:
$ devlink port show
auxiliary/mlx5_core.eth.0/65535: type eth netdev eth2 flavour physical port 0 splittable false
auxiliary/mlx5_core.eth.1/131071: type eth netdev eth3 flavour physical port 1 splittable false

$ devlink port show auxiliary/mlx5_core.eth.0
auxiliary/mlx5_core.eth.0/65535: type eth netdev eth2 flavour physical port 0 splittable false

$ devlink port show auxiliary/mlx5_core.eth.1
auxiliary/mlx5_core.eth.1/131071: type eth netdev eth3 flavour physical port 1 splittable false

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-11-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/netlink.c | 43 ++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 40 insertions(+), 3 deletions(-)

diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 47e44fb45815f..a9b43b0c59598 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -170,8 +170,30 @@ void devlink_nl_post_doit(const struct genl_split_ops *ops,
 	devlink_put(devlink);
 }
 
-int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
-		      devlink_nl_dump_one_func_t *dump_one)
+static int devlink_nl_inst_single_dumpit(struct sk_buff *msg,
+					 struct netlink_callback *cb, int flags,
+					 devlink_nl_dump_one_func_t *dump_one,
+					 struct nlattr **attrs)
+{
+	struct devlink *devlink;
+	int err;
+
+	devlink = devlink_get_from_attrs_lock(sock_net(msg->sk), attrs);
+	if (IS_ERR(devlink))
+		return PTR_ERR(devlink);
+	err = dump_one(msg, devlink, cb, flags | NLM_F_DUMP_FILTERED);
+
+	devl_unlock(devlink);
+	devlink_put(devlink);
+
+	if (err != -EMSGSIZE)
+		return err;
+	return msg->len;
+}
+
+static int devlink_nl_inst_iter_dumpit(struct sk_buff *msg,
+				       struct netlink_callback *cb, int flags,
+				       devlink_nl_dump_one_func_t *dump_one)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct devlink *devlink;
@@ -182,7 +204,7 @@ int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 		devl_lock(devlink);
 
 		if (devl_is_registered(devlink))
-			err = dump_one(msg, devlink, cb, NLM_F_MULTI);
+			err = dump_one(msg, devlink, cb, flags);
 		else
 			err = 0;
 
@@ -203,6 +225,21 @@ int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 	return msg->len;
 }
 
+int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
+		      devlink_nl_dump_one_func_t *dump_one)
+{
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	struct nlattr **attrs = info->attrs;
+	int flags = NLM_F_MULTI;
+
+	if (attrs &&
+	    (attrs[DEVLINK_ATTR_BUS_NAME] || attrs[DEVLINK_ATTR_DEV_NAME]))
+		return devlink_nl_inst_single_dumpit(msg, cb, flags, dump_one,
+						     attrs);
+	else
+		return devlink_nl_inst_iter_dumpit(msg, cb, flags, dump_one);
+}
+
 struct genl_family devlink_nl_family __ro_after_init = {
 	.name		= DEVLINK_GENL_NAME,
 	.version	= DEVLINK_GENL_VERSION,
-- 
GitLab


From 34493336e7d3d38a8ec6472243baa6660214d990 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:12 +0200
Subject: [PATCH 1204/1806] netlink: specs: devlink: extend per-instance dump
 commands to accept instance attributes

Extend per-instance dump command definitions to accept instance
attributes. Allow parsing of devlink handle attributes so they could
be used for instance selection.

Re-generate the related code.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-12-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/devlink.yaml |  39 +-
 net/devlink/netlink_gen.c                | 169 +++++--
 tools/net/ynl/generated/devlink-user.c   | 123 ++++-
 tools/net/ynl/generated/devlink-user.h   | 546 ++++++++++++++++++++++-
 4 files changed, 799 insertions(+), 78 deletions(-)

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 4f2aa48017a70..6dbebeebd63e0 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -284,7 +284,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit-port
@@ -299,6 +298,8 @@ operations:
           value: 7
           attributes: *port-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply:
           value: 3  # due to a bug, port dump returns DEVLINK_CMD_NEW
           attributes: *port-id-attrs
@@ -311,7 +312,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit
@@ -326,6 +326,8 @@ operations:
           value: 11
           attributes: *sb-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *sb-get-reply
 
       # TODO: fill in the operations in between
@@ -336,7 +338,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit
@@ -352,6 +353,8 @@ operations:
           value: 15
           attributes: *sb-pool-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *sb-pool-get-reply
 
       # TODO: fill in the operations in between
@@ -362,7 +365,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit-port
@@ -379,6 +381,8 @@ operations:
           value: 19
           attributes: *sb-port-pool-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *sb-port-pool-get-reply
 
       # TODO: fill in the operations in between
@@ -389,7 +393,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit-port
@@ -407,6 +410,8 @@ operations:
           value: 23
           attributes: *sb-tc-pool-bind-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *sb-tc-pool-bind-get-reply
 
       # TODO: fill in the operations in between
@@ -417,7 +422,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit
@@ -432,6 +436,8 @@ operations:
           value: 38
           attributes: *param-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *param-get-reply
 
       # TODO: fill in the operations in between
@@ -442,7 +448,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit-port-optional
@@ -458,6 +463,8 @@ operations:
           value: 42
           attributes: *region-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *region-get-reply
 
       # TODO: fill in the operations in between
@@ -495,7 +502,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit-port-optional
@@ -509,6 +515,8 @@ operations:
         reply: &health-reporter-get-reply
           attributes: *health-reporter-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *health-reporter-get-reply
 
       # TODO: fill in the operations in between
@@ -519,7 +527,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit
@@ -534,6 +541,8 @@ operations:
           value: 61
           attributes: *trap-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *trap-get-reply
 
       # TODO: fill in the operations in between
@@ -544,7 +553,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit
@@ -559,6 +567,8 @@ operations:
           value: 65
           attributes: *trap-group-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *trap-group-get-reply
 
       # TODO: fill in the operations in between
@@ -569,7 +579,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit
@@ -584,6 +593,8 @@ operations:
           value: 69
           attributes: *trap-policer-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *trap-policer-get-reply
 
       # TODO: fill in the operations in between
@@ -594,7 +605,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit
@@ -610,6 +620,8 @@ operations:
           value: 74
           attributes: *rate-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *rate-get-reply
 
       # TODO: fill in the operations in between
@@ -620,7 +632,6 @@ operations:
       attribute-set: devlink
       dont-validate:
         - strict
-        - dump
 
       do:
         pre: devlink-nl-pre-doit
@@ -635,6 +646,8 @@ operations:
           value: 78
           attributes: *linecard-id-attrs
       dump:
+        request:
+          attributes: *dev-id-attrs
         reply: *linecard-get-reply
 
       # TODO: fill in the operations in between
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
index e384b91b2e3ba..5f3e980c6a7c8 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -17,29 +17,47 @@ static const struct nla_policy devlink_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1]
 };
 
 /* DEVLINK_CMD_PORT_GET - do */
-static const struct nla_policy devlink_port_get_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = {
+static const struct nla_policy devlink_port_get_do_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
 };
 
+/* DEVLINK_CMD_PORT_GET - dump */
+static const struct nla_policy devlink_port_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_SB_GET - do */
-static const struct nla_policy devlink_sb_get_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = {
+static const struct nla_policy devlink_sb_get_do_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
 };
 
+/* DEVLINK_CMD_SB_GET - dump */
+static const struct nla_policy devlink_sb_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_SB_POOL_GET - do */
-static const struct nla_policy devlink_sb_pool_get_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = {
+static const struct nla_policy devlink_sb_pool_get_do_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
 	[DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, },
 };
 
+/* DEVLINK_CMD_SB_POOL_GET - dump */
+static const struct nla_policy devlink_sb_pool_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_SB_PORT_POOL_GET - do */
-static const struct nla_policy devlink_sb_port_pool_get_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = {
+static const struct nla_policy devlink_sb_port_pool_get_do_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
@@ -47,8 +65,14 @@ static const struct nla_policy devlink_sb_port_pool_get_nl_policy[DEVLINK_ATTR_S
 	[DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, },
 };
 
+/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */
+static const struct nla_policy devlink_sb_port_pool_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
-static const struct nla_policy devlink_sb_tc_pool_bind_get_nl_policy[DEVLINK_ATTR_SB_TC_INDEX + 1] = {
+static const struct nla_policy devlink_sb_tc_pool_bind_get_do_nl_policy[DEVLINK_ATTR_SB_TC_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
@@ -57,21 +81,39 @@ static const struct nla_policy devlink_sb_tc_pool_bind_get_nl_policy[DEVLINK_ATT
 	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16, },
 };
 
+/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */
+static const struct nla_policy devlink_sb_tc_pool_bind_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_PARAM_GET - do */
-static const struct nla_policy devlink_param_get_nl_policy[DEVLINK_ATTR_PARAM_NAME + 1] = {
+static const struct nla_policy devlink_param_get_do_nl_policy[DEVLINK_ATTR_PARAM_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_PARAM_GET - dump */
+static const struct nla_policy devlink_param_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_REGION_GET - do */
-static const struct nla_policy devlink_region_get_nl_policy[DEVLINK_ATTR_REGION_NAME + 1] = {
+static const struct nla_policy devlink_region_get_do_nl_policy[DEVLINK_ATTR_REGION_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
 	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_REGION_GET - dump */
+static const struct nla_policy devlink_region_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_INFO_GET - do */
 static const struct nla_policy devlink_info_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -79,49 +121,85 @@ static const struct nla_policy devlink_info_get_nl_policy[DEVLINK_ATTR_DEV_NAME
 };
 
 /* DEVLINK_CMD_HEALTH_REPORTER_GET - do */
-static const struct nla_policy devlink_health_reporter_get_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = {
+static const struct nla_policy devlink_health_reporter_get_do_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
 	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */
+static const struct nla_policy devlink_health_reporter_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_TRAP_GET - do */
-static const struct nla_policy devlink_trap_get_nl_policy[DEVLINK_ATTR_TRAP_NAME + 1] = {
+static const struct nla_policy devlink_trap_get_do_nl_policy[DEVLINK_ATTR_TRAP_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_TRAP_GET - dump */
+static const struct nla_policy devlink_trap_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_TRAP_GROUP_GET - do */
-static const struct nla_policy devlink_trap_group_get_nl_policy[DEVLINK_ATTR_TRAP_GROUP_NAME + 1] = {
+static const struct nla_policy devlink_trap_group_get_do_nl_policy[DEVLINK_ATTR_TRAP_GROUP_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_TRAP_GROUP_GET - dump */
+static const struct nla_policy devlink_trap_group_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_TRAP_POLICER_GET - do */
-static const struct nla_policy devlink_trap_policer_get_nl_policy[DEVLINK_ATTR_TRAP_POLICER_ID + 1] = {
+static const struct nla_policy devlink_trap_policer_get_do_nl_policy[DEVLINK_ATTR_TRAP_POLICER_ID + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32, },
 };
 
+/* DEVLINK_CMD_TRAP_POLICER_GET - dump */
+static const struct nla_policy devlink_trap_policer_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_RATE_GET - do */
-static const struct nla_policy devlink_rate_get_nl_policy[DEVLINK_ATTR_RATE_NODE_NAME + 1] = {
+static const struct nla_policy devlink_rate_get_do_nl_policy[DEVLINK_ATTR_RATE_NODE_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
 	[DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_RATE_GET - dump */
+static const struct nla_policy devlink_rate_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_LINECARD_GET - do */
-static const struct nla_policy devlink_linecard_get_nl_policy[DEVLINK_ATTR_LINECARD_INDEX + 1] = {
+static const struct nla_policy devlink_linecard_get_do_nl_policy[DEVLINK_ATTR_LINECARD_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32, },
 };
 
+/* DEVLINK_CMD_LINECARD_GET - dump */
+static const struct nla_policy devlink_linecard_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_SELFTESTS_GET - do */
 static const struct nla_policy devlink_selftests_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -152,14 +230,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit_port,
 		.doit		= devlink_nl_port_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_port_get_nl_policy,
+		.policy		= devlink_port_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_PORT_INDEX,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_PORT_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_port_get_dumpit,
+		.policy		= devlink_port_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -168,14 +247,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit,
 		.doit		= devlink_nl_sb_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_sb_get_nl_policy,
+		.policy		= devlink_sb_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_SB_INDEX,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_SB_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_sb_get_dumpit,
+		.policy		= devlink_sb_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -184,14 +264,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit,
 		.doit		= devlink_nl_sb_pool_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_sb_pool_get_nl_policy,
+		.policy		= devlink_sb_pool_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_SB_POOL_INDEX,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_SB_POOL_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_sb_pool_get_dumpit,
+		.policy		= devlink_sb_pool_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -200,14 +281,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit_port,
 		.doit		= devlink_nl_sb_port_pool_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_sb_port_pool_get_nl_policy,
+		.policy		= devlink_sb_port_pool_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_SB_POOL_INDEX,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_SB_PORT_POOL_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_sb_port_pool_get_dumpit,
+		.policy		= devlink_sb_port_pool_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -216,14 +298,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit_port,
 		.doit		= devlink_nl_sb_tc_pool_bind_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_sb_tc_pool_bind_get_nl_policy,
+		.policy		= devlink_sb_tc_pool_bind_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_SB_TC_INDEX,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_SB_TC_POOL_BIND_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_sb_tc_pool_bind_get_dumpit,
+		.policy		= devlink_sb_tc_pool_bind_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -232,14 +315,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit,
 		.doit		= devlink_nl_param_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_param_get_nl_policy,
+		.policy		= devlink_param_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_PARAM_NAME,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_PARAM_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_param_get_dumpit,
+		.policy		= devlink_param_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -248,14 +332,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit_port_optional,
 		.doit		= devlink_nl_region_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_region_get_nl_policy,
+		.policy		= devlink_region_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_REGION_NAME,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_REGION_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_region_get_dumpit,
+		.policy		= devlink_region_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -280,14 +365,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit_port_optional,
 		.doit		= devlink_nl_health_reporter_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_health_reporter_get_nl_policy,
+		.policy		= devlink_health_reporter_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_HEALTH_REPORTER_NAME,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_HEALTH_REPORTER_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_health_reporter_get_dumpit,
+		.policy		= devlink_health_reporter_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -296,14 +382,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit,
 		.doit		= devlink_nl_trap_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_trap_get_nl_policy,
+		.policy		= devlink_trap_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_TRAP_NAME,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_TRAP_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_trap_get_dumpit,
+		.policy		= devlink_trap_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -312,14 +399,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit,
 		.doit		= devlink_nl_trap_group_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_trap_group_get_nl_policy,
+		.policy		= devlink_trap_group_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_TRAP_GROUP_NAME,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_TRAP_GROUP_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_trap_group_get_dumpit,
+		.policy		= devlink_trap_group_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -328,14 +416,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit,
 		.doit		= devlink_nl_trap_policer_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_trap_policer_get_nl_policy,
+		.policy		= devlink_trap_policer_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_TRAP_POLICER_ID,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_TRAP_POLICER_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_trap_policer_get_dumpit,
+		.policy		= devlink_trap_policer_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -344,14 +433,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit,
 		.doit		= devlink_nl_rate_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_rate_get_nl_policy,
+		.policy		= devlink_rate_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_RATE_NODE_NAME,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_RATE_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_rate_get_dumpit,
+		.policy		= devlink_rate_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -360,14 +450,15 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.pre_doit	= devlink_nl_pre_doit,
 		.doit		= devlink_nl_linecard_get_doit,
 		.post_doit	= devlink_nl_post_doit,
-		.policy		= devlink_linecard_get_nl_policy,
+		.policy		= devlink_linecard_get_do_nl_policy,
 		.maxattr	= DEVLINK_ATTR_LINECARD_INDEX,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= DEVLINK_CMD_LINECARD_GET,
-		.validate	= GENL_DONT_VALIDATE_DUMP,
 		.dumpit		= devlink_nl_linecard_get_dumpit,
+		.policy		= devlink_linecard_get_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c
index e9ab98b5ffe32..80ee9d24eb163 100644
--- a/tools/net/ynl/generated/devlink-user.c
+++ b/tools/net/ynl/generated/devlink-user.c
@@ -723,7 +723,9 @@ void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp)
 	}
 }
 
-struct devlink_port_get_rsp_list *devlink_port_get_dump(struct ynl_sock *ys)
+struct devlink_port_get_rsp_list *
+devlink_port_get_dump(struct ynl_sock *ys,
+		      struct devlink_port_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -736,6 +738,12 @@ struct devlink_port_get_rsp_list *devlink_port_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -858,7 +866,8 @@ void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp)
 	}
 }
 
-struct devlink_sb_get_list *devlink_sb_get_dump(struct ynl_sock *ys)
+struct devlink_sb_get_list *
+devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -871,6 +880,12 @@ struct devlink_sb_get_list *devlink_sb_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -1000,7 +1015,9 @@ void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp)
 	}
 }
 
-struct devlink_sb_pool_get_list *devlink_sb_pool_get_dump(struct ynl_sock *ys)
+struct devlink_sb_pool_get_list *
+devlink_sb_pool_get_dump(struct ynl_sock *ys,
+			 struct devlink_sb_pool_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -1013,6 +1030,12 @@ struct devlink_sb_pool_get_list *devlink_sb_pool_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -1154,7 +1177,8 @@ devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp)
 }
 
 struct devlink_sb_port_pool_get_list *
-devlink_sb_port_pool_get_dump(struct ynl_sock *ys)
+devlink_sb_port_pool_get_dump(struct ynl_sock *ys,
+			      struct devlink_sb_port_pool_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -1167,6 +1191,12 @@ devlink_sb_port_pool_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -1316,7 +1346,8 @@ devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *r
 }
 
 struct devlink_sb_tc_pool_bind_get_list *
-devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys)
+devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys,
+				 struct devlink_sb_tc_pool_bind_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -1329,6 +1360,12 @@ devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -1460,7 +1497,9 @@ void devlink_param_get_list_free(struct devlink_param_get_list *rsp)
 	}
 }
 
-struct devlink_param_get_list *devlink_param_get_dump(struct ynl_sock *ys)
+struct devlink_param_get_list *
+devlink_param_get_dump(struct ynl_sock *ys,
+		       struct devlink_param_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -1473,6 +1512,12 @@ struct devlink_param_get_list *devlink_param_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -1611,7 +1656,9 @@ void devlink_region_get_list_free(struct devlink_region_get_list *rsp)
 	}
 }
 
-struct devlink_region_get_list *devlink_region_get_dump(struct ynl_sock *ys)
+struct devlink_region_get_list *
+devlink_region_get_dump(struct ynl_sock *ys,
+			struct devlink_region_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -1624,6 +1671,12 @@ struct devlink_region_get_list *devlink_region_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -2006,7 +2059,8 @@ devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *r
 }
 
 struct devlink_health_reporter_get_list *
-devlink_health_reporter_get_dump(struct ynl_sock *ys)
+devlink_health_reporter_get_dump(struct ynl_sock *ys,
+				 struct devlink_health_reporter_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -2019,6 +2073,12 @@ devlink_health_reporter_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -2150,7 +2210,9 @@ void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp)
 	}
 }
 
-struct devlink_trap_get_list *devlink_trap_get_dump(struct ynl_sock *ys)
+struct devlink_trap_get_list *
+devlink_trap_get_dump(struct ynl_sock *ys,
+		      struct devlink_trap_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -2163,6 +2225,12 @@ struct devlink_trap_get_list *devlink_trap_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -2296,7 +2364,8 @@ void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp)
 }
 
 struct devlink_trap_group_get_list *
-devlink_trap_group_get_dump(struct ynl_sock *ys)
+devlink_trap_group_get_dump(struct ynl_sock *ys,
+			    struct devlink_trap_group_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -2309,6 +2378,12 @@ devlink_trap_group_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -2436,7 +2511,8 @@ devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp)
 }
 
 struct devlink_trap_policer_get_list *
-devlink_trap_policer_get_dump(struct ynl_sock *ys)
+devlink_trap_policer_get_dump(struct ynl_sock *ys,
+			      struct devlink_trap_policer_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -2449,6 +2525,12 @@ devlink_trap_policer_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -2587,7 +2669,9 @@ void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp)
 	}
 }
 
-struct devlink_rate_get_list *devlink_rate_get_dump(struct ynl_sock *ys)
+struct devlink_rate_get_list *
+devlink_rate_get_dump(struct ynl_sock *ys,
+		      struct devlink_rate_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -2600,6 +2684,12 @@ struct devlink_rate_get_list *devlink_rate_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -2723,7 +2813,8 @@ void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp)
 }
 
 struct devlink_linecard_get_list *
-devlink_linecard_get_dump(struct ynl_sock *ys)
+devlink_linecard_get_dump(struct ynl_sock *ys,
+			  struct devlink_linecard_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
@@ -2736,6 +2827,12 @@ devlink_linecard_get_dump(struct ynl_sock *ys)
 	yds.rsp_policy = &devlink_nest;
 
 	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h
index f6ec5b6e5d26e..12530f1795ca4 100644
--- a/tools/net/ynl/generated/devlink-user.h
+++ b/tools/net/ynl/generated/devlink-user.h
@@ -210,6 +210,44 @@ struct devlink_port_get_rsp *
 devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req);
 
 /* DEVLINK_CMD_PORT_GET - dump */
+struct devlink_port_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_port_get_req_dump *
+devlink_port_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_port_get_req_dump));
+}
+void devlink_port_get_req_dump_free(struct devlink_port_get_req_dump *req);
+
+static inline void
+devlink_port_get_req_dump_set_bus_name(struct devlink_port_get_req_dump *req,
+				       const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_port_get_req_dump_set_dev_name(struct devlink_port_get_req_dump *req,
+				       const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_port_get_rsp_dump {
 	struct {
 		__u32 bus_name_len;
@@ -229,7 +267,9 @@ struct devlink_port_get_rsp_list {
 
 void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp);
 
-struct devlink_port_get_rsp_list *devlink_port_get_dump(struct ynl_sock *ys);
+struct devlink_port_get_rsp_list *
+devlink_port_get_dump(struct ynl_sock *ys,
+		      struct devlink_port_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_SB_GET ============== */
 /* DEVLINK_CMD_SB_GET - do */
@@ -299,6 +339,44 @@ struct devlink_sb_get_rsp *
 devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req);
 
 /* DEVLINK_CMD_SB_GET - dump */
+struct devlink_sb_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_sb_get_req_dump *
+devlink_sb_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_get_req_dump));
+}
+void devlink_sb_get_req_dump_free(struct devlink_sb_get_req_dump *req);
+
+static inline void
+devlink_sb_get_req_dump_set_bus_name(struct devlink_sb_get_req_dump *req,
+				     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_get_req_dump_set_dev_name(struct devlink_sb_get_req_dump *req,
+				     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_sb_get_list {
 	struct devlink_sb_get_list *next;
 	struct devlink_sb_get_rsp obj __attribute__ ((aligned (8)));
@@ -306,7 +384,8 @@ struct devlink_sb_get_list {
 
 void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp);
 
-struct devlink_sb_get_list *devlink_sb_get_dump(struct ynl_sock *ys);
+struct devlink_sb_get_list *
+devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_SB_POOL_GET ============== */
 /* DEVLINK_CMD_SB_POOL_GET - do */
@@ -389,6 +468,45 @@ struct devlink_sb_pool_get_rsp *
 devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req);
 
 /* DEVLINK_CMD_SB_POOL_GET - dump */
+struct devlink_sb_pool_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_sb_pool_get_req_dump *
+devlink_sb_pool_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_pool_get_req_dump));
+}
+void
+devlink_sb_pool_get_req_dump_free(struct devlink_sb_pool_get_req_dump *req);
+
+static inline void
+devlink_sb_pool_get_req_dump_set_bus_name(struct devlink_sb_pool_get_req_dump *req,
+					  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_pool_get_req_dump_set_dev_name(struct devlink_sb_pool_get_req_dump *req,
+					  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_sb_pool_get_list {
 	struct devlink_sb_pool_get_list *next;
 	struct devlink_sb_pool_get_rsp obj __attribute__ ((aligned (8)));
@@ -396,7 +514,9 @@ struct devlink_sb_pool_get_list {
 
 void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp);
 
-struct devlink_sb_pool_get_list *devlink_sb_pool_get_dump(struct ynl_sock *ys);
+struct devlink_sb_pool_get_list *
+devlink_sb_pool_get_dump(struct ynl_sock *ys,
+			 struct devlink_sb_pool_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */
 /* DEVLINK_CMD_SB_PORT_POOL_GET - do */
@@ -493,6 +613,45 @@ devlink_sb_port_pool_get(struct ynl_sock *ys,
 			 struct devlink_sb_port_pool_get_req *req);
 
 /* DEVLINK_CMD_SB_PORT_POOL_GET - dump */
+struct devlink_sb_port_pool_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_sb_port_pool_get_req_dump *
+devlink_sb_port_pool_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_port_pool_get_req_dump));
+}
+void
+devlink_sb_port_pool_get_req_dump_free(struct devlink_sb_port_pool_get_req_dump *req);
+
+static inline void
+devlink_sb_port_pool_get_req_dump_set_bus_name(struct devlink_sb_port_pool_get_req_dump *req,
+					       const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_port_pool_get_req_dump_set_dev_name(struct devlink_sb_port_pool_get_req_dump *req,
+					       const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_sb_port_pool_get_list {
 	struct devlink_sb_port_pool_get_list *next;
 	struct devlink_sb_port_pool_get_rsp obj __attribute__ ((aligned (8)));
@@ -502,7 +661,8 @@ void
 devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp);
 
 struct devlink_sb_port_pool_get_list *
-devlink_sb_port_pool_get_dump(struct ynl_sock *ys);
+devlink_sb_port_pool_get_dump(struct ynl_sock *ys,
+			      struct devlink_sb_port_pool_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */
 /* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
@@ -610,6 +770,45 @@ devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
 			    struct devlink_sb_tc_pool_bind_get_req *req);
 
 /* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */
+struct devlink_sb_tc_pool_bind_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_sb_tc_pool_bind_get_req_dump *
+devlink_sb_tc_pool_bind_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req_dump));
+}
+void
+devlink_sb_tc_pool_bind_get_req_dump_free(struct devlink_sb_tc_pool_bind_get_req_dump *req);
+
+static inline void
+devlink_sb_tc_pool_bind_get_req_dump_set_bus_name(struct devlink_sb_tc_pool_bind_get_req_dump *req,
+						  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_dump_set_dev_name(struct devlink_sb_tc_pool_bind_get_req_dump *req,
+						  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_sb_tc_pool_bind_get_list {
 	struct devlink_sb_tc_pool_bind_get_list *next;
 	struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__ ((aligned (8)));
@@ -619,7 +818,8 @@ void
 devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp);
 
 struct devlink_sb_tc_pool_bind_get_list *
-devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys);
+devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys,
+				 struct devlink_sb_tc_pool_bind_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_PARAM_GET ============== */
 /* DEVLINK_CMD_PARAM_GET - do */
@@ -693,6 +893,44 @@ struct devlink_param_get_rsp *
 devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req);
 
 /* DEVLINK_CMD_PARAM_GET - dump */
+struct devlink_param_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_param_get_req_dump *
+devlink_param_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_param_get_req_dump));
+}
+void devlink_param_get_req_dump_free(struct devlink_param_get_req_dump *req);
+
+static inline void
+devlink_param_get_req_dump_set_bus_name(struct devlink_param_get_req_dump *req,
+					const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_param_get_req_dump_set_dev_name(struct devlink_param_get_req_dump *req,
+					const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_param_get_list {
 	struct devlink_param_get_list *next;
 	struct devlink_param_get_rsp obj __attribute__ ((aligned (8)));
@@ -700,7 +938,9 @@ struct devlink_param_get_list {
 
 void devlink_param_get_list_free(struct devlink_param_get_list *rsp);
 
-struct devlink_param_get_list *devlink_param_get_dump(struct ynl_sock *ys);
+struct devlink_param_get_list *
+devlink_param_get_dump(struct ynl_sock *ys,
+		       struct devlink_param_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_REGION_GET ============== */
 /* DEVLINK_CMD_REGION_GET - do */
@@ -785,6 +1025,44 @@ struct devlink_region_get_rsp *
 devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req);
 
 /* DEVLINK_CMD_REGION_GET - dump */
+struct devlink_region_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_region_get_req_dump *
+devlink_region_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_region_get_req_dump));
+}
+void devlink_region_get_req_dump_free(struct devlink_region_get_req_dump *req);
+
+static inline void
+devlink_region_get_req_dump_set_bus_name(struct devlink_region_get_req_dump *req,
+					 const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_region_get_req_dump_set_dev_name(struct devlink_region_get_req_dump *req,
+					 const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_region_get_list {
 	struct devlink_region_get_list *next;
 	struct devlink_region_get_rsp obj __attribute__ ((aligned (8)));
@@ -792,7 +1070,9 @@ struct devlink_region_get_list {
 
 void devlink_region_get_list_free(struct devlink_region_get_list *rsp);
 
-struct devlink_region_get_list *devlink_region_get_dump(struct ynl_sock *ys);
+struct devlink_region_get_list *
+devlink_region_get_dump(struct ynl_sock *ys,
+			struct devlink_region_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_INFO_GET ============== */
 /* DEVLINK_CMD_INFO_GET - do */
@@ -958,6 +1238,45 @@ devlink_health_reporter_get(struct ynl_sock *ys,
 			    struct devlink_health_reporter_get_req *req);
 
 /* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */
+struct devlink_health_reporter_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_health_reporter_get_req_dump *
+devlink_health_reporter_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_health_reporter_get_req_dump));
+}
+void
+devlink_health_reporter_get_req_dump_free(struct devlink_health_reporter_get_req_dump *req);
+
+static inline void
+devlink_health_reporter_get_req_dump_set_bus_name(struct devlink_health_reporter_get_req_dump *req,
+						  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_health_reporter_get_req_dump_set_dev_name(struct devlink_health_reporter_get_req_dump *req,
+						  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_health_reporter_get_list {
 	struct devlink_health_reporter_get_list *next;
 	struct devlink_health_reporter_get_rsp obj __attribute__ ((aligned (8)));
@@ -967,7 +1286,8 @@ void
 devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp);
 
 struct devlink_health_reporter_get_list *
-devlink_health_reporter_get_dump(struct ynl_sock *ys);
+devlink_health_reporter_get_dump(struct ynl_sock *ys,
+				 struct devlink_health_reporter_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_TRAP_GET ============== */
 /* DEVLINK_CMD_TRAP_GET - do */
@@ -1041,6 +1361,44 @@ struct devlink_trap_get_rsp *
 devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req);
 
 /* DEVLINK_CMD_TRAP_GET - dump */
+struct devlink_trap_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_trap_get_req_dump *
+devlink_trap_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_trap_get_req_dump));
+}
+void devlink_trap_get_req_dump_free(struct devlink_trap_get_req_dump *req);
+
+static inline void
+devlink_trap_get_req_dump_set_bus_name(struct devlink_trap_get_req_dump *req,
+				       const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_trap_get_req_dump_set_dev_name(struct devlink_trap_get_req_dump *req,
+				       const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_trap_get_list {
 	struct devlink_trap_get_list *next;
 	struct devlink_trap_get_rsp obj __attribute__ ((aligned (8)));
@@ -1048,7 +1406,9 @@ struct devlink_trap_get_list {
 
 void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp);
 
-struct devlink_trap_get_list *devlink_trap_get_dump(struct ynl_sock *ys);
+struct devlink_trap_get_list *
+devlink_trap_get_dump(struct ynl_sock *ys,
+		      struct devlink_trap_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */
 /* DEVLINK_CMD_TRAP_GROUP_GET - do */
@@ -1124,6 +1484,45 @@ devlink_trap_group_get(struct ynl_sock *ys,
 		       struct devlink_trap_group_get_req *req);
 
 /* DEVLINK_CMD_TRAP_GROUP_GET - dump */
+struct devlink_trap_group_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_trap_group_get_req_dump *
+devlink_trap_group_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_trap_group_get_req_dump));
+}
+void
+devlink_trap_group_get_req_dump_free(struct devlink_trap_group_get_req_dump *req);
+
+static inline void
+devlink_trap_group_get_req_dump_set_bus_name(struct devlink_trap_group_get_req_dump *req,
+					     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_trap_group_get_req_dump_set_dev_name(struct devlink_trap_group_get_req_dump *req,
+					     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_trap_group_get_list {
 	struct devlink_trap_group_get_list *next;
 	struct devlink_trap_group_get_rsp obj __attribute__ ((aligned (8)));
@@ -1132,7 +1531,8 @@ struct devlink_trap_group_get_list {
 void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp);
 
 struct devlink_trap_group_get_list *
-devlink_trap_group_get_dump(struct ynl_sock *ys);
+devlink_trap_group_get_dump(struct ynl_sock *ys,
+			    struct devlink_trap_group_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */
 /* DEVLINK_CMD_TRAP_POLICER_GET - do */
@@ -1207,6 +1607,45 @@ devlink_trap_policer_get(struct ynl_sock *ys,
 			 struct devlink_trap_policer_get_req *req);
 
 /* DEVLINK_CMD_TRAP_POLICER_GET - dump */
+struct devlink_trap_policer_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_trap_policer_get_req_dump *
+devlink_trap_policer_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_trap_policer_get_req_dump));
+}
+void
+devlink_trap_policer_get_req_dump_free(struct devlink_trap_policer_get_req_dump *req);
+
+static inline void
+devlink_trap_policer_get_req_dump_set_bus_name(struct devlink_trap_policer_get_req_dump *req,
+					       const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_trap_policer_get_req_dump_set_dev_name(struct devlink_trap_policer_get_req_dump *req,
+					       const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_trap_policer_get_list {
 	struct devlink_trap_policer_get_list *next;
 	struct devlink_trap_policer_get_rsp obj __attribute__ ((aligned (8)));
@@ -1216,7 +1655,8 @@ void
 devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp);
 
 struct devlink_trap_policer_get_list *
-devlink_trap_policer_get_dump(struct ynl_sock *ys);
+devlink_trap_policer_get_dump(struct ynl_sock *ys,
+			      struct devlink_trap_policer_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_RATE_GET ============== */
 /* DEVLINK_CMD_RATE_GET - do */
@@ -1301,6 +1741,44 @@ struct devlink_rate_get_rsp *
 devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req);
 
 /* DEVLINK_CMD_RATE_GET - dump */
+struct devlink_rate_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_rate_get_req_dump *
+devlink_rate_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_rate_get_req_dump));
+}
+void devlink_rate_get_req_dump_free(struct devlink_rate_get_req_dump *req);
+
+static inline void
+devlink_rate_get_req_dump_set_bus_name(struct devlink_rate_get_req_dump *req,
+				       const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_rate_get_req_dump_set_dev_name(struct devlink_rate_get_req_dump *req,
+				       const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_rate_get_list {
 	struct devlink_rate_get_list *next;
 	struct devlink_rate_get_rsp obj __attribute__ ((aligned (8)));
@@ -1308,7 +1786,9 @@ struct devlink_rate_get_list {
 
 void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp);
 
-struct devlink_rate_get_list *devlink_rate_get_dump(struct ynl_sock *ys);
+struct devlink_rate_get_list *
+devlink_rate_get_dump(struct ynl_sock *ys,
+		      struct devlink_rate_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_LINECARD_GET ============== */
 /* DEVLINK_CMD_LINECARD_GET - do */
@@ -1380,6 +1860,45 @@ struct devlink_linecard_get_rsp *
 devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req);
 
 /* DEVLINK_CMD_LINECARD_GET - dump */
+struct devlink_linecard_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_linecard_get_req_dump *
+devlink_linecard_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_linecard_get_req_dump));
+}
+void
+devlink_linecard_get_req_dump_free(struct devlink_linecard_get_req_dump *req);
+
+static inline void
+devlink_linecard_get_req_dump_set_bus_name(struct devlink_linecard_get_req_dump *req,
+					   const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_linecard_get_req_dump_set_dev_name(struct devlink_linecard_get_req_dump *req,
+					   const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
 struct devlink_linecard_get_list {
 	struct devlink_linecard_get_list *next;
 	struct devlink_linecard_get_rsp obj __attribute__ ((aligned (8)));
@@ -1388,7 +1907,8 @@ struct devlink_linecard_get_list {
 void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp);
 
 struct devlink_linecard_get_list *
-devlink_linecard_get_dump(struct ynl_sock *ys);
+devlink_linecard_get_dump(struct ynl_sock *ys,
+			  struct devlink_linecard_get_req_dump *req);
 
 /* ============== DEVLINK_CMD_SELFTESTS_GET ============== */
 /* DEVLINK_CMD_SELFTESTS_GET - do */
-- 
GitLab


From b03f13cb67a59175ec7bb7201e5e746e50f2331e Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:13 +0200
Subject: [PATCH 1205/1806] devlink: extend health reporter dump selector by
 port index

Introduce a possibility for devlink object to expose attributes it
supports for selection of dumped objects.

Use this by health reporter to indicate it supports port index based
selection of dump objects. Implement this selection mechanism in
devlink_nl_cmd_health_reporter_get_dump_one()

Example:
$ devlink health
pci/0000:08:00.0:
  reporter fw
    state healthy error 0 recover 0 auto_dump true
  reporter fw_fatal
    state healthy error 0 recover 0 grace_period 60000 auto_recover true auto_dump true
  reporter vnic
    state healthy error 0 recover 0
pci/0000:08:00.0/32768:
  reporter vnic
    state healthy error 0 recover 0
pci/0000:08:00.0/32769:
  reporter vnic
    state healthy error 0 recover 0
pci/0000:08:00.0/32770:
  reporter vnic
    state healthy error 0 recover 0
pci/0000:08:00.1:
  reporter fw
    state healthy error 0 recover 0 auto_dump true
  reporter fw_fatal
    state healthy error 0 recover 0 grace_period 60000 auto_recover true auto_dump true
  reporter vnic
    state healthy error 0 recover 0
pci/0000:08:00.1/98304:
  reporter vnic
    state healthy error 0 recover 0
pci/0000:08:00.1/98305:
  reporter vnic
    state healthy error 0 recover 0
pci/0000:08:00.1/98306:
  reporter vnic
    state healthy error 0 recover 0

$ devlink health show pci/0000:08:00.0
pci/0000:08:00.0:
  reporter fw
    state healthy error 0 recover 0 auto_dump true
  reporter fw_fatal
    state healthy error 0 recover 0 grace_period 60000 auto_recover true auto_dump true
  reporter vnic
    state healthy error 0 recover 0
pci/0000:08:00.0/32768:
  reporter vnic
    state healthy error 0 recover 0
pci/0000:08:00.0/32769:
  reporter vnic
    state healthy error 0 recover 0
pci/0000:08:00.0/32770:
  reporter vnic
    state healthy error 0 recover 0

$ devlink health show pci/0000:08:00.0/32768
pci/0000:08:00.0/32768:
  reporter vnic
    state healthy error 0 recover 0

The last command is possible because of this patch.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-13-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/health.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/net/devlink/health.c b/net/devlink/health.c
index b9b3e68d90430..a85bdec348011 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -390,12 +390,23 @@ static int devlink_nl_health_reporter_get_dump_one(struct sk_buff *msg,
 						   int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
 	struct devlink_health_reporter *reporter;
+	unsigned long port_index_end = ULONG_MAX;
+	struct nlattr **attrs = info->attrs;
+	unsigned long port_index_start = 0;
 	struct devlink_port *port;
 	unsigned long port_index;
 	int idx = 0;
 	int err;
 
+	if (attrs && attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		port_index_start = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]);
+		port_index_end = port_index_start;
+		flags |= NLM_F_DUMP_FILTERED;
+		goto per_port_dump;
+	}
+
 	list_for_each_entry(reporter, &devlink->reporter_list, list) {
 		if (idx < state->idx) {
 			idx++;
@@ -412,7 +423,9 @@ static int devlink_nl_health_reporter_get_dump_one(struct sk_buff *msg,
 		}
 		idx++;
 	}
-	xa_for_each(&devlink->ports, port_index, port) {
+per_port_dump:
+	xa_for_each_range(&devlink->ports, port_index, port,
+			  port_index_start, port_index_end) {
 		list_for_each_entry(reporter, &port->reporter_list, list) {
 			if (idx < state->idx) {
 				idx++;
-- 
GitLab


From 0149bca172622d802c0caff8cf0928fb0ded767b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 11 Aug 2023 17:57:14 +0200
Subject: [PATCH 1206/1806] netlink: specs: devlink: extend health reporter
 dump attributes by port index

Allow user to pass port index for health reporter dump request.

Re-generate the related code.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230811155714.1736405-14-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/devlink.yaml | 2 +-
 net/devlink/netlink_gen.c                | 5 +++--
 tools/net/ynl/generated/devlink-user.c   | 2 ++
 tools/net/ynl/generated/devlink-user.h   | 9 +++++++++
 4 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 6dbebeebd63e0..d1ebcd9271497 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -516,7 +516,7 @@ operations:
           attributes: *health-reporter-id-attrs
       dump:
         request:
-          attributes: *dev-id-attrs
+          attributes: *port-id-attrs
         reply: *health-reporter-get-reply
 
       # TODO: fill in the operations in between
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
index 5f3e980c6a7c8..467b7a431de1f 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -129,9 +129,10 @@ static const struct nla_policy devlink_health_reporter_get_do_nl_policy[DEVLINK_
 };
 
 /* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */
-static const struct nla_policy devlink_health_reporter_get_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+static const struct nla_policy devlink_health_reporter_get_dump_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
 };
 
 /* DEVLINK_CMD_TRAP_GET - do */
@@ -373,7 +374,7 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.cmd		= DEVLINK_CMD_HEALTH_REPORTER_GET,
 		.dumpit		= devlink_nl_health_reporter_get_dumpit,
 		.policy		= devlink_health_reporter_get_dump_nl_policy,
-		.maxattr	= DEVLINK_ATTR_DEV_NAME,
+		.maxattr	= DEVLINK_ATTR_PORT_INDEX,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c
index 80ee9d24eb163..3a8d8499fab6e 100644
--- a/tools/net/ynl/generated/devlink-user.c
+++ b/tools/net/ynl/generated/devlink-user.c
@@ -2079,6 +2079,8 @@ devlink_health_reporter_get_dump(struct ynl_sock *ys,
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
 	if (req->_present.dev_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h
index 12530f1795ca4..4b686d147613f 100644
--- a/tools/net/ynl/generated/devlink-user.h
+++ b/tools/net/ynl/generated/devlink-user.h
@@ -1242,10 +1242,12 @@ struct devlink_health_reporter_get_req_dump {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
+		__u32 port_index:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
+	__u32 port_index;
 };
 
 static inline struct devlink_health_reporter_get_req_dump *
@@ -1276,6 +1278,13 @@ devlink_health_reporter_get_req_dump_set_dev_name(struct devlink_health_reporter
 	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
+static inline void
+devlink_health_reporter_get_req_dump_set_port_index(struct devlink_health_reporter_get_req_dump *req,
+						    __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
 
 struct devlink_health_reporter_get_list {
 	struct devlink_health_reporter_get_list *next;
-- 
GitLab


From b608dd670bb69c89d5074685899d4c1089f57a16 Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Mon, 27 Feb 2023 13:57:00 -0800
Subject: [PATCH 1207/1806] net/mlx5: Consolidate devlink documentation in
 devlink/mlx5.rst

De-duplicate documentation by removing mellanox/mlx5/devlink.rst. Instead,
only use the generic devlink documentation directory to document mlx5
devlink parameters. Avoid providing general devlink tool usage information
in mlx5-specific documentation.

Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/devlink.rst        | 313 ------------------
 .../ethernet/mellanox/mlx5/index.rst          |   1 -
 Documentation/networking/devlink/mlx5.rst     | 179 ++++++++++
 3 files changed, 179 insertions(+), 314 deletions(-)
 delete mode 100644 Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst
deleted file mode 100644
index a4edf908b707c..0000000000000
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst
+++ /dev/null
@@ -1,313 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
-.. include:: <isonum.txt>
-
-=======
-Devlink
-=======
-
-:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-
-Contents
-========
-
-- `Info`_
-- `Parameters`_
-- `Health reporters`_
-
-Info
-====
-
-The devlink info reports the running and stored firmware versions on device.
-It also prints the device PSID which represents the HCA board type ID.
-
-User command example::
-
-   $ devlink dev info pci/0000:00:06.0
-      pci/0000:00:06.0:
-      driver mlx5_core
-      versions:
-         fixed:
-            fw.psid MT_0000000009
-         running:
-            fw.version 16.26.0100
-         stored:
-            fw.version 16.26.0100
-
-Parameters
-==========
-
-flow_steering_mode: Device flow steering mode
----------------------------------------------
-The flow steering mode parameter controls the flow steering mode of the driver.
-Two modes are supported:
-
-1. 'dmfs' - Device managed flow steering.
-2. 'smfs' - Software/Driver managed flow steering.
-
-In DMFS mode, the HW steering entities are created and managed through the
-Firmware.
-In SMFS mode, the HW steering entities are created and managed though by
-the driver directly into hardware without firmware intervention.
-
-SMFS mode is faster and provides better rule insertion rate compared to default DMFS mode.
-
-User command examples:
-
-- Set SMFS flow steering mode::
-
-    $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime
-
-- Read device flow steering mode::
-
-    $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode
-      pci/0000:06:00.0:
-      name flow_steering_mode type driver-specific
-      values:
-         cmode runtime value smfs
-
-enable_roce: RoCE enablement state
-----------------------------------
-If the device supports RoCE disablement, RoCE enablement state controls device
-support for RoCE capability. Otherwise, the control occurs in the driver stack.
-When RoCE is disabled at the driver level, only raw ethernet QPs are supported.
-
-To change RoCE enablement state, a user must change the driverinit cmode value
-and run devlink reload.
-
-User command examples:
-
-- Disable RoCE::
-
-    $ devlink dev param set pci/0000:06:00.0 name enable_roce value false cmode driverinit
-    $ devlink dev reload pci/0000:06:00.0
-
-- Read RoCE enablement state::
-
-    $ devlink dev param show pci/0000:06:00.0 name enable_roce
-      pci/0000:06:00.0:
-      name enable_roce type generic
-      values:
-         cmode driverinit value true
-
-esw_port_metadata: Eswitch port metadata state
-----------------------------------------------
-When applicable, disabling eswitch metadata can increase packet rate
-up to 20% depending on the use case and packet sizes.
-
-Eswitch port metadata state controls whether to internally tag packets with
-metadata. Metadata tagging must be enabled for multi-port RoCE, failover
-between representors and stacked devices.
-By default metadata is enabled on the supported devices in E-switch.
-Metadata is applicable only for E-switch in switchdev mode and
-users may disable it when NONE of the below use cases will be in use:
-
-1. HCA is in Dual/multi-port RoCE mode.
-2. VF/SF representor bonding (Usually used for Live migration)
-3. Stacked devices
-
-When metadata is disabled, the above use cases will fail to initialize if
-users try to enable them.
-
-- Show eswitch port metadata::
-
-    $ devlink dev param show pci/0000:06:00.0 name esw_port_metadata
-      pci/0000:06:00.0:
-        name esw_port_metadata type driver-specific
-          values:
-            cmode runtime value true
-
-- Disable eswitch port metadata::
-
-    $ devlink dev param set pci/0000:06:00.0 name esw_port_metadata value false cmode runtime
-
-- Change eswitch mode to switchdev mode where after choosing the metadata value::
-
-    $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev
-
-hairpin_num_queues: Number of hairpin queues
---------------------------------------------
-We refer to a TC NIC rule that involves forwarding as "hairpin".
-
-Hairpin queues are mlx5 hardware specific implementation for hardware
-forwarding of such packets.
-
-- Show the number of hairpin queues::
-
-    $ devlink dev param show pci/0000:06:00.0 name hairpin_num_queues
-      pci/0000:06:00.0:
-        name hairpin_num_queues type driver-specific
-          values:
-            cmode driverinit value 2
-
-- Change the number of hairpin queues::
-
-    $ devlink dev param set pci/0000:06:00.0 name hairpin_num_queues value 4 cmode driverinit
-
-hairpin_queue_size: Size of the hairpin queues
-----------------------------------------------
-Control the size of the hairpin queues.
-
-- Show the size of the hairpin queues::
-
-    $ devlink dev param show pci/0000:06:00.0 name hairpin_queue_size
-      pci/0000:06:00.0:
-        name hairpin_queue_size type driver-specific
-          values:
-            cmode driverinit value 1024
-
-- Change the size (in packets) of the hairpin queues::
-
-    $ devlink dev param set pci/0000:06:00.0 name hairpin_queue_size value 512 cmode driverinit
-
-Health reporters
-================
-
-tx reporter
------------
-The tx reporter is responsible for reporting and recovering of the following two error scenarios:
-
-- tx timeout
-    Report on kernel tx timeout detection.
-    Recover by searching lost interrupts.
-- tx error completion
-    Report on error tx completion.
-    Recover by flushing the tx queue and reset it.
-
-tx reporter also support on demand diagnose callback, on which it provides
-real time information of its send queues status.
-
-User commands examples:
-
-- Diagnose send queues status::
-
-    $ devlink health diagnose pci/0000:82:00.0 reporter tx
-
-.. note::
-   This command has valid output only when interface is up, otherwise the command has empty output.
-
-- Show number of tx errors indicated, number of recover flows ended successfully,
-  is autorecover enabled and graceful period from last recover::
-
-    $ devlink health show pci/0000:82:00.0 reporter tx
-
-rx reporter
------------
-The rx reporter is responsible for reporting and recovering of the following two error scenarios:
-
-- rx queues' initialization (population) timeout
-    Population of rx queues' descriptors on ring initialization is done
-    in napi context via triggering an irq. In case of a failure to get
-    the minimum amount of descriptors, a timeout would occur, and
-    descriptors could be recovered by polling the EQ (Event Queue).
-- rx completions with errors (reported by HW on interrupt context)
-    Report on rx completion error.
-    Recover (if needed) by flushing the related queue and reset it.
-
-rx reporter also supports on demand diagnose callback, on which it
-provides real time information of its receive queues' status.
-
-- Diagnose rx queues' status and corresponding completion queue::
-
-    $ devlink health diagnose pci/0000:82:00.0 reporter rx
-
-NOTE: This command has valid output only when interface is up. Otherwise, the command has empty output.
-
-- Show number of rx errors indicated, number of recover flows ended successfully,
-  is autorecover enabled, and graceful period from last recover::
-
-    $ devlink health show pci/0000:82:00.0 reporter rx
-
-fw reporter
------------
-The fw reporter implements `diagnose` and `dump` callbacks.
-It follows symptoms of fw error such as fw syndrome by triggering
-fw core dump and storing it into the dump buffer.
-The fw reporter diagnose command can be triggered any time by the user to check
-current fw status.
-
-User commands examples:
-
-- Check fw heath status::
-
-    $ devlink health diagnose pci/0000:82:00.0 reporter fw
-
-- Read FW core dump if already stored or trigger new one::
-
-    $ devlink health dump show pci/0000:82:00.0 reporter fw
-
-.. note::
-   This command can run only on the PF which has fw tracer ownership,
-   running it on other PF or any VF will return "Operation not permitted".
-
-fw fatal reporter
------------------
-The fw fatal reporter implements `dump` and `recover` callbacks.
-It follows fatal errors indications by CR-space dump and recover flow.
-The CR-space dump uses vsc interface which is valid even if the FW command
-interface is not functional, which is the case in most FW fatal errors.
-The recover function runs recover flow which reloads the driver and triggers fw
-reset if needed.
-On firmware error, the health buffer is dumped into the dmesg. The log
-level is derived from the error's severity (given in health buffer).
-
-User commands examples:
-
-- Run fw recover flow manually::
-
-    $ devlink health recover pci/0000:82:00.0 reporter fw_fatal
-
-- Read FW CR-space dump if already stored or trigger new one::
-
-    $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal
-
-.. note::
-   This command can run only on PF.
-
-vnic reporter
--------------
-The vnic reporter implements only the `diagnose` callback.
-It is responsible for querying the vnic diagnostic counters from fw and displaying
-them in realtime.
-
-Description of the vnic counters:
-
-- total_q_under_processor_handle
-        number of queues in an error state due to
-        an async error or errored command.
-- send_queue_priority_update_flow
-        number of QP/SQ priority/SL update events.
-- cq_overrun
-        number of times CQ entered an error state due to an overflow.
-- async_eq_overrun
-        number of times an EQ mapped to async events was overrun.
-        comp_eq_overrun number of times an EQ mapped to completion events was
-        overrun.
-- quota_exceeded_command
-        number of commands issued and failed due to quota exceeded.
-- invalid_command
-        number of commands issued and failed dues to any reason other than quota
-        exceeded.
-- nic_receive_steering_discard
-        number of packets that completed RX flow
-        steering but were discarded due to a mismatch in flow table.
-- generated_pkt_steering_fail
-	number of packets generated by the VNIC experiencing unexpected steering
-	failure (at any point in steering flow).
-- handled_pkt_steering_fail
-	number of packets handled by the VNIC experiencing unexpected steering
-	failure (at any point in steering flow owned by the VNIC, including the FDB
-	for the eswitch owner).
-
-User commands examples:
-
-- Diagnose PF/VF vnic counters::
-
-        $ devlink health diagnose pci/0000:82:00.1 reporter vnic
-
-- Diagnose representor vnic counters (performed by supplying devlink port of the
-  representor, which can be obtained via devlink port command)::
-
-        $ devlink health diagnose pci/0000:82:00.1/65537 reporter vnic
-
-.. note::
-   This command can run over all interfaces such as PF/VF and representor ports.
diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst
index 3fdcd6b61ccfa..581a91caa5795 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst
@@ -13,7 +13,6 @@ Contents:
    :maxdepth: 2
 
    kconfig
-   devlink
    switchdev
    tracepoints
    counters
diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 202798d6501e7..196a4bb28df1e 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -18,6 +18,11 @@ Parameters
    * - ``enable_roce``
      - driverinit
      - Type: Boolean
+
+       If the device supports RoCE disablement, RoCE enablement state controls
+       device support for RoCE capability. Otherwise, the control occurs in the
+       driver stack. When RoCE is disabled at the driver level, only raw
+       ethernet QPs are supported.
    * - ``io_eq_size``
      - driverinit
      - The range is between 64 and 4096.
@@ -48,6 +53,9 @@ parameters.
        * ``smfs`` Software managed flow steering. In SMFS mode, the HW
          steering entities are created and manage through the driver without
          firmware intervention.
+
+       SMFS mode is faster and provides better rule insertion rate compared to
+       default DMFS mode.
    * - ``fdb_large_groups``
      - u32
      - driverinit
@@ -71,7 +79,24 @@ parameters.
        deprecated.
 
        Default: disabled
+   * - ``esw_port_metadata``
+     - Boolean
+     - runtime
+     - When applicable, disabling eswitch metadata can increase packet rate up
+       to 20% depending on the use case and packet sizes.
+
+       Eswitch port metadata state controls whether to internally tag packets
+       with metadata. Metadata tagging must be enabled for multi-port RoCE,
+       failover between representors and stacked devices. By default metadata is
+       enabled on the supported devices in E-switch. Metadata is applicable only
+       for E-switch in switchdev mode and users may disable it when NONE of the
+       below use cases will be in use:
+       1. HCA is in Dual/multi-port RoCE mode.
+       2. VF/SF representor bonding (Usually used for Live migration)
+       3. Stacked devices
 
+       When metadata is disabled, the above use cases will fail to initialize if
+       users try to enable them.
    * - ``hairpin_num_queues``
      - u32
      - driverinit
@@ -104,3 +129,157 @@ The ``mlx5`` driver reports the following versions
    * - ``fw.version``
      - stored, running
      - Three digit major.minor.subminor firmware version number.
+
+Health reporters
+================
+
+tx reporter
+-----------
+The tx reporter is responsible for reporting and recovering of the following two error scenarios:
+
+- tx timeout
+    Report on kernel tx timeout detection.
+    Recover by searching lost interrupts.
+- tx error completion
+    Report on error tx completion.
+    Recover by flushing the tx queue and reset it.
+
+tx reporter also support on demand diagnose callback, on which it provides
+real time information of its send queues status.
+
+User commands examples:
+
+- Diagnose send queues status::
+
+    $ devlink health diagnose pci/0000:82:00.0 reporter tx
+
+.. note::
+   This command has valid output only when interface is up, otherwise the command has empty output.
+
+- Show number of tx errors indicated, number of recover flows ended successfully,
+  is autorecover enabled and graceful period from last recover::
+
+    $ devlink health show pci/0000:82:00.0 reporter tx
+
+rx reporter
+-----------
+The rx reporter is responsible for reporting and recovering of the following two error scenarios:
+
+- rx queues' initialization (population) timeout
+    Population of rx queues' descriptors on ring initialization is done
+    in napi context via triggering an irq. In case of a failure to get
+    the minimum amount of descriptors, a timeout would occur, and
+    descriptors could be recovered by polling the EQ (Event Queue).
+- rx completions with errors (reported by HW on interrupt context)
+    Report on rx completion error.
+    Recover (if needed) by flushing the related queue and reset it.
+
+rx reporter also supports on demand diagnose callback, on which it
+provides real time information of its receive queues' status.
+
+- Diagnose rx queues' status and corresponding completion queue::
+
+    $ devlink health diagnose pci/0000:82:00.0 reporter rx
+
+.. note::
+   This command has valid output only when interface is up. Otherwise, the command has empty output.
+
+- Show number of rx errors indicated, number of recover flows ended successfully,
+  is autorecover enabled, and graceful period from last recover::
+
+    $ devlink health show pci/0000:82:00.0 reporter rx
+
+fw reporter
+-----------
+The fw reporter implements `diagnose` and `dump` callbacks.
+It follows symptoms of fw error such as fw syndrome by triggering
+fw core dump and storing it into the dump buffer.
+The fw reporter diagnose command can be triggered any time by the user to check
+current fw status.
+
+User commands examples:
+
+- Check fw heath status::
+
+    $ devlink health diagnose pci/0000:82:00.0 reporter fw
+
+- Read FW core dump if already stored or trigger new one::
+
+    $ devlink health dump show pci/0000:82:00.0 reporter fw
+
+.. note::
+   This command can run only on the PF which has fw tracer ownership,
+   running it on other PF or any VF will return "Operation not permitted".
+
+fw fatal reporter
+-----------------
+The fw fatal reporter implements `dump` and `recover` callbacks.
+It follows fatal errors indications by CR-space dump and recover flow.
+The CR-space dump uses vsc interface which is valid even if the FW command
+interface is not functional, which is the case in most FW fatal errors.
+The recover function runs recover flow which reloads the driver and triggers fw
+reset if needed.
+On firmware error, the health buffer is dumped into the dmesg. The log
+level is derived from the error's severity (given in health buffer).
+
+User commands examples:
+
+- Run fw recover flow manually::
+
+    $ devlink health recover pci/0000:82:00.0 reporter fw_fatal
+
+- Read FW CR-space dump if already stored or trigger new one::
+
+    $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal
+
+.. note::
+   This command can run only on PF.
+
+vnic reporter
+-------------
+The vnic reporter implements only the `diagnose` callback.
+It is responsible for querying the vnic diagnostic counters from fw and displaying
+them in realtime.
+
+Description of the vnic counters:
+
+- total_q_under_processor_handle
+        number of queues in an error state due to
+        an async error or errored command.
+- send_queue_priority_update_flow
+        number of QP/SQ priority/SL update events.
+- cq_overrun
+        number of times CQ entered an error state due to an overflow.
+- async_eq_overrun
+        number of times an EQ mapped to async events was overrun.
+        comp_eq_overrun number of times an EQ mapped to completion events was
+        overrun.
+- quota_exceeded_command
+        number of commands issued and failed due to quota exceeded.
+- invalid_command
+        number of commands issued and failed dues to any reason other than quota
+        exceeded.
+- nic_receive_steering_discard
+        number of packets that completed RX flow
+        steering but were discarded due to a mismatch in flow table.
+- generated_pkt_steering_fail
+	number of packets generated by the VNIC experiencing unexpected steering
+	failure (at any point in steering flow).
+- handled_pkt_steering_fail
+	number of packets handled by the VNIC experiencing unexpected steering
+	failure (at any point in steering flow owned by the VNIC, including the FDB
+	for the eswitch owner).
+
+User commands examples:
+
+- Diagnose PF/VF vnic counters::
+
+        $ devlink health diagnose pci/0000:82:00.1 reporter vnic
+
+- Diagnose representor vnic counters (performed by supplying devlink port of the
+  representor, which can be obtained via devlink port command)::
+
+        $ devlink health diagnose pci/0000:82:00.1/65537 reporter vnic
+
+.. note::
+   This command can run over all interfaces such as PF/VF and representor ports.
-- 
GitLab


From 3178308ad4ca38955cad684d235153d4939f1fcd Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Tue, 2 May 2023 16:31:40 -0700
Subject: [PATCH 1208/1806] net/mlx5e: Make tx_port_ts logic resilient to
 out-of-order CQEs

Use a map structure for associating CQEs containing port timestamping
information with the appropriate skb. Track order of WQEs submitted using a
FIFO. Check if the corresponding port timestamping CQEs from the lookup
values in the FIFO are considered dropped due to time elapsed. Return the
lookup value to a freelist after consuming the skb. Reuse the freed lookup
in future WQE submission iterations.

The map structure uses an integer identifier for the key and returns an skb
corresponding to that identifier. Embed the integer identifier in the WQE
submitted to the WQ for the transmit path when the SQ is a PTP (port
timestamping) SQ. The embedded identifier can then be queried using a field
in the CQE of the corresponding port timestamping CQ. In the port
timestamping napi_poll context, the identifier is queried from the CQE
polled from CQ and used to lookup the corresponding skb from the WQE submit
path. The skb reference is removed from map and then embedded with the port
HW timestamp information from the CQE and eventually consumed.

The metadata freelist FIFO is an array containing integer identifiers that
can be pushed and popped in the FIFO. The purpose of this structure is
bookkeeping what identifier values can safely be used in a subsequent WQE
submission and should not contain identifiers that have still not been
reaped by processing a corresponding CQE completion on the port
timestamping CQ.

The ts_cqe_pending_list structure is a combination of an array and linked
list. The array is pre-populated with the nodes that will be added and
removed from the head of the linked list. Each node contains the unique
identifier value associated with the values submitted in the WQEs and
retrieved in the port timestamping CQEs. When a WQE is submitted, the node
in the array corresponding to the identifier popped from the metadata
freelist is added to the end of the CQE pending list and is marked as
"in-use". The node is removed from the linked list under two conditions.
The first condition is that the corresponding port timestamping CQE is
polled in the PTP napi_poll context. The second condition is that more than
a second has elapsed since the DMA timestamp value corresponding to the WQE
submission. When the first condition occurs, the "in-use" bit in the linked
list node is cleared, and the resources corresponding to the WQE submission
are then released. The second condition, however, indicates that the port
timestamping CQE will likely never be delivered. It's not impossible for
the device to post a CQE after an infinite amount of time though highly
improbable. In order to be resilient to this improbable case, resources
related to the corresponding WQE submission are still kept, the identifier
value is not returned to the freelist, and the "in-use" bit is cleared on
the node to indicate that it's no longer part of the linked list of "likely
to be delivered" port timestamping CQE identifiers. A count for the number
of port timestamping CQEs considered highly likely to never be delivered by
the device is maintained. This count gets decremented in the unlikely event
a port timestamping CQE considered unlikely to ever be delivered is polled
in the PTP napi_poll context.

Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/counters.rst       |   6 +
 .../net/ethernet/mellanox/mlx5/core/en/ptp.c  | 215 +++++++++++++-----
 .../net/ethernet/mellanox/mlx5/core/en/ptp.h  |  57 ++++-
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  |   3 +-
 .../ethernet/mellanox/mlx5/core/en_stats.c    |   4 +-
 .../ethernet/mellanox/mlx5/core/en_stats.h    |   4 +-
 .../net/ethernet/mellanox/mlx5/core/en_tx.c   |  28 ++-
 7 files changed, 236 insertions(+), 81 deletions(-)

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
index a395df9c27513..008e560e12b58 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
@@ -683,6 +683,12 @@ the software port.
        time protocol.
      - Error
 
+   * - `ptp_cq[i]_late_cqe`
+     - Number of times a CQE has been delivered on the PTP timestamping CQ when
+       the CQE was not expected since a certain amount of time had elapsed where
+       the device typically ensures not posting the CQE.
+     - Error
+
 .. [#ring_global] The corresponding ring and global counters do not share the
                   same name (i.e. do not follow the common naming scheme).
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index b0b429a0321ed..8680d21f3e7b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -5,6 +5,8 @@
 #include "en/txrx.h"
 #include "en/params.h"
 #include "en/fs_tt_redirect.h"
+#include <linux/list.h>
+#include <linux/spinlock.h>
 
 struct mlx5e_ptp_fs {
 	struct mlx5_flow_handle *l2_rule;
@@ -19,6 +21,48 @@ struct mlx5e_ptp_params {
 	struct mlx5e_rq_param rq_param;
 };
 
+struct mlx5e_ptp_port_ts_cqe_tracker {
+	u8 metadata_id;
+	bool inuse : 1;
+	struct list_head entry;
+};
+
+struct mlx5e_ptp_port_ts_cqe_list {
+	struct mlx5e_ptp_port_ts_cqe_tracker *nodes;
+	struct list_head tracker_list_head;
+	/* Sync list operations in xmit and napi_poll contexts */
+	spinlock_t tracker_list_lock;
+};
+
+static inline void
+mlx5e_ptp_port_ts_cqe_list_add(struct mlx5e_ptp_port_ts_cqe_list *list, u8 metadata)
+{
+	struct mlx5e_ptp_port_ts_cqe_tracker *tracker = &list->nodes[metadata];
+
+	WARN_ON_ONCE(tracker->inuse);
+	tracker->inuse = true;
+	spin_lock(&list->tracker_list_lock);
+	list_add_tail(&tracker->entry, &list->tracker_list_head);
+	spin_unlock(&list->tracker_list_lock);
+}
+
+static void
+mlx5e_ptp_port_ts_cqe_list_remove(struct mlx5e_ptp_port_ts_cqe_list *list, u8 metadata)
+{
+	struct mlx5e_ptp_port_ts_cqe_tracker *tracker = &list->nodes[metadata];
+
+	WARN_ON_ONCE(!tracker->inuse);
+	tracker->inuse = false;
+	spin_lock(&list->tracker_list_lock);
+	list_del(&tracker->entry);
+	spin_unlock(&list->tracker_list_lock);
+}
+
+void mlx5e_ptpsq_track_metadata(struct mlx5e_ptpsq *ptpsq, u8 metadata)
+{
+	mlx5e_ptp_port_ts_cqe_list_add(ptpsq->ts_cqe_pending_list, metadata);
+}
+
 struct mlx5e_skb_cb_hwtstamp {
 	ktime_t cqe_hwtstamp;
 	ktime_t port_hwtstamp;
@@ -79,75 +123,88 @@ void mlx5e_skb_cb_hwtstamp_handler(struct sk_buff *skb, int hwtstamp_type,
 	memset(skb->cb, 0, sizeof(struct mlx5e_skb_cb_hwtstamp));
 }
 
-#define PTP_WQE_CTR2IDX(val) ((val) & ptpsq->ts_cqe_ctr_mask)
-
-static bool mlx5e_ptp_ts_cqe_drop(struct mlx5e_ptpsq *ptpsq, u16 skb_ci, u16 skb_id)
+static struct sk_buff *
+mlx5e_ptp_metadata_map_lookup(struct mlx5e_ptp_metadata_map *map, u16 metadata)
 {
-	return (ptpsq->ts_cqe_ctr_mask && (skb_ci != skb_id));
+	return map->data[metadata];
 }
 
-static bool mlx5e_ptp_ts_cqe_ooo(struct mlx5e_ptpsq *ptpsq, u16 skb_id)
+static struct sk_buff *
+mlx5e_ptp_metadata_map_remove(struct mlx5e_ptp_metadata_map *map, u16 metadata)
 {
-	u16 skb_ci = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc);
-	u16 skb_pi = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_pc);
+	struct sk_buff *skb;
 
-	if (PTP_WQE_CTR2IDX(skb_id - skb_ci) >= PTP_WQE_CTR2IDX(skb_pi - skb_ci))
-		return true;
+	skb = map->data[metadata];
+	map->data[metadata] = NULL;
 
-	return false;
+	return skb;
 }
 
-static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_ci,
-					     u16 skb_id, int budget)
+static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq,
+						 ktime_t port_tstamp)
 {
-	struct skb_shared_hwtstamps hwts = {};
-	struct sk_buff *skb;
+	struct mlx5e_ptp_port_ts_cqe_list *cqe_list = ptpsq->ts_cqe_pending_list;
+	ktime_t timeout = ns_to_ktime(MLX5E_PTP_TS_CQE_UNDELIVERED_TIMEOUT);
+	struct mlx5e_ptp_metadata_map *metadata_map = &ptpsq->metadata_map;
+	struct mlx5e_ptp_port_ts_cqe_tracker *pos, *n;
+
+	spin_lock(&cqe_list->tracker_list_lock);
+	list_for_each_entry_safe(pos, n, &cqe_list->tracker_list_head, entry) {
+		struct sk_buff *skb =
+			mlx5e_ptp_metadata_map_lookup(metadata_map, pos->metadata_id);
+		ktime_t dma_tstamp = mlx5e_skb_cb_get_hwts(skb)->cqe_hwtstamp;
 
-	ptpsq->cq_stats->resync_event++;
+		if (!dma_tstamp ||
+		    ktime_after(ktime_add(dma_tstamp, timeout), port_tstamp))
+			break;
 
-	while (skb_ci != skb_id) {
-		skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo);
-		hwts.hwtstamp = mlx5e_skb_cb_get_hwts(skb)->cqe_hwtstamp;
-		skb_tstamp_tx(skb, &hwts);
-		ptpsq->cq_stats->resync_cqe++;
-		napi_consume_skb(skb, budget);
-		skb_ci = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc);
+		metadata_map->undelivered_counter++;
+		WARN_ON_ONCE(!pos->inuse);
+		pos->inuse = false;
+		list_del(&pos->entry);
 	}
+	spin_unlock(&cqe_list->tracker_list_lock);
 }
 
+#define PTP_WQE_CTR2IDX(val) ((val) & ptpsq->ts_cqe_ctr_mask)
+
 static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
 				    struct mlx5_cqe64 *cqe,
 				    int budget)
 {
-	u16 skb_id = PTP_WQE_CTR2IDX(be16_to_cpu(cqe->wqe_counter));
-	u16 skb_ci = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc);
+	struct mlx5e_ptp_port_ts_cqe_list *pending_cqe_list = ptpsq->ts_cqe_pending_list;
+	u8 metadata_id = PTP_WQE_CTR2IDX(be16_to_cpu(cqe->wqe_counter));
+	bool is_err_cqe = !!MLX5E_RX_ERR_CQE(cqe);
 	struct mlx5e_txqsq *sq = &ptpsq->txqsq;
 	struct sk_buff *skb;
 	ktime_t hwtstamp;
 
-	if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
-		skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo);
-		ptpsq->cq_stats->err_cqe++;
-		goto out;
+	if (likely(pending_cqe_list->nodes[metadata_id].inuse)) {
+		mlx5e_ptp_port_ts_cqe_list_remove(pending_cqe_list, metadata_id);
+	} else {
+		/* Reclaim space in the unlikely event CQE was delivered after
+		 * marking it late.
+		 */
+		ptpsq->metadata_map.undelivered_counter--;
+		ptpsq->cq_stats->late_cqe++;
 	}
 
-	if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_ci, skb_id)) {
-		if (mlx5e_ptp_ts_cqe_ooo(ptpsq, skb_id)) {
-			/* already handled by a previous resync */
-			ptpsq->cq_stats->ooo_cqe_drop++;
-			return;
-		}
-		mlx5e_ptp_skb_fifo_ts_cqe_resync(ptpsq, skb_ci, skb_id, budget);
+	skb = mlx5e_ptp_metadata_map_remove(&ptpsq->metadata_map, metadata_id);
+
+	if (unlikely(is_err_cqe)) {
+		ptpsq->cq_stats->err_cqe++;
+		goto out;
 	}
 
-	skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo);
 	hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, get_cqe_ts(cqe));
 	mlx5e_skb_cb_hwtstamp_handler(skb, MLX5E_SKB_CB_PORT_HWTSTAMP,
 				      hwtstamp, ptpsq->cq_stats);
 	ptpsq->cq_stats->cqe++;
 
+	mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp);
 out:
 	napi_consume_skb(skb, budget);
+	mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, metadata_id);
 }
 
 static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
@@ -291,36 +348,78 @@ static void mlx5e_ptp_destroy_sq(struct mlx5_core_dev *mdev, u32 sqn)
 
 static int mlx5e_ptp_alloc_traffic_db(struct mlx5e_ptpsq *ptpsq, int numa)
 {
-	int wq_sz = mlx5_wq_cyc_get_size(&ptpsq->txqsq.wq);
-	struct mlx5_core_dev *mdev = ptpsq->txqsq.mdev;
+	struct mlx5e_ptp_metadata_fifo *metadata_freelist = &ptpsq->metadata_freelist;
+	struct mlx5e_ptp_metadata_map *metadata_map = &ptpsq->metadata_map;
+	struct mlx5e_ptp_port_ts_cqe_list *cqe_list;
+	int db_sz;
+	int md;
 
-	ptpsq->skb_fifo.fifo = kvzalloc_node(array_size(wq_sz, sizeof(*ptpsq->skb_fifo.fifo)),
-					     GFP_KERNEL, numa);
-	if (!ptpsq->skb_fifo.fifo)
+	cqe_list = kvzalloc_node(sizeof(*ptpsq->ts_cqe_pending_list), GFP_KERNEL, numa);
+	if (!cqe_list)
 		return -ENOMEM;
+	ptpsq->ts_cqe_pending_list = cqe_list;
+
+	db_sz = min_t(u32, mlx5_wq_cyc_get_size(&ptpsq->txqsq.wq),
+		      1 << MLX5_CAP_GEN_2(ptpsq->txqsq.mdev,
+					  ts_cqe_metadata_size2wqe_counter));
+	ptpsq->ts_cqe_ctr_mask = db_sz - 1;
+
+	cqe_list->nodes = kvzalloc_node(array_size(db_sz, sizeof(*cqe_list->nodes)),
+					GFP_KERNEL, numa);
+	if (!cqe_list->nodes)
+		goto free_cqe_list;
+	INIT_LIST_HEAD(&cqe_list->tracker_list_head);
+	spin_lock_init(&cqe_list->tracker_list_lock);
+
+	metadata_freelist->data =
+		kvzalloc_node(array_size(db_sz, sizeof(*metadata_freelist->data)),
+			      GFP_KERNEL, numa);
+	if (!metadata_freelist->data)
+		goto free_cqe_list_nodes;
+	metadata_freelist->mask = ptpsq->ts_cqe_ctr_mask;
+
+	for (md = 0; md < db_sz; ++md) {
+		cqe_list->nodes[md].metadata_id = md;
+		metadata_freelist->data[md] = md;
+	}
+	metadata_freelist->pc = db_sz;
+
+	metadata_map->data =
+		kvzalloc_node(array_size(db_sz, sizeof(*metadata_map->data)),
+			      GFP_KERNEL, numa);
+	if (!metadata_map->data)
+		goto free_metadata_freelist;
+	metadata_map->capacity = db_sz;
 
-	ptpsq->skb_fifo.pc   = &ptpsq->skb_fifo_pc;
-	ptpsq->skb_fifo.cc   = &ptpsq->skb_fifo_cc;
-	ptpsq->skb_fifo.mask = wq_sz - 1;
-	if (MLX5_CAP_GEN_2(mdev, ts_cqe_metadata_size2wqe_counter))
-		ptpsq->ts_cqe_ctr_mask =
-			(1 << MLX5_CAP_GEN_2(mdev, ts_cqe_metadata_size2wqe_counter)) - 1;
 	return 0;
+
+free_metadata_freelist:
+	kvfree(metadata_freelist->data);
+free_cqe_list_nodes:
+	kvfree(cqe_list->nodes);
+free_cqe_list:
+	kvfree(cqe_list);
+	return -ENOMEM;
 }
 
-static void mlx5e_ptp_drain_skb_fifo(struct mlx5e_skb_fifo *skb_fifo)
+static void mlx5e_ptp_drain_metadata_map(struct mlx5e_ptp_metadata_map *map)
 {
-	while (*skb_fifo->pc != *skb_fifo->cc) {
-		struct sk_buff *skb = mlx5e_skb_fifo_pop(skb_fifo);
+	int idx;
+
+	for (idx = 0; idx < map->capacity; ++idx) {
+		struct sk_buff *skb = map->data[idx];
 
 		dev_kfree_skb_any(skb);
 	}
 }
 
-static void mlx5e_ptp_free_traffic_db(struct mlx5e_skb_fifo *skb_fifo)
+static void mlx5e_ptp_free_traffic_db(struct mlx5e_ptpsq *ptpsq)
 {
-	mlx5e_ptp_drain_skb_fifo(skb_fifo);
-	kvfree(skb_fifo->fifo);
+	mlx5e_ptp_drain_metadata_map(&ptpsq->metadata_map);
+	kvfree(ptpsq->metadata_map.data);
+	kvfree(ptpsq->metadata_freelist.data);
+	kvfree(ptpsq->ts_cqe_pending_list->nodes);
+	kvfree(ptpsq->ts_cqe_pending_list);
 }
 
 static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
@@ -348,8 +447,7 @@ static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
 	if (err)
 		goto err_free_txqsq;
 
-	err = mlx5e_ptp_alloc_traffic_db(ptpsq,
-					 dev_to_node(mlx5_core_dma_dev(c->mdev)));
+	err = mlx5e_ptp_alloc_traffic_db(ptpsq, dev_to_node(mlx5_core_dma_dev(c->mdev)));
 	if (err)
 		goto err_free_txqsq;
 
@@ -366,7 +464,7 @@ static void mlx5e_ptp_close_txqsq(struct mlx5e_ptpsq *ptpsq)
 	struct mlx5e_txqsq *sq = &ptpsq->txqsq;
 	struct mlx5_core_dev *mdev = sq->mdev;
 
-	mlx5e_ptp_free_traffic_db(&ptpsq->skb_fifo);
+	mlx5e_ptp_free_traffic_db(ptpsq);
 	cancel_work_sync(&sq->recover_work);
 	mlx5e_ptp_destroy_sq(mdev, sq->sqn);
 	mlx5e_free_txqsq_descs(sq);
@@ -534,7 +632,10 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c,
 
 	/* SQ */
 	if (test_bit(MLX5E_PTP_STATE_TX, c->state)) {
-		params->log_sq_size = orig->log_sq_size;
+		params->log_sq_size =
+			min(MLX5_CAP_GEN_2(c->mdev, ts_cqe_metadata_size2wqe_counter),
+			    MLX5E_PTP_MAX_LOG_SQ_SIZE);
+		params->log_sq_size = min(params->log_sq_size, orig->log_sq_size);
 		mlx5e_ptp_build_sq_param(c->mdev, params, &cparams->txq_sq_param);
 	}
 	/* RQ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index cc7efde88ac3c..7c5597d4589df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -7,18 +7,36 @@
 #include "en.h"
 #include "en_stats.h"
 #include "en/txrx.h"
+#include <linux/ktime.h>
 #include <linux/ptp_classify.h>
+#include <linux/time64.h>
 
 #define MLX5E_PTP_CHANNEL_IX 0
+#define MLX5E_PTP_MAX_LOG_SQ_SIZE (8U)
+#define MLX5E_PTP_TS_CQE_UNDELIVERED_TIMEOUT (1 * NSEC_PER_SEC)
+
+struct mlx5e_ptp_metadata_fifo {
+	u8  cc;
+	u8  pc;
+	u8  mask;
+	u8  *data;
+};
+
+struct mlx5e_ptp_metadata_map {
+	u16             undelivered_counter;
+	u16             capacity;
+	struct sk_buff  **data;
+};
 
 struct mlx5e_ptpsq {
 	struct mlx5e_txqsq       txqsq;
 	struct mlx5e_cq          ts_cq;
-	u16                      skb_fifo_cc;
-	u16                      skb_fifo_pc;
-	struct mlx5e_skb_fifo    skb_fifo;
 	struct mlx5e_ptp_cq_stats *cq_stats;
 	u16                      ts_cqe_ctr_mask;
+
+	struct mlx5e_ptp_port_ts_cqe_list  *ts_cqe_pending_list;
+	struct mlx5e_ptp_metadata_fifo     metadata_freelist;
+	struct mlx5e_ptp_metadata_map      metadata_map;
 };
 
 enum {
@@ -69,12 +87,35 @@ static inline bool mlx5e_use_ptpsq(struct sk_buff *skb)
 		fk.ports.dst == htons(PTP_EV_PORT));
 }
 
-static inline bool mlx5e_ptpsq_fifo_has_room(struct mlx5e_txqsq *sq)
+static inline void mlx5e_ptp_metadata_fifo_push(struct mlx5e_ptp_metadata_fifo *fifo, u8 metadata)
 {
-	if (!sq->ptpsq)
-		return true;
+	fifo->data[fifo->mask & fifo->pc++] = metadata;
+}
+
+static inline u8
+mlx5e_ptp_metadata_fifo_pop(struct mlx5e_ptp_metadata_fifo *fifo)
+{
+	return fifo->data[fifo->mask & fifo->cc++];
+}
 
-	return mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo);
+static inline void
+mlx5e_ptp_metadata_map_put(struct mlx5e_ptp_metadata_map *map,
+			   struct sk_buff *skb, u8 metadata)
+{
+	WARN_ON_ONCE(map->data[metadata]);
+	map->data[metadata] = skb;
+}
+
+static inline bool mlx5e_ptpsq_metadata_freelist_empty(struct mlx5e_ptpsq *ptpsq)
+{
+	struct mlx5e_ptp_metadata_fifo *freelist;
+
+	if (likely(!ptpsq))
+		return false;
+
+	freelist = &ptpsq->metadata_freelist;
+
+	return freelist->pc == freelist->cc;
 }
 
 int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
@@ -89,6 +130,8 @@ void mlx5e_ptp_free_rx_fs(struct mlx5e_flow_steering *fs,
 			  const struct mlx5e_profile *profile);
 int mlx5e_ptp_rx_manage_fs(struct mlx5e_priv *priv, bool set);
 
+void mlx5e_ptpsq_track_metadata(struct mlx5e_ptpsq *ptpsq, u8 metadata);
+
 enum {
 	MLX5E_SKB_CB_CQE_HWTSTAMP  = BIT(0),
 	MLX5E_SKB_CB_PORT_HWTSTAMP = BIT(1),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 04195a673a6be..dff02434ff458 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -2061,7 +2061,8 @@ static int set_pflag_tx_port_ts(struct net_device *netdev, bool enable)
 	struct mlx5e_params new_params;
 	int err;
 
-	if (!MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn))
+	if (!MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn) ||
+	    !MLX5_CAP_GEN_2(mdev, ts_cqe_metadata_size2wqe_counter))
 		return -EOPNOTSUPP;
 
 	/* Don't allow changing the PTP state if HTB offload is active, because
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 07b84d668fcc0..52141729444e1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -2142,9 +2142,7 @@ static const struct counter_desc ptp_cq_stats_desc[] = {
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, err_cqe) },
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort) },
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort_abs_diff_ns) },
-	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_cqe) },
-	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_event) },
-	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, ooo_cqe_drop) },
+	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, late_cqe) },
 };
 
 static const struct counter_desc ptp_rq_stats_desc[] = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 1ff8a06027dcf..409e9a47e4333 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -449,9 +449,7 @@ struct mlx5e_ptp_cq_stats {
 	u64 err_cqe;
 	u64 abort;
 	u64 abort_abs_diff_ns;
-	u64 resync_cqe;
-	u64 resync_event;
-	u64 ooo_cqe_drop;
+	u64 late_cqe;
 };
 
 struct mlx5e_rep_stats {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index c7eb6b238c2ba..d41435c22ce56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -372,7 +372,7 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		     const struct mlx5e_tx_attr *attr,
 		     const struct mlx5e_tx_wqe_attr *wqe_attr, u8 num_dma,
 		     struct mlx5e_tx_wqe_info *wi, struct mlx5_wqe_ctrl_seg *cseg,
-		     bool xmit_more)
+		     struct mlx5_wqe_eth_seg *eseg, bool xmit_more)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	bool send_doorbell;
@@ -394,11 +394,16 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 
 	mlx5e_tx_check_stop(sq);
 
-	if (unlikely(sq->ptpsq)) {
+	if (unlikely(sq->ptpsq &&
+		     (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) {
+		u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata);
+
 		mlx5e_skb_cb_hwtstamp_init(skb);
-		mlx5e_skb_fifo_push(&sq->ptpsq->skb_fifo, skb);
+		mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index);
+		mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb,
+					   metadata_index);
 		if (!netif_tx_queue_stopped(sq->txq) &&
-		    !mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo)) {
+		    mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) {
 			netif_tx_stop_queue(sq->txq);
 			sq->stats->stopped++;
 		}
@@ -483,13 +488,16 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	if (unlikely(num_dma < 0))
 		goto err_drop;
 
-	mlx5e_txwqe_complete(sq, skb, attr, wqe_attr, num_dma, wi, cseg, xmit_more);
+	mlx5e_txwqe_complete(sq, skb, attr, wqe_attr, num_dma, wi, cseg, eseg, xmit_more);
 
 	return;
 
 err_drop:
 	stats->dropped++;
 	dev_kfree_skb_any(skb);
+	if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
+		mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist,
+					     be32_to_cpu(eseg->flow_table_metadata));
 	mlx5e_tx_flush(sq);
 }
 
@@ -645,9 +653,9 @@ void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq)
 static void mlx5e_cqe_ts_id_eseg(struct mlx5e_ptpsq *ptpsq, struct sk_buff *skb,
 				 struct mlx5_wqe_eth_seg *eseg)
 {
-	if (ptpsq->ts_cqe_ctr_mask && unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
-		eseg->flow_table_metadata = cpu_to_be32(ptpsq->skb_fifo_pc &
-							ptpsq->ts_cqe_ctr_mask);
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
+		eseg->flow_table_metadata =
+			cpu_to_be32(mlx5e_ptp_metadata_fifo_pop(&ptpsq->metadata_freelist));
 }
 
 static void mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
@@ -766,7 +774,7 @@ void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq)
 {
 	if (netif_tx_queue_stopped(sq->txq) &&
 	    mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) &&
-	    mlx5e_ptpsq_fifo_has_room(sq) &&
+	    !mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq) &&
 	    !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
 		netif_tx_wake_queue(sq->txq);
 		sq->stats->wake++;
@@ -1031,7 +1039,7 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	if (unlikely(num_dma < 0))
 		goto err_drop;
 
-	mlx5e_txwqe_complete(sq, skb, &attr, &wqe_attr, num_dma, wi, cseg, xmit_more);
+	mlx5e_txwqe_complete(sq, skb, &attr, &wqe_attr, num_dma, wi, cseg, eseg, xmit_more);
 
 	return;
 
-- 
GitLab


From 53b836a44db4259b94ffcfff321fb3d63f976b76 Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Tue, 8 Aug 2023 21:10:21 -0700
Subject: [PATCH 1209/1806] net/mlx5e: Add recovery flow for tx devlink health
 reporter for unhealthy PTP SQ

A new check for the tx devlink health reporter is introduced for
determining when the PTP port timestamping SQ is considered unhealthy. If
there are enough CQEs considered never to be delivered, the space that can
be utilized on the SQ decreases significantly, impacting performance and
usability of the SQ. The health reporter is triggered when the number of
likely never delivered port timestamping CQEs that utilize the space of the
PTP SQ is greater than 93.75% of the total capacity of the SQ. A devlink
health reporter recover method is also provided for this specific TX error
context that restarts the PTP SQ.

Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 Documentation/networking/devlink/mlx5.rst     |  5 +-
 .../ethernet/mellanox/mlx5/core/en/health.h   |  1 +
 .../net/ethernet/mellanox/mlx5/core/en/ptp.c  | 22 +++++++
 .../net/ethernet/mellanox/mlx5/core/en/ptp.h  |  2 +
 .../mellanox/mlx5/core/en/reporter_tx.c       | 65 +++++++++++++++++++
 5 files changed, 94 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 196a4bb28df1e..702f204a3dbd3 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -135,7 +135,7 @@ Health reporters
 
 tx reporter
 -----------
-The tx reporter is responsible for reporting and recovering of the following two error scenarios:
+The tx reporter is responsible for reporting and recovering of the following three error scenarios:
 
 - tx timeout
     Report on kernel tx timeout detection.
@@ -143,6 +143,9 @@ The tx reporter is responsible for reporting and recovering of the following two
 - tx error completion
     Report on error tx completion.
     Recover by flushing the tx queue and reset it.
+- tx PTP port timestamping CQ unhealthy
+    Report too many CQEs never delivered on port ts CQ.
+    Recover by flushing and re-creating all PTP channels.
 
 tx reporter also support on demand diagnose callback, on which it provides
 real time information of its send queues status.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index 0107e4e73bb06..415840c3ef84f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -18,6 +18,7 @@ void mlx5e_reporter_tx_create(struct mlx5e_priv *priv);
 void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv);
 void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq);
 int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq);
+void mlx5e_reporter_tx_ptpsq_unhealthy(struct mlx5e_ptpsq *ptpsq);
 
 int mlx5e_health_cq_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg);
 int mlx5e_health_cq_common_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index 8680d21f3e7b0..bb11e644d24f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2020 Mellanox Technologies
 
 #include "en/ptp.h"
+#include "en/health.h"
 #include "en/txrx.h"
 #include "en/params.h"
 #include "en/fs_tt_redirect.h"
@@ -140,6 +141,12 @@ mlx5e_ptp_metadata_map_remove(struct mlx5e_ptp_metadata_map *map, u16 metadata)
 	return skb;
 }
 
+static bool mlx5e_ptp_metadata_map_unhealthy(struct mlx5e_ptp_metadata_map *map)
+{
+	/* Considered beginning unhealthy state if size * 15 / 2^4 cannot be reclaimed. */
+	return map->undelivered_counter > (map->capacity >> 4) * 15;
+}
+
 static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq,
 						 ktime_t port_tstamp)
 {
@@ -205,6 +212,9 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
 out:
 	napi_consume_skb(skb, budget);
 	mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, metadata_id);
+	if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) &&
+	    !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
+		queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work);
 }
 
 static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
@@ -422,6 +432,14 @@ static void mlx5e_ptp_free_traffic_db(struct mlx5e_ptpsq *ptpsq)
 	kvfree(ptpsq->ts_cqe_pending_list);
 }
 
+static void mlx5e_ptpsq_unhealthy_work(struct work_struct *work)
+{
+	struct mlx5e_ptpsq *ptpsq =
+		container_of(work, struct mlx5e_ptpsq, report_unhealthy_work);
+
+	mlx5e_reporter_tx_ptpsq_unhealthy(ptpsq);
+}
+
 static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
 				int txq_ix, struct mlx5e_ptp_params *cparams,
 				int tc, struct mlx5e_ptpsq *ptpsq)
@@ -451,6 +469,8 @@ static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
 	if (err)
 		goto err_free_txqsq;
 
+	INIT_WORK(&ptpsq->report_unhealthy_work, mlx5e_ptpsq_unhealthy_work);
+
 	return 0;
 
 err_free_txqsq:
@@ -464,6 +484,8 @@ static void mlx5e_ptp_close_txqsq(struct mlx5e_ptpsq *ptpsq)
 	struct mlx5e_txqsq *sq = &ptpsq->txqsq;
 	struct mlx5_core_dev *mdev = sq->mdev;
 
+	if (current_work() != &ptpsq->report_unhealthy_work)
+		cancel_work_sync(&ptpsq->report_unhealthy_work);
 	mlx5e_ptp_free_traffic_db(ptpsq);
 	cancel_work_sync(&sq->recover_work);
 	mlx5e_ptp_destroy_sq(mdev, sq->sqn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index 7c5597d4589df..7b700d0f956a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -10,6 +10,7 @@
 #include <linux/ktime.h>
 #include <linux/ptp_classify.h>
 #include <linux/time64.h>
+#include <linux/workqueue.h>
 
 #define MLX5E_PTP_CHANNEL_IX 0
 #define MLX5E_PTP_MAX_LOG_SQ_SIZE (8U)
@@ -34,6 +35,7 @@ struct mlx5e_ptpsq {
 	struct mlx5e_ptp_cq_stats *cq_stats;
 	u16                      ts_cqe_ctr_mask;
 
+	struct work_struct                 report_unhealthy_work;
 	struct mlx5e_ptp_port_ts_cqe_list  *ts_cqe_pending_list;
 	struct mlx5e_ptp_metadata_fifo     metadata_freelist;
 	struct mlx5e_ptp_metadata_map      metadata_map;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index b35ff289af492..ff8242f67c545 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -164,6 +164,43 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx)
 	return err;
 }
 
+static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
+{
+	struct mlx5e_ptpsq *ptpsq = ctx;
+	struct mlx5e_channels *chs;
+	struct net_device *netdev;
+	struct mlx5e_priv *priv;
+	int carrier_ok;
+	int err;
+
+	if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &ptpsq->txqsq.state))
+		return 0;
+
+	priv = ptpsq->txqsq.priv;
+
+	mutex_lock(&priv->state_lock);
+	chs = &priv->channels;
+	netdev = priv->netdev;
+
+	carrier_ok = netif_carrier_ok(netdev);
+	netif_carrier_off(netdev);
+
+	mlx5e_deactivate_priv_channels(priv);
+
+	mlx5e_ptp_close(chs->ptp);
+	err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp);
+
+	mlx5e_activate_priv_channels(priv);
+
+	/* return carrier back if needed */
+	if (carrier_ok)
+		netif_carrier_on(netdev);
+
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
 /* state lock cannot be grabbed within this function.
  * It can cause a dead lock or a read-after-free.
  */
@@ -516,6 +553,15 @@ static int mlx5e_tx_reporter_timeout_dump(struct mlx5e_priv *priv, struct devlin
 	return mlx5e_tx_reporter_dump_sq(priv, fmsg, to_ctx->sq);
 }
 
+static int mlx5e_tx_reporter_ptpsq_unhealthy_dump(struct mlx5e_priv *priv,
+						  struct devlink_fmsg *fmsg,
+						  void *ctx)
+{
+	struct mlx5e_ptpsq *ptpsq = ctx;
+
+	return mlx5e_tx_reporter_dump_sq(priv, fmsg, &ptpsq->txqsq);
+}
+
 static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv,
 					  struct devlink_fmsg *fmsg)
 {
@@ -621,6 +667,25 @@ int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq)
 	return to_ctx.status;
 }
 
+void mlx5e_reporter_tx_ptpsq_unhealthy(struct mlx5e_ptpsq *ptpsq)
+{
+	struct mlx5e_ptp_metadata_map *map = &ptpsq->metadata_map;
+	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+	struct mlx5e_txqsq *txqsq = &ptpsq->txqsq;
+	struct mlx5e_cq *ts_cq = &ptpsq->ts_cq;
+	struct mlx5e_priv *priv = txqsq->priv;
+	struct mlx5e_err_ctx err_ctx = {};
+
+	err_ctx.ctx = ptpsq;
+	err_ctx.recover = mlx5e_tx_reporter_ptpsq_unhealthy_recover;
+	err_ctx.dump = mlx5e_tx_reporter_ptpsq_unhealthy_dump;
+	snprintf(err_str, sizeof(err_str),
+		 "Unhealthy TX port TS queue: %d, SQ: 0x%x, CQ: 0x%x, Undelivered CQEs: %u Map Capacity: %u",
+		 txqsq->ch_ix, txqsq->sqn, ts_cq->mcq.cqn, map->undelivered_counter, map->capacity);
+
+	mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx);
+}
+
 static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = {
 		.name = "tx",
 		.recover = mlx5e_tx_reporter_recover,
-- 
GitLab


From 6486c0f44ed8e91073c1b08e83075e3832618ae5 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 13 Jul 2023 14:54:57 +0300
Subject: [PATCH 1210/1806] net/mlx5: Expose max possible SFs via devlink
 resource

Introduce devlink resource for exposing max possible SFs on mlx5
devices.

For example:
$ devlink resource show pci/0000:00:0b.0
pci/0000:00:0b.0:
  name max_local_SFs size 5 unit entry dpipe_tables none
  name max_external_SFs size 0 unit entry dpipe_tables none

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/devlink.h |  8 ++++
 .../ethernet/mellanox/mlx5/core/sf/hw_table.c | 44 +++++++++++++++++--
 2 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
index defba5bd91d9c..961f75da62270 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -6,6 +6,14 @@
 
 #include <net/devlink.h>
 
+enum mlx5_devlink_resource_id {
+	MLX5_DL_RES_MAX_LOCAL_SFS = 1,
+	MLX5_DL_RES_MAX_EXTERNAL_SFS,
+
+	__MLX5_ID_RES_MAX,
+	MLX5_ID_RES_MAX = __MLX5_ID_RES_MAX - 1,
+};
+
 enum mlx5_devlink_param_id {
 	MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
index 17aa348989cbd..c4daeaaafeadd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -9,6 +9,7 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 #include "diag/sf_tracepoint.h"
+#include "devlink.h"
 
 struct mlx5_sf_hw {
 	u32 usr_sfnum;
@@ -243,6 +244,32 @@ static void mlx5_sf_hw_table_hwc_cleanup(struct mlx5_sf_hwc_table *hwc)
 	kfree(hwc->sfs);
 }
 
+static void mlx5_sf_hw_table_res_unregister(struct mlx5_core_dev *dev)
+{
+	devl_resources_unregister(priv_to_devlink(dev));
+}
+
+static int mlx5_sf_hw_table_res_register(struct mlx5_core_dev *dev, u16 max_fn,
+					 u16 max_ext_fn)
+{
+	struct devlink_resource_size_params size_params;
+	struct devlink *devlink = priv_to_devlink(dev);
+	int err;
+
+	devlink_resource_size_params_init(&size_params, max_fn, max_fn, 1,
+					  DEVLINK_RESOURCE_UNIT_ENTRY);
+	err = devl_resource_register(devlink, "max_local_SFs", max_fn, MLX5_DL_RES_MAX_LOCAL_SFS,
+				     DEVLINK_RESOURCE_ID_PARENT_TOP, &size_params);
+	if (err)
+		return err;
+
+	devlink_resource_size_params_init(&size_params, max_ext_fn, max_ext_fn, 1,
+					  DEVLINK_RESOURCE_UNIT_ENTRY);
+	return devl_resource_register(devlink, "max_external_SFs", max_ext_fn,
+				      MLX5_DL_RES_MAX_EXTERNAL_SFS, DEVLINK_RESOURCE_ID_PARENT_TOP,
+				      &size_params);
+}
+
 int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_sf_hw_table *table;
@@ -262,12 +289,17 @@ int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
 	if (err)
 		return err;
 
+	if (mlx5_sf_hw_table_res_register(dev, max_fn, max_ext_fn))
+		mlx5_core_dbg(dev, "failed to register max SFs resources");
+
 	if (!max_fn && !max_ext_fn)
 		return 0;
 
 	table = kzalloc(sizeof(*table), GFP_KERNEL);
-	if (!table)
-		return -ENOMEM;
+	if (!table) {
+		err = -ENOMEM;
+		goto alloc_err;
+	}
 
 	mutex_init(&table->table_lock);
 	table->dev = dev;
@@ -291,6 +323,8 @@ ext_err:
 table_err:
 	mutex_destroy(&table->table_lock);
 	kfree(table);
+alloc_err:
+	mlx5_sf_hw_table_res_unregister(dev);
 	return err;
 }
 
@@ -299,12 +333,14 @@ void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
 	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
 
 	if (!table)
-		return;
+		goto res_unregister;
 
-	mutex_destroy(&table->table_lock);
 	mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_EXTERNAL]);
 	mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_LOCAL]);
+	mutex_destroy(&table->table_lock);
 	kfree(table);
+res_unregister:
+	mlx5_sf_hw_table_res_unregister(dev);
 }
 
 static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data)
-- 
GitLab


From a9f168e4c6e1f623dcf2640b9d76a4f61b9731e5 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Wed, 31 May 2023 13:50:21 +0300
Subject: [PATCH 1211/1806] net/mlx5: Check with FW that sync reset completed
 successfully

Even if the PF driver had no error on his part of the sync reset flow,
the firmware can see wider picture as it syncs all the PFs in the flow.
So add at end of sync reset flow check with firmware by reading MFRL
register and initialization segment that the flow had no issue from
firmware point of view too.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/devlink.c |  3 ++
 .../ethernet/mellanox/mlx5/core/fw_reset.c    | 39 ++++++++++++++++---
 .../ethernet/mellanox/mlx5/core/fw_reset.h    |  2 +
 include/linux/mlx5/mlx5_ifc.h                 |  3 +-
 4 files changed, 40 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 3d82ec8906660..af8460bb257b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -212,6 +212,9 @@ static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_a
 		/* On fw_activate action, also driver is reloaded and reinit performed */
 		*actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
 		ret = mlx5_load_one_devl_locked(dev, true);
+		if (ret)
+			return ret;
+		ret = mlx5_fw_reset_verify_fw_complete(dev, extack);
 		break;
 	default:
 		/* Unsupported action should not get to this function */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 4804990b7f226..e87766f911506 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -127,17 +127,23 @@ static int mlx5_fw_reset_get_reset_state_err(struct mlx5_core_dev *dev,
 	if (mlx5_reg_mfrl_query(dev, NULL, NULL, &reset_state))
 		goto out;
 
+	if (!reset_state)
+		return 0;
+
 	switch (reset_state) {
 	case MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION:
 	case MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS:
-		NL_SET_ERR_MSG_MOD(extack, "Sync reset was already triggered");
+		NL_SET_ERR_MSG_MOD(extack, "Sync reset still in progress");
 		return -EBUSY;
-	case MLX5_MFRL_REG_RESET_STATE_TIMEOUT:
-		NL_SET_ERR_MSG_MOD(extack, "Sync reset got timeout");
+	case MLX5_MFRL_REG_RESET_STATE_NEG_TIMEOUT:
+		NL_SET_ERR_MSG_MOD(extack, "Sync reset negotiation timeout");
 		return -ETIMEDOUT;
 	case MLX5_MFRL_REG_RESET_STATE_NACK:
 		NL_SET_ERR_MSG_MOD(extack, "One of the hosts disabled reset");
 		return -EPERM;
+	case MLX5_MFRL_REG_RESET_STATE_UNLOAD_TIMEOUT:
+		NL_SET_ERR_MSG_MOD(extack, "Sync reset unload timeout");
+		return -ETIMEDOUT;
 	}
 
 out:
@@ -151,7 +157,7 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel,
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 	u32 out[MLX5_ST_SZ_DW(mfrl_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(mfrl_reg)] = {};
-	int err;
+	int err, rst_res;
 
 	set_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags);
 
@@ -164,13 +170,34 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel,
 		return 0;
 
 	clear_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags);
-	if (err == -EREMOTEIO && MLX5_CAP_MCAM_FEATURE(dev, reset_state))
-		return mlx5_fw_reset_get_reset_state_err(dev, extack);
+	if (err == -EREMOTEIO && MLX5_CAP_MCAM_FEATURE(dev, reset_state)) {
+		rst_res = mlx5_fw_reset_get_reset_state_err(dev, extack);
+		return rst_res ? rst_res : err;
+	}
 
 	NL_SET_ERR_MSG_MOD(extack, "Sync reset command failed");
 	return mlx5_cmd_check(dev, err, in, out);
 }
 
+int mlx5_fw_reset_verify_fw_complete(struct mlx5_core_dev *dev,
+				     struct netlink_ext_ack *extack)
+{
+	u8 rst_state;
+	int err;
+
+	err = mlx5_fw_reset_get_reset_state_err(dev, extack);
+	if (err)
+		return err;
+
+	rst_state = mlx5_get_fw_rst_state(dev);
+	if (!rst_state)
+		return 0;
+
+	mlx5_core_err(dev, "Sync reset did not complete, state=%d\n", rst_state);
+	NL_SET_ERR_MSG_MOD(extack, "Sync reset did not complete successfully");
+	return rst_state;
+}
+
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
 {
 	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
index c57465595f7c8..ea527d06a85f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
@@ -12,6 +12,8 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel,
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev);
 
 int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev);
+int mlx5_fw_reset_verify_fw_complete(struct mlx5_core_dev *dev,
+				     struct netlink_ext_ack *extack);
 void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev);
 void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev);
 void mlx5_drain_fw_reset(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 87fd6f9ed82cd..9aed7e9b9f29b 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10858,8 +10858,9 @@ enum {
 	MLX5_MFRL_REG_RESET_STATE_IDLE = 0,
 	MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1,
 	MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS = 2,
-	MLX5_MFRL_REG_RESET_STATE_TIMEOUT = 3,
+	MLX5_MFRL_REG_RESET_STATE_NEG_TIMEOUT = 3,
 	MLX5_MFRL_REG_RESET_STATE_NACK = 4,
+	MLX5_MFRL_REG_RESET_STATE_UNLOAD_TIMEOUT = 5,
 };
 
 enum {
-- 
GitLab


From e0e22d59b47a3306d448284a499169a361555099 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Wed, 19 Apr 2023 03:17:57 +0000
Subject: [PATCH 1212/1806] net/mlx5: E-switch, Add checking for flow rule
 destinations

Firmware doesn't allow flow rules in FDB to do header rewrite and send
packets to both internal and uplink vports. The following syndrome
will be generated when trying to offload such kind of rules:

mlx5_core 0000:08:00.0: mlx5_cmd_out_err:803:(pid 23569): SET_FLOW_TABLE_ENTRY(0x936) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x8c8f08), err(-22)

To avoid this syndrome, add a checking before creating FTE. If a rule
with header rewrite action forwards packets to both VF and PF, an
error is returned directly.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index e391535e1ab11..46b8c60ac39a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -535,6 +535,28 @@ esw_src_port_rewrite_supported(struct mlx5_eswitch *esw)
 	       MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level);
 }
 
+static bool
+esw_dests_to_vf_pf_vports(struct mlx5_flow_destination *dests, int max_dest)
+{
+	bool vf_dest = false, pf_dest = false;
+	int i;
+
+	for (i = 0; i < max_dest; i++) {
+		if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT)
+			continue;
+
+		if (dests[i].vport.num == MLX5_VPORT_UPLINK)
+			pf_dest = true;
+		else
+			vf_dest = true;
+
+		if (vf_dest && pf_dest)
+			return true;
+	}
+
+	return false;
+}
+
 static int
 esw_setup_dests(struct mlx5_flow_destination *dest,
 		struct mlx5_flow_act *flow_act,
@@ -671,6 +693,15 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 			rule = ERR_PTR(err);
 			goto err_create_goto_table;
 		}
+
+		/* Header rewrite with combined wire+loopback in FDB is not allowed */
+		if ((flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) &&
+		    esw_dests_to_vf_pf_vports(dest, i)) {
+			esw_warn(esw->dev,
+				 "FDB: Header rewrite with forwarding to both PF and VF is not allowed\n");
+			rule = ERR_PTR(-EINVAL);
+			goto err_esw_get;
+		}
 	}
 
 	if (esw_attr->decap_pkt_reformat)
-- 
GitLab


From 2ad0160c02be2a56bd80aaeb5c40221250814c25 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Wed, 28 Jun 2023 16:19:52 +0200
Subject: [PATCH 1213/1806] net/mlx5: Use auxiliary_device_uninit() instead of
 device_put()

Instead of using device_put(), use auxiliary_device_uninit() for
auxiliary device uninit which internally just calls device_put().

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index 8e2abbab05f04..b2c849b8c0c90 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -129,7 +129,7 @@ static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u16 fn_id,
 
 	err = auxiliary_device_add(&sf_dev->adev);
 	if (err) {
-		put_device(&sf_dev->adev.dev);
+		auxiliary_device_uninit(&sf_dev->adev);
 		goto add_err;
 	}
 
-- 
GitLab


From ae80d7a06fdb0b34a0f2842e1aac3da3bde93ccb Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 30 Jun 2023 09:32:14 +0200
Subject: [PATCH 1214/1806] net/mlx5: Remove redundant SF supported check from
 mlx5_sf_hw_table_init()

Since mlx5_sf_supported() check is done as a first thing in
mlx5_sf_max_functions(), remove the redundant check.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
index c4daeaaafeadd..1f613320fe077 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -275,15 +275,14 @@ int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
 	struct mlx5_sf_hw_table *table;
 	u16 max_ext_fn = 0;
 	u16 ext_base_id = 0;
-	u16 max_fn = 0;
 	u16 base_id;
+	u16 max_fn;
 	int err;
 
 	if (!mlx5_vhca_event_supported(dev))
 		return 0;
 
-	if (mlx5_sf_supported(dev))
-		max_fn = mlx5_sf_max_functions(dev);
+	max_fn = mlx5_sf_max_functions(dev);
 
 	err = mlx5_esw_sf_max_hpf_functions(dev, &max_ext_fn, &ext_base_id);
 	if (err)
-- 
GitLab


From 88074d81e5fe8b76010ea3437330d5ab55535537 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 30 Jun 2023 09:37:04 +0200
Subject: [PATCH 1215/1806] net/mlx5: Use mlx5_sf_start_function_id() helper
 instead of directly calling MLX5_CAP_GEN()

There is a helper called mlx5_sf_start_function_id() that
wraps up a query to get base SF function id. Use that instead of
calling MLX5_CAP_GEN() directly.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index b2c849b8c0c90..39132a6cc68ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -167,7 +167,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_
 	if (!max_functions)
 		return 0;
 
-	base_id = MLX5_CAP_GEN(table->dev, sf_base_id);
+	base_id = mlx5_sf_start_function_id(table->dev);
 	if (event->function_id < base_id || event->function_id >= (base_id + max_functions))
 		return 0;
 
@@ -209,7 +209,7 @@ static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table)
 	int i;
 
 	max_functions = mlx5_sf_max_functions(dev);
-	function_id = MLX5_CAP_GEN(dev, sf_base_id);
+	function_id = mlx5_sf_start_function_id(dev);
 	/* Arm the vhca context as the vhca event notifier */
 	for (i = 0; i < max_functions; i++) {
 		err = mlx5_vhca_event_arm(dev, function_id);
@@ -234,7 +234,7 @@ static void mlx5_sf_dev_add_active_work(struct work_struct *work)
 	int i;
 
 	max_functions = mlx5_sf_max_functions(dev);
-	function_id = MLX5_CAP_GEN(dev, sf_base_id);
+	function_id = mlx5_sf_start_function_id(dev);
 	for (i = 0; i < max_functions; i++, function_id++) {
 		if (table->stop_active_wq)
 			return;
-- 
GitLab


From b63f8bde2fbadc8eca96b42dd281bf99bc853167 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 30 Jun 2023 09:41:14 +0200
Subject: [PATCH 1216/1806] net/mlx5: Remove redundant check of
 mlx5_vhca_event_supported()

Since mlx5_vhca_event_supported() is called in mlx5_sf_dev_supported(),
remove the redundant call.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index 39132a6cc68ba..e617a270d74a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -299,7 +299,7 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
 	unsigned int max_sfs;
 	int err;
 
-	if (!mlx5_sf_dev_supported(dev) || !mlx5_vhca_event_supported(dev))
+	if (!mlx5_sf_dev_supported(dev))
 		return;
 
 	table = kzalloc(sizeof(*table), GFP_KERNEL);
-- 
GitLab


From 36e5a0efc81010dab29b17c66c58417a15851836 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 30 Jun 2023 12:45:39 +0200
Subject: [PATCH 1217/1806] net/mlx5: Fix error message in
 mlx5_sf_dev_state_change_handler()

sw_function_id contains sfnum, so fix the error message to name the
value properly.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index e617a270d74a0..05e148db98899 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -185,7 +185,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_
 			mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
 		else
 			mlx5_core_err(table->dev,
-				      "SF DEV: teardown state for invalid dev index=%d fn_id=0x%x\n",
+				      "SF DEV: teardown state for invalid dev index=%d sfnum=0x%x\n",
 				      sf_index, event->sw_function_id);
 		break;
 	case MLX5_VHCA_STATE_ACTIVE:
-- 
GitLab


From 0b4eb603d635ca47c1c372f69b4b96672e4c2c05 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Sun, 2 Jan 2022 14:57:39 +0200
Subject: [PATCH 1218/1806] net/mlx5: Remove unused CAPs

mlx5 driver queries the device for VECTOR_CALC and SHAMPO caps, but
there isn't any user who requires them.
As well as, MLX5_MCAM_REGS_0x9080_0x90FF is queried but not used.

Thus, drop all usages and definitions of the mentioned caps above.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Maher Sanalla <msanalla@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw.c  | 13 ------
 .../net/ethernet/mellanox/mlx5/core/main.c    |  2 -
 include/linux/mlx5/device.h                   | 17 +-------
 include/linux/mlx5/mlx5_ifc.h                 | 43 -------------------
 4 files changed, 1 insertion(+), 74 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index fb2035a5ec999..c982ce06d7a30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -206,12 +206,6 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
-	if (MLX5_CAP_GEN(dev, vector_calc)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_VECTOR_CALC);
-		if (err)
-			return err;
-	}
-
 	if (MLX5_CAP_GEN(dev, qos)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_QOS);
 		if (err)
@@ -226,7 +220,6 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 
 	if (MLX5_CAP_GEN(dev, mcam_reg)) {
 		mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_FIRST_128);
-		mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9080_0x90FF);
 		mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9100_0x917F);
 	}
 
@@ -270,12 +263,6 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
-	if (MLX5_CAP_GEN(dev, shampo)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_SHAMPO);
-		if (err)
-			return err;
-	}
-
 	if (MLX5_CAP_GEN_64(dev, general_obj_types) &
 	    MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_MACSEC);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f4fe06a5042ef..cb77b5774aadb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1714,7 +1714,6 @@ static const int types[] = {
 	MLX5_CAP_FLOW_TABLE,
 	MLX5_CAP_ESWITCH_FLOW_TABLE,
 	MLX5_CAP_ESWITCH,
-	MLX5_CAP_VECTOR_CALC,
 	MLX5_CAP_QOS,
 	MLX5_CAP_DEBUG,
 	MLX5_CAP_DEV_MEM,
@@ -1723,7 +1722,6 @@ static const int types[] = {
 	MLX5_CAP_VDPA_EMULATION,
 	MLX5_CAP_IPSEC,
 	MLX5_CAP_PORT_SELECTION,
-	MLX5_CAP_DEV_SHAMPO,
 	MLX5_CAP_MACSEC,
 	MLX5_CAP_ADV_VIRTUALIZATION,
 	MLX5_CAP_CRYPTO,
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 80cc12a9a5318..5041965250f64 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1208,9 +1208,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_FLOW_TABLE,
 	MLX5_CAP_ESWITCH_FLOW_TABLE,
 	MLX5_CAP_ESWITCH,
-	MLX5_CAP_RESERVED,
-	MLX5_CAP_VECTOR_CALC,
-	MLX5_CAP_QOS,
+	MLX5_CAP_QOS = 0xc,
 	MLX5_CAP_DEBUG,
 	MLX5_CAP_RESERVED_14,
 	MLX5_CAP_DEV_MEM,
@@ -1220,7 +1218,6 @@ enum mlx5_cap_type {
 	MLX5_CAP_DEV_EVENT = 0x14,
 	MLX5_CAP_IPSEC,
 	MLX5_CAP_CRYPTO = 0x1a,
-	MLX5_CAP_DEV_SHAMPO = 0x1d,
 	MLX5_CAP_MACSEC = 0x1f,
 	MLX5_CAP_GENERAL_2 = 0x20,
 	MLX5_CAP_PORT_SELECTION = 0x25,
@@ -1239,7 +1236,6 @@ enum mlx5_pcam_feature_groups {
 
 enum mlx5_mcam_reg_groups {
 	MLX5_MCAM_REGS_FIRST_128                    = 0x0,
-	MLX5_MCAM_REGS_0x9080_0x90FF                = 0x1,
 	MLX5_MCAM_REGS_0x9100_0x917F                = 0x2,
 	MLX5_MCAM_REGS_NUM                          = 0x3,
 };
@@ -1416,10 +1412,6 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_ODP_MAX(mdev, cap)\
 	MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap)
 
-#define MLX5_CAP_VECTOR_CALC(mdev, cap) \
-	MLX5_GET(vector_calc_cap, \
-		 mdev->caps.hca[MLX5_CAP_VECTOR_CALC]->cur, cap)
-
 #define MLX5_CAP_QOS(mdev, cap)\
 	MLX5_GET(qos_cap, mdev->caps.hca[MLX5_CAP_QOS]->cur, cap)
 
@@ -1436,10 +1428,6 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_FIRST_128], \
 		 mng_access_reg_cap_mask.access_regs.reg)
 
-#define MLX5_CAP_MCAM_REG1(mdev, reg) \
-	MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9080_0x90FF], \
-		 mng_access_reg_cap_mask.access_regs1.reg)
-
 #define MLX5_CAP_MCAM_REG2(mdev, reg) \
 	MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \
 		 mng_access_reg_cap_mask.access_regs2.reg)
@@ -1485,9 +1473,6 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_CRYPTO(mdev, cap)\
 	MLX5_GET(crypto_cap, (mdev)->caps.hca[MLX5_CAP_CRYPTO]->cur, cap)
 
-#define MLX5_CAP_DEV_SHAMPO(mdev, cap)\
-	MLX5_GET(shampo_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_SHAMPO], cap)
-
 #define MLX5_CAP_MACSEC(mdev, cap)\
 	MLX5_GET(macsec_cap, (mdev)->caps.hca[MLX5_CAP_MACSEC]->cur, cap)
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 9aed7e9b9f29b..08dcb1f43be72 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1314,33 +1314,6 @@ struct mlx5_ifc_odp_cap_bits {
 	u8         reserved_at_120[0x6E0];
 };
 
-struct mlx5_ifc_calc_op {
-	u8        reserved_at_0[0x10];
-	u8        reserved_at_10[0x9];
-	u8        op_swap_endianness[0x1];
-	u8        op_min[0x1];
-	u8        op_xor[0x1];
-	u8        op_or[0x1];
-	u8        op_and[0x1];
-	u8        op_max[0x1];
-	u8        op_add[0x1];
-};
-
-struct mlx5_ifc_vector_calc_cap_bits {
-	u8         calc_matrix[0x1];
-	u8         reserved_at_1[0x1f];
-	u8         reserved_at_20[0x8];
-	u8         max_vec_count[0x8];
-	u8         reserved_at_30[0xd];
-	u8         max_chunk_size[0x3];
-	struct mlx5_ifc_calc_op calc0;
-	struct mlx5_ifc_calc_op calc1;
-	struct mlx5_ifc_calc_op calc2;
-	struct mlx5_ifc_calc_op calc3;
-
-	u8         reserved_at_c0[0x720];
-};
-
 struct mlx5_ifc_tls_cap_bits {
 	u8         tls_1_2_aes_gcm_128[0x1];
 	u8         tls_1_3_aes_gcm_128[0x1];
@@ -3435,20 +3408,6 @@ struct mlx5_ifc_roce_addr_layout_bits {
 	u8         reserved_at_e0[0x20];
 };
 
-struct mlx5_ifc_shampo_cap_bits {
-	u8    reserved_at_0[0x3];
-	u8    shampo_log_max_reservation_size[0x5];
-	u8    reserved_at_8[0x3];
-	u8    shampo_log_min_reservation_size[0x5];
-	u8    shampo_min_mss_size[0x10];
-
-	u8    reserved_at_20[0x3];
-	u8    shampo_max_log_headers_entry_size[0x5];
-	u8    reserved_at_28[0x18];
-
-	u8    reserved_at_40[0x7c0];
-};
-
 struct mlx5_ifc_crypto_cap_bits {
 	u8    reserved_at_0[0x3];
 	u8    synchronize_dek[0x1];
@@ -3484,14 +3443,12 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap;
 	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
 	struct mlx5_ifc_port_selection_cap_bits port_selection_cap;
-	struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap;
 	struct mlx5_ifc_qos_cap_bits qos_cap;
 	struct mlx5_ifc_debug_cap_bits debug_cap;
 	struct mlx5_ifc_fpga_cap_bits fpga_cap;
 	struct mlx5_ifc_tls_cap_bits tls_cap;
 	struct mlx5_ifc_device_mem_cap_bits device_mem_cap;
 	struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap;
-	struct mlx5_ifc_shampo_cap_bits shampo_cap;
 	struct mlx5_ifc_macsec_cap_bits macsec_cap;
 	struct mlx5_ifc_crypto_cap_bits crypto_cap;
 	u8         reserved_at_0[0x8000];
-- 
GitLab


From a41cb59117fa12ee17cda5e5c781eecfcb15dc0f Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 11 Jul 2023 15:56:08 +0300
Subject: [PATCH 1219/1806] net/mlx5: Remove unused MAX HCA capabilities

Each device cap has two modes: MAX and CUR. The driver maintains a
cache of both modes of the capabilities. For most device caps, the MAX
cap mode is never used.

Hence, remove all driver queries of the MAX mode of the said caps as
well as their helper MACROs.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Maher Sanalla <msanalla@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw.c  | 34 ++++++------
 .../net/ethernet/mellanox/mlx5/core/main.c    | 14 ++---
 .../ethernet/mellanox/mlx5/core/mlx5_core.h   |  3 ++
 include/linux/mlx5/device.h                   | 52 -------------------
 include/linux/mlx5/driver.h                   |  1 -
 5 files changed, 30 insertions(+), 74 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index c982ce06d7a30..0e394408af75c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -160,13 +160,15 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 	}
 
 	if (MLX5_CAP_GEN(dev, eth_net_offloads)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ETHERNET_OFFLOADS,
+					      HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_IPOIB_ENHANCED_OFFLOADS);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_IPOIB_ENHANCED_OFFLOADS,
+					      HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
@@ -191,29 +193,30 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 
 	if (MLX5_CAP_GEN(dev, nic_flow_table) ||
 	    MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_FLOW_TABLE, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_ESWITCH_MANAGER(dev)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ESWITCH_FLOW_TABLE,
+					      HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 
-		err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ESWITCH, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, qos)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_QOS);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_QOS, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, debug))
-		mlx5_core_get_caps(dev, MLX5_CAP_DEBUG);
+		mlx5_core_get_caps_mode(dev, MLX5_CAP_DEBUG, HCA_CAP_OPMOD_GET_CUR);
 
 	if (MLX5_CAP_GEN(dev, pcam_reg))
 		mlx5_get_pcam_reg(dev);
@@ -227,51 +230,52 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 		mlx5_get_qcam_reg(dev);
 
 	if (MLX5_CAP_GEN(dev, device_memory)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_MEM);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_DEV_MEM, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, event_cap)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_EVENT);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_DEV_EVENT, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, tls_tx) || MLX5_CAP_GEN(dev, tls_rx)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_TLS);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_TLS, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN_64(dev, general_obj_types) &
 		MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_VDPA_EMULATION);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_VDPA_EMULATION, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, ipsec_offload)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_IPSEC);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_IPSEC, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, crypto)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_CRYPTO);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_CRYPTO, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN_64(dev, general_obj_types) &
 	    MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_MACSEC);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_MACSEC, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, adv_virtualization)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_ADV_VIRTUALIZATION);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ADV_VIRTUALIZATION,
+					      HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index cb77b5774aadb..15561965d2afa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -361,9 +361,8 @@ void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_core_uplink_netdev_event_replay);
 
-static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev,
-				   enum mlx5_cap_type cap_type,
-				   enum mlx5_cap_mode cap_mode)
+int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type,
+			    enum mlx5_cap_mode cap_mode)
 {
 	u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)];
 	int out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
@@ -1620,21 +1619,24 @@ static int mlx5_query_hca_caps_light(struct mlx5_core_dev *dev)
 		return err;
 
 	if (MLX5_CAP_GEN(dev, eth_net_offloads)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ETHERNET_OFFLOADS,
+					      HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, nic_flow_table) ||
 	    MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_FLOW_TABLE,
+					      HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN_64(dev, general_obj_types) &
 		MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_VDPA_EMULATION);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_VDPA_EMULATION,
+					      HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 8e2028d20a9e5..124352459c23d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -174,6 +174,9 @@ static inline int mlx5_flexible_inlen(struct mlx5_core_dev *dev, size_t fixed,
 #define MLX5_FLEXIBLE_INLEN(dev, fixed, item_size, num_items) \
 	mlx5_flexible_inlen(dev, fixed, item_size, num_items, __func__, __LINE__)
 
+int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
+int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type,
+			    enum mlx5_cap_mode cap_mode);
 int mlx5_query_hca_caps(struct mlx5_core_dev *dev);
 int mlx5_query_board_id(struct mlx5_core_dev *dev);
 int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 5041965250f64..93399802ba771 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1275,10 +1275,6 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(per_protocol_networking_offload_caps,\
 		 mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->cur, cap)
 
-#define MLX5_CAP_ETH_MAX(mdev, cap) \
-	MLX5_GET(per_protocol_networking_offload_caps,\
-		 mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->max, cap)
-
 #define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \
 	MLX5_GET(per_protocol_networking_offload_caps,\
 		 mdev->caps.hca[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS]->cur, cap)
@@ -1301,77 +1297,40 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP64_FLOWTABLE(mdev, cap) \
 	MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca[MLX5_CAP_FLOW_TABLE]->cur, cap)
 
-#define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \
-	MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE]->max, cap)
-
 #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap)
 
-#define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap)
-
 #define MLX5_CAP_FLOWTABLE_NIC_TX(mdev, cap) \
 		MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit.cap)
 
-#define MLX5_CAP_FLOWTABLE_NIC_TX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit.cap)
-
 #define MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_sniffer.cap)
 
-#define MLX5_CAP_FLOWTABLE_SNIFFER_RX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_sniffer.cap)
-
 #define MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_sniffer.cap)
 
-#define MLX5_CAP_FLOWTABLE_SNIFFER_TX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_sniffer.cap)
-
 #define MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_rdma.cap)
 
-#define MLX5_CAP_FLOWTABLE_RDMA_RX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_rdma.cap)
-
 #define MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_rdma.cap)
 
-#define MLX5_CAP_FLOWTABLE_RDMA_TX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_rdma.cap)
-
 #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
 		 mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap)
 
-#define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \
-	MLX5_GET(flow_table_eswitch_cap, \
-		 mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->max, cap)
-
 #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap)
 
-#define MLX5_CAP_ESW_FLOWTABLE_FDB_MAX(mdev, cap) \
-	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_nic_esw_fdb.cap)
-
 #define MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_egress.cap)
 
-#define MLX5_CAP_ESW_EGRESS_ACL_MAX(mdev, cap) \
-	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_egress.cap)
-
 #define MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_ingress.cap)
 
-#define MLX5_CAP_ESW_INGRESS_ACL_MAX(mdev, cap) \
-	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_ingress.cap)
-
 #define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap)
 
-#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2_MAX(mdev, cap) \
-	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, ft_field_support_2_esw_fdb.cap)
-
 #define MLX5_CAP_ESW(mdev, cap) \
 	MLX5_GET(e_switch_cap, \
 		 mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap)
@@ -1380,10 +1339,6 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET64(flow_table_eswitch_cap, \
 		(mdev)->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap)
 
-#define MLX5_CAP_ESW_MAX(mdev, cap) \
-	MLX5_GET(e_switch_cap, \
-		 mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap)
-
 #define MLX5_CAP_PORT_SELECTION(mdev, cap) \
 	MLX5_GET(port_selection_cap, \
 		 mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->cur, cap)
@@ -1396,16 +1351,9 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(adv_virtualization_cap, \
 		 mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->cur, cap)
 
-#define MLX5_CAP_ADV_VIRTUALIZATION_MAX(mdev, cap) \
-	MLX5_GET(adv_virtualization_cap, \
-		 mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->max, cap)
-
 #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \
 	MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap)
 
-#define MLX5_CAP_FLOWTABLE_PORT_SELECTION_MAX(mdev, cap) \
-	MLX5_CAP_PORT_SELECTION_MAX(mdev, flow_table_properties_port_selection.cap)
-
 #define MLX5_CAP_ODP(mdev, cap)\
 	MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap)
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e1c7e502a4fc0..c9d82e74daaa0 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1022,7 +1022,6 @@ bool mlx5_cmd_is_down(struct mlx5_core_dev *dev);
 void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev);
 void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev);
 
-int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
-- 
GitLab


From bd3a2f77809b84df5dc15edd72cf9955568e698e Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 11 Jul 2023 16:32:05 +0300
Subject: [PATCH 1220/1806] net/mlx5: Don't query MAX caps twice

Whenever mlx5 driver is probed or reloaded, it queries some capabilities
in MAX mode via set_hca_cap() API. Afterwards, the driver queries all
capabilities in MAX mode via mlx5_query_hca_caps() API.

Since MAX caps are read only caps, querying them twice is redundant.
Hence, delete the second query.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Maher Sanalla <msanalla@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 0e394408af75c..58f4c0d0fafa2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -143,18 +143,18 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 {
 	int err;
 
-	err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL);
+	err = mlx5_core_get_caps_mode(dev, MLX5_CAP_GENERAL, HCA_CAP_OPMOD_GET_CUR);
 	if (err)
 		return err;
 
 	if (MLX5_CAP_GEN(dev, port_selection_cap)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_PORT_SELECTION);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_PORT_SELECTION, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, hca_cap_2)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL_2);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_GENERAL_2, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
@@ -174,19 +174,19 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 	}
 
 	if (MLX5_CAP_GEN(dev, pg)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_ODP);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ODP, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, atomic)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_ATOMIC);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ATOMIC, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
 
 	if (MLX5_CAP_GEN(dev, roce)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE);
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ROCE, HCA_CAP_OPMOD_GET_CUR);
 		if (err)
 			return err;
 	}
-- 
GitLab


From 479b322ee6feaff612285a0e7f22c022e8cd84eb Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sat, 12 Aug 2023 10:30:33 +0100
Subject: [PATCH 1221/1806] net: dsa: mv88e6060: add phylink_get_caps
 implementation

Add a phylink_get_caps implementation for Marvell 88e6060 DSA switch.
This is a fast ethernet switch, with internal PHYs for ports 0 through
4. Port 4 also supports MII, REVMII, REVRMII and SNI. Port 5 supports
MII, REVMII, REVRMII and SNI without an internal PHY.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://lore.kernel.org/r/E1qUkx7-003dMX-9b@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mv88e6060.c | 45 +++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index fdda62d6eb16a..294312b58e4f1 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -247,11 +247,56 @@ mv88e6060_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val)
 	return reg_write(priv, addr, regnum, val);
 }
 
+static void mv88e6060_phylink_get_caps(struct dsa_switch *ds, int port,
+				       struct phylink_config *config)
+{
+	unsigned long *interfaces = config->supported_interfaces;
+	struct mv88e6060_priv *priv = ds->priv;
+	int addr = REG_PORT(port);
+	int ret;
+
+	ret = reg_read(priv, addr, PORT_STATUS);
+	if (ret < 0) {
+		dev_err(ds->dev,
+			"port %d: unable to read status register: %pe\n",
+			port, ERR_PTR(ret));
+		return;
+	}
+
+	/* If the port is configured in SNI mode (acts as a 10Mbps PHY),
+	 * it should have phy-mode = "sni", but that doesn't yet exist, so
+	 * forcibly fail validation until the need arises to introduce it.
+	 */
+	if (!(ret & PORT_STATUS_PORTMODE)) {
+		dev_warn(ds->dev, "port %d: SNI mode not supported\n", port);
+		return;
+	}
+
+	config->mac_capabilities = MAC_100 | MAC_10 | MAC_SYM_PAUSE;
+
+	if (port >= 4) {
+		/* Ports 4 and 5 can support MII, REVMII and REVRMII modes */
+		__set_bit(PHY_INTERFACE_MODE_MII, interfaces);
+		__set_bit(PHY_INTERFACE_MODE_REVMII, interfaces);
+		__set_bit(PHY_INTERFACE_MODE_REVRMII, interfaces);
+	}
+	if (port <= 4) {
+		/* Ports 0 to 3 have internal PHYs, and port 4 can optionally
+		 * use an internal PHY.
+		 */
+		/* Internal PHY */
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL, interfaces);
+		/* Default phylib interface mode */
+		__set_bit(PHY_INTERFACE_MODE_GMII, interfaces);
+	}
+}
+
 static const struct dsa_switch_ops mv88e6060_switch_ops = {
 	.get_tag_protocol = mv88e6060_get_tag_protocol,
 	.setup		= mv88e6060_setup,
 	.phy_read	= mv88e6060_phy_read,
 	.phy_write	= mv88e6060_phy_write,
+	.phylink_get_caps = mv88e6060_phylink_get_caps,
 };
 
 static int mv88e6060_probe(struct mdio_device *mdiodev)
-- 
GitLab


From ccd9a8be2e42a337ad4da5d8a051e8293200a4f3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 14 Aug 2023 18:14:10 +0200
Subject: [PATCH 1222/1806] selftests/bpf: Add various more tcx test cases

Add several new tcx test cases to improve test coverage. This also includes
a few new tests with ingress instead of clsact qdisc, to cover the fix from
commit dc644b540a2d ("tcx: Fix splat in ingress_destroy upon tcx_entry_free").

  # ./test_progs -t tc
  [...]
  #234     tc_links_after:OK
  #235     tc_links_append:OK
  #236     tc_links_basic:OK
  #237     tc_links_before:OK
  #238     tc_links_chain_classic:OK
  #239     tc_links_chain_mixed:OK
  #240     tc_links_dev_cleanup:OK
  #241     tc_links_dev_mixed:OK
  #242     tc_links_ingress:OK
  #243     tc_links_invalid:OK
  #244     tc_links_prepend:OK
  #245     tc_links_replace:OK
  #246     tc_links_revision:OK
  #247     tc_opts_after:OK
  #248     tc_opts_append:OK
  #249     tc_opts_basic:OK
  #250     tc_opts_before:OK
  #251     tc_opts_chain_classic:OK
  #252     tc_opts_chain_mixed:OK
  #253     tc_opts_delete_empty:OK
  #254     tc_opts_demixed:OK
  #255     tc_opts_detach:OK
  #256     tc_opts_detach_after:OK
  #257     tc_opts_detach_before:OK
  #258     tc_opts_dev_cleanup:OK
  #259     tc_opts_invalid:OK
  #260     tc_opts_mixed:OK
  #261     tc_opts_prepend:OK
  #262     tc_opts_replace:OK
  #263     tc_opts_revision:OK
  [...]
  Summary: 44/38 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/8699efc284b75ccdc51ddf7062fa2370330dc6c0.1692029283.git.daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/tc_links.c       | 336 ++++++++++++++++++
 .../selftests/bpf/prog_tests/tc_opts.c        | 110 ++++++
 .../selftests/bpf/progs/test_tc_link.c        |  16 +
 3 files changed, 462 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_links.c b/tools/testing/selftests/bpf/prog_tests/tc_links.c
index 81eea5f10742e..74fc1fe9ee261 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_links.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_links.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2023 Isovalent */
 #include <uapi/linux/if_link.h>
+#include <uapi/linux/pkt_sched.h>
 #include <net/if.h>
 #include <test_progs.h>
 
@@ -1581,3 +1582,338 @@ void serial_test_tc_links_dev_cleanup(void)
 	test_tc_links_dev_cleanup_target(BPF_TCX_INGRESS);
 	test_tc_links_dev_cleanup_target(BPF_TCX_EGRESS);
 }
+
+static void test_tc_chain_mixed(int target)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	__u32 pid1, pid2, pid3;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc5, target),
+		  0, "tc5_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc6, target),
+		  0, "tc6_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc5));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc6));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+			       BPF_TC_INGRESS : BPF_TC_EGRESS;
+	err = bpf_tc_hook_create(&tc_hook);
+	err = err == -EEXIST ? 0 : err;
+	if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+		goto cleanup;
+
+	tc_opts.prog_fd = bpf_program__fd(skel->progs.tc5);
+	err = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(err, "bpf_tc_attach"))
+		goto cleanup;
+
+	link = bpf_program__attach_tcx(skel->progs.tc6, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc6 = link;
+
+	assert_mprog_count(target, 1);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, false, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, true, "seen_tc6");
+
+	skel->bss->seen_tc4 = false;
+	skel->bss->seen_tc5 = false;
+	skel->bss->seen_tc6 = false;
+
+	err = bpf_link__update_program(skel->links.tc6, skel->progs.tc4);
+	if (!ASSERT_OK(err, "link_update"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+	skel->bss->seen_tc4 = false;
+	skel->bss->seen_tc5 = false;
+	skel->bss->seen_tc6 = false;
+
+	err = bpf_link__detach(skel->links.tc6);
+	if (!ASSERT_OK(err, "prog_detach"))
+		goto cleanup;
+
+	__assert_mprog_count(target, 0, true, loopback);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+cleanup:
+	tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+	err = bpf_tc_detach(&tc_hook, &tc_opts);
+	ASSERT_OK(err, "bpf_tc_detach");
+
+	tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+	bpf_tc_hook_destroy(&tc_hook);
+
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_links_chain_mixed(void)
+{
+	test_tc_chain_mixed(BPF_TCX_INGRESS);
+	test_tc_chain_mixed(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_ingress(int target, bool chain_tc_old,
+				  bool tcx_teardown_first)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts,
+		.handle		= 1,
+		.priority	= 1,
+	);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook,
+		.ifindex	= loopback,
+		.attach_point	= BPF_TC_CUSTOM,
+		.parent		= TC_H_INGRESS,
+	);
+	bool hook_created = false, tc_attached = false;
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, pid3;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	if (chain_tc_old) {
+		ASSERT_OK(system("tc qdisc add dev lo ingress"), "add_ingress");
+		hook_created = true;
+
+		tc_opts.prog_fd = bpf_program__fd(skel->progs.tc3);
+		err = bpf_tc_attach(&tc_hook, &tc_opts);
+		if (!ASSERT_OK(err, "bpf_tc_attach"))
+			goto cleanup;
+		tc_attached = true;
+	}
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	assert_mprog_count(target, 2);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+
+	skel->bss->seen_tc1 = false;
+	skel->bss->seen_tc2 = false;
+	skel->bss->seen_tc3 = false;
+
+	err = bpf_link__detach(skel->links.tc2);
+	if (!ASSERT_OK(err, "prog_detach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+cleanup:
+	if (tc_attached) {
+		tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+		err = bpf_tc_detach(&tc_hook, &tc_opts);
+		ASSERT_OK(err, "bpf_tc_detach");
+	}
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+	assert_mprog_count(target, 1);
+	if (hook_created && tcx_teardown_first)
+		ASSERT_OK(system("tc qdisc del dev lo ingress"), "del_ingress");
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+	test_tc_link__destroy(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+	if (hook_created && !tcx_teardown_first)
+		ASSERT_OK(system("tc qdisc del dev lo ingress"), "del_ingress");
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+	assert_mprog_count(target, 0);
+}
+
+void serial_test_tc_links_ingress(void)
+{
+	test_tc_links_ingress(BPF_TCX_INGRESS, true, true);
+	test_tc_links_ingress(BPF_TCX_INGRESS, true, false);
+	test_tc_links_ingress(BPF_TCX_INGRESS, false, false);
+}
+
+static void test_tc_links_dev_mixed(int target)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, pid3, pid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth");
+	ifindex = if_nametoindex("tcx_opts1");
+	ASSERT_NEQ(ifindex, 0, "non_zero_ifindex");
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 3);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 4);
+
+	tc_hook.ifindex = ifindex;
+	tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+			       BPF_TC_INGRESS : BPF_TC_EGRESS;
+
+	err = bpf_tc_hook_create(&tc_hook);
+	err = err == -EEXIST ? 0 : err;
+	if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+		goto cleanup;
+
+	tc_opts.prog_fd = bpf_program__fd(skel->progs.tc5);
+	err = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(err, "bpf_tc_attach"))
+		goto cleanup;
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc1)), 0, "tc1_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc2)), 0, "tc2_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc3)), 0, "tc3_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc4)), 0, "tc4_ifindex");
+
+	test_tc_link__destroy(skel);
+	return;
+cleanup:
+	test_tc_link__destroy(skel);
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+}
+
+void serial_test_tc_links_dev_mixed(void)
+{
+	test_tc_links_dev_mixed(BPF_TCX_INGRESS);
+	test_tc_links_dev_mixed(BPF_TCX_EGRESS);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
index 39bd253e41aa8..7a2ecd4eca5dd 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
@@ -2268,3 +2268,113 @@ void serial_test_tc_opts_delete_empty(void)
 	test_tc_opts_delete_empty(BPF_TCX_INGRESS, true);
 	test_tc_opts_delete_empty(BPF_TCX_EGRESS, true);
 }
+
+static void test_tc_chain_mixed(int target)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	__u32 fd1, fd2, fd3, id1, id2, id3;
+	struct test_tc_link *skel;
+	int err, detach_fd;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc4);
+	fd2 = bpf_program__fd(skel->progs.tc5);
+	fd3 = bpf_program__fd(skel->progs.tc6);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+			       BPF_TC_INGRESS : BPF_TC_EGRESS;
+	err = bpf_tc_hook_create(&tc_hook);
+	err = err == -EEXIST ? 0 : err;
+	if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+		goto cleanup;
+
+	tc_opts.prog_fd = fd2;
+	err = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(err, "bpf_tc_attach"))
+		goto cleanup_hook;
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_filter;
+
+	detach_fd = fd3;
+
+	assert_mprog_count(target, 1);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, false, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, true, "seen_tc6");
+
+	skel->bss->seen_tc4 = false;
+	skel->bss->seen_tc5 = false;
+	skel->bss->seen_tc6 = false;
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = fd3,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_opts;
+
+	detach_fd = fd1;
+
+	assert_mprog_count(target, 1);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+	skel->bss->seen_tc4 = false;
+	skel->bss->seen_tc5 = false;
+	skel->bss->seen_tc6 = false;
+
+cleanup_opts:
+	err = bpf_prog_detach_opts(detach_fd, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	__assert_mprog_count(target, 0, true, loopback);
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+cleanup_filter:
+	tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+	err = bpf_tc_detach(&tc_hook, &tc_opts);
+	ASSERT_OK(err, "bpf_tc_detach");
+
+cleanup_hook:
+	tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+	bpf_tc_hook_destroy(&tc_hook);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void serial_test_tc_opts_chain_mixed(void)
+{
+	test_tc_chain_mixed(BPF_TCX_INGRESS);
+	test_tc_chain_mixed(BPF_TCX_EGRESS);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c
index ed1fd0e9cee9c..30e7124c49a11 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_link.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_link.c
@@ -10,6 +10,8 @@ bool seen_tc1;
 bool seen_tc2;
 bool seen_tc3;
 bool seen_tc4;
+bool seen_tc5;
+bool seen_tc6;
 
 SEC("tc/ingress")
 int tc1(struct __sk_buff *skb)
@@ -38,3 +40,17 @@ int tc4(struct __sk_buff *skb)
 	seen_tc4 = true;
 	return TCX_NEXT;
 }
+
+SEC("tc/egress")
+int tc5(struct __sk_buff *skb)
+{
+	seen_tc5 = true;
+	return TCX_PASS;
+}
+
+SEC("tc/egress")
+int tc6(struct __sk_buff *skb)
+{
+	seen_tc6 = true;
+	return TCX_PASS;
+}
-- 
GitLab


From 8ba651ed7fa1641f7c4941b79f2e3dd4ddb58aec Mon Sep 17 00:00:00 2001
From: David Vernet <void@manifault.com>
Date: Mon, 14 Aug 2023 13:59:07 -0500
Subject: [PATCH 1223/1806] bpf: Support default .validate() and .update()
 behavior for struct_ops links

Currently, if a struct_ops map is loaded with BPF_F_LINK, it must also
define the .validate() and .update() callbacks in its corresponding
struct bpf_struct_ops in the kernel. Enabling struct_ops link is useful
in its own right to ensure that the map is unloaded if an application
crashes. For example, with sched_ext, we want to automatically unload
the host-wide scheduler if the application crashes. We would likely
never support updating elements of a sched_ext struct_ops map, so we'd
have to implement these callbacks showing that they _can't_ support
element updates just to benefit from the basic lifetime management of
struct_ops links.

Let's enable struct_ops maps to work with BPF_F_LINK even if they
haven't defined these callbacks, by assuming that a struct_ops map
element cannot be updated by default.

Acked-by: Kui-Feng Lee <thinker.li@gmail.com>
Signed-off-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/r/20230814185908.700553-2-void@manifault.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/bpf_struct_ops.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index eaff04eefb31e..fdc3e8705a3cb 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -509,9 +509,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	}
 
 	if (st_map->map.map_flags & BPF_F_LINK) {
-		err = st_ops->validate(kdata);
-		if (err)
-			goto reset_unlock;
+		err = 0;
+		if (st_ops->validate) {
+			err = st_ops->validate(kdata);
+			if (err)
+				goto reset_unlock;
+		}
 		set_memory_rox((long)st_map->image, 1);
 		/* Let bpf_link handle registration & unregistration.
 		 *
@@ -663,9 +666,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	if (attr->value_size != vt->size)
 		return ERR_PTR(-EINVAL);
 
-	if (attr->map_flags & BPF_F_LINK && (!st_ops->validate || !st_ops->update))
-		return ERR_PTR(-EOPNOTSUPP);
-
 	t = st_ops->type;
 
 	st_map_size = sizeof(*st_map) +
@@ -823,6 +823,9 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 	if (!bpf_struct_ops_valid_to_reg(new_map))
 		return -EINVAL;
 
+	if (!st_map->st_ops->update)
+		return -EOPNOTSUPP;
+
 	mutex_lock(&update_mutex);
 
 	old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
-- 
GitLab


From bb48cf1679d294d4fd3bfaa88289ed9004cbb025 Mon Sep 17 00:00:00 2001
From: David Vernet <void@manifault.com>
Date: Mon, 14 Aug 2023 13:59:08 -0500
Subject: [PATCH 1224/1806] bpf: Document struct bpf_struct_ops fields

Subsystems that want to implement a struct bpf_struct_ops structure to
enable struct_ops maps must currently reverse engineer how the structure
works. Given that this is meant to be a way for subsystem maintainers to
extend their subsystems using BPF, let's document it to make it a bit
easier on them.

Signed-off-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/r/20230814185908.700553-3-void@manifault.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/bpf.h | 47 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cfabbcf47bdb8..eced6400f7780 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1550,6 +1550,53 @@ struct bpf_struct_ops_value;
 struct btf_member;
 
 #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64
+/**
+ * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to
+ *			   define a BPF_MAP_TYPE_STRUCT_OPS map type composed
+ *			   of BPF_PROG_TYPE_STRUCT_OPS progs.
+ * @verifier_ops: A structure of callbacks that are invoked by the verifier
+ *		  when determining whether the struct_ops progs in the
+ *		  struct_ops map are valid.
+ * @init: A callback that is invoked a single time, and before any other
+ *	  callback, to initialize the structure. A nonzero return value means
+ *	  the subsystem could not be initialized.
+ * @check_member: When defined, a callback invoked by the verifier to allow
+ *		  the subsystem to determine if an entry in the struct_ops map
+ *		  is valid. A nonzero return value means that the map is
+ *		  invalid and should be rejected by the verifier.
+ * @init_member: A callback that is invoked for each member of the struct_ops
+ *		 map to allow the subsystem to initialize the member. A nonzero
+ *		 value means the member could not be initialized. This callback
+ *		 is exclusive with the @type, @type_id, @value_type, and
+ *		 @value_id fields.
+ * @reg: A callback that is invoked when the struct_ops map has been
+ *	 initialized and is being attached to. Zero means the struct_ops map
+ *	 has been successfully registered and is live. A nonzero return value
+ *	 means the struct_ops map could not be registered.
+ * @unreg: A callback that is invoked when the struct_ops map should be
+ *	   unregistered.
+ * @update: A callback that is invoked when the live struct_ops map is being
+ *	    updated to contain new values. This callback is only invoked when
+ *	    the struct_ops map is loaded with BPF_F_LINK. If not defined, the
+ *	    it is assumed that the struct_ops map cannot be updated.
+ * @validate: A callback that is invoked after all of the members have been
+ *	      initialized. This callback should perform static checks on the
+ *	      map, meaning that it should either fail or succeed
+ *	      deterministically. A struct_ops map that has been validated may
+ *	      not necessarily succeed in being registered if the call to @reg
+ *	      fails. For example, a valid struct_ops map may be loaded, but
+ *	      then fail to be registered due to there being another active
+ *	      struct_ops map on the system in the subsystem already. For this
+ *	      reason, if this callback is not defined, the check is skipped as
+ *	      the struct_ops map will have final verification performed in
+ *	      @reg.
+ * @type: BTF type.
+ * @value_type: Value type.
+ * @name: The name of the struct bpf_struct_ops object.
+ * @func_models: Func models
+ * @type_id: BTF type id.
+ * @value_id: BTF value id.
+ */
 struct bpf_struct_ops {
 	const struct bpf_verifier_ops *verifier_ops;
 	int (*init)(struct btf *btf);
-- 
GitLab


From 8897562f67b3e61ad736cd5c9f307447d33280e4 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@isovalent.com>
Date: Tue, 15 Aug 2023 09:53:41 +0100
Subject: [PATCH 1225/1806] net: Fix slab-out-of-bounds in inet[6]_steal_sock

Kumar reported a KASAN splat in tcp_v6_rcv:

  bash-5.2# ./test_progs -t btf_skc_cls_ingress
  ...
  [   51.810085] BUG: KASAN: slab-out-of-bounds in tcp_v6_rcv+0x2d7d/0x3440
  [   51.810458] Read of size 2 at addr ffff8881053f038c by task test_progs/226

The problem is that inet[6]_steal_sock accesses sk->sk_protocol without
accounting for request or timewait sockets. To fix this we can't just
check sock_common->skc_reuseport since that flag is present on timewait
sockets.

Instead, add a fullsock check to avoid the out of bands access of sk_protocol.

Fixes: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
Reported-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Link: https://lore.kernel.org/r/20230815-bpf-next-v2-1-95126eaa4c1b@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/net/inet6_hashtables.h | 2 +-
 include/net/inet_hashtables.h  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 284b5ce7205d9..533a7337865a4 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -116,7 +116,7 @@ struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
 	if (!sk)
 		return NULL;
 
-	if (!prefetched)
+	if (!prefetched || !sk_fullsock(sk))
 		return sk;
 
 	if (sk->sk_protocol == IPPROTO_TCP) {
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 8435572234143..3ecfeadbfa069 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -462,7 +462,7 @@ struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff,
 	if (!sk)
 		return NULL;
 
-	if (!prefetched)
+	if (!prefetched || !sk_fullsock(sk))
 		return sk;
 
 	if (sk->sk_protocol == IPPROTO_TCP) {
-- 
GitLab


From 84817d8c6042e6261ea45c53fe8b5a0bd55c3993 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 14:47:14 -0700
Subject: [PATCH 1226/1806] genetlink: push conditional locking into
 dumpit/done

Add helpers which take/release the genl mutex based
on family->parallel_ops. Remove the separation between
handling of ops in locked and parallel families.

Future patches would make the duplicated code grow even more.

Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230814214723.2924989-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netlink/genetlink.c | 90 ++++++++++++++++-------------------------
 1 file changed, 35 insertions(+), 55 deletions(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 6bd2ce51271f3..0d4285688ab98 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -52,6 +52,18 @@ static void genl_unlock_all(void)
 	up_write(&cb_lock);
 }
 
+static void genl_op_lock(const struct genl_family *family)
+{
+	if (!family->parallel_ops)
+		genl_lock();
+}
+
+static void genl_op_unlock(const struct genl_family *family)
+{
+	if (!family->parallel_ops)
+		genl_unlock();
+}
+
 static DEFINE_IDR(genl_fam_idr);
 
 /*
@@ -838,11 +850,9 @@ static int genl_start(struct netlink_callback *cb)
 
 	cb->data = info;
 	if (ops->start) {
-		if (!ctx->family->parallel_ops)
-			genl_lock();
+		genl_op_lock(ctx->family);
 		rc = ops->start(cb);
-		if (!ctx->family->parallel_ops)
-			genl_unlock();
+		genl_op_unlock(ctx->family);
 	}
 
 	if (rc) {
@@ -853,46 +863,34 @@ static int genl_start(struct netlink_callback *cb)
 	return rc;
 }
 
-static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	const struct genl_split_ops *ops = &genl_dumpit_info(cb)->op;
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	const struct genl_split_ops *ops = &info->op;
 	int rc;
 
-	genl_lock();
+	genl_op_lock(info->family);
 	rc = ops->dumpit(skb, cb);
-	genl_unlock();
+	genl_op_unlock(info->family);
 	return rc;
 }
 
-static int genl_lock_done(struct netlink_callback *cb)
+static int genl_done(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
 	const struct genl_split_ops *ops = &info->op;
 	int rc = 0;
 
 	if (ops->done) {
-		genl_lock();
+		genl_op_lock(info->family);
 		rc = ops->done(cb);
-		genl_unlock();
+		genl_op_unlock(info->family);
 	}
 	genl_family_rcv_msg_attrs_free(info->attrs);
 	genl_dumpit_info_free(info);
 	return rc;
 }
 
-static int genl_parallel_done(struct netlink_callback *cb)
-{
-	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	const struct genl_split_ops *ops = &info->op;
-	int rc = 0;
-
-	if (ops->done)
-		rc = ops->done(cb);
-	genl_family_rcv_msg_attrs_free(info->attrs);
-	genl_dumpit_info_free(info);
-	return rc;
-}
-
 static int genl_family_rcv_msg_dumpit(const struct genl_family *family,
 				      struct sk_buff *skb,
 				      struct nlmsghdr *nlh,
@@ -901,6 +899,14 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family,
 				      int hdrlen, struct net *net)
 {
 	struct genl_start_context ctx;
+	struct netlink_dump_control c = {
+		.module = family->module,
+		.data = &ctx,
+		.start = genl_start,
+		.dump = genl_dumpit,
+		.done = genl_done,
+		.extack = extack,
+	};
 	int err;
 
 	ctx.family = family;
@@ -909,31 +915,9 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family,
 	ctx.ops = ops;
 	ctx.hdrlen = hdrlen;
 
-	if (!family->parallel_ops) {
-		struct netlink_dump_control c = {
-			.module = family->module,
-			.data = &ctx,
-			.start = genl_start,
-			.dump = genl_lock_dumpit,
-			.done = genl_lock_done,
-			.extack = extack,
-		};
-
-		genl_unlock();
-		err = __netlink_dump_start(net->genl_sock, skb, nlh, &c);
-		genl_lock();
-	} else {
-		struct netlink_dump_control c = {
-			.module = family->module,
-			.data = &ctx,
-			.start = genl_start,
-			.dump = ops->dumpit,
-			.done = genl_parallel_done,
-			.extack = extack,
-		};
-
-		err = __netlink_dump_start(net->genl_sock, skb, nlh, &c);
-	}
+	genl_op_unlock(family);
+	err = __netlink_dump_start(net->genl_sock, skb, nlh, &c);
+	genl_op_lock(family);
 
 	return err;
 }
@@ -1065,13 +1049,9 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (family == NULL)
 		return -ENOENT;
 
-	if (!family->parallel_ops)
-		genl_lock();
-
+	genl_op_lock(family);
 	err = genl_family_rcv_msg(family, skb, nlh, extack);
-
-	if (!family->parallel_ops)
-		genl_unlock();
+	genl_op_unlock(family);
 
 	return err;
 }
-- 
GitLab


From fde9bd4a4d41b65a936d65eb416c1de27cb562f1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 14:47:15 -0700
Subject: [PATCH 1227/1806] genetlink: make genl_info->nlhdr const

struct netlink_callback has a const nlh pointer, make the
pointer in struct genl_info const as well, to make copying
between the two easier.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230814214723.2924989-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/genetlink.h | 2 +-
 net/ncsi/ncsi-netlink.c | 2 +-
 net/ncsi/ncsi-netlink.h | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index ed4622dd48281..0366d09255962 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -104,7 +104,7 @@ struct genl_family {
 struct genl_info {
 	u32			snd_seq;
 	u32			snd_portid;
-	struct nlmsghdr *	nlhdr;
+	const struct nlmsghdr *	nlhdr;
 	struct genlmsghdr *	genlhdr;
 	void *			userhdr;
 	struct nlattr **	attrs;
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index d27f4eccce6d7..a3a6753a1db76 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -563,7 +563,7 @@ int ncsi_send_netlink_timeout(struct ncsi_request *nr,
 int ncsi_send_netlink_err(struct net_device *dev,
 			  u32 snd_seq,
 			  u32 snd_portid,
-			  struct nlmsghdr *nlhdr,
+			  const struct nlmsghdr *nlhdr,
 			  int err)
 {
 	struct nlmsghdr *nlh;
diff --git a/net/ncsi/ncsi-netlink.h b/net/ncsi/ncsi-netlink.h
index 39a1a9d7bf77e..747767ea0aae6 100644
--- a/net/ncsi/ncsi-netlink.h
+++ b/net/ncsi/ncsi-netlink.h
@@ -19,7 +19,7 @@ int ncsi_send_netlink_timeout(struct ncsi_request *nr,
 int ncsi_send_netlink_err(struct net_device *dev,
 			  u32 snd_seq,
 			  u32 snd_portid,
-			  struct nlmsghdr *nlhdr,
+			  const struct nlmsghdr *nlhdr,
 			  int err);
 
 #endif /* __NCSI_NETLINK_H__ */
-- 
GitLab


From bffcc6882a1bb2be8c9420184966f4c2c822078e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 14:47:16 -0700
Subject: [PATCH 1228/1806] genetlink: remove userhdr from struct genl_info

Only three families use info->userhdr today and going forward
we discourage using fixed headers in new families.
So having the pointer to user header in struct genl_info
is an overkill. Compute the header pointer at runtime.

Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Aaron Conole <aconole@redhat.com>
Link: https://lore.kernel.org/r/20230814214723.2924989-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/block/drbd/drbd_nl.c |  9 +++++----
 include/net/genetlink.h      |  7 +++++--
 net/netlink/genetlink.c      |  1 -
 net/openvswitch/conntrack.c  |  2 +-
 net/openvswitch/datapath.c   | 29 ++++++++++++++++-------------
 net/openvswitch/meter.c      | 10 +++++-----
 net/tipc/netlink_compat.c    |  2 +-
 7 files changed, 33 insertions(+), 27 deletions(-)

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index cddae6f4b00fe..d3538bd83fb3b 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -159,7 +159,7 @@ static int drbd_msg_sprintf_info(struct sk_buff *skb, const char *fmt, ...)
 static int drbd_adm_prepare(struct drbd_config_context *adm_ctx,
 	struct sk_buff *skb, struct genl_info *info, unsigned flags)
 {
-	struct drbd_genlmsghdr *d_in = info->userhdr;
+	struct drbd_genlmsghdr *d_in = genl_info_userhdr(info);
 	const u8 cmd = info->genlhdr->cmd;
 	int err;
 
@@ -1396,8 +1396,9 @@ static void drbd_suspend_al(struct drbd_device *device)
 
 static bool should_set_defaults(struct genl_info *info)
 {
-	unsigned flags = ((struct drbd_genlmsghdr*)info->userhdr)->flags;
-	return 0 != (flags & DRBD_GENL_F_SET_DEFAULTS);
+	struct drbd_genlmsghdr *dh = genl_info_userhdr(info);
+
+	return 0 != (dh->flags & DRBD_GENL_F_SET_DEFAULTS);
 }
 
 static unsigned int drbd_al_extents_max(struct drbd_backing_dev *bdev)
@@ -4276,7 +4277,7 @@ static void device_to_info(struct device_info *info,
 int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
-	struct drbd_genlmsghdr *dh = info->userhdr;
+	struct drbd_genlmsghdr *dh = genl_info_userhdr(info);
 	enum drbd_ret_code retcode;
 
 	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE);
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 0366d09255962..9dc21ec157343 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -95,7 +95,6 @@ struct genl_family {
  * @snd_portid: netlink portid of sender
  * @nlhdr: netlink message header
  * @genlhdr: generic netlink message header
- * @userhdr: user specific header
  * @attrs: netlink attributes
  * @_net: network namespace
  * @user_ptr: user pointers
@@ -106,7 +105,6 @@ struct genl_info {
 	u32			snd_portid;
 	const struct nlmsghdr *	nlhdr;
 	struct genlmsghdr *	genlhdr;
-	void *			userhdr;
 	struct nlattr **	attrs;
 	possible_net_t		_net;
 	void *			user_ptr[2];
@@ -123,6 +121,11 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net)
 	write_pnet(&info->_net, net);
 }
 
+static inline void *genl_info_userhdr(const struct genl_info *info)
+{
+	return (u8 *)info->genlhdr + GENL_HDRLEN;
+}
+
 #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg)
 
 #define GENL_SET_ERR_MSG_FMT(info, msg, args...) \
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 0d4285688ab98..f98f730bb245b 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -943,7 +943,6 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family,
 	info.snd_portid = NETLINK_CB(skb).portid;
 	info.nlhdr = nlh;
 	info.genlhdr = nlmsg_data(nlh);
-	info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN;
 	info.attrs = attrbuf;
 	info.extack = extack;
 	genl_info_net_set(&info, net);
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 0cfa1e9482e63..0b9a785dea459 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1605,7 +1605,7 @@ static struct sk_buff *
 ovs_ct_limit_cmd_reply_start(struct genl_info *info, u8 cmd,
 			     struct ovs_header **ovs_reply_header)
 {
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct sk_buff *skb;
 
 	skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index d33cb739883f7..0a974eeef76e3 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -590,7 +590,7 @@ out:
 
 static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 {
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct net *net = sock_net(skb->sk);
 	struct nlattr **a = info->attrs;
 	struct sw_flow_actions *acts;
@@ -967,7 +967,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr **a = info->attrs;
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct sw_flow *flow = NULL, *new_flow;
 	struct sw_flow_mask mask;
 	struct sk_buff *reply;
@@ -1214,7 +1214,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr **a = info->attrs;
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct sw_flow_key key;
 	struct sw_flow *flow;
 	struct sk_buff *reply = NULL;
@@ -1315,7 +1315,7 @@ error:
 static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct net *net = sock_net(skb->sk);
 	struct sw_flow_key key;
 	struct sk_buff *reply;
@@ -1374,7 +1374,7 @@ unlock:
 static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct net *net = sock_net(skb->sk);
 	struct sw_flow_key key;
 	struct sk_buff *reply;
@@ -1642,7 +1642,7 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb,
 {
 	struct datapath *dp;
 
-	dp = lookup_datapath(sock_net(skb->sk), info->userhdr,
+	dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info),
 			     info->attrs);
 	if (IS_ERR(dp))
 		return;
@@ -1935,7 +1935,8 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 
 	ovs_lock();
-	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
+	dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info),
+			     info->attrs);
 	err = PTR_ERR(dp);
 	if (IS_ERR(dp))
 		goto err_unlock_free;
@@ -1968,7 +1969,8 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 
 	ovs_lock();
-	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
+	dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info),
+			     info->attrs);
 	err = PTR_ERR(dp);
 	if (IS_ERR(dp))
 		goto err_unlock_free;
@@ -2003,7 +2005,8 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 
 	ovs_lock();
-	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
+	dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info),
+			     info->attrs);
 	if (IS_ERR(dp)) {
 		err = PTR_ERR(dp);
 		goto err_unlock_free;
@@ -2246,7 +2249,7 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom)
 static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct vport_parms parms;
 	struct sk_buff *reply;
 	struct vport *vport;
@@ -2348,7 +2351,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 
 	ovs_lock();
-	vport = lookup_vport(sock_net(skb->sk), info->userhdr, a);
+	vport = lookup_vport(sock_net(skb->sk), genl_info_userhdr(info), a);
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
 		goto exit_unlock_free;
@@ -2404,7 +2407,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 
 	ovs_lock();
-	vport = lookup_vport(sock_net(skb->sk), info->userhdr, a);
+	vport = lookup_vport(sock_net(skb->sk), genl_info_userhdr(info), a);
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
 		goto exit_unlock_free;
@@ -2447,7 +2450,7 @@ exit_unlock_free:
 static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct sk_buff *reply;
 	struct vport *vport;
 	int err;
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index c4ebf810e4b1b..cc08e0403909a 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -211,7 +211,7 @@ ovs_meter_cmd_reply_start(struct genl_info *info, u8 cmd,
 			  struct ovs_header **ovs_reply_header)
 {
 	struct sk_buff *skb;
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 
 	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
 	if (!skb)
@@ -272,7 +272,7 @@ error:
 
 static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info)
 {
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct ovs_header *ovs_reply_header;
 	struct nlattr *nla, *band_nla;
 	struct sk_buff *reply;
@@ -409,7 +409,7 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct dp_meter *meter, *old_meter;
 	struct sk_buff *reply;
 	struct ovs_header *ovs_reply_header;
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct dp_meter_table *meter_tbl;
 	struct datapath *dp;
 	int err;
@@ -482,7 +482,7 @@ exit_free_meter:
 
 static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info)
 {
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct ovs_header *ovs_reply_header;
 	struct nlattr **a = info->attrs;
 	struct dp_meter *meter;
@@ -535,7 +535,7 @@ exit_unlock:
 
 static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info)
 {
-	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
 	struct ovs_header *ovs_reply_header;
 	struct nlattr **a = info->attrs;
 	struct dp_meter *old_meter;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 9b47c84092319..299cd6754f14c 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -1294,7 +1294,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info)
 	struct tipc_nl_compat_msg msg;
 	struct nlmsghdr *req_nlh;
 	struct nlmsghdr *rep_nlh;
-	struct tipc_genlmsghdr *req_userhdr = info->userhdr;
+	struct tipc_genlmsghdr *req_userhdr = genl_info_userhdr(info);
 
 	memset(&msg, 0, sizeof(msg));
 
-- 
GitLab


From 9272af109fe65d1a13f28c5c13777b62d3e97e8c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 14:47:17 -0700
Subject: [PATCH 1229/1806] genetlink: add struct genl_info to struct
 genl_dumpit_info

Netlink GET implementations must currently juggle struct genl_info
and struct netlink_callback, depending on whether they were called
from doit or dumpit.

Add genl_info to the dump state and populate the fields.
This way implementations can simply pass struct genl_info around.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230814214723.2924989-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/genetlink.h |  8 ++++++++
 net/netlink/genetlink.c | 16 ++++++++++++++--
 2 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 9dc21ec157343..86c8eaaa3a431 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -250,11 +250,13 @@ struct genl_split_ops {
  * @family: generic netlink family - for internal genl code usage
  * @op: generic netlink ops - for internal genl code usage
  * @attrs: netlink attributes
+ * @info: struct genl_info describing the request
  */
 struct genl_dumpit_info {
 	const struct genl_family *family;
 	struct genl_split_ops op;
 	struct nlattr **attrs;
+	struct genl_info info;
 };
 
 static inline const struct genl_dumpit_info *
@@ -263,6 +265,12 @@ genl_dumpit_info(struct netlink_callback *cb)
 	return cb->data;
 }
 
+static inline const struct genl_info *
+genl_info_dump(struct netlink_callback *cb)
+{
+	return &genl_dumpit_info(cb)->info;
+}
+
 int genl_register_family(struct genl_family *family);
 int genl_unregister_family(const struct genl_family *family);
 void genl_notify(const struct genl_family *family, struct sk_buff *skb,
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index f98f730bb245b..82ad26970b9bb 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -847,6 +847,14 @@ static int genl_start(struct netlink_callback *cb)
 	info->family = ctx->family;
 	info->op = *ops;
 	info->attrs = attrs;
+	info->info.snd_seq	= cb->nlh->nlmsg_seq;
+	info->info.snd_portid	= NETLINK_CB(cb->skb).portid;
+	info->info.nlhdr	= cb->nlh;
+	info->info.genlhdr	= nlmsg_data(cb->nlh);
+	info->info.attrs	= attrs;
+	genl_info_net_set(&info->info, sock_net(cb->skb->sk));
+	info->info.extack	= cb->extack;
+	memset(&info->info.user_ptr, 0, sizeof(info->info.user_ptr));
 
 	cb->data = info;
 	if (ops->start) {
@@ -865,10 +873,12 @@ static int genl_start(struct netlink_callback *cb)
 
 static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	struct genl_dumpit_info *info = cb->data;
 	const struct genl_split_ops *ops = &info->op;
 	int rc;
 
+	info->info.extack = cb->extack;
+
 	genl_op_lock(info->family);
 	rc = ops->dumpit(skb, cb);
 	genl_op_unlock(info->family);
@@ -877,10 +887,12 @@ static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 static int genl_done(struct netlink_callback *cb)
 {
-	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	struct genl_dumpit_info *info = cb->data;
 	const struct genl_split_ops *ops = &info->op;
 	int rc = 0;
 
+	info->info.extack = cb->extack;
+
 	if (ops->done) {
 		genl_op_lock(info->family);
 		rc = ops->done(cb);
-- 
GitLab


From 7288dd2fd4888c85c687f8ded69c280938d1a7b6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 14:47:18 -0700
Subject: [PATCH 1230/1806] genetlink: use attrs from struct genl_info

Since dumps carry struct genl_info now, use the attrs pointer
from genl_info and remove the one in struct genl_dumpit_info.

Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230814214723.2924989-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/wireguard/netlink.c | 2 +-
 include/net/genetlink.h         | 1 -
 net/devlink/health.c            | 4 ++--
 net/devlink/leftover.c          | 6 +++---
 net/devlink/netlink.c           | 2 +-
 net/ethtool/netlink.c           | 3 ++-
 net/ethtool/tunnels.c           | 2 +-
 net/ieee802154/nl802154.c       | 4 ++--
 net/netlink/genetlink.c         | 7 +++----
 net/nfc/netlink.c               | 4 ++--
 net/tipc/netlink_compat.c       | 2 +-
 net/tipc/node.c                 | 4 ++--
 net/tipc/socket.c               | 2 +-
 net/tipc/udp_media.c            | 2 +-
 14 files changed, 22 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c
index 6d1bd9f52d02a..dc09b75a32485 100644
--- a/drivers/net/wireguard/netlink.c
+++ b/drivers/net/wireguard/netlink.c
@@ -200,7 +200,7 @@ static int wg_get_device_start(struct netlink_callback *cb)
 {
 	struct wg_device *wg;
 
-	wg = lookup_interface(genl_dumpit_info(cb)->attrs, cb->skb);
+	wg = lookup_interface(genl_info_dump(cb)->attrs, cb->skb);
 	if (IS_ERR(wg))
 		return PTR_ERR(wg);
 	DUMP_CTX(cb)->wg = wg;
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 86c8eaaa3a431..a8a15b9c22c8a 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -255,7 +255,6 @@ struct genl_split_ops {
 struct genl_dumpit_info {
 	const struct genl_family *family;
 	struct genl_split_ops op;
-	struct nlattr **attrs;
 	struct genl_info info;
 };
 
diff --git a/net/devlink/health.c b/net/devlink/health.c
index a85bdec348011..638cad8d5c654 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -390,7 +390,7 @@ static int devlink_nl_health_reporter_get_dump_one(struct sk_buff *msg,
 						   int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	const struct genl_info *info = genl_info_dump(cb);
 	struct devlink_health_reporter *reporter;
 	unsigned long port_index_end = ULONG_MAX;
 	struct nlattr **attrs = info->attrs;
@@ -1264,7 +1264,7 @@ out:
 static struct devlink_health_reporter *
 devlink_health_reporter_get_from_cb(struct netlink_callback *cb)
 {
-	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	const struct genl_info *info = genl_info_dump(cb);
 	struct devlink_health_reporter *reporter;
 	struct nlattr **attrs = info->attrs;
 	struct devlink *devlink;
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 3883a90d32bb2..72ba8a7165255 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -5201,7 +5201,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
 	struct nlattr *chunks_attr, *region_attr, *snapshot_attr;
 	u64 ret_offset, start_offset, end_offset = U64_MAX;
-	struct nlattr **attrs = info->attrs;
+	struct nlattr **attrs = info->info.attrs;
 	struct devlink_port *port = NULL;
 	devlink_chunk_fill_t *region_cb;
 	struct devlink_region *region;
@@ -5224,8 +5224,8 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		goto out_unlock;
 	}
 
-	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
-		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+	if (attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]);
 
 		port = devlink_port_get_by_index(devlink, index);
 		if (!port) {
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index a9b43b0c59598..72a5005a64cd7 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -228,7 +228,7 @@ static int devlink_nl_inst_iter_dumpit(struct sk_buff *msg,
 int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 		      devlink_nl_dump_one_func_t *dump_one)
 {
-	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	const struct genl_info *info = genl_info_dump(cb);
 	struct nlattr **attrs = info->attrs;
 	int flags = NLM_F_MULTI;
 
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index ae344f1b0bbd1..9fc7c41f47863 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -538,7 +538,8 @@ static int ethnl_default_start(struct netlink_callback *cb)
 		goto free_req_info;
 	}
 
-	ret = ethnl_default_parse(req_info, info->attrs, sock_net(cb->skb->sk),
+	ret = ethnl_default_parse(req_info, info->info.attrs,
+				  sock_net(cb->skb->sk),
 				  ops, cb->extack, false);
 	if (req_info->dev) {
 		/* We ignore device specification in dump requests but as the
diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c
index 05f752557b5e0..b4ce47dd2aa60 100644
--- a/net/ethtool/tunnels.c
+++ b/net/ethtool/tunnels.c
@@ -219,7 +219,7 @@ int ethnl_tunnel_info_start(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
 	struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx;
-	struct nlattr **tb = info->attrs;
+	struct nlattr **tb = info->info.attrs;
 	int ret;
 
 	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index d610c1886160c..1a265a4213086 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -262,7 +262,7 @@ nl802154_prepare_wpan_dev_dump(struct sk_buff *skb,
 
 	if (!cb->args[0]) {
 		*wpan_dev = __cfg802154_wpan_dev_from_attrs(sock_net(skb->sk),
-							    info->attrs);
+							    info->info.attrs);
 		if (IS_ERR(*wpan_dev)) {
 			err = PTR_ERR(*wpan_dev);
 			goto out_unlock;
@@ -570,7 +570,7 @@ static int nl802154_dump_wpan_phy_parse(struct sk_buff *skb,
 					struct nl802154_dump_wpan_phy_state *state)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	struct nlattr **tb = info->attrs;
+	struct nlattr **tb = info->info.attrs;
 
 	if (tb[NL802154_ATTR_WPAN_PHY])
 		state->filter_wpan_phy = nla_get_u32(tb[NL802154_ATTR_WPAN_PHY]);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 82ad26970b9bb..d47879d5a74ca 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -846,7 +846,6 @@ static int genl_start(struct netlink_callback *cb)
 	}
 	info->family = ctx->family;
 	info->op = *ops;
-	info->attrs = attrs;
 	info->info.snd_seq	= cb->nlh->nlmsg_seq;
 	info->info.snd_portid	= NETLINK_CB(cb->skb).portid;
 	info->info.nlhdr	= cb->nlh;
@@ -864,7 +863,7 @@ static int genl_start(struct netlink_callback *cb)
 	}
 
 	if (rc) {
-		genl_family_rcv_msg_attrs_free(info->attrs);
+		genl_family_rcv_msg_attrs_free(info->info.attrs);
 		genl_dumpit_info_free(info);
 		cb->data = NULL;
 	}
@@ -898,7 +897,7 @@ static int genl_done(struct netlink_callback *cb)
 		rc = ops->done(cb);
 		genl_op_unlock(info->family);
 	}
-	genl_family_rcv_msg_attrs_free(info->attrs);
+	genl_family_rcv_msg_attrs_free(info->info.attrs);
 	genl_dumpit_info_free(info);
 	return rc;
 }
@@ -1387,7 +1386,7 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
 	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
-	struct nlattr **tb = info->attrs;
+	struct nlattr **tb = info->info.attrs;
 	const struct genl_family *rt;
 	struct genl_op_iter i;
 	int err;
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index e9ac6a6f934e7..aa1dbf654c3e5 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -110,10 +110,10 @@ static struct nfc_dev *__get_device_from_cb(struct netlink_callback *cb)
 	struct nfc_dev *dev;
 	u32 idx;
 
-	if (!info->attrs[NFC_ATTR_DEVICE_INDEX])
+	if (!info->info.attrs[NFC_ATTR_DEVICE_INDEX])
 		return ERR_PTR(-EINVAL);
 
-	idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]);
+	idx = nla_get_u32(info->info.attrs[NFC_ATTR_DEVICE_INDEX]);
 
 	dev = nfc_get_device(idx);
 	if (!dev)
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 299cd6754f14c..5bc076f2fa74a 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -208,7 +208,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 		goto err_out;
 	}
 
-	info.attrs = attrbuf;
+	info.info.attrs = attrbuf;
 
 	if (nlmsg_len(cb.nlh) > 0) {
 		err = nlmsg_parse_deprecated(cb.nlh, GENL_HDRLEN, attrbuf,
diff --git a/net/tipc/node.c b/net/tipc/node.c
index a9c5b6594889b..3105abe97bb9c 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -2662,7 +2662,7 @@ static int __tipc_nl_add_node_links(struct net *net, struct tipc_nl_msg *msg,
 int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
-	struct nlattr **attrs = genl_dumpit_info(cb)->attrs;
+	struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs;
 	struct nlattr *link[TIPC_NLA_LINK_MAX + 1];
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_node *node;
@@ -2870,7 +2870,7 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,
 	int err;
 
 	if (!prev_node) {
-		struct nlattr **attrs = genl_dumpit_info(cb)->attrs;
+		struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs;
 		struct nlattr *mon[TIPC_NLA_MON_MAX + 1];
 
 		if (!attrs[TIPC_NLA_MON])
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index ef8e5139a8737..bb1118d02f953 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -3791,7 +3791,7 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	struct tipc_sock *tsk;
 
 	if (!tsk_portid) {
-		struct nlattr **attrs = genl_dumpit_info(cb)->attrs;
+		struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs;
 		struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1];
 
 		if (!attrs[TIPC_NLA_SOCK])
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 926232557e77c..f892b0903dbaf 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -465,7 +465,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb)
 	int i;
 
 	if (!bid && !skip_cnt) {
-		struct nlattr **attrs = genl_dumpit_info(cb)->attrs;
+		struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs;
 		struct net *net = sock_net(skb->sk);
 		struct nlattr *battrs[TIPC_NLA_BEARER_MAX + 1];
 		char *bname;
-- 
GitLab


From 5c670a010de46687ed27553602d8131ce4d7a9fb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 14:47:19 -0700
Subject: [PATCH 1231/1806] genetlink: add a family pointer to struct genl_info

Having family in struct genl_info is quite useful. It cuts
down the number of arguments which need to be passed to
helpers which already take struct genl_info.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230814214723.2924989-7-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/genetlink.h |  4 ++--
 net/netlink/genetlink.c | 21 ++++++++++++---------
 2 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index a8a15b9c22c8a..6b858c4cba5b8 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -93,6 +93,7 @@ struct genl_family {
  * struct genl_info - receiving information
  * @snd_seq: sending sequence number
  * @snd_portid: netlink portid of sender
+ * @family: generic netlink family
  * @nlhdr: netlink message header
  * @genlhdr: generic netlink message header
  * @attrs: netlink attributes
@@ -103,6 +104,7 @@ struct genl_family {
 struct genl_info {
 	u32			snd_seq;
 	u32			snd_portid;
+	const struct genl_family *family;
 	const struct nlmsghdr *	nlhdr;
 	struct genlmsghdr *	genlhdr;
 	struct nlattr **	attrs;
@@ -247,13 +249,11 @@ struct genl_split_ops {
 
 /**
  * struct genl_dumpit_info - info that is available during dumpit op call
- * @family: generic netlink family - for internal genl code usage
  * @op: generic netlink ops - for internal genl code usage
  * @attrs: netlink attributes
  * @info: struct genl_info describing the request
  */
 struct genl_dumpit_info {
-	const struct genl_family *family;
 	struct genl_split_ops op;
 	struct genl_info info;
 };
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index d47879d5a74ca..8315d31b53db4 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -844,8 +844,8 @@ static int genl_start(struct netlink_callback *cb)
 		genl_family_rcv_msg_attrs_free(attrs);
 		return -ENOMEM;
 	}
-	info->family = ctx->family;
 	info->op = *ops;
+	info->info.family	= ctx->family;
 	info->info.snd_seq	= cb->nlh->nlmsg_seq;
 	info->info.snd_portid	= NETLINK_CB(cb->skb).portid;
 	info->info.nlhdr	= cb->nlh;
@@ -872,11 +872,12 @@ static int genl_start(struct netlink_callback *cb)
 
 static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct genl_dumpit_info *info = cb->data;
-	const struct genl_split_ops *ops = &info->op;
+	struct genl_dumpit_info *dump_info = cb->data;
+	const struct genl_split_ops *ops = &dump_info->op;
+	struct genl_info *info = &dump_info->info;
 	int rc;
 
-	info->info.extack = cb->extack;
+	info->extack = cb->extack;
 
 	genl_op_lock(info->family);
 	rc = ops->dumpit(skb, cb);
@@ -886,19 +887,20 @@ static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 static int genl_done(struct netlink_callback *cb)
 {
-	struct genl_dumpit_info *info = cb->data;
-	const struct genl_split_ops *ops = &info->op;
+	struct genl_dumpit_info *dump_info = cb->data;
+	const struct genl_split_ops *ops = &dump_info->op;
+	struct genl_info *info = &dump_info->info;
 	int rc = 0;
 
-	info->info.extack = cb->extack;
+	info->extack = cb->extack;
 
 	if (ops->done) {
 		genl_op_lock(info->family);
 		rc = ops->done(cb);
 		genl_op_unlock(info->family);
 	}
-	genl_family_rcv_msg_attrs_free(info->info.attrs);
-	genl_dumpit_info_free(info);
+	genl_family_rcv_msg_attrs_free(info->attrs);
+	genl_dumpit_info_free(dump_info);
 	return rc;
 }
 
@@ -952,6 +954,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family,
 
 	info.snd_seq = nlh->nlmsg_seq;
 	info.snd_portid = NETLINK_CB(skb).portid;
+	info.family = family;
 	info.nlhdr = nlh;
 	info.genlhdr = nlmsg_data(nlh);
 	info.attrs = attrbuf;
-- 
GitLab


From 5aa51d9f889ca61201044b28677eb60236b0d746 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 14:47:20 -0700
Subject: [PATCH 1232/1806] genetlink: add genlmsg_iput() API

Add some APIs and helpers required for convenient construction
of replies and notifications based on struct genl_info.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230814214723.2924989-8-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/genetlink.h | 54 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 53 insertions(+), 1 deletion(-)

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 6b858c4cba5b8..e18a4c0d69eed 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -113,7 +113,7 @@ struct genl_info {
 	struct netlink_ext_ack *extack;
 };
 
-static inline struct net *genl_info_net(struct genl_info *info)
+static inline struct net *genl_info_net(const struct genl_info *info)
 {
 	return read_pnet(&info->_net);
 }
@@ -270,6 +270,32 @@ genl_info_dump(struct netlink_callback *cb)
 	return &genl_dumpit_info(cb)->info;
 }
 
+/**
+ * genl_info_init_ntf() - initialize genl_info for notifications
+ * @info:   genl_info struct to set up
+ * @family: pointer to the genetlink family
+ * @cmd:    command to be used in the notification
+ *
+ * Initialize a locally declared struct genl_info to pass to various APIs.
+ * Intended to be used when creating notifications.
+ */
+static inline void
+genl_info_init_ntf(struct genl_info *info, const struct genl_family *family,
+		   u8 cmd)
+{
+	struct genlmsghdr *hdr = (void *) &info->user_ptr[0];
+
+	memset(info, 0, sizeof(*info));
+	info->family = family;
+	info->genlhdr = hdr;
+	hdr->cmd = cmd;
+}
+
+static inline bool genl_info_is_ntf(const struct genl_info *info)
+{
+	return !info->nlhdr;
+}
+
 int genl_register_family(struct genl_family *family);
 int genl_unregister_family(const struct genl_family *family);
 void genl_notify(const struct genl_family *family, struct sk_buff *skb,
@@ -278,6 +304,32 @@ void genl_notify(const struct genl_family *family, struct sk_buff *skb,
 void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq,
 		  const struct genl_family *family, int flags, u8 cmd);
 
+static inline void *
+__genlmsg_iput(struct sk_buff *skb, const struct genl_info *info, int flags)
+{
+	return genlmsg_put(skb, info->snd_portid, info->snd_seq, info->family,
+			   flags, info->genlhdr->cmd);
+}
+
+/**
+ * genlmsg_iput - start genetlink message based on genl_info
+ * @skb: skb in which message header will be placed
+ * @info: genl_info as provided to do/dump handlers
+ *
+ * Convenience wrapper which starts a genetlink message based on
+ * information in user request. @info should be either the struct passed
+ * by genetlink core to do/dump handlers (when constructing replies to
+ * such requests) or a struct initialized by genl_info_init_ntf()
+ * when constructing notifications.
+ *
+ * Returns pointer to new genetlink header.
+ */
+static inline void *
+genlmsg_iput(struct sk_buff *skb, const struct genl_info *info)
+{
+	return __genlmsg_iput(skb, info, 0);
+}
+
 /**
  * genlmsg_nlhdr - Obtain netlink header from user specified header
  * @user_hdr: user header as returned from genlmsg_put()
-- 
GitLab


From 0e19d3108aeab6a9edcef07bf0f123fa2961d0d6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 14:47:21 -0700
Subject: [PATCH 1233/1806] netdev-genl: use struct genl_info for reply
 construction

Use the just added APIs to make the code simpler.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230814214723.2924989-9-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netdev-genl.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 797c813c7c77b..c1aea8b756b6c 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -10,11 +10,11 @@
 
 static int
 netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
-		   u32 portid, u32 seq, int flags, u32 cmd)
+		   const struct genl_info *info)
 {
 	void *hdr;
 
-	hdr = genlmsg_put(rsp, portid, seq, &netdev_nl_family, flags, cmd);
+	hdr = genlmsg_iput(rsp, info);
 	if (!hdr)
 		return -EMSGSIZE;
 
@@ -41,17 +41,20 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
 static void
 netdev_genl_dev_notify(struct net_device *netdev, int cmd)
 {
+	struct genl_info info;
 	struct sk_buff *ntf;
 
 	if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev),
 				NETDEV_NLGRP_MGMT))
 		return;
 
+	genl_info_init_ntf(&info, &netdev_nl_family, cmd);
+
 	ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!ntf)
 		return;
 
-	if (netdev_nl_dev_fill(netdev, ntf, 0, 0, 0, cmd)) {
+	if (netdev_nl_dev_fill(netdev, ntf, &info)) {
 		nlmsg_free(ntf);
 		return;
 	}
@@ -80,8 +83,7 @@ int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info)
 
 	netdev = __dev_get_by_index(genl_info_net(info), ifindex);
 	if (netdev)
-		err = netdev_nl_dev_fill(netdev, rsp, info->snd_portid,
-					 info->snd_seq, 0, info->genlhdr->cmd);
+		err = netdev_nl_dev_fill(netdev, rsp, info);
 	else
 		err = -ENODEV;
 
@@ -105,10 +107,7 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rtnl_lock();
 	for_each_netdev_dump(net, netdev, cb->args[0]) {
-		err = netdev_nl_dev_fill(netdev, skb,
-					 NETLINK_CB(cb->skb).portid,
-					 cb->nlh->nlmsg_seq, 0,
-					 NETDEV_CMD_DEV_GET);
+		err = netdev_nl_dev_fill(netdev, skb, genl_info_dump(cb));
 		if (err < 0)
 			break;
 	}
-- 
GitLab


From ec0e5b09b834da3889be8458bb0451c3baa803d9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 14:47:22 -0700
Subject: [PATCH 1234/1806] ethtool: netlink: simplify arguments to
 ethnl_default_parse()

Pass struct genl_info directly instead of its members.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230814214723.2924989-10-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/netlink.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 9fc7c41f47863..f7b3171a0aad2 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -316,10 +316,8 @@ static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
 /**
  * ethnl_default_parse() - Parse request message
  * @req_info:    pointer to structure to put data into
- * @tb:		 parsed attributes
- * @net:         request netns
+ * @info:	 genl_info from the request
  * @request_ops: struct request_ops for request type
- * @extack:      netlink extack for error reporting
  * @require_dev: fail if no device identified in header
  *
  * Parse universal request header and call request specific ->parse_request()
@@ -328,19 +326,21 @@ static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
  * Return: 0 on success or negative error code
  */
 static int ethnl_default_parse(struct ethnl_req_info *req_info,
-			       struct nlattr **tb, struct net *net,
+			       const struct genl_info *info,
 			       const struct ethnl_request_ops *request_ops,
-			       struct netlink_ext_ack *extack, bool require_dev)
+			       bool require_dev)
 {
+	struct nlattr **tb = info->attrs;
 	int ret;
 
 	ret = ethnl_parse_header_dev_get(req_info, tb[request_ops->hdr_attr],
-					 net, extack, require_dev);
+					 genl_info_net(info), info->extack,
+					 require_dev);
 	if (ret < 0)
 		return ret;
 
 	if (request_ops->parse_request) {
-		ret = request_ops->parse_request(req_info, tb, extack);
+		ret = request_ops->parse_request(req_info, tb, info->extack);
 		if (ret < 0)
 			return ret;
 	}
@@ -393,8 +393,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	}
 
-	ret = ethnl_default_parse(req_info, info->attrs, genl_info_net(info),
-				  ops, info->extack, !ops->allow_nodev_do);
+	ret = ethnl_default_parse(req_info, info, ops, !ops->allow_nodev_do);
 	if (ret < 0)
 		goto err_dev;
 	ethnl_init_reply_data(reply_data, ops, req_info->dev);
@@ -538,9 +537,7 @@ static int ethnl_default_start(struct netlink_callback *cb)
 		goto free_req_info;
 	}
 
-	ret = ethnl_default_parse(req_info, info->info.attrs,
-				  sock_net(cb->skb->sk),
-				  ops, cb->extack, false);
+	ret = ethnl_default_parse(req_info, &info->info, ops, false);
 	if (req_info->dev) {
 		/* We ignore device specification in dump requests but as the
 		 * same parser as for non-dump (doit) requests is used, it
-- 
GitLab


From f946270d05c26044c67511ef5a9d91e06962d79f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 14:47:23 -0700
Subject: [PATCH 1235/1806] ethtool: netlink: always pass genl_info to
 .prepare_data

We had a number of bugs in the past because developers forgot
to fully test dumps, which pass NULL as info to .prepare_data.
.prepare_data implementations would try to access info->extack
leading to a null-deref.

Now that dumps and notifications can access struct genl_info
we can pass it in, and remove the info null checks.

Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> # pause
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230814214723.2924989-11-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/channels.c    |  2 +-
 net/ethtool/coalesce.c    |  6 +++---
 net/ethtool/debug.c       |  2 +-
 net/ethtool/eee.c         |  2 +-
 net/ethtool/eeprom.c      |  9 ++++-----
 net/ethtool/features.c    |  2 +-
 net/ethtool/fec.c         |  2 +-
 net/ethtool/linkinfo.c    |  2 +-
 net/ethtool/linkmodes.c   |  2 +-
 net/ethtool/linkstate.c   |  2 +-
 net/ethtool/mm.c          |  2 +-
 net/ethtool/module.c      |  5 ++---
 net/ethtool/netlink.c     | 13 ++++++++-----
 net/ethtool/netlink.h     |  2 +-
 net/ethtool/pause.c       |  5 ++---
 net/ethtool/phc_vclocks.c |  2 +-
 net/ethtool/plca.c        |  4 ++--
 net/ethtool/privflags.c   |  2 +-
 net/ethtool/pse-pd.c      |  6 +++---
 net/ethtool/rings.c       |  5 ++---
 net/ethtool/rss.c         |  3 ++-
 net/ethtool/stats.c       |  5 ++---
 net/ethtool/strset.c      |  2 +-
 net/ethtool/tsinfo.c      |  2 +-
 net/ethtool/wol.c         |  5 +++--
 25 files changed, 47 insertions(+), 47 deletions(-)

diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c
index 61c40e889a4de..7b4bbd674bae7 100644
--- a/net/ethtool/channels.c
+++ b/net/ethtool/channels.c
@@ -24,7 +24,7 @@ const struct nla_policy ethnl_channels_get_policy[] = {
 
 static int channels_prepare_data(const struct ethnl_req_info *req_base,
 				 struct ethnl_reply_data *reply_base,
-				 struct genl_info *info)
+				 const struct genl_info *info)
 {
 	struct channels_reply_data *data = CHANNELS_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c
index 01a59ce211c8f..83112c1a71ae8 100644
--- a/net/ethtool/coalesce.c
+++ b/net/ethtool/coalesce.c
@@ -59,10 +59,9 @@ const struct nla_policy ethnl_coalesce_get_policy[] = {
 
 static int coalesce_prepare_data(const struct ethnl_req_info *req_base,
 				 struct ethnl_reply_data *reply_base,
-				 struct genl_info *info)
+				 const struct genl_info *info)
 {
 	struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base);
-	struct netlink_ext_ack *extack = info ? info->extack : NULL;
 	struct net_device *dev = reply_base->dev;
 	int ret;
 
@@ -73,7 +72,8 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base,
 	if (ret < 0)
 		return ret;
 	ret = dev->ethtool_ops->get_coalesce(dev, &data->coalesce,
-					     &data->kernel_coalesce, extack);
+					     &data->kernel_coalesce,
+					     info->extack);
 	ethnl_ops_complete(dev);
 
 	return ret;
diff --git a/net/ethtool/debug.c b/net/ethtool/debug.c
index e4369769817ec..0b2dea56d4617 100644
--- a/net/ethtool/debug.c
+++ b/net/ethtool/debug.c
@@ -23,7 +23,7 @@ const struct nla_policy ethnl_debug_get_policy[] = {
 
 static int debug_prepare_data(const struct ethnl_req_info *req_base,
 			      struct ethnl_reply_data *reply_base,
-			      struct genl_info *info)
+			      const struct genl_info *info)
 {
 	struct debug_reply_data *data = DEBUG_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c
index 42104bcb0e47b..2853394d06a89 100644
--- a/net/ethtool/eee.c
+++ b/net/ethtool/eee.c
@@ -26,7 +26,7 @@ const struct nla_policy ethnl_eee_get_policy[] = {
 
 static int eee_prepare_data(const struct ethnl_req_info *req_base,
 			    struct ethnl_reply_data *reply_base,
-			    struct genl_info *info)
+			    const struct genl_info *info)
 {
 	struct eee_reply_data *data = EEE_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c
index 49c0a2a77f02d..6209c3a9c8f72 100644
--- a/net/ethtool/eeprom.c
+++ b/net/ethtool/eeprom.c
@@ -51,8 +51,7 @@ static int fallback_set_params(struct eeprom_req_info *request,
 }
 
 static int eeprom_fallback(struct eeprom_req_info *request,
-			   struct eeprom_reply_data *reply,
-			   struct genl_info *info)
+			   struct eeprom_reply_data *reply)
 {
 	struct net_device *dev = reply->base.dev;
 	struct ethtool_modinfo modinfo = {0};
@@ -103,7 +102,7 @@ static int get_module_eeprom_by_page(struct net_device *dev,
 
 static int eeprom_prepare_data(const struct ethnl_req_info *req_base,
 			       struct ethnl_reply_data *reply_base,
-			       struct genl_info *info)
+			       const struct genl_info *info)
 {
 	struct eeprom_reply_data *reply = MODULE_EEPROM_REPDATA(reply_base);
 	struct eeprom_req_info *request = MODULE_EEPROM_REQINFO(req_base);
@@ -124,7 +123,7 @@ static int eeprom_prepare_data(const struct ethnl_req_info *req_base,
 	if (ret)
 		goto err_free;
 
-	ret = get_module_eeprom_by_page(dev, &page_data, info ? info->extack : NULL);
+	ret = get_module_eeprom_by_page(dev, &page_data, info->extack);
 	if (ret < 0)
 		goto err_ops;
 
@@ -140,7 +139,7 @@ err_free:
 	kfree(page_data.data);
 
 	if (ret == -EOPNOTSUPP)
-		return eeprom_fallback(request, reply, info);
+		return eeprom_fallback(request, reply);
 	return ret;
 }
 
diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index 55d449a2d3fcb..a79af8c25a071 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -35,7 +35,7 @@ static void ethnl_features_to_bitmap32(u32 *dest, netdev_features_t src)
 
 static int features_prepare_data(const struct ethnl_req_info *req_base,
 				 struct ethnl_reply_data *reply_base,
-				 struct genl_info *info)
+				 const struct genl_info *info)
 {
 	struct features_reply_data *data = FEATURES_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/fec.c b/net/ethtool/fec.c
index 0d9a3d153170d..e7d3f2c352a34 100644
--- a/net/ethtool/fec.c
+++ b/net/ethtool/fec.c
@@ -92,7 +92,7 @@ fec_stats_recalc(struct fec_stat_grp *grp, struct ethtool_fec_stat *stats)
 
 static int fec_prepare_data(const struct ethnl_req_info *req_base,
 			    struct ethnl_reply_data *reply_base,
-			    struct genl_info *info)
+			    const struct genl_info *info)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(active_fec_modes) = {};
 	struct fec_reply_data *data = FEC_REPDATA(reply_base);
diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c
index 310dfe63292aa..5c317d23787b5 100644
--- a/net/ethtool/linkinfo.c
+++ b/net/ethtool/linkinfo.c
@@ -23,7 +23,7 @@ const struct nla_policy ethnl_linkinfo_get_policy[] = {
 
 static int linkinfo_prepare_data(const struct ethnl_req_info *req_base,
 				 struct ethnl_reply_data *reply_base,
-				 struct genl_info *info)
+				 const struct genl_info *info)
 {
 	struct linkinfo_reply_data *data = LINKINFO_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c
index 20165e07ef901..b2591db49f7db 100644
--- a/net/ethtool/linkmodes.c
+++ b/net/ethtool/linkmodes.c
@@ -27,7 +27,7 @@ const struct nla_policy ethnl_linkmodes_get_policy[] = {
 
 static int linkmodes_prepare_data(const struct ethnl_req_info *req_base,
 				  struct ethnl_reply_data *reply_base,
-				  struct genl_info *info)
+				  const struct genl_info *info)
 {
 	struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c
index 2158c17a0b320..b2de2108b356a 100644
--- a/net/ethtool/linkstate.c
+++ b/net/ethtool/linkstate.c
@@ -81,7 +81,7 @@ static int linkstate_get_link_ext_state(struct net_device *dev,
 
 static int linkstate_prepare_data(const struct ethnl_req_info *req_base,
 				  struct ethnl_reply_data *reply_base,
-				  struct genl_info *info)
+				  const struct genl_info *info)
 {
 	struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/mm.c b/net/ethtool/mm.c
index 4058a557b5a42..2816bb23c3ad9 100644
--- a/net/ethtool/mm.c
+++ b/net/ethtool/mm.c
@@ -27,7 +27,7 @@ const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1] = {
 
 static int mm_prepare_data(const struct ethnl_req_info *req_base,
 			   struct ethnl_reply_data *reply_base,
-			   struct genl_info *info)
+			   const struct genl_info *info)
 {
 	struct mm_reply_data *data = MM_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/module.c b/net/ethtool/module.c
index e0d539b21423c..ceb575efc290c 100644
--- a/net/ethtool/module.c
+++ b/net/ethtool/module.c
@@ -38,10 +38,9 @@ static int module_get_power_mode(struct net_device *dev,
 
 static int module_prepare_data(const struct ethnl_req_info *req_base,
 			       struct ethnl_reply_data *reply_base,
-			       struct genl_info *info)
+			       const struct genl_info *info)
 {
 	struct module_reply_data *data = MODULE_REPDATA(reply_base);
-	struct netlink_ext_ack *extack = info ? info->extack : NULL;
 	struct net_device *dev = reply_base->dev;
 	int ret;
 
@@ -49,7 +48,7 @@ static int module_prepare_data(const struct ethnl_req_info *req_base,
 	if (ret < 0)
 		return ret;
 
-	ret = module_get_power_mode(dev, data, extack);
+	ret = module_get_power_mode(dev, data, info->extack);
 	if (ret < 0)
 		goto out_complete;
 
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index f7b3171a0aad2..3bbd5afb7b31c 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -444,12 +444,12 @@ err_dev:
 
 static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
 				  const struct ethnl_dump_ctx *ctx,
-				  struct netlink_callback *cb)
+				  const struct genl_info *info)
 {
 	void *ehdr;
 	int ret;
 
-	ehdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+	ehdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
 			   &ethtool_genl_family, NLM_F_MULTI,
 			   ctx->ops->reply_cmd);
 	if (!ehdr)
@@ -457,7 +457,7 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
 
 	ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev);
 	rtnl_lock();
-	ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, NULL);
+	ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, info);
 	rtnl_unlock();
 	if (ret < 0)
 		goto out;
@@ -495,7 +495,7 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 		dev_hold(dev);
 		rtnl_unlock();
 
-		ret = ethnl_default_dump_one(skb, dev, ctx, cb);
+		ret = ethnl_default_dump_one(skb, dev, ctx, genl_info_dump(cb));
 
 		rtnl_lock();
 		dev_put(dev);
@@ -647,11 +647,14 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd,
 	struct ethnl_reply_data *reply_data;
 	const struct ethnl_request_ops *ops;
 	struct ethnl_req_info *req_info;
+	struct genl_info info;
 	struct sk_buff *skb;
 	void *reply_payload;
 	int reply_len;
 	int ret;
 
+	genl_info_init_ntf(&info, &ethtool_genl_family, cmd);
+
 	if (WARN_ONCE(cmd > ETHTOOL_MSG_KERNEL_MAX ||
 		      !ethnl_default_notify_ops[cmd],
 		      "unexpected notification type %u\n", cmd))
@@ -670,7 +673,7 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd,
 	req_info->flags |= ETHTOOL_FLAG_COMPACT_BITSETS;
 
 	ethnl_init_reply_data(reply_data, ops, dev);
-	ret = ops->prepare_data(req_info, reply_data, NULL);
+	ret = ops->prepare_data(req_info, reply_data, &info);
 	if (ret < 0)
 		goto err_cleanup;
 	ret = ops->reply_size(req_info, reply_data);
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 79424b34b553e..9a333a8d04c1f 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -355,7 +355,7 @@ struct ethnl_request_ops {
 			     struct netlink_ext_ack *extack);
 	int (*prepare_data)(const struct ethnl_req_info *req_info,
 			    struct ethnl_reply_data *reply_data,
-			    struct genl_info *info);
+			    const struct genl_info *info);
 	int (*reply_size)(const struct ethnl_req_info *req_info,
 			  const struct ethnl_reply_data *reply_data);
 	int (*fill_reply)(struct sk_buff *skb,
diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c
index 6657d0b888d83..f7c847aeb1a29 100644
--- a/net/ethtool/pause.c
+++ b/net/ethtool/pause.c
@@ -51,10 +51,9 @@ static int pause_parse_request(struct ethnl_req_info *req_base,
 
 static int pause_prepare_data(const struct ethnl_req_info *req_base,
 			      struct ethnl_reply_data *reply_base,
-			      struct genl_info *info)
+			      const struct genl_info *info)
 {
 	const struct pause_req_info *req_info = PAUSE_REQINFO(req_base);
-	struct netlink_ext_ack *extack = info ? info->extack : NULL;
 	struct pause_reply_data *data = PAUSE_REPDATA(reply_base);
 	enum ethtool_mac_stats_src src = req_info->src;
 	struct net_device *dev = reply_base->dev;
@@ -74,7 +73,7 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base,
 	if ((src == ETHTOOL_MAC_STATS_SRC_EMAC ||
 	     src == ETHTOOL_MAC_STATS_SRC_PMAC) &&
 	    !__ethtool_dev_mm_supported(dev)) {
-		NL_SET_ERR_MSG_MOD(extack,
+		NL_SET_ERR_MSG_MOD(info->extack,
 				   "Device does not support MAC merge layer");
 		ethnl_ops_complete(dev);
 		return -EOPNOTSUPP;
diff --git a/net/ethtool/phc_vclocks.c b/net/ethtool/phc_vclocks.c
index 637b2f5297d52..cadaabed60bd9 100644
--- a/net/ethtool/phc_vclocks.c
+++ b/net/ethtool/phc_vclocks.c
@@ -24,7 +24,7 @@ const struct nla_policy ethnl_phc_vclocks_get_policy[] = {
 
 static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base,
 				    struct ethnl_reply_data *reply_base,
-				    struct genl_info *info)
+				    const struct genl_info *info)
 {
 	struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c
index 5a8cab4df0c9c..b238a1afe9aed 100644
--- a/net/ethtool/plca.c
+++ b/net/ethtool/plca.c
@@ -40,7 +40,7 @@ const struct nla_policy ethnl_plca_get_cfg_policy[] = {
 
 static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base,
 				     struct ethnl_reply_data *reply_base,
-				     struct genl_info *info)
+				     const struct genl_info *info)
 {
 	struct plca_reply_data *data = PLCA_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
@@ -183,7 +183,7 @@ const struct nla_policy ethnl_plca_get_status_policy[] = {
 
 static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base,
 					struct ethnl_reply_data *reply_base,
-					struct genl_info *info)
+					const struct genl_info *info)
 {
 	struct plca_reply_data *data = PLCA_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/privflags.c b/net/ethtool/privflags.c
index 23264a1ebf122..297be6a13ab9a 100644
--- a/net/ethtool/privflags.c
+++ b/net/ethtool/privflags.c
@@ -57,7 +57,7 @@ static int ethnl_get_priv_flags_info(struct net_device *dev,
 
 static int privflags_prepare_data(const struct ethnl_req_info *req_base,
 				  struct ethnl_reply_data *reply_base,
-				  struct genl_info *info)
+				  const struct genl_info *info)
 {
 	struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index 530b8b99e6df7..cc478af77111f 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -53,8 +53,8 @@ static int pse_get_pse_attributes(struct net_device *dev,
 }
 
 static int pse_prepare_data(const struct ethnl_req_info *req_base,
-			       struct ethnl_reply_data *reply_base,
-			       struct genl_info *info)
+			    struct ethnl_reply_data *reply_base,
+			    const struct genl_info *info)
 {
 	struct pse_reply_data *data = PSE_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
@@ -64,7 +64,7 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base,
 	if (ret < 0)
 		return ret;
 
-	ret = pse_get_pse_attributes(dev, info ? info->extack : NULL, data);
+	ret = pse_get_pse_attributes(dev, info->extack, data);
 
 	ethnl_ops_complete(dev);
 
diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c
index 1c4972526142b..fb09f774ea01d 100644
--- a/net/ethtool/rings.c
+++ b/net/ethtool/rings.c
@@ -24,10 +24,9 @@ const struct nla_policy ethnl_rings_get_policy[] = {
 
 static int rings_prepare_data(const struct ethnl_req_info *req_base,
 			      struct ethnl_reply_data *reply_base,
-			      struct genl_info *info)
+			      const struct genl_info *info)
 {
 	struct rings_reply_data *data = RINGS_REPDATA(reply_base);
-	struct netlink_ext_ack *extack = info ? info->extack : NULL;
 	struct net_device *dev = reply_base->dev;
 	int ret;
 
@@ -39,7 +38,7 @@ static int rings_prepare_data(const struct ethnl_req_info *req_base,
 	if (ret < 0)
 		return ret;
 	dev->ethtool_ops->get_ringparam(dev, &data->ringparam,
-					&data->kernel_ringparam, extack);
+					&data->kernel_ringparam, info->extack);
 	ethnl_ops_complete(dev);
 
 	return 0;
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index be260ab34e580..5764202e6cb62 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -42,7 +42,8 @@ rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb,
 
 static int
 rss_prepare_data(const struct ethnl_req_info *req_base,
-		 struct ethnl_reply_data *reply_base, struct genl_info *info)
+		 struct ethnl_reply_data *reply_base,
+		 const struct genl_info *info)
 {
 	struct rss_reply_data *data = RSS_REPDATA(reply_base);
 	struct rss_req_info *request = RSS_REQINFO(req_base);
diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c
index 010ed19ccc99a..912f0c4fff2fb 100644
--- a/net/ethtool/stats.c
+++ b/net/ethtool/stats.c
@@ -114,10 +114,9 @@ static int stats_parse_request(struct ethnl_req_info *req_base,
 
 static int stats_prepare_data(const struct ethnl_req_info *req_base,
 			      struct ethnl_reply_data *reply_base,
-			      struct genl_info *info)
+			      const struct genl_info *info)
 {
 	const struct stats_req_info *req_info = STATS_REQINFO(req_base);
-	struct netlink_ext_ack *extack = info ? info->extack : NULL;
 	struct stats_reply_data *data = STATS_REPDATA(reply_base);
 	enum ethtool_mac_stats_src src = req_info->src;
 	struct net_device *dev = reply_base->dev;
@@ -130,7 +129,7 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base,
 	if ((src == ETHTOOL_MAC_STATS_SRC_EMAC ||
 	     src == ETHTOOL_MAC_STATS_SRC_PMAC) &&
 	    !__ethtool_dev_mm_supported(dev)) {
-		NL_SET_ERR_MSG_MOD(extack,
+		NL_SET_ERR_MSG_MOD(info->extack,
 				   "Device does not support MAC merge layer");
 		ethnl_ops_complete(dev);
 		return -EOPNOTSUPP;
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 3f7de54d85fb9..c678b484a0795 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -274,7 +274,7 @@ static int strset_prepare_set(struct strset_info *info, struct net_device *dev,
 
 static int strset_prepare_data(const struct ethnl_req_info *req_base,
 			       struct ethnl_reply_data *reply_base,
-			       struct genl_info *info)
+			       const struct genl_info *info)
 {
 	const struct strset_req_info *req_info = STRSET_REQINFO(req_base);
 	struct strset_reply_data *data = STRSET_REPDATA(reply_base);
diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c
index 63b5814bd460a..9daed0aab162a 100644
--- a/net/ethtool/tsinfo.c
+++ b/net/ethtool/tsinfo.c
@@ -25,7 +25,7 @@ const struct nla_policy ethnl_tsinfo_get_policy[] = {
 
 static int tsinfo_prepare_data(const struct ethnl_req_info *req_base,
 			       struct ethnl_reply_data *reply_base,
-			       struct genl_info *info)
+			       const struct genl_info *info)
 {
 	struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
diff --git a/net/ethtool/wol.c b/net/ethtool/wol.c
index a4a43d9e6e9d5..0ed56c9ac1bc4 100644
--- a/net/ethtool/wol.c
+++ b/net/ethtool/wol.c
@@ -24,7 +24,7 @@ const struct nla_policy ethnl_wol_get_policy[] = {
 
 static int wol_prepare_data(const struct ethnl_req_info *req_base,
 			    struct ethnl_reply_data *reply_base,
-			    struct genl_info *info)
+			    const struct genl_info *info)
 {
 	struct wol_reply_data *data = WOL_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
@@ -39,7 +39,8 @@ static int wol_prepare_data(const struct ethnl_req_info *req_base,
 	dev->ethtool_ops->get_wol(dev, &data->wol);
 	ethnl_ops_complete(dev);
 	/* do not include password in notifications */
-	data->show_sopass = info && (data->wol.supported & WAKE_MAGICSECURE);
+	data->show_sopass = !genl_info_is_ntf(info) &&
+		(data->wol.supported & WAKE_MAGICSECURE);
 
 	return 0;
 }
-- 
GitLab


From 7458575a07f1c6768e46b8eac6e09a358804c9f6 Mon Sep 17 00:00:00 2001
From: Andrea Mayer <andrea.mayer@uniroma2.it>
Date: Sat, 12 Aug 2023 20:09:25 +0200
Subject: [PATCH 1236/1806] seg6: add NEXT-C-SID support for SRv6 End.X
 behavior

The NEXT-C-SID mechanism described in [1] offers the possibility of
encoding several SRv6 segments within a single 128 bit SID address. Such
a SID address is called a Compressed SID (C-SID) container. In this way,
the length of the SID List can be drastically reduced.

A SID instantiated with the NEXT-C-SID flavor considers an IPv6 address
logically structured in three main blocks: i) Locator-Block; ii)
Locator-Node Function; iii) Argument.

                        C-SID container
+------------------------------------------------------------------+
|     Locator-Block      |Loc-Node|            Argument            |
|                        |Function|                                |
+------------------------------------------------------------------+
<--------- B -----------> <- NF -> <------------- A --------------->

   (i) The Locator-Block can be any IPv6 prefix available to the provider;

  (ii) The Locator-Node Function represents the node and the function to
       be triggered when a packet is received on the node;

 (iii) The Argument carries the remaining C-SIDs in the current C-SID
       container.

This patch leverages the NEXT-C-SID mechanism previously introduced in the
Linux SRv6 subsystem [2] to support SID compression capabilities in the
SRv6 End.X behavior [3].
An SRv6 End.X behavior with NEXT-C-SID flavor works as an End.X behavior
but it is capable of processing the compressed SID List encoded in C-SID
containers.

An SRv6 End.X behavior with NEXT-C-SID flavor can be configured to support
user-provided Locator-Block and Locator-Node Function lengths. In this
implementation, such lengths must be evenly divisible by 8 (i.e. must be
byte-aligned), otherwise the kernel informs the user about invalid
values with a meaningful error code and message through netlink_ext_ack.

If Locator-Block and/or Locator-Node Function lengths are not provided
by the user during configuration of an SRv6 End.X behavior instance with
NEXT-C-SID flavor, the kernel will choose their default values i.e.,
32-bit Locator-Block and 16-bit Locator-Node Function.

[1] - https://datatracker.ietf.org/doc/html/draft-ietf-spring-srv6-srh-compression
[2] - https://lore.kernel.org/all/20220912171619.16943-1-andrea.mayer@uniroma2.it/
[3] - https://datatracker.ietf.org/doc/html/rfc8986#name-endx-l3-cross-connect

Signed-off-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230812180926.16689-2-andrea.mayer@uniroma2.it
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/seg6_local.c | 108 ++++++++++++++++++++++++++++++++++--------
 1 file changed, 88 insertions(+), 20 deletions(-)

diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index dd433cc265c89..24e2b4b494cb0 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -109,15 +109,19 @@ struct bpf_lwt_prog {
 #define next_csid_chk_lcnode_fn_bits(flen)		\
 	next_csid_chk_lcblock_bits(flen)
 
+/* flag indicating that flavors are set up for a given End* behavior */
+#define SEG6_F_LOCAL_FLAVORS		SEG6_F_ATTR(SEG6_LOCAL_FLAVORS)
+
 #define SEG6_F_LOCAL_FLV_OP(flvname)	BIT(SEG6_LOCAL_FLV_OP_##flvname)
+#define SEG6_F_LOCAL_FLV_NEXT_CSID	SEG6_F_LOCAL_FLV_OP(NEXT_CSID)
 #define SEG6_F_LOCAL_FLV_PSP		SEG6_F_LOCAL_FLV_OP(PSP)
 
 /* Supported RFC8986 Flavor operations are reported in this bitmask */
 #define SEG6_LOCAL_FLV8986_SUPP_OPS	SEG6_F_LOCAL_FLV_PSP
 
-/* Supported Flavor operations are reported in this bitmask */
-#define SEG6_LOCAL_FLV_SUPP_OPS		(SEG6_F_LOCAL_FLV_OP(NEXT_CSID) | \
+#define SEG6_LOCAL_END_FLV_SUPP_OPS	(SEG6_F_LOCAL_FLV_NEXT_CSID | \
 					 SEG6_LOCAL_FLV8986_SUPP_OPS)
+#define SEG6_LOCAL_END_X_FLV_SUPP_OPS	SEG6_F_LOCAL_FLV_NEXT_CSID
 
 struct seg6_flavors_info {
 	/* Flavor operations */
@@ -411,9 +415,72 @@ static int end_next_csid_core(struct sk_buff *skb, struct seg6_local_lwt *slwt)
 	return input_action_end_finish(skb, slwt);
 }
 
+static int input_action_end_x_finish(struct sk_buff *skb,
+				     struct seg6_local_lwt *slwt)
+{
+	seg6_lookup_nexthop(skb, &slwt->nh6, 0);
+
+	return dst_input(skb);
+}
+
+static int input_action_end_x_core(struct sk_buff *skb,
+				   struct seg6_local_lwt *slwt)
+{
+	struct ipv6_sr_hdr *srh;
+
+	srh = get_and_validate_srh(skb);
+	if (!srh)
+		goto drop;
+
+	advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
+
+	return input_action_end_x_finish(skb, slwt);
+
+drop:
+	kfree_skb(skb);
+	return -EINVAL;
+}
+
+static int end_x_next_csid_core(struct sk_buff *skb,
+				struct seg6_local_lwt *slwt)
+{
+	const struct seg6_flavors_info *finfo = &slwt->flv_info;
+	struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
+
+	if (seg6_next_csid_is_arg_zero(daddr, finfo))
+		return input_action_end_x_core(skb, slwt);
+
+	/* update DA */
+	seg6_next_csid_advance_arg(daddr, finfo);
+
+	return input_action_end_x_finish(skb, slwt);
+}
+
 static bool seg6_next_csid_enabled(__u32 fops)
 {
-	return fops & BIT(SEG6_LOCAL_FLV_OP_NEXT_CSID);
+	return fops & SEG6_F_LOCAL_FLV_NEXT_CSID;
+}
+
+/* Processing of SRv6 End, End.X, and End.T behaviors can be extended through
+ * the flavors framework. These behaviors must report the subset of (flavor)
+ * operations they currently implement. In this way, if a user specifies a
+ * flavor combination that is not supported by a given End* behavior, the
+ * kernel refuses to instantiate the tunnel reporting the error.
+ */
+static int seg6_flv_supp_ops_by_action(int action, __u32 *fops)
+{
+	switch (action) {
+	case SEG6_LOCAL_ACTION_END:
+		*fops = SEG6_LOCAL_END_FLV_SUPP_OPS;
+		break;
+	case SEG6_LOCAL_ACTION_END_X:
+		*fops = SEG6_LOCAL_END_X_FLV_SUPP_OPS;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
 }
 
 /* We describe the packet state in relation to the absence/presence of the SRH
@@ -746,21 +813,14 @@ static int input_action_end(struct sk_buff *skb, struct seg6_local_lwt *slwt)
 /* regular endpoint, and forward to specified nexthop */
 static int input_action_end_x(struct sk_buff *skb, struct seg6_local_lwt *slwt)
 {
-	struct ipv6_sr_hdr *srh;
-
-	srh = get_and_validate_srh(skb);
-	if (!srh)
-		goto drop;
-
-	advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
-
-	seg6_lookup_nexthop(skb, &slwt->nh6, 0);
+	const struct seg6_flavors_info *finfo = &slwt->flv_info;
+	__u32 fops = finfo->flv_ops;
 
-	return dst_input(skb);
+	/* check for the presence of NEXT-C-SID since it applies first */
+	if (seg6_next_csid_enabled(fops))
+		return end_x_next_csid_core(skb, slwt);
 
-drop:
-	kfree_skb(skb);
-	return -EINVAL;
+	return input_action_end_x_core(skb, slwt);
 }
 
 static int input_action_end_t(struct sk_buff *skb, struct seg6_local_lwt *slwt)
@@ -1404,13 +1464,14 @@ static struct seg6_action_desc seg6_action_table[] = {
 		.action		= SEG6_LOCAL_ACTION_END,
 		.attrs		= 0,
 		.optattrs	= SEG6_F_LOCAL_COUNTERS |
-				  SEG6_F_ATTR(SEG6_LOCAL_FLAVORS),
+				  SEG6_F_LOCAL_FLAVORS,
 		.input		= input_action_end,
 	},
 	{
 		.action		= SEG6_LOCAL_ACTION_END_X,
 		.attrs		= SEG6_F_ATTR(SEG6_LOCAL_NH6),
-		.optattrs	= SEG6_F_LOCAL_COUNTERS,
+		.optattrs	= SEG6_F_LOCAL_COUNTERS |
+				  SEG6_F_LOCAL_FLAVORS,
 		.input		= input_action_end_x,
 	},
 	{
@@ -2070,7 +2131,8 @@ static int parse_nla_flavors(struct nlattr **attrs, struct seg6_local_lwt *slwt,
 {
 	struct seg6_flavors_info *finfo = &slwt->flv_info;
 	struct nlattr *tb[SEG6_LOCAL_FLV_MAX + 1];
-	unsigned long fops;
+	int action = slwt->action;
+	__u32 fops, supp_fops;
 	int rc;
 
 	rc = nla_parse_nested_deprecated(tb, SEG6_LOCAL_FLV_MAX,
@@ -2086,7 +2148,8 @@ static int parse_nla_flavors(struct nlattr **attrs, struct seg6_local_lwt *slwt,
 		return -EINVAL;
 
 	fops = nla_get_u32(tb[SEG6_LOCAL_FLV_OPERATION]);
-	if (fops & ~SEG6_LOCAL_FLV_SUPP_OPS) {
+	rc = seg6_flv_supp_ops_by_action(action, &supp_fops);
+	if (rc < 0 || (fops & ~supp_fops)) {
 		NL_SET_ERR_MSG(extack, "Unsupported Flavor operation(s)");
 		return -EOPNOTSUPP;
 	}
@@ -2618,6 +2681,11 @@ int __init seg6_local_init(void)
 	 */
 	BUILD_BUG_ON(SEG6_LOCAL_MAX + 1 > BITS_PER_TYPE(unsigned long));
 
+	/* Check whether the number of defined flavors exceeds the maximum
+	 * allowed value.
+	 */
+	BUILD_BUG_ON(SEG6_LOCAL_FLV_OP_MAX + 1 > BITS_PER_TYPE(__u32));
+
 	/* If the default NEXT-C-SID Locator-Block/Node Function lengths (in
 	 * bits) have been changed with invalid values, kernel build stops
 	 * here.
-- 
GitLab


From 1c53717c80740be035d2110e20ad4877a1784c61 Mon Sep 17 00:00:00 2001
From: Paolo Lungaroni <paolo.lungaroni@uniroma2.it>
Date: Sat, 12 Aug 2023 20:09:26 +0200
Subject: [PATCH 1237/1806] selftests: seg6: add selftest for NEXT-C-SID flavor
 in SRv6 End.X behavior

This selftest is designed for testing the support of NEXT-C-SID flavor
for SRv6 End.X behavior. It instantiates a virtual network composed of
several nodes: hosts and SRv6 routers. Each node is realized using a
network namespace that is properly interconnected to others through veth
pairs, according to the topology depicted in the selftest script file.
The test considers SRv6 routers implementing IPv4/IPv6 L3 VPNs leveraged
by hosts for communicating with each other. Such routers i) apply
different SRv6 Policies to the traffic received from connected hosts,
considering the IPv4 or IPv6 protocols; ii) use the NEXT-C-SID
compression mechanism for encoding several SRv6 segments within a single
128-bit SID address, referred to as a Compressed SID (C-SID) container.

The NEXT-C-SID is provided as a "flavor" of the SRv6 End.X behavior,
enabling it to properly process the C-SID containers. The correct
execution of the enabled NEXT-C-SID SRv6 End.X behavior is verified
through reachability tests carried out between hosts belonging to the
same VPN.

Signed-off-by: Paolo Lungaroni <paolo.lungaroni@uniroma2.it>
Co-developed-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Signed-off-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230812180926.16689-3-andrea.mayer@uniroma2.it
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile          |    1 +
 .../net/srv6_end_x_next_csid_l3vpn_test.sh    | 1213 +++++++++++++++++
 2 files changed, 1214 insertions(+)
 create mode 100755 tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 04341e1b38f04..8b017070960d3 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -40,6 +40,7 @@ TEST_PROGS += srv6_end_dt6_l3vpn_test.sh
 TEST_PROGS += srv6_hencap_red_l3vpn_test.sh
 TEST_PROGS += srv6_hl2encap_red_l2vpn_test.sh
 TEST_PROGS += srv6_end_next_csid_l3vpn_test.sh
+TEST_PROGS += srv6_end_x_next_csid_l3vpn_test.sh
 TEST_PROGS += srv6_end_flavors_test.sh
 TEST_PROGS += vrf_strict_mode_test.sh
 TEST_PROGS += arp_ndisc_evict_nocarrier.sh
diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
new file mode 100755
index 0000000000000..c79cb8ede17f4
--- /dev/null
+++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
@@ -0,0 +1,1213 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# author: Andrea Mayer <andrea.mayer@uniroma2.it>
+# author: Paolo Lungaroni <paolo.lungaroni@uniroma2.it>
+#
+# This script is designed for testing the support of NEXT-C-SID flavor for SRv6
+# End.X behavior.
+# A basic knowledge of SRv6 architecture [1] and of the compressed SID approach
+# [2] is assumed for the reader.
+#
+# The network topology used in the selftest is depicted hereafter, composed of
+# two hosts and four routers. Hosts hs-1 and hs-2 are connected through an
+# IPv4/IPv6 L3 VPN service, offered by routers rt-1, rt-2, rt-3 and rt-4 using
+# the NEXT-C-SID flavor. The key components for such VPNs are:
+#
+#    i) The SRv6 H.Encaps/H.Encaps.Red behaviors [1] apply SRv6 Policies on
+#       traffic received by connected hosts, initiating the VPN tunnel;
+#
+#   ii) The SRv6 End.X behavior [1] (Endpoint with L3 cross connect) is a
+#       variant of SRv6 End behavior. It advances the active SID in the SID
+#       List carried by the SRH and forwards the packet to an L3 adjacency;
+#
+#  iii) The NEXT-C-SID mechanism [2] offers the possibility of encoding several
+#       SRv6 segments within a single 128-bit SID address, referred to as a
+#       Compressed SID (C-SID) container. In this way, the length of the SID
+#       List can be drastically reduced.
+#       The NEXT-C-SID is provided as a "flavor" of the SRv6 End.X behavior
+#       which advances the current C-SID (i.e. the Locator-Node Function defined
+#       in [2]) with the next one carried in the Argument, if available.
+#       When no more C-SIDs are available in the Argument, the SRv6 End.X
+#       behavior will apply the End.X function selecting the next SID in the SID
+#       List;
+#
+#   iv) The SRv6 End.DT46 behavior [1] is used for removing the SRv6 Policy and,
+#       thus, it terminates the VPN tunnel. Such a behavior is capable of
+#       handling, at the same time, both tunneled IPv4 and IPv6 traffic.
+#
+# [1] https://datatracker.ietf.org/doc/html/rfc8986
+# [2] https://datatracker.ietf.org/doc/html/draft-ietf-spring-srv6-srh-compression
+#
+#
+#               cafe::1                      cafe::2
+#              10.0.0.1                     10.0.0.2
+#             +--------+                   +--------+
+#             |        |                   |        |
+#             |  hs-1  |                   |  hs-2  |
+#             |        |                   |        |
+#             +---+----+                   +----+---+
+#    cafe::/64    |                             |      cafe::/64
+#  10.0.0.0/24    |                             |    10.0.0.0/24
+#             +---+----+                   +----+---+
+#             |        |  fcf0:0:1:2::/64  |        |
+#             |  rt-1  +-------------------+  rt-2  |
+#             |        |                   |        |
+#             +---+----+                   +----+---+
+#                 |      .               .      |
+#                 |  fcf0:0:1:3::/64   .        |
+#                 |          .       .          |
+#                 |            .   .            |
+# fcf0:0:1:4::/64 |              .              | fcf0:0:2:3::/64
+#                 |            .   .            |
+#                 |          .       .          |
+#                 |  fcf0:0:2:4::/64   .        |
+#                 |      .               .      |
+#             +---+----+                   +----+---+
+#             |        |                   |        |
+#             |  rt-4  +-------------------+  rt-3  |
+#             |        |  fcf0:0:3:4::/64  |        |
+#             +---+----+                   +----+---+
+#
+# Every fcf0:0:x:y::/64 network interconnects the SRv6 routers rt-x with rt-y in
+# the selftest network.
+#
+# Local SID/C-SID table
+# =====================
+#
+# Each SRv6 router is configured with a Local SID/C-SID table in which
+# SIDs/C-SIDs are stored. Considering an SRv6 router rt-x, SIDs/C-SIDs are
+# configured in the Local SID/C-SIDs table as follows:
+#
+#   Local SID/C-SID table for SRv6 router rt-x
+#   +-----------------------------------------------------------+
+#   |fcff:x::d46 is associated with the non-compressed SRv6     |
+#   |   End.DT46 behavior                                       |
+#   +-----------------------------------------------------------+
+#   |fcbb:0:0x00::/48 is associated with the NEXT-C-SID flavor  |
+#   |   of SRv6 End.X behavior                                  |
+#   +-----------------------------------------------------------+
+#   |fcbb:0:0x00:d46::/64 is associated with the SRv6 End.DT46  |
+#   |   behavior when NEXT-C-SID compression is turned on       |
+#   +-----------------------------------------------------------+
+#
+# The fcff::/16 prefix is reserved for implementing SRv6 services with regular
+# (non compressed) SIDs. Reachability of SIDs is ensured by proper configuration
+# of the IPv6 routing tables in the routers.
+# Similarly, the fcbb:0::/32 prefix is reserved for implementing SRv6 VPN
+# services leveraging the NEXT-C-SID compression mechanism. Indeed, the
+# fcbb:0::/32 is used for encoding the Locator-Block while the Locator-Node
+# Function is encoded with 16 bits.
+#
+# Incoming traffic classification and application of SRv6 Policies
+# ================================================================
+#
+# An SRv6 ingress router applies different SRv6 Policies to the traffic received
+# from a connected host, considering the IPv4 or IPv6 destination address.
+# SRv6 policy enforcement consists of encapsulating the received traffic into a
+# new IPv6 packet with a given SID List contained in the SRH.
+# When the SID List contains only one SID, the SRH could be omitted completely
+# and that SID is stored directly in the IPv6 Destination Address (DA) (this is
+# called "reduced" encapsulation).
+#
+# Test cases for NEXT-C-SID
+# =========================
+#
+# We consider two test cases for NEXT-C-SID: i) single SID and ii) double SID.
+#
+# In the single SID test case we have a number of segments that are all
+# contained in a single Compressed SID (C-SID) container. Therefore the
+# resulting SID List has only one SID. Using the reduced encapsulation format
+# this will result in a packet with no SRH.
+#
+# In the double SID test case we have one segment carried in a Compressed SID
+# (C-SID) container, followed by a regular (non compressed) SID. The resulting
+# SID List has two segments and it is possible to test the advance to the next
+# SID when all the C-SIDs in a C-SID container have been processed. Using the
+# reduced encapsulation format this will result in a packet with an SRH
+# containing 1 segment.
+#
+# For the single SID test case, we use the IPv6 addresses of hs-1 and hs-2, for
+# the double SID test case, we use their IPv4 addresses. This is only done to
+# simplify the test setup and avoid adding other hosts or multiple addresses on
+# the same interface of a host.
+#
+# Traffic from hs-1 to hs-2
+# -------------------------
+#
+# Packets generated from hs-1 and directed towards hs-2 are handled by rt-1
+# which applies the SRv6 Policies as follows:
+#
+#   i) IPv6 DA=cafe::2, H.Encaps.Red with SID List=fcbb:0:0300:0200:d46::
+#  ii) IPv4 DA=10.0.0.2, H.Encaps.Red with SID List=fcbb:0:0300::,fcff:2::d46
+#
+# ### i) single SID
+#
+# The router rt-1 is configured to enforce the given Policy through the SRv6
+# H.Encaps.Red behavior which avoids the presence of the SRH at all, since it
+# pushes the single SID directly in the IPv6 DA. Such a SID encodes a whole
+# C-SID container carrying several C-SIDs (e.g. 0300, 0200, etc).
+#
+# As the packet reaches the router rt-3, the enabled NEXT-C-SID SRv6 End.X
+# behavior (associated with fcbb:0:0300::/48) is triggered. This behavior
+# analyzes the IPv6 DA and checks whether the Argument of the C-SID container
+# is zero or not. In this case, the Argument is *NOT* zero and the IPv6 DA is
+# updated as follows:
+#
+# +-----------------------------------------------------------------+
+# | Before applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior |
+# +-----------------------------------------------------------------+
+# |                            +---------- Argument                 |
+# |                     vvvvvvvvvv                                  |
+# | IPv6 DA fcbb:0:0300:0200:d46::                                  |
+# |                ^^^^    <-- shifting                             |
+# |                  |                                              |
+# |          Locator-Node Function                                  |
+# +-----------------------------------------------------------------+
+# | After applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior  |
+# +-----------------------------------------------------------------+
+# |                          +---------- Argument                   |
+# |                    vvvvvv                                       |
+# | IPv6 DA fcbb:0:0200:d46::                                       |
+# |                ^^^^                                             |
+# |                  |                                              |
+# |          Locator-Node Function                                  |
+# +-----------------------------------------------------------------+
+#
+# After having applied the enabled NEXT-C-SID SRv6 End.X behavior, the packet
+# is sent to rt-4 node using the L3 adjacency address fcf0:0:3:4::4.
+#
+# The node rt-4 performs a plain IPv6 forward to the rt-2 router according to
+# its Local SID table and using the IPv6 DA fcbb:0:0200:d46:: .
+#
+# The router rt-2 is configured for decapsulating the inner IPv6 packet and,
+# for this reason, it applies the SRv6 End.DT46 behavior on the received
+# packet. It is worth noting that the SRv6 End.DT46 behavior does not require
+# the presence of the SRH: it is fully capable to operate properly on
+# IPv4/IPv6-in-IPv6 encapsulations.
+# At the end of the decap operation, the packet is sent to the host hs-2.
+#
+# ### ii) double SID
+#
+# The router rt-1 is configured to enforce the given Policy through the SRv6
+# H.Encaps.Red. As a result, the first SID fcbb:0:0300:: is stored into the
+# IPv6 DA, while the SRH pushed into the packet is made of only one SID, i.e.
+# fcff:2::d46. Hence, the packet sent by hs-1 to hs-2 is encapsulated in an
+# outer IPv6 header plus the SRH.
+#
+# As the packet reaches the node rt-3, the router applies the enabled NEXT-C-SID
+# SRv6 End.X behavior.
+#
+# +-----------------------------------------------------------------+
+# | Before applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior |
+# +-----------------------------------------------------------------+
+# |                      +---------- Argument                       |
+# |                      vvvv (Argument is all filled with zeros)   |
+# | IPv6 DA fcbb:0:0300::                                           |
+# |                ^^^^                                             |
+# |                  |                                              |
+# |          Locator-Node Function                                  |
+# +-----------------------------------------------------------------+
+# | After applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior  |
+# +-----------------------------------------------------------------+
+# |                                                                 |
+# | IPv6 DA fcff:2::d46                                             |
+# |         ^^^^^^^^^^^                                             |
+# |              |                                                  |
+# |        SID copied from the SID List contained in the SRH        |
+# +-----------------------------------------------------------------+
+#
+# Since the Argument of the C-SID container is zero, the behavior can not
+# update the Locator-Node function with the next C-SID carried in the Argument
+# itself. Thus, the enabled NEXT-C-SID SRv6 End.X behavior operates as the
+# traditional End.X behavior: it updates the IPv6 DA by copying the next
+# available SID in the SID List carried by the SRH. Next, the packet is
+# forwarded to the rt-4 node using the L3 adjacency fcf0:3:4::4 previously
+# configured for this behavior.
+#
+# The node rt-4 performs a plain IPv6 forward to the rt-2 router according to
+# its Local SID table and using the IPv6 DA fcff:2::d46.
+#
+# Once the packet is received by rt-2, the router decapsulates the inner IPv4
+# packet using the SRv6 End.DT46 behavior (associated with the SID fcff:2::d46)
+# and sends it to the host hs-2.
+#
+# Traffic from hs-2 to hs-1
+# -------------------------
+#
+# Packets generated from hs-2 and directed towards hs-1 are handled by rt-2
+# which applies the SRv6 Policies as follows:
+#
+#   i) IPv6 DA=cafe::1, SID List=fcbb:0:0400:0100:d46::
+#  ii) IPv4 DA=10.0.0.1, SID List=fcbb:0:0300::,fcff:1::d46
+#
+# ### i) single SID
+#
+# The node hs-2 sends an IPv6 packet directed to node hs-1. The router rt-2 is
+# directly connected to hs-2 and receives the packet. Rt-2 applies the
+# H.Encap.Red behavior with policy i) described above. Since there is only one
+# SID, the SRH header is omitted and the policy is inserted directly into the DA
+# of IPv6 packet.
+#
+# The packet reaches the router rt-4 and the enabled NEXT-C-SID SRv6 End.X
+# behavior (associated with fcbb:0:0400::/48) is triggered. This behavior
+# analyzes the IPv6 DA and checks whether the Argument of the C-SID container
+# is zero or not. The Argument is *NOT* zero and the C-SID in the IPv6 DA is
+# advanced. At this point, the current IPv6 DA is fcbb:0:0100:d46:: .
+# The enabled NEXT-C-SID SRv6 End.X behavior is configured with the L3 adjacency
+# fcf0:0:1:4::1, used to route traffic to the rt-1 node.
+#
+# The router rt-1 is configured for decapsulating the inner packet. It applies
+# the SRv6 End.DT46 behavior on the received packet. Decapsulation does not
+# require the presence of the SRH. At the end of the decap operation, the packet
+# is sent to the host hs-1.
+#
+# ### ii) double SID
+#
+# The router rt-2 is configured to enforce the given Policy through the SRv6
+# H.Encaps.Red. As a result, the first SID fcbb:0:0300:: is stored into the
+# IPv6 DA, while the SRH pushed into the packet is made of only one SID, i.e.
+# fcff:1::d46. Hence, the packet sent by hs-2 to hs-1 is encapsulated in an
+# outer IPv6 header plus the SRH.
+#
+# As the packet reaches the node rt-3, the enabled NEXT-C-SID SRv6 End.X
+# behavior bound to the SID fcbb:0:0300::/48 is triggered.
+# Since the Argument of the C-SID container is zero, the behavior can not
+# update the Locator-Node function with the next C-SID carried in the Argument
+# itself. Thus, the enabled NEXT-C-SID SRv6 End-X behavior operates as the
+# traditional End.X behavior: it updates the IPv6 DA by copying the next
+# available SID in the SID List carried by the SRH. After that, the packet is
+# forwarded to the rt-4 node using the L3 adjacency (fcf0:3:4::4) previously
+# configured for this behavior.
+#
+# The node rt-4 performs a plain IPv6 forward to the rt-1 router according to
+# its Local SID table, considering the IPv6 DA fcff:1::d46.
+#
+# Once the packet is received by rt-1, the router decapsulates the inner IPv4
+# packet using the SRv6 End.DT46 behavior (associated with the SID fcff:1::d46)
+# and sends it to the host hs-1.
+
+# Kselftest framework requirement - SKIP code is 4.
+readonly ksft_skip=4
+
+readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
+readonly DUMMY_DEVNAME="dum0"
+readonly VRF_TID=100
+readonly VRF_DEVNAME="vrf-${VRF_TID}"
+readonly RT2HS_DEVNAME="veth-t${VRF_TID}"
+readonly LOCALSID_TABLE_ID=90
+readonly IPv6_RT_NETWORK=fcf0:0
+readonly IPv6_HS_NETWORK=cafe
+readonly IPv4_HS_NETWORK=10.0.0
+readonly VPN_LOCATOR_SERVICE=fcff
+readonly DT46_FUNC=0d46
+readonly HEADEND_ENCAP="encap.red"
+
+# do not add ':' as separator
+readonly LCBLOCK_ADDR=fcbb0000
+readonly LCBLOCK_BLEN=32
+# do not add ':' as separator
+readonly LCNODEFUNC_FMT="0%d00"
+readonly LCNODEFUNC_BLEN=16
+
+readonly LCBLOCK_NODEFUNC_BLEN=$((LCBLOCK_BLEN + LCNODEFUNC_BLEN))
+
+readonly CSID_CNTR_PREFIX="dead:beaf::/32"
+# ID of the router used for testing the C-SID container cfgs
+readonly CSID_CNTR_RT_ID_TEST=1
+# Routing table used for testing the C-SID container cfgs
+readonly CSID_CNTR_RT_TABLE=91
+
+# C-SID container configurations to be tested
+#
+# An entry of the array is defined as "a,b,c" where:
+# - 'a' and 'b' elements represent respectively the Locator-Block length
+#   (lblen) in bits and the Locator-Node Function length (nflen) in bits.
+#   'a' and 'b' can be set to default values using the placeholder "d" which
+#   indicates the default kernel values (32 for lblen and 16 for nflen);
+#   otherwise, any numeric value is accepted;
+# - 'c' indicates whether the C-SID configuration provided by the values 'a'
+#   and 'b' should be considered valid ("y") or invalid ("n").
+declare -ra CSID_CONTAINER_CFGS=(
+	"d,d,y"
+	"d,16,y"
+	"16,d,y"
+	"16,32,y"
+	"32,16,y"
+	"48,8,y"
+	"8,48,y"
+	"d,0,n"
+	"0,d,n"
+	"32,0,n"
+	"0,32,n"
+	"17,d,n"
+	"d,17,n"
+	"120,16,n"
+	"16,120,n"
+	"0,128,n"
+	"128,0,n"
+	"130,0,n"
+	"0,130,n"
+	"0,0,n"
+)
+
+PING_TIMEOUT_SEC=4
+PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+
+# IDs of routers and hosts are initialized during the setup of the testing
+# network
+ROUTERS=''
+HOSTS=''
+
+SETUP_ERR=1
+
+ret=${ksft_skip}
+nsuccess=0
+nfail=0
+
+log_test()
+{
+	local rc="$1"
+	local expected="$2"
+	local msg="$3"
+
+	if [ "${rc}" -eq "${expected}" ]; then
+		nsuccess=$((nsuccess+1))
+		printf "\n    TEST: %-60s  [ OK ]\n" "${msg}"
+	else
+		ret=1
+		nfail=$((nfail+1))
+		printf "\n    TEST: %-60s  [FAIL]\n" "${msg}"
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+			echo
+			echo "hit enter to continue, 'q' to quit"
+			read a
+			[ "$a" = "q" ] && exit 1
+		fi
+	fi
+}
+
+print_log_test_results()
+{
+	printf "\nTests passed: %3d\n" "${nsuccess}"
+	printf "Tests failed: %3d\n"   "${nfail}"
+
+	# when a test fails, the value of 'ret' is set to 1 (error code).
+	# Conversely, when all tests are passed successfully, the 'ret' value
+	# is set to 0 (success code).
+	if [ "${ret}" -ne 1 ]; then
+		ret=0
+	fi
+}
+
+log_section()
+{
+	echo
+	echo "################################################################################"
+	echo "TEST SECTION: $*"
+	echo "################################################################################"
+}
+
+test_command_or_ksft_skip()
+{
+	local cmd="$1"
+
+	if [ ! -x "$(command -v "${cmd}")" ]; then
+		echo "SKIP: Could not run test without \"${cmd}\" tool";
+		exit "${ksft_skip}"
+	fi
+}
+
+get_nodename()
+{
+	local name="$1"
+
+	echo "${name}-${RDMSUFF}"
+}
+
+get_rtname()
+{
+	local rtid="$1"
+
+	get_nodename "rt-${rtid}"
+}
+
+get_hsname()
+{
+	local hsid="$1"
+
+	get_nodename "hs-${hsid}"
+}
+
+__create_namespace()
+{
+	local name="$1"
+
+	ip netns add "${name}"
+}
+
+create_router()
+{
+	local rtid="$1"
+	local nsname
+
+	nsname="$(get_rtname "${rtid}")"
+
+	__create_namespace "${nsname}"
+
+	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
+	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
+	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
+
+	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
+	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
+	ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
+}
+
+create_host()
+{
+	local hsid="$1"
+	local nsname
+
+	nsname="$(get_hsname "${hsid}")"
+
+	__create_namespace "${nsname}"
+}
+
+cleanup()
+{
+	local nsname
+	local i
+
+	# destroy routers
+	for i in ${ROUTERS}; do
+		nsname="$(get_rtname "${i}")"
+
+		ip netns del "${nsname}" &>/dev/null || true
+	done
+
+	# destroy hosts
+	for i in ${HOSTS}; do
+		nsname="$(get_hsname "${i}")"
+
+		ip netns del "${nsname}" &>/dev/null || true
+	done
+
+	# check whether the setup phase was completed successfully or not. In
+	# case of an error during the setup phase of the testing environment,
+	# the selftest is considered as "skipped".
+	if [ "${SETUP_ERR}" -ne 0 ]; then
+		echo "SKIP: Setting up the testing environment failed"
+		exit "${ksft_skip}"
+	fi
+
+	exit "${ret}"
+}
+
+add_link_rt_pairs()
+{
+	local rt="$1"
+	local rt_neighs="$2"
+	local neigh
+	local nsname
+	local neigh_nsname
+
+	nsname="$(get_rtname "${rt}")"
+
+	for neigh in ${rt_neighs}; do
+		neigh_nsname="$(get_rtname "${neigh}")"
+
+		ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
+			type veth peer name "veth-rt-${neigh}-${rt}" \
+			netns "${neigh_nsname}"
+	done
+}
+
+get_network_prefix()
+{
+	local rt="$1"
+	local neigh="$2"
+	local p="${rt}"
+	local q="${neigh}"
+
+	if [ "${p}" -gt "${q}" ]; then
+		p="${q}"; q="${rt}"
+	fi
+
+	echo "${IPv6_RT_NETWORK}:${p}:${q}"
+}
+
+# Setup the basic networking for the routers
+setup_rt_networking()
+{
+	local rt="$1"
+	local rt_neighs="$2"
+	local nsname
+	local net_prefix
+	local devname
+	local neigh
+
+	nsname="$(get_rtname "${rt}")"
+
+	for neigh in ${rt_neighs}; do
+		devname="veth-rt-${rt}-${neigh}"
+
+		net_prefix="$(get_network_prefix "${rt}" "${neigh}")"
+
+		ip -netns "${nsname}" addr \
+			add "${net_prefix}::${rt}/64" dev "${devname}" nodad
+
+		ip -netns "${nsname}" link set "${devname}" up
+	done
+
+        ip -netns "${nsname}" link add "${DUMMY_DEVNAME}" type dummy
+
+        ip -netns "${nsname}" link set "${DUMMY_DEVNAME}" up
+	ip -netns "${nsname}" link set lo up
+}
+
+# build an ipv6 prefix/address based on the input string
+# Note that the input string does not contain ':' and '::' which are considered
+# to be implicit.
+# e.g.:
+#  - input:  fbcc00000400300
+#  - output: fbcc:0000:0400:0300:0000:0000:0000:0000
+#                                ^^^^^^^^^^^^^^^^^^^
+#                              fill the address with 0s
+build_ipv6_addr()
+{
+	local addr="$1"
+	local out=""
+	local strlen="${#addr}"
+	local padn
+	local i
+
+	# add ":" every 4 digits (16 bits)
+	for (( i = 0; i < strlen; i++ )); do
+		if (( i > 0 && i < 32 && (i % 4) == 0 )); then
+			out="${out}:"
+		fi
+
+		out="${out}${addr:$i:1}"
+	done
+
+	# fill the remaining bits of the address with 0s
+	padn=$((32 - strlen))
+	for (( i = padn; i > 0; i-- )); do
+		if (( i > 0 && i < 32 && (i % 4) == 0 )); then
+			out="${out}:"
+		fi
+
+		out="${out}0"
+	done
+
+	printf "${out}"
+}
+
+build_csid()
+{
+	local nodeid="$1"
+
+	printf "${LCNODEFUNC_FMT}" "${nodeid}"
+}
+
+build_lcnode_func_prefix()
+{
+	local nodeid="$1"
+	local lcnodefunc
+	local prefix
+	local out
+
+	lcnodefunc="$(build_csid "${nodeid}")"
+	prefix="$(build_ipv6_addr "${LCBLOCK_ADDR}${lcnodefunc}")"
+
+	out="${prefix}/${LCBLOCK_NODEFUNC_BLEN}"
+
+	echo "${out}"
+}
+
+set_end_x_nextcsid()
+{
+	local rt="$1"
+	local adj="$2"
+
+	nsname="$(get_rtname "${rt}")"
+	net_prefix="$(get_network_prefix "${rt}" "${adj}")"
+	lcnode_func_prefix="$(build_lcnode_func_prefix "${rt}")"
+
+	# enabled NEXT-C-SID SRv6 End.X behavior (note that "dev" is the dummy
+	# dum0 device chosen for the sake of simplicity).
+	ip -netns "${nsname}" -6 route \
+		replace "${lcnode_func_prefix}" \
+		table "${LOCALSID_TABLE_ID}" \
+		encap seg6local action End.X nh6 "${net_prefix}::${adj}" \
+		flavors next-csid lblen "${LCBLOCK_BLEN}" \
+		nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}"
+}
+
+set_underlay_sids_reachability()
+{
+	local rt="$1"
+	local rt_neighs="$2"
+
+	nsname="$(get_rtname "${rt}")"
+
+	for neigh in ${rt_neighs}; do
+		devname="veth-rt-${rt}-${neigh}"
+
+		net_prefix="$(get_network_prefix "${rt}" "${neigh}")"
+
+		# set underlay network routes for SIDs reachability
+		ip -netns "${nsname}" -6 route \
+			replace "${VPN_LOCATOR_SERVICE}:${neigh}::/32" \
+			table "${LOCALSID_TABLE_ID}" \
+			via "${net_prefix}::${neigh}" dev "${devname}"
+
+		# set the underlay network for C-SIDs reachability
+		lcnode_func_prefix="$(build_lcnode_func_prefix "${neigh}")"
+
+		ip -netns "${nsname}" -6 route \
+			replace "${lcnode_func_prefix}" \
+			table "${LOCALSID_TABLE_ID}" \
+			via "${net_prefix}::${neigh}" dev "${devname}"
+	done
+}
+
+# Setup local SIDs for an SRv6 router
+setup_rt_local_sids()
+{
+	local rt="$1"
+	local rt_neighs="$2"
+	local net_prefix
+	local devname
+	local nsname
+	local neigh
+	local lcnode_func_prefix
+	local lcblock_prefix
+
+	nsname="$(get_rtname "${rt}")"
+
+        set_underlay_sids_reachability "${rt}" "${rt_neighs}"
+
+	# all SIDs for VPNs start with a common locator. Routes and SRv6
+	# Endpoint behavior instaces are grouped together in the 'localsid'
+	# table.
+	ip -netns "${nsname}" -6 rule \
+		add to "${VPN_LOCATOR_SERVICE}::/16" \
+		lookup "${LOCALSID_TABLE_ID}" prio 999
+
+	# common locator block for NEXT-C-SIDS compression mechanism.
+	lcblock_prefix="$(build_ipv6_addr "${LCBLOCK_ADDR}")"
+	ip -netns "${nsname}" -6 rule \
+		add to "${lcblock_prefix}/${LCBLOCK_BLEN}" \
+		lookup "${LOCALSID_TABLE_ID}" prio 999
+}
+
+# build and install the SRv6 policy into the ingress SRv6 router as well as the
+# decap SID in the egress one.
+# args:
+#  $1 - src host (evaluate automatically the ingress router)
+#  $2 - dst host (evaluate automatically the egress router)
+#  $3 - SRv6 routers configured for steering traffic (End.X behaviors)
+#  $4 - single SID or double SID
+#  $5 - traffic type (IPv6 or IPv4)
+__setup_l3vpn()
+{
+	local src="$1"
+	local dst="$2"
+	local end_rts="$3"
+	local mode="$4"
+	local traffic="$5"
+	local nsname
+	local policy
+	local container
+	local decapsid
+	local lcnfunc
+	local dt
+	local n
+	local rtsrc_nsname
+	local rtdst_nsname
+
+	rtsrc_nsname="$(get_rtname "${src}")"
+	rtdst_nsname="$(get_rtname "${dst}")"
+
+	container="${LCBLOCK_ADDR}"
+
+	# build first SID (C-SID container)
+	for n in ${end_rts}; do
+		lcnfunc="$(build_csid "${n}")"
+
+		container="${container}${lcnfunc}"
+	done
+
+	if [ "${mode}" -eq 1 ]; then
+		# single SID policy
+		dt="$(build_csid "${dst}")${DT46_FUNC}"
+		container="${container}${dt}"
+		# build the full ipv6 address for the container
+		policy="$(build_ipv6_addr "${container}")"
+
+		# build the decap SID used in the decap node
+		container="${LCBLOCK_ADDR}${dt}"
+		decapsid="$(build_ipv6_addr "${container}")"
+	else
+		# double SID policy
+		decapsid="${VPN_LOCATOR_SERVICE}:${dst}::${DT46_FUNC}"
+
+		policy="$(build_ipv6_addr "${container}"),${decapsid}"
+	fi
+
+	# apply encap policy
+	if [ "${traffic}" -eq 6 ]; then
+		ip -netns "${rtsrc_nsname}" -6 route \
+			add "${IPv6_HS_NETWORK}::${dst}" vrf "${VRF_DEVNAME}" \
+			encap seg6 mode "${HEADEND_ENCAP}" segs "${policy}" \
+			dev "${VRF_DEVNAME}"
+
+		ip -netns "${rtsrc_nsname}" -6 neigh \
+			add proxy "${IPv6_HS_NETWORK}::${dst}" \
+			dev "${RT2HS_DEVNAME}"
+	else
+		# "dev" must be different from the one where the packet is
+		# received, otherwise the proxy arp does not work.
+		ip -netns "${rtsrc_nsname}" -4 route \
+			add "${IPv4_HS_NETWORK}.${dst}" vrf "${VRF_DEVNAME}" \
+			encap seg6 mode "${HEADEND_ENCAP}" segs "${policy}" \
+			dev "${VRF_DEVNAME}"
+	fi
+
+	# apply decap
+	# Local End.DT46 behavior (decap)
+	ip -netns "${rtdst_nsname}" -6 route \
+		add "${decapsid}" \
+		table "${LOCALSID_TABLE_ID}" \
+		encap seg6local action End.DT46 vrftable "${VRF_TID}" \
+		dev "${VRF_DEVNAME}"
+}
+
+# see __setup_l3vpn()
+setup_ipv4_vpn_2sids()
+{
+	__setup_l3vpn "$1" "$2" "$3" 2 4
+}
+
+# see __setup_l3vpn()
+setup_ipv6_vpn_1sid()
+{
+	__setup_l3vpn "$1" "$2" "$3" 1 6
+}
+
+setup_hs()
+{
+	local hs="$1"
+	local rt="$2"
+	local hsname
+	local rtname
+
+	hsname="$(get_hsname "${hs}")"
+	rtname="$(get_rtname "${rt}")"
+
+	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
+	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
+
+	ip -netns "${hsname}" link add veth0 type veth \
+		peer name "${RT2HS_DEVNAME}" netns "${rtname}"
+
+	ip -netns "${hsname}" addr \
+		add "${IPv6_HS_NETWORK}::${hs}/64" dev veth0 nodad
+	ip -netns "${hsname}" addr add "${IPv4_HS_NETWORK}.${hs}/24" dev veth0
+
+	ip -netns "${hsname}" link set veth0 up
+	ip -netns "${hsname}" link set lo up
+
+	# configure the VRF on the router which is directly connected to the
+	# source host.
+	ip -netns "${rtname}" link \
+		add "${VRF_DEVNAME}" type vrf table "${VRF_TID}"
+	ip -netns "${rtname}" link set "${VRF_DEVNAME}" up
+
+	# enslave the veth interface connecting the router with the host to the
+	# VRF in the access router
+	ip -netns "${rtname}" link \
+		set "${RT2HS_DEVNAME}" master "${VRF_DEVNAME}"
+
+	# set default routes to unreachable for both ipv6 and ipv4
+	ip -netns "${rtname}" -6 route \
+		add unreachable default metric 4278198272 \
+		vrf "${VRF_DEVNAME}"
+	ip -netns "${rtname}" -4 route \
+		add unreachable default metric 4278198272 \
+		vrf "${VRF_DEVNAME}"
+
+	ip -netns "${rtname}" addr \
+		add "${IPv6_HS_NETWORK}::254/64" dev "${RT2HS_DEVNAME}" nodad
+	ip -netns "${rtname}" addr \
+		add "${IPv4_HS_NETWORK}.254/24" dev "${RT2HS_DEVNAME}"
+
+	ip -netns "${rtname}" link set "${RT2HS_DEVNAME}" up
+
+	ip netns exec "${rtname}" \
+		sysctl -wq net.ipv6.conf."${RT2HS_DEVNAME}".proxy_ndp=1
+	ip netns exec "${rtname}" \
+		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1
+
+	# disable the rp_filter otherwise the kernel gets confused about how
+	# to route decap ipv4 packets.
+	ip netns exec "${rtname}" \
+		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
+
+	ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
+}
+
+setup()
+{
+	local i
+
+	# create routers
+	ROUTERS="1 2 3 4"; readonly ROUTERS
+	for i in ${ROUTERS}; do
+		create_router "${i}"
+	done
+
+	# create hosts
+	HOSTS="1 2"; readonly HOSTS
+	for i in ${HOSTS}; do
+		create_host "${i}"
+	done
+
+	# set up the links for connecting routers
+	add_link_rt_pairs 1 "2 3 4"
+	add_link_rt_pairs 2 "3 4"
+	add_link_rt_pairs 3 "4"
+
+	# set up the basic connectivity of routers and routes required for
+	# reachability of SIDs.
+	setup_rt_networking 1 "2 3 4"
+	setup_rt_networking 2 "1 3 4"
+	setup_rt_networking 3 "1 2 4"
+	setup_rt_networking 4 "1 2 3"
+
+	# set up the hosts connected to routers
+	setup_hs 1 1
+	setup_hs 2 2
+
+	# set up default SRv6 Endpoints (i.e. SRv6 End and SRv6 End.DT46)
+	setup_rt_local_sids 1 "2 3 4"
+	setup_rt_local_sids 2 "1 3 4"
+	setup_rt_local_sids 3 "1 2 4"
+	setup_rt_local_sids 4 "1 2 3"
+
+	# set up SRv6 Policies
+
+	# create an IPv6 VPN between hosts hs-1 and hs-2.
+	#
+	# Direction hs-1 -> hs-2
+	# - rt-1 encap (H.Encaps.Red)
+	# - rt-3 SRv6 End.X behavior adj rt-4 (NEXT-C-SID flavor)
+	# - rt-4 Plain IPv6 Forwarding to rt-2
+	# - rt-2 SRv6 End.DT46 behavior
+	setup_ipv6_vpn_1sid 1 2 "3"
+
+	# Direction hs2 -> hs-1
+	# - rt-2 encap (H.Encaps.Red)
+	# - rt-4 SRv6 End.X behavior adj rt-1 (NEXT-C-SID flavor)
+	# - rt-1 SRv6 End.DT46 behavior
+	setup_ipv6_vpn_1sid 2 1 "4"
+
+	# create an IPv4 VPN between hosts hs-1 and hs-2
+	#
+	# Direction hs-1 -> hs-2
+	# - rt-1 encap (H.Encaps.Red)
+	# - rt-3 SRv6 End.X behavior adj rt-4 (NEXT-C-SID flavor)
+	# - rt-4 Plain IPv6 Forwarding to rt-2
+	# - rt-2 SRv6 End.DT46 behavior
+	setup_ipv4_vpn_2sids 1 2 "3"
+
+	# Direction hs-2 -> hs-1
+	# - rt-2 encap (H.Encaps.Red)
+	# - rt-3 SRv6 End.X behavior adj rt-4 (NEXT-C-SID flavor)
+	# - rt-4 Plain IPv6 Forwarding to rt-1
+	# - rt-1 SRv6 End.DT46 behavior
+	setup_ipv4_vpn_2sids 2 1 "3"
+
+	# Setup the adjacencies in the SRv6 aware routers
+	# - rt-3 SRv6 End.X adjacency with rt-4
+	# - rt-4 SRv6 End.X adjacency with rt-1
+        set_end_x_nextcsid 3 4
+        set_end_x_nextcsid 4 1
+
+	# testing environment was set up successfully
+	SETUP_ERR=0
+}
+
+check_rt_connectivity()
+{
+	local rtsrc="$1"
+	local rtdst="$2"
+	local prefix
+	local rtsrc_nsname
+
+	rtsrc_nsname="$(get_rtname "${rtsrc}")"
+
+	prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
+
+	ip netns exec "${rtsrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
+		"${prefix}::${rtdst}" >/dev/null 2>&1
+}
+
+check_and_log_rt_connectivity()
+{
+	local rtsrc="$1"
+	local rtdst="$2"
+
+	check_rt_connectivity "${rtsrc}" "${rtdst}"
+	log_test $? 0 "Routers connectivity: rt-${rtsrc} -> rt-${rtdst}"
+}
+
+check_hs_ipv6_connectivity()
+{
+	local hssrc="$1"
+	local hsdst="$2"
+	local hssrc_nsname
+
+	hssrc_nsname="$(get_hsname "${hssrc}")"
+
+	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
+		"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
+}
+
+check_hs_ipv4_connectivity()
+{
+	local hssrc="$1"
+	local hsdst="$2"
+	local hssrc_nsname
+
+	hssrc_nsname="$(get_hsname "${hssrc}")"
+
+	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
+		"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
+}
+
+check_and_log_hs2gw_connectivity()
+{
+	local hssrc="$1"
+
+	check_hs_ipv6_connectivity "${hssrc}" 254
+	log_test $? 0 "IPv6 Hosts connectivity: hs-${hssrc} -> gw"
+
+	check_hs_ipv4_connectivity "${hssrc}" 254
+	log_test $? 0 "IPv4 Hosts connectivity: hs-${hssrc} -> gw"
+}
+
+check_and_log_hs_ipv6_connectivity()
+{
+	local hssrc="$1"
+	local hsdst="$2"
+
+	check_hs_ipv6_connectivity "${hssrc}" "${hsdst}"
+	log_test $? 0 "IPv6 Hosts connectivity: hs-${hssrc} -> hs-${hsdst}"
+}
+
+check_and_log_hs_ipv4_connectivity()
+{
+	local hssrc="$1"
+	local hsdst="$2"
+
+	check_hs_ipv4_connectivity "${hssrc}" "${hsdst}"
+	log_test $? 0 "IPv4 Hosts connectivity: hs-${hssrc} -> hs-${hsdst}"
+}
+
+router_tests()
+{
+	local i
+	local j
+
+	log_section "IPv6 routers connectivity test"
+
+	for i in ${ROUTERS}; do
+		for j in ${ROUTERS}; do
+			if [ "${i}" -eq "${j}" ]; then
+				continue
+			fi
+
+			check_and_log_rt_connectivity "${i}" "${j}"
+		done
+	done
+}
+
+host2gateway_tests()
+{
+	local hs
+
+	log_section "IPv4/IPv6 connectivity test among hosts and gateways"
+
+	for hs in ${HOSTS}; do
+		check_and_log_hs2gw_connectivity "${hs}"
+	done
+}
+
+host_vpn_tests()
+{
+	log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv6)"
+
+	check_and_log_hs_ipv6_connectivity 1 2
+	check_and_log_hs_ipv6_connectivity 2 1
+
+	log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv4)"
+
+	check_and_log_hs_ipv4_connectivity 1 2
+	check_and_log_hs_ipv4_connectivity 2 1
+}
+
+__nextcsid_end_x_behavior_test()
+{
+	local nsname="$1"
+	local cmd="$2"
+	local blen="$3"
+	local flen="$4"
+	local layout=""
+
+	if [ "${blen}" != "d" ]; then
+		layout="${layout} lblen ${blen}"
+	fi
+
+	if [ "${flen}" != "d" ]; then
+		layout="${layout} nflen ${flen}"
+	fi
+
+	ip -netns "${nsname}" -6 route \
+		"${cmd}" "${CSID_CNTR_PREFIX}" \
+		table "${CSID_CNTR_RT_TABLE}" \
+		encap seg6local action End.X nh6 :: \
+		flavors next-csid ${layout} \
+		dev "${DUMMY_DEVNAME}" &>/dev/null
+
+	return "$?"
+}
+
+rt_x_nextcsid_end_x_behavior_test()
+{
+	local rt="$1"
+	local blen="$2"
+	local flen="$3"
+	local nsname
+	local ret
+
+	nsname="$(get_rtname "${rt}")"
+
+	__nextcsid_end_x_behavior_test "${nsname}" "add" "${blen}" "${flen}"
+	ret="$?"
+	__nextcsid_end_x_behavior_test "${nsname}" "del" "${blen}" "${flen}"
+
+	return "${ret}"
+}
+
+__parse_csid_container_cfg()
+{
+	local cfg="$1"
+	local index="$2"
+	local out
+
+	echo "${cfg}" | cut -d',' -f"${index}"
+}
+
+csid_container_cfg_tests()
+{
+	local valid
+	local blen
+	local flen
+	local cfg
+	local ret
+
+	log_section "C-SID Container config tests (legend: d='kernel default')"
+
+	for cfg in "${CSID_CONTAINER_CFGS[@]}"; do
+		blen="$(__parse_csid_container_cfg "${cfg}" 1)"
+		flen="$(__parse_csid_container_cfg "${cfg}" 2)"
+		valid="$(__parse_csid_container_cfg "${cfg}" 3)"
+
+		rt_x_nextcsid_end_x_behavior_test \
+			"${CSID_CNTR_RT_ID_TEST}" \
+			"${blen}" \
+			"${flen}"
+		ret="$?"
+
+		if [ "${valid}" == "y" ]; then
+			log_test "${ret}" 0 \
+				"Accept valid C-SID container cfg (lblen=${blen}, nflen=${flen})"
+		else
+			log_test "${ret}" 2 \
+				"Reject invalid C-SID container cfg (lblen=${blen}, nflen=${flen})"
+		fi
+	done
+}
+
+test_iproute2_supp_or_ksft_skip()
+{
+	if ! ip route help 2>&1 | grep -qo "next-csid"; then
+		echo "SKIP: Missing SRv6 NEXT-C-SID flavor support in iproute2"
+		exit "${ksft_skip}"
+	fi
+}
+
+test_dummy_dev_or_ksft_skip()
+{
+        local test_netns
+
+        test_netns="dummy-$(mktemp -u XXXXXXXX)"
+
+        if ! ip netns add "${test_netns}"; then
+                echo "SKIP: Cannot set up netns for testing dummy dev support"
+                exit "${ksft_skip}"
+        fi
+
+        modprobe dummy &>/dev/null || true
+        if ! ip -netns "${test_netns}" link \
+                add "${DUMMY_DEVNAME}" type dummy; then
+                echo "SKIP: dummy dev not supported"
+
+                ip netns del "${test_netns}"
+                exit "${ksft_skip}"
+        fi
+
+        ip netns del "${test_netns}"
+}
+
+test_vrf_or_ksft_skip()
+{
+	modprobe vrf &>/dev/null || true
+	if [ ! -e /proc/sys/net/vrf/strict_mode ]; then
+		echo "SKIP: vrf sysctl does not exist"
+		exit "${ksft_skip}"
+	fi
+}
+
+if [ "$(id -u)" -ne 0 ]; then
+	echo "SKIP: Need root privileges"
+	exit "${ksft_skip}"
+fi
+
+# required programs to carry out this selftest
+test_command_or_ksft_skip ip
+test_command_or_ksft_skip ping
+test_command_or_ksft_skip sysctl
+test_command_or_ksft_skip grep
+test_command_or_ksft_skip cut
+
+test_iproute2_supp_or_ksft_skip
+test_dummy_dev_or_ksft_skip
+test_vrf_or_ksft_skip
+
+set -e
+trap cleanup EXIT
+
+setup
+set +e
+
+csid_container_cfg_tests
+
+router_tests
+host2gateway_tests
+host_vpn_tests
+
+print_log_test_results
-- 
GitLab


From 23ab9324fd260277f83a07c51fdc625442e98265 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Sun, 13 Aug 2023 19:48:55 +0300
Subject: [PATCH 1238/1806] nexthop: Simplify nexthop bucket dump

Before commit f10d3d9df49d ("nexthop: Make nexthop bucket dump more
efficient"), rtm_dump_nexthop_bucket_nh() returned a non-zero return
code for each resilient nexthop group whose buckets it dumped,
regardless if it encountered an error or not.

This meant that the sentinel ('dd->ctx->nh.idx') used by the function
that walked the different nexthops could not be used as a sentinel for
the bucket dump, as otherwise buckets from the same group would be
dumped over and over again.

This was dealt with by adding another sentinel ('dd->ctx->done_nh_idx')
that was incremented by rtm_dump_nexthop_bucket_nh() after successfully
dumping all the buckets from a given group.

After the previously mentioned commit this sentinel is no longer
necessary since the function no longer returns a non-zero return code
when successfully dumping all the buckets from a given group.

Remove this sentinel and simplify the code.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230813164856.2379822-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/nexthop.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 09d36bcbd7d4a..7e8bb85e9dcbe 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -3337,7 +3337,6 @@ static int nh_valid_dump_bucket_req(const struct nlmsghdr *nlh,
 struct rtm_dump_res_bucket_ctx {
 	struct rtm_dump_nh_ctx nh;
 	u16 bucket_index;
-	u32 done_nh_idx; /* 1 + the index of the last fully processed NH. */
 };
 
 static struct rtm_dump_res_bucket_ctx *
@@ -3366,9 +3365,6 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb,
 	u16 bucket_index;
 	int err;
 
-	if (dd->ctx->nh.idx < dd->ctx->done_nh_idx)
-		return 0;
-
 	nhg = rtnl_dereference(nh->nh_grp);
 	res_table = rtnl_dereference(nhg->res_table);
 	for (bucket_index = dd->ctx->bucket_index;
@@ -3395,7 +3391,6 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb,
 			return err;
 	}
 
-	dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1;
 	dd->ctx->bucket_index = 0;
 
 	return 0;
-- 
GitLab


From db1428f66a8c97793e6596e7c62047211dd6db79 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Sun, 13 Aug 2023 19:48:56 +0300
Subject: [PATCH 1239/1806] nexthop: Do not increment dump sentinel at the end
 of the dump

The nexthop and nexthop bucket dump callbacks previously returned a
positive return code even when the dump was complete, prompting the core
netlink code to invoke the callback again, until returning zero.

Zero was only returned by these callbacks when no information was filled
in the provided skb, which was achieved by incrementing the dump
sentinel at the end of the dump beyond the ID of the last nexthop.

This is no longer necessary as when the dump is complete these callbacks
return zero.

Remove the unnecessary increment.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230813164856.2379822-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/nexthop.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 7e8bb85e9dcbe..bbff68b5b5d4a 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -3209,7 +3209,6 @@ static int rtm_dump_walk_nexthops(struct sk_buff *skb,
 			return err;
 	}
 
-	ctx->idx++;
 	return 0;
 }
 
-- 
GitLab


From c66937b0f8dbb4c6c043663c702b1053fb47fab2 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Mon, 14 Aug 2023 02:58:14 +0100
Subject: [PATCH 1240/1806] net: phy: mediatek-ge-soc: support PHY LEDs

Implement netdev trigger and primitive bliking offloading as well as
simple set_brigthness function for both PHY LEDs of the in-SoC PHYs
found in MT7981 and MT7988.

For MT7988, read boottrap register and apply LED polarities accordingly
to get uniform behavior from all LEDs on MT7988.
This requires syscon phandle 'mediatek,pio' present in parenting MDIO bus
which should point to the syscon holding the boottrap register.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/dc324d48c00cd7350f3a506eaa785324cae97372.1691977904.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mediatek-ge-soc.c | 435 +++++++++++++++++++++++++++++-
 1 file changed, 426 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek-ge-soc.c
index da512fab0eb0b..8a20d9889f105 100644
--- a/drivers/net/phy/mediatek-ge-soc.c
+++ b/drivers/net/phy/mediatek-ge-soc.c
@@ -1,9 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0+
 #include <linux/bitfield.h>
+#include <linux/bitmap.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/nvmem-consumer.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/phy.h>
+#include <linux/regmap.h>
 
 #define MTK_GPHY_ID_MT7981			0x03a29461
 #define MTK_GPHY_ID_MT7988			0x03a29481
@@ -206,9 +209,42 @@
 #define MTK_PHY_DA_TX_R50_PAIR_C		0x53f
 #define MTK_PHY_DA_TX_R50_PAIR_D		0x540
 
+/* Registers on MDIO_MMD_VEND2 */
+#define MTK_PHY_LED0_ON_CTRL			0x24
+#define MTK_PHY_LED1_ON_CTRL			0x26
+#define   MTK_PHY_LED_ON_MASK			GENMASK(6, 0)
+#define   MTK_PHY_LED_ON_LINK1000		BIT(0)
+#define   MTK_PHY_LED_ON_LINK100		BIT(1)
+#define   MTK_PHY_LED_ON_LINK10			BIT(2)
+#define   MTK_PHY_LED_ON_LINKDOWN		BIT(3)
+#define   MTK_PHY_LED_ON_FDX			BIT(4) /* Full duplex */
+#define   MTK_PHY_LED_ON_HDX			BIT(5) /* Half duplex */
+#define   MTK_PHY_LED_ON_FORCE_ON		BIT(6)
+#define   MTK_PHY_LED_ON_POLARITY		BIT(14)
+#define   MTK_PHY_LED_ON_ENABLE			BIT(15)
+
+#define MTK_PHY_LED0_BLINK_CTRL			0x25
+#define MTK_PHY_LED1_BLINK_CTRL			0x27
+#define   MTK_PHY_LED_BLINK_1000TX		BIT(0)
+#define   MTK_PHY_LED_BLINK_1000RX		BIT(1)
+#define   MTK_PHY_LED_BLINK_100TX		BIT(2)
+#define   MTK_PHY_LED_BLINK_100RX		BIT(3)
+#define   MTK_PHY_LED_BLINK_10TX		BIT(4)
+#define   MTK_PHY_LED_BLINK_10RX		BIT(5)
+#define   MTK_PHY_LED_BLINK_COLLISION		BIT(6)
+#define   MTK_PHY_LED_BLINK_RX_CRC_ERR		BIT(7)
+#define   MTK_PHY_LED_BLINK_RX_IDLE_ERR		BIT(8)
+#define   MTK_PHY_LED_BLINK_FORCE_BLINK		BIT(9)
+
+#define MTK_PHY_LED1_DEFAULT_POLARITIES		BIT(1)
+
 #define MTK_PHY_RG_BG_RASEL			0x115
 #define   MTK_PHY_RG_BG_RASEL_MASK		GENMASK(2, 0)
 
+/* 'boottrap' register reflecting the configuration of the 4 PHY LEDs */
+#define RG_GPIO_MISC_TPBANK0			0x6f0
+#define   RG_GPIO_MISC_TPBANK0_BOOTMODE		GENMASK(11, 8)
+
 /* These macro privides efuse parsing for internal phy. */
 #define EFS_DA_TX_I2MPB_A(x)			(((x) >> 0) & GENMASK(5, 0))
 #define EFS_DA_TX_I2MPB_B(x)			(((x) >> 6) & GENMASK(5, 0))
@@ -236,13 +272,6 @@ enum {
 	PAIR_D,
 };
 
-enum {
-	GPHY_PORT0,
-	GPHY_PORT1,
-	GPHY_PORT2,
-	GPHY_PORT3,
-};
-
 enum calibration_mode {
 	EFUSE_K,
 	SW_K
@@ -261,6 +290,19 @@ enum CAL_MODE {
 	SW_M
 };
 
+#define MTK_PHY_LED_STATE_FORCE_ON	0
+#define MTK_PHY_LED_STATE_FORCE_BLINK	1
+#define MTK_PHY_LED_STATE_NETDEV	2
+
+struct mtk_socphy_priv {
+	unsigned long		led_state;
+};
+
+struct mtk_socphy_shared {
+	u32			boottrap;
+	struct mtk_socphy_priv	priv[4];
+};
+
 static int mtk_socphy_read_page(struct phy_device *phydev)
 {
 	return __phy_read(phydev, MTK_EXT_PAGE_ACCESS);
@@ -1071,6 +1113,371 @@ static int mt798x_phy_config_init(struct phy_device *phydev)
 	return mt798x_phy_calibration(phydev);
 }
 
+static int mt798x_phy_hw_led_on_set(struct phy_device *phydev, u8 index,
+				    bool on)
+{
+	unsigned int bit_on = MTK_PHY_LED_STATE_FORCE_ON + (index ? 16 : 0);
+	struct mtk_socphy_priv *priv = phydev->priv;
+	bool changed;
+
+	if (on)
+		changed = !test_and_set_bit(bit_on, &priv->led_state);
+	else
+		changed = !!test_and_clear_bit(bit_on, &priv->led_state);
+
+	changed |= !!test_and_clear_bit(MTK_PHY_LED_STATE_NETDEV +
+					(index ? 16 : 0), &priv->led_state);
+	if (changed)
+		return phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ?
+				      MTK_PHY_LED1_ON_CTRL : MTK_PHY_LED0_ON_CTRL,
+				      MTK_PHY_LED_ON_MASK,
+				      on ? MTK_PHY_LED_ON_FORCE_ON : 0);
+	else
+		return 0;
+}
+
+static int mt798x_phy_hw_led_blink_set(struct phy_device *phydev, u8 index,
+				       bool blinking)
+{
+	unsigned int bit_blink = MTK_PHY_LED_STATE_FORCE_BLINK + (index ? 16 : 0);
+	struct mtk_socphy_priv *priv = phydev->priv;
+	bool changed;
+
+	if (blinking)
+		changed = !test_and_set_bit(bit_blink, &priv->led_state);
+	else
+		changed = !!test_and_clear_bit(bit_blink, &priv->led_state);
+
+	changed |= !!test_bit(MTK_PHY_LED_STATE_NETDEV +
+			      (index ? 16 : 0), &priv->led_state);
+	if (changed)
+		return phy_write_mmd(phydev, MDIO_MMD_VEND2, index ?
+				     MTK_PHY_LED1_BLINK_CTRL : MTK_PHY_LED0_BLINK_CTRL,
+				     blinking ? MTK_PHY_LED_BLINK_FORCE_BLINK : 0);
+	else
+		return 0;
+}
+
+static int mt798x_phy_led_blink_set(struct phy_device *phydev, u8 index,
+				    unsigned long *delay_on,
+				    unsigned long *delay_off)
+{
+	bool blinking = false;
+	int err = 0;
+
+	if (index > 1)
+		return -EINVAL;
+
+	if (delay_on && delay_off && (*delay_on > 0) && (*delay_off > 0)) {
+		blinking = true;
+		*delay_on = 50;
+		*delay_off = 50;
+	}
+
+	err = mt798x_phy_hw_led_blink_set(phydev, index, blinking);
+	if (err)
+		return err;
+
+	return mt798x_phy_hw_led_on_set(phydev, index, false);
+}
+
+static int mt798x_phy_led_brightness_set(struct phy_device *phydev,
+					 u8 index, enum led_brightness value)
+{
+	int err;
+
+	err = mt798x_phy_hw_led_blink_set(phydev, index, false);
+	if (err)
+		return err;
+
+	return mt798x_phy_hw_led_on_set(phydev, index, (value != LED_OFF));
+}
+
+static const unsigned long supported_triggers = (BIT(TRIGGER_NETDEV_FULL_DUPLEX) |
+						 BIT(TRIGGER_NETDEV_HALF_DUPLEX) |
+						 BIT(TRIGGER_NETDEV_LINK)        |
+						 BIT(TRIGGER_NETDEV_LINK_10)     |
+						 BIT(TRIGGER_NETDEV_LINK_100)    |
+						 BIT(TRIGGER_NETDEV_LINK_1000)   |
+						 BIT(TRIGGER_NETDEV_RX)          |
+						 BIT(TRIGGER_NETDEV_TX));
+
+static int mt798x_phy_led_hw_is_supported(struct phy_device *phydev, u8 index,
+					  unsigned long rules)
+{
+	if (index > 1)
+		return -EINVAL;
+
+	/* All combinations of the supported triggers are allowed */
+	if (rules & ~supported_triggers)
+		return -EOPNOTSUPP;
+
+	return 0;
+};
+
+static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index,
+					 unsigned long *rules)
+{
+	unsigned int bit_blink = MTK_PHY_LED_STATE_FORCE_BLINK + (index ? 16 : 0);
+	unsigned int bit_netdev = MTK_PHY_LED_STATE_NETDEV + (index ? 16 : 0);
+	unsigned int bit_on = MTK_PHY_LED_STATE_FORCE_ON + (index ? 16 : 0);
+	struct mtk_socphy_priv *priv = phydev->priv;
+	int on, blink;
+
+	if (index > 1)
+		return -EINVAL;
+
+	on = phy_read_mmd(phydev, MDIO_MMD_VEND2,
+			  index ? MTK_PHY_LED1_ON_CTRL : MTK_PHY_LED0_ON_CTRL);
+
+	if (on < 0)
+		return -EIO;
+
+	blink = phy_read_mmd(phydev, MDIO_MMD_VEND2,
+			     index ? MTK_PHY_LED1_BLINK_CTRL :
+				     MTK_PHY_LED0_BLINK_CTRL);
+	if (blink < 0)
+		return -EIO;
+
+	if ((on & (MTK_PHY_LED_ON_LINK1000 | MTK_PHY_LED_ON_LINK100 |
+		   MTK_PHY_LED_ON_LINK10)) ||
+	    (blink & (MTK_PHY_LED_BLINK_1000RX | MTK_PHY_LED_BLINK_100RX |
+		      MTK_PHY_LED_BLINK_10RX | MTK_PHY_LED_BLINK_1000TX |
+		      MTK_PHY_LED_BLINK_100TX | MTK_PHY_LED_BLINK_10TX)))
+		set_bit(bit_netdev, &priv->led_state);
+	else
+		clear_bit(bit_netdev, &priv->led_state);
+
+	if (on & MTK_PHY_LED_ON_FORCE_ON)
+		set_bit(bit_on, &priv->led_state);
+	else
+		clear_bit(bit_on, &priv->led_state);
+
+	if (blink & MTK_PHY_LED_BLINK_FORCE_BLINK)
+		set_bit(bit_blink, &priv->led_state);
+	else
+		clear_bit(bit_blink, &priv->led_state);
+
+	if (!rules)
+		return 0;
+
+	if (on & (MTK_PHY_LED_ON_LINK1000 | MTK_PHY_LED_ON_LINK100 | MTK_PHY_LED_ON_LINK10))
+		*rules |= BIT(TRIGGER_NETDEV_LINK);
+
+	if (on & MTK_PHY_LED_ON_LINK10)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_10);
+
+	if (on & MTK_PHY_LED_ON_LINK100)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_100);
+
+	if (on & MTK_PHY_LED_ON_LINK1000)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_1000);
+
+	if (on & MTK_PHY_LED_ON_FDX)
+		*rules |= BIT(TRIGGER_NETDEV_FULL_DUPLEX);
+
+	if (on & MTK_PHY_LED_ON_HDX)
+		*rules |= BIT(TRIGGER_NETDEV_HALF_DUPLEX);
+
+	if (blink & (MTK_PHY_LED_BLINK_1000RX | MTK_PHY_LED_BLINK_100RX | MTK_PHY_LED_BLINK_10RX))
+		*rules |= BIT(TRIGGER_NETDEV_RX);
+
+	if (blink & (MTK_PHY_LED_BLINK_1000TX | MTK_PHY_LED_BLINK_100TX | MTK_PHY_LED_BLINK_10TX))
+		*rules |= BIT(TRIGGER_NETDEV_TX);
+
+	return 0;
+};
+
+static int mt798x_phy_led_hw_control_set(struct phy_device *phydev, u8 index,
+					 unsigned long rules)
+{
+	unsigned int bit_netdev = MTK_PHY_LED_STATE_NETDEV + (index ? 16 : 0);
+	struct mtk_socphy_priv *priv = phydev->priv;
+	u16 on = 0, blink = 0;
+	int ret;
+
+	if (index > 1)
+		return -EINVAL;
+
+	if (rules & BIT(TRIGGER_NETDEV_FULL_DUPLEX))
+		on |= MTK_PHY_LED_ON_FDX;
+
+	if (rules & BIT(TRIGGER_NETDEV_HALF_DUPLEX))
+		on |= MTK_PHY_LED_ON_HDX;
+
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_10) | BIT(TRIGGER_NETDEV_LINK)))
+		on |= MTK_PHY_LED_ON_LINK10;
+
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_100) | BIT(TRIGGER_NETDEV_LINK)))
+		on |= MTK_PHY_LED_ON_LINK100;
+
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_1000) | BIT(TRIGGER_NETDEV_LINK)))
+		on |= MTK_PHY_LED_ON_LINK1000;
+
+	if (rules & BIT(TRIGGER_NETDEV_RX)) {
+		blink |= MTK_PHY_LED_BLINK_10RX  |
+			 MTK_PHY_LED_BLINK_100RX |
+			 MTK_PHY_LED_BLINK_1000RX;
+	}
+
+	if (rules & BIT(TRIGGER_NETDEV_TX)) {
+		blink |= MTK_PHY_LED_BLINK_10TX  |
+			 MTK_PHY_LED_BLINK_100TX |
+			 MTK_PHY_LED_BLINK_1000TX;
+	}
+
+	if (blink || on)
+		set_bit(bit_netdev, &priv->led_state);
+	else
+		clear_bit(bit_netdev, &priv->led_state);
+
+	ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ?
+				MTK_PHY_LED1_ON_CTRL :
+				MTK_PHY_LED0_ON_CTRL,
+			     MTK_PHY_LED_ON_FDX     |
+			     MTK_PHY_LED_ON_HDX     |
+			     MTK_PHY_LED_ON_LINK10  |
+			     MTK_PHY_LED_ON_LINK100 |
+			     MTK_PHY_LED_ON_LINK1000,
+			     on);
+
+	if (ret)
+		return ret;
+
+	return phy_write_mmd(phydev, MDIO_MMD_VEND2, index ?
+				MTK_PHY_LED1_BLINK_CTRL :
+				MTK_PHY_LED0_BLINK_CTRL, blink);
+};
+
+static bool mt7988_phy_led_get_polarity(struct phy_device *phydev, int led_num)
+{
+	struct mtk_socphy_shared *priv = phydev->shared->priv;
+	u32 polarities;
+
+	if (led_num == 0)
+		polarities = ~(priv->boottrap);
+	else
+		polarities = MTK_PHY_LED1_DEFAULT_POLARITIES;
+
+	if (polarities & BIT(phydev->mdio.addr))
+		return true;
+
+	return false;
+}
+
+static int mt7988_phy_fix_leds_polarities(struct phy_device *phydev)
+{
+	struct pinctrl *pinctrl;
+	int index;
+
+	/* Setup LED polarity according to bootstrap use of LED pins */
+	for (index = 0; index < 2; ++index)
+		phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ?
+				MTK_PHY_LED1_ON_CTRL : MTK_PHY_LED0_ON_CTRL,
+			       MTK_PHY_LED_ON_POLARITY,
+			       mt7988_phy_led_get_polarity(phydev, index) ?
+				MTK_PHY_LED_ON_POLARITY : 0);
+
+	/* Only now setup pinctrl to avoid bogus blinking */
+	pinctrl = devm_pinctrl_get_select(&phydev->mdio.dev, "gbe-led");
+	if (IS_ERR(pinctrl))
+		dev_err(&phydev->mdio.bus->dev, "Failed to setup PHY LED pinctrl\n");
+
+	return 0;
+}
+
+static int mt7988_phy_probe_shared(struct phy_device *phydev)
+{
+	struct device_node *np = dev_of_node(&phydev->mdio.bus->dev);
+	struct mtk_socphy_shared *shared = phydev->shared->priv;
+	struct regmap *regmap;
+	u32 reg;
+	int ret;
+
+	/* The LED0 of the 4 PHYs in MT7988 are wired to SoC pins LED_A, LED_B,
+	 * LED_C and LED_D respectively. At the same time those pins are used to
+	 * bootstrap configuration of the reference clock source (LED_A),
+	 * DRAM DDRx16b x2/x1 (LED_B) and boot device (LED_C, LED_D).
+	 * In practise this is done using a LED and a resistor pulling the pin
+	 * either to GND or to VIO.
+	 * The detected value at boot time is accessible at run-time using the
+	 * TPBANK0 register located in the gpio base of the pinctrl, in order
+	 * to read it here it needs to be referenced by a phandle called
+	 * 'mediatek,pio' in the MDIO bus hosting the PHY.
+	 * The 4 bits in TPBANK0 are kept as package shared data and are used to
+	 * set LED polarity for each of the LED0.
+	 */
+	regmap = syscon_regmap_lookup_by_phandle(np, "mediatek,pio");
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	ret = regmap_read(regmap, RG_GPIO_MISC_TPBANK0, &reg);
+	if (ret)
+		return ret;
+
+	shared->boottrap = FIELD_GET(RG_GPIO_MISC_TPBANK0_BOOTMODE, reg);
+
+	return 0;
+}
+
+static void mt798x_phy_leds_state_init(struct phy_device *phydev)
+{
+	int i;
+
+	for (i = 0; i < 2; ++i)
+		mt798x_phy_led_hw_control_get(phydev, i, NULL);
+}
+
+static int mt7988_phy_probe(struct phy_device *phydev)
+{
+	struct mtk_socphy_shared *shared;
+	struct mtk_socphy_priv *priv;
+	int err;
+
+	if (phydev->mdio.addr > 3)
+		return -EINVAL;
+
+	err = devm_phy_package_join(&phydev->mdio.dev, phydev, 0,
+				    sizeof(struct mtk_socphy_shared));
+	if (err)
+		return err;
+
+	if (phy_package_probe_once(phydev)) {
+		err = mt7988_phy_probe_shared(phydev);
+		if (err)
+			return err;
+	}
+
+	shared = phydev->shared->priv;
+	priv = &shared->priv[phydev->mdio.addr];
+
+	phydev->priv = priv;
+
+	mt798x_phy_leds_state_init(phydev);
+
+	err = mt7988_phy_fix_leds_polarities(phydev);
+	if (err)
+		return err;
+
+	return mt798x_phy_calibration(phydev);
+}
+
+static int mt7981_phy_probe(struct phy_device *phydev)
+{
+	struct mtk_socphy_priv *priv;
+
+	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(struct mtk_socphy_priv),
+			    GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	phydev->priv = priv;
+
+	mt798x_phy_leds_state_init(phydev);
+
+	return mt798x_phy_calibration(phydev);
+}
+
 static struct phy_driver mtk_socphy_driver[] = {
 	{
 		PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7981),
@@ -1078,11 +1485,16 @@ static struct phy_driver mtk_socphy_driver[] = {
 		.config_init	= mt798x_phy_config_init,
 		.config_intr	= genphy_no_config_intr,
 		.handle_interrupt = genphy_handle_interrupt_no_ack,
-		.probe		= mt798x_phy_calibration,
+		.probe		= mt7981_phy_probe,
 		.suspend	= genphy_suspend,
 		.resume		= genphy_resume,
 		.read_page	= mtk_socphy_read_page,
 		.write_page	= mtk_socphy_write_page,
+		.led_blink_set	= mt798x_phy_led_blink_set,
+		.led_brightness_set = mt798x_phy_led_brightness_set,
+		.led_hw_is_supported = mt798x_phy_led_hw_is_supported,
+		.led_hw_control_set = mt798x_phy_led_hw_control_set,
+		.led_hw_control_get = mt798x_phy_led_hw_control_get,
 	},
 	{
 		PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7988),
@@ -1090,11 +1502,16 @@ static struct phy_driver mtk_socphy_driver[] = {
 		.config_init	= mt798x_phy_config_init,
 		.config_intr	= genphy_no_config_intr,
 		.handle_interrupt = genphy_handle_interrupt_no_ack,
-		.probe		= mt798x_phy_calibration,
+		.probe		= mt7988_phy_probe,
 		.suspend	= genphy_suspend,
 		.resume		= genphy_resume,
 		.read_page	= mtk_socphy_read_page,
 		.write_page	= mtk_socphy_write_page,
+		.led_blink_set	= mt798x_phy_led_blink_set,
+		.led_brightness_set = mt798x_phy_led_brightness_set,
+		.led_hw_is_supported = mt798x_phy_led_hw_is_supported,
+		.led_hw_control_set = mt798x_phy_led_hw_control_set,
+		.led_hw_control_get = mt798x_phy_led_hw_control_get,
 	},
 };
 
-- 
GitLab


From 7a456b894ea57cceee6951ce421205152f23a051 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Aug 2023 09:45:03 +0200
Subject: [PATCH 1241/1806] qed: remove unused 'resp_size' calculation

Newer versions of clang warn about this variable being assigned but
never used:

drivers/net/ethernet/qlogic/qed/qed_vf.c:63:67: error: parameter 'resp_size' set but not used [-Werror,-Wunused-but-set-parameter]

There is no indication in the git history on how this was ever
meant to be used, so just remove the entire calculation and argument
passing for it to avoid the warning.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230814074512.1067715-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qlogic/qed/qed_vf.c | 45 +++++++++---------------
 1 file changed, 17 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 7b0e390c0b07d..0e265ed1f501c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -60,7 +60,7 @@ static void qed_vf_pf_req_end(struct qed_hwfn *p_hwfn, int req_status)
 #define QED_VF_CHANNEL_MSLEEP_ITERATIONS	10
 #define QED_VF_CHANNEL_MSLEEP_DELAY		25
 
-static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
+static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done)
 {
 	union vfpf_tlvs *p_req = p_hwfn->vf_iov_info->vf2pf_request;
 	struct ustorm_trigger_vf_zone trigger;
@@ -72,9 +72,6 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 	/* output tlvs list */
 	qed_dp_tlv_list(p_hwfn, p_req);
 
-	/* need to add the END TLV to the message size */
-	resp_size += sizeof(struct channel_list_end_tlv);
-
 	/* Send TLVs over HW channel */
 	memset(&trigger, 0, sizeof(struct ustorm_trigger_vf_zone));
 	trigger.vf_pf_msg_valid = 1;
@@ -172,7 +169,7 @@ static int _qed_vf_pf_release(struct qed_hwfn *p_hwfn, bool b_final)
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
 	resp = &p_iov->pf2vf_reply->default_resp;
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 
 	if (!rc && resp->hdr.status != PFVF_STATUS_SUCCESS)
 		rc = -EAGAIN;
@@ -301,7 +298,7 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
 		memset(p_iov->pf2vf_reply, 0, sizeof(union pfvf_tlvs));
 
 		/* send acquire request */
-		rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+		rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 
 		/* Re-try acquire in case of vf-pf hw channel timeout */
 		if (retry_cnt && rc == -EBUSY) {
@@ -705,7 +702,7 @@ int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn,
 		    sizeof(struct channel_list_end_tlv));
 
 	p_resp = &p_iov->pf2vf_reply->tunn_param_resp;
-	rc = qed_send_msg2pf(p_hwfn, &p_resp->hdr.status, sizeof(*p_resp));
+	rc = qed_send_msg2pf(p_hwfn, &p_resp->hdr.status);
 
 	if (rc)
 		goto exit;
@@ -772,7 +769,7 @@ qed_vf_pf_rxq_start(struct qed_hwfn *p_hwfn,
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
 	resp = &p_iov->pf2vf_reply->queue_start;
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -822,7 +819,7 @@ int qed_vf_pf_rxq_stop(struct qed_hwfn *p_hwfn,
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
 	resp = &p_iov->pf2vf_reply->default_resp;
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -867,7 +864,7 @@ qed_vf_pf_txq_start(struct qed_hwfn *p_hwfn,
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
 	resp = &p_iov->pf2vf_reply->queue_start;
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -918,7 +915,7 @@ int qed_vf_pf_txq_stop(struct qed_hwfn *p_hwfn, struct qed_queue_cid *p_cid)
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
 	resp = &p_iov->pf2vf_reply->default_resp;
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -968,7 +965,7 @@ int qed_vf_pf_vport_start(struct qed_hwfn *p_hwfn,
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
 	resp = &p_iov->pf2vf_reply->default_resp;
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -997,7 +994,7 @@ int qed_vf_pf_vport_stop(struct qed_hwfn *p_hwfn)
 	qed_add_tlv(p_hwfn, &p_iov->offset,
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -1075,12 +1072,10 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 	struct vfpf_vport_update_tlv *req;
 	struct pfvf_def_resp_tlv *resp;
 	u8 update_rx, update_tx;
-	u32 resp_size = 0;
 	u16 size, tlv;
 	int rc;
 
 	resp = &p_iov->pf2vf_reply->default_resp;
-	resp_size = sizeof(*resp);
 
 	update_rx = p_params->update_vport_active_rx_flg;
 	update_tx = p_params->update_vport_active_tx_flg;
@@ -1096,7 +1091,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 		p_act_tlv = qed_add_tlv(p_hwfn, &p_iov->offset,
 					CHANNEL_TLV_VPORT_UPDATE_ACTIVATE,
 					size);
-		resp_size += sizeof(struct pfvf_def_resp_tlv);
 
 		if (update_rx) {
 			p_act_tlv->update_rx = update_rx;
@@ -1116,7 +1110,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 		tlv = CHANNEL_TLV_VPORT_UPDATE_TX_SWITCH;
 		p_tx_switch_tlv = qed_add_tlv(p_hwfn, &p_iov->offset,
 					      tlv, size);
-		resp_size += sizeof(struct pfvf_def_resp_tlv);
 
 		p_tx_switch_tlv->tx_switching = p_params->tx_switching_flg;
 	}
@@ -1127,7 +1120,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 		size = sizeof(struct vfpf_vport_update_mcast_bin_tlv);
 		p_mcast_tlv = qed_add_tlv(p_hwfn, &p_iov->offset,
 					  CHANNEL_TLV_VPORT_UPDATE_MCAST, size);
-		resp_size += sizeof(struct pfvf_def_resp_tlv);
 
 		memcpy(p_mcast_tlv->bins, p_params->bins,
 		       sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS);
@@ -1142,7 +1134,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 		tlv = CHANNEL_TLV_VPORT_UPDATE_ACCEPT_PARAM;
 		size = sizeof(struct vfpf_vport_update_accept_param_tlv);
 		p_accept_tlv = qed_add_tlv(p_hwfn, &p_iov->offset, tlv, size);
-		resp_size += sizeof(struct pfvf_def_resp_tlv);
 
 		if (update_rx) {
 			p_accept_tlv->update_rx_mode = update_rx;
@@ -1166,7 +1157,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 		p_rss_tlv = qed_add_tlv(p_hwfn,
 					&p_iov->offset,
 					CHANNEL_TLV_VPORT_UPDATE_RSS, size);
-		resp_size += sizeof(struct pfvf_def_resp_tlv);
 
 		if (rss_params->update_rss_config)
 			p_rss_tlv->update_rss_flags |=
@@ -1203,7 +1193,6 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 		tlv = CHANNEL_TLV_VPORT_UPDATE_ACCEPT_ANY_VLAN;
 		p_any_vlan_tlv = qed_add_tlv(p_hwfn, &p_iov->offset, tlv, size);
 
-		resp_size += sizeof(struct pfvf_def_resp_tlv);
 		p_any_vlan_tlv->accept_any_vlan = p_params->accept_any_vlan;
 		p_any_vlan_tlv->update_accept_any_vlan_flg =
 		    p_params->update_accept_any_vlan_flg;
@@ -1213,7 +1202,7 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 	qed_add_tlv(p_hwfn, &p_iov->offset,
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, resp_size);
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -1245,7 +1234,7 @@ int qed_vf_pf_reset(struct qed_hwfn *p_hwfn)
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
 	resp = &p_iov->pf2vf_reply->default_resp;
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -1303,7 +1292,7 @@ int qed_vf_pf_filter_ucast(struct qed_hwfn *p_hwfn,
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
 	resp = &p_iov->pf2vf_reply->default_resp;
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -1332,7 +1321,7 @@ int qed_vf_pf_int_cleanup(struct qed_hwfn *p_hwfn)
 	qed_add_tlv(p_hwfn, &p_iov->offset,
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -1364,7 +1353,7 @@ int qed_vf_pf_get_coalesce(struct qed_hwfn *p_hwfn,
 		    sizeof(struct channel_list_end_tlv));
 	resp = &p_iov->pf2vf_reply->read_coal_resp;
 
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
@@ -1402,7 +1391,7 @@ qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn,
 		    sizeof(struct channel_list_end_tlv));
 
 	p_resp = &p_iov->pf2vf_reply->default_resp;
-	rc = qed_send_msg2pf(p_hwfn, &p_resp->hdr.status, sizeof(*p_resp));
+	rc = qed_send_msg2pf(p_hwfn, &p_resp->hdr.status);
 	qed_vf_pf_req_end(p_hwfn, rc);
 	return rc;
 }
@@ -1433,7 +1422,7 @@ qed_vf_pf_set_coalesce(struct qed_hwfn *p_hwfn,
 		    sizeof(struct channel_list_end_tlv));
 
 	resp = &p_iov->pf2vf_reply->default_resp;
-	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status);
 	if (rc)
 		goto exit;
 
-- 
GitLab


From 3bfdcc324a04ba27f3fd2a6633c53de1758e7b6a Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 14 Aug 2023 21:58:21 +0800
Subject: [PATCH 1242/1806] net: e1000e: Remove unused declarations

Commit bdfe2da6aefd ("e1000e: cosmetic move of function prototypes to the new mac.h")
declared but never implemented them.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20230814135821.4808-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/e1000e/mac.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/mac.h b/drivers/net/ethernet/intel/e1000e/mac.h
index 6ab2611198015..563176fd436e5 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.h
+++ b/drivers/net/ethernet/intel/e1000e/mac.h
@@ -29,8 +29,6 @@ s32 e1000e_set_fc_watermarks(struct e1000_hw *hw);
 s32 e1000e_setup_fiber_serdes_link(struct e1000_hw *hw);
 s32 e1000e_setup_led_generic(struct e1000_hw *hw);
 s32 e1000e_setup_link_generic(struct e1000_hw *hw);
-s32 e1000e_validate_mdi_setting_generic(struct e1000_hw *hw);
-s32 e1000e_validate_mdi_setting_crossover_generic(struct e1000_hw *hw);
 
 void e1000e_clear_hw_cntrs_base(struct e1000_hw *hw);
 void e1000_clear_vfta_generic(struct e1000_hw *hw);
-- 
GitLab


From cf74eb5a5bc867258e7d0b0d1c3c4a60e1e3de2f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 08:35:21 -0700
Subject: [PATCH 1243/1806] eth: r8152: try to use a normal budget

Mario reports that loading r8152 on his system leads to a:

  netif_napi_add_weight() called with weight 256

warning getting printed. We don't have any solid data
on why such high budget was chosen, and it may cause
stalls in processing other softirqs and rt threads.
So try to switch back to the default (64) weight.

If this slows down someone's system we should investigate
which part of stopping starting the NAPI poll in this
driver are expensive.

Reported-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/all/0bfd445a-81f7-f702-08b0-bd5a72095e49@amd.com/
Acked-by: Hayes Wang <hayeswang@realtek.com>
Link: https://lore.kernel.org/r/20230814153521.2697982-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index db9897e825b45..bb234cf0cea0f 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -9760,8 +9760,7 @@ static int rtl8152_probe(struct usb_interface *intf,
 
 	usb_set_intfdata(intf, tp);
 
-	netif_napi_add_weight(netdev, &tp->napi, r8152_poll,
-			      tp->support_2500full ? 256 : 64);
+	netif_napi_add(netdev, &tp->napi, r8152_poll);
 
 	ret = register_netdev(netdev);
 	if (ret != 0) {
-- 
GitLab


From 956db0a13b47df7f3d6d624394e602e8bf9b057e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 13:56:25 -0700
Subject: [PATCH 1244/1806] net: warn about attempts to register negative
 ifindex

Since the xarray changes we mix returning valid ifindex and negative
errno in a single int returned from dev_index_reserve(). This depends
on the fact that ifindexes can't be negative. Otherwise we may insert
into the xarray and return a very large negative value. This in turn
may break ERR_PTR().

OvS is susceptible to this problem and lacking validation (fix posted
separately for net).

Reject negative ifindex explicitly. Add a warning because the input
validation is better handled by the caller.

Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230814205627.2914583-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 636b41f0b32d6..17e6281e408c7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9589,6 +9589,11 @@ static int dev_index_reserve(struct net *net, u32 ifindex)
 {
 	int err;
 
+	if (ifindex > INT_MAX) {
+		DEBUG_NET_WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
 	if (!ifindex)
 		err = xa_alloc_cyclic(&net->dev_by_index, &ifindex, NULL,
 				      xa_limit_31b, &net->ifindex, GFP_KERNEL);
-- 
GitLab


From ded67d90815a412f327051d27eb6c6de57cd2c03 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 13:56:26 -0700
Subject: [PATCH 1245/1806] netlink: specs: add ovs_vport new command

Add NEW to the spec, it was useful testing the fix for OvS
input validation.

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20230814205627.2914583-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ovs_vport.yaml | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/netlink/specs/ovs_vport.yaml b/Documentation/netlink/specs/ovs_vport.yaml
index 17336455bec14..ef298b0014453 100644
--- a/Documentation/netlink/specs/ovs_vport.yaml
+++ b/Documentation/netlink/specs/ovs_vport.yaml
@@ -81,6 +81,10 @@ attribute-sets:
     name-prefix: ovs-vport-attr-
     enum-name: ovs-vport-attr
     attributes:
+      -
+        name: unspec
+        type: unused
+        value: 0
       -
         name: port-no
         type: u32
@@ -120,6 +124,20 @@ attribute-sets:
 operations:
   name-prefix: ovs-vport-cmd-
   list:
+    -
+      name: new
+      doc: Create a new OVS vport
+      attribute-set: vport
+      fixed-header: ovs-header
+      do:
+        request:
+          attributes:
+            - name
+            - type
+            - upcall-pid
+            - dp-ifindex
+            - ifindex
+            - options
     -
       name: get
       doc: Get / dump OVS vport configuration and state
-- 
GitLab


From 7582113c6917c280c90352d1935cfa451e74376a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Aug 2023 13:56:27 -0700
Subject: [PATCH 1246/1806] tools: ynl: add more info to KeyErrors on missing
 attrs

When developing specs its useful to know which attr space
YNL was trying to find an attribute in on key error.

Instead of printing:
 KeyError: 0
add info about the space:
 Exception: Space 'vport' has no attribute with value '0'

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20230814205627.2914583-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/ynl.py | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 3ca28d4bcb188..6951bcc7efdcb 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -395,7 +395,10 @@ class YnlFamily(SpecFamily):
                              self.family.genl_family['mcast'][mcast_name])
 
     def _add_attr(self, space, name, value):
-        attr = self.attr_sets[space][name]
+        try:
+            attr = self.attr_sets[space][name]
+        except KeyError:
+            raise Exception(f"Space '{space}' has no attribute '{name}'")
         nl_type = attr.value
         if attr["type"] == 'nest':
             nl_type |= Netlink.NLA_F_NESTED
@@ -450,7 +453,10 @@ class YnlFamily(SpecFamily):
         attr_space = self.attr_sets[space]
         rsp = dict()
         for attr in attrs:
-            attr_spec = attr_space.attrs_by_val[attr.type]
+            try:
+                attr_spec = attr_space.attrs_by_val[attr.type]
+            except KeyError:
+                raise Exception(f"Space '{space}' has no attribute with value '{attr.type}'")
             if attr_spec["type"] == 'nest':
                 subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes'])
                 decoded = subdict
@@ -479,7 +485,10 @@ class YnlFamily(SpecFamily):
 
     def _decode_extack_path(self, attrs, attr_set, offset, target):
         for attr in attrs:
-            attr_spec = attr_set.attrs_by_val[attr.type]
+            try:
+                attr_spec = attr_set.attrs_by_val[attr.type]
+            except KeyError:
+                raise Exception(f"Space '{attr_set.name}' has no attribute with value '{attr.type}'")
             if offset > target:
                 break
             if offset == target:
-- 
GitLab


From e56e220d73caf06e9e6f5553f414376b4af51c8a Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Sat, 12 Aug 2023 16:40:36 +0800
Subject: [PATCH 1247/1806] selftests: bonding: remove redundant delete action
 of device link1_1

When run command "ip netns delete client", device link1_1 has been
deleted. So, it is no need to delete link1_1 again. Remove it.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/bonding/bond-arp-interval-causes-panic.sh        | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
index 71c00bfafbc99..7b2d421f09cf2 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
@@ -11,7 +11,6 @@ finish()
 {
 	ip netns delete server || true
 	ip netns delete client || true
-	ip link del link1_1 || true
 }
 
 trap finish EXIT
-- 
GitLab


From f601899e432155c1c7d372a7924f1a2301ca64b4 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 15 Aug 2023 13:19:54 +0800
Subject: [PATCH 1248/1806] net: fec: add XDP_TX feature support

The XDP_TX feature is not supported before, and all the frames
which are deemed to do XDP_TX action actually do the XDP_DROP
action. So this patch adds the XDP_TX support to FEC driver.

I tested the performance of XDP_TX in XDP_DRV mode and XDP_SKB
mode respectively on i.MX8MP-EVK platform, and as suggested by
Jesper, I also tested the performance of XDP_REDIRECT on the
same platform. And the test steps and results are as follows.

XDP_TX test:
Step 1: One board is used as generator and connects to switch,and
the FEC port of DUT also connects to the switch. Both boards with
flow control off. Then the generator runs the
pktgen_sample03_burst_single_flow.sh script to generate and send
burst traffic to DUT. Note that the size of packet was set to 64
bytes and the procotol of packet was UDP in my test scenario. In
addition, the SMAC of the packet need to be different from the MAC
of the generator, because the xdp2 program will swap the DMAC and
SMAC of the packet and send it back to the generator. If the SMAC
of the generated packet is the MAC of the generator, the generator
will receive the returned traffic which increase the CPU loading
and significantly degrade the transmit speed of the generator, and
finally it affects the test of XDP_TX performance.

Step 2: The DUT runs the xdp2 program to transmit received UDP
packets back out on the same port where they were received.

root@imx8mpevk:~# ./xdp2 eth0
proto 17:     353918 pkt/s
proto 17:     352923 pkt/s
proto 17:     353900 pkt/s
proto 17:     352672 pkt/s
proto 17:     353912 pkt/s
proto 17:     354219 pkt/s

root@imx8mpevk:~# ./xdp2 -S eth0
proto 17:     160604 pkt/s
proto 17:     160708 pkt/s
proto 17:     160564 pkt/s
proto 17:     160684 pkt/s
proto 17:     160640 pkt/s
proto 17:     160720 pkt/s

The above results show that the XDP_TX performance of XDP_DRV mode
is much better than XDP_SKB mode, more than twice that of XDP_SKB
mode, which is in line with our expectation.

XDP_REDIRECT test:
Step1: Both the generator and the FEC port of the DUT connet to the
switch port. All the ports with flow control off, then the generator
runs the pktgen script to generate and send burst traffic to DUT.
Note that the size of packet was set to 64 bytes and the procotol of
packet was UDP in my test scenario.

Step2: The DUT runs the xdp_redirect program to redirect the traffic
from the FEC port to the FEC port itself.

root@imx8mpevk:~# ./xdp_redirect eth0 eth0
Redirecting from eth0 (ifindex 2; driver fec) to eth0
(ifindex 2; driver fec)
Summary        232,302 rx/s        0 err,drop/s      232,344 xmit/s
Summary        234,579 rx/s        0 err,drop/s      234,577 xmit/s
Summary        235,548 rx/s        0 err,drop/s      235,549 xmit/s
Summary        234,704 rx/s        0 err,drop/s      234,703 xmit/s
Summary        235,504 rx/s        0 err,drop/s      235,504 xmit/s
Summary        235,223 rx/s        0 err,drop/s      235,224 xmit/s
Summary        234,509 rx/s        0 err,drop/s      234,507 xmit/s
Summary        235,481 rx/s        0 err,drop/s      235,482 xmit/s
Summary        234,684 rx/s        0 err,drop/s      234,683 xmit/s
Summary        235,520 rx/s        0 err,drop/s      235,520 xmit/s
Summary        235,461 rx/s        0 err,drop/s      235,461 xmit/s
Summary        234,627 rx/s        0 err,drop/s      234,627 xmit/s
Summary        235,611 rx/s        0 err,drop/s      235,611 xmit/s
  Packets received    : 3,053,753
  Average packets/s   : 234,904
  Packets transmitted : 3,053,792
  Average transmit/s  : 234,907

Compared the performance of XDP_TX with XDP_REDIRECT, XDP_TX is also
much better than XDP_REDIRECT. It's also in line with our expectation.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Suggested-by: Jesper Dangaard Brouer <hawk@kernel.org>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec.h      |   1 +
 drivers/net/ethernet/freescale/fec_main.c | 107 +++++++++++++++++-----
 2 files changed, 87 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 5ca9906d7c6a3..7bb02a9da2a6d 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -548,6 +548,7 @@ enum {
 enum fec_txbuf_type {
 	FEC_TXBUF_T_SKB,
 	FEC_TXBUF_T_XDP_NDO,
+	FEC_TXBUF_T_XDP_TX,
 };
 
 struct fec_tx_buffer {
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 3bd0bf03aedbf..9bba3d7c949c1 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -69,6 +69,7 @@
 #include <soc/imx/cpuidle.h>
 #include <linux/filter.h>
 #include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 
 #include <asm/cacheflush.h>
 
@@ -76,6 +77,9 @@
 
 static void set_multicast_list(struct net_device *ndev);
 static void fec_enet_itr_coal_set(struct net_device *ndev);
+static int fec_enet_xdp_tx_xmit(struct fec_enet_private *fep,
+				int cpu, struct xdp_buff *xdp,
+				u32 dma_sync_len);
 
 #define DRIVER_NAME	"fec"
 
@@ -961,7 +965,8 @@ static void fec_enet_bd_init(struct net_device *dev)
 					txq->tx_buf[i].skb = NULL;
 				}
 			} else {
-				if (bdp->cbd_bufaddr)
+				if (bdp->cbd_bufaddr &&
+				    txq->tx_buf[i].type == FEC_TXBUF_T_XDP_NDO)
 					dma_unmap_single(&fep->pdev->dev,
 							 fec32_to_cpu(bdp->cbd_bufaddr),
 							 fec16_to_cpu(bdp->cbd_datlen),
@@ -1424,13 +1429,14 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 				break;
 
 			xdpf = txq->tx_buf[index].xdp;
-			if (bdp->cbd_bufaddr)
+			if (bdp->cbd_bufaddr &&
+			    txq->tx_buf[index].type == FEC_TXBUF_T_XDP_NDO)
 				dma_unmap_single(&fep->pdev->dev,
 						 fec32_to_cpu(bdp->cbd_bufaddr),
 						 fec16_to_cpu(bdp->cbd_datlen),
 						 DMA_TO_DEVICE);
 			bdp->cbd_bufaddr = cpu_to_fec32(0);
-			if (!xdpf) {
+			if (unlikely(!xdpf)) {
 				txq->tx_buf[index].type = FEC_TXBUF_T_SKB;
 				goto tx_buf_done;
 			}
@@ -1483,7 +1489,16 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 			/* Free the sk buffer associated with this last transmit */
 			dev_kfree_skb_any(skb);
 		} else {
-			xdp_return_frame(xdpf);
+			if (txq->tx_buf[index].type == FEC_TXBUF_T_XDP_NDO) {
+				xdp_return_frame_rx_napi(xdpf);
+			} else { /* recycle pages of XDP_TX frames */
+				struct page *page = virt_to_head_page(xdpf->data);
+
+				/* The dma_sync_size = 0 as XDP_TX has already
+				 * synced DMA for_device.
+				 */
+				page_pool_put_page(page->pp, page, 0, true);
+			}
 
 			txq->tx_buf[index].xdp = NULL;
 			/* restore default tx buffer type: FEC_TXBUF_T_SKB */
@@ -1542,7 +1557,7 @@ static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq,
 
 static u32
 fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog,
-		 struct xdp_buff *xdp, struct fec_enet_priv_rx_q *rxq, int index)
+		 struct xdp_buff *xdp, struct fec_enet_priv_rx_q *rxq, int cpu)
 {
 	unsigned int sync, len = xdp->data_end - xdp->data;
 	u32 ret = FEC_ENET_XDP_PASS;
@@ -1552,8 +1567,10 @@ fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog,
 
 	act = bpf_prog_run_xdp(prog, xdp);
 
-	/* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */
-	sync = xdp->data_end - xdp->data_hard_start - FEC_ENET_XDP_HEADROOM;
+	/* Due xdp_adjust_tail and xdp_adjust_head: DMA sync for_device cover
+	 * max len CPU touch
+	 */
+	sync = xdp->data_end - xdp->data;
 	sync = max(sync, len);
 
 	switch (act) {
@@ -1574,11 +1591,19 @@ fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog,
 		}
 		break;
 
-	default:
-		bpf_warn_invalid_xdp_action(fep->netdev, prog, act);
-		fallthrough;
-
 	case XDP_TX:
+		err = fec_enet_xdp_tx_xmit(fep, cpu, xdp, sync);
+		if (unlikely(err)) {
+			ret = FEC_ENET_XDP_CONSUMED;
+			page = virt_to_head_page(xdp->data);
+			page_pool_put_page(rxq->page_pool, page, sync, true);
+			trace_xdp_exception(fep->netdev, prog, act);
+		} else {
+			ret = FEC_ENET_XDP_TX;
+		}
+		break;
+
+	default:
 		bpf_warn_invalid_xdp_action(fep->netdev, prog, act);
 		fallthrough;
 
@@ -1620,6 +1645,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	struct bpf_prog *xdp_prog = READ_ONCE(fep->xdp_prog);
 	u32 ret, xdp_result = FEC_ENET_XDP_PASS;
 	u32 data_start = FEC_ENET_XDP_HEADROOM;
+	int cpu = smp_processor_id();
 	struct xdp_buff xdp;
 	struct page *page;
 	u32 sub_len = 4;
@@ -1698,7 +1724,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 			/* subtract 16bit shift and FCS */
 			xdp_prepare_buff(&xdp, page_address(page),
 					 data_start, pkt_len - sub_len, false);
-			ret = fec_enet_run_xdp(fep, xdp_prog, &xdp, rxq, index);
+			ret = fec_enet_run_xdp(fep, xdp_prog, &xdp, rxq, cpu);
 			xdp_result |= ret;
 			if (ret != FEC_ENET_XDP_PASS)
 				goto rx_processing_done;
@@ -3767,7 +3793,8 @@ fec_enet_xdp_get_tx_queue(struct fec_enet_private *fep, int index)
 
 static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 				   struct fec_enet_priv_tx_q *txq,
-				   struct xdp_frame *frame)
+				   struct xdp_frame *frame,
+				   u32 dma_sync_len, bool ndo_xmit)
 {
 	unsigned int index, status, estatus;
 	struct bufdesc *bdp;
@@ -3787,10 +3814,24 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 
 	index = fec_enet_get_bd_index(bdp, &txq->bd);
 
-	dma_addr = dma_map_single(&fep->pdev->dev, frame->data,
-				  frame->len, DMA_TO_DEVICE);
-	if (dma_mapping_error(&fep->pdev->dev, dma_addr))
-		return -ENOMEM;
+	if (ndo_xmit) {
+		dma_addr = dma_map_single(&fep->pdev->dev, frame->data,
+					  frame->len, DMA_TO_DEVICE);
+		if (dma_mapping_error(&fep->pdev->dev, dma_addr))
+			return -ENOMEM;
+
+		txq->tx_buf[index].type = FEC_TXBUF_T_XDP_NDO;
+	} else {
+		struct page *page = virt_to_page(frame->data);
+
+		dma_addr = page_pool_get_dma_addr(page) + sizeof(*frame) +
+			   frame->headroom;
+		dma_sync_single_for_device(&fep->pdev->dev, dma_addr,
+					   dma_sync_len, DMA_BIDIRECTIONAL);
+		txq->tx_buf[index].type = FEC_TXBUF_T_XDP_TX;
+	}
+
+	txq->tx_buf[index].xdp = frame;
 
 	status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
 	if (fep->bufdesc_ex)
@@ -3809,9 +3850,6 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 		ebdp->cbd_esc = cpu_to_fec32(estatus);
 	}
 
-	txq->tx_buf[index].type = FEC_TXBUF_T_XDP_NDO;
-	txq->tx_buf[index].xdp = frame;
-
 	/* Make sure the updates to rest of the descriptor are performed before
 	 * transferring ownership.
 	 */
@@ -3837,6 +3875,33 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 	return 0;
 }
 
+static int fec_enet_xdp_tx_xmit(struct fec_enet_private *fep,
+				int cpu, struct xdp_buff *xdp,
+				u32 dma_sync_len)
+{
+	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
+	struct fec_enet_priv_tx_q *txq;
+	struct netdev_queue *nq;
+	int queue, ret;
+
+	if (unlikely(!xdpf))
+		return -EFAULT;
+
+	queue = fec_enet_xdp_get_tx_queue(fep, cpu);
+	txq = fep->tx_queue[queue];
+	nq = netdev_get_tx_queue(fep->netdev, queue);
+
+	__netif_tx_lock(nq, cpu);
+
+	/* Avoid tx timeout as XDP shares the queue with kernel stack */
+	txq_trans_cond_update(nq);
+	ret = fec_enet_txq_xmit_frame(fep, txq, xdpf, dma_sync_len, false);
+
+	__netif_tx_unlock(nq);
+
+	return ret;
+}
+
 static int fec_enet_xdp_xmit(struct net_device *dev,
 			     int num_frames,
 			     struct xdp_frame **frames,
@@ -3859,7 +3924,7 @@ static int fec_enet_xdp_xmit(struct net_device *dev,
 	/* Avoid tx timeout as XDP shares the queue with kernel stack */
 	txq_trans_cond_update(nq);
 	for (i = 0; i < num_frames; i++) {
-		if (fec_enet_txq_xmit_frame(fep, txq, frames[i]) < 0)
+		if (fec_enet_txq_xmit_frame(fep, txq, frames[i], 0, true) < 0)
 			break;
 		sent_frames++;
 	}
-- 
GitLab


From af6f4791380c320802df2106e295efd29c5e8b16 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 15 Aug 2023 13:19:55 +0800
Subject: [PATCH 1249/1806] net: fec: improve XDP_TX performance

As suggested by Jesper and Alexander, we can avoid converting xdp_buff
to xdp_frame in case of XDP_TX to save a bunch of CPU cycles, so that
we can further improve the XDP_TX performance.

Before this patch on i.MX8MP-EVK board, the performance shows as follows.
root@imx8mpevk:~# ./xdp2 eth0
proto 17:     353918 pkt/s
proto 17:     352923 pkt/s
proto 17:     353900 pkt/s
proto 17:     352672 pkt/s
proto 17:     353912 pkt/s
proto 17:     354219 pkt/s

After applying this patch, the performance is improved.
root@imx8mpevk:~# ./xdp2 eth0
proto 17:     369261 pkt/s
proto 17:     369267 pkt/s
proto 17:     369206 pkt/s
proto 17:     369214 pkt/s
proto 17:     369126 pkt/s
proto 17:     369272 pkt/s

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Suggested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Suggested-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec.h      |   5 +-
 drivers/net/ethernet/freescale/fec_main.c | 140 ++++++++++++----------
 2 files changed, 75 insertions(+), 70 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 7bb02a9da2a6d..a8fbcada6b01f 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -552,10 +552,7 @@ enum fec_txbuf_type {
 };
 
 struct fec_tx_buffer {
-	union {
-		struct sk_buff *skb;
-		struct xdp_frame *xdp;
-	};
+	void *buf_p;
 	enum fec_txbuf_type type;
 };
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 9bba3d7c949c1..f77105f017c1e 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -400,7 +400,7 @@ static void fec_dump(struct net_device *ndev)
 			fec16_to_cpu(bdp->cbd_sc),
 			fec32_to_cpu(bdp->cbd_bufaddr),
 			fec16_to_cpu(bdp->cbd_datlen),
-			txq->tx_buf[index].skb);
+			txq->tx_buf[index].buf_p);
 		bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
 		index++;
 	} while (bdp != txq->bd.base);
@@ -657,7 +657,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 
 	index = fec_enet_get_bd_index(last_bdp, &txq->bd);
 	/* Save skb pointer */
-	txq->tx_buf[index].skb = skb;
+	txq->tx_buf[index].buf_p = skb;
 
 	/* Make sure the updates to rest of the descriptor are performed before
 	 * transferring ownership.
@@ -863,7 +863,7 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	}
 
 	/* Save skb pointer */
-	txq->tx_buf[index].skb = skb;
+	txq->tx_buf[index].buf_p = skb;
 
 	skb_tx_timestamp(skb);
 	txq->bd.cur = bdp;
@@ -960,27 +960,27 @@ static void fec_enet_bd_init(struct net_device *dev)
 							 fec32_to_cpu(bdp->cbd_bufaddr),
 							 fec16_to_cpu(bdp->cbd_datlen),
 							 DMA_TO_DEVICE);
-				if (txq->tx_buf[i].skb) {
-					dev_kfree_skb_any(txq->tx_buf[i].skb);
-					txq->tx_buf[i].skb = NULL;
-				}
-			} else {
-				if (bdp->cbd_bufaddr &&
-				    txq->tx_buf[i].type == FEC_TXBUF_T_XDP_NDO)
+				if (txq->tx_buf[i].buf_p)
+					dev_kfree_skb_any(txq->tx_buf[i].buf_p);
+			} else if (txq->tx_buf[i].type == FEC_TXBUF_T_XDP_NDO) {
+				if (bdp->cbd_bufaddr)
 					dma_unmap_single(&fep->pdev->dev,
 							 fec32_to_cpu(bdp->cbd_bufaddr),
 							 fec16_to_cpu(bdp->cbd_datlen),
 							 DMA_TO_DEVICE);
 
-				if (txq->tx_buf[i].xdp) {
-					xdp_return_frame(txq->tx_buf[i].xdp);
-					txq->tx_buf[i].xdp = NULL;
-				}
+				if (txq->tx_buf[i].buf_p)
+					xdp_return_frame(txq->tx_buf[i].buf_p);
+			} else {
+				struct page *page = txq->tx_buf[i].buf_p;
 
-				/* restore default tx buffer type: FEC_TXBUF_T_SKB */
-				txq->tx_buf[i].type = FEC_TXBUF_T_SKB;
+				if (page)
+					page_pool_put_page(page->pp, page, 0, false);
 			}
 
+			txq->tx_buf[i].buf_p = NULL;
+			/* restore default tx buffer type: FEC_TXBUF_T_SKB */
+			txq->tx_buf[i].type = FEC_TXBUF_T_SKB;
 			bdp->cbd_bufaddr = cpu_to_fec32(0);
 			bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
 		}
@@ -1387,6 +1387,8 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 	struct netdev_queue *nq;
 	int	index = 0;
 	int	entries_free;
+	struct page *page;
+	int frame_len;
 
 	fep = netdev_priv(ndev);
 
@@ -1408,8 +1410,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 		index = fec_enet_get_bd_index(bdp, &txq->bd);
 
 		if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) {
-			skb = txq->tx_buf[index].skb;
-			txq->tx_buf[index].skb = NULL;
+			skb = txq->tx_buf[index].buf_p;
 			if (bdp->cbd_bufaddr &&
 			    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
 				dma_unmap_single(&fep->pdev->dev,
@@ -1428,18 +1429,24 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 			if (unlikely(!budget))
 				break;
 
-			xdpf = txq->tx_buf[index].xdp;
-			if (bdp->cbd_bufaddr &&
-			    txq->tx_buf[index].type == FEC_TXBUF_T_XDP_NDO)
-				dma_unmap_single(&fep->pdev->dev,
-						 fec32_to_cpu(bdp->cbd_bufaddr),
-						 fec16_to_cpu(bdp->cbd_datlen),
-						 DMA_TO_DEVICE);
+			if (txq->tx_buf[index].type == FEC_TXBUF_T_XDP_NDO) {
+				xdpf = txq->tx_buf[index].buf_p;
+				if (bdp->cbd_bufaddr)
+					dma_unmap_single(&fep->pdev->dev,
+							 fec32_to_cpu(bdp->cbd_bufaddr),
+							 fec16_to_cpu(bdp->cbd_datlen),
+							 DMA_TO_DEVICE);
+			} else {
+				page = txq->tx_buf[index].buf_p;
+			}
+
 			bdp->cbd_bufaddr = cpu_to_fec32(0);
-			if (unlikely(!xdpf)) {
+			if (unlikely(!txq->tx_buf[index].buf_p)) {
 				txq->tx_buf[index].type = FEC_TXBUF_T_SKB;
 				goto tx_buf_done;
 			}
+
+			frame_len = fec16_to_cpu(bdp->cbd_datlen);
 		}
 
 		/* Check for errors. */
@@ -1463,7 +1470,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 			if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB)
 				ndev->stats.tx_bytes += skb->len;
 			else
-				ndev->stats.tx_bytes += xdpf->len;
+				ndev->stats.tx_bytes += frame_len;
 		}
 
 		/* Deferred means some collisions occurred during transmit,
@@ -1488,23 +1495,17 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 
 			/* Free the sk buffer associated with this last transmit */
 			dev_kfree_skb_any(skb);
-		} else {
-			if (txq->tx_buf[index].type == FEC_TXBUF_T_XDP_NDO) {
-				xdp_return_frame_rx_napi(xdpf);
-			} else { /* recycle pages of XDP_TX frames */
-				struct page *page = virt_to_head_page(xdpf->data);
-
-				/* The dma_sync_size = 0 as XDP_TX has already
-				 * synced DMA for_device.
-				 */
-				page_pool_put_page(page->pp, page, 0, true);
-			}
-
-			txq->tx_buf[index].xdp = NULL;
-			/* restore default tx buffer type: FEC_TXBUF_T_SKB */
-			txq->tx_buf[index].type = FEC_TXBUF_T_SKB;
+		} else if (txq->tx_buf[index].type == FEC_TXBUF_T_XDP_NDO) {
+			xdp_return_frame_rx_napi(xdpf);
+		} else { /* recycle pages of XDP_TX frames */
+			/* The dma_sync_size = 0 as XDP_TX has already synced DMA for_device */
+			page_pool_put_page(page->pp, page, 0, true);
 		}
 
+		txq->tx_buf[index].buf_p = NULL;
+		/* restore default tx buffer type: FEC_TXBUF_T_SKB */
+		txq->tx_buf[index].type = FEC_TXBUF_T_SKB;
+
 tx_buf_done:
 		/* Make sure the update to bdp and tx_buf are performed
 		 * before dirty_tx
@@ -3234,7 +3235,6 @@ static void fec_enet_free_buffers(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	unsigned int i;
-	struct sk_buff *skb;
 	struct fec_enet_priv_tx_q *txq;
 	struct fec_enet_priv_rx_q *rxq;
 	unsigned int q;
@@ -3259,18 +3259,23 @@ static void fec_enet_free_buffers(struct net_device *ndev)
 			kfree(txq->tx_bounce[i]);
 			txq->tx_bounce[i] = NULL;
 
+			if (!txq->tx_buf[i].buf_p) {
+				txq->tx_buf[i].type = FEC_TXBUF_T_SKB;
+				continue;
+			}
+
 			if (txq->tx_buf[i].type == FEC_TXBUF_T_SKB) {
-				skb = txq->tx_buf[i].skb;
-				txq->tx_buf[i].skb = NULL;
-				dev_kfree_skb(skb);
+				dev_kfree_skb(txq->tx_buf[i].buf_p);
+			} else if (txq->tx_buf[i].type == FEC_TXBUF_T_XDP_NDO) {
+				xdp_return_frame(txq->tx_buf[i].buf_p);
 			} else {
-				if (txq->tx_buf[i].xdp) {
-					xdp_return_frame(txq->tx_buf[i].xdp);
-					txq->tx_buf[i].xdp = NULL;
-				}
+				struct page *page = txq->tx_buf[i].buf_p;
 
-				txq->tx_buf[i].type = FEC_TXBUF_T_SKB;
+				page_pool_put_page(page->pp, page, 0, false);
 			}
+
+			txq->tx_buf[i].buf_p = NULL;
+			txq->tx_buf[i].type = FEC_TXBUF_T_SKB;
 		}
 	}
 }
@@ -3793,13 +3798,14 @@ fec_enet_xdp_get_tx_queue(struct fec_enet_private *fep, int index)
 
 static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 				   struct fec_enet_priv_tx_q *txq,
-				   struct xdp_frame *frame,
-				   u32 dma_sync_len, bool ndo_xmit)
+				   void *frame, u32 dma_sync_len,
+				   bool ndo_xmit)
 {
 	unsigned int index, status, estatus;
 	struct bufdesc *bdp;
 	dma_addr_t dma_addr;
 	int entries_free;
+	u16 frame_len;
 
 	entries_free = fec_enet_get_free_txdesc_num(txq);
 	if (entries_free < MAX_SKB_FRAGS + 1) {
@@ -3815,30 +3821,36 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 	index = fec_enet_get_bd_index(bdp, &txq->bd);
 
 	if (ndo_xmit) {
-		dma_addr = dma_map_single(&fep->pdev->dev, frame->data,
-					  frame->len, DMA_TO_DEVICE);
+		struct xdp_frame *xdpf = frame;
+
+		dma_addr = dma_map_single(&fep->pdev->dev, xdpf->data,
+					  xdpf->len, DMA_TO_DEVICE);
 		if (dma_mapping_error(&fep->pdev->dev, dma_addr))
 			return -ENOMEM;
 
+		frame_len = xdpf->len;
+		txq->tx_buf[index].buf_p = xdpf;
 		txq->tx_buf[index].type = FEC_TXBUF_T_XDP_NDO;
 	} else {
-		struct page *page = virt_to_page(frame->data);
+		struct xdp_buff *xdpb = frame;
+		struct page *page;
 
-		dma_addr = page_pool_get_dma_addr(page) + sizeof(*frame) +
-			   frame->headroom;
+		page = virt_to_page(xdpb->data);
+		dma_addr = page_pool_get_dma_addr(page) +
+			   (xdpb->data - xdpb->data_hard_start);
 		dma_sync_single_for_device(&fep->pdev->dev, dma_addr,
 					   dma_sync_len, DMA_BIDIRECTIONAL);
+		frame_len = xdpb->data_end - xdpb->data;
+		txq->tx_buf[index].buf_p = page;
 		txq->tx_buf[index].type = FEC_TXBUF_T_XDP_TX;
 	}
 
-	txq->tx_buf[index].xdp = frame;
-
 	status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
 	if (fep->bufdesc_ex)
 		estatus = BD_ENET_TX_INT;
 
 	bdp->cbd_bufaddr = cpu_to_fec32(dma_addr);
-	bdp->cbd_datlen = cpu_to_fec16(frame->len);
+	bdp->cbd_datlen = cpu_to_fec16(frame_len);
 
 	if (fep->bufdesc_ex) {
 		struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
@@ -3879,14 +3891,10 @@ static int fec_enet_xdp_tx_xmit(struct fec_enet_private *fep,
 				int cpu, struct xdp_buff *xdp,
 				u32 dma_sync_len)
 {
-	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 	struct fec_enet_priv_tx_q *txq;
 	struct netdev_queue *nq;
 	int queue, ret;
 
-	if (unlikely(!xdpf))
-		return -EFAULT;
-
 	queue = fec_enet_xdp_get_tx_queue(fep, cpu);
 	txq = fep->tx_queue[queue];
 	nq = netdev_get_tx_queue(fep->netdev, queue);
@@ -3895,7 +3903,7 @@ static int fec_enet_xdp_tx_xmit(struct fec_enet_private *fep,
 
 	/* Avoid tx timeout as XDP shares the queue with kernel stack */
 	txq_trans_cond_update(nq);
-	ret = fec_enet_txq_xmit_frame(fep, txq, xdpf, dma_sync_len, false);
+	ret = fec_enet_txq_xmit_frame(fep, txq, xdp, dma_sync_len, false);
 
 	__netif_tx_unlock(nq);
 
-- 
GitLab


From 939ccd107ffcade20c9c7055a2e7ae0fd724fb72 Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Tue, 15 Aug 2023 14:06:38 +0800
Subject: [PATCH 1250/1806] net: hns3: move dump regs function to a separate
 file

The dump register function is being refactored.
The first step in refactoring is put the dump regs function
into a separate file.

Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/Makefile  |   4 +-
 .../hisilicon/hns3/hns3pf/hclge_debugfs.c     |   1 +
 .../hisilicon/hns3/hns3pf/hclge_main.c        | 558 +----------------
 .../hisilicon/hns3/hns3pf/hclge_main.h        |   2 -
 .../hisilicon/hns3/hns3pf/hclge_regs.c        | 567 ++++++++++++++++++
 .../hisilicon/hns3/hns3pf/hclge_regs.h        |  17 +
 .../hisilicon/hns3/hns3vf/hclgevf_main.c      | 121 +---
 .../hisilicon/hns3/hns3vf/hclgevf_main.h      |   1 +
 .../hisilicon/hns3/hns3vf/hclgevf_regs.c      | 127 ++++
 .../hisilicon/hns3/hns3vf/hclgevf_regs.h      |  13 +
 10 files changed, 731 insertions(+), 680 deletions(-)
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.h
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.h

diff --git a/drivers/net/ethernet/hisilicon/hns3/Makefile b/drivers/net/ethernet/hisilicon/hns3/Makefile
index 6efea46628587..e214bfaece1f3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/Makefile
@@ -17,11 +17,11 @@ hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o
 
 obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o
 
-hclgevf-objs = hns3vf/hclgevf_main.o hns3vf/hclgevf_mbx.o  hns3vf/hclgevf_devlink.o \
+hclgevf-objs = hns3vf/hclgevf_main.o hns3vf/hclgevf_mbx.o  hns3vf/hclgevf_devlink.o hns3vf/hclgevf_regs.o \
 		hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o
 
 obj-$(CONFIG_HNS3_HCLGE) += hclge.o
-hclge-objs = hns3pf/hclge_main.o hns3pf/hclge_mdio.o hns3pf/hclge_tm.o \
+hclge-objs = hns3pf/hclge_main.o hns3pf/hclge_mdio.o hns3pf/hclge_tm.o hns3pf/hclge_regs.o \
 		hns3pf/hclge_mbx.o hns3pf/hclge_err.o  hns3pf/hclge_debugfs.o hns3pf/hclge_ptp.o hns3pf/hclge_devlink.o \
 		hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 0fb2eaee3e8a0..f01a7a9ee02ca 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -7,6 +7,7 @@
 #include "hclge_debugfs.h"
 #include "hclge_err.h"
 #include "hclge_main.h"
+#include "hclge_regs.h"
 #include "hclge_tm.h"
 #include "hnae3.h"
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 437b510f2b809..36e8daf498117 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -20,6 +20,7 @@
 #include "hclge_main.h"
 #include "hclge_mbx.h"
 #include "hclge_mdio.h"
+#include "hclge_regs.h"
 #include "hclge_tm.h"
 #include "hclge_err.h"
 #include "hnae3.h"
@@ -40,20 +41,6 @@
 #define HCLGE_PF_RESET_SYNC_TIME	20
 #define HCLGE_PF_RESET_SYNC_CNT		1500
 
-/* Get DFX BD number offset */
-#define HCLGE_DFX_BIOS_BD_OFFSET        1
-#define HCLGE_DFX_SSU_0_BD_OFFSET       2
-#define HCLGE_DFX_SSU_1_BD_OFFSET       3
-#define HCLGE_DFX_IGU_BD_OFFSET         4
-#define HCLGE_DFX_RPU_0_BD_OFFSET       5
-#define HCLGE_DFX_RPU_1_BD_OFFSET       6
-#define HCLGE_DFX_NCSI_BD_OFFSET        7
-#define HCLGE_DFX_RTC_BD_OFFSET         8
-#define HCLGE_DFX_PPP_BD_OFFSET         9
-#define HCLGE_DFX_RCB_BD_OFFSET         10
-#define HCLGE_DFX_TQP_BD_OFFSET         11
-#define HCLGE_DFX_SSU_2_BD_OFFSET       12
-
 #define HCLGE_LINK_STATUS_MS	10
 
 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps);
@@ -94,62 +81,6 @@ static const struct pci_device_id ae_algo_pci_tbl[] = {
 
 MODULE_DEVICE_TABLE(pci, ae_algo_pci_tbl);
 
-static const u32 cmdq_reg_addr_list[] = {HCLGE_COMM_NIC_CSQ_BASEADDR_L_REG,
-					 HCLGE_COMM_NIC_CSQ_BASEADDR_H_REG,
-					 HCLGE_COMM_NIC_CSQ_DEPTH_REG,
-					 HCLGE_COMM_NIC_CSQ_TAIL_REG,
-					 HCLGE_COMM_NIC_CSQ_HEAD_REG,
-					 HCLGE_COMM_NIC_CRQ_BASEADDR_L_REG,
-					 HCLGE_COMM_NIC_CRQ_BASEADDR_H_REG,
-					 HCLGE_COMM_NIC_CRQ_DEPTH_REG,
-					 HCLGE_COMM_NIC_CRQ_TAIL_REG,
-					 HCLGE_COMM_NIC_CRQ_HEAD_REG,
-					 HCLGE_COMM_VECTOR0_CMDQ_SRC_REG,
-					 HCLGE_COMM_CMDQ_INTR_STS_REG,
-					 HCLGE_COMM_CMDQ_INTR_EN_REG,
-					 HCLGE_COMM_CMDQ_INTR_GEN_REG};
-
-static const u32 common_reg_addr_list[] = {HCLGE_MISC_VECTOR_REG_BASE,
-					   HCLGE_PF_OTHER_INT_REG,
-					   HCLGE_MISC_RESET_STS_REG,
-					   HCLGE_MISC_VECTOR_INT_STS,
-					   HCLGE_GLOBAL_RESET_REG,
-					   HCLGE_FUN_RST_ING,
-					   HCLGE_GRO_EN_REG};
-
-static const u32 ring_reg_addr_list[] = {HCLGE_RING_RX_ADDR_L_REG,
-					 HCLGE_RING_RX_ADDR_H_REG,
-					 HCLGE_RING_RX_BD_NUM_REG,
-					 HCLGE_RING_RX_BD_LENGTH_REG,
-					 HCLGE_RING_RX_MERGE_EN_REG,
-					 HCLGE_RING_RX_TAIL_REG,
-					 HCLGE_RING_RX_HEAD_REG,
-					 HCLGE_RING_RX_FBD_NUM_REG,
-					 HCLGE_RING_RX_OFFSET_REG,
-					 HCLGE_RING_RX_FBD_OFFSET_REG,
-					 HCLGE_RING_RX_STASH_REG,
-					 HCLGE_RING_RX_BD_ERR_REG,
-					 HCLGE_RING_TX_ADDR_L_REG,
-					 HCLGE_RING_TX_ADDR_H_REG,
-					 HCLGE_RING_TX_BD_NUM_REG,
-					 HCLGE_RING_TX_PRIORITY_REG,
-					 HCLGE_RING_TX_TC_REG,
-					 HCLGE_RING_TX_MERGE_EN_REG,
-					 HCLGE_RING_TX_TAIL_REG,
-					 HCLGE_RING_TX_HEAD_REG,
-					 HCLGE_RING_TX_FBD_NUM_REG,
-					 HCLGE_RING_TX_OFFSET_REG,
-					 HCLGE_RING_TX_EBD_NUM_REG,
-					 HCLGE_RING_TX_EBD_OFFSET_REG,
-					 HCLGE_RING_TX_BD_ERR_REG,
-					 HCLGE_RING_EN_REG};
-
-static const u32 tqp_intr_reg_addr_list[] = {HCLGE_TQP_INTR_CTRL_REG,
-					     HCLGE_TQP_INTR_GL0_REG,
-					     HCLGE_TQP_INTR_GL1_REG,
-					     HCLGE_TQP_INTR_GL2_REG,
-					     HCLGE_TQP_INTR_RL_REG};
-
 static const char hns3_nic_test_strs[][ETH_GSTRING_LEN] = {
 	"External Loopback test",
 	"App      Loopback test",
@@ -375,36 +306,6 @@ static const struct hclge_mac_mgr_tbl_entry_cmd hclge_mgr_table[] = {
 	},
 };
 
-static const u32 hclge_dfx_bd_offset_list[] = {
-	HCLGE_DFX_BIOS_BD_OFFSET,
-	HCLGE_DFX_SSU_0_BD_OFFSET,
-	HCLGE_DFX_SSU_1_BD_OFFSET,
-	HCLGE_DFX_IGU_BD_OFFSET,
-	HCLGE_DFX_RPU_0_BD_OFFSET,
-	HCLGE_DFX_RPU_1_BD_OFFSET,
-	HCLGE_DFX_NCSI_BD_OFFSET,
-	HCLGE_DFX_RTC_BD_OFFSET,
-	HCLGE_DFX_PPP_BD_OFFSET,
-	HCLGE_DFX_RCB_BD_OFFSET,
-	HCLGE_DFX_TQP_BD_OFFSET,
-	HCLGE_DFX_SSU_2_BD_OFFSET
-};
-
-static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = {
-	HCLGE_OPC_DFX_BIOS_COMMON_REG,
-	HCLGE_OPC_DFX_SSU_REG_0,
-	HCLGE_OPC_DFX_SSU_REG_1,
-	HCLGE_OPC_DFX_IGU_EGU_REG,
-	HCLGE_OPC_DFX_RPU_REG_0,
-	HCLGE_OPC_DFX_RPU_REG_1,
-	HCLGE_OPC_DFX_NCSI_REG,
-	HCLGE_OPC_DFX_RTC_REG,
-	HCLGE_OPC_DFX_PPP_REG,
-	HCLGE_OPC_DFX_RCB_REG,
-	HCLGE_OPC_DFX_TQP_REG,
-	HCLGE_OPC_DFX_SSU_REG_2
-};
-
 static const struct key_info meta_data_key_info[] = {
 	{ PACKET_TYPE_ID, 6 },
 	{ IP_FRAGEMENT, 1 },
@@ -12383,463 +12284,6 @@ out:
 	return ret;
 }
 
-static int hclge_get_regs_num(struct hclge_dev *hdev, u32 *regs_num_32_bit,
-			      u32 *regs_num_64_bit)
-{
-	struct hclge_desc desc;
-	u32 total_num;
-	int ret;
-
-	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_REG_NUM, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Query register number cmd failed, ret = %d.\n", ret);
-		return ret;
-	}
-
-	*regs_num_32_bit = le32_to_cpu(desc.data[0]);
-	*regs_num_64_bit = le32_to_cpu(desc.data[1]);
-
-	total_num = *regs_num_32_bit + *regs_num_64_bit;
-	if (!total_num)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int hclge_get_32_bit_regs(struct hclge_dev *hdev, u32 regs_num,
-				 void *data)
-{
-#define HCLGE_32_BIT_REG_RTN_DATANUM 8
-#define HCLGE_32_BIT_DESC_NODATA_LEN 2
-
-	struct hclge_desc *desc;
-	u32 *reg_val = data;
-	__le32 *desc_data;
-	int nodata_num;
-	int cmd_num;
-	int i, k, n;
-	int ret;
-
-	if (regs_num == 0)
-		return 0;
-
-	nodata_num = HCLGE_32_BIT_DESC_NODATA_LEN;
-	cmd_num = DIV_ROUND_UP(regs_num + nodata_num,
-			       HCLGE_32_BIT_REG_RTN_DATANUM);
-	desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL);
-	if (!desc)
-		return -ENOMEM;
-
-	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_32_BIT_REG, true);
-	ret = hclge_cmd_send(&hdev->hw, desc, cmd_num);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Query 32 bit register cmd failed, ret = %d.\n", ret);
-		kfree(desc);
-		return ret;
-	}
-
-	for (i = 0; i < cmd_num; i++) {
-		if (i == 0) {
-			desc_data = (__le32 *)(&desc[i].data[0]);
-			n = HCLGE_32_BIT_REG_RTN_DATANUM - nodata_num;
-		} else {
-			desc_data = (__le32 *)(&desc[i]);
-			n = HCLGE_32_BIT_REG_RTN_DATANUM;
-		}
-		for (k = 0; k < n; k++) {
-			*reg_val++ = le32_to_cpu(*desc_data++);
-
-			regs_num--;
-			if (!regs_num)
-				break;
-		}
-	}
-
-	kfree(desc);
-	return 0;
-}
-
-static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
-				 void *data)
-{
-#define HCLGE_64_BIT_REG_RTN_DATANUM 4
-#define HCLGE_64_BIT_DESC_NODATA_LEN 1
-
-	struct hclge_desc *desc;
-	u64 *reg_val = data;
-	__le64 *desc_data;
-	int nodata_len;
-	int cmd_num;
-	int i, k, n;
-	int ret;
-
-	if (regs_num == 0)
-		return 0;
-
-	nodata_len = HCLGE_64_BIT_DESC_NODATA_LEN;
-	cmd_num = DIV_ROUND_UP(regs_num + nodata_len,
-			       HCLGE_64_BIT_REG_RTN_DATANUM);
-	desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL);
-	if (!desc)
-		return -ENOMEM;
-
-	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_64_BIT_REG, true);
-	ret = hclge_cmd_send(&hdev->hw, desc, cmd_num);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Query 64 bit register cmd failed, ret = %d.\n", ret);
-		kfree(desc);
-		return ret;
-	}
-
-	for (i = 0; i < cmd_num; i++) {
-		if (i == 0) {
-			desc_data = (__le64 *)(&desc[i].data[0]);
-			n = HCLGE_64_BIT_REG_RTN_DATANUM - nodata_len;
-		} else {
-			desc_data = (__le64 *)(&desc[i]);
-			n = HCLGE_64_BIT_REG_RTN_DATANUM;
-		}
-		for (k = 0; k < n; k++) {
-			*reg_val++ = le64_to_cpu(*desc_data++);
-
-			regs_num--;
-			if (!regs_num)
-				break;
-		}
-	}
-
-	kfree(desc);
-	return 0;
-}
-
-#define MAX_SEPARATE_NUM	4
-#define SEPARATOR_VALUE		0xFDFCFBFA
-#define REG_NUM_PER_LINE	4
-#define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
-#define REG_SEPARATOR_LINE	1
-#define REG_NUM_REMAIN_MASK	3
-
-int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc)
-{
-	int i;
-
-	/* initialize command BD except the last one */
-	for (i = 0; i < HCLGE_GET_DFX_REG_TYPE_CNT - 1; i++) {
-		hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_BD_NUM,
-					   true);
-		desc[i].flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT);
-	}
-
-	/* initialize the last command BD */
-	hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_BD_NUM, true);
-
-	return hclge_cmd_send(&hdev->hw, desc, HCLGE_GET_DFX_REG_TYPE_CNT);
-}
-
-static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev,
-				    int *bd_num_list,
-				    u32 type_num)
-{
-	u32 entries_per_desc, desc_index, index, offset, i;
-	struct hclge_desc desc[HCLGE_GET_DFX_REG_TYPE_CNT];
-	int ret;
-
-	ret = hclge_query_bd_num_cmd_send(hdev, desc);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Get dfx bd num fail, status is %d.\n", ret);
-		return ret;
-	}
-
-	entries_per_desc = ARRAY_SIZE(desc[0].data);
-	for (i = 0; i < type_num; i++) {
-		offset = hclge_dfx_bd_offset_list[i];
-		index = offset % entries_per_desc;
-		desc_index = offset / entries_per_desc;
-		bd_num_list[i] = le32_to_cpu(desc[desc_index].data[index]);
-	}
-
-	return ret;
-}
-
-static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev,
-				  struct hclge_desc *desc_src, int bd_num,
-				  enum hclge_opcode_type cmd)
-{
-	struct hclge_desc *desc = desc_src;
-	int i, ret;
-
-	hclge_cmd_setup_basic_desc(desc, cmd, true);
-	for (i = 0; i < bd_num - 1; i++) {
-		desc->flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT);
-		desc++;
-		hclge_cmd_setup_basic_desc(desc, cmd, true);
-	}
-
-	desc = desc_src;
-	ret = hclge_cmd_send(&hdev->hw, desc, bd_num);
-	if (ret)
-		dev_err(&hdev->pdev->dev,
-			"Query dfx reg cmd(0x%x) send fail, status is %d.\n",
-			cmd, ret);
-
-	return ret;
-}
-
-static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num,
-				    void *data)
-{
-	int entries_per_desc, reg_num, separator_num, desc_index, index, i;
-	struct hclge_desc *desc = desc_src;
-	u32 *reg = data;
-
-	entries_per_desc = ARRAY_SIZE(desc->data);
-	reg_num = entries_per_desc * bd_num;
-	separator_num = REG_NUM_PER_LINE - (reg_num & REG_NUM_REMAIN_MASK);
-	for (i = 0; i < reg_num; i++) {
-		index = i % entries_per_desc;
-		desc_index = i / entries_per_desc;
-		*reg++ = le32_to_cpu(desc[desc_index].data[index]);
-	}
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
-
-	return reg_num + separator_num;
-}
-
-static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len)
-{
-	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
-	int data_len_per_desc, bd_num, i;
-	int *bd_num_list;
-	u32 data_len;
-	int ret;
-
-	bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL);
-	if (!bd_num_list)
-		return -ENOMEM;
-
-	ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Get dfx reg bd num fail, status is %d.\n", ret);
-		goto out;
-	}
-
-	data_len_per_desc = sizeof_field(struct hclge_desc, data);
-	*len = 0;
-	for (i = 0; i < dfx_reg_type_num; i++) {
-		bd_num = bd_num_list[i];
-		data_len = data_len_per_desc * bd_num;
-		*len += (data_len / REG_LEN_PER_LINE + 1) * REG_LEN_PER_LINE;
-	}
-
-out:
-	kfree(bd_num_list);
-	return ret;
-}
-
-static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
-{
-	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
-	int bd_num, bd_num_max, buf_len, i;
-	struct hclge_desc *desc_src;
-	int *bd_num_list;
-	u32 *reg = data;
-	int ret;
-
-	bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL);
-	if (!bd_num_list)
-		return -ENOMEM;
-
-	ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Get dfx reg bd num fail, status is %d.\n", ret);
-		goto out;
-	}
-
-	bd_num_max = bd_num_list[0];
-	for (i = 1; i < dfx_reg_type_num; i++)
-		bd_num_max = max_t(int, bd_num_max, bd_num_list[i]);
-
-	buf_len = sizeof(*desc_src) * bd_num_max;
-	desc_src = kzalloc(buf_len, GFP_KERNEL);
-	if (!desc_src) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	for (i = 0; i < dfx_reg_type_num; i++) {
-		bd_num = bd_num_list[i];
-		ret = hclge_dfx_reg_cmd_send(hdev, desc_src, bd_num,
-					     hclge_dfx_reg_opcode_list[i]);
-		if (ret) {
-			dev_err(&hdev->pdev->dev,
-				"Get dfx reg fail, status is %d.\n", ret);
-			break;
-		}
-
-		reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg);
-	}
-
-	kfree(desc_src);
-out:
-	kfree(bd_num_list);
-	return ret;
-}
-
-static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
-			      struct hnae3_knic_private_info *kinfo)
-{
-#define HCLGE_RING_REG_OFFSET		0x200
-#define HCLGE_RING_INT_REG_OFFSET	0x4
-
-	int i, j, reg_num, separator_num;
-	int data_num_sum;
-	u32 *reg = data;
-
-	/* fetching per-PF registers valus from PF PCIe register space */
-	reg_num = ARRAY_SIZE(cmdq_reg_addr_list);
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
-	for (i = 0; i < reg_num; i++)
-		*reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
-	data_num_sum = reg_num + separator_num;
-
-	reg_num = ARRAY_SIZE(common_reg_addr_list);
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
-	for (i = 0; i < reg_num; i++)
-		*reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
-	data_num_sum += reg_num + separator_num;
-
-	reg_num = ARRAY_SIZE(ring_reg_addr_list);
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
-	for (j = 0; j < kinfo->num_tqps; j++) {
-		for (i = 0; i < reg_num; i++)
-			*reg++ = hclge_read_dev(&hdev->hw,
-						ring_reg_addr_list[i] +
-						HCLGE_RING_REG_OFFSET * j);
-		for (i = 0; i < separator_num; i++)
-			*reg++ = SEPARATOR_VALUE;
-	}
-	data_num_sum += (reg_num + separator_num) * kinfo->num_tqps;
-
-	reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list);
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
-	for (j = 0; j < hdev->num_msi_used - 1; j++) {
-		for (i = 0; i < reg_num; i++)
-			*reg++ = hclge_read_dev(&hdev->hw,
-						tqp_intr_reg_addr_list[i] +
-						HCLGE_RING_INT_REG_OFFSET * j);
-		for (i = 0; i < separator_num; i++)
-			*reg++ = SEPARATOR_VALUE;
-	}
-	data_num_sum += (reg_num + separator_num) * (hdev->num_msi_used - 1);
-
-	return data_num_sum;
-}
-
-static int hclge_get_regs_len(struct hnae3_handle *handle)
-{
-	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
-	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
-	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_dev *hdev = vport->back;
-	int regs_num_32_bit, regs_num_64_bit, dfx_regs_len;
-	int regs_lines_32_bit, regs_lines_64_bit;
-	int ret;
-
-	ret = hclge_get_regs_num(hdev, &regs_num_32_bit, &regs_num_64_bit);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Get register number failed, ret = %d.\n", ret);
-		return ret;
-	}
-
-	ret = hclge_get_dfx_reg_len(hdev, &dfx_regs_len);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Get dfx reg len failed, ret = %d.\n", ret);
-		return ret;
-	}
-
-	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-	regs_lines_32_bit = regs_num_32_bit * sizeof(u32) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-	regs_lines_64_bit = regs_num_64_bit * sizeof(u64) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-
-	return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps +
-		tqp_intr_lines * (hdev->num_msi_used - 1) + regs_lines_32_bit +
-		regs_lines_64_bit) * REG_LEN_PER_LINE + dfx_regs_len;
-}
-
-static void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
-			   void *data)
-{
-	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
-	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_dev *hdev = vport->back;
-	u32 regs_num_32_bit, regs_num_64_bit;
-	int i, reg_num, separator_num, ret;
-	u32 *reg = data;
-
-	*version = hdev->fw_version;
-
-	ret = hclge_get_regs_num(hdev, &regs_num_32_bit, &regs_num_64_bit);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Get register number failed, ret = %d.\n", ret);
-		return;
-	}
-
-	reg += hclge_fetch_pf_reg(hdev, reg, kinfo);
-
-	ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Get 32 bit register failed, ret = %d.\n", ret);
-		return;
-	}
-	reg_num = regs_num_32_bit;
-	reg += reg_num;
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
-
-	ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Get 64 bit register failed, ret = %d.\n", ret);
-		return;
-	}
-	reg_num = regs_num_64_bit * 2;
-	reg += reg_num;
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
-
-	ret = hclge_get_dfx_reg(hdev, reg);
-	if (ret)
-		dev_err(&hdev->pdev->dev,
-			"Get dfx register failed, ret = %d.\n", ret);
-}
-
 static int hclge_set_led_status(struct hclge_dev *hdev, u8 locate_led_status)
 {
 	struct hclge_set_led_state_cmd *req;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 70b059e6d35f8..ec233ec57222a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1142,8 +1142,6 @@ int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
 				      u16 state,
 				      struct hclge_vlan_info *vlan_info);
 void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time);
-int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev,
-				struct hclge_desc *desc);
 void hclge_report_hw_error(struct hclge_dev *hdev,
 			   enum hnae3_hw_error_type type);
 int hclge_dbg_dump_rst_info(struct hclge_dev *hdev, char *buf, int len);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
new file mode 100644
index 0000000000000..e566443948756
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
@@ -0,0 +1,567 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2023 Hisilicon Limited.
+
+#include "hclge_cmd.h"
+#include "hclge_main.h"
+#include "hclge_regs.h"
+#include "hnae3.h"
+
+static const u32 cmdq_reg_addr_list[] = {HCLGE_COMM_NIC_CSQ_BASEADDR_L_REG,
+					 HCLGE_COMM_NIC_CSQ_BASEADDR_H_REG,
+					 HCLGE_COMM_NIC_CSQ_DEPTH_REG,
+					 HCLGE_COMM_NIC_CSQ_TAIL_REG,
+					 HCLGE_COMM_NIC_CSQ_HEAD_REG,
+					 HCLGE_COMM_NIC_CRQ_BASEADDR_L_REG,
+					 HCLGE_COMM_NIC_CRQ_BASEADDR_H_REG,
+					 HCLGE_COMM_NIC_CRQ_DEPTH_REG,
+					 HCLGE_COMM_NIC_CRQ_TAIL_REG,
+					 HCLGE_COMM_NIC_CRQ_HEAD_REG,
+					 HCLGE_COMM_VECTOR0_CMDQ_SRC_REG,
+					 HCLGE_COMM_CMDQ_INTR_STS_REG,
+					 HCLGE_COMM_CMDQ_INTR_EN_REG,
+					 HCLGE_COMM_CMDQ_INTR_GEN_REG};
+
+static const u32 common_reg_addr_list[] = {HCLGE_MISC_VECTOR_REG_BASE,
+					   HCLGE_PF_OTHER_INT_REG,
+					   HCLGE_MISC_RESET_STS_REG,
+					   HCLGE_MISC_VECTOR_INT_STS,
+					   HCLGE_GLOBAL_RESET_REG,
+					   HCLGE_FUN_RST_ING,
+					   HCLGE_GRO_EN_REG};
+
+static const u32 ring_reg_addr_list[] = {HCLGE_RING_RX_ADDR_L_REG,
+					 HCLGE_RING_RX_ADDR_H_REG,
+					 HCLGE_RING_RX_BD_NUM_REG,
+					 HCLGE_RING_RX_BD_LENGTH_REG,
+					 HCLGE_RING_RX_MERGE_EN_REG,
+					 HCLGE_RING_RX_TAIL_REG,
+					 HCLGE_RING_RX_HEAD_REG,
+					 HCLGE_RING_RX_FBD_NUM_REG,
+					 HCLGE_RING_RX_OFFSET_REG,
+					 HCLGE_RING_RX_FBD_OFFSET_REG,
+					 HCLGE_RING_RX_STASH_REG,
+					 HCLGE_RING_RX_BD_ERR_REG,
+					 HCLGE_RING_TX_ADDR_L_REG,
+					 HCLGE_RING_TX_ADDR_H_REG,
+					 HCLGE_RING_TX_BD_NUM_REG,
+					 HCLGE_RING_TX_PRIORITY_REG,
+					 HCLGE_RING_TX_TC_REG,
+					 HCLGE_RING_TX_MERGE_EN_REG,
+					 HCLGE_RING_TX_TAIL_REG,
+					 HCLGE_RING_TX_HEAD_REG,
+					 HCLGE_RING_TX_FBD_NUM_REG,
+					 HCLGE_RING_TX_OFFSET_REG,
+					 HCLGE_RING_TX_EBD_NUM_REG,
+					 HCLGE_RING_TX_EBD_OFFSET_REG,
+					 HCLGE_RING_TX_BD_ERR_REG,
+					 HCLGE_RING_EN_REG};
+
+static const u32 tqp_intr_reg_addr_list[] = {HCLGE_TQP_INTR_CTRL_REG,
+					     HCLGE_TQP_INTR_GL0_REG,
+					     HCLGE_TQP_INTR_GL1_REG,
+					     HCLGE_TQP_INTR_GL2_REG,
+					     HCLGE_TQP_INTR_RL_REG};
+
+/* Get DFX BD number offset */
+#define HCLGE_DFX_BIOS_BD_OFFSET        1
+#define HCLGE_DFX_SSU_0_BD_OFFSET       2
+#define HCLGE_DFX_SSU_1_BD_OFFSET       3
+#define HCLGE_DFX_IGU_BD_OFFSET         4
+#define HCLGE_DFX_RPU_0_BD_OFFSET       5
+#define HCLGE_DFX_RPU_1_BD_OFFSET       6
+#define HCLGE_DFX_NCSI_BD_OFFSET        7
+#define HCLGE_DFX_RTC_BD_OFFSET         8
+#define HCLGE_DFX_PPP_BD_OFFSET         9
+#define HCLGE_DFX_RCB_BD_OFFSET         10
+#define HCLGE_DFX_TQP_BD_OFFSET         11
+#define HCLGE_DFX_SSU_2_BD_OFFSET       12
+
+static const u32 hclge_dfx_bd_offset_list[] = {
+	HCLGE_DFX_BIOS_BD_OFFSET,
+	HCLGE_DFX_SSU_0_BD_OFFSET,
+	HCLGE_DFX_SSU_1_BD_OFFSET,
+	HCLGE_DFX_IGU_BD_OFFSET,
+	HCLGE_DFX_RPU_0_BD_OFFSET,
+	HCLGE_DFX_RPU_1_BD_OFFSET,
+	HCLGE_DFX_NCSI_BD_OFFSET,
+	HCLGE_DFX_RTC_BD_OFFSET,
+	HCLGE_DFX_PPP_BD_OFFSET,
+	HCLGE_DFX_RCB_BD_OFFSET,
+	HCLGE_DFX_TQP_BD_OFFSET,
+	HCLGE_DFX_SSU_2_BD_OFFSET
+};
+
+static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = {
+	HCLGE_OPC_DFX_BIOS_COMMON_REG,
+	HCLGE_OPC_DFX_SSU_REG_0,
+	HCLGE_OPC_DFX_SSU_REG_1,
+	HCLGE_OPC_DFX_IGU_EGU_REG,
+	HCLGE_OPC_DFX_RPU_REG_0,
+	HCLGE_OPC_DFX_RPU_REG_1,
+	HCLGE_OPC_DFX_NCSI_REG,
+	HCLGE_OPC_DFX_RTC_REG,
+	HCLGE_OPC_DFX_PPP_REG,
+	HCLGE_OPC_DFX_RCB_REG,
+	HCLGE_OPC_DFX_TQP_REG,
+	HCLGE_OPC_DFX_SSU_REG_2
+};
+
+#define MAX_SEPARATE_NUM	4
+#define SEPARATOR_VALUE		0xFDFCFBFA
+#define REG_NUM_PER_LINE	4
+#define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
+#define REG_SEPARATOR_LINE	1
+#define REG_NUM_REMAIN_MASK	3
+
+static int hclge_get_32_bit_regs(struct hclge_dev *hdev, u32 regs_num,
+				 void *data)
+{
+#define HCLGE_32_BIT_REG_RTN_DATANUM 8
+#define HCLGE_32_BIT_DESC_NODATA_LEN 2
+
+	struct hclge_desc *desc;
+	u32 *reg_val = data;
+	__le32 *desc_data;
+	int nodata_num;
+	int cmd_num;
+	int i, k, n;
+	int ret;
+
+	if (regs_num == 0)
+		return 0;
+
+	nodata_num = HCLGE_32_BIT_DESC_NODATA_LEN;
+	cmd_num = DIV_ROUND_UP(regs_num + nodata_num,
+			       HCLGE_32_BIT_REG_RTN_DATANUM);
+	desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_32_BIT_REG, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, cmd_num);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Query 32 bit register cmd failed, ret = %d.\n", ret);
+		kfree(desc);
+		return ret;
+	}
+
+	for (i = 0; i < cmd_num; i++) {
+		if (i == 0) {
+			desc_data = (__le32 *)(&desc[i].data[0]);
+			n = HCLGE_32_BIT_REG_RTN_DATANUM - nodata_num;
+		} else {
+			desc_data = (__le32 *)(&desc[i]);
+			n = HCLGE_32_BIT_REG_RTN_DATANUM;
+		}
+		for (k = 0; k < n; k++) {
+			*reg_val++ = le32_to_cpu(*desc_data++);
+
+			regs_num--;
+			if (!regs_num)
+				break;
+		}
+	}
+
+	kfree(desc);
+	return 0;
+}
+
+static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
+				 void *data)
+{
+#define HCLGE_64_BIT_REG_RTN_DATANUM 4
+#define HCLGE_64_BIT_DESC_NODATA_LEN 1
+
+	struct hclge_desc *desc;
+	u64 *reg_val = data;
+	__le64 *desc_data;
+	int nodata_len;
+	int cmd_num;
+	int i, k, n;
+	int ret;
+
+	if (regs_num == 0)
+		return 0;
+
+	nodata_len = HCLGE_64_BIT_DESC_NODATA_LEN;
+	cmd_num = DIV_ROUND_UP(regs_num + nodata_len,
+			       HCLGE_64_BIT_REG_RTN_DATANUM);
+	desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_64_BIT_REG, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, cmd_num);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Query 64 bit register cmd failed, ret = %d.\n", ret);
+		kfree(desc);
+		return ret;
+	}
+
+	for (i = 0; i < cmd_num; i++) {
+		if (i == 0) {
+			desc_data = (__le64 *)(&desc[i].data[0]);
+			n = HCLGE_64_BIT_REG_RTN_DATANUM - nodata_len;
+		} else {
+			desc_data = (__le64 *)(&desc[i]);
+			n = HCLGE_64_BIT_REG_RTN_DATANUM;
+		}
+		for (k = 0; k < n; k++) {
+			*reg_val++ = le64_to_cpu(*desc_data++);
+
+			regs_num--;
+			if (!regs_num)
+				break;
+		}
+	}
+
+	kfree(desc);
+	return 0;
+}
+
+int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc)
+{
+	int i;
+
+	/* initialize command BD except the last one */
+	for (i = 0; i < HCLGE_GET_DFX_REG_TYPE_CNT - 1; i++) {
+		hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_BD_NUM,
+					   true);
+		desc[i].flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT);
+	}
+
+	/* initialize the last command BD */
+	hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_BD_NUM, true);
+
+	return hclge_cmd_send(&hdev->hw, desc, HCLGE_GET_DFX_REG_TYPE_CNT);
+}
+
+static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev,
+				    int *bd_num_list,
+				    u32 type_num)
+{
+	u32 entries_per_desc, desc_index, index, offset, i;
+	struct hclge_desc desc[HCLGE_GET_DFX_REG_TYPE_CNT];
+	int ret;
+
+	ret = hclge_query_bd_num_cmd_send(hdev, desc);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get dfx bd num fail, status is %d.\n", ret);
+		return ret;
+	}
+
+	entries_per_desc = ARRAY_SIZE(desc[0].data);
+	for (i = 0; i < type_num; i++) {
+		offset = hclge_dfx_bd_offset_list[i];
+		index = offset % entries_per_desc;
+		desc_index = offset / entries_per_desc;
+		bd_num_list[i] = le32_to_cpu(desc[desc_index].data[index]);
+	}
+
+	return ret;
+}
+
+static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev,
+				  struct hclge_desc *desc_src, int bd_num,
+				  enum hclge_opcode_type cmd)
+{
+	struct hclge_desc *desc = desc_src;
+	int i, ret;
+
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	for (i = 0; i < bd_num - 1; i++) {
+		desc->flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT);
+		desc++;
+		hclge_cmd_setup_basic_desc(desc, cmd, true);
+	}
+
+	desc = desc_src;
+	ret = hclge_cmd_send(&hdev->hw, desc, bd_num);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"Query dfx reg cmd(0x%x) send fail, status is %d.\n",
+			cmd, ret);
+
+	return ret;
+}
+
+static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num,
+				    void *data)
+{
+	int entries_per_desc, reg_num, separator_num, desc_index, index, i;
+	struct hclge_desc *desc = desc_src;
+	u32 *reg = data;
+
+	entries_per_desc = ARRAY_SIZE(desc->data);
+	reg_num = entries_per_desc * bd_num;
+	separator_num = REG_NUM_PER_LINE - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < reg_num; i++) {
+		index = i % entries_per_desc;
+		desc_index = i / entries_per_desc;
+		*reg++ = le32_to_cpu(desc[desc_index].data[index]);
+	}
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	return reg_num + separator_num;
+}
+
+static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len)
+{
+	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
+	int data_len_per_desc, bd_num;
+	int *bd_num_list;
+	u32 data_len, i;
+	int ret;
+
+	bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL);
+	if (!bd_num_list)
+		return -ENOMEM;
+
+	ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get dfx reg bd num fail, status is %d.\n", ret);
+		goto out;
+	}
+
+	data_len_per_desc = sizeof_field(struct hclge_desc, data);
+	*len = 0;
+	for (i = 0; i < dfx_reg_type_num; i++) {
+		bd_num = bd_num_list[i];
+		data_len = data_len_per_desc * bd_num;
+		*len += (data_len / REG_LEN_PER_LINE + 1) * REG_LEN_PER_LINE;
+	}
+
+out:
+	kfree(bd_num_list);
+	return ret;
+}
+
+static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
+{
+	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
+	int bd_num, bd_num_max, buf_len;
+	struct hclge_desc *desc_src;
+	int *bd_num_list;
+	u32 *reg = data;
+	int ret;
+	u32 i;
+
+	bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL);
+	if (!bd_num_list)
+		return -ENOMEM;
+
+	ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get dfx reg bd num fail, status is %d.\n", ret);
+		goto out;
+	}
+
+	bd_num_max = bd_num_list[0];
+	for (i = 1; i < dfx_reg_type_num; i++)
+		bd_num_max = max_t(int, bd_num_max, bd_num_list[i]);
+
+	buf_len = sizeof(*desc_src) * bd_num_max;
+	desc_src = kzalloc(buf_len, GFP_KERNEL);
+	if (!desc_src) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < dfx_reg_type_num; i++) {
+		bd_num = bd_num_list[i];
+		ret = hclge_dfx_reg_cmd_send(hdev, desc_src, bd_num,
+					     hclge_dfx_reg_opcode_list[i]);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"Get dfx reg fail, status is %d.\n", ret);
+			break;
+		}
+
+		reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg);
+	}
+
+	kfree(desc_src);
+out:
+	kfree(bd_num_list);
+	return ret;
+}
+
+static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
+			      struct hnae3_knic_private_info *kinfo)
+{
+#define HCLGE_RING_REG_OFFSET		0x200
+#define HCLGE_RING_INT_REG_OFFSET	0x4
+
+	int i, j, reg_num, separator_num;
+	int data_num_sum;
+	u32 *reg = data;
+
+	/* fetching per-PF registers valus from PF PCIe register space */
+	reg_num = ARRAY_SIZE(cmdq_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < reg_num; i++)
+		*reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+	data_num_sum = reg_num + separator_num;
+
+	reg_num = ARRAY_SIZE(common_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < reg_num; i++)
+		*reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+	data_num_sum += reg_num + separator_num;
+
+	reg_num = ARRAY_SIZE(ring_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (j = 0; j < kinfo->num_tqps; j++) {
+		for (i = 0; i < reg_num; i++)
+			*reg++ = hclge_read_dev(&hdev->hw,
+						ring_reg_addr_list[i] +
+						HCLGE_RING_REG_OFFSET * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+	data_num_sum += (reg_num + separator_num) * kinfo->num_tqps;
+
+	reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (j = 0; j < hdev->num_msi_used - 1; j++) {
+		for (i = 0; i < reg_num; i++)
+			*reg++ = hclge_read_dev(&hdev->hw,
+						tqp_intr_reg_addr_list[i] +
+						HCLGE_RING_INT_REG_OFFSET * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+	data_num_sum += (reg_num + separator_num) * (hdev->num_msi_used - 1);
+
+	return data_num_sum;
+}
+
+static int hclge_get_regs_num(struct hclge_dev *hdev, u32 *regs_num_32_bit,
+			      u32 *regs_num_64_bit)
+{
+	struct hclge_desc desc;
+	u32 total_num;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_REG_NUM, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Query register number cmd failed, ret = %d.\n", ret);
+		return ret;
+	}
+
+	*regs_num_32_bit = le32_to_cpu(desc.data[0]);
+	*regs_num_64_bit = le32_to_cpu(desc.data[1]);
+
+	total_num = *regs_num_32_bit + *regs_num_64_bit;
+	if (!total_num)
+		return -EINVAL;
+
+	return 0;
+}
+
+int hclge_get_regs_len(struct hnae3_handle *handle)
+{
+	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	int regs_num_32_bit, regs_num_64_bit, dfx_regs_len;
+	int regs_lines_32_bit, regs_lines_64_bit;
+	int ret;
+
+	ret = hclge_get_regs_num(hdev, &regs_num_32_bit, &regs_num_64_bit);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get register number failed, ret = %d.\n", ret);
+		return ret;
+	}
+
+	ret = hclge_get_dfx_reg_len(hdev, &dfx_regs_len);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get dfx reg len failed, ret = %d.\n", ret);
+		return ret;
+	}
+
+	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	regs_lines_32_bit = regs_num_32_bit * sizeof(u32) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	regs_lines_64_bit = regs_num_64_bit * sizeof(u64) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+
+	return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps +
+		tqp_intr_lines * (hdev->num_msi_used - 1) + regs_lines_32_bit +
+		regs_lines_64_bit) * REG_LEN_PER_LINE + dfx_regs_len;
+}
+
+void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
+		    void *data)
+{
+#define HCLGE_REG_64_BIT_SPACE_MULTIPLE		2
+
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	u32 regs_num_32_bit, regs_num_64_bit;
+	int i, reg_num, separator_num, ret;
+	u32 *reg = data;
+
+	*version = hdev->fw_version;
+
+	ret = hclge_get_regs_num(hdev, &regs_num_32_bit, &regs_num_64_bit);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get register number failed, ret = %d.\n", ret);
+		return;
+	}
+
+	reg += hclge_fetch_pf_reg(hdev, reg, kinfo);
+
+	ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get 32 bit register failed, ret = %d.\n", ret);
+		return;
+	}
+	reg_num = regs_num_32_bit;
+	reg += reg_num;
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get 64 bit register failed, ret = %d.\n", ret);
+		return;
+	}
+	reg_num = regs_num_64_bit * HCLGE_REG_64_BIT_SPACE_MULTIPLE;
+	reg += reg_num;
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	ret = hclge_get_dfx_reg(hdev, reg);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"Get dfx register failed, ret = %d.\n", ret);
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.h
new file mode 100644
index 0000000000000..b6bc1ecb8054e
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+// Copyright (c) 2023 Hisilicon Limited.
+
+#ifndef __HCLGE_REGS_H
+#define __HCLGE_REGS_H
+#include <linux/types.h>
+#include "hclge_comm_cmd.h"
+
+struct hnae3_handle;
+struct hclge_dev;
+
+int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev,
+				struct hclge_desc *desc);
+int hclge_get_regs_len(struct hnae3_handle *handle);
+void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
+		    void *data);
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 34f02ca8d1d2d..7a2f9233d6954 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -6,6 +6,7 @@
 #include <net/rtnetlink.h>
 #include "hclgevf_cmd.h"
 #include "hclgevf_main.h"
+#include "hclgevf_regs.h"
 #include "hclge_mbx.h"
 #include "hnae3.h"
 #include "hclgevf_devlink.h"
@@ -33,58 +34,6 @@ static const struct pci_device_id ae_algovf_pci_tbl[] = {
 
 MODULE_DEVICE_TABLE(pci, ae_algovf_pci_tbl);
 
-static const u32 cmdq_reg_addr_list[] = {HCLGE_COMM_NIC_CSQ_BASEADDR_L_REG,
-					 HCLGE_COMM_NIC_CSQ_BASEADDR_H_REG,
-					 HCLGE_COMM_NIC_CSQ_DEPTH_REG,
-					 HCLGE_COMM_NIC_CSQ_TAIL_REG,
-					 HCLGE_COMM_NIC_CSQ_HEAD_REG,
-					 HCLGE_COMM_NIC_CRQ_BASEADDR_L_REG,
-					 HCLGE_COMM_NIC_CRQ_BASEADDR_H_REG,
-					 HCLGE_COMM_NIC_CRQ_DEPTH_REG,
-					 HCLGE_COMM_NIC_CRQ_TAIL_REG,
-					 HCLGE_COMM_NIC_CRQ_HEAD_REG,
-					 HCLGE_COMM_VECTOR0_CMDQ_SRC_REG,
-					 HCLGE_COMM_VECTOR0_CMDQ_STATE_REG,
-					 HCLGE_COMM_CMDQ_INTR_EN_REG,
-					 HCLGE_COMM_CMDQ_INTR_GEN_REG};
-
-static const u32 common_reg_addr_list[] = {HCLGEVF_MISC_VECTOR_REG_BASE,
-					   HCLGEVF_RST_ING,
-					   HCLGEVF_GRO_EN_REG};
-
-static const u32 ring_reg_addr_list[] = {HCLGEVF_RING_RX_ADDR_L_REG,
-					 HCLGEVF_RING_RX_ADDR_H_REG,
-					 HCLGEVF_RING_RX_BD_NUM_REG,
-					 HCLGEVF_RING_RX_BD_LENGTH_REG,
-					 HCLGEVF_RING_RX_MERGE_EN_REG,
-					 HCLGEVF_RING_RX_TAIL_REG,
-					 HCLGEVF_RING_RX_HEAD_REG,
-					 HCLGEVF_RING_RX_FBD_NUM_REG,
-					 HCLGEVF_RING_RX_OFFSET_REG,
-					 HCLGEVF_RING_RX_FBD_OFFSET_REG,
-					 HCLGEVF_RING_RX_STASH_REG,
-					 HCLGEVF_RING_RX_BD_ERR_REG,
-					 HCLGEVF_RING_TX_ADDR_L_REG,
-					 HCLGEVF_RING_TX_ADDR_H_REG,
-					 HCLGEVF_RING_TX_BD_NUM_REG,
-					 HCLGEVF_RING_TX_PRIORITY_REG,
-					 HCLGEVF_RING_TX_TC_REG,
-					 HCLGEVF_RING_TX_MERGE_EN_REG,
-					 HCLGEVF_RING_TX_TAIL_REG,
-					 HCLGEVF_RING_TX_HEAD_REG,
-					 HCLGEVF_RING_TX_FBD_NUM_REG,
-					 HCLGEVF_RING_TX_OFFSET_REG,
-					 HCLGEVF_RING_TX_EBD_NUM_REG,
-					 HCLGEVF_RING_TX_EBD_OFFSET_REG,
-					 HCLGEVF_RING_TX_BD_ERR_REG,
-					 HCLGEVF_RING_EN_REG};
-
-static const u32 tqp_intr_reg_addr_list[] = {HCLGEVF_TQP_INTR_CTRL_REG,
-					     HCLGEVF_TQP_INTR_GL0_REG,
-					     HCLGEVF_TQP_INTR_GL1_REG,
-					     HCLGEVF_TQP_INTR_GL2_REG,
-					     HCLGEVF_TQP_INTR_RL_REG};
-
 /* hclgevf_cmd_send - send command to command queue
  * @hw: pointer to the hw struct
  * @desc: prefilled descriptor for describing the command
@@ -111,7 +60,7 @@ void hclgevf_arq_init(struct hclgevf_dev *hdev)
 	spin_unlock(&cmdq->crq.lock);
 }
 
-static struct hclgevf_dev *hclgevf_ae_get_hdev(struct hnae3_handle *handle)
+struct hclgevf_dev *hclgevf_ae_get_hdev(struct hnae3_handle *handle)
 {
 	if (!handle->client)
 		return container_of(handle, struct hclgevf_dev, nic);
@@ -3258,72 +3207,6 @@ static void hclgevf_get_link_mode(struct hnae3_handle *handle,
 	*advertising = hdev->hw.mac.advertising;
 }
 
-#define MAX_SEPARATE_NUM	4
-#define SEPARATOR_VALUE		0xFDFCFBFA
-#define REG_NUM_PER_LINE	4
-#define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
-
-static int hclgevf_get_regs_len(struct hnae3_handle *handle)
-{
-	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-
-	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1;
-
-	return (cmdq_lines + common_lines + ring_lines * hdev->num_tqps +
-		tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE;
-}
-
-static void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
-			     void *data)
-{
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	int i, j, reg_um, separator_num;
-	u32 *reg = data;
-
-	*version = hdev->fw_version;
-
-	/* fetching per-VF registers values from VF PCIe register space */
-	reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
-	for (i = 0; i < reg_um; i++)
-		*reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
-
-	reg_um = sizeof(common_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
-	for (i = 0; i < reg_um; i++)
-		*reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
-
-	reg_um = sizeof(ring_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
-	for (j = 0; j < hdev->num_tqps; j++) {
-		for (i = 0; i < reg_um; i++)
-			*reg++ = hclgevf_read_dev(&hdev->hw,
-						  ring_reg_addr_list[i] +
-						  HCLGEVF_TQP_REG_SIZE * j);
-		for (i = 0; i < separator_num; i++)
-			*reg++ = SEPARATOR_VALUE;
-	}
-
-	reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
-	for (j = 0; j < hdev->num_msi_used - 1; j++) {
-		for (i = 0; i < reg_um; i++)
-			*reg++ = hclgevf_read_dev(&hdev->hw,
-						  tqp_intr_reg_addr_list[i] +
-						  4 * j);
-		for (i = 0; i < separator_num; i++)
-			*reg++ = SEPARATOR_VALUE;
-	}
-}
-
 void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state,
 				struct hclge_mbx_port_base_vlan *port_base_vlan)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 59ca6c794d6db..81c16b8c8da29 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -294,4 +294,5 @@ void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev);
 void hclgevf_mbx_task_schedule(struct hclgevf_dev *hdev);
 void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state,
 			struct hclge_mbx_port_base_vlan *port_base_vlan);
+struct hclgevf_dev *hclgevf_ae_get_hdev(struct hnae3_handle *handle);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
new file mode 100644
index 0000000000000..197ab733306b5
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2023 Hisilicon Limited.
+
+#include "hclgevf_main.h"
+#include "hclgevf_regs.h"
+#include "hnae3.h"
+
+static const u32 cmdq_reg_addr_list[] = {HCLGE_COMM_NIC_CSQ_BASEADDR_L_REG,
+					 HCLGE_COMM_NIC_CSQ_BASEADDR_H_REG,
+					 HCLGE_COMM_NIC_CSQ_DEPTH_REG,
+					 HCLGE_COMM_NIC_CSQ_TAIL_REG,
+					 HCLGE_COMM_NIC_CSQ_HEAD_REG,
+					 HCLGE_COMM_NIC_CRQ_BASEADDR_L_REG,
+					 HCLGE_COMM_NIC_CRQ_BASEADDR_H_REG,
+					 HCLGE_COMM_NIC_CRQ_DEPTH_REG,
+					 HCLGE_COMM_NIC_CRQ_TAIL_REG,
+					 HCLGE_COMM_NIC_CRQ_HEAD_REG,
+					 HCLGE_COMM_VECTOR0_CMDQ_SRC_REG,
+					 HCLGE_COMM_VECTOR0_CMDQ_STATE_REG,
+					 HCLGE_COMM_CMDQ_INTR_EN_REG,
+					 HCLGE_COMM_CMDQ_INTR_GEN_REG};
+
+static const u32 common_reg_addr_list[] = {HCLGEVF_MISC_VECTOR_REG_BASE,
+					   HCLGEVF_RST_ING,
+					   HCLGEVF_GRO_EN_REG};
+
+static const u32 ring_reg_addr_list[] = {HCLGEVF_RING_RX_ADDR_L_REG,
+					 HCLGEVF_RING_RX_ADDR_H_REG,
+					 HCLGEVF_RING_RX_BD_NUM_REG,
+					 HCLGEVF_RING_RX_BD_LENGTH_REG,
+					 HCLGEVF_RING_RX_MERGE_EN_REG,
+					 HCLGEVF_RING_RX_TAIL_REG,
+					 HCLGEVF_RING_RX_HEAD_REG,
+					 HCLGEVF_RING_RX_FBD_NUM_REG,
+					 HCLGEVF_RING_RX_OFFSET_REG,
+					 HCLGEVF_RING_RX_FBD_OFFSET_REG,
+					 HCLGEVF_RING_RX_STASH_REG,
+					 HCLGEVF_RING_RX_BD_ERR_REG,
+					 HCLGEVF_RING_TX_ADDR_L_REG,
+					 HCLGEVF_RING_TX_ADDR_H_REG,
+					 HCLGEVF_RING_TX_BD_NUM_REG,
+					 HCLGEVF_RING_TX_PRIORITY_REG,
+					 HCLGEVF_RING_TX_TC_REG,
+					 HCLGEVF_RING_TX_MERGE_EN_REG,
+					 HCLGEVF_RING_TX_TAIL_REG,
+					 HCLGEVF_RING_TX_HEAD_REG,
+					 HCLGEVF_RING_TX_FBD_NUM_REG,
+					 HCLGEVF_RING_TX_OFFSET_REG,
+					 HCLGEVF_RING_TX_EBD_NUM_REG,
+					 HCLGEVF_RING_TX_EBD_OFFSET_REG,
+					 HCLGEVF_RING_TX_BD_ERR_REG,
+					 HCLGEVF_RING_EN_REG};
+
+static const u32 tqp_intr_reg_addr_list[] = {HCLGEVF_TQP_INTR_CTRL_REG,
+					     HCLGEVF_TQP_INTR_GL0_REG,
+					     HCLGEVF_TQP_INTR_GL1_REG,
+					     HCLGEVF_TQP_INTR_GL2_REG,
+					     HCLGEVF_TQP_INTR_RL_REG};
+
+#define MAX_SEPARATE_NUM	4
+#define SEPARATOR_VALUE		0xFDFCFBFA
+#define REG_NUM_PER_LINE	4
+#define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
+
+int hclgevf_get_regs_len(struct hnae3_handle *handle)
+{
+	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1;
+
+	return (cmdq_lines + common_lines + ring_lines * hdev->num_tqps +
+		tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE;
+}
+
+void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
+		      void *data)
+{
+#define HCLGEVF_RING_REG_OFFSET		0x200
+#define HCLGEVF_RING_INT_REG_OFFSET	0x4
+
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int i, j, reg_um, separator_num;
+	u32 *reg = data;
+
+	*version = hdev->fw_version;
+
+	/* fetching per-VF registers values from VF PCIe register space */
+	reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (i = 0; i < reg_um; i++)
+		*reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	reg_um = sizeof(common_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (i = 0; i < reg_um; i++)
+		*reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	reg_um = sizeof(ring_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (j = 0; j < hdev->num_tqps; j++) {
+		for (i = 0; i < reg_um; i++)
+			*reg++ = hclgevf_read_dev(&hdev->hw,
+						  ring_reg_addr_list[i] +
+						  HCLGEVF_RING_REG_OFFSET * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+
+	reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (j = 0; j < hdev->num_msi_used - 1; j++) {
+		for (i = 0; i < reg_um; i++)
+			*reg++ = hclgevf_read_dev(&hdev->hw,
+						  tqp_intr_reg_addr_list[i] +
+						  HCLGEVF_RING_INT_REG_OFFSET * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.h
new file mode 100644
index 0000000000000..77bdcf60a1afe
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2023 Hisilicon Limited. */
+
+#ifndef __HCLGEVF_REGS_H
+#define __HCLGEVF_REGS_H
+#include <linux/types.h>
+
+struct hnae3_handle;
+
+int hclgevf_get_regs_len(struct hnae3_handle *handle);
+void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
+		      void *data);
+#endif
-- 
GitLab


From d8634b7c3f62d265fc2ecf29286aa9c5b78f969f Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Tue, 15 Aug 2023 14:06:39 +0800
Subject: [PATCH 1251/1806] net: hns3: Support tlv in regs data for HNS3 PF
 driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The dump register function is being refactored.
The second step in refactoring is to support tlv info in regs data for
HNS3 PF driver.

Currently, if we use "ethtool -d" to dump regs value,
the output is as follows:
  offset1: 00 01 02 03 04 05 ...
  offset2：10 11 12 13 14 15 ...
  ......

We can't get the value of a register directly.

This patch deletes the original separator information and
add tag_len_value information in regs data.
ethtool can parse register data in key-value format by -d command.

a patch will be added to the ethtool to parse regs data
in the following format:
  reg1 : value2
  reg2 : value2
  ......

Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../hisilicon/hns3/hns3pf/hclge_regs.c        | 167 +++++++++++-------
 1 file changed, 102 insertions(+), 65 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
index e566443948756..734e5f757b9c5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
@@ -106,12 +106,66 @@ static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = {
 	HCLGE_OPC_DFX_SSU_REG_2
 };
 
-#define MAX_SEPARATE_NUM	4
-#define SEPARATOR_VALUE		0xFDFCFBFA
-#define REG_NUM_PER_LINE	4
-#define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
-#define REG_SEPARATOR_LINE	1
-#define REG_NUM_REMAIN_MASK	3
+enum hclge_reg_tag {
+	HCLGE_REG_TAG_CMDQ = 0,
+	HCLGE_REG_TAG_COMMON,
+	HCLGE_REG_TAG_RING,
+	HCLGE_REG_TAG_TQP_INTR,
+	HCLGE_REG_TAG_QUERY_32_BIT,
+	HCLGE_REG_TAG_QUERY_64_BIT,
+	HCLGE_REG_TAG_DFX_BIOS_COMMON,
+	HCLGE_REG_TAG_DFX_SSU_0,
+	HCLGE_REG_TAG_DFX_SSU_1,
+	HCLGE_REG_TAG_DFX_IGU_EGU,
+	HCLGE_REG_TAG_DFX_RPU_0,
+	HCLGE_REG_TAG_DFX_RPU_1,
+	HCLGE_REG_TAG_DFX_NCSI,
+	HCLGE_REG_TAG_DFX_RTC,
+	HCLGE_REG_TAG_DFX_PPP,
+	HCLGE_REG_TAG_DFX_RCB,
+	HCLGE_REG_TAG_DFX_TQP,
+	HCLGE_REG_TAG_DFX_SSU_2,
+};
+
+#pragma pack(4)
+struct hclge_reg_tlv {
+	u16 tag;
+	u16 len;
+};
+
+struct hclge_reg_header {
+	u64 magic_number;
+	u8 is_vf;
+	u8 rsv[7];
+};
+
+#pragma pack()
+
+#define HCLGE_REG_TLV_SIZE	sizeof(struct hclge_reg_tlv)
+#define HCLGE_REG_HEADER_SIZE	sizeof(struct hclge_reg_header)
+#define HCLGE_REG_TLV_SPACE	(sizeof(struct hclge_reg_tlv) / sizeof(u32))
+#define HCLGE_REG_HEADER_SPACE	(sizeof(struct hclge_reg_header) / sizeof(u32))
+#define HCLGE_REG_MAGIC_NUMBER	0x686e733372656773 /* meaning is hns3regs */
+
+static u32 hclge_reg_get_header(void *data)
+{
+	struct hclge_reg_header *header = data;
+
+	header->magic_number = HCLGE_REG_MAGIC_NUMBER;
+	header->is_vf = 0x0;
+
+	return HCLGE_REG_HEADER_SPACE;
+}
+
+static u32 hclge_reg_get_tlv(u32 tag, u32 regs_num, void *data)
+{
+	struct hclge_reg_tlv *tlv = data;
+
+	tlv->tag = tag;
+	tlv->len = regs_num * sizeof(u32) + HCLGE_REG_TLV_SIZE;
+
+	return HCLGE_REG_TLV_SPACE;
+}
 
 static int hclge_get_32_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 				 void *data)
@@ -291,31 +345,28 @@ static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev,
 static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num,
 				    void *data)
 {
-	int entries_per_desc, reg_num, separator_num, desc_index, index, i;
+	int entries_per_desc, reg_num, desc_index, index, i;
 	struct hclge_desc *desc = desc_src;
 	u32 *reg = data;
 
 	entries_per_desc = ARRAY_SIZE(desc->data);
 	reg_num = entries_per_desc * bd_num;
-	separator_num = REG_NUM_PER_LINE - (reg_num & REG_NUM_REMAIN_MASK);
 	for (i = 0; i < reg_num; i++) {
 		index = i % entries_per_desc;
 		desc_index = i / entries_per_desc;
 		*reg++ = le32_to_cpu(desc[desc_index].data[index]);
 	}
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
 
-	return reg_num + separator_num;
+	return reg_num;
 }
 
 static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len)
 {
 	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
-	int data_len_per_desc, bd_num;
+	int data_len_per_desc;
 	int *bd_num_list;
-	u32 data_len, i;
 	int ret;
+	u32 i;
 
 	bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL);
 	if (!bd_num_list)
@@ -330,11 +381,8 @@ static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len)
 
 	data_len_per_desc = sizeof_field(struct hclge_desc, data);
 	*len = 0;
-	for (i = 0; i < dfx_reg_type_num; i++) {
-		bd_num = bd_num_list[i];
-		data_len = data_len_per_desc * bd_num;
-		*len += (data_len / REG_LEN_PER_LINE + 1) * REG_LEN_PER_LINE;
-	}
+	for (i = 0; i < dfx_reg_type_num; i++)
+		*len += bd_num_list[i] * data_len_per_desc + HCLGE_REG_TLV_SIZE;
 
 out:
 	kfree(bd_num_list);
@@ -383,6 +431,9 @@ static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
 			break;
 		}
 
+		reg += hclge_reg_get_tlv(HCLGE_REG_TAG_DFX_BIOS_COMMON + i,
+					 ARRAY_SIZE(desc_src->data) * bd_num,
+					 reg);
 		reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg);
 	}
 
@@ -398,50 +449,43 @@ static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
 #define HCLGE_RING_REG_OFFSET		0x200
 #define HCLGE_RING_INT_REG_OFFSET	0x4
 
-	int i, j, reg_num, separator_num;
+	int i, j, reg_num;
 	int data_num_sum;
 	u32 *reg = data;
 
 	/* fetching per-PF registers valus from PF PCIe register space */
 	reg_num = ARRAY_SIZE(cmdq_reg_addr_list);
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	reg += hclge_reg_get_tlv(HCLGE_REG_TAG_CMDQ, reg_num, reg);
 	for (i = 0; i < reg_num; i++)
 		*reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
-	data_num_sum = reg_num + separator_num;
+	data_num_sum = reg_num + HCLGE_REG_TLV_SPACE;
 
 	reg_num = ARRAY_SIZE(common_reg_addr_list);
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	reg += hclge_reg_get_tlv(HCLGE_REG_TAG_COMMON, reg_num, reg);
 	for (i = 0; i < reg_num; i++)
 		*reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
-	data_num_sum += reg_num + separator_num;
+	data_num_sum += reg_num + HCLGE_REG_TLV_SPACE;
 
 	reg_num = ARRAY_SIZE(ring_reg_addr_list);
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
 	for (j = 0; j < kinfo->num_tqps; j++) {
+		reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RING, reg_num, reg);
 		for (i = 0; i < reg_num; i++)
 			*reg++ = hclge_read_dev(&hdev->hw,
 						ring_reg_addr_list[i] +
 						HCLGE_RING_REG_OFFSET * j);
-		for (i = 0; i < separator_num; i++)
-			*reg++ = SEPARATOR_VALUE;
 	}
-	data_num_sum += (reg_num + separator_num) * kinfo->num_tqps;
+	data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) * kinfo->num_tqps;
 
 	reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list);
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
 	for (j = 0; j < hdev->num_msi_used - 1; j++) {
+		reg += hclge_reg_get_tlv(HCLGE_REG_TAG_TQP_INTR, reg_num, reg);
 		for (i = 0; i < reg_num; i++)
 			*reg++ = hclge_read_dev(&hdev->hw,
 						tqp_intr_reg_addr_list[i] +
 						HCLGE_RING_INT_REG_OFFSET * j);
-		for (i = 0; i < separator_num; i++)
-			*reg++ = SEPARATOR_VALUE;
 	}
-	data_num_sum += (reg_num + separator_num) * (hdev->num_msi_used - 1);
+	data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) *
+			(hdev->num_msi_used - 1);
 
 	return data_num_sum;
 }
@@ -473,12 +517,12 @@ static int hclge_get_regs_num(struct hclge_dev *hdev, u32 *regs_num_32_bit,
 
 int hclge_get_regs_len(struct hnae3_handle *handle)
 {
-	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_dev *hdev = vport->back;
 	int regs_num_32_bit, regs_num_64_bit, dfx_regs_len;
-	int regs_lines_32_bit, regs_lines_64_bit;
+	int cmdq_len, common_len, ring_len, tqp_intr_len;
+	int regs_len_32_bit, regs_len_64_bit;
+	struct hclge_dev *hdev = vport->back;
 	int ret;
 
 	ret = hclge_get_regs_num(hdev, &regs_num_32_bit, &regs_num_64_bit);
@@ -495,22 +539,17 @@ int hclge_get_regs_len(struct hnae3_handle *handle)
 		return ret;
 	}
 
-	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-	regs_lines_32_bit = regs_num_32_bit * sizeof(u32) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-	regs_lines_64_bit = regs_num_64_bit * sizeof(u64) / REG_LEN_PER_LINE +
-		REG_SEPARATOR_LINE;
-
-	return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps +
-		tqp_intr_lines * (hdev->num_msi_used - 1) + regs_lines_32_bit +
-		regs_lines_64_bit) * REG_LEN_PER_LINE + dfx_regs_len;
+	cmdq_len = HCLGE_REG_TLV_SIZE + sizeof(cmdq_reg_addr_list);
+	common_len = HCLGE_REG_TLV_SIZE + sizeof(common_reg_addr_list);
+	ring_len = HCLGE_REG_TLV_SIZE + sizeof(ring_reg_addr_list);
+	tqp_intr_len = HCLGE_REG_TLV_SIZE + sizeof(tqp_intr_reg_addr_list);
+	regs_len_32_bit = HCLGE_REG_TLV_SIZE + regs_num_32_bit * sizeof(u32);
+	regs_len_64_bit = HCLGE_REG_TLV_SIZE + regs_num_64_bit * sizeof(u64);
+
+	/* return the total length of all register values */
+	return HCLGE_REG_HEADER_SIZE + cmdq_len + common_len + ring_len *
+		kinfo->num_tqps + tqp_intr_len * (hdev->num_msi_used - 1) +
+		regs_len_32_bit + regs_len_64_bit + dfx_regs_len;
 }
 
 void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
@@ -522,8 +561,8 @@ void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 	u32 regs_num_32_bit, regs_num_64_bit;
-	int i, reg_num, separator_num, ret;
 	u32 *reg = data;
+	int ret;
 
 	*version = hdev->fw_version;
 
@@ -534,31 +573,29 @@ void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
 		return;
 	}
 
+	reg += hclge_reg_get_header(reg);
 	reg += hclge_fetch_pf_reg(hdev, reg, kinfo);
 
+	reg += hclge_reg_get_tlv(HCLGE_REG_TAG_QUERY_32_BIT,
+				 regs_num_32_bit, reg);
 	ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get 32 bit register failed, ret = %d.\n", ret);
 		return;
 	}
-	reg_num = regs_num_32_bit;
-	reg += reg_num;
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
+	reg += regs_num_32_bit;
 
+	reg += hclge_reg_get_tlv(HCLGE_REG_TAG_QUERY_64_BIT,
+				 regs_num_64_bit *
+				 HCLGE_REG_64_BIT_SPACE_MULTIPLE, reg);
 	ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get 64 bit register failed, ret = %d.\n", ret);
 		return;
 	}
-	reg_num = regs_num_64_bit * HCLGE_REG_64_BIT_SPACE_MULTIPLE;
-	reg += reg_num;
-	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
+	reg += regs_num_64_bit * HCLGE_REG_64_BIT_SPACE_MULTIPLE;
 
 	ret = hclge_get_dfx_reg(hdev, reg);
 	if (ret)
-- 
GitLab


From 3ef5d70b82ad5be1235e16318d9ab4f848a5bd68 Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Tue, 15 Aug 2023 14:06:40 +0800
Subject: [PATCH 1252/1806] net: hns3: Support tlv in regs data for HNS3 VF
 driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The dump register function is being refactored.
The third step in refactoring is to support tlv info in regs data for
HNS3 PF driver.

Currently, if we use "ethtool -d" to dump regs value,
the output is as follows:
  offset1: 00 01 02 03 04 05 ...
  offset2：10 11 12 13 14 15 ...
  ......

We can't get the value of a register directly.

This patch deletes the original separator information and
add tag_len_value information in regs data.
ethtool can parse register data in key-value format by -d command.

a patch will be added to the ethtool to parse regs data
in the following format:
  reg1 : value2
  reg2 : value2
  ......

Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../hisilicon/hns3/hns3vf/hclgevf_regs.c      | 85 +++++++++++++------
 1 file changed, 61 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
index 197ab733306b5..65b9dcd381375 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
@@ -57,23 +57,67 @@ static const u32 tqp_intr_reg_addr_list[] = {HCLGEVF_TQP_INTR_CTRL_REG,
 					     HCLGEVF_TQP_INTR_GL2_REG,
 					     HCLGEVF_TQP_INTR_RL_REG};
 
-#define MAX_SEPARATE_NUM	4
-#define SEPARATOR_VALUE		0xFDFCFBFA
-#define REG_NUM_PER_LINE	4
-#define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
+enum hclgevf_reg_tag {
+	HCLGEVF_REG_TAG_CMDQ = 0,
+	HCLGEVF_REG_TAG_COMMON,
+	HCLGEVF_REG_TAG_RING,
+	HCLGEVF_REG_TAG_TQP_INTR,
+};
+
+#pragma pack(4)
+struct hclgevf_reg_tlv {
+	u16 tag;
+	u16 len;
+};
+
+struct hclgevf_reg_header {
+	u64 magic_number;
+	u8 is_vf;
+	u8 rsv[7];
+};
+
+#pragma pack()
+
+#define HCLGEVF_REG_TLV_SIZE		sizeof(struct hclgevf_reg_tlv)
+#define HCLGEVF_REG_HEADER_SIZE		sizeof(struct hclgevf_reg_header)
+#define HCLGEVF_REG_TLV_SPACE		(sizeof(struct hclgevf_reg_tlv) / sizeof(u32))
+#define HCLGEVF_REG_HEADER_SPACE	(sizeof(struct hclgevf_reg_header) / sizeof(u32))
+#define HCLGEVF_REG_MAGIC_NUMBER	0x686e733372656773 /* meaning is hns3regs */
+
+static u32 hclgevf_reg_get_header(void *data)
+{
+	struct hclgevf_reg_header *header = data;
+
+	header->magic_number = HCLGEVF_REG_MAGIC_NUMBER;
+	header->is_vf = 0x1;
+
+	return HCLGEVF_REG_HEADER_SPACE;
+}
+
+static u32 hclgevf_reg_get_tlv(u32 tag, u32 regs_num, void *data)
+{
+	struct hclgevf_reg_tlv *tlv = data;
+
+	tlv->tag = tag;
+	tlv->len = regs_num * sizeof(u32) + HCLGEVF_REG_TLV_SIZE;
+
+	return HCLGEVF_REG_TLV_SPACE;
+}
 
 int hclgevf_get_regs_len(struct hnae3_handle *handle)
 {
-	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int cmdq_len, common_len, ring_len, tqp_intr_len;
 
-	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	cmdq_len = HCLGEVF_REG_TLV_SIZE + sizeof(cmdq_reg_addr_list);
+	common_len = HCLGEVF_REG_TLV_SIZE + sizeof(common_reg_addr_list);
+	ring_len = HCLGEVF_REG_TLV_SIZE + sizeof(ring_reg_addr_list);
+	tqp_intr_len = HCLGEVF_REG_TLV_SIZE + sizeof(tqp_intr_reg_addr_list);
 
-	return (cmdq_lines + common_lines + ring_lines * hdev->num_tqps +
-		tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE;
+	/* return the total length of all register values */
+	return HCLGEVF_REG_HEADER_SIZE + cmdq_len + common_len +
+	       tqp_intr_len * (hdev->num_msi_used - 1) +
+	       ring_len * hdev->num_tqps;
 }
 
 void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
@@ -83,45 +127,38 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
 #define HCLGEVF_RING_INT_REG_OFFSET	0x4
 
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	int i, j, reg_um, separator_num;
+	int i, j, reg_um;
 	u32 *reg = data;
 
 	*version = hdev->fw_version;
+	reg += hclgevf_reg_get_header(reg);
 
 	/* fetching per-VF registers values from VF PCIe register space */
 	reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_CMDQ, reg_um, reg);
 	for (i = 0; i < reg_um; i++)
 		*reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
 
 	reg_um = sizeof(common_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_COMMON, reg_um, reg);
 	for (i = 0; i < reg_um; i++)
 		*reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
 
 	reg_um = sizeof(ring_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
 	for (j = 0; j < hdev->num_tqps; j++) {
+		reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg);
 		for (i = 0; i < reg_um; i++)
 			*reg++ = hclgevf_read_dev(&hdev->hw,
 						  ring_reg_addr_list[i] +
 						  HCLGEVF_RING_REG_OFFSET * j);
-		for (i = 0; i < separator_num; i++)
-			*reg++ = SEPARATOR_VALUE;
 	}
 
 	reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
 	for (j = 0; j < hdev->num_msi_used - 1; j++) {
+		reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_TQP_INTR, reg_um, reg);
 		for (i = 0; i < reg_um; i++)
 			*reg++ = hclgevf_read_dev(&hdev->hw,
 						  tqp_intr_reg_addr_list[i] +
 						  HCLGEVF_RING_INT_REG_OFFSET * j);
-		for (i = 0; i < separator_num; i++)
-			*reg++ = SEPARATOR_VALUE;
 	}
 }
-- 
GitLab


From 36122201eeaefd78547def9681aa5d83b5a00b6a Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Tue, 15 Aug 2023 14:06:41 +0800
Subject: [PATCH 1253/1806] net: hns3: fix wrong rpu tln reg issue

In the original RPU query command, the status register values of
multiple RPU tunnels are accumulated by default, which is unreasonable.
This patch Fix it by querying the specified tunnel ID.
The tunnel number of the device can be obtained from firmware
during initialization.

Fixes: ddb54554fa51 ("net: hns3: add DFX registers information for ethtool -d")
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h   |  1 +
 .../hisilicon/hns3/hns3pf/hclge_cmd.h         |  4 +-
 .../hisilicon/hns3/hns3pf/hclge_main.c        |  2 +
 .../hisilicon/hns3/hns3pf/hclge_regs.c        | 66 ++++++++++++++++++-
 4 files changed, 71 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 514a20bce4f44..a4b43bcd2f0c9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -382,6 +382,7 @@ struct hnae3_dev_specs {
 	u16 umv_size;
 	u16 mc_mac_size;
 	u32 mac_stats_num;
+	u8 tnl_num;
 };
 
 struct hnae3_client_ops {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 0bd858620f27b..4d15eb73b9728 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -826,7 +826,9 @@ struct hclge_dev_specs_1_cmd {
 	u8 rsv0[2];
 	__le16 umv_size;
 	__le16 mc_mac_size;
-	u8 rsv1[12];
+	u8 rsv1[6];
+	u8 tnl_num;
+	u8 rsv2[5];
 };
 
 /* mac speed type defined in firmware command */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 36e8daf498117..0f50dba6cc478 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1326,6 +1326,7 @@ static void hclge_set_default_dev_specs(struct hclge_dev *hdev)
 	ae_dev->dev_specs.max_frm_size = HCLGE_MAC_MAX_FRAME;
 	ae_dev->dev_specs.max_qset_num = HCLGE_MAX_QSET_NUM;
 	ae_dev->dev_specs.umv_size = HCLGE_DEFAULT_UMV_SPACE_PER_PF;
+	ae_dev->dev_specs.tnl_num = 0;
 }
 
 static void hclge_parse_dev_specs(struct hclge_dev *hdev,
@@ -1349,6 +1350,7 @@ static void hclge_parse_dev_specs(struct hclge_dev *hdev,
 	ae_dev->dev_specs.max_frm_size = le16_to_cpu(req1->max_frm_size);
 	ae_dev->dev_specs.umv_size = le16_to_cpu(req1->umv_size);
 	ae_dev->dev_specs.mc_mac_size = le16_to_cpu(req1->mc_mac_size);
+	ae_dev->dev_specs.tnl_num = req1->tnl_num;
 }
 
 static void hclge_check_dev_specs(struct hclge_dev *hdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
index 734e5f757b9c5..43c1c18fa81f8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
@@ -125,6 +125,7 @@ enum hclge_reg_tag {
 	HCLGE_REG_TAG_DFX_RCB,
 	HCLGE_REG_TAG_DFX_TQP,
 	HCLGE_REG_TAG_DFX_SSU_2,
+	HCLGE_REG_TAG_RPU_TNL,
 };
 
 #pragma pack(4)
@@ -147,6 +148,8 @@ struct hclge_reg_header {
 #define HCLGE_REG_HEADER_SPACE	(sizeof(struct hclge_reg_header) / sizeof(u32))
 #define HCLGE_REG_MAGIC_NUMBER	0x686e733372656773 /* meaning is hns3regs */
 
+#define HCLGE_REG_RPU_TNL_ID_0	1
+
 static u32 hclge_reg_get_header(void *data)
 {
 	struct hclge_reg_header *header = data;
@@ -342,6 +345,28 @@ static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev,
 	return ret;
 }
 
+/* tnl_id = 0 means get sum of all tnl reg's value */
+static int hclge_dfx_reg_rpu_tnl_cmd_send(struct hclge_dev *hdev, u32 tnl_id,
+					  struct hclge_desc *desc, int bd_num)
+{
+	int i, ret;
+
+	for (i = 0; i < bd_num; i++) {
+		hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_RPU_REG_0,
+					   true);
+		if (i != bd_num - 1)
+			desc[i].flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT);
+	}
+
+	desc[0].data[0] = cpu_to_le32(tnl_id);
+	ret = hclge_cmd_send(&hdev->hw, desc, bd_num);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"failed to query dfx rpu tnl reg, ret = %d\n",
+			ret);
+	return ret;
+}
+
 static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num,
 				    void *data)
 {
@@ -363,6 +388,7 @@ static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num,
 static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len)
 {
 	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	int data_len_per_desc;
 	int *bd_num_list;
 	int ret;
@@ -384,11 +410,41 @@ static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len)
 	for (i = 0; i < dfx_reg_type_num; i++)
 		*len += bd_num_list[i] * data_len_per_desc + HCLGE_REG_TLV_SIZE;
 
+	/**
+	 * the num of dfx_rpu_0 is reused by each dfx_rpu_tnl
+	 * HCLGE_DFX_BD_OFFSET is starting at 1, but the array subscript is
+	 * starting at 0, so offset need '- 1'.
+	 */
+	*len += (bd_num_list[HCLGE_DFX_RPU_0_BD_OFFSET - 1] * data_len_per_desc +
+		 HCLGE_REG_TLV_SIZE) * ae_dev->dev_specs.tnl_num;
+
 out:
 	kfree(bd_num_list);
 	return ret;
 }
 
+static int hclge_get_dfx_rpu_tnl_reg(struct hclge_dev *hdev, u32 *reg,
+				     struct hclge_desc *desc_src,
+				     int bd_num)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+	int ret = 0;
+	u8 i;
+
+	for (i = HCLGE_REG_RPU_TNL_ID_0; i <= ae_dev->dev_specs.tnl_num; i++) {
+		ret = hclge_dfx_reg_rpu_tnl_cmd_send(hdev, i, desc_src, bd_num);
+		if (ret)
+			break;
+
+		reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RPU_TNL,
+					 ARRAY_SIZE(desc_src->data) * bd_num,
+					 reg);
+		reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg);
+	}
+
+	return ret;
+}
+
 static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
 {
 	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
@@ -428,7 +484,7 @@ static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"Get dfx reg fail, status is %d.\n", ret);
-			break;
+			goto free;
 		}
 
 		reg += hclge_reg_get_tlv(HCLGE_REG_TAG_DFX_BIOS_COMMON + i,
@@ -437,6 +493,14 @@ static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
 		reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg);
 	}
 
+	/**
+	 * HCLGE_DFX_BD_OFFSET is starting at 1, but the array subscript is
+	 * starting at 0, so offset need '- 1'.
+	 */
+	bd_num = bd_num_list[HCLGE_DFX_RPU_0_BD_OFFSET - 1];
+	ret = hclge_get_dfx_rpu_tnl_reg(hdev, reg, desc_src, bd_num);
+
+free:
 	kfree(desc_src);
 out:
 	kfree(bd_num_list);
-- 
GitLab


From 61a9b174f461de4d0668a98ca2f668b65ebdf131 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 15 Aug 2023 15:49:27 +0800
Subject: [PATCH 1254/1806] nfc: virtual_ncidev: Use module_misc_device macro
 to simplify the code

Use the module_misc_device macro to simplify the code, which is the
same as declaring with module_init() and module_exit().

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/virtual_ncidev.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c
index bb76c7c7cc822..b027be0b0b6ff 100644
--- a/drivers/nfc/virtual_ncidev.c
+++ b/drivers/nfc/virtual_ncidev.c
@@ -200,18 +200,7 @@ static struct miscdevice miscdev = {
 	.mode = 0600,
 };
 
-static int __init virtual_ncidev_init(void)
-{
-	return misc_register(&miscdev);
-}
-
-static void __exit virtual_ncidev_exit(void)
-{
-	misc_deregister(&miscdev);
-}
-
-module_init(virtual_ncidev_init);
-module_exit(virtual_ncidev_exit);
+module_misc_device(miscdev);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Virtual NCI device simulation driver");
-- 
GitLab


From aae249dfa089c0c9d845ef18d70c0b7ef367df64 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Mon, 14 Aug 2023 10:55:15 +0800
Subject: [PATCH 1255/1806] net: dsa: realtek: Remove redundant of_match_ptr()

The driver depends on CONFIG_OF, it is not necessary to use
of_match_ptr() here.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/realtek/realtek-mdio.c | 2 +-
 drivers/net/dsa/realtek/realtek-smi.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/realtek/realtek-mdio.c b/drivers/net/dsa/realtek/realtek-mdio.c
index 4310e7793e586..292e6d087e8b9 100644
--- a/drivers/net/dsa/realtek/realtek-mdio.c
+++ b/drivers/net/dsa/realtek/realtek-mdio.c
@@ -276,7 +276,7 @@ MODULE_DEVICE_TABLE(of, realtek_mdio_of_match);
 static struct mdio_driver realtek_mdio_driver = {
 	.mdiodrv.driver = {
 		.name = "realtek-mdio",
-		.of_match_table = of_match_ptr(realtek_mdio_of_match),
+		.of_match_table = realtek_mdio_of_match,
 	},
 	.probe  = realtek_mdio_probe,
 	.remove = realtek_mdio_remove,
diff --git a/drivers/net/dsa/realtek/realtek-smi.c b/drivers/net/dsa/realtek/realtek-smi.c
index c2bd8bb6c9c22..ff13563059c50 100644
--- a/drivers/net/dsa/realtek/realtek-smi.c
+++ b/drivers/net/dsa/realtek/realtek-smi.c
@@ -556,7 +556,7 @@ MODULE_DEVICE_TABLE(of, realtek_smi_of_match);
 static struct platform_driver realtek_smi_driver = {
 	.driver = {
 		.name = "realtek-smi",
-		.of_match_table = of_match_ptr(realtek_smi_of_match),
+		.of_match_table = realtek_smi_of_match,
 	},
 	.probe  = realtek_smi_probe,
 	.remove = realtek_smi_remove,
-- 
GitLab


From 81d463c02b910f4abb1415c365f9491e10333552 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Mon, 14 Aug 2023 10:55:16 +0800
Subject: [PATCH 1256/1806] net: dsa: rzn1-a5psw: Remove redundant
 of_match_ptr()

The driver depends on CONFIG_OF, it is not necessary to use
of_match_ptr() here.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rzn1_a5psw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c
index 2bb458f2c1f88..9167e83fbceb2 100644
--- a/drivers/net/dsa/rzn1_a5psw.c
+++ b/drivers/net/dsa/rzn1_a5psw.c
@@ -1314,7 +1314,7 @@ MODULE_DEVICE_TABLE(of, a5psw_of_mtable);
 static struct platform_driver a5psw_driver = {
 	.driver = {
 		.name	 = "rzn1_a5psw",
-		.of_match_table = of_match_ptr(a5psw_of_mtable),
+		.of_match_table = a5psw_of_mtable,
 	},
 	.probe = a5psw_probe,
 	.remove = a5psw_remove,
-- 
GitLab


From 21b566fda00f1907b41a06fb0255746639e4579f Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Mon, 14 Aug 2023 10:55:17 +0800
Subject: [PATCH 1257/1806] net: gemini: Remove redundant of_match_ptr()

The driver depends on CONFIG_OF, it is not necessary to use
of_match_ptr() here.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 692cb2d04c1c7..a8b9d1a3e4d57 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2538,7 +2538,7 @@ MODULE_DEVICE_TABLE(of, gemini_ethernet_port_of_match);
 static struct platform_driver gemini_ethernet_port_driver = {
 	.driver = {
 		.name = "gemini-ethernet-port",
-		.of_match_table = of_match_ptr(gemini_ethernet_port_of_match),
+		.of_match_table = gemini_ethernet_port_of_match,
 	},
 	.probe = gemini_ethernet_port_probe,
 	.remove = gemini_ethernet_port_remove,
@@ -2604,7 +2604,7 @@ MODULE_DEVICE_TABLE(of, gemini_ethernet_of_match);
 static struct platform_driver gemini_ethernet_driver = {
 	.driver = {
 		.name = DRV_NAME,
-		.of_match_table = of_match_ptr(gemini_ethernet_of_match),
+		.of_match_table = gemini_ethernet_of_match,
 	},
 	.probe = gemini_ethernet_probe,
 	.remove = gemini_ethernet_remove,
-- 
GitLab


From 537a6b9927083e2b7b0b3223dc77a985707d5339 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Mon, 14 Aug 2023 10:55:18 +0800
Subject: [PATCH 1258/1806] net: qualcomm: Remove redundant of_match_ptr()

The driver depends on CONFIG_OF, it is not necessary to use
of_match_ptr() here.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_uart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c
index ace99c62d03a8..9adec91f35e94 100644
--- a/drivers/net/ethernet/qualcomm/qca_uart.c
+++ b/drivers/net/ethernet/qualcomm/qca_uart.c
@@ -403,7 +403,7 @@ static struct serdev_device_driver qca_uart_driver = {
 	.remove = qca_uart_remove,
 	.driver = {
 		.name = QCAUART_DRV_NAME,
-		.of_match_table = of_match_ptr(qca_uart_of_match),
+		.of_match_table = qca_uart_of_match,
 	},
 };
 
-- 
GitLab


From cf2abd8724318195a0cd7e55ff1dcac74b4b110a Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Mon, 14 Aug 2023 10:55:19 +0800
Subject: [PATCH 1259/1806] wlcore: spi: Remove redundant of_match_ptr()

The driver depends on CONFIG_OF, it is not necessary to use
of_match_ptr() here.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/ti/wlcore/spi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c
index 3f88e6a0a510e..7d9a139db59e1 100644
--- a/drivers/net/wireless/ti/wlcore/spi.c
+++ b/drivers/net/wireless/ti/wlcore/spi.c
@@ -554,7 +554,7 @@ static void wl1271_remove(struct spi_device *spi)
 static struct spi_driver wl1271_spi_driver = {
 	.driver = {
 		.name		= "wl1271_spi",
-		.of_match_table = of_match_ptr(wlcore_spi_of_match_table),
+		.of_match_table = wlcore_spi_of_match_table,
 	},
 
 	.probe		= wl1271_probe,
-- 
GitLab


From c274af2242693f59f00851b3660a21b10bcd76cc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:33 +0000
Subject: [PATCH 1260/1806] inet: introduce inet->inet_flags

Various inet fields are currently racy.

do_ip_setsockopt() and do_ip_getsockopt() are mostly holding
the socket lock, but some (fast) paths do not.

Use a new inet->inet_flags to hold atomic bits in the series.

Remove inet->cmsg_flags, and use instead 9 bits from inet_flags.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h | 55 +++++++++++++++++++++------
 net/ipv4/ip_sockglue.c  | 84 +++++++++++++++--------------------------
 net/ipv4/ping.c         |  5 ++-
 net/ipv4/raw.c          |  2 +-
 net/ipv4/udp.c          |  2 +-
 net/ipv6/datagram.c     |  2 +-
 net/ipv6/udp.c          |  2 +-
 net/l2tp/l2tp_ip.c      |  2 +-
 8 files changed, 83 insertions(+), 71 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 0bb32bfc61832..e3b35b0015f33 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -194,6 +194,7 @@ struct rtable;
  * @inet_rcv_saddr - Bound local IPv4 addr
  * @inet_dport - Destination port
  * @inet_num - Local port
+ * @inet_flags - various atomic flags
  * @inet_saddr - Sending source
  * @uc_ttl - Unicast TTL
  * @inet_sport - Source port
@@ -218,11 +219,11 @@ struct inet_sock {
 #define inet_dport		sk.__sk_common.skc_dport
 #define inet_num		sk.__sk_common.skc_num
 
+	unsigned long		inet_flags;
 	__be32			inet_saddr;
 	__s16			uc_ttl;
-	__u16			cmsg_flags;
-	struct ip_options_rcu __rcu	*inet_opt;
 	__be16			inet_sport;
+	struct ip_options_rcu __rcu	*inet_opt;
 	__u16			inet_id;
 
 	__u8			tos;
@@ -259,16 +260,48 @@ struct inet_sock {
 #define IPCORK_OPT	1	/* ip-options has been held in ipcork.opt */
 #define IPCORK_ALLFRAG	2	/* always fragment (for ipv6 for now) */
 
+enum {
+	INET_FLAGS_PKTINFO	= 0,
+	INET_FLAGS_TTL		= 1,
+	INET_FLAGS_TOS		= 2,
+	INET_FLAGS_RECVOPTS	= 3,
+	INET_FLAGS_RETOPTS	= 4,
+	INET_FLAGS_PASSSEC	= 5,
+	INET_FLAGS_ORIGDSTADDR	= 6,
+	INET_FLAGS_CHECKSUM	= 7,
+	INET_FLAGS_RECVFRAGSIZE	= 8,
+};
+
 /* cmsg flags for inet */
-#define IP_CMSG_PKTINFO		BIT(0)
-#define IP_CMSG_TTL		BIT(1)
-#define IP_CMSG_TOS		BIT(2)
-#define IP_CMSG_RECVOPTS	BIT(3)
-#define IP_CMSG_RETOPTS		BIT(4)
-#define IP_CMSG_PASSSEC		BIT(5)
-#define IP_CMSG_ORIGDSTADDR	BIT(6)
-#define IP_CMSG_CHECKSUM	BIT(7)
-#define IP_CMSG_RECVFRAGSIZE	BIT(8)
+#define IP_CMSG_PKTINFO		BIT(INET_FLAGS_PKTINFO)
+#define IP_CMSG_TTL		BIT(INET_FLAGS_TTL)
+#define IP_CMSG_TOS		BIT(INET_FLAGS_TOS)
+#define IP_CMSG_RECVOPTS	BIT(INET_FLAGS_RECVOPTS)
+#define IP_CMSG_RETOPTS		BIT(INET_FLAGS_RETOPTS)
+#define IP_CMSG_PASSSEC		BIT(INET_FLAGS_PASSSEC)
+#define IP_CMSG_ORIGDSTADDR	BIT(INET_FLAGS_ORIGDSTADDR)
+#define IP_CMSG_CHECKSUM	BIT(INET_FLAGS_CHECKSUM)
+#define IP_CMSG_RECVFRAGSIZE	BIT(INET_FLAGS_RECVFRAGSIZE)
+
+#define IP_CMSG_ALL	(IP_CMSG_PKTINFO | IP_CMSG_TTL |		\
+			 IP_CMSG_TOS | IP_CMSG_RECVOPTS |		\
+			 IP_CMSG_RETOPTS | IP_CMSG_PASSSEC |		\
+			 IP_CMSG_ORIGDSTADDR | IP_CMSG_CHECKSUM |	\
+			 IP_CMSG_RECVFRAGSIZE)
+
+static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet)
+{
+	return READ_ONCE(inet->inet_flags) & IP_CMSG_ALL;
+}
+
+#define inet_test_bit(nr, sk)			\
+	test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags)
+#define inet_set_bit(nr, sk)			\
+	set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags)
+#define inet_clear_bit(nr, sk)			\
+	clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags)
+#define inet_assign_bit(nr, sk, val)		\
+	assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val)
 
 static inline bool sk_is_inet(struct sock *sk)
 {
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d41bce8927b2c..66f55f3db5ec8 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -171,8 +171,10 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 			 struct sk_buff *skb, int tlen, int offset)
 {
-	struct inet_sock *inet = inet_sk(sk);
-	unsigned int flags = inet->cmsg_flags;
+	unsigned long flags = inet_cmsg_flags(inet_sk(sk));
+
+	if (!flags)
+		return;
 
 	/* Ordered by supposed usage frequency */
 	if (flags & IP_CMSG_PKTINFO) {
@@ -568,7 +570,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
-		if (inet_sk(sk)->cmsg_flags)
+		if (inet_cmsg_flags(inet_sk(sk)))
 			ip_cmsg_recv(msg, skb);
 	}
 
@@ -635,7 +637,7 @@ EXPORT_SYMBOL(ip_sock_set_mtu_discover);
 void ip_sock_set_pktinfo(struct sock *sk)
 {
 	lock_sock(sk);
-	inet_sk(sk)->cmsg_flags |= IP_CMSG_PKTINFO;
+	inet_set_bit(PKTINFO, sk);
 	release_sock(sk);
 }
 EXPORT_SYMBOL(ip_sock_set_pktinfo);
@@ -990,67 +992,43 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		break;
 	}
 	case IP_PKTINFO:
-		if (val)
-			inet->cmsg_flags |= IP_CMSG_PKTINFO;
-		else
-			inet->cmsg_flags &= ~IP_CMSG_PKTINFO;
+		inet_assign_bit(PKTINFO, sk, val);
 		break;
 	case IP_RECVTTL:
-		if (val)
-			inet->cmsg_flags |=  IP_CMSG_TTL;
-		else
-			inet->cmsg_flags &= ~IP_CMSG_TTL;
+		inet_assign_bit(TTL, sk, val);
 		break;
 	case IP_RECVTOS:
-		if (val)
-			inet->cmsg_flags |=  IP_CMSG_TOS;
-		else
-			inet->cmsg_flags &= ~IP_CMSG_TOS;
+		inet_assign_bit(TOS, sk, val);
 		break;
 	case IP_RECVOPTS:
-		if (val)
-			inet->cmsg_flags |=  IP_CMSG_RECVOPTS;
-		else
-			inet->cmsg_flags &= ~IP_CMSG_RECVOPTS;
+		inet_assign_bit(RECVOPTS, sk, val);
 		break;
 	case IP_RETOPTS:
-		if (val)
-			inet->cmsg_flags |= IP_CMSG_RETOPTS;
-		else
-			inet->cmsg_flags &= ~IP_CMSG_RETOPTS;
+		inet_assign_bit(RETOPTS, sk, val);
 		break;
 	case IP_PASSSEC:
-		if (val)
-			inet->cmsg_flags |= IP_CMSG_PASSSEC;
-		else
-			inet->cmsg_flags &= ~IP_CMSG_PASSSEC;
+		inet_assign_bit(PASSSEC, sk, val);
 		break;
 	case IP_RECVORIGDSTADDR:
-		if (val)
-			inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR;
-		else
-			inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR;
+		inet_assign_bit(ORIGDSTADDR, sk, val);
 		break;
 	case IP_CHECKSUM:
 		if (val) {
-			if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) {
+			if (!(inet_test_bit(CHECKSUM, sk))) {
 				inet_inc_convert_csum(sk);
-				inet->cmsg_flags |= IP_CMSG_CHECKSUM;
+				inet_set_bit(CHECKSUM, sk);
 			}
 		} else {
-			if (inet->cmsg_flags & IP_CMSG_CHECKSUM) {
+			if (inet_test_bit(CHECKSUM, sk)) {
 				inet_dec_convert_csum(sk);
-				inet->cmsg_flags &= ~IP_CMSG_CHECKSUM;
+				inet_clear_bit(CHECKSUM, sk);
 			}
 		}
 		break;
 	case IP_RECVFRAGSIZE:
 		if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM)
 			goto e_inval;
-		if (val)
-			inet->cmsg_flags |= IP_CMSG_RECVFRAGSIZE;
-		else
-			inet->cmsg_flags &= ~IP_CMSG_RECVFRAGSIZE;
+		inet_assign_bit(RECVFRAGSIZE, sk, val);
 		break;
 	case IP_TOS:	/* This sets both TOS and Precedence */
 		__ip_sock_set_tos(sk, val);
@@ -1415,7 +1393,7 @@ e_inval:
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 {
 	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
-	bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) ||
+	bool prepare = inet_test_bit(PKTINFO, sk) ||
 		       ipv6_sk_rxinfo(sk);
 
 	if (prepare && skb_rtable(skb)) {
@@ -1601,31 +1579,31 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		return 0;
 	}
 	case IP_PKTINFO:
-		val = (inet->cmsg_flags & IP_CMSG_PKTINFO) != 0;
+		val = inet_test_bit(PKTINFO, sk);
 		break;
 	case IP_RECVTTL:
-		val = (inet->cmsg_flags & IP_CMSG_TTL) != 0;
+		val = inet_test_bit(TTL, sk);
 		break;
 	case IP_RECVTOS:
-		val = (inet->cmsg_flags & IP_CMSG_TOS) != 0;
+		val = inet_test_bit(TOS, sk);
 		break;
 	case IP_RECVOPTS:
-		val = (inet->cmsg_flags & IP_CMSG_RECVOPTS) != 0;
+		val = inet_test_bit(RECVOPTS, sk);
 		break;
 	case IP_RETOPTS:
-		val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0;
+		val = inet_test_bit(RETOPTS, sk);
 		break;
 	case IP_PASSSEC:
-		val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0;
+		val = inet_test_bit(PASSSEC, sk);
 		break;
 	case IP_RECVORIGDSTADDR:
-		val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0;
+		val = inet_test_bit(ORIGDSTADDR, sk);
 		break;
 	case IP_CHECKSUM:
-		val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0;
+		val = inet_test_bit(CHECKSUM, sk);
 		break;
 	case IP_RECVFRAGSIZE:
-		val = (inet->cmsg_flags & IP_CMSG_RECVFRAGSIZE) != 0;
+		val = inet_test_bit(RECVFRAGSIZE, sk);
 		break;
 	case IP_TOS:
 		val = inet->tos;
@@ -1737,7 +1715,7 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		msg.msg_controllen = len;
 		msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0;
 
-		if (inet->cmsg_flags & IP_CMSG_PKTINFO) {
+		if (inet_test_bit(PKTINFO, sk)) {
 			struct in_pktinfo info;
 
 			info.ipi_addr.s_addr = inet->inet_rcv_saddr;
@@ -1745,11 +1723,11 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			info.ipi_ifindex = inet->mc_index;
 			put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
 		}
-		if (inet->cmsg_flags & IP_CMSG_TTL) {
+		if (inet_test_bit(TTL, sk)) {
 			int hlim = inet->mc_ttl;
 			put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
 		}
-		if (inet->cmsg_flags & IP_CMSG_TOS) {
+		if (inet_test_bit(TOS, sk)) {
 			int tos = inet->rcv_tos;
 			put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos);
 		}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 25dd78cee1792..7e8702cb66344 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -894,7 +894,7 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
 			*addr_len = sizeof(*sin);
 		}
 
-		if (isk->cmsg_flags)
+		if (inet_cmsg_flags(isk))
 			ip_cmsg_recv(msg, skb);
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -921,7 +921,8 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
 		if (skb->protocol == htons(ETH_P_IPV6) &&
 		    inet6_sk(sk)->rxopt.all)
 			pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb);
-		else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags)
+		else if (skb->protocol == htons(ETH_P_IP) &&
+			 inet_cmsg_flags(isk))
 			ip_cmsg_recv(msg, skb);
 #endif
 	} else {
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index cb381f5aa4643..e6e813f4aa317 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -767,7 +767,7 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
 		*addr_len = sizeof(*sin);
 	}
-	if (inet->cmsg_flags)
+	if (inet_cmsg_flags(inet))
 		ip_cmsg_recv(msg, skb);
 	if (flags & MSG_TRUNC)
 		copied = skb->len;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3e2f29c14fa8c..4b791133989c0 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1870,7 +1870,7 @@ try_again:
 	if (udp_sk(sk)->gro_enabled)
 		udp_cmsg_recv(msg, sk, skb);
 
-	if (inet->cmsg_flags)
+	if (inet_cmsg_flags(inet))
 		ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off);
 
 	err = copied;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index d80d6024cafa9..41ebc4e574734 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -524,7 +524,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 		} else {
 			ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
 					       &sin->sin6_addr);
-			if (inet_sk(sk)->cmsg_flags)
+			if (inet_cmsg_flags(inet_sk(sk)))
 				ip_cmsg_recv(msg, skb);
 		}
 	}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1ea01b0d9be38..ebc6ae47cfead 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -420,7 +420,7 @@ try_again:
 		ip6_datagram_recv_common_ctl(sk, msg, skb);
 
 	if (is_udp4) {
-		if (inet->cmsg_flags)
+		if (inet_cmsg_flags(inet))
 			ip_cmsg_recv_offset(msg, sk, skb,
 					    sizeof(struct udphdr), off);
 	} else {
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index f9073bc7281f9..9a2a9ed3ba478 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -552,7 +552,7 @@ static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg,
 		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
 		*addr_len = sizeof(*sin);
 	}
-	if (inet->cmsg_flags)
+	if (inet_cmsg_flags(inet))
 		ip_cmsg_recv(msg, skb);
 	if (flags & MSG_TRUNC)
 		copied = skb->len;
-- 
GitLab


From b4d84bce4c437c4ac1b6f7ef4d612d7d52f62cfe Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:34 +0000
Subject: [PATCH 1261/1806] inet: set/get simple options locklessly

Now we have inet->inet_flags, we can set following options
without having to hold the socket lock:

IP_PKTINFO, IP_RECVTTL, IP_RECVTOS, IP_RECVOPTS, IP_RETOPTS,
IP_PASSSEC, IP_RECVORIGDSTADDR, IP_RECVFRAGSIZE.

ip_sock_set_pktinfo() no longer hold the socket lock.

Similarly we can get the following options whithout holding
the socket lock:

IP_PKTINFO, IP_RECVTTL, IP_RECVTOS, IP_RECVOPTS, IP_RETOPTS,
IP_PASSSEC, IP_RECVORIGDSTADDR, IP_CHECKSUM, IP_RECVFRAGSIZE.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 118 ++++++++++++++++++++++-------------------
 1 file changed, 62 insertions(+), 56 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 66f55f3db5ec8..69b87518348aa 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -636,9 +636,7 @@ EXPORT_SYMBOL(ip_sock_set_mtu_discover);
 
 void ip_sock_set_pktinfo(struct sock *sk)
 {
-	lock_sock(sk);
 	inet_set_bit(PKTINFO, sk);
-	release_sock(sk);
 }
 EXPORT_SYMBOL(ip_sock_set_pktinfo);
 
@@ -952,6 +950,36 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 	if (ip_mroute_opt(optname))
 		return ip_mroute_setsockopt(sk, optname, optval, optlen);
 
+	/* Handle options that can be set without locking the socket. */
+	switch (optname) {
+	case IP_PKTINFO:
+		inet_assign_bit(PKTINFO, sk, val);
+		return 0;
+	case IP_RECVTTL:
+		inet_assign_bit(TTL, sk, val);
+		return 0;
+	case IP_RECVTOS:
+		inet_assign_bit(TOS, sk, val);
+		return 0;
+	case IP_RECVOPTS:
+		inet_assign_bit(RECVOPTS, sk, val);
+		return 0;
+	case IP_RETOPTS:
+		inet_assign_bit(RETOPTS, sk, val);
+		return 0;
+	case IP_PASSSEC:
+		inet_assign_bit(PASSSEC, sk, val);
+		return 0;
+	case IP_RECVORIGDSTADDR:
+		inet_assign_bit(ORIGDSTADDR, sk, val);
+		return 0;
+	case IP_RECVFRAGSIZE:
+		if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM)
+			return -EINVAL;
+		inet_assign_bit(RECVFRAGSIZE, sk, val);
+		return 0;
+	}
+
 	err = 0;
 	if (needs_rtnl)
 		rtnl_lock();
@@ -991,27 +1019,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			kfree_rcu(old, rcu);
 		break;
 	}
-	case IP_PKTINFO:
-		inet_assign_bit(PKTINFO, sk, val);
-		break;
-	case IP_RECVTTL:
-		inet_assign_bit(TTL, sk, val);
-		break;
-	case IP_RECVTOS:
-		inet_assign_bit(TOS, sk, val);
-		break;
-	case IP_RECVOPTS:
-		inet_assign_bit(RECVOPTS, sk, val);
-		break;
-	case IP_RETOPTS:
-		inet_assign_bit(RETOPTS, sk, val);
-		break;
-	case IP_PASSSEC:
-		inet_assign_bit(PASSSEC, sk, val);
-		break;
-	case IP_RECVORIGDSTADDR:
-		inet_assign_bit(ORIGDSTADDR, sk, val);
-		break;
 	case IP_CHECKSUM:
 		if (val) {
 			if (!(inet_test_bit(CHECKSUM, sk))) {
@@ -1025,11 +1032,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			}
 		}
 		break;
-	case IP_RECVFRAGSIZE:
-		if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM)
-			goto e_inval;
-		inet_assign_bit(RECVFRAGSIZE, sk, val);
-		break;
 	case IP_TOS:	/* This sets both TOS and Precedence */
 		__ip_sock_set_tos(sk, val);
 		break;
@@ -1544,6 +1546,37 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	if (len < 0)
 		return -EINVAL;
 
+	/* Handle options that can be read without locking the socket. */
+	switch (optname) {
+	case IP_PKTINFO:
+		val = inet_test_bit(PKTINFO, sk);
+		goto copyval;
+	case IP_RECVTTL:
+		val = inet_test_bit(TTL, sk);
+		goto copyval;
+	case IP_RECVTOS:
+		val = inet_test_bit(TOS, sk);
+		goto copyval;
+	case IP_RECVOPTS:
+		val = inet_test_bit(RECVOPTS, sk);
+		goto copyval;
+	case IP_RETOPTS:
+		val = inet_test_bit(RETOPTS, sk);
+		goto copyval;
+	case IP_PASSSEC:
+		val = inet_test_bit(PASSSEC, sk);
+		goto copyval;
+	case IP_RECVORIGDSTADDR:
+		val = inet_test_bit(ORIGDSTADDR, sk);
+		goto copyval;
+	case IP_CHECKSUM:
+		val = inet_test_bit(CHECKSUM, sk);
+		goto copyval;
+	case IP_RECVFRAGSIZE:
+		val = inet_test_bit(RECVFRAGSIZE, sk);
+		goto copyval;
+	}
+
 	if (needs_rtnl)
 		rtnl_lock();
 	sockopt_lock_sock(sk);
@@ -1578,33 +1611,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			return -EFAULT;
 		return 0;
 	}
-	case IP_PKTINFO:
-		val = inet_test_bit(PKTINFO, sk);
-		break;
-	case IP_RECVTTL:
-		val = inet_test_bit(TTL, sk);
-		break;
-	case IP_RECVTOS:
-		val = inet_test_bit(TOS, sk);
-		break;
-	case IP_RECVOPTS:
-		val = inet_test_bit(RECVOPTS, sk);
-		break;
-	case IP_RETOPTS:
-		val = inet_test_bit(RETOPTS, sk);
-		break;
-	case IP_PASSSEC:
-		val = inet_test_bit(PASSSEC, sk);
-		break;
-	case IP_RECVORIGDSTADDR:
-		val = inet_test_bit(ORIGDSTADDR, sk);
-		break;
-	case IP_CHECKSUM:
-		val = inet_test_bit(CHECKSUM, sk);
-		break;
-	case IP_RECVFRAGSIZE:
-		val = inet_test_bit(RECVFRAGSIZE, sk);
-		break;
 	case IP_TOS:
 		val = inet->tos;
 		break;
@@ -1754,7 +1760,7 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		return -ENOPROTOOPT;
 	}
 	sockopt_release_sock(sk);
-
+copyval:
 	if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) {
 		unsigned char ucval = (unsigned char)val;
 		len = 1;
-- 
GitLab


From 6b5f43ea08150e7ff72f734545101c58489ead5b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:35 +0000
Subject: [PATCH 1262/1806] inet: move inet->recverr to inet->inet_flags

IP_RECVERR socket option can now be set/get without locking the socket.

This patch potentially avoid data-races around inet->recverr.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h |  5 +++--
 net/dccp/ipv4.c         |  4 +---
 net/ipv4/inet_diag.c    |  2 +-
 net/ipv4/ip_sockglue.c  | 23 ++++++++++-------------
 net/ipv4/ping.c         |  2 +-
 net/ipv4/raw.c          | 14 ++++++++------
 net/ipv4/tcp_ipv4.c     |  5 ++---
 net/ipv4/udp.c          |  5 +++--
 net/sctp/input.c        |  2 +-
 9 files changed, 30 insertions(+), 32 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index e3b35b0015f33..552188aa5a2d2 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -230,8 +230,7 @@ struct inet_sock {
 	__u8			min_ttl;
 	__u8			mc_ttl;
 	__u8			pmtudisc;
-	__u8			recverr:1,
-				is_icsk:1,
+	__u8			is_icsk:1,
 				freebind:1,
 				hdrincl:1,
 				mc_loop:1,
@@ -270,6 +269,8 @@ enum {
 	INET_FLAGS_ORIGDSTADDR	= 6,
 	INET_FLAGS_CHECKSUM	= 7,
 	INET_FLAGS_RECVFRAGSIZE	= 8,
+
+	INET_FLAGS_RECVERR	= 9,
 };
 
 /* cmsg flags for inet */
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 8e919cfe6e233..8dd6837c476a9 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -247,7 +247,6 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info)
 	const u8 offset = iph->ihl << 2;
 	const struct dccp_hdr *dh;
 	struct dccp_sock *dp;
-	struct inet_sock *inet;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
 	struct sock *sk;
@@ -361,8 +360,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info)
 	 *							--ANK (980905)
 	 */
 
-	inet = inet_sk(sk);
-	if (!sock_owned_by_user(sk) && inet->recverr) {
+	if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) {
 		sk->sk_err = err;
 		sk_error_report(sk);
 	} else { /* Only an error on timeout */
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index f7426926a1041..25d5f76b66bd8 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -182,7 +182,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	r->idiag_inode = sock_i_ino(sk);
 
 	memset(&inet_sockopt, 0, sizeof(inet_sockopt));
-	inet_sockopt.recverr	= inet->recverr;
+	inet_sockopt.recverr	= inet_test_bit(RECVERR, sk);
 	inet_sockopt.is_icsk	= inet->is_icsk;
 	inet_sockopt.freebind	= inet->freebind;
 	inet_sockopt.hdrincl	= inet->hdrincl;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 69b87518348aa..8283d862a9dbb 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -446,12 +446,11 @@ EXPORT_SYMBOL_GPL(ip_icmp_error);
 
 void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info)
 {
-	struct inet_sock *inet = inet_sk(sk);
 	struct sock_exterr_skb *serr;
 	struct iphdr *iph;
 	struct sk_buff *skb;
 
-	if (!inet->recverr)
+	if (!inet_test_bit(RECVERR, sk))
 		return;
 
 	skb = alloc_skb(sizeof(struct iphdr), GFP_ATOMIC);
@@ -617,9 +616,7 @@ EXPORT_SYMBOL(ip_sock_set_freebind);
 
 void ip_sock_set_recverr(struct sock *sk)
 {
-	lock_sock(sk);
-	inet_sk(sk)->recverr = true;
-	release_sock(sk);
+	inet_set_bit(RECVERR, sk);
 }
 EXPORT_SYMBOL(ip_sock_set_recverr);
 
@@ -978,6 +975,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		inet_assign_bit(RECVFRAGSIZE, sk, val);
 		return 0;
+	case IP_RECVERR:
+		inet_assign_bit(RECVERR, sk, val);
+		if (!val)
+			skb_queue_purge(&sk->sk_error_queue);
+		return 0;
 	}
 
 	err = 0;
@@ -1064,11 +1066,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			goto e_inval;
 		inet->pmtudisc = val;
 		break;
-	case IP_RECVERR:
-		inet->recverr = !!val;
-		if (!val)
-			skb_queue_purge(&sk->sk_error_queue);
-		break;
 	case IP_RECVERR_RFC4884:
 		if (val < 0 || val > 1)
 			goto e_inval;
@@ -1575,6 +1572,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_RECVFRAGSIZE:
 		val = inet_test_bit(RECVFRAGSIZE, sk);
 		goto copyval;
+	case IP_RECVERR:
+		val = inet_test_bit(RECVERR, sk);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1649,9 +1649,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		}
 		break;
 	}
-	case IP_RECVERR:
-		val = inet->recverr;
-		break;
 	case IP_RECVERR_RFC4884:
 		val = inet->recverr_rfc4884;
 		break;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 7e8702cb66344..75e0aee35eb78 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -580,7 +580,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info)
 	 *      RFC1122: OK.  Passes ICMP errors back to application, as per
 	 *	4.1.3.3.
 	 */
-	if ((family == AF_INET && !inet_sock->recverr) ||
+	if ((family == AF_INET && !inet_test_bit(RECVERR, sk)) ||
 	    (family == AF_INET6 && !inet6_sk(sk)->recverr)) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
 			goto out;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index e6e813f4aa317..f4c27dc5714bd 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -203,8 +203,9 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 	struct inet_sock *inet = inet_sk(sk);
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
-	int err = 0;
 	int harderr = 0;
+	bool recverr;
+	int err = 0;
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
 		ipv4_sk_update_pmtu(skb, sk, info);
@@ -218,7 +219,8 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 	   2. Socket is connected (otherwise the error indication
 	      is useless without ip_recverr and error is hard.
 	 */
-	if (!inet->recverr && sk->sk_state != TCP_ESTABLISHED)
+	recverr = inet_test_bit(RECVERR, sk);
+	if (!recverr && sk->sk_state != TCP_ESTABLISHED)
 		return;
 
 	switch (type) {
@@ -245,7 +247,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 		}
 	}
 
-	if (inet->recverr) {
+	if (recverr) {
 		const struct iphdr *iph = (const struct iphdr *)skb->data;
 		u8 *payload = skb->data + (iph->ihl << 2);
 
@@ -254,7 +256,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 		ip_icmp_error(sk, skb, err, 0, info, payload);
 	}
 
-	if (inet->recverr || harderr) {
+	if (recverr || harderr) {
 		sk->sk_err = err;
 		sk_error_report(sk);
 	}
@@ -413,7 +415,7 @@ error_free:
 	kfree_skb(skb);
 error:
 	IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
-	if (err == -ENOBUFS && !inet->recverr)
+	if (err == -ENOBUFS && !inet_test_bit(RECVERR, sk))
 		err = 0;
 	return err;
 }
@@ -645,7 +647,7 @@ back_from_confirm:
 			ip_flush_pending_frames(sk);
 		else if (!(msg->msg_flags & MSG_MORE)) {
 			err = ip_push_pending_frames(sk, &fl4);
-			if (err == -ENOBUFS && !inet->recverr)
+			if (err == -ENOBUFS && !inet_test_bit(RECVERR, sk))
 				err = 0;
 		}
 		release_sock(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5b18a048f613e..2a662d5f3072f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -477,7 +477,6 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2));
 	struct tcp_sock *tp;
-	struct inet_sock *inet;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
 	struct sock *sk;
@@ -625,8 +624,8 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
 	 *							--ANK (980905)
 	 */
 
-	inet = inet_sk(sk);
-	if (!sock_owned_by_user(sk) && inet->recverr) {
+	if (!sock_owned_by_user(sk) &&
+	    inet_test_bit(RECVERR, sk)) {
 		WRITE_ONCE(sk->sk_err, err);
 		sk_error_report(sk);
 	} else	{ /* Only an error on timeout */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4b791133989c0..0794a2c46a568 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -779,7 +779,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 						  (u8 *)(uh+1));
 		goto out;
 	}
-	if (!inet->recverr) {
+	if (!inet_test_bit(RECVERR, sk)) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
 			goto out;
 	} else
@@ -962,7 +962,8 @@ csum_partial:
 send:
 	err = ip_send_skb(sock_net(sk), skb);
 	if (err) {
-		if (err == -ENOBUFS && !inet->recverr) {
+		if (err == -ENOBUFS &&
+		    !inet_test_bit(RECVERR, sk)) {
 			UDP_INC_STATS(sock_net(sk),
 				      UDP_MIB_SNDBUFERRORS, is_udplite);
 			err = 0;
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 2613c4d74b169..17fcaa9b0df94 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -581,7 +581,7 @@ static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb,
 	default:
 		return;
 	}
-	if (!sock_owned_by_user(sk) && inet_sk(sk)->recverr) {
+	if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) {
 		sk->sk_err = err;
 		sk_error_report(sk);
 	} else {  /* Only an error on timeout */
-- 
GitLab


From 8e8cfb114d9f1e2efddb892f993c1ad61635c85e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:36 +0000
Subject: [PATCH 1263/1806] inet: move inet->recverr_rfc4884 to
 inet->inet_flags

IP_RECVERR_RFC4884 socket option can now be set/read
without locking the socket.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h |  2 +-
 net/ipv4/inet_diag.c    |  2 +-
 net/ipv4/ip_sockglue.c  | 18 +++++++++---------
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 552188aa5a2d2..c01f1f64a8617 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -238,7 +238,6 @@ struct inet_sock {
 				mc_all:1,
 				nodefrag:1;
 	__u8			bind_address_no_port:1,
-				recverr_rfc4884:1,
 				defer_connect:1; /* Indicates that fastopen_connect is set
 						  * and cookie exists so we defer connect
 						  * until first data frame is written
@@ -271,6 +270,7 @@ enum {
 	INET_FLAGS_RECVFRAGSIZE	= 8,
 
 	INET_FLAGS_RECVERR	= 9,
+	INET_FLAGS_RECVERR_RFC4884 = 10,
 };
 
 /* cmsg flags for inet */
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 25d5f76b66bd8..6255d6fdbc80d 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -191,7 +191,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	inet_sockopt.mc_all	= inet->mc_all;
 	inet_sockopt.nodefrag	= inet->nodefrag;
 	inet_sockopt.bind_address_no_port = inet->bind_address_no_port;
-	inet_sockopt.recverr_rfc4884 = inet->recverr_rfc4884;
+	inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk);
 	inet_sockopt.defer_connect = inet->defer_connect;
 	if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt),
 		    &inet_sockopt))
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 8283d862a9dbb..f75f44ad7b11a 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -433,7 +433,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 	serr->port = port;
 
 	if (skb_pull(skb, payload - skb->data)) {
-		if (inet_sk(sk)->recverr_rfc4884)
+		if (inet_test_bit(RECVERR_RFC4884, sk))
 			ipv4_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884);
 
 		skb_reset_transport_header(skb);
@@ -980,6 +980,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		if (!val)
 			skb_queue_purge(&sk->sk_error_queue);
 		return 0;
+	case IP_RECVERR_RFC4884:
+		if (val < 0 || val > 1)
+			return -EINVAL;
+		inet_assign_bit(RECVERR_RFC4884, sk, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1066,11 +1071,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			goto e_inval;
 		inet->pmtudisc = val;
 		break;
-	case IP_RECVERR_RFC4884:
-		if (val < 0 || val > 1)
-			goto e_inval;
-		inet->recverr_rfc4884 = !!val;
-		break;
 	case IP_MULTICAST_TTL:
 		if (sk->sk_type == SOCK_STREAM)
 			goto e_inval;
@@ -1575,6 +1575,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_RECVERR:
 		val = inet_test_bit(RECVERR, sk);
 		goto copyval;
+	case IP_RECVERR_RFC4884:
+		val = inet_test_bit(RECVERR_RFC4884, sk);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1649,9 +1652,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		}
 		break;
 	}
-	case IP_RECVERR_RFC4884:
-		val = inet->recverr_rfc4884;
-		break;
 	case IP_MULTICAST_TTL:
 		val = inet->mc_ttl;
 		break;
-- 
GitLab


From 3f7e753206bb20fc098b44ec40001befd1fe18d1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:37 +0000
Subject: [PATCH 1264/1806] inet: move inet->freebind to inet->inet_flags

IP_FREEBIND socket option can now be set/read
without locking the socket.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h  |  5 +++--
 include/net/ipv6.h       |  3 ++-
 net/ipv4/inet_diag.c     |  2 +-
 net/ipv4/ip_sockglue.c   | 21 +++++++++------------
 net/ipv6/ipv6_sockglue.c |  4 ++--
 net/mptcp/sockopt.c      |  7 ++++---
 net/sctp/protocol.c      |  2 +-
 7 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index c01f1f64a8617..d6ba963534b4a 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -231,7 +231,6 @@ struct inet_sock {
 	__u8			mc_ttl;
 	__u8			pmtudisc;
 	__u8			is_icsk:1,
-				freebind:1,
 				hdrincl:1,
 				mc_loop:1,
 				transparent:1,
@@ -271,6 +270,7 @@ enum {
 
 	INET_FLAGS_RECVERR	= 9,
 	INET_FLAGS_RECVERR_RFC4884 = 10,
+	INET_FLAGS_FREEBIND	= 11,
 };
 
 /* cmsg flags for inet */
@@ -423,7 +423,8 @@ static inline bool inet_can_nonlocal_bind(struct net *net,
 					  struct inet_sock *inet)
 {
 	return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) ||
-		inet->freebind || inet->transparent;
+		test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) ||
+		inet->transparent;
 }
 
 static inline bool inet_addr_valid_or_nonlocal(struct net *net,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 22643ffc2df8c..fd570d77588e7 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -937,7 +937,8 @@ static inline bool ipv6_can_nonlocal_bind(struct net *net,
 					  struct inet_sock *inet)
 {
 	return net->ipv6.sysctl.ip_nonlocal_bind ||
-		inet->freebind || inet->transparent;
+		test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) ||
+		inet->transparent;
 }
 
 /* Sysctl settings for net ipv6.auto_flowlabels */
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 6255d6fdbc80d..5a96f4f28eca6 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -184,7 +184,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	memset(&inet_sockopt, 0, sizeof(inet_sockopt));
 	inet_sockopt.recverr	= inet_test_bit(RECVERR, sk);
 	inet_sockopt.is_icsk	= inet->is_icsk;
-	inet_sockopt.freebind	= inet->freebind;
+	inet_sockopt.freebind	= inet_test_bit(FREEBIND, sk);
 	inet_sockopt.hdrincl	= inet->hdrincl;
 	inet_sockopt.mc_loop	= inet->mc_loop;
 	inet_sockopt.transparent = inet->transparent;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index f75f44ad7b11a..6af8431063128 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -608,9 +608,7 @@ EXPORT_SYMBOL(ip_sock_set_tos);
 
 void ip_sock_set_freebind(struct sock *sk)
 {
-	lock_sock(sk);
-	inet_sk(sk)->freebind = true;
-	release_sock(sk);
+	inet_set_bit(FREEBIND, sk);
 }
 EXPORT_SYMBOL(ip_sock_set_freebind);
 
@@ -985,6 +983,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		inet_assign_bit(RECVERR_RFC4884, sk, val);
 		return 0;
+	case IP_FREEBIND:
+		if (optlen < 1)
+			return -EINVAL;
+		inet_assign_bit(FREEBIND, sk, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1310,12 +1313,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		inet->mc_all = val;
 		break;
 
-	case IP_FREEBIND:
-		if (optlen < 1)
-			goto e_inval;
-		inet->freebind = !!val;
-		break;
-
 	case IP_IPSEC_POLICY:
 	case IP_XFRM_POLICY:
 		err = -EPERM;
@@ -1578,6 +1575,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_RECVERR_RFC4884:
 		val = inet_test_bit(RECVERR_RFC4884, sk);
 		goto copyval;
+	case IP_FREEBIND:
+		val = inet_test_bit(FREEBIND, sk);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1737,9 +1737,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		len -= msg.msg_controllen;
 		return copy_to_sockptr(optlen, &len, sizeof(int));
 	}
-	case IP_FREEBIND:
-		val = inet->freebind;
-		break;
 	case IP_TRANSPARENT:
 		val = inet->transparent;
 		break;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index ca377159967c8..3eb38436f8d43 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -641,7 +641,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optlen < sizeof(int))
 			goto e_inval;
 		/* we also don't have a separate freebind bit for IPV6 */
-		inet_sk(sk)->freebind = valbool;
+		inet_assign_bit(FREEBIND, sk, valbool);
 		retv = 0;
 		break;
 
@@ -1334,7 +1334,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_FREEBIND:
-		val = inet_sk(sk)->freebind;
+		val = inet_test_bit(FREEBIND, sk);
 		break;
 
 	case IPV6_RECVORIGDSTADDR:
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 21bc46acbe38e..ffbe2f5f5b44c 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -419,7 +419,8 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 			inet_sk(sk)->transparent = inet_sk(ssk)->transparent;
 			break;
 		case IPV6_FREEBIND:
-			inet_sk(sk)->freebind = inet_sk(ssk)->freebind;
+			inet_assign_bit(FREEBIND, sk,
+					inet_test_bit(FREEBIND, ssk));
 			break;
 		}
 
@@ -704,7 +705,7 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o
 
 	switch (optname) {
 	case IP_FREEBIND:
-		issk->freebind = inet_sk(sk)->freebind;
+		inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
 		break;
 	case IP_TRANSPARENT:
 		issk->transparent = inet_sk(sk)->transparent;
@@ -1441,7 +1442,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 	__tcp_sock_set_nodelay(ssk, !!msk->nodelay);
 
 	inet_sk(ssk)->transparent = inet_sk(sk)->transparent;
-	inet_sk(ssk)->freebind = inet_sk(sk)->freebind;
+	inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
 }
 
 static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk)
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 33c0895e101c0..2185f44198deb 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -360,7 +360,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
 	ret = inet_addr_type_table(net, addr->v4.sin_addr.s_addr, tb_id);
 	if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
 	   ret != RTN_LOCAL &&
-	   !sp->inet.freebind &&
+	   !inet_test_bit(FREEBIND, sk) &&
 	    !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind))
 		return 0;
 
-- 
GitLab


From cafbe182a467bf6799242fd7468438cf1ab833dc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:38 +0000
Subject: [PATCH 1265/1806] inet: move inet->hdrincl to inet->inet_flags

IP_HDRINCL socket option can now be set/read
without locking the socket.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h |  4 ++--
 net/ipv4/af_inet.c      |  2 +-
 net/ipv4/inet_diag.c    |  2 +-
 net/ipv4/ip_output.c    |  5 +++--
 net/ipv4/ip_sockglue.c  | 18 ++++++++----------
 net/ipv4/raw.c          | 10 +++-------
 net/ipv4/route.c        |  8 ++++----
 net/ipv6/af_inet6.c     |  2 +-
 net/ipv6/ip6_output.c   |  5 +++--
 net/ipv6/raw.c          | 16 +++++-----------
 10 files changed, 31 insertions(+), 41 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index d6ba963534b4a..ad1895e32e7d9 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -231,7 +231,6 @@ struct inet_sock {
 	__u8			mc_ttl;
 	__u8			pmtudisc;
 	__u8			is_icsk:1,
-				hdrincl:1,
 				mc_loop:1,
 				transparent:1,
 				mc_all:1,
@@ -271,6 +270,7 @@ enum {
 	INET_FLAGS_RECVERR	= 9,
 	INET_FLAGS_RECVERR_RFC4884 = 10,
 	INET_FLAGS_FREEBIND	= 11,
+	INET_FLAGS_HDRINCL	= 12,
 };
 
 /* cmsg flags for inet */
@@ -397,7 +397,7 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
 {
 	__u8 flags = 0;
 
-	if (inet_sk(sk)->transparent || inet_sk(sk)->hdrincl)
+	if (inet_sk(sk)->transparent || inet_test_bit(HDRINCL, sk))
 		flags |= FLOWI_FLAG_ANYSRC;
 	return flags;
 }
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index c59da65f19d23..5785fe9de58c2 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -338,7 +338,7 @@ lookup_protocol:
 	if (SOCK_RAW == sock->type) {
 		inet->inet_num = protocol;
 		if (IPPROTO_RAW == protocol)
-			inet->hdrincl = 1;
+			inet_set_bit(HDRINCL, sk);
 	}
 
 	if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc))
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 5a96f4f28eca6..98f3eb0ce16ab 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -185,7 +185,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	inet_sockopt.recverr	= inet_test_bit(RECVERR, sk);
 	inet_sockopt.is_icsk	= inet->is_icsk;
 	inet_sockopt.freebind	= inet_test_bit(FREEBIND, sk);
-	inet_sockopt.hdrincl	= inet->hdrincl;
+	inet_sockopt.hdrincl	= inet_test_bit(HDRINCL, sk);
 	inet_sockopt.mc_loop	= inet->mc_loop;
 	inet_sockopt.transparent = inet->transparent;
 	inet_sockopt.mc_all	= inet->mc_all;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index f28c87533a465..8f396eada1b6e 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1039,7 +1039,7 @@ static int __ip_append_data(struct sock *sk,
 			}
 		}
 	} else if ((flags & MSG_SPLICE_PAGES) && length) {
-		if (inet->hdrincl)
+		if (inet_test_bit(HDRINCL, sk))
 			return -EPERM;
 		if (rt->dst.dev->features & NETIF_F_SG &&
 		    getfrag == ip_generic_getfrag)
@@ -1467,7 +1467,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 		 * so icmphdr does not in skb linear region and can not get icmp_type
 		 * by icmp_hdr(skb)->type.
 		 */
-		if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl)
+		if (sk->sk_type == SOCK_RAW &&
+		    !inet_test_bit(HDRINCL, sk))
 			icmp_type = fl4->fl4_icmp_type;
 		else
 			icmp_type = icmp_hdr(skb)->type;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 6af8431063128..763456fd4f4fa 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -988,6 +988,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		inet_assign_bit(FREEBIND, sk, val);
 		return 0;
+	case IP_HDRINCL:
+		if (sk->sk_type != SOCK_RAW)
+			return -ENOPROTOOPT;
+		inet_assign_bit(HDRINCL, sk, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1052,13 +1057,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			goto e_inval;
 		inet->uc_ttl = val;
 		break;
-	case IP_HDRINCL:
-		if (sk->sk_type != SOCK_RAW) {
-			err = -ENOPROTOOPT;
-			break;
-		}
-		inet->hdrincl = val ? 1 : 0;
-		break;
 	case IP_NODEFRAG:
 		if (sk->sk_type != SOCK_RAW) {
 			err = -ENOPROTOOPT;
@@ -1578,6 +1576,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_FREEBIND:
 		val = inet_test_bit(FREEBIND, sk);
 		goto copyval;
+	case IP_HDRINCL:
+		val = inet_test_bit(HDRINCL, sk);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1625,9 +1626,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		       inet->uc_ttl);
 		break;
 	}
-	case IP_HDRINCL:
-		val = inet->hdrincl;
-		break;
 	case IP_NODEFRAG:
 		val = inet->nodefrag;
 		break;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index f4c27dc5714bd..4b5db5d1edc27 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -251,7 +251,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 		const struct iphdr *iph = (const struct iphdr *)skb->data;
 		u8 *payload = skb->data + (iph->ihl << 2);
 
-		if (inet->hdrincl)
+		if (inet_test_bit(HDRINCL, sk))
 			payload = skb->data;
 		ip_icmp_error(sk, skb, err, 0, info, payload);
 	}
@@ -491,12 +491,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (len > 0xFFFF)
 		goto out;
 
-	/* hdrincl should be READ_ONCE(inet->hdrincl)
-	 * but READ_ONCE() doesn't work with bit fields.
-	 * Doing this indirectly yields the same result.
-	 */
-	hdrincl = inet->hdrincl;
-	hdrincl = READ_ONCE(hdrincl);
+	hdrincl = inet_test_bit(HDRINCL, sk);
+
 	/*
 	 *	Check the flags.
 	 */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 92fede388d520..a4e153dd615ba 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -515,13 +515,12 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
 	__u8 scope = RT_SCOPE_UNIVERSE;
 
 	if (sk) {
-		const struct inet_sock *inet = inet_sk(sk);
-
 		oif = sk->sk_bound_dev_if;
 		mark = READ_ONCE(sk->sk_mark);
 		tos = ip_sock_rt_tos(sk);
 		scope = ip_sock_rt_scope(sk);
-		prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol;
+		prot = inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW :
+						    sk->sk_protocol;
 	}
 
 	flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope,
@@ -555,7 +554,8 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
 	flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark),
 			   ip_sock_rt_tos(sk) & IPTOS_RT_MASK,
 			   ip_sock_rt_scope(sk),
-			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+			   inet_test_bit(HDRINCL, sk) ?
+				IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk),
 			   daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
 	rcu_read_unlock();
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3ec0359d5c1f1..ed9d207080ac8 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -205,7 +205,7 @@ lookup_protocol:
 	if (SOCK_RAW == sock->type) {
 		inet->inet_num = protocol;
 		if (IPPROTO_RAW == protocol)
-			inet->hdrincl = 1;
+			inet_set_bit(HDRINCL, sk);
 	}
 
 	sk->sk_destruct		= inet6_sock_destruct;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index bc96559bbf0f8..f8a1f6bb3f872 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1591,7 +1591,7 @@ emsgsize:
 			}
 		}
 	} else if ((flags & MSG_SPLICE_PAGES) && length) {
-		if (inet_sk(sk)->hdrincl)
+		if (inet_test_bit(HDRINCL, sk))
 			return -EPERM;
 		if (rt->dst.dev->features & NETIF_F_SG &&
 		    getfrag == ip_generic_getfrag)
@@ -1995,7 +1995,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 		u8 icmp6_type;
 
-		if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl)
+		if (sk->sk_socket->type == SOCK_RAW &&
+		   !inet_test_bit(HDRINCL, sk))
 			icmp6_type = fl6->fl6_icmp_type;
 		else
 			icmp6_type = icmp6_hdr(skb)->icmp6_type;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ea16734f5e1f7..0eae7661a85c4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -291,7 +291,6 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb,
 	       struct inet6_skb_parm *opt,
 	       u8 type, u8 code, int offset, __be32 info)
 {
-	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	int err;
 	int harderr;
@@ -315,7 +314,7 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb,
 	}
 	if (np->recverr) {
 		u8 *payload = skb->data;
-		if (!inet->hdrincl)
+		if (!inet_test_bit(HDRINCL, sk))
 			payload += offset;
 		ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload);
 	}
@@ -406,7 +405,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
 							 skb->len,
 							 inet->inet_num, 0));
 
-	if (inet->hdrincl) {
+	if (inet_test_bit(HDRINCL, sk)) {
 		if (skb_checksum_complete(skb)) {
 			atomic_inc(&sk->sk_drops);
 			kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM);
@@ -762,12 +761,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	/* hdrincl should be READ_ONCE(inet->hdrincl)
-	 * but READ_ONCE() doesn't work with bit fields.
-	 * Doing this indirectly yields the same result.
-	 */
-	hdrincl = inet->hdrincl;
-	hdrincl = READ_ONCE(hdrincl);
+	hdrincl = inet_test_bit(HDRINCL, sk);
 
 	/*
 	 *	Get and verify the address.
@@ -1000,7 +994,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
 	case IPV6_HDRINCL:
 		if (sk->sk_type != SOCK_RAW)
 			return -EINVAL;
-		inet_sk(sk)->hdrincl = !!val;
+		inet_assign_bit(HDRINCL, sk, val);
 		return 0;
 	case IPV6_CHECKSUM:
 		if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 &&
@@ -1068,7 +1062,7 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
 
 	switch (optname) {
 	case IPV6_HDRINCL:
-		val = inet_sk(sk)->hdrincl;
+		val = inet_test_bit(HDRINCL, sk);
 		break;
 	case IPV6_CHECKSUM:
 		/*
-- 
GitLab


From b09bde5c3554d58cb711dac55a10ecc56d436966 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:39 +0000
Subject: [PATCH 1266/1806] inet: move inet->mc_loop to inet->inet_frags

IP_MULTICAST_LOOP socket option can now be set/read
without locking the socket.

v3: fix build bot error reported in ipvs set_mcast_loop()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h         |  2 +-
 net/core/sock.c                 |  2 +-
 net/ipv4/af_inet.c              |  2 +-
 net/ipv4/inet_diag.c            |  2 +-
 net/ipv4/ip_sockglue.c          | 16 ++++++++--------
 net/ipv4/udp_tunnel_core.c      |  2 +-
 net/ipv6/af_inet6.c             |  2 +-
 net/netfilter/ipvs/ip_vs_sync.c |  4 +---
 net/sctp/socket.c               |  2 +-
 9 files changed, 16 insertions(+), 18 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index ad1895e32e7d9..6c4eeca59f608 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -231,7 +231,6 @@ struct inet_sock {
 	__u8			mc_ttl;
 	__u8			pmtudisc;
 	__u8			is_icsk:1,
-				mc_loop:1,
 				transparent:1,
 				mc_all:1,
 				nodefrag:1;
@@ -271,6 +270,7 @@ enum {
 	INET_FLAGS_RECVERR_RFC4884 = 10,
 	INET_FLAGS_FREEBIND	= 11,
 	INET_FLAGS_HDRINCL	= 12,
+	INET_FLAGS_MC_LOOP	= 13,
 };
 
 /* cmsg flags for inet */
diff --git a/net/core/sock.c b/net/core/sock.c
index 525619776c6f4..22d94394335fb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -767,7 +767,7 @@ bool sk_mc_loop(struct sock *sk)
 		return true;
 	switch (sk->sk_family) {
 	case AF_INET:
-		return inet_sk(sk)->mc_loop;
+		return inet_test_bit(MC_LOOP, sk);
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		return inet6_sk(sk)->mc_loop;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 5785fe9de58c2..e847822df9b61 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -356,7 +356,7 @@ lookup_protocol:
 	sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash);
 
 	inet->uc_ttl	= -1;
-	inet->mc_loop	= 1;
+	inet_set_bit(MC_LOOP, sk);
 	inet->mc_ttl	= 1;
 	inet->mc_all	= 1;
 	inet->mc_index	= 0;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 98f3eb0ce16ab..cc797261893b9 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -186,7 +186,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	inet_sockopt.is_icsk	= inet->is_icsk;
 	inet_sockopt.freebind	= inet_test_bit(FREEBIND, sk);
 	inet_sockopt.hdrincl	= inet_test_bit(HDRINCL, sk);
-	inet_sockopt.mc_loop	= inet->mc_loop;
+	inet_sockopt.mc_loop	= inet_test_bit(MC_LOOP, sk);
 	inet_sockopt.transparent = inet->transparent;
 	inet_sockopt.mc_all	= inet->mc_all;
 	inet_sockopt.nodefrag	= inet->nodefrag;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 763456fd4f4fa..be569032b612b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -993,6 +993,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			return -ENOPROTOOPT;
 		inet_assign_bit(HDRINCL, sk, val);
 		return 0;
+	case IP_MULTICAST_LOOP:
+		if (optlen < 1)
+			return -EINVAL;
+		inet_assign_bit(MC_LOOP, sk, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1083,11 +1088,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			goto e_inval;
 		inet->mc_ttl = val;
 		break;
-	case IP_MULTICAST_LOOP:
-		if (optlen < 1)
-			goto e_inval;
-		inet->mc_loop = !!val;
-		break;
 	case IP_UNICAST_IF:
 	{
 		struct net_device *dev = NULL;
@@ -1579,6 +1579,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_HDRINCL:
 		val = inet_test_bit(HDRINCL, sk);
 		goto copyval;
+	case IP_MULTICAST_LOOP:
+		val = inet_test_bit(MC_LOOP, sk);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1653,9 +1656,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_MULTICAST_TTL:
 		val = inet->mc_ttl;
 		break;
-	case IP_MULTICAST_LOOP:
-		val = inet->mc_loop;
-		break;
 	case IP_UNICAST_IF:
 		val = (__force int)htonl((__u32) inet->uc_index);
 		break;
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index 5f8104cf082d0..9b18f371af0d4 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -63,7 +63,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 	struct sock *sk = sock->sk;
 
 	/* Disable multicast loopback */
-	inet_sk(sk)->mc_loop = 0;
+	inet_clear_bit(MC_LOOP, sk);
 
 	/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
 	inet_inc_convert_csum(sk);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index ed9d207080ac8..8e9d4c1f0e837 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -229,7 +229,7 @@ lookup_protocol:
 	 */
 	inet->uc_ttl	= -1;
 
-	inet->mc_loop	= 1;
+	inet_set_bit(MC_LOOP, sk);
 	inet->mc_ttl	= 1;
 	inet->mc_index	= 0;
 	RCU_INIT_POINTER(inet->mc_list, NULL);
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 264f2f87a4376..da5af28ff57b5 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1297,11 +1297,9 @@ static void set_sock_size(struct sock *sk, int mode, int val)
  */
 static void set_mcast_loop(struct sock *sk, u_char loop)
 {
-	struct inet_sock *inet = inet_sk(sk);
-
 	/* setsockopt(sock, SOL_IP, IP_MULTICAST_LOOP, &loop, sizeof(loop)); */
 	lock_sock(sk);
-	inet->mc_loop = loop ? 1 : 0;
+	inet_assign_bit(MC_LOOP, sk, loop);
 #ifdef CONFIG_IP_VS_IPV6
 	if (sk->sk_family == AF_INET6) {
 		struct ipv6_pinfo *np = inet6_sk(sk);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6e3d28aa587cd..04b390892827b 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -9482,7 +9482,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->inet_id = get_random_u16();
 
 	newinet->uc_ttl = inet->uc_ttl;
-	newinet->mc_loop = 1;
+	inet_set_bit(MC_LOOP, newsk);
 	newinet->mc_ttl = 1;
 	newinet->mc_index = 0;
 	newinet->mc_list = NULL;
-- 
GitLab


From 307b4ac6dc18436076cdd314aa3e556be077bf2d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:40 +0000
Subject: [PATCH 1267/1806] inet: move inet->mc_all to inet->inet_frags

IP_MULTICAST_ALL socket option can now be set/read
without locking the socket.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h |  2 +-
 net/ipv4/af_inet.c      |  2 +-
 net/ipv4/igmp.c         |  2 +-
 net/ipv4/inet_diag.c    |  2 +-
 net/ipv4/ip_sockglue.c  | 22 +++++++++++-----------
 5 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 6c4eeca59f608..fffd34fa6a7cb 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -232,7 +232,6 @@ struct inet_sock {
 	__u8			pmtudisc;
 	__u8			is_icsk:1,
 				transparent:1,
-				mc_all:1,
 				nodefrag:1;
 	__u8			bind_address_no_port:1,
 				defer_connect:1; /* Indicates that fastopen_connect is set
@@ -271,6 +270,7 @@ enum {
 	INET_FLAGS_FREEBIND	= 11,
 	INET_FLAGS_HDRINCL	= 12,
 	INET_FLAGS_MC_LOOP	= 13,
+	INET_FLAGS_MC_ALL	= 14,
 };
 
 /* cmsg flags for inet */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e847822df9b61..47c9cdd7687f9 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -358,7 +358,7 @@ lookup_protocol:
 	inet->uc_ttl	= -1;
 	inet_set_bit(MC_LOOP, sk);
 	inet->mc_ttl	= 1;
-	inet->mc_all	= 1;
+	inet_set_bit(MC_ALL, sk);
 	inet->mc_index	= 0;
 	inet->mc_list	= NULL;
 	inet->rcv_tos	= 0;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 48ff5f13e7979..0c9e768e5628b 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2658,7 +2658,7 @@ int ip_mc_sf_allow(const struct sock *sk, __be32 loc_addr, __be32 rmt_addr,
 		     (sdif && pmc->multi.imr_ifindex == sdif)))
 			break;
 	}
-	ret = inet->mc_all;
+	ret = inet_test_bit(MC_ALL, sk);
 	if (!pmc)
 		goto unlock;
 	psl = rcu_dereference(pmc->sflist);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index cc797261893b9..e009dab80c354 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -188,7 +188,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	inet_sockopt.hdrincl	= inet_test_bit(HDRINCL, sk);
 	inet_sockopt.mc_loop	= inet_test_bit(MC_LOOP, sk);
 	inet_sockopt.transparent = inet->transparent;
-	inet_sockopt.mc_all	= inet->mc_all;
+	inet_sockopt.mc_all	= inet_test_bit(MC_ALL, sk);
 	inet_sockopt.nodefrag	= inet->nodefrag;
 	inet_sockopt.bind_address_no_port = inet->bind_address_no_port;
 	inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index be569032b612b..2f27c30a4eccc 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -998,6 +998,14 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		inet_assign_bit(MC_LOOP, sk, val);
 		return 0;
+	case IP_MULTICAST_ALL:
+		if (optlen < 1)
+			return -EINVAL;
+		if (val != 0 && val != 1)
+			return -EINVAL;
+		inet_assign_bit(MC_ALL, sk, val);
+		return 0;
+
 	}
 
 	err = 0;
@@ -1303,14 +1311,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		else
 			err = ip_set_mcast_msfilter(sk, optval, optlen);
 		break;
-	case IP_MULTICAST_ALL:
-		if (optlen < 1)
-			goto e_inval;
-		if (val != 0 && val != 1)
-			goto e_inval;
-		inet->mc_all = val;
-		break;
-
 	case IP_IPSEC_POLICY:
 	case IP_XFRM_POLICY:
 		err = -EPERM;
@@ -1582,6 +1582,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_MULTICAST_LOOP:
 		val = inet_test_bit(MC_LOOP, sk);
 		goto copyval;
+	case IP_MULTICAST_ALL:
+		val = inet_test_bit(MC_ALL, sk);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1694,9 +1697,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		else
 			err = ip_get_mcast_msfilter(sk, optval, optlen, len);
 		goto out;
-	case IP_MULTICAST_ALL:
-		val = inet->mc_all;
-		break;
 	case IP_PKTOPTIONS:
 	{
 		struct msghdr msg;
-- 
GitLab


From 4bd0623f04eef65c0a324000fad73c4d3a677f8e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:41 +0000
Subject: [PATCH 1268/1806] inet: move inet->transparent to inet->inet_flags

IP_TRANSPARENT socket option can now be set/read
without locking the socket.

v2: removed unused issk variable in mptcp_setsockopt_sol_ip_set_transparent()
v4: rebased after commit 3f326a821b99 ("mptcp: change the mpc check helper to return a sk")

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h       |  6 +++---
 include/net/ipv6.h            |  2 +-
 include/net/route.h           |  2 +-
 include/net/tcp.h             |  2 +-
 net/ipv4/inet_diag.c          |  2 +-
 net/ipv4/inet_timewait_sock.c |  2 +-
 net/ipv4/ip_sockglue.c        | 28 +++++++++++++---------------
 net/ipv4/tcp_input.c          |  2 +-
 net/ipv4/tcp_minisocks.c      |  3 +--
 net/ipv6/ipv6_sockglue.c      |  4 ++--
 net/mptcp/sockopt.c           | 11 +++++------
 11 files changed, 30 insertions(+), 34 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index fffd34fa6a7cb..cefd9a60dc6d8 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -231,7 +231,6 @@ struct inet_sock {
 	__u8			mc_ttl;
 	__u8			pmtudisc;
 	__u8			is_icsk:1,
-				transparent:1,
 				nodefrag:1;
 	__u8			bind_address_no_port:1,
 				defer_connect:1; /* Indicates that fastopen_connect is set
@@ -271,6 +270,7 @@ enum {
 	INET_FLAGS_HDRINCL	= 12,
 	INET_FLAGS_MC_LOOP	= 13,
 	INET_FLAGS_MC_ALL	= 14,
+	INET_FLAGS_TRANSPARENT	= 15,
 };
 
 /* cmsg flags for inet */
@@ -397,7 +397,7 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
 {
 	__u8 flags = 0;
 
-	if (inet_sk(sk)->transparent || inet_test_bit(HDRINCL, sk))
+	if (inet_test_bit(TRANSPARENT, sk) || inet_test_bit(HDRINCL, sk))
 		flags |= FLOWI_FLAG_ANYSRC;
 	return flags;
 }
@@ -424,7 +424,7 @@ static inline bool inet_can_nonlocal_bind(struct net *net,
 {
 	return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) ||
 		test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) ||
-		inet->transparent;
+		test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags);
 }
 
 static inline bool inet_addr_valid_or_nonlocal(struct net *net,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index fd570d77588e7..d40d8238d4c2b 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -938,7 +938,7 @@ static inline bool ipv6_can_nonlocal_bind(struct net *net,
 {
 	return net->ipv6.sysctl.ip_nonlocal_bind ||
 		test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) ||
-		inet->transparent;
+		test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags);
 }
 
 /* Sysctl settings for net ipv6.auto_flowlabels */
diff --git a/include/net/route.h b/include/net/route.h
index d9ca98d2366ff..51a45b1887b56 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -298,7 +298,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
 {
 	__u8 flow_flags = 0;
 
-	if (inet_sk(sk)->transparent)
+	if (inet_test_bit(TRANSPARENT, sk))
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
 	flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk),
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6d77c08d83b76..07b21d9a96207 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2031,7 +2031,7 @@ static inline bool inet_sk_transparent(const struct sock *sk)
 	case TCP_NEW_SYN_RECV:
 		return inet_rsk(inet_reqsk(sk))->no_srccheck;
 	}
-	return inet_sk(sk)->transparent;
+	return inet_test_bit(TRANSPARENT, sk);
 }
 
 /* Determines whether this is a thin stream (which may suffer from
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index e009dab80c354..45fefd2f31fd7 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -187,7 +187,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	inet_sockopt.freebind	= inet_test_bit(FREEBIND, sk);
 	inet_sockopt.hdrincl	= inet_test_bit(HDRINCL, sk);
 	inet_sockopt.mc_loop	= inet_test_bit(MC_LOOP, sk);
-	inet_sockopt.transparent = inet->transparent;
+	inet_sockopt.transparent = inet_test_bit(TRANSPARENT, sk);
 	inet_sockopt.mc_all	= inet_test_bit(MC_ALL, sk);
 	inet_sockopt.nodefrag	= inet->nodefrag;
 	inet_sockopt.bind_address_no_port = inet->bind_address_no_port;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 2c1b245dba8e8..dd37a5bf68811 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -203,7 +203,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 		tw->tw_reuseport    = sk->sk_reuseport;
 		tw->tw_hash	    = sk->sk_hash;
 		tw->tw_ipv6only	    = 0;
-		tw->tw_transparent  = inet->transparent;
+		tw->tw_transparent  = inet_test_bit(TRANSPARENT, sk);
 		tw->tw_prot	    = sk->sk_prot_creator;
 		atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
 		twsk_net_set(tw, sock_net(sk));
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 2f27c30a4eccc..3f5323a230b3d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1005,7 +1005,16 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		inet_assign_bit(MC_ALL, sk, val);
 		return 0;
-
+	case IP_TRANSPARENT:
+		if (!!val && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+			err = -EPERM;
+			break;
+		}
+		if (optlen < 1)
+			goto e_inval;
+		inet_assign_bit(TRANSPARENT, sk, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1319,17 +1328,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		err = xfrm_user_policy(sk, optname, optval, optlen);
 		break;
 
-	case IP_TRANSPARENT:
-		if (!!val && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
-			err = -EPERM;
-			break;
-		}
-		if (optlen < 1)
-			goto e_inval;
-		inet->transparent = !!val;
-		break;
-
 	case IP_MINTTL:
 		if (optlen < 1)
 			goto e_inval;
@@ -1585,6 +1583,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_MULTICAST_ALL:
 		val = inet_test_bit(MC_ALL, sk);
 		goto copyval;
+	case IP_TRANSPARENT:
+		val = inet_test_bit(TRANSPARENT, sk);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1735,9 +1736,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		len -= msg.msg_controllen;
 		return copy_to_sockptr(optlen, &len, sizeof(int));
 	}
-	case IP_TRANSPARENT:
-		val = inet->transparent;
-		break;
 	case IP_MINTTL:
 		val = inet->min_ttl;
 		break;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d34d52fdfdb1e..06fe1cf645d5a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -7000,7 +7000,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
 	tcp_openreq_init(req, &tmp_opt, skb, sk);
-	inet_rsk(req)->no_srccheck = inet_sk(sk)->transparent;
+	inet_rsk(req)->no_srccheck = inet_test_bit(TRANSPARENT, sk);
 
 	/* Note: tcp_v6_init_req() might override ir_iif for link locals */
 	inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 13ee12983c429..b98d476f1594b 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -289,9 +289,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 	if (tw) {
 		struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 		const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
-		struct inet_sock *inet = inet_sk(sk);
 
-		tw->tw_transparent	= inet->transparent;
+		tw->tw_transparent	= inet_test_bit(TRANSPARENT, sk);
 		tw->tw_mark		= sk->sk_mark;
 		tw->tw_priority		= sk->sk_priority;
 		tw->tw_rcv_wscale	= tp->rx_opt.rcv_wscale;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 3eb38436f8d43..eb334122512c2 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -633,7 +633,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optlen < sizeof(int))
 			goto e_inval;
 		/* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */
-		inet_sk(sk)->transparent = valbool;
+		inet_assign_bit(TRANSPARENT, sk, valbool);
 		retv = 0;
 		break;
 
@@ -1330,7 +1330,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	}
 
 	case IPV6_TRANSPARENT:
-		val = inet_sk(sk)->transparent;
+		val = inet_test_bit(TRANSPARENT, sk);
 		break;
 
 	case IPV6_FREEBIND:
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index ffbe2f5f5b44c..8260202c00669 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -416,7 +416,8 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 			sk->sk_ipv6only = ssk->sk_ipv6only;
 			break;
 		case IPV6_TRANSPARENT:
-			inet_sk(sk)->transparent = inet_sk(ssk)->transparent;
+			inet_assign_bit(TRANSPARENT, sk,
+					inet_test_bit(TRANSPARENT, ssk));
 			break;
 		case IPV6_FREEBIND:
 			inet_assign_bit(FREEBIND, sk,
@@ -685,7 +686,6 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o
 						   sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = (struct sock *)msk;
-	struct inet_sock *issk;
 	struct sock *ssk;
 	int err;
 
@@ -701,14 +701,13 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o
 		return PTR_ERR(ssk);
 	}
 
-	issk = inet_sk(ssk);
-
 	switch (optname) {
 	case IP_FREEBIND:
 		inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
 		break;
 	case IP_TRANSPARENT:
-		issk->transparent = inet_sk(sk)->transparent;
+		inet_assign_bit(TRANSPARENT, ssk,
+				inet_test_bit(TRANSPARENT, sk));
 		break;
 	default:
 		release_sock(sk);
@@ -1441,7 +1440,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 	__tcp_sock_set_cork(ssk, !!msk->cork);
 	__tcp_sock_set_nodelay(ssk, !!msk->nodelay);
 
-	inet_sk(ssk)->transparent = inet_sk(sk)->transparent;
+	inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk));
 	inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
 }
 
-- 
GitLab


From b1c0356a58577ce0a583e3044bf801877fc0b5de Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:42 +0000
Subject: [PATCH 1269/1806] inet: move inet->is_icsk to inet->inet_flags

We move single bit fields to inet->inet_flags to avoid races.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h | 4 ++--
 include/net/inet_sock.h            | 5 ++---
 net/ipv4/af_inet.c                 | 2 +-
 net/ipv4/cipso_ipv4.c              | 4 ++--
 net/ipv4/inet_diag.c               | 2 +-
 net/ipv4/ip_sockglue.c             | 4 ++--
 net/ipv6/af_inet6.c                | 2 +-
 net/ipv6/ipv6_sockglue.c           | 4 ++--
 8 files changed, 13 insertions(+), 14 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index be3c858a2ebb7..5d2fcc137b881 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -342,9 +342,9 @@ static inline bool inet_csk_in_pingpong_mode(struct sock *sk)
 	return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH;
 }
 
-static inline bool inet_csk_has_ulp(struct sock *sk)
+static inline bool inet_csk_has_ulp(const struct sock *sk)
 {
-	return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops;
+	return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops;
 }
 
 #endif /* _INET_CONNECTION_SOCK_H */
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index cefd9a60dc6d8..38f7fc1c4dacf 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -201,7 +201,6 @@ struct rtable;
  * @inet_id - ID counter for DF pkts
  * @tos - TOS
  * @mc_ttl - Multicasting TTL
- * @is_icsk - is this an inet_connection_sock?
  * @uc_index - Unicast outgoing device index
  * @mc_index - Multicast device index
  * @mc_list - Group array
@@ -230,8 +229,7 @@ struct inet_sock {
 	__u8			min_ttl;
 	__u8			mc_ttl;
 	__u8			pmtudisc;
-	__u8			is_icsk:1,
-				nodefrag:1;
+	__u8			nodefrag:1;
 	__u8			bind_address_no_port:1,
 				defer_connect:1; /* Indicates that fastopen_connect is set
 						  * and cookie exists so we defer connect
@@ -271,6 +269,7 @@ enum {
 	INET_FLAGS_MC_LOOP	= 13,
 	INET_FLAGS_MC_ALL	= 14,
 	INET_FLAGS_TRANSPARENT	= 15,
+	INET_FLAGS_IS_ICSK	= 16,
 };
 
 /* cmsg flags for inet */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 47c9cdd7687f9..0f46b71f8a989 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -331,7 +331,7 @@ lookup_protocol:
 		sk->sk_reuse = SK_CAN_REUSE;
 
 	inet = inet_sk(sk);
-	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
+	inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
 
 	inet->nodefrag = 0;
 
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 79ae7204e8edb..d048aa8332938 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1881,7 +1881,7 @@ int cipso_v4_sock_setattr(struct sock *sk,
 
 	old = rcu_dereference_protected(sk_inet->inet_opt,
 					lockdep_sock_is_held(sk));
-	if (sk_inet->is_icsk) {
+	if (inet_test_bit(IS_ICSK, sk)) {
 		sk_conn = inet_csk(sk);
 		if (old)
 			sk_conn->icsk_ext_hdr_len -= old->opt.optlen;
@@ -2051,7 +2051,7 @@ void cipso_v4_sock_delattr(struct sock *sk)
 	sk_inet = inet_sk(sk);
 
 	hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt);
-	if (sk_inet->is_icsk && hdr_delta > 0) {
+	if (inet_test_bit(IS_ICSK, sk) && hdr_delta > 0) {
 		struct inet_connection_sock *sk_conn = inet_csk(sk);
 		sk_conn->icsk_ext_hdr_len -= hdr_delta;
 		sk_conn->icsk_sync_mss(sk, sk_conn->icsk_pmtu_cookie);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 45fefd2f31fd7..ada198fc1a92b 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -183,7 +183,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 
 	memset(&inet_sockopt, 0, sizeof(inet_sockopt));
 	inet_sockopt.recverr	= inet_test_bit(RECVERR, sk);
-	inet_sockopt.is_icsk	= inet->is_icsk;
+	inet_sockopt.is_icsk	= inet_test_bit(IS_ICSK, sk);
 	inet_sockopt.freebind	= inet_test_bit(FREEBIND, sk);
 	inet_sockopt.hdrincl	= inet_test_bit(HDRINCL, sk);
 	inet_sockopt.mc_loop	= inet_test_bit(MC_LOOP, sk);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 3f5323a230b3d..dac471ed067b4 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1034,7 +1034,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			break;
 		old = rcu_dereference_protected(inet->inet_opt,
 						lockdep_sock_is_held(sk));
-		if (inet->is_icsk) {
+		if (inet_test_bit(IS_ICSK, sk)) {
 			struct inet_connection_sock *icsk = inet_csk(sk);
 #if IS_ENABLED(CONFIG_IPV6)
 			if (sk->sk_family == PF_INET ||
@@ -1209,7 +1209,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		struct ip_mreqn mreq;
 
 		err = -EPROTO;
-		if (inet_sk(sk)->is_icsk)
+		if (inet_test_bit(IS_ICSK, sk))
 			break;
 
 		if (optlen < sizeof(struct ip_mreq))
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8e9d4c1f0e837..d8c56c7aba960 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -200,7 +200,7 @@ lookup_protocol:
 		sk->sk_reuse = SK_CAN_REUSE;
 
 	inet = inet_sk(sk);
-	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
+	inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
 
 	if (SOCK_RAW == sock->type) {
 		inet->inet_num = protocol;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index eb334122512c2..d19577a94bcc6 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -102,7 +102,7 @@ int ip6_ra_control(struct sock *sk, int sel)
 struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
 					   struct ipv6_txoptions *opt)
 {
-	if (inet_sk(sk)->is_icsk) {
+	if (inet_test_bit(IS_ICSK, sk)) {
 		if (opt &&
 		    !((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
 		    inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) {
@@ -831,7 +831,7 @@ done:
 			goto e_inval;
 
 		retv = -EPROTO;
-		if (inet_sk(sk)->is_icsk)
+		if (inet_test_bit(IS_ICSK, sk))
 			break;
 
 		retv = -EFAULT;
-- 
GitLab


From f04b8d3478a3a63f17d8dc0dc6da16a828b48df0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:43 +0000
Subject: [PATCH 1270/1806] inet: move inet->nodefrag to inet->inet_flags

IP_NODEFRAG socket option can now be set/read
without locking the socket.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h             |  2 +-
 net/ipv4/af_inet.c                  |  2 +-
 net/ipv4/inet_diag.c                |  2 +-
 net/ipv4/ip_sockglue.c              | 18 ++++++++----------
 net/ipv4/netfilter/nf_defrag_ipv4.c |  2 +-
 net/netfilter/ipvs/ip_vs_core.c     |  4 ++--
 6 files changed, 14 insertions(+), 16 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 38f7fc1c4dacf..0e6e1b017efb1 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -229,7 +229,6 @@ struct inet_sock {
 	__u8			min_ttl;
 	__u8			mc_ttl;
 	__u8			pmtudisc;
-	__u8			nodefrag:1;
 	__u8			bind_address_no_port:1,
 				defer_connect:1; /* Indicates that fastopen_connect is set
 						  * and cookie exists so we defer connect
@@ -270,6 +269,7 @@ enum {
 	INET_FLAGS_MC_ALL	= 14,
 	INET_FLAGS_TRANSPARENT	= 15,
 	INET_FLAGS_IS_ICSK	= 16,
+	INET_FLAGS_NODEFRAG	= 17,
 };
 
 /* cmsg flags for inet */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0f46b71f8a989..2fb9948b5230b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -333,7 +333,7 @@ lookup_protocol:
 	inet = inet_sk(sk);
 	inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
 
-	inet->nodefrag = 0;
+	inet_clear_bit(NODEFRAG, sk);
 
 	if (SOCK_RAW == sock->type) {
 		inet->inet_num = protocol;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index ada198fc1a92b..39606caad484a 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -189,7 +189,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	inet_sockopt.mc_loop	= inet_test_bit(MC_LOOP, sk);
 	inet_sockopt.transparent = inet_test_bit(TRANSPARENT, sk);
 	inet_sockopt.mc_all	= inet_test_bit(MC_ALL, sk);
-	inet_sockopt.nodefrag	= inet->nodefrag;
+	inet_sockopt.nodefrag	= inet_test_bit(NODEFRAG, sk);
 	inet_sockopt.bind_address_no_port = inet->bind_address_no_port;
 	inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk);
 	inet_sockopt.defer_connect = inet->defer_connect;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index dac471ed067b4..ec946c13ea206 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1015,6 +1015,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			goto e_inval;
 		inet_assign_bit(TRANSPARENT, sk, val);
 		return 0;
+	case IP_NODEFRAG:
+		if (sk->sk_type != SOCK_RAW)
+			return -ENOPROTOOPT;
+		inet_assign_bit(NODEFRAG, sk, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1079,13 +1084,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			goto e_inval;
 		inet->uc_ttl = val;
 		break;
-	case IP_NODEFRAG:
-		if (sk->sk_type != SOCK_RAW) {
-			err = -ENOPROTOOPT;
-			break;
-		}
-		inet->nodefrag = val ? 1 : 0;
-		break;
 	case IP_BIND_ADDRESS_NO_PORT:
 		inet->bind_address_no_port = val ? 1 : 0;
 		break;
@@ -1586,6 +1584,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_TRANSPARENT:
 		val = inet_test_bit(TRANSPARENT, sk);
 		goto copyval;
+	case IP_NODEFRAG:
+		val = inet_test_bit(NODEFRAG, sk);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1633,9 +1634,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		       inet->uc_ttl);
 		break;
 	}
-	case IP_NODEFRAG:
-		val = inet->nodefrag;
-		break;
 	case IP_BIND_ADDRESS_NO_PORT:
 		val = inet->bind_address_no_port;
 		break;
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index a9ba7de092c42..265b39bc435b4 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -66,7 +66,7 @@ static unsigned int ipv4_conntrack_defrag(void *priv,
 	struct sock *sk = skb->sk;
 
 	if (sk && sk_fullsock(sk) && (sk->sk_family == PF_INET) &&
-	    inet_sk(sk)->nodefrag)
+	    inet_test_bit(NODEFRAG, sk))
 		return NF_ACCEPT;
 
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index cb83ca506c5c9..3230506ae3ffd 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1346,7 +1346,7 @@ ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat
 	if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT &&
 		     af == AF_INET)) {
 
-		if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag)
+		if (sk->sk_family == PF_INET && inet_test_bit(NODEFRAG, sk))
 			return NF_ACCEPT;
 	}
 
@@ -1946,7 +1946,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state
 	if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT &&
 		     af == AF_INET)) {
 
-		if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag)
+		if (sk->sk_family == PF_INET && inet_test_bit(NODEFRAG, sk))
 			return NF_ACCEPT;
 	}
 
-- 
GitLab


From ca571e2eb7eb6202aa367e01c811aab023272f38 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:44 +0000
Subject: [PATCH 1271/1806] inet: move inet->bind_address_no_port to
 inet->inet_flags

IP_BIND_ADDRESS_NO_PORT socket option can now be set/read
without locking the socket.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h |  4 ++--
 net/ipv4/af_inet.c      |  2 +-
 net/ipv4/inet_diag.c    |  2 +-
 net/ipv4/ip_sockglue.c  | 12 ++++++------
 net/ipv6/af_inet6.c     |  2 +-
 5 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 0e6e1b017efb1..5eca2e70cbb2c 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -229,8 +229,7 @@ struct inet_sock {
 	__u8			min_ttl;
 	__u8			mc_ttl;
 	__u8			pmtudisc;
-	__u8			bind_address_no_port:1,
-				defer_connect:1; /* Indicates that fastopen_connect is set
+	__u8			defer_connect:1; /* Indicates that fastopen_connect is set
 						  * and cookie exists so we defer connect
 						  * until first data frame is written
 						  */
@@ -270,6 +269,7 @@ enum {
 	INET_FLAGS_TRANSPARENT	= 15,
 	INET_FLAGS_IS_ICSK	= 16,
 	INET_FLAGS_NODEFRAG	= 17,
+	INET_FLAGS_BIND_ADDRESS_NO_PORT = 18,
 };
 
 /* cmsg flags for inet */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 2fb9948b5230b..26e7cd9cb0591 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -529,7 +529,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 		inet->inet_saddr = 0;  /* Use device */
 
 	/* Make sure we are allowed to bind here. */
-	if (snum || !(inet->bind_address_no_port ||
+	if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) ||
 		      (flags & BIND_FORCE_ADDRESS_NO_PORT))) {
 		err = sk->sk_prot->get_port(sk, snum);
 		if (err) {
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 39606caad484a..128966dea5540 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -190,7 +190,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	inet_sockopt.transparent = inet_test_bit(TRANSPARENT, sk);
 	inet_sockopt.mc_all	= inet_test_bit(MC_ALL, sk);
 	inet_sockopt.nodefrag	= inet_test_bit(NODEFRAG, sk);
-	inet_sockopt.bind_address_no_port = inet->bind_address_no_port;
+	inet_sockopt.bind_address_no_port = inet_test_bit(BIND_ADDRESS_NO_PORT, sk);
 	inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk);
 	inet_sockopt.defer_connect = inet->defer_connect;
 	if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt),
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index ec946c13ea206..cfa65a0b0900f 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1020,6 +1020,9 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			return -ENOPROTOOPT;
 		inet_assign_bit(NODEFRAG, sk, val);
 		return 0;
+	case IP_BIND_ADDRESS_NO_PORT:
+		inet_assign_bit(BIND_ADDRESS_NO_PORT, sk, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1084,9 +1087,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			goto e_inval;
 		inet->uc_ttl = val;
 		break;
-	case IP_BIND_ADDRESS_NO_PORT:
-		inet->bind_address_no_port = val ? 1 : 0;
-		break;
 	case IP_MTU_DISCOVER:
 		if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
 			goto e_inval;
@@ -1587,6 +1587,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_NODEFRAG:
 		val = inet_test_bit(NODEFRAG, sk);
 		goto copyval;
+	case IP_BIND_ADDRESS_NO_PORT:
+		val = inet_test_bit(BIND_ADDRESS_NO_PORT, sk);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1634,9 +1637,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		       inet->uc_ttl);
 		break;
 	}
-	case IP_BIND_ADDRESS_NO_PORT:
-		val = inet->bind_address_no_port;
-		break;
 	case IP_MTU_DISCOVER:
 		val = inet->pmtudisc;
 		break;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d8c56c7aba960..368824fe9719f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -399,7 +399,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 		sk->sk_ipv6only = 1;
 
 	/* Make sure we are allowed to bind here. */
-	if (snum || !(inet->bind_address_no_port ||
+	if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) ||
 		      (flags & BIND_FORCE_ADDRESS_NO_PORT))) {
 		err = sk->sk_prot->get_port(sk, snum);
 		if (err) {
-- 
GitLab


From 08e39c0dfa29f233f5a621f7d274b793a080c769 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:45 +0000
Subject: [PATCH 1272/1806] inet: move inet->defer_connect to inet->inet_flags

Make room in struct inet_sock by removing this bit field,
using one available bit in inet_flags instead.

Also move local_port_range to fill the resulting hole,
saving 8 bytes on 64bit arches.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h | 10 ++++------
 net/ipv4/af_inet.c      |  4 ++--
 net/ipv4/inet_diag.c    |  2 +-
 net/ipv4/tcp.c          | 12 +++++++-----
 net/ipv4/tcp_fastopen.c |  2 +-
 net/mptcp/protocol.c    | 10 ++++++----
 6 files changed, 21 insertions(+), 19 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 5eca2e70cbb2c..acbb93d7607ab 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -229,21 +229,18 @@ struct inet_sock {
 	__u8			min_ttl;
 	__u8			mc_ttl;
 	__u8			pmtudisc;
-	__u8			defer_connect:1; /* Indicates that fastopen_connect is set
-						  * and cookie exists so we defer connect
-						  * until first data frame is written
-						  */
 	__u8			rcv_tos;
 	__u8			convert_csum;
 	int			uc_index;
 	int			mc_index;
 	__be32			mc_addr;
-	struct ip_mc_socklist __rcu	*mc_list;
-	struct inet_cork_full	cork;
 	struct {
 		__u16 lo;
 		__u16 hi;
 	}			local_port_range;
+
+	struct ip_mc_socklist __rcu	*mc_list;
+	struct inet_cork_full	cork;
 };
 
 #define IPCORK_OPT	1	/* ip-options has been held in ipcork.opt */
@@ -270,6 +267,7 @@ enum {
 	INET_FLAGS_IS_ICSK	= 16,
 	INET_FLAGS_NODEFRAG	= 17,
 	INET_FLAGS_BIND_ADDRESS_NO_PORT = 18,
+	INET_FLAGS_DEFER_CONNECT = 19,
 };
 
 /* cmsg flags for inet */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 26e7cd9cb0591..e07ee60625d91 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -656,7 +656,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		err = -EISCONN;
 		goto out;
 	case SS_CONNECTING:
-		if (inet_sk(sk)->defer_connect)
+		if (inet_test_bit(DEFER_CONNECT, sk))
 			err = is_sendmsg ? -EINPROGRESS : -EISCONN;
 		else
 			err = -EALREADY;
@@ -679,7 +679,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 
 		sock->state = SS_CONNECTING;
 
-		if (!err && inet_sk(sk)->defer_connect)
+		if (!err && inet_test_bit(DEFER_CONNECT, sk))
 			goto out;
 
 		/* Just entered SS_CONNECTING state; the only
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 128966dea5540..e13a84433413e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -192,7 +192,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	inet_sockopt.nodefrag	= inet_test_bit(NODEFRAG, sk);
 	inet_sockopt.bind_address_no_port = inet_test_bit(BIND_ADDRESS_NO_PORT, sk);
 	inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk);
-	inet_sockopt.defer_connect = inet->defer_connect;
+	inet_sockopt.defer_connect = inet_test_bit(DEFER_CONNECT, sk);
 	if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt),
 		    &inet_sockopt))
 		goto errout;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4fbc7ff8c53c0..cee1e548660cb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -583,7 +583,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 		if (urg_data & TCP_URG_VALID)
 			mask |= EPOLLPRI;
-	} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
+	} else if (state == TCP_SYN_SENT &&
+		   inet_test_bit(DEFER_CONNECT, sk)) {
 		/* Active TCP fastopen socket with defer_connect
 		 * Return EPOLLOUT so application can call write()
 		 * in order for kernel to generate SYN+data
@@ -1007,7 +1008,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
 	tp->fastopen_req->size = size;
 	tp->fastopen_req->uarg = uarg;
 
-	if (inet->defer_connect) {
+	if (inet_test_bit(DEFER_CONNECT, sk)) {
 		err = tcp_connect(sk);
 		/* Same failure procedure as in tcp_v4/6_connect */
 		if (err) {
@@ -1025,7 +1026,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
 	if (tp->fastopen_req) {
 		*copied = tp->fastopen_req->copied;
 		tcp_free_fastopen_req(tp);
-		inet->defer_connect = 0;
+		inet_clear_bit(DEFER_CONNECT, sk);
 	}
 	return err;
 }
@@ -1066,7 +1067,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 			zc = MSG_SPLICE_PAGES;
 	}
 
-	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
+	if (unlikely(flags & MSG_FASTOPEN ||
+		     inet_test_bit(DEFER_CONNECT, sk)) &&
 	    !tp->repair) {
 		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg);
 		if (err == -EINPROGRESS && copied_syn > 0)
@@ -3088,7 +3090,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
-	inet->defer_connect = 0;
+	inet_clear_bit(DEFER_CONNECT, sk);
 	tp->fastopen_client_fail = 0;
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 85e4953f11821..8ed54e7334a9c 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -451,7 +451,7 @@ bool tcp_fastopen_defer_connect(struct sock *sk, int *err)
 
 	if (tp->fastopen_connect && !tp->fastopen_req) {
 		if (tcp_fastopen_cookie_check(sk, &mss, &cookie)) {
-			inet_sk(sk)->defer_connect = 1;
+			inet_set_bit(DEFER_CONNECT, sk);
 			return true;
 		}
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6ea0a1da80685..6019a3cf1625f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1686,7 +1686,7 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 		if (!mptcp_disconnect(sk, 0))
 			sk->sk_socket->state = SS_UNCONNECTED;
 	}
-	inet_sk(sk)->defer_connect = 0;
+	inet_clear_bit(DEFER_CONNECT, sk);
 
 	return ret;
 }
@@ -1704,7 +1704,8 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	lock_sock(sk);
 
-	if (unlikely(inet_sk(sk)->defer_connect || msg->msg_flags & MSG_FASTOPEN)) {
+	if (unlikely(inet_test_bit(DEFER_CONNECT, sk) ||
+		     msg->msg_flags & MSG_FASTOPEN)) {
 		int copied_syn = 0;
 
 		ret = mptcp_sendmsg_fastopen(sk, msg, len, &copied_syn);
@@ -3601,7 +3602,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (err < 0)
 		goto out;
 
-	inet_sk(sk)->defer_connect = inet_sk(ssk)->defer_connect;
+	inet_assign_bit(DEFER_CONNECT, sk, inet_test_bit(DEFER_CONNECT, ssk));
 
 out:
 	if (!msk->fastopening)
@@ -3827,7 +3828,8 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 			mask |= EPOLLOUT | EPOLLWRNORM;
 		else
 			mask |= mptcp_check_writeable(msk);
-	} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
+	} else if (state == TCP_SYN_SENT &&
+		   inet_test_bit(DEFER_CONNECT, sk)) {
 		/* cf tcp_poll() note about TFO */
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	}
-- 
GitLab


From 10f42426e5bcea728d7fae96609b29b4fb1f7518 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:46 +0000
Subject: [PATCH 1273/1806] inet: implement lockless IP_TTL

ip_select_ttl() is racy, because it reads inet->uc_ttl
without proper locking.

Add READ_ONCE()/WRITE_ONCE() annotations while
allowing IP_TTL socket option to be set/read without
holding the socket lock.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c   |  2 +-
 net/ipv4/ip_sockglue.c | 27 ++++++++++++---------------
 2 files changed, 13 insertions(+), 16 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8f396eada1b6e..ce6257860a401 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -133,7 +133,7 @@ EXPORT_SYMBOL_GPL(ip_local_out);
 static inline int ip_select_ttl(const struct inet_sock *inet,
 				const struct dst_entry *dst)
 {
-	int ttl = inet->uc_ttl;
+	int ttl = READ_ONCE(inet->uc_ttl);
 
 	if (ttl < 0)
 		ttl = ip4_dst_hoplimit(dst);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index cfa65a0b0900f..dbb2d2342ebf0 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1023,6 +1023,13 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 	case IP_BIND_ADDRESS_NO_PORT:
 		inet_assign_bit(BIND_ADDRESS_NO_PORT, sk, val);
 		return 0;
+	case IP_TTL:
+		if (optlen < 1)
+			return -EINVAL;
+		if (val != -1 && (val < 1 || val > 255))
+			return -EINVAL;
+		WRITE_ONCE(inet->uc_ttl, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1080,13 +1087,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 	case IP_TOS:	/* This sets both TOS and Precedence */
 		__ip_sock_set_tos(sk, val);
 		break;
-	case IP_TTL:
-		if (optlen < 1)
-			goto e_inval;
-		if (val != -1 && (val < 1 || val > 255))
-			goto e_inval;
-		inet->uc_ttl = val;
-		break;
 	case IP_MTU_DISCOVER:
 		if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
 			goto e_inval;
@@ -1590,6 +1590,11 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_BIND_ADDRESS_NO_PORT:
 		val = inet_test_bit(BIND_ADDRESS_NO_PORT, sk);
 		goto copyval;
+	case IP_TTL:
+		val = READ_ONCE(inet->uc_ttl);
+		if (val < 0)
+			val = READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_default_ttl);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1629,14 +1634,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_TOS:
 		val = inet->tos;
 		break;
-	case IP_TTL:
-	{
-		struct net *net = sock_net(sk);
-		val = (inet->uc_ttl == -1 ?
-		       READ_ONCE(net->ipv4.sysctl_ip_default_ttl) :
-		       inet->uc_ttl);
-		break;
-	}
 	case IP_MTU_DISCOVER:
 		val = inet->pmtudisc;
 		break;
-- 
GitLab


From 12af73269fd942c98ff9999a2ce0c04165aae136 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2023 08:15:47 +0000
Subject: [PATCH 1274/1806] inet: implement lockless IP_MINTTL

inet->min_ttl is already read with READ_ONCE().

Implementing IP_MINTTL socket option set/read
without holding the socket lock is easy.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index dbb2d2342ebf0..61b2e7bc70315 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1030,6 +1030,17 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		WRITE_ONCE(inet->uc_ttl, val);
 		return 0;
+	case IP_MINTTL:
+		if (optlen < 1)
+			return -EINVAL;
+		if (val < 0 || val > 255)
+			return -EINVAL;
+
+		if (val)
+			static_branch_enable(&ip4_min_ttl);
+
+		WRITE_ONCE(inet->min_ttl, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1326,21 +1337,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		err = xfrm_user_policy(sk, optname, optval, optlen);
 		break;
 
-	case IP_MINTTL:
-		if (optlen < 1)
-			goto e_inval;
-		if (val < 0 || val > 255)
-			goto e_inval;
-
-		if (val)
-			static_branch_enable(&ip4_min_ttl);
-
-		/* tcp_v4_err() and tcp_v4_rcv() might read min_ttl
-		 * while we are changint it.
-		 */
-		WRITE_ONCE(inet->min_ttl, val);
-		break;
-
 	case IP_LOCAL_PORT_RANGE:
 	{
 		const __u16 lo = val;
@@ -1595,6 +1591,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		if (val < 0)
 			val = READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_default_ttl);
 		goto copyval;
+	case IP_MINTTL:
+		val = READ_ONCE(inet->min_ttl);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1731,9 +1730,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		len -= msg.msg_controllen;
 		return copy_to_sockptr(optlen, &len, sizeof(int));
 	}
-	case IP_MINTTL:
-		val = inet->min_ttl;
-		break;
 	case IP_LOCAL_PORT_RANGE:
 		val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
 		break;
-- 
GitLab


From 90bc21aaef4adaefceda2d385756138fc247c0c2 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Tue, 15 Aug 2023 11:21:05 +0300
Subject: [PATCH 1275/1806] net: ethernet: ti: am65-cpsw: add mqprio qdisc
 offload in channel mode

This patch adds MQPRIO Qdisc offload in full 'channel' mode which allows
not only setting up pri:tc mapping, but also configuring TX shapers on
external port FIFOs. The K3 CPSW MQPRIO Qdisc offload is expected to work
with VLAN/priority tagged packets. Non-tagged packets have to be mapped
only to TC0.

- TX traffic classes must be rated starting from TC that has highest
priority and with no gaps
- Traffic classes are used starting from 0, that has highest priority
- min_rate defines Committed Information Rate (guaranteed)
- max_rate defines Excess Information Rate (non guaranteed) and offloaded
as (max_rate[i] - tcX_min_rate[i])
- VLAN/priority tagged packets mapped to TC0 will exit switch with VLAN tag
priority 0

The configuration example:
 ethtool -L eth1 tx 5
 ethtool --set-priv-flags eth1 p0-rx-ptype-rrobin off

 tc qdisc add dev eth1 parent root handle 100: mqprio num_tc 3 \
 map 0 0 1 2 0 0 0 0 0 0 0 0 0 0 0 0 \
 queues 1@0 1@1 1@2 hw 1 mode channel \
 shaper bw_rlimit min_rate 0 100mbit 200mbit max_rate 0 101mbit 202mbit

 tc qdisc replace dev eth2 handle 100: parent root mqprio num_tc 1 \
 map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@0 hw 1

 ip link add link eth1 name eth1.100 type vlan id 100
 ip link set eth1.100 type vlan egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7

In the above example two ports share the same TX CPPI queue 0 for low
priority traffic. 3 traffic classes are defined for eth1 and mapped to:
TC0 - low priority, TX CPPI queue 0 -> ext Port 1 fifo0, no rate limit
TC1 - prio 2, TX CPPI queue 1 -> ext Port 1 fifo1, CIR=100Mbit/s, EIR=1Mbit/s
TC2 - prio 3, TX CPPI queue 2 -> ext Port 1 fifo2, CIR=200Mbit/s, EIR=2Mbit/s

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c |   3 +
 drivers/net/ethernet/ti/am65-cpsw-qos.c  | 295 ++++++++++++++++++++++-
 drivers/net/ethernet/ti/am65-cpsw-qos.h  |  14 ++
 3 files changed, 311 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index bea6fc0f324ce..09593d6fd618e 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -633,6 +633,9 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev)
 	/* restore vlan configurations */
 	vlan_for_each(ndev, cpsw_restore_vlans, port);
 
+	/* Initialize QoS */
+	am65_cpsw_qos_mqprio_init(port);
+
 	phylink_start(port->slave.phylink);
 
 	return 0;
diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c
index 9ac2ff05d5017..3b3e75fbb64d0 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-qos.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c
@@ -17,9 +17,12 @@
 
 #define AM65_CPSW_REG_CTL			0x004
 #define AM65_CPSW_PN_REG_CTL			0x004
+#define AM65_CPSW_PN_REG_TX_PRI_MAP		0x018
+#define AM65_CPSW_PN_REG_RX_PRI_MAP		0x020
 #define AM65_CPSW_PN_REG_FIFO_STATUS		0x050
 #define AM65_CPSW_PN_REG_EST_CTL		0x060
 #define AM65_CPSW_PN_REG_PRI_CIR(pri)		(0x140 + 4 * (pri))
+#define AM65_CPSW_PN_REG_PRI_EIR(pri)		(0x160 + 4 * (pri))
 
 /* AM65_CPSW_REG_CTL register fields */
 #define AM65_CPSW_CTL_EST_EN			BIT(18)
@@ -56,6 +59,12 @@ enum timer_act {
 	TACT_SKIP_PROG,		/* just buffer can be updated */
 };
 
+/* number of traffic classes (FIFOs) per port */
+#define AM65_CPSW_PN_TC_NUM			8
+#define AM65_CPSW_PN_TX_PRI_MAP_DEFAULT		0x76543210
+
+static int am65_cpsw_setup_mqprio(struct net_device *ndev, void *type_data);
+
 static int am65_cpsw_port_est_enabled(struct am65_cpsw_port *port)
 {
 	return port->qos.est_oper || port->qos.est_admin;
@@ -541,7 +550,6 @@ static void am65_cpsw_est_link_up(struct net_device *ndev, int link_speed)
 	ktime_t cur_time;
 	s64 delta;
 
-	port->qos.link_speed = link_speed;
 	if (!am65_cpsw_port_est_enabled(port))
 		return;
 
@@ -795,6 +803,8 @@ int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 		return am65_cpsw_tc_query_caps(ndev, type_data);
 	case TC_SETUP_QDISC_TAPRIO:
 		return am65_cpsw_setup_taprio(ndev, type_data);
+	case TC_SETUP_QDISC_MQPRIO:
+		return am65_cpsw_setup_mqprio(ndev, type_data);
 	case TC_SETUP_BLOCK:
 		return am65_cpsw_qos_setup_tc_block(ndev, type_data);
 	default:
@@ -802,10 +812,15 @@ int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	}
 }
 
+static void am65_cpsw_tx_pn_shaper_link_up(struct am65_cpsw_port *port);
+
 void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed)
 {
 	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
 
+	port->qos.link_speed = link_speed;
+	am65_cpsw_tx_pn_shaper_link_up(port);
+
 	if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS))
 		return;
 
@@ -937,3 +952,281 @@ void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common)
 		       host->port_base + AM65_CPSW_PN_REG_PRI_CIR(tx_ch));
 	}
 }
+
+static void am65_cpsw_tx_pn_shaper_apply(struct am65_cpsw_port *port)
+{
+	struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
+	struct am65_cpsw_common *common = port->common;
+	struct tc_mqprio_qopt_offload *mqprio;
+	bool shaper_en;
+	u32 rate_mbps;
+	int i;
+
+	mqprio = &p_mqprio->mqprio_hw;
+	shaper_en = p_mqprio->shaper_en && !p_mqprio->shaper_susp;
+
+	for (i = 0; i < mqprio->qopt.num_tc; i++) {
+		rate_mbps = 0;
+		if (shaper_en) {
+			rate_mbps = mqprio->min_rate[i] * 8 / 1000000;
+			rate_mbps = am65_cpsw_qos_tx_rate_calc(rate_mbps,
+							       common->bus_freq);
+		}
+
+		writel(rate_mbps,
+		       port->port_base + AM65_CPSW_PN_REG_PRI_CIR(i));
+	}
+
+	for (i = 0; i < mqprio->qopt.num_tc; i++) {
+		rate_mbps = 0;
+		if (shaper_en && mqprio->max_rate[i]) {
+			rate_mbps = mqprio->max_rate[i] - mqprio->min_rate[i];
+			rate_mbps = rate_mbps * 8 / 1000000;
+			rate_mbps = am65_cpsw_qos_tx_rate_calc(rate_mbps,
+							       common->bus_freq);
+		}
+
+		writel(rate_mbps,
+		       port->port_base + AM65_CPSW_PN_REG_PRI_EIR(i));
+	}
+}
+
+static void am65_cpsw_tx_pn_shaper_link_up(struct am65_cpsw_port *port)
+{
+	struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
+	struct am65_cpsw_common *common = port->common;
+	bool shaper_susp = false;
+
+	if (!p_mqprio->enable || !p_mqprio->shaper_en)
+		return;
+
+	if (p_mqprio->max_rate_total > port->qos.link_speed)
+		shaper_susp = true;
+
+	if (p_mqprio->shaper_susp == shaper_susp)
+		return;
+
+	if (shaper_susp)
+		dev_info(common->dev,
+			 "Port%u: total shaper tx rate > link speed - suspend shaper\n",
+			 port->port_id);
+	else
+		dev_info(common->dev,
+			 "Port%u: link recover - resume shaper\n",
+			 port->port_id);
+
+	p_mqprio->shaper_susp = shaper_susp;
+	am65_cpsw_tx_pn_shaper_apply(port);
+}
+
+void am65_cpsw_qos_mqprio_init(struct am65_cpsw_port *port)
+{
+	struct am65_cpsw_host *host = am65_common_get_host(port->common);
+	struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
+	struct tc_mqprio_qopt_offload *mqprio;
+	u32 tx_prio_map = 0, rx_prio_map;
+	int i, fifo;
+
+	mqprio = &p_mqprio->mqprio_hw;
+	rx_prio_map = readl(host->port_base + AM65_CPSW_PN_REG_RX_PRI_MAP);
+
+	if (p_mqprio->enable) {
+		for (i = 0; i < AM65_CPSW_PN_TC_NUM; i++) {
+			fifo = mqprio->qopt.prio_tc_map[i];
+			tx_prio_map |= fifo << (4 * i);
+		}
+
+		netdev_set_num_tc(port->ndev, mqprio->qopt.num_tc);
+		for (i = 0; i < mqprio->qopt.num_tc; i++) {
+			netdev_set_tc_queue(port->ndev, i,
+					    mqprio->qopt.count[i],
+					    mqprio->qopt.offset[i]);
+			if (!i) {
+				p_mqprio->tc0_q = mqprio->qopt.offset[i];
+				rx_prio_map &= ~(0x7 << (4 * p_mqprio->tc0_q));
+			}
+		}
+	} else {
+		/* restore default configuration */
+		netdev_reset_tc(port->ndev);
+		tx_prio_map = AM65_CPSW_PN_TX_PRI_MAP_DEFAULT;
+		rx_prio_map |= p_mqprio->tc0_q << (4 * p_mqprio->tc0_q);
+		p_mqprio->tc0_q = 0;
+	}
+
+	writel(tx_prio_map,
+	       port->port_base + AM65_CPSW_PN_REG_TX_PRI_MAP);
+	writel(rx_prio_map,
+	       host->port_base + AM65_CPSW_PN_REG_RX_PRI_MAP);
+
+	am65_cpsw_tx_pn_shaper_apply(port);
+}
+
+static int am65_cpsw_mqprio_verify(struct am65_cpsw_port *port,
+				   struct tc_mqprio_qopt_offload *mqprio)
+{
+	int i;
+
+	for (i = 0; i < mqprio->qopt.num_tc; i++) {
+		unsigned int last = mqprio->qopt.offset[i] +
+				    mqprio->qopt.count[i];
+
+		if (mqprio->qopt.offset[i] >= port->ndev->real_num_tx_queues ||
+		    !mqprio->qopt.count[i] ||
+		    last >  port->ndev->real_num_tx_queues)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int am65_cpsw_mqprio_verify_shaper(struct am65_cpsw_port *port,
+					  struct tc_mqprio_qopt_offload *mqprio,
+					  u64 *max_rate)
+{
+	struct am65_cpsw_common *common = port->common;
+	u64 min_rate_total = 0, max_rate_total = 0;
+	u32 min_rate_msk = 0, max_rate_msk = 0;
+	bool has_min_rate, has_max_rate;
+	int num_tc, i;
+
+	has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
+	has_max_rate = !!(mqprio->flags & TC_MQPRIO_F_MAX_RATE);
+
+	if (!has_min_rate && has_max_rate)
+		return -EOPNOTSUPP;
+
+	if (!has_min_rate)
+		return 0;
+
+	num_tc = mqprio->qopt.num_tc;
+
+	for (i = num_tc - 1; i >= 0; i--) {
+		u32 ch_msk;
+
+		if (mqprio->min_rate[i])
+			min_rate_msk |= BIT(i);
+		min_rate_total +=  mqprio->min_rate[i];
+
+		if (has_max_rate) {
+			if (mqprio->max_rate[i])
+				max_rate_msk |= BIT(i);
+			max_rate_total +=  mqprio->max_rate[i];
+
+			if (!mqprio->min_rate[i] && mqprio->max_rate[i]) {
+				dev_err(common->dev, "TX tc%d rate max>0 but min=0\n",
+					i);
+				return -EINVAL;
+			}
+
+			if (mqprio->max_rate[i] &&
+			    mqprio->max_rate[i] < mqprio->min_rate[i]) {
+				dev_err(common->dev, "TX tc%d rate min(%llu)>max(%llu)\n",
+					i, mqprio->min_rate[i],
+					mqprio->max_rate[i]);
+				return -EINVAL;
+			}
+		}
+
+		ch_msk = GENMASK(num_tc - 1, i);
+		if ((min_rate_msk & BIT(i)) && (min_rate_msk ^ ch_msk)) {
+			dev_err(common->dev, "TX Min rate limiting has to be enabled sequentially hi->lo tx_rate_msk%x\n",
+				min_rate_msk);
+			return -EINVAL;
+		}
+
+		if ((max_rate_msk & BIT(i)) && (max_rate_msk ^ ch_msk)) {
+			dev_err(common->dev, "TX max rate limiting has to be enabled sequentially hi->lo tx_rate_msk%x\n",
+				max_rate_msk);
+			return -EINVAL;
+		}
+	}
+	min_rate_total *= 8;
+	min_rate_total /= 1000 * 1000;
+	max_rate_total *= 8;
+	max_rate_total /= 1000 * 1000;
+
+	if (port->qos.link_speed != SPEED_UNKNOWN) {
+		if (min_rate_total > port->qos.link_speed) {
+			dev_err(common->dev, "TX rate min exceed %llu link speed %d\n",
+				min_rate_total, port->qos.link_speed);
+			return -EINVAL;
+		}
+
+		if (max_rate_total > port->qos.link_speed) {
+			dev_err(common->dev, "TX rate max exceed %llu link speed %d\n",
+				max_rate_total, port->qos.link_speed);
+			return -EINVAL;
+		}
+	}
+
+	*max_rate = max_t(u64, min_rate_total, max_rate_total);
+
+	return 0;
+}
+
+static int am65_cpsw_setup_mqprio(struct net_device *ndev, void *type_data)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct tc_mqprio_qopt_offload *mqprio = type_data;
+	struct am65_cpsw_common *common = port->common;
+	struct am65_cpsw_mqprio *p_mqprio;
+	bool has_min_rate;
+	int num_tc, ret;
+	u64 max_rate;
+
+	p_mqprio = &port->qos.mqprio;
+
+	if (!mqprio->qopt.hw)
+		goto skip_check;
+
+	if (mqprio->mode != TC_MQPRIO_MODE_CHANNEL)
+		return -EOPNOTSUPP;
+
+	num_tc = mqprio->qopt.num_tc;
+	if (num_tc > AM65_CPSW_PN_TC_NUM)
+		return -ERANGE;
+
+	if ((mqprio->flags & TC_MQPRIO_F_SHAPER) &&
+	    mqprio->shaper != TC_MQPRIO_SHAPER_BW_RATE)
+		return -EOPNOTSUPP;
+
+	ret = am65_cpsw_mqprio_verify(port, mqprio);
+	if (ret)
+		return ret;
+
+	ret = am65_cpsw_mqprio_verify_shaper(port, mqprio, &max_rate);
+	if (ret)
+		return ret;
+
+skip_check:
+	ret = pm_runtime_get_sync(common->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(common->dev);
+		return ret;
+	}
+
+	if (mqprio->qopt.hw) {
+		memcpy(&p_mqprio->mqprio_hw, mqprio, sizeof(*mqprio));
+		has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
+		p_mqprio->enable = 1;
+		p_mqprio->shaper_en = has_min_rate;
+		p_mqprio->shaper_susp = !has_min_rate;
+		p_mqprio->max_rate_total = max_rate;
+	} else {
+		unsigned int tc0_q = p_mqprio->tc0_q;
+
+		memset(p_mqprio, 0, sizeof(*p_mqprio));
+		p_mqprio->mqprio_hw.qopt.num_tc = AM65_CPSW_PN_TC_NUM;
+		p_mqprio->tc0_q = tc0_q;
+	}
+
+	if (!netif_running(ndev))
+		goto exit_put;
+
+	am65_cpsw_qos_mqprio_init(port);
+
+exit_put:
+	pm_runtime_put(common->dev);
+	return 0;
+}
diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.h b/drivers/net/ethernet/ti/am65-cpsw-qos.h
index 0cc2a3b3d7f9e..247a42788687b 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-qos.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-qos.h
@@ -7,8 +7,10 @@
 
 #include <linux/netdevice.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 
 struct am65_cpsw_common;
+struct am65_cpsw_port;
 
 struct am65_cpsw_est {
 	int buf;
@@ -16,6 +18,16 @@ struct am65_cpsw_est {
 	struct tc_taprio_qopt_offload taprio;
 };
 
+struct am65_cpsw_mqprio {
+	struct tc_mqprio_qopt_offload mqprio_hw;
+	u64 max_rate_total;
+
+	unsigned enable:1;
+	unsigned shaper_en:1;
+	unsigned shaper_susp:1;
+	unsigned tc0_q:3;
+};
+
 struct am65_cpsw_ale_ratelimit {
 	unsigned long cookie;
 	u64 rate_packet_ps;
@@ -26,6 +38,7 @@ struct am65_cpsw_qos {
 	struct am65_cpsw_est *est_oper;
 	ktime_t link_down_time;
 	int link_speed;
+	struct am65_cpsw_mqprio mqprio;
 
 	struct am65_cpsw_ale_ratelimit ale_bc_ratelimit;
 	struct am65_cpsw_ale_ratelimit ale_mc_ratelimit;
@@ -35,6 +48,7 @@ int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 			       void *type_data);
 void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed);
 void am65_cpsw_qos_link_down(struct net_device *ndev);
+void am65_cpsw_qos_mqprio_init(struct am65_cpsw_port *port);
 int am65_cpsw_qos_ndo_tx_p0_set_maxrate(struct net_device *ndev, int queue, u32 rate_mbps);
 void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common);
 
-- 
GitLab


From 7fd034bce6d276353a4e70c516789dfe6b2c32ae Mon Sep 17 00:00:00 2001
From: Louis Peens <louis.peens@corigine.com>
Date: Tue, 15 Aug 2023 14:43:25 +0200
Subject: [PATCH 1276/1806] nfp: update maintainer

Take over maintainership of the nfp driver from Simon as he
is moving away from Corigine.

Signed-off-by: Louis Peens <louis.peens@corigine.com>
Acked-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d984c9a7b12c5..f150561a396e3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14658,7 +14658,7 @@ F:	drivers/rtc/rtc-ntxec.c
 F:	include/linux/mfd/ntxec.h
 
 NETRONOME ETHERNET DRIVERS
-M:	Simon Horman <simon.horman@corigine.com>
+M:	Louis Peens <louis.peens@corigine.com>
 R:	Jakub Kicinski <kuba@kernel.org>
 L:	oss-drivers@corigine.com
 S:	Maintained
-- 
GitLab


From ac8a52962164a50e693fa021d3564d7745b83a7f Mon Sep 17 00:00:00 2001
From: Abel Wu <wuyun.abel@bytedance.com>
Date: Mon, 14 Aug 2023 15:09:11 +0800
Subject: [PATCH 1277/1806] net-memcg: Fix scope of sockmem pressure indicators

Now there are two indicators of socket memory pressure sit inside
struct mem_cgroup, socket_pressure and tcpmem_pressure, indicating
memory reclaim pressure in memcg->memory and ->tcpmem respectively.

When in legacy mode (cgroupv1), the socket memory is charged into
->tcpmem which is independent of ->memory, so socket_pressure has
nothing to do with socket's pressure at all. Things could be worse
by taking socket_pressure into consideration in legacy mode, as a
pressure in ->memory can lead to premature reclamation/throttling
in socket.

While for the default mode (cgroupv2), the socket memory is charged
into ->memory, and ->tcpmem/->tcpmem_pressure are simply not used.

So {socket,tcpmem}_pressure are only used in default/legacy mode
respectively for indicating socket memory pressure. This patch fixes
the pieces of code that make mixed use of both.

Fixes: 8e8ae645249b ("mm: memcontrol: hook up vmpressure to socket pressure")
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/memcontrol.h | 9 +++++++--
 mm/vmpressure.c            | 8 ++++++++
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5818af8eca5a5..dbf26bc89dd46 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -284,6 +284,11 @@ struct mem_cgroup {
 	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
 	atomic_long_t		memory_events_local[MEMCG_NR_MEMORY_EVENTS];
 
+	/*
+	 * Hint of reclaim pressure for socket memroy management. Note
+	 * that this indicator should NOT be used in legacy cgroup mode
+	 * where socket memory is accounted/charged separately.
+	 */
 	unsigned long		socket_pressure;
 
 	/* Legacy tcp memory accounting */
@@ -1727,8 +1732,8 @@ void mem_cgroup_sk_alloc(struct sock *sk);
 void mem_cgroup_sk_free(struct sock *sk);
 static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 {
-	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure)
-		return true;
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return !!memcg->tcpmem_pressure;
 	do {
 		if (time_before(jiffies, READ_ONCE(memcg->socket_pressure)))
 			return true;
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index b52644771cc43..22c6689d93027 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -244,6 +244,14 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
 	if (mem_cgroup_disabled())
 		return;
 
+	/*
+	 * The in-kernel users only care about the reclaim efficiency
+	 * for this @memcg rather than the whole subtree, and there
+	 * isn't and won't be any in-kernel user in a legacy cgroup.
+	 */
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !tree)
+		return;
+
 	vmpr = memcg_to_vmpressure(memcg);
 
 	/*
-- 
GitLab


From d147085183ea1b0efd2c18fca76e4dee873b1e4e Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Tue, 15 Aug 2023 10:01:11 -0700
Subject: [PATCH 1278/1806] e1000e: Use PME poll to circumvent unreliable ACPI
 wake

On some I219 devices, ethernet cable plugging detection only works once
from PCI D3 state. Subsequent cable plugging does set PME bit correctly,
but device still doesn't get woken up.

Since I219 connects to the root complex directly, it relies on platform
firmware (ACPI) to wake it up. In this case, the GPE from _PRW only
works for first cable plugging but fails to notify the driver for
subsequent plugging events.

The issue was originally found on CNP, but the same issue can be found
on ADL too. So workaround the issue by continuing use PME poll after
first ACPI wake. As PME poll is always used, the runtime suspend
restriction for CNP can also be removed.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/e1000e/netdev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 771a3c909c459..18a5e73b86806 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -7021,6 +7021,8 @@ static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev)
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	int rc;
 
+	pdev->pme_poll = true;
+
 	rc = __e1000_resume(pdev);
 	if (rc)
 		return rc;
@@ -7682,7 +7684,7 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_SMART_PREPARE);
 
-	if (pci_dev_run_wake(pdev) && hw->mac.type != e1000_pch_cnp)
+	if (pci_dev_run_wake(pdev))
 		pm_runtime_put_noidle(&pdev->dev);
 
 	return 0;
-- 
GitLab


From 3dec89b14d37ee635e772636dad3f09f78f1ab87 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Tue, 15 Aug 2023 11:07:05 -0700
Subject: [PATCH 1279/1806] net/ipv6: Remove expired routes with a separated
 list of routes.

FIB6 GC walks trees of fib6_tables to remove expired routes. Walking a tree
can be expensive if the number of routes in a table is big, even if most of
them are permanent. Checking routes in a separated list of routes having
expiration will avoid this potential issue.

Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 64 ++++++++++++++++++++++++++++++++++---------
 net/ipv6/ip6_fib.c    | 55 +++++++++++++++++++++++++++++++++----
 net/ipv6/route.c      |  6 ++--
 3 files changed, 103 insertions(+), 22 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 05e6f756feafe..c9ff23cf313e4 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -179,6 +179,9 @@ struct fib6_info {
 
 	refcount_t			fib6_ref;
 	unsigned long			expires;
+
+	struct hlist_node		gc_link;
+
 	struct dst_metrics		*fib6_metrics;
 #define fib6_pmtu		fib6_metrics->metrics[RTAX_MTU-1]
 
@@ -247,19 +250,6 @@ static inline bool fib6_requires_src(const struct fib6_info *rt)
 	return rt->fib6_src.plen > 0;
 }
 
-static inline void fib6_clean_expires(struct fib6_info *f6i)
-{
-	f6i->fib6_flags &= ~RTF_EXPIRES;
-	f6i->expires = 0;
-}
-
-static inline void fib6_set_expires(struct fib6_info *f6i,
-				    unsigned long expires)
-{
-	f6i->expires = expires;
-	f6i->fib6_flags |= RTF_EXPIRES;
-}
-
 static inline bool fib6_check_expired(const struct fib6_info *f6i)
 {
 	if (f6i->fib6_flags & RTF_EXPIRES)
@@ -267,6 +257,11 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i)
 	return false;
 }
 
+static inline bool fib6_has_expires(const struct fib6_info *f6i)
+{
+	return f6i->fib6_flags & RTF_EXPIRES;
+}
+
 /* Function to safely get fn->fn_sernum for passed in rt
  * and store result in passed in cookie.
  * Return true if we can get cookie safely
@@ -388,6 +383,7 @@ struct fib6_table {
 	struct inet_peer_base	tb6_peers;
 	unsigned int		flags;
 	unsigned int		fib_seq;
+	struct hlist_head       tb6_gc_hlist;	/* GC candidates */
 #define RT6_TABLE_HAS_DFLT_ROUTER	BIT(0)
 };
 
@@ -504,6 +500,48 @@ void fib6_gc_cleanup(void);
 
 int fib6_init(void);
 
+/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be
+ * NULL.
+ */
+static inline void fib6_set_expires_locked(struct fib6_info *f6i,
+					   unsigned long expires)
+{
+	struct fib6_table *tb6;
+
+	tb6 = f6i->fib6_table;
+	f6i->expires = expires;
+	if (tb6 && !fib6_has_expires(f6i))
+		hlist_add_head(&f6i->gc_link, &tb6->tb6_gc_hlist);
+	f6i->fib6_flags |= RTF_EXPIRES;
+}
+
+/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be
+ * NULL.  If fib6_table is NULL, the fib6_info will no be inserted into the
+ * list of GC candidates until it is inserted into a table.
+ */
+static inline void fib6_set_expires(struct fib6_info *f6i,
+				    unsigned long expires)
+{
+	spin_lock_bh(&f6i->fib6_table->tb6_lock);
+	fib6_set_expires_locked(f6i, expires);
+	spin_unlock_bh(&f6i->fib6_table->tb6_lock);
+}
+
+static inline void fib6_clean_expires_locked(struct fib6_info *f6i)
+{
+	if (fib6_has_expires(f6i))
+		hlist_del_init(&f6i->gc_link);
+	f6i->fib6_flags &= ~RTF_EXPIRES;
+	f6i->expires = 0;
+}
+
+static inline void fib6_clean_expires(struct fib6_info *f6i)
+{
+	spin_lock_bh(&f6i->fib6_table->tb6_lock);
+	fib6_clean_expires_locked(f6i);
+	spin_unlock_bh(&f6i->fib6_table->tb6_lock);
+}
+
 struct ipv6_route_iter {
 	struct seq_net_private p;
 	struct fib6_walker w;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index bac768d36cc19..28b01a068412a 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -160,6 +160,8 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
 	INIT_LIST_HEAD(&f6i->fib6_siblings);
 	refcount_set(&f6i->fib6_ref, 1);
 
+	INIT_HLIST_NODE(&f6i->gc_link);
+
 	return f6i;
 }
 
@@ -246,6 +248,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 				   net->ipv6.fib6_null_entry);
 		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 		inet_peer_base_init(&table->tb6_peers);
+		INIT_HLIST_HEAD(&table->tb6_gc_hlist);
 	}
 
 	return table;
@@ -1057,6 +1060,8 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 				    lockdep_is_held(&table->tb6_lock));
 		}
 	}
+
+	fib6_clean_expires_locked(rt);
 }
 
 /*
@@ -1118,9 +1123,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 				if (!(iter->fib6_flags & RTF_EXPIRES))
 					return -EEXIST;
 				if (!(rt->fib6_flags & RTF_EXPIRES))
-					fib6_clean_expires(iter);
+					fib6_clean_expires_locked(iter);
 				else
-					fib6_set_expires(iter, rt->expires);
+					fib6_set_expires_locked(iter,
+								rt->expires);
 
 				if (rt->fib6_pmtu)
 					fib6_metric_set(iter, RTAX_MTU,
@@ -1479,6 +1485,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 		if (rt->nh)
 			list_add(&rt->nh_list, &rt->nh->f6i_list);
 		__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
+
+		if (fib6_has_expires(rt))
+			hlist_add_head(&rt->gc_link, &table->tb6_gc_hlist);
+
 		fib6_start_gc(info->nl_net, rt);
 	}
 
@@ -2285,9 +2295,8 @@ static void fib6_flush_trees(struct net *net)
  *	Garbage collection
  */
 
-static int fib6_age(struct fib6_info *rt, void *arg)
+static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
 {
-	struct fib6_gc_args *gc_args = arg;
 	unsigned long now = jiffies;
 
 	/*
@@ -2295,7 +2304,7 @@ static int fib6_age(struct fib6_info *rt, void *arg)
 	 *	Routes are expired even if they are in use.
 	 */
 
-	if (rt->fib6_flags & RTF_EXPIRES && rt->expires) {
+	if (fib6_has_expires(rt) && rt->expires) {
 		if (time_after(now, rt->expires)) {
 			RT6_TRACE("expiring %p\n", rt);
 			return -1;
@@ -2312,6 +2321,40 @@ static int fib6_age(struct fib6_info *rt, void *arg)
 	return 0;
 }
 
+static void fib6_gc_table(struct net *net,
+			  struct fib6_table *tb6,
+			  struct fib6_gc_args *gc_args)
+{
+	struct fib6_info *rt;
+	struct hlist_node *n;
+	struct nl_info info = {
+		.nl_net = net,
+		.skip_notify = false,
+	};
+
+	hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link)
+		if (fib6_age(rt, gc_args) == -1)
+			fib6_del(rt, &info);
+}
+
+static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args)
+{
+	struct fib6_table *table;
+	struct hlist_head *head;
+	unsigned int h;
+
+	rcu_read_lock();
+	for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
+		head = &net->ipv6.fib_table_hash[h];
+		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
+			spin_lock_bh(&table->tb6_lock);
+			fib6_gc_table(net, table, gc_args);
+			spin_unlock_bh(&table->tb6_lock);
+		}
+	}
+	rcu_read_unlock();
+}
+
 void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 {
 	struct fib6_gc_args gc_args;
@@ -2327,7 +2370,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 			  net->ipv6.sysctl.ip6_rt_gc_interval;
 	gc_args.more = 0;
 
-	fib6_clean_all(net, fib6_age, &gc_args);
+	fib6_gc_all(net, &gc_args);
 	now = jiffies;
 	net->ipv6.ip6_rt_last_gc = now;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 10751df16dab2..db10c36f34bbc 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3761,10 +3761,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		rt->dst_nocount = true;
 
 	if (cfg->fc_flags & RTF_EXPIRES)
-		fib6_set_expires(rt, jiffies +
-				clock_t_to_jiffies(cfg->fc_expires));
+		fib6_set_expires_locked(rt, jiffies +
+					clock_t_to_jiffies(cfg->fc_expires));
 	else
-		fib6_clean_expires(rt);
+		fib6_clean_expires_locked(rt);
 
 	if (cfg->fc_protocol == RTPROT_UNSPEC)
 		cfg->fc_protocol = RTPROT_BOOT;
-- 
GitLab


From a63e10da42e757408d98732aaf5cf84bfd3a8276 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <thinker.li@gmail.com>
Date: Tue, 15 Aug 2023 11:07:06 -0700
Subject: [PATCH 1280/1806] selftests: fib_tests: Add a test case for IPv6
 garbage collection

Add 1000 IPv6 routes with expiration time (w/ and w/o additional 5000
permanet routes in the background.)  Wait for a few seconds to make sure
they are removed correctly.

The expected output of the test looks like the following example.

> Fib6 garbage collection test
>     TEST: ipv6 route garbage collection [ OK ]

Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 72 +++++++++++++++++++++++-
 1 file changed, 69 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 35d89dfa6f11b..c14ad6e75c1e2 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -9,13 +9,16 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh"
+TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \
+       ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \
+       ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \
+       ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
 PAUSE=no
-IP="ip -netns ns1"
-NS_EXEC="ip netns exec ns1"
+IP="$(which ip) -netns ns1"
+NS_EXEC="$(which ip) netns exec ns1"
 
 which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 
@@ -747,6 +750,68 @@ fib_notify_test()
 	cleanup &> /dev/null
 }
 
+fib6_gc_test()
+{
+	setup
+
+	echo
+	echo "Fib6 garbage collection test"
+	set -e
+
+	EXPIRE=3
+
+	# Check expiration of routes every $EXPIRE seconds (GC)
+	$NS_EXEC sysctl -wq net.ipv6.route.gc_interval=$EXPIRE
+
+	$IP link add dummy_10 type dummy
+	$IP link set dev dummy_10 up
+	$IP -6 address add 2001:10::1/64 dev dummy_10
+
+	$NS_EXEC sysctl -wq net.ipv6.route.flush=1
+
+	# Temporary routes
+	for i in $(seq 1 1000); do
+	    # Expire route after $EXPIRE seconds
+	    $IP -6 route add 2001:20::$i \
+		via 2001:10::2 dev dummy_10 expires $EXPIRE
+	done
+	sleep $(($EXPIRE * 2))
+	N_EXP_SLEEP=$($IP -6 route list |grep expires|wc -l)
+	if [ $N_EXP_SLEEP -ne 0 ]; then
+	    echo "FAIL: expected 0 routes with expires, got $N_EXP_SLEEP"
+	    ret=1
+	else
+	    ret=0
+	fi
+
+	# Permanent routes
+	for i in $(seq 1 5000); do
+	    $IP -6 route add 2001:30::$i \
+		via 2001:10::2 dev dummy_10
+	done
+	# Temporary routes
+	for i in $(seq 1 1000); do
+	    # Expire route after $EXPIRE seconds
+	    $IP -6 route add 2001:20::$i \
+		via 2001:10::2 dev dummy_10 expires $EXPIRE
+	done
+	sleep $(($EXPIRE * 2))
+	N_EXP_SLEEP=$($IP -6 route list |grep expires|wc -l)
+	if [ $N_EXP_SLEEP -ne 0 ]; then
+	    echo "FAIL: expected 0 routes with expires," \
+		 "got $N_EXP_SLEEP (5000 permanent routes)"
+	    ret=1
+	else
+	    ret=0
+	fi
+
+	set +e
+
+	log_test $ret 0 "ipv6 route garbage collection"
+
+	cleanup &> /dev/null
+}
+
 fib_suppress_test()
 {
 	echo
@@ -2217,6 +2282,7 @@ do
 	ipv4_mangle)			ipv4_mangle_test;;
 	ipv6_mangle)			ipv6_mangle_test;;
 	ipv4_bcast_neigh)		ipv4_bcast_neigh_test;;
+	fib6_gc_test|ipv6_gc)		fib6_gc_test;;
 
 	help) echo "Test names: $TESTS"; exit 0;;
 	esac
-- 
GitLab


From 0aa35162d2a1ed7ae5303b8d91f7290d3b8b9219 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 13 Aug 2023 14:18:59 +0000
Subject: [PATCH 1281/1806] bpf: Fix uninitialized symbol in
 bpf_perf_link_fill_kprobe()

The commit 1b715e1b0ec5 ("bpf: Support ->fill_link_info for perf_event") leads
to the following Smatch static checker warning:

    kernel/bpf/syscall.c:3416 bpf_perf_link_fill_kprobe()
    error: uninitialized symbol 'type'.

That can happens when uname is NULL. So fix it by verifying the uname when we
really need to fill it.

Fixes: 1b715e1b0ec5 ("bpf: Support ->fill_link_info for perf_event")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Closes: https://lore.kernel.org/bpf/85697a7e-f897-4f74-8b43-82721bebc462@kili.mountain
Link: https://lore.kernel.org/bpf/20230813141900.1268-2-laoar.shao@gmail.com
---
 kernel/bpf/syscall.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7f4e8c357a6af..cb658543bdb46 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3378,14 +3378,13 @@ static int bpf_perf_link_fill_common(const struct perf_event *event,
 
 	if (!ulen ^ !uname)
 		return -EINVAL;
-	if (!uname)
-		return 0;
 
 	err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf,
 				      probe_offset, probe_addr);
 	if (err)
 		return err;
-
+	if (!uname)
+		return 0;
 	if (buf) {
 		len = strlen(buf);
 		err = bpf_copy_to_user(uname, buf, ulen, len);
-- 
GitLab


From 23cf7aa539dc26f45e42ef6303613f03f4ae2142 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 13 Aug 2023 14:19:00 +0000
Subject: [PATCH 1282/1806] selftests/bpf: Add selftest for fill_link_info

Add selftest for the fill_link_info of uprobe, kprobe and tracepoint.
The result:

  $ tools/testing/selftests/bpf/test_progs --name=fill_link_info
  #79/1    fill_link_info/kprobe_link_info:OK
  #79/2    fill_link_info/kretprobe_link_info:OK
  #79/3    fill_link_info/kprobe_invalid_ubuff:OK
  #79/4    fill_link_info/tracepoint_link_info:OK
  #79/5    fill_link_info/uprobe_link_info:OK
  #79/6    fill_link_info/uretprobe_link_info:OK
  #79/7    fill_link_info/kprobe_multi_link_info:OK
  #79/8    fill_link_info/kretprobe_multi_link_info:OK
  #79/9    fill_link_info/kprobe_multi_invalid_ubuff:OK
  #79      fill_link_info:OK
  Summary: 1/9 PASSED, 0 SKIPPED, 0 FAILED

The test case for kprobe_multi won't be run on aarch64, as it is not
supported.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20230813141900.1268-3-laoar.shao@gmail.com
---
 tools/testing/selftests/bpf/DENYLIST.aarch64  |   3 +
 .../selftests/bpf/prog_tests/fill_link_info.c | 342 ++++++++++++++++++
 .../selftests/bpf/progs/test_fill_link_info.c |  42 +++
 3 files changed, 387 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/fill_link_info.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_fill_link_info.c

diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64
index 3b61e8b35d620..7f768d3356987 100644
--- a/tools/testing/selftests/bpf/DENYLIST.aarch64
+++ b/tools/testing/selftests/bpf/DENYLIST.aarch64
@@ -12,3 +12,6 @@ kprobe_multi_test/skel_api                       # libbpf: failed to load BPF sk
 module_attach                                    # prog 'kprobe_multi': failed to auto-attach: -95
 fentry_test/fentry_many_args                     # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524
 fexit_test/fexit_many_args                       # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524
+fill_link_info/kprobe_multi_link_info            # bpf_program__attach_kprobe_multi_opts unexpected error: -95
+fill_link_info/kretprobe_multi_link_info         # bpf_program__attach_kprobe_multi_opts unexpected error: -95
+fill_link_info/kprobe_multi_invalid_ubuff        # bpf_program__attach_kprobe_multi_opts unexpected error: -95
diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
new file mode 100644
index 0000000000000..9d768e0837149
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -0,0 +1,342 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/limits.h>
+#include <test_progs.h>
+#include "trace_helpers.h"
+#include "test_fill_link_info.skel.h"
+
+#define TP_CAT "sched"
+#define TP_NAME "sched_switch"
+
+static const char *kmulti_syms[] = {
+	"bpf_fentry_test2",
+	"bpf_fentry_test1",
+	"bpf_fentry_test3",
+};
+#define KMULTI_CNT ARRAY_SIZE(kmulti_syms)
+static __u64 kmulti_addrs[KMULTI_CNT];
+
+#define KPROBE_FUNC "bpf_fentry_test1"
+static __u64 kprobe_addr;
+
+#define UPROBE_FILE "/proc/self/exe"
+static ssize_t uprobe_offset;
+/* uprobe attach point */
+static noinline void uprobe_func(void)
+{
+	asm volatile ("");
+}
+
+static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long addr,
+				 ssize_t offset, ssize_t entry_offset)
+{
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	char buf[PATH_MAX];
+	int err;
+
+	memset(&info, 0, sizeof(info));
+	buf[0] = '\0';
+
+again:
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "get_link_info"))
+		return -1;
+
+	if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_PERF_EVENT, "link_type"))
+		return -1;
+	if (!ASSERT_EQ(info.perf_event.type, type, "perf_type_match"))
+		return -1;
+
+	switch (info.perf_event.type) {
+	case BPF_PERF_EVENT_KPROBE:
+	case BPF_PERF_EVENT_KRETPROBE:
+		ASSERT_EQ(info.perf_event.kprobe.offset, offset, "kprobe_offset");
+
+		/* In case kernel.kptr_restrict is not permitted or MAX_SYMS is reached */
+		if (addr)
+			ASSERT_EQ(info.perf_event.kprobe.addr, addr + entry_offset,
+				  "kprobe_addr");
+
+		if (!info.perf_event.kprobe.func_name) {
+			ASSERT_EQ(info.perf_event.kprobe.name_len, 0, "name_len");
+			info.perf_event.kprobe.func_name = ptr_to_u64(&buf);
+			info.perf_event.kprobe.name_len = sizeof(buf);
+			goto again;
+		}
+
+		err = strncmp(u64_to_ptr(info.perf_event.kprobe.func_name), KPROBE_FUNC,
+			      strlen(KPROBE_FUNC));
+		ASSERT_EQ(err, 0, "cmp_kprobe_func_name");
+		break;
+	case BPF_PERF_EVENT_TRACEPOINT:
+		if (!info.perf_event.tracepoint.tp_name) {
+			ASSERT_EQ(info.perf_event.tracepoint.name_len, 0, "name_len");
+			info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf);
+			info.perf_event.tracepoint.name_len = sizeof(buf);
+			goto again;
+		}
+
+		err = strncmp(u64_to_ptr(info.perf_event.tracepoint.tp_name), TP_NAME,
+			      strlen(TP_NAME));
+		ASSERT_EQ(err, 0, "cmp_tp_name");
+		break;
+	case BPF_PERF_EVENT_UPROBE:
+	case BPF_PERF_EVENT_URETPROBE:
+		ASSERT_EQ(info.perf_event.uprobe.offset, offset, "uprobe_offset");
+
+		if (!info.perf_event.uprobe.file_name) {
+			ASSERT_EQ(info.perf_event.uprobe.name_len, 0, "name_len");
+			info.perf_event.uprobe.file_name = ptr_to_u64(&buf);
+			info.perf_event.uprobe.name_len = sizeof(buf);
+			goto again;
+		}
+
+		err = strncmp(u64_to_ptr(info.perf_event.uprobe.file_name), UPROBE_FILE,
+			      strlen(UPROBE_FILE));
+			ASSERT_EQ(err, 0, "cmp_file_name");
+		break;
+	default:
+		err = -1;
+		break;
+	}
+	return err;
+}
+
+static void kprobe_fill_invalid_user_buffer(int fd)
+{
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	int err;
+
+	memset(&info, 0, sizeof(info));
+
+	info.perf_event.kprobe.func_name = 0x1; /* invalid address */
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "invalid_buff_and_len");
+
+	info.perf_event.kprobe.name_len = 64;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "invalid_buff");
+
+	info.perf_event.kprobe.func_name = 0;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "invalid_len");
+
+	ASSERT_EQ(info.perf_event.kprobe.addr, 0, "func_addr");
+	ASSERT_EQ(info.perf_event.kprobe.offset, 0, "func_offset");
+	ASSERT_EQ(info.perf_event.type, 0, "type");
+}
+
+static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
+				       enum bpf_perf_event_type type,
+				       bool invalid)
+{
+	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts,
+		.attach_mode = PROBE_ATTACH_MODE_LINK,
+		.retprobe = type == BPF_PERF_EVENT_KRETPROBE,
+	);
+	ssize_t entry_offset = 0;
+	int link_fd, err;
+
+	skel->links.kprobe_run = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run,
+								 KPROBE_FUNC, &opts);
+	if (!ASSERT_OK_PTR(skel->links.kprobe_run, "attach_kprobe"))
+		return;
+
+	link_fd = bpf_link__fd(skel->links.kprobe_run);
+	if (!invalid) {
+		/* See also arch_adjust_kprobe_addr(). */
+		if (skel->kconfig->CONFIG_X86_KERNEL_IBT)
+			entry_offset = 4;
+		err = verify_perf_link_info(link_fd, type, kprobe_addr, 0, entry_offset);
+		ASSERT_OK(err, "verify_perf_link_info");
+	} else {
+		kprobe_fill_invalid_user_buffer(link_fd);
+	}
+	bpf_link__detach(skel->links.kprobe_run);
+}
+
+static void test_tp_fill_link_info(struct test_fill_link_info *skel)
+{
+	int link_fd, err;
+
+	skel->links.tp_run = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME);
+	if (!ASSERT_OK_PTR(skel->links.tp_run, "attach_tp"))
+		return;
+
+	link_fd = bpf_link__fd(skel->links.tp_run);
+	err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_TRACEPOINT, 0, 0, 0);
+	ASSERT_OK(err, "verify_perf_link_info");
+	bpf_link__detach(skel->links.tp_run);
+}
+
+static void test_uprobe_fill_link_info(struct test_fill_link_info *skel,
+				       enum bpf_perf_event_type type)
+{
+	int link_fd, err;
+
+	skel->links.uprobe_run = bpf_program__attach_uprobe(skel->progs.uprobe_run,
+							    type == BPF_PERF_EVENT_URETPROBE,
+							    0, /* self pid */
+							    UPROBE_FILE, uprobe_offset);
+	if (!ASSERT_OK_PTR(skel->links.uprobe_run, "attach_uprobe"))
+		return;
+
+	link_fd = bpf_link__fd(skel->links.uprobe_run);
+	err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, 0);
+	ASSERT_OK(err, "verify_perf_link_info");
+	bpf_link__detach(skel->links.uprobe_run);
+}
+
+static int verify_kmulti_link_info(int fd, bool retprobe)
+{
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	__u64 addrs[KMULTI_CNT];
+	int flags, i, err;
+
+	memset(&info, 0, sizeof(info));
+
+again:
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "get_link_info"))
+		return -1;
+
+	if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_KPROBE_MULTI, "kmulti_type"))
+		return -1;
+
+	ASSERT_EQ(info.kprobe_multi.count, KMULTI_CNT, "func_cnt");
+	flags = info.kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN;
+	if (!retprobe)
+		ASSERT_EQ(flags, 0, "kmulti_flags");
+	else
+		ASSERT_NEQ(flags, 0, "kretmulti_flags");
+
+	if (!info.kprobe_multi.addrs) {
+		info.kprobe_multi.addrs = ptr_to_u64(addrs);
+		goto again;
+	}
+	for (i = 0; i < KMULTI_CNT; i++)
+		ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs");
+	return 0;
+}
+
+static void verify_kmulti_invalid_user_buffer(int fd)
+{
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	__u64 addrs[KMULTI_CNT];
+	int err, i;
+
+	memset(&info, 0, sizeof(info));
+
+	info.kprobe_multi.count = KMULTI_CNT;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "no_addr");
+
+	info.kprobe_multi.addrs = ptr_to_u64(addrs);
+	info.kprobe_multi.count = 0;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "no_cnt");
+
+	for (i = 0; i < KMULTI_CNT; i++)
+		addrs[i] = 0;
+	info.kprobe_multi.count = KMULTI_CNT - 1;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -ENOSPC, "smaller_cnt");
+	for (i = 0; i < KMULTI_CNT - 1; i++)
+		ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs");
+	ASSERT_EQ(addrs[i], 0, "kmulti_addrs");
+
+	for (i = 0; i < KMULTI_CNT; i++)
+		addrs[i] = 0;
+	info.kprobe_multi.count = KMULTI_CNT + 1;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, 0, "bigger_cnt");
+	for (i = 0; i < KMULTI_CNT; i++)
+		ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs");
+
+	info.kprobe_multi.count = KMULTI_CNT;
+	info.kprobe_multi.addrs = 0x1; /* invalid addr */
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "invalid_buff");
+}
+
+static int symbols_cmp_r(const void *a, const void *b)
+{
+	const char **str_a = (const char **) a;
+	const char **str_b = (const char **) b;
+
+	return strcmp(*str_a, *str_b);
+}
+
+static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel,
+					     bool retprobe, bool invalid)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	int link_fd, err;
+
+	opts.syms = kmulti_syms;
+	opts.cnt = KMULTI_CNT;
+	opts.retprobe = retprobe;
+	skel->links.kmulti_run = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run,
+								       NULL, &opts);
+	if (!ASSERT_OK_PTR(skel->links.kmulti_run, "attach_kprobe_multi"))
+		return;
+
+	link_fd = bpf_link__fd(skel->links.kmulti_run);
+	if (!invalid) {
+		err = verify_kmulti_link_info(link_fd, retprobe);
+		ASSERT_OK(err, "verify_kmulti_link_info");
+	} else {
+		verify_kmulti_invalid_user_buffer(link_fd);
+	}
+	bpf_link__detach(skel->links.kmulti_run);
+}
+
+void test_fill_link_info(void)
+{
+	struct test_fill_link_info *skel;
+	int i;
+
+	skel = test_fill_link_info__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	/* load kallsyms to compare the addr */
+	if (!ASSERT_OK(load_kallsyms_refresh(), "load_kallsyms_refresh"))
+		goto cleanup;
+
+	kprobe_addr = ksym_get_addr(KPROBE_FUNC);
+	if (test__start_subtest("kprobe_link_info"))
+		test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, false);
+	if (test__start_subtest("kretprobe_link_info"))
+		test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KRETPROBE, false);
+	if (test__start_subtest("kprobe_invalid_ubuff"))
+		test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, true);
+	if (test__start_subtest("tracepoint_link_info"))
+		test_tp_fill_link_info(skel);
+
+	uprobe_offset = get_uprobe_offset(&uprobe_func);
+	if (test__start_subtest("uprobe_link_info"))
+		test_uprobe_fill_link_info(skel, BPF_PERF_EVENT_UPROBE);
+	if (test__start_subtest("uretprobe_link_info"))
+		test_uprobe_fill_link_info(skel, BPF_PERF_EVENT_URETPROBE);
+
+	qsort(kmulti_syms, KMULTI_CNT, sizeof(kmulti_syms[0]), symbols_cmp_r);
+	for (i = 0; i < KMULTI_CNT; i++)
+		kmulti_addrs[i] = ksym_get_addr(kmulti_syms[i]);
+	if (test__start_subtest("kprobe_multi_link_info"))
+		test_kprobe_multi_fill_link_info(skel, false, false);
+	if (test__start_subtest("kretprobe_multi_link_info"))
+		test_kprobe_multi_fill_link_info(skel, true, false);
+	if (test__start_subtest("kprobe_multi_invalid_ubuff"))
+		test_kprobe_multi_fill_link_info(skel, true, true);
+
+cleanup:
+	test_fill_link_info__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
new file mode 100644
index 0000000000000..564f402d56fef
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+
+extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak;
+
+/* This function is here to have CONFIG_X86_KERNEL_IBT
+ * used and added to object BTF.
+ */
+int unused(void)
+{
+	return CONFIG_X86_KERNEL_IBT ? 0 : 1;
+}
+
+SEC("kprobe")
+int BPF_PROG(kprobe_run)
+{
+	return 0;
+}
+
+SEC("uprobe")
+int BPF_PROG(uprobe_run)
+{
+	return 0;
+}
+
+SEC("tracepoint")
+int BPF_PROG(tp_run)
+{
+	return 0;
+}
+
+SEC("kprobe.multi")
+int BPF_PROG(kmulti_run)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From dd2e84bb3804103ad1c26a21deb4b35b0e166746 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Fri, 28 Jul 2023 17:52:05 +0200
Subject: [PATCH 1283/1806] virtchnl: fix fake 1-elem arrays in structs
 allocated as `nents + 1` - 1

The two most problematic virtchnl structures are virtchnl_rss_key and
virtchnl_rss_lut. Their "flex" arrays have the type of u8, thus, when
allocating / checking, the actual size is calculated as `sizeof +
nents - 1 byte`. But their sizeof() is not 1 byte larger than the size
of such structure with proper flex array, it's two bytes larger due to
the padding. That said, their size is always 1 byte larger unless
there are no tail elements -- then it's +2 bytes.
Add virtchnl_struct_size() macro which will handle this case (and later
other cases as well). Make its calling conv the same as we call
struct_size() to allow it to be drop-in, even though it's unlikely to
become possible to switch to generic API. The macro will calculate a
proper size of a structure with a flex array at the end, so that it
becomes transparent for the compilers, but add the difference from the
old values, so that the real size of sorta-ABI-messages doesn't change.
Use it on the allocation side in IAVF and the receiving side (defined
as static inline in virtchnl.h) for the mentioned two structures.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/iavf/iavf_virtchnl.c   |  6 ++--
 include/linux/avf/virtchnl.h                  | 31 ++++++++++++++-----
 2 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index be3c007ce90a9..10f03054a6034 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1085,8 +1085,7 @@ void iavf_set_rss_key(struct iavf_adapter *adapter)
 			adapter->current_op);
 		return;
 	}
-	len = sizeof(struct virtchnl_rss_key) +
-	      (adapter->rss_key_size * sizeof(u8)) - 1;
+	len = virtchnl_struct_size(vrk, key, adapter->rss_key_size);
 	vrk = kzalloc(len, GFP_KERNEL);
 	if (!vrk)
 		return;
@@ -1117,8 +1116,7 @@ void iavf_set_rss_lut(struct iavf_adapter *adapter)
 			adapter->current_op);
 		return;
 	}
-	len = sizeof(struct virtchnl_rss_lut) +
-	      (adapter->rss_lut_size * sizeof(u8)) - 1;
+	len = virtchnl_struct_size(vrl, lut, adapter->rss_lut_size);
 	vrl = kzalloc(len, GFP_KERNEL);
 	if (!vrl)
 		return;
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index c15221dcb75ec..3ab207c148095 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -866,18 +866,20 @@ VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_promisc_info);
 struct virtchnl_rss_key {
 	u16 vsi_id;
 	u16 key_len;
-	u8 key[1];         /* RSS hash key, packed bytes */
+	u8 key[];          /* RSS hash key, packed bytes */
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key);
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rss_key);
+#define virtchnl_rss_key_LEGACY_SIZEOF	6
 
 struct virtchnl_rss_lut {
 	u16 vsi_id;
 	u16 lut_entries;
-	u8 lut[1];        /* RSS lookup table */
+	u8 lut[];         /* RSS lookup table */
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut);
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rss_lut);
+#define virtchnl_rss_lut_LEGACY_SIZEOF	6
 
 /* VIRTCHNL_OP_GET_RSS_HENA_CAPS
  * VIRTCHNL_OP_SET_RSS_HENA
@@ -1367,6 +1369,17 @@ struct virtchnl_fdir_del {
 
 VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del);
 
+#define __vss_byone(p, member, count, old)				      \
+	(struct_size(p, member, count) + (old - 1 - struct_size(p, member, 0)))
+
+#define __vss(type, func, p, member, count)		\
+	struct type: func(p, member, count, type##_LEGACY_SIZEOF)
+
+#define virtchnl_struct_size(p, m, c)					      \
+	_Generic(*p,							      \
+		 __vss(virtchnl_rss_key, __vss_byone, p, m, c),		      \
+		 __vss(virtchnl_rss_lut, __vss_byone, p, m, c))
+
 /**
  * virtchnl_vc_validate_vf_msg
  * @ver: Virtchnl version info
@@ -1479,19 +1492,21 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 		}
 		break;
 	case VIRTCHNL_OP_CONFIG_RSS_KEY:
-		valid_len = sizeof(struct virtchnl_rss_key);
+		valid_len = virtchnl_rss_key_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_rss_key *vrk =
 				(struct virtchnl_rss_key *)msg;
-			valid_len += vrk->key_len - 1;
+			valid_len = virtchnl_struct_size(vrk, key,
+							 vrk->key_len);
 		}
 		break;
 	case VIRTCHNL_OP_CONFIG_RSS_LUT:
-		valid_len = sizeof(struct virtchnl_rss_lut);
+		valid_len = virtchnl_rss_lut_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_rss_lut *vrl =
 				(struct virtchnl_rss_lut *)msg;
-			valid_len += vrl->lut_entries - 1;
+			valid_len = virtchnl_struct_size(vrl, lut,
+							 vrl->lut_entries);
 		}
 		break;
 	case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
-- 
GitLab


From 5e7f59fa07f86f554c301c7a383bba54d5ef9819 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Fri, 28 Jul 2023 17:52:06 +0200
Subject: [PATCH 1284/1806] virtchnl: fix fake 1-elem arrays in structures
 allocated as `nents + 1`

There are five virtchnl structures, which are allocated and checked in
the code as `nents + 1`, meaning that they always have memory for one
excessive element regardless of their actual number. This comes from
that their sizeof() includes space for 1 element and then they get
allocated via struct_size() or its open-coded equivalents, passing
the actual number of elements.
Expand virtchnl_struct_size() to handle such structures and replace
those 1-elem arrays with proper flex ones. Also fix several places
which open-code %IAVF_VIRTCHNL_VF_RESOURCE_SIZE. Finally, let the
virtchnl_ether_addr_list size be computed automatically when there's
no enough space for the whole list, otherwise we have to open-code
reverse struct_size() logics.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../ethernet/intel/i40e/i40e_virtchnl_pf.c    |  2 +-
 drivers/net/ethernet/intel/iavf/iavf.h        |  6 +-
 .../net/ethernet/intel/iavf/iavf_virtchnl.c   | 44 +++++++-------
 drivers/net/ethernet/intel/ice/ice_virtchnl.c |  2 +-
 include/linux/avf/virtchnl.h                  | 57 ++++++++++++-------
 5 files changed, 59 insertions(+), 52 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 98aca9f8b602d..a6983c2d7c303 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2103,7 +2103,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 		goto err;
 	}
 
-	len = struct_size(vfres, vsi_res, num_vsis);
+	len = virtchnl_struct_size(vfres, vsi_res, num_vsis);
 	vfres = kzalloc(len, GFP_KERNEL);
 	if (!vfres) {
 		aq_ret = -ENOMEM;
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 8cbdebc5b6989..85fba85fbb232 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -92,9 +92,9 @@ struct iavf_vsi {
 #define IAVF_MBPS_DIVISOR	125000 /* divisor to convert to Mbps */
 #define IAVF_MBPS_QUANTA	50
 
-#define IAVF_VIRTCHNL_VF_RESOURCE_SIZE (sizeof(struct virtchnl_vf_resource) + \
-					(IAVF_MAX_VF_VSI * \
-					 sizeof(struct virtchnl_vsi_resource)))
+#define IAVF_VIRTCHNL_VF_RESOURCE_SIZE					\
+	virtchnl_struct_size((struct virtchnl_vf_resource *)NULL,	\
+			     vsi_res, IAVF_MAX_VF_VSI)
 
 /* MAX_MSIX_Q_VECTORS of these are allocated,
  * but we only use one per queue-specific vector.
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 10f03054a6034..4fdac698eb380 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -215,8 +215,7 @@ int iavf_get_vf_config(struct iavf_adapter *adapter)
 	u16 len;
 	int err;
 
-	len = sizeof(struct virtchnl_vf_resource) +
-		IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource);
+	len = IAVF_VIRTCHNL_VF_RESOURCE_SIZE;
 	event.buf_len = len;
 	event.msg_buf = kzalloc(len, GFP_KERNEL);
 	if (!event.msg_buf)
@@ -284,7 +283,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 		return;
 	}
 	adapter->current_op = VIRTCHNL_OP_CONFIG_VSI_QUEUES;
-	len = struct_size(vqci, qpair, pairs);
+	len = virtchnl_struct_size(vqci, qpair, pairs);
 	vqci = kzalloc(len, GFP_KERNEL);
 	if (!vqci)
 		return;
@@ -397,7 +396,7 @@ void iavf_map_queues(struct iavf_adapter *adapter)
 
 	q_vectors = adapter->num_msix_vectors - NONQ_VECS;
 
-	len = struct_size(vimi, vecmap, adapter->num_msix_vectors);
+	len = virtchnl_struct_size(vimi, vecmap, adapter->num_msix_vectors);
 	vimi = kzalloc(len, GFP_KERNEL);
 	if (!vimi)
 		return;
@@ -476,13 +475,11 @@ void iavf_add_ether_addrs(struct iavf_adapter *adapter)
 	}
 	adapter->current_op = VIRTCHNL_OP_ADD_ETH_ADDR;
 
-	len = struct_size(veal, list, count);
+	len = virtchnl_struct_size(veal, list, count);
 	if (len > IAVF_MAX_AQ_BUF_SIZE) {
 		dev_warn(&adapter->pdev->dev, "Too many add MAC changes in one request\n");
-		count = (IAVF_MAX_AQ_BUF_SIZE -
-			 sizeof(struct virtchnl_ether_addr_list)) /
-			sizeof(struct virtchnl_ether_addr);
-		len = struct_size(veal, list, count);
+		while (len > IAVF_MAX_AQ_BUF_SIZE)
+			len = virtchnl_struct_size(veal, list, --count);
 		more = true;
 	}
 
@@ -547,13 +544,11 @@ void iavf_del_ether_addrs(struct iavf_adapter *adapter)
 	}
 	adapter->current_op = VIRTCHNL_OP_DEL_ETH_ADDR;
 
-	len = struct_size(veal, list, count);
+	len = virtchnl_struct_size(veal, list, count);
 	if (len > IAVF_MAX_AQ_BUF_SIZE) {
 		dev_warn(&adapter->pdev->dev, "Too many delete MAC changes in one request\n");
-		count = (IAVF_MAX_AQ_BUF_SIZE -
-			 sizeof(struct virtchnl_ether_addr_list)) /
-			sizeof(struct virtchnl_ether_addr);
-		len = struct_size(veal, list, count);
+		while (len > IAVF_MAX_AQ_BUF_SIZE)
+			len = virtchnl_struct_size(veal, list, --count);
 		more = true;
 	}
 	veal = kzalloc(len, GFP_ATOMIC);
@@ -687,12 +682,12 @@ void iavf_add_vlans(struct iavf_adapter *adapter)
 
 		adapter->current_op = VIRTCHNL_OP_ADD_VLAN;
 
-		len = sizeof(*vvfl) + (count * sizeof(u16));
+		len = virtchnl_struct_size(vvfl, vlan_id, count);
 		if (len > IAVF_MAX_AQ_BUF_SIZE) {
 			dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n");
-			count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(*vvfl)) /
-				sizeof(u16);
-			len = sizeof(*vvfl) + (count * sizeof(u16));
+			while (len > IAVF_MAX_AQ_BUF_SIZE)
+				len = virtchnl_struct_size(vvfl, vlan_id,
+							   --count);
 			more = true;
 		}
 		vvfl = kzalloc(len, GFP_ATOMIC);
@@ -838,12 +833,12 @@ void iavf_del_vlans(struct iavf_adapter *adapter)
 
 		adapter->current_op = VIRTCHNL_OP_DEL_VLAN;
 
-		len = sizeof(*vvfl) + (count * sizeof(u16));
+		len = virtchnl_struct_size(vvfl, vlan_id, count);
 		if (len > IAVF_MAX_AQ_BUF_SIZE) {
 			dev_warn(&adapter->pdev->dev, "Too many delete VLAN changes in one request\n");
-			count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(*vvfl)) /
-				sizeof(u16);
-			len = sizeof(*vvfl) + (count * sizeof(u16));
+			while (len > IAVF_MAX_AQ_BUF_SIZE)
+				len = virtchnl_struct_size(vvfl, vlan_id,
+							   --count);
 			more = true;
 		}
 		vvfl = kzalloc(len, GFP_ATOMIC);
@@ -2173,9 +2168,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		}
 		break;
 	case VIRTCHNL_OP_GET_VF_RESOURCES: {
-		u16 len = sizeof(struct virtchnl_vf_resource) +
-			  IAVF_MAX_VF_VSI *
-			  sizeof(struct virtchnl_vsi_resource);
+		u16 len = IAVF_VIRTCHNL_VF_RESOURCE_SIZE;
+
 		memcpy(adapter->vf_res, msg, min(msglen, len));
 		iavf_validate_num_queues(adapter);
 		iavf_vf_parse_hw_config(&adapter->hw, adapter->vf_res);
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 85d9965315021..4a02ed91ba737 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -428,7 +428,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 		goto err;
 	}
 
-	len = sizeof(struct virtchnl_vf_resource);
+	len = virtchnl_struct_size(vfres, vsi_res, 0);
 
 	vfres = kzalloc(len, GFP_KERNEL);
 	if (!vfres) {
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 3ab207c148095..c1a20b533fc0d 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -268,10 +268,11 @@ struct virtchnl_vf_resource {
 	u32 rss_key_size;
 	u32 rss_lut_size;
 
-	struct virtchnl_vsi_resource vsi_res[1];
+	struct virtchnl_vsi_resource vsi_res[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(36, virtchnl_vf_resource);
+VIRTCHNL_CHECK_STRUCT_LEN(20, virtchnl_vf_resource);
+#define virtchnl_vf_resource_LEGACY_SIZEOF	36
 
 /* VIRTCHNL_OP_CONFIG_TX_QUEUE
  * VF sends this message to set up parameters for one TX queue.
@@ -340,10 +341,11 @@ struct virtchnl_vsi_queue_config_info {
 	u16 vsi_id;
 	u16 num_queue_pairs;
 	u32 pad;
-	struct virtchnl_queue_pair_info qpair[1];
+	struct virtchnl_queue_pair_info qpair[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info);
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vsi_queue_config_info);
+#define virtchnl_vsi_queue_config_info_LEGACY_SIZEOF	72
 
 /* VIRTCHNL_OP_REQUEST_QUEUES
  * VF sends this message to request the PF to allocate additional queues to
@@ -385,10 +387,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_vector_map);
 
 struct virtchnl_irq_map_info {
 	u16 num_vectors;
-	struct virtchnl_vector_map vecmap[1];
+	struct virtchnl_vector_map vecmap[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(14, virtchnl_irq_map_info);
+VIRTCHNL_CHECK_STRUCT_LEN(2, virtchnl_irq_map_info);
+#define virtchnl_irq_map_info_LEGACY_SIZEOF	14
 
 /* VIRTCHNL_OP_ENABLE_QUEUES
  * VIRTCHNL_OP_DISABLE_QUEUES
@@ -459,10 +462,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr);
 struct virtchnl_ether_addr_list {
 	u16 vsi_id;
 	u16 num_elements;
-	struct virtchnl_ether_addr list[1];
+	struct virtchnl_ether_addr list[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_ether_addr_list);
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_ether_addr_list);
+#define virtchnl_ether_addr_list_LEGACY_SIZEOF	12
 
 /* VIRTCHNL_OP_ADD_VLAN
  * VF sends this message to add one or more VLAN tag filters for receives.
@@ -481,10 +485,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_ether_addr_list);
 struct virtchnl_vlan_filter_list {
 	u16 vsi_id;
 	u16 num_elements;
-	u16 vlan_id[1];
+	u16 vlan_id[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_vlan_filter_list);
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_vlan_filter_list);
+#define virtchnl_vlan_filter_list_LEGACY_SIZEOF	6
 
 /* This enum is used for all of the VIRTCHNL_VF_OFFLOAD_VLAN_V2_CAPS related
  * structures and opcodes.
@@ -1372,11 +1377,19 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del);
 #define __vss_byone(p, member, count, old)				      \
 	(struct_size(p, member, count) + (old - 1 - struct_size(p, member, 0)))
 
+#define __vss_full(p, member, count, old)				      \
+	(struct_size(p, member, count) + (old - struct_size(p, member, 0)))
+
 #define __vss(type, func, p, member, count)		\
 	struct type: func(p, member, count, type##_LEGACY_SIZEOF)
 
 #define virtchnl_struct_size(p, m, c)					      \
 	_Generic(*p,							      \
+		 __vss(virtchnl_vf_resource, __vss_full, p, m, c),	      \
+		 __vss(virtchnl_vsi_queue_config_info, __vss_full, p, m, c),  \
+		 __vss(virtchnl_irq_map_info, __vss_full, p, m, c),	      \
+		 __vss(virtchnl_ether_addr_list, __vss_full, p, m, c),	      \
+		 __vss(virtchnl_vlan_filter_list, __vss_full, p, m, c),	      \
 		 __vss(virtchnl_rss_key, __vss_byone, p, m, c),		      \
 		 __vss(virtchnl_rss_lut, __vss_byone, p, m, c))
 
@@ -1414,24 +1427,23 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 		valid_len = sizeof(struct virtchnl_rxq_info);
 		break;
 	case VIRTCHNL_OP_CONFIG_VSI_QUEUES:
-		valid_len = sizeof(struct virtchnl_vsi_queue_config_info);
+		valid_len = virtchnl_vsi_queue_config_info_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_vsi_queue_config_info *vqc =
 			    (struct virtchnl_vsi_queue_config_info *)msg;
-			valid_len += (vqc->num_queue_pairs *
-				      sizeof(struct
-					     virtchnl_queue_pair_info));
+			valid_len = virtchnl_struct_size(vqc, qpair,
+							 vqc->num_queue_pairs);
 			if (vqc->num_queue_pairs == 0)
 				err_msg_format = true;
 		}
 		break;
 	case VIRTCHNL_OP_CONFIG_IRQ_MAP:
-		valid_len = sizeof(struct virtchnl_irq_map_info);
+		valid_len = virtchnl_irq_map_info_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_irq_map_info *vimi =
 			    (struct virtchnl_irq_map_info *)msg;
-			valid_len += (vimi->num_vectors *
-				      sizeof(struct virtchnl_vector_map));
+			valid_len = virtchnl_struct_size(vimi, vecmap,
+							 vimi->num_vectors);
 			if (vimi->num_vectors == 0)
 				err_msg_format = true;
 		}
@@ -1442,23 +1454,24 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 		break;
 	case VIRTCHNL_OP_ADD_ETH_ADDR:
 	case VIRTCHNL_OP_DEL_ETH_ADDR:
-		valid_len = sizeof(struct virtchnl_ether_addr_list);
+		valid_len = virtchnl_ether_addr_list_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_ether_addr_list *veal =
 			    (struct virtchnl_ether_addr_list *)msg;
-			valid_len += veal->num_elements *
-			    sizeof(struct virtchnl_ether_addr);
+			valid_len = virtchnl_struct_size(veal, list,
+							 veal->num_elements);
 			if (veal->num_elements == 0)
 				err_msg_format = true;
 		}
 		break;
 	case VIRTCHNL_OP_ADD_VLAN:
 	case VIRTCHNL_OP_DEL_VLAN:
-		valid_len = sizeof(struct virtchnl_vlan_filter_list);
+		valid_len = virtchnl_vlan_filter_list_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_vlan_filter_list *vfl =
 			    (struct virtchnl_vlan_filter_list *)msg;
-			valid_len += vfl->num_elements * sizeof(u16);
+			valid_len = virtchnl_struct_size(vfl, vlan_id,
+							 vfl->num_elements);
 			if (vfl->num_elements == 0)
 				err_msg_format = true;
 		}
-- 
GitLab


From b0654e64dbaf62f565b5f2b4fbd92202e88dcba3 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Fri, 28 Jul 2023 17:52:07 +0200
Subject: [PATCH 1285/1806] virtchnl: fix fake 1-elem arrays for structures
 allocated as `nents`

Finally, fix 3 structures which are allocated technically correctly,
i.e. the calculated size equals to the one that struct_size() would
return, except for sizeof(). For &virtchnl_vlan_filter_list_v2, use
the same approach when there are no enough space as taken previously
for &virtchnl_vlan_filter_list, i.e. let the maximum size be calculated
automatically instead of trying to guestimate it using maths.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../ethernet/intel/i40e/i40e_virtchnl_pf.c    |  7 ++--
 drivers/net/ethernet/intel/iavf/iavf_client.c |  4 +-
 drivers/net/ethernet/intel/iavf/iavf_client.h |  2 +-
 .../net/ethernet/intel/iavf/iavf_virtchnl.c   | 25 +++++-------
 include/linux/avf/virtchnl.h                  | 39 ++++++++++++-------
 5 files changed, 40 insertions(+), 37 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index a6983c2d7c303..8ea1a238dcefe 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -506,6 +506,7 @@ i40e_config_rdma_qvlist(struct i40e_vf *vf,
 	struct virtchnl_rdma_qv_info *qv_info;
 	u32 v_idx, i, reg_idx, reg;
 	u32 next_q_idx, next_q_type;
+	size_t size;
 	u32 msix_vf;
 	int ret = 0;
 
@@ -521,9 +522,9 @@ i40e_config_rdma_qvlist(struct i40e_vf *vf,
 	}
 
 	kfree(vf->qvlist_info);
-	vf->qvlist_info = kzalloc(struct_size(vf->qvlist_info, qv_info,
-					      qvlist_info->num_vectors - 1),
-				  GFP_KERNEL);
+	size = virtchnl_struct_size(vf->qvlist_info, qv_info,
+				    qvlist_info->num_vectors);
+	vf->qvlist_info = kzalloc(size, GFP_KERNEL);
 	if (!vf->qvlist_info) {
 		ret = -ENOMEM;
 		goto err_out;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.c b/drivers/net/ethernet/intel/iavf/iavf_client.c
index 93c903c02c648..e6051b6355aa7 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_client.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_client.c
@@ -469,8 +469,8 @@ static int iavf_client_setup_qvlist(struct iavf_info *ldev,
 	}
 
 	v_qvlist_info = (struct virtchnl_rdma_qvlist_info *)qvlist_info;
-	msg_size = struct_size(v_qvlist_info, qv_info,
-			       v_qvlist_info->num_vectors - 1);
+	msg_size = virtchnl_struct_size(v_qvlist_info, qv_info,
+					v_qvlist_info->num_vectors);
 
 	adapter->client_pending |= BIT(VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP);
 	err = iavf_aq_send_msg_to_pf(&adapter->hw,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.h b/drivers/net/ethernet/intel/iavf/iavf_client.h
index c5d51d7dc7cc8..500269bc0f5b0 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_client.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_client.h
@@ -53,7 +53,7 @@ struct iavf_qv_info {
 
 struct iavf_qvlist_info {
 	u32 num_vectors;
-	struct iavf_qv_info qv_info[1];
+	struct iavf_qv_info qv_info[];
 };
 
 #define IAVF_CLIENT_MSIX_ALL 0xFFFFFFFF
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 4fdac698eb380..f9727e9c3d630 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -727,15 +727,12 @@ void iavf_add_vlans(struct iavf_adapter *adapter)
 			more = true;
 		}
 
-		len = sizeof(*vvfl_v2) + ((count - 1) *
-					  sizeof(struct virtchnl_vlan_filter));
+		len = virtchnl_struct_size(vvfl_v2, filters, count);
 		if (len > IAVF_MAX_AQ_BUF_SIZE) {
 			dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n");
-			count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(*vvfl_v2)) /
-				sizeof(struct virtchnl_vlan_filter);
-			len = sizeof(*vvfl_v2) +
-				((count - 1) *
-				 sizeof(struct virtchnl_vlan_filter));
+			while (len > IAVF_MAX_AQ_BUF_SIZE)
+				len = virtchnl_struct_size(vvfl_v2, filters,
+							   --count);
 			more = true;
 		}
 
@@ -879,16 +876,12 @@ void iavf_del_vlans(struct iavf_adapter *adapter)
 
 		adapter->current_op = VIRTCHNL_OP_DEL_VLAN_V2;
 
-		len = sizeof(*vvfl_v2) +
-			((count - 1) * sizeof(struct virtchnl_vlan_filter));
+		len = virtchnl_struct_size(vvfl_v2, filters, count);
 		if (len > IAVF_MAX_AQ_BUF_SIZE) {
 			dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n");
-			count = (IAVF_MAX_AQ_BUF_SIZE -
-				 sizeof(*vvfl_v2)) /
-				sizeof(struct virtchnl_vlan_filter);
-			len = sizeof(*vvfl_v2) +
-				((count - 1) *
-				 sizeof(struct virtchnl_vlan_filter));
+			while (len > IAVF_MAX_AQ_BUF_SIZE)
+				len = virtchnl_struct_size(vvfl_v2, filters,
+							   --count);
 			more = true;
 		}
 
@@ -1492,7 +1485,7 @@ void iavf_enable_channels(struct iavf_adapter *adapter)
 		return;
 	}
 
-	len = struct_size(vti, list, adapter->num_tc - 1);
+	len = virtchnl_struct_size(vti, list, adapter->num_tc);
 	vti = kzalloc(len, GFP_KERNEL);
 	if (!vti)
 		return;
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index c1a20b533fc0d..d0807ad43f933 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -716,10 +716,11 @@ struct virtchnl_vlan_filter_list_v2 {
 	u16 vport_id;
 	u16 num_elements;
 	u8 pad[4];
-	struct virtchnl_vlan_filter filters[1];
+	struct virtchnl_vlan_filter filters[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_vlan_filter_list_v2);
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vlan_filter_list_v2);
+#define virtchnl_vlan_filter_list_v2_LEGACY_SIZEOF	40
 
 /* VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2
  * VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2
@@ -918,10 +919,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_channel_info);
 struct virtchnl_tc_info {
 	u32	num_tc;
 	u32	pad;
-	struct	virtchnl_channel_info list[1];
+	struct virtchnl_channel_info list[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_tc_info);
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_tc_info);
+#define virtchnl_tc_info_LEGACY_SIZEOF	24
 
 /* VIRTCHNL_ADD_CLOUD_FILTER
  * VIRTCHNL_DEL_CLOUD_FILTER
@@ -1059,10 +1061,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_rdma_qv_info);
 
 struct virtchnl_rdma_qvlist_info {
 	u32 num_vectors;
-	struct virtchnl_rdma_qv_info qv_info[1];
+	struct virtchnl_rdma_qv_info qv_info[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_rdma_qvlist_info);
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rdma_qvlist_info);
+#define virtchnl_rdma_qvlist_info_LEGACY_SIZEOF	16
 
 /* VF reset states - these are written into the RSTAT register:
  * VFGEN_RSTAT on the VF
@@ -1377,6 +1380,9 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del);
 #define __vss_byone(p, member, count, old)				      \
 	(struct_size(p, member, count) + (old - 1 - struct_size(p, member, 0)))
 
+#define __vss_byelem(p, member, count, old)				      \
+	(struct_size(p, member, count - 1) + (old - struct_size(p, member, 0)))
+
 #define __vss_full(p, member, count, old)				      \
 	(struct_size(p, member, count) + (old - struct_size(p, member, 0)))
 
@@ -1390,6 +1396,9 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del);
 		 __vss(virtchnl_irq_map_info, __vss_full, p, m, c),	      \
 		 __vss(virtchnl_ether_addr_list, __vss_full, p, m, c),	      \
 		 __vss(virtchnl_vlan_filter_list, __vss_full, p, m, c),	      \
+		 __vss(virtchnl_vlan_filter_list_v2, __vss_byelem, p, m, c),  \
+		 __vss(virtchnl_tc_info, __vss_byelem, p, m, c),	      \
+		 __vss(virtchnl_rdma_qvlist_info, __vss_byelem, p, m, c),     \
 		 __vss(virtchnl_rss_key, __vss_byone, p, m, c),		      \
 		 __vss(virtchnl_rss_lut, __vss_byone, p, m, c))
 
@@ -1495,13 +1504,13 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 	case VIRTCHNL_OP_RELEASE_RDMA_IRQ_MAP:
 		break;
 	case VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP:
-		valid_len = sizeof(struct virtchnl_rdma_qvlist_info);
+		valid_len = virtchnl_rdma_qvlist_info_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_rdma_qvlist_info *qv =
 				(struct virtchnl_rdma_qvlist_info *)msg;
 
-			valid_len += ((qv->num_vectors - 1) *
-				sizeof(struct virtchnl_rdma_qv_info));
+			valid_len = virtchnl_struct_size(qv, qv_info,
+							 qv->num_vectors);
 		}
 		break;
 	case VIRTCHNL_OP_CONFIG_RSS_KEY:
@@ -1534,12 +1543,12 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 		valid_len = sizeof(struct virtchnl_vf_res_request);
 		break;
 	case VIRTCHNL_OP_ENABLE_CHANNELS:
-		valid_len = sizeof(struct virtchnl_tc_info);
+		valid_len = virtchnl_tc_info_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_tc_info *vti =
 				(struct virtchnl_tc_info *)msg;
-			valid_len += (vti->num_tc - 1) *
-				     sizeof(struct virtchnl_channel_info);
+			valid_len = virtchnl_struct_size(vti, list,
+							 vti->num_tc);
 			if (vti->num_tc == 0)
 				err_msg_format = true;
 		}
@@ -1566,13 +1575,13 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 		break;
 	case VIRTCHNL_OP_ADD_VLAN_V2:
 	case VIRTCHNL_OP_DEL_VLAN_V2:
-		valid_len = sizeof(struct virtchnl_vlan_filter_list_v2);
+		valid_len = virtchnl_vlan_filter_list_v2_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_vlan_filter_list_v2 *vfl =
 			    (struct virtchnl_vlan_filter_list_v2 *)msg;
 
-			valid_len += (vfl->num_elements - 1) *
-				sizeof(struct virtchnl_vlan_filter);
+			valid_len = virtchnl_struct_size(vfl, filters,
+							 vfl->num_elements);
 
 			if (vfl->num_elements == 0) {
 				err_msg_format = true;
-- 
GitLab


From e16e6c6df475b10b1ed933a6827798312612358f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 16 Aug 2023 11:56:50 +0200
Subject: [PATCH 1286/1806] bpftool: Implement link show support for tcx

Add support to dump tcx link information to bpftool. This adds a
common helper show_link_ifindex_{plain,json}() which can be reused
also for other link types. The plain text and json device output is
the same format as in bpftool net dump.

Below shows an example link dump output along with a cgroup link
for comparison:

  # bpftool link
  [...]
  10: cgroup  prog 1977
        cgroup_id 1  attach_type cgroup_inet6_post_bind
  [...]
  13: tcx  prog 2053
        ifindex enp5s0(3)  attach_type tcx_ingress
  14: tcx  prog 2080
        ifindex enp5s0(3)  attach_type tcx_egress
  [...]

Equivalent json output:

  # bpftool link --json
  [...]
  {
    "id": 10,
    "type": "cgroup",
    "prog_id": 1977,
    "cgroup_id": 1,
    "attach_type": "cgroup_inet6_post_bind"
  },
  [...]
  {
    "id": 13,
    "type": "tcx",
    "prog_id": 2053,
    "devname": "enp5s0",
    "ifindex": 3,
    "attach_type": "tcx_ingress"
  },
  {
    "id": 14,
    "type": "tcx",
    "prog_id": 2080,
    "devname": "enp5s0",
    "ifindex": 3,
    "attach_type": "tcx_egress"
  }
  [...]

Suggested-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Link: https://lore.kernel.org/r/20230816095651.10014-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/bpf/bpftool/link.c | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 65a168df63bc1..a3774594f1547 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -150,6 +150,18 @@ static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr)
 		jsonw_uint_field(wtr, "attach_type", attach_type);
 }
 
+static void show_link_ifindex_json(__u32 ifindex, json_writer_t *wtr)
+{
+	char devname[IF_NAMESIZE] = "(unknown)";
+
+	if (ifindex)
+		if_indextoname(ifindex, devname);
+	else
+		snprintf(devname, sizeof(devname), "(detached)");
+	jsonw_string_field(wtr, "devname", devname);
+	jsonw_uint_field(wtr, "ifindex", ifindex);
+}
+
 static bool is_iter_map_target(const char *target_name)
 {
 	return strcmp(target_name, "bpf_map_elem") == 0 ||
@@ -433,6 +445,10 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_NETFILTER:
 		netfilter_dump_json(info, json_wtr);
 		break;
+	case BPF_LINK_TYPE_TCX:
+		show_link_ifindex_json(info->tcx.ifindex, json_wtr);
+		show_link_attach_type_json(info->tcx.attach_type, json_wtr);
+		break;
 	case BPF_LINK_TYPE_STRUCT_OPS:
 		jsonw_uint_field(json_wtr, "map_id",
 				 info->struct_ops.map_id);
@@ -509,6 +525,22 @@ static void show_link_attach_type_plain(__u32 attach_type)
 		printf("attach_type %u  ", attach_type);
 }
 
+static void show_link_ifindex_plain(__u32 ifindex)
+{
+	char devname[IF_NAMESIZE * 2] = "(unknown)";
+	char tmpname[IF_NAMESIZE];
+	char *ret = NULL;
+
+	if (ifindex)
+		ret = if_indextoname(ifindex, tmpname);
+	else
+		snprintf(devname, sizeof(devname), "(detached)");
+	if (ret)
+		snprintf(devname, sizeof(devname), "%s(%d)",
+			 tmpname, ifindex);
+	printf("ifindex %s  ", devname);
+}
+
 static void show_iter_plain(struct bpf_link_info *info)
 {
 	const char *target_name = u64_to_ptr(info->iter.target_name);
@@ -745,6 +777,11 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_NETFILTER:
 		netfilter_dump_plain(info);
 		break;
+	case BPF_LINK_TYPE_TCX:
+		printf("\n\t");
+		show_link_ifindex_plain(info->tcx.ifindex);
+		show_link_attach_type_plain(info->tcx.attach_type);
+		break;
 	case BPF_LINK_TYPE_KPROBE_MULTI:
 		show_kprobe_multi_plain(info);
 		break;
-- 
GitLab


From 053bbf9bff58864be880d7e9a5af586793dbb7de Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 16 Aug 2023 11:56:51 +0200
Subject: [PATCH 1287/1806] bpftool: Implement link show support for xdp

Add support to dump XDP link information to bpftool. This reuses the
recently added show_link_ifindex_{plain,json}(). The XDP link info only
exposes the ifindex.

Below shows an example link dump output, and a cgroup link is included
for comparison, too:

  # bpftool link
  [...]
  10: cgroup  prog 2466
        cgroup_id 1  attach_type cgroup_inet6_post_bind
  [...]
  16: xdp  prog 2477
        ifindex enp5s0(3)
  [...]

Equivalent json output:

  # bpftool link --json
  [...]
  {
    "id": 10,
    "type": "cgroup",
    "prog_id": 2466,
    "cgroup_id": 1,
    "attach_type": "cgroup_inet6_post_bind"
  },
  [...]
  {
    "id": 16,
    "type": "xdp",
    "prog_id": 2477,
    "devname": "enp5s0",
    "ifindex": 3
  }
  [...]

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/r/20230816095651.10014-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/bpf/bpftool/link.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index a3774594f1547..0b214f6ab5c83 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -449,6 +449,9 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 		show_link_ifindex_json(info->tcx.ifindex, json_wtr);
 		show_link_attach_type_json(info->tcx.attach_type, json_wtr);
 		break;
+	case BPF_LINK_TYPE_XDP:
+		show_link_ifindex_json(info->xdp.ifindex, json_wtr);
+		break;
 	case BPF_LINK_TYPE_STRUCT_OPS:
 		jsonw_uint_field(json_wtr, "map_id",
 				 info->struct_ops.map_id);
@@ -782,6 +785,10 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 		show_link_ifindex_plain(info->tcx.ifindex);
 		show_link_attach_type_plain(info->tcx.attach_type);
 		break;
+	case BPF_LINK_TYPE_XDP:
+		printf("\n\t");
+		show_link_ifindex_plain(info->xdp.ifindex);
+		break;
 	case BPF_LINK_TYPE_KPROBE_MULTI:
 		show_kprobe_multi_plain(info);
 		break;
-- 
GitLab


From 0dd061a6a115f25132989cbd591a25afb2dee086 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 16 Aug 2023 09:11:56 +0800
Subject: [PATCH 1288/1806] bpf: Add update_socket_protocol hook

Add a hook named update_socket_protocol in __sys_socket(), for bpf
progs to attach to and update socket protocol. One user case is to
force legacy TCP apps to create and use MPTCP sockets instead of
TCP ones.

Define a fmod_ret set named bpf_mptcp_fmodret_ids, add the hook
update_socket_protocol into this set, and register it in
bpf_mptcp_kfunc_init().

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/79
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Link: https://lore.kernel.org/r/ac84be00f97072a46f8a72b4e2be46cbb7fa5053.1692147782.git.geliang.tang@suse.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 net/mptcp/bpf.c | 15 +++++++++++++++
 net/socket.c    | 26 +++++++++++++++++++++++++-
 2 files changed, 40 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index 5a0a84ad94af3..8a16672b94e23 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -19,3 +19,18 @@ struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk)
 
 	return NULL;
 }
+
+BTF_SET8_START(bpf_mptcp_fmodret_ids)
+BTF_ID_FLAGS(func, update_socket_protocol)
+BTF_SET8_END(bpf_mptcp_fmodret_ids)
+
+static const struct btf_kfunc_id_set bpf_mptcp_fmodret_set = {
+	.owner = THIS_MODULE,
+	.set   = &bpf_mptcp_fmodret_ids,
+};
+
+static int __init bpf_mptcp_kfunc_init(void)
+{
+	return register_btf_fmodret_id_set(&bpf_mptcp_fmodret_set);
+}
+late_initcall(bpf_mptcp_kfunc_init);
diff --git a/net/socket.c b/net/socket.c
index 5d4e37595e9aa..fdb5233bf560c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1657,12 +1657,36 @@ struct file *__sys_socket_file(int family, int type, int protocol)
 	return sock_alloc_file(sock, flags, NULL);
 }
 
+/*	A hook for bpf progs to attach to and update socket protocol.
+ *
+ *	A static noinline declaration here could cause the compiler to
+ *	optimize away the function. A global noinline declaration will
+ *	keep the definition, but may optimize away the callsite.
+ *	Therefore, __weak is needed to ensure that the call is still
+ *	emitted, by telling the compiler that we don't know what the
+ *	function might eventually be.
+ *
+ *	__diag_* below are needed to dismiss the missing prototype warning.
+ */
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "A fmod_ret entry point for BPF programs");
+
+__weak noinline int update_socket_protocol(int family, int type, int protocol)
+{
+	return protocol;
+}
+
+__diag_pop();
+
 int __sys_socket(int family, int type, int protocol)
 {
 	struct socket *sock;
 	int flags;
 
-	sock = __sys_socket_create(family, type, protocol);
+	sock = __sys_socket_create(family, type,
+				   update_socket_protocol(family, type, protocol));
 	if (IS_ERR(sock))
 		return PTR_ERR(sock);
 
-- 
GitLab


From 97c9c652089b7081d5ed03b1dd0076c04ab12a4a Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 16 Aug 2023 09:11:57 +0800
Subject: [PATCH 1289/1806] selftests/bpf: Add two mptcp netns helpers

Add two netns helpers for mptcp tests: create_netns() and
cleanup_netns(). Use them in test_base().

These new helpers will be re-used in the following commits
introducing new tests.

Acked-by: Yonghong Song <yonghong.song@linux.dev>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Link: https://lore.kernel.org/r/7506371fb6c417b401cc9d7365fe455754f4ba3f.1692147782.git.geliang.tang@suse.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 31 +++++++++++++------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index cd0c42fff7c05..76afb51917724 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -22,6 +22,24 @@ struct mptcp_storage {
 	char ca_name[TCP_CA_NAME_MAX];
 };
 
+static struct nstoken *create_netns(void)
+{
+	SYS(fail, "ip netns add %s", NS_TEST);
+	SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
+
+	return open_netns(NS_TEST);
+fail:
+	return NULL;
+}
+
+static void cleanup_netns(struct nstoken *nstoken)
+{
+	if (nstoken)
+		close_netns(nstoken);
+
+	SYS_NOFAIL("ip netns del %s &> /dev/null", NS_TEST);
+}
+
 static int verify_tsk(int map_fd, int client_fd)
 {
 	int err, cfd = client_fd;
@@ -147,11 +165,8 @@ static void test_base(void)
 	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
-	SYS(fail, "ip netns add %s", NS_TEST);
-	SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
-
-	nstoken = open_netns(NS_TEST);
-	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+	nstoken = create_netns();
+	if (!ASSERT_OK_PTR(nstoken, "create_netns"))
 		goto fail;
 
 	/* without MPTCP */
@@ -174,11 +189,7 @@ with_mptcp:
 	close(server_fd);
 
 fail:
-	if (nstoken)
-		close_netns(nstoken);
-
-	SYS_NOFAIL("ip netns del " NS_TEST " &> /dev/null");
-
+	cleanup_netns(nstoken);
 	close(cgroup_fd);
 }
 
-- 
GitLab


From 207746550262e81b1e360d003a67f7ef7bacfbae Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 16 Aug 2023 09:11:58 +0800
Subject: [PATCH 1290/1806] selftests/bpf: Fix error checks of mptcp
 open_and_load

Return libbpf_get_error(), instead of -EIO, for the error from
mptcp_sock__open_and_load().

Load success means prog_fd and map_fd are always valid. So drop these
unneeded ASSERT_GE checks for them in mptcp run_test().

Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Link: https://lore.kernel.org/r/db5fcb93293df9ab173edcbaf8252465b80da6f2.1692147782.git.geliang.tang@suse.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/mptcp.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 76afb51917724..3d3999067e276 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -118,24 +118,14 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 
 	sock_skel = mptcp_sock__open_and_load();
 	if (!ASSERT_OK_PTR(sock_skel, "skel_open_load"))
-		return -EIO;
+		return libbpf_get_error(sock_skel);
 
 	err = mptcp_sock__attach(sock_skel);
 	if (!ASSERT_OK(err, "skel_attach"))
 		goto out;
 
 	prog_fd = bpf_program__fd(sock_skel->progs._sockops);
-	if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd")) {
-		err = -EIO;
-		goto out;
-	}
-
 	map_fd = bpf_map__fd(sock_skel->maps.socket_storage_map);
-	if (!ASSERT_GE(map_fd, 0, "bpf_map__fd")) {
-		err = -EIO;
-		goto out;
-	}
-
 	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0);
 	if (!ASSERT_OK(err, "bpf_prog_attach"))
 		goto out;
-- 
GitLab


From ddba122428a75261fc4d3547f4e7e4aa6b67caef Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 16 Aug 2023 09:11:59 +0800
Subject: [PATCH 1291/1806] selftests/bpf: Add mptcpify test

Implement a new test program mptcpify: if the family is AF_INET or
AF_INET6, the type is SOCK_STREAM, and the protocol ID is 0 or
IPPROTO_TCP, set it to IPPROTO_MPTCP. It will be hooked in
update_socket_protocol().

Extend the MPTCP test base, add a selftest test_mptcpify() for the
mptcpify case. Open and load the mptcpify test prog to mptcpify the
TCP sockets dynamically, then use start_server() and connect_to_fd()
to create a TCP socket, but actually what's created is an MPTCP
socket, which can be verified through 'getsockopt(SOL_PROTOCOL)'
and 'getsockopt(MPTCP_INFO)'.

Acked-by: Yonghong Song <yonghong.song@linux.dev>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Link: https://lore.kernel.org/r/364e72f307e7bb38382ec7442c182d76298a9c41.1692147782.git.geliang.tang@suse.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 141 ++++++++++++++++++
 tools/testing/selftests/bpf/progs/mptcpify.c  |  20 +++
 2 files changed, 161 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcpify.c

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 3d3999067e276..7c0be7cf550b7 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -2,17 +2,59 @@
 /* Copyright (c) 2020, Tessares SA. */
 /* Copyright (c) 2022, SUSE. */
 
+#include <linux/const.h>
+#include <netinet/in.h>
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
 #include "mptcp_sock.skel.h"
+#include "mptcpify.skel.h"
 
 #define NS_TEST "mptcp_ns"
 
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
+#ifndef SOL_MPTCP
+#define SOL_MPTCP 284
+#endif
+#ifndef MPTCP_INFO
+#define MPTCP_INFO		1
+#endif
+#ifndef MPTCP_INFO_FLAG_FALLBACK
+#define MPTCP_INFO_FLAG_FALLBACK		_BITUL(0)
+#endif
+#ifndef MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED
+#define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED	_BITUL(1)
+#endif
+
 #ifndef TCP_CA_NAME_MAX
 #define TCP_CA_NAME_MAX	16
 #endif
 
+struct __mptcp_info {
+	__u8	mptcpi_subflows;
+	__u8	mptcpi_add_addr_signal;
+	__u8	mptcpi_add_addr_accepted;
+	__u8	mptcpi_subflows_max;
+	__u8	mptcpi_add_addr_signal_max;
+	__u8	mptcpi_add_addr_accepted_max;
+	__u32	mptcpi_flags;
+	__u32	mptcpi_token;
+	__u64	mptcpi_write_seq;
+	__u64	mptcpi_snd_una;
+	__u64	mptcpi_rcv_nxt;
+	__u8	mptcpi_local_addr_used;
+	__u8	mptcpi_local_addr_max;
+	__u8	mptcpi_csum_enabled;
+	__u32	mptcpi_retransmits;
+	__u64	mptcpi_bytes_retrans;
+	__u64	mptcpi_bytes_sent;
+	__u64	mptcpi_bytes_received;
+	__u64	mptcpi_bytes_acked;
+};
+
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
@@ -183,8 +225,107 @@ fail:
 	close(cgroup_fd);
 }
 
+static void send_byte(int fd)
+{
+	char b = 0x55;
+
+	ASSERT_EQ(write(fd, &b, sizeof(b)), 1, "send single byte");
+}
+
+static int verify_mptcpify(int server_fd, int client_fd)
+{
+	struct __mptcp_info info;
+	socklen_t optlen;
+	int protocol;
+	int err = 0;
+
+	optlen = sizeof(protocol);
+	if (!ASSERT_OK(getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen),
+		       "getsockopt(SOL_PROTOCOL)"))
+		return -1;
+
+	if (!ASSERT_EQ(protocol, IPPROTO_MPTCP, "protocol isn't MPTCP"))
+		err++;
+
+	optlen = sizeof(info);
+	if (!ASSERT_OK(getsockopt(client_fd, SOL_MPTCP, MPTCP_INFO, &info, &optlen),
+		       "getsockopt(MPTCP_INFO)"))
+		return -1;
+
+	if (!ASSERT_GE(info.mptcpi_flags, 0, "unexpected mptcpi_flags"))
+		err++;
+	if (!ASSERT_FALSE(info.mptcpi_flags & MPTCP_INFO_FLAG_FALLBACK,
+			  "MPTCP fallback"))
+		err++;
+	if (!ASSERT_TRUE(info.mptcpi_flags & MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED,
+			 "no remote key received"))
+		err++;
+
+	return err;
+}
+
+static int run_mptcpify(int cgroup_fd)
+{
+	int server_fd, client_fd, err = 0;
+	struct mptcpify *mptcpify_skel;
+
+	mptcpify_skel = mptcpify__open_and_load();
+	if (!ASSERT_OK_PTR(mptcpify_skel, "skel_open_load"))
+		return libbpf_get_error(mptcpify_skel);
+
+	err = mptcpify__attach(mptcpify_skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto out;
+
+	/* without MPTCP */
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(server_fd, 0, "start_server")) {
+		err = -EIO;
+		goto out;
+	}
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_GE(client_fd, 0, "connect to fd")) {
+		err = -EIO;
+		goto close_server;
+	}
+
+	send_byte(client_fd);
+
+	err = verify_mptcpify(server_fd, client_fd);
+
+	close(client_fd);
+close_server:
+	close(server_fd);
+out:
+	mptcpify__destroy(mptcpify_skel);
+	return err;
+}
+
+static void test_mptcpify(void)
+{
+	struct nstoken *nstoken = NULL;
+	int cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/mptcpify");
+	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
+		return;
+
+	nstoken = create_netns();
+	if (!ASSERT_OK_PTR(nstoken, "create_netns"))
+		goto fail;
+
+	ASSERT_OK(run_mptcpify(cgroup_fd), "run_mptcpify");
+
+fail:
+	cleanup_netns(nstoken);
+	close(cgroup_fd);
+}
+
 void test_mptcp(void)
 {
 	if (test__start_subtest("base"))
 		test_base();
+	if (test__start_subtest("mptcpify"))
+		test_mptcpify();
 }
diff --git a/tools/testing/selftests/bpf/progs/mptcpify.c b/tools/testing/selftests/bpf/progs/mptcpify.c
new file mode 100644
index 0000000000000..53301ae8a8f7c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcpify.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023, SUSE. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include "bpf_tracing_net.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fmod_ret/update_socket_protocol")
+int BPF_PROG(mptcpify, int family, int type, int protocol)
+{
+	if ((family == AF_INET || family == AF_INET6) &&
+	    type == SOCK_STREAM &&
+	    (!protocol || protocol == IPPROTO_TCP)) {
+		return IPPROTO_MPTCP;
+	}
+
+	return protocol;
+}
-- 
GitLab


From 42b118c9f97f5e0431b6a364a789c212bed96652 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 16 Aug 2023 19:33:44 -0700
Subject: [PATCH 1292/1806] Revert "net: ethernet: ti: am65-cpsw: add mqprio
 qdisc offload in channel mode"

This reverts commit 90bc21aaef4adaefceda2d385756138fc247c0c2.

Patch was merged too hastily, Vladimir requested changes in:
https://lore.kernel.org/all/20230816121305.5dio5tk3chge2ndh@skbuf/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c |   3 -
 drivers/net/ethernet/ti/am65-cpsw-qos.c  | 295 +----------------------
 drivers/net/ethernet/ti/am65-cpsw-qos.h  |  14 --
 3 files changed, 1 insertion(+), 311 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 09593d6fd618e..bea6fc0f324ce 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -633,9 +633,6 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev)
 	/* restore vlan configurations */
 	vlan_for_each(ndev, cpsw_restore_vlans, port);
 
-	/* Initialize QoS */
-	am65_cpsw_qos_mqprio_init(port);
-
 	phylink_start(port->slave.phylink);
 
 	return 0;
diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c
index 3b3e75fbb64d0..9ac2ff05d5017 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-qos.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c
@@ -17,12 +17,9 @@
 
 #define AM65_CPSW_REG_CTL			0x004
 #define AM65_CPSW_PN_REG_CTL			0x004
-#define AM65_CPSW_PN_REG_TX_PRI_MAP		0x018
-#define AM65_CPSW_PN_REG_RX_PRI_MAP		0x020
 #define AM65_CPSW_PN_REG_FIFO_STATUS		0x050
 #define AM65_CPSW_PN_REG_EST_CTL		0x060
 #define AM65_CPSW_PN_REG_PRI_CIR(pri)		(0x140 + 4 * (pri))
-#define AM65_CPSW_PN_REG_PRI_EIR(pri)		(0x160 + 4 * (pri))
 
 /* AM65_CPSW_REG_CTL register fields */
 #define AM65_CPSW_CTL_EST_EN			BIT(18)
@@ -59,12 +56,6 @@ enum timer_act {
 	TACT_SKIP_PROG,		/* just buffer can be updated */
 };
 
-/* number of traffic classes (FIFOs) per port */
-#define AM65_CPSW_PN_TC_NUM			8
-#define AM65_CPSW_PN_TX_PRI_MAP_DEFAULT		0x76543210
-
-static int am65_cpsw_setup_mqprio(struct net_device *ndev, void *type_data);
-
 static int am65_cpsw_port_est_enabled(struct am65_cpsw_port *port)
 {
 	return port->qos.est_oper || port->qos.est_admin;
@@ -550,6 +541,7 @@ static void am65_cpsw_est_link_up(struct net_device *ndev, int link_speed)
 	ktime_t cur_time;
 	s64 delta;
 
+	port->qos.link_speed = link_speed;
 	if (!am65_cpsw_port_est_enabled(port))
 		return;
 
@@ -803,8 +795,6 @@ int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 		return am65_cpsw_tc_query_caps(ndev, type_data);
 	case TC_SETUP_QDISC_TAPRIO:
 		return am65_cpsw_setup_taprio(ndev, type_data);
-	case TC_SETUP_QDISC_MQPRIO:
-		return am65_cpsw_setup_mqprio(ndev, type_data);
 	case TC_SETUP_BLOCK:
 		return am65_cpsw_qos_setup_tc_block(ndev, type_data);
 	default:
@@ -812,15 +802,10 @@ int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	}
 }
 
-static void am65_cpsw_tx_pn_shaper_link_up(struct am65_cpsw_port *port);
-
 void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed)
 {
 	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
 
-	port->qos.link_speed = link_speed;
-	am65_cpsw_tx_pn_shaper_link_up(port);
-
 	if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS))
 		return;
 
@@ -952,281 +937,3 @@ void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common)
 		       host->port_base + AM65_CPSW_PN_REG_PRI_CIR(tx_ch));
 	}
 }
-
-static void am65_cpsw_tx_pn_shaper_apply(struct am65_cpsw_port *port)
-{
-	struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
-	struct am65_cpsw_common *common = port->common;
-	struct tc_mqprio_qopt_offload *mqprio;
-	bool shaper_en;
-	u32 rate_mbps;
-	int i;
-
-	mqprio = &p_mqprio->mqprio_hw;
-	shaper_en = p_mqprio->shaper_en && !p_mqprio->shaper_susp;
-
-	for (i = 0; i < mqprio->qopt.num_tc; i++) {
-		rate_mbps = 0;
-		if (shaper_en) {
-			rate_mbps = mqprio->min_rate[i] * 8 / 1000000;
-			rate_mbps = am65_cpsw_qos_tx_rate_calc(rate_mbps,
-							       common->bus_freq);
-		}
-
-		writel(rate_mbps,
-		       port->port_base + AM65_CPSW_PN_REG_PRI_CIR(i));
-	}
-
-	for (i = 0; i < mqprio->qopt.num_tc; i++) {
-		rate_mbps = 0;
-		if (shaper_en && mqprio->max_rate[i]) {
-			rate_mbps = mqprio->max_rate[i] - mqprio->min_rate[i];
-			rate_mbps = rate_mbps * 8 / 1000000;
-			rate_mbps = am65_cpsw_qos_tx_rate_calc(rate_mbps,
-							       common->bus_freq);
-		}
-
-		writel(rate_mbps,
-		       port->port_base + AM65_CPSW_PN_REG_PRI_EIR(i));
-	}
-}
-
-static void am65_cpsw_tx_pn_shaper_link_up(struct am65_cpsw_port *port)
-{
-	struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
-	struct am65_cpsw_common *common = port->common;
-	bool shaper_susp = false;
-
-	if (!p_mqprio->enable || !p_mqprio->shaper_en)
-		return;
-
-	if (p_mqprio->max_rate_total > port->qos.link_speed)
-		shaper_susp = true;
-
-	if (p_mqprio->shaper_susp == shaper_susp)
-		return;
-
-	if (shaper_susp)
-		dev_info(common->dev,
-			 "Port%u: total shaper tx rate > link speed - suspend shaper\n",
-			 port->port_id);
-	else
-		dev_info(common->dev,
-			 "Port%u: link recover - resume shaper\n",
-			 port->port_id);
-
-	p_mqprio->shaper_susp = shaper_susp;
-	am65_cpsw_tx_pn_shaper_apply(port);
-}
-
-void am65_cpsw_qos_mqprio_init(struct am65_cpsw_port *port)
-{
-	struct am65_cpsw_host *host = am65_common_get_host(port->common);
-	struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
-	struct tc_mqprio_qopt_offload *mqprio;
-	u32 tx_prio_map = 0, rx_prio_map;
-	int i, fifo;
-
-	mqprio = &p_mqprio->mqprio_hw;
-	rx_prio_map = readl(host->port_base + AM65_CPSW_PN_REG_RX_PRI_MAP);
-
-	if (p_mqprio->enable) {
-		for (i = 0; i < AM65_CPSW_PN_TC_NUM; i++) {
-			fifo = mqprio->qopt.prio_tc_map[i];
-			tx_prio_map |= fifo << (4 * i);
-		}
-
-		netdev_set_num_tc(port->ndev, mqprio->qopt.num_tc);
-		for (i = 0; i < mqprio->qopt.num_tc; i++) {
-			netdev_set_tc_queue(port->ndev, i,
-					    mqprio->qopt.count[i],
-					    mqprio->qopt.offset[i]);
-			if (!i) {
-				p_mqprio->tc0_q = mqprio->qopt.offset[i];
-				rx_prio_map &= ~(0x7 << (4 * p_mqprio->tc0_q));
-			}
-		}
-	} else {
-		/* restore default configuration */
-		netdev_reset_tc(port->ndev);
-		tx_prio_map = AM65_CPSW_PN_TX_PRI_MAP_DEFAULT;
-		rx_prio_map |= p_mqprio->tc0_q << (4 * p_mqprio->tc0_q);
-		p_mqprio->tc0_q = 0;
-	}
-
-	writel(tx_prio_map,
-	       port->port_base + AM65_CPSW_PN_REG_TX_PRI_MAP);
-	writel(rx_prio_map,
-	       host->port_base + AM65_CPSW_PN_REG_RX_PRI_MAP);
-
-	am65_cpsw_tx_pn_shaper_apply(port);
-}
-
-static int am65_cpsw_mqprio_verify(struct am65_cpsw_port *port,
-				   struct tc_mqprio_qopt_offload *mqprio)
-{
-	int i;
-
-	for (i = 0; i < mqprio->qopt.num_tc; i++) {
-		unsigned int last = mqprio->qopt.offset[i] +
-				    mqprio->qopt.count[i];
-
-		if (mqprio->qopt.offset[i] >= port->ndev->real_num_tx_queues ||
-		    !mqprio->qopt.count[i] ||
-		    last >  port->ndev->real_num_tx_queues)
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int am65_cpsw_mqprio_verify_shaper(struct am65_cpsw_port *port,
-					  struct tc_mqprio_qopt_offload *mqprio,
-					  u64 *max_rate)
-{
-	struct am65_cpsw_common *common = port->common;
-	u64 min_rate_total = 0, max_rate_total = 0;
-	u32 min_rate_msk = 0, max_rate_msk = 0;
-	bool has_min_rate, has_max_rate;
-	int num_tc, i;
-
-	has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
-	has_max_rate = !!(mqprio->flags & TC_MQPRIO_F_MAX_RATE);
-
-	if (!has_min_rate && has_max_rate)
-		return -EOPNOTSUPP;
-
-	if (!has_min_rate)
-		return 0;
-
-	num_tc = mqprio->qopt.num_tc;
-
-	for (i = num_tc - 1; i >= 0; i--) {
-		u32 ch_msk;
-
-		if (mqprio->min_rate[i])
-			min_rate_msk |= BIT(i);
-		min_rate_total +=  mqprio->min_rate[i];
-
-		if (has_max_rate) {
-			if (mqprio->max_rate[i])
-				max_rate_msk |= BIT(i);
-			max_rate_total +=  mqprio->max_rate[i];
-
-			if (!mqprio->min_rate[i] && mqprio->max_rate[i]) {
-				dev_err(common->dev, "TX tc%d rate max>0 but min=0\n",
-					i);
-				return -EINVAL;
-			}
-
-			if (mqprio->max_rate[i] &&
-			    mqprio->max_rate[i] < mqprio->min_rate[i]) {
-				dev_err(common->dev, "TX tc%d rate min(%llu)>max(%llu)\n",
-					i, mqprio->min_rate[i],
-					mqprio->max_rate[i]);
-				return -EINVAL;
-			}
-		}
-
-		ch_msk = GENMASK(num_tc - 1, i);
-		if ((min_rate_msk & BIT(i)) && (min_rate_msk ^ ch_msk)) {
-			dev_err(common->dev, "TX Min rate limiting has to be enabled sequentially hi->lo tx_rate_msk%x\n",
-				min_rate_msk);
-			return -EINVAL;
-		}
-
-		if ((max_rate_msk & BIT(i)) && (max_rate_msk ^ ch_msk)) {
-			dev_err(common->dev, "TX max rate limiting has to be enabled sequentially hi->lo tx_rate_msk%x\n",
-				max_rate_msk);
-			return -EINVAL;
-		}
-	}
-	min_rate_total *= 8;
-	min_rate_total /= 1000 * 1000;
-	max_rate_total *= 8;
-	max_rate_total /= 1000 * 1000;
-
-	if (port->qos.link_speed != SPEED_UNKNOWN) {
-		if (min_rate_total > port->qos.link_speed) {
-			dev_err(common->dev, "TX rate min exceed %llu link speed %d\n",
-				min_rate_total, port->qos.link_speed);
-			return -EINVAL;
-		}
-
-		if (max_rate_total > port->qos.link_speed) {
-			dev_err(common->dev, "TX rate max exceed %llu link speed %d\n",
-				max_rate_total, port->qos.link_speed);
-			return -EINVAL;
-		}
-	}
-
-	*max_rate = max_t(u64, min_rate_total, max_rate_total);
-
-	return 0;
-}
-
-static int am65_cpsw_setup_mqprio(struct net_device *ndev, void *type_data)
-{
-	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
-	struct tc_mqprio_qopt_offload *mqprio = type_data;
-	struct am65_cpsw_common *common = port->common;
-	struct am65_cpsw_mqprio *p_mqprio;
-	bool has_min_rate;
-	int num_tc, ret;
-	u64 max_rate;
-
-	p_mqprio = &port->qos.mqprio;
-
-	if (!mqprio->qopt.hw)
-		goto skip_check;
-
-	if (mqprio->mode != TC_MQPRIO_MODE_CHANNEL)
-		return -EOPNOTSUPP;
-
-	num_tc = mqprio->qopt.num_tc;
-	if (num_tc > AM65_CPSW_PN_TC_NUM)
-		return -ERANGE;
-
-	if ((mqprio->flags & TC_MQPRIO_F_SHAPER) &&
-	    mqprio->shaper != TC_MQPRIO_SHAPER_BW_RATE)
-		return -EOPNOTSUPP;
-
-	ret = am65_cpsw_mqprio_verify(port, mqprio);
-	if (ret)
-		return ret;
-
-	ret = am65_cpsw_mqprio_verify_shaper(port, mqprio, &max_rate);
-	if (ret)
-		return ret;
-
-skip_check:
-	ret = pm_runtime_get_sync(common->dev);
-	if (ret < 0) {
-		pm_runtime_put_noidle(common->dev);
-		return ret;
-	}
-
-	if (mqprio->qopt.hw) {
-		memcpy(&p_mqprio->mqprio_hw, mqprio, sizeof(*mqprio));
-		has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
-		p_mqprio->enable = 1;
-		p_mqprio->shaper_en = has_min_rate;
-		p_mqprio->shaper_susp = !has_min_rate;
-		p_mqprio->max_rate_total = max_rate;
-	} else {
-		unsigned int tc0_q = p_mqprio->tc0_q;
-
-		memset(p_mqprio, 0, sizeof(*p_mqprio));
-		p_mqprio->mqprio_hw.qopt.num_tc = AM65_CPSW_PN_TC_NUM;
-		p_mqprio->tc0_q = tc0_q;
-	}
-
-	if (!netif_running(ndev))
-		goto exit_put;
-
-	am65_cpsw_qos_mqprio_init(port);
-
-exit_put:
-	pm_runtime_put(common->dev);
-	return 0;
-}
diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.h b/drivers/net/ethernet/ti/am65-cpsw-qos.h
index 247a42788687b..0cc2a3b3d7f9e 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-qos.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-qos.h
@@ -7,10 +7,8 @@
 
 #include <linux/netdevice.h>
 #include <net/pkt_sched.h>
-#include <net/pkt_cls.h>
 
 struct am65_cpsw_common;
-struct am65_cpsw_port;
 
 struct am65_cpsw_est {
 	int buf;
@@ -18,16 +16,6 @@ struct am65_cpsw_est {
 	struct tc_taprio_qopt_offload taprio;
 };
 
-struct am65_cpsw_mqprio {
-	struct tc_mqprio_qopt_offload mqprio_hw;
-	u64 max_rate_total;
-
-	unsigned enable:1;
-	unsigned shaper_en:1;
-	unsigned shaper_susp:1;
-	unsigned tc0_q:3;
-};
-
 struct am65_cpsw_ale_ratelimit {
 	unsigned long cookie;
 	u64 rate_packet_ps;
@@ -38,7 +26,6 @@ struct am65_cpsw_qos {
 	struct am65_cpsw_est *est_oper;
 	ktime_t link_down_time;
 	int link_speed;
-	struct am65_cpsw_mqprio mqprio;
 
 	struct am65_cpsw_ale_ratelimit ale_bc_ratelimit;
 	struct am65_cpsw_ale_ratelimit ale_mc_ratelimit;
@@ -48,7 +35,6 @@ int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 			       void *type_data);
 void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed);
 void am65_cpsw_qos_link_down(struct net_device *ndev);
-void am65_cpsw_qos_mqprio_init(struct am65_cpsw_port *port);
 int am65_cpsw_qos_ndo_tx_p0_set_maxrate(struct net_device *ndev, int queue, u32 rate_mbps);
 void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common);
 
-- 
GitLab


From 74e7940e0d21328784322b7966d1ec65e9c11c52 Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Fri, 11 Aug 2023 08:11:04 -0700
Subject: [PATCH 1293/1806] ice: remove unused methods

Following methods were found to no longer be in use:
ice_is_pca9575_present
ice_mac_fltr_exist
ice_napi_del

Remove them.

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c    | 15 -------
 drivers/net/ethernet/intel/ice/ice_lib.h    |  2 -
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 19 --------
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h |  1 -
 drivers/net/ethernet/intel/ice/ice_switch.c | 48 ---------------------
 drivers/net/ethernet/intel/ice/ice_switch.h |  1 -
 6 files changed, 86 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 927518fcad51c..54aa01d2a474c 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2943,21 +2943,6 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi)
 		synchronize_irq(vsi->q_vectors[i]->irq.virq);
 }
 
-/**
- * ice_napi_del - Remove NAPI handler for the VSI
- * @vsi: VSI for which NAPI handler is to be removed
- */
-void ice_napi_del(struct ice_vsi *vsi)
-{
-	int v_idx;
-
-	if (!vsi->netdev)
-		return;
-
-	ice_for_each_q_vector(vsi, v_idx)
-		netif_napi_del(&vsi->q_vectors[v_idx]->napi);
-}
-
 /**
  * ice_vsi_release - Delete a VSI and free its resources
  * @vsi: the VSI being removed
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index dd53fe968ad86..cb6599cb8be68 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -93,8 +93,6 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
 struct ice_vsi *
 ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);
 
-void ice_napi_del(struct ice_vsi *vsi);
-
 int ice_vsi_release(struct ice_vsi *vsi);
 
 void ice_vsi_close(struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index a38614d21ea8f..a0da1bb55ba1d 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -3308,25 +3308,6 @@ int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data)
 	return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL);
 }
 
-/**
- * ice_is_pca9575_present
- * @hw: pointer to the hw struct
- *
- * Check if the SW IO expander is present in the netlist
- */
-bool ice_is_pca9575_present(struct ice_hw *hw)
-{
-	u16 handle = 0;
-	int status;
-
-	if (!ice_is_e810t(hw))
-		return false;
-
-	status = ice_get_pca9575_handle(hw, &handle);
-
-	return !status && handle;
-}
-
 /**
  * ice_ptp_reset_ts_memory - Reset timestamp memory for all blocks
  * @hw: pointer to the HW struct
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 1969425f00848..07cd023b0efd0 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -199,7 +199,6 @@ int ice_ptp_init_phy_e810(struct ice_hw *hw);
 int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data);
 int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data);
 int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data);
-bool ice_is_pca9575_present(struct ice_hw *hw);
 
 #define PFTSYN_SEM_BYTES	4
 
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index a7afb612fe32e..24c3f481848b7 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -3408,54 +3408,6 @@ exit:
 	return status;
 }
 
-/**
- * ice_mac_fltr_exist - does this MAC filter exist for given VSI
- * @hw: pointer to the hardware structure
- * @mac: MAC address to be checked (for MAC filter)
- * @vsi_handle: check MAC filter for this VSI
- */
-bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle)
-{
-	struct ice_fltr_mgmt_list_entry *entry;
-	struct list_head *rule_head;
-	struct ice_switch_info *sw;
-	struct mutex *rule_lock; /* Lock to protect filter rule list */
-	u16 hw_vsi_id;
-
-	if (!ice_is_vsi_valid(hw, vsi_handle))
-		return false;
-
-	hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
-	sw = hw->switch_info;
-	rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules;
-	if (!rule_head)
-		return false;
-
-	rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock;
-	mutex_lock(rule_lock);
-	list_for_each_entry(entry, rule_head, list_entry) {
-		struct ice_fltr_info *f_info = &entry->fltr_info;
-		u8 *mac_addr = &f_info->l_data.mac.mac_addr[0];
-
-		if (is_zero_ether_addr(mac_addr))
-			continue;
-
-		if (f_info->flag != ICE_FLTR_TX ||
-		    f_info->src_id != ICE_SRC_ID_VSI ||
-		    f_info->lkup_type != ICE_SW_LKUP_MAC ||
-		    f_info->fltr_act != ICE_FWD_TO_VSI ||
-		    hw_vsi_id != f_info->fwd_id.hw_vsi_id)
-			continue;
-
-		if (ether_addr_equal(mac, mac_addr)) {
-			mutex_unlock(rule_lock);
-			return true;
-		}
-	}
-	mutex_unlock(rule_lock);
-	return false;
-}
-
 /**
  * ice_vlan_fltr_exist - does this VLAN filter exist for given VSI
  * @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index 0bd4320e39dfe..db7e501b7e0a4 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -371,7 +371,6 @@ int ice_add_vlan(struct ice_hw *hw, struct list_head *m_list);
 int ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list);
 int ice_add_mac(struct ice_hw *hw, struct list_head *m_lst);
 int ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst);
-bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle);
 bool ice_vlan_fltr_exist(struct ice_hw *hw, u16 vlan_id, u16 vsi_handle);
 int ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list);
 int ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list);
-- 
GitLab


From 708b352fc6938089d5fe9fce91ee51648d611ff1 Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Wed, 9 Aug 2023 15:39:08 +0200
Subject: [PATCH 1294/1806] ice: refactor ice_ddp to make functions static

As following methods are not used outside of ice_ddp,
they can be made static:
ice_verify_pgk
ice_pkg_val_buf
ice_aq_download_pkg
ice_aq_update_pkg
ice_find_seg_in_pkg

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ddp.c | 120 ++++++++++++-----------
 drivers/net/ethernet/intel/ice/ice_ddp.h |  10 --
 2 files changed, 61 insertions(+), 69 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index d71ed210f9c41..b27ec93638b6b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -30,7 +30,7 @@ static const struct ice_tunnel_type_scan tnls[] = {
  * Verifies various attributes of the package file, including length, format
  * version, and the requirement of at least one segment.
  */
-enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len)
+static enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len)
 {
 	u32 seg_count;
 	u32 i;
@@ -118,7 +118,7 @@ static enum ice_ddp_state ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver)
  *
  * This helper function validates a buffer's header.
  */
-struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf)
+static struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf)
 {
 	struct ice_buf_hdr *hdr;
 	u16 section_count;
@@ -1152,6 +1152,54 @@ static void ice_release_global_cfg_lock(struct ice_hw *hw)
 	ice_release_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID);
 }
 
+/**
+ * ice_aq_download_pkg
+ * @hw: pointer to the hardware structure
+ * @pkg_buf: the package buffer to transfer
+ * @buf_size: the size of the package buffer
+ * @last_buf: last buffer indicator
+ * @error_offset: returns error offset
+ * @error_info: returns error information
+ * @cd: pointer to command details structure or NULL
+ *
+ * Download Package (0x0C40)
+ */
+static int
+ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
+		    u16 buf_size, bool last_buf, u32 *error_offset,
+		    u32 *error_info, struct ice_sq_cd *cd)
+{
+	struct ice_aqc_download_pkg *cmd;
+	struct ice_aq_desc desc;
+	int status;
+
+	if (error_offset)
+		*error_offset = 0;
+	if (error_info)
+		*error_info = 0;
+
+	cmd = &desc.params.download_pkg;
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg);
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	if (last_buf)
+		cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
+
+	status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
+	if (status == -EIO) {
+		/* Read error from buffer only when the FW returned an error */
+		struct ice_aqc_download_pkg_resp *resp;
+
+		resp = (struct ice_aqc_download_pkg_resp *)pkg_buf;
+		if (error_offset)
+			*error_offset = le32_to_cpu(resp->error_offset);
+		if (error_info)
+			*error_info = le32_to_cpu(resp->error_info);
+	}
+
+	return status;
+}
+
 /**
  * ice_dwnld_cfg_bufs
  * @hw: pointer to the hardware structure
@@ -1294,20 +1342,20 @@ static enum ice_ddp_state ice_download_pkg(struct ice_hw *hw,
 }
 
 /**
- * ice_aq_download_pkg
+ * ice_aq_update_pkg
  * @hw: pointer to the hardware structure
- * @pkg_buf: the package buffer to transfer
- * @buf_size: the size of the package buffer
+ * @pkg_buf: the package cmd buffer
+ * @buf_size: the size of the package cmd buffer
  * @last_buf: last buffer indicator
  * @error_offset: returns error offset
  * @error_info: returns error information
  * @cd: pointer to command details structure or NULL
  *
- * Download Package (0x0C40)
+ * Update Package (0x0C42)
  */
-int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
-			u16 buf_size, bool last_buf, u32 *error_offset,
-			u32 *error_info, struct ice_sq_cd *cd)
+static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
+			     u16 buf_size, bool last_buf, u32 *error_offset,
+			     u32 *error_info, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_download_pkg *cmd;
 	struct ice_aq_desc desc;
@@ -1319,7 +1367,7 @@ int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 		*error_info = 0;
 
 	cmd = &desc.params.download_pkg;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg);
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg);
 	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
 
 	if (last_buf)
@@ -1360,53 +1408,6 @@ int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 	return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
 }
 
-/**
- * ice_aq_update_pkg
- * @hw: pointer to the hardware structure
- * @pkg_buf: the package cmd buffer
- * @buf_size: the size of the package cmd buffer
- * @last_buf: last buffer indicator
- * @error_offset: returns error offset
- * @error_info: returns error information
- * @cd: pointer to command details structure or NULL
- *
- * Update Package (0x0C42)
- */
-static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
-			     u16 buf_size, bool last_buf, u32 *error_offset,
-			     u32 *error_info, struct ice_sq_cd *cd)
-{
-	struct ice_aqc_download_pkg *cmd;
-	struct ice_aq_desc desc;
-	int status;
-
-	if (error_offset)
-		*error_offset = 0;
-	if (error_info)
-		*error_info = 0;
-
-	cmd = &desc.params.download_pkg;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-
-	if (last_buf)
-		cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
-
-	status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
-	if (status == -EIO) {
-		/* Read error from buffer only when the FW returned an error */
-		struct ice_aqc_download_pkg_resp *resp;
-
-		resp = (struct ice_aqc_download_pkg_resp *)pkg_buf;
-		if (error_offset)
-			*error_offset = le32_to_cpu(resp->error_offset);
-		if (error_info)
-			*error_info = le32_to_cpu(resp->error_info);
-	}
-
-	return status;
-}
-
 /**
  * ice_update_pkg_no_lock
  * @hw: pointer to the hardware structure
@@ -1470,8 +1471,9 @@ int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
  * success it returns a pointer to the segment header, otherwise it will
  * return NULL.
  */
-struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type,
-						struct ice_pkg_hdr *pkg_hdr)
+static struct ice_generic_seg_hdr *
+ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type,
+		    struct ice_pkg_hdr *pkg_hdr)
 {
 	u32 i;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h
index 41acfe26df1c6..abb5f32f2ef4e 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.h
@@ -416,21 +416,13 @@ struct ice_pkg_enum {
 	void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset);
 };
 
-int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
-			u16 buf_size, bool last_buf, u32 *error_offset,
-			u32 *error_info, struct ice_sq_cd *cd);
 int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 			  u16 buf_size, struct ice_sq_cd *cd);
 
 void *ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size);
 
-enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len);
-
 struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw);
 
-struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type,
-						struct ice_pkg_hdr *pkg_hdr);
-
 int ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count);
 int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count);
 
@@ -439,6 +431,4 @@ u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld);
 void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
 			   u32 sect_type);
 
-struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf);
-
 #endif
-- 
GitLab


From 45f5478c039c104c03c698c18ac30f21a728208f Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Wed, 9 Aug 2023 15:39:09 +0200
Subject: [PATCH 1295/1806] ice: refactor ice_lib to make functions static

As following methods are not used outside of ice_lib,
they can be made static:
ice_vsi_is_vlan_pruning_ena
ice_vsi_cfg_frame_size

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 70 ++++++++++++------------
 drivers/net/ethernet/intel/ice/ice_lib.h |  3 -
 2 files changed, 35 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 54aa01d2a474c..d3fb2b7535e76 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1227,6 +1227,20 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 	ctxt->info.q_mapping[1] = cpu_to_le16(qcount);
 }
 
+/**
+ * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not
+ * @vsi: VSI to check whether or not VLAN pruning is enabled.
+ *
+ * returns true if Rx VLAN pruning is enabled and false otherwise.
+ */
+static bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi)
+{
+	if (!vsi)
+		return false;
+
+	return (vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA);
+}
+
 /**
  * ice_vsi_init - Create and initialize a VSI
  * @vsi: the VSI being configured
@@ -1684,6 +1698,27 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi)
 			vsi_num, status);
 }
 
+/**
+ * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length
+ * @vsi: VSI
+ */
+static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi)
+{
+	if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) {
+		vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX;
+		vsi->rx_buf_len = ICE_RXBUF_1664;
+#if (PAGE_SIZE < 8192)
+	} else if (!ICE_2K_TOO_SMALL_WITH_PADDING &&
+		   (vsi->netdev->mtu <= ETH_DATA_LEN)) {
+		vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN;
+		vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN;
+#endif
+	} else {
+		vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX;
+		vsi->rx_buf_len = ICE_RXBUF_3072;
+	}
+}
+
 /**
  * ice_pf_state_is_nominal - checks the PF for nominal state
  * @pf: pointer to PF to check
@@ -1758,27 +1793,6 @@ void ice_update_eth_stats(struct ice_vsi *vsi)
 	vsi->stat_offsets_loaded = true;
 }
 
-/**
- * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length
- * @vsi: VSI
- */
-void ice_vsi_cfg_frame_size(struct ice_vsi *vsi)
-{
-	if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) {
-		vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX;
-		vsi->rx_buf_len = ICE_RXBUF_1664;
-#if (PAGE_SIZE < 8192)
-	} else if (!ICE_2K_TOO_SMALL_WITH_PADDING &&
-		   (vsi->netdev->mtu <= ETH_DATA_LEN)) {
-		vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN;
-		vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN;
-#endif
-	} else {
-		vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX;
-		vsi->rx_buf_len = ICE_RXBUF_3072;
-	}
-}
-
 /**
  * ice_write_qrxflxp_cntxt - write/configure QRXFLXP_CNTXT register
  * @hw: HW pointer
@@ -2185,20 +2199,6 @@ bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi)
 	return false;
 }
 
-/**
- * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not
- * @vsi: VSI to check whether or not VLAN pruning is enabled.
- *
- * returns true if Rx VLAN pruning is enabled and false otherwise.
- */
-bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi)
-{
-	if (!vsi)
-		return false;
-
-	return (vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA);
-}
-
 static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi)
 {
 	if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) {
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index cb6599cb8be68..f24f5d1e6f9c7 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -76,8 +76,6 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi);
 
 int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi);
 
-bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi);
-
 void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
 
 int ice_set_link(struct ice_vsi *vsi, bool ena);
@@ -128,7 +126,6 @@ void ice_update_tx_ring_stats(struct ice_tx_ring *ring, u64 pkts, u64 bytes);
 
 void ice_update_rx_ring_stats(struct ice_rx_ring *ring, u64 pkts, u64 bytes);
 
-void ice_vsi_cfg_frame_size(struct ice_vsi *vsi);
 void ice_write_intrl(struct ice_q_vector *q_vector, u8 intrl);
 void ice_write_itr(struct ice_ring_container *rc, u16 itr);
 void ice_set_q_vector_intrl(struct ice_q_vector *q_vector);
-- 
GitLab


From cc9c60c9edfed4fa629975848e80a45c17332b9a Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Wed, 9 Aug 2023 15:39:10 +0200
Subject: [PATCH 1296/1806] ice: refactor ice_vf_lib to make functions static

As following methods are not used outside ice_vf_lib,
they can be made static:
ice_vf_rebuild_host_vlan_cfg
ice_vf_rebuild_host_tx_rate_cfg
ice_vf_set_host_trust_cfg
ice_vf_rebuild_host_mac_cfg
ice_vf_rebuild_aggregator_node_cfg
ice_vf_rebuild_host_cfg
ice_set_vf_state_qs_dis
ice_vf_set_initialized

In order to achieve that, the order in which these
were defined was reorganized.

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_vf_lib.c   | 468 +++++++++---------
 .../ethernet/intel/ice/ice_vf_lib_private.h   |   2 -
 2 files changed, 234 insertions(+), 236 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index b26ce4425f455..20c4beaa05d85 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -322,6 +322,240 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf)
 	return 0;
 }
 
+/**
+ * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN
+ * @vf: VF to add MAC filters for
+ * @vsi: Pointer to VSI
+ *
+ * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver
+ * always re-adds either a VLAN 0 or port VLAN based filter after reset.
+ */
+static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf, struct ice_vsi *vsi)
+{
+	struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi);
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	int err;
+
+	if (ice_vf_is_port_vlan_ena(vf)) {
+		err = vlan_ops->set_port_vlan(vsi, &vf->port_vlan_info);
+		if (err) {
+			dev_err(dev, "failed to configure port VLAN via VSI parameters for VF %u, error %d\n",
+				vf->vf_id, err);
+			return err;
+		}
+
+		err = vlan_ops->add_vlan(vsi, &vf->port_vlan_info);
+	} else {
+		err = ice_vsi_add_vlan_zero(vsi);
+	}
+
+	if (err) {
+		dev_err(dev, "failed to add VLAN %u filter for VF %u during VF rebuild, error %d\n",
+			ice_vf_is_port_vlan_ena(vf) ?
+			ice_vf_get_port_vlan_id(vf) : 0, vf->vf_id, err);
+		return err;
+	}
+
+	err = vlan_ops->ena_rx_filtering(vsi);
+	if (err)
+		dev_warn(dev, "failed to enable Rx VLAN filtering for VF %d VSI %d during VF rebuild, error %d\n",
+			 vf->vf_id, vsi->idx, err);
+
+	return 0;
+}
+
+/**
+ * ice_vf_rebuild_host_tx_rate_cfg - re-apply the Tx rate limiting configuration
+ * @vf: VF to re-apply the configuration for
+ *
+ * Called after a VF VSI has been re-added/rebuild during reset. The PF driver
+ * needs to re-apply the host configured Tx rate limiting configuration.
+ */
+static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
+	int err;
+
+	if (WARN_ON(!vsi))
+		return -EINVAL;
+
+	if (vf->min_tx_rate) {
+		err = ice_set_min_bw_limit(vsi, (u64)vf->min_tx_rate * 1000);
+		if (err) {
+			dev_err(dev, "failed to set min Tx rate to %d Mbps for VF %u, error %d\n",
+				vf->min_tx_rate, vf->vf_id, err);
+			return err;
+		}
+	}
+
+	if (vf->max_tx_rate) {
+		err = ice_set_max_bw_limit(vsi, (u64)vf->max_tx_rate * 1000);
+		if (err) {
+			dev_err(dev, "failed to set max Tx rate to %d Mbps for VF %u, error %d\n",
+				vf->max_tx_rate, vf->vf_id, err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * ice_vf_set_host_trust_cfg - set trust setting based on pre-reset value
+ * @vf: VF to configure trust setting for
+ */
+static void ice_vf_set_host_trust_cfg(struct ice_vf *vf)
+{
+	if (vf->trusted)
+		set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
+	else
+		clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
+}
+
+/**
+ * ice_vf_rebuild_host_mac_cfg - add broadcast and the VF's perm_addr/LAA
+ * @vf: VF to add MAC filters for
+ *
+ * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver
+ * always re-adds a broadcast filter and the VF's perm_addr/LAA after reset.
+ */
+static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
+	u8 broadcast[ETH_ALEN];
+	int status;
+
+	if (WARN_ON(!vsi))
+		return -EINVAL;
+
+	if (ice_is_eswitch_mode_switchdev(vf->pf))
+		return 0;
+
+	eth_broadcast_addr(broadcast);
+	status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI);
+	if (status) {
+		dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %d\n",
+			vf->vf_id, status);
+		return status;
+	}
+
+	vf->num_mac++;
+
+	if (is_valid_ether_addr(vf->hw_lan_addr)) {
+		status = ice_fltr_add_mac(vsi, vf->hw_lan_addr,
+					  ICE_FWD_TO_VSI);
+		if (status) {
+			dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n",
+				&vf->hw_lan_addr[0], vf->vf_id,
+				status);
+			return status;
+		}
+		vf->num_mac++;
+
+		ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr);
+	}
+
+	return 0;
+}
+
+/**
+ * ice_vf_rebuild_aggregator_node_cfg - rebuild aggregator node config
+ * @vsi: Pointer to VSI
+ *
+ * This function moves VSI into corresponding scheduler aggregator node
+ * based on cached value of "aggregator node info" per VSI
+ */
+static void ice_vf_rebuild_aggregator_node_cfg(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	struct device *dev;
+	int status;
+
+	if (!vsi->agg_node)
+		return;
+
+	dev = ice_pf_to_dev(pf);
+	if (vsi->agg_node->num_vsis == ICE_MAX_VSIS_IN_AGG_NODE) {
+		dev_dbg(dev,
+			"agg_id %u already has reached max_num_vsis %u\n",
+			vsi->agg_node->agg_id, vsi->agg_node->num_vsis);
+		return;
+	}
+
+	status = ice_move_vsi_to_agg(pf->hw.port_info, vsi->agg_node->agg_id,
+				     vsi->idx, vsi->tc_cfg.ena_tc);
+	if (status)
+		dev_dbg(dev, "unable to move VSI idx %u into aggregator %u node",
+			vsi->idx, vsi->agg_node->agg_id);
+	else
+		vsi->agg_node->num_vsis++;
+}
+
+/**
+ * ice_vf_rebuild_host_cfg - host admin configuration is persistent across reset
+ * @vf: VF to rebuild host configuration on
+ */
+static void ice_vf_rebuild_host_cfg(struct ice_vf *vf)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
+
+	if (WARN_ON(!vsi))
+		return;
+
+	ice_vf_set_host_trust_cfg(vf);
+
+	if (ice_vf_rebuild_host_mac_cfg(vf))
+		dev_err(dev, "failed to rebuild default MAC configuration for VF %d\n",
+			vf->vf_id);
+
+	if (ice_vf_rebuild_host_vlan_cfg(vf, vsi))
+		dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n",
+			vf->vf_id);
+
+	if (ice_vf_rebuild_host_tx_rate_cfg(vf))
+		dev_err(dev, "failed to rebuild Tx rate limiting configuration for VF %u\n",
+			vf->vf_id);
+
+	if (ice_vsi_apply_spoofchk(vsi, vf->spoofchk))
+		dev_err(dev, "failed to rebuild spoofchk configuration for VF %d\n",
+			vf->vf_id);
+
+	/* rebuild aggregator node config for main VF VSI */
+	ice_vf_rebuild_aggregator_node_cfg(vsi);
+}
+
+/**
+ * ice_set_vf_state_qs_dis - Set VF queues state to disabled
+ * @vf: pointer to the VF structure
+ */
+static void ice_set_vf_state_qs_dis(struct ice_vf *vf)
+{
+	/* Clear Rx/Tx enabled queues flag */
+	bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF);
+	bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF);
+	clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states);
+}
+
+/**
+ * ice_vf_set_initialized - VF is ready for VIRTCHNL communication
+ * @vf: VF to set in initialized state
+ *
+ * After this function the VF will be ready to receive/handle the
+ * VIRTCHNL_OP_GET_VF_RESOURCES message
+ */
+static void ice_vf_set_initialized(struct ice_vf *vf)
+{
+	ice_set_vf_state_qs_dis(vf);
+	clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states);
+	clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states);
+	clear_bit(ICE_VF_STATE_DIS, vf->vf_states);
+	set_bit(ICE_VF_STATE_INIT, vf->vf_states);
+	memset(&vf->vlan_v2_caps, 0, sizeof(vf->vlan_v2_caps));
+}
+
 /**
  * ice_vf_post_vsi_rebuild - Reset tasks that occur after VSI rebuild
  * @vf: the VF being reset
@@ -725,18 +959,6 @@ out_unlock:
 	return err;
 }
 
-/**
- * ice_set_vf_state_qs_dis - Set VF queues state to disabled
- * @vf: pointer to the VF structure
- */
-static void ice_set_vf_state_qs_dis(struct ice_vf *vf)
-{
-	/* Clear Rx/Tx enabled queues flag */
-	bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF);
-	bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF);
-	clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states);
-}
-
 /**
  * ice_set_vf_state_dis - Set VF state to disabled
  * @vf: pointer to the VF structure
@@ -977,211 +1199,6 @@ bool ice_is_vf_link_up(struct ice_vf *vf)
 			ICE_AQ_LINK_UP;
 }
 
-/**
- * ice_vf_set_host_trust_cfg - set trust setting based on pre-reset value
- * @vf: VF to configure trust setting for
- */
-static void ice_vf_set_host_trust_cfg(struct ice_vf *vf)
-{
-	if (vf->trusted)
-		set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
-	else
-		clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
-}
-
-/**
- * ice_vf_rebuild_host_mac_cfg - add broadcast and the VF's perm_addr/LAA
- * @vf: VF to add MAC filters for
- *
- * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver
- * always re-adds a broadcast filter and the VF's perm_addr/LAA after reset.
- */
-static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf)
-{
-	struct device *dev = ice_pf_to_dev(vf->pf);
-	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
-	u8 broadcast[ETH_ALEN];
-	int status;
-
-	if (WARN_ON(!vsi))
-		return -EINVAL;
-
-	if (ice_is_eswitch_mode_switchdev(vf->pf))
-		return 0;
-
-	eth_broadcast_addr(broadcast);
-	status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI);
-	if (status) {
-		dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %d\n",
-			vf->vf_id, status);
-		return status;
-	}
-
-	vf->num_mac++;
-
-	if (is_valid_ether_addr(vf->hw_lan_addr)) {
-		status = ice_fltr_add_mac(vsi, vf->hw_lan_addr,
-					  ICE_FWD_TO_VSI);
-		if (status) {
-			dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n",
-				&vf->hw_lan_addr[0], vf->vf_id,
-				status);
-			return status;
-		}
-		vf->num_mac++;
-
-		ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr);
-	}
-
-	return 0;
-}
-
-/**
- * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN
- * @vf: VF to add MAC filters for
- * @vsi: Pointer to VSI
- *
- * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver
- * always re-adds either a VLAN 0 or port VLAN based filter after reset.
- */
-static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf, struct ice_vsi *vsi)
-{
-	struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi);
-	struct device *dev = ice_pf_to_dev(vf->pf);
-	int err;
-
-	if (ice_vf_is_port_vlan_ena(vf)) {
-		err = vlan_ops->set_port_vlan(vsi, &vf->port_vlan_info);
-		if (err) {
-			dev_err(dev, "failed to configure port VLAN via VSI parameters for VF %u, error %d\n",
-				vf->vf_id, err);
-			return err;
-		}
-
-		err = vlan_ops->add_vlan(vsi, &vf->port_vlan_info);
-	} else {
-		err = ice_vsi_add_vlan_zero(vsi);
-	}
-
-	if (err) {
-		dev_err(dev, "failed to add VLAN %u filter for VF %u during VF rebuild, error %d\n",
-			ice_vf_is_port_vlan_ena(vf) ?
-			ice_vf_get_port_vlan_id(vf) : 0, vf->vf_id, err);
-		return err;
-	}
-
-	err = vlan_ops->ena_rx_filtering(vsi);
-	if (err)
-		dev_warn(dev, "failed to enable Rx VLAN filtering for VF %d VSI %d during VF rebuild, error %d\n",
-			 vf->vf_id, vsi->idx, err);
-
-	return 0;
-}
-
-/**
- * ice_vf_rebuild_host_tx_rate_cfg - re-apply the Tx rate limiting configuration
- * @vf: VF to re-apply the configuration for
- *
- * Called after a VF VSI has been re-added/rebuild during reset. The PF driver
- * needs to re-apply the host configured Tx rate limiting configuration.
- */
-static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf)
-{
-	struct device *dev = ice_pf_to_dev(vf->pf);
-	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
-	int err;
-
-	if (WARN_ON(!vsi))
-		return -EINVAL;
-
-	if (vf->min_tx_rate) {
-		err = ice_set_min_bw_limit(vsi, (u64)vf->min_tx_rate * 1000);
-		if (err) {
-			dev_err(dev, "failed to set min Tx rate to %d Mbps for VF %u, error %d\n",
-				vf->min_tx_rate, vf->vf_id, err);
-			return err;
-		}
-	}
-
-	if (vf->max_tx_rate) {
-		err = ice_set_max_bw_limit(vsi, (u64)vf->max_tx_rate * 1000);
-		if (err) {
-			dev_err(dev, "failed to set max Tx rate to %d Mbps for VF %u, error %d\n",
-				vf->max_tx_rate, vf->vf_id, err);
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-/**
- * ice_vf_rebuild_aggregator_node_cfg - rebuild aggregator node config
- * @vsi: Pointer to VSI
- *
- * This function moves VSI into corresponding scheduler aggregator node
- * based on cached value of "aggregator node info" per VSI
- */
-static void ice_vf_rebuild_aggregator_node_cfg(struct ice_vsi *vsi)
-{
-	struct ice_pf *pf = vsi->back;
-	struct device *dev;
-	int status;
-
-	if (!vsi->agg_node)
-		return;
-
-	dev = ice_pf_to_dev(pf);
-	if (vsi->agg_node->num_vsis == ICE_MAX_VSIS_IN_AGG_NODE) {
-		dev_dbg(dev,
-			"agg_id %u already has reached max_num_vsis %u\n",
-			vsi->agg_node->agg_id, vsi->agg_node->num_vsis);
-		return;
-	}
-
-	status = ice_move_vsi_to_agg(pf->hw.port_info, vsi->agg_node->agg_id,
-				     vsi->idx, vsi->tc_cfg.ena_tc);
-	if (status)
-		dev_dbg(dev, "unable to move VSI idx %u into aggregator %u node",
-			vsi->idx, vsi->agg_node->agg_id);
-	else
-		vsi->agg_node->num_vsis++;
-}
-
-/**
- * ice_vf_rebuild_host_cfg - host admin configuration is persistent across reset
- * @vf: VF to rebuild host configuration on
- */
-void ice_vf_rebuild_host_cfg(struct ice_vf *vf)
-{
-	struct device *dev = ice_pf_to_dev(vf->pf);
-	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
-
-	if (WARN_ON(!vsi))
-		return;
-
-	ice_vf_set_host_trust_cfg(vf);
-
-	if (ice_vf_rebuild_host_mac_cfg(vf))
-		dev_err(dev, "failed to rebuild default MAC configuration for VF %d\n",
-			vf->vf_id);
-
-	if (ice_vf_rebuild_host_vlan_cfg(vf, vsi))
-		dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n",
-			vf->vf_id);
-
-	if (ice_vf_rebuild_host_tx_rate_cfg(vf))
-		dev_err(dev, "failed to rebuild Tx rate limiting configuration for VF %u\n",
-			vf->vf_id);
-
-	if (ice_vsi_apply_spoofchk(vsi, vf->spoofchk))
-		dev_err(dev, "failed to rebuild spoofchk configuration for VF %d\n",
-			vf->vf_id);
-
-	/* rebuild aggregator node config for main VF VSI */
-	ice_vf_rebuild_aggregator_node_cfg(vsi);
-}
-
 /**
  * ice_vf_ctrl_invalidate_vsi - invalidate ctrl_vsi_idx to remove VSI access
  * @vf: VF that control VSI is being invalidated on
@@ -1310,23 +1327,6 @@ void ice_vf_vsi_release(struct ice_vf *vf)
 	ice_vf_invalidate_vsi(vf);
 }
 
-/**
- * ice_vf_set_initialized - VF is ready for VIRTCHNL communication
- * @vf: VF to set in initialized state
- *
- * After this function the VF will be ready to receive/handle the
- * VIRTCHNL_OP_GET_VF_RESOURCES message
- */
-void ice_vf_set_initialized(struct ice_vf *vf)
-{
-	ice_set_vf_state_qs_dis(vf);
-	clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states);
-	clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states);
-	clear_bit(ICE_VF_STATE_DIS, vf->vf_states);
-	set_bit(ICE_VF_STATE_INIT, vf->vf_states);
-	memset(&vf->vlan_v2_caps, 0, sizeof(vf->vlan_v2_caps));
-}
-
 /**
  * ice_get_vf_ctrl_vsi - Get first VF control VSI pointer
  * @pf: the PF private structure
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
index 6f3293b793b5a..0c7e77c0a09fa 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
@@ -32,13 +32,11 @@ int ice_vsi_apply_spoofchk(struct ice_vsi *vsi, bool enable);
 bool ice_is_vf_trusted(struct ice_vf *vf);
 bool ice_vf_has_no_qs_ena(struct ice_vf *vf);
 bool ice_is_vf_link_up(struct ice_vf *vf);
-void ice_vf_rebuild_host_cfg(struct ice_vf *vf);
 void ice_vf_ctrl_invalidate_vsi(struct ice_vf *vf);
 void ice_vf_ctrl_vsi_release(struct ice_vf *vf);
 struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf);
 int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi);
 void ice_vf_invalidate_vsi(struct ice_vf *vf);
 void ice_vf_vsi_release(struct ice_vf *vf);
-void ice_vf_set_initialized(struct ice_vf *vf);
 
 #endif /* _ICE_VF_LIB_PRIVATE_H_ */
-- 
GitLab


From 54e852da07150b40de2d451618a557338ae98061 Mon Sep 17 00:00:00 2001
From: Tony Nguyen <anthony.l.nguyen@intel.com>
Date: Thu, 17 Aug 2023 09:59:01 -0700
Subject: [PATCH 1297/1806] ice: Utilize assign_bit() helper

The if/else check for bit setting can be replaced by using the
assign_bit() helper so do so.

Suggested-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_vf_lib.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 20c4beaa05d85..b95931272b16e 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -407,10 +407,7 @@ static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf)
  */
 static void ice_vf_set_host_trust_cfg(struct ice_vf *vf)
 {
-	if (vf->trusted)
-		set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
-	else
-		clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
+	assign_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps, vf->trusted);
 }
 
 /**
-- 
GitLab


From 9762f8fa832c33cd351cf3efd56ca74e2548dd06 Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Wed, 9 Aug 2023 15:39:11 +0200
Subject: [PATCH 1298/1806] ice: refactor ice_sched to make functions static

As ice_sched_set_node_bw_lmt_per_tc is not used
outside of ice_sched, it can be made static.

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_sched.c | 2 +-
 drivers/net/ethernet/intel/ice/ice_sched.h | 4 ----
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index f4677704b95e2..c0533d7b66b99 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -3971,7 +3971,7 @@ ice_sched_get_node_by_id_type(struct ice_port_info *pi, u32 id,
  * This function sets BW limit of VSI or Aggregator scheduling node
  * based on TC information from passed in argument BW.
  */
-int
+static int
 ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id,
 				 enum ice_agg_type agg_type, u8 tc,
 				 enum ice_rl_type rl_type, u32 bw)
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index 8bd26353d76a5..0055d9330c07c 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -141,10 +141,6 @@ ice_cfg_vsi_bw_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 int
 ice_cfg_vsi_bw_dflt_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 			       enum ice_rl_type rl_type);
-int
-ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id,
-				 enum ice_agg_type agg_type, u8 tc,
-				 enum ice_rl_type rl_type, u32 bw);
 int ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes);
 int
 ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids,
-- 
GitLab


From cae48047052f3baec0fbc0ebf498b19c72753294 Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Wed, 9 Aug 2023 15:39:12 +0200
Subject: [PATCH 1299/1806] ice: refactor ice_ptp_hw to make functions static

As following methods are not used outside ice_ptp_hw,
they can be made static:
ice_read_phy_reg_e822
ice_write_phy_reg_e822
ice_ptp_prep_port_adj_e822

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 6 +++---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h | 3 ---
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index a0da1bb55ba1d..68e2d5ca01f3a 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -293,7 +293,7 @@ static bool ice_is_40b_phy_reg_e822(u16 low_addr, u16 *high_addr)
  *
  * Read a PHY register for the given port over the device sideband queue.
  */
-int
+static int
 ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val)
 {
 	struct ice_sbq_msg_input msg = {0};
@@ -370,7 +370,7 @@ ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val)
  *
  * Write a PHY register for the given port over the device sideband queue.
  */
-int
+static int
 ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val)
 {
 	struct ice_sbq_msg_input msg = {0};
@@ -1079,7 +1079,7 @@ exit_err:
  *
  * Negative adjustments are supported using 2s complement arithmetic.
  */
-int
+static int
 ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time)
 {
 	u32 l_time, u_time;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 07cd023b0efd0..13547707b8e3f 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -141,11 +141,8 @@ int ice_ptp_init_phc(struct ice_hw *hw);
 int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready);
 
 /* E822 family functions */
-int ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val);
-int ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val);
 int ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val);
 int ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val);
-int ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time);
 void ice_ptp_reset_ts_memory_quad_e822(struct ice_hw *hw, u8 quad);
 
 /**
-- 
GitLab


From e528e5b237550b9c9f738a7e56174e5195c925d3 Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Wed, 9 Aug 2023 15:39:13 +0200
Subject: [PATCH 1300/1806] ice: refactor ice_vsi_is_vlan_pruning_ena

As this method became static, and is already called
with check for vsi being non-null, an unnecessary check along
with superfluous parentheses is removed.

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index d3fb2b7535e76..201570cd2e0b3 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1235,10 +1235,7 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
  */
 static bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi)
 {
-	if (!vsi)
-		return false;
-
-	return (vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA);
+	return vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
 }
 
 /**
-- 
GitLab


From 403e48539b160cd43f4ce67c641496b9911ff916 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 11 Jul 2023 16:47:34 -0700
Subject: [PATCH 1301/1806] ice: move E810T functions to before device agnostic
 ones

Commit 885fe6932a11 ("ice: Add support for SMA control multiplexer")
accidentally placed all of the E810T SMA control functions in the middle of
the device agnostic functions section of ice_ptp_hw.c

This works fine, but makes it harder for readers to follow. The
ice_ptp_hw.c file is laid out such that each hardware family has the
specific functions in one block, with the access functions placed at the
end of the file.

Move the E810T functions so that they are in a block just after the E810
functions. Also move the ice_get_phy_tx_tstamp_ready_e810 which got added
at the end of the E810T block.

This keeps the functions laid out in a logical order and avoids intermixing
the generic access functions with the device specific implementations.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Arpana Arland <arpanax.arland@intel.com> (A Contingent worker at Intel)
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 358 ++++++++++----------
 1 file changed, 179 insertions(+), 179 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 68e2d5ca01f3a..5a6ffa7383968 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -2869,6 +2869,185 @@ static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	return 0;
 }
 
+/**
+ * ice_get_phy_tx_tstamp_ready_e810 - Read Tx memory status register
+ * @hw: pointer to the HW struct
+ * @port: the PHY port to read
+ * @tstamp_ready: contents of the Tx memory status register
+ *
+ * E810 devices do not use a Tx memory status register. Instead simply
+ * indicate that all timestamps are currently ready.
+ */
+static int
+ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready)
+{
+	*tstamp_ready = 0xFFFFFFFFFFFFFFFF;
+	return 0;
+}
+
+/* E810T SMA functions
+ *
+ * The following functions operate specifically on E810T hardware and are used
+ * to access the extended GPIOs available.
+ */
+
+/**
+ * ice_get_pca9575_handle
+ * @hw: pointer to the hw struct
+ * @pca9575_handle: GPIO controller's handle
+ *
+ * Find and return the GPIO controller's handle in the netlist.
+ * When found - the value will be cached in the hw structure and following calls
+ * will return cached value
+ */
+static int
+ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
+{
+	struct ice_aqc_get_link_topo *cmd;
+	struct ice_aq_desc desc;
+	int status;
+	u8 idx;
+
+	/* If handle was read previously return cached value */
+	if (hw->io_expander_handle) {
+		*pca9575_handle = hw->io_expander_handle;
+		return 0;
+	}
+
+	/* If handle was not detected read it from the netlist */
+	cmd = &desc.params.get_link_topo;
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
+
+	/* Set node type to GPIO controller */
+	cmd->addr.topo_params.node_type_ctx =
+		(ICE_AQC_LINK_TOPO_NODE_TYPE_M &
+		 ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL);
+
+#define SW_PCA9575_SFP_TOPO_IDX		2
+#define SW_PCA9575_QSFP_TOPO_IDX	1
+
+	/* Check if the SW IO expander controlling SMA exists in the netlist. */
+	if (hw->device_id == ICE_DEV_ID_E810C_SFP)
+		idx = SW_PCA9575_SFP_TOPO_IDX;
+	else if (hw->device_id == ICE_DEV_ID_E810C_QSFP)
+		idx = SW_PCA9575_QSFP_TOPO_IDX;
+	else
+		return -EOPNOTSUPP;
+
+	cmd->addr.topo_params.index = idx;
+
+	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+	if (status)
+		return -EOPNOTSUPP;
+
+	/* Verify if we found the right IO expander type */
+	if (desc.params.get_link_topo.node_part_num !=
+		ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575)
+		return -EOPNOTSUPP;
+
+	/* If present save the handle and return it */
+	hw->io_expander_handle =
+		le16_to_cpu(desc.params.get_link_topo.addr.handle);
+	*pca9575_handle = hw->io_expander_handle;
+
+	return 0;
+}
+
+/**
+ * ice_read_sma_ctrl_e810t
+ * @hw: pointer to the hw struct
+ * @data: pointer to data to be read from the GPIO controller
+ *
+ * Read the SMA controller state. It is connected to pins 3-7 of Port 1 of the
+ * PCA9575 expander, so only bits 3-7 in data are valid.
+ */
+int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data)
+{
+	int status;
+	u16 handle;
+	u8 i;
+
+	status = ice_get_pca9575_handle(hw, &handle);
+	if (status)
+		return status;
+
+	*data = 0;
+
+	for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) {
+		bool pin;
+
+		status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET,
+					 &pin, NULL);
+		if (status)
+			break;
+		*data |= (u8)(!pin) << i;
+	}
+
+	return status;
+}
+
+/**
+ * ice_write_sma_ctrl_e810t
+ * @hw: pointer to the hw struct
+ * @data: data to be written to the GPIO controller
+ *
+ * Write the data to the SMA controller. It is connected to pins 3-7 of Port 1
+ * of the PCA9575 expander, so only bits 3-7 in data are valid.
+ */
+int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data)
+{
+	int status;
+	u16 handle;
+	u8 i;
+
+	status = ice_get_pca9575_handle(hw, &handle);
+	if (status)
+		return status;
+
+	for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) {
+		bool pin;
+
+		pin = !(data & (1 << i));
+		status = ice_aq_set_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET,
+					 pin, NULL);
+		if (status)
+			break;
+	}
+
+	return status;
+}
+
+/**
+ * ice_read_pca9575_reg_e810t
+ * @hw: pointer to the hw struct
+ * @offset: GPIO controller register offset
+ * @data: pointer to data to be read from the GPIO controller
+ *
+ * Read the register from the GPIO controller
+ */
+int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data)
+{
+	struct ice_aqc_link_topo_addr link_topo;
+	__le16 addr;
+	u16 handle;
+	int err;
+
+	memset(&link_topo, 0, sizeof(link_topo));
+
+	err = ice_get_pca9575_handle(hw, &handle);
+	if (err)
+		return err;
+
+	link_topo.handle = cpu_to_le16(handle);
+	link_topo.topo_params.node_type_ctx =
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M,
+			   ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED);
+
+	addr = cpu_to_le16((u16)offset);
+
+	return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL);
+}
+
 /* Device agnostic functions
  *
  * The following functions implement shared behavior common to both E822 and
@@ -3129,185 +3308,6 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx)
 		return ice_clear_phy_tstamp_e822(hw, block, idx);
 }
 
-/**
- * ice_get_phy_tx_tstamp_ready_e810 - Read Tx memory status register
- * @hw: pointer to the HW struct
- * @port: the PHY port to read
- * @tstamp_ready: contents of the Tx memory status register
- *
- * E810 devices do not use a Tx memory status register. Instead simply
- * indicate that all timestamps are currently ready.
- */
-static int
-ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready)
-{
-	*tstamp_ready = 0xFFFFFFFFFFFFFFFF;
-	return 0;
-}
-
-/* E810T SMA functions
- *
- * The following functions operate specifically on E810T hardware and are used
- * to access the extended GPIOs available.
- */
-
-/**
- * ice_get_pca9575_handle
- * @hw: pointer to the hw struct
- * @pca9575_handle: GPIO controller's handle
- *
- * Find and return the GPIO controller's handle in the netlist.
- * When found - the value will be cached in the hw structure and following calls
- * will return cached value
- */
-static int
-ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
-{
-	struct ice_aqc_get_link_topo *cmd;
-	struct ice_aq_desc desc;
-	int status;
-	u8 idx;
-
-	/* If handle was read previously return cached value */
-	if (hw->io_expander_handle) {
-		*pca9575_handle = hw->io_expander_handle;
-		return 0;
-	}
-
-	/* If handle was not detected read it from the netlist */
-	cmd = &desc.params.get_link_topo;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
-
-	/* Set node type to GPIO controller */
-	cmd->addr.topo_params.node_type_ctx =
-		(ICE_AQC_LINK_TOPO_NODE_TYPE_M &
-		 ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL);
-
-#define SW_PCA9575_SFP_TOPO_IDX		2
-#define SW_PCA9575_QSFP_TOPO_IDX	1
-
-	/* Check if the SW IO expander controlling SMA exists in the netlist. */
-	if (hw->device_id == ICE_DEV_ID_E810C_SFP)
-		idx = SW_PCA9575_SFP_TOPO_IDX;
-	else if (hw->device_id == ICE_DEV_ID_E810C_QSFP)
-		idx = SW_PCA9575_QSFP_TOPO_IDX;
-	else
-		return -EOPNOTSUPP;
-
-	cmd->addr.topo_params.index = idx;
-
-	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
-	if (status)
-		return -EOPNOTSUPP;
-
-	/* Verify if we found the right IO expander type */
-	if (desc.params.get_link_topo.node_part_num !=
-		ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575)
-		return -EOPNOTSUPP;
-
-	/* If present save the handle and return it */
-	hw->io_expander_handle =
-		le16_to_cpu(desc.params.get_link_topo.addr.handle);
-	*pca9575_handle = hw->io_expander_handle;
-
-	return 0;
-}
-
-/**
- * ice_read_sma_ctrl_e810t
- * @hw: pointer to the hw struct
- * @data: pointer to data to be read from the GPIO controller
- *
- * Read the SMA controller state. It is connected to pins 3-7 of Port 1 of the
- * PCA9575 expander, so only bits 3-7 in data are valid.
- */
-int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data)
-{
-	int status;
-	u16 handle;
-	u8 i;
-
-	status = ice_get_pca9575_handle(hw, &handle);
-	if (status)
-		return status;
-
-	*data = 0;
-
-	for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) {
-		bool pin;
-
-		status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET,
-					 &pin, NULL);
-		if (status)
-			break;
-		*data |= (u8)(!pin) << i;
-	}
-
-	return status;
-}
-
-/**
- * ice_write_sma_ctrl_e810t
- * @hw: pointer to the hw struct
- * @data: data to be written to the GPIO controller
- *
- * Write the data to the SMA controller. It is connected to pins 3-7 of Port 1
- * of the PCA9575 expander, so only bits 3-7 in data are valid.
- */
-int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data)
-{
-	int status;
-	u16 handle;
-	u8 i;
-
-	status = ice_get_pca9575_handle(hw, &handle);
-	if (status)
-		return status;
-
-	for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) {
-		bool pin;
-
-		pin = !(data & (1 << i));
-		status = ice_aq_set_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET,
-					 pin, NULL);
-		if (status)
-			break;
-	}
-
-	return status;
-}
-
-/**
- * ice_read_pca9575_reg_e810t
- * @hw: pointer to the hw struct
- * @offset: GPIO controller register offset
- * @data: pointer to data to be read from the GPIO controller
- *
- * Read the register from the GPIO controller
- */
-int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data)
-{
-	struct ice_aqc_link_topo_addr link_topo;
-	__le16 addr;
-	u16 handle;
-	int err;
-
-	memset(&link_topo, 0, sizeof(link_topo));
-
-	err = ice_get_pca9575_handle(hw, &handle);
-	if (err)
-		return err;
-
-	link_topo.handle = cpu_to_le16(handle);
-	link_topo.topo_params.node_type_ctx =
-		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M,
-			   ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED);
-
-	addr = cpu_to_le16((u16)offset);
-
-	return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL);
-}
-
 /**
  * ice_ptp_reset_ts_memory - Reset timestamp memory for all blocks
  * @hw: pointer to the HW struct
-- 
GitLab


From 467a17eea5c374cc4dd6a827e96dab5963df3793 Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@linux.intel.com>
Date: Mon, 31 Jul 2023 04:42:01 +0200
Subject: [PATCH 1302/1806] ice: Remove redundant VSI configuration in eswitch
 setup

Remove a call to disable VLAN stripping on switchdev control plane VSI, as
it is disabled by default.

Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_eswitch.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index 9a53a5e5d73eb..62b54100273f9 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -84,10 +84,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	struct ice_vsi_vlan_ops *vlan_ops;
 	bool rule_added = false;
 
-	vlan_ops = ice_get_compat_vsi_vlan_ops(ctrl_vsi);
-	if (vlan_ops->dis_stripping(ctrl_vsi))
-		return -ENODEV;
-
 	ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx);
 
 	netif_addr_lock_bh(uplink_netdev);
-- 
GitLab


From 1533b7743d35dc88808291b7f552697c8ee87f22 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Wed, 2 Aug 2023 17:07:39 +0800
Subject: [PATCH 1303/1806] ice: use list_for_each_entry() helper

Convert list_for_each() to list_for_each_entry() where applicable.
No functional changed.

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lag.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 36b7044717e81..a68974c1aa383 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -129,11 +129,9 @@ ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport)
 	struct ice_lag_netdev_list *entry;
 	struct net_device *tmp_netdev;
 	struct ice_netdev_priv *np;
-	struct list_head *tmp;
 	struct ice_hw *hw;
 
-	list_for_each(tmp, lag->netdev_head) {
-		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
+	list_for_each_entry(entry, lag->netdev_head, node) {
 		tmp_netdev = entry->netdev;
 		if (!tmp_netdev || !netif_is_ice(tmp_netdev))
 			continue;
@@ -1535,11 +1533,9 @@ static void ice_lag_disable_sriov_bond(struct ice_lag *lag)
 	struct ice_lag_netdev_list *entry;
 	struct ice_netdev_priv *np;
 	struct net_device *netdev;
-	struct list_head *tmp;
 	struct ice_pf *pf;
 
-	list_for_each(tmp, lag->netdev_head) {
-		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
+	list_for_each_entry(entry, lag->netdev_head, node) {
 		netdev = entry->netdev;
 		np = netdev_priv(netdev);
 		pf = np->vsi->back;
-- 
GitLab


From 52da2fb2693a7525fc3a0474978b4441ee272492 Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Mon, 31 Jul 2023 11:01:52 -0400
Subject: [PATCH 1304/1806] ice: drop two params from ice_aq_alloc_free_res()

Drop @num_entries and @cd params, latter of which was always NULL.

Number of entities to alloc is passed in internal buffer, the outer layer
(that @num_entries was assigned to) meaning is closer to "the number of
requests", which was =1 in all cases.
ice_free_hw_res() was always called with 1 as its @num arg.

Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 24 +++++++--------------
 drivers/net/ethernet/intel/ice/ice_common.h |  7 +++---
 drivers/net/ethernet/intel/ice/ice_lag.c    |  9 ++++----
 drivers/net/ethernet/intel/ice/ice_switch.c | 16 ++++++--------
 4 files changed, 22 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index a86255b529a0c..80deca45ab599 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -2000,37 +2000,31 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res)
 /**
  * ice_aq_alloc_free_res - command to allocate/free resources
  * @hw: pointer to the HW struct
- * @num_entries: number of resource entries in buffer
  * @buf: Indirect buffer to hold data parameters and response
  * @buf_size: size of buffer for indirect commands
  * @opc: pass in the command opcode
- * @cd: pointer to command details structure or NULL
  *
  * Helper function to allocate/free resources using the admin queue commands
  */
-int
-ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries,
-		      struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size,
-		      enum ice_adminq_opc opc, struct ice_sq_cd *cd)
+int ice_aq_alloc_free_res(struct ice_hw *hw,
+			  struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size,
+			  enum ice_adminq_opc opc)
 {
 	struct ice_aqc_alloc_free_res_cmd *cmd;
 	struct ice_aq_desc desc;
 
 	cmd = &desc.params.sw_res_ctrl;
 
-	if (!buf)
-		return -EINVAL;
-
-	if (buf_size < flex_array_size(buf, elem, num_entries))
+	if (!buf || buf_size < flex_array_size(buf, elem, 1))
 		return -EINVAL;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, opc);
 
 	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
 
-	cmd->num_entries = cpu_to_le16(num_entries);
+	cmd->num_entries = cpu_to_le16(1);
 
-	return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+	return ice_aq_send_cmd(hw, &desc, buf, buf_size, NULL);
 }
 
 /**
@@ -2060,8 +2054,7 @@ ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res)
 	if (btm)
 		buf->res_type |= cpu_to_le16(ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM);
 
-	status = ice_aq_alloc_free_res(hw, 1, buf, buf_len,
-				       ice_aqc_opc_alloc_res, NULL);
+	status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res);
 	if (status)
 		goto ice_alloc_res_exit;
 
@@ -2095,8 +2088,7 @@ int ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res)
 	buf->res_type = cpu_to_le16(type);
 	memcpy(buf->elem, res, sizeof(*buf->elem) * num);
 
-	status = ice_aq_alloc_free_res(hw, num, buf, buf_len,
-				       ice_aqc_opc_free_res, NULL);
+	status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res);
 	if (status)
 		ice_debug(hw, ICE_DBG_SW, "CQ CMD Buffer:\n");
 
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 71b82cdf4a6d8..226b81f97a92e 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -38,10 +38,9 @@ int
 ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res);
 int
 ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res);
-int
-ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries,
-		      struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size,
-		      enum ice_adminq_opc opc, struct ice_sq_cd *cd);
+int ice_aq_alloc_free_res(struct ice_hw *hw,
+			  struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size,
+			  enum ice_adminq_opc opc);
 bool ice_is_sbq_supported(struct ice_hw *hw);
 struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw);
 int
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index a68974c1aa383..4f39863b5537e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -983,9 +983,8 @@ ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
 	/* if unlinnking need to free the shared resource */
 	if (!link && local_lag->bond_swid) {
 		buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid);
-		status = ice_aq_alloc_free_res(&local_lag->pf->hw, 1, buf,
-					       buf_len, ice_aqc_opc_free_res,
-					       NULL);
+		status = ice_aq_alloc_free_res(&local_lag->pf->hw, buf,
+					       buf_len, ice_aqc_opc_free_res);
 		if (status)
 			dev_err(ice_pf_to_dev(local_lag->pf), "Error freeing SWID during LAG unlink\n");
 		local_lag->bond_swid = 0;
@@ -1002,8 +1001,8 @@ ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
 			cpu_to_le16(local_lag->pf->hw.port_info->sw_id);
 	}
 
-	status = ice_aq_alloc_free_res(&local_lag->pf->hw, 1, buf, buf_len,
-				       ice_aqc_opc_alloc_res, NULL);
+	status = ice_aq_alloc_free_res(&local_lag->pf->hw, buf, buf_len,
+				       ice_aqc_opc_alloc_res);
 	if (status)
 		dev_err(ice_pf_to_dev(local_lag->pf), "Error subscribing to SWID 0x%04X\n",
 			local_lag->bond_swid);
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 24c3f481848b7..2f77b684ff765 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -1847,7 +1847,7 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id,
 	if (opc == ice_aqc_opc_free_res)
 		sw_buf->elem[0].e.sw_resp = cpu_to_le16(*vsi_list_id);
 
-	status = ice_aq_alloc_free_res(hw, 1, sw_buf, buf_len, opc, NULL);
+	status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, opc);
 	if (status)
 		goto ice_aq_alloc_free_vsi_list_exit;
 
@@ -2101,8 +2101,8 @@ int ice_alloc_recipe(struct ice_hw *hw, u16 *rid)
 	sw_buf->res_type = cpu_to_le16((ICE_AQC_RES_TYPE_RECIPE <<
 					ICE_AQC_RES_TYPE_S) |
 					ICE_AQC_RES_TYPE_FLAG_SHARED);
-	status = ice_aq_alloc_free_res(hw, 1, sw_buf, buf_len,
-				       ice_aqc_opc_alloc_res, NULL);
+	status = ice_aq_alloc_free_res(hw, sw_buf, buf_len,
+				       ice_aqc_opc_alloc_res);
 	if (!status)
 		*rid = le16_to_cpu(sw_buf->elem[0].e.sw_resp);
 	kfree(sw_buf);
@@ -4448,8 +4448,7 @@ ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
 	buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) &
 				      ICE_AQC_RES_TYPE_M) | alloc_shared);
 
-	status = ice_aq_alloc_free_res(hw, 1, buf, buf_len,
-				       ice_aqc_opc_alloc_res, NULL);
+	status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res);
 	if (status)
 		goto exit;
 
@@ -4487,8 +4486,7 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
 				      ICE_AQC_RES_TYPE_M) | alloc_shared);
 	buf->elem[0].e.sw_resp = cpu_to_le16(counter_id);
 
-	status = ice_aq_alloc_free_res(hw, 1, buf, buf_len,
-				       ice_aqc_opc_free_res, NULL);
+	status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res);
 	if (status)
 		ice_debug(hw, ICE_DBG_SW, "counter resource could not be freed\n");
 
@@ -4530,8 +4528,8 @@ int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id)
 					    ~ICE_AQC_RES_TYPE_FLAG_SHARED);
 
 	buf->elem[0].e.sw_resp = cpu_to_le16(res_id);
-	status = ice_aq_alloc_free_res(hw, 1, buf, buf_len,
-				       ice_aqc_opc_share_res, NULL);
+	status = ice_aq_alloc_free_res(hw, buf, buf_len,
+				       ice_aqc_opc_share_res);
 	if (status)
 		ice_debug(hw, ICE_DBG_SW, "Could not set resource type %u id %u to %s\n",
 			  type, res_id, shared ? "SHARED" : "DEDICATED");
-- 
GitLab


From e1e8a142c43336e3d25bfa1cb3a4ae7d00875c48 Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Tue, 8 Aug 2023 17:54:15 -0400
Subject: [PATCH 1305/1806] ice: ice_aq_check_events: fix off-by-one check when
 filling buffer

Allow task's event buffer to be filled also in the case that it's size
is exactly the size of the message.

Fixes: d69ea414c9b4 ("ice: implement device flash update via devlink")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 0f04347eda39d..872bd5572294e 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1357,6 +1357,7 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout,
 static void ice_aq_check_events(struct ice_pf *pf, u16 opcode,
 				struct ice_rq_event_info *event)
 {
+	struct ice_rq_event_info *task_ev;
 	struct ice_aq_task *task;
 	bool found = false;
 
@@ -1365,15 +1366,15 @@ static void ice_aq_check_events(struct ice_pf *pf, u16 opcode,
 		if (task->state || task->opcode != opcode)
 			continue;
 
-		memcpy(&task->event->desc, &event->desc, sizeof(event->desc));
-		task->event->msg_len = event->msg_len;
+		task_ev = task->event;
+		memcpy(&task_ev->desc, &event->desc, sizeof(event->desc));
+		task_ev->msg_len = event->msg_len;
 
 		/* Only copy the data buffer if a destination was set */
-		if (task->event->msg_buf &&
-		    task->event->buf_len > event->buf_len) {
-			memcpy(task->event->msg_buf, event->msg_buf,
+		if (task_ev->msg_buf && task_ev->buf_len >= event->buf_len) {
+			memcpy(task_ev->msg_buf, event->msg_buf,
 			       event->buf_len);
-			task->event->buf_len = event->buf_len;
+			task_ev->buf_len = event->buf_len;
 		}
 
 		task->state = ICE_AQ_TASK_COMPLETE;
-- 
GitLab


From b214b98a7fc4dfcce7b67b2e08a22b7fe62c55d0 Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Tue, 8 Aug 2023 17:54:16 -0400
Subject: [PATCH 1306/1806] ice: embed &ice_rq_event_info event into struct
 ice_aq_task

Expose struct ice_aq_task to callers,
what takes burden of memory ownership out from AQ-wait family of functions,
and reduces need for heap-based allocations.

Embed struct ice_rq_event_info event into struct ice_aq_task
(instead of it being a ptr) to remove some more code from the callers.

Subsequent commit will improve more based on this one.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h          | 18 +++++++-
 .../net/ethernet/intel/ice/ice_fw_update.c    | 42 +++++++++----------
 drivers/net/ethernet/intel/ice/ice_main.c     | 29 ++-----------
 3 files changed, 40 insertions(+), 49 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 5ac0ad12f9f17..9a334287bd921 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -917,8 +917,22 @@ void ice_fdir_release_flows(struct ice_hw *hw);
 void ice_fdir_replay_flows(struct ice_hw *hw);
 void ice_fdir_replay_fltrs(struct ice_pf *pf);
 int ice_fdir_create_dflt_rules(struct ice_pf *pf);
-int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout,
-			  struct ice_rq_event_info *event);
+
+enum ice_aq_task_state {
+	ICE_AQ_TASK_WAITING,
+	ICE_AQ_TASK_COMPLETE,
+	ICE_AQ_TASK_CANCELED,
+};
+
+struct ice_aq_task {
+	struct hlist_node entry;
+	struct ice_rq_event_info event;
+	enum ice_aq_task_state state;
+	u16 opcode;
+};
+
+int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task,
+			  u16 opcode, unsigned long timeout);
 int ice_open(struct net_device *netdev);
 int ice_open_internal(struct net_device *netdev);
 int ice_stop(struct net_device *netdev);
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c
index 3dc5662d62a6a..819b70823e9c7 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.c
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c
@@ -293,13 +293,12 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 {
 	u16 completion_module, completion_retval;
 	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_rq_event_info event;
+	struct ice_aq_task task = {};
 	struct ice_hw *hw = &pf->hw;
+	struct ice_aq_desc *desc;
 	u32 completion_offset;
 	int err;
 
-	memset(&event, 0, sizeof(event));
-
 	dev_dbg(dev, "Writing block of %u bytes for module 0x%02x at offset %u\n",
 		block_size, module, offset);
 
@@ -319,7 +318,7 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	 * is conservative and is intended to prevent failure to update when
 	 * firmware is slow to respond.
 	 */
-	err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, 15 * HZ, &event);
+	err = ice_aq_wait_for_event(pf, &task, ice_aqc_opc_nvm_write, 15 * HZ);
 	if (err) {
 		dev_err(dev, "Timed out while trying to flash module 0x%02x with block of size %u at offset %u, err %d\n",
 			module, block_size, offset, err);
@@ -327,11 +326,12 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 		return -EIO;
 	}
 
-	completion_module = le16_to_cpu(event.desc.params.nvm.module_typeid);
-	completion_retval = le16_to_cpu(event.desc.retval);
+	desc = &task.event.desc;
+	completion_module = le16_to_cpu(desc->params.nvm.module_typeid);
+	completion_retval = le16_to_cpu(desc->retval);
 
-	completion_offset = le16_to_cpu(event.desc.params.nvm.offset_low);
-	completion_offset |= event.desc.params.nvm.offset_high << 16;
+	completion_offset = le16_to_cpu(desc->params.nvm.offset_low);
+	completion_offset |= desc->params.nvm.offset_high << 16;
 
 	if (completion_module != module) {
 		dev_err(dev, "Unexpected module_typeid in write completion: got 0x%x, expected 0x%x\n",
@@ -363,8 +363,8 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	 */
 	if (reset_level && last_cmd && module == ICE_SR_1ST_NVM_BANK_PTR) {
 		if (hw->dev_caps.common_cap.pcie_reset_avoidance) {
-			*reset_level = (event.desc.params.nvm.cmd_flags &
-					ICE_AQC_NVM_RESET_LVL_M);
+			*reset_level = desc->params.nvm.cmd_flags &
+				       ICE_AQC_NVM_RESET_LVL_M;
 			dev_dbg(dev, "Firmware reported required reset level as %u\n",
 				*reset_level);
 		} else {
@@ -479,15 +479,14 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 {
 	u16 completion_module, completion_retval;
 	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_rq_event_info event;
+	struct ice_aq_task task = {};
 	struct ice_hw *hw = &pf->hw;
+	struct ice_aq_desc *desc;
 	struct devlink *devlink;
 	int err;
 
 	dev_dbg(dev, "Beginning erase of flash component '%s', module 0x%02x\n", component, module);
 
-	memset(&event, 0, sizeof(event));
-
 	devlink = priv_to_devlink(pf);
 
 	devlink_flash_update_timeout_notify(devlink, "Erasing", component, ICE_FW_ERASE_TIMEOUT);
@@ -502,7 +501,7 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 		goto out_notify_devlink;
 	}
 
-	err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_erase, ICE_FW_ERASE_TIMEOUT * HZ, &event);
+	err = ice_aq_wait_for_event(pf, &task, ice_aqc_opc_nvm_erase, ICE_FW_ERASE_TIMEOUT * HZ);
 	if (err) {
 		dev_err(dev, "Timed out waiting for firmware to respond with erase completion for %s (module 0x%02x), err %d\n",
 			component, module, err);
@@ -510,8 +509,9 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 		goto out_notify_devlink;
 	}
 
-	completion_module = le16_to_cpu(event.desc.params.nvm.module_typeid);
-	completion_retval = le16_to_cpu(event.desc.retval);
+	desc = &task.event.desc;
+	completion_module = le16_to_cpu(desc->params.nvm.module_typeid);
+	completion_retval = le16_to_cpu(desc->retval);
 
 	if (completion_module != module) {
 		dev_err(dev, "Unexpected module_typeid in erase completion for %s: got 0x%x, expected 0x%x\n",
@@ -560,14 +560,12 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags,
 		       u8 *emp_reset_available, struct netlink_ext_ack *extack)
 {
 	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_rq_event_info event;
+	struct ice_aq_task task = {};
 	struct ice_hw *hw = &pf->hw;
 	u16 completion_retval;
 	u8 response_flags;
 	int err;
 
-	memset(&event, 0, sizeof(event));
-
 	err = ice_nvm_write_activate(hw, activate_flags, &response_flags);
 	if (err) {
 		dev_err(dev, "Failed to switch active flash banks, err %d aq_err %s\n",
@@ -592,8 +590,8 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags,
 		}
 	}
 
-	err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, 30 * HZ,
-				    &event);
+	err = ice_aq_wait_for_event(pf, &task, ice_aqc_opc_nvm_write_activate,
+				    30 * HZ);
 	if (err) {
 		dev_err(dev, "Timed out waiting for firmware to switch active flash banks, err %d\n",
 			err);
@@ -601,7 +599,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags,
 		return err;
 	}
 
-	completion_retval = le16_to_cpu(event.desc.retval);
+	completion_retval = le16_to_cpu(task.event.desc.retval);
 	if (completion_retval) {
 		dev_err(dev, "Firmware failed to switch active flash banks aq_err %s\n",
 			ice_aq_str((enum ice_aq_err)completion_retval));
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 872bd5572294e..b08be6700b2a8 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1250,26 +1250,12 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
 	return status;
 }
 
-enum ice_aq_task_state {
-	ICE_AQ_TASK_WAITING = 0,
-	ICE_AQ_TASK_COMPLETE,
-	ICE_AQ_TASK_CANCELED,
-};
-
-struct ice_aq_task {
-	struct hlist_node entry;
-
-	u16 opcode;
-	struct ice_rq_event_info *event;
-	enum ice_aq_task_state state;
-};
-
 /**
  * ice_aq_wait_for_event - Wait for an AdminQ event from firmware
  * @pf: pointer to the PF private structure
+ * @task: ptr to task structure
  * @opcode: the opcode to wait for
  * @timeout: how long to wait, in jiffies
- * @event: storage for the event info
  *
  * Waits for a specific AdminQ completion event on the ARQ for a given PF. The
  * current thread will be put to sleep until the specified event occurs or
@@ -1281,22 +1267,16 @@ struct ice_aq_task {
  *
  * Returns: zero on success, or a negative error code on failure.
  */
-int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout,
-			  struct ice_rq_event_info *event)
+int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task,
+			  u16 opcode, unsigned long timeout)
 {
 	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_aq_task *task;
 	unsigned long start;
 	long ret;
 	int err;
 
-	task = kzalloc(sizeof(*task), GFP_KERNEL);
-	if (!task)
-		return -ENOMEM;
-
 	INIT_HLIST_NODE(&task->entry);
 	task->opcode = opcode;
-	task->event = event;
 	task->state = ICE_AQ_TASK_WAITING;
 
 	spin_lock_bh(&pf->aq_wait_lock);
@@ -1331,7 +1311,6 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout,
 	spin_lock_bh(&pf->aq_wait_lock);
 	hlist_del(&task->entry);
 	spin_unlock_bh(&pf->aq_wait_lock);
-	kfree(task);
 
 	return err;
 }
@@ -1366,7 +1345,7 @@ static void ice_aq_check_events(struct ice_pf *pf, u16 opcode,
 		if (task->state || task->opcode != opcode)
 			continue;
 
-		task_ev = task->event;
+		task_ev = &task->event;
 		memcpy(&task_ev->desc, &event->desc, sizeof(event->desc));
 		task_ev->msg_len = event->msg_len;
 
-- 
GitLab


From fb9840c4ec13629f36c5e0e88a5df78ca2acc3e0 Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Tue, 8 Aug 2023 17:54:17 -0400
Subject: [PATCH 1307/1806] ice: split ice_aq_wait_for_event() func into two

Mitigate race between registering on wait list and receiving
AQ Response from FW.

ice_aq_prep_for_event() should be called before sending AQ command,
ice_aq_wait_for_event() should be called after sending AQ command,
to wait for AQ Response.

Please note, that this was found by reading the code,
an actual race has not yet materialized.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h          |  5 +-
 .../net/ethernet/intel/ice/ice_fw_update.c    | 13 ++--
 drivers/net/ethernet/intel/ice/ice_main.c     | 67 ++++++++++++-------
 3 files changed, 57 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 9a334287bd921..5022b036ca4f9 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -919,6 +919,7 @@ void ice_fdir_replay_fltrs(struct ice_pf *pf);
 int ice_fdir_create_dflt_rules(struct ice_pf *pf);
 
 enum ice_aq_task_state {
+	ICE_AQ_TASK_NOT_PREPARED,
 	ICE_AQ_TASK_WAITING,
 	ICE_AQ_TASK_COMPLETE,
 	ICE_AQ_TASK_CANCELED,
@@ -931,8 +932,10 @@ struct ice_aq_task {
 	u16 opcode;
 };
 
+void ice_aq_prep_for_event(struct ice_pf *pf, struct ice_aq_task *task,
+			   u16 opcode);
 int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task,
-			  u16 opcode, unsigned long timeout);
+			  unsigned long timeout);
 int ice_open(struct net_device *netdev);
 int ice_open_internal(struct net_device *netdev);
 int ice_stop(struct net_device *netdev);
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c
index 819b70823e9c7..319a2d6fe26c7 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.c
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c
@@ -302,6 +302,8 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	dev_dbg(dev, "Writing block of %u bytes for module 0x%02x at offset %u\n",
 		block_size, module, offset);
 
+	ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_write);
+
 	err = ice_aq_update_nvm(hw, module, offset, block_size, block,
 				last_cmd, 0, NULL);
 	if (err) {
@@ -318,7 +320,7 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	 * is conservative and is intended to prevent failure to update when
 	 * firmware is slow to respond.
 	 */
-	err = ice_aq_wait_for_event(pf, &task, ice_aqc_opc_nvm_write, 15 * HZ);
+	err = ice_aq_wait_for_event(pf, &task, 15 * HZ);
 	if (err) {
 		dev_err(dev, "Timed out while trying to flash module 0x%02x with block of size %u at offset %u, err %d\n",
 			module, block_size, offset, err);
@@ -491,6 +493,8 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 
 	devlink_flash_update_timeout_notify(devlink, "Erasing", component, ICE_FW_ERASE_TIMEOUT);
 
+	ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_erase);
+
 	err = ice_aq_erase_nvm(hw, module, NULL);
 	if (err) {
 		dev_err(dev, "Failed to erase %s (module 0x%02x), err %d aq_err %s\n",
@@ -501,7 +505,7 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 		goto out_notify_devlink;
 	}
 
-	err = ice_aq_wait_for_event(pf, &task, ice_aqc_opc_nvm_erase, ICE_FW_ERASE_TIMEOUT * HZ);
+	err = ice_aq_wait_for_event(pf, &task, ICE_FW_ERASE_TIMEOUT * HZ);
 	if (err) {
 		dev_err(dev, "Timed out waiting for firmware to respond with erase completion for %s (module 0x%02x), err %d\n",
 			component, module, err);
@@ -566,6 +570,8 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags,
 	u8 response_flags;
 	int err;
 
+	ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_write_activate);
+
 	err = ice_nvm_write_activate(hw, activate_flags, &response_flags);
 	if (err) {
 		dev_err(dev, "Failed to switch active flash banks, err %d aq_err %s\n",
@@ -590,8 +596,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags,
 		}
 	}
 
-	err = ice_aq_wait_for_event(pf, &task, ice_aqc_opc_nvm_write_activate,
-				    30 * HZ);
+	err = ice_aq_wait_for_event(pf, &task, 30 * HZ);
 	if (err) {
 		dev_err(dev, "Timed out waiting for firmware to switch active flash banks, err %d\n",
 			err);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index b08be6700b2a8..81c1018b57d1d 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1251,30 +1251,24 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
 }
 
 /**
- * ice_aq_wait_for_event - Wait for an AdminQ event from firmware
+ * ice_aq_prep_for_event - Prepare to wait for an AdminQ event from firmware
  * @pf: pointer to the PF private structure
- * @task: ptr to task structure
+ * @task: intermediate helper storage and identifier for waiting
  * @opcode: the opcode to wait for
- * @timeout: how long to wait, in jiffies
  *
- * Waits for a specific AdminQ completion event on the ARQ for a given PF. The
- * current thread will be put to sleep until the specified event occurs or
- * until the given timeout is reached.
+ * Prepares to wait for a specific AdminQ completion event on the ARQ for
+ * a given PF. Actual wait would be done by a call to ice_aq_wait_for_event().
  *
- * To obtain only the descriptor contents, pass an event without an allocated
- * msg_buf. If the complete data buffer is desired, allocate the
- * event->msg_buf with enough space ahead of time.
+ * Calls are separated to allow caller registering for event before sending
+ * the command, which mitigates a race between registering and FW responding.
  *
- * Returns: zero on success, or a negative error code on failure.
+ * To obtain only the descriptor contents, pass an task->event with null
+ * msg_buf. If the complete data buffer is desired, allocate the
+ * task->event.msg_buf with enough space ahead of time.
  */
-int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task,
-			  u16 opcode, unsigned long timeout)
+void ice_aq_prep_for_event(struct ice_pf *pf, struct ice_aq_task *task,
+			   u16 opcode)
 {
-	struct device *dev = ice_pf_to_dev(pf);
-	unsigned long start;
-	long ret;
-	int err;
-
 	INIT_HLIST_NODE(&task->entry);
 	task->opcode = opcode;
 	task->state = ICE_AQ_TASK_WAITING;
@@ -1282,12 +1276,37 @@ int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task,
 	spin_lock_bh(&pf->aq_wait_lock);
 	hlist_add_head(&task->entry, &pf->aq_wait_list);
 	spin_unlock_bh(&pf->aq_wait_lock);
+}
 
-	start = jiffies;
+/**
+ * ice_aq_wait_for_event - Wait for an AdminQ event from firmware
+ * @pf: pointer to the PF private structure
+ * @task: ptr prepared by ice_aq_prep_for_event()
+ * @timeout: how long to wait, in jiffies
+ *
+ * Waits for a specific AdminQ completion event on the ARQ for a given PF. The
+ * current thread will be put to sleep until the specified event occurs or
+ * until the given timeout is reached.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task,
+			  unsigned long timeout)
+{
+	enum ice_aq_task_state *state = &task->state;
+	struct device *dev = ice_pf_to_dev(pf);
+	unsigned long start = jiffies;
+	long ret;
+	int err;
 
-	ret = wait_event_interruptible_timeout(pf->aq_wait_queue, task->state,
+	ret = wait_event_interruptible_timeout(pf->aq_wait_queue,
+					       *state != ICE_AQ_TASK_WAITING,
 					       timeout);
-	switch (task->state) {
+	switch (*state) {
+	case ICE_AQ_TASK_NOT_PREPARED:
+		WARN(1, "call to %s without ice_aq_prep_for_event()", __func__);
+		err = -EINVAL;
+		break;
 	case ICE_AQ_TASK_WAITING:
 		err = ret < 0 ? ret : -ETIMEDOUT;
 		break;
@@ -1298,7 +1317,7 @@ int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task,
 		err = ret < 0 ? ret : 0;
 		break;
 	default:
-		WARN(1, "Unexpected AdminQ wait task state %u", task->state);
+		WARN(1, "Unexpected AdminQ wait task state %u", *state);
 		err = -EINVAL;
 		break;
 	}
@@ -1306,7 +1325,7 @@ int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task,
 	dev_dbg(dev, "Waited %u msecs (max %u msecs) for firmware response to op 0x%04x\n",
 		jiffies_to_msecs(jiffies - start),
 		jiffies_to_msecs(timeout),
-		opcode);
+		task->opcode);
 
 	spin_lock_bh(&pf->aq_wait_lock);
 	hlist_del(&task->entry);
@@ -1342,7 +1361,9 @@ static void ice_aq_check_events(struct ice_pf *pf, u16 opcode,
 
 	spin_lock_bh(&pf->aq_wait_lock);
 	hlist_for_each_entry(task, &pf->aq_wait_list, entry) {
-		if (task->state || task->opcode != opcode)
+		if (task->state != ICE_AQ_TASK_WAITING)
+			continue;
+		if (task->opcode != opcode)
 			continue;
 
 		task_ev = &task->event;
-- 
GitLab


From b2f8323364abf1b6fcd828851ea8be2f757c052a Mon Sep 17 00:00:00 2001
From: Ziyang Xuan <william.xuanziyang@huawei.com>
Date: Mon, 14 Aug 2023 16:30:00 +0800
Subject: [PATCH 1308/1806] tun: add __exit annotations to module exit func
 tun_cleanup()

Add missing __exit annotations to module exit func tun_cleanup().

Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230814083000.3893589-1-william.xuanziyang@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tun.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d4bd76297a2aa..89ab9efe522c3 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -3743,7 +3743,7 @@ err_linkops:
 	return ret;
 }
 
-static void tun_cleanup(void)
+static void __exit tun_cleanup(void)
 {
 	misc_deregister(&tun_miscdev);
 	rtnl_link_unregister(&tun_link_ops);
-- 
GitLab


From a5e5b2cd47bc7ac853b3ae9d4af97d08caaf585d Mon Sep 17 00:00:00 2001
From: Jialin Zhang <zhangjialin11@huawei.com>
Date: Tue, 15 Aug 2023 10:42:48 +0800
Subject: [PATCH 1309/1806] net: ena: Use pci_dev_id() to simplify the code

PCI core API pci_dev_id() can be used to get the BDF number for a pci
device. We don't need to compose it manually. Use pci_dev_id() to
simplify the code a little bit.

Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Shay Agroskin <shayagr@amazon.com>
Link: https://lore.kernel.org/r/20230815024248.3519068-1-zhangjialin11@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index d19593fae2265..ad32ca81f7ef4 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3267,7 +3267,7 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pd
 
 	host_info = ena_dev->host_attr.host_info;
 
-	host_info->bdf = (pdev->bus->number << 8) | pdev->devfn;
+	host_info->bdf = pci_dev_id(pdev);
 	host_info->os_type = ENA_ADMIN_OS_LINUX;
 	host_info->kernel_ver = LINUX_VERSION_CODE;
 	strscpy(host_info->kernel_ver_str, utsname()->version,
-- 
GitLab


From 4072d97ddc447ce9dd8f7a39cdf6f92d2031bb01 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fran=C3=A7ois=20Michel?= <francois.michel@uclouvain.be>
Date: Tue, 15 Aug 2023 11:23:38 +0200
Subject: [PATCH 1310/1806] netem: add prng attribute to netem_sched_data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add prng attribute to struct netem_sched_data and
allows setting the seed of the PRNG through netlink
using the new TCA_NETEM_PRNG_SEED attribute.
The PRNG attribute is not actually used yet.

Signed-off-by: François Michel <francois.michel@uclouvain.be>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Link: https://lore.kernel.org/r/20230815092348.1449179-2-francois.michel@uclouvain.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/pkt_sched.h |  1 +
 net/sched/sch_netem.c          | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 00f6ff0aff1ff..3f85ae5780563 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -603,6 +603,7 @@ enum {
 	TCA_NETEM_JITTER64,
 	TCA_NETEM_SLOT,
 	TCA_NETEM_SLOT_DIST,
+	TCA_NETEM_PRNG_SEED,
 	__TCA_NETEM_MAX,
 };
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 38d9aa0cd30e7..621c6acfd6448 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -105,6 +105,11 @@ struct netem_sched_data {
 		u32 rho;
 	} delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor;
 
+	struct prng  {
+		u64 seed;
+		struct rnd_state prng_state;
+	} prng;
+
 	struct disttable *delay_dist;
 
 	enum  {
@@ -922,6 +927,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
 	[TCA_NETEM_LATENCY64]	= { .type = NLA_S64 },
 	[TCA_NETEM_JITTER64]	= { .type = NLA_S64 },
 	[TCA_NETEM_SLOT]	= { .len = sizeof(struct tc_netem_slot) },
+	[TCA_NETEM_PRNG_SEED]	= { .type = NLA_U64 },
 };
 
 static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
@@ -1040,6 +1046,12 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 	/* capping jitter to the range acceptable by tabledist() */
 	q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
 
+	if (tb[TCA_NETEM_PRNG_SEED])
+		q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]);
+	else
+		q->prng.seed = get_random_u64();
+	prandom_seed_state(&q->prng.prng_state, q->prng.seed);
+
 unlock:
 	sch_tree_unlock(sch);
 
@@ -1203,6 +1215,10 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 			goto nla_put_failure;
 	}
 
+	if (nla_put_u64_64bit(skb, TCA_NETEM_PRNG_SEED, q->prng.seed,
+			      TCA_NETEM_PAD))
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, nla);
 
 nla_put_failure:
-- 
GitLab


From 9c87b2aeccf174bce220e527d48391439981273b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fran=C3=A7ois=20Michel?= <francois.michel@uclouvain.be>
Date: Tue, 15 Aug 2023 11:23:39 +0200
Subject: [PATCH 1311/1806] netem: use a seeded PRNG for generating random
 losses
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use prandom_u32_state() instead of get_random_u32() to generate
the random loss events of netem. The state of the prng is part
of the prng attribute of struct netem_sched_data.

Signed-off-by: François Michel <francois.michel@uclouvain.be>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Link: https://lore.kernel.org/r/20230815092348.1449179-3-francois.michel@uclouvain.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_netem.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 621c6acfd6448..8b54b1005a109 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -206,7 +206,7 @@ static u32 get_crandom(struct crndstate *state)
 static bool loss_4state(struct netem_sched_data *q)
 {
 	struct clgstate *clg = &q->clg;
-	u32 rnd = get_random_u32();
+	u32 rnd = prandom_u32_state(&q->prng.prng_state);
 
 	/*
 	 * Makes a comparison between rnd and the transition
@@ -271,18 +271,19 @@ static bool loss_4state(struct netem_sched_data *q)
 static bool loss_gilb_ell(struct netem_sched_data *q)
 {
 	struct clgstate *clg = &q->clg;
+	struct rnd_state *s = &q->prng.prng_state;
 
 	switch (clg->state) {
 	case GOOD_STATE:
-		if (get_random_u32() < clg->a1)
+		if (prandom_u32_state(s) < clg->a1)
 			clg->state = BAD_STATE;
-		if (get_random_u32() < clg->a4)
+		if (prandom_u32_state(s) < clg->a4)
 			return true;
 		break;
 	case BAD_STATE:
-		if (get_random_u32() < clg->a2)
+		if (prandom_u32_state(s) < clg->a2)
 			clg->state = GOOD_STATE;
-		if (get_random_u32() > clg->a3)
+		if (prandom_u32_state(s) > clg->a3)
 			return true;
 	}
 
-- 
GitLab


From 3cad70bc74ef8471e30a05a90798904ce8f8feb5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fran=C3=A7ois=20Michel?= <francois.michel@uclouvain.be>
Date: Tue, 15 Aug 2023 11:23:40 +0200
Subject: [PATCH 1312/1806] netem: use seeded PRNG for correlated loss events
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use prandom_u32_state() instead of get_random_u32() to generate
the correlated loss events of netem.

Signed-off-by: François Michel <francois.michel@uclouvain.be>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Link: https://lore.kernel.org/r/20230815092348.1449179-4-francois.michel@uclouvain.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_netem.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 8b54b1005a109..4ad39a4a3cf5b 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -184,15 +184,16 @@ static void init_crandom(struct crndstate *state, unsigned long rho)
  * Next number depends on last value.
  * rho is scaled to avoid floating point.
  */
-static u32 get_crandom(struct crndstate *state)
+static u32 get_crandom(struct crndstate *state, struct prng *p)
 {
 	u64 value, rho;
 	unsigned long answer;
+	struct rnd_state *s = &p->prng_state;
 
 	if (!state || state->rho == 0)	/* no correlation */
-		return get_random_u32();
+		return prandom_u32_state(s);
 
-	value = get_random_u32();
+	value = prandom_u32_state(s);
 	rho = (u64)state->rho + 1;
 	answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32;
 	state->last = answer;
@@ -295,7 +296,7 @@ static bool loss_event(struct netem_sched_data *q)
 	switch (q->loss_model) {
 	case CLG_RANDOM:
 		/* Random packet drop 0 => none, ~0 => all */
-		return q->loss && q->loss >= get_crandom(&q->loss_cor);
+		return q->loss && q->loss >= get_crandom(&q->loss_cor, &q->prng);
 
 	case CLG_4_STATES:
 		/* 4state loss model algorithm (used also for GI model)
@@ -324,6 +325,7 @@ static bool loss_event(struct netem_sched_data *q)
  */
 static s64 tabledist(s64 mu, s32 sigma,
 		     struct crndstate *state,
+		     struct prng *prng,
 		     const struct disttable *dist)
 {
 	s64 x;
@@ -333,7 +335,7 @@ static s64 tabledist(s64 mu, s32 sigma,
 	if (sigma == 0)
 		return mu;
 
-	rnd = get_crandom(state);
+	rnd = get_crandom(state, prng);
 
 	/* default uniform distribution */
 	if (dist == NULL)
@@ -455,7 +457,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	skb->prev = NULL;
 
 	/* Random duplication */
-	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
+	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor, &q->prng))
 		++count;
 
 	/* Drop packet? */
@@ -498,7 +500,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	 * If packet is going to be hardware checksummed, then
 	 * do it now in software before we mangle it.
 	 */
-	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
+	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor, &q->prng)) {
 		if (skb_is_gso(skb)) {
 			skb = netem_segment(skb, sch, to_free);
 			if (!skb)
@@ -536,12 +538,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	cb = netem_skb_cb(skb);
 	if (q->gap == 0 ||		/* not doing reordering */
 	    q->counter < q->gap - 1 ||	/* inside last reordering gap */
-	    q->reorder < get_crandom(&q->reorder_cor)) {
+	    q->reorder < get_crandom(&q->reorder_cor, &q->prng)) {
 		u64 now;
 		s64 delay;
 
 		delay = tabledist(q->latency, q->jitter,
-				  &q->delay_cor, q->delay_dist);
+				  &q->delay_cor, &q->prng, q->delay_dist);
 
 		now = ktime_get_ns();
 
@@ -645,7 +647,7 @@ static void get_slot_next(struct netem_sched_data *q, u64 now)
 	else
 		next_delay = tabledist(q->slot_config.dist_delay,
 				       (s32)(q->slot_config.dist_jitter),
-				       NULL, q->slot_dist);
+				       NULL, &q->prng, q->slot_dist);
 
 	q->slot.slot_next = now + next_delay;
 	q->slot.packets_left = q->slot_config.max_packets;
-- 
GitLab


From f3add6dec36d9d747929918ba1d7ce8866e1c054 Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Tue, 15 Aug 2023 20:35:59 +0000
Subject: [PATCH 1313/1806] net: mdio: fix -Wvoid-pointer-to-enum-cast warning

When building with clang 18 I see the following warning:
|       drivers/net/mdio/mdio-xgene.c:338:13: warning: cast to smaller integer
|               type 'enum xgene_mdio_id' from 'const void *' [-Wvoid-pointer-to-enum-cast]
|         338 |                 mdio_id = (enum xgene_mdio_id)of_id->data;

This is due to the fact that `of_id->data` is a void* while `enum
xgene_mdio_id` has the size of an int. This leads to truncation and
possible data loss.

Link: https://github.com/ClangBuiltLinux/linux/issues/1910
Reported-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Justin Stitt <justinstitt@google.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/20230815-void-drivers-net-mdio-mdio-xgene-v1-1-5304342e0659@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mdio/mdio-xgene.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/mdio/mdio-xgene.c b/drivers/net/mdio/mdio-xgene.c
index 683e8f8319abe..1af7a4d9f86c4 100644
--- a/drivers/net/mdio/mdio-xgene.c
+++ b/drivers/net/mdio/mdio-xgene.c
@@ -335,7 +335,7 @@ static int xgene_mdio_probe(struct platform_device *pdev)
 
 	of_id = of_match_device(xgene_mdio_of_match, &pdev->dev);
 	if (of_id) {
-		mdio_id = (enum xgene_mdio_id)of_id->data;
+		mdio_id = (uintptr_t)of_id->data;
 	} else {
 #ifdef CONFIG_ACPI
 		const struct acpi_device_id *acpi_id;
-- 
GitLab


From b0a9e2c9a99f64e3c59e8a32a11b90c667201203 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 11 Aug 2023 02:31:57 -0700
Subject: [PATCH 1314/1806] netconsole: Create a allocation helper

De-duplicate the initialization and allocation code for struct
netconsole_target.

The same allocation and initialization code is duplicated in two
different places in the netconsole subsystem, when the netconsole target
is initialized by command line parameters (alloc_param_target()), and
dynamically by sysfs (make_netconsole_target()).

Create a helper function, and call it from the two different functions.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230811093158.1678322-2-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 43 +++++++++++++++++++++-------------------
 1 file changed, 23 insertions(+), 20 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 87f18aedd3bd7..670b6f0a054c6 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -167,19 +167,16 @@ static void netconsole_target_put(struct netconsole_target *nt)
 
 #endif	/* CONFIG_NETCONSOLE_DYNAMIC */
 
-/* Allocate new target (from boot/module param) and setup netpoll for it */
-static struct netconsole_target *alloc_param_target(char *target_config)
+/* Allocate and initialize with defaults.
+ * Note that these targets get their config_item fields zeroed-out.
+ */
+static struct netconsole_target *alloc_and_init(void)
 {
-	int err = -ENOMEM;
 	struct netconsole_target *nt;
 
-	/*
-	 * Allocate and initialize with defaults.
-	 * Note that these targets get their config_item fields zeroed-out.
-	 */
 	nt = kzalloc(sizeof(*nt), GFP_KERNEL);
 	if (!nt)
-		goto fail;
+		return nt;
 
 	nt->np.name = "netconsole";
 	strscpy(nt->np.dev_name, "eth0", IFNAMSIZ);
@@ -187,6 +184,21 @@ static struct netconsole_target *alloc_param_target(char *target_config)
 	nt->np.remote_port = 6666;
 	eth_broadcast_addr(nt->np.remote_mac);
 
+	return nt;
+}
+
+/* Allocate new target (from boot/module param) and setup netpoll for it */
+static struct netconsole_target *alloc_param_target(char *target_config)
+{
+	struct netconsole_target *nt;
+	int err;
+
+	nt = alloc_and_init();
+	if (!nt) {
+		err = -ENOMEM;
+		goto fail;
+	}
+
 	if (*target_config == '+') {
 		nt->extended = true;
 		target_config++;
@@ -195,6 +207,7 @@ static struct netconsole_target *alloc_param_target(char *target_config)
 	if (*target_config == 'r') {
 		if (!nt->extended) {
 			pr_err("Netconsole configuration error. Release feature requires extended log message");
+			err = -EINVAL;
 			goto fail;
 		}
 		nt->release = true;
@@ -664,23 +677,13 @@ static const struct config_item_type netconsole_target_type = {
 static struct config_item *make_netconsole_target(struct config_group *group,
 						  const char *name)
 {
-	unsigned long flags;
 	struct netconsole_target *nt;
+	unsigned long flags;
 
-	/*
-	 * Allocate and initialize with defaults.
-	 * Target is disabled at creation (!enabled).
-	 */
-	nt = kzalloc(sizeof(*nt), GFP_KERNEL);
+	nt = alloc_and_init();
 	if (!nt)
 		return ERR_PTR(-ENOMEM);
 
-	nt->np.name = "netconsole";
-	strscpy(nt->np.dev_name, "eth0", IFNAMSIZ);
-	nt->np.local_port = 6665;
-	nt->np.remote_port = 6666;
-	eth_broadcast_addr(nt->np.remote_mac);
-
 	/* Initialize the config_item member */
 	config_item_init_type_name(&nt->item, name, &netconsole_target_type);
 
-- 
GitLab


From fad361a2ee9099028774ff9081bf9abf08bd2ff0 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 11 Aug 2023 02:31:58 -0700
Subject: [PATCH 1315/1806] netconsole: Enable compile time configuration

Enable netconsole features to be set at compilation time. Create two
Kconfig options that allow users to set extended logs and release
prepending features at compilation time.

Right now, the user needs to pass command line parameters to netconsole,
such as "+"/"r" to enable extended logs and version prepending features.

With these two options, the user could set the default values for the
features at compile time, and don't need to pass it in the command line
to get them enabled, simplifying the command line.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230811093158.1678322-3-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/Kconfig      | 22 ++++++++++++++++++++++
 drivers/net/netconsole.c |  5 +++++
 2 files changed, 27 insertions(+)

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index be43cd08027b5..44eeb5d61ba9f 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -332,6 +332,28 @@ config NETCONSOLE_DYNAMIC
 	  at runtime through a userspace interface exported using configfs.
 	  See <file:Documentation/networking/netconsole.rst> for details.
 
+config NETCONSOLE_EXTENDED_LOG
+	bool "Set kernel extended message by default"
+	depends on NETCONSOLE
+	default n
+	help
+	  Set extended log support for netconsole message. If this option is
+	  set, log messages are transmitted with extended metadata header in a
+	  format similar to /dev/kmsg.  See
+	  <file:Documentation/networking/netconsole.rst> for details.
+
+config NETCONSOLE_PREPEND_RELEASE
+	bool "Prepend kernel release version in the message by default"
+	depends on NETCONSOLE_EXTENDED_LOG
+	default n
+	help
+	  Set kernel release to be prepended to each netconsole message by
+	  default. If this option is set, the kernel release is prepended into
+	  the first field of every netconsole message, so, the netconsole
+	  server/peer can easily identify what kernel release is logging each
+	  message.  See <file:Documentation/networking/netconsole.rst> for
+	  details.
+
 config NETPOLL
 	def_bool NETCONSOLE
 
diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 670b6f0a054c6..3111e16485921 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -178,6 +178,11 @@ static struct netconsole_target *alloc_and_init(void)
 	if (!nt)
 		return nt;
 
+	if (IS_ENABLED(CONFIG_NETCONSOLE_EXTENDED_LOG))
+		nt->extended = true;
+	if (IS_ENABLED(CONFIG_NETCONSOLE_PREPEND_RELEASE))
+		nt->release = true;
+
 	nt->np.name = "netconsole";
 	strscpy(nt->np.dev_name, "eth0", IFNAMSIZ);
 	nt->np.local_port = 6665;
-- 
GitLab


From 6c9f86d3632c1abcbdaabeab1ee6d6de059b4ae7 Mon Sep 17 00:00:00 2001
From: Xu Kuohai <xukuohai@huawei.com>
Date: Tue, 15 Aug 2023 11:41:52 -0400
Subject: [PATCH 1316/1806] arm64: insn: Add encoders for LDRSB/LDRSH/LDRSW

To support BPF sign-extend load instructions, add encoders for
LDRSB/LDRSH/LDRSW.

LDRSB/LDRSH/LDRSW (immediate) is encoded as follows:

     3     2 2   2   2                       1         0         0
     0     7 6   4   2                       0         5         0
  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  | sz|1 1 1|0|0 1|opc|        imm12          |    Rn   |    Rt   |
  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

LDRSB/LDRSH/LDRSW (register) is encoded as follows:

     3     2 2   2   2 2         1     1 1   1         0         0
     0     7 6   4   2 1         6     3 2   0         5         0
  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  | sz|1 1 1|0|0 0|opc|1|    Rm   | opt |S|1 0|    Rn   |    Rt   |
  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

where:

   - sz
     indicates whether 8-bit, 16-bit or 32-bit data is to be loaded

   - opc
     opc[1] (bit 23) is always 1 and opc[0] == 1 indicates regsize
     is 32-bit. Since BPF signed load instructions always exend the
     sign bit to bit 63 regardless of whether it loads an 8-bit,
     16-bit or 32-bit data. So only 64-bit register size is required.
     That is, it's sufficient to set field opc fixed to 0x2.

   - opt
     Indicates whether to sign extend the offset register Rm and the
     effective bits of Rm. We set opt to 0x7 (SXTX) since we'll use
     Rm as a sgined 64-bit value in BPF.

   - S
     Optional only when opt field is 0x3 (LSL)

In short, the above fields are encoded to the values listed below.

                   sz   opc  opt   S
LDRSB (immediate)  0x0  0x2  na    na
LDRSH (immediate)  0x1  0x2  na    na
LDRSW (immediate)  0x2  0x2  na    na
LDRSB (register)   0x0  0x2  0x7   0
LDRSH (register)   0x1  0x2  0x7   0
LDRSW (register)   0x2  0x2  0x7   0

Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Florent Revest <revest@chromium.org>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/bpf/20230815154158.717901-2-xukuohai@huaweicloud.com
---
 arch/arm64/include/asm/insn.h | 4 ++++
 arch/arm64/lib/insn.c         | 6 ++++++
 2 files changed, 10 insertions(+)

diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 139a88e4e8522..db1aeacd4cd99 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -186,6 +186,8 @@ enum aarch64_insn_ldst_type {
 	AARCH64_INSN_LDST_LOAD_ACQ_EX,
 	AARCH64_INSN_LDST_STORE_EX,
 	AARCH64_INSN_LDST_STORE_REL_EX,
+	AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET,
+	AARCH64_INSN_LDST_SIGNED_LOAD_REG_OFFSET,
 };
 
 enum aarch64_insn_adsb_type {
@@ -324,6 +326,7 @@ __AARCH64_INSN_FUNCS(prfm,	0x3FC00000, 0x39800000)
 __AARCH64_INSN_FUNCS(prfm_lit,	0xFF000000, 0xD8000000)
 __AARCH64_INSN_FUNCS(store_imm,	0x3FC00000, 0x39000000)
 __AARCH64_INSN_FUNCS(load_imm,	0x3FC00000, 0x39400000)
+__AARCH64_INSN_FUNCS(signed_load_imm, 0X3FC00000, 0x39800000)
 __AARCH64_INSN_FUNCS(store_pre,	0x3FE00C00, 0x38000C00)
 __AARCH64_INSN_FUNCS(load_pre,	0x3FE00C00, 0x38400C00)
 __AARCH64_INSN_FUNCS(store_post,	0x3FE00C00, 0x38000400)
@@ -337,6 +340,7 @@ __AARCH64_INSN_FUNCS(ldset,	0x3F20FC00, 0x38203000)
 __AARCH64_INSN_FUNCS(swp,	0x3F20FC00, 0x38208000)
 __AARCH64_INSN_FUNCS(cas,	0x3FA07C00, 0x08A07C00)
 __AARCH64_INSN_FUNCS(ldr_reg,	0x3FE0EC00, 0x38606800)
+__AARCH64_INSN_FUNCS(signed_ldr_reg, 0X3FE0FC00, 0x38A0E800)
 __AARCH64_INSN_FUNCS(ldr_imm,	0x3FC00000, 0x39400000)
 __AARCH64_INSN_FUNCS(ldr_lit,	0xBF000000, 0x18000000)
 __AARCH64_INSN_FUNCS(ldrsw_lit,	0xFF000000, 0x98000000)
diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c
index 924934cb85eea..a635ab83fee35 100644
--- a/arch/arm64/lib/insn.c
+++ b/arch/arm64/lib/insn.c
@@ -385,6 +385,9 @@ u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg,
 	case AARCH64_INSN_LDST_LOAD_REG_OFFSET:
 		insn = aarch64_insn_get_ldr_reg_value();
 		break;
+	case AARCH64_INSN_LDST_SIGNED_LOAD_REG_OFFSET:
+		insn = aarch64_insn_get_signed_ldr_reg_value();
+		break;
 	case AARCH64_INSN_LDST_STORE_REG_OFFSET:
 		insn = aarch64_insn_get_str_reg_value();
 		break;
@@ -430,6 +433,9 @@ u32 aarch64_insn_gen_load_store_imm(enum aarch64_insn_register reg,
 	case AARCH64_INSN_LDST_LOAD_IMM_OFFSET:
 		insn = aarch64_insn_get_ldr_imm_value();
 		break;
+	case AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET:
+		insn = aarch64_insn_get_signed_load_imm_value();
+		break;
 	case AARCH64_INSN_LDST_STORE_IMM_OFFSET:
 		insn = aarch64_insn_get_str_imm_value();
 		break;
-- 
GitLab


From cc88f540da52d418ede80846c2fd771a4ef19227 Mon Sep 17 00:00:00 2001
From: Xu Kuohai <xukuohai@huawei.com>
Date: Tue, 15 Aug 2023 11:41:53 -0400
Subject: [PATCH 1317/1806] bpf, arm64: Support sign-extension load
 instructions

Add JIT support for sign-extension load instructions.

Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Florent Revest <revest@chromium.org>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/bpf/20230815154158.717901-3-xukuohai@huaweicloud.com
---
 arch/arm64/net/bpf_jit.h      |  6 +++++
 arch/arm64/net/bpf_jit_comp.c | 45 ++++++++++++++++++++++++++++-------
 2 files changed, 43 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index c2edadb8ec6a3..086ffbad0eb54 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -59,10 +59,13 @@
 		AARCH64_INSN_LDST_##type##_REG_OFFSET)
 #define A64_STRB(Wt, Xn, Xm)  A64_LS_REG(Wt, Xn, Xm, 8, STORE)
 #define A64_LDRB(Wt, Xn, Xm)  A64_LS_REG(Wt, Xn, Xm, 8, LOAD)
+#define A64_LDRSB(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 8, SIGNED_LOAD)
 #define A64_STRH(Wt, Xn, Xm)  A64_LS_REG(Wt, Xn, Xm, 16, STORE)
 #define A64_LDRH(Wt, Xn, Xm)  A64_LS_REG(Wt, Xn, Xm, 16, LOAD)
+#define A64_LDRSH(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 16, SIGNED_LOAD)
 #define A64_STR32(Wt, Xn, Xm) A64_LS_REG(Wt, Xn, Xm, 32, STORE)
 #define A64_LDR32(Wt, Xn, Xm) A64_LS_REG(Wt, Xn, Xm, 32, LOAD)
+#define A64_LDRSW(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 32, SIGNED_LOAD)
 #define A64_STR64(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 64, STORE)
 #define A64_LDR64(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 64, LOAD)
 
@@ -73,10 +76,13 @@
 		AARCH64_INSN_LDST_##type##_IMM_OFFSET)
 #define A64_STRBI(Wt, Xn, imm)  A64_LS_IMM(Wt, Xn, imm, 8, STORE)
 #define A64_LDRBI(Wt, Xn, imm)  A64_LS_IMM(Wt, Xn, imm, 8, LOAD)
+#define A64_LDRSBI(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 8, SIGNED_LOAD)
 #define A64_STRHI(Wt, Xn, imm)  A64_LS_IMM(Wt, Xn, imm, 16, STORE)
 #define A64_LDRHI(Wt, Xn, imm)  A64_LS_IMM(Wt, Xn, imm, 16, LOAD)
+#define A64_LDRSHI(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 16, SIGNED_LOAD)
 #define A64_STR32I(Wt, Xn, imm) A64_LS_IMM(Wt, Xn, imm, 32, STORE)
 #define A64_LDR32I(Wt, Xn, imm) A64_LS_IMM(Wt, Xn, imm, 32, LOAD)
+#define A64_LDRSWI(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 32, SIGNED_LOAD)
 #define A64_STR64I(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 64, STORE)
 #define A64_LDR64I(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 64, LOAD)
 
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index ec2174838f2af..22f1b0d5fb3c7 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -715,7 +715,8 @@ static int add_exception_handler(const struct bpf_insn *insn,
 		/* First pass */
 		return 0;
 
-	if (BPF_MODE(insn->code) != BPF_PROBE_MEM)
+	if (BPF_MODE(insn->code) != BPF_PROBE_MEM &&
+		BPF_MODE(insn->code) != BPF_PROBE_MEMSX)
 		return 0;
 
 	if (!ctx->prog->aux->extable ||
@@ -779,6 +780,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	u8 dst_adj;
 	int off_adj;
 	int ret;
+	bool sign_extend;
 
 	switch (code) {
 	/* dst = src */
@@ -1122,7 +1124,7 @@ emit_cond_jmp:
 		return 1;
 	}
 
-	/* LDX: dst = *(size *)(src + off) */
+	/* LDX: dst = (u64)*(unsigned size *)(src + off) */
 	case BPF_LDX | BPF_MEM | BPF_W:
 	case BPF_LDX | BPF_MEM | BPF_H:
 	case BPF_LDX | BPF_MEM | BPF_B:
@@ -1131,6 +1133,13 @@ emit_cond_jmp:
 	case BPF_LDX | BPF_PROBE_MEM | BPF_W:
 	case BPF_LDX | BPF_PROBE_MEM | BPF_H:
 	case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+	/* LDXS: dst_reg = (s64)*(signed size *)(src_reg + off) */
+	case BPF_LDX | BPF_MEMSX | BPF_B:
+	case BPF_LDX | BPF_MEMSX | BPF_H:
+	case BPF_LDX | BPF_MEMSX | BPF_W:
+	case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
+	case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
+	case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
 		if (ctx->fpb_offset > 0 && src == fp) {
 			src_adj = fpb;
 			off_adj = off + ctx->fpb_offset;
@@ -1138,29 +1147,49 @@ emit_cond_jmp:
 			src_adj = src;
 			off_adj = off;
 		}
+		sign_extend = (BPF_MODE(insn->code) == BPF_MEMSX ||
+				BPF_MODE(insn->code) == BPF_PROBE_MEMSX);
 		switch (BPF_SIZE(code)) {
 		case BPF_W:
 			if (is_lsi_offset(off_adj, 2)) {
-				emit(A64_LDR32I(dst, src_adj, off_adj), ctx);
+				if (sign_extend)
+					emit(A64_LDRSWI(dst, src_adj, off_adj), ctx);
+				else
+					emit(A64_LDR32I(dst, src_adj, off_adj), ctx);
 			} else {
 				emit_a64_mov_i(1, tmp, off, ctx);
-				emit(A64_LDR32(dst, src, tmp), ctx);
+				if (sign_extend)
+					emit(A64_LDRSW(dst, src_adj, off_adj), ctx);
+				else
+					emit(A64_LDR32(dst, src, tmp), ctx);
 			}
 			break;
 		case BPF_H:
 			if (is_lsi_offset(off_adj, 1)) {
-				emit(A64_LDRHI(dst, src_adj, off_adj), ctx);
+				if (sign_extend)
+					emit(A64_LDRSHI(dst, src_adj, off_adj), ctx);
+				else
+					emit(A64_LDRHI(dst, src_adj, off_adj), ctx);
 			} else {
 				emit_a64_mov_i(1, tmp, off, ctx);
-				emit(A64_LDRH(dst, src, tmp), ctx);
+				if (sign_extend)
+					emit(A64_LDRSH(dst, src, tmp), ctx);
+				else
+					emit(A64_LDRH(dst, src, tmp), ctx);
 			}
 			break;
 		case BPF_B:
 			if (is_lsi_offset(off_adj, 0)) {
-				emit(A64_LDRBI(dst, src_adj, off_adj), ctx);
+				if (sign_extend)
+					emit(A64_LDRSBI(dst, src_adj, off_adj), ctx);
+				else
+					emit(A64_LDRBI(dst, src_adj, off_adj), ctx);
 			} else {
 				emit_a64_mov_i(1, tmp, off, ctx);
-				emit(A64_LDRB(dst, src, tmp), ctx);
+				if (sign_extend)
+					emit(A64_LDRSB(dst, src, tmp), ctx);
+				else
+					emit(A64_LDRB(dst, src, tmp), ctx);
 			}
 			break;
 		case BPF_DW:
-- 
GitLab


From bb0a1d6b49cb8293b09d290536315b4a134ef1e7 Mon Sep 17 00:00:00 2001
From: Xu Kuohai <xukuohai@huawei.com>
Date: Tue, 15 Aug 2023 11:41:54 -0400
Subject: [PATCH 1318/1806] bpf, arm64: Support sign-extension mov instructions

Add JIT support for BPF sign-extension mov instructions with arm64
SXTB/SXTH/SXTW instructions.

Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Florent Revest <revest@chromium.org>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/bpf/20230815154158.717901-4-xukuohai@huaweicloud.com
---
 arch/arm64/net/bpf_jit.h      |  5 +++++
 arch/arm64/net/bpf_jit_comp.c | 15 ++++++++++++++-
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index 086ffbad0eb54..949810a0c48c8 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -192,6 +192,11 @@
 #define A64_UXTH(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 15)
 #define A64_UXTW(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 31)
 
+/* Sign extend */
+#define A64_SXTB(sf, Rd, Rn) A64_SBFM(sf, Rd, Rn, 0, 7)
+#define A64_SXTH(sf, Rd, Rn) A64_SBFM(sf, Rd, Rn, 0, 15)
+#define A64_SXTW(sf, Rd, Rn) A64_SBFM(sf, Rd, Rn, 0, 31)
+
 /* Move wide (immediate) */
 #define A64_MOVEW(sf, Rd, imm16, shift, type) \
 	aarch64_insn_gen_movewide(Rd, imm16, shift, \
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 22f1b0d5fb3c7..9b796e74ef42d 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -786,7 +786,20 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
 	case BPF_ALU64 | BPF_MOV | BPF_X:
-		emit(A64_MOV(is64, dst, src), ctx);
+		switch (insn->off) {
+		case 0:
+			emit(A64_MOV(is64, dst, src), ctx);
+			break;
+		case 8:
+			emit(A64_SXTB(is64, dst, src), ctx);
+			break;
+		case 16:
+			emit(A64_SXTH(is64, dst, src), ctx);
+			break;
+		case 32:
+			emit(A64_SXTW(is64, dst, src), ctx);
+			break;
+		}
 		break;
 	/* dst = dst OP src */
 	case BPF_ALU | BPF_ADD | BPF_X:
-- 
GitLab


From 1104247f3f97916f0afc29b73112c97affbfdbd2 Mon Sep 17 00:00:00 2001
From: Xu Kuohai <xukuohai@huawei.com>
Date: Tue, 15 Aug 2023 11:41:55 -0400
Subject: [PATCH 1319/1806] bpf, arm64: Support unconditional bswap

Add JIT support for unconditional bswap instructions.

Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Florent Revest <revest@chromium.org>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/bpf/20230815154158.717901-5-xukuohai@huaweicloud.com
---
 arch/arm64/net/bpf_jit_comp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 9b796e74ef42d..1d35acb880dc6 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -855,11 +855,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	/* dst = BSWAP##imm(dst) */
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
+	case BPF_ALU64 | BPF_END | BPF_FROM_LE:
 #ifdef CONFIG_CPU_BIG_ENDIAN
-		if (BPF_SRC(code) == BPF_FROM_BE)
+		if (BPF_CLASS(code) == BPF_ALU && BPF_SRC(code) == BPF_FROM_BE)
 			goto emit_bswap_uxt;
 #else /* !CONFIG_CPU_BIG_ENDIAN */
-		if (BPF_SRC(code) == BPF_FROM_LE)
+		if (BPF_CLASS(code) == BPF_ALU && BPF_SRC(code) == BPF_FROM_LE)
 			goto emit_bswap_uxt;
 #endif
 		switch (imm) {
-- 
GitLab


From c32b6ee514d26dc6c40c45984e534b2d87fba917 Mon Sep 17 00:00:00 2001
From: Xu Kuohai <xukuohai@huawei.com>
Date: Tue, 15 Aug 2023 11:41:56 -0400
Subject: [PATCH 1320/1806] bpf, arm64: Support 32-bit offset jmp instruction

Add support for 32-bit offset jmp instructions. Given the arm64 direct jump
range is +-128MB, which is large enough for BPF prog, jumps beyond this range
are not supported.

Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Florent Revest <revest@chromium.org>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/bpf/20230815154158.717901-6-xukuohai@huaweicloud.com
---
 arch/arm64/net/bpf_jit_comp.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 1d35acb880dc6..924b8ef2e46aa 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -982,7 +982,11 @@ emit_bswap_uxt:
 
 	/* JUMP off */
 	case BPF_JMP | BPF_JA:
-		jmp_offset = bpf2a64_offset(i, off, ctx);
+	case BPF_JMP32 | BPF_JA:
+		if (BPF_CLASS(code) == BPF_JMP)
+			jmp_offset = bpf2a64_offset(i, off, ctx);
+		else
+			jmp_offset = bpf2a64_offset(i, imm, ctx);
 		check_imm26(jmp_offset);
 		emit(A64_B(jmp_offset), ctx);
 		break;
-- 
GitLab


From 68b18191fe417459b4ebf4024cdf1b9d7b393de9 Mon Sep 17 00:00:00 2001
From: Xu Kuohai <xukuohai@huawei.com>
Date: Tue, 15 Aug 2023 11:41:57 -0400
Subject: [PATCH 1321/1806] bpf, arm64: Support signed div/mod instructions

Add JIT for signed div/mod instructions.

Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Florent Revest <revest@chromium.org>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/bpf/20230815154158.717901-7-xukuohai@huaweicloud.com
---
 arch/arm64/net/bpf_jit.h      |  1 +
 arch/arm64/net/bpf_jit_comp.c | 20 ++++++++++++++++----
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index 949810a0c48c8..23b1b34db088e 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -234,6 +234,7 @@
 #define A64_DATA2(sf, Rd, Rn, Rm, type) aarch64_insn_gen_data2(Rd, Rn, Rm, \
 	A64_VARIANT(sf), AARCH64_INSN_DATA2_##type)
 #define A64_UDIV(sf, Rd, Rn, Rm) A64_DATA2(sf, Rd, Rn, Rm, UDIV)
+#define A64_SDIV(sf, Rd, Rn, Rm) A64_DATA2(sf, Rd, Rn, Rm, SDIV)
 #define A64_LSLV(sf, Rd, Rn, Rm) A64_DATA2(sf, Rd, Rn, Rm, LSLV)
 #define A64_LSRV(sf, Rd, Rn, Rm) A64_DATA2(sf, Rd, Rn, Rm, LSRV)
 #define A64_ASRV(sf, Rd, Rn, Rm) A64_DATA2(sf, Rd, Rn, Rm, ASRV)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 924b8ef2e46aa..150d1c6543f7f 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -828,11 +828,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
-		emit(A64_UDIV(is64, dst, dst, src), ctx);
+		if (!off)
+			emit(A64_UDIV(is64, dst, dst, src), ctx);
+		else
+			emit(A64_SDIV(is64, dst, dst, src), ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
-		emit(A64_UDIV(is64, tmp, dst, src), ctx);
+		if (!off)
+			emit(A64_UDIV(is64, tmp, dst, src), ctx);
+		else
+			emit(A64_SDIV(is64, tmp, dst, src), ctx);
 		emit(A64_MSUB(is64, dst, dst, tmp, src), ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_X:
@@ -959,12 +965,18 @@ emit_bswap_uxt:
 	case BPF_ALU | BPF_DIV | BPF_K:
 	case BPF_ALU64 | BPF_DIV | BPF_K:
 		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_UDIV(is64, dst, dst, tmp), ctx);
+		if (!off)
+			emit(A64_UDIV(is64, dst, dst, tmp), ctx);
+		else
+			emit(A64_SDIV(is64, dst, dst, tmp), ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_K:
 	case BPF_ALU64 | BPF_MOD | BPF_K:
 		emit_a64_mov_i(is64, tmp2, imm, ctx);
-		emit(A64_UDIV(is64, tmp, dst, tmp2), ctx);
+		if (!off)
+			emit(A64_UDIV(is64, tmp, dst, tmp2), ctx);
+		else
+			emit(A64_SDIV(is64, tmp, dst, tmp2), ctx);
 		emit(A64_MSUB(is64, dst, dst, tmp, tmp2), ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_K:
-- 
GitLab


From 5f6395fd06806a009b93436612768fe3777a154f Mon Sep 17 00:00:00 2001
From: Xu Kuohai <xukuohai@huawei.com>
Date: Tue, 15 Aug 2023 11:41:58 -0400
Subject: [PATCH 1322/1806] selftests/bpf: Enable cpu v4 tests for arm64

Enable CPU v4 instruction tests for arm64. Below are the test results from
BPF test_progs selftests:

  # ./test_progs -t ldsx_insn,verifier_sdiv,verifier_movsx,verifier_ldsx,verifier_gotol,verifier_bswap
  #115/1   ldsx_insn/map_val and probed_memory:OK
  #115/2   ldsx_insn/ctx_member_sign_ext:OK
  #115/3   ldsx_insn/ctx_member_narrow_sign_ext:OK
  #115     ldsx_insn:OK
  #302/1   verifier_bswap/BSWAP, 16:OK
  #302/2   verifier_bswap/BSWAP, 16 @unpriv:OK
  #302/3   verifier_bswap/BSWAP, 32:OK
  #302/4   verifier_bswap/BSWAP, 32 @unpriv:OK
  #302/5   verifier_bswap/BSWAP, 64:OK
  #302/6   verifier_bswap/BSWAP, 64 @unpriv:OK
  #302     verifier_bswap:OK
  #316/1   verifier_gotol/gotol, small_imm:OK
  #316/2   verifier_gotol/gotol, small_imm @unpriv:OK
  #316     verifier_gotol:OK
  #324/1   verifier_ldsx/LDSX, S8:OK
  #324/2   verifier_ldsx/LDSX, S8 @unpriv:OK
  #324/3   verifier_ldsx/LDSX, S16:OK
  #324/4   verifier_ldsx/LDSX, S16 @unpriv:OK
  #324/5   verifier_ldsx/LDSX, S32:OK
  #324/6   verifier_ldsx/LDSX, S32 @unpriv:OK
  #324/7   verifier_ldsx/LDSX, S8 range checking, privileged:OK
  #324/8   verifier_ldsx/LDSX, S16 range checking:OK
  #324/9   verifier_ldsx/LDSX, S16 range checking @unpriv:OK
  #324/10  verifier_ldsx/LDSX, S32 range checking:OK
  #324/11  verifier_ldsx/LDSX, S32 range checking @unpriv:OK
  #324     verifier_ldsx:OK
  #335/1   verifier_movsx/MOV32SX, S8:OK
  #335/2   verifier_movsx/MOV32SX, S8 @unpriv:OK
  #335/3   verifier_movsx/MOV32SX, S16:OK
  #335/4   verifier_movsx/MOV32SX, S16 @unpriv:OK
  #335/5   verifier_movsx/MOV64SX, S8:OK
  #335/6   verifier_movsx/MOV64SX, S8 @unpriv:OK
  #335/7   verifier_movsx/MOV64SX, S16:OK
  #335/8   verifier_movsx/MOV64SX, S16 @unpriv:OK
  #335/9   verifier_movsx/MOV64SX, S32:OK
  #335/10  verifier_movsx/MOV64SX, S32 @unpriv:OK
  #335/11  verifier_movsx/MOV32SX, S8, range_check:OK
  #335/12  verifier_movsx/MOV32SX, S8, range_check @unpriv:OK
  #335/13  verifier_movsx/MOV32SX, S16, range_check:OK
  #335/14  verifier_movsx/MOV32SX, S16, range_check @unpriv:OK
  #335/15  verifier_movsx/MOV32SX, S16, range_check 2:OK
  #335/16  verifier_movsx/MOV32SX, S16, range_check 2 @unpriv:OK
  #335/17  verifier_movsx/MOV64SX, S8, range_check:OK
  #335/18  verifier_movsx/MOV64SX, S8, range_check @unpriv:OK
  #335/19  verifier_movsx/MOV64SX, S16, range_check:OK
  #335/20  verifier_movsx/MOV64SX, S16, range_check @unpriv:OK
  #335/21  verifier_movsx/MOV64SX, S32, range_check:OK
  #335/22  verifier_movsx/MOV64SX, S32, range_check @unpriv:OK
  #335/23  verifier_movsx/MOV64SX, S16, R10 Sign Extension:OK
  #335/24  verifier_movsx/MOV64SX, S16, R10 Sign Extension @unpriv:OK
  #335     verifier_movsx:OK
  #347/1   verifier_sdiv/SDIV32, non-zero imm divisor, check 1:OK
  #347/2   verifier_sdiv/SDIV32, non-zero imm divisor, check 1 @unpriv:OK
  #347/3   verifier_sdiv/SDIV32, non-zero imm divisor, check 2:OK
  #347/4   verifier_sdiv/SDIV32, non-zero imm divisor, check 2 @unpriv:OK
  #347/5   verifier_sdiv/SDIV32, non-zero imm divisor, check 3:OK
  #347/6   verifier_sdiv/SDIV32, non-zero imm divisor, check 3 @unpriv:OK
  #347/7   verifier_sdiv/SDIV32, non-zero imm divisor, check 4:OK
  #347/8   verifier_sdiv/SDIV32, non-zero imm divisor, check 4 @unpriv:OK
  #347/9   verifier_sdiv/SDIV32, non-zero imm divisor, check 5:OK
  #347/10  verifier_sdiv/SDIV32, non-zero imm divisor, check 5 @unpriv:OK
  #347/11  verifier_sdiv/SDIV32, non-zero imm divisor, check 6:OK
  #347/12  verifier_sdiv/SDIV32, non-zero imm divisor, check 6 @unpriv:OK
  #347/13  verifier_sdiv/SDIV32, non-zero imm divisor, check 7:OK
  #347/14  verifier_sdiv/SDIV32, non-zero imm divisor, check 7 @unpriv:OK
  #347/15  verifier_sdiv/SDIV32, non-zero imm divisor, check 8:OK
  #347/16  verifier_sdiv/SDIV32, non-zero imm divisor, check 8 @unpriv:OK
  #347/17  verifier_sdiv/SDIV32, non-zero reg divisor, check 1:OK
  #347/18  verifier_sdiv/SDIV32, non-zero reg divisor, check 1 @unpriv:OK
  #347/19  verifier_sdiv/SDIV32, non-zero reg divisor, check 2:OK
  #347/20  verifier_sdiv/SDIV32, non-zero reg divisor, check 2 @unpriv:OK
  #347/21  verifier_sdiv/SDIV32, non-zero reg divisor, check 3:OK
  #347/22  verifier_sdiv/SDIV32, non-zero reg divisor, check 3 @unpriv:OK
  #347/23  verifier_sdiv/SDIV32, non-zero reg divisor, check 4:OK
  #347/24  verifier_sdiv/SDIV32, non-zero reg divisor, check 4 @unpriv:OK
  #347/25  verifier_sdiv/SDIV32, non-zero reg divisor, check 5:OK
  #347/26  verifier_sdiv/SDIV32, non-zero reg divisor, check 5 @unpriv:OK
  #347/27  verifier_sdiv/SDIV32, non-zero reg divisor, check 6:OK
  #347/28  verifier_sdiv/SDIV32, non-zero reg divisor, check 6 @unpriv:OK
  #347/29  verifier_sdiv/SDIV32, non-zero reg divisor, check 7:OK
  #347/30  verifier_sdiv/SDIV32, non-zero reg divisor, check 7 @unpriv:OK
  #347/31  verifier_sdiv/SDIV32, non-zero reg divisor, check 8:OK
  #347/32  verifier_sdiv/SDIV32, non-zero reg divisor, check 8 @unpriv:OK
  #347/33  verifier_sdiv/SDIV64, non-zero imm divisor, check 1:OK
  #347/34  verifier_sdiv/SDIV64, non-zero imm divisor, check 1 @unpriv:OK
  #347/35  verifier_sdiv/SDIV64, non-zero imm divisor, check 2:OK
  #347/36  verifier_sdiv/SDIV64, non-zero imm divisor, check 2 @unpriv:OK
  #347/37  verifier_sdiv/SDIV64, non-zero imm divisor, check 3:OK
  #347/38  verifier_sdiv/SDIV64, non-zero imm divisor, check 3 @unpriv:OK
  #347/39  verifier_sdiv/SDIV64, non-zero imm divisor, check 4:OK
  #347/40  verifier_sdiv/SDIV64, non-zero imm divisor, check 4 @unpriv:OK
  #347/41  verifier_sdiv/SDIV64, non-zero imm divisor, check 5:OK
  #347/42  verifier_sdiv/SDIV64, non-zero imm divisor, check 5 @unpriv:OK
  #347/43  verifier_sdiv/SDIV64, non-zero imm divisor, check 6:OK
  #347/44  verifier_sdiv/SDIV64, non-zero imm divisor, check 6 @unpriv:OK
  #347/45  verifier_sdiv/SDIV64, non-zero reg divisor, check 1:OK
  #347/46  verifier_sdiv/SDIV64, non-zero reg divisor, check 1 @unpriv:OK
  #347/47  verifier_sdiv/SDIV64, non-zero reg divisor, check 2:OK
  #347/48  verifier_sdiv/SDIV64, non-zero reg divisor, check 2 @unpriv:OK
  #347/49  verifier_sdiv/SDIV64, non-zero reg divisor, check 3:OK
  #347/50  verifier_sdiv/SDIV64, non-zero reg divisor, check 3 @unpriv:OK
  #347/51  verifier_sdiv/SDIV64, non-zero reg divisor, check 4:OK
  #347/52  verifier_sdiv/SDIV64, non-zero reg divisor, check 4 @unpriv:OK
  #347/53  verifier_sdiv/SDIV64, non-zero reg divisor, check 5:OK
  #347/54  verifier_sdiv/SDIV64, non-zero reg divisor, check 5 @unpriv:OK
  #347/55  verifier_sdiv/SDIV64, non-zero reg divisor, check 6:OK
  #347/56  verifier_sdiv/SDIV64, non-zero reg divisor, check 6 @unpriv:OK
  #347/57  verifier_sdiv/SMOD32, non-zero imm divisor, check 1:OK
  #347/58  verifier_sdiv/SMOD32, non-zero imm divisor, check 1 @unpriv:OK
  #347/59  verifier_sdiv/SMOD32, non-zero imm divisor, check 2:OK
  #347/60  verifier_sdiv/SMOD32, non-zero imm divisor, check 2 @unpriv:OK
  #347/61  verifier_sdiv/SMOD32, non-zero imm divisor, check 3:OK
  #347/62  verifier_sdiv/SMOD32, non-zero imm divisor, check 3 @unpriv:OK
  #347/63  verifier_sdiv/SMOD32, non-zero imm divisor, check 4:OK
  #347/64  verifier_sdiv/SMOD32, non-zero imm divisor, check 4 @unpriv:OK
  #347/65  verifier_sdiv/SMOD32, non-zero imm divisor, check 5:OK
  #347/66  verifier_sdiv/SMOD32, non-zero imm divisor, check 5 @unpriv:OK
  #347/67  verifier_sdiv/SMOD32, non-zero imm divisor, check 6:OK
  #347/68  verifier_sdiv/SMOD32, non-zero imm divisor, check 6 @unpriv:OK
  #347/69  verifier_sdiv/SMOD32, non-zero reg divisor, check 1:OK
  #347/70  verifier_sdiv/SMOD32, non-zero reg divisor, check 1 @unpriv:OK
  #347/71  verifier_sdiv/SMOD32, non-zero reg divisor, check 2:OK
  #347/72  verifier_sdiv/SMOD32, non-zero reg divisor, check 2 @unpriv:OK
  #347/73  verifier_sdiv/SMOD32, non-zero reg divisor, check 3:OK
  #347/74  verifier_sdiv/SMOD32, non-zero reg divisor, check 3 @unpriv:OK
  #347/75  verifier_sdiv/SMOD32, non-zero reg divisor, check 4:OK
  #347/76  verifier_sdiv/SMOD32, non-zero reg divisor, check 4 @unpriv:OK
  #347/77  verifier_sdiv/SMOD32, non-zero reg divisor, check 5:OK
  #347/78  verifier_sdiv/SMOD32, non-zero reg divisor, check 5 @unpriv:OK
  #347/79  verifier_sdiv/SMOD32, non-zero reg divisor, check 6:OK
  #347/80  verifier_sdiv/SMOD32, non-zero reg divisor, check 6 @unpriv:OK
  #347/81  verifier_sdiv/SMOD64, non-zero imm divisor, check 1:OK
  #347/82  verifier_sdiv/SMOD64, non-zero imm divisor, check 1 @unpriv:OK
  #347/83  verifier_sdiv/SMOD64, non-zero imm divisor, check 2:OK
  #347/84  verifier_sdiv/SMOD64, non-zero imm divisor, check 2 @unpriv:OK
  #347/85  verifier_sdiv/SMOD64, non-zero imm divisor, check 3:OK
  #347/86  verifier_sdiv/SMOD64, non-zero imm divisor, check 3 @unpriv:OK
  #347/87  verifier_sdiv/SMOD64, non-zero imm divisor, check 4:OK
  #347/88  verifier_sdiv/SMOD64, non-zero imm divisor, check 4 @unpriv:OK
  #347/89  verifier_sdiv/SMOD64, non-zero imm divisor, check 5:OK
  #347/90  verifier_sdiv/SMOD64, non-zero imm divisor, check 5 @unpriv:OK
  #347/91  verifier_sdiv/SMOD64, non-zero imm divisor, check 6:OK
  #347/92  verifier_sdiv/SMOD64, non-zero imm divisor, check 6 @unpriv:OK
  #347/93  verifier_sdiv/SMOD64, non-zero imm divisor, check 7:OK
  #347/94  verifier_sdiv/SMOD64, non-zero imm divisor, check 7 @unpriv:OK
  #347/95  verifier_sdiv/SMOD64, non-zero imm divisor, check 8:OK
  #347/96  verifier_sdiv/SMOD64, non-zero imm divisor, check 8 @unpriv:OK
  #347/97  verifier_sdiv/SMOD64, non-zero reg divisor, check 1:OK
  #347/98  verifier_sdiv/SMOD64, non-zero reg divisor, check 1 @unpriv:OK
  #347/99  verifier_sdiv/SMOD64, non-zero reg divisor, check 2:OK
  #347/100 verifier_sdiv/SMOD64, non-zero reg divisor, check 2 @unpriv:OK
  #347/101 verifier_sdiv/SMOD64, non-zero reg divisor, check 3:OK
  #347/102 verifier_sdiv/SMOD64, non-zero reg divisor, check 3 @unpriv:OK
  #347/103 verifier_sdiv/SMOD64, non-zero reg divisor, check 4:OK
  #347/104 verifier_sdiv/SMOD64, non-zero reg divisor, check 4 @unpriv:OK
  #347/105 verifier_sdiv/SMOD64, non-zero reg divisor, check 5:OK
  #347/106 verifier_sdiv/SMOD64, non-zero reg divisor, check 5 @unpriv:OK
  #347/107 verifier_sdiv/SMOD64, non-zero reg divisor, check 6:OK
  #347/108 verifier_sdiv/SMOD64, non-zero reg divisor, check 6 @unpriv:OK
  #347/109 verifier_sdiv/SMOD64, non-zero reg divisor, check 7:OK
  #347/110 verifier_sdiv/SMOD64, non-zero reg divisor, check 7 @unpriv:OK
  #347/111 verifier_sdiv/SMOD64, non-zero reg divisor, check 8:OK
  #347/112 verifier_sdiv/SMOD64, non-zero reg divisor, check 8 @unpriv:OK
  #347/113 verifier_sdiv/SDIV32, zero divisor:OK
  #347/114 verifier_sdiv/SDIV32, zero divisor @unpriv:OK
  #347/115 verifier_sdiv/SDIV64, zero divisor:OK
  #347/116 verifier_sdiv/SDIV64, zero divisor @unpriv:OK
  #347/117 verifier_sdiv/SMOD32, zero divisor:OK
  #347/118 verifier_sdiv/SMOD32, zero divisor @unpriv:OK
  #347/119 verifier_sdiv/SMOD64, zero divisor:OK
  #347/120 verifier_sdiv/SMOD64, zero divisor @unpriv:OK
  #347     verifier_sdiv:OK
  Summary: 6/166 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Florent Revest <revest@chromium.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/bpf/20230815154158.717901-8-xukuohai@huaweicloud.com
---
 tools/testing/selftests/bpf/progs/test_ldsx_insn.c | 2 +-
 tools/testing/selftests/bpf/progs/verifier_bswap.c | 2 +-
 tools/testing/selftests/bpf/progs/verifier_gotol.c | 2 +-
 tools/testing/selftests/bpf/progs/verifier_ldsx.c  | 2 +-
 tools/testing/selftests/bpf/progs/verifier_movsx.c | 2 +-
 tools/testing/selftests/bpf/progs/verifier_sdiv.c  | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
index 321abf8628017..916d9435f12ce 100644
--- a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
+++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
@@ -5,7 +5,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
 const volatile int skip = 0;
 #else
 const volatile int skip = 1;
diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
index 724bb38988b53..770f9d8825421 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bswap.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -4,7 +4,7 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
 
 SEC("socket")
 __description("BSWAP, 16")
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index ce48f7757db24..17319a505e87d 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -4,7 +4,7 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
 
 SEC("socket")
 __description("gotol, small_imm")
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index 3c3d1bddd67f9..4a2b567c0f699 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -4,7 +4,7 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
 
 SEC("socket")
 __description("LDSX, S8")
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
index be6f69a6b6593..d9528d578bd90 100644
--- a/tools/testing/selftests/bpf/progs/verifier_movsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -4,7 +4,7 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
 
 SEC("socket")
 __description("MOV32SX, S8")
diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
index f61a9a1058c8e..fa3945930e938 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sdiv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -4,7 +4,7 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#if defined(__TARGET_ARCH_x86) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
 
 SEC("socket")
 __description("SDIV32, non-zero imm divisor, check 1")
-- 
GitLab


From 29b22badb7a84b783e3a4fffca16f7768fb31205 Mon Sep 17 00:00:00 2001
From: Yan Zhai <yan@cloudflare.com>
Date: Thu, 17 Aug 2023 19:58:11 -0700
Subject: [PATCH 1323/1806] lwt: Fix return values of BPF xmit ops

BPF encap ops can return different types of positive values, such like
NET_RX_DROP, NET_XMIT_CN, NETDEV_TX_BUSY, and so on, from function
skb_do_redirect and bpf_lwt_xmit_reroute. At the xmit hook, such return
values would be treated implicitly as LWTUNNEL_XMIT_CONTINUE in
ip(6)_finish_output2. When this happens, skbs that have been freed would
continue to the neighbor subsystem, causing use-after-free bug and
kernel crashes.

To fix the incorrect behavior, skb_do_redirect return values can be
simply discarded, the same as tc-egress behavior. On the other hand,
bpf_lwt_xmit_reroute returns useful errors to local senders, e.g. PMTU
information. Thus convert its return values to avoid the conflict with
LWTUNNEL_XMIT_CONTINUE.

Fixes: 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure")
Reported-by: Jordan Griege <jgriege@cloudflare.com>
Suggested-by: Martin KaFai Lau <martin.lau@linux.dev>
Suggested-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Yan Zhai <yan@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/0d2b878186cfe215fec6b45769c1cd0591d3628d.1692326837.git.yan@cloudflare.com
---
 net/core/lwt_bpf.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 8b6b5e72b2179..4a0797f0a154b 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -60,9 +60,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 			ret = BPF_OK;
 		} else {
 			skb_reset_mac_header(skb);
-			ret = skb_do_redirect(skb);
-			if (ret == 0)
-				ret = BPF_REDIRECT;
+			skb_do_redirect(skb);
+			ret = BPF_REDIRECT;
 		}
 		break;
 
@@ -255,7 +254,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb)
 
 	err = dst_output(dev_net(skb_dst(skb)->dev), skb->sk, skb);
 	if (unlikely(err))
-		return err;
+		return net_xmit_errno(err);
 
 	/* ip[6]_finish_output2 understand LWTUNNEL_XMIT_DONE */
 	return LWTUNNEL_XMIT_DONE;
-- 
GitLab


From a171fbec88a2c730b108c7147ac5e7b2f5a02b47 Mon Sep 17 00:00:00 2001
From: Yan Zhai <yan@cloudflare.com>
Date: Thu, 17 Aug 2023 19:58:14 -0700
Subject: [PATCH 1324/1806] lwt: Check LWTUNNEL_XMIT_CONTINUE strictly

LWTUNNEL_XMIT_CONTINUE is implicitly assumed in ip(6)_finish_output2,
such that any positive return value from a xmit hook could cause
unexpected continue behavior, despite that related skb may have been
freed. This could be error-prone for future xmit hook ops. One of the
possible errors is to return statuses of dst_output directly.

To make the code safer, redefine LWTUNNEL_XMIT_CONTINUE value to
distinguish from dst_output statuses and check the continue
condition explicitly.

Fixes: 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure")
Suggested-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Yan Zhai <yan@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/96b939b85eda00e8df4f7c080f770970a4c5f698.1692326837.git.yan@cloudflare.com
---
 include/net/lwtunnel.h | 5 ++++-
 net/ipv4/ip_output.c   | 2 +-
 net/ipv6/ip6_output.c  | 2 +-
 3 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 6f15e6fa154e6..53bd2d02a4f0d 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -16,9 +16,12 @@
 #define LWTUNNEL_STATE_INPUT_REDIRECT	BIT(1)
 #define LWTUNNEL_STATE_XMIT_REDIRECT	BIT(2)
 
+/* LWTUNNEL_XMIT_CONTINUE should be distinguishable from dst_output return
+ * values (NET_XMIT_xxx and NETDEV_TX_xxx in linux/netdevice.h) for safety.
+ */
 enum {
 	LWTUNNEL_XMIT_DONE,
-	LWTUNNEL_XMIT_CONTINUE,
+	LWTUNNEL_XMIT_CONTINUE = 0x100,
 };
 
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index ce6257860a401..43ba4b77b2484 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -216,7 +216,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
 	if (lwtunnel_xmit_redirect(dst->lwtstate)) {
 		int res = lwtunnel_xmit(skb);
 
-		if (res < 0 || res == LWTUNNEL_XMIT_DONE)
+		if (res != LWTUNNEL_XMIT_CONTINUE)
 			return res;
 	}
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f8a1f6bb3f872..0665e8b099680 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -113,7 +113,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	if (lwtunnel_xmit_redirect(dst->lwtstate)) {
 		int res = lwtunnel_xmit(skb);
 
-		if (res < 0 || res == LWTUNNEL_XMIT_DONE)
+		if (res != LWTUNNEL_XMIT_CONTINUE)
 			return res;
 	}
 
-- 
GitLab


From 43a7c3ef8a15d19ee59214fa1d1c6bab55f9d894 Mon Sep 17 00:00:00 2001
From: Yan Zhai <yan@cloudflare.com>
Date: Thu, 17 Aug 2023 19:58:16 -0700
Subject: [PATCH 1325/1806] selftests/bpf: Add lwt_xmit tests for BPF_REDIRECT

There is no lwt_xmit test case for BPF_REDIRECT yet. Add test cases for
both normal and abnormal situations. For abnormal test cases, devices
are set down or have its carrier set down. Without proper fixes,
BPF_REDIRECT to either ingress or egress of such device would panic the
kernel.

Signed-off-by: Yan Zhai <yan@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/96bf435243641939d9c9da329fab29cb45f7df22.1692326837.git.yan@cloudflare.com
---
 tools/testing/selftests/bpf/config            |   1 +
 .../selftests/bpf/prog_tests/lwt_helpers.h    | 139 ++++++++
 .../selftests/bpf/prog_tests/lwt_redirect.c   | 330 ++++++++++++++++++
 .../selftests/bpf/progs/test_lwt_redirect.c   |  90 +++++
 4 files changed, 560 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
 create mode 100644 tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_lwt_redirect.c

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 3b350bc313430..fa083f1e5b349 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -16,6 +16,7 @@ CONFIG_CRYPTO_USER_API_HASH=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_BTF=y
 CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_DUMMY=y
 CONFIG_DYNAMIC_FTRACE=y
 CONFIG_FPROBE=y
 CONFIG_FTRACE_SYSCALLS=y
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
new file mode 100644
index 0000000000000..61333f2a03f91
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __LWT_HELPERS_H
+#define __LWT_HELPERS_H
+
+#include <time.h>
+#include <net/if.h>
+#include <linux/if_tun.h>
+#include <linux/icmp.h>
+
+#include "test_progs.h"
+
+#define log_err(MSG, ...) \
+	fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
+		__FILE__, __LINE__, strerror(errno), ##__VA_ARGS__)
+
+#define RUN_TEST(name)                                                        \
+	({                                                                    \
+		if (test__start_subtest(#name))                               \
+			if (ASSERT_OK(netns_create(), "netns_create")) {      \
+				struct nstoken *token = open_netns(NETNS);    \
+				if (ASSERT_OK_PTR(token, "setns")) {          \
+					test_ ## name();                      \
+					close_netns(token);                   \
+				}                                             \
+				netns_delete();                               \
+			}                                                     \
+	})
+
+#define NETNS "ns_lwt"
+
+static inline int netns_create(void)
+{
+	return system("ip netns add " NETNS);
+}
+
+static inline int netns_delete(void)
+{
+	return system("ip netns del " NETNS ">/dev/null 2>&1");
+}
+
+static int open_tuntap(const char *dev_name, bool need_mac)
+{
+	int err = 0;
+	struct ifreq ifr;
+	int fd = open("/dev/net/tun", O_RDWR);
+
+	if (!ASSERT_GT(fd, 0, "open(/dev/net/tun)"))
+		return -1;
+
+	ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN);
+	memcpy(ifr.ifr_name, dev_name, IFNAMSIZ);
+
+	err = ioctl(fd, TUNSETIFF, &ifr);
+	if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) {
+		close(fd);
+		return -1;
+	}
+
+	err = fcntl(fd, F_SETFL, O_NONBLOCK);
+	if (!ASSERT_OK(err, "fcntl(O_NONBLOCK)")) {
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+#define ICMP_PAYLOAD_SIZE     100
+
+/* Match an ICMP packet with payload len ICMP_PAYLOAD_SIZE */
+static int __expect_icmp_ipv4(char *buf, ssize_t len)
+{
+	struct iphdr *ip = (struct iphdr *)buf;
+	struct icmphdr *icmp = (struct icmphdr *)(ip + 1);
+	ssize_t min_header_len = sizeof(*ip) + sizeof(*icmp);
+
+	if (len < min_header_len)
+		return -1;
+
+	if (ip->protocol != IPPROTO_ICMP)
+		return -1;
+
+	if (icmp->type != ICMP_ECHO)
+		return -1;
+
+	return len == ICMP_PAYLOAD_SIZE + min_header_len;
+}
+
+typedef int (*filter_t) (char *, ssize_t);
+
+/* wait_for_packet - wait for a packet that matches the filter
+ *
+ * @fd: tun fd/packet socket to read packet
+ * @filter: filter function, returning 1 if matches
+ * @timeout: timeout to wait for the packet
+ *
+ * Returns 1 if a matching packet is read, 0 if timeout expired, -1 on error.
+ */
+static int wait_for_packet(int fd, filter_t filter, struct timeval *timeout)
+{
+	char buf[4096];
+	int max_retry = 5; /* in case we read some spurious packets */
+	fd_set fds;
+
+	FD_ZERO(&fds);
+	while (max_retry--) {
+		/* Linux modifies timeout arg... So make a copy */
+		struct timeval copied_timeout = *timeout;
+		ssize_t ret = -1;
+
+		FD_SET(fd, &fds);
+
+		ret = select(1 + fd, &fds, NULL, NULL, &copied_timeout);
+		if (ret <= 0) {
+			if (errno == EINTR)
+				continue;
+			else if (errno == EAGAIN || ret == 0)
+				return 0;
+
+			log_err("select failed");
+			return -1;
+		}
+
+		ret = read(fd, buf, sizeof(buf));
+
+		if (ret <= 0) {
+			log_err("read(dev): %ld", ret);
+			return -1;
+		}
+
+		if (filter && filter(buf, ret) > 0)
+			return 1;
+	}
+
+	return 0;
+}
+
+#endif /* __LWT_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
new file mode 100644
index 0000000000000..59b38569f310b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
@@ -0,0 +1,330 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/*
+ * Test suite of lwt_xmit BPF programs that redirect packets
+ *   The file tests focus not only if these programs work as expected normally,
+ *   but also if they can handle abnormal situations gracefully.
+ *
+ * WARNING
+ * -------
+ *  This test suite may crash the kernel, thus should be run in a VM.
+ *
+ * Setup:
+ * ---------
+ *  All tests are performed in a single netns. Two lwt encap routes are setup for
+ *  each subtest:
+ *
+ *    ip route add 10.0.0.0/24 encap bpf xmit <obj> sec "<ingress_sec>" dev link_err
+ *    ip route add 20.0.0.0/24 encap bpf xmit <obj> sec "<egress_sec>" dev link_err
+ *
+ *  Here <obj> is statically defined to test_lwt_redirect.bpf.o, and each section
+ *  of this object holds a program entry to test. The BPF object is built from
+ *  progs/test_lwt_redirect.c. We didn't use generated BPF skeleton since the
+ *  attachment for lwt programs are not supported by libbpf yet.
+ *
+ *  For testing, ping commands are run in the test netns:
+ *
+ *    ping 10.0.0.<ifindex> -c 1 -w 1 -s 100
+ *    ping 20.0.0.<ifindex> -c 1 -w 1 -s 100
+ *
+ * Scenarios:
+ * --------------------------------
+ *  1. Redirect to a running tap/tun device
+ *  2. Redirect to a down tap/tun device
+ *  3. Redirect to a vlan device with lower layer down
+ *
+ *  Case 1, ping packets should be received by packet socket on target device
+ *  when redirected to ingress, and by tun/tap fd when redirected to egress.
+ *
+ *  Case 2,3 are considered successful as long as they do not crash the kernel
+ *  as a regression.
+ *
+ *  Case 1,2 use tap device to test redirect to device that requires MAC
+ *  header, and tun device to test the case with no MAC header added.
+ */
+#include <sys/socket.h>
+#include <net/if.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_tun.h>
+#include <linux/icmp.h>
+#include <arpa/inet.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stdbool.h>
+#include <stdlib.h>
+
+#include "lwt_helpers.h"
+#include "test_progs.h"
+#include "network_helpers.h"
+
+#define BPF_OBJECT            "test_lwt_redirect.bpf.o"
+#define INGRESS_SEC(need_mac) ((need_mac) ? "redir_ingress" : "redir_ingress_nomac")
+#define EGRESS_SEC(need_mac)  ((need_mac) ? "redir_egress" : "redir_egress_nomac")
+#define LOCAL_SRC             "10.0.0.1"
+#define CIDR_TO_INGRESS       "10.0.0.0/24"
+#define CIDR_TO_EGRESS        "20.0.0.0/24"
+
+/* ping to redirect toward given dev, with last byte of dest IP being the target
+ * device index.
+ *
+ * Note: ping command inside BPF-CI is busybox version, so it does not have certain
+ * function, such like -m option to set packet mark.
+ */
+static void ping_dev(const char *dev, bool is_ingress)
+{
+	int link_index = if_nametoindex(dev);
+	char ip[256];
+
+	if (!ASSERT_GE(link_index, 0, "if_nametoindex"))
+		return;
+
+	if (is_ingress)
+		snprintf(ip, sizeof(ip), "10.0.0.%d", link_index);
+	else
+		snprintf(ip, sizeof(ip), "20.0.0.%d", link_index);
+
+	/* We won't get a reply. Don't fail here */
+	SYS_NOFAIL("ping %s -c1 -W1 -s %d >/dev/null 2>&1",
+		   ip, ICMP_PAYLOAD_SIZE);
+}
+
+static int new_packet_sock(const char *ifname)
+{
+	int err = 0;
+	int ignore_outgoing = 1;
+	int ifindex = -1;
+	int s = -1;
+
+	s = socket(AF_PACKET, SOCK_RAW, 0);
+	if (!ASSERT_GE(s, 0, "socket(AF_PACKET)"))
+		return -1;
+
+	ifindex = if_nametoindex(ifname);
+	if (!ASSERT_GE(ifindex, 0, "if_nametoindex")) {
+		close(s);
+		return -1;
+	}
+
+	struct sockaddr_ll addr = {
+		.sll_family = AF_PACKET,
+		.sll_protocol = htons(ETH_P_IP),
+		.sll_ifindex = ifindex,
+	};
+
+	err = bind(s, (struct sockaddr *)&addr, sizeof(addr));
+	if (!ASSERT_OK(err, "bind(AF_PACKET)")) {
+		close(s);
+		return -1;
+	}
+
+	/* Use packet socket to capture only the ingress, so we can distinguish
+	 * the case where a regression that actually redirects the packet to
+	 * the egress.
+	 */
+	err = setsockopt(s, SOL_PACKET, PACKET_IGNORE_OUTGOING,
+			 &ignore_outgoing, sizeof(ignore_outgoing));
+	if (!ASSERT_OK(err, "setsockopt(PACKET_IGNORE_OUTGOING)")) {
+		close(s);
+		return -1;
+	}
+
+	err = fcntl(s, F_SETFL, O_NONBLOCK);
+	if (!ASSERT_OK(err, "fcntl(O_NONBLOCK)")) {
+		close(s);
+		return -1;
+	}
+
+	return s;
+}
+
+static int expect_icmp(char *buf, ssize_t len)
+{
+	struct ethhdr *eth = (struct ethhdr *)buf;
+
+	if (len < (ssize_t)sizeof(*eth))
+		return -1;
+
+	if (eth->h_proto == htons(ETH_P_IP))
+		return __expect_icmp_ipv4((char *)(eth + 1), len - sizeof(*eth));
+
+	return -1;
+}
+
+static int expect_icmp_nomac(char *buf, ssize_t len)
+{
+	return __expect_icmp_ipv4(buf, len);
+}
+
+static void send_and_capture_test_packets(const char *test_name, int tap_fd,
+					  const char *target_dev, bool need_mac)
+{
+	int psock = -1;
+	struct timeval timeo = {
+		.tv_sec = 0,
+		.tv_usec = 250000,
+	};
+	int ret = -1;
+
+	filter_t filter = need_mac ? expect_icmp : expect_icmp_nomac;
+
+	ping_dev(target_dev, false);
+
+	ret = wait_for_packet(tap_fd, filter, &timeo);
+	if (!ASSERT_EQ(ret, 1, "wait_for_epacket")) {
+		log_err("%s egress test fails", test_name);
+		goto out;
+	}
+
+	psock = new_packet_sock(target_dev);
+	ping_dev(target_dev, true);
+
+	ret = wait_for_packet(psock, filter, &timeo);
+	if (!ASSERT_EQ(ret, 1, "wait_for_ipacket")) {
+		log_err("%s ingress test fails", test_name);
+		goto out;
+	}
+
+out:
+	if (psock >= 0)
+		close(psock);
+}
+
+static int setup_redirect_target(const char *target_dev, bool need_mac)
+{
+	int target_index = -1;
+	int tap_fd = -1;
+
+	tap_fd = open_tuntap(target_dev, need_mac);
+	if (!ASSERT_GE(tap_fd, 0, "open_tuntap"))
+		goto fail;
+
+	target_index = if_nametoindex(target_dev);
+	if (!ASSERT_GE(target_index, 0, "if_nametoindex"))
+		goto fail;
+
+	SYS(fail, "ip link add link_err type dummy");
+	SYS(fail, "ip link set lo up");
+	SYS(fail, "ip addr add dev lo " LOCAL_SRC "/32");
+	SYS(fail, "ip link set link_err up");
+	SYS(fail, "ip link set %s up", target_dev);
+
+	SYS(fail, "ip route add %s dev link_err encap bpf xmit obj %s sec %s",
+	    CIDR_TO_INGRESS, BPF_OBJECT, INGRESS_SEC(need_mac));
+
+	SYS(fail, "ip route add %s dev link_err encap bpf xmit obj %s sec %s",
+	    CIDR_TO_EGRESS, BPF_OBJECT, EGRESS_SEC(need_mac));
+
+	return tap_fd;
+
+fail:
+	if (tap_fd >= 0)
+		close(tap_fd);
+	return -1;
+}
+
+static void test_lwt_redirect_normal(void)
+{
+	const char *target_dev = "tap0";
+	int tap_fd = -1;
+	bool need_mac = true;
+
+	tap_fd = setup_redirect_target(target_dev, need_mac);
+	if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target"))
+		return;
+
+	send_and_capture_test_packets(__func__, tap_fd, target_dev, need_mac);
+	close(tap_fd);
+}
+
+static void test_lwt_redirect_normal_nomac(void)
+{
+	const char *target_dev = "tun0";
+	int tap_fd = -1;
+	bool need_mac = false;
+
+	tap_fd = setup_redirect_target(target_dev, need_mac);
+	if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target"))
+		return;
+
+	send_and_capture_test_packets(__func__, tap_fd, target_dev, need_mac);
+	close(tap_fd);
+}
+
+/* This test aims to prevent regression of future. As long as the kernel does
+ * not panic, it is considered as success.
+ */
+static void __test_lwt_redirect_dev_down(bool need_mac)
+{
+	const char *target_dev = "tap0";
+	int tap_fd = -1;
+
+	tap_fd = setup_redirect_target(target_dev, need_mac);
+	if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target"))
+		return;
+
+	SYS(out, "ip link set %s down", target_dev);
+	ping_dev(target_dev, true);
+	ping_dev(target_dev, false);
+
+out:
+	close(tap_fd);
+}
+
+static void test_lwt_redirect_dev_down(void)
+{
+	__test_lwt_redirect_dev_down(true);
+}
+
+static void test_lwt_redirect_dev_down_nomac(void)
+{
+	__test_lwt_redirect_dev_down(false);
+}
+
+/* This test aims to prevent regression of future. As long as the kernel does
+ * not panic, it is considered as success.
+ */
+static void test_lwt_redirect_dev_carrier_down(void)
+{
+	const char *lower_dev = "tap0";
+	const char *vlan_dev = "vlan100";
+	int tap_fd = -1;
+
+	tap_fd = setup_redirect_target(lower_dev, true);
+	if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target"))
+		return;
+
+	SYS(out, "ip link add vlan100 link %s type vlan id 100", lower_dev);
+	SYS(out, "ip link set %s up", vlan_dev);
+	SYS(out, "ip link set %s down", lower_dev);
+	ping_dev(vlan_dev, true);
+	ping_dev(vlan_dev, false);
+
+out:
+	close(tap_fd);
+}
+
+static void *test_lwt_redirect_run(void *arg)
+{
+	netns_delete();
+	RUN_TEST(lwt_redirect_normal);
+	RUN_TEST(lwt_redirect_normal_nomac);
+	RUN_TEST(lwt_redirect_dev_down);
+	RUN_TEST(lwt_redirect_dev_down_nomac);
+	RUN_TEST(lwt_redirect_dev_carrier_down);
+	return NULL;
+}
+
+void test_lwt_redirect(void)
+{
+	pthread_t test_thread;
+	int err;
+
+	/* Run the tests in their own thread to isolate the namespace changes
+	 * so they do not affect the environment of other tests.
+	 * (specifically needed because of unshare(CLONE_NEWNS) in open_netns())
+	 */
+	err = pthread_create(&test_thread, NULL, &test_lwt_redirect_run, NULL);
+	if (ASSERT_OK(err, "pthread_create"))
+		ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join");
+}
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_redirect.c b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c
new file mode 100644
index 0000000000000..7ab1fd310efb3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/ip.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tracing_net.h"
+
+/* We don't care about whether the packet can be received by network stack.
+ * Just care if the packet is sent to the correct device at correct direction
+ * and not panic the kernel.
+ */
+static int prepend_dummy_mac(struct __sk_buff *skb)
+{
+	char mac[] = {0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0xf,
+		      0xe, 0xd, 0xc, 0xb, 0xa, 0x08, 0x00};
+
+	if (bpf_skb_change_head(skb, ETH_HLEN, 0))
+		return -1;
+
+	if (bpf_skb_store_bytes(skb, 0, mac, sizeof(mac), 0))
+		return -1;
+
+	return 0;
+}
+
+/* Use the last byte of IP address to redirect the packet */
+static int get_redirect_target(struct __sk_buff *skb)
+{
+	struct iphdr *iph = NULL;
+	void *start = (void *)(long)skb->data;
+	void *end = (void *)(long)skb->data_end;
+
+	if (start + sizeof(*iph) > end)
+		return -1;
+
+	iph = (struct iphdr *)start;
+	return bpf_ntohl(iph->daddr) & 0xff;
+}
+
+SEC("redir_ingress")
+int test_lwt_redirect_in(struct __sk_buff *skb)
+{
+	int target = get_redirect_target(skb);
+
+	if (target < 0)
+		return BPF_OK;
+
+	if (prepend_dummy_mac(skb))
+		return BPF_DROP;
+
+	return bpf_redirect(target, BPF_F_INGRESS);
+}
+
+SEC("redir_egress")
+int test_lwt_redirect_out(struct __sk_buff *skb)
+{
+	int target = get_redirect_target(skb);
+
+	if (target < 0)
+		return BPF_OK;
+
+	if (prepend_dummy_mac(skb))
+		return BPF_DROP;
+
+	return bpf_redirect(target, 0);
+}
+
+SEC("redir_egress_nomac")
+int test_lwt_redirect_out_nomac(struct __sk_buff *skb)
+{
+	int target = get_redirect_target(skb);
+
+	if (target < 0)
+		return BPF_OK;
+
+	return bpf_redirect(target, 0);
+}
+
+SEC("redir_ingress_nomac")
+int test_lwt_redirect_in_nomac(struct __sk_buff *skb)
+{
+	int target = get_redirect_target(skb);
+
+	if (target < 0)
+		return BPF_OK;
+
+	return bpf_redirect(target, BPF_F_INGRESS);
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From 6c77997bc63982ab718662fee0bff6756d3116bc Mon Sep 17 00:00:00 2001
From: Yan Zhai <yan@cloudflare.com>
Date: Thu, 17 Aug 2023 19:58:18 -0700
Subject: [PATCH 1326/1806] selftests/bpf: Add lwt_xmit tests for BPF_REROUTE

There is no lwt test case for BPF_REROUTE yet. Add test cases for both
normal and abnormal situations. The abnormal situation is set up with an
fq qdisc on the reroute target device. Without proper fixes, overflow
this qdisc queue limit (to trigger a drop) would panic the kernel.

Signed-off-by: Yan Zhai <yan@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/62c8ddc1e924269dcf80d2e8af1a1e632cee0b3a.1692326837.git.yan@cloudflare.com
---
 tools/testing/selftests/bpf/config            |   1 +
 .../selftests/bpf/prog_tests/lwt_reroute.c    | 262 ++++++++++++++++++
 .../selftests/bpf/progs/test_lwt_reroute.c    |  36 +++
 3 files changed, 299 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_lwt_reroute.c

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index fa083f1e5b349..1c7584e8dd9ea 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -60,6 +60,7 @@ CONFIG_NET_IPGRE=y
 CONFIG_NET_IPGRE_DEMUX=y
 CONFIG_NET_IPIP=y
 CONFIG_NET_MPLS_GSO=y
+CONFIG_NET_SCH_FQ=y
 CONFIG_NET_SCH_INGRESS=y
 CONFIG_NET_SCHED=y
 CONFIG_NETDEVSIM=y
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
new file mode 100644
index 0000000000000..f4bb2d5fcae0a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
@@ -0,0 +1,262 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/*
+ * Test suite of lwt BPF programs that reroutes packets
+ *   The file tests focus not only if these programs work as expected normally,
+ *   but also if they can handle abnormal situations gracefully. This test
+ *   suite currently only covers lwt_xmit hook. lwt_in tests have not been
+ *   implemented.
+ *
+ * WARNING
+ * -------
+ *  This test suite can crash the kernel, thus should be run in a VM.
+ *
+ * Setup:
+ * ---------
+ *  all tests are performed in a single netns. A lwt encap route is setup for
+ *  each subtest:
+ *
+ *    ip route add 10.0.0.0/24 encap bpf xmit <obj> sec "<section_N>" dev link_err
+ *
+ *  Here <obj> is statically defined to test_lwt_reroute.bpf.o, and it contains
+ *  a single test program entry. This program sets packet mark by last byte of
+ *  the IPv4 daddr. For example, a packet going to 1.2.3.4 will receive a skb
+ *  mark 4. A packet will only be marked once, and IP x.x.x.0 will be skipped
+ *  to avoid route loop. We didn't use generated BPF skeleton since the
+ *  attachment for lwt programs are not supported by libbpf yet.
+ *
+ *  The test program will bring up a tun device, and sets up the following
+ *  routes:
+ *
+ *    ip rule add pref 100 from all fwmark <tun_index> lookup 100
+ *    ip route add table 100 default dev tun0
+ *
+ *  For normal testing, a ping command is running in the test netns:
+ *
+ *    ping 10.0.0.<tun_index> -c 1 -w 1 -s 100
+ *
+ *  For abnormal testing, fq is used as the qdisc of the tun device. Then a UDP
+ *  socket will try to overflow the fq queue and trigger qdisc drop error.
+ *
+ * Scenarios:
+ * --------------------------------
+ *  1. Reroute to a running tun device
+ *  2. Reroute to a device where qdisc drop
+ *
+ *  For case 1, ping packets should be received by the tun device.
+ *
+ *  For case 2, force UDP packets to overflow fq limit. As long as kernel
+ *  is not crashed, it is considered successful.
+ */
+#include "lwt_helpers.h"
+#include "network_helpers.h"
+#include <linux/net_tstamp.h>
+
+#define BPF_OBJECT            "test_lwt_reroute.bpf.o"
+#define LOCAL_SRC             "10.0.0.1"
+#define TEST_CIDR             "10.0.0.0/24"
+#define XMIT_HOOK             "xmit"
+#define XMIT_SECTION          "lwt_xmit"
+#define NSEC_PER_SEC          1000000000ULL
+
+/* send a ping to be rerouted to the target device */
+static void ping_once(const char *ip)
+{
+	/* We won't get a reply. Don't fail here */
+	SYS_NOFAIL("ping %s -c1 -W1 -s %d >/dev/null 2>&1",
+		   ip, ICMP_PAYLOAD_SIZE);
+}
+
+/* Send snd_target UDP packets to overflow the fq queue and trigger qdisc drop
+ * error. This is done via TX tstamp to force buffering delayed packets.
+ */
+static int overflow_fq(int snd_target, const char *target_ip)
+{
+	struct sockaddr_in addr = {
+		.sin_family = AF_INET,
+		.sin_port = htons(1234),
+	};
+
+	char data_buf[8]; /* only #pkts matter, so use a random small buffer */
+	char control_buf[CMSG_SPACE(sizeof(uint64_t))];
+	struct iovec iov = {
+		.iov_base = data_buf,
+		.iov_len = sizeof(data_buf),
+	};
+	int err = -1;
+	int s = -1;
+	struct sock_txtime txtime_on = {
+		.clockid = CLOCK_MONOTONIC,
+		.flags = 0,
+	};
+	struct msghdr msg = {
+		.msg_name = &addr,
+		.msg_namelen = sizeof(addr),
+		.msg_control = control_buf,
+		.msg_controllen = sizeof(control_buf),
+		.msg_iovlen = 1,
+		.msg_iov = &iov,
+	};
+	struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+
+	memset(data_buf, 0, sizeof(data_buf));
+
+	s = socket(AF_INET, SOCK_DGRAM, 0);
+	if (!ASSERT_GE(s, 0, "socket"))
+		goto out;
+
+	err = setsockopt(s, SOL_SOCKET, SO_TXTIME, &txtime_on, sizeof(txtime_on));
+	if (!ASSERT_OK(err, "setsockopt(SO_TXTIME)"))
+		goto out;
+
+	err = inet_pton(AF_INET, target_ip, &addr.sin_addr);
+	if (!ASSERT_EQ(err, 1, "inet_pton"))
+		goto out;
+
+	while (snd_target > 0) {
+		struct timespec now;
+
+		memset(control_buf, 0, sizeof(control_buf));
+		cmsg->cmsg_type = SCM_TXTIME;
+		cmsg->cmsg_level = SOL_SOCKET;
+		cmsg->cmsg_len = CMSG_LEN(sizeof(uint64_t));
+
+		err = clock_gettime(CLOCK_MONOTONIC, &now);
+		if (!ASSERT_OK(err, "clock_gettime(CLOCK_MONOTONIC)")) {
+			err = -1;
+			goto out;
+		}
+
+		*(uint64_t *)CMSG_DATA(cmsg) = (now.tv_nsec + 1) * NSEC_PER_SEC +
+					       now.tv_nsec;
+
+		/* we will intentionally send more than fq limit, so ignore
+		 * the error here.
+		 */
+		sendmsg(s, &msg, MSG_NOSIGNAL);
+		snd_target--;
+	}
+
+	/* no kernel crash so far is considered success */
+	err = 0;
+
+out:
+	if (s >= 0)
+		close(s);
+
+	return err;
+}
+
+static int setup(const char *tun_dev)
+{
+	int target_index = -1;
+	int tap_fd = -1;
+
+	tap_fd = open_tuntap(tun_dev, false);
+	if (!ASSERT_GE(tap_fd, 0, "open_tun"))
+		return -1;
+
+	target_index = if_nametoindex(tun_dev);
+	if (!ASSERT_GE(target_index, 0, "if_nametoindex"))
+		return -1;
+
+	SYS(fail, "ip link add link_err type dummy");
+	SYS(fail, "ip link set lo up");
+	SYS(fail, "ip addr add dev lo " LOCAL_SRC "/32");
+	SYS(fail, "ip link set link_err up");
+	SYS(fail, "ip link set %s up", tun_dev);
+
+	SYS(fail, "ip route add %s dev link_err encap bpf xmit obj %s sec lwt_xmit",
+	    TEST_CIDR, BPF_OBJECT);
+
+	SYS(fail, "ip rule add pref 100 from all fwmark %d lookup 100",
+	    target_index);
+	SYS(fail, "ip route add t 100 default dev %s", tun_dev);
+
+	return tap_fd;
+
+fail:
+	if (tap_fd >= 0)
+		close(tap_fd);
+	return -1;
+}
+
+static void test_lwt_reroute_normal_xmit(void)
+{
+	const char *tun_dev = "tun0";
+	int tun_fd = -1;
+	int ifindex = -1;
+	char ip[256];
+	struct timeval timeo = {
+		.tv_sec = 0,
+		.tv_usec = 250000,
+	};
+
+	tun_fd = setup(tun_dev);
+	if (!ASSERT_GE(tun_fd, 0, "setup_reroute"))
+		return;
+
+	ifindex = if_nametoindex(tun_dev);
+	if (!ASSERT_GE(ifindex, 0, "if_nametoindex"))
+		return;
+
+	snprintf(ip, 256, "10.0.0.%d", ifindex);
+
+	/* ping packets should be received by the tun device */
+	ping_once(ip);
+
+	if (!ASSERT_EQ(wait_for_packet(tun_fd, __expect_icmp_ipv4, &timeo), 1,
+		       "wait_for_packet"))
+		log_err("%s xmit", __func__);
+}
+
+/*
+ * Test the failure case when the skb is dropped at the qdisc. This is a
+ * regression prevention at the xmit hook only.
+ */
+static void test_lwt_reroute_qdisc_dropped(void)
+{
+	const char *tun_dev = "tun0";
+	int tun_fd = -1;
+	int ifindex = -1;
+	char ip[256];
+
+	tun_fd = setup(tun_dev);
+	if (!ASSERT_GE(tun_fd, 0, "setup_reroute"))
+		goto fail;
+
+	SYS(fail, "tc qdisc replace dev %s root fq limit 5 flow_limit 5", tun_dev);
+
+	ifindex = if_nametoindex(tun_dev);
+	if (!ASSERT_GE(ifindex, 0, "if_nametoindex"))
+		return;
+
+	snprintf(ip, 256, "10.0.0.%d", ifindex);
+	ASSERT_EQ(overflow_fq(10, ip), 0, "overflow_fq");
+
+fail:
+	if (tun_fd >= 0)
+		close(tun_fd);
+}
+
+static void *test_lwt_reroute_run(void *arg)
+{
+	netns_delete();
+	RUN_TEST(lwt_reroute_normal_xmit);
+	RUN_TEST(lwt_reroute_qdisc_dropped);
+	return NULL;
+}
+
+void test_lwt_reroute(void)
+{
+	pthread_t test_thread;
+	int err;
+
+	/* Run the tests in their own thread to isolate the namespace changes
+	 * so they do not affect the environment of other tests.
+	 * (specifically needed because of unshare(CLONE_NEWNS) in open_netns())
+	 */
+	err = pthread_create(&test_thread, NULL, &test_lwt_reroute_run, NULL);
+	if (ASSERT_OK(err, "pthread_create"))
+		ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join");
+}
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_reroute.c b/tools/testing/selftests/bpf/progs/test_lwt_reroute.c
new file mode 100644
index 0000000000000..1dc64351929c0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_lwt_reroute.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+
+/* This function extracts the last byte of the daddr, and uses it
+ * as output dev index.
+ */
+SEC("lwt_xmit")
+int test_lwt_reroute(struct __sk_buff *skb)
+{
+	struct iphdr *iph = NULL;
+	void *start = (void *)(long)skb->data;
+	void *end = (void *)(long)skb->data_end;
+
+	/* set mark at most once */
+	if (skb->mark != 0)
+		return BPF_OK;
+
+	if (start + sizeof(*iph) > end)
+		return BPF_DROP;
+
+	iph = (struct iphdr *)start;
+	skb->mark = bpf_ntohl(iph->daddr) & 0xff;
+
+	/* do not reroute x.x.x.0 packets */
+	if (skb->mark == 0)
+		return BPF_OK;
+
+	return BPF_LWT_REROUTE;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From b6594a17ecce03ca70a3f36783924635eea5499d Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Fri, 18 Aug 2023 00:02:40 +0200
Subject: [PATCH 1327/1806] bpf/tests: Enhance output on error and fix typos

If a testcase returns a wrong (unexpected) value, print the expected and
returned value in hex notation in addition to the decimal notation.

This is very useful in tests which bit-shift hex values left or right and
helped me a lot while developing the JIT compiler for the hppa architecture.

Additionally fix two typos: dowrd -> dword, tall calls -> tail calls.

Signed-off-by: Helge Deller <deller@gmx.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/ZN6ZAAVoWZpsD1Jf@p100
---
 lib/test_bpf.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 913a7a079239e..ecde4216201e4 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -596,8 +596,8 @@ static int __bpf_fill_alu_shift(struct bpf_test *self, u8 op,
 {
 	static const s64 regs[] = {
 		0x0123456789abcdefLL, /* dword > 0, word < 0 */
-		0xfedcba9876543210LL, /* dowrd < 0, word > 0 */
-		0xfedcba0198765432LL, /* dowrd < 0, word < 0 */
+		0xfedcba9876543210LL, /* dword < 0, word > 0 */
+		0xfedcba0198765432LL, /* dword < 0, word < 0 */
 		0x0123458967abcdefLL, /* dword > 0, word > 0 */
 	};
 	int bits = alu32 ? 32 : 64;
@@ -14567,8 +14567,10 @@ static int run_one(const struct bpf_prog *fp, struct bpf_test *test)
 		if (ret == test->test[i].result) {
 			pr_cont("%lld ", duration);
 		} else {
-			pr_cont("ret %d != %d ", ret,
-				test->test[i].result);
+			s32 res = test->test[i].result;
+
+			pr_cont("ret %d != %d (%#x != %#x)",
+				ret, res, ret, res);
 			err_cnt++;
 		}
 	}
@@ -15045,7 +15047,7 @@ static __init int prepare_tail_call_tests(struct bpf_array **pprogs)
 	struct bpf_array *progs;
 	int which, err;
 
-	/* Allocate the table of programs to be used for tall calls */
+	/* Allocate the table of programs to be used for tail calls */
 	progs = kzalloc(struct_size(progs, ptrs, ntests + 1), GFP_KERNEL);
 	if (!progs)
 		goto out_nomem;
-- 
GitLab


From 5964a223f5e47a593c6ada9b9c54b61f04ac0a3b Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Thu, 17 Aug 2023 15:53:52 -0700
Subject: [PATCH 1328/1806] libbpf: Support triple-underscore flavors for kfunc
 relocation

The function signature of kfuncs can change at any time due to their
intentional lack of stability guarantees. As kfuncs become more widely
used, BPF program writers will need facilities to support calling
different versions of a kfunc from a single BPF object. Consider this
simplified example based on a real scenario we ran into at Meta:

  /* initial kfunc signature */
  int some_kfunc(void *ptr)

  /* Oops, we need to add some flag to modify behavior. No problem,
    change the kfunc. flags = 0 retains original behavior */
  int some_kfunc(void *ptr, long flags)

If the initial version of the kfunc is deployed on some portion of the
fleet and the new version on the rest, a fleetwide service that uses
some_kfunc will currently need to load different BPF programs depending
on which some_kfunc is available.

Luckily CO-RE provides a facility to solve a very similar problem,
struct definition changes, by allowing program writers to declare
my_struct___old and my_struct___new, with ___suffix being considered a
'flavor' of the non-suffixed name and being ignored by
bpf_core_type_exists and similar calls.

This patch extends the 'flavor' facility to the kfunc extern
relocation process. BPF program writers can now declare

  extern int some_kfunc___old(void *ptr)
  extern int some_kfunc___new(void *ptr, int flags)

then test which version of the kfunc exists with bpf_ksym_exists.
Relocation and verifier's dead code elimination will work in concert as
expected, allowing this pattern:

  if (bpf_ksym_exists(some_kfunc___old))
    some_kfunc___old(ptr);
  else
    some_kfunc___new(ptr, 0);

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: David Vernet <void@manifault.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20230817225353.2570845-1-davemarchevsky@fb.com
---
 tools/lib/bpf/libbpf.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index b14a4376a86e6..2178b28878e2b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -550,6 +550,7 @@ struct extern_desc {
 	int btf_id;
 	int sec_btf_id;
 	const char *name;
+	char *essent_name;
 	bool is_set;
 	bool is_weak;
 	union {
@@ -3770,6 +3771,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 	struct extern_desc *ext;
 	int i, n, off, dummy_var_btf_id;
 	const char *ext_name, *sec_name;
+	size_t ext_essent_len;
 	Elf_Scn *scn;
 	Elf64_Shdr *sh;
 
@@ -3819,6 +3821,14 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 		ext->sym_idx = i;
 		ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK;
 
+		ext_essent_len = bpf_core_essential_name_len(ext->name);
+		ext->essent_name = NULL;
+		if (ext_essent_len != strlen(ext->name)) {
+			ext->essent_name = strndup(ext->name, ext_essent_len);
+			if (!ext->essent_name)
+				return -ENOMEM;
+		}
+
 		ext->sec_btf_id = find_extern_sec_btf_id(obj->btf, ext->btf_id);
 		if (ext->sec_btf_id <= 0) {
 			pr_warn("failed to find BTF for extern '%s' [%d] section: %d\n",
@@ -7624,7 +7634,8 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
 
 	local_func_proto_id = ext->ksym.type_id;
 
-	kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC, &kern_btf, &mod_btf);
+	kfunc_id = find_ksym_btf_id(obj, ext->essent_name ?: ext->name, BTF_KIND_FUNC, &kern_btf,
+				    &mod_btf);
 	if (kfunc_id < 0) {
 		if (kfunc_id == -ESRCH && ext->is_weak)
 			return 0;
@@ -7639,6 +7650,9 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
 	ret = bpf_core_types_are_compat(obj->btf, local_func_proto_id,
 					kern_btf, kfunc_proto_id);
 	if (ret <= 0) {
+		if (ext->is_weak)
+			return 0;
+
 		pr_warn("extern (func ksym) '%s': func_proto [%d] incompatible with %s [%d]\n",
 			ext->name, local_func_proto_id,
 			mod_btf ? mod_btf->name : "vmlinux", kfunc_proto_id);
@@ -8370,6 +8384,10 @@ void bpf_object__close(struct bpf_object *obj)
 
 	zfree(&obj->btf_custom_path);
 	zfree(&obj->kconfig);
+
+	for (i = 0; i < obj->nr_extern; i++)
+		zfree(&obj->externs[i].essent_name);
+
 	zfree(&obj->externs);
 	obj->nr_extern = 0;
 
-- 
GitLab


From 63ae8eb2c5b1388eeda39bc95e89e4ad906fa336 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Thu, 17 Aug 2023 15:53:53 -0700
Subject: [PATCH 1329/1806] selftests/bpf: Add CO-RE relocs kfunc flavors tests

This patch adds selftests that exercise kfunc flavor relocation
functionality added in the previous patch. The actual kfunc defined
in kernel/bpf/helpers.c is:

  struct task_struct *bpf_task_acquire(struct task_struct *p)

The following relocation behaviors are checked:

  struct task_struct *bpf_task_acquire___one(struct task_struct *name)
    * Should succeed despite differing param name

  struct task_struct *bpf_task_acquire___two(struct task_struct *p, void *ctx)
    * Should fail because there is no two-param bpf_task_acquire

  struct task_struct *bpf_task_acquire___three(void *ctx)
    * Should fail because, despite vmlinux's bpf_task_acquire having one param,
      the types don't match

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/bpf/20230817225353.2570845-2-davemarchevsky@fb.com
---
 .../selftests/bpf/prog_tests/task_kfunc.c     |  2 +
 .../selftests/bpf/progs/task_kfunc_success.c  | 51 +++++++++++++++++++
 2 files changed, 53 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c
index 740d5f644b407..d4579f735398c 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c
@@ -79,6 +79,8 @@ static const char * const success_tests[] = {
 	"test_task_from_pid_current",
 	"test_task_from_pid_invalid",
 	"task_kfunc_acquire_trusted_walked",
+	"test_task_kfunc_flavor_relo",
+	"test_task_kfunc_flavor_relo_not_found",
 };
 
 void test_task_kfunc(void)
diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_success.c b/tools/testing/selftests/bpf/progs/task_kfunc_success.c
index b09371bba204f..70df695312dc5 100644
--- a/tools/testing/selftests/bpf/progs/task_kfunc_success.c
+++ b/tools/testing/selftests/bpf/progs/task_kfunc_success.c
@@ -18,6 +18,13 @@ int err, pid;
  */
 
 struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym __weak;
+
+struct task_struct *bpf_task_acquire___one(struct task_struct *task) __ksym __weak;
+/* The two-param bpf_task_acquire doesn't exist */
+struct task_struct *bpf_task_acquire___two(struct task_struct *p, void *ctx) __ksym __weak;
+/* Incorrect type for first param */
+struct task_struct *bpf_task_acquire___three(void *ctx) __ksym __weak;
+
 void invalid_kfunc(void) __ksym __weak;
 void bpf_testmod_test_mod_kfunc(int i) __ksym __weak;
 
@@ -55,6 +62,50 @@ static int test_acquire_release(struct task_struct *task)
 	return 0;
 }
 
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_task_kfunc_flavor_relo, struct task_struct *task, u64 clone_flags)
+{
+	struct task_struct *acquired = NULL;
+	int fake_ctx = 42;
+
+	if (bpf_ksym_exists(bpf_task_acquire___one)) {
+		acquired = bpf_task_acquire___one(task);
+	} else if (bpf_ksym_exists(bpf_task_acquire___two)) {
+		/* Here, bpf_object__resolve_ksym_func_btf_id's find_ksym_btf_id
+		 * call will find vmlinux's bpf_task_acquire, but subsequent
+		 * bpf_core_types_are_compat will fail
+		 */
+		acquired = bpf_task_acquire___two(task, &fake_ctx);
+		err = 3;
+		return 0;
+	} else if (bpf_ksym_exists(bpf_task_acquire___three)) {
+		/* bpf_core_types_are_compat will fail similarly to above case */
+		acquired = bpf_task_acquire___three(&fake_ctx);
+		err = 4;
+		return 0;
+	}
+
+	if (acquired)
+		bpf_task_release(acquired);
+	else
+		err = 5;
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_task_kfunc_flavor_relo_not_found, struct task_struct *task, u64 clone_flags)
+{
+	/* Neither symbol should successfully resolve.
+	 * Success or failure of one ___flavor should not affect others
+	 */
+	if (bpf_ksym_exists(bpf_task_acquire___two))
+		err = 1;
+	else if (bpf_ksym_exists(bpf_task_acquire___three))
+		err = 2;
+
+	return 0;
+}
+
 SEC("tp_btf/task_newtask")
 int BPF_PROG(test_task_acquire_release_argument, struct task_struct *task, u64 clone_flags)
 {
-- 
GitLab


From 0a55264cf966fb95ebf9d03d9f81fa992f069312 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Fri, 18 Aug 2023 10:43:12 -0700
Subject: [PATCH 1330/1806] selftests/bpf: Fix a selftest compilation error

When building the kernel and selftest with clang compiler (llvm17 or llvm18),
I hit the following compilation failure:
  In file included from progs/test_lwt_redirect.c:3:
  In file included from /usr/include/linux/ip.h:21:
  In file included from /usr/include/asm/byteorder.h:5:
  In file included from /usr/include/linux/byteorder/little_endian.h:13:
  /usr/include/linux/swab.h:136:8: error: unknown type name '__always_inline'
    136 | static __always_inline unsigned long __swab(const unsigned long y)
        |        ^
  /usr/include/linux/swab.h:171:8: error: unknown type name '__always_inline'
    171 | static __always_inline __u16 __swab16p(const __u16 *p)
  ...

bpf_helpers.h file provided a definition for __always_inline.
Putting 'ip.h' after 'bpf_helpers.h' fixed the issue.

Fixes: 43a7c3ef8a15 ("selftests/bpf: Add lwt_xmit tests for BPF_REDIRECT")
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230818174312.1883381-1-yonghong.song@linux.dev
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/progs/test_lwt_redirect.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/test_lwt_redirect.c b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c
index 7ab1fd310efb3..8c895122f2936 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
-#include <linux/ip.h>
 #include <bpf/bpf_endian.h>
 #include <bpf/bpf_helpers.h>
+#include <linux/ip.h>
 #include "bpf_tracing_net.h"
 
 /* We don't care about whether the packet can be received by network stack.
-- 
GitLab


From 0a0643164da4a1976455aa12f0a96d08ee290752 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <hawk@kernel.org>
Date: Tue, 15 Aug 2023 17:17:36 +0200
Subject: [PATCH 1331/1806] net: use SLAB_NO_MERGE for kmem_cache
 skbuff_head_cache

Since v6.5-rc1 MM-tree is merged and contains a new flag SLAB_NO_MERGE
in commit d0bf7d5759c1 ("mm/slab: introduce kmem_cache flag SLAB_NO_MERGE")
now is the time to use this flag for networking as proposed
earlier see link.

The SKB (sk_buff) kmem_cache slab is critical for network performance.
Network stack uses kmem_cache_{alloc,free}_bulk APIs to gain
performance by amortising the alloc/free cost.

For the bulk API to perform efficiently the slub fragmentation need to
be low. Especially for the SLUB allocator, the efficiency of bulk free
API depend on objects belonging to the same slab (page).

When running different network performance microbenchmarks, I started
to notice that performance was reduced (slightly) when machines had
longer uptimes. I believe the cause was 'skbuff_head_cache' got
aliased/merged into the general slub for 256 bytes sized objects (with
my kernel config, without CONFIG_HARDENED_USERCOPY).

For SKB kmem_cache network stack have other various reasons for
not merging, but it varies depending on kernel config (e.g.
CONFIG_HARDENED_USERCOPY). We want to explicitly set SLAB_NO_MERGE
for this kmem_cache to get most out of kmem_cache_{alloc,free}_bulk APIs.

When CONFIG_SLUB_TINY is configured the bulk APIs are essentially
disabled. Thus, for this case drop the SLAB_NO_MERGE flag.

Link: https://lore.kernel.org/all/167396280045.539803.7540459812377220500.stgit@firesoul/
Signed-off-by: Jesper Dangaard Brouer <hawk@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/169211265663.1491038.8580163757548985946.stgit@firesoul
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skbuff.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 33fdf04d4334d..9b5bc621daf74 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4795,12 +4795,23 @@ static void skb_extensions_init(void)
 static void skb_extensions_init(void) {}
 #endif
 
+/* The SKB kmem_cache slab is critical for network performance.  Never
+ * merge/alias the slab with similar sized objects.  This avoids fragmentation
+ * that hurts performance of kmem_cache_{alloc,free}_bulk APIs.
+ */
+#ifndef CONFIG_SLUB_TINY
+#define FLAG_SKB_NO_MERGE	SLAB_NO_MERGE
+#else /* CONFIG_SLUB_TINY - simple loop in kmem_cache_alloc_bulk */
+#define FLAG_SKB_NO_MERGE	0
+#endif
+
 void __init skb_init(void)
 {
 	skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache",
 					      sizeof(struct sk_buff),
 					      0,
-					      SLAB_HWCACHE_ALIGN|SLAB_PANIC,
+					      SLAB_HWCACHE_ALIGN|SLAB_PANIC|
+						FLAG_SKB_NO_MERGE,
 					      offsetof(struct sk_buff, cb),
 					      sizeof_field(struct sk_buff, cb),
 					      NULL);
-- 
GitLab


From 5cce781484cec087de22f730278eed7a3388f962 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Wed, 16 Aug 2023 08:49:44 +0800
Subject: [PATCH 1332/1806] sfc: Remove unneeded semicolon

./drivers/net/ethernet/sfc/tc_conntrack.c:464:2-3: Unneeded semicolon

Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Acked-by: Martin Habets <habetsm.xilinx@gmail.com>
Link: https://lore.kernel.org/r/20230816004944.10841-1-yang.lee@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/tc_conntrack.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/tc_conntrack.c b/drivers/net/ethernet/sfc/tc_conntrack.c
index 54ed288543d03..8e06bfbcbea17 100644
--- a/drivers/net/ethernet/sfc/tc_conntrack.c
+++ b/drivers/net/ethernet/sfc/tc_conntrack.c
@@ -461,7 +461,7 @@ static int efx_tc_flow_block(enum tc_setup_type type, void *type_data,
 		return efx_tc_ct_stats(ct_zone, tcb);
 	default:
 		break;
-	};
+	}
 
 	return -EOPNOTSUPP;
 }
-- 
GitLab


From 91a10efc89dc510edf57cb1d3a7ad480ef5160b8 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Wed, 16 Aug 2023 17:02:42 +0800
Subject: [PATCH 1333/1806] net: fec: use napi_consume_skb() in
 fec_enet_tx_queue()

Now that the "budget" is passed into fec_enet_tx_queue(), one
optimization we can do is to use napi_consume_skb() to instead
of dev_kfree_skb_any().

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Suggested-by: Alexander H Duyck <alexander.duyck@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230816090242.463822-1-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index f77105f017c1e..e23a559771839 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1494,7 +1494,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 			}
 
 			/* Free the sk buffer associated with this last transmit */
-			dev_kfree_skb_any(skb);
+			napi_consume_skb(skb, budget);
 		} else if (txq->tx_buf[index].type == FEC_TXBUF_T_XDP_NDO) {
 			xdp_return_frame_rx_napi(xdpf);
 		} else { /* recycle pages of XDP_TX frames */
-- 
GitLab


From 2f48b1d854e853b243fcd7e4f3f11d6ab5431bd7 Mon Sep 17 00:00:00 2001
From: Yu Liao <liaoyu15@huawei.com>
Date: Thu, 17 Aug 2023 10:57:09 +0800
Subject: [PATCH 1334/1806] pds_core: remove redundant pci_clear_master()

do_pci_disable_device() disable PCI bus-mastering as following:
static void do_pci_disable_device(struct pci_dev *dev)
{
		u16 pci_command;

		pci_read_config_word(dev, PCI_COMMAND, &pci_command);
		if (pci_command & PCI_COMMAND_MASTER) {
				pci_command &= ~PCI_COMMAND_MASTER;
				pci_write_config_word(dev, PCI_COMMAND, pci_command);
		}

		pcibios_disable_device(dev);
}
And pci_disable_device() sets dev->is_busmaster to 0.

pci_enable_device() is called only once before calling to
pci_disable_device() and such pci_clear_master() is not needed. So remove
redundant pci_clear_master().

Also rename goto label 'err_out_clear_master' to 'err_out_disable_device'.

Signed-off-by: Yu Liao <liaoyu15@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20230817025709.2023553-1-liaoyu15@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/main.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 6727579322469..3a45bf474a19a 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -367,14 +367,13 @@ static int pdsc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		err = pdsc_init_vf(pdsc);
 	if (err) {
 		dev_err(dev, "Cannot init device: %pe\n", ERR_PTR(err));
-		goto err_out_clear_master;
+		goto err_out_disable_device;
 	}
 
 	clear_bit(PDSC_S_INITING_DRIVER, &pdsc->state);
 	return 0;
 
-err_out_clear_master:
-	pci_clear_master(pdev);
+err_out_disable_device:
 	pci_disable_device(pdev);
 err_out_free_ida:
 	ida_free(&pdsc_ida, pdsc->uid);
@@ -439,7 +438,6 @@ static void pdsc_remove(struct pci_dev *pdev)
 		pci_release_regions(pdev);
 	}
 
-	pci_clear_master(pdev);
 	pci_disable_device(pdev);
 
 	ida_free(&pdsc_ida, pdsc->uid);
-- 
GitLab


From ee09e9deefac842a66cbbd39fd2f03aff6e2a656 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Thu, 17 Aug 2023 15:30:17 +0800
Subject: [PATCH 1335/1806] sky2: Remove redundant NULL check for
 debugfs_create_dir

Since debugfs_create_dir() returns ERR_PTR, IS_ERR() is enough to
check whether the directory is successfully created. So remove the
redundant NULL check.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230817073017.350002-1-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/sky2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index c4cca27fb0d53..07720841a8d70 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4528,7 +4528,7 @@ static __init void sky2_debug_init(void)
 	struct dentry *ent;
 
 	ent = debugfs_create_dir("sky2", NULL);
-	if (!ent || IS_ERR(ent))
+	if (IS_ERR(ent))
 		return;
 
 	sky2_debug = ent;
-- 
GitLab


From 829b3357dd9737d45b3724b5378adf8cf8334ea1 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Thu, 17 Aug 2023 10:24:18 +0800
Subject: [PATCH 1336/1806] net: dm9051: Use PTR_ERR_OR_ZERO() to simplify code

Return PTR_ERR_OR_ZERO() instead of return 0 or PTR_ERR() to
simplify code.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230817022418.3588831-1-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/davicom/dm9051.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/davicom/dm9051.c b/drivers/net/ethernet/davicom/dm9051.c
index 70728b2e5f18c..2caaf1e9f42fb 100644
--- a/drivers/net/ethernet/davicom/dm9051.c
+++ b/drivers/net/ethernet/davicom/dm9051.c
@@ -510,10 +510,7 @@ static int dm9051_map_init(struct spi_device *spi, struct board_info *db)
 
 	regconfigdmbulk.lock_arg = db;
 	db->regmap_dmbulk = devm_regmap_init_spi(db->spidev, &regconfigdmbulk);
-	if (IS_ERR(db->regmap_dmbulk))
-		return PTR_ERR(db->regmap_dmbulk);
-
-	return 0;
+	return PTR_ERR_OR_ZERO(db->regmap_dmbulk);
 }
 
 static int dm9051_map_chipid(struct board_info *db)
-- 
GitLab


From 86b05508f7759f41b530c6fec8858124745eada4 Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Thu, 17 Aug 2023 16:19:06 -0700
Subject: [PATCH 1337/1806] bnxt_en: Use the unified RX page pool buffers for
 XDP and non-XDP

Convert to use the page pool buffers for the aggregation ring when
running in non-XDP mode.  This simplifies the driver and we benefit
from the recycling of pages.  Adjust the page pool size to account
for the aggregation ring size.

Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20230817231911.165035-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 71 +++++------------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  3 -
 2 files changed, 14 insertions(+), 60 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7be917a8da482..6b815a2288e29 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -877,48 +877,15 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 	struct rx_bd *rxbd =
 		&rxr->rx_agg_desc_ring[RX_RING(prod)][RX_IDX(prod)];
 	struct bnxt_sw_rx_agg_bd *rx_agg_buf;
-	struct pci_dev *pdev = bp->pdev;
 	struct page *page;
 	dma_addr_t mapping;
 	u16 sw_prod = rxr->rx_sw_agg_prod;
 	unsigned int offset = 0;
 
-	if (BNXT_RX_PAGE_MODE(bp)) {
-		page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp);
-
-		if (!page)
-			return -ENOMEM;
-
-	} else {
-		if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) {
-			page = rxr->rx_page;
-			if (!page) {
-				page = alloc_page(gfp);
-				if (!page)
-					return -ENOMEM;
-				rxr->rx_page = page;
-				rxr->rx_page_offset = 0;
-			}
-			offset = rxr->rx_page_offset;
-			rxr->rx_page_offset += BNXT_RX_PAGE_SIZE;
-			if (rxr->rx_page_offset == PAGE_SIZE)
-				rxr->rx_page = NULL;
-			else
-				get_page(page);
-		} else {
-			page = alloc_page(gfp);
-			if (!page)
-				return -ENOMEM;
-		}
+	page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp);
 
-		mapping = dma_map_page_attrs(&pdev->dev, page, offset,
-					     BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
-					     DMA_ATTR_WEAK_ORDERING);
-		if (dma_mapping_error(&pdev->dev, mapping)) {
-			__free_page(page);
-			return -EIO;
-		}
-	}
+	if (!page)
+		return -ENOMEM;
 
 	if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
 		sw_prod = bnxt_find_next_agg_idx(rxr, sw_prod);
@@ -1204,6 +1171,7 @@ static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp,
 	total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo, idx,
 					     agg_bufs, tpa, NULL);
 	if (!total_frag_len) {
+		skb_mark_for_recycle(skb);
 		dev_kfree_skb(skb);
 		return NULL;
 	}
@@ -1794,6 +1762,7 @@ static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi,
 		return;
 	}
 	skb_record_rx_queue(skb, bnapi->index);
+	skb_mark_for_recycle(skb);
 	napi_gro_receive(&bnapi->napi, skb);
 }
 
@@ -3002,30 +2971,16 @@ skip_rx_buf_free:
 		if (!page)
 			continue;
 
-		if (BNXT_RX_PAGE_MODE(bp)) {
-			dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
-					     BNXT_RX_PAGE_SIZE, bp->rx_dir,
-					     DMA_ATTR_WEAK_ORDERING);
-			rx_agg_buf->page = NULL;
-			__clear_bit(i, rxr->rx_agg_bmap);
-
-			page_pool_recycle_direct(rxr->page_pool, page);
-		} else {
-			dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
-					     BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
-					     DMA_ATTR_WEAK_ORDERING);
-			rx_agg_buf->page = NULL;
-			__clear_bit(i, rxr->rx_agg_bmap);
+		dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
+				     BNXT_RX_PAGE_SIZE, bp->rx_dir,
+				     DMA_ATTR_WEAK_ORDERING);
+		rx_agg_buf->page = NULL;
+		__clear_bit(i, rxr->rx_agg_bmap);
 
-			__free_page(page);
-		}
+		page_pool_recycle_direct(rxr->page_pool, page);
 	}
 
 skip_rx_agg_free:
-	if (rxr->rx_page) {
-		__free_page(rxr->rx_page);
-		rxr->rx_page = NULL;
-	}
 	map = rxr->rx_tpa_idx_map;
 	if (map)
 		memset(map->agg_idx_bmap, 0, sizeof(map->agg_idx_bmap));
@@ -3244,7 +3199,9 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 {
 	struct page_pool_params pp = { 0 };
 
-	pp.pool_size = bp->rx_ring_size;
+	pp.pool_size = bp->rx_agg_ring_size;
+	if (BNXT_RX_PAGE_MODE(bp))
+		pp.pool_size += bp->rx_ring_size;
 	pp.nid = dev_to_node(&bp->pdev->dev);
 	pp.napi = &rxr->bnapi->napi;
 	pp.dev = &bp->pdev->dev;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 362918876d3ca..d6a1eaa69774d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -919,9 +919,6 @@ struct bnxt_rx_ring_info {
 	unsigned long		*rx_agg_bmap;
 	u16			rx_agg_bmap_size;
 
-	struct page		*rx_page;
-	unsigned int		rx_page_offset;
-
 	dma_addr_t		rx_desc_mapping[MAX_RX_PAGES];
 	dma_addr_t		rx_agg_desc_mapping[MAX_RX_AGG_PAGES];
 
-- 
GitLab


From 578fcfd26e2a1d0e687b347057959228567e2af8 Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Thu, 17 Aug 2023 16:19:07 -0700
Subject: [PATCH 1338/1806] bnxt_en: Let the page pool manage the DMA mapping

Use the page pool's ability to maintain DMA mappings for us.
This avoids re-mapping of the recycled pages.

Link: https://lore.kernel.org/netdev/20230728231829.235716-4-michael.chan@broadcom.com/
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20230817231911.165035-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 32 +++++++----------------
 1 file changed, 10 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6b815a2288e29..73a3936ee4980 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -761,7 +761,6 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 					 unsigned int *offset,
 					 gfp_t gfp)
 {
-	struct device *dev = &bp->pdev->dev;
 	struct page *page;
 
 	if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) {
@@ -774,12 +773,7 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 	if (!page)
 		return NULL;
 
-	*mapping = dma_map_page_attrs(dev, page, *offset, BNXT_RX_PAGE_SIZE,
-				      bp->rx_dir, DMA_ATTR_WEAK_ORDERING);
-	if (dma_mapping_error(dev, *mapping)) {
-		page_pool_recycle_direct(rxr->page_pool, page);
-		return NULL;
-	}
+	*mapping = page_pool_get_dma_addr(page) + *offset;
 	return page;
 }
 
@@ -998,8 +992,8 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp,
 		return NULL;
 	}
 	dma_addr -= bp->rx_dma_offset;
-	dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
-			     bp->rx_dir, DMA_ATTR_WEAK_ORDERING);
+	dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
+				bp->rx_dir);
 	skb = build_skb(data_ptr - bp->rx_offset, BNXT_RX_PAGE_SIZE);
 	if (!skb) {
 		page_pool_recycle_direct(rxr->page_pool, page);
@@ -1032,8 +1026,8 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 		return NULL;
 	}
 	dma_addr -= bp->rx_dma_offset;
-	dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
-			     bp->rx_dir, DMA_ATTR_WEAK_ORDERING);
+	dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
+				bp->rx_dir);
 
 	if (unlikely(!payload))
 		payload = eth_get_headlen(bp->dev, data_ptr, len);
@@ -1149,9 +1143,8 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 			return 0;
 		}
 
-		dma_unmap_page_attrs(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
-				     bp->rx_dir,
-				     DMA_ATTR_WEAK_ORDERING);
+		dma_sync_single_for_cpu(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
+					bp->rx_dir);
 
 		total_frag_len += frag_len;
 		prod = NEXT_RX_AGG(prod);
@@ -2947,10 +2940,6 @@ skip_rx_tpa_free:
 
 		rx_buf->data = NULL;
 		if (BNXT_RX_PAGE_MODE(bp)) {
-			mapping -= bp->rx_dma_offset;
-			dma_unmap_page_attrs(&pdev->dev, mapping,
-					     BNXT_RX_PAGE_SIZE, bp->rx_dir,
-					     DMA_ATTR_WEAK_ORDERING);
 			page_pool_recycle_direct(rxr->page_pool, data);
 		} else {
 			dma_unmap_single_attrs(&pdev->dev, mapping,
@@ -2971,9 +2960,6 @@ skip_rx_buf_free:
 		if (!page)
 			continue;
 
-		dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
-				     BNXT_RX_PAGE_SIZE, bp->rx_dir,
-				     DMA_ATTR_WEAK_ORDERING);
 		rx_agg_buf->page = NULL;
 		__clear_bit(i, rxr->rx_agg_bmap);
 
@@ -3205,7 +3191,9 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 	pp.nid = dev_to_node(&bp->pdev->dev);
 	pp.napi = &rxr->bnapi->napi;
 	pp.dev = &bp->pdev->dev;
-	pp.dma_dir = DMA_BIDIRECTIONAL;
+	pp.dma_dir = bp->rx_dir;
+	pp.max_len = PAGE_SIZE;
+	pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
 	if (PAGE_SIZE > BNXT_RX_PAGE_SIZE)
 		pp.flags |= PP_FLAG_PAGE_FRAG;
 
-- 
GitLab


From d38c19b13b1087890973ac24ae2798797b8a411b Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 17 Aug 2023 16:19:08 -0700
Subject: [PATCH 1339/1806] bnxt_en: Increment rx_resets counter in
 bnxt_disable_napi()

If we are doing a complete reset with irq_re_init set to true in
bnxt_close_nic(), all the ring structures will be freed.  New
structures will be allocated in bnxt_open_nic().  The current code
increments rx_resets counter in bnxt_enable_napi() if bnapi->in_reset
is true.  In a complete reset, bnapi->in_reset will never be true
since the structure is just allocated.

Increment the rx_resets counter in bnxt_disable_napi() instead.  This
will allow us to save all the ring error counters including the
rx_resets counters in the next patch.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20230817231911.165035-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 73a3936ee4980..34c3d231946e3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9393,10 +9393,14 @@ static void bnxt_disable_napi(struct bnxt *bp)
 		return;
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
-		struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring;
+		struct bnxt_napi *bnapi = bp->bnapi[i];
+		struct bnxt_cp_ring_info *cpr;
 
-		napi_disable(&bp->bnapi[i]->napi);
-		if (bp->bnapi[i]->rx_ring)
+		cpr = &bnapi->cp_ring;
+		if (bnapi->in_reset)
+			cpr->sw_stats.rx.rx_resets++;
+		napi_disable(&bnapi->napi);
+		if (bnapi->rx_ring)
 			cancel_work_sync(&cpr->dim.work);
 	}
 }
@@ -9413,8 +9417,6 @@ static void bnxt_enable_napi(struct bnxt *bp)
 		bnapi->tx_fault = 0;
 
 		cpr = &bnapi->cp_ring;
-		if (bnapi->in_reset)
-			cpr->sw_stats.rx.rx_resets++;
 		bnapi->in_reset = false;
 
 		bnapi->tx_pkts = 0;
-- 
GitLab


From 4c70dbe3c0087b439b9e5015057e3e378cf5d8b1 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 17 Aug 2023 16:19:09 -0700
Subject: [PATCH 1340/1806] bnxt_en: Save ring error counters across reset

Currently, the ring counters are stored in the per ring datastructure.
During reset, all the rings are freed together with the associated
datastructures.  As a result, all the ring error counters will be reset
to zero.

Add logic to keep track of the total error counts of all the rings
and save them before reset (including ifdown).  The next patch will
display these total ring error counters under ethtool -S.

Link: https://lore.kernel.org/netdev/CACKFLimD-bKmJ1tGZOLYRjWzEwxkri-Mw7iFme1x2Dr0twdCeg@mail.gmail.com/
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20230817231911.165035-5-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 32 ++++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 15 +++++++++++
 2 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 34c3d231946e3..bea562d08d6cb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10685,8 +10685,10 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_free_skbs(bp);
 
 	/* Save ring stats before shutdown */
-	if (bp->bnapi && irq_re_init)
+	if (bp->bnapi && irq_re_init) {
 		bnxt_get_ring_stats(bp, &bp->net_stats_prev);
+		bnxt_get_ring_err_stats(bp, &bp->ring_err_stats_prev);
+	}
 	if (irq_re_init) {
 		bnxt_free_irq(bp);
 		bnxt_del_napi(bp);
@@ -10935,6 +10937,34 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	clear_bit(BNXT_STATE_READ_STATS, &bp->state);
 }
 
+static void bnxt_get_one_ring_err_stats(struct bnxt *bp,
+					struct bnxt_total_ring_err_stats *stats,
+					struct bnxt_cp_ring_info *cpr)
+{
+	struct bnxt_sw_stats *sw_stats = &cpr->sw_stats;
+	u64 *hw_stats = cpr->stats.sw_stats;
+
+	stats->rx_total_l4_csum_errors += sw_stats->rx.rx_l4_csum_errors;
+	stats->rx_total_resets += sw_stats->rx.rx_resets;
+	stats->rx_total_buf_errors += sw_stats->rx.rx_buf_errors;
+	stats->rx_total_oom_discards += sw_stats->rx.rx_oom_discards;
+	stats->rx_total_netpoll_discards += sw_stats->rx.rx_netpoll_discards;
+	stats->rx_total_ring_discards +=
+		BNXT_GET_RING_STATS64(hw_stats, rx_discard_pkts);
+	stats->tx_total_ring_discards +=
+		BNXT_GET_RING_STATS64(hw_stats, tx_discard_pkts);
+	stats->total_missed_irqs += sw_stats->cmn.missed_irqs;
+}
+
+void bnxt_get_ring_err_stats(struct bnxt *bp,
+			     struct bnxt_total_ring_err_stats *stats)
+{
+	int i;
+
+	for (i = 0; i < bp->cp_nr_rings; i++)
+		bnxt_get_one_ring_err_stats(bp, stats, &bp->bnapi[i]->cp_ring);
+}
+
 static bool bnxt_mc_list_updated(struct bnxt *bp, u32 *rx_mask)
 {
 	struct net_device *dev = bp->dev;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index d6a1eaa69774d..7287fd3c0763a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -948,6 +948,17 @@ struct bnxt_sw_stats {
 	struct bnxt_cmn_sw_stats cmn;
 };
 
+struct bnxt_total_ring_err_stats {
+	u64			rx_total_l4_csum_errors;
+	u64			rx_total_resets;
+	u64			rx_total_buf_errors;
+	u64			rx_total_oom_discards;
+	u64			rx_total_netpoll_discards;
+	u64			rx_total_ring_discards;
+	u64			tx_total_ring_discards;
+	u64			total_missed_irqs;
+};
+
 struct bnxt_stats_mem {
 	u64		*sw_stats;
 	u64		*hw_masks;
@@ -2018,6 +2029,8 @@ struct bnxt {
 	u8			pri2cos_idx[8];
 	u8			pri2cos_valid;
 
+	struct bnxt_total_ring_err_stats ring_err_stats_prev;
+
 	u16			hwrm_max_req_len;
 	u16			hwrm_max_ext_req_len;
 	unsigned int		hwrm_cmd_timeout;
@@ -2344,6 +2357,8 @@ int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
 void bnxt_reenable_sriov(struct bnxt *bp);
 int bnxt_close_nic(struct bnxt *, bool, bool);
+void bnxt_get_ring_err_stats(struct bnxt *bp,
+			     struct bnxt_total_ring_err_stats *stats);
 int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words,
 			 u32 *reg_buf);
 void bnxt_fw_exception(struct bnxt *bp);
-- 
GitLab


From a080b47a04c503674c30dfe697b6fa1b98c3bb6b Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 17 Aug 2023 16:19:10 -0700
Subject: [PATCH 1341/1806] bnxt_en: Display the ring error counters under
 ethtool -S

The existing driver displays the sum of 4 ring counters under ethtool -S.
These counters are in the array bnxt_sw_func_stats.  These counters are
summed at the time of ethtool -S and will be lost when the device is reset.

Replace these counters with the new total ring error counters added in the
last patch.  These new counters are saved before reset.  ethtool -S will
now display the sum of the saved counters plus the current counters.

Link: https://lore.kernel.org/netdev/CACKFLimD-bKmJ1tGZOLYRjWzEwxkri-Mw7iFme1x2Dr0twdCeg@mail.gmail.com/
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20230817231911.165035-6-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 48 +++++++++----------
 1 file changed, 23 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 8fd5071d8b099..a9f1eede24e99 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -339,13 +339,15 @@ enum {
 	RX_NETPOLL_DISCARDS,
 };
 
-static struct {
-	u64			counter;
-	char			string[ETH_GSTRING_LEN];
-} bnxt_sw_func_stats[] = {
-	{0, "rx_total_discard_pkts"},
-	{0, "tx_total_discard_pkts"},
-	{0, "rx_total_netpoll_discards"},
+static const char *const bnxt_ring_err_stats_arr[] = {
+	"rx_total_l4_csum_errors",
+	"rx_total_resets",
+	"rx_total_buf_errors",
+	"rx_total_oom_discards",
+	"rx_total_netpoll_discards",
+	"rx_total_ring_discards",
+	"tx_total_ring_discards",
+	"total_missed_irqs",
 };
 
 #define NUM_RING_RX_SW_STATS		ARRAY_SIZE(bnxt_rx_sw_stats_str)
@@ -495,7 +497,7 @@ static const struct {
 	BNXT_TX_STATS_PRI_ENTRIES(tx_packets),
 };
 
-#define BNXT_NUM_SW_FUNC_STATS	ARRAY_SIZE(bnxt_sw_func_stats)
+#define BNXT_NUM_RING_ERR_STATS	ARRAY_SIZE(bnxt_ring_err_stats_arr)
 #define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr)
 #define BNXT_NUM_STATS_PRI			\
 	(ARRAY_SIZE(bnxt_rx_bytes_pri_arr) +	\
@@ -532,7 +534,7 @@ static int bnxt_get_num_stats(struct bnxt *bp)
 {
 	int num_stats = bnxt_get_num_ring_stats(bp);
 
-	num_stats += BNXT_NUM_SW_FUNC_STATS;
+	num_stats += BNXT_NUM_RING_ERR_STATS;
 
 	if (bp->flags & BNXT_FLAG_PORT_STATS)
 		num_stats += BNXT_NUM_PORT_STATS;
@@ -583,18 +585,17 @@ static bool is_tx_ring(struct bnxt *bp, int ring_num)
 static void bnxt_get_ethtool_stats(struct net_device *dev,
 				   struct ethtool_stats *stats, u64 *buf)
 {
-	u32 i, j = 0;
+	struct bnxt_total_ring_err_stats ring_err_stats = {0};
 	struct bnxt *bp = netdev_priv(dev);
+	u64 *curr, *prev;
 	u32 tpa_stats;
+	u32 i, j = 0;
 
 	if (!bp->bnapi) {
-		j += bnxt_get_num_ring_stats(bp) + BNXT_NUM_SW_FUNC_STATS;
+		j += bnxt_get_num_ring_stats(bp);
 		goto skip_ring_stats;
 	}
 
-	for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++)
-		bnxt_sw_func_stats[i].counter = 0;
-
 	tpa_stats = bnxt_get_num_tpa_ring_stats(bp);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
@@ -631,19 +632,16 @@ skip_tpa_ring_stats:
 		sw = (u64 *)&cpr->sw_stats.cmn;
 		for (k = 0; k < NUM_RING_CMN_SW_STATS; j++, k++)
 			buf[j] = sw[k];
-
-		bnxt_sw_func_stats[RX_TOTAL_DISCARDS].counter +=
-			BNXT_GET_RING_STATS64(sw_stats, rx_discard_pkts);
-		bnxt_sw_func_stats[TX_TOTAL_DISCARDS].counter +=
-			BNXT_GET_RING_STATS64(sw_stats, tx_discard_pkts);
-		bnxt_sw_func_stats[RX_NETPOLL_DISCARDS].counter +=
-			cpr->sw_stats.rx.rx_netpoll_discards;
 	}
 
-	for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++, j++)
-		buf[j] = bnxt_sw_func_stats[i].counter;
+	bnxt_get_ring_err_stats(bp, &ring_err_stats);
 
 skip_ring_stats:
+	curr = &ring_err_stats.rx_total_l4_csum_errors;
+	prev = &bp->ring_err_stats_prev.rx_total_l4_csum_errors;
+	for (i = 0; i < BNXT_NUM_RING_ERR_STATS; i++, j++, curr++, prev++)
+		buf[j] = *curr + *prev;
+
 	if (bp->flags & BNXT_FLAG_PORT_STATS) {
 		u64 *port_stats = bp->port_stats.sw_stats;
 
@@ -745,8 +743,8 @@ skip_tpa_stats:
 				buf += ETH_GSTRING_LEN;
 			}
 		}
-		for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++) {
-			strcpy(buf, bnxt_sw_func_stats[i].string);
+		for (i = 0; i < BNXT_NUM_RING_ERR_STATS; i++) {
+			strscpy(buf, bnxt_ring_err_stats_arr[i], ETH_GSTRING_LEN);
 			buf += ETH_GSTRING_LEN;
 		}
 
-- 
GitLab


From 8becd1961c734cb4bf96e3f98c50a644e8b8be2a Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 17 Aug 2023 16:19:11 -0700
Subject: [PATCH 1342/1806] bnxt_en: Add tx_resets ring counter

Add a new tx_resets ring counter.  This counter will be saved as
tx_total_resets across any reset.  Since we currently do a full reset
in bnxt_sched_reset_txr(), the per ring counter will always be cleared
during reset.  Only the tx_total_resets count will be meaningful and we
only display this under ethtool -S.

Link: https://lore.kernel.org/netdev/CACKFLimD-bKmJ1tGZOLYRjWzEwxkri-Mw7iFme1x2Dr0twdCeg@mail.gmail.com/
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20230817231911.165035-7-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 3 +++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         | 6 ++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 1 +
 3 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index bea562d08d6cb..5d6ea2782c2fc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9397,6 +9397,8 @@ static void bnxt_disable_napi(struct bnxt *bp)
 		struct bnxt_cp_ring_info *cpr;
 
 		cpr = &bnapi->cp_ring;
+		if (bnapi->tx_fault)
+			cpr->sw_stats.tx.tx_resets++;
 		if (bnapi->in_reset)
 			cpr->sw_stats.rx.rx_resets++;
 		napi_disable(&bnapi->napi);
@@ -10951,6 +10953,7 @@ static void bnxt_get_one_ring_err_stats(struct bnxt *bp,
 	stats->rx_total_netpoll_discards += sw_stats->rx.rx_netpoll_discards;
 	stats->rx_total_ring_discards +=
 		BNXT_GET_RING_STATS64(hw_stats, rx_discard_pkts);
+	stats->tx_total_resets += sw_stats->tx.tx_resets;
 	stats->tx_total_ring_discards +=
 		BNXT_GET_RING_STATS64(hw_stats, tx_discard_pkts);
 	stats->total_missed_irqs += sw_stats->cmn.missed_irqs;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 7287fd3c0763a..84cbcfa61bc12 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -939,12 +939,17 @@ struct bnxt_rx_sw_stats {
 	u64			rx_netpoll_discards;
 };
 
+struct bnxt_tx_sw_stats {
+	u64			tx_resets;
+};
+
 struct bnxt_cmn_sw_stats {
 	u64			missed_irqs;
 };
 
 struct bnxt_sw_stats {
 	struct bnxt_rx_sw_stats rx;
+	struct bnxt_tx_sw_stats tx;
 	struct bnxt_cmn_sw_stats cmn;
 };
 
@@ -955,6 +960,7 @@ struct bnxt_total_ring_err_stats {
 	u64			rx_total_oom_discards;
 	u64			rx_total_netpoll_discards;
 	u64			rx_total_ring_discards;
+	u64			tx_total_resets;
 	u64			tx_total_ring_discards;
 	u64			total_missed_irqs;
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index a9f1eede24e99..547247d98eba2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -346,6 +346,7 @@ static const char *const bnxt_ring_err_stats_arr[] = {
 	"rx_total_oom_discards",
 	"rx_total_netpoll_discards",
 	"rx_total_ring_discards",
+	"tx_total_resets",
 	"tx_total_ring_discards",
 	"total_missed_irqs",
 };
-- 
GitLab


From 726e9e8b94b92d69004af17a68f9f37ffc0358b9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 17 Aug 2023 18:23:53 +0000
Subject: [PATCH 1343/1806] tcp: refine skb->ooo_okay setting

Enabling BIG TCP on a low end platform apparently increased
chances of getting flows locked on one busy TX queue.

A similar problem was handled in commit 9b462d02d6dd
("tcp: TCP Small Queues and strange attractors"),
but the strategy worked for either bulk flows,
or 'large enough' RPC. BIG TCP changed how large
RPC needed to be to enable the work around:
If RPC fits in a single skb, TSQ never triggers.

Root cause for the problem is a busy TX queue,
with delayed TX completions.

This patch changes how we set skb->ooo_okay to detect
the case TX completion was not done, but incoming ACK
already was processed and emptied rtx queue.

Update the comment to explain the tricky details.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230817182353.2523746-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_output.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 769a558159ee1..e6b4fbd642f7e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1301,14 +1301,21 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	}
 	tcp_header_size = tcp_options_size + sizeof(struct tcphdr);
 
-	/* if no packet is in qdisc/device queue, then allow XPS to select
-	 * another queue. We can be called from tcp_tsq_handler()
-	 * which holds one reference to sk.
-	 *
-	 * TODO: Ideally, in-flight pure ACK packets should not matter here.
-	 * One way to get this would be to set skb->truesize = 2 on them.
+	/* We set skb->ooo_okay to one if this packet can select
+	 * a different TX queue than prior packets of this flow,
+	 * to avoid self inflicted reorders.
+	 * The 'other' queue decision is based on current cpu number
+	 * if XPS is enabled, or sk->sk_txhash otherwise.
+	 * We can switch to another (and better) queue if:
+	 * 1) No packet with payload is in qdisc/device queues.
+	 *    Delays in TX completion can defeat the test
+	 *    even if packets were already sent.
+	 * 2) Or rtx queue is empty.
+	 *    This mitigates above case if ACK packets for
+	 *    all prior packets were already processed.
 	 */
-	skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1);
+	skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) ||
+			tcp_rtx_queue_empty(sk);
 
 	/* If we had to use memory reserve to allocate this skb,
 	 * this might cause drops if packet is looped back :
-- 
GitLab


From cb49ec0349240a112d6dd50b04466eaa2188b76c Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Thu, 17 Aug 2023 21:41:59 +0800
Subject: [PATCH 1344/1806] net: freescale: Remove unused declarations

Commit 5d93cfcf7360 ("net: dpaa: Convert to phylink") removed
fman_set_mac_active_pause()/fman_get_pause_cfg() but not declarations.
Commit 48257c4f168e ("Add fs_enet ethernet network driver, for several
embedded platforms.") declared but never implemented
fs_enet_platform_init() and fs_enet_platform_cleanup().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Sean Anderson <sean.anderson@seco.com>
Acked-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230817134159.38484-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fman/mac.h        | 4 ----
 drivers/net/ethernet/freescale/fs_enet/fs_enet.h | 5 -----
 2 files changed, 9 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h
index ad06f8d7924be..fe747915cc737 100644
--- a/drivers/net/ethernet/freescale/fman/mac.h
+++ b/drivers/net/ethernet/freescale/fman/mac.h
@@ -68,10 +68,6 @@ struct dpaa_eth_data {
 
 extern const char	*mac_driver_description;
 
-int fman_set_mac_active_pause(struct mac_device *mac_dev, bool rx, bool tx);
-
-void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause,
-			bool *tx_pause);
 int fman_set_multi(struct net_device *net_dev, struct mac_device *mac_dev);
 
 #endif	/* __MAC_H */
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
index d371072fff608..759bb7080e22a 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
@@ -208,11 +208,6 @@ void fs_cleanup_bds(struct net_device *dev);
 #define DRV_MODULE_NAME		"fs_enet"
 #define PFX DRV_MODULE_NAME	": "
 
-/***************************************************************************/
-
-int fs_enet_platform_init(void);
-void fs_enet_platform_cleanup(void);
-
 /***************************************************************************/
 /* buffer descriptor access macros */
 
-- 
GitLab


From 1e700948c9db0d09f691f715e8f4b947e51e35b5 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 17 Aug 2023 21:20:27 +0800
Subject: [PATCH 1345/1806] net/smc: support smc release version negotiation in
 clc handshake

Support smc release version negotiation in clc handshake based on
SMC v2, where no negotiation process for different releases, but
for different versions. The latest smc release version was updated
to v2.1. And currently there are two release versions of SMCv2, v2.0
and v2.1. In the release version negotiation, client sends the preferred
release version by CLC Proposal Message, server makes decision for which
release version to use based on the client preferred release version and
self-supported release version (here choose the minimum release version
of the client preferred and server latest supported), then the decision
returns to client by CLC Accept Message. Client confirms the decision by
CLC Confirm Message.

Client                                    Server
      Proposal(preferred release version)
     ------------------------------------>

      Accept(accpeted release version)
 min(client preferred, server latest supported)
     <------------------------------------

      Confirm(accpeted release version)
     ------------------------------------>

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c   | 21 +++++++++++++++++----
 net/smc/smc.h      |  5 ++++-
 net/smc/smc_clc.c  | 14 +++++++-------
 net/smc/smc_clc.h  | 23 ++++++++++++++++++++++-
 net/smc/smc_core.h |  1 +
 5 files changed, 51 insertions(+), 13 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index f5834af5fad53..fff196b557caa 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1198,8 +1198,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
 	struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
 		(struct smc_clc_msg_accept_confirm_v2 *)aclc;
 	struct smc_clc_first_contact_ext *fce =
-		(struct smc_clc_first_contact_ext *)
-			(((u8 *)clc_v2) + sizeof(*clc_v2));
+		smc_get_clc_first_contact_ext(clc_v2, false);
 
 	if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1)
 		return 0;
@@ -1218,6 +1217,9 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
 			return SMC_CLC_DECL_NOINDIRECT;
 		}
 	}
+
+	ini->release_nr = fce->release;
+
 	return 0;
 }
 
@@ -1386,6 +1388,13 @@ static int smc_connect_ism(struct smc_sock *smc,
 		struct smc_clc_msg_accept_confirm_v2 *aclc_v2 =
 			(struct smc_clc_msg_accept_confirm_v2 *)aclc;
 
+		if (ini->first_contact_peer) {
+			struct smc_clc_first_contact_ext *fce =
+				smc_get_clc_first_contact_ext(aclc_v2, true);
+
+			ini->release_nr = fce->release;
+		}
+
 		rc = smc_v2_determine_accepted_chid(aclc_v2, ini);
 		if (rc)
 			return rc;
@@ -1420,7 +1429,7 @@ static int smc_connect_ism(struct smc_sock *smc,
 	}
 
 	rc = smc_clc_send_confirm(smc, ini->first_contact_local,
-				  aclc->hdr.version, eid, NULL);
+				  aclc->hdr.version, eid, ini);
 	if (rc)
 		goto connect_abort;
 	mutex_unlock(&smc_server_lgr_pending);
@@ -1996,6 +2005,10 @@ static int smc_listen_v2_check(struct smc_sock *new_smc,
 		}
 	}
 
+	ini->release_nr = pclc_v2_ext->hdr.flag.release;
+	if (pclc_v2_ext->hdr.flag.release > SMC_RELEASE)
+		ini->release_nr = SMC_RELEASE;
+
 out:
 	if (!ini->smcd_version && !ini->smcr_version)
 		return rc;
@@ -2443,7 +2456,7 @@ static void smc_listen_work(struct work_struct *work)
 	/* send SMC Accept CLC message */
 	accept_version = ini->is_smcd ? ini->smcd_version : ini->smcr_version;
 	rc = smc_clc_send_accept(new_smc, ini->first_contact_local,
-				 accept_version, ini->negotiated_eid);
+				 accept_version, ini->negotiated_eid, ini);
 	if (rc)
 		goto out_unlock;
 
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 1f2b912c43d10..24745fde4ac26 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -21,7 +21,10 @@
 
 #define SMC_V1		1		/* SMC version V1 */
 #define SMC_V2		2		/* SMC version V2 */
-#define SMC_RELEASE	0
+
+#define SMC_RELEASE_0 0
+#define SMC_RELEASE_1 1
+#define SMC_RELEASE	SMC_RELEASE_1 /* the latest release version */
 
 #define SMCPROTO_SMC		0	/* SMC protocol, IPv4 */
 #define SMCPROTO_SMC6		1	/* SMC protocol, IPv6 */
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index c90d9e5dda540..fb0be0817e8a5 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -420,11 +420,11 @@ smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc)
 	return true;
 }
 
-static void smc_clc_fill_fce(struct smc_clc_first_contact_ext *fce, int *len)
+static void smc_clc_fill_fce(struct smc_clc_first_contact_ext *fce, int *len, int release_nr)
 {
 	memset(fce, 0, sizeof(*fce));
 	fce->os_type = SMC_CLC_OS_LINUX;
-	fce->release = SMC_RELEASE;
+	fce->release = release_nr;
 	memcpy(fce->hostname, smc_hostname, sizeof(smc_hostname));
 	(*len) += sizeof(*fce);
 }
@@ -1019,7 +1019,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 				memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN);
 			len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
 			if (first_contact)
-				smc_clc_fill_fce(&fce, &len);
+				smc_clc_fill_fce(&fce, &len, ini->release_nr);
 			clc_v2->hdr.length = htons(len);
 		}
 		memcpy(trl.eyecatcher, SMCD_EYECATCHER,
@@ -1063,10 +1063,10 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 				memcpy(clc_v2->r1.eid, eid, SMC_MAX_EID_LEN);
 			len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2;
 			if (first_contact) {
-				smc_clc_fill_fce(&fce, &len);
+				smc_clc_fill_fce(&fce, &len, ini->release_nr);
 				fce.v2_direct = !link->lgr->uses_gateway;
 				memset(&gle, 0, sizeof(gle));
-				if (ini && clc->hdr.type == SMC_CLC_CONFIRM) {
+				if (clc->hdr.type == SMC_CLC_CONFIRM) {
 					gle.gid_cnt = ini->smcrv2.gidlist.len;
 					len += sizeof(gle);
 					len += gle.gid_cnt * sizeof(gle.gid[0]);
@@ -1141,7 +1141,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
 
 /* send CLC ACCEPT message across internal TCP socket */
 int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
-			u8 version, u8 *negotiated_eid)
+			u8 version, u8 *negotiated_eid, struct smc_init_info *ini)
 {
 	struct smc_clc_msg_accept_confirm_v2 aclc_v2;
 	int len;
@@ -1149,7 +1149,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
 	memset(&aclc_v2, 0, sizeof(aclc_v2));
 	aclc_v2.hdr.type = SMC_CLC_ACCEPT;
 	len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact,
-					  version, negotiated_eid, NULL);
+					  version, negotiated_eid, ini);
 	if (len < ntohs(aclc_v2.hdr.length))
 		len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err;
 
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 5fee545c9a109..b923e89acafb0 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -370,6 +370,27 @@ smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext)
 		 ntohs(prop_v2ext->hdr.smcd_v2_ext_offset));
 }
 
+static inline struct smc_clc_first_contact_ext *
+smc_get_clc_first_contact_ext(struct smc_clc_msg_accept_confirm_v2 *clc_v2,
+			      bool is_smcd)
+{
+	int clc_v2_len;
+
+	if (clc_v2->hdr.version == SMC_V1 ||
+	    !(clc_v2->hdr.typev2 & SMC_FIRST_CONTACT_MASK))
+		return NULL;
+
+	if (is_smcd)
+		clc_v2_len =
+			offsetofend(struct smc_clc_msg_accept_confirm_v2, d1);
+	else
+		clc_v2_len =
+			offsetofend(struct smc_clc_msg_accept_confirm_v2, r1);
+
+	return (struct smc_clc_first_contact_ext *)(((u8 *)clc_v2) +
+						    clc_v2_len);
+}
+
 struct smcd_dev;
 struct smc_init_info;
 
@@ -382,7 +403,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini);
 int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
 			 u8 version, u8 *eid, struct smc_init_info *ini);
 int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact,
-			u8 version, u8 *negotiated_eid);
+			u8 version, u8 *negotiated_eid, struct smc_init_info *ini);
 void smc_clc_init(void) __init;
 void smc_clc_exit(void);
 void smc_clc_get_hostname(u8 **host);
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 3c1b31bfa1cf3..b6c68db61f238 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -374,6 +374,7 @@ struct smc_init_info {
 	u8			is_smcd;
 	u8			smc_type_v1;
 	u8			smc_type_v2;
+	u8			release_nr;
 	u8			first_contact_peer;
 	u8			first_contact_local;
 	unsigned short		vlan_id;
-- 
GitLab


From 7290178a82fcc71694816ffe3c0c56453f0cf59c Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 17 Aug 2023 21:20:28 +0800
Subject: [PATCH 1346/1806] net/smc: add vendor unique experimental options
 area in clc handshake

Add vendor unique experimental options area in clc handshake. In clc
accept and confirm msg, vendor unique experimental options use the
16-Bytes reserved field, which defined in struct smc_clc_fce_gid_ext
in previous version. Because of the struct smc_clc_first_contact_ext
is widely used and limit the scope of modification, this patch moves
the 16-Bytes reserved field out of struct smc_clc_fce_gid_ext, and
followed with the struct smc_clc_first_contact_ext in a new struct
names struct smc_clc_first_contact_ext_v2x.

For SMC-R first connection, in previous version, the struct smc_clc_
first_contact_ext and the 16-Bytes reserved field has already been
included in clc accept and confirm msg. Thus, this patch use struct
smc_clc_first_contact_ext_v2x instead of the struct smc_clc_first_
contact_ext and the 16-Bytes reserved field in SMC-R clc accept and
confirm msg is compatible with previous version.

For SMC-D first connection, in previous version, only the struct smc_
clc_first_contact_ext is included in clc accept and confirm msg, and
the 16-Bytes reserved field is not included. Thus, when the negotiated
smc release version is the version before v2.1, we still use struct
smc_clc_first_contact_ext for compatible consideration. If the negotiated
smc release version is v2.1 or later, use struct smc_clc_first_contact_
ext_v2x instead.

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c  |  2 +-
 net/smc/smc_clc.c | 44 +++++++++++++++++++++++---------------------
 net/smc/smc_clc.h | 15 +++++++++++++--
 3 files changed, 37 insertions(+), 24 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index fff196b557caa..b80c5902f7032 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1144,7 +1144,7 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc,
 
 #define SMC_CLC_MAX_ACCEPT_LEN \
 	(sizeof(struct smc_clc_msg_accept_confirm_v2) + \
-	 sizeof(struct smc_clc_first_contact_ext) + \
+	 sizeof(struct smc_clc_first_contact_ext_v2x) + \
 	 sizeof(struct smc_clc_msg_trail))
 
 /* CLC handshake during connect */
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index fb0be0817e8a5..a5b28f9c037de 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -391,9 +391,7 @@ smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm_v2 *clc_v2)
 			return false;
 	} else {
 		if (hdr->typev1 == SMC_TYPE_D &&
-		    ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 &&
-		    (ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 +
-				sizeof(struct smc_clc_first_contact_ext)))
+		    ntohs(hdr->length) < SMCD_CLC_ACCEPT_CONFIRM_LEN_V2)
 			return false;
 		if (hdr->typev1 == SMC_TYPE_R &&
 		    ntohs(hdr->length) < SMCR_CLC_ACCEPT_CONFIRM_LEN_V2)
@@ -420,13 +418,19 @@ smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc)
 	return true;
 }
 
-static void smc_clc_fill_fce(struct smc_clc_first_contact_ext *fce, int *len, int release_nr)
+static int smc_clc_fill_fce(struct smc_clc_first_contact_ext_v2x *fce,
+			    struct smc_init_info *ini)
 {
+	int ret = sizeof(*fce);
+
 	memset(fce, 0, sizeof(*fce));
-	fce->os_type = SMC_CLC_OS_LINUX;
-	fce->release = release_nr;
-	memcpy(fce->hostname, smc_hostname, sizeof(smc_hostname));
-	(*len) += sizeof(*fce);
+	fce->fce_v2_base.os_type = SMC_CLC_OS_LINUX;
+	fce->fce_v2_base.release = ini->release_nr;
+	memcpy(fce->fce_v2_base.hostname, smc_hostname, sizeof(smc_hostname));
+	if (ini->is_smcd && ini->release_nr < SMC_RELEASE_1)
+		ret = sizeof(struct smc_clc_first_contact_ext);
+
+	return ret;
 }
 
 /* check if received message has a correct header length and contains valid
@@ -986,13 +990,13 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 				       u8 *eid, struct smc_init_info *ini)
 {
 	struct smc_connection *conn = &smc->conn;
+	struct smc_clc_first_contact_ext_v2x fce;
 	struct smc_clc_msg_accept_confirm *clc;
-	struct smc_clc_first_contact_ext fce;
 	struct smc_clc_fce_gid_ext gle;
 	struct smc_clc_msg_trail trl;
+	int i, len, fce_len;
 	struct kvec vec[5];
 	struct msghdr msg;
-	int i, len;
 
 	/* send SMC Confirm CLC msg */
 	clc = (struct smc_clc_msg_accept_confirm *)clc_v2;
@@ -1018,8 +1022,10 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 			if (eid && eid[0])
 				memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN);
 			len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
-			if (first_contact)
-				smc_clc_fill_fce(&fce, &len, ini->release_nr);
+			if (first_contact) {
+				fce_len = smc_clc_fill_fce(&fce, ini);
+				len += fce_len;
+			}
 			clc_v2->hdr.length = htons(len);
 		}
 		memcpy(trl.eyecatcher, SMCD_EYECATCHER,
@@ -1063,15 +1069,14 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 				memcpy(clc_v2->r1.eid, eid, SMC_MAX_EID_LEN);
 			len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2;
 			if (first_contact) {
-				smc_clc_fill_fce(&fce, &len, ini->release_nr);
-				fce.v2_direct = !link->lgr->uses_gateway;
-				memset(&gle, 0, sizeof(gle));
+				fce_len = smc_clc_fill_fce(&fce, ini);
+				len += fce_len;
+				fce.fce_v2_base.v2_direct = !link->lgr->uses_gateway;
 				if (clc->hdr.type == SMC_CLC_CONFIRM) {
+					memset(&gle, 0, sizeof(gle));
 					gle.gid_cnt = ini->smcrv2.gidlist.len;
 					len += sizeof(gle);
 					len += gle.gid_cnt * sizeof(gle.gid[0]);
-				} else {
-					len += sizeof(gle.reserved);
 				}
 			}
 			clc_v2->hdr.length = htons(len);
@@ -1094,7 +1099,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 				   sizeof(trl);
 	if (version > SMC_V1 && first_contact) {
 		vec[i].iov_base = &fce;
-		vec[i++].iov_len = sizeof(fce);
+		vec[i++].iov_len = fce_len;
 		if (!conn->lgr->is_smcd) {
 			if (clc->hdr.type == SMC_CLC_CONFIRM) {
 				vec[i].iov_base = &gle;
@@ -1102,9 +1107,6 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 				vec[i].iov_base = &ini->smcrv2.gidlist.list;
 				vec[i++].iov_len = gle.gid_cnt *
 						   sizeof(gle.gid[0]);
-			} else {
-				vec[i].iov_base = &gle.reserved;
-				vec[i++].iov_len = sizeof(gle.reserved);
 			}
 		}
 	}
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index b923e89acafb0..bd75382f374d5 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -147,7 +147,9 @@ struct smc_clc_msg_proposal_prefix {	/* prefix part of clc proposal message*/
 struct smc_clc_msg_smcd {	/* SMC-D GID information */
 	struct smc_clc_smcd_gid_chid ism; /* ISM native GID+CHID of requestor */
 	__be16 v2_ext_offset;	/* SMC Version 2 Extension Offset */
-	u8 reserved[28];
+	u8 vendor_oui[3];	/* vendor organizationally unique identifier */
+	u8 vendor_exp_options[5];
+	u8 reserved[20];
 };
 
 struct smc_clc_smcd_v2_extension {
@@ -231,8 +233,17 @@ struct smc_clc_first_contact_ext {
 	u8 hostname[SMC_MAX_HOSTNAME_LEN];
 };
 
+struct smc_clc_first_contact_ext_v2x {
+	struct smc_clc_first_contact_ext fce_v2_base;
+	u8 reserved3[4];
+	__be32 vendor_exp_options;
+	u8 reserved4[8];
+} __packed;		/* format defined in
+			 * IBM Shared Memory Communications Version 2 (Third Edition)
+			 * (https://www.ibm.com/support/pages/node/7009315)
+			 */
+
 struct smc_clc_fce_gid_ext {
-	u8 reserved[16];
 	u8 gid_cnt;
 	u8 reserved2[3];
 	u8 gid[][SMC_GID_SIZE];
-- 
GitLab


From 6ac1e6563f5915cd38b6bc6a8b26964b2252f751 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 17 Aug 2023 21:20:29 +0800
Subject: [PATCH 1347/1806] net/smc: support smc v2.x features validate

Support SMC v2.x features validate for SMC v2.1. This is the frame
code for SMC v2.x features validate, and will take effects only when
the negotiated release version is v2.1 or later.

For Server, v2.x features' validation should be done in smc_clc_srv_
v2x_features_validate when receiving v2.1 or later CLC Proposal Message,
such as max conns, max links negotiation, the decision of the final
value of max conns and max links should be made in this function.
And final check for server when receiving v2.1 or later CLC Confirm
Message should be done in smc_clc_v2x_features_confirm_check.

For client, v2.x features' validation should be done in smc_clc_clnt_
v2x_features_validate when receiving v2.1 or later CLC Accept Message,
for example, the decision to accpt the accepted value or to decline
should be made in this function.

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c  | 18 ++++++++++++++++++
 net/smc/smc_clc.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 net/smc/smc_clc.h |  7 +++++++
 3 files changed, 71 insertions(+)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index b80c5902f7032..337303b2a64ec 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1199,6 +1199,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
 		(struct smc_clc_msg_accept_confirm_v2 *)aclc;
 	struct smc_clc_first_contact_ext *fce =
 		smc_get_clc_first_contact_ext(clc_v2, false);
+	int rc;
 
 	if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1)
 		return 0;
@@ -1219,6 +1220,9 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
 	}
 
 	ini->release_nr = fce->release;
+	rc = smc_clc_clnt_v2x_features_validate(fce, ini);
+	if (rc)
+		return rc;
 
 	return 0;
 }
@@ -1393,6 +1397,9 @@ static int smc_connect_ism(struct smc_sock *smc,
 				smc_get_clc_first_contact_ext(aclc_v2, true);
 
 			ini->release_nr = fce->release;
+			rc = smc_clc_clnt_v2x_features_validate(fce, ini);
+			if (rc)
+				return rc;
 		}
 
 		rc = smc_v2_determine_accepted_chid(aclc_v2, ini);
@@ -2443,6 +2450,10 @@ static void smc_listen_work(struct work_struct *work)
 	if (rc)
 		goto out_decl;
 
+	rc = smc_clc_srv_v2x_features_validate(pclc, ini);
+	if (rc)
+		goto out_decl;
+
 	mutex_lock(&smc_server_lgr_pending);
 	smc_close_init(new_smc);
 	smc_rx_init(new_smc);
@@ -2475,6 +2486,13 @@ static void smc_listen_work(struct work_struct *work)
 		goto out_decl;
 	}
 
+	rc = smc_clc_v2x_features_confirm_check(cclc, ini);
+	if (rc) {
+		if (!ini->is_smcd)
+			goto out_unlock;
+		goto out_decl;
+	}
+
 	/* finish worker */
 	if (!ini->is_smcd) {
 		rc = smc_listen_rdma_finish(new_smc, cclc,
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index a5b28f9c037de..0232f189dad95 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -1158,6 +1158,52 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
 	return len > 0 ? 0 : len;
 }
 
+int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
+				      struct smc_init_info *ini)
+{
+	struct smc_clc_v2_extension *pclc_v2_ext;
+
+	if ((!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) ||
+	    ini->release_nr < SMC_RELEASE_1)
+		return 0;
+
+	pclc_v2_ext = smc_get_clc_v2_ext(pclc);
+	if (!pclc_v2_ext)
+		return SMC_CLC_DECL_NOV2EXT;
+
+	return 0;
+}
+
+int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
+				       struct smc_init_info *ini)
+{
+	if (ini->release_nr < SMC_RELEASE_1)
+		return 0;
+
+	return 0;
+}
+
+int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
+				       struct smc_init_info *ini)
+{
+	struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
+		(struct smc_clc_msg_accept_confirm_v2 *)cclc;
+	struct smc_clc_first_contact_ext *fce =
+		smc_get_clc_first_contact_ext(clc_v2, ini->is_smcd);
+
+	if (cclc->hdr.version == SMC_V1 ||
+	    !(cclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK))
+		return 0;
+
+	if (ini->release_nr != fce->release)
+		return SMC_CLC_DECL_RELEASEERR;
+
+	if (fce->release < SMC_RELEASE_1)
+		return 0;
+
+	return 0;
+}
+
 void smc_clc_get_hostname(u8 **host)
 {
 	*host = &smc_hostname[0];
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index bd75382f374d5..552d0656252c4 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -45,6 +45,7 @@
 #define SMC_CLC_DECL_NOSEID	0x03030006  /* peer sent no SEID	      */
 #define SMC_CLC_DECL_NOSMCD2DEV	0x03030007  /* no SMC-Dv2 device found	      */
 #define SMC_CLC_DECL_NOUEID	0x03030008  /* peer sent no UEID	      */
+#define SMC_CLC_DECL_RELEASEERR	0x03030009  /* release version negotiate failed */
 #define SMC_CLC_DECL_MODEUNSUPP	0x03040000  /* smc modes do not match (R or D)*/
 #define SMC_CLC_DECL_RMBE_EC	0x03050000  /* peer has eyecatcher in RMBE    */
 #define SMC_CLC_DECL_OPTUNSUPP	0x03060000  /* fastopen sockopt not supported */
@@ -415,6 +416,12 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
 			 u8 version, u8 *eid, struct smc_init_info *ini);
 int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact,
 			u8 version, u8 *negotiated_eid, struct smc_init_info *ini);
+int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
+				      struct smc_init_info *ini);
+int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
+				       struct smc_init_info *ini);
+int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
+				       struct smc_init_info *ini);
 void smc_clc_init(void) __init;
 void smc_clc_exit(void);
 void smc_clc_get_hostname(u8 **host);
-- 
GitLab


From 7f0620b9940b3b4c5d83a815d46b97ac0b88a595 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 17 Aug 2023 21:20:30 +0800
Subject: [PATCH 1348/1806] net/smc: support max connections per lgr
 negotiation

Support max connections per lgr negotiation for SMCR v2.1,
which is one of smc v2.1 features. Server makes decision for
the final value of max conns based on the client preferred
max conns and self-preferred max conns. Here use the minimum
value of client preferred max conns and server preferred max
conns.

Client                                     Server
     Proposal(max conns(client preferred))
     ------------------------------------>

     Accept(max conns(accepted value))
accepted value=min(client preferred, server preferred)
     <-----------------------------------

     Confirm(max conns(accepted value))
     ----------------------------------->

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c   |  1 +
 net/smc/smc_clc.c  | 38 ++++++++++++++++++++++++++++++++++++--
 net/smc/smc_clc.h  |  7 +++++--
 net/smc/smc_core.c |  4 +++-
 net/smc/smc_core.h | 12 ++++++++++++
 net/smc/smc_llc.c  |  6 +++++-
 6 files changed, 62 insertions(+), 6 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 337303b2a64ec..9a72eb8d30386 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1242,6 +1242,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	memcpy(ini->peer_systemid, aclc->r0.lcl.id_for_peer, SMC_SYSTEMID_LEN);
 	memcpy(ini->peer_gid, aclc->r0.lcl.gid, SMC_GID_SIZE);
 	memcpy(ini->peer_mac, aclc->r0.lcl.mac, ETH_ALEN);
+	ini->max_conns = SMC_CONN_PER_LGR_MAX;
 
 	reason_code = smc_connect_rdma_v2_prepare(smc, aclc, ini);
 	if (reason_code)
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 0232f189dad95..c88f5e2e65a27 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -427,9 +427,17 @@ static int smc_clc_fill_fce(struct smc_clc_first_contact_ext_v2x *fce,
 	fce->fce_v2_base.os_type = SMC_CLC_OS_LINUX;
 	fce->fce_v2_base.release = ini->release_nr;
 	memcpy(fce->fce_v2_base.hostname, smc_hostname, sizeof(smc_hostname));
-	if (ini->is_smcd && ini->release_nr < SMC_RELEASE_1)
+	if (ini->is_smcd && ini->release_nr < SMC_RELEASE_1) {
 		ret = sizeof(struct smc_clc_first_contact_ext);
+		goto out;
+	}
+
+	if (ini->release_nr >= SMC_RELEASE_1) {
+		if (!ini->is_smcd)
+			fce->max_conns = ini->max_conns;
+	}
 
+out:
 	return ret;
 }
 
@@ -931,8 +939,10 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 				sizeof(struct smc_clc_smcd_gid_chid);
 		}
 	}
-	if (smcr_indicated(ini->smc_type_v2))
+	if (smcr_indicated(ini->smc_type_v2)) {
 		memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE);
+		v2_ext->max_conns = SMC_CONN_PER_LGR_PREFER;
+	}
 
 	pclc_base->hdr.length = htons(plen);
 	memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
@@ -1163,6 +1173,8 @@ int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
 {
 	struct smc_clc_v2_extension *pclc_v2_ext;
 
+	ini->max_conns = SMC_CONN_PER_LGR_MAX;
+
 	if ((!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) ||
 	    ini->release_nr < SMC_RELEASE_1)
 		return 0;
@@ -1171,15 +1183,30 @@ int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
 	if (!pclc_v2_ext)
 		return SMC_CLC_DECL_NOV2EXT;
 
+	if (ini->smcr_version & SMC_V2) {
+		ini->max_conns = min_t(u8, pclc_v2_ext->max_conns, SMC_CONN_PER_LGR_PREFER);
+		if (ini->max_conns < SMC_CONN_PER_LGR_MIN)
+			return SMC_CLC_DECL_MAXCONNERR;
+	}
+
 	return 0;
 }
 
 int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
 				       struct smc_init_info *ini)
 {
+	struct smc_clc_first_contact_ext_v2x *fce_v2x =
+		(struct smc_clc_first_contact_ext_v2x *)fce;
+
 	if (ini->release_nr < SMC_RELEASE_1)
 		return 0;
 
+	if (!ini->is_smcd) {
+		if (fce_v2x->max_conns < SMC_CONN_PER_LGR_MIN)
+			return SMC_CLC_DECL_MAXCONNERR;
+		ini->max_conns = fce_v2x->max_conns;
+	}
+
 	return 0;
 }
 
@@ -1190,6 +1217,8 @@ int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
 		(struct smc_clc_msg_accept_confirm_v2 *)cclc;
 	struct smc_clc_first_contact_ext *fce =
 		smc_get_clc_first_contact_ext(clc_v2, ini->is_smcd);
+	struct smc_clc_first_contact_ext_v2x *fce_v2x =
+		(struct smc_clc_first_contact_ext_v2x *)fce;
 
 	if (cclc->hdr.version == SMC_V1 ||
 	    !(cclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK))
@@ -1201,6 +1230,11 @@ int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
 	if (fce->release < SMC_RELEASE_1)
 		return 0;
 
+	if (!ini->is_smcd) {
+		if (fce_v2x->max_conns != ini->max_conns)
+			return SMC_CLC_DECL_MAXCONNERR;
+	}
+
 	return 0;
 }
 
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 552d0656252c4..464b93b46047b 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -46,6 +46,7 @@
 #define SMC_CLC_DECL_NOSMCD2DEV	0x03030007  /* no SMC-Dv2 device found	      */
 #define SMC_CLC_DECL_NOUEID	0x03030008  /* peer sent no UEID	      */
 #define SMC_CLC_DECL_RELEASEERR	0x03030009  /* release version negotiate failed */
+#define SMC_CLC_DECL_MAXCONNERR	0x0303000a  /* max connections negotiate failed */
 #define SMC_CLC_DECL_MODEUNSUPP	0x03040000  /* smc modes do not match (R or D)*/
 #define SMC_CLC_DECL_RMBE_EC	0x03050000  /* peer has eyecatcher in RMBE    */
 #define SMC_CLC_DECL_OPTUNSUPP	0x03060000  /* fastopen sockopt not supported */
@@ -134,7 +135,8 @@ struct smc_clc_smcd_gid_chid {
 struct smc_clc_v2_extension {
 	struct smc_clnt_opts_area_hdr hdr;
 	u8 roce[16];		/* RoCEv2 GID */
-	u8 reserved[16];
+	u8 max_conns;
+	u8 reserved[15];
 	u8 user_eids[][SMC_MAX_EID_LEN];
 };
 
@@ -236,7 +238,8 @@ struct smc_clc_first_contact_ext {
 
 struct smc_clc_first_contact_ext_v2x {
 	struct smc_clc_first_contact_ext fce_v2_base;
-	u8 reserved3[4];
+	u8 max_conns; /* for SMC-R only */
+	u8 reserved3[3];
 	__be32 vendor_exp_options;
 	u8 reserved4[8];
 } __packed;		/* format defined in
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 6b78075404d7d..8c69cbb70f6e2 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -895,9 +895,11 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 			lgr->uses_gateway = ini->smcrv2.uses_gateway;
 			memcpy(lgr->nexthop_mac, ini->smcrv2.nexthop_mac,
 			       ETH_ALEN);
+			lgr->max_conns = ini->max_conns;
 		} else {
 			ibdev = ini->ib_dev;
 			ibport = ini->ib_port;
+			lgr->max_conns = SMC_CONN_PER_LGR_MAX;
 		}
 		memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1],
 		       SMC_MAX_PNETID_LEN);
@@ -1888,7 +1890,7 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 		    (ini->smcd_version == SMC_V2 ||
 		     lgr->vlan_id == ini->vlan_id) &&
 		    (role == SMC_CLNT || ini->is_smcd ||
-		    (lgr->conns_num < SMC_RMBS_PER_LGR_MAX &&
+		    (lgr->conns_num < lgr->max_conns &&
 		      !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) {
 			/* link group found */
 			ini->first_contact_local = 0;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index b6c68db61f238..32b199477ef3b 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -22,6 +22,15 @@
 #include "smc_ib.h"
 
 #define SMC_RMBS_PER_LGR_MAX	255	/* max. # of RMBs per link group */
+#define SMC_CONN_PER_LGR_MIN	16	/* min. # of connections per link group */
+#define SMC_CONN_PER_LGR_MAX	255	/* max. # of connections per link group,
+					 * also is the default value for SMC-R v1 and v2.0
+					 */
+#define SMC_CONN_PER_LGR_PREFER	255	/* Preferred connections per link group used for
+					 * SMC-R v2.1 and later negotiation, vendors or
+					 * distrubutions may modify it to a value between
+					 * 16-255 as needed.
+					 */
 
 struct smc_lgr_list {			/* list of link group definition */
 	struct list_head	list;
@@ -331,6 +340,8 @@ struct smc_link_group {
 			__be32			saddr;
 						/* net namespace */
 			struct net		*net;
+			u8			max_conns;
+						/* max conn can be assigned to lgr */
 		};
 		struct { /* SMC-D */
 			u64			peer_gid;
@@ -375,6 +386,7 @@ struct smc_init_info {
 	u8			smc_type_v1;
 	u8			smc_type_v2;
 	u8			release_nr;
+	u8			max_conns;
 	u8			first_contact_peer;
 	u8			first_contact_local;
 	unsigned short		vlan_id;
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 90f0b60b196ab..5347b62f15183 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -52,7 +52,8 @@ struct smc_llc_msg_confirm_link {	/* type 0x01 */
 	u8 link_num;
 	u8 link_uid[SMC_LGR_ID_SIZE];
 	u8 max_links;
-	u8 reserved[9];
+	u8 max_conns;
+	u8 reserved[8];
 };
 
 #define SMC_LLC_FLAG_ADD_LNK_REJ	0x40
@@ -472,6 +473,9 @@ int smc_llc_send_confirm_link(struct smc_link *link,
 	confllc->link_num = link->link_id;
 	memcpy(confllc->link_uid, link->link_uid, SMC_LGR_ID_SIZE);
 	confllc->max_links = SMC_LLC_ADD_LNK_MAX_LINKS;
+	if (link->lgr->smc_version == SMC_V2 &&
+	    link->lgr->peer_smc_release >= SMC_RELEASE_1)
+		confllc->max_conns = link->lgr->max_conns;
 	/* send llc message */
 	rc = smc_wr_tx_send(link, pend);
 put_out:
-- 
GitLab


From 69b888e3bb4b186ec597a368bc8348e0e4bc6e65 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 17 Aug 2023 21:20:31 +0800
Subject: [PATCH 1349/1806] net/smc: support max links per lgr negotiation in
 clc handshake

Support max links per lgr negotiation in clc handshake for SMCR v2.1,
which is one of smc v2.1 features. Server makes decision for the final
value of max links based on the client preferred max links and
self-preferred max links. Here use the minimum value of the client
preferred max links and server preferred max links.

Client                                       Server
     Proposal(max links(client preferred))
     -------------------------------------->

     Accept(max links(accepted value))
accepted value=min(client preferred, server preferred)
     <-------------------------------------

      Confirm(max links(accepted value))
     ------------------------------------->

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c   | 44 +++++++++++++++++++++++++++-----------------
 net/smc/smc_clc.c  | 17 ++++++++++++++++-
 net/smc/smc_clc.h  |  7 +++++--
 net/smc/smc_core.c |  5 +++++
 net/smc/smc_core.h | 12 ++++++++++++
 net/smc/smc_llc.c  | 21 +++++++++++++++++----
 6 files changed, 82 insertions(+), 24 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 9a72eb8d30386..c4f664fb2bcbd 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -641,20 +641,22 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc)
 	smc_llc_link_active(link);
 	smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE);
 
-	/* optional 2nd link, receive ADD LINK request from server */
-	qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME,
-			      SMC_LLC_ADD_LINK);
-	if (!qentry) {
-		struct smc_clc_msg_decline dclc;
-
-		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
-				      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
-		if (rc == -EAGAIN)
-			rc = 0; /* no DECLINE received, go with one link */
-		return rc;
+	if (link->lgr->max_links > 1) {
+		/* optional 2nd link, receive ADD LINK request from server */
+		qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME,
+				      SMC_LLC_ADD_LINK);
+		if (!qentry) {
+			struct smc_clc_msg_decline dclc;
+
+			rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
+					      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
+			if (rc == -EAGAIN)
+				rc = 0; /* no DECLINE received, go with one link */
+			return rc;
+		}
+		smc_llc_flow_qentry_clr(&link->lgr->llc_flow_lcl);
+		smc_llc_cli_add_link(link, qentry);
 	}
-	smc_llc_flow_qentry_clr(&link->lgr->llc_flow_lcl);
-	smc_llc_cli_add_link(link, qentry);
 	return 0;
 }
 
@@ -1243,6 +1245,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	memcpy(ini->peer_gid, aclc->r0.lcl.gid, SMC_GID_SIZE);
 	memcpy(ini->peer_mac, aclc->r0.lcl.mac, ETH_ALEN);
 	ini->max_conns = SMC_CONN_PER_LGR_MAX;
+	ini->max_links = SMC_LINKS_ADD_LNK_MAX;
 
 	reason_code = smc_connect_rdma_v2_prepare(smc, aclc, ini);
 	if (reason_code)
@@ -1887,10 +1890,12 @@ static int smcr_serv_conf_first_link(struct smc_sock *smc)
 	smc_llc_link_active(link);
 	smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE);
 
-	down_write(&link->lgr->llc_conf_mutex);
-	/* initial contact - try to establish second link */
-	smc_llc_srv_add_link(link, NULL);
-	up_write(&link->lgr->llc_conf_mutex);
+	if (link->lgr->max_links > 1) {
+		down_write(&link->lgr->llc_conf_mutex);
+		/* initial contact - try to establish second link */
+		smc_llc_srv_add_link(link, NULL);
+		up_write(&link->lgr->llc_conf_mutex);
+	}
 	return 0;
 }
 
@@ -2494,6 +2499,11 @@ static void smc_listen_work(struct work_struct *work)
 		goto out_decl;
 	}
 
+	/* fce smc release version is needed in smc_listen_rdma_finish,
+	 * so save fce info here.
+	 */
+	smc_conn_save_peer_info_fce(new_smc, cclc);
+
 	/* finish worker */
 	if (!ini->is_smcd) {
 		rc = smc_listen_rdma_finish(new_smc, cclc,
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index c88f5e2e65a27..8deb46c28f1d5 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -433,8 +433,10 @@ static int smc_clc_fill_fce(struct smc_clc_first_contact_ext_v2x *fce,
 	}
 
 	if (ini->release_nr >= SMC_RELEASE_1) {
-		if (!ini->is_smcd)
+		if (!ini->is_smcd) {
 			fce->max_conns = ini->max_conns;
+			fce->max_links = ini->max_links;
+		}
 	}
 
 out:
@@ -942,6 +944,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 	if (smcr_indicated(ini->smc_type_v2)) {
 		memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE);
 		v2_ext->max_conns = SMC_CONN_PER_LGR_PREFER;
+		v2_ext->max_links = SMC_LINKS_PER_LGR_MAX_PREFER;
 	}
 
 	pclc_base->hdr.length = htons(plen);
@@ -1174,6 +1177,7 @@ int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
 	struct smc_clc_v2_extension *pclc_v2_ext;
 
 	ini->max_conns = SMC_CONN_PER_LGR_MAX;
+	ini->max_links = SMC_LINKS_ADD_LNK_MAX;
 
 	if ((!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) ||
 	    ini->release_nr < SMC_RELEASE_1)
@@ -1187,6 +1191,10 @@ int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
 		ini->max_conns = min_t(u8, pclc_v2_ext->max_conns, SMC_CONN_PER_LGR_PREFER);
 		if (ini->max_conns < SMC_CONN_PER_LGR_MIN)
 			return SMC_CLC_DECL_MAXCONNERR;
+
+		ini->max_links = min_t(u8, pclc_v2_ext->max_links, SMC_LINKS_PER_LGR_MAX_PREFER);
+		if (ini->max_links < SMC_LINKS_ADD_LNK_MIN)
+			return SMC_CLC_DECL_MAXLINKERR;
 	}
 
 	return 0;
@@ -1205,6 +1213,11 @@ int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
 		if (fce_v2x->max_conns < SMC_CONN_PER_LGR_MIN)
 			return SMC_CLC_DECL_MAXCONNERR;
 		ini->max_conns = fce_v2x->max_conns;
+
+		if (fce_v2x->max_links > SMC_LINKS_ADD_LNK_MAX ||
+		    fce_v2x->max_links < SMC_LINKS_ADD_LNK_MIN)
+			return SMC_CLC_DECL_MAXLINKERR;
+		ini->max_links = fce_v2x->max_links;
 	}
 
 	return 0;
@@ -1233,6 +1246,8 @@ int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
 	if (!ini->is_smcd) {
 		if (fce_v2x->max_conns != ini->max_conns)
 			return SMC_CLC_DECL_MAXCONNERR;
+		if (fce_v2x->max_links != ini->max_links)
+			return SMC_CLC_DECL_MAXLINKERR;
 	}
 
 	return 0;
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 464b93b46047b..c5c8e7db775a7 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -47,6 +47,7 @@
 #define SMC_CLC_DECL_NOUEID	0x03030008  /* peer sent no UEID	      */
 #define SMC_CLC_DECL_RELEASEERR	0x03030009  /* release version negotiate failed */
 #define SMC_CLC_DECL_MAXCONNERR	0x0303000a  /* max connections negotiate failed */
+#define SMC_CLC_DECL_MAXLINKERR	0x0303000b  /* max links negotiate failed */
 #define SMC_CLC_DECL_MODEUNSUPP	0x03040000  /* smc modes do not match (R or D)*/
 #define SMC_CLC_DECL_RMBE_EC	0x03050000  /* peer has eyecatcher in RMBE    */
 #define SMC_CLC_DECL_OPTUNSUPP	0x03060000  /* fastopen sockopt not supported */
@@ -136,7 +137,8 @@ struct smc_clc_v2_extension {
 	struct smc_clnt_opts_area_hdr hdr;
 	u8 roce[16];		/* RoCEv2 GID */
 	u8 max_conns;
-	u8 reserved[15];
+	u8 max_links;
+	u8 reserved[14];
 	u8 user_eids[][SMC_MAX_EID_LEN];
 };
 
@@ -239,7 +241,8 @@ struct smc_clc_first_contact_ext {
 struct smc_clc_first_contact_ext_v2x {
 	struct smc_clc_first_contact_ext fce_v2_base;
 	u8 max_conns; /* for SMC-R only */
-	u8 reserved3[3];
+	u8 max_links; /* for SMC-R only */
+	u8 reserved3[2];
 	__be32 vendor_exp_options;
 	u8 reserved4[8];
 } __packed;		/* format defined in
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 8c69cbb70f6e2..aae8d3f5c3cf4 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -896,10 +896,12 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 			memcpy(lgr->nexthop_mac, ini->smcrv2.nexthop_mac,
 			       ETH_ALEN);
 			lgr->max_conns = ini->max_conns;
+			lgr->max_links = ini->max_links;
 		} else {
 			ibdev = ini->ib_dev;
 			ibport = ini->ib_port;
 			lgr->max_conns = SMC_CONN_PER_LGR_MAX;
+			lgr->max_links = SMC_LINKS_ADD_LNK_MAX;
 		}
 		memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1],
 		       SMC_MAX_PNETID_LEN);
@@ -1666,6 +1668,9 @@ void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport)
 		    !rdma_dev_access_netns(smcibdev->ibdev, lgr->net))
 			continue;
 
+		if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1)
+			continue;
+
 		/* trigger local add link processing */
 		link = smc_llc_usable_link(lgr);
 		if (link)
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 32b199477ef3b..120027d404692 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -173,6 +173,15 @@ struct smc_link {
  */
 #define SMC_LINKS_PER_LGR_MAX	3
 #define SMC_SINGLE_LINK		0
+#define SMC_LINKS_ADD_LNK_MIN	1	/* min. # of links per link group */
+#define SMC_LINKS_ADD_LNK_MAX	2	/* max. # of links per link group, also is the
+					 * default value for smc-r v1.0 and v2.0
+					 */
+#define SMC_LINKS_PER_LGR_MAX_PREFER	2	/* Preferred max links per link group used for
+						 * SMC-R v2.1 and later negotiation, vendors or
+						 * distrubutions may modify it to a value between
+						 * 1-2 as needed.
+						 */
 
 /* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */
 struct smc_buf_desc {
@@ -342,6 +351,8 @@ struct smc_link_group {
 			struct net		*net;
 			u8			max_conns;
 						/* max conn can be assigned to lgr */
+			u8			max_links;
+						/* max links can be added in lgr */
 		};
 		struct { /* SMC-D */
 			u64			peer_gid;
@@ -387,6 +398,7 @@ struct smc_init_info {
 	u8			smc_type_v2;
 	u8			release_nr;
 	u8			max_conns;
+	u8			max_links;
 	u8			first_contact_peer;
 	u8			first_contact_local;
 	unsigned short		vlan_id;
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 5347b62f15183..018ce8133b026 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -59,8 +59,6 @@ struct smc_llc_msg_confirm_link {	/* type 0x01 */
 #define SMC_LLC_FLAG_ADD_LNK_REJ	0x40
 #define SMC_LLC_REJ_RSN_NO_ALT_PATH	1
 
-#define SMC_LLC_ADD_LNK_MAX_LINKS	2
-
 struct smc_llc_msg_add_link {		/* type 0x02 */
 	struct smc_llc_hdr hd;
 	u8 sender_mac[ETH_ALEN];
@@ -472,10 +470,12 @@ int smc_llc_send_confirm_link(struct smc_link *link,
 	hton24(confllc->sender_qp_num, link->roce_qp->qp_num);
 	confllc->link_num = link->link_id;
 	memcpy(confllc->link_uid, link->link_uid, SMC_LGR_ID_SIZE);
-	confllc->max_links = SMC_LLC_ADD_LNK_MAX_LINKS;
+	confllc->max_links = SMC_LINKS_ADD_LNK_MAX;
 	if (link->lgr->smc_version == SMC_V2 &&
-	    link->lgr->peer_smc_release >= SMC_RELEASE_1)
+	    link->lgr->peer_smc_release >= SMC_RELEASE_1) {
 		confllc->max_conns = link->lgr->max_conns;
+		confllc->max_links = link->lgr->max_links;
+	}
 	/* send llc message */
 	rc = smc_wr_tx_send(link, pend);
 put_out:
@@ -1045,6 +1045,11 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry)
 		goto out_reject;
 	}
 
+	if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1) {
+		rc = 0;
+		goto out_reject;
+	}
+
 	ini->vlan_id = lgr->vlan_id;
 	if (lgr->smc_version == SMC_V2) {
 		ini->check_smcrv2 = true;
@@ -1169,6 +1174,9 @@ static void smc_llc_cli_add_link_invite(struct smc_link *link,
 	    lgr->type == SMC_LGR_ASYMMETRIC_PEER)
 		goto out;
 
+	if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1)
+		goto out;
+
 	ini = kzalloc(sizeof(*ini), GFP_KERNEL);
 	if (!ini)
 		goto out;
@@ -1414,6 +1422,11 @@ int smc_llc_srv_add_link(struct smc_link *link,
 		goto out;
 	}
 
+	if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1) {
+		rc = 0;
+		goto out;
+	}
+
 	/* ignore client add link recommendation, start new flow */
 	ini->vlan_id = lgr->vlan_id;
 	if (lgr->smc_version == SMC_V2) {
-- 
GitLab


From bbed596c74a527e0d0d30bc56732f26407f12d6e Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Thu, 17 Aug 2023 21:20:32 +0800
Subject: [PATCH 1350/1806] net/smc: Extend SMCR v2 linkgroup netlink attribute

Add SMC_NLA_LGR_R_V2_MAX_CONNS and SMC_NLA_LGR_R_V2_MAX_LINKS
to SMCR v2 linkgroup netlink attribute SMC_NLA_LGR_R_V2 for
linkgroup's detail info showing.

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/smc.h | 2 ++
 net/smc/smc_core.c       | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h
index bb4dacca31e74..837fcd4b0abcc 100644
--- a/include/uapi/linux/smc.h
+++ b/include/uapi/linux/smc.h
@@ -107,6 +107,8 @@ enum {
 enum {
 	SMC_NLA_LGR_R_V2_UNSPEC,
 	SMC_NLA_LGR_R_V2_DIRECT,	/* u8 */
+	SMC_NLA_LGR_R_V2_MAX_CONNS,	/* u8 */
+	SMC_NLA_LGR_R_V2_MAX_LINKS,	/* u8 */
 	__SMC_NLA_LGR_R_V2_MAX,
 	SMC_NLA_LGR_R_V2_MAX = __SMC_NLA_LGR_R_V2_MAX - 1
 };
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index aae8d3f5c3cf4..bd01dd31e4bd7 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -319,6 +319,10 @@ static int smc_nl_fill_smcr_lgr_v2(struct smc_link_group *lgr,
 		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_DIRECT, !lgr->uses_gateway))
 		goto errv2attr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_CONNS, lgr->max_conns))
+		goto errv2attr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_LINKS, lgr->max_links))
+		goto errv2attr;
 
 	nla_nest_end(skb, v2_attrs);
 	return 0;
-- 
GitLab


From 4025d3e73abde4f65f4b04d4b1d8449b00e31473 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 18 Aug 2023 09:40:39 +0000
Subject: [PATCH 1351/1806] net: add skb_queue_purge_reason and
 __skb_queue_purge_reason

skb_queue_purge() and __skb_queue_purge() become wrappers
around the new generic functions.

New SKB_DROP_REASON_QUEUE_PURGE drop reason is added,
but users can start adding more specific reasons.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h        | 23 +++++++++++++++++++----
 include/net/dropreason-core.h |  3 +++
 net/core/skbuff.c             | 11 +++++++----
 3 files changed, 29 insertions(+), 8 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index aa57e2eca33be..9aec136bc6901 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3149,20 +3149,35 @@ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask)
 }
 
 /**
- *	__skb_queue_purge - empty a list
+ *	__skb_queue_purge_reason - empty a list
  *	@list: list to empty
+ *	@reason: drop reason
  *
  *	Delete all buffers on an &sk_buff list. Each buffer is removed from
  *	the list and one reference dropped. This function does not take the
  *	list lock and the caller must hold the relevant locks to use it.
  */
-static inline void __skb_queue_purge(struct sk_buff_head *list)
+static inline void __skb_queue_purge_reason(struct sk_buff_head *list,
+					    enum skb_drop_reason reason)
 {
 	struct sk_buff *skb;
+
 	while ((skb = __skb_dequeue(list)) != NULL)
-		kfree_skb(skb);
+		kfree_skb_reason(skb, reason);
+}
+
+static inline void __skb_queue_purge(struct sk_buff_head *list)
+{
+	__skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE);
+}
+
+void skb_queue_purge_reason(struct sk_buff_head *list,
+			    enum skb_drop_reason reason);
+
+static inline void skb_queue_purge(struct sk_buff_head *list)
+{
+	skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE);
 }
-void skb_queue_purge(struct sk_buff_head *list);
 
 unsigned int skb_rbtree_purge(struct rb_root *root);
 
diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index f291a3b0f9e51..a587e83fc1694 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -79,6 +79,7 @@
 	FN(IPV6_NDISC_BAD_CODE)		\
 	FN(IPV6_NDISC_BAD_OPTIONS)	\
 	FN(IPV6_NDISC_NS_OTHERHOST)	\
+	FN(QUEUE_PURGE)			\
 	FNe(MAX)
 
 /**
@@ -342,6 +343,8 @@ enum skb_drop_reason {
 	 * for another host.
 	 */
 	SKB_DROP_REASON_IPV6_NDISC_NS_OTHERHOST,
+	/** @SKB_DROP_REASON_QUEUE_PURGE: bulk free. */
+	SKB_DROP_REASON_QUEUE_PURGE,
 	/**
 	 * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which
 	 * shouldn't be used as a real 'reason' - only for tracing code gen
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9b5bc621daf74..117d36b1fae3e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3701,20 +3701,23 @@ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list)
 EXPORT_SYMBOL(skb_dequeue_tail);
 
 /**
- *	skb_queue_purge - empty a list
+ *	skb_queue_purge_reason - empty a list
  *	@list: list to empty
+ *	@reason: drop reason
  *
  *	Delete all buffers on an &sk_buff list. Each buffer is removed from
  *	the list and one reference dropped. This function takes the list
  *	lock and is atomic with respect to other list locking functions.
  */
-void skb_queue_purge(struct sk_buff_head *list)
+void skb_queue_purge_reason(struct sk_buff_head *list,
+			    enum skb_drop_reason reason)
 {
 	struct sk_buff *skb;
+
 	while ((skb = skb_dequeue(list)) != NULL)
-		kfree_skb(skb);
+		kfree_skb_reason(skb, reason);
 }
-EXPORT_SYMBOL(skb_queue_purge);
+EXPORT_SYMBOL(skb_queue_purge_reason);
 
 /**
  *	skb_rbtree_purge - empty a skb rbtree
-- 
GitLab


From 58f2ffdedf7b05b318f2cdafaca69e4435c8478e Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Fri, 18 Aug 2023 13:14:01 +0200
Subject: [PATCH 1352/1806] stmmac: intel: Enable correction of MAC propagation
 delay

All captured timestamps should be corrected by PHY, MAC and CDC introduced
latency/errors. The CDC correction is already used. Enable MAC propagation delay
correction as well which is available since commit 26cfb838aa00 ("net: stmmac:
correct MAC propagation delay").

Before:
|ptp4l[390.458]: rms    7 max   21 freq   +177 +/-  14 delay   357 +/-   1

After:
|ptp4l[620.012]: rms    7 max   20 freq   +195 +/-  14 delay   345 +/-   1

Tested on Intel Elkhart Lake.

Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Johannes Zink <j.zink@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 979c755964b14..a3a249c635981 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -627,6 +627,7 @@ static int ehl_common_data(struct pci_dev *pdev,
 	plat->rx_queues_to_use = 8;
 	plat->tx_queues_to_use = 8;
 	plat->flags |= STMMAC_FLAG_USE_PHY_WOL;
+	plat->flags |= STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY;
 
 	plat->safety_feat_cfg->tsoee = 1;
 	plat->safety_feat_cfg->mrxpee = 1;
-- 
GitLab


From f65f305ae0089fd74174d24dd32241ffe53a8d46 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 18 Aug 2023 13:19:27 +0200
Subject: [PATCH 1353/1806] tools: ynl-gen: use temporary file for rendering

Currently any error during render leads to output an empty file.
That is quite annoying when using tools/net/ynl/ynl-regen.sh
which git greps files with content of "YNL-GEN.." and therefore ignores
empty files. So once you fail to regen, you have to checkout the file.

Avoid that by rendering to a temporary file first, only at the end
copy the content to the actual destination.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/net/ynl/ynl-gen-c.py | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 5f39d24906551..bdff8dfc29c94 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -5,6 +5,8 @@ import argparse
 import collections
 import os
 import re
+import shutil
+import tempfile
 import yaml
 
 from lib import SpecFamily, SpecAttrSet, SpecAttr, SpecOperation, SpecEnumSet, SpecEnumEntry
@@ -2304,7 +2306,7 @@ def main():
     parser.add_argument('-o', dest='out_file', type=str)
     args = parser.parse_args()
 
-    out_file = open(args.out_file, 'w+') if args.out_file else os.sys.stdout
+    tmp_file = tempfile.TemporaryFile('w+') if args.out_file else os.sys.stdout
 
     if args.header is None:
         parser.error("--header or --source is required")
@@ -2329,7 +2331,7 @@ def main():
         print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation')
         os.sys.exit(1)
 
-    cw = CodeWriter(BaseNlLib(), out_file)
+    cw = CodeWriter(BaseNlLib(), tmp_file)
 
     _, spec_kernel = find_kernel_root(args.spec)
     if args.mode == 'uapi' or args.header:
@@ -2578,6 +2580,10 @@ def main():
     if args.header:
         cw.p(f'#endif /* {hdr_prot} */')
 
+    if args.out_file:
+        out_file = open(args.out_file, 'w+')
+        tmp_file.seek(0)
+        shutil.copyfileobj(tmp_file, out_file)
 
 if __name__ == "__main__":
     main()
-- 
GitLab


From 44a696de720d6917f1d1844a05757624295b81c0 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Fri, 18 Aug 2023 12:33:24 +0100
Subject: [PATCH 1354/1806] net: mdio: xgene: remove useless xgene_mdio_status

xgene_mdio_status is declared static, and is only written once by the
driver. It appears to have been this way since the driver was first
added to the kernel tree. No other users can be found, so let's remove
it.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/mdio/mdio-xgene.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/mdio/mdio-xgene.c b/drivers/net/mdio/mdio-xgene.c
index 1af7a4d9f86c4..1190a793555a2 100644
--- a/drivers/net/mdio/mdio-xgene.c
+++ b/drivers/net/mdio/mdio-xgene.c
@@ -20,8 +20,6 @@
 #include <linux/prefetch.h>
 #include <net/ip.h>
 
-static bool xgene_mdio_status;
-
 u32 xgene_mdio_rd_mac(struct xgene_mdio_pdata *pdata, u32 rd_addr)
 {
 	void __iomem *addr, *rd, *cmd, *cmd_done;
@@ -421,7 +419,6 @@ static int xgene_mdio_probe(struct platform_device *pdev)
 		goto out_mdiobus;
 
 	pdata->mdio_bus = mdio_bus;
-	xgene_mdio_status = true;
 
 	return 0;
 
-- 
GitLab


From 093db9cda7b695f963cd7b468ed1488063548ce2 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Fri, 18 Aug 2023 13:05:03 +0800
Subject: [PATCH 1355/1806] net: microchip: vcap api: Always return ERR_PTR for
 vcap_get_rule()

As Simon Horman suggests, update vcap_get_rule() to always
return an ERR_PTR() and update the error detection conditions to
use IS_ERR(), which would be more cleaner in this case.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Suggested-by: Simon Horman <horms@kernel.org>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/vcap/vcap_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c
index a7b43f99bc808..300fe1a93dce8 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_api.c
+++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c
@@ -2429,7 +2429,7 @@ struct vcap_rule *vcap_get_rule(struct vcap_control *vctrl, u32 id)
 
 	elem = vcap_get_locked_rule(vctrl, id);
 	if (!elem)
-		return NULL;
+		return ERR_PTR(-ENOENT);
 
 	rule = vcap_decode_rule(elem);
 	mutex_unlock(&elem->admin->lock);
-- 
GitLab


From ab104318f63997113b0ce7ac288e51359925ed79 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Fri, 18 Aug 2023 13:05:04 +0800
Subject: [PATCH 1356/1806] net: lan966x: Fix return value check for
 vcap_get_rule()

As Simon Horman suggests, update vcap_get_rule() to always
return an ERR_PTR() and update the error detection conditions to
use IS_ERR(), so use IS_ERR() to fix the return value issue.

Fixes: 72df3489fb10 ("net: lan966x: Add ptp trap rules")
Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Suggested-by: Simon Horman <horms@kernel.org>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
index 60bd0cff66770..63905bb5a63a8 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
@@ -59,7 +59,7 @@ static int lan966x_ptp_add_trap(struct lan966x_port *port,
 	int err;
 
 	vrule = vcap_get_rule(lan966x->vcap_ctrl, rule_id);
-	if (vrule) {
+	if (!IS_ERR(vrule)) {
 		u32 value, mask;
 
 		/* Just modify the ingress port mask and exit */
@@ -106,7 +106,7 @@ static int lan966x_ptp_del_trap(struct lan966x_port *port,
 	int err;
 
 	vrule = vcap_get_rule(lan966x->vcap_ctrl, rule_id);
-	if (!vrule)
+	if (IS_ERR(vrule))
 		return -EEXIST;
 
 	vcap_rule_get_key_u32(vrule, VCAP_KF_IF_IGR_PORT_MASK, &value, &mask);
-- 
GitLab


From 95b358e4d9c7caad3a787f810265458ee477d0ef Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Fri, 18 Aug 2023 13:05:05 +0800
Subject: [PATCH 1357/1806] net: microchip: sparx5: Update return value check
 for vcap_get_rule()

As Simon Horman suggests, update vcap_get_rule() to always
return an ERR_PTR() and update the error detection conditions to
use IS_ERR(), so use IS_ERR() to check the return value.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Suggested-by: Simon Horman <horms@kernel.org>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
index 906299ad84251..523e0c470894f 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
@@ -1274,7 +1274,7 @@ static int sparx5_tc_free_rule_resources(struct net_device *ndev,
 	int ret = 0;
 
 	vrule = vcap_get_rule(vctrl, rule_id);
-	if (!vrule || IS_ERR(vrule))
+	if (IS_ERR(vrule))
 		return -EINVAL;
 
 	sparx5_tc_free_psfp_resources(sparx5, vrule);
-- 
GitLab


From f132fdd9dc81e045bcf95005d418a31fbe9d942f Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Mon, 2 May 2022 14:40:56 +0300
Subject: [PATCH 1358/1806] macsec: add functions to get macsec real netdevice
 and check offload

Given a macsec net_device add two functions to return the real net_device
for that device, and check if that macsec device is offloaded or not.

This is needed for auxiliary drivers that implement MACsec offload, but
have flows which are triggered over the macsec net_device, this allows
the drivers in such cases to verify if the device is offloaded or not,
and to access the real device of that macsec device, which would
belong to the driver, and would be needed for the offload procedure.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Raed Salem <raeds@nvidia.com>
Reviewed-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/macsec.c | 12 ++++++++++++
 include/net/macsec.h |  2 ++
 2 files changed, 14 insertions(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 984dfa5d6c11c..4895af1c5b7b5 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -4240,6 +4240,18 @@ static struct net *macsec_get_link_net(const struct net_device *dev)
 	return dev_net(macsec_priv(dev)->real_dev);
 }
 
+struct net_device *macsec_get_real_dev(const struct net_device *dev)
+{
+	return macsec_priv(dev)->real_dev;
+}
+EXPORT_SYMBOL_GPL(macsec_get_real_dev);
+
+bool macsec_netdev_is_offloaded(struct net_device *dev)
+{
+	return macsec_is_offloaded(macsec_priv(dev));
+}
+EXPORT_SYMBOL_GPL(macsec_netdev_is_offloaded);
+
 static size_t macsec_get_size(const struct net_device *dev)
 {
 	return  nla_total_size_64bit(8) + /* IFLA_MACSEC_SCI */
diff --git a/include/net/macsec.h b/include/net/macsec.h
index 441ed8fd4b5f6..75a6f4863c837 100644
--- a/include/net/macsec.h
+++ b/include/net/macsec.h
@@ -312,6 +312,8 @@ static inline bool macsec_send_sci(const struct macsec_secy *secy)
 	return tx_sc->send_sci ||
 		(secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb);
 }
+struct net_device *macsec_get_real_dev(const struct net_device *dev);
+bool macsec_netdev_is_offloaded(struct net_device *dev);
 
 static inline void *macsec_netdev_priv(const struct net_device *dev)
 {
-- 
GitLab


From 7390762a073743f936bd1b392ec42161d9f2d23e Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Tue, 29 Nov 2022 14:50:22 +0200
Subject: [PATCH 1359/1806] net/mlx5e: Move MACsec flow steering operations to
 be used as core library

Move MACsec flow steering operations(macsec_fs) from core/en_accel to
core/lib, this mandates moving MACsec statistics structure from the
general MACsec code header(en_accel/macsec.h) to macsec_fs header to
remove macsec_fs.h dependency over en_accel/macsec.h.

This to lay the ground for RoCE MACsec by moving all the data
that will need to be accessed by both ethernet MACsec and
RoCE MACsec to be shared at core.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/Kconfig   |  2 +-
 .../net/ethernet/mellanox/mlx5/core/Makefile  |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  2 +-
 .../mellanox/mlx5/core/en_accel/en_accel.h    |  4 ++--
 .../mellanox/mlx5/core/en_accel/macsec.c      |  1 -
 .../mellanox/mlx5/core/en_accel/macsec.h      | 22 +++----------------
 .../ethernet/mellanox/mlx5/core/en_stats.c    |  2 +-
 .../mlx5/core/{en_accel => lib}/macsec_fs.c   |  2 +-
 .../mlx5/core/{en_accel => lib}/macsec_fs.h   | 19 ++++++++++++++--
 9 files changed, 27 insertions(+), 29 deletions(-)
 rename drivers/net/ethernet/mellanox/mlx5/core/{en_accel => lib}/macsec_fs.c (99%)
 rename drivers/net/ethernet/mellanox/mlx5/core/{en_accel => lib}/macsec_fs.h (65%)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index bb1d7b039a7e5..f3b284db1b5bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -139,7 +139,7 @@ config MLX5_CORE_IPOIB
 	help
 	  MLX5 IPoIB offloads & acceleration support.
 
-config MLX5_EN_MACSEC
+config MLX5_MACSEC
 	bool "Connect-X support for MACSec offload"
 	depends on MLX5_CORE_EN
 	depends on MACSEC
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 35f00700a4d6c..ade063b57cd50 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -94,7 +94,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib
 #
 mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o
 
-mlx5_core-$(CONFIG_MLX5_EN_MACSEC) += en_accel/macsec.o en_accel/macsec_fs.o \
+mlx5_core-$(CONFIG_MLX5_MACSEC) += en_accel/macsec.o lib/macsec_fs.o \
 				      en_accel/macsec_stats.o
 
 mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index b1807bfb815f1..b82217de9e9f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -917,7 +917,7 @@ struct mlx5e_priv {
 
 	const struct mlx5e_profile *profile;
 	void                      *ppriv;
-#ifdef CONFIG_MLX5_EN_MACSEC
+#ifdef CONFIG_MLX5_MACSEC
 	struct mlx5e_macsec       *macsec;
 #endif
 #ifdef CONFIG_MLX5_EN_IPSEC
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index bac4717548c67..caa34b9c161e5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -138,7 +138,7 @@ static inline bool mlx5e_accel_tx_begin(struct net_device *dev,
 	}
 #endif
 
-#ifdef CONFIG_MLX5_EN_MACSEC
+#ifdef CONFIG_MLX5_MACSEC
 	if (unlikely(mlx5e_macsec_skb_is_offload(skb))) {
 		struct mlx5e_priv *priv = netdev_priv(dev);
 
@@ -173,7 +173,7 @@ static inline void mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
 		mlx5e_ipsec_tx_build_eseg(priv, skb, eseg);
 #endif
 
-#ifdef CONFIG_MLX5_EN_MACSEC
+#ifdef CONFIG_MLX5_MACSEC
 	if (unlikely(mlx5e_macsec_skb_is_offload(skb)))
 		mlx5e_macsec_tx_build_eseg(priv->macsec, skb, eseg);
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index 592b165530ffa..b26044efdec6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -10,7 +10,6 @@
 #include "lib/aso.h"
 #include "lib/crypto.h"
 #include "en_accel/macsec.h"
-#include "en_accel/macsec_fs.h"
 
 #define MLX5_MACSEC_EPN_SCOPE_MID 0x80000000L
 #define MLX5E_MACSEC_ASO_CTX_SZ MLX5_ST_SZ_BYTES(macsec_aso)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
index 347380a2cd9c7..1f9c4a2723b2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
@@ -4,32 +4,16 @@
 #ifndef __MLX5_EN_ACCEL_MACSEC_H__
 #define __MLX5_EN_ACCEL_MACSEC_H__
 
-#ifdef CONFIG_MLX5_EN_MACSEC
+#ifdef CONFIG_MLX5_MACSEC
 
 #include <linux/mlx5/driver.h>
 #include <net/macsec.h>
 #include <net/dst_metadata.h>
-
-/* Bit31 - 30: MACsec marker, Bit15-0: MACsec id */
-#define MLX5_MACEC_RX_FS_ID_MAX USHRT_MAX /* Must be power of two */
-#define MLX5_MACSEC_RX_FS_ID_MASK MLX5_MACEC_RX_FS_ID_MAX
-#define MLX5_MACSEC_METADATA_MARKER(metadata)  ((((metadata) >> 30) & 0x3)  == 0x1)
-#define MLX5_MACSEC_RX_METADAT_HANDLE(metadata)  ((metadata) & MLX5_MACSEC_RX_FS_ID_MASK)
+#include "lib/macsec_fs.h"
 
 struct mlx5e_priv;
 struct mlx5e_macsec;
 
-struct mlx5e_macsec_stats {
-	u64 macsec_rx_pkts;
-	u64 macsec_rx_bytes;
-	u64 macsec_rx_pkts_drop;
-	u64 macsec_rx_bytes_drop;
-	u64 macsec_tx_pkts;
-	u64 macsec_tx_bytes;
-	u64 macsec_tx_pkts_drop;
-	u64 macsec_tx_bytes_drop;
-};
-
 void mlx5e_macsec_build_netdev(struct mlx5e_priv *priv);
 int mlx5e_macsec_init(struct mlx5e_priv *priv);
 void mlx5e_macsec_cleanup(struct mlx5e_priv *priv);
@@ -68,6 +52,6 @@ static inline void mlx5e_macsec_offload_handle_rx_skb(struct net_device *netdev,
 						      struct mlx5_cqe64 *cqe)
 {}
 static inline bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev) { return false; }
-#endif  /* CONFIG_MLX5_EN_MACSEC */
+#endif  /* CONFIG_MLX5_MACSEC */
 
 #endif	/* __MLX5_ACCEL_EN_MACSEC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 4d77055abd4be..8d7a5a8151629 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -2490,7 +2490,7 @@ mlx5e_stats_grp_t mlx5e_nic_stats_grps[] = {
 	&MLX5E_STATS_GRP(per_port_buff_congest),
 	&MLX5E_STATS_GRP(ptp),
 	&MLX5E_STATS_GRP(qos),
-#ifdef CONFIG_MLX5_EN_MACSEC
+#ifdef CONFIG_MLX5_MACSEC
 	&MLX5E_STATS_GRP(macsec_hw),
 #endif
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
similarity index 99%
rename from drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c
rename to drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index 7fc901a6ec5fc..3d816ee382e3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -7,7 +7,7 @@
 #include <linux/if_vlan.h>
 #include "fs_core.h"
 #include "en/fs.h"
-#include "en_accel/macsec_fs.h"
+#include "lib/macsec_fs.h"
 #include "mlx5_core.h"
 
 /* MACsec TX flow steering */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
similarity index 65%
rename from drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.h
rename to drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
index b429648d4ee71..b282c0850e16f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
@@ -4,9 +4,13 @@
 #ifndef __MLX5_MACSEC_STEERING_H__
 #define __MLX5_MACSEC_STEERING_H__
 
-#ifdef CONFIG_MLX5_EN_MACSEC
+#ifdef CONFIG_MLX5_MACSEC
 
-#include "en_accel/macsec.h"
+/* Bit31 - 30: MACsec marker, Bit15-0: MACsec id */
+#define MLX5_MACEC_RX_FS_ID_MAX USHRT_MAX /* Must be power of two */
+#define MLX5_MACSEC_RX_FS_ID_MASK MLX5_MACEC_RX_FS_ID_MAX
+#define MLX5_MACSEC_METADATA_MARKER(metadata)  ((((metadata) >> 30) & 0x3)  == 0x1)
+#define MLX5_MACSEC_RX_METADAT_HANDLE(metadata)  ((metadata) & MLX5_MACSEC_RX_FS_ID_MASK)
 
 #define MLX5_MACSEC_NUM_OF_SUPPORTED_INTERFACES 16
 
@@ -20,6 +24,17 @@ struct mlx5_macsec_rule_attrs {
 	int action;
 };
 
+struct mlx5e_macsec_stats {
+	u64 macsec_rx_pkts;
+	u64 macsec_rx_bytes;
+	u64 macsec_rx_pkts_drop;
+	u64 macsec_rx_bytes_drop;
+	u64 macsec_tx_pkts;
+	u64 macsec_tx_bytes;
+	u64 macsec_tx_pkts_drop;
+	u64 macsec_tx_bytes_drop;
+};
+
 enum mlx5_macsec_action {
 	MLX5_ACCEL_MACSEC_ACTION_ENCRYPT,
 	MLX5_ACCEL_MACSEC_ACTION_DECRYPT,
-- 
GitLab


From 88ff18c01a0a3d2ee262c9c99979e0451af2c7af Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Mon, 1 May 2023 15:11:53 +0300
Subject: [PATCH 1360/1806] net/mlx5: Remove dependency of macsec flow steering
 on ethernet

Since macsec flow steering was moved to core, it should be independent
of all ethernet code and structures hence we remove all ethernet header
includes and redefine ethernet structs internally for macsec_fs usage
where needed.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/lib/macsec_fs.c        | 43 +++++++++++++++----
 1 file changed, 34 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index 3d816ee382e3c..40883d2b78c76 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -6,7 +6,6 @@
 #include <linux/mlx5/qp.h>
 #include <linux/if_vlan.h>
 #include "fs_core.h"
-#include "en/fs.h"
 #include "lib/macsec_fs.h"
 #include "mlx5_core.h"
 
@@ -57,8 +56,14 @@ struct mlx5e_macsec_tx_rule {
 	u32 fs_id;
 };
 
+struct mlx5_macsec_flow_table {
+	int num_groups;
+	struct mlx5_flow_table *t;
+	struct mlx5_flow_group **g;
+};
+
 struct mlx5e_macsec_tables {
-	struct mlx5e_flow_table ft_crypto;
+	struct mlx5_macsec_flow_table ft_crypto;
 	struct mlx5_flow_handle *crypto_miss_rule;
 
 	struct mlx5_flow_table *ft_check;
@@ -103,6 +108,26 @@ struct mlx5e_macsec_fs {
 	struct mlx5e_macsec_rx *rx_fs;
 };
 
+static void macsec_fs_destroy_groups(struct mlx5_macsec_flow_table *ft)
+{
+	int i;
+
+	for (i = ft->num_groups - 1; i >= 0; i--) {
+		if (!IS_ERR_OR_NULL(ft->g[i]))
+			mlx5_destroy_flow_group(ft->g[i]);
+		ft->g[i] = NULL;
+	}
+	ft->num_groups = 0;
+}
+
+static void macsec_fs_destroy_flow_table(struct mlx5_macsec_flow_table *ft)
+{
+	macsec_fs_destroy_groups(ft);
+	kfree(ft->g);
+	mlx5_destroy_flow_table(ft->t);
+	ft->t = NULL;
+}
+
 static void macsec_fs_tx_destroy(struct mlx5e_macsec_fs *macsec_fs)
 {
 	struct mlx5e_macsec_tx *tx_fs = macsec_fs->tx_fs;
@@ -142,10 +167,10 @@ static void macsec_fs_tx_destroy(struct mlx5e_macsec_fs *macsec_fs)
 		tx_tables->crypto_miss_rule = NULL;
 	}
 
-	mlx5e_destroy_flow_table(&tx_tables->ft_crypto);
+	macsec_fs_destroy_flow_table(&tx_tables->ft_crypto);
 }
 
-static int macsec_fs_tx_create_crypto_table_groups(struct mlx5e_flow_table *ft)
+static int macsec_fs_tx_create_crypto_table_groups(struct mlx5_macsec_flow_table *ft)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	int mclen = MLX5_ST_SZ_BYTES(fte_match_param);
@@ -244,7 +269,7 @@ static int macsec_fs_tx_create(struct mlx5e_macsec_fs *macsec_fs)
 	struct mlx5_flow_destination dest = {};
 	struct mlx5e_macsec_tables *tx_tables;
 	struct mlx5_flow_act flow_act = {};
-	struct mlx5e_flow_table *ft_crypto;
+	struct mlx5_macsec_flow_table *ft_crypto;
 	struct mlx5_flow_table *flow_table;
 	struct mlx5_flow_group *flow_group;
 	struct mlx5_flow_namespace *ns;
@@ -733,10 +758,10 @@ static void macsec_fs_rx_destroy(struct mlx5e_macsec_fs *macsec_fs)
 		rx_tables->crypto_miss_rule = NULL;
 	}
 
-	mlx5e_destroy_flow_table(&rx_tables->ft_crypto);
+	macsec_fs_destroy_flow_table(&rx_tables->ft_crypto);
 }
 
-static int macsec_fs_rx_create_crypto_table_groups(struct mlx5e_flow_table *ft)
+static int macsec_fs_rx_create_crypto_table_groups(struct mlx5_macsec_flow_table *ft)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	int mclen = MLX5_ST_SZ_BYTES(fte_match_param);
@@ -894,10 +919,10 @@ static int macsec_fs_rx_create(struct mlx5e_macsec_fs *macsec_fs)
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5e_macsec_rx *rx_fs = macsec_fs->rx_fs;
 	struct net_device *netdev = macsec_fs->netdev;
+	struct mlx5_macsec_flow_table *ft_crypto;
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_destination dest = {};
 	struct mlx5e_macsec_tables *rx_tables;
-	struct mlx5e_flow_table *ft_crypto;
 	struct mlx5_flow_table *flow_table;
 	struct mlx5_flow_group *flow_group;
 	struct mlx5_flow_act flow_act = {};
@@ -1122,11 +1147,11 @@ macsec_fs_rx_add_rule(struct mlx5e_macsec_fs *macsec_fs,
 	struct net_device *netdev = macsec_fs->netdev;
 	union mlx5e_macsec_rule *macsec_rule = NULL;
 	struct mlx5_modify_hdr *modify_hdr = NULL;
+	struct mlx5_macsec_flow_table *ft_crypto;
 	struct mlx5_flow_destination dest = {};
 	struct mlx5e_macsec_tables *rx_tables;
 	struct mlx5e_macsec_rx_rule *rx_rule;
 	struct mlx5_flow_act flow_act = {};
-	struct mlx5e_flow_table *ft_crypto;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
 	int err = 0;
-- 
GitLab


From 8603efbd18b091273876b72e6d9973df8b0a428a Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Tue, 29 Nov 2022 16:22:33 +0200
Subject: [PATCH 1361/1806] net/mlx5e: Rename MACsec flow steering
 functions/parameters to suit core naming style

Rename MACsec flow steering(macsec_fs) functions and parameters from
ethernet(core/en_accel) naming convention to core naming convention.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/macsec.c      |  22 +--
 .../mellanox/mlx5/core/en_accel/macsec.h      |   2 +-
 .../mlx5/core/en_accel/macsec_stats.c         |  16 +-
 .../mellanox/mlx5/core/lib/macsec_fs.c        | 168 +++++++++---------
 .../mellanox/mlx5/core/lib/macsec_fs.h        |  30 ++--
 5 files changed, 119 insertions(+), 119 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index b26044efdec6a..831d83094abd2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -67,7 +67,7 @@ struct mlx5e_macsec_sa {
 
 	struct rhash_head hash;
 	u32 fs_id;
-	union mlx5e_macsec_rule *macsec_rule;
+	union mlx5_macsec_rule *macsec_rule;
 	struct rcu_head rcu_head;
 	struct mlx5e_macsec_epn_state epn_state;
 };
@@ -124,7 +124,7 @@ struct mlx5e_macsec_device {
 struct mlx5e_macsec {
 	struct list_head macsec_device_list_head;
 	int num_of_devices;
-	struct mlx5e_macsec_fs *macsec_fs;
+	struct mlx5_macsec_fs *macsec_fs;
 	struct mutex lock; /* Protects mlx5e_macsec internal contexts */
 
 	/* Tx sci -> fs id mapping handling */
@@ -136,7 +136,7 @@ struct mlx5e_macsec {
 	struct mlx5_core_dev *mdev;
 
 	/* Stats manage */
-	struct mlx5e_macsec_stats stats;
+	struct mlx5_macsec_stats stats;
 
 	/* ASO */
 	struct mlx5e_macsec_aso aso;
@@ -343,7 +343,7 @@ static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec,
 	if (!sa->macsec_rule)
 		return;
 
-	mlx5e_macsec_fs_del_rule(macsec->macsec_fs, sa->macsec_rule, action);
+	mlx5_macsec_fs_del_rule(macsec->macsec_fs, sa->macsec_rule, action);
 	mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id);
 	sa->macsec_rule = NULL;
 }
@@ -358,7 +358,7 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
 	struct mlx5_macsec_rule_attrs rule_attrs;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_macsec_obj_attrs obj_attrs;
-	union mlx5e_macsec_rule *macsec_rule;
+	union mlx5_macsec_rule *macsec_rule;
 	int err;
 
 	obj_attrs.next_pn = sa->next_pn;
@@ -386,7 +386,7 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
 	rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT :
 				      MLX5_ACCEL_MACSEC_ACTION_DECRYPT;
 
-	macsec_rule = mlx5e_macsec_fs_add_rule(macsec->macsec_fs, ctx, &rule_attrs, &sa->fs_id);
+	macsec_rule = mlx5_macsec_fs_add_rule(macsec->macsec_fs, ctx, &rule_attrs, &sa->fs_id);
 	if (!macsec_rule) {
 		err = -ENOMEM;
 		goto destroy_macsec_object;
@@ -1679,10 +1679,10 @@ bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev)
 
 void mlx5e_macsec_get_stats_fill(struct mlx5e_macsec *macsec, void *macsec_stats)
 {
-	mlx5e_macsec_fs_get_stats_fill(macsec->macsec_fs, macsec_stats);
+	mlx5_macsec_fs_get_stats_fill(macsec->macsec_fs, macsec_stats);
 }
 
-struct mlx5e_macsec_stats *mlx5e_macsec_get_stats(struct mlx5e_macsec *macsec)
+struct mlx5_macsec_stats *mlx5e_macsec_get_stats(struct mlx5e_macsec *macsec)
 {
 	if (!macsec)
 		return NULL;
@@ -1781,7 +1781,7 @@ int mlx5e_macsec_init(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_macsec *macsec = NULL;
-	struct mlx5e_macsec_fs *macsec_fs;
+	struct mlx5_macsec_fs *macsec_fs;
 	int err;
 
 	if (!mlx5e_is_macsec_device(priv->mdev)) {
@@ -1821,7 +1821,7 @@ int mlx5e_macsec_init(struct mlx5e_priv *priv)
 
 	macsec->mdev = mdev;
 
-	macsec_fs = mlx5e_macsec_fs_init(mdev, priv->netdev);
+	macsec_fs = mlx5_macsec_fs_init(mdev, priv->netdev);
 	if (!macsec_fs) {
 		err = -ENOMEM;
 		goto err_out;
@@ -1857,7 +1857,7 @@ void mlx5e_macsec_cleanup(struct mlx5e_priv *priv)
 		return;
 
 	mlx5_notifier_unregister(mdev, &macsec->nb);
-	mlx5e_macsec_fs_cleanup(macsec->macsec_fs);
+	mlx5_macsec_fs_cleanup(macsec->macsec_fs);
 	destroy_workqueue(macsec->wq);
 	mlx5e_macsec_aso_cleanup(&macsec->aso, mdev);
 	rhashtable_destroy(&macsec->sci_hash);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
index 1f9c4a2723b2f..47dc1d4448d9b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
@@ -38,7 +38,7 @@ void mlx5e_macsec_offload_handle_rx_skb(struct net_device *netdev, struct sk_buf
 					struct mlx5_cqe64 *cqe);
 bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev);
 void mlx5e_macsec_get_stats_fill(struct mlx5e_macsec *macsec, void *macsec_stats);
-struct mlx5e_macsec_stats *mlx5e_macsec_get_stats(struct mlx5e_macsec *macsec);
+struct mlx5_macsec_stats *mlx5e_macsec_get_stats(struct mlx5e_macsec *macsec);
 
 #else
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c
index e50a2e3f3d18e..8326a593b3fb6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c
@@ -8,14 +8,14 @@
 #include "en_accel/macsec.h"
 
 static const struct counter_desc mlx5e_macsec_hw_stats_desc[] = {
-	{ MLX5E_DECLARE_STAT(struct mlx5e_macsec_stats, macsec_rx_pkts) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_macsec_stats, macsec_rx_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_macsec_stats, macsec_rx_pkts_drop) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_macsec_stats, macsec_rx_bytes_drop) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_macsec_stats, macsec_tx_pkts) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_macsec_stats, macsec_tx_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_macsec_stats, macsec_tx_pkts_drop) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_macsec_stats, macsec_tx_bytes_drop) },
+	{ MLX5E_DECLARE_STAT(struct mlx5_macsec_stats, macsec_rx_pkts) },
+	{ MLX5E_DECLARE_STAT(struct mlx5_macsec_stats, macsec_rx_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5_macsec_stats, macsec_rx_pkts_drop) },
+	{ MLX5E_DECLARE_STAT(struct mlx5_macsec_stats, macsec_rx_bytes_drop) },
+	{ MLX5E_DECLARE_STAT(struct mlx5_macsec_stats, macsec_tx_pkts) },
+	{ MLX5E_DECLARE_STAT(struct mlx5_macsec_stats, macsec_tx_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5_macsec_stats, macsec_tx_pkts_drop) },
+	{ MLX5E_DECLARE_STAT(struct mlx5_macsec_stats, macsec_tx_bytes_drop) },
 };
 
 #define NUM_MACSEC_HW_COUNTERS ARRAY_SIZE(mlx5e_macsec_hw_stats_desc)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index 40883d2b78c76..c585d61324bf1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -50,7 +50,7 @@ struct mlx5_sectag_header {
 	u8 sci[MACSEC_SCI_LEN]; /* optional */
 }  __packed;
 
-struct mlx5e_macsec_tx_rule {
+struct mlx5_macsec_tx_rule {
 	struct mlx5_flow_handle *rule;
 	struct mlx5_pkt_reformat *pkt_reformat;
 	u32 fs_id;
@@ -62,7 +62,7 @@ struct mlx5_macsec_flow_table {
 	struct mlx5_flow_group **g;
 };
 
-struct mlx5e_macsec_tables {
+struct mlx5_macsec_tables {
 	struct mlx5_macsec_flow_table ft_crypto;
 	struct mlx5_flow_handle *crypto_miss_rule;
 
@@ -75,37 +75,37 @@ struct mlx5e_macsec_tables {
 	u32 refcnt;
 };
 
-struct mlx5e_macsec_tx {
+struct mlx5_macsec_tx {
 	struct mlx5_flow_handle *crypto_mke_rule;
 	struct mlx5_flow_handle *check_rule;
 
 	struct ida tx_halloc;
 
-	struct mlx5e_macsec_tables tables;
+	struct mlx5_macsec_tables tables;
 };
 
-struct mlx5e_macsec_rx_rule {
+struct mlx5_macsec_rx_rule {
 	struct mlx5_flow_handle *rule[RX_NUM_OF_RULES_PER_SA];
 	struct mlx5_modify_hdr *meta_modhdr;
 };
 
-struct mlx5e_macsec_rx {
+struct mlx5_macsec_rx {
 	struct mlx5_flow_handle *check_rule[2];
 	struct mlx5_pkt_reformat *check_rule_pkt_reformat[2];
 
-	struct mlx5e_macsec_tables tables;
+	struct mlx5_macsec_tables tables;
 };
 
-union mlx5e_macsec_rule {
-	struct mlx5e_macsec_tx_rule tx_rule;
-	struct mlx5e_macsec_rx_rule rx_rule;
+union mlx5_macsec_rule {
+	struct mlx5_macsec_tx_rule tx_rule;
+	struct mlx5_macsec_rx_rule rx_rule;
 };
 
-struct mlx5e_macsec_fs {
+struct mlx5_macsec_fs {
 	struct mlx5_core_dev *mdev;
 	struct net_device *netdev;
-	struct mlx5e_macsec_tx *tx_fs;
-	struct mlx5e_macsec_rx *rx_fs;
+	struct mlx5_macsec_tx *tx_fs;
+	struct mlx5_macsec_rx *rx_fs;
 };
 
 static void macsec_fs_destroy_groups(struct mlx5_macsec_flow_table *ft)
@@ -128,10 +128,10 @@ static void macsec_fs_destroy_flow_table(struct mlx5_macsec_flow_table *ft)
 	ft->t = NULL;
 }
 
-static void macsec_fs_tx_destroy(struct mlx5e_macsec_fs *macsec_fs)
+static void macsec_fs_tx_destroy(struct mlx5_macsec_fs *macsec_fs)
 {
-	struct mlx5e_macsec_tx *tx_fs = macsec_fs->tx_fs;
-	struct mlx5e_macsec_tables *tx_tables;
+	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
+	struct mlx5_macsec_tables *tx_tables;
 
 	tx_tables = &tx_fs->tables;
 
@@ -260,14 +260,14 @@ static struct mlx5_flow_table
 	return fdb;
 }
 
-static int macsec_fs_tx_create(struct mlx5e_macsec_fs *macsec_fs)
+static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5e_macsec_tx *tx_fs = macsec_fs->tx_fs;
+	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
 	struct net_device *netdev = macsec_fs->netdev;
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_destination dest = {};
-	struct mlx5e_macsec_tables *tx_tables;
+	struct mlx5_macsec_tables *tx_tables;
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_macsec_flow_table *ft_crypto;
 	struct mlx5_flow_table *flow_table;
@@ -413,10 +413,10 @@ out_spec:
 	return err;
 }
 
-static int macsec_fs_tx_ft_get(struct mlx5e_macsec_fs *macsec_fs)
+static int macsec_fs_tx_ft_get(struct mlx5_macsec_fs *macsec_fs)
 {
-	struct mlx5e_macsec_tx *tx_fs = macsec_fs->tx_fs;
-	struct mlx5e_macsec_tables *tx_tables;
+	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
+	struct mlx5_macsec_tables *tx_tables;
 	int err = 0;
 
 	tx_tables = &tx_fs->tables;
@@ -432,9 +432,9 @@ out:
 	return err;
 }
 
-static void macsec_fs_tx_ft_put(struct mlx5e_macsec_fs *macsec_fs)
+static void macsec_fs_tx_ft_put(struct mlx5_macsec_fs *macsec_fs)
 {
-	struct mlx5e_macsec_tables *tx_tables = &macsec_fs->tx_fs->tables;
+	struct mlx5_macsec_tables *tx_tables = &macsec_fs->tx_fs->tables;
 
 	if (--tx_tables->refcnt)
 		return;
@@ -442,13 +442,13 @@ static void macsec_fs_tx_ft_put(struct mlx5e_macsec_fs *macsec_fs)
 	macsec_fs_tx_destroy(macsec_fs);
 }
 
-static int macsec_fs_tx_setup_fte(struct mlx5e_macsec_fs *macsec_fs,
+static int macsec_fs_tx_setup_fte(struct mlx5_macsec_fs *macsec_fs,
 				  struct mlx5_flow_spec *spec,
 				  struct mlx5_flow_act *flow_act,
 				  u32 macsec_obj_id,
 				  u32 *fs_id)
 {
-	struct mlx5e_macsec_tx *tx_fs = macsec_fs->tx_fs;
+	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
 	int err = 0;
 	u32 id;
 
@@ -511,8 +511,8 @@ static void macsec_fs_tx_create_sectag_header(const struct macsec_context *ctx,
 	memcpy(reformatbf, &sectag, *reformat_size);
 }
 
-static void macsec_fs_tx_del_rule(struct mlx5e_macsec_fs *macsec_fs,
-				  struct mlx5e_macsec_tx_rule *tx_rule)
+static void macsec_fs_tx_del_rule(struct mlx5_macsec_fs *macsec_fs,
+				  struct mlx5_macsec_tx_rule *tx_rule)
 {
 	if (tx_rule->rule) {
 		mlx5_del_flow_rules(tx_rule->rule);
@@ -536,20 +536,20 @@ static void macsec_fs_tx_del_rule(struct mlx5e_macsec_fs *macsec_fs,
 
 #define MLX5_REFORMAT_PARAM_ADD_MACSEC_OFFSET_4_BYTES 1
 
-static union mlx5e_macsec_rule *
-macsec_fs_tx_add_rule(struct mlx5e_macsec_fs *macsec_fs,
+static union mlx5_macsec_rule *
+macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 		      const struct macsec_context *macsec_ctx,
 		      struct mlx5_macsec_rule_attrs *attrs,
 		      u32 *sa_fs_id)
 {
 	char reformatbf[MLX5_MACSEC_TAG_LEN + MACSEC_SCI_LEN];
 	struct mlx5_pkt_reformat_params reformat_params = {};
-	struct mlx5e_macsec_tx *tx_fs = macsec_fs->tx_fs;
+	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
 	struct net_device *netdev = macsec_fs->netdev;
-	union mlx5e_macsec_rule *macsec_rule = NULL;
+	union mlx5_macsec_rule *macsec_rule = NULL;
 	struct mlx5_flow_destination dest = {};
-	struct mlx5e_macsec_tables *tx_tables;
-	struct mlx5e_macsec_tx_rule *tx_rule;
+	struct mlx5_macsec_tables *tx_tables;
+	struct mlx5_macsec_tx_rule *tx_rule;
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
@@ -630,11 +630,11 @@ out_spec:
 	return macsec_rule;
 }
 
-static void macsec_fs_tx_cleanup(struct mlx5e_macsec_fs *macsec_fs)
+static void macsec_fs_tx_cleanup(struct mlx5_macsec_fs *macsec_fs)
 {
-	struct mlx5e_macsec_tx *tx_fs = macsec_fs->tx_fs;
+	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
 	struct mlx5_core_dev *mdev = macsec_fs->mdev;
-	struct mlx5e_macsec_tables *tx_tables;
+	struct mlx5_macsec_tables *tx_tables;
 
 	if (!tx_fs)
 		return;
@@ -663,12 +663,12 @@ static void macsec_fs_tx_cleanup(struct mlx5e_macsec_fs *macsec_fs)
 	macsec_fs->tx_fs = NULL;
 }
 
-static int macsec_fs_tx_init(struct mlx5e_macsec_fs *macsec_fs)
+static int macsec_fs_tx_init(struct mlx5_macsec_fs *macsec_fs)
 {
 	struct net_device *netdev = macsec_fs->netdev;
 	struct mlx5_core_dev *mdev = macsec_fs->mdev;
-	struct mlx5e_macsec_tables *tx_tables;
-	struct mlx5e_macsec_tx *tx_fs;
+	struct mlx5_macsec_tables *tx_tables;
+	struct mlx5_macsec_tx *tx_fs;
 	struct mlx5_fc *flow_counter;
 	int err;
 
@@ -715,10 +715,10 @@ err_encrypt_counter:
 	return err;
 }
 
-static void macsec_fs_rx_destroy(struct mlx5e_macsec_fs *macsec_fs)
+static void macsec_fs_rx_destroy(struct mlx5_macsec_fs *macsec_fs)
 {
-	struct mlx5e_macsec_rx *rx_fs = macsec_fs->rx_fs;
-	struct mlx5e_macsec_tables *rx_tables;
+	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
+	struct mlx5_macsec_tables *rx_tables;
 	int i;
 
 	/* Rx check table */
@@ -843,7 +843,7 @@ err:
 	return err;
 }
 
-static int macsec_fs_rx_create_check_decap_rule(struct mlx5e_macsec_fs *macsec_fs,
+static int macsec_fs_rx_create_check_decap_rule(struct mlx5_macsec_fs *macsec_fs,
 						struct mlx5_flow_destination *dest,
 						struct mlx5_flow_act *flow_act,
 						struct mlx5_flow_spec *spec,
@@ -852,9 +852,9 @@ static int macsec_fs_rx_create_check_decap_rule(struct mlx5e_macsec_fs *macsec_f
 	int rule_index = (reformat_param_size == MLX5_SECTAG_HEADER_SIZE_WITH_SCI) ? 0 : 1;
 	u8 mlx5_reformat_buf[MLX5_SECTAG_HEADER_SIZE_WITH_SCI];
 	struct mlx5_pkt_reformat_params reformat_params = {};
-	struct mlx5e_macsec_rx *rx_fs = macsec_fs->rx_fs;
+	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
 	struct net_device *netdev = macsec_fs->netdev;
-	struct mlx5e_macsec_tables *rx_tables;
+	struct mlx5_macsec_tables *rx_tables;
 	struct mlx5_flow_handle *rule;
 	int err = 0;
 
@@ -914,15 +914,15 @@ static int macsec_fs_rx_create_check_decap_rule(struct mlx5e_macsec_fs *macsec_f
 	return 0;
 }
 
-static int macsec_fs_rx_create(struct mlx5e_macsec_fs *macsec_fs)
+static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5e_macsec_rx *rx_fs = macsec_fs->rx_fs;
+	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
 	struct net_device *netdev = macsec_fs->netdev;
 	struct mlx5_macsec_flow_table *ft_crypto;
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_destination dest = {};
-	struct mlx5e_macsec_tables *rx_tables;
+	struct mlx5_macsec_tables *rx_tables;
 	struct mlx5_flow_table *flow_table;
 	struct mlx5_flow_group *flow_group;
 	struct mlx5_flow_act flow_act = {};
@@ -1042,9 +1042,9 @@ free_spec:
 	return err;
 }
 
-static int macsec_fs_rx_ft_get(struct mlx5e_macsec_fs *macsec_fs)
+static int macsec_fs_rx_ft_get(struct mlx5_macsec_fs *macsec_fs)
 {
-	struct mlx5e_macsec_tables *rx_tables = &macsec_fs->rx_fs->tables;
+	struct mlx5_macsec_tables *rx_tables = &macsec_fs->rx_fs->tables;
 	int err = 0;
 
 	if (rx_tables->refcnt)
@@ -1059,9 +1059,9 @@ out:
 	return err;
 }
 
-static void macsec_fs_rx_ft_put(struct mlx5e_macsec_fs *macsec_fs)
+static void macsec_fs_rx_ft_put(struct mlx5_macsec_fs *macsec_fs)
 {
-	struct mlx5e_macsec_tables *rx_tables = &macsec_fs->rx_fs->tables;
+	struct mlx5_macsec_tables *rx_tables = &macsec_fs->rx_fs->tables;
 
 	if (--rx_tables->refcnt)
 		return;
@@ -1069,8 +1069,8 @@ static void macsec_fs_rx_ft_put(struct mlx5e_macsec_fs *macsec_fs)
 	macsec_fs_rx_destroy(macsec_fs);
 }
 
-static void macsec_fs_rx_del_rule(struct mlx5e_macsec_fs *macsec_fs,
-				  struct mlx5e_macsec_rx_rule *rx_rule)
+static void macsec_fs_rx_del_rule(struct mlx5_macsec_fs *macsec_fs,
+				  struct mlx5_macsec_rx_rule *rx_rule)
 {
 	int i;
 
@@ -1137,20 +1137,20 @@ static void macsec_fs_rx_setup_fte(struct mlx5_flow_spec *spec,
 	crypto_params->obj_id = attrs->macsec_obj_id;
 }
 
-static union mlx5e_macsec_rule *
-macsec_fs_rx_add_rule(struct mlx5e_macsec_fs *macsec_fs,
+static union mlx5_macsec_rule *
+macsec_fs_rx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 		      struct mlx5_macsec_rule_attrs *attrs,
 		      u32 fs_id)
 {
 	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
-	struct mlx5e_macsec_rx *rx_fs = macsec_fs->rx_fs;
+	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
 	struct net_device *netdev = macsec_fs->netdev;
-	union mlx5e_macsec_rule *macsec_rule = NULL;
+	union mlx5_macsec_rule *macsec_rule = NULL;
 	struct mlx5_modify_hdr *modify_hdr = NULL;
 	struct mlx5_macsec_flow_table *ft_crypto;
 	struct mlx5_flow_destination dest = {};
-	struct mlx5e_macsec_tables *rx_tables;
-	struct mlx5e_macsec_rx_rule *rx_rule;
+	struct mlx5_macsec_tables *rx_tables;
+	struct mlx5_macsec_rx_rule *rx_rule;
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
@@ -1249,12 +1249,12 @@ out_spec:
 	return macsec_rule;
 }
 
-static int macsec_fs_rx_init(struct mlx5e_macsec_fs *macsec_fs)
+static int macsec_fs_rx_init(struct mlx5_macsec_fs *macsec_fs)
 {
 	struct net_device *netdev = macsec_fs->netdev;
 	struct mlx5_core_dev *mdev = macsec_fs->mdev;
-	struct mlx5e_macsec_tables *rx_tables;
-	struct mlx5e_macsec_rx *rx_fs;
+	struct mlx5_macsec_tables *rx_tables;
+	struct mlx5_macsec_rx *rx_fs;
 	struct mlx5_fc *flow_counter;
 	int err;
 
@@ -1299,11 +1299,11 @@ err_encrypt_counter:
 	return err;
 }
 
-static void macsec_fs_rx_cleanup(struct mlx5e_macsec_fs *macsec_fs)
+static void macsec_fs_rx_cleanup(struct mlx5_macsec_fs *macsec_fs)
 {
-	struct mlx5e_macsec_rx *rx_fs = macsec_fs->rx_fs;
+	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
 	struct mlx5_core_dev *mdev = macsec_fs->mdev;
-	struct mlx5e_macsec_tables *rx_tables;
+	struct mlx5_macsec_tables *rx_tables;
 
 	if (!rx_fs)
 		return;
@@ -1331,11 +1331,11 @@ static void macsec_fs_rx_cleanup(struct mlx5e_macsec_fs *macsec_fs)
 	macsec_fs->rx_fs = NULL;
 }
 
-void mlx5e_macsec_fs_get_stats_fill(struct mlx5e_macsec_fs *macsec_fs, void *macsec_stats)
+void mlx5_macsec_fs_get_stats_fill(struct mlx5_macsec_fs *macsec_fs, void *macsec_stats)
 {
-	struct mlx5e_macsec_stats *stats = (struct mlx5e_macsec_stats *)macsec_stats;
-	struct mlx5e_macsec_tables *tx_tables = &macsec_fs->tx_fs->tables;
-	struct mlx5e_macsec_tables *rx_tables = &macsec_fs->rx_fs->tables;
+	struct mlx5_macsec_stats *stats = (struct mlx5_macsec_stats *)macsec_stats;
+	struct mlx5_macsec_tables *tx_tables = &macsec_fs->tx_fs->tables;
+	struct mlx5_macsec_tables *rx_tables = &macsec_fs->rx_fs->tables;
 	struct mlx5_core_dev *mdev = macsec_fs->mdev;
 
 	if (tx_tables->check_rule_counter)
@@ -1355,38 +1355,38 @@ void mlx5e_macsec_fs_get_stats_fill(struct mlx5e_macsec_fs *macsec_fs, void *mac
 			      &stats->macsec_rx_pkts_drop, &stats->macsec_rx_bytes_drop);
 }
 
-union mlx5e_macsec_rule *
-mlx5e_macsec_fs_add_rule(struct mlx5e_macsec_fs *macsec_fs,
-			 const struct macsec_context *macsec_ctx,
-			 struct mlx5_macsec_rule_attrs *attrs,
-			 u32 *sa_fs_id)
+union mlx5_macsec_rule *
+mlx5_macsec_fs_add_rule(struct mlx5_macsec_fs *macsec_fs,
+			const struct macsec_context *macsec_ctx,
+			struct mlx5_macsec_rule_attrs *attrs,
+			u32 *sa_fs_id)
 {
 	return (attrs->action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) ?
 		macsec_fs_tx_add_rule(macsec_fs, macsec_ctx, attrs, sa_fs_id) :
 		macsec_fs_rx_add_rule(macsec_fs, attrs, *sa_fs_id);
 }
 
-void mlx5e_macsec_fs_del_rule(struct mlx5e_macsec_fs *macsec_fs,
-			      union mlx5e_macsec_rule *macsec_rule,
-			      int action)
+void mlx5_macsec_fs_del_rule(struct mlx5_macsec_fs *macsec_fs,
+			     union mlx5_macsec_rule *macsec_rule,
+			     int action)
 {
 	(action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) ?
 		macsec_fs_tx_del_rule(macsec_fs, &macsec_rule->tx_rule) :
 		macsec_fs_rx_del_rule(macsec_fs, &macsec_rule->rx_rule);
 }
 
-void mlx5e_macsec_fs_cleanup(struct mlx5e_macsec_fs *macsec_fs)
+void mlx5_macsec_fs_cleanup(struct mlx5_macsec_fs *macsec_fs)
 {
 	macsec_fs_rx_cleanup(macsec_fs);
 	macsec_fs_tx_cleanup(macsec_fs);
 	kfree(macsec_fs);
 }
 
-struct mlx5e_macsec_fs *
-mlx5e_macsec_fs_init(struct mlx5_core_dev *mdev,
-		     struct net_device *netdev)
+struct mlx5_macsec_fs *
+mlx5_macsec_fs_init(struct mlx5_core_dev *mdev,
+		    struct net_device *netdev)
 {
-	struct mlx5e_macsec_fs *macsec_fs;
+	struct mlx5_macsec_fs *macsec_fs;
 	int err;
 
 	macsec_fs = kzalloc(sizeof(*macsec_fs), GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
index b282c0850e16f..6a749e036e688 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
@@ -14,8 +14,8 @@
 
 #define MLX5_MACSEC_NUM_OF_SUPPORTED_INTERFACES 16
 
-struct mlx5e_macsec_fs;
-union mlx5e_macsec_rule;
+struct mlx5_macsec_fs;
+union mlx5_macsec_rule;
 
 struct mlx5_macsec_rule_attrs {
 	sci_t sci;
@@ -24,7 +24,7 @@ struct mlx5_macsec_rule_attrs {
 	int action;
 };
 
-struct mlx5e_macsec_stats {
+struct mlx5_macsec_stats {
 	u64 macsec_rx_pkts;
 	u64 macsec_rx_bytes;
 	u64 macsec_rx_pkts_drop;
@@ -40,22 +40,22 @@ enum mlx5_macsec_action {
 	MLX5_ACCEL_MACSEC_ACTION_DECRYPT,
 };
 
-void mlx5e_macsec_fs_cleanup(struct mlx5e_macsec_fs *macsec_fs);
+void mlx5_macsec_fs_cleanup(struct mlx5_macsec_fs *macsec_fs);
 
-struct mlx5e_macsec_fs *
-mlx5e_macsec_fs_init(struct mlx5_core_dev *mdev, struct net_device *netdev);
+struct mlx5_macsec_fs *
+mlx5_macsec_fs_init(struct mlx5_core_dev *mdev, struct net_device *netdev);
 
-union mlx5e_macsec_rule *
-mlx5e_macsec_fs_add_rule(struct mlx5e_macsec_fs *macsec_fs,
-			 const struct macsec_context *ctx,
-			 struct mlx5_macsec_rule_attrs *attrs,
-			 u32 *sa_fs_id);
+union mlx5_macsec_rule *
+mlx5_macsec_fs_add_rule(struct mlx5_macsec_fs *macsec_fs,
+			const struct macsec_context *ctx,
+			struct mlx5_macsec_rule_attrs *attrs,
+			u32 *sa_fs_id);
 
-void mlx5e_macsec_fs_del_rule(struct mlx5e_macsec_fs *macsec_fs,
-			      union mlx5e_macsec_rule *macsec_rule,
-			      int action);
+void mlx5_macsec_fs_del_rule(struct mlx5_macsec_fs *macsec_fs,
+			     union mlx5_macsec_rule *macsec_rule,
+			     int action);
 
-void mlx5e_macsec_fs_get_stats_fill(struct mlx5e_macsec_fs *macsec_fs, void *macsec_stats);
+void mlx5_macsec_fs_get_stats_fill(struct mlx5_macsec_fs *macsec_fs, void *macsec_stats);
 
 #endif
 
-- 
GitLab


From 2e92f669b86d70a26a77b088c74e1cb6d26322e1 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Tue, 6 Dec 2022 14:33:49 +0200
Subject: [PATCH 1362/1806] net/mlx5e: Move MACsec flow steering and statistics
 database from ethernet to core

Since now MACsec flow steering (macsec_fs) and MACsec statistics (stats)
are maintained by the core driver, move their data as well to be saved
inside core structures instead of staying part of ethernet MACsec database.

In addition cleanup all MACsec stats functions from the ethernet MACsec
code and move what's needed to be part of macsec_fs instead.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/macsec.c      | 25 +++----------------
 .../mellanox/mlx5/core/en_accel/macsec.h      |  2 --
 .../mlx5/core/en_accel/macsec_stats.c         |  6 +++--
 .../mellanox/mlx5/core/lib/macsec_fs.c        | 11 ++++++++
 .../mellanox/mlx5/core/lib/macsec_fs.h        |  1 +
 include/linux/mlx5/driver.h                   |  3 +++
 6 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index 831d83094abd2..5e8ad355c67ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -124,7 +124,6 @@ struct mlx5e_macsec_device {
 struct mlx5e_macsec {
 	struct list_head macsec_device_list_head;
 	int num_of_devices;
-	struct mlx5_macsec_fs *macsec_fs;
 	struct mutex lock; /* Protects mlx5e_macsec internal contexts */
 
 	/* Tx sci -> fs id mapping handling */
@@ -135,9 +134,6 @@ struct mlx5e_macsec {
 
 	struct mlx5_core_dev *mdev;
 
-	/* Stats manage */
-	struct mlx5_macsec_stats stats;
-
 	/* ASO */
 	struct mlx5e_macsec_aso aso;
 
@@ -343,7 +339,7 @@ static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec,
 	if (!sa->macsec_rule)
 		return;
 
-	mlx5_macsec_fs_del_rule(macsec->macsec_fs, sa->macsec_rule, action);
+	mlx5_macsec_fs_del_rule(macsec->mdev->macsec_fs, sa->macsec_rule, action);
 	mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id);
 	sa->macsec_rule = NULL;
 }
@@ -386,7 +382,7 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
 	rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT :
 				      MLX5_ACCEL_MACSEC_ACTION_DECRYPT;
 
-	macsec_rule = mlx5_macsec_fs_add_rule(macsec->macsec_fs, ctx, &rule_attrs, &sa->fs_id);
+	macsec_rule = mlx5_macsec_fs_add_rule(mdev->macsec_fs, ctx, &rule_attrs, &sa->fs_id);
 	if (!macsec_rule) {
 		err = -ENOMEM;
 		goto destroy_macsec_object;
@@ -1677,19 +1673,6 @@ bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev)
 	return true;
 }
 
-void mlx5e_macsec_get_stats_fill(struct mlx5e_macsec *macsec, void *macsec_stats)
-{
-	mlx5_macsec_fs_get_stats_fill(macsec->macsec_fs, macsec_stats);
-}
-
-struct mlx5_macsec_stats *mlx5e_macsec_get_stats(struct mlx5e_macsec *macsec)
-{
-	if (!macsec)
-		return NULL;
-
-	return &macsec->stats;
-}
-
 static const struct macsec_ops macsec_offload_ops = {
 	.mdo_add_txsa = mlx5e_macsec_add_txsa,
 	.mdo_upd_txsa = mlx5e_macsec_upd_txsa,
@@ -1827,7 +1810,7 @@ int mlx5e_macsec_init(struct mlx5e_priv *priv)
 		goto err_out;
 	}
 
-	macsec->macsec_fs = macsec_fs;
+	mdev->macsec_fs = macsec_fs;
 
 	macsec->nb.notifier_call = macsec_obj_change_event;
 	mlx5_notifier_register(mdev, &macsec->nb);
@@ -1857,7 +1840,7 @@ void mlx5e_macsec_cleanup(struct mlx5e_priv *priv)
 		return;
 
 	mlx5_notifier_unregister(mdev, &macsec->nb);
-	mlx5_macsec_fs_cleanup(macsec->macsec_fs);
+	mlx5_macsec_fs_cleanup(mdev->macsec_fs);
 	destroy_workqueue(macsec->wq);
 	mlx5e_macsec_aso_cleanup(&macsec->aso, mdev);
 	rhashtable_destroy(&macsec->sci_hash);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
index 47dc1d4448d9b..2ecd769585f43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
@@ -37,8 +37,6 @@ static inline bool mlx5e_macsec_is_rx_flow(struct mlx5_cqe64 *cqe)
 void mlx5e_macsec_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
 					struct mlx5_cqe64 *cqe);
 bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev);
-void mlx5e_macsec_get_stats_fill(struct mlx5e_macsec *macsec, void *macsec_stats);
-struct mlx5_macsec_stats *mlx5e_macsec_get_stats(struct mlx5e_macsec *macsec);
 
 #else
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c
index 8326a593b3fb6..4559ee16a11a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c
@@ -52,6 +52,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(macsec_hw)
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(macsec_hw)
 {
+	struct mlx5_macsec_fs *macsec_fs;
 	int i;
 
 	if (!priv->macsec)
@@ -60,9 +61,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(macsec_hw)
 	if (!mlx5e_is_macsec_device(priv->mdev))
 		return idx;
 
-	mlx5e_macsec_get_stats_fill(priv->macsec, mlx5e_macsec_get_stats(priv->macsec));
+	macsec_fs = priv->mdev->macsec_fs;
+	mlx5_macsec_fs_get_stats_fill(macsec_fs, mlx5_macsec_fs_get_stats(macsec_fs));
 	for (i = 0; i < NUM_MACSEC_HW_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5e_macsec_get_stats(priv->macsec),
+		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_macsec_fs_get_stats(macsec_fs),
 						   mlx5e_macsec_hw_stats_desc,
 						   i);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index c585d61324bf1..11f9c5a8e43a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -106,6 +106,9 @@ struct mlx5_macsec_fs {
 	struct net_device *netdev;
 	struct mlx5_macsec_tx *tx_fs;
 	struct mlx5_macsec_rx *rx_fs;
+
+	/* Stats manage */
+	struct mlx5_macsec_stats stats;
 };
 
 static void macsec_fs_destroy_groups(struct mlx5_macsec_flow_table *ft)
@@ -1355,6 +1358,14 @@ void mlx5_macsec_fs_get_stats_fill(struct mlx5_macsec_fs *macsec_fs, void *macse
 			      &stats->macsec_rx_pkts_drop, &stats->macsec_rx_bytes_drop);
 }
 
+struct mlx5_macsec_stats *mlx5_macsec_fs_get_stats(struct mlx5_macsec_fs *macsec_fs)
+{
+	if (!macsec_fs)
+		return NULL;
+
+	return &macsec_fs->stats;
+}
+
 union mlx5_macsec_rule *
 mlx5_macsec_fs_add_rule(struct mlx5_macsec_fs *macsec_fs,
 			const struct macsec_context *macsec_ctx,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
index 6a749e036e688..c0c28d08eae51 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
@@ -56,6 +56,7 @@ void mlx5_macsec_fs_del_rule(struct mlx5_macsec_fs *macsec_fs,
 			     int action);
 
 void mlx5_macsec_fs_get_stats_fill(struct mlx5_macsec_fs *macsec_fs, void *macsec_stats);
+struct mlx5_macsec_stats *mlx5_macsec_fs_get_stats(struct mlx5_macsec_fs *macsec_fs);
 
 #endif
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 25d0528f92197..0e80241c270ff 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -805,6 +805,9 @@ struct mlx5_core_dev {
 	u32                      vsc_addr;
 	struct mlx5_hv_vhca	*hv_vhca;
 	struct mlx5_thermal	*thermal;
+#ifdef CONFIG_MLX5_MACSEC
+	struct mlx5_macsec_fs *macsec_fs;
+#endif
 };
 
 struct mlx5_db {
-- 
GitLab


From 7e2304f5bf1c9f4e22d8dce473fd9a8961e6a7b4 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 5 Jan 2023 13:28:11 +0200
Subject: [PATCH 1363/1806] net/mlx5: Remove netdevice from MACsec steering

Since MACsec steering was moved from ethernet private code to core,
remove the netdevice from the MACsec steering, and use core device
methods for error reporting instead.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/macsec.c      |   2 +-
 .../mellanox/mlx5/core/lib/macsec_fs.c        | 144 +++++++++---------
 .../mellanox/mlx5/core/lib/macsec_fs.h        |   2 +-
 3 files changed, 71 insertions(+), 77 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index 5e8ad355c67ff..fb599bacbe30f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -1804,7 +1804,7 @@ int mlx5e_macsec_init(struct mlx5e_priv *priv)
 
 	macsec->mdev = mdev;
 
-	macsec_fs = mlx5_macsec_fs_init(mdev, priv->netdev);
+	macsec_fs = mlx5_macsec_fs_init(mdev);
 	if (!macsec_fs) {
 		err = -ENOMEM;
 		goto err_out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index 11f9c5a8e43a9..8ecc91f30da13 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
 
 #include <net/macsec.h>
-#include <linux/netdevice.h>
 #include <linux/mlx5/qp.h>
 #include <linux/if_vlan.h>
 #include "fs_core.h"
@@ -103,7 +102,6 @@ union mlx5_macsec_rule {
 
 struct mlx5_macsec_fs {
 	struct mlx5_core_dev *mdev;
-	struct net_device *netdev;
 	struct mlx5_macsec_tx *tx_fs;
 	struct mlx5_macsec_rx *rx_fs;
 
@@ -267,7 +265,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
-	struct net_device *netdev = macsec_fs->netdev;
+	struct mlx5_core_dev *mdev = macsec_fs->mdev;
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_macsec_tables *tx_tables;
@@ -281,7 +279,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	u32 *flow_group_in;
 	int err;
 
-	ns = mlx5_get_flow_namespace(macsec_fs->mdev, MLX5_FLOW_NAMESPACE_EGRESS_MACSEC);
+	ns = mlx5_get_flow_namespace(mdev, MLX5_FLOW_NAMESPACE_EGRESS_MACSEC);
 	if (!ns)
 		return -ENOMEM;
 
@@ -306,7 +304,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	flow_table = mlx5_create_flow_table(ns, &ft_attr);
 	if (IS_ERR(flow_table)) {
 		err = PTR_ERR(flow_table);
-		netdev_err(netdev, "Failed to create MACsec Tx crypto table err(%d)\n", err);
+		mlx5_core_err(mdev, "Failed to create MACsec Tx crypto table err(%d)\n", err);
 		goto out_flow_group;
 	}
 	ft_crypto->t = flow_table;
@@ -314,9 +312,9 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	/* Tx crypto table groups */
 	err = macsec_fs_tx_create_crypto_table_groups(ft_crypto);
 	if (err) {
-		netdev_err(netdev,
-			   "Failed to create default flow group for MACsec Tx crypto table err(%d)\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to create default flow group for MACsec Tx crypto table err(%d)\n",
+			      err);
 		goto err;
 	}
 
@@ -330,7 +328,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	rule = mlx5_add_flow_rules(ft_crypto->t, spec, &flow_act, NULL, 0);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		netdev_err(netdev, "Failed to add MACsec TX MKE rule, err=%d\n", err);
+		mlx5_core_err(mdev, "Failed to add MACsec TX MKE rule, err=%d\n", err);
 		goto err;
 	}
 	tx_fs->crypto_mke_rule = rule;
@@ -341,7 +339,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	rule = mlx5_add_flow_rules(ft_crypto->t, NULL, &flow_act, NULL, 0);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		netdev_err(netdev, "Failed to add MACsec Tx table default miss rule %d\n", err);
+		mlx5_core_err(mdev, "Failed to add MACsec Tx table default miss rule %d\n", err);
 		goto err;
 	}
 	tx_tables->crypto_miss_rule = rule;
@@ -351,7 +349,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 						       TX_CHECK_TABLE_NUM_FTE);
 	if (IS_ERR(flow_table)) {
 		err = PTR_ERR(flow_table);
-		netdev_err(netdev, "fail to create MACsec TX check table, err(%d)\n", err);
+		mlx5_core_err(mdev, "Fail to create MACsec TX check table, err(%d)\n", err);
 		goto err;
 	}
 	tx_tables->ft_check = flow_table;
@@ -363,9 +361,9 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	flow_group = mlx5_create_flow_group(tx_tables->ft_check, flow_group_in);
 	if (IS_ERR(flow_group)) {
 		err = PTR_ERR(flow_group);
-		netdev_err(netdev,
-			   "Failed to create default flow group for MACsec Tx crypto table err(%d)\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to create default flow group for MACsec Tx crypto table err(%d)\n",
+			      err);
 		goto err;
 	}
 	tx_tables->ft_check_group = flow_group;
@@ -379,7 +377,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	rule = mlx5_add_flow_rules(tx_tables->ft_check,  NULL, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		netdev_err(netdev, "Failed to added MACsec tx check drop rule, err(%d)\n", err);
+		mlx5_core_err(mdev, "Failed to added MACsec tx check drop rule, err(%d)\n", err);
 		goto err;
 	}
 	tx_tables->check_miss_rule = rule;
@@ -400,7 +398,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	rule = mlx5_add_flow_rules(tx_tables->ft_check, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		netdev_err(netdev, "Failed to add MACsec check rule, err=%d\n", err);
+		mlx5_core_err(mdev, "Failed to add MACsec check rule, err=%d\n", err);
 		goto err;
 	}
 	tx_fs->check_rule = rule;
@@ -548,7 +546,7 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	char reformatbf[MLX5_MACSEC_TAG_LEN + MACSEC_SCI_LEN];
 	struct mlx5_pkt_reformat_params reformat_params = {};
 	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
-	struct net_device *netdev = macsec_fs->netdev;
+	struct mlx5_core_dev *mdev = macsec_fs->mdev;
 	union mlx5_macsec_rule *macsec_rule = NULL;
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_macsec_tables *tx_tables;
@@ -588,21 +586,21 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	if (is_vlan_dev(macsec_ctx->netdev))
 		reformat_params.param_0 = MLX5_REFORMAT_PARAM_ADD_MACSEC_OFFSET_4_BYTES;
 
-	flow_act.pkt_reformat = mlx5_packet_reformat_alloc(macsec_fs->mdev,
+	flow_act.pkt_reformat = mlx5_packet_reformat_alloc(mdev,
 							   &reformat_params,
 							   MLX5_FLOW_NAMESPACE_EGRESS_MACSEC);
 	if (IS_ERR(flow_act.pkt_reformat)) {
 		err = PTR_ERR(flow_act.pkt_reformat);
-		netdev_err(netdev, "Failed to allocate MACsec Tx reformat context err=%d\n",  err);
+		mlx5_core_err(mdev, "Failed to allocate MACsec Tx reformat context err=%d\n",  err);
 		goto err;
 	}
 	tx_rule->pkt_reformat = flow_act.pkt_reformat;
 
 	err = macsec_fs_tx_setup_fte(macsec_fs, spec, &flow_act, attrs->macsec_obj_id, &fs_id);
 	if (err) {
-		netdev_err(netdev,
-			   "Failed to add packet reformat for MACsec TX crypto rule, err=%d\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to add packet reformat for MACsec TX crypto rule, err=%d\n",
+			      err);
 		goto err;
 	}
 
@@ -617,7 +615,7 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	rule = mlx5_add_flow_rules(tx_tables->ft_crypto.t, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		netdev_err(netdev, "Failed to add MACsec TX crypto rule, err=%d\n", err);
+		mlx5_core_err(mdev, "Failed to add MACsec TX crypto rule, err=%d\n", err);
 		goto err;
 	}
 	tx_rule->rule = rule;
@@ -644,9 +642,9 @@ static void macsec_fs_tx_cleanup(struct mlx5_macsec_fs *macsec_fs)
 
 	tx_tables = &tx_fs->tables;
 	if (tx_tables->refcnt) {
-		netdev_err(macsec_fs->netdev,
-			   "Can't destroy MACsec offload tx_fs, refcnt(%u) isn't 0\n",
-			   tx_tables->refcnt);
+		mlx5_core_err(mdev,
+			      "Can't destroy MACsec offload tx_fs, refcnt(%u) isn't 0\n",
+			      tx_tables->refcnt);
 		return;
 	}
 
@@ -668,7 +666,6 @@ static void macsec_fs_tx_cleanup(struct mlx5_macsec_fs *macsec_fs)
 
 static int macsec_fs_tx_init(struct mlx5_macsec_fs *macsec_fs)
 {
-	struct net_device *netdev = macsec_fs->netdev;
 	struct mlx5_core_dev *mdev = macsec_fs->mdev;
 	struct mlx5_macsec_tables *tx_tables;
 	struct mlx5_macsec_tx *tx_fs;
@@ -684,9 +681,9 @@ static int macsec_fs_tx_init(struct mlx5_macsec_fs *macsec_fs)
 	flow_counter = mlx5_fc_create(mdev, false);
 	if (IS_ERR(flow_counter)) {
 		err = PTR_ERR(flow_counter);
-		netdev_err(netdev,
-			   "Failed to create MACsec Tx encrypt flow counter, err(%d)\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to create MACsec Tx encrypt flow counter, err(%d)\n",
+			      err);
 		goto err_encrypt_counter;
 	}
 	tx_tables->check_rule_counter = flow_counter;
@@ -694,9 +691,9 @@ static int macsec_fs_tx_init(struct mlx5_macsec_fs *macsec_fs)
 	flow_counter = mlx5_fc_create(mdev, false);
 	if (IS_ERR(flow_counter)) {
 		err = PTR_ERR(flow_counter);
-		netdev_err(netdev,
-			   "Failed to create MACsec Tx drop flow counter, err(%d)\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to create MACsec Tx drop flow counter, err(%d)\n",
+			      err);
 		goto err_drop_counter;
 	}
 	tx_tables->check_miss_rule_counter = flow_counter;
@@ -856,7 +853,7 @@ static int macsec_fs_rx_create_check_decap_rule(struct mlx5_macsec_fs *macsec_fs
 	u8 mlx5_reformat_buf[MLX5_SECTAG_HEADER_SIZE_WITH_SCI];
 	struct mlx5_pkt_reformat_params reformat_params = {};
 	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
-	struct net_device *netdev = macsec_fs->netdev;
+	struct mlx5_core_dev *mdev = macsec_fs->mdev;
 	struct mlx5_macsec_tables *rx_tables;
 	struct mlx5_flow_handle *rule;
 	int err = 0;
@@ -871,12 +868,12 @@ static int macsec_fs_rx_create_check_decap_rule(struct mlx5_macsec_fs *macsec_fs
 	reformat_params.type = MLX5_REFORMAT_TYPE_DEL_MACSEC;
 	reformat_params.size = reformat_param_size;
 	reformat_params.data = mlx5_reformat_buf;
-	flow_act->pkt_reformat = mlx5_packet_reformat_alloc(macsec_fs->mdev,
+	flow_act->pkt_reformat = mlx5_packet_reformat_alloc(mdev,
 							    &reformat_params,
 							    MLX5_FLOW_NAMESPACE_KERNEL_RX_MACSEC);
 	if (IS_ERR(flow_act->pkt_reformat)) {
 		err = PTR_ERR(flow_act->pkt_reformat);
-		netdev_err(netdev, "Failed to allocate MACsec Rx reformat context err=%d\n", err);
+		mlx5_core_err(mdev, "Failed to allocate MACsec Rx reformat context err=%d\n", err);
 		return err;
 	}
 	rx_fs->check_rule_pkt_reformat[rule_index] = flow_act->pkt_reformat;
@@ -908,7 +905,7 @@ static int macsec_fs_rx_create_check_decap_rule(struct mlx5_macsec_fs *macsec_fs
 	rule = mlx5_add_flow_rules(rx_tables->ft_check, spec, flow_act, dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		netdev_err(netdev, "Failed to add MACsec Rx check rule, err=%d\n", err);
+		mlx5_core_err(mdev, "Failed to add MACsec Rx check rule, err=%d\n", err);
 		return err;
 	}
 
@@ -921,7 +918,7 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
-	struct net_device *netdev = macsec_fs->netdev;
+	struct mlx5_core_dev *mdev = macsec_fs->mdev;
 	struct mlx5_macsec_flow_table *ft_crypto;
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_destination dest = {};
@@ -935,7 +932,7 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 	u32 *flow_group_in;
 	int err;
 
-	ns = mlx5_get_flow_namespace(macsec_fs->mdev, MLX5_FLOW_NAMESPACE_KERNEL_RX_MACSEC);
+	ns = mlx5_get_flow_namespace(mdev, MLX5_FLOW_NAMESPACE_KERNEL_RX_MACSEC);
 	if (!ns)
 		return -ENOMEM;
 
@@ -959,7 +956,7 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 	flow_table = mlx5_create_flow_table(ns, &ft_attr);
 	if (IS_ERR(flow_table)) {
 		err = PTR_ERR(flow_table);
-		netdev_err(netdev, "Failed to create MACsec Rx crypto table err(%d)\n", err);
+		mlx5_core_err(mdev, "Failed to create MACsec Rx crypto table err(%d)\n", err);
 		goto out_flow_group;
 	}
 	ft_crypto->t = flow_table;
@@ -967,9 +964,9 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 	/* Rx crypto table groups */
 	err = macsec_fs_rx_create_crypto_table_groups(ft_crypto);
 	if (err) {
-		netdev_err(netdev,
-			   "Failed to create default flow group for MACsec Tx crypto table err(%d)\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to create default flow group for MACsec Tx crypto table err(%d)\n",
+			      err);
 		goto err;
 	}
 
@@ -977,9 +974,9 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 	rule = mlx5_add_flow_rules(ft_crypto->t, NULL, &flow_act, NULL, 0);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		netdev_err(netdev,
-			   "Failed to add MACsec Rx crypto table default miss rule %d\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to add MACsec Rx crypto table default miss rule %d\n",
+			      err);
 		goto err;
 	}
 	rx_tables->crypto_miss_rule = rule;
@@ -991,7 +988,7 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 						       RX_CHECK_TABLE_NUM_FTE);
 	if (IS_ERR(flow_table)) {
 		err = PTR_ERR(flow_table);
-		netdev_err(netdev, "fail to create MACsec RX check table, err(%d)\n", err);
+		mlx5_core_err(mdev, "Fail to create MACsec RX check table, err(%d)\n", err);
 		goto err;
 	}
 	rx_tables->ft_check = flow_table;
@@ -1002,9 +999,9 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 	flow_group = mlx5_create_flow_group(rx_tables->ft_check, flow_group_in);
 	if (IS_ERR(flow_group)) {
 		err = PTR_ERR(flow_group);
-		netdev_err(netdev,
-			   "Failed to create default flow group for MACsec Rx check table err(%d)\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to create default flow group for MACsec Rx check table err(%d)\n",
+			      err);
 		goto err;
 	}
 	rx_tables->ft_check_group = flow_group;
@@ -1018,7 +1015,7 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 	rule = mlx5_add_flow_rules(rx_tables->ft_check,  NULL, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		netdev_err(netdev, "Failed to added MACsec Rx check drop rule, err(%d)\n", err);
+		mlx5_core_err(mdev, "Failed to added MACsec Rx check drop rule, err(%d)\n", err);
 		goto err;
 	}
 	rx_tables->check_miss_rule = rule;
@@ -1147,7 +1144,7 @@ macsec_fs_rx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 {
 	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
 	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
-	struct net_device *netdev = macsec_fs->netdev;
+	struct mlx5_core_dev *mdev = macsec_fs->mdev;
 	union mlx5_macsec_rule *macsec_rule = NULL;
 	struct mlx5_modify_hdr *modify_hdr = NULL;
 	struct mlx5_macsec_flow_table *ft_crypto;
@@ -1185,11 +1182,11 @@ macsec_fs_rx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	MLX5_SET(set_action_in, action, offset, 0);
 	MLX5_SET(set_action_in, action, length, 32);
 
-	modify_hdr = mlx5_modify_header_alloc(macsec_fs->mdev, MLX5_FLOW_NAMESPACE_KERNEL_RX_MACSEC,
+	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL_RX_MACSEC,
 					      1, action);
 	if (IS_ERR(modify_hdr)) {
 		err = PTR_ERR(modify_hdr);
-		netdev_err(netdev, "fail to alloc MACsec set modify_header_id err=%d\n", err);
+		mlx5_core_err(mdev, "Fail to alloc MACsec set modify_header_id err=%d\n", err);
 		modify_hdr = NULL;
 		goto err;
 	}
@@ -1208,9 +1205,9 @@ macsec_fs_rx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	rule = mlx5_add_flow_rules(ft_crypto->t, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		netdev_err(netdev,
-			   "Failed to add SA with SCI rule to Rx crypto rule, err=%d\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to add SA with SCI rule to Rx crypto rule, err=%d\n",
+			      err);
 		goto err;
 	}
 	rx_rule->rule[0] = rule;
@@ -1233,9 +1230,9 @@ macsec_fs_rx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 		rule = mlx5_add_flow_rules(ft_crypto->t, spec, &flow_act, &dest, 1);
 		if (IS_ERR(rule)) {
 			err = PTR_ERR(rule);
-			netdev_err(netdev,
-				   "Failed to add SA without SCI rule to Rx crypto rule, err=%d\n",
-				   err);
+			mlx5_core_err(mdev,
+				      "Failed to add SA without SCI rule to Rx crypto rule, err=%d\n",
+				      err);
 			goto err;
 		}
 		rx_rule->rule[1] = rule;
@@ -1254,7 +1251,6 @@ out_spec:
 
 static int macsec_fs_rx_init(struct mlx5_macsec_fs *macsec_fs)
 {
-	struct net_device *netdev = macsec_fs->netdev;
 	struct mlx5_core_dev *mdev = macsec_fs->mdev;
 	struct mlx5_macsec_tables *rx_tables;
 	struct mlx5_macsec_rx *rx_fs;
@@ -1268,9 +1264,9 @@ static int macsec_fs_rx_init(struct mlx5_macsec_fs *macsec_fs)
 	flow_counter = mlx5_fc_create(mdev, false);
 	if (IS_ERR(flow_counter)) {
 		err = PTR_ERR(flow_counter);
-		netdev_err(netdev,
-			   "Failed to create MACsec Rx encrypt flow counter, err(%d)\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to create MACsec Rx encrypt flow counter, err(%d)\n",
+			      err);
 		goto err_encrypt_counter;
 	}
 
@@ -1280,9 +1276,9 @@ static int macsec_fs_rx_init(struct mlx5_macsec_fs *macsec_fs)
 	flow_counter = mlx5_fc_create(mdev, false);
 	if (IS_ERR(flow_counter)) {
 		err = PTR_ERR(flow_counter);
-		netdev_err(netdev,
-			   "Failed to create MACsec Rx drop flow counter, err(%d)\n",
-			   err);
+		mlx5_core_err(mdev,
+			      "Failed to create MACsec Rx drop flow counter, err(%d)\n",
+			      err);
 		goto err_drop_counter;
 	}
 	rx_tables->check_miss_rule_counter = flow_counter;
@@ -1314,9 +1310,9 @@ static void macsec_fs_rx_cleanup(struct mlx5_macsec_fs *macsec_fs)
 	rx_tables = &rx_fs->tables;
 
 	if (rx_tables->refcnt) {
-		netdev_err(macsec_fs->netdev,
-			   "Can't destroy MACsec offload rx_fs, refcnt(%u) isn't 0\n",
-			   rx_tables->refcnt);
+		mlx5_core_err(mdev,
+			      "Can't destroy MACsec offload rx_fs, refcnt(%u) isn't 0\n",
+			      rx_tables->refcnt);
 		return;
 	}
 
@@ -1394,8 +1390,7 @@ void mlx5_macsec_fs_cleanup(struct mlx5_macsec_fs *macsec_fs)
 }
 
 struct mlx5_macsec_fs *
-mlx5_macsec_fs_init(struct mlx5_core_dev *mdev,
-		    struct net_device *netdev)
+mlx5_macsec_fs_init(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_macsec_fs *macsec_fs;
 	int err;
@@ -1405,17 +1400,16 @@ mlx5_macsec_fs_init(struct mlx5_core_dev *mdev,
 		return NULL;
 
 	macsec_fs->mdev = mdev;
-	macsec_fs->netdev = netdev;
 
 	err = macsec_fs_tx_init(macsec_fs);
 	if (err) {
-		netdev_err(netdev, "MACsec offload: Failed to init tx_fs, err=%d\n", err);
+		mlx5_core_err(mdev, "MACsec offload: Failed to init tx_fs, err=%d\n", err);
 		goto err;
 	}
 
 	err = macsec_fs_rx_init(macsec_fs);
 	if (err) {
-		netdev_err(netdev, "MACsec offload: Failed to init tx_fs, err=%d\n", err);
+		mlx5_core_err(mdev, "MACsec offload: Failed to init tx_fs, err=%d\n", err);
 		goto tx_cleanup;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
index c0c28d08eae51..f007c33369c28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
@@ -43,7 +43,7 @@ enum mlx5_macsec_action {
 void mlx5_macsec_fs_cleanup(struct mlx5_macsec_fs *macsec_fs);
 
 struct mlx5_macsec_fs *
-mlx5_macsec_fs_init(struct mlx5_core_dev *mdev, struct net_device *netdev);
+mlx5_macsec_fs_init(struct mlx5_core_dev *mdev);
 
 union mlx5_macsec_rule *
 mlx5_macsec_fs_add_rule(struct mlx5_macsec_fs *macsec_fs,
-- 
GitLab


From d4ece08f4b1d29471cc4c0eb0c87427600a77acd Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Sun, 8 Jan 2023 15:25:44 +0200
Subject: [PATCH 1364/1806] net/mlx5: Maintain fs_id xarray per MACsec device
 inside macsec steering

Remove fs_id from the MACsec SA, since it has no real usage there and
instead maintain with the MACsec steering data inside the core.

Downstream patches requires this change to facilitate IB driver accesses
to the fs_ids to avoid RoCE MACsec dependency on EN driver.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/macsec.c      | 115 +++-----
 .../mellanox/mlx5/core/lib/macsec_fs.c        | 247 +++++++++++++++++-
 .../mellanox/mlx5/core/lib/macsec_fs.h        |   3 +-
 3 files changed, 271 insertions(+), 94 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index fb599bacbe30f..b4f3f4f10af32 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -65,8 +65,6 @@ struct mlx5e_macsec_sa {
 	ssci_t ssci;
 	salt_t salt;
 
-	struct rhash_head hash;
-	u32 fs_id;
 	union mlx5_macsec_rule *macsec_rule;
 	struct rcu_head rcu_head;
 	struct mlx5e_macsec_epn_state epn_state;
@@ -105,14 +103,6 @@ struct mlx5e_macsec_aso {
 	u32 pdn;
 };
 
-static const struct rhashtable_params rhash_sci = {
-	.key_len = sizeof_field(struct mlx5e_macsec_sa, sci),
-	.key_offset = offsetof(struct mlx5e_macsec_sa, sci),
-	.head_offset = offsetof(struct mlx5e_macsec_sa, hash),
-	.automatic_shrinking = true,
-	.min_size = 1,
-};
-
 struct mlx5e_macsec_device {
 	const struct net_device *netdev;
 	struct mlx5e_macsec_sa *tx_sa[MACSEC_NUM_AN];
@@ -126,9 +116,6 @@ struct mlx5e_macsec {
 	int num_of_devices;
 	struct mutex lock; /* Protects mlx5e_macsec internal contexts */
 
-	/* Tx sci -> fs id mapping handling */
-	struct rhashtable sci_hash;      /* sci -> mlx5e_macsec_sa */
-
 	/* Rx fs_id -> rx_sc mapping */
 	struct xarray sc_xarray;
 
@@ -325,29 +312,23 @@ static void mlx5e_macsec_destroy_object(struct mlx5_core_dev *mdev, u32 macsec_o
 
 static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec,
 				    struct mlx5e_macsec_sa *sa,
-				    bool is_tx)
+				    bool is_tx, struct net_device *netdev, u32 fs_id)
 {
 	int action =  (is_tx) ?  MLX5_ACCEL_MACSEC_ACTION_ENCRYPT :
 				 MLX5_ACCEL_MACSEC_ACTION_DECRYPT;
 
-	if ((is_tx) && sa->fs_id) {
-		/* Make sure ongoing datapath readers sees a valid SA */
-		rhashtable_remove_fast(&macsec->sci_hash, &sa->hash, rhash_sci);
-		sa->fs_id = 0;
-	}
-
 	if (!sa->macsec_rule)
 		return;
 
-	mlx5_macsec_fs_del_rule(macsec->mdev->macsec_fs, sa->macsec_rule, action);
+	mlx5_macsec_fs_del_rule(macsec->mdev->macsec_fs, sa->macsec_rule, action, netdev,
+				fs_id);
 	mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id);
 	sa->macsec_rule = NULL;
 }
 
 static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
 				struct mlx5e_macsec_sa *sa,
-				bool encrypt,
-				bool is_tx)
+				bool encrypt, bool is_tx, u32 *fs_id)
 {
 	struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev);
 	struct mlx5e_macsec *macsec = priv->macsec;
@@ -382,7 +363,7 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
 	rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT :
 				      MLX5_ACCEL_MACSEC_ACTION_DECRYPT;
 
-	macsec_rule = mlx5_macsec_fs_add_rule(mdev->macsec_fs, ctx, &rule_attrs, &sa->fs_id);
+	macsec_rule = mlx5_macsec_fs_add_rule(mdev->macsec_fs, ctx, &rule_attrs, fs_id);
 	if (!macsec_rule) {
 		err = -ENOMEM;
 		goto destroy_macsec_object;
@@ -390,16 +371,8 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
 
 	sa->macsec_rule = macsec_rule;
 
-	if (is_tx) {
-		err = rhashtable_insert_fast(&macsec->sci_hash, &sa->hash, rhash_sci);
-		if (err)
-			goto destroy_macsec_object_and_rule;
-	}
-
 	return 0;
 
-destroy_macsec_object_and_rule:
-	mlx5e_macsec_cleanup_sa(macsec, sa, is_tx);
 destroy_macsec_object:
 	mlx5e_macsec_destroy_object(mdev, sa->macsec_obj_id);
 
@@ -421,7 +394,7 @@ mlx5e_macsec_get_rx_sc_from_sc_list(const struct list_head *list, sci_t sci)
 
 static int macsec_rx_sa_active_update(struct macsec_context *ctx,
 				      struct mlx5e_macsec_sa *rx_sa,
-				      bool active)
+				      bool active, u32 *fs_id)
 {
 	struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev);
 	struct mlx5e_macsec *macsec = priv->macsec;
@@ -432,11 +405,11 @@ static int macsec_rx_sa_active_update(struct macsec_context *ctx,
 
 	rx_sa->active = active;
 	if (!active) {
-		mlx5e_macsec_cleanup_sa(macsec, rx_sa, false);
+		mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, *fs_id);
 		return 0;
 	}
 
-	err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false);
+	err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false, fs_id);
 	if (err)
 		rx_sa->active = false;
 
@@ -558,7 +531,7 @@ static int mlx5e_macsec_add_txsa(struct macsec_context *ctx)
 	    !tx_sa->active)
 		goto out;
 
-	err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true);
+	err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL);
 	if (err)
 		goto destroy_encryption_key;
 
@@ -622,7 +595,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx)
 		goto out;
 
 	if (ctx_tx_sa->active) {
-		err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true);
+		err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL);
 		if (err)
 			goto out;
 	} else {
@@ -631,7 +604,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx)
 			goto out;
 		}
 
-		mlx5e_macsec_cleanup_sa(macsec, tx_sa, true);
+		mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0);
 	}
 out:
 	mutex_unlock(&macsec->lock);
@@ -664,7 +637,7 @@ static int mlx5e_macsec_del_txsa(struct macsec_context *ctx)
 		goto out;
 	}
 
-	mlx5e_macsec_cleanup_sa(macsec, tx_sa, true);
+	mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0);
 	mlx5_destroy_encryption_key(macsec->mdev, tx_sa->enc_key_id);
 	kfree_rcu_mightsleep(tx_sa);
 	macsec_device->tx_sa[assoc_num] = NULL;
@@ -675,20 +648,6 @@ out:
 	return err;
 }
 
-static u32 mlx5e_macsec_get_sa_from_hashtable(struct rhashtable *sci_hash, sci_t *sci)
-{
-	struct mlx5e_macsec_sa *macsec_sa;
-	u32 fs_id = 0;
-
-	rcu_read_lock();
-	macsec_sa = rhashtable_lookup(sci_hash, sci, rhash_sci);
-	if (macsec_sa)
-		fs_id = macsec_sa->fs_id;
-	rcu_read_unlock();
-
-	return fs_id;
-}
-
 static int mlx5e_macsec_add_rxsc(struct macsec_context *ctx)
 {
 	struct mlx5e_macsec_rx_sc_xarray_element *sc_xarray_element;
@@ -808,7 +767,8 @@ static int mlx5e_macsec_upd_rxsc(struct macsec_context *ctx)
 		if (!rx_sa)
 			continue;
 
-		err = macsec_rx_sa_active_update(ctx, rx_sa, rx_sa->active && ctx_rx_sc->active);
+		err = macsec_rx_sa_active_update(ctx, rx_sa, rx_sa->active && ctx_rx_sc->active,
+						 &rx_sc->sc_xarray_element->fs_id);
 		if (err)
 			goto out;
 	}
@@ -819,7 +779,8 @@ out:
 	return err;
 }
 
-static void macsec_del_rxsc_ctx(struct mlx5e_macsec *macsec, struct mlx5e_macsec_rx_sc *rx_sc)
+static void macsec_del_rxsc_ctx(struct mlx5e_macsec *macsec, struct mlx5e_macsec_rx_sc *rx_sc,
+				struct net_device *netdev)
 {
 	struct mlx5e_macsec_sa *rx_sa;
 	int i;
@@ -829,7 +790,8 @@ static void macsec_del_rxsc_ctx(struct mlx5e_macsec *macsec, struct mlx5e_macsec
 		if (!rx_sa)
 			continue;
 
-		mlx5e_macsec_cleanup_sa(macsec, rx_sa, false);
+		mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, netdev,
+					rx_sc->sc_xarray_element->fs_id);
 		mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id);
 
 		kfree(rx_sa);
@@ -877,7 +839,7 @@ static int mlx5e_macsec_del_rxsc(struct macsec_context *ctx)
 		goto out;
 	}
 
-	macsec_del_rxsc_ctx(macsec, rx_sc);
+	macsec_del_rxsc_ctx(macsec, rx_sc, ctx->secy->netdev);
 out:
 	mutex_unlock(&macsec->lock);
 
@@ -936,7 +898,6 @@ static int mlx5e_macsec_add_rxsa(struct macsec_context *ctx)
 	rx_sa->next_pn = ctx_rx_sa->next_pn;
 	rx_sa->sci = sci;
 	rx_sa->assoc_num = assoc_num;
-	rx_sa->fs_id = rx_sc->sc_xarray_element->fs_id;
 
 	if (ctx->secy->xpn)
 		update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves,
@@ -953,7 +914,7 @@ static int mlx5e_macsec_add_rxsa(struct macsec_context *ctx)
 		goto out;
 
 	//TODO - add support for both authentication and encryption flows
-	err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false);
+	err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false, &rx_sc->sc_xarray_element->fs_id);
 	if (err)
 		goto destroy_encryption_key;
 
@@ -1020,7 +981,8 @@ static int mlx5e_macsec_upd_rxsa(struct macsec_context *ctx)
 		goto out;
 	}
 
-	err = macsec_rx_sa_active_update(ctx, rx_sa, ctx_rx_sa->active);
+	err = macsec_rx_sa_active_update(ctx, rx_sa, ctx_rx_sa->active,
+					 &rx_sc->sc_xarray_element->fs_id);
 out:
 	mutex_unlock(&macsec->lock);
 
@@ -1068,7 +1030,8 @@ static int mlx5e_macsec_del_rxsa(struct macsec_context *ctx)
 		goto out;
 	}
 
-	mlx5e_macsec_cleanup_sa(macsec, rx_sa, false);
+	mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev,
+				rx_sc->sc_xarray_element->fs_id);
 	mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id);
 	kfree(rx_sa);
 	rx_sc->rx_sa[assoc_num] = NULL;
@@ -1149,7 +1112,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx,
 			if (!rx_sa || !rx_sa->macsec_rule)
 				continue;
 
-			mlx5e_macsec_cleanup_sa(macsec, rx_sa, false);
+			mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev,
+						rx_sc->sc_xarray_element->fs_id);
 		}
 	}
 
@@ -1160,7 +1124,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx,
 				continue;
 
 			if (rx_sa->active) {
-				err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false);
+				err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false,
+							   &rx_sc->sc_xarray_element->fs_id);
 				if (err)
 					goto out;
 			}
@@ -1213,7 +1178,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx)
 		if (!tx_sa)
 			continue;
 
-		mlx5e_macsec_cleanup_sa(macsec, tx_sa, true);
+		mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0);
 	}
 
 	for (i = 0; i < MACSEC_NUM_AN; ++i) {
@@ -1222,7 +1187,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx)
 			continue;
 
 		if (tx_sa->assoc_num == tx_sc->encoding_sa && tx_sa->active) {
-			err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true);
+			err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL);
 			if (err)
 				goto out;
 		}
@@ -1260,7 +1225,7 @@ static int mlx5e_macsec_del_secy(struct macsec_context *ctx)
 		if (!tx_sa)
 			continue;
 
-		mlx5e_macsec_cleanup_sa(macsec, tx_sa, true);
+		mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0);
 		mlx5_destroy_encryption_key(macsec->mdev, tx_sa->enc_key_id);
 		kfree(tx_sa);
 		macsec_device->tx_sa[i] = NULL;
@@ -1268,7 +1233,7 @@ static int mlx5e_macsec_del_secy(struct macsec_context *ctx)
 
 	list = &macsec_device->macsec_rx_sc_list_head;
 	list_for_each_entry_safe(rx_sc, tmp, list, rx_sc_list_element)
-		macsec_del_rxsc_ctx(macsec, rx_sc);
+		macsec_del_rxsc_ctx(macsec, rx_sc, ctx->secy->netdev);
 
 	kfree(macsec_device->dev_addr);
 	macsec_device->dev_addr = NULL;
@@ -1693,7 +1658,8 @@ bool mlx5e_macsec_handle_tx_skb(struct mlx5e_macsec *macsec, struct sk_buff *skb
 	struct metadata_dst *md_dst = skb_metadata_dst(skb);
 	u32 fs_id;
 
-	fs_id = mlx5e_macsec_get_sa_from_hashtable(&macsec->sci_hash, &md_dst->u.macsec_info.sci);
+	fs_id = mlx5_macsec_fs_get_fs_id_from_hashtable(macsec->mdev->macsec_fs,
+							&md_dst->u.macsec_info.sci);
 	if (!fs_id)
 		goto err_out;
 
@@ -1711,7 +1677,8 @@ void mlx5e_macsec_tx_build_eseg(struct mlx5e_macsec *macsec,
 	struct metadata_dst *md_dst = skb_metadata_dst(skb);
 	u32 fs_id;
 
-	fs_id = mlx5e_macsec_get_sa_from_hashtable(&macsec->sci_hash, &md_dst->u.macsec_info.sci);
+	fs_id = mlx5_macsec_fs_get_fs_id_from_hashtable(macsec->mdev->macsec_fs,
+							&md_dst->u.macsec_info.sci);
 	if (!fs_id)
 		return;
 
@@ -1779,13 +1746,6 @@ int mlx5e_macsec_init(struct mlx5e_priv *priv)
 	INIT_LIST_HEAD(&macsec->macsec_device_list_head);
 	mutex_init(&macsec->lock);
 
-	err = rhashtable_init(&macsec->sci_hash, &rhash_sci);
-	if (err) {
-		mlx5_core_err(mdev, "MACsec offload: Failed to init SCI hash table, err=%d\n",
-			      err);
-		goto err_hash;
-	}
-
 	err = mlx5e_macsec_aso_init(&macsec->aso, priv->mdev);
 	if (err) {
 		mlx5_core_err(mdev, "MACsec offload: Failed to init aso, err=%d\n", err);
@@ -1824,8 +1784,6 @@ err_out:
 err_wq:
 	mlx5e_macsec_aso_cleanup(&macsec->aso, priv->mdev);
 err_aso:
-	rhashtable_destroy(&macsec->sci_hash);
-err_hash:
 	kfree(macsec);
 	priv->macsec = NULL;
 	return err;
@@ -1843,7 +1801,6 @@ void mlx5e_macsec_cleanup(struct mlx5e_priv *priv)
 	mlx5_macsec_fs_cleanup(mdev->macsec_fs);
 	destroy_workqueue(macsec->wq);
 	mlx5e_macsec_aso_cleanup(&macsec->aso, mdev);
-	rhashtable_destroy(&macsec->sci_hash);
 	mutex_destroy(&macsec->lock);
 	kfree(macsec);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index 8ecc91f30da13..b3528516ba35f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -74,6 +74,20 @@ struct mlx5_macsec_tables {
 	u32 refcnt;
 };
 
+struct mlx5_fs_id {
+	u32 id;
+	refcount_t refcnt;
+	sci_t sci;
+	struct rhash_head hash;
+};
+
+struct mlx5_macsec_device {
+	struct list_head macsec_devices_list_entry;
+	void *macdev;
+	struct xarray tx_id_xa;
+	struct xarray rx_id_xa;
+};
+
 struct mlx5_macsec_tx {
 	struct mlx5_flow_handle *crypto_mke_rule;
 	struct mlx5_flow_handle *check_rule;
@@ -100,6 +114,22 @@ union mlx5_macsec_rule {
 	struct mlx5_macsec_rx_rule rx_rule;
 };
 
+static const struct rhashtable_params rhash_sci = {
+	.key_len = sizeof_field(struct mlx5_fs_id, sci),
+	.key_offset = offsetof(struct mlx5_fs_id, sci),
+	.head_offset = offsetof(struct mlx5_fs_id, hash),
+	.automatic_shrinking = true,
+	.min_size = 1,
+};
+
+static const struct rhashtable_params rhash_fs_id = {
+	.key_len = sizeof_field(struct mlx5_fs_id, id),
+	.key_offset = offsetof(struct mlx5_fs_id, id),
+	.head_offset = offsetof(struct mlx5_fs_id, hash),
+	.automatic_shrinking = true,
+	.min_size = 1,
+};
+
 struct mlx5_macsec_fs {
 	struct mlx5_core_dev *mdev;
 	struct mlx5_macsec_tx *tx_fs;
@@ -107,6 +137,15 @@ struct mlx5_macsec_fs {
 
 	/* Stats manage */
 	struct mlx5_macsec_stats stats;
+
+	/* Tx sci -> fs id mapping handling */
+	struct rhashtable sci_hash;      /* sci -> mlx5_fs_id */
+
+	/* RX fs_id -> mlx5_fs_id mapping handling */
+	struct rhashtable fs_id_hash;      /* fs_id -> mlx5_fs_id */
+
+	/* TX & RX fs_id lists per macsec device */
+	struct list_head macsec_devices_list;
 };
 
 static void macsec_fs_destroy_groups(struct mlx5_macsec_flow_table *ft)
@@ -512,9 +551,137 @@ static void macsec_fs_tx_create_sectag_header(const struct macsec_context *ctx,
 	memcpy(reformatbf, &sectag, *reformat_size);
 }
 
+static bool macsec_fs_is_macsec_device_empty(struct mlx5_macsec_device *macsec_device)
+{
+	if (xa_empty(&macsec_device->tx_id_xa) &&
+	    xa_empty(&macsec_device->rx_id_xa))
+		return true;
+
+	return false;
+}
+
+static void macsec_fs_id_del(struct list_head *macsec_devices_list, u32 fs_id,
+			     void *macdev, struct rhashtable *hash_table, bool is_tx)
+{
+	const struct rhashtable_params *rhash = (is_tx) ? &rhash_sci : &rhash_fs_id;
+	struct mlx5_macsec_device *iter, *macsec_device = NULL;
+	struct mlx5_fs_id *fs_id_found;
+	struct xarray *fs_id_xa;
+
+	list_for_each_entry(iter, macsec_devices_list, macsec_devices_list_entry) {
+		if (iter->macdev == macdev) {
+			macsec_device = iter;
+			break;
+		}
+	}
+	WARN_ON(!macsec_device);
+
+	fs_id_xa = (is_tx) ? &macsec_device->tx_id_xa :
+			     &macsec_device->rx_id_xa;
+	xa_lock(fs_id_xa);
+	fs_id_found = xa_load(fs_id_xa, fs_id);
+	WARN_ON(!fs_id_found);
+
+	if (!refcount_dec_and_test(&fs_id_found->refcnt)) {
+		xa_unlock(fs_id_xa);
+		return;
+	}
+
+	if (fs_id_found->id) {
+		/* Make sure ongoing datapath readers sees a valid SA */
+		rhashtable_remove_fast(hash_table, &fs_id_found->hash, *rhash);
+		fs_id_found->id = 0;
+	}
+	xa_unlock(fs_id_xa);
+
+	xa_erase(fs_id_xa, fs_id);
+
+	kfree(fs_id_found);
+
+	if (macsec_fs_is_macsec_device_empty(macsec_device)) {
+		list_del(&macsec_device->macsec_devices_list_entry);
+		kfree(macsec_device);
+	}
+}
+
+static int macsec_fs_id_add(struct list_head *macsec_devices_list, u32 fs_id,
+			    void *macdev, struct rhashtable *hash_table, sci_t sci,
+			    bool is_tx)
+{
+	const struct rhashtable_params *rhash = (is_tx) ? &rhash_sci : &rhash_fs_id;
+	struct mlx5_macsec_device *iter, *macsec_device = NULL;
+	struct mlx5_fs_id *fs_id_iter;
+	struct xarray *fs_id_xa;
+	int err;
+
+	if (!is_tx) {
+		rcu_read_lock();
+		fs_id_iter = rhashtable_lookup(hash_table, &fs_id, rhash_fs_id);
+		if (fs_id_iter) {
+			refcount_inc(&fs_id_iter->refcnt);
+			rcu_read_unlock();
+			return 0;
+		}
+		rcu_read_unlock();
+	}
+
+	fs_id_iter = kzalloc(sizeof(*fs_id_iter), GFP_KERNEL);
+	if (!fs_id_iter)
+		return -ENOMEM;
+
+	list_for_each_entry(iter, macsec_devices_list, macsec_devices_list_entry) {
+		if (iter->macdev == macdev) {
+			macsec_device = iter;
+			break;
+		}
+	}
+
+	if (!macsec_device) { /* first time adding a SA to that device */
+		macsec_device = kzalloc(sizeof(*macsec_device), GFP_KERNEL);
+		if (!macsec_device) {
+			err = -ENOMEM;
+			goto err_alloc_dev;
+		}
+		macsec_device->macdev = macdev;
+		xa_init(&macsec_device->tx_id_xa);
+		xa_init(&macsec_device->rx_id_xa);
+		list_add(&macsec_device->macsec_devices_list_entry, macsec_devices_list);
+	}
+
+	fs_id_xa = (is_tx) ? &macsec_device->tx_id_xa :
+			     &macsec_device->rx_id_xa;
+	fs_id_iter->id = fs_id;
+	refcount_set(&fs_id_iter->refcnt, 1);
+	fs_id_iter->sci = sci;
+	err = xa_err(xa_store(fs_id_xa, fs_id, fs_id_iter, GFP_KERNEL));
+	if (err)
+		goto err_store_id;
+
+	err = rhashtable_insert_fast(hash_table, &fs_id_iter->hash, *rhash);
+	if (err)
+		goto err_hash_insert;
+
+	return 0;
+
+err_hash_insert:
+	xa_erase(fs_id_xa, fs_id);
+err_store_id:
+	if (macsec_fs_is_macsec_device_empty(macsec_device)) {
+		list_del(&macsec_device->macsec_devices_list_entry);
+		kfree(macsec_device);
+	}
+err_alloc_dev:
+	kfree(fs_id_iter);
+	return err;
+}
+
 static void macsec_fs_tx_del_rule(struct mlx5_macsec_fs *macsec_fs,
-				  struct mlx5_macsec_tx_rule *tx_rule)
+				  struct mlx5_macsec_tx_rule *tx_rule,
+				  void *macdev)
 {
+	macsec_fs_id_del(&macsec_fs->macsec_devices_list, tx_rule->fs_id, macdev,
+			 &macsec_fs->sci_hash, true);
+
 	if (tx_rule->rule) {
 		mlx5_del_flow_rules(tx_rule->rule);
 		tx_rule->rule = NULL;
@@ -540,8 +707,7 @@ static void macsec_fs_tx_del_rule(struct mlx5_macsec_fs *macsec_fs,
 static union mlx5_macsec_rule *
 macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 		      const struct macsec_context *macsec_ctx,
-		      struct mlx5_macsec_rule_attrs *attrs,
-		      u32 *sa_fs_id)
+		      struct mlx5_macsec_rule_attrs *attrs)
 {
 	char reformatbf[MLX5_MACSEC_TAG_LEN + MACSEC_SCI_LEN];
 	struct mlx5_pkt_reformat_params reformat_params = {};
@@ -605,7 +771,6 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	}
 
 	tx_rule->fs_id = fs_id;
-	*sa_fs_id = fs_id;
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 			  MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT |
@@ -620,10 +785,17 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	}
 	tx_rule->rule = rule;
 
+	err = macsec_fs_id_add(&macsec_fs->macsec_devices_list, fs_id, macsec_ctx->secy->netdev,
+			       &macsec_fs->sci_hash, attrs->sci, true);
+	if (err) {
+		mlx5_core_err(mdev, "Failed to save fs_id, err=%d\n", err);
+		goto err;
+	}
+
 	goto out_spec;
 
 err:
-	macsec_fs_tx_del_rule(macsec_fs, tx_rule);
+	macsec_fs_tx_del_rule(macsec_fs, tx_rule, macsec_ctx->secy->netdev);
 	macsec_rule = NULL;
 out_spec:
 	kvfree(spec);
@@ -699,6 +871,7 @@ static int macsec_fs_tx_init(struct mlx5_macsec_fs *macsec_fs)
 	tx_tables->check_miss_rule_counter = flow_counter;
 
 	ida_init(&tx_fs->tx_halloc);
+	INIT_LIST_HEAD(&macsec_fs->macsec_devices_list);
 
 	macsec_fs->tx_fs = tx_fs;
 
@@ -1070,10 +1243,14 @@ static void macsec_fs_rx_ft_put(struct mlx5_macsec_fs *macsec_fs)
 }
 
 static void macsec_fs_rx_del_rule(struct mlx5_macsec_fs *macsec_fs,
-				  struct mlx5_macsec_rx_rule *rx_rule)
+				  struct mlx5_macsec_rx_rule *rx_rule,
+				  void *macdev, u32 fs_id)
 {
 	int i;
 
+	macsec_fs_id_del(&macsec_fs->macsec_devices_list, fs_id, macdev,
+			 &macsec_fs->fs_id_hash, false);
+
 	for (i = 0; i < RX_NUM_OF_RULES_PER_SA; ++i) {
 		if (rx_rule->rule[i]) {
 			mlx5_del_flow_rules(rx_rule->rule[i]);
@@ -1139,6 +1316,7 @@ static void macsec_fs_rx_setup_fte(struct mlx5_flow_spec *spec,
 
 static union mlx5_macsec_rule *
 macsec_fs_rx_add_rule(struct mlx5_macsec_fs *macsec_fs,
+		      const struct macsec_context *macsec_ctx,
 		      struct mlx5_macsec_rule_attrs *attrs,
 		      u32 fs_id)
 {
@@ -1238,11 +1416,18 @@ macsec_fs_rx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 		rx_rule->rule[1] = rule;
 	}
 
+	err = macsec_fs_id_add(&macsec_fs->macsec_devices_list, fs_id, macsec_ctx->secy->netdev,
+			       &macsec_fs->fs_id_hash, attrs->sci, false);
+	if (err) {
+		mlx5_core_err(mdev, "Failed to save fs_id, err=%d\n", err);
+		goto err;
+	}
+
 	kvfree(spec);
 	return macsec_rule;
 
 err:
-	macsec_fs_rx_del_rule(macsec_fs, rx_rule);
+	macsec_fs_rx_del_rule(macsec_fs, rx_rule, macsec_ctx->secy->netdev, fs_id);
 	macsec_rule = NULL;
 out_spec:
 	kvfree(spec);
@@ -1362,6 +1547,20 @@ struct mlx5_macsec_stats *mlx5_macsec_fs_get_stats(struct mlx5_macsec_fs *macsec
 	return &macsec_fs->stats;
 }
 
+u32 mlx5_macsec_fs_get_fs_id_from_hashtable(struct mlx5_macsec_fs *macsec_fs, sci_t *sci)
+{
+	struct mlx5_fs_id *mlx5_fs_id;
+	u32 fs_id = 0;
+
+	rcu_read_lock();
+	mlx5_fs_id = rhashtable_lookup(&macsec_fs->sci_hash, sci, rhash_sci);
+	if (mlx5_fs_id)
+		fs_id = mlx5_fs_id->id;
+	rcu_read_unlock();
+
+	return fs_id;
+}
+
 union mlx5_macsec_rule *
 mlx5_macsec_fs_add_rule(struct mlx5_macsec_fs *macsec_fs,
 			const struct macsec_context *macsec_ctx,
@@ -1369,23 +1568,25 @@ mlx5_macsec_fs_add_rule(struct mlx5_macsec_fs *macsec_fs,
 			u32 *sa_fs_id)
 {
 	return (attrs->action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) ?
-		macsec_fs_tx_add_rule(macsec_fs, macsec_ctx, attrs, sa_fs_id) :
-		macsec_fs_rx_add_rule(macsec_fs, attrs, *sa_fs_id);
+		macsec_fs_tx_add_rule(macsec_fs, macsec_ctx, attrs) :
+		macsec_fs_rx_add_rule(macsec_fs, macsec_ctx, attrs, *sa_fs_id);
 }
 
 void mlx5_macsec_fs_del_rule(struct mlx5_macsec_fs *macsec_fs,
 			     union mlx5_macsec_rule *macsec_rule,
-			     int action)
+			     int action, void *macdev, u32 sa_fs_id)
 {
 	(action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) ?
-		macsec_fs_tx_del_rule(macsec_fs, &macsec_rule->tx_rule) :
-		macsec_fs_rx_del_rule(macsec_fs, &macsec_rule->rx_rule);
+		macsec_fs_tx_del_rule(macsec_fs, &macsec_rule->tx_rule, macdev) :
+		macsec_fs_rx_del_rule(macsec_fs, &macsec_rule->rx_rule, macdev, sa_fs_id);
 }
 
 void mlx5_macsec_fs_cleanup(struct mlx5_macsec_fs *macsec_fs)
 {
 	macsec_fs_rx_cleanup(macsec_fs);
 	macsec_fs_tx_cleanup(macsec_fs);
+	rhashtable_destroy(&macsec_fs->fs_id_hash);
+	rhashtable_destroy(&macsec_fs->sci_hash);
 	kfree(macsec_fs);
 }
 
@@ -1401,10 +1602,24 @@ mlx5_macsec_fs_init(struct mlx5_core_dev *mdev)
 
 	macsec_fs->mdev = mdev;
 
+	err = rhashtable_init(&macsec_fs->sci_hash, &rhash_sci);
+	if (err) {
+		mlx5_core_err(mdev, "MACsec offload: Failed to init SCI hash table, err=%d\n",
+			      err);
+		goto err_hash;
+	}
+
+	err = rhashtable_init(&macsec_fs->fs_id_hash, &rhash_fs_id);
+	if (err) {
+		mlx5_core_err(mdev, "MACsec offload: Failed to init FS_ID hash table, err=%d\n",
+			      err);
+		goto sci_hash_cleanup;
+	}
+
 	err = macsec_fs_tx_init(macsec_fs);
 	if (err) {
 		mlx5_core_err(mdev, "MACsec offload: Failed to init tx_fs, err=%d\n", err);
-		goto err;
+		goto fs_id_hash_cleanup;
 	}
 
 	err = macsec_fs_rx_init(macsec_fs);
@@ -1417,7 +1632,11 @@ mlx5_macsec_fs_init(struct mlx5_core_dev *mdev)
 
 tx_cleanup:
 	macsec_fs_tx_cleanup(macsec_fs);
-err:
+fs_id_hash_cleanup:
+	rhashtable_destroy(&macsec_fs->fs_id_hash);
+sci_hash_cleanup:
+	rhashtable_destroy(&macsec_fs->sci_hash);
+err_hash:
 	kfree(macsec_fs);
 	return NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
index f007c33369c28..34b80c3ef6a50 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
@@ -53,10 +53,11 @@ mlx5_macsec_fs_add_rule(struct mlx5_macsec_fs *macsec_fs,
 
 void mlx5_macsec_fs_del_rule(struct mlx5_macsec_fs *macsec_fs,
 			     union mlx5_macsec_rule *macsec_rule,
-			     int action);
+			     int action, void *macdev, u32 sa_fs_id);
 
 void mlx5_macsec_fs_get_stats_fill(struct mlx5_macsec_fs *macsec_fs, void *macsec_stats);
 struct mlx5_macsec_stats *mlx5_macsec_fs_get_stats(struct mlx5_macsec_fs *macsec_fs);
+u32 mlx5_macsec_fs_get_fs_id_from_hashtable(struct mlx5_macsec_fs *macsec_fs, sci_t *sci);
 
 #endif
 
-- 
GitLab


From 758ce14aee825f8f3ca8f76c9991c108094cae8b Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Tue, 3 May 2022 08:37:48 +0300
Subject: [PATCH 1365/1806] RDMA/mlx5: Implement MACsec gid addition and
 deletion

Handle MACsec IP ambiguity issue, since mlx5 hw can't support
programming both the MACsec and the physical gid when they have the same
IP address, because it wouldn't know to whom to steer the traffic.
Hence in such case we delete the physical gid from the hw gid table,
which would then cause all traffic sent over it to fail, and we'll only
be able to send traffic over the MACsec gid.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Raed Salem <raeds@nvidia.com>
Reviewed-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/Makefile           |   1 +
 drivers/infiniband/hw/mlx5/macsec.c           | 155 ++++++++++++++++++
 drivers/infiniband/hw/mlx5/macsec.h           |  25 +++
 drivers/infiniband/hw/mlx5/main.c             |  37 ++++-
 drivers/infiniband/hw/mlx5/mlx5_ib.h          |   7 +
 .../mellanox/mlx5/core/en_accel/macsec.c      |  31 ----
 .../mellanox/mlx5/core/en_accel/macsec.h      |   2 -
 include/linux/mlx5/driver.h                   |  44 +++++
 8 files changed, 260 insertions(+), 42 deletions(-)
 create mode 100644 drivers/infiniband/hw/mlx5/macsec.c
 create mode 100644 drivers/infiniband/hw/mlx5/macsec.h

diff --git a/drivers/infiniband/hw/mlx5/Makefile b/drivers/infiniband/hw/mlx5/Makefile
index 612ee8190a2d3..72a526236c2e0 100644
--- a/drivers/infiniband/hw/mlx5/Makefile
+++ b/drivers/infiniband/hw/mlx5/Makefile
@@ -28,3 +28,4 @@ mlx5_ib-$(CONFIG_INFINIBAND_USER_ACCESS) += devx.o \
 					    fs.o \
 					    qos.o \
 					    std_types.o
+mlx5_ib-$(CONFIG_MLX5_MACSEC) += macsec.o
diff --git a/drivers/infiniband/hw/mlx5/macsec.c b/drivers/infiniband/hw/mlx5/macsec.c
new file mode 100644
index 0000000000000..349ad13af75d7
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/macsec.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */
+
+#include "macsec.h"
+
+struct mlx5_reserved_gids {
+	int macsec_index;
+	const struct ib_gid_attr *physical_gid;
+};
+
+int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev)
+{
+	int i, j, max_gids;
+
+	if (!mlx5_is_macsec_roce_supported(dev->mdev)) {
+		mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n");
+		return 0;
+	}
+
+	max_gids = MLX5_CAP_ROCE(dev->mdev, roce_address_table_size);
+	for (i = 0; i < dev->num_ports; i++) {
+		dev->port[i].reserved_gids = kcalloc(max_gids,
+						     sizeof(*dev->port[i].reserved_gids),
+						     GFP_KERNEL);
+		if (!dev->port[i].reserved_gids)
+			goto err;
+
+		for (j = 0; j < max_gids; j++)
+			dev->port[i].reserved_gids[j].macsec_index = -1;
+	}
+
+	return 0;
+err:
+	while (i >= 0) {
+		kfree(dev->port[i].reserved_gids);
+		i--;
+	}
+	return -ENOMEM;
+}
+
+void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev)
+{
+	int i;
+
+	if (!mlx5_is_macsec_roce_supported(dev->mdev))
+		mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n");
+
+	for (i = 0; i < dev->num_ports; i++)
+		kfree(dev->port[i].reserved_gids);
+}
+
+int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(attr->device);
+	const struct ib_gid_attr *physical_gid;
+	struct mlx5_reserved_gids *mgids;
+	struct net_device *ndev;
+	int ret = 0;
+
+	if (attr->gid_type != IB_GID_TYPE_ROCE_UDP_ENCAP)
+		return 0;
+
+	if (!mlx5_is_macsec_roce_supported(dev->mdev)) {
+		mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n");
+		return 0;
+	}
+
+	rcu_read_lock();
+	ndev = rcu_dereference(attr->ndev);
+	if (!ndev) {
+		rcu_read_unlock();
+		return -ENODEV;
+	}
+
+	if (!netif_is_macsec(ndev) || !macsec_netdev_is_offloaded(ndev)) {
+		rcu_read_unlock();
+		return 0;
+	}
+	rcu_read_unlock();
+
+	physical_gid = rdma_find_gid(attr->device, &attr->gid,
+				     attr->gid_type, NULL);
+	if (IS_ERR(physical_gid))
+		return 0;
+
+	ret = set_roce_addr(to_mdev(physical_gid->device),
+			    physical_gid->port_num,
+			    physical_gid->index, NULL,
+			    physical_gid);
+	if (ret)
+		goto gid_err;
+
+	mgids = &dev->port[attr->port_num - 1].reserved_gids[physical_gid->index];
+	mgids->macsec_index = attr->index;
+	mgids->physical_gid = physical_gid;
+
+	return 0;
+
+gid_err:
+	rdma_put_gid_attr(physical_gid);
+	return ret;
+}
+
+void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(attr->device);
+	struct mlx5_reserved_gids *mgids;
+	struct net_device *ndev;
+	int i, max_gids;
+
+	if (attr->gid_type != IB_GID_TYPE_ROCE_UDP_ENCAP)
+		return;
+
+	if (!mlx5_is_macsec_roce_supported(dev->mdev)) {
+		mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n");
+		return;
+	}
+
+	mgids = &dev->port[attr->port_num - 1].reserved_gids[attr->index];
+	if (mgids->macsec_index != -1) { /* Checking if physical gid has ambiguous IP */
+		rdma_put_gid_attr(mgids->physical_gid);
+		mgids->macsec_index = -1;
+		return;
+	}
+
+	rcu_read_lock();
+	ndev = rcu_dereference(attr->ndev);
+	if (!ndev) {
+		rcu_read_unlock();
+		return;
+	}
+
+	if (!netif_is_macsec(ndev) || !macsec_netdev_is_offloaded(ndev)) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	max_gids = MLX5_CAP_ROCE(dev->mdev, roce_address_table_size);
+	for (i = 0; i < max_gids; i++) { /* Checking if macsec gid has ambiguous IP */
+		mgids = &dev->port[attr->port_num - 1].reserved_gids[i];
+		if (mgids->macsec_index == attr->index) {
+			const struct ib_gid_attr *physical_gid = mgids->physical_gid;
+
+			set_roce_addr(to_mdev(physical_gid->device),
+				      physical_gid->port_num,
+				      physical_gid->index,
+				      &physical_gid->gid, physical_gid);
+
+			rdma_put_gid_attr(physical_gid);
+			mgids->macsec_index = -1;
+			break;
+		}
+	}
+}
diff --git a/drivers/infiniband/hw/mlx5/macsec.h b/drivers/infiniband/hw/mlx5/macsec.h
new file mode 100644
index 0000000000000..b60f8f046d6f4
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/macsec.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */
+
+#ifndef __MLX5_MACSEC_H__
+#define __MLX5_MACSEC_H__
+
+#include <net/macsec.h>
+#include <rdma/ib_cache.h>
+#include <rdma/ib_addr.h>
+#include "mlx5_ib.h"
+
+#ifdef CONFIG_MLX5_MACSEC
+struct mlx5_reserved_gids;
+
+int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr);
+void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr);
+int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev);
+void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev);
+#else
+static inline int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr) { return 0; }
+static inline void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr) {}
+static inline int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev) { return 0; }
+static inline void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev) {}
+#endif
+#endif /* __MLX5_MACSEC_H__ */
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index f0b394ed7452a..f463cf8b75014 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -46,6 +46,7 @@
 #include <rdma/uverbs_ioctl.h>
 #include <rdma/mlx5_user_ioctl_verbs.h>
 #include <rdma/mlx5_user_ioctl_cmds.h>
+#include "macsec.h"
 
 #define UVERBS_MODULE_NAME mlx5_ib
 #include <rdma/uverbs_named_ioctl.h>
@@ -564,9 +565,9 @@ out:
 	return err;
 }
 
-static int set_roce_addr(struct mlx5_ib_dev *dev, u32 port_num,
-			 unsigned int index, const union ib_gid *gid,
-			 const struct ib_gid_attr *attr)
+int set_roce_addr(struct mlx5_ib_dev *dev, u32 port_num,
+		  unsigned int index, const union ib_gid *gid,
+		  const struct ib_gid_attr *attr)
 {
 	enum ib_gid_type gid_type;
 	u16 vlan_id = 0xffff;
@@ -607,6 +608,12 @@ static int set_roce_addr(struct mlx5_ib_dev *dev, u32 port_num,
 static int mlx5_ib_add_gid(const struct ib_gid_attr *attr,
 			   __always_unused void **context)
 {
+	int ret;
+
+	ret = mlx5r_add_gid_macsec_operations(attr);
+	if (ret)
+		return ret;
+
 	return set_roce_addr(to_mdev(attr->device), attr->port_num,
 			     attr->index, &attr->gid, attr);
 }
@@ -614,8 +621,15 @@ static int mlx5_ib_add_gid(const struct ib_gid_attr *attr,
 static int mlx5_ib_del_gid(const struct ib_gid_attr *attr,
 			   __always_unused void **context)
 {
-	return set_roce_addr(to_mdev(attr->device), attr->port_num,
-			     attr->index, NULL, attr);
+	int ret;
+
+	ret = set_roce_addr(to_mdev(attr->device), attr->port_num,
+			    attr->index, NULL, attr);
+	if (ret)
+		return ret;
+
+	mlx5r_del_gid_macsec_operations(attr);
+	return 0;
 }
 
 __be16 mlx5_get_roce_udp_sport_min(const struct mlx5_ib_dev *dev,
@@ -3644,13 +3658,13 @@ static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev)
 	mutex_destroy(&dev->cap_mask_mutex);
 	WARN_ON(!xa_empty(&dev->sig_mrs));
 	WARN_ON(!bitmap_empty(dev->dm.memic_alloc_pages, MLX5_MAX_MEMIC_PAGES));
+	mlx5r_macsec_dealloc_gids(dev);
 }
 
 static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;
-	int err;
-	int i;
+	int err, i;
 
 	dev->ib_dev.node_type = RDMA_NODE_IB_CA;
 	dev->ib_dev.local_dma_lkey = 0 /* not supported for now */;
@@ -3670,10 +3684,14 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	if (err)
 		return err;
 
-	err = mlx5_ib_init_multiport_master(dev);
+	err = mlx5r_macsec_alloc_gids(dev);
 	if (err)
 		return err;
 
+	err = mlx5_ib_init_multiport_master(dev);
+	if (err)
+		goto err;
+
 	err = set_has_smi_cap(dev);
 	if (err)
 		goto err_mp;
@@ -3697,7 +3715,8 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	spin_lock_init(&dev->dm.lock);
 	dev->dm.dev = mdev;
 	return 0;
-
+err:
+	mlx5r_macsec_dealloc_gids(dev);
 err_mp:
 	mlx5_ib_cleanup_multiport_master(dev);
 	return err;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 9c33d960af3c5..a4b940b5035f2 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -26,6 +26,7 @@
 
 #include "srq.h"
 #include "qp.h"
+#include "macsec.h"
 
 #define mlx5_ib_dbg(_dev, format, arg...)                                      \
 	dev_dbg(&(_dev)->ib_dev.dev, "%s:%d:(pid %d): " format, __func__,      \
@@ -870,6 +871,9 @@ struct mlx5_ib_port {
 	struct mlx5_ib_dbg_cc_params *dbg_cc_params;
 	struct mlx5_roce roce;
 	struct mlx5_eswitch_rep		*rep;
+#ifdef CONFIG_MLX5_MACSEC
+	struct mlx5_reserved_gids *reserved_gids;
+#endif
 };
 
 struct mlx5_ib_dbg_param {
@@ -1648,4 +1652,7 @@ static inline bool mlx5_umem_needs_ats(struct mlx5_ib_dev *dev,
 	return access_flags & IB_ACCESS_RELAXED_ORDERING;
 }
 
+int set_roce_addr(struct mlx5_ib_dev *dev, u32 port_num,
+		  unsigned int index, const union ib_gid *gid,
+		  const struct ib_gid_attr *attr);
 #endif /* MLX5_IB_H */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index b4f3f4f10af32..c9c1db971652d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -1607,37 +1607,6 @@ static void mlx5e_macsec_aso_cleanup(struct mlx5e_macsec_aso *aso, struct mlx5_c
 	mlx5_core_dealloc_pd(mdev, aso->pdn);
 }
 
-bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev)
-{
-	if (!(MLX5_CAP_GEN_64(mdev, general_obj_types) &
-	    MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD))
-		return false;
-
-	if (!MLX5_CAP_GEN(mdev, log_max_dek))
-		return false;
-
-	if (!MLX5_CAP_MACSEC(mdev, log_max_macsec_offload))
-		return false;
-
-	if (!MLX5_CAP_FLOWTABLE_NIC_RX(mdev, macsec_decrypt) ||
-	    !MLX5_CAP_FLOWTABLE_NIC_RX(mdev, reformat_remove_macsec))
-		return false;
-
-	if (!MLX5_CAP_FLOWTABLE_NIC_TX(mdev, macsec_encrypt) ||
-	    !MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_macsec))
-		return false;
-
-	if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_encrypt) &&
-	    !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_encrypt))
-		return false;
-
-	if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_decrypt) &&
-	    !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_decrypt))
-		return false;
-
-	return true;
-}
-
 static const struct macsec_ops macsec_offload_ops = {
 	.mdo_add_txsa = mlx5e_macsec_add_txsa,
 	.mdo_upd_txsa = mlx5e_macsec_upd_txsa,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
index 2ecd769585f43..27df72e23106d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h
@@ -36,7 +36,6 @@ static inline bool mlx5e_macsec_is_rx_flow(struct mlx5_cqe64 *cqe)
 
 void mlx5e_macsec_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
 					struct mlx5_cqe64 *cqe);
-bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev);
 
 #else
 
@@ -49,7 +48,6 @@ static inline void mlx5e_macsec_offload_handle_rx_skb(struct net_device *netdev,
 						      struct sk_buff *skb,
 						      struct mlx5_cqe64 *cqe)
 {}
-static inline bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev) { return false; }
 #endif  /* CONFIG_MLX5_MACSEC */
 
 #endif	/* __MLX5_ACCEL_EN_MACSEC_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 0e80241c270ff..21954e7aeeba2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1323,6 +1323,50 @@ static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev)
 	return mlx5_is_roce_on(dev);
 }
 
+static inline bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev)
+{
+	if (!(MLX5_CAP_GEN_64(mdev, general_obj_types) &
+	    MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD))
+		return false;
+
+	if (!MLX5_CAP_GEN(mdev, log_max_dek))
+		return false;
+
+	if (!MLX5_CAP_MACSEC(mdev, log_max_macsec_offload))
+		return false;
+
+	if (!MLX5_CAP_FLOWTABLE_NIC_RX(mdev, macsec_decrypt) ||
+	    !MLX5_CAP_FLOWTABLE_NIC_RX(mdev, reformat_remove_macsec))
+		return false;
+
+	if (!MLX5_CAP_FLOWTABLE_NIC_TX(mdev, macsec_encrypt) ||
+	    !MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_macsec))
+		return false;
+
+	if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_encrypt) &&
+	    !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_encrypt))
+		return false;
+
+	if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_decrypt) &&
+	    !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_decrypt))
+		return false;
+
+	return true;
+}
+
+#define NIC_RDMA_BOTH_DIRS_CAPS (MLX5_FT_NIC_RX_2_NIC_RX_RDMA | MLX5_FT_NIC_TX_RDMA_2_NIC_TX)
+
+static inline bool mlx5_is_macsec_roce_supported(struct mlx5_core_dev *mdev)
+{
+	if (((MLX5_CAP_GEN_2(mdev, flow_table_type_2_type) &
+	     NIC_RDMA_BOTH_DIRS_CAPS) != NIC_RDMA_BOTH_DIRS_CAPS) ||
+	     !MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, max_modify_header_actions) ||
+	     !mlx5e_is_macsec_device(mdev))
+		return false;
+
+	return true;
+}
+
 enum {
 	MLX5_OCTWORD = 16,
 };
-- 
GitLab


From afcb21d5a89b40c3062aa48d39ab5340abf7dcd8 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 11 Aug 2022 05:20:02 +0300
Subject: [PATCH 1366/1806] net/mlx5: Add MACsec priorities in RDMA namespaces

Add MACsec flow steering priorities in RDMA namespaces. This allows
adding tables/rules to forward RoCEv2 traffic to the MACsec crypto
tables in NIC_TX domain, and accept RoCEv2 traffic from NIC_RX domain.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/fs_core.c | 35 +++++++++++++++++--
 include/linux/mlx5/fs.h                       |  2 ++
 2 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 4ef04aa287719..cc27908bb1135 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -224,6 +224,7 @@ static struct init_tree_node egress_root_fs = {
 
 enum {
 	RDMA_RX_IPSEC_PRIO,
+	RDMA_RX_MACSEC_PRIO,
 	RDMA_RX_COUNTERS_PRIO,
 	RDMA_RX_BYPASS_PRIO,
 	RDMA_RX_KERNEL_PRIO,
@@ -237,9 +238,13 @@ enum {
 #define RDMA_RX_KERNEL_MIN_LEVEL (RDMA_RX_BYPASS_MIN_LEVEL + 1)
 #define RDMA_RX_COUNTERS_MIN_LEVEL (RDMA_RX_KERNEL_MIN_LEVEL + 2)
 
+#define RDMA_RX_MACSEC_NUM_PRIOS 1
+#define RDMA_RX_MACSEC_PRIO_NUM_LEVELS 2
+#define RDMA_RX_MACSEC_MIN_LEVEL  (RDMA_RX_COUNTERS_MIN_LEVEL + RDMA_RX_MACSEC_NUM_PRIOS)
+
 static struct init_tree_node rdma_rx_root_fs = {
 	.type = FS_TYPE_NAMESPACE,
-	.ar_size = 4,
+	.ar_size = 5,
 	.children = (struct init_tree_node[]) {
 		[RDMA_RX_IPSEC_PRIO] =
 		ADD_PRIO(0, RDMA_RX_IPSEC_MIN_LEVEL, 0,
@@ -247,6 +252,12 @@ static struct init_tree_node rdma_rx_root_fs = {
 			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
 				ADD_MULTIPLE_PRIO(RDMA_RX_IPSEC_NUM_PRIOS,
 						  RDMA_RX_IPSEC_NUM_LEVELS))),
+		[RDMA_RX_MACSEC_PRIO] =
+		ADD_PRIO(0, RDMA_RX_MACSEC_MIN_LEVEL, 0,
+			 FS_CHAINING_CAPS,
+			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
+				ADD_MULTIPLE_PRIO(RDMA_RX_MACSEC_NUM_PRIOS,
+						  RDMA_RX_MACSEC_PRIO_NUM_LEVELS))),
 		[RDMA_RX_COUNTERS_PRIO] =
 		ADD_PRIO(0, RDMA_RX_COUNTERS_MIN_LEVEL, 0,
 			 FS_CHAINING_CAPS,
@@ -270,6 +281,7 @@ static struct init_tree_node rdma_rx_root_fs = {
 enum {
 	RDMA_TX_COUNTERS_PRIO,
 	RDMA_TX_IPSEC_PRIO,
+	RDMA_TX_MACSEC_PRIO,
 	RDMA_TX_BYPASS_PRIO,
 };
 
@@ -280,9 +292,13 @@ enum {
 #define RDMA_TX_IPSEC_PRIO_NUM_LEVELS 1
 #define RDMA_TX_IPSEC_MIN_LEVEL  (RDMA_TX_COUNTERS_MIN_LEVEL + RDMA_TX_IPSEC_NUM_PRIOS)
 
+#define RDMA_TX_MACSEC_NUM_PRIOS 1
+#define RDMA_TX_MACESC_PRIO_NUM_LEVELS 1
+#define RDMA_TX_MACSEC_MIN_LEVEL  (RDMA_TX_COUNTERS_MIN_LEVEL + RDMA_TX_MACSEC_NUM_PRIOS)
+
 static struct init_tree_node rdma_tx_root_fs = {
 	.type = FS_TYPE_NAMESPACE,
-	.ar_size = 3,
+	.ar_size = 4,
 	.children = (struct init_tree_node[]) {
 		[RDMA_TX_COUNTERS_PRIO] =
 		ADD_PRIO(0, RDMA_TX_COUNTERS_MIN_LEVEL, 0,
@@ -296,7 +312,12 @@ static struct init_tree_node rdma_tx_root_fs = {
 			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
 				ADD_MULTIPLE_PRIO(RDMA_TX_IPSEC_NUM_PRIOS,
 						  RDMA_TX_IPSEC_PRIO_NUM_LEVELS))),
-
+		[RDMA_TX_MACSEC_PRIO] =
+		ADD_PRIO(0, RDMA_TX_MACSEC_MIN_LEVEL, 0,
+			 FS_CHAINING_CAPS,
+			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
+				ADD_MULTIPLE_PRIO(RDMA_TX_MACSEC_NUM_PRIOS,
+						  RDMA_TX_MACESC_PRIO_NUM_LEVELS))),
 		[RDMA_TX_BYPASS_PRIO] =
 		ADD_PRIO(0, RDMA_TX_BYPASS_MIN_LEVEL, 0,
 			 FS_CHAINING_CAPS_RDMA_TX,
@@ -2403,6 +2424,14 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		root_ns = steering->rdma_tx_root_ns;
 		prio = RDMA_TX_IPSEC_PRIO;
 		break;
+	case MLX5_FLOW_NAMESPACE_RDMA_RX_MACSEC:
+		root_ns = steering->rdma_rx_root_ns;
+		prio = RDMA_RX_MACSEC_PRIO;
+		break;
+	case MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC:
+		root_ns = steering->rdma_tx_root_ns;
+		prio = RDMA_TX_MACSEC_PRIO;
+		break;
 	default: /* Must be NIC RX */
 		WARN_ON(!is_nic_rx_ns(type));
 		root_ns = steering->root_ns;
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 2cb404c7ea131..091ff1240959a 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -105,6 +105,8 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS,
 	MLX5_FLOW_NAMESPACE_RDMA_RX_IPSEC,
 	MLX5_FLOW_NAMESPACE_RDMA_TX_IPSEC,
+	MLX5_FLOW_NAMESPACE_RDMA_RX_MACSEC,
+	MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC,
 };
 
 enum {
-- 
GitLab


From a019b1258da14058668e249ade33b8b2951aaeae Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Mon, 21 Nov 2022 11:59:28 +0200
Subject: [PATCH 1367/1806] IB/core: Reorder GID delete code for RoCE

Reorder GID delete code so that the driver del_gid operation is executed
before nullifying the gid attribute ndev parameter, this allows drivers
to access the ndev during their gid delete operation, which makes more
sense since they had access to it during the gid addition operation.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/core/cache.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index 2e91d88793265..73f913cbd146a 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -400,6 +400,9 @@ static void del_gid(struct ib_device *ib_dev, u32 port,
 		table->data_vec[ix] = NULL;
 	write_unlock_irq(&table->rwlock);
 
+	if (rdma_cap_roce_gid_table(ib_dev, port))
+		ib_dev->ops.del_gid(&entry->attr, &entry->context);
+
 	ndev_storage = entry->ndev_storage;
 	if (ndev_storage) {
 		entry->ndev_storage = NULL;
@@ -407,9 +410,6 @@ static void del_gid(struct ib_device *ib_dev, u32 port,
 		call_rcu(&ndev_storage->rcu_head, put_gid_ndev);
 	}
 
-	if (rdma_cap_roce_gid_table(ib_dev, port))
-		ib_dev->ops.del_gid(&entry->attr, &entry->context);
-
 	put_gid_entry_locked(entry);
 }
 
-- 
GitLab


From 9b240d1094cba5ca4e1bf80ea9f6ef55e6961af9 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 11 Aug 2022 06:00:55 +0300
Subject: [PATCH 1368/1806] net/mlx5: Configure MACsec steering for egress
 RoCEv2 traffic

Add steering table in RDMA_TX domain, to forward MACsec traffic
to MACsec crypto table in NIC domain.
The tables are created in a lazy manner when the first TX SA is
being created, and destroyed upon the destruction of the last SA.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/lib/macsec_fs.c        | 46 ++++++++++++++++++-
 1 file changed, 45 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index b3528516ba35f..e5c42b1cc7613 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -95,6 +95,8 @@ struct mlx5_macsec_tx {
 	struct ida tx_halloc;
 
 	struct mlx5_macsec_tables tables;
+
+	struct mlx5_flow_table *ft_rdma_tx;
 };
 
 struct mlx5_macsec_rx_rule {
@@ -173,6 +175,9 @@ static void macsec_fs_tx_destroy(struct mlx5_macsec_fs *macsec_fs)
 	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
 	struct mlx5_macsec_tables *tx_tables;
 
+	if (mlx5_is_macsec_roce_supported(macsec_fs->mdev))
+		mlx5_destroy_flow_table(tx_fs->ft_rdma_tx);
+
 	tx_tables = &tx_fs->tables;
 
 	/* Tx check table */
@@ -300,6 +305,39 @@ static struct mlx5_flow_table
 	return fdb;
 }
 
+enum {
+	RDMA_TX_MACSEC_LEVEL = 0,
+};
+
+static int macsec_fs_tx_roce_create(struct mlx5_macsec_fs *macsec_fs)
+{
+	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
+	struct mlx5_core_dev *mdev = macsec_fs->mdev;
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_table *ft;
+	int err;
+
+	if (!mlx5_is_macsec_roce_supported(mdev)) {
+		mlx5_core_dbg(mdev, "Failed to init RoCE MACsec, capabilities not supported\n");
+		return 0;
+	}
+
+	ns = mlx5_get_flow_namespace(mdev, MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC);
+	if (!ns)
+		return -ENOMEM;
+
+	/* Tx RoCE crypto table  */
+	ft = macsec_fs_auto_group_table_create(ns, 0, RDMA_TX_MACSEC_LEVEL, CRYPTO_NUM_MAXSEC_FTE);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev, "Failed to create MACsec RoCE Tx crypto table err(%d)\n", err);
+		return err;
+	}
+	tx_fs->ft_rdma_tx = ft;
+
+	return 0;
+}
+
 static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
@@ -442,7 +480,13 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	}
 	tx_fs->check_rule = rule;
 
-	goto out_flow_group;
+	err = macsec_fs_tx_roce_create(macsec_fs);
+	if (err)
+		goto err;
+
+	kvfree(flow_group_in);
+	kvfree(spec);
+	return 0;
 
 err:
 	macsec_fs_tx_destroy(macsec_fs);
-- 
GitLab


From 8c14a2c7c96f1624ffb8406accd082b4aff36883 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 11 Aug 2022 06:09:18 +0300
Subject: [PATCH 1369/1806] net/mlx5: Configure MACsec steering for ingress
 RoCEv2 traffic

Add steering tables/rules to check if the decrypted traffic is RoCEv2,
if so copy reg_b_metadata to a temp reg and forward it to RDMA_RX domain.
The rules are added once the MACsec device is assigned an IP address
where we verify that the packet ip is for MACsec device and that the temp
reg has MACsec operation and a valid SCI inside.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/fs_core.c |   2 +-
 .../mellanox/mlx5/core/lib/macsec_fs.c        | 359 +++++++++++++++++-
 2 files changed, 352 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index cc27908bb1135..805a512867188 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -107,7 +107,7 @@
 			   LEFTOVERS_NUM_PRIOS)
 
 #define KERNEL_RX_MACSEC_NUM_PRIOS  1
-#define KERNEL_RX_MACSEC_NUM_LEVELS 2
+#define KERNEL_RX_MACSEC_NUM_LEVELS 3
 #define KERNEL_RX_MACSEC_MIN_LEVEL (BY_PASS_MIN_LEVEL + KERNEL_RX_MACSEC_NUM_PRIOS)
 
 #define ETHTOOL_PRIO_NUM_LEVELS 1
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index e5c42b1cc7613..552ab425ae394 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -22,7 +22,9 @@
 #define TX_CHECK_TABLE_NUM_FTE 2
 #define RX_CRYPTO_TABLE_LEVEL 0
 #define RX_CHECK_TABLE_LEVEL 1
+#define RX_ROCE_TABLE_LEVEL 2
 #define RX_CHECK_TABLE_NUM_FTE 3
+#define RX_ROCE_TABLE_NUM_FTE 2
 #define RX_CRYPTO_TABLE_NUM_GROUPS 3
 #define RX_CRYPTO_TABLE_SA_RULE_WITH_SCI_GROUP_SIZE \
 	((CRYPTO_NUM_MAXSEC_FTE - CRYPTO_TABLE_DEFAULT_RULE_GROUP_SIZE) / 2)
@@ -30,6 +32,9 @@
 	(CRYPTO_NUM_MAXSEC_FTE - RX_CRYPTO_TABLE_SA_RULE_WITH_SCI_GROUP_SIZE)
 #define RX_NUM_OF_RULES_PER_SA 2
 
+#define RDMA_RX_ROCE_IP_TABLE_LEVEL 0
+#define RDMA_RX_ROCE_MACSEC_OP_TABLE_LEVEL 1
+
 #define MLX5_MACSEC_TAG_LEN 8 /* SecTAG length with ethertype and without the optional SCI */
 #define MLX5_MACSEC_SECTAG_TCI_AN_FIELD_BITMASK 0x23
 #define MLX5_MACSEC_SECTAG_TCI_AN_FIELD_OFFSET 0x8
@@ -104,11 +109,31 @@ struct mlx5_macsec_rx_rule {
 	struct mlx5_modify_hdr *meta_modhdr;
 };
 
+struct mlx5_macsec_miss {
+	struct mlx5_flow_group *g;
+	struct mlx5_flow_handle *rule;
+};
+
+struct mlx5_macsec_rx_roce {
+	/* Flow table/rules in NIC domain, to check if it's a RoCE packet */
+	struct mlx5_flow_group *g;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_modify_hdr *copy_modify_hdr;
+	struct mlx5_macsec_miss nic_miss;
+
+	/* Flow table/rule in RDMA domain, to check dgid */
+	struct mlx5_flow_table *ft_ip_check;
+	struct mlx5_flow_table *ft_macsec_op_check;
+	struct mlx5_macsec_miss miss;
+};
+
 struct mlx5_macsec_rx {
 	struct mlx5_flow_handle *check_rule[2];
 	struct mlx5_pkt_reformat *check_rule_pkt_reformat[2];
 
 	struct mlx5_macsec_tables tables;
+	struct mlx5_macsec_rx_roce roce;
 };
 
 union mlx5_macsec_rule {
@@ -932,6 +957,29 @@ err_encrypt_counter:
 	return err;
 }
 
+static void macsec_fs_rx_roce_miss_destroy(struct mlx5_macsec_miss *miss)
+{
+	mlx5_del_flow_rules(miss->rule);
+	mlx5_destroy_flow_group(miss->g);
+}
+
+static void macsec_fs_rdma_rx_destroy(struct mlx5_macsec_rx_roce *roce, struct mlx5_core_dev *mdev)
+{
+	if (!mlx5_is_macsec_roce_supported(mdev))
+		return;
+
+	mlx5_del_flow_rules(roce->nic_miss.rule);
+	mlx5_del_flow_rules(roce->rule);
+	mlx5_modify_header_dealloc(mdev, roce->copy_modify_hdr);
+	mlx5_destroy_flow_group(roce->nic_miss.g);
+	mlx5_destroy_flow_group(roce->g);
+	mlx5_destroy_flow_table(roce->ft);
+
+	macsec_fs_rx_roce_miss_destroy(&roce->miss);
+	mlx5_destroy_flow_table(roce->ft_macsec_op_check);
+	mlx5_destroy_flow_table(roce->ft_ip_check);
+}
+
 static void macsec_fs_rx_destroy(struct mlx5_macsec_fs *macsec_fs)
 {
 	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
@@ -976,6 +1024,8 @@ static void macsec_fs_rx_destroy(struct mlx5_macsec_fs *macsec_fs)
 	}
 
 	macsec_fs_destroy_flow_table(&rx_tables->ft_crypto);
+
+	macsec_fs_rdma_rx_destroy(&macsec_fs->rx_fs->roce, macsec_fs->mdev);
 }
 
 static int macsec_fs_rx_create_crypto_table_groups(struct mlx5_macsec_flow_table *ft)
@@ -1071,9 +1121,10 @@ static int macsec_fs_rx_create_check_decap_rule(struct mlx5_macsec_fs *macsec_fs
 	struct mlx5_pkt_reformat_params reformat_params = {};
 	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
 	struct mlx5_core_dev *mdev = macsec_fs->mdev;
+	struct mlx5_flow_destination roce_dest[2];
 	struct mlx5_macsec_tables *rx_tables;
 	struct mlx5_flow_handle *rule;
-	int err = 0;
+	int err = 0, dstn = 0;
 
 	rx_tables = &rx_fs->tables;
 
@@ -1114,12 +1165,22 @@ static int macsec_fs_rx_create_check_decap_rule(struct mlx5_macsec_fs *macsec_fs
 			 MLX5_MACSEC_SECTAG_TCI_AN_FIELD_OFFSET);
 
 	flow_act->flags = FLOW_ACT_NO_APPEND;
-	flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO |
-			   MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
-			   MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	dest->type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest->counter_id = mlx5_fc_id(rx_tables->check_rule_counter);
-	rule = mlx5_add_flow_rules(rx_tables->ft_check, spec, flow_act, dest, 1);
+
+	if (rx_fs->roce.ft) {
+		flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+		roce_dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+		roce_dest[dstn].ft = rx_fs->roce.ft;
+		dstn++;
+	} else {
+		flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
+	}
+
+	flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
+			    MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	roce_dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	roce_dest[dstn].counter_id = mlx5_fc_id(rx_tables->check_rule_counter);
+	rule = mlx5_add_flow_rules(rx_tables->ft_check, spec, flow_act, roce_dest, dstn + 1);
+
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		mlx5_core_err(mdev, "Failed to add MACsec Rx check rule, err=%d\n", err);
@@ -1131,6 +1192,284 @@ static int macsec_fs_rx_create_check_decap_rule(struct mlx5_macsec_fs *macsec_fs
 	return 0;
 }
 
+static int macsec_fs_rx_roce_miss_create(struct mlx5_core_dev *mdev,
+					 struct mlx5_macsec_rx_roce *roce)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_group *flow_group;
+	struct mlx5_flow_handle *rule;
+	u32 *flow_group_in;
+	int err;
+
+	flow_group_in = kvzalloc(MLX5_ST_SZ_BYTES(create_flow_group_in), GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	/* IP check ft has no miss rule since we use default miss action which is go to next PRIO */
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index,
+		 roce->ft_macsec_op_check->max_fte - 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 roce->ft_macsec_op_check->max_fte - 1);
+	flow_group = mlx5_create_flow_group(roce->ft_macsec_op_check, flow_group_in);
+	if (IS_ERR(flow_group)) {
+		err = PTR_ERR(flow_group);
+		mlx5_core_err(mdev,
+			      "Failed to create miss flow group for MACsec RoCE operation check table err(%d)\n",
+			      err);
+		goto err_macsec_op_miss_group;
+	}
+	roce->miss.g = flow_group;
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
+	rule = mlx5_add_flow_rules(roce->ft_macsec_op_check,  NULL, &flow_act, NULL, 0);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "Failed to add miss rule to MACsec RoCE operation check table err(%d)\n",
+			      err);
+		goto err_macsec_op_rule;
+	}
+	roce->miss.rule = rule;
+
+	kvfree(flow_group_in);
+	return 0;
+
+err_macsec_op_rule:
+	mlx5_destroy_flow_group(roce->miss.g);
+err_macsec_op_miss_group:
+	kvfree(flow_group_in);
+	return err;
+}
+
+#define MLX5_RX_ROCE_GROUP_SIZE BIT(0)
+
+static int macsec_fs_rx_roce_jump_to_rdma_groups_create(struct mlx5_core_dev *mdev,
+							struct mlx5_macsec_rx_roce *roce)
+{
+	struct mlx5_flow_group *g;
+	void *outer_headers_c;
+	int ix = 0;
+	u32 *in;
+	int err;
+	u8 *mc;
+
+	in = kvzalloc(MLX5_ST_SZ_BYTES(create_flow_group_in), GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+	outer_headers_c = MLX5_ADDR_OF(fte_match_param, mc, outer_headers);
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol);
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, outer_headers_c, udp_dport);
+
+	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_RX_ROCE_GROUP_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	g = mlx5_create_flow_group(roce->ft, in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		mlx5_core_err(mdev, "Failed to create main flow group for MACsec RoCE NIC UDP table err(%d)\n",
+			      err);
+		goto err_udp_group;
+	}
+	roce->g = g;
+
+	memset(in, 0, MLX5_ST_SZ_BYTES(create_flow_group_in));
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_RX_ROCE_GROUP_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	g = mlx5_create_flow_group(roce->ft, in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		mlx5_core_err(mdev, "Failed to create miss flow group for MACsec RoCE NIC UDP table err(%d)\n",
+			      err);
+		goto err_udp_miss_group;
+	}
+	roce->nic_miss.g = g;
+
+	kvfree(in);
+	return 0;
+
+err_udp_miss_group:
+	mlx5_destroy_flow_group(roce->g);
+err_udp_group:
+	kvfree(in);
+	return err;
+}
+
+static int macsec_fs_rx_roce_jump_to_rdma_rules_create(struct mlx5_macsec_fs *macsec_fs,
+						       struct mlx5_macsec_rx_roce *roce)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	struct mlx5_core_dev *mdev = macsec_fs->mdev;
+	struct mlx5_flow_destination dst = {};
+	struct mlx5_modify_hdr *modify_hdr;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol);
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_UDP);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.udp_dport);
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.udp_dport, ROCE_V2_UDP_DPORT);
+
+	MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY);
+	MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
+	MLX5_SET(copy_action_in, action, src_offset, 0);
+	MLX5_SET(copy_action_in, action, length, 32);
+	MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_5);
+	MLX5_SET(copy_action_in, action, dst_offset, 0);
+
+	modify_hdr = mlx5_modify_header_alloc(macsec_fs->mdev, MLX5_FLOW_NAMESPACE_KERNEL_RX_MACSEC,
+					      1, action);
+
+	if (IS_ERR(modify_hdr)) {
+		err = PTR_ERR(modify_hdr);
+		mlx5_core_err(mdev,
+			      "Failed to alloc macsec copy modify_header_id err(%d)\n", err);
+		goto err_alloc_hdr;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	flow_act.modify_hdr = modify_hdr;
+	dst.type = MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE;
+	dst.ft = roce->ft_ip_check;
+	rule = mlx5_add_flow_rules(roce->ft, spec, &flow_act, &dst, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "Failed to add rule to MACsec RoCE NIC UDP table err(%d)\n",
+			      err);
+		goto err_add_rule;
+	}
+	roce->rule = rule;
+	roce->copy_modify_hdr = modify_hdr;
+
+	memset(&flow_act, 0, sizeof(flow_act));
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
+	rule = mlx5_add_flow_rules(roce->ft, NULL, &flow_act, NULL, 0);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "Failed to add miss rule to MACsec RoCE NIC UDP table err(%d)\n",
+			      err);
+		goto err_add_rule2;
+	}
+	roce->nic_miss.rule = rule;
+
+	kvfree(spec);
+	return 0;
+
+err_add_rule2:
+	mlx5_del_flow_rules(roce->rule);
+err_add_rule:
+	mlx5_modify_header_dealloc(macsec_fs->mdev, modify_hdr);
+err_alloc_hdr:
+	kvfree(spec);
+	return err;
+}
+
+static int macsec_fs_rx_roce_jump_to_rdma_create(struct mlx5_macsec_fs *macsec_fs,
+						 struct mlx5_macsec_rx_roce *roce)
+{
+	int err;
+
+	err = macsec_fs_rx_roce_jump_to_rdma_groups_create(macsec_fs->mdev, roce);
+	if (err)
+		return err;
+
+	err = macsec_fs_rx_roce_jump_to_rdma_rules_create(macsec_fs, roce);
+	if (err)
+		goto err;
+
+	return 0;
+err:
+	mlx5_destroy_flow_group(roce->nic_miss.g);
+	mlx5_destroy_flow_group(roce->g);
+	return err;
+}
+
+static int macsec_fs_rx_roce_create(struct mlx5_macsec_fs *macsec_fs)
+{
+	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
+	struct mlx5_core_dev *mdev = macsec_fs->mdev;
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_table *ft;
+	int err = 0;
+
+	if (!mlx5_is_macsec_roce_supported(macsec_fs->mdev)) {
+		mlx5_core_dbg(mdev, "Failed to init RoCE MACsec, capabilities not supported\n");
+		return 0;
+	}
+
+	ns = mlx5_get_flow_namespace(macsec_fs->mdev, MLX5_FLOW_NAMESPACE_RDMA_RX_MACSEC);
+	if (!ns)
+		return -ENOMEM;
+
+	ft = macsec_fs_auto_group_table_create(ns, 0, RDMA_RX_ROCE_IP_TABLE_LEVEL,
+					       CRYPTO_NUM_MAXSEC_FTE);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev,
+			      "Failed to create MACsec IP check RoCE table err(%d)\n", err);
+		return err;
+	}
+	rx_fs->roce.ft_ip_check = ft;
+
+	ft = macsec_fs_auto_group_table_create(ns, 0, RDMA_RX_ROCE_MACSEC_OP_TABLE_LEVEL,
+					       CRYPTO_NUM_MAXSEC_FTE);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev,
+			      "Failed to create MACsec operation check RoCE table err(%d)\n",
+			      err);
+		goto err_macsec_op;
+	}
+	rx_fs->roce.ft_macsec_op_check = ft;
+
+	err = macsec_fs_rx_roce_miss_create(mdev, &rx_fs->roce);
+	if (err)
+		goto err_miss_create;
+
+	ns = mlx5_get_flow_namespace(macsec_fs->mdev, MLX5_FLOW_NAMESPACE_KERNEL_RX_MACSEC);
+	if (!ns) {
+		err = -EOPNOTSUPP;
+		goto err_ns;
+	}
+
+	ft_attr.level = RX_ROCE_TABLE_LEVEL;
+	ft_attr.max_fte = RX_ROCE_TABLE_NUM_FTE;
+	ft = mlx5_create_flow_table(ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev,
+			      "Failed to create MACsec jump to RX RoCE, NIC table err(%d)\n", err);
+		goto err_ns;
+	}
+	rx_fs->roce.ft = ft;
+
+	err = macsec_fs_rx_roce_jump_to_rdma_create(macsec_fs, &rx_fs->roce);
+	if (err)
+		goto err_udp_ft;
+
+	return 0;
+
+err_udp_ft:
+	mlx5_destroy_flow_table(rx_fs->roce.ft);
+err_ns:
+	macsec_fs_rx_roce_miss_destroy(&rx_fs->roce.miss);
+err_miss_create:
+	mlx5_destroy_flow_table(rx_fs->roce.ft_macsec_op_check);
+err_macsec_op:
+	mlx5_destroy_flow_table(rx_fs->roce.ft_ip_check);
+	return err;
+}
+
 static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
@@ -1166,6 +1505,10 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 	rx_tables = &rx_fs->tables;
 	ft_crypto = &rx_tables->ft_crypto;
 
+	err = macsec_fs_rx_roce_create(macsec_fs);
+	if (err)
+		goto out_flow_group;
+
 	/* Rx crypto table */
 	ft_attr.level = RX_CRYPTO_TABLE_LEVEL;
 	ft_attr.max_fte = CRYPTO_NUM_MAXSEC_FTE;
@@ -1174,7 +1517,7 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 	if (IS_ERR(flow_table)) {
 		err = PTR_ERR(flow_table);
 		mlx5_core_err(mdev, "Failed to create MACsec Rx crypto table err(%d)\n", err);
-		goto out_flow_group;
+		goto err;
 	}
 	ft_crypto->t = flow_table;
 
-- 
GitLab


From ac7ea1c78f0edb910af1c17a3fb01345944bcb39 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 13 Apr 2023 12:04:42 +0300
Subject: [PATCH 1370/1806] net/mlx5: Add RoCE MACsec steering infrastructure
 in core

Adds all the core steering helper functions that are needed in order
to setup RoCE steering rules which includes both the RX and TX rules
addition and deletion.
As well as exporting the function to be ready to use from the IB driver
where we expose functions to allow deletion of all rules, which is
needed when a GID is deleted, or a deletion of a specific rule when an SA
is deleted, and a similar manner for the rules addition.

These functions are used in a later patch by IB driver to trigger the
rules addition/deletion when needed.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/fs_cmd.c  |   1 +
 .../mellanox/mlx5/core/lib/macsec_fs.c        | 399 +++++++++++++++++-
 include/linux/mlx5/device.h                   |   2 +
 include/linux/mlx5/driver.h                   |   2 +
 include/linux/mlx5/macsec.h                   |  32 ++
 5 files changed, 427 insertions(+), 9 deletions(-)
 create mode 100644 include/linux/mlx5/macsec.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 91dcb0dcad101..4e651c2f65c56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -967,6 +967,7 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 		max_actions = MLX5_CAP_ESW_INGRESS_ACL(dev, max_modify_header_actions);
 		table_type = FS_FT_ESW_INGRESS_ACL;
 		break;
+	case MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC:
 	case MLX5_FLOW_NAMESPACE_RDMA_TX:
 		max_actions = MLX5_CAP_FLOWTABLE_RDMA_TX(dev, max_modify_header_actions);
 		table_type = FS_FT_RDMA_TX;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index 552ab425ae394..2f2cb67717cdd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -4,6 +4,8 @@
 #include <net/macsec.h>
 #include <linux/mlx5/qp.h>
 #include <linux/if_vlan.h>
+#include <linux/mlx5/fs_helpers.h>
+#include <linux/mlx5/macsec.h>
 #include "fs_core.h"
 #include "lib/macsec_fs.h"
 #include "mlx5_core.h"
@@ -46,6 +48,10 @@
 /* MACsec RX flow steering */
 #define MLX5_ETH_WQE_FT_META_MACSEC_MASK 0x3E
 
+/* MACsec fs_id handling for steering */
+#define macsec_fs_set_tx_fs_id(fs_id) (MLX5_ETH_WQE_FT_META_MACSEC | (fs_id) << 2)
+#define macsec_fs_set_rx_fs_id(fs_id) ((fs_id) | BIT(30))
+
 struct mlx5_sectag_header {
 	__be16 ethertype;
 	u8 tci_an;
@@ -54,6 +60,14 @@ struct mlx5_sectag_header {
 	u8 sci[MACSEC_SCI_LEN]; /* optional */
 }  __packed;
 
+struct mlx5_roce_macsec_tx_rule {
+	u32 fs_id;
+	u16 gid_idx;
+	struct list_head entry;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_modify_hdr *meta_modhdr;
+};
+
 struct mlx5_macsec_tx_rule {
 	struct mlx5_flow_handle *rule;
 	struct mlx5_pkt_reformat *pkt_reformat;
@@ -104,6 +118,14 @@ struct mlx5_macsec_tx {
 	struct mlx5_flow_table *ft_rdma_tx;
 };
 
+struct mlx5_roce_macsec_rx_rule {
+	u32 fs_id;
+	u16 gid_idx;
+	struct mlx5_flow_handle *op;
+	struct mlx5_flow_handle *ip;
+	struct list_head entry;
+};
+
 struct mlx5_macsec_rx_rule {
 	struct mlx5_flow_handle *rule[RX_NUM_OF_RULES_PER_SA];
 	struct mlx5_modify_hdr *meta_modhdr;
@@ -574,7 +596,7 @@ static int macsec_fs_tx_setup_fte(struct mlx5_macsec_fs *macsec_fs,
 	MLX5_SET(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_a,
 		 MLX5_ETH_WQE_FT_META_MACSEC_MASK);
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_a,
-		 MLX5_ETH_WQE_FT_META_MACSEC | id << 2);
+		 macsec_fs_set_tx_fs_id(id));
 
 	*fs_id = id;
 	flow_act->crypto.type = MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_MACSEC;
@@ -776,7 +798,7 @@ static void macsec_fs_tx_del_rule(struct mlx5_macsec_fs *macsec_fs,
 static union mlx5_macsec_rule *
 macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 		      const struct macsec_context *macsec_ctx,
-		      struct mlx5_macsec_rule_attrs *attrs)
+		      struct mlx5_macsec_rule_attrs *attrs, u32 *fs_id)
 {
 	char reformatbf[MLX5_MACSEC_TAG_LEN + MACSEC_SCI_LEN];
 	struct mlx5_pkt_reformat_params reformat_params = {};
@@ -791,7 +813,6 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	struct mlx5_flow_spec *spec;
 	size_t reformat_size;
 	int err = 0;
-	u32 fs_id;
 
 	tx_tables = &tx_fs->tables;
 
@@ -831,7 +852,7 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	}
 	tx_rule->pkt_reformat = flow_act.pkt_reformat;
 
-	err = macsec_fs_tx_setup_fte(macsec_fs, spec, &flow_act, attrs->macsec_obj_id, &fs_id);
+	err = macsec_fs_tx_setup_fte(macsec_fs, spec, &flow_act, attrs->macsec_obj_id, fs_id);
 	if (err) {
 		mlx5_core_err(mdev,
 			      "Failed to add packet reformat for MACsec TX crypto rule, err=%d\n",
@@ -839,7 +860,7 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 		goto err;
 	}
 
-	tx_rule->fs_id = fs_id;
+	tx_rule->fs_id = *fs_id;
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 			  MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT |
@@ -854,7 +875,7 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	}
 	tx_rule->rule = rule;
 
-	err = macsec_fs_id_add(&macsec_fs->macsec_devices_list, fs_id, macsec_ctx->secy->netdev,
+	err = macsec_fs_id_add(&macsec_fs->macsec_devices_list, *fs_id, macsec_ctx->secy->netdev,
 			       &macsec_fs->sci_hash, attrs->sci, true);
 	if (err) {
 		mlx5_core_err(mdev, "Failed to save fs_id, err=%d\n", err);
@@ -1743,7 +1764,7 @@ macsec_fs_rx_add_rule(struct mlx5_macsec_fs *macsec_fs,
 	/* Set bit[15-0] fs id */
 	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
 	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
-	MLX5_SET(set_action_in, action, data, MLX5_MACSEC_RX_METADAT_HANDLE(fs_id) | BIT(30));
+	MLX5_SET(set_action_in, action, data, macsec_fs_set_rx_fs_id(fs_id));
 	MLX5_SET(set_action_in, action, offset, 0);
 	MLX5_SET(set_action_in, action, length, 32);
 
@@ -1902,6 +1923,114 @@ static void macsec_fs_rx_cleanup(struct mlx5_macsec_fs *macsec_fs)
 	macsec_fs->rx_fs = NULL;
 }
 
+static void set_ipaddr_spec_v4(struct sockaddr_in *in, struct mlx5_flow_spec *spec, bool is_dst_ip)
+{
+	MLX5_SET(fte_match_param, spec->match_value,
+		 outer_headers.ip_version, MLX5_FS_IPV4_VERSION);
+
+	if (is_dst_ip) {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+		       &in->sin_addr.s_addr, 4);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4),
+		       &in->sin_addr.s_addr, 4);
+	}
+}
+
+static void set_ipaddr_spec_v6(struct sockaddr_in6 *in6, struct mlx5_flow_spec *spec,
+			       bool is_dst_ip)
+{
+	MLX5_SET(fte_match_param, spec->match_value,
+		 outer_headers.ip_version, MLX5_FS_IPV6_VERSION);
+
+	if (is_dst_ip) {
+		memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+		       0xff, 16);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+		       &in6->sin6_addr, 16);
+	} else {
+		memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6),
+		       0xff, 16);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6),
+		       &in6->sin6_addr, 16);
+	}
+}
+
+static void set_ipaddr_spec(const struct sockaddr *addr,
+			    struct mlx5_flow_spec *spec, bool is_dst_ip)
+{
+	struct sockaddr_in6 *in6;
+
+	spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 outer_headers.ip_version);
+
+	if (addr->sa_family == AF_INET) {
+		struct sockaddr_in *in = (struct sockaddr_in *)addr;
+
+		set_ipaddr_spec_v4(in, spec, is_dst_ip);
+		return;
+	}
+
+	in6 = (struct sockaddr_in6 *)addr;
+	set_ipaddr_spec_v6(in6, spec, is_dst_ip);
+}
+
+static void macsec_fs_del_roce_rule_rx(struct mlx5_roce_macsec_rx_rule *rx_rule)
+{
+	mlx5_del_flow_rules(rx_rule->op);
+	mlx5_del_flow_rules(rx_rule->ip);
+	list_del(&rx_rule->entry);
+	kfree(rx_rule);
+}
+
+static void macsec_fs_del_roce_rules_rx(struct mlx5_macsec_fs *macsec_fs, u32 fs_id,
+					struct list_head *rx_rules_list)
+{
+	struct mlx5_roce_macsec_rx_rule *rx_rule, *next;
+
+	if (!mlx5_is_macsec_roce_supported(macsec_fs->mdev))
+		return;
+
+	list_for_each_entry_safe(rx_rule, next, rx_rules_list, entry) {
+		if (rx_rule->fs_id == fs_id)
+			macsec_fs_del_roce_rule_rx(rx_rule);
+	}
+}
+
+static void macsec_fs_del_roce_rule_tx(struct mlx5_core_dev *mdev,
+				       struct mlx5_roce_macsec_tx_rule *tx_rule)
+{
+	mlx5_del_flow_rules(tx_rule->rule);
+	mlx5_modify_header_dealloc(mdev, tx_rule->meta_modhdr);
+	list_del(&tx_rule->entry);
+	kfree(tx_rule);
+}
+
+static void macsec_fs_del_roce_rules_tx(struct mlx5_macsec_fs *macsec_fs, u32 fs_id,
+					struct list_head *tx_rules_list)
+{
+	struct mlx5_roce_macsec_tx_rule *tx_rule, *next;
+
+	if (!mlx5_is_macsec_roce_supported(macsec_fs->mdev))
+		return;
+
+	list_for_each_entry_safe(tx_rule, next, tx_rules_list, entry) {
+		if (tx_rule->fs_id == fs_id)
+			macsec_fs_del_roce_rule_tx(macsec_fs->mdev, tx_rule);
+	}
+}
+
 void mlx5_macsec_fs_get_stats_fill(struct mlx5_macsec_fs *macsec_fs, void *macsec_stats)
 {
 	struct mlx5_macsec_stats *stats = (struct mlx5_macsec_stats *)macsec_stats;
@@ -1954,20 +2083,270 @@ mlx5_macsec_fs_add_rule(struct mlx5_macsec_fs *macsec_fs,
 			struct mlx5_macsec_rule_attrs *attrs,
 			u32 *sa_fs_id)
 {
-	return (attrs->action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) ?
-		macsec_fs_tx_add_rule(macsec_fs, macsec_ctx, attrs) :
+	struct mlx5_macsec_event_data data = {.macsec_fs = macsec_fs,
+					      .macdev = macsec_ctx->secy->netdev,
+					      .is_tx =
+					      (attrs->action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT)
+	};
+	union mlx5_macsec_rule *macsec_rule;
+	u32 tx_new_fs_id;
+
+	macsec_rule = (attrs->action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) ?
+		macsec_fs_tx_add_rule(macsec_fs, macsec_ctx, attrs, &tx_new_fs_id) :
 		macsec_fs_rx_add_rule(macsec_fs, macsec_ctx, attrs, *sa_fs_id);
+
+	data.fs_id = (data.is_tx) ? tx_new_fs_id : *sa_fs_id;
+	if (macsec_rule)
+		blocking_notifier_call_chain(&macsec_fs->mdev->macsec_nh,
+					     MLX5_DRIVER_EVENT_MACSEC_SA_ADDED,
+					     &data);
+
+	return macsec_rule;
 }
 
 void mlx5_macsec_fs_del_rule(struct mlx5_macsec_fs *macsec_fs,
 			     union mlx5_macsec_rule *macsec_rule,
 			     int action, void *macdev, u32 sa_fs_id)
 {
+	struct mlx5_macsec_event_data data = {.macsec_fs = macsec_fs,
+					      .macdev = macdev,
+					      .is_tx = (action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT)
+	};
+
+	data.fs_id = (data.is_tx) ? macsec_rule->tx_rule.fs_id : sa_fs_id;
+	blocking_notifier_call_chain(&macsec_fs->mdev->macsec_nh,
+				     MLX5_DRIVER_EVENT_MACSEC_SA_DELETED,
+				     &data);
+
 	(action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) ?
 		macsec_fs_tx_del_rule(macsec_fs, &macsec_rule->tx_rule, macdev) :
 		macsec_fs_rx_del_rule(macsec_fs, &macsec_rule->rx_rule, macdev, sa_fs_id);
 }
 
+static int mlx5_macsec_fs_add_roce_rule_rx(struct mlx5_macsec_fs *macsec_fs, u32 fs_id, u16 gid_idx,
+					   const struct sockaddr *addr,
+					   struct list_head *rx_rules_list)
+{
+	struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs;
+	struct mlx5_roce_macsec_rx_rule *rx_rule;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *new_rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	rx_rule = kzalloc(sizeof(*rx_rule), GFP_KERNEL);
+	if (!rx_rule) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	set_ipaddr_spec(addr, spec, true);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	dest.ft = rx_fs->roce.ft_macsec_op_check;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	new_rule = mlx5_add_flow_rules(rx_fs->roce.ft_ip_check, spec, &flow_act,
+				       &dest, 1);
+	if (IS_ERR(new_rule)) {
+		err = PTR_ERR(new_rule);
+		goto ip_rule_err;
+	}
+	rx_rule->ip = new_rule;
+
+	memset(&flow_act, 0, sizeof(flow_act));
+	memset(spec, 0, sizeof(*spec));
+
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_5);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_5,
+		 macsec_fs_set_rx_fs_id(fs_id));
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	new_rule = mlx5_add_flow_rules(rx_fs->roce.ft_macsec_op_check, spec, &flow_act,
+				       NULL, 0);
+	if (IS_ERR(new_rule)) {
+		err = PTR_ERR(new_rule);
+		goto op_rule_err;
+	}
+	rx_rule->op = new_rule;
+	rx_rule->gid_idx = gid_idx;
+	rx_rule->fs_id = fs_id;
+	list_add_tail(&rx_rule->entry, rx_rules_list);
+
+	goto out;
+
+op_rule_err:
+	mlx5_del_flow_rules(rx_rule->ip);
+	rx_rule->ip = NULL;
+ip_rule_err:
+	kfree(rx_rule);
+out:
+	kvfree(spec);
+	return err;
+}
+
+static int mlx5_macsec_fs_add_roce_rule_tx(struct mlx5_macsec_fs *macsec_fs, u32 fs_id, u16 gid_idx,
+					   const struct sockaddr *addr,
+					   struct list_head *tx_rules_list)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs;
+	struct mlx5_core_dev *mdev = macsec_fs->mdev;
+	struct mlx5_modify_hdr *modify_hdr = NULL;
+	struct mlx5_roce_macsec_tx_rule *tx_rule;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *new_rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	tx_rule = kzalloc(sizeof(*tx_rule), GFP_KERNEL);
+	if (!tx_rule) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	set_ipaddr_spec(addr, spec, false);
+
+	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_A);
+	MLX5_SET(set_action_in, action, data, macsec_fs_set_tx_fs_id(fs_id));
+	MLX5_SET(set_action_in, action, offset, 0);
+	MLX5_SET(set_action_in, action, length, 32);
+
+	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC,
+					      1, action);
+	if (IS_ERR(modify_hdr)) {
+		err = PTR_ERR(modify_hdr);
+		mlx5_core_err(mdev, "Fail to alloc ROCE MACsec set modify_header_id err=%d\n",
+			      err);
+		modify_hdr = NULL;
+		goto modify_hdr_err;
+	}
+	tx_rule->meta_modhdr = modify_hdr;
+
+	flow_act.modify_hdr = modify_hdr;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE;
+	dest.ft = tx_fs->tables.ft_crypto.t;
+	new_rule = mlx5_add_flow_rules(tx_fs->ft_rdma_tx, spec, &flow_act, &dest, 1);
+	if (IS_ERR(new_rule)) {
+		err = PTR_ERR(new_rule);
+		mlx5_core_err(mdev, "Failed to add ROCE TX rule, err=%d\n", err);
+		goto rule_err;
+	}
+	tx_rule->rule = new_rule;
+	tx_rule->gid_idx = gid_idx;
+	tx_rule->fs_id = fs_id;
+	list_add_tail(&tx_rule->entry, tx_rules_list);
+
+	goto out;
+
+rule_err:
+	mlx5_modify_header_dealloc(mdev, tx_rule->meta_modhdr);
+modify_hdr_err:
+	kfree(tx_rule);
+out:
+	kvfree(spec);
+	return err;
+}
+
+void mlx5_macsec_del_roce_rule(u16 gid_idx, struct mlx5_macsec_fs *macsec_fs,
+			       struct list_head *tx_rules_list, struct list_head *rx_rules_list)
+{
+	struct mlx5_roce_macsec_rx_rule *rx_rule, *next_rx;
+	struct mlx5_roce_macsec_tx_rule *tx_rule, *next_tx;
+
+	list_for_each_entry_safe(tx_rule, next_tx, tx_rules_list, entry) {
+		if (tx_rule->gid_idx == gid_idx)
+			macsec_fs_del_roce_rule_tx(macsec_fs->mdev, tx_rule);
+	}
+
+	list_for_each_entry_safe(rx_rule, next_rx, rx_rules_list, entry) {
+		if (rx_rule->gid_idx == gid_idx)
+			macsec_fs_del_roce_rule_rx(rx_rule);
+	}
+}
+EXPORT_SYMBOL_GPL(mlx5_macsec_del_roce_rule);
+
+int mlx5_macsec_add_roce_rule(void *macdev, const struct sockaddr *addr, u16 gid_idx,
+			      struct list_head *tx_rules_list, struct list_head *rx_rules_list,
+			      struct mlx5_macsec_fs *macsec_fs)
+{
+	struct mlx5_macsec_device *iter, *macsec_device = NULL;
+	struct mlx5_core_dev *mdev = macsec_fs->mdev;
+	struct mlx5_fs_id *fs_id_iter;
+	unsigned long index = 0;
+	int err;
+
+	list_for_each_entry(iter, &macsec_fs->macsec_devices_list, macsec_devices_list_entry) {
+		if (iter->macdev == macdev) {
+			macsec_device = iter;
+			break;
+		}
+	}
+
+	if (!macsec_device)
+		return 0;
+
+	xa_for_each(&macsec_device->tx_id_xa, index, fs_id_iter) {
+		err = mlx5_macsec_fs_add_roce_rule_tx(macsec_fs, fs_id_iter->id, gid_idx, addr,
+						      tx_rules_list);
+		if (err) {
+			mlx5_core_err(mdev, "MACsec offload: Failed to add roce TX rule\n");
+			goto out;
+		}
+	}
+
+	index = 0;
+	xa_for_each(&macsec_device->rx_id_xa, index, fs_id_iter) {
+		err = mlx5_macsec_fs_add_roce_rule_rx(macsec_fs, fs_id_iter->id, gid_idx, addr,
+						      rx_rules_list);
+		if (err) {
+			mlx5_core_err(mdev, "MACsec offload: Failed to add roce TX rule\n");
+			goto out;
+		}
+	}
+
+	return 0;
+out:
+	mlx5_macsec_del_roce_rule(gid_idx, macsec_fs, tx_rules_list, rx_rules_list);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_macsec_add_roce_rule);
+
+void mlx5_macsec_add_roce_sa_rules(u32 fs_id, const struct sockaddr *addr, u16 gid_idx,
+				   struct list_head *tx_rules_list,
+				   struct list_head *rx_rules_list,
+				   struct mlx5_macsec_fs *macsec_fs, bool is_tx)
+{
+	(is_tx) ?
+		mlx5_macsec_fs_add_roce_rule_tx(macsec_fs, fs_id, gid_idx, addr,
+						tx_rules_list) :
+		mlx5_macsec_fs_add_roce_rule_rx(macsec_fs, fs_id, gid_idx, addr,
+						rx_rules_list);
+}
+EXPORT_SYMBOL_GPL(mlx5_macsec_add_roce_sa_rules);
+
+void mlx5_macsec_del_roce_sa_rules(u32 fs_id, struct mlx5_macsec_fs *macsec_fs,
+				   struct list_head *tx_rules_list,
+				   struct list_head *rx_rules_list, bool is_tx)
+{
+	(is_tx) ?
+		macsec_fs_del_roce_rules_tx(macsec_fs, fs_id, tx_rules_list) :
+		macsec_fs_del_roce_rules_rx(macsec_fs, fs_id, rx_rules_list);
+}
+EXPORT_SYMBOL_GPL(mlx5_macsec_del_roce_sa_rules);
+
 void mlx5_macsec_fs_cleanup(struct mlx5_macsec_fs *macsec_fs)
 {
 	macsec_fs_rx_cleanup(macsec_fs);
@@ -2015,6 +2394,8 @@ mlx5_macsec_fs_init(struct mlx5_core_dev *mdev)
 		goto tx_cleanup;
 	}
 
+	BLOCKING_INIT_NOTIFIER_HEAD(&mdev->macsec_nh);
+
 	return macsec_fs;
 
 tx_cleanup:
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 80cc12a9a5318..ca93a5ef9dac5 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -364,6 +364,8 @@ enum mlx5_event {
 enum mlx5_driver_event {
 	MLX5_DRIVER_EVENT_TYPE_TRAP = 0,
 	MLX5_DRIVER_EVENT_UPLINK_NETDEV,
+	MLX5_DRIVER_EVENT_MACSEC_SA_ADDED,
+	MLX5_DRIVER_EVENT_MACSEC_SA_DELETED,
 };
 
 enum {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 21954e7aeeba2..21014bc345165 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -807,6 +807,8 @@ struct mlx5_core_dev {
 	struct mlx5_thermal	*thermal;
 #ifdef CONFIG_MLX5_MACSEC
 	struct mlx5_macsec_fs *macsec_fs;
+	/* MACsec notifier chain to sync MACsec core and IB database */
+	struct blocking_notifier_head macsec_nh;
 #endif
 };
 
diff --git a/include/linux/mlx5/macsec.h b/include/linux/mlx5/macsec.h
new file mode 100644
index 0000000000000..f7ff4c2a95d0c
--- /dev/null
+++ b/include/linux/mlx5/macsec.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */
+
+#ifndef MLX5_MACSEC_H
+#define MLX5_MACSEC_H
+
+#ifdef CONFIG_MLX5_MACSEC
+struct mlx5_macsec_event_data {
+	struct mlx5_macsec_fs *macsec_fs;
+	void *macdev;
+	u32 fs_id;
+	bool is_tx;
+};
+
+int mlx5_macsec_add_roce_rule(void *macdev, const struct sockaddr *addr, u16 gid_idx,
+			      struct list_head *tx_rules_list, struct list_head *rx_rules_list,
+			      struct mlx5_macsec_fs *macsec_fs);
+
+void mlx5_macsec_del_roce_rule(u16 gid_idx, struct mlx5_macsec_fs *macsec_fs,
+			       struct list_head *tx_rules_list, struct list_head *rx_rules_list);
+
+void mlx5_macsec_add_roce_sa_rules(u32 fs_id, const struct sockaddr *addr, u16 gid_idx,
+				   struct list_head *tx_rules_list,
+				   struct list_head *rx_rules_list,
+				   struct mlx5_macsec_fs *macsec_fs, bool is_tx);
+
+void mlx5_macsec_del_roce_sa_rules(u32 fs_id, struct mlx5_macsec_fs *macsec_fs,
+				   struct list_head *tx_rules_list,
+				   struct list_head *rx_rules_list, bool is_tx);
+
+#endif
+#endif /* MLX5_MACSEC_H */
-- 
GitLab


From 58dbd6428a6819e55a3c52ec60126b5d00804a38 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 13 Apr 2023 12:04:59 +0300
Subject: [PATCH 1371/1806] RDMA/mlx5: Handles RoCE MACsec steering rules
 addition and deletion

Add RoCE MACsec rules when a gid is added for the MACsec netdevice and
handle their cleanup when the gid is removed or the MACsec SA is deleted.
Also support alias IP for the MACsec device, as long as we don't have
more ips than what the gid table can hold.
In addition handle the case where a gid is added but there are still no
SAs added for the MACsec device, so the rules are added later on when
the SAs are added.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/macsec.c  | 235 +++++++++++++++++++++++++--
 drivers/infiniband/hw/mlx5/macsec.h  |   8 +-
 drivers/infiniband/hw/mlx5/main.c    |   6 +-
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  10 ++
 include/linux/mlx5/driver.h          |   4 +-
 5 files changed, 246 insertions(+), 17 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/macsec.c b/drivers/infiniband/hw/mlx5/macsec.c
index 349ad13af75d7..3c56eb5eddf3b 100644
--- a/drivers/infiniband/hw/mlx5/macsec.c
+++ b/drivers/infiniband/hw/mlx5/macsec.c
@@ -2,13 +2,174 @@
 /* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */
 
 #include "macsec.h"
+#include <linux/mlx5/macsec.h>
 
 struct mlx5_reserved_gids {
 	int macsec_index;
 	const struct ib_gid_attr *physical_gid;
 };
 
-int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev)
+struct mlx5_roce_gids {
+	struct list_head roce_gid_list_entry;
+	u16 gid_idx;
+	union {
+		struct sockaddr_in  sockaddr_in;
+		struct sockaddr_in6 sockaddr_in6;
+	} addr;
+};
+
+struct mlx5_macsec_device {
+	struct list_head macsec_devices_list_entry;
+	void *macdev;
+	struct list_head macsec_roce_gids;
+	struct list_head tx_rules_list;
+	struct list_head rx_rules_list;
+};
+
+static void cleanup_macsec_device(struct mlx5_macsec_device *macsec_device)
+{
+	if (!list_empty(&macsec_device->tx_rules_list) ||
+	    !list_empty(&macsec_device->rx_rules_list) ||
+	    !list_empty(&macsec_device->macsec_roce_gids))
+		return;
+
+	list_del(&macsec_device->macsec_devices_list_entry);
+	kfree(macsec_device);
+}
+
+static struct mlx5_macsec_device *get_macsec_device(void *macdev,
+						    struct list_head *macsec_devices_list)
+{
+	struct mlx5_macsec_device *iter, *macsec_device = NULL;
+
+	list_for_each_entry(iter, macsec_devices_list, macsec_devices_list_entry) {
+		if (iter->macdev == macdev) {
+			macsec_device = iter;
+			break;
+		}
+	}
+
+	if (macsec_device)
+		return macsec_device;
+
+	macsec_device = kzalloc(sizeof(*macsec_device), GFP_KERNEL);
+	if (!macsec_device)
+		return NULL;
+
+	macsec_device->macdev = macdev;
+	INIT_LIST_HEAD(&macsec_device->tx_rules_list);
+	INIT_LIST_HEAD(&macsec_device->rx_rules_list);
+	INIT_LIST_HEAD(&macsec_device->macsec_roce_gids);
+	list_add(&macsec_device->macsec_devices_list_entry, macsec_devices_list);
+
+	return macsec_device;
+}
+
+static void mlx5_macsec_del_roce_gid(struct mlx5_macsec_device *macsec_device, u16 gid_idx)
+{
+	struct mlx5_roce_gids *current_gid, *next_gid;
+
+	list_for_each_entry_safe(current_gid, next_gid, &macsec_device->macsec_roce_gids,
+				 roce_gid_list_entry)
+		if (current_gid->gid_idx == gid_idx) {
+			list_del(&current_gid->roce_gid_list_entry);
+			kfree(current_gid);
+		}
+}
+
+static void mlx5_macsec_save_roce_gid(struct mlx5_macsec_device *macsec_device,
+				      const struct sockaddr *addr, u16 gid_idx)
+{
+	struct mlx5_roce_gids *roce_gids;
+
+	roce_gids = kzalloc(sizeof(*roce_gids), GFP_KERNEL);
+	if (!roce_gids)
+		return;
+
+	roce_gids->gid_idx = gid_idx;
+	if (addr->sa_family == AF_INET)
+		memcpy(&roce_gids->addr.sockaddr_in, addr, sizeof(roce_gids->addr.sockaddr_in));
+	else
+		memcpy(&roce_gids->addr.sockaddr_in6, addr, sizeof(roce_gids->addr.sockaddr_in6));
+
+	list_add_tail(&roce_gids->roce_gid_list_entry, &macsec_device->macsec_roce_gids);
+}
+
+static void handle_macsec_gids(struct list_head *macsec_devices_list,
+			       struct mlx5_macsec_event_data *data)
+{
+	struct mlx5_macsec_device *macsec_device;
+	struct mlx5_roce_gids *gid;
+
+	macsec_device = get_macsec_device(data->macdev, macsec_devices_list);
+	if (!macsec_device)
+		return;
+
+	list_for_each_entry(gid, &macsec_device->macsec_roce_gids, roce_gid_list_entry) {
+		mlx5_macsec_add_roce_sa_rules(data->fs_id, (struct sockaddr *)&gid->addr,
+					      gid->gid_idx, &macsec_device->tx_rules_list,
+					      &macsec_device->rx_rules_list, data->macsec_fs,
+					      data->is_tx);
+	}
+}
+
+static void del_sa_roce_rule(struct list_head *macsec_devices_list,
+			     struct mlx5_macsec_event_data *data)
+{
+	struct mlx5_macsec_device *macsec_device;
+
+	macsec_device = get_macsec_device(data->macdev, macsec_devices_list);
+	WARN_ON(!macsec_device);
+
+	mlx5_macsec_del_roce_sa_rules(data->fs_id, data->macsec_fs,
+				      &macsec_device->tx_rules_list,
+				      &macsec_device->rx_rules_list, data->is_tx);
+}
+
+static int macsec_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+	struct mlx5_macsec *macsec = container_of(nb, struct mlx5_macsec, blocking_events_nb);
+
+	mutex_lock(&macsec->lock);
+	switch (event) {
+	case MLX5_DRIVER_EVENT_MACSEC_SA_ADDED:
+		handle_macsec_gids(&macsec->macsec_devices_list, data);
+		break;
+	case MLX5_DRIVER_EVENT_MACSEC_SA_DELETED:
+		del_sa_roce_rule(&macsec->macsec_devices_list, data);
+		break;
+	default:
+		mutex_unlock(&macsec->lock);
+		return NOTIFY_DONE;
+	}
+	mutex_unlock(&macsec->lock);
+	return NOTIFY_OK;
+}
+
+void mlx5r_macsec_event_register(struct mlx5_ib_dev *dev)
+{
+	if (!mlx5_is_macsec_roce_supported(dev->mdev)) {
+		mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n");
+		return;
+	}
+
+	dev->macsec.blocking_events_nb.notifier_call = macsec_event;
+	blocking_notifier_chain_register(&dev->mdev->macsec_nh,
+					 &dev->macsec.blocking_events_nb);
+}
+
+void mlx5r_macsec_event_unregister(struct mlx5_ib_dev *dev)
+{
+	if (!mlx5_is_macsec_roce_supported(dev->mdev)) {
+		mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n");
+		return;
+	}
+
+	blocking_notifier_chain_unregister(&dev->mdev->macsec_nh,
+					   &dev->macsec.blocking_events_nb);
+}
+
+int mlx5r_macsec_init_gids_and_devlist(struct mlx5_ib_dev *dev)
 {
 	int i, j, max_gids;
 
@@ -29,6 +190,9 @@ int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev)
 			dev->port[i].reserved_gids[j].macsec_index = -1;
 	}
 
+	INIT_LIST_HEAD(&dev->macsec.macsec_devices_list);
+	mutex_init(&dev->macsec.lock);
+
 	return 0;
 err:
 	while (i >= 0) {
@@ -47,15 +211,22 @@ void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev)
 
 	for (i = 0; i < dev->num_ports; i++)
 		kfree(dev->port[i].reserved_gids);
+
+	mutex_destroy(&dev->macsec.lock);
 }
 
 int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr)
 {
 	struct mlx5_ib_dev *dev = to_mdev(attr->device);
+	struct mlx5_macsec_device *macsec_device;
 	const struct ib_gid_attr *physical_gid;
 	struct mlx5_reserved_gids *mgids;
 	struct net_device *ndev;
 	int ret = 0;
+	union {
+		struct sockaddr_in  sockaddr_in;
+		struct sockaddr_in6 sockaddr_in6;
+	} addr;
 
 	if (attr->gid_type != IB_GID_TYPE_ROCE_UDP_ENCAP)
 		return 0;
@@ -76,34 +247,62 @@ int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr)
 		rcu_read_unlock();
 		return 0;
 	}
+	dev_hold(ndev);
 	rcu_read_unlock();
 
+	mutex_lock(&dev->macsec.lock);
+	macsec_device = get_macsec_device(ndev, &dev->macsec.macsec_devices_list);
+	if (!macsec_device) {
+		ret = -ENOMEM;
+		goto dev_err;
+	}
+
 	physical_gid = rdma_find_gid(attr->device, &attr->gid,
 				     attr->gid_type, NULL);
-	if (IS_ERR(physical_gid))
-		return 0;
+	if (!IS_ERR(physical_gid)) {
+		ret = set_roce_addr(to_mdev(physical_gid->device),
+				    physical_gid->port_num,
+				    physical_gid->index, NULL,
+				    physical_gid);
+		if (ret)
+			goto gid_err;
 
-	ret = set_roce_addr(to_mdev(physical_gid->device),
-			    physical_gid->port_num,
-			    physical_gid->index, NULL,
-			    physical_gid);
-	if (ret)
-		goto gid_err;
+		mgids = &dev->port[attr->port_num - 1].reserved_gids[physical_gid->index];
+		mgids->macsec_index = attr->index;
+		mgids->physical_gid = physical_gid;
+	}
 
-	mgids = &dev->port[attr->port_num - 1].reserved_gids[physical_gid->index];
-	mgids->macsec_index = attr->index;
-	mgids->physical_gid = physical_gid;
+	/* Proceed with adding steering rules, regardless if there was gid ambiguity or not.*/
+	rdma_gid2ip((struct sockaddr *)&addr, &attr->gid);
+	ret = mlx5_macsec_add_roce_rule(ndev, (struct sockaddr *)&addr, attr->index,
+					&macsec_device->tx_rules_list,
+					&macsec_device->rx_rules_list, dev->mdev->macsec_fs);
+	if (ret && !IS_ERR(physical_gid))
+		goto rule_err;
 
-	return 0;
+	mlx5_macsec_save_roce_gid(macsec_device, (struct sockaddr *)&addr, attr->index);
+
+	dev_put(ndev);
+	mutex_unlock(&dev->macsec.lock);
+	return ret;
 
+rule_err:
+	set_roce_addr(to_mdev(physical_gid->device), physical_gid->port_num,
+		      physical_gid->index, &physical_gid->gid, physical_gid);
+	mgids->macsec_index = -1;
 gid_err:
 	rdma_put_gid_attr(physical_gid);
+	cleanup_macsec_device(macsec_device);
+dev_err:
+	dev_put(ndev);
+	mutex_unlock(&dev->macsec.lock);
 	return ret;
 }
 
 void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr)
 {
 	struct mlx5_ib_dev *dev = to_mdev(attr->device);
+	struct mlx5_macsec_device *macsec_device;
 	struct mlx5_reserved_gids *mgids;
 	struct net_device *ndev;
 	int i, max_gids;
@@ -134,8 +333,10 @@ void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr)
 		rcu_read_unlock();
 		return;
 	}
+	dev_hold(ndev);
 	rcu_read_unlock();
 
+	mutex_lock(&dev->macsec.lock);
 	max_gids = MLX5_CAP_ROCE(dev->mdev, roce_address_table_size);
 	for (i = 0; i < max_gids; i++) { /* Checking if macsec gid has ambiguous IP */
 		mgids = &dev->port[attr->port_num - 1].reserved_gids[i];
@@ -152,4 +353,12 @@ void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr)
 			break;
 		}
 	}
+	macsec_device = get_macsec_device(ndev, &dev->macsec.macsec_devices_list);
+	mlx5_macsec_del_roce_rule(attr->index, dev->mdev->macsec_fs,
+				  &macsec_device->tx_rules_list, &macsec_device->rx_rules_list);
+	mlx5_macsec_del_roce_gid(macsec_device, attr->index);
+	cleanup_macsec_device(macsec_device);
+
+	dev_put(ndev);
+	mutex_unlock(&dev->macsec.lock);
 }
diff --git a/drivers/infiniband/hw/mlx5/macsec.h b/drivers/infiniband/hw/mlx5/macsec.h
index b60f8f046d6f4..9b77ba90f0f41 100644
--- a/drivers/infiniband/hw/mlx5/macsec.h
+++ b/drivers/infiniband/hw/mlx5/macsec.h
@@ -14,12 +14,16 @@ struct mlx5_reserved_gids;
 
 int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr);
 void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr);
-int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev);
+int mlx5r_macsec_init_gids_and_devlist(struct mlx5_ib_dev *dev);
 void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev);
+void mlx5r_macsec_event_register(struct mlx5_ib_dev *dev);
+void mlx5r_macsec_event_unregister(struct mlx5_ib_dev *dev);
 #else
 static inline int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr) { return 0; }
 static inline void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr) {}
-static inline int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev) { return 0; }
+static inline int mlx5r_macsec_init_gids_and_devlist(struct mlx5_ib_dev *dev) { return 0; }
 static inline void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev) {}
+static inline void mlx5r_macsec_event_register(struct mlx5_ib_dev *dev) {}
+static inline void mlx5r_macsec_event_unregister(struct mlx5_ib_dev *dev) {}
 #endif
 #endif /* __MLX5_MACSEC_H__ */
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index f463cf8b75014..b4cc16a19757c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3684,7 +3684,7 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	if (err)
 		return err;
 
-	err = mlx5r_macsec_alloc_gids(dev);
+	err = mlx5r_macsec_init_gids_and_devlist(dev);
 	if (err)
 		return err;
 
@@ -4125,11 +4125,15 @@ static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev)
 {
 	dev->mdev_events.notifier_call = mlx5_ib_event;
 	mlx5_notifier_register(dev->mdev, &dev->mdev_events);
+
+	mlx5r_macsec_event_register(dev);
+
 	return 0;
 }
 
 static void mlx5_ib_stage_dev_notifier_cleanup(struct mlx5_ib_dev *dev)
 {
+	mlx5r_macsec_event_unregister(dev);
 	mlx5_notifier_unregister(dev->mdev, &dev->mdev_events);
 }
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index a4b940b5035f2..16713baf0d060 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1090,6 +1090,12 @@ struct mlx5_special_mkeys {
 	__be32 terminate_scatter_list_mkey;
 };
 
+struct mlx5_macsec {
+	struct mutex lock; /* Protects mlx5_macsec internal contexts */
+	struct list_head macsec_devices_list;
+	struct notifier_block blocking_events_nb;
+};
+
 struct mlx5_ib_dev {
 	struct ib_device		ib_dev;
 	struct mlx5_core_dev		*mdev;
@@ -1149,6 +1155,10 @@ struct mlx5_ib_dev {
 	u16 pkey_table_len;
 	u8 lag_ports;
 	struct mlx5_special_mkeys mkeys;
+
+#ifdef CONFIG_MLX5_MACSEC
+	struct mlx5_macsec macsec;
+#endif
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 21014bc345165..728bcd6d184c8 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1325,6 +1325,7 @@ static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev)
 	return mlx5_is_roce_on(dev);
 }
 
+#ifdef CONFIG_MLX5_MACSEC
 static inline bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev)
 {
 	if (!(MLX5_CAP_GEN_64(mdev, general_obj_types) &
@@ -1363,11 +1364,12 @@ static inline bool mlx5_is_macsec_roce_supported(struct mlx5_core_dev *mdev)
 	if (((MLX5_CAP_GEN_2(mdev, flow_table_type_2_type) &
 	     NIC_RDMA_BOTH_DIRS_CAPS) != NIC_RDMA_BOTH_DIRS_CAPS) ||
 	     !MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, max_modify_header_actions) ||
-	     !mlx5e_is_macsec_device(mdev))
+	     !mlx5e_is_macsec_device(mdev) || !mdev->macsec_fs)
 		return false;
 
 	return true;
 }
+#endif
 
 enum {
 	MLX5_OCTWORD = 16,
-- 
GitLab


From b22eef6864caadd2199e3db0be7235c176a04f89 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sat, 19 Aug 2023 12:11:06 +0100
Subject: [PATCH 1372/1806] net: dsa: realtek: add phylink_get_caps
 implementation

The user ports use RSGMII, but we don't have that, and DT doesn't
specify a phy interface mode, so phylib defaults to GMII. These support
1G, 100M and 10M with flow control. It is unknown whether asymetric
pause is supported at all speeds.

The CPU port uses MII/GMII/RGMII/REVMII by hardware pin strapping,
and support speeds specific to each, with full duplex only supported
in some modes. Flow control may be supported again by hardware pin
strapping, and theoretically is readable through a register but no
information is given in the datasheet for that.

So, we do a best efforts - and be lenient.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/realtek/rtl8366rb.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c
index 25f88022b9e44..7868ef237f6c0 100644
--- a/drivers/net/dsa/realtek/rtl8366rb.c
+++ b/drivers/net/dsa/realtek/rtl8366rb.c
@@ -1049,6 +1049,32 @@ static enum dsa_tag_protocol rtl8366_get_tag_protocol(struct dsa_switch *ds,
 	return DSA_TAG_PROTO_RTL4_A;
 }
 
+static void rtl8366rb_phylink_get_caps(struct dsa_switch *ds, int port,
+				       struct phylink_config *config)
+{
+	unsigned long *interfaces = config->supported_interfaces;
+	struct realtek_priv *priv = ds->priv;
+
+	if (port == priv->cpu_port) {
+		__set_bit(PHY_INTERFACE_MODE_MII, interfaces);
+		__set_bit(PHY_INTERFACE_MODE_GMII, interfaces);
+		/* REVMII only supports 100M FD */
+		__set_bit(PHY_INTERFACE_MODE_REVMII, interfaces);
+		/* RGMII only supports 1G FD */
+		phy_interface_set_rgmii(interfaces);
+
+		config->mac_capabilities = MAC_1000 | MAC_100 |
+					   MAC_SYM_PAUSE;
+	} else {
+		/* RSGMII port, but we don't have that, and we don't
+		 * specify in DT, so phylib uses the default of GMII
+		 */
+		__set_bit(PHY_INTERFACE_MODE_GMII, interfaces);
+		config->mac_capabilities = MAC_1000 | MAC_100 | MAC_10 |
+					   MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
+	}
+}
+
 static void
 rtl8366rb_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode,
 		      phy_interface_t interface, struct phy_device *phydev,
@@ -1796,6 +1822,7 @@ static int rtl8366rb_detect(struct realtek_priv *priv)
 static const struct dsa_switch_ops rtl8366rb_switch_ops_smi = {
 	.get_tag_protocol = rtl8366_get_tag_protocol,
 	.setup = rtl8366rb_setup,
+	.phylink_get_caps = rtl8366rb_phylink_get_caps,
 	.phylink_mac_link_up = rtl8366rb_mac_link_up,
 	.phylink_mac_link_down = rtl8366rb_mac_link_down,
 	.get_strings = rtl8366_get_strings,
@@ -1821,6 +1848,7 @@ static const struct dsa_switch_ops rtl8366rb_switch_ops_mdio = {
 	.setup = rtl8366rb_setup,
 	.phy_read = rtl8366rb_dsa_phy_read,
 	.phy_write = rtl8366rb_dsa_phy_write,
+	.phylink_get_caps = rtl8366rb_phylink_get_caps,
 	.phylink_mac_link_up = rtl8366rb_mac_link_up,
 	.phylink_mac_link_down = rtl8366rb_mac_link_down,
 	.get_strings = rtl8366_get_strings,
-- 
GitLab


From d6499f0b7c7ce3d69f658331e78e520c7ebcb238 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Fri, 18 Aug 2023 15:07:05 +0800
Subject: [PATCH 1373/1806] net: bgmac: Return PTR_ERR() for
 fixed_phy_register()

fixed_phy_register() returns -EPROBE_DEFER, -EINVAL and -EBUSY,
etc, in addition to -ENODEV. The best practice is to return
these error codes with PTR_ERR().

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bgmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 10c7c232cc4ec..7c19ba58e9ccd 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1450,7 +1450,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac)
 	phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
 	if (!phy_dev || IS_ERR(phy_dev)) {
 		dev_err(bgmac->dev, "Failed to register fixed PHY device\n");
-		return -ENODEV;
+		return PTR_ERR(phy_dev);
 	}
 
 	err = phy_connect_direct(bgmac->net_dev, phy_dev, bgmac_adjust_link,
-- 
GitLab


From acf50d1adbf440a01fc9cca16e80dde3da3eccab Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Fri, 18 Aug 2023 15:07:06 +0800
Subject: [PATCH 1374/1806] net: bcmgenet: Return PTR_ERR() for
 fixed_phy_register()

fixed_phy_register() returns -EPROBE_DEFER, -EINVAL and -EBUSY,
etc, in addition to -ENODEV. The Best practice is to return these
error codes with PTR_ERR().

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Acked-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmmii.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 0092e46c46f83..4012a141a229b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -619,7 +619,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
 		if (!phydev || IS_ERR(phydev)) {
 			dev_err(kdev, "failed to register fixed PHY device\n");
-			return -ENODEV;
+			return PTR_ERR(phydev);
 		}
 
 		/* Make sure we initialize MoCA PHYs with a link down */
-- 
GitLab


From 294f48e9b234415cbd8cc4e233d5fbd41e961148 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Fri, 18 Aug 2023 15:07:07 +0800
Subject: [PATCH 1375/1806] net: lan743x: Return PTR_ERR() for
 fixed_phy_register()

fixed_phy_register() returns -EPROBE_DEFER, -EINVAL and -EBUSY,
etc, in addition to -EIO. The Best practice is to return these
error codes with PTR_ERR().

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index a36f6369f1327..c81cdeb4d4e7e 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1515,7 +1515,7 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter)
 							    &fphy_status, NULL);
 				if (IS_ERR(phydev)) {
 					netdev_err(netdev, "No PHY/fixed_PHY found\n");
-					return -EIO;
+					return PTR_ERR(phydev);
 				}
 			} else {
 				goto return_error;
-- 
GitLab


From 0f158b32a9b146c9b86783efccfd9ed02c744623 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 18 Aug 2023 17:41:45 +0000
Subject: [PATCH 1376/1806] net: selectively purge error queue in IP_RECVERR /
 IPV6_RECVERR

Setting IP_RECVERR and IPV6_RECVERR options to zero currently
purges the socket error queue, which was probably not expected
for zerocopy and tx_timestamp users.

I discovered this issue while preparing commit 6b5f43ea0815
("inet: move inet->recverr to inet->inet_flags"), I presume this
change does not need to be backported to stable kernels.

Add skb_errqueue_purge() helper to purge error messages only.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h   |  1 +
 net/core/skbuff.c        | 21 +++++++++++++++++++++
 net/ipv4/ip_sockglue.c   |  2 +-
 net/ipv6/ipv6_sockglue.c |  2 +-
 4 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9aec136bc6901..4174c4b82d13b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3180,6 +3180,7 @@ static inline void skb_queue_purge(struct sk_buff_head *list)
 }
 
 unsigned int skb_rbtree_purge(struct rb_root *root);
+void skb_errqueue_purge(struct sk_buff_head *list);
 
 void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 117d36b1fae3e..faa6c86da2a54 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3745,6 +3745,27 @@ unsigned int skb_rbtree_purge(struct rb_root *root)
 	return sum;
 }
 
+void skb_errqueue_purge(struct sk_buff_head *list)
+{
+	struct sk_buff *skb, *next;
+	struct sk_buff_head kill;
+	unsigned long flags;
+
+	__skb_queue_head_init(&kill);
+
+	spin_lock_irqsave(&list->lock, flags);
+	skb_queue_walk_safe(list, skb, next) {
+		if (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY ||
+		    SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING)
+			continue;
+		__skb_unlink(skb, list);
+		__skb_queue_tail(&kill, skb);
+	}
+	spin_unlock_irqrestore(&list->lock, flags);
+	__skb_queue_purge(&kill);
+}
+EXPORT_SYMBOL(skb_errqueue_purge);
+
 /**
  *	skb_queue_head - queue a buffer at the list head
  *	@list: list to use
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 61b2e7bc70315..54ad0f0d5c2dd 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -976,7 +976,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 	case IP_RECVERR:
 		inet_assign_bit(RECVERR, sk, val);
 		if (!val)
-			skb_queue_purge(&sk->sk_error_queue);
+			skb_errqueue_purge(&sk->sk_error_queue);
 		return 0;
 	case IP_RECVERR_RFC4884:
 		if (val < 0 || val > 1)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d19577a94bcc6..0e2a0847b387f 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -923,7 +923,7 @@ done:
 			goto e_inval;
 		np->recverr = valbool;
 		if (!val)
-			skb_queue_purge(&sk->sk_error_queue);
+			skb_errqueue_purge(&sk->sk_error_queue);
 		retv = 0;
 		break;
 	case IPV6_FLOWINFO_SEND:
-- 
GitLab


From 5cb249686e67dbef3ffe53887fa725eefc5a7144 Mon Sep 17 00:00:00 2001
From: Patrick Rohr <prohr@google.com>
Date: Fri, 18 Aug 2023 11:22:49 -0700
Subject: [PATCH 1377/1806] net: release reference to inet6_dev pointer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

addrconf_prefix_rcv returned early without releasing the inet6_dev
pointer when the PIO lifetime is less than accept_ra_min_lft.

Fixes: 5027d54a9c30 ("net: change accept_ra_min_rtr_lft to affect all RA lifetimes")
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Cc: David Ahern <dsahern@kernel.org>
Cc: Simon Horman <horms@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Patrick Rohr <prohr@google.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 5184bd0ceb126..47d1dd8501b74 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2742,7 +2742,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 	}
 
 	if (valid_lft != 0 && valid_lft < in6_dev->cnf.accept_ra_min_lft)
-		return;
+		goto put;
 
 	/*
 	 *	Two things going on here:
-- 
GitLab


From c4cf2bc0d2c97214e41b44b2b05cedc7093ccbbd Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 18 Aug 2023 16:06:13 +0800
Subject: [PATCH 1378/1806] selftests: vrf_route_leaking: remove ipv6_ping_frag
 from default testing

As the initial commit 1a01727676a8 ("selftests: Add VRF route leaking
tests") said, the IPv6 MTU test fails as source address selection
picking ::1. Every time we run the selftest this one report failed.
There seems not much meaning  to keep reporting a failure for 3 years
that no one plan to fix/update. Let't just skip this one first. We can
add it back when the issue fixed.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/vrf_route_leaking.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh
index 23cf924754a53..dedc52562b4f3 100755
--- a/tools/testing/selftests/net/vrf_route_leaking.sh
+++ b/tools/testing/selftests/net/vrf_route_leaking.sh
@@ -565,7 +565,7 @@ EOF
 command -v ping6 > /dev/null 2>&1 && ping6=$(command -v ping6) || ping6=$(command -v ping)
 
 TESTS_IPV4="ipv4_ping_ttl ipv4_traceroute ipv4_ping_frag ipv4_ping_ttl_asym ipv4_traceroute_asym"
-TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_frag ipv6_ping_ttl_asym ipv6_traceroute_asym"
+TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_ttl_asym ipv6_traceroute_asym"
 
 ret=0
 nsuccess=0
-- 
GitLab


From b358f57f7db620f5c25e60d70015f4e4bb050688 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 18 Aug 2023 16:29:01 +0800
Subject: [PATCH 1379/1806] ipv6: do not match device when remove source route

After deleting an IPv6 address on an interface and cleaning up the
related preferred source entries, it is important to ensure that all
routes associated with the deleted address are properly cleared. The
current implementation of rt6_remove_prefsrc() only checks the preferred
source addresses bound to the current device. However, there may be
routes that are bound to other devices but still utilize the same
preferred source address.

To address this issue, it is necessary to also delete entries that are
bound to other interfaces but share the same source address with the
current device. Failure to delete these entries would leave routes that
are bound to the deleted address unclear. Here is an example reproducer
(I have omitted unrelated routes):

+ ip link add dummy1 type dummy
+ ip link add dummy2 type dummy
+ ip link set dummy1 up
+ ip link set dummy2 up
+ ip addr add 1:2:3:4::5/64 dev dummy1
+ ip route add 7:7:7:0::1 dev dummy1 src 1:2:3:4::5
+ ip route add 7:7:7:0::2 dev dummy2 src 1:2:3:4::5
+ ip -6 route show
1:2:3:4::/64 dev dummy1 proto kernel metric 256 pref medium
7:7:7::1 dev dummy1 src 1:2:3:4::5 metric 1024 pref medium
7:7:7::2 dev dummy2 src 1:2:3:4::5 metric 1024 pref medium
+ ip addr del 1:2:3:4::5/64 dev dummy1
+ ip -6 route show
7:7:7::1 dev dummy1 metric 1024 pref medium
7:7:7::2 dev dummy2 src 1:2:3:4::5 metric 1024 pref medium

As Ido reminds, in IPv6, the preferred source address is looked up in
the same VRF as the first nexthop device, which is different with IPv4.
So, while removing the device checking, we also need to add an
ipv6_chk_addr() check to make sure the address does not exist on the other
devices of the rt nexthop device's VRF.

After fix:
+ ip addr del 1:2:3:4::5/64 dev dummy1
+ ip -6 route show
7:7:7::1 dev dummy1 metric 1024 pref medium
7:7:7::2 dev dummy2 metric 1024 pref medium

Reported-by: Thomas Haller <thaller@redhat.com>
Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2170513
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index db10c36f34bbc..a5b74b91c8f39 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4582,21 +4582,19 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 
 /* remove deleted ip from prefsrc entries */
 struct arg_dev_net_ip {
-	struct net_device *dev;
 	struct net *net;
 	struct in6_addr *addr;
 };
 
 static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg)
 {
-	struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev;
 	struct net *net = ((struct arg_dev_net_ip *)arg)->net;
 	struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
 
 	if (!rt->nh &&
-	    ((void *)rt->fib6_nh->fib_nh_dev == dev || !dev) &&
 	    rt != net->ipv6.fib6_null_entry &&
-	    ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr)) {
+	    ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr) &&
+	    !ipv6_chk_addr(net, addr, rt->fib6_nh->fib_nh_dev, 0)) {
 		spin_lock_bh(&rt6_exception_lock);
 		/* remove prefsrc entry */
 		rt->fib6_prefsrc.plen = 0;
@@ -4609,7 +4607,6 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 {
 	struct net *net = dev_net(ifp->idev->dev);
 	struct arg_dev_net_ip adni = {
-		.dev = ifp->idev->dev,
 		.net = net,
 		.addr = &ifp->addr,
 	};
-- 
GitLab


From 429b55b441f3eb747425f87c8f194d4313692c41 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 18 Aug 2023 16:29:02 +0800
Subject: [PATCH 1380/1806] selftests: fib_test: add a test case for IPv6
 source address delete

Add a test case for IPv6 source address delete.

As David suggested, add tests:
- Single device using src address
- Two devices with the same source address
- VRF with single device using src address
- VRF with two devices using src address

As Ido points out, in IPv6, the preferred source address is looked up in
the same VRF as the first nexthop device. This will give us similar results
to IPv4 if the route is installed in the same VRF as the nexthop device, but
not when the nexthop device is enslaved to a different VRF. So add tests:
- src address and nexthop dev in same VR
- src address and nexthop device in different VRF

The link local address delete logic is different from the global address.
It should only affect the associate device it bonds to. So add tests cases
for link local address testing.

Here is the test result:

IPv6 delete address route tests
    Single device using src address
    TEST: Prefsrc removed when src address removed on other device      [ OK ]
    Two devices with the same source address
    TEST: Prefsrc not removed when src address exist on other device    [ OK ]
    TEST: Prefsrc removed when src address removed on all devices       [ OK ]
    VRF with single device using src address
    TEST: Prefsrc removed when src address removed on other device      [ OK ]
    VRF with two devices using src address
    TEST: Prefsrc not removed when src address exist on other device    [ OK ]
    TEST: Prefsrc removed when src address removed on all devices       [ OK ]
    src address and nexthop dev in same VRF
    TEST: Prefsrc removed from VRF when source address deleted          [ OK ]
    TEST: Prefsrc in default VRF not removed                            [ OK ]
    TEST: Prefsrc not removed from VRF when source address exist        [ OK ]
    TEST: Prefsrc in default VRF removed                                [ OK ]
    src address and nexthop device in different VRF
    TEST: Prefsrc not removed from VRF when nexthop dev in diff VRF     [ OK ]
    TEST: Prefsrc not removed in default VRF                            [ OK ]
    TEST: Prefsrc removed from VRF when nexthop dev in diff VRF         [ OK ]
    TEST: Prefsrc removed in default VRF                                [ OK ]
    Table ID 0
    TEST: Prefsrc removed from default VRF when source address deleted  [ OK ]
    Link local source route
    TEST: Prefsrc not removed when delete ll addr from other dev        [ OK ]
    TEST: Prefsrc removed when delete ll addr                           [ OK ]
    TEST: Prefsrc not removed when delete ll addr from other dev        [ OK ]
    TEST: Prefsrc removed even ll addr still exist on other dev         [ OK ]

Tests passed:  19
Tests failed:   0

Suggested-by: Ido Schimmel <idosch@idosch.org>
Suggested-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 152 ++++++++++++++++++++++-
 1 file changed, 151 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index c14ad6e75c1e2..d328af4a149c3 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -12,7 +12,7 @@ ksft_skip=4
 TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \
        ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \
        ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \
-       ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test"
+       ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
@@ -1934,6 +1934,155 @@ ipv4_del_addr_test()
 	cleanup
 }
 
+ipv6_del_addr_test()
+{
+	echo
+	echo "IPv6 delete address route tests"
+
+	setup
+
+	set -e
+	for i in $(seq 6); do
+		$IP li add dummy${i} up type dummy
+	done
+
+	$IP li add red up type vrf table 1111
+	$IP ro add vrf red unreachable default
+	for i in $(seq 4 6); do
+		$IP li set dummy${i} vrf red
+	done
+
+	$IP addr add dev dummy1 fe80::1/128
+	$IP addr add dev dummy1 2001:db8:101::1/64
+	$IP addr add dev dummy1 2001:db8:101::10/64
+	$IP addr add dev dummy1 2001:db8:101::11/64
+	$IP addr add dev dummy1 2001:db8:101::12/64
+	$IP addr add dev dummy1 2001:db8:101::13/64
+	$IP addr add dev dummy1 2001:db8:101::14/64
+	$IP addr add dev dummy1 2001:db8:101::15/64
+	$IP addr add dev dummy2 fe80::1/128
+	$IP addr add dev dummy2 2001:db8:101::1/64
+	$IP addr add dev dummy2 2001:db8:101::11/64
+	$IP addr add dev dummy3 fe80::1/128
+
+	$IP addr add dev dummy4 2001:db8:101::1/64
+	$IP addr add dev dummy4 2001:db8:101::10/64
+	$IP addr add dev dummy4 2001:db8:101::11/64
+	$IP addr add dev dummy4 2001:db8:101::12/64
+	$IP addr add dev dummy4 2001:db8:101::13/64
+	$IP addr add dev dummy4 2001:db8:101::14/64
+	$IP addr add dev dummy5 2001:db8:101::1/64
+	$IP addr add dev dummy5 2001:db8:101::11/64
+
+	# Single device using src address
+	$IP route add 2001:db8:110::/64 dev dummy3 src 2001:db8:101::10
+	# Two devices with the same source address
+	$IP route add 2001:db8:111::/64 dev dummy3 src 2001:db8:101::11
+	# VRF with single device using src address
+	$IP route add vrf red 2001:db8:110::/64 dev dummy6 src 2001:db8:101::10
+	# VRF with two devices using src address
+	$IP route add vrf red 2001:db8:111::/64 dev dummy6 src 2001:db8:101::11
+	# src address and nexthop dev in same VRF
+	$IP route add 2001:db8:112::/64 dev dummy3 src 2001:db8:101::12
+	$IP route add vrf red 2001:db8:112::/64 dev dummy6 src 2001:db8:101::12
+	# src address and nexthop device in different VRF
+	$IP route add 2001:db8:113::/64 dev lo src 2001:db8:101::13
+	$IP route add vrf red 2001:db8:113::/64 dev lo src 2001:db8:101::13
+	# table ID 0
+	$IP route add table 0 2001:db8:115::/64 via 2001:db8:101::2 src 2001:db8:101::15
+	# Link local source route
+	$IP route add 2001:db8:116::/64 dev dummy2 src fe80::1
+	$IP route add 2001:db8:117::/64 dev dummy3 src fe80::1
+	set +e
+
+	echo "    Single device using src address"
+
+	$IP addr del dev dummy1 2001:db8:101::10/64
+	$IP -6 route show | grep -q "src 2001:db8:101::10 "
+	log_test $? 1 "Prefsrc removed when src address removed on other device"
+
+	echo "    Two devices with the same source address"
+
+	$IP addr del dev dummy1 2001:db8:101::11/64
+	$IP -6 route show | grep -q "src 2001:db8:101::11 "
+	log_test $? 0 "Prefsrc not removed when src address exist on other device"
+
+	$IP addr del dev dummy2 2001:db8:101::11/64
+	$IP -6 route show | grep -q "src 2001:db8:101::11 "
+	log_test $? 1 "Prefsrc removed when src address removed on all devices"
+
+	echo "    VRF with single device using src address"
+
+	$IP addr del dev dummy4 2001:db8:101::10/64
+	$IP -6 route show vrf red | grep -q "src 2001:db8:101::10 "
+	log_test $? 1 "Prefsrc removed when src address removed on other device"
+
+	echo "    VRF with two devices using src address"
+
+	$IP addr del dev dummy4 2001:db8:101::11/64
+	$IP -6 route show vrf red | grep -q "src 2001:db8:101::11 "
+	log_test $? 0 "Prefsrc not removed when src address exist on other device"
+
+	$IP addr del dev dummy5 2001:db8:101::11/64
+	$IP -6 route show vrf red | grep -q "src 2001:db8:101::11 "
+	log_test $? 1 "Prefsrc removed when src address removed on all devices"
+
+	echo "    src address and nexthop dev in same VRF"
+
+	$IP addr del dev dummy4 2001:db8:101::12/64
+	$IP -6 route show vrf red | grep -q "src 2001:db8:101::12 "
+	log_test $? 1 "Prefsrc removed from VRF when source address deleted"
+	$IP -6 route show | grep -q " src 2001:db8:101::12 "
+	log_test $? 0 "Prefsrc in default VRF not removed"
+
+	$IP addr add dev dummy4 2001:db8:101::12/64
+	$IP route replace vrf red 2001:db8:112::/64 dev dummy6 src 2001:db8:101::12
+	$IP addr del dev dummy1 2001:db8:101::12/64
+	$IP -6 route show vrf red | grep -q "src 2001:db8:101::12 "
+	log_test $? 0 "Prefsrc not removed from VRF when source address exist"
+	$IP -6 route show | grep -q " src 2001:db8:101::12 "
+	log_test $? 1 "Prefsrc in default VRF removed"
+
+	echo "    src address and nexthop device in different VRF"
+
+	$IP addr del dev dummy4 2001:db8:101::13/64
+	$IP -6 route show vrf red | grep -q "src 2001:db8:101::13 "
+	log_test $? 0 "Prefsrc not removed from VRF when nexthop dev in diff VRF"
+	$IP -6 route show | grep -q "src 2001:db8:101::13 "
+	log_test $? 0 "Prefsrc not removed in default VRF"
+
+	$IP addr add dev dummy4 2001:db8:101::13/64
+	$IP addr del dev dummy1 2001:db8:101::13/64
+	$IP -6 route show vrf red | grep -q "src 2001:db8:101::13 "
+	log_test $? 1 "Prefsrc removed from VRF when nexthop dev in diff VRF"
+	$IP -6 route show | grep -q "src 2001:db8:101::13 "
+	log_test $? 1 "Prefsrc removed in default VRF"
+
+	echo "    Table ID 0"
+
+	$IP addr del dev dummy1 2001:db8:101::15/64
+	$IP -6 route show | grep -q "src 2001:db8:101::15"
+	log_test $? 1 "Prefsrc removed from default VRF when source address deleted"
+
+	echo "    Link local source route"
+	$IP addr del dev dummy1 fe80::1/128
+	$IP -6 route show | grep -q "2001:db8:116::/64 dev dummy2 src fe80::1"
+	log_test $? 0 "Prefsrc not removed when delete ll addr from other dev"
+	$IP addr del dev dummy2 fe80::1/128
+	$IP -6 route show | grep -q "2001:db8:116::/64 dev dummy2 src fe80::1"
+	log_test $? 1 "Prefsrc removed when delete ll addr"
+	$IP -6 route show | grep -q "2001:db8:117::/64 dev dummy3 src fe80::1"
+	log_test $? 0 "Prefsrc not removed when delete ll addr from other dev"
+	$IP addr add dev dummy1 fe80::1/128
+	$IP addr del dev dummy3 fe80::1/128
+	$IP -6 route show | grep -q "2001:db8:117::/64 dev dummy3 src fe80::1"
+	log_test $? 1 "Prefsrc removed even ll addr still exist on other dev"
+
+	for i in $(seq 6); do
+		$IP li del dummy${i}
+	done
+	cleanup
+}
 
 ipv4_route_v6_gw_test()
 {
@@ -2276,6 +2425,7 @@ do
 	ipv6_addr_metric)		ipv6_addr_metric_test;;
 	ipv4_addr_metric)		ipv4_addr_metric_test;;
 	ipv4_del_addr)			ipv4_del_addr_test;;
+	ipv6_del_addr)			ipv6_del_addr_test;;
 	ipv6_route_metrics)		ipv6_route_metrics_test;;
 	ipv4_route_metrics)		ipv4_route_metrics_test;;
 	ipv4_route_v6_gw)		ipv4_route_v6_gw_test;;
-- 
GitLab


From 669a55560e4b8fad3598d544d062ab40fd860bcb Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Sat, 19 Aug 2023 18:54:40 +0800
Subject: [PATCH 1381/1806] net: stmmac: Check more MAC HW features for XGMAC
 Core 3.20

1. XGMAC Core does not have hash_filter definition, it uses
vlhash(VLAN Hash Filtering) instead, skip hash_filter when XGMAC.
2. Show exact size of Hash Table instead of raw register value.
3. Show full description of safety features defined by Synopsys Databook.
4. When safety feature is configured with no parity, or ECC only,
keep FSM Parity Checking disabled.

Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h  | 36 ++++++++++
 .../net/ethernet/stmicro/stmmac/dwxgmac2.h    | 21 ++++++
 .../ethernet/stmicro/stmmac/dwxgmac2_core.c   |  6 +-
 .../ethernet/stmicro/stmmac/dwxgmac2_dma.c    | 23 ++++++
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 71 +++++++++++++++++--
 5 files changed, 149 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 1f5293c8cc047..403cb397d4d36 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -410,6 +410,18 @@ struct dma_features {
 	unsigned int number_tx_queues;
 	/* PPS output */
 	unsigned int pps_out_num;
+	/* Number of Traffic Classes */
+	unsigned int numtc;
+	/* DCB Feature Enable */
+	unsigned int dcben;
+	/* IEEE 1588 High Word Register Enable */
+	unsigned int advthword;
+	/* PTP Offload Enable */
+	unsigned int ptoen;
+	/* One-Step Timestamping Enable */
+	unsigned int osten;
+	/* Priority-Based Flow Control Enable */
+	unsigned int pfcen;
 	/* Alternate (enhanced) DESC mode */
 	unsigned int enh_desc;
 	/* TX and RX FIFO sizes */
@@ -430,16 +442,40 @@ struct dma_features {
 	unsigned int dvlan;
 	unsigned int l3l4fnum;
 	unsigned int arpoffsel;
+	/* One Step for PTP over UDP/IP Feature Enable */
+	unsigned int pou_ost_en;
+	/* Tx Timestamp FIFO Depth */
+	unsigned int ttsfd;
+	/* Queue/Channel-Based VLAN tag insertion on Tx */
+	unsigned int cbtisel;
+	/* Supported Parallel Instruction Processor Engines */
+	unsigned int frppipe_num;
+	/* Number of Extended VLAN Tag Filters */
+	unsigned int nrvf_num;
 	/* TSN Features */
 	unsigned int estwid;
 	unsigned int estdep;
 	unsigned int estsel;
 	unsigned int fpesel;
 	unsigned int tbssel;
+	/* Number of DMA channels enabled for TBS */
+	unsigned int tbs_ch_num;
+	/* Per-Stream Filtering Enable */
+	unsigned int sgfsel;
 	/* Numbers of Auxiliary Snapshot Inputs */
 	unsigned int aux_snapshot_n;
 	/* Timestamp System Time Source */
 	unsigned int tssrc;
+	/* Enhanced DMA Enable */
+	unsigned int edma;
+	/* Different Descriptor Cache Enable */
+	unsigned int ediffc;
+	/* VxLAN/NVGRE Enable */
+	unsigned int vxn;
+	/* Debug Memory Interface Enable */
+	unsigned int dbgmem;
+	/* Number of Policing Counters */
+	unsigned int pcsel;
 };
 
 /* RX Buffer size must be multiple of 4/8/16 bytes */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 7f68bef456b7f..7a8f47e7b728b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -122,6 +122,9 @@
 #define XGMAC_TLPIEN			BIT(0)
 #define XGMAC_LPI_TIMER_CTRL		0x000000d4
 #define XGMAC_HW_FEATURE0		0x0000011c
+#define XGMAC_HWFEAT_EDMA		BIT(31)
+#define XGMAC_HWFEAT_EDIFFC		BIT(30)
+#define XGMAC_HWFEAT_VXN		BIT(29)
 #define XGMAC_HWFEAT_SAVLANINS		BIT(27)
 #define XGMAC_HWFEAT_TSSTSSEL		GENMASK(26, 25)
 #define XGMAC_HWFEAT_ADDMACADRSEL	GENMASK(22, 18)
@@ -142,29 +145,47 @@
 #define XGMAC_HW_FEATURE1		0x00000120
 #define XGMAC_HWFEAT_L3L4FNUM		GENMASK(30, 27)
 #define XGMAC_HWFEAT_HASHTBLSZ		GENMASK(25, 24)
+#define XGMAC_HWFEAT_NUMTC		GENMASK(23, 21)
 #define XGMAC_HWFEAT_RSSEN		BIT(20)
+#define XGMAC_HWFEAT_DBGMEMA		BIT(19)
 #define XGMAC_HWFEAT_TSOEN		BIT(18)
 #define XGMAC_HWFEAT_SPHEN		BIT(17)
+#define XGMAC_HWFEAT_DCBEN		BIT(16)
 #define XGMAC_HWFEAT_ADDR64		GENMASK(15, 14)
+#define XGMAC_HWFEAT_ADVTHWORD		BIT(13)
+#define XGMAC_HWFEAT_PTOEN		BIT(12)
+#define XGMAC_HWFEAT_OSTEN		BIT(11)
 #define XGMAC_HWFEAT_TXFIFOSIZE		GENMASK(10, 6)
+#define XGMAC_HWFEAT_PFCEN		BIT(5)
 #define XGMAC_HWFEAT_RXFIFOSIZE		GENMASK(4, 0)
 #define XGMAC_HW_FEATURE2		0x00000124
+#define XGMAC_HWFEAT_AUXSNAPNUM		GENMASK(30, 28)
 #define XGMAC_HWFEAT_PPSOUTNUM		GENMASK(26, 24)
 #define XGMAC_HWFEAT_TXCHCNT		GENMASK(21, 18)
 #define XGMAC_HWFEAT_RXCHCNT		GENMASK(15, 12)
 #define XGMAC_HWFEAT_TXQCNT		GENMASK(9, 6)
 #define XGMAC_HWFEAT_RXQCNT		GENMASK(3, 0)
 #define XGMAC_HW_FEATURE3		0x00000128
+#define XGMAC_HWFEAT_TBSCH		GENMASK(31, 28)
 #define XGMAC_HWFEAT_TBSSEL		BIT(27)
 #define XGMAC_HWFEAT_FPESEL		BIT(26)
+#define XGMAC_HWFEAT_SGFSEL		BIT(25)
 #define XGMAC_HWFEAT_ESTWID		GENMASK(24, 23)
 #define XGMAC_HWFEAT_ESTDEP		GENMASK(22, 20)
 #define XGMAC_HWFEAT_ESTSEL		BIT(19)
+#define XGMAC_HWFEAT_TTSFD		GENMASK(18, 16)
 #define XGMAC_HWFEAT_ASP		GENMASK(15, 14)
 #define XGMAC_HWFEAT_DVLAN		BIT(13)
 #define XGMAC_HWFEAT_FRPES		GENMASK(12, 11)
 #define XGMAC_HWFEAT_FRPPB		GENMASK(10, 9)
+#define XGMAC_HWFEAT_POUOST		BIT(8)
+#define XGMAC_HWFEAT_FRPPIPE		GENMASK(7, 5)
+#define XGMAC_HWFEAT_CBTISEL		BIT(4)
 #define XGMAC_HWFEAT_FRPSEL		BIT(3)
+#define XGMAC_HWFEAT_NRVF		GENMASK(2, 0)
+#define XGMAC_HW_FEATURE4		0x0000012c
+#define XGMAC_HWFEAT_EASP		BIT(4)
+#define XGMAC_HWFEAT_PCSEL		GENMASK(1, 0)
 #define XGMAC_MAC_DPP_FSM_INT_STATUS	0x00000150
 #define XGMAC_MAC_FSM_CONTROL		0x00000158
 #define XGMAC_PRTYEN			BIT(1)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 38782662ff986..34e1b0c3f3461 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -861,8 +861,10 @@ dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
 	value |= XGMAC_TCEIE; /* TSO Memory Correctable Error */
 	writel(value, ioaddr + XGMAC_DMA_ECC_INT_ENABLE);
 
-	/* Only ECC Protection for External Memory feature is selected */
-	if (asp <= 0x1)
+	/* 0x2: Without ECC or Parity Ports on External Application Interface
+	 * 0x4: Only ECC Protection for External Memory feature is selected
+	 */
+	if (asp == 0x2 || asp == 0x4)
 		return 0;
 
 	/* 4. Enable Parity and Timeout for FSM */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 3aacf791efebc..fa69d64a86943 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -393,6 +393,9 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 
 	/* MAC HW feature 0 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE0);
+	dma_cap->edma = (hw_cap & XGMAC_HWFEAT_EDMA) >> 31;
+	dma_cap->ediffc = (hw_cap & XGMAC_HWFEAT_EDIFFC) >> 30;
+	dma_cap->vxn = (hw_cap & XGMAC_HWFEAT_VXN) >> 29;
 	dma_cap->vlins = (hw_cap & XGMAC_HWFEAT_SAVLANINS) >> 27;
 	dma_cap->tssrc = (hw_cap & XGMAC_HWFEAT_TSSTSSEL) >> 25;
 	dma_cap->multi_addr = (hw_cap & XGMAC_HWFEAT_ADDMACADRSEL) >> 18;
@@ -425,9 +428,12 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 		dma_cap->l3l4fnum = 32;
 
 	dma_cap->hash_tb_sz = (hw_cap & XGMAC_HWFEAT_HASHTBLSZ) >> 24;
+	dma_cap->numtc = ((hw_cap & XGMAC_HWFEAT_NUMTC) >> 21) + 1;
 	dma_cap->rssen = (hw_cap & XGMAC_HWFEAT_RSSEN) >> 20;
+	dma_cap->dbgmem = (hw_cap & XGMAC_HWFEAT_DBGMEMA) >> 19;
 	dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18;
 	dma_cap->sphen = (hw_cap & XGMAC_HWFEAT_SPHEN) >> 17;
+	dma_cap->dcben = (hw_cap & XGMAC_HWFEAT_DCBEN) >> 16;
 
 	dma_cap->addr64 = (hw_cap & XGMAC_HWFEAT_ADDR64) >> 14;
 	switch (dma_cap->addr64) {
@@ -445,13 +451,18 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 		break;
 	}
 
+	dma_cap->advthword = (hw_cap & XGMAC_HWFEAT_ADVTHWORD) >> 13;
+	dma_cap->ptoen = (hw_cap & XGMAC_HWFEAT_PTOEN) >> 12;
+	dma_cap->osten = (hw_cap & XGMAC_HWFEAT_OSTEN) >> 11;
 	dma_cap->tx_fifo_size =
 		128 << ((hw_cap & XGMAC_HWFEAT_TXFIFOSIZE) >> 6);
+	dma_cap->pfcen = (hw_cap & XGMAC_HWFEAT_PFCEN) >> 5;
 	dma_cap->rx_fifo_size =
 		128 << ((hw_cap & XGMAC_HWFEAT_RXFIFOSIZE) >> 0);
 
 	/* MAC HW feature 2 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE2);
+	dma_cap->aux_snapshot_n = (hw_cap & XGMAC_HWFEAT_AUXSNAPNUM) >> 28;
 	dma_cap->pps_out_num = (hw_cap & XGMAC_HWFEAT_PPSOUTNUM) >> 24;
 	dma_cap->number_tx_channel =
 		((hw_cap & XGMAC_HWFEAT_TXCHCNT) >> 18) + 1;
@@ -464,16 +475,28 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 
 	/* MAC HW feature 3 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE3);
+	dma_cap->tbs_ch_num = ((hw_cap & XGMAC_HWFEAT_TBSCH) >> 28) + 1;
 	dma_cap->tbssel = (hw_cap & XGMAC_HWFEAT_TBSSEL) >> 27;
 	dma_cap->fpesel = (hw_cap & XGMAC_HWFEAT_FPESEL) >> 26;
+	dma_cap->sgfsel = (hw_cap & XGMAC_HWFEAT_SGFSEL) >> 25;
 	dma_cap->estwid = (hw_cap & XGMAC_HWFEAT_ESTWID) >> 23;
 	dma_cap->estdep = (hw_cap & XGMAC_HWFEAT_ESTDEP) >> 20;
 	dma_cap->estsel = (hw_cap & XGMAC_HWFEAT_ESTSEL) >> 19;
+	dma_cap->ttsfd = (hw_cap & XGMAC_HWFEAT_TTSFD) >> 16;
 	dma_cap->asp = (hw_cap & XGMAC_HWFEAT_ASP) >> 14;
 	dma_cap->dvlan = (hw_cap & XGMAC_HWFEAT_DVLAN) >> 13;
 	dma_cap->frpes = (hw_cap & XGMAC_HWFEAT_FRPES) >> 11;
 	dma_cap->frpbs = (hw_cap & XGMAC_HWFEAT_FRPPB) >> 9;
+	dma_cap->pou_ost_en = (hw_cap & XGMAC_HWFEAT_POUOST) >> 8;
+	dma_cap->frppipe_num = ((hw_cap & XGMAC_HWFEAT_FRPPIPE) >> 5) + 1;
+	dma_cap->cbtisel = (hw_cap & XGMAC_HWFEAT_CBTISEL) >> 4;
 	dma_cap->frpsel = (hw_cap & XGMAC_HWFEAT_FRPSEL) >> 3;
+	dma_cap->nrvf_num = (hw_cap & XGMAC_HWFEAT_NRVF) >> 0;
+
+	/* MAC HW feature 4 */
+	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE4);
+	dma_cap->asp |= (hw_cap & XGMAC_HWFEAT_EASP) >> 2;
+	dma_cap->pcsel = (hw_cap & XGMAC_HWFEAT_PCSEL) >> 0;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 733b5e9008173..7a9bbcf03ea51 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6243,6 +6243,16 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 		"External",
 		"Both",
 	};
+	static const char * const dwxgmac_safety_feature_desc[] = {
+		"No",
+		"All Safety Features with ECC and Parity",
+		"All Safety Features without ECC or Parity",
+		"All Safety Features with Parity Only",
+		"ECC Only",
+		"UNDEFINED",
+		"UNDEFINED",
+		"UNDEFINED",
+	};
 	struct net_device *dev = seq->private;
 	struct stmmac_priv *priv = netdev_priv(dev);
 
@@ -6261,15 +6271,16 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 		   (priv->dma_cap.mbps_1000) ? "Y" : "N");
 	seq_printf(seq, "\tHalf duplex: %s\n",
 		   (priv->dma_cap.half_duplex) ? "Y" : "N");
-	seq_printf(seq, "\tHash Filter: %s\n",
-		   (priv->dma_cap.hash_filter) ? "Y" : "N");
-	if (priv->plat->has_xgmac)
+	if (priv->plat->has_xgmac) {
 		seq_printf(seq,
 			   "\tNumber of Additional MAC address registers: %d\n",
 			   priv->dma_cap.multi_addr);
-	else
+	} else {
+		seq_printf(seq, "\tHash Filter: %s\n",
+			   (priv->dma_cap.hash_filter) ? "Y" : "N");
 		seq_printf(seq, "\tMultiple MAC address registers: %s\n",
 			   (priv->dma_cap.multi_addr) ? "Y" : "N");
+	}
 	seq_printf(seq, "\tPCS (TBI/SGMII/RTBI PHY interfaces): %s\n",
 		   (priv->dma_cap.pcs) ? "Y" : "N");
 	seq_printf(seq, "\tSMA (MDIO) Interface: %s\n",
@@ -6316,12 +6327,13 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 		   (priv->dma_cap.enh_desc) ? "Y" : "N");
 	seq_printf(seq, "\tTX Fifo Size: %d\n", priv->dma_cap.tx_fifo_size);
 	seq_printf(seq, "\tRX Fifo Size: %d\n", priv->dma_cap.rx_fifo_size);
-	seq_printf(seq, "\tHash Table Size: %d\n", priv->dma_cap.hash_tb_sz);
+	seq_printf(seq, "\tHash Table Size: %lu\n", priv->dma_cap.hash_tb_sz ?
+		   (BIT(priv->dma_cap.hash_tb_sz) << 5) : 0);
 	seq_printf(seq, "\tTSO: %s\n", priv->dma_cap.tsoen ? "Y" : "N");
 	seq_printf(seq, "\tNumber of PPS Outputs: %d\n",
 		   priv->dma_cap.pps_out_num);
 	seq_printf(seq, "\tSafety Features: %s\n",
-		   priv->dma_cap.asp ? "Y" : "N");
+		   dwxgmac_safety_feature_desc[priv->dma_cap.asp]);
 	seq_printf(seq, "\tFlexible RX Parser: %s\n",
 		   priv->dma_cap.frpsel ? "Y" : "N");
 	seq_printf(seq, "\tEnhanced Addressing: %d\n",
@@ -6346,6 +6358,53 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 		   priv->dma_cap.fpesel ? "Y" : "N");
 	seq_printf(seq, "\tTime-Based Scheduling (TBS): %s\n",
 		   priv->dma_cap.tbssel ? "Y" : "N");
+	seq_printf(seq, "\tNumber of DMA Channels Enabled for TBS: %d\n",
+		   priv->dma_cap.tbs_ch_num);
+	seq_printf(seq, "\tPer-Stream Filtering: %s\n",
+		   priv->dma_cap.sgfsel ? "Y" : "N");
+	seq_printf(seq, "\tTX Timestamp FIFO Depth: %lu\n",
+		   BIT(priv->dma_cap.ttsfd) >> 1);
+	seq_printf(seq, "\tNumber of Traffic Classes: %d\n",
+		   priv->dma_cap.numtc);
+	seq_printf(seq, "\tDCB Feature: %s\n",
+		   priv->dma_cap.dcben ? "Y" : "N");
+	seq_printf(seq, "\tIEEE 1588 High Word Register: %s\n",
+		   priv->dma_cap.advthword ? "Y" : "N");
+	seq_printf(seq, "\tPTP Offload: %s\n",
+		   priv->dma_cap.ptoen ? "Y" : "N");
+	seq_printf(seq, "\tOne-Step Timestamping: %s\n",
+		   priv->dma_cap.osten ? "Y" : "N");
+	seq_printf(seq, "\tPriority-Based Flow Control: %s\n",
+		   priv->dma_cap.pfcen ? "Y" : "N");
+	seq_printf(seq, "\tNumber of Flexible RX Parser Instructions: %lu\n",
+		   BIT(priv->dma_cap.frpes) << 6);
+	seq_printf(seq, "\tNumber of Flexible RX Parser Parsable Bytes: %lu\n",
+		   BIT(priv->dma_cap.frpbs) << 6);
+	seq_printf(seq, "\tParallel Instruction Processor Engines: %d\n",
+		   priv->dma_cap.frppipe_num);
+	seq_printf(seq, "\tNumber of Extended VLAN Tag Filters: %lu\n",
+		   priv->dma_cap.nrvf_num ?
+		   (BIT(priv->dma_cap.nrvf_num) << 1) : 0);
+	seq_printf(seq, "\tWidth of the Time Interval Field in GCL: %d\n",
+		   priv->dma_cap.estwid ? 4 * priv->dma_cap.estwid + 12 : 0);
+	seq_printf(seq, "\tDepth of GCL: %lu\n",
+		   priv->dma_cap.estdep ? (BIT(priv->dma_cap.estdep) << 5) : 0);
+	seq_printf(seq, "\tQueue/Channel-Based VLAN Tag Insertion on TX: %s\n",
+		   priv->dma_cap.cbtisel ? "Y" : "N");
+	seq_printf(seq, "\tNumber of Auxiliary Snapshot Inputs: %d\n",
+		   priv->dma_cap.aux_snapshot_n);
+	seq_printf(seq, "\tOne-Step Timestamping for PTP over UDP/IP: %s\n",
+		   priv->dma_cap.pou_ost_en ? "Y" : "N");
+	seq_printf(seq, "\tEnhanced DMA: %s\n",
+		   priv->dma_cap.edma ? "Y" : "N");
+	seq_printf(seq, "\tDifferent Descriptor Cache: %s\n",
+		   priv->dma_cap.ediffc ? "Y" : "N");
+	seq_printf(seq, "\tVxLAN/NVGRE: %s\n",
+		   priv->dma_cap.vxn ? "Y" : "N");
+	seq_printf(seq, "\tDebug Memory Interface: %s\n",
+		   priv->dma_cap.dbgmem ? "Y" : "N");
+	seq_printf(seq, "\tNumber of Policing Counters: %lu\n",
+		   priv->dma_cap.pcsel ? BIT(priv->dma_cap.pcsel + 3) : 0);
 	return 0;
 }
 DEFINE_SHOW_ATTRIBUTE(stmmac_dma_cap);
-- 
GitLab


From b4672c733713f3bc9029c83efa7a2f1ef42ddf5b Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 18 Aug 2023 16:25:23 +0800
Subject: [PATCH 1382/1806] IPv4: add extack info for IPv4 address add/delete

Add extack info for IPv4 address add/delete, which would be useful for
users to understand the problem without having to read kernel code.

No extack message for the ifa_local checking in __inet_insert_ifa() as
it has been checked in find_matching_ifa().

Suggested-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 5deac0517ef70..c3658b8755bca 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -509,6 +509,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 				return -EEXIST;
 			}
 			if (ifa1->ifa_scope != ifa->ifa_scope) {
+				NL_SET_ERR_MSG(extack, "ipv4: Invalid scope value");
 				inet_free_ifa(ifa);
 				return -EINVAL;
 			}
@@ -664,6 +665,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	ifm = nlmsg_data(nlh);
 	in_dev = inetdev_by_index(net, ifm->ifa_index);
 	if (!in_dev) {
+		NL_SET_ERR_MSG(extack, "ipv4: Device not found");
 		err = -ENODEV;
 		goto errout;
 	}
@@ -688,6 +690,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return 0;
 	}
 
+	NL_SET_ERR_MSG(extack, "ipv4: Address not found");
 	err = -EADDRNOTAVAIL;
 errout:
 	return err;
@@ -839,13 +842,23 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 
 	ifm = nlmsg_data(nlh);
 	err = -EINVAL;
-	if (ifm->ifa_prefixlen > 32 || !tb[IFA_LOCAL])
+
+	if (ifm->ifa_prefixlen > 32) {
+		NL_SET_ERR_MSG(extack, "ipv4: Invalid prefix length");
+		goto errout;
+	}
+
+	if (!tb[IFA_LOCAL]) {
+		NL_SET_ERR_MSG(extack, "ipv4: Local address is not supplied");
 		goto errout;
+	}
 
 	dev = __dev_get_by_index(net, ifm->ifa_index);
 	err = -ENODEV;
-	if (!dev)
+	if (!dev) {
+		NL_SET_ERR_MSG(extack, "ipv4: Device not found");
 		goto errout;
+	}
 
 	in_dev = __in_dev_get_rtnl(dev);
 	err = -ENOBUFS;
@@ -897,6 +910,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 
 		ci = nla_data(tb[IFA_CACHEINFO]);
 		if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) {
+			NL_SET_ERR_MSG(extack, "ipv4: address lifetime invalid");
 			err = -EINVAL;
 			goto errout_free;
 		}
@@ -954,6 +968,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 			int ret = ip_mc_autojoin_config(net, true, ifa);
 
 			if (ret < 0) {
+				NL_SET_ERR_MSG(extack, "ipv4: Multicast auto join failed");
 				inet_free_ifa(ifa);
 				return ret;
 			}
@@ -967,8 +982,10 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		inet_free_ifa(ifa);
 
 		if (nlh->nlmsg_flags & NLM_F_EXCL ||
-		    !(nlh->nlmsg_flags & NLM_F_REPLACE))
+		    !(nlh->nlmsg_flags & NLM_F_REPLACE)) {
+			NL_SET_ERR_MSG(extack, "ipv4: Address already assigned");
 			return -EEXIST;
+		}
 		ifa = ifa_existing;
 
 		if (ifa->ifa_rt_priority != new_metric) {
-- 
GitLab


From bc1fb82ae11753c5dec53c667a055dc37796dbd2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 19 Aug 2023 04:06:46 +0000
Subject: [PATCH 1383/1806] net: annotate data-races around sk->sk_lingertime

sk_getsockopt() runs locklessly. This means sk->sk_lingertime
can be read while other threads are changing its value.

Other reads also happen without socket lock being held,
and must be annotated.

Remove preprocessor logic using BITS_PER_LONG, compilers
are smart enough to figure this by themselves.

v2: fixed a clang W=1 (-Wtautological-constant-out-of-range-compare) warning
    (Jakub)

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bluetooth/iso.c |  2 +-
 net/bluetooth/sco.c |  2 +-
 net/core/sock.c     | 18 +++++++++---------
 net/sched/em_meta.c |  2 +-
 net/smc/af_smc.c    |  2 +-
 5 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 6b66d6a88b9a2..3c03e49422c75 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1475,7 +1475,7 @@ static int iso_sock_release(struct socket *sock)
 
 	iso_sock_close(sk);
 
-	if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+	if (sock_flag(sk, SOCK_LINGER) && READ_ONCE(sk->sk_lingertime) &&
 	    !(current->flags & PF_EXITING)) {
 		lock_sock(sk);
 		err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 50ad5935ae47a..c736186aba26b 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1245,7 +1245,7 @@ static int sco_sock_release(struct socket *sock)
 
 	sco_sock_close(sk);
 
-	if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+	if (sock_flag(sk, SOCK_LINGER) && READ_ONCE(sk->sk_lingertime) &&
 	    !(current->flags & PF_EXITING)) {
 		lock_sock(sk);
 		err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
diff --git a/net/core/sock.c b/net/core/sock.c
index a0722954e4a8f..666a17cab4f56 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -797,7 +797,7 @@ EXPORT_SYMBOL(sock_set_reuseport);
 void sock_no_linger(struct sock *sk)
 {
 	lock_sock(sk);
-	sk->sk_lingertime = 0;
+	WRITE_ONCE(sk->sk_lingertime, 0);
 	sock_set_flag(sk, SOCK_LINGER);
 	release_sock(sk);
 }
@@ -1230,15 +1230,15 @@ set_sndbuf:
 			ret = -EFAULT;
 			break;
 		}
-		if (!ling.l_onoff)
+		if (!ling.l_onoff) {
 			sock_reset_flag(sk, SOCK_LINGER);
-		else {
-#if (BITS_PER_LONG == 32)
-			if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
-				sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
+		} else {
+			unsigned long t_sec = ling.l_linger;
+
+			if (t_sec >= MAX_SCHEDULE_TIMEOUT / HZ)
+				WRITE_ONCE(sk->sk_lingertime, MAX_SCHEDULE_TIMEOUT);
 			else
-#endif
-				sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
+				WRITE_ONCE(sk->sk_lingertime, t_sec * HZ);
 			sock_set_flag(sk, SOCK_LINGER);
 		}
 		break;
@@ -1692,7 +1692,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 	case SO_LINGER:
 		lv		= sizeof(v.ling);
 		v.ling.l_onoff	= sock_flag(sk, SOCK_LINGER);
-		v.ling.l_linger	= sk->sk_lingertime / HZ;
+		v.ling.l_linger	= READ_ONCE(sk->sk_lingertime) / HZ;
 		break;
 
 	case SO_BSDCOMPAT:
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 6fdba069f6bfd..da34fd4c92695 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -502,7 +502,7 @@ META_COLLECTOR(int_sk_lingertime)
 		*err = -1;
 		return;
 	}
-	dst->value = sk->sk_lingertime / HZ;
+	dst->value = READ_ONCE(sk->sk_lingertime) / HZ;
 }
 
 META_COLLECTOR(int_sk_err_qlen)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index c4f664fb2bcbd..bacdd971615e4 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1840,7 +1840,7 @@ void smc_close_non_accepted(struct sock *sk)
 	lock_sock(sk);
 	if (!sk->sk_lingertime)
 		/* wait for peer closing */
-		sk->sk_lingertime = SMC_MAX_STREAM_WAIT_TIMEOUT;
+		WRITE_ONCE(sk->sk_lingertime, SMC_MAX_STREAM_WAIT_TIMEOUT);
 	__smc_release(smc);
 	release_sock(sk);
 	sock_put(sk); /* sock_hold above */
-- 
GitLab


From cb39c35783f26892bb1a72b1115c94fa2e77f4c5 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Mon, 21 Aug 2023 09:55:37 +0800
Subject: [PATCH 1384/1806] pds_core: Fix some kernel-doc comments

Fix some kernel-doc comments to silence the warnings:

drivers/net/ethernet/amd/pds_core/auxbus.c:18: warning: Function parameter or member 'pf' not described in 'pds_client_register'
drivers/net/ethernet/amd/pds_core/auxbus.c:18: warning: Excess function parameter 'pf_pdev' description in 'pds_client_register'
drivers/net/ethernet/amd/pds_core/auxbus.c:58: warning: Function parameter or member 'pf' not described in 'pds_client_unregister'
drivers/net/ethernet/amd/pds_core/auxbus.c:58: warning: Excess function parameter 'pf_pdev' description in 'pds_client_unregister'

Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/pds_core/auxbus.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index 6787a5fae908e..f46efebaaea95 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -8,7 +8,7 @@
 
 /**
  * pds_client_register - Link the client to the firmware
- * @pf_pdev:	ptr to the PF driver struct
+ * @pf:	a pointer to the pdsc structure
  * @devname:	name that includes service into, e.g. pds_core.vDPA
  *
  * Return: positive client ID (ci) on success, or
@@ -53,7 +53,7 @@ EXPORT_SYMBOL_GPL(pds_client_register);
 
 /**
  * pds_client_unregister - Unlink the client from the firmware
- * @pf_pdev:	ptr to the PF driver struct
+ * @pf:	a pointer to the pdsc structure
  * @client_id:	id returned from pds_client_register()
  *
  * Return: 0 on success, or
-- 
GitLab


From 9c8fd72a5c2a031cbc680a2990107ecd958ffcdb Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 2 Aug 2023 19:07:15 +0300
Subject: [PATCH 1385/1806] wifi: mwifiex: fix memory leak in
 mwifiex_histogram_read()

Always free the zeroed page on return from 'mwifiex_histogram_read()'.

Fixes: cbf6e05527a7 ("mwifiex: add rx histogram statistics support")

Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230802160726.85545-1-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/debugfs.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c
index 52b18f4a774b7..0cdd6c50c1c08 100644
--- a/drivers/net/wireless/marvell/mwifiex/debugfs.c
+++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c
@@ -253,8 +253,11 @@ mwifiex_histogram_read(struct file *file, char __user *ubuf,
 	if (!p)
 		return -ENOMEM;
 
-	if (!priv || !priv->hist_data)
-		return -EFAULT;
+	if (!priv || !priv->hist_data) {
+		ret = -EFAULT;
+		goto free_and_exit;
+	}
+
 	phist_data = priv->hist_data;
 
 	p += sprintf(p, "\n"
@@ -309,6 +312,8 @@ mwifiex_histogram_read(struct file *file, char __user *ubuf,
 	ret = simple_read_from_buffer(ubuf, count, ppos, (char *)page,
 				      (unsigned long)p - page);
 
+free_and_exit:
+	free_page(page);
 	return ret;
 }
 
-- 
GitLab


From 9b1cd8266f350c4e8453361c6e183e6174d63e4b Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 2 Aug 2023 19:07:16 +0300
Subject: [PATCH 1386/1806] wifi: mwifiex: cleanup private data structures

Drop unused fields 'status_code' of 'struct mwifiex_txinfo',
'dfs_chan_switch_timer', 'sleep_params' (including related data
type 'struct mwifiex_sleep_params') of 'struct mwifiex_adapter',
adjust related code.

Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230802160726.85545-2-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/decl.h     |  1 -
 drivers/net/wireless/marvell/mwifiex/init.c     |  1 -
 drivers/net/wireless/marvell/mwifiex/main.h     | 11 -----------
 drivers/net/wireless/marvell/mwifiex/sta_tx.c   |  1 -
 drivers/net/wireless/marvell/mwifiex/uap_txrx.c |  1 -
 5 files changed, 15 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/decl.h b/drivers/net/wireless/marvell/mwifiex/decl.h
index 88648c062713c..326ffb05d7913 100644
--- a/drivers/net/wireless/marvell/mwifiex/decl.h
+++ b/drivers/net/wireless/marvell/mwifiex/decl.h
@@ -180,7 +180,6 @@ struct mwifiex_rxinfo {
 };
 
 struct mwifiex_txinfo {
-	u32 status_code;
 	u8 flags;
 	u8 bss_num;
 	u8 bss_type;
diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c
index 7dddb4b5dea1d..86293be782a25 100644
--- a/drivers/net/wireless/marvell/mwifiex/init.c
+++ b/drivers/net/wireless/marvell/mwifiex/init.c
@@ -282,7 +282,6 @@ static void mwifiex_init_adapter(struct mwifiex_adapter *adapter)
 	sleep_cfm_buf->action = cpu_to_le16(SLEEP_CONFIRM);
 	sleep_cfm_buf->resp_ctrl = cpu_to_le16(RESP_NEEDED);
 
-	memset(&adapter->sleep_params, 0, sizeof(adapter->sleep_params));
 	memset(&adapter->sleep_period, 0, sizeof(adapter->sleep_period));
 	adapter->tx_lock_flag = false;
 	adapter->null_pkt_interval = 0;
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index b95886e1413ee..7421e9bf8650e 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -444,15 +444,6 @@ struct mwifiex_current_bss_params {
 	u8 data_rates[MWIFIEX_SUPPORTED_RATES];
 };
 
-struct mwifiex_sleep_params {
-	u16 sp_error;
-	u16 sp_offset;
-	u16 sp_stable_time;
-	u8 sp_cal_control;
-	u8 sp_ext_sleep_clk;
-	u16 sp_reserved;
-};
-
 struct mwifiex_sleep_period {
 	u16 period;
 	u16 reserved;
@@ -681,7 +672,6 @@ struct mwifiex_private {
 	struct cfg80211_chan_def dfs_chandef;
 	struct workqueue_struct *dfs_cac_workqueue;
 	struct delayed_work dfs_cac_work;
-	struct timer_list dfs_chan_switch_timer;
 	struct workqueue_struct *dfs_chan_sw_workqueue;
 	struct delayed_work dfs_chan_sw_work;
 	struct cfg80211_beacon_data beacon_after;
@@ -955,7 +945,6 @@ struct mwifiex_adapter {
 	u8 config_bands;
 	struct mwifiex_chan_scan_param_set *scan_channels;
 	u8 tx_lock_flag;
-	struct mwifiex_sleep_params sleep_params;
 	struct mwifiex_sleep_period sleep_period;
 	u16 ps_mode;
 	u32 ps_state;
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_tx.c b/drivers/net/wireless/marvell/mwifiex/sta_tx.c
index 13c0e67ededfc..d27b6e6493f30 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_tx.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_tx.c
@@ -42,7 +42,6 @@ void *mwifiex_process_sta_txpd(struct mwifiex_private *priv,
 	if (!skb->len) {
 		mwifiex_dbg(adapter, ERROR,
 			    "Tx: bad packet length: %d\n", skb->len);
-		tx_info->status_code = -1;
 		return skb->data;
 	}
 
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
index 04ff051f5d186..360d36ceeb1d3 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
@@ -474,7 +474,6 @@ void *mwifiex_process_uap_txpd(struct mwifiex_private *priv,
 	if (!skb->len) {
 		mwifiex_dbg(adapter, ERROR,
 			    "Tx: bad packet length: %d\n", skb->len);
-		tx_info->status_code = -1;
 		return skb->data;
 	}
 
-- 
GitLab


From 968d02c61311221deb881634d15f191effa1ab22 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 2 Aug 2023 19:07:17 +0300
Subject: [PATCH 1387/1806] wifi: mwifiex: handle possible sscanf() errors

Return -EINVAL on possible 'sscanf()' errors in
'mwifiex_regrdwr_write()' and 'mwifiex_rdeeprom_write()'.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230802160726.85545-3-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/debugfs.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c
index 0cdd6c50c1c08..f9c9fec7c792a 100644
--- a/drivers/net/wireless/marvell/mwifiex/debugfs.c
+++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c
@@ -425,7 +425,10 @@ mwifiex_regrdwr_write(struct file *file,
 	if (IS_ERR(buf))
 		return PTR_ERR(buf);
 
-	sscanf(buf, "%u %x %x", &reg_type, &reg_offset, &reg_value);
+	if (sscanf(buf, "%u %x %x", &reg_type, &reg_offset, &reg_value) != 3) {
+		ret = -EINVAL;
+		goto done;
+	}
 
 	if (reg_type == 0 || reg_offset == 0) {
 		ret = -EINVAL;
@@ -691,7 +694,10 @@ mwifiex_rdeeprom_write(struct file *file,
 	if (IS_ERR(buf))
 		return PTR_ERR(buf);
 
-	sscanf(buf, "%d %d", &offset, &bytes);
+	if (sscanf(buf, "%d %d", &offset, &bytes) != 2) {
+		ret = -EINVAL;
+		goto done;
+	}
 
 	if (offset == -1 || bytes == -1) {
 		ret = -EINVAL;
-- 
GitLab


From a6b3a0169ade026b257be58f9295f5eec7edd359 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 2 Aug 2023 19:07:18 +0300
Subject: [PATCH 1388/1806] wifi: mwifiex: handle possible mwifiex_write_reg()
 errors

Return -1 on possible 'mwifiex_write_reg()' errors in
'mwifiex_init_sdio_ioport()', do not ignore the value
returned by the latter in 'mwifiex_init_sdio()' and
'mwifiex_sdio_up_dev()' as well.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230802160726.85545-4-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/sdio.c | 22 +++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index a24bd40dd41ab..0d60484cd5df4 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -1083,17 +1083,17 @@ cont:
 		    "info: SDIO FUNC1 IO port: %#x\n", adapter->ioport);
 
 	/* Set Host interrupt reset to read to clear */
-	if (!mwifiex_read_reg(adapter, card->reg->host_int_rsr_reg, &reg))
-		mwifiex_write_reg(adapter, card->reg->host_int_rsr_reg,
-				  reg | card->reg->sdio_int_mask);
-	else
+	if (mwifiex_read_reg(adapter, card->reg->host_int_rsr_reg, &reg))
+		return -1;
+	if (mwifiex_write_reg(adapter, card->reg->host_int_rsr_reg,
+			      reg | card->reg->sdio_int_mask))
 		return -1;
 
 	/* Dnld/Upld ready set to auto reset */
-	if (!mwifiex_read_reg(adapter, card->reg->card_misc_cfg_reg, &reg))
-		mwifiex_write_reg(adapter, card->reg->card_misc_cfg_reg,
-				  reg | AUTO_RE_ENABLE_INT);
-	else
+	if (mwifiex_read_reg(adapter, card->reg->card_misc_cfg_reg, &reg))
+		return -1;
+	if (mwifiex_write_reg(adapter, card->reg->card_misc_cfg_reg,
+			      reg | AUTO_RE_ENABLE_INT))
 		return -1;
 
 	return 0;
@@ -2525,7 +2525,8 @@ static int mwifiex_init_sdio(struct mwifiex_adapter *adapter)
 	mwifiex_read_reg(adapter, card->reg->host_int_status_reg, &sdio_ireg);
 
 	/* Get SDIO ioport */
-	mwifiex_init_sdio_ioport(adapter);
+	if (mwifiex_init_sdio_ioport(adapter))
+		return -EIO;
 
 	/* Initialize SDIO variables in card */
 	card->mp_rd_bitmap = 0;
@@ -3141,7 +3142,8 @@ static void mwifiex_sdio_up_dev(struct mwifiex_adapter *adapter)
 	 */
 	mwifiex_read_reg(adapter, card->reg->host_int_status_reg, &sdio_ireg);
 
-	mwifiex_init_sdio_ioport(adapter);
+	if (mwifiex_init_sdio_ioport(adapter))
+		dev_err(&card->func->dev, "error enabling SDIO port\n");
 }
 
 static struct mwifiex_if_ops sdio_ops = {
-- 
GitLab


From 359838758ceaabeadec2aab7a4ae1c8c89372c21 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 2 Aug 2023 19:07:19 +0300
Subject: [PATCH 1389/1806] wifi: mwifiex: drop BUG_ON from TX paths

In 'mwifiex_process_sta_txpd()' and 'mwifiex_process_uap_txpd()',
replace 'BUG_ON()' with runtime check, and move all these checks
to 'mwifiex_process_tx()'. This way, both callees may be converted
to 'void', and the caller may be simplified as well.

Suggested-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230802160726.85545-5-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/main.h   |  6 ++-
 drivers/net/wireless/marvell/mwifiex/sta_tx.c | 14 +-----
 drivers/net/wireless/marvell/mwifiex/txrx.c   | 44 +++++++++++--------
 .../net/wireless/marvell/mwifiex/uap_txrx.c   | 14 +-----
 4 files changed, 34 insertions(+), 44 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 7421e9bf8650e..97e7c835d729e 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -1144,8 +1144,10 @@ int mwifiex_process_uap_event(struct mwifiex_private *);
 void mwifiex_delete_all_station_list(struct mwifiex_private *priv);
 void mwifiex_wmm_del_peer_ra_list(struct mwifiex_private *priv,
 				  const u8 *ra_addr);
-void *mwifiex_process_sta_txpd(struct mwifiex_private *, struct sk_buff *skb);
-void *mwifiex_process_uap_txpd(struct mwifiex_private *, struct sk_buff *skb);
+void mwifiex_process_sta_txpd(struct mwifiex_private *priv,
+			      struct sk_buff *skb);
+void mwifiex_process_uap_txpd(struct mwifiex_private *priv,
+			      struct sk_buff *skb);
 int mwifiex_sta_init_cmd(struct mwifiex_private *, u8 first_sta, bool init);
 int mwifiex_cmd_802_11_scan(struct host_cmd_ds_command *cmd,
 			    struct mwifiex_scan_cmd_config *scan_cfg);
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_tx.c b/drivers/net/wireless/marvell/mwifiex/sta_tx.c
index d27b6e6493f30..70c2790b8e351 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_tx.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_tx.c
@@ -29,8 +29,8 @@
  *      - Priority specific Tx control
  *      - Flags
  */
-void *mwifiex_process_sta_txpd(struct mwifiex_private *priv,
-				struct sk_buff *skb)
+void mwifiex_process_sta_txpd(struct mwifiex_private *priv,
+			      struct sk_buff *skb)
 {
 	struct mwifiex_adapter *adapter = priv->adapter;
 	struct txpd *local_tx_pd;
@@ -39,14 +39,6 @@ void *mwifiex_process_sta_txpd(struct mwifiex_private *priv,
 	u16 pkt_type, pkt_offset;
 	int hroom = adapter->intf_hdr_len;
 
-	if (!skb->len) {
-		mwifiex_dbg(adapter, ERROR,
-			    "Tx: bad packet length: %d\n", skb->len);
-		return skb->data;
-	}
-
-	BUG_ON(skb_headroom(skb) < MWIFIEX_MIN_DATA_HEADER_LEN);
-
 	pkt_type = mwifiex_is_skb_mgmt_frame(skb) ? PKT_TYPE_MGMT : 0;
 
 	pad = ((uintptr_t)skb->data - (sizeof(*local_tx_pd) + hroom)) &
@@ -108,8 +100,6 @@ void *mwifiex_process_sta_txpd(struct mwifiex_private *priv,
 	if (!local_tx_pd->tx_control)
 		/* TxCtrl set by user or default */
 		local_tx_pd->tx_control = cpu_to_le32(priv->pkt_tx_ctrl);
-
-	return skb->data;
 }
 
 /*
diff --git a/drivers/net/wireless/marvell/mwifiex/txrx.c b/drivers/net/wireless/marvell/mwifiex/txrx.c
index 54c204608dab9..bd91678d26b49 100644
--- a/drivers/net/wireless/marvell/mwifiex/txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/txrx.c
@@ -72,13 +72,18 @@ EXPORT_SYMBOL_GPL(mwifiex_handle_rx_packet);
 int mwifiex_process_tx(struct mwifiex_private *priv, struct sk_buff *skb,
 		       struct mwifiex_tx_param *tx_param)
 {
-	int hroom, ret = -1;
+	int hroom, ret;
 	struct mwifiex_adapter *adapter = priv->adapter;
-	u8 *head_ptr;
 	struct txpd *local_tx_pd = NULL;
 	struct mwifiex_sta_node *dest_node;
 	struct ethhdr *hdr = (void *)skb->data;
 
+	if (unlikely(!skb->len ||
+		     skb_headroom(skb) < MWIFIEX_MIN_DATA_HEADER_LEN)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	hroom = adapter->intf_hdr_len;
 
 	if (priv->bss_role == MWIFIEX_BSS_ROLE_UAP) {
@@ -88,33 +93,31 @@ int mwifiex_process_tx(struct mwifiex_private *priv, struct sk_buff *skb,
 			dest_node->stats.tx_packets++;
 		}
 
-		head_ptr = mwifiex_process_uap_txpd(priv, skb);
+		mwifiex_process_uap_txpd(priv, skb);
 	} else {
-		head_ptr = mwifiex_process_sta_txpd(priv, skb);
+		mwifiex_process_sta_txpd(priv, skb);
 	}
 
-	if ((adapter->data_sent || adapter->tx_lock_flag) && head_ptr) {
+	if (adapter->data_sent || adapter->tx_lock_flag) {
 		skb_queue_tail(&adapter->tx_data_q, skb);
 		atomic_inc(&adapter->tx_queued);
 		return 0;
 	}
 
-	if (head_ptr) {
-		if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA)
-			local_tx_pd = (struct txpd *)(head_ptr + hroom);
-		if (adapter->iface_type == MWIFIEX_USB) {
-			ret = adapter->if_ops.host_to_card(adapter,
-							   priv->usb_port,
-							   skb, tx_param);
-		} else {
-			ret = adapter->if_ops.host_to_card(adapter,
-							   MWIFIEX_TYPE_DATA,
-							   skb, tx_param);
-		}
+	if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA)
+		local_tx_pd = (struct txpd *)(skb->data + hroom);
+	if (adapter->iface_type == MWIFIEX_USB) {
+		ret = adapter->if_ops.host_to_card(adapter,
+						   priv->usb_port,
+						   skb, tx_param);
+	} else {
+		ret = adapter->if_ops.host_to_card(adapter,
+						   MWIFIEX_TYPE_DATA,
+						   skb, tx_param);
 	}
 	mwifiex_dbg_dump(adapter, DAT_D, "tx pkt:", skb->data,
 			 min_t(size_t, skb->len, DEBUG_DUMP_DATA_MAX_LEN));
-
+out:
 	switch (ret) {
 	case -ENOSR:
 		mwifiex_dbg(adapter, DATA, "data: -ENOSR is returned\n");
@@ -137,6 +140,11 @@ int mwifiex_process_tx(struct mwifiex_private *priv, struct sk_buff *skb,
 		break;
 	case -EINPROGRESS:
 		break;
+	case -EINVAL:
+		mwifiex_dbg(adapter, ERROR,
+			    "malformed skb (length: %u, headroom: %u)\n",
+			    skb->len, skb_headroom(skb));
+		fallthrough;
 	case 0:
 		mwifiex_write_data_complete(adapter, skb, 0, ret);
 		break;
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
index 360d36ceeb1d3..caff442399f34 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
@@ -461,8 +461,8 @@ int mwifiex_process_uap_rx_packet(struct mwifiex_private *priv,
  *      - Priority specific Tx control
  *      - Flags
  */
-void *mwifiex_process_uap_txpd(struct mwifiex_private *priv,
-			       struct sk_buff *skb)
+void mwifiex_process_uap_txpd(struct mwifiex_private *priv,
+			      struct sk_buff *skb)
 {
 	struct mwifiex_adapter *adapter = priv->adapter;
 	struct uap_txpd *txpd;
@@ -471,14 +471,6 @@ void *mwifiex_process_uap_txpd(struct mwifiex_private *priv,
 	u16 pkt_type, pkt_offset;
 	int hroom = adapter->intf_hdr_len;
 
-	if (!skb->len) {
-		mwifiex_dbg(adapter, ERROR,
-			    "Tx: bad packet length: %d\n", skb->len);
-		return skb->data;
-	}
-
-	BUG_ON(skb_headroom(skb) < MWIFIEX_MIN_DATA_HEADER_LEN);
-
 	pkt_type = mwifiex_is_skb_mgmt_frame(skb) ? PKT_TYPE_MGMT : 0;
 
 	pad = ((uintptr_t)skb->data - (sizeof(*txpd) + hroom)) &
@@ -526,6 +518,4 @@ void *mwifiex_process_uap_txpd(struct mwifiex_private *priv,
 	if (!txpd->tx_control)
 		/* TxCtrl set by user or default */
 		txpd->tx_control = cpu_to_le32(priv->pkt_tx_ctrl);
-
-	return skb->data;
 }
-- 
GitLab


From a9be18642ad6561e3313de2c7870b226f451d495 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Tue, 8 Aug 2023 16:10:23 +0800
Subject: [PATCH 1390/1806] wifi: mwifiex: use is_zero_ether_addr() instead of
 ether_addr_equal()

Use is_zero_ether_addr() instead of ether_addr_equal()
to check if the ethernet address is all zeros.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230808081023.2303423-1-ruanjinjie@huawei.com
---
 drivers/net/wireless/marvell/mwifiex/scan.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 644b1e134b01c..fb3105a763377 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -828,7 +828,6 @@ mwifiex_config_scan(struct mwifiex_private *priv,
 	u8 ssid_filter;
 	struct mwifiex_ie_types_htcap *ht_cap;
 	struct mwifiex_ie_types_bss_mode *bss_mode;
-	const u8 zero_mac[6] = {0, 0, 0, 0, 0, 0};
 
 	/* The tlv_buf_len is calculated for each scan command.  The TLVs added
 	   in this routine will be preserved since the routine that sends the
@@ -966,7 +965,7 @@ mwifiex_config_scan(struct mwifiex_private *priv,
 				  sizeof(struct mwifiex_ie_types_scan_chan_gap);
 		}
 
-		if (!ether_addr_equal(user_scan_in->random_mac, zero_mac)) {
+		if (!is_zero_ether_addr(user_scan_in->random_mac)) {
 			random_mac_tlv = (void *)tlv_pos;
 			random_mac_tlv->header.type =
 					 cpu_to_le16(TLV_TYPE_RANDOM_MAC);
-- 
GitLab


From 2785851c627f2db05f9271f7f63661b5dbd95c4c Mon Sep 17 00:00:00 2001
From: Polaris Pi <pinkperfect2021@gmail.com>
Date: Thu, 10 Aug 2023 08:39:11 +0000
Subject: [PATCH 1391/1806] wifi: mwifiex: Fix missed return in oob checks
 failed path

Add missed return in mwifiex_uap_queue_bridged_pkt() and
mwifiex_process_rx_packet().

Fixes: 119585281617 ("wifi: mwifiex: Fix OOB and integer underflow when rx packets")
Signed-off-by: Polaris Pi <pinkperfect2021@gmail.com>
Reported-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230810083911.3725248-1-pinkperfect2021@gmail.com
---
 drivers/net/wireless/marvell/mwifiex/sta_rx.c   | 1 +
 drivers/net/wireless/marvell/mwifiex/uap_txrx.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/wireless/marvell/mwifiex/sta_rx.c b/drivers/net/wireless/marvell/mwifiex/sta_rx.c
index f2899d53a43f9..65420ad674167 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_rx.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_rx.c
@@ -92,6 +92,7 @@ int mwifiex_process_rx_packet(struct mwifiex_private *priv,
 			    skb->len, rx_pkt_off);
 		priv->stats.rx_dropped++;
 		dev_kfree_skb_any(skb);
+		return -1;
 	}
 
 	if ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header,
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
index caff442399f34..b9866f2e26440 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
@@ -110,6 +110,7 @@ static void mwifiex_uap_queue_bridged_pkt(struct mwifiex_private *priv,
 			    skb->len, le16_to_cpu(uap_rx_pd->rx_pkt_offset));
 		priv->stats.rx_dropped++;
 		dev_kfree_skb_any(skb);
+		return;
 	}
 
 	if ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header,
-- 
GitLab


From 0e6ccd25e0d09fe7b03f783a3918c2b67c55ecd5 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Mon, 14 Aug 2023 17:19:04 +0300
Subject: [PATCH 1392/1806] wifi: mwifiex: cleanup adapter data

Remove unused and set but unused 'dfs_workqueue', 'dfs_work', and
'scan_channels' members of 'struct mwifiex_adapter', adjust users.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230814142101.60308-1-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/init.c | 1 -
 drivers/net/wireless/marvell/mwifiex/main.h | 3 ---
 drivers/net/wireless/marvell/mwifiex/scan.c | 4 ----
 3 files changed, 8 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c
index 86293be782a25..c9c58419c37bf 100644
--- a/drivers/net/wireless/marvell/mwifiex/init.c
+++ b/drivers/net/wireless/marvell/mwifiex/init.c
@@ -288,7 +288,6 @@ static void mwifiex_init_adapter(struct mwifiex_adapter *adapter)
 	adapter->fw_bands = 0;
 	adapter->config_bands = 0;
 	adapter->adhoc_start_band = 0;
-	adapter->scan_channels = NULL;
 	adapter->fw_release_number = 0;
 	adapter->fw_cap_info = 0;
 	memset(&adapter->upld_buf, 0, sizeof(adapter->upld_buf));
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 97e7c835d729e..7bdec6c622481 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -878,8 +878,6 @@ struct mwifiex_adapter {
 	struct work_struct main_work;
 	struct workqueue_struct *rx_workqueue;
 	struct work_struct rx_work;
-	struct workqueue_struct *dfs_workqueue;
-	struct work_struct dfs_work;
 	bool rx_work_enabled;
 	bool rx_processing;
 	bool delay_main_work;
@@ -943,7 +941,6 @@ struct mwifiex_adapter {
 	u8 fw_bands;
 	u8 adhoc_start_band;
 	u8 config_bands;
-	struct mwifiex_chan_scan_param_set *scan_channels;
 	u8 tx_lock_flag;
 	struct mwifiex_sleep_period sleep_period;
 	u16 ps_mode;
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index fb3105a763377..72904c275461e 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -612,7 +612,6 @@ mwifiex_scan_channel_list(struct mwifiex_private *priv,
 	struct mwifiex_adapter *adapter = priv->adapter;
 	int ret = 0;
 	struct mwifiex_chan_scan_param_set *tmp_chan_list;
-	struct mwifiex_chan_scan_param_set *start_chan;
 	u32 tlv_idx, rates_size, cmd_no;
 	u32 total_scan_time;
 	u32 done_early;
@@ -643,7 +642,6 @@ mwifiex_scan_channel_list(struct mwifiex_private *priv,
 		total_scan_time = 0;
 		radio_type = 0;
 		chan_tlv_out->header.len = 0;
-		start_chan = tmp_chan_list;
 		done_early = false;
 
 		/*
@@ -750,8 +748,6 @@ mwifiex_scan_channel_list(struct mwifiex_private *priv,
 		rates_size = mwifiex_append_rate_tlv(priv, scan_cfg_out,
 						     radio_type);
 
-		priv->adapter->scan_channels = start_chan;
-
 		/* Send the scan command to the firmware with the specified
 		   cfg */
 		if (priv->adapter->ext_scan)
-- 
GitLab


From ab55a976095e0c5396ca21a81cab95a7d2a42eee Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Mon, 14 Aug 2023 17:19:05 +0300
Subject: [PATCH 1393/1806] wifi: mwifiex: fix comment typos in SDIO module

Fix comment typos around ' mwifiex_deaggr_sdio_pkt()'
and 'mwifiex_host_to_card_mp_aggr()'.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230814142101.60308-2-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/sdio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index 0d60484cd5df4..774858cfe86f2 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -1556,7 +1556,7 @@ done:
 }
 
 /*
- * This function decode sdio aggreation pkt.
+ * This function decodes sdio aggregation pkt.
  *
  * Based on the data block size and pkt_len,
  * skb data will be decoded to few packets.
@@ -2266,7 +2266,7 @@ static int mwifiex_host_to_card_mp_aggr(struct mwifiex_adapter *adapter,
 		ret = mwifiex_write_data_to_card(adapter, card->mpa_tx.buf,
 						 card->mpa_tx.buf_len, mport);
 
-		/* Save the last multi port tx aggreagation info to debug log */
+		/* Save the last multi port tx aggregation info to debug log. */
 		index = adapter->dbg.last_sdio_mp_index;
 		index = (index + 1) % MWIFIEX_DBG_SDIO_MP_NUM;
 		adapter->dbg.last_sdio_mp_index = index;
-- 
GitLab


From 87677749463463973589a85edd96b1468c9ea4ea Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Wed, 2 Aug 2023 01:23:06 +0000
Subject: [PATCH 1394/1806] wifi: ipw2x00: refactor to use kstrtoul

The current implementation seems to reinvent what `kstrtoul` already does
in terms of functionality and error handling. Remove uses of `simple_strtoul()`
in favor of `kstrtoul()`.

There is the following note at `lib/vsprintf.c:simple_strtoull()` which
further backs this change:
| * This function has caveats. Please use kstrtoull (or kstrtoul) instead.

And here, simple_str* are explicitly deprecated [3].

This patch also removes an instance of the deprecated `strncpy` which helps [2].

Compile tested only.

Link: https://lore.kernel.org/all/202308011602.3CC1C0244C@keescook/ [1]
Link: https://github.com/KSPP/linux/issues/90 [2]
Link: https://docs.kernel.org/process/deprecated.html#simple-strtol-simple-strtoll-simple-strtoul-simple-strtoull [3]
Cc: linux-hardening@vger.kernel.org
Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Justin Stitt <justinstitt@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230802-wifi-ipw2x00-refactor-v2-1-d33f765e9cd5@google.com
---
 drivers/net/wireless/intel/ipw2x00/ipw2200.c | 39 ++++++--------------
 1 file changed, 12 insertions(+), 27 deletions(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
index dfe0f74369e62..820100cac4915 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
@@ -1176,23 +1176,20 @@ static ssize_t debug_level_show(struct device_driver *d, char *buf)
 static ssize_t debug_level_store(struct device_driver *d, const char *buf,
 				 size_t count)
 {
-	char *p = (char *)buf;
-	u32 val;
+	unsigned long val;
 
-	if (p[1] == 'x' || p[1] == 'X' || p[0] == 'x' || p[0] == 'X') {
-		p++;
-		if (p[0] == 'x' || p[0] == 'X')
-			p++;
-		val = simple_strtoul(p, &p, 16);
-	} else
-		val = simple_strtoul(p, &p, 10);
-	if (p == buf)
+	int result = kstrtoul(buf, 0, &val);
+
+	if (result == -EINVAL)
 		printk(KERN_INFO DRV_NAME
 		       ": %s is not in hex or decimal form.\n", buf);
+	else if (result == -ERANGE)
+		printk(KERN_INFO DRV_NAME
+			 ": %s has overflowed.\n", buf);
 	else
 		ipw_debug_level = val;
 
-	return strnlen(buf, count);
+	return count;
 }
 static DRIVER_ATTR_RW(debug_level);
 
@@ -1461,25 +1458,13 @@ static ssize_t scan_age_store(struct device *d, struct device_attribute *attr,
 {
 	struct ipw_priv *priv = dev_get_drvdata(d);
 	struct net_device *dev = priv->net_dev;
-	char buffer[] = "00000000";
-	unsigned long len =
-	    (sizeof(buffer) - 1) > count ? count : sizeof(buffer) - 1;
-	unsigned long val;
-	char *p = buffer;
 
 	IPW_DEBUG_INFO("enter\n");
 
-	strncpy(buffer, buf, len);
-	buffer[len] = 0;
+	unsigned long val;
+	int result = kstrtoul(buf, 0, &val);
 
-	if (p[1] == 'x' || p[1] == 'X' || p[0] == 'x' || p[0] == 'X') {
-		p++;
-		if (p[0] == 'x' || p[0] == 'X')
-			p++;
-		val = simple_strtoul(p, &p, 16);
-	} else
-		val = simple_strtoul(p, &p, 10);
-	if (p == buffer) {
+	if (result == -EINVAL || result == -ERANGE) {
 		IPW_DEBUG_INFO("%s: user supplied invalid value.\n", dev->name);
 	} else {
 		priv->ieee->scan_age = val;
@@ -1487,7 +1472,7 @@ static ssize_t scan_age_store(struct device *d, struct device_attribute *attr,
 	}
 
 	IPW_DEBUG_INFO("exit\n");
-	return len;
+	return count;
 }
 
 static DEVICE_ATTR_RW(scan_age);
-- 
GitLab


From b3bfc4fb1edc8136396ece2d7204c2ee5cae188d Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Thu, 3 Aug 2023 19:01:50 +0800
Subject: [PATCH 1395/1806] wifi: rtw89: 8852b: rfk: fine tune IQK parameters
 to improve performance on 2GHz band

A few samples get bad performance on 2GHz band, so use proper IQK command
code and select another group to have wider range of calibration value.

Fixes: f2abe804e823 ("wifi: rtw89: 8852b: rfk: add IQK")
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230803110150.8457-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
index fa018e1f499b2..259df67836a0e 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
@@ -846,7 +846,7 @@ static bool _iqk_one_shot(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
 	case ID_NBTXK:
 		rtw89_phy_write32_mask(rtwdev, R_P0_RFCTM, B_P0_RFCTM_EN, 0x0);
 		rtw89_phy_write32_mask(rtwdev, R_IQK_DIF4, B_IQK_DIF4_TXT, 0x011);
-		iqk_cmd = 0x308 | (1 << (4 + path));
+		iqk_cmd = 0x408 | (1 << (4 + path));
 		break;
 	case ID_NBRXK:
 		rtw89_phy_write32_mask(rtwdev, R_P0_RFCTM, B_P0_RFCTM_EN, 0x1);
@@ -1078,7 +1078,7 @@ static bool _iqk_nbtxk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u8
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	bool kfail;
-	u8 gp = 0x3;
+	u8 gp = 0x2;
 
 	switch (iqk_info->iqk_band[path]) {
 	case RTW89_BAND_2G:
-- 
GitLab


From eb2624f55ad14634f97efbf56cb0cb815800508a Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Fri, 4 Aug 2023 13:34:58 +0800
Subject: [PATCH 1396/1806] wifi: rtw89: Introduce Time Averaged SAR (TAS)
 feature

Time Averaged SAR (TAS) tracks the amount of transmit power over a
period of time and adjusts the power accordingly. Two thresholds are
used to determine when to increase or reduce transmit power: Dynamic
Power Reduction (DPR) on/off. Compared to Static SAR, which has a
constant transmit power, TAS can improve the user experience or
range extension.

TAS can be enabled through BIOS, and the driver will evaluate
Realtek ACPI DSM with RTW89_ACPI_DSM_FUNC_TAS_EN to determine
whether TAS should be enabled.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230804053458.31492-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c  |   4 +
 drivers/net/wireless/realtek/rtw89/core.h  |  18 ++
 drivers/net/wireless/realtek/rtw89/debug.c |   3 +
 drivers/net/wireless/realtek/rtw89/reg.h   |   4 +
 drivers/net/wireless/realtek/rtw89/sar.c   | 197 +++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/sar.h   |   4 +
 6 files changed, 230 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 62c21c09cf92b..71eb9cfd48965 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -2682,6 +2682,7 @@ static void rtw89_track_work(struct work_struct *work)
 	rtw89_phy_tx_path_div_track(rtwdev);
 	rtw89_phy_antdiv_track(rtwdev);
 	rtw89_phy_ul_tb_ctrl_track(rtwdev);
+	rtw89_tas_track(rtwdev);
 
 	if (rtwdev->lps_enabled && !rtwdev->btc.lps)
 		rtw89_enter_lps_track(rtwdev);
@@ -3496,6 +3497,8 @@ int rtw89_core_start(struct rtw89_dev *rtwdev)
 	rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, true);
 	rtw89_mac_update_rts_threshold(rtwdev, RTW89_MAC_0);
 
+	rtw89_tas_reset(rtwdev);
+
 	ret = rtw89_hci_start(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to start hci\n");
@@ -3612,6 +3615,7 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 
 	rtw89_ser_init(rtwdev);
 	rtw89_entity_init(rtwdev);
+	rtw89_tas_init(rtwdev);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index fa4bbc4095ab9..b5a08f90f5bd7 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3690,6 +3690,23 @@ struct rtw89_sar_info {
 	};
 };
 
+enum rtw89_tas_state {
+	RTW89_TAS_STATE_DPR_OFF,
+	RTW89_TAS_STATE_DPR_ON,
+	RTW89_TAS_STATE_DPR_FORBID,
+};
+
+#define RTW89_TAS_MAX_WINDOW 50
+struct rtw89_tas_info {
+	s16 txpwr_history[RTW89_TAS_MAX_WINDOW];
+	s32 total_txpwr;
+	u8 cur_idx;
+	s8 dpr_gap;
+	s8 delta;
+	enum rtw89_tas_state state;
+	bool enable;
+};
+
 struct rtw89_chanctx_cfg {
 	enum rtw89_sub_entity_idx idx;
 };
@@ -4365,6 +4382,7 @@ struct rtw89_dev {
 
 	struct rtw89_regulatory_info regulatory;
 	struct rtw89_sar_info sar;
+	struct rtw89_tas_info tas;
 
 	struct rtw89_btc btc;
 	enum rtw89_ps_mode ps_mode;
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index f1e5ac4186c2a..f6f1e90c39344 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -615,6 +615,9 @@ static int rtw89_debug_priv_txpwr_table_get(struct seq_file *m, void *v)
 	seq_puts(m, "[SAR]\n");
 	rtw89_print_sar(m, rtwdev);
 
+	seq_puts(m, "[TAS]\n");
+	rtw89_print_tas(m, rtwdev);
+
 	seq_puts(m, "\n[TX power byrate]\n");
 	ret = __print_txpwr_map(m, rtwdev, &__txpwr_map_byr);
 	if (ret)
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index 55595fde74949..2d34b43cda3a2 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -4109,6 +4109,8 @@
 #define B_TXAGC_BB_OFT GENMASK(31, 16)
 #define B_TXAGC_BB GENMASK(31, 24)
 #define B_TXAGC_RF GENMASK(5, 0)
+#define R_PATH0_TXPWR 0x1C78
+#define B_PATH0_TXPWR GENMASK(8, 0)
 #define R_S0_ADDCK 0x1E00
 #define B_S0_ADDCK_I GENMASK(9, 0)
 #define B_S0_ADDCK_Q GENMASK(19, 10)
@@ -4184,6 +4186,8 @@
 #define R_TXAGC_BB_S1 0x3C60
 #define B_TXAGC_BB_S1_OFT GENMASK(31, 16)
 #define B_TXAGC_BB_S1 GENMASK(31, 24)
+#define R_PATH1_TXPWR 0x3C78
+#define B_PATH1_TXPWR GENMASK(8, 0)
 #define R_S1_ADDCK 0x3E00
 #define B_S1_ADDCK_I GENMASK(9, 0)
 #define B_S1_ADDCK_Q GENMASK(19, 10)
diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index dfccae81c3804..fafc7a0cfe97c 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -2,9 +2,16 @@
 /* Copyright(c) 2019-2020  Realtek Corporation
  */
 
+#include "acpi.h"
 #include "debug.h"
+#include "phy.h"
+#include "reg.h"
 #include "sar.h"
 
+#define RTW89_TAS_FACTOR 2 /* unit: 0.25 dBm */
+#define RTW89_TAS_DPR_GAP (1 << RTW89_TAS_FACTOR)
+#define RTW89_TAS_DELTA (2 << RTW89_TAS_FACTOR)
+
 static enum rtw89_sar_subband rtw89_sar_get_subband(struct rtw89_dev *rtwdev,
 						    u32 center_freq)
 {
@@ -157,11 +164,35 @@ static s8 rtw89_txpwr_sar_to_mac(struct rtw89_dev *rtwdev, u8 fct, s32 cfg)
 			   RTW89_SAR_TXPWR_MAC_MAX);
 }
 
+static s8 rtw89_txpwr_tas_to_sar(const struct rtw89_sar_handler *sar_hdl,
+				 s8 cfg)
+{
+	const u8 fct = sar_hdl->txpwr_factor_sar;
+
+	if (fct > RTW89_TAS_FACTOR)
+		return cfg << (fct - RTW89_TAS_FACTOR);
+	else
+		return cfg >> (RTW89_TAS_FACTOR - fct);
+}
+
+static s8 rtw89_txpwr_sar_to_tas(const struct rtw89_sar_handler *sar_hdl,
+				 s8 cfg)
+{
+	const u8 fct = sar_hdl->txpwr_factor_sar;
+
+	if (fct > RTW89_TAS_FACTOR)
+		return cfg >> (fct - RTW89_TAS_FACTOR);
+	else
+		return cfg << (RTW89_TAS_FACTOR - fct);
+}
+
 s8 rtw89_query_sar(struct rtw89_dev *rtwdev)
 {
 	const enum rtw89_sar_sources src = rtwdev->sar.src;
 	/* its members are protected by rtw89_sar_set_src() */
 	const struct rtw89_sar_handler *sar_hdl = &rtw89_sar_handlers[src];
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	s8 delta;
 	int ret;
 	s32 cfg;
 	u8 fct;
@@ -175,6 +206,19 @@ s8 rtw89_query_sar(struct rtw89_dev *rtwdev)
 	if (ret)
 		return RTW89_SAR_TXPWR_MAC_MAX;
 
+	if (tas->enable) {
+		switch (tas->state) {
+		case RTW89_TAS_STATE_DPR_OFF:
+			return RTW89_SAR_TXPWR_MAC_MAX;
+		case RTW89_TAS_STATE_DPR_ON:
+			delta = rtw89_txpwr_tas_to_sar(sar_hdl, tas->delta);
+			cfg -= delta;
+		case RTW89_TAS_STATE_DPR_FORBID:
+		default:
+			break;
+		}
+	}
+
 	fct = sar_hdl->txpwr_factor_sar;
 
 	return rtw89_txpwr_sar_to_mac(rtwdev, fct, cfg);
@@ -212,6 +256,19 @@ void rtw89_print_sar(struct seq_file *m, struct rtw89_dev *rtwdev)
 	seq_printf(m, "config: %d (unit: 1/%lu dBm)\n", cfg, BIT(fct));
 }
 
+void rtw89_print_tas(struct seq_file *m, struct rtw89_dev *rtwdev)
+{
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+
+	if (!tas->enable) {
+		seq_puts(m, "no TAS is applied\n");
+		return;
+	}
+
+	seq_printf(m, "DPR gap: %d\n", tas->dpr_gap);
+	seq_printf(m, "TAS delta: %d\n", tas->delta);
+}
+
 static int rtw89_apply_sar_common(struct rtw89_dev *rtwdev,
 				  const struct rtw89_sar_cfg_common *sar)
 {
@@ -292,3 +349,143 @@ int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw,
 
 	return rtw89_apply_sar_common(rtwdev, &sar_common);
 }
+
+static void rtw89_tas_state_update(struct rtw89_dev *rtwdev)
+{
+	const enum rtw89_sar_sources src = rtwdev->sar.src;
+	/* its members are protected by rtw89_sar_set_src() */
+	const struct rtw89_sar_handler *sar_hdl = &rtw89_sar_handlers[src];
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	s32 txpwr_avg = tas->total_txpwr / RTW89_TAS_MAX_WINDOW / PERCENT;
+	s32 dpr_on_threshold, dpr_off_threshold, cfg;
+	enum rtw89_tas_state state = tas->state;
+	int ret;
+
+	lockdep_assert_held(&rtwdev->mutex);
+
+	if (src == RTW89_SAR_SOURCE_NONE)
+		return;
+
+	ret = sar_hdl->query_sar_config(rtwdev, &cfg);
+	if (ret)
+		return;
+
+	cfg = rtw89_txpwr_sar_to_tas(sar_hdl, cfg);
+
+	if (tas->delta >= cfg) {
+		rtw89_debug(rtwdev, RTW89_DBG_SAR,
+			    "TAS delta exceed SAR limit\n");
+		state = RTW89_TAS_STATE_DPR_FORBID;
+		goto out;
+	}
+
+	dpr_on_threshold = cfg;
+	dpr_off_threshold = cfg - tas->dpr_gap;
+	rtw89_debug(rtwdev, RTW89_DBG_SAR,
+		    "DPR_ON thold: %d, DPR_OFF thold: %d, txpwr_avg: %d\n",
+		    dpr_on_threshold, dpr_off_threshold, txpwr_avg);
+
+	if (txpwr_avg >= dpr_on_threshold)
+		state = RTW89_TAS_STATE_DPR_ON;
+	else if (txpwr_avg < dpr_off_threshold)
+		state = RTW89_TAS_STATE_DPR_OFF;
+
+out:
+	if (tas->state == state)
+		return;
+
+	rtw89_debug(rtwdev, RTW89_DBG_SAR,
+		    "TAS old state: %d, new state: %d\n", tas->state, state);
+	tas->state = state;
+	rtw89_core_set_chip_txpwr(rtwdev);
+}
+
+void rtw89_tas_init(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	int ret;
+	u8 val;
+
+	ret = rtw89_acpi_evaluate_dsm(rtwdev, RTW89_ACPI_DSM_FUNC_TAS_EN, &val);
+	if (ret) {
+		rtw89_debug(rtwdev, RTW89_DBG_SAR,
+			    "acpi: cannot get TAS: %d\n", ret);
+		return;
+	}
+
+	switch (val) {
+	case 0:
+		tas->enable = false;
+		break;
+	case 1:
+		tas->enable = true;
+		break;
+	default:
+		break;
+	}
+
+	if (!tas->enable) {
+		rtw89_debug(rtwdev, RTW89_DBG_SAR, "TAS not enable\n");
+		return;
+	}
+
+	tas->dpr_gap = RTW89_TAS_DPR_GAP;
+	tas->delta = RTW89_TAS_DELTA;
+}
+
+void rtw89_tas_reset(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+
+	if (!tas->enable)
+		return;
+
+	memset(&tas->txpwr_history, 0, sizeof(tas->txpwr_history));
+	tas->total_txpwr = 0;
+	tas->cur_idx = 0;
+	tas->state = RTW89_TAS_STATE_DPR_OFF;
+}
+
+static const struct rtw89_reg_def txpwr_regs[] = {
+	{R_PATH0_TXPWR, B_PATH0_TXPWR},
+	{R_PATH1_TXPWR, B_PATH1_TXPWR},
+};
+
+void rtw89_tas_track(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	const enum rtw89_sar_sources src = rtwdev->sar.src;
+	u8 max_nss_num = rtwdev->chip->rf_path_num;
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	s16 tmp, txpwr, instant_txpwr = 0;
+	u32 val;
+	int i;
+
+	if (!tas->enable || src == RTW89_SAR_SOURCE_NONE)
+		return;
+
+	if (env->ccx_watchdog_result != RTW89_PHY_ENV_MON_IFS_CLM)
+		return;
+
+	for (i = 0; i < max_nss_num; i++) {
+		val = rtw89_phy_read32_mask(rtwdev, txpwr_regs[i].addr,
+					    txpwr_regs[i].mask);
+		tmp = sign_extend32(val, 8);
+		if (tmp <= 0)
+			return;
+		instant_txpwr += tmp;
+	}
+
+	instant_txpwr /= max_nss_num;
+	/* in unit of 0.25 dBm multiply by percentage */
+	txpwr = instant_txpwr * env->ifs_clm_tx_ratio;
+	tas->total_txpwr += txpwr - tas->txpwr_history[tas->cur_idx];
+	tas->txpwr_history[tas->cur_idx] = txpwr;
+	rtw89_debug(rtwdev, RTW89_DBG_SAR,
+		    "instant_txpwr: %d, tx_ratio: %d, txpwr: %d\n",
+		    instant_txpwr, env->ifs_clm_tx_ratio, txpwr);
+
+	tas->cur_idx = (tas->cur_idx + 1) % RTW89_TAS_MAX_WINDOW;
+
+	rtw89_tas_state_update(rtwdev);
+}
diff --git a/drivers/net/wireless/realtek/rtw89/sar.h b/drivers/net/wireless/realtek/rtw89/sar.h
index 7b5484c84eb11..40ce5990ceaf5 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.h
+++ b/drivers/net/wireless/realtek/rtw89/sar.h
@@ -20,7 +20,11 @@ extern const struct cfg80211_sar_capa rtw89_sar_capa;
 
 s8 rtw89_query_sar(struct rtw89_dev *rtwdev);
 void rtw89_print_sar(struct seq_file *m, struct rtw89_dev *rtwdev);
+void rtw89_print_tas(struct seq_file *m, struct rtw89_dev *rtwdev);
 int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw,
 			    const struct cfg80211_sar_specs *sar);
+void rtw89_tas_init(struct rtw89_dev *rtwdev);
+void rtw89_tas_reset(struct rtw89_dev *rtwdev);
+void rtw89_tas_track(struct rtw89_dev *rtwdev);
 
 #endif
-- 
GitLab


From 66311106b20b5aba36ca4974d0bc5d637ccf0948 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Fri, 4 Aug 2023 17:01:20 +0800
Subject: [PATCH 1397/1806] wifi: rtlwifi: use eth_broadcast_addr() to assign
 broadcast address

Use eth_broadcast_addr() to assign broadcast address instead
of memcpy().

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230804090120.1332091-1-yangyingliang@huawei.com
---
 drivers/net/wireless/realtek/rtlwifi/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index 4fb16f5f6f83b..3835b639d453f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -1656,7 +1656,7 @@ static int rtl_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			memcpy(rtlpriv->sec.key_buf[key_idx],
 			       key->key, key->keylen);
 			rtlpriv->sec.key_len[key_idx] = key->keylen;
-			memcpy(mac_addr, bcast_addr, ETH_ALEN);
+			eth_broadcast_addr(mac_addr);
 		} else {	/* pairwise key */
 			rtl_dbg(rtlpriv, COMP_SEC, DBG_DMESG,
 				"set pairwise key\n");
-- 
GitLab


From 186f2432741f6d28d86ff723ac7830446affddfc Mon Sep 17 00:00:00 2001
From: Shiji Yang <yangshiji66@outlook.com>
Date: Sat, 5 Aug 2023 17:17:28 +0800
Subject: [PATCH 1398/1806] wifi: rt2x00: correct MAC_SYS_CTRL register RX mask
 in R-Calibration

For MAC_SYS_CTRL register, Bit[2] controls MAC_TX_EN and Bit[3]
controls MAC_RX_EN (Bit index starts from 0). Therefore, 0x08 is
the correct mask for RX.

Signed-off-by: Shiji Yang <yangshiji66@outlook.com>
Acked-by: Stanislaw Gruszka <stf_xl@wp.pl>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/TYAP286MB03150B571B67B896A504AC34BC0EA@TYAP286MB0315.JPNP286.PROD.OUTLOOK.COM
---
 drivers/net/wireless/ralink/rt2x00/rt2800lib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
index 1226a883cd671..ab374c50c35d8 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
@@ -8561,7 +8561,7 @@ static void rt2800_r_calibration(struct rt2x00_dev *rt2x00dev)
 		rt2x00_warn(rt2x00dev, "Wait MAC Tx Status to MAX !!!\n");
 
 	maccfg = rt2800_register_read(rt2x00dev, MAC_SYS_CTRL);
-	maccfg &= (~0x04);
+	maccfg &= (~0x08);
 	rt2800_register_write(rt2x00dev, MAC_SYS_CTRL, maccfg);
 
 	if (unlikely(rt2800_wait_bbp_rf_ready(rt2x00dev, MAC_STATUS_CFG_BBP_RF_BUSY_RX)))
-- 
GitLab


From e2a61151ff8c38ae7b3afae0e91cb97fb211a6bf Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 8 Aug 2023 08:36:09 +0300
Subject: [PATCH 1399/1806] wifi: rtw89: fix a width vs precision bug

The "buf" is skb->data that comes from the firmware.  We want to print
"len" number of bytes.  But there is a missing period so the "len"
variable is used for formatting (width) instead of limiting the output
(precision).

Fixes: cad2bd8a136c ("wifi: rtw89: support firmware log with formatted text")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/0700c7b9-bfd3-4aa6-82bf-5bf3c74644e1@moroto.mountain
---
 drivers/net/wireless/realtek/rtw89/fw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 2811a94b5f69a..bcd9050f989ff 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -1165,7 +1165,7 @@ void rtw89_fw_log_dump(struct rtw89_dev *rtwdev, u8 *buf, u32 len)
 	return;
 
 plain_log:
-	rtw89_info(rtwdev, "C2H log: %*s", len, buf);
+	rtw89_info(rtwdev, "C2H log: %.*s", len, buf);
 
 }
 
-- 
GitLab


From f585f4ab0b998578b4ef3610ccfc08e207fc3499 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Tue, 15 Aug 2023 20:02:53 +0800
Subject: [PATCH 1400/1806] wifi: rtw89: regd: update regulatory map to R64-R43

Sync Realtek Regulatory R43 and Realtek Channel Plan R64.

1. add entry for XK (Kosovo)
2. change TH (Thailand) to Realtek regd world-wide
3. configures Realtek 6 GHz regd for below countries
   * AR, MX, HT -> FCC
   * LB, ZA, BF, LA, MN -> ETSI

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230815120253.9901-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/regd.c | 27 ++++++++++++-----------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index 34c4d40cfa022..9e2328db18656 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -13,10 +13,10 @@
 	}
 
 static const struct rtw89_regd rtw89_ww_regd =
-	COUNTRY_REGD("00", RTW89_WW, RTW89_WW);
+	COUNTRY_REGD("00", RTW89_WW, RTW89_WW, RTW89_WW);
 
 static const struct rtw89_regd rtw89_regd_map[] = {
-	COUNTRY_REGD("AR", RTW89_MEXICO, RTW89_MEXICO, RTW89_NA),
+	COUNTRY_REGD("AR", RTW89_MEXICO, RTW89_MEXICO, RTW89_FCC),
 	COUNTRY_REGD("BO", RTW89_FCC, RTW89_FCC, RTW89_FCC),
 	COUNTRY_REGD("BR", RTW89_FCC, RTW89_FCC, RTW89_FCC),
 	COUNTRY_REGD("CL", RTW89_CHILE, RTW89_CHILE, RTW89_CHILE),
@@ -26,7 +26,7 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("SV", RTW89_FCC, RTW89_FCC, RTW89_FCC),
 	COUNTRY_REGD("GT", RTW89_FCC, RTW89_FCC, RTW89_FCC),
 	COUNTRY_REGD("HN", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("MX", RTW89_MEXICO, RTW89_MEXICO, RTW89_NA),
+	COUNTRY_REGD("MX", RTW89_MEXICO, RTW89_MEXICO, RTW89_FCC),
 	COUNTRY_REGD("NI", RTW89_FCC, RTW89_FCC, RTW89_NA),
 	COUNTRY_REGD("PA", RTW89_FCC, RTW89_FCC, RTW89_NA),
 	COUNTRY_REGD("PY", RTW89_FCC, RTW89_FCC, RTW89_NA),
@@ -81,7 +81,7 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("KE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("KW", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("KG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LB", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
+	COUNTRY_REGD("LB", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("LS", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("MK", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("MA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
@@ -96,7 +96,7 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("SN", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("RS", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("ME", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("ZA", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
+	COUNTRY_REGD("ZA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("TR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("UA", RTW89_UKRAINE, RTW89_UKRAINE, RTW89_UKRAINE),
 	COUNTRY_REGD("AE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
@@ -115,7 +115,7 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("SG", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("LK", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("TW", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("TH", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
+	COUNTRY_REGD("TH", RTW89_WW, RTW89_WW, RTW89_WW),
 	COUNTRY_REGD("VN", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("AU", RTW89_ACMA, RTW89_ACMA, RTW89_ACMA),
 	COUNTRY_REGD("NZ", RTW89_ACMA, RTW89_ACMA, RTW89_ACMA),
@@ -148,7 +148,7 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("IO", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("VG", RTW89_FCC, RTW89_FCC, RTW89_FCC),
 	COUNTRY_REGD("BN", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("BF", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
+	COUNTRY_REGD("BF", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("MM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("BI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("CM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
@@ -164,7 +164,7 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("CK", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("CI", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("DJ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("DM", RTW89_FCC, RTW89_FCC, RTW89_FCC),
+	COUNTRY_REGD("DM", RTW89_FCC, RTW89_FCC, RTW89_NA),
 	COUNTRY_REGD("GQ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("ER", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("ET", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
@@ -179,20 +179,21 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("GE", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("GI", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("GL", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("GD", RTW89_FCC, RTW89_FCC, RTW89_FCC),
+	COUNTRY_REGD("GD", RTW89_FCC, RTW89_FCC, RTW89_NA),
 	COUNTRY_REGD("GP", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("GU", RTW89_FCC, RTW89_FCC, RTW89_NA),
 	COUNTRY_REGD("GG", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("GN", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("GW", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("GY", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("HT", RTW89_FCC, RTW89_FCC, RTW89_NA),
+	COUNTRY_REGD("GY", RTW89_FCC, RTW89_FCC, RTW89_NA),
+	COUNTRY_REGD("HT", RTW89_FCC, RTW89_FCC, RTW89_FCC),
 	COUNTRY_REGD("HM", RTW89_ACMA, RTW89_ACMA, RTW89_NA),
 	COUNTRY_REGD("VA", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("IM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("JE", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("KI", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("LA", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
+	COUNTRY_REGD("XK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
+	COUNTRY_REGD("LA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("LR", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("LY", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("MO", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
@@ -207,7 +208,7 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("YT", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("FM", RTW89_FCC, RTW89_FCC, RTW89_NA),
 	COUNTRY_REGD("MD", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("MN", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
+	COUNTRY_REGD("MN", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("MS", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("NR", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("NP", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-- 
GitLab


From 7a73cf0bf7f96cd2b9f2ea890bf1e981730d8d6c Mon Sep 17 00:00:00 2001
From: Adham Faris <afaris@nvidia.com>
Date: Wed, 8 Mar 2023 11:59:36 +0200
Subject: [PATCH 1401/1806] net/mlx5e: aRFS, Prevent repeated kernel rule
 migrations requests

aRFS rule movement requests from one Rx ring to other Rx ring arrive
from the kernel to ensure that packets are steered to the right Rx ring.
In the time interval until satisfying such a request, several more
requests might follow, for the same flow.

This patch detects and prevents repeated aRFS rules movement requests.

In mlx5e_rx_flow_steer() ndo, after finding the aRFS rule that have been
requested to move by the kernel, check if it's already requested to move
by calling work_busy(&arfs_rule->arfs_work) handler. IOW, if this
request is pending to be executed (in the work queue) or it's executing
now but hasn't finished yet, return current filter ID and don't issue a
new transition work.

Signed-off-by: Adham Faris <afaris@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 5aa51d74f8b43..67d8b198a0141 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -740,7 +740,7 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	spin_lock_bh(&arfs->arfs_lock);
 	arfs_rule = arfs_find_rule(arfs_t, &fk);
 	if (arfs_rule) {
-		if (arfs_rule->rxq == rxq_index) {
+		if (arfs_rule->rxq == rxq_index || work_busy(&arfs_rule->arfs_work)) {
 			spin_unlock_bh(&arfs->arfs_lock);
 			return arfs_rule->filter_id;
 		}
-- 
GitLab


From 7653d80672455658ea106a6ba1bcabfd7a9c3917 Mon Sep 17 00:00:00 2001
From: Adham Faris <afaris@nvidia.com>
Date: Mon, 8 May 2023 14:27:48 +0300
Subject: [PATCH 1402/1806] net/mlx5e: aRFS, Warn if aRFS table does not exist
 for aRFS rule

aRFS tables should be allocated and exist in advance. Driver shouldn't
reach a point where it tries to add aRFS rule to table that does not
exist.

Add warning if driver encounters such situation.

Signed-off-by: Adham Faris <afaris@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 67d8b198a0141..e8b0acf7d454c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -519,6 +519,8 @@ static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
 		 ntohs(tuple->etype));
 	arfs_table = arfs_get_table(arfs, tuple->ip_proto, tuple->etype);
 	if (!arfs_table) {
+		WARN_ONCE(1, "arfs table does not exist for etype %u and ip_proto %u\n",
+			  tuple->etype, tuple->ip_proto);
 		err = -EINVAL;
 		goto out;
 	}
-- 
GitLab


From f98e51585f2ca00efbd16e27ed1d94a5e5520703 Mon Sep 17 00:00:00 2001
From: Adham Faris <afaris@nvidia.com>
Date: Wed, 8 Mar 2023 12:08:43 +0200
Subject: [PATCH 1403/1806] net/mlx5e: aRFS, Introduce ethtool stats

Improve aRFS observability by adding new set of counters. Each Rx
ring will have this set of counters listed below.
These counters are exposed through ethtool -S.

1) arfs_add: number of times a new rule has been created.
2) arfs_request_in: number of times a rule  was requested to move from
   its current Rx ring to a new Rx ring (incremented on the destination
   Rx ring).
3) arfs_request_out: number of times a rule  was requested to move out
   from its current Rx ring (incremented on source/current Rx ring).
4) arfs_expired: number of times a rule has been expired by the
   kernel and removed from HW.
5) arfs_err: number of times a rule creation or modification has
   failed.

This patch removes rx[i]_xsk_arfs_err counter and its documentation in
mlx5/counters.rst since aRFS activity does not occur in XSK RQ's.

Signed-off-by: Adham Faris <afaris@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
---
 .../ethernet/mellanox/mlx5/counters.rst       | 23 +++++++++++++++----
 .../net/ethernet/mellanox/mlx5/core/en_arfs.c | 17 +++++++++++---
 .../ethernet/mellanox/mlx5/core/en_stats.c    | 22 ++++++++++++++----
 .../ethernet/mellanox/mlx5/core/en_stats.h    | 13 ++++++++++-
 4 files changed, 62 insertions(+), 13 deletions(-)

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
index 008e560e12b58..f69ee1ebee010 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
@@ -346,6 +346,24 @@ the software port.
      - The number of receive packets with CQE compression on ring i [#accel]_.
      - Acceleration
 
+   * - `rx[i]_arfs_add`
+     - The number of aRFS flow rules added to the device for direct RQ steering
+       on ring i [#accel]_.
+     - Acceleration
+
+   * - `rx[i]_arfs_request_in`
+     - Number of flow rules that have been requested to move into ring i for
+       direct RQ steering [#accel]_.
+     - Acceleration
+
+   * - `rx[i]_arfs_request_out`
+     - Number of flow rules that have been requested to move out of ring i [#accel]_.
+     - Acceleration
+
+   * - `rx[i]_arfs_expired`
+     - Number of flow rules that have been expired and removed [#accel]_.
+     - Acceleration
+
    * - `rx[i]_arfs_err`
      - Number of flow rules that failed to be added to the flow table.
      - Error
@@ -445,11 +463,6 @@ the software port.
        context.
      - Error
 
-   * - `rx[i]_xsk_arfs_err`
-     - aRFS (accelerated Receive Flow Steering) does not occur in the XSK RQ
-       context, so this counter should never increment.
-     - Error
-
    * - `rx[i]_xdp_tx_xmit`
      - The number of packets forwarded back to the port due to XDP program
        `XDP_TX` action (bouncing). these packets are not counted by other
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index e8b0acf7d454c..bb7f86c993e55 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -432,8 +432,10 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv)
 	}
 	spin_unlock_bh(&arfs->arfs_lock);
 	hlist_for_each_entry_safe(arfs_rule, htmp, &del_list, hlist) {
-		if (arfs_rule->rule)
+		if (arfs_rule->rule) {
 			mlx5_del_flow_rules(arfs_rule->rule);
+			priv->channel_stats[arfs_rule->rxq]->rq.arfs_expired++;
+		}
 		hlist_del(&arfs_rule->hlist);
 		kfree(arfs_rule);
 	}
@@ -509,6 +511,7 @@ static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec) {
+		priv->channel_stats[arfs_rule->rxq]->rq.arfs_err++;
 		err = -ENOMEM;
 		goto out;
 	}
@@ -602,9 +605,11 @@ static void arfs_modify_rule_rq(struct mlx5e_priv *priv,
 	dst.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 	dst.tir_num = mlx5e_rx_res_get_tirn_direct(priv->rx_res, rxq);
 	err =  mlx5_modify_rule_destination(rule, &dst, NULL);
-	if (err)
+	if (err) {
+		priv->channel_stats[rxq]->rq.arfs_err++;
 		netdev_warn(priv->netdev,
 			    "Failed to modify aRFS rule destination to rq=%d\n", rxq);
+	}
 }
 
 static void arfs_handle_work(struct work_struct *work)
@@ -634,6 +639,7 @@ static void arfs_handle_work(struct work_struct *work)
 		if (IS_ERR(rule))
 			goto out;
 		arfs_rule->rule = rule;
+		priv->channel_stats[arfs_rule->rxq]->rq.arfs_add++;
 	} else {
 		arfs_modify_rule_rq(priv, arfs_rule->rule,
 				    arfs_rule->rxq);
@@ -652,8 +658,10 @@ static struct arfs_rule *arfs_alloc_rule(struct mlx5e_priv *priv,
 	struct arfs_tuple *tuple;
 
 	rule = kzalloc(sizeof(*rule), GFP_ATOMIC);
-	if (!rule)
+	if (!rule) {
+		priv->channel_stats[rxq]->rq.arfs_err++;
 		return NULL;
+	}
 
 	rule->priv = priv;
 	rule->rxq = rxq;
@@ -746,6 +754,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 			spin_unlock_bh(&arfs->arfs_lock);
 			return arfs_rule->filter_id;
 		}
+
+		priv->channel_stats[rxq_index]->rq.arfs_request_in++;
+		priv->channel_stats[arfs_rule->rxq]->rq.arfs_request_out++;
 		arfs_rule->rxq = rxq_index;
 	} else {
 		arfs_rule = arfs_alloc_rule(priv, arfs_t, &fk, rxq_index, flow_id);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 52141729444e1..348fb140858ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -180,7 +180,13 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
+#ifdef CONFIG_MLX5_EN_ARFS
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_add) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_request_in) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_request_out) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_expired) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) },
+#endif
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_recover) },
 #ifdef CONFIG_PAGE_POOL_STATS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_alloc_fast) },
@@ -231,7 +237,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_cqe_compress_pkts) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_congst_umr) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_arfs_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_xmit) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_mpwqe) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_inlnw) },
@@ -321,7 +326,6 @@ static void mlx5e_stats_grp_sw_update_stats_xskrq(struct mlx5e_sw_stats *s,
 	s->rx_xsk_cqe_compress_blks      += xskrq_stats->cqe_compress_blks;
 	s->rx_xsk_cqe_compress_pkts      += xskrq_stats->cqe_compress_pkts;
 	s->rx_xsk_congst_umr             += xskrq_stats->congst_umr;
-	s->rx_xsk_arfs_err               += xskrq_stats->arfs_err;
 }
 
 static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
@@ -354,7 +358,13 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 	s->rx_cqe_compress_blks       += rq_stats->cqe_compress_blks;
 	s->rx_cqe_compress_pkts       += rq_stats->cqe_compress_pkts;
 	s->rx_congst_umr              += rq_stats->congst_umr;
+#ifdef CONFIG_MLX5_EN_ARFS
+	s->rx_arfs_add                += rq_stats->arfs_add;
+	s->rx_arfs_request_in         += rq_stats->arfs_request_in;
+	s->rx_arfs_request_out        += rq_stats->arfs_request_out;
+	s->rx_arfs_expired            += rq_stats->arfs_expired;
 	s->rx_arfs_err                += rq_stats->arfs_err;
+#endif
 	s->rx_recover                 += rq_stats->recover;
 #ifdef CONFIG_PAGE_POOL_STATS
 	s->rx_pp_alloc_fast          += rq_stats->pp_alloc_fast;
@@ -1990,7 +2000,13 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) },
+#ifdef CONFIG_MLX5_EN_ARFS
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_add) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_request_in) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_request_out) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_expired) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) },
+#endif
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, recover) },
 #ifdef CONFIG_PAGE_POOL_STATS
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_alloc_fast) },
@@ -2092,7 +2108,6 @@ static const struct counter_desc xskrq_stats_desc[] = {
 	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
 	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, congst_umr) },
-	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, arfs_err) },
 };
 
 static const struct counter_desc xsksq_stats_desc[] = {
@@ -2168,7 +2183,6 @@ static const struct counter_desc ptp_rq_stats_desc[] = {
 	{ MLX5E_DECLARE_PTP_RQ_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_PTP_RQ_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
 	{ MLX5E_DECLARE_PTP_RQ_STAT(struct mlx5e_rq_stats, congst_umr) },
-	{ MLX5E_DECLARE_PTP_RQ_STAT(struct mlx5e_rq_stats, arfs_err) },
 	{ MLX5E_DECLARE_PTP_RQ_STAT(struct mlx5e_rq_stats, recover) },
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 409e9a47e4333..176fa5976259f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -194,7 +194,13 @@ struct mlx5e_sw_stats {
 	u64 rx_cqe_compress_blks;
 	u64 rx_cqe_compress_pkts;
 	u64 rx_congst_umr;
+#ifdef CONFIG_MLX5_EN_ARFS
+	u64 rx_arfs_add;
+	u64 rx_arfs_request_in;
+	u64 rx_arfs_request_out;
+	u64 rx_arfs_expired;
 	u64 rx_arfs_err;
+#endif
 	u64 rx_recover;
 	u64 ch_events;
 	u64 ch_poll;
@@ -256,7 +262,6 @@ struct mlx5e_sw_stats {
 	u64 rx_xsk_cqe_compress_blks;
 	u64 rx_xsk_cqe_compress_pkts;
 	u64 rx_xsk_congst_umr;
-	u64 rx_xsk_arfs_err;
 	u64 tx_xsk_xmit;
 	u64 tx_xsk_mpwqe;
 	u64 tx_xsk_inlnw;
@@ -358,7 +363,13 @@ struct mlx5e_rq_stats {
 	u64 cqe_compress_blks;
 	u64 cqe_compress_pkts;
 	u64 congst_umr;
+#ifdef CONFIG_MLX5_EN_ARFS
+	u64 arfs_add;
+	u64 arfs_request_in;
+	u64 arfs_request_out;
+	u64 arfs_expired;
 	u64 arfs_err;
+#endif
 	u64 recover;
 #ifdef CONFIG_PAGE_POOL_STATS
 	u64 pp_alloc_fast;
-- 
GitLab


From d7cea02a1fac70808423b6c7a64464ba3185f7a9 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Fri, 4 Aug 2023 19:23:06 +0100
Subject: [PATCH 1404/1806] net/mlx5e: Fix spelling mistake "Faided" ->
 "Failed"

There is a spelling mistake in a warning message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 455746952260f..095f31f380fa3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -316,7 +316,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev)
 			err = mlx5_esw_ipsec_modify_flow_dests(esw, flow);
 			if (err)
 				mlx5_core_warn_once(mdev,
-						    "Faided to modify flow dests for IPsec");
+						    "Failed to modify flow dests for IPsec");
 		}
 		rhashtable_walk_stop(&iter);
 		rhashtable_walk_exit(&iter);
-- 
GitLab


From 9e9ff54e63b4bc4e2436112f008ddb9e3aed4910 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@nvidia.com>
Date: Fri, 9 Jun 2023 12:10:27 -0700
Subject: [PATCH 1405/1806] net/mlx5: IRQ, consolidate irq and affinity mask
 allocation

Consolidate the mlx5_irq and mlx5_irq->mask allocation, to simplify
error flows and to match the dealloctation sequence @irq_release for
symmetry.

Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 33a133c9918cd..653648216730a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -259,8 +259,11 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
 	int err;
 
 	irq = kzalloc(sizeof(*irq), GFP_KERNEL);
-	if (!irq)
+	if (!irq || !zalloc_cpumask_var(&irq->mask, GFP_KERNEL)) {
+		kfree(irq);
 		return ERR_PTR(-ENOMEM);
+	}
+
 	if (!i || !pci_msix_can_alloc_dyn(dev->pdev)) {
 		/* The vector at index 0 is always statically allocated. If
 		 * dynamic irq is not supported all vectors are statically
@@ -297,11 +300,7 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
 		mlx5_core_err(dev, "Failed to request irq. err = %d\n", err);
 		goto err_req_irq;
 	}
-	if (!zalloc_cpumask_var(&irq->mask, GFP_KERNEL)) {
-		mlx5_core_warn(dev, "zalloc_cpumask_var failed\n");
-		err = -ENOMEM;
-		goto err_cpumask;
-	}
+
 	if (af_desc) {
 		cpumask_copy(irq->mask, &af_desc->mask);
 		irq_set_affinity_and_hint(irq->map.virq, irq->mask);
@@ -319,8 +318,6 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
 err_xa:
 	if (af_desc)
 		irq_update_affinity_hint(irq->map.virq, NULL);
-	free_cpumask_var(irq->mask);
-err_cpumask:
 	free_irq(irq->map.virq, &irq->nh);
 err_req_irq:
 #ifdef CONFIG_RFS_ACCEL
@@ -333,6 +330,7 @@ err_irq_rmap:
 	if (i && pci_msix_can_alloc_dyn(dev->pdev))
 		pci_msix_free_irq(dev->pdev, irq->map);
 err_alloc_irq:
+	free_cpumask_var(irq->mask);
 	kfree(irq);
 	return ERR_PTR(err);
 }
-- 
GitLab


From f83e2d8aef4acc044465ad6464f54b6a704ec34b Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Wed, 2 Aug 2023 01:01:14 +0300
Subject: [PATCH 1406/1806] net/mlx5: DR, Fix code indentation

Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index feb307fb3440b..14f6df88b1f9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -336,7 +336,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		if (fte->action.pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_FW) {
 			err = -EINVAL;
 			mlx5dr_err(domain, "FW-owned reformat can't be used in SW rule\n");
-				goto free_actions;
+			goto free_actions;
 		}
 
 		is_decap = fte->action.pkt_reformat->reformat_type ==
-- 
GitLab


From a15e472f8834826668fecba89bd11d2e49530ab0 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Wed, 2 Aug 2023 01:03:31 +0300
Subject: [PATCH 1407/1806] net/mlx5: DR, Remove unneeded local variable

Remove local variable that is already defined outside of
the scope of this block.

Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 54bb0866ed727..5b83da08692d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -1422,7 +1422,6 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn,
 	case DR_ACTION_TYP_TNL_L3_TO_L2:
 	{
 		u8 *hw_actions;
-		int ret;
 
 		hw_actions = kzalloc(DR_ACTION_CACHE_LINE_SIZE, GFP_KERNEL);
 		if (!hw_actions)
-- 
GitLab


From ab943e2efd5da306920fd45387c05c77bf9c3168 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 26 Jun 2023 14:26:17 +0300
Subject: [PATCH 1408/1806] net/mlx5: Remove health syndrome enum duplication

Health syndrome enum values were duplicated in mlx5_ifc and health.c,
the correct place for them is mlx5_ifc.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/health.c  | 36 ++++++-------------
 1 file changed, 11 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 187cb2c464f86..2fb2598b775ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -49,20 +49,6 @@ enum {
 	MAX_MISSES			= 3,
 };
 
-enum {
-	MLX5_HEALTH_SYNDR_FW_ERR		= 0x1,
-	MLX5_HEALTH_SYNDR_IRISC_ERR		= 0x7,
-	MLX5_HEALTH_SYNDR_HW_UNRECOVERABLE_ERR	= 0x8,
-	MLX5_HEALTH_SYNDR_CRC_ERR		= 0x9,
-	MLX5_HEALTH_SYNDR_FETCH_PCI_ERR		= 0xa,
-	MLX5_HEALTH_SYNDR_HW_FTL_ERR		= 0xb,
-	MLX5_HEALTH_SYNDR_ASYNC_EQ_OVERRUN_ERR	= 0xc,
-	MLX5_HEALTH_SYNDR_EQ_ERR		= 0xd,
-	MLX5_HEALTH_SYNDR_EQ_INV		= 0xe,
-	MLX5_HEALTH_SYNDR_FFSER_ERR		= 0xf,
-	MLX5_HEALTH_SYNDR_HIGH_TEMP		= 0x10
-};
-
 enum {
 	MLX5_DROP_HEALTH_WORK,
 };
@@ -357,27 +343,27 @@ static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
 static const char *hsynd_str(u8 synd)
 {
 	switch (synd) {
-	case MLX5_HEALTH_SYNDR_FW_ERR:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_FW_INTERNAL_ERR:
 		return "firmware internal error";
-	case MLX5_HEALTH_SYNDR_IRISC_ERR:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_DEAD_IRISC:
 		return "irisc not responding";
-	case MLX5_HEALTH_SYNDR_HW_UNRECOVERABLE_ERR:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_HW_FATAL_ERR:
 		return "unrecoverable hardware error";
-	case MLX5_HEALTH_SYNDR_CRC_ERR:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_FW_CRC_ERR:
 		return "firmware CRC error";
-	case MLX5_HEALTH_SYNDR_FETCH_PCI_ERR:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_FETCH_PCI_ERR:
 		return "ICM fetch PCI error";
-	case MLX5_HEALTH_SYNDR_HW_FTL_ERR:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PAGE_ERR:
 		return "HW fatal error\n";
-	case MLX5_HEALTH_SYNDR_ASYNC_EQ_OVERRUN_ERR:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_ASYNCHRONOUS_EQ_BUF_OVERRUN:
 		return "async EQ buffer overrun";
-	case MLX5_HEALTH_SYNDR_EQ_ERR:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_IN_ERR:
 		return "EQ error";
-	case MLX5_HEALTH_SYNDR_EQ_INV:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_INV:
 		return "Invalid EQ referenced";
-	case MLX5_HEALTH_SYNDR_FFSER_ERR:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_FFSER_ERR:
 		return "FFSER error";
-	case MLX5_HEALTH_SYNDR_HIGH_TEMP:
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_HIGH_TEMP_ERR:
 		return "High temperature";
 	default:
 		return "unrecognized error";
-- 
GitLab


From 6c8f7c4344876d9984dde2d1f5e9f6676b7a2df5 Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Mon, 10 Jul 2023 18:32:46 -0700
Subject: [PATCH 1409/1806] net/mlx5: Update dead links in Kconfig
 documentation

Point to NVIDIA documentation for device specific information now that the
Mellanox documentation site is deprecated. Refer to kernel documentation
sources for generic information not specific to mlx5 devices.

Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/kconfig.rst             | 14 +++++++-------
 Documentation/networking/xfrm_device.rst           |  1 +
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst
index 43b1f7e87ec47..0a42c3395ffab 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst
@@ -36,7 +36,7 @@ Enabling the driver and kconfig options
 
 **CONFIG_MLX5_CORE_EN_DCB=(y/n)**:
 
-|    Enables `Data Center Bridging (DCB) Support <https://community.mellanox.com/s/article/howto-auto-config-pfc-and-ets-on-connectx-4-via-lldp-dcbx>`_.
+|    Enables `Data Center Bridging (DCB) Support <https://enterprise-support.nvidia.com/s/article/howto-auto-config-pfc-and-ets-on-connectx-4-via-lldp-dcbx>`_.
 
 
 **CONFIG_MLX5_CORE_IPOIB=(y/n)**
@@ -59,12 +59,12 @@ Enabling the driver and kconfig options
 **CONFIG_MLX5_EN_ARFS=(y/n)**
 
 |    Enables Hardware-accelerated receive flow steering (arfs) support, and ntuple filtering.
-|    https://community.mellanox.com/s/article/howto-configure-arfs-on-connectx-4
+|    https://enterprise-support.nvidia.com/s/article/howto-configure-arfs-on-connectx-4
 
 
 **CONFIG_MLX5_EN_IPSEC=(y/n)**
 
-|    Enables `IPSec XFRM cryptography-offload acceleration <https://support.mellanox.com/s/article/ConnectX-6DX-Bluefield-2-IPsec-HW-Full-Offload-Configuration-Guide>`_.
+|    Enables :ref:`IPSec XFRM cryptography-offload acceleration <xfrm_device>`.
 
 
 **CONFIG_MLX5_EN_MACSEC=(y/n)**
@@ -87,8 +87,8 @@ Enabling the driver and kconfig options
 
 |    Ethernet SRIOV E-Switch support in ConnectX NIC. E-Switch provides internal SRIOV packet steering
 |    and switching for the enabled VFs and PF in two available modes:
-|           1) `Legacy SRIOV mode (L2 mac vlan steering based) <https://community.mellanox.com/s/article/howto-configure-sr-iov-for-connectx-4-connectx-5-with-kvm--ethernet-x>`_.
-|           2) `Switchdev mode (eswitch offloads) <https://www.mellanox.com/related-docs/prod_software/ASAP2_Hardware_Offloading_for_vSwitches_User_Manual_v4.4.pdf>`_.
+|           1) `Legacy SRIOV mode (L2 mac vlan steering based) <https://enterprise-support.nvidia.com/s/article/HowTo-Configure-SR-IOV-for-ConnectX-4-ConnectX-5-ConnectX-6-with-KVM-Ethernet>`_.
+|           2) :ref:`Switchdev mode (eswitch offloads) <switchdev>`.
 
 
 **CONFIG_MLX5_FPGA=(y/n)**
@@ -101,13 +101,13 @@ Enabling the driver and kconfig options
 
 **CONFIG_MLX5_INFINIBAND=(y/n/m)** (module mlx5_ib.ko)
 
-|    Provides low-level InfiniBand/RDMA and `RoCE <https://community.mellanox.com/s/article/recommended-network-configuration-examples-for-roce-deployment>`_ support.
+|    Provides low-level InfiniBand/RDMA and `RoCE <https://enterprise-support.nvidia.com/s/article/recommended-network-configuration-examples-for-roce-deployment>`_ support.
 
 
 **CONFIG_MLX5_MPFS=(y/n)**
 
 |    Ethernet Multi-Physical Function Switch (MPFS) support in ConnectX NIC.
-|    MPFs is required for when `Multi-Host <http://www.mellanox.com/page/multihost>`_ configuration is enabled to allow passing
+|    MPFs is required for when `Multi-Host <https://www.nvidia.com/en-us/networking/multi-host/>`_ configuration is enabled to allow passing
 |    user configured unicast MAC addresses to the requesting PF.
 
 
diff --git a/Documentation/networking/xfrm_device.rst b/Documentation/networking/xfrm_device.rst
index 83abdfef4ec35..535077cbeb07d 100644
--- a/Documentation/networking/xfrm_device.rst
+++ b/Documentation/networking/xfrm_device.rst
@@ -1,4 +1,5 @@
 .. SPDX-License-Identifier: GPL-2.0
+.. _xfrm_device:
 
 ===============================================
 XFRM device - offloading the IPsec computations
-- 
GitLab


From ba3d85f008f293ed1b721a4d892b0d55a7d16e9f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Wed, 24 May 2023 19:14:38 +0200
Subject: [PATCH 1410/1806] net/mlx5: Call mlx5_esw_offloads_rep_load/unload()
 for uplink port directly

For uplink port, mlx5_esw_offloads_load/unload_rep() are currently
called. There are 2 check inside, which effectively make the
functions a simple wrappers of mlx5_esw_offloads_rep_load/unload()
for uplink port. So avoid one check and indirection and call
mlx5_esw_offloads_rep_load/unload() for uplink port directly.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 20 ++++++++-----------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 46b8c60ac39a9..c0b1b7b66cffd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2542,11 +2542,9 @@ int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
 	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return 0;
 
-	if (vport_num != MLX5_VPORT_UPLINK) {
-		err = mlx5_esw_offloads_devlink_port_register(esw, vport_num);
-		if (err)
-			return err;
-	}
+	err = mlx5_esw_offloads_devlink_port_register(esw, vport_num);
+	if (err)
+		return err;
 
 	err = mlx5_esw_offloads_rep_load(esw, vport_num);
 	if (err)
@@ -2554,8 +2552,7 @@ int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
 	return err;
 
 load_err:
-	if (vport_num != MLX5_VPORT_UPLINK)
-		mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
+	mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
 	return err;
 }
 
@@ -2566,8 +2563,7 @@ void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
 
 	mlx5_esw_offloads_rep_unload(esw, vport_num);
 
-	if (vport_num != MLX5_VPORT_UPLINK)
-		mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
+	mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
 }
 
 static int esw_set_slave_root_fdb(struct mlx5_core_dev *master,
@@ -3471,7 +3467,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 			vport->info.link_state = MLX5_VPORT_ADMIN_STATE_DOWN;
 
 	/* Uplink vport rep must load first. */
-	err = mlx5_esw_offloads_load_rep(esw, MLX5_VPORT_UPLINK);
+	err = mlx5_esw_offloads_rep_load(esw, MLX5_VPORT_UPLINK);
 	if (err)
 		goto err_uplink;
 
@@ -3482,7 +3478,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	return 0;
 
 err_vports:
-	mlx5_esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
+	mlx5_esw_offloads_rep_unload(esw, MLX5_VPORT_UPLINK);
 err_uplink:
 	esw_offloads_steering_cleanup(esw);
 err_steering_init:
@@ -3520,7 +3516,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 void esw_offloads_disable(struct mlx5_eswitch *esw)
 {
 	mlx5_eswitch_disable_pf_vf_vports(esw);
-	mlx5_esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
+	mlx5_esw_offloads_rep_unload(esw, MLX5_VPORT_UPLINK);
 	esw_set_passing_vport_metadata(esw, false);
 	esw_offloads_steering_cleanup(esw);
 	mapping_destroy(esw->offloads.reg_c0_obj_pool);
-- 
GitLab


From 52020903f35c78e5d147c21f8a1fea1ad7631e3e Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 25 May 2023 11:07:32 +0200
Subject: [PATCH 1411/1806] net/mlx5: Remove VPORT_UPLINK handling from
 devlink_port.c

It is not possible that the functions in devlink_port.c are called for
uplink port. Remove this leftover code.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/esw/devlink_port.c   | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 0313432d50a19..ccf8cdedeab43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -16,8 +16,7 @@ mlx5_esw_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_i
 
 static bool mlx5_esw_devlink_port_supported(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	return vport_num == MLX5_VPORT_UPLINK ||
-	       (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) ||
+	return (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) ||
 	       mlx5_eswitch_is_vf_vport(esw, vport_num) ||
 	       mlx5_core_is_ec_vf_vport(esw->dev, vport_num);
 }
@@ -25,7 +24,6 @@ static bool mlx5_esw_devlink_port_supported(struct mlx5_eswitch *esw, u16 vport_
 static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct mlx5_core_dev *dev = esw->dev;
-	struct devlink_port_attrs attrs = {};
 	struct netdev_phys_item_id ppid = {};
 	struct devlink_port *dl_port;
 	u32 controller_num = 0;
@@ -42,13 +40,7 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16
 	if (external)
 		controller_num = dev->priv.eswitch->offloads.host_number + 1;
 
-	if (vport_num == MLX5_VPORT_UPLINK) {
-		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-		attrs.phys.port_number = pfnum;
-		memcpy(attrs.switch_id.id, ppid.id, ppid.id_len);
-		attrs.switch_id.id_len = ppid.id_len;
-		devlink_port_attrs_set(dl_port, &attrs);
-	} else if (vport_num == MLX5_VPORT_PF) {
+	if (vport_num == MLX5_VPORT_PF) {
 		memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len);
 		dl_port->attrs.switch_id.id_len = ppid.id_len;
 		devlink_port_attrs_pci_pf_set(dl_port, controller_num, pfnum, external);
-- 
GitLab


From df3822f5808de66903a3627bf0694909447faa32 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 26 May 2023 14:23:54 +0200
Subject: [PATCH 1412/1806] net/mlx5: Rename devlink port ops struct for
 PFs/VFs

As this struct is only used for devlink ports created for PF/VF,
add it to the name of the variable to distinguish from the SF related
ops struct.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index ccf8cdedeab43..234fd4c28e797 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -63,7 +63,7 @@ static void mlx5_esw_dl_port_free(struct devlink_port *dl_port)
 	kfree(dl_port);
 }
 
-static const struct devlink_port_ops mlx5_esw_dl_port_ops = {
+static const struct devlink_port_ops mlx5_esw_pf_vf_dl_port_ops = {
 	.port_fn_hw_addr_get = mlx5_devlink_port_fn_hw_addr_get,
 	.port_fn_hw_addr_set = mlx5_devlink_port_fn_hw_addr_set,
 	.port_fn_roce_get = mlx5_devlink_port_fn_roce_get,
@@ -95,7 +95,7 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 	devlink = priv_to_devlink(dev);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num);
 	err = devl_port_register_with_ops(devlink, dl_port, dl_port_index,
-					  &mlx5_esw_dl_port_ops);
+					  &mlx5_esw_pf_vf_dl_port_ops);
 	if (err)
 		goto reg_err;
 
-- 
GitLab


From 95c337cce0e11d06a715da73e6796ade9216637f Mon Sep 17 00:00:00 2001
From: Itamar Gozlan <igozlan@nvidia.com>
Date: Mon, 7 Aug 2023 15:07:26 +0300
Subject: [PATCH 1413/1806] net/mlx5: DR, Supporting inline WQE when possible

In WQE (Work Queue Entry), the two types of data segments memories are
pointers and inline data, where inline data is passed directly as
part of the WQE.
For software steering, the maximal inline size should be less than
2*MLX5_SEND_WQE_BB, i.e., the potential data must fit with the required
inline WQE headers.

Two consecutive blocks (MLX5_SEND_WQE_BB) are not guaranteed to reside
on the same memory page. Hence, writes to MLX5_SEND_WQE_BB should be
done separately, i.e., each MLX5_SEND_WQE_BB  should be obtained using
the mlx5_wq_cyc_get_wqe macro.

Signed-off-by: Itamar Gozlan <igozlan@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/steering/dr_send.c     | 115 ++++++++++++++++--
 1 file changed, 102 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 6fa06ba2d3465..4e8527a724f50 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -52,6 +52,7 @@ struct dr_qp_init_attr {
 	u32 cqn;
 	u32 pdn;
 	u32 max_send_wr;
+	u32 max_send_sge;
 	struct mlx5_uars_page *uar;
 	u8 isolate_vl_tc:1;
 };
@@ -246,6 +247,37 @@ static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne)
 	return err == CQ_POLL_ERR ? err : npolled;
 }
 
+static int dr_qp_get_args_update_send_wqe_size(struct dr_qp_init_attr *attr)
+{
+	return roundup_pow_of_two(sizeof(struct mlx5_wqe_ctrl_seg) +
+				  sizeof(struct mlx5_wqe_flow_update_ctrl_seg) +
+				  sizeof(struct mlx5_wqe_header_modify_argument_update_seg));
+}
+
+/* We calculate for specific RC QP with the required functionality */
+static int dr_qp_calc_rc_send_wqe(struct dr_qp_init_attr *attr)
+{
+	int update_arg_size;
+	int inl_size = 0;
+	int tot_size;
+	int size;
+
+	update_arg_size = dr_qp_get_args_update_send_wqe_size(attr);
+
+	size = sizeof(struct mlx5_wqe_ctrl_seg) +
+	       sizeof(struct mlx5_wqe_raddr_seg);
+	inl_size = size + ALIGN(sizeof(struct mlx5_wqe_inline_seg) +
+				DR_STE_SIZE, 16);
+
+	size += attr->max_send_sge * sizeof(struct mlx5_wqe_data_seg);
+
+	size = max(size, update_arg_size);
+
+	tot_size = max(size, inl_size);
+
+	return ALIGN(tot_size, MLX5_SEND_WQE_BB);
+}
+
 static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 					 struct dr_qp_init_attr *attr)
 {
@@ -253,6 +285,7 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 	u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {};
 	struct mlx5_wq_param wqp;
 	struct mlx5dr_qp *dr_qp;
+	int wqe_size;
 	int inlen;
 	void *qpc;
 	void *in;
@@ -332,6 +365,15 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 	if (err)
 		goto err_in;
 	dr_qp->uar = attr->uar;
+	wqe_size = dr_qp_calc_rc_send_wqe(attr);
+	dr_qp->max_inline_data = min(wqe_size -
+				     (sizeof(struct mlx5_wqe_ctrl_seg) +
+				      sizeof(struct mlx5_wqe_raddr_seg) +
+				      sizeof(struct mlx5_wqe_inline_seg)),
+				     (2 * MLX5_SEND_WQE_BB -
+				      (sizeof(struct mlx5_wqe_ctrl_seg) +
+				       sizeof(struct mlx5_wqe_raddr_seg) +
+				       sizeof(struct mlx5_wqe_inline_seg))));
 
 	return dr_qp;
 
@@ -395,8 +437,48 @@ dr_rdma_handle_flow_access_arg_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl,
 		MLX5_SEND_WQE_DS;
 }
 
+static int dr_set_data_inl_seg(struct mlx5dr_qp *dr_qp,
+			       struct dr_data_seg *data_seg, void *wqe)
+{
+	int inline_header_size = sizeof(struct mlx5_wqe_ctrl_seg) +
+				sizeof(struct mlx5_wqe_raddr_seg) +
+				sizeof(struct mlx5_wqe_inline_seg);
+	struct mlx5_wqe_inline_seg *seg;
+	int left_space;
+	int inl = 0;
+	void *addr;
+	int len;
+	int idx;
+
+	seg = wqe;
+	wqe += sizeof(*seg);
+	addr = (void *)(unsigned long)(data_seg->addr);
+	len  = data_seg->length;
+	inl += len;
+	left_space = MLX5_SEND_WQE_BB - inline_header_size;
+
+	if (likely(len > left_space)) {
+		memcpy(wqe, addr, left_space);
+		len -= left_space;
+		addr += left_space;
+		idx = (dr_qp->sq.pc + 1) & (dr_qp->sq.wqe_cnt - 1);
+		wqe = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx);
+	}
+
+	memcpy(wqe, addr, len);
+
+	if (likely(inl)) {
+		seg->byte_count = cpu_to_be32(inl | MLX5_INLINE_SEG);
+		return DIV_ROUND_UP(inl + sizeof(seg->byte_count),
+				    MLX5_SEND_WQE_DS);
+	} else {
+		return 0;
+	}
+}
+
 static void
-dr_rdma_handle_icm_write_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl,
+dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp,
+				  struct mlx5_wqe_ctrl_seg *wq_ctrl,
 				  u64 remote_addr,
 				  u32 rkey,
 				  struct dr_data_seg *data_seg,
@@ -412,15 +494,17 @@ dr_rdma_handle_icm_write_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl,
 	wq_raddr->reserved = 0;
 
 	wq_dseg = (void *)(wq_raddr + 1);
+	/* WQE ctrl segment + WQE remote addr segment */
+	*size = (sizeof(*wq_ctrl) + sizeof(*wq_raddr)) / MLX5_SEND_WQE_DS;
 
-	wq_dseg->byte_count = cpu_to_be32(data_seg->length);
-	wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
-	wq_dseg->addr = cpu_to_be64(data_seg->addr);
-
-	*size = (sizeof(*wq_ctrl) +    /* WQE ctrl segment */
-		 sizeof(*wq_dseg) +    /* WQE data segment */
-		 sizeof(*wq_raddr)) /  /* WQE remote addr segment */
-		MLX5_SEND_WQE_DS;
+	if (data_seg->send_flags & IB_SEND_INLINE) {
+		*size += dr_set_data_inl_seg(dr_qp, data_seg, wq_dseg);
+	} else {
+		wq_dseg->byte_count = cpu_to_be32(data_seg->length);
+		wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
+		wq_dseg->addr = cpu_to_be64(data_seg->addr);
+		*size += sizeof(*wq_dseg) / MLX5_SEND_WQE_DS;  /* WQE data segment */
+	}
 }
 
 static void dr_set_ctrl_seg(struct mlx5_wqe_ctrl_seg *wq_ctrl,
@@ -451,7 +535,7 @@ static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr,
 	switch (opcode) {
 	case MLX5_OPCODE_RDMA_READ:
 	case MLX5_OPCODE_RDMA_WRITE:
-		dr_rdma_handle_icm_write_segments(wq_ctrl, remote_addr,
+		dr_rdma_handle_icm_write_segments(dr_qp, wq_ctrl, remote_addr,
 						  rkey, data_seg, &size);
 		break;
 	case MLX5_OPCODE_FLOW_TBL_ACCESS:
@@ -572,7 +656,7 @@ static void dr_fill_write_args_segs(struct mlx5dr_send_ring *send_ring,
 	if (send_ring->pending_wqe % send_ring->signal_th == 0)
 		send_info->write.send_flags |= IB_SEND_SIGNALED;
 	else
-		send_info->write.send_flags = 0;
+		send_info->write.send_flags &= ~IB_SEND_SIGNALED;
 }
 
 static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
@@ -596,9 +680,13 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
 	}
 
 	send_ring->pending_wqe++;
+	if (!send_info->write.lkey)
+		send_info->write.send_flags |= IB_SEND_INLINE;
 
 	if (send_ring->pending_wqe % send_ring->signal_th == 0)
 		send_info->write.send_flags |= IB_SEND_SIGNALED;
+	else
+		send_info->write.send_flags &= ~IB_SEND_SIGNALED;
 
 	send_ring->pending_wqe++;
 	send_info->read.length = send_info->write.length;
@@ -608,9 +696,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
 	send_info->read.lkey = send_ring->sync_mr->mkey;
 
 	if (send_ring->pending_wqe % send_ring->signal_th == 0)
-		send_info->read.send_flags = IB_SEND_SIGNALED;
+		send_info->read.send_flags |= IB_SEND_SIGNALED;
 	else
-		send_info->read.send_flags = 0;
+		send_info->read.send_flags &= ~IB_SEND_SIGNALED;
 }
 
 static void dr_fill_data_segs(struct mlx5dr_domain *dmn,
@@ -1257,6 +1345,7 @@ int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn)
 	dmn->send_ring->cq->qp = dmn->send_ring->qp;
 
 	dmn->info.max_send_wr = QUEUE_SIZE;
+	init_attr.max_send_sge = 1;
 	dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data,
 					DR_STE_SIZE);
 
-- 
GitLab


From 7d7c6e8c5fe4e8cceea7f66e93cee1c951670836 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Mon, 14 Aug 2023 15:23:42 +0800
Subject: [PATCH 1414/1806] net/mlx5: Devcom, only use devcom after NULL check
 in mlx5_devcom_send_event()

There is a warning reported by kernel test robot:

smatch warnings:
drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c:264
	mlx5_devcom_send_event() warn: variable dereferenced before
		IS_ERR check devcom (see line 259)

The reason for the warning is that the pointer is used before check, put
the assignment to comp after devcom check to silence the warning.

Fixes: 88d162b47981 ("net/mlx5: Devcom, Infrastructure changes")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202308041028.AkXYDwJ6-lkp@intel.com/
Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
index feb62d9526435..00e67910e3ee9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
@@ -256,14 +256,15 @@ int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom,
 			   int event, int rollback_event,
 			   void *event_data)
 {
-	struct mlx5_devcom_comp *comp = devcom->comp;
 	struct mlx5_devcom_comp_dev *pos;
+	struct mlx5_devcom_comp *comp;
 	int err = 0;
 	void *data;
 
 	if (IS_ERR_OR_NULL(devcom))
 		return -ENODEV;
 
+	comp = devcom->comp;
 	down_write(&comp->sem);
 	list_for_each_entry(pos, &comp->comp_dev_list_head, list) {
 		data = rcu_dereference_protected(pos->data, lockdep_is_held(&comp->sem));
-- 
GitLab


From 7eb6deb3f55678216a6a0e956846c04958093ea5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 21 Aug 2023 12:11:35 -0700
Subject: [PATCH 1415/1806] Revert "pds_core: Fix some kernel-doc comments"

This reverts commit cb39c35783f26892bb1a72b1115c94fa2e77f4c5.
Patch was applied to hastily, the problem is already fixed
in Alex's vfio tree:
https://lore.kernel.org/all/20230821112237.105872b5.alex.williamson@redhat.com/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/auxbus.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index f46efebaaea95..6787a5fae908e 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -8,7 +8,7 @@
 
 /**
  * pds_client_register - Link the client to the firmware
- * @pf:	a pointer to the pdsc structure
+ * @pf_pdev:	ptr to the PF driver struct
  * @devname:	name that includes service into, e.g. pds_core.vDPA
  *
  * Return: positive client ID (ci) on success, or
@@ -53,7 +53,7 @@ EXPORT_SYMBOL_GPL(pds_client_register);
 
 /**
  * pds_client_unregister - Unlink the client from the firmware
- * @pf:	a pointer to the pdsc structure
+ * @pf_pdev:	ptr to the PF driver struct
  * @client_id:	id returned from pds_client_register()
  *
  * Return: 0 on success, or
-- 
GitLab


From 8f8500a247c91e0d263283879166fffbb3329584 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Wed, 16 Aug 2023 12:59:57 +0800
Subject: [PATCH 1416/1806] bpf, cpumap: Use queue_rcu_work() to remove
 unnecessary rcu_barrier()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As for now __cpu_map_entry_replace() uses call_rcu() to wait for the
inflight xdp program to exit the RCU read critical section, and then
launch kworker cpu_map_kthread_stop() to call kthread_stop() to flush
all pending xdp frames or skbs.

But it is unnecessary to use rcu_barrier() in cpu_map_kthread_stop() to
wait for the completion of __cpu_map_entry_free(), because rcu_barrier()
will wait for all pending RCU callbacks and cpu_map_kthread_stop() only
needs to wait for the completion of a specific __cpu_map_entry_free().

So use queue_rcu_work() to replace call_rcu(), schedule_work() and
rcu_barrier(). queue_rcu_work() will queue a __cpu_map_entry_free()
kworker after a RCU grace period. Because __cpu_map_entry_free() is
running in a kworker context, so it is OK to do all of these freeing
procedures include kthread_stop() in it.

After the update, there is no need to do reference-counting for
bpf_cpu_map_entry, because bpf_cpu_map_entry is freed directly in
__cpu_map_entry_free(), so just remove it.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20230816045959.358059-2-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/cpumap.c | 96 +++++++++++++--------------------------------
 1 file changed, 27 insertions(+), 69 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index ef28c64f1eb13..93fbd3e5079e4 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -68,11 +68,8 @@ struct bpf_cpu_map_entry {
 	struct bpf_cpumap_val value;
 	struct bpf_prog *prog;
 
-	atomic_t refcnt; /* Control when this struct can be free'ed */
-	struct rcu_head rcu;
-
-	struct work_struct kthread_stop_wq;
 	struct completion kthread_running;
+	struct rcu_work free_work;
 };
 
 struct bpf_cpu_map {
@@ -117,11 +114,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 	return &cmap->map;
 }
 
-static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
-{
-	atomic_inc(&rcpu->refcnt);
-}
-
 static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 {
 	/* The tear-down procedure should have made sure that queue is
@@ -142,35 +134,6 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 	}
 }
 
-static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
-{
-	if (atomic_dec_and_test(&rcpu->refcnt)) {
-		if (rcpu->prog)
-			bpf_prog_put(rcpu->prog);
-		/* The queue should be empty at this point */
-		__cpu_map_ring_cleanup(rcpu->queue);
-		ptr_ring_cleanup(rcpu->queue, NULL);
-		kfree(rcpu->queue);
-		kfree(rcpu);
-	}
-}
-
-/* called from workqueue, to workaround syscall using preempt_disable */
-static void cpu_map_kthread_stop(struct work_struct *work)
-{
-	struct bpf_cpu_map_entry *rcpu;
-
-	rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
-
-	/* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
-	 * as it waits until all in-flight call_rcu() callbacks complete.
-	 */
-	rcu_barrier();
-
-	/* kthread_stop will wake_up_process and wait for it to complete */
-	kthread_stop(rcpu->kthread);
-}
-
 static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
 				     struct list_head *listp,
 				     struct xdp_cpumap_stats *stats)
@@ -395,7 +358,6 @@ static int cpu_map_kthread_run(void *data)
 	}
 	__set_current_state(TASK_RUNNING);
 
-	put_cpu_map_entry(rcpu);
 	return 0;
 }
 
@@ -472,9 +434,6 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 	if (IS_ERR(rcpu->kthread))
 		goto free_prog;
 
-	get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
-	get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
-
 	/* Make sure kthread runs on a single CPU */
 	kthread_bind(rcpu->kthread, cpu);
 	wake_up_process(rcpu->kthread);
@@ -501,40 +460,40 @@ free_rcu:
 	return NULL;
 }
 
-static void __cpu_map_entry_free(struct rcu_head *rcu)
+static void __cpu_map_entry_free(struct work_struct *work)
 {
 	struct bpf_cpu_map_entry *rcpu;
 
 	/* This cpu_map_entry have been disconnected from map and one
-	 * RCU grace-period have elapsed.  Thus, XDP cannot queue any
+	 * RCU grace-period have elapsed. Thus, XDP cannot queue any
 	 * new packets and cannot change/set flush_needed that can
 	 * find this entry.
 	 */
-	rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
+	rcpu = container_of(to_rcu_work(work), struct bpf_cpu_map_entry, free_work);
+
+	/* kthread_stop will wake_up_process and wait for it to complete.
+	 * cpu_map_kthread_run() makes sure the pointer ring is empty
+	 * before exiting.
+	 */
+	kthread_stop(rcpu->kthread);
 
+	if (rcpu->prog)
+		bpf_prog_put(rcpu->prog);
+	/* The queue should be empty at this point */
+	__cpu_map_ring_cleanup(rcpu->queue);
+	ptr_ring_cleanup(rcpu->queue, NULL);
+	kfree(rcpu->queue);
 	free_percpu(rcpu->bulkq);
-	/* Cannot kthread_stop() here, last put free rcpu resources */
-	put_cpu_map_entry(rcpu);
+	kfree(rcpu);
 }
 
-/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
- * ensure any driver rcu critical sections have completed, but this
- * does not guarantee a flush has happened yet. Because driver side
- * rcu_read_lock/unlock only protects the running XDP program.  The
- * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
- * pending flush op doesn't fail.
- *
- * The bpf_cpu_map_entry is still used by the kthread, and there can
- * still be pending packets (in queue and percpu bulkq).  A refcnt
- * makes sure to last user (kthread_stop vs. call_rcu) free memory
- * resources.
- *
- * The rcu callback __cpu_map_entry_free flush remaining packets in
- * percpu bulkq to queue.  Due to caller map_delete_elem() disable
- * preemption, cannot call kthread_stop() to make sure queue is empty.
- * Instead a work_queue is started for stopping kthread,
- * cpu_map_kthread_stop, which waits for an RCU grace period before
- * stopping kthread, emptying the queue.
+/* After the xchg of the bpf_cpu_map_entry pointer, we need to make sure the old
+ * entry is no longer in use before freeing. We use queue_rcu_work() to call
+ * __cpu_map_entry_free() in a separate workqueue after waiting for an RCU grace
+ * period. This means that (a) all pending enqueue and flush operations have
+ * completed (because of the RCU callback), and (b) we are in a workqueue
+ * context where we can stop the kthread and wait for it to exit before freeing
+ * everything.
  */
 static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
 				    u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
@@ -543,9 +502,8 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
 
 	old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu)));
 	if (old_rcpu) {
-		call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
-		INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
-		schedule_work(&old_rcpu->kthread_stop_wq);
+		INIT_RCU_WORK(&old_rcpu->free_work, __cpu_map_entry_free);
+		queue_rcu_work(system_wq, &old_rcpu->free_work);
 	}
 }
 
@@ -557,7 +515,7 @@ static long cpu_map_delete_elem(struct bpf_map *map, void *key)
 	if (key_cpu >= map->max_entries)
 		return -EINVAL;
 
-	/* notice caller map_delete_elem() use preempt_disable() */
+	/* notice caller map_delete_elem() uses rcu_read_lock() */
 	__cpu_map_entry_replace(cmap, key_cpu, NULL);
 	return 0;
 }
-- 
GitLab


From c2e42ddf26cad03ea92400c88b024e8ce1601dff Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Wed, 16 Aug 2023 12:59:58 +0800
Subject: [PATCH 1417/1806] bpf, cpumask: Clean up bpf_cpu_map_entry directly
 in cpu_map_free
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After synchronous_rcu(), both the dettached XDP program and
xdp_do_flush() are completed, and the only user of bpf_cpu_map_entry
will be cpu_map_kthread_run(), so instead of calling
__cpu_map_entry_replace() to stop kthread and cleanup entry after a RCU
grace period, do these things directly.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20230816045959.358059-3-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/cpumap.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 93fbd3e5079e4..e42a1bdb7f536 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -566,16 +566,15 @@ static void cpu_map_free(struct bpf_map *map)
 	/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
 	 * so the bpf programs (can be more than one that used this map) were
 	 * disconnected from events. Wait for outstanding critical sections in
-	 * these programs to complete. The rcu critical section only guarantees
-	 * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
-	 * It does __not__ ensure pending flush operations (if any) are
-	 * complete.
+	 * these programs to complete. synchronize_rcu() below not only
+	 * guarantees no further "XDP/bpf-side" reads against
+	 * bpf_cpu_map->cpu_map, but also ensure pending flush operations
+	 * (if any) are completed.
 	 */
-
 	synchronize_rcu();
 
-	/* For cpu_map the remote CPUs can still be using the entries
-	 * (struct bpf_cpu_map_entry).
+	/* The only possible user of bpf_cpu_map_entry is
+	 * cpu_map_kthread_run().
 	 */
 	for (i = 0; i < cmap->map.max_entries; i++) {
 		struct bpf_cpu_map_entry *rcpu;
@@ -584,8 +583,8 @@ static void cpu_map_free(struct bpf_map *map)
 		if (!rcpu)
 			continue;
 
-		/* bq flush and cleanup happens after RCU grace-period */
-		__cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
+		/* Stop kthread and cleanup entry directly */
+		__cpu_map_entry_free(&rcpu->free_work.work);
 	}
 	bpf_map_area_free(cmap->cpu_map);
 	bpf_map_area_free(cmap);
-- 
GitLab


From 34f6e38f58db9a94718c273edc9ca3fc8b4dba5f Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 18 Aug 2023 18:01:11 +0900
Subject: [PATCH 1418/1806] samples/bpf: fix warning with ignored-attributes

Currently, compiling the bpf programs will result the warning with the
ignored attribute as follows. This commit fixes the warning by adding
cf-protection option.

    In file included from ./arch/x86/include/asm/linkage.h:6:
    ./arch/x86/include/asm/ibt.h:77:8: warning: 'nocf_check' attribute ignored; use -fcf-protection to enable the attribute [-Wignored-attributes]
    extern __noendbr u64 ibt_save(bool disable);
           ^
    ./arch/x86/include/asm/ibt.h:32:34: note: expanded from macro '__noendbr'
                                       ^

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Link: https://lore.kernel.org/r/20230818090119.477441-2-danieltimlee@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 595b98d825cee..b32cb8a62335e 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -440,7 +440,7 @@ $(obj)/%.o: $(src)/%.c
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
 		-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
-		-fno-asynchronous-unwind-tables \
+		-fno-asynchronous-unwind-tables -fcf-protection \
 		-I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \
 		-O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \
 		$(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \
-- 
GitLab


From e7e6c774f5d40244444f23b8c49dac2ded158d8c Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 18 Aug 2023 18:01:12 +0900
Subject: [PATCH 1419/1806] samples/bpf: convert to vmlinux.h with tracing
 programs

This commit replaces separate headers with a single vmlinux.h to
tracing programs. Thanks to that, we no longer need to define the
argument structure for tracing programs directly. For example, argument
for the sched_switch tracpepoint (sched_switch_args) can be replaced
with the vmlinux.h provided trace_event_raw_sched_switch.

Additional defines have been added to the BPF program either directly
or through the inclusion of net_shared.h. Defined values are
PERF_MAX_STACK_DEPTH, IFNAMSIZ constants and __stringify() macro. This
change enables the BPF program to access internal structures with BTF
generated "vmlinux.h" header.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Link: https://lore.kernel.org/r/20230818090119.477441-3-danieltimlee@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/net_shared.h           |  2 ++
 samples/bpf/offwaketime_kern.c     | 21 ++++++---------------
 samples/bpf/spintest_kern.c        | 10 ++++++----
 samples/bpf/test_overhead_tp.bpf.c | 29 ++---------------------------
 samples/bpf/tracex1_kern.c         |  5 ++---
 samples/bpf/tracex3_kern.c         |  4 +---
 samples/bpf/tracex4_kern.c         |  3 +--
 samples/bpf/tracex5_kern.c         |  7 +++----
 samples/bpf/tracex6_kern.c         |  3 +--
 samples/bpf/tracex7_kern.c         |  3 +--
 10 files changed, 25 insertions(+), 62 deletions(-)

diff --git a/samples/bpf/net_shared.h b/samples/bpf/net_shared.h
index e9429af9aa44e..88cc52461c986 100644
--- a/samples/bpf/net_shared.h
+++ b/samples/bpf/net_shared.h
@@ -17,6 +17,8 @@
 #define TC_ACT_OK		0
 #define TC_ACT_SHOT		2
 
+#define IFNAMSIZ 16
+
 #if defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && \
 	__BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define bpf_ntohs(x)		__builtin_bswap16(x)
diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c
index 23f12b47e9e57..8e51058111783 100644
--- a/samples/bpf/offwaketime_kern.c
+++ b/samples/bpf/offwaketime_kern.c
@@ -4,14 +4,15 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
-#include <uapi/linux/bpf.h>
-#include <uapi/linux/ptrace.h>
-#include <uapi/linux/perf_event.h>
+#include "vmlinux.h"
 #include <linux/version.h>
-#include <linux/sched.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+#ifndef PERF_MAX_STACK_DEPTH
+#define PERF_MAX_STACK_DEPTH         127
+#endif
+
 #define _(P)                                                                   \
 	({                                                                     \
 		typeof(P) val;                                                 \
@@ -111,18 +112,8 @@ static inline int update_counts(void *ctx, u32 pid, u64 delta)
 
 #if 1
 /* taken from /sys/kernel/tracing/events/sched/sched_switch/format */
-struct sched_switch_args {
-	unsigned long long pad;
-	char prev_comm[TASK_COMM_LEN];
-	int prev_pid;
-	int prev_prio;
-	long long prev_state;
-	char next_comm[TASK_COMM_LEN];
-	int next_pid;
-	int next_prio;
-};
 SEC("tracepoint/sched/sched_switch")
-int oncpu(struct sched_switch_args *ctx)
+int oncpu(struct trace_event_raw_sched_switch *ctx)
 {
 	/* record previous thread sleep time */
 	u32 pid = ctx->prev_pid;
diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c
index 455da77319d9a..15740b16a3f7a 100644
--- a/samples/bpf/spintest_kern.c
+++ b/samples/bpf/spintest_kern.c
@@ -4,14 +4,15 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
+#include "vmlinux.h"
 #include <linux/version.h>
-#include <uapi/linux/bpf.h>
-#include <uapi/linux/perf_event.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+#ifndef PERF_MAX_STACK_DEPTH
+#define PERF_MAX_STACK_DEPTH         127
+#endif
+
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, long);
@@ -60,6 +61,7 @@ SEC("kprobe/_raw_spin_lock_irq")PROG(p11)
 SEC("kprobe/_raw_spin_trylock")PROG(p12)
 SEC("kprobe/_raw_spin_lock")PROG(p13)
 SEC("kprobe/_raw_spin_lock_bh")PROG(p14)
+
 /* and to inner bpf helpers */
 SEC("kprobe/htab_map_update_elem")PROG(p15)
 SEC("kprobe/__htab_percpu_map_update_elem")PROG(p16)
diff --git a/samples/bpf/test_overhead_tp.bpf.c b/samples/bpf/test_overhead_tp.bpf.c
index 8b498328e9618..5dc08b5879788 100644
--- a/samples/bpf/test_overhead_tp.bpf.c
+++ b/samples/bpf/test_overhead_tp.bpf.c
@@ -8,40 +8,15 @@
 #include <bpf/bpf_helpers.h>
 
 /* from /sys/kernel/tracing/events/task/task_rename/format */
-struct task_rename {
-	__u64 pad;
-	__u32 pid;
-	char oldcomm[TASK_COMM_LEN];
-	char newcomm[TASK_COMM_LEN];
-	__u16 oom_score_adj;
-};
 SEC("tracepoint/task/task_rename")
-int prog(struct task_rename *ctx)
+int prog(struct trace_event_raw_task_rename *ctx)
 {
 	return 0;
 }
 
 /* from /sys/kernel/tracing/events/fib/fib_table_lookup/format */
-struct fib_table_lookup {
-	__u64 pad;
-	__u32 tb_id;
-	int err;
-	int oif;
-	int iif;
-	__u8 proto;
-	__u8 tos;
-	__u8 scope;
-	__u8 flags;
-	__u8 src[4];
-	__u8 dst[4];
-	__u8 gw4[4];
-	__u8 gw6[16];
-	__u16 sport;
-	__u16 dport;
-	char name[16];
-};
 SEC("tracepoint/fib/fib_table_lookup")
-int prog2(struct fib_table_lookup *ctx)
+int prog2(struct trace_event_raw_fib_table_lookup *ctx)
 {
 	return 0;
 }
diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c
index ef30d2b353b0f..bb78bdbffa87a 100644
--- a/samples/bpf/tracex1_kern.c
+++ b/samples/bpf/tracex1_kern.c
@@ -4,9 +4,8 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <uapi/linux/bpf.h>
+#include "vmlinux.h"
+#include "net_shared.h"
 #include <linux/version.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c
index bde6591cb20c5..7cc60f10d2e54 100644
--- a/samples/bpf/tracex3_kern.c
+++ b/samples/bpf/tracex3_kern.c
@@ -4,10 +4,8 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
+#include "vmlinux.h"
 #include <linux/version.h>
-#include <uapi/linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4_kern.c
index eb0f8fdd14bf5..ca826750901ae 100644
--- a/samples/bpf/tracex4_kern.c
+++ b/samples/bpf/tracex4_kern.c
@@ -4,9 +4,8 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
-#include <linux/ptrace.h>
+#include "vmlinux.h"
 #include <linux/version.h>
-#include <uapi/linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c
index 64a1f7550d7e9..8cd697ee70473 100644
--- a/samples/bpf/tracex5_kern.c
+++ b/samples/bpf/tracex5_kern.c
@@ -4,15 +4,14 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
-#include <linux/ptrace.h>
+#include "vmlinux.h"
+#include "syscall_nrs.h"
 #include <linux/version.h>
-#include <uapi/linux/bpf.h>
-#include <uapi/linux/seccomp.h>
 #include <uapi/linux/unistd.h>
-#include "syscall_nrs.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+#define __stringify(x) #x
 #define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F
 
 struct {
diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c
index acad5712d8b4f..6ad82e68f9986 100644
--- a/samples/bpf/tracex6_kern.c
+++ b/samples/bpf/tracex6_kern.c
@@ -1,6 +1,5 @@
-#include <linux/ptrace.h>
+#include "vmlinux.h"
 #include <linux/version.h>
-#include <uapi/linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
 struct {
diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7_kern.c
index c5a92df8ac311..ab8d6704a5a43 100644
--- a/samples/bpf/tracex7_kern.c
+++ b/samples/bpf/tracex7_kern.c
@@ -1,5 +1,4 @@
-#include <uapi/linux/ptrace.h>
-#include <uapi/linux/bpf.h>
+#include "vmlinux.h"
 #include <linux/version.h>
 #include <bpf/bpf_helpers.h>
 
-- 
GitLab


From 4a0ee78890699706f59cc9bdf8283ecaa4e0a141 Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 18 Aug 2023 18:01:13 +0900
Subject: [PATCH 1420/1806] samples/bpf: unify bpf program suffix to .bpf with
 tracing programs

Currently, BPF programs typically have a suffix of .bpf.c. However,
some programs still utilize a mixture of _kern.c suffix alongside the
naming convention. In order to achieve consistency in the naming of
these programs, this commit unifies the inconsistency in the naming
convention of BPF kernel programs.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Link: https://lore.kernel.org/r/20230818090119.477441-4-danieltimlee@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile                           | 18 +++++++++---------
 .../{offwaketime_kern.c => offwaketime.bpf.c}  |  0
 samples/bpf/offwaketime_user.c                 |  2 +-
 .../bpf/{spintest_kern.c => spintest.bpf.c}    |  0
 samples/bpf/spintest_user.c                    |  2 +-
 samples/bpf/{tracex1_kern.c => tracex1.bpf.c}  |  0
 samples/bpf/tracex1_user.c                     |  2 +-
 samples/bpf/{tracex3_kern.c => tracex3.bpf.c}  |  0
 samples/bpf/tracex3_user.c                     |  2 +-
 samples/bpf/{tracex4_kern.c => tracex4.bpf.c}  |  0
 samples/bpf/tracex4_user.c                     |  2 +-
 samples/bpf/{tracex5_kern.c => tracex5.bpf.c}  |  0
 samples/bpf/tracex5_user.c                     |  2 +-
 samples/bpf/{tracex6_kern.c => tracex6.bpf.c}  |  0
 samples/bpf/tracex6_user.c                     |  2 +-
 samples/bpf/{tracex7_kern.c => tracex7.bpf.c}  |  0
 samples/bpf/tracex7_user.c                     |  2 +-
 17 files changed, 17 insertions(+), 17 deletions(-)
 rename samples/bpf/{offwaketime_kern.c => offwaketime.bpf.c} (100%)
 rename samples/bpf/{spintest_kern.c => spintest.bpf.c} (100%)
 rename samples/bpf/{tracex1_kern.c => tracex1.bpf.c} (100%)
 rename samples/bpf/{tracex3_kern.c => tracex3.bpf.c} (100%)
 rename samples/bpf/{tracex4_kern.c => tracex4.bpf.c} (100%)
 rename samples/bpf/{tracex5_kern.c => tracex5.bpf.c} (100%)
 rename samples/bpf/{tracex6_kern.c => tracex6.bpf.c} (100%)
 rename samples/bpf/{tracex7_kern.c => tracex7.bpf.c} (100%)

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index b32cb8a62335e..f90bcd3696bdf 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -124,21 +124,21 @@ always-y := $(tprogs-y)
 always-y += sockex1_kern.o
 always-y += sockex2_kern.o
 always-y += sockex3_kern.o
-always-y += tracex1_kern.o
+always-y += tracex1.bpf.o
 always-y += tracex2.bpf.o
-always-y += tracex3_kern.o
-always-y += tracex4_kern.o
-always-y += tracex5_kern.o
-always-y += tracex6_kern.o
-always-y += tracex7_kern.o
+always-y += tracex3.bpf.o
+always-y += tracex4.bpf.o
+always-y += tracex5.bpf.o
+always-y += tracex6.bpf.o
+always-y += tracex7.bpf.o
 always-y += sock_flags.bpf.o
 always-y += test_probe_write_user.bpf.o
 always-y += trace_output.bpf.o
 always-y += tcbpf1_kern.o
 always-y += tc_l2_redirect_kern.o
 always-y += lathist_kern.o
-always-y += offwaketime_kern.o
-always-y += spintest_kern.o
+always-y += offwaketime.bpf.o
+always-y += spintest.bpf.o
 always-y += map_perf_test.bpf.o
 always-y += test_overhead_tp.bpf.o
 always-y += test_overhead_raw_tp.bpf.o
@@ -333,7 +333,7 @@ $(obj)/xdp_redirect_user.o: $(obj)/xdp_redirect.skel.h
 $(obj)/xdp_monitor_user.o: $(obj)/xdp_monitor.skel.h
 $(obj)/xdp_router_ipv4_user.o: $(obj)/xdp_router_ipv4.skel.h
 
-$(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
+$(obj)/tracex5.bpf.o: $(obj)/syscall_nrs.h
 $(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
 $(obj)/hbm.o: $(src)/hbm.h
 $(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime.bpf.c
similarity index 100%
rename from samples/bpf/offwaketime_kern.c
rename to samples/bpf/offwaketime.bpf.c
diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c
index b6eedcb98fb9a..5557b53936424 100644
--- a/samples/bpf/offwaketime_user.c
+++ b/samples/bpf/offwaketime_user.c
@@ -105,7 +105,7 @@ int main(int argc, char **argv)
 		return 2;
 	}
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
 	obj = bpf_object__open_file(filename, NULL);
 	if (libbpf_get_error(obj)) {
 		fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest.bpf.c
similarity index 100%
rename from samples/bpf/spintest_kern.c
rename to samples/bpf/spintest.bpf.c
diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c
index aadac14f748a9..8c77600776fb4 100644
--- a/samples/bpf/spintest_user.c
+++ b/samples/bpf/spintest_user.c
@@ -23,7 +23,7 @@ int main(int ac, char **argv)
 		return 2;
 	}
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
 	obj = bpf_object__open_file(filename, NULL);
 	if (libbpf_get_error(obj)) {
 		fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1.bpf.c
similarity index 100%
rename from samples/bpf/tracex1_kern.c
rename to samples/bpf/tracex1.bpf.c
diff --git a/samples/bpf/tracex1_user.c b/samples/bpf/tracex1_user.c
index 9d4adb7fd8341..8c3d9043a2b6b 100644
--- a/samples/bpf/tracex1_user.c
+++ b/samples/bpf/tracex1_user.c
@@ -12,7 +12,7 @@ int main(int ac, char **argv)
 	char filename[256];
 	FILE *f;
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
 	obj = bpf_object__open_file(filename, NULL);
 	if (libbpf_get_error(obj)) {
 		fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3.bpf.c
similarity index 100%
rename from samples/bpf/tracex3_kern.c
rename to samples/bpf/tracex3.bpf.c
diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c
index d5eebace31e69..1002eb0323b40 100644
--- a/samples/bpf/tracex3_user.c
+++ b/samples/bpf/tracex3_user.c
@@ -125,7 +125,7 @@ int main(int ac, char **argv)
 		}
 	}
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
 	obj = bpf_object__open_file(filename, NULL);
 	if (libbpf_get_error(obj)) {
 		fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4.bpf.c
similarity index 100%
rename from samples/bpf/tracex4_kern.c
rename to samples/bpf/tracex4.bpf.c
diff --git a/samples/bpf/tracex4_user.c b/samples/bpf/tracex4_user.c
index dee8f0a091ba6..a5145ad72cbf6 100644
--- a/samples/bpf/tracex4_user.c
+++ b/samples/bpf/tracex4_user.c
@@ -53,7 +53,7 @@ int main(int ac, char **argv)
 	char filename[256];
 	int map_fd, j = 0;
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
 	obj = bpf_object__open_file(filename, NULL);
 	if (libbpf_get_error(obj)) {
 		fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5.bpf.c
similarity index 100%
rename from samples/bpf/tracex5_kern.c
rename to samples/bpf/tracex5.bpf.c
diff --git a/samples/bpf/tracex5_user.c b/samples/bpf/tracex5_user.c
index 9d7d79f0d47d2..7e2d8397fb98a 100644
--- a/samples/bpf/tracex5_user.c
+++ b/samples/bpf/tracex5_user.c
@@ -42,7 +42,7 @@ int main(int ac, char **argv)
 	char filename[256];
 	FILE *f;
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
 	obj = bpf_object__open_file(filename, NULL);
 	if (libbpf_get_error(obj)) {
 		fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6.bpf.c
similarity index 100%
rename from samples/bpf/tracex6_kern.c
rename to samples/bpf/tracex6.bpf.c
diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c
index 8e83bf2a84a46..ae811ac83bc22 100644
--- a/samples/bpf/tracex6_user.c
+++ b/samples/bpf/tracex6_user.c
@@ -180,7 +180,7 @@ int main(int argc, char **argv)
 	char filename[256];
 	int i = 0;
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
 	obj = bpf_object__open_file(filename, NULL);
 	if (libbpf_get_error(obj)) {
 		fprintf(stderr, "ERROR: opening BPF object file failed\n");
diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7.bpf.c
similarity index 100%
rename from samples/bpf/tracex7_kern.c
rename to samples/bpf/tracex7.bpf.c
diff --git a/samples/bpf/tracex7_user.c b/samples/bpf/tracex7_user.c
index 8be7ce18d3ba0..b10b5e03a226e 100644
--- a/samples/bpf/tracex7_user.c
+++ b/samples/bpf/tracex7_user.c
@@ -19,7 +19,7 @@ int main(int argc, char **argv)
 		return 0;
 	}
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
 	obj = bpf_object__open_file(filename, NULL);
 	if (libbpf_get_error(obj)) {
 		fprintf(stderr, "ERROR: opening BPF object file failed\n");
-- 
GitLab


From 02dabc247ad68b41758bf39f11e2d682b8b32dd7 Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 18 Aug 2023 18:01:14 +0900
Subject: [PATCH 1421/1806] samples/bpf: fix symbol mismatch by compiler
 optimization

Currently, multiple kprobe programs are suffering from symbol mismatch
due to compiler optimization. These optimizations might induce
additional suffix to the symbol name such as '.isra' or '.constprop'.

    # egrep ' finish_task_switch| __netif_receive_skb_core' /proc/kallsyms
    ffffffff81135e50 t finish_task_switch.isra.0
    ffffffff81dd36d0 t __netif_receive_skb_core.constprop.0
    ffffffff8205cc0e t finish_task_switch.isra.0.cold
    ffffffff820b1aba t __netif_receive_skb_core.constprop.0.cold

To avoid this, this commit replaces the original kprobe section to
kprobe.multi in order to match symbol with wildcard characters. Here,
asterisk is used for avoiding symbol mismatch.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Link: https://lore.kernel.org/r/20230818090119.477441-5-danieltimlee@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/offwaketime.bpf.c | 2 +-
 samples/bpf/tracex1.bpf.c     | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/samples/bpf/offwaketime.bpf.c b/samples/bpf/offwaketime.bpf.c
index 8e51058111783..3200a0f449690 100644
--- a/samples/bpf/offwaketime.bpf.c
+++ b/samples/bpf/offwaketime.bpf.c
@@ -118,7 +118,7 @@ int oncpu(struct trace_event_raw_sched_switch *ctx)
 	/* record previous thread sleep time */
 	u32 pid = ctx->prev_pid;
 #else
-SEC("kprobe/finish_task_switch")
+SEC("kprobe.multi/finish_task_switch*")
 int oncpu(struct pt_regs *ctx)
 {
 	struct task_struct *p = (void *) PT_REGS_PARM1(ctx);
diff --git a/samples/bpf/tracex1.bpf.c b/samples/bpf/tracex1.bpf.c
index bb78bdbffa87a..f3be14a03964d 100644
--- a/samples/bpf/tracex1.bpf.c
+++ b/samples/bpf/tracex1.bpf.c
@@ -22,11 +22,12 @@
  * Number of arguments and their positions can change, etc.
  * In such case this bpf+kprobe example will no longer be meaningful
  */
-SEC("kprobe/__netif_receive_skb_core")
+SEC("kprobe.multi/__netif_receive_skb_core*")
 int bpf_prog1(struct pt_regs *ctx)
 {
 	/* attaches to kprobe __netif_receive_skb_core,
 	 * looks for packets on loobpack device and prints them
+	 * (wildcard is used for avoiding symbol mismatch due to optimization)
 	 */
 	char devname[IFNAMSIZ];
 	struct net_device *dev;
-- 
GitLab


From 11430421b440427e10dfb4bd2bdc418fab0ff166 Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 18 Aug 2023 18:01:15 +0900
Subject: [PATCH 1422/1806] samples/bpf: make tracing programs to be more CO-RE
 centric

The existing tracing programs have been developed for a considerable
period of time and, as a result, do not properly incorporate the
features of the current libbpf, such as CO-RE. This is evident in
frequent usage of functions like PT_REGS* and the persistence of "hack"
methods using underscore-style bpf_probe_read_kernel from the past.

These programs are far behind the current level of libbpf and can
potentially confuse users. Therefore, this commit aims to convert the
outdated BPF programs to be more CO-RE centric.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Link: https://lore.kernel.org/r/20230818090119.477441-6-danieltimlee@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/offwaketime.bpf.c          | 18 +++++-------------
 samples/bpf/test_overhead_kprobe.bpf.c | 20 +++++++-------------
 samples/bpf/tracex1.bpf.c              | 17 +++++------------
 samples/bpf/tracex5.bpf.c              |  5 +++--
 4 files changed, 20 insertions(+), 40 deletions(-)

diff --git a/samples/bpf/offwaketime.bpf.c b/samples/bpf/offwaketime.bpf.c
index 3200a0f449690..4a65ba76c1b13 100644
--- a/samples/bpf/offwaketime.bpf.c
+++ b/samples/bpf/offwaketime.bpf.c
@@ -8,18 +8,12 @@
 #include <linux/version.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
 
 #ifndef PERF_MAX_STACK_DEPTH
 #define PERF_MAX_STACK_DEPTH         127
 #endif
 
-#define _(P)                                                                   \
-	({                                                                     \
-		typeof(P) val;                                                 \
-		bpf_probe_read_kernel(&val, sizeof(val), &(P));                \
-		val;                                                           \
-	})
-
 #define MINBLOCK_US	1
 #define MAX_ENTRIES	10000
 
@@ -68,11 +62,9 @@ struct {
 SEC("kprobe/try_to_wake_up")
 int waker(struct pt_regs *ctx)
 {
-	struct task_struct *p = (void *) PT_REGS_PARM1(ctx);
+	struct task_struct *p = (void *)PT_REGS_PARM1_CORE(ctx);
+	u32 pid = BPF_CORE_READ(p, pid);
 	struct wokeby_t woke;
-	u32 pid;
-
-	pid = _(p->pid);
 
 	bpf_get_current_comm(&woke.name, sizeof(woke.name));
 	woke.ret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS);
@@ -121,9 +113,9 @@ int oncpu(struct trace_event_raw_sched_switch *ctx)
 SEC("kprobe.multi/finish_task_switch*")
 int oncpu(struct pt_regs *ctx)
 {
-	struct task_struct *p = (void *) PT_REGS_PARM1(ctx);
+	struct task_struct *p = (void *)PT_REGS_PARM1_CORE(ctx);
 	/* record previous thread sleep time */
-	u32 pid = _(p->pid);
+	u32 pid = BPF_CORE_READ(p, pid);
 #endif
 	u64 delta, ts, *tsp;
 
diff --git a/samples/bpf/test_overhead_kprobe.bpf.c b/samples/bpf/test_overhead_kprobe.bpf.c
index c3528731e0e1c..668cf5259c605 100644
--- a/samples/bpf/test_overhead_kprobe.bpf.c
+++ b/samples/bpf/test_overhead_kprobe.bpf.c
@@ -8,13 +8,7 @@
 #include <linux/version.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-
-#define _(P)                                                                   \
-	({                                                                     \
-		typeof(P) val = 0;                                             \
-		bpf_probe_read_kernel(&val, sizeof(val), &(P));                \
-		val;                                                           \
-	})
+#include <bpf/bpf_core_read.h>
 
 SEC("kprobe/__set_task_comm")
 int prog(struct pt_regs *ctx)
@@ -26,14 +20,14 @@ int prog(struct pt_regs *ctx)
 	u16 oom_score_adj;
 	u32 pid;
 
-	tsk = (void *)PT_REGS_PARM1(ctx);
+	tsk = (void *)PT_REGS_PARM1_CORE(ctx);
 
-	pid = _(tsk->pid);
-	bpf_probe_read_kernel_str(oldcomm, sizeof(oldcomm), &tsk->comm);
-	bpf_probe_read_kernel_str(newcomm, sizeof(newcomm),
+	pid = BPF_CORE_READ(tsk, pid);
+	bpf_core_read_str(oldcomm, sizeof(oldcomm), &tsk->comm);
+	bpf_core_read_str(newcomm, sizeof(newcomm),
 				  (void *)PT_REGS_PARM2(ctx));
-	signal = _(tsk->signal);
-	oom_score_adj = _(signal->oom_score_adj);
+	signal = BPF_CORE_READ(tsk, signal);
+	oom_score_adj = BPF_CORE_READ(signal, oom_score_adj);
 	return 0;
 }
 
diff --git a/samples/bpf/tracex1.bpf.c b/samples/bpf/tracex1.bpf.c
index f3be14a03964d..0ab39d76ff8f0 100644
--- a/samples/bpf/tracex1.bpf.c
+++ b/samples/bpf/tracex1.bpf.c
@@ -8,15 +8,9 @@
 #include "net_shared.h"
 #include <linux/version.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 #include <bpf/bpf_tracing.h>
 
-#define _(P)                                                                   \
-	({                                                                     \
-		typeof(P) val = 0;                                             \
-		bpf_probe_read_kernel(&val, sizeof(val), &(P));                \
-		val;                                                           \
-	})
-
 /* kprobe is NOT a stable ABI
  * kernel functions can be removed, renamed or completely change semantics.
  * Number of arguments and their positions can change, etc.
@@ -34,12 +28,11 @@ int bpf_prog1(struct pt_regs *ctx)
 	struct sk_buff *skb;
 	int len;
 
-	/* non-portable! works for the given kernel only */
-	bpf_probe_read_kernel(&skb, sizeof(skb), (void *)PT_REGS_PARM1(ctx));
-	dev = _(skb->dev);
-	len = _(skb->len);
+	bpf_core_read(&skb, sizeof(skb), (void *)PT_REGS_PARM1(ctx));
+	dev = BPF_CORE_READ(skb, dev);
+	len = BPF_CORE_READ(skb, len);
 
-	bpf_probe_read_kernel(devname, sizeof(devname), dev->name);
+	BPF_CORE_READ_STR_INTO(&devname, dev, name);
 
 	if (devname[0] == 'l' && devname[1] == 'o') {
 		char fmt[] = "skb %p len %d\n";
diff --git a/samples/bpf/tracex5.bpf.c b/samples/bpf/tracex5.bpf.c
index 8cd697ee70473..4d3d6c9b25fa5 100644
--- a/samples/bpf/tracex5.bpf.c
+++ b/samples/bpf/tracex5.bpf.c
@@ -10,6 +10,7 @@
 #include <uapi/linux/unistd.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
 
 #define __stringify(x) #x
 #define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F
@@ -46,7 +47,7 @@ PROG(SYS__NR_write)(struct pt_regs *ctx)
 {
 	struct seccomp_data sd;
 
-	bpf_probe_read_kernel(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx));
+	bpf_core_read(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx));
 	if (sd.args[2] == 512) {
 		char fmt[] = "write(fd=%d, buf=%p, size=%d)\n";
 		bpf_trace_printk(fmt, sizeof(fmt),
@@ -59,7 +60,7 @@ PROG(SYS__NR_read)(struct pt_regs *ctx)
 {
 	struct seccomp_data sd;
 
-	bpf_probe_read_kernel(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx));
+	bpf_core_read(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx));
 	if (sd.args[2] > 128 && sd.args[2] <= 1024) {
 		char fmt[] = "read(fd=%d, buf=%p, size=%d)\n";
 		bpf_trace_printk(fmt, sizeof(fmt),
-- 
GitLab


From 92632115fb57ff9e368f256913e96d6fd5abf5ab Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 18 Aug 2023 18:01:16 +0900
Subject: [PATCH 1423/1806] samples/bpf: fix bio latency check with tracepoint

Recently, a new tracepoint for the block layer, specifically the
block_io_start/done tracepoints, was introduced in commit 5a80bd075f3b
("block: introduce block_io_start/block_io_done tracepoints").

Previously, the kprobe entry used for this purpose was quite unstable
and inherently broke relevant probes [1]. Now that a stable tracepoint
is available, this commit replaces the bio latency check with it.

One of the changes made during this replacement is the key used for the
hash table. Since 'struct request' cannot be used as a hash key, the
approach taken follows that which was implemented in bcc/biolatency [2].
(uses dev:sector for the key)

[1]: https://github.com/iovisor/bcc/issues/4261
[2]: https://github.com/iovisor/bcc/pull/4691

Fixes: 450b7879e345 ("block: move blk_account_io_{start,done} to blk-mq.c")
Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Link: https://lore.kernel.org/r/20230818090119.477441-7-danieltimlee@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/tracex3.bpf.c | 36 ++++++++++++++++++++++++------------
 1 file changed, 24 insertions(+), 12 deletions(-)

diff --git a/samples/bpf/tracex3.bpf.c b/samples/bpf/tracex3.bpf.c
index 7cc60f10d2e54..41f37966f5f57 100644
--- a/samples/bpf/tracex3.bpf.c
+++ b/samples/bpf/tracex3.bpf.c
@@ -9,6 +9,12 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+struct start_key {
+	dev_t dev;
+	u32 _pad;
+	sector_t sector;
+};
+
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, long);
@@ -16,16 +22,17 @@ struct {
 	__uint(max_entries, 4096);
 } my_map SEC(".maps");
 
-/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe
- * example will no longer be meaningful
- */
-SEC("kprobe/blk_mq_start_request")
-int bpf_prog1(struct pt_regs *ctx)
+/* from /sys/kernel/tracing/events/block/block_io_start/format */
+SEC("tracepoint/block/block_io_start")
+int bpf_prog1(struct trace_event_raw_block_rq *ctx)
 {
-	long rq = PT_REGS_PARM1(ctx);
 	u64 val = bpf_ktime_get_ns();
+	struct start_key key = {
+		.dev = ctx->dev,
+		.sector = ctx->sector
+	};
 
-	bpf_map_update_elem(&my_map, &rq, &val, BPF_ANY);
+	bpf_map_update_elem(&my_map, &key, &val, BPF_ANY);
 	return 0;
 }
 
@@ -47,21 +54,26 @@ struct {
 	__uint(max_entries, SLOTS);
 } lat_map SEC(".maps");
 
-SEC("kprobe/__blk_account_io_done")
-int bpf_prog2(struct pt_regs *ctx)
+/* from /sys/kernel/tracing/events/block/block_io_done/format */
+SEC("tracepoint/block/block_io_done")
+int bpf_prog2(struct trace_event_raw_block_rq *ctx)
 {
-	long rq = PT_REGS_PARM1(ctx);
+	struct start_key key = {
+		.dev = ctx->dev,
+		.sector = ctx->sector
+	};
+
 	u64 *value, l, base;
 	u32 index;
 
-	value = bpf_map_lookup_elem(&my_map, &rq);
+	value = bpf_map_lookup_elem(&my_map, &key);
 	if (!value)
 		return 0;
 
 	u64 cur_time = bpf_ktime_get_ns();
 	u64 delta = cur_time - *value;
 
-	bpf_map_delete_elem(&my_map, &rq);
+	bpf_map_delete_elem(&my_map, &key);
 
 	/* the lines below are computing index = log10(delta)*10
 	 * using integer arithmetic
-- 
GitLab


From d93a7cf6ca2cfcd7de5d06f753ce8d5e863316ac Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 18 Aug 2023 18:01:17 +0900
Subject: [PATCH 1424/1806] samples/bpf: fix broken map lookup probe

In the commit 7c4cd051add3 ("bpf: Fix syscall's stackmap lookup
potential deadlock"), a potential deadlock issue was addressed, which
resulted in *_map_lookup_elem not triggering BPF programs.
(prior to lookup, bpf_disable_instrumentation() is used)

To resolve the broken map lookup probe using "htab_map_lookup_elem",
this commit introduces an alternative approach. Instead, it utilize
"bpf_map_copy_value" and apply a filter specifically for the hash table
with map_type.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Fixes: 7c4cd051add3 ("bpf: Fix syscall's stackmap lookup potential deadlock")
Link: https://lore.kernel.org/r/20230818090119.477441-8-danieltimlee@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/tracex6.bpf.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/samples/bpf/tracex6.bpf.c b/samples/bpf/tracex6.bpf.c
index 6ad82e68f9986..9b23b4737cfb2 100644
--- a/samples/bpf/tracex6.bpf.c
+++ b/samples/bpf/tracex6.bpf.c
@@ -1,6 +1,8 @@
 #include "vmlinux.h"
 #include <linux/version.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
@@ -44,13 +46,24 @@ int bpf_prog1(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("kprobe/htab_map_lookup_elem")
-int bpf_prog2(struct pt_regs *ctx)
+/*
+ * Since *_map_lookup_elem can't be expected to trigger bpf programs
+ * due to potential deadlocks (bpf_disable_instrumentation), this bpf
+ * program will be attached to bpf_map_copy_value (which is called
+ * from map_lookup_elem) and will only filter the hashtable type.
+ */
+SEC("kprobe/bpf_map_copy_value")
+int BPF_KPROBE(bpf_prog2, struct bpf_map *map)
 {
 	u32 key = bpf_get_smp_processor_id();
 	struct bpf_perf_event_value *val, buf;
+	enum bpf_map_type type;
 	int error;
 
+	type = BPF_CORE_READ(map, map_type);
+	if (type != BPF_MAP_TYPE_HASH)
+		return 0;
+
 	error = bpf_perf_event_read_value(&counters, key, &buf, sizeof(buf));
 	if (error)
 		return 0;
-- 
GitLab


From 8dc80551463197ec79ce0966ec2b5bd700042614 Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 18 Aug 2023 18:01:18 +0900
Subject: [PATCH 1425/1806] samples/bpf: refactor syscall tracing programs
 using BPF_KSYSCALL macro

This commit refactors the syscall tracing programs by adopting the
BPF_KSYSCALL macro. This change aims to enhance the clarity and
simplicity of the BPF programs by reducing the complexity of argument
parsing from pt_regs.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Link: https://lore.kernel.org/r/20230818090119.477441-9-danieltimlee@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/test_map_in_map.bpf.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/samples/bpf/test_map_in_map.bpf.c b/samples/bpf/test_map_in_map.bpf.c
index 1883559e59772..9f030f9c4e1b7 100644
--- a/samples/bpf/test_map_in_map.bpf.c
+++ b/samples/bpf/test_map_in_map.bpf.c
@@ -103,19 +103,15 @@ static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port)
 	return result ? *result : -ENOENT;
 }
 
-SEC("kprobe/__sys_connect")
-int trace_sys_connect(struct pt_regs *ctx)
+SEC("ksyscall/connect")
+int BPF_KSYSCALL(trace_sys_connect, unsigned int fd, struct sockaddr_in6 *in6, int addrlen)
 {
-	struct sockaddr_in6 *in6;
 	u16 test_case, port, dst6[8];
-	int addrlen, ret, inline_ret, ret_key = 0;
+	int ret, inline_ret, ret_key = 0;
 	u32 port_key;
 	void *outer_map, *inner_map;
 	bool inline_hash = false;
 
-	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(ctx);
-	addrlen = (int)PT_REGS_PARM3_CORE(ctx);
-
 	if (addrlen != sizeof(*in6))
 		return 0;
 
-- 
GitLab


From 456d53554ca7e93d7e5e8eb7fe8c906d5ec6e7d0 Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 18 Aug 2023 18:01:19 +0900
Subject: [PATCH 1426/1806] samples/bpf: simplify spintest with kprobe.multi

With the introduction of kprobe.multi, it is now possible to attach
multiple kprobes to a single BPF program without the need for multiple
definitions. Additionally, this method supports wildcard-based
matching, allowing for further simplification of BPF programs. In here,
an asterisk (*) wildcard is used to map to all symbols relevant to
spin_{lock|unlock}.

Furthermore, since kprobe.multi handles symbol matching, this commit
eliminates the need for the previous logic of reading the ksym table to
verify the existence of symbols.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Link: https://lore.kernel.org/r/20230818090119.477441-10-danieltimlee@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/spintest.bpf.c  | 17 +++--------------
 samples/bpf/spintest_user.c | 22 +++++++---------------
 2 files changed, 10 insertions(+), 29 deletions(-)

diff --git a/samples/bpf/spintest.bpf.c b/samples/bpf/spintest.bpf.c
index 15740b16a3f7a..cba5a9d507831 100644
--- a/samples/bpf/spintest.bpf.c
+++ b/samples/bpf/spintest.bpf.c
@@ -47,20 +47,9 @@ int foo(struct pt_regs *ctx) \
 }
 
 /* add kprobes to all possible *spin* functions */
-SEC("kprobe/spin_unlock")PROG(p1)
-SEC("kprobe/spin_lock")PROG(p2)
-SEC("kprobe/mutex_spin_on_owner")PROG(p3)
-SEC("kprobe/rwsem_spin_on_owner")PROG(p4)
-SEC("kprobe/spin_unlock_irqrestore")PROG(p5)
-SEC("kprobe/_raw_spin_unlock_irqrestore")PROG(p6)
-SEC("kprobe/_raw_spin_unlock_bh")PROG(p7)
-SEC("kprobe/_raw_spin_unlock")PROG(p8)
-SEC("kprobe/_raw_spin_lock_irqsave")PROG(p9)
-SEC("kprobe/_raw_spin_trylock_bh")PROG(p10)
-SEC("kprobe/_raw_spin_lock_irq")PROG(p11)
-SEC("kprobe/_raw_spin_trylock")PROG(p12)
-SEC("kprobe/_raw_spin_lock")PROG(p13)
-SEC("kprobe/_raw_spin_lock_bh")PROG(p14)
+SEC("kprobe.multi/spin_*lock*")PROG(spin_lock)
+SEC("kprobe.multi/*_spin_on_owner")PROG(spin_on_owner)
+SEC("kprobe.multi/_raw_spin_*lock*")PROG(raw_spin_lock)
 
 /* and to inner bpf helpers */
 SEC("kprobe/htab_map_update_elem")PROG(p15)
diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c
index 8c77600776fb4..55971edb10889 100644
--- a/samples/bpf/spintest_user.c
+++ b/samples/bpf/spintest_user.c
@@ -9,13 +9,12 @@
 
 int main(int ac, char **argv)
 {
-	char filename[256], symbol[256];
 	struct bpf_object *obj = NULL;
 	struct bpf_link *links[20];
 	long key, next_key, value;
 	struct bpf_program *prog;
 	int map_fd, i, j = 0;
-	const char *section;
+	char filename[256];
 	struct ksym *sym;
 
 	if (load_kallsyms()) {
@@ -44,20 +43,13 @@ int main(int ac, char **argv)
 	}
 
 	bpf_object__for_each_program(prog, obj) {
-		section = bpf_program__section_name(prog);
-		if (sscanf(section, "kprobe/%s", symbol) != 1)
-			continue;
-
-		/* Attach prog only when symbol exists */
-		if (ksym_get_addr(symbol)) {
-			links[j] = bpf_program__attach(prog);
-			if (libbpf_get_error(links[j])) {
-				fprintf(stderr, "bpf_program__attach failed\n");
-				links[j] = NULL;
-				goto cleanup;
-			}
-			j++;
+		links[j] = bpf_program__attach(prog);
+		if (libbpf_get_error(links[j])) {
+			fprintf(stderr, "bpf_program__attach failed\n");
+			links[j] = NULL;
+			goto cleanup;
 		}
+		j++;
 	}
 
 	for (i = 0; i < 5; i++) {
-- 
GitLab


From c5487f8d91868eeab17a59cf4d164ea113f90252 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:13 +0200
Subject: [PATCH 1427/1806] bpf: Switch BPF_F_KPROBE_MULTI_RETURN macro to enum

Switching BPF_F_KPROBE_MULTI_RETURN macro to anonymous enum,
so it'd show up in vmlinux.h. There's not functional change
compared to having this as macro.

Acked-by: Yafang Shao <laoar.shao@gmail.com>
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230809083440.3209381-2-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       | 4 +++-
 tools/include/uapi/linux/bpf.h | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d21deb46f49f3..a4e55e5e84a74 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1186,7 +1186,9 @@ enum bpf_perf_event_type {
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */
-#define BPF_F_KPROBE_MULTI_RETURN	(1U << 0)
+enum {
+	BPF_F_KPROBE_MULTI_RETURN = (1U << 0)
+};
 
 /* link_create.netfilter.flags used in LINK_CREATE command for
  * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d21deb46f49f3..a4e55e5e84a74 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1186,7 +1186,9 @@ enum bpf_perf_event_type {
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */
-#define BPF_F_KPROBE_MULTI_RETURN	(1U << 0)
+enum {
+	BPF_F_KPROBE_MULTI_RETURN = (1U << 0)
+};
 
 /* link_create.netfilter.flags used in LINK_CREATE command for
  * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
-- 
GitLab


From 3505cb9fa26cfec9512744466e754a8cbc2365b0 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:14 +0200
Subject: [PATCH 1428/1806] bpf: Add attach_type checks under
 bpf_prog_attach_check_attach_type

Add extra attach_type checks from link_create under
bpf_prog_attach_check_attach_type.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230809083440.3209381-3-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/syscall.c | 120 +++++++++++++++++++------------------------
 1 file changed, 52 insertions(+), 68 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cb658543bdb46..b14036cccd086 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3655,34 +3655,6 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 	return fd;
 }
 
-static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
-					     enum bpf_attach_type attach_type)
-{
-	switch (prog->type) {
-	case BPF_PROG_TYPE_CGROUP_SOCK:
-	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
-	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
-	case BPF_PROG_TYPE_SK_LOOKUP:
-		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
-	case BPF_PROG_TYPE_CGROUP_SKB:
-		if (!capable(CAP_NET_ADMIN))
-			/* cg-skb progs can be loaded by unpriv user.
-			 * check permissions at attach time.
-			 */
-			return -EPERM;
-		return prog->enforce_expected_attach_type &&
-			prog->expected_attach_type != attach_type ?
-			-EINVAL : 0;
-	case BPF_PROG_TYPE_KPROBE:
-		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
-		    attach_type != BPF_TRACE_KPROBE_MULTI)
-			return -EINVAL;
-		return 0;
-	default:
-		return 0;
-	}
-}
-
 static enum bpf_prog_type
 attach_type_to_prog_type(enum bpf_attach_type attach_type)
 {
@@ -3749,6 +3721,58 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 	}
 }
 
+static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
+					     enum bpf_attach_type attach_type)
+{
+	enum bpf_prog_type ptype;
+
+	switch (prog->type) {
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
+	case BPF_PROG_TYPE_CGROUP_SKB:
+		if (!capable(CAP_NET_ADMIN))
+			/* cg-skb progs can be loaded by unpriv user.
+			 * check permissions at attach time.
+			 */
+			return -EPERM;
+		return prog->enforce_expected_attach_type &&
+			prog->expected_attach_type != attach_type ?
+			-EINVAL : 0;
+	case BPF_PROG_TYPE_EXT:
+		return 0;
+	case BPF_PROG_TYPE_NETFILTER:
+		if (attach_type != BPF_NETFILTER)
+			return -EINVAL;
+		return 0;
+	case BPF_PROG_TYPE_PERF_EVENT:
+	case BPF_PROG_TYPE_TRACEPOINT:
+		if (attach_type != BPF_PERF_EVENT)
+			return -EINVAL;
+		return 0;
+	case BPF_PROG_TYPE_KPROBE:
+		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
+		    attach_type != BPF_TRACE_KPROBE_MULTI)
+			return -EINVAL;
+		if (attach_type != BPF_PERF_EVENT &&
+		    attach_type != BPF_TRACE_KPROBE_MULTI)
+			return -EINVAL;
+		return 0;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		if (attach_type != BPF_TCX_INGRESS &&
+		    attach_type != BPF_TCX_EGRESS)
+			return -EINVAL;
+		return 0;
+	default:
+		ptype = attach_type_to_prog_type(attach_type);
+		if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type)
+			return -EINVAL;
+		return 0;
+	}
+}
+
 #define BPF_PROG_ATTACH_LAST_FIELD expected_revision
 
 #define BPF_F_ATTACH_MASK_BASE	\
@@ -4855,7 +4879,6 @@ err_put:
 #define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies
 static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 {
-	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
 	int ret;
 
@@ -4874,45 +4897,6 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	if (ret)
 		goto out;
 
-	switch (prog->type) {
-	case BPF_PROG_TYPE_EXT:
-		break;
-	case BPF_PROG_TYPE_NETFILTER:
-		if (attr->link_create.attach_type != BPF_NETFILTER) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-	case BPF_PROG_TYPE_PERF_EVENT:
-	case BPF_PROG_TYPE_TRACEPOINT:
-		if (attr->link_create.attach_type != BPF_PERF_EVENT) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-	case BPF_PROG_TYPE_KPROBE:
-		if (attr->link_create.attach_type != BPF_PERF_EVENT &&
-		    attr->link_create.attach_type != BPF_TRACE_KPROBE_MULTI) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-	case BPF_PROG_TYPE_SCHED_CLS:
-		if (attr->link_create.attach_type != BPF_TCX_INGRESS &&
-		    attr->link_create.attach_type != BPF_TCX_EGRESS) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-	default:
-		ptype = attach_type_to_prog_type(attr->link_create.attach_type);
-		if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-	}
-
 	switch (prog->type) {
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
-- 
GitLab


From 89ae89f53d201143560f1e9ed4bfa62eee34f88e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:15 +0200
Subject: [PATCH 1429/1806] bpf: Add multi uprobe link

Adding new multi uprobe link that allows to attach bpf program
to multiple uprobes.

Uprobes to attach are specified via new link_create uprobe_multi
union:

  struct {
    __aligned_u64   path;
    __aligned_u64   offsets;
    __aligned_u64   ref_ctr_offsets;
    __u32           cnt;
    __u32           flags;
  } uprobe_multi;

Uprobes are defined for single binary specified in path and multiple
calling sites specified in offsets array with optional reference
counters specified in ref_ctr_offsets array. All specified arrays
have length of 'cnt'.

The 'flags' supports single bit for now that marks the uprobe as
return probe.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230809083440.3209381-4-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/trace_events.h   |   6 +
 include/uapi/linux/bpf.h       |  16 +++
 kernel/bpf/syscall.c           |  14 +-
 kernel/trace/bpf_trace.c       | 233 +++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  16 +++
 5 files changed, 282 insertions(+), 3 deletions(-)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index e66d04dbe56a0..5b85cf18c3507 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -752,6 +752,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 			    u32 *fd_type, const char **buf,
 			    u64 *probe_offset, u64 *probe_addr);
 int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 #else
 static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 {
@@ -798,6 +799,11 @@ bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
 	return -EOPNOTSUPP;
 }
+static inline int
+bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 enum {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a4e55e5e84a74..e48780951fc79 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1039,6 +1039,7 @@ enum bpf_attach_type {
 	BPF_NETFILTER,
 	BPF_TCX_INGRESS,
 	BPF_TCX_EGRESS,
+	BPF_TRACE_UPROBE_MULTI,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1057,6 +1058,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_STRUCT_OPS = 9,
 	BPF_LINK_TYPE_NETFILTER = 10,
 	BPF_LINK_TYPE_TCX = 11,
+	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	MAX_BPF_LINK_TYPE,
 };
 
@@ -1190,6 +1192,13 @@ enum {
 	BPF_F_KPROBE_MULTI_RETURN = (1U << 0)
 };
 
+/* link_create.uprobe_multi.flags used in LINK_CREATE command for
+ * BPF_TRACE_UPROBE_MULTI attach type to create return probe.
+ */
+enum {
+	BPF_F_UPROBE_MULTI_RETURN = (1U << 0)
+};
+
 /* link_create.netfilter.flags used in LINK_CREATE command for
  * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
  */
@@ -1626,6 +1635,13 @@ union bpf_attr {
 				};
 				__u64		expected_revision;
 			} tcx;
+			struct {
+				__aligned_u64	path;
+				__aligned_u64	offsets;
+				__aligned_u64	ref_ctr_offsets;
+				__u32		cnt;
+				__u32		flags;
+			} uprobe_multi;
 		};
 	} link_create;
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b14036cccd086..fe291b000814f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2815,10 +2815,12 @@ static void bpf_link_free_id(int id)
 
 /* Clean up bpf_link and corresponding anon_inode file and FD. After
  * anon_inode is created, bpf_link can't be just kfree()'d due to deferred
- * anon_inode's release() call. This helper marksbpf_link as
+ * anon_inode's release() call. This helper marks bpf_link as
  * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt
  * is not decremented, it's the responsibility of a calling code that failed
  * to complete bpf_link initialization.
+ * This helper eventually calls link's dealloc callback, but does not call
+ * link's release callback.
  */
 void bpf_link_cleanup(struct bpf_link_primer *primer)
 {
@@ -3756,8 +3758,12 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
 		    attach_type != BPF_TRACE_KPROBE_MULTI)
 			return -EINVAL;
+		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI &&
+		    attach_type != BPF_TRACE_UPROBE_MULTI)
+			return -EINVAL;
 		if (attach_type != BPF_PERF_EVENT &&
-		    attach_type != BPF_TRACE_KPROBE_MULTI)
+		    attach_type != BPF_TRACE_KPROBE_MULTI &&
+		    attach_type != BPF_TRACE_UPROBE_MULTI)
 			return -EINVAL;
 		return 0;
 	case BPF_PROG_TYPE_SCHED_CLS:
@@ -4953,8 +4959,10 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	case BPF_PROG_TYPE_KPROBE:
 		if (attr->link_create.attach_type == BPF_PERF_EVENT)
 			ret = bpf_perf_link_attach(attr, prog);
-		else
+		else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI)
 			ret = bpf_kprobe_multi_link_attach(attr, prog);
+		else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI)
+			ret = bpf_uprobe_multi_link_attach(attr, prog);
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 792445e1f3f04..f0b54a3480f85 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -23,6 +23,7 @@
 #include <linux/sort.h>
 #include <linux/key.h>
 #include <linux/verification.h>
+#include <linux/namei.h>
 
 #include <net/bpf_sk_storage.h>
 
@@ -2970,3 +2971,235 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
 	return 0;
 }
 #endif
+
+#ifdef CONFIG_UPROBES
+struct bpf_uprobe_multi_link;
+
+struct bpf_uprobe {
+	struct bpf_uprobe_multi_link *link;
+	loff_t offset;
+	struct uprobe_consumer consumer;
+};
+
+struct bpf_uprobe_multi_link {
+	struct path path;
+	struct bpf_link link;
+	u32 cnt;
+	struct bpf_uprobe *uprobes;
+};
+
+struct bpf_uprobe_multi_run_ctx {
+	struct bpf_run_ctx run_ctx;
+	unsigned long entry_ip;
+};
+
+static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes,
+				  u32 cnt)
+{
+	u32 i;
+
+	for (i = 0; i < cnt; i++) {
+		uprobe_unregister(d_real_inode(path->dentry), uprobes[i].offset,
+				  &uprobes[i].consumer);
+	}
+}
+
+static void bpf_uprobe_multi_link_release(struct bpf_link *link)
+{
+	struct bpf_uprobe_multi_link *umulti_link;
+
+	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
+	bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt);
+}
+
+static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_uprobe_multi_link *umulti_link;
+
+	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
+	path_put(&umulti_link->path);
+	kvfree(umulti_link->uprobes);
+	kfree(umulti_link);
+}
+
+static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
+	.release = bpf_uprobe_multi_link_release,
+	.dealloc = bpf_uprobe_multi_link_dealloc,
+};
+
+static int uprobe_prog_run(struct bpf_uprobe *uprobe,
+			   unsigned long entry_ip,
+			   struct pt_regs *regs)
+{
+	struct bpf_uprobe_multi_link *link = uprobe->link;
+	struct bpf_uprobe_multi_run_ctx run_ctx = {
+		.entry_ip = entry_ip,
+	};
+	struct bpf_prog *prog = link->link.prog;
+	bool sleepable = prog->aux->sleepable;
+	struct bpf_run_ctx *old_run_ctx;
+	int err = 0;
+
+	if (sleepable)
+		rcu_read_lock_trace();
+	else
+		rcu_read_lock();
+
+	migrate_disable();
+
+	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+	err = bpf_prog_run(link->link.prog, regs);
+	bpf_reset_run_ctx(old_run_ctx);
+
+	migrate_enable();
+
+	if (sleepable)
+		rcu_read_unlock_trace();
+	else
+		rcu_read_unlock();
+	return err;
+}
+
+static int
+uprobe_multi_link_handler(struct uprobe_consumer *con, struct pt_regs *regs)
+{
+	struct bpf_uprobe *uprobe;
+
+	uprobe = container_of(con, struct bpf_uprobe, consumer);
+	return uprobe_prog_run(uprobe, instruction_pointer(regs), regs);
+}
+
+static int
+uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs)
+{
+	struct bpf_uprobe *uprobe;
+
+	uprobe = container_of(con, struct bpf_uprobe, consumer);
+	return uprobe_prog_run(uprobe, func, regs);
+}
+
+int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_uprobe_multi_link *link = NULL;
+	unsigned long __user *uref_ctr_offsets;
+	unsigned long *ref_ctr_offsets = NULL;
+	struct bpf_link_primer link_primer;
+	struct bpf_uprobe *uprobes = NULL;
+	unsigned long __user *uoffsets;
+	void __user *upath;
+	u32 flags, cnt, i;
+	struct path path;
+	char *name;
+	int err;
+
+	/* no support for 32bit archs yet */
+	if (sizeof(u64) != sizeof(void *))
+		return -EOPNOTSUPP;
+
+	if (prog->expected_attach_type != BPF_TRACE_UPROBE_MULTI)
+		return -EINVAL;
+
+	flags = attr->link_create.uprobe_multi.flags;
+	if (flags & ~BPF_F_UPROBE_MULTI_RETURN)
+		return -EINVAL;
+
+	/*
+	 * path, offsets and cnt are mandatory,
+	 * ref_ctr_offsets is optional
+	 */
+	upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path);
+	uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets);
+	cnt = attr->link_create.uprobe_multi.cnt;
+
+	if (!upath || !uoffsets || !cnt)
+		return -EINVAL;
+
+	uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets);
+
+	name = strndup_user(upath, PATH_MAX);
+	if (IS_ERR(name)) {
+		err = PTR_ERR(name);
+		return err;
+	}
+
+	err = kern_path(name, LOOKUP_FOLLOW, &path);
+	kfree(name);
+	if (err)
+		return err;
+
+	if (!d_is_reg(path.dentry)) {
+		err = -EBADF;
+		goto error_path_put;
+	}
+
+	err = -ENOMEM;
+
+	link = kzalloc(sizeof(*link), GFP_KERNEL);
+	uprobes = kvcalloc(cnt, sizeof(*uprobes), GFP_KERNEL);
+
+	if (!uprobes || !link)
+		goto error_free;
+
+	if (uref_ctr_offsets) {
+		ref_ctr_offsets = kvcalloc(cnt, sizeof(*ref_ctr_offsets), GFP_KERNEL);
+		if (!ref_ctr_offsets)
+			goto error_free;
+	}
+
+	for (i = 0; i < cnt; i++) {
+		if (uref_ctr_offsets && __get_user(ref_ctr_offsets[i], uref_ctr_offsets + i)) {
+			err = -EFAULT;
+			goto error_free;
+		}
+		if (__get_user(uprobes[i].offset, uoffsets + i)) {
+			err = -EFAULT;
+			goto error_free;
+		}
+
+		uprobes[i].link = link;
+
+		if (flags & BPF_F_UPROBE_MULTI_RETURN)
+			uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler;
+		else
+			uprobes[i].consumer.handler = uprobe_multi_link_handler;
+	}
+
+	link->cnt = cnt;
+	link->uprobes = uprobes;
+	link->path = path;
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI,
+		      &bpf_uprobe_multi_link_lops, prog);
+
+	for (i = 0; i < cnt; i++) {
+		err = uprobe_register_refctr(d_real_inode(link->path.dentry),
+					     uprobes[i].offset,
+					     ref_ctr_offsets ? ref_ctr_offsets[i] : 0,
+					     &uprobes[i].consumer);
+		if (err) {
+			bpf_uprobe_unregister(&path, uprobes, i);
+			goto error_free;
+		}
+	}
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err)
+		goto error_free;
+
+	kvfree(ref_ctr_offsets);
+	return bpf_link_settle(&link_primer);
+
+error_free:
+	kvfree(ref_ctr_offsets);
+	kvfree(uprobes);
+	kfree(link);
+error_path_put:
+	path_put(&path);
+	return err;
+}
+#else /* !CONFIG_UPROBES */
+int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_UPROBES */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a4e55e5e84a74..e48780951fc79 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1039,6 +1039,7 @@ enum bpf_attach_type {
 	BPF_NETFILTER,
 	BPF_TCX_INGRESS,
 	BPF_TCX_EGRESS,
+	BPF_TRACE_UPROBE_MULTI,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1057,6 +1058,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_STRUCT_OPS = 9,
 	BPF_LINK_TYPE_NETFILTER = 10,
 	BPF_LINK_TYPE_TCX = 11,
+	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	MAX_BPF_LINK_TYPE,
 };
 
@@ -1190,6 +1192,13 @@ enum {
 	BPF_F_KPROBE_MULTI_RETURN = (1U << 0)
 };
 
+/* link_create.uprobe_multi.flags used in LINK_CREATE command for
+ * BPF_TRACE_UPROBE_MULTI attach type to create return probe.
+ */
+enum {
+	BPF_F_UPROBE_MULTI_RETURN = (1U << 0)
+};
+
 /* link_create.netfilter.flags used in LINK_CREATE command for
  * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
  */
@@ -1626,6 +1635,13 @@ union bpf_attr {
 				};
 				__u64		expected_revision;
 			} tcx;
+			struct {
+				__aligned_u64	path;
+				__aligned_u64	offsets;
+				__aligned_u64	ref_ctr_offsets;
+				__u32		cnt;
+				__u32		flags;
+			} uprobe_multi;
 		};
 	} link_create;
 
-- 
GitLab


From 0b779b61f651851df5c5c42938a6c441eb1b5100 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:16 +0200
Subject: [PATCH 1430/1806] bpf: Add cookies support for uprobe_multi link

Adding support to specify cookies array for uprobe_multi link.

The cookies array share indexes and length with other uprobe_multi
arrays (offsets/ref_ctr_offsets).

The cookies[i] value defines cookie for i-the uprobe and will be
returned by bpf_get_attach_cookie helper when called from ebpf
program hooked to that specific uprobe.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230809083440.3209381-5-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/syscall.c           |  2 +-
 kernel/trace/bpf_trace.c       | 45 +++++++++++++++++++++++++++++++---
 tools/include/uapi/linux/bpf.h |  1 +
 4 files changed, 44 insertions(+), 5 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e48780951fc79..d7f4f50b1e58a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1639,6 +1639,7 @@ union bpf_attr {
 				__aligned_u64	path;
 				__aligned_u64	offsets;
 				__aligned_u64	ref_ctr_offsets;
+				__aligned_u64	cookies;
 				__u32		cnt;
 				__u32		flags;
 			} uprobe_multi;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index fe291b000814f..ef17cd05262e6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4882,7 +4882,7 @@ err_put:
 	return err;
 }
 
-#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies
+#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.flags
 static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 {
 	struct bpf_prog *prog;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index f0b54a3480f85..0d59cac30c7ed 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -87,6 +87,8 @@ static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
 static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx);
 static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx);
 
+static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx);
+
 /**
  * trace_call_bpf - invoke BPF program
  * @call: tracepoint event
@@ -1104,6 +1106,18 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_1(bpf_get_attach_cookie_uprobe_multi, struct pt_regs *, regs)
+{
+	return bpf_uprobe_multi_cookie(current->bpf_ctx);
+}
+
+static const struct bpf_func_proto bpf_get_attach_cookie_proto_umulti = {
+	.func		= bpf_get_attach_cookie_uprobe_multi,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx)
 {
 	struct bpf_trace_run_ctx *run_ctx;
@@ -1550,9 +1564,11 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 			&bpf_get_func_ip_proto_kprobe_multi :
 			&bpf_get_func_ip_proto_kprobe;
 	case BPF_FUNC_get_attach_cookie:
-		return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
-			&bpf_get_attach_cookie_proto_kmulti :
-			&bpf_get_attach_cookie_proto_trace;
+		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI)
+			return &bpf_get_attach_cookie_proto_kmulti;
+		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
+			return &bpf_get_attach_cookie_proto_umulti;
+		return &bpf_get_attach_cookie_proto_trace;
 	default:
 		return bpf_tracing_func_proto(func_id, prog);
 	}
@@ -2978,6 +2994,7 @@ struct bpf_uprobe_multi_link;
 struct bpf_uprobe {
 	struct bpf_uprobe_multi_link *link;
 	loff_t offset;
+	u64 cookie;
 	struct uprobe_consumer consumer;
 };
 
@@ -2991,6 +3008,7 @@ struct bpf_uprobe_multi_link {
 struct bpf_uprobe_multi_run_ctx {
 	struct bpf_run_ctx run_ctx;
 	unsigned long entry_ip;
+	struct bpf_uprobe *uprobe;
 };
 
 static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes,
@@ -3034,6 +3052,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe,
 	struct bpf_uprobe_multi_link *link = uprobe->link;
 	struct bpf_uprobe_multi_run_ctx run_ctx = {
 		.entry_ip = entry_ip,
+		.uprobe = uprobe,
 	};
 	struct bpf_prog *prog = link->link.prog;
 	bool sleepable = prog->aux->sleepable;
@@ -3078,6 +3097,14 @@ uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, s
 	return uprobe_prog_run(uprobe, func, regs);
 }
 
+static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx)
+{
+	struct bpf_uprobe_multi_run_ctx *run_ctx;
+
+	run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, run_ctx);
+	return run_ctx->uprobe->cookie;
+}
+
 int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
 	struct bpf_uprobe_multi_link *link = NULL;
@@ -3086,6 +3113,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	struct bpf_link_primer link_primer;
 	struct bpf_uprobe *uprobes = NULL;
 	unsigned long __user *uoffsets;
+	u64 __user *ucookies;
 	void __user *upath;
 	u32 flags, cnt, i;
 	struct path path;
@@ -3105,7 +3133,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 
 	/*
 	 * path, offsets and cnt are mandatory,
-	 * ref_ctr_offsets is optional
+	 * ref_ctr_offsets and cookies are optional
 	 */
 	upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path);
 	uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets);
@@ -3115,6 +3143,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 		return -EINVAL;
 
 	uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets);
+	ucookies = u64_to_user_ptr(attr->link_create.uprobe_multi.cookies);
 
 	name = strndup_user(upath, PATH_MAX);
 	if (IS_ERR(name)) {
@@ -3147,6 +3176,10 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	}
 
 	for (i = 0; i < cnt; i++) {
+		if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) {
+			err = -EFAULT;
+			goto error_free;
+		}
 		if (uref_ctr_offsets && __get_user(ref_ctr_offsets[i], uref_ctr_offsets + i)) {
 			err = -EFAULT;
 			goto error_free;
@@ -3202,4 +3235,8 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 {
 	return -EOPNOTSUPP;
 }
+static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx)
+{
+	return 0;
+}
 #endif /* CONFIG_UPROBES */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e48780951fc79..d7f4f50b1e58a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1639,6 +1639,7 @@ union bpf_attr {
 				__aligned_u64	path;
 				__aligned_u64	offsets;
 				__aligned_u64	ref_ctr_offsets;
+				__aligned_u64	cookies;
 				__u32		cnt;
 				__u32		flags;
 			} uprobe_multi;
-- 
GitLab


From b733eeade4204423711793595c3c8d78a2fa8b2e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:17 +0200
Subject: [PATCH 1431/1806] bpf: Add pid filter support for uprobe_multi link

Adding support to specify pid for uprobe_multi link and the uprobes
are created only for task with given pid value.

Using the consumer.filter filter callback for that, so the task gets
filtered during the uprobe installation.

We still need to check the task during runtime in the uprobe handler,
because the handler could get executed if there's another system
wide consumer on the same uprobe (thanks Oleg for the insight).

Cc: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230809083440.3209381-6-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/syscall.c           |  2 +-
 kernel/trace/bpf_trace.c       | 33 +++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  1 +
 4 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d7f4f50b1e58a..8790b3962e4b8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1642,6 +1642,7 @@ union bpf_attr {
 				__aligned_u64	cookies;
 				__u32		cnt;
 				__u32		flags;
+				__u32		pid;
 			} uprobe_multi;
 		};
 	} link_create;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ef17cd05262e6..10666d17b9e3b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4882,7 +4882,7 @@ err_put:
 	return err;
 }
 
-#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.flags
+#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid
 static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 {
 	struct bpf_prog *prog;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0d59cac30c7ed..e45aebed62f52 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3003,6 +3003,7 @@ struct bpf_uprobe_multi_link {
 	struct bpf_link link;
 	u32 cnt;
 	struct bpf_uprobe *uprobes;
+	struct task_struct *task;
 };
 
 struct bpf_uprobe_multi_run_ctx {
@@ -3035,6 +3036,8 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
 	struct bpf_uprobe_multi_link *umulti_link;
 
 	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
+	if (umulti_link->task)
+		put_task_struct(umulti_link->task);
 	path_put(&umulti_link->path);
 	kvfree(umulti_link->uprobes);
 	kfree(umulti_link);
@@ -3059,6 +3062,9 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe,
 	struct bpf_run_ctx *old_run_ctx;
 	int err = 0;
 
+	if (link->task && current != link->task)
+		return 0;
+
 	if (sleepable)
 		rcu_read_lock_trace();
 	else
@@ -3079,6 +3085,16 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe,
 	return err;
 }
 
+static bool
+uprobe_multi_link_filter(struct uprobe_consumer *con, enum uprobe_filter_ctx ctx,
+			 struct mm_struct *mm)
+{
+	struct bpf_uprobe *uprobe;
+
+	uprobe = container_of(con, struct bpf_uprobe, consumer);
+	return uprobe->link->task->mm == mm;
+}
+
 static int
 uprobe_multi_link_handler(struct uprobe_consumer *con, struct pt_regs *regs)
 {
@@ -3112,12 +3128,14 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	unsigned long *ref_ctr_offsets = NULL;
 	struct bpf_link_primer link_primer;
 	struct bpf_uprobe *uprobes = NULL;
+	struct task_struct *task = NULL;
 	unsigned long __user *uoffsets;
 	u64 __user *ucookies;
 	void __user *upath;
 	u32 flags, cnt, i;
 	struct path path;
 	char *name;
+	pid_t pid;
 	int err;
 
 	/* no support for 32bit archs yet */
@@ -3161,6 +3179,15 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 		goto error_path_put;
 	}
 
+	pid = attr->link_create.uprobe_multi.pid;
+	if (pid) {
+		rcu_read_lock();
+		task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
+		rcu_read_unlock();
+		if (!task)
+			goto error_path_put;
+	}
+
 	err = -ENOMEM;
 
 	link = kzalloc(sizeof(*link), GFP_KERNEL);
@@ -3195,11 +3222,15 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 			uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler;
 		else
 			uprobes[i].consumer.handler = uprobe_multi_link_handler;
+
+		if (pid)
+			uprobes[i].consumer.filter = uprobe_multi_link_filter;
 	}
 
 	link->cnt = cnt;
 	link->uprobes = uprobes;
 	link->path = path;
+	link->task = task;
 
 	bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI,
 		      &bpf_uprobe_multi_link_lops, prog);
@@ -3226,6 +3257,8 @@ error_free:
 	kvfree(ref_ctr_offsets);
 	kvfree(uprobes);
 	kfree(link);
+	if (task)
+		put_task_struct(task);
 error_path_put:
 	path_put(&path);
 	return err;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d7f4f50b1e58a..8790b3962e4b8 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1642,6 +1642,7 @@ union bpf_attr {
 				__aligned_u64	cookies;
 				__u32		cnt;
 				__u32		flags;
+				__u32		pid;
 			} uprobe_multi;
 		};
 	} link_create;
-- 
GitLab


From 686328d80c4346329d37a838021fa6b7d5ca64ec Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:18 +0200
Subject: [PATCH 1432/1806] bpf: Add bpf_get_func_ip helper support for uprobe
 link

Adding support for bpf_get_func_ip helper being called from
ebpf program attached by uprobe_multi link.

It returns the ip of the uprobe.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230809083440.3209381-7-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/bpf_trace.c | 33 ++++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index e45aebed62f52..a7264b2c17ad7 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -88,6 +88,7 @@ static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx);
 static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx);
 
 static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx);
+static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx);
 
 /**
  * trace_call_bpf - invoke BPF program
@@ -1106,6 +1107,18 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_1(bpf_get_func_ip_uprobe_multi, struct pt_regs *, regs)
+{
+	return bpf_uprobe_multi_entry_ip(current->bpf_ctx);
+}
+
+static const struct bpf_func_proto bpf_get_func_ip_proto_uprobe_multi = {
+	.func		= bpf_get_func_ip_uprobe_multi,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 BPF_CALL_1(bpf_get_attach_cookie_uprobe_multi, struct pt_regs *, regs)
 {
 	return bpf_uprobe_multi_cookie(current->bpf_ctx);
@@ -1560,9 +1573,11 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_override_return_proto;
 #endif
 	case BPF_FUNC_get_func_ip:
-		return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
-			&bpf_get_func_ip_proto_kprobe_multi :
-			&bpf_get_func_ip_proto_kprobe;
+		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI)
+			return &bpf_get_func_ip_proto_kprobe_multi;
+		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
+			return &bpf_get_func_ip_proto_uprobe_multi;
+		return &bpf_get_func_ip_proto_kprobe;
 	case BPF_FUNC_get_attach_cookie:
 		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI)
 			return &bpf_get_attach_cookie_proto_kmulti;
@@ -3113,6 +3128,14 @@ uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, s
 	return uprobe_prog_run(uprobe, func, regs);
 }
 
+static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
+{
+	struct bpf_uprobe_multi_run_ctx *run_ctx;
+
+	run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, run_ctx);
+	return run_ctx->entry_ip;
+}
+
 static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx)
 {
 	struct bpf_uprobe_multi_run_ctx *run_ctx;
@@ -3272,4 +3295,8 @@ static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx)
 {
 	return 0;
 }
+static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
+{
+	return 0;
+}
 #endif /* CONFIG_UPROBES */
-- 
GitLab


From 8097e460cabd9973e424e0f93bc1ad44cebf6466 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:19 +0200
Subject: [PATCH 1433/1806] libbpf: Add uprobe_multi attach type and link names

Adding new uprobe_multi attach type and link names,
so the functions can resolve the new values.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-8-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2178b28878e2b..7da15d878618e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -120,6 +120,7 @@ static const char * const attach_type_name[] = {
 	[BPF_NETFILTER]			= "netfilter",
 	[BPF_TCX_INGRESS]		= "tcx_ingress",
 	[BPF_TCX_EGRESS]		= "tcx_egress",
+	[BPF_TRACE_UPROBE_MULTI]	= "trace_uprobe_multi",
 };
 
 static const char * const link_type_name[] = {
@@ -135,6 +136,7 @@ static const char * const link_type_name[] = {
 	[BPF_LINK_TYPE_STRUCT_OPS]		= "struct_ops",
 	[BPF_LINK_TYPE_NETFILTER]		= "netfilter",
 	[BPF_LINK_TYPE_TCX]			= "tcx",
+	[BPF_LINK_TYPE_UPROBE_MULTI]		= "uprobe_multi",
 };
 
 static const char * const map_type_name[] = {
-- 
GitLab


From 5c742725045ae9c15b7ae2041d1fbd1f2180ab86 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:20 +0200
Subject: [PATCH 1434/1806] libbpf: Move elf_find_func_offset* functions to elf
 object

Adding new elf object that will contain elf related functions.
There's no functional change.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-9-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Build             |   2 +-
 tools/lib/bpf/elf.c             | 197 ++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.c          | 185 ------------------------------
 tools/lib/bpf/libbpf_internal.h |   4 +
 4 files changed, 202 insertions(+), 186 deletions(-)
 create mode 100644 tools/lib/bpf/elf.c

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index b8b0a6369363e..2d0c282c8588b 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,4 +1,4 @@
 libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
 	    netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \
 	    btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \
-	    usdt.o zip.o
+	    usdt.o zip.o elf.o
diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
new file mode 100644
index 0000000000000..735ef10093ac0
--- /dev/null
+++ b/tools/lib/bpf/elf.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+#include <libelf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
+
+#include "libbpf_internal.h"
+#include "str_error.h"
+
+#define STRERR_BUFSIZE  128
+
+/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */
+static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
+{
+	while ((scn = elf_nextscn(elf, scn)) != NULL) {
+		GElf_Shdr sh;
+
+		if (!gelf_getshdr(scn, &sh))
+			continue;
+		if (sh.sh_type == sh_type)
+			return scn;
+	}
+	return NULL;
+}
+
+/* Find offset of function name in the provided ELF object. "binary_path" is
+ * the path to the ELF binary represented by "elf", and only used for error
+ * reporting matters. "name" matches symbol name or name@@LIB for library
+ * functions.
+ */
+long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
+{
+	int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
+	bool is_shared_lib, is_name_qualified;
+	long ret = -ENOENT;
+	size_t name_len;
+	GElf_Ehdr ehdr;
+
+	if (!gelf_getehdr(elf, &ehdr)) {
+		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
+		ret = -LIBBPF_ERRNO__FORMAT;
+		goto out;
+	}
+	/* for shared lib case, we do not need to calculate relative offset */
+	is_shared_lib = ehdr.e_type == ET_DYN;
+
+	name_len = strlen(name);
+	/* Does name specify "@@LIB"? */
+	is_name_qualified = strstr(name, "@@") != NULL;
+
+	/* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if
+	 * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically
+	 * linked binary may not have SHT_DYMSYM, so absence of a section should not be
+	 * reported as a warning/error.
+	 */
+	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
+		size_t nr_syms, strtabidx, idx;
+		Elf_Data *symbols = NULL;
+		Elf_Scn *scn = NULL;
+		int last_bind = -1;
+		const char *sname;
+		GElf_Shdr sh;
+
+		scn = elf_find_next_scn_by_type(elf, sh_types[i], NULL);
+		if (!scn) {
+			pr_debug("elf: failed to find symbol table ELF sections in '%s'\n",
+				 binary_path);
+			continue;
+		}
+		if (!gelf_getshdr(scn, &sh))
+			continue;
+		strtabidx = sh.sh_link;
+		symbols = elf_getdata(scn, 0);
+		if (!symbols) {
+			pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n",
+				binary_path, elf_errmsg(-1));
+			ret = -LIBBPF_ERRNO__FORMAT;
+			goto out;
+		}
+		nr_syms = symbols->d_size / sh.sh_entsize;
+
+		for (idx = 0; idx < nr_syms; idx++) {
+			int curr_bind;
+			GElf_Sym sym;
+			Elf_Scn *sym_scn;
+			GElf_Shdr sym_sh;
+
+			if (!gelf_getsym(symbols, idx, &sym))
+				continue;
+
+			if (GELF_ST_TYPE(sym.st_info) != STT_FUNC)
+				continue;
+
+			sname = elf_strptr(elf, strtabidx, sym.st_name);
+			if (!sname)
+				continue;
+
+			curr_bind = GELF_ST_BIND(sym.st_info);
+
+			/* User can specify func, func@@LIB or func@@LIB_VERSION. */
+			if (strncmp(sname, name, name_len) != 0)
+				continue;
+			/* ...but we don't want a search for "foo" to match 'foo2" also, so any
+			 * additional characters in sname should be of the form "@@LIB".
+			 */
+			if (!is_name_qualified && sname[name_len] != '\0' && sname[name_len] != '@')
+				continue;
+
+			if (ret >= 0) {
+				/* handle multiple matches */
+				if (last_bind != STB_WEAK && curr_bind != STB_WEAK) {
+					/* Only accept one non-weak bind. */
+					pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
+						sname, name, binary_path);
+					ret = -LIBBPF_ERRNO__FORMAT;
+					goto out;
+				} else if (curr_bind == STB_WEAK) {
+					/* already have a non-weak bind, and
+					 * this is a weak bind, so ignore.
+					 */
+					continue;
+				}
+			}
+
+			/* Transform symbol's virtual address (absolute for
+			 * binaries and relative for shared libs) into file
+			 * offset, which is what kernel is expecting for
+			 * uprobe/uretprobe attachment.
+			 * See Documentation/trace/uprobetracer.rst for more
+			 * details.
+			 * This is done by looking up symbol's containing
+			 * section's header and using it's virtual address
+			 * (sh_addr) and corresponding file offset (sh_offset)
+			 * to transform sym.st_value (virtual address) into
+			 * desired final file offset.
+			 */
+			sym_scn = elf_getscn(elf, sym.st_shndx);
+			if (!sym_scn)
+				continue;
+			if (!gelf_getshdr(sym_scn, &sym_sh))
+				continue;
+
+			ret = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset;
+			last_bind = curr_bind;
+		}
+		if (ret > 0)
+			break;
+	}
+
+	if (ret > 0) {
+		pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path,
+			 ret);
+	} else {
+		if (ret == 0) {
+			pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path,
+				is_shared_lib ? "should not be 0 in a shared library" :
+						"try using shared library path instead");
+			ret = -ENOENT;
+		} else {
+			pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path);
+		}
+	}
+out:
+	return ret;
+}
+
+/* Find offset of function name in ELF object specified by path. "name" matches
+ * symbol name or name@@LIB for library functions.
+ */
+long elf_find_func_offset_from_file(const char *binary_path, const char *name)
+{
+	char errmsg[STRERR_BUFSIZE];
+	long ret = -ENOENT;
+	Elf *elf;
+	int fd;
+
+	fd = open(binary_path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		ret = -errno;
+		pr_warn("failed to open %s: %s\n", binary_path,
+			libbpf_strerror_r(ret, errmsg, sizeof(errmsg)));
+		return ret;
+	}
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf) {
+		pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1));
+		close(fd);
+		return -LIBBPF_ERRNO__FORMAT;
+	}
+
+	ret = elf_find_func_offset(elf, binary_path, name);
+	elf_end(elf);
+	close(fd);
+	return ret;
+}
+
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7da15d878618e..c05dd32910e06 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -11004,191 +11004,6 @@ err_clean_legacy:
 	return err;
 }
 
-/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */
-static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
-{
-	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		GElf_Shdr sh;
-
-		if (!gelf_getshdr(scn, &sh))
-			continue;
-		if (sh.sh_type == sh_type)
-			return scn;
-	}
-	return NULL;
-}
-
-/* Find offset of function name in the provided ELF object. "binary_path" is
- * the path to the ELF binary represented by "elf", and only used for error
- * reporting matters. "name" matches symbol name or name@@LIB for library
- * functions.
- */
-static long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
-{
-	int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
-	bool is_shared_lib, is_name_qualified;
-	long ret = -ENOENT;
-	size_t name_len;
-	GElf_Ehdr ehdr;
-
-	if (!gelf_getehdr(elf, &ehdr)) {
-		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
-		ret = -LIBBPF_ERRNO__FORMAT;
-		goto out;
-	}
-	/* for shared lib case, we do not need to calculate relative offset */
-	is_shared_lib = ehdr.e_type == ET_DYN;
-
-	name_len = strlen(name);
-	/* Does name specify "@@LIB"? */
-	is_name_qualified = strstr(name, "@@") != NULL;
-
-	/* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if
-	 * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically
-	 * linked binary may not have SHT_DYMSYM, so absence of a section should not be
-	 * reported as a warning/error.
-	 */
-	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
-		size_t nr_syms, strtabidx, idx;
-		Elf_Data *symbols = NULL;
-		Elf_Scn *scn = NULL;
-		int last_bind = -1;
-		const char *sname;
-		GElf_Shdr sh;
-
-		scn = elf_find_next_scn_by_type(elf, sh_types[i], NULL);
-		if (!scn) {
-			pr_debug("elf: failed to find symbol table ELF sections in '%s'\n",
-				 binary_path);
-			continue;
-		}
-		if (!gelf_getshdr(scn, &sh))
-			continue;
-		strtabidx = sh.sh_link;
-		symbols = elf_getdata(scn, 0);
-		if (!symbols) {
-			pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n",
-				binary_path, elf_errmsg(-1));
-			ret = -LIBBPF_ERRNO__FORMAT;
-			goto out;
-		}
-		nr_syms = symbols->d_size / sh.sh_entsize;
-
-		for (idx = 0; idx < nr_syms; idx++) {
-			int curr_bind;
-			GElf_Sym sym;
-			Elf_Scn *sym_scn;
-			GElf_Shdr sym_sh;
-
-			if (!gelf_getsym(symbols, idx, &sym))
-				continue;
-
-			if (GELF_ST_TYPE(sym.st_info) != STT_FUNC)
-				continue;
-
-			sname = elf_strptr(elf, strtabidx, sym.st_name);
-			if (!sname)
-				continue;
-
-			curr_bind = GELF_ST_BIND(sym.st_info);
-
-			/* User can specify func, func@@LIB or func@@LIB_VERSION. */
-			if (strncmp(sname, name, name_len) != 0)
-				continue;
-			/* ...but we don't want a search for "foo" to match 'foo2" also, so any
-			 * additional characters in sname should be of the form "@@LIB".
-			 */
-			if (!is_name_qualified && sname[name_len] != '\0' && sname[name_len] != '@')
-				continue;
-
-			if (ret >= 0) {
-				/* handle multiple matches */
-				if (last_bind != STB_WEAK && curr_bind != STB_WEAK) {
-					/* Only accept one non-weak bind. */
-					pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
-						sname, name, binary_path);
-					ret = -LIBBPF_ERRNO__FORMAT;
-					goto out;
-				} else if (curr_bind == STB_WEAK) {
-					/* already have a non-weak bind, and
-					 * this is a weak bind, so ignore.
-					 */
-					continue;
-				}
-			}
-
-			/* Transform symbol's virtual address (absolute for
-			 * binaries and relative for shared libs) into file
-			 * offset, which is what kernel is expecting for
-			 * uprobe/uretprobe attachment.
-			 * See Documentation/trace/uprobetracer.rst for more
-			 * details.
-			 * This is done by looking up symbol's containing
-			 * section's header and using it's virtual address
-			 * (sh_addr) and corresponding file offset (sh_offset)
-			 * to transform sym.st_value (virtual address) into
-			 * desired final file offset.
-			 */
-			sym_scn = elf_getscn(elf, sym.st_shndx);
-			if (!sym_scn)
-				continue;
-			if (!gelf_getshdr(sym_scn, &sym_sh))
-				continue;
-
-			ret = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset;
-			last_bind = curr_bind;
-		}
-		if (ret > 0)
-			break;
-	}
-
-	if (ret > 0) {
-		pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path,
-			 ret);
-	} else {
-		if (ret == 0) {
-			pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path,
-				is_shared_lib ? "should not be 0 in a shared library" :
-						"try using shared library path instead");
-			ret = -ENOENT;
-		} else {
-			pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path);
-		}
-	}
-out:
-	return ret;
-}
-
-/* Find offset of function name in ELF object specified by path. "name" matches
- * symbol name or name@@LIB for library functions.
- */
-static long elf_find_func_offset_from_file(const char *binary_path, const char *name)
-{
-	char errmsg[STRERR_BUFSIZE];
-	long ret = -ENOENT;
-	Elf *elf;
-	int fd;
-
-	fd = open(binary_path, O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		ret = -errno;
-		pr_warn("failed to open %s: %s\n", binary_path,
-			libbpf_strerror_r(ret, errmsg, sizeof(errmsg)));
-		return ret;
-	}
-	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
-	if (!elf) {
-		pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1));
-		close(fd);
-		return -LIBBPF_ERRNO__FORMAT;
-	}
-
-	ret = elf_find_func_offset(elf, binary_path, name);
-	elf_end(elf);
-	close(fd);
-	return ret;
-}
-
 /* Find offset of function name in archive specified by path. Currently
  * supported are .zip files that do not compress their contents, as used on
  * Android in the form of APKs, for example. "file_name" is the name of the ELF
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index e4d05662a96ce..44eb635415070 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <libelf.h>
 #include "relo_core.h"
 
 /* make sure libbpf doesn't use kernel-only integer typedefs */
@@ -577,4 +578,7 @@ static inline bool is_pow_of_2(size_t x)
 #define PROG_LOAD_ATTEMPTS 5
 int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
 
+long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name);
+long elf_find_func_offset_from_file(const char *binary_path, const char *name);
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
-- 
GitLab


From f90eb70d4489ea6fa6f3a7638aa614e15ad7181f Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:21 +0200
Subject: [PATCH 1435/1806] libbpf: Add elf_open/elf_close functions

Adding elf_open/elf_close functions and using it in
elf_find_func_offset_from_file function. It will be
used in following changes to save some common code.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-10-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/elf.c             | 61 ++++++++++++++++++++++-----------
 tools/lib/bpf/libbpf_internal.h |  8 +++++
 tools/lib/bpf/usdt.c            | 30 +++++-----------
 3 files changed, 57 insertions(+), 42 deletions(-)

diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 735ef10093ac0..71363acdeb678 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -10,6 +10,42 @@
 
 #define STRERR_BUFSIZE  128
 
+int elf_open(const char *binary_path, struct elf_fd *elf_fd)
+{
+	char errmsg[STRERR_BUFSIZE];
+	int fd, ret;
+	Elf *elf;
+
+	if (elf_version(EV_CURRENT) == EV_NONE) {
+		pr_warn("elf: failed to init libelf for %s\n", binary_path);
+		return -LIBBPF_ERRNO__LIBELF;
+	}
+	fd = open(binary_path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		ret = -errno;
+		pr_warn("elf: failed to open %s: %s\n", binary_path,
+			libbpf_strerror_r(ret, errmsg, sizeof(errmsg)));
+		return ret;
+	}
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf) {
+		pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1));
+		close(fd);
+		return -LIBBPF_ERRNO__FORMAT;
+	}
+	elf_fd->fd = fd;
+	elf_fd->elf = elf;
+	return 0;
+}
+
+void elf_close(struct elf_fd *elf_fd)
+{
+	if (!elf_fd)
+		return;
+	elf_end(elf_fd->elf);
+	close(elf_fd->fd);
+}
+
 /* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */
 static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
 {
@@ -170,28 +206,13 @@ out:
  */
 long elf_find_func_offset_from_file(const char *binary_path, const char *name)
 {
-	char errmsg[STRERR_BUFSIZE];
+	struct elf_fd elf_fd;
 	long ret = -ENOENT;
-	Elf *elf;
-	int fd;
 
-	fd = open(binary_path, O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		ret = -errno;
-		pr_warn("failed to open %s: %s\n", binary_path,
-			libbpf_strerror_r(ret, errmsg, sizeof(errmsg)));
+	ret = elf_open(binary_path, &elf_fd);
+	if (ret)
 		return ret;
-	}
-	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
-	if (!elf) {
-		pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1));
-		close(fd);
-		return -LIBBPF_ERRNO__FORMAT;
-	}
-
-	ret = elf_find_func_offset(elf, binary_path, name);
-	elf_end(elf);
-	close(fd);
+	ret = elf_find_func_offset(elf_fd.elf, binary_path, name);
+	elf_close(&elf_fd);
 	return ret;
 }
-
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 44eb635415070..0bbcd8e6fdc58 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -581,4 +581,12 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
 long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name);
 long elf_find_func_offset_from_file(const char *binary_path, const char *name);
 
+struct elf_fd {
+	Elf *elf;
+	int fd;
+};
+
+int elf_open(const char *binary_path, struct elf_fd *elf_fd);
+void elf_close(struct elf_fd *elf_fd);
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index 37455d00b239c..8322337ab65b4 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -946,32 +946,22 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 					  const char *usdt_provider, const char *usdt_name,
 					  __u64 usdt_cookie)
 {
-	int i, fd, err, spec_map_fd, ip_map_fd;
+	int i, err, spec_map_fd, ip_map_fd;
 	LIBBPF_OPTS(bpf_uprobe_opts, opts);
 	struct hashmap *specs_hash = NULL;
 	struct bpf_link_usdt *link = NULL;
 	struct usdt_target *targets = NULL;
+	struct elf_fd elf_fd;
 	size_t target_cnt;
-	Elf *elf;
 
 	spec_map_fd = bpf_map__fd(man->specs_map);
 	ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map);
 
-	fd = open(path, O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		err = -errno;
-		pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err);
+	err = elf_open(path, &elf_fd);
+	if (err)
 		return libbpf_err_ptr(err);
-	}
 
-	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
-	if (!elf) {
-		err = -EBADF;
-		pr_warn("usdt: failed to parse ELF binary '%s': %s\n", path, elf_errmsg(-1));
-		goto err_out;
-	}
-
-	err = sanity_check_usdt_elf(elf, path);
+	err = sanity_check_usdt_elf(elf_fd.elf, path);
 	if (err)
 		goto err_out;
 
@@ -984,7 +974,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 	/* discover USDT in given binary, optionally limiting
 	 * activations to a given PID, if pid > 0
 	 */
-	err = collect_usdt_targets(man, elf, path, pid, usdt_provider, usdt_name,
+	err = collect_usdt_targets(man, elf_fd.elf, path, pid, usdt_provider, usdt_name,
 				   usdt_cookie, &targets, &target_cnt);
 	if (err <= 0) {
 		err = (err == 0) ? -ENOENT : err;
@@ -1069,9 +1059,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 
 	free(targets);
 	hashmap__free(specs_hash);
-	elf_end(elf);
-	close(fd);
-
+	elf_close(&elf_fd);
 	return &link->link;
 
 err_out:
@@ -1079,9 +1067,7 @@ err_out:
 		bpf_link__destroy(&link->link);
 	free(targets);
 	hashmap__free(specs_hash);
-	if (elf)
-		elf_end(elf);
-	close(fd);
+	elf_close(&elf_fd);
 	return libbpf_err_ptr(err);
 }
 
-- 
GitLab


From 3774705db1718a671a4ed2ac5066fea839b1d7d1 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:22 +0200
Subject: [PATCH 1436/1806] libbpf: Add elf symbol iterator

Adding elf symbol iterator object (and some functions) that follow
open-coded iterator pattern and some functions to ease up iterating
elf object symbols.

The idea is to iterate single symbol section with:

  struct elf_sym_iter iter;
  struct elf_sym *sym;

  if (elf_sym_iter_new(&iter, elf, binary_path, SHT_DYNSYM))
        goto error;

  while ((sym = elf_sym_iter_next(&iter))) {
        ...
  }

I considered opening the elf inside the iterator and iterate all symbol
sections, but then it gets more complicated wrt user checks for when
the next section is processed.

Plus side is the we don't need 'exit' function, because caller/user is
in charge of that.

The returned iterated symbol object from elf_sym_iter_next function
is placed inside the struct elf_sym_iter, so no extra allocation or
argument is needed.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-11-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/elf.c | 179 ++++++++++++++++++++++++++++----------------
 1 file changed, 115 insertions(+), 64 deletions(-)

diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 71363acdeb678..8a3f8a7259816 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -60,6 +60,104 @@ static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
 	return NULL;
 }
 
+struct elf_sym {
+	const char *name;
+	GElf_Sym sym;
+	GElf_Shdr sh;
+};
+
+struct elf_sym_iter {
+	Elf *elf;
+	Elf_Data *syms;
+	size_t nr_syms;
+	size_t strtabidx;
+	size_t next_sym_idx;
+	struct elf_sym sym;
+	int st_type;
+};
+
+static int elf_sym_iter_new(struct elf_sym_iter *iter,
+			    Elf *elf, const char *binary_path,
+			    int sh_type, int st_type)
+{
+	Elf_Scn *scn = NULL;
+	GElf_Ehdr ehdr;
+	GElf_Shdr sh;
+
+	memset(iter, 0, sizeof(*iter));
+
+	if (!gelf_getehdr(elf, &ehdr)) {
+		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
+		return -EINVAL;
+	}
+
+	scn = elf_find_next_scn_by_type(elf, sh_type, NULL);
+	if (!scn) {
+		pr_debug("elf: failed to find symbol table ELF sections in '%s'\n",
+			 binary_path);
+		return -ENOENT;
+	}
+
+	if (!gelf_getshdr(scn, &sh))
+		return -EINVAL;
+
+	iter->strtabidx = sh.sh_link;
+	iter->syms = elf_getdata(scn, 0);
+	if (!iter->syms) {
+		pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n",
+			binary_path, elf_errmsg(-1));
+		return -EINVAL;
+	}
+	iter->nr_syms = iter->syms->d_size / sh.sh_entsize;
+	iter->elf = elf;
+	iter->st_type = st_type;
+	return 0;
+}
+
+static struct elf_sym *elf_sym_iter_next(struct elf_sym_iter *iter)
+{
+	struct elf_sym *ret = &iter->sym;
+	GElf_Sym *sym = &ret->sym;
+	const char *name = NULL;
+	Elf_Scn *sym_scn;
+	size_t idx;
+
+	for (idx = iter->next_sym_idx; idx < iter->nr_syms; idx++) {
+		if (!gelf_getsym(iter->syms, idx, sym))
+			continue;
+		if (GELF_ST_TYPE(sym->st_info) != iter->st_type)
+			continue;
+		name = elf_strptr(iter->elf, iter->strtabidx, sym->st_name);
+		if (!name)
+			continue;
+		sym_scn = elf_getscn(iter->elf, sym->st_shndx);
+		if (!sym_scn)
+			continue;
+		if (!gelf_getshdr(sym_scn, &ret->sh))
+			continue;
+
+		iter->next_sym_idx = idx + 1;
+		ret->name = name;
+		return ret;
+	}
+
+	return NULL;
+}
+
+
+/* Transform symbol's virtual address (absolute for binaries and relative
+ * for shared libs) into file offset, which is what kernel is expecting
+ * for uprobe/uretprobe attachment.
+ * See Documentation/trace/uprobetracer.rst for more details. This is done
+ * by looking up symbol's containing section's header and using iter's virtual
+ * address (sh_addr) and corresponding file offset (sh_offset) to transform
+ * sym.st_value (virtual address) into desired final file offset.
+ */
+static unsigned long elf_sym_offset(struct elf_sym *sym)
+{
+	return sym->sym.st_value - sym->sh.sh_addr + sym->sh.sh_offset;
+}
+
 /* Find offset of function name in the provided ELF object. "binary_path" is
  * the path to the ELF binary represented by "elf", and only used for error
  * reporting matters. "name" matches symbol name or name@@LIB for library
@@ -91,67 +189,38 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
 	 * reported as a warning/error.
 	 */
 	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
-		size_t nr_syms, strtabidx, idx;
-		Elf_Data *symbols = NULL;
-		Elf_Scn *scn = NULL;
+		struct elf_sym_iter iter;
+		struct elf_sym *sym;
 		int last_bind = -1;
-		const char *sname;
-		GElf_Shdr sh;
+		int cur_bind;
 
-		scn = elf_find_next_scn_by_type(elf, sh_types[i], NULL);
-		if (!scn) {
-			pr_debug("elf: failed to find symbol table ELF sections in '%s'\n",
-				 binary_path);
+		ret = elf_sym_iter_new(&iter, elf, binary_path, sh_types[i], STT_FUNC);
+		if (ret == -ENOENT)
 			continue;
-		}
-		if (!gelf_getshdr(scn, &sh))
-			continue;
-		strtabidx = sh.sh_link;
-		symbols = elf_getdata(scn, 0);
-		if (!symbols) {
-			pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n",
-				binary_path, elf_errmsg(-1));
-			ret = -LIBBPF_ERRNO__FORMAT;
+		if (ret)
 			goto out;
-		}
-		nr_syms = symbols->d_size / sh.sh_entsize;
-
-		for (idx = 0; idx < nr_syms; idx++) {
-			int curr_bind;
-			GElf_Sym sym;
-			Elf_Scn *sym_scn;
-			GElf_Shdr sym_sh;
-
-			if (!gelf_getsym(symbols, idx, &sym))
-				continue;
-
-			if (GELF_ST_TYPE(sym.st_info) != STT_FUNC)
-				continue;
-
-			sname = elf_strptr(elf, strtabidx, sym.st_name);
-			if (!sname)
-				continue;
-
-			curr_bind = GELF_ST_BIND(sym.st_info);
 
+		while ((sym = elf_sym_iter_next(&iter))) {
 			/* User can specify func, func@@LIB or func@@LIB_VERSION. */
-			if (strncmp(sname, name, name_len) != 0)
+			if (strncmp(sym->name, name, name_len) != 0)
 				continue;
 			/* ...but we don't want a search for "foo" to match 'foo2" also, so any
 			 * additional characters in sname should be of the form "@@LIB".
 			 */
-			if (!is_name_qualified && sname[name_len] != '\0' && sname[name_len] != '@')
+			if (!is_name_qualified && sym->name[name_len] != '\0' && sym->name[name_len] != '@')
 				continue;
 
-			if (ret >= 0) {
+			cur_bind = GELF_ST_BIND(sym->sym.st_info);
+
+			if (ret > 0) {
 				/* handle multiple matches */
-				if (last_bind != STB_WEAK && curr_bind != STB_WEAK) {
+				if (last_bind != STB_WEAK && cur_bind != STB_WEAK) {
 					/* Only accept one non-weak bind. */
 					pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
-						sname, name, binary_path);
+						sym->name, name, binary_path);
 					ret = -LIBBPF_ERRNO__FORMAT;
 					goto out;
-				} else if (curr_bind == STB_WEAK) {
+				} else if (cur_bind == STB_WEAK) {
 					/* already have a non-weak bind, and
 					 * this is a weak bind, so ignore.
 					 */
@@ -159,26 +228,8 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
 				}
 			}
 
-			/* Transform symbol's virtual address (absolute for
-			 * binaries and relative for shared libs) into file
-			 * offset, which is what kernel is expecting for
-			 * uprobe/uretprobe attachment.
-			 * See Documentation/trace/uprobetracer.rst for more
-			 * details.
-			 * This is done by looking up symbol's containing
-			 * section's header and using it's virtual address
-			 * (sh_addr) and corresponding file offset (sh_offset)
-			 * to transform sym.st_value (virtual address) into
-			 * desired final file offset.
-			 */
-			sym_scn = elf_getscn(elf, sym.st_shndx);
-			if (!sym_scn)
-				continue;
-			if (!gelf_getshdr(sym_scn, &sym_sh))
-				continue;
-
-			ret = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset;
-			last_bind = curr_bind;
+			ret = elf_sym_offset(sym);
+			last_bind = cur_bind;
 		}
 		if (ret > 0)
 			break;
-- 
GitLab


From 7ace84c6892971766b7c252b3998d5662679e472 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:23 +0200
Subject: [PATCH 1437/1806] libbpf: Add elf_resolve_syms_offsets function

Adding elf_resolve_syms_offsets function that looks up
offsets for symbols specified in syms array argument.

Offsets are returned in allocated array with the 'cnt' size,
that needs to be released by the caller.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-12-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/elf.c             | 110 ++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf_internal.h |   2 +
 2 files changed, 112 insertions(+)

diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 8a3f8a7259816..8c512641c1d78 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -267,3 +267,113 @@ long elf_find_func_offset_from_file(const char *binary_path, const char *name)
 	elf_close(&elf_fd);
 	return ret;
 }
+
+struct symbol {
+	const char *name;
+	int bind;
+	int idx;
+};
+
+static int symbol_cmp(const void *a, const void *b)
+{
+	const struct symbol *sym_a = a;
+	const struct symbol *sym_b = b;
+
+	return strcmp(sym_a->name, sym_b->name);
+}
+
+/*
+ * Return offsets in @poffsets for symbols specified in @syms array argument.
+ * On success returns 0 and offsets are returned in allocated array with @cnt
+ * size, that needs to be released by the caller.
+ */
+int elf_resolve_syms_offsets(const char *binary_path, int cnt,
+			     const char **syms, unsigned long **poffsets)
+{
+	int sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
+	int err = 0, i, cnt_done = 0;
+	unsigned long *offsets;
+	struct symbol *symbols;
+	struct elf_fd elf_fd;
+
+	err = elf_open(binary_path, &elf_fd);
+	if (err)
+		return err;
+
+	offsets = calloc(cnt, sizeof(*offsets));
+	symbols = calloc(cnt, sizeof(*symbols));
+
+	if (!offsets || !symbols) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < cnt; i++) {
+		symbols[i].name = syms[i];
+		symbols[i].idx = i;
+	}
+
+	qsort(symbols, cnt, sizeof(*symbols), symbol_cmp);
+
+	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
+		struct elf_sym_iter iter;
+		struct elf_sym *sym;
+
+		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC);
+		if (err == -ENOENT)
+			continue;
+		if (err)
+			goto out;
+
+		while ((sym = elf_sym_iter_next(&iter))) {
+			unsigned long sym_offset = elf_sym_offset(sym);
+			int bind = GELF_ST_BIND(sym->sym.st_info);
+			struct symbol *found, tmp = {
+				.name = sym->name,
+			};
+			unsigned long *offset;
+
+			found = bsearch(&tmp, symbols, cnt, sizeof(*symbols), symbol_cmp);
+			if (!found)
+				continue;
+
+			offset = &offsets[found->idx];
+			if (*offset > 0) {
+				/* same offset, no problem */
+				if (*offset == sym_offset)
+					continue;
+				/* handle multiple matches */
+				if (found->bind != STB_WEAK && bind != STB_WEAK) {
+					/* Only accept one non-weak bind. */
+					pr_warn("elf: ambiguous match found '%s@%lu' in '%s' previous offset %lu\n",
+						sym->name, sym_offset, binary_path, *offset);
+					err = -ESRCH;
+					goto out;
+				} else if (bind == STB_WEAK) {
+					/* already have a non-weak bind, and
+					 * this is a weak bind, so ignore.
+					 */
+					continue;
+				}
+			} else {
+				cnt_done++;
+			}
+			*offset = sym_offset;
+			found->bind = bind;
+		}
+	}
+
+	if (cnt != cnt_done) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	*poffsets = offsets;
+
+out:
+	free(symbols);
+	if (err)
+		free(offsets);
+	elf_close(&elf_fd);
+	return err;
+}
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 0bbcd8e6fdc58..92851c5f912d6 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -589,4 +589,6 @@ struct elf_fd {
 int elf_open(const char *binary_path, struct elf_fd *elf_fd);
 void elf_close(struct elf_fd *elf_fd);
 
+int elf_resolve_syms_offsets(const char *binary_path, int cnt,
+			     const char **syms, unsigned long **poffsets);
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
-- 
GitLab


From e613d1d0f7d4f6ee9b458c62f85c577872dce9a6 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:24 +0200
Subject: [PATCH 1438/1806] libbpf: Add elf_resolve_pattern_offsets function

Adding elf_resolve_pattern_offsets function that looks up
offsets for symbols specified by pattern argument.

The 'pattern' argument allows wildcards (*?' supported).

Offsets are returned in allocated array together with its
size and needs to be released by the caller.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-13-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/elf.c             | 61 +++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.c          |  2 +-
 tools/lib/bpf/libbpf_internal.h |  5 +++
 3 files changed, 67 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 8c512641c1d78..9d0296c1726a8 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -377,3 +377,64 @@ out:
 	elf_close(&elf_fd);
 	return err;
 }
+
+/*
+ * Return offsets in @poffsets for symbols specified by @pattern argument.
+ * On success returns 0 and offsets are returned in allocated @poffsets
+ * array with the @pctn size, that needs to be released by the caller.
+ */
+int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
+				unsigned long **poffsets, size_t *pcnt)
+{
+	int sh_types[2] = { SHT_SYMTAB, SHT_DYNSYM };
+	unsigned long *offsets = NULL;
+	size_t cap = 0, cnt = 0;
+	struct elf_fd elf_fd;
+	int err = 0, i;
+
+	err = elf_open(binary_path, &elf_fd);
+	if (err)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
+		struct elf_sym_iter iter;
+		struct elf_sym *sym;
+
+		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC);
+		if (err == -ENOENT)
+			continue;
+		if (err)
+			goto out;
+
+		while ((sym = elf_sym_iter_next(&iter))) {
+			if (!glob_match(sym->name, pattern))
+				continue;
+
+			err = libbpf_ensure_mem((void **) &offsets, &cap, sizeof(*offsets),
+						cnt + 1);
+			if (err)
+				goto out;
+
+			offsets[cnt++] = elf_sym_offset(sym);
+		}
+
+		/* If we found anything in the first symbol section,
+		 * do not search others to avoid duplicates.
+		 */
+		if (cnt)
+			break;
+	}
+
+	if (cnt) {
+		*poffsets = offsets;
+		*pcnt = cnt;
+	} else {
+		err = -ENOENT;
+	}
+
+out:
+	if (err)
+		free(offsets);
+	elf_close(&elf_fd);
+	return err;
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c05dd32910e06..88a38e6079595 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10569,7 +10569,7 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog,
 }
 
 /* Adapted from perf/util/string.c */
-static bool glob_match(const char *str, const char *pat)
+bool glob_match(const char *str, const char *pat)
 {
 	while (*str && *pat && *pat != '*') {
 		if (*pat == '?') {      /* Matches any single character */
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 92851c5f912d6..ead551318fecd 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -578,6 +578,8 @@ static inline bool is_pow_of_2(size_t x)
 #define PROG_LOAD_ATTEMPTS 5
 int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
 
+bool glob_match(const char *str, const char *pat);
+
 long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name);
 long elf_find_func_offset_from_file(const char *binary_path, const char *name);
 
@@ -591,4 +593,7 @@ void elf_close(struct elf_fd *elf_fd);
 
 int elf_resolve_syms_offsets(const char *binary_path, int cnt,
 			     const char **syms, unsigned long **poffsets);
+int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
+				 unsigned long **poffsets, size_t *pcnt);
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
-- 
GitLab


From 5054a303f8960a45ea823021656d5ac19fb8fc89 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:25 +0200
Subject: [PATCH 1439/1806] libbpf: Add bpf_link_create support for multi
 uprobes

Adding new uprobe_multi struct to bpf_link_create_opts object
to pass multiple uprobe data to link_create attr uapi.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-14-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c | 11 +++++++++++
 tools/lib/bpf/bpf.h | 11 ++++++++++-
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index c9b6b311a441f..b0f1913763a33 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -767,6 +767,17 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, kprobe_multi))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_TRACE_UPROBE_MULTI:
+		attr.link_create.uprobe_multi.flags = OPTS_GET(opts, uprobe_multi.flags, 0);
+		attr.link_create.uprobe_multi.cnt = OPTS_GET(opts, uprobe_multi.cnt, 0);
+		attr.link_create.uprobe_multi.path = ptr_to_u64(OPTS_GET(opts, uprobe_multi.path, 0));
+		attr.link_create.uprobe_multi.offsets = ptr_to_u64(OPTS_GET(opts, uprobe_multi.offsets, 0));
+		attr.link_create.uprobe_multi.ref_ctr_offsets = ptr_to_u64(OPTS_GET(opts, uprobe_multi.ref_ctr_offsets, 0));
+		attr.link_create.uprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, uprobe_multi.cookies, 0));
+		attr.link_create.uprobe_multi.pid = OPTS_GET(opts, uprobe_multi.pid, 0);
+		if (!OPTS_ZEROED(opts, uprobe_multi))
+			return libbpf_err(-EINVAL);
+		break;
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
 	case BPF_MODIFY_RETURN:
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 044a74ffc38aa..74c2887cfd24a 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -392,6 +392,15 @@ struct bpf_link_create_opts {
 			const unsigned long *addrs;
 			const __u64 *cookies;
 		} kprobe_multi;
+		struct {
+			__u32 flags;
+			__u32 cnt;
+			const char *path;
+			const unsigned long *offsets;
+			const unsigned long *ref_ctr_offsets;
+			const __u64 *cookies;
+			__u32 pid;
+		} uprobe_multi;
 		struct {
 			__u64 cookie;
 		} tracing;
@@ -409,7 +418,7 @@ struct bpf_link_create_opts {
 	};
 	size_t :0;
 };
-#define bpf_link_create_opts__last_field kprobe_multi.cookies
+#define bpf_link_create_opts__last_field uprobe_multi.pid
 
 LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
 			       enum bpf_attach_type attach_type,
-- 
GitLab


From 3140cf121c255686084bb31dd86ba3bdd4a8a540 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:26 +0200
Subject: [PATCH 1440/1806] libbpf: Add bpf_program__attach_uprobe_multi
 function

Adding bpf_program__attach_uprobe_multi function that
allows to attach multiple uprobes with uprobe_multi link.

The user can specify uprobes with direct arguments:

  binary_path/func_pattern/pid

or with struct bpf_uprobe_multi_opts opts argument fields:

  const char **syms;
  const unsigned long *offsets;
  const unsigned long *ref_ctr_offsets;
  const __u64 *cookies;

User can specify 2 mutually exclusive set of inputs:

 1) use only path/func_pattern/pid arguments

 2) use path/pid with allowed combinations of:
    syms/offsets/ref_ctr_offsets/cookies/cnt

    - syms and offsets are mutually exclusive
    - ref_ctr_offsets and cookies are optional

Any other usage results in error.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-15-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c   | 114 +++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.h   |  51 ++++++++++++++++++
 tools/lib/bpf/libbpf.map |   1 +
 3 files changed, 166 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 88a38e6079595..0789c704fe766 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -11146,6 +11146,120 @@ static int resolve_full_path(const char *file, char *result, size_t result_sz)
 	return -ENOENT;
 }
 
+struct bpf_link *
+bpf_program__attach_uprobe_multi(const struct bpf_program *prog,
+				 pid_t pid,
+				 const char *path,
+				 const char *func_pattern,
+				 const struct bpf_uprobe_multi_opts *opts)
+{
+	const unsigned long *ref_ctr_offsets = NULL, *offsets = NULL;
+	LIBBPF_OPTS(bpf_link_create_opts, lopts);
+	unsigned long *resolved_offsets = NULL;
+	int err = 0, link_fd, prog_fd;
+	struct bpf_link *link = NULL;
+	char errmsg[STRERR_BUFSIZE];
+	char full_path[PATH_MAX];
+	const __u64 *cookies;
+	const char **syms;
+	size_t cnt;
+
+	if (!OPTS_VALID(opts, bpf_uprobe_multi_opts))
+		return libbpf_err_ptr(-EINVAL);
+
+	syms = OPTS_GET(opts, syms, NULL);
+	offsets = OPTS_GET(opts, offsets, NULL);
+	ref_ctr_offsets = OPTS_GET(opts, ref_ctr_offsets, NULL);
+	cookies = OPTS_GET(opts, cookies, NULL);
+	cnt = OPTS_GET(opts, cnt, 0);
+
+	/*
+	 * User can specify 2 mutually exclusive set of inputs:
+	 *
+	 * 1) use only path/func_pattern/pid arguments
+	 *
+	 * 2) use path/pid with allowed combinations of:
+	 *    syms/offsets/ref_ctr_offsets/cookies/cnt
+	 *
+	 *    - syms and offsets are mutually exclusive
+	 *    - ref_ctr_offsets and cookies are optional
+	 *
+	 * Any other usage results in error.
+	 */
+
+	if (!path)
+		return libbpf_err_ptr(-EINVAL);
+	if (!func_pattern && cnt == 0)
+		return libbpf_err_ptr(-EINVAL);
+
+	if (func_pattern) {
+		if (syms || offsets || ref_ctr_offsets || cookies || cnt)
+			return libbpf_err_ptr(-EINVAL);
+	} else {
+		if (!!syms == !!offsets)
+			return libbpf_err_ptr(-EINVAL);
+	}
+
+	if (func_pattern) {
+		if (!strchr(path, '/')) {
+			err = resolve_full_path(path, full_path, sizeof(full_path));
+			if (err) {
+				pr_warn("prog '%s': failed to resolve full path for '%s': %d\n",
+					prog->name, path, err);
+				return libbpf_err_ptr(err);
+			}
+			path = full_path;
+		}
+
+		err = elf_resolve_pattern_offsets(path, func_pattern,
+						  &resolved_offsets, &cnt);
+		if (err < 0)
+			return libbpf_err_ptr(err);
+		offsets = resolved_offsets;
+	} else if (syms) {
+		err = elf_resolve_syms_offsets(path, cnt, syms, &resolved_offsets);
+		if (err < 0)
+			return libbpf_err_ptr(err);
+		offsets = resolved_offsets;
+	}
+
+	lopts.uprobe_multi.path = path;
+	lopts.uprobe_multi.offsets = offsets;
+	lopts.uprobe_multi.ref_ctr_offsets = ref_ctr_offsets;
+	lopts.uprobe_multi.cookies = cookies;
+	lopts.uprobe_multi.cnt = cnt;
+	lopts.uprobe_multi.flags = OPTS_GET(opts, retprobe, false) ? BPF_F_UPROBE_MULTI_RETURN : 0;
+
+	if (pid == 0)
+		pid = getpid();
+	if (pid > 0)
+		lopts.uprobe_multi.pid = pid;
+
+	link = calloc(1, sizeof(*link));
+	if (!link) {
+		err = -ENOMEM;
+		goto error;
+	}
+	link->detach = &bpf_link__detach_fd;
+
+	prog_fd = bpf_program__fd(prog);
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &lopts);
+	if (link_fd < 0) {
+		err = -errno;
+		pr_warn("prog '%s': failed to attach multi-uprobe: %s\n",
+			prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		goto error;
+	}
+	link->fd = link_fd;
+	free(resolved_offsets);
+	return link;
+
+error:
+	free(resolved_offsets);
+	free(link);
+	return libbpf_err_ptr(err);
+}
+
 LIBBPF_API struct bpf_link *
 bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid,
 				const char *binary_path, size_t func_offset,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 55b97b2087540..2e3eb3614c40b 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -529,6 +529,57 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 				      const char *pattern,
 				      const struct bpf_kprobe_multi_opts *opts);
 
+struct bpf_uprobe_multi_opts {
+	/* size of this struct, for forward/backward compatibility */
+	size_t sz;
+	/* array of function symbols to attach to */
+	const char **syms;
+	/* array of function addresses to attach to */
+	const unsigned long *offsets;
+	/* optional, array of associated ref counter offsets */
+	const unsigned long *ref_ctr_offsets;
+	/* optional, array of associated BPF cookies */
+	const __u64 *cookies;
+	/* number of elements in syms/addrs/cookies arrays */
+	size_t cnt;
+	/* create return uprobes */
+	bool retprobe;
+	size_t :0;
+};
+
+#define bpf_uprobe_multi_opts__last_field retprobe
+
+/**
+ * @brief **bpf_program__attach_uprobe_multi()** attaches a BPF program
+ * to multiple uprobes with uprobe_multi link.
+ *
+ * User can specify 2 mutually exclusive set of inputs:
+ *
+ *   1) use only path/func_pattern/pid arguments
+ *
+ *   2) use path/pid with allowed combinations of
+ *      syms/offsets/ref_ctr_offsets/cookies/cnt
+ *
+ *      - syms and offsets are mutually exclusive
+ *      - ref_ctr_offsets and cookies are optional
+ *
+ *
+ * @param prog BPF program to attach
+ * @param pid Process ID to attach the uprobe to, 0 for self (own process),
+ * -1 for all processes
+ * @param binary_path Path to binary
+ * @param func_pattern Regular expression to specify functions to attach
+ * BPF program to
+ * @param opts Additional options (see **struct bpf_uprobe_multi_opts**)
+ * @return 0, on success; negative error code, otherwise
+ */
+LIBBPF_API struct bpf_link *
+bpf_program__attach_uprobe_multi(const struct bpf_program *prog,
+				 pid_t pid,
+				 const char *binary_path,
+				 const char *func_pattern,
+				 const struct bpf_uprobe_multi_opts *opts);
+
 struct bpf_ksyscall_opts {
 	/* size of this struct, for forward/backward compatibility */
 	size_t sz;
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 9c7538dd5835e..841a2f9c6fef4 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -398,4 +398,5 @@ LIBBPF_1.3.0 {
 		bpf_prog_detach_opts;
 		bpf_program__attach_netfilter;
 		bpf_program__attach_tcx;
+		bpf_program__attach_uprobe_multi;
 } LIBBPF_1.2.0;
-- 
GitLab


From 5bfdd32dd575cb516878a4ee46db75659cded540 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:27 +0200
Subject: [PATCH 1441/1806] libbpf: Add support for u[ret]probe.multi[.s]
 program sections

Adding support for several uprobe_multi program sections
to allow auto attach of multi_uprobe programs.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-16-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 0789c704fe766..c9c390542040c 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8701,6 +8701,7 @@ static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_lin
 static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link);
+static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 
@@ -8716,6 +8717,10 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("uretprobe.s+",		KPROBE, 0, SEC_SLEEPABLE, attach_uprobe),
 	SEC_DEF("kprobe.multi+",	KPROBE,	BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi),
 	SEC_DEF("kretprobe.multi+",	KPROBE,	BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi),
+	SEC_DEF("uprobe.multi+",	KPROBE,	BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi),
+	SEC_DEF("uretprobe.multi+",	KPROBE,	BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi),
+	SEC_DEF("uprobe.multi.s+",	KPROBE,	BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi),
+	SEC_DEF("uretprobe.multi.s+",	KPROBE,	BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi),
 	SEC_DEF("ksyscall+",		KPROBE,	0, SEC_NONE, attach_ksyscall),
 	SEC_DEF("kretsyscall+",		KPROBE, 0, SEC_NONE, attach_ksyscall),
 	SEC_DEF("usdt+",		KPROBE,	0, SEC_NONE, attach_usdt),
@@ -10922,6 +10927,37 @@ static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, stru
 	return libbpf_get_error(*link);
 }
 
+static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link)
+{
+	char *probe_type = NULL, *binary_path = NULL, *func_name = NULL;
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+	int n, ret = -EINVAL;
+
+	*link = NULL;
+
+	n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%ms",
+		   &probe_type, &binary_path, &func_name);
+	switch (n) {
+	case 1:
+		/* handle SEC("u[ret]probe") - format is valid, but auto-attach is impossible. */
+		ret = 0;
+		break;
+	case 3:
+		opts.retprobe = strcmp(probe_type, "uretprobe.multi") == 0;
+		*link = bpf_program__attach_uprobe_multi(prog, -1, binary_path, func_name, &opts);
+		ret = libbpf_get_error(*link);
+		break;
+	default:
+		pr_warn("prog '%s': invalid format of section definition '%s'\n", prog->name,
+			prog->sec_name);
+		break;
+	}
+	free(probe_type);
+	free(binary_path);
+	free(func_name);
+	return ret;
+}
+
 static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz,
 					 const char *binary_path, uint64_t offset)
 {
-- 
GitLab


From 7e1b468123453bbb047eab7c7d6cecd4dd318ff0 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:28 +0200
Subject: [PATCH 1442/1806] libbpf: Add uprobe multi link detection

Adding uprobe-multi link detection. It will be used later in
bpf_program__attach_usdt function to check and use uprobe_multi
link over standard uprobe links.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-17-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c          | 36 +++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf_internal.h |  2 ++
 2 files changed, 38 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c9c390542040c..07b6cbe700599 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4829,6 +4829,39 @@ static int probe_perf_link(void)
 	return link_fd < 0 && err == -EBADF;
 }
 
+static int probe_uprobe_multi_link(void)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
+		.expected_attach_type = BPF_TRACE_UPROBE_MULTI,
+	);
+	LIBBPF_OPTS(bpf_link_create_opts, link_opts);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, link_fd, err;
+	unsigned long offset = 0;
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL",
+				insns, ARRAY_SIZE(insns), &load_opts);
+	if (prog_fd < 0)
+		return -errno;
+
+	/* Creating uprobe in '/' binary should fail with -EBADF. */
+	link_opts.uprobe_multi.path = "/";
+	link_opts.uprobe_multi.offsets = &offset;
+	link_opts.uprobe_multi.cnt = 1;
+
+	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
+	err = -errno; /* close() can clobber errno */
+
+	if (link_fd >= 0)
+		close(link_fd);
+	close(prog_fd);
+
+	return link_fd < 0 && err == -EBADF;
+}
+
 static int probe_kern_bpf_cookie(void)
 {
 	struct bpf_insn insns[] = {
@@ -4925,6 +4958,9 @@ static struct kern_feature_desc {
 	[FEAT_SYSCALL_WRAPPER] = {
 		"Kernel using syscall wrapper", probe_kern_syscall_wrapper,
 	},
+	[FEAT_UPROBE_MULTI_LINK] = {
+		"BPF multi-uprobe link support", probe_uprobe_multi_link,
+	},
 };
 
 bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index ead551318fecd..f0f08635adb0d 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -355,6 +355,8 @@ enum kern_feature_id {
 	FEAT_BTF_ENUM64,
 	/* Kernel uses syscall wrapper (CONFIG_ARCH_HAS_SYSCALL_WRAPPER) */
 	FEAT_SYSCALL_WRAPPER,
+	/* BPF multi-uprobe link support */
+	FEAT_UPROBE_MULTI_LINK,
 	__FEAT_CNT,
 };
 
-- 
GitLab


From 5902da6d8a523ed468ea1f28e001c7d5f30c042d Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:29 +0200
Subject: [PATCH 1443/1806] libbpf: Add uprobe multi link support to
 bpf_program__attach_usdt

Adding support for usdt_manager_attach_usdt to use uprobe_multi
link to attach to usdt probes.

The uprobe_multi support is detected before the usdt program is
loaded and its expected_attach_type is set accordingly.

If uprobe_multi support is detected the usdt_manager_attach_usdt
gathers uprobes info and calls bpf_program__attach_uprobe to
create all needed uprobes.

If uprobe_multi support is not detected the old behaviour stays.

Also adding usdt.s program section for sleepable usdt probes.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-18-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 13 ++++++-
 tools/lib/bpf/usdt.c   | 86 ++++++++++++++++++++++++++++++++++--------
 2 files changed, 82 insertions(+), 17 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 07b6cbe700599..b8afe2f5bc934 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -367,6 +367,8 @@ enum sec_def_flags {
 	SEC_SLEEPABLE = 8,
 	/* BPF program support non-linear XDP buffer */
 	SEC_XDP_FRAGS = 16,
+	/* Setup proper attach type for usdt probes. */
+	SEC_USDT = 32,
 };
 
 struct bpf_sec_def {
@@ -6828,6 +6830,10 @@ static int libbpf_prepare_prog_load(struct bpf_program *prog,
 	if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS))
 		opts->prog_flags |= BPF_F_XDP_HAS_FRAGS;
 
+	/* special check for usdt to use uprobe_multi link */
+	if ((def & SEC_USDT) && kernel_supports(prog->obj, FEAT_UPROBE_MULTI_LINK))
+		prog->expected_attach_type = BPF_TRACE_UPROBE_MULTI;
+
 	if ((def & SEC_ATTACH_BTF) && !prog->attach_btf_id) {
 		int btf_obj_fd = 0, btf_type_id = 0, err;
 		const char *attach_name;
@@ -6896,7 +6902,6 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	if (!insns || !insns_cnt)
 		return -EINVAL;
 
-	load_attr.expected_attach_type = prog->expected_attach_type;
 	if (kernel_supports(obj, FEAT_PROG_NAME))
 		prog_name = prog->name;
 	load_attr.attach_prog_fd = prog->attach_prog_fd;
@@ -6932,6 +6937,9 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 		insns_cnt = prog->insns_cnt;
 	}
 
+	/* allow prog_prepare_load_fn to change expected_attach_type */
+	load_attr.expected_attach_type = prog->expected_attach_type;
+
 	if (obj->gen_loader) {
 		bpf_gen__prog_load(obj->gen_loader, prog->type, prog->name,
 				   license, insns, insns_cnt, &load_attr,
@@ -8759,7 +8767,8 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("uretprobe.multi.s+",	KPROBE,	BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi),
 	SEC_DEF("ksyscall+",		KPROBE,	0, SEC_NONE, attach_ksyscall),
 	SEC_DEF("kretsyscall+",		KPROBE, 0, SEC_NONE, attach_ksyscall),
-	SEC_DEF("usdt+",		KPROBE,	0, SEC_NONE, attach_usdt),
+	SEC_DEF("usdt+",		KPROBE,	0, SEC_USDT, attach_usdt),
+	SEC_DEF("usdt.s+",		KPROBE,	0, SEC_USDT | SEC_SLEEPABLE, attach_usdt),
 	SEC_DEF("tc/ingress",		SCHED_CLS, BPF_TCX_INGRESS, SEC_NONE), /* alias for tcx */
 	SEC_DEF("tc/egress",		SCHED_CLS, BPF_TCX_EGRESS, SEC_NONE),  /* alias for tcx */
 	SEC_DEF("tcx/ingress",		SCHED_CLS, BPF_TCX_INGRESS, SEC_NONE),
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index 8322337ab65b4..93794f01bb67c 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -250,6 +250,7 @@ struct usdt_manager {
 
 	bool has_bpf_cookie;
 	bool has_sema_refcnt;
+	bool has_uprobe_multi;
 };
 
 struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
@@ -284,6 +285,11 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
 	 */
 	man->has_sema_refcnt = faccessat(AT_FDCWD, ref_ctr_sysfs_path, F_OK, AT_EACCESS) == 0;
 
+	/*
+	 * Detect kernel support for uprobe multi link to be used for attaching
+	 * usdt probes.
+	 */
+	man->has_uprobe_multi = kernel_supports(obj, FEAT_UPROBE_MULTI_LINK);
 	return man;
 }
 
@@ -808,6 +814,8 @@ struct bpf_link_usdt {
 		long abs_ip;
 		struct bpf_link *link;
 	} *uprobes;
+
+	struct bpf_link *multi_link;
 };
 
 static int bpf_link_usdt_detach(struct bpf_link *link)
@@ -816,6 +824,9 @@ static int bpf_link_usdt_detach(struct bpf_link *link)
 	struct usdt_manager *man = usdt_link->usdt_man;
 	int i;
 
+	bpf_link__destroy(usdt_link->multi_link);
+
+	/* When having multi_link, uprobe_cnt is 0 */
 	for (i = 0; i < usdt_link->uprobe_cnt; i++) {
 		/* detach underlying uprobe link */
 		bpf_link__destroy(usdt_link->uprobes[i].link);
@@ -946,11 +957,13 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 					  const char *usdt_provider, const char *usdt_name,
 					  __u64 usdt_cookie)
 {
+	unsigned long *offsets = NULL, *ref_ctr_offsets = NULL;
 	int i, err, spec_map_fd, ip_map_fd;
 	LIBBPF_OPTS(bpf_uprobe_opts, opts);
 	struct hashmap *specs_hash = NULL;
 	struct bpf_link_usdt *link = NULL;
 	struct usdt_target *targets = NULL;
+	__u64 *cookies = NULL;
 	struct elf_fd elf_fd;
 	size_t target_cnt;
 
@@ -997,10 +1010,21 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 	link->link.detach = &bpf_link_usdt_detach;
 	link->link.dealloc = &bpf_link_usdt_dealloc;
 
-	link->uprobes = calloc(target_cnt, sizeof(*link->uprobes));
-	if (!link->uprobes) {
-		err = -ENOMEM;
-		goto err_out;
+	if (man->has_uprobe_multi) {
+		offsets = calloc(target_cnt, sizeof(*offsets));
+		cookies = calloc(target_cnt, sizeof(*cookies));
+		ref_ctr_offsets = calloc(target_cnt, sizeof(*ref_ctr_offsets));
+
+		if (!offsets || !ref_ctr_offsets || !cookies) {
+			err = -ENOMEM;
+			goto err_out;
+		}
+	} else {
+		link->uprobes = calloc(target_cnt, sizeof(*link->uprobes));
+		if (!link->uprobes) {
+			err = -ENOMEM;
+			goto err_out;
+		}
 	}
 
 	for (i = 0; i < target_cnt; i++) {
@@ -1041,20 +1065,48 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 			goto err_out;
 		}
 
-		opts.ref_ctr_offset = target->sema_off;
-		opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0;
-		uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path,
-							      target->rel_ip, &opts);
-		err = libbpf_get_error(uprobe_link);
-		if (err) {
-			pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n",
-				i, usdt_provider, usdt_name, path, err);
+		if (man->has_uprobe_multi) {
+			offsets[i] = target->rel_ip;
+			ref_ctr_offsets[i] = target->sema_off;
+			cookies[i] = spec_id;
+		} else {
+			opts.ref_ctr_offset = target->sema_off;
+			opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0;
+			uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path,
+								      target->rel_ip, &opts);
+			err = libbpf_get_error(uprobe_link);
+			if (err) {
+				pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n",
+					i, usdt_provider, usdt_name, path, err);
+				goto err_out;
+			}
+
+			link->uprobes[i].link = uprobe_link;
+			link->uprobes[i].abs_ip = target->abs_ip;
+			link->uprobe_cnt++;
+		}
+	}
+
+	if (man->has_uprobe_multi) {
+		LIBBPF_OPTS(bpf_uprobe_multi_opts, opts_multi,
+			.ref_ctr_offsets = ref_ctr_offsets,
+			.offsets = offsets,
+			.cookies = cookies,
+			.cnt = target_cnt,
+		);
+
+		link->multi_link = bpf_program__attach_uprobe_multi(prog, pid, path,
+								    NULL, &opts_multi);
+		if (!link->multi_link) {
+			err = -errno;
+			pr_warn("usdt: failed to attach uprobe multi for '%s:%s' in '%s': %d\n",
+				usdt_provider, usdt_name, path, err);
 			goto err_out;
 		}
 
-		link->uprobes[i].link = uprobe_link;
-		link->uprobes[i].abs_ip = target->abs_ip;
-		link->uprobe_cnt++;
+		free(offsets);
+		free(ref_ctr_offsets);
+		free(cookies);
 	}
 
 	free(targets);
@@ -1063,6 +1115,10 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 	return &link->link;
 
 err_out:
+	free(offsets);
+	free(ref_ctr_offsets);
+	free(cookies);
+
 	if (link)
 		bpf_link__destroy(&link->link);
 	free(targets);
-- 
GitLab


From 3830d04a7401f277185e4439eb259c1b13e76788 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:30 +0200
Subject: [PATCH 1444/1806] selftests/bpf: Move get_time_ns to
 testing_helpers.h

We'd like to have single copy of get_time_ns used b bench and test_progs,
but we can't just include bench.h, because of conflicting 'struct env'
objects.

Moving get_time_ns to testing_helpers.h which is being included by both
bench and test_progs objects.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-19-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bench.h                    |  9 ---------
 .../selftests/bpf/prog_tests/kprobe_multi_test.c       |  8 --------
 tools/testing/selftests/bpf/testing_helpers.h          | 10 ++++++++++
 3 files changed, 10 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
index 7ff32be3d7300..68180d8f8558e 100644
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -81,15 +81,6 @@ void grace_period_latency_basic_stats(struct bench_res res[], int res_cnt,
 void grace_period_ticks_basic_stats(struct bench_res res[], int res_cnt,
 				    struct basic_stats *gp_stat);
 
-static inline __u64 get_time_ns(void)
-{
-	struct timespec t;
-
-	clock_gettime(CLOCK_MONOTONIC, &t);
-
-	return (u64)t.tv_sec * 1000000000 + t.tv_nsec;
-}
-
 static inline void atomic_inc(long *value)
 {
 	(void)__atomic_add_fetch(value, 1, __ATOMIC_RELAXED);
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 2173c4bb555ec..179fe300534f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -304,14 +304,6 @@ cleanup:
 	kprobe_multi__destroy(skel);
 }
 
-static inline __u64 get_time_ns(void)
-{
-	struct timespec t;
-
-	clock_gettime(CLOCK_MONOTONIC, &t);
-	return (__u64) t.tv_sec * 1000000000 + t.tv_nsec;
-}
-
 static size_t symbol_hash(long key, void *ctx __maybe_unused)
 {
 	return str_hash((const char *) key);
diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h
index 5312323881b65..5b7a55136741a 100644
--- a/tools/testing/selftests/bpf/testing_helpers.h
+++ b/tools/testing/selftests/bpf/testing_helpers.h
@@ -7,6 +7,7 @@
 #include <stdbool.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include <time.h>
 
 int parse_num_list(const char *s, bool **set, int *set_len);
 __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info);
@@ -33,4 +34,13 @@ int load_bpf_testmod(bool verbose);
 int unload_bpf_testmod(bool verbose);
 int kern_sync_rcu(void);
 
+static inline __u64 get_time_ns(void)
+{
+	struct timespec t;
+
+	clock_gettime(CLOCK_MONOTONIC, &t);
+
+	return (u64)t.tv_sec * 1000000000 + t.tv_nsec;
+}
+
 #endif /* __TESTING_HELPERS_H */
-- 
GitLab


From 75b3715720d731c45b2a66f7f292504e97b109e6 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:31 +0200
Subject: [PATCH 1445/1806] selftests/bpf: Add uprobe_multi skel test

Adding uprobe_multi test for skeleton load/attach functions,
to test skeleton auto attach for uprobe_multi link.

Test that bpf_get_func_ip works properly for uprobe_multi
attachment.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-20-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/uprobe_multi_test.c        | 76 ++++++++++++++++
 .../selftests/bpf/progs/uprobe_multi.c        | 91 +++++++++++++++++++
 2 files changed, 167 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
 create mode 100644 tools/testing/selftests/bpf/progs/uprobe_multi.c

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
new file mode 100644
index 0000000000000..5cd1116bbb62f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <unistd.h>
+#include <test_progs.h>
+#include "uprobe_multi.skel.h"
+
+static char test_data[] = "test_data";
+
+noinline void uprobe_multi_func_1(void)
+{
+	asm volatile ("");
+}
+
+noinline void uprobe_multi_func_2(void)
+{
+	asm volatile ("");
+}
+
+noinline void uprobe_multi_func_3(void)
+{
+	asm volatile ("");
+}
+
+static void uprobe_multi_test_run(struct uprobe_multi *skel)
+{
+	skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1;
+	skel->bss->uprobe_multi_func_2_addr = (__u64) uprobe_multi_func_2;
+	skel->bss->uprobe_multi_func_3_addr = (__u64) uprobe_multi_func_3;
+
+	skel->bss->user_ptr = test_data;
+	skel->bss->pid = getpid();
+
+	/* trigger all probes */
+	uprobe_multi_func_1();
+	uprobe_multi_func_2();
+	uprobe_multi_func_3();
+
+	/*
+	 * There are 2 entry and 2 exit probe called for each uprobe_multi_func_[123]
+	 * function and each slepable probe (6) increments uprobe_multi_sleep_result.
+	 */
+	ASSERT_EQ(skel->bss->uprobe_multi_func_1_result, 2, "uprobe_multi_func_1_result");
+	ASSERT_EQ(skel->bss->uprobe_multi_func_2_result, 2, "uprobe_multi_func_2_result");
+	ASSERT_EQ(skel->bss->uprobe_multi_func_3_result, 2, "uprobe_multi_func_3_result");
+
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_1_result, 2, "uretprobe_multi_func_1_result");
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_2_result, 2, "uretprobe_multi_func_2_result");
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_3_result, 2, "uretprobe_multi_func_3_result");
+
+	ASSERT_EQ(skel->bss->uprobe_multi_sleep_result, 6, "uprobe_multi_sleep_result");
+}
+
+static void test_skel_api(void)
+{
+	struct uprobe_multi *skel = NULL;
+	int err;
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		goto cleanup;
+
+	err = uprobe_multi__attach(skel);
+	if (!ASSERT_OK(err, "uprobe_multi__attach"))
+		goto cleanup;
+
+	uprobe_multi_test_run(skel);
+
+cleanup:
+	uprobe_multi__destroy(skel);
+}
+
+void test_uprobe_multi_test(void)
+{
+	if (test__start_subtest("skel_api"))
+		test_skel_api();
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c
new file mode 100644
index 0000000000000..ab467970256a6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 uprobe_multi_func_1_addr = 0;
+__u64 uprobe_multi_func_2_addr = 0;
+__u64 uprobe_multi_func_3_addr = 0;
+
+__u64 uprobe_multi_func_1_result = 0;
+__u64 uprobe_multi_func_2_result = 0;
+__u64 uprobe_multi_func_3_result = 0;
+
+__u64 uretprobe_multi_func_1_result = 0;
+__u64 uretprobe_multi_func_2_result = 0;
+__u64 uretprobe_multi_func_3_result = 0;
+
+__u64 uprobe_multi_sleep_result = 0;
+
+int pid = 0;
+bool test_cookie = false;
+void *user_ptr = 0;
+
+static __always_inline bool verify_sleepable_user_copy(void)
+{
+	char data[9];
+
+	bpf_copy_from_user(data, sizeof(data), user_ptr);
+	return bpf_strncmp(data, sizeof(data), "test_data") == 0;
+}
+
+static void uprobe_multi_check(void *ctx, bool is_return, bool is_sleep)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return;
+
+	__u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0;
+	__u64 addr = bpf_get_func_ip(ctx);
+
+#define SET(__var, __addr, __cookie) ({			\
+	if (addr == __addr &&				\
+	   (!test_cookie || (cookie == __cookie)))	\
+		__var += 1;				\
+})
+
+	if (is_return) {
+		SET(uretprobe_multi_func_1_result, uprobe_multi_func_1_addr, 2);
+		SET(uretprobe_multi_func_2_result, uprobe_multi_func_2_addr, 3);
+		SET(uretprobe_multi_func_3_result, uprobe_multi_func_3_addr, 1);
+	} else {
+		SET(uprobe_multi_func_1_result, uprobe_multi_func_1_addr, 3);
+		SET(uprobe_multi_func_2_result, uprobe_multi_func_2_addr, 1);
+		SET(uprobe_multi_func_3_result, uprobe_multi_func_3_addr, 2);
+	}
+
+#undef SET
+
+	if (is_sleep && verify_sleepable_user_copy())
+		uprobe_multi_sleep_result += 1;
+}
+
+SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*")
+int uprobe(struct pt_regs *ctx)
+{
+	uprobe_multi_check(ctx, false, false);
+	return 0;
+}
+
+SEC("uretprobe.multi//proc/self/exe:uprobe_multi_func_*")
+int uretprobe(struct pt_regs *ctx)
+{
+	uprobe_multi_check(ctx, true, false);
+	return 0;
+}
+
+SEC("uprobe.multi.s//proc/self/exe:uprobe_multi_func_*")
+int uprobe_sleep(struct pt_regs *ctx)
+{
+	uprobe_multi_check(ctx, false, true);
+	return 0;
+}
+
+SEC("uretprobe.multi.s//proc/self/exe:uprobe_multi_func_*")
+int uretprobe_sleep(struct pt_regs *ctx)
+{
+	uprobe_multi_check(ctx, true, true);
+	return 0;
+}
-- 
GitLab


From ffc68903617a29f000806aac1961dd7ac64c3d87 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:32 +0200
Subject: [PATCH 1446/1806] selftests/bpf: Add uprobe_multi api test

Adding uprobe_multi test for bpf_program__attach_uprobe_multi
attach function.

Testing attachment using glob patterns and via bpf_uprobe_multi_opts
paths/syms fields.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-21-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/uprobe_multi_test.c        | 65 +++++++++++++++++++
 1 file changed, 65 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 5cd1116bbb62f..2ac8954123e43 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -69,8 +69,73 @@ cleanup:
 	uprobe_multi__destroy(skel);
 }
 
+static void
+test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi_opts *opts)
+{
+	struct uprobe_multi *skel = NULL;
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		goto cleanup;
+
+	opts->retprobe = false;
+	skel->links.uprobe = bpf_program__attach_uprobe_multi(skel->progs.uprobe, -1,
+							      binary, pattern, opts);
+	if (!ASSERT_OK_PTR(skel->links.uprobe, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	opts->retprobe = true;
+	skel->links.uretprobe = bpf_program__attach_uprobe_multi(skel->progs.uretprobe, -1,
+								 binary, pattern, opts);
+	if (!ASSERT_OK_PTR(skel->links.uretprobe, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	opts->retprobe = false;
+	skel->links.uprobe_sleep = bpf_program__attach_uprobe_multi(skel->progs.uprobe_sleep, -1,
+								    binary, pattern, opts);
+	if (!ASSERT_OK_PTR(skel->links.uprobe_sleep, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	opts->retprobe = true;
+	skel->links.uretprobe_sleep = bpf_program__attach_uprobe_multi(skel->progs.uretprobe_sleep,
+								       -1, binary, pattern, opts);
+	if (!ASSERT_OK_PTR(skel->links.uretprobe_sleep, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	uprobe_multi_test_run(skel);
+
+cleanup:
+	uprobe_multi__destroy(skel);
+}
+
+static void test_attach_api_pattern(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+
+	test_attach_api("/proc/self/exe", "uprobe_multi_func_*", &opts);
+	test_attach_api("/proc/self/exe", "uprobe_multi_func_?", &opts);
+}
+
+static void test_attach_api_syms(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+	const char *syms[3] = {
+		"uprobe_multi_func_1",
+		"uprobe_multi_func_2",
+		"uprobe_multi_func_3",
+	};
+
+	opts.syms = syms;
+	opts.cnt = ARRAY_SIZE(syms);
+	test_attach_api("/proc/self/exe", NULL, &opts);
+}
+
 void test_uprobe_multi_test(void)
 {
 	if (test__start_subtest("skel_api"))
 		test_skel_api();
+	if (test__start_subtest("attach_api_pattern"))
+		test_attach_api_pattern();
+	if (test__start_subtest("attach_api_syms"))
+		test_attach_api_syms();
 }
-- 
GitLab


From a93d22ea6092f464c9bcb1e9e53537d103f2f6fa Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:33 +0200
Subject: [PATCH 1447/1806] selftests/bpf: Add uprobe_multi link test

Adding uprobe_multi test for bpf_link_create attach function.

Testing attachment using the struct bpf_link_create_opts.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-22-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/uprobe_multi_test.c        | 69 +++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 2ac8954123e43..3860beda82c80 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -3,6 +3,7 @@
 #include <unistd.h>
 #include <test_progs.h>
 #include "uprobe_multi.skel.h"
+#include "bpf/libbpf_internal.h"
 
 static char test_data[] = "test_data";
 
@@ -130,6 +131,72 @@ static void test_attach_api_syms(void)
 	test_attach_api("/proc/self/exe", NULL, &opts);
 }
 
+static void test_link_api(void)
+{
+	int prog_fd, link1_fd = -1, link2_fd = -1, link3_fd = -1, link4_fd = -1;
+	LIBBPF_OPTS(bpf_link_create_opts, opts);
+	const char *path = "/proc/self/exe";
+	struct uprobe_multi *skel = NULL;
+	unsigned long *offsets = NULL;
+	const char *syms[3] = {
+		"uprobe_multi_func_1",
+		"uprobe_multi_func_2",
+		"uprobe_multi_func_3",
+	};
+	int err;
+
+	err = elf_resolve_syms_offsets(path, 3, syms, (unsigned long **) &offsets);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets"))
+		return;
+
+	opts.uprobe_multi.path = path;
+	opts.uprobe_multi.offsets = offsets;
+	opts.uprobe_multi.cnt = ARRAY_SIZE(syms);
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		goto cleanup;
+
+	opts.kprobe_multi.flags = 0;
+	prog_fd = bpf_program__fd(skel->progs.uprobe);
+	link1_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_GE(link1_fd, 0, "link1_fd"))
+		goto cleanup;
+
+	opts.kprobe_multi.flags = BPF_F_UPROBE_MULTI_RETURN;
+	prog_fd = bpf_program__fd(skel->progs.uretprobe);
+	link2_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_GE(link2_fd, 0, "link2_fd"))
+		goto cleanup;
+
+	opts.kprobe_multi.flags = 0;
+	prog_fd = bpf_program__fd(skel->progs.uprobe_sleep);
+	link3_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_GE(link3_fd, 0, "link3_fd"))
+		goto cleanup;
+
+	opts.kprobe_multi.flags = BPF_F_UPROBE_MULTI_RETURN;
+	prog_fd = bpf_program__fd(skel->progs.uretprobe_sleep);
+	link4_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_GE(link4_fd, 0, "link4_fd"))
+		goto cleanup;
+
+	uprobe_multi_test_run(skel);
+
+cleanup:
+	if (link1_fd >= 0)
+		close(link1_fd);
+	if (link2_fd >= 0)
+		close(link2_fd);
+	if (link3_fd >= 0)
+		close(link3_fd);
+	if (link4_fd >= 0)
+		close(link4_fd);
+
+	uprobe_multi__destroy(skel);
+	free(offsets);
+}
+
 void test_uprobe_multi_test(void)
 {
 	if (test__start_subtest("skel_api"))
@@ -138,4 +205,6 @@ void test_uprobe_multi_test(void)
 		test_attach_api_pattern();
 	if (test__start_subtest("attach_api_syms"))
 		test_attach_api_syms();
+	if (test__start_subtest("link_api"))
+		test_link_api();
 }
-- 
GitLab


From 519dfeaf5119e316c1b3301ba2e38eb6d5eb0733 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:34 +0200
Subject: [PATCH 1448/1806] selftests/bpf: Add uprobe_multi test program

Adding uprobe_multi test program that defines 50k uprobe_multi_func_*
functions and will serve as attach point for uprobe_multi bench test
in following patch.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-23-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/Makefile       |  5 ++
 tools/testing/selftests/bpf/uprobe_multi.c | 67 ++++++++++++++++++++++
 2 files changed, 72 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/uprobe_multi.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e4e1e64922684..edef49fcd23e3 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -585,6 +585,7 @@ TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko	\
 		       $(OUTPUT)/liburandom_read.so			\
 		       $(OUTPUT)/xdp_synproxy				\
 		       $(OUTPUT)/sign-file				\
+		       $(OUTPUT)/uprobe_multi				\
 		       ima_setup.sh 					\
 		       verify_sig_setup.sh				\
 		       $(wildcard progs/btf_dump_test_case_*.c)		\
@@ -698,6 +699,10 @@ $(OUTPUT)/veristat: $(OUTPUT)/veristat.o
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
 
+$(OUTPUT)/uprobe_multi: uprobe_multi.c
+	$(call msg,BINARY,,$@)
+	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $^ $(LDLIBS) -o $@
+
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)	\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
 	feature bpftool							\
diff --git a/tools/testing/selftests/bpf/uprobe_multi.c b/tools/testing/selftests/bpf/uprobe_multi.c
new file mode 100644
index 0000000000000..d19184103fa31
--- /dev/null
+++ b/tools/testing/selftests/bpf/uprobe_multi.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <string.h>
+
+#define __PASTE(a, b) a##b
+#define PASTE(a, b) __PASTE(a, b)
+
+#define NAME(name, idx) PASTE(name, idx)
+
+#define DEF(name, idx)  int NAME(name, idx)(void) { return 0; }
+#define CALL(name, idx) NAME(name, idx)();
+
+#define F(body, name, idx) body(name, idx)
+
+#define F10(body, name, idx) \
+	F(body, PASTE(name, idx), 0) F(body, PASTE(name, idx), 1) F(body, PASTE(name, idx), 2) \
+	F(body, PASTE(name, idx), 3) F(body, PASTE(name, idx), 4) F(body, PASTE(name, idx), 5) \
+	F(body, PASTE(name, idx), 6) F(body, PASTE(name, idx), 7) F(body, PASTE(name, idx), 8) \
+	F(body, PASTE(name, idx), 9)
+
+#define F100(body, name, idx) \
+	F10(body, PASTE(name, idx), 0) F10(body, PASTE(name, idx), 1) F10(body, PASTE(name, idx), 2) \
+	F10(body, PASTE(name, idx), 3) F10(body, PASTE(name, idx), 4) F10(body, PASTE(name, idx), 5) \
+	F10(body, PASTE(name, idx), 6) F10(body, PASTE(name, idx), 7) F10(body, PASTE(name, idx), 8) \
+	F10(body, PASTE(name, idx), 9)
+
+#define F1000(body, name, idx) \
+	F100(body, PASTE(name, idx), 0) F100(body, PASTE(name, idx), 1) F100(body, PASTE(name, idx), 2) \
+	F100(body, PASTE(name, idx), 3) F100(body, PASTE(name, idx), 4) F100(body, PASTE(name, idx), 5) \
+	F100(body, PASTE(name, idx), 6) F100(body, PASTE(name, idx), 7) F100(body, PASTE(name, idx), 8) \
+	F100(body, PASTE(name, idx), 9)
+
+#define F10000(body, name, idx) \
+	F1000(body, PASTE(name, idx), 0) F1000(body, PASTE(name, idx), 1) F1000(body, PASTE(name, idx), 2) \
+	F1000(body, PASTE(name, idx), 3) F1000(body, PASTE(name, idx), 4) F1000(body, PASTE(name, idx), 5) \
+	F1000(body, PASTE(name, idx), 6) F1000(body, PASTE(name, idx), 7) F1000(body, PASTE(name, idx), 8) \
+	F1000(body, PASTE(name, idx), 9)
+
+F10000(DEF, uprobe_multi_func_, 0)
+F10000(DEF, uprobe_multi_func_, 1)
+F10000(DEF, uprobe_multi_func_, 2)
+F10000(DEF, uprobe_multi_func_, 3)
+F10000(DEF, uprobe_multi_func_, 4)
+
+static int bench(void)
+{
+	F10000(CALL, uprobe_multi_func_, 0)
+	F10000(CALL, uprobe_multi_func_, 1)
+	F10000(CALL, uprobe_multi_func_, 2)
+	F10000(CALL, uprobe_multi_func_, 3)
+	F10000(CALL, uprobe_multi_func_, 4)
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	if (argc != 2)
+		goto error;
+
+	if (!strcmp("bench", argv[1]))
+		return bench();
+
+error:
+	fprintf(stderr, "usage: %s <bench>\n", argv[0]);
+	return -1;
+}
-- 
GitLab


From 3706919ee05f7667f5751eba3e06ae5b2bf1bffa Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:35 +0200
Subject: [PATCH 1449/1806] selftests/bpf: Add uprobe_multi bench test

Adding test that attaches 50k uprobes in uprobe_multi binary.

After the attach is done we run the binary and make sure we
get proper amount of hits.

The resulting attach/detach times on my setup:

  test_bench_attach_uprobe:PASS:uprobe_multi__open 0 nsec
  test_bench_attach_uprobe:PASS:uprobe_multi__attach 0 nsec
  test_bench_attach_uprobe:PASS:uprobes_count 0 nsec
  test_bench_attach_uprobe: attached in   0.346s
  test_bench_attach_uprobe: detached in   0.419s
  #262/5   uprobe_multi_test/bench_uprobe:OK

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-24-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/uprobe_multi_test.c        | 40 +++++++++++++++++++
 .../selftests/bpf/progs/uprobe_multi_bench.c  | 15 +++++++
 2 files changed, 55 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/uprobe_multi_bench.c

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 3860beda82c80..5fa555f4f68d2 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -3,7 +3,9 @@
 #include <unistd.h>
 #include <test_progs.h>
 #include "uprobe_multi.skel.h"
+#include "uprobe_multi_bench.skel.h"
 #include "bpf/libbpf_internal.h"
+#include "testing_helpers.h"
 
 static char test_data[] = "test_data";
 
@@ -197,6 +199,42 @@ cleanup:
 	free(offsets);
 }
 
+static void test_bench_attach_uprobe(void)
+{
+	long attach_start_ns = 0, attach_end_ns = 0;
+	struct uprobe_multi_bench *skel = NULL;
+	long detach_start_ns, detach_end_ns;
+	double attach_delta, detach_delta;
+	int err;
+
+	skel = uprobe_multi_bench__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi_bench__open_and_load"))
+		goto cleanup;
+
+	attach_start_ns = get_time_ns();
+
+	err = uprobe_multi_bench__attach(skel);
+	if (!ASSERT_OK(err, "uprobe_multi_bench__attach"))
+		goto cleanup;
+
+	attach_end_ns = get_time_ns();
+
+	system("./uprobe_multi bench");
+
+	ASSERT_EQ(skel->bss->count, 50000, "uprobes_count");
+
+cleanup:
+	detach_start_ns = get_time_ns();
+	uprobe_multi_bench__destroy(skel);
+	detach_end_ns = get_time_ns();
+
+	attach_delta = (attach_end_ns - attach_start_ns) / 1000000000.0;
+	detach_delta = (detach_end_ns - detach_start_ns) / 1000000000.0;
+
+	printf("%s: attached in %7.3lfs\n", __func__, attach_delta);
+	printf("%s: detached in %7.3lfs\n", __func__, detach_delta);
+}
+
 void test_uprobe_multi_test(void)
 {
 	if (test__start_subtest("skel_api"))
@@ -207,4 +245,6 @@ void test_uprobe_multi_test(void)
 		test_attach_api_syms();
 	if (test__start_subtest("link_api"))
 		test_link_api();
+	if (test__start_subtest("bench_uprobe"))
+		test_bench_attach_uprobe();
 }
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c b/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c
new file mode 100644
index 0000000000000..5367f6105e303
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int count;
+
+SEC("uprobe.multi/./uprobe_multi:uprobe_multi_func_*")
+int uprobe_bench(struct pt_regs *ctx)
+{
+	count++;
+	return 0;
+}
-- 
GitLab


From 4cde2d8aa7f705fdc395e05d4acd7a9512871f59 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:36 +0200
Subject: [PATCH 1450/1806] selftests/bpf: Add uprobe_multi usdt test code

Adding code in uprobe_multi test binary that defines 50k usdts
and will serve as attach point for uprobe_multi usdt bench test
in following patch.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-25-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/uprobe_multi.c | 26 +++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/uprobe_multi.c b/tools/testing/selftests/bpf/uprobe_multi.c
index d19184103fa31..a61ceab60b68a 100644
--- a/tools/testing/selftests/bpf/uprobe_multi.c
+++ b/tools/testing/selftests/bpf/uprobe_multi.c
@@ -2,6 +2,7 @@
 
 #include <stdio.h>
 #include <string.h>
+#include <sdt.h>
 
 #define __PASTE(a, b) a##b
 #define PASTE(a, b) __PASTE(a, b)
@@ -53,6 +54,27 @@ static int bench(void)
 	return 0;
 }
 
+#define PROBE STAP_PROBE(test, usdt);
+
+#define PROBE10    PROBE PROBE PROBE PROBE PROBE \
+		   PROBE PROBE PROBE PROBE PROBE
+#define PROBE100   PROBE10 PROBE10 PROBE10 PROBE10 PROBE10 \
+		   PROBE10 PROBE10 PROBE10 PROBE10 PROBE10
+#define PROBE1000  PROBE100 PROBE100 PROBE100 PROBE100 PROBE100 \
+		   PROBE100 PROBE100 PROBE100 PROBE100 PROBE100
+#define PROBE10000 PROBE1000 PROBE1000 PROBE1000 PROBE1000 PROBE1000 \
+		   PROBE1000 PROBE1000 PROBE1000 PROBE1000 PROBE1000
+
+static int usdt(void)
+{
+	PROBE10000
+	PROBE10000
+	PROBE10000
+	PROBE10000
+	PROBE10000
+	return 0;
+}
+
 int main(int argc, char **argv)
 {
 	if (argc != 2)
@@ -60,8 +82,10 @@ int main(int argc, char **argv)
 
 	if (!strcmp("bench", argv[1]))
 		return bench();
+	if (!strcmp("usdt", argv[1]))
+		return usdt();
 
 error:
-	fprintf(stderr, "usage: %s <bench>\n", argv[0]);
+	fprintf(stderr, "usage: %s <bench|usdt>\n", argv[0]);
 	return -1;
 }
-- 
GitLab


From 85209e839fc2933ca1a167f3af89dce5abff42d4 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:37 +0200
Subject: [PATCH 1451/1806] selftests/bpf: Add uprobe_multi usdt bench test

Adding test that attaches 50k usdt probes in usdt_multi binary.

After the attach is done we run the binary and make sure we get
proper amount of hits.

With current uprobes:

  # perf stat --null ./test_progs -n 254/6
  #254/6   uprobe_multi_test/bench_usdt:OK
  #254     uprobe_multi_test:OK
  Summary: 1/1 PASSED, 0 SKIPPED, 0 FAILED

   Performance counter stats for './test_progs -n 254/6':

      1353.659680562 seconds time elapsed

With uprobe_multi link:

  # perf stat --null ./test_progs -n 254/6
  #254/6   uprobe_multi_test/bench_usdt:OK
  #254     uprobe_multi_test:OK
  Summary: 1/1 PASSED, 0 SKIPPED, 0 FAILED

   Performance counter stats for './test_progs -n 254/6':

         0.322046364 seconds time elapsed

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-26-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/uprobe_multi_test.c        | 39 +++++++++++++++++++
 .../selftests/bpf/progs/uprobe_multi_usdt.c   | 16 ++++++++
 2 files changed, 55 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 5fa555f4f68d2..d7e30934feb9b 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -4,6 +4,7 @@
 #include <test_progs.h>
 #include "uprobe_multi.skel.h"
 #include "uprobe_multi_bench.skel.h"
+#include "uprobe_multi_usdt.skel.h"
 #include "bpf/libbpf_internal.h"
 #include "testing_helpers.h"
 
@@ -235,6 +236,42 @@ cleanup:
 	printf("%s: detached in %7.3lfs\n", __func__, detach_delta);
 }
 
+static void test_bench_attach_usdt(void)
+{
+	long attach_start_ns = 0, attach_end_ns = 0;
+	struct uprobe_multi_usdt *skel = NULL;
+	long detach_start_ns, detach_end_ns;
+	double attach_delta, detach_delta;
+
+	skel = uprobe_multi_usdt__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open"))
+		goto cleanup;
+
+	attach_start_ns = get_time_ns();
+
+	skel->links.usdt0 = bpf_program__attach_usdt(skel->progs.usdt0, -1, "./uprobe_multi",
+						     "test", "usdt", NULL);
+	if (!ASSERT_OK_PTR(skel->links.usdt0, "bpf_program__attach_usdt"))
+		goto cleanup;
+
+	attach_end_ns = get_time_ns();
+
+	system("./uprobe_multi usdt");
+
+	ASSERT_EQ(skel->bss->count, 50000, "usdt_count");
+
+cleanup:
+	detach_start_ns = get_time_ns();
+	uprobe_multi_usdt__destroy(skel);
+	detach_end_ns = get_time_ns();
+
+	attach_delta = (attach_end_ns - attach_start_ns) / 1000000000.0;
+	detach_delta = (detach_end_ns - detach_start_ns) / 1000000000.0;
+
+	printf("%s: attached in %7.3lfs\n", __func__, attach_delta);
+	printf("%s: detached in %7.3lfs\n", __func__, detach_delta);
+}
+
 void test_uprobe_multi_test(void)
 {
 	if (test__start_subtest("skel_api"))
@@ -247,4 +284,6 @@ void test_uprobe_multi_test(void)
 		test_link_api();
 	if (test__start_subtest("bench_uprobe"))
 		test_bench_attach_uprobe();
+	if (test__start_subtest("bench_usdt"))
+		test_bench_attach_usdt();
 }
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c b/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c
new file mode 100644
index 0000000000000..9e1c33d0bd2ff
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/usdt.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+int count;
+
+SEC("usdt")
+int usdt0(struct pt_regs *ctx)
+{
+	count++;
+	return 0;
+}
-- 
GitLab


From e7cf9a48f8d634a3c65a28715158b6f6c0540e71 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:38 +0200
Subject: [PATCH 1452/1806] selftests/bpf: Add uprobe_multi cookie test

Adding test for cookies setup/retrieval in uprobe_link uprobes
and making sure bpf_get_attach_cookie works properly.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-27-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/bpf_cookie.c     | 78 +++++++++++++++++++
 1 file changed, 78 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
index 26b2d1bffdfd5..1454cebc262b6 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -11,6 +11,7 @@
 #include <bpf/btf.h>
 #include "test_bpf_cookie.skel.h"
 #include "kprobe_multi.skel.h"
+#include "uprobe_multi.skel.h"
 
 /* uprobe attach point */
 static noinline void trigger_func(void)
@@ -239,6 +240,81 @@ cleanup:
 	bpf_link__destroy(link1);
 	kprobe_multi__destroy(skel);
 }
+
+/* defined in prog_tests/uprobe_multi_test.c */
+void uprobe_multi_func_1(void);
+void uprobe_multi_func_2(void);
+void uprobe_multi_func_3(void);
+
+static void uprobe_multi_test_run(struct uprobe_multi *skel)
+{
+	skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1;
+	skel->bss->uprobe_multi_func_2_addr = (__u64) uprobe_multi_func_2;
+	skel->bss->uprobe_multi_func_3_addr = (__u64) uprobe_multi_func_3;
+
+	skel->bss->pid = getpid();
+	skel->bss->test_cookie = true;
+
+	uprobe_multi_func_1();
+	uprobe_multi_func_2();
+	uprobe_multi_func_3();
+
+	ASSERT_EQ(skel->bss->uprobe_multi_func_1_result, 1, "uprobe_multi_func_1_result");
+	ASSERT_EQ(skel->bss->uprobe_multi_func_2_result, 1, "uprobe_multi_func_2_result");
+	ASSERT_EQ(skel->bss->uprobe_multi_func_3_result, 1, "uprobe_multi_func_3_result");
+
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_1_result, 1, "uretprobe_multi_func_1_result");
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_2_result, 1, "uretprobe_multi_func_2_result");
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_3_result, 1, "uretprobe_multi_func_3_result");
+}
+
+static void uprobe_multi_attach_api_subtest(void)
+{
+	struct bpf_link *link1 = NULL, *link2 = NULL;
+	struct uprobe_multi *skel = NULL;
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+	const char *syms[3] = {
+		"uprobe_multi_func_1",
+		"uprobe_multi_func_2",
+		"uprobe_multi_func_3",
+	};
+	__u64 cookies[3];
+
+	cookies[0] = 3; /* uprobe_multi_func_1 */
+	cookies[1] = 1; /* uprobe_multi_func_2 */
+	cookies[2] = 2; /* uprobe_multi_func_3 */
+
+	opts.syms = syms;
+	opts.cnt = ARRAY_SIZE(syms);
+	opts.cookies = &cookies[0];
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi"))
+		goto cleanup;
+
+	link1 = bpf_program__attach_uprobe_multi(skel->progs.uprobe, -1,
+						 "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link1, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	cookies[0] = 2; /* uprobe_multi_func_1 */
+	cookies[1] = 3; /* uprobe_multi_func_2 */
+	cookies[2] = 1; /* uprobe_multi_func_3 */
+
+	opts.retprobe = true;
+	link2 = bpf_program__attach_uprobe_multi(skel->progs.uretprobe, -1,
+						      "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link2, "bpf_program__attach_uprobe_multi_retprobe"))
+		goto cleanup;
+
+	uprobe_multi_test_run(skel);
+
+cleanup:
+	bpf_link__destroy(link2);
+	bpf_link__destroy(link1);
+	uprobe_multi__destroy(skel);
+}
+
 static void uprobe_subtest(struct test_bpf_cookie *skel)
 {
 	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts);
@@ -515,6 +591,8 @@ void test_bpf_cookie(void)
 		kprobe_multi_attach_api_subtest();
 	if (test__start_subtest("uprobe"))
 		uprobe_subtest(skel);
+	if (test__start_subtest("multi_uprobe_attach_api"))
+		uprobe_multi_attach_api_subtest();
 	if (test__start_subtest("tracepoint"))
 		tp_subtest(skel);
 	if (test__start_subtest("perf_event"))
-- 
GitLab


From d571efae0f1d3d3b6c3aa294889d47a39b4ab8a1 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:39 +0200
Subject: [PATCH 1453/1806] selftests/bpf: Add uprobe_multi pid filter tests

Running api and link tests also with pid filter and checking
the probe gets executed only for specific pid.

Spawning extra process to trigger attached uprobes and checking
we get correct counts from executed programs.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-28-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/uprobe_multi_test.c        | 132 ++++++++++++++++--
 .../selftests/bpf/progs/uprobe_multi.c        |   6 +-
 2 files changed, 126 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index d7e30934feb9b..bc07921a5a77a 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -25,14 +25,87 @@ noinline void uprobe_multi_func_3(void)
 	asm volatile ("");
 }
 
-static void uprobe_multi_test_run(struct uprobe_multi *skel)
+struct child {
+	int go[2];
+	int pid;
+};
+
+static void release_child(struct child *child)
+{
+	int child_status;
+
+	if (!child)
+		return;
+	close(child->go[1]);
+	close(child->go[0]);
+	if (child->pid > 0)
+		waitpid(child->pid, &child_status, 0);
+}
+
+static void kick_child(struct child *child)
+{
+	char c = 1;
+
+	if (child) {
+		write(child->go[1], &c, 1);
+		release_child(child);
+	}
+	fflush(NULL);
+}
+
+static struct child *spawn_child(void)
+{
+	static struct child child;
+	int err;
+	int c;
+
+	/* pipe to notify child to execute the trigger functions */
+	if (pipe(child.go))
+		return NULL;
+
+	child.pid = fork();
+	if (child.pid < 0) {
+		release_child(&child);
+		errno = EINVAL;
+		return NULL;
+	}
+
+	/* child */
+	if (child.pid == 0) {
+		close(child.go[1]);
+
+		/* wait for parent's kick */
+		err = read(child.go[0], &c, 1);
+		if (err != 1)
+			exit(err);
+
+		uprobe_multi_func_1();
+		uprobe_multi_func_2();
+		uprobe_multi_func_3();
+
+		exit(errno);
+	}
+
+	return &child;
+}
+
+static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child)
 {
 	skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1;
 	skel->bss->uprobe_multi_func_2_addr = (__u64) uprobe_multi_func_2;
 	skel->bss->uprobe_multi_func_3_addr = (__u64) uprobe_multi_func_3;
 
 	skel->bss->user_ptr = test_data;
-	skel->bss->pid = getpid();
+
+	/*
+	 * Disable pid check in bpf program if we are pid filter test,
+	 * because the probe should be executed only by child->pid
+	 * passed at the probe attach.
+	 */
+	skel->bss->pid = child ? 0 : getpid();
+
+	if (child)
+		kick_child(child);
 
 	/* trigger all probes */
 	uprobe_multi_func_1();
@@ -52,6 +125,9 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel)
 	ASSERT_EQ(skel->bss->uretprobe_multi_func_3_result, 2, "uretprobe_multi_func_3_result");
 
 	ASSERT_EQ(skel->bss->uprobe_multi_sleep_result, 6, "uprobe_multi_sleep_result");
+
+	if (child)
+		ASSERT_EQ(skel->bss->child_pid, child->pid, "uprobe_multi_child_pid");
 }
 
 static void test_skel_api(void)
@@ -67,15 +143,17 @@ static void test_skel_api(void)
 	if (!ASSERT_OK(err, "uprobe_multi__attach"))
 		goto cleanup;
 
-	uprobe_multi_test_run(skel);
+	uprobe_multi_test_run(skel, NULL);
 
 cleanup:
 	uprobe_multi__destroy(skel);
 }
 
 static void
-test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi_opts *opts)
+__test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi_opts *opts,
+		  struct child *child)
 {
+	pid_t pid = child ? child->pid : -1;
 	struct uprobe_multi *skel = NULL;
 
 	skel = uprobe_multi__open_and_load();
@@ -83,35 +161,51 @@ test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi
 		goto cleanup;
 
 	opts->retprobe = false;
-	skel->links.uprobe = bpf_program__attach_uprobe_multi(skel->progs.uprobe, -1,
+	skel->links.uprobe = bpf_program__attach_uprobe_multi(skel->progs.uprobe, pid,
 							      binary, pattern, opts);
 	if (!ASSERT_OK_PTR(skel->links.uprobe, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
 	opts->retprobe = true;
-	skel->links.uretprobe = bpf_program__attach_uprobe_multi(skel->progs.uretprobe, -1,
+	skel->links.uretprobe = bpf_program__attach_uprobe_multi(skel->progs.uretprobe, pid,
 								 binary, pattern, opts);
 	if (!ASSERT_OK_PTR(skel->links.uretprobe, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
 	opts->retprobe = false;
-	skel->links.uprobe_sleep = bpf_program__attach_uprobe_multi(skel->progs.uprobe_sleep, -1,
+	skel->links.uprobe_sleep = bpf_program__attach_uprobe_multi(skel->progs.uprobe_sleep, pid,
 								    binary, pattern, opts);
 	if (!ASSERT_OK_PTR(skel->links.uprobe_sleep, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
 	opts->retprobe = true;
 	skel->links.uretprobe_sleep = bpf_program__attach_uprobe_multi(skel->progs.uretprobe_sleep,
-								       -1, binary, pattern, opts);
+								       pid, binary, pattern, opts);
 	if (!ASSERT_OK_PTR(skel->links.uretprobe_sleep, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
-	uprobe_multi_test_run(skel);
+	uprobe_multi_test_run(skel, child);
 
 cleanup:
 	uprobe_multi__destroy(skel);
 }
 
+static void
+test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi_opts *opts)
+{
+	struct child *child;
+
+	/* no pid filter */
+	__test_attach_api(binary, pattern, opts, NULL);
+
+	/* pid filter */
+	child = spawn_child();
+	if (!ASSERT_OK_PTR(child, "spawn_child"))
+		return;
+
+	__test_attach_api(binary, pattern, opts, child);
+}
+
 static void test_attach_api_pattern(void)
 {
 	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
@@ -134,7 +228,7 @@ static void test_attach_api_syms(void)
 	test_attach_api("/proc/self/exe", NULL, &opts);
 }
 
-static void test_link_api(void)
+static void __test_link_api(struct child *child)
 {
 	int prog_fd, link1_fd = -1, link2_fd = -1, link3_fd = -1, link4_fd = -1;
 	LIBBPF_OPTS(bpf_link_create_opts, opts);
@@ -155,6 +249,7 @@ static void test_link_api(void)
 	opts.uprobe_multi.path = path;
 	opts.uprobe_multi.offsets = offsets;
 	opts.uprobe_multi.cnt = ARRAY_SIZE(syms);
+	opts.uprobe_multi.pid = child ? child->pid : 0;
 
 	skel = uprobe_multi__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
@@ -184,7 +279,7 @@ static void test_link_api(void)
 	if (!ASSERT_GE(link4_fd, 0, "link4_fd"))
 		goto cleanup;
 
-	uprobe_multi_test_run(skel);
+	uprobe_multi_test_run(skel, child);
 
 cleanup:
 	if (link1_fd >= 0)
@@ -200,6 +295,21 @@ cleanup:
 	free(offsets);
 }
 
+void test_link_api(void)
+{
+	struct child *child;
+
+	/* no pid filter */
+	__test_link_api(NULL);
+
+	/* pid filter */
+	child = spawn_child();
+	if (!ASSERT_OK_PTR(child, "spawn_child"))
+		return;
+
+	__test_link_api(child);
+}
+
 static void test_bench_attach_uprobe(void)
 {
 	long attach_start_ns = 0, attach_end_ns = 0;
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c
index ab467970256a6..ec648a6699e63 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_multi.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c
@@ -21,6 +21,8 @@ __u64 uretprobe_multi_func_3_result = 0;
 __u64 uprobe_multi_sleep_result = 0;
 
 int pid = 0;
+int child_pid = 0;
+
 bool test_cookie = false;
 void *user_ptr = 0;
 
@@ -34,7 +36,9 @@ static __always_inline bool verify_sleepable_user_copy(void)
 
 static void uprobe_multi_check(void *ctx, bool is_return, bool is_sleep)
 {
-	if (bpf_get_current_pid_tgid() >> 32 != pid)
+	child_pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid && child_pid != pid)
 		return;
 
 	__u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0;
-- 
GitLab


From 8909a9392b4193f6d76dab9508c63c71458210df Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 9 Aug 2023 10:34:40 +0200
Subject: [PATCH 1454/1806] selftests/bpf: Add extra link to uprobe_multi tests

Attaching extra program to same functions system wide for api
and link tests.

This way we can test the pid filter works properly when there's
extra system wide consumer on the same uprobe that will trigger
the original uprobe handler.

We expect to have the same counts as before.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230809083440.3209381-29-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/uprobe_multi_test.c | 16 ++++++++++++++++
 tools/testing/selftests/bpf/progs/uprobe_multi.c |  6 ++++++
 2 files changed, 22 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index bc07921a5a77a..cd051d3901a99 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -184,6 +184,12 @@ __test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_mul
 	if (!ASSERT_OK_PTR(skel->links.uretprobe_sleep, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
+	opts->retprobe = false;
+	skel->links.uprobe_extra = bpf_program__attach_uprobe_multi(skel->progs.uprobe_extra, -1,
+								    binary, pattern, opts);
+	if (!ASSERT_OK_PTR(skel->links.uprobe_extra, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
 	uprobe_multi_test_run(skel, child);
 
 cleanup:
@@ -240,6 +246,7 @@ static void __test_link_api(struct child *child)
 		"uprobe_multi_func_2",
 		"uprobe_multi_func_3",
 	};
+	int link_extra_fd = -1;
 	int err;
 
 	err = elf_resolve_syms_offsets(path, 3, syms, (unsigned long **) &offsets);
@@ -279,6 +286,13 @@ static void __test_link_api(struct child *child)
 	if (!ASSERT_GE(link4_fd, 0, "link4_fd"))
 		goto cleanup;
 
+	opts.kprobe_multi.flags = 0;
+	opts.uprobe_multi.pid = 0;
+	prog_fd = bpf_program__fd(skel->progs.uprobe_extra);
+	link_extra_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_GE(link_extra_fd, 0, "link_extra_fd"))
+		goto cleanup;
+
 	uprobe_multi_test_run(skel, child);
 
 cleanup:
@@ -290,6 +304,8 @@ cleanup:
 		close(link3_fd);
 	if (link4_fd >= 0)
 		close(link4_fd);
+	if (link_extra_fd >= 0)
+		close(link_extra_fd);
 
 	uprobe_multi__destroy(skel);
 	free(offsets);
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c
index ec648a6699e63..419d9aa28fce5 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_multi.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c
@@ -93,3 +93,9 @@ int uretprobe_sleep(struct pt_regs *ctx)
 	uprobe_multi_check(ctx, true, true);
 	return 0;
 }
+
+SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*")
+int uprobe_extra(struct pt_regs *ctx)
+{
+	return 0;
+}
-- 
GitLab


From 90308679c297ffcbb317c715ef434e9fb3c881dc Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Fri, 18 Aug 2023 04:07:46 +0100
Subject: [PATCH 1455/1806] net: pcs: lynxi: implement pcs_disable op

When switching from 10GBase-R/5GBase-R/USXGMII to one of the interface
modes provided by mtk-pcs-lynxi we need to make sure to always perform
a full configuration of the PHYA.

Implement pcs_disable op which resets the stored interface mode to
PHY_INTERFACE_MODE_NA to trigger a full reconfiguration once the LynxI
PCS driver had previously been deselected in favor of another PCS
driver such as the to-be-added driver for the USXGMII PCS found in
MT7988.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/f23d1a60d2c9d2fb72e32dcb0eaa5f7e867a3d68.1692327891.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-mtk-lynxi.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/pcs/pcs-mtk-lynxi.c b/drivers/net/pcs/pcs-mtk-lynxi.c
index b0f3ede945d96..8501dd365279b 100644
--- a/drivers/net/pcs/pcs-mtk-lynxi.c
+++ b/drivers/net/pcs/pcs-mtk-lynxi.c
@@ -233,11 +233,19 @@ static void mtk_pcs_lynxi_link_up(struct phylink_pcs *pcs,
 	}
 }
 
+static void mtk_pcs_lynxi_disable(struct phylink_pcs *pcs)
+{
+	struct mtk_pcs_lynxi *mpcs = pcs_to_mtk_pcs_lynxi(pcs);
+
+	mpcs->interface = PHY_INTERFACE_MODE_NA;
+}
+
 static const struct phylink_pcs_ops mtk_pcs_lynxi_ops = {
 	.pcs_get_state = mtk_pcs_lynxi_get_state,
 	.pcs_config = mtk_pcs_lynxi_config,
 	.pcs_an_restart = mtk_pcs_lynxi_restart_an,
 	.pcs_link_up = mtk_pcs_lynxi_link_up,
+	.pcs_disable = mtk_pcs_lynxi_disable,
 };
 
 struct phylink_pcs *mtk_pcs_lynxi_create(struct device *dev,
-- 
GitLab


From 3a198c95c95da10ad844cbeade2fe40bdf14c411 Mon Sep 17 00:00:00 2001
From: "GONG, Ruiqi" <gongruiqi1@huawei.com>
Date: Mon, 21 Aug 2023 09:32:18 +0800
Subject: [PATCH 1456/1806] alx: fix OOB-read compiler warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The following message shows up when compiling with W=1:

In function ‘fortify_memcpy_chk’,
    inlined from ‘alx_get_ethtool_stats’ at drivers/net/ethernet/atheros/alx/ethtool.c:297:2:
./include/linux/fortify-string.h:592:4: error: call to ‘__read_overflow2_field’
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Werror=attribute-warning]
  592 |    __read_overflow2_field(q_size_field, size);
      |    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

In order to get alx stats altogether, alx_get_ethtool_stats() reads
beyond hw->stats.rx_ok. Fix this warning by directly copying hw->stats,
and refactor the unnecessarily complicated BUILD_BUG_ON btw.

Signed-off-by: GONG, Ruiqi <gongruiqi1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230821013218.1614265-1-gongruiqi@huaweicloud.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/atheros/alx/ethtool.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/atheros/alx/ethtool.c b/drivers/net/ethernet/atheros/alx/ethtool.c
index b716adacd8159..7f6b69a523676 100644
--- a/drivers/net/ethernet/atheros/alx/ethtool.c
+++ b/drivers/net/ethernet/atheros/alx/ethtool.c
@@ -292,9 +292,8 @@ static void alx_get_ethtool_stats(struct net_device *netdev,
 	spin_lock(&alx->stats_lock);
 
 	alx_update_hw_stats(hw);
-	BUILD_BUG_ON(sizeof(hw->stats) - offsetof(struct alx_hw_stats, rx_ok) <
-		     ALX_NUM_STATS * sizeof(u64));
-	memcpy(data, &hw->stats.rx_ok, ALX_NUM_STATS * sizeof(u64));
+	BUILD_BUG_ON(sizeof(hw->stats) != ALX_NUM_STATS * sizeof(u64));
+	memcpy(data, &hw->stats, sizeof(hw->stats));
 
 	spin_unlock(&alx->stats_lock);
 }
-- 
GitLab


From 93ca82447c3eab149b5b2588ab8bd9aa2eacef7c Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 17 Aug 2023 14:15:23 -0700
Subject: [PATCH 1457/1806] wifi: cfg80211: Annotate struct cfg80211_acl_data
 with __counted_by

Prepare for the coming implementation by GCC and Clang of the __counted_by
attribute. Flexible array members annotated with __counted_by can have
their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS
(for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family
functions).

As found with Coccinelle[1], add __counted_by for struct cfg80211_acl_data.
Additionally, since the element count member must be set before accessing
the annotated flexible array member, move its initialization earlier.

[1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci

Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-wireless@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20230817211531.4193219-1-keescook@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 2 +-
 net/wireless/nl80211.c | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index d6fa7c8767ad3..eb73b5af5d043 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1282,7 +1282,7 @@ struct cfg80211_acl_data {
 	int n_acl_entries;
 
 	/* Keep it last */
-	struct mac_address mac_addrs[];
+	struct mac_address mac_addrs[] __counted_by(n_acl_entries);
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 8bcf8e293308e..80633e815311d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4889,13 +4889,12 @@ static struct cfg80211_acl_data *parse_acl_data(struct wiphy *wiphy,
 	acl = kzalloc(struct_size(acl, mac_addrs, n_entries), GFP_KERNEL);
 	if (!acl)
 		return ERR_PTR(-ENOMEM);
+	acl->n_acl_entries = n_entries;
 
 	nla_for_each_nested(attr, info->attrs[NL80211_ATTR_MAC_ADDRS], tmp) {
 		memcpy(acl->mac_addrs[i].addr, nla_data(attr), ETH_ALEN);
 		i++;
 	}
-
-	acl->n_acl_entries = n_entries;
 	acl->acl_policy = acl_policy;
 
 	return acl;
-- 
GitLab


From d4d3aaf25a6600d58774978cea9068974a8ea674 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 17 Aug 2023 14:15:24 -0700
Subject: [PATCH 1458/1806] wifi: cfg80211: Annotate struct cfg80211_cqm_config
 with __counted_by

Prepare for the coming implementation by GCC and Clang of the __counted_by
attribute. Flexible array members annotated with __counted_by can have
their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS
(for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family
functions).

As found with Coccinelle[1], add __counted_by for struct cfg80211_cqm_config.

[1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci

Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-wireless@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20230817211531.4193219-2-keescook@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/core.h b/net/wireless/core.h
index 8a807b609ef73..507d184b8b40b 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -298,7 +298,7 @@ struct cfg80211_cqm_config {
 	u32 rssi_hyst;
 	s32 last_rssi_event_value;
 	int n_rssi_thresholds;
-	s32 rssi_thresholds[];
+	s32 rssi_thresholds[] __counted_by(n_rssi_thresholds);
 };
 
 void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev);
-- 
GitLab


From c14679d7005a4d26289eadb4f5fe499aca78ef7c Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 17 Aug 2023 14:15:25 -0700
Subject: [PATCH 1459/1806] wifi: cfg80211: Annotate struct
 cfg80211_mbssid_elems with __counted_by

Prepare for the coming implementation by GCC and Clang of the __counted_by
attribute. Flexible array members annotated with __counted_by can have
their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS
(for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family
functions).

As found with Coccinelle[1], add __counted_by for struct cfg80211_mbssid_elems.
Additionally, since the element count member must be set before accessing
the annotated flexible array member, move its initialization earlier.

[1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci

Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-wireless@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20230817211531.4193219-3-keescook@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 2 +-
 net/wireless/nl80211.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index eb73b5af5d043..5c7d091b39253 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1187,7 +1187,7 @@ struct cfg80211_mbssid_elems {
 	struct {
 		const u8 *data;
 		size_t len;
-	} elem[];
+	} elem[] __counted_by(cnt);
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 80633e815311d..9ba4266368db1 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5438,13 +5438,13 @@ nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs)
 	elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL);
 	if (!elems)
 		return ERR_PTR(-ENOMEM);
+	elems->cnt = num_elems;
 
 	nla_for_each_nested(nl_elems, attrs, rem_elems) {
 		elems->elem[i].data = nla_data(nl_elems);
 		elems->elem[i].len = nla_len(nl_elems);
 		i++;
 	}
-	elems->cnt = num_elems;
 	return elems;
 }
 
-- 
GitLab


From 342bc7c9e877847d602c4a67c3135051df07cc4d Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 17 Aug 2023 14:15:26 -0700
Subject: [PATCH 1460/1806] wifi: cfg80211: Annotate struct
 cfg80211_pmsr_request with __counted_by

Prepare for the coming implementation by GCC and Clang of the __counted_by
attribute. Flexible array members annotated with __counted_by can have
their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS
(for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family
functions).

As found with Coccinelle[1], add __counted_by for struct cfg80211_pmsr_request.
Additionally, since the element count member must be set before accessing
the annotated flexible array member, move its initialization earlier.

[1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci

Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-wireless@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20230817211531.4193219-4-keescook@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 2 +-
 net/wireless/pmsr.c    | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 5c7d091b39253..e9ca4726a7324 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3948,7 +3948,7 @@ struct cfg80211_pmsr_request {
 
 	struct list_head list;
 
-	struct cfg80211_pmsr_request_peer peers[];
+	struct cfg80211_pmsr_request_peer peers[] __counted_by(n_peers);
 };
 
 /**
diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c
index 77000a2648554..9611aa0bd0513 100644
--- a/net/wireless/pmsr.c
+++ b/net/wireless/pmsr.c
@@ -291,6 +291,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info)
 	req = kzalloc(struct_size(req, peers, count), GFP_KERNEL);
 	if (!req)
 		return -ENOMEM;
+	req->n_peers = count;
 
 	if (info->attrs[NL80211_ATTR_TIMEOUT])
 		req->timeout = nla_get_u32(info->attrs[NL80211_ATTR_TIMEOUT]);
@@ -321,8 +322,6 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info)
 			goto out_err;
 		idx++;
 	}
-
-	req->n_peers = count;
 	req->cookie = cfg80211_assign_cookie(rdev);
 	req->nl_portid = info->snd_portid;
 
-- 
GitLab


From 7b6d7087031b69f0694cbef4485616c905664feb Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 17 Aug 2023 14:15:27 -0700
Subject: [PATCH 1461/1806] wifi: cfg80211: Annotate struct cfg80211_rnr_elems
 with __counted_by

Prepare for the coming implementation by GCC and Clang of the __counted_by
attribute. Flexible array members annotated with __counted_by can have
their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS
(for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family
functions).

As found with Coccinelle[1], add __counted_by for struct cfg80211_rnr_elems.
Additionally, since the element count member must be set before accessing
the annotated flexible array member, move its initialization earlier.

[1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci

Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-wireless@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20230817211531.4193219-5-keescook@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 2 +-
 net/wireless/nl80211.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index e9ca4726a7324..6efe216c01d25 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1204,7 +1204,7 @@ struct cfg80211_rnr_elems {
 	struct {
 		const u8 *data;
 		size_t len;
-	} elem[];
+	} elem[] __counted_by(cnt);
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 9ba4266368db1..0ffebf1a1eb62 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5470,13 +5470,13 @@ nl80211_parse_rnr_elems(struct wiphy *wiphy, struct nlattr *attrs,
 	elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL);
 	if (!elems)
 		return ERR_PTR(-ENOMEM);
+	elems->cnt = num_elems;
 
 	nla_for_each_nested(nl_elems, attrs, rem_elems) {
 		elems->elem[i].data = nla_data(nl_elems);
 		elems->elem[i].len = nla_len(nl_elems);
 		i++;
 	}
-	elems->cnt = num_elems;
 	return elems;
 }
 
-- 
GitLab


From e3eac9f32ec04112b39e01b574ac739382469bf9 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 17 Aug 2023 14:15:28 -0700
Subject: [PATCH 1462/1806] wifi: cfg80211: Annotate struct
 cfg80211_scan_request with __counted_by

Prepare for the coming implementation by GCC and Clang of the __counted_by
attribute. Flexible array members annotated with __counted_by can have
their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS
(for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family
functions).

As found with Coccinelle[1], add __counted_by for struct cfg80211_scan_request.
Additionally, since the element count member must be set before accessing
the annotated flexible array member, move its initialization earlier.

[1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci

Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-wireless@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20230817211531.4193219-6-keescook@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 6efe216c01d25..a2afc94a54084 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2544,7 +2544,7 @@ struct cfg80211_scan_request {
 	struct cfg80211_scan_6ghz_params *scan_6ghz_params;
 
 	/* keep last */
-	struct ieee80211_channel *channels[];
+	struct ieee80211_channel *channels[] __counted_by(n_channels);
 };
 
 static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask)
-- 
GitLab


From 545d3523dff0cf61ccd65da1c352f7c7c21fcfb0 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 17 Aug 2023 14:15:29 -0700
Subject: [PATCH 1463/1806] wifi: cfg80211: Annotate struct cfg80211_tid_config
 with __counted_by

Prepare for the coming implementation by GCC and Clang of the __counted_by
attribute. Flexible array members annotated with __counted_by can have
their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS
(for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family
functions).

As found with Coccinelle[1], add __counted_by for struct cfg80211_tid_config.

[1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci

Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-wireless@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20230817211531.4193219-7-keescook@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index a2afc94a54084..423fe9b85cb06 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -811,7 +811,7 @@ struct cfg80211_tid_cfg {
 struct cfg80211_tid_config {
 	const u8 *peer;
 	u32 n_tid_conf;
-	struct cfg80211_tid_cfg tid_conf[];
+	struct cfg80211_tid_cfg tid_conf[] __counted_by(n_tid_conf);
 };
 
 /**
-- 
GitLab


From 43c2817225fce05701f062a996255007481935e2 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Mon, 21 Aug 2023 16:41:04 +0800
Subject: [PATCH 1464/1806] net: remove unnecessary input parameter 'how' in
 ifdown function

When the ifdown function in the dst_ops structure is referenced, the input
parameter 'how' is always true. In the current implementation of the
ifdown interface, ip6_dst_ifdown does not use the input parameter 'how',
xfrm6_dst_ifdown and xfrm4_dst_ifdown functions use the input parameter
'unregister'. But false judgment on 'unregister' in xfrm6_dst_ifdown and
xfrm4_dst_ifdown is false, so remove the input parameter 'how' in ifdown
function.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230821084104.3812233-1-shaozhengchao@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/dst_ops.h   |  2 +-
 net/core/dst.c          |  2 +-
 net/ipv4/xfrm4_policy.c | 11 +----------
 net/ipv6/route.c        |  5 ++---
 net/ipv6/xfrm6_policy.c |  6 +-----
 5 files changed, 6 insertions(+), 20 deletions(-)

diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 632086b2f644a..6d1c8541183db 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -23,7 +23,7 @@ struct dst_ops {
 	u32 *			(*cow_metrics)(struct dst_entry *, unsigned long);
 	void			(*destroy)(struct dst_entry *);
 	void			(*ifdown)(struct dst_entry *,
-					  struct net_device *dev, int how);
+					  struct net_device *dev);
 	struct dst_entry *	(*negative_advice)(struct dst_entry *);
 	void			(*link_failure)(struct sk_buff *);
 	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
diff --git a/net/core/dst.c b/net/core/dst.c
index 79d9306ad1ee9..980e2fd2f013b 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -152,7 +152,7 @@ void dst_dev_put(struct dst_entry *dst)
 
 	dst->obsolete = DST_OBSOLETE_DEAD;
 	if (dst->ops->ifdown)
-		dst->ops->ifdown(dst, dev, true);
+		dst->ops->ifdown(dst, dev);
 	dst->input = dst_discard;
 	dst->output = dst_discard_out;
 	dst->dev = blackhole_netdev;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 9403bbaf1b616..cdcc0f6b4f0a2 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -124,22 +124,13 @@ static void xfrm4_dst_destroy(struct dst_entry *dst)
 	xfrm_dst_destroy(xdst);
 }
 
-static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
-			     int unregister)
-{
-	if (!unregister)
-		return;
-
-	xfrm_dst_ifdown(dst, dev);
-}
-
 static struct dst_ops xfrm4_dst_ops_template = {
 	.family =		AF_INET,
 	.update_pmtu =		xfrm4_update_pmtu,
 	.redirect =		xfrm4_redirect,
 	.cow_metrics =		dst_cow_metrics_generic,
 	.destroy =		xfrm4_dst_destroy,
-	.ifdown =		xfrm4_dst_ifdown,
+	.ifdown =		xfrm_dst_ifdown,
 	.local_out =		__ip_local_out,
 	.gc_thresh =		32768,
 };
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a5b74b91c8f39..846aec8e00933 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -90,7 +90,7 @@ unsigned int		ip6_mtu(const struct dst_entry *dst);
 static struct dst_entry *ip6_negative_advice(struct dst_entry *);
 static void		ip6_dst_destroy(struct dst_entry *);
 static void		ip6_dst_ifdown(struct dst_entry *,
-				       struct net_device *dev, int how);
+				       struct net_device *dev);
 static void		 ip6_dst_gc(struct dst_ops *ops);
 
 static int		ip6_pkt_discard(struct sk_buff *skb);
@@ -371,8 +371,7 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 	fib6_info_release(from);
 }
 
-static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
-			   int how)
+static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
 {
 	struct rt6_info *rt = (struct rt6_info *)dst;
 	struct inet6_dev *idev = rt->rt6i_idev;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index eecc5e59da17c..188224a76685d 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -124,14 +124,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
 	xfrm_dst_destroy(xdst);
 }
 
-static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
-			     int unregister)
+static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
 {
 	struct xfrm_dst *xdst;
 
-	if (!unregister)
-		return;
-
 	xdst = (struct xfrm_dst *)dst;
 	if (xdst->u.rt6.rt6i_idev->dev == dev) {
 		struct inet6_dev *loopback_idev =
-- 
GitLab


From b33663307002db8c9aac6783e31e3a786ed991c3 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 11:10:43 +0300
Subject: [PATCH 1465/1806] wifi: iwlwifi: mvm: advertise MLO only if EHT is
 enabled

If 11ax/EHT is disabled, then we shouldn't advertise MLO
support either.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.ae4f9151440e.I6ce0b98d063d5005fd7a613454fcdb8b866a417a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index ce7905faa08ff..e7fe5b76def4c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -315,8 +315,9 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	ieee80211_hw_set(hw, STA_MMPDU_TXQ);
 
 	/* Set this early since we need to have it for the check below */
-	if (mvm->mld_api_is_used &&
-	    mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	if (mvm->mld_api_is_used && mvm->nvm_data->sku_cap_11be_enable &&
+	    !iwlwifi_mod_params.disable_11ax &&
+	    !iwlwifi_mod_params.disable_11be)
 		hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO;
 
 	/* With MLD FW API, it tracks timing by itself,
-- 
GitLab


From 0c2f92f6a5ac258457e7c9d55c74f14a0f1937cd Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 11:10:44 +0300
Subject: [PATCH 1466/1806] wifi: iwlwifi: api: fix a small upper/lower-case
 typo

The structure name in the docs should be given in all
lower case matching the actual C declaration.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.c06f98055dbb.Ie9267108c57edcbb913f0d0f349eac85ca39409b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/debug.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
index 8fef38139bf6d..48ffab22bb7b4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2022 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -377,7 +377,7 @@ struct iwl_buf_alloc_cmd {
 #define DRAM_INFO_SECOND_MAGIC_WORD 0x89ABCDEF
 
 /**
- * struct iwL_dram_info - DRAM fragments allocation struct
+ * struct iwl_dram_info - DRAM fragments allocation struct
  *
  * Driver will fill in the first 1K(+) of the pointed DRAM fragment
  *
-- 
GitLab


From d9d115fed674351effd8610aad1e8f1178a5f8b9 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 11:10:45 +0300
Subject: [PATCH 1467/1806] wifi: iwlwifi: remove WARN from read_mem32()

There's no reason to warn here, it's not an internal consistency
issue, we even use this to check if the device is dead, and if it
read_mem() returns an error that's either because grab NIC access
or memory allocation failed, both of which are already noisy.

Just remove the warning entirely.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.5f4e80eb63cc.Iffd88f63f95575f28e503da13b473724e3341aee@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index d02943d0ea625..8a6ddb5fb0c37 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2022 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -1490,7 +1490,7 @@ static inline u32 iwl_trans_read_mem32(struct iwl_trans *trans, u32 addr)
 {
 	u32 value;
 
-	if (WARN_ON(iwl_trans_read_mem(trans, addr, &value, 1)))
+	if (iwl_trans_read_mem(trans, addr, &value, 1))
 		return 0xa5a5a5a5;
 
 	return value;
-- 
GitLab


From a06320044a30d2ef33fa07f3df5d7411c217d4c0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 11:10:46 +0300
Subject: [PATCH 1468/1806] wifi: iwlwifi: pcie: clean up gen1/gen2 TFD unmap

This is a bit messy right now, there are functions for both,
but then gen1 function can actually deal with both gen1 and
gen2, due to the confusion about use_tfh/gen2 cleaned up in
the previous patch.

Fix the common paths to call the right functions and remove
handling of gen2 from the gen1 function.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.baf23841ec5c.I40702e94b25db05e82f935f14548316f8c6429b9@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c  |  6 +++-
 drivers/net/wireless/intel/iwlwifi/queue/tx.c | 33 ++++++-------------
 drivers/net/wireless/intel/iwlwifi/queue/tx.h | 11 +------
 3 files changed, 16 insertions(+), 34 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 790e5b124740e..9ab1b2590dd2d 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1203,7 +1203,11 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 	group_id = cmd->hdr.group_id;
 	cmd_id = WIDE_ID(group_id, cmd->hdr.cmd);
 
-	iwl_txq_gen1_tfd_unmap(trans, meta, txq, index);
+	if (trans->trans_cfg->gen2)
+		iwl_txq_gen2_tfd_unmap(trans, meta,
+				       iwl_txq_get_tfd(trans, txq, index));
+	else
+		iwl_txq_gen1_tfd_unmap(trans, meta, txq, index);
 
 	/* Input error checking is done when commands are added to queue. */
 	if (meta->flags & CMD_WANT_SKB) {
diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c
index 5bb3cc3367c9f..5b1100e6e1d1f 100644
--- a/drivers/net/wireless/intel/iwlwifi/queue/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c
@@ -1340,22 +1340,12 @@ error:
 }
 
 static inline dma_addr_t iwl_txq_gen1_tfd_tb_get_addr(struct iwl_trans *trans,
-						      void *_tfd, u8 idx)
+						      struct iwl_tfd *tfd, u8 idx)
 {
-	struct iwl_tfd *tfd;
-	struct iwl_tfd_tb *tb;
+	struct iwl_tfd_tb *tb = &tfd->tbs[idx];
 	dma_addr_t addr;
 	dma_addr_t hi_len;
 
-	if (trans->trans_cfg->gen2) {
-		struct iwl_tfh_tfd *tfh_tfd = _tfd;
-		struct iwl_tfh_tb *tfh_tb = &tfh_tfd->tbs[idx];
-
-		return (dma_addr_t)(le64_to_cpu(tfh_tb->addr));
-	}
-
-	tfd = _tfd;
-	tb = &tfd->tbs[idx];
 	addr = get_unaligned_le32(&tb->lo);
 
 	if (sizeof(dma_addr_t) <= sizeof(u32))
@@ -1376,7 +1366,7 @@ void iwl_txq_gen1_tfd_unmap(struct iwl_trans *trans,
 			    struct iwl_txq *txq, int index)
 {
 	int i, num_tbs;
-	void *tfd = iwl_txq_get_tfd(trans, txq, index);
+	struct iwl_tfd *tfd = iwl_txq_get_tfd(trans, txq, index);
 
 	/* Sanity check on number of chunks */
 	num_tbs = iwl_txq_gen1_tfd_get_num_tbs(trans, tfd);
@@ -1408,15 +1398,7 @@ void iwl_txq_gen1_tfd_unmap(struct iwl_trans *trans,
 
 	meta->tbs = 0;
 
-	if (trans->trans_cfg->gen2) {
-		struct iwl_tfh_tfd *tfd_fh = (void *)tfd;
-
-		tfd_fh->num_tbs = 0;
-	} else {
-		struct iwl_tfd *tfd_fh = (void *)tfd;
-
-		tfd_fh->num_tbs = 0;
-	}
+	tfd->num_tbs = 0;
 }
 
 #define IWL_TX_CRC_SIZE 4
@@ -1520,7 +1502,12 @@ void iwl_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
 	/* We have only q->n_window txq->entries, but we use
 	 * TFD_QUEUE_SIZE_MAX tfds
 	 */
-	iwl_txq_gen1_tfd_unmap(trans, &txq->entries[idx].meta, txq, rd_ptr);
+	if (trans->trans_cfg->gen2)
+		iwl_txq_gen2_tfd_unmap(trans, &txq->entries[idx].meta,
+				       iwl_txq_get_tfd(trans, txq, rd_ptr));
+	else
+		iwl_txq_gen1_tfd_unmap(trans, &txq->entries[idx].meta,
+				       txq, rd_ptr);
 
 	/* free SKB */
 	skb = txq->entries[idx].skb;
diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.h b/drivers/net/wireless/intel/iwlwifi/queue/tx.h
index 1e4a24ab9bab2..15b3edce56e00 100644
--- a/drivers/net/wireless/intel/iwlwifi/queue/tx.h
+++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.h
@@ -131,17 +131,8 @@ struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
 				      struct sk_buff *skb);
 #endif
 static inline u8 iwl_txq_gen1_tfd_get_num_tbs(struct iwl_trans *trans,
-					      void *_tfd)
+					      struct iwl_tfd *tfd)
 {
-	struct iwl_tfd *tfd;
-
-	if (trans->trans_cfg->gen2) {
-		struct iwl_tfh_tfd *tfh_tfd = _tfd;
-
-		return le16_to_cpu(tfh_tfd->num_tbs) & 0x1f;
-	}
-
-	tfd = (struct iwl_tfd *)_tfd;
 	return tfd->num_tbs & 0x1f;
 }
 
-- 
GitLab


From d5050543f1ed78beb85f85b5830242cb0c4968c0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 11:10:47 +0300
Subject: [PATCH 1469/1806] wifi: iwlwifi: remove 'def_rx_queue' struct member

This is only ever initialized to zero, use a new define
for the default RX queue instead.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.e0c6fa57c162.I907bbb428cf99725f06a348c8dbce5d3dd877136@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-fh.h        | 2 ++
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h | 4 +---
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c       | 2 +-
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c    | 2 --
 4 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
index 4e4a60ddf9b27..41ab5a6e2dd3f 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
@@ -565,6 +565,8 @@ static inline unsigned int FH_MEM_CBBC_QUEUE(struct iwl_trans *trans,
 #define RX_QUEUE_MASK                         255
 #define RX_QUEUE_SIZE_LOG                     8
 
+#define IWL_DEFAULT_RX_QUEUE			0
+
 /**
  * struct iwl_rb_status - reserve buffer status
  * 	host memory mapped FH registers
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 0adcf0e13e85a..0f6493dab8cbd 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2003-2015, 2018-2022 Intel Corporation
+ * Copyright (C) 2003-2015, 2018-2023 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -315,7 +315,6 @@ enum iwl_pcie_imr_status {
  * @ucode_write_complete: indicates that the ucode has been copied.
  * @ucode_write_waitq: wait queue for uCode load
  * @cmd_queue - command queue number
- * @def_rx_queue - default rx queue number
  * @rx_buf_size: Rx buffer size
  * @scd_set_active: should the transport configure the SCD for HCMD queue
  * @rx_page_order: page order for receive buffer size
@@ -398,7 +397,6 @@ struct iwl_trans_pcie {
 	wait_queue_head_t ucode_write_waitq;
 	wait_queue_head_t sx_waitq;
 
-	u8 def_rx_queue;
 	u8 n_no_reclaim_cmds;
 	u8 no_reclaim_cmds[MAX_NO_RECLAIM_CMDS];
 	u16 num_rx_bufs;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index f87b28edc267d..4614acee9f7ba 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1373,7 +1373,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 			}
 		}
 
-		if (rxq->id == trans_pcie->def_rx_queue)
+		if (rxq->id == IWL_DEFAULT_RX_QUEUE)
 			iwl_op_mode_rx(trans->op_mode, &rxq->napi,
 				       &rxcb);
 		else
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 3e988da449738..2096f71587287 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -3617,8 +3617,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 				       PCIE_LINK_STATE_CLKPM);
 	}
 
-	trans_pcie->def_rx_queue = 0;
-
 	pci_set_master(pdev);
 
 	addr_size = trans->txqs.tfd.addr_size;
-- 
GitLab


From c522948a4718a4c577cea05ae6e48d74d3b6cab7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 11:10:48 +0300
Subject: [PATCH 1470/1806] wifi: iwlwifi: pcie: move gen1 TB handling to
 header

We will need this in another place soon in reclaim and init,
so add this function to the queue header file instead.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.52b6f66de219.Ic8403fd098c187fac067977808c0129d96514c91@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c  | 18 +-----------------
 drivers/net/wireless/intel/iwlwifi/queue/tx.h | 15 +++++++++++++++
 2 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 9ab1b2590dd2d..2f39b639c43f9 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -132,22 +132,6 @@ void iwl_pcie_txq_check_wrptrs(struct iwl_trans *trans)
 	}
 }
 
-static inline void iwl_pcie_tfd_set_tb(struct iwl_trans *trans, void *tfd,
-				       u8 idx, dma_addr_t addr, u16 len)
-{
-	struct iwl_tfd *tfd_fh = (void *)tfd;
-	struct iwl_tfd_tb *tb = &tfd_fh->tbs[idx];
-
-	u16 hi_n_len = len << 4;
-
-	put_unaligned_le32(addr, &tb->lo);
-	hi_n_len |= iwl_get_dma_hi_addr(addr);
-
-	tb->hi_n_len = cpu_to_le16(hi_n_len);
-
-	tfd_fh->num_tbs = idx + 1;
-}
-
 static int iwl_pcie_txq_build_tfd(struct iwl_trans *trans, struct iwl_txq *txq,
 				  dma_addr_t addr, u16 len, bool reset)
 {
@@ -172,7 +156,7 @@ static int iwl_pcie_txq_build_tfd(struct iwl_trans *trans, struct iwl_txq *txq,
 		 "Unaligned address = %llx\n", (unsigned long long)addr))
 		return -EINVAL;
 
-	iwl_pcie_tfd_set_tb(trans, tfd, num_tbs, addr, len);
+	iwl_pcie_gen1_tfd_set_tb(trans, tfd, num_tbs, addr, len);
 
 	return num_tbs;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.h b/drivers/net/wireless/intel/iwlwifi/queue/tx.h
index 15b3edce56e00..b7d3808588bfb 100644
--- a/drivers/net/wireless/intel/iwlwifi/queue/tx.h
+++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.h
@@ -155,6 +155,21 @@ static inline u16 iwl_txq_gen1_tfd_tb_get_len(struct iwl_trans *trans,
 	return le16_to_cpu(tb->hi_n_len) >> 4;
 }
 
+static inline void iwl_pcie_gen1_tfd_set_tb(struct iwl_trans *trans,
+					    struct iwl_tfd *tfd,
+					    u8 idx, dma_addr_t addr, u16 len)
+{
+	struct iwl_tfd_tb *tb = &tfd->tbs[idx];
+	u16 hi_n_len = len << 4;
+
+	put_unaligned_le32(addr, &tb->lo);
+	hi_n_len |= iwl_get_dma_hi_addr(addr);
+
+	tb->hi_n_len = cpu_to_le16(hi_n_len);
+
+	tfd->num_tbs = idx + 1;
+}
+
 void iwl_txq_gen1_tfd_unmap(struct iwl_trans *trans,
 			    struct iwl_cmd_meta *meta,
 			    struct iwl_txq *txq, int index);
-- 
GitLab


From 80fa8377f5c64aac66699f98186605f7fa25089e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 11:10:49 +0300
Subject: [PATCH 1471/1806] wifi: iwlwifi: queue: move iwl_txq_gen2_set_tb() up

We need this earlier in the file next, move it up to have
an easier to read change, since this moves other things
in the diff git generates by default.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.c6d798b600bb.I9b891ee3d3dc67822a28e44941409f5b7cb637cf@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/queue/tx.c | 71 +++++++++----------
 1 file changed, 35 insertions(+), 36 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c
index 5b1100e6e1d1f..95c2af54ea46e 100644
--- a/drivers/net/wireless/intel/iwlwifi/queue/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c
@@ -84,6 +84,41 @@ static u8 iwl_txq_gen2_get_num_tbs(struct iwl_trans *trans,
 	return le16_to_cpu(tfd->num_tbs) & 0x1f;
 }
 
+int iwl_txq_gen2_set_tb(struct iwl_trans *trans, struct iwl_tfh_tfd *tfd,
+			dma_addr_t addr, u16 len)
+{
+	int idx = iwl_txq_gen2_get_num_tbs(trans, tfd);
+	struct iwl_tfh_tb *tb;
+
+	/* Only WARN here so we know about the issue, but we mess up our
+	 * unmap path because not every place currently checks for errors
+	 * returned from this function - it can only return an error if
+	 * there's no more space, and so when we know there is enough we
+	 * don't always check ...
+	 */
+	WARN(iwl_txq_crosses_4g_boundary(addr, len),
+	     "possible DMA problem with iova:0x%llx, len:%d\n",
+	     (unsigned long long)addr, len);
+
+	if (WARN_ON(idx >= IWL_TFH_NUM_TBS))
+		return -EINVAL;
+	tb = &tfd->tbs[idx];
+
+	/* Each TFD can point to a maximum max_tbs Tx buffers */
+	if (le16_to_cpu(tfd->num_tbs) >= trans->txqs.tfd.max_tbs) {
+		IWL_ERR(trans, "Error can not send more than %d chunks\n",
+			trans->txqs.tfd.max_tbs);
+		return -EINVAL;
+	}
+
+	put_unaligned_le64(addr, &tb->addr);
+	tb->tb_len = cpu_to_le16(len);
+
+	tfd->num_tbs = cpu_to_le16(idx + 1);
+
+	return idx;
+}
+
 void iwl_txq_gen2_tfd_unmap(struct iwl_trans *trans, struct iwl_cmd_meta *meta,
 			    struct iwl_tfh_tfd *tfd)
 {
@@ -142,42 +177,6 @@ void iwl_txq_gen2_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
 	}
 }
 
-int iwl_txq_gen2_set_tb(struct iwl_trans *trans, struct iwl_tfh_tfd *tfd,
-			dma_addr_t addr, u16 len)
-{
-	int idx = iwl_txq_gen2_get_num_tbs(trans, tfd);
-	struct iwl_tfh_tb *tb;
-
-	/*
-	 * Only WARN here so we know about the issue, but we mess up our
-	 * unmap path because not every place currently checks for errors
-	 * returned from this function - it can only return an error if
-	 * there's no more space, and so when we know there is enough we
-	 * don't always check ...
-	 */
-	WARN(iwl_txq_crosses_4g_boundary(addr, len),
-	     "possible DMA problem with iova:0x%llx, len:%d\n",
-	     (unsigned long long)addr, len);
-
-	if (WARN_ON(idx >= IWL_TFH_NUM_TBS))
-		return -EINVAL;
-	tb = &tfd->tbs[idx];
-
-	/* Each TFD can point to a maximum max_tbs Tx buffers */
-	if (le16_to_cpu(tfd->num_tbs) >= trans->txqs.tfd.max_tbs) {
-		IWL_ERR(trans, "Error can not send more than %d chunks\n",
-			trans->txqs.tfd.max_tbs);
-		return -EINVAL;
-	}
-
-	put_unaligned_le64(addr, &tb->addr);
-	tb->tb_len = cpu_to_le16(len);
-
-	tfd->num_tbs = cpu_to_le16(idx + 1);
-
-	return idx;
-}
-
 static struct page *get_workaround_page(struct iwl_trans *trans,
 					struct sk_buff *skb)
 {
-- 
GitLab


From c83031afaaaa4a1129394439c8cd93ffe94f9970 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 11:10:50 +0300
Subject: [PATCH 1472/1806] wifi: iwlwifi: pcie: point invalid TFDs to invalid
 data

There are occasionally bugs which cause the device to try
to use a TFD that it wasn't supposed to, and these are
very hard to diagnose. Fill all unused TFDs with a debug
command that immediately causes an error to be detected
in these cases.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.10a9af1ca91f.Ifc790d62c52b4bc9a74c9581610af498509f5759@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/fw/api/debug.h |  5 +++
 .../net/wireless/intel/iwlwifi/iwl-trans.h    |  3 ++
 .../net/wireless/intel/iwlwifi/pcie/trans.c   | 29 ++++++++++++++
 drivers/net/wireless/intel/iwlwifi/queue/tx.c | 40 ++++++++++++++++---
 4 files changed, 71 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
index 48ffab22bb7b4..90ce8d9b6ad3a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
@@ -29,6 +29,11 @@ enum iwl_debug_cmds {
 	 * &struct iwl_dbg_host_event_cfg_cmd
 	 */
 	HOST_EVENT_CFG = 0x3,
+	/**
+	 * @INVALID_WR_PTR_CMD: invalid write pointer, set in the TFD
+	 *	when it's not in use
+	 */
+	INVALID_WR_PTR_CMD = 0x6,
 	/**
 	 * @DBGC_SUSPEND_RESUME:
 	 * DBGC suspend/resume commad. Uses a single dword as data:
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 8a6ddb5fb0c37..3b6b0e03037f1 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -1069,6 +1069,7 @@ struct iwl_trans_txqs {
  * @mbx_addr_1_step: step address data 1
  * @pcie_link_speed: current PCIe link speed (%PCI_EXP_LNKSTA_CLS_*),
  *	only valid for discrete (not integrated) NICs
+ * @invalid_tx_cmd: invalid TX command buffer
  */
 struct iwl_trans {
 	bool csme_own;
@@ -1133,6 +1134,8 @@ struct iwl_trans {
 
 	u8 pcie_link_speed;
 
+	struct iwl_dma_ptr invalid_tx_cmd;
+
 	/* pointer to trans specific struct */
 	/*Ensure that this pointer will always be aligned to sizeof pointer */
 	char trans_specific[] __aligned(sizeof(void *));
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 2096f71587287..198933f853c55 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2018,6 +2018,30 @@ void iwl_trans_pcie_free_pnvm_dram_regions(struct iwl_dram_regions *dram_regions
 	memset(desc_dram, 0, sizeof(*desc_dram));
 }
 
+static void iwl_pcie_free_invalid_tx_cmd(struct iwl_trans *trans)
+{
+	iwl_pcie_free_dma_ptr(trans, &trans->invalid_tx_cmd);
+}
+
+static int iwl_pcie_alloc_invalid_tx_cmd(struct iwl_trans *trans)
+{
+	struct iwl_cmd_header_wide bad_cmd = {
+		.cmd = INVALID_WR_PTR_CMD,
+		.group_id = DEBUG_GROUP,
+		.sequence = cpu_to_le16(0xffff),
+		.length = cpu_to_le16(0),
+		.version = 0,
+	};
+	int ret;
+
+	ret = iwl_pcie_alloc_dma_ptr(trans, &trans->invalid_tx_cmd,
+				     sizeof(bad_cmd));
+	if (ret)
+		return ret;
+	memcpy(trans->invalid_tx_cmd.addr, &bad_cmd, sizeof(bad_cmd));
+	return 0;
+}
+
 void iwl_trans_pcie_free(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -2048,6 +2072,8 @@ void iwl_trans_pcie_free(struct iwl_trans *trans)
 		iwl_pcie_free_ict(trans);
 	}
 
+	iwl_pcie_free_invalid_tx_cmd(trans);
+
 	iwl_pcie_free_fw_monitor(trans);
 
 	iwl_trans_pcie_free_pnvm_dram_regions(&trans_pcie->pnvm_data,
@@ -3684,6 +3710,9 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 
 	init_waitqueue_head(&trans_pcie->sx_waitq);
 
+	ret = iwl_pcie_alloc_invalid_tx_cmd(trans);
+	if (ret)
+		goto out_no_pci;
 
 	if (trans_pcie->msix_enabled) {
 		ret = iwl_pcie_init_msix_handler(pdev, trans_pcie);
diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c
index 95c2af54ea46e..340240b8954f6 100644
--- a/drivers/net/wireless/intel/iwlwifi/queue/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c
@@ -10,6 +10,7 @@
 #include "fw/api/commands.h"
 #include "fw/api/tx.h"
 #include "fw/api/datapath.h"
+#include "fw/api/debug.h"
 #include "queue/tx.h"
 #include "iwl-fh.h"
 #include "iwl-scd.h"
@@ -119,6 +120,15 @@ int iwl_txq_gen2_set_tb(struct iwl_trans *trans, struct iwl_tfh_tfd *tfd,
 	return idx;
 }
 
+static void iwl_txq_set_tfd_invalid_gen2(struct iwl_trans *trans,
+					 struct iwl_tfh_tfd *tfd)
+{
+	tfd->num_tbs = 0;
+
+	iwl_txq_gen2_set_tb(trans, tfd, trans->invalid_tx_cmd.dma,
+			    trans->invalid_tx_cmd.size);
+}
+
 void iwl_txq_gen2_tfd_unmap(struct iwl_trans *trans, struct iwl_cmd_meta *meta,
 			    struct iwl_tfh_tfd *tfd)
 {
@@ -146,7 +156,7 @@ void iwl_txq_gen2_tfd_unmap(struct iwl_trans *trans, struct iwl_cmd_meta *meta,
 					 DMA_TO_DEVICE);
 	}
 
-	tfd->num_tbs = 0;
+	iwl_txq_set_tfd_invalid_gen2(trans, tfd);
 }
 
 void iwl_txq_gen2_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
@@ -1025,11 +1035,21 @@ static void iwl_txq_stuck_timer(struct timer_list *t)
 	iwl_force_nmi(trans);
 }
 
+static void iwl_txq_set_tfd_invalid_gen1(struct iwl_trans *trans,
+					 struct iwl_tfd *tfd)
+{
+	tfd->num_tbs = 0;
+
+	iwl_pcie_gen1_tfd_set_tb(trans, tfd, 0, trans->invalid_tx_cmd.dma,
+				 trans->invalid_tx_cmd.size);
+}
+
 int iwl_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num,
 		  bool cmd_queue)
 {
-	size_t tfd_sz = trans->txqs.tfd.size *
-		trans->trans_cfg->base_params->max_tfd_queue_size;
+	size_t num_entries = trans->trans_cfg->gen2 ?
+		slots_num : trans->trans_cfg->base_params->max_tfd_queue_size;
+	size_t tfd_sz;
 	size_t tb0_buf_sz;
 	int i;
 
@@ -1039,8 +1059,7 @@ int iwl_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num,
 	if (WARN_ON(txq->entries || txq->tfds))
 		return -EINVAL;
 
-	if (trans->trans_cfg->gen2)
-		tfd_sz = trans->txqs.tfd.size * slots_num;
+	tfd_sz = trans->txqs.tfd.size * num_entries;
 
 	timer_setup(&txq->stuck_timer, iwl_txq_stuck_timer, 0);
 	txq->trans = trans;
@@ -1080,6 +1099,15 @@ int iwl_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num,
 	if (!txq->first_tb_bufs)
 		goto err_free_tfds;
 
+	for (i = 0; i < num_entries; i++) {
+		void *tfd = iwl_txq_get_tfd(trans, txq, i);
+
+		if (trans->trans_cfg->gen2)
+			iwl_txq_set_tfd_invalid_gen2(trans, tfd);
+		else
+			iwl_txq_set_tfd_invalid_gen1(trans, tfd);
+	}
+
 	return 0;
 err_free_tfds:
 	dma_free_coherent(trans->dev, tfd_sz, txq->tfds, txq->dma_addr);
@@ -1397,7 +1425,7 @@ void iwl_txq_gen1_tfd_unmap(struct iwl_trans *trans,
 
 	meta->tbs = 0;
 
-	tfd->num_tbs = 0;
+	iwl_txq_set_tfd_invalid_gen1(trans, tfd);
 }
 
 #define IWL_TX_CRC_SIZE 4
-- 
GitLab


From 533d93086248735aa958bccbbb13053e9031f9ba Mon Sep 17 00:00:00 2001
From: Gregory Greenman <gregory.greenman@intel.com>
Date: Wed, 16 Aug 2023 11:10:51 +0300
Subject: [PATCH 1473/1806] wifi: iwlwifi: add Razer to ppag approved list

Add a new vendor (Razer) to PPAG approved list.

Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.f586a86fa644.I97408afb20bd7c46fcff8c3561ead8ed9c60b37e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index dfe8357036eb0..b26f90e522564 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -69,6 +69,11 @@ static const struct dmi_system_id dmi_ppag_approved_list[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
 		},
 	},
+	{ .ident = "RAZER",
+	  .matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Razer"),
+		},
+	},
 	{}
 };
 
-- 
GitLab


From 0922a71079038b565b249a5926b4f8ba7ed62893 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 11:10:52 +0300
Subject: [PATCH 1474/1806] wifi: iwlwifi: mvm: enable HE TX/RX <242 tone RU on
 new RFs

Two new RFs were added in the code, but we forgot to
add them to the list here that enables HE TX/RX 1024
QAM less than 242 tone RU.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.ddb090c86c8c.Ic630aa579e3dc52069758d8698069480d555eefe@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 8c23f57f5c89f..31176897b7463 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -990,6 +990,8 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 	case IWL_CFG_RF_TYPE_GF:
 	case IWL_CFG_RF_TYPE_MR:
 	case IWL_CFG_RF_TYPE_MS:
+	case IWL_CFG_RF_TYPE_FM:
+	case IWL_CFG_RF_TYPE_WH:
 		iftype_data->he_cap.he_cap_elem.phy_cap_info[9] |=
 			IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU;
 		if (!is_ap)
-- 
GitLab


From d09d290ae39345fb914163e45ee2b42f8c938f7b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 11:10:53 +0300
Subject: [PATCH 1475/1806] wifi: iwlwifi: mvm: support flush on AP interfaces

Support TX flush on AP interfaces so that we will do a
proper flush for frames on the queue before keys are
removed.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.f4b749b91ec2.Ia8381bd4f7d47592e74387c564739798a01c4049@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index e7fe5b76def4c..5918c1f2b10c3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -5605,9 +5605,6 @@ void iwl_mvm_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		return;
 	}
 
-	if (vif->type != NL80211_IFTYPE_STATION)
-		return;
-
 	/* Make sure we're done with the deferred traffic before flushing */
 	flush_work(&mvm->add_stream_wk);
 
@@ -5631,9 +5628,6 @@ void iwl_mvm_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			ap_sta_done = true;
 		}
 
-		/* make sure only TDLS peers or the AP are flushed */
-		WARN_ON_ONCE(sta != mvmvif->ap_sta && !sta->tdls);
-
 		if (drop) {
 			if (iwl_mvm_flush_sta(mvm, mvmsta, false))
 				IWL_ERR(mvm, "flush request fail\n");
-- 
GitLab


From d166a5c9775f8cc0b20e3331e238844a3fe57fa1 Mon Sep 17 00:00:00 2001
From: Mukesh Sisodiya <mukesh.sisodiya@intel.com>
Date: Wed, 16 Aug 2023 11:10:54 +0300
Subject: [PATCH 1476/1806] wifi: iwlwifi: remove memory check for LMAC error
 address

LMAC error table address was checked against UMAC
error table minimum address defined. Because of that,
the LMAC error table was not read, since both addresses
belong to different ranges. As addresses are updated from
FW alive message and should be correct, this check is not
needed.

Still keep the check for address 0 to avoid NULL address read.

Signed-off-by: Mukesh Sisodiya <mukesh.sisodiya@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230816104355.08ab1497904d.I270d4c5bcc23c5ecd0b7db475501032c450852ad@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dump.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dump.c b/drivers/net/wireless/intel/iwlwifi/fw/dump.c
index 5876f917e5361..8f107ceec4076 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dump.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dump.c
@@ -182,8 +182,7 @@ static void iwl_fwrt_dump_lmac_error_log(struct iwl_fw_runtime *fwrt, u8 lmac_nu
 			base = fwrt->fw->inst_errlog_ptr;
 	}
 
-	if ((fwrt->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ && !base) ||
-	    (fwrt->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_BZ && base < 0x400000)) {
+	if (!base) {
 		IWL_ERR(fwrt,
 			"Not valid error log pointer 0x%08X for %s uCode\n",
 			base,
-- 
GitLab


From 057381ddac0593c6e4ca8f58732830d8542b9c4e Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Tue, 22 Aug 2023 10:33:15 +0300
Subject: [PATCH 1477/1806] wifi: iwlwifi: pcie: avoid a warning in case
 prepare card failed

In case CSME holds the NIC and SAP connection is already established,
iwl_pcie_prepare_card_hw() during iwl_pci_probe() will fail
(which is fine since CSME will release the nic later when asked with
a SAP message). In this case tring to grab nic access to read the
crf ids will fail with a warning.
Avoid the warning by only trying to read the crf ids in case prepare
card succeeded.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230822103048.9b026fa7b97e.I12bea7e6eef54eeeaf916b68d71583e92ff310fd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 73c1fb3c0c5ec..bc83d2ba55c67 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1132,12 +1132,6 @@ static int get_crf_id(struct iwl_trans *iwl_trans)
 	else
 		sd_reg_ver_addr = SD_REG_VER;
 
-	if (!iwl_trans_grab_nic_access(iwl_trans)) {
-		IWL_ERR(iwl_trans, "Failed to grab nic access before reading crf id\n");
-		ret = -EIO;
-		goto out;
-	}
-
 	/* Enable access to peripheral registers */
 	val = iwl_read_umac_prph_no_grab(iwl_trans, WFPM_CTRL_REG);
 	val |= ENABLE_WFPM;
@@ -1157,9 +1151,6 @@ static int get_crf_id(struct iwl_trans *iwl_trans)
 		 iwl_trans->hw_crf_id, iwl_trans->hw_cnv_id,
 		 iwl_trans->hw_wfpm_id);
 
-	iwl_trans_release_nic_access(iwl_trans);
-
-out:
 	return ret;
 }
 
@@ -1351,6 +1342,7 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		if (ret)
 			goto out_free_trans;
 		if (iwl_trans_grab_nic_access(iwl_trans)) {
+			get_crf_id(iwl_trans);
 			/* all good */
 			iwl_trans_release_nic_access(iwl_trans);
 		} else {
@@ -1360,7 +1352,6 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	iwl_trans->hw_rf_id = iwl_read32(iwl_trans, CSR_HW_RF_ID);
-	get_crf_id(iwl_trans);
 
 	/*
 	 * The RF_ID is set to zero in blank OTP so read version to
-- 
GitLab


From ef030ab17e060b0ef47028e86cf85b68988b56ae Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Tue, 22 Aug 2023 10:33:16 +0300
Subject: [PATCH 1478/1806] wifi: iwlmei: don't send SAP messages if AMT is
 disabled

SAP messages should not be sent when AMT is disabled.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230822103048.db16b55c27c1.I48834c14f5af8d31792f5048b3023509cba191dd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mei/main.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mei/main.c b/drivers/net/wireless/intel/iwlwifi/mei/main.c
index 54445f39fd551..908506f98242a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mei/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/mei/main.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2021-2022 Intel Corporation
+ * Copyright (C) 2021-2023 Intel Corporation
  */
 
 #include <linux/etherdevice.h>
@@ -1532,7 +1532,7 @@ void iwl_mei_host_associated(const struct iwl_mei_conn_info *conn_info,
 
 	mei = mei_cldev_get_drvdata(iwl_mei_global_cldev);
 
-	if (!mei && !mei->amt_enabled)
+	if (!mei || !mei->amt_enabled)
 		goto out;
 
 	iwl_mei_send_sap_msg_payload(mei->cldev, &msg.hdr);
@@ -1561,7 +1561,7 @@ void iwl_mei_host_disassociated(void)
 
 	mei = mei_cldev_get_drvdata(iwl_mei_global_cldev);
 
-	if (!mei && !mei->amt_enabled)
+	if (!mei || !mei->amt_enabled)
 		goto out;
 
 	iwl_mei_send_sap_msg_payload(mei->cldev, &msg.hdr);
@@ -1597,7 +1597,7 @@ void iwl_mei_set_rfkill_state(bool hw_rfkill, bool sw_rfkill)
 
 	mei = mei_cldev_get_drvdata(iwl_mei_global_cldev);
 
-	if (!mei && !mei->amt_enabled)
+	if (!mei || !mei->amt_enabled)
 		goto out;
 
 	iwl_mei_send_sap_msg_payload(mei->cldev, &msg.hdr);
@@ -1626,7 +1626,7 @@ void iwl_mei_set_nic_info(const u8 *mac_address, const u8 *nvm_address)
 
 	mei = mei_cldev_get_drvdata(iwl_mei_global_cldev);
 
-	if (!mei && !mei->amt_enabled)
+	if (!mei || !mei->amt_enabled)
 		goto out;
 
 	iwl_mei_send_sap_msg_payload(mei->cldev, &msg.hdr);
@@ -1654,7 +1654,7 @@ void iwl_mei_set_country_code(u16 mcc)
 
 	mei = mei_cldev_get_drvdata(iwl_mei_global_cldev);
 
-	if (!mei && !mei->amt_enabled)
+	if (!mei || !mei->amt_enabled)
 		goto out;
 
 	iwl_mei_send_sap_msg_payload(mei->cldev, &msg.hdr);
@@ -1680,7 +1680,7 @@ void iwl_mei_set_power_limit(const __le16 *power_limit)
 
 	mei = mei_cldev_get_drvdata(iwl_mei_global_cldev);
 
-	if (!mei && !mei->amt_enabled)
+	if (!mei || !mei->amt_enabled)
 		goto out;
 
 	memcpy(msg.sar_chain_info_table, power_limit, sizeof(msg.sar_chain_info_table));
-- 
GitLab


From 3243aee1cb9206521c82a49fa5879934c69cee7c Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Tue, 22 Aug 2023 10:33:17 +0300
Subject: [PATCH 1479/1806] wifi: iwlmei: send HOST_GOES_DOWN message even if
 wiamt is disabled

The HOST_GOES_DOWN message should be sent even if wiamt is disabled.
Otherwise wiamt may still use the shared memory (e.g. if enabled
later) while it's no longer valid.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230822103048.2baad50eb1c3.If7b7c1dc2d6bfc6bacf7f6c72972f19714d9d973@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mei/main.c | 42 +++++++++----------
 1 file changed, 19 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mei/main.c b/drivers/net/wireless/intel/iwlwifi/mei/main.c
index 908506f98242a..27f45f5ea264a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mei/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/mei/main.c
@@ -2070,33 +2070,29 @@ static void iwl_mei_remove(struct mei_cl_device *cldev)
 
 	mutex_lock(&iwl_mei_mutex);
 
-	if (mei->amt_enabled) {
-		/*
-		 * Tell CSME that we are going down so that it won't access the
-		 * memory anymore, make sure this message goes through immediately.
-		 */
-		mei->csa_throttled = false;
-		iwl_mei_send_sap_msg(mei->cldev,
-				     SAP_MSG_NOTIF_HOST_GOES_DOWN);
-
-		for (i = 0; i < SEND_SAP_MAX_WAIT_ITERATION; i++) {
-			if (!iwl_mei_host_to_me_data_pending(mei))
-				break;
+	/* Tell CSME that we are going down so that it won't access the
+	 * memory anymore, make sure this message goes through immediately.
+	 */
+	mei->csa_throttled = false;
+	iwl_mei_send_sap_msg(mei->cldev,
+			     SAP_MSG_NOTIF_HOST_GOES_DOWN);
 
-			msleep(20);
-		}
+	for (i = 0; i < SEND_SAP_MAX_WAIT_ITERATION; i++) {
+		if (!iwl_mei_host_to_me_data_pending(mei))
+			break;
 
-		/*
-		 * If we couldn't make sure that CSME saw the HOST_GOES_DOWN
-		 * message, it means that it will probably keep reading memory
-		 * that we are going to unmap and free, expect IOMMU error
-		 * messages.
-		 */
-		if (i == SEND_SAP_MAX_WAIT_ITERATION)
-			dev_err(&mei->cldev->dev,
-				"Couldn't get ACK from CSME on HOST_GOES_DOWN message\n");
+		msleep(20);
 	}
 
+	/* If we couldn't make sure that CSME saw the HOST_GOES_DOWN
+	 * message, it means that it will probably keep reading memory
+	 * that we are going to unmap and free, expect IOMMU error
+	 * messages.
+	 */
+	if (i == SEND_SAP_MAX_WAIT_ITERATION)
+		dev_err(&mei->cldev->dev,
+			"Couldn't get ACK from CSME on HOST_GOES_DOWN message\n");
+
 	mutex_unlock(&iwl_mei_mutex);
 
 	/*
-- 
GitLab


From a7d9ac48a6512acdb81bb3d1f55c7b30d9b9d1c0 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Tue, 22 Aug 2023 10:33:18 +0300
Subject: [PATCH 1480/1806] wifi: iwlmei: send driver down SAP message only if
 wiamt is enabled

When wiamt is disabled the driver up SAP message is not sent, so
there is no need to send the driver down message as well.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230822103048.100f41b84656.I583d3e18ea65793f53aa710af13e47f8af82b53d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mei/main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mei/main.c b/drivers/net/wireless/intel/iwlwifi/mei/main.c
index 27f45f5ea264a..78b78a772f547 100644
--- a/drivers/net/wireless/intel/iwlwifi/mei/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/mei/main.c
@@ -1832,7 +1832,9 @@ void iwl_mei_unregister_complete(void)
 		struct iwl_mei *mei =
 			mei_cldev_get_drvdata(iwl_mei_global_cldev);
 
-		iwl_mei_send_sap_msg(mei->cldev, SAP_MSG_NOTIF_WIFIDR_DOWN);
+		if (mei->amt_enabled)
+			iwl_mei_send_sap_msg(mei->cldev,
+					     SAP_MSG_NOTIF_WIFIDR_DOWN);
 		mei->got_ownership = false;
 	}
 
-- 
GitLab


From 6d2c360b4badf78fb778afe1f5b85196ff18383e Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Tue, 22 Aug 2023 10:33:19 +0300
Subject: [PATCH 1481/1806] wifi: iwlmei: don't send nic info with invalid mac
 address

In case the SAP connection is established before the interface is
added, the mac address is still not set. Don't send the nic info
SAP message in this case since it will result in sending an invalid
mac address. The nic info message will be sent with a valid mac
address when the interface is added.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20230822103048.a49436bed387.I0ca88d72456e6e9f939bbc2e0c52ffb173fbc97e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mei/main.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mei/main.c b/drivers/net/wireless/intel/iwlwifi/mei/main.c
index 78b78a772f547..1dd9106c65136 100644
--- a/drivers/net/wireless/intel/iwlwifi/mei/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/mei/main.c
@@ -774,9 +774,13 @@ static void iwl_mei_set_init_conf(struct iwl_mei *mei)
 		iwl_mei_send_sap_msg_payload(mei->cldev, &sar_msg.hdr);
 	}
 
-	ether_addr_copy(nic_info_msg.mac_address, iwl_mei_cache.mac_address);
-	ether_addr_copy(nic_info_msg.nvm_address, iwl_mei_cache.nvm_address);
-	iwl_mei_send_sap_msg_payload(mei->cldev, &nic_info_msg.hdr);
+	if (is_valid_ether_addr(iwl_mei_cache.mac_address)) {
+		ether_addr_copy(nic_info_msg.mac_address,
+				iwl_mei_cache.mac_address);
+		ether_addr_copy(nic_info_msg.nvm_address,
+				iwl_mei_cache.nvm_address);
+		iwl_mei_send_sap_msg_payload(mei->cldev, &nic_info_msg.hdr);
+	}
 
 	iwl_mei_send_sap_msg_payload(mei->cldev, &rfkill_msg.hdr);
 }
-- 
GitLab


From 19e4a47ee74718a22e963e8a647c8c3bfe8bb05c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 15 Aug 2023 17:51:05 +0200
Subject: [PATCH 1482/1806] wifi: mac80211: check S1G action frame size

Before checking the action code, check that it even
exists in the frame.

Reported-by: syzbot+be9c824e6f269d608288@syzkaller.appspotmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/rx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 4f707d2a160fd..33f9764b94de2 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3732,6 +3732,10 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx)
 			break;
 		goto queue;
 	case WLAN_CATEGORY_S1G:
+		if (len < offsetofend(typeof(*mgmt),
+				      u.action.u.s1g.action_code))
+			break;
+
 		switch (mgmt->u.action.u.s1g.action_code) {
 		case WLAN_S1G_TWT_SETUP:
 		case WLAN_S1G_TWT_TEARDOWN:
-- 
GitLab


From 691b2bf1494620ff8c292626e4967c57e5705a8b Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 21 Aug 2023 18:10:08 +0800
Subject: [PATCH 1483/1806] bonding: update port speed when getting bond speed

Andrew reported a bonding issue that if we put an active-back bond on top
of a 802.3ad bond interface. When the 802.3ad bond's speed/duplex changed
dynamically. The upper bonding interface's speed/duplex can't be changed at
the same time, which will show incorrect speed.

Fix it by updating the port speed when calling ethtool.

Reported-by: Andrew Schorr <ajschorr@alumni.princeton.edu>
Closes: https://lore.kernel.org/netdev/ZEt3hvyREPVdbesO@Laptop-X1/
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Link: https://lore.kernel.org/r/20230821101008.797482-1-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f398bec784574..ed7212e61c541 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5718,6 +5718,7 @@ static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
 	 */
 	bond_for_each_slave(bond, slave, iter) {
 		if (bond_slave_can_tx(slave)) {
+			bond_update_speed_duplex(slave);
 			if (slave->speed != SPEED_UNKNOWN) {
 				if (BOND_MODE(bond) == BOND_MODE_BROADCAST)
 					speed = bond_mode_bcast_speed(slave,
-- 
GitLab


From a7ed3465daa240bdf01a5420f64336fee879c09d Mon Sep 17 00:00:00 2001
From: "GONG, Ruiqi" <gongruiqi1@huawei.com>
Date: Wed, 9 Aug 2023 15:45:03 +0800
Subject: [PATCH 1484/1806] netfilter: ebtables: fix fortify warnings in
 size_entry_mwt()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When compiling with gcc 13 and CONFIG_FORTIFY_SOURCE=y, the following
warning appears:

In function ‘fortify_memcpy_chk’,
    inlined from ‘size_entry_mwt’ at net/bridge/netfilter/ebtables.c:2118:2:
./include/linux/fortify-string.h:592:25: error: call to ‘__read_overflow2_field’
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Werror=attribute-warning]
  592 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The compiler is complaining:

memcpy(&offsets[1], &entry->watchers_offset,
                       sizeof(offsets) - sizeof(offsets[0]));

where memcpy reads beyong &entry->watchers_offset to copy
{watchers,target,next}_offset altogether into offsets[]. Silence the
warning by wrapping these three up via struct_group().

Signed-off-by: GONG, Ruiqi <gongruiqi1@huawei.com>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/uapi/linux/netfilter_bridge/ebtables.h | 14 ++++++++------
 net/bridge/netfilter/ebtables.c                |  3 +--
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/include/uapi/linux/netfilter_bridge/ebtables.h b/include/uapi/linux/netfilter_bridge/ebtables.h
index a494cf43a7552..b0caad82b6937 100644
--- a/include/uapi/linux/netfilter_bridge/ebtables.h
+++ b/include/uapi/linux/netfilter_bridge/ebtables.h
@@ -182,12 +182,14 @@ struct ebt_entry {
 	unsigned char sourcemsk[ETH_ALEN];
 	unsigned char destmac[ETH_ALEN];
 	unsigned char destmsk[ETH_ALEN];
-	/* sizeof ebt_entry + matches */
-	unsigned int watchers_offset;
-	/* sizeof ebt_entry + matches + watchers */
-	unsigned int target_offset;
-	/* sizeof ebt_entry + matches + watchers + target */
-	unsigned int next_offset;
+	__struct_group(/* no tag */, offsets, /* no attrs */,
+		/* sizeof ebt_entry + matches */
+		unsigned int watchers_offset;
+		/* sizeof ebt_entry + matches + watchers */
+		unsigned int target_offset;
+		/* sizeof ebt_entry + matches + watchers + target */
+		unsigned int next_offset;
+	);
 	unsigned char elems[0] __attribute__ ((aligned (__alignof__(struct ebt_replace))));
 };
 
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 757ec46fc45a0..aa23479b20b2a 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -2115,8 +2115,7 @@ static int size_entry_mwt(const struct ebt_entry *entry, const unsigned char *ba
 		return ret;
 
 	offsets[0] = sizeof(struct ebt_entry); /* matches come first */
-	memcpy(&offsets[1], &entry->watchers_offset,
-			sizeof(offsets) - sizeof(offsets[0]));
+	memcpy(&offsets[1], &entry->offsets, sizeof(entry->offsets));
 
 	if (state->buf_kern_start) {
 		buf_start = state->buf_kern_start + state->buf_kern_offset;
-- 
GitLab


From a2f02c9920b2cc3c6cc1f2c2aee37354e6edd801 Mon Sep 17 00:00:00 2001
From: "GONG, Ruiqi" <gongruiqi1@huawei.com>
Date: Wed, 9 Aug 2023 15:51:36 +0800
Subject: [PATCH 1485/1806] netfilter: ebtables: replace zero-length array
 members

As suggested by Kees[1], replace the old-style 0-element array members
of multiple structs in ebtables.h with modern C99 flexible array.

[1]: https://lore.kernel.org/all/5E8E0F9C-EE3F-4B0D-B827-DC47397E2A4A@kernel.org/

[ fw@strlen.de:
  keep struct ebt_entry_target as-is, causes compiler warning:
  "variable sized type 'struct ebt_entry_target' not at the end of a
  struct or class is a GNU extension" ]

Link: https://github.com/KSPP/linux/issues/21
Signed-off-by: GONG, Ruiqi <gongruiqi1@huawei.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/uapi/linux/netfilter_bridge/ebtables.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/netfilter_bridge/ebtables.h b/include/uapi/linux/netfilter_bridge/ebtables.h
index b0caad82b6937..4ff328f3d3397 100644
--- a/include/uapi/linux/netfilter_bridge/ebtables.h
+++ b/include/uapi/linux/netfilter_bridge/ebtables.h
@@ -87,7 +87,7 @@ struct ebt_entries {
 	/* nr. of entries */
 	unsigned int nentries;
 	/* entry list */
-	char data[0] __attribute__ ((aligned (__alignof__(struct ebt_replace))));
+	char data[] __attribute__ ((aligned (__alignof__(struct ebt_replace))));
 };
 
 /* used for the bitmask of struct ebt_entry */
@@ -129,7 +129,7 @@ struct ebt_entry_match {
 	} u;
 	/* size of data */
 	unsigned int match_size;
-	unsigned char data[0] __attribute__ ((aligned (__alignof__(struct ebt_replace))));
+	unsigned char data[] __attribute__ ((aligned (__alignof__(struct ebt_replace))));
 };
 
 struct ebt_entry_watcher {
@@ -142,7 +142,7 @@ struct ebt_entry_watcher {
 	} u;
 	/* size of data */
 	unsigned int watcher_size;
-	unsigned char data[0] __attribute__ ((aligned (__alignof__(struct ebt_replace))));
+	unsigned char data[] __attribute__ ((aligned (__alignof__(struct ebt_replace))));
 };
 
 struct ebt_entry_target {
@@ -190,7 +190,7 @@ struct ebt_entry {
 		/* sizeof ebt_entry + matches + watchers + target */
 		unsigned int next_offset;
 	);
-	unsigned char elems[0] __attribute__ ((aligned (__alignof__(struct ebt_replace))));
+	unsigned char elems[] __attribute__ ((aligned (__alignof__(struct ebt_replace))));
 };
 
 static __inline__ struct ebt_entry_target *
-- 
GitLab


From e53314034b2374cfe9a426a5edab51e30cfe8f02 Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Wed, 9 Aug 2023 01:06:04 +0000
Subject: [PATCH 1486/1806] netfilter: ipset: refactor deprecated strncpy

Use `strscpy_pad` instead of `strncpy`.

Link: https://github.com/KSPP/linux/issues/90
Cc: linux-hardening@vger.kernel.org
Signed-off-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/ipset/ip_set_core.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 0b68e2e2824e1..e564b51742611 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -872,7 +872,7 @@ ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name)
 	BUG_ON(!set);
 
 	read_lock_bh(&ip_set_ref_lock);
-	strncpy(name, set->name, IPSET_MAXNAMELEN);
+	strscpy_pad(name, set->name, IPSET_MAXNAMELEN);
 	read_unlock_bh(&ip_set_ref_lock);
 }
 EXPORT_SYMBOL_GPL(ip_set_name_byindex);
@@ -1326,7 +1326,7 @@ static int ip_set_rename(struct sk_buff *skb, const struct nfnl_info *info,
 			goto out;
 		}
 	}
-	strncpy(set->name, name2, IPSET_MAXNAMELEN);
+	strscpy_pad(set->name, name2, IPSET_MAXNAMELEN);
 
 out:
 	write_unlock_bh(&ip_set_ref_lock);
@@ -1380,9 +1380,9 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info,
 		return -EBUSY;
 	}
 
-	strncpy(from_name, from->name, IPSET_MAXNAMELEN);
-	strncpy(from->name, to->name, IPSET_MAXNAMELEN);
-	strncpy(to->name, from_name, IPSET_MAXNAMELEN);
+	strscpy_pad(from_name, from->name, IPSET_MAXNAMELEN);
+	strscpy_pad(from->name, to->name, IPSET_MAXNAMELEN);
+	strscpy_pad(to->name, from_name, IPSET_MAXNAMELEN);
 
 	swap(from->ref, to->ref);
 	ip_set(inst, from_id) = to;
-- 
GitLab


From 6cdd75a4a66b7c9b2a2667d87619816d6e744d0e Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Wed, 9 Aug 2023 01:06:05 +0000
Subject: [PATCH 1487/1806] netfilter: nf_tables: refactor deprecated strncpy

Prefer `strscpy_pad` over `strncpy`.

Signed-off-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_ct.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index e87fd4314c686..86bb9d7797d9e 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -108,7 +108,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 		helper = rcu_dereference(help->helper);
 		if (helper == NULL)
 			goto err;
-		strncpy((char *)dest, helper->name, NF_CT_HELPER_NAME_LEN);
+		strscpy_pad((char *)dest, helper->name, NF_CT_HELPER_NAME_LEN);
 		return;
 #ifdef CONFIG_NF_CONNTRACK_LABELS
 	case NFT_CT_LABELS: {
-- 
GitLab


From 7457af8bf9948aeb31de21e4be3bc1fef2730958 Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Wed, 9 Aug 2023 01:06:06 +0000
Subject: [PATCH 1488/1806] netfilter: nf_tables: refactor deprecated strncpy

Prefer `strscpy_pad` over `strncpy`.

Signed-off-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_fib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index 601c9e09d07aa..04b51f2853321 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -151,7 +151,7 @@ void nft_fib_store_result(void *reg, const struct nft_fib *priv,
 		if (priv->flags & NFTA_FIB_F_PRESENT)
 			*dreg = !!dev;
 		else
-			strncpy(reg, dev ? dev->name : "", IFNAMSIZ);
+			strscpy_pad(reg, dev ? dev->name : "", IFNAMSIZ);
 		break;
 	default:
 		WARN_ON_ONCE(1);
-- 
GitLab


From 6d87a4eae89e2ae015b40fd0adc90e9a7dc9fccb Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Wed, 9 Aug 2023 01:06:08 +0000
Subject: [PATCH 1489/1806] netfilter: nft_osf: refactor deprecated strncpy

Use `strscpy_pad` over `strncpy` for NUL-terminated strings.

We can also drop the + 1 from `NFT_OSF_MAXGENRELEN + 1` since `strscpy`
will guarantee NUL-termination.

Signed-off-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_osf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index 70820c66b5913..7f61506e5b44b 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -23,7 +23,7 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	struct nft_osf *priv = nft_expr_priv(expr);
 	u32 *dest = &regs->data[priv->dreg];
 	struct sk_buff *skb = pkt->skb;
-	char os_match[NFT_OSF_MAXGENRELEN + 1];
+	char os_match[NFT_OSF_MAXGENRELEN];
 	const struct tcphdr *tcp;
 	struct nf_osf_data data;
 	struct tcphdr _tcph;
@@ -45,7 +45,7 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	}
 
 	if (!nf_osf_find(skb, nf_osf_fingers, priv->ttl, &data)) {
-		strncpy((char *)dest, "unknown", NFT_OSF_MAXGENRELEN);
+		strscpy_pad((char *)dest, "unknown", NFT_OSF_MAXGENRELEN);
 	} else {
 		if (priv->flags & NFT_OSF_F_VERSION)
 			snprintf(os_match, NFT_OSF_MAXGENRELEN, "%s:%s",
@@ -53,7 +53,7 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		else
 			strscpy(os_match, data.genre, NFT_OSF_MAXGENRELEN);
 
-		strncpy((char *)dest, os_match, NFT_OSF_MAXGENRELEN);
+		strscpy_pad((char *)dest, os_match, NFT_OSF_MAXGENRELEN);
 	}
 }
 
-- 
GitLab


From ad156c23d65c1f44f8b4616c2a7505832e323069 Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Wed, 9 Aug 2023 01:06:07 +0000
Subject: [PATCH 1490/1806] netfilter: nft_meta: refactor deprecated strncpy

Prefer `strscpy_pad` to `strncpy`.

Signed-off-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_meta.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 8fdc7318c03c7..f7da7c43333b5 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -185,12 +185,12 @@ static noinline bool nft_meta_get_eval_kind(enum nft_meta_keys key,
 	case NFT_META_IIFKIND:
 		if (!in || !in->rtnl_link_ops)
 			return false;
-		strncpy((char *)dest, in->rtnl_link_ops->kind, IFNAMSIZ);
+		strscpy_pad((char *)dest, in->rtnl_link_ops->kind, IFNAMSIZ);
 		break;
 	case NFT_META_OIFKIND:
 		if (!out || !out->rtnl_link_ops)
 			return false;
-		strncpy((char *)dest, out->rtnl_link_ops->kind, IFNAMSIZ);
+		strscpy_pad((char *)dest, out->rtnl_link_ops->kind, IFNAMSIZ);
 		break;
 	default:
 		return false;
@@ -206,7 +206,7 @@ static void nft_meta_store_ifindex(u32 *dest, const struct net_device *dev)
 
 static void nft_meta_store_ifname(u32 *dest, const struct net_device *dev)
 {
-	strncpy((char *)dest, dev ? dev->name : "", IFNAMSIZ);
+	strscpy_pad((char *)dest, dev ? dev->name : "", IFNAMSIZ);
 }
 
 static bool nft_meta_store_iftype(u32 *dest, const struct net_device *dev)
-- 
GitLab


From 06f7d3c3f82c3a53de32a2c0c08e96c0d9ef69ec Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Wed, 9 Aug 2023 01:06:09 +0000
Subject: [PATCH 1491/1806] netfilter: x_tables: refactor deprecated strncpy

Prefer `strscpy_pad` to `strncpy`.

Signed-off-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/x_tables.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 470282cf3fae6..21624d68314f9 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -768,7 +768,7 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
 	m->u.user.match_size = msize;
 	strscpy(name, match->name, sizeof(name));
 	module_put(match->me);
-	strncpy(m->u.user.name, name, sizeof(m->u.user.name));
+	strscpy_pad(m->u.user.name, name, sizeof(m->u.user.name));
 
 	*size += off;
 	*dstptr += msize;
@@ -1148,7 +1148,7 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 	t->u.user.target_size = tsize;
 	strscpy(name, target->name, sizeof(name));
 	module_put(target->me);
-	strncpy(t->u.user.name, name, sizeof(t->u.user.name));
+	strscpy_pad(t->u.user.name, name, sizeof(t->u.user.name));
 
 	*size += off;
 	*dstptr += tsize;
@@ -2014,4 +2014,3 @@ static void __exit xt_fini(void)
 
 module_init(xt_init);
 module_exit(xt_fini);
-
-- 
GitLab


From aa222dd190d69ca8e0e2b990ec171c67a74d5383 Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Wed, 9 Aug 2023 01:06:10 +0000
Subject: [PATCH 1492/1806] netfilter: xtables: refactor deprecated strncpy

Prefer `strscpy_pad` as it's a more robust interface whilst maintaing
zero-padding behavior.

There may have existed a bug here due to both `tbl->repl.name` and
`info->name` having a size of 32 as defined below:
|  #define XT_TABLE_MAXNAMELEN 32

This may lead to buffer overreads in some situations -- `strscpy` solves
this by guaranteeing NUL-termination of the dest buffer.

Signed-off-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/xt_repldata.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/xt_repldata.h b/net/netfilter/xt_repldata.h
index 68ccbe50bb1ea..5d1fb7018dbac 100644
--- a/net/netfilter/xt_repldata.h
+++ b/net/netfilter/xt_repldata.h
@@ -29,7 +29,7 @@
 	if (tbl == NULL) \
 		return NULL; \
 	term = (struct type##_error *)&(((char *)tbl)[term_offset]); \
-	strncpy(tbl->repl.name, info->name, sizeof(tbl->repl.name)); \
+	strscpy_pad(tbl->repl.name, info->name, sizeof(tbl->repl.name)); \
 	*term = (struct type##_error)typ2##_ERROR_INIT;  \
 	tbl->repl.valid_hooks = hook_mask; \
 	tbl->repl.num_entries = nhooks + 1; \
-- 
GitLab


From 169384fbe8513185499bcbb817d198e6a63eb37e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 21 Jun 2023 10:36:26 +0200
Subject: [PATCH 1493/1806] netfilter: nf_tables: allow loop termination for
 pending fatal signal

abort early so task can exit faster if a fatal signal is pending,
no need to continue validation in that case.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_tables_api.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3e841e45f2c07..f00a1dff85e80 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3675,6 +3675,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
 		return -EMLINK;
 
 	list_for_each_entry(rule, &chain->rules, list) {
+		if (fatal_signal_pending(current))
+			return -EINTR;
+
 		if (!nft_is_active_next(ctx->net, rule))
 			continue;
 
@@ -10479,6 +10482,9 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 	if (ctx->chain == chain)
 		return -ELOOP;
 
+	if (fatal_signal_pending(current))
+		return -EINTR;
+
 	list_for_each_entry(rule, &chain->rules, list) {
 		nft_rule_for_each_expr(expr, last, rule) {
 			struct nft_immediate_expr *priv;
-- 
GitLab


From f708ed71775d2216d829fe6e00f1b4c6b38bc03c Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Mon, 21 Aug 2023 10:57:09 +0300
Subject: [PATCH 1494/1806] wifi: ath5k: Remove redundant dev_err()

There is no need to call the dev_err() function directly to print a custom
message when handling an error from platform_get_irq() function as it is
going to display an appropriate error message in case of a failure.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230726171235.2475625-1-ruanjinjie@huawei.com
---
 drivers/net/wireless/ath/ath5k/ahb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath5k/ahb.c b/drivers/net/wireless/ath/ath5k/ahb.c
index 28a1e5eff204e..08bd5d3b00f10 100644
--- a/drivers/net/wireless/ath/ath5k/ahb.c
+++ b/drivers/net/wireless/ath/ath5k/ahb.c
@@ -115,7 +115,6 @@ static int ath_ahb_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
-		dev_err(&pdev->dev, "no IRQ resource found: %d\n", irq);
 		ret = irq;
 		goto err_iounmap;
 	}
-- 
GitLab


From b674fb513e2e7a514fcde287c0f73915d393fdb6 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Tue, 25 Apr 2023 22:26:06 +0300
Subject: [PATCH 1495/1806] wifi: ath9k: fix races between ath9k_wmi_cmd and
 ath9k_wmi_ctrl_rx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, the synchronization between ath9k_wmi_cmd() and
ath9k_wmi_ctrl_rx() is exposed to a race condition which, although being
rather unlikely, can lead to invalid behaviour of ath9k_wmi_cmd().

Consider the following scenario:

CPU0					CPU1

ath9k_wmi_cmd(...)
  mutex_lock(&wmi->op_mutex)
  ath9k_wmi_cmd_issue(...)
  wait_for_completion_timeout(...)
  ---
  timeout
  ---
					/* the callback is being processed
					 * before last_seq_id became zero
					 */
					ath9k_wmi_ctrl_rx(...)
					  spin_lock_irqsave(...)
					  /* wmi->last_seq_id check here
					   * doesn't detect timeout yet
					   */
					  spin_unlock_irqrestore(...)
  /* last_seq_id is zeroed to
   * indicate there was a timeout
   */
  wmi->last_seq_id = 0
  mutex_unlock(&wmi->op_mutex)
  return -ETIMEDOUT

ath9k_wmi_cmd(...)
  mutex_lock(&wmi->op_mutex)
  /* the buffer is replaced with
   * another one
   */
  wmi->cmd_rsp_buf = rsp_buf
  wmi->cmd_rsp_len = rsp_len
  ath9k_wmi_cmd_issue(...)
    spin_lock_irqsave(...)
    spin_unlock_irqrestore(...)
  wait_for_completion_timeout(...)
					/* the continuation of the
					 * callback left after the first
					 * ath9k_wmi_cmd call
					 */
					  ath9k_wmi_rsp_callback(...)
					    /* copying data designated
					     * to already timeouted
					     * WMI command into an
					     * inappropriate wmi_cmd_buf
					     */
					    memcpy(...)
					    complete(&wmi->cmd_wait)
  /* awakened by the bogus callback
   * => invalid return result
   */
  mutex_unlock(&wmi->op_mutex)
  return 0

To fix this, update last_seq_id on timeout path inside ath9k_wmi_cmd()
under the wmi_lock. Move ath9k_wmi_rsp_callback() under wmi_lock inside
ath9k_wmi_ctrl_rx() so that the wmi->cmd_wait can be completed only for
initially designated wmi_cmd call, otherwise the path would be rejected
with last_seq_id check.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: fb9987d0f748 ("ath9k_htc: Support for AR9271 chipset.")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230425192607.18015-1-pchelkin@ispras.ru
---
 drivers/net/wireless/ath/ath9k/wmi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c
index d652c647d56b5..04f363cb90fe5 100644
--- a/drivers/net/wireless/ath/ath9k/wmi.c
+++ b/drivers/net/wireless/ath/ath9k/wmi.c
@@ -242,10 +242,10 @@ static void ath9k_wmi_ctrl_rx(void *priv, struct sk_buff *skb,
 		spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 		goto free_skb;
 	}
-	spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 
 	/* WMI command response */
 	ath9k_wmi_rsp_callback(wmi, skb);
+	spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 
 free_skb:
 	kfree_skb(skb);
@@ -308,8 +308,8 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id,
 	struct ath_common *common = ath9k_hw_common(ah);
 	u16 headroom = sizeof(struct htc_frame_hdr) +
 		       sizeof(struct wmi_cmd_hdr);
+	unsigned long time_left, flags;
 	struct sk_buff *skb;
-	unsigned long time_left;
 	int ret = 0;
 
 	if (ah->ah_flags & AH_UNPLUGGED)
@@ -345,7 +345,9 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id,
 	if (!time_left) {
 		ath_dbg(common, WMI, "Timeout waiting for WMI command: %s\n",
 			wmi_cmd_to_name(cmd_id));
+		spin_lock_irqsave(&wmi->wmi_lock, flags);
 		wmi->last_seq_id = 0;
+		spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 		mutex_unlock(&wmi->op_mutex);
 		return -ETIMEDOUT;
 	}
-- 
GitLab


From 454994cfa9e4c18b6df9f78b60db8eadc20a6c25 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Tue, 25 Apr 2023 22:26:07 +0300
Subject: [PATCH 1496/1806] wifi: ath9k: protect WMI command response buffer
 replacement with a lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If ath9k_wmi_cmd() has exited with a timeout, it is possible that during
next ath9k_wmi_cmd() call the wmi_rsp callback for previous wmi command
writes to new wmi->cmd_rsp_buf and makes a completion. This results in an
invalid ath9k_wmi_cmd() return value.

Move the replacement of WMI command response buffer and length under
wmi_lock. Note that last_seq_id value is updated there, too.

Thus, the buffer cannot be written to by a belated wmi_rsp callback
because that path is properly rejected by the last_seq_id check.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: fb9987d0f748 ("ath9k_htc: Support for AR9271 chipset.")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230425192607.18015-2-pchelkin@ispras.ru
---
 drivers/net/wireless/ath/ath9k/wmi.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c
index 04f363cb90fe5..1476b42b52a91 100644
--- a/drivers/net/wireless/ath/ath9k/wmi.c
+++ b/drivers/net/wireless/ath/ath9k/wmi.c
@@ -283,7 +283,8 @@ int ath9k_wmi_connect(struct htc_target *htc, struct wmi *wmi,
 
 static int ath9k_wmi_cmd_issue(struct wmi *wmi,
 			       struct sk_buff *skb,
-			       enum wmi_cmd_id cmd, u16 len)
+			       enum wmi_cmd_id cmd, u16 len,
+			       u8 *rsp_buf, u32 rsp_len)
 {
 	struct wmi_cmd_hdr *hdr;
 	unsigned long flags;
@@ -293,6 +294,11 @@ static int ath9k_wmi_cmd_issue(struct wmi *wmi,
 	hdr->seq_no = cpu_to_be16(++wmi->tx_seq_id);
 
 	spin_lock_irqsave(&wmi->wmi_lock, flags);
+
+	/* record the rsp buffer and length */
+	wmi->cmd_rsp_buf = rsp_buf;
+	wmi->cmd_rsp_len = rsp_len;
+
 	wmi->last_seq_id = wmi->tx_seq_id;
 	spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 
@@ -333,11 +339,7 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id,
 		goto out;
 	}
 
-	/* record the rsp buffer and length */
-	wmi->cmd_rsp_buf = rsp_buf;
-	wmi->cmd_rsp_len = rsp_len;
-
-	ret = ath9k_wmi_cmd_issue(wmi, skb, cmd_id, cmd_len);
+	ret = ath9k_wmi_cmd_issue(wmi, skb, cmd_id, cmd_len, rsp_buf, rsp_len);
 	if (ret)
 		goto out;
 
-- 
GitLab


From 6edb4ba6fb5b946d112259f54f4657f82eb71e89 Mon Sep 17 00:00:00 2001
From: Minjie Du <duminjie@vivo.com>
Date: Wed, 12 Jul 2023 19:47:40 +0800
Subject: [PATCH 1497/1806] wifi: ath9k: fix parameter check in
 ath9k_init_debug()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make IS_ERR() judge the debugfs_create_dir() function return
in ath9k_init_debug()

Signed-off-by: Minjie Du <duminjie@vivo.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230712114740.13226-1-duminjie@vivo.com
---
 drivers/net/wireless/ath/ath9k/debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index fb7a2952d0ce8..995c6e705637a 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -1420,7 +1420,7 @@ int ath9k_init_debug(struct ath_hw *ah)
 
 	sc->debug.debugfs_phy = debugfs_create_dir("ath9k",
 						   sc->hw->wiphy->debugfsdir);
-	if (!sc->debug.debugfs_phy)
+	if (IS_ERR(sc->debug.debugfs_phy))
 		return -ENOMEM;
 
 #ifdef CONFIG_ATH_DEBUG
-- 
GitLab


From 8b804643f42db68a1b7c56dc90a2fe5da6e5cf83 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 26 Jul 2023 21:50:08 +0300
Subject: [PATCH 1498/1806] wifi: ath9k: consistently use kstrtoX_from_user()
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use 'kstrtoul_from_user()' and 'kstrtobool_from_user()'
where appropriate and thus avoid some code duplication.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230726185046.188225-1-dmantipov@yandex.ru
---
 .../net/wireless/ath/ath9k/common-spectral.c  |  53 +++------
 drivers/net/wireless/ath/ath9k/debug.c        | 106 ++++++------------
 drivers/net/wireless/ath/ath9k/dfs_debug.c    |  14 +--
 .../net/wireless/ath/ath9k/htc_drv_debug.c    |  13 +--
 drivers/net/wireless/ath/ath9k/tx99.c         |  14 +--
 5 files changed, 61 insertions(+), 139 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/common-spectral.c b/drivers/net/wireless/ath/ath9k/common-spectral.c
index e055adfb5361b..a5349c72c3321 100644
--- a/drivers/net/wireless/ath/ath9k/common-spectral.c
+++ b/drivers/net/wireless/ath/ath9k/common-spectral.c
@@ -855,16 +855,11 @@ static ssize_t write_file_spectral_short_repeat(struct file *file,
 {
 	struct ath_spec_scan_priv *spec_priv = file->private_data;
 	unsigned long val;
-	char buf[32];
-	ssize_t len;
-
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
+	ssize_t ret;
 
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &val))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &val);
+	if (ret)
+		return ret;
 
 	if (val > 1)
 		return -EINVAL;
@@ -903,17 +898,11 @@ static ssize_t write_file_spectral_count(struct file *file,
 {
 	struct ath_spec_scan_priv *spec_priv = file->private_data;
 	unsigned long val;
-	char buf[32];
-	ssize_t len;
-
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
-
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &val))
-		return -EINVAL;
+	ssize_t ret;
 
+	ret = kstrtoul_from_user(user_buf, count, 0, &val);
+	if (ret)
+		return ret;
 	if (val > 255)
 		return -EINVAL;
 
@@ -951,16 +940,11 @@ static ssize_t write_file_spectral_period(struct file *file,
 {
 	struct ath_spec_scan_priv *spec_priv = file->private_data;
 	unsigned long val;
-	char buf[32];
-	ssize_t len;
-
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
+	ssize_t ret;
 
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &val))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &val);
+	if (ret)
+		return ret;
 
 	if (val > 255)
 		return -EINVAL;
@@ -999,16 +983,11 @@ static ssize_t write_file_spectral_fft_period(struct file *file,
 {
 	struct ath_spec_scan_priv *spec_priv = file->private_data;
 	unsigned long val;
-	char buf[32];
-	ssize_t len;
-
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
+	ssize_t ret;
 
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &val))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &val);
+	if (ret)
+		return ret;
 
 	if (val > 15)
 		return -EINVAL;
diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index 995c6e705637a..9bc57c5a89bfe 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -96,21 +96,16 @@ static ssize_t read_file_debug(struct file *file, char __user *user_buf,
 }
 
 static ssize_t write_file_debug(struct file *file, const char __user *user_buf,
-			     size_t count, loff_t *ppos)
+				size_t count, loff_t *ppos)
 {
 	struct ath_softc *sc = file->private_data;
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	unsigned long mask;
-	char buf[32];
-	ssize_t len;
+	ssize_t ret;
 
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
-
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &mask))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &mask);
+	if (ret)
+		return ret;
 
 	common->debug_mask = mask;
 	return count;
@@ -191,16 +186,11 @@ static ssize_t write_file_ani(struct file *file,
 	struct ath_softc *sc = file->private_data;
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	unsigned long ani;
-	char buf[32];
-	ssize_t len;
+	ssize_t ret;
 
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
-
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &ani))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &ani);
+	if (ret)
+		return ret;
 
 	if (ani > 1)
 		return -EINVAL;
@@ -248,20 +238,15 @@ static ssize_t write_file_bt_ant_diversity(struct file *file,
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	struct ath9k_hw_capabilities *pCap = &sc->sc_ah->caps;
 	unsigned long bt_ant_diversity;
-	char buf[32];
-	ssize_t len;
+	ssize_t ret;
 
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
+	ret = kstrtoul_from_user(user_buf, count, 0, &bt_ant_diversity);
+	if (ret)
+		return ret;
 
 	if (!(pCap->hw_caps & ATH9K_HW_CAP_BT_ANT_DIV))
 		goto exit;
 
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &bt_ant_diversity))
-		return -EINVAL;
-
 	common->bt_ant_diversity = !!bt_ant_diversity;
 	ath9k_ps_wakeup(sc);
 	ath9k_hw_set_bt_ant_diversity(sc->sc_ah, common->bt_ant_diversity);
@@ -792,16 +777,11 @@ static ssize_t write_file_reset(struct file *file,
 	struct ath_hw *ah = sc->sc_ah;
 	struct ath_common *common = ath9k_hw_common(ah);
 	unsigned long val;
-	char buf[32];
-	ssize_t len;
-
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
+	ssize_t ret;
 
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &val))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &val);
+	if (ret)
+		return ret;
 
 	if (val != 1)
 		return -EINVAL;
@@ -886,16 +866,11 @@ static ssize_t write_file_regidx(struct file *file, const char __user *user_buf,
 {
 	struct ath_softc *sc = file->private_data;
 	unsigned long regidx;
-	char buf[32];
-	ssize_t len;
+	ssize_t ret;
 
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
-
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &regidx))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &regidx);
+	if (ret)
+		return ret;
 
 	sc->debug.regidx = regidx;
 	return count;
@@ -931,16 +906,11 @@ static ssize_t write_file_regval(struct file *file, const char __user *user_buf,
 	struct ath_softc *sc = file->private_data;
 	struct ath_hw *ah = sc->sc_ah;
 	unsigned long regval;
-	char buf[32];
-	ssize_t len;
-
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
+	ssize_t ret;
 
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &regval))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &regval);
+	if (ret)
+		return ret;
 
 	ath9k_ps_wakeup(sc);
 	REG_WRITE_D(ah, sc->debug.regidx, regval);
@@ -1128,16 +1098,11 @@ static ssize_t write_file_wow(struct file *file, const char __user *user_buf,
 {
 	struct ath_softc *sc = file->private_data;
 	unsigned long val;
-	char buf[32];
-	ssize_t len;
-
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
+	ssize_t ret;
 
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &val))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &val);
+	if (ret)
+		return ret;
 
 	if (val != 1)
 		return -EINVAL;
@@ -1191,17 +1156,12 @@ static ssize_t write_file_tpc(struct file *file, const char __user *user_buf,
 	struct ath_softc *sc = file->private_data;
 	struct ath_hw *ah = sc->sc_ah;
 	unsigned long val;
-	char buf[32];
-	ssize_t len;
+	ssize_t ret;
 	bool tpc_enabled;
 
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
-
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &val))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &val);
+	if (ret)
+		return ret;
 
 	if (val > 1)
 		return -EINVAL;
diff --git a/drivers/net/wireless/ath/ath9k/dfs_debug.c b/drivers/net/wireless/ath/ath9k/dfs_debug.c
index 2a79c2fa84152..8e18e9b4ef483 100644
--- a/drivers/net/wireless/ath/ath9k/dfs_debug.c
+++ b/drivers/net/wireless/ath/ath9k/dfs_debug.c
@@ -99,17 +99,11 @@ static ssize_t write_file_dfs(struct file *file, const char __user *user_buf,
 {
 	struct ath_softc *sc = file->private_data;
 	unsigned long val;
-	char buf[32];
-	ssize_t len;
-
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
-
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &val))
-		return -EINVAL;
+	ssize_t ret;
 
+	ret = kstrtoul_from_user(user_buf, count, 0, &val);
+	if (ret)
+		return ret;
 	if (val == DFS_STATS_RESET_MAGIC)
 		memset(&sc->debug.stats.dfs_stats, 0,
 		       sizeof(sc->debug.stats.dfs_stats));
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
index b3ed65e5c4da8..1ed2b1216bce9 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
@@ -375,16 +375,11 @@ static ssize_t write_file_debug(struct file *file, const char __user *user_buf,
 	struct ath9k_htc_priv *priv = file->private_data;
 	struct ath_common *common = ath9k_hw_common(priv->ah);
 	unsigned long mask;
-	char buf[32];
-	ssize_t len;
-
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
+	ssize_t ret;
 
-	buf[len] = '\0';
-	if (kstrtoul(buf, 0, &mask))
-		return -EINVAL;
+	ret = kstrtoul_from_user(user_buf, count, 0, &mask);
+	if (ret)
+		return ret;
 
 	common->debug_mask = mask;
 	return count;
diff --git a/drivers/net/wireless/ath/ath9k/tx99.c b/drivers/net/wireless/ath/ath9k/tx99.c
index 8a996ed9a3bef..f2144fd390932 100644
--- a/drivers/net/wireless/ath/ath9k/tx99.c
+++ b/drivers/net/wireless/ath/ath9k/tx99.c
@@ -172,9 +172,8 @@ static ssize_t write_file_tx99(struct file *file, const char __user *user_buf,
 {
 	struct ath_softc *sc = file->private_data;
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
-	char buf[32];
 	bool start;
-	ssize_t len;
+	ssize_t ret;
 	int r;
 
 	if (count < 1)
@@ -183,14 +182,9 @@ static ssize_t write_file_tx99(struct file *file, const char __user *user_buf,
 	if (sc->cur_chan->nvifs > 1)
 		return -EOPNOTSUPP;
 
-	len = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, len))
-		return -EFAULT;
-
-	buf[len] = '\0';
-
-	if (kstrtobool(buf, &start))
-		return -EINVAL;
+	ret = kstrtobool_from_user(user_buf, count, &start);
+	if (ret)
+		return ret;
 
 	mutex_lock(&sc->mutex);
 
-- 
GitLab


From b2fd72aafb13118503df6798b18ed28f83dda2c2 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Mon, 31 Jul 2023 20:44:55 +0800
Subject: [PATCH 1499/1806] wifi: ath9k: Remove unnecessary ternary operators
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Ther are a little ternary operators, the true or false judgement
of which is unnecessary in C language semantics.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230731124455.2039184-1-ruanjinjie@huawei.com
---
 drivers/net/wireless/ath/ath9k/eeprom_9287.c  | 3 +--
 drivers/net/wireless/ath/ath9k/hif_usb.c      | 2 +-
 drivers/net/wireless/ath/ath9k/htc_drv_main.c | 2 +-
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/eeprom_9287.c b/drivers/net/wireless/ath/ath9k/eeprom_9287.c
index 3caa149b10131..fd5312c2a7e30 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom_9287.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom_9287.c
@@ -572,8 +572,7 @@ static void ath9k_hw_set_ar9287_power_per_rate_table(struct ath_hw *ah,
 	}
 
 	for (ctlMode = 0; ctlMode < numCtlModes; ctlMode++) {
-		bool isHt40CtlMode =
-			(pCtlMode[ctlMode] == CTL_2GHT40) ? true : false;
+		bool isHt40CtlMode = pCtlMode[ctlMode] == CTL_2GHT40;
 
 		if (isHt40CtlMode)
 			freq = centers.synth_center;
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index 27ff1ca2631fc..e5414435b1414 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -1432,7 +1432,7 @@ static void ath9k_hif_usb_disconnect(struct usb_interface *interface)
 {
 	struct usb_device *udev = interface_to_usbdev(interface);
 	struct hif_device_usb *hif_dev = usb_get_intfdata(interface);
-	bool unplugged = (udev->state == USB_STATE_NOTATTACHED) ? true : false;
+	bool unplugged = udev->state == USB_STATE_NOTATTACHED;
 
 	if (!hif_dev)
 		return;
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 51766de5ec3b6..44e02cfe24380 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -719,7 +719,7 @@ static int ath9k_htc_tx_aggr_oper(struct ath9k_htc_priv *priv,
 
 	aggr.sta_index = ista->index;
 	aggr.tidno = tid & 0xf;
-	aggr.aggr_enable = (action == IEEE80211_AMPDU_TX_START) ? true : false;
+	aggr.aggr_enable = action == IEEE80211_AMPDU_TX_START;
 
 	WMI_CMD_BUF(WMI_TX_AGGR_ENABLE_CMDID, &aggr);
 	if (ret)
-- 
GitLab


From 383e1b6a90c33f6e48dd39691e8b9000145247b6 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Thu, 10 Aug 2023 22:52:22 +0800
Subject: [PATCH 1500/1806] wifi: ath9k: Remove unused declarations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit b57ba3b2f7b0 ("ath9k: move ath9k_reload_chainmask_settings to common")
removed the implementation ath9k_reload_chainmask_settings() but not the declaration.
Also commit 978f78bf7137 ("ath9k_hw: Move bt_stomp to hw from common.") left behind
ath9k_cmn_btcoex_bt_stomp() declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230810145222.34364-1-yuehaibing@huawei.com
---
 drivers/net/wireless/ath/ath9k/ath9k.h  | 1 -
 drivers/net/wireless/ath/ath9k/common.h | 2 --
 2 files changed, 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index 2cc23605c9fc5..668fc07b30735 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -1129,7 +1129,6 @@ void ath_restart_work(struct ath_softc *sc);
 int ath9k_init_device(u16 devid, struct ath_softc *sc,
 		    const struct ath_bus_ops *bus_ops);
 void ath9k_deinit_device(struct ath_softc *sc);
-void ath9k_reload_chainmask_settings(struct ath_softc *sc);
 u8 ath_txchainmask_reduction(struct ath_softc *sc, u8 chainmask, u32 rate);
 void ath_start_rfkill_poll(struct ath_softc *sc);
 void ath9k_rfkill_poll_state(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/ath/ath9k/common.h b/drivers/net/wireless/ath/ath9k/common.h
index f0ab6f9955e40..12204cf86fcf9 100644
--- a/drivers/net/wireless/ath/ath9k/common.h
+++ b/drivers/net/wireless/ath/ath9k/common.h
@@ -85,8 +85,6 @@ struct ath9k_channel *ath9k_cmn_get_channel(struct ieee80211_hw *hw,
 					    struct ath_hw *ah,
 					    struct cfg80211_chan_def *chandef);
 int ath9k_cmn_count_streams(unsigned int chainmask, int max);
-void ath9k_cmn_btcoex_bt_stomp(struct ath_common *common,
-				  enum ath_stomp_type stomp_type);
 void ath9k_cmn_update_txpow(struct ath_hw *ah, u16 cur_txpow,
 			    u16 new_txpow, u16 *txpower);
 void ath9k_cmn_init_crypto(struct ath_hw *ah);
-- 
GitLab


From ab6c637ad0276e42f8acabcbc64932a6d346dab3 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Mon, 21 Aug 2023 22:00:53 -0700
Subject: [PATCH 1501/1806] bpf: Fix a bpf_kptr_xchg() issue with local kptr

When reviewing local percpu kptr support, Alexei discovered a bug
wherea bpf_kptr_xchg() may succeed even if the map value kptr type and
locally allocated obj type do not match ([1]). Missed struct btf_id
comparison is the reason for the bug. This patch added such struct btf_id
comparison and will flag verification failure if types do not match.

  [1] https://lore.kernel.org/bpf/20230819002907.io3iphmnuk43xblu@macbook-pro-8.dhcp.thefacebook.com/#t

Reported-by: Alexei Starovoitov <ast@kernel.org>
Fixes: 738c96d5e2e3 ("bpf: Allow local kptrs to be exchanged via bpf_kptr_xchg")
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230822050053.2886960-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4ccca1f6c9981..3a91bfd7b9cce 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4990,20 +4990,22 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
 			       struct bpf_reg_state *reg, u32 regno)
 {
 	const char *targ_name = btf_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id);
-	int perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU;
+	int perm_flags;
 	const char *reg_name = "";
 
-	/* Only unreferenced case accepts untrusted pointers */
-	if (kptr_field->type == BPF_KPTR_UNREF)
-		perm_flags |= PTR_UNTRUSTED;
+	if (btf_is_kernel(reg->btf)) {
+		perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU;
+
+		/* Only unreferenced case accepts untrusted pointers */
+		if (kptr_field->type == BPF_KPTR_UNREF)
+			perm_flags |= PTR_UNTRUSTED;
+	} else {
+		perm_flags = PTR_MAYBE_NULL | MEM_ALLOC;
+	}
 
 	if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags))
 		goto bad_type;
 
-	if (!btf_is_kernel(reg->btf)) {
-		verbose(env, "R%d must point to kernel BTF\n", regno);
-		return -EINVAL;
-	}
 	/* We need to verify reg->type and reg->btf, before accessing reg->btf */
 	reg_name = btf_type_name(reg->btf, reg->btf_id);
 
@@ -5016,7 +5018,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
 	if (__check_ptr_off_reg(env, reg, regno, true))
 		return -EACCES;
 
-	/* A full type match is needed, as BTF can be vmlinux or module BTF, and
+	/* A full type match is needed, as BTF can be vmlinux, module or prog BTF, and
 	 * we also need to take into account the reg->off.
 	 *
 	 * We want to support cases like:
@@ -7916,7 +7918,10 @@ found:
 			verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n");
 			return -EFAULT;
 		}
-		/* Handled by helper specific checks */
+		if (meta->func_id == BPF_FUNC_kptr_xchg) {
+			if (map_kptr_match_type(env, meta->kptr_field, reg, regno))
+				return -EACCES;
+		}
 		break;
 	case PTR_TO_BTF_ID | MEM_PERCPU:
 	case PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED:
-- 
GitLab


From fb30159426439bfe9a1435c0555f67201198988c Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Mon, 21 Aug 2023 22:00:58 -0700
Subject: [PATCH 1502/1806] selftests/bpf: Add a failure test for
 bpf_kptr_xchg() with local kptr

For a bpf_kptr_xchg() with local kptr, if the map value kptr type and
allocated local obj type does not match, with the previous patch,
the below verifier error message will be logged:
  R2 is of type <allocated local obj type> but <map value kptr type> is expected

Without the previous patch, the test will have unexpected success.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230822050058.2887354-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/local_kptr_stash.c         | 10 ++-
 .../bpf/progs/local_kptr_stash_fail.c         | 65 +++++++++++++++++++
 2 files changed, 74 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c

diff --git a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
index 76f1da877f818..158616c946582 100644
--- a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
+++ b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
@@ -5,6 +5,7 @@
 #include <network_helpers.h>
 
 #include "local_kptr_stash.skel.h"
+#include "local_kptr_stash_fail.skel.h"
 static void test_local_kptr_stash_simple(void)
 {
 	LIBBPF_OPTS(bpf_test_run_opts, opts,
@@ -51,10 +52,17 @@ static void test_local_kptr_stash_unstash(void)
 	local_kptr_stash__destroy(skel);
 }
 
-void test_local_kptr_stash_success(void)
+static void test_local_kptr_stash_fail(void)
+{
+	RUN_TESTS(local_kptr_stash_fail);
+}
+
+void test_local_kptr_stash(void)
 {
 	if (test__start_subtest("local_kptr_stash_simple"))
 		test_local_kptr_stash_simple();
 	if (test__start_subtest("local_kptr_stash_unstash"))
 		test_local_kptr_stash_unstash();
+	if (test__start_subtest("local_kptr_stash_fail"))
+		test_local_kptr_stash_fail();
 }
diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c
new file mode 100644
index 0000000000000..5484d1e9801d3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "../bpf_experimental.h"
+#include "bpf_misc.h"
+
+struct node_data {
+	long key;
+	long data;
+	struct bpf_rb_node node;
+};
+
+struct map_value {
+	struct node_data __kptr *node;
+};
+
+struct node_data2 {
+	long key[4];
+};
+
+/* This is necessary so that LLVM generates BTF for node_data struct
+ * If it's not included, a fwd reference for node_data will be generated but
+ * no struct. Example BTF of "node" field in map_value when not included:
+ *
+ * [10] PTR '(anon)' type_id=35
+ * [34] FWD 'node_data' fwd_kind=struct
+ * [35] TYPE_TAG 'kptr_ref' type_id=34
+ */
+struct node_data *just_here_because_btf_bug;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 2);
+} some_nodes SEC(".maps");
+
+SEC("tc")
+__failure __msg("invalid kptr access, R2 type=ptr_node_data2 expected=ptr_node_data")
+long stash_rb_nodes(void *ctx)
+{
+	struct map_value *mapval;
+	struct node_data2 *res;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	res = bpf_obj_new(typeof(*res));
+	if (!res)
+		return 1;
+	res->key[0] = 40;
+
+	res = bpf_kptr_xchg(&mapval->node, res);
+	if (res)
+		bpf_obj_drop(res);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From 73582f090f053ffdd168f6c2b42b18c67906d120 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 21 Aug 2023 20:55:01 +0800
Subject: [PATCH 1503/1806] net: dsa: microchip: Remove unused declarations

Commit 91a98917a883 ("net: dsa: microchip: move switch chip_id detection to ksz_common")
removed ksz8_switch_detect() but not its declaration.
Commit 6ec23aaaac43 ("net: dsa: microchip: move ksz_dev_ops to ksz_common.c")
declared but never implemented other functions.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://lore.kernel.org/r/20230821125501.19624-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz8.h    | 2 --
 drivers/net/dsa/microchip/ksz9477.h | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz8.h b/drivers/net/dsa/microchip/ksz8.h
index e68465fdf6b99..4cea811e73ac6 100644
--- a/drivers/net/dsa/microchip/ksz8.h
+++ b/drivers/net/dsa/microchip/ksz8.h
@@ -48,13 +48,11 @@ int ksz8_port_mirror_add(struct ksz_device *dev, int port,
 			 bool ingress, struct netlink_ext_ack *extack);
 void ksz8_port_mirror_del(struct ksz_device *dev, int port,
 			  struct dsa_mall_mirror_tc_entry *mirror);
-int ksz8_get_stp_reg(void);
 void ksz8_get_caps(struct ksz_device *dev, int port,
 		   struct phylink_config *config);
 void ksz8_config_cpu_port(struct dsa_switch *ds);
 int ksz8_enable_stp_addr(struct ksz_device *dev);
 int ksz8_reset_switch(struct ksz_device *dev);
-int ksz8_switch_detect(struct ksz_device *dev);
 int ksz8_switch_init(struct ksz_device *dev);
 void ksz8_switch_exit(struct ksz_device *dev);
 int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu);
diff --git a/drivers/net/dsa/microchip/ksz9477.h b/drivers/net/dsa/microchip/ksz9477.h
index b6f7e3c46e3f9..a6f425866a29a 100644
--- a/drivers/net/dsa/microchip/ksz9477.h
+++ b/drivers/net/dsa/microchip/ksz9477.h
@@ -36,7 +36,6 @@ int ksz9477_port_mirror_add(struct ksz_device *dev, int port,
 			    bool ingress, struct netlink_ext_ack *extack);
 void ksz9477_port_mirror_del(struct ksz_device *dev, int port,
 			     struct dsa_mall_mirror_tc_entry *mirror);
-int ksz9477_get_stp_reg(void);
 void ksz9477_get_caps(struct ksz_device *dev, int port,
 		      struct phylink_config *config);
 int ksz9477_fdb_dump(struct ksz_device *dev, int port,
@@ -54,7 +53,6 @@ void ksz9477_config_cpu_port(struct dsa_switch *ds);
 int ksz9477_tc_cbs_set_cinc(struct ksz_device *dev, int port, u32 val);
 int ksz9477_enable_stp_addr(struct ksz_device *dev);
 int ksz9477_reset_switch(struct ksz_device *dev);
-int ksz9477_dsa_init(struct ksz_device *dev);
 int ksz9477_switch_init(struct ksz_device *dev);
 void ksz9477_switch_exit(struct ksz_device *dev);
 void ksz9477_port_queue_split(struct ksz_device *dev, int port);
-- 
GitLab


From 49e62a0462a2d669e35f97eb3e0a6f2aab20518d Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 21 Aug 2023 21:02:18 +0800
Subject: [PATCH 1504/1806] net: mscc: ocelot: Remove unused declarations

Commit 6c30384eb1de ("net: mscc: ocelot: register devlink ports")
declared but never implemented ocelot_devlink_init() and
ocelot_devlink_teardown().
Commit 2096805497e2 ("net: mscc: ocelot: automatically detect VCAP constants")
declared but never implemented ocelot_detect_vcap_constants().
Commit 403ffc2c34de ("net: mscc: ocelot: add support for preemptible traffic classes")
declared but never implemented ocelot_port_update_preemptible_tcs().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230821130218.19096-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mscc/ocelot.h      | 2 --
 drivers/net/ethernet/mscc/ocelot_vcap.h | 1 -
 include/soc/mscc/ocelot.h               | 1 -
 3 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 87f2055c242c9..e50be508c1663 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -97,8 +97,6 @@ int ocelot_netdev_to_port(struct net_device *dev);
 int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target,
 		      struct device_node *portnp);
 void ocelot_release_port(struct ocelot_port *ocelot_port);
-int ocelot_devlink_init(struct ocelot *ocelot);
-void ocelot_devlink_teardown(struct ocelot *ocelot);
 int ocelot_port_devlink_init(struct ocelot *ocelot, int port,
 			     enum devlink_port_flavour flavour);
 void ocelot_port_devlink_teardown(struct ocelot *ocelot, int port);
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.h b/drivers/net/ethernet/mscc/ocelot_vcap.h
index 523611ccc48fd..6f546695faa5a 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.h
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.h
@@ -15,7 +15,6 @@
 int ocelot_vcap_filter_stats_update(struct ocelot *ocelot,
 				    struct ocelot_vcap_filter *rule);
 
-void ocelot_detect_vcap_constants(struct ocelot *ocelot);
 int ocelot_vcap_init(struct ocelot *ocelot);
 
 int ocelot_setup_tc_cls_flower(struct ocelot_port_private *priv,
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index a8c2817335b9a..1e1b40f4e664e 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -1165,7 +1165,6 @@ int ocelot_port_get_mm(struct ocelot *ocelot, int port,
 		       struct ethtool_mm_state *state);
 int ocelot_port_mqprio(struct ocelot *ocelot, int port,
 		       struct tc_mqprio_qopt_offload *mqprio);
-void ocelot_port_update_preemptible_tcs(struct ocelot *ocelot, int port);
 
 #if IS_ENABLED(CONFIG_BRIDGE_MRP)
 int ocelot_mrp_add(struct ocelot *ocelot, int port,
-- 
GitLab


From efa47e80c2bfdd6cab9c9de014fca3e630eb6cfe Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 21 Aug 2023 21:47:17 +0800
Subject: [PATCH 1505/1806] ionic: Remove unused declarations

Commit fbfb8031533c ("ionic: Add hardware init and device commands")
declared but never implemented ionic_q_rewind()/ionic_set_dma_mask().
Commit 969f84394604 ("ionic: sync the filters in the work task")
declared but never implemented ionic_rx_filters_need_sync().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Acked-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20230821134717.51936-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic.h           | 1 -
 drivers/net/ethernet/pensando/ionic/ionic_dev.h       | 1 -
 drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h | 1 -
 3 files changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h
index 602f4d45d5291..2453a40f6ee81 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic.h
@@ -81,7 +81,6 @@ int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_wait);
 int ionic_dev_cmd_wait_nomsg(struct ionic *ionic, unsigned long max_wait);
 void ionic_dev_cmd_dev_err_print(struct ionic *ionic, u8 opcode, u8 status,
 				 int err);
-int ionic_set_dma_mask(struct ionic *ionic);
 int ionic_setup(struct ionic *ionic);
 
 int ionic_identify(struct ionic *ionic);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index 0bea208bfba2f..6aac98bcb9f4b 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -376,7 +376,6 @@ void ionic_q_cmb_map(struct ionic_queue *q, void __iomem *base, dma_addr_t base_
 void ionic_q_sg_map(struct ionic_queue *q, void *base, dma_addr_t base_pa);
 void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb,
 		  void *cb_arg);
-void ionic_q_rewind(struct ionic_queue *q, struct ionic_desc_info *start);
 void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info,
 		     unsigned int stop_index);
 int ionic_heartbeat_check(struct ionic *ionic);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h
index 87b2666f248b0..ee9e99cd1b5ed 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h
@@ -43,7 +43,6 @@ struct ionic_rx_filter *ionic_rx_filter_by_addr(struct ionic_lif *lif, const u8
 struct ionic_rx_filter *ionic_rx_filter_rxsteer(struct ionic_lif *lif);
 void ionic_rx_filter_sync(struct ionic_lif *lif);
 int ionic_lif_list_addr(struct ionic_lif *lif, const u8 *addr, bool mode);
-int ionic_rx_filters_need_sync(struct ionic_lif *lif);
 int ionic_lif_vlan_add(struct ionic_lif *lif, const u16 vid);
 int ionic_lif_vlan_del(struct ionic_lif *lif, const u16 vid);
 
-- 
GitLab


From dff96d7c0cda7cedcbfd382f15fa1c0908e8f317 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 21 Aug 2023 21:55:56 +0800
Subject: [PATCH 1506/1806] net: microchip: Remove unused declarations

Commit 264a9c5c9dff ("net: sparx5: Remove unused GLAG handling in PGID")
removed sparx5_pgid_alloc_glag() but not its declaration.
Commit 27d293cceee5 ("net: microchip: sparx5: Add support for rule count by cookie")
removed vcap_rule_iter() but not its declaration.
Commit 8beef08f4618 ("net: microchip: sparx5: Adding initial VCAP API support")
declared but never implemented vcap_api_set_client().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230821135556.43224-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microchip/sparx5/sparx5_main.h   | 1 -
 drivers/net/ethernet/microchip/vcap/vcap_api.h        | 3 ---
 drivers/net/ethernet/microchip/vcap/vcap_api_client.h | 3 ---
 3 files changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index 89a9a7afa32c7..6f565c0c0c3dc 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -414,7 +414,6 @@ enum sparx5_pgid_type {
 };
 
 void sparx5_pgid_init(struct sparx5 *spx5);
-int sparx5_pgid_alloc_glag(struct sparx5 *spx5, u16 *idx);
 int sparx5_pgid_alloc_mcast(struct sparx5 *spx5, u16 *idx);
 int sparx5_pgid_free(struct sparx5 *spx5, u16 idx);
 
diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.h b/drivers/net/ethernet/microchip/vcap/vcap_api.h
index 62db270f65af2..9eccfa633c1af 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_api.h
+++ b/drivers/net/ethernet/microchip/vcap/vcap_api.h
@@ -277,7 +277,4 @@ struct vcap_control {
 	struct list_head list; /* list of vcap instances */
 };
 
-/* Set client control interface on the API */
-int vcap_api_set_client(struct vcap_control *vctrl);
-
 #endif /* __VCAP_API__ */
diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h
index d9d1f7c9d762c..88641508f885e 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h
+++ b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h
@@ -226,9 +226,6 @@ int vcap_chain_offset(struct vcap_control *vctrl, int from_cid, int to_cid);
 bool vcap_is_next_lookup(struct vcap_control *vctrl, int cur_cid, int next_cid);
 /* Is this chain id the last lookup of all VCAPs */
 bool vcap_is_last_chain(struct vcap_control *vctrl, int cid, bool ingress);
-/* Provide all rules via a callback interface */
-int vcap_rule_iter(struct vcap_control *vctrl,
-		   int (*callback)(void *, struct vcap_rule *), void *arg);
 /* Match a list of keys against the keysets available in a vcap type */
 bool vcap_rule_find_keysets(struct vcap_rule *rule,
 			    struct vcap_keyset_list *matches);
-- 
GitLab


From a491add19faf335faa75d6baa69adb0a9a588df2 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 21 Aug 2023 21:40:29 +0800
Subject: [PATCH 1507/1806] net: ethernet: ti: Remove unused declarations

Commit e8609e69470f ("net: ethernet: ti: am65-cpsw: Convert to PHYLINK")
removed am65_cpsw_nuss_adjust_link() but not its declaration.
Commit 84640e27f230 ("net: netcp: Add Keystone NetCP core ethernet driver")
declared but never implemented netcp_device_find_module().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Roger Quadros <rogerq@kernel.org>
Link: https://lore.kernel.org/r/20230821134029.40084-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.h | 1 -
 drivers/net/ethernet/ti/netcp.h          | 2 --
 2 files changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index bf40c88fbd9bd..f3dad2ab9828b 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -192,7 +192,6 @@ struct am65_cpsw_ndev_priv {
 
 extern const struct ethtool_ops am65_cpsw_ethtool_ops_slave;
 
-void am65_cpsw_nuss_adjust_link(struct net_device *ndev);
 void am65_cpsw_nuss_set_p0_ptype(struct am65_cpsw_common *common);
 void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common);
 int am65_cpsw_nuss_update_tx_chns(struct am65_cpsw_common *common, int num_tx);
diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h
index 43d5cd59b56bb..7007eb8bed365 100644
--- a/drivers/net/ethernet/ti/netcp.h
+++ b/drivers/net/ethernet/ti/netcp.h
@@ -233,8 +233,6 @@ int netcp_register_rxhook(struct netcp_intf *netcp_priv, int order,
 			  netcp_hook_rtn *hook_rtn, void *hook_data);
 int netcp_unregister_rxhook(struct netcp_intf *netcp_priv, int order,
 			    netcp_hook_rtn *hook_rtn, void *hook_data);
-void *netcp_device_find_module(struct netcp_device *netcp_device,
-			       const char *name);
 
 /* SGMII functions */
 int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port);
-- 
GitLab


From 63c11dc2ca8bf5d8fb85a29db7d23ae083c919df Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 21 Aug 2023 17:19:23 +0300
Subject: [PATCH 1508/1806] vxlan: vnifilter: Use GFP_KERNEL instead of
 GFP_ATOMIC

The function is not called from an atomic context so use GFP_KERNEL
instead of GFP_ATOMIC. The allocation of the per-CPU stats is already
performed with GFP_KERNEL.

Tested using test_vxlan_vnifiltering.sh with CONFIG_DEBUG_ATOMIC_SLEEP.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20230821141923.1889776-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_vnifilter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c
index c3ff30ab782e9..9c59d0bf8c3de 100644
--- a/drivers/net/vxlan/vxlan_vnifilter.c
+++ b/drivers/net/vxlan/vxlan_vnifilter.c
@@ -696,7 +696,7 @@ static struct vxlan_vni_node *vxlan_vni_alloc(struct vxlan_dev *vxlan,
 {
 	struct vxlan_vni_node *vninode;
 
-	vninode = kzalloc(sizeof(*vninode), GFP_ATOMIC);
+	vninode = kzalloc(sizeof(*vninode), GFP_KERNEL);
 	if (!vninode)
 		return NULL;
 	vninode->stats = netdev_alloc_pcpu_stats(struct vxlan_vni_stats_pcpu);
-- 
GitLab


From 504fc6f4f7f681d2a03aa5f68aad549d90eab853 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 21 Aug 2023 17:23:39 +0300
Subject: [PATCH 1509/1806] vrf: Remove unnecessary RCU-bh critical section

dev_queue_xmit_nit() already uses rcu_read_lock() / rcu_read_unlock()
and nothing suggests that softIRQs should be disabled around it.
Therefore, remove the rcu_read_lock_bh() / rcu_read_unlock_bh()
surrounding it.

Tested using [1] with lockdep enabled.

[1]
 #!/bin/bash

 ip link add name vrf1 up type vrf table 100
 ip link add name veth0 type veth peer name veth1
 ip link set dev veth1 master vrf1
 ip link set dev veth0 up
 ip link set dev veth1 up
 ip address add 192.0.2.1/24 dev veth0
 ip address add 192.0.2.2/24 dev veth1
 ip rule add pref 32765 table local
 ip rule del pref 0
 tcpdump -i vrf1 -c 20 -w /dev/null &
 sleep 10
 ping -i 0.1 -c 10 -q 192.0.2.2

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230821142339.1889961-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vrf.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 6043e63b42f97..43f374444684d 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -638,9 +638,7 @@ static void vrf_finish_direct(struct sk_buff *skb)
 		eth_zero_addr(eth->h_dest);
 		eth->h_proto = skb->protocol;
 
-		rcu_read_lock_bh();
 		dev_queue_xmit_nit(skb, vrf_dev);
-		rcu_read_unlock_bh();
 
 		skb_pull(skb, ETH_HLEN);
 	}
-- 
GitLab


From 5d4e04bf3a0f098bd9033de3a5291810fa14c7a6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 15 Aug 2023 18:09:00 +0200
Subject: [PATCH 1510/1806] wifi: cfg80211: reject auth/assoc to AP with our
 address

If the AP uses our own address as its MLD address or BSSID, then
clearly something's wrong. Reject such connections so we don't
try and fail later.

Reported-by: syzbot+2676771ed06a6df166ad@syzkaller.appspotmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/mlme.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index ac059cefbeb39..775cac4d61006 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -281,6 +281,11 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
 	    ether_addr_equal(req->bss->bssid, wdev->u.client.connected_addr))
 		return -EALREADY;
 
+	if (ether_addr_equal(req->bss->bssid, dev->dev_addr) ||
+	    (req->link_id >= 0 &&
+	     ether_addr_equal(req->ap_mld_addr, dev->dev_addr)))
+		return -EINVAL;
+
 	return rdev_auth(rdev, dev, req);
 }
 
@@ -335,6 +340,9 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev,
 			if (req->links[i].bss == req->links[j].bss)
 				return -EINVAL;
 		}
+
+		if (ether_addr_equal(req->links[i].bss->bssid, dev->dev_addr))
+			return -EINVAL;
 	}
 
 	if (wdev->connected &&
@@ -342,6 +350,11 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev,
 	     !ether_addr_equal(wdev->u.client.connected_addr, req->prev_bssid)))
 		return -EALREADY;
 
+	if ((req->bss && ether_addr_equal(req->bss->bssid, dev->dev_addr)) ||
+	    (req->link_id >= 0 &&
+	     ether_addr_equal(req->ap_mld_addr, dev->dev_addr)))
+		return -EINVAL;
+
 	cfg80211_oper_and_ht_capa(&req->ht_capa_mask,
 				  rdev->wiphy.ht_capa_mod_mask);
 	cfg80211_oper_and_vht_capa(&req->vht_capa_mask,
-- 
GitLab


From abc76cf552e13cfa88a204b362a86b0e08e95228 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 15 Aug 2023 18:32:03 +0200
Subject: [PATCH 1511/1806] wifi: cfg80211: ocb: don't leave if not joined

If there's no OCB state, don't ask the driver/mac80211 to
leave, since that's just confusing. Since set/clear the
chandef state, that's a simple check.

Reported-by: syzbot+09d1cd2f71e6dd3bfd2c@syzkaller.appspotmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/ocb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/wireless/ocb.c b/net/wireless/ocb.c
index 27a1732264f95..29afaf3da54f3 100644
--- a/net/wireless/ocb.c
+++ b/net/wireless/ocb.c
@@ -68,6 +68,9 @@ int __cfg80211_leave_ocb(struct cfg80211_registered_device *rdev,
 	if (!rdev->ops->leave_ocb)
 		return -EOPNOTSUPP;
 
+	if (!wdev->u.ocb.chandef.chan)
+		return -ENOTCONN;
+
 	err = rdev_leave_ocb(rdev, dev);
 	if (!err)
 		memset(&wdev->u.ocb.chandef, 0, sizeof(wdev->u.ocb.chandef));
-- 
GitLab


From 67dfa589aa8806c7959cbca2f4613b8d41c75a06 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 15 Aug 2023 18:41:32 +0200
Subject: [PATCH 1512/1806] wifi: mac80211: check for station first in client
 probe

When probing a client, first check if we have it, and then
check for the channel context, otherwise you can trigger
the warning there easily by probing when the AP isn't even
started yet. Since a client existing means the AP is also
operating, we can then keep the warning.

Also simplify the moved code a bit.

Reported-by: syzbot+999fac712d84878a7379@syzkaller.appspotmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index e7ac246038925..953f24166ffcf 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -4133,19 +4133,20 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
 	mutex_lock(&local->mtx);
 
 	rcu_read_lock();
+	sta = sta_info_get_bss(sdata, peer);
+	if (!sta) {
+		ret = -ENOLINK;
+		goto unlock;
+	}
+
+	qos = sta->sta.wme;
+
 	chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf);
 	if (WARN_ON(!chanctx_conf)) {
 		ret = -EINVAL;
 		goto unlock;
 	}
 	band = chanctx_conf->def.chan->band;
-	sta = sta_info_get_bss(sdata, peer);
-	if (sta) {
-		qos = sta->sta.wme;
-	} else {
-		ret = -ENOLINK;
-		goto unlock;
-	}
 
 	if (qos) {
 		fc = cpu_to_le16(IEEE80211_FTYPE_DATA |
-- 
GitLab


From fba360a047d5eeeb9d4b7c3a9b1c8308980ce9a6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 15 Aug 2023 21:28:01 +0200
Subject: [PATCH 1513/1806] wifi: mac80211_hwsim: drop short frames

While technically some control frames like ACK are shorter and
end after Address 1, such frames shouldn't be forwarded through
wmediumd or similar userspace, so require the full 3-address
header to avoid accessing invalid memory if shorter frames are
passed in.

Reported-by: syzbot+b2645b5bf1512b81fa22@syzkaller.appspotmail.com
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virtual/mac80211_hwsim.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index f446fd0e8cd0d..dd516cec41973 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -5626,14 +5626,15 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2,
 	frame_data_len = nla_len(info->attrs[HWSIM_ATTR_FRAME]);
 	frame_data = (void *)nla_data(info->attrs[HWSIM_ATTR_FRAME]);
 
+	if (frame_data_len < sizeof(struct ieee80211_hdr_3addr) ||
+	    frame_data_len > IEEE80211_MAX_DATA_LEN)
+		goto err;
+
 	/* Allocate new skb here */
 	skb = alloc_skb(frame_data_len, GFP_KERNEL);
 	if (skb == NULL)
 		goto err;
 
-	if (frame_data_len > IEEE80211_MAX_DATA_LEN)
-		goto err;
-
 	/* Copy the data */
 	skb_put_data(skb, frame_data, frame_data_len);
 
-- 
GitLab


From 927521170c4a18c620f97865f7bad48f17c48967 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 16 Aug 2023 12:13:36 +0200
Subject: [PATCH 1514/1806] wifi: mac80211: fix puncturing bitmap handling in
 CSA

Code inspection reveals that we switch the puncturing bitmap
before the real channel switch, since that happens only in
the second round of the worker after the channel context is
switched by ieee80211_link_use_reserved_context().

Fixes: 2cc25e4b2a04 ("wifi: mac80211: configure puncturing bitmap")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 953f24166ffcf..45e7a5d9c7d94 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3648,12 +3648,6 @@ static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
 	lockdep_assert_held(&local->mtx);
 	lockdep_assert_held(&local->chanctx_mtx);
 
-	if (sdata->vif.bss_conf.eht_puncturing != sdata->vif.bss_conf.csa_punct_bitmap) {
-		sdata->vif.bss_conf.eht_puncturing =
-					sdata->vif.bss_conf.csa_punct_bitmap;
-		changed |= BSS_CHANGED_EHT_PUNCTURING;
-	}
-
 	/*
 	 * using reservation isn't immediate as it may be deferred until later
 	 * with multi-vif. once reservation is complete it will re-schedule the
@@ -3683,6 +3677,12 @@ static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
 	if (err)
 		return err;
 
+	if (sdata->vif.bss_conf.eht_puncturing != sdata->vif.bss_conf.csa_punct_bitmap) {
+		sdata->vif.bss_conf.eht_puncturing =
+					sdata->vif.bss_conf.csa_punct_bitmap;
+		changed |= BSS_CHANGED_EHT_PUNCTURING;
+	}
+
 	ieee80211_link_info_change_notify(sdata, &sdata->deflink, changed);
 
 	if (sdata->deflink.csa_block_tx) {
-- 
GitLab


From d40de0ad3d1b95da2b263c9361e91b984ab9c16d Mon Sep 17 00:00:00 2001
From: EN-WEI WU <rickywu0421@gmail.com>
Date: Tue, 15 Aug 2023 17:54:27 +0800
Subject: [PATCH 1515/1806] wifi: mac80211_hwsim: avoid calling nlmsg_free() in
 IRQ or IRQ disabled

The nlmsg_free() ends up calling kfree_skb(), and kfree_skb() is not allowed to be called
from hardware interrupt context or with hardware interrupts being disabled. Replace the
mistaken usage of nlmsg_free() by dev_kfree_skb_irq(), which is safe in both cases.

Signed-off-by: EN-WEI WU <enweiwu@FreeBSD.org>
Link: https://lore.kernel.org/r/20230815095427.13589-1-enweiwu@FreeBSD.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virtual/mac80211_hwsim.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index dd516cec41973..ec78fe13dd3eb 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -6315,7 +6315,7 @@ static void hwsim_virtio_tx_done(struct virtqueue *vq)
 
 	spin_lock_irqsave(&hwsim_virtio_lock, flags);
 	while ((skb = virtqueue_get_buf(vq, &len)))
-		nlmsg_free(skb);
+		dev_kfree_skb_irq(skb);
 	spin_unlock_irqrestore(&hwsim_virtio_lock, flags);
 }
 
@@ -6384,14 +6384,14 @@ static void hwsim_virtio_rx_work(struct work_struct *work)
 
 	spin_lock_irqsave(&hwsim_virtio_lock, flags);
 	if (!hwsim_virtio_enabled) {
-		nlmsg_free(skb);
+		dev_kfree_skb_irq(skb);
 		goto out_unlock;
 	}
 	vq = hwsim_vqs[HWSIM_VQ_RX];
 	sg_init_one(sg, skb->head, skb_end_offset(skb));
 	err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_ATOMIC);
 	if (WARN(err, "virtqueue_add_inbuf returned %d\n", err))
-		nlmsg_free(skb);
+		dev_kfree_skb_irq(skb);
 	else
 		virtqueue_kick(vq);
 	schedule_work(&hwsim_virtio_rx);
-- 
GitLab


From 218d690c49b7e9c94ad0d317adbdd4af846ea0dc Mon Sep 17 00:00:00 2001
From: Lin Ma <linma@zju.edu.cn>
Date: Wed, 9 Aug 2023 11:31:51 +0800
Subject: [PATCH 1516/1806] wifi: nl80211/cfg80211: add forgotten nla_policy
 for BSS color attribute

The previous commit dd3e4fc75b4a ("nl80211/cfg80211: add BSS color to
NDP ranging parameters") adds a parameter for NDP ranging by introducing
a new attribute type named NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR.

However, the author forgot to also describe the nla_policy at
nl80211_pmsr_ftm_req_attr_policy (net/wireless/nl80211.c). Just
complement it to avoid malformed attribute that causes out-of-attribute
access.

Fixes: dd3e4fc75b4a ("nl80211/cfg80211: add BSS color to NDP ranging parameters")
Signed-off-by: Lin Ma <linma@zju.edu.cn>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230809033151.768910-1-linma@zju.edu.cn
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0ffebf1a1eb62..de47838aca4f2 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -323,6 +323,7 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = {
 	[NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED] = { .type = NLA_FLAG },
 	[NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED] = { .type = NLA_FLAG },
 	[NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK] = { .type = NLA_FLAG },
+	[NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR] = { .type = NLA_U8 },
 };
 
 static const struct nla_policy
-- 
GitLab


From 7bdfda42f043fce2e590252f264e0832b31a3e92 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 7 Aug 2023 22:50:32 +0800
Subject: [PATCH 1517/1806] wifi: wext: Remove unused declaration
 dev_get_wireless_info()

Commit 556829657397 ("[NL80211]: add netlink interface to cfg80211")
declared but never implemented this, remove it.
Commit 11433ee450eb ("[WEXT]: Move to net/wireless") rename net/core/wireless.c
to net/wireless/wext.c, then commit 3d23e349d807 ("wext: refactor") refactor
wext.c to wext-core.c, fix the wext comment.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230807145032.44768-1-yuehaibing@huawei.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/iw_handler.h | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h
index d2ea5863eedca..b2cf243ebe44e 100644
--- a/include/net/iw_handler.h
+++ b/include/net/iw_handler.h
@@ -426,17 +426,10 @@ struct iw_public_data {
 
 /**************************** PROTOTYPES ****************************/
 /*
- * Functions part of the Wireless Extensions (defined in net/core/wireless.c).
- * Those may be called only within the kernel.
+ * Functions part of the Wireless Extensions (defined in net/wireless/wext-core.c).
+ * Those may be called by driver modules.
  */
 
-/* First : function strictly used inside the kernel */
-
-/* Handle /proc/net/wireless, called in net/code/dev.c */
-int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length);
-
-/* Second : functions that may be called by driver modules */
-
 /* Send a single event to user space */
 void wireless_send_event(struct net_device *dev, unsigned int cmd,
 			 union iwreq_data *wrqu, const char *extra);
-- 
GitLab


From f14cef00456fb7cd6d2ca7389c149b5f079f0091 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 1 Aug 2023 21:43:37 +0800
Subject: [PATCH 1518/1806] wifi: mac80211: Remove unused function declarations

Commit 685429623f88 ("mac80211: Fix circular locking dependency in
ARP filter handling") left the ieee80211_set_arp_filter() declaration
unused.
And commit 164eb02d070a ("mac80211: add radar detection command/event")
introducted ieee80211_dfs_cac_timer() declaration but never implemented
it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230801134337.24452-1-yuehaibing@huawei.com
[reword commit message]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ieee80211_i.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 91633a0b723e0..06bd406846d29 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1872,7 +1872,6 @@ void ieee80211_send_pspoll(struct ieee80211_local *local,
 			   struct ieee80211_sub_if_data *sdata);
 void ieee80211_recalc_ps(struct ieee80211_local *local);
 void ieee80211_recalc_ps_vif(struct ieee80211_sub_if_data *sdata);
-int ieee80211_set_arp_filter(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				  struct sk_buff *skb);
@@ -2564,7 +2563,6 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local,
 				      struct ieee80211_link_data *rsvd_for);
 bool ieee80211_is_radar_required(struct ieee80211_local *local);
 
-void ieee80211_dfs_cac_timer(unsigned long data);
 void ieee80211_dfs_cac_timer_work(struct work_struct *work);
 void ieee80211_dfs_cac_cancel(struct ieee80211_local *local);
 void ieee80211_dfs_radar_detected_work(struct work_struct *work);
-- 
GitLab


From a3d9c4f7c43dd9b0accc26573b54e4a0bce1f4a6 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 31 Jul 2023 22:07:12 +0800
Subject: [PATCH 1519/1806] wifi: mac80211: mesh: Remove unused function
 declaration mesh_ids_set_default()

Commit ccf80ddfe492 ("mac80211: mesh function and data structures
definitions") introducted this but never implemented it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230731140712.1204-1-yuehaibing@huawei.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mesh.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index 6c94222a9df59..ad8469293d712 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -212,7 +212,6 @@ int mesh_rmc_check(struct ieee80211_sub_if_data *sdata,
 		   const u8 *addr, struct ieee80211s_hdr *mesh_hdr);
 bool mesh_matches_local(struct ieee80211_sub_if_data *sdata,
 			struct ieee802_11_elems *ie);
-void mesh_ids_set_default(struct ieee80211_if_mesh *mesh);
 int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata,
 			 struct sk_buff *skb);
 int mesh_add_meshid_ie(struct ieee80211_sub_if_data *sdata,
-- 
GitLab


From 9265f78b69a70a03b57f41d8da3c194d0c8aad22 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 29 Jul 2023 20:16:51 +0800
Subject: [PATCH 1520/1806] wifi: nl80211: Remove unused declaration
 nl80211_pmsr_dump_results()

nl80211_pmsr_dump_results() is never implemented since it was added in
commit 9bb7e0f24e7e ("cfg80211: add peer measurement with FTM initiator
API").

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230729121651.36836-1-yuehaibing@huawei.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index 0278d817bb023..b4af53f9b2273 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -120,6 +120,5 @@ void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev);
 
 /* peer measurement */
 int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info);
-int nl80211_pmsr_dump_results(struct sk_buff *skb, struct netlink_callback *cb);
 
 #endif /* __NET_WIRELESS_NL80211_H */
-- 
GitLab


From 1dcf396b4223143fcd3ef6d5e2acdbb6f7bea2e5 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 13 Jul 2023 16:29:36 +0300
Subject: [PATCH 1521/1806] wifi: cfg80211: improve documentation for flag
 fields

Fix and hopefully improve documentation for 'flag' fields of
a few types by adding references to relevant enumerations.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://lore.kernel.org/r/20230713132957.275859-1-dmantipov@yandex.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 423fe9b85cb06..070ac0c62bd43 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -263,7 +263,7 @@ enum ieee80211_privacy {
  * are only for driver use when pointers to this structure are
  * passed around.
  *
- * @flags: rate-specific flags
+ * @flags: rate-specific flags from &enum ieee80211_rate_flags
  * @bitrate: bitrate in units of 100 Kbps
  * @hw_value: driver/hardware value for this rate
  * @hw_value_short: driver/hardware value for this rate when
@@ -1353,7 +1353,7 @@ struct cfg80211_unsol_bcast_probe_resp {
  * @twt_responder: Enable Target Wait Time
  * @he_required: stations must support HE
  * @sae_h2e_required: stations must support direct H2E technique in SAE
- * @flags: flags, as defined in enum cfg80211_ap_settings_flags
+ * @flags: flags, as defined in &enum nl80211_ap_settings_flags
  * @he_obss_pd: OBSS Packet Detection settings
  * @he_oper: HE operation IE (or %NULL if HE isn't enabled)
  * @fils_discovery: FILS discovery transmission parameters
@@ -2156,7 +2156,7 @@ enum mpath_info_flags {
  * @sn: target sequence number
  * @metric: metric (cost) of this mesh path
  * @exptime: expiration time for the mesh path from now, in msecs
- * @flags: mesh path flags
+ * @flags: mesh path flags from &enum mesh_path_flags
  * @discovery_timeout: total mesh path discovery timeout, in msecs
  * @discovery_retries: mesh path discovery retries
  * @generation: generation number for nl80211 dumps.
@@ -2496,7 +2496,7 @@ struct cfg80211_scan_6ghz_params {
  *	the actual dwell time may be shorter.
  * @duration_mandatory: if set, the scan duration must be as specified by the
  *	%duration field.
- * @flags: bit field of flags controlling operation
+ * @flags: control flags from &enum nl80211_scan_flags
  * @rates: bitmap of rates to advertise for each band
  * @wiphy: the wiphy this was for
  * @scan_start: time (in jiffies) when the scan started
@@ -2616,7 +2616,7 @@ struct cfg80211_bss_select_adjust {
  * @scan_width: channel width for scanning
  * @ie: optional information element(s) to add into Probe Request or %NULL
  * @ie_len: length of ie in octets
- * @flags: bit field of flags controlling operation
+ * @flags: control flags from &enum nl80211_scan_flags
  * @match_sets: sets of parameters to be matched for a scan result
  *	entry to be considered valid and to be passed to the host
  *	(others are filtered out).
@@ -8118,7 +8118,7 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr,
  * @link_id: the ID of the link the frame was received	on
  * @buf: Management frame (header + body)
  * @len: length of the frame data
- * @flags: flags, as defined in enum nl80211_rxmgmt_flags
+ * @flags: flags, as defined in &enum nl80211_rxmgmt_flags
  * @rx_tstamp: Hardware timestamp of frame RX in nanoseconds
  * @ack_tstamp: Hardware timestamp of ack TX in nanoseconds
  */
-- 
GitLab


From a49a0d4e573e22f47218668ee4137cdcdc391652 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 10 Jul 2023 16:03:02 -0700
Subject: [PATCH 1522/1806] wifi: cfg80211: remove dead/unused enum value

Drop an unused (extra) enum value to prevent a kernel-doc warning.

cfg80211.h:1492: warning: Excess enum value 'STATION_PARAM_APPLY_STA_TXPOWER' description in 'station_parameters_apply_mask'

Fixes: 2d8b08fef0af ("wifi: cfg80211: fix kernel-doc warnings all over the file")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: linux-wireless@vger.kernel.org
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Link: https://lore.kernel.org/r/20230710230312.31197-3-rdunlap@infradead.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 070ac0c62bd43..3a4b684f89bf7 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1482,7 +1482,6 @@ struct iface_combination_params {
  * @STATION_PARAM_APPLY_UAPSD: apply new uAPSD parameters (uapsd_queues, max_sp)
  * @STATION_PARAM_APPLY_CAPABILITY: apply new capability
  * @STATION_PARAM_APPLY_PLINK_STATE: apply new plink state
- * @STATION_PARAM_APPLY_STA_TXPOWER: apply tx power for STA
  *
  * Not all station parameters have in-band "no change" signalling,
  * for those that don't these flags will are used.
-- 
GitLab


From 266a5cd768da7e243cd26bc6840ce48cad1c907e Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 10 Jul 2023 16:03:06 -0700
Subject: [PATCH 1523/1806] wifi: radiotap: fix kernel-doc notation warnings

Fix a typo (82011 -> 80211) to prevent a kernel-doc warning.
Add one missing function parameter description to prevent a
kernel-doc warning.

ieee80211_radiotap.h:52: warning: expecting prototype for struct ieee82011_radiotap_header. Prototype was for struct ieee80211_radiotap_header instead
ieee80211_radiotap.h:581: warning: Function parameter or member 'data' not described in 'ieee80211_get_radiotap_len'

Fixes: 42f82e2e62ae ("wireless: radiotap: rewrite the radiotap header file")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: linux-wireless@vger.kernel.org
Link: https://lore.kernel.org/r/20230710230312.31197-7-rdunlap@infradead.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/ieee80211_radiotap.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index c4722a9963de8..2338f8d2a8b33 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -21,7 +21,7 @@
 #include <asm/unaligned.h>
 
 /**
- * struct ieee82011_radiotap_header - base radiotap header
+ * struct ieee80211_radiotap_header - base radiotap header
  */
 struct ieee80211_radiotap_header {
 	/**
@@ -575,6 +575,7 @@ enum ieee80211_radiotap_eht_usig_tb {
 
 /**
  * ieee80211_get_radiotap_len - get radiotap header length
+ * @data: pointer to the header
  */
 static inline u16 ieee80211_get_radiotap_len(const char *data)
 {
-- 
GitLab


From c6662a4b3ecf03aa832125e9705a185402cd3b17 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 10 Jul 2023 16:03:09 -0700
Subject: [PATCH 1524/1806] wifi: mac80211: fix kernel-doc notation warning

Add description for struct member 'agg' to prevent a kernel-doc
warning.

mac80211.h:2289: warning: Function parameter or member 'agg' not described in 'ieee80211_link_sta'

Fixes: 4c51541ddb78 ("wifi: mac80211: keep A-MSDU data in sta and per-link")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Benjamin Berg <benjamin.berg@intel.com>
Cc: linux-wireless@vger.kernel.org
Link: https://lore.kernel.org/r/20230710230312.31197-10-rdunlap@infradead.org
[reword the kernel-doc comment]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 3a8a2d2c58c38..d7fa0a55067e2 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2259,6 +2259,7 @@ struct ieee80211_sta_aggregates {
  * @he_cap: HE capabilities of this STA
  * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities
  * @eht_cap: EHT capabilities of this STA
+ * @agg: per-link data for multi-link aggregation
  * @bandwidth: current bandwidth the station can receive with
  * @rx_nss: in HT/VHT, the maximum number of spatial streams the
  *	station can receive at the moment, changed by operating mode
-- 
GitLab


From a7a2ef0c4b3efbd7d6f3fabd87dbbc0b3f2de5af Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 23 Jun 2023 17:24:00 +0200
Subject: [PATCH 1525/1806] mac80211: make ieee80211_tx_info padding explicit

While looking at a bug, I got rather confused by the layout of the
'status' field in ieee80211_tx_info. Apparently, the intention is that
status_driver_data[] is used for driver specific data, and fills up the
size of the union to 40 bytes, just like the other ones.

This is indeed what actually happens, but only because of the
combination of two mistakes:

 - "void *status_driver_data[18 / sizeof(void *)];" is intended
   to be 18 bytes long but is actually two bytes shorter because of
   rounding-down in the division, to a multiple of the pointer
   size (4 bytes or 8 bytes).

 - The other fields combined are intended to be 22 bytes long, but
   are actually 24 bytes because of padding in front of the
   unaligned tx_time member, and in front of the pointer array.

The two mistakes cancel out. so the size ends up fine, but it seems
more helpful to make this explicit, by having a multiple of 8 bytes
in the size calculation and explicitly describing the padding.

Fixes: ea5907db2a9cc ("mac80211: fix struct ieee80211_tx_info size")
Fixes: 02219b3abca59 ("mac80211: add WMM admission control support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20230623152443.2296825-2-arnd@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d7fa0a55067e2..f1420e5af5de1 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1192,9 +1192,11 @@ struct ieee80211_tx_info {
 			u8 ampdu_ack_len;
 			u8 ampdu_len;
 			u8 antenna;
+			u8 pad;
 			u16 tx_time;
 			u8 flags;
-			void *status_driver_data[18 / sizeof(void *)];
+			u8 pad2;
+			void *status_driver_data[16 / sizeof(void *)];
 		} status;
 		struct {
 			struct ieee80211_tx_rate driver_rates[
-- 
GitLab


From 1b78dd34560e9962f8e917fe4adde6f2ab0eb89f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 22 Aug 2023 14:17:21 +0200
Subject: [PATCH 1526/1806] Revert "wifi: mac80211_hwsim: check the return
 value of nla_put_u32"

This reverts commit b970ac68e0c4 ("wifi: mac80211_hwsim: check the
return value of nla_put_u32") since it introduced a memory leak in
the error path, which seems worse than sending an incomplete skb,
and the put can't fail anyway since the SKB was just allocated.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virtual/mac80211_hwsim.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index ec78fe13dd3eb..1f524030b186e 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -582,9 +582,8 @@ static int mac80211_hwsim_vendor_cmd_test(struct wiphy *wiphy,
 		 */
 
 		/* Add vendor data */
-		err = nla_put_u32(skb, QCA_WLAN_VENDOR_ATTR_TEST, val + 1);
-		if (err)
-			return err;
+		nla_put_u32(skb, QCA_WLAN_VENDOR_ATTR_TEST, val + 1);
+
 		/* Send the event - this will call nla_nest_end() */
 		cfg80211_vendor_event(skb, GFP_KERNEL);
 	}
-- 
GitLab


From 9e261e6da0a814f4ee1856ab06b19c25190aeffb Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Tue, 22 Aug 2023 09:30:17 -0700
Subject: [PATCH 1527/1806] wifi: Fix ieee80211.h kernel-doc issues

The kernel-doc script identified multiple issues in ieee80211.h, so
fix them. In the process update some references to the latest
applicable specification.

include/linux/ieee80211.h:848: warning: Function parameter or member 'count' not described in 'ieee80211_quiet_ie'
include/linux/ieee80211.h:848: warning: Function parameter or member 'period' not described in 'ieee80211_quiet_ie'
include/linux/ieee80211.h:848: warning: Function parameter or member 'duration' not described in 'ieee80211_quiet_ie'
include/linux/ieee80211.h:848: warning: Function parameter or member 'offset' not described in 'ieee80211_quiet_ie'
include/linux/ieee80211.h:860: warning: Function parameter or member 'token' not described in 'ieee80211_msrment_ie'
include/linux/ieee80211.h:860: warning: Function parameter or member 'mode' not described in 'ieee80211_msrment_ie'
include/linux/ieee80211.h:860: warning: Function parameter or member 'type' not described in 'ieee80211_msrment_ie'
include/linux/ieee80211.h:860: warning: Function parameter or member 'request' not described in 'ieee80211_msrment_ie'
include/linux/ieee80211.h:871: warning: Function parameter or member 'mode' not described in 'ieee80211_channel_sw_ie'
include/linux/ieee80211.h:871: warning: Function parameter or member 'new_ch_num' not described in 'ieee80211_channel_sw_ie'
include/linux/ieee80211.h:871: warning: Function parameter or member 'count' not described in 'ieee80211_channel_sw_ie'
include/linux/ieee80211.h:883: warning: Function parameter or member 'mode' not described in 'ieee80211_ext_chansw_ie'
include/linux/ieee80211.h:883: warning: Function parameter or member 'new_operating_class' not described in 'ieee80211_ext_chansw_ie'
include/linux/ieee80211.h:883: warning: Function parameter or member 'new_ch_num' not described in 'ieee80211_ext_chansw_ie'
include/linux/ieee80211.h:883: warning: Function parameter or member 'count' not described in 'ieee80211_ext_chansw_ie'
include/linux/ieee80211.h:905: warning: Function parameter or member 'mesh_ttl' not described in 'ieee80211_mesh_chansw_params_ie'
include/linux/ieee80211.h:905: warning: Function parameter or member 'mesh_flags' not described in 'ieee80211_mesh_chansw_params_ie'
include/linux/ieee80211.h:905: warning: Function parameter or member 'mesh_reason' not described in 'ieee80211_mesh_chansw_params_ie'
include/linux/ieee80211.h:905: warning: Function parameter or member 'mesh_pre_value' not described in 'ieee80211_mesh_chansw_params_ie'
include/linux/ieee80211.h:913: warning: Function parameter or member 'new_channel_width' not described in 'ieee80211_wide_bw_chansw_ie'
include/linux/ieee80211.h:913: warning: Function parameter or member 'new_center_freq_seg0' not described in 'ieee80211_wide_bw_chansw_ie'
include/linux/ieee80211.h:913: warning: Function parameter or member 'new_center_freq_seg1' not described in 'ieee80211_wide_bw_chansw_ie'
include/linux/ieee80211.h:926: warning: expecting prototype for struct ieee80211_tim. Prototype was for struct ieee80211_tim_ie instead
include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_psel' not described in 'ieee80211_meshconf_ie'
include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_pmetric' not described in 'ieee80211_meshconf_ie'
include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_congest' not described in 'ieee80211_meshconf_ie'
include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_synch' not described in 'ieee80211_meshconf_ie'
include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_auth' not described in 'ieee80211_meshconf_ie'
include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_form' not described in 'ieee80211_meshconf_ie'
include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_cap' not described in 'ieee80211_meshconf_ie'
include/linux/ieee80211.h:964: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * mesh channel switch parameters element's flag indicator
include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_flags' not described in 'ieee80211_rann_ie'
include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_hopcount' not described in 'ieee80211_rann_ie'
include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_ttl' not described in 'ieee80211_rann_ie'
include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_addr' not described in 'ieee80211_rann_ie'
include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_seq' not described in 'ieee80211_rann_ie'
include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_interval' not described in 'ieee80211_rann_ie'
include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_metric' not described in 'ieee80211_rann_ie'
include/linux/ieee80211.h:1019: warning: expecting prototype for enum ieee80211_opmode_bits. Prototype was for enum ieee80211_vht_opmode_bits instead
include/linux/ieee80211.h:1052: warning: Function parameter or member 'tx_power' not described in 'ieee80211_tpc_report_ie'
include/linux/ieee80211.h:1052: warning: Function parameter or member 'link_margin' not described in 'ieee80211_tpc_report_ie'
include/linux/ieee80211.h:1073: warning: Function parameter or member 'compat_info' not described in 'ieee80211_s1g_bcn_compat_ie'
include/linux/ieee80211.h:1073: warning: Function parameter or member 'beacon_int' not described in 'ieee80211_s1g_bcn_compat_ie'
include/linux/ieee80211.h:1073: warning: Function parameter or member 'tsf_completion' not described in 'ieee80211_s1g_bcn_compat_ie'
include/linux/ieee80211.h:1086: warning: Function parameter or member 'ch_width' not described in 'ieee80211_s1g_oper_ie'
include/linux/ieee80211.h:1086: warning: Function parameter or member 'oper_class' not described in 'ieee80211_s1g_oper_ie'
include/linux/ieee80211.h:1086: warning: Function parameter or member 'primary_ch' not described in 'ieee80211_s1g_oper_ie'
include/linux/ieee80211.h:1086: warning: Function parameter or member 'oper_ch' not described in 'ieee80211_s1g_oper_ie'
include/linux/ieee80211.h:1086: warning: Function parameter or member 'basic_mcs_nss' not described in 'ieee80211_s1g_oper_ie'
include/linux/ieee80211.h:1097: warning: Function parameter or member 'aid' not described in 'ieee80211_aid_response_ie'
include/linux/ieee80211.h:1097: warning: Function parameter or member 'switch_count' not described in 'ieee80211_aid_response_ie'
include/linux/ieee80211.h:1097: warning: Function parameter or member 'response_int' not described in 'ieee80211_aid_response_ie'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_STATUS' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_MINOR_REASON' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_CAPABILITY' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_DEVICE_ID' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_GO_INTENT' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_GO_CONFIG_TIMEOUT' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_LISTEN_CHANNEL' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_GROUP_BSSID' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_EXT_LISTEN_TIMING' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_INTENDED_IFACE_ADDR' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_MANAGABILITY' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_CHANNEL_LIST' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_ABSENCE_NOTICE' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_DEVICE_INFO' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_GROUP_INFO' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_GROUP_ID' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_INTERFACE' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_OPER_CHANNEL' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_INVITE_FLAGS' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_VENDOR_SPECIFIC' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_MAX' not described in enum 'ieee80211_p2p_attr_id'
include/linux/ieee80211.h:1554: warning: Function parameter or member 'frame_control' not described in 'ieee80211_bar'
include/linux/ieee80211.h:1554: warning: Function parameter or member 'duration' not described in 'ieee80211_bar'
include/linux/ieee80211.h:1554: warning: Function parameter or member 'ra' not described in 'ieee80211_bar'
include/linux/ieee80211.h:1554: warning: Function parameter or member 'ta' not described in 'ieee80211_bar'
include/linux/ieee80211.h:1554: warning: Function parameter or member 'control' not described in 'ieee80211_bar'
include/linux/ieee80211.h:1554: warning: Function parameter or member 'start_seq_num' not described in 'ieee80211_bar'
include/linux/ieee80211.h:1579: warning: Function parameter or member 'reserved' not described in 'ieee80211_mcs_info'
include/linux/ieee80211.h:1618: warning: Function parameter or member 'cap_info' not described in 'ieee80211_ht_cap'
include/linux/ieee80211.h:1618: warning: Function parameter or member 'ampdu_params_info' not described in 'ieee80211_ht_cap'
include/linux/ieee80211.h:1618: warning: Function parameter or member 'mcs' not described in 'ieee80211_ht_cap'
include/linux/ieee80211.h:1618: warning: Function parameter or member 'extended_ht_cap_info' not described in 'ieee80211_ht_cap'
include/linux/ieee80211.h:1618: warning: Function parameter or member 'tx_BF_cap_info' not described in 'ieee80211_ht_cap'
include/linux/ieee80211.h:1618: warning: Function parameter or member 'antenna_selection_info' not described in 'ieee80211_ht_cap'
include/linux/ieee80211.h:1704: warning: Function parameter or member 'primary_chan' not described in 'ieee80211_ht_operation'
include/linux/ieee80211.h:1704: warning: Function parameter or member 'ht_param' not described in 'ieee80211_ht_operation'
include/linux/ieee80211.h:1704: warning: Function parameter or member 'operation_mode' not described in 'ieee80211_ht_operation'
include/linux/ieee80211.h:1704: warning: Function parameter or member 'stbc_param' not described in 'ieee80211_ht_operation'
include/linux/ieee80211.h:1704: warning: Function parameter or member 'basic_set' not described in 'ieee80211_ht_operation'
include/linux/ieee80211.h:1872: warning: Function parameter or member 'mac_cap_info' not described in 'ieee80211_he_cap_elem'
include/linux/ieee80211.h:1872: warning: Function parameter or member 'phy_cap_info' not described in 'ieee80211_he_cap_elem'
include/linux/ieee80211.h:1936: warning: Function parameter or member 'he_oper_params' not described in 'ieee80211_he_operation'
include/linux/ieee80211.h:1936: warning: Function parameter or member 'he_mcs_nss_set' not described in 'ieee80211_he_operation'
include/linux/ieee80211.h:1936: warning: Function parameter or member 'optional' not described in 'ieee80211_he_operation'
include/linux/ieee80211.h:1948: warning: Function parameter or member 'he_sr_control' not described in 'ieee80211_he_spr'
include/linux/ieee80211.h:1948: warning: Function parameter or member 'optional' not described in 'ieee80211_he_spr'
include/linux/ieee80211.h:1960: warning: Function parameter or member 'aifsn' not described in 'ieee80211_he_mu_edca_param_ac_rec'
include/linux/ieee80211.h:1960: warning: Function parameter or member 'ecw_min_max' not described in 'ieee80211_he_mu_edca_param_ac_rec'
include/linux/ieee80211.h:1960: warning: Function parameter or member 'mu_edca_timer' not described in 'ieee80211_he_mu_edca_param_ac_rec'
include/linux/ieee80211.h:1974: warning: Function parameter or member 'mu_qos_info' not described in 'ieee80211_mu_edca_param_set'
include/linux/ieee80211.h:1974: warning: Function parameter or member 'ac_be' not described in 'ieee80211_mu_edca_param_set'
include/linux/ieee80211.h:1974: warning: Function parameter or member 'ac_bk' not described in 'ieee80211_mu_edca_param_set'
include/linux/ieee80211.h:1974: warning: Function parameter or member 'ac_vi' not described in 'ieee80211_mu_edca_param_set'
include/linux/ieee80211.h:1974: warning: Function parameter or member 'ac_vo' not described in 'ieee80211_mu_edca_param_set'
include/linux/ieee80211.h:2194: warning: Enum value 'IEEE80211_REG_LPI_AP' not described in enum 'ieee80211_ap_reg_power'
include/linux/ieee80211.h:2194: warning: Enum value 'IEEE80211_REG_SP_AP' not described in enum 'ieee80211_ap_reg_power'
include/linux/ieee80211.h:2194: warning: Enum value 'IEEE80211_REG_VLP_AP' not described in enum 'ieee80211_ap_reg_power'
include/linux/ieee80211.h:2194: warning: Excess enum value 'IEEE80211_REG_SP' description in 'ieee80211_ap_reg_power'
include/linux/ieee80211.h:2194: warning: Excess enum value 'IEEE80211_REG_VLP' description in 'ieee80211_ap_reg_power'
include/linux/ieee80211.h:2194: warning: Excess enum value 'IEEE80211_REG_LPI' description in 'ieee80211_ap_reg_power'
include/linux/ieee80211.h:2577: warning: cannot understand function prototype: 'struct ieee80211_he_6ghz_oper '
include/linux/ieee80211.h:2624: warning: Function parameter or member 'tx_power_info' not described in 'ieee80211_tx_pwr_env'
include/linux/ieee80211.h:2624: warning: Function parameter or member 'tx_power' not described in 'ieee80211_tx_pwr_env'
include/linux/ieee80211.h:4485: warning: expecting prototype for RSNX Capabilities(). Prototype was for WLAN_RSNX_CAPA_PROTECTED_TWT() instead
include/linux/ieee80211.h:4734: warning: expecting prototype for ieee80211_mle_get_eml_sync_delay(). Prototype was for ieee80211_mle_get_eml_med_sync_delay() instead
117 warnings as Errors

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20230822-kerneldoc-v1-1-0d42ce5029bf@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 235 ++++++++++++++++++++++++++++----------
 1 file changed, 177 insertions(+), 58 deletions(-)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 4b998090898e3..bd2f6e19c357a 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -836,9 +836,14 @@ enum ieee80211_preq_target_flags {
 };
 
 /**
- * struct ieee80211_quiet_ie
+ * struct ieee80211_quiet_ie - Quiet element
+ * @count: Quiet Count
+ * @period: Quiet Period
+ * @duration: Quiet Duration
+ * @offset: Quiet Offset
  *
- * This structure refers to "Quiet information element"
+ * This structure represents the payload of the "Quiet element" as
+ * described in IEEE Std 802.11-2020 section 9.4.2.22.
  */
 struct ieee80211_quiet_ie {
 	u8 count;
@@ -848,9 +853,15 @@ struct ieee80211_quiet_ie {
 } __packed;
 
 /**
- * struct ieee80211_msrment_ie
+ * struct ieee80211_msrment_ie - Measurement element
+ * @token: Measurement Token
+ * @mode: Measurement Report Mode
+ * @type: Measurement Type
+ * @request: Measurement Request or Measurement Report
  *
- * This structure refers to "Measurement Request/Report information element"
+ * This structure represents the payload of both the "Measurement
+ * Request element" and the "Measurement Report element" as described
+ * in IEEE Std 802.11-2020 sections 9.4.2.20 and 9.4.2.21.
  */
 struct ieee80211_msrment_ie {
 	u8 token;
@@ -860,9 +871,14 @@ struct ieee80211_msrment_ie {
 } __packed;
 
 /**
- * struct ieee80211_channel_sw_ie
+ * struct ieee80211_channel_sw_ie - Channel Switch Announcement element
+ * @mode: Channel Switch Mode
+ * @new_ch_num: New Channel Number
+ * @count: Channel Switch Count
  *
- * This structure refers to "Channel Switch Announcement information element"
+ * This structure represents the payload of the "Channel Switch
+ * Announcement element" as described in IEEE Std 802.11-2020 section
+ * 9.4.2.18.
  */
 struct ieee80211_channel_sw_ie {
 	u8 mode;
@@ -871,9 +887,14 @@ struct ieee80211_channel_sw_ie {
 } __packed;
 
 /**
- * struct ieee80211_ext_chansw_ie
+ * struct ieee80211_ext_chansw_ie - Extended Channel Switch Announcement element
+ * @mode: Channel Switch Mode
+ * @new_operating_class: New Operating Class
+ * @new_ch_num: New Channel Number
+ * @count: Channel Switch Count
  *
- * This structure represents the "Extended Channel Switch Announcement element"
+ * This structure represents the "Extended Channel Switch Announcement
+ * element" as described in IEEE Std 802.11-2020 section 9.4.2.52.
  */
 struct ieee80211_ext_chansw_ie {
 	u8 mode;
@@ -894,8 +915,14 @@ struct ieee80211_sec_chan_offs_ie {
 
 /**
  * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE
+ * @mesh_ttl: Time To Live
+ * @mesh_flags: Flags
+ * @mesh_reason: Reason Code
+ * @mesh_pre_value: Precedence Value
  *
- * This structure represents the "Mesh Channel Switch Paramters element"
+ * This structure represents the payload of the "Mesh Channel Switch
+ * Parameters element" as described in IEEE Std 802.11-2020 section
+ * 9.4.2.102.
  */
 struct ieee80211_mesh_chansw_params_ie {
 	u8 mesh_ttl;
@@ -906,6 +933,13 @@ struct ieee80211_mesh_chansw_params_ie {
 
 /**
  * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE
+ * @new_channel_width: New Channel Width
+ * @new_center_freq_seg0: New Channel Center Frequency Segment 0
+ * @new_center_freq_seg1: New Channel Center Frequency Segment 1
+ *
+ * This structure represents the payload of the "Wide Bandwidth
+ * Channel Switch element" as described in IEEE Std 802.11-2020
+ * section 9.4.2.160.
  */
 struct ieee80211_wide_bw_chansw_ie {
 	u8 new_channel_width;
@@ -913,9 +947,14 @@ struct ieee80211_wide_bw_chansw_ie {
 } __packed;
 
 /**
- * struct ieee80211_tim
+ * struct ieee80211_tim_ie - Traffic Indication Map information element
+ * @dtim_count: DTIM Count
+ * @dtim_period: DTIM Period
+ * @bitmap_ctrl: Bitmap Control
+ * @virtual_map: Partial Virtual Bitmap
  *
- * This structure refers to "Traffic Indication Map information element"
+ * This structure represents the payload of the "TIM element" as
+ * described in IEEE Std 802.11-2020 section 9.4.2.5.
  */
 struct ieee80211_tim_ie {
 	u8 dtim_count;
@@ -926,9 +965,17 @@ struct ieee80211_tim_ie {
 } __packed;
 
 /**
- * struct ieee80211_meshconf_ie
+ * struct ieee80211_meshconf_ie - Mesh Configuration element
+ * @meshconf_psel: Active Path Selection Protocol Identifier
+ * @meshconf_pmetric: Active Path Selection Metric Identifier
+ * @meshconf_congest: Congestion Control Mode Identifier
+ * @meshconf_synch: Synchronization Method Identifier
+ * @meshconf_auth: Authentication Protocol Identifier
+ * @meshconf_form: Mesh Formation Info
+ * @meshconf_cap: Mesh Capability (see &enum mesh_config_capab_flags)
  *
- * This structure refers to "Mesh Configuration information element"
+ * This structure represents the payload of the "Mesh Configuration
+ * element" as described in IEEE Std 802.11-2020 section 9.4.2.97.
  */
 struct ieee80211_meshconf_ie {
 	u8 meshconf_psel;
@@ -950,6 +997,9 @@ struct ieee80211_meshconf_ie {
  *	is ongoing
  * @IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL: STA is in deep sleep mode or has
  *	neighbors in deep sleep mode
+ *
+ * Enumerates the "Mesh Capability" as described in IEEE Std
+ * 802.11-2020 section 9.4.2.97.7.
  */
 enum mesh_config_capab_flags {
 	IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS		= 0x01,
@@ -960,7 +1010,7 @@ enum mesh_config_capab_flags {
 
 #define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1
 
-/**
+/*
  * mesh channel switch parameters element's flag indicator
  *
  */
@@ -969,9 +1019,17 @@ enum mesh_config_capab_flags {
 #define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2)
 
 /**
- * struct ieee80211_rann_ie
+ * struct ieee80211_rann_ie - RANN (root announcement) element
+ * @rann_flags: Flags
+ * @rann_hopcount: Hop Count
+ * @rann_ttl: Element TTL
+ * @rann_addr: Root Mesh STA Address
+ * @rann_seq: HWMP Sequence Number
+ * @rann_interval: Interval
+ * @rann_metric: Metric
  *
- * This structure refers to "Root Announcement information element"
+ * This structure represents the payload of the "RANN element" as
+ * described in IEEE Std 802.11-2020 section 9.4.2.111.
  */
 struct ieee80211_rann_ie {
 	u8 rann_flags;
@@ -993,7 +1051,7 @@ enum ieee80211_ht_chanwidth_values {
 };
 
 /**
- * enum ieee80211_opmode_bits - VHT operating mode field bits
+ * enum ieee80211_vht_opmode_bits - VHT operating mode field bits
  * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask
  * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: 20 MHz channel width
  * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width
@@ -1042,9 +1100,12 @@ enum ieee80211_s1g_chanwidth {
 #define WLAN_USER_POSITION_LEN 16
 
 /**
- * struct ieee80211_tpc_report_ie
+ * struct ieee80211_tpc_report_ie - TPC Report element
+ * @tx_power: Transmit Power
+ * @link_margin: Link Margin
  *
- * This structure refers to "TPC Report element"
+ * This structure represents the payload of the "TPC Report element" as
+ * described in IEEE Std 802.11-2020 section 9.4.2.16.
  */
 struct ieee80211_tpc_report_ie {
 	u8 tx_power;
@@ -1062,9 +1123,14 @@ struct ieee80211_addba_ext_ie {
 } __packed;
 
 /**
- * struct ieee80211_s1g_bcn_compat_ie
+ * struct ieee80211_s1g_bcn_compat_ie - S1G Beacon Compatibility element
+ * @compat_info: Compatibility Information
+ * @beacon_int: Beacon Interval
+ * @tsf_completion: TSF Completion
  *
- * S1G Beacon Compatibility element
+ * This structure represents the payload of the "S1G Beacon
+ * Compatibility element" as described in IEEE Std 802.11-2020 section
+ * 9.4.2.196.
  */
 struct ieee80211_s1g_bcn_compat_ie {
 	__le16 compat_info;
@@ -1073,9 +1139,15 @@ struct ieee80211_s1g_bcn_compat_ie {
 } __packed;
 
 /**
- * struct ieee80211_s1g_oper_ie
+ * struct ieee80211_s1g_oper_ie - S1G Operation element
+ * @ch_width: S1G Operation Information Channel Width
+ * @oper_class: S1G Operation Information Operating Class
+ * @primary_ch: S1G Operation Information Primary Channel Number
+ * @oper_ch: S1G Operation Information  Channel Center Frequency
+ * @basic_mcs_nss: Basic S1G-MCS and NSS Set
  *
- * S1G Operation element
+ * This structure represents the payload of the "S1G Operation
+ * element" as described in IEEE Std 802.11-2020 section 9.4.2.212.
  */
 struct ieee80211_s1g_oper_ie {
 	u8 ch_width;
@@ -1086,9 +1158,13 @@ struct ieee80211_s1g_oper_ie {
 } __packed;
 
 /**
- * struct ieee80211_aid_response_ie
+ * struct ieee80211_aid_response_ie - AID Response element
+ * @aid: AID/Group AID
+ * @switch_count: AID Switch Count
+ * @response_int: AID Response Interval
  *
- * AID Response element
+ * This structure represents the payload of the "AID Response element"
+ * as described in IEEE Std 802.11-2020 section 9.4.2.194.
  */
 struct ieee80211_aid_response_ie {
 	__le16 aid;
@@ -1489,7 +1565,7 @@ struct ieee80211_tdls_data {
 /*
  * Peer-to-Peer IE attribute related definitions.
  */
-/**
+/*
  * enum ieee80211_p2p_attr_id - identifies type of peer-to-peer attribute.
  */
 enum ieee80211_p2p_attr_id {
@@ -1539,11 +1615,17 @@ struct ieee80211_p2p_noa_attr {
 #define IEEE80211_P2P_OPPPS_CTWINDOW_MASK	0x7F
 
 /**
- * struct ieee80211_bar - HT Block Ack Request
+ * struct ieee80211_bar - Block Ack Request frame format
+ * @frame_control: Frame Control
+ * @duration: Duration
+ * @ra: RA
+ * @ta: TA
+ * @control: BAR Control
+ * @start_seq_num: Starting Sequence Number (see Figure 9-37)
  *
- * This structure refers to "HT BlockAckReq" as
- * described in 802.11n draft section 7.2.1.7.1
- */
+ * This structure represents the "BlockAckReq frame format"
+ * as described in IEEE Std 802.11-2020 section 9.3.1.7.
+*/
 struct ieee80211_bar {
 	__le16 frame_control;
 	__le16 duration;
@@ -1563,13 +1645,17 @@ struct ieee80211_bar {
 #define IEEE80211_HT_MCS_MASK_LEN		10
 
 /**
- * struct ieee80211_mcs_info - MCS information
+ * struct ieee80211_mcs_info - Supported MCS Set field
  * @rx_mask: RX mask
  * @rx_highest: highest supported RX rate. If set represents
  *	the highest supported RX data rate in units of 1 Mbps.
  *	If this field is 0 this value should not be used to
  *	consider the highest RX data rate supported.
  * @tx_params: TX parameters
+ * @reserved: Reserved bits
+ *
+ * This structure represents the "Supported MCS Set field" as
+ * described in IEEE Std 802.11-2020 section 9.4.2.55.4.
  */
 struct ieee80211_mcs_info {
 	u8 rx_mask[IEEE80211_HT_MCS_MASK_LEN];
@@ -1600,10 +1686,16 @@ struct ieee80211_mcs_info {
 	(IEEE80211_HT_MCS_UNEQUAL_MODULATION_START / 8)
 
 /**
- * struct ieee80211_ht_cap - HT capabilities
+ * struct ieee80211_ht_cap - HT capabilities element
+ * @cap_info: HT Capability Information
+ * @ampdu_params_info: A-MPDU Parameters
+ * @mcs: Supported MCS Set
+ * @extended_ht_cap_info: HT Extended Capabilities
+ * @tx_BF_cap_info: Transmit Beamforming Capabilities
+ * @antenna_selection_info: ASEL Capability
  *
- * This structure is the "HT capabilities element" as
- * described in 802.11n D5.0 7.3.2.57
+ * This structure represents the payload of the "HT Capabilities
+ * element" as described in IEEE Std 802.11-2020 section 9.4.2.55.
  */
 struct ieee80211_ht_cap {
 	__le16 cap_info;
@@ -1691,9 +1783,14 @@ enum ieee80211_min_mpdu_spacing {
 
 /**
  * struct ieee80211_ht_operation - HT operation IE
+ * @primary_chan: Primary Channel
+ * @ht_param: HT Operation Information parameters
+ * @operation_mode: HT Operation Information operation mode
+ * @stbc_param: HT Operation Information STBC params
+ * @basic_set: Basic HT-MCS Set
  *
- * This structure is the "HT operation element" as
- * described in 802.11n-2009 7.3.2.57
+ * This structure represents the payload of the "HT Operation
+ * element" as described in IEEE Std 802.11-2020 section 9.4.2.56.
  */
 struct ieee80211_ht_operation {
 	u8 primary_chan;
@@ -1862,9 +1959,12 @@ struct ieee80211_vht_operation {
 
 /**
  * struct ieee80211_he_cap_elem - HE capabilities element
+ * @mac_cap_info: HE MAC Capabilities Information
+ * @phy_cap_info: HE PHY Capabilities Information
  *
- * This structure is the "HE capabilities element" fixed fields as
- * described in P802.11ax_D4.0 section 9.4.2.242.2 and 9.4.2.242.3
+ * This structure represents the fixed fields of the payload of the
+ * "HE capabilities element" as described in IEEE Std 802.11ax-2021
+ * sections 9.4.2.248.2 and 9.4.2.248.3.
  */
 struct ieee80211_he_cap_elem {
 	u8 mac_cap_info[6];
@@ -1923,35 +2023,45 @@ struct ieee80211_he_mcs_nss_supp {
 } __packed;
 
 /**
- * struct ieee80211_he_operation - HE capabilities element
+ * struct ieee80211_he_operation - HE Operation element
+ * @he_oper_params: HE Operation Parameters + BSS Color Information
+ * @he_mcs_nss_set: Basic HE-MCS And NSS Set
+ * @optional: Optional fields VHT Operation Information, Max Co-Hosted
+ *            BSSID Indicator, and 6 GHz Operation Information
  *
- * This structure is the "HE operation element" fields as
- * described in P802.11ax_D4.0 section 9.4.2.243
+ * This structure represents the payload of the "HE Operation
+ * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.249.
  */
 struct ieee80211_he_operation {
 	__le32 he_oper_params;
 	__le16 he_mcs_nss_set;
-	/* Optional 0,1,3,4,5,7 or 8 bytes: depends on @he_oper_params */
 	u8 optional[];
 } __packed;
 
 /**
- * struct ieee80211_he_spr - HE spatial reuse element
+ * struct ieee80211_he_spr - Spatial Reuse Parameter Set element
+ * @he_sr_control: SR Control
+ * @optional: Optional fields Non-SRG OBSS PD Max Offset, SRG OBSS PD
+ *            Min Offset, SRG OBSS PD Max Offset, SRG BSS Color
+ *            Bitmap, and SRG Partial BSSID Bitmap
  *
- * This structure is the "HE spatial reuse element" element as
- * described in P802.11ax_D4.0 section 9.4.2.241
+ * This structure represents the payload of the "Spatial Reuse
+ * Parameter Set element" as described in IEEE Std 802.11ax-2021
+ * section 9.4.2.252.
  */
 struct ieee80211_he_spr {
 	u8 he_sr_control;
-	/* Optional 0 to 19 bytes: depends on @he_sr_control */
 	u8 optional[];
 } __packed;
 
 /**
  * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field
+ * @aifsn: ACI/AIFSN
+ * @ecw_min_max: ECWmin/ECWmax
+ * @mu_edca_timer: MU EDCA Timer
  *
- * This structure is the "MU AC Parameter Record" fields as
- * described in P802.11ax_D4.0 section 9.4.2.245
+ * This structure represents the "MU AC Parameter Record" as described
+ * in IEEE Std 802.11ax-2021 section 9.4.2.251, Figure 9-788p.
  */
 struct ieee80211_he_mu_edca_param_ac_rec {
 	u8 aifsn;
@@ -1961,9 +2071,14 @@ struct ieee80211_he_mu_edca_param_ac_rec {
 
 /**
  * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element
+ * @mu_qos_info: QoS Info
+ * @ac_be: MU AC_BE Parameter Record
+ * @ac_bk: MU AC_BK Parameter Record
+ * @ac_vi: MU AC_VI Parameter Record
+ * @ac_vo: MU AC_VO Parameter Record
  *
- * This structure is the "MU EDCA Parameter Set element" fields as
- * described in P802.11ax_D4.0 section 9.4.2.245
+ * This structure represents the payload of the "MU EDCA Parameter Set
+ * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.251.
  */
 struct ieee80211_mu_edca_param_set {
 	u8 mu_qos_info;
@@ -2177,9 +2292,9 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap,
  * enum ieee80211_ap_reg_power - regulatory power for a Access Point
  *
  * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode
- * @IEEE80211_REG_LPI: Indoor Access Point
- * @IEEE80211_REG_SP: Standard power Access Point
- * @IEEE80211_REG_VLP: Very low power Access Point
+ * @IEEE80211_REG_LPI_AP: Indoor Access Point
+ * @IEEE80211_REG_SP_AP: Standard power Access Point
+ * @IEEE80211_REG_VLP_AP: Very low power Access Point
  * @IEEE80211_REG_AP_POWER_AFTER_LAST: internal
  * @IEEE80211_REG_AP_POWER_MAX: maximum value
  */
@@ -2567,7 +2682,7 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len)
 #define IEEE80211_6GHZ_CTRL_REG_SP_AP	1
 
 /**
- * ieee80211_he_6ghz_oper - HE 6 GHz operation Information field
+ * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field
  * @primary: primary channel
  * @control: control flags
  * @ccfs0: channel center frequency segment 0
@@ -2614,9 +2729,13 @@ enum ieee80211_tx_power_intrpt_type {
 };
 
 /**
- * struct ieee80211_tx_pwr_env
+ * struct ieee80211_tx_pwr_env - Transmit Power Envelope
+ * @tx_power_info: Transmit Power Information field
+ * @tx_power: Maximum Transmit Power field
  *
- * This structure represents the "Transmit Power Envelope element"
+ * This structure represents the payload of the "Transmit Power
+ * Envelope element" as described in IEEE Std 802.11ax-2021 section
+ * 9.4.2.161
  */
 struct ieee80211_tx_pwr_env {
 	u8 tx_power_info;
@@ -4478,7 +4597,7 @@ static inline bool for_each_element_completed(const struct element *element,
 	return (const u8 *)element == (const u8 *)data + datalen;
 }
 
-/**
+/*
  * RSNX Capabilities:
  * bits 0-3: Field length (n-1)
  */
@@ -4721,7 +4840,7 @@ ieee80211_mle_get_bss_param_ch_cnt(const struct ieee80211_multi_link_elem *mle)
 }
 
 /**
- * ieee80211_mle_get_eml_sync_delay - returns the medium sync delay
+ * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay
  * @data: pointer to the multi link EHT IE
  *
  * The element is assumed to be of the correct type (BASIC) and big enough,
-- 
GitLab


From 6785b2edf48c6b1c3ea61fe3b0d2e02b8fbf90c0 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Tue, 22 Aug 2023 23:21:39 +0530
Subject: [PATCH 1528/1806] bpf: Fix check_func_arg_reg_off bug for graph
 root/node

The commit being fixed introduced a hunk into check_func_arg_reg_off
that bypasses reg->off == 0 enforcement when offset points to a graph
node or root. This might possibly be done for treating bpf_rbtree_remove
and others as KF_RELEASE and then later check correct reg->off in helper
argument checks.

But this is not the case, those helpers are already not KF_RELEASE and
permit non-zero reg->off and verify it later to match the subobject in
BTF type.

However, this logic leads to bpf_obj_drop permitting free of register
arguments with non-zero offset when they point to a graph root or node
within them, which is not ok.

For instance:

struct foo {
	int i;
	int j;
	struct bpf_rb_node node;
};

struct foo *f = bpf_obj_new(typeof(*f));
if (!f) ...
bpf_obj_drop(f); // OK
bpf_obj_drop(&f->i); // still ok from verifier PoV
bpf_obj_drop(&f->node); // Not OK, but permitted right now

Fix this by dropping the whole part of code altogether.

Fixes: 6a3cd3318ff6 ("bpf: Migrate release_on_unlock logic to non-owning ref semantics")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230822175140.1317749-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3a91bfd7b9cce..3d51c737a034f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7973,17 +7973,6 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 		if (arg_type_is_dynptr(arg_type) && type == PTR_TO_STACK)
 			return 0;
 
-		if ((type_is_ptr_alloc_obj(type) || type_is_non_owning_ref(type)) && reg->off) {
-			if (reg_find_field_offset(reg, reg->off, BPF_GRAPH_NODE_OR_ROOT))
-				return __check_ptr_off_reg(env, reg, regno, true);
-
-			verbose(env, "R%d must have zero offset when passed to release func\n",
-				regno);
-			verbose(env, "No graph node or root found at R%d type:%s off:%d\n", regno,
-				btf_type_name(reg->btf, reg->btf_id), reg->off);
-			return -EINVAL;
-		}
-
 		/* Doing check_ptr_off_reg check for the offset will catch this
 		 * because fixed_off_ok is false, but checking here allows us
 		 * to give the user a better error message.
-- 
GitLab


From fbc5bc4c8e6ca6f5720798c96107307906dc49c0 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Tue, 22 Aug 2023 23:21:40 +0530
Subject: [PATCH 1529/1806] selftests/bpf: Add test for bpf_obj_drop with bad
 reg->off

Add a selftest for the fix provided in the previous commit. Without the
fix, the selftest passes the verifier while it should fail. The special
logic for detecting graph root or node for reg->off and bypassing
reg->off == 0 guarantee for release helpers/kfuncs has been dropped.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230822175140.1317749-3-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/progs/local_kptr_stash_fail.c         | 20 +++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c
index 5484d1e9801d3..fcf7a7567da22 100644
--- a/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c
+++ b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c
@@ -62,4 +62,24 @@ long stash_rb_nodes(void *ctx)
 	return 0;
 }
 
+SEC("tc")
+__failure __msg("R1 must have zero offset when passed to release func")
+long drop_rb_node_off(void *ctx)
+{
+	struct map_value *mapval;
+	struct node_data *res;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	res = bpf_obj_new(typeof(*res));
+	if (!res)
+		return 1;
+	/* Try releasing with graph node offset */
+	bpf_obj_drop(&res->node);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
GitLab


From 29d67fdebc42af6466d1909c60fdd1ef4f3e5240 Mon Sep 17 00:00:00 2001
From: Hao Luo <haoluo@google.com>
Date: Tue, 22 Aug 2023 12:38:40 -0700
Subject: [PATCH 1530/1806] libbpf: Free btf_vmlinux when closing bpf_object

I hit a memory leak when testing bpf_program__set_attach_target().
Basically, set_attach_target() may allocate btf_vmlinux, for example,
when setting attach target for bpf_iter programs. But btf_vmlinux
is freed only in bpf_object_load(), which means if we only open
bpf object but not load it, setting attach target may leak
btf_vmlinux.

So let's free btf_vmlinux in bpf_object__close() anyway.

Signed-off-by: Hao Luo <haoluo@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230822193840.1509809-1-haoluo@google.com
---
 tools/lib/bpf/libbpf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index b8afe2f5bc934..4c3967d94b6d3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8423,6 +8423,7 @@ void bpf_object__close(struct bpf_object *obj)
 	bpf_object__elf_finish(obj);
 	bpf_object_unload(obj);
 	btf__free(obj->btf);
+	btf__free(obj->btf_vmlinux);
 	btf_ext__free(obj->btf_ext);
 
 	for (i = 0; i < obj->nr_maps; i++)
-- 
GitLab


From c5b4297dee9110b63f2c8202e4876bdcad43d4c4 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 21 Aug 2023 15:25:12 -0700
Subject: [PATCH 1531/1806] mptcp: refactor push_pending logic

To support redundant package schedulers more easily, this patch refactors
__mptcp_push_pending() logic from:

For each dfrag:
	While sends succeed:
		Call the scheduler (selects subflow and msk->snd_burst)
		Update subflow locks (push/release/acquire as needed)
		Send the dfrag data with mptcp_sendmsg_frag()
		Update already_sent, snd_nxt, snd_burst
	Update msk->first_pending
Push/release on final subflow

->

While first_pending isn't empty:
	Call the scheduler (selects subflow and msk->snd_burst)
	Update subflow locks (push/release/acquire as needed)
	For each pending dfrag:
		While sends succeed:
			Send the dfrag data with mptcp_sendmsg_frag()
			Update already_sent, snd_nxt, snd_burst
		Update msk->first_pending
		Break if required by msk->snd_burst / etc
	Push/release on final subflow

Refactors __mptcp_subflow_push_pending logic from:

For each dfrag:
	While sends succeed:
		Call the scheduler (selects subflow and msk->snd_burst)
		Send the dfrag data with mptcp_subflow_delegate(), break
		Send the dfrag data with mptcp_sendmsg_frag()
		Update dfrag->already_sent, msk->snd_nxt, msk->snd_burst
	Update msk->first_pending

->

While first_pending isn't empty:
	Call the scheduler (selects subflow and msk->snd_burst)
	Send the dfrag data with mptcp_subflow_delegate(), break
	Send the dfrag data with mptcp_sendmsg_frag()
	For each pending dfrag:
		While sends succeed:
			Send the dfrag data with mptcp_sendmsg_frag()
			Update already_sent, snd_nxt, snd_burst
		Update msk->first_pending
		Break if required by msk->snd_burst / etc

Move the duplicate code from __mptcp_push_pending() and
__mptcp_subflow_push_pending() into a new helper function, named
__subflow_push_pending(). Simplify __mptcp_push_pending() and
__mptcp_subflow_push_pending() by invoking this helper.

Also move the burst check conditions out of the function
mptcp_subflow_get_send(), check them in __subflow_push_pending() in
the inner "for each pending dfrag" loop.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-1-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c | 153 +++++++++++++++++++++++--------------------
 1 file changed, 81 insertions(+), 72 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6019a3cf1625f..29c662ffcd05b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1386,14 +1386,6 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 		       sk_stream_memory_free(msk->first) ? msk->first : NULL;
 	}
 
-	/* re-use last subflow, if the burst allow that */
-	if (msk->last_snd && msk->snd_burst > 0 &&
-	    sk_stream_memory_free(msk->last_snd) &&
-	    mptcp_subflow_active(mptcp_subflow_ctx(msk->last_snd))) {
-		mptcp_set_timeout(sk);
-		return msk->last_snd;
-	}
-
 	/* pick the subflow with the lower wmem/wspace ratio */
 	for (i = 0; i < SSK_MODE_MAX; ++i) {
 		send_info[i].ssk = NULL;
@@ -1499,57 +1491,86 @@ void mptcp_check_and_set_pending(struct sock *sk)
 		mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
 }
 
-void __mptcp_push_pending(struct sock *sk, unsigned int flags)
+static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
+				  struct mptcp_sendmsg_info *info)
 {
-	struct sock *prev_ssk = NULL, *ssk = NULL;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct mptcp_sendmsg_info info = {
-				.flags = flags,
-	};
-	bool do_check_data_fin = false;
 	struct mptcp_data_frag *dfrag;
-	int len;
+	int len, copied = 0, err = 0;
 
 	while ((dfrag = mptcp_send_head(sk))) {
-		info.sent = dfrag->already_sent;
-		info.limit = dfrag->data_len;
+		info->sent = dfrag->already_sent;
+		info->limit = dfrag->data_len;
 		len = dfrag->data_len - dfrag->already_sent;
 		while (len > 0) {
 			int ret = 0;
 
-			prev_ssk = ssk;
-			ssk = mptcp_subflow_get_send(msk);
-
-			/* First check. If the ssk has changed since
-			 * the last round, release prev_ssk
-			 */
-			if (ssk != prev_ssk && prev_ssk)
-				mptcp_push_release(prev_ssk, &info);
-			if (!ssk)
-				goto out;
-
-			/* Need to lock the new subflow only if different
-			 * from the previous one, otherwise we are still
-			 * helding the relevant lock
-			 */
-			if (ssk != prev_ssk)
-				lock_sock(ssk);
-
-			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, info);
 			if (ret <= 0) {
-				if (ret == -EAGAIN)
-					continue;
-				mptcp_push_release(ssk, &info);
+				err = copied ? : ret;
 				goto out;
 			}
 
-			do_check_data_fin = true;
-			info.sent += ret;
+			info->sent += ret;
+			copied += ret;
 			len -= ret;
 
 			mptcp_update_post_push(msk, dfrag, ret);
 		}
 		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+
+		if (msk->snd_burst <= 0 ||
+		    !sk_stream_memory_free(ssk) ||
+		    !mptcp_subflow_active(mptcp_subflow_ctx(ssk))) {
+			err = copied;
+			goto out;
+		}
+		mptcp_set_timeout(sk);
+	}
+	err = copied;
+
+out:
+	return err;
+}
+
+void __mptcp_push_pending(struct sock *sk, unsigned int flags)
+{
+	struct sock *prev_ssk = NULL, *ssk = NULL;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_sendmsg_info info = {
+				.flags = flags,
+	};
+	bool do_check_data_fin = false;
+
+	while (mptcp_send_head(sk)) {
+		int ret = 0;
+
+		prev_ssk = ssk;
+		ssk = mptcp_subflow_get_send(msk);
+
+		/* First check. If the ssk has changed since
+		 * the last round, release prev_ssk
+		 */
+		if (ssk != prev_ssk && prev_ssk)
+			mptcp_push_release(prev_ssk, &info);
+		if (!ssk)
+			goto out;
+
+		/* Need to lock the new subflow only if different
+		 * from the previous one, otherwise we are still
+		 * helding the relevant lock
+		 */
+		if (ssk != prev_ssk)
+			lock_sock(ssk);
+
+		ret = __subflow_push_pending(sk, ssk, &info);
+		if (ret <= 0) {
+			if (ret == -EAGAIN)
+				continue;
+			mptcp_push_release(ssk, &info);
+			goto out;
+		}
+		do_check_data_fin = true;
 	}
 
 	/* at this point we held the socket lock for the last subflow we used */
@@ -1570,42 +1591,30 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
 	struct mptcp_sendmsg_info info = {
 		.data_lock_held = true,
 	};
-	struct mptcp_data_frag *dfrag;
 	struct sock *xmit_ssk;
-	int len, copied = 0;
+	int copied = 0;
 
 	info.flags = 0;
-	while ((dfrag = mptcp_send_head(sk))) {
-		info.sent = dfrag->already_sent;
-		info.limit = dfrag->data_len;
-		len = dfrag->data_len - dfrag->already_sent;
-		while (len > 0) {
-			int ret = 0;
-
-			/* check for a different subflow usage only after
-			 * spooling the first chunk of data
-			 */
-			xmit_ssk = first ? ssk : mptcp_subflow_get_send(msk);
-			if (!xmit_ssk)
-				goto out;
-			if (xmit_ssk != ssk) {
-				mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk),
-						       MPTCP_DELEGATE_SEND);
-				goto out;
-			}
-
-			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
-			if (ret <= 0)
-				goto out;
+	while (mptcp_send_head(sk)) {
+		int ret = 0;
 
-			info.sent += ret;
-			copied += ret;
-			len -= ret;
-			first = false;
-
-			mptcp_update_post_push(msk, dfrag, ret);
+		/* check for a different subflow usage only after
+		 * spooling the first chunk of data
+		 */
+		xmit_ssk = first ? ssk : mptcp_subflow_get_send(msk);
+		if (!xmit_ssk)
+			goto out;
+		if (xmit_ssk != ssk) {
+			mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk),
+					       MPTCP_DELEGATE_SEND);
+			goto out;
 		}
-		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+
+		ret = __subflow_push_pending(sk, ssk, &info);
+		first = false;
+		if (ret <= 0)
+			break;
+		copied += ret;
 	}
 
 out:
-- 
GitLab


From ebc1e08f01ebedbf962e6417bbf6952bd4ca2142 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 21 Aug 2023 15:25:13 -0700
Subject: [PATCH 1532/1806] mptcp: drop last_snd and MPTCP_RESET_SCHEDULER

Since the burst check conditions have moved out of the function
mptcp_subflow_get_send(), it makes all msk->last_snd useless.
This patch drops them as well as the macro MPTCP_RESET_SCHEDULER.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-2-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c         |  9 +--------
 net/mptcp/pm_netlink.c |  3 ---
 net/mptcp/protocol.c   | 11 +----------
 net/mptcp/protocol.h   |  2 --
 4 files changed, 2 insertions(+), 23 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 7dbbad1e4f555..d8da5374d9e13 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -299,15 +299,8 @@ void mptcp_pm_mp_prio_received(struct sock *ssk, u8 bkup)
 
 	pr_debug("subflow->backup=%d, bkup=%d\n", subflow->backup, bkup);
 	msk = mptcp_sk(sk);
-	if (subflow->backup != bkup) {
+	if (subflow->backup != bkup)
 		subflow->backup = bkup;
-		mptcp_data_lock(sk);
-		if (!sock_owned_by_user(sk))
-			msk->last_snd = NULL;
-		else
-			__set_bit(MPTCP_RESET_SCHEDULER,  &msk->cb_flags);
-		mptcp_data_unlock(sk);
-	}
 
 	mptcp_event(MPTCP_EVENT_SUB_PRIORITY, msk, ssk, GFP_ATOMIC);
 }
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index c75d9d88a053d..9661f38126826 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -472,9 +472,6 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con
 
 	slow = lock_sock_fast(ssk);
 	if (prio) {
-		if (subflow->backup != backup)
-			msk->last_snd = NULL;
-
 		subflow->send_mp_prio = 1;
 		subflow->backup = backup;
 		subflow->request_bkup = backup;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 29c662ffcd05b..f15ff80be30f9 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1438,16 +1438,13 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 
 	burst = min_t(int, MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt);
 	wmem = READ_ONCE(ssk->sk_wmem_queued);
-	if (!burst) {
-		msk->last_snd = NULL;
+	if (!burst)
 		return ssk;
-	}
 
 	subflow = mptcp_subflow_ctx(ssk);
 	subflow->avg_pacing_rate = div_u64((u64)subflow->avg_pacing_rate * wmem +
 					   READ_ONCE(ssk->sk_pacing_rate) * burst,
 					   burst + wmem);
-	msk->last_snd = ssk;
 	msk->snd_burst = burst;
 	return ssk;
 }
@@ -2379,9 +2376,6 @@ out_release:
 		WRITE_ONCE(msk->first, NULL);
 
 out:
-	if (ssk == msk->last_snd)
-		msk->last_snd = NULL;
-
 	if (need_push)
 		__mptcp_push_pending(sk, 0);
 }
@@ -3046,7 +3040,6 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	 * subflow
 	 */
 	mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
-	msk->last_snd = NULL;
 	WRITE_ONCE(msk->flags, 0);
 	msk->cb_flags = 0;
 	msk->push_pending = 0;
@@ -3316,8 +3309,6 @@ static void mptcp_release_cb(struct sock *sk)
 			__mptcp_set_connected(sk);
 		if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
 			__mptcp_error_report(sk);
-		if (__test_and_clear_bit(MPTCP_RESET_SCHEDULER, &msk->cb_flags))
-			msk->last_snd = NULL;
 	}
 
 	__mptcp_update_rmem(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 38c7ea0133610..cbf9a9e176b24 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -123,7 +123,6 @@
 #define MPTCP_RETRANSMIT	4
 #define MPTCP_FLUSH_JOIN_LIST	5
 #define MPTCP_CONNECTED		6
-#define MPTCP_RESET_SCHEDULER	7
 
 struct mptcp_skb_cb {
 	u64 map_seq;
@@ -269,7 +268,6 @@ struct mptcp_sock {
 	u64		rcv_data_fin_seq;
 	u64		bytes_retrans;
 	int		rmem_fwd_alloc;
-	struct sock	*last_snd;
 	int		snd_burst;
 	int		old_wspace;
 	u64		recovery_snd_nxt;	/* in recovery mode accept up to this seq;
-- 
GitLab


From 740ebe35bd3f5c4ff8ec60e5e521e47ea8f5492c Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 21 Aug 2023 15:25:14 -0700
Subject: [PATCH 1533/1806] mptcp: add struct mptcp_sched_ops

This patch defines struct mptcp_sched_ops, which has three struct members,
name, owner and list, and four function pointers: init(), release() and
get_subflow().

The scheduler function get_subflow() have a struct mptcp_sched_data
parameter, which contains a reinject flag for retrans or not, a subflows
number and a mptcp_subflow_context array.

Add the scheduler registering, unregistering and finding functions to add,
delete and find a packet scheduler on the global list mptcp_sched_list.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-3-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/mptcp.h  | 21 +++++++++++++++++
 net/mptcp/Makefile   |  2 +-
 net/mptcp/protocol.h |  3 +++
 net/mptcp/sched.c    | 56 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 81 insertions(+), 1 deletion(-)
 create mode 100644 net/mptcp/sched.c

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 3c5c68618fcc5..fb996124b3d5c 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -96,6 +96,27 @@ struct mptcp_out_options {
 #endif
 };
 
+#define MPTCP_SCHED_NAME_MAX	16
+#define MPTCP_SUBFLOWS_MAX	8
+
+struct mptcp_sched_data {
+	bool	reinject;
+	u8	subflows;
+	struct mptcp_subflow_context *contexts[MPTCP_SUBFLOWS_MAX];
+};
+
+struct mptcp_sched_ops {
+	int (*get_subflow)(struct mptcp_sock *msk,
+			   struct mptcp_sched_data *data);
+
+	char			name[MPTCP_SCHED_NAME_MAX];
+	struct module		*owner;
+	struct list_head	list;
+
+	void (*init)(struct mptcp_sock *msk);
+	void (*release)(struct mptcp_sock *msk);
+} ____cacheline_aligned_in_smp;
+
 #ifdef CONFIG_MPTCP
 void mptcp_init(void);
 
diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile
index a3829ce548f94..84e531f86b82f 100644
--- a/net/mptcp/Makefile
+++ b/net/mptcp/Makefile
@@ -2,7 +2,7 @@
 obj-$(CONFIG_MPTCP) += mptcp.o
 
 mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \
-	   mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o
+	   mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o sched.o
 
 obj-$(CONFIG_SYN_COOKIES) += syncookies.o
 obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index cbf9a9e176b24..985e8f86668d9 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -655,6 +655,9 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 			 struct sockaddr_storage *addr,
 			 unsigned short family);
+struct mptcp_sched_ops *mptcp_sched_find(const char *name);
+int mptcp_register_scheduler(struct mptcp_sched_ops *sched);
+void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
 
 static inline bool __tcp_can_send(const struct sock *ssk)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
new file mode 100644
index 0000000000000..c5d3bbafba71e
--- /dev/null
+++ b/net/mptcp/sched.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2022, SUSE.
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include "protocol.h"
+
+static DEFINE_SPINLOCK(mptcp_sched_list_lock);
+static LIST_HEAD(mptcp_sched_list);
+
+/* Must be called with rcu read lock held */
+struct mptcp_sched_ops *mptcp_sched_find(const char *name)
+{
+	struct mptcp_sched_ops *sched, *ret = NULL;
+
+	list_for_each_entry_rcu(sched, &mptcp_sched_list, list) {
+		if (!strcmp(sched->name, name)) {
+			ret = sched;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
+{
+	if (!sched->get_subflow)
+		return -EINVAL;
+
+	spin_lock(&mptcp_sched_list_lock);
+	if (mptcp_sched_find(sched->name)) {
+		spin_unlock(&mptcp_sched_list_lock);
+		return -EEXIST;
+	}
+	list_add_tail_rcu(&sched->list, &mptcp_sched_list);
+	spin_unlock(&mptcp_sched_list_lock);
+
+	pr_debug("%s registered", sched->name);
+	return 0;
+}
+
+void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched)
+{
+	spin_lock(&mptcp_sched_list_lock);
+	list_del_rcu(&sched->list);
+	spin_unlock(&mptcp_sched_list_lock);
+}
-- 
GitLab


From e3b2870b6d220d1cbd2d52d7acc9f0de9fdfeccf Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 21 Aug 2023 15:25:15 -0700
Subject: [PATCH 1534/1806] mptcp: add a new sysctl scheduler

This patch adds a new sysctl, named scheduler, to support for selection
of different schedulers. Export mptcp_get_scheduler helper to get this
sysctl.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-4-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/mptcp-sysctl.rst |  8 ++++++++
 net/mptcp/ctrl.c                          | 14 ++++++++++++++
 net/mptcp/protocol.h                      |  1 +
 3 files changed, 23 insertions(+)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index 213510698014e..15f1919d640c0 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -74,3 +74,11 @@ stale_loss_cnt - INTEGER
 	This is a per-namespace sysctl.
 
 	Default: 4
+
+scheduler - STRING
+	Select the scheduler of your choice.
+
+	Support for selection of different schedulers. This is a per-namespace
+	sysctl.
+
+	Default: "default"
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index ae20b7d92e288..c46c22a84d235 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -32,6 +32,7 @@ struct mptcp_pernet {
 	u8 checksum_enabled;
 	u8 allow_join_initial_addr_port;
 	u8 pm_type;
+	char scheduler[MPTCP_SCHED_NAME_MAX];
 };
 
 static struct mptcp_pernet *mptcp_get_pernet(const struct net *net)
@@ -69,6 +70,11 @@ int mptcp_get_pm_type(const struct net *net)
 	return mptcp_get_pernet(net)->pm_type;
 }
 
+const char *mptcp_get_scheduler(const struct net *net)
+{
+	return mptcp_get_pernet(net)->scheduler;
+}
+
 static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 {
 	pernet->mptcp_enabled = 1;
@@ -77,6 +83,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 	pernet->allow_join_initial_addr_port = 1;
 	pernet->stale_loss_cnt = 4;
 	pernet->pm_type = MPTCP_PM_TYPE_KERNEL;
+	strcpy(pernet->scheduler, "default");
 }
 
 #ifdef CONFIG_SYSCTL
@@ -128,6 +135,12 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.extra1       = SYSCTL_ZERO,
 		.extra2       = &mptcp_pm_type_max
 	},
+	{
+		.procname = "scheduler",
+		.maxlen	= MPTCP_SCHED_NAME_MAX,
+		.mode = 0644,
+		.proc_handler = proc_dostring,
+	},
 	{}
 };
 
@@ -149,6 +162,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	table[3].data = &pernet->allow_join_initial_addr_port;
 	table[4].data = &pernet->stale_loss_cnt;
 	table[5].data = &pernet->pm_type;
+	table[6].data = &pernet->scheduler;
 
 	hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
 	if (!hdr)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 985e8f86668d9..bfa13a50f276f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -623,6 +623,7 @@ int mptcp_is_checksum_enabled(const struct net *net);
 int mptcp_allow_join_id0(const struct net *net);
 unsigned int mptcp_stale_loss_cnt(const struct net *net);
 int mptcp_get_pm_type(const struct net *net);
+const char *mptcp_get_scheduler(const struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     const struct mptcp_options_received *mp_opt);
 bool __mptcp_retransmit_pending_data(struct sock *sk);
-- 
GitLab


From 1730b2b2c5a5a886007b247366aebe0976dc8881 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 21 Aug 2023 15:25:16 -0700
Subject: [PATCH 1535/1806] mptcp: add sched in mptcp_sock

This patch adds a new struct member sched in struct mptcp_sock.
And two helpers mptcp_init_sched() and mptcp_release_sched() to
init and release it.

Init it with the sysctl scheduler in mptcp_init_sock(), copy the
scheduler from the parent in mptcp_sk_clone(), and release it in
__mptcp_destroy_sock().

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-5-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c |  8 ++++++++
 net/mptcp/protocol.h |  4 ++++
 net/mptcp/sched.c    | 33 +++++++++++++++++++++++++++++++++
 3 files changed, 45 insertions(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index f15ff80be30f9..54a3eccfa731c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2697,6 +2697,7 @@ static void mptcp_ca_reset(struct sock *sk)
 static int mptcp_init_sock(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
+	int ret;
 
 	__mptcp_init_sock(sk);
 
@@ -2706,6 +2707,11 @@ static int mptcp_init_sock(struct sock *sk)
 	if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net))
 		return -ENOMEM;
 
+	ret = mptcp_init_sched(mptcp_sk(sk),
+			       mptcp_sched_find(mptcp_get_scheduler(net)));
+	if (ret)
+		return ret;
+
 	set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);
 
 	/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
@@ -2851,6 +2857,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	mptcp_stop_timer(sk);
 	sk_stop_timer(sk, &sk->sk_timer);
 	msk->pm.status = 0;
+	mptcp_release_sched(msk);
 
 	sk->sk_prot->destroy(sk);
 
@@ -3105,6 +3112,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	msk->snd_una = msk->write_seq;
 	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
+	mptcp_init_sched(msk, mptcp_sk(sk)->sched);
 
 	/* passive msk is created after the first/MPC subflow */
 	msk->subflow_id = 2;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index bfa13a50f276f..548c302a757ee 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -312,6 +312,7 @@ struct mptcp_sock {
 				 * lock as such sock is freed after close().
 				 */
 	struct mptcp_pm_data	pm;
+	struct mptcp_sched_ops	*sched;
 	struct {
 		u32	space;	/* bytes copied in last measurement window */
 		u32	copied; /* bytes copied in this measurement window */
@@ -659,6 +660,9 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 struct mptcp_sched_ops *mptcp_sched_find(const char *name);
 int mptcp_register_scheduler(struct mptcp_sched_ops *sched);
 void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
+int mptcp_init_sched(struct mptcp_sock *msk,
+		     struct mptcp_sched_ops *sched);
+void mptcp_release_sched(struct mptcp_sock *msk);
 
 static inline bool __tcp_can_send(const struct sock *ssk)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index c5d3bbafba71e..53773668b5ee0 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -54,3 +54,36 @@ void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched)
 	list_del_rcu(&sched->list);
 	spin_unlock(&mptcp_sched_list_lock);
 }
+
+int mptcp_init_sched(struct mptcp_sock *msk,
+		     struct mptcp_sched_ops *sched)
+{
+	if (!sched)
+		goto out;
+
+	if (!bpf_try_module_get(sched, sched->owner))
+		return -EBUSY;
+
+	msk->sched = sched;
+	if (msk->sched->init)
+		msk->sched->init(msk);
+
+	pr_debug("sched=%s", msk->sched->name);
+
+out:
+	return 0;
+}
+
+void mptcp_release_sched(struct mptcp_sock *msk)
+{
+	struct mptcp_sched_ops *sched = msk->sched;
+
+	if (!sched)
+		return;
+
+	msk->sched = NULL;
+	if (sched->release)
+		sched->release(msk);
+
+	bpf_module_put(sched, sched->owner);
+}
-- 
GitLab


From fce68b03086fd00eb5a8ba4744f36f0d007d0f9d Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 21 Aug 2023 15:25:17 -0700
Subject: [PATCH 1536/1806] mptcp: add scheduled in mptcp_subflow_context

This patch adds a new member scheduled in struct mptcp_subflow_context,
which will be set in the MPTCP scheduler context when the scheduler
picks this subflow to send data.

Add a new helper mptcp_subflow_set_scheduled() to set this flag using
WRITE_ONCE().

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-6-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.h | 3 +++
 net/mptcp/sched.c    | 6 ++++++
 2 files changed, 9 insertions(+)

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 548c302a757ee..e7523a40132f5 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -491,6 +491,7 @@ struct mptcp_subflow_context {
 		is_mptfo : 1,	    /* subflow is doing TFO */
 		__unused : 9;
 	enum mptcp_data_avail data_avail;
+	bool	scheduled;
 	u32	remote_nonce;
 	u64	thmac;
 	u32	local_nonce;
@@ -663,6 +664,8 @@ void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
 int mptcp_init_sched(struct mptcp_sock *msk,
 		     struct mptcp_sched_ops *sched);
 void mptcp_release_sched(struct mptcp_sock *msk);
+void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
+				 bool scheduled);
 
 static inline bool __tcp_can_send(const struct sock *ssk)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 53773668b5ee0..d295b92a57899 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -87,3 +87,9 @@ void mptcp_release_sched(struct mptcp_sock *msk)
 
 	bpf_module_put(sched, sched->owner);
 }
+
+void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
+				 bool scheduled)
+{
+	WRITE_ONCE(subflow->scheduled, scheduled);
+}
-- 
GitLab


From 07336a87fe871518a7b3508e29a21ca1735b3edc Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 21 Aug 2023 15:25:18 -0700
Subject: [PATCH 1537/1806] mptcp: add scheduler wrappers

This patch defines two packet scheduler wrappers mptcp_sched_get_send()
and mptcp_sched_get_retrans(), invoke get_subflow() of msk->sched in
them.

Set data->reinject to true in mptcp_sched_get_retrans(), set it false in
mptcp_sched_get_send().

If msk->sched is NULL, use default functions mptcp_subflow_get_send()
and mptcp_subflow_get_retrans() to send data.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-7-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c |  4 ++--
 net/mptcp/protocol.h |  4 ++++
 net/mptcp/sched.c    | 48 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 54a3eccfa731c..9cd172d2c8d6f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1366,7 +1366,7 @@ bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
  * returns the subflow that will transmit the next DSS
  * additionally updates the rtx timeout
  */
-static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
+struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 {
 	struct subflow_send_info send_info[SSK_MODE_MAX];
 	struct mptcp_subflow_context *subflow;
@@ -2204,7 +2204,7 @@ static void mptcp_timeout_timer(struct timer_list *t)
  *
  * A backup subflow is returned only if that is the only kind available.
  */
-static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
+struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
 {
 	struct sock *backup = NULL, *pick = NULL;
 	struct mptcp_subflow_context *subflow;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index e7523a40132f5..78562f695c46d 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -666,6 +666,10 @@ int mptcp_init_sched(struct mptcp_sock *msk,
 void mptcp_release_sched(struct mptcp_sock *msk);
 void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 				 bool scheduled);
+struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
+struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk);
+int mptcp_sched_get_send(struct mptcp_sock *msk);
+int mptcp_sched_get_retrans(struct mptcp_sock *msk);
 
 static inline bool __tcp_can_send(const struct sock *ssk)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index d295b92a57899..884606686cfe9 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -93,3 +93,51 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 {
 	WRITE_ONCE(subflow->scheduled, scheduled);
 }
+
+int mptcp_sched_get_send(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sched_data data;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		if (READ_ONCE(subflow->scheduled))
+			return 0;
+	}
+
+	if (!msk->sched) {
+		struct sock *ssk;
+
+		ssk = mptcp_subflow_get_send(msk);
+		if (!ssk)
+			return -EINVAL;
+		mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+		return 0;
+	}
+
+	data.reinject = false;
+	return msk->sched->get_subflow(msk, &data);
+}
+
+int mptcp_sched_get_retrans(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sched_data data;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		if (READ_ONCE(subflow->scheduled))
+			return 0;
+	}
+
+	if (!msk->sched) {
+		struct sock *ssk;
+
+		ssk = mptcp_subflow_get_retrans(msk);
+		if (!ssk)
+			return -EINVAL;
+		mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+		return 0;
+	}
+
+	data.reinject = true;
+	return msk->sched->get_subflow(msk, &data);
+}
-- 
GitLab


From 0fa1b3783a17d75a4aa1651a18ede041ffca5750 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 21 Aug 2023 15:25:19 -0700
Subject: [PATCH 1538/1806] mptcp: use get_send wrapper

This patch adds the multiple subflows support for __mptcp_push_pending
and __mptcp_subflow_push_pending. Use get_send() wrapper instead of
mptcp_subflow_get_send() in them.

Check the subflow scheduled flags to test which subflow or subflows are
picked by the scheduler, use them to send data.

Move msk_owned_by_me() and fallback checks into get_send() wrapper from
mptcp_subflow_get_send().

This commit allows the scheduler to set the subflow->scheduled bit in
multiple subflows, but it does not allow for sending redundant data.
Multiple scheduled subflows will send sequential data on each subflow.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-8-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c | 113 ++++++++++++++++++++++++++-----------------
 net/mptcp/sched.c    |  13 +++++
 2 files changed, 81 insertions(+), 45 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 9cd172d2c8d6f..77e94ee828593 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1377,15 +1377,6 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	u64 linger_time;
 	long tout = 0;
 
-	msk_owned_by_me(msk);
-
-	if (__mptcp_check_fallback(msk)) {
-		if (!msk->first)
-			return NULL;
-		return __tcp_can_send(msk->first) &&
-		       sk_stream_memory_free(msk->first) ? msk->first : NULL;
-	}
-
 	/* pick the subflow with the lower wmem/wspace ratio */
 	for (i = 0; i < SSK_MODE_MAX; ++i) {
 		send_info[i].ssk = NULL;
@@ -1538,43 +1529,56 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 				.flags = flags,
 	};
 	bool do_check_data_fin = false;
+	int push_count = 1;
 
-	while (mptcp_send_head(sk)) {
+	while (mptcp_send_head(sk) && (push_count > 0)) {
+		struct mptcp_subflow_context *subflow;
 		int ret = 0;
 
-		prev_ssk = ssk;
-		ssk = mptcp_subflow_get_send(msk);
+		if (mptcp_sched_get_send(msk))
+			break;
 
-		/* First check. If the ssk has changed since
-		 * the last round, release prev_ssk
-		 */
-		if (ssk != prev_ssk && prev_ssk)
-			mptcp_push_release(prev_ssk, &info);
-		if (!ssk)
-			goto out;
+		push_count = 0;
 
-		/* Need to lock the new subflow only if different
-		 * from the previous one, otherwise we are still
-		 * helding the relevant lock
-		 */
-		if (ssk != prev_ssk)
-			lock_sock(ssk);
+		mptcp_for_each_subflow(msk, subflow) {
+			if (READ_ONCE(subflow->scheduled)) {
+				mptcp_subflow_set_scheduled(subflow, false);
 
-		ret = __subflow_push_pending(sk, ssk, &info);
-		if (ret <= 0) {
-			if (ret == -EAGAIN)
-				continue;
-			mptcp_push_release(ssk, &info);
-			goto out;
+				prev_ssk = ssk;
+				ssk = mptcp_subflow_tcp_sock(subflow);
+				if (ssk != prev_ssk) {
+					/* First check. If the ssk has changed since
+					 * the last round, release prev_ssk
+					 */
+					if (prev_ssk)
+						mptcp_push_release(prev_ssk, &info);
+
+					/* Need to lock the new subflow only if different
+					 * from the previous one, otherwise we are still
+					 * helding the relevant lock
+					 */
+					lock_sock(ssk);
+				}
+
+				push_count++;
+
+				ret = __subflow_push_pending(sk, ssk, &info);
+				if (ret <= 0) {
+					if (ret != -EAGAIN ||
+					    (1 << ssk->sk_state) &
+					     (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSE))
+						push_count--;
+					continue;
+				}
+				do_check_data_fin = true;
+			}
 		}
-		do_check_data_fin = true;
 	}
 
 	/* at this point we held the socket lock for the last subflow we used */
 	if (ssk)
 		mptcp_push_release(ssk, &info);
 
-out:
 	/* ensure the rtx timer is running */
 	if (!mptcp_timer_pending(sk))
 		mptcp_reset_timer(sk);
@@ -1588,30 +1592,49 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
 	struct mptcp_sendmsg_info info = {
 		.data_lock_held = true,
 	};
+	bool keep_pushing = true;
 	struct sock *xmit_ssk;
 	int copied = 0;
 
 	info.flags = 0;
-	while (mptcp_send_head(sk)) {
+	while (mptcp_send_head(sk) && keep_pushing) {
+		struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 		int ret = 0;
 
 		/* check for a different subflow usage only after
 		 * spooling the first chunk of data
 		 */
-		xmit_ssk = first ? ssk : mptcp_subflow_get_send(msk);
-		if (!xmit_ssk)
-			goto out;
-		if (xmit_ssk != ssk) {
-			mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk),
-					       MPTCP_DELEGATE_SEND);
+		if (first) {
+			mptcp_subflow_set_scheduled(subflow, false);
+			ret = __subflow_push_pending(sk, ssk, &info);
+			first = false;
+			if (ret <= 0)
+				break;
+			copied += ret;
+			continue;
+		}
+
+		if (mptcp_sched_get_send(msk))
 			goto out;
+
+		if (READ_ONCE(subflow->scheduled)) {
+			mptcp_subflow_set_scheduled(subflow, false);
+			ret = __subflow_push_pending(sk, ssk, &info);
+			if (ret <= 0)
+				keep_pushing = false;
+			copied += ret;
 		}
 
-		ret = __subflow_push_pending(sk, ssk, &info);
-		first = false;
-		if (ret <= 0)
-			break;
-		copied += ret;
+		mptcp_for_each_subflow(msk, subflow) {
+			if (READ_ONCE(subflow->scheduled)) {
+				xmit_ssk = mptcp_subflow_tcp_sock(subflow);
+				if (xmit_ssk != ssk) {
+					mptcp_subflow_delegate(subflow,
+							       MPTCP_DELEGATE_SEND);
+					keep_pushing = false;
+				}
+			}
+		}
 	}
 
 out:
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 884606686cfe9..078b5d44978d6 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -99,6 +99,19 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sched_data data;
 
+	msk_owned_by_me(msk);
+
+	/* the following check is moved out of mptcp_subflow_get_send */
+	if (__mptcp_check_fallback(msk)) {
+		if (msk->first &&
+		    __tcp_can_send(msk->first) &&
+		    sk_stream_memory_free(msk->first)) {
+			mptcp_subflow_set_scheduled(mptcp_subflow_ctx(msk->first), true);
+			return 0;
+		}
+		return -EINVAL;
+	}
+
 	mptcp_for_each_subflow(msk, subflow) {
 		if (READ_ONCE(subflow->scheduled))
 			return 0;
-- 
GitLab


From ee2708aedad00544d38dba6df88efeb4a330bd66 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 21 Aug 2023 15:25:20 -0700
Subject: [PATCH 1539/1806] mptcp: use get_retrans wrapper

This patch adds the multiple subflows support for __mptcp_retrans(). Use
get_retrans() wrapper instead of mptcp_subflow_get_retrans() in it.

Check the subflow scheduled flags to test which subflow or subflows are
picked by the scheduler, use them to send data.

Move msk_owned_by_me() and fallback checks into get_retrans() wrapper
from mptcp_subflow_get_retrans().

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-9-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c | 65 +++++++++++++++++++++++++-------------------
 net/mptcp/sched.c    |  6 ++++
 2 files changed, 43 insertions(+), 28 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 77e94ee828593..61590ff2b9ee0 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2233,11 +2233,6 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
 	struct mptcp_subflow_context *subflow;
 	int min_stale_count = INT_MAX;
 
-	msk_owned_by_me(msk);
-
-	if (__mptcp_check_fallback(msk))
-		return NULL;
-
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
@@ -2515,16 +2510,17 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 static void __mptcp_retrans(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sendmsg_info info = {};
 	struct mptcp_data_frag *dfrag;
-	size_t copied = 0;
 	struct sock *ssk;
-	int ret;
+	int ret, err;
+	u16 len = 0;
 
 	mptcp_clean_una_wakeup(sk);
 
 	/* first check ssk: need to kick "stale" logic */
-	ssk = mptcp_subflow_get_retrans(msk);
+	err = mptcp_sched_get_retrans(msk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag) {
 		if (mptcp_data_fin_enabled(msk)) {
@@ -2543,32 +2539,45 @@ static void __mptcp_retrans(struct sock *sk)
 		goto reset_timer;
 	}
 
-	if (!ssk)
+	if (err)
 		goto reset_timer;
 
-	lock_sock(ssk);
+	mptcp_for_each_subflow(msk, subflow) {
+		if (READ_ONCE(subflow->scheduled)) {
+			u16 copied = 0;
 
-	/* limit retransmission to the bytes already sent on some subflows */
-	info.sent = 0;
-	info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
-	while (info.sent < info.limit) {
-		ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
-		if (ret <= 0)
-			break;
+			mptcp_subflow_set_scheduled(subflow, false);
 
-		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
-		copied += ret;
-		info.sent += ret;
-	}
-	if (copied) {
-		dfrag->already_sent = max(dfrag->already_sent, info.sent);
-		msk->bytes_retrans += copied;
-		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
-			 info.size_goal);
-		WRITE_ONCE(msk->allow_infinite_fallback, false);
+			ssk = mptcp_subflow_tcp_sock(subflow);
+
+			lock_sock(ssk);
+
+			/* limit retransmission to the bytes already sent on some subflows */
+			info.sent = 0;
+			info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len :
+								    dfrag->already_sent;
+			while (info.sent < info.limit) {
+				ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+				if (ret <= 0)
+					break;
+
+				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
+				copied += ret;
+				info.sent += ret;
+			}
+			if (copied) {
+				len = max(copied, len);
+				tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+					 info.size_goal);
+				WRITE_ONCE(msk->allow_infinite_fallback, false);
+			}
+
+			release_sock(ssk);
+		}
 	}
 
-	release_sock(ssk);
+	msk->bytes_retrans += len;
+	dfrag->already_sent = max(dfrag->already_sent, len);
 
 reset_timer:
 	mptcp_check_and_set_pending(sk);
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 078b5d44978d6..cac1cc1fa3b0d 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -136,6 +136,12 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sched_data data;
 
+	msk_owned_by_me(msk);
+
+	/* the following check is moved out of mptcp_subflow_get_retrans */
+	if (__mptcp_check_fallback(msk))
+		return -EINVAL;
+
 	mptcp_for_each_subflow(msk, subflow) {
 		if (READ_ONCE(subflow->scheduled))
 			return 0;
-- 
GitLab


From ed1ad86b8527f8f864df3c182adbfcd12a445de6 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Mon, 21 Aug 2023 15:25:21 -0700
Subject: [PATCH 1540/1806] mptcp: register default scheduler

This patch defines the default packet scheduler mptcp_sched_default.
Register it in mptcp_sched_init(), which is invoked in mptcp_proto_init().
Skip deleting this default scheduler in mptcp_unregister_scheduler().

Set msk->sched to the default scheduler when the input parameter of
mptcp_init_sched() is NULL.

Invoke mptcp_sched_default_get_subflow in get_send() and get_retrans()
if the defaut scheduler is set or msk->sched is NULL.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-10-0c860fb256a8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c |  1 +
 net/mptcp/protocol.h |  1 +
 net/mptcp/sched.c    | 55 ++++++++++++++++++++++++++------------------
 3 files changed, 35 insertions(+), 22 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 61590ff2b9ee0..933b257eee024 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3965,6 +3965,7 @@ void __init mptcp_proto_init(void)
 
 	mptcp_subflow_init();
 	mptcp_pm_init();
+	mptcp_sched_init();
 	mptcp_token_init();
 
 	if (proto_register(&mptcp_prot, 1) != 0)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 78562f695c46d..7254b35625756 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -661,6 +661,7 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 struct mptcp_sched_ops *mptcp_sched_find(const char *name);
 int mptcp_register_scheduler(struct mptcp_sched_ops *sched);
 void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
+void mptcp_sched_init(void);
 int mptcp_init_sched(struct mptcp_sock *msk,
 		     struct mptcp_sched_ops *sched);
 void mptcp_release_sched(struct mptcp_sock *msk);
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index cac1cc1fa3b0d..4ab0693c069c0 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -16,6 +16,26 @@
 static DEFINE_SPINLOCK(mptcp_sched_list_lock);
 static LIST_HEAD(mptcp_sched_list);
 
+static int mptcp_sched_default_get_subflow(struct mptcp_sock *msk,
+					   struct mptcp_sched_data *data)
+{
+	struct sock *ssk;
+
+	ssk = data->reinject ? mptcp_subflow_get_retrans(msk) :
+			       mptcp_subflow_get_send(msk);
+	if (!ssk)
+		return -EINVAL;
+
+	mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+	return 0;
+}
+
+static struct mptcp_sched_ops mptcp_sched_default = {
+	.get_subflow	= mptcp_sched_default_get_subflow,
+	.name		= "default",
+	.owner		= THIS_MODULE,
+};
+
 /* Must be called with rcu read lock held */
 struct mptcp_sched_ops *mptcp_sched_find(const char *name)
 {
@@ -50,16 +70,24 @@ int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
 
 void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched)
 {
+	if (sched == &mptcp_sched_default)
+		return;
+
 	spin_lock(&mptcp_sched_list_lock);
 	list_del_rcu(&sched->list);
 	spin_unlock(&mptcp_sched_list_lock);
 }
 
+void mptcp_sched_init(void)
+{
+	mptcp_register_scheduler(&mptcp_sched_default);
+}
+
 int mptcp_init_sched(struct mptcp_sock *msk,
 		     struct mptcp_sched_ops *sched)
 {
 	if (!sched)
-		goto out;
+		sched = &mptcp_sched_default;
 
 	if (!bpf_try_module_get(sched, sched->owner))
 		return -EBUSY;
@@ -70,7 +98,6 @@ int mptcp_init_sched(struct mptcp_sock *msk,
 
 	pr_debug("sched=%s", msk->sched->name);
 
-out:
 	return 0;
 }
 
@@ -117,17 +144,9 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
 			return 0;
 	}
 
-	if (!msk->sched) {
-		struct sock *ssk;
-
-		ssk = mptcp_subflow_get_send(msk);
-		if (!ssk)
-			return -EINVAL;
-		mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
-		return 0;
-	}
-
 	data.reinject = false;
+	if (msk->sched == &mptcp_sched_default || !msk->sched)
+		return mptcp_sched_default_get_subflow(msk, &data);
 	return msk->sched->get_subflow(msk, &data);
 }
 
@@ -147,16 +166,8 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 			return 0;
 	}
 
-	if (!msk->sched) {
-		struct sock *ssk;
-
-		ssk = mptcp_subflow_get_retrans(msk);
-		if (!ssk)
-			return -EINVAL;
-		mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
-		return 0;
-	}
-
 	data.reinject = true;
+	if (msk->sched == &mptcp_sched_default || !msk->sched)
+		return mptcp_sched_default_get_subflow(msk, &data);
 	return msk->sched->get_subflow(msk, &data);
 }
-- 
GitLab


From 4c0dac1ef8abc6295a91197884f5ceb5d11c2bd9 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Wed, 24 May 2023 17:46:47 +0200
Subject: [PATCH 1541/1806] net/mlx5: Rework devlink port alloc/free into
 init/cleanup

In order to prepare the devlink port registration function to be common
for PFs/VFs and SFs, change the existing devlink port allocation and
free functions into PF/VF init and cleanup, so similar helpers could be
later on introduced for SFs. Make the init/cleanup helpers responsible
for setting/clearing the vport->dl_port pointer.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/esw/devlink_port.c     | 65 ++++++++++++-------
 1 file changed, 43 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 234fd4c28e797..1864bf83aaa23 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -21,19 +21,16 @@ static bool mlx5_esw_devlink_port_supported(struct mlx5_eswitch *esw, u16 vport_
 	       mlx5_core_is_ec_vf_vport(esw->dev, vport_num);
 }
 
-static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 vport_num)
+static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *esw,
+							   u16 vport_num,
+							   struct devlink_port *dl_port)
 {
 	struct mlx5_core_dev *dev = esw->dev;
 	struct netdev_phys_item_id ppid = {};
-	struct devlink_port *dl_port;
 	u32 controller_num = 0;
 	bool external;
 	u16 pfnum;
 
-	dl_port = kzalloc(sizeof(*dl_port), GFP_KERNEL);
-	if (!dl_port)
-		return NULL;
-
 	mlx5_esw_get_port_parent_id(dev, &ppid);
 	pfnum = mlx5_get_dev_index(dev);
 	external = mlx5_core_is_ecpf_esw_manager(dev);
@@ -55,12 +52,40 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16
 		devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum,
 					      vport_num - 1, false);
 	}
-	return dl_port;
 }
 
-static void mlx5_esw_dl_port_free(struct devlink_port *dl_port)
+static int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	struct devlink_port *dl_port;
+	struct mlx5_vport *vport;
+
+	if (!mlx5_esw_devlink_port_supported(esw, vport_num))
+		return 0;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	dl_port = kzalloc(sizeof(*dl_port), GFP_KERNEL);
+	if (!dl_port)
+		return -ENOMEM;
+
+	mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(esw, vport_num, dl_port);
+
+	vport->dl_port = dl_port;
+	return 0;
+}
+
+static void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	kfree(dl_port);
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport) || !vport->dl_port)
+		return;
+
+	kfree(vport->dl_port);
+	vport->dl_port = NULL;
 }
 
 static const struct devlink_port_ops mlx5_esw_pf_vf_dl_port_ops = {
@@ -81,16 +106,17 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 	struct devlink *devlink;
 	int err;
 
-	if (!mlx5_esw_devlink_port_supported(esw, vport_num))
-		return 0;
-
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
 	if (IS_ERR(vport))
 		return PTR_ERR(vport);
 
-	dl_port = mlx5_esw_dl_port_alloc(esw, vport_num);
+	err = mlx5_esw_offloads_pf_vf_devlink_port_init(esw, vport_num);
+	if (err)
+		return err;
+
+	dl_port = vport->dl_port;
 	if (!dl_port)
-		return -ENOMEM;
+		return 0;
 
 	devlink = priv_to_devlink(dev);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num);
@@ -103,13 +129,12 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 	if (err)
 		goto rate_err;
 
-	vport->dl_port = dl_port;
 	return 0;
 
 rate_err:
 	devl_port_unregister(dl_port);
 reg_err:
-	mlx5_esw_dl_port_free(dl_port);
+	mlx5_esw_offloads_pf_vf_devlink_port_cleanup(esw, vport_num);
 	return err;
 }
 
@@ -117,19 +142,15 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo
 {
 	struct mlx5_vport *vport;
 
-	if (!mlx5_esw_devlink_port_supported(esw, vport_num))
-		return;
-
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
+	if (IS_ERR(vport) || !vport->dl_port)
 		return;
 
 	mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
 	devl_rate_leaf_destroy(vport->dl_port);
 
 	devl_port_unregister(vport->dl_port);
-	mlx5_esw_dl_port_free(vport->dl_port);
-	vport->dl_port = NULL;
+	mlx5_esw_offloads_pf_vf_devlink_port_cleanup(esw, vport_num);
 }
 
 struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num)
-- 
GitLab


From 638002252544a20f3f62ffb2cadbfa70207bd9b8 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 25 May 2023 10:30:45 +0200
Subject: [PATCH 1542/1806] net/mlx5: Push out SF devlink port init and cleanup
 code to separate helpers

Similar to what was done for PFs/VFs, introduce devlink port init and
cleanup helpers for SFs and manage the vport->dl_port pointer there.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/esw/devlink_port.c     | 61 ++++++++++++++++---
 1 file changed, 51 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 1864bf83aaa23..dfb1101dfef0f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -97,6 +97,48 @@ static const struct devlink_port_ops mlx5_esw_pf_vf_dl_port_ops = {
 	.port_fn_migratable_set = mlx5_devlink_port_fn_migratable_set,
 };
 
+static void mlx5_esw_offloads_sf_devlink_port_attrs_set(struct mlx5_eswitch *esw,
+							struct devlink_port *dl_port,
+							u32 controller, u32 sfnum)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	struct netdev_phys_item_id ppid = {};
+	u16 pfnum;
+
+	pfnum = mlx5_get_dev_index(dev);
+	mlx5_esw_get_port_parent_id(dev, &ppid);
+	memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len);
+	dl_port->attrs.switch_id.id_len = ppid.id_len;
+	devlink_port_attrs_pci_sf_set(dl_port, controller, pfnum, sfnum, !!controller);
+}
+
+static int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num,
+						  struct devlink_port *dl_port,
+						  u32 controller, u32 sfnum)
+{
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	mlx5_esw_offloads_sf_devlink_port_attrs_set(esw, dl_port, controller, sfnum);
+
+	vport->dl_port = dl_port;
+	return 0;
+}
+
+static void mlx5_esw_offloads_sf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return;
+
+	vport->dl_port = NULL;
+}
+
 int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct mlx5_core_dev *dev = esw->dev;
@@ -179,38 +221,37 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p
 				      u16 vport_num, u32 controller, u32 sfnum)
 {
 	struct mlx5_core_dev *dev = esw->dev;
-	struct netdev_phys_item_id ppid = {};
 	unsigned int dl_port_index;
 	struct mlx5_vport *vport;
 	struct devlink *devlink;
-	u16 pfnum;
 	int err;
 
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
 	if (IS_ERR(vport))
 		return PTR_ERR(vport);
 
-	pfnum = mlx5_get_dev_index(dev);
-	mlx5_esw_get_port_parent_id(dev, &ppid);
-	memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len);
-	dl_port->attrs.switch_id.id_len = ppid.id_len;
-	devlink_port_attrs_pci_sf_set(dl_port, controller, pfnum, sfnum, !!controller);
+	err = mlx5_esw_offloads_sf_devlink_port_init(esw, vport_num, dl_port, controller, sfnum);
+	if (err)
+		return err;
+
 	devlink = priv_to_devlink(dev);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num);
 	err = devl_port_register_with_ops(devlink, dl_port, dl_port_index,
 					  &mlx5_esw_dl_sf_port_ops);
 	if (err)
-		return err;
+		goto reg_err;
 
 	err = devl_rate_leaf_create(dl_port, vport, NULL);
 	if (err)
 		goto rate_err;
 
-	vport->dl_port = dl_port;
 	return 0;
 
 rate_err:
 	devl_port_unregister(dl_port);
+
+reg_err:
+	mlx5_esw_offloads_sf_devlink_port_cleanup(esw, vport_num);
 	return err;
 }
 
@@ -226,5 +267,5 @@ void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num
 	devl_rate_leaf_destroy(vport->dl_port);
 
 	devl_port_unregister(vport->dl_port);
-	vport->dl_port = NULL;
+	mlx5_esw_offloads_sf_devlink_port_cleanup(esw, vport_num);
 }
-- 
GitLab


From d9833bcfe840fff5d368b1c7c68e05c95be8d19c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 25 May 2023 10:01:02 +0200
Subject: [PATCH 1543/1806] net/mlx5: Push devlink port PF/VF init/cleanup
 calls out of devlink_port_register/unregister()

In order to prepare for
mlx5_esw_offloads_devlink_port_register/unregister() to be used
for SFs as well, push out the PF/VF specific init/cleanup calls outside.
Introduce mlx5_eswitch_load/unload_pf_vf_vport() and call them from
there. Use these new helpers of PF/VF loading and make
mlx5_eswitch_local/unload_vport() reusable for SFs.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/esw/devlink_port.c     | 13 ++----
 .../net/ethernet/mellanox/mlx5/core/eswitch.c | 45 ++++++++++++++-----
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  4 ++
 .../mellanox/mlx5/core/eswitch_offloads.c     | 16 +++++++
 4 files changed, 58 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index dfb1101dfef0f..5e8557f7564c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -54,7 +54,7 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 	}
 }
 
-static int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num)
+int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct devlink_port *dl_port;
 	struct mlx5_vport *vport;
@@ -76,7 +76,7 @@ static int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u
 	return 0;
 }
 
-static void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct mlx5_vport *vport;
 
@@ -152,10 +152,6 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 	if (IS_ERR(vport))
 		return PTR_ERR(vport);
 
-	err = mlx5_esw_offloads_pf_vf_devlink_port_init(esw, vport_num);
-	if (err)
-		return err;
-
 	dl_port = vport->dl_port;
 	if (!dl_port)
 		return 0;
@@ -165,7 +161,7 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 	err = devl_port_register_with_ops(devlink, dl_port, dl_port_index,
 					  &mlx5_esw_pf_vf_dl_port_ops);
 	if (err)
-		goto reg_err;
+		return err;
 
 	err = devl_rate_leaf_create(dl_port, vport, NULL);
 	if (err)
@@ -175,8 +171,6 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 
 rate_err:
 	devl_port_unregister(dl_port);
-reg_err:
-	mlx5_esw_offloads_pf_vf_devlink_port_cleanup(esw, vport_num);
 	return err;
 }
 
@@ -192,7 +186,6 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo
 	devl_rate_leaf_destroy(vport->dl_port);
 
 	devl_port_unregister(vport->dl_port);
-	mlx5_esw_offloads_pf_vf_devlink_port_cleanup(esw, vport_num);
 }
 
 struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 4a7a13169a90c..76d05e2337704 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1094,6 +1094,31 @@ static void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num)
 	mlx5_esw_vport_disable(esw, vport_num);
 }
 
+static int mlx5_eswitch_load_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_num,
+					 enum mlx5_eswitch_vport_event enabled_events)
+{
+	int err;
+
+	err = mlx5_esw_offloads_init_pf_vf_rep(esw, vport_num);
+	if (err)
+		return err;
+
+	err = mlx5_eswitch_load_vport(esw, vport_num, enabled_events);
+	if (err)
+		goto err_load;
+	return 0;
+
+err_load:
+	mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport_num);
+	return err;
+}
+
+static void mlx5_eswitch_unload_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	mlx5_eswitch_unload_vport(esw, vport_num);
+	mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport_num);
+}
+
 void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs)
 {
 	struct mlx5_vport *vport;
@@ -1102,7 +1127,7 @@ void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs)
 	mlx5_esw_for_each_vf_vport(esw, i, vport, num_vfs) {
 		if (!vport->enabled)
 			continue;
-		mlx5_eswitch_unload_vport(esw, vport->vport);
+		mlx5_eswitch_unload_pf_vf_vport(esw, vport->vport);
 	}
 }
 
@@ -1115,7 +1140,7 @@ static void mlx5_eswitch_unload_ec_vf_vports(struct mlx5_eswitch *esw,
 	mlx5_esw_for_each_ec_vf_vport(esw, i, vport, num_ec_vfs) {
 		if (!vport->enabled)
 			continue;
-		mlx5_eswitch_unload_vport(esw, vport->vport);
+		mlx5_eswitch_unload_pf_vf_vport(esw, vport->vport);
 	}
 }
 
@@ -1127,7 +1152,7 @@ int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
 	int err;
 
 	mlx5_esw_for_each_vf_vport(esw, i, vport, num_vfs) {
-		err = mlx5_eswitch_load_vport(esw, vport->vport, enabled_events);
+		err = mlx5_eswitch_load_pf_vf_vport(esw, vport->vport, enabled_events);
 		if (err)
 			goto vf_err;
 	}
@@ -1147,7 +1172,7 @@ static int mlx5_eswitch_load_ec_vf_vports(struct mlx5_eswitch *esw, u16 num_ec_v
 	int err;
 
 	mlx5_esw_for_each_ec_vf_vport(esw, i, vport, num_ec_vfs) {
-		err = mlx5_eswitch_load_vport(esw, vport->vport, enabled_events);
+		err = mlx5_eswitch_load_pf_vf_vport(esw, vport->vport, enabled_events);
 		if (err)
 			goto vf_err;
 	}
@@ -1189,7 +1214,7 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 	int ret;
 
 	/* Enable PF vport */
-	ret = mlx5_eswitch_load_vport(esw, MLX5_VPORT_PF, enabled_events);
+	ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_PF, enabled_events);
 	if (ret)
 		return ret;
 
@@ -1200,7 +1225,7 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 
 	/* Enable ECPF vport */
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		ret = mlx5_eswitch_load_vport(esw, MLX5_VPORT_ECPF, enabled_events);
+		ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_ECPF, enabled_events);
 		if (ret)
 			goto ecpf_err;
 		if (mlx5_core_ec_sriov_enabled(esw->dev)) {
@@ -1223,11 +1248,11 @@ vf_err:
 		mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs);
 ec_vf_err:
 	if (mlx5_ecpf_vport_exists(esw->dev))
-		mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF);
+		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
 ecpf_err:
 	host_pf_disable_hca(esw->dev);
 pf_hca_err:
-	mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF);
+	mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF);
 	return ret;
 }
 
@@ -1241,11 +1266,11 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
 		if (mlx5_core_ec_sriov_enabled(esw->dev))
 			mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_vfs);
-		mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF);
+		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
 	}
 
 	host_pf_disable_hca(esw->dev);
-	mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF);
+	mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF);
 }
 
 static void mlx5_eswitch_get_devlink_param(struct mlx5_eswitch *esw)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index f3a6a1826e00f..8367c639e234e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -729,6 +729,8 @@ void mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw,
 				   u16 vport,
 				   struct mlx5_flow_spec *spec);
 
+int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num);
+void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num);
 int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num);
 void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num);
 
@@ -736,6 +738,8 @@ int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
 				enum mlx5_eswitch_vport_event enabled_events);
 void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs);
 
+int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num);
+void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num);
 int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num);
 void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num);
 struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index c0b1b7b66cffd..055faaf5dbb7c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2535,6 +2535,22 @@ static void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num
 		__esw_offloads_unload_rep(esw, rep, rep_type);
 }
 
+int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
+		return 0;
+
+	return mlx5_esw_offloads_pf_vf_devlink_port_init(esw, vport_num);
+}
+
+void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
+		return;
+
+	mlx5_esw_offloads_pf_vf_devlink_port_cleanup(esw, vport_num);
+}
+
 int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	int err;
-- 
GitLab


From 382fe5747b8a2f5057f515ee67bdcc2d0ccd9240 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 26 May 2023 15:05:29 +0200
Subject: [PATCH 1544/1806] net/mlx5: Allow
 mlx5_esw_offloads_devlink_port_register() to register SFs

Currently there is a separate set of functions used to
register/unregister the SF. The only difference is currently the ops
struct. Move the struct up and use it for SFs in
mlx5_esw_offloads_devlink_port_register().

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/esw/devlink_port.c     | 37 +++++++++++--------
 1 file changed, 21 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 5e8557f7564c4..60e25fbaef5fd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -139,9 +139,24 @@ static void mlx5_esw_offloads_sf_devlink_port_cleanup(struct mlx5_eswitch *esw,
 	vport->dl_port = NULL;
 }
 
+static const struct devlink_port_ops mlx5_esw_dl_sf_port_ops = {
+#ifdef CONFIG_MLX5_SF_MANAGER
+	.port_del = mlx5_devlink_sf_port_del,
+#endif
+	.port_fn_hw_addr_get = mlx5_devlink_port_fn_hw_addr_get,
+	.port_fn_hw_addr_set = mlx5_devlink_port_fn_hw_addr_set,
+	.port_fn_roce_get = mlx5_devlink_port_fn_roce_get,
+	.port_fn_roce_set = mlx5_devlink_port_fn_roce_set,
+#ifdef CONFIG_MLX5_SF_MANAGER
+	.port_fn_state_get = mlx5_devlink_sf_port_fn_state_get,
+	.port_fn_state_set = mlx5_devlink_sf_port_fn_state_set,
+#endif
+};
+
 int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct mlx5_core_dev *dev = esw->dev;
+	const struct devlink_port_ops *ops;
 	struct devlink_port *dl_port;
 	unsigned int dl_port_index;
 	struct mlx5_vport *vport;
@@ -156,10 +171,14 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 	if (!dl_port)
 		return 0;
 
+	if (mlx5_esw_is_sf_vport(esw, vport_num))
+		ops = &mlx5_esw_dl_sf_port_ops;
+	else
+		ops = &mlx5_esw_pf_vf_dl_port_ops;
+
 	devlink = priv_to_devlink(dev);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num);
-	err = devl_port_register_with_ops(devlink, dl_port, dl_port_index,
-					  &mlx5_esw_pf_vf_dl_port_ops);
+	err = devl_port_register_with_ops(devlink, dl_port, dl_port_index, ops);
 	if (err)
 		return err;
 
@@ -196,20 +215,6 @@ struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u1
 	return IS_ERR(vport) ? ERR_CAST(vport) : vport->dl_port;
 }
 
-static const struct devlink_port_ops mlx5_esw_dl_sf_port_ops = {
-#ifdef CONFIG_MLX5_SF_MANAGER
-	.port_del = mlx5_devlink_sf_port_del,
-#endif
-	.port_fn_hw_addr_get = mlx5_devlink_port_fn_hw_addr_get,
-	.port_fn_hw_addr_set = mlx5_devlink_port_fn_hw_addr_set,
-	.port_fn_roce_get = mlx5_devlink_port_fn_roce_get,
-	.port_fn_roce_set = mlx5_devlink_port_fn_roce_set,
-#ifdef CONFIG_MLX5_SF_MANAGER
-	.port_fn_state_get = mlx5_devlink_sf_port_fn_state_get,
-	.port_fn_state_set = mlx5_devlink_sf_port_fn_state_set,
-#endif
-};
-
 int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port,
 				      u16 vport_num, u32 controller, u32 sfnum)
 {
-- 
GitLab


From e855afd715656a9f25cf62fa68d99c33213b83b7 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 26 May 2023 15:01:47 +0200
Subject: [PATCH 1545/1806] net/mlx5: Introduce
 mlx5_eswitch_load/unload_sf_vport() and use it from SF code

Similar to the PF/VF helpers, introduce a set of load/unload helpers
for SF vports. From there, call mlx5_eswitch_load/unload_vport() which
are common for PFs/VFs and newly introduced SF helpers.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/esw/devlink_port.c     |  8 +++---
 .../net/ethernet/mellanox/mlx5/core/eswitch.c | 27 +++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/eswitch.h | 17 ++++++++++++
 .../mellanox/mlx5/core/eswitch_offloads.c     | 12 +++++++++
 .../ethernet/mellanox/mlx5/core/sf/devlink.c  |  8 +++---
 5 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 60e25fbaef5fd..540bebd93ea58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -112,9 +112,9 @@ static void mlx5_esw_offloads_sf_devlink_port_attrs_set(struct mlx5_eswitch *esw
 	devlink_port_attrs_pci_sf_set(dl_port, controller, pfnum, sfnum, !!controller);
 }
 
-static int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num,
-						  struct devlink_port *dl_port,
-						  u32 controller, u32 sfnum)
+int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num,
+					   struct devlink_port *dl_port,
+					   u32 controller, u32 sfnum)
 {
 	struct mlx5_vport *vport;
 
@@ -128,7 +128,7 @@ static int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, u16
 	return 0;
 }
 
-static void mlx5_esw_offloads_sf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_offloads_sf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct mlx5_vport *vport;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 76d05e2337704..f77237401ee9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1119,6 +1119,33 @@ static void mlx5_eswitch_unload_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_
 	mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport_num);
 }
 
+int mlx5_eswitch_load_sf_vport(struct mlx5_eswitch *esw, u16 vport_num,
+			       enum mlx5_eswitch_vport_event enabled_events,
+			       struct devlink_port *dl_port, u32 controller, u32 sfnum)
+{
+	int err;
+
+	err = mlx5_esw_offloads_init_sf_rep(esw, vport_num, dl_port, controller, sfnum);
+	if (err)
+		return err;
+
+	err = mlx5_eswitch_load_vport(esw, vport_num, enabled_events);
+	if (err)
+		goto err_load;
+
+	return 0;
+
+err_load:
+	mlx5_esw_offloads_cleanup_sf_rep(esw, vport_num);
+	return err;
+}
+
+void mlx5_eswitch_unload_sf_vport(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	mlx5_eswitch_unload_vport(esw, vport_num);
+	mlx5_esw_offloads_cleanup_sf_rep(esw, vport_num);
+}
+
 void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs)
 {
 	struct mlx5_vport *vport;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 8367c639e234e..89efeffa075d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -731,15 +731,32 @@ void mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw,
 
 int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num);
 void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num);
+
+int mlx5_esw_offloads_init_sf_rep(struct mlx5_eswitch *esw, u16 vport_num,
+				  struct devlink_port *dl_port,
+				  u32 controller, u32 sfnum);
+void mlx5_esw_offloads_cleanup_sf_rep(struct mlx5_eswitch *esw, u16 vport_num);
+
 int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num);
 void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num);
 
+int mlx5_eswitch_load_sf_vport(struct mlx5_eswitch *esw, u16 vport_num,
+			       enum mlx5_eswitch_vport_event enabled_events,
+			       struct devlink_port *dl_port, u32 controller, u32 sfnum);
+void mlx5_eswitch_unload_sf_vport(struct mlx5_eswitch *esw, u16 vport_num);
+
 int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
 				enum mlx5_eswitch_vport_event enabled_events);
 void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs);
 
 int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num);
 void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num);
+
+int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num,
+					   struct devlink_port *dl_port,
+					   u32 controller, u32 sfnum);
+void mlx5_esw_offloads_sf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num);
+
 int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num);
 void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num);
 struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 055faaf5dbb7c..998e56cf43db7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2551,6 +2551,18 @@ void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num
 	mlx5_esw_offloads_pf_vf_devlink_port_cleanup(esw, vport_num);
 }
 
+int mlx5_esw_offloads_init_sf_rep(struct mlx5_eswitch *esw, u16 vport_num,
+				  struct devlink_port *dl_port,
+				  u32 controller, u32 sfnum)
+{
+	return mlx5_esw_offloads_sf_devlink_port_init(esw, vport_num, dl_port, controller, sfnum);
+}
+
+void mlx5_esw_offloads_cleanup_sf_rep(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	mlx5_esw_offloads_sf_devlink_port_cleanup(esw, vport_num);
+}
+
 int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	int err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index 6a3fa30b2bf20..f7bdbeb92eb3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -292,8 +292,8 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
 	if (IS_ERR(sf))
 		return PTR_ERR(sf);
 
-	err = mlx5_esw_offloads_sf_vport_enable(esw, &sf->dl_port, sf->hw_fn_id,
-						new_attr->controller, new_attr->sfnum);
+	err = mlx5_eswitch_load_sf_vport(esw, sf->hw_fn_id, MLX5_VPORT_UC_ADDR_CHANGE,
+					 &sf->dl_port, new_attr->controller, new_attr->sfnum);
 	if (err)
 		goto esw_err;
 	*dl_port = &sf->dl_port;
@@ -400,7 +400,7 @@ int mlx5_devlink_sf_port_del(struct devlink *devlink,
 		goto sf_err;
 	}
 
-	mlx5_esw_offloads_sf_vport_disable(esw, sf->hw_fn_id);
+	mlx5_eswitch_unload_sf_vport(esw, sf->hw_fn_id);
 	mlx5_sf_id_erase(table, sf);
 
 	mutex_lock(&table->sf_state_lock);
@@ -472,7 +472,7 @@ static void mlx5_sf_deactivate_all(struct mlx5_sf_table *table)
 	 * arrive. It is safe to destroy all user created SFs.
 	 */
 	xa_for_each(&table->port_indices, index, sf) {
-		mlx5_esw_offloads_sf_vport_disable(esw, sf->hw_fn_id);
+		mlx5_eswitch_unload_sf_vport(esw, sf->hw_fn_id);
 		mlx5_sf_id_erase(table, sf);
 		mlx5_sf_dealloc(table, sf);
 	}
-- 
GitLab


From b940ec4b25beec39358f483d01a19144b88ee1aa Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 26 May 2023 15:12:55 +0200
Subject: [PATCH 1546/1806] net/mlx5: Remove no longer used
 mlx5_esw_offloads_sf_vport_enable/disable()

Since the previous patch removed the only users of these functions,
remove them.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/esw/devlink_port.c     | 53 -------------------
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  7 ---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 32 -----------
 3 files changed, 92 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 540bebd93ea58..b778935074769 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -214,56 +214,3 @@ struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u1
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
 	return IS_ERR(vport) ? ERR_CAST(vport) : vport->dl_port;
 }
-
-int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port,
-				      u16 vport_num, u32 controller, u32 sfnum)
-{
-	struct mlx5_core_dev *dev = esw->dev;
-	unsigned int dl_port_index;
-	struct mlx5_vport *vport;
-	struct devlink *devlink;
-	int err;
-
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
-
-	err = mlx5_esw_offloads_sf_devlink_port_init(esw, vport_num, dl_port, controller, sfnum);
-	if (err)
-		return err;
-
-	devlink = priv_to_devlink(dev);
-	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num);
-	err = devl_port_register_with_ops(devlink, dl_port, dl_port_index,
-					  &mlx5_esw_dl_sf_port_ops);
-	if (err)
-		goto reg_err;
-
-	err = devl_rate_leaf_create(dl_port, vport, NULL);
-	if (err)
-		goto rate_err;
-
-	return 0;
-
-rate_err:
-	devl_port_unregister(dl_port);
-
-reg_err:
-	mlx5_esw_offloads_sf_devlink_port_cleanup(esw, vport_num);
-	return err;
-}
-
-void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num)
-{
-	struct mlx5_vport *vport;
-
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return;
-
-	mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
-	devl_rate_leaf_destroy(vport->dl_port);
-
-	devl_port_unregister(vport->dl_port);
-	mlx5_esw_offloads_sf_devlink_port_cleanup(esw, vport_num);
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 89efeffa075d9..e1e808105e989 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -761,13 +761,6 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num);
 struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num);
 
-int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port,
-				      u16 vport_num, u32 controller, u32 sfnum);
-void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num);
-
-int mlx5_esw_offloads_sf_vport_enable(struct mlx5_eswitch *esw, struct devlink_port *dl_port,
-				      u16 vport_num, u32 controller, u32 sfnum);
-void mlx5_esw_offloads_sf_vport_disable(struct mlx5_eswitch *esw, u16 vport_num);
 int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 *sf_base_id);
 
 int mlx5_esw_vport_vhca_id_set(struct mlx5_eswitch *esw, u16 vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 998e56cf43db7..4b03f2bf605d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4130,38 +4130,6 @@ u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw,
 }
 EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);
 
-int mlx5_esw_offloads_sf_vport_enable(struct mlx5_eswitch *esw, struct devlink_port *dl_port,
-				      u16 vport_num, u32 controller, u32 sfnum)
-{
-	int err;
-
-	err = mlx5_esw_vport_enable(esw, vport_num, MLX5_VPORT_UC_ADDR_CHANGE);
-	if (err)
-		return err;
-
-	err = mlx5_esw_devlink_sf_port_register(esw, dl_port, vport_num, controller, sfnum);
-	if (err)
-		goto devlink_err;
-
-	err = mlx5_esw_offloads_rep_load(esw, vport_num);
-	if (err)
-		goto rep_err;
-	return 0;
-
-rep_err:
-	mlx5_esw_devlink_sf_port_unregister(esw, vport_num);
-devlink_err:
-	mlx5_esw_vport_disable(esw, vport_num);
-	return err;
-}
-
-void mlx5_esw_offloads_sf_vport_disable(struct mlx5_eswitch *esw, u16 vport_num)
-{
-	mlx5_esw_offloads_rep_unload(esw, vport_num);
-	mlx5_esw_devlink_sf_port_unregister(esw, vport_num);
-	mlx5_esw_vport_disable(esw, vport_num);
-}
-
 static int mlx5_esw_query_vport_vhca_id(struct mlx5_eswitch *esw, u16 vport_num, u16 *vhca_id)
 {
 	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-- 
GitLab


From 13f878a22c20d1c0e1d8ffa7aa97c33519b5bd7c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 1 Jun 2023 09:09:12 +0200
Subject: [PATCH 1547/1806] net/mlx5: Don't register ops for non-PF/VF/SF port
 and avoid checks in ops

Currently each PF/VF/SF devlink port op called into mlx5 code calls
is_port_function_supported() to check if the port is either
PF, VF or SF. So make sure that the ops are registered with devlink
port only for those and avoid the is_port_function_supported() checks
in ops.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/esw/devlink_port.c      |  4 +++-
 .../net/ethernet/mellanox/mlx5/core/eswitch.c  |  6 ++++++
 .../net/ethernet/mellanox/mlx5/core/eswitch.h  |  1 +
 .../mellanox/mlx5/core/eswitch_offloads.c      | 18 ------------------
 4 files changed, 10 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index b778935074769..69084673e7e68 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -173,8 +173,10 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 
 	if (mlx5_esw_is_sf_vport(esw, vport_num))
 		ops = &mlx5_esw_dl_sf_port_ops;
-	else
+	else if (mlx5_eswitch_is_pf_vf_vport(esw, vport_num))
 		ops = &mlx5_esw_pf_vf_dl_port_ops;
+	else
+		ops = NULL;
 
 	devlink = priv_to_devlink(dev);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index f77237401ee9e..5d8d4a4f3e4eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1970,6 +1970,12 @@ bool mlx5_eswitch_is_vf_vport(struct mlx5_eswitch *esw, u16 vport_num)
 	return mlx5_esw_check_port_type(esw, vport_num, MLX5_ESW_VPT_VF);
 }
 
+bool mlx5_eswitch_is_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	return vport_num == MLX5_VPORT_PF ||
+		mlx5_eswitch_is_vf_vport(esw, vport_num);
+}
+
 bool mlx5_esw_is_sf_vport(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	return mlx5_esw_check_port_type(esw, vport_num, MLX5_ESW_VPT_SF);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index e1e808105e989..ad2ebd843ed2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -680,6 +680,7 @@ struct mlx5_vport *__must_check
 mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num);
 
 bool mlx5_eswitch_is_vf_vport(struct mlx5_eswitch *esw, u16 vport_num);
+bool mlx5_eswitch_is_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_num);
 bool mlx5_esw_is_sf_vport(struct mlx5_eswitch *esw, u16 vport_num);
 
 int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 4b03f2bf605d7..1aa404218817d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4218,14 +4218,6 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
 }
 EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_set);
 
-static bool
-is_port_function_supported(struct mlx5_eswitch *esw, u16 vport_num)
-{
-	return vport_num == MLX5_VPORT_PF ||
-	       mlx5_eswitch_is_vf_vport(esw, vport_num) ||
-	       mlx5_esw_is_sf_vport(esw, vport_num);
-}
-
 int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port,
 				     u8 *hw_addr, int *hw_addr_len,
 				     struct netlink_ext_ack *extack)
@@ -4239,8 +4231,6 @@ int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port,
 		return PTR_ERR(esw);
 
 	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
-	if (!is_port_function_supported(esw, vport_num))
-		return -EOPNOTSUPP;
 
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
 	if (IS_ERR(vport)) {
@@ -4269,11 +4259,6 @@ int mlx5_devlink_port_fn_hw_addr_set(struct devlink_port *port,
 	}
 
 	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
-	if (!is_port_function_supported(esw, vport_num)) {
-		NL_SET_ERR_MSG_MOD(extack, "Port doesn't support set hw_addr");
-		return -EINVAL;
-	}
-
 	return mlx5_eswitch_set_vport_mac(esw, vport_num, hw_addr);
 }
 
@@ -4286,9 +4271,6 @@ mlx5_devlink_port_fn_get_vport(struct devlink_port *port, struct mlx5_eswitch *e
 		return ERR_PTR(-EOPNOTSUPP);
 
 	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
-	if (!is_port_function_supported(esw, vport_num))
-		return ERR_PTR(-EOPNOTSUPP);
-
 	return mlx5_eswitch_get_vport(esw, vport_num);
 }
 
-- 
GitLab


From 2c5f33f6b9406cc092998cdc96ed015e73cb581b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Wed, 31 May 2023 13:34:19 +0200
Subject: [PATCH 1548/1806] net/mlx5: Embed struct devlink_port into driver
 structure

Struct devlink_port is usually embedded in a driver-specific struct
which allows to carry driver context to devlink port ops.

Introduce a container struct to include devlink_port struct
in preparation to also include driver context for devlink port ops.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/esw/devlink_port.c     | 25 +++++++++++--------
 .../net/ethernet/mellanox/mlx5/core/eswitch.c |  2 +-
 .../net/ethernet/mellanox/mlx5/core/eswitch.h | 12 ++++++---
 .../mellanox/mlx5/core/eswitch_offloads.c     |  2 +-
 .../ethernet/mellanox/mlx5/core/sf/devlink.c  |  4 +--
 5 files changed, 26 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 69084673e7e68..35cf2739a2aa7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -56,7 +56,7 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 
 int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	struct devlink_port *dl_port;
+	struct mlx5_devlink_port *dl_port;
 	struct mlx5_vport *vport;
 
 	if (!mlx5_esw_devlink_port_supported(esw, vport_num))
@@ -70,7 +70,8 @@ int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vpor
 	if (!dl_port)
 		return -ENOMEM;
 
-	mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(esw, vport_num, dl_port);
+	mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(esw, vport_num,
+						       &dl_port->dl_port);
 
 	vport->dl_port = dl_port;
 	return 0;
@@ -113,7 +114,7 @@ static void mlx5_esw_offloads_sf_devlink_port_attrs_set(struct mlx5_eswitch *esw
 }
 
 int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num,
-					   struct devlink_port *dl_port,
+					   struct mlx5_devlink_port *dl_port,
 					   u32 controller, u32 sfnum)
 {
 	struct mlx5_vport *vport;
@@ -122,7 +123,7 @@ int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_n
 	if (IS_ERR(vport))
 		return PTR_ERR(vport);
 
-	mlx5_esw_offloads_sf_devlink_port_attrs_set(esw, dl_port, controller, sfnum);
+	mlx5_esw_offloads_sf_devlink_port_attrs_set(esw, &dl_port->dl_port, controller, sfnum);
 
 	vport->dl_port = dl_port;
 	return 0;
@@ -157,7 +158,7 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 {
 	struct mlx5_core_dev *dev = esw->dev;
 	const struct devlink_port_ops *ops;
-	struct devlink_port *dl_port;
+	struct mlx5_devlink_port *dl_port;
 	unsigned int dl_port_index;
 	struct mlx5_vport *vport;
 	struct devlink *devlink;
@@ -180,33 +181,35 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 
 	devlink = priv_to_devlink(dev);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num);
-	err = devl_port_register_with_ops(devlink, dl_port, dl_port_index, ops);
+	err = devl_port_register_with_ops(devlink, &dl_port->dl_port, dl_port_index, ops);
 	if (err)
 		return err;
 
-	err = devl_rate_leaf_create(dl_port, vport, NULL);
+	err = devl_rate_leaf_create(&dl_port->dl_port, vport, NULL);
 	if (err)
 		goto rate_err;
 
 	return 0;
 
 rate_err:
-	devl_port_unregister(dl_port);
+	devl_port_unregister(&dl_port->dl_port);
 	return err;
 }
 
 void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num)
 {
+	struct mlx5_devlink_port *dl_port;
 	struct mlx5_vport *vport;
 
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
 	if (IS_ERR(vport) || !vport->dl_port)
 		return;
+	dl_port = vport->dl_port;
 
 	mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
-	devl_rate_leaf_destroy(vport->dl_port);
+	devl_rate_leaf_destroy(&dl_port->dl_port);
 
-	devl_port_unregister(vport->dl_port);
+	devl_port_unregister(&dl_port->dl_port);
 }
 
 struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num)
@@ -214,5 +217,5 @@ struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u1
 	struct mlx5_vport *vport;
 
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	return IS_ERR(vport) ? ERR_CAST(vport) : vport->dl_port;
+	return IS_ERR(vport) ? ERR_CAST(vport) : &vport->dl_port->dl_port;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 5d8d4a4f3e4eb..044d0ba9fcf6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1121,7 +1121,7 @@ static void mlx5_eswitch_unload_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_
 
 int mlx5_eswitch_load_sf_vport(struct mlx5_eswitch *esw, u16 vport_num,
 			       enum mlx5_eswitch_vport_event enabled_events,
-			       struct devlink_port *dl_port, u32 controller, u32 sfnum)
+			       struct mlx5_devlink_port *dl_port, u32 controller, u32 sfnum)
 {
 	int err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index ad2ebd843ed2f..b45013465738f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -172,6 +172,10 @@ enum mlx5_eswitch_vport_event {
 	MLX5_VPORT_PROMISC_CHANGE = BIT(3),
 };
 
+struct mlx5_devlink_port {
+	struct devlink_port dl_port;
+};
+
 struct mlx5_vport {
 	struct mlx5_core_dev    *dev;
 	struct hlist_head       uc_list[MLX5_L2_ADDR_HASH_SIZE];
@@ -200,7 +204,7 @@ struct mlx5_vport {
 	bool                    enabled;
 	enum mlx5_eswitch_vport_event enabled_events;
 	int index;
-	struct devlink_port *dl_port;
+	struct mlx5_devlink_port *dl_port;
 };
 
 struct mlx5_esw_indir_table;
@@ -734,7 +738,7 @@ int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num);
 void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num);
 
 int mlx5_esw_offloads_init_sf_rep(struct mlx5_eswitch *esw, u16 vport_num,
-				  struct devlink_port *dl_port,
+				  struct mlx5_devlink_port *dl_port,
 				  u32 controller, u32 sfnum);
 void mlx5_esw_offloads_cleanup_sf_rep(struct mlx5_eswitch *esw, u16 vport_num);
 
@@ -743,7 +747,7 @@ void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num);
 
 int mlx5_eswitch_load_sf_vport(struct mlx5_eswitch *esw, u16 vport_num,
 			       enum mlx5_eswitch_vport_event enabled_events,
-			       struct devlink_port *dl_port, u32 controller, u32 sfnum);
+			       struct mlx5_devlink_port *dl_port, u32 controller, u32 sfnum);
 void mlx5_eswitch_unload_sf_vport(struct mlx5_eswitch *esw, u16 vport_num);
 
 int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
@@ -754,7 +758,7 @@ int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vpor
 void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num);
 
 int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num,
-					   struct devlink_port *dl_port,
+					   struct mlx5_devlink_port *dl_port,
 					   u32 controller, u32 sfnum);
 void mlx5_esw_offloads_sf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 1aa404218817d..b7ece8767ffe9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2552,7 +2552,7 @@ void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num
 }
 
 int mlx5_esw_offloads_init_sf_rep(struct mlx5_eswitch *esw, u16 vport_num,
-				  struct devlink_port *dl_port,
+				  struct mlx5_devlink_port *dl_port,
 				  u32 controller, u32 sfnum)
 {
 	return mlx5_esw_offloads_sf_devlink_port_init(esw, vport_num, dl_port, controller, sfnum);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index f7bdbeb92eb3f..e34a8f88c518c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -12,7 +12,7 @@
 #include "diag/sf_tracepoint.h"
 
 struct mlx5_sf {
-	struct devlink_port dl_port;
+	struct mlx5_devlink_port dl_port;
 	unsigned int port_index;
 	u32 controller;
 	u16 id;
@@ -296,7 +296,7 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
 					 &sf->dl_port, new_attr->controller, new_attr->sfnum);
 	if (err)
 		goto esw_err;
-	*dl_port = &sf->dl_port;
+	*dl_port = &sf->dl_port.dl_port;
 	trace_mlx5_sf_add(dev, sf->port_index, sf->controller, sf->hw_fn_id, new_attr->sfnum);
 	return 0;
 
-- 
GitLab


From 2caa2a39116f07fd06778052a90b3e35bc262c44 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Wed, 31 May 2023 14:14:50 +0200
Subject: [PATCH 1549/1806] net/mlx5: Reduce number of vport lookups passing
 vport pointer instead of index

During devlink port init/cleanup and register/unregister calls, there
are many lookups of vport. Instead of passing vport_num as argument to
functions, pass the vport struct pointer directly and avoid repeated
lookups.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/esw/devlink_port.c     | 47 +++--------
 .../net/ethernet/mellanox/mlx5/core/eswitch.c | 79 +++++++++++--------
 .../net/ethernet/mellanox/mlx5/core/eswitch.h | 30 +++----
 .../mellanox/mlx5/core/eswitch_offloads.c     | 30 +++----
 4 files changed, 90 insertions(+), 96 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 35cf2739a2aa7..2dc7b0bf38c70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -54,18 +54,15 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 	}
 }
 
-int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num)
+int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw,
+					      struct mlx5_vport *vport)
 {
 	struct mlx5_devlink_port *dl_port;
-	struct mlx5_vport *vport;
+	u16 vport_num = vport->vport;
 
 	if (!mlx5_esw_devlink_port_supported(esw, vport_num))
 		return 0;
 
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
-
 	dl_port = kzalloc(sizeof(*dl_port), GFP_KERNEL);
 	if (!dl_port)
 		return -ENOMEM;
@@ -77,12 +74,10 @@ int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vpor
 	return 0;
 }
 
-void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw,
+						  struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport;
-
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport) || !vport->dl_port)
+	if (!vport->dl_port)
 		return;
 
 	kfree(vport->dl_port);
@@ -113,30 +108,18 @@ static void mlx5_esw_offloads_sf_devlink_port_attrs_set(struct mlx5_eswitch *esw
 	devlink_port_attrs_pci_sf_set(dl_port, controller, pfnum, sfnum, !!controller);
 }
 
-int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num,
+int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 					   struct mlx5_devlink_port *dl_port,
 					   u32 controller, u32 sfnum)
 {
-	struct mlx5_vport *vport;
-
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
-
 	mlx5_esw_offloads_sf_devlink_port_attrs_set(esw, &dl_port->dl_port, controller, sfnum);
 
 	vport->dl_port = dl_port;
 	return 0;
 }
 
-void mlx5_esw_offloads_sf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_offloads_sf_devlink_port_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport;
-
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return;
-
 	vport->dl_port = NULL;
 }
 
@@ -154,20 +137,16 @@ static const struct devlink_port_ops mlx5_esw_dl_sf_port_ops = {
 #endif
 };
 
-int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num)
+int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
 	struct mlx5_core_dev *dev = esw->dev;
 	const struct devlink_port_ops *ops;
 	struct mlx5_devlink_port *dl_port;
+	u16 vport_num = vport->vport;
 	unsigned int dl_port_index;
-	struct mlx5_vport *vport;
 	struct devlink *devlink;
 	int err;
 
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
-
 	dl_port = vport->dl_port;
 	if (!dl_port)
 		return 0;
@@ -196,13 +175,11 @@ rate_err:
 	return err;
 }
 
-void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
 	struct mlx5_devlink_port *dl_port;
-	struct mlx5_vport *vport;
 
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport) || !vport->dl_port)
+	if (!vport->dl_port)
 		return;
 	dl_port = vport->dl_port;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 044d0ba9fcf6a..5368b33fde638 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -882,16 +882,12 @@ static void esw_vport_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport
 	esw_vport_cleanup_acl(esw, vport);
 }
 
-int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num,
+int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 			  enum mlx5_eswitch_vport_event enabled_events)
 {
-	struct mlx5_vport *vport;
+	u16 vport_num = vport->vport;
 	int ret;
 
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
-
 	mutex_lock(&esw->state_lock);
 	WARN_ON(vport->enabled);
 
@@ -912,7 +908,7 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num,
 	    (!vport_num && mlx5_core_is_ecpf(esw->dev)))
 		vport->info.trusted = true;
 
-	if (!mlx5_esw_is_manager_vport(esw, vport->vport) &&
+	if (!mlx5_esw_is_manager_vport(esw, vport_num) &&
 	    MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
 		ret = mlx5_esw_vport_vhca_id_set(esw, vport_num);
 		if (ret)
@@ -939,15 +935,12 @@ err_vhca_mapping:
 	return ret;
 }
 
-void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport;
-
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return;
+	u16 vport_num = vport->vport;
 
 	mutex_lock(&esw->state_lock);
+
 	if (!vport->enabled)
 		goto done;
 
@@ -957,9 +950,9 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, u16 vport_num)
 
 	/* Disable events from this vport */
 	if (MLX5_CAP_GEN(esw->dev, log_max_l2_table))
-		arm_vport_context_events_cmd(esw->dev, vport->vport, 0);
+		arm_vport_context_events_cmd(esw->dev, vport_num, 0);
 
-	if (!mlx5_esw_is_manager_vport(esw, vport->vport) &&
+	if (!mlx5_esw_is_manager_vport(esw, vport_num) &&
 	    MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
 		mlx5_esw_vport_vhca_id_clear(esw, vport_num);
 
@@ -1068,82 +1061,104 @@ static void mlx5_eswitch_clear_ec_vf_vports_info(struct mlx5_eswitch *esw)
 	}
 }
 
-static int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num,
+static int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 				   enum mlx5_eswitch_vport_event enabled_events)
 {
 	int err;
 
-	err = mlx5_esw_vport_enable(esw, vport_num, enabled_events);
+	err = mlx5_esw_vport_enable(esw, vport, enabled_events);
 	if (err)
 		return err;
 
-	err = mlx5_esw_offloads_load_rep(esw, vport_num);
+	err = mlx5_esw_offloads_load_rep(esw, vport);
 	if (err)
 		goto err_rep;
 
 	return err;
 
 err_rep:
-	mlx5_esw_vport_disable(esw, vport_num);
+	mlx5_esw_vport_disable(esw, vport);
 	return err;
 }
 
-static void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num)
+static void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
-	mlx5_esw_offloads_unload_rep(esw, vport_num);
-	mlx5_esw_vport_disable(esw, vport_num);
+	mlx5_esw_offloads_unload_rep(esw, vport);
+	mlx5_esw_vport_disable(esw, vport);
 }
 
 static int mlx5_eswitch_load_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_num,
 					 enum mlx5_eswitch_vport_event enabled_events)
 {
+	struct mlx5_vport *vport;
 	int err;
 
-	err = mlx5_esw_offloads_init_pf_vf_rep(esw, vport_num);
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	err = mlx5_esw_offloads_init_pf_vf_rep(esw, vport);
 	if (err)
 		return err;
 
-	err = mlx5_eswitch_load_vport(esw, vport_num, enabled_events);
+	err = mlx5_eswitch_load_vport(esw, vport, enabled_events);
 	if (err)
 		goto err_load;
 	return 0;
 
 err_load:
-	mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport_num);
+	mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport);
 	return err;
 }
 
 static void mlx5_eswitch_unload_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	mlx5_eswitch_unload_vport(esw, vport_num);
-	mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport_num);
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return;
+
+	mlx5_eswitch_unload_vport(esw, vport);
+	mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport);
 }
 
 int mlx5_eswitch_load_sf_vport(struct mlx5_eswitch *esw, u16 vport_num,
 			       enum mlx5_eswitch_vport_event enabled_events,
 			       struct mlx5_devlink_port *dl_port, u32 controller, u32 sfnum)
 {
+	struct mlx5_vport *vport;
 	int err;
 
-	err = mlx5_esw_offloads_init_sf_rep(esw, vport_num, dl_port, controller, sfnum);
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	err = mlx5_esw_offloads_init_sf_rep(esw, vport, dl_port, controller, sfnum);
 	if (err)
 		return err;
 
-	err = mlx5_eswitch_load_vport(esw, vport_num, enabled_events);
+	err = mlx5_eswitch_load_vport(esw, vport, enabled_events);
 	if (err)
 		goto err_load;
 
 	return 0;
 
 err_load:
-	mlx5_esw_offloads_cleanup_sf_rep(esw, vport_num);
+	mlx5_esw_offloads_cleanup_sf_rep(esw, vport);
 	return err;
 }
 
 void mlx5_eswitch_unload_sf_vport(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	mlx5_eswitch_unload_vport(esw, vport_num);
-	mlx5_esw_offloads_cleanup_sf_rep(esw, vport_num);
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return;
+
+	mlx5_eswitch_unload_vport(esw, vport);
+	mlx5_esw_offloads_cleanup_sf_rep(esw, vport);
 }
 
 void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index b45013465738f..8d03d4fe6eec2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -694,9 +694,9 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 				 enum mlx5_eswitch_vport_event enabled_events);
 void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw);
 
-int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num,
+int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 			  enum mlx5_eswitch_vport_event enabled_events);
-void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, u16 vport_num);
+void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 
 int
 esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
@@ -734,16 +734,16 @@ void mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw,
 				   u16 vport,
 				   struct mlx5_flow_spec *spec);
 
-int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num);
-void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num);
+int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 
-int mlx5_esw_offloads_init_sf_rep(struct mlx5_eswitch *esw, u16 vport_num,
+int mlx5_esw_offloads_init_sf_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 				  struct mlx5_devlink_port *dl_port,
 				  u32 controller, u32 sfnum);
-void mlx5_esw_offloads_cleanup_sf_rep(struct mlx5_eswitch *esw, u16 vport_num);
+void mlx5_esw_offloads_cleanup_sf_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 
-int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num);
-void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num);
+int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 
 int mlx5_eswitch_load_sf_vport(struct mlx5_eswitch *esw, u16 vport_num,
 			       enum mlx5_eswitch_vport_event enabled_events,
@@ -754,16 +754,18 @@ int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
 				enum mlx5_eswitch_vport_event enabled_events);
 void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs);
 
-int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num);
-void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num);
+int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw,
+					      struct mlx5_vport *vport);
+void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw,
+						  struct mlx5_vport *vport);
 
-int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num,
+int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 					   struct mlx5_devlink_port *dl_port,
 					   u32 controller, u32 sfnum);
-void mlx5_esw_offloads_sf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num);
+void mlx5_esw_offloads_sf_devlink_port_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 
-int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num);
-void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num);
+int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num);
 
 int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 *sf_base_id);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b7ece8767ffe9..609605c42d6d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2535,63 +2535,63 @@ static void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num
 		__esw_offloads_unload_rep(esw, rep, rep_type);
 }
 
-int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num)
+int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
 	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return 0;
 
-	return mlx5_esw_offloads_pf_vf_devlink_port_init(esw, vport_num);
+	return mlx5_esw_offloads_pf_vf_devlink_port_init(esw, vport);
 }
 
-void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
 	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return;
 
-	mlx5_esw_offloads_pf_vf_devlink_port_cleanup(esw, vport_num);
+	mlx5_esw_offloads_pf_vf_devlink_port_cleanup(esw, vport);
 }
 
-int mlx5_esw_offloads_init_sf_rep(struct mlx5_eswitch *esw, u16 vport_num,
+int mlx5_esw_offloads_init_sf_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 				  struct mlx5_devlink_port *dl_port,
 				  u32 controller, u32 sfnum)
 {
-	return mlx5_esw_offloads_sf_devlink_port_init(esw, vport_num, dl_port, controller, sfnum);
+	return mlx5_esw_offloads_sf_devlink_port_init(esw, vport, dl_port, controller, sfnum);
 }
 
-void mlx5_esw_offloads_cleanup_sf_rep(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_offloads_cleanup_sf_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
-	mlx5_esw_offloads_sf_devlink_port_cleanup(esw, vport_num);
+	mlx5_esw_offloads_sf_devlink_port_cleanup(esw, vport);
 }
 
-int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
+int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
 	int err;
 
 	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return 0;
 
-	err = mlx5_esw_offloads_devlink_port_register(esw, vport_num);
+	err = mlx5_esw_offloads_devlink_port_register(esw, vport);
 	if (err)
 		return err;
 
-	err = mlx5_esw_offloads_rep_load(esw, vport_num);
+	err = mlx5_esw_offloads_rep_load(esw, vport->vport);
 	if (err)
 		goto load_err;
 	return err;
 
 load_err:
-	mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
+	mlx5_esw_offloads_devlink_port_unregister(esw, vport);
 	return err;
 }
 
-void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
 	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return;
 
-	mlx5_esw_offloads_rep_unload(esw, vport_num);
+	mlx5_esw_offloads_rep_unload(esw, vport->vport);
 
-	mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
+	mlx5_esw_offloads_devlink_port_unregister(esw, vport);
 }
 
 static int esw_set_slave_root_fdb(struct mlx5_core_dev *master,
-- 
GitLab


From c0ae0092927222a1399465325ff778a78cc5f826 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 1 Jun 2023 14:16:41 +0200
Subject: [PATCH 1550/1806] net/mlx5: Return -EOPNOTSUPP in
 mlx5_devlink_port_fn_migratable_set() directly

Instead of initializing "err" variable, just return "-EOPNOTSUPP"
directly where it is needed.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 609605c42d6d7..87cc6ad2e17fd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4309,7 +4309,7 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
 	struct mlx5_vport *vport;
 	void *query_ctx;
 	void *hca_caps;
-	int err = -EOPNOTSUPP;
+	int err;
 
 	esw = mlx5_devlink_eswitch_get(port->devlink);
 	if (IS_ERR(esw))
@@ -4317,7 +4317,7 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
 
 	if (!MLX5_CAP_GEN(esw->dev, migration)) {
 		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support migration");
-		return err;
+		return -EOPNOTSUPP;
 	}
 
 	vport = mlx5_devlink_port_fn_get_vport(port, esw);
-- 
GitLab


From 5c632cc352e1ca7995e9ccea9a11f7f9a53b1717 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 1 Jun 2023 13:59:52 +0200
Subject: [PATCH 1551/1806] net/mlx5: Relax mlx5_devlink_eswitch_get() return
 value checking

If called from port ops, it is not needed to perform the checks in
mlx5_devlink_eswitch_get(). The reason is devlink port would not be
registered if the checks are not true. Introduce relaxed version
mlx5_devlink_eswitch_nocheck_get() and use it in port ops.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch.c | 21 ++++++++--
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  6 ++-
 .../mellanox/mlx5/core/eswitch_offloads.c     | 39 ++++---------------
 3 files changed, 29 insertions(+), 37 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 5368b33fde638..db1c2a0763643 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -77,18 +77,31 @@ static int mlx5_eswitch_check(const struct mlx5_core_dev *dev)
 	return 0;
 }
 
-struct mlx5_eswitch *mlx5_devlink_eswitch_get(struct devlink *devlink)
+static struct mlx5_eswitch *__mlx5_devlink_eswitch_get(struct devlink *devlink, bool check)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	int err;
 
-	err = mlx5_eswitch_check(dev);
-	if (err)
-		return ERR_PTR(err);
+	if (check) {
+		err = mlx5_eswitch_check(dev);
+		if (err)
+			return ERR_PTR(err);
+	}
 
 	return dev->priv.eswitch;
 }
 
+struct mlx5_eswitch *__must_check
+mlx5_devlink_eswitch_get(struct devlink *devlink)
+{
+	return __mlx5_devlink_eswitch_get(devlink, true);
+}
+
+struct mlx5_eswitch *mlx5_devlink_eswitch_nocheck_get(struct devlink *devlink)
+{
+	return __mlx5_devlink_eswitch_get(devlink, false);
+}
+
 struct mlx5_vport *__must_check
 mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 8d03d4fe6eec2..9f94c3d6d6e55 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -679,7 +679,11 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
 			  MLX5_CAP_GEN_2((esw->dev), ec_vf_vport_base) +\
 			  (last) - 1)
 
-struct mlx5_eswitch *mlx5_devlink_eswitch_get(struct devlink *devlink);
+struct mlx5_eswitch *__must_check
+mlx5_devlink_eswitch_get(struct devlink *devlink);
+
+struct mlx5_eswitch *mlx5_devlink_eswitch_nocheck_get(struct devlink *devlink);
+
 struct mlx5_vport *__must_check
 mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 87cc6ad2e17fd..23b562f07c68d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3634,7 +3634,7 @@ static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink)
 	struct net *devl_net, *netdev_net;
 	struct mlx5_eswitch *esw;
 
-	esw = mlx5_devlink_eswitch_get(devlink);
+	esw = mlx5_devlink_eswitch_nocheck_get(devlink);
 	netdev_net = dev_net(esw->dev->mlx5e_res.uplink_netdev);
 	devl_net = devlink_net(devlink);
 
@@ -4222,13 +4222,10 @@ int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port,
 				     u8 *hw_addr, int *hw_addr_len,
 				     struct netlink_ext_ack *extack)
 {
-	struct mlx5_eswitch *esw;
+	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
 	struct mlx5_vport *vport;
 	u16 vport_num;
 
-	esw = mlx5_devlink_eswitch_get(port->devlink);
-	if (IS_ERR(esw))
-		return PTR_ERR(esw);
 
 	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
 
@@ -4249,15 +4246,9 @@ int mlx5_devlink_port_fn_hw_addr_set(struct devlink_port *port,
 				     const u8 *hw_addr, int hw_addr_len,
 				     struct netlink_ext_ack *extack)
 {
-	struct mlx5_eswitch *esw;
+	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
 	u16 vport_num;
 
-	esw = mlx5_devlink_eswitch_get(port->devlink);
-	if (IS_ERR(esw)) {
-		NL_SET_ERR_MSG_MOD(extack, "Eswitch doesn't support set hw_addr");
-		return PTR_ERR(esw);
-	}
-
 	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
 	return mlx5_eswitch_set_vport_mac(esw, vport_num, hw_addr);
 }
@@ -4277,13 +4268,9 @@ mlx5_devlink_port_fn_get_vport(struct devlink_port *port, struct mlx5_eswitch *e
 int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enabled,
 					struct netlink_ext_ack *extack)
 {
-	struct mlx5_eswitch *esw;
+	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
 	struct mlx5_vport *vport;
 
-	esw = mlx5_devlink_eswitch_get(port->devlink);
-	if (IS_ERR(esw))
-		return PTR_ERR(esw);
-
 	if (!MLX5_CAP_GEN(esw->dev, migration)) {
 		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support migration");
 		return -EOPNOTSUPP;
@@ -4304,17 +4291,13 @@ int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enab
 int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
 					struct netlink_ext_ack *extack)
 {
+	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
 	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	struct mlx5_eswitch *esw;
 	struct mlx5_vport *vport;
 	void *query_ctx;
 	void *hca_caps;
 	int err;
 
-	esw = mlx5_devlink_eswitch_get(port->devlink);
-	if (IS_ERR(esw))
-		return PTR_ERR(esw);
-
 	if (!MLX5_CAP_GEN(esw->dev, migration)) {
 		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support migration");
 		return -EOPNOTSUPP;
@@ -4368,13 +4351,9 @@ out:
 int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled,
 				  struct netlink_ext_ack *extack)
 {
-	struct mlx5_eswitch *esw;
+	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
 	struct mlx5_vport *vport;
 
-	esw = mlx5_devlink_eswitch_get(port->devlink);
-	if (IS_ERR(esw))
-		return PTR_ERR(esw);
-
 	vport = mlx5_devlink_port_fn_get_vport(port, esw);
 	if (IS_ERR(vport)) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
@@ -4390,18 +4369,14 @@ int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled,
 int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable,
 				  struct netlink_ext_ack *extack)
 {
+	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
 	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	struct mlx5_eswitch *esw;
 	struct mlx5_vport *vport;
 	void *query_ctx;
 	void *hca_caps;
 	u16 vport_num;
 	int err;
 
-	esw = mlx5_devlink_eswitch_get(port->devlink);
-	if (IS_ERR(esw))
-		return PTR_ERR(esw);
-
 	vport = mlx5_devlink_port_fn_get_vport(port, esw);
 	if (IS_ERR(vport)) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
-- 
GitLab


From eb555e34f0841c880f709559d58866ff9d9321a1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 1 Jun 2023 14:13:31 +0200
Subject: [PATCH 1552/1806] net/mlx5: Check vhca_resource_manager capability in
 each op and add extack msg

Since the follow-up patch is going to remove
mlx5_devlink_port_fn_get_vport() entirely, move the vhca_resource_manager
capability checking to individual ops. Add proper extack message
on the way.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 23 ++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 23b562f07c68d..e4d1744516f7e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4258,9 +4258,6 @@ mlx5_devlink_port_fn_get_vport(struct devlink_port *port, struct mlx5_eswitch *e
 {
 	u16 vport_num;
 
-	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
-		return ERR_PTR(-EOPNOTSUPP);
-
 	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
 	return mlx5_eswitch_get_vport(esw, vport_num);
 }
@@ -4276,6 +4273,11 @@ int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enab
 		return -EOPNOTSUPP;
 	}
 
+	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support VHCA management");
+		return -EOPNOTSUPP;
+	}
+
 	vport = mlx5_devlink_port_fn_get_vport(port, esw);
 	if (IS_ERR(vport)) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
@@ -4303,6 +4305,11 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
 		return -EOPNOTSUPP;
 	}
 
+	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support VHCA management");
+		return -EOPNOTSUPP;
+	}
+
 	vport = mlx5_devlink_port_fn_get_vport(port, esw);
 	if (IS_ERR(vport)) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
@@ -4354,6 +4361,11 @@ int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled,
 	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
 	struct mlx5_vport *vport;
 
+	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support VHCA management");
+		return -EOPNOTSUPP;
+	}
+
 	vport = mlx5_devlink_port_fn_get_vport(port, esw);
 	if (IS_ERR(vport)) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
@@ -4377,6 +4389,11 @@ int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable,
 	u16 vport_num;
 	int err;
 
+	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support VHCA management");
+		return -EOPNOTSUPP;
+	}
+
 	vport = mlx5_devlink_port_fn_get_vport(port, esw);
 	if (IS_ERR(vport)) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
-- 
GitLab


From 7d8335200c94f6f76fbc3a1682993888bc4eb665 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Wed, 31 May 2023 13:36:43 +0200
Subject: [PATCH 1553/1806] net/mlx5: Store vport in struct mlx5_devlink_port
 and use it in port ops

Instead of using internal devlink_port->index to perform vport lookup in
every devlink port op, store the vport pointer to the container struct
mlx5_devlink_port and use it directly in port ops.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/esw/devlink_port.c     |  2 +
 .../net/ethernet/mellanox/mlx5/core/eswitch.h | 19 ++++++
 .../mellanox/mlx5/core/eswitch_offloads.c     | 61 +++----------------
 3 files changed, 29 insertions(+), 53 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 2dc7b0bf38c70..3c254a7100066 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -71,6 +71,7 @@ int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw,
 						       &dl_port->dl_port);
 
 	vport->dl_port = dl_port;
+	mlx5_devlink_port_init(dl_port, vport);
 	return 0;
 }
 
@@ -115,6 +116,7 @@ int mlx5_esw_offloads_sf_devlink_port_init(struct mlx5_eswitch *esw, struct mlx5
 	mlx5_esw_offloads_sf_devlink_port_attrs_set(esw, &dl_port->dl_port, controller, sfnum);
 
 	vport->dl_port = dl_port;
+	mlx5_devlink_port_init(dl_port, vport);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 9f94c3d6d6e55..6fcece69d3bea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -172,10 +172,29 @@ enum mlx5_eswitch_vport_event {
 	MLX5_VPORT_PROMISC_CHANGE = BIT(3),
 };
 
+struct mlx5_vport;
+
 struct mlx5_devlink_port {
 	struct devlink_port dl_port;
+	struct mlx5_vport *vport;
 };
 
+static inline void mlx5_devlink_port_init(struct mlx5_devlink_port *dl_port,
+					  struct mlx5_vport *vport)
+{
+	dl_port->vport = vport;
+}
+
+static inline struct mlx5_devlink_port *mlx5_devlink_port_get(struct devlink_port *dl_port)
+{
+	return container_of(dl_port, struct mlx5_devlink_port, dl_port);
+}
+
+static inline struct mlx5_vport *mlx5_devlink_port_vport_get(struct devlink_port *dl_port)
+{
+	return mlx5_devlink_port_get(dl_port)->vport;
+}
+
 struct mlx5_vport {
 	struct mlx5_core_dev    *dev;
 	struct hlist_head       uc_list[MLX5_L2_ADDR_HASH_SIZE];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index e4d1744516f7e..67eab99f95b18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4223,17 +4223,7 @@ int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port,
 				     struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
-	struct mlx5_vport *vport;
-	u16 vport_num;
-
-
-	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
-
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport)) {
-		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
-		return PTR_ERR(vport);
-	}
+	struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
 
 	mutex_lock(&esw->state_lock);
 	ether_addr_copy(hw_addr, vport->info.mac);
@@ -4247,26 +4237,16 @@ int mlx5_devlink_port_fn_hw_addr_set(struct devlink_port *port,
 				     struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
-	u16 vport_num;
+	struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
 
-	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
-	return mlx5_eswitch_set_vport_mac(esw, vport_num, hw_addr);
-}
-
-static struct mlx5_vport *
-mlx5_devlink_port_fn_get_vport(struct devlink_port *port, struct mlx5_eswitch *esw)
-{
-	u16 vport_num;
-
-	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
-	return mlx5_eswitch_get_vport(esw, vport_num);
+	return mlx5_eswitch_set_vport_mac(esw, vport->vport, hw_addr);
 }
 
 int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enabled,
 					struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
-	struct mlx5_vport *vport;
+	struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
 
 	if (!MLX5_CAP_GEN(esw->dev, migration)) {
 		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support migration");
@@ -4278,12 +4258,6 @@ int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enab
 		return -EOPNOTSUPP;
 	}
 
-	vport = mlx5_devlink_port_fn_get_vport(port, esw);
-	if (IS_ERR(vport)) {
-		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
-		return PTR_ERR(vport);
-	}
-
 	mutex_lock(&esw->state_lock);
 	*is_enabled = vport->info.mig_enabled;
 	mutex_unlock(&esw->state_lock);
@@ -4294,8 +4268,8 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
 					struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
+	struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
 	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	struct mlx5_vport *vport;
 	void *query_ctx;
 	void *hca_caps;
 	int err;
@@ -4310,12 +4284,6 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
 		return -EOPNOTSUPP;
 	}
 
-	vport = mlx5_devlink_port_fn_get_vport(port, esw);
-	if (IS_ERR(vport)) {
-		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
-		return PTR_ERR(vport);
-	}
-
 	mutex_lock(&esw->state_lock);
 
 	if (vport->info.mig_enabled == enable) {
@@ -4359,19 +4327,13 @@ int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled,
 				  struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
-	struct mlx5_vport *vport;
+	struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
 
 	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
 		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support VHCA management");
 		return -EOPNOTSUPP;
 	}
 
-	vport = mlx5_devlink_port_fn_get_vport(port, esw);
-	if (IS_ERR(vport)) {
-		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
-		return PTR_ERR(vport);
-	}
-
 	mutex_lock(&esw->state_lock);
 	*is_enabled = vport->info.roce_enabled;
 	mutex_unlock(&esw->state_lock);
@@ -4382,11 +4344,11 @@ int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable,
 				  struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
+	struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
 	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	struct mlx5_vport *vport;
+	u16 vport_num = vport->vport;
 	void *query_ctx;
 	void *hca_caps;
-	u16 vport_num;
 	int err;
 
 	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
@@ -4394,13 +4356,6 @@ int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable,
 		return -EOPNOTSUPP;
 	}
 
-	vport = mlx5_devlink_port_fn_get_vport(port, esw);
-	if (IS_ERR(vport)) {
-		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
-		return PTR_ERR(vport);
-	}
-	vport_num = vport->vport;
-
 	mutex_lock(&esw->state_lock);
 
 	if (vport->info.roce_enabled == enable) {
-- 
GitLab


From c338325f7a18b1b5e04f4fc21672cf8956072733 Mon Sep 17 00:00:00 2001
From: Emeel Hakim <ehakim@nvidia.com>
Date: Tue, 8 Aug 2023 22:14:54 +0300
Subject: [PATCH 1554/1806] net/mlx5e: Support IPsec upper protocol selector
 field offload for RX

Support RX policy/state upper protocol selector field offload,
to enable selecting RX traffic for IPsec operation based on l4
protocol UDP with specific source/destination port.

Signed-off-by: Emeel Hakim <ehakim@nvidia.com>
Reviewed-by: Raed Salem <raeds@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c   | 10 ++++------
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c    |  2 ++
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index a577f0edabe86..2bbe232c2ffa7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -440,9 +440,8 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev,
 		return -EINVAL;
 	}
 
-	if (x->sel.proto != IPPROTO_IP &&
-	    (x->sel.proto != IPPROTO_UDP || x->xso.dir != XFRM_DEV_OFFLOAD_OUT)) {
-		NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than UDP, and only Tx direction");
+	if (x->sel.proto != IPPROTO_IP && x->sel.proto != IPPROTO_UDP) {
+		NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than UDP");
 		return -EINVAL;
 	}
 
@@ -983,9 +982,8 @@ static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev,
 		return -EINVAL;
 	}
 
-	if (sel->proto != IPPROTO_IP &&
-	    (sel->proto != IPPROTO_UDP || x->xdo.dir != XFRM_DEV_OFFLOAD_OUT)) {
-		NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than UDP, and only Tx direction");
+	if (x->selector.proto != IPPROTO_IP && x->selector.proto != IPPROTO_UDP) {
+		NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than UDP");
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 3781c72d97f1a..f5e29b7f5ba0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -1243,6 +1243,7 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	setup_fte_spi(spec, attrs->spi);
 	setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
+	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
 	if (rx != ipsec->rx_esw)
 		err = setup_modify_header(ipsec, attrs->type,
@@ -1519,6 +1520,7 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
 
 	setup_fte_no_frags(spec);
+	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
 	switch (attrs->action) {
 	case XFRM_POLICY_ALLOW:
-- 
GitLab


From b8c697e177bba0f802232c3f06b7769b1e1fc516 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 8 Aug 2023 22:14:55 +0300
Subject: [PATCH 1555/1806] net/mlx5e: Support IPsec upper TCP protocol
 selector

Support TCP as protocol selector for policy and state in IPsec
packet offload mode.

Example of state configuration is as follows:
  ip xfrm state add src 192.168.25.3 dst 192.168.25.1 \
	proto esp spi 1001 reqid 10001 aead 'rfc4106(gcm(aes))' \
	0x54a7588d36873b031e4bd46301be5a86b3a53879 128 mode transport \
	offload packet dev re0 dir in sel src 192.168.25.3 dst 192.168.25.1 \
	proto tcp dport 9003

Acked-by: Raed Salem <raeds@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec.c       | 11 +++--
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 43 +++++++++++++------
 2 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 2bbe232c2ffa7..3b88a8bb70822 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -440,8 +440,9 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev,
 		return -EINVAL;
 	}
 
-	if (x->sel.proto != IPPROTO_IP && x->sel.proto != IPPROTO_UDP) {
-		NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than UDP");
+	if (x->sel.proto != IPPROTO_IP && x->sel.proto != IPPROTO_UDP &&
+	    x->sel.proto != IPPROTO_TCP) {
+		NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than TCP/UDP");
 		return -EINVAL;
 	}
 
@@ -982,8 +983,10 @@ static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev,
 		return -EINVAL;
 	}
 
-	if (x->selector.proto != IPPROTO_IP && x->selector.proto != IPPROTO_UDP) {
-		NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than UDP");
+	if (x->selector.proto != IPPROTO_IP &&
+	    x->selector.proto != IPPROTO_UDP &&
+	    x->selector.proto != IPPROTO_TCP) {
+		NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than TCP/UDP");
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index f5e29b7f5ba0e..a1cfddd05bc4b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -936,23 +936,42 @@ static void setup_fte_reg_c4(struct mlx5_flow_spec *spec, u32 reqid)
 
 static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upspec *upspec)
 {
-	if (upspec->proto != IPPROTO_UDP)
+	switch (upspec->proto) {
+	case IPPROTO_UDP:
+		if (upspec->dport) {
+			MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria,
+				 udp_dport, upspec->dport_mask);
+			MLX5_SET(fte_match_set_lyr_2_4, spec->match_value,
+				 udp_dport, upspec->dport);
+		}
+		if (upspec->sport) {
+			MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria,
+				 udp_sport, upspec->sport_mask);
+			MLX5_SET(fte_match_set_lyr_2_4, spec->match_value,
+				 udp_sport, upspec->sport);
+		}
+		break;
+	case IPPROTO_TCP:
+		if (upspec->dport) {
+			MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria,
+				 tcp_dport, upspec->dport_mask);
+			MLX5_SET(fte_match_set_lyr_2_4, spec->match_value,
+				 tcp_dport, upspec->dport);
+		}
+		if (upspec->sport) {
+			MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria,
+				 tcp_sport, upspec->sport_mask);
+			MLX5_SET(fte_match_set_lyr_2_4, spec->match_value,
+				 tcp_sport, upspec->sport);
+		}
+		break;
+	default:
 		return;
+	}
 
 	spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
 	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, spec->match_criteria, ip_protocol);
 	MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, ip_protocol, upspec->proto);
-	if (upspec->dport) {
-		MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_dport,
-			 upspec->dport_mask);
-		MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_dport, upspec->dport);
-	}
-
-	if (upspec->sport) {
-		MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_sport,
-			 upspec->sport_mask);
-		MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_sport, upspec->sport);
-	}
 }
 
 static enum mlx5_flow_namespace_type ipsec_fs_get_ns(struct mlx5e_ipsec *ipsec,
-- 
GitLab


From bdf79b128685458fecc42cd8709375d46407dae2 Mon Sep 17 00:00:00 2001
From: Sai Krishna <saikrishnag@marvell.com>
Date: Mon, 21 Aug 2023 16:06:29 +0530
Subject: [PATCH 1556/1806] octeontx2-pf: Use PTP HW timestamp counter atomic
 update feature

Some of the newer silicon versions in CN10K series supports a feature
where in the current PTP timestamp in HW can be updated atomically
without losing any cpu cycles unlike read/modify/write register.
This patch uses this feature so that PTP accuracy can be improved
while adjusting the master offset in HW. There is no need for SW
timecounter when using this feature. So removed references to SW
timecounter wherever appropriate.

Signed-off-by: Sai Krishna <saikrishnag@marvell.com>
Signed-off-by: Naveen Mamindlapalli <naveenm@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/octeontx2/af/mbox.h  |  12 ++
 .../net/ethernet/marvell/octeontx2/af/ptp.c   | 155 +++++++++++++--
 .../net/ethernet/marvell/octeontx2/af/ptp.h   |   3 +-
 .../net/ethernet/marvell/octeontx2/af/rvu.c   |   2 +-
 .../net/ethernet/marvell/octeontx2/af/rvu.h   |  12 ++
 .../marvell/octeontx2/nic/otx2_common.h       |   1 +
 .../ethernet/marvell/octeontx2/nic/otx2_ptp.c | 177 ++++++++++++++----
 7 files changed, 307 insertions(+), 55 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index e2f2b2179eef3..6b5b06c2b4e99 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -136,6 +136,7 @@ M(GET_HW_CAP,		0x008, get_hw_cap, msg_req, get_hw_cap_rsp)	\
 M(LMTST_TBL_SETUP,	0x00a, lmtst_tbl_setup, lmtst_tbl_setup_req,    \
 				msg_rsp)				\
 M(SET_VF_PERM,		0x00b, set_vf_perm, set_vf_perm, msg_rsp)	\
+M(PTP_GET_CAP,		0x00c, ptp_get_cap, msg_req, ptp_get_cap_rsp)	\
 /* CGX mbox IDs (range 0x200 - 0x3FF) */				\
 M(CGX_START_RXTX,	0x200, cgx_start_rxtx, msg_req, msg_rsp)	\
 M(CGX_STOP_RXTX,	0x201, cgx_stop_rxtx, msg_req, msg_rsp)		\
@@ -1437,6 +1438,12 @@ struct npc_get_kex_cfg_rsp {
 	u8 mkex_pfl_name[MKEX_NAME_LEN];
 };
 
+struct ptp_get_cap_rsp {
+	struct mbox_msghdr hdr;
+#define        PTP_CAP_HW_ATOMIC_UPDATE BIT_ULL(0)
+	u64 cap;
+};
+
 struct flow_msg {
 	unsigned char dmac[6];
 	unsigned char smac[6];
@@ -1568,6 +1575,8 @@ enum ptp_op {
 	PTP_OP_GET_TSTMP = 2,
 	PTP_OP_SET_THRESH = 3,
 	PTP_OP_EXTTS_ON = 4,
+	PTP_OP_ADJTIME = 5,
+	PTP_OP_SET_CLOCK = 6,
 };
 
 struct ptp_req {
@@ -1576,11 +1585,14 @@ struct ptp_req {
 	s64 scaled_ppm;
 	u64 thresh;
 	int extts_on;
+	s64 delta;
+	u64 clk;
 };
 
 struct ptp_rsp {
 	struct mbox_msghdr hdr;
 	u64 clk;
+	u64 tsc;
 };
 
 struct npc_get_field_status_req {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
index c55c2c441a1a7..ffbd22797163f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
@@ -12,8 +12,8 @@
 #include <linux/hrtimer.h>
 #include <linux/ktime.h>
 
-#include "ptp.h"
 #include "mbox.h"
+#include "ptp.h"
 #include "rvu.h"
 
 #define DRV_NAME				"Marvell PTP Driver"
@@ -40,6 +40,7 @@
 #define PTP_CLOCK_CFG_TSTMP_EDGE		BIT_ULL(9)
 #define PTP_CLOCK_CFG_TSTMP_EN			BIT_ULL(8)
 #define PTP_CLOCK_CFG_TSTMP_IN_MASK		GENMASK_ULL(15, 10)
+#define PTP_CLOCK_CFG_ATOMIC_OP_MASK		GENMASK_ULL(28, 26)
 #define PTP_CLOCK_CFG_PPS_EN			BIT_ULL(30)
 #define PTP_CLOCK_CFG_PPS_INV			BIT_ULL(31)
 
@@ -53,36 +54,62 @@
 #define PTP_TIMESTAMP				0xF20ULL
 #define PTP_CLOCK_SEC				0xFD0ULL
 #define PTP_SEC_ROLLOVER			0xFD8ULL
+/* Atomic update related CSRs */
+#define PTP_FRNS_TIMESTAMP			0xFE0ULL
+#define PTP_NXT_ROLLOVER_SET			0xFE8ULL
+#define PTP_CURR_ROLLOVER_SET			0xFF0ULL
+#define PTP_NANO_TIMESTAMP			0xFF8ULL
+#define PTP_SEC_TIMESTAMP			0x1000ULL
 
 #define CYCLE_MULT				1000
 
+#define is_rev_A0(ptp) (((ptp)->pdev->revision & 0x0F) == 0x0)
+#define is_rev_A1(ptp) (((ptp)->pdev->revision & 0x0F) == 0x1)
+
+/* PTP atomic update operation type */
+enum atomic_opcode {
+	ATOMIC_SET = 1,
+	ATOMIC_INC = 3,
+	ATOMIC_DEC = 4
+};
+
 static struct ptp *first_ptp_block;
 static const struct pci_device_id ptp_id_table[];
 
-static bool is_ptp_dev_cnf10kb(struct ptp *ptp)
+static bool is_ptp_dev_cnf10ka(struct ptp *ptp)
 {
-	return ptp->pdev->subsystem_device == PCI_SUBSYS_DEVID_CNF10K_B_PTP;
+	return ptp->pdev->subsystem_device == PCI_SUBSYS_DEVID_CNF10K_A_PTP;
 }
 
-static bool is_ptp_dev_cn10k(struct ptp *ptp)
+static bool is_ptp_dev_cn10ka(struct ptp *ptp)
 {
-	return ptp->pdev->device == PCI_DEVID_CN10K_PTP;
+	return ptp->pdev->subsystem_device == PCI_SUBSYS_DEVID_CN10K_A_PTP;
 }
 
 static bool cn10k_ptp_errata(struct ptp *ptp)
 {
-	if (ptp->pdev->subsystem_device == PCI_SUBSYS_DEVID_CN10K_A_PTP ||
-	    ptp->pdev->subsystem_device == PCI_SUBSYS_DEVID_CNF10K_A_PTP)
+	if ((is_ptp_dev_cn10ka(ptp) || is_ptp_dev_cnf10ka(ptp)) &&
+	    (is_rev_A0(ptp) || is_rev_A1(ptp)))
 		return true;
+
 	return false;
 }
 
-static bool is_ptp_tsfmt_sec_nsec(struct ptp *ptp)
+static bool is_tstmp_atomic_update_supported(struct rvu *rvu)
 {
-	if (ptp->pdev->subsystem_device == PCI_SUBSYS_DEVID_CN10K_A_PTP ||
-	    ptp->pdev->subsystem_device == PCI_SUBSYS_DEVID_CNF10K_A_PTP)
-		return true;
-	return false;
+	struct ptp *ptp = rvu->ptp;
+
+	if (is_rvu_otx2(rvu))
+		return false;
+
+	/* On older silicon variants of CN10K, atomic update feature
+	 * is not available.
+	 */
+	if ((is_ptp_dev_cn10ka(ptp) || is_ptp_dev_cnf10ka(ptp)) &&
+	    (is_rev_A0(ptp) || is_rev_A1(ptp)))
+		return false;
+
+	return true;
 }
 
 static enum hrtimer_restart ptp_reset_thresh(struct hrtimer *hrtimer)
@@ -222,6 +249,65 @@ void ptp_put(struct ptp *ptp)
 	pci_dev_put(ptp->pdev);
 }
 
+static void ptp_atomic_update(struct ptp *ptp, u64 timestamp)
+{
+	u64 regval, curr_rollover_set, nxt_rollover_set;
+
+	/* First setup NSECs and SECs */
+	writeq(timestamp, ptp->reg_base + PTP_NANO_TIMESTAMP);
+	writeq(0, ptp->reg_base + PTP_FRNS_TIMESTAMP);
+	writeq(timestamp / NSEC_PER_SEC,
+	       ptp->reg_base + PTP_SEC_TIMESTAMP);
+
+	nxt_rollover_set = roundup(timestamp, NSEC_PER_SEC);
+	curr_rollover_set = nxt_rollover_set - NSEC_PER_SEC;
+	writeq(nxt_rollover_set, ptp->reg_base + PTP_NXT_ROLLOVER_SET);
+	writeq(curr_rollover_set, ptp->reg_base + PTP_CURR_ROLLOVER_SET);
+
+	/* Now, initiate atomic update */
+	regval = readq(ptp->reg_base + PTP_CLOCK_CFG);
+	regval &= ~PTP_CLOCK_CFG_ATOMIC_OP_MASK;
+	regval |= (ATOMIC_SET << 26);
+	writeq(regval, ptp->reg_base + PTP_CLOCK_CFG);
+}
+
+static void ptp_atomic_adjtime(struct ptp *ptp, s64 delta)
+{
+	bool neg_adj = false, atomic_inc_dec = false;
+	u64 regval, ptp_clock_hi;
+
+	if (delta < 0) {
+		delta = -delta;
+		neg_adj = true;
+	}
+
+	/* use atomic inc/dec when delta < 1 second */
+	if (delta < NSEC_PER_SEC)
+		atomic_inc_dec = true;
+
+	if (!atomic_inc_dec) {
+		ptp_clock_hi = readq(ptp->reg_base + PTP_CLOCK_HI);
+		if (neg_adj) {
+			if (ptp_clock_hi > delta)
+				ptp_clock_hi -= delta;
+			else
+				ptp_clock_hi = delta - ptp_clock_hi;
+		} else {
+			ptp_clock_hi += delta;
+		}
+		ptp_atomic_update(ptp, ptp_clock_hi);
+	} else {
+		writeq(delta, ptp->reg_base + PTP_NANO_TIMESTAMP);
+		writeq(0, ptp->reg_base + PTP_FRNS_TIMESTAMP);
+
+		/* initiate atomic inc/dec */
+		regval = readq(ptp->reg_base + PTP_CLOCK_CFG);
+		regval &= ~PTP_CLOCK_CFG_ATOMIC_OP_MASK;
+		regval |= neg_adj ? (ATOMIC_DEC << 26) : (ATOMIC_INC << 26);
+		writeq(regval, ptp->reg_base + PTP_CLOCK_CFG);
+	}
+}
+
 static int ptp_adjfine(struct ptp *ptp, long scaled_ppm)
 {
 	bool neg_adj = false;
@@ -277,8 +363,9 @@ static int ptp_get_clock(struct ptp *ptp, u64 *clk)
 	return 0;
 }
 
-void ptp_start(struct ptp *ptp, u64 sclk, u32 ext_clk_freq, u32 extts)
+void ptp_start(struct rvu *rvu, u64 sclk, u32 ext_clk_freq, u32 extts)
 {
+	struct ptp *ptp = rvu->ptp;
 	struct pci_dev *pdev;
 	u64 clock_comp;
 	u64 clock_cfg;
@@ -297,8 +384,14 @@ void ptp_start(struct ptp *ptp, u64 sclk, u32 ext_clk_freq, u32 extts)
 	ptp->clock_rate = sclk * 1000000;
 
 	/* Program the seconds rollover value to 1 second */
-	if (is_ptp_dev_cnf10kb(ptp))
+	if (is_tstmp_atomic_update_supported(rvu)) {
+		writeq(0, ptp->reg_base + PTP_NANO_TIMESTAMP);
+		writeq(0, ptp->reg_base + PTP_FRNS_TIMESTAMP);
+		writeq(0, ptp->reg_base + PTP_SEC_TIMESTAMP);
+		writeq(0, ptp->reg_base + PTP_CURR_ROLLOVER_SET);
+		writeq(0x3b9aca00, ptp->reg_base + PTP_NXT_ROLLOVER_SET);
 		writeq(0x3b9aca00, ptp->reg_base + PTP_SEC_ROLLOVER);
+	}
 
 	/* Enable PTP clock */
 	clock_cfg = readq(ptp->reg_base + PTP_CLOCK_CFG);
@@ -320,6 +413,10 @@ void ptp_start(struct ptp *ptp, u64 sclk, u32 ext_clk_freq, u32 extts)
 	clock_cfg |= PTP_CLOCK_CFG_PTP_EN;
 	clock_cfg |= PTP_CLOCK_CFG_PPS_EN | PTP_CLOCK_CFG_PPS_INV;
 	writeq(clock_cfg, ptp->reg_base + PTP_CLOCK_CFG);
+	clock_cfg = readq(ptp->reg_base + PTP_CLOCK_CFG);
+	clock_cfg &= ~PTP_CLOCK_CFG_ATOMIC_OP_MASK;
+	clock_cfg |= (ATOMIC_SET << 26);
+	writeq(clock_cfg, ptp->reg_base + PTP_CLOCK_CFG);
 
 	/* Set 50% duty cycle for 1Hz output */
 	writeq(0x1dcd650000000000, ptp->reg_base + PTP_PPS_HI_INCR);
@@ -350,7 +447,7 @@ static int ptp_get_tstmp(struct ptp *ptp, u64 *clk)
 {
 	u64 timestamp;
 
-	if (is_ptp_dev_cn10k(ptp)) {
+	if (is_ptp_dev_cn10ka(ptp) || is_ptp_dev_cnf10ka(ptp)) {
 		timestamp = readq(ptp->reg_base + PTP_TIMESTAMP);
 		*clk = (timestamp >> 32) * NSEC_PER_SEC + (timestamp & 0xFFFFFFFF);
 	} else {
@@ -414,14 +511,12 @@ static int ptp_probe(struct pci_dev *pdev,
 		first_ptp_block = ptp;
 
 	spin_lock_init(&ptp->ptp_lock);
-	if (is_ptp_tsfmt_sec_nsec(ptp))
-		ptp->read_ptp_tstmp = &read_ptp_tstmp_sec_nsec;
-	else
-		ptp->read_ptp_tstmp = &read_ptp_tstmp_nsec;
-
 	if (cn10k_ptp_errata(ptp)) {
+		ptp->read_ptp_tstmp = &read_ptp_tstmp_sec_nsec;
 		hrtimer_init(&ptp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		ptp->hrtimer.function = ptp_reset_thresh;
+	} else {
+		ptp->read_ptp_tstmp = &read_ptp_tstmp_nsec;
 	}
 
 	return 0;
@@ -521,6 +616,12 @@ int rvu_mbox_handler_ptp_op(struct rvu *rvu, struct ptp_req *req,
 	case PTP_OP_EXTTS_ON:
 		err = ptp_extts_on(rvu->ptp, req->extts_on);
 		break;
+	case PTP_OP_ADJTIME:
+		ptp_atomic_adjtime(rvu->ptp, req->delta);
+		break;
+	case PTP_OP_SET_CLOCK:
+		ptp_atomic_update(rvu->ptp, (u64)req->clk);
+		break;
 	default:
 		err = -EINVAL;
 		break;
@@ -528,3 +629,17 @@ int rvu_mbox_handler_ptp_op(struct rvu *rvu, struct ptp_req *req,
 
 	return err;
 }
+
+int rvu_mbox_handler_ptp_get_cap(struct rvu *rvu, struct msg_req *req,
+				 struct ptp_get_cap_rsp *rsp)
+{
+	if (!rvu->ptp)
+		return -ENODEV;
+
+	if (is_tstmp_atomic_update_supported(rvu))
+		rsp->cap |= PTP_CAP_HW_ATOMIC_UPDATE;
+	else
+		rsp->cap &= ~BIT_ULL_MASK(0);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.h b/drivers/net/ethernet/marvell/octeontx2/af/ptp.h
index b9d92abc38440..1229344c72792 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.h
@@ -23,9 +23,10 @@ struct ptp {
 	u32 clock_period;
 };
 
+struct rvu;
 struct ptp *ptp_get(void);
 void ptp_put(struct ptp *ptp);
-void ptp_start(struct ptp *ptp, u64 sclk, u32 ext_clk_freq, u32 extts);
+void ptp_start(struct rvu *rvu, u64 sclk, u32 ext_clk_freq, u32 extts);
 
 extern struct pci_driver ptp_driver;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 73df2d5645455..22c395c7d040b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -3322,7 +3322,7 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mutex_init(&rvu->rswitch.switch_lock);
 
 	if (rvu->fwdata)
-		ptp_start(rvu->ptp, rvu->fwdata->sclk, rvu->fwdata->ptp_ext_clk_rate,
+		ptp_start(rvu, rvu->fwdata->sclk, rvu->fwdata->ptp_ext_clk_rate,
 			  rvu->fwdata->ptp_ext_tstamp);
 
 	return 0;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index e8e65fd7888df..c4d999ef5ab4b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -17,6 +17,7 @@
 #include "mbox.h"
 #include "npc.h"
 #include "rvu_reg.h"
+#include "ptp.h"
 
 /* PCI device IDs */
 #define	PCI_DEVID_OCTEONTX2_RVU_AF		0xA065
@@ -26,6 +27,7 @@
 #define PCI_SUBSYS_DEVID_98XX                  0xB100
 #define PCI_SUBSYS_DEVID_96XX                  0xB200
 #define PCI_SUBSYS_DEVID_CN10K_A	       0xB900
+#define PCI_SUBSYS_DEVID_CNF10K_A	       0xBA00
 #define PCI_SUBSYS_DEVID_CNF10K_B              0xBC00
 #define PCI_SUBSYS_DEVID_CN10K_B               0xBD00
 
@@ -634,6 +636,16 @@ static inline bool is_rvu_otx2(struct rvu *rvu)
 		midr == PCI_REVISION_ID_95XXMM || midr == PCI_REVISION_ID_95XXO);
 }
 
+static inline bool is_cnf10ka_a0(struct rvu *rvu)
+{
+	struct pci_dev *pdev = rvu->pdev;
+
+	if (pdev->subsystem_device == PCI_SUBSYS_DEVID_CNF10K_A &&
+	    (pdev->revision & 0x0F) == 0x0)
+		return true;
+	return false;
+}
+
 static inline bool is_rvu_npc_hash_extract_en(struct rvu *rvu)
 {
 	u64 npc_const3;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 5fd05d94de7c8..4c6032ee7800d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -326,6 +326,7 @@ struct otx2_ptp {
 	struct ptp_pin_desc extts_config;
 	u64 (*convert_rx_ptp_tstmp)(u64 timestamp);
 	u64 (*convert_tx_ptp_tstmp)(u64 timestamp);
+	u64 (*ptp_tstamp2nsec)(const struct timecounter *time_counter, u64 timestamp);
 	struct delayed_work synctstamp_work;
 	u64 tstamp;
 	u32 base_ns;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
index 896b2f9bac344..3a72b0793d4a7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
@@ -10,6 +10,65 @@
 #include "otx2_common.h"
 #include "otx2_ptp.h"
 
+static bool is_tstmp_atomic_update_supported(struct otx2_ptp *ptp)
+{
+	struct ptp_get_cap_rsp *rsp;
+	struct msg_req *req;
+	int err;
+
+	if (!ptp->nic)
+		return false;
+
+	mutex_lock(&ptp->nic->mbox.lock);
+	req = otx2_mbox_alloc_msg_ptp_get_cap(&ptp->nic->mbox);
+	if (!req) {
+		mutex_unlock(&ptp->nic->mbox.lock);
+		return false;
+	}
+
+	err = otx2_sync_mbox_msg(&ptp->nic->mbox);
+	if (err) {
+		mutex_unlock(&ptp->nic->mbox.lock);
+		return false;
+	}
+	rsp = (struct ptp_get_cap_rsp *)otx2_mbox_get_rsp(&ptp->nic->mbox.mbox, 0,
+							  &req->hdr);
+	mutex_unlock(&ptp->nic->mbox.lock);
+
+	if (IS_ERR(rsp))
+		return false;
+
+	if (rsp->cap & PTP_CAP_HW_ATOMIC_UPDATE)
+		return true;
+
+	return false;
+}
+
+static int otx2_ptp_hw_adjtime(struct ptp_clock_info *ptp_info, s64 delta)
+{
+	struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp,
+					    ptp_info);
+	struct otx2_nic *pfvf = ptp->nic;
+	struct ptp_req *req;
+	int rc;
+
+	if (!ptp->nic)
+		return -ENODEV;
+
+	mutex_lock(&pfvf->mbox.lock);
+	req = otx2_mbox_alloc_msg_ptp_op(&ptp->nic->mbox);
+	if (!req) {
+		mutex_unlock(&pfvf->mbox.lock);
+		return -ENOMEM;
+	}
+	req->op = PTP_OP_ADJTIME;
+	req->delta = delta;
+	rc = otx2_sync_mbox_msg(&ptp->nic->mbox);
+	mutex_unlock(&pfvf->mbox.lock);
+
+	return rc;
+}
+
 static u64 otx2_ptp_get_clock(struct otx2_ptp *ptp)
 {
 	struct ptp_req *req;
@@ -37,6 +96,49 @@ static u64 otx2_ptp_get_clock(struct otx2_ptp *ptp)
 	return rsp->clk;
 }
 
+static int otx2_ptp_hw_gettime(struct ptp_clock_info *ptp_info,
+			       struct timespec64 *ts)
+{
+	struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp,
+					    ptp_info);
+	u64 tstamp;
+
+	tstamp = otx2_ptp_get_clock(ptp);
+
+	*ts = ns_to_timespec64(tstamp);
+	return 0;
+}
+
+static int otx2_ptp_hw_settime(struct ptp_clock_info *ptp_info,
+			       const struct timespec64 *ts)
+{
+	struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp,
+					    ptp_info);
+	struct otx2_nic *pfvf = ptp->nic;
+	struct ptp_req *req;
+	u64 nsec;
+	int rc;
+
+	if (!ptp->nic)
+		return -ENODEV;
+
+	nsec = timespec64_to_ns(ts);
+
+	mutex_lock(&pfvf->mbox.lock);
+	req = otx2_mbox_alloc_msg_ptp_op(&ptp->nic->mbox);
+	if (!req) {
+		mutex_unlock(&pfvf->mbox.lock);
+		return -ENOMEM;
+	}
+
+	req->op = PTP_OP_SET_CLOCK;
+	req->clk = nsec;
+	rc = otx2_sync_mbox_msg(&ptp->nic->mbox);
+	mutex_unlock(&pfvf->mbox.lock);
+
+	return rc;
+}
+
 static int otx2_ptp_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm)
 {
 	struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp,
@@ -124,16 +226,7 @@ static u64 ptp_tstmp_read(struct otx2_ptp *ptp)
 	return rsp->clk;
 }
 
-static void otx2_get_ptpclock(struct otx2_ptp *ptp, u64 *tstamp)
-{
-	struct otx2_nic *pfvf = ptp->nic;
-
-	mutex_lock(&pfvf->mbox.lock);
-	*tstamp = timecounter_read(&ptp->time_counter);
-	mutex_unlock(&pfvf->mbox.lock);
-}
-
-static int otx2_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta)
+static int otx2_ptp_tc_adjtime(struct ptp_clock_info *ptp_info, s64 delta)
 {
 	struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp,
 					    ptp_info);
@@ -146,32 +239,33 @@ static int otx2_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta)
 	return 0;
 }
 
-static int otx2_ptp_gettime(struct ptp_clock_info *ptp_info,
-			    struct timespec64 *ts)
+static int otx2_ptp_tc_gettime(struct ptp_clock_info *ptp_info,
+			       struct timespec64 *ts)
 {
 	struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp,
 					    ptp_info);
 	u64 tstamp;
 
-	otx2_get_ptpclock(ptp, &tstamp);
+	mutex_lock(&ptp->nic->mbox.lock);
+	tstamp = timecounter_read(&ptp->time_counter);
+	mutex_unlock(&ptp->nic->mbox.lock);
 	*ts = ns_to_timespec64(tstamp);
 
 	return 0;
 }
 
-static int otx2_ptp_settime(struct ptp_clock_info *ptp_info,
-			    const struct timespec64 *ts)
+static int otx2_ptp_tc_settime(struct ptp_clock_info *ptp_info,
+			       const struct timespec64 *ts)
 {
 	struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp,
 					    ptp_info);
-	struct otx2_nic *pfvf = ptp->nic;
 	u64 nsec;
 
 	nsec = timespec64_to_ns(ts);
 
-	mutex_lock(&pfvf->mbox.lock);
+	mutex_lock(&ptp->nic->mbox.lock);
 	timecounter_init(&ptp->time_counter, &ptp->cycle_counter, nsec);
-	mutex_unlock(&pfvf->mbox.lock);
+	mutex_unlock(&ptp->nic->mbox.lock);
 
 	return 0;
 }
@@ -190,6 +284,12 @@ static int otx2_ptp_verify_pin(struct ptp_clock_info *ptp, unsigned int pin,
 	return 0;
 }
 
+static u64 otx2_ptp_hw_tstamp2time(const struct timecounter *time_counter, u64 tstamp)
+{
+	/* On HW which supports atomic updates, timecounter is not initialized */
+	return tstamp;
+}
+
 static void otx2_ptp_extts_check(struct work_struct *work)
 {
 	struct otx2_ptp *ptp = container_of(work, struct otx2_ptp,
@@ -204,7 +304,7 @@ static void otx2_ptp_extts_check(struct work_struct *work)
 	if (tstmp != ptp->last_extts) {
 		event.type = PTP_CLOCK_EXTTS;
 		event.index = 0;
-		event.timestamp = timecounter_cyc2time(&ptp->time_counter, tstmp);
+		event.timestamp = ptp->ptp_tstamp2nsec(&ptp->time_counter, tstmp);
 		ptp_clock_event(ptp->ptp_clock, &event);
 		new_thresh = tstmp % 500000000;
 		if (ptp->thresh != new_thresh) {
@@ -229,7 +329,7 @@ static void otx2_sync_tstamp(struct work_struct *work)
 	tstamp = otx2_ptp_get_clock(ptp);
 	mutex_unlock(&pfvf->mbox.lock);
 
-	ptp->tstamp = timecounter_cyc2time(&pfvf->ptp->time_counter, tstamp);
+	ptp->tstamp = ptp->ptp_tstamp2nsec(&ptp->time_counter, tstamp);
 	ptp->base_ns = tstamp % NSEC_PER_SEC;
 
 	schedule_delayed_work(&ptp->synctstamp_work, msecs_to_jiffies(250));
@@ -302,15 +402,6 @@ int otx2_ptp_init(struct otx2_nic *pfvf)
 
 	ptp_ptr->nic = pfvf;
 
-	cc = &ptp_ptr->cycle_counter;
-	cc->read = ptp_cc_read;
-	cc->mask = CYCLECOUNTER_MASK(64);
-	cc->mult = 1;
-	cc->shift = 0;
-
-	timecounter_init(&ptp_ptr->time_counter, &ptp_ptr->cycle_counter,
-			 ktime_to_ns(ktime_get_real()));
-
 	snprintf(ptp_ptr->extts_config.name, sizeof(ptp_ptr->extts_config.name), "TSTAMP");
 	ptp_ptr->extts_config.index = 0;
 	ptp_ptr->extts_config.func = PTP_PF_NONE;
@@ -324,13 +415,33 @@ int otx2_ptp_init(struct otx2_nic *pfvf)
 		.pps            = 0,
 		.pin_config     = &ptp_ptr->extts_config,
 		.adjfine        = otx2_ptp_adjfine,
-		.adjtime        = otx2_ptp_adjtime,
-		.gettime64      = otx2_ptp_gettime,
-		.settime64      = otx2_ptp_settime,
 		.enable         = otx2_ptp_enable,
 		.verify         = otx2_ptp_verify_pin,
 	};
 
+	/* Check whether hardware supports atomic updates to timestamp */
+	if (is_tstmp_atomic_update_supported(ptp_ptr)) {
+		ptp_ptr->ptp_info.adjtime = otx2_ptp_hw_adjtime;
+		ptp_ptr->ptp_info.gettime64 = otx2_ptp_hw_gettime;
+		ptp_ptr->ptp_info.settime64 = otx2_ptp_hw_settime;
+
+		ptp_ptr->ptp_tstamp2nsec = otx2_ptp_hw_tstamp2time;
+	} else {
+		ptp_ptr->ptp_info.adjtime = otx2_ptp_tc_adjtime;
+		ptp_ptr->ptp_info.gettime64 = otx2_ptp_tc_gettime;
+		ptp_ptr->ptp_info.settime64 = otx2_ptp_tc_settime;
+
+		cc = &ptp_ptr->cycle_counter;
+		cc->read = ptp_cc_read;
+		cc->mask = CYCLECOUNTER_MASK(64);
+		cc->mult = 1;
+		cc->shift = 0;
+		ptp_ptr->ptp_tstamp2nsec = timecounter_cyc2time;
+
+		timecounter_init(&ptp_ptr->time_counter, &ptp_ptr->cycle_counter,
+				 ktime_to_ns(ktime_get_real()));
+	}
+
 	INIT_DELAYED_WORK(&ptp_ptr->extts_work, otx2_ptp_extts_check);
 
 	ptp_ptr->ptp_clock = ptp_clock_register(&ptp_ptr->ptp_info, pfvf->dev);
@@ -387,7 +498,7 @@ int otx2_ptp_tstamp2time(struct otx2_nic *pfvf, u64 tstamp, u64 *tsns)
 	if (!pfvf->ptp)
 		return -ENODEV;
 
-	*tsns = timecounter_cyc2time(&pfvf->ptp->time_counter, tstamp);
+	*tsns = pfvf->ptp->ptp_tstamp2nsec(&pfvf->ptp->time_counter, tstamp);
 
 	return 0;
 }
-- 
GitLab


From eb6603246ab9a3787e9603f0fd6a321b46623e46 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 21 Aug 2023 21:00:02 +0800
Subject: [PATCH 1557/1806] qed/qede: Remove unused declarations

Commit 8cd160a29415 ("qede: convert to new udp_tunnel_nic infra")
removed qede_udp_tunnel_{add,del}() but not the declarations.
Commit 0ebcebbef1cc ("qed: Read device port count from the shmem")
removed qed_device_num_engines() but not its declaration.
Commit 1e128c81290a ("qed: Add support for hardware offloaded FCoE.")
declared but never implemented qed_fcoe_set_pf_params().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h   | 1 -
 drivers/net/ethernet/qlogic/qede/qede.h | 3 ---
 include/linux/qed/qed_fcoe_if.h         | 3 ---
 3 files changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index d613095b78e09..1d719726f72b2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -909,7 +909,6 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev,
 					 u32 min_pf_rate);
 
 void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
-int qed_device_num_engines(struct qed_dev *cdev);
 void qed_set_fw_mac_addr(__le16 *fw_msb,
 			 __le16 *fw_mid, __le16 *fw_lsb, u8 *mac);
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 4d83ceebdc498..042a75f340608 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -556,9 +556,6 @@ void qede_config_rx_mode(struct net_device *ndev);
 void qede_fill_rss_params(struct qede_dev *edev,
 			  struct qed_update_vport_rss_params *rss, u8 *update);
 
-void qede_udp_tunnel_add(struct net_device *dev, struct udp_tunnel_info *ti);
-void qede_udp_tunnel_del(struct net_device *dev, struct udp_tunnel_info *ti);
-
 int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp);
 
 #ifdef CONFIG_DCB
diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h
index 90e3045b2dcbc..0d3b6ed21628c 100644
--- a/include/linux/qed/qed_fcoe_if.h
+++ b/include/linux/qed/qed_fcoe_if.h
@@ -67,9 +67,6 @@ struct qed_fcoe_cb_ops {
 	 u32 (*get_login_failures)(void *cookie);
 };
 
-void qed_fcoe_set_pf_params(struct qed_dev *cdev,
-			    struct qed_fcoe_pf_params *params);
-
 /**
  * struct qed_fcoe_ops - qed FCoE operations.
  * @common:		common operations pointer
-- 
GitLab


From 71ab55a9af80fcffe1f42b9b8dba4d0e3dd0c351 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:15 +0200
Subject: [PATCH 1558/1806] mlx4: Get rid of the mlx4_interface.get_dev
 callback

Simplify the mlx4 driver interface by removing mlx4_get_protocol_dev()
and the associated mlx4_interface.get_dev callbacks. This is done in
preparation to use an auxiliary bus to model the mlx4 driver structure.

The change is motivated by the following situation:
* The mlx4_en interface is being initialized by mlx4_en_add() and
  mlx4_en_activate().
* The latter activate function calls mlx4_en_init_netdev() ->
  register_netdev() to register a new net_device.
* A netdev event NETDEV_REGISTER is raised for the device.
* The netdev notififier mlx4_ib_netdev_event() is called and it invokes
  mlx4_ib_scan_netdevs() -> mlx4_get_protocol_dev() ->
  mlx4_en_get_netdev() [via mlx4_interface.get_dev].

This chain creates a problem when mlx4_en gets switched to be an
auxiliary driver. It contains two device calls which would both need to
take a respective device lock.

Avoid this situation by updating mlx4_ib_scan_netdevs() to no longer
call mlx4_get_protocol_dev() but instead to utilize the information
passed in net_device.parent and net_device.dev_port. This data is
sufficient to determine that an updated port is one that the mlx4_ib
driver should take care of and to keep mlx4_ib_dev.iboe.netdevs up to
date.

Following that, update mlx4_ib_get_netdev() to also not call
mlx4_get_protocol_dev() and instead scan all current netdevs to find
find a matching one. Note that mlx4_ib_get_netdev() is called early from
ib_register_device() and cannot use data tracked in
mlx4_ib_dev.iboe.netdevs which is not at that point yet set.

Finally, remove function mlx4_get_protocol_dev() and the
mlx4_interface.get_dev callbacks (only mlx4_en_get_netdev()) as they
became unused.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c            | 89 ++++++++++----------
 drivers/net/ethernet/mellanox/mlx4/en_main.c |  8 --
 drivers/net/ethernet/mellanox/mlx4/intf.c    | 21 -----
 include/linux/mlx4/driver.h                  |  3 -
 4 files changed, 43 insertions(+), 78 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index b18e9f2adc82d..7dd70d778b6be 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -125,12 +125,14 @@ static struct net_device *mlx4_ib_get_netdev(struct ib_device *device,
 					     u32 port_num)
 {
 	struct mlx4_ib_dev *ibdev = to_mdev(device);
-	struct net_device *dev;
+	struct net_device *dev, *ret = NULL;
 
 	rcu_read_lock();
-	dev = mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port_num);
+	for_each_netdev_rcu(&init_net, dev) {
+		if (dev->dev.parent != ibdev->ib_dev.dev.parent ||
+		    dev->dev_port + 1 != port_num)
+			continue;
 
-	if (dev) {
 		if (mlx4_is_bonded(ibdev->dev)) {
 			struct net_device *upper = NULL;
 
@@ -143,11 +145,14 @@ static struct net_device *mlx4_ib_get_netdev(struct ib_device *device,
 					dev = active;
 			}
 		}
+
+		dev_hold(dev);
+		ret = dev;
+		break;
 	}
-	dev_hold(dev);
 
 	rcu_read_unlock();
-	return dev;
+	return ret;
 }
 
 static int mlx4_ib_update_gids_v1(struct gid_entry *gids,
@@ -2319,61 +2324,53 @@ unlock:
 	mutex_unlock(&ibdev->qp1_proxy_lock[port - 1]);
 }
 
-static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev,
-				 struct net_device *dev,
-				 unsigned long event)
+static void mlx4_ib_scan_netdev(struct mlx4_ib_dev *ibdev,
+				struct net_device *dev,
+				unsigned long event)
 
 {
-	struct mlx4_ib_iboe *iboe;
-	int update_qps_port = -1;
-	int port;
+	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
 
 	ASSERT_RTNL();
 
-	iboe = &ibdev->iboe;
+	if (dev->dev.parent != ibdev->ib_dev.dev.parent)
+		return;
 
 	spin_lock_bh(&iboe->lock);
-	mlx4_foreach_ib_transport_port(port, ibdev->dev) {
-
-		iboe->netdevs[port - 1] =
-			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
 
-		if (dev == iboe->netdevs[port - 1] &&
-		    (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER ||
-		     event == NETDEV_UP || event == NETDEV_CHANGE))
-			update_qps_port = port;
+	iboe->netdevs[dev->dev_port] = event != NETDEV_UNREGISTER ? dev : NULL;
 
-		if (dev == iboe->netdevs[port - 1] &&
-		    (event == NETDEV_UP || event == NETDEV_DOWN)) {
-			enum ib_port_state port_state;
-			struct ib_event ibev = { };
-
-			if (ib_get_cached_port_state(&ibdev->ib_dev, port,
-						     &port_state))
-				continue;
+	if (event == NETDEV_UP || event == NETDEV_DOWN) {
+		enum ib_port_state port_state;
+		struct ib_event ibev = { };
 
-			if (event == NETDEV_UP &&
-			    (port_state != IB_PORT_ACTIVE ||
-			     iboe->last_port_state[port - 1] != IB_PORT_DOWN))
-				continue;
-			if (event == NETDEV_DOWN &&
-			    (port_state != IB_PORT_DOWN ||
-			     iboe->last_port_state[port - 1] != IB_PORT_ACTIVE))
-				continue;
-			iboe->last_port_state[port - 1] = port_state;
+		if (ib_get_cached_port_state(&ibdev->ib_dev, dev->dev_port + 1,
+					     &port_state))
+			goto iboe_out;
 
-			ibev.device = &ibdev->ib_dev;
-			ibev.element.port_num = port;
-			ibev.event = event == NETDEV_UP ? IB_EVENT_PORT_ACTIVE :
-							  IB_EVENT_PORT_ERR;
-			ib_dispatch_event(&ibev);
-		}
+		if (event == NETDEV_UP &&
+		    (port_state != IB_PORT_ACTIVE ||
+		     iboe->last_port_state[dev->dev_port] != IB_PORT_DOWN))
+			goto iboe_out;
+		if (event == NETDEV_DOWN &&
+		    (port_state != IB_PORT_DOWN ||
+		     iboe->last_port_state[dev->dev_port] != IB_PORT_ACTIVE))
+			goto iboe_out;
+		iboe->last_port_state[dev->dev_port] = port_state;
 
+		ibev.device = &ibdev->ib_dev;
+		ibev.element.port_num = dev->dev_port + 1;
+		ibev.event = event == NETDEV_UP ? IB_EVENT_PORT_ACTIVE :
+						  IB_EVENT_PORT_ERR;
+		ib_dispatch_event(&ibev);
 	}
+
+iboe_out:
 	spin_unlock_bh(&iboe->lock);
 
-	if (update_qps_port > 0)
-		mlx4_ib_update_qps(ibdev, dev, update_qps_port);
+	if (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER ||
+	    event == NETDEV_UP || event == NETDEV_CHANGE)
+		mlx4_ib_update_qps(ibdev, dev, dev->dev_port + 1);
 }
 
 static int mlx4_ib_netdev_event(struct notifier_block *this,
@@ -2386,7 +2383,7 @@ static int mlx4_ib_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
-	mlx4_ib_scan_netdevs(ibdev, dev, event);
+	mlx4_ib_scan_netdev(ibdev, dev, event);
 
 	return NOTIFY_DONE;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index f1259bdb1a296..6a42bec6bd850 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -183,13 +183,6 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 	}
 }
 
-static void *mlx4_en_get_netdev(struct mlx4_dev *dev, void *ctx, u8 port)
-{
-	struct mlx4_en_dev *endev = ctx;
-
-	return endev->pndev[port];
-}
-
 static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 			  enum mlx4_dev_event event, unsigned long port)
 {
@@ -354,7 +347,6 @@ static struct mlx4_interface mlx4_en_interface = {
 	.add		= mlx4_en_add,
 	.remove		= mlx4_en_remove,
 	.event		= mlx4_en_event,
-	.get_dev	= mlx4_en_get_netdev,
 	.protocol	= MLX4_PROT_ETH,
 	.activate	= mlx4_en_activate,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 65482f004e50a..28d7da925d36f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -245,27 +245,6 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 	mutex_unlock(&intf_mutex);
 }
 
-void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port)
-{
-	struct mlx4_priv *priv = mlx4_priv(dev);
-	struct mlx4_device_context *dev_ctx;
-	unsigned long flags;
-	void *result = NULL;
-
-	spin_lock_irqsave(&priv->ctx_lock, flags);
-
-	list_for_each_entry(dev_ctx, &priv->ctx_list, list)
-		if (dev_ctx->intf->protocol == proto && dev_ctx->intf->get_dev) {
-			result = dev_ctx->intf->get_dev(dev, dev_ctx->context, port);
-			break;
-		}
-
-	spin_unlock_irqrestore(&priv->ctx_lock, flags);
-
-	return result;
-}
-EXPORT_SYMBOL_GPL(mlx4_get_protocol_dev);
-
 struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port)
 {
 	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 1834c8fad12ea..923951e193000 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -59,7 +59,6 @@ struct mlx4_interface {
 	void			(*remove)(struct mlx4_dev *dev, void *context);
 	void			(*event) (struct mlx4_dev *dev, void *context,
 					  enum mlx4_dev_event event, unsigned long param);
-	void *			(*get_dev)(struct mlx4_dev *dev, void *context, u8 port);
 	void			(*activate)(struct mlx4_dev *dev, void *context);
 	struct list_head	list;
 	enum mlx4_protocol	protocol;
@@ -88,8 +87,6 @@ struct mlx4_port_map {
 
 int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p);
 
-void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port);
-
 struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port);
 
 #endif /* MLX4_DRIVER_H */
-- 
GitLab


From ef5617e34376545a1e230480beaed49466535274 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:16 +0200
Subject: [PATCH 1559/1806] mlx4: Rename member mlx4_en_dev.nb to netdev_nb

Rename the mlx4_en_dev.nb notifier_block member to netdev_nb in
preparation to add a mlx4 core notifier_block.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_main.c   | 14 +++++++-------
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |  2 +-
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  2 +-
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 6a42bec6bd850..be8ba34c9025a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -235,8 +235,8 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
 	iounmap(mdev->uar_map);
 	mlx4_uar_free(dev, &mdev->priv_uar);
 	mlx4_pd_free(dev, mdev->priv_pdn);
-	if (mdev->nb.notifier_call)
-		unregister_netdevice_notifier(&mdev->nb);
+	if (mdev->netdev_nb.notifier_call)
+		unregister_netdevice_notifier(&mdev->netdev_nb);
 	kfree(mdev);
 }
 
@@ -252,11 +252,11 @@ static void mlx4_en_activate(struct mlx4_dev *dev, void *ctx)
 			mdev->pndev[i] = NULL;
 	}
 
-	/* register notifier */
-	mdev->nb.notifier_call = mlx4_en_netdev_event;
-	if (register_netdevice_notifier(&mdev->nb)) {
-		mdev->nb.notifier_call = NULL;
-		mlx4_err(mdev, "Failed to create notifier\n");
+	/* register netdev notifier */
+	mdev->netdev_nb.notifier_call = mlx4_en_netdev_event;
+	if (register_netdevice_notifier(&mdev->netdev_nb)) {
+		mdev->netdev_nb.notifier_call = NULL;
+		mlx4_err(mdev, "Failed to create netdev notifier\n");
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 403604ceebc8f..7066c426b95c5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2967,7 +2967,7 @@ int mlx4_en_netdev_event(struct notifier_block *this,
 	if (!net_eq(dev_net(ndev), &init_net))
 		return NOTIFY_DONE;
 
-	mdev = container_of(this, struct mlx4_en_dev, nb);
+	mdev = container_of(this, struct mlx4_en_dev, netdev_nb);
 	dev = mdev->dev;
 
 	/* Go into this mode only when two network devices set on two ports
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 321f801c1d7c5..72a3fea36702c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -432,7 +432,7 @@ struct mlx4_en_dev {
 	unsigned long		last_overflow_check;
 	struct ptp_clock	*ptp_clock;
 	struct ptp_clock_info	ptp_clock_info;
-	struct notifier_block	nb;
+	struct notifier_block	netdev_nb;
 };
 
 
-- 
GitLab


From 7ba189ac52acab44129f09b302069e5a86fd92c2 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:17 +0200
Subject: [PATCH 1560/1806] mlx4: Use 'void *' as the event param of
 mlx4_dispatch_event()

Function mlx4_dispatch_event() takes an 'unsigned long' as its event
parameter. The actual value is none (MLX4_DEV_EVENT_CATASTROPHIC_ERROR),
a pointer to mlx4_eqe (MLX4_DEV_EVENT_PORT_MGMT_CHANGE), or a 32-bit
integer (remaining events).

In preparation to switch mlx4_en and mlx4_ib to be an auxiliary device,
the mlx4_interface.event callback is replaced with a notifier and
function mlx4_dispatch_event() gets updated to invoke
atomic_notifier_call_chain(). This requires forwarding the input 'param'
value from the former function to the latter. A problem is that the
notifier call takes 'void *' as its 'param' value, compared to
'unsigned long' used by mlx4_dispatch_event(). Re-passing the value
would need either punning it to 'void *' or passing down the address of
the input 'param'. Both approaches create a number of unnecessary casts.

Change instead the input 'param' of mlx4_dispatch_event() from
'unsigned long' to 'void *'. A mlx4_eqe pointer can be passed directly,
callers using an int value are adjusted to pass its address.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c            | 14 ++++++++++----
 drivers/net/ethernet/mellanox/mlx4/catas.c   |  2 +-
 drivers/net/ethernet/mellanox/mlx4/cmd.c     |  4 ++--
 drivers/net/ethernet/mellanox/mlx4/en_main.c | 17 +++++++++++++++--
 drivers/net/ethernet/mellanox/mlx4/eq.c      | 15 ++++++++-------
 drivers/net/ethernet/mellanox/mlx4/intf.c    |  2 +-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h    |  2 +-
 include/linux/mlx4/driver.h                  |  2 +-
 8 files changed, 39 insertions(+), 19 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 7dd70d778b6be..2c5fd8174b3ca 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -3174,7 +3174,7 @@ void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev,
 }
 
 static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
-			  enum mlx4_dev_event event, unsigned long param)
+			  enum mlx4_dev_event event, void *param)
 {
 	struct ib_event ibev;
 	struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr);
@@ -3194,10 +3194,16 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 		return;
 	}
 
-	if (event == MLX4_DEV_EVENT_PORT_MGMT_CHANGE)
+	switch (event) {
+	case MLX4_DEV_EVENT_CATASTROPHIC_ERROR:
+		break;
+	case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
 		eqe = (struct mlx4_eqe *)param;
-	else
-		p = (int) param;
+		break;
+	default:
+		p = *(int *)param;
+		break;
+	}
 
 	switch (event) {
 	case MLX4_DEV_EVENT_PORT_UP:
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 0eb7b83637d85..0d8a362c26739 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -194,7 +194,7 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
 	mutex_unlock(&persist->device_state_mutex);
 
 	/* At that step HW was already reset, now notify clients */
-	mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0);
+	mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, NULL);
 	mlx4_cmd_wake_completions(dev);
 	return;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index c56d2194cbfcd..f5b1f8c7834fe 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2113,7 +2113,7 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 		if (MLX4_COMM_CMD_FLR == slave_state[slave].last_cmd)
 			goto inform_slave_state;
 
-		mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_SHUTDOWN, slave);
+		mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_SHUTDOWN, &slave);
 
 		/* write the version in the event field */
 		reply |= mlx4_comm_get_version();
@@ -2152,7 +2152,7 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 		if (mlx4_master_activate_admin_state(priv, slave))
 				goto reset_slave;
 		slave_state[slave].active = true;
-		mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_INIT, slave);
+		mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_INIT, &slave);
 		break;
 	case MLX4_COMM_CMD_VHCR_POST:
 		if ((slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_EN) &&
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index be8ba34c9025a..83dae886ade6e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -184,10 +184,22 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 }
 
 static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
-			  enum mlx4_dev_event event, unsigned long port)
+			  enum mlx4_dev_event event, void *param)
 {
 	struct mlx4_en_dev *mdev = (struct mlx4_en_dev *) endev_ptr;
 	struct mlx4_en_priv *priv;
+	int port;
+
+	switch (event) {
+	case MLX4_DEV_EVENT_CATASTROPHIC_ERROR:
+	case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
+	case MLX4_DEV_EVENT_SLAVE_INIT:
+	case MLX4_DEV_EVENT_SLAVE_SHUTDOWN:
+		break;
+	default:
+		port = *(int *)param;
+		break;
+	}
 
 	switch (event) {
 	case MLX4_DEV_EVENT_PORT_UP:
@@ -205,6 +217,7 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 		mlx4_err(mdev, "Internal error detected, restarting device\n");
 		break;
 
+	case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
 	case MLX4_DEV_EVENT_SLAVE_INIT:
 	case MLX4_DEV_EVENT_SLAVE_SHUTDOWN:
 		break;
@@ -213,7 +226,7 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 		    !mdev->pndev[port])
 			return;
 		mlx4_warn(mdev, "Unhandled event %d for port %d\n", event,
-			  (int) port);
+			  port);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 414e390e6b48c..6598b10a9ff49 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -501,7 +501,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 	int port;
 	int slave = 0;
 	int ret;
-	u32 flr_slave;
+	int flr_slave;
 	u8 update_slave_state;
 	int i;
 	enum slave_port_gen_event gen_event;
@@ -606,8 +606,8 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			port = be32_to_cpu(eqe->event.port_change.port) >> 28;
 			slaves_port = mlx4_phys_to_slaves_pport(dev, port);
 			if (eqe->subtype == MLX4_PORT_CHANGE_SUBTYPE_DOWN) {
-				mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_DOWN,
-						    port);
+				mlx4_dispatch_event(
+					dev, MLX4_DEV_EVENT_PORT_DOWN, &port);
 				mlx4_priv(dev)->sense.do_sense_port[port] = 1;
 				if (!mlx4_is_master(dev))
 					break;
@@ -647,7 +647,8 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 					}
 				}
 			} else {
-				mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_UP, port);
+				mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_UP,
+						    &port);
 
 				mlx4_priv(dev)->sense.do_sense_port[port] = 0;
 
@@ -758,7 +759,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			}
 			spin_unlock_irqrestore(&priv->mfunc.master.slave_state_lock, flags);
 			mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_SHUTDOWN,
-					    flr_slave);
+					    &flr_slave);
 			queue_work(priv->mfunc.master.comm_wq,
 				   &priv->mfunc.master.slave_flr_event_work);
 			break;
@@ -787,8 +788,8 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			break;
 
 		case MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT:
-			mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_MGMT_CHANGE,
-					    (unsigned long) eqe);
+			mlx4_dispatch_event(
+				dev, MLX4_DEV_EVENT_PORT_MGMT_CHANGE, eqe);
 			break;
 
 		case MLX4_EVENT_TYPE_RECOVERABLE_ERROR_EVENT:
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 28d7da925d36f..a761971cd0c4c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -180,7 +180,7 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
 }
 
 void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
-			 unsigned long param)
+			 void *param)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_device_context *dev_ctx;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 6ccf340660d99..de5699a4ddaab 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1048,7 +1048,7 @@ int mlx4_restart_one(struct pci_dev *pdev);
 int mlx4_register_device(struct mlx4_dev *dev);
 void mlx4_unregister_device(struct mlx4_dev *dev);
 void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
-			 unsigned long param);
+			 void *param);
 
 struct mlx4_dev_cap;
 struct mlx4_init_hca_param;
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 923951e193000..032d7f5bfef67 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -58,7 +58,7 @@ struct mlx4_interface {
 	void *			(*add)	 (struct mlx4_dev *dev);
 	void			(*remove)(struct mlx4_dev *dev, void *context);
 	void			(*event) (struct mlx4_dev *dev, void *context,
-					  enum mlx4_dev_event event, unsigned long param);
+					  enum mlx4_dev_event event, void *param);
 	void			(*activate)(struct mlx4_dev *dev, void *context);
 	struct list_head	list;
 	enum mlx4_protocol	protocol;
-- 
GitLab


From 73d68002a02efd370dba6b8fc570427326e36d1a Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:18 +0200
Subject: [PATCH 1561/1806] mlx4: Replace the mlx4_interface.event callback
 with a notifier

Use a notifier to implement mlx4_dispatch_event() in preparation to
switch mlx4_en and mlx4_ib to be an auxiliary device.

A problem is that if the mlx4_interface.event callback was replaced with
something as mlx4_adrv.event then the implementation of
mlx4_dispatch_event() would need to acquire a lock on a given device
before executing this callback. That is necessary because otherwise
there is no guarantee that the associated driver cannot get unbound when
the callback is running. However, taking this lock is not possible
because mlx4_dispatch_event() can be invoked from the hardirq context.
Using an atomic notifier allows the driver to accurately record when it
wants to receive these events and solves this problem.

A handler registration is done by both mlx4_en and mlx4_ib at the end of
their mlx4_interface.add callback. This matches the current situation
when mlx4_add_device() would enable events for a given device
immediately after this callback, by adding the device on the
mlx4_priv.list.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c            | 40 +++++++++++++-------
 drivers/infiniband/hw/mlx4/mlx4_ib.h         |  2 +
 drivers/net/ethernet/mellanox/mlx4/en_main.c | 26 +++++++++----
 drivers/net/ethernet/mellanox/mlx4/intf.c    | 24 ++++++++----
 drivers/net/ethernet/mellanox/mlx4/main.c    |  2 +
 drivers/net/ethernet/mellanox/mlx4/mlx4.h    |  2 +
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  2 +
 include/linux/mlx4/driver.h                  |  8 +++-
 8 files changed, 75 insertions(+), 31 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 2c5fd8174b3ca..6debee494a162 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -82,6 +82,8 @@ static const char mlx4_ib_version[] =
 static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init);
 static enum rdma_link_layer mlx4_ib_port_link_layer(struct ib_device *device,
 						    u32 port_num);
+static int mlx4_ib_event(struct notifier_block *this, unsigned long event,
+			 void *param);
 
 static struct workqueue_struct *wq;
 
@@ -2836,6 +2838,12 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 				do_slave_init(ibdev, j, 1);
 		}
 	}
+
+	/* register mlx4 core notifier */
+	ibdev->mlx_nb.notifier_call = mlx4_ib_event;
+	err = mlx4_register_event_notifier(dev, &ibdev->mlx_nb);
+	WARN(err, "failed to register mlx4 event notifier (%d)", err);
+
 	return ibdev;
 
 err_notif:
@@ -2953,6 +2961,8 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 	int p;
 	int i;
 
+	mlx4_unregister_event_notifier(dev, &ibdev->mlx_nb);
+
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
 		devlink_port_type_clear(mlx4_get_devlink_port(dev, i));
 	ibdev->ib_active = false;
@@ -3173,11 +3183,13 @@ void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev,
 	}
 }
 
-static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
-			  enum mlx4_dev_event event, void *param)
+static int mlx4_ib_event(struct notifier_block *this, unsigned long event,
+			 void *param)
 {
+	struct mlx4_ib_dev *ibdev =
+		container_of(this, struct mlx4_ib_dev, mlx_nb);
+	struct mlx4_dev *dev = ibdev->dev;
 	struct ib_event ibev;
-	struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr);
 	struct mlx4_eqe *eqe = NULL;
 	struct ib_event_work *ew;
 	int p = 0;
@@ -3187,11 +3199,11 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 	    (event == MLX4_DEV_EVENT_PORT_DOWN))) {
 		ew = kmalloc(sizeof(*ew), GFP_ATOMIC);
 		if (!ew)
-			return;
+			return NOTIFY_DONE;
 		INIT_WORK(&ew->work, handle_bonded_port_state_event);
 		ew->ib_dev = ibdev;
 		queue_work(wq, &ew->work);
-		return;
+		return NOTIFY_DONE;
 	}
 
 	switch (event) {
@@ -3208,7 +3220,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 	switch (event) {
 	case MLX4_DEV_EVENT_PORT_UP:
 		if (p > ibdev->num_ports)
-			return;
+			return NOTIFY_DONE;
 		if (!mlx4_is_slave(dev) &&
 		    rdma_port_get_link_layer(&ibdev->ib_dev, p) ==
 			IB_LINK_LAYER_INFINIBAND) {
@@ -3223,7 +3235,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 
 	case MLX4_DEV_EVENT_PORT_DOWN:
 		if (p > ibdev->num_ports)
-			return;
+			return NOTIFY_DONE;
 		ibev.event = IB_EVENT_PORT_ERR;
 		break;
 
@@ -3236,7 +3248,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 	case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
 		ew = kmalloc(sizeof *ew, GFP_ATOMIC);
 		if (!ew)
-			return;
+			return NOTIFY_DONE;
 
 		INIT_WORK(&ew->work, handle_port_mgmt_change_event);
 		memcpy(&ew->ib_eqe, eqe, sizeof *eqe);
@@ -3246,7 +3258,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 			queue_work(wq, &ew->work);
 		else
 			handle_port_mgmt_change_event(&ew->work);
-		return;
+		return NOTIFY_DONE;
 
 	case MLX4_DEV_EVENT_SLAVE_INIT:
 		/* here, p is the slave id */
@@ -3262,7 +3274,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 								       1);
 			}
 		}
-		return;
+		return NOTIFY_DONE;
 
 	case MLX4_DEV_EVENT_SLAVE_SHUTDOWN:
 		if (mlx4_is_master(dev)) {
@@ -3278,22 +3290,22 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 		}
 		/* here, p is the slave id */
 		do_slave_init(ibdev, p, 0);
-		return;
+		return NOTIFY_DONE;
 
 	default:
-		return;
+		return NOTIFY_DONE;
 	}
 
-	ibev.device	      = ibdev_ptr;
+	ibev.device	      = &ibdev->ib_dev;
 	ibev.element.port_num = mlx4_is_bonded(ibdev->dev) ? 1 : (u8)p;
 
 	ib_dispatch_event(&ibev);
+	return NOTIFY_DONE;
 }
 
 static struct mlx4_interface mlx4_ib_interface = {
 	.add		= mlx4_ib_add,
 	.remove		= mlx4_ib_remove,
-	.event		= mlx4_ib_event,
 	.protocol	= MLX4_PROT_IB_IPV6,
 	.flags		= MLX4_INTFF_BONDING
 };
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 17fee1e73a45a..41ca1114a9958 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -38,6 +38,7 @@
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/idr.h>
+#include <linux/notifier.h>
 
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_umem.h>
@@ -644,6 +645,7 @@ struct mlx4_ib_dev {
 	spinlock_t		reset_flow_resource_lock;
 	struct list_head		qp_list;
 	struct mlx4_ib_diag_counters diag_counters[MLX4_DIAG_COUNTERS_TYPES];
+	struct notifier_block	mlx_nb;
 };
 
 struct ib_event_work {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 83dae886ade6e..31bf625b8158e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -183,10 +183,12 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 	}
 }
 
-static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
-			  enum mlx4_dev_event event, void *param)
+static int mlx4_en_event(struct notifier_block *this, unsigned long event,
+			 void *param)
 {
-	struct mlx4_en_dev *mdev = (struct mlx4_en_dev *) endev_ptr;
+	struct mlx4_en_dev *mdev =
+		container_of(this, struct mlx4_en_dev, mlx_nb);
+	struct mlx4_dev *dev = mdev->dev;
 	struct mlx4_en_priv *priv;
 	int port;
 
@@ -205,7 +207,7 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 	case MLX4_DEV_EVENT_PORT_UP:
 	case MLX4_DEV_EVENT_PORT_DOWN:
 		if (!mdev->pndev[port])
-			return;
+			return NOTIFY_DONE;
 		priv = netdev_priv(mdev->pndev[port]);
 		/* To prevent races, we poll the link state in a separate
 		  task rather than changing it here */
@@ -224,10 +226,12 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 	default:
 		if (port < 1 || port > dev->caps.num_ports ||
 		    !mdev->pndev[port])
-			return;
-		mlx4_warn(mdev, "Unhandled event %d for port %d\n", event,
+			return NOTIFY_DONE;
+		mlx4_warn(mdev, "Unhandled event %d for port %d\n", (int)event,
 			  port);
 	}
+
+	return NOTIFY_DONE;
 }
 
 static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
@@ -235,6 +239,8 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
 	struct mlx4_en_dev *mdev = endev_ptr;
 	int i;
 
+	mlx4_unregister_event_notifier(dev, &mdev->mlx_nb);
+
 	mutex_lock(&mdev->state_lock);
 	mdev->device_up = false;
 	mutex_unlock(&mdev->state_lock);
@@ -276,7 +282,7 @@ static void mlx4_en_activate(struct mlx4_dev *dev, void *ctx)
 static void *mlx4_en_add(struct mlx4_dev *dev)
 {
 	struct mlx4_en_dev *mdev;
-	int i;
+	int err, i;
 
 	printk_once(KERN_INFO "%s", mlx4_en_version);
 
@@ -339,6 +345,11 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 	mutex_init(&mdev->state_lock);
 	mdev->device_up = true;
 
+	/* register mlx4 core notifier */
+	mdev->mlx_nb.notifier_call = mlx4_en_event;
+	err = mlx4_register_event_notifier(dev, &mdev->mlx_nb);
+	WARN(err, "failed to register mlx4 event notifier (%d)", err);
+
 	return mdev;
 
 err_mr:
@@ -359,7 +370,6 @@ err_free_res:
 static struct mlx4_interface mlx4_en_interface = {
 	.add		= mlx4_en_add,
 	.remove		= mlx4_en_remove,
-	.event		= mlx4_en_event,
 	.protocol	= MLX4_PROT_ETH,
 	.activate	= mlx4_en_activate,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index a761971cd0c4c..fecb63e696073 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -183,17 +183,27 @@ void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
 			 void *param)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	struct mlx4_device_context *dev_ctx;
-	unsigned long flags;
 
-	spin_lock_irqsave(&priv->ctx_lock, flags);
+	atomic_notifier_call_chain(&priv->event_nh, type, param);
+}
 
-	list_for_each_entry(dev_ctx, &priv->ctx_list, list)
-		if (dev_ctx->intf->event)
-			dev_ctx->intf->event(dev, dev_ctx->context, type, param);
+int mlx4_register_event_notifier(struct mlx4_dev *dev,
+				 struct notifier_block *nb)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
 
-	spin_unlock_irqrestore(&priv->ctx_lock, flags);
+	return atomic_notifier_chain_register(&priv->event_nh, nb);
+}
+EXPORT_SYMBOL(mlx4_register_event_notifier);
+
+int mlx4_unregister_event_notifier(struct mlx4_dev *dev,
+				   struct notifier_block *nb)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	return atomic_notifier_chain_unregister(&priv->event_nh, nb);
 }
+EXPORT_SYMBOL(mlx4_unregister_event_notifier);
 
 int mlx4_register_device(struct mlx4_dev *dev)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 8a5409b00530f..5f3ba8385e230 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3378,6 +3378,8 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
 
+	ATOMIC_INIT_NOTIFIER_HEAD(&priv->event_nh);
+
 	mutex_init(&priv->port_mutex);
 	mutex_init(&priv->bond_mutex);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index de5699a4ddaab..8dbea814a2f5e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -47,6 +47,7 @@
 #include <linux/spinlock.h>
 #include <net/devlink.h>
 #include <linux/rwsem.h>
+#include <linux/notifier.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/driver.h>
@@ -878,6 +879,7 @@ struct mlx4_priv {
 	struct list_head	dev_list;
 	struct list_head	ctx_list;
 	spinlock_t		ctx_lock;
+	struct atomic_notifier_head event_nh;
 
 	int			pci_dev_data;
 	int                     removed;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 72a3fea36702c..efe3f97b874fe 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -49,6 +49,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/irq.h>
 #include <net/xdp.h>
+#include <linux/notifier.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/qp.h>
@@ -433,6 +434,7 @@ struct mlx4_en_dev {
 	struct ptp_clock	*ptp_clock;
 	struct ptp_clock_info	ptp_clock_info;
 	struct notifier_block	netdev_nb;
+	struct notifier_block	mlx_nb;
 };
 
 
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 032d7f5bfef67..228da8ed7e750 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -34,6 +34,7 @@
 #define MLX4_DRIVER_H
 
 #include <net/devlink.h>
+#include <linux/notifier.h>
 #include <linux/mlx4/device.h>
 
 struct mlx4_dev;
@@ -57,8 +58,6 @@ enum {
 struct mlx4_interface {
 	void *			(*add)	 (struct mlx4_dev *dev);
 	void			(*remove)(struct mlx4_dev *dev, void *context);
-	void			(*event) (struct mlx4_dev *dev, void *context,
-					  enum mlx4_dev_event event, void *param);
 	void			(*activate)(struct mlx4_dev *dev, void *context);
 	struct list_head	list;
 	enum mlx4_protocol	protocol;
@@ -87,6 +86,11 @@ struct mlx4_port_map {
 
 int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p);
 
+int mlx4_register_event_notifier(struct mlx4_dev *dev,
+				 struct notifier_block *nb);
+int mlx4_unregister_event_notifier(struct mlx4_dev *dev,
+				   struct notifier_block *nb);
+
 struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port);
 
 #endif /* MLX4_DRIVER_H */
-- 
GitLab


From 13f857111cb23f2a8dbcd0271c3ff1824913d980 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:19 +0200
Subject: [PATCH 1562/1806] mlx4: Get rid of the mlx4_interface.activate
 callback

The mlx4_interface.activate callback was introduced in commit
79857cd31fe7 ("net/mlx4: Postpone the registration of net_device"). It
dealt with a situation when a netdev notifier received a NETDEV_REGISTER
event for a new net_device created by mlx4_en but the same device was
not yet visible to mlx4_get_protocol_dev(). The callback can be removed
now that mlx4_get_protocol_dev() is gone.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_main.c | 37 +++++++++-----------
 drivers/net/ethernet/mellanox/mlx4/intf.c    |  2 --
 include/linux/mlx4/driver.h                  |  1 -
 3 files changed, 16 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 31bf625b8158e..39c9befeb6388 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -259,26 +259,6 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
 	kfree(mdev);
 }
 
-static void mlx4_en_activate(struct mlx4_dev *dev, void *ctx)
-{
-	int i;
-	struct mlx4_en_dev *mdev = ctx;
-
-	/* Create a netdev for each port */
-	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
-		mlx4_info(mdev, "Activating port:%d\n", i);
-		if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i]))
-			mdev->pndev[i] = NULL;
-	}
-
-	/* register netdev notifier */
-	mdev->netdev_nb.notifier_call = mlx4_en_netdev_event;
-	if (register_netdevice_notifier(&mdev->netdev_nb)) {
-		mdev->netdev_nb.notifier_call = NULL;
-		mlx4_err(mdev, "Failed to create netdev notifier\n");
-	}
-}
-
 static void *mlx4_en_add(struct mlx4_dev *dev)
 {
 	struct mlx4_en_dev *mdev;
@@ -350,6 +330,22 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 	err = mlx4_register_event_notifier(dev, &mdev->mlx_nb);
 	WARN(err, "failed to register mlx4 event notifier (%d)", err);
 
+	/* Setup ports */
+
+	/* Create a netdev for each port */
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
+		mlx4_info(mdev, "Activating port:%d\n", i);
+		if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i]))
+			mdev->pndev[i] = NULL;
+	}
+
+	/* register netdev notifier */
+	mdev->netdev_nb.notifier_call = mlx4_en_netdev_event;
+	if (register_netdevice_notifier(&mdev->netdev_nb)) {
+		mdev->netdev_nb.notifier_call = NULL;
+		mlx4_err(mdev, "Failed to create netdev notifier\n");
+	}
+
 	return mdev;
 
 err_mr:
@@ -371,7 +367,6 @@ static struct mlx4_interface mlx4_en_interface = {
 	.add		= mlx4_en_add,
 	.remove		= mlx4_en_remove,
 	.protocol	= MLX4_PROT_ETH,
-	.activate	= mlx4_en_activate,
 };
 
 static void mlx4_en_verify_params(void)
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index fecb63e696073..8cbc1bcdfe777 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -64,8 +64,6 @@ static void mlx4_add_device(struct mlx4_interface *intf, struct mlx4_priv *priv)
 		spin_lock_irq(&priv->ctx_lock);
 		list_add_tail(&dev_ctx->list, &priv->ctx_list);
 		spin_unlock_irq(&priv->ctx_lock);
-		if (intf->activate)
-			intf->activate(&priv->dev, dev_ctx->context);
 	} else
 		kfree(dev_ctx);
 
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 228da8ed7e750..0f8c9ba4c5744 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -58,7 +58,6 @@ enum {
 struct mlx4_interface {
 	void *			(*add)	 (struct mlx4_dev *dev);
 	void			(*remove)(struct mlx4_dev *dev, void *context);
-	void			(*activate)(struct mlx4_dev *dev, void *context);
 	struct list_head	list;
 	enum mlx4_protocol	protocol;
 	int			flags;
-- 
GitLab


From e2fb47d4eb5cd245c38c8c57d969ac6b12efc764 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:20 +0200
Subject: [PATCH 1563/1806] mlx4: Move the bond work to the core driver

Function mlx4_en_queue_bond_work() is used in mlx4_en to start a bond
reconfiguration. It gathers data about a new port map setting, takes
a reference on the netdev that triggered the change and queues a work
object on mlx4_en_priv.mdev.workqueue to perform the operation. The
scheduled work is mlx4_en_bond_work() which calls
mlx4_bond()/mlx4_unbond() and consequently mlx4_do_bond().

At the same time, function mlx4_change_port_types() in mlx4_core might
be invoked to change the port type configuration. As part of its logic,
it re-registers the whole device by calling mlx4_unregister_device(),
followed by mlx4_register_device().

The two operations can result in concurrent access to the data about
currently active interfaces on the device.

Functions mlx4_register_device() and mlx4_unregister_device() lock the
intf_mutex to gain exclusive access to this data. The current
implementation of mlx4_do_bond() doesn't do that which could result in
an unexpected behavior. An updated version of mlx4_do_bond() for use
with an auxiliary bus goes and locks the intf_mutex when accessing a new
auxiliary device array.

However, doing so can then result in the following deadlock:
* A two-port mlx4 device is configured as an Ethernet bond.
* One of the ports is changed from eth to ib, for instance, by writing
  into a mlx4_port<x> sysfs attribute file.
* mlx4_change_port_types() is called to update port types. It invokes
  mlx4_unregister_device() to unregister the device which locks the
  intf_mutex and starts removing all associated interfaces.
* Function mlx4_en_remove() gets invoked and starts destroying its first
  netdev. This triggers mlx4_en_netdev_event() which recognizes that the
  configured bond is broken. It runs mlx4_en_queue_bond_work() which
  takes a reference on the netdev. Removing the netdev now cannot
  proceed until the work is completed.
* Work function mlx4_en_bond_work() gets scheduled. It calls
  mlx4_unbond() -> mlx4_do_bond(). The latter function tries to lock the
  intf_mutex but that is not possible because it is held already by
  mlx4_unregister_device().

This particular case could be possibly solved by unregistering the
mlx4_en_netdev_event() notifier in mlx4_en_remove() earlier, but it
seems better to decouple mlx4_en more and break this reference order.

Avoid then this scenario by recognizing that the bond reconfiguration
operates only on a mlx4_dev. The logic to queue and execute the bond
work can be moved into the mlx4_core driver. Only a reference on the
respective mlx4_dev object is needed to be taken during the work's
lifetime. This removes a call from mlx4_en that can directly result in
needing to lock the intf_mutex, it remains a privilege of the core
driver.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx4/en_netdev.c    | 62 +-----------------
 drivers/net/ethernet/mellanox/mlx4/main.c     | 65 +++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx4/mlx4.h     |  5 ++
 include/linux/mlx4/device.h                   | 13 ++++
 include/linux/mlx4/driver.h                   | 19 ------
 5 files changed, 77 insertions(+), 87 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 7066c426b95c5..33bbcced81059 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2894,63 +2894,6 @@ static const struct xdp_metadata_ops mlx4_xdp_metadata_ops = {
 	.xmo_rx_hash			= mlx4_en_xdp_rx_hash,
 };
 
-struct mlx4_en_bond {
-	struct work_struct work;
-	struct mlx4_en_priv *priv;
-	int is_bonded;
-	struct mlx4_port_map port_map;
-};
-
-static void mlx4_en_bond_work(struct work_struct *work)
-{
-	struct mlx4_en_bond *bond = container_of(work,
-						     struct mlx4_en_bond,
-						     work);
-	int err = 0;
-	struct mlx4_dev *dev = bond->priv->mdev->dev;
-
-	if (bond->is_bonded) {
-		if (!mlx4_is_bonded(dev)) {
-			err = mlx4_bond(dev);
-			if (err)
-				en_err(bond->priv, "Fail to bond device\n");
-		}
-		if (!err) {
-			err = mlx4_port_map_set(dev, &bond->port_map);
-			if (err)
-				en_err(bond->priv, "Fail to set port map [%d][%d]: %d\n",
-				       bond->port_map.port1,
-				       bond->port_map.port2,
-				       err);
-		}
-	} else if (mlx4_is_bonded(dev)) {
-		err = mlx4_unbond(dev);
-		if (err)
-			en_err(bond->priv, "Fail to unbond device\n");
-	}
-	dev_put(bond->priv->dev);
-	kfree(bond);
-}
-
-static int mlx4_en_queue_bond_work(struct mlx4_en_priv *priv, int is_bonded,
-				   u8 v2p_p1, u8 v2p_p2)
-{
-	struct mlx4_en_bond *bond;
-
-	bond = kzalloc(sizeof(*bond), GFP_ATOMIC);
-	if (!bond)
-		return -ENOMEM;
-
-	INIT_WORK(&bond->work, mlx4_en_bond_work);
-	bond->priv = priv;
-	bond->is_bonded = is_bonded;
-	bond->port_map.port1 = v2p_p1;
-	bond->port_map.port2 = v2p_p2;
-	dev_hold(priv->dev);
-	queue_work(priv->mdev->workqueue, &bond->work);
-	return 0;
-}
-
 int mlx4_en_netdev_event(struct notifier_block *this,
 			 unsigned long event, void *ptr)
 {
@@ -2960,7 +2903,6 @@ int mlx4_en_netdev_event(struct notifier_block *this,
 	struct mlx4_dev *dev;
 	int i, num_eth_ports = 0;
 	bool do_bond = true;
-	struct mlx4_en_priv *priv;
 	u8 v2p_port1 = 0;
 	u8 v2p_port2 = 0;
 
@@ -2995,7 +2937,6 @@ int mlx4_en_netdev_event(struct notifier_block *this,
 	if ((do_bond && (event != NETDEV_BONDING_INFO)) || !port)
 		return NOTIFY_DONE;
 
-	priv = netdev_priv(ndev);
 	if (do_bond) {
 		struct netdev_notifier_bonding_info *notifier_info = ptr;
 		struct netdev_bonding_info *bonding_info =
@@ -3062,8 +3003,7 @@ int mlx4_en_netdev_event(struct notifier_block *this,
 		}
 	}
 
-	mlx4_en_queue_bond_work(priv, do_bond,
-				v2p_port1, v2p_port2);
+	mlx4_queue_bond_work(dev, do_bond, v2p_port1, v2p_port2);
 
 	return NOTIFY_DONE;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 5f3ba8385e230..0ed490b991630 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1441,7 +1441,7 @@ static int mlx4_mf_unbond(struct mlx4_dev *dev)
 	return ret;
 }
 
-int mlx4_bond(struct mlx4_dev *dev)
+static int mlx4_bond(struct mlx4_dev *dev)
 {
 	int ret = 0;
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1467,9 +1467,8 @@ int mlx4_bond(struct mlx4_dev *dev)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(mlx4_bond);
 
-int mlx4_unbond(struct mlx4_dev *dev)
+static int mlx4_unbond(struct mlx4_dev *dev)
 {
 	int ret = 0;
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1496,10 +1495,8 @@ int mlx4_unbond(struct mlx4_dev *dev)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(mlx4_unbond);
 
-
-int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p)
+static int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p)
 {
 	u8 port1 = v2p->port1;
 	u8 port2 = v2p->port2;
@@ -1541,7 +1538,61 @@ int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p)
 	mutex_unlock(&priv->bond_mutex);
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx4_port_map_set);
+
+struct mlx4_bond {
+	struct work_struct work;
+	struct mlx4_dev *dev;
+	int is_bonded;
+	struct mlx4_port_map port_map;
+};
+
+static void mlx4_bond_work(struct work_struct *work)
+{
+	struct mlx4_bond *bond = container_of(work, struct mlx4_bond, work);
+	int err = 0;
+
+	if (bond->is_bonded) {
+		if (!mlx4_is_bonded(bond->dev)) {
+			err = mlx4_bond(bond->dev);
+			if (err)
+				mlx4_err(bond->dev, "Fail to bond device\n");
+		}
+		if (!err) {
+			err = mlx4_port_map_set(bond->dev, &bond->port_map);
+			if (err)
+				mlx4_err(bond->dev,
+					 "Fail to set port map [%d][%d]: %d\n",
+					 bond->port_map.port1,
+					 bond->port_map.port2, err);
+		}
+	} else if (mlx4_is_bonded(bond->dev)) {
+		err = mlx4_unbond(bond->dev);
+		if (err)
+			mlx4_err(bond->dev, "Fail to unbond device\n");
+	}
+	put_device(&bond->dev->persist->pdev->dev);
+	kfree(bond);
+}
+
+int mlx4_queue_bond_work(struct mlx4_dev *dev, int is_bonded, u8 v2p_p1,
+			 u8 v2p_p2)
+{
+	struct mlx4_bond *bond;
+
+	bond = kzalloc(sizeof(*bond), GFP_ATOMIC);
+	if (!bond)
+		return -ENOMEM;
+
+	INIT_WORK(&bond->work, mlx4_bond_work);
+	get_device(&dev->persist->pdev->dev);
+	bond->dev = dev;
+	bond->is_bonded = is_bonded;
+	bond->port_map.port1 = v2p_p1;
+	bond->port_map.port2 = v2p_p2;
+	queue_work(mlx4_wq, &bond->work);
+	return 0;
+}
+EXPORT_SYMBOL(mlx4_queue_bond_work);
 
 static int mlx4_load_fw(struct mlx4_dev *dev)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 8dbea814a2f5e..73b4fdfd63f4c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -863,6 +863,11 @@ struct mlx4_steer {
 	struct list_head steer_entries[MLX4_NUM_STEERS];
 };
 
+struct mlx4_port_map {
+	u8	port1;
+	u8	port2;
+};
+
 enum {
 	MLX4_PCI_DEV_IS_VF		= 1 << 0,
 	MLX4_PCI_DEV_FORCE_SENSE_PORT	= 1 << 1,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 6646634a0b9d4..049d8a4b044de 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1087,6 +1087,19 @@ static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset)
 			(offset & (PAGE_SIZE - 1));
 }
 
+static inline int mlx4_is_bonded(struct mlx4_dev *dev)
+{
+	return !!(dev->flags & MLX4_FLAG_BONDED);
+}
+
+static inline int mlx4_is_mf_bonded(struct mlx4_dev *dev)
+{
+	return (mlx4_is_bonded(dev) && mlx4_is_mfunc(dev));
+}
+
+int mlx4_queue_bond_work(struct mlx4_dev *dev, int is_bonded, u8 v2p_p1,
+			 u8 v2p_p2);
+
 int mlx4_pd_alloc(struct mlx4_dev *dev, u32 *pdn);
 void mlx4_pd_free(struct mlx4_dev *dev, u32 pdn);
 int mlx4_xrcd_alloc(struct mlx4_dev *dev, u32 *xrcdn);
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 0f8c9ba4c5744..781d5a0c2faa0 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -66,25 +66,6 @@ struct mlx4_interface {
 int mlx4_register_interface(struct mlx4_interface *intf);
 void mlx4_unregister_interface(struct mlx4_interface *intf);
 
-int mlx4_bond(struct mlx4_dev *dev);
-int mlx4_unbond(struct mlx4_dev *dev);
-static inline int mlx4_is_bonded(struct mlx4_dev *dev)
-{
-	return !!(dev->flags & MLX4_FLAG_BONDED);
-}
-
-static inline int mlx4_is_mf_bonded(struct mlx4_dev *dev)
-{
-	return (mlx4_is_bonded(dev) && mlx4_is_mfunc(dev));
-}
-
-struct mlx4_port_map {
-	u8	port1;
-	u8	port2;
-};
-
-int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p);
-
 int mlx4_register_event_notifier(struct mlx4_dev *dev,
 				 struct notifier_block *nb);
 int mlx4_unregister_event_notifier(struct mlx4_dev *dev,
-- 
GitLab


From c9452b8fd2ec249fa61e8a36726bde3af60a86d4 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:21 +0200
Subject: [PATCH 1564/1806] mlx4: Avoid resetting MLX4_INTFF_BONDING per driver

The mlx4_core driver has a logic that allows a sub-driver to set the
MLX4_INTFF_BONDING flag which then causes that function mlx4_do_bond()
asks the sub-driver to fully re-probe a device when its bonding
configuration changes.

Performing this operation is disallowed in mlx4_register_interface()
when it is detected that any mlx4 device is multifunction (SRIOV). The
code then resets MLX4_INTFF_BONDING in the driver flags.

Move this check directly into mlx4_do_bond(). It provides a better
separation as mlx4_core no longer directly modifies the sub-driver flags
and it will allow to get rid of explicitly keeping track of all mlx4
devices by the intf.c code when it is switched to an auxiliary bus.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/intf.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 8cbc1bcdfe777..d578f754d8822 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -96,11 +96,6 @@ int mlx4_register_interface(struct mlx4_interface *intf)
 
 	list_add_tail(&intf->list, &intf_list);
 	list_for_each_entry(priv, &dev_list, dev_list) {
-		if (mlx4_is_mfunc(&priv->dev) && (intf->flags & MLX4_INTFF_BONDING)) {
-			mlx4_dbg(&priv->dev,
-				 "SRIOV, disabling HA mode for intf proto %d\n", intf->protocol);
-			intf->flags &= ~MLX4_INTFF_BONDING;
-		}
 		mlx4_add_device(intf, priv);
 	}
 
@@ -155,10 +150,18 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
 
 	spin_lock_irqsave(&priv->ctx_lock, flags);
 	list_for_each_entry_safe(dev_ctx, temp_dev_ctx, &priv->ctx_list, list) {
-		if (dev_ctx->intf->flags & MLX4_INTFF_BONDING) {
-			list_add_tail(&dev_ctx->bond_list, &bond_list);
-			list_del(&dev_ctx->list);
+		if (!(dev_ctx->intf->flags & MLX4_INTFF_BONDING))
+			continue;
+
+		if (mlx4_is_mfunc(dev)) {
+			mlx4_dbg(dev,
+				 "SRIOV, disabled HA mode for intf proto %d\n",
+				 dev_ctx->intf->protocol);
+			continue;
 		}
+
+		list_add_tail(&dev_ctx->bond_list, &bond_list);
+		list_del(&dev_ctx->list);
 	}
 	spin_unlock_irqrestore(&priv->ctx_lock, flags);
 
-- 
GitLab


From 8c2d2b87719bad9c1db4a7919e74f7818a8ca3de Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:22 +0200
Subject: [PATCH 1565/1806] mlx4: Register mlx4 devices to an auxiliary virtual
 bus

Add an auxiliary virtual bus to model the mlx4 driver structure. The
code is added along the current custom device management logic.
Subsequent patches switch mlx4_en and mlx4_ib to the auxiliary bus and
the old interface is then removed.

Structure mlx4_priv gains a new adev dynamic array to keep track of its
auxiliary devices. Access to the array is protected by the global
mlx4_intf mutex.

Functions mlx4_register_device() and mlx4_unregister_device() are
updated to expose auxiliary devices on the bus in order to load mlx4_en
and/or mlx4_ib. Functions mlx4_register_auxiliary_driver() and
mlx4_unregister_auxiliary_driver() are added to substitute
mlx4_register_interface() and mlx4_unregister_interface(), respectively.
Function mlx4_do_bond() is adjusted to walk over the adev array and
re-adds a specific auxiliary device if its driver sets the
MLX4_INTFF_BONDING flag.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/Kconfig |   1 +
 drivers/net/ethernet/mellanox/mlx4/intf.c  | 230 ++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/main.c  |  17 +-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h  |   6 +
 include/linux/mlx4/device.h                |   7 +
 include/linux/mlx4/driver.h                |  11 +
 6 files changed, 268 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index 1b4b1f6423174..825e05fb86078 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -27,6 +27,7 @@ config MLX4_EN_DCB
 config MLX4_CORE
 	tristate
 	depends on PCI
+	select AUXILIARY_BUS
 	select NET_DEVLINK
 	default n
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index d578f754d8822..79b1eaa62ac2c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -48,6 +48,89 @@ struct mlx4_device_context {
 static LIST_HEAD(intf_list);
 static LIST_HEAD(dev_list);
 static DEFINE_MUTEX(intf_mutex);
+static DEFINE_IDA(mlx4_adev_ida);
+
+static const struct mlx4_adev_device {
+	const char *suffix;
+	bool (*is_supported)(struct mlx4_dev *dev);
+} mlx4_adev_devices[1] = {};
+
+int mlx4_adev_init(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	priv->adev_idx = ida_alloc(&mlx4_adev_ida, GFP_KERNEL);
+	if (priv->adev_idx < 0)
+		return priv->adev_idx;
+
+	priv->adev = kcalloc(ARRAY_SIZE(mlx4_adev_devices),
+			     sizeof(struct mlx4_adev *), GFP_KERNEL);
+	if (!priv->adev) {
+		ida_free(&mlx4_adev_ida, priv->adev_idx);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void mlx4_adev_cleanup(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	kfree(priv->adev);
+	ida_free(&mlx4_adev_ida, priv->adev_idx);
+}
+
+static void adev_release(struct device *dev)
+{
+	struct mlx4_adev *mlx4_adev =
+		container_of(dev, struct mlx4_adev, adev.dev);
+	struct mlx4_priv *priv = mlx4_priv(mlx4_adev->mdev);
+	int idx = mlx4_adev->idx;
+
+	kfree(mlx4_adev);
+	priv->adev[idx] = NULL;
+}
+
+static struct mlx4_adev *add_adev(struct mlx4_dev *dev, int idx)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	const char *suffix = mlx4_adev_devices[idx].suffix;
+	struct auxiliary_device *adev;
+	struct mlx4_adev *madev;
+	int ret;
+
+	madev = kzalloc(sizeof(*madev), GFP_KERNEL);
+	if (!madev)
+		return ERR_PTR(-ENOMEM);
+
+	adev = &madev->adev;
+	adev->id = priv->adev_idx;
+	adev->name = suffix;
+	adev->dev.parent = &dev->persist->pdev->dev;
+	adev->dev.release = adev_release;
+	madev->mdev = dev;
+	madev->idx = idx;
+
+	ret = auxiliary_device_init(adev);
+	if (ret) {
+		kfree(madev);
+		return ERR_PTR(ret);
+	}
+
+	ret = auxiliary_device_add(adev);
+	if (ret) {
+		auxiliary_device_uninit(adev);
+		return ERR_PTR(ret);
+	}
+	return madev;
+}
+
+static void del_adev(struct auxiliary_device *adev)
+{
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
+}
 
 static void mlx4_add_device(struct mlx4_interface *intf, struct mlx4_priv *priv)
 {
@@ -120,12 +203,24 @@ void mlx4_unregister_interface(struct mlx4_interface *intf)
 }
 EXPORT_SYMBOL_GPL(mlx4_unregister_interface);
 
+int mlx4_register_auxiliary_driver(struct mlx4_adrv *madrv)
+{
+	return auxiliary_driver_register(&madrv->adrv);
+}
+EXPORT_SYMBOL_GPL(mlx4_register_auxiliary_driver);
+
+void mlx4_unregister_auxiliary_driver(struct mlx4_adrv *madrv)
+{
+	auxiliary_driver_unregister(&madrv->adrv);
+}
+EXPORT_SYMBOL_GPL(mlx4_unregister_auxiliary_driver);
+
 int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_device_context *dev_ctx = NULL, *temp_dev_ctx;
 	unsigned long flags;
-	int ret;
+	int i, ret;
 	LIST_HEAD(bond_list);
 
 	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP))
@@ -177,6 +272,57 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
 			 dev_ctx->intf->protocol, enable ?
 			 "enabled" : "disabled");
 	}
+
+	mutex_lock(&intf_mutex);
+
+	for (i = 0; i < ARRAY_SIZE(mlx4_adev_devices); i++) {
+		struct mlx4_adev *madev = priv->adev[i];
+		struct mlx4_adrv *madrv;
+		enum mlx4_protocol protocol;
+
+		if (!madev)
+			continue;
+
+		device_lock(&madev->adev.dev);
+		if (!madev->adev.dev.driver) {
+			device_unlock(&madev->adev.dev);
+			continue;
+		}
+
+		madrv = container_of(madev->adev.dev.driver, struct mlx4_adrv,
+				     adrv.driver);
+		if (!(madrv->flags & MLX4_INTFF_BONDING)) {
+			device_unlock(&madev->adev.dev);
+			continue;
+		}
+
+		if (mlx4_is_mfunc(dev)) {
+			mlx4_dbg(dev,
+				 "SRIOV, disabled HA mode for intf proto %d\n",
+				 madrv->protocol);
+			device_unlock(&madev->adev.dev);
+			continue;
+		}
+
+		protocol = madrv->protocol;
+		device_unlock(&madev->adev.dev);
+
+		del_adev(&madev->adev);
+		priv->adev[i] = add_adev(dev, i);
+		if (IS_ERR(priv->adev[i])) {
+			mlx4_warn(dev, "Device[%d] (%s) failed to load\n", i,
+				  mlx4_adev_devices[i].suffix);
+			priv->adev[i] = NULL;
+			continue;
+		}
+
+		mlx4_dbg(dev,
+			 "Interface for protocol %d restarted with bonded mode %s\n",
+			 protocol, enable ? "enabled" : "disabled");
+	}
+
+	mutex_unlock(&intf_mutex);
+
 	return 0;
 }
 
@@ -206,10 +352,80 @@ int mlx4_unregister_event_notifier(struct mlx4_dev *dev,
 }
 EXPORT_SYMBOL(mlx4_unregister_event_notifier);
 
+static int add_drivers(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int i, ret = 0;
+
+	for (i = 0; i < ARRAY_SIZE(mlx4_adev_devices); i++) {
+		bool is_supported = false;
+
+		if (priv->adev[i])
+			continue;
+
+		if (mlx4_adev_devices[i].is_supported)
+			is_supported = mlx4_adev_devices[i].is_supported(dev);
+
+		if (!is_supported)
+			continue;
+
+		priv->adev[i] = add_adev(dev, i);
+		if (IS_ERR(priv->adev[i])) {
+			mlx4_warn(dev, "Device[%d] (%s) failed to load\n", i,
+				  mlx4_adev_devices[i].suffix);
+			/* We continue to rescan drivers and leave to the caller
+			 * to make decision if to release everything or
+			 * continue. */
+			ret = PTR_ERR(priv->adev[i]);
+			priv->adev[i] = NULL;
+		}
+	}
+	return ret;
+}
+
+static void delete_drivers(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	bool delete_all;
+	int i;
+
+	delete_all = !(dev->persist->interface_state & MLX4_INTERFACE_STATE_UP);
+
+	for (i = ARRAY_SIZE(mlx4_adev_devices) - 1; i >= 0; i--) {
+		bool is_supported = false;
+
+		if (!priv->adev[i])
+			continue;
+
+		if (mlx4_adev_devices[i].is_supported && !delete_all)
+			is_supported = mlx4_adev_devices[i].is_supported(dev);
+
+		if (is_supported)
+			continue;
+
+		del_adev(&priv->adev[i]->adev);
+		priv->adev[i] = NULL;
+	}
+}
+
+/* This function is used after mlx4_dev is reconfigured.
+ */
+static int rescan_drivers_locked(struct mlx4_dev *dev)
+{
+	lockdep_assert_held(&intf_mutex);
+
+	delete_drivers(dev);
+	if (!(dev->persist->interface_state & MLX4_INTERFACE_STATE_UP))
+		return 0;
+
+	return add_drivers(dev);
+}
+
 int mlx4_register_device(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_interface *intf;
+	int ret;
 
 	mutex_lock(&intf_mutex);
 
@@ -218,10 +434,18 @@ int mlx4_register_device(struct mlx4_dev *dev)
 	list_for_each_entry(intf, &intf_list, list)
 		mlx4_add_device(intf, priv);
 
+	ret = rescan_drivers_locked(dev);
+
 	mutex_unlock(&intf_mutex);
+
+	if (ret) {
+		mlx4_unregister_device(dev);
+		return ret;
+	}
+
 	mlx4_start_catas_poll(dev);
 
-	return 0;
+	return ret;
 }
 
 void mlx4_unregister_device(struct mlx4_dev *dev)
@@ -253,6 +477,8 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 	list_del(&priv->dev_list);
 	dev->persist->interface_state &= ~MLX4_INTERFACE_STATE_UP;
 
+	rescan_drivers_locked(dev);
+
 	mutex_unlock(&intf_mutex);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 0ed490b991630..c4ec7377aa71e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3429,6 +3429,10 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
 
+	err = mlx4_adev_init(dev);
+	if (err)
+		return err;
+
 	ATOMIC_INIT_NOTIFIER_HEAD(&priv->event_nh);
 
 	mutex_init(&priv->port_mutex);
@@ -3455,10 +3459,11 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 		err = mlx4_get_ownership(dev);
 		if (err) {
 			if (err < 0)
-				return err;
+				goto err_adev;
 			else {
 				mlx4_warn(dev, "Multiple PFs not yet supported - Skipping PF\n");
-				return -EINVAL;
+				err = -EINVAL;
+				goto err_adev;
 			}
 		}
 
@@ -3806,6 +3811,9 @@ err_sriov:
 		mlx4_free_ownership(dev);
 
 	kfree(dev_cap);
+
+err_adev:
+	mlx4_adev_cleanup(dev);
 	return err;
 }
 
@@ -4186,6 +4194,8 @@ static void mlx4_unload_one(struct pci_dev *pdev)
 	mlx4_slave_destroy_special_qp_cap(dev);
 	kfree(dev->dev_vfs);
 
+	mlx4_adev_cleanup(dev);
+
 	mlx4_clean_dev(dev);
 	priv->pci_dev_data = pci_dev_data;
 	priv->removed = 1;
@@ -4573,6 +4583,9 @@ static int __init mlx4_init(void)
 {
 	int ret;
 
+	WARN_ONCE(strcmp(MLX4_ADEV_NAME, KBUILD_MODNAME),
+		  "mlx4_core name not in sync with kernel module name");
+
 	if (mlx4_verify_params())
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 73b4fdfd63f4c..36de79c8d0538 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -47,6 +47,7 @@
 #include <linux/spinlock.h>
 #include <net/devlink.h>
 #include <linux/rwsem.h>
+#include <linux/auxiliary_bus.h>
 #include <linux/notifier.h>
 
 #include <linux/mlx4/device.h>
@@ -884,6 +885,8 @@ struct mlx4_priv {
 	struct list_head	dev_list;
 	struct list_head	ctx_list;
 	spinlock_t		ctx_lock;
+	struct mlx4_adev	**adev;
+	int			adev_idx;
 	struct atomic_notifier_head event_nh;
 
 	int			pci_dev_data;
@@ -1052,6 +1055,9 @@ void mlx4_catas_end(struct mlx4_dev *dev);
 int mlx4_crdump_init(struct mlx4_dev *dev);
 void mlx4_crdump_end(struct mlx4_dev *dev);
 int mlx4_restart_one(struct pci_dev *pdev);
+
+int mlx4_adev_init(struct mlx4_dev *dev);
+void mlx4_adev_cleanup(struct mlx4_dev *dev);
 int mlx4_register_device(struct mlx4_dev *dev);
 void mlx4_unregister_device(struct mlx4_dev *dev);
 void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 049d8a4b044de..27f42f713c891 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -33,6 +33,7 @@
 #ifndef MLX4_DEVICE_H
 #define MLX4_DEVICE_H
 
+#include <linux/auxiliary_bus.h>
 #include <linux/if_ether.h>
 #include <linux/pci.h>
 #include <linux/completion.h>
@@ -889,6 +890,12 @@ struct mlx4_dev {
 	u8  uar_page_shift;
 };
 
+struct mlx4_adev {
+	struct auxiliary_device adev;
+	struct mlx4_dev *mdev;
+	int idx;
+};
+
 struct mlx4_clock_params {
 	u64 offset;
 	u8 bar;
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 781d5a0c2faa0..9cf157d381c6e 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -34,9 +34,12 @@
 #define MLX4_DRIVER_H
 
 #include <net/devlink.h>
+#include <linux/auxiliary_bus.h>
 #include <linux/notifier.h>
 #include <linux/mlx4/device.h>
 
+#define MLX4_ADEV_NAME "mlx4_core"
+
 struct mlx4_dev;
 
 #define MLX4_MAC_MASK	   0xffffffffffffULL
@@ -63,8 +66,16 @@ struct mlx4_interface {
 	int			flags;
 };
 
+struct mlx4_adrv {
+	struct auxiliary_driver	adrv;
+	enum mlx4_protocol	protocol;
+	int			flags;
+};
+
 int mlx4_register_interface(struct mlx4_interface *intf);
 void mlx4_unregister_interface(struct mlx4_interface *intf);
+int mlx4_register_auxiliary_driver(struct mlx4_adrv *madrv);
+void mlx4_unregister_auxiliary_driver(struct mlx4_adrv *madrv);
 
 int mlx4_register_event_notifier(struct mlx4_dev *dev,
 				 struct notifier_block *nb);
-- 
GitLab


From eb93ae495a73b189ab3b15d5c0e95a747cf6b6c3 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:23 +0200
Subject: [PATCH 1566/1806] mlx4: Connect the ethernet part to the auxiliary
 bus

Use the auxiliary bus to perform device management of the ethernet part
of the mlx4 driver.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_main.c | 65 ++++++++++++++------
 drivers/net/ethernet/mellanox/mlx4/intf.c    | 13 +++-
 2 files changed, 58 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 39c9befeb6388..d8f4d00ad26b6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -234,9 +234,11 @@ static int mlx4_en_event(struct notifier_block *this, unsigned long event,
 	return NOTIFY_DONE;
 }
 
-static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
+static void mlx4_en_remove(struct auxiliary_device *adev)
 {
-	struct mlx4_en_dev *mdev = endev_ptr;
+	struct mlx4_adev *madev = container_of(adev, struct mlx4_adev, adev);
+	struct mlx4_dev *dev = madev->mdev;
+	struct mlx4_en_dev *mdev = auxiliary_get_drvdata(adev);
 	int i;
 
 	mlx4_unregister_event_notifier(dev, &mdev->mlx_nb);
@@ -259,27 +261,36 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
 	kfree(mdev);
 }
 
-static void *mlx4_en_add(struct mlx4_dev *dev)
+static int mlx4_en_probe(struct auxiliary_device *adev,
+			 const struct auxiliary_device_id *id)
 {
+	struct mlx4_adev *madev = container_of(adev, struct mlx4_adev, adev);
+	struct mlx4_dev *dev = madev->mdev;
 	struct mlx4_en_dev *mdev;
 	int err, i;
 
 	printk_once(KERN_INFO "%s", mlx4_en_version);
 
 	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
-	if (!mdev)
+	if (!mdev) {
+		err = -ENOMEM;
 		goto err_free_res;
+	}
 
-	if (mlx4_pd_alloc(dev, &mdev->priv_pdn))
+	err = mlx4_pd_alloc(dev, &mdev->priv_pdn);
+	if (err)
 		goto err_free_dev;
 
-	if (mlx4_uar_alloc(dev, &mdev->priv_uar))
+	err = mlx4_uar_alloc(dev, &mdev->priv_uar);
+	if (err)
 		goto err_pd;
 
 	mdev->uar_map = ioremap((phys_addr_t) mdev->priv_uar.pfn << PAGE_SHIFT,
 				PAGE_SIZE);
-	if (!mdev->uar_map)
+	if (!mdev->uar_map) {
+		err = -ENOMEM;
 		goto err_uar;
+	}
 	spin_lock_init(&mdev->uar_lock);
 
 	mdev->dev = dev;
@@ -291,13 +302,15 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 	if (!mdev->LSO_support)
 		mlx4_warn(mdev, "LSO not supported, please upgrade to later FW version to enable LSO\n");
 
-	if (mlx4_mr_alloc(mdev->dev, mdev->priv_pdn, 0, ~0ull,
-			 MLX4_PERM_LOCAL_WRITE |  MLX4_PERM_LOCAL_READ,
-			 0, 0, &mdev->mr)) {
+	err = mlx4_mr_alloc(mdev->dev, mdev->priv_pdn, 0, ~0ull,
+			    MLX4_PERM_LOCAL_WRITE | MLX4_PERM_LOCAL_READ, 0, 0,
+			    &mdev->mr);
+	if (err) {
 		mlx4_err(mdev, "Failed allocating memory region\n");
 		goto err_map;
 	}
-	if (mlx4_mr_enable(mdev->dev, &mdev->mr)) {
+	err = mlx4_mr_enable(mdev->dev, &mdev->mr);
+	if (err) {
 		mlx4_err(mdev, "Failed enabling memory region\n");
 		goto err_mr;
 	}
@@ -317,8 +330,10 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 	 * Note: we cannot use the shared workqueue because of deadlocks caused
 	 *       by the rtnl lock */
 	mdev->workqueue = create_singlethread_workqueue("mlx4_en");
-	if (!mdev->workqueue)
+	if (!mdev->workqueue) {
+		err = -ENOMEM;
 		goto err_mr;
+	}
 
 	/* At this stage all non-port specific tasks are complete:
 	 * mark the card state as up */
@@ -346,7 +361,8 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 		mlx4_err(mdev, "Failed to create netdev notifier\n");
 	}
 
-	return mdev;
+	auxiliary_set_drvdata(adev, mdev);
+	return 0;
 
 err_mr:
 	(void) mlx4_mr_free(dev, &mdev->mr);
@@ -360,12 +376,23 @@ err_pd:
 err_free_dev:
 	kfree(mdev);
 err_free_res:
-	return NULL;
+	return err;
 }
 
-static struct mlx4_interface mlx4_en_interface = {
-	.add		= mlx4_en_add,
-	.remove		= mlx4_en_remove,
+static const struct auxiliary_device_id mlx4_en_id_table[] = {
+	{ .name = MLX4_ADEV_NAME ".eth" },
+	{},
+};
+
+MODULE_DEVICE_TABLE(auxiliary, mlx4_en_id_table);
+
+static struct mlx4_adrv mlx4_en_adrv = {
+	.adrv = {
+		.name	= "eth",
+		.probe	= mlx4_en_probe,
+		.remove	= mlx4_en_remove,
+		.id_table = mlx4_en_id_table,
+	},
 	.protocol	= MLX4_PROT_ETH,
 };
 
@@ -395,12 +422,12 @@ static int __init mlx4_en_init(void)
 	mlx4_en_verify_params();
 	mlx4_en_init_ptys2ethtool_map();
 
-	return mlx4_register_interface(&mlx4_en_interface);
+	return mlx4_register_auxiliary_driver(&mlx4_en_adrv);
 }
 
 static void __exit mlx4_en_cleanup(void)
 {
-	mlx4_unregister_interface(&mlx4_en_interface);
+	mlx4_unregister_auxiliary_driver(&mlx4_en_adrv);
 }
 
 module_init(mlx4_en_init);
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 79b1eaa62ac2c..95ff0ea435e22 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -50,10 +50,21 @@ static LIST_HEAD(dev_list);
 static DEFINE_MUTEX(intf_mutex);
 static DEFINE_IDA(mlx4_adev_ida);
 
+static bool is_eth_supported(struct mlx4_dev *dev)
+{
+	for (int port = 1; port <= dev->caps.num_ports; port++)
+		if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH)
+			return true;
+
+	return false;
+}
+
 static const struct mlx4_adev_device {
 	const char *suffix;
 	bool (*is_supported)(struct mlx4_dev *dev);
-} mlx4_adev_devices[1] = {};
+} mlx4_adev_devices[] = {
+	{ "eth", is_eth_supported },
+};
 
 int mlx4_adev_init(struct mlx4_dev *dev)
 {
-- 
GitLab


From 7d22b1cb9d84d209bdd6f43ef683d7322682d6b4 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:24 +0200
Subject: [PATCH 1567/1806] mlx4: Connect the infiniband part to the auxiliary
 bus

Use the auxiliary bus to perform device management of the infiniband
part of the mlx4 driver.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c         | 77 ++++++++++++++++-------
 drivers/net/ethernet/mellanox/mlx4/intf.c | 13 ++++
 2 files changed, 67 insertions(+), 23 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 6debee494a162..1f8d0d2c5f173 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2609,8 +2609,11 @@ static const struct ib_device_ops mlx4_ib_dev_fs_ops = {
 	.destroy_flow = mlx4_ib_destroy_flow,
 };
 
-static void *mlx4_ib_add(struct mlx4_dev *dev)
+static int mlx4_ib_probe(struct auxiliary_device *adev,
+			 const struct auxiliary_device_id *id)
 {
+	struct mlx4_adev *madev = container_of(adev, struct mlx4_adev, adev);
+	struct mlx4_dev *dev = madev->mdev;
 	struct mlx4_ib_dev *ibdev;
 	int num_ports = 0;
 	int i, j;
@@ -2630,27 +2633,31 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 
 	/* No point in registering a device with no ports... */
 	if (num_ports == 0)
-		return NULL;
+		return -ENODEV;
 
 	ibdev = ib_alloc_device(mlx4_ib_dev, ib_dev);
 	if (!ibdev) {
 		dev_err(&dev->persist->pdev->dev,
 			"Device struct alloc failed\n");
-		return NULL;
+		return -ENOMEM;
 	}
 
 	iboe = &ibdev->iboe;
 
-	if (mlx4_pd_alloc(dev, &ibdev->priv_pdn))
+	err = mlx4_pd_alloc(dev, &ibdev->priv_pdn);
+	if (err)
 		goto err_dealloc;
 
-	if (mlx4_uar_alloc(dev, &ibdev->priv_uar))
+	err = mlx4_uar_alloc(dev, &ibdev->priv_uar);
+	if (err)
 		goto err_pd;
 
 	ibdev->uar_map = ioremap((phys_addr_t) ibdev->priv_uar.pfn << PAGE_SHIFT,
 				 PAGE_SIZE);
-	if (!ibdev->uar_map)
+	if (!ibdev->uar_map) {
+		err = -ENOMEM;
 		goto err_uar;
+	}
 	MLX4_INIT_DOORBELL_LOCK(&ibdev->uar_lock);
 
 	ibdev->dev = dev;
@@ -2694,7 +2701,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 
 	spin_lock_init(&iboe->lock);
 
-	if (init_node_data(ibdev))
+	err = init_node_data(ibdev);
+	if (err)
 		goto err_map;
 	mlx4_init_sl2vl_tbl(ibdev);
 
@@ -2726,6 +2734,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		new_counter_index = kmalloc(sizeof(*new_counter_index),
 					    GFP_KERNEL);
 		if (!new_counter_index) {
+			err = -ENOMEM;
 			if (allocated)
 				mlx4_counter_free(ibdev->dev, counter_index);
 			goto err_counter;
@@ -2743,8 +2752,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 			new_counter_index =
 					kmalloc(sizeof(struct counter_index),
 						GFP_KERNEL);
-			if (!new_counter_index)
+			if (!new_counter_index) {
+				err = -ENOMEM;
 				goto err_counter;
+			}
 			new_counter_index->index = counter_index;
 			new_counter_index->allocated = 0;
 			list_add_tail(&new_counter_index->list,
@@ -2773,8 +2784,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 
 		ibdev->ib_uc_qpns_bitmap = bitmap_alloc(ibdev->steer_qpn_count,
 							GFP_KERNEL);
-		if (!ibdev->ib_uc_qpns_bitmap)
+		if (!ibdev->ib_uc_qpns_bitmap) {
+			err = -ENOMEM;
 			goto err_steer_qp_release;
+		}
 
 		if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB) {
 			bitmap_zero(ibdev->ib_uc_qpns_bitmap,
@@ -2794,17 +2807,21 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	for (j = 1; j <= ibdev->dev->caps.num_ports; j++)
 		atomic64_set(&iboe->mac[j - 1], ibdev->dev->caps.def_mac[j]);
 
-	if (mlx4_ib_alloc_diag_counters(ibdev))
+	err = mlx4_ib_alloc_diag_counters(ibdev);
+	if (err)
 		goto err_steer_free_bitmap;
 
-	if (ib_register_device(&ibdev->ib_dev, "mlx4_%d",
-			       &dev->persist->pdev->dev))
+	err = ib_register_device(&ibdev->ib_dev, "mlx4_%d",
+				 &dev->persist->pdev->dev);
+	if (err)
 		goto err_diag_counters;
 
-	if (mlx4_ib_mad_init(ibdev))
+	err = mlx4_ib_mad_init(ibdev);
+	if (err)
 		goto err_reg;
 
-	if (mlx4_ib_init_sriov(ibdev))
+	err = mlx4_ib_init_sriov(ibdev);
+	if (err)
 		goto err_mad;
 
 	if (!iboe->nb.notifier_call) {
@@ -2844,7 +2861,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	err = mlx4_register_event_notifier(dev, &ibdev->mlx_nb);
 	WARN(err, "failed to register mlx4 event notifier (%d)", err);
 
-	return ibdev;
+	auxiliary_set_drvdata(adev, ibdev);
+	return 0;
 
 err_notif:
 	if (ibdev->iboe.nb.notifier_call) {
@@ -2888,7 +2906,7 @@ err_pd:
 err_dealloc:
 	ib_dealloc_device(&ibdev->ib_dev);
 
-	return NULL;
+	return err;
 }
 
 int mlx4_ib_steer_qp_alloc(struct mlx4_ib_dev *dev, int count, int *qpn)
@@ -2955,9 +2973,11 @@ int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 	return err;
 }
 
-static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
+static void mlx4_ib_remove(struct auxiliary_device *adev)
 {
-	struct mlx4_ib_dev *ibdev = ibdev_ptr;
+	struct mlx4_adev *madev = container_of(adev, struct mlx4_adev, adev);
+	struct mlx4_dev *dev = madev->mdev;
+	struct mlx4_ib_dev *ibdev = auxiliary_get_drvdata(adev);
 	int p;
 	int i;
 
@@ -3303,9 +3323,20 @@ static int mlx4_ib_event(struct notifier_block *this, unsigned long event,
 	return NOTIFY_DONE;
 }
 
-static struct mlx4_interface mlx4_ib_interface = {
-	.add		= mlx4_ib_add,
-	.remove		= mlx4_ib_remove,
+static const struct auxiliary_device_id mlx4_ib_id_table[] = {
+	{ .name = MLX4_ADEV_NAME ".ib" },
+	{},
+};
+
+MODULE_DEVICE_TABLE(auxiliary, mlx4_ib_id_table);
+
+static struct mlx4_adrv mlx4_ib_adrv = {
+	.adrv = {
+		.name	= "ib",
+		.probe	= mlx4_ib_probe,
+		.remove	= mlx4_ib_remove,
+		.id_table = mlx4_ib_id_table,
+	},
 	.protocol	= MLX4_PROT_IB_IPV6,
 	.flags		= MLX4_INTFF_BONDING
 };
@@ -3330,7 +3361,7 @@ static int __init mlx4_ib_init(void)
 	if (err)
 		goto clean_cm;
 
-	err = mlx4_register_interface(&mlx4_ib_interface);
+	err = mlx4_register_auxiliary_driver(&mlx4_ib_adrv);
 	if (err)
 		goto clean_mcg;
 
@@ -3352,7 +3383,7 @@ clean_qp_event:
 
 static void __exit mlx4_ib_cleanup(void)
 {
-	mlx4_unregister_interface(&mlx4_ib_interface);
+	mlx4_unregister_auxiliary_driver(&mlx4_ib_adrv);
 	mlx4_ib_mcg_destroy();
 	mlx4_ib_cm_destroy();
 	mlx4_ib_qp_event_cleanup();
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 95ff0ea435e22..7579031786acc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -59,11 +59,24 @@ static bool is_eth_supported(struct mlx4_dev *dev)
 	return false;
 }
 
+static bool is_ib_supported(struct mlx4_dev *dev)
+{
+	for (int port = 1; port <= dev->caps.num_ports; port++)
+		if (dev->caps.port_type[port] == MLX4_PORT_TYPE_IB)
+			return true;
+
+	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE)
+		return true;
+
+	return false;
+}
+
 static const struct mlx4_adev_device {
 	const char *suffix;
 	bool (*is_supported)(struct mlx4_dev *dev);
 } mlx4_adev_devices[] = {
 	{ "eth", is_eth_supported },
+	{ "ib", is_ib_supported },
 };
 
 int mlx4_adev_init(struct mlx4_dev *dev)
-- 
GitLab


From c138cdb89a14ce00d45e77d3db18263e4b9f9465 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 21 Aug 2023 15:12:25 +0200
Subject: [PATCH 1568/1806] mlx4: Delete custom device management logic

After the conversion to use the auxiliary bus, the custom device
management is not needed anymore and can be deleted.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/intf.c | 125 ----------------------
 drivers/net/ethernet/mellanox/mlx4/main.c |  28 -----
 drivers/net/ethernet/mellanox/mlx4/mlx4.h |   3 -
 include/linux/mlx4/driver.h               |  10 --
 4 files changed, 166 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 7579031786acc..a371b970ac1e2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -38,15 +38,6 @@
 
 #include "mlx4.h"
 
-struct mlx4_device_context {
-	struct list_head	list;
-	struct list_head	bond_list;
-	struct mlx4_interface  *intf;
-	void		       *context;
-};
-
-static LIST_HEAD(intf_list);
-static LIST_HEAD(dev_list);
 static DEFINE_MUTEX(intf_mutex);
 static DEFINE_IDA(mlx4_adev_ida);
 
@@ -156,77 +147,6 @@ static void del_adev(struct auxiliary_device *adev)
 	auxiliary_device_uninit(adev);
 }
 
-static void mlx4_add_device(struct mlx4_interface *intf, struct mlx4_priv *priv)
-{
-	struct mlx4_device_context *dev_ctx;
-
-	dev_ctx = kmalloc(sizeof(*dev_ctx), GFP_KERNEL);
-	if (!dev_ctx)
-		return;
-
-	dev_ctx->intf    = intf;
-	dev_ctx->context = intf->add(&priv->dev);
-
-	if (dev_ctx->context) {
-		spin_lock_irq(&priv->ctx_lock);
-		list_add_tail(&dev_ctx->list, &priv->ctx_list);
-		spin_unlock_irq(&priv->ctx_lock);
-	} else
-		kfree(dev_ctx);
-
-}
-
-static void mlx4_remove_device(struct mlx4_interface *intf, struct mlx4_priv *priv)
-{
-	struct mlx4_device_context *dev_ctx;
-
-	list_for_each_entry(dev_ctx, &priv->ctx_list, list)
-		if (dev_ctx->intf == intf) {
-			spin_lock_irq(&priv->ctx_lock);
-			list_del(&dev_ctx->list);
-			spin_unlock_irq(&priv->ctx_lock);
-
-			intf->remove(&priv->dev, dev_ctx->context);
-			kfree(dev_ctx);
-			return;
-		}
-}
-
-int mlx4_register_interface(struct mlx4_interface *intf)
-{
-	struct mlx4_priv *priv;
-
-	if (!intf->add || !intf->remove)
-		return -EINVAL;
-
-	mutex_lock(&intf_mutex);
-
-	list_add_tail(&intf->list, &intf_list);
-	list_for_each_entry(priv, &dev_list, dev_list) {
-		mlx4_add_device(intf, priv);
-	}
-
-	mutex_unlock(&intf_mutex);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx4_register_interface);
-
-void mlx4_unregister_interface(struct mlx4_interface *intf)
-{
-	struct mlx4_priv *priv;
-
-	mutex_lock(&intf_mutex);
-
-	list_for_each_entry(priv, &dev_list, dev_list)
-		mlx4_remove_device(intf, priv);
-
-	list_del(&intf->list);
-
-	mutex_unlock(&intf_mutex);
-}
-EXPORT_SYMBOL_GPL(mlx4_unregister_interface);
-
 int mlx4_register_auxiliary_driver(struct mlx4_adrv *madrv)
 {
 	return auxiliary_driver_register(&madrv->adrv);
@@ -242,10 +162,7 @@ EXPORT_SYMBOL_GPL(mlx4_unregister_auxiliary_driver);
 int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	struct mlx4_device_context *dev_ctx = NULL, *temp_dev_ctx;
-	unsigned long flags;
 	int i, ret;
-	LIST_HEAD(bond_list);
 
 	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP))
 		return -EOPNOTSUPP;
@@ -267,36 +184,6 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
 		dev->flags &= ~MLX4_FLAG_BONDED;
 	}
 
-	spin_lock_irqsave(&priv->ctx_lock, flags);
-	list_for_each_entry_safe(dev_ctx, temp_dev_ctx, &priv->ctx_list, list) {
-		if (!(dev_ctx->intf->flags & MLX4_INTFF_BONDING))
-			continue;
-
-		if (mlx4_is_mfunc(dev)) {
-			mlx4_dbg(dev,
-				 "SRIOV, disabled HA mode for intf proto %d\n",
-				 dev_ctx->intf->protocol);
-			continue;
-		}
-
-		list_add_tail(&dev_ctx->bond_list, &bond_list);
-		list_del(&dev_ctx->list);
-	}
-	spin_unlock_irqrestore(&priv->ctx_lock, flags);
-
-	list_for_each_entry(dev_ctx, &bond_list, bond_list) {
-		dev_ctx->intf->remove(dev, dev_ctx->context);
-		dev_ctx->context =  dev_ctx->intf->add(dev);
-
-		spin_lock_irqsave(&priv->ctx_lock, flags);
-		list_add_tail(&dev_ctx->list, &priv->ctx_list);
-		spin_unlock_irqrestore(&priv->ctx_lock, flags);
-
-		mlx4_dbg(dev, "Interface for protocol %d restarted with bonded mode %s\n",
-			 dev_ctx->intf->protocol, enable ?
-			 "enabled" : "disabled");
-	}
-
 	mutex_lock(&intf_mutex);
 
 	for (i = 0; i < ARRAY_SIZE(mlx4_adev_devices); i++) {
@@ -447,16 +334,11 @@ static int rescan_drivers_locked(struct mlx4_dev *dev)
 
 int mlx4_register_device(struct mlx4_dev *dev)
 {
-	struct mlx4_priv *priv = mlx4_priv(dev);
-	struct mlx4_interface *intf;
 	int ret;
 
 	mutex_lock(&intf_mutex);
 
 	dev->persist->interface_state |= MLX4_INTERFACE_STATE_UP;
-	list_add_tail(&priv->dev_list, &dev_list);
-	list_for_each_entry(intf, &intf_list, list)
-		mlx4_add_device(intf, priv);
 
 	ret = rescan_drivers_locked(dev);
 
@@ -474,9 +356,6 @@ int mlx4_register_device(struct mlx4_dev *dev)
 
 void mlx4_unregister_device(struct mlx4_dev *dev)
 {
-	struct mlx4_priv *priv = mlx4_priv(dev);
-	struct mlx4_interface *intf;
-
 	if (!(dev->persist->interface_state & MLX4_INTERFACE_STATE_UP))
 		return;
 
@@ -495,10 +374,6 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 	}
 	mutex_lock(&intf_mutex);
 
-	list_for_each_entry(intf, &intf_list, list)
-		mlx4_remove_device(intf, priv);
-
-	list_del(&priv->dev_list);
 	dev->persist->interface_state &= ~MLX4_INTERFACE_STATE_UP;
 
 	rescan_drivers_locked(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index c4ec7377aa71e..2581226836b59 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -42,7 +42,6 @@
 #include <linux/slab.h>
 #include <linux/io-mapping.h>
 #include <linux/delay.h>
-#include <linux/kmod.h>
 #include <linux/etherdevice.h>
 #include <net/devlink.h>
 
@@ -1091,27 +1090,6 @@ free_mem:
 	return err;
 }
 
-static void mlx4_request_modules(struct mlx4_dev *dev)
-{
-	int port;
-	int has_ib_port = false;
-	int has_eth_port = false;
-#define EN_DRV_NAME	"mlx4_en"
-#define IB_DRV_NAME	"mlx4_ib"
-
-	for (port = 1; port <= dev->caps.num_ports; port++) {
-		if (dev->caps.port_type[port] == MLX4_PORT_TYPE_IB)
-			has_ib_port = true;
-		else if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH)
-			has_eth_port = true;
-	}
-
-	if (has_eth_port)
-		request_module_nowait(EN_DRV_NAME);
-	if (has_ib_port || (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
-		request_module_nowait(IB_DRV_NAME);
-}
-
 /*
  * Change the port configuration of the device.
  * Every user of this function must hold the port mutex.
@@ -1147,7 +1125,6 @@ int mlx4_change_port_types(struct mlx4_dev *dev,
 			mlx4_err(dev, "Failed to register device\n");
 			goto out;
 		}
-		mlx4_request_modules(dev);
 	}
 
 out:
@@ -3426,9 +3403,6 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 	devl_assert_locked(devlink);
 	dev = &priv->dev;
 
-	INIT_LIST_HEAD(&priv->ctx_list);
-	spin_lock_init(&priv->ctx_lock);
-
 	err = mlx4_adev_init(dev);
 	if (err)
 		return err;
@@ -3732,8 +3706,6 @@ slave_start:
 	if (err)
 		goto err_port;
 
-	mlx4_request_modules(dev);
-
 	mlx4_sense_init(dev);
 	mlx4_start_sense(dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 36de79c8d0538..d7d856d1758a3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -882,9 +882,6 @@ enum {
 struct mlx4_priv {
 	struct mlx4_dev		dev;
 
-	struct list_head	dev_list;
-	struct list_head	ctx_list;
-	spinlock_t		ctx_lock;
 	struct mlx4_adev	**adev;
 	int			adev_idx;
 	struct atomic_notifier_head event_nh;
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 9cf157d381c6e..69825223081f3 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -58,22 +58,12 @@ enum {
 	MLX4_INTFF_BONDING	= 1 << 0
 };
 
-struct mlx4_interface {
-	void *			(*add)	 (struct mlx4_dev *dev);
-	void			(*remove)(struct mlx4_dev *dev, void *context);
-	struct list_head	list;
-	enum mlx4_protocol	protocol;
-	int			flags;
-};
-
 struct mlx4_adrv {
 	struct auxiliary_driver	adrv;
 	enum mlx4_protocol	protocol;
 	int			flags;
 };
 
-int mlx4_register_interface(struct mlx4_interface *intf);
-void mlx4_unregister_interface(struct mlx4_interface *intf);
 int mlx4_register_auxiliary_driver(struct mlx4_adrv *madrv);
 void mlx4_unregister_auxiliary_driver(struct mlx4_adrv *madrv);
 
-- 
GitLab


From 45f9cb6bd9716461faf0613dcc13f181a526a9e2 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Mon, 21 Aug 2023 21:35:28 +0800
Subject: [PATCH 1569/1806] dp83640: Use list_for_each_entry() helper

Convert list_for_each() to list_for_each_entry() where applicable.

No functional changed.

Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index ef8b14135133e..2657be7cc049f 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -631,7 +631,6 @@ static void recalibrate(struct dp83640_clock *clock)
 	s64 now, diff;
 	struct phy_txts event_ts;
 	struct timespec64 ts;
-	struct list_head *this;
 	struct dp83640_private *tmp;
 	struct phy_device *master = clock->chosen->phydev;
 	u16 cal_gpio, cfg0, evnt, ptp_trig, trigger, val;
@@ -648,8 +647,7 @@ static void recalibrate(struct dp83640_clock *clock)
 	/*
 	 * enable broadcast, disable status frames, enable ptp clock
 	 */
-	list_for_each(this, &clock->phylist) {
-		tmp = list_entry(this, struct dp83640_private, list);
+	list_for_each_entry(tmp, &clock->phylist, list) {
 		enable_broadcast(tmp->phydev, clock->page, 1);
 		tmp->cfg0 = ext_read(tmp->phydev, PAGE5, PSF_CFG0);
 		ext_write(0, tmp->phydev, PAGE5, PSF_CFG0, 0);
@@ -667,10 +665,8 @@ static void recalibrate(struct dp83640_clock *clock)
 	evnt |= (CAL_EVENT & EVNT_SEL_MASK) << EVNT_SEL_SHIFT;
 	evnt |= (cal_gpio & EVNT_GPIO_MASK) << EVNT_GPIO_SHIFT;
 
-	list_for_each(this, &clock->phylist) {
-		tmp = list_entry(this, struct dp83640_private, list);
+	list_for_each_entry(tmp, &clock->phylist, list)
 		ext_write(0, tmp->phydev, PAGE5, PTP_EVNT, evnt);
-	}
 	ext_write(0, master, PAGE5, PTP_EVNT, evnt);
 
 	/*
@@ -709,8 +705,7 @@ static void recalibrate(struct dp83640_clock *clock)
 	event_ts.sec_hi = ext_read(master, PAGE4, PTP_EDATA);
 	now = phy2txts(&event_ts);
 
-	list_for_each(this, &clock->phylist) {
-		tmp = list_entry(this, struct dp83640_private, list);
+	list_for_each_entry(tmp, &clock->phylist, list) {
 		val = ext_read(tmp->phydev, PAGE4, PTP_STS);
 		phydev_info(tmp->phydev, "slave  PTP_STS  0x%04hx\n", val);
 		val = ext_read(tmp->phydev, PAGE4, PTP_ESTS);
@@ -730,10 +725,8 @@ static void recalibrate(struct dp83640_clock *clock)
 	/*
 	 * restore status frames
 	 */
-	list_for_each(this, &clock->phylist) {
-		tmp = list_entry(this, struct dp83640_private, list);
+	list_for_each_entry(tmp, &clock->phylist, list)
 		ext_write(0, tmp->phydev, PAGE5, PSF_CFG0, tmp->cfg0);
-	}
 	ext_write(0, master, PAGE5, PSF_CFG0, cfg0);
 
 	mutex_unlock(&clock->extreg_lock);
-- 
GitLab


From dae64749db25be11ebfef2cf704cd451a25d3cfa Mon Sep 17 00:00:00 2001
From: Feng Liu <feliu@nvidia.com>
Date: Mon, 21 Aug 2023 10:27:13 -0400
Subject: [PATCH 1570/1806] virtio_net: Introduce skb_vnet_common_hdr to avoid
 typecasting

The virtio_net driver currently deals with different versions and types
of virtio net headers, such as virtio_net_hdr_mrg_rxbuf,
virtio_net_hdr_v1_hash, etc. Due to these variations, the code relies
on multiple type casts to convert memory between different structures,
potentially leading to bugs when there are changes in these structures.

Introduces the "struct skb_vnet_common_hdr" as a unifying header
structure using a union. With this approach, various virtio net header
structures can be converted by accessing different members of this
structure, thus eliminating the need for type casting and reducing the
risk of potential bugs.

For example following code:
static struct sk_buff *page_to_skb(struct virtnet_info *vi,
		struct receive_queue *rq,
		struct page *page, unsigned int offset,
		unsigned int len, unsigned int truesize,
		unsigned int headroom)
{
[...]
	struct virtio_net_hdr_mrg_rxbuf *hdr;
[...]
	hdr_len = vi->hdr_len;
[...]
ok:
	hdr = skb_vnet_hdr(skb);
	memcpy(hdr, hdr_p, hdr_len);
[...]
}

When VIRTIO_NET_F_HASH_REPORT feature is enabled, hdr_len = 20
But the sizeof(*hdr) is 12,
memcpy(hdr, hdr_p, hdr_len); will copy 20 bytes to the hdr,
which make a potential risk of bug. And this risk can be avoided by
introducing struct skb_vnet_common_hdr.

Change log
v1->v2
feedback from Willem de Bruijn <willemdebruijn.kernel@gmail.com>
feedback from Simon Horman <horms@kernel.org>
1. change to use net-next tree.
2. move skb_vnet_common_hdr inside kernel file instead of the UAPI header.

v2->v3
feedback from Willem de Bruijn <willemdebruijn.kernel@gmail.com>
1. fix typo in commit message.
2. add original struct virtio_net_hdr into union
3. remove virtio_net_hdr_mrg_rxbuf variable in receive_buf;

Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 494242bb9cf60..231ad91a919d1 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -312,6 +312,14 @@ struct padded_vnet_hdr {
 	char padding[12];
 };
 
+struct virtio_net_common_hdr {
+	union {
+		struct virtio_net_hdr hdr;
+		struct virtio_net_hdr_mrg_rxbuf	mrg_hdr;
+		struct virtio_net_hdr_v1_hash hash_v1_hdr;
+	};
+};
+
 static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
 static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
 
@@ -353,9 +361,10 @@ static int rxq2vq(int rxq)
 	return rxq * 2;
 }
 
-static inline struct virtio_net_hdr_mrg_rxbuf *skb_vnet_hdr(struct sk_buff *skb)
+static inline struct virtio_net_common_hdr *
+skb_vnet_common_hdr(struct sk_buff *skb)
 {
-	return (struct virtio_net_hdr_mrg_rxbuf *)skb->cb;
+	return (struct virtio_net_common_hdr *)skb->cb;
 }
 
 /*
@@ -478,7 +487,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   unsigned int headroom)
 {
 	struct sk_buff *skb;
-	struct virtio_net_hdr_mrg_rxbuf *hdr;
+	struct virtio_net_common_hdr *hdr;
 	unsigned int copy, hdr_len, hdr_padded_len;
 	struct page *page_to_free = NULL;
 	int tailroom, shinfo_size;
@@ -563,7 +572,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 		give_pages(rq, page);
 
 ok:
-	hdr = skb_vnet_hdr(skb);
+	hdr = skb_vnet_common_hdr(skb);
 	memcpy(hdr, hdr_p, hdr_len);
 	if (page_to_free)
 		put_page(page_to_free);
@@ -975,7 +984,7 @@ static struct sk_buff *receive_small_build_skb(struct virtnet_info *vi,
 		return NULL;
 
 	buf += header_offset;
-	memcpy(skb_vnet_hdr(skb), buf, vi->hdr_len);
+	memcpy(skb_vnet_common_hdr(skb), buf, vi->hdr_len);
 
 	return skb;
 }
@@ -1586,7 +1595,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
-	struct virtio_net_hdr_mrg_rxbuf *hdr;
+	struct virtio_net_common_hdr *hdr;
 
 	if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
@@ -1606,9 +1615,9 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	if (unlikely(!skb))
 		return;
 
-	hdr = skb_vnet_hdr(skb);
+	hdr = skb_vnet_common_hdr(skb);
 	if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report)
-		virtio_skb_set_hash((const struct virtio_net_hdr_v1_hash *)hdr, skb);
+		virtio_skb_set_hash(&hdr->hash_v1_hdr, skb);
 
 	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -2114,7 +2123,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	if (can_push)
 		hdr = (struct virtio_net_hdr_mrg_rxbuf *)(skb->data - hdr_len);
 	else
-		hdr = skb_vnet_hdr(skb);
+		hdr = &skb_vnet_common_hdr(skb)->mrg_hdr;
 
 	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
 				    virtio_is_little_endian(vi->vdev), false,
-- 
GitLab


From 0bdf399342c5acbd817c9098b6c7ed21f1974312 Mon Sep 17 00:00:00 2001
From: Jordan Rife <jrife@google.com>
Date: Mon, 21 Aug 2023 16:45:23 -0500
Subject: [PATCH 1571/1806] net: Avoid address overwrite in kernel_connect

BPF programs that run on connect can rewrite the connect address. For
the connect system call this isn't a problem, because a copy of the address
is made when it is moved into kernel space. However, kernel_connect
simply passes through the address it is given, so the caller may observe
its address value unexpectedly change.

A practical example where this is problematic is where NFS is combined
with a system such as Cilium which implements BPF-based load balancing.
A common pattern in software-defined storage systems is to have an NFS
mount that connects to a persistent virtual IP which in turn maps to an
ephemeral server IP. This is usually done to achieve high availability:
if your server goes down you can quickly spin up a replacement and remap
the virtual IP to that endpoint. With BPF-based load balancing, mounts
will forget the virtual IP address when the address rewrite occurs
because a pointer to the only copy of that address is passed down the
stack. Server failover then breaks, because clients have forgotten the
virtual IP address. Reconnects fail and mounts remain broken. This patch
was tested by setting up a scenario like this and ensuring that NFS
reconnects worked after applying the patch.

Signed-off-by: Jordan Rife <jrife@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/socket.c b/net/socket.c
index fdb5233bf560c..848116d06b511 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -3567,7 +3567,12 @@ EXPORT_SYMBOL(kernel_accept);
 int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
 		   int flags)
 {
-	return READ_ONCE(sock->ops)->connect(sock, addr, addrlen, flags);
+	struct sockaddr_storage address;
+
+	memcpy(&address, addr, addrlen);
+
+	return READ_ONCE(sock->ops)->connect(sock, (struct sockaddr *)&address,
+					     addrlen, flags);
 }
 EXPORT_SYMBOL(kernel_connect);
 
-- 
GitLab


From 2e0c8ee2b56ffaf4ceac934d75f131a9c9becf72 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= <alexis.lothore@bootlin.com>
Date: Tue, 22 Aug 2023 10:41:12 +0200
Subject: [PATCH 1572/1806] net: dsa: rzn1-a5psw: remove redundant logs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove debug logs in port vlan management, since there are already multiple
tracepoints defined for those operations in DSA

Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rzn1_a5psw.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c
index 9167e83fbceb2..2eda10b33f2e5 100644
--- a/drivers/net/dsa/rzn1_a5psw.c
+++ b/drivers/net/dsa/rzn1_a5psw.c
@@ -735,10 +735,6 @@ static int a5psw_port_vlan_add(struct dsa_switch *ds, int port,
 	u16 vid = vlan->vid;
 	int vlan_res_id;
 
-	dev_dbg(a5psw->dev, "Add VLAN %d on port %d, %s, %s\n",
-		vid, port, tagged ? "tagged" : "untagged",
-		pvid ? "PVID" : "no PVID");
-
 	vlan_res_id = a5psw_find_vlan_entry(a5psw, vid);
 	if (vlan_res_id < 0) {
 		vlan_res_id = a5psw_new_vlan_res_entry(a5psw, vid);
@@ -767,8 +763,6 @@ static int a5psw_port_vlan_del(struct dsa_switch *ds, int port,
 	u16 vid = vlan->vid;
 	int vlan_res_id;
 
-	dev_dbg(a5psw->dev, "Removing VLAN %d on port %d\n", vid, port);
-
 	vlan_res_id = a5psw_find_vlan_entry(a5psw, vid);
 	if (vlan_res_id < 0)
 		return -EINVAL;
-- 
GitLab


From e3b3a87967cef1fa157d93fd726960b1b812401d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 22 Aug 2023 14:51:42 -0700
Subject: [PATCH 1573/1806] bnxt: use the NAPI skb allocation cache

All callers of build_skb() (*) in bnxt are in NAPI context.
The budget checking is somewhat convoluted because in the shared
completion queue cases Rx packets are discarded by netpoll
by forcing an error (E). But that happens before skb allocation.
Only a call chain starting at __bnxt_poll_work() can lead to
an skb allocation and it checks budget (b).

* bnxt_rx_multi_page_skb
* bnxt_rx_skb
  ` bp->rx_skb_func
  * bnxt_tpa_end
    ` bnxt_rx_pkt
      E bnxt_force_rx_discard
      E bnxt_poll_nitroa0
      b __bnxt_poll_work

Use napi_build_skb() to take advantage of the skb cache.
In iperf tests with HW-GRO enabled it barely makes a difference
but in cases where HW-GRO is not as effective (or disabled) it
can give even a >10% boost (20.7Gbps -> 23.1Gbps).

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5d6ea2782c2fc..5cc0dbe121327 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -994,7 +994,7 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp,
 	dma_addr -= bp->rx_dma_offset;
 	dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
 				bp->rx_dir);
-	skb = build_skb(data_ptr - bp->rx_offset, BNXT_RX_PAGE_SIZE);
+	skb = napi_build_skb(data_ptr - bp->rx_offset, BNXT_RX_PAGE_SIZE);
 	if (!skb) {
 		page_pool_recycle_direct(rxr->page_pool, page);
 		return NULL;
@@ -1069,7 +1069,7 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
 		return NULL;
 	}
 
-	skb = build_skb(data, bp->rx_buf_size);
+	skb = napi_build_skb(data, bp->rx_buf_size);
 	dma_unmap_single_attrs(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size,
 			       bp->rx_dir, DMA_ATTR_WEAK_ORDERING);
 	if (!skb) {
@@ -1677,7 +1677,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		tpa_info->data_ptr = new_data + bp->rx_offset;
 		tpa_info->mapping = new_mapping;
 
-		skb = build_skb(data, bp->rx_buf_size);
+		skb = napi_build_skb(data, bp->rx_buf_size);
 		dma_unmap_single_attrs(&bp->pdev->dev, mapping,
 				       bp->rx_buf_use_size, bp->rx_dir,
 				       DMA_ATTR_WEAK_ORDERING);
-- 
GitLab


From 5f48e91624b35fc85d087978feaea70a8c35be56 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Thu, 3 Aug 2023 15:34:40 +0800
Subject: [PATCH 1574/1806] wifi: rsi: rsi_91x_coex: Remove unnecessary (void*)
 conversions

No need cast (void*) to (struct rsi_coex_ctrl_block *) or
(struct rsi_common *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230803073440.3666204-1-yunchuan@nfschina.com
---
 drivers/net/wireless/rsi/rsi_91x_coex.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_coex.c b/drivers/net/wireless/rsi/rsi_91x_coex.c
index 45ac9371f2621..372eaaa2b9efc 100644
--- a/drivers/net/wireless/rsi/rsi_91x_coex.c
+++ b/drivers/net/wireless/rsi/rsi_91x_coex.c
@@ -52,8 +52,7 @@ static void rsi_coex_sched_tx_pkts(struct rsi_coex_ctrl_block *coex_cb)
 
 static void rsi_coex_scheduler_thread(struct rsi_common *common)
 {
-	struct rsi_coex_ctrl_block *coex_cb =
-		(struct rsi_coex_ctrl_block *)common->coex_cb;
+	struct rsi_coex_ctrl_block *coex_cb = common->coex_cb;
 	u32 timeout = EVENT_WAIT_FOREVER;
 
 	do {
@@ -100,9 +99,8 @@ static inline int rsi_map_coex_q(u8 hal_queue)
 
 int rsi_coex_send_pkt(void *priv, struct sk_buff *skb, u8 hal_queue)
 {
-	struct rsi_common *common = (struct rsi_common *)priv;
-	struct rsi_coex_ctrl_block *coex_cb =
-		(struct rsi_coex_ctrl_block *)common->coex_cb;
+	struct rsi_common *common = priv;
+	struct rsi_coex_ctrl_block *coex_cb = common->coex_cb;
 	struct skb_info *tx_params = NULL;
 	enum rsi_coex_queues coex_q;
 	int status;
@@ -168,8 +166,7 @@ int rsi_coex_attach(struct rsi_common *common)
 
 void rsi_coex_detach(struct rsi_common *common)
 {
-	struct rsi_coex_ctrl_block *coex_cb =
-		(struct rsi_coex_ctrl_block *)common->coex_cb;
+	struct rsi_coex_ctrl_block *coex_cb = common->coex_cb;
 	int cnt;
 
 	rsi_kill_thread(&coex_cb->coex_tx_thread);
-- 
GitLab


From 148924e537df01598870c7c55092e61859df292c Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Thu, 3 Aug 2023 15:34:55 +0800
Subject: [PATCH 1575/1806] wifi: rsi: rsi_91x_debugfs: Remove unnecessary
 (void*) conversions

No need cast (void*) to (struct rsi_91x_sdiodev *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230803073455.3666306-1-yunchuan@nfschina.com
---
 drivers/net/wireless/rsi/rsi_91x_debugfs.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_debugfs.c b/drivers/net/wireless/rsi/rsi_91x_debugfs.c
index bf22fd9482765..c528e6ca2c8dc 100644
--- a/drivers/net/wireless/rsi/rsi_91x_debugfs.c
+++ b/drivers/net/wireless/rsi/rsi_91x_debugfs.c
@@ -28,8 +28,7 @@ static int rsi_sdio_stats_read(struct seq_file *seq, void *data)
 {
 	struct rsi_common *common = seq->private;
 	struct rsi_hw *adapter = common->priv;
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 
 	seq_printf(seq, "total_sdio_interrupts: %d\n",
 		   dev->rx_info.sdio_int_counter);
-- 
GitLab


From 52424e0c49d614cbeec3a7a9f5e0fcfe123a5601 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Thu, 3 Aug 2023 15:35:07 +0800
Subject: [PATCH 1576/1806] wifi: rsi: rsi_91x_hal: Remove unnecessary
 conversions

No need cast (struct rsi_hw *) to (struct rsi_hw *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230803073507.3666471-1-yunchuan@nfschina.com
---
 drivers/net/wireless/rsi/rsi_91x_hal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index d4489b9438735..2cebe562a1f4b 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -424,7 +424,7 @@ out:
 
 int rsi_prepare_beacon(struct rsi_common *common, struct sk_buff *skb)
 {
-	struct rsi_hw *adapter = (struct rsi_hw *)common->priv;
+	struct rsi_hw *adapter = common->priv;
 	struct rsi_data_desc *bcn_frm;
 	struct ieee80211_hw *hw = common->priv->hw;
 	struct ieee80211_conf *conf = &hw->conf;
-- 
GitLab


From 6d5d2dbd00bfc320d642f7c3911dee4f43db5fea Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Thu, 3 Aug 2023 15:35:17 +0800
Subject: [PATCH 1577/1806] wifi: rsi: rsi_91x_mac80211: Remove unnecessary
 conversions

No need cast (struct rsi_hw *) to (struct rsi_hw *),
or cast (struct rsi_common *) to (struct rsi_common *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230803073517.3666559-1-yunchuan@nfschina.com
---
 drivers/net/wireless/rsi/rsi_91x_mac80211.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
index bc1f038d16550..05890536e3538 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
@@ -1763,8 +1763,8 @@ static int rsi_mac80211_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			    struct ieee80211_channel *chan, int duration,
 			    enum ieee80211_roc_type type)
 {
-	struct rsi_hw *adapter = (struct rsi_hw *)hw->priv;
-	struct rsi_common *common = (struct rsi_common *)adapter->priv;
+	struct rsi_hw *adapter = hw->priv;
+	struct rsi_common *common = adapter->priv;
 	int status = 0;
 
 	rsi_dbg(INFO_ZONE, "***** Remain on channel *****\n");
-- 
GitLab


From db2be1a01fc540ba12135b8ae9ec1acc0634dfa8 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Thu, 3 Aug 2023 15:35:29 +0800
Subject: [PATCH 1578/1806] wifi: rsi: rsi_91x_main: Remove unnecessary (void*)
 conversions

No need cast (void*) to (struct rsi_common *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230803073529.3666653-1-yunchuan@nfschina.com
---
 drivers/net/wireless/rsi/rsi_91x_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c
index f9f004446b07d..2112d8d277a99 100644
--- a/drivers/net/wireless/rsi/rsi_91x_main.c
+++ b/drivers/net/wireless/rsi/rsi_91x_main.c
@@ -270,14 +270,14 @@ static void rsi_tx_scheduler_thread(struct rsi_common *common)
 #ifdef CONFIG_RSI_COEX
 enum rsi_host_intf rsi_get_host_intf(void *priv)
 {
-	struct rsi_common *common = (struct rsi_common *)priv;
+	struct rsi_common *common = priv;
 
 	return common->priv->rsi_host_intf;
 }
 
 void rsi_set_bt_context(void *priv, void *bt_context)
 {
-	struct rsi_common *common = (struct rsi_common *)priv;
+	struct rsi_common *common = priv;
 
 	common->bt_adapter = bt_context;
 }
-- 
GitLab


From f9bf6e729f4ebcd81729ee96ecbc465796318ebd Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Thu, 3 Aug 2023 15:35:39 +0800
Subject: [PATCH 1579/1806] wifi: rsi: rsi_91x_sdio: Remove unnecessary (void*)
 conversions

No need cast (void*) to (struct rsi_91x_sdiodev *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230803073539.3666735-1-yunchuan@nfschina.com
---
 drivers/net/wireless/rsi/rsi_91x_sdio.c | 39 +++++++++----------------
 1 file changed, 14 insertions(+), 25 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c
index 1911fef3bbad6..8e7b757475d26 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c
@@ -144,8 +144,7 @@ static int rsi_issue_sdiocommand(struct sdio_func *func,
 static void rsi_handle_interrupt(struct sdio_func *function)
 {
 	struct rsi_hw *adapter = sdio_get_drvdata(function);
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 
 	if (adapter->priv->fsm_state == FSM_FW_NOT_LOADED)
 		return;
@@ -337,8 +336,7 @@ static void rsi_reset_card(struct sdio_func *pfunction)
  */
 static void rsi_setclock(struct rsi_hw *adapter, u32 freq)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	struct mmc_host *host = dev->pfunction->card->host;
 	u32 clock;
 
@@ -358,8 +356,7 @@ static void rsi_setclock(struct rsi_hw *adapter, u32 freq)
  */
 static int rsi_setblocklength(struct rsi_hw *adapter, u32 length)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	int status;
 	rsi_dbg(INIT_ZONE, "%s: Setting the block length\n", __func__);
 
@@ -380,8 +377,7 @@ static int rsi_setblocklength(struct rsi_hw *adapter, u32 length)
  */
 static int rsi_setupcard(struct rsi_hw *adapter)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	int status = 0;
 
 	rsi_setclock(adapter, 50000);
@@ -407,8 +403,7 @@ int rsi_sdio_read_register(struct rsi_hw *adapter,
 			   u32 addr,
 			   u8 *data)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	u8 fun_num = 0;
 	int status;
 
@@ -441,8 +436,7 @@ int rsi_sdio_write_register(struct rsi_hw *adapter,
 			    u32 addr,
 			    u8 *data)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	int status = 0;
 
 	if (likely(dev->sdio_irq_task != current))
@@ -495,8 +489,7 @@ static int rsi_sdio_read_register_multiple(struct rsi_hw *adapter,
 					   u8 *data,
 					   u16 count)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	u32 status;
 
 	if (likely(dev->sdio_irq_task != current))
@@ -527,8 +520,7 @@ int rsi_sdio_write_register_multiple(struct rsi_hw *adapter,
 				     u8 *data,
 				     u16 count)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	int status;
 
 	if (dev->write_fail > 1) {
@@ -762,8 +754,7 @@ static int rsi_sdio_host_intf_write_pkt(struct rsi_hw *adapter,
 					u8 *pkt,
 					u32 len)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	u32 block_size = dev->tx_blk_size;
 	u32 num_blocks, address, length;
 	u32 queueno;
@@ -1045,7 +1036,7 @@ static int rsi_probe(struct sdio_func *pfunction,
 		goto fail_free_adapter;
 	}
 
-	sdev = (struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	sdev = adapter->rsi_dev;
 	rsi_init_event(&sdev->rx_thread.event);
 	status = rsi_create_kthread(adapter->priv, &sdev->rx_thread,
 				    rsi_sdio_rx_thread, "SDIO-RX-Thread");
@@ -1221,7 +1212,7 @@ static void rsi_disconnect(struct sdio_func *pfunction)
 	if (!adapter)
 		return;
 
-	dev = (struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	dev = adapter->rsi_dev;
 
 	rsi_kill_thread(&dev->rx_thread);
 	sdio_claim_host(pfunction);
@@ -1255,8 +1246,7 @@ static void rsi_disconnect(struct sdio_func *pfunction)
 #ifdef CONFIG_PM
 static int rsi_set_sdio_pm_caps(struct rsi_hw *adapter)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	struct sdio_func *func = dev->pfunction;
 	int ret;
 
@@ -1407,7 +1397,7 @@ static int rsi_freeze(struct device *dev)
 		return -ENODEV;
 	}
 	common = adapter->priv;
-	sdev = (struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	sdev = adapter->rsi_dev;
 
 	if ((common->wow_flags & RSI_WOW_ENABLED) &&
 	    (common->wow_flags & RSI_WOW_NO_CONNECTION))
@@ -1457,8 +1447,7 @@ static void rsi_shutdown(struct device *dev)
 {
 	struct sdio_func *pfunction = dev_to_sdio_func(dev);
 	struct rsi_hw *adapter = sdio_get_drvdata(pfunction);
-	struct rsi_91x_sdiodev *sdev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *sdev = adapter->rsi_dev;
 	struct ieee80211_hw *hw = adapter->hw;
 
 	rsi_dbg(ERR_ZONE, "SDIO Bus shutdown =====>\n");
-- 
GitLab


From 361beddbfb7cfa2f280faca5d9df43eace381db6 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Thu, 3 Aug 2023 15:35:50 +0800
Subject: [PATCH 1580/1806] wifi: rsi: rsi_91x_sdio_ops: Remove unnecessary
 (void*) conversions

No need cast (void*) to (struct rsi_91x_sdiodev *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230803073550.3666829-1-yunchuan@nfschina.com
---
 drivers/net/wireless/rsi/rsi_91x_sdio_ops.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
index b2b47a0abcbf1..597b238e22949 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
@@ -88,8 +88,7 @@ void rsi_sdio_rx_thread(struct rsi_common *common)
 static int rsi_process_pkt(struct rsi_common *common)
 {
 	struct rsi_hw *adapter = common->priv;
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	u8 num_blks = 0;
 	u32 rcv_pkt_len = 0;
 	int status = 0;
@@ -147,8 +146,7 @@ static int rsi_process_pkt(struct rsi_common *common)
  */
 int rsi_init_sdio_slave_regs(struct rsi_hw *adapter)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	u8 function = 0;
 	u8 byte;
 	int status = 0;
@@ -233,8 +231,7 @@ int rsi_init_sdio_slave_regs(struct rsi_hw *adapter)
 static void rsi_rx_handler(struct rsi_hw *adapter)
 {
 	struct rsi_common *common = adapter->priv;
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	int status;
 	u8 isr_status = 0;
 	u8 fw_status = 0;
@@ -339,8 +336,7 @@ static void rsi_rx_handler(struct rsi_hw *adapter)
 int rsi_sdio_check_buffer_status(struct rsi_hw *adapter, u8 q_num)
 {
 	struct rsi_common *common = adapter->priv;
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 	u8 buf_status = 0;
 	int status = 0;
 	static int counter = 4;
@@ -409,8 +405,7 @@ out:
  */
 int rsi_sdio_determine_event_timeout(struct rsi_hw *adapter)
 {
-	struct rsi_91x_sdiodev *dev =
-		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct rsi_91x_sdiodev *dev = adapter->rsi_dev;
 
 	/* Once buffer full is seen, event timeout to occur every 2 msecs */
 	if (dev->rx_info.buffer_full)
-- 
GitLab


From f543235c394837275366669a3b769d17d5015d10 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Thu, 3 Aug 2023 15:35:58 +0800
Subject: [PATCH 1581/1806] wifi: rsi: rsi_91x_usb: Remove unnecessary (void*)
 conversions

No need cast (void*) to (struct rsi_91x_usbdev *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230803073558.3666936-1-yunchuan@nfschina.com
---
 drivers/net/wireless/rsi/rsi_91x_usb.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c
index 66fe386ec9cc6..10a465686439e 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb.c
@@ -43,7 +43,7 @@ static int rsi_usb_card_write(struct rsi_hw *adapter,
 			      u16 len,
 			      u8 endpoint)
 {
-	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rsi_91x_usbdev *dev = adapter->rsi_dev;
 	int status;
 	u8 *seg = dev->tx_buffer;
 	int transfer;
@@ -91,7 +91,7 @@ static int rsi_write_multiple(struct rsi_hw *adapter,
 	if (endpoint == 0)
 		return -EINVAL;
 
-	dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	dev = adapter->rsi_dev;
 	if (dev->write_fail)
 		return -ENETDOWN;
 
@@ -109,7 +109,7 @@ static int rsi_write_multiple(struct rsi_hw *adapter,
 static int rsi_find_bulk_in_and_out_endpoints(struct usb_interface *interface,
 					      struct rsi_hw *adapter)
 {
-	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rsi_91x_usbdev *dev = adapter->rsi_dev;
 	struct usb_host_interface *iface_desc;
 	struct usb_endpoint_descriptor *endpoint;
 	__le16 buffer_size;
@@ -306,7 +306,7 @@ out:
 
 static void rsi_rx_urb_kill(struct rsi_hw *adapter, u8 ep_num)
 {
-	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rsi_91x_usbdev *dev = adapter->rsi_dev;
 	struct rx_usb_ctrl_block *rx_cb = &dev->rx_cb[ep_num - 1];
 	struct urb *urb = rx_cb->rx_urb;
 
@@ -323,7 +323,7 @@ static void rsi_rx_urb_kill(struct rsi_hw *adapter, u8 ep_num)
  */
 static int rsi_rx_urb_submit(struct rsi_hw *adapter, u8 ep_num, gfp_t mem_flags)
 {
-	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rsi_91x_usbdev *dev = adapter->rsi_dev;
 	struct rx_usb_ctrl_block *rx_cb = &dev->rx_cb[ep_num - 1];
 	struct urb *urb = rx_cb->rx_urb;
 	int status;
@@ -362,7 +362,7 @@ static int rsi_rx_urb_submit(struct rsi_hw *adapter, u8 ep_num, gfp_t mem_flags)
 static int rsi_usb_read_register_multiple(struct rsi_hw *adapter, u32 addr,
 					  u8 *data, u16 count)
 {
-	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rsi_91x_usbdev *dev = adapter->rsi_dev;
 	u8 *buf;
 	u16 transfer;
 	int status;
@@ -412,7 +412,7 @@ static int rsi_usb_read_register_multiple(struct rsi_hw *adapter, u32 addr,
 static int rsi_usb_write_register_multiple(struct rsi_hw *adapter, u32 addr,
 					   u8 *data, u16 count)
 {
-	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rsi_91x_usbdev *dev = adapter->rsi_dev;
 	u8 *buf;
 	u16 transfer;
 	int status = 0;
@@ -559,7 +559,7 @@ static struct rsi_host_intf_ops usb_host_intf_ops = {
  */
 static void rsi_deinit_usb_interface(struct rsi_hw *adapter)
 {
-	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rsi_91x_usbdev *dev = adapter->rsi_dev;
 
 	rsi_kill_thread(&dev->rx_thread);
 
@@ -572,7 +572,7 @@ static void rsi_deinit_usb_interface(struct rsi_hw *adapter)
 
 static int rsi_usb_init_rx(struct rsi_hw *adapter)
 {
-	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rsi_91x_usbdev *dev = adapter->rsi_dev;
 	struct rx_usb_ctrl_block *rx_cb;
 	u8 idx, num_rx_cb;
 
@@ -822,7 +822,7 @@ static int rsi_probe(struct usb_interface *pfunction,
 		goto err1;
 	}
 
-	dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	dev = adapter->rsi_dev;
 
 	status = rsi_usb_reg_read(dev->usbdev, FW_STATUS_REG, &fw_status, 2);
 	if (status < 0)
-- 
GitLab


From 7d8473c799be80a89ab8b1f26f021e5cf0d4aa20 Mon Sep 17 00:00:00 2001
From: Wu Yunchuan <yunchuan@nfschina.com>
Date: Thu, 3 Aug 2023 15:36:06 +0800
Subject: [PATCH 1582/1806] wifi: rsi: rsi_91x_usb_ops: Remove unnecessary
 (void*) conversions

No need cast (void*) to (struct rsi_91x_usbdev *).

Signed-off-by: Wu Yunchuan <yunchuan@nfschina.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230803073606.3667062-1-yunchuan@nfschina.com
---
 drivers/net/wireless/rsi/rsi_91x_usb_ops.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
index 5130b0e72adcf..25c2b232394a6 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
@@ -28,7 +28,7 @@
 void rsi_usb_rx_thread(struct rsi_common *common)
 {
 	struct rsi_hw *adapter = common->priv;
-	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rsi_91x_usbdev *dev = adapter->rsi_dev;
 	int status;
 	struct sk_buff *skb;
 
-- 
GitLab


From eaa8023e9bb30926b154af72be0cadbebfc8e878 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 10 Aug 2023 19:49:39 +0800
Subject: [PATCH 1583/1806] wifi: wfx: Use devm_kmemdup to replace devm_kmalloc
 + memcpy
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the helper function devm_kmemdup() rather than duplicating its
implementation, which helps to enhance code readability.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230810114939.2104013-1-lizetao1@huawei.com
---
 drivers/net/wireless/silabs/wfx/main.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/silabs/wfx/main.c b/drivers/net/wireless/silabs/wfx/main.c
index 0b50f7058bbbc..ede822d771aaf 100644
--- a/drivers/net/wireless/silabs/wfx/main.c
+++ b/drivers/net/wireless/silabs/wfx/main.c
@@ -293,13 +293,12 @@ struct wfx_dev *wfx_init_common(struct device *dev, const struct wfx_platform_da
 	hw->wiphy->max_scan_ie_len = IEEE80211_MAX_DATA_LEN;
 	hw->wiphy->n_iface_combinations = ARRAY_SIZE(wfx_iface_combinations);
 	hw->wiphy->iface_combinations = wfx_iface_combinations;
-	hw->wiphy->bands[NL80211_BAND_2GHZ] = devm_kmalloc(dev, sizeof(wfx_band_2ghz), GFP_KERNEL);
+	/* FIXME: also copy wfx_rates and wfx_2ghz_chantable */
+	hw->wiphy->bands[NL80211_BAND_2GHZ] = devm_kmemdup(dev, &wfx_band_2ghz,
+							   sizeof(wfx_band_2ghz), GFP_KERNEL);
 	if (!hw->wiphy->bands[NL80211_BAND_2GHZ])
 		goto err;
 
-	/* FIXME: also copy wfx_rates and wfx_2ghz_chantable */
-	memcpy(hw->wiphy->bands[NL80211_BAND_2GHZ], &wfx_band_2ghz, sizeof(wfx_band_2ghz));
-
 	wdev = hw->priv;
 	wdev->hw = hw;
 	wdev->dev = dev;
-- 
GitLab


From 821b5192c955144bd2f0aeea6cd153e1aedd16e1 Mon Sep 17 00:00:00 2001
From: Shiji Yang <yangshiji66@outlook.com>
Date: Fri, 11 Aug 2023 14:34:54 +0800
Subject: [PATCH 1584/1806] wifi: rt2x00: limit MT7620 TX power based on eeprom
 calibration

In the vendor driver, the current channel power is queried from
EEPROM_TXPOWER_BG1 and EEPROM_TXPOWER_BG2. And then the mixed value
will be written into the low half-word of the TX_ALC_CFG_0 register.
The high half-word of the TX_ALC_CFG_0 is a fixed value 0x2f2f.

We can't get the accurate TX power. Based on my tests and the new
MediaTek mt76 driver source code, the real TX power is approximately
equal to channel_power + (max) rate_power. Usually max rate_power is
the gain of the OFDM 6M rate, which can be readed from the offset
EEPROM_TXPOWER_BYRATE +1.

Based on these eeprom values, this patch adds basic TX power control
for the MT7620 and limits its maximum TX power. This can avoid the
link speed decrease caused by chip overheating. rt2800_config_alc()
function has also been renamed to rt2800_config_alc_rt6352() because
it's only used by RT6352 (MT7620).

Notice:
It's still need some work to sync the max channel power to the user
interface. This part is missing from the rt2x00 driver framework. If
we set the power exceed the calibration value, it won't take effect.

Signed-off-by: Shiji Yang <yangshiji66@outlook.com>
Acked-by: Stanislaw Gruszka <stf_xl@wp.pl>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/TYAP286MB03159090ED14044215E59FD6BC10A@TYAP286MB0315.JPNP286.PROD.OUTLOOK.COM
---
 .../net/wireless/ralink/rt2x00/rt2800lib.c    | 57 +++++++++++++------
 1 file changed, 40 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
index ab374c50c35d8..e65cc00fa17c9 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
@@ -3865,28 +3865,51 @@ static void rt2800_config_channel_rf7620(struct rt2x00_dev *rt2x00dev,
 	}
 }
 
-static void rt2800_config_alc(struct rt2x00_dev *rt2x00dev,
-			      struct ieee80211_channel *chan,
-			      int power_level) {
-	u16 eeprom, target_power, max_power;
+static void rt2800_config_alc_rt6352(struct rt2x00_dev *rt2x00dev,
+				     struct ieee80211_channel *chan,
+				     int power_level)
+{
+	int cur_channel = rt2x00dev->rf_channel;
+	u16 eeprom, chan_power, rate_power, target_power;
+	u16 tx_power[2];
+	s8 *power_group[2];
 	u32 mac_sys_ctrl;
-	u32 reg;
+	u32 cnt, reg;
 	u8 bbp;
 
-	/* hardware unit is 0.5dBm, limited to 23.5dBm */
-	power_level *= 2;
-	if (power_level > 0x2f)
-		power_level = 0x2f;
+	if (WARN_ON(cur_channel < 1 || cur_channel > 14))
+		return;
+
+	/* get per chain power, 2 chains in total, unit is 0.5dBm */
+	power_level = (power_level - 3) * 2;
 
-	max_power = chan->max_power * 2;
-	if (max_power > 0x2f)
-		max_power = 0x2f;
+	/* We can't get the accurate TX power. Based on some tests, the real
+	 * TX power is approximately equal to channel_power + (max)rate_power.
+	 * Usually max rate_power is the gain of the OFDM 6M rate. The antenna
+	 * gain and externel PA gain are not included as we are unable to
+	 * obtain these values.
+	 */
+	rate_power = rt2800_eeprom_read_from_array(rt2x00dev,
+						   EEPROM_TXPOWER_BYRATE, 1);
+	rate_power &= 0x3f;
+	power_level -= rate_power;
+	if (power_level < 1)
+		power_level = 1;
+
+	power_group[0] = rt2800_eeprom_addr(rt2x00dev, EEPROM_TXPOWER_BG1);
+	power_group[1] = rt2800_eeprom_addr(rt2x00dev, EEPROM_TXPOWER_BG2);
+	for (cnt = 0; cnt < 2; cnt++) {
+		chan_power = power_group[cnt][cur_channel - 1];
+		if (chan_power >= 0x20 || chan_power == 0)
+			chan_power = 0x10;
+		tx_power[cnt] = power_level < chan_power ? power_level : chan_power;
+	}
 
 	reg = rt2800_register_read(rt2x00dev, TX_ALC_CFG_0);
-	rt2x00_set_field32(&reg, TX_ALC_CFG_0_CH_INIT_0, power_level);
-	rt2x00_set_field32(&reg, TX_ALC_CFG_0_CH_INIT_1, power_level);
-	rt2x00_set_field32(&reg, TX_ALC_CFG_0_LIMIT_0, max_power);
-	rt2x00_set_field32(&reg, TX_ALC_CFG_0_LIMIT_1, max_power);
+	rt2x00_set_field32(&reg, TX_ALC_CFG_0_CH_INIT_0, tx_power[0]);
+	rt2x00_set_field32(&reg, TX_ALC_CFG_0_CH_INIT_1, tx_power[1]);
+	rt2x00_set_field32(&reg, TX_ALC_CFG_0_LIMIT_0, 0x2f);
+	rt2x00_set_field32(&reg, TX_ALC_CFG_0_LIMIT_1, 0x2f);
 
 	eeprom = rt2800_eeprom_read(rt2x00dev, EEPROM_NIC_CONF1);
 	if (rt2x00_get_field16(eeprom, EEPROM_NIC_CONF1_INTERNAL_TX_ALC)) {
@@ -5268,7 +5291,7 @@ static void rt2800_config_txpower_rt6352(struct rt2x00_dev *rt2x00dev,
 	rt2x00_set_field32(&pwreg, TX_PWR_CFG_9B_STBC_MCS7, t);
 	rt2800_register_write(rt2x00dev, TX_PWR_CFG_9, pwreg);
 
-	rt2800_config_alc(rt2x00dev, chan, power_level);
+	rt2800_config_alc_rt6352(rt2x00dev, chan, power_level);
 
 	/* TODO: temperature compensation code! */
 }
-- 
GitLab


From 35a7a1ce7c7d61664ee54f5239a1f120ab95a87e Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Mon, 14 Aug 2023 12:49:57 +0300
Subject: [PATCH 1585/1806] wifi: mwifiex: avoid possible NULL skb pointer
 dereference

In 'mwifiex_handle_uap_rx_forward()', always check the value
returned by 'skb_copy()' to avoid potential NULL pointer
dereference in 'mwifiex_uap_queue_bridged_pkt()', and drop
original skb in case of copying failure.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 838e4f449297 ("mwifiex: improve uAP RX handling")
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230814095041.16416-1-dmantipov@yandex.ru
---
 drivers/net/wireless/marvell/mwifiex/uap_txrx.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
index b9866f2e26440..318bd4ed8399e 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
@@ -253,7 +253,15 @@ int mwifiex_handle_uap_rx_forward(struct mwifiex_private *priv,
 
 	if (is_multicast_ether_addr(ra)) {
 		skb_uap = skb_copy(skb, GFP_ATOMIC);
-		mwifiex_uap_queue_bridged_pkt(priv, skb_uap);
+		if (likely(skb_uap)) {
+			mwifiex_uap_queue_bridged_pkt(priv, skb_uap);
+		} else {
+			mwifiex_dbg(adapter, ERROR,
+				    "failed to copy skb for uAP\n");
+			priv->stats.rx_dropped++;
+			dev_kfree_skb_any(skb);
+			return -1;
+		}
 	} else {
 		if (mwifiex_get_sta_entry(priv, ra)) {
 			/* Requeue Intra-BSS packet */
-- 
GitLab


From c4125bf88341056a2051c6c083a7f69661733fc6 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 19 Aug 2023 18:21:00 +0800
Subject: [PATCH 1586/1806] wifi: wilc1000: Remove unused declarations

Commit 8399918f3056 ("staging: wilc1000: use RCU list to maintain vif interfaces list")
removed wilc_get_interface() but not its declaration.
Commit 9bc061e88054 ("staging: wilc1000: added support to dynamically add/remove interfaces")
declared but never implemented wilc_cfg_alloc() and wilc_netdev_interface().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230819102100.13720-1-yuehaibing@huawei.com
---
 drivers/net/wireless/microchip/wilc1000/cfg80211.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.h b/drivers/net/wireless/microchip/wilc1000/cfg80211.h
index 37b294cb3b372..8c65951cfaf96 100644
--- a/drivers/net/wireless/microchip/wilc1000/cfg80211.h
+++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.h
@@ -8,15 +8,12 @@
 #define WILC_CFG80211_H
 #include "netdev.h"
 
-struct wiphy *wilc_cfg_alloc(void);
 int wilc_cfg80211_init(struct wilc **wilc, struct device *dev, int io_type,
 		       const struct wilc_hif_func *ops);
 struct wilc *wilc_create_wiphy(struct device *dev);
 void wilc_deinit_host_int(struct net_device *net);
 int wilc_init_host_int(struct net_device *net);
 void wilc_wfi_monitor_rx(struct net_device *mon_dev, u8 *buff, u32 size);
-struct wilc_vif *wilc_netdev_interface(struct wilc *wl, const char *name,
-				       enum nl80211_iftype type);
 void wilc_wfi_deinit_mon_interface(struct wilc *wl, bool rtnl_locked);
 struct net_device *wilc_wfi_init_mon_interface(struct wilc *wl,
 					       const char *name,
@@ -24,7 +21,6 @@ struct net_device *wilc_wfi_init_mon_interface(struct wilc *wl,
 void wilc_update_mgmt_frame_registrations(struct wiphy *wiphy,
 					  struct wireless_dev *wdev,
 					  struct mgmt_frame_regs *upd);
-struct wilc_vif *wilc_get_interface(struct wilc *wl);
 struct wilc_vif *wilc_get_wl_to_vif(struct wilc *wl);
 void wlan_deinit_locks(struct wilc *wilc);
 #endif
-- 
GitLab


From 400ece6c7f346b0a30867bd00b03b5b2563d4357 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 22 Aug 2023 16:42:24 +0300
Subject: [PATCH 1587/1806] wifi: ath11k: Don't drop tx_status when peer cannot
 be found

When a station idles for a long time, hostapd will try to send a QoS Null
frame to the station as "poll". NL80211_CMD_PROBE_CLIENT is used for this
purpose. And the skb will be added to ack_status_frame - waiting for a
completion via ieee80211_report_ack_skb().

But when the peer was already removed before the tx_complete arrives, the
peer will be missing. And when using dev_kfree_skb_any (instead of going
through mac80211), the entry will stay inside ack_status_frames. This IDR
will therefore run full after 8K request were generated for such clients.
At this point, the access point will then just stall and not allow any new
clients because idr_alloc() for ack_status_frame will fail.

ieee80211_free_txskb() on the other hand will (when required) call
ieee80211_report_ack_skb() and make sure that (when required) remove the
entry from the ack_status_frame.

Tested-on: IPQ6018 hw1.0 WLAN.HK.2.5.0.1-01100-QCAHKSWPL_SILICONZ-1

Fixes: 6257c702264c ("wifi: ath11k: fix tx status reporting in encap offload mode")
Fixes: 94739d45c388 ("ath11k: switch to using ieee80211_tx_status_ext()")
Cc: stable@vger.kernel.org
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230802-ath11k-ack_status_leak-v2-1-c0af729d6229@narfation.org
---
 drivers/net/wireless/ath/ath11k/dp_tx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c
index a34833de7c676..27c976f52c7a9 100644
--- a/drivers/net/wireless/ath/ath11k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_tx.c
@@ -369,7 +369,7 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab,
 			   "dp_tx: failed to find the peer with peer_id %d\n",
 			    ts->peer_id);
 		spin_unlock_bh(&ab->base_lock);
-		dev_kfree_skb_any(msdu);
+		ieee80211_free_txskb(ar->hw, msdu);
 		return;
 	}
 	spin_unlock_bh(&ab->base_lock);
@@ -624,7 +624,7 @@ static void ath11k_dp_tx_complete_msdu(struct ath11k *ar,
 			   "dp_tx: failed to find the peer with peer_id %d\n",
 			    ts->peer_id);
 		spin_unlock_bh(&ab->base_lock);
-		dev_kfree_skb_any(msdu);
+		ieee80211_free_txskb(ar->hw, msdu);
 		return;
 	}
 	arsta = (struct ath11k_sta *)peer->sta->drv_priv;
-- 
GitLab


From 29d15589f084d71a4ea8c544039c5839db0236e2 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 22 Aug 2023 16:42:24 +0300
Subject: [PATCH 1588/1806] wifi: ath11k: Cleanup mac80211 references on
 failure during tx_complete

When a function is using functions from mac80211 to free an skb then it
should do it consistently and not switch to the generic dev_kfree_skb_any
(or similar functions). Otherwise (like in the error handlers), mac80211
will will not be aware of the freed skb and thus not clean up related
information in its internal data structures.

Not doing so lead in the past to filled up structure which then prevented
new clients to connect.

Fixes: d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices")
Fixes: 6257c702264c ("wifi: ath11k: fix tx status reporting in encap offload mode")
Cc: stable@vger.kernel.org
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230802-ath11k-ack_status_leak-v2-2-c0af729d6229@narfation.org
---
 drivers/net/wireless/ath/ath11k/dp_tx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c
index 27c976f52c7a9..b85a4a03b37ab 100644
--- a/drivers/net/wireless/ath/ath11k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_tx.c
@@ -344,7 +344,7 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab,
 	dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
 
 	if (!skb_cb->vif) {
-		dev_kfree_skb_any(msdu);
+		ieee80211_free_txskb(ar->hw, msdu);
 		return;
 	}
 
@@ -566,12 +566,12 @@ static void ath11k_dp_tx_complete_msdu(struct ath11k *ar,
 	dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
 
 	if (unlikely(!rcu_access_pointer(ab->pdevs_active[ar->pdev_idx]))) {
-		dev_kfree_skb_any(msdu);
+		ieee80211_free_txskb(ar->hw, msdu);
 		return;
 	}
 
 	if (unlikely(!skb_cb->vif)) {
-		dev_kfree_skb_any(msdu);
+		ieee80211_free_txskb(ar->hw, msdu);
 		return;
 	}
 
-- 
GitLab


From 9476cda44c136089f14f8951ae5197d63e91735c Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Mon, 21 Aug 2023 07:13:36 -0700
Subject: [PATCH 1589/1806] wifi: ath11k: Consistently use
 ath11k_vif_to_arvif()

Helper function ath11k_vif_to_arvif() exists to retrieve a struct
ath11k_vif from a struct ieee80211_vif. However, in multiple places
this logic is open-coded with inline typecasting. Since the
typecasting prevents the compiler from type-checking the source and
destination, update the driver to consistently use the helper
function.

No functional changes, compile tested only.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230821-ath11k_vif_to_arvif-v1-1-fa2c3b60b5cf@quicinc.com
---
 drivers/net/wireless/ath/ath11k/mac.c      | 64 +++++++++++-----------
 drivers/net/wireless/ath/ath11k/testmode.c |  2 +-
 2 files changed, 33 insertions(+), 33 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 2aadf2c387b62..c071bf5841af6 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -566,7 +566,7 @@ static void ath11k_get_arvif_iter(void *data, u8 *mac,
 				  struct ieee80211_vif *vif)
 {
 	struct ath11k_vif_iter *arvif_iter = data;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 
 	if (arvif->vdev_id == arvif_iter->vdev_id)
 		arvif_iter->arvif = arvif;
@@ -1464,7 +1464,7 @@ static int ath11k_mac_setup_bcn_tmpl_ema(struct ath11k_vif *arvif)
 	u32 params = 0;
 	u8 i = 0;
 
-	tx_arvif = (void *)arvif->vif->mbssid_tx_vif->drv_priv;
+	tx_arvif = ath11k_vif_to_arvif(arvif->vif->mbssid_tx_vif);
 
 	beacons = ieee80211_beacon_get_template_ema_list(tx_arvif->ar->hw,
 							 tx_arvif->vif, 0);
@@ -1520,8 +1520,8 @@ static int ath11k_mac_setup_bcn_tmpl_mbssid(struct ath11k_vif *arvif)
 	struct sk_buff *bcn;
 	int ret;
 
-	if (arvif->vif->mbssid_tx_vif) {
-		tx_arvif = (void *)arvif->vif->mbssid_tx_vif->drv_priv;
+	if (vif->mbssid_tx_vif) {
+		tx_arvif = ath11k_vif_to_arvif(vif->mbssid_tx_vif);
 		if (tx_arvif != arvif) {
 			ar = tx_arvif->ar;
 			ab = ar->ab;
@@ -1562,7 +1562,7 @@ static int ath11k_mac_setup_bcn_tmpl(struct ath11k_vif *arvif)
 	 * non-transmitting interfaces, and results in a crash if sent.
 	 */
 	if (vif->mbssid_tx_vif &&
-	    arvif != (void *)vif->mbssid_tx_vif->drv_priv && arvif->is_up)
+	    arvif != ath11k_vif_to_arvif(vif->mbssid_tx_vif) && arvif->is_up)
 		return 0;
 
 	if (vif->bss_conf.ema_ap && vif->mbssid_tx_vif)
@@ -1626,7 +1626,7 @@ static void ath11k_control_beaconing(struct ath11k_vif *arvif,
 	ether_addr_copy(arvif->bssid, info->bssid);
 
 	if (arvif->vif->mbssid_tx_vif)
-		tx_arvif = (struct ath11k_vif *)arvif->vif->mbssid_tx_vif->drv_priv;
+		tx_arvif = ath11k_vif_to_arvif(arvif->vif->mbssid_tx_vif);
 
 	ret = ath11k_wmi_vdev_up(arvif->ar, arvif->vdev_id, arvif->aid,
 				 arvif->bssid,
@@ -1649,7 +1649,7 @@ static void ath11k_mac_handle_beacon_iter(void *data, u8 *mac,
 {
 	struct sk_buff *skb = data;
 	struct ieee80211_mgmt *mgmt = (void *)skb->data;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 
 	if (vif->type != NL80211_IFTYPE_STATION)
 		return;
@@ -1672,7 +1672,7 @@ static void ath11k_mac_handle_beacon_miss_iter(void *data, u8 *mac,
 					       struct ieee80211_vif *vif)
 {
 	u32 *vdev_id = data;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct ath11k *ar = arvif->ar;
 	struct ieee80211_hw *hw = ar->hw;
 
@@ -1718,7 +1718,7 @@ static void ath11k_peer_assoc_h_basic(struct ath11k *ar,
 				      struct ieee80211_sta *sta,
 				      struct peer_assoc_params *arg)
 {
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	u32 aid;
 
 	lockdep_assert_held(&ar->conf_mutex);
@@ -1746,7 +1746,7 @@ static void ath11k_peer_assoc_h_crypto(struct ath11k *ar,
 	struct ieee80211_bss_conf *info = &vif->bss_conf;
 	struct cfg80211_chan_def def;
 	struct cfg80211_bss *bss;
-	struct ath11k_vif *arvif = (struct ath11k_vif *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	const u8 *rsnie = NULL;
 	const u8 *wpaie = NULL;
 
@@ -1804,7 +1804,7 @@ static void ath11k_peer_assoc_h_rates(struct ath11k *ar,
 				      struct ieee80211_sta *sta,
 				      struct peer_assoc_params *arg)
 {
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct wmi_rate_set_arg *rateset = &arg->peer_legacy_rates;
 	struct cfg80211_chan_def def;
 	const struct ieee80211_supported_band *sband;
@@ -1867,7 +1867,7 @@ static void ath11k_peer_assoc_h_ht(struct ath11k *ar,
 				   struct peer_assoc_params *arg)
 {
 	const struct ieee80211_sta_ht_cap *ht_cap = &sta->deflink.ht_cap;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct cfg80211_chan_def def;
 	enum nl80211_band band;
 	const u8 *ht_mcs_mask;
@@ -2064,7 +2064,7 @@ static void ath11k_peer_assoc_h_vht(struct ath11k *ar,
 				    struct peer_assoc_params *arg)
 {
 	const struct ieee80211_sta_vht_cap *vht_cap = &sta->deflink.vht_cap;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct cfg80211_chan_def def;
 	enum nl80211_band band;
 	u16 *vht_mcs_mask;
@@ -2261,7 +2261,7 @@ static void ath11k_peer_assoc_h_he(struct ath11k *ar,
 				   struct ieee80211_sta *sta,
 				   struct peer_assoc_params *arg)
 {
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct cfg80211_chan_def def;
 	const struct ieee80211_sta_he_cap *he_cap = &sta->deflink.he_cap;
 	enum nl80211_band band;
@@ -2584,7 +2584,7 @@ static void ath11k_peer_assoc_h_qos(struct ath11k *ar,
 				    struct ieee80211_sta *sta,
 				    struct peer_assoc_params *arg)
 {
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 
 	switch (arvif->vdev_type) {
 	case WMI_VDEV_TYPE_AP:
@@ -2747,7 +2747,7 @@ static void ath11k_peer_assoc_h_phymode(struct ath11k *ar,
 					struct ieee80211_sta *sta,
 					struct peer_assoc_params *arg)
 {
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct cfg80211_chan_def def;
 	enum nl80211_band band;
 	const u8 *ht_mcs_mask;
@@ -2933,7 +2933,7 @@ static bool ath11k_mac_vif_recalc_sta_he_txbf(struct ath11k *ar,
 					      struct ieee80211_vif *vif,
 					      struct ieee80211_sta_he_cap *he_cap)
 {
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct ieee80211_he_cap_elem he_cap_elem = {0};
 	struct ieee80211_sta_he_cap *cap_band = NULL;
 	struct cfg80211_chan_def def;
@@ -2995,7 +2995,7 @@ static void ath11k_bss_assoc(struct ieee80211_hw *hw,
 			     struct ieee80211_bss_conf *bss_conf)
 {
 	struct ath11k *ar = hw->priv;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct peer_assoc_params peer_arg;
 	struct ieee80211_sta *ap_sta;
 	struct ath11k_peer *peer;
@@ -3111,7 +3111,7 @@ static void ath11k_bss_disassoc(struct ieee80211_hw *hw,
 				struct ieee80211_vif *vif)
 {
 	struct ath11k *ar = hw->priv;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	int ret;
 
 	lockdep_assert_held(&ar->conf_mutex);
@@ -3160,7 +3160,7 @@ static void ath11k_recalculate_mgmt_rate(struct ath11k *ar,
 					 struct ieee80211_vif *vif,
 					 struct cfg80211_chan_def *def)
 {
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	const struct ieee80211_supported_band *sband;
 	u8 basic_rate_idx;
 	int hw_rate_code;
@@ -4632,7 +4632,7 @@ static int ath11k_station_disassoc(struct ath11k *ar,
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_sta *sta)
 {
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	int ret = 0;
 
 	lockdep_assert_held(&ar->conf_mutex);
@@ -5160,7 +5160,7 @@ static int ath11k_mac_op_sta_set_txpwr(struct ieee80211_hw *hw,
 				       struct ieee80211_sta *sta)
 {
 	struct ath11k *ar = hw->priv;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	int ret = 0;
 	s16 txpwr;
 
@@ -5210,7 +5210,7 @@ static void ath11k_mac_op_sta_rc_update(struct ieee80211_hw *hw,
 {
 	struct ath11k *ar = hw->priv;
 	struct ath11k_sta *arsta = (struct ath11k_sta *)sta->drv_priv;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct ath11k_peer *peer;
 	u32 bw, smps;
 
@@ -5337,7 +5337,7 @@ static int ath11k_mac_op_conf_tx(struct ieee80211_hw *hw,
 				 const struct ieee80211_tx_queue_params *params)
 {
 	struct ath11k *ar = hw->priv;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct wmi_wmm_params_arg *p = NULL;
 	int ret;
 
@@ -6455,7 +6455,7 @@ static int ath11k_mac_setup_vdev_params_mbssid(struct ath11k_vif *arvif,
 		return 0;
 	}
 
-	tx_arvif = (void *)tx_vif->drv_priv;
+	tx_arvif = ath11k_vif_to_arvif(tx_vif);
 
 	if (arvif->vif->bss_conf.nontransmitted) {
 		if (ar->hw->wiphy != ieee80211_vif_to_wdev(tx_vif)->wiphy)
@@ -7408,7 +7408,7 @@ ath11k_mac_update_vif_chan(struct ath11k *ar,
 	/* TODO: Update ar->rx_channel */
 
 	for (i = 0; i < n_vifs; i++) {
-		arvif = (void *)vifs[i].vif->drv_priv;
+		arvif = ath11k_vif_to_arvif(vifs[i].vif);
 
 		if (WARN_ON(!arvif->is_started))
 			continue;
@@ -7450,7 +7450,7 @@ ath11k_mac_update_vif_chan(struct ath11k *ar,
 
 		mbssid_tx_vif = arvif->vif->mbssid_tx_vif;
 		if (mbssid_tx_vif)
-			tx_arvif = (struct ath11k_vif *)mbssid_tx_vif->drv_priv;
+			tx_arvif = ath11k_vif_to_arvif(mbssid_tx_vif);
 
 		ret = ath11k_wmi_vdev_up(arvif->ar, arvif->vdev_id, arvif->aid,
 					 arvif->bssid,
@@ -7546,7 +7546,7 @@ static int ath11k_start_vdev_delay(struct ieee80211_hw *hw,
 {
 	struct ath11k *ar = hw->priv;
 	struct ath11k_base *ab = ar->ab;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	int ret;
 
 	if (WARN_ON(arvif->is_started))
@@ -7596,7 +7596,7 @@ ath11k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 {
 	struct ath11k *ar = hw->priv;
 	struct ath11k_base *ab = ar->ab;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	int ret;
 	struct peer_create_params param;
 
@@ -7686,7 +7686,7 @@ ath11k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 {
 	struct ath11k *ar = hw->priv;
 	struct ath11k_base *ab = ar->ab;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct ath11k_peer *peer;
 	int ret;
 
@@ -8307,7 +8307,7 @@ ath11k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw,
 			       struct ieee80211_vif *vif,
 			       const struct cfg80211_bitrate_mask *mask)
 {
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct cfg80211_chan_def def;
 	struct ath11k_pdev_cap *cap;
 	struct ath11k *ar = arvif->ar;
@@ -8904,7 +8904,7 @@ static int ath11k_mac_op_remain_on_channel(struct ieee80211_hw *hw,
 					   enum ieee80211_roc_type type)
 {
 	struct ath11k *ar = hw->priv;
-	struct ath11k_vif *arvif = (void *)vif->drv_priv;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct scan_req_params arg;
 	int ret;
 	u32 scan_time_msec;
diff --git a/drivers/net/wireless/ath/ath11k/testmode.c b/drivers/net/wireless/ath/ath11k/testmode.c
index 8fc5cddb28bde..43bb23265d346 100644
--- a/drivers/net/wireless/ath/ath11k/testmode.c
+++ b/drivers/net/wireless/ath/ath11k/testmode.c
@@ -350,7 +350,7 @@ static int ath11k_tm_cmd_wmi(struct ath11k *ar, struct nlattr *tb[],
 	if (ar->ab->fw_mode != ATH11K_FIRMWARE_MODE_FTM &&
 	    (tag == WMI_TAG_VDEV_SET_PARAM_CMD || tag == WMI_TAG_UNIT_TEST_CMD)) {
 		if (vif) {
-			arvif = (struct ath11k_vif *)vif->drv_priv;
+			arvif = ath11k_vif_to_arvif(vif);
 			*ptr = arvif->vdev_id;
 		} else {
 			ret = -EINVAL;
-- 
GitLab


From 3ced39049d4d87231c3ddabfb335fe78a99591c2 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Tue, 22 Aug 2023 07:50:48 -0700
Subject: [PATCH 1590/1806] wifi: ath10k: Fix a few spelling errors

Fix a few issues flagged by 'codespell'.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230822-ath_spelling-v1-1-8e2698759564@quicinc.com
---
 drivers/net/wireless/ath/ath10k/htt.h  | 4 ++--
 drivers/net/wireless/ath/ath10k/pci.c  | 2 +-
 drivers/net/wireless/ath/ath10k/sdio.c | 2 +-
 drivers/net/wireless/ath/ath10k/wmi.h  | 8 ++++----
 4 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h
index e0c9f45e74761..7b24297146e72 100644
--- a/drivers/net/wireless/ath/ath10k/htt.h
+++ b/drivers/net/wireless/ath/ath10k/htt.h
@@ -69,7 +69,7 @@ struct htt_ver_req {
  * The HTT tx descriptor is defined in two manners: by a struct with
  * bitfields, and by a series of [dword offset, bit mask, bit shift]
  * definitions.
- * The target should use the struct def, for simplicitly and clarity,
+ * The target should use the struct def, for simplicity and clarity,
  * but the host shall use the bit-mast + bit-shift defs, to be endian-
  * neutral.  Specifically, the host shall use the get/set macros built
  * around the mask + shift defs.
@@ -2086,7 +2086,7 @@ static inline bool ath10k_htt_rx_proc_rx_frag_ind(struct ath10k_htt *htt,
  * for correctly accessing rx descriptor data.
  */
 
-/* base struct used for abstracting the rx descritor representation */
+/* base struct used for abstracting the rx descriptor representation */
 struct htt_rx_desc {
 	union {
 		/* This field is filled on the host using the msdu buffer
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index a7f44f6335fb8..57177890a4633 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -1636,7 +1636,7 @@ static int ath10k_pci_dump_memory_generic(struct ath10k *ar,
 						      buf,
 						      current_region->len);
 
-	/* No individiual memory sections defined so we can
+	/* No individual memory sections defined so we can
 	 * copy the entire memory region.
 	 */
 	ret = ath10k_pci_diag_read_mem(ar,
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index 79e09c7a82b3d..56fbcfb80bf88 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -2389,7 +2389,7 @@ static int ath10k_sdio_dump_memory_generic(struct ath10k *ar,
 						      buf,
 						      current_region->len);
 
-	/* No individiual memory sections defined so we can
+	/* No individual memory sections defined so we can
 	 * copy the entire memory region.
 	 */
 	if (fast_dump)
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index 6d04a66fe5e02..b112e88260931 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -3854,9 +3854,9 @@ enum wmi_pdev_param {
 	 * retransmitting frames.
 	 */
 	WMI_PDEV_PARAM_DYNAMIC_BW,
-	/* Non aggregrate/ 11g sw retry threshold.0-disable */
+	/* Non aggregate/ 11g sw retry threshold.0-disable */
 	WMI_PDEV_PARAM_NON_AGG_SW_RETRY_TH,
-	/* aggregrate sw retry threshold. 0-disable*/
+	/* aggregate sw retry threshold. 0-disable*/
 	WMI_PDEV_PARAM_AGG_SW_RETRY_TH,
 	/* Station kickout threshold (non of consecutive failures).0-disable */
 	WMI_PDEV_PARAM_STA_KICKOUT_TH,
@@ -3953,9 +3953,9 @@ enum wmi_10x_pdev_param {
 	WMI_10X_PDEV_PARAM_PROTECTION_MODE,
 	/* Dynamic bandwidth 0: disable 1: enable */
 	WMI_10X_PDEV_PARAM_DYNAMIC_BW,
-	/* Non aggregrate/ 11g sw retry threshold.0-disable */
+	/* Non aggregate/ 11g sw retry threshold.0-disable */
 	WMI_10X_PDEV_PARAM_NON_AGG_SW_RETRY_TH,
-	/* aggregrate sw retry threshold. 0-disable*/
+	/* aggregate sw retry threshold. 0-disable*/
 	WMI_10X_PDEV_PARAM_AGG_SW_RETRY_TH,
 	/* Station kickout threshold (non of consecutive failures).0-disable */
 	WMI_10X_PDEV_PARAM_STA_KICKOUT_TH,
-- 
GitLab


From d68a283bfc39aeed2a51c67804e014bf4b35c7e1 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Tue, 22 Aug 2023 07:50:49 -0700
Subject: [PATCH 1591/1806] wifi: ath11k: Fix a few spelling errors

Fix a few issues flagged by 'codespell'.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230822-ath_spelling-v1-2-8e2698759564@quicinc.com
---
 drivers/net/wireless/ath/ath11k/dp.h    | 2 +-
 drivers/net/wireless/ath/ath11k/dp_rx.c | 2 +-
 drivers/net/wireless/ath/ath11k/dp_tx.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp.h b/drivers/net/wireless/ath/ath11k/dp.h
index d04f78ab6b373..15815af453b2a 100644
--- a/drivers/net/wireless/ath/ath11k/dp.h
+++ b/drivers/net/wireless/ath/ath11k/dp.h
@@ -635,7 +635,7 @@ enum htt_ppdu_stats_tag_type {
  *          b'24    - status_swap: 1 is to swap status TLV
  *          b'25    - pkt_swap:  1 is to swap packet TLV
  *          b'26:31 - rsvd1:  reserved for future use
- * dword1 - b'0:16  - ring_buffer_size: size of bufferes referenced by rx ring,
+ * dword1 - b'0:16  - ring_buffer_size: size of buffers referenced by rx ring,
  *                    in byte units.
  *                    Valid only for HW_TO_SW_RING and SW_TO_HW_RING
  *        - b'16:31 - rsvd2: Reserved for future use
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 1e488eed282b5..62bc98852f0f7 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -3423,7 +3423,7 @@ static int ath11k_dp_rx_h_defrag_reo_reinject(struct ath11k *ar, struct dp_rx_ti
 	ath11k_hal_rx_buf_addr_info_set(msdu0, paddr, cookie,
 					ab->hw_params.hal_params->rx_buf_rbm);
 
-	/* Fill mpdu details into reo entrace ring */
+	/* Fill mpdu details into reo entrance ring */
 	srng = &ab->hal.srng_list[ab->dp.reo_reinject_ring.ring_id];
 
 	spin_lock_bh(&srng->lock);
diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c
index b85a4a03b37ab..0dda76f7a4b50 100644
--- a/drivers/net/wireless/ath/ath11k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_tx.c
@@ -238,7 +238,7 @@ tcl_ring_sel:
 		spin_unlock_bh(&tcl_ring->lock);
 		ret = -ENOMEM;
 
-		/* Checking for available tcl descritors in another ring in
+		/* Checking for available tcl descriptors in another ring in
 		 * case of failure due to full tcl ring now, is better than
 		 * checking this ring earlier for each pkt tx.
 		 * Restart ring selection if some rings are not checked yet.
-- 
GitLab


From 4f1dbb4904c3d06b0f0d5f2dda8ccff839110726 Mon Sep 17 00:00:00 2001
From: Jeff Johnson <quic_jjohnson@quicinc.com>
Date: Tue, 22 Aug 2023 07:50:50 -0700
Subject: [PATCH 1592/1806] wifi: ath12k: Fix a few spelling errors

Fix a few issues flagged by 'codespell'.

Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230822-ath_spelling-v1-3-8e2698759564@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp.h      | 2 +-
 drivers/net/wireless/ath/ath12k/dp_rx.c   | 2 +-
 drivers/net/wireless/ath/ath12k/dp_tx.c   | 2 +-
 drivers/net/wireless/ath/ath12k/mac.c     | 2 +-
 drivers/net/wireless/ath/ath12k/rx_desc.h | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index 7c5dafce5a68d..6e7b7281d549b 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -712,7 +712,7 @@ enum htt_stats_internal_ppdu_frametype {
  *          b'24    - status_swap: 1 is to swap status TLV
  *          b'25    - pkt_swap:  1 is to swap packet TLV
  *          b'26:31 - rsvd1:  reserved for future use
- * dword1 - b'0:16  - ring_buffer_size: size of bufferes referenced by rx ring,
+ * dword1 - b'0:16  - ring_buffer_size: size of buffers referenced by rx ring,
  *                    in byte units.
  *                    Valid only for HW_TO_SW_RING and SW_TO_HW_RING
  *        - b'16:31 - rsvd2: Reserved for future use
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 67f8c140840fb..e6e64d437c47a 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -3027,7 +3027,7 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
 					desc_info->cookie,
 					HAL_RX_BUF_RBM_SW3_BM);
 
-	/* Fill mpdu details into reo entrace ring */
+	/* Fill mpdu details into reo entrance ring */
 	srng = &ab->hal.srng_list[dp->reo_reinject_ring.ring_id];
 
 	spin_lock_bh(&srng->lock);
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index d661fe586651f..8874c815d7faf 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -301,7 +301,7 @@ tcl_ring_sel:
 		spin_unlock_bh(&tcl_ring->lock);
 		ret = -ENOMEM;
 
-		/* Checking for available tcl descritors in another ring in
+		/* Checking for available tcl descriptors in another ring in
 		 * case of failure due to full tcl ring now, is better than
 		 * checking this ring earlier for each pkt tx.
 		 * Restart ring selection if some rings are not checked yet.
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 0f2af2f14ef76..6bb82064ff999 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -6771,7 +6771,7 @@ ath12k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 			/* After trigger disconnect, then upper layer will
 			 * trigger connect again, then the PN number of
 			 * upper layer will be reset to keep up with AP
-			 * side, hence PN number mis-match will not happened.
+			 * side, hence PN number mismatch will not happen.
 			 */
 			if (arvif->is_up &&
 			    arvif->vdev_type == WMI_VDEV_TYPE_STA &&
diff --git a/drivers/net/wireless/ath/ath12k/rx_desc.h b/drivers/net/wireless/ath/ath12k/rx_desc.h
index f99556a253e56..bfa87cb8d0213 100644
--- a/drivers/net/wireless/ath/ath12k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath12k/rx_desc.h
@@ -221,7 +221,7 @@ struct rx_mpdu_start_qcn9274 {
  *		PPE routing even if RXOLE CCE or flow search indicate 'Use_PPE'
  *		This is set by SW for peers which are being handled by a
  *		host SW/accelerator subsystem that also handles packet
- *		uffer management for WiFi-to-PPE routing.
+ *		buffer management for WiFi-to-PPE routing.
  *
  *		This is cleared by SW for peers which are being handled
  *		by a different subsystem, completely disabling WiFi-to-PPE
-- 
GitLab


From 749a660b39030bfbacc366cd8670df2ee0e878b2 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Fri, 4 Aug 2023 17:12:55 +0800
Subject: [PATCH 1593/1806] wifi: ath11k: simplify the code with
 module_platform_driver

The init/exit() of driver only calls platform_driver_register/unregister,
it can be simpilfied with module_platform_driver.

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230804091255.1347178-1-yangyingliang@huawei.com
---
 drivers/net/wireless/ath/ath11k/ahb.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index ceb3ccbb1827d..20eee5881a31d 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -1306,17 +1306,7 @@ static struct platform_driver ath11k_ahb_driver = {
 	.shutdown = ath11k_ahb_shutdown,
 };
 
-static int ath11k_ahb_init(void)
-{
-	return platform_driver_register(&ath11k_ahb_driver);
-}
-module_init(ath11k_ahb_init);
-
-static void ath11k_ahb_exit(void)
-{
-	platform_driver_unregister(&ath11k_ahb_driver);
-}
-module_exit(ath11k_ahb_exit);
+module_platform_driver(ath11k_ahb_driver);
 
 MODULE_DESCRIPTION("Driver support for Qualcomm Technologies 802.11ax WLAN AHB devices");
 MODULE_LICENSE("Dual BSD/GPL");
-- 
GitLab


From 6763ef191d672ff3c2db0622652d49b0c0a60c4a Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Aug 2023 11:12:23 +0200
Subject: [PATCH 1594/1806] wifi: ath11k: fix Wvoid-pointer-to-enum-cast
 warning

'hw_rev' is an enum, thus cast of pointer on 64-bit compile test with W=1
causes:

  h11k/ahb.c:1124:11: error: cast to smaller integer type 'enum ath11k_hw_rev' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast]

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230810091224.70088-1-krzysztof.kozlowski@linaro.org
---
 drivers/net/wireless/ath/ath11k/ahb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index 20eee5881a31d..1215ebdf173a8 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -1096,7 +1096,7 @@ static int ath11k_ahb_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	hw_rev = (enum ath11k_hw_rev)of_id->data;
+	hw_rev = (uintptr_t)of_id->data;
 
 	switch (hw_rev) {
 	case ATH11K_HW_IPQ8074:
-- 
GitLab


From de43b07db2a1af0d11ed167bb028f1038ae04086 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Aug 2023 11:12:24 +0200
Subject: [PATCH 1595/1806] wifi: ath10k: fix Wvoid-pointer-to-enum-cast
 warning

'hw_rev' is an enum, thus cast of pointer on 64-bit compile test with W=1
causes:

  ath10k/ahb.c:736:11: error: cast to smaller integer type 'enum ath10k_hw_rev' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast]

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230810091224.70088-2-krzysztof.kozlowski@linaro.org
---
 drivers/net/wireless/ath/ath10k/ahb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/ahb.c b/drivers/net/wireless/ath/ath10k/ahb.c
index 76efea2f11389..a378bc48b1d2b 100644
--- a/drivers/net/wireless/ath/ath10k/ahb.c
+++ b/drivers/net/wireless/ath/ath10k/ahb.c
@@ -733,7 +733,7 @@ static int ath10k_ahb_probe(struct platform_device *pdev)
 	int ret;
 	struct ath10k_bus_params bus_params = {};
 
-	hw_rev = (enum ath10k_hw_rev)of_device_get_match_data(&pdev->dev);
+	hw_rev = (uintptr_t)of_device_get_match_data(&pdev->dev);
 	if (!hw_rev) {
 		dev_err(&pdev->dev, "OF data missing\n");
 		return -EINVAL;
-- 
GitLab


From adb0b206709f4f2f1256a1ea20619ab98e99f2e7 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 11 Aug 2023 18:44:13 +0800
Subject: [PATCH 1596/1806] wifi: ath11k: Remove unused declarations

Commit 2c3960c2253d ("ath11k: setup ce tasklet for control path")
declared but never implemented ath11k_ce_map_service_to_pipe().
Commit e3396b8bddd2 ("ath11k: ce: support different CE configurations")
declared but never implemented ath11k_ce_attr_attach().
Commit d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices")
declared but never implemented ath11k_qmi_event_work()/ath11k_qmi_msg_recv_work().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230811104413.33668-1-yuehaibing@huawei.com
---
 drivers/net/wireless/ath/ath11k/ce.h  | 3 ---
 drivers/net/wireless/ath/ath11k/qmi.h | 2 --
 2 files changed, 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/ce.h b/drivers/net/wireless/ath/ath11k/ce.h
index 1fc6360e7f01b..c0f6a0ba86df0 100644
--- a/drivers/net/wireless/ath/ath11k/ce.h
+++ b/drivers/net/wireless/ath/ath11k/ce.h
@@ -203,9 +203,6 @@ int ath11k_ce_alloc_pipes(struct ath11k_base *ab);
 void ath11k_ce_free_pipes(struct ath11k_base *ab);
 int ath11k_ce_get_attr_flags(struct ath11k_base *ab, int ce_id);
 void ath11k_ce_poll_send_completed(struct ath11k_base *ab, u8 pipe_id);
-int ath11k_ce_map_service_to_pipe(struct ath11k_base *ab, u16 service_id,
-				  u8 *ul_pipe, u8 *dl_pipe);
-int ath11k_ce_attr_attach(struct ath11k_base *ab);
 void ath11k_ce_get_shadow_config(struct ath11k_base *ab,
 				 u32 **shadow_cfg, u32 *shadow_cfg_len);
 void ath11k_ce_stop_shadow_timers(struct ath11k_base *ab);
diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h
index b0407abf90cd9..d477e2be814b1 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.h
+++ b/drivers/net/wireless/ath/ath11k/qmi.h
@@ -514,8 +514,6 @@ struct qmi_wlanfw_wlan_ini_resp_msg_v01 {
 int ath11k_qmi_firmware_start(struct ath11k_base *ab,
 			      u32 mode);
 void ath11k_qmi_firmware_stop(struct ath11k_base *ab);
-void ath11k_qmi_event_work(struct work_struct *work);
-void ath11k_qmi_msg_recv_work(struct work_struct *work);
 void ath11k_qmi_deinit_service(struct ath11k_base *ab);
 int ath11k_qmi_init_service(struct ath11k_base *ab);
 void ath11k_qmi_free_resource(struct ath11k_base *ab);
-- 
GitLab


From 3b86f86d0f163454c4043a629f0ba95641d371bc Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Aug 2023 09:32:23 +0200
Subject: [PATCH 1597/1806] wifi: ath: remove unused-but-set parameter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This has never been used since the driver was merged, but it now causes
a W=1 warning in recent clang versions

drivers/net/wireless/ath/ath9k/main.c:1566:21: error: parameter 'changed_flags' set but not used [-Werror,-Wunused-but-set-parameter]
drivers/net/wireless/ath/ath9k/htc_drv_main.c:1258:25: error: parameter 'changed_flags' set but not used [-Werror,-Wunused-but-set-parameter]
drivers/net/wireless/ath/ath5k/mac80211-ops.c:367:62: error: parameter 'changed_flags' set but not used [-Werror,-Wunused-but-set-parameter]

Remove the bit manipulation on the otherwise unused parameter.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230814073255.1065242-1-arnd@kernel.org
---
 drivers/net/wireless/ath/ath12k/mac.c         | 5 ++---
 drivers/net/wireless/ath/ath5k/mac80211-ops.c | 1 -
 drivers/net/wireless/ath/ath9k/htc_drv_main.c | 1 -
 drivers/net/wireless/ath/ath9k/main.c         | 1 -
 4 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 6bb82064ff999..88346e66bb753 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -5660,7 +5660,6 @@ static void ath12k_mac_op_configure_filter(struct ieee80211_hw *hw,
 
 	mutex_lock(&ar->conf_mutex);
 
-	changed_flags &= SUPPORTED_FILTERS;
 	*total_flags &= SUPPORTED_FILTERS;
 	ar->filter_flags = *total_flags;
 
@@ -5678,8 +5677,8 @@ static void ath12k_mac_op_configure_filter(struct ieee80211_hw *hw,
 			    "fail to set monitor filter: %d\n", ret);
 	}
 	ath12k_dbg(ar->ab, ATH12K_DBG_MAC,
-		   "changed_flags:0x%x, total_flags:0x%x, reset_flag:%d\n",
-		   changed_flags, *total_flags, reset_flag);
+		   "total_flags:0x%x, reset_flag:%d\n",
+		   *total_flags, reset_flag);
 
 	mutex_unlock(&ar->conf_mutex);
 }
diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index 11ed30d6b595a..c630343ca4f9b 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -382,7 +382,6 @@ ath5k_configure_filter(struct ieee80211_hw *hw, unsigned int changed_flags,
 	mfilt[1] = multicast >> 32;
 
 	/* Only deal with supported flags */
-	changed_flags &= SUPPORTED_FIF_FLAGS;
 	*new_flags &= SUPPORTED_FIF_FLAGS;
 
 	/* If HW detects any phy or radar errors, leave those filters on.
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 44e02cfe24380..9a9b5212051af 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -1264,7 +1264,6 @@ static void ath9k_htc_configure_filter(struct ieee80211_hw *hw,
 	u32 rfilt;
 
 	mutex_lock(&priv->mutex);
-	changed_flags &= SUPPORTED_FILTERS;
 	*total_flags &= SUPPORTED_FILTERS;
 
 	if (test_bit(ATH_OP_INVALID, &common->op_flags)) {
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 6360d3356e256..1494feedb27db 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -1571,7 +1571,6 @@ static void ath9k_configure_filter(struct ieee80211_hw *hw,
 	struct ath_chanctx *ctx;
 	u32 rfilt;
 
-	changed_flags &= SUPPORTED_FILTERS;
 	*total_flags &= SUPPORTED_FILTERS;
 
 	spin_lock_bh(&sc->chan_lock);
-- 
GitLab


From e10ec6ea612ca54e3266996875b0742619dac20f Mon Sep 17 00:00:00 2001
From: Mahmoud Maatuq <mahmoudmatook.mm@gmail.com>
Date: Tue, 15 Aug 2023 08:08:19 +0400
Subject: [PATCH 1598/1806] wifi: ath5k: ath5k_hw_get_median_noise_floor(): use
 swap()

coccinielle reported the following:
./drivers/net/wireless/ath/ath5k/phy.c:1573:25-26: WARNING opportunity for swap()

while trying to fix the above warning, it reveals that ath5k_hw_get_median_noise_floor()
had open-coded sort() functionality. Since ath5k_hw_get_median_noise_floor() only
executes once every 10 seconds, any extra overhead due to sort() calling
its "compare" and "swap" functions can be ignored, so replace the
existing logic with a call to sort().

Signed-off-by: Mahmoud Maatuq <mahmoudmatook.mm@gmail.com>
Suggested-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230815040819.649455-1-mahmoudmatook.mm@gmail.com
---
 drivers/net/wireless/ath/ath5k/phy.c | 29 +++++++++++++---------------
 1 file changed, 13 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/ath/ath5k/phy.c b/drivers/net/wireless/ath/ath5k/phy.c
index 5797ef9c73d72..7ee4e1616f45a 100644
--- a/drivers/net/wireless/ath/ath5k/phy.c
+++ b/drivers/net/wireless/ath/ath5k/phy.c
@@ -26,6 +26,7 @@
 
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/sort.h>
 #include <asm/unaligned.h>
 
 #include "ath5k.h"
@@ -1554,6 +1555,11 @@ static void ath5k_hw_update_nfcal_hist(struct ath5k_hw *ah, s16 noise_floor)
 	hist->nfval[hist->index] = noise_floor;
 }
 
+static int cmps16(const void *a, const void *b)
+{
+	return *(s16 *)a - *(s16 *)b;
+}
+
 /**
  * ath5k_hw_get_median_noise_floor() - Get median NF from history buffer
  * @ah: The &struct ath5k_hw
@@ -1561,25 +1567,16 @@ static void ath5k_hw_update_nfcal_hist(struct ath5k_hw *ah, s16 noise_floor)
 static s16
 ath5k_hw_get_median_noise_floor(struct ath5k_hw *ah)
 {
-	s16 sort[ATH5K_NF_CAL_HIST_MAX];
-	s16 tmp;
-	int i, j;
-
-	memcpy(sort, ah->ah_nfcal_hist.nfval, sizeof(sort));
-	for (i = 0; i < ATH5K_NF_CAL_HIST_MAX - 1; i++) {
-		for (j = 1; j < ATH5K_NF_CAL_HIST_MAX - i; j++) {
-			if (sort[j] > sort[j - 1]) {
-				tmp = sort[j];
-				sort[j] = sort[j - 1];
-				sort[j - 1] = tmp;
-			}
-		}
-	}
+	s16 sorted_nfval[ATH5K_NF_CAL_HIST_MAX];
+	int i;
+
+	memcpy(sorted_nfval, ah->ah_nfcal_hist.nfval, sizeof(sorted_nfval));
+	sort(sorted_nfval, ATH5K_NF_CAL_HIST_MAX, sizeof(s16), cmps16, NULL);
 	for (i = 0; i < ATH5K_NF_CAL_HIST_MAX; i++) {
 		ATH5K_DBG(ah, ATH5K_DEBUG_CALIBRATE,
-			"cal %d:%d\n", i, sort[i]);
+			"cal %d:%d\n", i, sorted_nfval[i]);
 	}
-	return sort[(ATH5K_NF_CAL_HIST_MAX - 1) / 2];
+	return sorted_nfval[(ATH5K_NF_CAL_HIST_MAX - 1) / 2];
 }
 
 /**
-- 
GitLab


From afb522b36e76acaa9f8fc06d0a9742d841c47c16 Mon Sep 17 00:00:00 2001
From: Rajat Soni <quic_rajson@quicinc.com>
Date: Tue, 22 Aug 2023 16:42:23 +0300
Subject: [PATCH 1599/1806] wifi: ath12k: Fix memory leak in rx_desc and
 tx_desc

Currently when ath12k_dp_cc_desc_init() is called we allocate
memory to rx_descs and tx_descs. In ath12k_dp_cc_cleanup(), during
descriptor cleanup rx_descs and tx_descs memory is not freed.

This is cause of memory leak. These allocated memory should be
freed in ath12k_dp_cc_cleanup.

In ath12k_dp_cc_desc_init(), we can save base address of rx_descs
and tx_descs. In ath12k_dp_cc_cleanup(), we can free rx_descs and
tx_descs memory using their base address.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1

Signed-off-by: Rajat Soni <quic_rajson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230718053510.30894-1-quic_rajson@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp.c | 30 +++++++++++++++++++++++++++-
 drivers/net/wireless/ath/ath12k/dp.h |  2 ++
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index ae1645d0f42a2..f933896f2a68d 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -1129,6 +1129,7 @@ static void ath12k_dp_cc_cleanup(struct ath12k_base *ab)
 	struct ath12k_dp *dp = &ab->dp;
 	struct sk_buff *skb;
 	int i;
+	u32 pool_id, tx_spt_page;
 
 	if (!dp->spt_info)
 		return;
@@ -1148,6 +1149,14 @@ static void ath12k_dp_cc_cleanup(struct ath12k_base *ab)
 		dev_kfree_skb_any(skb);
 	}
 
+	for (i = 0; i < ATH12K_NUM_RX_SPT_PAGES; i++) {
+		if (!dp->spt_info->rxbaddr[i])
+			continue;
+
+		kfree(dp->spt_info->rxbaddr[i]);
+		dp->spt_info->rxbaddr[i] = NULL;
+	}
+
 	spin_unlock_bh(&dp->rx_desc_lock);
 
 	/* TX Descriptor cleanup */
@@ -1170,6 +1179,21 @@ static void ath12k_dp_cc_cleanup(struct ath12k_base *ab)
 		spin_unlock_bh(&dp->tx_desc_lock[i]);
 	}
 
+	for (pool_id = 0; pool_id < ATH12K_HW_MAX_QUEUES; pool_id++) {
+		spin_lock_bh(&dp->tx_desc_lock[pool_id]);
+
+		for (i = 0; i < ATH12K_TX_SPT_PAGES_PER_POOL; i++) {
+			tx_spt_page = i + pool_id * ATH12K_TX_SPT_PAGES_PER_POOL;
+			if (!dp->spt_info->txbaddr[tx_spt_page])
+				continue;
+
+			kfree(dp->spt_info->txbaddr[tx_spt_page]);
+			dp->spt_info->txbaddr[tx_spt_page] = NULL;
+		}
+
+		spin_unlock_bh(&dp->tx_desc_lock[pool_id]);
+	}
+
 	/* unmap SPT pages */
 	for (i = 0; i < dp->num_spt_pages; i++) {
 		if (!dp->spt_info[i].vaddr)
@@ -1343,6 +1367,8 @@ static int ath12k_dp_cc_desc_init(struct ath12k_base *ab)
 			return -ENOMEM;
 		}
 
+		dp->spt_info->rxbaddr[i] = &rx_descs[0];
+
 		for (j = 0; j < ATH12K_MAX_SPT_ENTRIES; j++) {
 			rx_descs[j].cookie = ath12k_dp_cc_cookie_gen(i, j);
 			rx_descs[j].magic = ATH12K_DP_RX_DESC_MAGIC;
@@ -1368,8 +1394,10 @@ static int ath12k_dp_cc_desc_init(struct ath12k_base *ab)
 				return -ENOMEM;
 			}
 
+			tx_spt_page = i + pool_id * ATH12K_TX_SPT_PAGES_PER_POOL;
+			dp->spt_info->txbaddr[tx_spt_page] = &tx_descs[0];
+
 			for (j = 0; j < ATH12K_MAX_SPT_ENTRIES; j++) {
-				tx_spt_page = i + pool_id * ATH12K_TX_SPT_PAGES_PER_POOL;
 				ppt_idx = ATH12K_NUM_RX_SPT_PAGES + tx_spt_page;
 				tx_descs[j].desc_id = ath12k_dp_cc_cookie_gen(ppt_idx, j);
 				tx_descs[j].pool_id = pool_id;
diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index 6e7b7281d549b..61f765432516b 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -289,6 +289,8 @@ struct ath12k_tx_desc_info {
 struct ath12k_spt_info {
 	dma_addr_t paddr;
 	u64 *vaddr;
+	struct ath12k_rx_desc_info *rxbaddr[ATH12K_NUM_RX_SPT_PAGES];
+	struct ath12k_tx_desc_info *txbaddr[ATH12K_NUM_TX_SPT_PAGES];
 };
 
 struct ath12k_reo_queue_ref {
-- 
GitLab


From d75e30dddf73449bc2d10bb8e2f1a2c446bc67a2 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Wed, 23 Aug 2023 02:07:02 +0000
Subject: [PATCH 1600/1806] bpf: Fix issue in verifying allow_ptr_leaks

After we converted the capabilities of our networking-bpf program from
cap_sys_admin to cap_net_admin+cap_bpf, our networking-bpf program
failed to start. Because it failed the bpf verifier, and the error log
is "R3 pointer comparison prohibited".

A simple reproducer as follows,

SEC("cls-ingress")
int ingress(struct __sk_buff *skb)
{
	struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr);

	if ((long)(iph + 1) > (long)skb->data_end)
		return TC_ACT_STOLEN;
	return TC_ACT_OK;
}

Per discussion with Yonghong and Alexei [1], comparison of two packet
pointers is not a pointer leak. This patch fixes it.

Our local kernel is 6.1.y and we expect this fix to be backported to
6.1.y, so stable is CCed.

[1]. https://lore.kernel.org/bpf/CAADnVQ+Nmspr7Si+pxWn8zkE7hX-7s93ugwC+94aXSy4uQ9vBg@mail.gmail.com/

Suggested-by: Yonghong Song <yonghong.song@linux.dev>
Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230823020703.3790-2-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3d51c737a034f..0680569f9bd07 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -14041,6 +14041,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	/* check src2 operand */
+	err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+	if (err)
+		return err;
+
+	dst_reg = &regs[insn->dst_reg];
 	if (BPF_SRC(insn->code) == BPF_X) {
 		if (insn->imm != 0) {
 			verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
@@ -14052,12 +14058,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		if (err)
 			return err;
 
-		if (is_pointer_value(env, insn->src_reg)) {
+		src_reg = &regs[insn->src_reg];
+		if (!(reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg)) &&
+		    is_pointer_value(env, insn->src_reg)) {
 			verbose(env, "R%d pointer comparison prohibited\n",
 				insn->src_reg);
 			return -EACCES;
 		}
-		src_reg = &regs[insn->src_reg];
 	} else {
 		if (insn->src_reg != BPF_REG_0) {
 			verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
@@ -14065,12 +14072,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		}
 	}
 
-	/* check src2 operand */
-	err = check_reg_arg(env, insn->dst_reg, SRC_OP);
-	if (err)
-		return err;
-
-	dst_reg = &regs[insn->dst_reg];
 	is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
 
 	if (BPF_SRC(insn->code) == BPF_K) {
-- 
GitLab


From 0072e3624b463636c842ad8e261f1dc91deb8c78 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Wed, 23 Aug 2023 02:07:03 +0000
Subject: [PATCH 1601/1806] selftests/bpf: Add selftest for allow_ptr_leaks

- Without prev commit

  $ tools/testing/selftests/bpf/test_progs --name=tc_bpf
  #232/1   tc_bpf/tc_bpf_root:OK
  test_tc_bpf_non_root:PASS:set_cap_bpf_cap_net_admin 0 nsec
  test_tc_bpf_non_root:PASS:disable_cap_sys_admin 0 nsec
  0: R1=ctx(off=0,imm=0) R10=fp0
  ; if ((long)(iph + 1) > (long)skb->data_end)
  0: (61) r2 = *(u32 *)(r1 +80)         ; R1=ctx(off=0,imm=0) R2_w=pkt_end(off=0,imm=0)
  ; struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr);
  1: (61) r1 = *(u32 *)(r1 +76)         ; R1_w=pkt(off=0,r=0,imm=0)
  ; if ((long)(iph + 1) > (long)skb->data_end)
  2: (07) r1 += 34                      ; R1_w=pkt(off=34,r=0,imm=0)
  3: (b4) w0 = 1                        ; R0_w=1
  4: (2d) if r1 > r2 goto pc+1
  R2 pointer comparison prohibited
  processed 5 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0
  test_tc_bpf_non_root:FAIL:test_tc_bpf__open_and_load unexpected error: -13
  #233/2   tc_bpf_non_root:FAIL

- With prev commit

  $ tools/testing/selftests/bpf/test_progs --name=tc_bpf
  #232/1   tc_bpf/tc_bpf_root:OK
  #232/2   tc_bpf/tc_bpf_non_root:OK
  #232     tc_bpf:OK
  Summary: 1/2 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Link: https://lore.kernel.org/r/20230823020703.3790-3-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/prog_tests/tc_bpf.c | 36 ++++++++++++++++++-
 .../testing/selftests/bpf/progs/test_tc_bpf.c | 13 +++++++
 2 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c
index e873766276d10..48b55539331ee 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c
@@ -3,6 +3,7 @@
 #include <test_progs.h>
 #include <linux/pkt_cls.h>
 
+#include "cap_helpers.h"
 #include "test_tc_bpf.skel.h"
 
 #define LO_IFINDEX 1
@@ -327,7 +328,7 @@ static int test_tc_bpf_api(struct bpf_tc_hook *hook, int fd)
 	return 0;
 }
 
-void test_tc_bpf(void)
+void tc_bpf_root(void)
 {
 	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
 			    .attach_point = BPF_TC_INGRESS);
@@ -393,3 +394,36 @@ end:
 	}
 	test_tc_bpf__destroy(skel);
 }
+
+void tc_bpf_non_root(void)
+{
+	struct test_tc_bpf *skel = NULL;
+	__u64 caps = 0;
+	int ret;
+
+	/* In case CAP_BPF and CAP_PERFMON is not set */
+	ret = cap_enable_effective(1ULL << CAP_BPF | 1ULL << CAP_NET_ADMIN, &caps);
+	if (!ASSERT_OK(ret, "set_cap_bpf_cap_net_admin"))
+		return;
+	ret = cap_disable_effective(1ULL << CAP_SYS_ADMIN | 1ULL << CAP_PERFMON, NULL);
+	if (!ASSERT_OK(ret, "disable_cap_sys_admin"))
+		goto restore_cap;
+
+	skel = test_tc_bpf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tc_bpf__open_and_load"))
+		goto restore_cap;
+
+	test_tc_bpf__destroy(skel);
+
+restore_cap:
+	if (caps)
+		cap_enable_effective(caps, NULL);
+}
+
+void test_tc_bpf(void)
+{
+	if (test__start_subtest("tc_bpf_root"))
+		tc_bpf_root();
+	if (test__start_subtest("tc_bpf_non_root"))
+		tc_bpf_non_root();
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c
index d28ca8d1f3d07..ef7da419632a2 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_bpf.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c
@@ -2,6 +2,8 @@
 
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
 
 /* Dummy prog to test TC-BPF API */
 
@@ -10,3 +12,14 @@ int cls(struct __sk_buff *skb)
 {
 	return 0;
 }
+
+/* Prog to verify tc-bpf without cap_sys_admin and cap_perfmon */
+SEC("tcx/ingress")
+int pkt_ptr(struct __sk_buff *skb)
+{
+	struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr);
+
+	if ((long)(iph + 1) > (long)skb->data_end)
+		return 1;
+	return 0;
+}
-- 
GitLab


From 068ca522d5a563ac4ecc48c2c7c390102537fefd Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Wed, 23 Aug 2023 17:15:02 -0600
Subject: [PATCH 1602/1806] libbpf: Add bpf_object__unpin()

For bpf_object__pin_programs() there is bpf_object__unpin_programs().
Likewise bpf_object__unpin_maps() for bpf_object__pin_maps().

But no bpf_object__unpin() for bpf_object__pin(). Adding the former adds
symmetry to the API.

It's also convenient for cleanup in application code. It's an API I
would've used if it was available for a repro I was writing earlier.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/bpf/b2f9d41da4a350281a0b53a804d11b68327e14e5.1692832478.git.dxu@dxuuu.xyz
---
 tools/lib/bpf/libbpf.c   | 15 +++++++++++++++
 tools/lib/bpf/libbpf.h   |  1 +
 tools/lib/bpf/libbpf.map |  1 +
 3 files changed, 17 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4c3967d94b6d3..96ff1aa4bf6a0 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8376,6 +8376,21 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 	return 0;
 }
 
+int bpf_object__unpin(struct bpf_object *obj, const char *path)
+{
+	int err;
+
+	err = bpf_object__unpin_programs(obj, path);
+	if (err)
+		return libbpf_err(err);
+
+	err = bpf_object__unpin_maps(obj, path);
+	if (err)
+		return libbpf_err(err);
+
+	return 0;
+}
+
 static void bpf_map__destroy(struct bpf_map *map)
 {
 	if (map->inner_map) {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 2e3eb3614c40b..0e52621cba435 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -266,6 +266,7 @@ LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj,
 LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj,
 					  const char *path);
 LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path);
+LIBBPF_API int bpf_object__unpin(struct bpf_object *object, const char *path);
 
 LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
 LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 841a2f9c6fef4..57712321490f8 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -395,6 +395,7 @@ LIBBPF_1.2.0 {
 LIBBPF_1.3.0 {
 	global:
 		bpf_obj_pin_opts;
+		bpf_object__unpin;
 		bpf_prog_detach_opts;
 		bpf_program__attach_netfilter;
 		bpf_program__attach_tcx;
-- 
GitLab


From 664c84c26d7a77d4b19813831466d67253f2326e Mon Sep 17 00:00:00 2001
From: Yu Liao <liaoyu15@huawei.com>
Date: Tue, 22 Aug 2023 10:14:55 +0800
Subject: [PATCH 1603/1806] net: dm9051: Use PTR_ERR_OR_ZERO() to simplify code

Use the standard error pointer macro to shorten the code and simplify.

Signed-off-by: Yu Liao <liaoyu15@huawei.com>
Link: https://lore.kernel.org/r/20230822021455.205101-2-liaoyu15@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/davicom/dm9051.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/davicom/dm9051.c b/drivers/net/ethernet/davicom/dm9051.c
index 2caaf1e9f42fb..bcfe52c11804a 100644
--- a/drivers/net/ethernet/davicom/dm9051.c
+++ b/drivers/net/ethernet/davicom/dm9051.c
@@ -1158,9 +1158,7 @@ static int dm9051_phy_connect(struct board_info *db)
 
 	db->phydev = phy_connect(db->ndev, phy_id, dm9051_handle_link_change,
 				 PHY_INTERFACE_MODE_MII);
-	if (IS_ERR(db->phydev))
-		return PTR_ERR_OR_ZERO(db->phydev);
-	return 0;
+	return PTR_ERR_OR_ZERO(db->phydev);
 }
 
 static int dm9051_probe(struct spi_device *spi)
-- 
GitLab


From e83fabb797b98a9ead4b5bb50c85fb499966ad7e Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 22 Aug 2023 14:52:55 +0800
Subject: [PATCH 1604/1806] net: fec: add exception tracing for XDP

As we already added the exception tracing for XDP_TX, I think it is
necessary to add the exception tracing for other XDP actions, such
as XDP_REDIRECT, XDP_ABORTED and unknown error actions.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230822065255.606739-1-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c | 26 ++++++++++-------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index e23a559771839..8909899e9a31f 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1583,25 +1583,18 @@ fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog,
 	case XDP_REDIRECT:
 		rxq->stats[RX_XDP_REDIRECT]++;
 		err = xdp_do_redirect(fep->netdev, xdp, prog);
-		if (!err) {
-			ret = FEC_ENET_XDP_REDIR;
-		} else {
-			ret = FEC_ENET_XDP_CONSUMED;
-			page = virt_to_head_page(xdp->data);
-			page_pool_put_page(rxq->page_pool, page, sync, true);
-		}
+		if (unlikely(err))
+			goto xdp_err;
+
+		ret = FEC_ENET_XDP_REDIR;
 		break;
 
 	case XDP_TX:
 		err = fec_enet_xdp_tx_xmit(fep, cpu, xdp, sync);
-		if (unlikely(err)) {
-			ret = FEC_ENET_XDP_CONSUMED;
-			page = virt_to_head_page(xdp->data);
-			page_pool_put_page(rxq->page_pool, page, sync, true);
-			trace_xdp_exception(fep->netdev, prog, act);
-		} else {
-			ret = FEC_ENET_XDP_TX;
-		}
+		if (unlikely(err))
+			goto xdp_err;
+
+		ret = FEC_ENET_XDP_TX;
 		break;
 
 	default:
@@ -1613,9 +1606,12 @@ fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog,
 
 	case XDP_DROP:
 		rxq->stats[RX_XDP_DROP]++;
+xdp_err:
 		ret = FEC_ENET_XDP_CONSUMED;
 		page = virt_to_head_page(xdp->data);
 		page_pool_put_page(rxq->page_pool, page, sync, true);
+		if (act != XDP_DROP)
+			trace_xdp_exception(fep->netdev, prog, act);
 		break;
 	}
 
-- 
GitLab


From cfb5677de5babe3664356155a391e2ff781c9ee1 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 22 Aug 2023 17:31:24 +0100
Subject: [PATCH 1605/1806] net: ethernet: mtk_eth_soc: fix register
 definitions for MT7988

More register macros need to be adjusted for the 3rd GMAC on MT7988.
Account for added bit in SYSCFG0_SGMII_MASK.

Fixes: 445eb6448ed3 ("net: ethernet: mtk_eth_soc: add basic support for MT7988 SoC")
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/1c8da012e2ca80939906d85f314138c552139f0f.1692721443.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 4a2470fbad2cf..8d2d35b322351 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -133,10 +133,12 @@
 #define MTK_GDMA_XGDM_SEL	BIT(31)
 
 /* Unicast Filter MAC Address Register - Low */
-#define MTK_GDMA_MAC_ADRL(x)	(0x508 + (x * 0x1000))
+#define MTK_GDMA_MAC_ADRL(x)	({ typeof(x) _x = (x); (_x == MTK_GMAC3_ID) ?	\
+				   0x548 : 0x508 + (_x * 0x1000); })
 
 /* Unicast Filter MAC Address Register - High */
-#define MTK_GDMA_MAC_ADRH(x)	(0x50C + (x * 0x1000))
+#define MTK_GDMA_MAC_ADRH(x)	({ typeof(x) _x = (x); (_x == MTK_GMAC3_ID) ?	\
+				   0x54C : 0x50C + (_x * 0x1000); })
 
 /* FE global misc reg*/
 #define MTK_FE_GLO_MISC         0x124
@@ -503,7 +505,7 @@
 #define ETHSYS_SYSCFG0		0x14
 #define SYSCFG0_GE_MASK		0x3
 #define SYSCFG0_GE_MODE(x, y)	(x << (12 + (y * 2)))
-#define SYSCFG0_SGMII_MASK     GENMASK(9, 8)
+#define SYSCFG0_SGMII_MASK     GENMASK(9, 7)
 #define SYSCFG0_SGMII_GMAC1    ((2 << 8) & SYSCFG0_SGMII_MASK)
 #define SYSCFG0_SGMII_GMAC2    ((3 << 8) & SYSCFG0_SGMII_MASK)
 #define SYSCFG0_SGMII_GMAC1_V2 BIT(9)
-- 
GitLab


From 88c1e6efb7a58ff64ce196ec09d831263793c858 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 22 Aug 2023 17:32:03 +0100
Subject: [PATCH 1606/1806] net: ethernet: mtk_eth_soc: add reset bits for
 MT7988

Add bits needed to reset the frame engine on MT7988.

Fixes: 445eb6448ed3 ("net: ethernet: mtk_eth_soc: add basic support for MT7988 SoC")
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/89b6c38380e7a3800c1362aa7575600717bc7543.1692721443.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 76 +++++++++++++++------
 drivers/net/ethernet/mediatek/mtk_eth_soc.h | 16 +++--
 2 files changed, 68 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index fe05c90202699..2482f47313085 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -3613,19 +3613,34 @@ static void mtk_hw_reset(struct mtk_eth *eth)
 {
 	u32 val;
 
-	if (mtk_is_netsys_v2_or_greater(eth)) {
+	if (mtk_is_netsys_v2_or_greater(eth))
 		regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN, 0);
+
+	if (mtk_is_netsys_v3_or_greater(eth)) {
+		val = RSTCTRL_PPE0_V3;
+
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1))
+			val |= RSTCTRL_PPE1_V3;
+
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE2))
+			val |= RSTCTRL_PPE2;
+
+		val |= RSTCTRL_WDMA0 | RSTCTRL_WDMA1 | RSTCTRL_WDMA2;
+	} else if (mtk_is_netsys_v2_or_greater(eth)) {
 		val = RSTCTRL_PPE0_V2;
+
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1))
+			val |= RSTCTRL_PPE1;
 	} else {
 		val = RSTCTRL_PPE0;
 	}
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1))
-		val |= RSTCTRL_PPE1;
-
 	ethsys_reset(eth, RSTCTRL_ETH | RSTCTRL_FE | val);
 
-	if (mtk_is_netsys_v2_or_greater(eth))
+	if (mtk_is_netsys_v3_or_greater(eth))
+		regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN,
+			     0x6f8ff);
+	else if (mtk_is_netsys_v2_or_greater(eth))
 		regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN,
 			     0x3ffffff);
 }
@@ -3651,13 +3666,21 @@ static void mtk_hw_warm_reset(struct mtk_eth *eth)
 		return;
 	}
 
-	if (mtk_is_netsys_v2_or_greater(eth))
+	if (mtk_is_netsys_v3_or_greater(eth)) {
+		rst_mask = RSTCTRL_ETH | RSTCTRL_PPE0_V3;
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1))
+			rst_mask |= RSTCTRL_PPE1_V3;
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE2))
+			rst_mask |= RSTCTRL_PPE2;
+
+		rst_mask |= RSTCTRL_WDMA0 | RSTCTRL_WDMA1 | RSTCTRL_WDMA2;
+	} else if (mtk_is_netsys_v2_or_greater(eth)) {
 		rst_mask = RSTCTRL_ETH | RSTCTRL_PPE0_V2;
-	else
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1))
+			rst_mask |= RSTCTRL_PPE1;
+	} else {
 		rst_mask = RSTCTRL_ETH | RSTCTRL_PPE0;
-
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1))
-		rst_mask |= RSTCTRL_PPE1;
+	}
 
 	regmap_update_bits(eth->ethsys, ETHSYS_RSTCTRL, rst_mask, rst_mask);
 
@@ -4009,11 +4032,17 @@ static void mtk_prepare_for_reset(struct mtk_eth *eth)
 	u32 val;
 	int i;
 
-	/* disabe FE P3 and P4 */
-	val = mtk_r32(eth, MTK_FE_GLO_CFG) | MTK_FE_LINK_DOWN_P3;
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1))
-		val |= MTK_FE_LINK_DOWN_P4;
-	mtk_w32(eth, val, MTK_FE_GLO_CFG);
+	/* set FE PPE ports link down */
+	for (i = MTK_GMAC1_ID;
+	     i <= (mtk_is_netsys_v3_or_greater(eth) ? MTK_GMAC3_ID : MTK_GMAC2_ID);
+	     i += 2) {
+		val = mtk_r32(eth, MTK_FE_GLO_CFG(i)) | MTK_FE_LINK_DOWN_P(PSE_PPE0_PORT);
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1))
+			val |= MTK_FE_LINK_DOWN_P(PSE_PPE1_PORT);
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE2))
+			val |= MTK_FE_LINK_DOWN_P(PSE_PPE2_PORT);
+		mtk_w32(eth, val, MTK_FE_GLO_CFG(i));
+	}
 
 	/* adjust PPE configurations to prepare for reset */
 	for (i = 0; i < ARRAY_SIZE(eth->ppe); i++)
@@ -4074,11 +4103,18 @@ static void mtk_pending_work(struct work_struct *work)
 		}
 	}
 
-	/* enabe FE P3 and P4 */
-	val = mtk_r32(eth, MTK_FE_GLO_CFG) & ~MTK_FE_LINK_DOWN_P3;
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1))
-		val &= ~MTK_FE_LINK_DOWN_P4;
-	mtk_w32(eth, val, MTK_FE_GLO_CFG);
+	/* set FE PPE ports link up */
+	for (i = MTK_GMAC1_ID;
+	     i <= (mtk_is_netsys_v3_or_greater(eth) ? MTK_GMAC3_ID : MTK_GMAC2_ID);
+	     i += 2) {
+		val = mtk_r32(eth, MTK_FE_GLO_CFG(i)) & ~MTK_FE_LINK_DOWN_P(PSE_PPE0_PORT);
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1))
+			val &= ~MTK_FE_LINK_DOWN_P(PSE_PPE1_PORT);
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE2))
+			val &= ~MTK_FE_LINK_DOWN_P(PSE_PPE2_PORT);
+
+		mtk_w32(eth, val, MTK_FE_GLO_CFG(i));
+	}
 
 	clear_bit(MTK_RESETTING, &eth->state);
 
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 8d2d35b322351..cf9381a3d68b7 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -76,9 +76,8 @@
 #define	MTK_HW_LRO_SDL_REMAIN_ROOM	1522
 
 /* Frame Engine Global Configuration */
-#define MTK_FE_GLO_CFG		0x00
-#define MTK_FE_LINK_DOWN_P3	BIT(11)
-#define MTK_FE_LINK_DOWN_P4	BIT(12)
+#define MTK_FE_GLO_CFG(x)	(((x) == MTK_GMAC3_ID) ? 0x24 : 0x00)
+#define MTK_FE_LINK_DOWN_P(x)	BIT(((x) + 8) % 16)
 
 /* Frame Engine Global Reset Register */
 #define MTK_RST_GL		0x04
@@ -522,9 +521,15 @@
 /* ethernet reset control register */
 #define ETHSYS_RSTCTRL			0x34
 #define RSTCTRL_FE			BIT(6)
+#define RSTCTRL_WDMA0			BIT(24)
+#define RSTCTRL_WDMA1			BIT(25)
+#define RSTCTRL_WDMA2			BIT(26)
 #define RSTCTRL_PPE0			BIT(31)
 #define RSTCTRL_PPE0_V2			BIT(30)
 #define RSTCTRL_PPE1			BIT(31)
+#define RSTCTRL_PPE0_V3			BIT(29)
+#define RSTCTRL_PPE1_V3			BIT(30)
+#define RSTCTRL_PPE2			BIT(31)
 #define RSTCTRL_ETH			BIT(23)
 
 /* ethernet reset check idle register */
@@ -931,6 +936,7 @@ enum mkt_eth_capabilities {
 	MTK_QDMA_BIT,
 	MTK_SOC_MT7628_BIT,
 	MTK_RSTCTRL_PPE1_BIT,
+	MTK_RSTCTRL_PPE2_BIT,
 	MTK_U3_COPHY_V2_BIT,
 
 	/* MUX BITS*/
@@ -965,6 +971,7 @@ enum mkt_eth_capabilities {
 #define MTK_QDMA		BIT_ULL(MTK_QDMA_BIT)
 #define MTK_SOC_MT7628		BIT_ULL(MTK_SOC_MT7628_BIT)
 #define MTK_RSTCTRL_PPE1	BIT_ULL(MTK_RSTCTRL_PPE1_BIT)
+#define MTK_RSTCTRL_PPE2	BIT_ULL(MTK_RSTCTRL_PPE2_BIT)
 #define MTK_U3_COPHY_V2		BIT_ULL(MTK_U3_COPHY_V2_BIT)
 
 #define MTK_ETH_MUX_GDM1_TO_GMAC1_ESW		\
@@ -1047,7 +1054,8 @@ enum mkt_eth_capabilities {
 		      MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \
 		      MTK_RSTCTRL_PPE1)
 
-#define MT7988_CAPS  (MTK_GDM1_ESW | MTK_QDMA | MTK_RSTCTRL_PPE1)
+#define MT7988_CAPS  (MTK_GDM1_ESW | MTK_QDMA | MTK_RSTCTRL_PPE1 | \
+		      MTK_RSTCTRL_PPE2)
 
 struct mtk_tx_dma_desc_info {
 	dma_addr_t	addr;
-- 
GitLab


From ebb1e4f9cf38da2139b37e24b5e10bff3dcc4187 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 22 Aug 2023 17:32:54 +0100
Subject: [PATCH 1607/1806] net: ethernet: mtk_eth_soc: add support for in-SoC
 SRAM

MT7981, MT7986 and MT7988 come with in-SoC SRAM dedicated for Ethernet
DMA rings. Support using the SRAM without breaking existing device tree
bindings, ie. only new SoC starting from MT7988 will have the SRAM
declared as additional resource in device tree. For MT7981 and MT7986
an offset on top of the main I/O base is used.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/e45e0f230c63ad58869e8fe35b95a2fb8925b625.1692721443.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 88 ++++++++++++++++-----
 drivers/net/ethernet/mediatek/mtk_eth_soc.h | 12 ++-
 2 files changed, 78 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 2482f47313085..ec6a251a0f026 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1135,10 +1135,13 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 	dma_addr_t dma_addr;
 	int i;
 
-	eth->scratch_ring = dma_alloc_coherent(eth->dma_dev,
-					       cnt * soc->txrx.txd_size,
-					       &eth->phy_scratch_ring,
-					       GFP_KERNEL);
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM))
+		eth->scratch_ring = eth->sram_base;
+	else
+		eth->scratch_ring = dma_alloc_coherent(eth->dma_dev,
+						       cnt * soc->txrx.txd_size,
+						       &eth->phy_scratch_ring,
+						       GFP_KERNEL);
 	if (unlikely(!eth->scratch_ring))
 		return -ENOMEM;
 
@@ -2446,8 +2449,14 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 	if (!ring->buf)
 		goto no_tx_mem;
 
-	ring->dma = dma_alloc_coherent(eth->dma_dev, ring_size * sz,
-				       &ring->phys, GFP_KERNEL);
+	if (MTK_HAS_CAPS(soc->caps, MTK_SRAM)) {
+		ring->dma = eth->sram_base + ring_size * sz;
+		ring->phys = eth->phy_scratch_ring + ring_size * (dma_addr_t)sz;
+	} else {
+		ring->dma = dma_alloc_coherent(eth->dma_dev, ring_size * sz,
+					       &ring->phys, GFP_KERNEL);
+	}
+
 	if (!ring->dma)
 		goto no_tx_mem;
 
@@ -2546,8 +2555,7 @@ static void mtk_tx_clean(struct mtk_eth *eth)
 		kfree(ring->buf);
 		ring->buf = NULL;
 	}
-
-	if (ring->dma) {
+	if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && ring->dma) {
 		dma_free_coherent(eth->dma_dev,
 				  ring->dma_size * soc->txrx.txd_size,
 				  ring->dma, ring->phys);
@@ -2566,9 +2574,14 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 {
 	const struct mtk_reg_map *reg_map = eth->soc->reg_map;
 	struct mtk_rx_ring *ring;
-	int rx_data_len, rx_dma_size;
+	int rx_data_len, rx_dma_size, tx_ring_size;
 	int i;
 
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA))
+		tx_ring_size = MTK_QDMA_RING_SIZE;
+	else
+		tx_ring_size = MTK_DMA_SIZE;
+
 	if (rx_flag == MTK_RX_FLAGS_QDMA) {
 		if (ring_no)
 			return -EINVAL;
@@ -2603,9 +2616,20 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 		ring->page_pool = pp;
 	}
 
-	ring->dma = dma_alloc_coherent(eth->dma_dev,
-				       rx_dma_size * eth->soc->txrx.rxd_size,
-				       &ring->phys, GFP_KERNEL);
+	if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM) ||
+	    rx_flag != MTK_RX_FLAGS_NORMAL) {
+		ring->dma = dma_alloc_coherent(eth->dma_dev,
+					       rx_dma_size * eth->soc->txrx.rxd_size,
+					       &ring->phys, GFP_KERNEL);
+	} else {
+		struct mtk_tx_ring *tx_ring = &eth->tx_ring;
+
+		ring->dma = tx_ring->dma + tx_ring_size *
+			    eth->soc->txrx.txd_size * (ring_no + 1);
+		ring->phys = tx_ring->phys + tx_ring_size *
+			     eth->soc->txrx.txd_size * (ring_no + 1);
+	}
+
 	if (!ring->dma)
 		return -ENOMEM;
 
@@ -2690,7 +2714,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 	return 0;
 }
 
-static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring)
+static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring, bool in_sram)
 {
 	int i;
 
@@ -2713,7 +2737,7 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring)
 		ring->data = NULL;
 	}
 
-	if (ring->dma) {
+	if (!in_sram && ring->dma) {
 		dma_free_coherent(eth->dma_dev,
 				  ring->dma_size * eth->soc->txrx.rxd_size,
 				  ring->dma, ring->phys);
@@ -3073,7 +3097,7 @@ static void mtk_dma_free(struct mtk_eth *eth)
 	for (i = 0; i < MTK_MAX_DEVS; i++)
 		if (eth->netdev[i])
 			netdev_reset_queue(eth->netdev[i]);
-	if (eth->scratch_ring) {
+	if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) {
 		dma_free_coherent(eth->dma_dev,
 				  MTK_QDMA_RING_SIZE * soc->txrx.txd_size,
 				  eth->scratch_ring, eth->phy_scratch_ring);
@@ -3081,13 +3105,13 @@ static void mtk_dma_free(struct mtk_eth *eth)
 		eth->phy_scratch_ring = 0;
 	}
 	mtk_tx_clean(eth);
-	mtk_rx_clean(eth, &eth->rx_ring[0]);
-	mtk_rx_clean(eth, &eth->rx_ring_qdma);
+	mtk_rx_clean(eth, &eth->rx_ring[0], MTK_HAS_CAPS(soc->caps, MTK_SRAM));
+	mtk_rx_clean(eth, &eth->rx_ring_qdma, false);
 
 	if (eth->hwlro) {
 		mtk_hwlro_rx_uninit(eth);
 		for (i = 1; i < MTK_MAX_RX_RING_NUM; i++)
-			mtk_rx_clean(eth, &eth->rx_ring[i]);
+			mtk_rx_clean(eth, &eth->rx_ring[i], false);
 	}
 
 	kfree(eth->scratch_head);
@@ -4676,7 +4700,7 @@ static int mtk_sgmii_init(struct mtk_eth *eth)
 
 static int mtk_probe(struct platform_device *pdev)
 {
-	struct resource *res = NULL;
+	struct resource *res = NULL, *res_sram;
 	struct device_node *mac_np;
 	struct mtk_eth *eth;
 	int err, i;
@@ -4696,6 +4720,20 @@ static int mtk_probe(struct platform_device *pdev)
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
 		eth->ip_align = NET_IP_ALIGN;
 
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM)) {
+		/* SRAM is actual memory and supports transparent access just like DRAM.
+		 * Hence we don't require __iomem being set and don't need to use accessor
+		 * functions to read from or write to SRAM.
+		 */
+		if (mtk_is_netsys_v3_or_greater(eth)) {
+			eth->sram_base = (void __force *)devm_platform_ioremap_resource(pdev, 1);
+			if (IS_ERR(eth->sram_base))
+				return PTR_ERR(eth->sram_base);
+		} else {
+			eth->sram_base = (void __force *)eth->base + MTK_ETH_SRAM_OFFSET;
+		}
+	}
+
 	spin_lock_init(&eth->page_lock);
 	spin_lock_init(&eth->tx_irq_lock);
 	spin_lock_init(&eth->rx_irq_lock);
@@ -4759,6 +4797,18 @@ static int mtk_probe(struct platform_device *pdev)
 			err = -EINVAL;
 			goto err_destroy_sgmii;
 		}
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM)) {
+			if (mtk_is_netsys_v3_or_greater(eth)) {
+				res_sram = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+				if (!res_sram) {
+					err = -EINVAL;
+					goto err_destroy_sgmii;
+				}
+				eth->phy_scratch_ring = res_sram->start;
+			} else {
+				eth->phy_scratch_ring = res->start + MTK_ETH_SRAM_OFFSET;
+			}
+		}
 	}
 
 	if (eth->soc->offload_version) {
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index cf9381a3d68b7..7e961fff94f35 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -139,6 +139,9 @@
 #define MTK_GDMA_MAC_ADRH(x)	({ typeof(x) _x = (x); (_x == MTK_GMAC3_ID) ?	\
 				   0x54C : 0x50C + (_x * 0x1000); })
 
+/* Internal SRAM offset */
+#define MTK_ETH_SRAM_OFFSET	0x40000
+
 /* FE global misc reg*/
 #define MTK_FE_GLO_MISC         0x124
 
@@ -938,6 +941,7 @@ enum mkt_eth_capabilities {
 	MTK_RSTCTRL_PPE1_BIT,
 	MTK_RSTCTRL_PPE2_BIT,
 	MTK_U3_COPHY_V2_BIT,
+	MTK_SRAM_BIT,
 
 	/* MUX BITS*/
 	MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT,
@@ -973,6 +977,7 @@ enum mkt_eth_capabilities {
 #define MTK_RSTCTRL_PPE1	BIT_ULL(MTK_RSTCTRL_PPE1_BIT)
 #define MTK_RSTCTRL_PPE2	BIT_ULL(MTK_RSTCTRL_PPE2_BIT)
 #define MTK_U3_COPHY_V2		BIT_ULL(MTK_U3_COPHY_V2_BIT)
+#define MTK_SRAM		BIT_ULL(MTK_SRAM_BIT)
 
 #define MTK_ETH_MUX_GDM1_TO_GMAC1_ESW		\
 	BIT_ULL(MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT)
@@ -1048,14 +1053,14 @@ enum mkt_eth_capabilities {
 #define MT7981_CAPS  (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | MTK_GMAC2_GEPHY | \
 		      MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \
 		      MTK_MUX_U3_GMAC2_TO_QPHY | MTK_U3_COPHY_V2 | \
-		      MTK_RSTCTRL_PPE1)
+		      MTK_RSTCTRL_PPE1 | MTK_SRAM)
 
 #define MT7986_CAPS  (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | \
 		      MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \
-		      MTK_RSTCTRL_PPE1)
+		      MTK_RSTCTRL_PPE1 | MTK_SRAM)
 
 #define MT7988_CAPS  (MTK_GDM1_ESW | MTK_QDMA | MTK_RSTCTRL_PPE1 | \
-		      MTK_RSTCTRL_PPE2)
+		      MTK_RSTCTRL_PPE2 | MTK_SRAM)
 
 struct mtk_tx_dma_desc_info {
 	dma_addr_t	addr;
@@ -1215,6 +1220,7 @@ struct mtk_eth {
 	struct device			*dev;
 	struct device			*dma_dev;
 	void __iomem			*base;
+	void				*sram_base;
 	spinlock_t			page_lock;
 	spinlock_t			tx_irq_lock;
 	spinlock_t			rx_irq_lock;
-- 
GitLab


From 2d75891ebc09ba9cf30697dfd54497ef0220308f Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 22 Aug 2023 17:33:12 +0100
Subject: [PATCH 1608/1806] net: ethernet: mtk_eth_soc: support 36-bit DMA
 addressing on MT7988

Systems having 4 GiB of RAM and more require DMA addressing beyond the
current 32-bit limit. Starting from MT7988 the hardware now supports
36-bit DMA addressing, let's use that new capability in the driver to
avoid running into swiotlb on systems with 4 GiB of RAM or more.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/95b919c98876c9e49761e44662e7c937479eecb8.1692721443.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 30 +++++++++++++++++++--
 drivers/net/ethernet/mediatek/mtk_eth_soc.h | 22 +++++++++++++--
 2 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index ec6a251a0f026..6ad42e3b488f7 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1328,6 +1328,10 @@ static void mtk_tx_set_dma_desc_v2(struct net_device *dev, void *txd,
 	data = TX_DMA_PLEN0(info->size);
 	if (info->last)
 		data |= TX_DMA_LS0;
+
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA))
+		data |= TX_DMA_PREP_ADDR64(info->addr);
+
 	WRITE_ONCE(desc->txd3, data);
 
 	 /* set forward port */
@@ -1997,6 +2001,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 	bool xdp_flush = false;
 	int idx;
 	struct sk_buff *skb;
+	u64 addr64 = 0;
 	u8 *data, *new_data;
 	struct mtk_rx_dma_v2 *rxd, trxd;
 	int done = 0, bytes = 0;
@@ -2112,7 +2117,10 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 				goto release_desc;
 			}
 
-			dma_unmap_single(eth->dma_dev, trxd.rxd1,
+			if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA))
+				addr64 = RX_DMA_GET_ADDR64(trxd.rxd2);
+
+			dma_unmap_single(eth->dma_dev, ((u64)trxd.rxd1 | addr64),
 					 ring->buf_size, DMA_FROM_DEVICE);
 
 			skb = build_skb(data, ring->frag_size);
@@ -2178,6 +2186,9 @@ release_desc:
 		else
 			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size);
 
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA))
+			rxd->rxd2 |= RX_DMA_PREP_ADDR64(dma_addr);
+
 		ring->calc_idx = idx;
 		done++;
 	}
@@ -2670,6 +2681,9 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 		else
 			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size);
 
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA))
+			rxd->rxd2 |= RX_DMA_PREP_ADDR64(dma_addr);
+
 		rxd->rxd3 = 0;
 		rxd->rxd4 = 0;
 		if (mtk_is_netsys_v2_or_greater(eth)) {
@@ -2716,6 +2730,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 
 static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring, bool in_sram)
 {
+	u64 addr64 = 0;
 	int i;
 
 	if (ring->data && ring->dma) {
@@ -2729,7 +2744,10 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring, bool in_
 			if (!rxd->rxd1)
 				continue;
 
-			dma_unmap_single(eth->dma_dev, rxd->rxd1,
+			if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA))
+				addr64 = RX_DMA_GET_ADDR64(rxd->rxd2);
+
+			dma_unmap_single(eth->dma_dev, ((u64)rxd->rxd1 | addr64),
 					 ring->buf_size, DMA_FROM_DEVICE);
 			mtk_rx_put_buff(ring, ring->data[i], false);
 		}
@@ -4734,6 +4752,14 @@ static int mtk_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36));
+		if (err) {
+			dev_err(&pdev->dev, "Wrong DMA config\n");
+			return -EINVAL;
+		}
+	}
+
 	spin_lock_init(&eth->page_lock);
 	spin_lock_init(&eth->tx_irq_lock);
 	spin_lock_init(&eth->rx_irq_lock);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 7e961fff94f35..403219d987eff 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -331,6 +331,14 @@
 #define TX_DMA_PLEN1(x)		((x) & eth->soc->txrx.dma_max_len)
 #define TX_DMA_SWC		BIT(14)
 #define TX_DMA_PQID		GENMASK(3, 0)
+#define TX_DMA_ADDR64_MASK	GENMASK(3, 0)
+#if IS_ENABLED(CONFIG_64BIT)
+# define TX_DMA_GET_ADDR64(x)	(((u64)FIELD_GET(TX_DMA_ADDR64_MASK, (x))) << 32)
+# define TX_DMA_PREP_ADDR64(x)	FIELD_PREP(TX_DMA_ADDR64_MASK, ((x) >> 32))
+#else
+# define TX_DMA_GET_ADDR64(x)	(0)
+# define TX_DMA_PREP_ADDR64(x)	(0)
+#endif
 
 /* PDMA on MT7628 */
 #define TX_DMA_DONE		BIT(31)
@@ -343,6 +351,14 @@
 #define RX_DMA_PREP_PLEN0(x)	(((x) & eth->soc->txrx.dma_max_len) << eth->soc->txrx.dma_len_offset)
 #define RX_DMA_GET_PLEN0(x)	(((x) >> eth->soc->txrx.dma_len_offset) & eth->soc->txrx.dma_max_len)
 #define RX_DMA_VTAG		BIT(15)
+#define RX_DMA_ADDR64_MASK	GENMASK(3, 0)
+#if IS_ENABLED(CONFIG_64BIT)
+# define RX_DMA_GET_ADDR64(x)	(((u64)FIELD_GET(RX_DMA_ADDR64_MASK, (x))) << 32)
+# define RX_DMA_PREP_ADDR64(x)	FIELD_PREP(RX_DMA_ADDR64_MASK, ((x) >> 32))
+#else
+# define RX_DMA_GET_ADDR64(x)	(0)
+# define RX_DMA_PREP_ADDR64(x)	(0)
+#endif
 
 /* QDMA descriptor rxd3 */
 #define RX_DMA_VID(x)		((x) & VLAN_VID_MASK)
@@ -942,6 +958,7 @@ enum mkt_eth_capabilities {
 	MTK_RSTCTRL_PPE2_BIT,
 	MTK_U3_COPHY_V2_BIT,
 	MTK_SRAM_BIT,
+	MTK_36BIT_DMA_BIT,
 
 	/* MUX BITS*/
 	MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT,
@@ -978,6 +995,7 @@ enum mkt_eth_capabilities {
 #define MTK_RSTCTRL_PPE2	BIT_ULL(MTK_RSTCTRL_PPE2_BIT)
 #define MTK_U3_COPHY_V2		BIT_ULL(MTK_U3_COPHY_V2_BIT)
 #define MTK_SRAM		BIT_ULL(MTK_SRAM_BIT)
+#define MTK_36BIT_DMA	BIT_ULL(MTK_36BIT_DMA_BIT)
 
 #define MTK_ETH_MUX_GDM1_TO_GMAC1_ESW		\
 	BIT_ULL(MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT)
@@ -1059,8 +1077,8 @@ enum mkt_eth_capabilities {
 		      MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \
 		      MTK_RSTCTRL_PPE1 | MTK_SRAM)
 
-#define MT7988_CAPS  (MTK_GDM1_ESW | MTK_QDMA | MTK_RSTCTRL_PPE1 | \
-		      MTK_RSTCTRL_PPE2 | MTK_SRAM)
+#define MT7988_CAPS  (MTK_36BIT_DMA | MTK_GDM1_ESW | MTK_QDMA | \
+		      MTK_RSTCTRL_PPE1 | MTK_RSTCTRL_PPE2 | MTK_SRAM)
 
 struct mtk_tx_dma_desc_info {
 	dma_addr_t	addr;
-- 
GitLab


From a182e64147f7db006691c181077e456321f23bff Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 23 Aug 2023 17:00:15 -0700
Subject: [PATCH 1609/1806] selftests/bpf: add uprobe_multi test binary to
 .gitignore

It seems like it was forgotten to add uprobe_multi binary to .gitignore.
Fix this trivial omission.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230824000016.2658017-1-andrii@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/.gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 110518ba48042..f1aebabfb0176 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -44,6 +44,7 @@ test_cpp
 /bench
 /veristat
 /sign-file
+/uprobe_multi
 *.ko
 *.tmp
 xskxceiver
-- 
GitLab


From f3bdb54f09ab4cdbca48bf7befa8997cadd8d6a1 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 23 Aug 2023 17:00:16 -0700
Subject: [PATCH 1610/1806] libbpf: fix signedness determination in CO-RE relo
 handling logic

Extracting btf_int_encoding() is only meaningful for BTF_KIND_INT, so we
need to check that first before inferring signedness.

Closes: https://github.com/libbpf/libbpf/issues/704
Reported-by: Lorenz Bauer <lmb@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230824000016.2658017-2-andrii@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/lib/bpf/relo_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
index a26b2f5fa0fc9..63a4d5ad12d1a 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -776,7 +776,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 		break;
 	case BPF_CORE_FIELD_SIGNED:
 		*val = (btf_is_any_enum(mt) && BTF_INFO_KFLAG(mt->info)) ||
-		       (btf_int_encoding(mt) & BTF_INT_SIGNED);
+		       (btf_is_int(mt) && (btf_int_encoding(mt) & BTF_INT_SIGNED));
 		if (validate)
 			*validate = true; /* signedness is never ambiguous */
 		break;
-- 
GitLab


From 8da1985ff75226fd758ef379f9dd98986c811704 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 23 Aug 2023 18:32:25 +0800
Subject: [PATCH 1611/1806] wifi: mac80211: Do not include crypto/algapi.h

The header file crypto/algapi.h is for internal use only.  Use the
header file crypto/utils.h instead.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Link: https://lore.kernel.org/r/E1qYlA0-006vFr-Ts@formenos.hmeau.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/fils_aead.c | 2 +-
 net/mac80211/key.c       | 2 +-
 net/mac80211/wpa.c       | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/fils_aead.c b/net/mac80211/fils_aead.c
index e1d4cfd991285..912c46f74d244 100644
--- a/net/mac80211/fils_aead.c
+++ b/net/mac80211/fils_aead.c
@@ -5,9 +5,9 @@
  */
 
 #include <crypto/aes.h>
-#include <crypto/algapi.h>
 #include <crypto/hash.h>
 #include <crypto/skcipher.h>
+#include <crypto/utils.h>
 
 #include "ieee80211_i.h"
 #include "aes_cmac.h"
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 21cf5a2089101..13050dc9321f1 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -9,6 +9,7 @@
  * Copyright 2018-2020, 2022-2023  Intel Corporation
  */
 
+#include <crypto/utils.h>
 #include <linux/if_ether.h>
 #include <linux/etherdevice.h>
 #include <linux/list.h>
@@ -17,7 +18,6 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <net/mac80211.h>
-#include <crypto/algapi.h>
 #include <asm/unaligned.h>
 #include "ieee80211_i.h"
 #include "driver-ops.h"
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 4133496da3789..2d8e38b3bcb50 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -15,7 +15,7 @@
 #include <asm/unaligned.h>
 #include <net/mac80211.h>
 #include <crypto/aes.h>
-#include <crypto/algapi.h>
+#include <crypto/utils.h>
 
 #include "ieee80211_i.h"
 #include "michael.h"
-- 
GitLab


From 393dc4bd92de3711012d791a93072c8cc94c4c57 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Wed, 23 Aug 2023 23:34:17 -0700
Subject: [PATCH 1612/1806] bpf: Remove a WARN_ON_ONCE warning related to local
 kptr

Currently, in function bpf_obj_free_fields(), for local kptr,
a warning will be issued if the struct does not contain any
special fields. But actually the kernel seems totally okay
with a local kptr without any special fields. Permitting
no special fields also aligns with future percpu kptr which
also allows no special fields.

Acked-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230824063417.201925-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/syscall.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 10666d17b9e3b..ebeb0695305a7 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -657,7 +657,6 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
 			if (!btf_is_kernel(field->kptr.btf)) {
 				pointee_struct_meta = btf_find_struct_meta(field->kptr.btf,
 									   field->kptr.btf_id);
-				WARN_ON_ONCE(!pointee_struct_meta);
 				migrate_disable();
 				__bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ?
 								 pointee_struct_meta->record :
-- 
GitLab


From 001fedacc907d641f7cfb89eb19c5d0535998662 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Wed, 23 Aug 2023 23:34:22 -0700
Subject: [PATCH 1613/1806] selftests/bpf: Add a local kptr test with no
 special fields

Add a local kptr test with no special fields in the struct. Without the
previous patch, the following warning will hit:

  [   44.683877] WARNING: CPU: 3 PID: 485 at kernel/bpf/syscall.c:660 bpf_obj_free_fields+0x220/0x240
  [   44.684640] Modules linked in: bpf_testmod(OE)
  [   44.685044] CPU: 3 PID: 485 Comm: kworker/u8:5 Tainted: G           OE      6.5.0-rc5-01703-g260d855e9b90 #248
  [   44.685827] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
  [   44.686693] Workqueue: events_unbound bpf_map_free_deferred
  [   44.687297] RIP: 0010:bpf_obj_free_fields+0x220/0x240
  [   44.687775] Code: e8 55 17 1f 00 49 8b 74 24 08 4c 89 ef e8 e8 14 05 00 e8 a3 da e2 ff e9 55 fe ff ff 0f 0b e9 4e fe ff
                       ff 0f 0b e9 47 fe ff ff <0f> 0b e8 d9 d9 e2 ff 31 f6 eb d5 48 83 c4 10 5b 41 5c e
  [   44.689353] RSP: 0018:ffff888106467cb8 EFLAGS: 00010246
  [   44.689806] RAX: 0000000000000000 RBX: ffff888112b3a200 RCX: 0000000000000001
  [   44.690433] RDX: 0000000000000000 RSI: dffffc0000000000 RDI: ffff8881128ad988
  [   44.691094] RBP: 0000000000000002 R08: ffffffff81370bd0 R09: 1ffff110216231a5
  [   44.691643] R10: dffffc0000000000 R11: ffffed10216231a6 R12: ffff88810d68a488
  [   44.692245] R13: ffff88810767c288 R14: ffff88810d68a400 R15: ffff88810d68a418
  [   44.692829] FS:  0000000000000000(0000) GS:ffff8881f7580000(0000) knlGS:0000000000000000
  [   44.693484] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  [   44.693964] CR2: 000055c7f2afce28 CR3: 000000010fee4002 CR4: 0000000000370ee0
  [   44.694513] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  [   44.695102] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  [   44.695747] Call Trace:
  [   44.696001]  <TASK>
  [   44.696183]  ? __warn+0xfe/0x270
  [   44.696447]  ? bpf_obj_free_fields+0x220/0x240
  [   44.696817]  ? report_bug+0x220/0x2d0
  [   44.697180]  ? handle_bug+0x3d/0x70
  [   44.697507]  ? exc_invalid_op+0x1a/0x50
  [   44.697887]  ? asm_exc_invalid_op+0x1a/0x20
  [   44.698282]  ? btf_find_struct_meta+0xd0/0xd0
  [   44.698634]  ? bpf_obj_free_fields+0x220/0x240
  [   44.699027]  ? bpf_obj_free_fields+0x1e2/0x240
  [   44.699414]  array_map_free+0x1a3/0x260
  [   44.699763]  bpf_map_free_deferred+0x7b/0xe0
  [   44.700154]  process_one_work+0x46d/0x750
  [   44.700523]  worker_thread+0x49e/0x900
  [   44.700892]  ? pr_cont_work+0x270/0x270
  [   44.701224]  kthread+0x1ae/0x1d0
  [   44.701516]  ? kthread_blkcg+0x50/0x50
  [   44.701860]  ret_from_fork+0x34/0x50
  [   44.702178]  ? kthread_blkcg+0x50/0x50
  [   44.702508]  ret_from_fork_asm+0x11/0x20
  [   44.702880]  </TASK>

With the previous patch, there is no warnings.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230824063422.203097-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/local_kptr_stash.c         | 23 +++++++++++++++
 .../selftests/bpf/progs/local_kptr_stash.c    | 28 +++++++++++++++++++
 2 files changed, 51 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
index 158616c946582..b25b870f87ba9 100644
--- a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
+++ b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
@@ -27,6 +27,27 @@ static void test_local_kptr_stash_simple(void)
 	local_kptr_stash__destroy(skel);
 }
 
+static void test_local_kptr_stash_plain(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct local_kptr_stash *skel;
+	int ret;
+
+	skel = local_kptr_stash__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_plain), &opts);
+	ASSERT_OK(ret, "local_kptr_stash_add_plain run");
+	ASSERT_OK(opts.retval, "local_kptr_stash_add_plain retval");
+
+	local_kptr_stash__destroy(skel);
+}
+
 static void test_local_kptr_stash_unstash(void)
 {
 	LIBBPF_OPTS(bpf_test_run_opts, opts,
@@ -61,6 +82,8 @@ void test_local_kptr_stash(void)
 {
 	if (test__start_subtest("local_kptr_stash_simple"))
 		test_local_kptr_stash_simple();
+	if (test__start_subtest("local_kptr_stash_plain"))
+		test_local_kptr_stash_plain();
 	if (test__start_subtest("local_kptr_stash_unstash"))
 		test_local_kptr_stash_unstash();
 	if (test__start_subtest("local_kptr_stash_fail"))
diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c
index 06838083079c1..b567a666d2b87 100644
--- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c
+++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c
@@ -14,10 +14,16 @@ struct node_data {
 	struct bpf_rb_node node;
 };
 
+struct plain_local {
+	long key;
+	long data;
+};
+
 struct map_value {
 	struct prog_test_ref_kfunc *not_kptr;
 	struct prog_test_ref_kfunc __kptr *val;
 	struct node_data __kptr *node;
+	struct plain_local __kptr *plain;
 };
 
 /* This is necessary so that LLVM generates BTF for node_data struct
@@ -66,6 +72,28 @@ long stash_rb_nodes(void *ctx)
 	return create_and_stash(0, 41) ?: create_and_stash(1, 42);
 }
 
+SEC("tc")
+long stash_plain(void *ctx)
+{
+	struct map_value *mapval;
+	struct plain_local *res;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	res = bpf_obj_new(typeof(*res));
+	if (!res)
+		return 1;
+	res->key = 41;
+
+	res = bpf_kptr_xchg(&mapval->plain, res);
+	if (res)
+		bpf_obj_drop(res);
+	return 0;
+}
+
 SEC("tc")
 long unstash_rb_node(void *ctx)
 {
-- 
GitLab


From e7c9e73d082252ecd026f7e01d8015a347c375c1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 24 Aug 2023 12:22:44 +0200
Subject: [PATCH 1614/1806] samples/bpf: Remove the xdp_monitor utility
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This utility has been ported as-is to xdp-tools as 'xdp-monitor'. The only
difference in usage between the samples and xdp-tools versions is that the
'-v' command line parameter has been changed to '-e' in the xdp-tools
version for consistency with the other utilities.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20230824102255.1561885-2-toke@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile           |   8 +--
 samples/bpf/xdp_monitor.bpf.c  |   8 ---
 samples/bpf/xdp_monitor_user.c | 118 ---------------------------------
 3 files changed, 1 insertion(+), 133 deletions(-)
 delete mode 100644 samples/bpf/xdp_monitor.bpf.c
 delete mode 100644 samples/bpf/xdp_monitor_user.c

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index f90bcd3696bdf..29b07c4ec066a 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -55,7 +55,6 @@ tprogs-y += xdp_redirect_cpu
 tprogs-y += xdp_redirect_map_multi
 tprogs-y += xdp_redirect_map
 tprogs-y += xdp_redirect
-tprogs-y += xdp_monitor
 
 # Libbpf dependencies
 LIBBPF_SRC = $(TOOLS_PATH)/lib/bpf
@@ -116,7 +115,6 @@ xdp_redirect_map_multi-objs := xdp_redirect_map_multi_user.o $(XDP_SAMPLE)
 xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o $(XDP_SAMPLE)
 xdp_redirect_map-objs := xdp_redirect_map_user.o $(XDP_SAMPLE)
 xdp_redirect-objs := xdp_redirect_user.o $(XDP_SAMPLE)
-xdp_monitor-objs := xdp_monitor_user.o $(XDP_SAMPLE)
 xdp_router_ipv4-objs := xdp_router_ipv4_user.o $(XDP_SAMPLE)
 
 # Tell kbuild to always build the programs
@@ -207,7 +205,6 @@ TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib
 endif
 
 TPROGS_LDLIBS			+= $(LIBBPF) -lelf -lz
-TPROGLDLIBS_xdp_monitor		+= -lm
 TPROGLDLIBS_xdp_redirect	+= -lm
 TPROGLDLIBS_xdp_redirect_cpu	+= -lm
 TPROGLDLIBS_xdp_redirect_map	+= -lm
@@ -330,7 +327,6 @@ $(obj)/xdp_redirect_cpu_user.o: $(obj)/xdp_redirect_cpu.skel.h
 $(obj)/xdp_redirect_map_multi_user.o: $(obj)/xdp_redirect_map_multi.skel.h
 $(obj)/xdp_redirect_map_user.o: $(obj)/xdp_redirect_map.skel.h
 $(obj)/xdp_redirect_user.o: $(obj)/xdp_redirect.skel.h
-$(obj)/xdp_monitor_user.o: $(obj)/xdp_monitor.skel.h
 $(obj)/xdp_router_ipv4_user.o: $(obj)/xdp_router_ipv4.skel.h
 
 $(obj)/tracex5.bpf.o: $(obj)/syscall_nrs.h
@@ -387,7 +383,6 @@ $(obj)/xdp_redirect_cpu.bpf.o: $(obj)/xdp_sample.bpf.o
 $(obj)/xdp_redirect_map_multi.bpf.o: $(obj)/xdp_sample.bpf.o
 $(obj)/xdp_redirect_map.bpf.o: $(obj)/xdp_sample.bpf.o
 $(obj)/xdp_redirect.bpf.o: $(obj)/xdp_sample.bpf.o
-$(obj)/xdp_monitor.bpf.o: $(obj)/xdp_sample.bpf.o
 $(obj)/xdp_router_ipv4.bpf.o: $(obj)/xdp_sample.bpf.o
 
 $(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/xdp_sample_shared.h
@@ -399,7 +394,7 @@ $(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/x
 		-c $(filter %.bpf.c,$^) -o $@
 
 LINKED_SKELS := xdp_redirect_cpu.skel.h xdp_redirect_map_multi.skel.h \
-		xdp_redirect_map.skel.h xdp_redirect.skel.h xdp_monitor.skel.h \
+		xdp_redirect_map.skel.h xdp_redirect.skel.h \
 		xdp_router_ipv4.skel.h
 clean-files += $(LINKED_SKELS)
 
@@ -407,7 +402,6 @@ xdp_redirect_cpu.skel.h-deps := xdp_redirect_cpu.bpf.o xdp_sample.bpf.o
 xdp_redirect_map_multi.skel.h-deps := xdp_redirect_map_multi.bpf.o xdp_sample.bpf.o
 xdp_redirect_map.skel.h-deps := xdp_redirect_map.bpf.o xdp_sample.bpf.o
 xdp_redirect.skel.h-deps := xdp_redirect.bpf.o xdp_sample.bpf.o
-xdp_monitor.skel.h-deps := xdp_monitor.bpf.o xdp_sample.bpf.o
 xdp_router_ipv4.skel.h-deps := xdp_router_ipv4.bpf.o xdp_sample.bpf.o
 
 LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.bpf.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
diff --git a/samples/bpf/xdp_monitor.bpf.c b/samples/bpf/xdp_monitor.bpf.c
deleted file mode 100644
index cfb41e2205f46..0000000000000
--- a/samples/bpf/xdp_monitor.bpf.c
+++ /dev/null
@@ -1,8 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*  Copyright(c) 2017-2018 Jesper Dangaard Brouer, Red Hat Inc.
- *
- * XDP monitor tool, based on tracepoints
- */
-#include "xdp_sample.bpf.h"
-
-char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c
deleted file mode 100644
index 58015eb2ffaee..0000000000000
--- a/samples/bpf/xdp_monitor_user.c
+++ /dev/null
@@ -1,118 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. */
-static const char *__doc__=
-"XDP monitor tool, based on tracepoints\n";
-
-static const char *__doc_err_only__=
-" NOTICE: Only tracking XDP redirect errors\n"
-"         Enable redirect success stats via '-s/--stats'\n"
-"         (which comes with a per packet processing overhead)\n";
-
-#include <errno.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <stdbool.h>
-#include <stdint.h>
-#include <string.h>
-#include <ctype.h>
-#include <unistd.h>
-#include <locale.h>
-#include <getopt.h>
-#include <net/if.h>
-#include <time.h>
-#include <signal.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-#include "bpf_util.h"
-#include "xdp_sample_user.h"
-#include "xdp_monitor.skel.h"
-
-static int mask = SAMPLE_REDIRECT_ERR_CNT | SAMPLE_CPUMAP_ENQUEUE_CNT |
-		  SAMPLE_CPUMAP_KTHREAD_CNT | SAMPLE_EXCEPTION_CNT |
-		  SAMPLE_DEVMAP_XMIT_CNT | SAMPLE_DEVMAP_XMIT_CNT_MULTI;
-
-DEFINE_SAMPLE_INIT(xdp_monitor);
-
-static const struct option long_options[] = {
-	{ "help", no_argument, NULL, 'h' },
-	{ "stats", no_argument, NULL, 's' },
-	{ "interval", required_argument, NULL, 'i' },
-	{ "verbose", no_argument, NULL, 'v' },
-	{}
-};
-
-int main(int argc, char **argv)
-{
-	unsigned long interval = 2;
-	int ret = EXIT_FAIL_OPTION;
-	struct xdp_monitor *skel;
-	bool errors_only = true;
-	int longindex = 0, opt;
-	bool error = true;
-
-	/* Parse commands line args */
-	while ((opt = getopt_long(argc, argv, "si:vh",
-				  long_options, &longindex)) != -1) {
-		switch (opt) {
-		case 's':
-			errors_only = false;
-			mask |= SAMPLE_REDIRECT_CNT;
-			break;
-		case 'i':
-			interval = strtoul(optarg, NULL, 0);
-			break;
-		case 'v':
-			sample_switch_mode();
-			break;
-		case 'h':
-			error = false;
-		default:
-			sample_usage(argv, long_options, __doc__, mask, error);
-			return ret;
-		}
-	}
-
-	skel = xdp_monitor__open();
-	if (!skel) {
-		fprintf(stderr, "Failed to xdp_monitor__open: %s\n",
-			strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end;
-	}
-
-	ret = sample_init_pre_load(skel);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	ret = xdp_monitor__load(skel);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to xdp_monitor__load: %s\n", strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	ret = sample_init(skel, mask);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	if (errors_only)
-		printf("%s", __doc_err_only__);
-
-	ret = sample_run(interval, NULL, NULL);
-	if (ret < 0) {
-		fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
-		ret = EXIT_FAIL;
-		goto end_destroy;
-	}
-	ret = EXIT_OK;
-end_destroy:
-	xdp_monitor__destroy(skel);
-end:
-	sample_exit(ret);
-}
-- 
GitLab


From 91dda69b08de93465632561701a337ec18321ea4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 24 Aug 2023 12:22:45 +0200
Subject: [PATCH 1615/1806] samples/bpf: Remove the xdp_redirect* utilities
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These utilities have all been ported to xdp-tools as functions of the
xdp-bench utility. The four different utilities in samples are incorporated
as separate subcommands to xdp-bench, with most of the command line
parameters left intact, except that mandatory arguments are always
positional in xdp-bench. For full usage details see the --help output of
each command, or the xdp-bench man page.

Some examples of how to convert usage to xdp-bench are:

xdp_redirect eth0 eth1
  --> xdp-bench redirect eth0 eth1

xdp_redirect_map eth0 eth1
  --> xdp-bench redirect-map eth0 eth1

xdp_redirect_map_multi eth0 eth1 eth2 eth3
  --> xdp-bench redirect-multi eth0 eth1 eth2 eth3

xdp_redirect_cpu -d eth0 -c 0 -c 1
  --> xdp-bench redirect-cpu -c 0 -c 1 eth0

xdp_redirect_cpu -d eth0 -c 0 -c 1 -r eth1
  --> xdp-bench redirect-cpu -c 0 -c 1 eth0 -r redirect -D eth1

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20230824102255.1561885-3-toke@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile                      |  29 +-
 samples/bpf/xdp_redirect.bpf.c            |  49 --
 samples/bpf/xdp_redirect_cpu.bpf.c        | 539 ---------------------
 samples/bpf/xdp_redirect_cpu_user.c       | 559 ----------------------
 samples/bpf/xdp_redirect_map.bpf.c        |  97 ----
 samples/bpf/xdp_redirect_map_multi.bpf.c  |  77 ---
 samples/bpf/xdp_redirect_map_multi_user.c | 232 ---------
 samples/bpf/xdp_redirect_map_user.c       | 228 ---------
 samples/bpf/xdp_redirect_user.c           | 172 -------
 9 files changed, 1 insertion(+), 1981 deletions(-)
 delete mode 100644 samples/bpf/xdp_redirect.bpf.c
 delete mode 100644 samples/bpf/xdp_redirect_cpu.bpf.c
 delete mode 100644 samples/bpf/xdp_redirect_cpu_user.c
 delete mode 100644 samples/bpf/xdp_redirect_map.bpf.c
 delete mode 100644 samples/bpf/xdp_redirect_map_multi.bpf.c
 delete mode 100644 samples/bpf/xdp_redirect_map_multi_user.c
 delete mode 100644 samples/bpf/xdp_redirect_map_user.c
 delete mode 100644 samples/bpf/xdp_redirect_user.c

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 29b07c4ec066a..d2f5c043e4f37 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -51,11 +51,6 @@ tprogs-y += xdp_sample_pkts
 tprogs-y += ibumad
 tprogs-y += hbm
 
-tprogs-y += xdp_redirect_cpu
-tprogs-y += xdp_redirect_map_multi
-tprogs-y += xdp_redirect_map
-tprogs-y += xdp_redirect
-
 # Libbpf dependencies
 LIBBPF_SRC = $(TOOLS_PATH)/lib/bpf
 LIBBPF_OUTPUT = $(abspath $(BPF_SAMPLES_PATH))/libbpf
@@ -111,10 +106,6 @@ xdp_sample_pkts-objs := xdp_sample_pkts_user.o
 ibumad-objs := ibumad_user.o
 hbm-objs := hbm.o $(CGROUP_HELPERS)
 
-xdp_redirect_map_multi-objs := xdp_redirect_map_multi_user.o $(XDP_SAMPLE)
-xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o $(XDP_SAMPLE)
-xdp_redirect_map-objs := xdp_redirect_map_user.o $(XDP_SAMPLE)
-xdp_redirect-objs := xdp_redirect_user.o $(XDP_SAMPLE)
 xdp_router_ipv4-objs := xdp_router_ipv4_user.o $(XDP_SAMPLE)
 
 # Tell kbuild to always build the programs
@@ -205,10 +196,6 @@ TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib
 endif
 
 TPROGS_LDLIBS			+= $(LIBBPF) -lelf -lz
-TPROGLDLIBS_xdp_redirect	+= -lm
-TPROGLDLIBS_xdp_redirect_cpu	+= -lm
-TPROGLDLIBS_xdp_redirect_map	+= -lm
-TPROGLDLIBS_xdp_redirect_map_multi += -lm
 TPROGLDLIBS_xdp_router_ipv4	+= -lm -pthread
 TPROGLDLIBS_tracex4		+= -lrt
 TPROGLDLIBS_trace_output	+= -lrt
@@ -323,10 +310,6 @@ $(obj)/$(TRACE_HELPERS) $(obj)/$(CGROUP_HELPERS) $(obj)/$(XDP_SAMPLE): | libbpf_
 
 .PHONY: libbpf_hdrs
 
-$(obj)/xdp_redirect_cpu_user.o: $(obj)/xdp_redirect_cpu.skel.h
-$(obj)/xdp_redirect_map_multi_user.o: $(obj)/xdp_redirect_map_multi.skel.h
-$(obj)/xdp_redirect_map_user.o: $(obj)/xdp_redirect_map.skel.h
-$(obj)/xdp_redirect_user.o: $(obj)/xdp_redirect.skel.h
 $(obj)/xdp_router_ipv4_user.o: $(obj)/xdp_router_ipv4.skel.h
 
 $(obj)/tracex5.bpf.o: $(obj)/syscall_nrs.h
@@ -379,10 +362,6 @@ endef
 
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
 
-$(obj)/xdp_redirect_cpu.bpf.o: $(obj)/xdp_sample.bpf.o
-$(obj)/xdp_redirect_map_multi.bpf.o: $(obj)/xdp_sample.bpf.o
-$(obj)/xdp_redirect_map.bpf.o: $(obj)/xdp_sample.bpf.o
-$(obj)/xdp_redirect.bpf.o: $(obj)/xdp_sample.bpf.o
 $(obj)/xdp_router_ipv4.bpf.o: $(obj)/xdp_sample.bpf.o
 
 $(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/xdp_sample_shared.h
@@ -393,15 +372,9 @@ $(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/x
 		-I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \
 		-c $(filter %.bpf.c,$^) -o $@
 
-LINKED_SKELS := xdp_redirect_cpu.skel.h xdp_redirect_map_multi.skel.h \
-		xdp_redirect_map.skel.h xdp_redirect.skel.h \
-		xdp_router_ipv4.skel.h
+LINKED_SKELS := xdp_router_ipv4.skel.h
 clean-files += $(LINKED_SKELS)
 
-xdp_redirect_cpu.skel.h-deps := xdp_redirect_cpu.bpf.o xdp_sample.bpf.o
-xdp_redirect_map_multi.skel.h-deps := xdp_redirect_map_multi.bpf.o xdp_sample.bpf.o
-xdp_redirect_map.skel.h-deps := xdp_redirect_map.bpf.o xdp_sample.bpf.o
-xdp_redirect.skel.h-deps := xdp_redirect.bpf.o xdp_sample.bpf.o
 xdp_router_ipv4.skel.h-deps := xdp_router_ipv4.bpf.o xdp_sample.bpf.o
 
 LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.bpf.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
diff --git a/samples/bpf/xdp_redirect.bpf.c b/samples/bpf/xdp_redirect.bpf.c
deleted file mode 100644
index 7c02bacfe96b5..0000000000000
--- a/samples/bpf/xdp_redirect.bpf.c
+++ /dev/null
@@ -1,49 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2016 John Fastabend <john.r.fastabend@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- */
-#include "vmlinux.h"
-#include "xdp_sample.bpf.h"
-#include "xdp_sample_shared.h"
-
-const volatile int ifindex_out;
-
-SEC("xdp")
-int xdp_redirect_prog(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data = (void *)(long)ctx->data;
-	u32 key = bpf_get_smp_processor_id();
-	struct ethhdr *eth = data;
-	struct datarec *rec;
-	u64 nh_off;
-
-	nh_off = sizeof(*eth);
-	if (data + nh_off > data_end)
-		return XDP_DROP;
-
-	rec = bpf_map_lookup_elem(&rx_cnt, &key);
-	if (!rec)
-		return XDP_PASS;
-	NO_TEAR_INC(rec->processed);
-
-	swap_src_dst_mac(data);
-	return bpf_redirect(ifindex_out, 0);
-}
-
-/* Redirect require an XDP bpf_prog loaded on the TX device */
-SEC("xdp")
-int xdp_redirect_dummy_prog(struct xdp_md *ctx)
-{
-	return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_redirect_cpu.bpf.c b/samples/bpf/xdp_redirect_cpu.bpf.c
deleted file mode 100644
index 87c54bfdbb70d..0000000000000
--- a/samples/bpf/xdp_redirect_cpu.bpf.c
+++ /dev/null
@@ -1,539 +0,0 @@
-/*  XDP redirect to CPUs via cpumap (BPF_MAP_TYPE_CPUMAP)
- *
- *  GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
- */
-#include "vmlinux.h"
-#include "xdp_sample.bpf.h"
-#include "xdp_sample_shared.h"
-#include "hash_func01.h"
-
-/* Special map type that can XDP_REDIRECT frames to another CPU */
-struct {
-	__uint(type, BPF_MAP_TYPE_CPUMAP);
-	__uint(key_size, sizeof(u32));
-	__uint(value_size, sizeof(struct bpf_cpumap_val));
-} cpu_map SEC(".maps");
-
-/* Set of maps controlling available CPU, and for iterating through
- * selectable redirect CPUs.
- */
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__type(key, u32);
-	__type(value, u32);
-} cpus_available SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__type(key, u32);
-	__type(value, u32);
-	__uint(max_entries, 1);
-} cpus_count SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, u32);
-	__uint(max_entries, 1);
-} cpus_iterator SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_DEVMAP);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(struct bpf_devmap_val));
-	__uint(max_entries, 1);
-} tx_port SEC(".maps");
-
-char tx_mac_addr[ETH_ALEN];
-
-/* Helper parse functions */
-
-static __always_inline
-bool parse_eth(struct ethhdr *eth, void *data_end,
-	       u16 *eth_proto, u64 *l3_offset)
-{
-	u16 eth_type;
-	u64 offset;
-
-	offset = sizeof(*eth);
-	if ((void *)eth + offset > data_end)
-		return false;
-
-	eth_type = eth->h_proto;
-
-	/* Skip non 802.3 Ethertypes */
-	if (__builtin_expect(bpf_ntohs(eth_type) < ETH_P_802_3_MIN, 0))
-		return false;
-
-	/* Handle VLAN tagged packet */
-	if (eth_type == bpf_htons(ETH_P_8021Q) ||
-	    eth_type == bpf_htons(ETH_P_8021AD)) {
-		struct vlan_hdr *vlan_hdr;
-
-		vlan_hdr = (void *)eth + offset;
-		offset += sizeof(*vlan_hdr);
-		if ((void *)eth + offset > data_end)
-			return false;
-		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
-	}
-	/* Handle double VLAN tagged packet */
-	if (eth_type == bpf_htons(ETH_P_8021Q) ||
-	    eth_type == bpf_htons(ETH_P_8021AD)) {
-		struct vlan_hdr *vlan_hdr;
-
-		vlan_hdr = (void *)eth + offset;
-		offset += sizeof(*vlan_hdr);
-		if ((void *)eth + offset > data_end)
-			return false;
-		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
-	}
-
-	*eth_proto = bpf_ntohs(eth_type);
-	*l3_offset = offset;
-	return true;
-}
-
-static __always_inline
-u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	struct iphdr *iph = data + nh_off;
-	struct udphdr *udph;
-
-	if (iph + 1 > data_end)
-		return 0;
-	if (!(iph->protocol == IPPROTO_UDP))
-		return 0;
-
-	udph = (void *)(iph + 1);
-	if (udph + 1 > data_end)
-		return 0;
-
-	return bpf_ntohs(udph->dest);
-}
-
-static __always_inline
-int get_proto_ipv4(struct xdp_md *ctx, u64 nh_off)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	struct iphdr *iph = data + nh_off;
-
-	if (iph + 1 > data_end)
-		return 0;
-	return iph->protocol;
-}
-
-static __always_inline
-int get_proto_ipv6(struct xdp_md *ctx, u64 nh_off)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	struct ipv6hdr *ip6h = data + nh_off;
-
-	if (ip6h + 1 > data_end)
-		return 0;
-	return ip6h->nexthdr;
-}
-
-SEC("xdp")
-int  xdp_prognum0_no_touch(struct xdp_md *ctx)
-{
-	u32 key = bpf_get_smp_processor_id();
-	struct datarec *rec;
-	u32 *cpu_selected;
-	u32 cpu_dest = 0;
-	u32 key0 = 0;
-
-	/* Only use first entry in cpus_available */
-	cpu_selected = bpf_map_lookup_elem(&cpus_available, &key0);
-	if (!cpu_selected)
-		return XDP_ABORTED;
-	cpu_dest = *cpu_selected;
-
-	rec = bpf_map_lookup_elem(&rx_cnt, &key);
-	if (!rec)
-		return XDP_PASS;
-	NO_TEAR_INC(rec->processed);
-
-	if (cpu_dest >= nr_cpus) {
-		NO_TEAR_INC(rec->issue);
-		return XDP_ABORTED;
-	}
-	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
-}
-
-SEC("xdp")
-int  xdp_prognum1_touch_data(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	u32 key = bpf_get_smp_processor_id();
-	struct ethhdr *eth = data;
-	struct datarec *rec;
-	u32 *cpu_selected;
-	u32 cpu_dest = 0;
-	u32 key0 = 0;
-	u16 eth_type;
-
-	/* Only use first entry in cpus_available */
-	cpu_selected = bpf_map_lookup_elem(&cpus_available, &key0);
-	if (!cpu_selected)
-		return XDP_ABORTED;
-	cpu_dest = *cpu_selected;
-
-	/* Validate packet length is minimum Eth header size */
-	if (eth + 1 > data_end)
-		return XDP_ABORTED;
-
-	rec = bpf_map_lookup_elem(&rx_cnt, &key);
-	if (!rec)
-		return XDP_PASS;
-	NO_TEAR_INC(rec->processed);
-
-	/* Read packet data, and use it (drop non 802.3 Ethertypes) */
-	eth_type = eth->h_proto;
-	if (bpf_ntohs(eth_type) < ETH_P_802_3_MIN) {
-		NO_TEAR_INC(rec->dropped);
-		return XDP_DROP;
-	}
-
-	if (cpu_dest >= nr_cpus) {
-		NO_TEAR_INC(rec->issue);
-		return XDP_ABORTED;
-	}
-	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
-}
-
-SEC("xdp")
-int  xdp_prognum2_round_robin(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	u32 key = bpf_get_smp_processor_id();
-	struct datarec *rec;
-	u32 cpu_dest = 0;
-	u32 key0 = 0;
-
-	u32 *cpu_selected;
-	u32 *cpu_iterator;
-	u32 *cpu_max;
-	u32 cpu_idx;
-
-	cpu_max = bpf_map_lookup_elem(&cpus_count, &key0);
-	if (!cpu_max)
-		return XDP_ABORTED;
-
-	cpu_iterator = bpf_map_lookup_elem(&cpus_iterator, &key0);
-	if (!cpu_iterator)
-		return XDP_ABORTED;
-	cpu_idx = *cpu_iterator;
-
-	*cpu_iterator += 1;
-	if (*cpu_iterator == *cpu_max)
-		*cpu_iterator = 0;
-
-	cpu_selected = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
-	if (!cpu_selected)
-		return XDP_ABORTED;
-	cpu_dest = *cpu_selected;
-
-	rec = bpf_map_lookup_elem(&rx_cnt, &key);
-	if (!rec)
-		return XDP_PASS;
-	NO_TEAR_INC(rec->processed);
-
-	if (cpu_dest >= nr_cpus) {
-		NO_TEAR_INC(rec->issue);
-		return XDP_ABORTED;
-	}
-	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
-}
-
-SEC("xdp")
-int  xdp_prognum3_proto_separate(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	u32 key = bpf_get_smp_processor_id();
-	struct ethhdr *eth = data;
-	u8 ip_proto = IPPROTO_UDP;
-	struct datarec *rec;
-	u16 eth_proto = 0;
-	u64 l3_offset = 0;
-	u32 cpu_dest = 0;
-	u32 *cpu_lookup;
-	u32 cpu_idx = 0;
-
-	rec = bpf_map_lookup_elem(&rx_cnt, &key);
-	if (!rec)
-		return XDP_PASS;
-	NO_TEAR_INC(rec->processed);
-
-	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
-		return XDP_PASS; /* Just skip */
-
-	/* Extract L4 protocol */
-	switch (eth_proto) {
-	case ETH_P_IP:
-		ip_proto = get_proto_ipv4(ctx, l3_offset);
-		break;
-	case ETH_P_IPV6:
-		ip_proto = get_proto_ipv6(ctx, l3_offset);
-		break;
-	case ETH_P_ARP:
-		cpu_idx = 0; /* ARP packet handled on separate CPU */
-		break;
-	default:
-		cpu_idx = 0;
-	}
-
-	/* Choose CPU based on L4 protocol */
-	switch (ip_proto) {
-	case IPPROTO_ICMP:
-	case IPPROTO_ICMPV6:
-		cpu_idx = 2;
-		break;
-	case IPPROTO_TCP:
-		cpu_idx = 0;
-		break;
-	case IPPROTO_UDP:
-		cpu_idx = 1;
-		break;
-	default:
-		cpu_idx = 0;
-	}
-
-	cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
-	if (!cpu_lookup)
-		return XDP_ABORTED;
-	cpu_dest = *cpu_lookup;
-
-	if (cpu_dest >= nr_cpus) {
-		NO_TEAR_INC(rec->issue);
-		return XDP_ABORTED;
-	}
-	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
-}
-
-SEC("xdp")
-int  xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	u32 key = bpf_get_smp_processor_id();
-	struct ethhdr *eth = data;
-	u8 ip_proto = IPPROTO_UDP;
-	struct datarec *rec;
-	u16 eth_proto = 0;
-	u64 l3_offset = 0;
-	u32 cpu_dest = 0;
-	u32 *cpu_lookup;
-	u32 cpu_idx = 0;
-	u16 dest_port;
-
-	rec = bpf_map_lookup_elem(&rx_cnt, &key);
-	if (!rec)
-		return XDP_PASS;
-	NO_TEAR_INC(rec->processed);
-
-	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
-		return XDP_PASS; /* Just skip */
-
-	/* Extract L4 protocol */
-	switch (eth_proto) {
-	case ETH_P_IP:
-		ip_proto = get_proto_ipv4(ctx, l3_offset);
-		break;
-	case ETH_P_IPV6:
-		ip_proto = get_proto_ipv6(ctx, l3_offset);
-		break;
-	case ETH_P_ARP:
-		cpu_idx = 0; /* ARP packet handled on separate CPU */
-		break;
-	default:
-		cpu_idx = 0;
-	}
-
-	/* Choose CPU based on L4 protocol */
-	switch (ip_proto) {
-	case IPPROTO_ICMP:
-	case IPPROTO_ICMPV6:
-		cpu_idx = 2;
-		break;
-	case IPPROTO_TCP:
-		cpu_idx = 0;
-		break;
-	case IPPROTO_UDP:
-		cpu_idx = 1;
-		/* DDoS filter UDP port 9 (pktgen) */
-		dest_port = get_dest_port_ipv4_udp(ctx, l3_offset);
-		if (dest_port == 9) {
-			NO_TEAR_INC(rec->dropped);
-			return XDP_DROP;
-		}
-		break;
-	default:
-		cpu_idx = 0;
-	}
-
-	cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
-	if (!cpu_lookup)
-		return XDP_ABORTED;
-	cpu_dest = *cpu_lookup;
-
-	if (cpu_dest >= nr_cpus) {
-		NO_TEAR_INC(rec->issue);
-		return XDP_ABORTED;
-	}
-	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
-}
-
-/* Hashing initval */
-#define INITVAL 15485863
-
-static __always_inline
-u32 get_ipv4_hash_ip_pair(struct xdp_md *ctx, u64 nh_off)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	struct iphdr *iph = data + nh_off;
-	u32 cpu_hash;
-
-	if (iph + 1 > data_end)
-		return 0;
-
-	cpu_hash = iph->saddr + iph->daddr;
-	cpu_hash = SuperFastHash((char *)&cpu_hash, 4, INITVAL + iph->protocol);
-
-	return cpu_hash;
-}
-
-static __always_inline
-u32 get_ipv6_hash_ip_pair(struct xdp_md *ctx, u64 nh_off)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	struct ipv6hdr *ip6h = data + nh_off;
-	u32 cpu_hash;
-
-	if (ip6h + 1 > data_end)
-		return 0;
-
-	cpu_hash  = ip6h->saddr.in6_u.u6_addr32[0] + ip6h->daddr.in6_u.u6_addr32[0];
-	cpu_hash += ip6h->saddr.in6_u.u6_addr32[1] + ip6h->daddr.in6_u.u6_addr32[1];
-	cpu_hash += ip6h->saddr.in6_u.u6_addr32[2] + ip6h->daddr.in6_u.u6_addr32[2];
-	cpu_hash += ip6h->saddr.in6_u.u6_addr32[3] + ip6h->daddr.in6_u.u6_addr32[3];
-	cpu_hash = SuperFastHash((char *)&cpu_hash, 4, INITVAL + ip6h->nexthdr);
-
-	return cpu_hash;
-}
-
-/* Load-Balance traffic based on hashing IP-addrs + L4-proto.  The
- * hashing scheme is symmetric, meaning swapping IP src/dest still hit
- * same CPU.
- */
-SEC("xdp")
-int  xdp_prognum5_lb_hash_ip_pairs(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	u32 key = bpf_get_smp_processor_id();
-	struct ethhdr *eth = data;
-	struct datarec *rec;
-	u16 eth_proto = 0;
-	u64 l3_offset = 0;
-	u32 cpu_dest = 0;
-	u32 cpu_idx = 0;
-	u32 *cpu_lookup;
-	u32 key0 = 0;
-	u32 *cpu_max;
-	u32 cpu_hash;
-
-	rec = bpf_map_lookup_elem(&rx_cnt, &key);
-	if (!rec)
-		return XDP_PASS;
-	NO_TEAR_INC(rec->processed);
-
-	cpu_max = bpf_map_lookup_elem(&cpus_count, &key0);
-	if (!cpu_max)
-		return XDP_ABORTED;
-
-	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
-		return XDP_PASS; /* Just skip */
-
-	/* Hash for IPv4 and IPv6 */
-	switch (eth_proto) {
-	case ETH_P_IP:
-		cpu_hash = get_ipv4_hash_ip_pair(ctx, l3_offset);
-		break;
-	case ETH_P_IPV6:
-		cpu_hash = get_ipv6_hash_ip_pair(ctx, l3_offset);
-		break;
-	case ETH_P_ARP: /* ARP packet handled on CPU idx 0 */
-	default:
-		cpu_hash = 0;
-	}
-
-	/* Choose CPU based on hash */
-	cpu_idx = cpu_hash % *cpu_max;
-
-	cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
-	if (!cpu_lookup)
-		return XDP_ABORTED;
-	cpu_dest = *cpu_lookup;
-
-	if (cpu_dest >= nr_cpus) {
-		NO_TEAR_INC(rec->issue);
-		return XDP_ABORTED;
-	}
-	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
-}
-
-SEC("xdp/cpumap")
-int xdp_redirect_cpu_devmap(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data = (void *)(long)ctx->data;
-	struct ethhdr *eth = data;
-	u64 nh_off;
-
-	nh_off = sizeof(*eth);
-	if (data + nh_off > data_end)
-		return XDP_DROP;
-
-	swap_src_dst_mac(data);
-	return bpf_redirect_map(&tx_port, 0, 0);
-}
-
-SEC("xdp/cpumap")
-int xdp_redirect_cpu_pass(struct xdp_md *ctx)
-{
-	return XDP_PASS;
-}
-
-SEC("xdp/cpumap")
-int xdp_redirect_cpu_drop(struct xdp_md *ctx)
-{
-	return XDP_DROP;
-}
-
-SEC("xdp/devmap")
-int xdp_redirect_egress_prog(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data = (void *)(long)ctx->data;
-	struct ethhdr *eth = data;
-	u64 nh_off;
-
-	nh_off = sizeof(*eth);
-	if (data + nh_off > data_end)
-		return XDP_DROP;
-
-	__builtin_memcpy(eth->h_source, (const char *)tx_mac_addr, ETH_ALEN);
-
-	return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
deleted file mode 100644
index e1458405e2ba2..0000000000000
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ /dev/null
@@ -1,559 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/* Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
- */
-static const char *__doc__ =
-"XDP CPU redirect tool, using BPF_MAP_TYPE_CPUMAP\n"
-"Usage: xdp_redirect_cpu -d <IFINDEX|IFNAME> -c 0 ... -c N\n"
-"Valid specification for CPUMAP BPF program:\n"
-"  --mprog-name/-e pass (use built-in XDP_PASS program)\n"
-"  --mprog-name/-e drop (use built-in XDP_DROP program)\n"
-"  --redirect-device/-r <ifindex|ifname> (use built-in DEVMAP redirect program)\n"
-"  Custom CPUMAP BPF program:\n"
-"    --mprog-filename/-f <filename> --mprog-name/-e <program>\n"
-"    Optionally, also pass --redirect-map/-m and --redirect-device/-r together\n"
-"    to configure DEVMAP in BPF object <filename>\n";
-
-#include <errno.h>
-#include <signal.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <stdbool.h>
-#include <string.h>
-#include <unistd.h>
-#include <locale.h>
-#include <sys/sysinfo.h>
-#include <getopt.h>
-#include <net/if.h>
-#include <time.h>
-#include <linux/limits.h>
-#include <arpa/inet.h>
-#include <linux/if_link.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-#include "bpf_util.h"
-#include "xdp_sample_user.h"
-#include "xdp_redirect_cpu.skel.h"
-
-static int map_fd;
-static int avail_fd;
-static int count_fd;
-
-static int mask = SAMPLE_RX_CNT | SAMPLE_REDIRECT_ERR_MAP_CNT |
-		  SAMPLE_CPUMAP_ENQUEUE_CNT | SAMPLE_CPUMAP_KTHREAD_CNT |
-		  SAMPLE_EXCEPTION_CNT;
-
-DEFINE_SAMPLE_INIT(xdp_redirect_cpu);
-
-static const struct option long_options[] = {
-	{ "help", no_argument, NULL, 'h' },
-	{ "dev", required_argument, NULL, 'd' },
-	{ "skb-mode", no_argument, NULL, 'S' },
-	{ "progname", required_argument, NULL, 'p' },
-	{ "qsize", required_argument, NULL, 'q' },
-	{ "cpu", required_argument, NULL, 'c' },
-	{ "stress-mode", no_argument, NULL, 'x' },
-	{ "force", no_argument, NULL, 'F' },
-	{ "interval", required_argument, NULL, 'i' },
-	{ "verbose", no_argument, NULL, 'v' },
-	{ "stats", no_argument, NULL, 's' },
-	{ "mprog-name", required_argument, NULL, 'e' },
-	{ "mprog-filename", required_argument, NULL, 'f' },
-	{ "redirect-device", required_argument, NULL, 'r' },
-	{ "redirect-map", required_argument, NULL, 'm' },
-	{}
-};
-
-static void print_avail_progs(struct bpf_object *obj)
-{
-	struct bpf_program *pos;
-
-	printf(" Programs to be used for -p/--progname:\n");
-	bpf_object__for_each_program(pos, obj) {
-		if (bpf_program__type(pos) == BPF_PROG_TYPE_XDP) {
-			if (!strncmp(bpf_program__name(pos), "xdp_prognum",
-				     sizeof("xdp_prognum") - 1))
-				printf(" %s\n", bpf_program__name(pos));
-		}
-	}
-}
-
-static void usage(char *argv[], const struct option *long_options,
-		  const char *doc, int mask, bool error, struct bpf_object *obj)
-{
-	sample_usage(argv, long_options, doc, mask, error);
-	print_avail_progs(obj);
-}
-
-static int create_cpu_entry(__u32 cpu, struct bpf_cpumap_val *value,
-			    __u32 avail_idx, bool new)
-{
-	__u32 curr_cpus_count = 0;
-	__u32 key = 0;
-	int ret;
-
-	/* Add a CPU entry to cpumap, as this allocate a cpu entry in
-	 * the kernel for the cpu.
-	 */
-	ret = bpf_map_update_elem(map_fd, &cpu, value, 0);
-	if (ret < 0) {
-		fprintf(stderr, "Create CPU entry failed: %s\n", strerror(errno));
-		return ret;
-	}
-
-	/* Inform bpf_prog's that a new CPU is available to select
-	 * from via some control maps.
-	 */
-	ret = bpf_map_update_elem(avail_fd, &avail_idx, &cpu, 0);
-	if (ret < 0) {
-		fprintf(stderr, "Add to avail CPUs failed: %s\n", strerror(errno));
-		return ret;
-	}
-
-	/* When not replacing/updating existing entry, bump the count */
-	ret = bpf_map_lookup_elem(count_fd, &key, &curr_cpus_count);
-	if (ret < 0) {
-		fprintf(stderr, "Failed reading curr cpus_count: %s\n",
-			strerror(errno));
-		return ret;
-	}
-	if (new) {
-		curr_cpus_count++;
-		ret = bpf_map_update_elem(count_fd, &key,
-					  &curr_cpus_count, 0);
-		if (ret < 0) {
-			fprintf(stderr, "Failed write curr cpus_count: %s\n",
-				strerror(errno));
-			return ret;
-		}
-	}
-
-	printf("%s CPU: %u as idx: %u qsize: %d cpumap_prog_fd: %d (cpus_count: %u)\n",
-	       new ? "Add new" : "Replace", cpu, avail_idx,
-	       value->qsize, value->bpf_prog.fd, curr_cpus_count);
-
-	return 0;
-}
-
-/* CPUs are zero-indexed. Thus, add a special sentinel default value
- * in map cpus_available to mark CPU index'es not configured
- */
-static int mark_cpus_unavailable(void)
-{
-	int ret, i, n_cpus = libbpf_num_possible_cpus();
-	__u32 invalid_cpu = n_cpus;
-
-	for (i = 0; i < n_cpus; i++) {
-		ret = bpf_map_update_elem(avail_fd, &i,
-					  &invalid_cpu, 0);
-		if (ret < 0) {
-			fprintf(stderr, "Failed marking CPU unavailable: %s\n",
-				strerror(errno));
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-/* Stress cpumap management code by concurrently changing underlying cpumap */
-static void stress_cpumap(void *ctx)
-{
-	struct bpf_cpumap_val *value = ctx;
-
-	/* Changing qsize will cause kernel to free and alloc a new
-	 * bpf_cpu_map_entry, with an associated/complicated tear-down
-	 * procedure.
-	 */
-	value->qsize = 1024;
-	create_cpu_entry(1, value, 0, false);
-	value->qsize = 8;
-	create_cpu_entry(1, value, 0, false);
-	value->qsize = 16000;
-	create_cpu_entry(1, value, 0, false);
-}
-
-static int set_cpumap_prog(struct xdp_redirect_cpu *skel,
-			   const char *redir_interface, const char *redir_map,
-			   const char *mprog_filename, const char *mprog_name)
-{
-	if (mprog_filename) {
-		struct bpf_program *prog;
-		struct bpf_object *obj;
-		int ret;
-
-		if (!mprog_name) {
-			fprintf(stderr, "BPF program not specified for file %s\n",
-				mprog_filename);
-			goto end;
-		}
-		if ((redir_interface && !redir_map) || (!redir_interface && redir_map)) {
-			fprintf(stderr, "--redirect-%s specified but --redirect-%s not specified\n",
-				redir_interface ? "device" : "map", redir_interface ? "map" : "device");
-			goto end;
-		}
-
-		/* Custom BPF program */
-		obj = bpf_object__open_file(mprog_filename, NULL);
-		if (!obj) {
-			ret = -errno;
-			fprintf(stderr, "Failed to bpf_prog_load_xattr: %s\n",
-				strerror(errno));
-			return ret;
-		}
-
-		ret = bpf_object__load(obj);
-		if (ret < 0) {
-			ret = -errno;
-			fprintf(stderr, "Failed to bpf_object__load: %s\n",
-				strerror(errno));
-			return ret;
-		}
-
-		if (redir_map) {
-			int err, redir_map_fd, ifindex_out, key = 0;
-
-			redir_map_fd = bpf_object__find_map_fd_by_name(obj, redir_map);
-			if (redir_map_fd < 0) {
-				fprintf(stderr, "Failed to bpf_object__find_map_fd_by_name: %s\n",
-					strerror(errno));
-				return redir_map_fd;
-			}
-
-			ifindex_out = if_nametoindex(redir_interface);
-			if (!ifindex_out)
-				ifindex_out = strtoul(redir_interface, NULL, 0);
-			if (!ifindex_out) {
-				fprintf(stderr, "Bad interface name or index\n");
-				return -EINVAL;
-			}
-
-			err = bpf_map_update_elem(redir_map_fd, &key, &ifindex_out, 0);
-			if (err < 0)
-				return err;
-		}
-
-		prog = bpf_object__find_program_by_name(obj, mprog_name);
-		if (!prog) {
-			ret = -errno;
-			fprintf(stderr, "Failed to bpf_object__find_program_by_name: %s\n",
-				strerror(errno));
-			return ret;
-		}
-
-		return bpf_program__fd(prog);
-	} else {
-		if (mprog_name) {
-			if (redir_interface || redir_map) {
-				fprintf(stderr, "Need to specify --mprog-filename/-f\n");
-				goto end;
-			}
-			if (!strcmp(mprog_name, "pass") || !strcmp(mprog_name, "drop")) {
-				/* Use built-in pass/drop programs */
-				return *mprog_name == 'p' ? bpf_program__fd(skel->progs.xdp_redirect_cpu_pass)
-					: bpf_program__fd(skel->progs.xdp_redirect_cpu_drop);
-			} else {
-				fprintf(stderr, "Unknown name \"%s\" for built-in BPF program\n",
-					mprog_name);
-				goto end;
-			}
-		} else {
-			if (redir_map) {
-				fprintf(stderr, "Need to specify --mprog-filename, --mprog-name and"
-					" --redirect-device with --redirect-map\n");
-				goto end;
-			}
-			if (redir_interface) {
-				/* Use built-in devmap redirect */
-				struct bpf_devmap_val val = {};
-				int ifindex_out, err;
-				__u32 key = 0;
-
-				if (!redir_interface)
-					return 0;
-
-				ifindex_out = if_nametoindex(redir_interface);
-				if (!ifindex_out)
-					ifindex_out = strtoul(redir_interface, NULL, 0);
-				if (!ifindex_out) {
-					fprintf(stderr, "Bad interface name or index\n");
-					return -EINVAL;
-				}
-
-				if (get_mac_addr(ifindex_out, skel->bss->tx_mac_addr) < 0) {
-					printf("Get interface %d mac failed\n", ifindex_out);
-					return -EINVAL;
-				}
-
-				val.ifindex = ifindex_out;
-				val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_redirect_egress_prog);
-				err = bpf_map_update_elem(bpf_map__fd(skel->maps.tx_port), &key, &val, 0);
-				if (err < 0)
-					return -errno;
-
-				return bpf_program__fd(skel->progs.xdp_redirect_cpu_devmap);
-			}
-		}
-	}
-
-	/* Disabled */
-	return 0;
-end:
-	fprintf(stderr, "Invalid options for CPUMAP BPF program\n");
-	return -EINVAL;
-}
-
-int main(int argc, char **argv)
-{
-	const char *redir_interface = NULL, *redir_map = NULL;
-	const char *mprog_filename = NULL, *mprog_name = NULL;
-	struct xdp_redirect_cpu *skel;
-	struct bpf_map_info info = {};
-	struct bpf_cpumap_val value;
-	__u32 infosz = sizeof(info);
-	int ret = EXIT_FAIL_OPTION;
-	unsigned long interval = 2;
-	bool stress_mode = false;
-	struct bpf_program *prog;
-	const char *prog_name;
-	bool generic = false;
-	bool force = false;
-	int added_cpus = 0;
-	bool error = true;
-	int longindex = 0;
-	int add_cpu = -1;
-	int ifindex = -1;
-	int *cpu, i, opt;
-	__u32 qsize;
-	int n_cpus;
-
-	n_cpus = libbpf_num_possible_cpus();
-
-	/* Notice: Choosing the queue size is very important when CPU is
-	 * configured with power-saving states.
-	 *
-	 * If deepest state take 133 usec to wakeup from (133/10^6). When link
-	 * speed is 10Gbit/s ((10*10^9/8) in bytes/sec). How many bytes can
-	 * arrive with in 133 usec at this speed: (10*10^9/8)*(133/10^6) =
-	 * 166250 bytes. With MTU size packets this is 110 packets, and with
-	 * minimum Ethernet (MAC-preamble + intergap) 84 bytes is 1979 packets.
-	 *
-	 * Setting default cpumap queue to 2048 as worst-case (small packet)
-	 * should be +64 packet due kthread wakeup call (due to xdp_do_flush)
-	 * worst-case is 2043 packets.
-	 *
-	 * Sysadm can configured system to avoid deep-sleep via:
-	 *   tuned-adm profile network-latency
-	 */
-	qsize = 2048;
-
-	skel = xdp_redirect_cpu__open();
-	if (!skel) {
-		fprintf(stderr, "Failed to xdp_redirect_cpu__open: %s\n",
-			strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end;
-	}
-
-	ret = sample_init_pre_load(skel);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	if (bpf_map__set_max_entries(skel->maps.cpu_map, n_cpus) < 0) {
-		fprintf(stderr, "Failed to set max entries for cpu_map map: %s",
-			strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	if (bpf_map__set_max_entries(skel->maps.cpus_available, n_cpus) < 0) {
-		fprintf(stderr, "Failed to set max entries for cpus_available map: %s",
-			strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	cpu = calloc(n_cpus, sizeof(int));
-	if (!cpu) {
-		fprintf(stderr, "Failed to allocate cpu array\n");
-		goto end_destroy;
-	}
-
-	prog = skel->progs.xdp_prognum5_lb_hash_ip_pairs;
-	while ((opt = getopt_long(argc, argv, "d:si:Sxp:f:e:r:m:c:q:Fvh",
-				  long_options, &longindex)) != -1) {
-		switch (opt) {
-		case 'd':
-			if (strlen(optarg) >= IF_NAMESIZE) {
-				fprintf(stderr, "-d/--dev name too long\n");
-				usage(argv, long_options, __doc__, mask, true, skel->obj);
-				goto end_cpu;
-			}
-			ifindex = if_nametoindex(optarg);
-			if (!ifindex)
-				ifindex = strtoul(optarg, NULL, 0);
-			if (!ifindex) {
-				fprintf(stderr, "Bad interface index or name (%d): %s\n",
-					errno, strerror(errno));
-				usage(argv, long_options, __doc__, mask, true, skel->obj);
-				goto end_cpu;
-			}
-			break;
-		case 's':
-			mask |= SAMPLE_REDIRECT_MAP_CNT;
-			break;
-		case 'i':
-			interval = strtoul(optarg, NULL, 0);
-			break;
-		case 'S':
-			generic = true;
-			break;
-		case 'x':
-			stress_mode = true;
-			break;
-		case 'p':
-			/* Selecting eBPF prog to load */
-			prog_name = optarg;
-			prog = bpf_object__find_program_by_name(skel->obj,
-								prog_name);
-			if (!prog) {
-				fprintf(stderr,
-					"Failed to find program %s specified by"
-					" option -p/--progname\n",
-					prog_name);
-				print_avail_progs(skel->obj);
-				goto end_cpu;
-			}
-			break;
-		case 'f':
-			mprog_filename = optarg;
-			break;
-		case 'e':
-			mprog_name = optarg;
-			break;
-		case 'r':
-			redir_interface = optarg;
-			mask |= SAMPLE_DEVMAP_XMIT_CNT_MULTI;
-			break;
-		case 'm':
-			redir_map = optarg;
-			break;
-		case 'c':
-			/* Add multiple CPUs */
-			add_cpu = strtoul(optarg, NULL, 0);
-			if (add_cpu >= n_cpus) {
-				fprintf(stderr,
-				"--cpu nr too large for cpumap err (%d):%s\n",
-					errno, strerror(errno));
-				usage(argv, long_options, __doc__, mask, true, skel->obj);
-				goto end_cpu;
-			}
-			cpu[added_cpus++] = add_cpu;
-			break;
-		case 'q':
-			qsize = strtoul(optarg, NULL, 0);
-			break;
-		case 'F':
-			force = true;
-			break;
-		case 'v':
-			sample_switch_mode();
-			break;
-		case 'h':
-			error = false;
-		default:
-			usage(argv, long_options, __doc__, mask, error, skel->obj);
-			goto end_cpu;
-		}
-	}
-
-	ret = EXIT_FAIL_OPTION;
-	if (ifindex == -1) {
-		fprintf(stderr, "Required option --dev missing\n");
-		usage(argv, long_options, __doc__, mask, true, skel->obj);
-		goto end_cpu;
-	}
-
-	if (add_cpu == -1) {
-		fprintf(stderr, "Required option --cpu missing\n"
-				"Specify multiple --cpu option to add more\n");
-		usage(argv, long_options, __doc__, mask, true, skel->obj);
-		goto end_cpu;
-	}
-
-	skel->rodata->from_match[0] = ifindex;
-	if (redir_interface)
-		skel->rodata->to_match[0] = if_nametoindex(redir_interface);
-
-	ret = xdp_redirect_cpu__load(skel);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to xdp_redirect_cpu__load: %s\n",
-			strerror(errno));
-		goto end_cpu;
-	}
-
-	ret = bpf_map_get_info_by_fd(bpf_map__fd(skel->maps.cpu_map), &info, &infosz);
-	if (ret < 0) {
-		fprintf(stderr, "Failed bpf_map_get_info_by_fd for cpumap: %s\n",
-			strerror(errno));
-		goto end_cpu;
-	}
-
-	skel->bss->cpumap_map_id = info.id;
-
-	map_fd = bpf_map__fd(skel->maps.cpu_map);
-	avail_fd = bpf_map__fd(skel->maps.cpus_available);
-	count_fd = bpf_map__fd(skel->maps.cpus_count);
-
-	ret = mark_cpus_unavailable();
-	if (ret < 0) {
-		fprintf(stderr, "Unable to mark CPUs as unavailable\n");
-		goto end_cpu;
-	}
-
-	ret = sample_init(skel, mask);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
-		ret = EXIT_FAIL;
-		goto end_cpu;
-	}
-
-	value.bpf_prog.fd = set_cpumap_prog(skel, redir_interface, redir_map,
-					    mprog_filename, mprog_name);
-	if (value.bpf_prog.fd < 0) {
-		fprintf(stderr, "Failed to set CPUMAP BPF program: %s\n",
-			strerror(-value.bpf_prog.fd));
-		usage(argv, long_options, __doc__, mask, true, skel->obj);
-		ret = EXIT_FAIL_BPF;
-		goto end_cpu;
-	}
-	value.qsize = qsize;
-
-	for (i = 0; i < added_cpus; i++) {
-		if (create_cpu_entry(cpu[i], &value, i, true) < 0) {
-			fprintf(stderr, "Cannot proceed, exiting\n");
-			usage(argv, long_options, __doc__, mask, true, skel->obj);
-			goto end_cpu;
-		}
-	}
-
-	ret = EXIT_FAIL_XDP;
-	if (sample_install_xdp(prog, ifindex, generic, force) < 0)
-		goto end_cpu;
-
-	ret = sample_run(interval, stress_mode ? stress_cpumap : NULL, &value);
-	if (ret < 0) {
-		fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
-		ret = EXIT_FAIL;
-		goto end_cpu;
-	}
-	ret = EXIT_OK;
-end_cpu:
-	free(cpu);
-end_destroy:
-	xdp_redirect_cpu__destroy(skel);
-end:
-	sample_exit(ret);
-}
diff --git a/samples/bpf/xdp_redirect_map.bpf.c b/samples/bpf/xdp_redirect_map.bpf.c
deleted file mode 100644
index 8557c278df778..0000000000000
--- a/samples/bpf/xdp_redirect_map.bpf.c
+++ /dev/null
@@ -1,97 +0,0 @@
-/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- */
-#define KBUILD_MODNAME "foo"
-
-#include "vmlinux.h"
-#include "xdp_sample.bpf.h"
-#include "xdp_sample_shared.h"
-
-/* The 2nd xdp prog on egress does not support skb mode, so we define two
- * maps, tx_port_general and tx_port_native.
- */
-struct {
-	__uint(type, BPF_MAP_TYPE_DEVMAP);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
-	__uint(max_entries, 1);
-} tx_port_general SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_DEVMAP);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(struct bpf_devmap_val));
-	__uint(max_entries, 1);
-} tx_port_native SEC(".maps");
-
-/* store egress interface mac address */
-const volatile __u8 tx_mac_addr[ETH_ALEN];
-
-static __always_inline int xdp_redirect_map(struct xdp_md *ctx, void *redirect_map)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data = (void *)(long)ctx->data;
-	u32 key = bpf_get_smp_processor_id();
-	struct ethhdr *eth = data;
-	struct datarec *rec;
-	u64 nh_off;
-
-	nh_off = sizeof(*eth);
-	if (data + nh_off > data_end)
-		return XDP_DROP;
-
-	rec = bpf_map_lookup_elem(&rx_cnt, &key);
-	if (!rec)
-		return XDP_PASS;
-	NO_TEAR_INC(rec->processed);
-	swap_src_dst_mac(data);
-	return bpf_redirect_map(redirect_map, 0, 0);
-}
-
-SEC("xdp")
-int xdp_redirect_map_general(struct xdp_md *ctx)
-{
-	return xdp_redirect_map(ctx, &tx_port_general);
-}
-
-SEC("xdp")
-int xdp_redirect_map_native(struct xdp_md *ctx)
-{
-	return xdp_redirect_map(ctx, &tx_port_native);
-}
-
-SEC("xdp/devmap")
-int xdp_redirect_map_egress(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data = (void *)(long)ctx->data;
-	u8 *mac_addr = (u8 *) tx_mac_addr;
-	struct ethhdr *eth = data;
-	u64 nh_off;
-
-	nh_off = sizeof(*eth);
-	if (data + nh_off > data_end)
-		return XDP_DROP;
-
-	barrier_var(mac_addr); /* prevent optimizing out memcpy */
-	__builtin_memcpy(eth->h_source, mac_addr, ETH_ALEN);
-
-	return XDP_PASS;
-}
-
-/* Redirect require an XDP bpf_prog loaded on the TX device */
-SEC("xdp")
-int xdp_redirect_dummy_prog(struct xdp_md *ctx)
-{
-	return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_redirect_map_multi.bpf.c b/samples/bpf/xdp_redirect_map_multi.bpf.c
deleted file mode 100644
index 8b2fd4ec2c767..0000000000000
--- a/samples/bpf/xdp_redirect_map_multi.bpf.c
+++ /dev/null
@@ -1,77 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define KBUILD_MODNAME "foo"
-
-#include "vmlinux.h"
-#include "xdp_sample.bpf.h"
-#include "xdp_sample_shared.h"
-
-struct {
-	__uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
-	__uint(max_entries, 32);
-} forward_map_general SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(struct bpf_devmap_val));
-	__uint(max_entries, 32);
-} forward_map_native SEC(".maps");
-
-/* map to store egress interfaces mac addresses */
-struct {
-	__uint(type, BPF_MAP_TYPE_HASH);
-	__type(key, u32);
-	__type(value, __be64);
-	__uint(max_entries, 32);
-} mac_map SEC(".maps");
-
-static int xdp_redirect_map(struct xdp_md *ctx, void *forward_map)
-{
-	u32 key = bpf_get_smp_processor_id();
-	struct datarec *rec;
-
-	rec = bpf_map_lookup_elem(&rx_cnt, &key);
-	if (!rec)
-		return XDP_PASS;
-	NO_TEAR_INC(rec->processed);
-
-	return bpf_redirect_map(forward_map, 0,
-				BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
-}
-
-SEC("xdp")
-int xdp_redirect_map_general(struct xdp_md *ctx)
-{
-	return xdp_redirect_map(ctx, &forward_map_general);
-}
-
-SEC("xdp")
-int xdp_redirect_map_native(struct xdp_md *ctx)
-{
-	return xdp_redirect_map(ctx, &forward_map_native);
-}
-
-SEC("xdp/devmap")
-int xdp_devmap_prog(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data = (void *)(long)ctx->data;
-	u32 key = ctx->egress_ifindex;
-	struct ethhdr *eth = data;
-	__be64 *mac;
-	u64 nh_off;
-
-	nh_off = sizeof(*eth);
-	if (data + nh_off > data_end)
-		return XDP_DROP;
-
-	mac = bpf_map_lookup_elem(&mac_map, &key);
-	if (mac)
-		__builtin_memcpy(eth->h_source, mac, ETH_ALEN);
-
-	return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_redirect_map_multi_user.c b/samples/bpf/xdp_redirect_map_multi_user.c
deleted file mode 100644
index 9e24f2705b677..0000000000000
--- a/samples/bpf/xdp_redirect_map_multi_user.c
+++ /dev/null
@@ -1,232 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-static const char *__doc__ =
-"XDP multi redirect tool, using BPF_MAP_TYPE_DEVMAP and BPF_F_BROADCAST flag for bpf_redirect_map\n"
-"Usage: xdp_redirect_map_multi <IFINDEX|IFNAME> <IFINDEX|IFNAME> ... <IFINDEX|IFNAME>\n";
-
-#include <linux/bpf.h>
-#include <linux/if_link.h>
-#include <assert.h>
-#include <getopt.h>
-#include <errno.h>
-#include <signal.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <net/if.h>
-#include <unistd.h>
-#include <libgen.h>
-#include <sys/ioctl.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <netinet/in.h>
-#include <linux/if_ether.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-#include "bpf_util.h"
-#include "xdp_sample_user.h"
-#include "xdp_redirect_map_multi.skel.h"
-
-#define MAX_IFACE_NUM 32
-static int ifaces[MAX_IFACE_NUM] = {};
-
-static int mask = SAMPLE_RX_CNT | SAMPLE_REDIRECT_ERR_MAP_CNT |
-		  SAMPLE_EXCEPTION_CNT | SAMPLE_DEVMAP_XMIT_CNT |
-		  SAMPLE_DEVMAP_XMIT_CNT_MULTI | SAMPLE_SKIP_HEADING;
-
-DEFINE_SAMPLE_INIT(xdp_redirect_map_multi);
-
-static const struct option long_options[] = {
-	{ "help", no_argument, NULL, 'h' },
-	{ "skb-mode", no_argument, NULL, 'S' },
-	{ "force", no_argument, NULL, 'F' },
-	{ "load-egress", no_argument, NULL, 'X' },
-	{ "stats", no_argument, NULL, 's' },
-	{ "interval", required_argument, NULL, 'i' },
-	{ "verbose", no_argument, NULL, 'v' },
-	{}
-};
-
-static int update_mac_map(struct bpf_map *map)
-{
-	int mac_map_fd = bpf_map__fd(map);
-	unsigned char mac_addr[6];
-	unsigned int ifindex;
-	int i, ret = -1;
-
-	for (i = 0; ifaces[i] > 0; i++) {
-		ifindex = ifaces[i];
-
-		ret = get_mac_addr(ifindex, mac_addr);
-		if (ret < 0) {
-			fprintf(stderr, "get interface %d mac failed\n",
-				ifindex);
-			return ret;
-		}
-
-		ret = bpf_map_update_elem(mac_map_fd, &ifindex, mac_addr, 0);
-		if (ret < 0) {
-			fprintf(stderr, "Failed to update mac address for ifindex %d\n",
-				ifindex);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-int main(int argc, char **argv)
-{
-	struct bpf_devmap_val devmap_val = {};
-	struct xdp_redirect_map_multi *skel;
-	struct bpf_program *ingress_prog;
-	bool xdp_devmap_attached = false;
-	struct bpf_map *forward_map;
-	int ret = EXIT_FAIL_OPTION;
-	unsigned long interval = 2;
-	char ifname[IF_NAMESIZE];
-	unsigned int ifindex;
-	bool generic = false;
-	bool force = false;
-	bool tried = false;
-	bool error = true;
-	int i, opt;
-
-	while ((opt = getopt_long(argc, argv, "hSFXi:vs",
-				  long_options, NULL)) != -1) {
-		switch (opt) {
-		case 'S':
-			generic = true;
-			/* devmap_xmit tracepoint not available */
-			mask &= ~(SAMPLE_DEVMAP_XMIT_CNT |
-				  SAMPLE_DEVMAP_XMIT_CNT_MULTI);
-			break;
-		case 'F':
-			force = true;
-			break;
-		case 'X':
-			xdp_devmap_attached = true;
-			break;
-		case 'i':
-			interval = strtoul(optarg, NULL, 0);
-			break;
-		case 'v':
-			sample_switch_mode();
-			break;
-		case 's':
-			mask |= SAMPLE_REDIRECT_MAP_CNT;
-			break;
-		case 'h':
-			error = false;
-		default:
-			sample_usage(argv, long_options, __doc__, mask, error);
-			return ret;
-		}
-	}
-
-	if (argc <= optind + 1) {
-		sample_usage(argv, long_options, __doc__, mask, error);
-		return ret;
-	}
-
-	skel = xdp_redirect_map_multi__open();
-	if (!skel) {
-		fprintf(stderr, "Failed to xdp_redirect_map_multi__open: %s\n",
-			strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end;
-	}
-
-	ret = sample_init_pre_load(skel);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	ret = EXIT_FAIL_OPTION;
-	for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
-		ifaces[i] = if_nametoindex(argv[optind + i]);
-		if (!ifaces[i])
-			ifaces[i] = strtoul(argv[optind + i], NULL, 0);
-		if (!if_indextoname(ifaces[i], ifname)) {
-			fprintf(stderr, "Bad interface index or name\n");
-			sample_usage(argv, long_options, __doc__, mask, true);
-			goto end_destroy;
-		}
-
-		skel->rodata->from_match[i] = ifaces[i];
-		skel->rodata->to_match[i] = ifaces[i];
-	}
-
-	ret = xdp_redirect_map_multi__load(skel);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to xdp_redirect_map_multi__load: %s\n",
-			strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	if (xdp_devmap_attached) {
-		/* Update mac_map with all egress interfaces' mac addr */
-		if (update_mac_map(skel->maps.mac_map) < 0) {
-			fprintf(stderr, "Updating mac address failed\n");
-			ret = EXIT_FAIL;
-			goto end_destroy;
-		}
-	}
-
-	ret = sample_init(skel, mask);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
-		ret = EXIT_FAIL;
-		goto end_destroy;
-	}
-
-	ingress_prog = skel->progs.xdp_redirect_map_native;
-	forward_map = skel->maps.forward_map_native;
-
-	for (i = 0; ifaces[i] > 0; i++) {
-		ifindex = ifaces[i];
-
-		ret = EXIT_FAIL_XDP;
-restart:
-		/* bind prog_fd to each interface */
-		if (sample_install_xdp(ingress_prog, ifindex, generic, force) < 0) {
-			if (generic && !tried) {
-				fprintf(stderr,
-					"Trying fallback to sizeof(int) as value_size for devmap in generic mode\n");
-				ingress_prog = skel->progs.xdp_redirect_map_general;
-				forward_map = skel->maps.forward_map_general;
-				tried = true;
-				goto restart;
-			}
-			goto end_destroy;
-		}
-
-		/* Add all the interfaces to forward group and attach
-		 * egress devmap program if exist
-		 */
-		devmap_val.ifindex = ifindex;
-		if (xdp_devmap_attached)
-			devmap_val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_devmap_prog);
-		ret = bpf_map_update_elem(bpf_map__fd(forward_map), &ifindex, &devmap_val, 0);
-		if (ret < 0) {
-			fprintf(stderr, "Failed to update devmap value: %s\n",
-				strerror(errno));
-			ret = EXIT_FAIL_BPF;
-			goto end_destroy;
-		}
-	}
-
-	ret = sample_run(interval, NULL, NULL);
-	if (ret < 0) {
-		fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
-		ret = EXIT_FAIL;
-		goto end_destroy;
-	}
-	ret = EXIT_OK;
-end_destroy:
-	xdp_redirect_map_multi__destroy(skel);
-end:
-	sample_exit(ret);
-}
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
deleted file mode 100644
index c889a1394dc14..0000000000000
--- a/samples/bpf/xdp_redirect_map_user.c
+++ /dev/null
@@ -1,228 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
- */
-static const char *__doc__ =
-"XDP redirect tool, using BPF_MAP_TYPE_DEVMAP\n"
-"Usage: xdp_redirect_map <IFINDEX|IFNAME>_IN <IFINDEX|IFNAME>_OUT\n";
-
-#include <linux/bpf.h>
-#include <linux/if_link.h>
-#include <assert.h>
-#include <errno.h>
-#include <signal.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <stdbool.h>
-#include <string.h>
-#include <net/if.h>
-#include <unistd.h>
-#include <libgen.h>
-#include <getopt.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-#include "bpf_util.h"
-#include "xdp_sample_user.h"
-#include "xdp_redirect_map.skel.h"
-
-static int mask = SAMPLE_RX_CNT | SAMPLE_REDIRECT_ERR_MAP_CNT |
-		  SAMPLE_EXCEPTION_CNT | SAMPLE_DEVMAP_XMIT_CNT_MULTI;
-
-DEFINE_SAMPLE_INIT(xdp_redirect_map);
-
-static const struct option long_options[] = {
-	{ "help", no_argument, NULL, 'h' },
-	{ "skb-mode", no_argument, NULL, 'S' },
-	{ "force", no_argument, NULL, 'F' },
-	{ "load-egress", no_argument, NULL, 'X' },
-	{ "stats", no_argument, NULL, 's' },
-	{ "interval", required_argument, NULL, 'i' },
-	{ "verbose", no_argument, NULL, 'v' },
-	{}
-};
-
-static int verbose = 0;
-
-int main(int argc, char **argv)
-{
-	struct bpf_devmap_val devmap_val = {};
-	bool xdp_devmap_attached = false;
-	struct xdp_redirect_map *skel;
-	char str[2 * IF_NAMESIZE + 1];
-	char ifname_out[IF_NAMESIZE];
-	struct bpf_map *tx_port_map;
-	char ifname_in[IF_NAMESIZE];
-	int ifindex_in, ifindex_out;
-	unsigned long interval = 2;
-	int ret = EXIT_FAIL_OPTION;
-	struct bpf_program *prog;
-	bool generic = false;
-	bool force = false;
-	bool tried = false;
-	bool error = true;
-	int opt, key = 0;
-
-	while ((opt = getopt_long(argc, argv, "hSFXi:vs",
-				  long_options, NULL)) != -1) {
-		switch (opt) {
-		case 'S':
-			generic = true;
-			/* devmap_xmit tracepoint not available */
-			mask &= ~(SAMPLE_DEVMAP_XMIT_CNT |
-				  SAMPLE_DEVMAP_XMIT_CNT_MULTI);
-			break;
-		case 'F':
-			force = true;
-			break;
-		case 'X':
-			xdp_devmap_attached = true;
-			break;
-		case 'i':
-			interval = strtoul(optarg, NULL, 0);
-			break;
-		case 'v':
-			sample_switch_mode();
-			verbose = 1;
-			break;
-		case 's':
-			mask |= SAMPLE_REDIRECT_MAP_CNT;
-			break;
-		case 'h':
-			error = false;
-		default:
-			sample_usage(argv, long_options, __doc__, mask, error);
-			return ret;
-		}
-	}
-
-	if (argc <= optind + 1) {
-		sample_usage(argv, long_options, __doc__, mask, true);
-		goto end;
-	}
-
-	ifindex_in = if_nametoindex(argv[optind]);
-	if (!ifindex_in)
-		ifindex_in = strtoul(argv[optind], NULL, 0);
-
-	ifindex_out = if_nametoindex(argv[optind + 1]);
-	if (!ifindex_out)
-		ifindex_out = strtoul(argv[optind + 1], NULL, 0);
-
-	if (!ifindex_in || !ifindex_out) {
-		fprintf(stderr, "Bad interface index or name\n");
-		sample_usage(argv, long_options, __doc__, mask, true);
-		goto end;
-	}
-
-	skel = xdp_redirect_map__open();
-	if (!skel) {
-		fprintf(stderr, "Failed to xdp_redirect_map__open: %s\n",
-			strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end;
-	}
-
-	ret = sample_init_pre_load(skel);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	/* Load 2nd xdp prog on egress. */
-	if (xdp_devmap_attached) {
-		ret = get_mac_addr(ifindex_out, skel->rodata->tx_mac_addr);
-		if (ret < 0) {
-			fprintf(stderr, "Failed to get interface %d mac address: %s\n",
-				ifindex_out, strerror(-ret));
-			ret = EXIT_FAIL;
-			goto end_destroy;
-		}
-		if (verbose)
-			printf("Egress ifindex:%d using src MAC %02x:%02x:%02x:%02x:%02x:%02x\n",
-			       ifindex_out,
-			       skel->rodata->tx_mac_addr[0], skel->rodata->tx_mac_addr[1],
-			       skel->rodata->tx_mac_addr[2], skel->rodata->tx_mac_addr[3],
-			       skel->rodata->tx_mac_addr[4], skel->rodata->tx_mac_addr[5]);
-	}
-
-	skel->rodata->from_match[0] = ifindex_in;
-	skel->rodata->to_match[0] = ifindex_out;
-
-	ret = xdp_redirect_map__load(skel);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to xdp_redirect_map__load: %s\n",
-			strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	ret = sample_init(skel, mask);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
-		ret = EXIT_FAIL;
-		goto end_destroy;
-	}
-
-	prog = skel->progs.xdp_redirect_map_native;
-	tx_port_map = skel->maps.tx_port_native;
-restart:
-	if (sample_install_xdp(prog, ifindex_in, generic, force) < 0) {
-		/* First try with struct bpf_devmap_val as value for generic
-		 * mode, then fallback to sizeof(int) for older kernels.
-		 */
-		fprintf(stderr,
-			"Trying fallback to sizeof(int) as value_size for devmap in generic mode\n");
-		if (generic && !tried) {
-			prog = skel->progs.xdp_redirect_map_general;
-			tx_port_map = skel->maps.tx_port_general;
-			tried = true;
-			goto restart;
-		}
-		ret = EXIT_FAIL_XDP;
-		goto end_destroy;
-	}
-
-	/* Loading dummy XDP prog on out-device */
-	sample_install_xdp(skel->progs.xdp_redirect_dummy_prog, ifindex_out, generic, force);
-
-	devmap_val.ifindex = ifindex_out;
-	if (xdp_devmap_attached)
-		devmap_val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_redirect_map_egress);
-	ret = bpf_map_update_elem(bpf_map__fd(tx_port_map), &key, &devmap_val, 0);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to update devmap value: %s\n",
-			strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	ret = EXIT_FAIL;
-	if (!if_indextoname(ifindex_in, ifname_in)) {
-		fprintf(stderr, "Failed to if_indextoname for %d: %s\n", ifindex_in,
-			strerror(errno));
-		goto end_destroy;
-	}
-
-	if (!if_indextoname(ifindex_out, ifname_out)) {
-		fprintf(stderr, "Failed to if_indextoname for %d: %s\n", ifindex_out,
-			strerror(errno));
-		goto end_destroy;
-	}
-
-	safe_strncpy(str, get_driver_name(ifindex_in), sizeof(str));
-	printf("Redirecting from %s (ifindex %d; driver %s) to %s (ifindex %d; driver %s)\n",
-	       ifname_in, ifindex_in, str, ifname_out, ifindex_out, get_driver_name(ifindex_out));
-	snprintf(str, sizeof(str), "%s->%s", ifname_in, ifname_out);
-
-	ret = sample_run(interval, NULL, NULL);
-	if (ret < 0) {
-		fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
-		ret = EXIT_FAIL;
-		goto end_destroy;
-	}
-	ret = EXIT_OK;
-end_destroy:
-	xdp_redirect_map__destroy(skel);
-end:
-	sample_exit(ret);
-}
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
deleted file mode 100644
index 8663dd631b6ee..0000000000000
--- a/samples/bpf/xdp_redirect_user.c
+++ /dev/null
@@ -1,172 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (c) 2016 John Fastabend <john.r.fastabend@intel.com>
- */
-static const char *__doc__ =
-"XDP redirect tool, using bpf_redirect helper\n"
-"Usage: xdp_redirect <IFINDEX|IFNAME>_IN <IFINDEX|IFNAME>_OUT\n";
-
-#include <linux/bpf.h>
-#include <linux/if_link.h>
-#include <assert.h>
-#include <errno.h>
-#include <signal.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <stdbool.h>
-#include <string.h>
-#include <net/if.h>
-#include <unistd.h>
-#include <libgen.h>
-#include <getopt.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-#include "bpf_util.h"
-#include "xdp_sample_user.h"
-#include "xdp_redirect.skel.h"
-
-static int mask = SAMPLE_RX_CNT | SAMPLE_REDIRECT_ERR_CNT |
-		  SAMPLE_EXCEPTION_CNT | SAMPLE_DEVMAP_XMIT_CNT_MULTI;
-
-DEFINE_SAMPLE_INIT(xdp_redirect);
-
-static const struct option long_options[] = {
-	{"help",	no_argument,		NULL, 'h' },
-	{"skb-mode",	no_argument,		NULL, 'S' },
-	{"force",	no_argument,		NULL, 'F' },
-	{"stats",	no_argument,		NULL, 's' },
-	{"interval",	required_argument,	NULL, 'i' },
-	{"verbose",	no_argument,		NULL, 'v' },
-	{}
-};
-
-int main(int argc, char **argv)
-{
-	int ifindex_in, ifindex_out, opt;
-	char str[2 * IF_NAMESIZE + 1];
-	char ifname_out[IF_NAMESIZE];
-	char ifname_in[IF_NAMESIZE];
-	int ret = EXIT_FAIL_OPTION;
-	unsigned long interval = 2;
-	struct xdp_redirect *skel;
-	bool generic = false;
-	bool force = false;
-	bool error = true;
-
-	while ((opt = getopt_long(argc, argv, "hSFi:vs",
-				  long_options, NULL)) != -1) {
-		switch (opt) {
-		case 'S':
-			generic = true;
-			mask &= ~(SAMPLE_DEVMAP_XMIT_CNT |
-				  SAMPLE_DEVMAP_XMIT_CNT_MULTI);
-			break;
-		case 'F':
-			force = true;
-			break;
-		case 'i':
-			interval = strtoul(optarg, NULL, 0);
-			break;
-		case 'v':
-			sample_switch_mode();
-			break;
-		case 's':
-			mask |= SAMPLE_REDIRECT_CNT;
-			break;
-		case 'h':
-			error = false;
-		default:
-			sample_usage(argv, long_options, __doc__, mask, error);
-			return ret;
-		}
-	}
-
-	if (argc <= optind + 1) {
-		sample_usage(argv, long_options, __doc__, mask, true);
-		return ret;
-	}
-
-	ifindex_in = if_nametoindex(argv[optind]);
-	if (!ifindex_in)
-		ifindex_in = strtoul(argv[optind], NULL, 0);
-
-	ifindex_out = if_nametoindex(argv[optind + 1]);
-	if (!ifindex_out)
-		ifindex_out = strtoul(argv[optind + 1], NULL, 0);
-
-	if (!ifindex_in || !ifindex_out) {
-		fprintf(stderr, "Bad interface index or name\n");
-		sample_usage(argv, long_options, __doc__, mask, true);
-		goto end;
-	}
-
-	skel = xdp_redirect__open();
-	if (!skel) {
-		fprintf(stderr, "Failed to xdp_redirect__open: %s\n", strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end;
-	}
-
-	ret = sample_init_pre_load(skel);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	skel->rodata->from_match[0] = ifindex_in;
-	skel->rodata->to_match[0] = ifindex_out;
-	skel->rodata->ifindex_out = ifindex_out;
-
-	ret = xdp_redirect__load(skel);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to xdp_redirect__load: %s\n", strerror(errno));
-		ret = EXIT_FAIL_BPF;
-		goto end_destroy;
-	}
-
-	ret = sample_init(skel, mask);
-	if (ret < 0) {
-		fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
-		ret = EXIT_FAIL;
-		goto end_destroy;
-	}
-
-	ret = EXIT_FAIL_XDP;
-	if (sample_install_xdp(skel->progs.xdp_redirect_prog, ifindex_in,
-			       generic, force) < 0)
-		goto end_destroy;
-
-	/* Loading dummy XDP prog on out-device */
-	sample_install_xdp(skel->progs.xdp_redirect_dummy_prog, ifindex_out,
-			   generic, force);
-
-	ret = EXIT_FAIL;
-	if (!if_indextoname(ifindex_in, ifname_in)) {
-		fprintf(stderr, "Failed to if_indextoname for %d: %s\n", ifindex_in,
-			strerror(errno));
-		goto end_destroy;
-	}
-
-	if (!if_indextoname(ifindex_out, ifname_out)) {
-		fprintf(stderr, "Failed to if_indextoname for %d: %s\n", ifindex_out,
-			strerror(errno));
-		goto end_destroy;
-	}
-
-	safe_strncpy(str, get_driver_name(ifindex_in), sizeof(str));
-	printf("Redirecting from %s (ifindex %d; driver %s) to %s (ifindex %d; driver %s)\n",
-	       ifname_in, ifindex_in, str, ifname_out, ifindex_out, get_driver_name(ifindex_out));
-	snprintf(str, sizeof(str), "%s->%s", ifname_in, ifname_out);
-
-	ret = sample_run(interval, NULL, NULL);
-	if (ret < 0) {
-		fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
-		ret = EXIT_FAIL;
-		goto end_destroy;
-	}
-	ret = EXIT_OK;
-end_destroy:
-	xdp_redirect__destroy(skel);
-end:
-	sample_exit(ret);
-}
-- 
GitLab


From 0e445e115f8f4f3d3de5b9199dc2da83d75b1f3c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 24 Aug 2023 12:22:46 +0200
Subject: [PATCH 1616/1806] samples/bpf: Remove the xdp_rxq_info utility
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The functionality of this utility has been incorporated into the xdp-bench
utility in xdp-tools, by way of the --rxq-stats argument to the 'drop',
'pass' and 'tx' commands of xdp-bench.

Some examples of how to convert xdp_rxq_info invocations into equivalent
xdp-bench commands:

xdp_rxq_info -d eth0
  --> xdp-bench pass --rxq-stats eth0

xdp_rxq_info -d eth0 -a XDP_DROP -m
  --> xdp-bench drop --rxq-stats -p swap-macs eth0

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20230824102255.1561885-4-toke@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile            |   3 -
 samples/bpf/xdp_rxq_info_kern.c | 140 --------
 samples/bpf/xdp_rxq_info_user.c | 614 --------------------------------
 3 files changed, 757 deletions(-)
 delete mode 100644 samples/bpf/xdp_rxq_info_kern.c
 delete mode 100644 samples/bpf/xdp_rxq_info_user.c

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index d2f5c043e4f37..fb1dc9d96b2a5 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -41,7 +41,6 @@ tprogs-y += lwt_len_hist
 tprogs-y += xdp_tx_iptunnel
 tprogs-y += test_map_in_map
 tprogs-y += per_socket_stats_example
-tprogs-y += xdp_rxq_info
 tprogs-y += syscall_tp
 tprogs-y += cpustat
 tprogs-y += xdp_adjust_tail
@@ -96,7 +95,6 @@ lwt_len_hist-objs := lwt_len_hist_user.o
 xdp_tx_iptunnel-objs := xdp_tx_iptunnel_user.o
 test_map_in_map-objs := test_map_in_map_user.o
 per_socket_stats_example-objs := cookie_uid_helper_example.o
-xdp_rxq_info-objs := xdp_rxq_info_user.o
 syscall_tp-objs := syscall_tp_user.o
 cpustat-objs := cpustat_user.o
 xdp_adjust_tail-objs := xdp_adjust_tail_user.o
@@ -151,7 +149,6 @@ always-y += tcp_clamp_kern.o
 always-y += tcp_basertt_kern.o
 always-y += tcp_tos_reflect_kern.o
 always-y += tcp_dumpstats_kern.o
-always-y += xdp_rxq_info_kern.o
 always-y += xdp2skb_meta_kern.o
 always-y += syscall_tp_kern.o
 always-y += cpustat_kern.o
diff --git a/samples/bpf/xdp_rxq_info_kern.c b/samples/bpf/xdp_rxq_info_kern.c
deleted file mode 100644
index 5e7459f9bf3e5..0000000000000
--- a/samples/bpf/xdp_rxq_info_kern.c
+++ /dev/null
@@ -1,140 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
- *
- *  Example howto extract XDP RX-queue info
- */
-#include <uapi/linux/bpf.h>
-#include <uapi/linux/if_ether.h>
-#include <uapi/linux/in.h>
-#include <bpf/bpf_helpers.h>
-
-/* Config setup from with userspace
- *
- * User-side setup ifindex in config_map, to verify that
- * ctx->ingress_ifindex is correct (against configured ifindex)
- */
-struct config {
-	__u32 action;
-	int ifindex;
-	__u32 options;
-};
-enum cfg_options_flags {
-	NO_TOUCH = 0x0U,
-	READ_MEM = 0x1U,
-	SWAP_MAC = 0x2U,
-};
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__type(key, int);
-	__type(value, struct config);
-	__uint(max_entries, 1);
-} config_map SEC(".maps");
-
-/* Common stats data record (shared with userspace) */
-struct datarec {
-	__u64 processed;
-	__u64 issue;
-};
-
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, struct datarec);
-	__uint(max_entries, 1);
-} stats_global_map SEC(".maps");
-
-#define MAX_RXQs 64
-
-/* Stats per rx_queue_index (per CPU) */
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, struct datarec);
-	__uint(max_entries, MAX_RXQs + 1);
-} rx_queue_index_map SEC(".maps");
-
-static __always_inline
-void swap_src_dst_mac(void *data)
-{
-	unsigned short *p = data;
-	unsigned short dst[3];
-
-	dst[0] = p[0];
-	dst[1] = p[1];
-	dst[2] = p[2];
-	p[0] = p[3];
-	p[1] = p[4];
-	p[2] = p[5];
-	p[3] = dst[0];
-	p[4] = dst[1];
-	p[5] = dst[2];
-}
-
-SEC("xdp_prog0")
-int  xdp_prognum0(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
-	struct datarec *rec, *rxq_rec;
-	int ingress_ifindex;
-	struct config *config;
-	u32 key = 0;
-
-	/* Global stats record */
-	rec = bpf_map_lookup_elem(&stats_global_map, &key);
-	if (!rec)
-		return XDP_ABORTED;
-	rec->processed++;
-
-	/* Accessing ctx->ingress_ifindex, cause BPF to rewrite BPF
-	 * instructions inside kernel to access xdp_rxq->dev->ifindex
-	 */
-	ingress_ifindex = ctx->ingress_ifindex;
-
-	config = bpf_map_lookup_elem(&config_map, &key);
-	if (!config)
-		return XDP_ABORTED;
-
-	/* Simple test: check ctx provided ifindex is as expected */
-	if (ingress_ifindex != config->ifindex) {
-		/* count this error case */
-		rec->issue++;
-		return XDP_ABORTED;
-	}
-
-	/* Update stats per rx_queue_index. Handle if rx_queue_index
-	 * is larger than stats map can contain info for.
-	 */
-	key = ctx->rx_queue_index;
-	if (key >= MAX_RXQs)
-		key = MAX_RXQs;
-	rxq_rec = bpf_map_lookup_elem(&rx_queue_index_map, &key);
-	if (!rxq_rec)
-		return XDP_ABORTED;
-	rxq_rec->processed++;
-	if (key == MAX_RXQs)
-		rxq_rec->issue++;
-
-	/* Default: Don't touch packet data, only count packets */
-	if (unlikely(config->options & (READ_MEM|SWAP_MAC))) {
-		struct ethhdr *eth = data;
-
-		if (eth + 1 > data_end)
-			return XDP_ABORTED;
-
-		/* Avoid compiler removing this: Drop non 802.3 Ethertypes */
-		if (ntohs(eth->h_proto) < ETH_P_802_3_MIN)
-			return XDP_ABORTED;
-
-		/* XDP_TX requires changing MAC-addrs, else HW may drop.
-		 * Can also be enabled with --swapmac (for test purposes)
-		 */
-		if (unlikely(config->options & SWAP_MAC))
-			swap_src_dst_mac(data);
-	}
-
-	return config->action;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
deleted file mode 100644
index b95e0ef61f065..0000000000000
--- a/samples/bpf/xdp_rxq_info_user.c
+++ /dev/null
@@ -1,614 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
- */
-static const char *__doc__ = " XDP RX-queue info extract example\n\n"
-	"Monitor how many packets per sec (pps) are received\n"
-	"per NIC RX queue index and which CPU processed the packet\n"
-	;
-
-#include <errno.h>
-#include <signal.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <stdbool.h>
-#include <string.h>
-#include <unistd.h>
-#include <locale.h>
-#include <getopt.h>
-#include <net/if.h>
-#include <time.h>
-#include <limits.h>
-#include <arpa/inet.h>
-#include <linux/if_link.h>
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-#include "bpf_util.h"
-
-static int ifindex = -1;
-static char ifname_buf[IF_NAMESIZE];
-static char *ifname;
-static __u32 prog_id;
-
-static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-
-static struct bpf_map *stats_global_map;
-static struct bpf_map *rx_queue_index_map;
-
-/* Exit return codes */
-#define EXIT_OK		0
-#define EXIT_FAIL		1
-#define EXIT_FAIL_OPTION	2
-#define EXIT_FAIL_XDP		3
-#define EXIT_FAIL_BPF		4
-#define EXIT_FAIL_MEM		5
-
-#define FAIL_MEM_SIG		INT_MAX
-#define FAIL_STAT_SIG		(INT_MAX - 1)
-
-static const struct option long_options[] = {
-	{"help",	no_argument,		NULL, 'h' },
-	{"dev",		required_argument,	NULL, 'd' },
-	{"skb-mode",	no_argument,		NULL, 'S' },
-	{"sec",		required_argument,	NULL, 's' },
-	{"no-separators", no_argument,		NULL, 'z' },
-	{"action",	required_argument,	NULL, 'a' },
-	{"readmem",	no_argument,		NULL, 'r' },
-	{"swapmac",	no_argument,		NULL, 'm' },
-	{"force",	no_argument,		NULL, 'F' },
-	{0, 0, NULL,  0 }
-};
-
-static void int_exit(int sig)
-{
-	__u32 curr_prog_id = 0;
-
-	if (ifindex > -1) {
-		if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) {
-			printf("bpf_xdp_query_id failed\n");
-			exit(EXIT_FAIL);
-		}
-		if (prog_id == curr_prog_id) {
-			fprintf(stderr,
-				"Interrupted: Removing XDP program on ifindex:%d device:%s\n",
-				ifindex, ifname);
-			bpf_xdp_detach(ifindex, xdp_flags, NULL);
-		} else if (!curr_prog_id) {
-			printf("couldn't find a prog id on a given iface\n");
-		} else {
-			printf("program on interface changed, not removing\n");
-		}
-	}
-
-	if (sig == FAIL_MEM_SIG)
-		exit(EXIT_FAIL_MEM);
-	else if (sig == FAIL_STAT_SIG)
-		exit(EXIT_FAIL);
-
-	exit(EXIT_OK);
-}
-
-struct config {
-	__u32 action;
-	int ifindex;
-	__u32 options;
-};
-enum cfg_options_flags {
-	NO_TOUCH = 0x0U,
-	READ_MEM = 0x1U,
-	SWAP_MAC = 0x2U,
-};
-#define XDP_ACTION_MAX (XDP_TX + 1)
-#define XDP_ACTION_MAX_STRLEN 11
-static const char *xdp_action_names[XDP_ACTION_MAX] = {
-	[XDP_ABORTED]	= "XDP_ABORTED",
-	[XDP_DROP]	= "XDP_DROP",
-	[XDP_PASS]	= "XDP_PASS",
-	[XDP_TX]	= "XDP_TX",
-};
-
-static const char *action2str(int action)
-{
-	if (action < XDP_ACTION_MAX)
-		return xdp_action_names[action];
-	return NULL;
-}
-
-static int parse_xdp_action(char *action_str)
-{
-	size_t maxlen;
-	__u64 action = -1;
-	int i;
-
-	for (i = 0; i < XDP_ACTION_MAX; i++) {
-		maxlen = XDP_ACTION_MAX_STRLEN;
-		if (strncmp(xdp_action_names[i], action_str, maxlen) == 0) {
-			action = i;
-			break;
-		}
-	}
-	return action;
-}
-
-static void list_xdp_actions(void)
-{
-	int i;
-
-	printf("Available XDP --action <options>\n");
-	for (i = 0; i < XDP_ACTION_MAX; i++)
-		printf("\t%s\n", xdp_action_names[i]);
-	printf("\n");
-}
-
-static char* options2str(enum cfg_options_flags flag)
-{
-	if (flag == NO_TOUCH)
-		return "no_touch";
-	if (flag & SWAP_MAC)
-		return "swapmac";
-	if (flag & READ_MEM)
-		return "read";
-	fprintf(stderr, "ERR: Unknown config option flags");
-	int_exit(FAIL_STAT_SIG);
-	return "unknown";
-}
-
-static void usage(char *argv[])
-{
-	int i;
-
-	printf("\nDOCUMENTATION:\n%s\n", __doc__);
-	printf(" Usage: %s (options-see-below)\n", argv[0]);
-	printf(" Listing options:\n");
-	for (i = 0; long_options[i].name != 0; i++) {
-		printf(" --%-12s", long_options[i].name);
-		if (long_options[i].flag != NULL)
-			printf(" flag (internal value:%d)",
-				*long_options[i].flag);
-		else
-			printf(" short-option: -%c",
-				long_options[i].val);
-		printf("\n");
-	}
-	printf("\n");
-	list_xdp_actions();
-}
-
-#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
-static __u64 gettime(void)
-{
-	struct timespec t;
-	int res;
-
-	res = clock_gettime(CLOCK_MONOTONIC, &t);
-	if (res < 0) {
-		fprintf(stderr, "Error with gettimeofday! (%i)\n", res);
-		int_exit(FAIL_STAT_SIG);
-	}
-	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
-}
-
-/* Common stats data record shared with _kern.c */
-struct datarec {
-	__u64 processed;
-	__u64 issue;
-};
-struct record {
-	__u64 timestamp;
-	struct datarec total;
-	struct datarec *cpu;
-};
-struct stats_record {
-	struct record stats;
-	struct record *rxq;
-};
-
-static struct datarec *alloc_record_per_cpu(void)
-{
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	struct datarec *array;
-
-	array = calloc(nr_cpus, sizeof(struct datarec));
-	if (!array) {
-		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
-		int_exit(FAIL_MEM_SIG);
-	}
-	return array;
-}
-
-static struct record *alloc_record_per_rxq(void)
-{
-	unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map);
-	struct record *array;
-
-	array = calloc(nr_rxqs, sizeof(struct record));
-	if (!array) {
-		fprintf(stderr, "Mem alloc error (nr_rxqs:%u)\n", nr_rxqs);
-		int_exit(FAIL_MEM_SIG);
-	}
-	return array;
-}
-
-static struct stats_record *alloc_stats_record(void)
-{
-	unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map);
-	struct stats_record *rec;
-	int i;
-
-	rec = calloc(1, sizeof(struct stats_record));
-	if (!rec) {
-		fprintf(stderr, "Mem alloc error\n");
-		int_exit(FAIL_MEM_SIG);
-	}
-	rec->rxq = alloc_record_per_rxq();
-	for (i = 0; i < nr_rxqs; i++)
-		rec->rxq[i].cpu = alloc_record_per_cpu();
-
-	rec->stats.cpu = alloc_record_per_cpu();
-	return rec;
-}
-
-static void free_stats_record(struct stats_record *r)
-{
-	unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map);
-	int i;
-
-	for (i = 0; i < nr_rxqs; i++)
-		free(r->rxq[i].cpu);
-
-	free(r->rxq);
-	free(r->stats.cpu);
-	free(r);
-}
-
-static bool map_collect_percpu(int fd, __u32 key, struct record *rec)
-{
-	/* For percpu maps, userspace gets a value per possible CPU */
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	struct datarec values[nr_cpus];
-	__u64 sum_processed = 0;
-	__u64 sum_issue = 0;
-	int i;
-
-	if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
-		fprintf(stderr,
-			"ERR: bpf_map_lookup_elem failed key:0x%X\n", key);
-		return false;
-	}
-	/* Get time as close as possible to reading map contents */
-	rec->timestamp = gettime();
-
-	/* Record and sum values from each CPU */
-	for (i = 0; i < nr_cpus; i++) {
-		rec->cpu[i].processed = values[i].processed;
-		sum_processed        += values[i].processed;
-		rec->cpu[i].issue = values[i].issue;
-		sum_issue        += values[i].issue;
-	}
-	rec->total.processed = sum_processed;
-	rec->total.issue     = sum_issue;
-	return true;
-}
-
-static void stats_collect(struct stats_record *rec)
-{
-	int fd, i, max_rxqs;
-
-	fd = bpf_map__fd(stats_global_map);
-	map_collect_percpu(fd, 0, &rec->stats);
-
-	fd = bpf_map__fd(rx_queue_index_map);
-	max_rxqs = bpf_map__max_entries(rx_queue_index_map);
-	for (i = 0; i < max_rxqs; i++)
-		map_collect_percpu(fd, i, &rec->rxq[i]);
-}
-
-static double calc_period(struct record *r, struct record *p)
-{
-	double period_ = 0;
-	__u64 period = 0;
-
-	period = r->timestamp - p->timestamp;
-	if (period > 0)
-		period_ = ((double) period / NANOSEC_PER_SEC);
-
-	return period_;
-}
-
-static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_)
-{
-	__u64 packets = 0;
-	__u64 pps = 0;
-
-	if (period_ > 0) {
-		packets = r->processed - p->processed;
-		pps = packets / period_;
-	}
-	return pps;
-}
-
-static __u64 calc_errs_pps(struct datarec *r,
-			    struct datarec *p, double period_)
-{
-	__u64 packets = 0;
-	__u64 pps = 0;
-
-	if (period_ > 0) {
-		packets = r->issue - p->issue;
-		pps = packets / period_;
-	}
-	return pps;
-}
-
-static void stats_print(struct stats_record *stats_rec,
-			struct stats_record *stats_prev,
-			int action, __u32 cfg_opt)
-{
-	unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map);
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	double pps = 0, err = 0;
-	struct record *rec, *prev;
-	double t;
-	int rxq;
-	int i;
-
-	/* Header */
-	printf("\nRunning XDP on dev:%s (ifindex:%d) action:%s options:%s\n",
-	       ifname, ifindex, action2str(action), options2str(cfg_opt));
-
-	/* stats_global_map */
-	{
-		char *fmt_rx = "%-15s %-7d %'-11.0f %'-10.0f %s\n";
-		char *fm2_rx = "%-15s %-7s %'-11.0f\n";
-		char *errstr = "";
-
-		printf("%-15s %-7s %-11s %-11s\n",
-		       "XDP stats", "CPU", "pps", "issue-pps");
-
-		rec  =  &stats_rec->stats;
-		prev = &stats_prev->stats;
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			pps = calc_pps     (r, p, t);
-			err = calc_errs_pps(r, p, t);
-			if (err > 0)
-				errstr = "invalid-ifindex";
-			if (pps > 0)
-				printf(fmt_rx, "XDP-RX CPU",
-					i, pps, err, errstr);
-		}
-		pps  = calc_pps     (&rec->total, &prev->total, t);
-		err  = calc_errs_pps(&rec->total, &prev->total, t);
-		printf(fm2_rx, "XDP-RX CPU", "total", pps, err);
-	}
-
-	/* rx_queue_index_map */
-	printf("\n%-15s %-7s %-11s %-11s\n",
-	       "RXQ stats", "RXQ:CPU", "pps", "issue-pps");
-
-	for (rxq = 0; rxq < nr_rxqs; rxq++) {
-		char *fmt_rx = "%-15s %3d:%-3d %'-11.0f %'-10.0f %s\n";
-		char *fm2_rx = "%-15s %3d:%-3s %'-11.0f\n";
-		char *errstr = "";
-		int rxq_ = rxq;
-
-		/* Last RXQ in map catch overflows */
-		if (rxq_ == nr_rxqs - 1)
-			rxq_ = -1;
-
-		rec  =  &stats_rec->rxq[rxq];
-		prev = &stats_prev->rxq[rxq];
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			pps = calc_pps     (r, p, t);
-			err = calc_errs_pps(r, p, t);
-			if (err > 0) {
-				if (rxq_ == -1)
-					errstr = "map-overflow-RXQ";
-				else
-					errstr = "err";
-			}
-			if (pps > 0)
-				printf(fmt_rx, "rx_queue_index",
-				       rxq_, i, pps, err, errstr);
-		}
-		pps  = calc_pps     (&rec->total, &prev->total, t);
-		err  = calc_errs_pps(&rec->total, &prev->total, t);
-		if (pps || err)
-			printf(fm2_rx, "rx_queue_index", rxq_, "sum", pps, err);
-	}
-}
-
-
-/* Pointer swap trick */
-static inline void swap(struct stats_record **a, struct stats_record **b)
-{
-	struct stats_record *tmp;
-
-	tmp = *a;
-	*a = *b;
-	*b = tmp;
-}
-
-static void stats_poll(int interval, int action, __u32 cfg_opt)
-{
-	struct stats_record *record, *prev;
-
-	record = alloc_stats_record();
-	prev   = alloc_stats_record();
-	stats_collect(record);
-
-	while (1) {
-		swap(&prev, &record);
-		stats_collect(record);
-		stats_print(record, prev, action, cfg_opt);
-		sleep(interval);
-	}
-
-	free_stats_record(record);
-	free_stats_record(prev);
-}
-
-
-int main(int argc, char **argv)
-{
-	__u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	int prog_fd, map_fd, opt, err;
-	bool use_separators = true;
-	struct config cfg = { 0 };
-	struct bpf_program *prog;
-	struct bpf_object *obj;
-	struct bpf_map *map;
-	char filename[256];
-	int longindex = 0;
-	int interval = 2;
-	__u32 key = 0;
-
-
-	char action_str_buf[XDP_ACTION_MAX_STRLEN + 1 /* for \0 */] = { 0 };
-	int action = XDP_PASS; /* Default action */
-	char *action_str = NULL;
-
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-
-	obj = bpf_object__open_file(filename, NULL);
-	if (libbpf_get_error(obj))
-		return EXIT_FAIL;
-
-	prog = bpf_object__next_program(obj, NULL);
-	bpf_program__set_type(prog, BPF_PROG_TYPE_XDP);
-
-	err = bpf_object__load(obj);
-	if (err)
-		return EXIT_FAIL;
-	prog_fd = bpf_program__fd(prog);
-
-	map =  bpf_object__find_map_by_name(obj, "config_map");
-	stats_global_map = bpf_object__find_map_by_name(obj, "stats_global_map");
-	rx_queue_index_map = bpf_object__find_map_by_name(obj, "rx_queue_index_map");
-	if (!map || !stats_global_map || !rx_queue_index_map) {
-		printf("finding a map in obj file failed\n");
-		return EXIT_FAIL;
-	}
-	map_fd = bpf_map__fd(map);
-
-	if (!prog_fd) {
-		fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n", strerror(errno));
-		return EXIT_FAIL;
-	}
-
-	/* Parse commands line args */
-	while ((opt = getopt_long(argc, argv, "FhSrmzd:s:a:",
-				  long_options, &longindex)) != -1) {
-		switch (opt) {
-		case 'd':
-			if (strlen(optarg) >= IF_NAMESIZE) {
-				fprintf(stderr, "ERR: --dev name too long\n");
-				goto error;
-			}
-			ifname = (char *)&ifname_buf;
-			strncpy(ifname, optarg, IF_NAMESIZE);
-			ifindex = if_nametoindex(ifname);
-			if (ifindex == 0) {
-				fprintf(stderr,
-					"ERR: --dev name unknown err(%d):%s\n",
-					errno, strerror(errno));
-				goto error;
-			}
-			break;
-		case 's':
-			interval = atoi(optarg);
-			break;
-		case 'S':
-			xdp_flags |= XDP_FLAGS_SKB_MODE;
-			break;
-		case 'z':
-			use_separators = false;
-			break;
-		case 'a':
-			action_str = (char *)&action_str_buf;
-			strncpy(action_str, optarg, XDP_ACTION_MAX_STRLEN);
-			break;
-		case 'r':
-			cfg_options |= READ_MEM;
-			break;
-		case 'm':
-			cfg_options |= SWAP_MAC;
-			break;
-		case 'F':
-			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
-			break;
-		case 'h':
-		error:
-		default:
-			usage(argv);
-			return EXIT_FAIL_OPTION;
-		}
-	}
-
-	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
-		xdp_flags |= XDP_FLAGS_DRV_MODE;
-
-	/* Required option */
-	if (ifindex == -1) {
-		fprintf(stderr, "ERR: required option --dev missing\n");
-		usage(argv);
-		return EXIT_FAIL_OPTION;
-	}
-	cfg.ifindex = ifindex;
-
-	/* Parse action string */
-	if (action_str) {
-		action = parse_xdp_action(action_str);
-		if (action < 0) {
-			fprintf(stderr, "ERR: Invalid XDP --action: %s\n",
-				action_str);
-			list_xdp_actions();
-			return EXIT_FAIL_OPTION;
-		}
-	}
-	cfg.action = action;
-
-	/* XDP_TX requires changing MAC-addrs, else HW may drop */
-	if (action == XDP_TX)
-		cfg_options |= SWAP_MAC;
-	cfg.options = cfg_options;
-
-	/* Trick to pretty printf with thousands separators use %' */
-	if (use_separators)
-		setlocale(LC_NUMERIC, "en_US");
-
-	/* User-side setup ifindex in config_map */
-	err = bpf_map_update_elem(map_fd, &key, &cfg, 0);
-	if (err) {
-		fprintf(stderr, "Store config failed (err:%d)\n", err);
-		exit(EXIT_FAIL_BPF);
-	}
-
-	/* Remove XDP program when program is interrupted or killed */
-	signal(SIGINT, int_exit);
-	signal(SIGTERM, int_exit);
-
-	if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) {
-		fprintf(stderr, "link set xdp fd failed\n");
-		return EXIT_FAIL_XDP;
-	}
-
-	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
-	if (err) {
-		printf("can't get prog info - %s\n", strerror(errno));
-		return err;
-	}
-	prog_id = info.id;
-
-	stats_poll(interval, action, cfg_options);
-	return EXIT_OK;
-}
-- 
GitLab


From eaca21d6eee9bb9b9f53c1c187d488ff1cbb6168 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 24 Aug 2023 12:22:47 +0200
Subject: [PATCH 1617/1806] samples/bpf: Remove the xdp1 and xdp2 utilities
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The functionality of these utilities have been incorporated into the
xdp-bench utility in xdp-tools.

Equivalent functionality is:

xdp1 eth0
  --> xdp-bench drop -p parse-ip -l load-bytes eth0

xdp2 eth0
  --> xdp-bench drop -p swap-macs eth0

Note that there's a slight difference in behaviour of those examples: the
swap-macs operation of xdp-bench doesn't use the bpf_xdp_load_bytes()
helper to load the packet data, whereas the xdp2 utility did so
unconditionally. For the parse-ip action the use of bpf_xdp_load_bytes()
can be selected by the '-l load-bytes' switch, with the difference that the
xdp-bench utility will perform two separate calls to the helper, one to
load the ethernet header and another to load the IP header; where the xdp1
utility only performed one call always loading 60 bytes of data.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20230824102255.1561885-5-toke@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile    |   7 --
 samples/bpf/xdp1_kern.c | 100 ------------------------
 samples/bpf/xdp1_user.c | 166 ----------------------------------------
 samples/bpf/xdp2_kern.c | 125 ------------------------------
 4 files changed, 398 deletions(-)
 delete mode 100644 samples/bpf/xdp1_kern.c
 delete mode 100644 samples/bpf/xdp1_user.c
 delete mode 100644 samples/bpf/xdp2_kern.c

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index fb1dc9d96b2a5..decd31167ee4a 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -30,8 +30,6 @@ tprogs-y += test_cgrp2_array_pin
 tprogs-y += test_cgrp2_attach
 tprogs-y += test_cgrp2_sock
 tprogs-y += test_cgrp2_sock2
-tprogs-y += xdp1
-tprogs-y += xdp2
 tprogs-y += xdp_router_ipv4
 tprogs-y += test_current_task_under_cgroup
 tprogs-y += trace_event
@@ -83,9 +81,6 @@ test_cgrp2_array_pin-objs := test_cgrp2_array_pin.o
 test_cgrp2_attach-objs := test_cgrp2_attach.o
 test_cgrp2_sock-objs := test_cgrp2_sock.o
 test_cgrp2_sock2-objs := test_cgrp2_sock2.o
-xdp1-objs := xdp1_user.o
-# reuse xdp1 source intentionally
-xdp2-objs := xdp1_user.o
 test_current_task_under_cgroup-objs := $(CGROUP_HELPERS) \
 				       test_current_task_under_cgroup_user.o
 trace_event-objs := trace_event_user.o $(TRACE_HELPERS)
@@ -132,8 +127,6 @@ always-y += test_overhead_raw_tp.bpf.o
 always-y += test_overhead_kprobe.bpf.o
 always-y += parse_varlen.o parse_simple.o parse_ldabs.o
 always-y += test_cgrp2_tc.bpf.o
-always-y += xdp1_kern.o
-always-y += xdp2_kern.o
 always-y += test_current_task_under_cgroup.bpf.o
 always-y += trace_event_kern.o
 always-y += sampleip_kern.o
diff --git a/samples/bpf/xdp1_kern.c b/samples/bpf/xdp1_kern.c
deleted file mode 100644
index d91f27cbcfa99..0000000000000
--- a/samples/bpf/xdp1_kern.c
+++ /dev/null
@@ -1,100 +0,0 @@
-/* Copyright (c) 2016 PLUMgrid
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- */
-#define KBUILD_MODNAME "foo"
-#include <uapi/linux/bpf.h>
-#include <linux/in.h>
-#include <linux/if_ether.h>
-#include <linux/if_packet.h>
-#include <linux/if_vlan.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <bpf/bpf_helpers.h>
-
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, long);
-	__uint(max_entries, 256);
-} rxcnt SEC(".maps");
-
-static int parse_ipv4(void *data, u64 nh_off, void *data_end)
-{
-	struct iphdr *iph = data + nh_off;
-
-	if (iph + 1 > data_end)
-		return 0;
-	return iph->protocol;
-}
-
-static int parse_ipv6(void *data, u64 nh_off, void *data_end)
-{
-	struct ipv6hdr *ip6h = data + nh_off;
-
-	if (ip6h + 1 > data_end)
-		return 0;
-	return ip6h->nexthdr;
-}
-
-#define XDPBUFSIZE	60
-SEC("xdp.frags")
-int xdp_prog1(struct xdp_md *ctx)
-{
-	__u8 pkt[XDPBUFSIZE] = {};
-	void *data_end = &pkt[XDPBUFSIZE-1];
-	void *data = pkt;
-	struct ethhdr *eth = data;
-	int rc = XDP_DROP;
-	long *value;
-	u16 h_proto;
-	u64 nh_off;
-	u32 ipproto;
-
-	if (bpf_xdp_load_bytes(ctx, 0, pkt, sizeof(pkt)))
-		return rc;
-
-	nh_off = sizeof(*eth);
-	if (data + nh_off > data_end)
-		return rc;
-
-	h_proto = eth->h_proto;
-
-	/* Handle VLAN tagged packet */
-	if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
-		struct vlan_hdr *vhdr;
-
-		vhdr = data + nh_off;
-		nh_off += sizeof(struct vlan_hdr);
-		if (data + nh_off > data_end)
-			return rc;
-		h_proto = vhdr->h_vlan_encapsulated_proto;
-	}
-	/* Handle double VLAN tagged packet */
-	if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
-		struct vlan_hdr *vhdr;
-
-		vhdr = data + nh_off;
-		nh_off += sizeof(struct vlan_hdr);
-		if (data + nh_off > data_end)
-			return rc;
-		h_proto = vhdr->h_vlan_encapsulated_proto;
-	}
-
-	if (h_proto == htons(ETH_P_IP))
-		ipproto = parse_ipv4(data, nh_off, data_end);
-	else if (h_proto == htons(ETH_P_IPV6))
-		ipproto = parse_ipv6(data, nh_off, data_end);
-	else
-		ipproto = 0;
-
-	value = bpf_map_lookup_elem(&rxcnt, &ipproto);
-	if (value)
-		*value += 1;
-
-	return rc;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
deleted file mode 100644
index f05e797013e96..0000000000000
--- a/samples/bpf/xdp1_user.c
+++ /dev/null
@@ -1,166 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (c) 2016 PLUMgrid
- */
-#include <linux/bpf.h>
-#include <linux/if_link.h>
-#include <assert.h>
-#include <errno.h>
-#include <signal.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <libgen.h>
-#include <net/if.h>
-
-#include "bpf_util.h"
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-static int ifindex;
-static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-static __u32 prog_id;
-
-static void int_exit(int sig)
-{
-	__u32 curr_prog_id = 0;
-
-	if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) {
-		printf("bpf_xdp_query_id failed\n");
-		exit(1);
-	}
-	if (prog_id == curr_prog_id)
-		bpf_xdp_detach(ifindex, xdp_flags, NULL);
-	else if (!curr_prog_id)
-		printf("couldn't find a prog id on a given interface\n");
-	else
-		printf("program on interface changed, not removing\n");
-	exit(0);
-}
-
-/* simple per-protocol drop counter
- */
-static void poll_stats(int map_fd, int interval)
-{
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	__u64 values[nr_cpus], prev[UINT8_MAX] = { 0 };
-	int i;
-
-	while (1) {
-		__u32 key = UINT32_MAX;
-
-		sleep(interval);
-
-		while (bpf_map_get_next_key(map_fd, &key, &key) == 0) {
-			__u64 sum = 0;
-
-			assert(bpf_map_lookup_elem(map_fd, &key, values) == 0);
-			for (i = 0; i < nr_cpus; i++)
-				sum += values[i];
-			if (sum > prev[key])
-				printf("proto %u: %10llu pkt/s\n",
-				       key, (sum - prev[key]) / interval);
-			prev[key] = sum;
-		}
-	}
-}
-
-static void usage(const char *prog)
-{
-	fprintf(stderr,
-		"usage: %s [OPTS] IFACE\n\n"
-		"OPTS:\n"
-		"    -S    use skb-mode\n"
-		"    -N    enforce native mode\n"
-		"    -F    force loading prog\n",
-		prog);
-}
-
-int main(int argc, char **argv)
-{
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	const char *optstr = "FSN";
-	int prog_fd, map_fd, opt;
-	struct bpf_program *prog;
-	struct bpf_object *obj;
-	struct bpf_map *map;
-	char filename[256];
-	int err;
-
-	while ((opt = getopt(argc, argv, optstr)) != -1) {
-		switch (opt) {
-		case 'S':
-			xdp_flags |= XDP_FLAGS_SKB_MODE;
-			break;
-		case 'N':
-			/* default, set below */
-			break;
-		case 'F':
-			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
-			break;
-		default:
-			usage(basename(argv[0]));
-			return 1;
-		}
-	}
-
-	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
-		xdp_flags |= XDP_FLAGS_DRV_MODE;
-
-	if (optind == argc) {
-		usage(basename(argv[0]));
-		return 1;
-	}
-
-	ifindex = if_nametoindex(argv[optind]);
-	if (!ifindex) {
-		perror("if_nametoindex");
-		return 1;
-	}
-
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-	obj = bpf_object__open_file(filename, NULL);
-	if (libbpf_get_error(obj))
-		return 1;
-
-	prog = bpf_object__next_program(obj, NULL);
-	bpf_program__set_type(prog, BPF_PROG_TYPE_XDP);
-
-	err = bpf_object__load(obj);
-	if (err)
-		return 1;
-
-	prog_fd = bpf_program__fd(prog);
-
-	map = bpf_object__next_map(obj, NULL);
-	if (!map) {
-		printf("finding a map in obj file failed\n");
-		return 1;
-	}
-	map_fd = bpf_map__fd(map);
-
-	if (!prog_fd) {
-		printf("bpf_prog_load_xattr: %s\n", strerror(errno));
-		return 1;
-	}
-
-	signal(SIGINT, int_exit);
-	signal(SIGTERM, int_exit);
-
-	if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) {
-		printf("link set xdp fd failed\n");
-		return 1;
-	}
-
-	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
-	if (err) {
-		printf("can't get prog info - %s\n", strerror(errno));
-		return err;
-	}
-	prog_id = info.id;
-
-	poll_stats(map_fd, 1);
-
-	return 0;
-}
diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c
deleted file mode 100644
index 8bca674451ed1..0000000000000
--- a/samples/bpf/xdp2_kern.c
+++ /dev/null
@@ -1,125 +0,0 @@
-/* Copyright (c) 2016 PLUMgrid
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- */
-#define KBUILD_MODNAME "foo"
-#include <uapi/linux/bpf.h>
-#include <linux/in.h>
-#include <linux/if_ether.h>
-#include <linux/if_packet.h>
-#include <linux/if_vlan.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <bpf/bpf_helpers.h>
-
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, long);
-	__uint(max_entries, 256);
-} rxcnt SEC(".maps");
-
-static void swap_src_dst_mac(void *data)
-{
-	unsigned short *p = data;
-	unsigned short dst[3];
-
-	dst[0] = p[0];
-	dst[1] = p[1];
-	dst[2] = p[2];
-	p[0] = p[3];
-	p[1] = p[4];
-	p[2] = p[5];
-	p[3] = dst[0];
-	p[4] = dst[1];
-	p[5] = dst[2];
-}
-
-static int parse_ipv4(void *data, u64 nh_off, void *data_end)
-{
-	struct iphdr *iph = data + nh_off;
-
-	if (iph + 1 > data_end)
-		return 0;
-	return iph->protocol;
-}
-
-static int parse_ipv6(void *data, u64 nh_off, void *data_end)
-{
-	struct ipv6hdr *ip6h = data + nh_off;
-
-	if (ip6h + 1 > data_end)
-		return 0;
-	return ip6h->nexthdr;
-}
-
-#define XDPBUFSIZE	60
-SEC("xdp.frags")
-int xdp_prog1(struct xdp_md *ctx)
-{
-	__u8 pkt[XDPBUFSIZE] = {};
-	void *data_end = &pkt[XDPBUFSIZE-1];
-	void *data = pkt;
-	struct ethhdr *eth = data;
-	int rc = XDP_DROP;
-	long *value;
-	u16 h_proto;
-	u64 nh_off;
-	u32 ipproto;
-
-	if (bpf_xdp_load_bytes(ctx, 0, pkt, sizeof(pkt)))
-		return rc;
-
-	nh_off = sizeof(*eth);
-	if (data + nh_off > data_end)
-		return rc;
-
-	h_proto = eth->h_proto;
-
-	/* Handle VLAN tagged packet */
-	if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
-		struct vlan_hdr *vhdr;
-
-		vhdr = data + nh_off;
-		nh_off += sizeof(struct vlan_hdr);
-		if (data + nh_off > data_end)
-			return rc;
-		h_proto = vhdr->h_vlan_encapsulated_proto;
-	}
-	/* Handle double VLAN tagged packet */
-	if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
-		struct vlan_hdr *vhdr;
-
-		vhdr = data + nh_off;
-		nh_off += sizeof(struct vlan_hdr);
-		if (data + nh_off > data_end)
-			return rc;
-		h_proto = vhdr->h_vlan_encapsulated_proto;
-	}
-
-	if (h_proto == htons(ETH_P_IP))
-		ipproto = parse_ipv4(data, nh_off, data_end);
-	else if (h_proto == htons(ETH_P_IPV6))
-		ipproto = parse_ipv6(data, nh_off, data_end);
-	else
-		ipproto = 0;
-
-	value = bpf_map_lookup_elem(&rxcnt, &ipproto);
-	if (value)
-		*value += 1;
-
-	if (ipproto == IPPROTO_UDP) {
-		swap_src_dst_mac(data);
-
-		if (bpf_xdp_store_bytes(ctx, 0, pkt, sizeof(pkt)))
-			return rc;
-
-		rc = XDP_TX;
-	}
-
-	return rc;
-}
-
-char _license[] SEC("license") = "GPL";
-- 
GitLab


From cced0699cbf1ebfb39234d764ade2f907c5ca0b5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 24 Aug 2023 12:22:48 +0200
Subject: [PATCH 1618/1806] samples/bpf: Remove the xdp_sample_pkts utility
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The functionality of this utility is covered by the xdpdump utility in
xdp-tools.

There's a slight difference in usage as the xdpdump utility's main focus is
to dump packets before or after they are processed by an existing XDP
program. However, xdpdump also has the --load-xdp-program switch, which
will make it attach its own program if no existing program is loaded. With
this, xdp_sample_pkts usage can be converted as:

xdp_sample_pkts eth0
  --> xdpdump --load-xdp-program eth0

To get roughly equivalent behaviour.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20230824102255.1561885-6-toke@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile               |   3 -
 samples/bpf/xdp_sample_pkts_kern.c |  57 ---------
 samples/bpf/xdp_sample_pkts_user.c | 196 -----------------------------
 3 files changed, 256 deletions(-)
 delete mode 100644 samples/bpf/xdp_sample_pkts_kern.c
 delete mode 100644 samples/bpf/xdp_sample_pkts_user.c

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index decd31167ee4a..4ccf4236031c1 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -44,7 +44,6 @@ tprogs-y += cpustat
 tprogs-y += xdp_adjust_tail
 tprogs-y += xdp_fwd
 tprogs-y += task_fd_query
-tprogs-y += xdp_sample_pkts
 tprogs-y += ibumad
 tprogs-y += hbm
 
@@ -95,7 +94,6 @@ cpustat-objs := cpustat_user.o
 xdp_adjust_tail-objs := xdp_adjust_tail_user.o
 xdp_fwd-objs := xdp_fwd_user.o
 task_fd_query-objs := task_fd_query_user.o $(TRACE_HELPERS)
-xdp_sample_pkts-objs := xdp_sample_pkts_user.o
 ibumad-objs := ibumad_user.o
 hbm-objs := hbm.o $(CGROUP_HELPERS)
 
@@ -148,7 +146,6 @@ always-y += cpustat_kern.o
 always-y += xdp_adjust_tail_kern.o
 always-y += xdp_fwd_kern.o
 always-y += task_fd_query_kern.o
-always-y += xdp_sample_pkts_kern.o
 always-y += ibumad_kern.o
 always-y += hbm_out_kern.o
 always-y += hbm_edt_kern.o
diff --git a/samples/bpf/xdp_sample_pkts_kern.c b/samples/bpf/xdp_sample_pkts_kern.c
deleted file mode 100644
index 9cf76b340dd7f..0000000000000
--- a/samples/bpf/xdp_sample_pkts_kern.c
+++ /dev/null
@@ -1,57 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/ptrace.h>
-#include <linux/version.h>
-#include <uapi/linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-
-#define SAMPLE_SIZE 64ul
-
-struct {
-	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(u32));
-} my_map SEC(".maps");
-
-SEC("xdp_sample")
-int xdp_sample_prog(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data = (void *)(long)ctx->data;
-
-	/* Metadata will be in the perf event before the packet data. */
-	struct S {
-		u16 cookie;
-		u16 pkt_len;
-	} __packed metadata;
-
-	if (data < data_end) {
-		/* The XDP perf_event_output handler will use the upper 32 bits
-		 * of the flags argument as a number of bytes to include of the
-		 * packet payload in the event data. If the size is too big, the
-		 * call to bpf_perf_event_output will fail and return -EFAULT.
-		 *
-		 * See bpf_xdp_event_output in net/core/filter.c.
-		 *
-		 * The BPF_F_CURRENT_CPU flag means that the event output fd
-		 * will be indexed by the CPU number in the event map.
-		 */
-		u64 flags = BPF_F_CURRENT_CPU;
-		u16 sample_size;
-		int ret;
-
-		metadata.cookie = 0xdead;
-		metadata.pkt_len = (u16)(data_end - data);
-		sample_size = min(metadata.pkt_len, SAMPLE_SIZE);
-		flags |= (u64)sample_size << 32;
-
-		ret = bpf_perf_event_output(ctx, &my_map, flags,
-					    &metadata, sizeof(metadata));
-		if (ret)
-			bpf_printk("perf_event_output failed: %d\n", ret);
-	}
-
-	return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
-u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c
deleted file mode 100644
index e39d7f654f304..0000000000000
--- a/samples/bpf/xdp_sample_pkts_user.c
+++ /dev/null
@@ -1,196 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <linux/perf_event.h>
-#include <linux/bpf.h>
-#include <net/if.h>
-#include <errno.h>
-#include <assert.h>
-#include <sys/sysinfo.h>
-#include <sys/ioctl.h>
-#include <signal.h>
-#include <bpf/libbpf.h>
-#include <bpf/bpf.h>
-#include <libgen.h>
-#include <linux/if_link.h>
-
-#include "perf-sys.h"
-
-static int if_idx;
-static char *if_name;
-static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-static __u32 prog_id;
-static struct perf_buffer *pb = NULL;
-
-static int do_attach(int idx, int fd, const char *name)
-{
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	int err;
-
-	err = bpf_xdp_attach(idx, fd, xdp_flags, NULL);
-	if (err < 0) {
-		printf("ERROR: failed to attach program to %s\n", name);
-		return err;
-	}
-
-	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
-	if (err) {
-		printf("can't get prog info - %s\n", strerror(errno));
-		return err;
-	}
-	prog_id = info.id;
-
-	return err;
-}
-
-static int do_detach(int idx, const char *name)
-{
-	__u32 curr_prog_id = 0;
-	int err = 0;
-
-	err = bpf_xdp_query_id(idx, xdp_flags, &curr_prog_id);
-	if (err) {
-		printf("bpf_xdp_query_id failed\n");
-		return err;
-	}
-	if (prog_id == curr_prog_id) {
-		err = bpf_xdp_detach(idx, xdp_flags, NULL);
-		if (err < 0)
-			printf("ERROR: failed to detach prog from %s\n", name);
-	} else if (!curr_prog_id) {
-		printf("couldn't find a prog id on a %s\n", name);
-	} else {
-		printf("program on interface changed, not removing\n");
-	}
-
-	return err;
-}
-
-#define SAMPLE_SIZE 64
-
-static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size)
-{
-	struct {
-		__u16 cookie;
-		__u16 pkt_len;
-		__u8  pkt_data[SAMPLE_SIZE];
-	} __packed *e = data;
-	int i;
-
-	if (e->cookie != 0xdead) {
-		printf("BUG cookie %x sized %d\n", e->cookie, size);
-		return;
-	}
-
-	printf("Pkt len: %-5d bytes. Ethernet hdr: ", e->pkt_len);
-	for (i = 0; i < 14 && i < e->pkt_len; i++)
-		printf("%02x ", e->pkt_data[i]);
-	printf("\n");
-}
-
-static void sig_handler(int signo)
-{
-	do_detach(if_idx, if_name);
-	perf_buffer__free(pb);
-	exit(0);
-}
-
-static void usage(const char *prog)
-{
-	fprintf(stderr,
-		"%s: %s [OPTS] <ifname|ifindex>\n\n"
-		"OPTS:\n"
-		"    -F    force loading prog\n"
-		"    -S    use skb-mode\n",
-		__func__, prog);
-}
-
-int main(int argc, char **argv)
-{
-	const char *optstr = "FS";
-	int prog_fd, map_fd, opt;
-	struct bpf_program *prog;
-	struct bpf_object *obj;
-	struct bpf_map *map;
-	char filename[256];
-	int ret, err;
-
-	while ((opt = getopt(argc, argv, optstr)) != -1) {
-		switch (opt) {
-		case 'F':
-			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
-			break;
-		case 'S':
-			xdp_flags |= XDP_FLAGS_SKB_MODE;
-			break;
-		default:
-			usage(basename(argv[0]));
-			return 1;
-		}
-	}
-
-	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
-		xdp_flags |= XDP_FLAGS_DRV_MODE;
-
-	if (optind == argc) {
-		usage(basename(argv[0]));
-		return 1;
-	}
-
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-
-	obj = bpf_object__open_file(filename, NULL);
-	if (libbpf_get_error(obj))
-		return 1;
-
-	prog = bpf_object__next_program(obj, NULL);
-	bpf_program__set_type(prog, BPF_PROG_TYPE_XDP);
-
-	err = bpf_object__load(obj);
-	if (err)
-		return 1;
-
-	prog_fd = bpf_program__fd(prog);
-
-	map = bpf_object__next_map(obj, NULL);
-	if (!map) {
-		printf("finding a map in obj file failed\n");
-		return 1;
-	}
-	map_fd = bpf_map__fd(map);
-
-	if_idx = if_nametoindex(argv[optind]);
-	if (!if_idx)
-		if_idx = strtoul(argv[optind], NULL, 0);
-
-	if (!if_idx) {
-		fprintf(stderr, "Invalid ifname\n");
-		return 1;
-	}
-	if_name = argv[optind];
-	err = do_attach(if_idx, prog_fd, if_name);
-	if (err)
-		return err;
-
-	if (signal(SIGINT, sig_handler) ||
-	    signal(SIGHUP, sig_handler) ||
-	    signal(SIGTERM, sig_handler)) {
-		perror("signal");
-		return 1;
-	}
-
-	pb = perf_buffer__new(map_fd, 8, print_bpf_output, NULL, NULL, NULL);
-	err = libbpf_get_error(pb);
-	if (err) {
-		perror("perf_buffer setup failed");
-		return 1;
-	}
-
-	while ((ret = perf_buffer__poll(pb, 1000)) >= 0) {
-	}
-
-	kill(0, SIGINT);
-	return ret;
-}
-- 
GitLab


From 91b965136d536a981ed22097bc2b72625f5c4211 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 24 Aug 2023 12:22:49 +0200
Subject: [PATCH 1619/1806] samples/bpf: Cleanup .gitignore
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove no longer present XDP utilities from .gitignore. Apart from the
recently removed XDP utilities this also includes the previously removed
xdpsock and xsk utilities.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20230824102255.1561885-7-toke@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/.gitignore | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore
index 0e7bfdbff80a6..0002cd359fb11 100644
--- a/samples/bpf/.gitignore
+++ b/samples/bpf/.gitignore
@@ -37,22 +37,10 @@ tracex4
 tracex5
 tracex6
 tracex7
-xdp1
-xdp2
 xdp_adjust_tail
 xdp_fwd
-xdp_monitor
-xdp_redirect
-xdp_redirect_cpu
-xdp_redirect_map
-xdp_redirect_map_multi
 xdp_router_ipv4
-xdp_rxq_info
-xdp_sample_pkts
 xdp_tx_iptunnel
-xdpsock
-xdpsock_ctrl_proc
-xsk_fwd
 testfile.img
 hbm_out.log
 iperf.*
-- 
GitLab


From 5a9fd0f778ebb2076fa1098df23e741c794d9992 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 24 Aug 2023 12:22:50 +0200
Subject: [PATCH 1620/1806] samples/bpf: Add note to README about the XDP
 utilities moved to xdp-tools
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To help users find the XDP utilities, add a note to the README about the
new location and the conversion documentation in the commit messages.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20230824102255.1561885-8-toke@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/README.rst | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst
index f16fc48e55a5d..cabe2d2169972 100644
--- a/samples/bpf/README.rst
+++ b/samples/bpf/README.rst
@@ -4,6 +4,12 @@ eBPF sample programs
 This directory contains a test stubs, verifier test-suite and examples
 for using eBPF. The examples use libbpf from tools/lib/bpf.
 
+Note that the XDP-specific samples have been removed from this directory and
+moved to the xdp-tools repository: https://github.com/xdp-project/xdp-tools
+See the commit messages removing each tool from this directory for how to
+convert specific command invocations between the old samples and the utilities
+in xdp-tools.
+
 Build dependencies
 ==================
 
-- 
GitLab


From 469fb2c3c1bbaa092f541e3a8d3b3554042aa6a5 Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Thu, 24 Aug 2023 09:49:55 +0000
Subject: [PATCH 1621/1806] riscv, bpf: Fix missing exception handling and
 redundant zext for LDX_B/H/W

For LDX_B/H/W, when zext has been inserted by verifier, it'll return 1,
and no exception handling will continue. Also, when the offset is 12-bit
value, the redundant zext inserted by the verifier is not removed. Fix
both scenarios by moving down the removal of redundant zext.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
Link: https://lore.kernel.org/r/20230824095001.3408573-2-pulehui@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/net/bpf_jit_comp64.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 0ca4f5c0097c6..f2644e7ea6b59 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1512,8 +1512,6 @@ out_be:
 			insns_start = ctx->ninsns;
 			emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
 			insn_len = ctx->ninsns - insns_start;
-			if (insn_is_zext(&insn[1]))
-				return 1;
 			break;
 		case BPF_H:
 			if (is_12b_int(off)) {
@@ -1528,8 +1526,6 @@ out_be:
 			insns_start = ctx->ninsns;
 			emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
 			insn_len = ctx->ninsns - insns_start;
-			if (insn_is_zext(&insn[1]))
-				return 1;
 			break;
 		case BPF_W:
 			if (is_12b_int(off)) {
@@ -1544,8 +1540,6 @@ out_be:
 			insns_start = ctx->ninsns;
 			emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
 			insn_len = ctx->ninsns - insns_start;
-			if (insn_is_zext(&insn[1]))
-				return 1;
 			break;
 		case BPF_DW:
 			if (is_12b_int(off)) {
@@ -1566,6 +1560,9 @@ out_be:
 		ret = add_exception_handler(insn, ctx, rd, insn_len);
 		if (ret)
 			return ret;
+
+		if (BPF_SIZE(code) != BPF_DW && insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	}
 	/* speculation barrier */
-- 
GitLab


From 3d06d8163f98594dfb950c3aeae9f798e4fb45c7 Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Thu, 24 Aug 2023 09:49:56 +0000
Subject: [PATCH 1622/1806] riscv, bpf: Support sign-extension load insns
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add Support sign-extension load instructions for RV64.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/r/20230824095001.3408573-3-pulehui@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/net/bpf_jit.h        | 10 +++++++
 arch/riscv/net/bpf_jit_comp64.c | 46 +++++++++++++++++++++++++++------
 2 files changed, 48 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 2717f54904287..a52a3dda18c30 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -501,6 +501,16 @@ static inline u32 rv_ble(u8 rs1, u8 rs2, u16 imm12_1)
 	return rv_bge(rs2, rs1, imm12_1);
 }
 
+static inline u32 rv_lb(u8 rd, u16 imm11_0, u8 rs1)
+{
+	return rv_i_insn(imm11_0, rs1, 0, rd, 0x03);
+}
+
+static inline u32 rv_lh(u8 rd, u16 imm11_0, u8 rs1)
+{
+	return rv_i_insn(imm11_0, rs1, 1, rd, 0x03);
+}
+
 static inline u32 rv_lw(u8 rd, u16 imm11_0, u8 rs1)
 {
 	return rv_i_insn(imm11_0, rs1, 2, rd, 0x03);
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index f2644e7ea6b59..fd36cb17101aa 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -580,7 +580,8 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	unsigned long pc;
 	off_t offset;
 
-	if (!ctx->insns || !ctx->prog->aux->extable || BPF_MODE(insn->code) != BPF_PROBE_MEM)
+	if (!ctx->insns || !ctx->prog->aux->extable ||
+	    (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX))
 		return 0;
 
 	if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries))
@@ -1486,7 +1487,7 @@ out_be:
 		return 1;
 	}
 
-	/* LDX: dst = *(size *)(src + off) */
+	/* LDX: dst = *(unsigned size *)(src + off) */
 	case BPF_LDX | BPF_MEM | BPF_B:
 	case BPF_LDX | BPF_MEM | BPF_H:
 	case BPF_LDX | BPF_MEM | BPF_W:
@@ -1495,14 +1496,28 @@ out_be:
 	case BPF_LDX | BPF_PROBE_MEM | BPF_H:
 	case BPF_LDX | BPF_PROBE_MEM | BPF_W:
 	case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+	/* LDSX: dst = *(signed size *)(src + off) */
+	case BPF_LDX | BPF_MEMSX | BPF_B:
+	case BPF_LDX | BPF_MEMSX | BPF_H:
+	case BPF_LDX | BPF_MEMSX | BPF_W:
+	case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
+	case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
+	case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
 	{
 		int insn_len, insns_start;
+		bool sign_ext;
+
+		sign_ext = BPF_MODE(insn->code) == BPF_MEMSX ||
+			   BPF_MODE(insn->code) == BPF_PROBE_MEMSX;
 
 		switch (BPF_SIZE(code)) {
 		case BPF_B:
 			if (is_12b_int(off)) {
 				insns_start = ctx->ninsns;
-				emit(rv_lbu(rd, off, rs), ctx);
+				if (sign_ext)
+					emit(rv_lb(rd, off, rs), ctx);
+				else
+					emit(rv_lbu(rd, off, rs), ctx);
 				insn_len = ctx->ninsns - insns_start;
 				break;
 			}
@@ -1510,13 +1525,19 @@ out_be:
 			emit_imm(RV_REG_T1, off, ctx);
 			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
 			insns_start = ctx->ninsns;
-			emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
+			if (sign_ext)
+				emit(rv_lb(rd, 0, RV_REG_T1), ctx);
+			else
+				emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
 			insn_len = ctx->ninsns - insns_start;
 			break;
 		case BPF_H:
 			if (is_12b_int(off)) {
 				insns_start = ctx->ninsns;
-				emit(rv_lhu(rd, off, rs), ctx);
+				if (sign_ext)
+					emit(rv_lh(rd, off, rs), ctx);
+				else
+					emit(rv_lhu(rd, off, rs), ctx);
 				insn_len = ctx->ninsns - insns_start;
 				break;
 			}
@@ -1524,13 +1545,19 @@ out_be:
 			emit_imm(RV_REG_T1, off, ctx);
 			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
 			insns_start = ctx->ninsns;
-			emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
+			if (sign_ext)
+				emit(rv_lh(rd, 0, RV_REG_T1), ctx);
+			else
+				emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
 			insn_len = ctx->ninsns - insns_start;
 			break;
 		case BPF_W:
 			if (is_12b_int(off)) {
 				insns_start = ctx->ninsns;
-				emit(rv_lwu(rd, off, rs), ctx);
+				if (sign_ext)
+					emit(rv_lw(rd, off, rs), ctx);
+				else
+					emit(rv_lwu(rd, off, rs), ctx);
 				insn_len = ctx->ninsns - insns_start;
 				break;
 			}
@@ -1538,7 +1565,10 @@ out_be:
 			emit_imm(RV_REG_T1, off, ctx);
 			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
 			insns_start = ctx->ninsns;
-			emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
+			if (sign_ext)
+				emit(rv_lw(rd, 0, RV_REG_T1), ctx);
+			else
+				emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
 			insn_len = ctx->ninsns - insns_start;
 			break;
 		case BPF_DW:
-- 
GitLab


From 694896ad3ca79b3291efaf29702a94d2568b5279 Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Thu, 24 Aug 2023 09:49:57 +0000
Subject: [PATCH 1623/1806] riscv, bpf: Support sign-extension mov insns
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support sign-extension mov instructions for RV64.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/r/20230824095001.3408573-4-pulehui@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/net/bpf_jit_comp64.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index fd36cb17101aa..bcf1e7509cb98 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1047,7 +1047,19 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_zext_32(rd, ctx);
 			break;
 		}
-		emit_mv(rd, rs, ctx);
+		switch (insn->off) {
+		case 0:
+			emit_mv(rd, rs, ctx);
+			break;
+		case 8:
+		case 16:
+			emit_slli(RV_REG_T1, rs, 64 - insn->off, ctx);
+			emit_srai(rd, RV_REG_T1, 64 - insn->off, ctx);
+			break;
+		case 32:
+			emit_addiw(rd, rs, 0, ctx);
+			break;
+		}
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
-- 
GitLab


From d9839f16c1502556993552746452c862cb1c41af Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Thu, 24 Aug 2023 09:49:58 +0000
Subject: [PATCH 1624/1806] riscv, bpf: Support 32-bit offset jmp insn
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support 32-bit offset jmp instruction for RV64.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/r/20230824095001.3408573-5-pulehui@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/net/bpf_jit_comp64.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index bcf1e7509cb98..076619f4aa824 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1327,7 +1327,11 @@ out_be:
 
 	/* JUMP off */
 	case BPF_JMP | BPF_JA:
-		rvoff = rv_offset(i, off, ctx);
+	case BPF_JMP32 | BPF_JA:
+		if (BPF_CLASS(code) == BPF_JMP)
+			rvoff = rv_offset(i, off, ctx);
+		else
+			rvoff = rv_offset(i, imm, ctx);
 		ret = emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx);
 		if (ret)
 			return ret;
-- 
GitLab


From 3e18ff4bce9b50d351479bb4baee6e8305e98a5b Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Thu, 24 Aug 2023 09:49:59 +0000
Subject: [PATCH 1625/1806] riscv, bpf: Support signed div/mod insns
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support signed div/mod instructions for RV64.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/r/20230824095001.3408573-6-pulehui@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/net/bpf_jit.h        | 20 ++++++++++++++++++++
 arch/riscv/net/bpf_jit_comp64.c | 26 ++++++++++++++++++++------
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index a52a3dda18c30..d21c6c92a683d 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -431,11 +431,21 @@ static inline u32 rv_mulhu(u8 rd, u8 rs1, u8 rs2)
 	return rv_r_insn(1, rs2, rs1, 3, rd, 0x33);
 }
 
+static inline u32 rv_div(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 4, rd, 0x33);
+}
+
 static inline u32 rv_divu(u8 rd, u8 rs1, u8 rs2)
 {
 	return rv_r_insn(1, rs2, rs1, 5, rd, 0x33);
 }
 
+static inline u32 rv_rem(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 6, rd, 0x33);
+}
+
 static inline u32 rv_remu(u8 rd, u8 rs1, u8 rs2)
 {
 	return rv_r_insn(1, rs2, rs1, 7, rd, 0x33);
@@ -776,11 +786,21 @@ static inline u32 rv_mulw(u8 rd, u8 rs1, u8 rs2)
 	return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b);
 }
 
+static inline u32 rv_divw(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 4, rd, 0x3b);
+}
+
 static inline u32 rv_divuw(u8 rd, u8 rs1, u8 rs2)
 {
 	return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b);
 }
 
+static inline u32 rv_remw(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(1, rs2, rs1, 6, rd, 0x3b);
+}
+
 static inline u32 rv_remuw(u8 rd, u8 rs1, u8 rs2)
 {
 	return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b);
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 076619f4aa824..ba4535ac194fd 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1107,13 +1107,19 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
-		emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx);
+		if (off)
+			emit(is64 ? rv_div(rd, rd, rs) : rv_divw(rd, rd, rs), ctx);
+		else
+			emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx);
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
-		emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx);
+		if (off)
+			emit(is64 ? rv_rem(rd, rd, rs) : rv_remw(rd, rd, rs), ctx);
+		else
+			emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx);
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
@@ -1284,16 +1290,24 @@ out_be:
 	case BPF_ALU | BPF_DIV | BPF_K:
 	case BPF_ALU64 | BPF_DIV | BPF_K:
 		emit_imm(RV_REG_T1, imm, ctx);
-		emit(is64 ? rv_divu(rd, rd, RV_REG_T1) :
-		     rv_divuw(rd, rd, RV_REG_T1), ctx);
+		if (off)
+			emit(is64 ? rv_div(rd, rd, RV_REG_T1) :
+			     rv_divw(rd, rd, RV_REG_T1), ctx);
+		else
+			emit(is64 ? rv_divu(rd, rd, RV_REG_T1) :
+			     rv_divuw(rd, rd, RV_REG_T1), ctx);
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_K:
 	case BPF_ALU64 | BPF_MOD | BPF_K:
 		emit_imm(RV_REG_T1, imm, ctx);
-		emit(is64 ? rv_remu(rd, rd, RV_REG_T1) :
-		     rv_remuw(rd, rd, RV_REG_T1), ctx);
+		if (off)
+			emit(is64 ? rv_rem(rd, rd, RV_REG_T1) :
+			     rv_remw(rd, rd, RV_REG_T1), ctx);
+		else
+			emit(is64 ? rv_remu(rd, rd, RV_REG_T1) :
+			     rv_remuw(rd, rd, RV_REG_T1), ctx);
 		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
-- 
GitLab


From 83cc63afab718c5a31ce94d3e7f3827acc501042 Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Thu, 24 Aug 2023 09:50:00 +0000
Subject: [PATCH 1626/1806] riscv, bpf: Support unconditional bswap insn
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support unconditional bswap instruction. Since riscv is always
little-endian, just treat the unconditional scenario the same as
big-endian conversion.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/r/20230824095001.3408573-7-pulehui@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/net/bpf_jit_comp64.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index ba4535ac194fd..8423f4ddf8f5f 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1168,6 +1168,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		break;
 
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
+	case BPF_ALU64 | BPF_END | BPF_FROM_LE:
 		emit_li(RV_REG_T2, 0, ctx);
 
 		emit_andi(RV_REG_T1, rd, 0xff, ctx);
-- 
GitLab


From 0209fd511fa4371f49d6e38f25a258831bb90391 Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Thu, 24 Aug 2023 09:50:01 +0000
Subject: [PATCH 1627/1806] selftests/bpf: Enable cpu v4 tests for RV64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Enable cpu v4 tests for RV64, and the relevant tests have passed.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/r/20230824095001.3408573-8-pulehui@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/test_ldsx_insn.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_bswap.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_gotol.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_ldsx.c  | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_movsx.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_sdiv.c  | 3 ++-
 6 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
index 916d9435f12ce..67c14ba1e87b4 100644
--- a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
+++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
@@ -5,7 +5,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
 const volatile int skip = 0;
 #else
 const volatile int skip = 1;
diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
index 770f9d8825421..8893094725f0e 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bswap.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -4,7 +4,8 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
 
 SEC("socket")
 __description("BSWAP, 16")
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index 17319a505e87d..2dae5322a18e5 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -4,7 +4,8 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
 
 SEC("socket")
 __description("gotol, small_imm")
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index 4a2b567c0f699..0c638f45aaf16 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -4,7 +4,8 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
 
 SEC("socket")
 __description("LDSX, S8")
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
index d9528d578bd90..3c8ac2c57b1b5 100644
--- a/tools/testing/selftests/bpf/progs/verifier_movsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -4,7 +4,8 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
 
 SEC("socket")
 __description("MOV32SX, S8")
diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
index fa3945930e938..0990f88256758 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sdiv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -4,7 +4,8 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) && __clang_major__ >= 18
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
 
 SEC("socket")
 __description("SDIV32, non-zero imm divisor, check 1")
-- 
GitLab


From 5d21d0a65b573507bae774708199328b38dedfe6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Wed, 23 Aug 2023 11:28:38 +0200
Subject: [PATCH 1628/1806] net: generalize calculation of skb extensions
 length
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the necessity to modify skb_ext_total_length() when new extension
types are added.
Also reduces the line count a bit.

With optimizations enabled the function is folded down to the same
constant value as before during compilation.
This has been validated on x86 with GCC 6.5.0 and 13.2.1.
Also a similar construct has been validated on godbolt.org with GCC 5.1.
In any case the compiler has to be able to evaluate the construct at
compile-time for the BUILD_BUG_ON() in skb_extensions_init().

Even if not evaluated at compile-time this function would only ever
be executed once at run-time, so the overhead would be very minuscule.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230823-skb_ext-simplify-v2-1-66e26cd66860@weissschuh.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skbuff.c | 24 +++++++-----------------
 1 file changed, 7 insertions(+), 17 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index faa6c86da2a54..45707059082f2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4785,23 +4785,13 @@ static const u8 skb_ext_type_len[] = {
 
 static __always_inline unsigned int skb_ext_total_length(void)
 {
-	return SKB_EXT_CHUNKSIZEOF(struct skb_ext) +
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		skb_ext_type_len[SKB_EXT_BRIDGE_NF] +
-#endif
-#ifdef CONFIG_XFRM
-		skb_ext_type_len[SKB_EXT_SEC_PATH] +
-#endif
-#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
-		skb_ext_type_len[TC_SKB_EXT] +
-#endif
-#if IS_ENABLED(CONFIG_MPTCP)
-		skb_ext_type_len[SKB_EXT_MPTCP] +
-#endif
-#if IS_ENABLED(CONFIG_MCTP_FLOWS)
-		skb_ext_type_len[SKB_EXT_MCTP] +
-#endif
-		0;
+	unsigned int l = SKB_EXT_CHUNKSIZEOF(struct skb_ext);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(skb_ext_type_len); i++)
+		l += skb_ext_type_len[i];
+
+	return l;
 }
 
 static void skb_extensions_init(void)
-- 
GitLab


From 35b4b6d0c53a3872e846dbcda9074117efdc078a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 23 Aug 2023 08:49:22 -0700
Subject: [PATCH 1629/1806] docs: netdev: recommend against --in-reply-to

It's somewhat unfortunate but with (my?) the current tooling
if people post new versions of a set in reply to an old version
managing the review queue gets difficult. So recommend against it.

Reviewed-by: Martin Habets <habetsm.xilinx@gmail.com>
Link: https://lore.kernel.org/r/20230823154922.1162644-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/process/maintainer-netdev.rst | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index 2ab843cde830c..c1c732e9748bd 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -167,6 +167,8 @@ Asking the maintainer for status updates on your
 patch is a good way to ensure your patch is ignored or pushed to the
 bottom of the priority list.
 
+.. _Changes requested:
+
 Changes requested
 ~~~~~~~~~~~~~~~~~
 
@@ -359,6 +361,10 @@ Make sure you address all the feedback in your new posting. Do not post a new
 version of the code if the discussion about the previous version is still
 ongoing, unless directly instructed by a reviewer.
 
+The new version of patches should be posted as a separate thread,
+not as a reply to the previous posting. Change log should include a link
+to the previous posting (see :ref:`Changes requested`).
+
 Testing
 -------
 
-- 
GitLab


From 59da9885767a75df697c84c06aaf2296e10d85a4 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 23 Aug 2023 10:56:32 +0200
Subject: [PATCH 1630/1806] net: dsa: use capital "OR" for multiple licenses in
 SPDX

Documentation/process/license-rules.rst and checkpatch expect the SPDX
identifier syntax for multiple licenses to use capital "OR".  Correct it
to keep consistent format and avoid copy-paste issues.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: FLorian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20230823085632.116725-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/b53/b53_serdes.c                   | 2 +-
 drivers/net/dsa/b53/b53_serdes.h                   | 2 +-
 drivers/net/dsa/hirschmann/hellcreek.c             | 2 +-
 drivers/net/dsa/hirschmann/hellcreek.h             | 2 +-
 include/linux/platform_data/hirschmann-hellcreek.h | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c
index b0ccebcd3ffa5..3f8a491ce885b 100644
--- a/drivers/net/dsa/b53/b53_serdes.c
+++ b/drivers/net/dsa/b53/b53_serdes.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Northstar Plus switch SerDes/SGMII PHY main logic
  *
diff --git a/drivers/net/dsa/b53/b53_serdes.h b/drivers/net/dsa/b53/b53_serdes.h
index ef81f5da5f81f..3d367c4df4d9b 100644
--- a/drivers/net/dsa/b53/b53_serdes.h
+++ b/drivers/net/dsa/b53/b53_serdes.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
  * Northstar Plus switch SerDes/SGMII PHY definitions
  *
diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c
index 720f4e4ed0b03..11ef1d7ea2293 100644
--- a/drivers/net/dsa/hirschmann/hellcreek.c
+++ b/drivers/net/dsa/hirschmann/hellcreek.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: (GPL-2.0 or MIT)
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
 /*
  * DSA driver for:
  * Hirschmann Hellcreek TSN switch.
diff --git a/drivers/net/dsa/hirschmann/hellcreek.h b/drivers/net/dsa/hirschmann/hellcreek.h
index 4a678f7d61ae0..6874cb9dc3614 100644
--- a/drivers/net/dsa/hirschmann/hellcreek.h
+++ b/drivers/net/dsa/hirschmann/hellcreek.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: (GPL-2.0 or MIT) */
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
 /*
  * DSA driver for:
  * Hirschmann Hellcreek TSN switch.
diff --git a/include/linux/platform_data/hirschmann-hellcreek.h b/include/linux/platform_data/hirschmann-hellcreek.h
index 6a000df5541f0..8748680e9e3cc 100644
--- a/include/linux/platform_data/hirschmann-hellcreek.h
+++ b/include/linux/platform_data/hirschmann-hellcreek.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: (GPL-2.0 or MIT) */
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
 /*
  * Hirschmann Hellcreek TSN switch platform data.
  *
-- 
GitLab


From 7de05cb47134a3ac179f28f5363c36d9ac17c6c3 Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Fri, 11 Aug 2023 15:42:31 +0530
Subject: [PATCH 1631/1806] Bluetooth: btnxpuart: Remove check for CTS low
 after FW download

This removes the unnecessary check for CTS low after FW download.

After FW download is complete, the CTS line is already seen low.
It becomes high after 2 msec, and low again after FW initialization
is complete.
This makes the current check for CTS low redundant.

This removes the wait for CTS low section and increase delay to
1200msec instead, which is sufficiant for all NXP chipsets to
initialize FW.

Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index ee6f6c872a34e..1dd60c7e6fe07 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -558,16 +558,11 @@ static int nxp_download_firmware(struct hci_dev *hdev)
 	}
 
 	serdev_device_set_flow_control(nxpdev->serdev, true);
-	err = serdev_device_wait_for_cts(nxpdev->serdev, 1, 60000);
-	if (err < 0) {
-		bt_dev_err(hdev, "CTS is still high. FW Download failed.");
-		return err;
-	}
 	release_firmware(nxpdev->fw);
 	memset(nxpdev->fw_name, 0, sizeof(nxpdev->fw_name));
 
 	/* Allow the downloaded FW to initialize */
-	usleep_range(800 * USEC_PER_MSEC, 1 * USEC_PER_SEC);
+	msleep(1200);
 
 	return 0;
 }
-- 
GitLab


From 8b7630deb40e04901a09646f7c556373b1438b18 Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Fri, 11 Aug 2023 15:42:32 +0530
Subject: [PATCH 1632/1806] Bluetooth: btnxpuart: Add support for IW624 chipset

This adds support for NXP IW624 chipset in btnxpuart driver
by adding FW name and bootloader signature. Based on the
loader version bits 7:6 of the bootloader signature, the
driver can choose between selecting secure and non-secure
FW files.
For cmd5 payload during FW download, this chip has addresses
of few registers offset by 1, so added boot_reg_offset to
handle the chip specific offset.

Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 37 ++++++++++++++++++++++++++++-------
 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 1dd60c7e6fe07..b42572ca63afd 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -34,6 +34,8 @@
 #define FIRMWARE_W9098		"nxp/uartuart9098_bt_v1.bin"
 #define FIRMWARE_IW416		"nxp/uartiw416_bt_v0.bin"
 #define FIRMWARE_IW612		"nxp/uartspi_n61x_v1.bin.se"
+#define FIRMWARE_IW624		"nxp/uartiw624_bt.bin"
+#define FIRMWARE_SECURE_IW624	"nxp/uartiw624_bt.bin.se"
 #define FIRMWARE_AW693		"nxp/uartaw693_bt.bin"
 #define FIRMWARE_SECURE_AW693	"nxp/uartaw693_bt.bin.se"
 #define FIRMWARE_HELPER		"nxp/helper_uart_3000000.bin"
@@ -41,6 +43,8 @@
 #define CHIP_ID_W9098		0x5c03
 #define CHIP_ID_IW416		0x7201
 #define CHIP_ID_IW612		0x7601
+#define CHIP_ID_IW624a		0x8000
+#define CHIP_ID_IW624c		0x8001
 #define CHIP_ID_AW693		0x8200
 
 #define FW_SECURE_MASK		0xc0
@@ -152,6 +156,7 @@ struct btnxpuart_dev {
 	u32 fw_v1_sent_bytes;
 	u32 fw_v3_offset_correction;
 	u32 fw_v1_expected_len;
+	u32 boot_reg_offset;
 	wait_queue_head_t fw_dnld_done_wait_q;
 	wait_queue_head_t check_boot_sign_wait_q;
 
@@ -538,6 +543,7 @@ static int nxp_download_firmware(struct hci_dev *hdev)
 	nxpdev->fw_dnld_v1_offset = 0;
 	nxpdev->fw_v1_sent_bytes = 0;
 	nxpdev->fw_v1_expected_len = HDR_LEN;
+	nxpdev->boot_reg_offset = 0;
 	nxpdev->fw_v3_offset_correction = 0;
 	nxpdev->baudrate_changed = false;
 	nxpdev->timeout_changed = false;
@@ -547,7 +553,7 @@ static int nxp_download_firmware(struct hci_dev *hdev)
 	serdev_device_set_flow_control(nxpdev->serdev, false);
 	nxpdev->current_baudrate = HCI_NXP_PRI_BAUDRATE;
 
-	/* Wait till FW is downloaded and CTS becomes low */
+	/* Wait till FW is downloaded */
 	err = wait_event_interruptible_timeout(nxpdev->fw_dnld_done_wait_q,
 					       !test_bit(BTNXPUART_FW_DOWNLOADING,
 							 &nxpdev->tx_state),
@@ -586,6 +592,12 @@ static bool nxp_fw_change_baudrate(struct hci_dev *hdev, u16 req_len)
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
 	struct nxp_bootloader_cmd nxp_cmd5;
 	struct uart_config uart_config;
+	u32 clkdivaddr = CLKDIVADDR - nxpdev->boot_reg_offset;
+	u32 uartdivaddr = UARTDIVADDR - nxpdev->boot_reg_offset;
+	u32 uartmcraddr = UARTMCRADDR - nxpdev->boot_reg_offset;
+	u32 uartreinitaddr = UARTREINITADDR - nxpdev->boot_reg_offset;
+	u32 uarticraddr = UARTICRADDR - nxpdev->boot_reg_offset;
+	u32 uartfcraddr = UARTFCRADDR - nxpdev->boot_reg_offset;
 
 	if (req_len == sizeof(nxp_cmd5)) {
 		nxp_cmd5.header = __cpu_to_le32(5);
@@ -598,17 +610,17 @@ static bool nxp_fw_change_baudrate(struct hci_dev *hdev, u16 req_len)
 		serdev_device_write_buf(nxpdev->serdev, (u8 *)&nxp_cmd5, sizeof(nxp_cmd5));
 		nxpdev->fw_v3_offset_correction += req_len;
 	} else if (req_len == sizeof(uart_config)) {
-		uart_config.clkdiv.address = __cpu_to_le32(CLKDIVADDR);
+		uart_config.clkdiv.address = __cpu_to_le32(clkdivaddr);
 		uart_config.clkdiv.value = __cpu_to_le32(0x00c00000);
-		uart_config.uartdiv.address = __cpu_to_le32(UARTDIVADDR);
+		uart_config.uartdiv.address = __cpu_to_le32(uartdivaddr);
 		uart_config.uartdiv.value = __cpu_to_le32(1);
-		uart_config.mcr.address = __cpu_to_le32(UARTMCRADDR);
+		uart_config.mcr.address = __cpu_to_le32(uartmcraddr);
 		uart_config.mcr.value = __cpu_to_le32(MCR);
-		uart_config.re_init.address = __cpu_to_le32(UARTREINITADDR);
+		uart_config.re_init.address = __cpu_to_le32(uartreinitaddr);
 		uart_config.re_init.value = __cpu_to_le32(INIT);
-		uart_config.icr.address = __cpu_to_le32(UARTICRADDR);
+		uart_config.icr.address = __cpu_to_le32(uarticraddr);
 		uart_config.icr.value = __cpu_to_le32(ICR);
-		uart_config.fcr.address = __cpu_to_le32(UARTFCRADDR);
+		uart_config.fcr.address = __cpu_to_le32(uartfcraddr);
 		uart_config.fcr.value = __cpu_to_le32(FCR);
 		/* FW expects swapped CRC bytes */
 		uart_config.crc = __cpu_to_be32(crc32_be(0UL, (char *)&uart_config,
@@ -822,6 +834,7 @@ free_skb:
 static char *nxp_get_fw_name_from_chipid(struct hci_dev *hdev, u16 chipid,
 					 u8 loader_ver)
 {
+	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
 	char *fw_name = NULL;
 
 	switch (chipid) {
@@ -834,6 +847,16 @@ static char *nxp_get_fw_name_from_chipid(struct hci_dev *hdev, u16 chipid,
 	case CHIP_ID_IW612:
 		fw_name = FIRMWARE_IW612;
 		break;
+	case CHIP_ID_IW624a:
+	case CHIP_ID_IW624c:
+		nxpdev->boot_reg_offset = 1;
+		if ((loader_ver & FW_SECURE_MASK) == FW_OPEN)
+			fw_name = FIRMWARE_IW624;
+		else if ((loader_ver & FW_SECURE_MASK) != FW_AUTH_ILLEGAL)
+			fw_name = FIRMWARE_SECURE_IW624;
+		else
+			bt_dev_err(hdev, "Illegal loader version %02x", loader_ver);
+		break;
 	case CHIP_ID_AW693:
 		if ((loader_ver & FW_SECURE_MASK) == FW_OPEN)
 			fw_name = FIRMWARE_AW693;
-- 
GitLab


From 491f9eff276012f3036f5546198cdf4a9e268284 Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Thu, 10 Aug 2023 19:25:09 +0530
Subject: [PATCH 1633/1806] Bluetooth: btnxpuart: Improve inband Independent
 Reset handling

This improves the inband IR command handling for NXP BT chipsets.
When the IR vendor command is received, the driver injects a HW
error event, which causes a reset sequence in hci_error_reset().
The vendor IR command is sent to the controller while hci dev
is been closed, and FW is re-downloaded when nxp_setup() is
called during hci_dev_do_open().
The HCI_SETUP flag is set in nxp_hw_err() to make sure that
nxp_setup() is been called during hci_dev_do_open().

This also makes the nxp_setup() and power save functions more
generic.

Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 172 +++++++++++++++++++---------------
 1 file changed, 96 insertions(+), 76 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index b42572ca63afd..b7e66b7ac5702 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -28,6 +28,10 @@
 #define BTNXPUART_FW_DOWNLOADING	2
 #define BTNXPUART_CHECK_BOOT_SIGNATURE	3
 #define BTNXPUART_SERDEV_OPEN		4
+#define BTNXPUART_IR_IN_PROGRESS	5
+
+/* NXP HW err codes */
+#define BTNXPUART_IR_HW_ERR		0xb0
 
 #define FIRMWARE_W8987		"nxp/uartuart8987_bt.bin"
 #define FIRMWARE_W8997		"nxp/uartuart8997_bt_v4.bin"
@@ -380,39 +384,13 @@ static void ps_timeout_func(struct timer_list *t)
 	}
 }
 
-static int ps_init_work(struct hci_dev *hdev)
+static void ps_setup(struct hci_dev *hdev)
 {
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
 	struct ps_data *psdata = &nxpdev->psdata;
 
-	psdata->h2c_ps_interval = PS_DEFAULT_TIMEOUT_PERIOD_MS;
-	psdata->ps_state = PS_STATE_AWAKE;
-	psdata->target_ps_mode = DEFAULT_PS_MODE;
 	psdata->hdev = hdev;
-	psdata->c2h_wakeupmode = BT_HOST_WAKEUP_METHOD_NONE;
-	psdata->c2h_wakeup_gpio = 0xff;
-
-	switch (DEFAULT_H2C_WAKEUP_MODE) {
-	case WAKEUP_METHOD_DTR:
-		psdata->h2c_wakeupmode = WAKEUP_METHOD_DTR;
-		break;
-	case WAKEUP_METHOD_BREAK:
-	default:
-		psdata->h2c_wakeupmode = WAKEUP_METHOD_BREAK;
-		break;
-	}
-	psdata->cur_psmode = PS_MODE_DISABLE;
-	psdata->cur_h2c_wakeupmode = WAKEUP_METHOD_INVALID;
 	INIT_WORK(&psdata->work, ps_work_func);
-
-	return 0;
-}
-
-static void ps_init_timer(struct hci_dev *hdev)
-{
-	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
-	struct ps_data *psdata = &nxpdev->psdata;
-
 	timer_setup(&psdata->ps_timer, ps_timeout_func, 0);
 }
 
@@ -515,19 +493,31 @@ static void ps_init(struct hci_dev *hdev)
 	serdev_device_set_tiocm(nxpdev->serdev, TIOCM_RTS, 0);
 	usleep_range(5000, 10000);
 
-	switch (psdata->h2c_wakeupmode) {
+	psdata->ps_state = PS_STATE_AWAKE;
+	psdata->c2h_wakeupmode = BT_HOST_WAKEUP_METHOD_NONE;
+	psdata->c2h_wakeup_gpio = 0xff;
+
+	psdata->cur_h2c_wakeupmode = WAKEUP_METHOD_INVALID;
+	psdata->h2c_ps_interval = PS_DEFAULT_TIMEOUT_PERIOD_MS;
+	switch (DEFAULT_H2C_WAKEUP_MODE) {
 	case WAKEUP_METHOD_DTR:
+		psdata->h2c_wakeupmode = WAKEUP_METHOD_DTR;
 		serdev_device_set_tiocm(nxpdev->serdev, 0, TIOCM_DTR);
 		serdev_device_set_tiocm(nxpdev->serdev, TIOCM_DTR, 0);
 		break;
 	case WAKEUP_METHOD_BREAK:
 	default:
+		psdata->h2c_wakeupmode = WAKEUP_METHOD_BREAK;
 		serdev_device_break_ctl(nxpdev->serdev, -1);
 		usleep_range(5000, 10000);
 		serdev_device_break_ctl(nxpdev->serdev, 0);
 		usleep_range(5000, 10000);
 		break;
 	}
+
+	psdata->cur_psmode = PS_MODE_DISABLE;
+	psdata->target_ps_mode = DEFAULT_PS_MODE;
+
 	if (psdata->cur_h2c_wakeupmode != psdata->h2c_wakeupmode)
 		hci_cmd_sync_queue(hdev, send_wakeup_method_cmd, NULL, NULL);
 	if (psdata->cur_psmode != psdata->target_ps_mode)
@@ -709,7 +699,7 @@ static int nxp_recv_chip_ver_v1(struct hci_dev *hdev, struct sk_buff *skb)
 		goto free_skb;
 
 	chip_id = le16_to_cpu(req->chip_id ^ req->chip_id_comp);
-	if (chip_id == 0xffff) {
+	if (chip_id == 0xffff && nxpdev->fw_dnld_v1_offset) {
 		nxpdev->fw_dnld_v1_offset = 0;
 		nxpdev->fw_v1_sent_bytes = 0;
 		nxpdev->fw_v1_expected_len = HDR_LEN;
@@ -987,45 +977,13 @@ static int nxp_set_baudrate_cmd(struct hci_dev *hdev, void *data)
 	return 0;
 }
 
-static int nxp_set_ind_reset(struct hci_dev *hdev, void *data)
-{
-	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
-	struct sk_buff *skb;
-	u8 *status;
-	u8 pcmd = 0;
-	int err = 0;
-
-	skb = nxp_drv_send_cmd(hdev, HCI_NXP_IND_RESET, 1, &pcmd);
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
-
-	status = skb_pull_data(skb, 1);
-	if (!status || *status)
-		goto free_skb;
-
-	set_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
-	err = nxp_download_firmware(hdev);
-	if (err < 0)
-		goto free_skb;
-	serdev_device_set_baudrate(nxpdev->serdev, nxpdev->fw_init_baudrate);
-	nxpdev->current_baudrate = nxpdev->fw_init_baudrate;
-	if (nxpdev->current_baudrate != HCI_NXP_SEC_BAUDRATE) {
-		nxpdev->new_baudrate = HCI_NXP_SEC_BAUDRATE;
-		nxp_set_baudrate_cmd(hdev, NULL);
-	}
-	hci_cmd_sync_queue(hdev, send_wakeup_method_cmd, NULL, NULL);
-	hci_cmd_sync_queue(hdev, send_ps_cmd, NULL, NULL);
-
-free_skb:
-	kfree_skb(skb);
-	return err;
-}
-
-/* NXP protocol */
 static int nxp_check_boot_sign(struct btnxpuart_dev *nxpdev)
 {
 	serdev_device_set_baudrate(nxpdev->serdev, HCI_NXP_PRI_BAUDRATE);
-	serdev_device_set_flow_control(nxpdev->serdev, true);
+	if (test_bit(BTNXPUART_IR_IN_PROGRESS, &nxpdev->tx_state))
+		serdev_device_set_flow_control(nxpdev->serdev, false);
+	else
+		serdev_device_set_flow_control(nxpdev->serdev, true);
 	set_bit(BTNXPUART_CHECK_BOOT_SIGNATURE, &nxpdev->tx_state);
 
 	return wait_event_interruptible_timeout(nxpdev->check_boot_sign_wait_q,
@@ -1034,15 +992,29 @@ static int nxp_check_boot_sign(struct btnxpuart_dev *nxpdev)
 					       msecs_to_jiffies(1000));
 }
 
+static int nxp_set_ind_reset(struct hci_dev *hdev, void *data)
+{
+	static const u8 ir_hw_err[] = { HCI_EV_HARDWARE_ERROR,
+					0x01, BTNXPUART_IR_HW_ERR };
+	struct sk_buff *skb;
+
+	skb = bt_skb_alloc(3, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	hci_skb_pkt_type(skb) = HCI_EVENT_PKT;
+	skb_put_data(skb, ir_hw_err, 3);
+
+	/* Inject Hardware Error to upper stack */
+	return hci_recv_frame(hdev, skb);
+}
+
+/* NXP protocol */
 static int nxp_setup(struct hci_dev *hdev)
 {
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
 	int err = 0;
 
-	set_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
-	init_waitqueue_head(&nxpdev->fw_dnld_done_wait_q);
-	init_waitqueue_head(&nxpdev->check_boot_sign_wait_q);
-
 	if (nxp_check_boot_sign(nxpdev)) {
 		bt_dev_dbg(hdev, "Need FW Download.");
 		err = nxp_download_firmware(hdev);
@@ -1053,10 +1025,6 @@ static int nxp_setup(struct hci_dev *hdev)
 		clear_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
 	}
 
-	device_property_read_u32(&nxpdev->serdev->dev, "fw-init-baudrate",
-				 &nxpdev->fw_init_baudrate);
-	if (!nxpdev->fw_init_baudrate)
-		nxpdev->fw_init_baudrate = FW_INIT_BAUDRATE;
 	serdev_device_set_baudrate(nxpdev->serdev, nxpdev->fw_init_baudrate);
 	nxpdev->current_baudrate = nxpdev->fw_init_baudrate;
 
@@ -1067,6 +1035,46 @@ static int nxp_setup(struct hci_dev *hdev)
 
 	ps_init(hdev);
 
+	if (test_and_clear_bit(BTNXPUART_IR_IN_PROGRESS, &nxpdev->tx_state))
+		hci_dev_clear_flag(hdev, HCI_SETUP);
+
+	return 0;
+}
+
+static void nxp_hw_err(struct hci_dev *hdev, u8 code)
+{
+	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
+
+	switch (code) {
+	case BTNXPUART_IR_HW_ERR:
+		set_bit(BTNXPUART_IR_IN_PROGRESS, &nxpdev->tx_state);
+		hci_dev_set_flag(hdev, HCI_SETUP);
+		break;
+	default:
+		break;
+	}
+}
+
+static int nxp_shutdown(struct hci_dev *hdev)
+{
+	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
+	struct sk_buff *skb;
+	u8 *status;
+	u8 pcmd = 0;
+
+	if (test_bit(BTNXPUART_IR_IN_PROGRESS, &nxpdev->tx_state)) {
+		skb = nxp_drv_send_cmd(hdev, HCI_NXP_IND_RESET, 1, &pcmd);
+		if (IS_ERR(skb))
+			return PTR_ERR(skb);
+
+		status = skb_pull_data(skb, 1);
+		if (status) {
+			serdev_device_set_flow_control(nxpdev->serdev, false);
+			set_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
+		}
+		kfree_skb(skb);
+	}
+
 	return 0;
 }
 
@@ -1274,7 +1282,8 @@ static int btnxpuart_receive_buf(struct serdev_device *serdev, const u8 *data,
 		nxpdev->rx_skb = NULL;
 		return err;
 	}
-	nxpdev->hdev->stat.byte_rx += count;
+	if (!is_fw_downloading(nxpdev))
+		nxpdev->hdev->stat.byte_rx += count;
 	return count;
 }
 
@@ -1307,6 +1316,16 @@ static int nxp_serdev_probe(struct serdev_device *serdev)
 	INIT_WORK(&nxpdev->tx_work, btnxpuart_tx_work);
 	skb_queue_head_init(&nxpdev->txq);
 
+	init_waitqueue_head(&nxpdev->fw_dnld_done_wait_q);
+	init_waitqueue_head(&nxpdev->check_boot_sign_wait_q);
+
+	device_property_read_u32(&nxpdev->serdev->dev, "fw-init-baudrate",
+				 &nxpdev->fw_init_baudrate);
+	if (!nxpdev->fw_init_baudrate)
+		nxpdev->fw_init_baudrate = FW_INIT_BAUDRATE;
+
+	set_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
+
 	crc8_populate_msb(crc8_table, POLYNOMIAL8);
 
 	/* Initialize and register HCI device */
@@ -1327,6 +1346,8 @@ static int nxp_serdev_probe(struct serdev_device *serdev)
 	hdev->flush = btnxpuart_flush;
 	hdev->setup = nxp_setup;
 	hdev->send  = nxp_enqueue;
+	hdev->hw_error = nxp_hw_err;
+	hdev->shutdown = nxp_shutdown;
 	SET_HCIDEV_DEV(hdev, &serdev->dev);
 
 	if (hci_register_dev(hdev) < 0) {
@@ -1335,8 +1356,7 @@ static int nxp_serdev_probe(struct serdev_device *serdev)
 		return -ENODEV;
 	}
 
-	ps_init_work(hdev);
-	ps_init_timer(hdev);
+	ps_setup(hdev);
 
 	return 0;
 }
-- 
GitLab


From 94d9ba9f9888b748d4abd2aa1547af56ae85f772 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 9 Aug 2023 16:49:33 -0700
Subject: [PATCH 1634/1806] Bluetooth: hci_sync: Fix UAF in
 hci_disconnect_all_sync

Use-after-free can occur in hci_disconnect_all_sync if a connection is
deleted by concurrent processing of a controller event.

To prevent this the code now tries to iterate over the list backwards
to ensure the links are cleanup before its parents, also it no longer
relies on a cursor, instead it always uses the last element since
hci_abort_conn_sync is guaranteed to call hci_conn_del.

UAF crash log:
==================================================================
BUG: KASAN: slab-use-after-free in hci_set_powered_sync
(net/bluetooth/hci_sync.c:5424) [bluetooth]
Read of size 8 at addr ffff888009d9c000 by task kworker/u9:0/124

CPU: 0 PID: 124 Comm: kworker/u9:0 Tainted: G        W
6.5.0-rc1+ #10
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
1.16.2-1.fc38 04/01/2014
Workqueue: hci0 hci_cmd_sync_work [bluetooth]
Call Trace:
 <TASK>
 dump_stack_lvl+0x5b/0x90
 print_report+0xcf/0x670
 ? __virt_addr_valid+0xdd/0x160
 ? hci_set_powered_sync+0x2c9/0x4a0 [bluetooth]
 kasan_report+0xa6/0xe0
 ? hci_set_powered_sync+0x2c9/0x4a0 [bluetooth]
 ? __pfx_set_powered_sync+0x10/0x10 [bluetooth]
 hci_set_powered_sync+0x2c9/0x4a0 [bluetooth]
 ? __pfx_hci_set_powered_sync+0x10/0x10 [bluetooth]
 ? __pfx_lock_release+0x10/0x10
 ? __pfx_set_powered_sync+0x10/0x10 [bluetooth]
 hci_cmd_sync_work+0x137/0x220 [bluetooth]
 process_one_work+0x526/0x9d0
 ? __pfx_process_one_work+0x10/0x10
 ? __pfx_do_raw_spin_lock+0x10/0x10
 ? mark_held_locks+0x1a/0x90
 worker_thread+0x92/0x630
 ? __pfx_worker_thread+0x10/0x10
 kthread+0x196/0x1e0
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x2c/0x50
 </TASK>

Allocated by task 1782:
 kasan_save_stack+0x33/0x60
 kasan_set_track+0x25/0x30
 __kasan_kmalloc+0x8f/0xa0
 hci_conn_add+0xa5/0xa80 [bluetooth]
 hci_bind_cis+0x881/0x9b0 [bluetooth]
 iso_connect_cis+0x121/0x520 [bluetooth]
 iso_sock_connect+0x3f6/0x790 [bluetooth]
 __sys_connect+0x109/0x130
 __x64_sys_connect+0x40/0x50
 do_syscall_64+0x60/0x90
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

Freed by task 695:
 kasan_save_stack+0x33/0x60
 kasan_set_track+0x25/0x30
 kasan_save_free_info+0x2b/0x50
 __kasan_slab_free+0x10a/0x180
 __kmem_cache_free+0x14d/0x2e0
 device_release+0x5d/0xf0
 kobject_put+0xdf/0x270
 hci_disconn_complete_evt+0x274/0x3a0 [bluetooth]
 hci_event_packet+0x579/0x7e0 [bluetooth]
 hci_rx_work+0x287/0xaa0 [bluetooth]
 process_one_work+0x526/0x9d0
 worker_thread+0x92/0x630
 kthread+0x196/0x1e0
 ret_from_fork+0x2c/0x50
==================================================================

Fixes: 182ee45da083 ("Bluetooth: hci_sync: Rework hci_suspend_notifier")
Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 55 +++++++++++++++++++++++++---------------
 1 file changed, 35 insertions(+), 20 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 5eb30ba213708..d10a0f36b947c 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5370,6 +5370,7 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
 {
 	int err = 0;
 	u16 handle = conn->handle;
+	struct hci_conn *c;
 
 	switch (conn->state) {
 	case BT_CONNECTED:
@@ -5389,43 +5390,57 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
 		hci_dev_unlock(hdev);
 		return 0;
 	default:
+		hci_dev_lock(hdev);
 		conn->state = BT_CLOSED;
+		hci_disconn_cfm(conn, reason);
+		hci_conn_del(conn);
+		hci_dev_unlock(hdev);
 		return 0;
 	}
 
+	hci_dev_lock(hdev);
+
+	/* Check if the connection hasn't been cleanup while waiting
+	 * commands to complete.
+	 */
+	c = hci_conn_hash_lookup_handle(hdev, handle);
+	if (!c || c != conn) {
+		err = 0;
+		goto unlock;
+	}
+
 	/* Cleanup hci_conn object if it cannot be cancelled as it
 	 * likelly means the controller and host stack are out of sync
 	 * or in case of LE it was still scanning so it can be cleanup
 	 * safely.
 	 */
-	if (err) {
-		struct hci_conn *c;
-
-		/* Check if the connection hasn't been cleanup while waiting
-		 * commands to complete.
-		 */
-		c = hci_conn_hash_lookup_handle(hdev, handle);
-		if (!c || c != conn)
-			return 0;
-
-		hci_dev_lock(hdev);
-		hci_conn_failed(conn, err);
-		hci_dev_unlock(hdev);
-	}
+	hci_conn_failed(conn, reason);
 
+unlock:
+	hci_dev_unlock(hdev);
 	return err;
 }
 
 static int hci_disconnect_all_sync(struct hci_dev *hdev, u8 reason)
 {
-	struct hci_conn *conn, *tmp;
-	int err;
+	struct list_head *head = &hdev->conn_hash.list;
+	struct hci_conn *conn;
 
-	list_for_each_entry_safe(conn, tmp, &hdev->conn_hash.list, list) {
-		err = hci_abort_conn_sync(hdev, conn, reason);
-		if (err)
-			return err;
+	rcu_read_lock();
+	while ((conn = list_first_or_null_rcu(head, struct hci_conn, list))) {
+		/* Make sure the connection is not freed while unlocking */
+		conn = hci_conn_get(conn);
+		rcu_read_unlock();
+		/* Disregard possible errors since hci_conn_del shall have been
+		 * called even in case of errors had occurred since it would
+		 * then cause hci_conn_failed to be called which calls
+		 * hci_conn_del internally.
+		 */
+		hci_abort_conn_sync(hdev, conn, reason);
+		hci_conn_put(conn);
+		rcu_read_lock();
 	}
+	rcu_read_unlock();
 
 	return 0;
 }
-- 
GitLab


From 3a15324fd4bb94c31a5fb893413b04e634567957 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 15 Aug 2023 14:15:05 -0700
Subject: [PATCH 1635/1806] Bluetooth: hci_conn: Fix sending
 BT_HCI_CMD_LE_CREATE_CONN_CANCEL

This fixes sending BT_HCI_CMD_LE_CREATE_CONN_CANCEL when
hci_le_create_conn_sync has not been called because HCI_CONN_SCANNING
has been clear too early before its cmd_sync callback has been run.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 234746721047f..95339623883c7 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1299,6 +1299,7 @@ static int hci_connect_le_sync(struct hci_dev *hdev, void *data)
 
 	bt_dev_dbg(hdev, "conn %p", conn);
 
+	clear_bit(HCI_CONN_SCANNING, &conn->flags);
 	conn->state = BT_CONNECT;
 
 	return hci_le_create_conn_sync(hdev, conn);
@@ -1370,8 +1371,6 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	conn->sec_level = BT_SECURITY_LOW;
 	conn->conn_timeout = conn_timeout;
 
-	clear_bit(HCI_CONN_SCANNING, &conn->flags);
-
 	err = hci_cmd_sync_queue(hdev, hci_connect_le_sync,
 				 UINT_PTR(conn->handle),
 				 create_le_conn_complete);
-- 
GitLab


From 9f19fb8fa1e1f55537fa74b90538ac44da68749c Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Wed, 16 Aug 2023 10:06:46 +0200
Subject: [PATCH 1636/1806] dt-bindings: net: bluetooth: qualcomm: document
 WCN7850 chipset

Document the WCN7850 Bluetooth chipset.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 .../net/bluetooth/qualcomm-bluetooth.yaml     | 23 +++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
index 2735c6a4f336d..eba2f3026ab0a 100644
--- a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
+++ b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
@@ -26,6 +26,7 @@ properties:
       - qcom,qca6390-bt
       - qcom,wcn6750-bt
       - qcom,wcn6855-bt
+      - qcom,wcn7850-bt
 
   enable-gpios:
     maxItems: 1
@@ -58,6 +59,9 @@ properties:
   vddaon-supply:
     description: VDD_AON supply regulator handle
 
+  vdddig-supply:
+    description: VDD_DIG supply regulator handle
+
   vddbtcxmx-supply:
     description: VDD_BT_CXMX supply regulator handle
 
@@ -73,6 +77,9 @@ properties:
   vddrfa1p2-supply:
     description: VDD_RFA_1P2 supply regulator handle
 
+  vddrfa1p9-supply:
+    description: VDD_RFA_1P9 supply regulator handle
+
   vddrfa2p2-supply:
     description: VDD_RFA_2P2 supply regulator handle
 
@@ -157,6 +164,22 @@ allOf:
         - vddrfa0p8-supply
         - vddrfa1p2-supply
         - vddrfa1p7-supply
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,wcn7850-bt
+    then:
+      required:
+        - enable-gpios
+        - swctrl-gpios
+        - vddio-supply
+        - vddaon-supply
+        - vdddig-supply
+        - vddrfa0p8-supply
+        - vddrfa1p2-supply
+        - vddrfa1p9-supply
 
 examples:
   - |
-- 
GitLab


From 691d54d0f7cb14baac1ff4af210d13c0e4897e27 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Wed, 16 Aug 2023 10:06:47 +0200
Subject: [PATCH 1637/1806] Bluetooth: qca: use switch case for soc type
 behavior

Use switch/case to handle soc type specific behaviour,
the permit dropping the qca_is_xxx() inline functions
and make the code clearer and easier to update for new
SoCs.

Suggested-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Suggested-by: Luiz Augusto von Dentz <luiz.dentz@gmail.com>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btqca.c   |  87 +++++++++-----
 drivers/bluetooth/btqca.h   |  36 ------
 drivers/bluetooth/hci_qca.c | 233 +++++++++++++++++++++++++++---------
 3 files changed, 236 insertions(+), 120 deletions(-)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 6f2187fab55f5..e301f571e9710 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -604,26 +604,34 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 
 	/* Download rampatch file */
 	config.type = TLV_TYPE_PATCH;
-	if (soc_type == QCA_WCN3988) {
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/apbtfw%02x.tlv", rom_ver);
-	} else if (qca_is_wcn399x(soc_type)) {
+	switch (soc_type) {
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/crbtfw%02x.tlv", rom_ver);
-	} else if (soc_type == QCA_QCA6390) {
+		break;
+	case QCA_WCN3988:
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/apbtfw%02x.tlv", rom_ver);
+		break;
+	case QCA_QCA6390:
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/htbtfw%02x.tlv", rom_ver);
-	} else if (soc_type == QCA_WCN6750) {
+		break;
+	case QCA_WCN6750:
 		/* Choose mbn file by default.If mbn file is not found
 		 * then choose tlv file
 		 */
 		config.type = ELF_TYPE_PATCH;
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/msbtfw%02x.mbn", rom_ver);
-	} else if (soc_type == QCA_WCN6855) {
+		break;
+	case QCA_WCN6855:
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/hpbtfw%02x.tlv", rom_ver);
-	} else {
+		break;
+	default:
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/rampatch_%08x.bin", soc_ver);
 	}
@@ -639,33 +647,44 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 
 	/* Download NVM configuration */
 	config.type = TLV_TYPE_NVM;
-	if (firmware_name)
+	if (firmware_name) {
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/%s", firmware_name);
-	else if (soc_type == QCA_WCN3988)
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/apnv%02x.bin", rom_ver);
-	else if (qca_is_wcn399x(soc_type)) {
-		if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) {
+	} else {
+		switch (soc_type) {
+		case QCA_WCN3990:
+		case QCA_WCN3991:
+		case QCA_WCN3998:
+			if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) {
+				snprintf(config.fwname, sizeof(config.fwname),
+					 "qca/crnv%02xu.bin", rom_ver);
+			} else {
+				snprintf(config.fwname, sizeof(config.fwname),
+					 "qca/crnv%02x.bin", rom_ver);
+			}
+			break;
+		case QCA_WCN3988:
 			snprintf(config.fwname, sizeof(config.fwname),
-				 "qca/crnv%02xu.bin", rom_ver);
-		} else {
+				 "qca/apnv%02x.bin", rom_ver);
+			break;
+		case QCA_QCA6390:
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/htnv%02x.bin", rom_ver);
+			break;
+		case QCA_WCN6750:
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/msnv%02x.bin", rom_ver);
+			break;
+		case QCA_WCN6855:
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/hpnv%02x.bin", rom_ver);
+			break;
+
+		default:
 			snprintf(config.fwname, sizeof(config.fwname),
-				 "qca/crnv%02x.bin", rom_ver);
+				 "qca/nvm_%08x.bin", soc_ver);
 		}
 	}
-	else if (soc_type == QCA_QCA6390)
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/htnv%02x.bin", rom_ver);
-	else if (soc_type == QCA_WCN6750)
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/msnv%02x.bin", rom_ver);
-	else if (soc_type == QCA_WCN6855)
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/hpnv%02x.bin", rom_ver);
-	else
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/nvm_%08x.bin", soc_ver);
 
 	err = qca_download_firmware(hdev, &config, soc_type, rom_ver);
 	if (err < 0) {
@@ -673,16 +692,24 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		return err;
 	}
 
-	if (soc_type >= QCA_WCN3991) {
+	switch (soc_type) {
+	case QCA_WCN3991:
+	case QCA_QCA6390:
+	case QCA_WCN6750:
+	case QCA_WCN6855:
 		err = qca_disable_soc_logging(hdev);
 		if (err < 0)
 			return err;
+		break;
+	default:
+		break;
 	}
 
 	/* WCN399x and WCN6750 supports the Microsoft vendor extension with 0xFD70 as the
 	 * VsMsftOpCode.
 	 */
 	switch (soc_type) {
+	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
 	case QCA_WCN3998:
diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h
index fc6cf314eb0ef..fe51c632d7720 100644
--- a/drivers/bluetooth/btqca.h
+++ b/drivers/bluetooth/btqca.h
@@ -161,27 +161,6 @@ int qca_read_soc_version(struct hci_dev *hdev, struct qca_btsoc_version *ver,
 			 enum qca_btsoc_type);
 int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr);
 int qca_send_pre_shutdown_cmd(struct hci_dev *hdev);
-static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type)
-{
-	switch (soc_type) {
-	case QCA_WCN3988:
-	case QCA_WCN3990:
-	case QCA_WCN3991:
-	case QCA_WCN3998:
-		return true;
-	default:
-		return false;
-	}
-}
-static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type)
-{
-	return soc_type == QCA_WCN6750;
-}
-static inline bool qca_is_wcn6855(enum qca_btsoc_type soc_type)
-{
-	return soc_type == QCA_WCN6855;
-}
-
 #else
 
 static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr)
@@ -209,21 +188,6 @@ static inline int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 	return -EOPNOTSUPP;
 }
 
-static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type)
-{
-	return false;
-}
-
-static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type)
-{
-	return false;
-}
-
-static inline bool qca_is_wcn6855(enum qca_btsoc_type soc_type)
-{
-	return false;
-}
-
 static inline int qca_send_pre_shutdown_cmd(struct hci_dev *hdev)
 {
 	return -EOPNOTSUPP;
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 0118225196021..548157119b75a 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -607,9 +607,18 @@ static int qca_open(struct hci_uart *hu)
 	if (hu->serdev) {
 		qcadev = serdev_device_get_drvdata(hu->serdev);
 
-		if (qca_is_wcn399x(qcadev->btsoc_type) ||
-		    qca_is_wcn6750(qcadev->btsoc_type))
+		switch (qcadev->btsoc_type) {
+		case QCA_WCN3988:
+		case QCA_WCN3990:
+		case QCA_WCN3991:
+		case QCA_WCN3998:
+		case QCA_WCN6750:
 			hu->init_speed = qcadev->init_speed;
+			break;
+
+		default:
+			break;
+		}
 
 		if (qcadev->oper_speed)
 			hu->oper_speed = qcadev->oper_speed;
@@ -1341,12 +1350,19 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 		      msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS));
 
 	/* Give the controller time to process the request */
-	if (qca_is_wcn399x(qca_soc_type(hu)) ||
-	    qca_is_wcn6750(qca_soc_type(hu)) ||
-	    qca_is_wcn6855(qca_soc_type(hu)))
+	switch (qca_soc_type(hu)) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
+	case QCA_WCN6750:
+	case QCA_WCN6855:
 		usleep_range(1000, 10000);
-	else
+		break;
+
+	default:
 		msleep(300);
+	}
 
 	return 0;
 }
@@ -1419,13 +1435,19 @@ static unsigned int qca_get_speed(struct hci_uart *hu,
 
 static int qca_check_speeds(struct hci_uart *hu)
 {
-	if (qca_is_wcn399x(qca_soc_type(hu)) ||
-	    qca_is_wcn6750(qca_soc_type(hu)) ||
-	    qca_is_wcn6855(qca_soc_type(hu))) {
+	switch (qca_soc_type(hu)) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
+	case QCA_WCN6750:
+	case QCA_WCN6855:
 		if (!qca_get_speed(hu, QCA_INIT_SPEED) &&
 		    !qca_get_speed(hu, QCA_OPER_SPEED))
 			return -EINVAL;
-	} else {
+		break;
+
+	default:
 		if (!qca_get_speed(hu, QCA_INIT_SPEED) ||
 		    !qca_get_speed(hu, QCA_OPER_SPEED))
 			return -EINVAL;
@@ -1454,14 +1476,28 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
 		/* Disable flow control for wcn3990 to deassert RTS while
 		 * changing the baudrate of chip and host.
 		 */
-		if (qca_is_wcn399x(soc_type) ||
-		    qca_is_wcn6750(soc_type) ||
-		    qca_is_wcn6855(soc_type))
+		switch (soc_type) {
+		case QCA_WCN3988:
+		case QCA_WCN3990:
+		case QCA_WCN3991:
+		case QCA_WCN3998:
+		case QCA_WCN6750:
+		case QCA_WCN6855:
 			hci_uart_set_flow_control(hu, true);
+			break;
 
-		if (soc_type == QCA_WCN3990) {
+		default:
+			break;
+		}
+
+		switch (soc_type) {
+		case QCA_WCN3990:
 			reinit_completion(&qca->drop_ev_comp);
 			set_bit(QCA_DROP_VENDOR_EVENT, &qca->flags);
+			break;
+
+		default:
+			break;
 		}
 
 		qca_baudrate = qca_get_baudrate_value(speed);
@@ -1473,12 +1509,22 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
 		host_set_baudrate(hu, speed);
 
 error:
-		if (qca_is_wcn399x(soc_type) ||
-		    qca_is_wcn6750(soc_type) ||
-		    qca_is_wcn6855(soc_type))
+		switch (soc_type) {
+		case QCA_WCN3988:
+		case QCA_WCN3990:
+		case QCA_WCN3991:
+		case QCA_WCN3998:
+		case QCA_WCN6750:
+		case QCA_WCN6855:
 			hci_uart_set_flow_control(hu, false);
+			break;
 
-		if (soc_type == QCA_WCN3990) {
+		default:
+			break;
+		}
+
+		switch (soc_type) {
+		case QCA_WCN3990:
 			/* Wait for the controller to send the vendor event
 			 * for the baudrate change command.
 			 */
@@ -1490,6 +1536,10 @@ error:
 			}
 
 			clear_bit(QCA_DROP_VENDOR_EVENT, &qca->flags);
+			break;
+
+		default:
+			break;
 		}
 	}
 
@@ -1651,12 +1701,20 @@ static int qca_regulator_init(struct hci_uart *hu)
 		}
 	}
 
-	if (qca_is_wcn399x(soc_type)) {
+	switch (soc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
 		/* Forcefully enable wcn399x to enter in to boot mode. */
 		host_set_baudrate(hu, 2400);
 		ret = qca_send_power_pulse(hu, false);
 		if (ret)
 			return ret;
+		break;
+
+	default:
+		break;
 	}
 
 	/* For wcn6750 need to enable gpio bt_en */
@@ -1673,10 +1731,18 @@ static int qca_regulator_init(struct hci_uart *hu)
 
 	qca_set_speed(hu, QCA_INIT_SPEED);
 
-	if (qca_is_wcn399x(soc_type)) {
+	switch (soc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
 		ret = qca_send_power_pulse(hu, true);
 		if (ret)
 			return ret;
+		break;
+
+	default:
+		break;
 	}
 
 	/* Now the device is in ready state to communicate with host.
@@ -1710,11 +1776,17 @@ static int qca_power_on(struct hci_dev *hdev)
 	if (!hu->serdev)
 		return 0;
 
-	if (qca_is_wcn399x(soc_type) ||
-	    qca_is_wcn6750(soc_type) ||
-	    qca_is_wcn6855(soc_type)) {
+	switch (soc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
+	case QCA_WCN6750:
+	case QCA_WCN6855:
 		ret = qca_regulator_init(hu);
-	} else {
+		break;
+
+	default:
 		qcadev = serdev_device_get_drvdata(hu->serdev);
 		if (qcadev->bt_en) {
 			gpiod_set_value_cansleep(qcadev->bt_en, 1);
@@ -1748,6 +1820,7 @@ static int qca_setup(struct hci_uart *hu)
 	const char *firmware_name = qca_get_firmware_name(hu);
 	int ret;
 	struct qca_btsoc_version ver;
+	const char *soc_name;
 
 	ret = qca_check_speeds(hu);
 	if (ret)
@@ -1762,10 +1835,26 @@ static int qca_setup(struct hci_uart *hu)
 	 */
 	set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks);
 
-	bt_dev_info(hdev, "setting up %s",
-		qca_is_wcn399x(soc_type) ? "wcn399x" :
-		(soc_type == QCA_WCN6750) ? "wcn6750" :
-		(soc_type == QCA_WCN6855) ? "wcn6855" : "ROME/QCA6390");
+	switch (soc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
+		soc_name = "wcn399x";
+		break;
+
+	case QCA_WCN6750:
+		soc_name = "wcn6750";
+		break;
+
+	case QCA_WCN6855:
+		soc_name = "wcn6855";
+		break;
+
+	default:
+		soc_name = "ROME/QCA6390";
+	}
+	bt_dev_info(hdev, "setting up %s", soc_name);
 
 	qca->memdump_state = QCA_MEMDUMP_IDLE;
 
@@ -1776,16 +1865,22 @@ retry:
 
 	clear_bit(QCA_SSR_TRIGGERED, &qca->flags);
 
-	if (qca_is_wcn399x(soc_type) ||
-	    qca_is_wcn6750(soc_type) ||
-	    qca_is_wcn6855(soc_type)) {
+	switch (soc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
+	case QCA_WCN6750:
+	case QCA_WCN6855:
 		set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
 		hci_set_aosp_capable(hdev);
 
 		ret = qca_read_soc_version(hdev, &ver, soc_type);
 		if (ret)
 			goto out;
-	} else {
+		break;
+
+	default:
 		qca_set_speed(hu, QCA_INIT_SPEED);
 	}
 
@@ -1799,9 +1894,16 @@ retry:
 		qca_baudrate = qca_get_baudrate_value(speed);
 	}
 
-	if (!(qca_is_wcn399x(soc_type) ||
-	      qca_is_wcn6750(soc_type) ||
-	      qca_is_wcn6855(soc_type))) {
+	switch (soc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
+	case QCA_WCN6750:
+	case QCA_WCN6855:
+		break;
+
+	default:
 		/* Get QCA version information */
 		ret = qca_read_soc_version(hdev, &ver, soc_type);
 		if (ret)
@@ -1980,11 +2082,18 @@ static void qca_power_shutdown(struct hci_uart *hu)
 
 	qcadev = serdev_device_get_drvdata(hu->serdev);
 
-	if (qca_is_wcn399x(soc_type)) {
+	switch (soc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
 		host_set_baudrate(hu, 2400);
 		qca_send_power_pulse(hu, false);
 		qca_regulator_disable(qcadev);
-	} else if (soc_type == QCA_WCN6750 || soc_type == QCA_WCN6855) {
+		break;
+
+	case QCA_WCN6750:
+	case QCA_WCN6855:
 		gpiod_set_value_cansleep(qcadev->bt_en, 0);
 		msleep(100);
 		qca_regulator_disable(qcadev);
@@ -1992,7 +2101,9 @@ static void qca_power_shutdown(struct hci_uart *hu)
 			sw_ctrl_state = gpiod_get_value_cansleep(qcadev->sw_ctrl);
 			bt_dev_dbg(hu->hdev, "SW_CTRL is %d", sw_ctrl_state);
 		}
-	} else if (qcadev->bt_en) {
+		break;
+
+	default:
 		gpiod_set_value_cansleep(qcadev->bt_en, 0);
 	}
 
@@ -2117,11 +2228,18 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 	if (!qcadev->oper_speed)
 		BT_DBG("UART will pick default operating speed");
 
-	if (data &&
-	    (qca_is_wcn399x(data->soc_type) ||
-	     qca_is_wcn6750(data->soc_type) ||
-	     qca_is_wcn6855(data->soc_type))) {
+	if (data)
 		qcadev->btsoc_type = data->soc_type;
+	else
+		qcadev->btsoc_type = QCA_ROME;
+
+	switch (qcadev->btsoc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
+	case QCA_WCN6750:
+	case QCA_WCN6855:
 		qcadev->bt_power = devm_kzalloc(&serdev->dev,
 						sizeof(struct qca_power),
 						GFP_KERNEL);
@@ -2165,12 +2283,9 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 			BT_ERR("wcn3990 serdev registration failed");
 			return err;
 		}
-	} else {
-		if (data)
-			qcadev->btsoc_type = data->soc_type;
-		else
-			qcadev->btsoc_type = QCA_ROME;
+		break;
 
+	default:
 		qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable",
 					       GPIOD_OUT_LOW);
 		if (IS_ERR_OR_NULL(qcadev->bt_en)) {
@@ -2226,13 +2341,23 @@ static void qca_serdev_remove(struct serdev_device *serdev)
 	struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev);
 	struct qca_power *power = qcadev->bt_power;
 
-	if ((qca_is_wcn399x(qcadev->btsoc_type) ||
-	     qca_is_wcn6750(qcadev->btsoc_type) ||
-	     qca_is_wcn6855(qcadev->btsoc_type)) &&
-	    power->vregs_on)
-		qca_power_shutdown(&qcadev->serdev_hu);
-	else if (qcadev->susclk)
-		clk_disable_unprepare(qcadev->susclk);
+	switch (qcadev->btsoc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
+	case QCA_WCN6750:
+	case QCA_WCN6855:
+		if (power->vregs_on) {
+			qca_power_shutdown(&qcadev->serdev_hu);
+			break;
+		}
+		fallthrough;
+
+	default:
+		if (qcadev->susclk)
+			clk_disable_unprepare(qcadev->susclk);
+	}
 
 	hci_uart_unregister_device(&qcadev->serdev_hu);
 }
-- 
GitLab


From e0c1278ac89b0390fe9a74f673b6f25172292db2 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Wed, 16 Aug 2023 10:06:48 +0200
Subject: [PATCH 1638/1806] Bluetooth: qca: add support for WCN7850

Add support for the WCN7850 Bluetooth chipset.

Tested on the SM8550 QRD platform.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btqca.c   | 10 ++++++++++
 drivers/bluetooth/btqca.h   |  1 +
 drivers/bluetooth/hci_qca.c | 31 ++++++++++++++++++++++++++++++-
 3 files changed, 41 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index e301f571e9710..5a35ac4138c6c 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -631,6 +631,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/hpbtfw%02x.tlv", rom_ver);
 		break;
+	case QCA_WCN7850:
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/hmtbtfw%02x.tlv", rom_ver);
+		break;
 	default:
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/rampatch_%08x.bin", soc_ver);
@@ -679,6 +683,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 			snprintf(config.fwname, sizeof(config.fwname),
 				 "qca/hpnv%02x.bin", rom_ver);
 			break;
+		case QCA_WCN7850:
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/hmtnv%02x.bin", rom_ver);
+			break;
 
 		default:
 			snprintf(config.fwname, sizeof(config.fwname),
@@ -697,6 +705,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	case QCA_QCA6390:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		err = qca_disable_soc_logging(hdev);
 		if (err < 0)
 			return err;
@@ -731,6 +740,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	case QCA_WCN3991:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		/* get fw build info */
 		err = qca_read_fw_build_info(hdev);
 		if (err < 0)
diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h
index fe51c632d7720..03bff5c0059de 100644
--- a/drivers/bluetooth/btqca.h
+++ b/drivers/bluetooth/btqca.h
@@ -149,6 +149,7 @@ enum qca_btsoc_type {
 	QCA_QCA6390,
 	QCA_WCN6750,
 	QCA_WCN6855,
+	QCA_WCN7850,
 };
 
 #if IS_ENABLED(CONFIG_BT_QCA)
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 548157119b75a..4b57e15f9c7a7 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -1357,6 +1357,7 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		usleep_range(1000, 10000);
 		break;
 
@@ -1442,6 +1443,7 @@ static int qca_check_speeds(struct hci_uart *hu)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		if (!qca_get_speed(hu, QCA_INIT_SPEED) &&
 		    !qca_get_speed(hu, QCA_OPER_SPEED))
 			return -EINVAL;
@@ -1483,6 +1485,7 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
 		case QCA_WCN3998:
 		case QCA_WCN6750:
 		case QCA_WCN6855:
+		case QCA_WCN7850:
 			hci_uart_set_flow_control(hu, true);
 			break;
 
@@ -1516,6 +1519,7 @@ error:
 		case QCA_WCN3998:
 		case QCA_WCN6750:
 		case QCA_WCN6855:
+		case QCA_WCN7850:
 			hci_uart_set_flow_control(hu, false);
 			break;
 
@@ -1783,6 +1787,7 @@ static int qca_power_on(struct hci_dev *hdev)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		ret = qca_regulator_init(hu);
 		break;
 
@@ -1851,6 +1856,10 @@ static int qca_setup(struct hci_uart *hu)
 		soc_name = "wcn6855";
 		break;
 
+	case QCA_WCN7850:
+		soc_name = "wcn7850";
+		break;
+
 	default:
 		soc_name = "ROME/QCA6390";
 	}
@@ -1872,6 +1881,7 @@ retry:
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
 		hci_set_aosp_capable(hdev);
 
@@ -1901,6 +1911,7 @@ retry:
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		break;
 
 	default:
@@ -2057,6 +2068,20 @@ static const struct qca_device_data qca_soc_data_wcn6855 __maybe_unused = {
 	.capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES,
 };
 
+static const struct qca_device_data qca_soc_data_wcn7850 __maybe_unused = {
+	.soc_type = QCA_WCN7850,
+	.vregs = (struct qca_vreg []) {
+		{ "vddio", 5000 },
+		{ "vddaon", 26000 },
+		{ "vdddig", 126000 },
+		{ "vddrfa0p8", 102000 },
+		{ "vddrfa1p2", 257000 },
+		{ "vddrfa1p9", 302000 },
+	},
+	.num_vregs = 6,
+	.capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES,
+};
+
 static void qca_power_shutdown(struct hci_uart *hu)
 {
 	struct qca_serdev *qcadev;
@@ -2240,6 +2265,7 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		qcadev->bt_power = devm_kzalloc(&serdev->dev,
 						sizeof(struct qca_power),
 						GFP_KERNEL);
@@ -2269,7 +2295,8 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 					       GPIOD_IN);
 		if (IS_ERR_OR_NULL(qcadev->sw_ctrl) &&
 		    (data->soc_type == QCA_WCN6750 ||
-		     data->soc_type == QCA_WCN6855))
+		     data->soc_type == QCA_WCN6855 ||
+		     data->soc_type == QCA_WCN7850))
 			dev_warn(&serdev->dev, "failed to acquire SW_CTRL gpio\n");
 
 		qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL);
@@ -2348,6 +2375,7 @@ static void qca_serdev_remove(struct serdev_device *serdev)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		if (power->vregs_on) {
 			qca_power_shutdown(&qcadev->serdev_hu);
 			break;
@@ -2540,6 +2568,7 @@ static const struct of_device_id qca_bluetooth_of_match[] = {
 	{ .compatible = "qcom,wcn3998-bt", .data = &qca_soc_data_wcn3998},
 	{ .compatible = "qcom,wcn6750-bt", .data = &qca_soc_data_wcn6750},
 	{ .compatible = "qcom,wcn6855-bt", .data = &qca_soc_data_wcn6855},
+	{ .compatible = "qcom,wcn7850-bt", .data = &qca_soc_data_wcn7850},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match);
-- 
GitLab


From fbdc4bc47268953c80853489f696e02d61f9a2c6 Mon Sep 17 00:00:00 2001
From: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Date: Thu, 17 Aug 2023 09:44:27 +0300
Subject: [PATCH 1639/1806] Bluetooth: ISO: Use defer setup to separate PA sync
 and BIG sync

This commit implements defer setup support for the Broadcast Sink
scenario: By setting defer setup on a broadcast socket before calling
listen, the user is able to trigger the PA sync and BIG sync procedures
separately.

This is useful if the user first wants to synchronize to the periodic
advertising transmitted by a Broadcast Source, and trigger the BIG sync
procedure later on.

If defer setup is set, once a PA sync established event arrives, a new
hcon is created and notified to the ISO layer. A child socket associated
with the PA sync connection will be added to the accept queue of the
listening socket.

Once the accept call returns the fd for the PA sync child socket, the
user should call read on that fd. This will trigger the BIG create sync
procedure, and the PA sync socket will become a listening socket itself.

When the BIG sync established event is notified to the ISO layer, the
bis connections will be added to the accept queue of the PA sync parent.
The user should call accept on the PA sync socket to get the final bis
connections.

Signed-off-by: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  30 +++++-
 net/bluetooth/hci_conn.c         |  13 ++-
 net/bluetooth/hci_event.c        |  41 +++++++-
 net/bluetooth/hci_sync.c         |  15 +++
 net/bluetooth/iso.c              | 160 ++++++++++++++++++++++++-------
 5 files changed, 218 insertions(+), 41 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index c53d74236e3a1..6fb055e3c595b 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -978,6 +978,8 @@ enum {
 	HCI_CONN_CREATE_CIS,
 	HCI_CONN_BIG_SYNC,
 	HCI_CONN_BIG_SYNC_FAILED,
+	HCI_CONN_PA_SYNC,
+	HCI_CONN_PA_SYNC_FAILED,
 };
 
 static inline bool hci_conn_ssp_enabled(struct hci_conn *conn)
@@ -1300,7 +1302,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_big_any_dst(struct hci_dev *
 		if (c->type != ISO_LINK)
 			continue;
 
-		if (handle == c->iso_qos.bcast.big) {
+		if (handle != BT_ISO_QOS_BIG_UNSET && handle == c->iso_qos.bcast.big) {
 			rcu_read_unlock();
 			return c;
 		}
@@ -1311,6 +1313,29 @@ static inline struct hci_conn *hci_conn_hash_lookup_big_any_dst(struct hci_dev *
 	return NULL;
 }
 
+static inline struct hci_conn *
+hci_conn_hash_lookup_pa_sync(struct hci_dev *hdev, __u8 big)
+{
+	struct hci_conn_hash *h = &hdev->conn_hash;
+	struct hci_conn  *c;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(c, &h->list, list) {
+		if (c->type != ISO_LINK ||
+			!test_bit(HCI_CONN_PA_SYNC, &c->flags))
+			continue;
+
+		if (c->iso_qos.bcast.big == big) {
+			rcu_read_unlock();
+			return c;
+		}
+	}
+	rcu_read_unlock();
+
+	return NULL;
+}
+
 static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev,
 							__u8 type, __u16 state)
 {
@@ -1435,7 +1460,8 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
 				 __u8 data_len, __u8 *data);
 int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type,
 		       __u8 sid, struct bt_iso_qos *qos);
-int hci_le_big_create_sync(struct hci_dev *hdev, struct bt_iso_qos *qos,
+int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
+			   struct bt_iso_qos *qos,
 			   __u16 sync_handle, __u8 num_bis, __u8 bis[]);
 int hci_conn_check_link_mode(struct hci_conn *conn);
 int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 95339623883c7..8b0c8e6313243 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -734,6 +734,7 @@ struct iso_list_data {
 	};
 	int count;
 	bool big_term;
+	bool pa_sync_term;
 	bool big_sync_term;
 };
 
@@ -807,7 +808,10 @@ static int big_terminate_sync(struct hci_dev *hdev, void *data)
 	if (d->big_sync_term)
 		hci_le_big_terminate_sync(hdev, d->big);
 
-	return hci_le_pa_terminate_sync(hdev, d->sync_handle);
+	if (d->pa_sync_term)
+		return hci_le_pa_terminate_sync(hdev, d->sync_handle);
+
+	return 0;
 }
 
 static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn)
@@ -823,6 +827,7 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c
 
 	d->big = big;
 	d->sync_handle = conn->sync_handle;
+	d->pa_sync_term = test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags);
 	d->big_sync_term = test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags);
 
 	ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d,
@@ -2099,7 +2104,8 @@ int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type,
 	return hci_cmd_sync_queue(hdev, create_pa_sync, cp, create_pa_complete);
 }
 
-int hci_le_big_create_sync(struct hci_dev *hdev, struct bt_iso_qos *qos,
+int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
+			   struct bt_iso_qos *qos,
 			   __u16 sync_handle, __u8 num_bis, __u8 bis[])
 {
 	struct _packed {
@@ -2115,6 +2121,9 @@ int hci_le_big_create_sync(struct hci_dev *hdev, struct bt_iso_qos *qos,
 	if (err)
 		return err;
 
+	if (hcon)
+		hcon->iso_qos.bcast.big = qos->bcast.big;
+
 	memset(&pdu, 0, sizeof(pdu));
 	pdu.cp.handle = qos->bcast.big;
 	pdu.cp.sync_handle = cpu_to_le16(sync_handle);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 559b6080706ce..b4b72070f5f6f 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6581,20 +6581,39 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data,
 	struct hci_ev_le_pa_sync_established *ev = data;
 	int mask = hdev->link_mode;
 	__u8 flags = 0;
+	struct hci_conn *bis;
 
 	bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
 
-	if (ev->status)
-		return;
-
 	hci_dev_lock(hdev);
 
 	hci_dev_clear_flag(hdev, HCI_PA_SYNC);
 
 	mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ISO_LINK, &flags);
-	if (!(mask & HCI_LM_ACCEPT))
+	if (!(mask & HCI_LM_ACCEPT)) {
 		hci_le_pa_term_sync(hdev, ev->handle);
+		goto unlock;
+	}
+
+	if (!(flags & HCI_PROTO_DEFER))
+		goto unlock;
+
+	/* Add connection to indicate the PA sync event */
+	bis = hci_conn_add(hdev, ISO_LINK, BDADDR_ANY,
+			   HCI_ROLE_SLAVE);
 
+	if (!bis)
+		goto unlock;
+
+	if (ev->status)
+		set_bit(HCI_CONN_PA_SYNC_FAILED, &bis->flags);
+	else
+		set_bit(HCI_CONN_PA_SYNC, &bis->flags);
+
+	/* Notify connection to iso layer */
+	hci_connect_cfm(bis, ev->status);
+
+unlock:
 	hci_dev_unlock(hdev);
 }
 
@@ -7045,6 +7064,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
 {
 	struct hci_evt_le_big_sync_estabilished *ev = data;
 	struct hci_conn *bis;
+	struct hci_conn *pa_sync;
 	int i;
 
 	bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
@@ -7055,6 +7075,15 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
 
 	hci_dev_lock(hdev);
 
+	if (!ev->status) {
+		pa_sync = hci_conn_hash_lookup_pa_sync(hdev, ev->handle);
+		if (pa_sync)
+			/* Also mark the BIG sync established event on the
+			 * associated PA sync hcon
+			 */
+			set_bit(HCI_CONN_BIG_SYNC, &pa_sync->flags);
+	}
+
 	for (i = 0; i < ev->num_bis; i++) {
 		u16 handle = le16_to_cpu(ev->bis[i]);
 		__le32 interval;
@@ -7068,6 +7097,10 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
 			bis->handle = handle;
 		}
 
+		if (ev->status != 0x42)
+			/* Mark PA sync as established */
+			set_bit(HCI_CONN_PA_SYNC, &bis->flags);
+
 		bis->iso_qos.bcast.big = ev->handle;
 		memset(&interval, 0, sizeof(interval));
 		memcpy(&interval, ev->latency, sizeof(ev->latency));
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index d10a0f36b947c..0cb7808171983 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5384,6 +5384,21 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
 		err = hci_reject_conn_sync(hdev, conn, reason);
 		break;
 	case BT_OPEN:
+		hci_dev_lock(hdev);
+
+		/* Cleanup bis or pa sync connections */
+		if (test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags) ||
+		    test_and_clear_bit(HCI_CONN_PA_SYNC_FAILED, &conn->flags)) {
+			hci_conn_failed(conn, reason);
+		} else if (test_bit(HCI_CONN_PA_SYNC, &conn->flags) ||
+			   test_bit(HCI_CONN_BIG_SYNC, &conn->flags)) {
+			conn->state = BT_CLOSED;
+			hci_disconn_cfm(conn, reason);
+			hci_conn_del(conn);
+		}
+
+		hci_dev_unlock(hdev);
+		return 0;
 	case BT_BOUND:
 		hci_dev_lock(hdev);
 		hci_conn_failed(conn, reason);
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 3c03e49422c75..2a2c37789e1f2 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -51,6 +51,7 @@ static void iso_sock_kill(struct sock *sk);
 /* iso_pinfo flags values */
 enum {
 	BT_SK_BIG_SYNC,
+	BT_SK_PA_SYNC,
 };
 
 struct iso_pinfo {
@@ -75,6 +76,8 @@ static struct bt_iso_qos default_qos;
 
 static bool check_ucast_qos(struct bt_iso_qos *qos);
 static bool check_bcast_qos(struct bt_iso_qos *qos);
+static bool iso_match_sid(struct sock *sk, void *data);
+static void iso_sock_disconn(struct sock *sk);
 
 /* ---- ISO timers ---- */
 #define ISO_CONN_TIMEOUT	(HZ * 40)
@@ -598,6 +601,15 @@ static void iso_sock_cleanup_listen(struct sock *parent)
 		iso_sock_kill(sk);
 	}
 
+	/* If listening socket stands for a PA sync connection,
+	 * properly disconnect the hcon and socket.
+	 */
+	if (iso_pi(parent)->conn && iso_pi(parent)->conn->hcon &&
+	    test_bit(HCI_CONN_PA_SYNC, &iso_pi(parent)->conn->hcon->flags)) {
+		iso_sock_disconn(parent);
+		return;
+	}
+
 	parent->sk_state  = BT_CLOSED;
 	sock_set_flag(parent, SOCK_ZAPPED);
 }
@@ -619,6 +631,16 @@ static void iso_sock_kill(struct sock *sk)
 	sock_put(sk);
 }
 
+static void iso_sock_disconn(struct sock *sk)
+{
+	sk->sk_state = BT_DISCONN;
+	iso_sock_set_timer(sk, ISO_DISCONN_TIMEOUT);
+	iso_conn_lock(iso_pi(sk)->conn);
+	hci_conn_drop(iso_pi(sk)->conn->hcon);
+	iso_pi(sk)->conn->hcon = NULL;
+	iso_conn_unlock(iso_pi(sk)->conn);
+}
+
 static void __iso_sock_close(struct sock *sk)
 {
 	BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket);
@@ -631,20 +653,19 @@ static void __iso_sock_close(struct sock *sk)
 	case BT_CONNECT:
 	case BT_CONNECTED:
 	case BT_CONFIG:
-		if (iso_pi(sk)->conn->hcon) {
-			sk->sk_state = BT_DISCONN;
-			iso_sock_set_timer(sk, ISO_DISCONN_TIMEOUT);
-			iso_conn_lock(iso_pi(sk)->conn);
-			hci_conn_drop(iso_pi(sk)->conn->hcon);
-			iso_pi(sk)->conn->hcon = NULL;
-			iso_conn_unlock(iso_pi(sk)->conn);
-		} else {
+		if (iso_pi(sk)->conn->hcon)
+			iso_sock_disconn(sk);
+		else
 			iso_chan_del(sk, ECONNRESET);
-		}
 		break;
 
 	case BT_CONNECT2:
-		iso_chan_del(sk, ECONNRESET);
+		if (iso_pi(sk)->conn->hcon &&
+		    (test_bit(HCI_CONN_PA_SYNC, &iso_pi(sk)->conn->hcon->flags) ||
+		    test_bit(HCI_CONN_PA_SYNC_FAILED, &iso_pi(sk)->conn->hcon->flags)))
+			iso_sock_disconn(sk);
+		else
+			iso_chan_del(sk, ECONNRESET);
 		break;
 	case BT_DISCONN:
 		iso_chan_del(sk, ECONNRESET);
@@ -1139,6 +1160,29 @@ static void iso_conn_defer_accept(struct hci_conn *conn)
 	hci_send_cmd(hdev, HCI_OP_LE_ACCEPT_CIS, sizeof(cp), &cp);
 }
 
+static void iso_conn_big_sync(struct sock *sk)
+{
+	int err;
+	struct hci_dev *hdev;
+
+	hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src,
+			     iso_pi(sk)->src_type);
+
+	if (!hdev)
+		return;
+
+	if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) {
+		err = hci_le_big_create_sync(hdev, iso_pi(sk)->conn->hcon,
+					     &iso_pi(sk)->qos,
+					     iso_pi(sk)->sync_handle,
+					     iso_pi(sk)->bc_num_bis,
+					     iso_pi(sk)->bc_bis);
+		if (err)
+			bt_dev_err(hdev, "hci_le_big_create_sync: %d",
+				   err);
+	}
+}
+
 static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 			    size_t len, int flags)
 {
@@ -1151,8 +1195,15 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 		lock_sock(sk);
 		switch (sk->sk_state) {
 		case BT_CONNECT2:
-			iso_conn_defer_accept(pi->conn->hcon);
-			sk->sk_state = BT_CONFIG;
+			if (pi->conn->hcon &&
+			    test_bit(HCI_CONN_PA_SYNC, &pi->conn->hcon->flags)) {
+				iso_conn_big_sync(sk);
+				sk->sk_state = BT_LISTEN;
+				set_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags);
+			} else {
+				iso_conn_defer_accept(pi->conn->hcon);
+				sk->sk_state = BT_CONFIG;
+			}
 			release_sock(sk);
 			return 0;
 		case BT_CONNECT:
@@ -1513,11 +1564,17 @@ static bool iso_match_big(struct sock *sk, void *data)
 	return ev->handle == iso_pi(sk)->qos.bcast.big;
 }
 
+static bool iso_match_pa_sync_flag(struct sock *sk, void *data)
+{
+	return test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags);
+}
+
 static void iso_conn_ready(struct iso_conn *conn)
 {
-	struct sock *parent;
+	struct sock *parent = NULL;
 	struct sock *sk = conn->sk;
-	struct hci_ev_le_big_sync_estabilished *ev;
+	struct hci_ev_le_big_sync_estabilished *ev = NULL;
+	struct hci_ev_le_pa_sync_established *ev2 = NULL;
 	struct hci_conn *hcon;
 
 	BT_DBG("conn %p", conn);
@@ -1529,15 +1586,32 @@ static void iso_conn_ready(struct iso_conn *conn)
 		if (!hcon)
 			return;
 
-		ev = hci_recv_event_data(hcon->hdev,
-					 HCI_EVT_LE_BIG_SYNC_ESTABILISHED);
-		if (ev)
+		if (test_bit(HCI_CONN_BIG_SYNC, &hcon->flags) ||
+		    test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) {
+			ev = hci_recv_event_data(hcon->hdev,
+						 HCI_EVT_LE_BIG_SYNC_ESTABILISHED);
+
+			/* Get reference to PA sync parent socket, if it exists */
 			parent = iso_get_sock_listen(&hcon->src,
 						     &hcon->dst,
-						     iso_match_big, ev);
-		else
+						     iso_match_pa_sync_flag, NULL);
+			if (!parent && ev)
+				parent = iso_get_sock_listen(&hcon->src,
+							     &hcon->dst,
+							     iso_match_big, ev);
+		} else if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags) ||
+				test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) {
+			ev2 = hci_recv_event_data(hcon->hdev,
+						  HCI_EV_LE_PA_SYNC_ESTABLISHED);
+			if (ev2)
+				parent = iso_get_sock_listen(&hcon->src,
+							     &hcon->dst,
+							     iso_match_sid, ev2);
+		}
+
+		if (!parent)
 			parent = iso_get_sock_listen(&hcon->src,
-						     BDADDR_ANY, NULL, NULL);
+							BDADDR_ANY, NULL, NULL);
 
 		if (!parent)
 			return;
@@ -1554,11 +1628,17 @@ static void iso_conn_ready(struct iso_conn *conn)
 		iso_sock_init(sk, parent);
 
 		bacpy(&iso_pi(sk)->src, &hcon->src);
-		iso_pi(sk)->src_type = hcon->src_type;
+
+		/* Convert from HCI to three-value type */
+		if (hcon->src_type == ADDR_LE_DEV_PUBLIC)
+			iso_pi(sk)->src_type = BDADDR_LE_PUBLIC;
+		else
+			iso_pi(sk)->src_type = BDADDR_LE_RANDOM;
 
 		/* If hcon has no destination address (BDADDR_ANY) it means it
-		 * was created by HCI_EV_LE_BIG_SYNC_ESTABILISHED so we need to
-		 * initialize using the parent socket destination address.
+		 * was created by HCI_EV_LE_BIG_SYNC_ESTABILISHED or
+		 * HCI_EV_LE_PA_SYNC_ESTABLISHED so we need to initialize using
+		 * the parent socket destination address.
 		 */
 		if (!bacmp(&hcon->dst, BDADDR_ANY)) {
 			bacpy(&hcon->dst, &iso_pi(parent)->dst);
@@ -1566,13 +1646,21 @@ static void iso_conn_ready(struct iso_conn *conn)
 			hcon->sync_handle = iso_pi(parent)->sync_handle;
 		}
 
+		if (ev2 && !ev2->status) {
+			iso_pi(sk)->sync_handle = iso_pi(parent)->sync_handle;
+			iso_pi(sk)->qos = iso_pi(parent)->qos;
+			iso_pi(sk)->bc_num_bis = iso_pi(parent)->bc_num_bis;
+			memcpy(iso_pi(sk)->bc_bis, iso_pi(parent)->bc_bis, ISO_MAX_NUM_BIS);
+		}
+
 		bacpy(&iso_pi(sk)->dst, &hcon->dst);
 		iso_pi(sk)->dst_type = hcon->dst_type;
 
 		hci_conn_hold(hcon);
 		iso_chan_add(conn, sk, parent);
 
-		if (ev && ((struct hci_evt_le_big_sync_estabilished *)ev)->status) {
+		if ((ev && ((struct hci_evt_le_big_sync_estabilished *)ev)->status) ||
+		    (ev2 && ev2->status)) {
 			/* Trigger error signal on child socket */
 			sk->sk_err = ECONNREFUSED;
 			sk->sk_error_report(sk);
@@ -1630,7 +1718,7 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 	if (ev1) {
 		sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, iso_match_sid,
 					 ev1);
-		if (sk)
+		if (sk && !ev1->status)
 			iso_pi(sk)->sync_handle = le16_to_cpu(ev1->handle);
 
 		goto done;
@@ -1638,16 +1726,21 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 
 	ev2 = hci_recv_event_data(hdev, HCI_EVT_LE_BIG_INFO_ADV_REPORT);
 	if (ev2) {
+		/* Try to get PA sync listening socket, if it exists */
 		sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr,
-					 iso_match_sync_handle, ev2);
+						iso_match_pa_sync_flag, NULL);
+		if (!sk)
+			sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr,
+						 iso_match_sync_handle, ev2);
 		if (sk) {
 			int err;
 
 			if (ev2->num_bis < iso_pi(sk)->bc_num_bis)
 				iso_pi(sk)->bc_num_bis = ev2->num_bis;
 
-			if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) {
-				err = hci_le_big_create_sync(hdev,
+			if (!test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) &&
+			    !test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) {
+				err = hci_le_big_create_sync(hdev, NULL,
 							     &iso_pi(sk)->qos,
 							     iso_pi(sk)->sync_handle,
 							     iso_pi(sk)->bc_num_bis,
@@ -1699,12 +1792,13 @@ static void iso_connect_cfm(struct hci_conn *hcon, __u8 status)
 
 	BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status);
 
-	/* Similar to the success case, if HCI_CONN_BIG_SYNC_FAILED is set,
-	 * queue the failed bis connection into the accept queue of the
-	 * listening socket and wake up userspace, to inform the user about
-	 * the BIG sync failed event.
+	/* Similar to the success case, if HCI_CONN_BIG_SYNC_FAILED or
+	 * HCI_CONN_PA_SYNC_FAILED is set, queue the failed connection
+	 * into the accept queue of the listening socket and wake up
+	 * userspace, to inform the user about the event.
 	 */
-	if (!status || test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) {
+	if (!status || test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags) ||
+	    test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) {
 		struct iso_conn *conn;
 
 		conn = iso_conn_add(hcon);
-- 
GitLab


From db08722fc7d46168fe31d9b8a7b29229dd959f9f Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 18 Aug 2023 14:19:27 -0700
Subject: [PATCH 1640/1806] Bluetooth: hci_core: Fix missing instances using
 HCI_MAX_AD_LENGTH

There a few instances still using HCI_MAX_AD_LENGTH instead of using
max_adv_len which takes care of detecting what is the actual maximum
length depending on if the controller supports EA or not.

Fixes: 112b5090c219 ("Bluetooth: MGMT: Fix always using HCI_MAX_AD_LENGTH")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h | 6 +++---
 net/bluetooth/eir.c              | 2 +-
 net/bluetooth/mgmt.c             | 6 +++---
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 6fb055e3c595b..6e2988b11f998 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -83,7 +83,7 @@ struct discovery_state {
 	u8			last_adv_addr_type;
 	s8			last_adv_rssi;
 	u32			last_adv_flags;
-	u8			last_adv_data[HCI_MAX_AD_LENGTH];
+	u8			last_adv_data[HCI_MAX_EXT_AD_LENGTH];
 	u8			last_adv_data_len;
 	bool			report_invalid_rssi;
 	bool			result_filtering;
@@ -290,7 +290,7 @@ struct adv_pattern {
 	__u8 ad_type;
 	__u8 offset;
 	__u8 length;
-	__u8 value[HCI_MAX_AD_LENGTH];
+	__u8 value[HCI_MAX_EXT_AD_LENGTH];
 };
 
 struct adv_rssi_thresholds {
@@ -726,7 +726,7 @@ struct hci_conn {
 	__u16		le_conn_interval;
 	__u16		le_conn_latency;
 	__u16		le_supv_timeout;
-	__u8		le_adv_data[HCI_MAX_AD_LENGTH];
+	__u8		le_adv_data[HCI_MAX_EXT_AD_LENGTH];
 	__u8		le_adv_data_len;
 	__u8		le_per_adv_data[HCI_MAX_PER_AD_LENGTH];
 	__u8		le_per_adv_data_len;
diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c
index 8a85f6cdfbc16..9214189279e80 100644
--- a/net/bluetooth/eir.c
+++ b/net/bluetooth/eir.c
@@ -33,7 +33,7 @@ u8 eir_append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len)
 	size_t complete_len;
 
 	/* no space left for name (+ NULL + type + len) */
-	if ((HCI_MAX_AD_LENGTH - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3)
+	if ((max_adv_len(hdev) - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3)
 		return ad_len;
 
 	/* use complete name if present and fits */
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index d6c9b7bc85929..ba2e00646e8e8 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -5381,9 +5381,9 @@ static u8 parse_adv_monitor_pattern(struct adv_monitor *m, u8 pattern_count,
 	for (i = 0; i < pattern_count; i++) {
 		offset = patterns[i].offset;
 		length = patterns[i].length;
-		if (offset >= HCI_MAX_AD_LENGTH ||
-		    length > HCI_MAX_AD_LENGTH ||
-		    (offset + length) > HCI_MAX_AD_LENGTH)
+		if (offset >= HCI_MAX_EXT_AD_LENGTH ||
+		    length > HCI_MAX_EXT_AD_LENGTH ||
+		    (offset + length) > HCI_MAX_EXT_AD_LENGTH)
 			return MGMT_STATUS_INVALID_PARAMS;
 
 		p = kmalloc(sizeof(*p), GFP_KERNEL);
-- 
GitLab


From 3344d318337d9dca928fd448e966557ec5063f85 Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Sat, 19 Aug 2023 16:33:36 +0300
Subject: [PATCH 1641/1806] Bluetooth: hci_conn: fail SCO/ISO via
 hci_conn_failed if ACL gone early

Not calling hci_(dis)connect_cfm before deleting conn referred to by a
socket generally results to use-after-free.

When cleaning up SCO connections when the parent ACL is deleted too
early, use hci_conn_failed to do the connection cleanup properly.

We also need to clean up ISO connections in a similar situation when
connecting has started but LE Create CIS is not yet sent, so do it too
here.

Fixes: ca1fd42e7dbf ("Bluetooth: Fix potential double free caused by hci_conn_unlink")
Reported-by: syzbot+cf54c1da6574b6c1b049@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-bluetooth/00000000000013b93805fbbadc50@google.com/
Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 8b0c8e6313243..9d5057cef30a3 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1044,6 +1044,29 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst,
 	return conn;
 }
 
+static void hci_conn_cleanup_child(struct hci_conn *conn, u8 reason)
+{
+	if (!reason)
+		reason = HCI_ERROR_REMOTE_USER_TERM;
+
+	/* Due to race, SCO/ISO conn might be not established yet at this point,
+	 * and nothing else will clean it up. In other cases it is done via HCI
+	 * events.
+	 */
+	switch (conn->type) {
+	case SCO_LINK:
+	case ESCO_LINK:
+		if (HCI_CONN_HANDLE_UNSET(conn->handle))
+			hci_conn_failed(conn, reason);
+		break;
+	case ISO_LINK:
+		if (conn->state != BT_CONNECTED &&
+		    !test_bit(HCI_CONN_CREATE_CIS, &conn->flags))
+			hci_conn_failed(conn, reason);
+		break;
+	}
+}
+
 static void hci_conn_unlink(struct hci_conn *conn)
 {
 	struct hci_dev *hdev = conn->hdev;
@@ -1066,14 +1089,7 @@ static void hci_conn_unlink(struct hci_conn *conn)
 			if (!test_bit(HCI_UP, &hdev->flags))
 				continue;
 
-			/* Due to race, SCO connection might be not established
-			 * yet at this point. Delete it now, otherwise it is
-			 * possible for it to be stuck and can't be deleted.
-			 */
-			if ((child->type == SCO_LINK ||
-			     child->type == ESCO_LINK) &&
-			    HCI_CONN_HANDLE_UNSET(child->handle))
-				hci_conn_del(child);
+			hci_conn_cleanup_child(child, conn->abort_reason);
 		}
 
 		return;
-- 
GitLab


From 9c0826310bfb784c9bac7d1d9454e304185446c5 Mon Sep 17 00:00:00 2001
From: Claudia Draghicescu <claudia.rosu@nxp.com>
Date: Fri, 30 Jun 2023 12:59:28 +0300
Subject: [PATCH 1642/1806] Bluetooth: ISO: Add support for periodic adv
 reports processing

In the case of a Periodic Synchronized Receiver,
the PA report received from a Broadcaster contains the BASE,
which has information about codec and other parameters of a BIG.
This isnformation is stored and the application can retrieve it
using getsockopt(BT_ISO_BASE).

Signed-off-by: Claudia Draghicescu <claudia.rosu@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci.h | 11 +++++++++++
 net/bluetooth/hci_event.c   | 23 +++++++++++++++++++++++
 net/bluetooth/iso.c         | 28 +++++++++++++++++++++++++++-
 3 files changed, 61 insertions(+), 1 deletion(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 5723405b833e9..c58425d4c592c 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -2771,6 +2771,17 @@ struct hci_ev_le_enh_conn_complete {
 	__u8      clk_accurancy;
 } __packed;
 
+#define HCI_EV_LE_PER_ADV_REPORT    0x0f
+struct hci_ev_le_per_adv_report {
+	__le16	 sync_handle;
+	__u8	 tx_power;
+	__u8	 rssi;
+	__u8	 cte_type;
+	__u8	 data_status;
+	__u8     length;
+	__u8     data[];
+} __packed;
+
 #define HCI_EV_LE_EXT_ADV_SET_TERM	0x12
 struct hci_evt_le_ext_adv_set_term {
 	__u8	status;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index b4b72070f5f6f..35f251041eeb9 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6617,6 +6617,24 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+static void hci_le_per_adv_report_evt(struct hci_dev *hdev, void *data,
+				      struct sk_buff *skb)
+{
+	struct hci_ev_le_per_adv_report *ev = data;
+	int mask = hdev->link_mode;
+	__u8 flags = 0;
+
+	bt_dev_dbg(hdev, "sync_handle 0x%4.4x", le16_to_cpu(ev->sync_handle));
+
+	hci_dev_lock(hdev);
+
+	mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, ISO_LINK, &flags);
+	if (!(mask & HCI_LM_ACCEPT))
+		hci_le_pa_term_sync(hdev, ev->sync_handle);
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, void *data,
 					    struct sk_buff *skb)
 {
@@ -7213,6 +7231,11 @@ static const struct hci_le_ev {
 	HCI_LE_EV(HCI_EV_LE_PA_SYNC_ESTABLISHED,
 		  hci_le_pa_sync_estabilished_evt,
 		  sizeof(struct hci_ev_le_pa_sync_established)),
+	/* [0x0f = HCI_EV_LE_PER_ADV_REPORT] */
+	HCI_LE_EV_VL(HCI_EV_LE_PER_ADV_REPORT,
+				 hci_le_per_adv_report_evt,
+				 sizeof(struct hci_ev_le_per_adv_report),
+				 HCI_MAX_EVENT_SIZE),
 	/* [0x12 = HCI_EV_LE_EXT_ADV_SET_TERM] */
 	HCI_LE_EV(HCI_EV_LE_EXT_ADV_SET_TERM, hci_le_ext_adv_term_evt,
 		  sizeof(struct hci_evt_le_ext_adv_set_term)),
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 2a2c37789e1f2..16da946f5881b 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1446,7 +1446,8 @@ static int iso_sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case BT_ISO_BASE:
-		if (sk->sk_state == BT_CONNECTED) {
+		if (sk->sk_state == BT_CONNECTED &&
+		    !bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) {
 			base_len = iso_pi(sk)->conn->hcon->le_per_adv_data_len;
 			base = iso_pi(sk)->conn->hcon->le_per_adv_data;
 		} else {
@@ -1655,6 +1656,9 @@ static void iso_conn_ready(struct iso_conn *conn)
 
 		bacpy(&iso_pi(sk)->dst, &hcon->dst);
 		iso_pi(sk)->dst_type = hcon->dst_type;
+		iso_pi(sk)->sync_handle = iso_pi(parent)->sync_handle;
+		memcpy(iso_pi(sk)->base, iso_pi(parent)->base, iso_pi(parent)->base_len);
+		iso_pi(sk)->base_len = iso_pi(parent)->base_len;
 
 		hci_conn_hold(hcon);
 		iso_chan_add(conn, sk, parent);
@@ -1692,12 +1696,20 @@ static bool iso_match_sync_handle(struct sock *sk, void *data)
 	return le16_to_cpu(ev->sync_handle) == iso_pi(sk)->sync_handle;
 }
 
+static bool iso_match_sync_handle_pa_report(struct sock *sk, void *data)
+{
+	struct hci_ev_le_per_adv_report *ev = data;
+
+	return le16_to_cpu(ev->sync_handle) == iso_pi(sk)->sync_handle;
+}
+
 /* ----- ISO interface with lower layer (HCI) ----- */
 
 int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 {
 	struct hci_ev_le_pa_sync_established *ev1;
 	struct hci_evt_le_big_info_adv_report *ev2;
+	struct hci_ev_le_per_adv_report *ev3;
 	struct sock *sk;
 	int lm = 0;
 
@@ -1713,6 +1725,9 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 	 * 2. HCI_EVT_LE_BIG_INFO_ADV_REPORT: When connect_ind is triggered by a
 	 * a BIG Info it attempts to check if there any listening socket with
 	 * the same sync_handle and if it does then attempt to create a sync.
+	 * 3. HCI_EV_LE_PER_ADV_REPORT: When a PA report is received, it is stored
+	 * in iso_pi(sk)->base so it can be passed up to user, in the case of a
+	 * broadcast sink.
 	 */
 	ev1 = hci_recv_event_data(hdev, HCI_EV_LE_PA_SYNC_ESTABLISHED);
 	if (ev1) {
@@ -1752,6 +1767,17 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 				}
 			}
 		}
+	}
+
+	ev3 = hci_recv_event_data(hdev, HCI_EV_LE_PER_ADV_REPORT);
+	if (ev3) {
+		sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr,
+					 iso_match_sync_handle_pa_report, ev3);
+
+		if (sk) {
+			memcpy(iso_pi(sk)->base, ev3->data, ev3->length);
+			iso_pi(sk)->base_len = ev3->length;
+		}
 	} else {
 		sk = iso_get_sock_listen(&hdev->bdaddr, BDADDR_ANY, NULL, NULL);
 	}
-- 
GitLab


From 7866b9faf0a8c20de41f3d08fb5cae9bdcf7756f Mon Sep 17 00:00:00 2001
From: Lokendra Singh <lokendra.singh@intel.com>
Date: Thu, 17 Aug 2023 17:12:50 +0530
Subject: [PATCH 1643/1806] Bluetooth: btintel: Send new command for PPAG

Added support for the new command opcode FE0B
(HCI Intel PPAG Enable).

btmon log:
< HCI Command: Intel PPAG Enable (0x3f|0x020b) plen 4
        Enable: 0x00000002
> HCI Event: Command Complete (0x0e) plen 4
      Intel PPAG Enable (0x3f|0x020b) ncmd 1
        Status: Success (0x00)

Signed-off-by: Seema Sreemantha <seema.sreemantha@intel.com>
Signed-off-by: Lokendra Singh <lokendra.singh@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.c | 25 ++++++++++++++++---------
 drivers/bluetooth/btintel.h |  7 +++----
 2 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 633e8d9bf58f9..9b239ce96fa45 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -2401,7 +2401,7 @@ static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver
 {
 	struct btintel_ppag ppag;
 	struct sk_buff *skb;
-	struct btintel_loc_aware_reg ppag_cmd;
+	struct hci_ppag_enable_cmd ppag_cmd;
 	acpi_handle handle;
 
 	/* PPAG is not supported if CRF is HrP2, Jfp2, JfP1 */
@@ -2409,6 +2409,8 @@ static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver
 	case 0x504:     /* Hrp2 */
 	case 0x202:     /* Jfp2 */
 	case 0x201:     /* Jfp1 */
+		bt_dev_dbg(hdev, "PPAG not supported for Intel CNVr (0x%3x)",
+			   ver->cnvr_top & 0xFFF);
 		return;
 	}
 
@@ -2434,24 +2436,29 @@ static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver
 	}
 
 	if (ppag.domain != 0x12) {
-		bt_dev_warn(hdev, "PPAG-BT: domain is not bluetooth");
+		bt_dev_dbg(hdev, "PPAG-BT: Bluetooth domain is disabled in ACPI firmware");
 		return;
 	}
 
-	/* PPAG mode, BIT0 = 0 Disabled, BIT0 = 1 Enabled */
-	if (!(ppag.mode & BIT(0))) {
-		bt_dev_dbg(hdev, "PPAG-BT: disabled");
+	/* PPAG mode
+	 * BIT 0 : 0 Disabled in EU
+	 *         1 Enabled in EU
+	 * BIT 1 : 0 Disabled in China
+	 *         1 Enabled in China
+	 */
+	if ((ppag.mode & 0x01) != BIT(0) && (ppag.mode & 0x02) != BIT(1)) {
+		bt_dev_dbg(hdev, "PPAG-BT: EU, China mode are disabled in CB/BIOS");
 		return;
 	}
 
-	ppag_cmd.mcc = cpu_to_le32(0);
-	ppag_cmd.sel = cpu_to_le32(0); /* 0 - Enable , 1 - Disable, 2 - Testing mode */
-	ppag_cmd.delta = cpu_to_le32(0);
-	skb = __hci_cmd_sync(hdev, 0xfe19, sizeof(ppag_cmd), &ppag_cmd, HCI_CMD_TIMEOUT);
+	ppag_cmd.ppag_enable_flags = cpu_to_le32(ppag.mode);
+
+	skb = __hci_cmd_sync(hdev, INTEL_OP_PPAG_CMD, sizeof(ppag_cmd), &ppag_cmd, HCI_CMD_TIMEOUT);
 	if (IS_ERR(skb)) {
 		bt_dev_warn(hdev, "Failed to send PPAG Enable (%ld)", PTR_ERR(skb));
 		return;
 	}
+	bt_dev_info(hdev, "PPAG-BT: Enabled (Mode %d)", ppag.mode);
 	kfree_skb(skb);
 }
 
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 2ed646609deec..3a2d5b4219ddb 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -137,10 +137,9 @@ struct intel_offload_use_cases {
 	__u8	preset[8];
 } __packed;
 
-struct btintel_loc_aware_reg {
-	__le32 mcc;
-	__le32 sel;
-	__le32 delta;
+#define INTEL_OP_PPAG_CMD		0xFE0B
+struct hci_ppag_enable_cmd {
+	__le32	ppag_enable_flags;
 } __packed;
 
 #define INTEL_TLV_TYPE_ID		0x01
-- 
GitLab


From 253f3399f4c09ce6f4e67350f839be0361b4d5ff Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 22 Aug 2023 12:02:03 -0700
Subject: [PATCH 1644/1806] Bluetooth: HCI: Introduce HCI_QUIRK_BROKEN_LE_CODED

This introduces HCI_QUIRK_BROKEN_LE_CODED which is used to indicate
that LE Coded PHY shall not be used, it is then set for some Intel
models that claim to support it but when used causes many problems.

Cc: stable@vger.kernel.org # 6.4.y+
Link: https://github.com/bluez/bluez/issues/577
Link: https://github.com/bluez/bluez/issues/582
Link: https://lore.kernel.org/linux-bluetooth/CABBYNZKco-v7wkjHHexxQbgwwSz-S=GZ=dZKbRE1qxT1h4fFbQ@mail.gmail.com/T/#
Fixes: 288c90224eec ("Bluetooth: Enable all supported LE PHY by default")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.c      |  6 ++++++
 include/net/bluetooth/hci.h      | 10 ++++++++++
 include/net/bluetooth/hci_core.h |  4 +++-
 net/bluetooth/hci_sync.c         |  5 ++++-
 4 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 9b239ce96fa45..2462796a512a5 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -2787,6 +2787,9 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 			set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
 				&hdev->quirks);
 
+			/* These variants don't seem to support LE Coded PHY */
+			set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks);
+
 			/* Setup MSFT Extension support */
 			btintel_set_msft_opcode(hdev, ver.hw_variant);
 
@@ -2858,6 +2861,9 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 		 */
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
 
+		/* These variants don't seem to support LE Coded PHY */
+		set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks);
+
 		/* Set Valid LE States quirk */
 		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
 
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index c58425d4c592c..87d92accc26ea 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -319,6 +319,16 @@ enum {
 	 * This quirk must be set before hci_register_dev is called.
 	 */
 	HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER,
+
+	/*
+	 * When this quirk is set, LE Coded PHY shall not be used. This is
+	 * required for some Intel controllers which erroneously claim to
+	 * support it but it causes problems with extended scanning.
+	 *
+	 * This quirk can be set before hci_register_dev is called or
+	 * during the hdev->setup vendor callback.
+	 */
+	HCI_QUIRK_BROKEN_LE_CODED,
 };
 
 /* HCI device flags */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 6e2988b11f998..e6359f7346f1f 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1817,7 +1817,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define scan_2m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_2M) || \
 		      ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_2M))
 
-#define le_coded_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_CODED))
+#define le_coded_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_CODED) && \
+			       !test_bit(HCI_QUIRK_BROKEN_LE_CODED, \
+					 &(dev)->quirks))
 
 #define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \
 			 ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED))
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 0cb7808171983..9b93653c61973 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4668,7 +4668,10 @@ static const struct {
 			 "advertised, but not supported."),
 	HCI_QUIRK_BROKEN(SET_RPA_TIMEOUT,
 			 "HCI LE Set Random Private Address Timeout command is "
-			 "advertised, but not supported.")
+			 "advertised, but not supported."),
+	HCI_QUIRK_BROKEN(LE_CODED,
+			 "HCI LE Coded PHY feature bit is set, "
+			 "but its usage is not supported.")
 };
 
 /* This function handles hdev setup stage:
-- 
GitLab


From d831e3612111d385e8629104af5429808ef26e25 Mon Sep 17 00:00:00 2001
From: Bastien Nocera <hadess@hadess.net>
Date: Tue, 22 Aug 2023 12:20:24 +0200
Subject: [PATCH 1645/1806] Bluetooth: btusb: Fix quirks table naming

The quirks table was named "blacklist_table" which isn't a good
description for that table as devices detected using it weren't ignored
by the driver.

Rename the table to match what it actually does.

Signed-off-by: Bastien Nocera <hadess@hadess.net>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 1bb3b09013b07..e98f5fc06cfdb 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -175,7 +175,7 @@ static const struct usb_device_id btusb_table[] = {
 
 MODULE_DEVICE_TABLE(usb, btusb_table);
 
-static const struct usb_device_id blacklist_table[] = {
+static const struct usb_device_id quirks_table[] = {
 	/* CSR BlueCore devices */
 	{ USB_DEVICE(0x0a12, 0x0001), .driver_info = BTUSB_CSR },
 
@@ -4194,7 +4194,7 @@ static int btusb_probe(struct usb_interface *intf,
 	if (!id->driver_info) {
 		const struct usb_device_id *match;
 
-		match = usb_match_id(intf, blacklist_table);
+		match = usb_match_id(intf, quirks_table);
 		if (match)
 			id = match;
 	}
-- 
GitLab


From 2a05334d7f91ff189692089c05fc48cc1d8204de Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Wed, 23 Aug 2023 11:46:37 +0800
Subject: [PATCH 1646/1806] Bluetooth: btusb: Do not call kfree_skb() under
 spin_lock_irqsave()

It is not allowed to call kfree_skb() from hardware interrupt
context or with hardware interrupts being disabled.
So replace kfree_skb() with dev_kfree_skb_irq() under
spin_lock_irqsave(). Compile tested only.

Fixes: baac6276c0a9 ("Bluetooth: btusb: handle mSBC audio over USB Endpoints")
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index e98f5fc06cfdb..82597ab4f747b 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2162,7 +2162,7 @@ static int btusb_switch_alt_setting(struct hci_dev *hdev, int new_alts)
 		 * alternate setting.
 		 */
 		spin_lock_irqsave(&data->rxlock, flags);
-		kfree_skb(data->sco_skb);
+		dev_kfree_skb_irq(data->sco_skb);
 		data->sco_skb = NULL;
 		spin_unlock_irqrestore(&data->rxlock, flags);
 
-- 
GitLab


From 3ed247e789114c5bbb3380c3666eb819336b94e5 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Fri, 28 Jul 2023 17:17:59 -0700
Subject: [PATCH 1647/1806] igc: Add support for multiple in-flight TX
 timestamps

Add support for using the four sets of timestamping registers that
i225/i226 have available for TX.

In some workloads, where multiple applications request hardware
transmission timestamps, it was possible that some of those requests
were denied because the only in use register was already occupied.

This is also in preparation to future support for hardware
timestamping with multiple PTP domains. With multiple domains chances
of multiple TX timestamps being requested at the same time increase.

Before:
$ sudo ./ntpperf -i enp3s0 -m 10:22:22:22:22:21 -d 192.168.1.3 -s 172.18.0.0/16 -I -H -o 37
               |          responses            |     TX timestamp offset (ns)
rate   clients |  lost invalid   basic  xleave |    min    mean     max stddev
1000       100   0.00%   0.00%   0.00% 100.00%       +1     +41     +73     13
1500       150   0.00%   0.00%   0.00% 100.00%       +9     +49     +87     15
2250       225   0.00%   0.00%   0.00% 100.00%       +9     +42     +79     13
3375       337   0.00%   0.00%   0.00% 100.00%      +11     +46     +81     13
5062       506   0.00%   0.00%   0.00% 100.00%       +7     +44     +80     13
7593       759   0.00%   0.00%   0.00% 100.00%       +9     +44     +79     12
11389     1138   0.00%   0.00%   0.00% 100.00%      +14     +51     +87     13
17083     1708   0.00%   0.00%   0.00% 100.00%       +1     +41     +80     14
25624     2562   0.00%   0.00%   0.00% 100.00%      +11     +50   +5107     51
38436     3843   0.00%   0.00%   0.00% 100.00%       -2     +36   +7843     38
57654     5765   0.00%   0.00%   0.00% 100.00%       +4     +42  +10503     69
86481     8648   0.00%   0.00%   0.00% 100.00%      +11     +54   +5492     65
129721   12972   0.00%   0.00%   0.00% 100.00%      +31   +2680   +6942   2606
194581   16384  16.79%   0.00%   0.87%  82.34%      +73   +4444  +15879   3116
291871   16384  35.05%   0.00%   1.53%  63.42%     +188   +5381  +17019   3035
437806   16384  54.95%   0.00%   2.55%  42.50%     +233   +6302  +13885   2846

After:
$ sudo ./ntpperf -i enp3s0 -m 10:22:22:22:22:21 -d 192.168.1.3 -s 172.18.0.0/16 -I -H -o 37
               |          responses            |     TX timestamp offset (ns)
rate   clients |  lost invalid   basic  xleave |    min    mean     max stddev
1000       100   0.00%   0.00%   0.00% 100.00%      -20     +12     +43     13
1500       150   0.00%   0.00%   0.00% 100.00%      -23     +18     +57     14
2250       225   0.00%   0.00%   0.00% 100.00%       -2     +33     +67     13
3375       337   0.00%   0.00%   0.00% 100.00%       +1     +38     +76     13
5062       506   0.00%   0.00%   0.00% 100.00%       +9     +52     +93     14
7593       759   0.00%   0.00%   0.00% 100.00%      +11     +47     +82     13
11389     1138   0.00%   0.00%   0.00% 100.00%       -9     +27     +74     13
17083     1708   0.00%   0.00%   0.00% 100.00%      -13     +25     +66     14
25624     2562   0.00%   0.00%   0.00% 100.00%       -8     +28     +65     13
38436     3843   0.00%   0.00%   0.00% 100.00%      -13     +28     +69     13
57654     5765   0.00%   0.00%   0.00% 100.00%      -11     +32     +71     14
86481     8648   0.00%   0.00%   0.00% 100.00%       +2     +44     +83     14
129721   12972  15.36%   0.00%   0.35%  84.29%       -2   +2248  +22907   4252
194581   16384  42.98%   0.00%   1.98%  55.04%       -4   +5278  +65039   5856
291871   16384  54.33%   0.00%   2.21%  43.46%       -3   +6306  +22608   5665

We can see that with 4 registers, as expected, we are able to handle a
increasing number of requests more consistently, but as soon as all
registers are in use, the decrease in quality of service happens in a
sharp step.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  18 +-
 drivers/net/ethernet/intel/igc/igc_base.h    |   3 +
 drivers/net/ethernet/intel/igc/igc_defines.h |   7 +
 drivers/net/ethernet/intel/igc/igc_main.c    |  41 ++++-
 drivers/net/ethernet/intel/igc/igc_ptp.c     | 174 +++++++++++++------
 drivers/net/ethernet/intel/igc/igc_regs.h    |  12 ++
 6 files changed, 192 insertions(+), 63 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 1c6ab340c020a..8ebe6999a528c 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -38,6 +38,8 @@ void igc_ethtool_set_ops(struct net_device *);
 
 #define MAX_FLEX_FILTER			32
 
+#define IGC_MAX_TX_TSTAMP_REGS		4
+
 enum igc_mac_filter_type {
 	IGC_MAC_FILTER_TYPE_DST = 0,
 	IGC_MAC_FILTER_TYPE_SRC
@@ -70,6 +72,15 @@ struct igc_rx_packet_stats {
 	u64 other_packets;
 };
 
+struct igc_tx_timestamp_request {
+	struct sk_buff *skb;   /* reference to the packet being timestamped */
+	unsigned long start;   /* when the tstamp request started (jiffies) */
+	u32 mask;              /* _TSYNCTXCTL_TXTT_{X} bit for this request */
+	u32 regl;              /* which TXSTMPL_{X} register should be used */
+	u32 regh;              /* which TXSTMPH_{X} register should be used */
+	u32 flags;             /* flags that should be added to the tx_buffer */
+};
+
 struct igc_ring_container {
 	struct igc_ring *ring;          /* pointer to linked list of rings */
 	unsigned int total_bytes;       /* total bytes processed this int */
@@ -245,9 +256,8 @@ struct igc_adapter {
 	 * ptp_tx_lock.
 	 */
 	spinlock_t ptp_tx_lock;
-	struct sk_buff *ptp_tx_skb;
+	struct igc_tx_timestamp_request tx_tstamp[IGC_MAX_TX_TSTAMP_REGS];
 	struct hwtstamp_config tstamp_config;
-	unsigned long ptp_tx_start;
 	unsigned int ptp_flags;
 	/* System time value lock */
 	spinlock_t tmreg_lock;
@@ -455,6 +465,10 @@ enum igc_tx_flags {
 	/* olinfo flags */
 	IGC_TX_FLAGS_IPV4	= 0x10,
 	IGC_TX_FLAGS_CSUM	= 0x20,
+
+	IGC_TX_FLAGS_TSTAMP_1	= 0x100,
+	IGC_TX_FLAGS_TSTAMP_2	= 0x200,
+	IGC_TX_FLAGS_TSTAMP_3	= 0x400,
 };
 
 enum igc_boards {
diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h
index 9f3827eda157c..f7d6491d4c608 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.h
+++ b/drivers/net/ethernet/intel/igc/igc_base.h
@@ -34,6 +34,9 @@ struct igc_adv_tx_context_desc {
 
 /* Adv Transmit Descriptor Config Masks */
 #define IGC_ADVTXD_MAC_TSTAMP	0x00080000 /* IEEE1588 Timestamp packet */
+#define IGC_ADVTXD_TSTAMP_REG_1	0x00010000 /* Select register 1 for timestamp */
+#define IGC_ADVTXD_TSTAMP_REG_2	0x00020000 /* Select register 2 for timestamp */
+#define IGC_ADVTXD_TSTAMP_REG_3	0x00030000 /* Select register 3 for timestamp */
 #define IGC_ADVTXD_DTYP_CTXT	0x00200000 /* Advanced Context Descriptor */
 #define IGC_ADVTXD_DTYP_DATA	0x00300000 /* Advanced Data Descriptor */
 #define IGC_ADVTXD_DCMD_EOP	0x01000000 /* End of Packet */
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 2f780cc90883c..700827bdd626e 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -454,6 +454,9 @@
 
 /* Time Sync Transmit Control bit definitions */
 #define IGC_TSYNCTXCTL_TXTT_0			0x00000001  /* Tx timestamp reg 0 valid */
+#define IGC_TSYNCTXCTL_TXTT_1			0x00000002  /* Tx timestamp reg 1 valid */
+#define IGC_TSYNCTXCTL_TXTT_2			0x00000004  /* Tx timestamp reg 2 valid */
+#define IGC_TSYNCTXCTL_TXTT_3			0x00000008  /* Tx timestamp reg 3 valid */
 #define IGC_TSYNCTXCTL_ENABLED			0x00000010  /* enable Tx timestamping */
 #define IGC_TSYNCTXCTL_MAX_ALLOWED_DLY_MASK	0x0000F000  /* max delay */
 #define IGC_TSYNCTXCTL_SYNC_COMP_ERR		0x20000000  /* sync err */
@@ -461,6 +464,10 @@
 #define IGC_TSYNCTXCTL_START_SYNC		0x80000000  /* initiate sync */
 #define IGC_TSYNCTXCTL_TXSYNSIG			0x00000020  /* Sample TX tstamp in PHY sop */
 
+#define IGC_TSYNCTXCTL_TXTT_ANY ( \
+		IGC_TSYNCTXCTL_TXTT_0 | IGC_TSYNCTXCTL_TXTT_1 | \
+		IGC_TSYNCTXCTL_TXTT_2 | IGC_TSYNCTXCTL_TXTT_3)
+
 /* Timer selection bits */
 #define IGC_AUX_IO_TIMER_SEL_SYSTIM0	(0u << 30) /* Select SYSTIM0 for auxiliary time stamp */
 #define IGC_AUX_IO_TIMER_SEL_SYSTIM1	(1u << 30) /* Select SYSTIM1 for auxiliary time stamp */
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index e7701866d8b47..293b457176838 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1271,10 +1271,21 @@ static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags)
 	cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSO,
 				 (IGC_ADVTXD_DCMD_TSE));
 
-	/* set timestamp bit if present */
+	/* set timestamp bit if present, will select the register set
+	 * based on the _TSTAMP(_X) bit.
+	 */
 	cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP,
 				 (IGC_ADVTXD_MAC_TSTAMP));
 
+	cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_1,
+				 (IGC_ADVTXD_TSTAMP_REG_1));
+
+	cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_2,
+				 (IGC_ADVTXD_TSTAMP_REG_2));
+
+	cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_3,
+				 (IGC_ADVTXD_TSTAMP_REG_3));
+
 	/* insert frame checksum */
 	cmd_type ^= IGC_SET_FLAG(skb->no_fcs, 1, IGC_ADVTXD_DCMD_IFCS);
 
@@ -1533,6 +1544,26 @@ static int igc_tso(struct igc_ring *tx_ring,
 	return 1;
 }
 
+static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *skb, u32 *flags)
+{
+	int i;
+
+	for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) {
+		struct igc_tx_timestamp_request *tstamp = &adapter->tx_tstamp[i];
+
+		if (tstamp->skb)
+			continue;
+
+		tstamp->skb = skb_get(skb);
+		tstamp->start = jiffies;
+		*flags = tstamp->flags;
+
+		return true;
+	}
+
+	return false;
+}
+
 static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 				       struct igc_ring *tx_ring)
 {
@@ -1614,14 +1645,12 @@ done:
 		 * timestamping request.
 		 */
 		unsigned long flags;
+		u32 tstamp_flags;
 
 		spin_lock_irqsave(&adapter->ptp_tx_lock, flags);
-		if (!adapter->ptp_tx_skb) {
+		if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-			tx_flags |= IGC_TX_FLAGS_TSTAMP;
-
-			adapter->ptp_tx_skb = skb_get(skb);
-			adapter->ptp_tx_start = jiffies;
+			tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags;
 		} else {
 			adapter->tx_hwtstamp_skipped++;
 		}
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index f0b979a706552..928f38792203a 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -558,11 +558,16 @@ static void igc_ptp_enable_rx_timestamp(struct igc_adapter *adapter)
 static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter)
 {
 	unsigned long flags;
+	int i;
 
 	spin_lock_irqsave(&adapter->ptp_tx_lock, flags);
 
-	dev_kfree_skb_any(adapter->ptp_tx_skb);
-	adapter->ptp_tx_skb = NULL;
+	for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) {
+		struct igc_tx_timestamp_request *tstamp = &adapter->tx_tstamp[i];
+
+		dev_kfree_skb_any(tstamp->skb);
+		tstamp->skb = NULL;
+	}
 
 	spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags);
 }
@@ -659,61 +664,106 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter,
 }
 
 /* Requires adapter->ptp_tx_lock held by caller. */
-static void igc_ptp_tx_timeout(struct igc_adapter *adapter)
+static void igc_ptp_tx_timeout(struct igc_adapter *adapter,
+			       struct igc_tx_timestamp_request *tstamp)
 {
-	struct igc_hw *hw = &adapter->hw;
-
-	dev_kfree_skb_any(adapter->ptp_tx_skb);
-	adapter->ptp_tx_skb = NULL;
+	dev_kfree_skb_any(tstamp->skb);
+	tstamp->skb = NULL;
 	adapter->tx_hwtstamp_timeouts++;
-	/* Clear the tx valid bit in TSYNCTXCTL register to enable interrupt. */
-	rd32(IGC_TXSTMPH);
+
 	netdev_warn(adapter->netdev, "Tx timestamp timeout\n");
 }
 
 void igc_ptp_tx_hang(struct igc_adapter *adapter)
 {
+	struct igc_tx_timestamp_request *tstamp;
+	struct igc_hw *hw = &adapter->hw;
 	unsigned long flags;
+	bool found = false;
+	int i;
 
 	spin_lock_irqsave(&adapter->ptp_tx_lock, flags);
 
-	if (!adapter->ptp_tx_skb)
-		goto unlock;
+	for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) {
+		tstamp = &adapter->tx_tstamp[i];
+
+		if (!tstamp->skb)
+			continue;
 
-	if (time_is_after_jiffies(adapter->ptp_tx_start + IGC_PTP_TX_TIMEOUT))
-		goto unlock;
+		if (time_is_after_jiffies(tstamp->start + IGC_PTP_TX_TIMEOUT))
+			continue;
 
-	igc_ptp_tx_timeout(adapter);
+		igc_ptp_tx_timeout(adapter, tstamp);
+		found = true;
+	}
+
+	if (found) {
+		/* Reading the high register of the first set of timestamp registers
+		 * clears all the equivalent bits in the TSYNCTXCTL register.
+		 */
+		rd32(IGC_TXSTMPH_0);
+	}
 
-unlock:
 	spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags);
 }
 
+static void igc_ptp_tx_reg_to_stamp(struct igc_adapter *adapter,
+				    struct igc_tx_timestamp_request *tstamp, u64 regval)
+{
+	struct skb_shared_hwtstamps shhwtstamps;
+	struct sk_buff *skb;
+	int adjust = 0;
+
+	skb = tstamp->skb;
+	if (!skb)
+		return;
+
+	if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval))
+		return;
+
+	switch (adapter->link_speed) {
+	case SPEED_10:
+		adjust = IGC_I225_TX_LATENCY_10;
+		break;
+	case SPEED_100:
+		adjust = IGC_I225_TX_LATENCY_100;
+		break;
+	case SPEED_1000:
+		adjust = IGC_I225_TX_LATENCY_1000;
+		break;
+	case SPEED_2500:
+		adjust = IGC_I225_TX_LATENCY_2500;
+		break;
+	}
+
+	shhwtstamps.hwtstamp =
+		ktime_add_ns(shhwtstamps.hwtstamp, adjust);
+
+	tstamp->skb = NULL;
+
+	skb_tstamp_tx(skb, &shhwtstamps);
+	dev_kfree_skb_any(skb);
+}
+
 /**
  * igc_ptp_tx_hwtstamp - utility function which checks for TX time stamp
  * @adapter: Board private structure
  *
- * If we were asked to do hardware stamping and such a time stamp is
- * available, then it must have been for this skb here because we only
- * allow only one such packet into the queue.
+ * Check against the ready mask for which of the timestamp register
+ * sets are ready to be retrieved, then retrieve that and notify the
+ * rest of the stack.
  *
  * Context: Expects adapter->ptp_tx_lock to be held by caller.
  */
 static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter)
 {
-	struct sk_buff *skb = adapter->ptp_tx_skb;
-	struct skb_shared_hwtstamps shhwtstamps;
 	struct igc_hw *hw = &adapter->hw;
-	u32 tsynctxctl;
-	int adjust = 0;
 	u64 regval;
+	u32 mask;
+	int i;
 
-	if (WARN_ON_ONCE(!skb))
-		return;
-
-	tsynctxctl = rd32(IGC_TSYNCTXCTL);
-	tsynctxctl &= IGC_TSYNCTXCTL_TXTT_0;
-	if (tsynctxctl) {
+	mask = rd32(IGC_TSYNCTXCTL) & IGC_TSYNCTXCTL_TXTT_ANY;
+	if (mask & IGC_TSYNCTXCTL_TXTT_0) {
 		regval = rd32(IGC_TXSTMPL);
 		regval |= (u64)rd32(IGC_TXSTMPH) << 32;
 	} else {
@@ -742,37 +792,30 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter)
 		txstmpl_new = rd32(IGC_TXSTMPL);
 
 		if (txstmpl_old == txstmpl_new)
-			return;
+			goto done;
 
 		regval = txstmpl_new;
 		regval |= (u64)rd32(IGC_TXSTMPH) << 32;
 	}
-	if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval))
-		return;
 
-	switch (adapter->link_speed) {
-	case SPEED_10:
-		adjust = IGC_I225_TX_LATENCY_10;
-		break;
-	case SPEED_100:
-		adjust = IGC_I225_TX_LATENCY_100;
-		break;
-	case SPEED_1000:
-		adjust = IGC_I225_TX_LATENCY_1000;
-		break;
-	case SPEED_2500:
-		adjust = IGC_I225_TX_LATENCY_2500;
-		break;
-	}
+	igc_ptp_tx_reg_to_stamp(adapter, &adapter->tx_tstamp[0], regval);
 
-	shhwtstamps.hwtstamp =
-		ktime_add_ns(shhwtstamps.hwtstamp, adjust);
+done:
+	/* Now that the problematic first register was handled, we can
+	 * use retrieve the timestamps from the other registers
+	 * (starting from '1') with less complications.
+	 */
+	for (i = 1; i < IGC_MAX_TX_TSTAMP_REGS; i++) {
+		struct igc_tx_timestamp_request *tstamp = &adapter->tx_tstamp[i];
 
-	adapter->ptp_tx_skb = NULL;
+		if (!(tstamp->mask & mask))
+			continue;
 
-	/* Notify the stack and free the skb after we've unlocked */
-	skb_tstamp_tx(skb, &shhwtstamps);
-	dev_kfree_skb_any(skb);
+		regval = rd32(tstamp->regl);
+		regval |= (u64)rd32(tstamp->regh) << 32;
+
+		igc_ptp_tx_reg_to_stamp(adapter, tstamp, regval);
+	}
 }
 
 /**
@@ -788,12 +831,8 @@ void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter)
 
 	spin_lock_irqsave(&adapter->ptp_tx_lock, flags);
 
-	if (!adapter->ptp_tx_skb)
-		goto unlock;
-
 	igc_ptp_tx_hwtstamp(adapter);
 
-unlock:
 	spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags);
 }
 
@@ -1006,9 +1045,34 @@ static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 void igc_ptp_init(struct igc_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
+	struct igc_tx_timestamp_request *tstamp;
 	struct igc_hw *hw = &adapter->hw;
 	int i;
 
+	tstamp = &adapter->tx_tstamp[0];
+	tstamp->mask = IGC_TSYNCTXCTL_TXTT_0;
+	tstamp->regl = IGC_TXSTMPL_0;
+	tstamp->regh = IGC_TXSTMPH_0;
+	tstamp->flags = 0;
+
+	tstamp = &adapter->tx_tstamp[1];
+	tstamp->mask = IGC_TSYNCTXCTL_TXTT_1;
+	tstamp->regl = IGC_TXSTMPL_1;
+	tstamp->regh = IGC_TXSTMPH_1;
+	tstamp->flags = IGC_TX_FLAGS_TSTAMP_1;
+
+	tstamp = &adapter->tx_tstamp[2];
+	tstamp->mask = IGC_TSYNCTXCTL_TXTT_2;
+	tstamp->regl = IGC_TXSTMPL_2;
+	tstamp->regh = IGC_TXSTMPH_2;
+	tstamp->flags = IGC_TX_FLAGS_TSTAMP_2;
+
+	tstamp = &adapter->tx_tstamp[3];
+	tstamp->mask = IGC_TSYNCTXCTL_TXTT_3;
+	tstamp->regl = IGC_TXSTMPL_3;
+	tstamp->regh = IGC_TXSTMPH_3;
+	tstamp->flags = IGC_TX_FLAGS_TSTAMP_3;
+
 	switch (hw->mac.type) {
 	case igc_i225:
 		for (i = 0; i < IGC_N_SDP; i++) {
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index dba5a5759b1c0..20e17f5fbce37 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -243,6 +243,18 @@
 #define IGC_SYSTIMR	0x0B6F8  /* System time register Residue */
 #define IGC_TIMINCA	0x0B608  /* Increment attributes register - RW */
 
+/* TX Timestamp Low */
+#define IGC_TXSTMPL_0		0x0B618
+#define IGC_TXSTMPL_1		0x0B698
+#define IGC_TXSTMPL_2		0x0B6B8
+#define IGC_TXSTMPL_3		0x0B6D8
+
+/* TX Timestamp High */
+#define IGC_TXSTMPH_0		0x0B61C
+#define IGC_TXSTMPH_1		0x0B69C
+#define IGC_TXSTMPH_2		0x0B6BC
+#define IGC_TXSTMPH_3		0x0B6DC
+
 #define IGC_TXSTMPL	0x0B618  /* Tx timestamp value Low - RO */
 #define IGC_TXSTMPH	0x0B61C  /* Tx timestamp value High - RO */
 
-- 
GitLab


From 6b8aa753a9f93c835abc140e5e33db136322d428 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Thu, 20 Jul 2023 06:48:35 +0300
Subject: [PATCH 1648/1806] igc: Decrease PTM short interval from 10 us to 1 us

With the 10us interval, we were seeing PTM transactions take around 12us.
Hardware team suggested this interval could be lowered to 1us which was
confirmed with PCIe sniffer. With the 1us interval, PTM dialogs took
around 2us.

Suggested-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Reviewed-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 700827bdd626e..b3037016f31d2 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -556,7 +556,7 @@
 #define IGC_PTM_CTRL_SHRT_CYC(usec)	(((usec) & 0x3f) << 2)
 #define IGC_PTM_CTRL_PTM_TO(usec)	(((usec) & 0xff) << 8)
 
-#define IGC_PTM_SHORT_CYC_DEFAULT	10  /* Default Short/interrupted cycle interval */
+#define IGC_PTM_SHORT_CYC_DEFAULT	1   /* Default short cycle interval */
 #define IGC_PTM_CYC_TIME_DEFAULT	5   /* Default PTM cycle time */
 #define IGC_PTM_TIMEOUT_DEFAULT		255 /* Default timeout for PTM errors */
 
-- 
GitLab


From 1fe4f45ea461986a3213e78e00631beede3a12c2 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Tue, 18 Jul 2023 19:28:57 +0300
Subject: [PATCH 1649/1806] e1000e: Add support for the next LOM generation

Add devices IDs for the next LOM generations that will be available on the
next Intel Client platforms. This patch provides the initial support for
these devices.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/ethtool.c | 2 ++
 drivers/net/ethernet/intel/e1000e/hw.h      | 3 +++
 drivers/net/ethernet/intel/e1000e/ich8lan.c | 7 +++++++
 drivers/net/ethernet/intel/e1000e/netdev.c  | 4 ++++
 drivers/net/ethernet/intel/e1000e/ptp.c     | 1 +
 5 files changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 721f86fd5802d..9835e6a90d56c 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -917,6 +917,7 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 		mask |= BIT(18);
 		break;
 	default:
@@ -1585,6 +1586,7 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 		fext_nvm11 = er32(FEXTNVM11);
 		fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX;
 		ew32(FEXTNVM11, fext_nvm11);
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index 29f9fae35f426..1fef6bb5a5fbc 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -122,6 +122,8 @@ struct e1000_hw;
 #define E1000_DEV_ID_PCH_PTP_I219_V26		0x57B6
 #define E1000_DEV_ID_PCH_PTP_I219_LM27		0x57B7
 #define E1000_DEV_ID_PCH_PTP_I219_V27		0x57B8
+#define E1000_DEV_ID_PCH_NVL_I219_LM29		0x57B9
+#define E1000_DEV_ID_PCH_NVL_I219_V29		0x57BA
 
 #define E1000_REVISION_4	4
 
@@ -150,6 +152,7 @@ enum e1000_mac_type {
 	e1000_pch_mtp,
 	e1000_pch_lnp,
 	e1000_pch_ptp,
+	e1000_pch_nvp,
 };
 
 enum e1000_media_type {
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 0c7fd10312c8d..39e9fc601bf5a 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -323,6 +323,7 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 		if (e1000_phy_is_accessible_pchlan(hw))
 			break;
 
@@ -470,6 +471,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
 		case e1000_pch_mtp:
 		case e1000_pch_lnp:
 		case e1000_pch_ptp:
+		case e1000_pch_nvp:
 			/* In case the PHY needs to be in mdio slow mode,
 			 * set slow mode and try to get the PHY id again.
 			 */
@@ -717,6 +719,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 	case e1000_pchlan:
 		/* check management mode */
 		mac->ops.check_mng_mode = e1000_check_mng_mode_pchlan;
@@ -1685,6 +1688,7 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 		rc = e1000_init_phy_params_pchlan(hw);
 		break;
 	default:
@@ -2142,6 +2146,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 		sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG_ICH8M;
 		break;
 	default:
@@ -3188,6 +3193,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 		bank1_offset = nvm->flash_bank_size;
 		act_offset = E1000_ICH_NVM_SIG_WORD;
 
@@ -4129,6 +4135,7 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 		word = NVM_COMPAT;
 		valid_csum_mask = NVM_COMPAT_VALID_CSUM;
 		break;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 18a5e73b86806..f536c856727cb 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3545,6 +3545,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 24MHz frequency */
 			incperiod = INCPERIOD_24MHZ;
@@ -4061,6 +4062,7 @@ void e1000e_reset(struct e1000_adapter *adapter)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 		fc->refresh_time = 0xFFFF;
 		fc->pause_time = 0xFFFF;
 
@@ -7913,6 +7915,8 @@ static const struct pci_device_id e1000_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V26), board_pch_mtp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_mtp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_mtp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_mtp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_mtp },
 
 	{ 0, 0, 0, 0, 0, 0, 0 }	/* terminate list */
 };
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index def4566a916f3..02d871bc112a7 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -288,6 +288,7 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_mtp:
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
+	case e1000_pch_nvp:
 		if ((hw->mac.type < e1000_pch_lpt) ||
 		    (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) {
 			adapter->ptp_clock_info.max_adj = 24000000 - 1;
-- 
GitLab


From 84a58e60038fa0366006977dba85eae16b2e3d78 Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Mon, 21 Aug 2023 16:05:54 -0700
Subject: [PATCH 1650/1806] net/mlx5: Dynamic cyclecounter shift calculation
 for PTP free running clock

Use a dynamic calculation to determine the shift value for the internal
timer cyclecounter that will lead to the highest precision frequency
adjustments. Previously used a constant for the shift value assuming all
devices supported by the driver had a nominal frequency of 1GHz. However,
there are devices that operate at different frequencies. The previous shift
value constant would break the PHC functionality for those devices.

Reported-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Closes: https://lore.kernel.org/netdev/20230815151507.3028503-1-vadfed@meta.com/
Fixes: 6a4010927562 ("net/mlx5: Update cyclecounter shift value to improve ptp free running mode precision")
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Tested-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20230821230554.236210-1-rrameshbabu@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/lib/clock.c   | 32 ++++++++++++++++---
 1 file changed, 27 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 377372f0578ae..aa29f09e83564 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -32,16 +32,13 @@
 
 #include <linux/clocksource.h>
 #include <linux/highmem.h>
+#include <linux/log2.h>
 #include <linux/ptp_clock_kernel.h>
 #include <rdma/mlx5-abi.h>
 #include "lib/eq.h"
 #include "en.h"
 #include "clock.h"
 
-enum {
-	MLX5_CYCLES_SHIFT	= 31
-};
-
 enum {
 	MLX5_PIN_MODE_IN		= 0x0,
 	MLX5_PIN_MODE_OUT		= 0x1,
@@ -93,6 +90,31 @@ static bool mlx5_modify_mtutc_allowed(struct mlx5_core_dev *mdev)
 	return MLX5_CAP_MCAM_FEATURE(mdev, ptpcyc2realtime_modify);
 }
 
+static u32 mlx5_ptp_shift_constant(u32 dev_freq_khz)
+{
+	/* Optimal shift constant leads to corrections above just 1 scaled ppm.
+	 *
+	 * Two sets of equations are needed to derive the optimal shift
+	 * constant for the cyclecounter.
+	 *
+	 *    dev_freq_khz * 1000 / 2^shift_constant = 1 scaled_ppm
+	 *    ppb = scaled_ppm * 1000 / 2^16
+	 *
+	 * Using the two equations together
+	 *
+	 *    dev_freq_khz * 1000 / 1 scaled_ppm = 2^shift_constant
+	 *    dev_freq_khz * 2^16 / 1 ppb = 2^shift_constant
+	 *    dev_freq_khz = 2^(shift_constant - 16)
+	 *
+	 * then yields
+	 *
+	 *    shift_constant = ilog2(dev_freq_khz) + 16
+	 */
+
+	return min(ilog2(dev_freq_khz) + 16,
+		   ilog2((U32_MAX / NSEC_PER_MSEC) * dev_freq_khz));
+}
+
 static s32 mlx5_ptp_getmaxphase(struct ptp_clock_info *ptp)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
@@ -909,7 +931,7 @@ static void mlx5_timecounter_init(struct mlx5_core_dev *mdev)
 
 	dev_freq = MLX5_CAP_GEN(mdev, device_frequency_khz);
 	timer->cycles.read = read_internal_timer;
-	timer->cycles.shift = MLX5_CYCLES_SHIFT;
+	timer->cycles.shift = mlx5_ptp_shift_constant(dev_freq);
 	timer->cycles.mult = clocksource_khz2mult(dev_freq,
 						  timer->cycles.shift);
 	timer->nominal_c_mult = timer->cycles.mult;
-- 
GitLab


From 10ea77e49c5761008d0e2bf6d30b434cbc62446d Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Tue, 15 Aug 2023 12:37:25 +1000
Subject: [PATCH 1651/1806] net/mlx5e: fix up for "net/mlx5e: Move MACsec flow
 steering operations to be used as core library"

Recent merge had a conflict in:

  drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c

between commit:

  aeb660171b06 ("net/mlx5e: fix double free in macsec_fs_tx_create_crypto_table_groups")

from Linus' tree and commit:

  cb5ebe4896f9 ("net/mlx5e: Move MACsec flow steering operations to be used as core library")

from the mlx5-next tree. This was missed and the former commit
got lost, bring it back.

Fixes: 3c5066c6b0a5 ("Merge branch 'mlx5-next' of https://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux")
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Link: https://lore.kernel.org/r/20230815123725.4ef5b7b9@canb.auug.org.au
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index 2f2cb67717cdd..4a078113e292d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -278,6 +278,7 @@ static int macsec_fs_tx_create_crypto_table_groups(struct mlx5_macsec_flow_table
 
 	if (!in) {
 		kfree(ft->g);
+		ft->g = NULL;
 		return -ENOMEM;
 	}
 
-- 
GitLab


From 649bde9004ac7e034383dcd810cb52f3f5d9e577 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 23 Aug 2023 17:30:52 -0700
Subject: [PATCH 1652/1806] tools: ynl: allow passing binary data

Recent changes made us assume that input for binary data is in hex.
When using YNL as a Python library it's possible to pass in raw bytes.
Bring the ability to do that back.

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20230824003056.1436637-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/ynl.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 6951bcc7efdcb..fa4f1c28efc55 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -410,7 +410,12 @@ class YnlFamily(SpecFamily):
         elif attr["type"] == 'string':
             attr_payload = str(value).encode('ascii') + b'\x00'
         elif attr["type"] == 'binary':
-            attr_payload = bytes.fromhex(value)
+            if isinstance(value, bytes):
+                attr_payload = value
+            elif isinstance(value, str):
+                attr_payload = bytes.fromhex(value)
+            else:
+                raise Exception(f'Unknown type for binary attribute, value: {value}')
         elif attr['type'] in NlAttr.type_formats:
             format = NlAttr.get_format(attr['type'], attr.byte_order)
             attr_payload = format.pack(int(value))
-- 
GitLab


From a149a3a13bbcc5b87ade9073b6f1c9584f85ab18 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 23 Aug 2023 17:30:53 -0700
Subject: [PATCH 1653/1806] tools: ynl-gen: set length of binary fields

Remember to set the length field in the request setters.

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20230824003056.1436637-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/generated/ethtool-user.h | 4 ++++
 tools/net/ynl/generated/fou-user.h     | 6 ++++++
 tools/net/ynl/ynl-gen-c.py             | 1 +
 3 files changed, 11 insertions(+)

diff --git a/tools/net/ynl/generated/ethtool-user.h b/tools/net/ynl/generated/ethtool-user.h
index d7d4ba855f439..ddc1a52099929 100644
--- a/tools/net/ynl/generated/ethtool-user.h
+++ b/tools/net/ynl/generated/ethtool-user.h
@@ -1422,6 +1422,7 @@ ethtool_wol_set_req_set_sopass(struct ethtool_wol_set_req *req,
 			       const void *sopass, size_t len)
 {
 	free(req->sopass);
+	req->_present.sopass_len = len;
 	req->sopass = malloc(req->_present.sopass_len);
 	memcpy(req->sopass, sopass, req->_present.sopass_len);
 }
@@ -4071,6 +4072,7 @@ ethtool_fec_set_req_set_stats_corrected(struct ethtool_fec_set_req *req,
 					const void *corrected, size_t len)
 {
 	free(req->stats.corrected);
+	req->stats._present.corrected_len = len;
 	req->stats.corrected = malloc(req->stats._present.corrected_len);
 	memcpy(req->stats.corrected, corrected, req->stats._present.corrected_len);
 }
@@ -4079,6 +4081,7 @@ ethtool_fec_set_req_set_stats_uncorr(struct ethtool_fec_set_req *req,
 				     const void *uncorr, size_t len)
 {
 	free(req->stats.uncorr);
+	req->stats._present.uncorr_len = len;
 	req->stats.uncorr = malloc(req->stats._present.uncorr_len);
 	memcpy(req->stats.uncorr, uncorr, req->stats._present.uncorr_len);
 }
@@ -4087,6 +4090,7 @@ ethtool_fec_set_req_set_stats_corr_bits(struct ethtool_fec_set_req *req,
 					const void *corr_bits, size_t len)
 {
 	free(req->stats.corr_bits);
+	req->stats._present.corr_bits_len = len;
 	req->stats.corr_bits = malloc(req->stats._present.corr_bits_len);
 	memcpy(req->stats.corr_bits, corr_bits, req->stats._present.corr_bits_len);
 }
diff --git a/tools/net/ynl/generated/fou-user.h b/tools/net/ynl/generated/fou-user.h
index d8ab50579cd13..a8f860892540b 100644
--- a/tools/net/ynl/generated/fou-user.h
+++ b/tools/net/ynl/generated/fou-user.h
@@ -91,6 +91,7 @@ fou_add_req_set_local_v6(struct fou_add_req *req, const void *local_v6,
 			 size_t len)
 {
 	free(req->local_v6);
+	req->_present.local_v6_len = len;
 	req->local_v6 = malloc(req->_present.local_v6_len);
 	memcpy(req->local_v6, local_v6, req->_present.local_v6_len);
 }
@@ -99,6 +100,7 @@ fou_add_req_set_peer_v6(struct fou_add_req *req, const void *peer_v6,
 			size_t len)
 {
 	free(req->peer_v6);
+	req->_present.peer_v6_len = len;
 	req->peer_v6 = malloc(req->_present.peer_v6_len);
 	memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len);
 }
@@ -192,6 +194,7 @@ fou_del_req_set_local_v6(struct fou_del_req *req, const void *local_v6,
 			 size_t len)
 {
 	free(req->local_v6);
+	req->_present.local_v6_len = len;
 	req->local_v6 = malloc(req->_present.local_v6_len);
 	memcpy(req->local_v6, local_v6, req->_present.local_v6_len);
 }
@@ -200,6 +203,7 @@ fou_del_req_set_peer_v6(struct fou_del_req *req, const void *peer_v6,
 			size_t len)
 {
 	free(req->peer_v6);
+	req->_present.peer_v6_len = len;
 	req->peer_v6 = malloc(req->_present.peer_v6_len);
 	memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len);
 }
@@ -280,6 +284,7 @@ fou_get_req_set_local_v6(struct fou_get_req *req, const void *local_v6,
 			 size_t len)
 {
 	free(req->local_v6);
+	req->_present.local_v6_len = len;
 	req->local_v6 = malloc(req->_present.local_v6_len);
 	memcpy(req->local_v6, local_v6, req->_present.local_v6_len);
 }
@@ -288,6 +293,7 @@ fou_get_req_set_peer_v6(struct fou_get_req *req, const void *peer_v6,
 			size_t len)
 {
 	free(req->peer_v6);
+	req->_present.peer_v6_len = len;
 	req->peer_v6 = malloc(req->_present.peer_v6_len);
 	memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len);
 }
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index bdff8dfc29c94..e27deb199a707 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -428,6 +428,7 @@ class TypeBinary(Type):
 
     def _setter_lines(self, ri, member, presence):
         return [f"free({member});",
+                f"{presence}_len = len;",
                 f"{member} = malloc({presence}_len);",
                 f'memcpy({member}, {self.c_name}, {presence}_len);']
 
-- 
GitLab


From dc2ef94d892634fba912e4fdeb01cd1c19346c9a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 23 Aug 2023 17:30:54 -0700
Subject: [PATCH 1654/1806] tools: ynl-gen: fix collecting global policy attrs

We look for attributes inside do.request, but there's another
layer of nesting in the spec, look inside do.request.attributes.

This bug had no effect as all global policies we generate (fou)
seem to be full, anyway, and we treat full and empty the same.

Next patch will change the treatment of empty policies.

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20230824003056.1436637-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index e27deb199a707..13d06931c045e 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -978,7 +978,9 @@ class Family(SpecFamily):
 
             for op_mode in ['do', 'dump']:
                 if op_mode in op:
-                    global_set.update(op[op_mode].get('request', []))
+                    req = op[op_mode].get('request')
+                    if req:
+                        global_set.update(req.get('attributes', []))
 
         self.global_policy = []
         self.global_policy_set = attr_set_name
-- 
GitLab


From 4c8c24e801e60a2b4a6f78401c9b7cb6cbf47cbf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 23 Aug 2023 17:30:55 -0700
Subject: [PATCH 1655/1806] tools: ynl-gen: support empty attribute lists

Differentiate between empty list and None for member lists.
New families may want to create request responses with no attribute.
If we treat those the same as None we end up rendering
a full parsing policy in user space, instead of an empty one.

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20230824003056.1436637-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 13d06931c045e..9209bdcca9c61 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -615,7 +615,7 @@ class Struct:
 
         self.attr_list = []
         self.attrs = dict()
-        if type_list:
+        if type_list is not None:
             for t in type_list:
                 self.attr_list.append((t, self.attr_set[t]),)
         else:
@@ -1543,7 +1543,14 @@ def parse_rsp_msg(ri, deref=False):
 
     ri.cw.write_func_prot('int', f'{op_prefix(ri, "reply", deref=deref)}_parse', func_args)
 
-    _multi_parse(ri, ri.struct["reply"], init_lines, local_vars)
+    if ri.struct["reply"].member_list():
+        _multi_parse(ri, ri.struct["reply"], init_lines, local_vars)
+    else:
+        # Empty reply
+        ri.cw.block_start()
+        ri.cw.p('return MNL_CB_OK;')
+        ri.cw.block_end()
+        ri.cw.nl()
 
 
 def print_req(ri):
-- 
GitLab


From e83d4e9b2d0ff12f02f85fbef909c46c6447d41e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 23 Aug 2023 17:30:56 -0700
Subject: [PATCH 1656/1806] netlink: specs: fix indent in fou

Fix up the indentation. This has no functional effect, AFAICT.

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20230824003056.1436637-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/fou.yaml | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/Documentation/netlink/specs/fou.yaml b/Documentation/netlink/specs/fou.yaml
index 3e13826a3fdf1..0af5ab842c04d 100644
--- a/Documentation/netlink/specs/fou.yaml
+++ b/Documentation/netlink/specs/fou.yaml
@@ -107,16 +107,16 @@ operations:
       flags: [ admin-perm ]
 
       do:
-        request:  &select_attrs
+        request: &select_attrs
           attributes:
-          - af
-          - ifindex
-          - port
-          - peer_port
-          - local_v4
-          - peer_v4
-          - local_v6
-          - peer_v6
+            - af
+            - ifindex
+            - port
+            - peer_port
+            - local_v4
+            - peer_v4
+            - local_v6
+            - peer_v6
 
     -
       name: get
-- 
GitLab


From d55595f04dcc8bd6f6ff33f451dda8de3f1232da Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Wed, 23 Aug 2023 14:19:28 +0800
Subject: [PATCH 1657/1806] net: pcs: xpcs: add specific vendor supoprt for
 Wangxun 10Gb NICs

Since Wangxun 10Gb NICs require some special configuration on the IP of
Synopsys Designware XPCS, introduce dev_flag for different vendors. Read
OUI from device identifier registers, to detect Wangxun devices.

And xpcs_soft_reset() is skipped to avoid the reset of device identifier
registers.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/pcs/pcs-xpcs.c   | 35 ++++++++++++++++++++++++++++++++---
 include/linux/pcs/pcs-xpcs.h |  7 +++++++
 2 files changed, 39 insertions(+), 3 deletions(-)

diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 44b0376468653..8b56b2f9f24d2 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -238,6 +238,29 @@ static int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val)
 	return xpcs_write_vendor(xpcs, MDIO_MMD_PCS, reg, val);
 }
 
+static int xpcs_dev_flag(struct dw_xpcs *xpcs)
+{
+	int ret, oui;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_DEVID1);
+	if (ret < 0)
+		return ret;
+
+	oui = ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_DEVID2);
+	if (ret < 0)
+		return ret;
+
+	ret = (ret >> 10) & 0x3F;
+	oui |= ret << 16;
+
+	if (oui == DW_OUI_WX)
+		xpcs->dev_flag = DW_DEV_TXGBE;
+
+	return 0;
+}
+
 static int xpcs_poll_reset(struct dw_xpcs *xpcs, int dev)
 {
 	/* Poll until the reset bit clears (50ms per retry == 0.6 sec) */
@@ -1284,6 +1307,10 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev,
 			goto out;
 		}
 
+		ret = xpcs_dev_flag(xpcs);
+		if (ret)
+			goto out;
+
 		xpcs->pcs.ops = &xpcs_phylink_ops;
 		xpcs->pcs.neg_mode = true;
 		if (compat->an_mode == DW_10GBASER)
@@ -1291,9 +1318,11 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev,
 
 		xpcs->pcs.poll = true;
 
-		ret = xpcs_soft_reset(xpcs, compat);
-		if (ret)
-			goto out;
+		if (xpcs->dev_flag != DW_DEV_TXGBE) {
+			ret = xpcs_soft_reset(xpcs, compat);
+			if (ret)
+				goto out;
+		}
 
 		return xpcs;
 	}
diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h
index ff99cf7a5d0db..f37e8acfd351b 100644
--- a/include/linux/pcs/pcs-xpcs.h
+++ b/include/linux/pcs/pcs-xpcs.h
@@ -20,12 +20,19 @@
 #define DW_AN_C37_1000BASEX		4
 #define DW_10GBASER			5
 
+/* device vendor OUI */
+#define DW_OUI_WX			0x0018fc80
+
+/* dev_flag */
+#define DW_DEV_TXGBE			BIT(0)
+
 struct xpcs_id;
 
 struct dw_xpcs {
 	struct mdio_device *mdiodev;
 	const struct xpcs_id *id;
 	struct phylink_pcs pcs;
+	int dev_flag;
 };
 
 int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface);
-- 
GitLab


From f629acc6f21043fdc80ae93cdafa6713888db0fd Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Wed, 23 Aug 2023 14:19:29 +0800
Subject: [PATCH 1658/1806] net: pcs: xpcs: support to switch mode for Wangxun
 NICs

According to chapter 6 of DesignWare Cores Ethernet PCS (version 3.20a)
and custom design manual, add a configuration flow for switching interface
mode.

If the interface changes, the following setting is required:
1. wait VR_XS_PCS_DIG_STS bit(4, 2) [PSEQ_STATE] = 100b (Power-Good)
2. write SR_XS_PCS_CTRL2 to select various PCS type
3. write SR_PMA_CTRL1 and/or SR_XS_PCS_CTRL1 for link speed
4. program PMA registers
5. write VR_XS_PCS_DIG_CTRL1 bit(15) [VR_RST] = 1b (Vendor-Specific
   Soft Reset)
6. wait for VR_XS_PCS_DIG_CTRL1 bit(15) [VR_RST] to get cleared

Only 10GBASE-R/SGMII/1000BASE-X modes are planned for the current Wangxun
devices. And there is a quirk for Wangxun devices to switch mode although
the interface in phylink state has not changed, since PCS will change to
default 10GBASE-R when the ethernet driver(txgbe) do LAN reset.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                   |   1 +
 drivers/net/pcs/Makefile      |   2 +-
 drivers/net/pcs/pcs-xpcs-wx.c | 208 ++++++++++++++++++++++++++++++++++
 drivers/net/pcs/pcs-xpcs.c    |  13 ++-
 drivers/net/pcs/pcs-xpcs.h    |   8 ++
 include/linux/pcs/pcs-xpcs.h  |   1 +
 6 files changed, 227 insertions(+), 6 deletions(-)
 create mode 100644 drivers/net/pcs/pcs-xpcs-wx.c

diff --git a/MAINTAINERS b/MAINTAINERS
index dfc2ba0c20f32..5f527a9ae4b24 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22925,6 +22925,7 @@ S:	Maintained
 W:	https://www.net-swift.com
 F:	Documentation/networking/device_drivers/ethernet/wangxun/*
 F:	drivers/net/ethernet/wangxun/
+F:	drivers/net/pcs/pcs-xpcs-wx.c
 
 WATCHDOG DEVICE DRIVERS
 M:	Wim Van Sebroeck <wim@linux-watchdog.org>
diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile
index ea662a7989b29..fb1694192ae63 100644
--- a/drivers/net/pcs/Makefile
+++ b/drivers/net/pcs/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for Linux PCS drivers
 
-pcs_xpcs-$(CONFIG_PCS_XPCS)	:= pcs-xpcs.o pcs-xpcs-nxp.o
+pcs_xpcs-$(CONFIG_PCS_XPCS)	:= pcs-xpcs.o pcs-xpcs-nxp.o pcs-xpcs-wx.o
 
 obj-$(CONFIG_PCS_XPCS)		+= pcs_xpcs.o
 obj-$(CONFIG_PCS_LYNX)		+= pcs-lynx.o
diff --git a/drivers/net/pcs/pcs-xpcs-wx.c b/drivers/net/pcs/pcs-xpcs-wx.c
new file mode 100644
index 0000000000000..1f228d5a13983
--- /dev/null
+++ b/drivers/net/pcs/pcs-xpcs-wx.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2015 - 2023 Beijing WangXun Technology Co., Ltd. */
+
+#include <linux/pcs/pcs-xpcs.h>
+#include <linux/mdio.h>
+#include "pcs-xpcs.h"
+
+/* VR_XS_PMA_MMD */
+#define TXGBE_PMA_MMD			0x8020
+#define TXGBE_TX_GENCTL1		0x11
+#define TXGBE_TX_GENCTL1_VBOOST_LVL	GENMASK(10, 8)
+#define TXGBE_TX_GENCTL1_VBOOST_EN0	BIT(4)
+#define TXGBE_TX_GEN_CTL2		0x12
+#define TXGBE_TX_GEN_CTL2_TX0_WIDTH(v)	FIELD_PREP(GENMASK(9, 8), v)
+#define TXGBE_TX_RATE_CTL		0x14
+#define TXGBE_TX_RATE_CTL_TX0_RATE(v)	FIELD_PREP(GENMASK(2, 0), v)
+#define TXGBE_RX_GEN_CTL2		0x32
+#define TXGBE_RX_GEN_CTL2_RX0_WIDTH(v)	FIELD_PREP(GENMASK(9, 8), v)
+#define TXGBE_RX_GEN_CTL3		0x33
+#define TXGBE_RX_GEN_CTL3_LOS_TRSHLD0	GENMASK(2, 0)
+#define TXGBE_RX_RATE_CTL		0x34
+#define TXGBE_RX_RATE_CTL_RX0_RATE(v)	FIELD_PREP(GENMASK(1, 0), v)
+#define TXGBE_RX_EQ_ATTN_CTL		0x37
+#define TXGBE_RX_EQ_ATTN_LVL0		GENMASK(2, 0)
+#define TXGBE_RX_EQ_CTL0		0x38
+#define TXGBE_RX_EQ_CTL0_VGA1_GAIN(v)	FIELD_PREP(GENMASK(15, 12), v)
+#define TXGBE_RX_EQ_CTL0_VGA2_GAIN(v)	FIELD_PREP(GENMASK(11, 8), v)
+#define TXGBE_RX_EQ_CTL0_CTLE_POLE(v)	FIELD_PREP(GENMASK(7, 5), v)
+#define TXGBE_RX_EQ_CTL0_CTLE_BOOST(v)	FIELD_PREP(GENMASK(4, 0), v)
+#define TXGBE_RX_EQ_CTL4		0x3C
+#define TXGBE_RX_EQ_CTL4_CONT_OFF_CAN0	BIT(4)
+#define TXGBE_RX_EQ_CTL4_CONT_ADAPT0	BIT(0)
+#define TXGBE_AFE_DFE_ENABLE		0x3D
+#define TXGBE_DFE_EN_0			BIT(4)
+#define TXGBE_AFE_EN_0			BIT(0)
+#define TXGBE_DFE_TAP_CTL0		0x3E
+#define TXGBE_MPLLA_CTL0		0x51
+#define TXGBE_MPLLA_CTL2		0x53
+#define TXGBE_MPLLA_CTL2_DIV16P5_CLK_EN	BIT(10)
+#define TXGBE_MPLLA_CTL2_DIV10_CLK_EN	BIT(9)
+#define TXGBE_MPLLA_CTL3		0x57
+#define TXGBE_MISC_CTL0			0x70
+#define TXGBE_MISC_CTL0_PLL		BIT(15)
+#define TXGBE_MISC_CTL0_CR_PARA_SEL	BIT(14)
+#define TXGBE_MISC_CTL0_RX_VREF(v)	FIELD_PREP(GENMASK(12, 8), v)
+#define TXGBE_VCO_CAL_LD0		0x72
+#define TXGBE_VCO_CAL_REF0		0x76
+
+static int txgbe_read_pma(struct dw_xpcs *xpcs, int reg)
+{
+	return xpcs_read(xpcs, MDIO_MMD_PMAPMD, TXGBE_PMA_MMD + reg);
+}
+
+static int txgbe_write_pma(struct dw_xpcs *xpcs, int reg, u16 val)
+{
+	return xpcs_write(xpcs, MDIO_MMD_PMAPMD, TXGBE_PMA_MMD + reg, val);
+}
+
+static void txgbe_pma_config_10gbaser(struct dw_xpcs *xpcs)
+{
+	int val;
+
+	txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL0, 0x21);
+	txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL3, 0);
+	val = txgbe_read_pma(xpcs, TXGBE_TX_GENCTL1);
+	val = u16_replace_bits(val, 0x5, TXGBE_TX_GENCTL1_VBOOST_LVL);
+	txgbe_write_pma(xpcs, TXGBE_TX_GENCTL1, val);
+	txgbe_write_pma(xpcs, TXGBE_MISC_CTL0, TXGBE_MISC_CTL0_PLL |
+			TXGBE_MISC_CTL0_CR_PARA_SEL | TXGBE_MISC_CTL0_RX_VREF(0xF));
+	txgbe_write_pma(xpcs, TXGBE_VCO_CAL_LD0, 0x549);
+	txgbe_write_pma(xpcs, TXGBE_VCO_CAL_REF0, 0x29);
+	txgbe_write_pma(xpcs, TXGBE_TX_RATE_CTL, 0);
+	txgbe_write_pma(xpcs, TXGBE_RX_RATE_CTL, 0);
+	txgbe_write_pma(xpcs, TXGBE_TX_GEN_CTL2, TXGBE_TX_GEN_CTL2_TX0_WIDTH(3));
+	txgbe_write_pma(xpcs, TXGBE_RX_GEN_CTL2, TXGBE_RX_GEN_CTL2_RX0_WIDTH(3));
+	txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL2, TXGBE_MPLLA_CTL2_DIV16P5_CLK_EN |
+			TXGBE_MPLLA_CTL2_DIV10_CLK_EN);
+
+	txgbe_write_pma(xpcs, TXGBE_RX_EQ_CTL0, TXGBE_RX_EQ_CTL0_CTLE_POLE(2) |
+			TXGBE_RX_EQ_CTL0_CTLE_BOOST(5));
+	val = txgbe_read_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL);
+	val &= ~TXGBE_RX_EQ_ATTN_LVL0;
+	txgbe_write_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL, val);
+	txgbe_write_pma(xpcs, TXGBE_DFE_TAP_CTL0, 0xBE);
+	val = txgbe_read_pma(xpcs, TXGBE_AFE_DFE_ENABLE);
+	val &= ~(TXGBE_DFE_EN_0 | TXGBE_AFE_EN_0);
+	txgbe_write_pma(xpcs, TXGBE_AFE_DFE_ENABLE, val);
+	val = txgbe_read_pma(xpcs, TXGBE_RX_EQ_CTL4);
+	val &= ~TXGBE_RX_EQ_CTL4_CONT_ADAPT0;
+	txgbe_write_pma(xpcs, TXGBE_RX_EQ_CTL4, val);
+}
+
+static void txgbe_pma_config_1g(struct dw_xpcs *xpcs)
+{
+	int val;
+
+	val = txgbe_read_pma(xpcs, TXGBE_TX_GENCTL1);
+	val = u16_replace_bits(val, 0x5, TXGBE_TX_GENCTL1_VBOOST_LVL);
+	val &= ~TXGBE_TX_GENCTL1_VBOOST_EN0;
+	txgbe_write_pma(xpcs, TXGBE_TX_GENCTL1, val);
+	txgbe_write_pma(xpcs, TXGBE_MISC_CTL0, TXGBE_MISC_CTL0_PLL |
+			TXGBE_MISC_CTL0_CR_PARA_SEL | TXGBE_MISC_CTL0_RX_VREF(0xF));
+
+	txgbe_write_pma(xpcs, TXGBE_RX_EQ_CTL0, TXGBE_RX_EQ_CTL0_VGA1_GAIN(7) |
+			TXGBE_RX_EQ_CTL0_VGA2_GAIN(7) | TXGBE_RX_EQ_CTL0_CTLE_BOOST(6));
+	val = txgbe_read_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL);
+	val &= ~TXGBE_RX_EQ_ATTN_LVL0;
+	txgbe_write_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL, val);
+	txgbe_write_pma(xpcs, TXGBE_DFE_TAP_CTL0, 0);
+	val = txgbe_read_pma(xpcs, TXGBE_RX_GEN_CTL3);
+	val = u16_replace_bits(val, 0x4, TXGBE_RX_GEN_CTL3_LOS_TRSHLD0);
+	txgbe_write_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL, val);
+
+	txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL0, 0x20);
+	txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL3, 0x46);
+	txgbe_write_pma(xpcs, TXGBE_VCO_CAL_LD0, 0x540);
+	txgbe_write_pma(xpcs, TXGBE_VCO_CAL_REF0, 0x2A);
+	txgbe_write_pma(xpcs, TXGBE_AFE_DFE_ENABLE, 0);
+	txgbe_write_pma(xpcs, TXGBE_RX_EQ_CTL4, TXGBE_RX_EQ_CTL4_CONT_OFF_CAN0);
+	txgbe_write_pma(xpcs, TXGBE_TX_RATE_CTL, TXGBE_TX_RATE_CTL_TX0_RATE(3));
+	txgbe_write_pma(xpcs, TXGBE_RX_RATE_CTL, TXGBE_RX_RATE_CTL_RX0_RATE(3));
+	txgbe_write_pma(xpcs, TXGBE_TX_GEN_CTL2, TXGBE_TX_GEN_CTL2_TX0_WIDTH(1));
+	txgbe_write_pma(xpcs, TXGBE_RX_GEN_CTL2, TXGBE_RX_GEN_CTL2_RX0_WIDTH(1));
+	txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL2, TXGBE_MPLLA_CTL2_DIV10_CLK_EN);
+}
+
+static int txgbe_pcs_poll_power_up(struct dw_xpcs *xpcs)
+{
+	int val, ret;
+
+	/* Wait xpcs power-up good */
+	ret = read_poll_timeout(xpcs_read_vpcs, val,
+				(val & DW_PSEQ_ST) == DW_PSEQ_ST_GOOD,
+				10000, 1000000, false,
+				xpcs, DW_VR_XS_PCS_DIG_STS);
+	if (ret < 0)
+		dev_err(&xpcs->mdiodev->dev, "xpcs power-up timeout\n");
+
+	return ret;
+}
+
+static int txgbe_pma_init_done(struct dw_xpcs *xpcs)
+{
+	int val, ret;
+
+	xpcs_write_vpcs(xpcs, DW_VR_XS_PCS_DIG_CTRL1, DW_VR_RST | DW_EN_VSMMD1);
+
+	/* wait pma initialization done */
+	ret = read_poll_timeout(xpcs_read_vpcs, val, !(val & DW_VR_RST),
+				100000, 10000000, false,
+				xpcs, DW_VR_XS_PCS_DIG_CTRL1);
+	if (ret < 0)
+		dev_err(&xpcs->mdiodev->dev, "xpcs pma initialization timeout\n");
+
+	return ret;
+}
+
+static bool txgbe_xpcs_mode_quirk(struct dw_xpcs *xpcs)
+{
+	int ret;
+
+	/* When txgbe do LAN reset, PCS will change to default 10GBASE-R mode */
+	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_CTRL2);
+	ret &= MDIO_PCS_CTRL2_TYPE;
+	if (ret == MDIO_PCS_CTRL2_10GBR &&
+	    xpcs->interface != PHY_INTERFACE_MODE_10GBASER)
+		return true;
+
+	return false;
+}
+
+int txgbe_xpcs_switch_mode(struct dw_xpcs *xpcs, phy_interface_t interface)
+{
+	int val, ret;
+
+	switch (interface) {
+	case PHY_INTERFACE_MODE_10GBASER:
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_1000BASEX:
+		break;
+	default:
+		return 0;
+	}
+
+	if (xpcs->interface == interface && !txgbe_xpcs_mode_quirk(xpcs))
+		return 0;
+
+	xpcs->interface = interface;
+
+	ret = txgbe_pcs_poll_power_up(xpcs);
+	if (ret < 0)
+		return ret;
+
+	if (interface == PHY_INTERFACE_MODE_10GBASER) {
+		xpcs_write(xpcs, MDIO_MMD_PCS, MDIO_CTRL2, MDIO_PCS_CTRL2_10GBR);
+		val = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_CTRL1);
+		val |= MDIO_CTRL1_SPEED10G;
+		xpcs_write(xpcs, MDIO_MMD_PMAPMD, MDIO_CTRL1, val);
+		txgbe_pma_config_10gbaser(xpcs);
+	} else {
+		xpcs_write(xpcs, MDIO_MMD_PCS, MDIO_CTRL2, MDIO_PCS_CTRL2_10GBX);
+		xpcs_write(xpcs, MDIO_MMD_PMAPMD, MDIO_CTRL1, 0);
+		xpcs_write(xpcs, MDIO_MMD_PCS, MDIO_CTRL1, 0);
+		txgbe_pma_config_1g(xpcs);
+	}
+
+	return txgbe_pma_init_done(xpcs);
+}
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 8b56b2f9f24d2..4cd011405376f 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -228,12 +228,12 @@ static int xpcs_write_vendor(struct dw_xpcs *xpcs, int dev, int reg,
 	return xpcs_write(xpcs, dev, DW_VENDOR | reg, val);
 }
 
-static int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg)
+int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg)
 {
 	return xpcs_read_vendor(xpcs, MDIO_MMD_PCS, reg);
 }
 
-static int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val)
+int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val)
 {
 	return xpcs_write_vendor(xpcs, MDIO_MMD_PCS, reg, val);
 }
@@ -841,6 +841,12 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface,
 	if (!compat)
 		return -ENODEV;
 
+	if (xpcs->dev_flag == DW_DEV_TXGBE) {
+		ret = txgbe_xpcs_switch_mode(xpcs, interface);
+		if (ret)
+			return ret;
+	}
+
 	switch (compat->an_mode) {
 	case DW_10GBASER:
 		break;
@@ -1313,9 +1319,6 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev,
 
 		xpcs->pcs.ops = &xpcs_phylink_ops;
 		xpcs->pcs.neg_mode = true;
-		if (compat->an_mode == DW_10GBASER)
-			return xpcs;
-
 		xpcs->pcs.poll = true;
 
 		if (xpcs->dev_flag != DW_DEV_TXGBE) {
diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h
index 68c6b5a620881..da61ad36946c0 100644
--- a/drivers/net/pcs/pcs-xpcs.h
+++ b/drivers/net/pcs/pcs-xpcs.h
@@ -15,8 +15,13 @@
 /* VR_XS_PCS */
 #define DW_USXGMII_RST			BIT(10)
 #define DW_USXGMII_EN			BIT(9)
+#define DW_VR_XS_PCS_DIG_CTRL1		0x0000
+#define DW_VR_RST			BIT(15)
+#define DW_EN_VSMMD1			BIT(13)
 #define DW_VR_XS_PCS_DIG_STS		0x0010
 #define DW_RXFIFO_ERR			GENMASK(6, 5)
+#define DW_PSEQ_ST			GENMASK(4, 2)
+#define DW_PSEQ_ST_GOOD			FIELD_PREP(GENMASK(4, 2), 0x4)
 
 /* SR_MII */
 #define DW_USXGMII_FULL			BIT(8)
@@ -106,6 +111,9 @@
 
 int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg);
 int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val);
+int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg);
+int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val);
 int nxp_sja1105_sgmii_pma_config(struct dw_xpcs *xpcs);
 int nxp_sja1110_sgmii_pma_config(struct dw_xpcs *xpcs);
 int nxp_sja1110_2500basex_pma_config(struct dw_xpcs *xpcs);
+int txgbe_xpcs_switch_mode(struct dw_xpcs *xpcs, phy_interface_t interface);
diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h
index f37e8acfd351b..da3a6c30f6d24 100644
--- a/include/linux/pcs/pcs-xpcs.h
+++ b/include/linux/pcs/pcs-xpcs.h
@@ -32,6 +32,7 @@ struct dw_xpcs {
 	struct mdio_device *mdiodev;
 	const struct xpcs_id *id;
 	struct phylink_pcs pcs;
+	phy_interface_t interface;
 	int dev_flag;
 };
 
-- 
GitLab


From 2deea43f386d5c02cd490108aa3c6d02724594f8 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Wed, 23 Aug 2023 14:19:30 +0800
Subject: [PATCH 1659/1806] net: pcs: xpcs: add 1000BASE-X AN interrupt support

Enable CL37 AN complete interrupt for DW XPCS. It requires to clear the
bit(0) [CL37_ANCMPLT_INTR] of VR_MII_AN_INTR_STS after AN completed.

And there is a quirk for Wangxun devices to enable CL37 AN in backplane
configurations because of the special hardware design.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/pcs/pcs-xpcs.c | 19 ++++++++++++++++++-
 drivers/net/pcs/pcs-xpcs.h |  3 +++
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 4cd011405376f..b806a9beecded 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -755,6 +755,9 @@ static int xpcs_config_aneg_c37_1000basex(struct dw_xpcs *xpcs,
 	int ret, mdio_ctrl, adv;
 	bool changed = 0;
 
+	if (xpcs->dev_flag == DW_DEV_TXGBE)
+		xpcs_write_vpcs(xpcs, DW_VR_XS_PCS_DIG_CTRL1, DW_CL37_BP | DW_EN_VSMMD1);
+
 	/* According to Chap 7.12, to set 1000BASE-X C37 AN, AN must
 	 * be disabled first:-
 	 * 1) VR_MII_MMD_CTRL Bit(12)[AN_ENABLE] = 0b
@@ -776,6 +779,8 @@ static int xpcs_config_aneg_c37_1000basex(struct dw_xpcs *xpcs,
 		return ret;
 
 	ret &= ~DW_VR_MII_PCS_MODE_MASK;
+	if (!xpcs->pcs.poll)
+		ret |= DW_VR_MII_AN_INTR_EN;
 	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_CTRL, ret);
 	if (ret < 0)
 		return ret;
@@ -1029,6 +1034,17 @@ static int xpcs_get_state_c37_1000basex(struct dw_xpcs *xpcs,
 		if (bmsr < 0)
 			return bmsr;
 
+		/* Clear AN complete interrupt */
+		if (!xpcs->pcs.poll) {
+			int an_intr;
+
+			an_intr = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS);
+			if (an_intr & DW_VR_MII_AN_STS_C37_ANCMPLT_INTR) {
+				an_intr &= ~DW_VR_MII_AN_STS_C37_ANCMPLT_INTR;
+				xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS, an_intr);
+			}
+		}
+
 		phylink_mii_c22_pcs_decode_state(state, bmsr, lpa);
 	}
 
@@ -1319,9 +1335,10 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev,
 
 		xpcs->pcs.ops = &xpcs_phylink_ops;
 		xpcs->pcs.neg_mode = true;
-		xpcs->pcs.poll = true;
 
 		if (xpcs->dev_flag != DW_DEV_TXGBE) {
+			xpcs->pcs.poll = true;
+
 			ret = xpcs_soft_reset(xpcs, compat);
 			if (ret)
 				goto out;
diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h
index da61ad36946c0..ff04f6bc00a19 100644
--- a/drivers/net/pcs/pcs-xpcs.h
+++ b/drivers/net/pcs/pcs-xpcs.h
@@ -18,6 +18,7 @@
 #define DW_VR_XS_PCS_DIG_CTRL1		0x0000
 #define DW_VR_RST			BIT(15)
 #define DW_EN_VSMMD1			BIT(13)
+#define DW_CL37_BP			BIT(12)
 #define DW_VR_XS_PCS_DIG_STS		0x0010
 #define DW_RXFIFO_ERR			GENMASK(6, 5)
 #define DW_PSEQ_ST			GENMASK(4, 2)
@@ -80,8 +81,10 @@
 #define DW_VR_MII_PCS_MODE_MASK			GENMASK(2, 1)
 #define DW_VR_MII_PCS_MODE_C37_1000BASEX	0x0
 #define DW_VR_MII_PCS_MODE_C37_SGMII		0x2
+#define DW_VR_MII_AN_INTR_EN			BIT(0)
 
 /* VR_MII_AN_INTR_STS */
+#define DW_VR_MII_AN_STS_C37_ANCMPLT_INTR	BIT(0)
 #define DW_VR_MII_AN_STS_C37_ANSGM_FD		BIT(1)
 #define DW_VR_MII_AN_STS_C37_ANSGM_SP_SHIFT	2
 #define DW_VR_MII_AN_STS_C37_ANSGM_SP		GENMASK(3, 2)
-- 
GitLab


From 2a22b7ae2fa3b579d650c068c668fb252c49582b Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Wed, 23 Aug 2023 14:19:31 +0800
Subject: [PATCH 1660/1806] net: pcs: xpcs: adapt Wangxun NICs for SGMII mode

Wangxun NICs support the connection with SFP to RJ45 module. In this case,
PCS need to be configured in SGMII mode.

According to chapter 6.11.1 "SGMII Auto-Negitiation" of DesignWare Cores
Ethernet PCS (version 3.20a) and custom design manual, do the following
configuration when the interface mode is SGMII.

1. program VR_MII_AN_CTRL bit(3) [TX_CONFIG] = 1b (PHY side SGMII)
2. program VR_MII_AN_CTRL bit(8) [MII_CTRL] = 1b (8-bit MII)
3. program VR_MII_DIG_CTRL1 bit(0) [PHY_MODE_CTRL] = 1b

Also CL37 AN in backplane configurations need to be enabled because of the
special hardware design. Another thing to note is that PMA needs to be
reconfigured before each CL37 AN configuration for SGMII, otherwise AN will
fail, although we don't know why.

On this device, CL37_ANSGM_STS (bit[4:1] of VR_MII_AN_INTR_STS) indicates
the status received from remote link during the auto-negotiation, and
self-clear after the auto-negotiation is complete.
Meanwhile, CL37_ANCMPLT_INTR will be set to 1, to indicate CL37 AN is
complete. So add another way to get the state for CL37 SGMII.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/pcs/pcs-xpcs-wx.c |  5 ++--
 drivers/net/pcs/pcs-xpcs.c    | 47 ++++++++++++++++++++++++++++++++---
 drivers/net/pcs/pcs-xpcs.h    |  6 +++++
 3 files changed, 52 insertions(+), 6 deletions(-)

diff --git a/drivers/net/pcs/pcs-xpcs-wx.c b/drivers/net/pcs/pcs-xpcs-wx.c
index 1f228d5a13983..19c75886f070e 100644
--- a/drivers/net/pcs/pcs-xpcs-wx.c
+++ b/drivers/net/pcs/pcs-xpcs-wx.c
@@ -162,8 +162,9 @@ static bool txgbe_xpcs_mode_quirk(struct dw_xpcs *xpcs)
 	/* When txgbe do LAN reset, PCS will change to default 10GBASE-R mode */
 	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_CTRL2);
 	ret &= MDIO_PCS_CTRL2_TYPE;
-	if (ret == MDIO_PCS_CTRL2_10GBR &&
-	    xpcs->interface != PHY_INTERFACE_MODE_10GBASER)
+	if ((ret == MDIO_PCS_CTRL2_10GBR &&
+	     xpcs->interface != PHY_INTERFACE_MODE_10GBASER) ||
+	    xpcs->interface == PHY_INTERFACE_MODE_SGMII)
 		return true;
 
 	return false;
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index b806a9beecded..4dbc21f604f20 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -683,7 +683,10 @@ EXPORT_SYMBOL_GPL(xpcs_config_eee);
 static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs,
 				      unsigned int neg_mode)
 {
-	int ret, mdio_ctrl;
+	int ret, mdio_ctrl, tx_conf;
+
+	if (xpcs->dev_flag == DW_DEV_TXGBE)
+		xpcs_write_vpcs(xpcs, DW_VR_XS_PCS_DIG_CTRL1, DW_CL37_BP | DW_EN_VSMMD1);
 
 	/* For AN for C37 SGMII mode, the settings are :-
 	 * 1) VR_MII_MMD_CTRL Bit(12) [AN_ENABLE] = 0b (Disable SGMII AN in case
@@ -720,9 +723,15 @@ static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs,
 	ret |= (DW_VR_MII_PCS_MODE_C37_SGMII <<
 		DW_VR_MII_AN_CTRL_PCS_MODE_SHIFT &
 		DW_VR_MII_PCS_MODE_MASK);
-	ret |= (DW_VR_MII_TX_CONFIG_MAC_SIDE_SGMII <<
-		DW_VR_MII_AN_CTRL_TX_CONFIG_SHIFT &
-		DW_VR_MII_TX_CONFIG_MASK);
+	if (xpcs->dev_flag == DW_DEV_TXGBE) {
+		ret |= DW_VR_MII_AN_CTRL_8BIT;
+		/* Hardware requires it to be PHY side SGMII */
+		tx_conf = DW_VR_MII_TX_CONFIG_PHY_SIDE_SGMII;
+	} else {
+		tx_conf = DW_VR_MII_TX_CONFIG_MAC_SIDE_SGMII;
+	}
+	ret |= tx_conf << DW_VR_MII_AN_CTRL_TX_CONFIG_SHIFT &
+		DW_VR_MII_TX_CONFIG_MASK;
 	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_CTRL, ret);
 	if (ret < 0)
 		return ret;
@@ -736,6 +745,9 @@ static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs,
 	else
 		ret &= ~DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW;
 
+	if (xpcs->dev_flag == DW_DEV_TXGBE)
+		ret |= DW_VR_MII_DIG_CTRL1_PHY_MODE_CTRL;
+
 	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret);
 	if (ret < 0)
 		return ret;
@@ -1011,6 +1023,33 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs,
 			state->duplex = DUPLEX_FULL;
 		else
 			state->duplex = DUPLEX_HALF;
+	} else if (ret == DW_VR_MII_AN_STS_C37_ANCMPLT_INTR) {
+		int speed, duplex;
+
+		state->link = true;
+
+		speed = xpcs_read(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1);
+		if (speed < 0)
+			return speed;
+
+		speed &= SGMII_SPEED_SS13 | SGMII_SPEED_SS6;
+		if (speed == SGMII_SPEED_SS6)
+			state->speed = SPEED_1000;
+		else if (speed == SGMII_SPEED_SS13)
+			state->speed = SPEED_100;
+		else if (speed == 0)
+			state->speed = SPEED_10;
+
+		duplex = xpcs_read(xpcs, MDIO_MMD_VEND2, MII_ADVERTISE);
+		if (duplex < 0)
+			return duplex;
+
+		if (duplex & DW_FULL_DUPLEX)
+			state->duplex = DUPLEX_FULL;
+		else if (duplex & DW_HALF_DUPLEX)
+			state->duplex = DUPLEX_HALF;
+
+		xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS, 0);
 	}
 
 	return 0;
diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h
index ff04f6bc00a19..39a90417e5357 100644
--- a/drivers/net/pcs/pcs-xpcs.h
+++ b/drivers/net/pcs/pcs-xpcs.h
@@ -67,12 +67,14 @@
 
 /* VR_MII_DIG_CTRL1 */
 #define DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW		BIT(9)
+#define DW_VR_MII_DIG_CTRL1_PHY_MODE_CTRL	BIT(0)
 
 /* VR_MII_DIG_CTRL2 */
 #define DW_VR_MII_DIG_CTRL2_TX_POL_INV		BIT(4)
 #define DW_VR_MII_DIG_CTRL2_RX_POL_INV		BIT(0)
 
 /* VR_MII_AN_CTRL */
+#define DW_VR_MII_AN_CTRL_8BIT			BIT(8)
 #define DW_VR_MII_AN_CTRL_TX_CONFIG_SHIFT	3
 #define DW_VR_MII_TX_CONFIG_MASK		BIT(3)
 #define DW_VR_MII_TX_CONFIG_PHY_SIDE_SGMII	0x1
@@ -98,6 +100,10 @@
 #define SGMII_SPEED_SS13		BIT(13)	/* SGMII speed along with SS6 */
 #define SGMII_SPEED_SS6			BIT(6)	/* SGMII speed along with SS13 */
 
+/* SR MII MMD AN Advertisement defines */
+#define DW_HALF_DUPLEX			BIT(6)
+#define DW_FULL_DUPLEX			BIT(5)
+
 /* VR MII EEE Control 0 defines */
 #define DW_VR_MII_EEE_LTX_EN			BIT(0)  /* LPI Tx Enable */
 #define DW_VR_MII_EEE_LRX_EN			BIT(1)  /* LPI Rx Enable */
-- 
GitLab


From ab928c24e6cd9473a2f9ec04df8849cdad1ba2ca Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Wed, 23 Aug 2023 14:19:32 +0800
Subject: [PATCH 1661/1806] net: txgbe: add FW version warning

Since XPCS device identifier is implemented in the firmware version
0x20010 and above, so add a warning to prompt the users to upgrade the
firmware to make sure the driver works.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/wangxun/txgbe/txgbe_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index 46eba6d6188b2..641b8188da4ee 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -663,6 +663,9 @@ static int txgbe_probe(struct pci_dev *pdev,
 			 "0x%08x", etrack_id);
 	}
 
+	if (etrack_id < 0x20010)
+		dev_warn(&pdev->dev, "Please upgrade the firmware to 0x20010 or above.\n");
+
 	txgbe = devm_kzalloc(&pdev->dev, sizeof(*txgbe), GFP_KERNEL);
 	if (!txgbe) {
 		err = -ENOMEM;
-- 
GitLab


From a4414dd13f21d4e40a29a6ba068d17e4d3090021 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Wed, 23 Aug 2023 14:19:33 +0800
Subject: [PATCH 1662/1806] net: txgbe: support switching mode to 1000BASE-X
 and SGMII

Disable data path before PCS VR reset while switching PCS mode, to prevent
the blocking of data path. Enable AN interrupt for CL37 auto-negotiation.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |  2 ++
 drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c | 28 +++++++++++++++++
 drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h |  2 ++
 .../net/ethernet/wangxun/txgbe/txgbe_phy.c    | 30 ++++++++++++++++++-
 4 files changed, 61 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 1de88a33a698a..50b92cfb46a09 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -205,6 +205,8 @@
 #define WX_TSC_CTL                   0x1D000
 #define WX_TSC_CTL_TX_DIS            BIT(1)
 #define WX_TSC_CTL_TSEC_DIS          BIT(0)
+#define WX_TSC_ST                    0x1D004
+#define WX_TSC_ST_SECTX_RDY          BIT(0)
 #define WX_TSC_BUF_AE                0x1D00C
 #define WX_TSC_BUF_AE_THR            GENMASK(9, 0)
 
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
index 6e130d1f7a7bb..90168aab11aea 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
@@ -13,6 +13,34 @@
 #include "txgbe_type.h"
 #include "txgbe_hw.h"
 
+/**
+ *  txgbe_disable_sec_tx_path - Stops the transmit data path
+ *  @wx: pointer to hardware structure
+ *
+ *  Stops the transmit data path and waits for the HW to internally empty
+ *  the tx security block
+ **/
+int txgbe_disable_sec_tx_path(struct wx *wx)
+{
+	int val;
+
+	wr32m(wx, WX_TSC_CTL, WX_TSC_CTL_TX_DIS, WX_TSC_CTL_TX_DIS);
+	return read_poll_timeout(rd32, val, val & WX_TSC_ST_SECTX_RDY,
+				 1000, 20000, false, wx, WX_TSC_ST);
+}
+
+/**
+ *  txgbe_enable_sec_tx_path - Enables the transmit data path
+ *  @wx: pointer to hardware structure
+ *
+ *  Enables the transmit data path.
+ **/
+void txgbe_enable_sec_tx_path(struct wx *wx)
+{
+	wr32m(wx, WX_TSC_CTL, WX_TSC_CTL_TX_DIS, 0);
+	WX_WRITE_FLUSH(wx);
+}
+
 /**
  *  txgbe_init_thermal_sensor_thresh - Inits thermal sensor thresholds
  *  @wx: pointer to hardware structure
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h
index e82f65dff8a6c..abc729eb187ae 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h
@@ -4,6 +4,8 @@
 #ifndef _TXGBE_HW_H_
 #define _TXGBE_HW_H_
 
+int txgbe_disable_sec_tx_path(struct wx *wx);
+void txgbe_enable_sec_tx_path(struct wx *wx);
 int txgbe_read_pba_string(struct wx *wx, u8 *pba_num, u32 pba_num_size);
 int txgbe_validate_eeprom_checksum(struct wx *wx, u16 *checksum_val);
 int txgbe_reset_hw(struct wx *wx);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 819d1db346433..d2124547394d2 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -18,6 +18,7 @@
 #include "../libwx/wx_hw.h"
 #include "txgbe_type.h"
 #include "txgbe_phy.h"
+#include "txgbe_hw.h"
 
 static int txgbe_swnodes_register(struct txgbe *txgbe)
 {
@@ -210,8 +211,32 @@ static void txgbe_mac_link_up(struct phylink_config *config,
 	wr32(wx, WX_MAC_WDG_TIMEOUT, wdg);
 }
 
+static int txgbe_mac_prepare(struct phylink_config *config, unsigned int mode,
+			     phy_interface_t interface)
+{
+	struct wx *wx = netdev_priv(to_net_dev(config->dev));
+
+	wr32m(wx, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0);
+	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_RE, 0);
+
+	return txgbe_disable_sec_tx_path(wx);
+}
+
+static int txgbe_mac_finish(struct phylink_config *config, unsigned int mode,
+			    phy_interface_t interface)
+{
+	struct wx *wx = netdev_priv(to_net_dev(config->dev));
+
+	txgbe_enable_sec_tx_path(wx);
+	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_RE, WX_MAC_RX_CFG_RE);
+
+	return 0;
+}
+
 static const struct phylink_mac_ops txgbe_mac_ops = {
 	.mac_select_pcs = txgbe_phylink_mac_select,
+	.mac_prepare = txgbe_mac_prepare,
+	.mac_finish = txgbe_mac_finish,
 	.mac_config = txgbe_mac_config,
 	.mac_link_down = txgbe_mac_link_down,
 	.mac_link_up = txgbe_mac_link_up,
@@ -234,6 +259,8 @@ static int txgbe_phylink_init(struct txgbe *txgbe)
 	config->mac_capabilities = MAC_10000FD | MAC_1000FD | MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
 	phy_mode = PHY_INTERFACE_MODE_10GBASER;
 	__set_bit(PHY_INTERFACE_MODE_10GBASER, config->supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_1000BASEX, config->supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_SGMII, config->supported_interfaces);
 	fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_PHYLINK]);
 	phylink = phylink_create(config, fwnode, phy_mode, &txgbe_mac_ops);
 	if (IS_ERR(phylink))
@@ -431,7 +458,8 @@ static void txgbe_irq_handler(struct irq_desc *desc)
 
 	chained_irq_exit(chip, desc);
 
-	if (eicr & (TXGBE_PX_MISC_ETH_LK | TXGBE_PX_MISC_ETH_LKDN)) {
+	if (eicr & (TXGBE_PX_MISC_ETH_LK | TXGBE_PX_MISC_ETH_LKDN |
+		    TXGBE_PX_MISC_ETH_AN)) {
 		u32 reg = rd32(wx, TXGBE_CFG_PORT_ST);
 
 		phylink_mac_change(txgbe->phylink, !!(reg & TXGBE_CFG_PORT_ST_LINK_UP));
-- 
GitLab


From 02b2a6f91b9042552bc3aa728622bda97e3916fa Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Wed, 23 Aug 2023 14:19:34 +0800
Subject: [PATCH 1663/1806] net: txgbe: support copper NIC with external PHY

Wangxun SP chip supports to connect with external PHY (marvell 88x3310),
which links to 10GBASE-T/1000BASE-T/100BASE-T. Add the identification of
media types from subsystem device IDs. For sp_media_copper, register mdio
bus for the external PHY.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/wangxun/Kconfig          |   1 +
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |  26 +++
 drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c |  13 +-
 .../net/ethernet/wangxun/txgbe/txgbe_main.c   |  53 +++++--
 .../net/ethernet/wangxun/txgbe/txgbe_phy.c    | 150 +++++++++++++++++-
 5 files changed, 221 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig
index 39596cd135394..23cd610bd3766 100644
--- a/drivers/net/ethernet/wangxun/Kconfig
+++ b/drivers/net/ethernet/wangxun/Kconfig
@@ -41,6 +41,7 @@ config TXGBE
 	tristate "Wangxun(R) 10GbE PCI Express adapters support"
 	depends on PCI
 	depends on COMMON_CLK
+	select MARVELL_10G_PHY
 	select REGMAP
 	select I2C
 	select I2C_DESIGNWARE_PLATFORM
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 50b92cfb46a09..c5cbd177ef627 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -233,6 +233,24 @@
 #define WX_MAC_WDG_TIMEOUT           0x1100C
 #define WX_MAC_RX_FLOW_CTRL          0x11090
 #define WX_MAC_RX_FLOW_CTRL_RFE      BIT(0) /* receive fc enable */
+/* MDIO Registers */
+#define WX_MSCA                      0x11200
+#define WX_MSCA_RA(v)                FIELD_PREP(U16_MAX, v)
+#define WX_MSCA_PA(v)                FIELD_PREP(GENMASK(20, 16), v)
+#define WX_MSCA_DA(v)                FIELD_PREP(GENMASK(25, 21), v)
+#define WX_MSCC                      0x11204
+#define WX_MSCC_CMD(v)               FIELD_PREP(GENMASK(17, 16), v)
+
+enum WX_MSCA_CMD_value {
+	WX_MSCA_CMD_RSV = 0,
+	WX_MSCA_CMD_WRITE,
+	WX_MSCA_CMD_POST_READ,
+	WX_MSCA_CMD_READ,
+};
+
+#define WX_MSCC_SADDR                BIT(18)
+#define WX_MSCC_BUSY                 BIT(22)
+#define WX_MDIO_CLK(v)               FIELD_PREP(GENMASK(21, 19), v)
 #define WX_MMC_CONTROL               0x11800
 #define WX_MMC_CONTROL_RSTONRD       BIT(2) /* reset on read */
 
@@ -582,6 +600,13 @@ enum wx_mac_type {
 	wx_mac_em
 };
 
+enum sp_media_type {
+	sp_media_unknown = 0,
+	sp_media_fiber,
+	sp_media_copper,
+	sp_media_backplane
+};
+
 enum em_mac_type {
 	em_mac_type_unknown = 0,
 	em_mac_type_mdi,
@@ -829,6 +854,7 @@ struct wx {
 	struct wx_bus_info bus;
 	struct wx_mac_info mac;
 	enum em_mac_type mac_type;
+	enum sp_media_type media_type;
 	struct wx_eeprom_info eeprom;
 	struct wx_addr_filter_info addr_ctrl;
 	struct wx_mac_addr *mac_table;
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
index 90168aab11aea..3727452502700 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
@@ -285,17 +285,20 @@ static void txgbe_reset_misc(struct wx *wx)
 int txgbe_reset_hw(struct wx *wx)
 {
 	int status;
-	u32 val;
 
 	/* Call adapter stop to disable tx/rx and clear interrupts */
 	status = wx_stop_adapter(wx);
 	if (status != 0)
 		return status;
 
-	val = WX_MIS_RST_LAN_RST(wx->bus.func);
-	wr32(wx, WX_MIS_RST, val | rd32(wx, WX_MIS_RST));
-	WX_WRITE_FLUSH(wx);
-	usleep_range(10, 100);
+	if (wx->media_type != sp_media_copper) {
+		u32 val;
+
+		val = WX_MIS_RST_LAN_RST(wx->bus.func);
+		wr32(wx, WX_MIS_RST, val | rd32(wx, WX_MIS_RST));
+		WX_WRITE_FLUSH(wx);
+		usleep_range(10, 100);
+	}
 
 	status = wx_check_flash_load(wx, TXGBE_SPI_ILDR_STATUS_LAN_SW_RST(wx->bus.func));
 	if (status != 0)
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index 641b8188da4ee..5c3aed516ac20 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -300,6 +300,49 @@ static void txgbe_down(struct wx *wx)
 	wx_clean_all_rx_rings(wx);
 }
 
+/**
+ *  txgbe_init_type_code - Initialize the shared code
+ *  @wx: pointer to hardware structure
+ **/
+static void txgbe_init_type_code(struct wx *wx)
+{
+	u8 device_type = wx->subsystem_device_id & 0xF0;
+
+	switch (wx->device_id) {
+	case TXGBE_DEV_ID_SP1000:
+	case TXGBE_DEV_ID_WX1820:
+		wx->mac.type = wx_mac_sp;
+		break;
+	default:
+		wx->mac.type = wx_mac_unknown;
+		break;
+	}
+
+	switch (device_type) {
+	case TXGBE_ID_SFP:
+		wx->media_type = sp_media_fiber;
+		break;
+	case TXGBE_ID_XAUI:
+	case TXGBE_ID_SGMII:
+		wx->media_type = sp_media_copper;
+		break;
+	case TXGBE_ID_KR_KX_KX4:
+	case TXGBE_ID_MAC_XAUI:
+	case TXGBE_ID_MAC_SGMII:
+		wx->media_type = sp_media_backplane;
+		break;
+	case TXGBE_ID_SFI_XAUI:
+		if (wx->bus.func == 0)
+			wx->media_type = sp_media_fiber;
+		else
+			wx->media_type = sp_media_copper;
+		break;
+	default:
+		wx->media_type = sp_media_unknown;
+		break;
+	}
+}
+
 /**
  * txgbe_sw_init - Initialize general software structures (struct wx)
  * @wx: board private structure to initialize
@@ -324,15 +367,7 @@ static int txgbe_sw_init(struct wx *wx)
 		return err;
 	}
 
-	switch (wx->device_id) {
-	case TXGBE_DEV_ID_SP1000:
-	case TXGBE_DEV_ID_WX1820:
-		wx->mac.type = wx_mac_sp;
-		break;
-	default:
-		wx->mac.type = wx_mac_unknown;
-		break;
-	}
+	txgbe_init_type_code(wx);
 
 	/* Set common capability flags and settings */
 	wx->max_q_vectors = TXGBE_MAX_MSIX_VECTORS;
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index d2124547394d2..4159c84035fdc 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -161,7 +161,10 @@ static struct phylink_pcs *txgbe_phylink_mac_select(struct phylink_config *confi
 {
 	struct txgbe *txgbe = netdev_to_txgbe(to_net_dev(config->dev));
 
-	return &txgbe->xpcs->pcs;
+	if (interface == PHY_INTERFACE_MODE_10GBASER)
+		return &txgbe->xpcs->pcs;
+
+	return NULL;
 }
 
 static void txgbe_mac_config(struct phylink_config *config, unsigned int mode,
@@ -244,8 +247,8 @@ static const struct phylink_mac_ops txgbe_mac_ops = {
 
 static int txgbe_phylink_init(struct txgbe *txgbe)
 {
+	struct fwnode_handle *fwnode = NULL;
 	struct phylink_config *config;
-	struct fwnode_handle *fwnode;
 	struct wx *wx = txgbe->wx;
 	phy_interface_t phy_mode;
 	struct phylink *phylink;
@@ -256,16 +259,34 @@ static int txgbe_phylink_init(struct txgbe *txgbe)
 
 	config->dev = &wx->netdev->dev;
 	config->type = PHYLINK_NETDEV;
-	config->mac_capabilities = MAC_10000FD | MAC_1000FD | MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
-	phy_mode = PHY_INTERFACE_MODE_10GBASER;
-	__set_bit(PHY_INTERFACE_MODE_10GBASER, config->supported_interfaces);
-	__set_bit(PHY_INTERFACE_MODE_1000BASEX, config->supported_interfaces);
-	__set_bit(PHY_INTERFACE_MODE_SGMII, config->supported_interfaces);
-	fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_PHYLINK]);
+	config->mac_capabilities = MAC_10000FD | MAC_1000FD | MAC_100FD |
+				   MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
+
+	if (wx->media_type == sp_media_copper) {
+		phy_mode = PHY_INTERFACE_MODE_XAUI;
+		__set_bit(PHY_INTERFACE_MODE_XAUI, config->supported_interfaces);
+	} else {
+		phy_mode = PHY_INTERFACE_MODE_10GBASER;
+		fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_PHYLINK]);
+		__set_bit(PHY_INTERFACE_MODE_10GBASER, config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_1000BASEX, config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_SGMII, config->supported_interfaces);
+	}
+
 	phylink = phylink_create(config, fwnode, phy_mode, &txgbe_mac_ops);
 	if (IS_ERR(phylink))
 		return PTR_ERR(phylink);
 
+	if (wx->phydev) {
+		int ret;
+
+		ret = phylink_connect_phy(phylink, wx->phydev);
+		if (ret) {
+			phylink_destroy(phylink);
+			return ret;
+		}
+	}
+
 	txgbe->phylink = phylink;
 
 	return 0;
@@ -626,10 +647,117 @@ static int txgbe_sfp_register(struct txgbe *txgbe)
 	return 0;
 }
 
+static int txgbe_phy_read(struct mii_bus *bus, int phy_addr,
+			  int devnum, int regnum)
+{
+	struct wx *wx = bus->priv;
+	u32 val, command;
+	int ret;
+
+	/* setup and write the address cycle command */
+	command = WX_MSCA_RA(regnum) |
+		  WX_MSCA_PA(phy_addr) |
+		  WX_MSCA_DA(devnum);
+	wr32(wx, WX_MSCA, command);
+
+	command = WX_MSCC_CMD(WX_MSCA_CMD_READ) | WX_MSCC_BUSY;
+	wr32(wx, WX_MSCC, command);
+
+	/* wait to complete */
+	ret = read_poll_timeout(rd32, val, !(val & WX_MSCC_BUSY), 1000,
+				100000, false, wx, WX_MSCC);
+	if (ret) {
+		wx_err(wx, "Mdio read c45 command did not complete.\n");
+		return ret;
+	}
+
+	return (u16)rd32(wx, WX_MSCC);
+}
+
+static int txgbe_phy_write(struct mii_bus *bus, int phy_addr,
+			   int devnum, int regnum, u16 value)
+{
+	struct wx *wx = bus->priv;
+	int ret, command;
+	u16 val;
+
+	/* setup and write the address cycle command */
+	command = WX_MSCA_RA(regnum) |
+		  WX_MSCA_PA(phy_addr) |
+		  WX_MSCA_DA(devnum);
+	wr32(wx, WX_MSCA, command);
+
+	command = value | WX_MSCC_CMD(WX_MSCA_CMD_WRITE) | WX_MSCC_BUSY;
+	wr32(wx, WX_MSCC, command);
+
+	/* wait to complete */
+	ret = read_poll_timeout(rd32, val, !(val & WX_MSCC_BUSY), 1000,
+				100000, false, wx, WX_MSCC);
+	if (ret)
+		wx_err(wx, "Mdio write c45 command did not complete.\n");
+
+	return ret;
+}
+
+static int txgbe_ext_phy_init(struct txgbe *txgbe)
+{
+	struct phy_device *phydev;
+	struct mii_bus *mii_bus;
+	struct pci_dev *pdev;
+	struct wx *wx;
+	int ret = 0;
+
+	wx = txgbe->wx;
+	pdev = wx->pdev;
+
+	mii_bus = devm_mdiobus_alloc(&pdev->dev);
+	if (!mii_bus)
+		return -ENOMEM;
+
+	mii_bus->name = "txgbe_mii_bus";
+	mii_bus->read_c45 = &txgbe_phy_read;
+	mii_bus->write_c45 = &txgbe_phy_write;
+	mii_bus->parent = &pdev->dev;
+	mii_bus->phy_mask = GENMASK(31, 1);
+	mii_bus->priv = wx;
+	snprintf(mii_bus->id, MII_BUS_ID_SIZE, "txgbe-%x",
+		 (pdev->bus->number << 8) | pdev->devfn);
+
+	ret = devm_mdiobus_register(&pdev->dev, mii_bus);
+	if (ret) {
+		wx_err(wx, "failed to register MDIO bus: %d\n", ret);
+		return ret;
+	}
+
+	phydev = phy_find_first(mii_bus);
+	if (!phydev) {
+		wx_err(wx, "no PHY found\n");
+		return -ENODEV;
+	}
+
+	phy_attached_info(phydev);
+
+	wx->link = 0;
+	wx->speed = 0;
+	wx->duplex = 0;
+	wx->phydev = phydev;
+
+	ret = txgbe_phylink_init(txgbe);
+	if (ret) {
+		wx_err(wx, "failed to init phylink: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 int txgbe_init_phy(struct txgbe *txgbe)
 {
 	int ret;
 
+	if (txgbe->wx->media_type == sp_media_copper)
+		return txgbe_ext_phy_init(txgbe);
+
 	ret = txgbe_swnodes_register(txgbe);
 	if (ret) {
 		wx_err(txgbe->wx, "failed to register software nodes\n");
@@ -691,6 +819,12 @@ err_unregister_swnode:
 
 void txgbe_remove_phy(struct txgbe *txgbe)
 {
+	if (txgbe->wx->media_type == sp_media_copper) {
+		phylink_disconnect_phy(txgbe->phylink);
+		phylink_destroy(txgbe->phylink);
+		return;
+	}
+
 	platform_device_unregister(txgbe->sfp_dev);
 	platform_device_unregister(txgbe->i2c_dev);
 	clkdev_drop(txgbe->clock);
-- 
GitLab


From ad63f7aa585ee58ebf5e83af09653134a21cd082 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Wed, 23 Aug 2023 14:19:35 +0800
Subject: [PATCH 1664/1806] net: ngbe: move mdio access registers to libwx

Registers of mdio accessing are common defined in libwx, remove the
redundant macro definitions in ngbe driver.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c | 84 +++++++++----------
 drivers/net/ethernet/wangxun/ngbe/ngbe_type.h | 19 -----
 2 files changed, 42 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
index fe20f02ecb3aa..591f5b7b6da65 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
@@ -37,24 +37,24 @@ static int ngbe_phy_read_reg_mdi_c22(struct mii_bus *bus, int phy_addr, int regn
 
 	wr32(wx, NGBE_MDIO_CLAUSE_SELECT, 0xF);
 	/* setup and write the address cycle command */
-	command = NGBE_MSCA_RA(regnum) |
-		  NGBE_MSCA_PA(phy_addr) |
-		  NGBE_MSCA_DA(device_type);
-	wr32(wx, NGBE_MSCA, command);
-	command = NGBE_MSCC_CMD(NGBE_MSCA_CMD_READ) |
-		  NGBE_MSCC_BUSY |
-		  NGBE_MDIO_CLK(6);
-	wr32(wx, NGBE_MSCC, command);
+	command = WX_MSCA_RA(regnum) |
+		  WX_MSCA_PA(phy_addr) |
+		  WX_MSCA_DA(device_type);
+	wr32(wx, WX_MSCA, command);
+	command = WX_MSCC_CMD(WX_MSCA_CMD_READ) |
+		  WX_MSCC_BUSY |
+		  WX_MDIO_CLK(6);
+	wr32(wx, WX_MSCC, command);
 
 	/* wait to complete */
-	ret = read_poll_timeout(rd32, val, !(val & NGBE_MSCC_BUSY), 1000,
-				100000, false, wx, NGBE_MSCC);
+	ret = read_poll_timeout(rd32, val, !(val & WX_MSCC_BUSY), 1000,
+				100000, false, wx, WX_MSCC);
 	if (ret) {
 		wx_err(wx, "Mdio read c22 command did not complete.\n");
 		return ret;
 	}
 
-	return (u16)rd32(wx, NGBE_MSCC);
+	return (u16)rd32(wx, WX_MSCC);
 }
 
 static int ngbe_phy_write_reg_mdi_c22(struct mii_bus *bus, int phy_addr, int regnum, u16 value)
@@ -65,19 +65,19 @@ static int ngbe_phy_write_reg_mdi_c22(struct mii_bus *bus, int phy_addr, int reg
 
 	wr32(wx, NGBE_MDIO_CLAUSE_SELECT, 0xF);
 	/* setup and write the address cycle command */
-	command = NGBE_MSCA_RA(regnum) |
-		  NGBE_MSCA_PA(phy_addr) |
-		  NGBE_MSCA_DA(device_type);
-	wr32(wx, NGBE_MSCA, command);
+	command = WX_MSCA_RA(regnum) |
+		  WX_MSCA_PA(phy_addr) |
+		  WX_MSCA_DA(device_type);
+	wr32(wx, WX_MSCA, command);
 	command = value |
-		  NGBE_MSCC_CMD(NGBE_MSCA_CMD_WRITE) |
-		  NGBE_MSCC_BUSY |
-		  NGBE_MDIO_CLK(6);
-	wr32(wx, NGBE_MSCC, command);
+		  WX_MSCC_CMD(WX_MSCA_CMD_WRITE) |
+		  WX_MSCC_BUSY |
+		  WX_MDIO_CLK(6);
+	wr32(wx, WX_MSCC, command);
 
 	/* wait to complete */
-	ret = read_poll_timeout(rd32, val, !(val & NGBE_MSCC_BUSY), 1000,
-				100000, false, wx, NGBE_MSCC);
+	ret = read_poll_timeout(rd32, val, !(val & WX_MSCC_BUSY), 1000,
+				100000, false, wx, WX_MSCC);
 	if (ret)
 		wx_err(wx, "Mdio write c22 command did not complete.\n");
 
@@ -92,24 +92,24 @@ static int ngbe_phy_read_reg_mdi_c45(struct mii_bus *bus, int phy_addr, int devn
 
 	wr32(wx, NGBE_MDIO_CLAUSE_SELECT, 0x0);
 	/* setup and write the address cycle command */
-	command = NGBE_MSCA_RA(regnum) |
-		  NGBE_MSCA_PA(phy_addr) |
-		  NGBE_MSCA_DA(devnum);
-	wr32(wx, NGBE_MSCA, command);
-	command = NGBE_MSCC_CMD(NGBE_MSCA_CMD_READ) |
-		  NGBE_MSCC_BUSY |
-		  NGBE_MDIO_CLK(6);
-	wr32(wx, NGBE_MSCC, command);
+	command = WX_MSCA_RA(regnum) |
+		  WX_MSCA_PA(phy_addr) |
+		  WX_MSCA_DA(devnum);
+	wr32(wx, WX_MSCA, command);
+	command = WX_MSCC_CMD(WX_MSCA_CMD_READ) |
+		  WX_MSCC_BUSY |
+		  WX_MDIO_CLK(6);
+	wr32(wx, WX_MSCC, command);
 
 	/* wait to complete */
-	ret = read_poll_timeout(rd32, val, !(val & NGBE_MSCC_BUSY), 1000,
-				100000, false, wx, NGBE_MSCC);
+	ret = read_poll_timeout(rd32, val, !(val & WX_MSCC_BUSY), 1000,
+				100000, false, wx, WX_MSCC);
 	if (ret) {
 		wx_err(wx, "Mdio read c45 command did not complete.\n");
 		return ret;
 	}
 
-	return (u16)rd32(wx, NGBE_MSCC);
+	return (u16)rd32(wx, WX_MSCC);
 }
 
 static int ngbe_phy_write_reg_mdi_c45(struct mii_bus *bus, int phy_addr,
@@ -121,19 +121,19 @@ static int ngbe_phy_write_reg_mdi_c45(struct mii_bus *bus, int phy_addr,
 
 	wr32(wx, NGBE_MDIO_CLAUSE_SELECT, 0x0);
 	/* setup and write the address cycle command */
-	command = NGBE_MSCA_RA(regnum) |
-		  NGBE_MSCA_PA(phy_addr) |
-		  NGBE_MSCA_DA(devnum);
-	wr32(wx, NGBE_MSCA, command);
+	command = WX_MSCA_RA(regnum) |
+		  WX_MSCA_PA(phy_addr) |
+		  WX_MSCA_DA(devnum);
+	wr32(wx, WX_MSCA, command);
 	command = value |
-		  NGBE_MSCC_CMD(NGBE_MSCA_CMD_WRITE) |
-		  NGBE_MSCC_BUSY |
-		  NGBE_MDIO_CLK(6);
-	wr32(wx, NGBE_MSCC, command);
+		  WX_MSCC_CMD(WX_MSCA_CMD_WRITE) |
+		  WX_MSCC_BUSY |
+		  WX_MDIO_CLK(6);
+	wr32(wx, WX_MSCC, command);
 
 	/* wait to complete */
-	ret = read_poll_timeout(rd32, val, !(val & NGBE_MSCC_BUSY), 1000,
-				100000, false, wx, NGBE_MSCC);
+	ret = read_poll_timeout(rd32, val, !(val & WX_MSCC_BUSY), 1000,
+				100000, false, wx, WX_MSCC);
 	if (ret)
 		wx_err(wx, "Mdio write c45 command did not complete.\n");
 
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
index b70eca397b672..72c8cd2d55751 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
@@ -59,25 +59,6 @@
 #define NGBE_EEPROM_VERSION_L			0x1D
 #define NGBE_EEPROM_VERSION_H			0x1E
 
-/* mdio access */
-#define NGBE_MSCA				0x11200
-#define NGBE_MSCA_RA(v)				FIELD_PREP(U16_MAX, v)
-#define NGBE_MSCA_PA(v)				FIELD_PREP(GENMASK(20, 16), v)
-#define NGBE_MSCA_DA(v)				FIELD_PREP(GENMASK(25, 21), v)
-#define NGBE_MSCC				0x11204
-#define NGBE_MSCC_CMD(v)			FIELD_PREP(GENMASK(17, 16), v)
-
-enum NGBE_MSCA_CMD_value {
-	NGBE_MSCA_CMD_RSV = 0,
-	NGBE_MSCA_CMD_WRITE,
-	NGBE_MSCA_CMD_POST_READ,
-	NGBE_MSCA_CMD_READ,
-};
-
-#define NGBE_MSCC_SADDR				BIT(18)
-#define NGBE_MSCC_BUSY				BIT(22)
-#define NGBE_MDIO_CLK(v)			FIELD_PREP(GENMASK(21, 19), v)
-
 /* Media-dependent registers. */
 #define NGBE_MDIO_CLAUSE_SELECT			0x11220
 
-- 
GitLab


From a4f39c9f14a634e4cd35fcd338c239d11fcc73fc Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 23 Aug 2023 15:41:02 +0200
Subject: [PATCH 1665/1806] net: handle ARPHRD_PPP in dev_is_mac_header_xmit()

The goal is to support a bpf_redirect() from an ethernet device (ingress)
to a ppp device (egress).
The l2 header is added automatically by the ppp driver, thus the ethernet
header should be removed.

CC: stable@vger.kernel.org
Fixes: 27b29f63058d ("bpf: add bpf_redirect() helper")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Tested-by: Siwar Zitouni <siwar.zitouni@6wind.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_arp.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h
index 1ed52441972f9..10a1e81434cb9 100644
--- a/include/linux/if_arp.h
+++ b/include/linux/if_arp.h
@@ -53,6 +53,10 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev)
 	case ARPHRD_NONE:
 	case ARPHRD_RAWIP:
 	case ARPHRD_PIMREG:
+	/* PPP adds its l2 header automatically in ppp_start_xmit().
+	 * This makes it look like an l3 device to __bpf_redirect() and tcf_mirred_init().
+	 */
+	case ARPHRD_PPP:
 		return false;
 	default:
 		return true;
-- 
GitLab


From 1e4134610d93271535ecf900a676e1f094e9944c Mon Sep 17 00:00:00 2001
From: Wang Ming <machel@vivo.com>
Date: Thu, 13 Jul 2023 11:03:44 +0800
Subject: [PATCH 1666/1806] wifi: ath9k: use IS_ERR() with debugfs_create_dir()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The debugfs_create_dir() function returns error pointers,
it never returns NULL. Most incorrect error checks were fixed,
but the one in ath9k_htc_init_debug() was forgotten.

Fix the remaining error check.

Fixes: e5facc75fa91 ("ath9k_htc: Cleanup HTC debugfs")
Signed-off-by: Wang Ming <machel@vivo.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230713030358.12379-1-machel@vivo.com
---
 drivers/net/wireless/ath/ath9k/htc_drv_debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
index 1ed2b1216bce9..c549ff3abcdc4 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
@@ -486,7 +486,7 @@ int ath9k_htc_init_debug(struct ath_hw *ah)
 
 	priv->debug.debugfs_phy = debugfs_create_dir(KBUILD_MODNAME,
 					     priv->hw->wiphy->debugfsdir);
-	if (!priv->debug.debugfs_phy)
+	if (IS_ERR(priv->debug.debugfs_phy))
 		return -ENOMEM;
 
 	ath9k_cmn_spectral_init_debug(&priv->spec_priv, priv->debug.debugfs_phy);
-- 
GitLab


From 2f5124e86ae74b7ba24c9ae2644107b750cbf38f Mon Sep 17 00:00:00 2001
From: Wen Gong <quic_wgong@quicinc.com>
Date: Wed, 9 Aug 2023 04:16:57 -0400
Subject: [PATCH 1667/1806] wifi: ath12k: add check max message length while
 scanning with extraie

Currently the extraie length is directly used to allocate skb buffer. When
the length of skb is greater than the max message length which firmware
supports, error will happen in firmware side.

Hence add check for the skb length and drop extraie when overflow and
print a message.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230809081657.13858-1-quic_wgong@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index cc9a377c06fd0..ef0f3cf35cfd1 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -2239,12 +2239,6 @@ int ath12k_wmi_send_scan_start_cmd(struct ath12k *ar,
 	if (arg->num_bssid)
 		len += sizeof(*bssid) * arg->num_bssid;
 
-	len += TLV_HDR_SIZE;
-	if (arg->extraie.len)
-		extraie_len_with_pad =
-			roundup(arg->extraie.len, sizeof(u32));
-	len += extraie_len_with_pad;
-
 	if (arg->num_hint_bssid)
 		len += TLV_HDR_SIZE +
 		       arg->num_hint_bssid * sizeof(*hint_bssid);
@@ -2253,6 +2247,18 @@ int ath12k_wmi_send_scan_start_cmd(struct ath12k *ar,
 		len += TLV_HDR_SIZE +
 		       arg->num_hint_s_ssid * sizeof(*s_ssid);
 
+	len += TLV_HDR_SIZE;
+	if (arg->extraie.len)
+		extraie_len_with_pad =
+			roundup(arg->extraie.len, sizeof(u32));
+	if (extraie_len_with_pad <= (wmi->wmi_ab->max_msg_len[ar->pdev_idx] - len)) {
+		len += extraie_len_with_pad;
+	} else {
+		ath12k_warn(ar->ab, "discard large size %d bytes extraie for scan start\n",
+			    arg->extraie.len);
+		extraie_len_with_pad = 0;
+	}
+
 	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len);
 	if (!skb)
 		return -ENOMEM;
@@ -2342,7 +2348,7 @@ int ath12k_wmi_send_scan_start_cmd(struct ath12k *ar,
 	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_BYTE, len);
 	ptr += TLV_HDR_SIZE;
 
-	if (arg->extraie.len)
+	if (extraie_len_with_pad)
 		memcpy(ptr, arg->extraie.ptr,
 		       arg->extraie.len);
 
-- 
GitLab


From 0e5b1b46925b005bd4f701a116d06a561c7262e8 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 16 Aug 2023 21:05:50 +0800
Subject: [PATCH 1668/1806] wifi: ath12k: Remove unused declarations

Commit d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
declared but never implemented these, remove it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230816130550.50896-1-yuehaibing@huawei.com
---
 drivers/net/wireless/ath/ath12k/ce.h   | 3 ---
 drivers/net/wireless/ath/ath12k/core.h | 1 -
 drivers/net/wireless/ath/ath12k/qmi.h  | 2 --
 drivers/net/wireless/ath/ath12k/wmi.h  | 2 --
 4 files changed, 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/ce.h b/drivers/net/wireless/ath/ath12k/ce.h
index 17cf16235e0b3..79af3b6159f1c 100644
--- a/drivers/net/wireless/ath/ath12k/ce.h
+++ b/drivers/net/wireless/ath/ath12k/ce.h
@@ -176,9 +176,6 @@ int ath12k_ce_alloc_pipes(struct ath12k_base *ab);
 void ath12k_ce_free_pipes(struct ath12k_base *ab);
 int ath12k_ce_get_attr_flags(struct ath12k_base *ab, int ce_id);
 void ath12k_ce_poll_send_completed(struct ath12k_base *ab, u8 pipe_id);
-int ath12k_ce_map_service_to_pipe(struct ath12k_base *ab, u16 service_id,
-				  u8 *ul_pipe, u8 *dl_pipe);
-int ath12k_ce_attr_attach(struct ath12k_base *ab);
 void ath12k_ce_get_shadow_config(struct ath12k_base *ab,
 				 u32 **shadow_cfg, u32 *shadow_cfg_len);
 #endif
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 4389ff40b49db..d873b573dac66 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -788,7 +788,6 @@ int ath12k_core_fetch_board_data_api_1(struct ath12k_base *ab,
 int ath12k_core_fetch_bdf(struct ath12k_base *ath12k,
 			  struct ath12k_board_data *bd);
 void ath12k_core_free_bdf(struct ath12k_base *ab, struct ath12k_board_data *bd);
-int ath12k_core_check_dt(struct ath12k_base *ath12k);
 
 void ath12k_core_halt(struct ath12k *ar);
 int ath12k_core_resume(struct ath12k_base *ab);
diff --git a/drivers/net/wireless/ath/ath12k/qmi.h b/drivers/net/wireless/ath/ath12k/qmi.h
index df76149c49f5f..15944f5f33ab0 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.h
+++ b/drivers/net/wireless/ath/ath12k/qmi.h
@@ -562,8 +562,6 @@ struct qmi_wlanfw_wlan_cfg_resp_msg_v01 {
 int ath12k_qmi_firmware_start(struct ath12k_base *ab,
 			      u32 mode);
 void ath12k_qmi_firmware_stop(struct ath12k_base *ab);
-void ath12k_qmi_event_work(struct work_struct *work);
-void ath12k_qmi_msg_recv_work(struct work_struct *work);
 void ath12k_qmi_deinit_service(struct ath12k_base *ab);
 int ath12k_qmi_init_service(struct ath12k_base *ab);
 
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 8c047a9623f9b..c75a6fa1f7e08 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -4855,8 +4855,6 @@ int ath12k_wmi_vdev_install_key(struct ath12k *ar,
 				struct wmi_vdev_install_key_arg *arg);
 int ath12k_wmi_pdev_bss_chan_info_request(struct ath12k *ar,
 					  enum wmi_bss_chan_info_req_type type);
-int ath12k_wmi_send_stats_request_cmd(struct ath12k *ar, u32 stats_id,
-				      u32 vdev_id, u32 pdev_id);
 int ath12k_wmi_send_pdev_temperature_cmd(struct ath12k *ar);
 int ath12k_wmi_send_peer_flush_tids_cmd(struct ath12k *ar,
 					u8 peer_addr[ETH_ALEN],
-- 
GitLab


From 4c2964ef553b9c7c4ae1803158386a8b169f8f4e Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Mon, 14 Aug 2023 20:42:11 +0800
Subject: [PATCH 1669/1806] wifi: ath: Use is_multicast_ether_addr() to check
 multicast Ether address

Use is_multicast_ether_addr() to perform the Checking.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230814124212.302738-2-ruanjinjie@huawei.com
---
 drivers/net/wireless/ath/key.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/key.c b/drivers/net/wireless/ath/key.c
index b7b61d4f02bae..21a93fec284d6 100644
--- a/drivers/net/wireless/ath/key.c
+++ b/drivers/net/wireless/ath/key.c
@@ -104,7 +104,7 @@ bool ath_hw_keysetmac(struct ath_common *common, u16 entry, const u8 *mac)
 		 * Not setting this bit allows the hardware to use the key
 		 * for multicast frame decryption.
 		 */
-		if (mac[0] & 0x01)
+		if (is_multicast_ether_addr(mac))
 			unicast_flag = 0;
 
 		macLo = get_unaligned_le32(mac);
-- 
GitLab


From 0aacec49c29e7c5b1487e859b0c0a42388c34092 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 23 Aug 2023 08:18:14 -0700
Subject: [PATCH 1670/1806] ice: avoid executing commands on other ports when
 driving sync

The ice hardware has a synchronization mechanism used to drive the
simultaneous application of commands on both PHY ports and the source timer
in the MAC.

When issuing a sync via ice_ptp_exec_tmr_cmd(), the hardware will
simultaneously apply the commands programmed for the main timer and each
PHY port. Neither the main timer command register, nor the PHY port command
registers auto clear on command execution.

During the execution of a timer command intended for a single port on E822
devices, such as those used to configure a PHY during link up, the driver
is not correctly clearing the previous commands.

This results in unintentionally executing the last programmed command on
the main timer and other PHY ports whenever performing reconfiguration on
E822 ports after link up. This results in unintended side effects on other
timers, depending on what command was previously programmed.

To fix this, the driver must ensure that the main timer and all other PHY
ports are properly initialized to perform no action.

The enumeration for timer commands does not include an enumeration value
for doing nothing. Introduce ICE_PTP_NOP for this purpose. When writing a
timer command to hardware, leave the command bits set to zero which
indicates that no operation should be performed on that port.

Modify ice_ptp_one_port_cmd() to always initialize all ports. For all ports
other than the one being configured, write their timer command register to
ICE_PTP_NOP. This ensures that no side effect happens on the timer command.

To fix this for the PHY ports, modify ice_ptp_one_port_cmd() to always
initialize all other ports to ICE_PTP_NOP. This ensures that no side
effects happen on the other ports.

Call ice_ptp_src_cmd() with a command value if ICE_PTP_NOP in
ice_sync_phy_timer_e822() and ice_start_phy_timer_e822().

With both of these changes, the driver should no longer execute a stale
command on the main timer or another PHY port when reconfiguring one of the
PHY ports after link up.

Fixes: 3a7496234d17 ("ice: implement basic E822 PTP support")
Signed-off-by: Siddaraju DH <siddaraju.dh@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Sunitha Mekala <sunithax.d.mekala@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 55 +++++++++++++++++++--
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h |  3 +-
 2 files changed, 52 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index a38614d21ea8f..de1d83300481d 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -131,6 +131,8 @@ static void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	case READ_TIME:
 		cmd_val |= GLTSYN_CMD_READ_TIME;
 		break;
+	case ICE_PTP_NOP:
+		break;
 	}
 
 	wr32(hw, GLTSYN_CMD, cmd_val);
@@ -1226,18 +1228,18 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts)
 }
 
 /**
- * ice_ptp_one_port_cmd - Prepare a single PHY port for a timer command
+ * ice_ptp_write_port_cmd_e822 - Prepare a single PHY port for a timer command
  * @hw: pointer to HW struct
  * @port: Port to which cmd has to be sent
  * @cmd: Command to be sent to the port
  *
  * Prepare the requested port for an upcoming timer sync command.
  *
- * Note there is no equivalent of this operation on E810, as that device
- * always handles all external PHYs internally.
+ * Do not use this function directly. If you want to configure exactly one
+ * port, use ice_ptp_one_port_cmd() instead.
  */
 static int
-ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd)
+ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd)
 {
 	u32 cmd_val, val;
 	u8 tmr_idx;
@@ -1261,6 +1263,8 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd)
 	case ADJ_TIME_AT_TIME:
 		cmd_val |= PHY_CMD_ADJ_TIME_AT_TIME;
 		break;
+	case ICE_PTP_NOP:
+		break;
 	}
 
 	/* Tx case */
@@ -1306,6 +1310,39 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd)
 	return 0;
 }
 
+/**
+ * ice_ptp_one_port_cmd - Prepare one port for a timer command
+ * @hw: pointer to the HW struct
+ * @configured_port: the port to configure with configured_cmd
+ * @configured_cmd: timer command to prepare on the configured_port
+ *
+ * Prepare the configured_port for the configured_cmd, and prepare all other
+ * ports for ICE_PTP_NOP. This causes the configured_port to execute the
+ * desired command while all other ports perform no operation.
+ */
+static int
+ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port,
+		     enum ice_ptp_tmr_cmd configured_cmd)
+{
+	u8 port;
+
+	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
+		enum ice_ptp_tmr_cmd cmd;
+		int err;
+
+		if (port == configured_port)
+			cmd = configured_cmd;
+		else
+			cmd = ICE_PTP_NOP;
+
+		err = ice_ptp_write_port_cmd_e822(hw, port, cmd);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 /**
  * ice_ptp_port_cmd_e822 - Prepare all ports for a timer command
  * @hw: pointer to the HW struct
@@ -1322,7 +1359,7 @@ ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
 		int err;
 
-		err = ice_ptp_one_port_cmd(hw, port, cmd);
+		err = ice_ptp_write_port_cmd_e822(hw, port, cmd);
 		if (err)
 			return err;
 	}
@@ -2252,6 +2289,9 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port)
 	if (err)
 		goto err_unlock;
 
+	/* Do not perform any action on the main timer */
+	ice_ptp_src_cmd(hw, ICE_PTP_NOP);
+
 	/* Issue the sync to activate the time adjustment */
 	ice_ptp_exec_tmr_cmd(hw);
 
@@ -2372,6 +2412,9 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port)
 	if (err)
 		return err;
 
+	/* Do not perform any action on the main timer */
+	ice_ptp_src_cmd(hw, ICE_PTP_NOP);
+
 	ice_ptp_exec_tmr_cmd(hw);
 
 	err = ice_read_phy_reg_e822(hw, port, P_REG_PS, &val);
@@ -2847,6 +2890,8 @@ static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	case ADJ_TIME_AT_TIME:
 		cmd_val = GLTSYN_CMD_ADJ_INIT_TIME;
 		break;
+	case ICE_PTP_NOP:
+		return 0;
 	}
 
 	/* Read, modify, write */
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 3b68cb91bd819..096685237ca61 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -9,7 +9,8 @@ enum ice_ptp_tmr_cmd {
 	INIT_INCVAL,
 	ADJ_TIME,
 	ADJ_TIME_AT_TIME,
-	READ_TIME
+	READ_TIME,
+	ICE_PTP_NOP,
 };
 
 enum ice_ptp_serdes {
-- 
GitLab


From 9540329452b737340960b4273600e61a6a236a78 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Thu, 24 Aug 2023 14:11:50 +0800
Subject: [PATCH 1671/1806] net: fec: add statistics for XDP_TX

The FEC driver supports the statistics for XDP actions except for
XDP_TX before, because the XDP_TX was not supported when adding
the statistics for XDP. Now the FEC driver has supported XDP_TX
since commit f601899e4321 ("net: fec: add XDP_TX feature support").
So it's reasonable and necessary to add statistics for XDP_TX.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8909899e9a31f..77c8e9cfb4456 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1590,9 +1590,12 @@ fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog,
 		break;
 
 	case XDP_TX:
+		rxq->stats[RX_XDP_TX]++;
 		err = fec_enet_xdp_tx_xmit(fep, cpu, xdp, sync);
-		if (unlikely(err))
+		if (unlikely(err)) {
+			rxq->stats[RX_XDP_TX_ERRORS]++;
 			goto xdp_err;
+		}
 
 		ret = FEC_ENET_XDP_TX;
 		break;
-- 
GitLab


From 49fa4b0d06705a24a81bb8be6eb175059b77f0a7 Mon Sep 17 00:00:00 2001
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: Thu, 24 Aug 2023 08:33:01 +0530
Subject: [PATCH 1672/1806] octeontx2-pf: fix page_pool creation fail for rings
 > 32k

octeontx2 driver calls page_pool_create() during driver probe()
and fails if queue size > 32k. Page pool infra uses these buffers
as shock absorbers for burst traffic. These pages are pinned down
over time as working sets varies, due to the recycling nature
of page pool, given page pool (currently) don't have a shrinker
mechanism, the pages remain pinned down in ptr_ring.
Instead of clamping page_pool size to 32k at
most, limit it even more to 2k to avoid wasting memory.

This have been tested on octeontx2 CN10KA hardware.
TCP and UDP tests using iperf shows no performance regressions.

Fixes: b2e3406a38f0 ("octeontx2-pf: Add support for page pool")
Suggested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 2 +-
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h   | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 77c8f650f7ac1..3e1c70c746227 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1432,7 +1432,7 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
 	}
 
 	pp_params.flags = PP_FLAG_PAGE_FRAG | PP_FLAG_DMA_MAP;
-	pp_params.pool_size = numptrs;
+	pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs);
 	pp_params.nid = NUMA_NO_NODE;
 	pp_params.dev = pfvf->dev;
 	pp_params.dma_dir = DMA_FROM_DEVICE;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index b5d689eeff80b..9e3bfbe5c4809 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -23,6 +23,8 @@
 #define	OTX2_ETH_HLEN		(VLAN_ETH_HLEN + VLAN_HLEN)
 #define	OTX2_MIN_MTU		60
 
+#define OTX2_PAGE_POOL_SZ	2048
+
 #define OTX2_MAX_GSO_SEGS	255
 #define OTX2_MAX_FRAGS_IN_SQE	9
 
-- 
GitLab


From 786c96e92fb9e854cb8b0cb7399bb2fb28e15c4b Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Thu, 24 Aug 2023 14:43:36 +0800
Subject: [PATCH 1673/1806] net: arcnet: Do not call kfree_skb() under
 local_irq_disable()

It is not allowed to call kfree_skb() from hardware interrupt
context or with hardware interrupts being disabled.
So replace kfree_skb() with dev_kfree_skb_irq() under
local_irq_disable(). Compile tested only.

Fixes: 05fcd31cc472 ("arcnet: add err_skb package for package status feedback")
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/arcnet/arcnet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c
index 99265667538c3..d9e052c49ba1a 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -464,7 +464,7 @@ static void arcnet_reply_tasklet(struct tasklet_struct *t)
 
 	ret = sock_queue_err_skb(sk, ackskb);
 	if (ret)
-		kfree_skb(ackskb);
+		dev_kfree_skb_irq(ackskb);
 
 	local_irq_enable();
 };
-- 
GitLab


From b38460bc463c54e0c15ff3b37e81f7e2059bb9bb Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Wed, 23 Aug 2023 15:21:43 +0200
Subject: [PATCH 1674/1806] kunit: Fix checksum tests on big endian CPUs

On powerpc64le checksum kunit tests work:

[    2.011457][    T1]     KTAP version 1
[    2.011662][    T1]     # Subtest: checksum
[    2.011848][    T1]     1..3
[    2.034710][    T1]     ok 1 test_csum_fixed_random_inputs
[    2.079325][    T1]     ok 2 test_csum_all_carry_inputs
[    2.127102][    T1]     ok 3 test_csum_no_carry_inputs
[    2.127202][    T1] # checksum: pass:3 fail:0 skip:0 total:3
[    2.127533][    T1] # Totals: pass:3 fail:0 skip:0 total:3
[    2.127956][    T1] ok 1 checksum

But on powerpc64 and powerpc32 they fail:

[    1.859890][    T1]     KTAP version 1
[    1.860041][    T1]     # Subtest: checksum
[    1.860201][    T1]     1..3
[    1.861927][   T58]     # test_csum_fixed_random_inputs: ASSERTION FAILED at lib/checksum_kunit.c:243
[    1.861927][   T58]     Expected result == expec, but
[    1.861927][   T58]         result == 54991 (0xd6cf)
[    1.861927][   T58]         expec == 33316 (0x8224)
[    1.863742][    T1]     not ok 1 test_csum_fixed_random_inputs
[    1.864520][   T60]     # test_csum_all_carry_inputs: ASSERTION FAILED at lib/checksum_kunit.c:267
[    1.864520][   T60]     Expected result == expec, but
[    1.864520][   T60]         result == 255 (0xff)
[    1.864520][   T60]         expec == 65280 (0xff00)
[    1.868820][    T1]     not ok 2 test_csum_all_carry_inputs
[    1.869977][   T62]     # test_csum_no_carry_inputs: ASSERTION FAILED at lib/checksum_kunit.c:306
[    1.869977][   T62]     Expected result == expec, but
[    1.869977][   T62]         result == 64515 (0xfc03)
[    1.869977][   T62]         expec == 0 (0x0)
[    1.872060][    T1]     not ok 3 test_csum_no_carry_inputs
[    1.872102][    T1] # checksum: pass:0 fail:3 skip:0 total:3
[    1.872458][    T1] # Totals: pass:0 fail:3 skip:0 total:3
[    1.872791][    T1] not ok 3 checksum

This is because all expected values were calculated for X86 which
is little endian. On big endian systems all precalculated 16 bits
halves must be byte swapped.

And this is confirmed by a huge amount of sparse errors when building
with C=2

So fix all sparse errors and it will naturally work on all endianness.

Fixes: 688eb8191b47 ("x86/csum: Improve performance of `csum_partial`")
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/checksum_kunit.c | 54 +++++++++++++++++++++++++++++++-------------
 1 file changed, 38 insertions(+), 16 deletions(-)

diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c
index ace3c4799fe15..0eed92b77ba37 100644
--- a/lib/checksum_kunit.c
+++ b/lib/checksum_kunit.c
@@ -10,7 +10,8 @@
 #define MAX_ALIGN 64
 #define TEST_BUFLEN (MAX_LEN + MAX_ALIGN)
 
-static const __wsum random_init_sum = 0x2847aab;
+/* Values for a little endian CPU. Byte swap each half on big endian CPU. */
+static const u32 random_init_sum = 0x2847aab;
 static const u8 random_buf[] = {
 	0xac, 0xd7, 0x76, 0x69, 0x6e, 0xf2, 0x93, 0x2c, 0x1f, 0xe0, 0xde, 0x86,
 	0x8f, 0x54, 0x33, 0x90, 0x95, 0xbf, 0xff, 0xb9, 0xea, 0x62, 0x6e, 0xb5,
@@ -56,7 +57,9 @@ static const u8 random_buf[] = {
 	0xe1, 0xdf, 0x4b, 0xe1, 0x81, 0xe2, 0x17, 0x02, 0x7b, 0x58, 0x8b, 0x92,
 	0x1a, 0xac, 0x46, 0xdd, 0x2e, 0xce, 0x40, 0x09
 };
-static const __sum16 expected_results[] = {
+
+/* Values for a little endian CPU. Byte swap on big endian CPU. */
+static const u16 expected_results[] = {
 	0x82d0, 0x8224, 0xab23, 0xaaad, 0x41ad, 0x413f, 0x4f3e, 0x4eab, 0x22ab,
 	0x228c, 0x428b, 0x41ad, 0xbbac, 0xbb1d, 0x671d, 0x66ea, 0xd6e9, 0xd654,
 	0x1754, 0x1655, 0x5d54, 0x5c6a, 0xfa69, 0xf9fb, 0x44fb, 0x4428, 0xf527,
@@ -115,7 +118,9 @@ static const __sum16 expected_results[] = {
 	0x1d47, 0x3c46, 0x3bc5, 0x59c4, 0x59ad, 0x57ad, 0x5732, 0xff31, 0xfea6,
 	0x6ca6, 0x6c8c, 0xc08b, 0xc045, 0xe344, 0xe316, 0x1516, 0x14d6,
 };
-static const __wsum init_sums_no_overflow[] = {
+
+/* Values for a little endian CPU. Byte swap each half on big endian CPU. */
+static const u32 init_sums_no_overflow[] = {
 	0xffffffff, 0xfffffffb, 0xfffffbfb, 0xfffffbf7, 0xfffff7f7, 0xfffff7f3,
 	0xfffff3f3, 0xfffff3ef, 0xffffefef, 0xffffefeb, 0xffffebeb, 0xffffebe7,
 	0xffffe7e7, 0xffffe7e3, 0xffffe3e3, 0xffffe3df, 0xffffdfdf, 0xffffdfdb,
@@ -208,7 +213,21 @@ static u8 tmp_buf[TEST_BUFLEN];
 
 #define full_csum(buff, len, sum) csum_fold(csum_partial(buff, len, sum))
 
-#define CHECK_EQ(lhs, rhs) KUNIT_ASSERT_EQ(test, lhs, rhs)
+#define CHECK_EQ(lhs, rhs) KUNIT_ASSERT_EQ(test, (__force u64)lhs, (__force u64)rhs)
+
+static __sum16 to_sum16(u16 x)
+{
+	return (__force __sum16)le16_to_cpu((__force __le16)x);
+}
+
+/* This function swaps the bytes inside each half of a __wsum */
+static __wsum to_wsum(u32 x)
+{
+	u16 hi = le16_to_cpu((__force __le16)(x >> 16));
+	u16 lo = le16_to_cpu((__force __le16)x);
+
+	return (__force __wsum)((hi << 16) | lo);
+}
 
 static void assert_setup_correct(struct kunit *test)
 {
@@ -226,7 +245,8 @@ static void assert_setup_correct(struct kunit *test)
 static void test_csum_fixed_random_inputs(struct kunit *test)
 {
 	int len, align;
-	__wsum result, expec, sum;
+	__wsum sum;
+	__sum16 result, expec;
 
 	assert_setup_correct(test);
 	for (align = 0; align < TEST_BUFLEN; ++align) {
@@ -237,9 +257,9 @@ static void test_csum_fixed_random_inputs(struct kunit *test)
 			/*
 			 * Test the precomputed random input.
 			 */
-			sum = random_init_sum;
+			sum = to_wsum(random_init_sum);
 			result = full_csum(&tmp_buf[align], len, sum);
-			expec = expected_results[len];
+			expec = to_sum16(expected_results[len]);
 			CHECK_EQ(result, expec);
 		}
 	}
@@ -251,7 +271,8 @@ static void test_csum_fixed_random_inputs(struct kunit *test)
 static void test_csum_all_carry_inputs(struct kunit *test)
 {
 	int len, align;
-	__wsum result, expec, sum;
+	__wsum sum;
+	__sum16 result, expec;
 
 	assert_setup_correct(test);
 	memset(tmp_buf, 0xff, TEST_BUFLEN);
@@ -261,9 +282,9 @@ static void test_csum_all_carry_inputs(struct kunit *test)
 			/*
 			 * All carries from input and initial sum.
 			 */
-			sum = 0xffffffff;
+			sum = to_wsum(0xffffffff);
 			result = full_csum(&tmp_buf[align], len, sum);
-			expec = (len & 1) ? 0xff00 : 0;
+			expec = to_sum16((len & 1) ? 0xff00 : 0);
 			CHECK_EQ(result, expec);
 
 			/*
@@ -272,11 +293,11 @@ static void test_csum_all_carry_inputs(struct kunit *test)
 			sum = 0;
 			result = full_csum(&tmp_buf[align], len, sum);
 			if (len & 1)
-				expec = 0xff00;
+				expec = to_sum16(0xff00);
 			else if (len)
 				expec = 0;
 			else
-				expec = 0xffff;
+				expec = to_sum16(0xffff);
 			CHECK_EQ(result, expec);
 		}
 	}
@@ -290,7 +311,8 @@ static void test_csum_all_carry_inputs(struct kunit *test)
 static void test_csum_no_carry_inputs(struct kunit *test)
 {
 	int len, align;
-	__wsum result, expec, sum;
+	__wsum sum;
+	__sum16 result, expec;
 
 	assert_setup_correct(test);
 	memset(tmp_buf, 0x4, TEST_BUFLEN);
@@ -300,7 +322,7 @@ static void test_csum_no_carry_inputs(struct kunit *test)
 			/*
 			 * Expect no carries.
 			 */
-			sum = init_sums_no_overflow[len];
+			sum = to_wsum(init_sums_no_overflow[len]);
 			result = full_csum(&tmp_buf[align], len, sum);
 			expec = 0;
 			CHECK_EQ(result, expec);
@@ -308,9 +330,9 @@ static void test_csum_no_carry_inputs(struct kunit *test)
 			/*
 			 * Expect one carry.
 			 */
-			sum = init_sums_no_overflow[len] + 1;
+			sum = to_wsum(init_sums_no_overflow[len] + 1);
 			result = full_csum(&tmp_buf[align], len, sum);
-			expec = len ? 0xfffe : 0xffff;
+			expec = to_sum16(len ? 0xfffe : 0xffff);
 			CHECK_EQ(result, expec);
 		}
 	}
-- 
GitLab


From 146c7c330507c0384bf29d567186632bfe975927 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@nvidia.com>
Date: Thu, 24 Aug 2023 15:43:08 +0200
Subject: [PATCH 1675/1806] mlxsw: i2c: Fix chunk size setting in output
 mailbox buffer

The driver reads commands output from the output mailbox. If the size
of the output mailbox is not a multiple of the transaction /
block size, then the driver will not issue enough read transactions
to read the entire output, which can result in driver initialization
errors.

Fix by determining the number of transactions using DIV_ROUND_UP().

Fixes: 3029a693beda ("mlxsw: i2c: Allow flexible setting of I2C transactions size")
Signed-off-by: Vadim Pasternak <vadimp@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
index 41298835a11e1..47af7ef7e4eee 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
@@ -444,7 +444,7 @@ mlxsw_i2c_cmd(struct device *dev, u16 opcode, u32 in_mod, size_t in_mbox_size,
 	} else {
 		/* No input mailbox is case of initialization query command. */
 		reg_size = MLXSW_I2C_MAX_DATA_SIZE;
-		num = reg_size / mlxsw_i2c->block_size;
+		num = DIV_ROUND_UP(reg_size, mlxsw_i2c->block_size);
 
 		if (mutex_lock_interruptible(&mlxsw_i2c->cmd.lock) < 0) {
 			dev_err(&client->dev, "Could not acquire lock");
-- 
GitLab


From d7248f1cc835bd80e936dc5b2d94b149bdd0077d Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@nvidia.com>
Date: Thu, 24 Aug 2023 15:43:09 +0200
Subject: [PATCH 1676/1806] mlxsw: i2c: Limit single transaction buffer size

Maximum size of buffer is obtained from underlying I2C adapter and in
case adapter allows I2C transaction buffer size greater than 100 bytes,
transaction will fail due to firmware limitation.

As a result driver will fail initialization.

Limit the maximum size of transaction buffer by 100 bytes to fit to
firmware.

Remove unnecessary calculation:
max_t(u16, MLXSW_I2C_BLK_DEF, quirk_size).
This condition can not happened.

Fixes: 3029a693beda ("mlxsw: i2c: Allow flexible setting of I2C transactions size")
Signed-off-by: Vadim Pasternak <vadimp@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/i2c.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
index 47af7ef7e4eee..d23f293e285cb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
@@ -48,6 +48,7 @@
 #define MLXSW_I2C_MBOX_SIZE_BITS	12
 #define MLXSW_I2C_ADDR_BUF_SIZE		4
 #define MLXSW_I2C_BLK_DEF		32
+#define MLXSW_I2C_BLK_MAX		100
 #define MLXSW_I2C_RETRY			5
 #define MLXSW_I2C_TIMEOUT_MSECS		5000
 #define MLXSW_I2C_MAX_DATA_SIZE		256
@@ -653,7 +654,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client)
 			return -EOPNOTSUPP;
 		}
 
-		mlxsw_i2c->block_size = max_t(u16, MLXSW_I2C_BLK_DEF,
+		mlxsw_i2c->block_size = min_t(u16, MLXSW_I2C_BLK_MAX,
 					      min_t(u16, quirks->max_read_len,
 						    quirks->max_write_len));
 	} else {
-- 
GitLab


From 3fc134a07438055fc93ce1bbacf2702ddd09500c Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@nvidia.com>
Date: Thu, 24 Aug 2023 15:43:10 +0200
Subject: [PATCH 1677/1806] mlxsw: core_hwmon: Adjust module label names based
 on MTCAP sensor counter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Transceiver module temperature sensors are indexed after ASIC and
platform sensors. The current label printing method does not take this
into account and simply prints the index of the transceiver module
sensor.

On new systems that have platform sensors this results in incorrect
(shifted) transceiver module labels being printed:

$ sensors
[...]
front panel 002:  +37.0°C  (crit = +70.0°C, emerg = +75.0°C)
front panel 003:  +47.0°C  (crit = +70.0°C, emerg = +75.0°C)
[...]

Fix by taking the sensor count into account. After the fix:

$ sensors
[...]
front panel 001:  +37.0°C  (crit = +70.0°C, emerg = +75.0°C)
front panel 002:  +47.0°C  (crit = +70.0°C, emerg = +75.0°C)
[...]

Fixes: a53779de6a0e ("mlxsw: core: Add QSFP module temperature label attribute to hwmon")
Signed-off-by: Vadim Pasternak <vadimp@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index 70735068cf292..0fd290d776ffe 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -405,7 +405,8 @@ mlxsw_hwmon_module_temp_label_show(struct device *dev,
 			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
 
 	return sprintf(buf, "front panel %03u\n",
-		       mlxsw_hwmon_attr->type_index);
+		       mlxsw_hwmon_attr->type_index + 1 -
+		       mlxsw_hwmon_attr->mlxsw_hwmon_dev->sensor_count);
 }
 
 static ssize_t
-- 
GitLab


From 5d7cf67f72ae34d38e090bdfa673da4aefe4048e Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 8 Aug 2023 20:44:48 -0400
Subject: [PATCH 1678/1806] Fix nomenclature for USB and PCI wireless devices

A mouse that uses a USB connection is called a "USB mouse" device (or
"USB mouse" for short), not a "mouse USB" device.  By analogy, a WiFi
adapter that connects to the host computer via USB is a "USB wireless"
device, not a "wireless USB" device.  (The latter term more properly
refers to a defunct Wireless USB specification, which described a
technology for sending USB protocol messages over an ultra wideband
radio link.)

Similarly for a WiFi adapter card that plugs into a PCIe slot: It is a
"PCIe wireless" device, not a "wireless PCIe" device.

Rephrase the text in the kernel source where the word ordering is
wrong.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/57da7c80-0e48-41b5-8427-884a02648f55@rowland.harvard.edu
---
 drivers/net/wireless/ath/ath10k/pci.c         |  2 +-
 drivers/net/wireless/ath/ath10k/usb.c         |  2 +-
 drivers/net/wireless/ath/ath11k/pci.c         |  2 +-
 drivers/net/wireless/ath/ath12k/pci.c         |  2 +-
 drivers/net/wireless/atmel/at76c50x-usb.c     |  8 ++--
 .../wireless/intersil/orinoco/orinoco_usb.c   | 12 ++---
 drivers/net/wireless/legacy/rndis_wlan.c      |  2 +-
 .../net/wireless/mediatek/mt76/mt7603/Kconfig |  2 +-
 .../net/wireless/mediatek/mt76/mt7615/Kconfig |  2 +-
 .../net/wireless/mediatek/mt76/mt76x0/Kconfig |  4 +-
 .../net/wireless/mediatek/mt76/mt76x2/Kconfig |  4 +-
 .../net/wireless/mediatek/mt76/mt7915/Kconfig |  2 +-
 .../net/wireless/mediatek/mt76/mt7996/Kconfig |  2 +-
 drivers/net/wireless/mediatek/mt7601u/Kconfig |  2 +-
 drivers/net/wireless/purelifi/plfxlc/Kconfig  |  2 +-
 drivers/net/wireless/ralink/rt2x00/Kconfig    |  2 +-
 drivers/net/wireless/realtek/rtw88/pci.c      |  2 +-
 drivers/net/wireless/realtek/rtw88/usb.c      |  2 +-
 drivers/net/wireless/realtek/rtw89/pci.c      |  2 +-
 drivers/net/wireless/zydas/zd1201.c           |  6 +--
 drivers/platform/x86/eeepc-laptop.c           |  2 +-
 drivers/staging/wlan-ng/prism2usb.c           | 48 +++++++++----------
 22 files changed, 57 insertions(+), 57 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index a7f44f6335fb8..3ef414b613bf3 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -3816,7 +3816,7 @@ static void __exit ath10k_pci_exit(void)
 module_exit(ath10k_pci_exit);
 
 MODULE_AUTHOR("Qualcomm Atheros");
-MODULE_DESCRIPTION("Driver support for Qualcomm Atheros 802.11ac WLAN PCIe/AHB devices");
+MODULE_DESCRIPTION("Driver support for Qualcomm Atheros PCIe/AHB 802.11ac WLAN devices");
 MODULE_LICENSE("Dual BSD/GPL");
 
 /* QCA988x 2.0 firmware files */
diff --git a/drivers/net/wireless/ath/ath10k/usb.c b/drivers/net/wireless/ath/ath10k/usb.c
index b0067af685b16..3c482baacec10 100644
--- a/drivers/net/wireless/ath/ath10k/usb.c
+++ b/drivers/net/wireless/ath/ath10k/usb.c
@@ -1126,5 +1126,5 @@ static struct usb_driver ath10k_usb_driver = {
 module_usb_driver(ath10k_usb_driver);
 
 MODULE_AUTHOR("Atheros Communications, Inc.");
-MODULE_DESCRIPTION("Driver support for Qualcomm Atheros 802.11ac WLAN USB devices");
+MODULE_DESCRIPTION("Driver support for Qualcomm Atheros USB 802.11ac WLAN devices");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index 5fd08ffc2a9f6..9573bd959caca 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -1036,7 +1036,7 @@ static void ath11k_pci_exit(void)
 
 module_exit(ath11k_pci_exit);
 
-MODULE_DESCRIPTION("Driver support for Qualcomm Technologies 802.11ax WLAN PCIe devices");
+MODULE_DESCRIPTION("Driver support for Qualcomm Technologies PCIe 802.11ax WLAN devices");
 MODULE_LICENSE("Dual BSD/GPL");
 
 /* firmware files */
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 5990a55801f0a..bd689efa7daaf 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -1409,5 +1409,5 @@ static void ath12k_pci_exit(void)
 
 module_exit(ath12k_pci_exit);
 
-MODULE_DESCRIPTION("Driver support for Qualcomm Technologies 802.11be WLAN PCIe devices");
+MODULE_DESCRIPTION("Driver support for Qualcomm Technologies PCIe 802.11be WLAN devices");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/atmel/at76c50x-usb.c b/drivers/net/wireless/atmel/at76c50x-usb.c
index 009bca34ece30..447b51cff8f96 100644
--- a/drivers/net/wireless/atmel/at76c50x-usb.c
+++ b/drivers/net/wireless/atmel/at76c50x-usb.c
@@ -10,7 +10,7 @@
  * Copyright (c) 2007 Kalle Valo <kalle.valo@iki.fi>
  * Copyright (c) 2010 Sebastian Smolorz <sesmo@gmx.net>
  *
- * This file is part of the Berlios driver for WLAN USB devices based on the
+ * This file is part of the Berlios driver for USB WLAN devices based on the
  * Atmel AT76C503A/505/505A.
  *
  * Some iw_handler code was taken from airo.c, (C) 1999 Benjamin Reed
@@ -143,7 +143,7 @@ static const struct usb_device_id dev_table[] = {
 	{ USB_DEVICE(0x0cde, 0x0001), USB_DEVICE_DATA(BOARD_503_ISL3861) },
 	/* Dynalink/Askey WLL013 (intersil) */
 	{ USB_DEVICE(0x069a, 0x0320), USB_DEVICE_DATA(BOARD_503_ISL3861) },
-	/* EZ connect 11Mpbs Wireless USB Adapter SMC2662W v1 */
+	/* EZ connect 11Mpbs USB Wireless Adapter SMC2662W v1 */
 	{ USB_DEVICE(0x0d5c, 0xa001), USB_DEVICE_DATA(BOARD_503_ISL3861) },
 	/* BenQ AWL300 */
 	{ USB_DEVICE(0x04a5, 0x9000), USB_DEVICE_DATA(BOARD_503_ISL3861) },
@@ -195,7 +195,7 @@ static const struct usb_device_id dev_table[] = {
 	{ USB_DEVICE(0x04a5, 0x9001), USB_DEVICE_DATA(BOARD_503) },
 	/* 3Com 3CRSHEW696 */
 	{ USB_DEVICE(0x0506, 0x0a01), USB_DEVICE_DATA(BOARD_503) },
-	/* Siemens Santis ADSL WLAN USB adapter WLL 013 */
+	/* Siemens Santis ADSL USB WLAN adapter WLL 013 */
 	{ USB_DEVICE(0x0681, 0x001b), USB_DEVICE_DATA(BOARD_503) },
 	/* Belkin F5D6050, version 2 */
 	{ USB_DEVICE(0x050d, 0x0050), USB_DEVICE_DATA(BOARD_503) },
@@ -238,7 +238,7 @@ static const struct usb_device_id dev_table[] = {
 	{ USB_DEVICE(0x1915, 0x2233), USB_DEVICE_DATA(BOARD_505_2958) },
 	/* Xterasys XN-2122B, IBlitzz BWU613B/BWU613SB */
 	{ USB_DEVICE(0x12fd, 0x1001), USB_DEVICE_DATA(BOARD_505_2958) },
-	/* Corega WLAN USB Stick 11 */
+	/* Corega USB WLAN Stick 11 */
 	{ USB_DEVICE(0x07aa, 0x7613), USB_DEVICE_DATA(BOARD_505_2958) },
 	/* Microstar MSI Box MS6978 */
 	{ USB_DEVICE(0x0db0, 0x1020), USB_DEVICE_DATA(BOARD_505_2958) },
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
index dd31929261ab9..866e0230df251 100644
--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
@@ -129,18 +129,18 @@ MODULE_FIRMWARE("orinoco_ezusb_fw");
 
 #define USB_AVAYA8_VENDOR_ID     0x0D98
 #define USB_AVAYAE_VENDOR_ID     0x0D9E
-#define USB_AVAYA_WIRELESS_ID    0x0300 /* Avaya Wireless USB Card */
+#define USB_AVAYA_WIRELESS_ID    0x0300 /* Avaya USB Wireless Card */
 
 #define USB_AGERE_VENDOR_ID      0x0D4E /* Agere Systems */
-#define USB_AGERE_MODEL0801_ID   0x1000 /* Wireless USB Card Model 0801 */
-#define USB_AGERE_MODEL0802_ID   0x1001 /* Wireless USB Card Model 0802 */
-#define USB_AGERE_REBRANDED_ID   0x047A /* WLAN USB Card */
+#define USB_AGERE_MODEL0801_ID   0x1000 /* USB Wireless Card Model 0801 */
+#define USB_AGERE_MODEL0802_ID   0x1001 /* USB Wireless Card Model 0802 */
+#define USB_AGERE_REBRANDED_ID   0x047A /* USB WLAN Card */
 
 #define USB_ELSA_VENDOR_ID       0x05CC
 #define USB_ELSA_AIRLANCER_ID    0x3100 /* ELSA AirLancer USB-11 */
 
 #define USB_LEGEND_VENDOR_ID     0x0E7C
-#define USB_LEGEND_JOYNET_ID     0x0300 /* Joynet WLAN USB Card */
+#define USB_LEGEND_JOYNET_ID     0x0300 /* Joynet USB WLAN Card */
 
 #define USB_SAMSUNG_VENDOR_ID    0x04E8
 #define USB_SAMSUNG_SEW2001U1_ID 0x5002 /* Samsung SEW-2001u Card */
@@ -154,7 +154,7 @@ MODULE_FIRMWARE("orinoco_ezusb_fw");
 #define USB_FUJITSU_E1100_ID     0x1002 /* connect2AIR WLAN E-1100 USB */
 
 #define USB_2WIRE_VENDOR_ID      0x1630
-#define USB_2WIRE_WIRELESS_ID    0xff81 /* 2Wire Wireless USB adapter */
+#define USB_2WIRE_WIRELESS_ID    0xff81 /* 2Wire USB Wireless adapter */
 
 
 #define EZUSB_REQUEST_FW_TRANS		0xA0
diff --git a/drivers/net/wireless/legacy/rndis_wlan.c b/drivers/net/wireless/legacy/rndis_wlan.c
index 712038d46bdb3..e7fea7ded6d5c 100644
--- a/drivers/net/wireless/legacy/rndis_wlan.c
+++ b/drivers/net/wireless/legacy/rndis_wlan.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Driver for RNDIS based wireless USB devices.
+ * Driver for RNDIS based USB wireless devices.
  *
  * Copyright (C) 2007 by Bjorge Dijkstra <bjd@jooz.net>
  * Copyright (C) 2008-2009 by Jussi Kivilinna <jussi.kivilinna@iki.fi>
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/Kconfig b/drivers/net/wireless/mediatek/mt76/mt7603/Kconfig
index 6a0080f1d91c7..dd16acfd9735d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/Kconfig
@@ -5,7 +5,7 @@ config MT7603E
 	depends on MAC80211
 	depends on PCI
 	help
-	  This adds support for MT7603E wireless PCIe devices and the WLAN core
+	  This adds support for MT7603E PCIe wireless devices and the WLAN core
 	  on MT7628/MT7688 SoC devices. This family supports IEEE 802.11n 2x2
 	  to 300Mbps PHY rate
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/Kconfig b/drivers/net/wireless/mediatek/mt76/mt7615/Kconfig
index 30fba36ff46bb..1ab1439143f41 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/Kconfig
@@ -11,7 +11,7 @@ config MT7615E
 	depends on MAC80211
 	depends on PCI
 	help
-	  This adds support for MT7615-based wireless PCIe devices,
+	  This adds support for MT7615-based PCIe wireless devices,
 	  which support concurrent dual-band operation at both 5GHz
 	  and 2.4GHz, IEEE 802.11ac 4x4:4SS 1733Mbps PHY rate, wave2
 	  MU-MIMO up to 4 users/group and 160MHz channels.
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/Kconfig b/drivers/net/wireless/mediatek/mt76/mt76x0/Kconfig
index 7c88ed8b8f1e9..3ed888782a709 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/Kconfig
@@ -10,7 +10,7 @@ config MT76x0U
 	depends on MAC80211
 	depends on USB
 	help
-	  This adds support for MT7610U-based wireless USB 2.0 dongles,
+	  This adds support for MT7610U-based USB 2.0 wireless dongles,
 	  which comply with IEEE 802.11ac standards and support 1x1
 	  433Mbps PHY rate.
 
@@ -22,7 +22,7 @@ config MT76x0E
 	depends on MAC80211
 	depends on PCI
 	help
-	  This adds support for MT7610/MT7630-based wireless PCIe devices,
+	  This adds support for MT7610/MT7630-based PCIe wireless devices,
 	  which comply with IEEE 802.11ac standards and support 1x1
 	  433Mbps PHY rate.
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/Kconfig b/drivers/net/wireless/mediatek/mt76/mt76x2/Kconfig
index 5fd4973e32dfb..482a32b70ddfe 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/Kconfig
@@ -9,7 +9,7 @@ config MT76x2E
 	depends on MAC80211
 	depends on PCI
 	help
-	  This adds support for MT7612/MT7602/MT7662-based wireless PCIe
+	  This adds support for MT7612/MT7602/MT7662-based PCIe wireless
 	  devices, which comply with IEEE 802.11ac standards and support
 	  2SS to 866Mbit/s PHY rate.
 
@@ -22,7 +22,7 @@ config MT76x2U
 	depends on MAC80211
 	depends on USB
 	help
-	  This adds support for MT7612U-based wireless USB 3.0 dongles,
+	  This adds support for MT7612U-based USB 3.0 wireless dongles,
 	  which comply with IEEE 802.11ac standards and support 2SS to
 	  866Mbit/s PHY rate.
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig b/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig
index 896ec38c23d9b..193112c49bd19 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig
@@ -7,7 +7,7 @@ config MT7915E
 	depends on PCI
 	select RELAY
 	help
-	  This adds support for MT7915-based wireless PCIe devices,
+	  This adds support for MT7915-based PCIe wireless devices,
 	  which support concurrent dual-band operation at both 5GHz
 	  and 2.4GHz IEEE 802.11ax 4x4:4SS 1024-QAM, 160MHz channels,
 	  OFDMA, spatial reuse and dual carrier modulation.
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig b/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig
index 1afa2f662e473..bb44d4a5e2dc9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig
@@ -7,7 +7,7 @@ config MT7996E
 	depends on MAC80211
 	depends on PCI
 	help
-	  This adds support for MT7996-based wireless PCIe devices,
+	  This adds support for MT7996-based PCIe wireless devices,
 	  which support concurrent tri-band operation at 6GHz, 5GHz,
 	  and 2.4GHz IEEE 802.11be 4x4:4SS 4096-QAM, 320MHz channels.
 
diff --git a/drivers/net/wireless/mediatek/mt7601u/Kconfig b/drivers/net/wireless/mediatek/mt7601u/Kconfig
index 4a8b962806707..4880fc053d9d3 100644
--- a/drivers/net/wireless/mediatek/mt7601u/Kconfig
+++ b/drivers/net/wireless/mediatek/mt7601u/Kconfig
@@ -4,4 +4,4 @@ config MT7601U
 	depends on MAC80211
 	depends on USB
 	help
-	  This adds support for MT7601U-based wireless USB dongles.
+	  This adds support for MT7601U-based USB wireless dongles.
diff --git a/drivers/net/wireless/purelifi/plfxlc/Kconfig b/drivers/net/wireless/purelifi/plfxlc/Kconfig
index 4e0be27a5e0eb..dd5fca480d7ef 100644
--- a/drivers/net/wireless/purelifi/plfxlc/Kconfig
+++ b/drivers/net/wireless/purelifi/plfxlc/Kconfig
@@ -3,7 +3,7 @@ config PLFXLC
 	tristate "pureLiFi X, XL, XC device support"
 	depends on CFG80211 && MAC80211 && USB
 	help
-	   This option adds support for pureLiFi LiFi wireless USB
+	   This option adds support for pureLiFi LiFi USB wireless
 	   adapters. The pureLiFi X, XL, XC USB devices are based on
 	   802.11 OFDM PHY but uses light as the transmission medium.
 	   The driver supports common 802.11 encryption/authentication
diff --git a/drivers/net/wireless/ralink/rt2x00/Kconfig b/drivers/net/wireless/ralink/rt2x00/Kconfig
index dcccc290a7f52..d1fd66d44a7ed 100644
--- a/drivers/net/wireless/ralink/rt2x00/Kconfig
+++ b/drivers/net/wireless/ralink/rt2x00/Kconfig
@@ -170,7 +170,7 @@ config RT2800USB_RT35XX
 config RT2800USB_RT3573
 	bool "rt2800usb - Include support for rt3573 devices (EXPERIMENTAL)"
 	help
-	  This enables support for RT3573 chipset based wireless USB devices
+	  This enables support for RT3573 chipset based USB wireless devices
 	  in the rt2800usb driver.
 
 config RT2800USB_RT53XX
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index 44a8fff34cddf..2bfc0e822b8d0 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -1828,5 +1828,5 @@ void rtw_pci_shutdown(struct pci_dev *pdev)
 EXPORT_SYMBOL(rtw_pci_shutdown);
 
 MODULE_AUTHOR("Realtek Corporation");
-MODULE_DESCRIPTION("Realtek 802.11ac wireless PCI driver");
+MODULE_DESCRIPTION("Realtek PCI 802.11ac wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 91ed6d10ba8ac..95b9d933158f2 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -909,5 +909,5 @@ void rtw_usb_disconnect(struct usb_interface *intf)
 EXPORT_SYMBOL(rtw_usb_disconnect);
 
 MODULE_AUTHOR("Realtek Corporation");
-MODULE_DESCRIPTION("Realtek 802.11ac wireless USB driver");
+MODULE_DESCRIPTION("Realtek USB 802.11ac wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c
index 9402f1a0caea8..3a4bfc44142b6 100644
--- a/drivers/net/wireless/realtek/rtw89/pci.c
+++ b/drivers/net/wireless/realtek/rtw89/pci.c
@@ -3939,5 +3939,5 @@ void rtw89_pci_remove(struct pci_dev *pdev)
 EXPORT_SYMBOL(rtw89_pci_remove);
 
 MODULE_AUTHOR("Realtek Corporation");
-MODULE_DESCRIPTION("Realtek 802.11ax wireless PCI driver");
+MODULE_DESCRIPTION("Realtek PCI 802.11ax wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/zydas/zd1201.c b/drivers/net/wireless/zydas/zd1201.c
index a85fe7e4c6d47..2814df1ecc78f 100644
--- a/drivers/net/wireless/zydas/zd1201.c
+++ b/drivers/net/wireless/zydas/zd1201.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- *	Driver for ZyDAS zd1201 based wireless USB devices.
+ *	Driver for ZyDAS zd1201 based USB wireless devices.
  *
  *	Copyright (c) 2004, 2005 Jeroen Vreeken (pe1rxq@amsat.org)
  *
@@ -23,8 +23,8 @@
 #include "zd1201.h"
 
 static const struct usb_device_id zd1201_table[] = {
-	{USB_DEVICE(0x0586, 0x3400)}, /* Peabird Wireless USB Adapter */
-	{USB_DEVICE(0x0ace, 0x1201)}, /* ZyDAS ZD1201 Wireless USB Adapter */
+	{USB_DEVICE(0x0586, 0x3400)}, /* Peabird USB Wireless Adapter */
+	{USB_DEVICE(0x0ace, 0x1201)}, /* ZyDAS ZD1201 USB Wireless Adapter */
 	{USB_DEVICE(0x050d, 0x6051)}, /* Belkin F5D6051 usb  adapter */
 	{USB_DEVICE(0x0db0, 0x6823)}, /* MSI UB11B usb  adapter */
 	{USB_DEVICE(0x1044, 0x8004)}, /* Gigabyte GN-WLBZ101 */
diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index 62b71e8e3567a..ff1b70269ccbf 100644
--- a/drivers/platform/x86/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
@@ -1394,7 +1394,7 @@ static int eeepc_acpi_add(struct acpi_device *device)
 	 * and machine-specific scripts find the fixed name convenient.  But
 	 * It's also good for us to exclude multiple instances because both
 	 * our hwmon and our wlan rfkill subdevice use global ACPI objects
-	 * (the EC and the wlan PCI slot respectively).
+	 * (the EC and the PCI wlan slot respectively).
 	 */
 	result = eeepc_platform_init(eeepc);
 	if (result)
diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c
index 80e36d03c4e25..0e0ccef4871e9 100644
--- a/drivers/staging/wlan-ng/prism2usb.c
+++ b/drivers/staging/wlan-ng/prism2usb.c
@@ -11,45 +11,45 @@
 
 static const struct usb_device_id usb_prism_tbl[] = {
 	PRISM_DEV(0x04bb, 0x0922, "IOData AirPort WN-B11/USBS"),
-	PRISM_DEV(0x07aa, 0x0012, "Corega Wireless LAN USB Stick-11"),
-	PRISM_DEV(0x09aa, 0x3642, "Prism2.x 11Mbps WLAN USB Adapter"),
-	PRISM_DEV(0x1668, 0x0408, "Actiontec Prism2.5 11Mbps WLAN USB Adapter"),
-	PRISM_DEV(0x1668, 0x0421, "Actiontec Prism2.5 11Mbps WLAN USB Adapter"),
-	PRISM_DEV(0x1915, 0x2236, "Linksys WUSB11v3.0 11Mbps WLAN USB Adapter"),
-	PRISM_DEV(0x066b, 0x2212, "Linksys WUSB11v2.5 11Mbps WLAN USB Adapter"),
-	PRISM_DEV(0x066b, 0x2213, "Linksys WUSB12v1.1 11Mbps WLAN USB Adapter"),
+	PRISM_DEV(0x07aa, 0x0012, "Corega USB Wireless LAN Stick-11"),
+	PRISM_DEV(0x09aa, 0x3642, "Prism2.x 11Mbps USB WLAN Adapter"),
+	PRISM_DEV(0x1668, 0x0408, "Actiontec Prism2.5 11Mbps USB WLAN Adapter"),
+	PRISM_DEV(0x1668, 0x0421, "Actiontec Prism2.5 11Mbps USB WLAN Adapter"),
+	PRISM_DEV(0x1915, 0x2236, "Linksys WUSB11v3.0 11Mbps USB WLAN Adapter"),
+	PRISM_DEV(0x066b, 0x2212, "Linksys WUSB11v2.5 11Mbps USB WLAN Adapter"),
+	PRISM_DEV(0x066b, 0x2213, "Linksys WUSB12v1.1 11Mbps USB WLAN Adapter"),
 	PRISM_DEV(0x0411, 0x0016, "Melco WLI-USB-S11 11Mbps WLAN Adapter"),
-	PRISM_DEV(0x08de, 0x7a01, "PRISM25 IEEE 802.11 Mini USB Adapter"),
-	PRISM_DEV(0x8086, 0x1111, "Intel PRO/Wireless 2011B LAN USB Adapter"),
+	PRISM_DEV(0x08de, 0x7a01, "PRISM25 USB IEEE 802.11 Mini Adapter"),
+	PRISM_DEV(0x8086, 0x1111, "Intel PRO/Wireless 2011B USB LAN Adapter"),
 	PRISM_DEV(0x0d8e, 0x7a01, "PRISM25 IEEE 802.11 Mini USB Adapter"),
-	PRISM_DEV(0x045e, 0x006e, "Microsoft MN510 Wireless USB Adapter"),
+	PRISM_DEV(0x045e, 0x006e, "Microsoft MN510 USB Wireless Adapter"),
 	PRISM_DEV(0x0967, 0x0204, "Acer Warplink USB Adapter"),
 	PRISM_DEV(0x0cde, 0x0002, "Z-Com 725/726 Prism2.5 USB/USB Integrated"),
-	PRISM_DEV(0x0cde, 0x0005, "Z-Com Xl735 Wireless 802.11b USB Adapter"),
-	PRISM_DEV(0x413c, 0x8100, "Dell TrueMobile 1180 Wireless USB Adapter"),
-	PRISM_DEV(0x0b3b, 0x1601, "ALLNET 0193 11Mbps WLAN USB Adapter"),
-	PRISM_DEV(0x0b3b, 0x1602, "ZyXEL ZyAIR B200 Wireless USB Adapter"),
-	PRISM_DEV(0x0baf, 0x00eb, "USRobotics USR1120 Wireless USB Adapter"),
+	PRISM_DEV(0x0cde, 0x0005, "Z-Com Xl735 USB Wireless 802.11b Adapter"),
+	PRISM_DEV(0x413c, 0x8100, "Dell TrueMobile 1180 USB Wireless Adapter"),
+	PRISM_DEV(0x0b3b, 0x1601, "ALLNET 0193 11Mbps USB WLAN Adapter"),
+	PRISM_DEV(0x0b3b, 0x1602, "ZyXEL ZyAIR B200 USB Wireless Adapter"),
+	PRISM_DEV(0x0baf, 0x00eb, "USRobotics USR1120 USB Wireless Adapter"),
 	PRISM_DEV(0x0411, 0x0027, "Melco WLI-USB-KS11G 11Mbps WLAN Adapter"),
 	PRISM_DEV(0x04f1, 0x3009, "JVC MP-XP7250 Builtin USB WLAN Adapter"),
 	PRISM_DEV(0x0846, 0x4110, "NetGear MA111"),
 	PRISM_DEV(0x03f3, 0x0020, "Adaptec AWN-8020 USB WLAN Adapter"),
-	PRISM_DEV(0x2821, 0x3300, "ASUS-WL140 / Hawking HighDB Wireless USB Adapter"),
-	PRISM_DEV(0x2001, 0x3700, "DWL-122 Wireless USB Adapter"),
-	PRISM_DEV(0x2001, 0x3702, "DWL-120 Rev F Wireless USB Adapter"),
+	PRISM_DEV(0x2821, 0x3300, "ASUS-WL140 / Hawking HighDB USB Wireless Adapter"),
+	PRISM_DEV(0x2001, 0x3700, "DWL-122 USB Wireless Adapter"),
+	PRISM_DEV(0x2001, 0x3702, "DWL-120 Rev F USB Wireless Adapter"),
 	PRISM_DEV(0x50c2, 0x4013, "Averatec USB WLAN Adapter"),
-	PRISM_DEV(0x2c02, 0x14ea, "Planex GW-US11H WLAN USB Adapter"),
-	PRISM_DEV(0x124a, 0x168b, "Airvast PRISM3 WLAN USB Adapter"),
+	PRISM_DEV(0x2c02, 0x14ea, "Planex GW-US11H USB WLAN Adapter"),
+	PRISM_DEV(0x124a, 0x168b, "Airvast PRISM3 USB WLAN Adapter"),
 	PRISM_DEV(0x083a, 0x3503, "T-Sinus 111 USB WLAN Adapter"),
 	PRISM_DEV(0x0411, 0x0044, "Melco WLI-USB-KB11 11Mbps WLAN Adapter"),
-	PRISM_DEV(0x1668, 0x6106, "ROPEX FreeLan 802.11b USB Adapter"),
-	PRISM_DEV(0x124a, 0x4017, "Pheenet WL-503IA 802.11b USB Adapter"),
+	PRISM_DEV(0x1668, 0x6106, "ROPEX FreeLan USB 802.11b Adapter"),
+	PRISM_DEV(0x124a, 0x4017, "Pheenet WL-503IA USB 802.11b Adapter"),
 	PRISM_DEV(0x0bb2, 0x0302, "Ambit Microsystems Corp."),
-	PRISM_DEV(0x9016, 0x182d, "Sitecom WL-022 802.11b USB Adapter"),
+	PRISM_DEV(0x9016, 0x182d, "Sitecom WL-022 USB 802.11b Adapter"),
 	PRISM_DEV(0x0543, 0x0f01,
 		  "ViewSonic Airsync USB Adapter 11Mbps (Prism2.5)"),
 	PRISM_DEV(0x067c, 0x1022,
-		  "Siemens SpeedStream 1022 11Mbps WLAN USB Adapter"),
+		  "Siemens SpeedStream 1022 11Mbps USB WLAN Adapter"),
 	PRISM_DEV(0x049f, 0x0033,
 		  "Compaq/Intel W100 PRO/Wireless 11Mbps multiport WLAN Adapter"),
 	{ } /* terminator */
-- 
GitLab


From 64a24cb63a4b6036e4af280767b305a5044ff303 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Wed, 16 Aug 2023 16:21:28 +0800
Subject: [PATCH 1679/1806] wifi: rtw89: add function prototype for coex
 request duration

The request duration comes from coex mechanism, indicating the
length of time that should be reserved for BT in each time division.
It is required to handle update notification when channel concurrency
processes. Since it will involve in both coex and wifi code flow, this
commit ahead adds the prototype for required function interfaces to
split the implementation of coex and wifi in the following.

The follow-up are expected be add afterwards.
1. coex mechanism call rtw89_core_ntfy_btc_event() once bt req len changes
2. channel concurrency flow updates related stuffs when notified

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230816082133.57474-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.h |  9 +++++++++
 drivers/net/wireless/realtek/rtw89/core.c | 21 +++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/core.h | 12 ++++++++++++
 3 files changed, 42 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.h b/drivers/net/wireless/realtek/rtw89/coex.h
index f16421cb30efb..e761537097934 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.h
+++ b/drivers/net/wireless/realtek/rtw89/coex.h
@@ -193,4 +193,13 @@ static inline u8 rtw89_btc_path_phymap(struct rtw89_dev *rtwdev,
 	return rtw89_btc_phymap(rtwdev, phy_idx, BIT(path));
 }
 
+/* return bt req len in TU */
+static inline u16 rtw89_coex_query_bt_req_len(struct rtw89_dev *rtwdev,
+					      enum rtw89_phy_idx phy_idx)
+{
+	struct rtw89_btc *btc = &rtwdev->btc;
+
+	return btc->bt_req_len;
+}
+
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 71eb9cfd48965..a338b0a97910e 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -3464,6 +3464,27 @@ void rtw89_complete_cond(struct rtw89_wait_info *wait, unsigned int cond,
 	complete(&wait->completion);
 }
 
+void rtw89_core_ntfy_btc_event(struct rtw89_dev *rtwdev, enum rtw89_btc_hmsg event)
+{
+	u16 bt_req_len;
+
+	switch (event) {
+	case RTW89_BTC_HMSG_SET_BT_REQ_SLOT:
+		bt_req_len = rtw89_coex_query_bt_req_len(rtwdev, RTW89_PHY_0);
+		rtw89_debug(rtwdev, RTW89_DBG_BTC,
+			    "coex updates BT req len to %d TU\n", bt_req_len);
+		break;
+	default:
+		if (event < NUM_OF_RTW89_BTC_HMSG)
+			rtw89_debug(rtwdev, RTW89_DBG_BTC,
+				    "unhandled BTC HMSG event: %d\n", event);
+		else
+			rtw89_warn(rtwdev,
+				   "unrecognized BTC HMSG event: %d\n", event);
+		break;
+	}
+}
+
 int rtw89_core_start(struct rtw89_dev *rtwdev)
 {
 	int ret;
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index b5a08f90f5bd7..5b60bc72b4a51 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -2656,6 +2656,17 @@ struct rtw89_btc {
 	bool lps;
 };
 
+enum rtw89_btc_hmsg {
+	RTW89_BTC_HMSG_TMR_EN = 0x0,
+	RTW89_BTC_HMSG_BT_REG_READBACK = 0x1,
+	RTW89_BTC_HMSG_SET_BT_REQ_SLOT = 0x2,
+	RTW89_BTC_HMSG_FW_EV = 0x3,
+	RTW89_BTC_HMSG_BT_LINK_CHG = 0x4,
+	RTW89_BTC_HMSG_SET_BT_REQ_STBC = 0x5,
+
+	NUM_OF_RTW89_BTC_HMSG,
+};
+
 enum rtw89_ra_mode {
 	RTW89_RA_MODE_CCK = BIT(0),
 	RTW89_RA_MODE_OFDM = BIT(1),
@@ -5325,5 +5336,6 @@ void rtw89_core_scan_complete(struct rtw89_dev *rtwdev,
 			      struct ieee80211_vif *vif, bool hw_scan);
 void rtw89_reg_6ghz_power_recalc(struct rtw89_dev *rtwdev,
 				 struct rtw89_vif *rtwvif, bool active);
+void rtw89_core_ntfy_btc_event(struct rtw89_dev *rtwdev, enum rtw89_btc_hmsg event);
 
 #endif
-- 
GitLab


From b05fdc46c5a64358f515c4db31991f609a572b53 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Wed, 16 Aug 2023 16:21:29 +0800
Subject: [PATCH 1680/1806] wifi: rtw89: refine rtw89_correct_cck_chan() by
 rtw89_hw_to_nl80211_band()

In rtw89_correct_cck_chan(), we turn to use rtw89_hw_to_nl80211_band().
The difference between rtw89_hw_to_nl80211_band() and the original raw
judgement is the case on 6 GHz. Since rtw89_correct_cck_chan() is common
code independent on chip, if runtime chip doesn't support 6 GHz, it is
probably safe. Otherwise, it might not.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230816082133.57474-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index a338b0a97910e..aedabd2622510 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -1659,8 +1659,7 @@ static void rtw89_correct_cck_chan(struct rtw89_dev *rtwdev,
 	const struct rtw89_chan_rcd *rcd =
 		rtw89_chan_rcd_get(rtwdev, RTW89_SUB_ENTITY_0);
 	u16 chan = rcd->prev_primary_channel;
-	u8 band = rcd->prev_band_type == RTW89_BAND_2G ?
-		  NL80211_BAND_2GHZ : NL80211_BAND_5GHZ;
+	u8 band = rtw89_hw_to_nl80211_band(rcd->prev_band_type);
 
 	if (status->band != NL80211_BAND_2GHZ &&
 	    status->encoding == RX_ENC_LEGACY &&
-- 
GitLab


From bfbadacf37a204afbfb829d508412d501a22d62c Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Wed, 16 Aug 2023 16:21:30 +0800
Subject: [PATCH 1681/1806] wifi: rtw89: sar: let caller decide the center
 frequency to query

If multiple channels, SAR will be hard to determine the center frequency
to query. Therefore, we move this decision out of SAR.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230816082133.57474-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/debug.c | 10 +++++----
 drivers/net/wireless/realtek/rtw89/phy.c   |  8 ++++++--
 drivers/net/wireless/realtek/rtw89/sar.c   | 24 +++++++++++-----------
 drivers/net/wireless/realtek/rtw89/sar.h   |  6 +++---
 4 files changed, 27 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index f6f1e90c39344..48635458c36ac 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -572,9 +572,9 @@ static int __print_txpwr_map(struct seq_file *m, struct rtw89_dev *rtwdev,
 		seq_puts(m, #_regd "\n"); \
 		break
 
-static void __print_regd(struct seq_file *m, struct rtw89_dev *rtwdev)
+static void __print_regd(struct seq_file *m, struct rtw89_dev *rtwdev,
+			 const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
 	u8 band = chan->band_type;
 	u8 regd = rtw89_regd_get(rtwdev, band);
 
@@ -604,16 +604,18 @@ static int rtw89_debug_priv_txpwr_table_get(struct seq_file *m, void *v)
 {
 	struct rtw89_debugfs_priv *debugfs_priv = m->private;
 	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+	const struct rtw89_chan *chan;
 	int ret = 0;
 
 	mutex_lock(&rtwdev->mutex);
 	rtw89_leave_ps_mode(rtwdev);
+	chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
 
 	seq_puts(m, "[Regulatory] ");
-	__print_regd(m, rtwdev);
+	__print_regd(m, rtwdev, chan);
 
 	seq_puts(m, "[SAR]\n");
-	rtw89_print_sar(m, rtwdev);
+	rtw89_print_sar(m, rtwdev, chan->freq);
 
 	seq_puts(m, "[TAS]\n");
 	rtw89_print_tas(m, rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index c40c4f8c1271c..fcdc61597b9bc 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -1647,6 +1647,8 @@ s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, u8 band,
 	const struct rtw89_txpwr_rule_5ghz *rule_5ghz = &rfe_parms->rule_5ghz;
 	const struct rtw89_txpwr_rule_6ghz *rule_6ghz = &rfe_parms->rule_6ghz;
 	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	enum nl80211_band nl_band = rtw89_hw_to_nl80211_band(band);
+	u32 freq = ieee80211_channel_to_frequency(ch, nl_band);
 	u8 ch_idx = rtw89_channel_to_idx(rtwdev, band, ch);
 	u8 regd = rtw89_regd_get(rtwdev, band);
 	u8 reg6 = regulatory->reg_6ghz_power;
@@ -1682,7 +1684,7 @@ s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, u8 band,
 	}
 
 	lmt = _phy_txpwr_rf_to_mac(rtwdev, lmt);
-	sar = rtw89_query_sar(rtwdev);
+	sar = rtw89_query_sar(rtwdev, freq);
 
 	return min(lmt, sar);
 }
@@ -1902,6 +1904,8 @@ static s8 rtw89_phy_read_txpwr_limit_ru(struct rtw89_dev *rtwdev, u8 band,
 	const struct rtw89_txpwr_rule_5ghz *rule_5ghz = &rfe_parms->rule_5ghz;
 	const struct rtw89_txpwr_rule_6ghz *rule_6ghz = &rfe_parms->rule_6ghz;
 	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	enum nl80211_band nl_band = rtw89_hw_to_nl80211_band(band);
+	u32 freq = ieee80211_channel_to_frequency(ch, nl_band);
 	u8 ch_idx = rtw89_channel_to_idx(rtwdev, band, ch);
 	u8 regd = rtw89_regd_get(rtwdev, band);
 	u8 reg6 = regulatory->reg_6ghz_power;
@@ -1937,7 +1941,7 @@ static s8 rtw89_phy_read_txpwr_limit_ru(struct rtw89_dev *rtwdev, u8 band,
 	}
 
 	lmt_ru = _phy_txpwr_rf_to_mac(rtwdev, lmt_ru);
-	sar = rtw89_query_sar(rtwdev);
+	sar = rtw89_query_sar(rtwdev, freq);
 
 	return min(lmt_ru, sar);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index fafc7a0cfe97c..881322f85d79d 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -85,17 +85,15 @@ static const struct rtw89_sar_span rtw89_sar_overlapping_6ghz[] = {
 	RTW89_DECL_SAR_6GHZ_SPAN(6885, SUBBAND_7_H, SUBBAND_8),
 };
 
-static int rtw89_query_sar_config_common(struct rtw89_dev *rtwdev, s32 *cfg)
+static int rtw89_query_sar_config_common(struct rtw89_dev *rtwdev,
+					 u32 center_freq, s32 *cfg)
 {
 	struct rtw89_sar_cfg_common *rtwsar = &rtwdev->sar.cfg_common;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
-	enum rtw89_band band = chan->band_type;
-	u32 center_freq = chan->freq;
 	const struct rtw89_sar_span *span = NULL;
 	enum rtw89_sar_subband subband_l, subband_h;
 	int idx;
 
-	if (band == RTW89_BAND_6G) {
+	if (center_freq >= RTW89_SAR_6GHZ_SPAN_HEAD) {
 		idx = RTW89_SAR_6GHZ_SPAN_IDX(center_freq);
 		/* To decrease size of rtw89_sar_overlapping_6ghz[],
 		 * RTW89_SAR_6GHZ_SPAN_IDX() truncates the leading NULLs
@@ -115,8 +113,8 @@ static int rtw89_query_sar_config_common(struct rtw89_dev *rtwdev, s32 *cfg)
 	}
 
 	rtw89_debug(rtwdev, RTW89_DBG_SAR,
-		    "for {band %u, center_freq %u}, SAR subband: {%u, %u}\n",
-		    band, center_freq, subband_l, subband_h);
+		    "center_freq %u: SAR subband {%u, %u}\n",
+		    center_freq, subband_l, subband_h);
 
 	if (!rtwsar->set[subband_l] && !rtwsar->set[subband_h])
 		return -ENODATA;
@@ -186,7 +184,7 @@ static s8 rtw89_txpwr_sar_to_tas(const struct rtw89_sar_handler *sar_hdl,
 		return cfg << (RTW89_TAS_FACTOR - fct);
 }
 
-s8 rtw89_query_sar(struct rtw89_dev *rtwdev)
+s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq)
 {
 	const enum rtw89_sar_sources src = rtwdev->sar.src;
 	/* its members are protected by rtw89_sar_set_src() */
@@ -202,7 +200,7 @@ s8 rtw89_query_sar(struct rtw89_dev *rtwdev)
 	if (src == RTW89_SAR_SOURCE_NONE)
 		return RTW89_SAR_TXPWR_MAC_MAX;
 
-	ret = sar_hdl->query_sar_config(rtwdev, &cfg);
+	ret = sar_hdl->query_sar_config(rtwdev, center_freq, &cfg);
 	if (ret)
 		return RTW89_SAR_TXPWR_MAC_MAX;
 
@@ -224,7 +222,7 @@ s8 rtw89_query_sar(struct rtw89_dev *rtwdev)
 	return rtw89_txpwr_sar_to_mac(rtwdev, fct, cfg);
 }
 
-void rtw89_print_sar(struct seq_file *m, struct rtw89_dev *rtwdev)
+void rtw89_print_sar(struct seq_file *m, struct rtw89_dev *rtwdev, u32 center_freq)
 {
 	const enum rtw89_sar_sources src = rtwdev->sar.src;
 	/* its members are protected by rtw89_sar_set_src() */
@@ -243,7 +241,7 @@ void rtw89_print_sar(struct seq_file *m, struct rtw89_dev *rtwdev)
 
 	seq_printf(m, "source: %d (%s)\n", src, sar_hdl->descr_sar_source);
 
-	ret = sar_hdl->query_sar_config(rtwdev, &cfg);
+	ret = sar_hdl->query_sar_config(rtwdev, center_freq, &cfg);
 	if (ret) {
 		seq_printf(m, "config: return code: %d\n", ret);
 		seq_printf(m, "assign: max setting: %d (unit: 1/%lu dBm)\n",
@@ -359,6 +357,7 @@ static void rtw89_tas_state_update(struct rtw89_dev *rtwdev)
 	s32 txpwr_avg = tas->total_txpwr / RTW89_TAS_MAX_WINDOW / PERCENT;
 	s32 dpr_on_threshold, dpr_off_threshold, cfg;
 	enum rtw89_tas_state state = tas->state;
+	const struct rtw89_chan *chan;
 	int ret;
 
 	lockdep_assert_held(&rtwdev->mutex);
@@ -366,7 +365,8 @@ static void rtw89_tas_state_update(struct rtw89_dev *rtwdev)
 	if (src == RTW89_SAR_SOURCE_NONE)
 		return;
 
-	ret = sar_hdl->query_sar_config(rtwdev, &cfg);
+	chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	ret = sar_hdl->query_sar_config(rtwdev, chan->freq, &cfg);
 	if (ret)
 		return;
 
diff --git a/drivers/net/wireless/realtek/rtw89/sar.h b/drivers/net/wireless/realtek/rtw89/sar.h
index 40ce5990ceaf5..bd7a657188d91 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.h
+++ b/drivers/net/wireless/realtek/rtw89/sar.h
@@ -13,13 +13,13 @@
 struct rtw89_sar_handler {
 	const char *descr_sar_source;
 	u8 txpwr_factor_sar;
-	int (*query_sar_config)(struct rtw89_dev *rtwdev, s32 *cfg);
+	int (*query_sar_config)(struct rtw89_dev *rtwdev, u32 center_freq, s32 *cfg);
 };
 
 extern const struct cfg80211_sar_capa rtw89_sar_capa;
 
-s8 rtw89_query_sar(struct rtw89_dev *rtwdev);
-void rtw89_print_sar(struct seq_file *m, struct rtw89_dev *rtwdev);
+s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq);
+void rtw89_print_sar(struct seq_file *m, struct rtw89_dev *rtwdev, u32 center_freq);
 void rtw89_print_tas(struct seq_file *m, struct rtw89_dev *rtwdev);
 int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw,
 			    const struct cfg80211_sar_specs *sar);
-- 
GitLab


From ad3dc7220220ae2b86152c67882f9cf5bad4bc1f Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Wed, 16 Aug 2023 16:21:31 +0800
Subject: [PATCH 1682/1806] wifi: rtw89: call rtw89_chan_get() by vif chanctx
 if aware of vif

We adjust these processes which can work accodrding to vif but call
rtw89_chan_get() with static RTW89_SUB_ENTITY_0. After multi-channel
support, chanctx of vif won't always be on RTW89_SUB_ENTITY_0. So,
we make them call rtw89_chan_get() with rtwvif->sub_entity_idx.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230816082133.57474-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c     |  3 ++-
 drivers/net/wireless/realtek/rtw89/core.c     | 22 +++++++++++--------
 drivers/net/wireless/realtek/rtw89/core.h     | 12 ++++++++++
 drivers/net/wireless/realtek/rtw89/fw.c       |  6 +++--
 drivers/net/wireless/realtek/rtw89/mac80211.c |  3 ++-
 drivers/net/wireless/realtek/rtw89/phy.c      | 21 ++++++++++--------
 6 files changed, 45 insertions(+), 22 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index bda0e1e99a8c6..4ba8b3df70aeb 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -5666,7 +5666,8 @@ enum btc_wl_mode {
 void rtw89_btc_ntfy_role_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			      struct rtw89_sta *rtwsta, enum btc_role_state state)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
+						       rtwvif->sub_entity_idx);
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
 	struct ieee80211_sta *sta = rtwsta_to_sta(rtwsta);
 	struct rtw89_btc *btc = &rtwdev->btc;
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index aedabd2622510..91f9a587220b1 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -523,12 +523,12 @@ rtw89_core_tx_update_sec_key(struct rtw89_dev *rtwdev,
 }
 
 static u16 rtw89_core_get_mgmt_rate(struct rtw89_dev *rtwdev,
-				    struct rtw89_core_tx_request *tx_req)
+				    struct rtw89_core_tx_request *tx_req,
+				    const struct rtw89_chan *chan)
 {
 	struct sk_buff *skb = tx_req->skb;
 	struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_vif *vif = tx_info->control.vif;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
 	u16 lowest_rate;
 
 	if (tx_info->flags & IEEE80211_TX_CTL_NO_CCK_RATE ||
@@ -567,7 +567,8 @@ rtw89_core_tx_update_mgmt_info(struct rtw89_dev *rtwdev,
 	struct ieee80211_vif *vif = tx_req->vif;
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	struct rtw89_tx_desc_info *desc_info = &tx_req->desc_info;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
+						       rtwvif->sub_entity_idx);
 	u8 qsel, ch_dma;
 
 	qsel = desc_info->hiq ? RTW89_TX_QSEL_B0_HI : RTW89_TX_QSEL_B0_MGMT;
@@ -584,7 +585,7 @@ rtw89_core_tx_update_mgmt_info(struct rtw89_dev *rtwdev,
 	desc_info->en_wd_info = true;
 	desc_info->use_rate = true;
 	desc_info->dis_data_fb = true;
-	desc_info->data_rate = rtw89_core_get_mgmt_rate(rtwdev, tx_req);
+	desc_info->data_rate = rtw89_core_get_mgmt_rate(rtwdev, tx_req, chan);
 
 	rtw89_debug(rtwdev, RTW89_DBG_TXRX,
 		    "tx mgmt frame with rate 0x%x on channel %d (band %d, bw %d)\n",
@@ -603,7 +604,8 @@ rtw89_core_tx_update_h2c_info(struct rtw89_dev *rtwdev,
 	desc_info->ch_dma = RTW89_DMA_H2C;
 }
 
-static void rtw89_core_get_no_ul_ofdma_htc(struct rtw89_dev *rtwdev, __le32 *htc)
+static void rtw89_core_get_no_ul_ofdma_htc(struct rtw89_dev *rtwdev, __le32 *htc,
+					   const struct rtw89_chan *chan)
 {
 	static const u8 rtw89_bandwidth_to_om[] = {
 		[RTW89_CHANNEL_WIDTH_20] = HTC_OM_CHANNEL_WIDTH_20,
@@ -614,7 +616,6 @@ static void rtw89_core_get_no_ul_ofdma_htc(struct rtw89_dev *rtwdev, __le32 *htc
 	};
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct rtw89_hal *hal = &rtwdev->hal;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
 	u8 om_bandwidth;
 
 	if (!chip->dis_2g_40m_ul_ofdma ||
@@ -1899,7 +1900,6 @@ static void rtw89_core_update_rx_status(struct rtw89_dev *rtwdev,
 {
 	const struct cfg80211_chan_def *chandef =
 		rtw89_chandef_get(rtwdev, RTW89_SUB_ENTITY_0);
-	const struct rtw89_chan *cur = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
 	u16 data_rate;
 	u8 data_rate_mode;
 
@@ -1909,6 +1909,7 @@ static void rtw89_core_update_rx_status(struct rtw89_dev *rtwdev,
 
 	if (rtwdev->scanning &&
 	    RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw)) {
+		const struct rtw89_chan *cur = rtw89_scan_chan_get(rtwdev);
 		u8 chan = cur->primary_channel;
 		u8 band = cur->band_type;
 		enum nl80211_band nl_band;
@@ -2970,6 +2971,8 @@ int rtw89_core_sta_assoc(struct rtw89_dev *rtwdev,
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv;
 	struct rtw89_bssid_cam_entry *bssid_cam = rtw89_get_bssid_cam_of(rtwvif, rtwsta);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
+						       rtwvif->sub_entity_idx);
 	int ret;
 
 	if (vif->type == NL80211_IFTYPE_AP || sta->tdls) {
@@ -3023,7 +3026,7 @@ int rtw89_core_sta_assoc(struct rtw89_dev *rtwdev,
 
 		rtw89_btc_ntfy_role_info(rtwdev, rtwvif, rtwsta,
 					 BTC_ROLE_MSTS_STA_CONN_END);
-		rtw89_core_get_no_ul_ofdma_htc(rtwdev, &rtwsta->htc_template);
+		rtw89_core_get_no_ul_ofdma_htc(rtwdev, &rtwsta->htc_template, chan);
 		rtw89_phy_ul_tb_assoc(rtwdev, rtwvif);
 
 		ret = rtw89_fw_h2c_general_pkt(rtwdev, rtwvif, rtwsta->mac_id);
@@ -3656,7 +3659,8 @@ EXPORT_SYMBOL(rtw89_core_deinit);
 void rtw89_core_scan_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			   const u8 *mac_addr, bool hw_scan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
+						       rtwvif->sub_entity_idx);
 
 	rtwdev->scanning = true;
 	rtw89_leave_lps(rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 5b60bc72b4a51..257582fc39ea5 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4929,6 +4929,18 @@ const struct rtw89_chan_rcd *rtw89_chan_rcd_get(struct rtw89_dev *rtwdev,
 	return &hal->sub[idx].rcd;
 }
 
+static inline
+const struct rtw89_chan *rtw89_scan_chan_get(struct rtw89_dev *rtwdev)
+{
+	struct ieee80211_vif *vif = rtwdev->scan_info.scanning_vif;
+	struct rtw89_vif *rtwvif = vif_to_rtwvif_safe(vif);
+
+	if (rtwvif)
+		return rtw89_chan_get(rtwdev, rtwvif->sub_entity_idx);
+	else
+		return rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+}
+
 static inline void rtw89_chip_fem_setup(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index bcd9050f989ff..4c044dbc90b6d 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -1758,7 +1758,8 @@ int rtw89_fw_h2c_assoc_cmac_tbl(struct rtw89_dev *rtwdev,
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta);
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
+						       rtwvif->sub_entity_idx);
 	struct sk_buff *skb;
 	u8 pads[RTW89_PPE_BW_NUM];
 	u8 mac_id = rtwsta ? rtwsta->mac_id : rtwvif->mac_id;
@@ -1915,7 +1916,8 @@ int rtw89_fw_h2c_update_beacon(struct rtw89_dev *rtwdev,
 			       struct rtw89_vif *rtwvif)
 {
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
+						       rtwvif->sub_entity_idx);
 	struct sk_buff *skb;
 	struct sk_buff *skb_beacon;
 	u16 tim_offset;
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index a66503eb35b80..7c3066c0a5501 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -296,7 +296,8 @@ static u8 rtw89_aifsn_to_aifs(struct rtw89_dev *rtwdev,
 			      struct rtw89_vif *rtwvif, u8 aifsn)
 {
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
+						       rtwvif->sub_entity_idx);
 	u8 slot_time;
 	u8 sifs;
 
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index fcdc61597b9bc..5ff2871b230b3 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -133,10 +133,10 @@ static u64 rtw89_phy_ra_mask_recover(u64 ra_mask, u64 ra_mask_bak)
 	return ra_mask;
 }
 
-static u64 rtw89_phy_ra_mask_cfg(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta)
+static u64 rtw89_phy_ra_mask_cfg(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta,
+				 const struct rtw89_chan *chan)
 {
 	struct ieee80211_sta *sta = rtwsta_to_sta(rtwsta);
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
 	struct cfg80211_bitrate_mask *mask = &rtwsta->mask;
 	enum nl80211_band band;
 	u64 cfg_mask;
@@ -197,9 +197,9 @@ rtw89_ra_mask_he_rates[4] = {RA_MASK_HE_1SS_RATES, RA_MASK_HE_2SS_RATES,
 
 static void rtw89_phy_ra_gi_ltf(struct rtw89_dev *rtwdev,
 				struct rtw89_sta *rtwsta,
+				const struct rtw89_chan *chan,
 				bool *fix_giltf_en, u8 *fix_giltf)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
 	struct cfg80211_bitrate_mask *mask = &rtwsta->mask;
 	u8 band = chan->band_type;
 	enum nl80211_band nl_band = rtw89_hw_to_nl80211_band(band);
@@ -236,7 +236,8 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev,
 	struct rtw89_vif *rtwvif = rtwsta->rtwvif;
 	struct rtw89_phy_rate_pattern *rate_pattern = &rtwvif->rate_pattern;
 	struct rtw89_ra_info *ra = &rtwsta->ra;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
+						       rtwvif->sub_entity_idx);
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwsta->rtwvif);
 	const u64 *high_rate_masks = rtw89_ra_mask_ht_rates;
 	u8 rssi = ewma_rssi_read(&rtwsta->avg_rssi);
@@ -265,7 +266,7 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev,
 		if (sta->deflink.he_cap.he_cap_elem.phy_cap_info[1] &
 		    IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD)
 			ldpc_en = 1;
-		rtw89_phy_ra_gi_ltf(rtwdev, rtwsta, &fix_giltf_en, &fix_giltf);
+		rtw89_phy_ra_gi_ltf(rtwdev, rtwsta, chan, &fix_giltf_en, &fix_giltf);
 	} else if (sta->deflink.vht_cap.vht_supported) {
 		u16 mcs_map = le16_to_cpu(sta->deflink.vht_cap.vht_mcs.rx_mcs_map);
 
@@ -332,7 +333,7 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev,
 		ra_mask &= rtw89_phy_ra_mask_rssi(rtwdev, rssi, 0);
 
 	ra_mask = rtw89_phy_ra_mask_recover(ra_mask, ra_mask_bak);
-	ra_mask &= rtw89_phy_ra_mask_cfg(rtwdev, rtwsta);
+	ra_mask &= rtw89_phy_ra_mask_cfg(rtwdev, rtwsta, chan);
 
 	switch (sta->deflink.bandwidth) {
 	case IEEE80211_STA_RX_BW_160:
@@ -362,7 +363,7 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev,
 		ra->dcm_cap = 1;
 
 	if (rate_pattern->enable && !vif->p2p) {
-		ra_mask = rtw89_phy_ra_mask_cfg(rtwdev, rtwsta);
+		ra_mask = rtw89_phy_ra_mask_cfg(rtwdev, rtwsta, chan);
 		ra_mask &= rate_pattern->ra_mask;
 		mode = rate_pattern->ra_mode;
 	}
@@ -457,7 +458,8 @@ void rtw89_phy_rate_pattern_vif(struct rtw89_dev *rtwdev,
 	struct ieee80211_supported_band *sband;
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	struct rtw89_phy_rate_pattern next_pattern = {0};
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
+						       rtwvif->sub_entity_idx);
 	static const u16 hw_rate_he[][RTW89_CHIP_GEN_NUM] = {
 		RTW89_HW_RATE_BY_CHIP_GEN(HE_NSS1_MCS0),
 		RTW89_HW_RATE_BY_CHIP_GEN(HE_NSS2_MCS0),
@@ -2889,7 +2891,8 @@ void rtw89_phy_cfo_parse(struct rtw89_dev *rtwdev, s16 cfo_val,
 void rtw89_phy_ul_tb_assoc(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
+						       rtwvif->sub_entity_idx);
 	struct rtw89_phy_ul_tb_info *ul_tb_info = &rtwdev->ul_tb_info;
 
 	if (!chip->support_ul_tb_ctrl)
-- 
GitLab


From 51383fd77791333868ef69bff223629a964beb8c Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Wed, 16 Aug 2023 16:21:32 +0800
Subject: [PATCH 1683/1806] wifi: rtw89: provide functions to configure NoA for
 beacon update

Callers call renew function when wanting to generate a new P2P NoA
information element, and call append function to append NoA attribute
one by one. Then, updating beacon work will fetch the P2P NoA information
element configured by callers and add it to beacon.

The use case of MCC (multi-channel concurrent) <GO + STA> for example:
* start MCC - GO part
	renew P2P NoA
	append period NoA after calculation
* download beacon for GO
	fetch P2P NoA and add to beacon content
* stop MCC - GO part
	renew P2P NoA (reset)

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230816082133.57474-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h | 27 ++++++++++
 drivers/net/wireless/realtek/rtw89/fw.c   | 10 ++++
 drivers/net/wireless/realtek/rtw89/ps.c   | 61 +++++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/ps.h   |  4 ++
 4 files changed, 102 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 257582fc39ea5..431b0d3daa2a2 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -2896,6 +2896,32 @@ struct rtw89_roc {
 
 #define RTW89_P2P_MAX_NOA_NUM 2
 
+struct rtw89_p2p_ie_head {
+	u8 eid;
+	u8 ie_len;
+	u8 oui[3];
+	u8 oui_type;
+} __packed;
+
+struct rtw89_noa_attr_head {
+	u8 attr_type;
+	__le16 attr_len;
+	u8 index;
+	u8 oppps_ctwindow;
+} __packed;
+
+struct rtw89_p2p_noa_ie {
+	struct rtw89_p2p_ie_head p2p_head;
+	struct rtw89_noa_attr_head noa_head;
+	struct ieee80211_p2p_noa_desc noa_desc[RTW89_P2P_MAX_NOA_NUM];
+} __packed;
+
+struct rtw89_p2p_noa_setter {
+	struct rtw89_p2p_noa_ie ie;
+	u8 noa_count;
+	u8 noa_index;
+};
+
 struct rtw89_vif {
 	struct list_head list;
 	struct rtw89_dev *rtwdev;
@@ -2938,6 +2964,7 @@ struct rtw89_vif {
 	struct cfg80211_scan_request *scan_req;
 	struct ieee80211_scan_ies *scan_ies;
 	struct list_head general_pkt_list;
+	struct rtw89_p2p_noa_setter p2p_noa;
 };
 
 enum rtw89_lv1_rcvy_step {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 4c044dbc90b6d..772b0f107f40e 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -9,6 +9,7 @@
 #include "fw.h"
 #include "mac.h"
 #include "phy.h"
+#include "ps.h"
 #include "reg.h"
 #include "util.h"
 
@@ -1923,6 +1924,8 @@ int rtw89_fw_h2c_update_beacon(struct rtw89_dev *rtwdev,
 	u16 tim_offset;
 	int bcn_total_len;
 	u16 beacon_rate;
+	void *noa_data;
+	u8 noa_len;
 	int ret;
 
 	if (vif->p2p)
@@ -1939,6 +1942,13 @@ int rtw89_fw_h2c_update_beacon(struct rtw89_dev *rtwdev,
 		return -ENOMEM;
 	}
 
+	noa_len = rtw89_p2p_noa_fetch(rtwvif, &noa_data);
+	if (noa_len &&
+	    (noa_len <= skb_tailroom(skb_beacon) ||
+	     pskb_expand_head(skb_beacon, 0, noa_len, GFP_KERNEL) == 0)) {
+		skb_put_data(skb_beacon, noa_data, noa_len);
+	}
+
 	bcn_total_len = H2C_BCN_BASE_LEN + skb_beacon->len;
 	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, bcn_total_len);
 	if (!skb) {
diff --git a/drivers/net/wireless/realtek/rtw89/ps.c b/drivers/net/wireless/realtek/rtw89/ps.c
index 84201ef19c176..b98ec178abe12 100644
--- a/drivers/net/wireless/realtek/rtw89/ps.c
+++ b/drivers/net/wireless/realtek/rtw89/ps.c
@@ -278,3 +278,64 @@ void rtw89_recalc_lps(struct rtw89_dev *rtwdev)
 		rtwdev->lps_enabled = false;
 	}
 }
+
+void rtw89_p2p_noa_renew(struct rtw89_vif *rtwvif)
+{
+	struct rtw89_p2p_noa_setter *setter = &rtwvif->p2p_noa;
+	struct rtw89_p2p_noa_ie *ie = &setter->ie;
+	struct rtw89_p2p_ie_head *p2p_head = &ie->p2p_head;
+	struct rtw89_noa_attr_head *noa_head = &ie->noa_head;
+
+	if (setter->noa_count) {
+		setter->noa_index++;
+		setter->noa_count = 0;
+	}
+
+	memset(ie, 0, sizeof(*ie));
+
+	p2p_head->eid = WLAN_EID_VENDOR_SPECIFIC;
+	p2p_head->ie_len = 4 + sizeof(*noa_head);
+	p2p_head->oui[0] = (WLAN_OUI_WFA >> 16) & 0xff;
+	p2p_head->oui[1] = (WLAN_OUI_WFA >> 8) & 0xff;
+	p2p_head->oui[2] = (WLAN_OUI_WFA >> 0) & 0xff;
+	p2p_head->oui_type = WLAN_OUI_TYPE_WFA_P2P;
+
+	noa_head->attr_type = IEEE80211_P2P_ATTR_ABSENCE_NOTICE;
+	noa_head->attr_len = cpu_to_le16(2);
+	noa_head->index = setter->noa_index;
+	noa_head->oppps_ctwindow = 0;
+}
+
+void rtw89_p2p_noa_append(struct rtw89_vif *rtwvif,
+			  const struct ieee80211_p2p_noa_desc *desc)
+{
+	struct rtw89_p2p_noa_setter *setter = &rtwvif->p2p_noa;
+	struct rtw89_p2p_noa_ie *ie = &setter->ie;
+	struct rtw89_p2p_ie_head *p2p_head = &ie->p2p_head;
+	struct rtw89_noa_attr_head *noa_head = &ie->noa_head;
+
+	if (!desc->count || !desc->duration)
+		return;
+
+	if (setter->noa_count >= RTW89_P2P_MAX_NOA_NUM)
+		return;
+
+	p2p_head->ie_len += sizeof(*desc);
+	le16_add_cpu(&noa_head->attr_len, sizeof(*desc));
+
+	ie->noa_desc[setter->noa_count++] = *desc;
+}
+
+u8 rtw89_p2p_noa_fetch(struct rtw89_vif *rtwvif, void **data)
+{
+	struct rtw89_p2p_noa_setter *setter = &rtwvif->p2p_noa;
+	struct rtw89_p2p_noa_ie *ie = &setter->ie;
+	void *tail;
+
+	if (!setter->noa_count)
+		return 0;
+
+	*data = ie;
+	tail = ie->noa_desc + setter->noa_count;
+	return tail - *data;
+}
diff --git a/drivers/net/wireless/realtek/rtw89/ps.h b/drivers/net/wireless/realtek/rtw89/ps.h
index 4c18f49204b28..aff0fba71cb0b 100644
--- a/drivers/net/wireless/realtek/rtw89/ps.h
+++ b/drivers/net/wireless/realtek/rtw89/ps.h
@@ -16,6 +16,10 @@ void rtw89_leave_ips(struct rtw89_dev *rtwdev);
 void rtw89_set_coex_ctrl_lps(struct rtw89_dev *rtwdev, bool btc_ctrl);
 void rtw89_process_p2p_ps(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif);
 void rtw89_recalc_lps(struct rtw89_dev *rtwdev);
+void rtw89_p2p_noa_renew(struct rtw89_vif *rtwvif);
+void rtw89_p2p_noa_append(struct rtw89_vif *rtwvif,
+			  const struct ieee80211_p2p_noa_desc *desc);
+u8 rtw89_p2p_noa_fetch(struct rtw89_vif *rtwvif, void **data);
 
 static inline void rtw89_leave_ips_by_hwflags(struct rtw89_dev *rtwdev)
 {
-- 
GitLab


From 4843aa3768e2c7f4dc61400c2db03671236d7c98 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Wed, 16 Aug 2023 16:21:33 +0800
Subject: [PATCH 1684/1806] wifi: rtw89: initialize multi-channel handling

We prepare to deal with multiple channels via new entity modes.
* MCC_PREPARE:	Transitional mode before MCC
* MCC:		Multi-Channel Concurrent mode
And, enum of sub-entity is extended for second channel context.

We add the entry flow of multi-channel handling and the core stuffs
for extended index of sub-entity. And, we now deal with the filling
of entity channels' info in entity recalc where we know the number
of active chanctx. However, the other detail coding of MCC start/stop
will be implemented in the following.

Besides, chanctx listener struct is pre-added in chip info. Each
component can add callback type in chanctx listener and configure
its callback function to react according to chanctx states. We know
at least RFK (RF calibration) and BTC (BT coexistence) will require
such callbacks.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230816082133.57474-7-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/chan.c     | 124 ++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/chan.h     |   5 +
 drivers/net/wireless/realtek/rtw89/core.c     |  68 +++++++---
 drivers/net/wireless/realtek/rtw89/core.h     |  27 ++++
 drivers/net/wireless/realtek/rtw89/mac80211.c |   4 +
 drivers/net/wireless/realtek/rtw89/ps.c       |  14 +-
 6 files changed, 219 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index 4663db4ce2f66..e1bc3606f9ae6 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -4,6 +4,8 @@
 
 #include "chan.h"
 #include "debug.h"
+#include "fw.h"
+#include "ps.h"
 #include "util.h"
 
 static enum rtw89_subband rtw89_get_subband_type(enum rtw89_band band,
@@ -116,6 +118,7 @@ bool rtw89_assign_entity_chan(struct rtw89_dev *rtwdev,
 	rcd->prev_primary_channel = chan->primary_channel;
 	rcd->prev_band_type = chan->band_type;
 	band_changed = new->band_type != chan->band_type;
+	rcd->band_changed = band_changed;
 
 	*chan = *new;
 	return band_changed;
@@ -193,8 +196,12 @@ void rtw89_entity_init(struct rtw89_dev *rtwdev)
 enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
+	const struct cfg80211_chan_def *chandef;
 	enum rtw89_entity_mode mode;
+	struct rtw89_chan chan;
 	u8 weight;
+	u8 last;
+	u8 idx;
 
 	weight = bitmap_weight(hal->entity_map, NUM_OF_RTW89_SUB_ENTITY);
 	switch (weight) {
@@ -206,14 +213,121 @@ enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev)
 		rtw89_config_default_chandef(rtwdev);
 		fallthrough;
 	case 1:
+		last = RTW89_SUB_ENTITY_0;
 		mode = RTW89_ENTITY_MODE_SCC;
 		break;
+	case 2:
+		last = RTW89_SUB_ENTITY_1;
+		mode = rtw89_get_entity_mode(rtwdev);
+		if (mode == RTW89_ENTITY_MODE_MCC)
+			break;
+
+		mode = RTW89_ENTITY_MODE_MCC_PREPARE;
+		break;
+	}
+
+	for (idx = 0; idx <= last; idx++) {
+		chandef = rtw89_chandef_get(rtwdev, idx);
+		rtw89_get_channel_params(chandef, &chan);
+		if (chan.channel == 0) {
+			WARN(1, "Invalid channel on chanctx %d\n", idx);
+			return RTW89_ENTITY_MODE_INVALID;
+		}
+
+		rtw89_assign_entity_chan(rtwdev, idx, &chan);
 	}
 
 	rtw89_set_entity_mode(rtwdev, mode);
 	return mode;
 }
 
+static void rtw89_chanctx_notify(struct rtw89_dev *rtwdev,
+				 enum rtw89_chanctx_state state)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	const struct rtw89_chanctx_listener *listener = chip->chanctx_listener;
+	int i;
+
+	if (!listener)
+		return;
+
+	for (i = 0; i < NUM_OF_RTW89_CHANCTX_CALLBACKS; i++) {
+		if (!listener->callbacks[i])
+			continue;
+
+		rtw89_debug(rtwdev, RTW89_DBG_CHAN,
+			    "chanctx notify listener: cb %d, state %d\n",
+			    i, state);
+
+		listener->callbacks[i](rtwdev, state);
+	}
+}
+
+static int rtw89_mcc_start(struct rtw89_dev *rtwdev)
+{
+	if (rtwdev->scanning)
+		rtw89_hw_scan_abort(rtwdev, rtwdev->scan_info.scanning_vif);
+
+	rtw89_leave_lps(rtwdev);
+
+	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "MCC start\n");
+	rtw89_chanctx_notify(rtwdev, RTW89_CHANCTX_STATE_MCC_START);
+	return 0;
+}
+
+static void rtw89_mcc_stop(struct rtw89_dev *rtwdev)
+{
+	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "MCC stop\n");
+	rtw89_chanctx_notify(rtwdev, RTW89_CHANCTX_STATE_MCC_STOP);
+}
+
+void rtw89_chanctx_work(struct work_struct *work)
+{
+	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
+						chanctx_work.work);
+	enum rtw89_entity_mode mode;
+	int ret;
+
+	mutex_lock(&rtwdev->mutex);
+
+	mode = rtw89_get_entity_mode(rtwdev);
+	switch (mode) {
+	case RTW89_ENTITY_MODE_MCC_PREPARE:
+		rtw89_set_entity_mode(rtwdev, RTW89_ENTITY_MODE_MCC);
+		rtw89_set_channel(rtwdev);
+
+		ret = rtw89_mcc_start(rtwdev);
+		if (ret)
+			rtw89_warn(rtwdev, "failed to start MCC: %d\n", ret);
+		break;
+	default:
+		break;
+	}
+
+	mutex_unlock(&rtwdev->mutex);
+}
+
+void rtw89_queue_chanctx_work(struct rtw89_dev *rtwdev)
+{
+	enum rtw89_entity_mode mode;
+	u32 delay;
+
+	mode = rtw89_get_entity_mode(rtwdev);
+	switch (mode) {
+	default:
+		return;
+	case RTW89_ENTITY_MODE_MCC_PREPARE:
+		delay = ieee80211_tu_to_usec(RTW89_CHANCTX_TIME_MCC_PREPARE);
+		break;
+	}
+
+	rtw89_debug(rtwdev, RTW89_DBG_CHAN,
+		    "queue chanctx work for mode %d with delay %d us\n",
+		    mode, delay);
+	ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->chanctx_work,
+				     usecs_to_jiffies(delay));
+}
+
 int rtw89_chanctx_ops_add(struct rtw89_dev *rtwdev,
 			  struct ieee80211_chanctx_conf *ctx)
 {
@@ -238,6 +352,7 @@ void rtw89_chanctx_ops_remove(struct rtw89_dev *rtwdev,
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
 	struct rtw89_chanctx_cfg *cfg = (struct rtw89_chanctx_cfg *)ctx->drv_priv;
+	enum rtw89_entity_mode mode;
 	struct rtw89_vif *rtwvif;
 	u8 drop, roll;
 
@@ -267,6 +382,15 @@ void rtw89_chanctx_ops_remove(struct rtw89_dev *rtwdev,
 	drop = roll;
 
 out:
+	mode = rtw89_get_entity_mode(rtwdev);
+	switch (mode) {
+	case RTW89_ENTITY_MODE_MCC:
+		rtw89_mcc_stop(rtwdev);
+		break;
+	default:
+		break;
+	}
+
 	clear_bit(drop, hal->entity_map);
 	rtw89_set_channel(rtwdev);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/chan.h b/drivers/net/wireless/realtek/rtw89/chan.h
index bdf369db50417..448e6c5df9f18 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.h
+++ b/drivers/net/wireless/realtek/rtw89/chan.h
@@ -7,6 +7,9 @@
 
 #include "core.h"
 
+/* The dwell time in TU before doing rtw89_chanctx_work(). */
+#define RTW89_CHANCTX_TIME_MCC_PREPARE 100
+
 static inline bool rtw89_get_entity_state(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
@@ -50,6 +53,8 @@ void rtw89_config_roc_chandef(struct rtw89_dev *rtwdev,
 			      const struct cfg80211_chan_def *chandef);
 void rtw89_entity_init(struct rtw89_dev *rtwdev);
 enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev);
+void rtw89_chanctx_work(struct work_struct *work);
+void rtw89_queue_chanctx_work(struct rtw89_dev *rtwdev);
 int rtw89_chanctx_ops_add(struct rtw89_dev *rtwdev,
 			  struct ieee80211_chanctx_conf *ctx);
 void rtw89_chanctx_ops_remove(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 91f9a587220b1..92fbbcd5dd3f1 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -256,8 +256,8 @@ void rtw89_get_default_chandef(struct cfg80211_chan_def *chandef)
 				NL80211_CHAN_NO_HT);
 }
 
-static void rtw89_get_channel_params(const struct cfg80211_chan_def *chandef,
-				     struct rtw89_chan *chan)
+void rtw89_get_channel_params(const struct cfg80211_chan_def *chandef,
+			      struct rtw89_chan *chan)
 {
 	struct ieee80211_channel *channel = chandef->chan;
 	enum nl80211_chan_width width = chandef->width;
@@ -318,9 +318,11 @@ static void rtw89_get_channel_params(const struct cfg80211_chan_def *chandef,
 
 void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev)
 {
+	struct rtw89_hal *hal = &rtwdev->hal;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_chan *chan;
 	enum rtw89_sub_entity_idx sub_entity_idx;
+	enum rtw89_sub_entity_idx roc_idx;
 	enum rtw89_phy_idx phy_idx;
 	enum rtw89_entity_mode mode;
 	bool entity_active;
@@ -330,10 +332,23 @@ void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev)
 		return;
 
 	mode = rtw89_get_entity_mode(rtwdev);
-	if (WARN(mode != RTW89_ENTITY_MODE_SCC, "Invalid ent mode: %d\n", mode))
+	switch (mode) {
+	case RTW89_ENTITY_MODE_SCC:
+	case RTW89_ENTITY_MODE_MCC:
+		sub_entity_idx = RTW89_SUB_ENTITY_0;
+		break;
+	case RTW89_ENTITY_MODE_MCC_PREPARE:
+		sub_entity_idx = RTW89_SUB_ENTITY_1;
+		break;
+	default:
+		WARN(1, "Invalid ent mode: %d\n", mode);
 		return;
+	}
+
+	roc_idx = atomic_read(&hal->roc_entity_idx);
+	if (roc_idx != RTW89_SUB_ENTITY_IDLE)
+		sub_entity_idx = roc_idx;
 
-	sub_entity_idx = RTW89_SUB_ENTITY_0;
 	phy_idx = RTW89_PHY_0;
 	chan = rtw89_chan_get(rtwdev, sub_entity_idx);
 	chip->ops->set_txpwr(rtwdev, chan, phy_idx);
@@ -341,43 +356,54 @@ void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev)
 
 void rtw89_set_channel(struct rtw89_dev *rtwdev)
 {
+	struct rtw89_hal *hal = &rtwdev->hal;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
-	const struct cfg80211_chan_def *chandef;
+	const struct rtw89_chan_rcd *chan_rcd;
+	const struct rtw89_chan *chan;
 	enum rtw89_sub_entity_idx sub_entity_idx;
+	enum rtw89_sub_entity_idx roc_idx;
 	enum rtw89_mac_idx mac_idx;
 	enum rtw89_phy_idx phy_idx;
-	struct rtw89_chan chan;
 	struct rtw89_channel_help_params bak;
 	enum rtw89_entity_mode mode;
-	bool band_changed;
 	bool entity_active;
 
 	entity_active = rtw89_get_entity_state(rtwdev);
 
 	mode = rtw89_entity_recalc(rtwdev);
-	if (WARN(mode != RTW89_ENTITY_MODE_SCC, "Invalid ent mode: %d\n", mode))
+	switch (mode) {
+	case RTW89_ENTITY_MODE_SCC:
+	case RTW89_ENTITY_MODE_MCC:
+		sub_entity_idx = RTW89_SUB_ENTITY_0;
+		break;
+	case RTW89_ENTITY_MODE_MCC_PREPARE:
+		sub_entity_idx = RTW89_SUB_ENTITY_1;
+		break;
+	default:
+		WARN(1, "Invalid ent mode: %d\n", mode);
 		return;
+	}
+
+	roc_idx = atomic_read(&hal->roc_entity_idx);
+	if (roc_idx != RTW89_SUB_ENTITY_IDLE)
+		sub_entity_idx = roc_idx;
 
-	sub_entity_idx = RTW89_SUB_ENTITY_0;
 	mac_idx = RTW89_MAC_0;
 	phy_idx = RTW89_PHY_0;
-	chandef = rtw89_chandef_get(rtwdev, sub_entity_idx);
-	rtw89_get_channel_params(chandef, &chan);
-	if (WARN(chan.channel == 0, "Invalid channel\n"))
-		return;
 
-	band_changed = rtw89_assign_entity_chan(rtwdev, sub_entity_idx, &chan);
+	chan = rtw89_chan_get(rtwdev, sub_entity_idx);
+	chan_rcd = rtw89_chan_rcd_get(rtwdev, sub_entity_idx);
 
-	rtw89_chip_set_channel_prepare(rtwdev, &bak, &chan, mac_idx, phy_idx);
+	rtw89_chip_set_channel_prepare(rtwdev, &bak, chan, mac_idx, phy_idx);
 
-	chip->ops->set_channel(rtwdev, &chan, mac_idx, phy_idx);
+	chip->ops->set_channel(rtwdev, chan, mac_idx, phy_idx);
 
-	chip->ops->set_txpwr(rtwdev, &chan, phy_idx);
+	chip->ops->set_txpwr(rtwdev, chan, phy_idx);
 
-	rtw89_chip_set_channel_done(rtwdev, &bak, &chan, mac_idx, phy_idx);
+	rtw89_chip_set_channel_done(rtwdev, &bak, chan, mac_idx, phy_idx);
 
-	if (!entity_active || band_changed) {
-		rtw89_btc_ntfy_switch_band(rtwdev, phy_idx, chan.band_type);
+	if (!entity_active || chan_rcd->band_changed) {
+		rtw89_btc_ntfy_switch_band(rtwdev, phy_idx, chan->band_type);
 		rtw89_chip_rfk_band_changed(rtwdev, phy_idx);
 	}
 
@@ -3562,6 +3588,7 @@ void rtw89_core_stop(struct rtw89_dev *rtwdev)
 	cancel_work_sync(&btc->icmp_notify_work);
 	cancel_delayed_work_sync(&rtwdev->txq_reinvoke_work);
 	cancel_delayed_work_sync(&rtwdev->track_work);
+	cancel_delayed_work_sync(&rtwdev->chanctx_work);
 	cancel_delayed_work_sync(&rtwdev->coex_act1_work);
 	cancel_delayed_work_sync(&rtwdev->coex_bt_devinfo_work);
 	cancel_delayed_work_sync(&rtwdev->coex_rfk_chk_work);
@@ -3598,6 +3625,7 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 	INIT_WORK(&rtwdev->txq_work, rtw89_core_txq_work);
 	INIT_DELAYED_WORK(&rtwdev->txq_reinvoke_work, rtw89_core_txq_reinvoke_work);
 	INIT_DELAYED_WORK(&rtwdev->track_work, rtw89_track_work);
+	INIT_DELAYED_WORK(&rtwdev->chanctx_work, rtw89_chanctx_work);
 	INIT_DELAYED_WORK(&rtwdev->coex_act1_work, rtw89_coex_act1_work);
 	INIT_DELAYED_WORK(&rtwdev->coex_bt_devinfo_work, rtw89_coex_bt_devinfo_work);
 	INIT_DELAYED_WORK(&rtwdev->coex_rfk_chk_work, rtw89_coex_rfk_chk_work);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 431b0d3daa2a2..284d8f7a7a0c1 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -789,6 +789,7 @@ enum rtw89_phy_idx {
 
 enum rtw89_sub_entity_idx {
 	RTW89_SUB_ENTITY_0 = 0,
+	RTW89_SUB_ENTITY_1 = 1,
 
 	NUM_OF_RTW89_SUB_ENTITY,
 	RTW89_SUB_ENTITY_IDLE = NUM_OF_RTW89_SUB_ENTITY,
@@ -900,6 +901,7 @@ struct rtw89_chan {
 struct rtw89_chan_rcd {
 	u8 prev_primary_channel;
 	enum rtw89_band prev_band_type;
+	bool band_changed;
 };
 
 struct rtw89_channel_help_params {
@@ -3413,6 +3415,22 @@ struct rtw89_antdiv_info {
 	bool get_stats;
 };
 
+enum rtw89_chanctx_state {
+	RTW89_CHANCTX_STATE_MCC_START,
+	RTW89_CHANCTX_STATE_MCC_STOP,
+};
+
+enum rtw89_chanctx_callbacks {
+	RTW89_CHANCTX_CALLBACK_PLACEHOLDER,
+
+	NUM_OF_RTW89_CHANCTX_CALLBACKS,
+};
+
+struct rtw89_chanctx_listener {
+	void (*callbacks[NUM_OF_RTW89_CHANCTX_CALLBACKS])
+		(struct rtw89_dev *rtwdev, enum rtw89_chanctx_state state);
+};
+
 struct rtw89_chip_info {
 	enum rtw89_core_chip_id chip_id;
 	enum rtw89_chip_gen chip_gen;
@@ -3472,6 +3490,7 @@ struct rtw89_chip_info {
 	/* NULL if no rfe-specific, or a null-terminated array by rfe_parms */
 	const struct rtw89_rfe_parms_conf *rfe_parms_conf;
 	const struct rtw89_rfe_parms *dflt_parms;
+	const struct rtw89_chanctx_listener *chanctx_listener;
 
 	u8 txpwr_factor_rf;
 	u8 txpwr_factor_mac;
@@ -3751,6 +3770,11 @@ struct rtw89_chanctx_cfg {
 
 enum rtw89_entity_mode {
 	RTW89_ENTITY_MODE_SCC,
+	RTW89_ENTITY_MODE_MCC_PREPARE,
+	RTW89_ENTITY_MODE_MCC,
+
+	NUM_OF_RTW89_ENTITY_MODE,
+	RTW89_ENTITY_MODE_INVALID = NUM_OF_RTW89_ENTITY_MODE,
 };
 
 struct rtw89_sub_entity {
@@ -4407,6 +4431,7 @@ struct rtw89_dev {
 	struct rtw89_antdiv_info antdiv;
 
 	struct delayed_work track_work;
+	struct delayed_work chanctx_work;
 	struct delayed_work coex_act1_work;
 	struct delayed_work coex_bt_devinfo_work;
 	struct delayed_work coex_rfk_chk_work;
@@ -5341,6 +5366,8 @@ struct rtw89_dev *rtw89_alloc_ieee80211_hw(struct device *device,
 void rtw89_free_ieee80211_hw(struct rtw89_dev *rtwdev);
 void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev);
 void rtw89_get_default_chandef(struct cfg80211_chan_def *chandef);
+void rtw89_get_channel_params(const struct cfg80211_chan_def *chandef,
+			      struct rtw89_chan *chan);
 void rtw89_set_channel(struct rtw89_dev *rtwdev);
 void rtw89_get_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 		       struct rtw89_chan *chan);
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 7c3066c0a5501..c9ed369015fef 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -414,6 +414,8 @@ static void rtw89_ops_bss_info_changed(struct ieee80211_hw *hw,
 			rtw89_chip_cfg_txpwr_ul_tb_offset(rtwdev, vif);
 			rtw89_mac_port_update(rtwdev, rtwvif);
 			rtw89_mac_set_he_obss_narrow_bw_ru(rtwdev, vif);
+
+			rtw89_queue_chanctx_work(rtwdev);
 		} else {
 			/* Abort ongoing scan if cancel_scan isn't issued
 			 * when disconnected by peer
@@ -477,6 +479,8 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
 	rtw89_fw_h2c_join_info(rtwdev, rtwvif, NULL, true);
 	rtw89_fw_h2c_cam(rtwdev, rtwvif, NULL, NULL);
 	rtw89_chip_rfk_channel(rtwdev);
+
+	rtw89_queue_chanctx_work(rtwdev);
 	mutex_unlock(&rtwdev->mutex);
 
 	return 0;
diff --git a/drivers/net/wireless/realtek/rtw89/ps.c b/drivers/net/wireless/realtek/rtw89/ps.c
index b98ec178abe12..917c01e5e9eda 100644
--- a/drivers/net/wireless/realtek/rtw89/ps.c
+++ b/drivers/net/wireless/realtek/rtw89/ps.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2019-2020  Realtek Corporation
  */
 
+#include "chan.h"
 #include "coex.h"
 #include "core.h"
 #include "debug.h"
@@ -257,8 +258,13 @@ void rtw89_recalc_lps(struct rtw89_dev *rtwdev)
 {
 	struct ieee80211_vif *vif, *found_vif = NULL;
 	struct rtw89_vif *rtwvif;
+	enum rtw89_entity_mode mode;
 	int count = 0;
 
+	mode = rtw89_get_entity_mode(rtwdev);
+	if (mode == RTW89_ENTITY_MODE_MCC)
+		goto disable_lps;
+
 	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
 		vif = rtwvif_to_vif(rtwvif);
 
@@ -273,10 +279,12 @@ void rtw89_recalc_lps(struct rtw89_dev *rtwdev)
 
 	if (count == 1 && found_vif->cfg.ps) {
 		rtwdev->lps_enabled = true;
-	} else {
-		rtw89_leave_lps(rtwdev);
-		rtwdev->lps_enabled = false;
+		return;
 	}
+
+disable_lps:
+	rtw89_leave_lps(rtwdev);
+	rtwdev->lps_enabled = false;
 }
 
 void rtw89_p2p_noa_renew(struct rtw89_vif *rtwvif)
-- 
GitLab


From 98fdd77d3df7ba269941f9a262d82a31537cf013 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Mon, 21 Aug 2023 22:03:45 +0800
Subject: [PATCH 1685/1806] wifi: wlcore: sdio: Use module_sdio_driver macro to
 simplify the code

Use the module_sdio_driver macro to simplify the code, which is the
same as declaring with module_init() and module_exit().

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230821140345.3140493-1-lizetao1@huawei.com
---
 drivers/net/wireless/ti/wlcore/sdio.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c
index cf8d909fa8261..f0686635db46e 100644
--- a/drivers/net/wireless/ti/wlcore/sdio.c
+++ b/drivers/net/wireless/ti/wlcore/sdio.c
@@ -442,18 +442,7 @@ static struct sdio_driver wl1271_sdio_driver = {
 #endif
 };
 
-static int __init wl1271_init(void)
-{
-	return sdio_register_driver(&wl1271_sdio_driver);
-}
-
-static void __exit wl1271_exit(void)
-{
-	sdio_unregister_driver(&wl1271_sdio_driver);
-}
-
-module_init(wl1271_init);
-module_exit(wl1271_exit);
+module_sdio_driver(wl1271_sdio_driver);
 
 module_param(dump, bool, 0600);
 MODULE_PARM_DESC(dump, "Enable sdio read/write dumps.");
-- 
GitLab


From c220d08e1f981c8d381874a55c3c3c76ade43393 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 22 Aug 2023 20:58:17 +0800
Subject: [PATCH 1686/1806] wifi: rtw89: mac: add mac_gen_def::band1_offset to
 map MAC band1 register address

There are two copies of MAC hardware called band0 and band1. Basically,
the only difference between them is base address, so we can share functions
with a 'band' (or 'mac_idx') argument.

The offset of base address of WiFi 6 and 7 are 0x2000 and 0x4000
respectively, so add band1_offset field to new introduced struct
mac_gen_def to possibly reuse functions.

Using below spatch script to convert callers:

  @@
  expression reg, band;
  @@
  - rtw89_mac_reg_by_idx(reg, band)
  + rtw89_mac_reg_by_idx(rtwdev, reg, band)

  @@
  expression reg, port, band;
  @@
  - rtw89_mac_reg_by_port(reg, port, band)
  + rtw89_mac_reg_by_port(rtwdev, reg, port, band)

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230822125822.23817-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c     |   4 +-
 drivers/net/wireless/realtek/rtw89/core.h     |   2 +
 drivers/net/wireless/realtek/rtw89/fw.c       |   4 +-
 drivers/net/wireless/realtek/rtw89/mac.c      | 171 +++++++++---------
 drivers/net/wireless/realtek/rtw89/mac.h      |  36 ++--
 drivers/net/wireless/realtek/rtw89/mac80211.c |   6 +-
 drivers/net/wireless/realtek/rtw89/mac_be.c   |  10 +
 drivers/net/wireless/realtek/rtw89/phy.c      |   6 +-
 drivers/net/wireless/realtek/rtw89/rtw8851b.c |  13 +-
 drivers/net/wireless/realtek/rtw89/rtw8852a.c |  14 +-
 drivers/net/wireless/realtek/rtw89/rtw8852b.c |  13 +-
 drivers/net/wireless/realtek/rtw89/rtw8852c.c |  19 +-
 12 files changed, 165 insertions(+), 133 deletions(-)
 create mode 100644 drivers/net/wireless/realtek/rtw89/mac_be.c

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 92fbbcd5dd3f1..eca973b95fbb3 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -2504,7 +2504,7 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_config_roc_chandef(rtwdev, rtwvif->sub_entity_idx, &roc_chan);
 	rtw89_set_channel(rtwdev);
 	rtw89_write32_clr(rtwdev,
-			  rtw89_mac_reg_by_idx(R_AX_RX_FLTR_OPT, RTW89_MAC_0),
+			  rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_0),
 			  B_AX_A_UC_CAM_MATCH | B_AX_A_BC_CAM_MATCH);
 
 	ieee80211_ready_on_channel(hw);
@@ -2525,7 +2525,7 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_leave_lps(rtwdev);
 
 	rtw89_write32_mask(rtwdev,
-			   rtw89_mac_reg_by_idx(R_AX_RX_FLTR_OPT, RTW89_MAC_0),
+			   rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_0),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rtwdev->hal.rx_fltr);
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 284d8f7a7a0c1..2806d1cf2c0d6 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -14,6 +14,7 @@
 
 struct rtw89_dev;
 struct rtw89_pci_info;
+struct rtw89_mac_gen_def;
 
 extern const struct ieee80211_ops rtw89_ops;
 
@@ -3435,6 +3436,7 @@ struct rtw89_chip_info {
 	enum rtw89_core_chip_id chip_id;
 	enum rtw89_chip_gen chip_gen;
 	const struct rtw89_chip_ops *ops;
+	const struct rtw89_mac_gen_def *mac_def;
 	const char *fw_basename;
 	u8 fw_format_max;
 	bool try_ce_fw;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 772b0f107f40e..ba873a5d1a8d5 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -3885,7 +3885,7 @@ void rtw89_hw_scan_start(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 	rx_fltr &= ~B_AX_A_BC;
 	rx_fltr &= ~B_AX_A_A1_MATCH;
 	rtw89_write32_mask(rtwdev,
-			   rtw89_mac_reg_by_idx(R_AX_RX_FLTR_OPT, RTW89_MAC_0),
+			   rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_0),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rx_fltr);
 }
@@ -3903,7 +3903,7 @@ void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 		return;
 
 	rtw89_write32_mask(rtwdev,
-			   rtw89_mac_reg_by_idx(R_AX_RX_FLTR_OPT, RTW89_MAC_0),
+			   rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_0),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rtwdev->hal.rx_fltr);
 
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index cebefa3b1db3e..edfa1a2e677aa 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -2082,7 +2082,7 @@ static int addr_cam_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	if (ret)
 		return ret;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_ADDR_CAM_CTRL, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_ADDR_CAM_CTRL, mac_idx);
 
 	val = rtw89_read32(rtwdev, reg);
 	val |= u32_encode_bits(0x7f, B_AX_ADDR_CAM_RANGE_MASK) |
@@ -2109,7 +2109,7 @@ static int scheduler_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	if (ret)
 		return ret;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_PREBKF_CFG_1, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PREBKF_CFG_1, mac_idx);
 	if (rtwdev->chip->chip_id == RTL8852C)
 		rtw89_write32_mask(rtwdev, reg, B_AX_SIFS_MACTXEN_T1_MASK,
 				   SIFS_MACTXEN_T1_V1);
@@ -2118,14 +2118,14 @@ static int scheduler_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 				   SIFS_MACTXEN_T1);
 
 	if (rtwdev->chip->chip_id == RTL8852B || rtwdev->chip->chip_id == RTL8851B) {
-		reg = rtw89_mac_reg_by_idx(R_AX_SCH_EXT_CTRL, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_SCH_EXT_CTRL, mac_idx);
 		rtw89_write32_set(rtwdev, reg, B_AX_PORT_RST_TSF_ADV);
 	}
 
-	reg = rtw89_mac_reg_by_idx(R_AX_CCA_CFG_0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_CCA_CFG_0, mac_idx);
 	rtw89_write32_clr(rtwdev, reg, B_AX_BTCCA_EN);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_PREBKF_CFG_0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PREBKF_CFG_0, mac_idx);
 	if (rtwdev->chip->chip_id == RTL8852C) {
 		val = rtw89_read32_mask(rtwdev, R_AX_SEC_ENG_CTRL,
 					B_AX_TX_PARTIAL_MODE);
@@ -2165,13 +2165,13 @@ int rtw89_mac_typ_fltr_opt(struct rtw89_dev *rtwdev,
 
 	switch (type) {
 	case RTW89_MGNT:
-		reg = rtw89_mac_reg_by_idx(R_AX_MGNT_FLTR, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_MGNT_FLTR, mac_idx);
 		break;
 	case RTW89_CTRL:
-		reg = rtw89_mac_reg_by_idx(R_AX_CTRL_FLTR, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_CTRL_FLTR, mac_idx);
 		break;
 	case RTW89_DATA:
-		reg = rtw89_mac_reg_by_idx(R_AX_DATA_FLTR, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_DATA_FLTR, mac_idx);
 		break;
 	default:
 		rtw89_err(rtwdev, "[ERR]set rx filter type err\n");
@@ -2202,9 +2202,9 @@ static int rx_fltr_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 		    B_AX_LSIG_PARITY_CHK_EN | B_AX_SIGA_CRC_CHK |
 		    B_AX_VHT_SU_SIGB_CRC_CHK | B_AX_VHT_MU_SIGB_CRC_CHK |
 		    B_AX_HE_SIGB_CRC_CHK;
-	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(R_AX_RX_FLTR_OPT, mac_idx),
+	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, mac_idx),
 		      mac_ftlr);
-	rtw89_write16(rtwdev, rtw89_mac_reg_by_idx(R_AX_PLCP_HDR_FLTR, mac_idx),
+	rtw89_write16(rtwdev, rtw89_mac_reg_by_idx(rtwdev, R_AX_PLCP_HDR_FLTR, mac_idx),
 		      plcp_ftlr);
 
 	return 0;
@@ -2224,20 +2224,20 @@ static void _patch_dis_resp_chk(struct rtw89_dev *rtwdev, u8 mac_idx)
 	switch (rtwdev->chip->chip_id) {
 	case RTL8852A:
 	case RTL8852B:
-		reg = rtw89_mac_reg_by_idx(R_AX_RSP_CHK_SIG, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_RSP_CHK_SIG, mac_idx);
 		val32 = rtw89_read32(rtwdev, reg) & ~b_rsp_chk_nav;
 		rtw89_write32(rtwdev, reg, val32);
 
-		reg = rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_0, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_0, mac_idx);
 		val32 = rtw89_read32(rtwdev, reg) & ~b_rsp_chk_cca;
 		rtw89_write32(rtwdev, reg, val32);
 		break;
 	default:
-		reg = rtw89_mac_reg_by_idx(R_AX_RSP_CHK_SIG, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_RSP_CHK_SIG, mac_idx);
 		val32 = rtw89_read32(rtwdev, reg) | b_rsp_chk_nav;
 		rtw89_write32(rtwdev, reg, val32);
 
-		reg = rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_0, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_0, mac_idx);
 		val32 = rtw89_read32(rtwdev, reg) | b_rsp_chk_cca;
 		rtw89_write32(rtwdev, reg, val32);
 		break;
@@ -2253,7 +2253,7 @@ static int cca_ctrl_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	if (ret)
 		return ret;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_CCA_CONTROL, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_CCA_CONTROL, mac_idx);
 	val = rtw89_read32(rtwdev, reg);
 	val |= (B_AX_TB_CHK_BASIC_NAV | B_AX_TB_CHK_BTCCA |
 		B_AX_TB_CHK_EDCCA | B_AX_TB_CHK_CCA_P20 |
@@ -2294,7 +2294,7 @@ static int spatial_reuse_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
 	if (ret)
 		return ret;
-	reg = rtw89_mac_reg_by_idx(R_AX_RX_SR_CTRL, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_SR_CTRL, mac_idx);
 	rtw89_write8_clr(rtwdev, reg, B_AX_SR_EN);
 
 	return 0;
@@ -2309,13 +2309,13 @@ static int tmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	if (ret)
 		return ret;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_MAC_LOOPBACK, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_MAC_LOOPBACK, mac_idx);
 	rtw89_write32_clr(rtwdev, reg, B_AX_MACLBK_EN);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_TCR0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TCR0, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_TCR_UDF_THSD_MASK, TCR_UDF_THSD);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_TXD_FIFO_CTRL, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TXD_FIFO_CTRL, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_TXDFIFO_HIGH_MCS_THRE_MASK, TXDFIFO_HIGH_MCS_THRE);
 	rtw89_write32_mask(rtwdev, reg, B_AX_TXDFIFO_LOW_MCS_THRE_MASK, TXDFIFO_LOW_MCS_THRE);
 
@@ -2333,7 +2333,7 @@ static int trxptcl_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	if (ret)
 		return ret;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_0, mac_idx);
 	val = rtw89_read32(rtwdev, reg);
 	val &= ~B_AX_WMAC_SPEC_SIFS_CCK_MASK;
 	val |= FIELD_PREP(B_AX_WMAC_SPEC_SIFS_CCK_MASK, WMAC_SPEC_SIFS_CCK);
@@ -2353,12 +2353,12 @@ static int trxptcl_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	val |= FIELD_PREP(B_AX_WMAC_SPEC_SIFS_OFDM_MASK, sifs);
 	rtw89_write32(rtwdev, reg, val);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_RXTRIG_TEST_USER_2, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_RXTRIG_TEST_USER_2, mac_idx);
 	rtw89_write32_set(rtwdev, reg, B_AX_RXTRIG_FCSCHK_EN);
 
-	reg = rtw89_mac_reg_by_idx(rrsr->ref_rate.addr, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, rrsr->ref_rate.addr, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, rrsr->ref_rate.mask, rrsr->ref_rate.data);
-	reg = rtw89_mac_reg_by_idx(rrsr->rsc.addr, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, rrsr->rsc.addr, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, rrsr->rsc.mask, rrsr->rsc.data);
 
 	return 0;
@@ -2397,10 +2397,10 @@ static int rmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	if (mac_idx == RTW89_MAC_0)
 		rst_bacam(rtwdev);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_RESPBA_CAM_CTRL, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_RESPBA_CAM_CTRL, mac_idx);
 	rtw89_write8_set(rtwdev, reg, B_AX_SSN_SEL);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_DLK_PROTECT_CTL, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_DLK_PROTECT_CTL, mac_idx);
 	val = rtw89_read16(rtwdev, reg);
 	val = u16_replace_bits(val, TRXCFG_RMAC_DATA_TO,
 			       B_AX_RX_DLK_DATA_TIME_MASK);
@@ -2408,10 +2408,10 @@ static int rmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 			       B_AX_RX_DLK_CCA_TIME_MASK);
 	rtw89_write16(rtwdev, reg, val);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_RCR, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_RCR, mac_idx);
 	rtw89_write8_mask(rtwdev, reg, B_AX_CH_EN_MASK, 0x1);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_RX_FLTR_OPT, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, mac_idx);
 	if (mac_idx == RTW89_MAC_0)
 		rx_qta = rtwdev->mac.dle_info.c0_rx_qta;
 	else
@@ -2425,13 +2425,13 @@ static int rmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	if (rtwdev->chip->chip_id == RTL8852A &&
 	    rtwdev->hal.cv == CHIP_CBV) {
 		rtw89_write16_mask(rtwdev,
-				   rtw89_mac_reg_by_idx(R_AX_DLK_PROTECT_CTL, mac_idx),
+				   rtw89_mac_reg_by_idx(rtwdev, R_AX_DLK_PROTECT_CTL, mac_idx),
 				   B_AX_RX_DLK_CCA_TIME_MASK, 0);
-		rtw89_write16_set(rtwdev, rtw89_mac_reg_by_idx(R_AX_RCR, mac_idx),
+		rtw89_write16_set(rtwdev, rtw89_mac_reg_by_idx(rtwdev, R_AX_RCR, mac_idx),
 				  BIT(12));
 	}
 
-	reg = rtw89_mac_reg_by_idx(R_AX_PLCP_HDR_FLTR, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PLCP_HDR_FLTR, mac_idx);
 	rtw89_write8_clr(rtwdev, reg, B_AX_VHT_SU_SIGB_CRC_CHK);
 
 	return ret;
@@ -2447,7 +2447,7 @@ static int cmac_com_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	if (ret)
 		return ret;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_TX_SUB_CARRIER_VALUE, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TX_SUB_CARRIER_VALUE, mac_idx);
 	val = rtw89_read32(rtwdev, reg);
 	val = u32_replace_bits(val, 0, B_AX_TXSC_20M_MASK);
 	val = u32_replace_bits(val, 0, B_AX_TXSC_40M_MASK);
@@ -2455,7 +2455,7 @@ static int cmac_com_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	rtw89_write32(rtwdev, reg, val);
 
 	if (chip_id == RTL8852A || chip_id == RTL8852B) {
-		reg = rtw89_mac_reg_by_idx(R_AX_PTCL_RRSR1, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PTCL_RRSR1, mac_idx);
 		rtw89_write32_mask(rtwdev, reg, B_AX_RRSR_RATE_EN_MASK, RRSR_OFDM_CCK_EN);
 	}
 
@@ -2485,7 +2485,7 @@ static int ptcl_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 		return ret;
 
 	if (rtwdev->hci.type == RTW89_HCI_TYPE_PCIE) {
-		reg = rtw89_mac_reg_by_idx(R_AX_SIFS_SETTING, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_SIFS_SETTING, mac_idx);
 		val = rtw89_read32(rtwdev, reg);
 		val = u32_replace_bits(val, S_AX_CTS2S_TH_1K,
 				       B_AX_HW_CTS2SELF_PKT_LEN_TH_MASK);
@@ -2494,7 +2494,7 @@ static int ptcl_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 		val |= B_AX_HW_CTS2SELF_EN;
 		rtw89_write32(rtwdev, reg, val);
 
-		reg = rtw89_mac_reg_by_idx(R_AX_PTCL_FSM_MON, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PTCL_FSM_MON, mac_idx);
 		val = rtw89_read32(rtwdev, reg);
 		val = u32_replace_bits(val, S_AX_PTCL_TO_2MS, B_AX_PTCL_TX_ARB_TO_THR_MASK);
 		val &= ~B_AX_PTCL_TX_ARB_TO_MODE;
@@ -2531,7 +2531,7 @@ static int cmac_dma_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	if (ret)
 		return ret;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_RXDMA_CTRL_0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_RXDMA_CTRL_0, mac_idx);
 	rtw89_write8_clr(rtwdev, reg, RX_FULL_MODE);
 
 	return 0;
@@ -2725,7 +2725,7 @@ static int rtw89_hw_sch_tx_en_h2c(struct rtw89_dev *rtwdev, u8 band,
 static int rtw89_set_hw_sch_tx_en(struct rtw89_dev *rtwdev, u8 mac_idx,
 				  u16 tx_en, u16 tx_en_mask)
 {
-	u32 reg = rtw89_mac_reg_by_idx(R_AX_CTN_TXEN, mac_idx);
+	u32 reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_CTN_TXEN, mac_idx);
 	u16 val;
 	int ret;
 
@@ -2747,7 +2747,7 @@ static int rtw89_set_hw_sch_tx_en(struct rtw89_dev *rtwdev, u8 mac_idx,
 static int rtw89_set_hw_sch_tx_en_v1(struct rtw89_dev *rtwdev, u8 mac_idx,
 				     u32 tx_en, u32 tx_en_mask)
 {
-	u32 reg = rtw89_mac_reg_by_idx(R_AX_CTN_DRV_TXEN, mac_idx);
+	u32 reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_CTN_DRV_TXEN, mac_idx);
 	u32 val;
 	int ret;
 
@@ -2768,7 +2768,7 @@ int rtw89_mac_stop_sch_tx(struct rtw89_dev *rtwdev, u8 mac_idx,
 	int ret;
 
 	*tx_en = rtw89_read16(rtwdev,
-			      rtw89_mac_reg_by_idx(R_AX_CTN_TXEN, mac_idx));
+			      rtw89_mac_reg_by_idx(rtwdev, R_AX_CTN_TXEN, mac_idx));
 
 	switch (sel) {
 	case RTW89_SCH_TX_SEL_ALL:
@@ -2809,7 +2809,7 @@ int rtw89_mac_stop_sch_tx_v1(struct rtw89_dev *rtwdev, u8 mac_idx,
 	int ret;
 
 	*tx_en = rtw89_read32(rtwdev,
-			      rtw89_mac_reg_by_idx(R_AX_CTN_DRV_TXEN, mac_idx));
+			      rtw89_mac_reg_by_idx(rtwdev, R_AX_CTN_DRV_TXEN, mac_idx));
 
 	switch (sel) {
 	case RTW89_SCH_TX_SEL_ALL:
@@ -3016,7 +3016,7 @@ static int band_idle_ck_b(struct rtw89_dev *rtwdev, u8 mac_idx)
 	if (ret)
 		return ret;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_PTCL_TX_CTN_SEL, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PTCL_TX_CTN_SEL, mac_idx);
 
 	ret = read_poll_timeout(rtw89_read8, val,
 				(val & B_AX_PTCL_TX_ON_STAT) == 0,
@@ -3224,7 +3224,7 @@ static void rtw89_scheduler_imr_enable(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_SCHEDULE_ERR_IMR, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_SCHEDULE_ERR_IMR, mac_idx);
 	rtw89_write32_clr(rtwdev, reg, B_AX_SORT_NON_IDLE_ERR_INT_EN |
 				       B_AX_FSM_TIMEOUT_ERR_INT_EN);
 	rtw89_write32_set(rtwdev, reg, B_AX_FSM_TIMEOUT_ERR_INT_EN);
@@ -3235,7 +3235,7 @@ static void rtw89_ptcl_imr_enable(struct rtw89_dev *rtwdev, u8 mac_idx)
 	const struct rtw89_imr_info *imr = rtwdev->chip->imr_info;
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_PTCL_IMR0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PTCL_IMR0, mac_idx);
 	rtw89_write32_clr(rtwdev, reg, imr->ptcl_imr_clr);
 	rtw89_write32_set(rtwdev, reg, imr->ptcl_imr_set);
 }
@@ -3246,12 +3246,12 @@ static void rtw89_cdma_imr_enable(struct rtw89_dev *rtwdev, u8 mac_idx)
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_idx(imr->cdma_imr_0_reg, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, imr->cdma_imr_0_reg, mac_idx);
 	rtw89_write32_clr(rtwdev, reg, imr->cdma_imr_0_clr);
 	rtw89_write32_set(rtwdev, reg, imr->cdma_imr_0_set);
 
 	if (chip_id == RTL8852C) {
-		reg = rtw89_mac_reg_by_idx(imr->cdma_imr_1_reg, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, imr->cdma_imr_1_reg, mac_idx);
 		rtw89_write32_clr(rtwdev, reg, imr->cdma_imr_1_clr);
 		rtw89_write32_set(rtwdev, reg, imr->cdma_imr_1_set);
 	}
@@ -3262,7 +3262,7 @@ static void rtw89_phy_intf_imr_enable(struct rtw89_dev *rtwdev, u8 mac_idx)
 	const struct rtw89_imr_info *imr = rtwdev->chip->imr_info;
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_idx(imr->phy_intf_imr_reg, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, imr->phy_intf_imr_reg, mac_idx);
 	rtw89_write32_clr(rtwdev, reg, imr->phy_intf_imr_clr);
 	rtw89_write32_set(rtwdev, reg, imr->phy_intf_imr_set);
 }
@@ -3272,7 +3272,7 @@ static void rtw89_rmac_imr_enable(struct rtw89_dev *rtwdev, u8 mac_idx)
 	const struct rtw89_imr_info *imr = rtwdev->chip->imr_info;
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_idx(imr->rmac_imr_reg, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, imr->rmac_imr_reg, mac_idx);
 	rtw89_write32_clr(rtwdev, reg, imr->rmac_imr_clr);
 	rtw89_write32_set(rtwdev, reg, imr->rmac_imr_set);
 }
@@ -3282,7 +3282,7 @@ static void rtw89_tmac_imr_enable(struct rtw89_dev *rtwdev, u8 mac_idx)
 	const struct rtw89_imr_info *imr = rtwdev->chip->imr_info;
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_idx(imr->tmac_imr_reg, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, imr->tmac_imr_reg, mac_idx);
 	rtw89_write32_clr(rtwdev, reg, imr->tmac_imr_clr);
 	rtw89_write32_set(rtwdev, reg, imr->tmac_imr_set);
 }
@@ -3860,7 +3860,7 @@ static void rtw89_mac_port_cfg_hiq_win(struct rtw89_dev *rtwdev,
 	u8 port = rtwvif->port;
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_idx(hiq_win_addr[port], rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, hiq_win_addr[port], rtwvif->mac_idx);
 	rtw89_write8(rtwdev, reg, win);
 }
 
@@ -3871,7 +3871,7 @@ static void rtw89_mac_port_cfg_hiq_dtim(struct rtw89_dev *rtwdev,
 	const struct rtw89_port_reg *p = &rtw_port_base;
 	u32 addr;
 
-	addr = rtw89_mac_reg_by_idx(R_AX_MD_TSFT_STMP_CTL, rtwvif->mac_idx);
+	addr = rtw89_mac_reg_by_idx(rtwdev, R_AX_MD_TSFT_STMP_CTL, rtwvif->mac_idx);
 	rtw89_write8_set(rtwdev, addr, B_AX_UPD_HGQMD | B_AX_UPD_TIMIE);
 
 	rtw89_write16_port_mask(rtwdev, rtwvif, p->dtim_ctrl, B_AX_DTIM_NUM_MASK,
@@ -3930,7 +3930,7 @@ static void rtw89_mac_port_cfg_bss_color(struct rtw89_dev *rtwdev,
 
 	bss_color = vif->bss_conf.he_bss_color.color;
 	reg_base = port >= 4 ? R_AX_PTCL_BSS_COLOR_1 : R_AX_PTCL_BSS_COLOR_0;
-	reg = rtw89_mac_reg_by_idx(reg_base, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, reg_base, rtwvif->mac_idx);
 	rtw89_write32_mask(rtwdev, reg, masks[port], bss_color);
 }
 
@@ -3944,7 +3944,7 @@ static void rtw89_mac_port_cfg_mbssid(struct rtw89_dev *rtwdev,
 		return;
 
 	if (port == 0) {
-		reg = rtw89_mac_reg_by_idx(R_AX_MBSSID_CTRL, rtwvif->mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_MBSSID_CTRL, rtwvif->mac_idx);
 		rtw89_write32_clr(rtwdev, reg, B_AX_P0MB_ALL_MASK);
 	}
 }
@@ -3956,7 +3956,7 @@ static void rtw89_mac_port_cfg_hiq_drop(struct rtw89_dev *rtwdev,
 	u32 reg;
 	u32 val;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_MBSSID_DROP_0, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_MBSSID_DROP_0, rtwvif->mac_idx);
 	val = rtw89_read32(rtwdev, reg);
 	val &= ~FIELD_PREP(B_AX_PORT_DROP_4_0_MASK, BIT(port));
 	if (port == 0)
@@ -4014,7 +4014,7 @@ void rtw89_mac_port_tsf_sync(struct rtw89_dev *rtwdev,
 	u32 val, reg;
 
 	val = RTW89_PORT_OFFSET_TU_TO_32US(offset_tu);
-	reg = rtw89_mac_reg_by_idx(R_AX_PORT0_TSF_SYNC + rtwvif->port * 4,
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PORT0_TSF_SYNC + rtwvif->port * 4,
 				   rtwvif->mac_idx);
 
 	rtw89_write32_mask(rtwdev, reg, B_AX_SYNC_PORT_SRC, rtwvif_src->port);
@@ -4204,7 +4204,7 @@ void rtw89_mac_set_he_obss_narrow_bw_ru(struct rtw89_dev *rtwdev,
 			  rtw89_mac_check_he_obss_narrow_bw_ru_iter,
 			  &tolerated);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_RXTRIG_TEST_USER_2, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_RXTRIG_TEST_USER_2, rtwvif->mac_idx);
 	if (tolerated)
 		rtw89_write32_clr(rtwdev, reg, B_AX_RXTRIG_RU26_DIS);
 	else
@@ -4731,7 +4731,7 @@ bool rtw89_mac_get_txpwr_cr(struct rtw89_dev *rtwdev,
 {
 	const struct rtw89_dle_mem *dle_mem = rtwdev->chip->dle_mem;
 	enum rtw89_qta_mode mode = dle_mem->mode;
-	u32 addr = rtw89_mac_reg_by_idx(reg_base, phy_idx);
+	u32 addr = rtw89_mac_reg_by_idx(rtwdev, reg_base, phy_idx);
 
 	if (addr < R_AX_PWR_RATE_CTRL || addr > CMAC1_END_ADDR) {
 		rtw89_err(rtwdev, "[TXPWR] addr=0x%x exceed txpwr cr\n",
@@ -4760,7 +4760,7 @@ EXPORT_SYMBOL(rtw89_mac_get_txpwr_cr);
 
 int rtw89_mac_cfg_ppdu_status(struct rtw89_dev *rtwdev, u8 mac_idx, bool enable)
 {
-	u32 reg = rtw89_mac_reg_by_idx(R_AX_PPDU_STAT, mac_idx);
+	u32 reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PPDU_STAT, mac_idx);
 	int ret;
 
 	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
@@ -4807,7 +4807,7 @@ void rtw89_mac_update_rts_threshold(struct rtw89_dev *rtwdev, u8 mac_idx)
 	time_th = min_t(u32, time_th >> MAC_AX_TIME_TH_SH, MAC_AX_TIME_TH_MAX);
 	len_th = min_t(u32, len_th >> MAC_AX_LEN_TH_SH, MAC_AX_LEN_TH_MAX);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_AGG_LEN_HT_0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_AGG_LEN_HT_0, mac_idx);
 	rtw89_write16_mask(rtwdev, reg, B_AX_RTS_TXTIME_TH_MASK, time_th);
 	rtw89_write16_mask(rtwdev, reg, B_AX_RTS_LEN_TH_MASK, len_th);
 }
@@ -5043,7 +5043,7 @@ int rtw89_mac_cfg_plt(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_plt *plt)
 	if (ret)
 		return ret;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_BT_PLT, plt->band);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_BT_PLT, plt->band);
 	val = (plt->tx & RTW89_MAC_AX_PLT_LTE_RX ? B_AX_TX_PLT_GNT_LTE_RX : 0) |
 	      (plt->tx & RTW89_MAC_AX_PLT_GNT_BT_TX ? B_AX_TX_PLT_GNT_BT_TX : 0) |
 	      (plt->tx & RTW89_MAC_AX_PLT_GNT_BT_RX ? B_AX_TX_PLT_GNT_BT_RX : 0) |
@@ -5133,7 +5133,7 @@ u16 rtw89_mac_get_plt_cnt(struct rtw89_dev *rtwdev, u8 band)
 	u32 reg;
 	u16 cnt;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_BT_PLT, band);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_BT_PLT, band);
 	cnt = rtw89_read32_mask(rtwdev, reg, B_AX_BT_PLT_PKT_CNT_MASK);
 	rtw89_write16_set(rtwdev, reg, B_AX_BT_PLT_RST);
 
@@ -5146,7 +5146,7 @@ static void rtw89_mac_bfee_standby_timer(struct rtw89_dev *rtwdev, u8 mac_idx,
 	u32 reg;
 
 	rtw89_debug(rtwdev, RTW89_DBG_BF, "set bfee standby_timer to %d\n", keep);
-	reg = rtw89_mac_reg_by_idx(R_AX_BFMEE_RESP_OPTION, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_BFMEE_RESP_OPTION, mac_idx);
 	if (keep) {
 		set_bit(RTW89_FLAG_BFEE_TIMER_KEEP, rtwdev->flags);
 		rtw89_write32_mask(rtwdev, reg, B_AX_BFMEE_BFRP_RX_STANDBY_TIMER_MASK,
@@ -5165,7 +5165,7 @@ static void rtw89_mac_bfee_ctrl(struct rtw89_dev *rtwdev, u8 mac_idx, bool en)
 		   B_AX_BFMEE_HE_NDPA_EN;
 
 	rtw89_debug(rtwdev, RTW89_DBG_BF, "set bfee ndpa_en to %d\n", en);
-	reg = rtw89_mac_reg_by_idx(R_AX_BFMEE_RESP_OPTION, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_BFMEE_RESP_OPTION, mac_idx);
 	if (en) {
 		set_bit(RTW89_FLAG_BFEE_EN, rtwdev->flags);
 		rtw89_write32_set(rtwdev, reg, mask);
@@ -5187,30 +5187,30 @@ static int rtw89_mac_init_bfee(struct rtw89_dev *rtwdev, u8 mac_idx)
 
 	/* AP mode set tx gid to 63 */
 	/* STA mode set tx gid to 0(default) */
-	reg = rtw89_mac_reg_by_idx(R_AX_BFMER_CTRL_0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_BFMER_CTRL_0, mac_idx);
 	rtw89_write32_set(rtwdev, reg, B_AX_BFMER_NDP_BFEN);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_CSI_RRSC, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_CSI_RRSC, mac_idx);
 	rtw89_write32(rtwdev, reg, CSI_RRSC_BMAP);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_BFMEE_RESP_OPTION, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_BFMEE_RESP_OPTION, mac_idx);
 	val32 = FIELD_PREP(B_AX_BFMEE_NDP_RX_STANDBY_TIMER_MASK, NDP_RX_STANDBY_TIMER);
 	rtw89_write32(rtwdev, reg, val32);
 	rtw89_mac_bfee_standby_timer(rtwdev, mac_idx, true);
 	rtw89_mac_bfee_ctrl(rtwdev, mac_idx, true);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_CSI_CTRL_0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_CSI_CTRL_0, mac_idx);
 	rtw89_write32_set(rtwdev, reg, B_AX_BFMEE_BFPARAM_SEL |
 				       B_AX_BFMEE_USE_NSTS |
 				       B_AX_BFMEE_CSI_GID_SEL |
 				       B_AX_BFMEE_CSI_FORCE_RETE_EN);
-	reg = rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_CSI_RATE, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_CSI_RATE, mac_idx);
 	rtw89_write32(rtwdev, reg,
 		      u32_encode_bits(CSI_INIT_RATE_HT, B_AX_BFMEE_HT_CSI_RATE_MASK) |
 		      u32_encode_bits(CSI_INIT_RATE_VHT, B_AX_BFMEE_VHT_CSI_RATE_MASK) |
 		      u32_encode_bits(CSI_INIT_RATE_HE, B_AX_BFMEE_HE_CSI_RATE_MASK));
 
-	reg = rtw89_mac_reg_by_idx(R_AX_CSIRPT_OPTION, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_CSIRPT_OPTION, mac_idx);
 	rtw89_write32_set(rtwdev, reg,
 			  B_AX_CSIPRT_VHTSU_AID_EN | B_AX_CSIPRT_HESU_AID_EN);
 
@@ -5254,7 +5254,7 @@ static int rtw89_mac_set_csi_para_reg(struct rtw89_dev *rtwdev,
 	nc = min(nc, sound_dim);
 	nr = min(nr, sound_dim);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_CSI_CTRL_0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_CSI_CTRL_0, mac_idx);
 	rtw89_write32_set(rtwdev, reg, B_AX_BFMEE_BFPARAM_SEL);
 
 	val = FIELD_PREP(B_AX_BFMEE_CSIINFO0_NC_MASK, nc) |
@@ -5266,9 +5266,9 @@ static int rtw89_mac_set_csi_para_reg(struct rtw89_dev *rtwdev,
 	      FIELD_PREP(B_AX_BFMEE_CSIINFO0_STBC_EN, stbc_en);
 
 	if (port_sel == 0)
-		reg = rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_CSI_CTRL_0, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_CSI_CTRL_0, mac_idx);
 	else
-		reg = rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_CSI_CTRL_1, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_CSI_CTRL_1, mac_idx);
 
 	rtw89_write16(rtwdev, reg, val);
 
@@ -5304,11 +5304,11 @@ static int rtw89_mac_csi_rrsc(struct rtw89_dev *rtwdev,
 			 BIT(RTW89_MAC_BF_RRSC_HT_MSC3) |
 			 BIT(RTW89_MAC_BF_RRSC_HT_MSC5));
 	}
-	reg = rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_CSI_CTRL_0, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_CSI_CTRL_0, mac_idx);
 	rtw89_write32_set(rtwdev, reg, B_AX_BFMEE_BFPARAM_SEL);
 	rtw89_write32_clr(rtwdev, reg, B_AX_BFMEE_CSI_FORCE_RETE_EN);
 	rtw89_write32(rtwdev,
-		      rtw89_mac_reg_by_idx(R_AX_TRXPTCL_RESP_CSI_RRSC, mac_idx),
+		      rtw89_mac_reg_by_idx(rtwdev, R_AX_TRXPTCL_RESP_CSI_RRSC, mac_idx),
 		      rrsc);
 
 	return 0;
@@ -5346,19 +5346,21 @@ void rtw89_mac_bf_set_gid_table(struct rtw89_dev *rtwdev, struct ieee80211_vif *
 	rtw89_debug(rtwdev, RTW89_DBG_BF, "update bf GID table\n");
 
 	p = (__le32 *)conf->mu_group.membership;
-	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(R_AX_GID_POSITION_EN0, mac_idx),
+	rtw89_write32(rtwdev,
+		      rtw89_mac_reg_by_idx(rtwdev, R_AX_GID_POSITION_EN0, mac_idx),
 		      le32_to_cpu(p[0]));
-	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(R_AX_GID_POSITION_EN1, mac_idx),
+	rtw89_write32(rtwdev,
+		      rtw89_mac_reg_by_idx(rtwdev, R_AX_GID_POSITION_EN1, mac_idx),
 		      le32_to_cpu(p[1]));
 
 	p = (__le32 *)conf->mu_group.position;
-	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(R_AX_GID_POSITION0, mac_idx),
+	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(rtwdev, R_AX_GID_POSITION0, mac_idx),
 		      le32_to_cpu(p[0]));
-	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(R_AX_GID_POSITION1, mac_idx),
+	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(rtwdev, R_AX_GID_POSITION1, mac_idx),
 		      le32_to_cpu(p[1]));
-	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(R_AX_GID_POSITION2, mac_idx),
+	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(rtwdev, R_AX_GID_POSITION2, mac_idx),
 		      le32_to_cpu(p[2]));
-	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(R_AX_GID_POSITION3, mac_idx),
+	rtw89_write32(rtwdev, rtw89_mac_reg_by_idx(rtwdev, R_AX_GID_POSITION3, mac_idx),
 		      le32_to_cpu(p[3]));
 }
 
@@ -5449,7 +5451,7 @@ __rtw89_mac_set_tx_time(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta,
 			return ret;
 		}
 
-		reg = rtw89_mac_reg_by_idx(R_AX_AMPDU_AGG_LIMIT, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_AMPDU_AGG_LIMIT, mac_idx);
 		rtw89_write32_mask(rtwdev, reg, B_AX_AMPDU_MAX_TIME_MASK,
 				   max_tx_time >> 5);
 	}
@@ -5489,7 +5491,7 @@ int rtw89_mac_get_tx_time(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta,
 			return ret;
 		}
 
-		reg = rtw89_mac_reg_by_idx(R_AX_AMPDU_AGG_LIMIT, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_AMPDU_AGG_LIMIT, mac_idx);
 		*tx_time = rtw89_read32_mask(rtwdev, reg, B_AX_AMPDU_MAX_TIME_MASK) << 5;
 	}
 
@@ -5531,7 +5533,7 @@ int rtw89_mac_get_tx_retry_limit(struct rtw89_dev *rtwdev,
 			return ret;
 		}
 
-		reg = rtw89_mac_reg_by_idx(R_AX_TXCNT, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TXCNT, mac_idx);
 		*tx_retry = rtw89_read32_mask(rtwdev, reg, B_AX_L_TXCNT_LMT_MASK);
 	}
 
@@ -5550,7 +5552,7 @@ int rtw89_mac_set_hw_muedca_ctrl(struct rtw89_dev *rtwdev,
 	if (ret)
 		return ret;
 
-	reg = rtw89_mac_reg_by_idx(R_AX_MUEDCA_EN, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_MUEDCA_EN, mac_idx);
 	if (en)
 		rtw89_write16_set(rtwdev, reg, set);
 	else
@@ -5673,3 +5675,8 @@ int rtw89_mac_ptk_drop_by_band_and_wait(struct rtw89_dev *rtwdev,
 	}
 	return ret;
 }
+
+const struct rtw89_mac_gen_def rtw89_mac_gen_ax = {
+	.band1_offset = RTW89_MAC_AX_BAND_REG_OFFSET,
+};
+EXPORT_SYMBOL(rtw89_mac_gen_ax);
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index 0e1570451c2c5..26a89130fa489 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -478,6 +478,7 @@ enum rtw89_mac_bf_rrsc_rate {
 	({typeof(_addr) __addr = (_addr); \
 	  __addr >= R_AX_CMAC_REG_START && __addr <= R_AX_CMAC_REG_END; })
 #define RTW89_MAC_AX_BAND_REG_OFFSET 0x2000
+#define RTW89_MAC_BE_BAND_REG_OFFSET 0x4000
 
 #define PTCL_IDLE_POLL_CNT	10000
 #define SW_CVR_DUR_US	8
@@ -826,14 +827,25 @@ struct rtw89_mac_size_set {
 
 extern const struct rtw89_mac_size_set rtw89_mac_size;
 
-static inline u32 rtw89_mac_reg_by_idx(u32 reg_base, u8 band)
+struct rtw89_mac_gen_def {
+	u32 band1_offset;
+};
+
+extern const struct rtw89_mac_gen_def rtw89_mac_gen_ax;
+extern const struct rtw89_mac_gen_def rtw89_mac_gen_be;
+
+static inline
+u32 rtw89_mac_reg_by_idx(struct rtw89_dev *rtwdev, u32 reg_base, u8 band)
 {
-	return band == 0 ? reg_base : (reg_base + 0x2000);
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+
+	return band == 0 ? reg_base : (reg_base + mac->band1_offset);
 }
 
-static inline u32 rtw89_mac_reg_by_port(u32 base, u8 port, u8 mac_idx)
+static inline
+u32 rtw89_mac_reg_by_port(struct rtw89_dev *rtwdev, u32 base, u8 port, u8 mac_idx)
 {
-	return rtw89_mac_reg_by_idx(base + port * 0x40, mac_idx);
+	return rtw89_mac_reg_by_idx(rtwdev, base + port * 0x40, mac_idx);
 }
 
 static inline u32
@@ -841,7 +853,7 @@ rtw89_read32_port(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, u32 base)
 {
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_port(base, rtwvif->port, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_port(rtwdev, base, rtwvif->port, rtwvif->mac_idx);
 	return rtw89_read32(rtwdev, reg);
 }
 
@@ -851,7 +863,7 @@ rtw89_read32_port_mask(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 {
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_port(base, rtwvif->port, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_port(rtwdev, base, rtwvif->port, rtwvif->mac_idx);
 	return rtw89_read32_mask(rtwdev, reg, mask);
 }
 
@@ -861,7 +873,7 @@ rtw89_write32_port(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, u32 base,
 {
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_port(base, rtwvif->port, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_port(rtwdev, base, rtwvif->port, rtwvif->mac_idx);
 	rtw89_write32(rtwdev, reg, data);
 }
 
@@ -871,7 +883,7 @@ rtw89_write32_port_mask(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 {
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_port(base, rtwvif->port, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_port(rtwdev, base, rtwvif->port, rtwvif->mac_idx);
 	rtw89_write32_mask(rtwdev, reg, mask, data);
 }
 
@@ -881,7 +893,7 @@ rtw89_write16_port_mask(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 {
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_port(base, rtwvif->port, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_port(rtwdev, base, rtwvif->port, rtwvif->mac_idx);
 	rtw89_write16_mask(rtwdev, reg, mask, data);
 }
 
@@ -891,7 +903,7 @@ rtw89_write32_port_clr(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 {
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_port(base, rtwvif->port, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_port(rtwdev, base, rtwvif->port, rtwvif->mac_idx);
 	rtw89_write32_clr(rtwdev, reg, bit);
 }
 
@@ -901,7 +913,7 @@ rtw89_write16_port_clr(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 {
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_port(base, rtwvif->port, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_port(rtwdev, base, rtwvif->port, rtwvif->mac_idx);
 	rtw89_write16_clr(rtwdev, reg, bit);
 }
 
@@ -911,7 +923,7 @@ rtw89_write32_port_set(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 {
 	u32 reg;
 
-	reg = rtw89_mac_reg_by_port(base, rtwvif->port, rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_port(rtwdev, base, rtwvif->port, rtwvif->mac_idx);
 	rtw89_write32_set(rtwdev, reg, bit);
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index c9ed369015fef..1f4f126f46678 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -271,13 +271,13 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw,
 	}
 
 	rtw89_write32_mask(rtwdev,
-			   rtw89_mac_reg_by_idx(R_AX_RX_FLTR_OPT, RTW89_MAC_0),
+			   rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_0),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rtwdev->hal.rx_fltr);
 	if (!rtwdev->dbcc_en)
 		goto out;
 	rtw89_write32_mask(rtwdev,
-			   rtw89_mac_reg_by_idx(R_AX_RX_FLTR_OPT, RTW89_MAC_1),
+			   rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_1),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rtwdev->hal.rx_fltr);
 
@@ -354,7 +354,7 @@ static void ____rtw89_conf_tx_mu_edca(struct rtw89_dev *rtwdev,
 	val = FIELD_PREP(B_AX_MUEDCA_BE_PARAM_0_TIMER_MASK, timer_32us) |
 	      FIELD_PREP(B_AX_MUEDCA_BE_PARAM_0_CW_MASK, mu_edca->ecw_min_max) |
 	      FIELD_PREP(B_AX_MUEDCA_BE_PARAM_0_AIFS_MASK, aifs);
-	reg = rtw89_mac_reg_by_idx(ac_to_mu_edca_param[ac], rtwvif->mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, ac_to_mu_edca_param[ac], rtwvif->mac_idx);
 	rtw89_write32(rtwdev, reg, val);
 
 	rtw89_mac_set_hw_muedca_ctrl(rtwdev, rtwvif, true);
diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c
new file mode 100644
index 0000000000000..05bb8efaad232
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw89/mac_be.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2019-2020  Realtek Corporation
+ */
+
+#include "mac.h"
+
+const struct rtw89_mac_gen_def rtw89_mac_gen_be = {
+	.band1_offset = RTW89_MAC_BE_BAND_REG_OFFSET,
+};
+EXPORT_SYMBOL(rtw89_mac_gen_be);
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 5ff2871b230b3..7c72d92d5c91b 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -4568,7 +4568,7 @@ void rtw89_phy_tssi_ctrl_set_fast_mode_cfg(struct rtw89_dev *rtwdev,
 		regs = rtw89_tssi_fastmode_regs_level;
 
 	for (i = 0; i < RTW89_TSSI_FAST_MODE_NUM; i++) {
-		reg = rtw89_mac_reg_by_idx(regs[i].addr, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, regs[i].addr, mac_idx);
 		rtw89_write32_mask(rtwdev, reg, regs[i].mask, val);
 	}
 }
@@ -4630,11 +4630,11 @@ void rtw89_phy_tssi_ctrl_set_bandedge_cfg(struct rtw89_dev *rtwdev,
 	data = chip->tssi_dbw_table->data[bandedge_cfg];
 
 	for (i = 0; i < RTW89_TSSI_SBW_NUM; i++) {
-		reg = rtw89_mac_reg_by_idx(regs[i].addr, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, regs[i].addr, mac_idx);
 		rtw89_write32_mask(rtwdev, reg, regs[i].mask, data[i]);
 	}
 
-	reg = rtw89_mac_reg_by_idx(R_AX_BANDEDGE_CFG, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_BANDEDGE_CFG, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_BANDEDGE_CFG_IDX_MASK, bandedge_cfg);
 
 	rtw89_phy_tssi_ctrl_set_fast_mode_cfg(rtwdev, mac_idx, bandedge_cfg,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index b5740639e2679..ccf96c963bb43 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -756,9 +756,9 @@ static void rtw8851b_set_channel_mac(struct rtw89_dev *rtwdev,
 				     const struct rtw89_chan *chan,
 				     u8 mac_idx)
 {
-	u32 sub_carr = rtw89_mac_reg_by_idx(R_AX_TX_SUB_CARRIER_VALUE, mac_idx);
-	u32 chk_rate = rtw89_mac_reg_by_idx(R_AX_TXRATE_CHK, mac_idx);
-	u32 rf_mod = rtw89_mac_reg_by_idx(R_AX_WMAC_RFMOD, mac_idx);
+	u32 sub_carr = rtw89_mac_reg_by_idx(rtwdev, R_AX_TX_SUB_CARRIER_VALUE, mac_idx);
+	u32 chk_rate = rtw89_mac_reg_by_idx(rtwdev, R_AX_TXRATE_CHK, mac_idx);
+	u32 rf_mod = rtw89_mac_reg_by_idx(rtwdev, R_AX_WMAC_RFMOD, mac_idx);
 	u8 txsc20 = 0, txsc40 = 0;
 
 	switch (chan->band_width) {
@@ -1740,14 +1740,14 @@ void rtw8851b_set_txpwr_ul_tb_offset(struct rtw89_dev *rtwdev,
 		return;
 	}
 
-	reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_CTRL, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_CTRL, mac_idx);
 	rtw89_write32_set(rtwdev, reg, B_AX_PWR_UL_TB_CTRL_EN);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_1T, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_1T, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_PWR_UL_TB_1T_MASK, pw_ofst);
 
 	pw_ofst = max_t(s8, pw_ofst - 3, -16);
-	reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_2T, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_2T, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_PWR_UL_TB_2T_MASK, pw_ofst);
 }
 
@@ -2336,6 +2336,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.chip_id		= RTL8851B,
 	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8851b_chip_ops,
+	.mac_def		= &rtw89_mac_gen_ax,
 	.fw_basename		= RTW8851B_FW_BASENAME,
 	.fw_format_max		= RTW8851B_FW_FORMAT_MAX,
 	.try_ce_fw		= true,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 41f05276406d1..aefc72f24cf26 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -704,10 +704,9 @@ static void rtw8852a_set_channel_mac(struct rtw89_dev *rtwdev,
 				     const struct rtw89_chan *chan,
 				     u8 mac_idx)
 {
-	u32 rf_mod = rtw89_mac_reg_by_idx(R_AX_WMAC_RFMOD, mac_idx);
-	u32 sub_carr = rtw89_mac_reg_by_idx(R_AX_TX_SUB_CARRIER_VALUE,
-					     mac_idx);
-	u32 chk_rate = rtw89_mac_reg_by_idx(R_AX_TXRATE_CHK, mac_idx);
+	u32 rf_mod = rtw89_mac_reg_by_idx(rtwdev, R_AX_WMAC_RFMOD, mac_idx);
+	u32 sub_carr = rtw89_mac_reg_by_idx(rtwdev, R_AX_TX_SUB_CARRIER_VALUE, mac_idx);
+	u32 chk_rate = rtw89_mac_reg_by_idx(rtwdev, R_AX_TXRATE_CHK, mac_idx);
 	u8 txsc20 = 0, txsc40 = 0;
 
 	switch (chan->band_width) {
@@ -1380,13 +1379,13 @@ void rtw8852a_set_txpwr_ul_tb_offset(struct rtw89_dev *rtwdev,
 			    pw_ofst);
 		return;
 	}
-	reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_CTRL, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_CTRL, mac_idx);
 	rtw89_write32_set(rtwdev, reg, B_AX_PWR_UL_TB_CTRL_EN);
 	val_1t = pw_ofst;
-	reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_1T, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_1T, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_PWR_UL_TB_1T_MASK, val_1t);
 	val_2t = max(val_1t - 3, -16);
-	reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_2T, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_2T, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_PWR_UL_TB_2T_MASK, val_2t);
 	rtw89_debug(rtwdev, RTW89_DBG_TXPWR, "[ULTB] Set TB pwr_offset=(%d, %d)\n",
 		    val_1t, val_2t);
@@ -2073,6 +2072,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.chip_id		= RTL8852A,
 	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8852a_chip_ops,
+	.mac_def		= &rtw89_mac_gen_ax,
 	.fw_basename		= RTW8852A_FW_BASENAME,
 	.fw_format_max		= RTW8852A_FW_FORMAT_MAX,
 	.try_ce_fw		= false,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index eb2210cb7e099..cd1863e7e6d41 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -843,9 +843,9 @@ static void rtw8852b_set_channel_mac(struct rtw89_dev *rtwdev,
 				     const struct rtw89_chan *chan,
 				     u8 mac_idx)
 {
-	u32 rf_mod = rtw89_mac_reg_by_idx(R_AX_WMAC_RFMOD, mac_idx);
-	u32 sub_carr = rtw89_mac_reg_by_idx(R_AX_TX_SUB_CARRIER_VALUE, mac_idx);
-	u32 chk_rate = rtw89_mac_reg_by_idx(R_AX_TXRATE_CHK, mac_idx);
+	u32 rf_mod = rtw89_mac_reg_by_idx(rtwdev, R_AX_WMAC_RFMOD, mac_idx);
+	u32 sub_carr = rtw89_mac_reg_by_idx(rtwdev, R_AX_TX_SUB_CARRIER_VALUE, mac_idx);
+	u32 chk_rate = rtw89_mac_reg_by_idx(rtwdev, R_AX_TXRATE_CHK, mac_idx);
 	u8 txsc20 = 0, txsc40 = 0;
 
 	switch (chan->band_width) {
@@ -1725,14 +1725,14 @@ void rtw8852b_set_txpwr_ul_tb_offset(struct rtw89_dev *rtwdev,
 		return;
 	}
 
-	reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_CTRL, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_CTRL, mac_idx);
 	rtw89_write32_set(rtwdev, reg, B_AX_PWR_UL_TB_CTRL_EN);
 
-	reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_1T, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_1T, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_PWR_UL_TB_1T_MASK, pw_ofst);
 
 	pw_ofst = max_t(s8, pw_ofst - 3, -16);
-	reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_2T, mac_idx);
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_2T, mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_PWR_UL_TB_2T_MASK, pw_ofst);
 }
 
@@ -2505,6 +2505,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.chip_id		= RTL8852B,
 	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8852b_chip_ops,
+	.mac_def		= &rtw89_mac_gen_ax,
 	.fw_basename		= RTW8852B_FW_BASENAME,
 	.fw_format_max		= RTW8852B_FW_FORMAT_MAX,
 	.try_ce_fw		= true,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index b1af72fbf0857..4e936e0ba407a 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -606,10 +606,9 @@ static void rtw8852c_set_channel_mac(struct rtw89_dev *rtwdev,
 				     const struct rtw89_chan *chan,
 				     u8 mac_idx)
 {
-	u32 rf_mod = rtw89_mac_reg_by_idx(R_AX_WMAC_RFMOD, mac_idx);
-	u32 sub_carr = rtw89_mac_reg_by_idx(R_AX_TX_SUB_CARRIER_VALUE,
-					     mac_idx);
-	u32 chk_rate = rtw89_mac_reg_by_idx(R_AX_TXRATE_CHK, mac_idx);
+	u32 rf_mod = rtw89_mac_reg_by_idx(rtwdev, R_AX_WMAC_RFMOD, mac_idx);
+	u32 sub_carr = rtw89_mac_reg_by_idx(rtwdev, R_AX_TX_SUB_CARRIER_VALUE, mac_idx);
+	u32 chk_rate = rtw89_mac_reg_by_idx(rtwdev, R_AX_TXRATE_CHK, mac_idx);
 	u8 txsc20 = 0, txsc40 = 0, txsc80 = 0;
 	u8 rf_mod_val = 0, chk_rate_mask = 0;
 	u32 txsc;
@@ -1654,8 +1653,7 @@ static void rtw8852c_set_channel_bb(struct rtw89_dev *rtwdev,
 	    rtwdev->hal.cv != CHIP_CAV) {
 		rtw89_phy_write32_idx(rtwdev, R_P80_AT_HIGH_FREQ,
 				      B_P80_AT_HIGH_FREQ, 0x0, phy_idx);
-		reg = rtw89_mac_reg_by_idx(R_P80_AT_HIGH_FREQ_BB_WRP,
-					   phy_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_P80_AT_HIGH_FREQ_BB_WRP, phy_idx);
 		if (chan->primary_channel > chan->channel) {
 			rtw89_phy_write32_mask(rtwdev,
 					       R_P80_AT_HIGH_FREQ_RU_ALLOC,
@@ -1859,12 +1857,12 @@ void rtw8852c_set_txpwr_ul_tb_offset(struct rtw89_dev *rtwdev,
 
 	for (i = 0; i < 4; i++) {
 		/* 1TX */
-		reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_1T, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_1T, mac_idx);
 		rtw89_write32_mask(rtwdev, reg,
 				   B_AX_PWR_UL_TB_1T_V1_MASK << (8 * i),
 				   val_1t);
 		/* 2TX */
-		reg = rtw89_mac_reg_by_idx(R_AX_PWR_UL_TB_2T, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_PWR_UL_TB_2T, mac_idx);
 		rtw89_write32_mask(rtwdev, reg,
 				   B_AX_PWR_UL_TB_2T_V1_MASK << (8 * i),
 				   val_2t);
@@ -2181,7 +2179,7 @@ static void rtw8852c_ctrl_tx_path_tmac(struct rtw89_dev *rtwdev, u8 tx_path,
 
 	for (addr = R_AX_MACID_ANT_TABLE;
 	     addr <= R_AX_MACID_ANT_TABLE_LAST; addr += 4) {
-		reg = rtw89_mac_reg_by_idx(addr, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, addr, mac_idx);
 		rtw89_write32(rtwdev, reg, 0);
 	}
 
@@ -2211,7 +2209,7 @@ static void rtw8852c_ctrl_tx_path_tmac(struct rtw89_dev *rtwdev, u8 tx_path,
 	for (i = 0; i < cr_size; i++) {
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI, "0x%x = 0x%x\n",
 			    path_com[i].addr, path_com[i].data);
-		reg = rtw89_mac_reg_by_idx(path_com[i].addr, mac_idx);
+		reg = rtw89_mac_reg_by_idx(rtwdev, path_com[i].addr, mac_idx);
 		rtw89_write32(rtwdev, reg, path_com[i].data);
 	}
 }
@@ -2804,6 +2802,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.chip_id		= RTL8852C,
 	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8852c_chip_ops,
+	.mac_def		= &rtw89_mac_gen_ax,
 	.fw_basename		= RTW8852C_FW_BASENAME,
 	.fw_format_max		= RTW8852C_FW_FORMAT_MAX,
 	.try_ce_fw		= false,
-- 
GitLab


From 60168f6c50edd6b972c538aae11cb8861a892c7c Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 22 Aug 2023 20:58:18 +0800
Subject: [PATCH 1687/1806] wifi: rtw89: mac: generalize code to indirectly
 access WiFi internal memory

To diagnose abnormal behavior, we need to dump certain internal memory.
For example, dump security CAM when debugging encryption/decryption
problems, or dump BA CAM when debugging abnormal BlockAck.

Since the indirect address and internal memory base address are different
between WiFi 6 and 7 chips, add fields to reuse codes.

Also, only WiFi 6 chips initialize DMAC and CMAC tables via this indirect
interface, so no need to change the constant register address, and
new firmware will help to initialize these tables.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230822125822.23817-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/debug.c | 13 ++++++-----
 drivers/net/wireless/realtek/rtw89/mac.c   | 25 ++++++++++++++++------
 drivers/net/wireless/realtek/rtw89/mac.h   |  5 +++--
 drivers/net/wireless/realtek/rtw89/ser.c   | 20 +++++++++++------
 4 files changed, 42 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index 48635458c36ac..d162e64f60647 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -795,6 +795,9 @@ static void rtw89_debug_dump_mac_mem(struct seq_file *m,
 				     struct rtw89_dev *rtwdev,
 				     u8 sel, u32 start_addr, u32 len)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	u32 filter_model_addr = mac->filter_model_addr;
+	u32 indir_access_addr = mac->indir_access_addr;
 	u32 base_addr, start_page, residue;
 	u32 i, j, p, pages;
 	u32 dump_len, remain;
@@ -804,17 +807,17 @@ static void rtw89_debug_dump_mac_mem(struct seq_file *m,
 	pages = len / MAC_MEM_DUMP_PAGE_SIZE + 1;
 	start_page = start_addr / MAC_MEM_DUMP_PAGE_SIZE;
 	residue = start_addr % MAC_MEM_DUMP_PAGE_SIZE;
-	base_addr = rtw89_mac_mem_base_addrs[sel];
+	base_addr = mac->mem_base_addrs[sel];
 	base_addr += start_page * MAC_MEM_DUMP_PAGE_SIZE;
 
 	for (p = 0; p < pages; p++) {
 		dump_len = min_t(u32, remain, MAC_MEM_DUMP_PAGE_SIZE);
-		rtw89_write32(rtwdev, R_AX_FILTER_MODEL_ADDR, base_addr);
-		for (i = R_AX_INDIR_ACCESS_ENTRY + residue;
-		     i < R_AX_INDIR_ACCESS_ENTRY + dump_len;) {
+		rtw89_write32(rtwdev, filter_model_addr, base_addr);
+		for (i = indir_access_addr + residue;
+		     i < indir_access_addr + dump_len;) {
 			seq_printf(m, "%08xh:", i);
 			for (j = 0;
-			     j < 4 && i < R_AX_INDIR_ACCESS_ENTRY + dump_len;
+			     j < 4 && i < indir_access_addr + dump_len;
 			     j++, i += 4) {
 				val = rtw89_read32(rtwdev, i);
 				seq_printf(m, "  %08x", val);
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index edfa1a2e677aa..e0925a21a0963 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -12,7 +12,7 @@
 #include "reg.h"
 #include "util.h"
 
-const u32 rtw89_mac_mem_base_addrs[RTW89_MAC_MEM_NUM] = {
+static const u32 rtw89_mac_mem_base_addrs_ax[RTW89_MAC_MEM_NUM] = {
 	[RTW89_MAC_MEM_AXIDMA]	        = AXIDMA_BASE_ADDR,
 	[RTW89_MAC_MEM_SHARED_BUF]	= SHARED_BUF_BASE_ADDR,
 	[RTW89_MAC_MEM_DMAC_TBL]	= DMAC_TBL_BASE_ADDR,
@@ -39,19 +39,21 @@ const u32 rtw89_mac_mem_base_addrs[RTW89_MAC_MEM_NUM] = {
 static void rtw89_mac_mem_write(struct rtw89_dev *rtwdev, u32 offset,
 				u32 val, enum rtw89_mac_mem_sel sel)
 {
-	u32 addr = rtw89_mac_mem_base_addrs[sel] + offset;
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	u32 addr = mac->mem_base_addrs[sel] + offset;
 
-	rtw89_write32(rtwdev, R_AX_FILTER_MODEL_ADDR, addr);
-	rtw89_write32(rtwdev, R_AX_INDIR_ACCESS_ENTRY, val);
+	rtw89_write32(rtwdev, mac->filter_model_addr, addr);
+	rtw89_write32(rtwdev, mac->indir_access_addr, val);
 }
 
 static u32 rtw89_mac_mem_read(struct rtw89_dev *rtwdev, u32 offset,
 			      enum rtw89_mac_mem_sel sel)
 {
-	u32 addr = rtw89_mac_mem_base_addrs[sel] + offset;
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	u32 addr = mac->mem_base_addrs[sel] + offset;
 
-	rtw89_write32(rtwdev, R_AX_FILTER_MODEL_ADDR, addr);
-	return rtw89_read32(rtwdev, R_AX_INDIR_ACCESS_ENTRY);
+	rtw89_write32(rtwdev, mac->filter_model_addr, addr);
+	return rtw89_read32(rtwdev, mac->indir_access_addr);
 }
 
 int rtw89_mac_check_mac_en(struct rtw89_dev *rtwdev, u8 mac_idx,
@@ -3661,6 +3663,9 @@ static void rtw89_mac_dmac_tbl_init(struct rtw89_dev *rtwdev, u8 macid)
 {
 	u8 i;
 
+	if (rtwdev->chip->chip_gen != RTW89_CHIP_AX)
+		return;
+
 	for (i = 0; i < 4; i++) {
 		rtw89_write32(rtwdev, R_AX_FILTER_MODEL_ADDR,
 			      DMAC_TBL_BASE_ADDR + (macid << 4) + (i << 2));
@@ -3670,6 +3675,9 @@ static void rtw89_mac_dmac_tbl_init(struct rtw89_dev *rtwdev, u8 macid)
 
 static void rtw89_mac_cmac_tbl_init(struct rtw89_dev *rtwdev, u8 macid)
 {
+	if (rtwdev->chip->chip_gen != RTW89_CHIP_AX)
+		return;
+
 	rtw89_write32(rtwdev, R_AX_FILTER_MODEL_ADDR,
 		      CMAC_TBL_BASE_ADDR + macid * CCTL_INFO_SIZE);
 	rtw89_write32(rtwdev, R_AX_INDIR_ACCESS_ENTRY, 0x4);
@@ -5678,5 +5686,8 @@ int rtw89_mac_ptk_drop_by_band_and_wait(struct rtw89_dev *rtwdev,
 
 const struct rtw89_mac_gen_def rtw89_mac_gen_ax = {
 	.band1_offset = RTW89_MAC_AX_BAND_REG_OFFSET,
+	.filter_model_addr = R_AX_FILTER_MODEL_ADDR,
+	.indir_access_addr = R_AX_INDIR_ACCESS_ENTRY,
+	.mem_base_addrs = rtw89_mac_mem_base_addrs_ax,
 };
 EXPORT_SYMBOL(rtw89_mac_gen_ax);
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index 26a89130fa489..b31c78ca27da7 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -327,8 +327,6 @@ enum rtw89_mac_mem_sel {
 	RTW89_MAC_MEM_NUM,
 };
 
-extern const u32 rtw89_mac_mem_base_addrs[];
-
 enum rtw89_rpwm_req_pwr_state {
 	RTW89_MAC_RPWM_REQ_PWR_STATE_ACTIVE = 0,
 	RTW89_MAC_RPWM_REQ_PWR_STATE_BAND0_RFON = 1,
@@ -829,6 +827,9 @@ extern const struct rtw89_mac_size_set rtw89_mac_size;
 
 struct rtw89_mac_gen_def {
 	u32 band1_offset;
+	u32 filter_model_addr;
+	u32 indir_access_addr;
+	const u32 *mem_base_addrs;
 };
 
 extern const struct rtw89_mac_gen_def rtw89_mac_gen_ax;
diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c
index 0462ba693f6fd..c1644353053f0 100644
--- a/drivers/net/wireless/realtek/rtw89/ser.c
+++ b/drivers/net/wireless/realtek/rtw89/ser.c
@@ -529,6 +529,9 @@ static void ser_do_hci_st_hdl(struct rtw89_ser *ser, u8 evt)
 static void ser_mac_mem_dump(struct rtw89_dev *rtwdev, u8 *buf,
 			     u8 sel, u32 start_addr, u32 len)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	u32 filter_model_addr = mac->filter_model_addr;
+	u32 indir_access_addr = mac->indir_access_addr;
 	u32 *ptr = (u32 *)buf;
 	u32 base_addr, start_page, residue;
 	u32 cnt = 0;
@@ -536,14 +539,14 @@ static void ser_mac_mem_dump(struct rtw89_dev *rtwdev, u8 *buf,
 
 	start_page = start_addr / MAC_MEM_DUMP_PAGE_SIZE;
 	residue = start_addr % MAC_MEM_DUMP_PAGE_SIZE;
-	base_addr = rtw89_mac_mem_base_addrs[sel];
+	base_addr = mac->mem_base_addrs[sel];
 	base_addr += start_page * MAC_MEM_DUMP_PAGE_SIZE;
 
 	while (cnt < len) {
-		rtw89_write32(rtwdev, R_AX_FILTER_MODEL_ADDR, base_addr);
+		rtw89_write32(rtwdev, filter_model_addr, base_addr);
 
-		for (i = R_AX_INDIR_ACCESS_ENTRY + residue;
-		     i < R_AX_INDIR_ACCESS_ENTRY + MAC_MEM_DUMP_PAGE_SIZE;
+		for (i = indir_access_addr + residue;
+		     i < indir_access_addr + MAC_MEM_DUMP_PAGE_SIZE;
 		     i += 4, ptr++) {
 			*ptr = rtw89_read32(rtwdev, i);
 			cnt += 4;
@@ -585,6 +588,9 @@ static int rtw89_ser_fw_backtrace_dump(struct rtw89_dev *rtwdev, u8 *buf,
 				       const struct __fw_backtrace_entry *ent)
 {
 	struct __fw_backtrace_info *ptr = (struct __fw_backtrace_info *)buf;
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	u32 filter_model_addr = mac->filter_model_addr;
+	u32 indir_access_addr = mac->indir_access_addr;
 	u32 fwbt_addr = ent->wcpu_addr & RTW89_WCPU_BASE_MASK;
 	u32 fwbt_size = ent->size;
 	u32 fwbt_key = ent->key;
@@ -610,10 +616,10 @@ static int rtw89_ser_fw_backtrace_dump(struct rtw89_dev *rtwdev, u8 *buf,
 	}
 
 	rtw89_debug(rtwdev, RTW89_DBG_SER, "dump fw backtrace start\n");
-	rtw89_write32(rtwdev, R_AX_FILTER_MODEL_ADDR, fwbt_addr);
+	rtw89_write32(rtwdev, filter_model_addr, fwbt_addr);
 
-	for (i = R_AX_INDIR_ACCESS_ENTRY;
-	     i < R_AX_INDIR_ACCESS_ENTRY + fwbt_size;
+	for (i = indir_access_addr;
+	     i < indir_access_addr + fwbt_size;
 	     i += RTW89_FW_BACKTRACE_INFO_SIZE, ptr++) {
 		*ptr = (struct __fw_backtrace_info){
 			.ra = rtw89_read32(rtwdev, i),
-- 
GitLab


From 3a7e4f56eb184da66b7f60d4b001ce0248a7b519 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 22 Aug 2023 20:58:19 +0800
Subject: [PATCH 1688/1806] wifi: rtw89: mac: define internal memory address
 for WiFi 7 chip

Define base address of WiFi 7 internal memory according to design to
provide the same functions as existing WiFi 6 chips.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230822125822.23817-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/mac.h    | 27 +++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/mac_be.c | 27 +++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/reg.h    |  2 ++
 3 files changed, 56 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index b31c78ca27da7..7c79400934803 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -275,6 +275,7 @@ enum rtw89_mac_dbg_port_sel {
 
 /* SRAM mem dump */
 #define R_AX_INDIR_ACCESS_ENTRY 0x40000
+#define R_BE_INDIR_ACCESS_ENTRY 0x80000
 
 #define	AXIDMA_BASE_ADDR		0x18006000
 #define	STA_SCHED_BASE_ADDR		0x18808000
@@ -298,6 +299,31 @@ enum rtw89_mac_dbg_port_sel {
 #define	TXDATA_FIFO_1_BASE_ADDR		0x188A1000
 #define	CPU_LOCAL_BASE_ADDR		0x18003000
 
+#define WD_PAGE_BASE_ADDR_BE		0x0
+#define CPU_LOCAL_BASE_ADDR_BE		0x18003000
+#define AXIDMA_BASE_ADDR_BE		0x18006000
+#define SHARED_BUF_BASE_ADDR_BE		0x18700000
+#define DMAC_TBL_BASE_ADDR_BE		0x18800000
+#define SHCUT_MACHDR_BASE_ADDR_BE	0x18800800
+#define STA_SCHED_BASE_ADDR_BE		0x18818000
+#define NAT25_CAM_BASE_ADDR_BE		0x18820000
+#define RXPLD_FLTR_CAM_BASE_ADDR_BE	0x18823000
+#define SEC_CAM_BASE_ADDR_BE		0x18824000
+#define WOW_CAM_BASE_ADDR_BE		0x18828000
+#define MLD_TBL_BASE_ADDR_BE		0x18829000
+#define RX_CLSF_CAM_BASE_ADDR_BE	0x1882A000
+#define CMAC_TBL_BASE_ADDR_BE		0x18840000
+#define ADDR_CAM_BASE_ADDR_BE		0x18850000
+#define BSSID_CAM_BASE_ADDR_BE		0x18858000
+#define BA_CAM_BASE_ADDR_BE		0x18859000
+#define BCN_IE_CAM0_BASE_ADDR_BE	0x18860000
+#define TXDATA_FIFO_0_BASE_ADDR_BE	0x18861000
+#define TXD_FIFO_0_BASE_ADDR_BE		0x18862000
+#define BCN_IE_CAM1_BASE_ADDR_BE	0x18880000
+#define TXDATA_FIFO_1_BASE_ADDR_BE	0x18881000
+#define TXD_FIFO_1_BASE_ADDR_BE		0x18881800
+#define DCPU_LOCAL_BASE_ADDR_BE		0x19C02000
+
 #define CCTL_INFO_SIZE		32
 
 enum rtw89_mac_mem_sel {
@@ -322,6 +348,7 @@ enum rtw89_mac_mem_sel {
 	RTW89_MAC_MEM_BSSID_CAM,
 	RTW89_MAC_MEM_TXD_FIFO_0_V1,
 	RTW89_MAC_MEM_TXD_FIFO_1_V1,
+	RTW89_MAC_MEM_WD_PAGE,
 
 	/* keep last */
 	RTW89_MAC_MEM_NUM,
diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c
index 05bb8efaad232..ec920978195e6 100644
--- a/drivers/net/wireless/realtek/rtw89/mac_be.c
+++ b/drivers/net/wireless/realtek/rtw89/mac_be.c
@@ -3,8 +3,35 @@
  */
 
 #include "mac.h"
+#include "reg.h"
+
+static const u32 rtw89_mac_mem_base_addrs_be[RTW89_MAC_MEM_NUM] = {
+	[RTW89_MAC_MEM_AXIDMA]	        = AXIDMA_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_SHARED_BUF]	= SHARED_BUF_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_DMAC_TBL]	= DMAC_TBL_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_SHCUT_MACHDR]	= SHCUT_MACHDR_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_STA_SCHED]	= STA_SCHED_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_RXPLD_FLTR_CAM]	= RXPLD_FLTR_CAM_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_SECURITY_CAM]	= SEC_CAM_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_WOW_CAM]		= WOW_CAM_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_CMAC_TBL]	= CMAC_TBL_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_ADDR_CAM]	= ADDR_CAM_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_BA_CAM]		= BA_CAM_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_BCN_IE_CAM0]	= BCN_IE_CAM0_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_BCN_IE_CAM1]	= BCN_IE_CAM1_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_TXD_FIFO_0]	= TXD_FIFO_0_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_TXD_FIFO_1]	= TXD_FIFO_1_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_TXDATA_FIFO_0]	= TXDATA_FIFO_0_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_TXDATA_FIFO_1]	= TXDATA_FIFO_1_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_CPU_LOCAL]	= CPU_LOCAL_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_BSSID_CAM]	= BSSID_CAM_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_WD_PAGE]		= WD_PAGE_BASE_ADDR_BE,
+};
 
 const struct rtw89_mac_gen_def rtw89_mac_gen_be = {
 	.band1_offset = RTW89_MAC_BE_BAND_REG_OFFSET,
+	.filter_model_addr = R_BE_FILTER_MODEL_ADDR,
+	.indir_access_addr = R_BE_INDIR_ACCESS_ENTRY,
+	.mem_base_addrs = rtw89_mac_mem_base_addrs_be,
 };
 EXPORT_SYMBOL(rtw89_mac_gen_be);
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index 2d34b43cda3a2..cab07cc993f00 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -3625,6 +3625,8 @@
 #define B_AX_GNT_BT_TX_SW_VAL BIT(1)
 #define B_AX_GNT_BT_TX_SW_CTRL BIT(0)
 
+#define R_BE_FILTER_MODEL_ADDR 0x0C04
+
 #define RR_MOD 0x00
 #define RR_MOD_V1 0x10000
 #define RR_MOD_IQK GENMASK(19, 4)
-- 
GitLab


From 9d87e7dc930e149def617c152f03ed97e3d7d899 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 22 Aug 2023 20:58:20 +0800
Subject: [PATCH 1689/1806] wifi: rtw89: mac: define register address of
 rx_filter to generalize code

rx_filter is used to decide which kind of packets are received to driver,
or just dropped by MAC layer to reduce bus traffic.

The bit definitions of old and new chips are the sames, but only address
is changed, so define a field to generalize usage.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230822125822.23817-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c     |  6 ++++--
 drivers/net/wireless/realtek/rtw89/fw.c       |  6 ++++--
 drivers/net/wireless/realtek/rtw89/mac.c      |  1 +
 drivers/net/wireless/realtek/rtw89/mac.h      |  1 +
 drivers/net/wireless/realtek/rtw89/mac80211.c |  5 +++--
 drivers/net/wireless/realtek/rtw89/mac_be.c   |  1 +
 drivers/net/wireless/realtek/rtw89/reg.h      | 19 +++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/wow.c      |  3 ++-
 8 files changed, 35 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index eca973b95fbb3..133bf289bacb4 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -2477,6 +2477,7 @@ out:
 
 void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	struct ieee80211_hw *hw = rtwdev->hw;
 	struct rtw89_roc *roc = &rtwvif->roc;
 	struct cfg80211_chan_def roc_chan;
@@ -2504,7 +2505,7 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_config_roc_chandef(rtwdev, rtwvif->sub_entity_idx, &roc_chan);
 	rtw89_set_channel(rtwdev);
 	rtw89_write32_clr(rtwdev,
-			  rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_0),
+			  rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, RTW89_MAC_0),
 			  B_AX_A_UC_CAM_MATCH | B_AX_A_BC_CAM_MATCH);
 
 	ieee80211_ready_on_channel(hw);
@@ -2512,6 +2513,7 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 
 void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	struct ieee80211_hw *hw = rtwdev->hw;
 	struct rtw89_roc *roc = &rtwvif->roc;
 	struct rtw89_vif *tmp;
@@ -2525,7 +2527,7 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_leave_lps(rtwdev);
 
 	rtw89_write32_mask(rtwdev,
-			   rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_0),
+			   rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, RTW89_MAC_0),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rtwdev->hal.rx_fltr);
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index ba873a5d1a8d5..df1dc2f43c86b 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -3863,6 +3863,7 @@ void rtw89_hw_scan_start(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 			 struct ieee80211_scan_request *scan_req)
 {
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	struct cfg80211_scan_request *req = &scan_req->req;
 	u32 rx_fltr = rtwdev->hal.rx_fltr;
 	u8 mac_addr[ETH_ALEN];
@@ -3885,7 +3886,7 @@ void rtw89_hw_scan_start(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 	rx_fltr &= ~B_AX_A_BC;
 	rx_fltr &= ~B_AX_A_A1_MATCH;
 	rtw89_write32_mask(rtwdev,
-			   rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_0),
+			   rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, RTW89_MAC_0),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rx_fltr);
 }
@@ -3893,6 +3894,7 @@ void rtw89_hw_scan_start(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 			    bool aborted)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
 	struct cfg80211_scan_info info = {
 		.aborted = aborted,
@@ -3903,7 +3905,7 @@ void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 		return;
 
 	rtw89_write32_mask(rtwdev,
-			   rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_0),
+			   rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, RTW89_MAC_0),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rtwdev->hal.rx_fltr);
 
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index e0925a21a0963..fab9f5004a75e 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -5689,5 +5689,6 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_ax = {
 	.filter_model_addr = R_AX_FILTER_MODEL_ADDR,
 	.indir_access_addr = R_AX_INDIR_ACCESS_ENTRY,
 	.mem_base_addrs = rtw89_mac_mem_base_addrs_ax,
+	.rx_fltr = R_AX_RX_FLTR_OPT,
 };
 EXPORT_SYMBOL(rtw89_mac_gen_ax);
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index 7c79400934803..7cf34137c0bcf 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -857,6 +857,7 @@ struct rtw89_mac_gen_def {
 	u32 filter_model_addr;
 	u32 indir_access_addr;
 	const u32 *mem_base_addrs;
+	u32 rx_fltr;
 };
 
 extern const struct rtw89_mac_gen_def rtw89_mac_gen_ax;
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 1f4f126f46678..5e48618706d91 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -224,6 +224,7 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw,
 				       u64 multicast)
 {
 	struct rtw89_dev *rtwdev = hw->priv;
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 
 	mutex_lock(&rtwdev->mutex);
 	rtw89_leave_ps_mode(rtwdev);
@@ -271,13 +272,13 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw,
 	}
 
 	rtw89_write32_mask(rtwdev,
-			   rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_0),
+			   rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, RTW89_MAC_0),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rtwdev->hal.rx_fltr);
 	if (!rtwdev->dbcc_en)
 		goto out;
 	rtw89_write32_mask(rtwdev,
-			   rtw89_mac_reg_by_idx(rtwdev, R_AX_RX_FLTR_OPT, RTW89_MAC_1),
+			   rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, RTW89_MAC_1),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rtwdev->hal.rx_fltr);
 
diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c
index ec920978195e6..9a63fb35e867f 100644
--- a/drivers/net/wireless/realtek/rtw89/mac_be.c
+++ b/drivers/net/wireless/realtek/rtw89/mac_be.c
@@ -33,5 +33,6 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_be = {
 	.filter_model_addr = R_BE_FILTER_MODEL_ADDR,
 	.indir_access_addr = R_BE_INDIR_ACCESS_ENTRY,
 	.mem_base_addrs = rtw89_mac_mem_base_addrs_be,
+	.rx_fltr = R_BE_RX_FLTR_OPT,
 };
 EXPORT_SYMBOL(rtw89_mac_gen_be);
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index cab07cc993f00..eab26039242a0 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -3627,6 +3627,25 @@
 
 #define R_BE_FILTER_MODEL_ADDR 0x0C04
 
+#define R_BE_RX_FLTR_OPT 0x11420
+#define R_BE_RX_FLTR_OPT_C1 0x15420
+#define B_BE_UID_FILTER_MASK GENMASK(31, 24)
+#define B_BE_UNSPT_TYPE BIT(22)
+#define B_BE_RX_MPDU_MAX_LEN_MASK GENMASK(21, 16)
+#define B_BE_A_FTM_REQ BIT(14)
+#define B_BE_A_ERR_PKT BIT(13)
+#define B_BE_A_UNSUP_PKT BIT(12)
+#define B_BE_A_CRC32_ERR BIT(11)
+#define B_BE_A_BCN_CHK_RULE_MASK GENMASK(9, 8)
+#define B_BE_A_BCN_CHK_EN BIT(7)
+#define B_BE_A_MC_LIST_CAM_MATCH BIT(6)
+#define B_BE_A_BC_CAM_MATCH BIT(5)
+#define B_BE_A_UC_CAM_MATCH BIT(4)
+#define B_BE_A_MC BIT(3)
+#define B_BE_A_BC BIT(2)
+#define B_BE_A_A1_MATCH BIT(1)
+#define B_BE_SNIFFER_MODE BIT(0)
+
 #define RR_MOD 0x00
 #define RR_MOD_V1 0x10000
 #define RR_MOD_IQK GENMASK(19, 4)
diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c
index 364e546221500..aa9efca040253 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.c
+++ b/drivers/net/wireless/realtek/rtw89/wow.c
@@ -40,6 +40,7 @@ static void rtw89_wow_leave_lps(struct rtw89_dev *rtwdev)
 
 static int rtw89_wow_config_mac(struct rtw89_dev *rtwdev, bool enable_wow)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	int ret;
 
 	if (enable_wow) {
@@ -49,7 +50,7 @@ static int rtw89_wow_config_mac(struct rtw89_dev *rtwdev, bool enable_wow)
 			return ret;
 		}
 		rtw89_write32_set(rtwdev, R_AX_RX_FUNCTION_STOP, B_AX_HDR_RX_STOP);
-		rtw89_write32_clr(rtwdev, R_AX_RX_FLTR_OPT, B_AX_SNIFFER_MODE);
+		rtw89_write32_clr(rtwdev, mac->rx_fltr, B_AX_SNIFFER_MODE);
 		rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, false);
 		rtw89_write32(rtwdev, R_AX_ACTION_FWD0, 0);
 		rtw89_write32(rtwdev, R_AX_ACTION_FWD1, 0);
-- 
GitLab


From 1165f5719229882442e67ad845a07491b0795ded Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Tue, 22 Aug 2023 20:58:21 +0800
Subject: [PATCH 1690/1806] wifi: rtw89: phy: add phy_gen_def::cr_base to
 support WiFi 7 chips

cr_base is base address of PHY control register. The base of WiFi 6 and 7
chips are 0x1_0000 and 0x2_0000 respectively, so define them accordingly.
For example, if PHY address is 0x1330, absolute address is 0x1_1330 for
WiFi 6 chips, and 0x2_1330 for WiFi 7 chips.

Meanwhile, there are two copies of PHY hardware named PHY0 and PHY1. The
offset between them is 0x2_0000, so the base address of PHY0 and PHY1 are
0x2_0000 and 0x4_0000 respectively.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230822125822.23817-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h     |  2 +
 drivers/net/wireless/realtek/rtw89/phy.c      |  8 ++++
 drivers/net/wireless/realtek/rtw89/phy.h      | 48 ++++++++++++++-----
 drivers/net/wireless/realtek/rtw89/phy_be.c   | 10 ++++
 drivers/net/wireless/realtek/rtw89/rtw8851b.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c |  1 +
 8 files changed, 61 insertions(+), 11 deletions(-)
 create mode 100644 drivers/net/wireless/realtek/rtw89/phy_be.c

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 2806d1cf2c0d6..17f6418e44046 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -15,6 +15,7 @@
 struct rtw89_dev;
 struct rtw89_pci_info;
 struct rtw89_mac_gen_def;
+struct rtw89_phy_gen_def;
 
 extern const struct ieee80211_ops rtw89_ops;
 
@@ -3437,6 +3438,7 @@ struct rtw89_chip_info {
 	enum rtw89_chip_gen chip_gen;
 	const struct rtw89_chip_ops *ops;
 	const struct rtw89_mac_gen_def *mac_def;
+	const struct rtw89_phy_gen_def *phy_def;
 	const char *fw_basename;
 	u8 fw_format_max;
 	bool try_ce_fw;
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 7c72d92d5c91b..85d3205d6e680 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -1448,6 +1448,9 @@ static u32 rtw89_phy0_phy1_offset(struct rtw89_dev *rtwdev, u32 addr)
 	u32 phy_page = addr >> 8;
 	u32 ofst = 0;
 
+	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE)
+		return addr < 0x10000 ? 0x20000 : 0;
+
 	switch (phy_page) {
 	case 0x6:
 	case 0x7:
@@ -4732,3 +4735,8 @@ void rtw89_phy_config_edcca(struct rtw89_dev *rtwdev, bool scan)
 		rtw89_phy_write32(rtwdev, reg, hal->edcca_bak);
 	}
 }
+
+const struct rtw89_phy_gen_def rtw89_phy_gen_ax = {
+	.cr_base = 0x10000,
+};
+EXPORT_SYMBOL(rtw89_phy_gen_ax);
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index ab174a0ba4888..36a24676b2fe0 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -7,7 +7,6 @@
 
 #include "core.h"
 
-#define RTW89_PHY_ADDR_OFFSET	0x10000
 #define RTW89_RF_ADDR_ADSEL_MASK  BIT(16)
 
 #define get_phy_headline(addr)		FIELD_GET(GENMASK(31, 28), addr)
@@ -337,61 +336,88 @@ struct rtw89_nbi_reg_def {
 	struct rtw89_reg_def notch2_en;
 };
 
+struct rtw89_phy_gen_def {
+	u32 cr_base;
+};
+
+extern const struct rtw89_phy_gen_def rtw89_phy_gen_ax;
+extern const struct rtw89_phy_gen_def rtw89_phy_gen_be;
+
 static inline void rtw89_phy_write8(struct rtw89_dev *rtwdev,
 				    u32 addr, u8 data)
 {
-	rtw89_write8(rtwdev, addr | RTW89_PHY_ADDR_OFFSET, data);
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+
+	rtw89_write8(rtwdev, addr + phy->cr_base, data);
 }
 
 static inline void rtw89_phy_write16(struct rtw89_dev *rtwdev,
 				     u32 addr, u16 data)
 {
-	rtw89_write16(rtwdev, addr | RTW89_PHY_ADDR_OFFSET, data);
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+
+	rtw89_write16(rtwdev, addr + phy->cr_base, data);
 }
 
 static inline void rtw89_phy_write32(struct rtw89_dev *rtwdev,
 				     u32 addr, u32 data)
 {
-	rtw89_write32(rtwdev, addr | RTW89_PHY_ADDR_OFFSET, data);
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+
+	rtw89_write32(rtwdev, addr + phy->cr_base, data);
 }
 
 static inline void rtw89_phy_write32_set(struct rtw89_dev *rtwdev,
 					 u32 addr, u32 bits)
 {
-	rtw89_write32_set(rtwdev, addr | RTW89_PHY_ADDR_OFFSET, bits);
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+
+	rtw89_write32_set(rtwdev, addr + phy->cr_base, bits);
 }
 
 static inline void rtw89_phy_write32_clr(struct rtw89_dev *rtwdev,
 					 u32 addr, u32 bits)
 {
-	rtw89_write32_clr(rtwdev, addr | RTW89_PHY_ADDR_OFFSET, bits);
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+
+	rtw89_write32_clr(rtwdev, addr + phy->cr_base, bits);
 }
 
 static inline void rtw89_phy_write32_mask(struct rtw89_dev *rtwdev,
 					  u32 addr, u32 mask, u32 data)
 {
-	rtw89_write32_mask(rtwdev, addr | RTW89_PHY_ADDR_OFFSET, mask, data);
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+
+	rtw89_write32_mask(rtwdev, addr + phy->cr_base, mask, data);
 }
 
 static inline u8 rtw89_phy_read8(struct rtw89_dev *rtwdev, u32 addr)
 {
-	return rtw89_read8(rtwdev, addr | RTW89_PHY_ADDR_OFFSET);
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+
+	return rtw89_read8(rtwdev, addr + phy->cr_base);
 }
 
 static inline u16 rtw89_phy_read16(struct rtw89_dev *rtwdev, u32 addr)
 {
-	return rtw89_read16(rtwdev, addr | RTW89_PHY_ADDR_OFFSET);
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+
+	return rtw89_read16(rtwdev, addr + phy->cr_base);
 }
 
 static inline u32 rtw89_phy_read32(struct rtw89_dev *rtwdev, u32 addr)
 {
-	return rtw89_read32(rtwdev, addr | RTW89_PHY_ADDR_OFFSET);
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+
+	return rtw89_read32(rtwdev, addr + phy->cr_base);
 }
 
 static inline u32 rtw89_phy_read32_mask(struct rtw89_dev *rtwdev,
 					u32 addr, u32 mask)
 {
-	return rtw89_read32_mask(rtwdev, addr | RTW89_PHY_ADDR_OFFSET, mask);
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+
+	return rtw89_read32_mask(rtwdev, addr + phy->cr_base, mask);
 }
 
 static inline
diff --git a/drivers/net/wireless/realtek/rtw89/phy_be.c b/drivers/net/wireless/realtek/rtw89/phy_be.c
new file mode 100644
index 0000000000000..143f900d29a67
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw89/phy_be.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2023  Realtek Corporation
+ */
+
+#include "phy.h"
+
+const struct rtw89_phy_gen_def rtw89_phy_gen_be = {
+	.cr_base = 0x20000,
+};
+EXPORT_SYMBOL(rtw89_phy_gen_be);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index ccf96c963bb43..52eb7030fd0b1 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2337,6 +2337,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8851b_chip_ops,
 	.mac_def		= &rtw89_mac_gen_ax,
+	.phy_def		= &rtw89_phy_gen_ax,
 	.fw_basename		= RTW8851B_FW_BASENAME,
 	.fw_format_max		= RTW8851B_FW_FORMAT_MAX,
 	.try_ce_fw		= true,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index aefc72f24cf26..eb6aad3bbb852 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2073,6 +2073,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8852a_chip_ops,
 	.mac_def		= &rtw89_mac_gen_ax,
+	.phy_def		= &rtw89_phy_gen_ax,
 	.fw_basename		= RTW8852A_FW_BASENAME,
 	.fw_format_max		= RTW8852A_FW_FORMAT_MAX,
 	.try_ce_fw		= false,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index cd1863e7e6d41..49664cc44f364 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -2506,6 +2506,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8852b_chip_ops,
 	.mac_def		= &rtw89_mac_gen_ax,
+	.phy_def		= &rtw89_phy_gen_ax,
 	.fw_basename		= RTW8852B_FW_BASENAME,
 	.fw_format_max		= RTW8852B_FW_FORMAT_MAX,
 	.try_ce_fw		= true,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 4e936e0ba407a..abd01e808d831 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2803,6 +2803,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.chip_gen		= RTW89_CHIP_AX,
 	.ops			= &rtw8852c_chip_ops,
 	.mac_def		= &rtw89_mac_gen_ax,
+	.phy_def		= &rtw89_phy_gen_ax,
 	.fw_basename		= RTW8852C_FW_BASENAME,
 	.fw_format_max		= RTW8852C_FW_FORMAT_MAX,
 	.try_ce_fw		= false,
-- 
GitLab


From 058b207481977c4fab7f5d979aa783cf536e21f3 Mon Sep 17 00:00:00 2001
From: Cheng-Chieh Hsieh <cj.hsieh@realtek.com>
Date: Tue, 22 Aug 2023 20:58:22 +0800
Subject: [PATCH 1691/1806] wifi: rtw89: phy: modify register setting of
 ENV_MNTR, PHYSTS and DIG

The ENV_MNTR(environment monitor) is the dynamic mechanism which based on
the HW of CCX(Cisco Compatible Extensions) which provide the channel
loading and noisy level indicator to debug or support the 802.11k. The
PHYSTS provide the detail PHY information per packet we received for
debugging. The DIG(dynamic initial gain) is the dynamic mechanism to
adjust the packet detect power level by received signal strength to avoid
false detection of the WiFi packet.

The address of registers used for ENV_MNTR, PHYSTS and DIG of WiFi 7 IC
are different with WiFi 6 series, so we modify the method to access the
register address in order to compatible with all WiFi 7 and 6 ICs.

Signed-off-by: Cheng-Chieh Hsieh <cj.hsieh@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230822125822.23817-7-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h     |   4 +
 drivers/net/wireless/realtek/rtw89/phy.c      | 223 +++++++++++++-----
 drivers/net/wireless/realtek/rtw89/phy.h      |  66 ++++++
 drivers/net/wireless/realtek/rtw89/phy_be.c   |  67 ++++++
 drivers/net/wireless/realtek/rtw89/reg.h      |  13 +
 drivers/net/wireless/realtek/rtw89/rtw8851b.c |   4 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c |   4 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c |   4 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c |   4 +
 9 files changed, 325 insertions(+), 64 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 17f6418e44046..04ce221730f99 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3381,6 +3381,10 @@ struct rtw89_dig_regs {
 	u32 seg0_pd_reg;
 	u32 pd_lower_bound_mask;
 	u32 pd_spatial_reuse_en;
+	u32 bmode_pd_reg;
+	u32 bmode_cca_rssi_limit_en;
+	u32 bmode_pd_lower_bound_reg;
+	u32 bmode_rssi_nocca_low_th_mask;
 	struct rtw89_reg_def p0_lna_init;
 	struct rtw89_reg_def p1_lna_init;
 	struct rtw89_reg_def p0_tia_init;
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 85d3205d6e680..7139146cb3fad 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -3237,7 +3237,9 @@ static u32 rtw89_phy_ccx_idx_to_us(struct rtw89_dev *rtwdev, u16 idx)
 
 static void rtw89_phy_ccx_top_setting_init(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
 	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	const struct rtw89_ccx_regs *ccx = phy->ccx;
 
 	env->ccx_manual_ctrl = false;
 	env->ccx_ongoing = false;
@@ -3245,10 +3247,10 @@ static void rtw89_phy_ccx_top_setting_init(struct rtw89_dev *rtwdev)
 	env->ccx_period = 0;
 	env->ccx_unit_idx = RTW89_CCX_32_US;
 
-	rtw89_phy_set_phy_regs(rtwdev, R_CCX, B_CCX_EN_MSK, 1);
-	rtw89_phy_set_phy_regs(rtwdev, R_CCX, B_CCX_TRIG_OPT_MSK, 1);
-	rtw89_phy_set_phy_regs(rtwdev, R_CCX, B_MEASUREMENT_TRIG_MSK, 1);
-	rtw89_phy_set_phy_regs(rtwdev, R_CCX, B_CCX_EDCCA_OPT_MSK,
+	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->en_mask, 1);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->trig_opt_mask, 1);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->measurement_trig_mask, 1);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->edcca_opt_mask,
 			       RTW89_CCX_EDCCA_BW20_0);
 }
 
@@ -3363,25 +3365,27 @@ ifs_update_finished:
 
 static void rtw89_phy_ifs_clm_set_th_reg(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
 	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	const struct rtw89_ccx_regs *ccx = phy->ccx;
 	u8 i = 0;
 
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T1, B_IFS_T1_TH_LOW_MSK,
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t1_addr, ccx->ifs_t1_th_l_mask,
 			       env->ifs_clm_th_l[0]);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T2, B_IFS_T2_TH_LOW_MSK,
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t2_addr, ccx->ifs_t2_th_l_mask,
 			       env->ifs_clm_th_l[1]);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T3, B_IFS_T3_TH_LOW_MSK,
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t3_addr, ccx->ifs_t3_th_l_mask,
 			       env->ifs_clm_th_l[2]);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T4, B_IFS_T4_TH_LOW_MSK,
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t4_addr, ccx->ifs_t4_th_l_mask,
 			       env->ifs_clm_th_l[3]);
 
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T1, B_IFS_T1_TH_HIGH_MSK,
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t1_addr, ccx->ifs_t1_th_h_mask,
 			       env->ifs_clm_th_h[0]);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T2, B_IFS_T2_TH_HIGH_MSK,
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t2_addr, ccx->ifs_t2_th_h_mask,
 			       env->ifs_clm_th_h[1]);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T3, B_IFS_T3_TH_HIGH_MSK,
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t3_addr, ccx->ifs_t3_th_h_mask,
 			       env->ifs_clm_th_h[2]);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T4, B_IFS_T4_TH_HIGH_MSK,
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t4_addr, ccx->ifs_t4_th_h_mask,
 			       env->ifs_clm_th_h[3]);
 
 	for (i = 0; i < RTW89_IFS_CLM_NUM; i++)
@@ -3392,7 +3396,9 @@ static void rtw89_phy_ifs_clm_set_th_reg(struct rtw89_dev *rtwdev)
 
 static void rtw89_phy_ifs_clm_setting_init(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
 	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	const struct rtw89_ccx_regs *ccx = phy->ccx;
 	struct rtw89_ccx_para_info para = {0};
 
 	env->ifs_clm_app = RTW89_IFS_CLM_BACKGROUND;
@@ -3402,12 +3408,11 @@ static void rtw89_phy_ifs_clm_setting_init(struct rtw89_dev *rtwdev)
 	if (rtw89_phy_ifs_clm_th_update_check(rtwdev, &para))
 		rtw89_phy_ifs_clm_set_th_reg(rtwdev);
 
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_COUNTER, B_IFS_COLLECT_EN,
-			       true);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T1, B_IFS_T1_EN_MSK, true);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T2, B_IFS_T2_EN_MSK, true);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T3, B_IFS_T3_EN_MSK, true);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_T4, B_IFS_T4_EN_MSK, true);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_cnt_addr, ccx->ifs_collect_en_mask, true);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t1_addr, ccx->ifs_t1_en_mask, true);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t2_addr, ccx->ifs_t2_en_mask, true);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t3_addr, ccx->ifs_t3_en_mask, true);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t4_addr, ccx->ifs_t4_en_mask, true);
 }
 
 static int rtw89_phy_ccx_racing_ctrl(struct rtw89_dev *rtwdev,
@@ -3444,12 +3449,14 @@ static int rtw89_phy_ccx_racing_ctrl(struct rtw89_dev *rtwdev,
 
 static void rtw89_phy_ccx_trigger(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
 	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	const struct rtw89_ccx_regs *ccx = phy->ccx;
 
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_COUNTER, B_IFS_COUNTER_CLR_MSK, 0);
-	rtw89_phy_set_phy_regs(rtwdev, R_CCX, B_MEASUREMENT_TRIG_MSK, 0);
-	rtw89_phy_set_phy_regs(rtwdev, R_IFS_COUNTER, B_IFS_COUNTER_CLR_MSK, 1);
-	rtw89_phy_set_phy_regs(rtwdev, R_CCX, B_MEASUREMENT_TRIG_MSK, 1);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_cnt_addr, ccx->ifs_clm_cnt_clear_mask, 0);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->measurement_trig_mask, 0);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_cnt_addr, ccx->ifs_clm_cnt_clear_mask, 1);
+	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->measurement_trig_mask, 1);
 
 	env->ccx_ongoing = true;
 }
@@ -3521,63 +3528,79 @@ static void rtw89_phy_ifs_clm_get_utility(struct rtw89_dev *rtwdev)
 
 static bool rtw89_phy_ifs_clm_get_result(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
 	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	const struct rtw89_ccx_regs *ccx = phy->ccx;
 	u8 i = 0;
 
-	if (rtw89_phy_read32_mask(rtwdev, R_IFSCNT, B_IFSCNT_DONE_MSK) == 0) {
+	if (rtw89_phy_read32_mask(rtwdev, ccx->ifs_total_addr,
+				  ccx->ifs_cnt_done_mask) == 0) {
 		rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK,
 			    "Get IFS_CLM report Fail\n");
 		return false;
 	}
 
 	env->ifs_clm_tx =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_CLM_TX_CNT,
-				      B_IFS_CLM_TX_CNT_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_tx_cnt_addr,
+				      ccx->ifs_clm_tx_cnt_msk);
 	env->ifs_clm_edcca_excl_cca =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_CLM_TX_CNT,
-				      B_IFS_CLM_EDCCA_EXCLUDE_CCA_FA_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_tx_cnt_addr,
+				      ccx->ifs_clm_edcca_excl_cca_fa_mask);
 	env->ifs_clm_cckcca_excl_fa =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_CLM_CCA,
-				      B_IFS_CLM_CCKCCA_EXCLUDE_FA_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_cca_addr,
+				      ccx->ifs_clm_cckcca_excl_fa_mask);
 	env->ifs_clm_ofdmcca_excl_fa =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_CLM_CCA,
-				      B_IFS_CLM_OFDMCCA_EXCLUDE_FA_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_cca_addr,
+				      ccx->ifs_clm_ofdmcca_excl_fa_mask);
 	env->ifs_clm_cckfa =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_CLM_FA,
-				      B_IFS_CLM_CCK_FA_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_fa_addr,
+				      ccx->ifs_clm_cck_fa_mask);
 	env->ifs_clm_ofdmfa =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_CLM_FA,
-				      B_IFS_CLM_OFDM_FA_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_fa_addr,
+				      ccx->ifs_clm_ofdm_fa_mask);
 
 	env->ifs_clm_his[0] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_HIS, B_IFS_T1_HIS_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_his_addr,
+				      ccx->ifs_t1_his_mask);
 	env->ifs_clm_his[1] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_HIS, B_IFS_T2_HIS_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_his_addr,
+				      ccx->ifs_t2_his_mask);
 	env->ifs_clm_his[2] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_HIS, B_IFS_T3_HIS_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_his_addr,
+				      ccx->ifs_t3_his_mask);
 	env->ifs_clm_his[3] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_HIS, B_IFS_T4_HIS_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_his_addr,
+				      ccx->ifs_t4_his_mask);
 
 	env->ifs_clm_avg[0] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_AVG_L, B_IFS_T1_AVG_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_avg_l_addr,
+				      ccx->ifs_t1_avg_mask);
 	env->ifs_clm_avg[1] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_AVG_L, B_IFS_T2_AVG_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_avg_l_addr,
+				      ccx->ifs_t2_avg_mask);
 	env->ifs_clm_avg[2] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_AVG_H, B_IFS_T3_AVG_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_avg_h_addr,
+				      ccx->ifs_t3_avg_mask);
 	env->ifs_clm_avg[3] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_AVG_H, B_IFS_T4_AVG_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_avg_h_addr,
+				      ccx->ifs_t4_avg_mask);
 
 	env->ifs_clm_cca[0] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_CCA_L, B_IFS_T1_CCA_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_cca_l_addr,
+				      ccx->ifs_t1_cca_mask);
 	env->ifs_clm_cca[1] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_CCA_L, B_IFS_T2_CCA_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_cca_l_addr,
+				      ccx->ifs_t2_cca_mask);
 	env->ifs_clm_cca[2] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_CCA_H, B_IFS_T3_CCA_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_cca_h_addr,
+				      ccx->ifs_t3_cca_mask);
 	env->ifs_clm_cca[3] =
-		rtw89_phy_read32_mask(rtwdev, R_IFS_CCA_H, B_IFS_T4_CCA_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_cca_h_addr,
+				      ccx->ifs_t4_cca_mask);
 
 	env->ifs_clm_total_ifs =
-		rtw89_phy_read32_mask(rtwdev, R_IFSCNT, B_IFSCNT_TOTAL_CNT_MSK);
+		rtw89_phy_read32_mask(rtwdev, ccx->ifs_total_addr,
+				      ccx->ifs_total_mask);
 
 	rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK, "IFS-CLM total_ifs = %d\n",
 		    env->ifs_clm_total_ifs);
@@ -3605,7 +3628,9 @@ static bool rtw89_phy_ifs_clm_get_result(struct rtw89_dev *rtwdev)
 static int rtw89_phy_ifs_clm_set(struct rtw89_dev *rtwdev,
 				 struct rtw89_ccx_para_info *para)
 {
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
 	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	const struct rtw89_ccx_regs *ccx = phy->ccx;
 	u32 period = 0;
 	u32 unit_idx = 0;
 
@@ -3621,10 +3646,11 @@ static int rtw89_phy_ifs_clm_set(struct rtw89_dev *rtwdev,
 	if (para->mntr_time != env->ifs_clm_mntr_time) {
 		rtw89_phy_ccx_ms_to_period_unit(rtwdev, para->mntr_time,
 						&period, &unit_idx);
-		rtw89_phy_set_phy_regs(rtwdev, R_IFS_COUNTER,
-				       B_IFS_CLM_PERIOD_MSK, period);
-		rtw89_phy_set_phy_regs(rtwdev, R_IFS_COUNTER,
-				       B_IFS_CLM_COUNTER_UNIT_MSK, unit_idx);
+		rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_cnt_addr,
+				       ccx->ifs_clm_period_mask, period);
+		rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_cnt_addr,
+				       ccx->ifs_clm_cnt_unit_mask,
+				       unit_idx);
 
 		rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK,
 			    "Update IFS-CLM time ((%d)) -> ((%d))\n",
@@ -3742,16 +3768,19 @@ static void rtw89_physts_enable_fail_report(struct rtw89_dev *rtwdev,
 					    bool enable,
 					    enum rtw89_phy_idx phy_idx)
 {
+	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
+	const struct rtw89_physts_regs *physts = phy->physts;
+
 	if (enable) {
-		rtw89_phy_write32_clr(rtwdev, R_PLCP_HISTOGRAM,
-				      B_STS_DIS_TRIG_BY_FAIL);
-		rtw89_phy_write32_clr(rtwdev, R_PLCP_HISTOGRAM,
-				      B_STS_DIS_TRIG_BY_BRK);
+		rtw89_phy_write32_clr(rtwdev, physts->setting_addr,
+				      physts->dis_trigger_fail_mask);
+		rtw89_phy_write32_clr(rtwdev, physts->setting_addr,
+				      physts->dis_trigger_brk_mask);
 	} else {
-		rtw89_phy_write32_set(rtwdev, R_PLCP_HISTOGRAM,
-				      B_STS_DIS_TRIG_BY_FAIL);
-		rtw89_phy_write32_set(rtwdev, R_PLCP_HISTOGRAM,
-				      B_STS_DIS_TRIG_BY_BRK);
+		rtw89_phy_write32_set(rtwdev, physts->setting_addr,
+				      physts->dis_trigger_fail_mask);
+		rtw89_phy_write32_set(rtwdev, physts->setting_addr,
+				      physts->dis_trigger_brk_mask);
 	}
 }
 
@@ -4179,10 +4208,10 @@ static void rtw89_phy_dig_dyn_pd_th(struct rtw89_dev *rtwdev, u8 rssi,
 		    "igi=%d, cck_ccaTH=%d, backoff=%d, cck_PD_low=((%d))dB\n",
 		    final_rssi, cck_cca_th, under_region, pd_val);
 
-	rtw89_phy_write32_mask(rtwdev, R_BMODE_PDTH_EN_V1,
-			       B_BMODE_PDTH_LIMIT_EN_MSK_V1, enable);
-	rtw89_phy_write32_mask(rtwdev, R_BMODE_PDTH_V1,
-			       B_BMODE_PDTH_LOWER_BOUND_MSK_V1, pd_val);
+	rtw89_phy_write32_mask(rtwdev, dig_regs->bmode_pd_reg,
+			       dig_regs->bmode_cca_rssi_limit_en, enable);
+	rtw89_phy_write32_mask(rtwdev, dig_regs->bmode_pd_lower_bound_reg,
+			       dig_regs->bmode_rssi_nocca_low_th_mask, pd_val);
 }
 
 void rtw89_phy_dig_reset(struct rtw89_dev *rtwdev)
@@ -4736,7 +4765,73 @@ void rtw89_phy_config_edcca(struct rtw89_dev *rtwdev, bool scan)
 	}
 }
 
+static const struct rtw89_ccx_regs rtw89_ccx_regs_ax = {
+	.setting_addr = R_CCX,
+	.edcca_opt_mask = B_CCX_EDCCA_OPT_MSK,
+	.measurement_trig_mask = B_MEASUREMENT_TRIG_MSK,
+	.trig_opt_mask = B_CCX_TRIG_OPT_MSK,
+	.en_mask = B_CCX_EN_MSK,
+	.ifs_cnt_addr = R_IFS_COUNTER,
+	.ifs_clm_period_mask = B_IFS_CLM_PERIOD_MSK,
+	.ifs_clm_cnt_unit_mask = B_IFS_CLM_COUNTER_UNIT_MSK,
+	.ifs_clm_cnt_clear_mask = B_IFS_COUNTER_CLR_MSK,
+	.ifs_collect_en_mask = B_IFS_COLLECT_EN,
+	.ifs_t1_addr = R_IFS_T1,
+	.ifs_t1_th_h_mask = B_IFS_T1_TH_HIGH_MSK,
+	.ifs_t1_en_mask = B_IFS_T1_EN_MSK,
+	.ifs_t1_th_l_mask = B_IFS_T1_TH_LOW_MSK,
+	.ifs_t2_addr = R_IFS_T2,
+	.ifs_t2_th_h_mask = B_IFS_T2_TH_HIGH_MSK,
+	.ifs_t2_en_mask = B_IFS_T2_EN_MSK,
+	.ifs_t2_th_l_mask = B_IFS_T2_TH_LOW_MSK,
+	.ifs_t3_addr = R_IFS_T3,
+	.ifs_t3_th_h_mask = B_IFS_T3_TH_HIGH_MSK,
+	.ifs_t3_en_mask = B_IFS_T3_EN_MSK,
+	.ifs_t3_th_l_mask = B_IFS_T3_TH_LOW_MSK,
+	.ifs_t4_addr = R_IFS_T4,
+	.ifs_t4_th_h_mask = B_IFS_T4_TH_HIGH_MSK,
+	.ifs_t4_en_mask = B_IFS_T4_EN_MSK,
+	.ifs_t4_th_l_mask = B_IFS_T4_TH_LOW_MSK,
+	.ifs_clm_tx_cnt_addr = R_IFS_CLM_TX_CNT,
+	.ifs_clm_edcca_excl_cca_fa_mask = B_IFS_CLM_EDCCA_EXCLUDE_CCA_FA_MSK,
+	.ifs_clm_tx_cnt_msk = B_IFS_CLM_TX_CNT_MSK,
+	.ifs_clm_cca_addr = R_IFS_CLM_CCA,
+	.ifs_clm_ofdmcca_excl_fa_mask = B_IFS_CLM_OFDMCCA_EXCLUDE_FA_MSK,
+	.ifs_clm_cckcca_excl_fa_mask = B_IFS_CLM_CCKCCA_EXCLUDE_FA_MSK,
+	.ifs_clm_fa_addr = R_IFS_CLM_FA,
+	.ifs_clm_ofdm_fa_mask = B_IFS_CLM_OFDM_FA_MSK,
+	.ifs_clm_cck_fa_mask = B_IFS_CLM_CCK_FA_MSK,
+	.ifs_his_addr = R_IFS_HIS,
+	.ifs_t4_his_mask = B_IFS_T4_HIS_MSK,
+	.ifs_t3_his_mask = B_IFS_T3_HIS_MSK,
+	.ifs_t2_his_mask = B_IFS_T2_HIS_MSK,
+	.ifs_t1_his_mask = B_IFS_T1_HIS_MSK,
+	.ifs_avg_l_addr = R_IFS_AVG_L,
+	.ifs_t2_avg_mask = B_IFS_T2_AVG_MSK,
+	.ifs_t1_avg_mask = B_IFS_T1_AVG_MSK,
+	.ifs_avg_h_addr = R_IFS_AVG_H,
+	.ifs_t4_avg_mask = B_IFS_T4_AVG_MSK,
+	.ifs_t3_avg_mask = B_IFS_T3_AVG_MSK,
+	.ifs_cca_l_addr = R_IFS_CCA_L,
+	.ifs_t2_cca_mask = B_IFS_T2_CCA_MSK,
+	.ifs_t1_cca_mask = B_IFS_T1_CCA_MSK,
+	.ifs_cca_h_addr = R_IFS_CCA_H,
+	.ifs_t4_cca_mask = B_IFS_T4_CCA_MSK,
+	.ifs_t3_cca_mask = B_IFS_T3_CCA_MSK,
+	.ifs_total_addr = R_IFSCNT,
+	.ifs_cnt_done_mask = B_IFSCNT_DONE_MSK,
+	.ifs_total_mask = B_IFSCNT_TOTAL_CNT_MSK,
+};
+
+static const struct rtw89_physts_regs rtw89_physts_regs_ax = {
+	.setting_addr = R_PLCP_HISTOGRAM,
+	.dis_trigger_fail_mask = B_STS_DIS_TRIG_BY_FAIL,
+	.dis_trigger_brk_mask = B_STS_DIS_TRIG_BY_BRK,
+};
+
 const struct rtw89_phy_gen_def rtw89_phy_gen_ax = {
 	.cr_base = 0x10000,
+	.ccx = &rtw89_ccx_regs_ax,
+	.physts = &rtw89_physts_regs_ax,
 };
 EXPORT_SYMBOL(rtw89_phy_gen_ax);
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index 36a24676b2fe0..d6dc0cbbae43b 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -336,8 +336,74 @@ struct rtw89_nbi_reg_def {
 	struct rtw89_reg_def notch2_en;
 };
 
+struct rtw89_ccx_regs {
+	u32 setting_addr;
+	u32 edcca_opt_mask;
+	u32 measurement_trig_mask;
+	u32 trig_opt_mask;
+	u32 en_mask;
+	u32 ifs_cnt_addr;
+	u32 ifs_clm_period_mask;
+	u32 ifs_clm_cnt_unit_mask;
+	u32 ifs_clm_cnt_clear_mask;
+	u32 ifs_collect_en_mask;
+	u32 ifs_t1_addr;
+	u32 ifs_t1_th_h_mask;
+	u32 ifs_t1_en_mask;
+	u32 ifs_t1_th_l_mask;
+	u32 ifs_t2_addr;
+	u32 ifs_t2_th_h_mask;
+	u32 ifs_t2_en_mask;
+	u32 ifs_t2_th_l_mask;
+	u32 ifs_t3_addr;
+	u32 ifs_t3_th_h_mask;
+	u32 ifs_t3_en_mask;
+	u32 ifs_t3_th_l_mask;
+	u32 ifs_t4_addr;
+	u32 ifs_t4_th_h_mask;
+	u32 ifs_t4_en_mask;
+	u32 ifs_t4_th_l_mask;
+	u32 ifs_clm_tx_cnt_addr;
+	u32 ifs_clm_edcca_excl_cca_fa_mask;
+	u32 ifs_clm_tx_cnt_msk;
+	u32 ifs_clm_cca_addr;
+	u32 ifs_clm_ofdmcca_excl_fa_mask;
+	u32 ifs_clm_cckcca_excl_fa_mask;
+	u32 ifs_clm_fa_addr;
+	u32 ifs_clm_ofdm_fa_mask;
+	u32 ifs_clm_cck_fa_mask;
+	u32 ifs_his_addr;
+	u32 ifs_t4_his_mask;
+	u32 ifs_t3_his_mask;
+	u32 ifs_t2_his_mask;
+	u32 ifs_t1_his_mask;
+	u32 ifs_avg_l_addr;
+	u32 ifs_t2_avg_mask;
+	u32 ifs_t1_avg_mask;
+	u32 ifs_avg_h_addr;
+	u32 ifs_t4_avg_mask;
+	u32 ifs_t3_avg_mask;
+	u32 ifs_cca_l_addr;
+	u32 ifs_t2_cca_mask;
+	u32 ifs_t1_cca_mask;
+	u32 ifs_cca_h_addr;
+	u32 ifs_t4_cca_mask;
+	u32 ifs_t3_cca_mask;
+	u32 ifs_total_addr;
+	u32 ifs_cnt_done_mask;
+	u32 ifs_total_mask;
+};
+
+struct rtw89_physts_regs {
+	u32 setting_addr;
+	u32 dis_trigger_fail_mask;
+	u32 dis_trigger_brk_mask;
+};
+
 struct rtw89_phy_gen_def {
 	u32 cr_base;
+	const struct rtw89_ccx_regs *ccx;
+	const struct rtw89_physts_regs *physts;
 };
 
 extern const struct rtw89_phy_gen_def rtw89_phy_gen_ax;
diff --git a/drivers/net/wireless/realtek/rtw89/phy_be.c b/drivers/net/wireless/realtek/rtw89/phy_be.c
index 143f900d29a67..778e4b0c8e871 100644
--- a/drivers/net/wireless/realtek/rtw89/phy_be.c
+++ b/drivers/net/wireless/realtek/rtw89/phy_be.c
@@ -3,8 +3,75 @@
  */
 
 #include "phy.h"
+#include "reg.h"
+
+static const struct rtw89_ccx_regs rtw89_ccx_regs_be = {
+	.setting_addr = R_CCX,
+	.edcca_opt_mask = B_CCX_EDCCA_OPT_MSK_V1,
+	.measurement_trig_mask = B_MEASUREMENT_TRIG_MSK,
+	.trig_opt_mask = B_CCX_TRIG_OPT_MSK,
+	.en_mask = B_CCX_EN_MSK,
+	.ifs_cnt_addr = R_IFS_COUNTER,
+	.ifs_clm_period_mask = B_IFS_CLM_PERIOD_MSK,
+	.ifs_clm_cnt_unit_mask = B_IFS_CLM_COUNTER_UNIT_MSK,
+	.ifs_clm_cnt_clear_mask = B_IFS_COUNTER_CLR_MSK,
+	.ifs_collect_en_mask = B_IFS_COLLECT_EN,
+	.ifs_t1_addr = R_IFS_T1,
+	.ifs_t1_th_h_mask = B_IFS_T1_TH_HIGH_MSK,
+	.ifs_t1_en_mask = B_IFS_T1_EN_MSK,
+	.ifs_t1_th_l_mask = B_IFS_T1_TH_LOW_MSK,
+	.ifs_t2_addr = R_IFS_T2,
+	.ifs_t2_th_h_mask = B_IFS_T2_TH_HIGH_MSK,
+	.ifs_t2_en_mask = B_IFS_T2_EN_MSK,
+	.ifs_t2_th_l_mask = B_IFS_T2_TH_LOW_MSK,
+	.ifs_t3_addr = R_IFS_T3,
+	.ifs_t3_th_h_mask = B_IFS_T3_TH_HIGH_MSK,
+	.ifs_t3_en_mask = B_IFS_T3_EN_MSK,
+	.ifs_t3_th_l_mask = B_IFS_T3_TH_LOW_MSK,
+	.ifs_t4_addr = R_IFS_T4,
+	.ifs_t4_th_h_mask = B_IFS_T4_TH_HIGH_MSK,
+	.ifs_t4_en_mask = B_IFS_T4_EN_MSK,
+	.ifs_t4_th_l_mask = B_IFS_T4_TH_LOW_MSK,
+	.ifs_clm_tx_cnt_addr = R_IFS_CLM_TX_CNT_V1,
+	.ifs_clm_edcca_excl_cca_fa_mask = B_IFS_CLM_EDCCA_EXCLUDE_CCA_FA_MSK,
+	.ifs_clm_tx_cnt_msk = B_IFS_CLM_TX_CNT_MSK,
+	.ifs_clm_cca_addr = R_IFS_CLM_CCA_V1,
+	.ifs_clm_ofdmcca_excl_fa_mask = B_IFS_CLM_OFDMCCA_EXCLUDE_FA_MSK,
+	.ifs_clm_cckcca_excl_fa_mask = B_IFS_CLM_CCKCCA_EXCLUDE_FA_MSK,
+	.ifs_clm_fa_addr = R_IFS_CLM_FA_V1,
+	.ifs_clm_ofdm_fa_mask = B_IFS_CLM_OFDM_FA_MSK,
+	.ifs_clm_cck_fa_mask = B_IFS_CLM_CCK_FA_MSK,
+	.ifs_his_addr = R_IFS_HIS_V1,
+	.ifs_t4_his_mask = B_IFS_T4_HIS_MSK,
+	.ifs_t3_his_mask = B_IFS_T3_HIS_MSK,
+	.ifs_t2_his_mask = B_IFS_T2_HIS_MSK,
+	.ifs_t1_his_mask = B_IFS_T1_HIS_MSK,
+	.ifs_avg_l_addr = R_IFS_AVG_L_V1,
+	.ifs_t2_avg_mask = B_IFS_T2_AVG_MSK,
+	.ifs_t1_avg_mask = B_IFS_T1_AVG_MSK,
+	.ifs_avg_h_addr = R_IFS_AVG_H_V1,
+	.ifs_t4_avg_mask = B_IFS_T4_AVG_MSK,
+	.ifs_t3_avg_mask = B_IFS_T3_AVG_MSK,
+	.ifs_cca_l_addr = R_IFS_CCA_L_V1,
+	.ifs_t2_cca_mask = B_IFS_T2_CCA_MSK,
+	.ifs_t1_cca_mask = B_IFS_T1_CCA_MSK,
+	.ifs_cca_h_addr = R_IFS_CCA_H_V1,
+	.ifs_t4_cca_mask = B_IFS_T4_CCA_MSK,
+	.ifs_t3_cca_mask = B_IFS_T3_CCA_MSK,
+	.ifs_total_addr = R_IFSCNT_V1,
+	.ifs_cnt_done_mask = B_IFSCNT_DONE_MSK,
+	.ifs_total_mask = B_IFSCNT_TOTAL_CNT_MSK,
+};
+
+static const struct rtw89_physts_regs rtw89_physts_regs_be = {
+	.setting_addr = R_PLCP_HISTOGRAM,
+	.dis_trigger_fail_mask = B_STS_DIS_TRIG_BY_FAIL,
+	.dis_trigger_brk_mask = B_STS_DIS_TRIG_BY_BRK,
+};
 
 const struct rtw89_phy_gen_def rtw89_phy_gen_be = {
 	.cr_base = 0x20000,
+	.ccx = &rtw89_ccx_regs_be,
+	.physts = &rtw89_physts_regs_be,
 };
 EXPORT_SYMBOL(rtw89_phy_gen_be);
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index eab26039242a0..c0aac4d3678a3 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -3998,6 +3998,7 @@
 #define B_DBCC_80P80_SEL_EVM_RPT_EN BIT(0)
 #define R_CCX 0x0C00
 #define B_CCX_EDCCA_OPT_MSK GENMASK(6, 4)
+#define B_CCX_EDCCA_OPT_MSK_V1 GENMASK(7, 4)
 #define B_MEASUREMENT_TRIG_MSK BIT(2)
 #define B_CCX_TRIG_OPT_MSK BIT(1)
 #define B_CCX_EN_MSK BIT(0)
@@ -4089,32 +4090,41 @@
 #define B_SWSI_R_DATA_DONE_V1 BIT(26)
 #define R_TX_COUNTER 0x1A40
 #define R_IFS_CLM_TX_CNT 0x1ACC
+#define R_IFS_CLM_TX_CNT_V1 0x0ECC
 #define B_IFS_CLM_EDCCA_EXCLUDE_CCA_FA_MSK GENMASK(31, 16)
 #define B_IFS_CLM_TX_CNT_MSK GENMASK(15, 0)
 #define R_IFS_CLM_CCA 0x1AD0
+#define R_IFS_CLM_CCA_V1 0x0ED0
 #define B_IFS_CLM_OFDMCCA_EXCLUDE_FA_MSK GENMASK(31, 16)
 #define B_IFS_CLM_CCKCCA_EXCLUDE_FA_MSK GENMASK(15, 0)
 #define R_IFS_CLM_FA 0x1AD4
+#define R_IFS_CLM_FA_V1 0x0ED4
 #define B_IFS_CLM_OFDM_FA_MSK GENMASK(31, 16)
 #define B_IFS_CLM_CCK_FA_MSK GENMASK(15, 0)
 #define R_IFS_HIS 0x1AD8
+#define R_IFS_HIS_V1 0x0ED8
 #define B_IFS_T4_HIS_MSK GENMASK(31, 24)
 #define B_IFS_T3_HIS_MSK GENMASK(23, 16)
 #define B_IFS_T2_HIS_MSK GENMASK(15, 8)
 #define B_IFS_T1_HIS_MSK GENMASK(7, 0)
 #define R_IFS_AVG_L 0x1ADC
+#define R_IFS_AVG_L_V1 0x0EDC
 #define B_IFS_T2_AVG_MSK GENMASK(31, 16)
 #define B_IFS_T1_AVG_MSK GENMASK(15, 0)
 #define R_IFS_AVG_H 0x1AE0
+#define R_IFS_AVG_H_V1 0x0EE0
 #define B_IFS_T4_AVG_MSK GENMASK(31, 16)
 #define B_IFS_T3_AVG_MSK GENMASK(15, 0)
 #define R_IFS_CCA_L 0x1AE4
+#define R_IFS_CCA_L_V1 0x0EE4
 #define B_IFS_T2_CCA_MSK GENMASK(31, 16)
 #define B_IFS_T1_CCA_MSK GENMASK(15, 0)
 #define R_IFS_CCA_H 0x1AE8
+#define R_IFS_CCA_H_V1 0x0EE8
 #define B_IFS_T4_CCA_MSK GENMASK(31, 16)
 #define B_IFS_T3_CCA_MSK GENMASK(15, 0)
 #define R_IFSCNT 0x1AEC
+#define R_IFSCNT_V1 0x0EEC
 #define B_IFSCNT_DONE_MSK BIT(16)
 #define B_IFSCNT_TOTAL_CNT_MSK GENMASK(15, 0)
 #define R_TXAGC_TP 0x1C04
@@ -4385,6 +4395,7 @@
 #define B_PKT_POP_EN BIT(8)
 #define R_SEG0R_PD 0x481C
 #define R_SEG0R_PD_V1 0x4860
+#define R_SEG0R_PD_V2 0x6A74
 #define R_SEG0R_EDCCA_LVL 0x4840
 #define R_SEG0R_EDCCA_LVL_V1 0x4884
 #define B_SEG0R_PPDU_LVL_MSK GENMASK(31, 24)
@@ -4503,8 +4514,10 @@
 #define R_DCFO_COMP_S0_V1 0x4A40
 #define B_DCFO_COMP_S0_V1_MSK GENMASK(13, 0)
 #define R_BMODE_PDTH_V1 0x4B64
+#define R_BMODE_PDTH_V2 0x6708
 #define B_BMODE_PDTH_LOWER_BOUND_MSK_V1 GENMASK(31, 24)
 #define R_BMODE_PDTH_EN_V1 0x4B74
+#define R_BMODE_PDTH_EN_V2 0x6718
 #define B_BMODE_PDTH_LIMIT_EN_MSK_V1 BIT(30)
 #define R_CFO_COMP_SEG1_L 0x5384
 #define R_CFO_COMP_SEG1_H 0x5388
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 52eb7030fd0b1..103893f28b517 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -185,6 +185,10 @@ static const struct rtw89_dig_regs rtw8851b_dig_regs = {
 	.seg0_pd_reg = R_SEG0R_PD_V1,
 	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
 	.pd_spatial_reuse_en = B_SEG0R_PD_SPATIAL_REUSE_EN_MSK_V1,
+	.bmode_pd_reg = R_BMODE_PDTH_EN_V1,
+	.bmode_cca_rssi_limit_en = B_BMODE_PDTH_LIMIT_EN_MSK_V1,
+	.bmode_pd_lower_bound_reg = R_BMODE_PDTH_V1,
+	.bmode_rssi_nocca_low_th_mask = B_BMODE_PDTH_LOWER_BOUND_MSK_V1,
 	.p0_lna_init = {R_PATH0_LNA_INIT_V1, B_PATH0_LNA_INIT_IDX_MSK},
 	.p1_lna_init = {R_PATH1_LNA_INIT_V1, B_PATH1_LNA_INIT_IDX_MSK},
 	.p0_tia_init = {R_PATH0_TIA_INIT_V1, B_PATH0_TIA_INIT_IDX_MSK_V1},
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index eb6aad3bbb852..d068eae6a2f08 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -478,6 +478,10 @@ static const struct rtw89_dig_regs rtw8852a_dig_regs = {
 	.seg0_pd_reg = R_SEG0R_PD,
 	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
 	.pd_spatial_reuse_en = B_SEG0R_PD_SPATIAL_REUSE_EN_MSK,
+	.bmode_pd_reg = R_BMODE_PDTH_EN_V1,
+	.bmode_cca_rssi_limit_en = B_BMODE_PDTH_LIMIT_EN_MSK_V1,
+	.bmode_pd_lower_bound_reg = R_BMODE_PDTH_V1,
+	.bmode_rssi_nocca_low_th_mask = B_BMODE_PDTH_LOWER_BOUND_MSK_V1,
 	.p0_lna_init = {R_PATH0_LNA_INIT, B_PATH0_LNA_INIT_IDX_MSK},
 	.p1_lna_init = {R_PATH1_LNA_INIT, B_PATH1_LNA_INIT_IDX_MSK},
 	.p0_tia_init = {R_PATH0_TIA_INIT, B_PATH0_TIA_INIT_IDX_MSK},
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 49664cc44f364..0063301952b35 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -310,6 +310,10 @@ static const struct rtw89_dig_regs rtw8852b_dig_regs = {
 	.seg0_pd_reg = R_SEG0R_PD_V1,
 	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
 	.pd_spatial_reuse_en = B_SEG0R_PD_SPATIAL_REUSE_EN_MSK_V1,
+	.bmode_pd_reg = R_BMODE_PDTH_EN_V1,
+	.bmode_cca_rssi_limit_en = B_BMODE_PDTH_LIMIT_EN_MSK_V1,
+	.bmode_pd_lower_bound_reg = R_BMODE_PDTH_V1,
+	.bmode_rssi_nocca_low_th_mask = B_BMODE_PDTH_LOWER_BOUND_MSK_V1,
 	.p0_lna_init = {R_PATH0_LNA_INIT_V1, B_PATH0_LNA_INIT_IDX_MSK},
 	.p1_lna_init = {R_PATH1_LNA_INIT_V1, B_PATH1_LNA_INIT_IDX_MSK},
 	.p0_tia_init = {R_PATH0_TIA_INIT_V1, B_PATH0_TIA_INIT_IDX_MSK_V1},
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index abd01e808d831..1e16cc0a05dc9 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -146,6 +146,10 @@ static const struct rtw89_dig_regs rtw8852c_dig_regs = {
 	.seg0_pd_reg = R_SEG0R_PD,
 	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
 	.pd_spatial_reuse_en = B_SEG0R_PD_SPATIAL_REUSE_EN_MSK,
+	.bmode_pd_reg = R_BMODE_PDTH_EN_V1,
+	.bmode_cca_rssi_limit_en = B_BMODE_PDTH_LIMIT_EN_MSK_V1,
+	.bmode_pd_lower_bound_reg = R_BMODE_PDTH_V1,
+	.bmode_rssi_nocca_low_th_mask = B_BMODE_PDTH_LOWER_BOUND_MSK_V1,
 	.p0_lna_init = {R_PATH0_LNA_INIT_V1, B_PATH0_LNA_INIT_IDX_MSK},
 	.p1_lna_init = {R_PATH1_LNA_INIT_V1, B_PATH1_LNA_INIT_IDX_MSK},
 	.p0_tia_init = {R_PATH0_TIA_INIT_V1, B_PATH0_TIA_INIT_IDX_MSK_V1},
-- 
GitLab


From 78d84f35d2c3bf4434e9d785e4b4c33fa8e57878 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 22 Aug 2023 08:27:16 -0700
Subject: [PATCH 1692/1806] wifi: rtw89: Fix clang -Wimplicit-fallthrough in
 rtw89_query_sar()

clang warns (or errors with CONFIG_WERROR=y):

  drivers/net/wireless/realtek/rtw89/sar.c:216:3: error: unannotated fall-through between switch labels [-Werror,-Wimplicit-fallthrough]
    216 |                 case RTW89_TAS_STATE_DPR_FORBID:
        |                 ^
  drivers/net/wireless/realtek/rtw89/sar.c:216:3: note: insert 'break;' to avoid fall-through
    216 |                 case RTW89_TAS_STATE_DPR_FORBID:
        |                 ^
        |                 break;
  1 error generated.

Clang is a little more pedantic than GCC, which does not warn when
falling through to a case that is just break or return. Clang's version
is more in line with the kernel's own stance in deprecated.rst, which
states that all switch/case blocks must end in either break,
fallthrough, continue, goto, or return. Add the missing break to silence
the warning.

Closes: https://github.com/ClangBuiltLinux/linux/issues/1921
Fixes: eb2624f55ad1 ("wifi: rtw89: Introduce Time Averaged SAR (TAS) feature")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230822-rtw89-tas-clang-implicit-fallthrough-v1-1-5cb73f0fa976@kernel.org
---
 drivers/net/wireless/realtek/rtw89/sar.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index 881322f85d79d..aed05b026c6c3 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -211,6 +211,7 @@ s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq)
 		case RTW89_TAS_STATE_DPR_ON:
 			delta = rtw89_txpwr_tas_to_sar(sar_hdl, tas->delta);
 			cfg -= delta;
+			break;
 		case RTW89_TAS_STATE_DPR_FORBID:
 		default:
 			break;
-- 
GitLab


From 290564367ab7fa7e2048bdc00d9c0ad016b41eea Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Wed, 23 Aug 2023 09:50:21 +0200
Subject: [PATCH 1693/1806] wifi: rtw88: usb: kill and free rx urbs on probe
 failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After rtw_usb_alloc_rx_bufs() has been called rx urbs have been
allocated and must be freed in the error path. After rtw_usb_init_rx()
has been called they are submitted, so they also must be killed.

Add these forgotten steps to the probe error path.

Besides the lost memory this also fixes a problem when the driver
fails to download the firmware in rtw_chip_info_setup(). In this
case it can happen that the completion of the rx urbs handler runs
at a time when we already freed our data structures resulting in
a kernel crash.

Fixes: a82dfd33d123 ("wifi: rtw88: Add common USB chip support")
Cc: stable@vger.kernel.org
Reported-by: Ilgaz Öcal <ilgaz@ilgaz.gen.tr>
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Acked-by: Larry Finger <Larry.Finger@lwfinger.net>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230823075021.588596-1-s.hauer@pengutronix.de
---
 drivers/net/wireless/realtek/rtw88/usb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 95b9d933158f2..d879d7e3dc81f 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -826,7 +826,7 @@ int rtw_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
 
 	ret = rtw_core_init(rtwdev);
 	if (ret)
-		goto err_release_hw;
+		goto err_free_rx_bufs;
 
 	ret = rtw_usb_intf_init(rtwdev, intf);
 	if (ret) {
@@ -872,6 +872,9 @@ err_destroy_usb:
 err_deinit_core:
 	rtw_core_deinit(rtwdev);
 
+err_free_rx_bufs:
+	rtw_usb_free_rx_bufs(rtwusb);
+
 err_release_hw:
 	ieee80211_free_hw(hw);
 
-- 
GitLab


From e8afebbf434b7d7aede0122032ece40ae671bb44 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Thu, 24 Aug 2023 14:23:39 +0800
Subject: [PATCH 1694/1806] wifi: rtlwifi: rtl8723: Remove unused function
 rtl8723_cmd_send_packet()

The function rtl8723_cmd_send_packet() is not used anywhere, so remove it.

Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230824062339.1885385-1-ruanjinjie@huawei.com
---
 .../realtek/rtlwifi/rtl8723com/fw_common.c    | 28 -------------------
 .../realtek/rtlwifi/rtl8723com/fw_common.h    |  2 --
 2 files changed, 30 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c
index 36c00b89ccae1..50b79cf8fb3c4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c
@@ -215,31 +215,3 @@ int rtl8723_download_fw(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL_GPL(rtl8723_download_fw);
 
-bool rtl8723_cmd_send_packet(struct ieee80211_hw *hw,
-			     struct sk_buff *skb)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
-	struct rtl8192_tx_ring *ring;
-	struct rtl_tx_desc *pdesc;
-	struct sk_buff *pskb = NULL;
-	unsigned long flags;
-
-	ring = &rtlpci->tx_ring[BEACON_QUEUE];
-
-	pskb = __skb_dequeue(&ring->queue);
-	kfree_skb(pskb);
-	spin_lock_irqsave(&rtlpriv->locks.irq_th_lock, flags);
-
-	pdesc = &ring->desc[0];
-	rtlpriv->cfg->ops->fill_tx_cmddesc(hw, (u8 *)pdesc, 1, 1, skb);
-
-	__skb_queue_tail(&ring->queue, skb);
-
-	spin_unlock_irqrestore(&rtlpriv->locks.irq_th_lock, flags);
-
-	rtlpriv->cfg->ops->tx_polling(hw, BEACON_QUEUE);
-
-	return true;
-}
-EXPORT_SYMBOL_GPL(rtl8723_cmd_send_packet);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.h
index b527fcbbdf080..c8e04f9722aed 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.h
@@ -66,7 +66,5 @@ void rtl8723_write_fw(struct ieee80211_hw *hw,
 		      u8 *buffer, u32 size, u8 max_page);
 int rtl8723_fw_free_to_go(struct ieee80211_hw *hw, bool is_8723be, int count);
 int rtl8723_download_fw(struct ieee80211_hw *hw, bool is_8723be, int count);
-bool rtl8723_cmd_send_packet(struct ieee80211_hw *hw,
-			     struct sk_buff *skb);
 
 #endif
-- 
GitLab


From f0d991a070750ada4f4397304b580ed6f68d3187 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Mon, 21 Aug 2023 12:33:05 -0700
Subject: [PATCH 1695/1806] bpf: Ensure kptr_struct_meta is non-NULL for
 collection insert and refcount_acquire

It's straightforward to prove that kptr_struct_meta must be non-NULL for
any valid call to these kfuncs:

  * btf_parse_struct_metas in btf.c creates a btf_struct_meta for any
    struct in user BTF with a special field (e.g. bpf_refcount,
    {rb,list}_node). These are stored in that BTF's struct_meta_tab.

  * __process_kf_arg_ptr_to_graph_node in verifier.c ensures that nodes
    have {rb,list}_node field and that it's at the correct offset.
    Similarly, check_kfunc_args ensures bpf_refcount field existence for
    node param to bpf_refcount_acquire.

  * So a btf_struct_meta must have been created for the struct type of
    node param to these kfuncs

  * That BTF and its struct_meta_tab are guaranteed to still be around.
    Any arbitrary {rb,list} node the BPF program interacts with either:
    came from bpf_obj_new or a collection removal kfunc in the same
    program, in which case the BTF is associated with the program and
    still around; or came from bpf_kptr_xchg, in which case the BTF was
    associated with the map and is still around

Instead of silently continuing with NULL struct_meta, which caused
confusing bugs such as those addressed by commit 2140a6e3422d ("bpf: Set
kptr_struct_meta for node param to list and rbtree insert funcs"), let's
error out. Then, at runtime, we can confidently say that the
implementations of these kfuncs were given a non-NULL kptr_struct_meta,
meaning that special-field-specific functionality like
bpf_obj_free_fields and the bpf_obj_drop change introduced later in this
series are guaranteed to execute.

This patch doesn't change functionality, just makes it easier to reason
about existing functionality.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230821193311.3290257-2-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0680569f9bd07..5a610896202a8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -18276,6 +18276,13 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
 		struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
 
+		if (desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] &&
+		    !kptr_struct_meta) {
+			verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n",
+				insn_idx);
+			return -EFAULT;
+		}
+
 		insn_buf[0] = addr[0];
 		insn_buf[1] = addr[1];
 		insn_buf[2] = *insn;
@@ -18283,6 +18290,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	} else if (desc->func_id == special_kfunc_list[KF_bpf_list_push_back_impl] ||
 		   desc->func_id == special_kfunc_list[KF_bpf_list_push_front_impl] ||
 		   desc->func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
+		struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
 		int struct_meta_reg = BPF_REG_3;
 		int node_offset_reg = BPF_REG_4;
 
@@ -18292,6 +18300,12 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			node_offset_reg = BPF_REG_5;
 		}
 
+		if (!kptr_struct_meta) {
+			verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n",
+				insn_idx);
+			return -EFAULT;
+		}
+
 		__fixup_collection_insert_kfunc(&env->insn_aux_data[insn_idx], struct_meta_reg,
 						node_offset_reg, insn, insn_buf, cnt);
 	} else if (desc->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] ||
-- 
GitLab


From 2a6d50b50d6d589d43a90d6ca990b8b811e67701 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Mon, 21 Aug 2023 12:33:06 -0700
Subject: [PATCH 1696/1806] bpf: Consider non-owning refs trusted

Recent discussions around default kptr "trustedness" led to changes such
as commit 6fcd486b3a0a ("bpf: Refactor RCU enforcement in the
verifier."). One of the conclusions of those discussions, as expressed
in code and comments in that patch, is that we'd like to move away from
'raw' PTR_TO_BTF_ID without some type flag or other register state
indicating trustedness. Although PTR_TRUSTED and PTR_UNTRUSTED flags mark
this state explicitly, the verifier currently considers trustedness
implied by other register state. For example, owning refs to graph
collection nodes must have a nonzero ref_obj_id, so they pass the
is_trusted_reg check despite having no explicit PTR_{UN}TRUSTED flag.
This patch makes trustedness of non-owning refs to graph collection
nodes explicit as well.

By definition, non-owning refs are currently trusted. Although the ref
has no control over pointee lifetime, due to non-owning ref clobbering
rules (see invalidate_non_owning_refs) dereferencing a non-owning ref is
safe in the critical section controlled by bpf_spin_lock associated with
its owning collection.

Note that the previous statement does not hold true for nodes with shared
ownership due to the use-after-free issue that this series is
addressing. True shared ownership was disabled by commit 7deca5eae833
("bpf: Disable bpf_refcount_acquire kfunc calls until race conditions are fixed"),
though, so the statement holds for now. Further patches in the series will change
the trustedness state of non-owning refs before re-enabling
bpf_refcount_acquire.

Let's add NON_OWN_REF type flag to BPF_REG_TRUSTED_MODIFIERS such that a
non-owning ref reg state would pass is_trusted_reg check. Somewhat
surprisingly, this doesn't result in any change to user-visible
functionality elsewhere in the verifier: graph collection nodes are all
marked MEM_ALLOC, which tends to be handled in separate codepaths from
"raw" PTR_TO_BTF_ID. Regardless, let's be explicit here and document the
current state of things before changing it elsewhere in the series.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230821193311.3290257-3-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index f70f9ac884d24..b6e58dab8e275 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -745,7 +745,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
 	}
 }
 
-#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED)
+#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED | NON_OWN_REF)
 
 static inline bool bpf_type_has_unsafe_modifiers(u32 type)
 {
-- 
GitLab


From 7e26cd12ad1c8f3e55d32542c7e4708a9e6a3c02 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Mon, 21 Aug 2023 12:33:07 -0700
Subject: [PATCH 1697/1806] bpf: Use bpf_mem_free_rcu when bpf_obj_dropping
 refcounted nodes

This is the final fix for the use-after-free scenario described in
commit 7793fc3babe9 ("bpf: Make bpf_refcount_acquire fallible for
non-owning refs"). That commit, by virtue of changing
bpf_refcount_acquire's refcount_inc to a refcount_inc_not_zero, fixed
the "refcount incr on 0" splat. The not_zero check in
refcount_inc_not_zero, though, still occurs on memory that could have
been free'd and reused, so the commit didn't properly fix the root
cause.

This patch actually fixes the issue by free'ing using the recently-added
bpf_mem_free_rcu, which ensures that the memory is not reused until
RCU grace period has elapsed. If that has happened then
there are no non-owning references alive that point to the
recently-free'd memory, so it can be safely reused.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230821193311.3290257-4-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/helpers.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index eb91cae0612ae..945a85e25ac5e 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1913,7 +1913,11 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec)
 
 	if (rec)
 		bpf_obj_free_fields(rec, p);
-	bpf_mem_free(&bpf_global_ma, p);
+
+	if (rec && rec->refcount_off >= 0)
+		bpf_mem_free_rcu(&bpf_global_ma, p);
+	else
+		bpf_mem_free(&bpf_global_ma, p);
 }
 
 __bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
-- 
GitLab


From ba2464c86f182c6fdb69fe2f77a3d04c19a72357 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Mon, 21 Aug 2023 12:33:08 -0700
Subject: [PATCH 1698/1806] bpf: Reenable bpf_refcount_acquire

Now that all reported issues are fixed, bpf_refcount_acquire can be
turned back on. Also reenable all bpf_refcount-related tests which were
disabled.

This a revert of:
 * commit f3514a5d6740 ("selftests/bpf: Disable newly-added 'owner' field test until refcount re-enabled")
 * commit 7deca5eae833 ("bpf: Disable bpf_refcount_acquire kfunc calls until race conditions are fixed")

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230821193311.3290257-5-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                         |  5 +---
 .../bpf/prog_tests/refcounted_kptr.c          | 26 +++++++++++++++++++
 2 files changed, 27 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5a610896202a8..b875f511c3b73 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11217,10 +11217,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 				verbose(env, "arg#%d doesn't point to a type with bpf_refcount field\n", i);
 				return -EINVAL;
 			}
-			if (rec->refcount_off >= 0) {
-				verbose(env, "bpf_refcount_acquire calls are disabled for now\n");
-				return -EINVAL;
-			}
+
 			meta->arg_btf = reg->btf;
 			meta->arg_btf_id = reg->btf_id;
 			break;
diff --git a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
index 7423983472c7c..d6bd5e16e6372 100644
--- a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
@@ -9,12 +9,38 @@
 
 void test_refcounted_kptr(void)
 {
+	RUN_TESTS(refcounted_kptr);
 }
 
 void test_refcounted_kptr_fail(void)
 {
+	RUN_TESTS(refcounted_kptr_fail);
 }
 
 void test_refcounted_kptr_wrong_owner(void)
 {
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct refcounted_kptr *skel;
+	int ret;
+
+	skel = refcounted_kptr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "refcounted_kptr__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_a1), &opts);
+	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_a1");
+	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a1 retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_b), &opts);
+	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_b");
+	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_b retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_a2), &opts);
+	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_a2");
+	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a2 retval");
+	refcounted_kptr__destroy(skel);
 }
-- 
GitLab


From 0816b8c6bf7fc87cec4273dc199e8f0764b9e7b1 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Mon, 21 Aug 2023 12:33:09 -0700
Subject: [PATCH 1699/1806] bpf: Consider non-owning refs to refcounted nodes
 RCU protected

An earlier patch in the series ensures that the underlying memory of
nodes with bpf_refcount - which can have multiple owners - is not reused
until RCU grace period has elapsed. This prevents
use-after-free with non-owning references that may point to
recently-freed memory. While RCU read lock is held, it's safe to
dereference such a non-owning ref, as by definition RCU GP couldn't have
elapsed and therefore underlying memory couldn't have been reused.

From the perspective of verifier "trustedness" non-owning refs to
refcounted nodes are now trusted only in RCU CS and therefore should no
longer pass is_trusted_reg, but rather is_rcu_reg. Let's mark them
MEM_RCU in order to reflect this new state.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/r/20230821193311.3290257-6-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   |  3 ++-
 kernel/bpf/verifier.c | 13 ++++++++++++-
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index eced6400f7780..12596af59c004 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -653,7 +653,8 @@ enum bpf_type_flag {
 	MEM_RCU			= BIT(13 + BPF_BASE_TYPE_BITS),
 
 	/* Used to tag PTR_TO_BTF_ID | MEM_ALLOC references which are non-owning.
-	 * Currently only valid for linked-list and rbtree nodes.
+	 * Currently only valid for linked-list and rbtree nodes. If the nodes
+	 * have a bpf_refcount_field, they must be tagged MEM_RCU as well.
 	 */
 	NON_OWN_REF		= BIT(14 + BPF_BASE_TYPE_BITS),
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b875f511c3b73..4b638eb1bdad5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -8007,6 +8007,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	case PTR_TO_BTF_ID | PTR_TRUSTED:
 	case PTR_TO_BTF_ID | MEM_RCU:
 	case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF:
+	case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU:
 		/* When referenced PTR_TO_BTF_ID is passed to release function,
 		 * its fixed offset must be 0. In the other cases, fixed offset
 		 * can be non-zero. This was already checked above. So pass
@@ -10473,6 +10474,7 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env,
 static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
 {
 	struct bpf_verifier_state *state = env->cur_state;
+	struct btf_record *rec = reg_btf_record(reg);
 
 	if (!state->active_lock.ptr) {
 		verbose(env, "verifier internal error: ref_set_non_owning w/o active lock\n");
@@ -10485,6 +10487,9 @@ static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state
 	}
 
 	reg->type |= NON_OWN_REF;
+	if (rec->refcount_off >= 0)
+		reg->type |= MEM_RCU;
+
 	return 0;
 }
 
@@ -11322,6 +11327,11 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		struct bpf_func_state *state;
 		struct bpf_reg_state *reg;
 
+		if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) {
+			verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n");
+			return -EACCES;
+		}
+
 		if (rcu_lock) {
 			verbose(env, "nested rcu read lock (kernel function %s)\n", func_name);
 			return -EINVAL;
@@ -16684,7 +16694,8 @@ static int do_check(struct bpf_verifier_env *env)
 					return -EINVAL;
 				}
 
-				if (env->cur_state->active_rcu_lock) {
+				if (env->cur_state->active_rcu_lock &&
+				    !in_rbtree_lock_required_cb(env)) {
 					verbose(env, "bpf_rcu_read_unlock is missing\n");
 					return -EINVAL;
 				}
-- 
GitLab


From 5861d1e8dbc4e1a03ebffb96ac041026cdd34c07 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Mon, 21 Aug 2023 12:33:10 -0700
Subject: [PATCH 1700/1806] bpf: Allow bpf_spin_{lock,unlock} in sleepable
 progs

Commit 9e7a4d9831e8 ("bpf: Allow LSM programs to use bpf spin locks")
disabled bpf_spin_lock usage in sleepable progs, stating:

 Sleepable LSM programs can be preempted which means that allowng spin
 locks will need more work (disabling preemption and the verifier
 ensuring that no sleepable helpers are called when a spin lock is
 held).

This patch disables preemption before grabbing bpf_spin_lock. The second
requirement above "no sleepable helpers are called when a spin lock is
held" is implicitly enforced by current verifier logic due to helper
calls in spin_lock CS being disabled except for a few exceptions, none
of which sleep.

Due to above preemption changes, bpf_spin_lock CS can also be considered
a RCU CS, so verifier's in_rcu_cs check is modified to account for this.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/r/20230821193311.3290257-7-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/helpers.c  | 2 ++
 kernel/bpf/verifier.c | 9 +++------
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 945a85e25ac5e..8bd3812fb8df4 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -286,6 +286,7 @@ static inline void __bpf_spin_lock(struct bpf_spin_lock *lock)
 	compiletime_assert(u.val == 0, "__ARCH_SPIN_LOCK_UNLOCKED not 0");
 	BUILD_BUG_ON(sizeof(*l) != sizeof(__u32));
 	BUILD_BUG_ON(sizeof(*lock) != sizeof(__u32));
+	preempt_disable();
 	arch_spin_lock(l);
 }
 
@@ -294,6 +295,7 @@ static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock)
 	arch_spinlock_t *l = (void *)lock;
 
 	arch_spin_unlock(l);
+	preempt_enable();
 }
 
 #else
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4b638eb1bdad5..bb78212fa5b27 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5064,7 +5064,9 @@ bad_type:
  */
 static bool in_rcu_cs(struct bpf_verifier_env *env)
 {
-	return env->cur_state->active_rcu_lock || !env->prog->aux->sleepable;
+	return env->cur_state->active_rcu_lock ||
+	       env->cur_state->active_lock.ptr ||
+	       !env->prog->aux->sleepable;
 }
 
 /* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */
@@ -16975,11 +16977,6 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 			verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
 			return -EINVAL;
 		}
-
-		if (prog->aux->sleepable) {
-			verbose(env, "sleepable progs cannot use bpf_spin_lock yet\n");
-			return -EINVAL;
-		}
 	}
 
 	if (btf_record_has_field(map->record, BPF_TIMER)) {
-- 
GitLab


From 312aa5bde8985dd2aef99d3e20abc0889c6f2a3e Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Mon, 21 Aug 2023 12:33:11 -0700
Subject: [PATCH 1701/1806] selftests/bpf: Add tests for rbtree API interaction
 in sleepable progs

Confirm that the following sleepable prog states fail verification:
  * bpf_rcu_read_unlock before bpf_spin_unlock
     * RCU CS will last at least as long as spin_lock CS

Also confirm that correct usage passes verification, specifically:
  * Explicit use of bpf_rcu_read_{lock, unlock} in sleepable test prog
  * Implied RCU CS due to spin_lock CS

None of the selftest progs actually attach to bpf_testmod's
bpf_testmod_test_read.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/r/20230821193311.3290257-8-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/progs/refcounted_kptr.c     | 71 +++++++++++++++++++
 .../bpf/progs/refcounted_kptr_fail.c          | 28 ++++++++
 2 files changed, 99 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c
index c55652fdc63ab..893a4fdb4b6e9 100644
--- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c
@@ -8,6 +8,9 @@
 #include "bpf_misc.h"
 #include "bpf_experimental.h"
 
+extern void bpf_rcu_read_lock(void) __ksym;
+extern void bpf_rcu_read_unlock(void) __ksym;
+
 struct node_data {
 	long key;
 	long list_data;
@@ -497,4 +500,72 @@ long rbtree_wrong_owner_remove_fail_a2(void *ctx)
 	return 0;
 }
 
+SEC("?fentry.s/bpf_testmod_test_read")
+__success
+int BPF_PROG(rbtree_sleepable_rcu,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	struct bpf_rb_node *rb;
+	struct node_data *n, *m = NULL;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 0;
+
+	bpf_rcu_read_lock();
+	bpf_spin_lock(&lock);
+	bpf_rbtree_add(&root, &n->r, less);
+	rb = bpf_rbtree_first(&root);
+	if (!rb)
+		goto err_out;
+
+	rb = bpf_rbtree_remove(&root, rb);
+	if (!rb)
+		goto err_out;
+
+	m = container_of(rb, struct node_data, r);
+
+err_out:
+	bpf_spin_unlock(&lock);
+	bpf_rcu_read_unlock();
+	if (m)
+		bpf_obj_drop(m);
+	return 0;
+}
+
+SEC("?fentry.s/bpf_testmod_test_read")
+__success
+int BPF_PROG(rbtree_sleepable_rcu_no_explicit_rcu_lock,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	struct bpf_rb_node *rb;
+	struct node_data *n, *m = NULL;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 0;
+
+	/* No explicit bpf_rcu_read_lock */
+	bpf_spin_lock(&lock);
+	bpf_rbtree_add(&root, &n->r, less);
+	rb = bpf_rbtree_first(&root);
+	if (!rb)
+		goto err_out;
+
+	rb = bpf_rbtree_remove(&root, rb);
+	if (!rb)
+		goto err_out;
+
+	m = container_of(rb, struct node_data, r);
+
+err_out:
+	bpf_spin_unlock(&lock);
+	/* No explicit bpf_rcu_read_unlock */
+	if (m)
+		bpf_obj_drop(m);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
index 0b09e5c915b15..1ef07f6ee580d 100644
--- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
@@ -13,6 +13,9 @@ struct node_acquire {
 	struct bpf_refcount refcount;
 };
 
+extern void bpf_rcu_read_lock(void) __ksym;
+extern void bpf_rcu_read_unlock(void) __ksym;
+
 #define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
 private(A) struct bpf_spin_lock glock;
 private(A) struct bpf_rb_root groot __contains(node_acquire, node);
@@ -71,4 +74,29 @@ long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)
 	return 0;
 }
 
+SEC("?fentry.s/bpf_testmod_test_read")
+__failure __msg("function calls are not allowed while holding a lock")
+int BPF_PROG(rbtree_fail_sleepable_lock_across_rcu,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	struct node_acquire *n;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 0;
+
+	/* spin_{lock,unlock} are in different RCU CS */
+	bpf_rcu_read_lock();
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+	bpf_rcu_read_unlock();
+
+	bpf_rcu_read_lock();
+	bpf_spin_unlock(&glock);
+	bpf_rcu_read_unlock();
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
GitLab


From a9ac2e18779597f280d68a5b5f5bdd51a34080fa Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Thu, 24 Aug 2023 13:40:30 +0530
Subject: [PATCH 1702/1806] octeontx2-pf: Fix PFC TX scheduler free

During PFC TX schedulers free, flag TXSCHQ_FREE_ALL was being set
which caused free up all schedulers other than the PFC schedulers.
This patch fixes that to free only the PFC Tx schedulers.

Fixes: 99c969a83d82 ("octeontx2-pf: Add egress PFC support")
Signed-off-by: Suman Ghosh <sumang@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230824081032.436432-2-sumang@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/marvell/octeontx2/nic/otx2_common.c  |  1 +
 .../ethernet/marvell/octeontx2/nic/otx2_dcbnl.c   | 15 ++++-----------
 2 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 3e1c70c746227..b9712040a0bc2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -804,6 +804,7 @@ void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq)
 
 	mutex_unlock(&pfvf->mbox.lock);
 }
+EXPORT_SYMBOL(otx2_txschq_free_one);
 
 void otx2_txschq_stop(struct otx2_nic *pfvf)
 {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
index ccaf97bb1ce03..6492749dd7c89 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
@@ -125,19 +125,12 @@ int otx2_pfc_txschq_alloc(struct otx2_nic *pfvf)
 
 static int otx2_pfc_txschq_stop_one(struct otx2_nic *pfvf, u8 prio)
 {
-	struct nix_txsch_free_req *free_req;
+	int lvl;
 
-	mutex_lock(&pfvf->mbox.lock);
 	/* free PFC TLx nodes */
-	free_req = otx2_mbox_alloc_msg_nix_txsch_free(&pfvf->mbox);
-	if (!free_req) {
-		mutex_unlock(&pfvf->mbox.lock);
-		return -ENOMEM;
-	}
-
-	free_req->flags = TXSCHQ_FREE_ALL;
-	otx2_sync_mbox_msg(&pfvf->mbox);
-	mutex_unlock(&pfvf->mbox.lock);
+	for (lvl = 0; lvl < pfvf->hw.txschq_link_cfg_lvl; lvl++)
+		otx2_txschq_free_one(pfvf, lvl,
+				     pfvf->pfc_schq_list[lvl][prio]);
 
 	pfvf->pfc_alloc_status[prio] = false;
 	return 0;
-- 
GitLab


From 47bcc9c1cf6aa60156c7532983090e86d9d171b6 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Thu, 24 Aug 2023 13:40:31 +0530
Subject: [PATCH 1703/1806] octeontx2-af: CN10KB: fix PFC configuration

Suppose user has enabled pfc with prio 0,1 on a PF netdev(eth0)
	dcb pfc set dev eth0 prio-pfc o:on 1:on
later user enabled pfc priorities 2 and 3 on the VF interface(eth1)
	dcb pfc set dev eth1 prio-pfc 2:on 3:on

Instead of enabling pfc on all priorities (0..3), the driver only
enables on priorities 2,3. This patch corrects the issue by using
the proper CSR address.

Fixes: b9d0fedc6234 ("octeontx2-af: cn10kb: Add RPM_USX MAC support")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230824081032.436432-3-sumang@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rpm.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index b4fcb20c3f4fd..af21e2030cff2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -355,8 +355,8 @@ int rpm_lmac_enadis_pause_frm(void *rpmd, int lmac_id, u8 tx_pause,
 
 void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable)
 {
+	u64 cfg, pfc_class_mask_cfg;
 	rpm_t *rpm = rpmd;
-	u64 cfg;
 
 	/* ALL pause frames received are completely ignored */
 	cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG);
@@ -380,9 +380,11 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable)
 		rpm_write(rpm, 0, RPMX_CMR_CHAN_MSK_OR, ~0ULL);
 
 	/* Disable all PFC classes */
-	cfg = rpm_read(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL);
+	pfc_class_mask_cfg = is_dev_rpm2(rpm) ? RPM2_CMRX_PRT_CBFC_CTL :
+						RPMX_CMRX_PRT_CBFC_CTL;
+	cfg = rpm_read(rpm, lmac_id, pfc_class_mask_cfg);
 	cfg = FIELD_SET(RPM_PFC_CLASS_MASK, 0, cfg);
-	rpm_write(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL, cfg);
+	rpm_write(rpm, lmac_id, pfc_class_mask_cfg, cfg);
 }
 
 int rpm_get_rx_stats(void *rpmd, int lmac_id, int idx, u64 *rx_stat)
@@ -605,8 +607,11 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p
 	if (!is_lmac_valid(rpm, lmac_id))
 		return -ENODEV;
 
+	pfc_class_mask_cfg = is_dev_rpm2(rpm) ? RPM2_CMRX_PRT_CBFC_CTL :
+						RPMX_CMRX_PRT_CBFC_CTL;
+
 	cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG);
-	class_en = rpm_read(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL);
+	class_en = rpm_read(rpm, lmac_id, pfc_class_mask_cfg);
 	pfc_en |= FIELD_GET(RPM_PFC_CLASS_MASK, class_en);
 
 	if (rx_pause) {
@@ -635,10 +640,6 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p
 		cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_PFC_MODE;
 
 	rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
-
-	pfc_class_mask_cfg = is_dev_rpm2(rpm) ? RPM2_CMRX_PRT_CBFC_CTL :
-						RPMX_CMRX_PRT_CBFC_CTL;
-
 	rpm_write(rpm, lmac_id, pfc_class_mask_cfg, class_en);
 
 	return 0;
-- 
GitLab


From 597d0ec0e4ca6a912affea4cc94df08959e9ec74 Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Thu, 24 Aug 2023 13:40:32 +0530
Subject: [PATCH 1704/1806] cteonxt2-pf: Fix backpressure config for multiple
 PFC priorities to work simultaneously

MAC (CGX or RPM) asserts backpressure at TL3 or TL2 node of the egress
hierarchical scheduler tree depending on link level config done. If
there are multiple PFC priorities enabled at a time and for all such
flows to backoff, each priority will have to assert backpressure at
different TL3/TL2 scheduler nodes and these flows will need to submit
egress pkts to these nodes.

Current PFC configuration has an issue where in only one backpressure
scheduler node is being allocated which is resulting in only one PFC
priority to work. This patch fixes this issue.

Fixes: 99c969a83d82 ("octeontx2-pf: Add egress PFC support")
Signed-off-by: Suman Ghosh <sumang@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230824081032.436432-4-sumang@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
index 6492749dd7c89..bfddbff7bcdfb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
@@ -70,7 +70,7 @@ static int otx2_pfc_txschq_alloc_one(struct otx2_nic *pfvf, u8 prio)
 	 * link config level. These rest of the scheduler can be
 	 * same as hw.txschq_list.
 	 */
-	for (lvl = 0; lvl < pfvf->hw.txschq_link_cfg_lvl; lvl++)
+	for (lvl = 0; lvl <= pfvf->hw.txschq_link_cfg_lvl; lvl++)
 		req->schq[lvl] = 1;
 
 	rc = otx2_sync_mbox_msg(&pfvf->mbox);
@@ -83,7 +83,7 @@ static int otx2_pfc_txschq_alloc_one(struct otx2_nic *pfvf, u8 prio)
 		return PTR_ERR(rsp);
 
 	/* Setup transmit scheduler list */
-	for (lvl = 0; lvl < pfvf->hw.txschq_link_cfg_lvl; lvl++) {
+	for (lvl = 0; lvl <= pfvf->hw.txschq_link_cfg_lvl; lvl++) {
 		if (!rsp->schq[lvl])
 			return -ENOSPC;
 
@@ -128,7 +128,7 @@ static int otx2_pfc_txschq_stop_one(struct otx2_nic *pfvf, u8 prio)
 	int lvl;
 
 	/* free PFC TLx nodes */
-	for (lvl = 0; lvl < pfvf->hw.txschq_link_cfg_lvl; lvl++)
+	for (lvl = 0; lvl <= pfvf->hw.txschq_link_cfg_lvl; lvl++)
 		otx2_txschq_free_one(pfvf, lvl,
 				     pfvf->pfc_schq_list[lvl][prio]);
 
-- 
GitLab


From 215eb9f962091ebaab96be2c18cf5d0f5174a4d6 Mon Sep 17 00:00:00 2001
From: Liang Chen <liangchen.linux@gmail.com>
Date: Thu, 24 Aug 2023 20:31:31 +0800
Subject: [PATCH 1705/1806] veth: Avoid NAPI scheduling on failed SKB
 forwarding

When an skb fails to be forwarded to the peer(e.g., skb data buffer
length exceeds MTU), it will not be added to the peer's receive queue.
Therefore, we should schedule the peer's NAPI poll function only when
skb forwarding is successful to avoid unnecessary overhead.

Signed-off-by: Liang Chen <liangchen.linux@gmail.com>
Link: https://lore.kernel.org/r/20230824123131.7673-1-liangchen.linux@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/veth.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index da44bb1331ffb..d43e62ebc2fcd 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -373,14 +373,13 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) {
 		if (!use_napi)
 			dev_lstats_add(dev, length);
+		else
+			__veth_xdp_flush(rq);
 	} else {
 drop:
 		atomic64_inc(&priv->dropped);
 	}
 
-	if (use_napi)
-		__veth_xdp_flush(rq);
-
 	rcu_read_unlock();
 
 	return NETDEV_TX_OK;
-- 
GitLab


From 70934c7c99ad01778eef83e898df4c624e52492f Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 24 Aug 2023 14:37:53 +0100
Subject: [PATCH 1706/1806] net: phylink: add phylink_limit_mac_speed()

Add a function which can be used to limit the phylink MAC capabilities
to an upper speed limit.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZAX3-005pTi-K1@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c | 18 ++++++++++++++++++
 include/linux/phylink.h   |  2 ++
 2 files changed, 20 insertions(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 160bce608c343..0d7354955d626 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -426,6 +426,24 @@ static struct {
 	{ MAC_10HD,     SPEED_10,     DUPLEX_HALF },
 };
 
+/**
+ * phylink_limit_mac_speed - limit the phylink_config to a maximum speed
+ * @config: pointer to a &struct phylink_config
+ * @max_speed: maximum speed
+ *
+ * Mask off MAC capabilities for speeds higher than the @max_speed parameter.
+ * Any further motifications of config.mac_capabilities will override this.
+ */
+void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(phylink_caps_params) &&
+		    phylink_caps_params[i].speed > max_speed; i++)
+		config->mac_capabilities &= ~phylink_caps_params[i].mask;
+}
+EXPORT_SYMBOL_GPL(phylink_limit_mac_speed);
+
 /**
  * phylink_cap_from_speed_duplex - Get mac capability from speed/duplex
  * @speed: the speed to search for
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 789c516c6b4a8..7d07f87364313 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -223,6 +223,8 @@ struct phylink_config {
 	unsigned long mac_capabilities;
 };
 
+void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed);
+
 /**
  * struct phylink_mac_ops - MAC operations structure.
  * @validate: Validate and update the link configuration.
-- 
GitLab


From e80af2acdef73d90ce56d6849d96f2a5862cec2c Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 24 Aug 2023 14:37:58 +0100
Subject: [PATCH 1707/1806] net: stmmac: convert plat->phylink_node to fwnode

All users of plat->phylink_node first convert it to a fwnode. Rather
than repeatedly convert to a fwnode, store it as a fwnode. To reflect
this change, call it plat->port_node instead - it is used for more
than just phylink.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZAX8-005pTo-OT@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c     | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c     | 3 ++-
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +-
 include/linux/stmmac.h                                | 2 +-
 4 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 7a9bbcf03ea51..a2dfb624e10cd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1153,7 +1153,7 @@ static int stmmac_init_phy(struct net_device *dev)
 	if (!phylink_expects_phy(priv->phylink))
 		return 0;
 
-	fwnode = of_fwnode_handle(priv->plat->phylink_node);
+	fwnode = priv->plat->port_node;
 	if (!fwnode)
 		fwnode = dev_fwnode(priv->device);
 
@@ -1200,7 +1200,7 @@ static int stmmac_init_phy(struct net_device *dev)
 static int stmmac_phy_setup(struct stmmac_priv *priv)
 {
 	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
-	struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node);
+	struct fwnode_handle *fwnode = priv->plat->port_node;
 	int max_speed = priv->plat->max_speed;
 	int mode = priv->plat->phy_interface;
 	struct phylink *phylink;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index dd9e2fec53281..fa9e7e7040b94 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -533,11 +533,11 @@ int stmmac_mdio_register(struct net_device *ndev)
 	int err = 0;
 	struct mii_bus *new_bus;
 	struct stmmac_priv *priv = netdev_priv(ndev);
-	struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node);
 	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
 	struct device_node *mdio_node = priv->plat->mdio_node;
 	struct device *dev = ndev->dev.parent;
 	struct fwnode_handle *fixed_node;
+	struct fwnode_handle *fwnode;
 	int addr, found, max_addr;
 
 	if (!mdio_bus_data)
@@ -601,6 +601,7 @@ int stmmac_mdio_register(struct net_device *ndev)
 		stmmac_xgmac2_mdio_read_c45(new_bus, 0, 0, 0);
 
 	/* If fixed-link is set, skip PHY scanning */
+	fwnode = priv->plat->port_node;
 	if (!fwnode)
 		fwnode = dev_fwnode(priv->device);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index be8e79c7aa349..ff330423ee661 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -428,7 +428,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	plat->phy_node = of_parse_phandle(np, "phy-handle", 0);
 
 	/* PHYLINK automatically parses the phy-handle property */
-	plat->phylink_node = np;
+	plat->port_node = of_fwnode_handle(np);
 
 	/* Get max speed of operation from device tree */
 	of_property_read_u32(np, "max-speed", &plat->max_speed);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 784277d666eb5..b2ccd827bb801 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -227,7 +227,7 @@ struct plat_stmmacenet_data {
 	phy_interface_t phy_interface;
 	struct stmmac_mdio_bus_data *mdio_bus_data;
 	struct device_node *phy_node;
-	struct device_node *phylink_node;
+	struct fwnode_handle *port_node;
 	struct device_node *mdio_node;
 	struct stmmac_dma_cfg *dma_cfg;
 	struct stmmac_est *est;
-- 
GitLab


From 1a37c1c198320cce184b70772f78368aba0dec57 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 24 Aug 2023 14:38:03 +0100
Subject: [PATCH 1708/1806] net: stmmac: clean up passing fwnode to phylink

Move the initialisation of the fwnode variable closer to its use
site, rather than scattered throughout stmmac_phy_setup().

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZAXD-005pTv-TN@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a2dfb624e10cd..7d97166194b5d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1200,9 +1200,9 @@ static int stmmac_init_phy(struct net_device *dev)
 static int stmmac_phy_setup(struct stmmac_priv *priv)
 {
 	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
-	struct fwnode_handle *fwnode = priv->plat->port_node;
 	int max_speed = priv->plat->max_speed;
 	int mode = priv->plat->phy_interface;
+	struct fwnode_handle *fwnode;
 	struct phylink *phylink;
 
 	priv->phylink_config.dev = &priv->dev->dev;
@@ -1211,9 +1211,6 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 		priv->phylink_config.ovr_an_inband =
 			mdio_bus_data->xpcs_an_inband;
 
-	if (!fwnode)
-		fwnode = dev_fwnode(priv->device);
-
 	/* Set the platform/firmware specified interface mode */
 	__set_bit(mode, priv->phylink_config.supported_interfaces);
 
@@ -1254,6 +1251,10 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 			~(MAC_10HD | MAC_100HD | MAC_1000HD);
 	priv->phylink_config.mac_managed_pm = true;
 
+	fwnode = priv->plat->port_node;
+	if (!fwnode)
+		fwnode = dev_fwnode(priv->device);
+
 	phylink = phylink_create(&priv->phylink_config, fwnode,
 				 mode, &stmmac_phylink_mac_ops);
 	if (IS_ERR(phylink))
-- 
GitLab


From 2b070cdd3afd53518e04d2813bb9df5ad93505f7 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 24 Aug 2023 14:38:09 +0100
Subject: [PATCH 1709/1806] net: stmmac: use "mdio_bus_data" local variable

We have a local variable for priv->plat->mdio_bus_data, which we use
later in the conditional if() block, but we evaluate the above within
the conditional expression. Use mdio_bus_data instead. Since these
will be the only two users of this local variable, move its assignment
just before the if().

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZAXJ-005pU1-1z@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 7d97166194b5d..fe733a9f5fe4c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1199,7 +1199,7 @@ static int stmmac_init_phy(struct net_device *dev)
 
 static int stmmac_phy_setup(struct stmmac_priv *priv)
 {
-	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
+	struct stmmac_mdio_bus_data *mdio_bus_data;
 	int max_speed = priv->plat->max_speed;
 	int mode = priv->plat->phy_interface;
 	struct fwnode_handle *fwnode;
@@ -1207,7 +1207,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 
 	priv->phylink_config.dev = &priv->dev->dev;
 	priv->phylink_config.type = PHYLINK_NETDEV;
-	if (priv->plat->mdio_bus_data)
+
+	mdio_bus_data = priv->plat->mdio_bus_data;
+	if (mdio_bus_data)
 		priv->phylink_config.ovr_an_inband =
 			mdio_bus_data->xpcs_an_inband;
 
-- 
GitLab


From a4ac612bd345d676f2d70125a729df2861f91c1d Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 24 Aug 2023 14:38:14 +0100
Subject: [PATCH 1710/1806] net: stmmac: use phylink_limit_mac_speed()

Use phylink_limit_mac_speed() to limit the MAC capabilities rather
than coding this for each speed.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZAXO-005pU7-61@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 35 ++++++++-----------
 1 file changed, 14 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fe733a9f5fe4c..30a085f2b8fac 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1200,10 +1200,10 @@ static int stmmac_init_phy(struct net_device *dev)
 static int stmmac_phy_setup(struct stmmac_priv *priv)
 {
 	struct stmmac_mdio_bus_data *mdio_bus_data;
-	int max_speed = priv->plat->max_speed;
 	int mode = priv->plat->phy_interface;
 	struct fwnode_handle *fwnode;
 	struct phylink *phylink;
+	int max_speed;
 
 	priv->phylink_config.dev = &priv->dev->dev;
 	priv->phylink_config.type = PHYLINK_NETDEV;
@@ -1222,29 +1222,18 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 				    priv->phylink_config.supported_interfaces);
 
 	priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
-		MAC_10 | MAC_100;
-
-	if (!max_speed || max_speed >= 1000)
-		priv->phylink_config.mac_capabilities |= MAC_1000;
+		MAC_10 | MAC_100 | MAC_1000;
 
 	if (priv->plat->has_gmac4) {
-		if (!max_speed || max_speed >= 2500)
-			priv->phylink_config.mac_capabilities |= MAC_2500FD;
+		priv->phylink_config.mac_capabilities |= MAC_2500FD;
 	} else if (priv->plat->has_xgmac) {
-		if (!max_speed || max_speed >= 2500)
-			priv->phylink_config.mac_capabilities |= MAC_2500FD;
-		if (!max_speed || max_speed >= 5000)
-			priv->phylink_config.mac_capabilities |= MAC_5000FD;
-		if (!max_speed || max_speed >= 10000)
-			priv->phylink_config.mac_capabilities |= MAC_10000FD;
-		if (!max_speed || max_speed >= 25000)
-			priv->phylink_config.mac_capabilities |= MAC_25000FD;
-		if (!max_speed || max_speed >= 40000)
-			priv->phylink_config.mac_capabilities |= MAC_40000FD;
-		if (!max_speed || max_speed >= 50000)
-			priv->phylink_config.mac_capabilities |= MAC_50000FD;
-		if (!max_speed || max_speed >= 100000)
-			priv->phylink_config.mac_capabilities |= MAC_100000FD;
+		priv->phylink_config.mac_capabilities |= MAC_2500FD;
+		priv->phylink_config.mac_capabilities |= MAC_5000FD;
+		priv->phylink_config.mac_capabilities |= MAC_10000FD;
+		priv->phylink_config.mac_capabilities |= MAC_25000FD;
+		priv->phylink_config.mac_capabilities |= MAC_40000FD;
+		priv->phylink_config.mac_capabilities |= MAC_50000FD;
+		priv->phylink_config.mac_capabilities |= MAC_100000FD;
 	}
 
 	/* Half-Duplex can only work with single queue */
@@ -1253,6 +1242,10 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 			~(MAC_10HD | MAC_100HD | MAC_1000HD);
 	priv->phylink_config.mac_managed_pm = true;
 
+	max_speed = priv->plat->max_speed;
+	if (max_speed)
+		phylink_limit_mac_speed(&priv->phylink_config, max_speed);
+
 	fwnode = priv->plat->port_node;
 	if (!fwnode)
 		fwnode = dev_fwnode(priv->device);
-- 
GitLab


From d42ca04e044891c9cf2e5a8dbcef85dd57f94827 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 24 Aug 2023 14:38:19 +0100
Subject: [PATCH 1711/1806] net: stmmac: provide stmmac_mac_phylink_get_caps()

Allow MACs to provide their own capabilities via the MAC operations
struct.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZAXT-005pUD-Aj@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/hwif.h        | 4 ++++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 +++
 2 files changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 238f17c50a1ea..b95d3e1378136 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -300,6 +300,8 @@ struct stmmac_est;
 struct stmmac_ops {
 	/* MAC core initialization */
 	void (*core_init)(struct mac_device_info *hw, struct net_device *dev);
+	/* Get phylink capabilities */
+	void (*phylink_get_caps)(struct stmmac_priv *priv);
 	/* Enable the MAC RX/TX */
 	void (*set_mac)(void __iomem *ioaddr, bool enable);
 	/* Enable and verify that the IPC module is supported */
@@ -419,6 +421,8 @@ struct stmmac_ops {
 
 #define stmmac_core_init(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, core_init, __args)
+#define stmmac_mac_phylink_get_caps(__priv) \
+	stmmac_do_void_callback(__priv, mac, phylink_get_caps, __priv)
 #define stmmac_mac_set(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, set_mac, __args)
 #define stmmac_rx_ipc(__priv, __args...) \
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 30a085f2b8fac..a9cf6aecdddfe 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1224,6 +1224,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 	priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100 | MAC_1000;
 
+	/* Get the MAC specific capabilities */
+	stmmac_mac_phylink_get_caps(priv);
+
 	if (priv->plat->has_gmac4) {
 		priv->phylink_config.mac_capabilities |= MAC_2500FD;
 	} else if (priv->plat->has_xgmac) {
-- 
GitLab


From f1dae3d222c63b605d75d338a34e975c8a018640 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 24 Aug 2023 14:38:24 +0100
Subject: [PATCH 1712/1806] net: stmmac: move gmac4 specific phylink
 capabilities to gmac4

Move the setup of gmac4 speicifc phylink capabilities into gmac4 code.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZAXY-005pUJ-Ez@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 8 ++++++++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +---
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 03b1c5a97826e..c6ff1fa0e04d8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -68,6 +68,11 @@ static void dwmac4_core_init(struct mac_device_info *hw,
 		init_waitqueue_head(&priv->tstamp_busy_wait);
 }
 
+static void dwmac4_phylink_get_caps(struct stmmac_priv *priv)
+{
+	priv->phylink_config.mac_capabilities |= MAC_2500FD;
+}
+
 static void dwmac4_rx_queue_enable(struct mac_device_info *hw,
 				   u8 mode, u32 queue)
 {
@@ -1131,6 +1136,7 @@ static int dwmac4_config_l4_filter(struct mac_device_info *hw, u32 filter_no,
 
 const struct stmmac_ops dwmac4_ops = {
 	.core_init = dwmac4_core_init,
+	.phylink_get_caps = dwmac4_phylink_get_caps,
 	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac4_rx_ipc_enable,
 	.rx_queue_enable = dwmac4_rx_queue_enable,
@@ -1173,6 +1179,7 @@ const struct stmmac_ops dwmac4_ops = {
 
 const struct stmmac_ops dwmac410_ops = {
 	.core_init = dwmac4_core_init,
+	.phylink_get_caps = dwmac4_phylink_get_caps,
 	.set_mac = stmmac_dwmac4_set_mac,
 	.rx_ipc = dwmac4_rx_ipc_enable,
 	.rx_queue_enable = dwmac4_rx_queue_enable,
@@ -1221,6 +1228,7 @@ const struct stmmac_ops dwmac410_ops = {
 
 const struct stmmac_ops dwmac510_ops = {
 	.core_init = dwmac4_core_init,
+	.phylink_get_caps = dwmac4_phylink_get_caps,
 	.set_mac = stmmac_dwmac4_set_mac,
 	.rx_ipc = dwmac4_rx_ipc_enable,
 	.rx_queue_enable = dwmac4_rx_queue_enable,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a9cf6aecdddfe..0b02845e7e9db 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1227,9 +1227,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 	/* Get the MAC specific capabilities */
 	stmmac_mac_phylink_get_caps(priv);
 
-	if (priv->plat->has_gmac4) {
-		priv->phylink_config.mac_capabilities |= MAC_2500FD;
-	} else if (priv->plat->has_xgmac) {
+	if (priv->plat->has_xgmac) {
 		priv->phylink_config.mac_capabilities |= MAC_2500FD;
 		priv->phylink_config.mac_capabilities |= MAC_5000FD;
 		priv->phylink_config.mac_capabilities |= MAC_10000FD;
-- 
GitLab


From bedf9b81233dc3c7f70c65cd5370de883199e3f6 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 24 Aug 2023 14:38:29 +0100
Subject: [PATCH 1713/1806] net: stmmac: move xgmac specific phylink caps to
 dwxgmac2 core

Move the xgmac specific phylink capabilities to the dwxgmac2 support
core.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZAXd-005pUP-JL@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 10 ++++++++++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c   | 10 ----------
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 34e1b0c3f3461..f352be269deb5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -47,6 +47,14 @@ static void dwxgmac2_core_init(struct mac_device_info *hw,
 	writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN);
 }
 
+static void xgmac_phylink_get_caps(struct stmmac_priv *priv)
+{
+	priv->phylink_config.mac_capabilities |= MAC_2500FD | MAC_5000FD |
+						 MAC_10000FD | MAC_25000FD |
+						 MAC_40000FD | MAC_50000FD |
+						 MAC_100000FD;
+}
+
 static void dwxgmac2_set_mac(void __iomem *ioaddr, bool enable)
 {
 	u32 tx = readl(ioaddr + XGMAC_TX_CONFIG);
@@ -1490,6 +1498,7 @@ static void dwxgmac3_fpe_configure(void __iomem *ioaddr, u32 num_txq,
 
 const struct stmmac_ops dwxgmac210_ops = {
 	.core_init = dwxgmac2_core_init,
+	.phylink_get_caps = xgmac_phylink_get_caps,
 	.set_mac = dwxgmac2_set_mac,
 	.rx_ipc = dwxgmac2_rx_ipc,
 	.rx_queue_enable = dwxgmac2_rx_queue_enable,
@@ -1551,6 +1560,7 @@ static void dwxlgmac2_rx_queue_enable(struct mac_device_info *hw, u8 mode,
 
 const struct stmmac_ops dwxlgmac2_ops = {
 	.core_init = dwxgmac2_core_init,
+	.phylink_get_caps = xgmac_phylink_get_caps,
 	.set_mac = dwxgmac2_set_mac,
 	.rx_ipc = dwxgmac2_rx_ipc,
 	.rx_queue_enable = dwxlgmac2_rx_queue_enable,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 0b02845e7e9db..5cf8304564c65 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1227,16 +1227,6 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 	/* Get the MAC specific capabilities */
 	stmmac_mac_phylink_get_caps(priv);
 
-	if (priv->plat->has_xgmac) {
-		priv->phylink_config.mac_capabilities |= MAC_2500FD;
-		priv->phylink_config.mac_capabilities |= MAC_5000FD;
-		priv->phylink_config.mac_capabilities |= MAC_10000FD;
-		priv->phylink_config.mac_capabilities |= MAC_25000FD;
-		priv->phylink_config.mac_capabilities |= MAC_40000FD;
-		priv->phylink_config.mac_capabilities |= MAC_50000FD;
-		priv->phylink_config.mac_capabilities |= MAC_100000FD;
-	}
-
 	/* Half-Duplex can only work with single queue */
 	if (priv->plat->tx_queues_to_use > 1)
 		priv->phylink_config.mac_capabilities &=
-- 
GitLab


From 64961f1b8ca1c6f515478887db70cd0e88f47af4 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 24 Aug 2023 14:38:34 +0100
Subject: [PATCH 1714/1806] net: stmmac: move
 priv->phylink_config.mac_managed_pm

Move priv->phylink_config.mac_managed_pm to be along side the other
phylink initialisations.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZAXi-005pUV-Nq@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5cf8304564c65..7cfc2918c913f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1207,6 +1207,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 
 	priv->phylink_config.dev = &priv->dev->dev;
 	priv->phylink_config.type = PHYLINK_NETDEV;
+	priv->phylink_config.mac_managed_pm = true;
 
 	mdio_bus_data = priv->plat->mdio_bus_data;
 	if (mdio_bus_data)
@@ -1231,7 +1232,6 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 	if (priv->plat->tx_queues_to_use > 1)
 		priv->phylink_config.mac_capabilities &=
 			~(MAC_10HD | MAC_100HD | MAC_1000HD);
-	priv->phylink_config.mac_managed_pm = true;
 
 	max_speed = priv->plat->max_speed;
 	if (max_speed)
-- 
GitLab


From 76649fc93f097785e9b173950d0fbb1d7a9c4a76 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 24 Aug 2023 14:38:39 +0100
Subject: [PATCH 1715/1806] net: stmmac: convert half-duplex support to
 positive logic

Rather than detecting when half-duplex is not supported, and clearing
the MAC capabilities, reverse the if() condition and use it to set the
capabilities instead.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZAXn-005pUb-SP@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 7cfc2918c913f..33ca5c50bdcd8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1223,16 +1223,17 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 				    priv->phylink_config.supported_interfaces);
 
 	priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
-		MAC_10 | MAC_100 | MAC_1000;
+						MAC_10FD | MAC_100FD |
+						MAC_1000FD;
+
+	/* Half-Duplex can only work with single queue */
+	if (priv->plat->tx_queues_to_use <= 1)
+		priv->phylink_config.mac_capabilities |= MAC_10HD | MAC_100HD |
+							 MAC_1000HD;
 
 	/* Get the MAC specific capabilities */
 	stmmac_mac_phylink_get_caps(priv);
 
-	/* Half-Duplex can only work with single queue */
-	if (priv->plat->tx_queues_to_use > 1)
-		priv->phylink_config.mac_capabilities &=
-			~(MAC_10HD | MAC_100HD | MAC_1000HD);
-
 	max_speed = priv->plat->max_speed;
 	if (max_speed)
 		phylink_limit_mac_speed(&priv->phylink_config, max_speed);
-- 
GitLab


From a02430c06f56931675f19a914b11a960607b2505 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 24 Aug 2023 14:24:31 -0700
Subject: [PATCH 1716/1806] tools: ynl-gen: fix uAPI generation after tempfile
 changes

We use a tempfile for code generation, to avoid wiping the target
file out if the code generator crashes. File contents are copied
from tempfile to actual destination at the end of main().

uAPI generation is relatively simple so when generating the uAPI
header we return from main() early, and never reach the "copy code
over" stage. Since commit under Fixes uAPI headers are not updated
by ynl-gen.

Move the copy/commit of the code into CodeWriter, to make it
easier to call at any point in time. Hook it into the destructor
to make sure we don't miss calling it.

Fixes: f65f305ae008 ("tools: ynl-gen: use temporary file for rendering")
Link: https://lore.kernel.org/r/20230824212431.1683612-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 9209bdcca9c61..897af958cee85 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -1045,14 +1045,30 @@ class RenderInfo:
 
 
 class CodeWriter:
-    def __init__(self, nlib, out_file):
+    def __init__(self, nlib, out_file=None):
         self.nlib = nlib
 
         self._nl = False
         self._block_end = False
         self._silent_block = False
         self._ind = 0
-        self._out = out_file
+        if out_file is None:
+            self._out = os.sys.stdout
+        else:
+            self._out = tempfile.TemporaryFile('w+')
+            self._out_file = out_file
+
+    def __del__(self):
+        self.close_out_file()
+
+    def close_out_file(self):
+        if self._out == os.sys.stdout:
+            return
+        with open(self._out_file, 'w+') as out_file:
+            self._out.seek(0)
+            shutil.copyfileobj(self._out, out_file)
+            self._out.close()
+        self._out = os.sys.stdout
 
     @classmethod
     def _is_cond(cls, line):
@@ -2313,11 +2329,9 @@ def main():
     parser.add_argument('--source', dest='header', action='store_false')
     parser.add_argument('--user-header', nargs='+', default=[])
     parser.add_argument('--exclude-op', action='append', default=[])
-    parser.add_argument('-o', dest='out_file', type=str)
+    parser.add_argument('-o', dest='out_file', type=str, default=None)
     args = parser.parse_args()
 
-    tmp_file = tempfile.TemporaryFile('w+') if args.out_file else os.sys.stdout
-
     if args.header is None:
         parser.error("--header or --source is required")
 
@@ -2341,7 +2355,7 @@ def main():
         print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation')
         os.sys.exit(1)
 
-    cw = CodeWriter(BaseNlLib(), tmp_file)
+    cw = CodeWriter(BaseNlLib(), args.out_file)
 
     _, spec_kernel = find_kernel_root(args.spec)
     if args.mode == 'uapi' or args.header:
@@ -2590,10 +2604,6 @@ def main():
     if args.header:
         cw.p(f'#endif /* {hdr_prot} */')
 
-    if args.out_file:
-        out_file = open(args.out_file, 'w+')
-        tmp_file.seek(0)
-        shutil.copyfileobj(tmp_file, out_file)
 
 if __name__ == "__main__":
     main()
-- 
GitLab


From c4413a20fa6d7c4888009fb7dd391685f196cd36 Mon Sep 17 00:00:00 2001
From: Alex Austin <alex.austin@amd.com>
Date: Thu, 24 Aug 2023 17:46:57 +0100
Subject: [PATCH 1717/1806] sfc: Check firmware supports Ethernet PTP filter

Not all firmware variants support RSS filters. Do not fail all PTP
functionality when raw ethernet PTP filters fail to insert.

Fixes: e4616f64726b ("sfc: support PTP over Ethernet")
Signed-off-by: Alex Austin <alex.austin@amd.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Link: https://lore.kernel.org/r/20230824164657.42379-1-alex.austin@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/ptp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 0c40571133cb9..00cf6de3bb2be 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1485,7 +1485,9 @@ static int efx_ptp_insert_multicast_filters(struct efx_nic *efx)
 			goto fail;
 
 		rc = efx_ptp_insert_eth_multicast_filter(efx);
-		if (rc < 0)
+
+		/* Not all firmware variants support this filter */
+		if (rc < 0 && rc != -EPROTONOSUPPORT)
 			goto fail;
 	}
 
-- 
GitLab


From b3d26c5702c7d6c45456326e56d2ccf3f103e60f Mon Sep 17 00:00:00 2001
From: Budimir Markovic <markovicbudimir@gmail.com>
Date: Thu, 24 Aug 2023 01:49:05 -0700
Subject: [PATCH 1718/1806] net/sched: sch_hfsc: Ensure inner classes have fsc
 curve

HFSC assumes that inner classes have an fsc curve, but it is currently
possible for classes without an fsc curve to become parents. This leads
to bugs including a use-after-free.

Don't allow non-root classes without HFSC_FSC to become parents.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Budimir Markovic <markovicbudimir@gmail.com>
Signed-off-by: Budimir Markovic <markovicbudimir@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/20230824084905.422-1-markovicbudimir@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_hfsc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 70b0c5873d326..61d52594ff6d8 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1012,6 +1012,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		if (parent == NULL)
 			return -ENOENT;
 	}
+	if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) {
+		NL_SET_ERR_MSG(extack, "Invalid parent - parent class must have FSC");
+		return -EINVAL;
+	}
 
 	if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0)
 		return -EINVAL;
-- 
GitLab


From 52d08fda3516145f26d71af3c19f709e62f928d2 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Thu, 24 Aug 2023 15:22:21 +0100
Subject: [PATCH 1719/1806] doc/netlink: Add delete operation to ovs_vport spec

Add del operation to the spec to help with testing.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20230824142221.71339-1-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ovs_vport.yaml | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/Documentation/netlink/specs/ovs_vport.yaml b/Documentation/netlink/specs/ovs_vport.yaml
index ef298b0014453..f65ce62cd60de 100644
--- a/Documentation/netlink/specs/ovs_vport.yaml
+++ b/Documentation/netlink/specs/ovs_vport.yaml
@@ -138,10 +138,21 @@ operations:
             - dp-ifindex
             - ifindex
             - options
+    -
+      name: del
+      doc: Delete existing OVS vport from a data path
+      attribute-set: vport
+      fixed-header: ovs-header
+      do:
+        request:
+          attributes:
+            - dp-ifindex
+            - port-no
+            - type
+            - name
     -
       name: get
       doc: Get / dump OVS vport configuration and state
-      value: 3
       attribute-set: vport
       fixed-header: ovs-header
       do: &vport-get-op
-- 
GitLab


From 91202ce78fcd070982a115f0bf6f328af619aa00 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Thu, 24 Aug 2023 09:17:50 -0700
Subject: [PATCH 1720/1806] pds_core: protect devlink callbacks from fw_down
 state

Don't access structs that have been cleared when in the fw_down
state and the various structs have been cleaned and are waiting
to recover.  This caused a panic on rmmod when already in fw_down
and devlink_param_unregister() tried to check the parameters.

Fixes: 40ced8944536 ("pds_core: devlink params for enabling VIF support")
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230824161754.34264-2-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/devlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index 9c6b3653c1c7c..d9607033bbf21 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -10,6 +10,9 @@ pdsc_viftype *pdsc_dl_find_viftype_by_id(struct pdsc *pdsc,
 {
 	int vt;
 
+	if (!pdsc->viftype_status)
+		return NULL;
+
 	for (vt = 0; vt < PDS_DEV_TYPE_MAX; vt++) {
 		if (pdsc->viftype_status[vt].dl_id == dl_id)
 			return &pdsc->viftype_status[vt];
-- 
GitLab


From e48b894a1db7f6ce66bff0402ab21ff9f0e56034 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Thu, 24 Aug 2023 09:17:51 -0700
Subject: [PATCH 1721/1806] pds_core: no health reporter in VF

Make sure the health reporter is set up before we use it in
our devlink health updates, especially since the VF doesn't
set up the health reporter.

Fixes: 25b450c05a49 ("pds_core: add devlink health facilities")
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230824161754.34264-3-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/core.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index f2c79456d7452..383e3311a52c2 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -524,7 +524,8 @@ static void pdsc_fw_down(struct pdsc *pdsc)
 	}
 
 	/* Notify clients of fw_down */
-	devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc);
+	if (pdsc->fw_reporter)
+		devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc);
 	pdsc_notify(PDS_EVENT_RESET, &reset_event);
 
 	pdsc_stop(pdsc);
@@ -554,8 +555,9 @@ static void pdsc_fw_up(struct pdsc *pdsc)
 
 	/* Notify clients of fw_up */
 	pdsc->fw_recoveries++;
-	devlink_health_reporter_state_update(pdsc->fw_reporter,
-					     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+	if (pdsc->fw_reporter)
+		devlink_health_reporter_state_update(pdsc->fw_reporter,
+						     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
 	pdsc_notify(PDS_EVENT_RESET, &reset_event);
 
 	return;
-- 
GitLab


From 95e383226d6fcda6c217912f11edf8d74de9cc85 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Thu, 24 Aug 2023 09:17:52 -0700
Subject: [PATCH 1722/1806] pds_core: no reset command for VF

The VF doesn't need to send a reset command, and in a PCI reset
scenario it might not have a valid IO space to write to anyway.

Fixes: 523847df1b37 ("pds_core: add devcmd device interfaces")
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230824161754.34264-4-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 383e3311a52c2..36f9b932b9e2a 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -464,7 +464,8 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 {
 	int i;
 
-	pdsc_devcmd_reset(pdsc);
+	if (!pdsc->pdev->is_virtfn)
+		pdsc_devcmd_reset(pdsc);
 	pdsc_qcq_free(pdsc, &pdsc->notifyqcq);
 	pdsc_qcq_free(pdsc, &pdsc->adminqcq);
 
-- 
GitLab


From 969cfd4c8ca50c32901342cdd3d677c3ffe61371 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Thu, 24 Aug 2023 09:17:53 -0700
Subject: [PATCH 1723/1806] pds_core: check for work queue before use

Add a check that the wq exists before queuing up work for a
failed devcmd, as the PF is responsible for health and the VF
doesn't have a wq.

Fixes: c2dbb0904310 ("pds_core: health timer and workqueue")
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230824161754.34264-5-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index debe5216fe29e..524f422ee7ace 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -183,7 +183,7 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd,
 	err = pdsc_devcmd_wait(pdsc, max_seconds);
 	memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp));
 
-	if (err == -ENXIO || err == -ETIMEDOUT)
+	if ((err == -ENXIO || err == -ETIMEDOUT) && pdsc->wq)
 		queue_work(pdsc->wq, &pdsc->health_work);
 
 	return err;
-- 
GitLab


From 0ea064e74bc8f915aba3f2d0fb3418247a09b73d Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Thu, 24 Aug 2023 09:17:54 -0700
Subject: [PATCH 1724/1806] pds_core: pass opcode to devcmd_wait

Don't rely on the PCI memory for the devcmd opcode because we
read a 0xff value if the PCI bus is broken, which can cause us
to report a bogus dev_cmd opcode later.

Fixes: 523847df1b37 ("pds_core: add devcmd device interfaces")
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230824161754.34264-6-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/dev.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index 524f422ee7ace..f77cd9f5a2fda 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -121,7 +121,7 @@ static const char *pdsc_devcmd_str(int opcode)
 	}
 }
 
-static int pdsc_devcmd_wait(struct pdsc *pdsc, int max_seconds)
+static int pdsc_devcmd_wait(struct pdsc *pdsc, u8 opcode, int max_seconds)
 {
 	struct device *dev = pdsc->dev;
 	unsigned long start_time;
@@ -131,9 +131,6 @@ static int pdsc_devcmd_wait(struct pdsc *pdsc, int max_seconds)
 	int done = 0;
 	int err = 0;
 	int status;
-	int opcode;
-
-	opcode = ioread8(&pdsc->cmd_regs->cmd.opcode);
 
 	start_time = jiffies;
 	max_wait = start_time + (max_seconds * HZ);
@@ -180,7 +177,7 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd,
 
 	memcpy_toio(&pdsc->cmd_regs->cmd, cmd, sizeof(*cmd));
 	pdsc_devcmd_dbell(pdsc);
-	err = pdsc_devcmd_wait(pdsc, max_seconds);
+	err = pdsc_devcmd_wait(pdsc, cmd->opcode, max_seconds);
 	memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp));
 
 	if ((err == -ENXIO || err == -ETIMEDOUT) && pdsc->wq)
-- 
GitLab


From 439c4be98318751415a8f3690e4fa0fb62474a72 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Date: Thu, 24 Aug 2023 12:28:37 +0100
Subject: [PATCH 1725/1806] sfc: introduce ethernet pedit set action
 infrastructure

Introduce the initial ethernet pedit set action infrastructure in
preparation for adding mac src and dst pedit action offloads.

Co-developed-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/mae.c | 83 ++++++++++++++++++++++++++++++++--
 drivers/net/ethernet/sfc/mae.h |  4 ++
 drivers/net/ethernet/sfc/tc.c  | 70 ++++++++++++++++++++++++++++
 drivers/net/ethernet/sfc/tc.h  | 56 ++++++++++++++++++++---
 4 files changed, 202 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c
index 3b8780c76b6e2..a7ad7ab8c5f48 100644
--- a/drivers/net/ethernet/sfc/mae.c
+++ b/drivers/net/ethernet/sfc/mae.c
@@ -1219,6 +1219,71 @@ fail:
 	return rc;
 }
 
+/**
+ * efx_mae_allocate_pedit_mac() - allocate pedit MAC address in HW.
+ * @efx:	NIC we're installing a pedit MAC address on
+ * @ped:	pedit MAC action to be installed
+ *
+ * Attempts to install @ped in HW and populates its id with an index of this
+ * entry in the firmware MAC address table on success.
+ *
+ * Return: negative value on error, 0 in success.
+ */
+int efx_mae_allocate_pedit_mac(struct efx_nic *efx,
+			       struct efx_tc_mac_pedit_action *ped)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_MAC_ADDR_ALLOC_OUT_LEN);
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_MAC_ADDR_ALLOC_IN_LEN);
+	size_t outlen;
+	int rc;
+
+	BUILD_BUG_ON(MC_CMD_MAE_MAC_ADDR_ALLOC_IN_MAC_ADDR_LEN !=
+		     sizeof(ped->h_addr));
+	memcpy(MCDI_PTR(inbuf, MAE_MAC_ADDR_ALLOC_IN_MAC_ADDR), ped->h_addr,
+	       sizeof(ped->h_addr));
+	rc = efx_mcdi_rpc(efx, MC_CMD_MAE_MAC_ADDR_ALLOC, inbuf, sizeof(inbuf),
+			  outbuf, sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < sizeof(outbuf))
+		return -EIO;
+	ped->fw_id = MCDI_DWORD(outbuf, MAE_MAC_ADDR_ALLOC_OUT_MAC_ID);
+	return 0;
+}
+
+/**
+ * efx_mae_free_pedit_mac() - free pedit MAC address in HW.
+ * @efx:	NIC we're installing a pedit MAC address on
+ * @ped:	pedit MAC action that needs to be freed
+ *
+ * Frees @ped in HW, check that firmware did not free a different one and clears
+ * the id (which denotes the index of the entry in the MAC address table).
+ */
+void efx_mae_free_pedit_mac(struct efx_nic *efx,
+			    struct efx_tc_mac_pedit_action *ped)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_MAC_ADDR_FREE_OUT_LEN(1));
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_MAC_ADDR_FREE_IN_LEN(1));
+	size_t outlen;
+	int rc;
+
+	MCDI_SET_DWORD(inbuf, MAE_MAC_ADDR_FREE_IN_MAC_ID, ped->fw_id);
+	rc = efx_mcdi_rpc(efx, MC_CMD_MAE_MAC_ADDR_FREE, inbuf,
+			  sizeof(inbuf), outbuf, sizeof(outbuf), &outlen);
+	if (rc || outlen < sizeof(outbuf))
+		return;
+	/* FW freed a different ID than we asked for, should also never happen.
+	 * Warn because it means we've now got a different idea to the FW of
+	 * what MAC addresses exist, which could cause mayhem later.
+	 */
+	if (WARN_ON(MCDI_DWORD(outbuf, MAE_MAC_ADDR_FREE_OUT_FREED_MAC_ID) != ped->fw_id))
+		return;
+	/* We're probably about to free @ped, but let's just make sure its
+	 * fw_id is blatted so that it won't look valid if it leaks out.
+	 */
+	ped->fw_id = MC_CMD_MAE_MAC_ADDR_ALLOC_OUT_MAC_ID_NULL;
+}
+
 int efx_mae_alloc_action_set(struct efx_nic *efx, struct efx_tc_action_set *act)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_ACTION_SET_ALLOC_OUT_LEN);
@@ -1231,10 +1296,20 @@ int efx_mae_alloc_action_set(struct efx_nic *efx, struct efx_tc_action_set *act)
 			      MAE_ACTION_SET_ALLOC_IN_VLAN_POP, act->vlan_pop,
 			      MAE_ACTION_SET_ALLOC_IN_DECAP, act->decap);
 
-	MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_SRC_MAC_ID,
-		       MC_CMD_MAE_MAC_ADDR_ALLOC_OUT_MAC_ID_NULL);
-	MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_DST_MAC_ID,
-		       MC_CMD_MAE_MAC_ADDR_ALLOC_OUT_MAC_ID_NULL);
+	if (act->src_mac)
+		MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_SRC_MAC_ID,
+			       act->src_mac->fw_id);
+	else
+		MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_SRC_MAC_ID,
+			       MC_CMD_MAE_MAC_ADDR_ALLOC_OUT_MAC_ID_NULL);
+
+	if (act->dst_mac)
+		MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_DST_MAC_ID,
+			       act->dst_mac->fw_id);
+	else
+		MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_DST_MAC_ID,
+			       MC_CMD_MAE_MAC_ADDR_ALLOC_OUT_MAC_ID_NULL);
+
 	if (act->count && !WARN_ON(!act->count->cnt))
 		MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_COUNTER_ID,
 			       act->count->cnt->fw_id);
diff --git a/drivers/net/ethernet/sfc/mae.h b/drivers/net/ethernet/sfc/mae.h
index e88e80574f155..8df30bc4f3ba7 100644
--- a/drivers/net/ethernet/sfc/mae.h
+++ b/drivers/net/ethernet/sfc/mae.h
@@ -103,6 +103,10 @@ int efx_mae_update_encap_md(struct efx_nic *efx,
 int efx_mae_free_encap_md(struct efx_nic *efx,
 			  struct efx_tc_encap_action *encap);
 
+int efx_mae_allocate_pedit_mac(struct efx_nic *efx,
+			       struct efx_tc_mac_pedit_action *ped);
+void efx_mae_free_pedit_mac(struct efx_nic *efx,
+			    struct efx_tc_mac_pedit_action *ped);
 int efx_mae_alloc_action_set(struct efx_nic *efx, struct efx_tc_action_set *act);
 int efx_mae_free_action_set(struct efx_nic *efx, u32 fw_id);
 
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 039180c61c830..8a9fc2f475145 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -86,6 +86,12 @@ s64 efx_tc_flower_external_mport(struct efx_nic *efx, struct efx_rep *efv)
 	return mport;
 }
 
+static const struct rhashtable_params efx_tc_mac_ht_params = {
+	.key_len	= offsetofend(struct efx_tc_mac_pedit_action, h_addr),
+	.key_offset	= 0,
+	.head_offset	= offsetof(struct efx_tc_mac_pedit_action, linkage),
+};
+
 static const struct rhashtable_params efx_tc_encap_match_ht_params = {
 	.key_len	= offsetof(struct efx_tc_encap_match, linkage),
 	.key_offset	= 0,
@@ -110,6 +116,56 @@ static const struct rhashtable_params efx_tc_recirc_ht_params = {
 	.head_offset	= offsetof(struct efx_tc_recirc_id, linkage),
 };
 
+static struct efx_tc_mac_pedit_action __maybe_unused *efx_tc_flower_get_mac(struct efx_nic *efx,
+							     unsigned char h_addr[ETH_ALEN],
+							     struct netlink_ext_ack *extack)
+{
+	struct efx_tc_mac_pedit_action *ped, *old;
+	int rc;
+
+	ped = kzalloc(sizeof(*ped), GFP_USER);
+	if (!ped)
+		return ERR_PTR(-ENOMEM);
+	memcpy(ped->h_addr, h_addr, ETH_ALEN);
+	old = rhashtable_lookup_get_insert_fast(&efx->tc->mac_ht,
+						&ped->linkage,
+						efx_tc_mac_ht_params);
+	if (old) {
+		/* don't need our new entry */
+		kfree(ped);
+		if (!refcount_inc_not_zero(&old->ref))
+			return ERR_PTR(-EAGAIN);
+		/* existing entry found, ref taken */
+		return old;
+	}
+
+	rc = efx_mae_allocate_pedit_mac(efx, ped);
+	if (rc < 0) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to store pedit MAC address in hw");
+		goto out_remove;
+	}
+
+	/* ref and return */
+	refcount_set(&ped->ref, 1);
+	return ped;
+out_remove:
+	rhashtable_remove_fast(&efx->tc->mac_ht, &ped->linkage,
+			       efx_tc_mac_ht_params);
+	kfree(ped);
+	return ERR_PTR(rc);
+}
+
+static void __maybe_unused efx_tc_flower_put_mac(struct efx_nic *efx,
+				  struct efx_tc_mac_pedit_action *ped)
+{
+	if (!refcount_dec_and_test(&ped->ref))
+		return; /* still in use */
+	rhashtable_remove_fast(&efx->tc->mac_ht, &ped->linkage,
+			       efx_tc_mac_ht_params);
+	efx_mae_free_pedit_mac(efx, ped);
+	kfree(ped);
+}
+
 static void efx_tc_free_action_set(struct efx_nic *efx,
 				   struct efx_tc_action_set *act, bool in_hw)
 {
@@ -2156,6 +2212,14 @@ static void efx_tc_lhs_free(void *ptr, void *arg)
 	kfree(rule);
 }
 
+static void efx_tc_mac_free(void *ptr, void *__unused)
+{
+	struct efx_tc_mac_pedit_action *ped = ptr;
+
+	WARN_ON(refcount_read(&ped->ref));
+	kfree(ped);
+}
+
 static void efx_tc_flow_free(void *ptr, void *arg)
 {
 	struct efx_tc_flow_rule *rule = ptr;
@@ -2196,6 +2260,9 @@ int efx_init_struct_tc(struct efx_nic *efx)
 	rc = efx_tc_init_counters(efx);
 	if (rc < 0)
 		goto fail_counters;
+	rc = rhashtable_init(&efx->tc->mac_ht, &efx_tc_mac_ht_params);
+	if (rc < 0)
+		goto fail_mac_ht;
 	rc = rhashtable_init(&efx->tc->encap_match_ht, &efx_tc_encap_match_ht_params);
 	if (rc < 0)
 		goto fail_encap_match_ht;
@@ -2233,6 +2300,8 @@ fail_lhs_rule_ht:
 fail_match_action_ht:
 	rhashtable_destroy(&efx->tc->encap_match_ht);
 fail_encap_match_ht:
+	rhashtable_destroy(&efx->tc->mac_ht);
+fail_mac_ht:
 	efx_tc_destroy_counters(efx);
 fail_counters:
 	efx_tc_destroy_encap_actions(efx);
@@ -2268,6 +2337,7 @@ void efx_fini_struct_tc(struct efx_nic *efx)
 	rhashtable_free_and_destroy(&efx->tc->recirc_ht, efx_tc_recirc_free, efx);
 	WARN_ON(!ida_is_empty(&efx->tc->recirc_ida));
 	ida_destroy(&efx->tc->recirc_ida);
+	rhashtable_free_and_destroy(&efx->tc->mac_ht, efx_tc_mac_free, NULL);
 	efx_tc_fini_counters(efx);
 	efx_tc_fini_encap_actions(efx);
 	mutex_unlock(&efx->tc->mutex);
diff --git a/drivers/net/ethernet/sfc/tc.h b/drivers/net/ethernet/sfc/tc.h
index 40d2c803fca82..7b6a6a3d8e4ca 100644
--- a/drivers/net/ethernet/sfc/tc.h
+++ b/drivers/net/ethernet/sfc/tc.h
@@ -18,6 +18,23 @@
 
 #define IS_ALL_ONES(v)	(!(typeof (v))~(v))
 
+/**
+ * struct efx_tc_mac_pedit_action - mac pedit action fields
+ *
+ * @h_addr:	mac address field of ethernet header
+ * @linkage:	rhashtable reference
+ * @ref:	reference count
+ * @fw_id:	index of this entry in firmware MAC address table
+ *
+ * MAC address edits are indirected through a table in the hardware
+ */
+struct efx_tc_mac_pedit_action {
+	u8 h_addr[ETH_ALEN];
+	struct rhash_head linkage;
+	refcount_t ref;
+	u32 fw_id; /* index of this entry in firmware MAC address table */
+};
+
 static inline bool efx_ipv6_addr_all_ones(struct in6_addr *addr)
 {
 	return !memchr_inv(addr, 0xff, sizeof(*addr));
@@ -25,20 +42,43 @@ static inline bool efx_ipv6_addr_all_ones(struct in6_addr *addr)
 
 struct efx_tc_encap_action; /* see tc_encap_actions.h */
 
+/**
+ * struct efx_tc_action_set - collection of tc action fields
+ *
+ * @vlan_push: the number of vlan headers to push
+ * @vlan_pop: the number of vlan headers to pop
+ * @decap: used to indicate a tunnel header decapsulation should take place
+ * @deliver: used to indicate a deliver action should take place
+ * @vlan_tci: tci fields for vlan push actions
+ * @vlan_proto: ethernet types for vlan push actions
+ * @count: counter mapping
+ * @encap_md: encap entry in tc_encap_ht table
+ * @encap_user: linked list of encap users (encap_md->users)
+ * @user: owning action-set-list. Only populated if @encap_md is; used by efx_tc_update_encap() fallback handling
+ * @count_user: linked list of counter users (counter->users)
+ * @dest_mport: destination mport
+ * @src_mac: source mac entry in tc_mac_ht table
+ * @dst_mac: destination mac entry in tc_mac_ht table
+ * @fw_id: index of this entry in firmware actions table
+ * @list: linked list of tc actions
+ *
+ */
 struct efx_tc_action_set {
 	u16 vlan_push:2;
 	u16 vlan_pop:2;
 	u16 decap:1;
 	u16 deliver:1;
-	__be16 vlan_tci[2]; /* TCIs for vlan_push */
-	__be16 vlan_proto[2]; /* Ethertypes for vlan_push */
+	__be16 vlan_tci[2];
+	__be16 vlan_proto[2];
 	struct efx_tc_counter_index *count;
-	struct efx_tc_encap_action *encap_md; /* entry in tc_encap_ht table */
-	struct list_head encap_user; /* entry on encap_md->users list */
-	struct efx_tc_action_set_list *user; /* Only populated if encap_md */
-	struct list_head count_user; /* entry on counter->users list, if encap */
+	struct efx_tc_encap_action *encap_md;
+	struct list_head encap_user;
+	struct efx_tc_action_set_list *user;
+	struct list_head count_user;
 	u32 dest_mport;
-	u32 fw_id; /* index of this entry in firmware actions table */
+	struct efx_tc_mac_pedit_action *src_mac;
+	struct efx_tc_mac_pedit_action *dst_mac;
+	u32 fw_id;
 	struct list_head list;
 };
 
@@ -220,6 +260,7 @@ struct efx_tc_table_ct { /* TABLE_ID_CONNTRACK_TABLE */
  * @counter_ht: Hashtable of TC counters (FW IDs and counter values)
  * @counter_id_ht: Hashtable mapping TC counter cookies to counters
  * @encap_ht: Hashtable of TC encap actions
+ * @mac_ht: Hashtable of MAC address entries (for pedits)
  * @encap_match_ht: Hashtable of TC encap matches
  * @match_action_ht: Hashtable of TC match-action rules
  * @lhs_rule_ht: Hashtable of TC left-hand (act ct & goto chain) rules
@@ -257,6 +298,7 @@ struct efx_tc_state {
 	struct rhashtable counter_ht;
 	struct rhashtable counter_id_ht;
 	struct rhashtable encap_ht;
+	struct rhashtable mac_ht;
 	struct rhashtable encap_match_ht;
 	struct rhashtable match_action_ht;
 	struct rhashtable lhs_rule_ht;
-- 
GitLab


From 0c676503bd4ff726f5a4adc8fb54e09a78685b1f Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Date: Thu, 24 Aug 2023 12:28:38 +0100
Subject: [PATCH 1726/1806] sfc: add mac source and destination pedit action
 offload

Introduce the first pedit set offload functionality for the sfc driver.
In addition to this, add offload functionality for both mac source and
destination pedit set actions.

Co-developed-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/tc.c | 209 +++++++++++++++++++++++++++++++++-
 1 file changed, 207 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 8a9fc2f475145..b9d7c4bb7e696 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -116,7 +116,7 @@ static const struct rhashtable_params efx_tc_recirc_ht_params = {
 	.head_offset	= offsetof(struct efx_tc_recirc_id, linkage),
 };
 
-static struct efx_tc_mac_pedit_action __maybe_unused *efx_tc_flower_get_mac(struct efx_nic *efx,
+static struct efx_tc_mac_pedit_action *efx_tc_flower_get_mac(struct efx_nic *efx,
 							     unsigned char h_addr[ETH_ALEN],
 							     struct netlink_ext_ack *extack)
 {
@@ -155,7 +155,7 @@ out_remove:
 	return ERR_PTR(rc);
 }
 
-static void __maybe_unused efx_tc_flower_put_mac(struct efx_nic *efx,
+static void efx_tc_flower_put_mac(struct efx_nic *efx,
 				  struct efx_tc_mac_pedit_action *ped)
 {
 	if (!refcount_dec_and_test(&ped->ref))
@@ -191,6 +191,10 @@ static void efx_tc_free_action_set(struct efx_nic *efx,
 		list_del(&act->encap_user);
 		efx_tc_flower_release_encap_md(efx, act->encap_md);
 	}
+	if (act->src_mac)
+		efx_tc_flower_put_mac(efx, act->src_mac);
+	if (act->dst_mac)
+		efx_tc_flower_put_mac(efx, act->dst_mac);
 	kfree(act);
 }
 
@@ -753,6 +757,7 @@ static const char *efx_tc_encap_type_name(enum efx_encap_type typ)
 /* For details of action order constraints refer to SF-123102-TC-1§12.6.1 */
 enum efx_tc_action_order {
 	EFX_TC_AO_DECAP,
+	EFX_TC_AO_PEDIT_MAC_ADDRS,
 	EFX_TC_AO_VLAN_POP,
 	EFX_TC_AO_VLAN_PUSH,
 	EFX_TC_AO_COUNT,
@@ -767,6 +772,11 @@ static bool efx_tc_flower_action_order_ok(const struct efx_tc_action_set *act,
 	case EFX_TC_AO_DECAP:
 		if (act->decap)
 			return false;
+		/* PEDIT_MAC_ADDRS must not happen before DECAP, though it
+		 * can wait until much later
+		 */
+		if (act->dst_mac || act->src_mac)
+			return false;
 		fallthrough;
 	case EFX_TC_AO_VLAN_POP:
 		if (act->vlan_pop >= 2)
@@ -786,6 +796,7 @@ static bool efx_tc_flower_action_order_ok(const struct efx_tc_action_set *act,
 		if (act->count)
 			return false;
 		fallthrough;
+	case EFX_TC_AO_PEDIT_MAC_ADDRS:
 	case EFX_TC_AO_ENCAP:
 		if (act->encap_md)
 			return false;
@@ -956,6 +967,191 @@ static void efx_tc_flower_release_lhs_actions(struct efx_nic *efx,
 		efx_tc_flower_put_counter_index(efx, act->count);
 }
 
+/**
+ * struct efx_tc_mangler_state - accumulates 32-bit pedits into fields
+ *
+ * @dst_mac_32:	dst_mac[0:3] has been populated
+ * @dst_mac_16:	dst_mac[4:5] has been populated
+ * @src_mac_16:	src_mac[0:1] has been populated
+ * @src_mac_32:	src_mac[2:5] has been populated
+ * @dst_mac:	h_dest field of ethhdr
+ * @src_mac:	h_source field of ethhdr
+ *
+ * Since FLOW_ACTION_MANGLE comes in 32-bit chunks that do not
+ * necessarily equate to whole fields of the packet header, this
+ * structure is used to hold the cumulative effect of the partial
+ * field pedits that have been processed so far.
+ */
+struct efx_tc_mangler_state {
+	u8 dst_mac_32:1; /* eth->h_dest[0:3] */
+	u8 dst_mac_16:1; /* eth->h_dest[4:5] */
+	u8 src_mac_16:1; /* eth->h_source[0:1] */
+	u8 src_mac_32:1; /* eth->h_source[2:5] */
+	unsigned char dst_mac[ETH_ALEN];
+	unsigned char src_mac[ETH_ALEN];
+};
+
+/** efx_tc_complete_mac_mangle() - pull complete field pedits out of @mung
+ * @efx:	NIC we're installing a flow rule on
+ * @act:	action set (cursor) to update
+ * @mung:	accumulated partial mangles
+ * @extack:	netlink extended ack for reporting errors
+ *
+ * Check @mung to find any combinations of partial mangles that can be
+ * combined into a complete packet field edit, add that edit to @act,
+ * and consume the partial mangles from @mung.
+ */
+
+static int efx_tc_complete_mac_mangle(struct efx_nic *efx,
+				      struct efx_tc_action_set *act,
+				      struct efx_tc_mangler_state *mung,
+				      struct netlink_ext_ack *extack)
+{
+	struct efx_tc_mac_pedit_action *ped;
+
+	if (mung->dst_mac_32 && mung->dst_mac_16) {
+		ped = efx_tc_flower_get_mac(efx, mung->dst_mac, extack);
+		if (IS_ERR(ped))
+			return PTR_ERR(ped);
+
+		/* Check that we have not already populated dst_mac */
+		if (act->dst_mac)
+			efx_tc_flower_put_mac(efx, act->dst_mac);
+
+		act->dst_mac = ped;
+
+		/* consume the incomplete state */
+		mung->dst_mac_32 = 0;
+		mung->dst_mac_16 = 0;
+	}
+	if (mung->src_mac_16 && mung->src_mac_32) {
+		ped = efx_tc_flower_get_mac(efx, mung->src_mac, extack);
+		if (IS_ERR(ped))
+			return PTR_ERR(ped);
+
+		/* Check that we have not already populated src_mac */
+		if (act->src_mac)
+			efx_tc_flower_put_mac(efx, act->src_mac);
+
+		act->src_mac = ped;
+
+		/* consume the incomplete state */
+		mung->src_mac_32 = 0;
+		mung->src_mac_16 = 0;
+	}
+	return 0;
+}
+
+/**
+ * efx_tc_mangle() - handle a single 32-bit (or less) pedit
+ * @efx:	NIC we're installing a flow rule on
+ * @act:	action set (cursor) to update
+ * @fa:		FLOW_ACTION_MANGLE action metadata
+ * @mung:	accumulator for partial mangles
+ * @extack:	netlink extended ack for reporting errors
+ *
+ * Identify the fields written by a FLOW_ACTION_MANGLE, and record
+ * the partial mangle state in @mung.  If this mangle completes an
+ * earlier partial mangle, consume and apply to @act by calling
+ * efx_tc_complete_mac_mangle().
+ */
+
+static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act,
+			 const struct flow_action_entry *fa,
+			 struct efx_tc_mangler_state *mung,
+			 struct netlink_ext_ack *extack)
+{
+	__le32 mac32;
+	__le16 mac16;
+
+	switch (fa->mangle.htype) {
+	case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
+		BUILD_BUG_ON(offsetof(struct ethhdr, h_dest) != 0);
+		BUILD_BUG_ON(offsetof(struct ethhdr, h_source) != 6);
+		if (!efx_tc_flower_action_order_ok(act, EFX_TC_AO_PEDIT_MAC_ADDRS)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Pedit mangle mac action violates action order");
+			return -EOPNOTSUPP;
+		}
+		switch (fa->mangle.offset) {
+		case 0:
+			if (fa->mangle.mask) {
+				NL_SET_ERR_MSG_FMT_MOD(extack,
+						       "Unsupported: mask (%#x) of eth.dst32 mangle",
+						       fa->mangle.mask);
+				return -EOPNOTSUPP;
+			}
+			/* Ethernet address is little-endian */
+			mac32 = cpu_to_le32(fa->mangle.val);
+			memcpy(mung->dst_mac, &mac32, sizeof(mac32));
+			mung->dst_mac_32 = 1;
+			return efx_tc_complete_mac_mangle(efx, act, mung, extack);
+		case 4:
+			if (fa->mangle.mask == 0xffff) {
+				mac16 = cpu_to_le16(fa->mangle.val >> 16);
+				memcpy(mung->src_mac, &mac16, sizeof(mac16));
+				mung->src_mac_16 = 1;
+			} else if (fa->mangle.mask == 0xffff0000) {
+				mac16 = cpu_to_le16((u16)fa->mangle.val);
+				memcpy(mung->dst_mac + 4, &mac16, sizeof(mac16));
+				mung->dst_mac_16 = 1;
+			} else {
+				NL_SET_ERR_MSG_FMT_MOD(extack,
+						       "Unsupported: mask (%#x) of eth+4 mangle is not high or low 16b",
+						       fa->mangle.mask);
+				return -EOPNOTSUPP;
+			}
+			return efx_tc_complete_mac_mangle(efx, act, mung, extack);
+		case 8:
+			if (fa->mangle.mask) {
+				NL_SET_ERR_MSG_FMT_MOD(extack,
+						       "Unsupported: mask (%#x) of eth.src32 mangle",
+						       fa->mangle.mask);
+				return -EOPNOTSUPP;
+			}
+			mac32 = cpu_to_le32(fa->mangle.val);
+			memcpy(mung->src_mac + 2, &mac32, sizeof(mac32));
+			mung->src_mac_32 = 1;
+			return efx_tc_complete_mac_mangle(efx, act, mung, extack);
+		default:
+			NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported: mangle eth+%u %x/%x",
+					       fa->mangle.offset, fa->mangle.val, fa->mangle.mask);
+			return -EOPNOTSUPP;
+		}
+		break;
+	default:
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled mangle htype %u for action rule",
+				       fa->mangle.htype);
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+/**
+ * efx_tc_incomplete_mangle() - check for leftover partial pedits
+ * @mung:	accumulator for partial mangles
+ * @extack:	netlink extended ack for reporting errors
+ *
+ * Since the MAE can only overwrite whole fields, any partial
+ * field mangle left over on reaching packet delivery (mirred or
+ * end of TC actions) cannot be offloaded.  Check for any such
+ * and reject them with -%EOPNOTSUPP.
+ */
+
+static int efx_tc_incomplete_mangle(struct efx_tc_mangler_state *mung,
+				    struct netlink_ext_ack *extack)
+{
+	if (mung->dst_mac_32 || mung->dst_mac_16) {
+		NL_SET_ERR_MSG_MOD(extack, "Incomplete pedit of destination MAC address");
+		return -EOPNOTSUPP;
+	}
+	if (mung->src_mac_16 || mung->src_mac_32) {
+		NL_SET_ERR_MSG_MOD(extack, "Incomplete pedit of source MAC address");
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
 static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 					 struct net_device *net_dev,
 					 struct flow_cls_offload *tc)
@@ -1351,6 +1547,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 	struct netlink_ext_ack *extack = tc->common.extack;
 	const struct ip_tunnel_info *encap_info = NULL;
 	struct efx_tc_flow_rule *rule = NULL, *old;
+	struct efx_tc_mangler_state mung = {};
 	struct efx_tc_action_set *act = NULL;
 	const struct flow_action_entry *fa;
 	struct efx_rep *from_efv, *to_efv;
@@ -1687,6 +1884,11 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 			act->vlan_proto[act->vlan_push] = fa->vlan.proto;
 			act->vlan_push++;
 			break;
+		case FLOW_ACTION_MANGLE:
+			rc = efx_tc_mangle(efx, act, fa, &mung, extack);
+			if (rc < 0)
+				goto release;
+			break;
 		case FLOW_ACTION_TUNNEL_ENCAP:
 			if (encap_info) {
 				/* Can't specify encap multiple times.
@@ -1726,6 +1928,9 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 		}
 	}
 
+	rc = efx_tc_incomplete_mangle(&mung, extack);
+	if (rc < 0)
+		goto release;
 	if (act) {
 		/* Not shot/redirected, so deliver to default dest */
 		if (from_efv == EFX_EFV_PF)
-- 
GitLab


From 66f728872636e1167aedc5a18be6760083911900 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Date: Thu, 24 Aug 2023 12:28:39 +0100
Subject: [PATCH 1727/1806] sfc: add decrement ttl by offloading set ipv4 ttl
 actions

Offload pedit set ipv4 ttl field, where the ttl field has already been
matched and the new value is one less, by translating it to a decrement.

Co-developed-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/mae.c |  6 ++-
 drivers/net/ethernet/sfc/tc.c  | 75 +++++++++++++++++++++++++++++++++-
 drivers/net/ethernet/sfc/tc.h  |  2 +
 3 files changed, 79 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c
index a7ad7ab8c5f48..c3e2b4a21d105 100644
--- a/drivers/net/ethernet/sfc/mae.c
+++ b/drivers/net/ethernet/sfc/mae.c
@@ -1291,10 +1291,12 @@ int efx_mae_alloc_action_set(struct efx_nic *efx, struct efx_tc_action_set *act)
 	size_t outlen;
 	int rc;
 
-	MCDI_POPULATE_DWORD_3(inbuf, MAE_ACTION_SET_ALLOC_IN_FLAGS,
+	MCDI_POPULATE_DWORD_4(inbuf, MAE_ACTION_SET_ALLOC_IN_FLAGS,
 			      MAE_ACTION_SET_ALLOC_IN_VLAN_PUSH, act->vlan_push,
 			      MAE_ACTION_SET_ALLOC_IN_VLAN_POP, act->vlan_pop,
-			      MAE_ACTION_SET_ALLOC_IN_DECAP, act->decap);
+			      MAE_ACTION_SET_ALLOC_IN_DECAP, act->decap,
+			      MAE_ACTION_SET_ALLOC_IN_DO_DECR_IP_TTL,
+			      act->do_ttl_dec);
 
 	if (act->src_mac)
 		MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_SRC_MAC_ID,
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index b9d7c4bb7e696..57bdd56b71134 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -31,6 +31,7 @@ enum efx_encap_type efx_tc_indr_netdev_type(struct net_device *net_dev)
 	return EFX_ENCAP_TYPE_NONE;
 }
 
+#define EFX_TC_HDR_TYPE_TTL_MASK ((u32)0xff)
 #define EFX_EFV_PF	NULL
 /* Look up the representor information (efv) for a device.
  * May return NULL for the PF (us), or an error pointer for a device that
@@ -757,6 +758,7 @@ static const char *efx_tc_encap_type_name(enum efx_encap_type typ)
 /* For details of action order constraints refer to SF-123102-TC-1§12.6.1 */
 enum efx_tc_action_order {
 	EFX_TC_AO_DECAP,
+	EFX_TC_AO_DEC_TTL,
 	EFX_TC_AO_PEDIT_MAC_ADDRS,
 	EFX_TC_AO_VLAN_POP,
 	EFX_TC_AO_VLAN_PUSH,
@@ -777,6 +779,10 @@ static bool efx_tc_flower_action_order_ok(const struct efx_tc_action_set *act,
 		 */
 		if (act->dst_mac || act->src_mac)
 			return false;
+
+		/* Decrementing ttl must not happen before DECAP */
+		if (act->do_ttl_dec)
+			return false;
 		fallthrough;
 	case EFX_TC_AO_VLAN_POP:
 		if (act->vlan_pop >= 2)
@@ -803,6 +809,10 @@ static bool efx_tc_flower_action_order_ok(const struct efx_tc_action_set *act,
 		fallthrough;
 	case EFX_TC_AO_DELIVER:
 		return !act->deliver;
+	case EFX_TC_AO_DEC_TTL:
+		if (act->encap_md)
+			return false;
+		return !act->do_ttl_dec;
 	default:
 		/* Bad caller.  Whatever they wanted to do, say they can't. */
 		WARN_ON_ONCE(1);
@@ -1049,6 +1059,7 @@ static int efx_tc_complete_mac_mangle(struct efx_nic *efx,
  * @fa:		FLOW_ACTION_MANGLE action metadata
  * @mung:	accumulator for partial mangles
  * @extack:	netlink extended ack for reporting errors
+ * @match:	original match used along with the mangle action
  *
  * Identify the fields written by a FLOW_ACTION_MANGLE, and record
  * the partial mangle state in @mung.  If this mangle completes an
@@ -1059,10 +1070,12 @@ static int efx_tc_complete_mac_mangle(struct efx_nic *efx,
 static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act,
 			 const struct flow_action_entry *fa,
 			 struct efx_tc_mangler_state *mung,
-			 struct netlink_ext_ack *extack)
+			 struct netlink_ext_ack *extack,
+			 struct efx_tc_match *match)
 {
 	__le32 mac32;
 	__le16 mac16;
+	u8 tr_ttl;
 
 	switch (fa->mangle.htype) {
 	case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
@@ -1119,6 +1132,64 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act,
 			return -EOPNOTSUPP;
 		}
 		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+		switch (fa->mangle.offset) {
+		case offsetof(struct iphdr, ttl):
+			/* we currently only support pedit IP4 when it applies
+			 * to TTL and then only when it can be achieved with a
+			 * decrement ttl action
+			 */
+
+			/* check that pedit applies to ttl only */
+			if (fa->mangle.mask != ~EFX_TC_HDR_TYPE_TTL_MASK) {
+				NL_SET_ERR_MSG_FMT_MOD(extack,
+						       "Unsupported: mask (%#x) out of range, only support mangle action on ipv4.ttl",
+						       fa->mangle.mask);
+				return -EOPNOTSUPP;
+			}
+
+			/* we can only convert to a dec ttl when we have an
+			 * exact match on the ttl field
+			 */
+			if (match->mask.ip_ttl != U8_MAX) {
+				NL_SET_ERR_MSG_FMT_MOD(extack,
+						       "Unsupported: only support mangle ipv4.ttl when we have an exact match on ttl, mask used for match (%#x)",
+						       match->mask.ip_ttl);
+				return -EOPNOTSUPP;
+			}
+
+			/* check that we don't try to decrement 0, which equates
+			 * to setting the ttl to 0xff
+			 */
+			if (match->value.ip_ttl == 0) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Unsupported: we cannot decrement ttl past 0");
+				return -EOPNOTSUPP;
+			}
+
+			/* check that we do not decrement ttl twice */
+			if (!efx_tc_flower_action_order_ok(act,
+							   EFX_TC_AO_DEC_TTL)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Unsupported: multiple dec ttl");
+				return -EOPNOTSUPP;
+			}
+
+			/* check pedit can be achieved with decrement action */
+			tr_ttl = match->value.ip_ttl - 1;
+			if ((fa->mangle.val & EFX_TC_HDR_TYPE_TTL_MASK) == tr_ttl) {
+				act->do_ttl_dec = 1;
+				return 0;
+			}
+
+			fallthrough;
+		default:
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Unsupported: only support mangle on the ttl field (offset is %u)",
+					       fa->mangle.offset);
+			return -EOPNOTSUPP;
+		}
+		break;
 	default:
 		NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled mangle htype %u for action rule",
 				       fa->mangle.htype);
@@ -1885,7 +1956,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 			act->vlan_push++;
 			break;
 		case FLOW_ACTION_MANGLE:
-			rc = efx_tc_mangle(efx, act, fa, &mung, extack);
+			rc = efx_tc_mangle(efx, act, fa, &mung, extack, &match);
 			if (rc < 0)
 				goto release;
 			break;
diff --git a/drivers/net/ethernet/sfc/tc.h b/drivers/net/ethernet/sfc/tc.h
index 7b6a6a3d8e4ca..4dd2c378fd9f5 100644
--- a/drivers/net/ethernet/sfc/tc.h
+++ b/drivers/net/ethernet/sfc/tc.h
@@ -48,6 +48,7 @@ struct efx_tc_encap_action; /* see tc_encap_actions.h */
  * @vlan_push: the number of vlan headers to push
  * @vlan_pop: the number of vlan headers to pop
  * @decap: used to indicate a tunnel header decapsulation should take place
+ * @do_ttl_dec: used to indicate IP TTL / Hop Limit should be decremented
  * @deliver: used to indicate a deliver action should take place
  * @vlan_tci: tci fields for vlan push actions
  * @vlan_proto: ethernet types for vlan push actions
@@ -67,6 +68,7 @@ struct efx_tc_action_set {
 	u16 vlan_push:2;
 	u16 vlan_pop:2;
 	u16 decap:1;
+	u16 do_ttl_dec:1;
 	u16 deliver:1;
 	__be16 vlan_tci[2];
 	__be16 vlan_proto[2];
-- 
GitLab


From 9dbc8d2b9a02f938d32741297d56cc364dc0dce6 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Date: Thu, 24 Aug 2023 12:28:40 +0100
Subject: [PATCH 1728/1806] sfc: add decrement ipv6 hop limit by offloading set
 hop limit actions

Offload pedit set ipv6 hop limit, where the hop limit has already been
matched and the new value is one less, by translating it to a decrement.

Co-developed-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/tc.c | 59 +++++++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 57bdd56b71134..354c635be59ff 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -32,6 +32,8 @@ enum efx_encap_type efx_tc_indr_netdev_type(struct net_device *net_dev)
 }
 
 #define EFX_TC_HDR_TYPE_TTL_MASK ((u32)0xff)
+/* Hoplimit is stored in the most significant byte in the pedit ipv6 header action */
+#define EFX_TC_HDR_TYPE_HLIMIT_MASK ~((u32)0xff000000)
 #define EFX_EFV_PF	NULL
 /* Look up the representor information (efv) for a device.
  * May return NULL for the PF (us), or an error pointer for a device that
@@ -1190,6 +1192,63 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act,
 			return -EOPNOTSUPP;
 		}
 		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
+		switch (fa->mangle.offset) {
+		case round_down(offsetof(struct ipv6hdr, hop_limit), 4):
+			/* we currently only support pedit IP6 when it applies
+			 * to the hoplimit and then only when it can be achieved
+			 * with a decrement hoplimit action
+			 */
+
+			/* check that pedit applies to ttl only */
+			if (fa->mangle.mask != EFX_TC_HDR_TYPE_HLIMIT_MASK) {
+				NL_SET_ERR_MSG_FMT_MOD(extack,
+						       "Unsupported: mask (%#x) out of range, only support mangle action on ipv6.hop_limit",
+						       fa->mangle.mask);
+
+				return -EOPNOTSUPP;
+			}
+
+			/* we can only convert to a dec ttl when we have an
+			 * exact match on the ttl field
+			 */
+			if (match->mask.ip_ttl != U8_MAX) {
+				NL_SET_ERR_MSG_FMT_MOD(extack,
+						       "Unsupported: only support mangle ipv6.hop_limit when we have an exact match on ttl, mask used for match (%#x)",
+						       match->mask.ip_ttl);
+				return -EOPNOTSUPP;
+			}
+
+			/* check that we don't try to decrement 0, which equates
+			 * to setting the ttl to 0xff
+			 */
+			if (match->value.ip_ttl == 0) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Unsupported: we cannot decrement hop_limit past 0");
+				return -EOPNOTSUPP;
+			}
+
+			/* check that we do not decrement hoplimit twice */
+			if (!efx_tc_flower_action_order_ok(act,
+							   EFX_TC_AO_DEC_TTL)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Unsupported: multiple dec ttl");
+				return -EOPNOTSUPP;
+			}
+
+			/* check pedit can be achieved with decrement action */
+			tr_ttl = match->value.ip_ttl - 1;
+			if ((fa->mangle.val >> 24) == tr_ttl) {
+				act->do_ttl_dec = 1;
+				return 0;
+			}
+
+			fallthrough;
+		default:
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Unsupported: only support mangle on the hop_limit field");
+			return -EOPNOTSUPP;
+		}
 	default:
 		NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled mangle htype %u for action rule",
 				       fa->mangle.htype);
-- 
GitLab


From 64848f062e33df61fb1f9f7b7a3dc7b44e0d36d7 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Date: Thu, 24 Aug 2023 12:28:41 +0100
Subject: [PATCH 1729/1806] sfc: introduce pedit add actions on the ipv4 ttl
 field

Introduce pedit add actions and use it to achieve decrement ttl offload.
Decrement ttl can be achieved by adding 0xff to the ttl field.

Co-developed-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/tc.c | 46 +++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 354c635be59ff..dfe3a8bf74f04 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -1054,6 +1054,47 @@ static int efx_tc_complete_mac_mangle(struct efx_nic *efx,
 	return 0;
 }
 
+static int efx_tc_pedit_add(struct efx_nic *efx, struct efx_tc_action_set *act,
+			    const struct flow_action_entry *fa,
+			    struct netlink_ext_ack *extack)
+{
+	switch (fa->mangle.htype) {
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+		switch (fa->mangle.offset) {
+		case offsetof(struct iphdr, ttl):
+			/* check that pedit applies to ttl only */
+			if (fa->mangle.mask != ~EFX_TC_HDR_TYPE_TTL_MASK)
+				break;
+
+			/* Adding 0xff is equivalent to decrementing the ttl.
+			 * Other added values are not supported.
+			 */
+			if ((fa->mangle.val & EFX_TC_HDR_TYPE_TTL_MASK) != U8_MAX)
+				break;
+
+			/* check that we do not decrement ttl twice */
+			if (!efx_tc_flower_action_order_ok(act,
+							   EFX_TC_AO_DEC_TTL)) {
+				NL_SET_ERR_MSG_MOD(extack, "Unsupported: multiple dec ttl");
+				return -EOPNOTSUPP;
+			}
+			act->do_ttl_dec = 1;
+			return 0;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	NL_SET_ERR_MSG_FMT_MOD(extack,
+			       "Unsupported: ttl add action type %x %x %x/%x",
+			       fa->mangle.htype, fa->mangle.offset,
+			       fa->mangle.val, fa->mangle.mask);
+	return -EOPNOTSUPP;
+}
+
 /**
  * efx_tc_mangle() - handle a single 32-bit (or less) pedit
  * @efx:	NIC we're installing a flow rule on
@@ -2014,6 +2055,11 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 			act->vlan_proto[act->vlan_push] = fa->vlan.proto;
 			act->vlan_push++;
 			break;
+		case FLOW_ACTION_ADD:
+			rc = efx_tc_pedit_add(efx, act, fa, extack);
+			if (rc < 0)
+				goto release;
+			break;
 		case FLOW_ACTION_MANGLE:
 			rc = efx_tc_mangle(efx, act, fa, &mung, extack, &match);
 			if (rc < 0)
-- 
GitLab


From e8e0bd60e4833e5bcfa220d7b4c07456c83c1ea2 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Date: Thu, 24 Aug 2023 12:28:42 +0100
Subject: [PATCH 1730/1806] sfc: extend pedit add action to handle decrement
 ipv6 hop limit

Extend the pedit add actions to handle this case for ipv6. Similar to ipv4
dec ttl, decrementing ipv6 hop limit can be achieved by adding 0xff to the
hop limit field.

Co-developed-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/tc.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index dfe3a8bf74f04..047322b04d4f5 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -1084,6 +1084,31 @@ static int efx_tc_pedit_add(struct efx_nic *efx, struct efx_tc_action_set *act,
 			break;
 		}
 		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
+		switch (fa->mangle.offset) {
+		case round_down(offsetof(struct ipv6hdr, hop_limit), 4):
+			/* check that pedit applies to hoplimit only */
+			if (fa->mangle.mask != EFX_TC_HDR_TYPE_HLIMIT_MASK)
+				break;
+
+			/* Adding 0xff is equivalent to decrementing the hoplimit.
+			 * Other added values are not supported.
+			 */
+			if ((fa->mangle.val >> 24) != U8_MAX)
+				break;
+
+			/* check that we do not decrement hoplimit twice */
+			if (!efx_tc_flower_action_order_ok(act,
+							   EFX_TC_AO_DEC_TTL)) {
+				NL_SET_ERR_MSG_MOD(extack, "Unsupported: multiple dec ttl");
+				return -EOPNOTSUPP;
+			}
+			act->do_ttl_dec = 1;
+			return 0;
+		default:
+			break;
+		}
+		break;
 	default:
 		break;
 	}
-- 
GitLab


From f0035689c036ade6faba4a91e2dc4879d1f02f82 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Thu, 24 Aug 2023 17:16:14 +0530
Subject: [PATCH 1731/1806] dt-bindings: net: Add ICSS IEP

Add a DT binding document for the ICSS Industrial Ethernet Peripheral(IEP)
hardware. IEP supports packet timestamping, PTP and PPS.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/net/ti,icss-iep.yaml  | 45 +++++++++++++++++++
 1 file changed, 45 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/ti,icss-iep.yaml

diff --git a/Documentation/devicetree/bindings/net/ti,icss-iep.yaml b/Documentation/devicetree/bindings/net/ti,icss-iep.yaml
new file mode 100644
index 0000000000000..f5c22d6dcaee1
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ti,icss-iep.yaml
@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/ti,icss-iep.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments ICSS Industrial Ethernet Peripheral (IEP) module
+
+maintainers:
+  - Md Danish Anwar <danishanwar@ti.com>
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - ti,am642-icss-iep
+              - ti,j721e-icss-iep
+          - const: ti,am654-icss-iep
+
+      - const: ti,am654-icss-iep
+
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+    description: phandle to the IEP source clock
+
+required:
+  - compatible
+  - reg
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    /* AM65x */
+    icssg0_iep0: iep@2e000 {
+        compatible = "ti,am654-icss-iep";
+        reg = <0x2e000 0x1000>;
+        clocks = <&icssg0_iepclk_mux>;
+    };
-- 
GitLab


From b12056278378c4fb995a32a26034ac370d177d98 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Thu, 24 Aug 2023 17:16:15 +0530
Subject: [PATCH 1732/1806] dt-bindings: net: Add IEP property in ICSSG

Add IEP property in ICSSG hardware DT binding document.
ICSSG uses IEP (Industrial Ethernet Peripheral) to support timestamping
of ethernet packets, PTP and PPS.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/net/ti,icssg-prueth.yaml         | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml b/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml
index 8ec30b3eb7600..311c570165f9c 100644
--- a/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml
+++ b/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml
@@ -52,6 +52,14 @@ properties:
     description:
       phandle to MII_RT module's syscon regmap
 
+  ti,iep:
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    maxItems: 2
+    items:
+      maxItems: 1
+    description:
+      phandle to IEP (Industrial Ethernet Peripheral) for ICSSG
+
   interrupts:
     maxItems: 2
     description:
@@ -155,6 +163,7 @@ examples:
                     "tx1-0", "tx1-1", "tx1-2", "tx1-3",
                     "rx0", "rx1";
         ti,mii-g-rt = <&icssg2_mii_g_rt>;
+        ti,iep = <&icssg2_iep0>, <&icssg2_iep1>;
         interrupt-parent = <&icssg2_intc>;
         interrupts = <24 0 2>, <25 1 3>;
         interrupt-names = "tx_ts0", "tx_ts1";
-- 
GitLab


From c1e0230eeaab26984f6e5c5575486e96a63e2e48 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Thu, 24 Aug 2023 17:16:16 +0530
Subject: [PATCH 1733/1806] net: ti: icss-iep: Add IEP driver

Add a driver for Industrial Ethernet Peripheral (IEP) block of PRUSS to
support timestamping of ethernet packets and thus support PTP and PPS
for PRU ethernet ports.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Lokesh Vutla <lokeshvutla@ti.com>
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/Kconfig          |  11 +
 drivers/net/ethernet/ti/Makefile         |   1 +
 drivers/net/ethernet/ti/icssg/icss_iep.c | 939 +++++++++++++++++++++++
 drivers/net/ethernet/ti/icssg/icss_iep.h |  38 +
 4 files changed, 989 insertions(+)
 create mode 100644 drivers/net/ethernet/ti/icssg/icss_iep.c
 create mode 100644 drivers/net/ethernet/ti/icssg/icss_iep.h

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 63e510b6860fd..1af5a90720ec0 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -196,4 +196,15 @@ config TI_ICSSG_PRUETH
 	  to support the Ethernet operation. Currently, it supports Ethernet
 	  with 1G and 100M link speed.
 
+config TI_ICSS_IEP
+	tristate "TI PRU ICSS IEP driver"
+	depends on TI_PRUSS
+	default TI_PRUSS
+	help
+	  This driver enables support for the PRU-ICSS Industrial Ethernet
+	  Peripheral within a PRU-ICSS subsystem present on various TI SoCs.
+
+	  To compile this driver as a module, choose M here. The module
+	  will be called icss_iep.
+
 endif # NET_VENDOR_TI
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 9176d79c36e1e..34fd7a716ba6e 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -38,3 +38,4 @@ icssg-prueth-y := k3-cppi-desc-pool.o \
 		  icssg/icssg_mii_cfg.o \
 		  icssg/icssg_stats.o \
 		  icssg/icssg_ethtool.o
+obj-$(CONFIG_TI_ICSS_IEP) += icssg/icss_iep.o
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
new file mode 100644
index 0000000000000..bcc056bf45da9
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -0,0 +1,939 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Texas Instruments ICSSG Industrial Ethernet Peripheral (IEP) Driver
+ *
+ * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/timekeeping.h>
+#include <linux/interrupt.h>
+#include <linux/of_irq.h>
+
+#include "icss_iep.h"
+
+#define IEP_MAX_DEF_INC		0xf
+#define IEP_MAX_COMPEN_INC		0xfff
+#define IEP_MAX_COMPEN_COUNT	0xffffff
+
+#define IEP_GLOBAL_CFG_CNT_ENABLE	BIT(0)
+#define IEP_GLOBAL_CFG_DEFAULT_INC_MASK		GENMASK(7, 4)
+#define IEP_GLOBAL_CFG_DEFAULT_INC_SHIFT	4
+#define IEP_GLOBAL_CFG_COMPEN_INC_MASK		GENMASK(19, 8)
+#define IEP_GLOBAL_CFG_COMPEN_INC_SHIFT		8
+
+#define IEP_GLOBAL_STATUS_CNT_OVF	BIT(0)
+
+#define IEP_CMP_CFG_SHADOW_EN		BIT(17)
+#define IEP_CMP_CFG_CMP0_RST_CNT_EN	BIT(0)
+#define IEP_CMP_CFG_CMP_EN(cmp)		(GENMASK(16, 1) & (1 << ((cmp) + 1)))
+
+#define IEP_CMP_STATUS(cmp)		(1 << (cmp))
+
+#define IEP_SYNC_CTRL_SYNC_EN		BIT(0)
+#define IEP_SYNC_CTRL_SYNC_N_EN(n)	(GENMASK(2, 1) & (BIT(1) << (n)))
+
+#define IEP_MIN_CMP	0
+#define IEP_MAX_CMP	15
+
+#define ICSS_IEP_64BIT_COUNTER_SUPPORT		BIT(0)
+#define ICSS_IEP_SLOW_COMPEN_REG_SUPPORT	BIT(1)
+#define ICSS_IEP_SHADOW_MODE_SUPPORT		BIT(2)
+
+#define LATCH_INDEX(ts_index)			((ts_index) + 6)
+#define IEP_CAP_CFG_CAPNR_1ST_EVENT_EN(n)	BIT(LATCH_INDEX(n))
+#define IEP_CAP_CFG_CAP_ASYNC_EN(n)		BIT(LATCH_INDEX(n) + 10)
+
+enum {
+	ICSS_IEP_GLOBAL_CFG_REG,
+	ICSS_IEP_GLOBAL_STATUS_REG,
+	ICSS_IEP_COMPEN_REG,
+	ICSS_IEP_SLOW_COMPEN_REG,
+	ICSS_IEP_COUNT_REG0,
+	ICSS_IEP_COUNT_REG1,
+	ICSS_IEP_CAPTURE_CFG_REG,
+	ICSS_IEP_CAPTURE_STAT_REG,
+
+	ICSS_IEP_CAP6_RISE_REG0,
+	ICSS_IEP_CAP6_RISE_REG1,
+
+	ICSS_IEP_CAP7_RISE_REG0,
+	ICSS_IEP_CAP7_RISE_REG1,
+
+	ICSS_IEP_CMP_CFG_REG,
+	ICSS_IEP_CMP_STAT_REG,
+	ICSS_IEP_CMP0_REG0,
+	ICSS_IEP_CMP0_REG1,
+	ICSS_IEP_CMP1_REG0,
+	ICSS_IEP_CMP1_REG1,
+
+	ICSS_IEP_CMP8_REG0,
+	ICSS_IEP_CMP8_REG1,
+	ICSS_IEP_SYNC_CTRL_REG,
+	ICSS_IEP_SYNC0_STAT_REG,
+	ICSS_IEP_SYNC1_STAT_REG,
+	ICSS_IEP_SYNC_PWIDTH_REG,
+	ICSS_IEP_SYNC0_PERIOD_REG,
+	ICSS_IEP_SYNC1_DELAY_REG,
+	ICSS_IEP_SYNC_START_REG,
+	ICSS_IEP_MAX_REGS,
+};
+
+/**
+ * struct icss_iep_plat_data - Plat data to handle SoC variants
+ * @config: Regmap configuration data
+ * @reg_offs: register offsets to capture offset differences across SoCs
+ * @flags: Flags to represent IEP properties
+ */
+struct icss_iep_plat_data {
+	struct regmap_config *config;
+	u32 reg_offs[ICSS_IEP_MAX_REGS];
+	u32 flags;
+};
+
+struct icss_iep {
+	struct device *dev;
+	void __iomem *base;
+	const struct icss_iep_plat_data *plat_data;
+	struct regmap *map;
+	struct device_node *client_np;
+	unsigned long refclk_freq;
+	int clk_tick_time;	/* one refclk tick time in ns */
+	struct ptp_clock_info ptp_info;
+	struct ptp_clock *ptp_clock;
+	struct mutex ptp_clk_mutex;	/* PHC access serializer */
+	spinlock_t irq_lock; /* CMP IRQ vs icss_iep_ptp_enable access */
+	u32 def_inc;
+	s16 slow_cmp_inc;
+	u32 slow_cmp_count;
+	const struct icss_iep_clockops *ops;
+	void *clockops_data;
+	u32 cycle_time_ns;
+	u32 perout_enabled;
+	bool pps_enabled;
+	int cap_cmp_irq;
+	u64 period;
+	u32 latch_enable;
+};
+
+/**
+ * icss_iep_get_count_hi() - Get the upper 32 bit IEP counter
+ * @iep: Pointer to structure representing IEP.
+ *
+ * Return: upper 32 bit IEP counter
+ */
+int icss_iep_get_count_hi(struct icss_iep *iep)
+{
+	u32 val = 0;
+
+	if (iep && (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT))
+		val = readl(iep->base + iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG1]);
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(icss_iep_get_count_hi);
+
+/**
+ * icss_iep_get_count_low() - Get the lower 32 bit IEP counter
+ * @iep: Pointer to structure representing IEP.
+ *
+ * Return: lower 32 bit IEP counter
+ */
+int icss_iep_get_count_low(struct icss_iep *iep)
+{
+	u32 val = 0;
+
+	if (iep)
+		val = readl(iep->base + iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG0]);
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(icss_iep_get_count_low);
+
+/**
+ * icss_iep_get_ptp_clock_idx() - Get PTP clock index using IEP driver
+ * @iep: Pointer to structure representing IEP.
+ *
+ * Return: PTP clock index, -1 if not registered
+ */
+int icss_iep_get_ptp_clock_idx(struct icss_iep *iep)
+{
+	if (!iep || !iep->ptp_clock)
+		return -1;
+	return ptp_clock_index(iep->ptp_clock);
+}
+EXPORT_SYMBOL_GPL(icss_iep_get_ptp_clock_idx);
+
+static void icss_iep_set_counter(struct icss_iep *iep, u64 ns)
+{
+	if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+		writel(upper_32_bits(ns), iep->base +
+		       iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG1]);
+	writel(upper_32_bits(ns), iep->base + iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG0]);
+}
+
+static void icss_iep_update_to_next_boundary(struct icss_iep *iep, u64 start_ns);
+
+/**
+ * icss_iep_settime() - Set time of the PTP clock using IEP driver
+ * @iep: Pointer to structure representing IEP.
+ * @ns: Time to be set in nanoseconds
+ *
+ * This API uses writel() instead of regmap_write() for write operations as
+ * regmap_write() is too slow and this API is time sensitive.
+ */
+static void icss_iep_settime(struct icss_iep *iep, u64 ns)
+{
+	unsigned long flags;
+
+	if (iep->ops && iep->ops->settime) {
+		iep->ops->settime(iep->clockops_data, ns);
+		return;
+	}
+
+	spin_lock_irqsave(&iep->irq_lock, flags);
+	if (iep->pps_enabled || iep->perout_enabled)
+		writel(0, iep->base + iep->plat_data->reg_offs[ICSS_IEP_SYNC_CTRL_REG]);
+
+	icss_iep_set_counter(iep, ns);
+
+	if (iep->pps_enabled || iep->perout_enabled) {
+		icss_iep_update_to_next_boundary(iep, ns);
+		writel(IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN,
+		       iep->base + iep->plat_data->reg_offs[ICSS_IEP_SYNC_CTRL_REG]);
+	}
+	spin_unlock_irqrestore(&iep->irq_lock, flags);
+}
+
+/**
+ * icss_iep_gettime() - Get time of the PTP clock using IEP driver
+ * @iep: Pointer to structure representing IEP.
+ * @sts: Pointer to structure representing PTP system timestamp.
+ *
+ * This API uses readl() instead of regmap_read() for read operations as
+ * regmap_read() is too slow and this API is time sensitive.
+ *
+ * Return: The current timestamp of the PTP clock using IEP driver
+ */
+static u64 icss_iep_gettime(struct icss_iep *iep,
+			    struct ptp_system_timestamp *sts)
+{
+	u32 ts_hi = 0, ts_lo;
+	unsigned long flags;
+
+	if (iep->ops && iep->ops->gettime)
+		return iep->ops->gettime(iep->clockops_data, sts);
+
+	/* use local_irq_x() to make it work for both RT/non-RT */
+	local_irq_save(flags);
+
+	/* no need to play with hi-lo, hi is latched when lo is read */
+	ptp_read_system_prets(sts);
+	ts_lo = readl(iep->base + iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG0]);
+	ptp_read_system_postts(sts);
+	if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+		ts_hi = readl(iep->base + iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG1]);
+
+	local_irq_restore(flags);
+
+	return (u64)ts_lo | (u64)ts_hi << 32;
+}
+
+static void icss_iep_enable(struct icss_iep *iep)
+{
+	regmap_update_bits(iep->map, ICSS_IEP_GLOBAL_CFG_REG,
+			   IEP_GLOBAL_CFG_CNT_ENABLE,
+			   IEP_GLOBAL_CFG_CNT_ENABLE);
+}
+
+static void icss_iep_disable(struct icss_iep *iep)
+{
+	regmap_update_bits(iep->map, ICSS_IEP_GLOBAL_CFG_REG,
+			   IEP_GLOBAL_CFG_CNT_ENABLE,
+			   0);
+}
+
+static void icss_iep_enable_shadow_mode(struct icss_iep *iep)
+{
+	u32 cycle_time;
+	int cmp;
+
+	cycle_time = iep->cycle_time_ns - iep->def_inc;
+
+	icss_iep_disable(iep);
+
+	/* disable shadow mode */
+	regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+			   IEP_CMP_CFG_SHADOW_EN, 0);
+
+	/* enable shadow mode */
+	regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+			   IEP_CMP_CFG_SHADOW_EN, IEP_CMP_CFG_SHADOW_EN);
+
+	/* clear counters */
+	icss_iep_set_counter(iep, 0);
+
+	/* clear overflow status */
+	regmap_update_bits(iep->map, ICSS_IEP_GLOBAL_STATUS_REG,
+			   IEP_GLOBAL_STATUS_CNT_OVF,
+			   IEP_GLOBAL_STATUS_CNT_OVF);
+
+	/* clear compare status */
+	for (cmp = IEP_MIN_CMP; cmp < IEP_MAX_CMP; cmp++) {
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_STAT_REG,
+				   IEP_CMP_STATUS(cmp), IEP_CMP_STATUS(cmp));
+	}
+
+	/* enable reset counter on CMP0 event */
+	regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+			   IEP_CMP_CFG_CMP0_RST_CNT_EN,
+			   IEP_CMP_CFG_CMP0_RST_CNT_EN);
+	/* enable compare */
+	regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+			   IEP_CMP_CFG_CMP_EN(0),
+			   IEP_CMP_CFG_CMP_EN(0));
+
+	/* set CMP0 value to cycle time */
+	regmap_write(iep->map, ICSS_IEP_CMP0_REG0, cycle_time);
+	if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+		regmap_write(iep->map, ICSS_IEP_CMP0_REG1, cycle_time);
+
+	icss_iep_set_counter(iep, 0);
+	icss_iep_enable(iep);
+}
+
+static void icss_iep_set_default_inc(struct icss_iep *iep, u8 def_inc)
+{
+	regmap_update_bits(iep->map, ICSS_IEP_GLOBAL_CFG_REG,
+			   IEP_GLOBAL_CFG_DEFAULT_INC_MASK,
+			   def_inc << IEP_GLOBAL_CFG_DEFAULT_INC_SHIFT);
+}
+
+static void icss_iep_set_compensation_inc(struct icss_iep *iep, u16 compen_inc)
+{
+	struct device *dev = regmap_get_device(iep->map);
+
+	if (compen_inc > IEP_MAX_COMPEN_INC) {
+		dev_err(dev, "%s: too high compensation inc %d\n",
+			__func__, compen_inc);
+		compen_inc = IEP_MAX_COMPEN_INC;
+	}
+
+	regmap_update_bits(iep->map, ICSS_IEP_GLOBAL_CFG_REG,
+			   IEP_GLOBAL_CFG_COMPEN_INC_MASK,
+			   compen_inc << IEP_GLOBAL_CFG_COMPEN_INC_SHIFT);
+}
+
+static void icss_iep_set_compensation_count(struct icss_iep *iep,
+					    u32 compen_count)
+{
+	struct device *dev = regmap_get_device(iep->map);
+
+	if (compen_count > IEP_MAX_COMPEN_COUNT) {
+		dev_err(dev, "%s: too high compensation count %d\n",
+			__func__, compen_count);
+		compen_count = IEP_MAX_COMPEN_COUNT;
+	}
+
+	regmap_write(iep->map, ICSS_IEP_COMPEN_REG, compen_count);
+}
+
+static void icss_iep_set_slow_compensation_count(struct icss_iep *iep,
+						 u32 compen_count)
+{
+	regmap_write(iep->map, ICSS_IEP_SLOW_COMPEN_REG, compen_count);
+}
+
+/* PTP PHC operations */
+static int icss_iep_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	struct icss_iep *iep = container_of(ptp, struct icss_iep, ptp_info);
+	s32 ppb = scaled_ppm_to_ppb(scaled_ppm);
+	u32 cyc_count;
+	u16 cmp_inc;
+
+	mutex_lock(&iep->ptp_clk_mutex);
+
+	/* ppb is amount of frequency we want to adjust in 1GHz (billion)
+	 * e.g. 100ppb means we need to speed up clock by 100Hz
+	 * i.e. at end of 1 second (1 billion ns) clock time, we should be
+	 * counting 100 more ns.
+	 * We use IEP slow compensation to achieve continuous freq. adjustment.
+	 * There are 2 parts. Cycle time and adjustment per cycle.
+	 * Simplest case would be 1 sec Cycle time. Then adjustment
+	 * pre cycle would be (def_inc + ppb) value.
+	 * Cycle time will have to be chosen based on how worse the ppb is.
+	 * e.g. smaller the ppb, cycle time has to be large.
+	 * The minimum adjustment we can do is +-1ns per cycle so let's
+	 * reduce the cycle time to get 1ns per cycle adjustment.
+	 *	1ppb = 1sec cycle time & 1ns adjust
+	 *	1000ppb = 1/1000 cycle time & 1ns adjust per cycle
+	 */
+
+	if (iep->cycle_time_ns)
+		iep->slow_cmp_inc = iep->clk_tick_time;	/* 4ns adj per cycle */
+	else
+		iep->slow_cmp_inc = 1;	/* 1ns adjust per cycle */
+
+	if (ppb < 0) {
+		iep->slow_cmp_inc = -iep->slow_cmp_inc;
+		ppb = -ppb;
+	}
+
+	cyc_count = NSEC_PER_SEC;		/* 1s cycle time @1GHz */
+	cyc_count /= ppb;		/* cycle time per ppb */
+
+	/* slow_cmp_count is decremented every clock cycle, e.g. @250MHz */
+	if (!iep->cycle_time_ns)
+		cyc_count /= iep->clk_tick_time;
+	iep->slow_cmp_count = cyc_count;
+
+	/* iep->clk_tick_time is def_inc */
+	cmp_inc = iep->clk_tick_time + iep->slow_cmp_inc;
+	icss_iep_set_compensation_inc(iep, cmp_inc);
+	icss_iep_set_slow_compensation_count(iep, iep->slow_cmp_count);
+
+	mutex_unlock(&iep->ptp_clk_mutex);
+
+	return 0;
+}
+
+static int icss_iep_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct icss_iep *iep = container_of(ptp, struct icss_iep, ptp_info);
+	s64 ns;
+
+	mutex_lock(&iep->ptp_clk_mutex);
+	if (iep->ops && iep->ops->adjtime) {
+		iep->ops->adjtime(iep->clockops_data, delta);
+	} else {
+		ns = icss_iep_gettime(iep, NULL);
+		ns += delta;
+		icss_iep_settime(iep, ns);
+	}
+	mutex_unlock(&iep->ptp_clk_mutex);
+
+	return 0;
+}
+
+static int icss_iep_ptp_gettimeex(struct ptp_clock_info *ptp,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
+{
+	struct icss_iep *iep = container_of(ptp, struct icss_iep, ptp_info);
+	u64 ns;
+
+	mutex_lock(&iep->ptp_clk_mutex);
+	ns = icss_iep_gettime(iep, sts);
+	*ts = ns_to_timespec64(ns);
+	mutex_unlock(&iep->ptp_clk_mutex);
+
+	return 0;
+}
+
+static int icss_iep_ptp_settime(struct ptp_clock_info *ptp,
+				const struct timespec64 *ts)
+{
+	struct icss_iep *iep = container_of(ptp, struct icss_iep, ptp_info);
+	u64 ns;
+
+	mutex_lock(&iep->ptp_clk_mutex);
+	ns = timespec64_to_ns(ts);
+	icss_iep_settime(iep, ns);
+	mutex_unlock(&iep->ptp_clk_mutex);
+
+	return 0;
+}
+
+static void icss_iep_update_to_next_boundary(struct icss_iep *iep, u64 start_ns)
+{
+	u64 ns, p_ns;
+	u32 offset;
+
+	ns = icss_iep_gettime(iep, NULL);
+	if (start_ns < ns)
+		start_ns = ns;
+	p_ns = iep->period;
+	/* Round up to next period boundary */
+	start_ns += p_ns - 1;
+	offset = do_div(start_ns, p_ns);
+	start_ns = start_ns * p_ns;
+	/* If it is too close to update, shift to next boundary */
+	if (p_ns - offset < 10)
+		start_ns += p_ns;
+
+	regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(start_ns));
+	if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+		regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(start_ns));
+}
+
+static int icss_iep_perout_enable_hw(struct icss_iep *iep,
+				     struct ptp_perout_request *req, int on)
+{
+	int ret;
+	u64 cmp;
+
+	if (iep->ops && iep->ops->perout_enable) {
+		ret = iep->ops->perout_enable(iep->clockops_data, req, on, &cmp);
+		if (ret)
+			return ret;
+
+		if (on) {
+			/* Configure CMP */
+			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(cmp));
+			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(cmp));
+			/* Configure SYNC, 1ms pulse width */
+			regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG, 1000000);
+			regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
+			regmap_write(iep->map, ICSS_IEP_SYNC_START_REG, 0);
+			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
+			/* Enable CMP 1 */
+			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+					   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
+		} else {
+			/* Disable CMP 1 */
+			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+					   IEP_CMP_CFG_CMP_EN(1), 0);
+
+			/* clear regs */
+			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
+			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
+		}
+	} else {
+		if (on) {
+			u64 start_ns;
+
+			iep->period = ((u64)req->period.sec * NSEC_PER_SEC) +
+				      req->period.nsec;
+			start_ns = ((u64)req->period.sec * NSEC_PER_SEC)
+				   + req->period.nsec;
+			icss_iep_update_to_next_boundary(iep, start_ns);
+
+			/* Enable Sync in single shot mode  */
+			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
+				     IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
+			/* Enable CMP 1 */
+			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+					   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
+		} else {
+			/* Disable CMP 1 */
+			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+					   IEP_CMP_CFG_CMP_EN(1), 0);
+
+			/* clear CMP regs */
+			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
+			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
+
+			/* Disable sync */
+			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0);
+		}
+	}
+
+	return 0;
+}
+
+static int icss_iep_perout_enable(struct icss_iep *iep,
+				  struct ptp_perout_request *req, int on)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	mutex_lock(&iep->ptp_clk_mutex);
+
+	if (iep->pps_enabled) {
+		ret = -EBUSY;
+		goto exit;
+	}
+
+	if (iep->perout_enabled == !!on)
+		goto exit;
+
+	spin_lock_irqsave(&iep->irq_lock, flags);
+	ret = icss_iep_perout_enable_hw(iep, req, on);
+	if (!ret)
+		iep->perout_enabled = !!on;
+	spin_unlock_irqrestore(&iep->irq_lock, flags);
+
+exit:
+	mutex_unlock(&iep->ptp_clk_mutex);
+
+	return ret;
+}
+
+static int icss_iep_pps_enable(struct icss_iep *iep, int on)
+{
+	struct ptp_clock_request rq;
+	struct timespec64 ts;
+	unsigned long flags;
+	int ret = 0;
+	u64 ns;
+
+	mutex_lock(&iep->ptp_clk_mutex);
+
+	if (iep->perout_enabled) {
+		ret = -EBUSY;
+		goto exit;
+	}
+
+	if (iep->pps_enabled == !!on)
+		goto exit;
+
+	spin_lock_irqsave(&iep->irq_lock, flags);
+
+	rq.perout.index = 0;
+	if (on) {
+		ns = icss_iep_gettime(iep, NULL);
+		ts = ns_to_timespec64(ns);
+		rq.perout.period.sec = 1;
+		rq.perout.period.nsec = 0;
+		rq.perout.start.sec = ts.tv_sec + 2;
+		rq.perout.start.nsec = 0;
+		ret = icss_iep_perout_enable_hw(iep, &rq.perout, on);
+	} else {
+		ret = icss_iep_perout_enable_hw(iep, &rq.perout, on);
+	}
+
+	if (!ret)
+		iep->pps_enabled = !!on;
+
+	spin_unlock_irqrestore(&iep->irq_lock, flags);
+
+exit:
+	mutex_unlock(&iep->ptp_clk_mutex);
+
+	return ret;
+}
+
+static int icss_iep_extts_enable(struct icss_iep *iep, u32 index, int on)
+{
+	u32 val, cap, ret = 0;
+
+	mutex_lock(&iep->ptp_clk_mutex);
+
+	if (iep->ops && iep->ops->extts_enable) {
+		ret = iep->ops->extts_enable(iep->clockops_data, index, on);
+		goto exit;
+	}
+
+	if (((iep->latch_enable & BIT(index)) >> index) == on)
+		goto exit;
+
+	regmap_read(iep->map, ICSS_IEP_CAPTURE_CFG_REG, &val);
+	cap = IEP_CAP_CFG_CAP_ASYNC_EN(index) | IEP_CAP_CFG_CAPNR_1ST_EVENT_EN(index);
+	if (on) {
+		val |= cap;
+		iep->latch_enable |= BIT(index);
+	} else {
+		val &= ~cap;
+		iep->latch_enable &= ~BIT(index);
+	}
+	regmap_write(iep->map, ICSS_IEP_CAPTURE_CFG_REG, val);
+
+exit:
+	mutex_unlock(&iep->ptp_clk_mutex);
+
+	return ret;
+}
+
+static int icss_iep_ptp_enable(struct ptp_clock_info *ptp,
+			       struct ptp_clock_request *rq, int on)
+{
+	struct icss_iep *iep = container_of(ptp, struct icss_iep, ptp_info);
+
+	switch (rq->type) {
+	case PTP_CLK_REQ_PEROUT:
+		return icss_iep_perout_enable(iep, &rq->perout, on);
+	case PTP_CLK_REQ_PPS:
+		return icss_iep_pps_enable(iep, on);
+	case PTP_CLK_REQ_EXTTS:
+		return icss_iep_extts_enable(iep, rq->extts.index, on);
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static struct ptp_clock_info icss_iep_ptp_info = {
+	.owner		= THIS_MODULE,
+	.name		= "ICSS IEP timer",
+	.max_adj	= 10000000,
+	.adjfine	= icss_iep_ptp_adjfine,
+	.adjtime	= icss_iep_ptp_adjtime,
+	.gettimex64	= icss_iep_ptp_gettimeex,
+	.settime64	= icss_iep_ptp_settime,
+	.enable		= icss_iep_ptp_enable,
+};
+
+struct icss_iep *icss_iep_get_idx(struct device_node *np, int idx)
+{
+	struct platform_device *pdev;
+	struct device_node *iep_np;
+	struct icss_iep *iep;
+
+	iep_np = of_parse_phandle(np, "ti,iep", idx);
+	if (!iep_np || !of_device_is_available(iep_np))
+		return ERR_PTR(-ENODEV);
+
+	pdev = of_find_device_by_node(iep_np);
+	of_node_put(iep_np);
+
+	if (!pdev)
+		/* probably IEP not yet probed */
+		return ERR_PTR(-EPROBE_DEFER);
+
+	iep = platform_get_drvdata(pdev);
+	if (!iep)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	device_lock(iep->dev);
+	if (iep->client_np) {
+		device_unlock(iep->dev);
+		dev_err(iep->dev, "IEP is already acquired by %s",
+			iep->client_np->name);
+		return ERR_PTR(-EBUSY);
+	}
+	iep->client_np = np;
+	device_unlock(iep->dev);
+	get_device(iep->dev);
+
+	return iep;
+}
+EXPORT_SYMBOL_GPL(icss_iep_get_idx);
+
+struct icss_iep *icss_iep_get(struct device_node *np)
+{
+	return icss_iep_get_idx(np, 0);
+}
+EXPORT_SYMBOL_GPL(icss_iep_get);
+
+void icss_iep_put(struct icss_iep *iep)
+{
+	device_lock(iep->dev);
+	iep->client_np = NULL;
+	device_unlock(iep->dev);
+	put_device(iep->dev);
+}
+EXPORT_SYMBOL_GPL(icss_iep_put);
+
+int icss_iep_init(struct icss_iep *iep, const struct icss_iep_clockops *clkops,
+		  void *clockops_data, u32 cycle_time_ns)
+{
+	int ret = 0;
+
+	iep->cycle_time_ns = cycle_time_ns;
+	iep->clk_tick_time = iep->def_inc;
+	iep->ops = clkops;
+	iep->clockops_data = clockops_data;
+	icss_iep_set_default_inc(iep, iep->def_inc);
+	icss_iep_set_compensation_inc(iep, iep->def_inc);
+	icss_iep_set_compensation_count(iep, 0);
+	regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG, iep->refclk_freq / 10); /* 100 ms pulse */
+	regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
+	if (iep->plat_data->flags & ICSS_IEP_SLOW_COMPEN_REG_SUPPORT)
+		icss_iep_set_slow_compensation_count(iep, 0);
+
+	if (!(iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT) ||
+	    !(iep->plat_data->flags & ICSS_IEP_SLOW_COMPEN_REG_SUPPORT))
+		goto skip_perout;
+
+	if (iep->ops && iep->ops->perout_enable) {
+		iep->ptp_info.n_per_out = 1;
+		iep->ptp_info.pps = 1;
+	}
+
+	if (iep->ops && iep->ops->extts_enable)
+		iep->ptp_info.n_ext_ts = 2;
+
+skip_perout:
+	if (cycle_time_ns)
+		icss_iep_enable_shadow_mode(iep);
+	else
+		icss_iep_enable(iep);
+	icss_iep_settime(iep, ktime_get_real_ns());
+
+	iep->ptp_clock = ptp_clock_register(&iep->ptp_info, iep->dev);
+	if (IS_ERR(iep->ptp_clock)) {
+		ret = PTR_ERR(iep->ptp_clock);
+		iep->ptp_clock = NULL;
+		dev_err(iep->dev, "Failed to register ptp clk %d\n", ret);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(icss_iep_init);
+
+int icss_iep_exit(struct icss_iep *iep)
+{
+	if (iep->ptp_clock) {
+		ptp_clock_unregister(iep->ptp_clock);
+		iep->ptp_clock = NULL;
+	}
+	icss_iep_disable(iep);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(icss_iep_exit);
+
+static int icss_iep_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct icss_iep *iep;
+	struct clk *iep_clk;
+
+	iep = devm_kzalloc(dev, sizeof(*iep), GFP_KERNEL);
+	if (!iep)
+		return -ENOMEM;
+
+	iep->dev = dev;
+	iep->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(iep->base))
+		return -ENODEV;
+
+	iep_clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(iep_clk))
+		return PTR_ERR(iep_clk);
+
+	iep->refclk_freq = clk_get_rate(iep_clk);
+
+	iep->def_inc = NSEC_PER_SEC / iep->refclk_freq;	/* ns per clock tick */
+	if (iep->def_inc > IEP_MAX_DEF_INC) {
+		dev_err(dev, "Failed to set def_inc %d.  IEP_clock is too slow to be supported\n",
+			iep->def_inc);
+		return -EINVAL;
+	}
+
+	iep->plat_data = device_get_match_data(dev);
+	if (!iep->plat_data)
+		return -EINVAL;
+
+	iep->map = devm_regmap_init(dev, NULL, iep, iep->plat_data->config);
+	if (IS_ERR(iep->map)) {
+		dev_err(dev, "Failed to create regmap for IEP %ld\n",
+			PTR_ERR(iep->map));
+		return PTR_ERR(iep->map);
+	}
+
+	iep->ptp_info = icss_iep_ptp_info;
+	mutex_init(&iep->ptp_clk_mutex);
+	spin_lock_init(&iep->irq_lock);
+	dev_set_drvdata(dev, iep);
+	icss_iep_disable(iep);
+
+	return 0;
+}
+
+static bool am654_icss_iep_valid_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ICSS_IEP_GLOBAL_CFG_REG ... ICSS_IEP_SYNC_START_REG:
+		return true;
+	default:
+		return false;
+	}
+
+	return false;
+}
+
+static int icss_iep_regmap_write(void *context, unsigned int reg,
+				 unsigned int val)
+{
+	struct icss_iep *iep = context;
+
+	writel(val, iep->base + iep->plat_data->reg_offs[reg]);
+
+	return 0;
+}
+
+static int icss_iep_regmap_read(void *context, unsigned int reg,
+				unsigned int *val)
+{
+	struct icss_iep *iep = context;
+
+	*val = readl(iep->base + iep->plat_data->reg_offs[reg]);
+
+	return 0;
+}
+
+static struct regmap_config am654_icss_iep_regmap_config = {
+	.name = "icss iep",
+	.reg_stride = 1,
+	.reg_write = icss_iep_regmap_write,
+	.reg_read = icss_iep_regmap_read,
+	.writeable_reg = am654_icss_iep_valid_reg,
+	.readable_reg = am654_icss_iep_valid_reg,
+	.fast_io = 1,
+};
+
+static const struct icss_iep_plat_data am654_icss_iep_plat_data = {
+	.flags = ICSS_IEP_64BIT_COUNTER_SUPPORT |
+		 ICSS_IEP_SLOW_COMPEN_REG_SUPPORT |
+		 ICSS_IEP_SHADOW_MODE_SUPPORT,
+	.reg_offs = {
+		[ICSS_IEP_GLOBAL_CFG_REG] = 0x00,
+		[ICSS_IEP_COMPEN_REG] = 0x08,
+		[ICSS_IEP_SLOW_COMPEN_REG] = 0x0C,
+		[ICSS_IEP_COUNT_REG0] = 0x10,
+		[ICSS_IEP_COUNT_REG1] = 0x14,
+		[ICSS_IEP_CAPTURE_CFG_REG] = 0x18,
+		[ICSS_IEP_CAPTURE_STAT_REG] = 0x1c,
+
+		[ICSS_IEP_CAP6_RISE_REG0] = 0x50,
+		[ICSS_IEP_CAP6_RISE_REG1] = 0x54,
+
+		[ICSS_IEP_CAP7_RISE_REG0] = 0x60,
+		[ICSS_IEP_CAP7_RISE_REG1] = 0x64,
+
+		[ICSS_IEP_CMP_CFG_REG] = 0x70,
+		[ICSS_IEP_CMP_STAT_REG] = 0x74,
+		[ICSS_IEP_CMP0_REG0] = 0x78,
+		[ICSS_IEP_CMP0_REG1] = 0x7c,
+		[ICSS_IEP_CMP1_REG0] = 0x80,
+		[ICSS_IEP_CMP1_REG1] = 0x84,
+
+		[ICSS_IEP_CMP8_REG0] = 0xc0,
+		[ICSS_IEP_CMP8_REG1] = 0xc4,
+		[ICSS_IEP_SYNC_CTRL_REG] = 0x180,
+		[ICSS_IEP_SYNC0_STAT_REG] = 0x188,
+		[ICSS_IEP_SYNC1_STAT_REG] = 0x18c,
+		[ICSS_IEP_SYNC_PWIDTH_REG] = 0x190,
+		[ICSS_IEP_SYNC0_PERIOD_REG] = 0x194,
+		[ICSS_IEP_SYNC1_DELAY_REG] = 0x198,
+		[ICSS_IEP_SYNC_START_REG] = 0x19c,
+	},
+	.config = &am654_icss_iep_regmap_config,
+};
+
+static const struct of_device_id icss_iep_of_match[] = {
+	{
+		.compatible = "ti,am654-icss-iep",
+		.data = &am654_icss_iep_plat_data,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, icss_iep_of_match);
+
+static struct platform_driver icss_iep_driver = {
+	.driver = {
+		.name = "icss-iep",
+		.of_match_table = icss_iep_of_match,
+	},
+	.probe = icss_iep_probe,
+};
+module_platform_driver(icss_iep_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("TI ICSS IEP driver");
+MODULE_AUTHOR("Roger Quadros <rogerq@ti.com>");
+MODULE_AUTHOR("Md Danish Anwar <danishanwar@ti.com>");
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.h b/drivers/net/ethernet/ti/icssg/icss_iep.h
new file mode 100644
index 0000000000000..9eee44ae49909
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Texas Instruments ICSSG Industrial Ethernet Peripheral (IEP) Driver
+ *
+ * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ */
+
+#ifndef __NET_TI_ICSS_IEP_H
+#define __NET_TI_ICSS_IEP_H
+
+#include <linux/mutex.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/regmap.h>
+
+struct icss_iep;
+
+/* Firmware specific clock operations */
+struct icss_iep_clockops {
+	void (*settime)(void *clockops_data, u64 ns);
+	void (*adjtime)(void *clockops_data, s64 delta);
+	u64 (*gettime)(void *clockops_data, struct ptp_system_timestamp *sts);
+	int (*perout_enable)(void *clockops_data,
+			     struct ptp_perout_request *req, int on,
+			     u64 *cmp);
+	int (*extts_enable)(void *clockops_data, u32 index, int on);
+};
+
+struct icss_iep *icss_iep_get(struct device_node *np);
+struct icss_iep *icss_iep_get_idx(struct device_node *np, int idx);
+void icss_iep_put(struct icss_iep *iep);
+int icss_iep_init(struct icss_iep *iep, const struct icss_iep_clockops *clkops,
+		  void *clockops_data, u32 cycle_time_ns);
+int icss_iep_exit(struct icss_iep *iep);
+int icss_iep_get_count_low(struct icss_iep *iep);
+int icss_iep_get_count_hi(struct icss_iep *iep);
+int icss_iep_get_ptp_clock_idx(struct icss_iep *iep);
+
+#endif /* __NET_TI_ICSS_IEP_H */
-- 
GitLab


From 186734c158865747f7160b461afcabfaab8f9bca Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Thu, 24 Aug 2023 17:16:17 +0530
Subject: [PATCH 1734/1806] net: ti: icssg-prueth: add packet timestamping and
 ptp support

Add packet timestamping TS and PTP PHC clock support.

For AM65x and AM64x:
 - IEP1 is not used
 - IEP0 is configured in shadow mode with 1ms cycle and shared between
Linux and FW. It provides time and TS in number cycles, so special
conversation in ns is required.
 - IEP0 shared between PRUeth ports.
 - IEP0 supports PPS, periodic output.
 - IEP0 settime() and enabling PPS required FW interraction.
 - RX TS provided with each packet in CPPI5 descriptor.
 - TX TS returned through separate ICSSG hw queues for each port. TX TS
readiness is signaled by INTC IRQ. Only one packet at time can be requested
for TX TS.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Co-developed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/Kconfig               |   1 +
 drivers/net/ethernet/ti/icssg/icss_iep.h      |   1 +
 drivers/net/ethernet/ti/icssg/icssg_ethtool.c |  21 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.c  | 424 +++++++++++++++++-
 drivers/net/ethernet/ti/icssg/icssg_prueth.h  |  26 +-
 5 files changed, 467 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 1af5a90720ec0..88b5b1b47779a 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -186,6 +186,7 @@ config CPMAC
 config TI_ICSSG_PRUETH
 	tristate "TI Gigabit PRU Ethernet driver"
 	select PHYLIB
+	select TI_ICSS_IEP
 	depends on PRU_REMOTEPROC
 	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
 	help
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.h b/drivers/net/ethernet/ti/icssg/icss_iep.h
index 9eee44ae49909..9c7f4d0a09167 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.h
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.h
@@ -13,6 +13,7 @@
 #include <linux/regmap.h>
 
 struct icss_iep;
+extern const struct icss_iep_clockops prueth_iep_clockops;
 
 /* Firmware specific clock operations */
 struct icss_iep_clockops {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
index 02c312f01d10f..a27ec1dcc8d56 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
@@ -109,6 +109,26 @@ static void emac_get_ethtool_stats(struct net_device *ndev,
 			*(data++) = emac->stats[i];
 }
 
+static int emac_get_ts_info(struct net_device *ndev,
+			    struct ethtool_ts_info *info)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	info->so_timestamping =
+		SOF_TIMESTAMPING_TX_HARDWARE |
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+		SOF_TIMESTAMPING_RX_HARDWARE |
+		SOF_TIMESTAMPING_RX_SOFTWARE |
+		SOF_TIMESTAMPING_SOFTWARE |
+		SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	info->phc_index = icss_iep_get_ptp_clock_idx(emac->iep);
+	info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
+
+	return 0;
+}
+
 static int emac_set_channels(struct net_device *ndev,
 			     struct ethtool_channels *ch)
 {
@@ -176,6 +196,7 @@ const struct ethtool_ops icssg_ethtool_ops = {
 	.get_sset_count = emac_get_sset_count,
 	.get_ethtool_stats = emac_get_ethtool_stats,
 	.get_strings = emac_get_strings,
+	.get_ts_info = emac_get_ts_info,
 	.get_channels = emac_get_channels,
 	.set_channels = emac_set_channels,
 	.get_link_ksettings = emac_get_link_ksettings,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 47b941fb0198d..1bcb4e1746527 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -56,6 +56,8 @@
 /* CTRLMMR_ICSSG_RGMII_CTRL register bits */
 #define ICSSG_CTRL_RGMII_ID_MODE                BIT(24)
 
+#define IEP_DEFAULT_CYCLE_TIME_NS	1000000	/* 1 ms */
+
 static void prueth_cleanup_rx_chns(struct prueth_emac *emac,
 				   struct prueth_rx_chn *rx_chn,
 				   int max_rflows)
@@ -471,6 +473,37 @@ static int prueth_dma_rx_push(struct prueth_emac *emac,
 					desc_rx, desc_dma);
 }
 
+static u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns)
+{
+	u32 iepcount_lo, iepcount_hi, hi_rollover_count;
+	u64 ns;
+
+	iepcount_lo = lo & GENMASK(19, 0);
+	iepcount_hi = (hi & GENMASK(11, 0)) << 12 | lo >> 20;
+	hi_rollover_count = hi >> 11;
+
+	ns = ((u64)hi_rollover_count) << 23 | (iepcount_hi + hi_sw);
+	ns = ns * cycle_time_ns + iepcount_lo;
+
+	return ns;
+}
+
+static void emac_rx_timestamp(struct prueth_emac *emac,
+			      struct sk_buff *skb, u32 *psdata)
+{
+	struct skb_shared_hwtstamps *ssh;
+	u64 ns;
+
+	u32 hi_sw = readl(emac->prueth->shram.va +
+			  TIMESYNC_FW_WC_COUNT_HI_SW_OFFSET_OFFSET);
+	ns = icssg_ts_to_ns(hi_sw, psdata[1], psdata[0],
+			    IEP_DEFAULT_CYCLE_TIME_NS);
+
+	ssh = skb_hwtstamps(skb);
+	memset(ssh, 0, sizeof(*ssh));
+	ssh->hwtstamp = ns_to_ktime(ns);
+}
+
 static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 {
 	struct prueth_rx_chn *rx_chn = &emac->rx_chns;
@@ -480,6 +513,7 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 	struct sk_buff *skb, *new_skb;
 	dma_addr_t desc_dma, buf_dma;
 	void **swdata;
+	u32 *psdata;
 	int ret;
 
 	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma);
@@ -497,6 +531,11 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
 	skb = *swdata;
 
+	psdata = cppi5_hdesc_get_psdata(desc_rx);
+	/* RX HW timestamp */
+	if (emac->rx_ts_enabled)
+		emac_rx_timestamp(emac, skb, psdata);
+
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
 	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
 	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
@@ -557,6 +596,86 @@ static void prueth_rx_cleanup(void *data, dma_addr_t desc_dma)
 	dev_kfree_skb_any(skb);
 }
 
+static int emac_get_tx_ts(struct prueth_emac *emac,
+			  struct emac_tx_ts_response *rsp)
+{
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+	int addr;
+
+	addr = icssg_queue_pop(prueth, slice == 0 ?
+			       ICSSG_TS_POP_SLICE0 : ICSSG_TS_POP_SLICE1);
+	if (addr < 0)
+		return addr;
+
+	memcpy_fromio(rsp, prueth->shram.va + addr, sizeof(*rsp));
+	/* return buffer back for to pool */
+	icssg_queue_push(prueth, slice == 0 ?
+			 ICSSG_TS_PUSH_SLICE0 : ICSSG_TS_PUSH_SLICE1, addr);
+
+	return 0;
+}
+
+static void tx_ts_work(struct prueth_emac *emac)
+{
+	struct skb_shared_hwtstamps ssh;
+	struct emac_tx_ts_response tsr;
+	struct sk_buff *skb;
+	int ret = 0;
+	u32 hi_sw;
+	u64 ns;
+
+	/* There may be more than one pending requests */
+	while (1) {
+		ret = emac_get_tx_ts(emac, &tsr);
+		if (ret) /* nothing more */
+			break;
+
+		if (tsr.cookie >= PRUETH_MAX_TX_TS_REQUESTS ||
+		    !emac->tx_ts_skb[tsr.cookie]) {
+			netdev_err(emac->ndev, "Invalid TX TS cookie 0x%x\n",
+				   tsr.cookie);
+			break;
+		}
+
+		skb = emac->tx_ts_skb[tsr.cookie];
+		emac->tx_ts_skb[tsr.cookie] = NULL;	/* free slot */
+		if (!skb) {
+			netdev_err(emac->ndev, "Driver Bug! got NULL skb\n");
+			break;
+		}
+
+		hi_sw = readl(emac->prueth->shram.va +
+			      TIMESYNC_FW_WC_COUNT_HI_SW_OFFSET_OFFSET);
+		ns = icssg_ts_to_ns(hi_sw, tsr.hi_ts, tsr.lo_ts,
+				    IEP_DEFAULT_CYCLE_TIME_NS);
+
+		memset(&ssh, 0, sizeof(ssh));
+		ssh.hwtstamp = ns_to_ktime(ns);
+
+		skb_tstamp_tx(skb, &ssh);
+		dev_consume_skb_any(skb);
+
+		if (atomic_dec_and_test(&emac->tx_ts_pending))	/* no more? */
+			break;
+	}
+}
+
+static int prueth_tx_ts_cookie_get(struct prueth_emac *emac)
+{
+	int i;
+
+	/* search and get the next free slot */
+	for (i = 0; i < PRUETH_MAX_TX_TS_REQUESTS; i++) {
+		if (!emac->tx_ts_skb[i]) {
+			emac->tx_ts_skb[i] = ERR_PTR(-EBUSY); /* reserve slot */
+			return i;
+		}
+	}
+
+	return -EBUSY;
+}
+
 /**
  * emac_ndo_start_xmit - EMAC Transmit function
  * @skb: SKB pointer
@@ -577,6 +696,8 @@ static enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device
 	struct prueth_tx_chn *tx_chn;
 	dma_addr_t desc_dma, buf_dma;
 	int i, ret = 0, q_idx;
+	bool in_tx_ts = 0;
+	int tx_ts_cookie;
 	void **swdata;
 	u32 pkt_len;
 	u32 *epib;
@@ -608,6 +729,18 @@ static enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device
 	epib = first_desc->epib;
 	epib[0] = 0;
 	epib[1] = 0;
+	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
+	    emac->tx_ts_enabled) {
+		tx_ts_cookie = prueth_tx_ts_cookie_get(emac);
+		if (tx_ts_cookie >= 0) {
+			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+			/* Request TX timestamp */
+			epib[0] = (u32)tx_ts_cookie;
+			epib[1] = 0x80000000;	/* TX TS request */
+			emac->tx_ts_skb[tx_ts_cookie] = skb_get(skb);
+			in_tx_ts = 1;
+		}
+	}
 
 	/* set dst tag to indicate internal qid at the firmware which is at
 	 * bit8..bit15. bit0..bit7 indicates port num for directed
@@ -629,7 +762,7 @@ static enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device
 		if (!next_desc) {
 			netdev_err(ndev,
 				   "tx: failed to allocate frag. descriptor\n");
-			goto free_desc_stop_q_busy;
+			goto free_desc_stop_q_busy_cleanup_tx_ts;
 		}
 
 		buf_dma = skb_frag_dma_map(tx_chn->dma_dev, frag, 0, frag_size,
@@ -638,7 +771,7 @@ static enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device
 			netdev_err(ndev, "tx: Failed to map skb page\n");
 			k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
 			ret = NETDEV_TX_OK;
-			goto drop_free_descs;
+			goto cleanup_tx_ts;
 		}
 
 		cppi5_hdesc_reset_hbdesc(next_desc);
@@ -670,6 +803,9 @@ static enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device
 		goto drop_free_descs;
 	}
 
+	if (in_tx_ts)
+		atomic_inc(&emac->tx_ts_pending);
+
 	if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) < MAX_SKB_FRAGS) {
 		netif_tx_stop_queue(netif_txq);
 		/* Barrier, so that stop_queue visible to other cpus */
@@ -682,6 +818,12 @@ static enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device
 
 	return NETDEV_TX_OK;
 
+cleanup_tx_ts:
+	if (in_tx_ts) {
+		dev_kfree_skb_any(emac->tx_ts_skb[tx_ts_cookie]);
+		emac->tx_ts_skb[tx_ts_cookie] = NULL;
+	}
+
 drop_free_descs:
 	prueth_xmit_free(tx_chn, first_desc);
 
@@ -694,7 +836,11 @@ drop_free_skb:
 
 	return ret;
 
-free_desc_stop_q_busy:
+free_desc_stop_q_busy_cleanup_tx_ts:
+	if (in_tx_ts) {
+		dev_kfree_skb_any(emac->tx_ts_skb[tx_ts_cookie]);
+		emac->tx_ts_skb[tx_ts_cookie] = NULL;
+	}
 	prueth_xmit_free(tx_chn, first_desc);
 
 drop_stop_q_busy:
@@ -717,6 +863,16 @@ static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma)
 	dev_kfree_skb_any(skb);
 }
 
+static irqreturn_t prueth_tx_ts_irq(int irq, void *dev_id)
+{
+	struct prueth_emac *emac = dev_id;
+
+	/* currently only TX timestamp is being returned */
+	tx_ts_work(emac);
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t prueth_rx_irq(int irq, void *dev_id)
 {
 	struct prueth_emac *emac = dev_id;
@@ -820,6 +976,18 @@ static void prueth_emac_stop(struct prueth_emac *emac)
 	rproc_shutdown(prueth->pru[slice]);
 }
 
+static void prueth_cleanup_tx_ts(struct prueth_emac *emac)
+{
+	int i;
+
+	for (i = 0; i < PRUETH_MAX_TX_TS_REQUESTS; i++) {
+		if (emac->tx_ts_skb[i]) {
+			dev_kfree_skb_any(emac->tx_ts_skb[i]);
+			emac->tx_ts_skb[i] = NULL;
+		}
+	}
+}
+
 /* called back by PHY layer if there is change in link state of hw port*/
 static void emac_adjust_link(struct net_device *ndev)
 {
@@ -881,6 +1049,7 @@ static void emac_adjust_link(struct net_device *ndev)
 		netif_tx_wake_all_queues(ndev);
 	} else {
 		netif_tx_stop_all_queues(ndev);
+		prueth_cleanup_tx_ts(emac);
 	}
 }
 
@@ -992,6 +1161,139 @@ static int emac_phy_connect(struct prueth_emac *emac)
 	return 0;
 }
 
+static u64 prueth_iep_gettime(void *clockops_data, struct ptp_system_timestamp *sts)
+{
+	u32 hi_rollover_count, hi_rollover_count_r;
+	struct prueth_emac *emac = clockops_data;
+	struct prueth *prueth = emac->prueth;
+	void __iomem *fw_hi_r_count_addr;
+	void __iomem *fw_count_hi_addr;
+	u32 iepcount_hi, iepcount_hi_r;
+	unsigned long flags;
+	u32 iepcount_lo;
+	u64 ts = 0;
+
+	fw_count_hi_addr = prueth->shram.va + TIMESYNC_FW_WC_COUNT_HI_SW_OFFSET_OFFSET;
+	fw_hi_r_count_addr = prueth->shram.va + TIMESYNC_FW_WC_HI_ROLLOVER_COUNT_OFFSET;
+
+	local_irq_save(flags);
+	do {
+		iepcount_hi = icss_iep_get_count_hi(emac->iep);
+		iepcount_hi += readl(fw_count_hi_addr);
+		hi_rollover_count = readl(fw_hi_r_count_addr);
+		ptp_read_system_prets(sts);
+		iepcount_lo = icss_iep_get_count_low(emac->iep);
+		ptp_read_system_postts(sts);
+
+		iepcount_hi_r = icss_iep_get_count_hi(emac->iep);
+		iepcount_hi_r += readl(fw_count_hi_addr);
+		hi_rollover_count_r = readl(fw_hi_r_count_addr);
+	} while ((iepcount_hi_r != iepcount_hi) ||
+		 (hi_rollover_count != hi_rollover_count_r));
+	local_irq_restore(flags);
+
+	ts = ((u64)hi_rollover_count) << 23 | iepcount_hi;
+	ts = ts * (u64)IEP_DEFAULT_CYCLE_TIME_NS + iepcount_lo;
+
+	return ts;
+}
+
+static void prueth_iep_settime(void *clockops_data, u64 ns)
+{
+	struct icssg_setclock_desc __iomem *sc_descp;
+	struct prueth_emac *emac = clockops_data;
+	struct icssg_setclock_desc sc_desc;
+	u64 cyclecount;
+	u32 cycletime;
+	int timeout;
+
+	if (!emac->fw_running)
+		return;
+
+	sc_descp = emac->prueth->shram.va + TIMESYNC_FW_WC_SETCLOCK_DESC_OFFSET;
+
+	cycletime = IEP_DEFAULT_CYCLE_TIME_NS;
+	cyclecount = ns / cycletime;
+
+	memset(&sc_desc, 0, sizeof(sc_desc));
+	sc_desc.margin = cycletime - 1000;
+	sc_desc.cyclecounter0_set = cyclecount & GENMASK(31, 0);
+	sc_desc.cyclecounter1_set = (cyclecount & GENMASK(63, 32)) >> 32;
+	sc_desc.iepcount_set = ns % cycletime;
+	sc_desc.CMP0_current = cycletime - 4; //Count from 0 to (cycle time)-4
+
+	memcpy_toio(sc_descp, &sc_desc, sizeof(sc_desc));
+
+	writeb(1, &sc_descp->request);
+
+	timeout = 5;	/* fw should take 2-3 ms */
+	while (timeout--) {
+		if (readb(&sc_descp->acknowledgment))
+			return;
+
+		usleep_range(500, 1000);
+	}
+
+	dev_err(emac->prueth->dev, "settime timeout\n");
+}
+
+static int prueth_perout_enable(void *clockops_data,
+				struct ptp_perout_request *req, int on,
+				u64 *cmp)
+{
+	struct prueth_emac *emac = clockops_data;
+	u32 reduction_factor = 0, offset = 0;
+	struct timespec64 ts;
+	u64 ns_period;
+
+	if (!on)
+		return 0;
+
+	/* Any firmware specific stuff for PPS/PEROUT handling */
+	ts.tv_sec = req->period.sec;
+	ts.tv_nsec = req->period.nsec;
+	ns_period = timespec64_to_ns(&ts);
+
+	/* f/w doesn't support period less than cycle time */
+	if (ns_period < IEP_DEFAULT_CYCLE_TIME_NS)
+		return -ENXIO;
+
+	reduction_factor = ns_period / IEP_DEFAULT_CYCLE_TIME_NS;
+	offset = ns_period % IEP_DEFAULT_CYCLE_TIME_NS;
+
+	/* f/w requires at least 1uS within a cycle so CMP
+	 * can trigger after SYNC is enabled
+	 */
+	if (offset < 5 * NSEC_PER_USEC)
+		offset = 5 * NSEC_PER_USEC;
+
+	/* if offset is close to cycle time then we will miss
+	 * the CMP event for last tick when IEP rolls over.
+	 * In normal mode, IEP tick is 4ns.
+	 * In slow compensation it could be 0ns or 8ns at
+	 * every slow compensation cycle.
+	 */
+	if (offset > IEP_DEFAULT_CYCLE_TIME_NS - 8)
+		offset = IEP_DEFAULT_CYCLE_TIME_NS - 8;
+
+	/* we're in shadow mode so need to set upper 32-bits */
+	*cmp = (u64)offset << 32;
+
+	writel(reduction_factor, emac->prueth->shram.va +
+		TIMESYNC_FW_WC_SYNCOUT_REDUCTION_FACTOR_OFFSET);
+
+	writel(0, emac->prueth->shram.va +
+		TIMESYNC_FW_WC_SYNCOUT_START_TIME_CYCLECOUNT_OFFSET);
+
+	return 0;
+}
+
+const struct icss_iep_clockops prueth_iep_clockops = {
+	.settime = prueth_iep_settime,
+	.gettime = prueth_iep_gettime,
+	.perout_enable = prueth_perout_enable,
+};
+
 /**
  * emac_ndo_open - EMAC device open
  * @ndev: network adapter device
@@ -1066,10 +1368,20 @@ static int emac_ndo_open(struct net_device *ndev)
 
 	icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu);
 
+	if (!prueth->emacs_initialized) {
+		ret = icss_iep_init(emac->iep, &prueth_iep_clockops,
+				    emac, IEP_DEFAULT_CYCLE_TIME_NS);
+	}
+
+	ret = request_threaded_irq(emac->tx_ts_irq, NULL, prueth_tx_ts_irq,
+				   IRQF_ONESHOT, dev_name(dev), emac);
+	if (ret)
+		goto stop;
+
 	/* Prepare RX */
 	ret = prueth_prepare_rx_chan(emac, &emac->rx_chns, PRUETH_MAX_PKT_SIZE);
 	if (ret)
-		goto stop;
+		goto free_tx_ts_irq;
 
 	ret = k3_udma_glue_enable_rx_chn(emac->rx_chns.rx_chn);
 	if (ret)
@@ -1102,6 +1414,8 @@ reset_tx_chan:
 	prueth_reset_tx_chan(emac, i, false);
 reset_rx_chn:
 	prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, false);
+free_tx_ts_irq:
+	free_irq(emac->tx_ts_irq, emac);
 stop:
 	prueth_emac_stop(emac);
 free_rx_irq:
@@ -1173,6 +1487,14 @@ static int emac_ndo_stop(struct net_device *ndev)
 	/* stop PRUs */
 	prueth_emac_stop(emac);
 
+	if (prueth->emacs_initialized == 1)
+		icss_iep_exit(emac->iep);
+
+	/* stop PRUs */
+	prueth_emac_stop(emac);
+
+	free_irq(emac->tx_ts_irq, emac);
+
 	free_irq(emac->rx_chns.irq[rx_flow], emac);
 	prueth_ndev_del_tx_napi(emac, emac->tx_ch_num);
 	prueth_cleanup_tx_chns(emac);
@@ -1235,8 +1557,79 @@ static void emac_ndo_set_rx_mode(struct net_device *ndev)
 	queue_work(emac->cmd_wq, &emac->rx_mode_work);
 }
 
+static int emac_set_ts_config(struct net_device *ndev, struct ifreq *ifr)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct hwtstamp_config config;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+		emac->tx_ts_enabled = 0;
+		break;
+	case HWTSTAMP_TX_ON:
+		emac->tx_ts_enabled = 1;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config.rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		emac->rx_ts_enabled = 0;
+		break;
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
+		emac->rx_ts_enabled = 1;
+		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+		-EFAULT : 0;
+}
+
+static int emac_get_ts_config(struct net_device *ndev, struct ifreq *ifr)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct hwtstamp_config config;
+
+	config.flags = 0;
+	config.tx_type = emac->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	config.rx_filter = emac->rx_ts_enabled ? HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+			    -EFAULT : 0;
+}
+
 static int emac_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
 {
+	switch (cmd) {
+	case SIOCGHWTSTAMP:
+		return emac_get_ts_config(ndev, ifr);
+	case SIOCSHWTSTAMP:
+		return emac_set_ts_config(ndev, ifr);
+	default:
+		break;
+	}
+
 	return phy_do_ioctl(ndev, ifr, cmd);
 }
 
@@ -1316,6 +1709,7 @@ static int prueth_netdev_init(struct prueth *prueth,
 	struct prueth_emac *emac;
 	struct net_device *ndev;
 	enum prueth_port port;
+	const char *irq_name;
 	enum prueth_mac mac;
 
 	port = prueth_node_port(eth_node);
@@ -1355,6 +1749,15 @@ static int prueth_netdev_init(struct prueth *prueth,
 
 	emac->tx_ch_num = 1;
 
+	irq_name = "tx_ts0";
+	if (emac->port_id == PRUETH_PORT_MII1)
+		irq_name = "tx_ts1";
+	emac->tx_ts_irq = platform_get_irq_byname_optional(prueth->pdev, irq_name);
+	if (emac->tx_ts_irq < 0) {
+		ret = dev_err_probe(prueth->dev, emac->tx_ts_irq, "could not get tx_ts_irq\n");
+		goto free;
+	}
+
 	SET_NETDEV_DEV(ndev, prueth->dev);
 	spin_lock_init(&emac->lock);
 	mutex_init(&emac->cmd_lock);
@@ -1680,6 +2083,13 @@ static int prueth_probe(struct platform_device *pdev)
 	dev_dbg(dev, "sram: pa %llx va %p size %zx\n", prueth->msmcram.pa,
 		prueth->msmcram.va, prueth->msmcram.size);
 
+	prueth->iep0 = icss_iep_get_idx(np, 0);
+	if (IS_ERR(prueth->iep0)) {
+		ret = dev_err_probe(dev, PTR_ERR(prueth->iep0), "iep0 get failed\n");
+		prueth->iep0 = NULL;
+		goto free_pool;
+	}
+
 	/* setup netdev interfaces */
 	if (eth0_node) {
 		ret = prueth_netdev_init(prueth, eth0_node);
@@ -1688,6 +2098,7 @@ static int prueth_probe(struct platform_device *pdev)
 				      eth0_node->name);
 			goto netdev_exit;
 		}
+		prueth->emac[PRUETH_MAC0]->iep = prueth->iep0;
 	}
 
 	if (eth1_node) {
@@ -1697,6 +2108,8 @@ static int prueth_probe(struct platform_device *pdev)
 				      eth1_node->name);
 			goto netdev_exit;
 		}
+
+		prueth->emac[PRUETH_MAC1]->iep = prueth->iep0;
 	}
 
 	/* register the network devices */
@@ -1754,6 +2167,7 @@ netdev_exit:
 		prueth_netdev_exit(prueth, eth_node);
 	}
 
+free_pool:
 	gen_pool_free(prueth->sram_pool,
 		      (unsigned long)prueth->msmcram.va, msmc_ram_size);
 
@@ -1798,6 +2212,8 @@ static void prueth_remove(struct platform_device *pdev)
 		prueth_netdev_exit(prueth, eth_node);
 	}
 
+	icss_iep_put(prueth->iep0);
+
 	gen_pool_free(prueth->sram_pool,
 		      (unsigned long)prueth->msmcram.va,
 		      MSMC_RAM_SIZE);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index a8ce4d01ef160..a56ab4cdc83c4 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -35,6 +35,7 @@
 #include <net/devlink.h>
 
 #include "icssg_config.h"
+#include "icss_iep.h"
 #include "icssg_switch_map.h"
 
 #define PRUETH_MAX_MTU          (2000 - ETH_HLEN - ETH_FCS_LEN)
@@ -122,6 +123,8 @@ struct prueth_rx_chn {
  */
 #define PRUETH_MAX_TX_QUEUES	4
 
+#define PRUETH_MAX_TX_TS_REQUESTS	50 /* Max simultaneous TX_TS requests */
+
 /* data for each emac port */
 struct prueth_emac {
 	bool fw_running;
@@ -139,6 +142,9 @@ struct prueth_emac {
 	struct device_node *phy_node;
 	phy_interface_t phy_if;
 	enum prueth_port port_id;
+	struct icss_iep *iep;
+	unsigned int rx_ts_enabled : 1;
+	unsigned int tx_ts_enabled : 1;
 
 	/* DMA related */
 	struct prueth_tx_chn tx_chns[PRUETH_MAX_TX_QUEUES];
@@ -150,7 +156,15 @@ struct prueth_emac {
 
 	spinlock_t lock;	/* serialize access */
 
-	unsigned long state;
+	/* TX HW Timestamping */
+	/* TX TS cookie will be index to the tx_ts_skb array */
+	struct sk_buff *tx_ts_skb[PRUETH_MAX_TX_TS_REQUESTS];
+	atomic_t tx_ts_pending;
+	int tx_ts_irq;
+
+	u8 cmd_seq;
+	/* shutdown related */
+	u32 cmd_data[4];
 	struct completion cmd_complete;
 	/* Mutex to serialize access to firmware command interface */
 	struct mutex cmd_lock;
@@ -193,6 +207,7 @@ struct prueth_pdata {
  * @pdata: pointer to platform data for ICSSG driver
  * @icssg_hwcmdseq: seq counter or HWQ messages
  * @emacs_initialized: num of EMACs/ext ports that are up/running
+ * @iep0: pointer to IEP0 device
  */
 struct prueth {
 	struct device *dev;
@@ -214,8 +229,15 @@ struct prueth {
 	struct platform_device *pdev;
 	struct prueth_pdata pdata;
 	u8 icssg_hwcmdseq;
-
 	int emacs_initialized;
+	struct icss_iep *iep0;
+};
+
+struct emac_tx_ts_response {
+	u32 reserved[2];
+	u32 cookie;
+	u32 lo_ts;
+	u32 hi_ts;
 };
 
 /* get PRUSS SLICE number from prueth_emac */
-- 
GitLab


From 443a2367ba3c96e0f35ce801bcdfb2ce91f5038c Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 24 Aug 2023 17:16:18 +0530
Subject: [PATCH 1735/1806] net: ti: icssg-prueth: am65x SR2.0 add 10M full
 duplex support

For AM65x SR2.0 it's required to enable IEP1 in raw 64bit mode which is
used by PRU FW to monitor the link and apply w/a for 10M link issue.
Note. No public errata available yet.

Without this w/a the PRU FW will stuck if link state changes under TX
traffic pressure.

Hence, add support for 10M full duplex for AM65x SR2.0:
 - add new IEP API to enable IEP, but without PTP support
 - add pdata quirk_10m_link_issue to enable 10M link issue w/a.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/icssg/icss_iep.c     | 26 +++++++++++++++++++
 drivers/net/ethernet/ti/icssg/icss_iep.h     |  2 ++
 drivers/net/ethernet/ti/icssg/icssg_config.c |  7 +++++
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 27 ++++++++++++++++++--
 drivers/net/ethernet/ti/icssg/icssg_prueth.h |  2 ++
 5 files changed, 62 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index bcc056bf45da9..4cf2a52e43783 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -727,6 +727,32 @@ void icss_iep_put(struct icss_iep *iep)
 }
 EXPORT_SYMBOL_GPL(icss_iep_put);
 
+void icss_iep_init_fw(struct icss_iep *iep)
+{
+	/* start IEP for FW use in raw 64bit mode, no PTP support */
+	iep->clk_tick_time = iep->def_inc;
+	iep->cycle_time_ns = 0;
+	iep->ops = NULL;
+	iep->clockops_data = NULL;
+	icss_iep_set_default_inc(iep, iep->def_inc);
+	icss_iep_set_compensation_inc(iep, iep->def_inc);
+	icss_iep_set_compensation_count(iep, 0);
+	regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG, iep->refclk_freq / 10); /* 100 ms pulse */
+	regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
+	if (iep->plat_data->flags & ICSS_IEP_SLOW_COMPEN_REG_SUPPORT)
+		icss_iep_set_slow_compensation_count(iep, 0);
+
+	icss_iep_enable(iep);
+	icss_iep_settime(iep, 0);
+}
+EXPORT_SYMBOL_GPL(icss_iep_init_fw);
+
+void icss_iep_exit_fw(struct icss_iep *iep)
+{
+	icss_iep_disable(iep);
+}
+EXPORT_SYMBOL_GPL(icss_iep_exit_fw);
+
 int icss_iep_init(struct icss_iep *iep, const struct icss_iep_clockops *clkops,
 		  void *clockops_data, u32 cycle_time_ns)
 {
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.h b/drivers/net/ethernet/ti/icssg/icss_iep.h
index 9c7f4d0a09167..803a4b7148930 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.h
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.h
@@ -35,5 +35,7 @@ int icss_iep_exit(struct icss_iep *iep);
 int icss_iep_get_count_low(struct icss_iep *iep);
 int icss_iep_get_count_hi(struct icss_iep *iep);
 int icss_iep_get_ptp_clock_idx(struct icss_iep *iep);
+void icss_iep_init_fw(struct icss_iep *iep);
+void icss_iep_exit_fw(struct icss_iep *iep);
 
 #endif /* __NET_TI_ICSS_IEP_H */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
index ab648d3efe855..933b846665749 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -210,6 +210,10 @@ void icssg_config_ipg(struct prueth_emac *emac)
 	case SPEED_100:
 		icssg_mii_update_ipg(prueth->mii_rt, slice, MII_RT_TX_IPG_100M);
 		break;
+	case SPEED_10:
+		/* IPG for 10M is same as 100M */
+		icssg_mii_update_ipg(prueth->mii_rt, slice, MII_RT_TX_IPG_100M);
+		break;
 	default:
 		/* Other links speeds not supported */
 		netdev_err(emac->ndev, "Unsupported link speed\n");
@@ -440,6 +444,9 @@ void icssg_config_set_speed(struct prueth_emac *emac)
 	case SPEED_100:
 		fw_speed = FW_LINK_SPEED_100M;
 		break;
+	case SPEED_10:
+		fw_speed = FW_LINK_SPEED_10M;
+		break;
 	default:
 		/* Other links speeds not supported */
 		netdev_err(emac->ndev, "Unsupported link speed\n");
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 1bcb4e1746527..410612f43cbd0 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1149,7 +1149,6 @@ static int emac_phy_connect(struct prueth_emac *emac)
 
 	/* remove unsupported modes */
 	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT);
-	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT);
 	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
 	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
 	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_Pause_BIT);
@@ -2090,13 +2089,29 @@ static int prueth_probe(struct platform_device *pdev)
 		goto free_pool;
 	}
 
+	prueth->iep1 = icss_iep_get_idx(np, 1);
+	if (IS_ERR(prueth->iep1)) {
+		ret = dev_err_probe(dev, PTR_ERR(prueth->iep1), "iep1 get failed\n");
+		icss_iep_put(prueth->iep0);
+		prueth->iep0 = NULL;
+		prueth->iep1 = NULL;
+		goto free_pool;
+	}
+
+	if (prueth->pdata.quirk_10m_link_issue) {
+		/* Enable IEP1 for FW in 64bit mode as W/A for 10M FD link detect issue under TX
+		 * traffic.
+		 */
+		icss_iep_init_fw(prueth->iep1);
+	}
+
 	/* setup netdev interfaces */
 	if (eth0_node) {
 		ret = prueth_netdev_init(prueth, eth0_node);
 		if (ret) {
 			dev_err_probe(dev, ret, "netdev init %s failed\n",
 				      eth0_node->name);
-			goto netdev_exit;
+			goto exit_iep;
 		}
 		prueth->emac[PRUETH_MAC0]->iep = prueth->iep0;
 	}
@@ -2167,6 +2182,10 @@ netdev_exit:
 		prueth_netdev_exit(prueth, eth_node);
 	}
 
+exit_iep:
+	if (prueth->pdata.quirk_10m_link_issue)
+		icss_iep_exit_fw(prueth->iep1);
+
 free_pool:
 	gen_pool_free(prueth->sram_pool,
 		      (unsigned long)prueth->msmcram.va, msmc_ram_size);
@@ -2212,6 +2231,10 @@ static void prueth_remove(struct platform_device *pdev)
 		prueth_netdev_exit(prueth, eth_node);
 	}
 
+	if (prueth->pdata.quirk_10m_link_issue)
+		icss_iep_exit_fw(prueth->iep1);
+
+	icss_iep_put(prueth->iep1);
 	icss_iep_put(prueth->iep0);
 
 	gen_pool_free(prueth->sram_pool,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index a56ab4cdc83c4..3fe80a8758d30 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -208,6 +208,7 @@ struct prueth_pdata {
  * @icssg_hwcmdseq: seq counter or HWQ messages
  * @emacs_initialized: num of EMACs/ext ports that are up/running
  * @iep0: pointer to IEP0 device
+ * @iep1: pointer to IEP1 device
  */
 struct prueth {
 	struct device *dev;
@@ -231,6 +232,7 @@ struct prueth {
 	u8 icssg_hwcmdseq;
 	int emacs_initialized;
 	struct icss_iep *iep0;
+	struct icss_iep *iep1;
 };
 
 struct emac_tx_ts_response {
-- 
GitLab


From 62b6442c58dc17b168f69b37b398a9cab7cd90c9 Mon Sep 17 00:00:00 2001
From: Dima Chumak <dchumak@nvidia.com>
Date: Thu, 24 Aug 2023 23:28:29 -0700
Subject: [PATCH 1736/1806] devlink: Expose port function commands to control
 IPsec crypto offloads

Expose port function commands to enable / disable IPsec crypto offloads,
this is used to control the port IPsec capabilities.

When IPsec crypto is disabled for a function of the port (default),
function cannot offload any IPsec crypto operations (Encrypt/Decrypt and
XFRM state offloading). When enabled, IPsec crypto operations can be
offloaded by the function of the port.

Example of a PCI VF port which supports IPsec crypto offloads:

$ devlink port show pci/0000:06:00.0/1
    pci/0000:06:00.0/1: type eth netdev enp6s0pf0vf0 flavour pcivf pfnum 0 vfnum 0
        function:
        hw_addr 00:00:00:00:00:00 roce enable ipsec_crypto disable

$ devlink port function set pci/0000:06:00.0/1 ipsec_crypto enable

$ devlink port show pci/0000:06:00.0/1
    pci/0000:06:00.0/1: type eth netdev enp6s0pf0vf0 flavour pcivf pfnum 0 vfnum 0
        function:
        hw_addr 00:00:00:00:00:00 roce enable ipsec_crypto enable

Signed-off-by: Dima Chumak <dchumak@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230825062836.103744-2-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../networking/devlink/devlink-port.rst       | 27 ++++++++++
 include/net/devlink.h                         | 15 ++++++
 include/uapi/linux/devlink.h                  |  2 +
 net/devlink/leftover.c                        | 52 +++++++++++++++++++
 4 files changed, 96 insertions(+)

diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
index 3da590953ce85..6983b11559cbc 100644
--- a/Documentation/networking/devlink/devlink-port.rst
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -128,6 +128,9 @@ Users may also set the RoCE capability of the function using
 Users may also set the function as migratable using
 'devlink port function set migratable' command.
 
+Users may also set the IPsec crypto capability of the function using
+`devlink port function set ipsec_crypto` command.
+
 Function attributes
 ===================
 
@@ -240,6 +243,30 @@ Attach VF to the VM.
 Start the VM.
 Perform live migration.
 
+IPsec crypto capability setup
+-----------------------------
+When user enables IPsec crypto capability for a VF, user application can offload
+XFRM state crypto operation (Encrypt/Decrypt) to this VF.
+
+When IPsec crypto capability is disabled (default) for a VF, the XFRM state is
+processed in software by the kernel.
+
+- Get IPsec crypto capability of the VF device::
+
+    $ devlink port show pci/0000:06:00.0/2
+    pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1
+        function:
+            hw_addr 00:00:00:00:00:00 ipsec_crypto disabled
+
+- Set IPsec crypto capability of the VF device::
+
+    $ devlink port function set pci/0000:06:00.0/2 ipsec_crypto enable
+
+    $ devlink port show pci/0000:06:00.0/2
+    pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1
+        function:
+            hw_addr 00:00:00:00:00:00 ipsec_crypto enabled
+
 Subfunction
 ============
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index f7fec0791acc2..1cf07a820a0e4 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1583,6 +1583,15 @@ void devlink_free(struct devlink *devlink);
  *		       Should be used by device drivers set
  *		       the admin state of a function managed
  *		       by the devlink port.
+ * @port_fn_ipsec_crypto_get: Callback used to get port function's ipsec_crypto
+ *			      capability. Should be used by device drivers
+ *			      to report the current state of ipsec_crypto
+ *			      capability of a function managed by the devlink
+ *			      port.
+ * @port_fn_ipsec_crypto_set: Callback used to set port function's ipsec_crypto
+ *			      capability. Should be used by device drivers to
+ *			      enable/disable ipsec_crypto capability of a
+ *			      function managed by the devlink port.
  *
  * Note: Driver should return -EOPNOTSUPP if it doesn't support
  * port function (@port_fn_*) handling for a particular port.
@@ -1620,6 +1629,12 @@ struct devlink_port_ops {
 	int (*port_fn_state_set)(struct devlink_port *port,
 				 enum devlink_port_fn_state state,
 				 struct netlink_ext_ack *extack);
+	int (*port_fn_ipsec_crypto_get)(struct devlink_port *devlink_port,
+					bool *is_enable,
+					struct netlink_ext_ack *extack);
+	int (*port_fn_ipsec_crypto_set)(struct devlink_port *devlink_port,
+					bool enable,
+					struct netlink_ext_ack *extack);
 };
 
 void devlink_port_init(struct devlink *devlink,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 3782d4219ac93..f9ae9a058ad25 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -661,6 +661,7 @@ enum devlink_resource_unit {
 enum devlink_port_fn_attr_cap {
 	DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT,
 	DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT,
+	DEVLINK_PORT_FN_ATTR_CAP_IPSEC_CRYPTO_BIT,
 
 	/* Add new caps above */
 	__DEVLINK_PORT_FN_ATTR_CAPS_MAX,
@@ -669,6 +670,7 @@ enum devlink_port_fn_attr_cap {
 #define DEVLINK_PORT_FN_CAP_ROCE _BITUL(DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT)
 #define DEVLINK_PORT_FN_CAP_MIGRATABLE \
 	_BITUL(DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT)
+#define DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO _BITUL(DEVLINK_PORT_FN_ATTR_CAP_IPSEC_CRYPTO_BIT)
 
 enum devlink_port_function_attr {
 	DEVLINK_PORT_FUNCTION_ATTR_UNSPEC,
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index e2cd13958cc27..fcc1a06cae48a 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -492,6 +492,28 @@ static int devlink_port_fn_migratable_fill(struct devlink_port *devlink_port,
 	return 0;
 }
 
+static int devlink_port_fn_ipsec_crypto_fill(struct devlink_port *devlink_port,
+					     struct nla_bitfield32 *caps,
+					     struct netlink_ext_ack *extack)
+{
+	bool is_enable;
+	int err;
+
+	if (!devlink_port->ops->port_fn_ipsec_crypto_get ||
+	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF)
+		return 0;
+
+	err = devlink_port->ops->port_fn_ipsec_crypto_get(devlink_port, &is_enable, extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, is_enable);
+	return 0;
+}
+
 static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port,
 				     struct sk_buff *msg,
 				     struct netlink_ext_ack *extack,
@@ -508,6 +530,10 @@ static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port,
 	if (err)
 		return err;
 
+	err = devlink_port_fn_ipsec_crypto_fill(devlink_port, &caps, extack);
+	if (err)
+		return err;
+
 	if (!caps.selector)
 		return 0;
 	err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value,
@@ -838,6 +864,13 @@ devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable,
 						   extack);
 }
 
+static int
+devlink_port_fn_ipsec_crypto_set(struct devlink_port *devlink_port, bool enable,
+				 struct netlink_ext_ack *extack)
+{
+	return devlink_port->ops->port_fn_ipsec_crypto_set(devlink_port, enable, extack);
+}
+
 static int devlink_port_fn_caps_set(struct devlink_port *devlink_port,
 				    const struct nlattr *attr,
 				    struct netlink_ext_ack *extack)
@@ -862,6 +895,13 @@ static int devlink_port_fn_caps_set(struct devlink_port *devlink_port,
 		if (err)
 			return err;
 	}
+	if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) {
+		err = devlink_port_fn_ipsec_crypto_set(devlink_port, caps_value &
+						       DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO,
+						       extack);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -1226,6 +1266,18 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port,
 				return -EOPNOTSUPP;
 			}
 		}
+		if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) {
+			if (!ops->port_fn_ipsec_crypto_set) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "Port doesn't support ipsec_crypto function attribute");
+				return -EOPNOTSUPP;
+			}
+			if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "ipsec_crypto function attribute supported for VFs only");
+				return -EOPNOTSUPP;
+			}
+		}
 	}
 	return 0;
 }
-- 
GitLab


From 390a24cbc39626a8a38c6d877a59f758fe209f2d Mon Sep 17 00:00:00 2001
From: Dima Chumak <dchumak@nvidia.com>
Date: Thu, 24 Aug 2023 23:28:30 -0700
Subject: [PATCH 1737/1806] devlink: Expose port function commands to control
 IPsec packet offloads

Expose port function commands to enable / disable IPsec packet offloads,
this is used to control the port IPsec capabilities.

When IPsec packet is disabled for a function of the port (default),
function cannot offload IPsec packet operations (encapsulation and XFRM
policy offload). When enabled, IPsec packet operations can be offloaded
by the function of the port, which includes crypto operation
(Encrypt/Decrypt), IPsec encapsulation and XFRM state and policy
offload.

Example of a PCI VF port which supports IPsec packet offloads:

$ devlink port show pci/0000:06:00.0/1
    pci/0000:06:00.0/1: type eth netdev enp6s0pf0vf0 flavour pcivf pfnum 0 vfnum 0
        function:
        hw_addr 00:00:00:00:00:00 roce enable ipsec_packet disable

$ devlink port function set pci/0000:06:00.0/1 ipsec_packet enable

$ devlink port show pci/0000:06:00.0/1
    pci/0000:06:00.0/1: type eth netdev enp6s0pf0vf0 flavour pcivf pfnum 0 vfnum 0
        function:
        hw_addr 00:00:00:00:00:00 roce enable ipsec_packet enable

Signed-off-by: Dima Chumak <dchumak@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230825062836.103744-3-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../networking/devlink/devlink-port.rst       | 28 ++++++++++
 include/net/devlink.h                         | 15 ++++++
 include/uapi/linux/devlink.h                  |  2 +
 net/devlink/leftover.c                        | 52 +++++++++++++++++++
 4 files changed, 97 insertions(+)

diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
index 6983b11559cbc..f5adb910427a8 100644
--- a/Documentation/networking/devlink/devlink-port.rst
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -131,6 +131,9 @@ Users may also set the function as migratable using
 Users may also set the IPsec crypto capability of the function using
 `devlink port function set ipsec_crypto` command.
 
+Users may also set the IPsec packet capability of the function using
+`devlink port function set ipsec_packet` command.
+
 Function attributes
 ===================
 
@@ -267,6 +270,31 @@ processed in software by the kernel.
         function:
             hw_addr 00:00:00:00:00:00 ipsec_crypto enabled
 
+IPsec packet capability setup
+-----------------------------
+When user enables IPsec packet capability for a VF, user application can offload
+XFRM state and policy crypto operation (Encrypt/Decrypt) to this VF, as well as
+IPsec encapsulation.
+
+When IPsec packet capability is disabled (default) for a VF, the XFRM state and
+policy is processed in software by the kernel.
+
+- Get IPsec packet capability of the VF device::
+
+    $ devlink port show pci/0000:06:00.0/2
+    pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1
+        function:
+            hw_addr 00:00:00:00:00:00 ipsec_packet disabled
+
+- Set IPsec packet capability of the VF device::
+
+    $ devlink port function set pci/0000:06:00.0/2 ipsec_packet enable
+
+    $ devlink port show pci/0000:06:00.0/2
+    pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1
+        function:
+            hw_addr 00:00:00:00:00:00 ipsec_packet enabled
+
 Subfunction
 ============
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 1cf07a820a0e4..29fd1b4ee6548 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1592,6 +1592,15 @@ void devlink_free(struct devlink *devlink);
  *			      capability. Should be used by device drivers to
  *			      enable/disable ipsec_crypto capability of a
  *			      function managed by the devlink port.
+ * @port_fn_ipsec_packet_get: Callback used to get port function's ipsec_packet
+ *			      capability. Should be used by device drivers
+ *			      to report the current state of ipsec_packet
+ *			      capability of a function managed by the devlink
+ *			      port.
+ * @port_fn_ipsec_packet_set: Callback used to set port function's ipsec_packet
+ *			      capability. Should be used by device drivers to
+ *			      enable/disable ipsec_packet capability of a
+ *			      function managed by the devlink port.
  *
  * Note: Driver should return -EOPNOTSUPP if it doesn't support
  * port function (@port_fn_*) handling for a particular port.
@@ -1635,6 +1644,12 @@ struct devlink_port_ops {
 	int (*port_fn_ipsec_crypto_set)(struct devlink_port *devlink_port,
 					bool enable,
 					struct netlink_ext_ack *extack);
+	int (*port_fn_ipsec_packet_get)(struct devlink_port *devlink_port,
+					bool *is_enable,
+					struct netlink_ext_ack *extack);
+	int (*port_fn_ipsec_packet_set)(struct devlink_port *devlink_port,
+					bool enable,
+					struct netlink_ext_ack *extack);
 };
 
 void devlink_port_init(struct devlink *devlink,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index f9ae9a058ad25..03875e078be84 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -662,6 +662,7 @@ enum devlink_port_fn_attr_cap {
 	DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT,
 	DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT,
 	DEVLINK_PORT_FN_ATTR_CAP_IPSEC_CRYPTO_BIT,
+	DEVLINK_PORT_FN_ATTR_CAP_IPSEC_PACKET_BIT,
 
 	/* Add new caps above */
 	__DEVLINK_PORT_FN_ATTR_CAPS_MAX,
@@ -671,6 +672,7 @@ enum devlink_port_fn_attr_cap {
 #define DEVLINK_PORT_FN_CAP_MIGRATABLE \
 	_BITUL(DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT)
 #define DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO _BITUL(DEVLINK_PORT_FN_ATTR_CAP_IPSEC_CRYPTO_BIT)
+#define DEVLINK_PORT_FN_CAP_IPSEC_PACKET _BITUL(DEVLINK_PORT_FN_ATTR_CAP_IPSEC_PACKET_BIT)
 
 enum devlink_port_function_attr {
 	DEVLINK_PORT_FUNCTION_ATTR_UNSPEC,
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index fcc1a06cae48a..149752bc9f2df 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -514,6 +514,28 @@ static int devlink_port_fn_ipsec_crypto_fill(struct devlink_port *devlink_port,
 	return 0;
 }
 
+static int devlink_port_fn_ipsec_packet_fill(struct devlink_port *devlink_port,
+					     struct nla_bitfield32 *caps,
+					     struct netlink_ext_ack *extack)
+{
+	bool is_enable;
+	int err;
+
+	if (!devlink_port->ops->port_fn_ipsec_packet_get ||
+	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF)
+		return 0;
+
+	err = devlink_port->ops->port_fn_ipsec_packet_get(devlink_port, &is_enable, extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_PACKET, is_enable);
+	return 0;
+}
+
 static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port,
 				     struct sk_buff *msg,
 				     struct netlink_ext_ack *extack,
@@ -534,6 +556,10 @@ static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port,
 	if (err)
 		return err;
 
+	err = devlink_port_fn_ipsec_packet_fill(devlink_port, &caps, extack);
+	if (err)
+		return err;
+
 	if (!caps.selector)
 		return 0;
 	err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value,
@@ -871,6 +897,13 @@ devlink_port_fn_ipsec_crypto_set(struct devlink_port *devlink_port, bool enable,
 	return devlink_port->ops->port_fn_ipsec_crypto_set(devlink_port, enable, extack);
 }
 
+static int
+devlink_port_fn_ipsec_packet_set(struct devlink_port *devlink_port, bool enable,
+				 struct netlink_ext_ack *extack)
+{
+	return devlink_port->ops->port_fn_ipsec_packet_set(devlink_port, enable, extack);
+}
+
 static int devlink_port_fn_caps_set(struct devlink_port *devlink_port,
 				    const struct nlattr *attr,
 				    struct netlink_ext_ack *extack)
@@ -902,6 +935,13 @@ static int devlink_port_fn_caps_set(struct devlink_port *devlink_port,
 		if (err)
 			return err;
 	}
+	if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) {
+		err = devlink_port_fn_ipsec_packet_set(devlink_port, caps_value &
+						       DEVLINK_PORT_FN_CAP_IPSEC_PACKET,
+						       extack);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -1278,6 +1318,18 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port,
 				return -EOPNOTSUPP;
 			}
 		}
+		if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) {
+			if (!ops->port_fn_ipsec_packet_set) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "Port doesn't support ipsec_packet function attribute");
+				return -EOPNOTSUPP;
+			}
+			if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "ipsec_packet function attribute supported for VFs only");
+				return -EOPNOTSUPP;
+			}
+		}
 	}
 	return 0;
 }
-- 
GitLab


From c46fb77383a6d5eea723c785135e79d73614f1c3 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Thu, 24 Aug 2023 23:28:31 -0700
Subject: [PATCH 1738/1806] net/mlx5: Drop extra layer of locks in IPsec

There is no need in holding devlink lock as it gives nothing
compared to already used write mode_lock.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20230825062836.103744-4-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/eswitch_offloads.c      | 18 ++++--------------
 1 file changed, 4 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 67eab99f95b18..28c4b9724e389 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3903,38 +3903,28 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 
 bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev)
 {
-	struct devlink *devlink = priv_to_devlink(dev);
-	struct mlx5_eswitch *esw;
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
 
-	devl_lock(devlink);
-	esw = mlx5_devlink_eswitch_get(devlink);
-	if (IS_ERR(esw)) {
-		devl_unlock(devlink);
-		/* Failure means no eswitch => not possible to change encap */
+	if (!mlx5_esw_allowed(esw))
 		return true;
-	}
 
 	down_write(&esw->mode_lock);
 	if (esw->mode != MLX5_ESWITCH_LEGACY &&
 	    esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) {
 		up_write(&esw->mode_lock);
-		devl_unlock(devlink);
 		return false;
 	}
 
 	esw->offloads.num_block_encap++;
 	up_write(&esw->mode_lock);
-	devl_unlock(devlink);
 	return true;
 }
 
 void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev)
 {
-	struct devlink *devlink = priv_to_devlink(dev);
-	struct mlx5_eswitch *esw;
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
 
-	esw = mlx5_devlink_eswitch_get(devlink);
-	if (IS_ERR(esw))
+	if (!mlx5_esw_allowed(esw))
 		return;
 
 	down_write(&esw->mode_lock);
-- 
GitLab


From e2537341667830fa1e6dd51bc9dbf19c58954d35 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Thu, 24 Aug 2023 23:28:32 -0700
Subject: [PATCH 1739/1806] net/mlx5e: Rewrite IPsec vs. TC block interface

In the commit 366e46242b8e ("net/mlx5e: Make IPsec offload work together
with eswitch and TC"), new API to block IPsec vs. TC creation was introduced.

Internally, that API used devlink lock to avoid races with userspace, but it is
not really needed as dev->priv.eswitch is stable and can't be changed. So remove
dependency on devlink lock and move block encap code back to its original place.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20230825062836.103744-5-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 63 +++++++------------
 .../net/ethernet/mellanox/mlx5/core/eswitch.h | 15 ++---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 53 +++-------------
 3 files changed, 38 insertions(+), 93 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index a1cfddd05bc4b..7dba4221993f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -254,6 +254,8 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_del_flow_rules(rx->sa.rule);
 	mlx5_destroy_flow_group(rx->sa.group);
 	mlx5_destroy_flow_table(rx->ft.sa);
+	if (rx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(mdev);
 	if (rx == ipsec->rx_esw) {
 		mlx5_esw_ipsec_rx_status_destroy(ipsec, rx);
 	} else {
@@ -357,6 +359,8 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		goto err_add;
 
 	/* Create FT */
+	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
+		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (rx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 	ft = ipsec_ft_create(attr.ns, attr.sa_level, attr.prio, 2, flags);
@@ -411,6 +415,8 @@ err_pol_ft:
 err_fs:
 	mlx5_destroy_flow_table(rx->ft.sa);
 err_fs_ft:
+	if (rx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(mdev);
 	mlx5_del_flow_rules(rx->status.rule);
 	mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
 err_add:
@@ -428,26 +434,19 @@ static int rx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (rx->ft.refcnt)
 		goto skip;
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
-		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
-
-	err = mlx5_eswitch_block_mode_trylock(mdev);
+	err = mlx5_eswitch_block_mode(mdev);
 	if (err)
-		goto err_out;
+		return err;
 
 	err = rx_create(mdev, ipsec, rx, family);
-	mlx5_eswitch_block_mode_unlock(mdev, err);
-	if (err)
-		goto err_out;
+	if (err) {
+		mlx5_eswitch_unblock_mode(mdev);
+		return err;
+	}
 
 skip:
 	rx->ft.refcnt++;
 	return 0;
-
-err_out:
-	if (rx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
-	return err;
 }
 
 static void rx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx,
@@ -456,12 +455,8 @@ static void rx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx,
 	if (--rx->ft.refcnt)
 		return;
 
-	mlx5_eswitch_unblock_mode_lock(ipsec->mdev);
 	rx_destroy(ipsec->mdev, ipsec, rx, family);
-	mlx5_eswitch_unblock_mode_unlock(ipsec->mdev);
-
-	if (rx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(ipsec->mdev);
+	mlx5_eswitch_unblock_mode(ipsec->mdev);
 }
 
 static struct mlx5e_ipsec_rx *rx_ft_get(struct mlx5_core_dev *mdev,
@@ -581,6 +576,8 @@ static void tx_destroy(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		mlx5_destroy_flow_group(tx->sa.group);
 	}
 	mlx5_destroy_flow_table(tx->ft.sa);
+	if (tx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(ipsec->mdev);
 	mlx5_del_flow_rules(tx->status.rule);
 	mlx5_destroy_flow_table(tx->ft.status);
 }
@@ -621,6 +618,8 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 	if (err)
 		goto err_status_rule;
 
+	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
+		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (tx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 4, flags);
@@ -687,6 +686,8 @@ err_pol_ft:
 err_sa_miss:
 	mlx5_destroy_flow_table(tx->ft.sa);
 err_sa_ft:
+	if (tx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(mdev);
 	mlx5_del_flow_rules(tx->status.rule);
 err_status_rule:
 	mlx5_destroy_flow_table(tx->ft.status);
@@ -720,32 +721,22 @@ static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (tx->ft.refcnt)
 		goto skip;
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
-		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
-
-	err = mlx5_eswitch_block_mode_trylock(mdev);
+	err = mlx5_eswitch_block_mode(mdev);
 	if (err)
-		goto err_out;
+		return err;
 
 	err = tx_create(ipsec, tx, ipsec->roce);
 	if (err) {
-		mlx5_eswitch_block_mode_unlock(mdev, err);
-		goto err_out;
+		mlx5_eswitch_unblock_mode(mdev);
+		return err;
 	}
 
 	if (tx == ipsec->tx_esw)
 		ipsec_esw_tx_ft_policy_set(mdev, tx->ft.pol);
 
-	mlx5_eswitch_block_mode_unlock(mdev, err);
-
 skip:
 	tx->ft.refcnt++;
 	return 0;
-
-err_out:
-	if (tx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
-	return err;
 }
 
 static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
@@ -753,19 +744,13 @@ static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
 	if (--tx->ft.refcnt)
 		return;
 
-	mlx5_eswitch_unblock_mode_lock(ipsec->mdev);
-
 	if (tx == ipsec->tx_esw) {
 		mlx5_esw_ipsec_restore_dest_uplink(ipsec->mdev);
 		ipsec_esw_tx_ft_policy_set(ipsec->mdev, NULL);
 	}
 
 	tx_destroy(ipsec, tx, ipsec->roce);
-
-	mlx5_eswitch_unblock_mode_unlock(ipsec->mdev);
-
-	if (tx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(ipsec->mdev);
+	mlx5_eswitch_unblock_mode(ipsec->mdev);
 }
 
 static struct mlx5_flow_table *tx_ft_get_policy(struct mlx5_core_dev *mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 6fcece69d3bea..ed3abcd70c461 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -829,10 +829,8 @@ int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw);
 bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev);
 void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev);
 
-int mlx5_eswitch_block_mode_trylock(struct mlx5_core_dev *dev);
-void mlx5_eswitch_block_mode_unlock(struct mlx5_core_dev *dev, int err);
-void mlx5_eswitch_unblock_mode_lock(struct mlx5_core_dev *dev);
-void mlx5_eswitch_unblock_mode_unlock(struct mlx5_core_dev *dev);
+int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev);
+void mlx5_eswitch_unblock_mode(struct mlx5_core_dev *dev);
 
 static inline int mlx5_eswitch_num_vfs(struct mlx5_eswitch *esw)
 {
@@ -916,13 +914,8 @@ static inline void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev)
 {
 }
 
-static inline int mlx5_eswitch_block_mode_trylock(struct mlx5_core_dev *dev) { return 0; }
-
-static inline void mlx5_eswitch_block_mode_unlock(struct mlx5_core_dev *dev, int err) {}
-
-static inline void mlx5_eswitch_unblock_mode_lock(struct mlx5_core_dev *dev) {}
-
-static inline void mlx5_eswitch_unblock_mode_unlock(struct mlx5_core_dev *dev) {}
+static inline int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev) { return 0; }
+static inline void mlx5_eswitch_unblock_mode(struct mlx5_core_dev *dev) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif /* __MLX5_ESWITCH_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 28c4b9724e389..d4697dadd27d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3641,65 +3641,32 @@ static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink)
 	return net_eq(devl_net, netdev_net);
 }
 
-int mlx5_eswitch_block_mode_trylock(struct mlx5_core_dev *dev)
+int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev)
 {
-	struct devlink *devlink = priv_to_devlink(dev);
-	struct mlx5_eswitch *esw;
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
 	int err;
 
-	devl_lock(devlink);
-	esw = mlx5_devlink_eswitch_get(devlink);
-	if (IS_ERR(esw)) {
-		/* Failure means no eswitch => not possible to change eswitch mode */
-		devl_unlock(devlink);
+	if (!mlx5_esw_allowed(esw))
 		return 0;
-	}
 
+	/* Take TC into account */
 	err = mlx5_esw_try_lock(esw);
-	if (err < 0) {
-		devl_unlock(devlink);
+	if (err < 0)
 		return err;
-	}
-
-	return 0;
-}
-
-void mlx5_eswitch_block_mode_unlock(struct mlx5_core_dev *dev, int err)
-{
-	struct devlink *devlink = priv_to_devlink(dev);
-	struct mlx5_eswitch *esw;
-
-	esw = mlx5_devlink_eswitch_get(devlink);
-	if (IS_ERR(esw))
-		return;
 
-	if (!err)
-		esw->offloads.num_block_mode++;
+	esw->offloads.num_block_mode++;
 	mlx5_esw_unlock(esw);
-	devl_unlock(devlink);
+	return 0;
 }
 
-void mlx5_eswitch_unblock_mode_lock(struct mlx5_core_dev *dev)
+void mlx5_eswitch_unblock_mode(struct mlx5_core_dev *dev)
 {
-	struct devlink *devlink = priv_to_devlink(dev);
-	struct mlx5_eswitch *esw;
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
 
-	esw = mlx5_devlink_eswitch_get(devlink);
-	if (IS_ERR(esw))
+	if (!mlx5_esw_allowed(esw))
 		return;
 
 	down_write(&esw->mode_lock);
-}
-
-void mlx5_eswitch_unblock_mode_unlock(struct mlx5_core_dev *dev)
-{
-	struct devlink *devlink = priv_to_devlink(dev);
-	struct mlx5_eswitch *esw;
-
-	esw = mlx5_devlink_eswitch_get(devlink);
-	if (IS_ERR(esw))
-		return;
-
 	esw->offloads.num_block_mode--;
 	up_write(&esw->mode_lock);
 }
-- 
GitLab


From 17c8da5a3423c9f3800a256dbaa685bae18e1264 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Thu, 24 Aug 2023 23:28:33 -0700
Subject: [PATCH 1740/1806] net/mlx5: Add IFC bits to support IPsec
 enable/disable

Add hardware definitions to allow to control IPSec capabilities.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20230825062836.103744-6-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 08dcb1f43be72..fc3db401f8a28 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -65,9 +65,11 @@ enum {
 
 enum {
 	MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE        = 0x0,
+	MLX5_SET_HCA_CAP_OP_MOD_ETHERNET_OFFLOADS     = 0x1,
 	MLX5_SET_HCA_CAP_OP_MOD_ODP                   = 0x2,
 	MLX5_SET_HCA_CAP_OP_MOD_ATOMIC                = 0x3,
 	MLX5_SET_HCA_CAP_OP_MOD_ROCE                  = 0x4,
+	MLX5_SET_HCA_CAP_OP_MOD_IPSEC                 = 0x15,
 	MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2       = 0x20,
 	MLX5_SET_HCA_CAP_OP_MOD_PORT_SELECTION        = 0x25,
 };
@@ -3451,6 +3453,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap;
 	struct mlx5_ifc_macsec_cap_bits macsec_cap;
 	struct mlx5_ifc_crypto_cap_bits crypto_cap;
+	struct mlx5_ifc_ipsec_cap_bits ipsec_cap;
 	u8         reserved_at_0[0x8000];
 };
 
-- 
GitLab


From 8efd7b17a3b03242c97281d88463ad56e8f551f8 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Thu, 24 Aug 2023 23:28:34 -0700
Subject: [PATCH 1741/1806] net/mlx5: Provide an interface to block change of
 IPsec capabilities

mlx5 HW can't perform IPsec offload operation simultaneously both on PF
and VFs at the same time. While the previous patches added devlink knobs
to change IPsec capabilities dynamically, there is a need to add a logic
to block such IPsec capabilities for the cases when IPsec is already
configured.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20230825062836.103744-7-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec.c       | 20 +++++++++++-
 .../net/ethernet/mellanox/mlx5/core/eswitch.c | 32 +++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  9 ++++++
 include/linux/mlx5/driver.h                   |  1 +
 4 files changed, 61 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 3b88a8bb70822..7d4ceb9b9c16f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -38,6 +38,7 @@
 #include <net/netevent.h>
 
 #include "en.h"
+#include "eswitch.h"
 #include "ipsec.h"
 #include "ipsec_rxtx.h"
 #include "en_rep.h"
@@ -670,6 +671,11 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 	if (err)
 		goto err_xfrm;
 
+	if (!mlx5_eswitch_block_ipsec(priv->mdev)) {
+		err = -EBUSY;
+		goto err_xfrm;
+	}
+
 	/* check esn */
 	if (x->props.flags & XFRM_STATE_ESN)
 		mlx5e_ipsec_update_esn_state(sa_entry);
@@ -678,7 +684,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 
 	err = mlx5_ipsec_create_work(sa_entry);
 	if (err)
-		goto err_xfrm;
+		goto unblock_ipsec;
 
 	err = mlx5e_ipsec_create_dwork(sa_entry);
 	if (err)
@@ -735,6 +741,8 @@ release_work:
 	if (sa_entry->work)
 		kfree(sa_entry->work->data);
 	kfree(sa_entry->work);
+unblock_ipsec:
+	mlx5_eswitch_unblock_ipsec(priv->mdev);
 err_xfrm:
 	kfree(sa_entry);
 	NL_SET_ERR_MSG_WEAK_MOD(extack, "Device failed to offload this state");
@@ -764,6 +772,7 @@ static void mlx5e_xfrm_del_state(struct xfrm_state *x)
 static void mlx5e_xfrm_free_state(struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
 
 	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ)
 		goto sa_entry_free;
@@ -780,6 +789,7 @@ static void mlx5e_xfrm_free_state(struct xfrm_state *x)
 	if (sa_entry->work)
 		kfree(sa_entry->work->data);
 	kfree(sa_entry->work);
+	mlx5_eswitch_unblock_ipsec(ipsec->mdev);
 sa_entry_free:
 	kfree(sa_entry);
 }
@@ -1055,6 +1065,11 @@ static int mlx5e_xfrm_add_policy(struct xfrm_policy *x,
 	pol_entry->x = x;
 	pol_entry->ipsec = priv->ipsec;
 
+	if (!mlx5_eswitch_block_ipsec(priv->mdev)) {
+		err = -EBUSY;
+		goto ipsec_busy;
+	}
+
 	mlx5e_ipsec_build_accel_pol_attrs(pol_entry, &pol_entry->attrs);
 	err = mlx5e_accel_ipsec_fs_add_pol(pol_entry);
 	if (err)
@@ -1064,6 +1079,8 @@ static int mlx5e_xfrm_add_policy(struct xfrm_policy *x,
 	return 0;
 
 err_fs:
+	mlx5_eswitch_unblock_ipsec(priv->mdev);
+ipsec_busy:
 	kfree(pol_entry);
 	NL_SET_ERR_MSG_MOD(extack, "Device failed to offload this policy");
 	return err;
@@ -1074,6 +1091,7 @@ static void mlx5e_xfrm_del_policy(struct xfrm_policy *x)
 	struct mlx5e_ipsec_pol_entry *pol_entry = to_ipsec_pol_entry(x);
 
 	mlx5e_accel_ipsec_fs_del_pol(pol_entry);
+	mlx5_eswitch_unblock_ipsec(pol_entry->ipsec->mdev);
 }
 
 static void mlx5e_xfrm_free_policy(struct xfrm_policy *x)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index db1c2a0763643..38a149dd479f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -48,6 +48,7 @@
 #include "devlink.h"
 #include "ecpf.h"
 #include "en/mod_hdr.h"
+#include "en_accel/ipsec.h"
 
 enum {
 	MLX5_ACTION_NONE = 0,
@@ -2336,3 +2337,34 @@ struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw)
 	return mlx5_esw_allowed(esw) ? esw->dev : NULL;
 }
 EXPORT_SYMBOL(mlx5_eswitch_get_core_dev);
+
+bool mlx5_eswitch_block_ipsec(struct mlx5_core_dev *dev)
+{
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+
+	if (!mlx5_esw_allowed(esw))
+		return true;
+
+	mutex_lock(&esw->state_lock);
+	if (esw->enabled_ipsec_vf_count) {
+		mutex_unlock(&esw->state_lock);
+		return false;
+	}
+
+	dev->num_ipsec_offloads++;
+	mutex_unlock(&esw->state_lock);
+	return true;
+}
+
+void mlx5_eswitch_unblock_ipsec(struct mlx5_core_dev *dev)
+{
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+
+	if (!mlx5_esw_allowed(esw))
+		/* Failure means no eswitch => core dev is not a PF */
+		return;
+
+	mutex_lock(&esw->state_lock);
+	dev->num_ipsec_offloads--;
+	mutex_unlock(&esw->state_lock);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index ed3abcd70c461..0e51fd066fcca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -380,6 +380,7 @@ struct mlx5_eswitch {
 	struct blocking_notifier_head n_head;
 	struct xarray paired;
 	struct mlx5_devcom_comp_dev *devcom;
+	u16 enabled_ipsec_vf_count;
 };
 
 void esw_offloads_disable(struct mlx5_eswitch *esw);
@@ -855,6 +856,8 @@ mlx5_eswitch_get_slow_fdb(struct mlx5_eswitch *esw)
 
 int mlx5_eswitch_restore_ipsec_rule(struct mlx5_eswitch *esw, struct mlx5_flow_handle *rule,
 				    struct mlx5_esw_flow_attr *esw_attr, int attr_idx);
+bool mlx5_eswitch_block_ipsec(struct mlx5_core_dev *dev);
+void mlx5_eswitch_unblock_ipsec(struct mlx5_core_dev *dev);
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
@@ -916,6 +919,12 @@ static inline void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev)
 
 static inline int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_eswitch_unblock_mode(struct mlx5_core_dev *dev) {}
+static inline bool mlx5_eswitch_block_ipsec(struct mlx5_core_dev *dev)
+{
+	return false;
+}
+
+static inline void mlx5_eswitch_unblock_ipsec(struct mlx5_core_dev *dev) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif /* __MLX5_ESWITCH_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e95f10066eac3..3033bbaeac81c 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -813,6 +813,7 @@ struct mlx5_core_dev {
 	/* MACsec notifier chain to sync MACsec core and IB database */
 	struct blocking_notifier_head macsec_nh;
 #endif
+	u64 num_ipsec_offloads;
 };
 
 struct mlx5_db {
-- 
GitLab


From 06bab69658a8afb493204448f29703e12e6d3960 Mon Sep 17 00:00:00 2001
From: Dima Chumak <dchumak@nvidia.com>
Date: Thu, 24 Aug 2023 23:28:35 -0700
Subject: [PATCH 1742/1806] net/mlx5: Implement devlink port function cmds to
 control ipsec_crypto

Implement devlink port function commands to enable / disable IPsec
crypto offloads.  This is used to control the IPsec capability of the
device.

When ipsec_crypto is enabled for a VF, it prevents adding IPsec crypto
offloads on the PF, because the two cannot be active simultaneously due
to HW constraints. Conversely, if there are any active IPsec crypto
offloads on the PF, it's not allowed to enable ipsec_crypto on a VF,
until PF IPsec offloads are cleared.

Signed-off-by: Dima Chumak <dchumak@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20230825062836.103744-8-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/switchdev.rst      |  10 +
 .../net/ethernet/mellanox/mlx5/core/Makefile  |   2 +-
 .../mellanox/mlx5/core/esw/devlink_port.c     |   4 +
 .../ethernet/mellanox/mlx5/core/esw/ipsec.c   | 309 ++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/eswitch.c |   8 +
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  14 +
 .../mellanox/mlx5/core/eswitch_offloads.c     |  85 +++++
 7 files changed, 431 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst
index 6e3f5ee8b0d01..de51e55dcfe33 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst
@@ -190,6 +190,16 @@ explicitly enable the VF migratable capability.
 mlx5 driver support devlink port function attr mechanism to setup migratable
 capability. (refer to Documentation/networking/devlink/devlink-port.rst)
 
+IPsec crypto capability setup
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+User who wants mlx5 PCI VFs to be able to perform IPsec crypto offloading need
+to explicitly enable the VF ipsec_crypto capability. Enabling IPsec capability
+for VFs is supported starting with ConnectX6dx devices and above. When a VF has
+IPsec capability enabled, any IPsec offloading is blocked on the PF.
+
+mlx5 driver support devlink port function attr mechanism to setup ipsec_crypto
+capability. (refer to Documentation/networking/devlink/devlink-port.rst)
+
 SF state setup
 --------------
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index b56b187a9097b..7e94caca48886 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -69,7 +69,7 @@ mlx5_core-$(CONFIG_MLX5_TC_SAMPLE)   += en/tc/sample.o
 #
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \
 				      ecpf.o rdma.o esw/legacy.o \
-				      esw/devlink_port.o esw/vporttbl.o esw/qos.o
+				      esw/devlink_port.o esw/vporttbl.o esw/qos.o esw/ipsec.o
 
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/acl/helper.o \
 				      esw/acl/egress_lgcy.o esw/acl/egress_ofld.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 3c254a7100066..12205e913417b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -92,6 +92,10 @@ static const struct devlink_port_ops mlx5_esw_pf_vf_dl_port_ops = {
 	.port_fn_roce_set = mlx5_devlink_port_fn_roce_set,
 	.port_fn_migratable_get = mlx5_devlink_port_fn_migratable_get,
 	.port_fn_migratable_set = mlx5_devlink_port_fn_migratable_set,
+#ifdef CONFIG_XFRM_OFFLOAD
+	.port_fn_ipsec_crypto_get = mlx5_devlink_port_fn_ipsec_crypto_get,
+	.port_fn_ipsec_crypto_set = mlx5_devlink_port_fn_ipsec_crypto_set,
+#endif /* CONFIG_XFRM_OFFLOAD */
 };
 
 static void mlx5_esw_offloads_sf_devlink_port_attrs_set(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c
new file mode 100644
index 0000000000000..187fb5f2d0cb6
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c
@@ -0,0 +1,309 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+#include <linux/mlx5/device.h>
+#include <linux/mlx5/vport.h>
+#include "mlx5_core.h"
+#include "eswitch.h"
+
+static int esw_ipsec_vf_query_generic(struct mlx5_core_dev *dev, u16 vport_num, bool *result)
+{
+	int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *hca_cap, *query_cap;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, vhca_resource_manager))
+		return -EOPNOTSUPP;
+
+	if (!mlx5_esw_ipsec_vf_offload_supported(dev)) {
+		*result = false;
+		return 0;
+	}
+
+	query_cap = kvzalloc(query_sz, GFP_KERNEL);
+	if (!query_cap)
+		return -ENOMEM;
+
+	err = mlx5_vport_get_other_func_general_cap(dev, vport_num, query_cap);
+	if (err)
+		goto free;
+
+	hca_cap = MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability);
+	*result = MLX5_GET(cmd_hca_cap, hca_cap, ipsec_offload);
+free:
+	kvfree(query_cap);
+	return err;
+}
+
+enum esw_vport_ipsec_offload {
+	MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD,
+};
+
+int mlx5_esw_ipsec_vf_offload_get(struct mlx5_core_dev *dev, struct mlx5_vport *vport)
+{
+	int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *hca_cap, *query_cap;
+	bool ipsec_enabled;
+	int err;
+
+	/* Querying IPsec caps only makes sense when generic ipsec_offload
+	 * HCA cap is enabled
+	 */
+	err = esw_ipsec_vf_query_generic(dev, vport->vport, &ipsec_enabled);
+	if (err)
+		return err;
+
+	if (!ipsec_enabled) {
+		vport->info.ipsec_crypto_enabled = false;
+		return 0;
+	}
+
+	query_cap = kvzalloc(query_sz, GFP_KERNEL);
+	if (!query_cap)
+		return -ENOMEM;
+
+	err = mlx5_vport_get_other_func_cap(dev, vport->vport, query_cap, MLX5_CAP_IPSEC);
+	if (err)
+		goto free;
+
+	hca_cap = MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability);
+	vport->info.ipsec_crypto_enabled =
+		MLX5_GET(ipsec_cap, hca_cap, ipsec_crypto_offload);
+free:
+	kvfree(query_cap);
+	return err;
+}
+
+static int esw_ipsec_vf_set_generic(struct mlx5_core_dev *dev, u16 vport_num, bool ipsec_ofld)
+{
+	int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	void *hca_cap, *query_cap, *cap;
+	int ret;
+
+	if (!MLX5_CAP_GEN(dev, vhca_resource_manager))
+		return -EOPNOTSUPP;
+
+	query_cap = kvzalloc(query_sz, GFP_KERNEL);
+	hca_cap = kvzalloc(set_sz, GFP_KERNEL);
+	if (!hca_cap || !query_cap) {
+		ret = -ENOMEM;
+		goto free;
+	}
+
+	ret = mlx5_vport_get_other_func_general_cap(dev, vport_num, query_cap);
+	if (ret)
+		goto free;
+
+	cap = MLX5_ADDR_OF(set_hca_cap_in, hca_cap, capability);
+	memcpy(cap, MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability),
+	       MLX5_UN_SZ_BYTES(hca_cap_union));
+	MLX5_SET(cmd_hca_cap, cap, ipsec_offload, ipsec_ofld);
+
+	MLX5_SET(set_hca_cap_in, hca_cap, opcode, MLX5_CMD_OP_SET_HCA_CAP);
+	MLX5_SET(set_hca_cap_in, hca_cap, other_function, 1);
+	MLX5_SET(set_hca_cap_in, hca_cap, function_id, vport_num);
+
+	MLX5_SET(set_hca_cap_in, hca_cap, op_mod,
+		 MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1);
+	ret = mlx5_cmd_exec_in(dev, set_hca_cap, hca_cap);
+free:
+	kvfree(hca_cap);
+	kvfree(query_cap);
+	return ret;
+}
+
+static int esw_ipsec_vf_set_bytype(struct mlx5_core_dev *dev, struct mlx5_vport *vport,
+				   bool enable, enum esw_vport_ipsec_offload type)
+{
+	int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	void *hca_cap, *query_cap, *cap;
+	int ret;
+
+	if (!MLX5_CAP_GEN(dev, vhca_resource_manager))
+		return -EOPNOTSUPP;
+
+	query_cap = kvzalloc(query_sz, GFP_KERNEL);
+	hca_cap = kvzalloc(set_sz, GFP_KERNEL);
+	if (!hca_cap || !query_cap) {
+		ret = -ENOMEM;
+		goto free;
+	}
+
+	ret = mlx5_vport_get_other_func_cap(dev, vport->vport, query_cap, MLX5_CAP_IPSEC);
+	if (ret)
+		goto free;
+
+	cap = MLX5_ADDR_OF(set_hca_cap_in, hca_cap, capability);
+	memcpy(cap, MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability),
+	       MLX5_UN_SZ_BYTES(hca_cap_union));
+
+	switch (type) {
+	case MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD:
+		MLX5_SET(ipsec_cap, cap, ipsec_crypto_offload, enable);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		goto free;
+	}
+
+	MLX5_SET(set_hca_cap_in, hca_cap, opcode, MLX5_CMD_OP_SET_HCA_CAP);
+	MLX5_SET(set_hca_cap_in, hca_cap, other_function, 1);
+	MLX5_SET(set_hca_cap_in, hca_cap, function_id, vport->vport);
+
+	MLX5_SET(set_hca_cap_in, hca_cap, op_mod,
+		 MLX5_SET_HCA_CAP_OP_MOD_IPSEC << 1);
+	ret = mlx5_cmd_exec_in(dev, set_hca_cap, hca_cap);
+free:
+	kvfree(hca_cap);
+	kvfree(query_cap);
+	return ret;
+}
+
+static int esw_ipsec_vf_crypto_aux_caps_set(struct mlx5_core_dev *dev, u16 vport_num, bool enable)
+{
+	int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	void *hca_cap, *query_cap, *cap;
+	int ret;
+
+	query_cap = kvzalloc(query_sz, GFP_KERNEL);
+	hca_cap = kvzalloc(set_sz, GFP_KERNEL);
+	if (!hca_cap || !query_cap) {
+		ret = -ENOMEM;
+		goto free;
+	}
+
+	ret = mlx5_vport_get_other_func_cap(dev, vport_num, query_cap, MLX5_CAP_ETHERNET_OFFLOADS);
+	if (ret)
+		goto free;
+
+	cap = MLX5_ADDR_OF(set_hca_cap_in, hca_cap, capability);
+	memcpy(cap, MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability),
+	       MLX5_UN_SZ_BYTES(hca_cap_union));
+	MLX5_SET(per_protocol_networking_offload_caps, cap, insert_trailer, enable);
+	MLX5_SET(set_hca_cap_in, hca_cap, opcode, MLX5_CMD_OP_SET_HCA_CAP);
+	MLX5_SET(set_hca_cap_in, hca_cap, other_function, 1);
+	MLX5_SET(set_hca_cap_in, hca_cap, function_id, vport_num);
+	MLX5_SET(set_hca_cap_in, hca_cap, op_mod,
+		 MLX5_SET_HCA_CAP_OP_MOD_ETHERNET_OFFLOADS << 1);
+	ret = mlx5_cmd_exec_in(esw->dev, set_hca_cap, hca_cap);
+free:
+	kvfree(hca_cap);
+	kvfree(query_cap);
+	return ret;
+}
+
+static int esw_ipsec_vf_offload_set_bytype(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+					   bool enable, enum esw_vport_ipsec_offload type)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	int err;
+
+	if (vport->vport == MLX5_VPORT_PF)
+		return -EOPNOTSUPP;
+
+	if (type == MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD) {
+		err = esw_ipsec_vf_crypto_aux_caps_set(dev, vport->vport, enable);
+		if (err)
+			return err;
+	}
+
+	if (enable) {
+		err = esw_ipsec_vf_set_generic(dev, vport->vport, enable);
+		if (err)
+			return err;
+		err = esw_ipsec_vf_set_bytype(dev, vport, enable, type);
+		if (err)
+			return err;
+	} else {
+		err = esw_ipsec_vf_set_bytype(dev, vport, enable, type);
+		if (err)
+			return err;
+		err = esw_ipsec_vf_set_generic(dev, vport->vport, enable);
+		if (err)
+			return err;
+	}
+
+	switch (type) {
+	case MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD:
+		vport->info.ipsec_crypto_enabled = enable;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int esw_ipsec_offload_supported(struct mlx5_core_dev *dev, u16 vport_num)
+{
+	int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *hca_cap, *query_cap;
+	int ret;
+
+	query_cap = kvzalloc(query_sz, GFP_KERNEL);
+	if (!query_cap)
+		return -ENOMEM;
+
+	ret = mlx5_vport_get_other_func_cap(dev, vport_num, query_cap, MLX5_CAP_GENERAL);
+	if (ret)
+		goto free;
+
+	hca_cap = MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability);
+	if (!MLX5_GET(cmd_hca_cap, hca_cap, log_max_dek))
+		ret = -EOPNOTSUPP;
+free:
+	kvfree(query_cap);
+	return ret;
+}
+
+bool mlx5_esw_ipsec_vf_offload_supported(struct mlx5_core_dev *dev)
+{
+	/* Old firmware doesn't support ipsec_offload capability for VFs. This
+	 * can be detected by checking reformat_add_esp_trasport capability -
+	 * when this cap isn't supported it means firmware cannot be trusted
+	 * about what it reports for ipsec_offload cap.
+	 */
+	return MLX5_CAP_FLOWTABLE_NIC_TX(dev, reformat_add_esp_trasport);
+}
+
+int mlx5_esw_ipsec_vf_crypto_offload_supported(struct mlx5_core_dev *dev,
+					       u16 vport_num)
+{
+	int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *hca_cap, *query_cap;
+	int err;
+
+	if (!mlx5_esw_ipsec_vf_offload_supported(dev))
+		return -EOPNOTSUPP;
+
+	err = esw_ipsec_offload_supported(dev, vport_num);
+	if (err)
+		return err;
+
+	query_cap = kvzalloc(query_sz, GFP_KERNEL);
+	if (!query_cap)
+		return -ENOMEM;
+
+	err = mlx5_vport_get_other_func_cap(dev, vport_num, query_cap, MLX5_CAP_ETHERNET_OFFLOADS);
+	if (err)
+		goto free;
+
+	hca_cap = MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability);
+	if (!MLX5_GET(per_protocol_networking_offload_caps, hca_cap, swp))
+		goto free;
+
+free:
+	kvfree(query_cap);
+	return err;
+}
+
+int mlx5_esw_ipsec_vf_crypto_offload_set(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+					 bool enable)
+{
+	return esw_ipsec_vf_offload_set_bytype(esw, vport, enable,
+					       MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 38a149dd479f9..79ae6ad94f556 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -832,6 +832,9 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *
 
 	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
 	vport->info.mig_enabled = MLX5_GET(cmd_hca_cap_2, hca_caps, migratable);
+
+	err = mlx5_esw_ipsec_vf_offload_get(esw->dev, vport);
+
 out_free:
 	kfree(query_ctx);
 	return err;
@@ -914,6 +917,8 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 	/* Sync with current vport context */
 	vport->enabled_events = enabled_events;
 	vport->enabled = true;
+	if (vport->vport != MLX5_VPORT_PF && vport->info.ipsec_crypto_enabled)
+		esw->enabled_ipsec_vf_count++;
 
 	/* Esw manager is trusted by default. Host PF (vport 0) is trusted as well
 	 * in smartNIC as it's a vport group manager.
@@ -970,6 +975,9 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 	    MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
 		mlx5_esw_vport_vhca_id_clear(esw, vport_num);
 
+	if (vport->vport != MLX5_VPORT_PF && vport->info.ipsec_crypto_enabled)
+		esw->enabled_ipsec_vf_count--;
+
 	/* We don't assume VFs will cleanup after themselves.
 	 * Calling vport change handler while vport is disabled will cleanup
 	 * the vport resources.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 0e51fd066fcca..cde5712aa6977 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -163,6 +163,7 @@ struct mlx5_vport_info {
 	u8                      trusted: 1;
 	u8                      roce_enabled: 1;
 	u8                      mig_enabled: 1;
+	u8                      ipsec_crypto_enabled: 1;
 };
 
 /* Vport context events */
@@ -559,6 +560,12 @@ int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enab
 					struct netlink_ext_ack *extack);
 int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
 					struct netlink_ext_ack *extack);
+#ifdef CONFIG_XFRM_OFFLOAD
+int mlx5_devlink_port_fn_ipsec_crypto_get(struct devlink_port *port, bool *is_enabled,
+					  struct netlink_ext_ack *extack);
+int mlx5_devlink_port_fn_ipsec_crypto_set(struct devlink_port *port, bool enable,
+					  struct netlink_ext_ack *extack);
+#endif /* CONFIG_XFRM_OFFLOAD */
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type);
 
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
@@ -858,6 +865,13 @@ int mlx5_eswitch_restore_ipsec_rule(struct mlx5_eswitch *esw, struct mlx5_flow_h
 				    struct mlx5_esw_flow_attr *esw_attr, int attr_idx);
 bool mlx5_eswitch_block_ipsec(struct mlx5_core_dev *dev);
 void mlx5_eswitch_unblock_ipsec(struct mlx5_core_dev *dev);
+bool mlx5_esw_ipsec_vf_offload_supported(struct mlx5_core_dev *dev);
+int mlx5_esw_ipsec_vf_offload_get(struct mlx5_core_dev *dev,
+				  struct mlx5_vport *vport);
+int mlx5_esw_ipsec_vf_crypto_offload_supported(struct mlx5_core_dev *dev,
+					       u16 vport_num);
+int mlx5_esw_ipsec_vf_crypto_offload_set(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+					 bool enable);
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index d4697dadd27d3..f37d30a096c01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4367,3 +4367,88 @@ mlx5_eswitch_restore_ipsec_rule(struct mlx5_eswitch *esw, struct mlx5_flow_handl
 
 	return mlx5_modify_rule_destination(rule, &new_dest, &old_dest);
 }
+
+#ifdef CONFIG_XFRM_OFFLOAD
+int mlx5_devlink_port_fn_ipsec_crypto_get(struct devlink_port *port, bool *is_enabled,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	int err = 0;
+
+	esw = mlx5_devlink_eswitch_get(port->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	if (!mlx5_esw_ipsec_vf_offload_supported(esw->dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support IPSec crypto");
+		return -EOPNOTSUPP;
+	}
+
+	vport = mlx5_devlink_port_vport_get(port);
+
+	mutex_lock(&esw->state_lock);
+	if (!vport->enabled) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	*is_enabled = vport->info.ipsec_crypto_enabled;
+unlock:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_devlink_port_fn_ipsec_crypto_set(struct devlink_port *port, bool enable,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	u16 vport_num;
+	int err;
+
+	esw = mlx5_devlink_eswitch_get(port->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
+	err = mlx5_esw_ipsec_vf_crypto_offload_supported(esw->dev, vport_num);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Device doesn't support IPsec crypto");
+		return err;
+	}
+
+	vport = mlx5_devlink_port_vport_get(port);
+
+	mutex_lock(&esw->state_lock);
+	if (!vport->enabled) {
+		err = -EOPNOTSUPP;
+		NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
+		goto unlock;
+	}
+
+	if (vport->info.ipsec_crypto_enabled == enable)
+		goto unlock;
+
+	if (!esw->enabled_ipsec_vf_count && esw->dev->num_ipsec_offloads) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
+	err = mlx5_esw_ipsec_vf_crypto_offload_set(esw, vport, enable);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to set IPsec crypto");
+		goto unlock;
+	}
+
+	vport->info.ipsec_crypto_enabled = enable;
+	if (enable)
+		esw->enabled_ipsec_vf_count++;
+	else
+		esw->enabled_ipsec_vf_count--;
+unlock:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+#endif /* CONFIG_XFRM_OFFLOAD */
-- 
GitLab


From b691b1116e820450de8a5d50eb4ce546a7de93dc Mon Sep 17 00:00:00 2001
From: Dima Chumak <dchumak@nvidia.com>
Date: Thu, 24 Aug 2023 23:28:36 -0700
Subject: [PATCH 1743/1806] net/mlx5: Implement devlink port function cmds to
 control ipsec_packet

Implement devlink port function commands to enable / disable IPsec
packet offloads. This is used to control the IPsec capability of the
device.

When ipsec_offload is enabled for a VF, it prevents adding IPsec packet
offloads on the PF, because the two cannot be active simultaneously due
to HW constraints. Conversely, if there are any active IPsec packet
offloads on the PF, it's not allowed to enable ipsec_packet on a VF,
until PF IPsec offloads are cleared.

Signed-off-by: Dima Chumak <dchumak@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20230825062836.103744-9-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/switchdev.rst      | 10 +++
 .../mellanox/mlx5/core/esw/devlink_port.c     |  2 +
 .../ethernet/mellanox/mlx5/core/esw/ipsec.c   | 62 +++++++++++++-
 .../net/ethernet/mellanox/mlx5/core/eswitch.c |  7 +-
 .../net/ethernet/mellanox/mlx5/core/eswitch.h | 12 +++
 .../mellanox/mlx5/core/eswitch_offloads.c     | 84 +++++++++++++++++++
 6 files changed, 173 insertions(+), 4 deletions(-)

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst
index de51e55dcfe33..b617e93d7c2c3 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst
@@ -200,6 +200,16 @@ IPsec capability enabled, any IPsec offloading is blocked on the PF.
 mlx5 driver support devlink port function attr mechanism to setup ipsec_crypto
 capability. (refer to Documentation/networking/devlink/devlink-port.rst)
 
+IPsec packet capability setup
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+User who wants mlx5 PCI VFs to be able to perform IPsec packet offloading need
+to explicitly enable the VF ipsec_packet capability. Enabling IPsec capability
+for VFs is supported starting with ConnectX6dx devices and above. When a VF has
+IPsec capability enabled, any IPsec offloading is blocked on the PF.
+
+mlx5 driver support devlink port function attr mechanism to setup ipsec_packet
+capability. (refer to Documentation/networking/devlink/devlink-port.rst)
+
 SF state setup
 --------------
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 12205e913417b..d8e739cbcbced 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -95,6 +95,8 @@ static const struct devlink_port_ops mlx5_esw_pf_vf_dl_port_ops = {
 #ifdef CONFIG_XFRM_OFFLOAD
 	.port_fn_ipsec_crypto_get = mlx5_devlink_port_fn_ipsec_crypto_get,
 	.port_fn_ipsec_crypto_set = mlx5_devlink_port_fn_ipsec_crypto_set,
+	.port_fn_ipsec_packet_get = mlx5_devlink_port_fn_ipsec_packet_get,
+	.port_fn_ipsec_packet_set = mlx5_devlink_port_fn_ipsec_packet_set,
 #endif /* CONFIG_XFRM_OFFLOAD */
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c
index 187fb5f2d0cb6..da10e04777cf7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c
@@ -37,6 +37,7 @@ free:
 
 enum esw_vport_ipsec_offload {
 	MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD,
+	MLX5_ESW_VPORT_IPSEC_PACKET_OFFLOAD,
 };
 
 int mlx5_esw_ipsec_vf_offload_get(struct mlx5_core_dev *dev, struct mlx5_vport *vport)
@@ -55,6 +56,7 @@ int mlx5_esw_ipsec_vf_offload_get(struct mlx5_core_dev *dev, struct mlx5_vport *
 
 	if (!ipsec_enabled) {
 		vport->info.ipsec_crypto_enabled = false;
+		vport->info.ipsec_packet_enabled = false;
 		return 0;
 	}
 
@@ -69,6 +71,8 @@ int mlx5_esw_ipsec_vf_offload_get(struct mlx5_core_dev *dev, struct mlx5_vport *
 	hca_cap = MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability);
 	vport->info.ipsec_crypto_enabled =
 		MLX5_GET(ipsec_cap, hca_cap, ipsec_crypto_offload);
+	vport->info.ipsec_packet_enabled =
+		MLX5_GET(ipsec_cap, hca_cap, ipsec_full_offload);
 free:
 	kvfree(query_cap);
 	return err;
@@ -143,6 +147,9 @@ static int esw_ipsec_vf_set_bytype(struct mlx5_core_dev *dev, struct mlx5_vport
 	case MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD:
 		MLX5_SET(ipsec_cap, cap, ipsec_crypto_offload, enable);
 		break;
+	case MLX5_ESW_VPORT_IPSEC_PACKET_OFFLOAD:
+		MLX5_SET(ipsec_cap, cap, ipsec_full_offload, enable);
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		goto free;
@@ -222,15 +229,28 @@ static int esw_ipsec_vf_offload_set_bytype(struct mlx5_eswitch *esw, struct mlx5
 		err = esw_ipsec_vf_set_bytype(dev, vport, enable, type);
 		if (err)
 			return err;
-		err = esw_ipsec_vf_set_generic(dev, vport->vport, enable);
+		err = mlx5_esw_ipsec_vf_offload_get(dev, vport);
 		if (err)
 			return err;
+
+		/* The generic ipsec_offload cap can be disabled only if both
+		 * ipsec_crypto_offload and ipsec_full_offload aren't enabled.
+		 */
+		if (!vport->info.ipsec_crypto_enabled &&
+		    !vport->info.ipsec_packet_enabled) {
+			err = esw_ipsec_vf_set_generic(dev, vport->vport, enable);
+			if (err)
+				return err;
+		}
 	}
 
 	switch (type) {
 	case MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD:
 		vport->info.ipsec_crypto_enabled = enable;
 		break;
+	case MLX5_ESW_VPORT_IPSEC_PACKET_OFFLOAD:
+		vport->info.ipsec_packet_enabled = enable;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -301,9 +321,49 @@ free:
 	return err;
 }
 
+int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev,
+					       u16 vport_num)
+{
+	int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *hca_cap, *query_cap;
+	int ret;
+
+	if (!mlx5_esw_ipsec_vf_offload_supported(dev))
+		return -EOPNOTSUPP;
+
+	ret = esw_ipsec_offload_supported(dev, vport_num);
+	if (ret)
+		return ret;
+
+	query_cap = kvzalloc(query_sz, GFP_KERNEL);
+	if (!query_cap)
+		return -ENOMEM;
+
+	ret = mlx5_vport_get_other_func_cap(dev, vport_num, query_cap, MLX5_CAP_FLOW_TABLE);
+	if (ret)
+		goto out;
+
+	hca_cap = MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability);
+	if (!MLX5_GET(flow_table_nic_cap, hca_cap, flow_table_properties_nic_receive.decap)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+out:
+	kvfree(query_cap);
+	return ret;
+}
+
 int mlx5_esw_ipsec_vf_crypto_offload_set(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 					 bool enable)
 {
 	return esw_ipsec_vf_offload_set_bytype(esw, vport, enable,
 					       MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD);
 }
+
+int mlx5_esw_ipsec_vf_packet_offload_set(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+					 bool enable)
+{
+	return esw_ipsec_vf_offload_set_bytype(esw, vport, enable,
+					       MLX5_ESW_VPORT_IPSEC_PACKET_OFFLOAD);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 79ae6ad94f556..6cd7d6497e109 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -834,7 +834,6 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *
 	vport->info.mig_enabled = MLX5_GET(cmd_hca_cap_2, hca_caps, migratable);
 
 	err = mlx5_esw_ipsec_vf_offload_get(esw->dev, vport);
-
 out_free:
 	kfree(query_ctx);
 	return err;
@@ -917,7 +916,8 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 	/* Sync with current vport context */
 	vport->enabled_events = enabled_events;
 	vport->enabled = true;
-	if (vport->vport != MLX5_VPORT_PF && vport->info.ipsec_crypto_enabled)
+	if (vport->vport != MLX5_VPORT_PF &&
+	    (vport->info.ipsec_crypto_enabled || vport->info.ipsec_packet_enabled))
 		esw->enabled_ipsec_vf_count++;
 
 	/* Esw manager is trusted by default. Host PF (vport 0) is trusted as well
@@ -975,7 +975,8 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 	    MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
 		mlx5_esw_vport_vhca_id_clear(esw, vport_num);
 
-	if (vport->vport != MLX5_VPORT_PF && vport->info.ipsec_crypto_enabled)
+	if (vport->vport != MLX5_VPORT_PF &&
+	    (vport->info.ipsec_crypto_enabled || vport->info.ipsec_packet_enabled))
 		esw->enabled_ipsec_vf_count--;
 
 	/* We don't assume VFs will cleanup after themselves.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index cde5712aa6977..37ab66e7b403f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -164,6 +164,7 @@ struct mlx5_vport_info {
 	u8                      roce_enabled: 1;
 	u8                      mig_enabled: 1;
 	u8                      ipsec_crypto_enabled: 1;
+	u8                      ipsec_packet_enabled: 1;
 };
 
 /* Vport context events */
@@ -565,6 +566,10 @@ int mlx5_devlink_port_fn_ipsec_crypto_get(struct devlink_port *port, bool *is_en
 					  struct netlink_ext_ack *extack);
 int mlx5_devlink_port_fn_ipsec_crypto_set(struct devlink_port *port, bool enable,
 					  struct netlink_ext_ack *extack);
+int mlx5_devlink_port_fn_ipsec_packet_get(struct devlink_port *port, bool *is_enabled,
+					  struct netlink_ext_ack *extack);
+int mlx5_devlink_port_fn_ipsec_packet_set(struct devlink_port *port, bool enable,
+					  struct netlink_ext_ack *extack);
 #endif /* CONFIG_XFRM_OFFLOAD */
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type);
 
@@ -872,6 +877,13 @@ int mlx5_esw_ipsec_vf_crypto_offload_supported(struct mlx5_core_dev *dev,
 					       u16 vport_num);
 int mlx5_esw_ipsec_vf_crypto_offload_set(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 					 bool enable);
+int mlx5_esw_ipsec_vf_packet_offload_set(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+					 bool enable);
+int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev,
+					       u16 vport_num);
+void mlx5_esw_vport_ipsec_offload_enable(struct mlx5_eswitch *esw);
+void mlx5_esw_vport_ipsec_offload_disable(struct mlx5_eswitch *esw);
+
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f37d30a096c01..752fb0dfb111b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4451,4 +4451,88 @@ unlock:
 	mutex_unlock(&esw->state_lock);
 	return err;
 }
+
+int mlx5_devlink_port_fn_ipsec_packet_get(struct devlink_port *port, bool *is_enabled,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	int err = 0;
+
+	esw = mlx5_devlink_eswitch_get(port->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	if (!mlx5_esw_ipsec_vf_offload_supported(esw->dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support IPsec packet");
+		return -EOPNOTSUPP;
+	}
+
+	vport = mlx5_devlink_port_vport_get(port);
+
+	mutex_lock(&esw->state_lock);
+	if (!vport->enabled) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	*is_enabled = vport->info.ipsec_packet_enabled;
+unlock:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_devlink_port_fn_ipsec_packet_set(struct devlink_port *port,
+					  bool enable,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	u16 vport_num;
+	int err;
+
+	esw = mlx5_devlink_eswitch_get(port->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
+	err = mlx5_esw_ipsec_vf_packet_offload_supported(esw->dev, vport_num);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Device doesn't support IPsec packet mode");
+		return err;
+	}
+
+	vport = mlx5_devlink_port_vport_get(port);
+	mutex_lock(&esw->state_lock);
+	if (!vport->enabled) {
+		err = -EOPNOTSUPP;
+		NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
+		goto unlock;
+	}
+
+	if (vport->info.ipsec_packet_enabled == enable)
+		goto unlock;
+
+	if (!esw->enabled_ipsec_vf_count && esw->dev->num_ipsec_offloads) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
+	err = mlx5_esw_ipsec_vf_packet_offload_set(esw, vport, enable);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to set IPsec packet mode");
+		goto unlock;
+	}
+
+	vport->info.ipsec_packet_enabled = enable;
+	if (enable)
+		esw->enabled_ipsec_vf_count++;
+	else
+		esw->enabled_ipsec_vf_count--;
+unlock:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
 #endif /* CONFIG_XFRM_OFFLOAD */
-- 
GitLab


From c4e1ab07b5572b9c732fcf7ac86e168ee2835adf Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:44 +0100
Subject: [PATCH 1744/1806] doc/netlink: Fix typo in genetlink-* schemas

Fix typo verion -> version in genetlink-c and genetlink-legacy.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-2-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/genetlink-c.yaml      | 2 +-
 Documentation/netlink/genetlink-legacy.yaml | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index 4c1f8c22627bb..9806c44f604c3 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -41,7 +41,7 @@ properties:
     description: Name of the define for the family name.
     type: string
   c-version-name:
-    description: Name of the define for the verion of the family.
+    description: Name of the define for the version of the family.
     type: string
   max-by-define:
     description: Makes the number of attributes and commands be specified by a define, not an enum value.
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index 196076dfa3096..12a0a045605d2 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -41,7 +41,7 @@ properties:
     description: Name of the define for the family name.
     type: string
   c-version-name:
-    description: Name of the define for the verion of the family.
+    description: Name of the define for the version of the family.
     type: string
   max-by-define:
     description: Makes the number of attributes and commands be specified by a define, not an enum value.
-- 
GitLab


From ed68c58c0eb4867df2e995d872aec6342171619c Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:45 +0100
Subject: [PATCH 1745/1806] doc/netlink: Add a schema for netlink-raw families

This schema is largely a copy of the genetlink-legacy schema with the
following modifications:

 - change the schema id to netlink-raw
 - add a top-level protonum property, e.g. 0 (for NETLINK_ROUTE)
 - change the protocol enumeration to netlink-raw, removing the
   genetlink options.
 - replace doc references to generic netlink with raw netlink
 - add a value property to mcast-group definitions

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-3-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/netlink-raw.yaml | 410 +++++++++++++++++++++++++
 1 file changed, 410 insertions(+)
 create mode 100644 Documentation/netlink/netlink-raw.yaml

diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml
new file mode 100644
index 0000000000000..8967978764146
--- /dev/null
+++ b/Documentation/netlink/netlink-raw.yaml
@@ -0,0 +1,410 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+%YAML 1.2
+---
+$id: http://kernel.org/schemas/netlink/netlink-raw.yaml#
+$schema: https://json-schema.org/draft-07/schema
+
+# Common defines
+$defs:
+  uint:
+    type: integer
+    minimum: 0
+  len-or-define:
+    type: [ string, integer ]
+    pattern: ^[0-9A-Za-z_]+( - 1)?$
+    minimum: 0
+
+# Schema for specs
+title: Protocol
+description: Specification of a raw netlink protocol
+type: object
+required: [ name, doc, attribute-sets, operations ]
+additionalProperties: False
+properties:
+  name:
+    description: Name of the netlink family.
+    type: string
+  doc:
+    type: string
+  protocol:
+    description: Schema compatibility level.
+    enum: [ netlink-raw ] # Trim
+  # Start netlink-raw
+  protonum:
+    description: Protocol number to use for netlink-raw
+    type: integer
+  # End netlink-raw
+  uapi-header:
+    description: Path to the uAPI header, default is linux/${family-name}.h
+    type: string
+  # Start genetlink-c
+  c-family-name:
+    description: Name of the define for the family name.
+    type: string
+  c-version-name:
+    description: Name of the define for the version of the family.
+    type: string
+  max-by-define:
+    description: Makes the number of attributes and commands be specified by a define, not an enum value.
+    type: boolean
+  # End genetlink-c
+  # Start genetlink-legacy
+  kernel-policy:
+    description: |
+      Defines if the input policy in the kernel is global, per-operation, or split per operation type.
+      Default is split.
+    enum: [ split, per-op, global ]
+  # End genetlink-legacy
+
+  definitions:
+    description: List of type and constant definitions (enums, flags, defines).
+    type: array
+    items:
+      type: object
+      required: [ type, name ]
+      additionalProperties: False
+      properties:
+        name:
+          type: string
+        header:
+          description: For C-compatible languages, header which already defines this value.
+          type: string
+        type:
+          enum: [ const, enum, flags, struct ] # Trim
+        doc:
+          type: string
+        # For const
+        value:
+          description: For const - the value.
+          type: [ string, integer ]
+        # For enum and flags
+        value-start:
+          description: For enum or flags the literal initializer for the first value.
+          type: [ string, integer ]
+        entries:
+          description: For enum or flags array of values.
+          type: array
+          items:
+            oneOf:
+              - type: string
+              - type: object
+                required: [ name ]
+                additionalProperties: False
+                properties:
+                  name:
+                    type: string
+                  value:
+                    type: integer
+                  doc:
+                    type: string
+        render-max:
+          description: Render the max members for this enum.
+          type: boolean
+        # Start genetlink-c
+        enum-name:
+          description: Name for enum, if empty no name will be used.
+          type: [ string, "null" ]
+        name-prefix:
+          description: For enum the prefix of the values, optional.
+          type: string
+        # End genetlink-c
+        # Start genetlink-legacy
+        members:
+          description: List of struct members. Only scalars and strings members allowed.
+          type: array
+          items:
+            type: object
+            required: [ name, type ]
+            additionalProperties: False
+            properties:
+              name:
+                type: string
+              type:
+                description: The netlink attribute type
+                enum: [ u8, u16, u32, u64, s8, s16, s32, s64, string, binary ]
+              len:
+                $ref: '#/$defs/len-or-define'
+              byte-order:
+                enum: [ little-endian, big-endian ]
+              doc:
+                description: Documentation for the struct member attribute.
+                type: string
+              enum:
+                description: Name of the enum type used for the attribute.
+                type: string
+              enum-as-flags:
+                description: |
+                  Treat the enum as flags. In most cases enum is either used as flags or as values.
+                  Sometimes, however, both forms are necessary, in which case header contains the enum
+                  form while specific attributes may request to convert the values into a bitfield.
+                type: boolean
+              display-hint: &display-hint
+                description: |
+                  Optional format indicator that is intended only for choosing
+                  the right formatting mechanism when displaying values of this
+                  type.
+                enum: [ hex, mac, fddi, ipv4, ipv6, uuid ]
+        # End genetlink-legacy
+
+  attribute-sets:
+    description: Definition of attribute spaces for this family.
+    type: array
+    items:
+      description: Definition of a single attribute space.
+      type: object
+      required: [ name, attributes ]
+      additionalProperties: False
+      properties:
+        name:
+          description: |
+            Name used when referring to this space in other definitions, not used outside of the spec.
+          type: string
+        name-prefix:
+          description: |
+            Prefix for the C enum name of the attributes. Default family[name]-set[name]-a-
+          type: string
+        enum-name:
+          description: Name for the enum type of the attribute.
+          type: string
+        doc:
+          description: Documentation of the space.
+          type: string
+        subset-of:
+          description: |
+            Name of another space which this is a logical part of. Sub-spaces can be used to define
+            a limited group of attributes which are used in a nest.
+          type: string
+        # Start genetlink-c
+        attr-cnt-name:
+          description: The explicit name for constant holding the count of attributes (last attr + 1).
+          type: string
+        attr-max-name:
+          description: The explicit name for last member of attribute enum.
+          type: string
+        # End genetlink-c
+        attributes:
+          description: List of attributes in the space.
+          type: array
+          items:
+            type: object
+            required: [ name, type ]
+            additionalProperties: False
+            properties:
+              name:
+                type: string
+              type: &attr-type
+                description: The netlink attribute type
+                enum: [ unused, pad, flag, binary, u8, u16, u32, u64, s32, s64,
+                        string, nest, array-nest, nest-type-value ]
+              doc:
+                description: Documentation of the attribute.
+                type: string
+              value:
+                description: Value for the enum item representing this attribute in the uAPI.
+                $ref: '#/$defs/uint'
+              type-value:
+                description: Name of the value extracted from the type of a nest-type-value attribute.
+                type: array
+                items:
+                  type: string
+              byte-order:
+                enum: [ little-endian, big-endian ]
+              multi-attr:
+                type: boolean
+              nested-attributes:
+                description: Name of the space (sub-space) used inside the attribute.
+                type: string
+              enum:
+                description: Name of the enum type used for the attribute.
+                type: string
+              enum-as-flags:
+                description: |
+                  Treat the enum as flags. In most cases enum is either used as flags or as values.
+                  Sometimes, however, both forms are necessary, in which case header contains the enum
+                  form while specific attributes may request to convert the values into a bitfield.
+                type: boolean
+              checks:
+                description: Kernel input validation.
+                type: object
+                additionalProperties: False
+                properties:
+                  flags-mask:
+                    description: Name of the flags constant on which to base mask (unsigned scalar types only).
+                    type: string
+                  min:
+                    description: Min value for an integer attribute.
+                    type: integer
+                  min-len:
+                    description: Min length for a binary attribute.
+                    $ref: '#/$defs/len-or-define'
+                  max-len:
+                    description: Max length for a string or a binary attribute.
+                    $ref: '#/$defs/len-or-define'
+              sub-type: *attr-type
+              display-hint: *display-hint
+              # Start genetlink-c
+              name-prefix:
+                type: string
+              # End genetlink-c
+              # Start genetlink-legacy
+              struct:
+                description: Name of the struct type used for the attribute.
+                type: string
+              # End genetlink-legacy
+
+      # Make sure name-prefix does not appear in subsets (subsets inherit naming)
+      dependencies:
+        name-prefix:
+          not:
+            required: [ subset-of ]
+        subset-of:
+          not:
+            required: [ name-prefix ]
+
+  operations:
+    description: Operations supported by the protocol.
+    type: object
+    required: [ list ]
+    additionalProperties: False
+    properties:
+      enum-model:
+        description: |
+          The model of assigning values to the operations.
+          "unified" is the recommended model where all message types belong
+          to a single enum.
+          "directional" has the messages sent to the kernel and from the kernel
+          enumerated separately.
+        enum: [ unified, directional ] # Trim
+      name-prefix:
+        description: |
+          Prefix for the C enum name of the command. The name is formed by concatenating
+          the prefix with the upper case name of the command, with dashes replaced by underscores.
+        type: string
+      enum-name:
+        description: Name for the enum type with commands.
+        type: string
+      async-prefix:
+        description: Same as name-prefix but used to render notifications and events to separate enum.
+        type: string
+      async-enum:
+        description: Name for the enum type with notifications/events.
+        type: string
+      # Start genetlink-legacy
+      fixed-header: &fixed-header
+        description: |
+          Name of the structure defining the optional fixed-length protocol
+          header. This header is placed in a message after the netlink and
+          genetlink headers and before any attributes.
+        type: string
+      # End genetlink-legacy
+      list:
+        description: List of commands
+        type: array
+        items:
+          type: object
+          additionalProperties: False
+          required: [ name, doc ]
+          properties:
+            name:
+              description: Name of the operation, also defining its C enum value in uAPI.
+              type: string
+            doc:
+              description: Documentation for the command.
+              type: string
+            value:
+              description: Value for the enum in the uAPI.
+              $ref: '#/$defs/uint'
+            attribute-set:
+              description: |
+                Attribute space from which attributes directly in the requests and replies
+                to this command are defined.
+              type: string
+            flags: &cmd_flags
+              description: Command flags.
+              type: array
+              items:
+                enum: [ admin-perm ]
+            dont-validate:
+              description: Kernel attribute validation flags.
+              type: array
+              items:
+                enum: [ strict, dump ]
+            # Start genetlink-legacy
+            fixed-header: *fixed-header
+            # End genetlink-legacy
+            do: &subop-type
+              description: Main command handler.
+              type: object
+              additionalProperties: False
+              properties:
+                request: &subop-attr-list
+                  description: Definition of the request message for a given command.
+                  type: object
+                  additionalProperties: False
+                  properties:
+                    attributes:
+                      description: |
+                        Names of attributes from the attribute-set (not full attribute
+                        definitions, just names).
+                      type: array
+                      items:
+                        type: string
+                    # Start genetlink-legacy
+                    value:
+                      description: |
+                        ID of this message if value for request and response differ,
+                        i.e. requests and responses have different message enums.
+                      $ref: '#/$defs/uint'
+                    # End genetlink-legacy
+                reply: *subop-attr-list
+                pre:
+                  description: Hook for a function to run before the main callback (pre_doit or start).
+                  type: string
+                post:
+                  description: Hook for a function to run after the main callback (post_doit or done).
+                  type: string
+            dump: *subop-type
+            notify:
+              description: Name of the command sharing the reply type with this notification.
+              type: string
+            event:
+              type: object
+              additionalProperties: False
+              properties:
+                attributes:
+                  description: Explicit list of the attributes for the notification.
+                  type: array
+                  items:
+                    type: string
+            mcgrp:
+              description: Name of the multicast group generating given notification.
+              type: string
+  mcast-groups:
+    description: List of multicast groups.
+    type: object
+    required: [ list ]
+    additionalProperties: False
+    properties:
+      list:
+        description: List of groups.
+        type: array
+        items:
+          type: object
+          required: [ name ]
+          additionalProperties: False
+          properties:
+            name:
+              description: |
+                The name for the group, used to form the define and the value of the define.
+              type: string
+            # Start genetlink-c
+            c-define-name:
+              description: Override for the name of the define in C uAPI.
+              type: string
+            # End genetlink-c
+            flags: *cmd_flags
+            # Start netlink-raw
+            value:
+              description: Value of the netlink multicast group in the uAPI.
+              type: integer
+            # End netlink-raw
-- 
GitLab


From 294f37fc87728230cf81f387aa6a0a8438066751 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:46 +0100
Subject: [PATCH 1746/1806] doc/netlink: Update genetlink-legacy documentation

Add documentation for recently added genetlink-legacy schema attributes.
Remove statements about 'work in progress' and 'todo'.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-4-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/core-api/netlink.rst            |  9 ++++---
 .../netlink/genetlink-legacy.rst              | 26 ++++++++++++-------
 Documentation/userspace-api/netlink/specs.rst | 13 ++++++++++
 3 files changed, 35 insertions(+), 13 deletions(-)

diff --git a/Documentation/core-api/netlink.rst b/Documentation/core-api/netlink.rst
index e4a938a05cc95..9f692b02bfe61 100644
--- a/Documentation/core-api/netlink.rst
+++ b/Documentation/core-api/netlink.rst
@@ -67,10 +67,11 @@ Globals
 kernel-policy
 ~~~~~~~~~~~~~
 
-Defines if the kernel validation policy is per operation (``per-op``)
-or for the entire family (``global``). New families should use ``per-op``
-(default) to be able to narrow down the attributes accepted by a specific
-command.
+Defines whether the kernel validation policy is ``global`` i.e. the same for all
+operations of the family, defined for each operation individually - ``per-op``,
+or separately for each operation and operation type (do vs dump) - ``split``.
+New families should use ``per-op`` (default) to be able to narrow down the
+attributes accepted by a specific command.
 
 checks
 ------
diff --git a/Documentation/userspace-api/netlink/genetlink-legacy.rst b/Documentation/userspace-api/netlink/genetlink-legacy.rst
index 802875a37a270..40b82ad5d54a5 100644
--- a/Documentation/userspace-api/netlink/genetlink-legacy.rst
+++ b/Documentation/userspace-api/netlink/genetlink-legacy.rst
@@ -8,11 +8,8 @@ This document describes the many additional quirks and properties
 required to describe older Generic Netlink families which form
 the ``genetlink-legacy`` protocol level.
 
-The spec is a work in progress, some of the quirks are just documented
-for future reference.
-
-Specification (defined)
-=======================
+Specification
+=============
 
 Attribute type nests
 --------------------
@@ -156,16 +153,27 @@ it will be allocated 3 for the request (``a`` is the previous operation
 with a request section and the value of 2) and 8 for response (``c`` is
 the previous operation in the "from-kernel" direction).
 
-Other quirks (todo)
-===================
+Other quirks
+============
 
 Structures
 ----------
 
 Legacy families can define C structures both to be used as the contents of
 an attribute and as a fixed message header. Structures are defined in
-``definitions``  and referenced in operations or attributes. Note that
-structures defined in YAML are implicitly packed according to C
+``definitions``  and referenced in operations or attributes.
+
+members
+~~~~~~~
+
+ - ``name`` - The attribute name of the struct member
+ - ``type`` - One of the scalar types ``u8``, ``u16``, ``u32``, ``u64``, ``s8``,
+   ``s16``, ``s32``, ``s64``, ``string`` or ``binary``.
+ - ``byte-order`` - ``big-endian`` or ``little-endian``
+ - ``doc``, ``enum``, ``enum-as-flags``, ``display-hint`` - Same as for
+   :ref:`attribute definitions <attribute_properties>`
+
+Note that structures defined in YAML are implicitly packed according to C
 conventions. For example, the following struct is 4 bytes, not 6 bytes:
 
 .. code-block:: c
diff --git a/Documentation/userspace-api/netlink/specs.rst b/Documentation/userspace-api/netlink/specs.rst
index 2e4acde890b76..cc4e2430997ef 100644
--- a/Documentation/userspace-api/netlink/specs.rst
+++ b/Documentation/userspace-api/netlink/specs.rst
@@ -68,6 +68,10 @@ The following sections describe the properties of the most modern ``genetlink``
 schema. See the documentation of :doc:`genetlink-c <c-code-gen>`
 for information on how C names are derived from name properties.
 
+See also :ref:`Documentation/core-api/netlink.rst <kernel_netlink>` for
+information on the Netlink specification properties that are only relevant to
+the kernel space and not part of the user space API.
+
 genetlink
 =========
 
@@ -180,6 +184,8 @@ attributes
 
 List of attributes in the set.
 
+.. _attribute_properties:
+
 Attribute properties
 --------------------
 
@@ -264,6 +270,13 @@ a C array of u32 values can be specified with ``type: binary`` and
 ``sub-type: u32``. Binary types and legacy array formats are described in
 more detail in :doc:`genetlink-legacy`.
 
+display-hint
+~~~~~~~~~~~~
+
+Optional format indicator that is intended only for choosing the right
+formatting mechanism when displaying values of this type. Currently supported
+hints are ``hex``, ``mac``, ``fddi``, ``ipv4``, ``ipv6`` and ``uuid``.
+
 operations
 ----------
 
-- 
GitLab


From 2db8abf0b455e7494bbdd695775bd43c9d4824a8 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:47 +0100
Subject: [PATCH 1747/1806] doc/netlink: Document the netlink-raw schema
 extensions

Add a doc page for netlink-raw that describes the schema attributes
needed for netlink-raw.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-5-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/userspace-api/netlink/index.rst |  1 +
 .../userspace-api/netlink/netlink-raw.rst     | 58 +++++++++++++++++++
 2 files changed, 59 insertions(+)
 create mode 100644 Documentation/userspace-api/netlink/netlink-raw.rst

diff --git a/Documentation/userspace-api/netlink/index.rst b/Documentation/userspace-api/netlink/index.rst
index 26f3720cb3be4..62725dafbbdb5 100644
--- a/Documentation/userspace-api/netlink/index.rst
+++ b/Documentation/userspace-api/netlink/index.rst
@@ -14,5 +14,6 @@ Netlink documentation for users.
    specs
    c-code-gen
    genetlink-legacy
+   netlink-raw
 
 See also :ref:`Documentation/core-api/netlink.rst <kernel_netlink>`.
diff --git a/Documentation/userspace-api/netlink/netlink-raw.rst b/Documentation/userspace-api/netlink/netlink-raw.rst
new file mode 100644
index 0000000000000..f07fb9b9c101e
--- /dev/null
+++ b/Documentation/userspace-api/netlink/netlink-raw.rst
@@ -0,0 +1,58 @@
+.. SPDX-License-Identifier: BSD-3-Clause
+
+======================================================
+Netlink specification support for raw Netlink families
+======================================================
+
+This document describes the additional properties required by raw Netlink
+families such as ``NETLINK_ROUTE`` which use the ``netlink-raw`` protocol
+specification.
+
+Specification
+=============
+
+The netlink-raw schema extends the :doc:`genetlink-legacy <genetlink-legacy>`
+schema with properties that are needed to specify the protocol numbers and
+multicast IDs used by raw netlink families. See :ref:`classic_netlink` for more
+information.
+
+Globals
+-------
+
+protonum
+~~~~~~~~
+
+The ``protonum`` property is used to specify the protocol number to use when
+opening a netlink socket.
+
+.. code-block:: yaml
+
+  # SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+
+  name: rt-addr
+  protocol: netlink-raw
+  protonum: 0             # part of the NETLINK_ROUTE protocol
+
+
+Multicast group properties
+--------------------------
+
+value
+~~~~~
+
+The ``value`` property is used to specify the group ID to use for multicast
+group registration.
+
+.. code-block:: yaml
+
+  mcast-groups:
+    list:
+      -
+        name: rtnlgrp-ipv4-ifaddr
+        value: 5
+      -
+        name: rtnlgrp-ipv6-ifaddr
+        value: 9
+      -
+        name: rtnlgrp-mctp-ifaddr
+        value: 34
-- 
GitLab


From 88901b967958eaa70478db1c6ddc8cdea748b2e6 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:48 +0100
Subject: [PATCH 1748/1806] tools/ynl: Add mcast-group schema parsing to ynl

Add a SpecMcastGroup class to the nlspec lib.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-6-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/nlspec.py | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py
index 0ff0d18666b2d..37bcb4d8b37b0 100644
--- a/tools/net/ynl/lib/nlspec.py
+++ b/tools/net/ynl/lib/nlspec.py
@@ -322,6 +322,26 @@ class SpecOperation(SpecElement):
             self.attr_set = self.family.attr_sets[attr_set_name]
 
 
+class SpecMcastGroup(SpecElement):
+    """Netlink Multicast Group
+
+    Information about a multicast group.
+
+    Value is only used for classic netlink families that use the
+    netlink-raw schema. Genetlink families use dynamic ID allocation
+    where the ids of multicast groups get resolved at runtime. Value
+    will be None for genetlink families.
+
+    Attributes:
+        name      name of the mulitcast group
+        value     integer id of this multicast group for netlink-raw or None
+        yaml      raw spec as loaded from the spec file
+    """
+    def __init__(self, family, yaml):
+        super().__init__(family, yaml)
+        self.value = self.yaml.get('value')
+
+
 class SpecFamily(SpecElement):
     """ Netlink Family Spec class.
 
@@ -343,6 +363,7 @@ class SpecFamily(SpecElement):
         ntfs       dict of all async events
         consts     dict of all constants/enums
         fixed_header  string, optional name of family default fixed header struct
+        mcast_groups  dict of all multicast groups (index by name)
     """
     def __init__(self, spec_path, schema_path=None, exclude_ops=None):
         with open(spec_path, "r") as stream:
@@ -384,6 +405,7 @@ class SpecFamily(SpecElement):
         self.ops = collections.OrderedDict()
         self.ntfs = collections.OrderedDict()
         self.consts = collections.OrderedDict()
+        self.mcast_groups = collections.OrderedDict()
 
         last_exception = None
         while len(self._resolution_list) > 0:
@@ -416,6 +438,9 @@ class SpecFamily(SpecElement):
     def new_operation(self, elem, req_val, rsp_val):
         return SpecOperation(self, elem, req_val, rsp_val)
 
+    def new_mcast_group(self, elem):
+        return SpecMcastGroup(self, elem)
+
     def add_unresolved(self, elem):
         self._resolution_list.append(elem)
 
@@ -512,3 +537,9 @@ class SpecFamily(SpecElement):
                 self.ops[op.name] = op
             elif op.is_async:
                 self.ntfs[op.name] = op
+
+        mcgs = self.yaml.get('mcast-groups')
+        if mcgs:
+            for elem in mcgs['list']:
+                mcg = self.new_mcast_group(elem)
+                self.mcast_groups[elem['name']] = mcg
-- 
GitLab


From fb0a06d455d64443fefea6843ed6c5ae7ee0b395 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:49 +0100
Subject: [PATCH 1749/1806] tools/net/ynl: Fix extack parsing with fixed header
 genlmsg

Move decode_fixed_header into YnlFamily and add a _fixed_header_size
method to allow extack decoding to skip the fixed header.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-7-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/ynl.py | 65 ++++++++++++++++++++++++----------------
 1 file changed, 40 insertions(+), 25 deletions(-)

diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index fa4f1c28efc55..db556dcb931e2 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -293,7 +293,7 @@ def _genl_load_families():
 
                 gm = GenlMsg(nl_msg)
                 fam = dict()
-                for attr in gm.raw_attrs:
+                for attr in NlAttrs(gm.raw):
                     if attr.type == Netlink.CTRL_ATTR_FAMILY_ID:
                         fam['id'] = attr.as_scalar('u16')
                     elif attr.type == Netlink.CTRL_ATTR_FAMILY_NAME:
@@ -317,23 +317,10 @@ def _genl_load_families():
 
 
 class GenlMsg:
-    def __init__(self, nl_msg, fixed_header_members=[]):
+    def __init__(self, nl_msg):
         self.nl = nl_msg
-
-        self.hdr = nl_msg.raw[0:4]
-        offset = 4
-
-        self.genl_cmd, self.genl_version, _ = struct.unpack("BBH", self.hdr)
-
-        self.fixed_header_attrs = dict()
-        for m in fixed_header_members:
-            format = NlAttr.get_format(m.type, m.byte_order)
-            decoded = format.unpack_from(nl_msg.raw, offset)
-            offset += format.size
-            self.fixed_header_attrs[m.name] = decoded[0]
-
-        self.raw = nl_msg.raw[offset:]
-        self.raw_attrs = NlAttrs(self.raw)
+        self.genl_cmd, self.genl_version, _ = struct.unpack_from("BBH", nl_msg.raw, 0)
+        self.raw = nl_msg.raw[4:]
 
     def __repr__(self):
         msg = repr(self.nl)
@@ -514,17 +501,44 @@ class YnlFamily(SpecFamily):
 
         return None
 
-    def _decode_extack(self, request, attr_space, extack):
+    def _decode_extack(self, request, op, extack):
         if 'bad-attr-offs' not in extack:
             return
 
-        genl_req = GenlMsg(NlMsg(request, 0, attr_space=attr_space))
-        path = self._decode_extack_path(genl_req.raw_attrs, attr_space,
-                                        20, extack['bad-attr-offs'])
+        genl_req = GenlMsg(NlMsg(request, 0, op.attr_set))
+        fixed_header_size = self._fixed_header_size(op)
+        offset = 20 + fixed_header_size
+        path = self._decode_extack_path(NlAttrs(genl_req.raw[fixed_header_size:]),
+                                        op.attr_set, offset,
+                                        extack['bad-attr-offs'])
         if path:
             del extack['bad-attr-offs']
             extack['bad-attr'] = path
 
+    def _fixed_header_size(self, op):
+        if op.fixed_header:
+            fixed_header_members = self.consts[op.fixed_header].members
+            size = 0
+            for m in fixed_header_members:
+                format = NlAttr.get_format(m.type, m.byte_order)
+                size += format.size
+            return size
+        else:
+            return 0
+
+    def _decode_fixed_header(self, msg, name):
+        fixed_header_members = self.consts[name].members
+        fixed_header_attrs = dict()
+        offset = 0
+        for m in fixed_header_members:
+            format = NlAttr.get_format(m.type, m.byte_order)
+            [ value ] = format.unpack_from(msg.raw, offset)
+            offset += format.size
+            if m.enum:
+                value = self._decode_enum(value, m)
+            fixed_header_attrs[m.name] = value
+        return fixed_header_attrs
+
     def handle_ntf(self, nl_msg, genl_msg):
         msg = dict()
         if self.include_raw:
@@ -599,7 +613,7 @@ class YnlFamily(SpecFamily):
             nms = NlMsgs(reply, attr_space=op.attr_set)
             for nl_msg in nms:
                 if nl_msg.extack:
-                    self._decode_extack(msg, op.attr_set, nl_msg.extack)
+                    self._decode_extack(msg, op, nl_msg.extack)
 
                 if nl_msg.error:
                     raise NlError(nl_msg)
@@ -610,7 +624,7 @@ class YnlFamily(SpecFamily):
                     done = True
                     break
 
-                gm = GenlMsg(nl_msg, fixed_header_members)
+                gm = GenlMsg(nl_msg)
                 # Check if this is a reply to our request
                 if nl_msg.nl_seq != req_seq or gm.genl_cmd != op.rsp_value:
                     if gm.genl_cmd in self.async_msg_ids:
@@ -620,8 +634,9 @@ class YnlFamily(SpecFamily):
                         print('Unexpected message: ' + repr(gm))
                         continue
 
-                rsp_msg = self._decode(gm.raw_attrs, op.attr_set.name)
-                rsp_msg.update(gm.fixed_header_attrs)
+                rsp_msg = self._decode(NlAttrs(gm.raw), op.attr_set.name)
+                if op.fixed_header:
+                    rsp_msg.update(self._decode_fixed_header(gm, op.fixed_header))
                 rsp.append(rsp_msg)
 
         if not rsp:
-- 
GitLab


From e46dd903efe367214802b8d1cac01bdc43708339 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:50 +0100
Subject: [PATCH 1750/1806] tools/net/ynl: Add support for netlink-raw families

Refactor the ynl code to encapsulate protocol specifics into
NetlinkProtocol and GenlProtocol.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20230825122756.7603-8-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/ynl.py | 124 ++++++++++++++++++++++++++++-----------
 1 file changed, 91 insertions(+), 33 deletions(-)

diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index db556dcb931e2..43022dec1076c 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -25,6 +25,7 @@ class Netlink:
     NETLINK_ADD_MEMBERSHIP = 1
     NETLINK_CAP_ACK = 10
     NETLINK_EXT_ACK = 11
+    NETLINK_GET_STRICT_CHK = 12
 
     # Netlink message
     NLMSG_ERROR = 2
@@ -228,6 +229,9 @@ class NlMsg:
                             desc += f" ({spec['doc']})"
                         self.extack['miss-type'] = desc
 
+    def cmd(self):
+        return self.nl_type
+
     def __repr__(self):
         msg = f"nl_len = {self.nl_len} ({len(self.raw)}) nl_flags = 0x{self.nl_flags:x} nl_type = {self.nl_type}\n"
         if self.error:
@@ -322,6 +326,9 @@ class GenlMsg:
         self.genl_cmd, self.genl_version, _ = struct.unpack_from("BBH", nl_msg.raw, 0)
         self.raw = nl_msg.raw[4:]
 
+    def cmd(self):
+        return self.genl_cmd
+
     def __repr__(self):
         msg = repr(self.nl)
         msg += f"\tgenl_cmd = {self.genl_cmd} genl_ver = {self.genl_version}\n"
@@ -330,9 +337,41 @@ class GenlMsg:
         return msg
 
 
-class GenlFamily:
-    def __init__(self, family_name):
+class NetlinkProtocol:
+    def __init__(self, family_name, proto_num):
         self.family_name = family_name
+        self.proto_num = proto_num
+
+    def _message(self, nl_type, nl_flags, seq=None):
+        if seq is None:
+            seq = random.randint(1, 1024)
+        nlmsg = struct.pack("HHII", nl_type, nl_flags, seq, 0)
+        return nlmsg
+
+    def message(self, flags, command, version, seq=None):
+        return self._message(command, flags, seq)
+
+    def _decode(self, nl_msg):
+        return nl_msg
+
+    def decode(self, ynl, nl_msg):
+        msg = self._decode(nl_msg)
+        fixed_header_size = 0
+        if ynl:
+            op = ynl.rsp_by_value[msg.cmd()]
+            fixed_header_size = ynl._fixed_header_size(op)
+        msg.raw_attrs = NlAttrs(msg.raw[fixed_header_size:])
+        return msg
+
+    def get_mcast_id(self, mcast_name, mcast_groups):
+        if mcast_name not in mcast_groups:
+            raise Exception(f'Multicast group "{mcast_name}" not present in the spec')
+        return mcast_groups[mcast_name].value
+
+
+class GenlProtocol(NetlinkProtocol):
+    def __init__(self, family_name):
+        super().__init__(family_name, Netlink.NETLINK_GENERIC)
 
         global genl_family_name_to_id
         if genl_family_name_to_id is None:
@@ -341,6 +380,19 @@ class GenlFamily:
         self.genl_family = genl_family_name_to_id[family_name]
         self.family_id = genl_family_name_to_id[family_name]['id']
 
+    def message(self, flags, command, version, seq=None):
+        nlmsg = self._message(self.family_id, flags, seq)
+        genlmsg = struct.pack("BBH", command, version, 0)
+        return nlmsg + genlmsg
+
+    def _decode(self, nl_msg):
+        return GenlMsg(nl_msg)
+
+    def get_mcast_id(self, mcast_name, mcast_groups):
+        if mcast_name not in self.genl_family['mcast']:
+            raise Exception(f'Multicast group "{mcast_name}" not present in the family')
+        return self.genl_family['mcast'][mcast_name]
+
 
 #
 # YNL implementation details.
@@ -353,9 +405,19 @@ class YnlFamily(SpecFamily):
 
         self.include_raw = False
 
-        self.sock = socket.socket(socket.AF_NETLINK, socket.SOCK_RAW, Netlink.NETLINK_GENERIC)
+        try:
+            if self.proto == "netlink-raw":
+                self.nlproto = NetlinkProtocol(self.yaml['name'],
+                                               self.yaml['protonum'])
+            else:
+                self.nlproto = GenlProtocol(self.yaml['name'])
+        except KeyError:
+            raise Exception(f"Family '{self.yaml['name']}' not supported by the kernel")
+
+        self.sock = socket.socket(socket.AF_NETLINK, socket.SOCK_RAW, self.nlproto.proto_num)
         self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_CAP_ACK, 1)
         self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_EXT_ACK, 1)
+        self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_GET_STRICT_CHK, 1)
 
         self.async_msg_ids = set()
         self.async_msg_queue = []
@@ -368,18 +430,12 @@ class YnlFamily(SpecFamily):
             bound_f = functools.partial(self._op, op_name)
             setattr(self, op.ident_name, bound_f)
 
-        try:
-            self.family = GenlFamily(self.yaml['name'])
-        except KeyError:
-            raise Exception(f"Family '{self.yaml['name']}' not supported by the kernel")
 
     def ntf_subscribe(self, mcast_name):
-        if mcast_name not in self.family.genl_family['mcast']:
-            raise Exception(f'Multicast group "{mcast_name}" not present in the family')
-
+        mcast_id = self.nlproto.get_mcast_id(mcast_name, self.mcast_groups)
         self.sock.bind((0, 0))
         self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_ADD_MEMBERSHIP,
-                             self.family.genl_family['mcast'][mcast_name])
+                             mcast_id)
 
     def _add_attr(self, space, name, value):
         try:
@@ -505,11 +561,9 @@ class YnlFamily(SpecFamily):
         if 'bad-attr-offs' not in extack:
             return
 
-        genl_req = GenlMsg(NlMsg(request, 0, op.attr_set))
-        fixed_header_size = self._fixed_header_size(op)
-        offset = 20 + fixed_header_size
-        path = self._decode_extack_path(NlAttrs(genl_req.raw[fixed_header_size:]),
-                                        op.attr_set, offset,
+        msg = self.nlproto.decode(self, NlMsg(request, 0, op.attr_set))
+        offset = 20 + self._fixed_header_size(op)
+        path = self._decode_extack_path(msg.raw_attrs, op.attr_set, offset,
                                         extack['bad-attr-offs'])
         if path:
             del extack['bad-attr-offs']
@@ -539,14 +593,17 @@ class YnlFamily(SpecFamily):
             fixed_header_attrs[m.name] = value
         return fixed_header_attrs
 
-    def handle_ntf(self, nl_msg, genl_msg):
+    def handle_ntf(self, decoded):
         msg = dict()
         if self.include_raw:
-            msg['nlmsg'] = nl_msg
-            msg['genlmsg'] = genl_msg
-        op = self.rsp_by_value[genl_msg.genl_cmd]
+            msg['raw'] = decoded
+        op = self.rsp_by_value[decoded.cmd()]
+        attrs = self._decode(decoded.raw_attrs, op.attr_set.name)
+        if op.fixed_header:
+            attrs.update(self._decode_fixed_header(decoded, op.fixed_header))
+
         msg['name'] = op['name']
-        msg['msg'] = self._decode(genl_msg.raw_attrs, op.attr_set.name)
+        msg['msg'] = attrs
         self.async_msg_queue.append(msg)
 
     def check_ntf(self):
@@ -566,12 +623,12 @@ class YnlFamily(SpecFamily):
                     print("Netlink done while checking for ntf!?")
                     continue
 
-                gm = GenlMsg(nl_msg)
-                if gm.genl_cmd not in self.async_msg_ids:
-                    print("Unexpected msg id done while checking for ntf", gm)
+                decoded = self.nlproto.decode(self, nl_msg)
+                if decoded.cmd() not in self.async_msg_ids:
+                    print("Unexpected msg id done while checking for ntf", decoded)
                     continue
 
-                self.handle_ntf(nl_msg, gm)
+                self.handle_ntf(decoded)
 
     def operation_do_attributes(self, name):
       """
@@ -592,7 +649,7 @@ class YnlFamily(SpecFamily):
             nl_flags |= Netlink.NLM_F_DUMP
 
         req_seq = random.randint(1024, 65535)
-        msg = _genl_msg(self.family.family_id, nl_flags, op.req_value, 1, req_seq)
+        msg = self.nlproto.message(nl_flags, op.req_value, 1, req_seq)
         fixed_header_members = []
         if op.fixed_header:
             fixed_header_members = self.consts[op.fixed_header].members
@@ -624,19 +681,20 @@ class YnlFamily(SpecFamily):
                     done = True
                     break
 
-                gm = GenlMsg(nl_msg)
+                decoded = self.nlproto.decode(self, nl_msg)
+
                 # Check if this is a reply to our request
-                if nl_msg.nl_seq != req_seq or gm.genl_cmd != op.rsp_value:
-                    if gm.genl_cmd in self.async_msg_ids:
-                        self.handle_ntf(nl_msg, gm)
+                if nl_msg.nl_seq != req_seq or decoded.cmd() != op.rsp_value:
+                    if decoded.cmd() in self.async_msg_ids:
+                        self.handle_ntf(decoded)
                         continue
                     else:
-                        print('Unexpected message: ' + repr(gm))
+                        print('Unexpected message: ' + repr(decoded))
                         continue
 
-                rsp_msg = self._decode(NlAttrs(gm.raw), op.attr_set.name)
+                rsp_msg = self._decode(decoded.raw_attrs, op.attr_set.name)
                 if op.fixed_header:
-                    rsp_msg.update(self._decode_fixed_header(gm, op.fixed_header))
+                    rsp_msg.update(self._decode_fixed_header(decoded, op.fixed_header))
                 rsp.append(rsp_msg)
 
         if not rsp:
-- 
GitLab


From 0493e56d021d371d3511159a38facbc92969c0f6 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:51 +0100
Subject: [PATCH 1751/1806] tools/net/ynl: Implement nlattr array-nest decoding
 in ynl

Add support for the 'array-nest' attribute type that is used by several
netlink-raw families.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-9-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/ynl.py | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 43022dec1076c..cab84c407ba2b 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -497,6 +497,17 @@ class YnlFamily(SpecFamily):
                 decoded = NlAttr.formatted_string(decoded, attr_spec.display_hint)
         return decoded
 
+    def _decode_array_nest(self, attr, attr_spec):
+        decoded = []
+        offset = 0
+        while offset < len(attr.raw):
+            item = NlAttr(attr.raw, offset)
+            offset += item.full_len
+
+            subattrs = self._decode(NlAttrs(item.raw), attr_spec['nested-attributes'])
+            decoded.append({ item.type: subattrs })
+        return decoded
+
     def _decode(self, attrs, space):
         attr_space = self.attr_sets[space]
         rsp = dict()
@@ -516,6 +527,8 @@ class YnlFamily(SpecFamily):
                 decoded = True
             elif attr_spec["type"] in NlAttr.type_formats:
                 decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order)
+            elif attr_spec["type"] == 'array-nest':
+                decoded = self._decode_array_nest(attr, attr_spec)
             else:
                 raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}')
 
-- 
GitLab


From 1768d8a767f8e7049407fe467364e7ea56f0bdce Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:52 +0100
Subject: [PATCH 1752/1806] tools/net/ynl: Add support for create flags

Add support for using NLM_F_REPLACE, _EXCL, _CREATE and _APPEND flags
in requests.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-10-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/cli.py          | 12 ++++++++++--
 tools/net/ynl/lib/__init__.py |  4 ++--
 tools/net/ynl/lib/ynl.py      | 14 ++++++++++----
 3 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/cli.py
index ffaa8038aa8c6..564ecf07cd2c8 100755
--- a/tools/net/ynl/cli.py
+++ b/tools/net/ynl/cli.py
@@ -6,7 +6,7 @@ import json
 import pprint
 import time
 
-from lib import YnlFamily
+from lib import YnlFamily, Netlink
 
 
 def main():
@@ -19,6 +19,14 @@ def main():
     parser.add_argument('--dump', dest='dump', type=str)
     parser.add_argument('--sleep', dest='sleep', type=int)
     parser.add_argument('--subscribe', dest='ntf', type=str)
+    parser.add_argument('--replace', dest='flags', action='append_const',
+                        const=Netlink.NLM_F_REPLACE)
+    parser.add_argument('--excl', dest='flags', action='append_const',
+                        const=Netlink.NLM_F_EXCL)
+    parser.add_argument('--create', dest='flags', action='append_const',
+                        const=Netlink.NLM_F_CREATE)
+    parser.add_argument('--append', dest='flags', action='append_const',
+                        const=Netlink.NLM_F_APPEND)
     args = parser.parse_args()
 
     if args.no_schema:
@@ -37,7 +45,7 @@ def main():
         time.sleep(args.sleep)
 
     if args.do:
-        reply = ynl.do(args.do, attrs)
+        reply = ynl.do(args.do, attrs, args.flags)
         pprint.PrettyPrinter().pprint(reply)
     if args.dump:
         reply = ynl.dump(args.dump, attrs)
diff --git a/tools/net/ynl/lib/__init__.py b/tools/net/ynl/lib/__init__.py
index 4b3797fe784ba..f7eaa07783e75 100644
--- a/tools/net/ynl/lib/__init__.py
+++ b/tools/net/ynl/lib/__init__.py
@@ -2,7 +2,7 @@
 
 from .nlspec import SpecAttr, SpecAttrSet, SpecEnumEntry, SpecEnumSet, \
     SpecFamily, SpecOperation
-from .ynl import YnlFamily
+from .ynl import YnlFamily, Netlink
 
 __all__ = ["SpecAttr", "SpecAttrSet", "SpecEnumEntry", "SpecEnumSet",
-           "SpecFamily", "SpecOperation", "YnlFamily"]
+           "SpecFamily", "SpecOperation", "YnlFamily", "Netlink"]
diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index cab84c407ba2b..13c4b019a881f 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -35,6 +35,10 @@ class Netlink:
     NLM_F_ACK = 4
     NLM_F_ROOT = 0x100
     NLM_F_MATCH = 0x200
+
+    NLM_F_REPLACE = 0x100
+    NLM_F_EXCL = 0x200
+    NLM_F_CREATE = 0x400
     NLM_F_APPEND = 0x800
 
     NLM_F_CAPPED = 0x100
@@ -654,10 +658,12 @@ class YnlFamily(SpecFamily):
 
       return op['do']['request']['attributes'].copy()
 
-    def _op(self, method, vals, dump=False):
+    def _op(self, method, vals, flags, dump=False):
         op = self.ops[method]
 
         nl_flags = Netlink.NLM_F_REQUEST | Netlink.NLM_F_ACK
+        for flag in flags or []:
+            nl_flags |= flag
         if dump:
             nl_flags |= Netlink.NLM_F_DUMP
 
@@ -716,8 +722,8 @@ class YnlFamily(SpecFamily):
             return rsp[0]
         return rsp
 
-    def do(self, method, vals):
-        return self._op(method, vals)
+    def do(self, method, vals, flags):
+        return self._op(method, vals, flags)
 
     def dump(self, method, vals):
-        return self._op(method, vals, dump=True)
+        return self._op(method, vals, [], dump=True)
-- 
GitLab


From dfb0f7d9d979567ad7b1194093e649c7a0d42f90 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:53 +0100
Subject: [PATCH 1753/1806] doc/netlink: Add spec for rt addr messages

Add schema for rt addr with support for:
     - newaddr, deladdr, getaddr (dump)

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-11-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt_addr.yaml | 179 +++++++++++++++++++++++
 1 file changed, 179 insertions(+)
 create mode 100644 Documentation/netlink/specs/rt_addr.yaml

diff --git a/Documentation/netlink/specs/rt_addr.yaml b/Documentation/netlink/specs/rt_addr.yaml
new file mode 100644
index 0000000000000..cbee1cedb177c
--- /dev/null
+++ b/Documentation/netlink/specs/rt_addr.yaml
@@ -0,0 +1,179 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+
+name: rt-addr
+protocol: netlink-raw
+protonum: 0
+
+doc:
+  Address configuration over rtnetlink.
+
+definitions:
+  -
+    name: ifaddrmsg
+    type: struct
+    members:
+      -
+        name: ifa-family
+        type: u8
+      -
+        name: ifa-prefixlen
+        type: u8
+      -
+        name: ifa-flags
+        type: u8
+        enum: ifa-flags
+        enum-as-flags: true
+      -
+        name: ifa-scope
+        type: u8
+      -
+        name: ifa-index
+        type: u32
+  -
+    name: ifa-cacheinfo
+    type: struct
+    members:
+      -
+        name: ifa-prefered
+        type: u32
+      -
+        name: ifa-valid
+        type: u32
+      -
+        name: cstamp
+        type: u32
+      -
+        name: tstamp
+        type: u32
+
+  -
+    name: ifa-flags
+    type: flags
+    entries:
+      -
+        name: secondary
+      -
+        name: nodad
+      -
+        name: optimistic
+      -
+        name: dadfailed
+      -
+        name: homeaddress
+      -
+        name: deprecated
+      -
+        name: tentative
+      -
+        name: permanent
+      -
+        name: managetempaddr
+      -
+        name: noprefixroute
+      -
+        name: mcautojoin
+      -
+        name: stable-privacy
+
+attribute-sets:
+  -
+    name: addr-attrs
+    attributes:
+      -
+        name: ifa-address
+        type: binary
+        display-hint: ipv4
+      -
+        name: ifa-local
+        type: binary
+        display-hint: ipv4
+      -
+        name: ifa-label
+        type: string
+      -
+        name: ifa-broadcast
+        type: binary
+        display-hint: ipv4
+      -
+        name: ifa-anycast
+        type: binary
+      -
+        name: ifa-cacheinfo
+        type: binary
+        struct: ifa-cacheinfo
+      -
+        name: ifa-multicast
+        type: binary
+      -
+        name: ifa-flags
+        type: u32
+        enum: ifa-flags
+        enum-as-flags: true
+      -
+        name: ifa-rt-priority
+        type: u32
+      -
+        name: ifa-target-netnsid
+        type: binary
+      -
+        name: ifa-proto
+        type: u8
+
+
+operations:
+  fixed-header: ifaddrmsg
+  enum-model: directional
+  list:
+    -
+      name: newaddr
+      doc: Add new address
+      attribute-set: addr-attrs
+      do:
+        request:
+          value: 20
+          attributes: &ifaddr-all
+            - ifa-family
+            - ifa-flags
+            - ifa-prefixlen
+            - ifa-scope
+            - ifa-index
+            - ifa-address
+            - ifa-label
+            - ifa-local
+            - ifa-cacheinfo
+    -
+      name: deladdr
+      doc: Remove address
+      attribute-set: addr-attrs
+      do:
+        request:
+          value: 21
+          attributes:
+            - ifa-family
+            - ifa-flags
+            - ifa-prefixlen
+            - ifa-scope
+            - ifa-index
+            - ifa-address
+            - ifa-local
+    -
+      name: getaddr
+      doc: Dump address information.
+      attribute-set: addr-attrs
+      dump:
+        request:
+          value: 22
+          attributes:
+            - ifa-index
+        reply:
+          value: 20
+          attributes: *ifaddr-all
+
+mcast-groups:
+  list:
+    -
+      name: rtnlgrp-ipv4-ifaddr
+      value: 5
+    -
+      name: rtnlgrp-ipv6-ifaddr
+      value: 9
-- 
GitLab


From b2f63d904e7254de447e6e809fc6ebd98323aa39 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:54 +0100
Subject: [PATCH 1754/1806] doc/netlink: Add spec for rt link messages

Add schema for rt link with support for newlink, dellink, getlink,
setlink and getstats.

A dummy link can be created like this:

sudo ./tools/net/ynl/cli.py \
    --spec Documentation/netlink/specs/rt_link.yaml \
    --do newlink --create \
    --json '{"ifname": "dummy0", "linkinfo": {"kind": "dummy"}}'

For example, offload stats can be fetched like this:

./tools/net/ynl/cli.py \
    --spec Documentation/netlink/specs/rt_link.yaml \
    --dump getstats --json '{ "filter-mask": 8 }'

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-12-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt_link.yaml | 1432 ++++++++++++++++++++++
 1 file changed, 1432 insertions(+)
 create mode 100644 Documentation/netlink/specs/rt_link.yaml

diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
new file mode 100644
index 0000000000000..d86a68f8475ca
--- /dev/null
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -0,0 +1,1432 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+
+name: rt-link
+protocol: netlink-raw
+protonum: 0
+
+doc:
+  Link configuration over rtnetlink.
+
+definitions:
+  -
+    name: ifinfo-flags
+    type: flags
+    entries:
+      -
+        name: up
+      -
+        name: broadcast
+      -
+        name: debug
+      -
+        name: loopback
+      -
+        name: point-to-point
+      -
+        name: no-trailers
+      -
+        name: running
+      -
+        name: no-arp
+      -
+        name: promisc
+      -
+        name: all-multi
+      -
+        name: master
+      -
+        name: slave
+      -
+        name: multicast
+      -
+        name: portsel
+      -
+        name: auto-media
+      -
+        name: dynamic
+      -
+        name: lower-up
+      -
+        name: dormant
+      -
+        name: echo
+
+  -
+    name: rtgenmsg
+    type: struct
+    members:
+      -
+        name: family
+        type: u8
+  -
+    name: ifinfomsg
+    type: struct
+    members:
+      -
+        name: ifi-family
+        type: u8
+      -
+        name: padding
+        type: u8
+      -
+        name: ifi-type
+        type: u16
+      -
+        name: ifi-index
+        type: s32
+      -
+        name: ifi-flags
+        type: u32
+        enum: ifinfo-flags
+        enum-as-flags: true
+      -
+        name: ifi-change
+        type: u32
+  -
+    name: ifla-cacheinfo
+    type: struct
+    members:
+      -
+        name: max-reasm-len
+        type: u32
+      -
+        name: tstamp
+        type: u32
+      -
+        name: reachable-time
+        type: s32
+      -
+        name: retrans-time
+        type: u32
+  -
+    name: rtnl-link-stats
+    type: struct
+    members:
+      -
+        name: rx-packets
+        type: u32
+      -
+        name: tx-packets
+        type: u32
+      -
+        name: rx-bytes
+        type: u32
+      -
+        name: tx-bytes
+        type: u32
+      -
+        name: rx-errors
+        type: u32
+      -
+        name: tx-errors
+        type: u32
+      -
+        name: rx-dropped
+        type: u32
+      -
+        name: tx-dropped
+        type: u32
+      -
+        name: multicast
+        type: u32
+      -
+        name: collisions
+        type: u32
+      -
+        name: rx-length-errors
+        type: u32
+      -
+        name: rx-over-errors
+        type: u32
+      -
+        name: rx-crc-errors
+        type: u32
+      -
+        name: rx-frame-errors
+        type: u32
+      -
+        name: rx-fifo-errors
+        type: u32
+      -
+        name: rx-missed-errors
+        type: u32
+      -
+        name: tx-aborted-errors
+        type: u32
+      -
+        name: tx-carrier-errors
+        type: u32
+      -
+        name: tx-fifo-errors
+        type: u32
+      -
+        name: tx-heartbeat-errors
+        type: u32
+      -
+        name: tx-window-errors
+        type: u32
+      -
+        name: rx-compressed
+        type: u32
+      -
+        name: tx-compressed
+        type: u32
+      -
+        name: rx-nohandler
+        type: u32
+  -
+    name: rtnl-link-stats64
+    type: struct
+    members:
+      -
+        name: rx-packets
+        type: u64
+      -
+        name: tx-packets
+        type: u64
+      -
+        name: rx-bytes
+        type: u64
+      -
+        name: tx-bytes
+        type: u64
+      -
+        name: rx-errors
+        type: u64
+      -
+        name: tx-errors
+        type: u64
+      -
+        name: rx-dropped
+        type: u64
+      -
+        name: tx-dropped
+        type: u64
+      -
+        name: multicast
+        type: u64
+      -
+        name: collisions
+        type: u64
+      -
+        name: rx-length-errors
+        type: u64
+      -
+        name: rx-over-errors
+        type: u64
+      -
+        name: rx-crc-errors
+        type: u64
+      -
+        name: rx-frame-errors
+        type: u64
+      -
+        name: rx-fifo-errors
+        type: u64
+      -
+        name: rx-missed-errors
+        type: u64
+      -
+        name: tx-aborted-errors
+        type: u64
+      -
+        name: tx-carrier-errors
+        type: u64
+      -
+        name: tx-fifo-errors
+        type: u64
+      -
+        name: tx-heartbeat-errors
+        type: u64
+      -
+        name: tx-window-errors
+        type: u64
+      -
+        name: rx-compressed
+        type: u64
+      -
+        name: tx-compressed
+        type: u64
+      -
+        name: rx-nohandler
+        type: u64
+      -
+        name: rx-otherhost-dropped
+        type: u64
+  -
+    name: rtnl-link-ifmap
+    type: struct
+    members:
+      -
+        name: mem-start
+        type: u64
+      -
+        name: mem-end
+        type: u64
+      -
+        name: base-addr
+        type: u64
+      -
+        name: irq
+        type: u16
+      -
+        name: dma
+        type: u8
+      -
+        name: port
+        type: u8
+  -
+    name: ipv4-devconf
+    type: struct
+    members:
+      -
+        name: forwarding
+        type: u32
+      -
+        name: mc-forwarding
+        type: u32
+      -
+        name: proxy-arp
+        type: u32
+      -
+        name: accept-redirects
+        type: u32
+      -
+        name: secure-redirects
+        type: u32
+      -
+        name: send-redirects
+        type: u32
+      -
+        name: shared-media
+        type: u32
+      -
+        name: rp-filter
+        type: u32
+      -
+        name: accept-source-route
+        type: u32
+      -
+        name: bootp-relay
+        type: u32
+      -
+        name: log-martians
+        type: u32
+      -
+        name: tag
+        type: u32
+      -
+        name: arpfilter
+        type: u32
+      -
+        name: medium-id
+        type: u32
+      -
+        name: noxfrm
+        type: u32
+      -
+        name: nopolicy
+        type: u32
+      -
+        name: force-igmp-version
+        type: u32
+      -
+        name: arp-announce
+        type: u32
+      -
+        name: arp-ignore
+        type: u32
+      -
+        name: promote-secondaries
+        type: u32
+      -
+        name: arp-accept
+        type: u32
+      -
+        name: arp-notify
+        type: u32
+      -
+        name: accept-local
+        type: u32
+      -
+        name: src-vmark
+        type: u32
+      -
+        name: proxy-arp-pvlan
+        type: u32
+      -
+        name: route-localnet
+        type: u32
+      -
+        name: igmpv2-unsolicited-report-interval
+        type: u32
+      -
+        name: igmpv3-unsolicited-report-interval
+        type: u32
+      -
+        name: ignore-routes-with-linkdown
+        type: u32
+      -
+        name: drop-unicast-in-l2-multicast
+        type: u32
+      -
+        name: drop-gratuitous-arp
+        type: u32
+      -
+        name: bc-forwarding
+        type: u32
+      -
+        name: arp-evict-nocarrier
+        type: u32
+  -
+    name: ipv6-devconf
+    type: struct
+    members:
+      -
+        name: forwarding
+        type: u32
+      -
+        name: hoplimit
+        type: u32
+      -
+        name: mtu6
+        type: u32
+      -
+        name: accept-ra
+        type: u32
+      -
+        name: accept-redirects
+        type: u32
+      -
+        name: autoconf
+        type: u32
+      -
+        name: dad-transmits
+        type: u32
+      -
+        name: rtr-solicits
+        type: u32
+      -
+        name: rtr-solicit-interval
+        type: u32
+      -
+        name: rtr-solicit-delay
+        type: u32
+      -
+        name: use-tempaddr
+        type: u32
+      -
+        name: temp-valid-lft
+        type: u32
+      -
+        name: temp-prefered-lft
+        type: u32
+      -
+        name: regen-max-retry
+        type: u32
+      -
+        name: max-desync-factor
+        type: u32
+      -
+        name: max-addresses
+        type: u32
+      -
+        name: force-mld-version
+        type: u32
+      -
+        name: accept-ra-defrtr
+        type: u32
+      -
+        name: accept-ra-pinfo
+        type: u32
+      -
+        name: accept-ra-rtr-pref
+        type: u32
+      -
+        name: rtr-probe-interval
+        type: u32
+      -
+        name: accept-ra-rt-info-max-plen
+        type: u32
+      -
+        name: proxy-ndp
+        type: u32
+      -
+        name: optimistic-dad
+        type: u32
+      -
+        name: accept-source-route
+        type: u32
+      -
+        name: mc-forwarding
+        type: u32
+      -
+        name: disable-ipv6
+        type: u32
+      -
+        name: accept-dad
+        type: u32
+      -
+        name: force-tllao
+        type: u32
+      -
+        name: ndisc-notify
+        type: u32
+      -
+        name: mldv1-unsolicited-report-interval
+        type: u32
+      -
+        name: mldv2-unsolicited-report-interval
+        type: u32
+      -
+        name: suppress-frag-ndisc
+        type: u32
+      -
+        name: accept-ra-from-local
+        type: u32
+      -
+        name: use-optimistic
+        type: u32
+      -
+        name: accept-ra-mtu
+        type: u32
+      -
+        name: stable-secret
+        type: u32
+      -
+        name: use-oif-addrs-only
+        type: u32
+      -
+        name: accept-ra-min-hop-limit
+        type: u32
+      -
+        name: ignore-routes-with-linkdown
+        type: u32
+      -
+        name: drop-unicast-in-l2-multicast
+        type: u32
+      -
+        name: drop-unsolicited-na
+        type: u32
+      -
+        name: keep-addr-on-down
+        type: u32
+      -
+        name: rtr-solicit-max-interval
+        type: u32
+      -
+        name: seg6-enabled
+        type: u32
+      -
+        name: seg6-require-hmac
+        type: u32
+      -
+        name: enhanced-dad
+        type: u32
+      -
+        name: addr-gen-mode
+        type: u8
+      -
+        name: disable-policy
+        type: u32
+      -
+        name: accept-ra-rt-info-min-plen
+        type: u32
+      -
+        name: ndisc-tclass
+        type: u32
+      -
+        name: rpl-seg-enabled
+        type: u32
+      -
+        name: ra-defrtr-metric
+        type: u32
+      -
+        name: ioam6-enabled
+        type: u32
+      -
+        name: ioam6-id
+        type: u32
+      -
+        name: ioam6-id-wide
+        type: u32
+      -
+        name: ndisc-evict-nocarrier
+        type: u32
+      -
+        name: accept-untracked-na
+        type: u32
+  -
+    name: ifla-icmp6-stats
+    type: struct
+    members:
+      -
+        name: inmsgs
+        type: u64
+      -
+        name: inerrors
+        type: u64
+      -
+        name: outmsgs
+        type: u64
+      -
+        name: outerrors
+        type: u64
+      -
+        name: csumerrors
+        type: u64
+      -
+        name: ratelimithost
+        type: u64
+  -
+    name: ifla-inet6-stats
+    type: struct
+    members:
+      -
+        name: inpkts
+        type: u64
+      -
+        name: inoctets
+        type: u64
+      -
+        name: indelivers
+        type: u64
+      -
+        name: outforwdatagrams
+        type: u64
+      -
+        name: outpkts
+        type: u64
+      -
+        name: outoctets
+        type: u64
+      -
+        name: inhdrerrors
+        type: u64
+      -
+        name: intoobigerrors
+        type: u64
+      -
+        name: innoroutes
+        type: u64
+      -
+        name: inaddrerrors
+        type: u64
+      -
+        name: inunknownprotos
+        type: u64
+      -
+        name: intruncatedpkts
+        type: u64
+      -
+        name: indiscards
+        type: u64
+      -
+        name: outdiscards
+        type: u64
+      -
+        name: outnoroutes
+        type: u64
+      -
+        name: reasmtimeout
+        type: u64
+      -
+        name: reasmreqds
+        type: u64
+      -
+        name: reasmoks
+        type: u64
+      -
+        name: reasmfails
+        type: u64
+      -
+        name: fragoks
+        type: u64
+      -
+        name: fragfails
+        type: u64
+      -
+        name: fragcreates
+        type: u64
+      -
+        name: inmcastpkts
+        type: u64
+      -
+        name: outmcastpkts
+        type: u64
+      -
+        name: inbcastpkts
+        type: u64
+      -
+        name: outbcastpkts
+        type: u64
+      -
+        name: inmcastoctets
+        type: u64
+      -
+        name: outmcastoctets
+        type: u64
+      -
+        name: inbcastoctets
+        type: u64
+      -
+        name: outbcastoctets
+        type: u64
+      -
+        name: csumerrors
+        type: u64
+      -
+        name: noectpkts
+        type: u64
+      -
+        name: ect1-pkts
+        type: u64
+      -
+        name: ect0-pkts
+        type: u64
+      -
+        name: cepkts
+        type: u64
+      -
+        name: reasm-overlaps
+        type: u64
+  - name: br-boolopt-multi
+    type: struct
+    members:
+      -
+        name: optval
+        type: u32
+      -
+        name: optmask
+        type: u32
+  -
+    name: if_stats_msg
+    type: struct
+    members:
+      -
+        name: family
+        type: u8
+      -
+        name: pad1
+        type: u8
+      -
+        name: pad2
+        type: u16
+      -
+        name: ifindex
+        type: u32
+      -
+        name: filter-mask
+        type: u32
+
+
+attribute-sets:
+  -
+    name: link-attrs
+    name-prefix: ifla-
+    attributes:
+      -
+        name: address
+        type: binary
+        display-hint: mac
+      -
+        name: broadcast
+        type: binary
+        display-hint: mac
+      -
+        name: ifname
+        type: string
+      -
+        name: mtu
+        type: u32
+      -
+        name: link
+        type: u32
+      -
+        name: qdisc
+        type: string
+      -
+        name: stats
+        type: binary
+        struct: rtnl-link-stats
+      -
+        name: cost
+        type: string
+      -
+        name: priority
+        type: string
+      -
+        name: master
+        type: u32
+      -
+        name: wireless
+        type: string
+      -
+        name: protinfo
+        type: string
+      -
+        name: txqlen
+        type: u32
+      -
+        name: map
+        type: binary
+        struct: rtnl-link-ifmap
+      -
+        name: weight
+        type: u32
+      -
+        name: operstate
+        type: u8
+      -
+        name: linkmode
+        type: u8
+      -
+        name: linkinfo
+        type: nest
+        nested-attributes: linkinfo-attrs
+      -
+        name: net-ns-pid
+        type: u32
+      -
+        name: ifalias
+        type: string
+      -
+        name: num-vf
+        type: u32
+      -
+        name: vfinfo-list
+        type: nest
+        nested-attributes: vfinfo-attrs
+      -
+        name: stats64
+        type: binary
+        struct: rtnl-link-stats64
+      -
+        name: vf-ports
+        type: nest
+        nested-attributes: vf-ports-attrs
+      -
+        name: port-self
+        type: nest
+        nested-attributes: port-self-attrs
+      -
+        name: af-spec
+        type: nest
+        nested-attributes: af-spec-attrs
+      -
+        name: group
+        type: u32
+      -
+        name: net-ns-fd
+        type: u32
+      -
+        name: ext-mask
+        type: u32
+      -
+        name: promiscuity
+        type: u32
+      -
+        name: num-tx-queues
+        type: u32
+      -
+        name: num-rx-queues
+        type: u32
+      -
+        name: carrier
+        type: u8
+      -
+        name: phys-port-id
+        type: binary
+      -
+        name: carrier-changes
+        type: u32
+      -
+        name: phys-switch-id
+        type: binary
+      -
+        name: link-netnsid
+        type: s32
+      -
+        name: phys-port-name
+        type: string
+      -
+        name: proto-down
+        type: u8
+      -
+        name: gso-max-segs
+        type: u32
+      -
+        name: gso-max-size
+        type: u32
+      -
+        name: pad
+        type: pad
+      -
+        name: xdp
+        type: nest
+        nested-attributes: xdp-attrs
+      -
+        name: event
+        type: u32
+      -
+        name: new-netnsid
+        type: s32
+      -
+        name: target-netnsid
+        type: s32
+      -
+        name: carrier-up-count
+        type: u32
+      -
+        name: carrier-down-count
+        type: u32
+      -
+        name: new-ifindex
+        type: s32
+      -
+        name: min-mtu
+        type: u32
+      -
+        name: max-mtu
+        type: u32
+      -
+        name: prop-list
+        type: nest
+        nested-attributes: link-attrs
+      -
+        name: alt-ifname
+        type: string
+        multi-attr: true
+      -
+        name: perm-address
+        type: binary
+        display-hint: mac
+      -
+        name: proto-down-reason
+        type: string
+      -
+        name: parent-dev-name
+        type: string
+      -
+        name: parent-dev-bus-name
+        type: string
+      -
+        name: gro-max-size
+        type: u32
+      -
+        name: tso-max-size
+        type: u32
+      -
+        name: tso-max-segs
+        type: u32
+      -
+        name: allmulti
+        type: u32
+      -
+        name: devlink-port
+        type: binary
+      -
+        name: gso-ipv4-max-size
+        type: u32
+      -
+        name: gro-ipv4-max-size
+        type: u32
+  -
+    name: af-spec-attrs
+    attributes:
+      -
+        name: "inet"
+        type: nest
+        value: 2
+        nested-attributes: ifla-attrs
+      -
+        name: "inet6"
+        type: nest
+        value: 10
+        nested-attributes: ifla6-attrs
+      -
+        name: "mctp"
+        type: nest
+        value: 45
+        nested-attributes: mctp-attrs
+  -
+    name: vfinfo-attrs
+    attributes: []
+  -
+    name: vf-ports-attrs
+    attributes: []
+  -
+    name: port-self-attrs
+    attributes: []
+  -
+    name: linkinfo-attrs
+    attributes:
+      -
+        name: kind
+        type: string
+      -
+        name: data
+        type: binary
+        # kind specific nest, e.g. linkinfo-bridge-attrs
+      -
+        name: xstats
+        type: binary
+      -
+        name: slave-kind
+        type: string
+      -
+        name: slave-data
+        type: binary
+        # kind specific nest
+  -
+    name: linkinfo-bridge-attrs
+    attributes:
+      -
+        name: forward-delay
+        type: u32
+      -
+        name: hello-time
+        type: u32
+      -
+        name: max-age
+        type: u32
+      -
+        name: ageing-time
+        type: u32
+      -
+        name: stp-state
+        type: u32
+      -
+        name: priority
+        type: u16
+      -
+        name: vlan-filtering
+        type: u8
+      -
+        name: vlan-protocol
+        type: u16
+      -
+        name: group-fwd-mask
+        type: u16
+      -
+        name: root-id
+        type: binary
+      -
+        name: bridge-id
+        type: binary
+      -
+        name: root-port
+        type: u16
+      -
+        name: root-path-cost
+        type: u32
+      -
+        name: topology-change
+        type: u8
+      -
+        name: topology-change-detected
+        type: u8
+      -
+        name: hello-timer
+        type: u64
+      -
+        name: tcn-timer
+        type: u64
+      -
+        name: topology-change-timer
+        type: u64
+      -
+        name: gc-timer
+        type: u64
+      -
+        name: group-addr
+        type: binary
+      -
+        name: fdb-flush
+        type: binary
+      -
+        name: mcast-router
+        type: u8
+      -
+        name: mcast-snooping
+        type: u8
+      -
+        name: mcast-query-use-ifaddr
+        type: u8
+      -
+        name: mcast-querier
+        type: u8
+      -
+        name: mcast-hash-elasticity
+        type: u32
+      -
+        name: mcast-hash-max
+        type: u32
+      -
+        name: mcast-last-member-cnt
+        type: u32
+      -
+        name: mcast-startup-query-cnt
+        type: u32
+      -
+        name: mcast-last-member-intvl
+        type: u64
+      -
+        name: mcast-membership-intvl
+        type: u64
+      -
+        name: mcast-querier-intvl
+        type: u64
+      -
+        name: mcast-query-intvl
+        type: u64
+      -
+        name: mcast-query-response-intvl
+        type: u64
+      -
+        name: mcast-startup-query-intvl
+        type: u64
+      -
+        name: nf-call-iptables
+        type: u8
+      -
+        name: nf-call-ip6-tables
+        type: u8
+      -
+        name: nf-call-arptables
+        type: u8
+      -
+        name: vlan-default-pvid
+        type: u16
+      -
+        name: pad
+        type: pad
+      -
+        name: vlan-stats-enabled
+        type: u8
+      -
+        name: mcast-stats-enabled
+        type: u8
+      -
+        name: mcast-igmp-version
+        type: u8
+      -
+        name: mcast-mld-version
+        type: u8
+      -
+        name: vlan-stats-per-port
+        type: u8
+      -
+        name: multi-boolopt
+        type: binary
+        struct: br-boolopt-multi
+      -
+        name: mcast-querier-state
+        type: binary
+  -
+    name: xdp-attrs
+    attributes:
+      -
+        name: fd
+        type: s32
+      -
+        name: attached
+        type: u8
+      -
+        name: flags
+        type: u32
+      -
+        name: prog-id
+        type: u32
+      -
+        name: drv-prog-id
+        type: u32
+      -
+        name: skb-prog-id
+        type: u32
+      -
+        name: hw-prog-id
+        type: u32
+      -
+        name: expected-fd
+        type: s32
+  -
+    name: ifla-attrs
+    attributes:
+      -
+        name: conf
+        type: binary
+        struct: ipv4-devconf
+  -
+    name: ifla6-attrs
+    attributes:
+      -
+        name: flags
+        type: u32
+      -
+        name: conf
+        type: binary
+        struct: ipv6-devconf
+      -
+        name: stats
+        type: binary
+        struct: ifla-inet6-stats
+      -
+        name: mcast
+        type: binary
+      -
+        name: cacheinfo
+        type: binary
+        struct: ifla-cacheinfo
+      -
+        name: icmp6-stats
+        type: binary
+        struct: ifla-icmp6-stats
+      -
+        name: token
+        type: binary
+      -
+        name: addr-gen-mode
+        type: u8
+      -
+        name: ra-mtu
+        type: u32
+  -
+    name: mctp-attrs
+    attributes:
+      -
+        name: mctp-net
+        type: u32
+  -
+    name: stats-attrs
+    name-prefix: ifla-stats-
+    attributes:
+      -
+        name: link-64
+        type: binary
+        struct: rtnl-link-stats64
+      -
+        name: link-xstats
+        type: binary
+      -
+        name: link-xstats-slave
+        type: binary
+      -
+        name: link-offload-xstats
+        type: nest
+        nested-attributes: link-offload-xstats
+      -
+        name: af-spec
+        type: binary
+  -
+    name: link-offload-xstats
+    attributes:
+      -
+        name: cpu-hit
+        type: binary
+      -
+        name: hw-s-info
+        type: array-nest
+        nested-attributes: hw-s-info-one
+      -
+        name: l3-stats
+        type: binary
+  -
+    name: hw-s-info-one
+    attributes:
+      -
+        name: request
+        type: u8
+      -
+        name: used
+        type: u8
+
+operations:
+  enum-model: directional
+  list:
+    -
+      name: newlink
+      doc: Create a new link.
+      attribute-set: link-attrs
+      fixed-header: ifinfomsg
+      do:
+        request:
+          value: 16
+          attributes: &link-new-attrs
+            - ifi-index
+            - ifname
+            - net-ns-pid
+            - net-ns-fd
+            - target-netnsid
+            - link-netnsid
+            - linkinfo
+            - group
+            - num-tx-queues
+            - num-rx-queues
+            - address
+            - broadcast
+            - mtu
+            - txqlen
+            - operstate
+            - linkmode
+            - group
+            - gso-max-size
+            - gso-max-segs
+            - gro-max-size
+            - gso-ipv4-max-size
+            - gro-ipv4-max-size
+            - af-spec
+    -
+      name: dellink
+      doc: Delete an existing link.
+      attribute-set: link-attrs
+      fixed-header: ifinfomsg
+      do:
+        request:
+          value: 17
+          attributes:
+            - ifi-index
+            - ifname
+    -
+      name: getlink
+      doc: Get / dump information about a link.
+      attribute-set: link-attrs
+      fixed-header: ifinfomsg
+      do:
+        request:
+          value: 18
+          attributes:
+            - ifi-index
+            - ifname
+            - alt-ifname
+            - ext-mask
+            - target-netnsid
+        reply:
+          value: 16
+          attributes: &link-all-attrs
+            - ifi-family
+            - ifi-type
+            - ifi-index
+            - ifi-flags
+            - ifi-change
+            - address
+            - broadcast
+            - ifname
+            - mtu
+            - link
+            - qdisc
+            - stats
+            - cost
+            - priority
+            - master
+            - wireless
+            - protinfo
+            - txqlen
+            - map
+            - weight
+            - operstate
+            - linkmode
+            - linkinfo
+            - net-ns-pid
+            - ifalias
+            - num-vf
+            - vfinfo-list
+            - stats64
+            - vf-ports
+            - port-self
+            - af-spec
+            - group
+            - net-ns-fd
+            - ext-mask
+            - promiscuity
+            - num-tx-queues
+            - num-rx-queues
+            - carrier
+            - phys-port-id
+            - carrier-changes
+            - phys-switch-id
+            - link-netnsid
+            - phys-port-name
+            - proto-down
+            - gso-max-segs
+            - gso-max-size
+            - pad
+            - xdp
+            - event
+            - new-netnsid
+            - if-netnsid
+            - target-netnsid
+            - carrier-up-count
+            - carrier-down-count
+            - new-ifindex
+            - min-mtu
+            - max-mtu
+            - prop-list
+            - alt-ifname
+            - perm-address
+            - proto-down-reason
+            - parent-dev-name
+            - parent-dev-bus-name
+            - gro-max-size
+            - tso-max-size
+            - tso-max-segs
+            - allmulti
+            - devlink-port
+            - gso-ipv4-max-size
+            - gro-ipv4-max-size
+      dump:
+        request:
+          value: 18
+          attributes:
+            - target-netnsid
+            - ext-mask
+            - master
+            - linkinfo
+        reply:
+          value: 16
+          attributes: *link-all-attrs
+    -
+      name: setlink
+      doc: Set information about a link.
+      attribute-set: link-attrs
+      fixed-header: ifinfomsg
+      do:
+        request:
+          value: 19
+          attributes: *link-all-attrs
+    -
+      name: getstats
+      doc: Get / dump link stats.
+      attribute-set: stats-attrs
+      fixed-header: if_stats_msg
+      do:
+        request:
+          value: 94
+          attributes:
+            - ifindex
+        reply:
+          value: 92
+          attributes: &link-stats-attrs
+            - family
+            - ifindex
+            - filter-mask
+            - link-64
+            - link-xstats
+            - link-xstats-slave
+            - link-offload-xstats
+            - af-spec
+      dump:
+        request:
+          value: 94
+        reply:
+          value: 92
+          attributes: *link-stats-attrs
+
+mcast-groups:
+  list:
+    -
+      name: rtnlgrp-link
+      value: 1
+    -
+      name: rtnlgrp-stats
+      value: 36
-- 
GitLab


From 023289b4f582820f3124fa7ff42a61959fe7dea6 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 25 Aug 2023 13:27:55 +0100
Subject: [PATCH 1755/1806] doc/netlink: Add spec for rt route messages

Add schema for rt route with support for getroute, newroute and
delroute.

Routes can be dumped with filter attributes like this:

./tools/net/ynl/cli.py \
    --spec Documentation/netlink/specs/rt_route.yaml \
    --dump getroute --json '{"rtm-family": 2, "rtm-table": 254}'

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230825122756.7603-13-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt_route.yaml | 327 ++++++++++++++++++++++
 1 file changed, 327 insertions(+)
 create mode 100644 Documentation/netlink/specs/rt_route.yaml

diff --git a/Documentation/netlink/specs/rt_route.yaml b/Documentation/netlink/specs/rt_route.yaml
new file mode 100644
index 0000000000000..f4368be0caed9
--- /dev/null
+++ b/Documentation/netlink/specs/rt_route.yaml
@@ -0,0 +1,327 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+
+name: rt-route
+protocol: netlink-raw
+protonum: 0
+
+doc:
+  Route configuration over rtnetlink.
+
+definitions:
+  -
+    name: rtm-type
+    name-prefix: rtn-
+    type: enum
+    entries:
+      - unspec
+      - unicast
+      - local
+      - broadcast
+      - anycast
+      - multicast
+      - blackhole
+      - unreachable
+      - prohibit
+      - throw
+      - nat
+      - xresolve
+  -
+    name: rtmsg
+    type: struct
+    members:
+      -
+        name: rtm-family
+        type: u8
+      -
+        name: rtm-dst-len
+        type: u8
+      -
+        name: rtm-src-len
+        type: u8
+      -
+        name: rtm-tos
+        type: u8
+      -
+        name: rtm-table
+        type: u8
+      -
+        name: rtm-protocol
+        type: u8
+      -
+        name: rtm-scope
+        type: u8
+      -
+        name: rtm-type
+        type: u8
+        enum: rtm-type
+      -
+        name: rtm-flags
+        type: u32
+  -
+    name: rta-cacheinfo
+    type: struct
+    members:
+      -
+        name: rta-clntref
+        type: u32
+      -
+        name: rta-lastuse
+        type: u32
+      -
+        name: rta-expires
+        type: u32
+      -
+        name: rta-error
+        type: u32
+      -
+        name: rta-used
+        type: u32
+
+attribute-sets:
+  -
+    name: route-attrs
+    attributes:
+      -
+        name: rta-dst
+        type: binary
+        display-hint: ipv4
+      -
+        name: rta-src
+        type: binary
+        display-hint: ipv4
+      -
+        name: rta-iif
+        type: u32
+      -
+        name: rta-oif
+        type: u32
+      -
+        name: rta-gateway
+        type: binary
+        display-hint: ipv4
+      -
+        name: rta-priority
+        type: u32
+      -
+        name: rta-prefsrc
+        type: binary
+        display-hint: ipv4
+      -
+        name: rta-metrics
+        type: nest
+        nested-attributes: rta-metrics
+      -
+        name: rta-multipath
+        type: binary
+      -
+        name: rta-protoinfo # not used
+        type: binary
+      -
+        name: rta-flow
+        type: u32
+      -
+        name: rta-cacheinfo
+        type: binary
+        struct: rta-cacheinfo
+      -
+        name: rta-session # not used
+        type: binary
+      -
+        name: rta-mp-algo # not used
+        type: binary
+      -
+        name: rta-table
+        type: u32
+      -
+        name: rta-mark
+        type: u32
+      -
+        name: rta-mfc-stats
+        type: binary
+      -
+        name: rta-via
+        type: binary
+      -
+        name: rta-newdst
+        type: binary
+      -
+        name: rta-pref
+        type: u8
+      -
+        name: rta-encap-type
+        type: u16
+      -
+        name: rta-encap
+        type: binary # tunnel specific nest
+      -
+        name: rta-expires
+        type: u32
+      -
+        name: rta-pad
+        type: binary
+      -
+        name: rta-uid
+        type: u32
+      -
+        name: rta-ttl-propagate
+        type: u8
+      -
+        name: rta-ip-proto
+        type: u8
+      -
+        name: rta-sport
+        type: u16
+      -
+        name: rta-dport
+        type: u16
+      -
+        name: rta-nh-id
+        type: u32
+  -
+    name: rta-metrics
+    attributes:
+      -
+        name: rtax-unspec
+        type: unused
+        value: 0
+      -
+        name: rtax-lock
+        type: u32
+      -
+        name: rtax-mtu
+        type: u32
+      -
+        name: rtax-window
+        type: u32
+      -
+        name: rtax-rtt
+        type: u32
+      -
+        name: rtax-rttvar
+        type: u32
+      -
+        name: rtax-ssthresh
+        type: u32
+      -
+        name: rtax-cwnd
+        type: u32
+      -
+        name: rtax-advmss
+        type: u32
+      -
+        name: rtax-reordering
+        type: u32
+      -
+        name: rtax-hoplimit
+        type: u32
+      -
+        name: rtax-initcwnd
+        type: u32
+      -
+        name: rtax-features
+        type: u32
+      -
+        name: rtax-rto-min
+        type: u32
+      -
+        name: rtax-initrwnd
+        type: u32
+      -
+        name: rtax-quickack
+        type: u32
+      -
+        name: rtax-cc-algo
+        type: string
+      -
+        name: rtax-fastopen-no-cookie
+        type: u32
+
+operations:
+  enum-model: directional
+  list:
+    -
+      name: getroute
+      doc: Dump route information.
+      attribute-set: route-attrs
+      fixed-header: rtmsg
+      do:
+        request:
+          value: 26
+          attributes:
+            - rtm-family
+            - rta-src
+            - rtm-src-len
+            - rta-dst
+            - rtm-dst-len
+            - rta-iif
+            - rta-oif
+            - rta-ip-proto
+            - rta-sport
+            - rta-dport
+            - rta-mark
+            - rta-uid
+        reply:
+          value: 24
+          attributes: &all-route-attrs
+            - rtm-family
+            - rtm-dst-len
+            - rtm-src-len
+            - rtm-tos
+            - rtm-table
+            - rtm-protocol
+            - rtm-scope
+            - rtm-type
+            - rtm-flags
+            - rta-dst
+            - rta-src
+            - rta-iif
+            - rta-oif
+            - rta-gateway
+            - rta-priority
+            - rta-prefsrc
+            - rta-metrics
+            - rta-multipath
+            - rta-flow
+            - rta-cacheinfo
+            - rta-table
+            - rta-mark
+            - rta-mfc-stats
+            - rta-via
+            - rta-newdst
+            - rta-pref
+            - rta-encap-type
+            - rta-encap
+            - rta-expires
+            - rta-pad
+            - rta-uid
+            - rta-ttl-propagate
+            - rta-ip-proto
+            - rta-sport
+            - rta-dport
+            - rta-nh-id
+      dump:
+        request:
+          value: 26
+          attributes:
+            - rtm-family
+        reply:
+          value: 24
+          attributes: *all-route-attrs
+    -
+      name: newroute
+      doc: Create a new route
+      attribute-set: route-attrs
+      fixed-header: rtmsg
+      do:
+        request:
+          value: 24
+          attributes: *all-route-attrs
+    -
+      name: delroute
+      doc: Delete an existing route
+      attribute-set: route-attrs
+      fixed-header: rtmsg
+      do:
+        request:
+          value: 25
+          attributes: *all-route-attrs
-- 
GitLab


From 84e306b0834077f5bd9fb6b9e37298b45c3f5a09 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:06 +0200
Subject: [PATCH 1756/1806] selftests: tls: add test variants for aria-gcm

Only supported for TLS1.2.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/ccf4a4d3f3820f8ff30431b7629f5210cb33fa89.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config |  1 +
 tools/testing/selftests/net/tls.c  | 24 ++++++++++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index cd3cc52c59b4c..8da562a9ae87e 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -51,3 +51,4 @@ CONFIG_AMT=m
 CONFIG_VXLAN=m
 CONFIG_IP_SCTP=m
 CONFIG_NETFILTER_XT_MATCH_POLICY=m
+CONFIG_CRYPTO_ARIA=y
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 4b63708c6a818..95bef2be48cd7 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -36,6 +36,8 @@ struct tls_crypto_info_keys {
 		struct tls12_crypto_info_sm4_ccm sm4ccm;
 		struct tls12_crypto_info_aes_ccm_128 aesccm128;
 		struct tls12_crypto_info_aes_gcm_256 aesgcm256;
+		struct tls12_crypto_info_aria_gcm_128 ariagcm128;
+		struct tls12_crypto_info_aria_gcm_256 ariagcm256;
 	};
 	size_t len;
 };
@@ -76,6 +78,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type,
 		tls12->aesgcm256.info.version = tls_version;
 		tls12->aesgcm256.info.cipher_type = cipher_type;
 		break;
+	case TLS_CIPHER_ARIA_GCM_128:
+		tls12->len = sizeof(struct tls12_crypto_info_aria_gcm_128);
+		tls12->ariagcm128.info.version = tls_version;
+		tls12->ariagcm128.info.cipher_type = cipher_type;
+		break;
+	case TLS_CIPHER_ARIA_GCM_256:
+		tls12->len = sizeof(struct tls12_crypto_info_aria_gcm_256);
+		tls12->ariagcm256.info.version = tls_version;
+		tls12->ariagcm256.info.cipher_type = cipher_type;
+		break;
 	default:
 		break;
 	}
@@ -312,6 +324,18 @@ FIXTURE_VARIANT_ADD(tls, 13_nopad)
 	.nopad = true,
 };
 
+FIXTURE_VARIANT_ADD(tls, 12_aria_gcm)
+{
+	.tls_version = TLS_1_2_VERSION,
+	.cipher_type = TLS_CIPHER_ARIA_GCM_128,
+};
+
+FIXTURE_VARIANT_ADD(tls, 12_aria_gcm_256)
+{
+	.tls_version = TLS_1_2_VERSION,
+	.cipher_type = TLS_CIPHER_ARIA_GCM_256,
+};
+
 FIXTURE_SETUP(tls)
 {
 	struct tls_crypto_info_keys tls12;
-- 
GitLab


From f27ad62fe38cf7c0a561628734f348217777127b Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:07 +0200
Subject: [PATCH 1757/1806] selftests: tls: add getsockopt test

The kernel accepts fetching either just the version and cipher type,
or exactly the per-cipher struct. Also check that getsockopt returns
what we just passed to the kernel.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/81a007ca13de9a74f4af45635d06682cdb385a54.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 35 +++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 95bef2be48cd7..0da6952a047a0 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -30,6 +30,7 @@ static int fips_enabled;
 
 struct tls_crypto_info_keys {
 	union {
+		struct tls_crypto_info crypto_info;
 		struct tls12_crypto_info_aes_gcm_128 aes128;
 		struct tls12_crypto_info_chacha20_poly1305 chacha20;
 		struct tls12_crypto_info_sm4_gcm sm4gcm;
@@ -1496,6 +1497,40 @@ TEST_F(tls, shutdown_reuse)
 	EXPECT_EQ(errno, EISCONN);
 }
 
+TEST_F(tls, getsockopt)
+{
+	struct tls_crypto_info_keys expect, get;
+	socklen_t len;
+
+	/* get only the version/cipher */
+	len = sizeof(struct tls_crypto_info);
+	memrnd(&get, sizeof(get));
+	EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), 0);
+	EXPECT_EQ(len, sizeof(struct tls_crypto_info));
+	EXPECT_EQ(get.crypto_info.version, variant->tls_version);
+	EXPECT_EQ(get.crypto_info.cipher_type, variant->cipher_type);
+
+	/* get the full crypto_info */
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &expect);
+	len = expect.len;
+	memrnd(&get, sizeof(get));
+	EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), 0);
+	EXPECT_EQ(len, expect.len);
+	EXPECT_EQ(get.crypto_info.version, variant->tls_version);
+	EXPECT_EQ(get.crypto_info.cipher_type, variant->cipher_type);
+	EXPECT_EQ(memcmp(&get, &expect, expect.len), 0);
+
+	/* short get should fail */
+	len = sizeof(struct tls_crypto_info) - 1;
+	EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* partial get of the cipher data should fail */
+	len = expect.len - 1;
+	EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), -1);
+	EXPECT_EQ(errno, EINVAL);
+}
+
 FIXTURE(tls_err)
 {
 	int fd, cfd;
-- 
GitLab


From 4bfb6224ed80ca2df13cff391fecded00cc072ee Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:08 +0200
Subject: [PATCH 1758/1806] selftests: tls: test some invalid inputs for
 setsockopt

This test will need to be updated if new ciphers are added.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/bfcfa9cffda56d2064296ab7c99a05775dd4c28e.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 0da6952a047a0..297d972558fba 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -241,6 +241,31 @@ TEST_F(tls_basic, base_base)
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 };
 
+TEST_F(tls_basic, bad_cipher)
+{
+	struct tls_crypto_info_keys tls12;
+
+	tls12.crypto_info.version = 200;
+	tls12.crypto_info.cipher_type = TLS_CIPHER_AES_GCM_128;
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1);
+
+	tls12.crypto_info.version = TLS_1_2_VERSION;
+	tls12.crypto_info.cipher_type = 50;
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1);
+
+	tls12.crypto_info.version = TLS_1_2_VERSION;
+	tls12.crypto_info.cipher_type = 59;
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1);
+
+	tls12.crypto_info.version = TLS_1_2_VERSION;
+	tls12.crypto_info.cipher_type = 10;
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1);
+
+	tls12.crypto_info.version = TLS_1_2_VERSION;
+	tls12.crypto_info.cipher_type = 70;
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1);
+}
+
 FIXTURE(tls)
 {
 	int fd, cfd;
-- 
GitLab


From fd0fc6fdd8896a195cb7b0210a5ee46774718fc8 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:09 +0200
Subject: [PATCH 1759/1806] tls: move tls_cipher_size_desc to net/tls/tls.h

It's only used in net/tls/*, no need to bloat include/net/tls.h.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/dd9fad80415e5b3575b41f56b331871038362eab.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tls.h | 10 ----------
 net/tls/tls.h     | 10 ++++++++++
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 06fca91603465..a2b44578dcb75 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -51,16 +51,6 @@
 
 struct tls_rec;
 
-struct tls_cipher_size_desc {
-	unsigned int iv;
-	unsigned int key;
-	unsigned int salt;
-	unsigned int tag;
-	unsigned int rec_seq;
-};
-
-extern const struct tls_cipher_size_desc tls_cipher_size_desc[];
-
 /* Maximum data size carried in a TLS record */
 #define TLS_MAX_PAYLOAD_SIZE		((size_t)1 << 14)
 
diff --git a/net/tls/tls.h b/net/tls/tls.h
index 164d6a955e26a..7aae92972e004 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -51,6 +51,16 @@
 #define TLS_DEC_STATS(net, field)				\
 	SNMP_DEC_STATS((net)->mib.tls_statistics, field)
 
+struct tls_cipher_size_desc {
+	unsigned int iv;
+	unsigned int key;
+	unsigned int salt;
+	unsigned int tag;
+	unsigned int rec_seq;
+};
+
+extern const struct tls_cipher_size_desc tls_cipher_size_desc[];
+
 /* TLS records are maintained in 'struct tls_rec'. It stores the memory pages
  * allocated or mapped for each TLS record. After encryption, the records are
  * stores in a linked list.
-- 
GitLab


From 200e23165109a173ffde3310dffa5ef5e502d97f Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:10 +0200
Subject: [PATCH 1760/1806] tls: add TLS_CIPHER_ARIA_GCM_* to
 tls_cipher_size_desc

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/b2e0fb79e6d0a4478be9bf33781dc9c9281c9d56.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index f550c84f34087..9843c2af994fe 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -73,6 +73,8 @@ const struct tls_cipher_size_desc tls_cipher_size_desc[] = {
 	CIPHER_SIZE_DESC(TLS_CIPHER_CHACHA20_POLY1305),
 	CIPHER_SIZE_DESC(TLS_CIPHER_SM4_GCM),
 	CIPHER_SIZE_DESC(TLS_CIPHER_SM4_CCM),
+	CIPHER_SIZE_DESC(TLS_CIPHER_ARIA_GCM_128),
+	CIPHER_SIZE_DESC(TLS_CIPHER_ARIA_GCM_256),
 };
 
 static const struct proto *saved_tcpv6_prot;
-- 
GitLab


From 037303d6760751fdb95ba62cf448ecbc1ac29c98 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:11 +0200
Subject: [PATCH 1761/1806] tls: reduce size of tls_cipher_size_desc

tls_cipher_size_desc indexes ciphers by their type, but we're not
using indices 0..50 of the array. Each struct tls_cipher_size_desc is
20B, so that's a lot of unused memory. We can reindex the array
starting at the lowest used cipher_type.

Introduce the get_cipher_size_desc helper to find the right item and
avoid out-of-bounds accesses, and make tls_cipher_size_desc's size
explicit so that gcc reminds us to update TLS_CIPHER_MIN/MAX when we
add a new cipher.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/5e054e370e240247a5d37881a1cd93a67c15f4ca.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls.h                 | 13 ++++++++++++-
 net/tls/tls_device.c          |  4 ++--
 net/tls/tls_device_fallback.c |  8 ++++----
 net/tls/tls_main.c            |  4 ++--
 4 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/net/tls/tls.h b/net/tls/tls.h
index 7aae92972e004..ea799ef77bf8f 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -59,7 +59,18 @@ struct tls_cipher_size_desc {
 	unsigned int rec_seq;
 };
 
-extern const struct tls_cipher_size_desc tls_cipher_size_desc[];
+#define TLS_CIPHER_MIN TLS_CIPHER_AES_GCM_128
+#define TLS_CIPHER_MAX TLS_CIPHER_ARIA_GCM_256
+extern const struct tls_cipher_size_desc tls_cipher_size_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN];
+
+static inline const struct tls_cipher_size_desc *get_cipher_size_desc(u16 cipher_type)
+{
+	if (cipher_type < TLS_CIPHER_MIN || cipher_type > TLS_CIPHER_MAX)
+		return NULL;
+
+	return &tls_cipher_size_desc[cipher_type - TLS_CIPHER_MIN];
+}
+
 
 /* TLS records are maintained in 'struct tls_rec'. It stores the memory pages
  * allocated or mapped for each TLS record. After encryption, the records are
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 2392d06845aaa..9bc42041c2ce4 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -898,7 +898,7 @@ tls_device_reencrypt(struct sock *sk, struct tls_context *tls_ctx)
 	default:
 		return -EINVAL;
 	}
-	cipher_sz = &tls_cipher_size_desc[tls_ctx->crypto_recv.info.cipher_type];
+	cipher_sz = get_cipher_size_desc(tls_ctx->crypto_recv.info.cipher_type);
 
 	rxm = strp_msg(tls_strp_msg(sw_ctx));
 	orig_buf = kmalloc(rxm->full_len + TLS_HEADER_SIZE + cipher_sz->iv,
@@ -1094,7 +1094,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 		rc = -EINVAL;
 		goto release_netdev;
 	}
-	cipher_sz = &tls_cipher_size_desc[crypto_info->cipher_type];
+	cipher_sz = get_cipher_size_desc(crypto_info->cipher_type);
 
 	/* Sanity-check the rec_seq_size for stack allocations */
 	if (cipher_sz->rec_seq > TLS_MAX_REC_SEQ_SIZE) {
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index b28c5e296dfd6..dd21fa4961b68 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -69,7 +69,7 @@ static int tls_enc_record(struct aead_request *aead_req,
 	default:
 		return -EINVAL;
 	}
-	cipher_sz = &tls_cipher_size_desc[prot->cipher_type];
+	cipher_sz = get_cipher_size_desc(prot->cipher_type);
 
 	buf_size = TLS_HEADER_SIZE + cipher_sz->iv;
 	len = min_t(int, *in_len, buf_size);
@@ -310,7 +310,7 @@ static void fill_sg_out(struct scatterlist sg_out[3], void *buf,
 			void *dummy_buf)
 {
 	const struct tls_cipher_size_desc *cipher_sz =
-		&tls_cipher_size_desc[tls_ctx->crypto_send.info.cipher_type];
+		get_cipher_size_desc(tls_ctx->crypto_send.info.cipher_type);
 
 	sg_set_buf(&sg_out[0], dummy_buf, sync_size);
 	sg_set_buf(&sg_out[1], nskb->data + tcp_payload_offset, payload_len);
@@ -348,7 +348,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx,
 	default:
 		goto free_req;
 	}
-	cipher_sz = &tls_cipher_size_desc[tls_ctx->crypto_send.info.cipher_type];
+	cipher_sz = get_cipher_size_desc(tls_ctx->crypto_send.info.cipher_type);
 	buf_len = cipher_sz->salt + cipher_sz->iv + TLS_AAD_SPACE_SIZE +
 		  sync_size + cipher_sz->tag;
 	buf = kmalloc(buf_len, GFP_ATOMIC);
@@ -495,7 +495,7 @@ int tls_sw_fallback_init(struct sock *sk,
 		rc = -EINVAL;
 		goto free_aead;
 	}
-	cipher_sz = &tls_cipher_size_desc[crypto_info->cipher_type];
+	cipher_sz = get_cipher_size_desc(crypto_info->cipher_type);
 
 	rc = crypto_aead_setkey(offload_ctx->aead_send, key, cipher_sz->key);
 	if (rc)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 9843c2af994fe..1bf04636948d7 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -58,7 +58,7 @@ enum {
 	TLS_NUM_PROTS,
 };
 
-#define CIPHER_SIZE_DESC(cipher) [cipher] = { \
+#define CIPHER_SIZE_DESC(cipher) [cipher - TLS_CIPHER_MIN] = {	\
 	.iv = cipher ## _IV_SIZE, \
 	.key = cipher ## _KEY_SIZE, \
 	.salt = cipher ## _SALT_SIZE, \
@@ -66,7 +66,7 @@ enum {
 	.rec_seq = cipher ## _REC_SEQ_SIZE, \
 }
 
-const struct tls_cipher_size_desc tls_cipher_size_desc[] = {
+const struct tls_cipher_size_desc tls_cipher_size_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN] = {
 	CIPHER_SIZE_DESC(TLS_CIPHER_AES_GCM_128),
 	CIPHER_SIZE_DESC(TLS_CIPHER_AES_GCM_256),
 	CIPHER_SIZE_DESC(TLS_CIPHER_AES_CCM_128),
-- 
GitLab


From 8db44ab26bebe969851468bea6072d9a094b2ace Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:12 +0200
Subject: [PATCH 1762/1806] tls: rename tls_cipher_size_desc to tls_cipher_desc

We're going to add other fields to it to fully describe a cipher, so
the "_size" name won't match the contents.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/76ca6c7686bd6d1534dfa188fb0f1f6fabebc791.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls.h                 |  8 +++----
 net/tls/tls_device.c          | 34 ++++++++++++++--------------
 net/tls/tls_device_fallback.c | 42 +++++++++++++++++------------------
 net/tls/tls_main.c            | 20 ++++++++---------
 4 files changed, 52 insertions(+), 52 deletions(-)

diff --git a/net/tls/tls.h b/net/tls/tls.h
index ea799ef77bf8f..d4b56ca9d2671 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -51,7 +51,7 @@
 #define TLS_DEC_STATS(net, field)				\
 	SNMP_DEC_STATS((net)->mib.tls_statistics, field)
 
-struct tls_cipher_size_desc {
+struct tls_cipher_desc {
 	unsigned int iv;
 	unsigned int key;
 	unsigned int salt;
@@ -61,14 +61,14 @@ struct tls_cipher_size_desc {
 
 #define TLS_CIPHER_MIN TLS_CIPHER_AES_GCM_128
 #define TLS_CIPHER_MAX TLS_CIPHER_ARIA_GCM_256
-extern const struct tls_cipher_size_desc tls_cipher_size_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN];
+extern const struct tls_cipher_desc tls_cipher_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN];
 
-static inline const struct tls_cipher_size_desc *get_cipher_size_desc(u16 cipher_type)
+static inline const struct tls_cipher_desc *get_cipher_desc(u16 cipher_type)
 {
 	if (cipher_type < TLS_CIPHER_MIN || cipher_type > TLS_CIPHER_MAX)
 		return NULL;
 
-	return &tls_cipher_size_desc[cipher_type - TLS_CIPHER_MIN];
+	return &tls_cipher_desc[cipher_type - TLS_CIPHER_MIN];
 }
 
 
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 9bc42041c2ce4..98885d872d4ce 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -884,7 +884,7 @@ static int
 tls_device_reencrypt(struct sock *sk, struct tls_context *tls_ctx)
 {
 	struct tls_sw_context_rx *sw_ctx = tls_sw_ctx_rx(tls_ctx);
-	const struct tls_cipher_size_desc *cipher_sz;
+	const struct tls_cipher_desc *cipher_desc;
 	int err, offset, copy, data_len, pos;
 	struct sk_buff *skb, *skb_iter;
 	struct scatterlist sg[1];
@@ -898,10 +898,10 @@ tls_device_reencrypt(struct sock *sk, struct tls_context *tls_ctx)
 	default:
 		return -EINVAL;
 	}
-	cipher_sz = get_cipher_size_desc(tls_ctx->crypto_recv.info.cipher_type);
+	cipher_desc = get_cipher_desc(tls_ctx->crypto_recv.info.cipher_type);
 
 	rxm = strp_msg(tls_strp_msg(sw_ctx));
-	orig_buf = kmalloc(rxm->full_len + TLS_HEADER_SIZE + cipher_sz->iv,
+	orig_buf = kmalloc(rxm->full_len + TLS_HEADER_SIZE + cipher_desc->iv,
 			   sk->sk_allocation);
 	if (!orig_buf)
 		return -ENOMEM;
@@ -917,8 +917,8 @@ tls_device_reencrypt(struct sock *sk, struct tls_context *tls_ctx)
 
 	sg_init_table(sg, 1);
 	sg_set_buf(&sg[0], buf,
-		   rxm->full_len + TLS_HEADER_SIZE + cipher_sz->iv);
-	err = skb_copy_bits(skb, offset, buf, TLS_HEADER_SIZE + cipher_sz->iv);
+		   rxm->full_len + TLS_HEADER_SIZE + cipher_desc->iv);
+	err = skb_copy_bits(skb, offset, buf, TLS_HEADER_SIZE + cipher_desc->iv);
 	if (err)
 		goto free_buf;
 
@@ -929,7 +929,7 @@ tls_device_reencrypt(struct sock *sk, struct tls_context *tls_ctx)
 	else
 		err = 0;
 
-	data_len = rxm->full_len - cipher_sz->tag;
+	data_len = rxm->full_len - cipher_desc->tag;
 
 	if (skb_pagelen(skb) > offset) {
 		copy = min_t(int, skb_pagelen(skb) - offset, data_len);
@@ -1046,7 +1046,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_prot_info *prot = &tls_ctx->prot_info;
-	const struct tls_cipher_size_desc *cipher_sz;
+	const struct tls_cipher_desc *cipher_desc;
 	struct tls_record_info *start_marker_record;
 	struct tls_offload_context_tx *offload_ctx;
 	struct tls_crypto_info *crypto_info;
@@ -1094,31 +1094,31 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 		rc = -EINVAL;
 		goto release_netdev;
 	}
-	cipher_sz = get_cipher_size_desc(crypto_info->cipher_type);
+	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
 
 	/* Sanity-check the rec_seq_size for stack allocations */
-	if (cipher_sz->rec_seq > TLS_MAX_REC_SEQ_SIZE) {
+	if (cipher_desc->rec_seq > TLS_MAX_REC_SEQ_SIZE) {
 		rc = -EINVAL;
 		goto release_netdev;
 	}
 
 	prot->version = crypto_info->version;
 	prot->cipher_type = crypto_info->cipher_type;
-	prot->prepend_size = TLS_HEADER_SIZE + cipher_sz->iv;
-	prot->tag_size = cipher_sz->tag;
+	prot->prepend_size = TLS_HEADER_SIZE + cipher_desc->iv;
+	prot->tag_size = cipher_desc->tag;
 	prot->overhead_size = prot->prepend_size + prot->tag_size;
-	prot->iv_size = cipher_sz->iv;
-	prot->salt_size = cipher_sz->salt;
-	ctx->tx.iv = kmalloc(cipher_sz->iv + cipher_sz->salt, GFP_KERNEL);
+	prot->iv_size = cipher_desc->iv;
+	prot->salt_size = cipher_desc->salt;
+	ctx->tx.iv = kmalloc(cipher_desc->iv + cipher_desc->salt, GFP_KERNEL);
 	if (!ctx->tx.iv) {
 		rc = -ENOMEM;
 		goto release_netdev;
 	}
 
-	memcpy(ctx->tx.iv + cipher_sz->salt, iv, cipher_sz->iv);
+	memcpy(ctx->tx.iv + cipher_desc->salt, iv, cipher_desc->iv);
 
-	prot->rec_seq_size = cipher_sz->rec_seq;
-	ctx->tx.rec_seq = kmemdup(rec_seq, cipher_sz->rec_seq, GFP_KERNEL);
+	prot->rec_seq_size = cipher_desc->rec_seq;
+	ctx->tx.rec_seq = kmemdup(rec_seq, cipher_desc->rec_seq, GFP_KERNEL);
 	if (!ctx->tx.rec_seq) {
 		rc = -ENOMEM;
 		goto free_iv;
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index dd21fa4961b68..cb224fb2a394d 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -55,7 +55,7 @@ static int tls_enc_record(struct aead_request *aead_req,
 			  struct tls_prot_info *prot)
 {
 	unsigned char buf[TLS_HEADER_SIZE + MAX_IV_SIZE];
-	const struct tls_cipher_size_desc *cipher_sz;
+	const struct tls_cipher_desc *cipher_desc;
 	struct scatterlist sg_in[3];
 	struct scatterlist sg_out[3];
 	unsigned int buf_size;
@@ -69,9 +69,9 @@ static int tls_enc_record(struct aead_request *aead_req,
 	default:
 		return -EINVAL;
 	}
-	cipher_sz = get_cipher_size_desc(prot->cipher_type);
+	cipher_desc = get_cipher_desc(prot->cipher_type);
 
-	buf_size = TLS_HEADER_SIZE + cipher_sz->iv;
+	buf_size = TLS_HEADER_SIZE + cipher_desc->iv;
 	len = min_t(int, *in_len, buf_size);
 
 	scatterwalk_copychunks(buf, in, len, 0);
@@ -85,11 +85,11 @@ static int tls_enc_record(struct aead_request *aead_req,
 	scatterwalk_pagedone(out, 1, 1);
 
 	len = buf[4] | (buf[3] << 8);
-	len -= cipher_sz->iv;
+	len -= cipher_desc->iv;
 
-	tls_make_aad(aad, len - cipher_sz->tag, (char *)&rcd_sn, buf[0], prot);
+	tls_make_aad(aad, len - cipher_desc->tag, (char *)&rcd_sn, buf[0], prot);
 
-	memcpy(iv + cipher_sz->salt, buf + TLS_HEADER_SIZE, cipher_sz->iv);
+	memcpy(iv + cipher_desc->salt, buf + TLS_HEADER_SIZE, cipher_desc->iv);
 
 	sg_init_table(sg_in, ARRAY_SIZE(sg_in));
 	sg_init_table(sg_out, ARRAY_SIZE(sg_out));
@@ -100,7 +100,7 @@ static int tls_enc_record(struct aead_request *aead_req,
 
 	*in_len -= len;
 	if (*in_len < 0) {
-		*in_len += cipher_sz->tag;
+		*in_len += cipher_desc->tag;
 		/* the input buffer doesn't contain the entire record.
 		 * trim len accordingly. The resulting authentication tag
 		 * will contain garbage, but we don't care, so we won't
@@ -121,7 +121,7 @@ static int tls_enc_record(struct aead_request *aead_req,
 		scatterwalk_pagedone(out, 1, 1);
 	}
 
-	len -= cipher_sz->tag;
+	len -= cipher_desc->tag;
 	aead_request_set_crypt(aead_req, sg_in, sg_out, len, iv);
 
 	rc = crypto_aead_encrypt(aead_req);
@@ -309,14 +309,14 @@ static void fill_sg_out(struct scatterlist sg_out[3], void *buf,
 			int sync_size,
 			void *dummy_buf)
 {
-	const struct tls_cipher_size_desc *cipher_sz =
-		get_cipher_size_desc(tls_ctx->crypto_send.info.cipher_type);
+	const struct tls_cipher_desc *cipher_desc =
+		get_cipher_desc(tls_ctx->crypto_send.info.cipher_type);
 
 	sg_set_buf(&sg_out[0], dummy_buf, sync_size);
 	sg_set_buf(&sg_out[1], nskb->data + tcp_payload_offset, payload_len);
 	/* Add room for authentication tag produced by crypto */
 	dummy_buf += sync_size;
-	sg_set_buf(&sg_out[2], dummy_buf, cipher_sz->tag);
+	sg_set_buf(&sg_out[2], dummy_buf, cipher_desc->tag);
 }
 
 static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx,
@@ -328,7 +328,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx,
 	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
 	int tcp_payload_offset = skb_tcp_all_headers(skb);
 	int payload_len = skb->len - tcp_payload_offset;
-	const struct tls_cipher_size_desc *cipher_sz;
+	const struct tls_cipher_desc *cipher_desc;
 	void *buf, *iv, *aad, *dummy_buf, *salt;
 	struct aead_request *aead_req;
 	struct sk_buff *nskb = NULL;
@@ -348,16 +348,16 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx,
 	default:
 		goto free_req;
 	}
-	cipher_sz = get_cipher_size_desc(tls_ctx->crypto_send.info.cipher_type);
-	buf_len = cipher_sz->salt + cipher_sz->iv + TLS_AAD_SPACE_SIZE +
-		  sync_size + cipher_sz->tag;
+	cipher_desc = get_cipher_desc(tls_ctx->crypto_send.info.cipher_type);
+	buf_len = cipher_desc->salt + cipher_desc->iv + TLS_AAD_SPACE_SIZE +
+		  sync_size + cipher_desc->tag;
 	buf = kmalloc(buf_len, GFP_ATOMIC);
 	if (!buf)
 		goto free_req;
 
 	iv = buf;
-	memcpy(iv, salt, cipher_sz->salt);
-	aad = buf + cipher_sz->salt + cipher_sz->iv;
+	memcpy(iv, salt, cipher_desc->salt);
+	aad = buf + cipher_desc->salt + cipher_desc->iv;
 	dummy_buf = aad + TLS_AAD_SPACE_SIZE;
 
 	nskb = alloc_skb(skb_headroom(skb) + skb->len, GFP_ATOMIC);
@@ -471,7 +471,7 @@ int tls_sw_fallback_init(struct sock *sk,
 			 struct tls_offload_context_tx *offload_ctx,
 			 struct tls_crypto_info *crypto_info)
 {
-	const struct tls_cipher_size_desc *cipher_sz;
+	const struct tls_cipher_desc *cipher_desc;
 	const u8 *key;
 	int rc;
 
@@ -495,13 +495,13 @@ int tls_sw_fallback_init(struct sock *sk,
 		rc = -EINVAL;
 		goto free_aead;
 	}
-	cipher_sz = get_cipher_size_desc(crypto_info->cipher_type);
+	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
 
-	rc = crypto_aead_setkey(offload_ctx->aead_send, key, cipher_sz->key);
+	rc = crypto_aead_setkey(offload_ctx->aead_send, key, cipher_desc->key);
 	if (rc)
 		goto free_aead;
 
-	rc = crypto_aead_setauthsize(offload_ctx->aead_send, cipher_sz->tag);
+	rc = crypto_aead_setauthsize(offload_ctx->aead_send, cipher_desc->tag);
 	if (rc)
 		goto free_aead;
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 1bf04636948d7..217c2aa004dc3 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -58,7 +58,7 @@ enum {
 	TLS_NUM_PROTS,
 };
 
-#define CIPHER_SIZE_DESC(cipher) [cipher - TLS_CIPHER_MIN] = {	\
+#define CIPHER_DESC(cipher) [cipher - TLS_CIPHER_MIN] = {	\
 	.iv = cipher ## _IV_SIZE, \
 	.key = cipher ## _KEY_SIZE, \
 	.salt = cipher ## _SALT_SIZE, \
@@ -66,15 +66,15 @@ enum {
 	.rec_seq = cipher ## _REC_SEQ_SIZE, \
 }
 
-const struct tls_cipher_size_desc tls_cipher_size_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN] = {
-	CIPHER_SIZE_DESC(TLS_CIPHER_AES_GCM_128),
-	CIPHER_SIZE_DESC(TLS_CIPHER_AES_GCM_256),
-	CIPHER_SIZE_DESC(TLS_CIPHER_AES_CCM_128),
-	CIPHER_SIZE_DESC(TLS_CIPHER_CHACHA20_POLY1305),
-	CIPHER_SIZE_DESC(TLS_CIPHER_SM4_GCM),
-	CIPHER_SIZE_DESC(TLS_CIPHER_SM4_CCM),
-	CIPHER_SIZE_DESC(TLS_CIPHER_ARIA_GCM_128),
-	CIPHER_SIZE_DESC(TLS_CIPHER_ARIA_GCM_256),
+const struct tls_cipher_desc tls_cipher_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN] = {
+	CIPHER_DESC(TLS_CIPHER_AES_GCM_128),
+	CIPHER_DESC(TLS_CIPHER_AES_GCM_256),
+	CIPHER_DESC(TLS_CIPHER_AES_CCM_128),
+	CIPHER_DESC(TLS_CIPHER_CHACHA20_POLY1305),
+	CIPHER_DESC(TLS_CIPHER_SM4_GCM),
+	CIPHER_DESC(TLS_CIPHER_SM4_CCM),
+	CIPHER_DESC(TLS_CIPHER_ARIA_GCM_128),
+	CIPHER_DESC(TLS_CIPHER_ARIA_GCM_256),
 };
 
 static const struct proto *saved_tcpv6_prot;
-- 
GitLab


From 176a3f50bc6a327c82c6b051b0bedd19917081a2 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:13 +0200
Subject: [PATCH 1763/1806] tls: extend tls_cipher_desc to fully describe the
 ciphers

- add nonce, usually equal to iv_size but not for chacha
 - add offsets into the crypto_info for each field
 - add algorithm name
 - add offloadable flag

Also add helpers to access each field of a crypto_info struct
described by a tls_cipher_desc.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/39d5f476d63c171097764e8d38f6f158b7c109ae.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls.h      | 32 ++++++++++++++++++++++++++++++++
 net/tls/tls_main.c | 41 ++++++++++++++++++++++++++++++++---------
 2 files changed, 64 insertions(+), 9 deletions(-)

diff --git a/net/tls/tls.h b/net/tls/tls.h
index d4b56ca9d2671..28a8c0e80e3c5 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -52,11 +52,19 @@
 	SNMP_DEC_STATS((net)->mib.tls_statistics, field)
 
 struct tls_cipher_desc {
+	unsigned int nonce;
 	unsigned int iv;
 	unsigned int key;
 	unsigned int salt;
 	unsigned int tag;
 	unsigned int rec_seq;
+	unsigned int iv_offset;
+	unsigned int key_offset;
+	unsigned int salt_offset;
+	unsigned int rec_seq_offset;
+	char *cipher_name;
+	bool offloadable;
+	size_t crypto_info;
 };
 
 #define TLS_CIPHER_MIN TLS_CIPHER_AES_GCM_128
@@ -71,6 +79,30 @@ static inline const struct tls_cipher_desc *get_cipher_desc(u16 cipher_type)
 	return &tls_cipher_desc[cipher_type - TLS_CIPHER_MIN];
 }
 
+static inline char *crypto_info_iv(struct tls_crypto_info *crypto_info,
+				   const struct tls_cipher_desc *cipher_desc)
+{
+	return (char *)crypto_info + cipher_desc->iv_offset;
+}
+
+static inline char *crypto_info_key(struct tls_crypto_info *crypto_info,
+				    const struct tls_cipher_desc *cipher_desc)
+{
+	return (char *)crypto_info + cipher_desc->key_offset;
+}
+
+static inline char *crypto_info_salt(struct tls_crypto_info *crypto_info,
+				     const struct tls_cipher_desc *cipher_desc)
+{
+	return (char *)crypto_info + cipher_desc->salt_offset;
+}
+
+static inline char *crypto_info_rec_seq(struct tls_crypto_info *crypto_info,
+					const struct tls_cipher_desc *cipher_desc)
+{
+	return (char *)crypto_info + cipher_desc->rec_seq_offset;
+}
+
 
 /* TLS records are maintained in 'struct tls_rec'. It stores the memory pages
  * allocated or mapped for each TLS record. After encryption, the records are
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 217c2aa004dc3..bbdf211cc8983 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -58,23 +58,46 @@ enum {
 	TLS_NUM_PROTS,
 };
 
-#define CIPHER_DESC(cipher) [cipher - TLS_CIPHER_MIN] = {	\
+#define __CIPHER_DESC(ci) \
+	.iv_offset = offsetof(struct ci, iv), \
+	.key_offset = offsetof(struct ci, key), \
+	.salt_offset = offsetof(struct ci, salt), \
+	.rec_seq_offset = offsetof(struct ci, rec_seq), \
+	.crypto_info = sizeof(struct ci)
+
+#define CIPHER_DESC(cipher,ci,algname,_offloadable) [cipher - TLS_CIPHER_MIN] = {	\
+	.nonce = cipher ## _IV_SIZE, \
 	.iv = cipher ## _IV_SIZE, \
 	.key = cipher ## _KEY_SIZE, \
 	.salt = cipher ## _SALT_SIZE, \
 	.tag = cipher ## _TAG_SIZE, \
 	.rec_seq = cipher ## _REC_SEQ_SIZE, \
+	.cipher_name = algname,	\
+	.offloadable = _offloadable, \
+	__CIPHER_DESC(ci), \
+}
+
+#define CIPHER_DESC_NONCE0(cipher,ci,algname,_offloadable) [cipher - TLS_CIPHER_MIN] = { \
+	.nonce = 0, \
+	.iv = cipher ## _IV_SIZE, \
+	.key = cipher ## _KEY_SIZE, \
+	.salt = cipher ## _SALT_SIZE, \
+	.tag = cipher ## _TAG_SIZE, \
+	.rec_seq = cipher ## _REC_SEQ_SIZE, \
+	.cipher_name = algname,	\
+	.offloadable = _offloadable, \
+	__CIPHER_DESC(ci), \
 }
 
 const struct tls_cipher_desc tls_cipher_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN] = {
-	CIPHER_DESC(TLS_CIPHER_AES_GCM_128),
-	CIPHER_DESC(TLS_CIPHER_AES_GCM_256),
-	CIPHER_DESC(TLS_CIPHER_AES_CCM_128),
-	CIPHER_DESC(TLS_CIPHER_CHACHA20_POLY1305),
-	CIPHER_DESC(TLS_CIPHER_SM4_GCM),
-	CIPHER_DESC(TLS_CIPHER_SM4_CCM),
-	CIPHER_DESC(TLS_CIPHER_ARIA_GCM_128),
-	CIPHER_DESC(TLS_CIPHER_ARIA_GCM_256),
+	CIPHER_DESC(TLS_CIPHER_AES_GCM_128, tls12_crypto_info_aes_gcm_128, "gcm(aes)", true),
+	CIPHER_DESC(TLS_CIPHER_AES_GCM_256, tls12_crypto_info_aes_gcm_256, "gcm(aes)", true),
+	CIPHER_DESC(TLS_CIPHER_AES_CCM_128, tls12_crypto_info_aes_ccm_128, "ccm(aes)", false),
+	CIPHER_DESC_NONCE0(TLS_CIPHER_CHACHA20_POLY1305, tls12_crypto_info_chacha20_poly1305, "rfc7539(chacha20,poly1305)", false),
+	CIPHER_DESC(TLS_CIPHER_SM4_GCM, tls12_crypto_info_sm4_gcm, "gcm(sm4)", false),
+	CIPHER_DESC(TLS_CIPHER_SM4_CCM, tls12_crypto_info_sm4_ccm, "ccm(sm4)", false),
+	CIPHER_DESC(TLS_CIPHER_ARIA_GCM_128, tls12_crypto_info_aria_gcm_128, "gcm(aria)", false),
+	CIPHER_DESC(TLS_CIPHER_ARIA_GCM_256, tls12_crypto_info_aria_gcm_256, "gcm(aria)", false),
 };
 
 static const struct proto *saved_tcpv6_prot;
-- 
GitLab


From 0d98cc02022d60004f78f6e7e6cc1bd39db80ef9 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:14 +0200
Subject: [PATCH 1764/1806] tls: validate cipher descriptions at compile time

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/b38fb8cf60e099e82ae9979c3c9c92421042417c.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_main.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index bbdf211cc8983..9d8629be70173 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -58,6 +58,15 @@ enum {
 	TLS_NUM_PROTS,
 };
 
+#define CHECK_CIPHER_DESC(cipher,ci)				\
+	static_assert(cipher ## _IV_SIZE <= MAX_IV_SIZE);		\
+	static_assert(cipher ## _REC_SEQ_SIZE <= TLS_MAX_REC_SEQ_SIZE);	\
+	static_assert(cipher ## _TAG_SIZE == TLS_TAG_SIZE);		\
+	static_assert(sizeof_field(struct ci, iv) == cipher ## _IV_SIZE);	\
+	static_assert(sizeof_field(struct ci, key) == cipher ## _KEY_SIZE);	\
+	static_assert(sizeof_field(struct ci, salt) == cipher ## _SALT_SIZE);	\
+	static_assert(sizeof_field(struct ci, rec_seq) == cipher ## _REC_SEQ_SIZE);
+
 #define __CIPHER_DESC(ci) \
 	.iv_offset = offsetof(struct ci, iv), \
 	.key_offset = offsetof(struct ci, key), \
@@ -100,6 +109,15 @@ const struct tls_cipher_desc tls_cipher_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN
 	CIPHER_DESC(TLS_CIPHER_ARIA_GCM_256, tls12_crypto_info_aria_gcm_256, "gcm(aria)", false),
 };
 
+CHECK_CIPHER_DESC(TLS_CIPHER_AES_GCM_128, tls12_crypto_info_aes_gcm_128);
+CHECK_CIPHER_DESC(TLS_CIPHER_AES_GCM_256, tls12_crypto_info_aes_gcm_256);
+CHECK_CIPHER_DESC(TLS_CIPHER_AES_CCM_128, tls12_crypto_info_aes_ccm_128);
+CHECK_CIPHER_DESC(TLS_CIPHER_CHACHA20_POLY1305, tls12_crypto_info_chacha20_poly1305);
+CHECK_CIPHER_DESC(TLS_CIPHER_SM4_GCM, tls12_crypto_info_sm4_gcm);
+CHECK_CIPHER_DESC(TLS_CIPHER_SM4_CCM, tls12_crypto_info_sm4_ccm);
+CHECK_CIPHER_DESC(TLS_CIPHER_ARIA_GCM_128, tls12_crypto_info_aria_gcm_128);
+CHECK_CIPHER_DESC(TLS_CIPHER_ARIA_GCM_256, tls12_crypto_info_aria_gcm_256);
+
 static const struct proto *saved_tcpv6_prot;
 static DEFINE_MUTEX(tcpv6_prot_mutex);
 static const struct proto *saved_tcpv4_prot;
-- 
GitLab


From 3524dd4d5f1fb9e75fdfaf280822a34fa82059bd Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:15 +0200
Subject: [PATCH 1765/1806] tls: expand use of tls_cipher_desc in
 tls_set_device_offload

tls_set_device_offload is already getting iv and rec_seq sizes from
tls_cipher_desc. We can now also check if the cipher_type coming from
userspace is valid and can be offloaded.

We can also remove the runtime check on rec_seq, since we validate it
at compile time.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/8ab71b8eca856c7aaf981a45fe91ac649eb0e2e9.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_device.c | 22 ++++------------------
 1 file changed, 4 insertions(+), 18 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 98885d872d4ce..8c94c926606ad 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -1079,29 +1079,15 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 		goto release_netdev;
 	}
 
-	switch (crypto_info->cipher_type) {
-	case TLS_CIPHER_AES_GCM_128:
-		iv = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->iv;
-		rec_seq =
-		 ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq;
-		break;
-	case TLS_CIPHER_AES_GCM_256:
-		iv = ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->iv;
-		rec_seq =
-		 ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->rec_seq;
-		break;
-	default:
-		rc = -EINVAL;
-		goto release_netdev;
-	}
 	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
-
-	/* Sanity-check the rec_seq_size for stack allocations */
-	if (cipher_desc->rec_seq > TLS_MAX_REC_SEQ_SIZE) {
+	if (!cipher_desc || !cipher_desc->offloadable) {
 		rc = -EINVAL;
 		goto release_netdev;
 	}
 
+	iv = crypto_info_iv(crypto_info, cipher_desc);
+	rec_seq = crypto_info_rec_seq(crypto_info, cipher_desc);
+
 	prot->version = crypto_info->version;
 	prot->cipher_type = crypto_info->cipher_type;
 	prot->prepend_size = TLS_HEADER_SIZE + cipher_desc->iv;
-- 
GitLab


From d2322cf5ed59f084ac86d9339f7c3acccd177bfd Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:16 +0200
Subject: [PATCH 1766/1806] tls: allocate the fallback aead after checking that
 the cipher is valid

No need to allocate the aead if we're going to fail afterwards.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/335e32511ed55a0b30f3f81a78fa8f323b3bdf8f.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_device_fallback.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index cb224fb2a394d..4de9061f38f55 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -475,15 +475,6 @@ int tls_sw_fallback_init(struct sock *sk,
 	const u8 *key;
 	int rc;
 
-	offload_ctx->aead_send =
-	    crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(offload_ctx->aead_send)) {
-		rc = PTR_ERR(offload_ctx->aead_send);
-		pr_err_ratelimited("crypto_alloc_aead failed rc=%d\n", rc);
-		offload_ctx->aead_send = NULL;
-		goto err_out;
-	}
-
 	switch (crypto_info->cipher_type) {
 	case TLS_CIPHER_AES_GCM_128:
 		key = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->key;
@@ -493,10 +484,19 @@ int tls_sw_fallback_init(struct sock *sk,
 		break;
 	default:
 		rc = -EINVAL;
-		goto free_aead;
+		goto err_out;
 	}
 	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
 
+	offload_ctx->aead_send =
+	    crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(offload_ctx->aead_send)) {
+		rc = PTR_ERR(offload_ctx->aead_send);
+		pr_err_ratelimited("crypto_alloc_aead failed rc=%d\n", rc);
+		offload_ctx->aead_send = NULL;
+		goto err_out;
+	}
+
 	rc = crypto_aead_setkey(offload_ctx->aead_send, key, cipher_desc->key);
 	if (rc)
 		goto free_aead;
-- 
GitLab


From e907277aeb6caad1c4be96e20195f24531fcfefc Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:17 +0200
Subject: [PATCH 1767/1806] tls: expand use of tls_cipher_desc in
 tls_sw_fallback_init

tls_sw_fallback_init already gets the key and tag size from
tls_cipher_desc. We can now also check that the cipher type is valid,
and stop hard-coding the algorithm name passed to crypto_alloc_aead.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/c8c94b8fcafbfb558e09589c1f1ad48dbdf92f76.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_device_fallback.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 4de9061f38f55..1d743f310f4f0 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -472,24 +472,14 @@ int tls_sw_fallback_init(struct sock *sk,
 			 struct tls_crypto_info *crypto_info)
 {
 	const struct tls_cipher_desc *cipher_desc;
-	const u8 *key;
 	int rc;
 
-	switch (crypto_info->cipher_type) {
-	case TLS_CIPHER_AES_GCM_128:
-		key = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->key;
-		break;
-	case TLS_CIPHER_AES_GCM_256:
-		key = ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->key;
-		break;
-	default:
-		rc = -EINVAL;
-		goto err_out;
-	}
 	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
+	if (!cipher_desc || !cipher_desc->offloadable)
+		return -EINVAL;
 
 	offload_ctx->aead_send =
-	    crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+	    crypto_alloc_aead(cipher_desc->cipher_name, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(offload_ctx->aead_send)) {
 		rc = PTR_ERR(offload_ctx->aead_send);
 		pr_err_ratelimited("crypto_alloc_aead failed rc=%d\n", rc);
@@ -497,7 +487,9 @@ int tls_sw_fallback_init(struct sock *sk,
 		goto err_out;
 	}
 
-	rc = crypto_aead_setkey(offload_ctx->aead_send, key, cipher_desc->key);
+	rc = crypto_aead_setkey(offload_ctx->aead_send,
+				crypto_info_key(crypto_info, cipher_desc),
+				cipher_desc->key);
 	if (rc)
 		goto free_aead;
 
-- 
GitLab


From 5f309ade49c7068b1149ecf825c4c16e56a3b865 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:18 +0200
Subject: [PATCH 1768/1806] tls: get crypto_info size from tls_cipher_desc in
 do_tls_setsockopt_conf

We can simplify do_tls_setsockopt_conf using tls_cipher_desc. Also use
get_cipher_desc's result to check if the cipher_type coming from
userspace is valid.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/e97658eb4c6a5832f8ba20a06c4f36a77763c59e.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_main.c | 39 ++++++++-------------------------------
 1 file changed, 8 insertions(+), 31 deletions(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 9d8629be70173..73cae5dec3924 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -739,7 +739,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 	struct tls_crypto_info *crypto_info;
 	struct tls_crypto_info *alt_crypto_info;
 	struct tls_context *ctx = tls_get_ctx(sk);
-	size_t optsize;
+	const struct tls_cipher_desc *cipher_desc;
 	int rc = 0;
 	int conf;
 
@@ -780,46 +780,23 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 		}
 	}
 
-	switch (crypto_info->cipher_type) {
-	case TLS_CIPHER_AES_GCM_128:
-		optsize = sizeof(struct tls12_crypto_info_aes_gcm_128);
-		break;
-	case TLS_CIPHER_AES_GCM_256: {
-		optsize = sizeof(struct tls12_crypto_info_aes_gcm_256);
-		break;
+	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
+	if (!cipher_desc) {
+		rc = -EINVAL;
+		goto err_crypto_info;
 	}
-	case TLS_CIPHER_AES_CCM_128:
-		optsize = sizeof(struct tls12_crypto_info_aes_ccm_128);
-		break;
-	case TLS_CIPHER_CHACHA20_POLY1305:
-		optsize = sizeof(struct tls12_crypto_info_chacha20_poly1305);
-		break;
-	case TLS_CIPHER_SM4_GCM:
-		optsize = sizeof(struct tls12_crypto_info_sm4_gcm);
-		break;
-	case TLS_CIPHER_SM4_CCM:
-		optsize = sizeof(struct tls12_crypto_info_sm4_ccm);
-		break;
+
+	switch (crypto_info->cipher_type) {
 	case TLS_CIPHER_ARIA_GCM_128:
-		if (crypto_info->version != TLS_1_2_VERSION) {
-			rc = -EINVAL;
-			goto err_crypto_info;
-		}
-		optsize = sizeof(struct tls12_crypto_info_aria_gcm_128);
-		break;
 	case TLS_CIPHER_ARIA_GCM_256:
 		if (crypto_info->version != TLS_1_2_VERSION) {
 			rc = -EINVAL;
 			goto err_crypto_info;
 		}
-		optsize = sizeof(struct tls12_crypto_info_aria_gcm_256);
 		break;
-	default:
-		rc = -EINVAL;
-		goto err_crypto_info;
 	}
 
-	if (optlen != optsize) {
+	if (optlen != cipher_desc->crypto_info) {
 		rc = -EINVAL;
 		goto err_crypto_info;
 	}
-- 
GitLab


From 077e05d135489e144d9e0d01454886bf613d32a4 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:19 +0200
Subject: [PATCH 1769/1806] tls: use tls_cipher_desc to simplify
 do_tls_getsockopt_conf

Every cipher uses the same code to update its crypto_info struct based
on the values contained in the cctx, with only the struct type and
size/offset changing. We can get those  from tls_cipher_desc, and use
a single pair of memcpy and final copy_to_user.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/c21a904b91e972bdbbf9d1c6d2731ccfa1eedf72.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_main.c | 174 +++------------------------------------------
 1 file changed, 11 insertions(+), 163 deletions(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 73cae5dec3924..02f583ff92395 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -435,6 +435,7 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval,
 				  int __user *optlen, int tx)
 {
 	int rc = 0;
+	const struct tls_cipher_desc *cipher_desc;
 	struct tls_context *ctx = tls_get_ctx(sk);
 	struct tls_crypto_info *crypto_info;
 	struct cipher_context *cctx;
@@ -473,172 +474,19 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval,
 		goto out;
 	}
 
-	switch (crypto_info->cipher_type) {
-	case TLS_CIPHER_AES_GCM_128: {
-		struct tls12_crypto_info_aes_gcm_128 *
-		  crypto_info_aes_gcm_128 =
-		  container_of(crypto_info,
-			       struct tls12_crypto_info_aes_gcm_128,
-			       info);
-
-		if (len != sizeof(*crypto_info_aes_gcm_128)) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(crypto_info_aes_gcm_128->iv,
-		       cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
-		       TLS_CIPHER_AES_GCM_128_IV_SIZE);
-		memcpy(crypto_info_aes_gcm_128->rec_seq, cctx->rec_seq,
-		       TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE);
-		if (copy_to_user(optval,
-				 crypto_info_aes_gcm_128,
-				 sizeof(*crypto_info_aes_gcm_128)))
-			rc = -EFAULT;
-		break;
-	}
-	case TLS_CIPHER_AES_GCM_256: {
-		struct tls12_crypto_info_aes_gcm_256 *
-		  crypto_info_aes_gcm_256 =
-		  container_of(crypto_info,
-			       struct tls12_crypto_info_aes_gcm_256,
-			       info);
-
-		if (len != sizeof(*crypto_info_aes_gcm_256)) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(crypto_info_aes_gcm_256->iv,
-		       cctx->iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE,
-		       TLS_CIPHER_AES_GCM_256_IV_SIZE);
-		memcpy(crypto_info_aes_gcm_256->rec_seq, cctx->rec_seq,
-		       TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE);
-		if (copy_to_user(optval,
-				 crypto_info_aes_gcm_256,
-				 sizeof(*crypto_info_aes_gcm_256)))
-			rc = -EFAULT;
-		break;
-	}
-	case TLS_CIPHER_AES_CCM_128: {
-		struct tls12_crypto_info_aes_ccm_128 *aes_ccm_128 =
-			container_of(crypto_info,
-				struct tls12_crypto_info_aes_ccm_128, info);
-
-		if (len != sizeof(*aes_ccm_128)) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(aes_ccm_128->iv,
-		       cctx->iv + TLS_CIPHER_AES_CCM_128_SALT_SIZE,
-		       TLS_CIPHER_AES_CCM_128_IV_SIZE);
-		memcpy(aes_ccm_128->rec_seq, cctx->rec_seq,
-		       TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE);
-		if (copy_to_user(optval, aes_ccm_128, sizeof(*aes_ccm_128)))
-			rc = -EFAULT;
-		break;
-	}
-	case TLS_CIPHER_CHACHA20_POLY1305: {
-		struct tls12_crypto_info_chacha20_poly1305 *chacha20_poly1305 =
-			container_of(crypto_info,
-				struct tls12_crypto_info_chacha20_poly1305,
-				info);
-
-		if (len != sizeof(*chacha20_poly1305)) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(chacha20_poly1305->iv,
-		       cctx->iv + TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE,
-		       TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE);
-		memcpy(chacha20_poly1305->rec_seq, cctx->rec_seq,
-		       TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE);
-		if (copy_to_user(optval, chacha20_poly1305,
-				sizeof(*chacha20_poly1305)))
-			rc = -EFAULT;
-		break;
+	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
+	if (!cipher_desc || len != cipher_desc->crypto_info) {
+		rc = -EINVAL;
+		goto out;
 	}
-	case TLS_CIPHER_SM4_GCM: {
-		struct tls12_crypto_info_sm4_gcm *sm4_gcm_info =
-			container_of(crypto_info,
-				struct tls12_crypto_info_sm4_gcm, info);
 
-		if (len != sizeof(*sm4_gcm_info)) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(sm4_gcm_info->iv,
-		       cctx->iv + TLS_CIPHER_SM4_GCM_SALT_SIZE,
-		       TLS_CIPHER_SM4_GCM_IV_SIZE);
-		memcpy(sm4_gcm_info->rec_seq, cctx->rec_seq,
-		       TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE);
-		if (copy_to_user(optval, sm4_gcm_info, sizeof(*sm4_gcm_info)))
-			rc = -EFAULT;
-		break;
-	}
-	case TLS_CIPHER_SM4_CCM: {
-		struct tls12_crypto_info_sm4_ccm *sm4_ccm_info =
-			container_of(crypto_info,
-				struct tls12_crypto_info_sm4_ccm, info);
+	memcpy(crypto_info_iv(crypto_info, cipher_desc),
+	       cctx->iv + cipher_desc->salt, cipher_desc->iv);
+	memcpy(crypto_info_rec_seq(crypto_info, cipher_desc),
+	       cctx->rec_seq, cipher_desc->rec_seq);
 
-		if (len != sizeof(*sm4_ccm_info)) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(sm4_ccm_info->iv,
-		       cctx->iv + TLS_CIPHER_SM4_CCM_SALT_SIZE,
-		       TLS_CIPHER_SM4_CCM_IV_SIZE);
-		memcpy(sm4_ccm_info->rec_seq, cctx->rec_seq,
-		       TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE);
-		if (copy_to_user(optval, sm4_ccm_info, sizeof(*sm4_ccm_info)))
-			rc = -EFAULT;
-		break;
-	}
-	case TLS_CIPHER_ARIA_GCM_128: {
-		struct tls12_crypto_info_aria_gcm_128 *
-		  crypto_info_aria_gcm_128 =
-		  container_of(crypto_info,
-			       struct tls12_crypto_info_aria_gcm_128,
-			       info);
-
-		if (len != sizeof(*crypto_info_aria_gcm_128)) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(crypto_info_aria_gcm_128->iv,
-		       cctx->iv + TLS_CIPHER_ARIA_GCM_128_SALT_SIZE,
-		       TLS_CIPHER_ARIA_GCM_128_IV_SIZE);
-		memcpy(crypto_info_aria_gcm_128->rec_seq, cctx->rec_seq,
-		       TLS_CIPHER_ARIA_GCM_128_REC_SEQ_SIZE);
-		if (copy_to_user(optval,
-				 crypto_info_aria_gcm_128,
-				 sizeof(*crypto_info_aria_gcm_128)))
-			rc = -EFAULT;
-		break;
-	}
-	case TLS_CIPHER_ARIA_GCM_256: {
-		struct tls12_crypto_info_aria_gcm_256 *
-		  crypto_info_aria_gcm_256 =
-		  container_of(crypto_info,
-			       struct tls12_crypto_info_aria_gcm_256,
-			       info);
-
-		if (len != sizeof(*crypto_info_aria_gcm_256)) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(crypto_info_aria_gcm_256->iv,
-		       cctx->iv + TLS_CIPHER_ARIA_GCM_256_SALT_SIZE,
-		       TLS_CIPHER_ARIA_GCM_256_IV_SIZE);
-		memcpy(crypto_info_aria_gcm_256->rec_seq, cctx->rec_seq,
-		       TLS_CIPHER_ARIA_GCM_256_REC_SEQ_SIZE);
-		if (copy_to_user(optval,
-				 crypto_info_aria_gcm_256,
-				 sizeof(*crypto_info_aria_gcm_256)))
-			rc = -EFAULT;
-		break;
-	}
-	default:
-		rc = -EINVAL;
-	}
+	if (copy_to_user(optval, crypto_info, cipher_desc->crypto_info))
+		rc = -EFAULT;
 
 out:
 	return rc;
-- 
GitLab


From d9a6ca1a975839e61c0463a5e29dd8053fd3e8a4 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:20 +0200
Subject: [PATCH 1770/1806] tls: use tls_cipher_desc to get per-cipher sizes in
 tls_set_sw_offload

We can get rid of some local variables, but we have to keep nonce_size
because tls1.3 uses nonce_size = 0 for all ciphers.

We can also drop the runtime sanity checks on iv/rec_seq/tag size,
since we have compile time checks on those values.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/deed9c4430a62c31751a72b8c03ad66ffe710717.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 79 ++++++++++--------------------------------------
 1 file changed, 16 insertions(+), 63 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 5c122d7bb7847..85708656dcd4f 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2590,10 +2590,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	struct tls_sw_context_rx *sw_ctx_rx = NULL;
 	struct cipher_context *cctx;
 	struct crypto_aead **aead;
-	u16 nonce_size, tag_size, iv_size, rec_seq_size, salt_size;
 	struct crypto_tfm *tfm;
 	char *iv, *rec_seq, *key, *salt, *cipher_name;
-	size_t keysize;
+	const struct tls_cipher_desc *cipher_desc;
+	u16 nonce_size;
 	int rc = 0;
 
 	if (!ctx) {
@@ -2652,16 +2652,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
 
 		gcm_128_info = (void *)crypto_info;
-		nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
-		tag_size = TLS_CIPHER_AES_GCM_128_TAG_SIZE;
-		iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
 		iv = gcm_128_info->iv;
-		rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE;
 		rec_seq = gcm_128_info->rec_seq;
-		keysize = TLS_CIPHER_AES_GCM_128_KEY_SIZE;
 		key = gcm_128_info->key;
 		salt = gcm_128_info->salt;
-		salt_size = TLS_CIPHER_AES_GCM_128_SALT_SIZE;
 		cipher_name = "gcm(aes)";
 		break;
 	}
@@ -2669,16 +2663,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		struct tls12_crypto_info_aes_gcm_256 *gcm_256_info;
 
 		gcm_256_info = (void *)crypto_info;
-		nonce_size = TLS_CIPHER_AES_GCM_256_IV_SIZE;
-		tag_size = TLS_CIPHER_AES_GCM_256_TAG_SIZE;
-		iv_size = TLS_CIPHER_AES_GCM_256_IV_SIZE;
 		iv = gcm_256_info->iv;
-		rec_seq_size = TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE;
 		rec_seq = gcm_256_info->rec_seq;
-		keysize = TLS_CIPHER_AES_GCM_256_KEY_SIZE;
 		key = gcm_256_info->key;
 		salt = gcm_256_info->salt;
-		salt_size = TLS_CIPHER_AES_GCM_256_SALT_SIZE;
 		cipher_name = "gcm(aes)";
 		break;
 	}
@@ -2686,16 +2674,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		struct tls12_crypto_info_aes_ccm_128 *ccm_128_info;
 
 		ccm_128_info = (void *)crypto_info;
-		nonce_size = TLS_CIPHER_AES_CCM_128_IV_SIZE;
-		tag_size = TLS_CIPHER_AES_CCM_128_TAG_SIZE;
-		iv_size = TLS_CIPHER_AES_CCM_128_IV_SIZE;
 		iv = ccm_128_info->iv;
-		rec_seq_size = TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE;
 		rec_seq = ccm_128_info->rec_seq;
-		keysize = TLS_CIPHER_AES_CCM_128_KEY_SIZE;
 		key = ccm_128_info->key;
 		salt = ccm_128_info->salt;
-		salt_size = TLS_CIPHER_AES_CCM_128_SALT_SIZE;
 		cipher_name = "ccm(aes)";
 		break;
 	}
@@ -2703,16 +2685,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		struct tls12_crypto_info_chacha20_poly1305 *chacha20_poly1305_info;
 
 		chacha20_poly1305_info = (void *)crypto_info;
-		nonce_size = 0;
-		tag_size = TLS_CIPHER_CHACHA20_POLY1305_TAG_SIZE;
-		iv_size = TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE;
 		iv = chacha20_poly1305_info->iv;
-		rec_seq_size = TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE;
 		rec_seq = chacha20_poly1305_info->rec_seq;
-		keysize = TLS_CIPHER_CHACHA20_POLY1305_KEY_SIZE;
 		key = chacha20_poly1305_info->key;
 		salt = chacha20_poly1305_info->salt;
-		salt_size = TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE;
 		cipher_name = "rfc7539(chacha20,poly1305)";
 		break;
 	}
@@ -2720,16 +2696,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		struct tls12_crypto_info_sm4_gcm *sm4_gcm_info;
 
 		sm4_gcm_info = (void *)crypto_info;
-		nonce_size = TLS_CIPHER_SM4_GCM_IV_SIZE;
-		tag_size = TLS_CIPHER_SM4_GCM_TAG_SIZE;
-		iv_size = TLS_CIPHER_SM4_GCM_IV_SIZE;
 		iv = sm4_gcm_info->iv;
-		rec_seq_size = TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE;
 		rec_seq = sm4_gcm_info->rec_seq;
-		keysize = TLS_CIPHER_SM4_GCM_KEY_SIZE;
 		key = sm4_gcm_info->key;
 		salt = sm4_gcm_info->salt;
-		salt_size = TLS_CIPHER_SM4_GCM_SALT_SIZE;
 		cipher_name = "gcm(sm4)";
 		break;
 	}
@@ -2737,16 +2707,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		struct tls12_crypto_info_sm4_ccm *sm4_ccm_info;
 
 		sm4_ccm_info = (void *)crypto_info;
-		nonce_size = TLS_CIPHER_SM4_CCM_IV_SIZE;
-		tag_size = TLS_CIPHER_SM4_CCM_TAG_SIZE;
-		iv_size = TLS_CIPHER_SM4_CCM_IV_SIZE;
 		iv = sm4_ccm_info->iv;
-		rec_seq_size = TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE;
 		rec_seq = sm4_ccm_info->rec_seq;
-		keysize = TLS_CIPHER_SM4_CCM_KEY_SIZE;
 		key = sm4_ccm_info->key;
 		salt = sm4_ccm_info->salt;
-		salt_size = TLS_CIPHER_SM4_CCM_SALT_SIZE;
 		cipher_name = "ccm(sm4)";
 		break;
 	}
@@ -2754,16 +2718,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		struct tls12_crypto_info_aria_gcm_128 *aria_gcm_128_info;
 
 		aria_gcm_128_info = (void *)crypto_info;
-		nonce_size = TLS_CIPHER_ARIA_GCM_128_IV_SIZE;
-		tag_size = TLS_CIPHER_ARIA_GCM_128_TAG_SIZE;
-		iv_size = TLS_CIPHER_ARIA_GCM_128_IV_SIZE;
 		iv = aria_gcm_128_info->iv;
-		rec_seq_size = TLS_CIPHER_ARIA_GCM_128_REC_SEQ_SIZE;
 		rec_seq = aria_gcm_128_info->rec_seq;
-		keysize = TLS_CIPHER_ARIA_GCM_128_KEY_SIZE;
 		key = aria_gcm_128_info->key;
 		salt = aria_gcm_128_info->salt;
-		salt_size = TLS_CIPHER_ARIA_GCM_128_SALT_SIZE;
 		cipher_name = "gcm(aria)";
 		break;
 	}
@@ -2771,16 +2729,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		struct tls12_crypto_info_aria_gcm_256 *gcm_256_info;
 
 		gcm_256_info = (void *)crypto_info;
-		nonce_size = TLS_CIPHER_ARIA_GCM_256_IV_SIZE;
-		tag_size = TLS_CIPHER_ARIA_GCM_256_TAG_SIZE;
-		iv_size = TLS_CIPHER_ARIA_GCM_256_IV_SIZE;
 		iv = gcm_256_info->iv;
-		rec_seq_size = TLS_CIPHER_ARIA_GCM_256_REC_SEQ_SIZE;
 		rec_seq = gcm_256_info->rec_seq;
-		keysize = TLS_CIPHER_ARIA_GCM_256_KEY_SIZE;
 		key = gcm_256_info->key;
 		salt = gcm_256_info->salt;
-		salt_size = TLS_CIPHER_ARIA_GCM_256_SALT_SIZE;
 		cipher_name = "gcm(aria)";
 		break;
 	}
@@ -2789,6 +2741,9 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		goto free_priv;
 	}
 
+	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
+	nonce_size = cipher_desc->nonce;
+
 	if (crypto_info->version == TLS_1_3_VERSION) {
 		nonce_size = 0;
 		prot->aad_size = TLS_HEADER_SIZE;
@@ -2799,9 +2754,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	}
 
 	/* Sanity-check the sizes for stack allocations. */
-	if (iv_size > MAX_IV_SIZE || nonce_size > MAX_IV_SIZE ||
-	    rec_seq_size > TLS_MAX_REC_SEQ_SIZE || tag_size != TLS_TAG_SIZE ||
-	    prot->aad_size > TLS_MAX_AAD_SIZE) {
+	if (nonce_size > MAX_IV_SIZE || prot->aad_size > TLS_MAX_AAD_SIZE) {
 		rc = -EINVAL;
 		goto free_priv;
 	}
@@ -2809,21 +2762,22 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	prot->version = crypto_info->version;
 	prot->cipher_type = crypto_info->cipher_type;
 	prot->prepend_size = TLS_HEADER_SIZE + nonce_size;
-	prot->tag_size = tag_size;
+	prot->tag_size = cipher_desc->tag;
 	prot->overhead_size = prot->prepend_size +
 			      prot->tag_size + prot->tail_size;
-	prot->iv_size = iv_size;
-	prot->salt_size = salt_size;
-	cctx->iv = kmalloc(iv_size + salt_size, GFP_KERNEL);
+	prot->iv_size = cipher_desc->iv;
+	prot->salt_size = cipher_desc->salt;
+	cctx->iv = kmalloc(cipher_desc->iv + cipher_desc->salt, GFP_KERNEL);
 	if (!cctx->iv) {
 		rc = -ENOMEM;
 		goto free_priv;
 	}
 	/* Note: 128 & 256 bit salt are the same size */
-	prot->rec_seq_size = rec_seq_size;
-	memcpy(cctx->iv, salt, salt_size);
-	memcpy(cctx->iv + salt_size, iv, iv_size);
-	cctx->rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL);
+	prot->rec_seq_size = cipher_desc->rec_seq;
+	memcpy(cctx->iv, salt, cipher_desc->salt);
+	memcpy(cctx->iv + cipher_desc->salt, iv, cipher_desc->iv);
+
+	cctx->rec_seq = kmemdup(rec_seq, cipher_desc->rec_seq, GFP_KERNEL);
 	if (!cctx->rec_seq) {
 		rc = -ENOMEM;
 		goto free_iv;
@@ -2840,8 +2794,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 
 	ctx->push_pending_record = tls_sw_push_pending_record;
 
-	rc = crypto_aead_setkey(*aead, key, keysize);
-
+	rc = crypto_aead_setkey(*aead, key, cipher_desc->key);
 	if (rc)
 		goto free_aead;
 
-- 
GitLab


From 48dfad27fd4045df82eee54186c2513cbfc54c1d Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:21 +0200
Subject: [PATCH 1771/1806] tls: use tls_cipher_desc to access per-cipher
 crypto_info in tls_set_sw_offload

The crypto_info_* helpers allow us to fetch pointers into the
per-cipher crypto_info's data.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/c23af110caf0af6b68de2f86c58064913e2e902a.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 89 +++++++-----------------------------------------
 1 file changed, 13 insertions(+), 76 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 85708656dcd4f..9c18ddf0d568f 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2648,94 +2648,26 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	}
 
 	switch (crypto_info->cipher_type) {
-	case TLS_CIPHER_AES_GCM_128: {
-		struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
-
-		gcm_128_info = (void *)crypto_info;
-		iv = gcm_128_info->iv;
-		rec_seq = gcm_128_info->rec_seq;
-		key = gcm_128_info->key;
-		salt = gcm_128_info->salt;
+	case TLS_CIPHER_AES_GCM_128:
+	case TLS_CIPHER_AES_GCM_256:
 		cipher_name = "gcm(aes)";
 		break;
-	}
-	case TLS_CIPHER_AES_GCM_256: {
-		struct tls12_crypto_info_aes_gcm_256 *gcm_256_info;
-
-		gcm_256_info = (void *)crypto_info;
-		iv = gcm_256_info->iv;
-		rec_seq = gcm_256_info->rec_seq;
-		key = gcm_256_info->key;
-		salt = gcm_256_info->salt;
-		cipher_name = "gcm(aes)";
-		break;
-	}
-	case TLS_CIPHER_AES_CCM_128: {
-		struct tls12_crypto_info_aes_ccm_128 *ccm_128_info;
-
-		ccm_128_info = (void *)crypto_info;
-		iv = ccm_128_info->iv;
-		rec_seq = ccm_128_info->rec_seq;
-		key = ccm_128_info->key;
-		salt = ccm_128_info->salt;
+	case TLS_CIPHER_AES_CCM_128:
 		cipher_name = "ccm(aes)";
 		break;
-	}
-	case TLS_CIPHER_CHACHA20_POLY1305: {
-		struct tls12_crypto_info_chacha20_poly1305 *chacha20_poly1305_info;
-
-		chacha20_poly1305_info = (void *)crypto_info;
-		iv = chacha20_poly1305_info->iv;
-		rec_seq = chacha20_poly1305_info->rec_seq;
-		key = chacha20_poly1305_info->key;
-		salt = chacha20_poly1305_info->salt;
+	case TLS_CIPHER_CHACHA20_POLY1305:
 		cipher_name = "rfc7539(chacha20,poly1305)";
 		break;
-	}
-	case TLS_CIPHER_SM4_GCM: {
-		struct tls12_crypto_info_sm4_gcm *sm4_gcm_info;
-
-		sm4_gcm_info = (void *)crypto_info;
-		iv = sm4_gcm_info->iv;
-		rec_seq = sm4_gcm_info->rec_seq;
-		key = sm4_gcm_info->key;
-		salt = sm4_gcm_info->salt;
+	case TLS_CIPHER_SM4_GCM:
 		cipher_name = "gcm(sm4)";
 		break;
-	}
-	case TLS_CIPHER_SM4_CCM: {
-		struct tls12_crypto_info_sm4_ccm *sm4_ccm_info;
-
-		sm4_ccm_info = (void *)crypto_info;
-		iv = sm4_ccm_info->iv;
-		rec_seq = sm4_ccm_info->rec_seq;
-		key = sm4_ccm_info->key;
-		salt = sm4_ccm_info->salt;
+	case TLS_CIPHER_SM4_CCM:
 		cipher_name = "ccm(sm4)";
 		break;
-	}
-	case TLS_CIPHER_ARIA_GCM_128: {
-		struct tls12_crypto_info_aria_gcm_128 *aria_gcm_128_info;
-
-		aria_gcm_128_info = (void *)crypto_info;
-		iv = aria_gcm_128_info->iv;
-		rec_seq = aria_gcm_128_info->rec_seq;
-		key = aria_gcm_128_info->key;
-		salt = aria_gcm_128_info->salt;
+	case TLS_CIPHER_ARIA_GCM_128:
+	case TLS_CIPHER_ARIA_GCM_256:
 		cipher_name = "gcm(aria)";
 		break;
-	}
-	case TLS_CIPHER_ARIA_GCM_256: {
-		struct tls12_crypto_info_aria_gcm_256 *gcm_256_info;
-
-		gcm_256_info = (void *)crypto_info;
-		iv = gcm_256_info->iv;
-		rec_seq = gcm_256_info->rec_seq;
-		key = gcm_256_info->key;
-		salt = gcm_256_info->salt;
-		cipher_name = "gcm(aria)";
-		break;
-	}
 	default:
 		rc = -EINVAL;
 		goto free_priv;
@@ -2744,6 +2676,11 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
 	nonce_size = cipher_desc->nonce;
 
+	iv = crypto_info_iv(crypto_info, cipher_desc);
+	key = crypto_info_key(crypto_info, cipher_desc);
+	salt = crypto_info_salt(crypto_info, cipher_desc);
+	rec_seq = crypto_info_rec_seq(crypto_info, cipher_desc);
+
 	if (crypto_info->version == TLS_1_3_VERSION) {
 		nonce_size = 0;
 		prot->aad_size = TLS_HEADER_SIZE;
-- 
GitLab


From f3e444e31f9fa45ad59cc2d0e0c1bcc86eef4780 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 25 Aug 2023 23:35:22 +0200
Subject: [PATCH 1772/1806] tls: get cipher_name from cipher_desc in
 tls_set_sw_offload

tls_cipher_desc also contains the algorithm name needed by
crypto_alloc_aead, use it.

Finally, use get_cipher_desc to check if the cipher_type coming from
userspace is valid, and remove the cipher_type switch.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/53d021d80138aa125a9cef4468aa5ce531975a7b.1692977948.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 29 ++++-------------------------
 1 file changed, 4 insertions(+), 25 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 9c18ddf0d568f..1ed4a611631fe 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2591,7 +2591,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	struct cipher_context *cctx;
 	struct crypto_aead **aead;
 	struct crypto_tfm *tfm;
-	char *iv, *rec_seq, *key, *salt, *cipher_name;
+	char *iv, *rec_seq, *key, *salt;
 	const struct tls_cipher_desc *cipher_desc;
 	u16 nonce_size;
 	int rc = 0;
@@ -2647,33 +2647,12 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		aead = &sw_ctx_rx->aead_recv;
 	}
 
-	switch (crypto_info->cipher_type) {
-	case TLS_CIPHER_AES_GCM_128:
-	case TLS_CIPHER_AES_GCM_256:
-		cipher_name = "gcm(aes)";
-		break;
-	case TLS_CIPHER_AES_CCM_128:
-		cipher_name = "ccm(aes)";
-		break;
-	case TLS_CIPHER_CHACHA20_POLY1305:
-		cipher_name = "rfc7539(chacha20,poly1305)";
-		break;
-	case TLS_CIPHER_SM4_GCM:
-		cipher_name = "gcm(sm4)";
-		break;
-	case TLS_CIPHER_SM4_CCM:
-		cipher_name = "ccm(sm4)";
-		break;
-	case TLS_CIPHER_ARIA_GCM_128:
-	case TLS_CIPHER_ARIA_GCM_256:
-		cipher_name = "gcm(aria)";
-		break;
-	default:
+	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
+	if (!cipher_desc) {
 		rc = -EINVAL;
 		goto free_priv;
 	}
 
-	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
 	nonce_size = cipher_desc->nonce;
 
 	iv = crypto_info_iv(crypto_info, cipher_desc);
@@ -2721,7 +2700,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	}
 
 	if (!*aead) {
-		*aead = crypto_alloc_aead(cipher_name, 0, 0);
+		*aead = crypto_alloc_aead(cipher_desc->cipher_name, 0, 0);
 		if (IS_ERR(*aead)) {
 			rc = PTR_ERR(*aead);
 			*aead = NULL;
-- 
GitLab


From c639a708a0b8b69b7d580292a8f0405124488bad Mon Sep 17 00:00:00 2001
From: Pranavi Somisetty <pranavi.somisetty@amd.com>
Date: Thu, 24 Aug 2023 17:14:56 +0530
Subject: [PATCH 1773/1806] dt-bindings: net: xilinx_gmii2rgmii: Convert to
 json schema

Convert the Xilinx GMII to RGMII Converter device tree binding
documentation to json schema.
This converter is usually used as gem <---> gmii2rgmii <---> external phy
and, it's phy-handle should point to the phandle of the external phy.

Signed-off-by: Pranavi Somisetty <pranavi.somisetty@amd.com>
Signed-off-by: Harini Katakam <harini.katakam@amd.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../bindings/net/xilinx_gmii2rgmii.txt        | 35 ------------
 .../bindings/net/xlnx,gmii-to-rgmii.yaml      | 55 +++++++++++++++++++
 2 files changed, 55 insertions(+), 35 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/net/xilinx_gmii2rgmii.txt
 create mode 100644 Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml

diff --git a/Documentation/devicetree/bindings/net/xilinx_gmii2rgmii.txt b/Documentation/devicetree/bindings/net/xilinx_gmii2rgmii.txt
deleted file mode 100644
index 038dda48b8e61..0000000000000
--- a/Documentation/devicetree/bindings/net/xilinx_gmii2rgmii.txt
+++ /dev/null
@@ -1,35 +0,0 @@
-XILINX GMIITORGMII Converter Driver Device Tree Bindings
---------------------------------------------------------
-
-The Gigabit Media Independent Interface (GMII) to Reduced Gigabit Media
-Independent Interface (RGMII) core provides the RGMII between RGMII-compliant
-Ethernet physical media devices (PHY) and the Gigabit Ethernet controller.
-This core can be used in all three modes of operation(10/100/1000 Mb/s).
-The Management Data Input/Output (MDIO) interface is used to configure the
-Speed of operation. This core can switch dynamically between the three
-Different speed modes by configuring the conveter register through mdio write.
-
-This converter sits between the ethernet MAC and the external phy.
-MAC <==> GMII2RGMII <==> RGMII_PHY
-
-For more details about mdio please refer phy.txt file in the same directory.
-
-Required properties:
-- compatible	: Should be "xlnx,gmii-to-rgmii-1.0"
-- reg		: The ID number for the phy, usually a small integer
-- phy-handle	: Should point to the external phy device.
-		  See ethernet.txt file in the same directory.
-
-Example:
-	mdio {
-		#address-cells = <1>;
-		#size-cells = <0>;
-		phy: ethernet-phy@0 {
-			......
-		};
-		gmiitorgmii: gmiitorgmii@8 {
-			compatible = "xlnx,gmii-to-rgmii-1.0";
-			reg = <8>;
-			phy-handle = <&phy>;
-		};
-	};
diff --git a/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml b/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml
new file mode 100644
index 0000000000000..0f781dac6717c
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/xlnx,gmii-to-rgmii.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Xilinx GMII to RGMII Converter
+
+maintainers:
+  - Harini Katakam <harini.katakam@amd.com>
+
+description:
+  The Gigabit Media Independent Interface (GMII) to Reduced Gigabit Media
+  Independent Interface (RGMII) core provides the RGMII between RGMII-compliant
+  ethernet physical media devices (PHY) and the Gigabit Ethernet controller.
+  This core can be used in all three modes of operation(10/100/1000 Mb/s).
+  The Management Data Input/Output (MDIO) interface is used to configure the
+  speed of operation. This core can switch dynamically between the three
+  different speed modes by configuring the converter register through mdio write.
+  The core cannot function without an external phy connected to it.
+
+properties:
+  compatible:
+    const: xlnx,gmii-to-rgmii-1.0
+
+  reg:
+    minimum: 0
+    maximum: 31
+    description: The ID number for the phy.
+
+  phy-handle:
+    $ref: ethernet-controller.yaml#/properties/phy-handle
+
+required:
+  - compatible
+  - reg
+  - phy-handle
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    mdio {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        phy: ethernet-phy@0 {
+            reg = <0>;
+        };
+        gmiitorgmii@8 {
+            compatible = "xlnx,gmii-to-rgmii-1.0";
+            reg = <8>;
+            phy-handle = <&phy>;
+        };
+    };
-- 
GitLab


From c2f8fd7949603efb03908e05abbf7726748c8de3 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 24 Aug 2023 09:50:59 -0700
Subject: [PATCH 1774/1806] netrom: Deny concurrent connect().

syzkaller reported null-ptr-deref [0] related to AF_NETROM.
This is another self-accept issue from the strace log. [1]

syz-executor creates an AF_NETROM socket and calls connect(), which
is blocked at that time.  Then, sk->sk_state is TCP_SYN_SENT and
sock->state is SS_CONNECTING.

  [pid  5059] socket(AF_NETROM, SOCK_SEQPACKET, 0) = 4
  [pid  5059] connect(4, {sa_family=AF_NETROM, sa_data="..." <unfinished ...>

Another thread calls connect() concurrently, which finally fails
with -EINVAL.  However, the problem here is the socket state is
reset even while the first connect() is blocked.

  [pid  5060] connect(4, NULL, 0 <unfinished ...>
  [pid  5060] <... connect resumed>)      = -1 EINVAL (Invalid argument)

As sk->state is TCP_CLOSE and sock->state is SS_UNCONNECTED, the
following listen() succeeds.  Then, the first connect() looks up
itself as a listener and puts skb into the queue with skb->sk itself.
As a result, the next accept() gets another FD of itself as 3, and
the first connect() finishes.

  [pid  5060] listen(4, 0 <unfinished ...>
  [pid  5060] <... listen resumed>)       = 0
  [pid  5060] accept(4, NULL, NULL <unfinished ...>
  [pid  5060] <... accept resumed>)       = 3
  [pid  5059] <... connect resumed>)      = 0

Then, accept4() is called but blocked, which causes the general protection
fault later.

  [pid  5059] accept4(4, NULL, 0x20000400, SOCK_NONBLOCK <unfinished ...>

After that, another self-accept occurs by accept() and writev().

  [pid  5060] accept(4, NULL, NULL <unfinished ...>
  [pid  5061] writev(3, [{iov_base=...}] <unfinished ...>
  [pid  5061] <... writev resumed>)       = 99
  [pid  5060] <... accept resumed>)       = 6

Finally, the leader thread close()s all FDs.  Since the three FDs
reference the same socket, nr_release() does the cleanup for it
three times, and the remaining accept4() causes the following fault.

  [pid  5058] close(3)                    = 0
  [pid  5058] close(4)                    = 0
  [pid  5058] close(5)                    = -1 EBADF (Bad file descriptor)
  [pid  5058] close(6)                    = 0
  [pid  5058] <... exit_group resumed>)   = ?
  [   83.456055][ T5059] general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN

To avoid the issue, we need to return an error for connect() if
another connect() is in progress, as done in __inet_stream_connect().

[0]:
general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f]
CPU: 0 PID: 5059 Comm: syz-executor.0 Not tainted 6.5.0-rc5-syzkaller-00194-gace0ab3a4b54 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
RIP: 0010:__lock_acquire+0x109/0x5de0 kernel/locking/lockdep.c:5012
Code: 45 85 c9 0f 84 cc 0e 00 00 44 8b 05 11 6e 23 0b 45 85 c0 0f 84 be 0d 00 00 48 ba 00 00 00 00 00 fc ff df 4c 89 d1 48 c1 e9 03 <80> 3c 11 00 0f 85 e8 40 00 00 49 81 3a a0 69 48 90 0f 84 96 0d 00
RSP: 0018:ffffc90003d6f9e0 EFLAGS: 00010006
RAX: ffff8880244c8000 RBX: 1ffff920007adf6c RCX: 0000000000000003
RDX: dffffc0000000000 RSI: 0000000000000000 RDI: 0000000000000018
RBP: 0000000000000001 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000000018 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
FS:  00007f51d519a6c0(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f51d5158d58 CR3: 000000002943f000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 lock_acquire kernel/locking/lockdep.c:5761 [inline]
 lock_acquire+0x1ae/0x510 kernel/locking/lockdep.c:5726
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
 _raw_spin_lock_irqsave+0x3a/0x50 kernel/locking/spinlock.c:162
 prepare_to_wait+0x47/0x380 kernel/sched/wait.c:269
 nr_accept+0x20d/0x650 net/netrom/af_netrom.c:798
 do_accept+0x3a6/0x570 net/socket.c:1872
 __sys_accept4_file net/socket.c:1913 [inline]
 __sys_accept4+0x99/0x120 net/socket.c:1943
 __do_sys_accept4 net/socket.c:1954 [inline]
 __se_sys_accept4 net/socket.c:1951 [inline]
 __x64_sys_accept4+0x96/0x100 net/socket.c:1951
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7f51d447cae9
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f51d519a0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000120
RAX: ffffffffffffffda RBX: 00007f51d459bf80 RCX: 00007f51d447cae9
RDX: 0000000020000400 RSI: 0000000000000000 RDI: 0000000000000004
RBP: 00007f51d44c847a R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000800 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007f51d459bf80 R15: 00007ffc25c34e48
 </TASK>

Link: https://syzkaller.appspot.com/text?tag=CrashLog&x=152cdb63a80000 [1]
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+666c97e4686410e79649@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=666c97e4686410e79649
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/af_netrom.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index eb8ccbd58df74..96e91ab71573c 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -660,6 +660,11 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto out_release;
 	}
 
+	if (sock->state == SS_CONNECTING) {
+		err = -EALREADY;
+		goto out_release;
+	}
+
 	sk->sk_state   = TCP_CLOSE;
 	sock->state = SS_UNCONNECTED;
 
-- 
GitLab


From bb5ed01cd2428cd25b1c88a3a9cba87055eb289f Mon Sep 17 00:00:00 2001
From: Radoslaw Tyl <radoslawx.tyl@intel.com>
Date: Thu, 24 Aug 2023 13:46:19 -0700
Subject: [PATCH 1775/1806] igb: set max size RX buffer when store bad packet
 is enabled

Increase the RX buffer size to 3K when the SBP bit is on. The size of
the RX buffer determines the number of pages allocated which may not
be sufficient for receive frames larger than the set MTU size.

Cc: stable@vger.kernel.org
Fixes: 89eaefb61dc9 ("igb: Support RX-ALL feature flag.")
Reported-by: Manfred Rudigier <manfred.rudigier@omicronenergy.com>
Signed-off-by: Radoslaw Tyl <radoslawx.tyl@intel.com>
Tested-by: Arpana Arland <arpanax.arland@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 9a2561409b06f..08e3df37089fe 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -4814,6 +4814,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 static void igb_set_rx_buffer_len(struct igb_adapter *adapter,
 				  struct igb_ring *rx_ring)
 {
+#if (PAGE_SIZE < 8192)
+	struct e1000_hw *hw = &adapter->hw;
+#endif
+
 	/* set build_skb and buffer size flags */
 	clear_ring_build_skb_enabled(rx_ring);
 	clear_ring_uses_large_buffer(rx_ring);
@@ -4824,10 +4828,9 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter,
 	set_ring_build_skb_enabled(rx_ring);
 
 #if (PAGE_SIZE < 8192)
-	if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB)
-		return;
-
-	set_ring_uses_large_buffer(rx_ring);
+	if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB ||
+	    rd32(E1000_RCTL) & E1000_RCTL_SBP)
+		set_ring_uses_large_buffer(rx_ring);
 #endif
 }
 
-- 
GitLab


From 72dd7e427e16fca901daaa399e4b0893c3bb85c0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= <alexis.lothore@bootlin.com>
Date: Fri, 25 Aug 2023 10:20:27 +0200
Subject: [PATCH 1776/1806] dt-bindings: net: dsa: marvell: fix wrong model in
 compatibility list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix wrong switch name in compatibility list. 88E6163 switch does not exist
and is in fact 88E6361

Fixes: 9229a9483d80 ("dt-bindings: net: dsa: marvell: add MV88E6361 switch to compatibility list")
Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/dsa/marvell.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/dsa/marvell.txt b/Documentation/devicetree/bindings/net/dsa/marvell.txt
index 33726134f5c96..6ec0c181b6db2 100644
--- a/Documentation/devicetree/bindings/net/dsa/marvell.txt
+++ b/Documentation/devicetree/bindings/net/dsa/marvell.txt
@@ -20,7 +20,7 @@ which is at a different MDIO base address in different switch families.
 			  6171, 6172, 6175, 6176, 6185, 6240, 6320, 6321,
 			  6341, 6350, 6351, 6352
 - "marvell,mv88e6190"	: Switch has base address 0x00. Use with models:
-			  6163, 6190, 6190X, 6191, 6290, 6390, 6390X
+			  6190, 6190X, 6191, 6290, 6361, 6390, 6390X
 - "marvell,mv88e6250"	: Switch has base address 0x08 or 0x18. Use with model:
 			  6220, 6250
 
-- 
GitLab


From 5266733c798652925aaf556aacc3f3389abc9d32 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 25 Aug 2023 16:10:19 +0530
Subject: [PATCH 1777/1806] octeontx2-af: CN10KB: Add USGMII LMAC mode

Upon physical link change, firmware reports to the kernel about the
change along with the details like speed, lmac_type_id, etc.
Kernel derives lmac_type based on lmac_type_id received from firmware.

This patch extends current lmac list with new USGMII mode supported
by CN10KB RPM block.

Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 1 +
 drivers/net/ethernet/marvell/octeontx2/af/cgx.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 988383e20bb8a..9392ef95a2457 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -55,6 +55,7 @@ static const char *cgx_lmactype_string[LMAC_MODE_MAX] = {
 	[LMAC_MODE_50G_R] = "50G_R",
 	[LMAC_MODE_100G_R] = "100G_R",
 	[LMAC_MODE_USXGMII] = "USXGMII",
+	[LMAC_MODE_USGMII] = "USGMII",
 };
 
 /* CGX PHY management internal APIs */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 5741141796880..6f7d1dee58308 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -110,6 +110,7 @@ enum LMAC_TYPE {
 	LMAC_MODE_50G_R		= 8,
 	LMAC_MODE_100G_R	= 9,
 	LMAC_MODE_USXGMII	= 10,
+	LMAC_MODE_USGMII	= 11,
 	LMAC_MODE_MAX,
 };
 
-- 
GitLab


From f027fd51edebb326c1edb5d283ceaa7b8f7508df Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Fri, 25 Aug 2023 16:10:20 +0530
Subject: [PATCH 1778/1806] octeontx2-af: Don't treat lack of CGX interfaces as
 error

Don't treat lack of CGX LMACs on the system as a error.
Instead ignore it so that LBK VFs are created and can be used.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index b3f766b970ca8..4e3aec7bdbee1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -345,7 +345,7 @@ int rvu_cgx_init(struct rvu *rvu)
 	rvu->cgx_cnt_max = cgx_get_cgxcnt_max();
 	if (!rvu->cgx_cnt_max) {
 		dev_info(rvu->dev, "No CGX devices found!\n");
-		return -ENODEV;
+		return 0;
 	}
 
 	rvu->cgx_idmap = devm_kzalloc(rvu->dev, rvu->cgx_cnt_max *
-- 
GitLab


From 2f387525d484c0eca841b71842e1cd672220c20c Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 25 Aug 2023 16:10:21 +0530
Subject: [PATCH 1779/1806] octeontx2-af: Add validation of lmac

With the addition of new MAC blocks like CN10K RPM and CN10KB
RPM_USX, LMACs are noncontiguous. Though in most of the functions,
lmac validation checks exist but in few functions they are missing.
This patch adds the same.

Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 9392ef95a2457..e06f77ad6106b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -232,6 +232,9 @@ int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr)
 	int index, id;
 	u64 cfg;
 
+	if (!lmac)
+		return -ENODEV;
+
 	/* access mac_ops to know csr_offset */
 	mac_ops = cgx_dev->mac_ops;
 
@@ -550,15 +553,16 @@ void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable)
 {
 	struct cgx *cgx = cgx_get_pdata(cgx_id);
 	struct lmac *lmac = lmac_pdata(lmac_id, cgx);
-	u16 max_dmac = lmac->mac_to_index_bmap.max;
 	struct mac_ops *mac_ops;
+	u16 max_dmac;
 	int index, i;
 	u64 cfg = 0;
 	int id;
 
-	if (!cgx)
+	if (!cgx || !lmac)
 		return;
 
+	max_dmac = lmac->mac_to_index_bmap.max;
 	id = get_sequence_id_of_lmac(cgx, lmac_id);
 
 	mac_ops = cgx->mac_ops;
@@ -731,7 +735,7 @@ int cgx_get_fec_stats(void *cgxd, int lmac_id, struct cgx_fec_stats_rsp *rsp)
 	int corr_reg, uncorr_reg;
 	struct cgx *cgx = cgxd;
 
-	if (!cgx || lmac_id >= cgx->lmac_count)
+	if (!is_lmac_valid(cgx, lmac_id))
 		return -ENODEV;
 
 	if (cgx->lmac_idmap[lmac_id]->link_info.fec == OTX2_FEC_NONE)
-- 
GitLab


From 17d1368f4f19eec2047c7527e7e606496481f1bf Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 25 Aug 2023 16:10:22 +0530
Subject: [PATCH 1780/1806] octeontx2-af: print error message incase of invalid
 pf mapping

During AF driver initialization, it creates a mapping between pf to
cgx,lmac pair. Whenever there is a physical link change, using this
mapping driver forwards the message to the associated netdev.

This patch prints error message incase of cgx,lmac pair is not
associated with any pf netdev.

Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 4e3aec7bdbee1..f2b1edf1bb43c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -236,6 +236,11 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu)
 
 	linfo = &event->link_uinfo;
 	pfmap = cgxlmac_to_pfmap(rvu, event->cgx_id, event->lmac_id);
+	if (!pfmap) {
+		dev_err(rvu->dev, "CGX port%d:%d not mapped with PF\n",
+			event->cgx_id, event->lmac_id);
+		return;
+	}
 
 	do {
 		pfid = find_first_bit(&pfmap,
-- 
GitLab


From 977ad86c2a1bcaf58f01ab98df5cc145083c489c Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Fri, 25 Aug 2023 15:32:41 +0200
Subject: [PATCH 1781/1806] dccp: Fix out of bounds access in DCCP error
 handler

There was a previous attempt to fix an out-of-bounds access in the DCCP
error handlers, but that fix assumed that the error handlers only want
to access the first 8 bytes of the DCCP header. Actually, they also look
at the DCCP sequence number, which is stored beyond 8 bytes, so an
explicit pskb_may_pull() is required.

Fixes: 6706a97fec96 ("dccp: fix out of bound access in dccp_v4_err()")
Fixes: 1aa9d1a0e7ee ("ipv6: dccp: fix out of bound access in dccp_v6_err()")
Cc: stable@vger.kernel.org
Signed-off-by: Jann Horn <jannh@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c | 13 +++++++++----
 net/dccp/ipv6.c | 15 ++++++++++-----
 2 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index a545ad71201c8..a5361fb7a415b 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -255,12 +255,17 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info)
 	int err;
 	struct net *net = dev_net(skb->dev);
 
-	/* Only need dccph_dport & dccph_sport which are the first
-	 * 4 bytes in dccp header.
+	/* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x,
+	 * which is in byte 7 of the dccp header.
 	 * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us.
+	 *
+	 * Later on, we want to access the sequence number fields, which are
+	 * beyond 8 bytes, so we have to pskb_may_pull() ourselves.
 	 */
-	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
-	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+	dh = (struct dccp_hdr *)(skb->data + offset);
+	if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh)))
+		return -EINVAL;
+	iph = (struct iphdr *)skb->data;
 	dh = (struct dccp_hdr *)(skb->data + offset);
 
 	sk = __inet_lookup_established(net, &dccp_hashinfo,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index d29d1163203d9..25816e790527d 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -74,7 +74,7 @@ static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb)
 static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			u8 type, u8 code, int offset, __be32 info)
 {
-	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
+	const struct ipv6hdr *hdr;
 	const struct dccp_hdr *dh;
 	struct dccp_sock *dp;
 	struct ipv6_pinfo *np;
@@ -83,12 +83,17 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	__u64 seq;
 	struct net *net = dev_net(skb->dev);
 
-	/* Only need dccph_dport & dccph_sport which are the first
-	 * 4 bytes in dccp header.
+	/* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x,
+	 * which is in byte 7 of the dccp header.
 	 * Our caller (icmpv6_notify()) already pulled 8 bytes for us.
+	 *
+	 * Later on, we want to access the sequence number fields, which are
+	 * beyond 8 bytes, so we have to pskb_may_pull() ourselves.
 	 */
-	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
-	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+	dh = (struct dccp_hdr *)(skb->data + offset);
+	if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh)))
+		return -EINVAL;
+	hdr = (const struct ipv6hdr *)skb->data;
 	dh = (struct dccp_hdr *)(skb->data + offset);
 
 	sk = __inet6_lookup_established(net, &dccp_hashinfo,
-- 
GitLab


From 28d18b673ffa2d13112ddb6e4c32c60d9b0cda50 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 25 Aug 2023 15:49:45 +0200
Subject: [PATCH 1782/1806] net: Fix skb consume leak in sch_handle_egress

Fix a memory leak for the tc egress path with TC_ACT_{STOLEN,QUEUED,TRAP}:

  [...]
  unreferenced object 0xffff88818bcb4f00 (size 232):
  comm "softirq", pid 0, jiffies 4299085078 (age 134.028s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 80 70 61 81 88 ff ff 00 41 31 14 81 88 ff ff  ..pa.....A1.....
  backtrace:
    [<ffffffff9991b938>] kmem_cache_alloc_node+0x268/0x400
    [<ffffffff9b3d9231>] __alloc_skb+0x211/0x2c0
    [<ffffffff9b3f0c7e>] alloc_skb_with_frags+0xbe/0x6b0
    [<ffffffff9b3bf9a9>] sock_alloc_send_pskb+0x6a9/0x870
    [<ffffffff9b6b3f00>] __ip_append_data+0x14d0/0x3bf0
    [<ffffffff9b6ba24e>] ip_append_data+0xee/0x190
    [<ffffffff9b7e1496>] icmp_push_reply+0xa6/0x470
    [<ffffffff9b7e4030>] icmp_reply+0x900/0xa00
    [<ffffffff9b7e42e3>] icmp_echo.part.0+0x1a3/0x230
    [<ffffffff9b7e444d>] icmp_echo+0xcd/0x190
    [<ffffffff9b7e9566>] icmp_rcv+0x806/0xe10
    [<ffffffff9b699bd1>] ip_protocol_deliver_rcu+0x351/0x3d0
    [<ffffffff9b699f14>] ip_local_deliver_finish+0x2b4/0x450
    [<ffffffff9b69a234>] ip_local_deliver+0x174/0x1f0
    [<ffffffff9b69a4b2>] ip_sublist_rcv_finish+0x1f2/0x420
    [<ffffffff9b69ab56>] ip_sublist_rcv+0x466/0x920
  [...]

I was able to reproduce this via:

  ip link add dev dummy0 type dummy
  ip link set dev dummy0 up
  tc qdisc add dev eth0 clsact
  tc filter add dev eth0 egress protocol ip prio 1 u32 match ip protocol 1 0xff action mirred egress redirect dev dummy0
  ping 1.1.1.1
  <stolen>

After the fix, there are no kmemleak reports with the reproducer. This is
in line with what is also done on the ingress side, and from debugging the
skb_unref(skb) on dummy xmit and sch_handle_egress() side, it is visible
that these are two different skbs with both skb_unref(skb) as true. The two
seen skbs are due to mirred doing a skb_clone() internally as use_reinsert
is false in tcf_mirred_act() for egress. This was initially reported by Gal.

Fixes: e420bed02507 ("bpf: Add fd-based tcx multi-prog infra with link support")
Reported-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/bdfc2640-8f65-5b56-4472-db8e2b161aab@nvidia.com
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 17e6281e408c7..9f6ed6d97f89d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4061,6 +4061,7 @@ egress_verdict:
 	case TC_ACT_STOLEN:
 	case TC_ACT_QUEUED:
 	case TC_ACT_TRAP:
+		consume_skb(skb);
 		*ret = NET_XMIT_SUCCESS;
 		return NULL;
 	}
-- 
GitLab


From 3a1e2f43985af0dea5750c6436f8cb979780c084 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 25 Aug 2023 15:49:46 +0200
Subject: [PATCH 1783/1806] net: Make consumed action consistent in
 sch_handle_egress

While looking at TC_ACT_* handling, the TC_ACT_CONSUMED is only handled in
sch_handle_ingress but not sch_handle_egress. This was added via cd11b164073b
("net/tc: introduce TC_ACT_REINSERT.") and e5cf1baf92cb ("act_mirred: use
TC_ACT_REINSERT when possible") and later got renamed into TC_ACT_CONSUMED
via 720f22fed81b ("net: sched: refactor reinsert action").

The initial work was targeted for ovs back then and only needed on ingress,
and the mirred action module also restricts it to only that. However, given
it's an API contract it would still make sense to make this consistent to
sch_handle_ingress and handle it on egress side in the same way, that is,
setting return code to "success" and returning NULL back to the caller as
otherwise an action module sitting on egress returning TC_ACT_CONSUMED could
lead to an UAF when untreated.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 9f6ed6d97f89d..ccff2b6ef9583 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4062,6 +4062,8 @@ egress_verdict:
 	case TC_ACT_QUEUED:
 	case TC_ACT_TRAP:
 		consume_skb(skb);
+		fallthrough;
+	case TC_ACT_CONSUMED:
 		*ret = NET_XMIT_SUCCESS;
 		return NULL;
 	}
-- 
GitLab


From ec1b90886f3cd7e90d4c0381dffb418e2d3a1473 Mon Sep 17 00:00:00 2001
From: Mikhail Kobuk <m.kobuk@ispras.ru>
Date: Fri, 25 Aug 2023 22:04:41 +0300
Subject: [PATCH 1784/1806] ethernet: tg3: remove unreachable code

'tp->irq_max' value is either 1 [L16336] or 5 [L16354], as indicated in
tg3_get_invariants(). Therefore, 'i' can't exceed 4 in tg3_init_one()
that makes (i <= 4) always true. Moreover, 'intmbx' value set at the
last iteration is not used later in it's scope.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 78f90dcf184b ("tg3: Move napi_add calls below tg3_get_invariants")
Signed-off-by: Mikhail Kobuk <m.kobuk@ispras.ru>
Reviewed-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index cb2810f175ccd..5408ed0517726 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -17795,10 +17795,7 @@ static int tg3_init_one(struct pci_dev *pdev,
 		tnapi->tx_pending = TG3_DEF_TX_RING_PENDING;
 
 		tnapi->int_mbox = intmbx;
-		if (i <= 4)
-			intmbx += 0x8;
-		else
-			intmbx += 0x4;
+		intmbx += 0x8;
 
 		tnapi->consmbox = rcvmbx;
 		tnapi->prodmbox = sndmbx;
-- 
GitLab


From 90ca51e8c654699b672ba61aeaa418dfb3252e5e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 25 Aug 2023 21:44:01 +0200
Subject: [PATCH 1785/1806] r8169: fix ASPM-related issues on a number of
 systems with NIC version from RTL8168h

This effectively reverts 4b5f82f6aaef. On a number of systems ASPM L1
causes tx timeouts with RTL8168h, see referenced bug report.

Fixes: 4b5f82f6aaef ("r8169: enable ASPM L1/L1.1 from RTL8168h")
Cc: stable@vger.kernel.org
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217814
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 5eb50b265c0bd..6351a2dc13bce 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5239,13 +5239,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Disable ASPM L1 as that cause random device stop working
 	 * problems as well as full system hangs for some PCIe devices users.
-	 * Chips from RTL8168h partially have issues with L1.2, but seem
-	 * to work fine with L1 and L1.1.
 	 */
 	if (rtl_aspm_is_safe(tp))
 		rc = 0;
-	else if (tp->mac_version >= RTL_GIGA_MAC_VER_46)
-		rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
 	else
 		rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1);
 	tp->aspm_manageable = !rc;
-- 
GitLab


From bf68583624c56bab26b4394fb4721461ded62f94 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Sat, 26 Aug 2023 10:23:30 +0800
Subject: [PATCH 1786/1806] selftests: bonding: create directly devices in the
 target namespaces

If failed to set link1_1 to netns client, we should delete link1_1 in the
cleanup path. But if set link1_1 to netns client successfully, delete
link1_1 will report warning. So it will be safer creating directly the
devices in the target namespaces.

Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Closes: https://lore.kernel.org/all/ZNyJx1HtXaUzOkNA@Laptop-X1/
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Acked-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/bonding/bond-arp-interval-causes-panic.sh | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
index 7b2d421f09cf2..4917dbb35a44d 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
@@ -22,14 +22,12 @@ server_ip4=192.168.1.254
 echo 180 >/proc/sys/kernel/panic
 
 # build namespaces
-ip link add dev link1_1 type veth peer name link1_2
-
 ip netns add "server"
-ip link set dev link1_2 netns server up name eth0
+ip netns add "client"
+ip -n client link add eth0 type veth peer name eth0 netns server
+ip netns exec server ip link set dev eth0 up
 ip netns exec server ip addr add ${server_ip4}/24 dev eth0
 
-ip netns add "client"
-ip link set dev link1_1 netns client down name eth0
 ip netns exec client ip link add dev bond0 down type bond mode 1 \
 	miimon 100 all_slaves_active 1
 ip netns exec client ip link set dev eth0 down master bond0
-- 
GitLab


From 8be6f88b9d3fe1f6724daec4a70d6023742c9df7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 28 Aug 2023 08:47:32 +0000
Subject: [PATCH 1787/1806] inet: fix IP_TRANSPARENT error handling

My recent patch forgot to change error handling for IP_TRANSPARENT
socket option.

WARNING: bad unlock balance detected!
6.5.0-rc7-syzkaller-01717-g59da9885767a #0 Not tainted
-------------------------------------
syz-executor151/5028 is trying to release lock (sk_lock-AF_INET) at:
[<ffffffff88213983>] sockopt_release_sock+0x53/0x70 net/core/sock.c:1073
but there are no more locks to release!

other info that might help us debug this:
1 lock held by syz-executor151/5028:

stack backtrace:
CPU: 0 PID: 5028 Comm: syz-executor151 Not tainted 6.5.0-rc7-syzkaller-01717-g59da9885767a #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xd9/0x1b0 lib/dump_stack.c:106
__lock_release kernel/locking/lockdep.c:5438 [inline]
lock_release+0x4b5/0x680 kernel/locking/lockdep.c:5781
sock_release_ownership include/net/sock.h:1824 [inline]
release_sock+0x175/0x1b0 net/core/sock.c:3527
sockopt_release_sock+0x53/0x70 net/core/sock.c:1073
do_ip_setsockopt+0x12c1/0x3640 net/ipv4/ip_sockglue.c:1364
ip_setsockopt+0x59/0xe0 net/ipv4/ip_sockglue.c:1419
raw_setsockopt+0x218/0x290 net/ipv4/raw.c:833
__sys_setsockopt+0x2cd/0x5b0 net/socket.c:2305
__do_sys_setsockopt net/socket.c:2316 [inline]
__se_sys_setsockopt net/socket.c:2313 [inline]

Fixes: 4bd0623f04ee ("inet: move inet->transparent to inet->inet_flags")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Simon Horman <horms@kernel.org>
Cc: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 54ad0f0d5c2dd..d1c73660b8449 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1007,12 +1007,10 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		return 0;
 	case IP_TRANSPARENT:
 		if (!!val && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
-			err = -EPERM;
-			break;
-		}
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
 		if (optlen < 1)
-			goto e_inval;
+			return -EINVAL;
 		inet_assign_bit(TRANSPARENT, sk, val);
 		return 0;
 	case IP_NODEFRAG:
-- 
GitLab


From 56e65312830ec45e3ccbc929de6f5b86bc301546 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:43 +0200
Subject: [PATCH 1788/1806] devlink: push object register/unregister
 notifications into separate helpers

In preparations of leftover.c split to individual files, avoid need to
have object structures exposed in devl_internal.h and allow to have them
maintained in object files.

The register/unregister notifications need to know the structures
to iterate lists. To avoid the need, introduce per-object
register/unregister notification helpers and use them.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-2-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/leftover.c | 247 +++++++++++++++++++++++++++--------------
 1 file changed, 163 insertions(+), 84 deletions(-)

diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 149752bc9f2df..890eafac9f8f7 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -1058,6 +1058,26 @@ static void devlink_port_notify(struct devlink_port *devlink_port,
 				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_ports_notify(struct devlink *devlink,
+				 enum devlink_command cmd)
+{
+	struct devlink_port *devlink_port;
+	unsigned long port_index;
+
+	xa_for_each(&devlink->ports, port_index, devlink_port)
+		devlink_port_notify(devlink_port, cmd);
+}
+
+static void devlink_ports_notify_register(struct devlink *devlink)
+{
+	devlink_ports_notify(devlink, DEVLINK_CMD_PORT_NEW);
+}
+
+static void devlink_ports_notify_unregister(struct devlink *devlink)
+{
+	devlink_ports_notify(devlink, DEVLINK_CMD_PORT_DEL);
+}
+
 static void devlink_rate_notify(struct devlink_rate *devlink_rate,
 				enum devlink_command cmd)
 {
@@ -1084,6 +1104,22 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate,
 				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_rates_notify_register(struct devlink *devlink)
+{
+	struct devlink_rate *rate_node;
+
+	list_for_each_entry(rate_node, &devlink->rate_list, list)
+		devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+}
+
+static void devlink_rates_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_rate *rate_node;
+
+	list_for_each_entry_reverse(rate_node, &devlink->rate_list, list)
+		devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
+}
+
 static int
 devlink_nl_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 			     struct netlink_callback *cb, int flags)
@@ -1928,6 +1964,22 @@ static void devlink_linecard_notify(struct devlink_linecard *linecard,
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_linecards_notify_register(struct devlink *devlink)
+{
+	struct devlink_linecard *linecard;
+
+	list_for_each_entry(linecard, &devlink->linecard_list, list)
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+}
+
+static void devlink_linecards_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_linecard *linecard;
+
+	list_for_each_entry_reverse(linecard, &devlink->linecard_list, list)
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
+}
+
 int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
@@ -4285,6 +4337,26 @@ static void devlink_param_notify(struct devlink *devlink,
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_params_notify(struct devlink *devlink,
+				  enum devlink_command cmd)
+{
+	struct devlink_param_item *param_item;
+	unsigned long param_id;
+
+	xa_for_each(&devlink->params, param_id, param_item)
+		devlink_param_notify(devlink, 0, param_item, cmd);
+}
+
+static void devlink_params_notify_register(struct devlink *devlink)
+{
+	devlink_params_notify(devlink, DEVLINK_CMD_PARAM_NEW);
+}
+
+static void devlink_params_notify_unregister(struct devlink *devlink)
+{
+	devlink_params_notify(devlink, DEVLINK_CMD_PARAM_DEL);
+}
+
 static int devlink_nl_param_get_dump_one(struct sk_buff *msg,
 					 struct devlink *devlink,
 					 struct netlink_callback *cb,
@@ -4694,6 +4766,22 @@ static void devlink_nl_region_notify(struct devlink_region *region,
 				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_regions_notify_register(struct devlink *devlink)
+{
+	struct devlink_region *region;
+
+	list_for_each_entry(region, &devlink->region_list, list)
+		devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
+}
+
+static void devlink_regions_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_region *region;
+
+	list_for_each_entry_reverse(region, &devlink->region_list, list)
+		devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL);
+}
+
 /**
  * __devlink_snapshot_id_increment - Increment number of snapshots using an id
  *	@devlink: devlink instance
@@ -6662,98 +6750,36 @@ const struct genl_small_ops devlink_nl_small_ops[40] = {
 	/* -- No new ops here! Use split ops going forward! -- */
 };
 
-static void
-devlink_trap_policer_notify(struct devlink *devlink,
-			    const struct devlink_trap_policer_item *policer_item,
-			    enum devlink_command cmd);
-static void
-devlink_trap_group_notify(struct devlink *devlink,
-			  const struct devlink_trap_group_item *group_item,
-			  enum devlink_command cmd);
-static void devlink_trap_notify(struct devlink *devlink,
-				const struct devlink_trap_item *trap_item,
-				enum devlink_command cmd);
+static void devlink_trap_policers_notify_register(struct devlink *devlink);
+static void devlink_trap_policers_notify_unregister(struct devlink *devlink);
+static void devlink_trap_groups_notify_register(struct devlink *devlink);
+static void devlink_trap_groups_notify_unregister(struct devlink *devlink);
+static void devlink_traps_notify_register(struct devlink *devlink);
+static void devlink_traps_notify_unregister(struct devlink *devlink);
 
 void devlink_notify_register(struct devlink *devlink)
 {
-	struct devlink_trap_policer_item *policer_item;
-	struct devlink_trap_group_item *group_item;
-	struct devlink_param_item *param_item;
-	struct devlink_trap_item *trap_item;
-	struct devlink_port *devlink_port;
-	struct devlink_linecard *linecard;
-	struct devlink_rate *rate_node;
-	struct devlink_region *region;
-	unsigned long port_index;
-	unsigned long param_id;
-
 	devlink_notify(devlink, DEVLINK_CMD_NEW);
-	list_for_each_entry(linecard, &devlink->linecard_list, list)
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-
-	xa_for_each(&devlink->ports, port_index, devlink_port)
-		devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
-
-	list_for_each_entry(policer_item, &devlink->trap_policer_list, list)
-		devlink_trap_policer_notify(devlink, policer_item,
-					    DEVLINK_CMD_TRAP_POLICER_NEW);
-
-	list_for_each_entry(group_item, &devlink->trap_group_list, list)
-		devlink_trap_group_notify(devlink, group_item,
-					  DEVLINK_CMD_TRAP_GROUP_NEW);
-
-	list_for_each_entry(trap_item, &devlink->trap_list, list)
-		devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW);
-
-	list_for_each_entry(rate_node, &devlink->rate_list, list)
-		devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
-
-	list_for_each_entry(region, &devlink->region_list, list)
-		devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
-
-	xa_for_each(&devlink->params, param_id, param_item)
-		devlink_param_notify(devlink, 0, param_item,
-				     DEVLINK_CMD_PARAM_NEW);
+	devlink_linecards_notify_register(devlink);
+	devlink_ports_notify_register(devlink);
+	devlink_trap_policers_notify_register(devlink);
+	devlink_trap_groups_notify_register(devlink);
+	devlink_traps_notify_register(devlink);
+	devlink_rates_notify_register(devlink);
+	devlink_regions_notify_register(devlink);
+	devlink_params_notify_register(devlink);
 }
 
 void devlink_notify_unregister(struct devlink *devlink)
 {
-	struct devlink_trap_policer_item *policer_item;
-	struct devlink_trap_group_item *group_item;
-	struct devlink_param_item *param_item;
-	struct devlink_trap_item *trap_item;
-	struct devlink_port *devlink_port;
-	struct devlink_linecard *linecard;
-	struct devlink_rate *rate_node;
-	struct devlink_region *region;
-	unsigned long port_index;
-	unsigned long param_id;
-
-	xa_for_each(&devlink->params, param_id, param_item)
-		devlink_param_notify(devlink, 0, param_item,
-				     DEVLINK_CMD_PARAM_DEL);
-
-	list_for_each_entry_reverse(region, &devlink->region_list, list)
-		devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL);
-
-	list_for_each_entry_reverse(rate_node, &devlink->rate_list, list)
-		devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
-
-	list_for_each_entry_reverse(trap_item, &devlink->trap_list, list)
-		devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL);
-
-	list_for_each_entry_reverse(group_item, &devlink->trap_group_list, list)
-		devlink_trap_group_notify(devlink, group_item,
-					  DEVLINK_CMD_TRAP_GROUP_DEL);
-	list_for_each_entry_reverse(policer_item, &devlink->trap_policer_list,
-				    list)
-		devlink_trap_policer_notify(devlink, policer_item,
-					    DEVLINK_CMD_TRAP_POLICER_DEL);
-
-	xa_for_each(&devlink->ports, port_index, devlink_port)
-		devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL);
-	list_for_each_entry_reverse(linecard, &devlink->linecard_list, list)
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
+	devlink_params_notify_unregister(devlink);
+	devlink_regions_notify_unregister(devlink);
+	devlink_rates_notify_unregister(devlink);
+	devlink_traps_notify_unregister(devlink);
+	devlink_trap_groups_notify_unregister(devlink);
+	devlink_trap_policers_notify_unregister(devlink);
+	devlink_ports_notify_unregister(devlink);
+	devlink_linecards_notify_unregister(devlink);
 	devlink_notify(devlink, DEVLINK_CMD_DEL);
 }
 
@@ -8879,6 +8905,24 @@ devlink_trap_group_notify(struct devlink *devlink,
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_trap_groups_notify_register(struct devlink *devlink)
+{
+	struct devlink_trap_group_item *group_item;
+
+	list_for_each_entry(group_item, &devlink->trap_group_list, list)
+		devlink_trap_group_notify(devlink, group_item,
+					  DEVLINK_CMD_TRAP_GROUP_NEW);
+}
+
+static void devlink_trap_groups_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_trap_group_item *group_item;
+
+	list_for_each_entry_reverse(group_item, &devlink->trap_group_list, list)
+		devlink_trap_group_notify(devlink, group_item,
+					  DEVLINK_CMD_TRAP_GROUP_DEL);
+}
+
 static int
 devlink_trap_item_group_link(struct devlink *devlink,
 			     struct devlink_trap_item *trap_item)
@@ -8921,6 +8965,22 @@ static void devlink_trap_notify(struct devlink *devlink,
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_traps_notify_register(struct devlink *devlink)
+{
+	struct devlink_trap_item *trap_item;
+
+	list_for_each_entry(trap_item, &devlink->trap_list, list)
+		devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW);
+}
+
+static void devlink_traps_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_trap_item *trap_item;
+
+	list_for_each_entry_reverse(trap_item, &devlink->trap_list, list)
+		devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL);
+}
+
 static int
 devlink_trap_register(struct devlink *devlink,
 		      const struct devlink_trap *trap, void *priv)
@@ -9382,6 +9442,25 @@ devlink_trap_policer_notify(struct devlink *devlink,
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_trap_policers_notify_register(struct devlink *devlink)
+{
+	struct devlink_trap_policer_item *policer_item;
+
+	list_for_each_entry(policer_item, &devlink->trap_policer_list, list)
+		devlink_trap_policer_notify(devlink, policer_item,
+					    DEVLINK_CMD_TRAP_POLICER_NEW);
+}
+
+static void devlink_trap_policers_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_trap_policer_item *policer_item;
+
+	list_for_each_entry_reverse(policer_item, &devlink->trap_policer_list,
+				    list)
+		devlink_trap_policer_notify(devlink, policer_item,
+					    DEVLINK_CMD_TRAP_POLICER_DEL);
+}
+
 static int
 devlink_trap_policer_register(struct devlink *devlink,
 			      const struct devlink_trap_policer *policer)
-- 
GitLab


From eec1e5ea1d715ce2df8dcdf3dac7112df77a6e17 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:44 +0200
Subject: [PATCH 1789/1806] devlink: push port related code into separate file

Cut out another chunk from leftover.c and put port related code
into a separate file.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-3-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/Makefile        |    2 +-
 net/devlink/devl_internal.h |   32 +-
 net/devlink/leftover.c      | 1550 +----------------------------------
 net/devlink/port.c          | 1515 ++++++++++++++++++++++++++++++++++
 4 files changed, 1558 insertions(+), 1541 deletions(-)
 create mode 100644 net/devlink/port.c

diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index a087af581847e..456bfb336540a 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o health.o
+obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o health.o
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index eb1d5066c73fe..7d01e2060702d 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -3,6 +3,7 @@
  * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
  */
 
+#include <linux/etherdevice.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/notifier.h>
@@ -11,6 +12,8 @@
 #include <linux/xarray.h>
 #include <net/devlink.h>
 #include <net/net_namespace.h>
+#include <net/rtnetlink.h>
+#include <rdma/ib_verbs.h>
 
 #include "netlink_gen.h"
 
@@ -149,16 +152,37 @@ devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
 
 /* Notify */
 void devlink_notify(struct devlink *devlink, enum devlink_command cmd);
+void devlink_ports_notify_register(struct devlink *devlink);
+void devlink_ports_notify_unregister(struct devlink *devlink);
 
 /* Ports */
+#define ASSERT_DEVLINK_PORT_INITIALIZED(devlink_port)				\
+	WARN_ON_ONCE(!(devlink_port)->initialized)
+
+struct devlink_port *devlink_port_get_by_index(struct devlink *devlink,
+					       unsigned int port_index);
 int devlink_port_netdevice_event(struct notifier_block *nb,
 				 unsigned long event, void *ptr);
-
 struct devlink_port *
 devlink_port_get_from_info(struct devlink *devlink, struct genl_info *info);
 struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink,
 						 struct nlattr **attrs);
 
+/* Linecards */
+struct devlink_linecard {
+	struct list_head list;
+	struct devlink *devlink;
+	unsigned int index;
+	const struct devlink_linecard_ops *ops;
+	void *priv;
+	enum devlink_linecard_state state;
+	struct mutex state_lock; /* Protects state */
+	const char *type;
+	struct devlink_linecard_type *types;
+	unsigned int types_count;
+	struct devlink *nested_devlink;
+};
+
 /* Reload */
 bool devlink_reload_actions_valid(const struct devlink_ops *ops);
 int devlink_reload(struct devlink *devlink, struct net *dest_net,
@@ -190,6 +214,12 @@ int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info)
 int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 					    struct genl_info *info);
 int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 890eafac9f8f7..d14b40fb8fdf2 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -33,20 +33,6 @@
 
 #include "devl_internal.h"
 
-struct devlink_linecard {
-	struct list_head list;
-	struct devlink *devlink;
-	unsigned int index;
-	const struct devlink_linecard_ops *ops;
-	void *priv;
-	enum devlink_linecard_state state;
-	struct mutex state_lock; /* Protects state */
-	const char *type;
-	struct devlink_linecard_type *types;
-	unsigned int types_count;
-	struct devlink *nested_devlink;
-};
-
 /**
  * struct devlink_resource - devlink resource
  * @name: name of the resource
@@ -131,52 +117,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
-#define DEVLINK_PORT_FN_CAPS_VALID_MASK \
-	(_BITUL(__DEVLINK_PORT_FN_ATTR_CAPS_MAX) - 1)
-
-static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = {
-	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY },
-	[DEVLINK_PORT_FN_ATTR_STATE] =
-		NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE,
-				 DEVLINK_PORT_FN_STATE_ACTIVE),
-	[DEVLINK_PORT_FN_ATTR_CAPS] =
-		NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK),
-};
-
-#define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port)				\
-	WARN_ON_ONCE(!(devlink_port)->registered)
-#define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port)			\
-	WARN_ON_ONCE((devlink_port)->registered)
-#define ASSERT_DEVLINK_PORT_INITIALIZED(devlink_port)				\
-	WARN_ON_ONCE(!(devlink_port)->initialized)
-
-static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink,
-						      unsigned int port_index)
-{
-	return xa_load(&devlink->ports, port_index);
-}
-
-struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink,
-						 struct nlattr **attrs)
-{
-	if (attrs[DEVLINK_ATTR_PORT_INDEX]) {
-		u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]);
-		struct devlink_port *devlink_port;
-
-		devlink_port = devlink_port_get_by_index(devlink, port_index);
-		if (!devlink_port)
-			return ERR_PTR(-ENODEV);
-		return devlink_port;
-	}
-	return ERR_PTR(-EINVAL);
-}
-
-struct devlink_port *devlink_port_get_from_info(struct devlink *devlink,
-						struct genl_info *info)
-{
-	return devlink_port_get_from_attrs(devlink, info->attrs);
-}
-
 static inline bool
 devlink_rate_is_leaf(struct devlink_rate *devlink_rate)
 {
@@ -439,138 +379,6 @@ devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb,
 	return 0;
 }
 
-static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps,
-				     u32 cap, bool is_enable)
-{
-	caps->selector |= cap;
-	if (is_enable)
-		caps->value |= cap;
-}
-
-static int devlink_port_fn_roce_fill(struct devlink_port *devlink_port,
-				     struct nla_bitfield32 *caps,
-				     struct netlink_ext_ack *extack)
-{
-	bool is_enable;
-	int err;
-
-	if (!devlink_port->ops->port_fn_roce_get)
-		return 0;
-
-	err = devlink_port->ops->port_fn_roce_get(devlink_port, &is_enable,
-						  extack);
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			return 0;
-		return err;
-	}
-
-	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_ROCE, is_enable);
-	return 0;
-}
-
-static int devlink_port_fn_migratable_fill(struct devlink_port *devlink_port,
-					   struct nla_bitfield32 *caps,
-					   struct netlink_ext_ack *extack)
-{
-	bool is_enable;
-	int err;
-
-	if (!devlink_port->ops->port_fn_migratable_get ||
-	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF)
-		return 0;
-
-	err = devlink_port->ops->port_fn_migratable_get(devlink_port,
-							&is_enable, extack);
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			return 0;
-		return err;
-	}
-
-	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_MIGRATABLE, is_enable);
-	return 0;
-}
-
-static int devlink_port_fn_ipsec_crypto_fill(struct devlink_port *devlink_port,
-					     struct nla_bitfield32 *caps,
-					     struct netlink_ext_ack *extack)
-{
-	bool is_enable;
-	int err;
-
-	if (!devlink_port->ops->port_fn_ipsec_crypto_get ||
-	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF)
-		return 0;
-
-	err = devlink_port->ops->port_fn_ipsec_crypto_get(devlink_port, &is_enable, extack);
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			return 0;
-		return err;
-	}
-
-	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, is_enable);
-	return 0;
-}
-
-static int devlink_port_fn_ipsec_packet_fill(struct devlink_port *devlink_port,
-					     struct nla_bitfield32 *caps,
-					     struct netlink_ext_ack *extack)
-{
-	bool is_enable;
-	int err;
-
-	if (!devlink_port->ops->port_fn_ipsec_packet_get ||
-	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF)
-		return 0;
-
-	err = devlink_port->ops->port_fn_ipsec_packet_get(devlink_port, &is_enable, extack);
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			return 0;
-		return err;
-	}
-
-	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_PACKET, is_enable);
-	return 0;
-}
-
-static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port,
-				     struct sk_buff *msg,
-				     struct netlink_ext_ack *extack,
-				     bool *msg_updated)
-{
-	struct nla_bitfield32 caps = {};
-	int err;
-
-	err = devlink_port_fn_roce_fill(devlink_port, &caps, extack);
-	if (err)
-		return err;
-
-	err = devlink_port_fn_migratable_fill(devlink_port, &caps, extack);
-	if (err)
-		return err;
-
-	err = devlink_port_fn_ipsec_crypto_fill(devlink_port, &caps, extack);
-	if (err)
-		return err;
-
-	err = devlink_port_fn_ipsec_packet_fill(devlink_port, &caps, extack);
-	if (err)
-		return err;
-
-	if (!caps.selector)
-		return 0;
-	err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value,
-				 caps.selector);
-	if (err)
-		return err;
-
-	*msg_updated = true;
-	return 0;
-}
-
 static int
 devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,
 				  struct genl_info *info,
@@ -661,113 +469,6 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port)
-{
-	if (devlink_nl_put_handle(msg, devlink_port->devlink))
-		return -EMSGSIZE;
-	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
-		return -EMSGSIZE;
-	return 0;
-}
-
-size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port)
-{
-	struct devlink *devlink = devlink_port->devlink;
-
-	return nla_total_size(strlen(devlink->dev->bus->name) + 1) /* DEVLINK_ATTR_BUS_NAME */
-	     + nla_total_size(strlen(dev_name(devlink->dev)) + 1) /* DEVLINK_ATTR_DEV_NAME */
-	     + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */
-}
-
-static int devlink_nl_port_attrs_put(struct sk_buff *msg,
-				     struct devlink_port *devlink_port)
-{
-	struct devlink_port_attrs *attrs = &devlink_port->attrs;
-
-	if (!devlink_port->attrs_set)
-		return 0;
-	if (attrs->lanes) {
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_LANES, attrs->lanes))
-			return -EMSGSIZE;
-	}
-	if (nla_put_u8(msg, DEVLINK_ATTR_PORT_SPLITTABLE, attrs->splittable))
-		return -EMSGSIZE;
-	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour))
-		return -EMSGSIZE;
-	switch (devlink_port->attrs.flavour) {
-	case DEVLINK_PORT_FLAVOUR_PCI_PF:
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
-				attrs->pci_pf.controller) ||
-		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf))
-			return -EMSGSIZE;
-		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external))
-			return -EMSGSIZE;
-		break;
-	case DEVLINK_PORT_FLAVOUR_PCI_VF:
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
-				attrs->pci_vf.controller) ||
-		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) ||
-		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf))
-			return -EMSGSIZE;
-		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external))
-			return -EMSGSIZE;
-		break;
-	case DEVLINK_PORT_FLAVOUR_PCI_SF:
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
-				attrs->pci_sf.controller) ||
-		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
-				attrs->pci_sf.pf) ||
-		    nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER,
-				attrs->pci_sf.sf))
-			return -EMSGSIZE;
-		break;
-	case DEVLINK_PORT_FLAVOUR_PHYSICAL:
-	case DEVLINK_PORT_FLAVOUR_CPU:
-	case DEVLINK_PORT_FLAVOUR_DSA:
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER,
-				attrs->phys.port_number))
-			return -EMSGSIZE;
-		if (!attrs->split)
-			return 0;
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP,
-				attrs->phys.port_number))
-			return -EMSGSIZE;
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER,
-				attrs->phys.split_subport_number))
-			return -EMSGSIZE;
-		break;
-	default:
-		break;
-	}
-	return 0;
-}
-
-static int devlink_port_fn_hw_addr_fill(struct devlink_port *port,
-					struct sk_buff *msg,
-					struct netlink_ext_ack *extack,
-					bool *msg_updated)
-{
-	u8 hw_addr[MAX_ADDR_LEN];
-	int hw_addr_len;
-	int err;
-
-	if (!port->ops->port_fn_hw_addr_get)
-		return 0;
-
-	err = port->ops->port_fn_hw_addr_get(port, hw_addr, &hw_addr_len,
-					     extack);
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			return 0;
-		return err;
-	}
-	err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr);
-	if (err)
-		return err;
-	*msg_updated = true;
-	return 0;
-}
-
 static int devlink_nl_rate_fill(struct sk_buff *msg,
 				struct devlink_rate *devlink_rate,
 				enum devlink_command cmd, u32 portid, u32 seq,
@@ -825,259 +526,6 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static bool
-devlink_port_fn_state_valid(enum devlink_port_fn_state state)
-{
-	return state == DEVLINK_PORT_FN_STATE_INACTIVE ||
-	       state == DEVLINK_PORT_FN_STATE_ACTIVE;
-}
-
-static bool
-devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate)
-{
-	return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED ||
-	       opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED;
-}
-
-static int devlink_port_fn_state_fill(struct devlink_port *port,
-				      struct sk_buff *msg,
-				      struct netlink_ext_ack *extack,
-				      bool *msg_updated)
-{
-	enum devlink_port_fn_opstate opstate;
-	enum devlink_port_fn_state state;
-	int err;
-
-	if (!port->ops->port_fn_state_get)
-		return 0;
-
-	err = port->ops->port_fn_state_get(port, &state, &opstate, extack);
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			return 0;
-		return err;
-	}
-	if (!devlink_port_fn_state_valid(state)) {
-		WARN_ON_ONCE(1);
-		NL_SET_ERR_MSG(extack, "Invalid state read from driver");
-		return -EINVAL;
-	}
-	if (!devlink_port_fn_opstate_valid(opstate)) {
-		WARN_ON_ONCE(1);
-		NL_SET_ERR_MSG(extack, "Invalid operational state read from driver");
-		return -EINVAL;
-	}
-	if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) ||
-	    nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate))
-		return -EMSGSIZE;
-	*msg_updated = true;
-	return 0;
-}
-
-static int
-devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable,
-			struct netlink_ext_ack *extack)
-{
-	return devlink_port->ops->port_fn_migratable_set(devlink_port, enable,
-							 extack);
-}
-
-static int
-devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable,
-			 struct netlink_ext_ack *extack)
-{
-	return devlink_port->ops->port_fn_roce_set(devlink_port, enable,
-						   extack);
-}
-
-static int
-devlink_port_fn_ipsec_crypto_set(struct devlink_port *devlink_port, bool enable,
-				 struct netlink_ext_ack *extack)
-{
-	return devlink_port->ops->port_fn_ipsec_crypto_set(devlink_port, enable, extack);
-}
-
-static int
-devlink_port_fn_ipsec_packet_set(struct devlink_port *devlink_port, bool enable,
-				 struct netlink_ext_ack *extack)
-{
-	return devlink_port->ops->port_fn_ipsec_packet_set(devlink_port, enable, extack);
-}
-
-static int devlink_port_fn_caps_set(struct devlink_port *devlink_port,
-				    const struct nlattr *attr,
-				    struct netlink_ext_ack *extack)
-{
-	struct nla_bitfield32 caps;
-	u32 caps_value;
-	int err;
-
-	caps = nla_get_bitfield32(attr);
-	caps_value = caps.value & caps.selector;
-	if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE) {
-		err = devlink_port_fn_roce_set(devlink_port,
-					       caps_value & DEVLINK_PORT_FN_CAP_ROCE,
-					       extack);
-		if (err)
-			return err;
-	}
-	if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) {
-		err = devlink_port_fn_mig_set(devlink_port, caps_value &
-					      DEVLINK_PORT_FN_CAP_MIGRATABLE,
-					      extack);
-		if (err)
-			return err;
-	}
-	if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) {
-		err = devlink_port_fn_ipsec_crypto_set(devlink_port, caps_value &
-						       DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO,
-						       extack);
-		if (err)
-			return err;
-	}
-	if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) {
-		err = devlink_port_fn_ipsec_packet_set(devlink_port, caps_value &
-						       DEVLINK_PORT_FN_CAP_IPSEC_PACKET,
-						       extack);
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
-static int
-devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port,
-				   struct netlink_ext_ack *extack)
-{
-	struct nlattr *function_attr;
-	bool msg_updated = false;
-	int err;
-
-	function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION);
-	if (!function_attr)
-		return -EMSGSIZE;
-
-	err = devlink_port_fn_hw_addr_fill(port, msg, extack, &msg_updated);
-	if (err)
-		goto out;
-	err = devlink_port_fn_caps_fill(port, msg, extack, &msg_updated);
-	if (err)
-		goto out;
-	err = devlink_port_fn_state_fill(port, msg, extack, &msg_updated);
-out:
-	if (err || !msg_updated)
-		nla_nest_cancel(msg, function_attr);
-	else
-		nla_nest_end(msg, function_attr);
-	return err;
-}
-
-static int devlink_nl_port_fill(struct sk_buff *msg,
-				struct devlink_port *devlink_port,
-				enum devlink_command cmd, u32 portid, u32 seq,
-				int flags, struct netlink_ext_ack *extack)
-{
-	struct devlink *devlink = devlink_port->devlink;
-	void *hdr;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
-		goto nla_put_failure;
-
-	spin_lock_bh(&devlink_port->type_lock);
-	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))
-		goto nla_put_failure_type_locked;
-	if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET &&
-	    nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE,
-			devlink_port->desired_type))
-		goto nla_put_failure_type_locked;
-	if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
-		if (devlink_port->type_eth.netdev &&
-		    (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
-				 devlink_port->type_eth.ifindex) ||
-		     nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,
-				    devlink_port->type_eth.ifname)))
-			goto nla_put_failure_type_locked;
-	}
-	if (devlink_port->type == DEVLINK_PORT_TYPE_IB) {
-		struct ib_device *ibdev = devlink_port->type_ib.ibdev;
-
-		if (ibdev &&
-		    nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME,
-				   ibdev->name))
-			goto nla_put_failure_type_locked;
-	}
-	spin_unlock_bh(&devlink_port->type_lock);
-	if (devlink_nl_port_attrs_put(msg, devlink_port))
-		goto nla_put_failure;
-	if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack))
-		goto nla_put_failure;
-	if (devlink_port->linecard &&
-	    nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX,
-			devlink_port->linecard->index))
-		goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-	return 0;
-
-nla_put_failure_type_locked:
-	spin_unlock_bh(&devlink_port->type_lock);
-nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
-}
-
-static void devlink_port_notify(struct devlink_port *devlink_port,
-				enum devlink_command cmd)
-{
-	struct devlink *devlink = devlink_port->devlink;
-	struct sk_buff *msg;
-	int err;
-
-	WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL);
-
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
-		return;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return;
-
-	err = devlink_nl_port_fill(msg, devlink_port, cmd, 0, 0, 0, NULL);
-	if (err) {
-		nlmsg_free(msg);
-		return;
-	}
-
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
-}
-
-static void devlink_ports_notify(struct devlink *devlink,
-				 enum devlink_command cmd)
-{
-	struct devlink_port *devlink_port;
-	unsigned long port_index;
-
-	xa_for_each(&devlink->ports, port_index, devlink_port)
-		devlink_port_notify(devlink_port, cmd);
-}
-
-static void devlink_ports_notify_register(struct devlink *devlink)
-{
-	devlink_ports_notify(devlink, DEVLINK_CMD_PORT_NEW);
-}
-
-static void devlink_ports_notify_unregister(struct devlink *devlink)
-{
-	devlink_ports_notify(devlink, DEVLINK_CMD_PORT_DEL);
-}
-
 static void devlink_rate_notify(struct devlink_rate *devlink_rate,
 				enum devlink_command cmd)
 {
@@ -1176,391 +624,20 @@ int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info)
 		nlmsg_free(msg);
 		return err;
 	}
-
-	return genlmsg_reply(msg, info);
-}
-
-static bool
-devlink_rate_is_parent_node(struct devlink_rate *devlink_rate,
-			    struct devlink_rate *parent)
-{
-	while (parent) {
-		if (parent == devlink_rate)
-			return true;
-		parent = parent->parent;
-	}
-	return false;
-}
-
-int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct devlink_port *devlink_port = info->user_ptr[1];
-	struct sk_buff *msg;
-	int err;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW,
-				   info->snd_portid, info->snd_seq, 0,
-				   info->extack);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
-
-	return genlmsg_reply(msg, info);
-}
-
-static int
-devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-			     struct netlink_callback *cb, int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_port *devlink_port;
-	unsigned long port_index;
-	int err = 0;
-
-	xa_for_each_start(&devlink->ports, port_index, devlink_port, state->idx) {
-		err = devlink_nl_port_fill(msg, devlink_port,
-					   DEVLINK_CMD_NEW,
-					   NETLINK_CB(cb->skb).portid,
-					   cb->nlh->nlmsg_seq, flags,
-					   cb->extack);
-		if (err) {
-			state->idx = port_index;
-			break;
-		}
-	}
-
-	return err;
-}
-
-int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_port_get_dump_one);
-}
-
-static int devlink_port_type_set(struct devlink_port *devlink_port,
-				 enum devlink_port_type port_type)
-
-{
-	int err;
-
-	if (!devlink_port->ops->port_type_set)
-		return -EOPNOTSUPP;
-
-	if (port_type == devlink_port->type)
-		return 0;
-
-	err = devlink_port->ops->port_type_set(devlink_port, port_type);
-	if (err)
-		return err;
-
-	devlink_port->desired_type = port_type;
-	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
-	return 0;
-}
-
-static int devlink_port_function_hw_addr_set(struct devlink_port *port,
-					     const struct nlattr *attr,
-					     struct netlink_ext_ack *extack)
-{
-	const u8 *hw_addr;
-	int hw_addr_len;
-
-	hw_addr = nla_data(attr);
-	hw_addr_len = nla_len(attr);
-	if (hw_addr_len > MAX_ADDR_LEN) {
-		NL_SET_ERR_MSG(extack, "Port function hardware address too long");
-		return -EINVAL;
-	}
-	if (port->type == DEVLINK_PORT_TYPE_ETH) {
-		if (hw_addr_len != ETH_ALEN) {
-			NL_SET_ERR_MSG(extack, "Address must be 6 bytes for Ethernet device");
-			return -EINVAL;
-		}
-		if (!is_unicast_ether_addr(hw_addr)) {
-			NL_SET_ERR_MSG(extack, "Non-unicast hardware address unsupported");
-			return -EINVAL;
-		}
-	}
-
-	return port->ops->port_fn_hw_addr_set(port, hw_addr, hw_addr_len,
-					      extack);
-}
-
-static int devlink_port_fn_state_set(struct devlink_port *port,
-				     const struct nlattr *attr,
-				     struct netlink_ext_ack *extack)
-{
-	enum devlink_port_fn_state state;
-
-	state = nla_get_u8(attr);
-	return port->ops->port_fn_state_set(port, state, extack);
-}
-
-static int devlink_port_function_validate(struct devlink_port *devlink_port,
-					  struct nlattr **tb,
-					  struct netlink_ext_ack *extack)
-{
-	const struct devlink_port_ops *ops = devlink_port->ops;
-	struct nlattr *attr;
-
-	if (tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] &&
-	    !ops->port_fn_hw_addr_set) {
-		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR],
-				    "Port doesn't support function attributes");
-		return -EOPNOTSUPP;
-	}
-	if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) {
-		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR],
-				    "Function does not support state setting");
-		return -EOPNOTSUPP;
-	}
-	attr = tb[DEVLINK_PORT_FN_ATTR_CAPS];
-	if (attr) {
-		struct nla_bitfield32 caps;
-
-		caps = nla_get_bitfield32(attr);
-		if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE &&
-		    !ops->port_fn_roce_set) {
-			NL_SET_ERR_MSG_ATTR(extack, attr,
-					    "Port doesn't support RoCE function attribute");
-			return -EOPNOTSUPP;
-		}
-		if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) {
-			if (!ops->port_fn_migratable_set) {
-				NL_SET_ERR_MSG_ATTR(extack, attr,
-						    "Port doesn't support migratable function attribute");
-				return -EOPNOTSUPP;
-			}
-			if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) {
-				NL_SET_ERR_MSG_ATTR(extack, attr,
-						    "migratable function attribute supported for VFs only");
-				return -EOPNOTSUPP;
-			}
-		}
-		if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) {
-			if (!ops->port_fn_ipsec_crypto_set) {
-				NL_SET_ERR_MSG_ATTR(extack, attr,
-						    "Port doesn't support ipsec_crypto function attribute");
-				return -EOPNOTSUPP;
-			}
-			if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) {
-				NL_SET_ERR_MSG_ATTR(extack, attr,
-						    "ipsec_crypto function attribute supported for VFs only");
-				return -EOPNOTSUPP;
-			}
-		}
-		if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) {
-			if (!ops->port_fn_ipsec_packet_set) {
-				NL_SET_ERR_MSG_ATTR(extack, attr,
-						    "Port doesn't support ipsec_packet function attribute");
-				return -EOPNOTSUPP;
-			}
-			if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) {
-				NL_SET_ERR_MSG_ATTR(extack, attr,
-						    "ipsec_packet function attribute supported for VFs only");
-				return -EOPNOTSUPP;
-			}
-		}
-	}
-	return 0;
-}
-
-static int devlink_port_function_set(struct devlink_port *port,
-				     const struct nlattr *attr,
-				     struct netlink_ext_ack *extack)
-{
-	struct nlattr *tb[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1];
-	int err;
-
-	err = nla_parse_nested(tb, DEVLINK_PORT_FUNCTION_ATTR_MAX, attr,
-			       devlink_function_nl_policy, extack);
-	if (err < 0) {
-		NL_SET_ERR_MSG(extack, "Fail to parse port function attributes");
-		return err;
-	}
-
-	err = devlink_port_function_validate(port, tb, extack);
-	if (err)
-		return err;
-
-	attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR];
-	if (attr) {
-		err = devlink_port_function_hw_addr_set(port, attr, extack);
-		if (err)
-			return err;
-	}
-
-	attr = tb[DEVLINK_PORT_FN_ATTR_CAPS];
-	if (attr) {
-		err = devlink_port_fn_caps_set(port, attr, extack);
-		if (err)
-			return err;
-	}
-
-	/* Keep this as the last function attribute set, so that when
-	 * multiple port function attributes are set along with state,
-	 * Those can be applied first before activating the state.
-	 */
-	attr = tb[DEVLINK_PORT_FN_ATTR_STATE];
-	if (attr)
-		err = devlink_port_fn_state_set(port, attr, extack);
-
-	if (!err)
-		devlink_port_notify(port, DEVLINK_CMD_PORT_NEW);
-	return err;
-}
-
-static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb,
-					struct genl_info *info)
-{
-	struct devlink_port *devlink_port = info->user_ptr[1];
-	int err;
-
-	if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) {
-		enum devlink_port_type port_type;
-
-		port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]);
-		err = devlink_port_type_set(devlink_port, port_type);
-		if (err)
-			return err;
-	}
-
-	if (info->attrs[DEVLINK_ATTR_PORT_FUNCTION]) {
-		struct nlattr *attr = info->attrs[DEVLINK_ATTR_PORT_FUNCTION];
-		struct netlink_ext_ack *extack = info->extack;
-
-		err = devlink_port_function_set(devlink_port, attr, extack);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb,
-					  struct genl_info *info)
-{
-	struct devlink_port *devlink_port = info->user_ptr[1];
-	struct devlink *devlink = info->user_ptr[0];
-	u32 count;
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_SPLIT_COUNT))
-		return -EINVAL;
-	if (!devlink_port->ops->port_split)
-		return -EOPNOTSUPP;
-
-	count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]);
-
-	if (!devlink_port->attrs.splittable) {
-		/* Split ports cannot be split. */
-		if (devlink_port->attrs.split)
-			NL_SET_ERR_MSG(info->extack, "Port cannot be split further");
-		else
-			NL_SET_ERR_MSG(info->extack, "Port cannot be split");
-		return -EINVAL;
-	}
-
-	if (count < 2 || !is_power_of_2(count) || count > devlink_port->attrs.lanes) {
-		NL_SET_ERR_MSG(info->extack, "Invalid split count");
-		return -EINVAL;
-	}
-
-	return devlink_port->ops->port_split(devlink, devlink_port, count,
-					     info->extack);
-}
-
-static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb,
-					    struct genl_info *info)
-{
-	struct devlink_port *devlink_port = info->user_ptr[1];
-	struct devlink *devlink = info->user_ptr[0];
-
-	if (!devlink_port->ops->port_unsplit)
-		return -EOPNOTSUPP;
-	return devlink_port->ops->port_unsplit(devlink, devlink_port, info->extack);
-}
-
-static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb,
-					struct genl_info *info)
-{
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink_port_new_attrs new_attrs = {};
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_port *devlink_port;
-	struct sk_buff *msg;
-	int err;
-
-	if (!devlink->ops->port_new)
-		return -EOPNOTSUPP;
-
-	if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] ||
-	    !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) {
-		NL_SET_ERR_MSG(extack, "Port flavour or PCI PF are not specified");
-		return -EINVAL;
-	}
-	new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]);
-	new_attrs.pfnum =
-		nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]);
-
-	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
-		/* Port index of the new port being created by driver. */
-		new_attrs.port_index =
-			nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
-		new_attrs.port_index_valid = true;
-	}
-	if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) {
-		new_attrs.controller =
-			nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]);
-		new_attrs.controller_valid = true;
-	}
-	if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF &&
-	    info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) {
-		new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]);
-		new_attrs.sfnum_valid = true;
-	}
-
-	err = devlink->ops->port_new(devlink, &new_attrs,
-				     extack, &devlink_port);
-	if (err)
-		return err;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg) {
-		err = -ENOMEM;
-		goto err_out_port_del;
-	}
-	err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW,
-				   info->snd_portid, info->snd_seq, 0, NULL);
-	if (WARN_ON_ONCE(err))
-		goto err_out_msg_free;
-	err = genlmsg_reply(msg, info);
-	if (err)
-		goto err_out_port_del;
-	return 0;
-
-err_out_msg_free:
-	nlmsg_free(msg);
-err_out_port_del:
-	devlink_port->ops->port_del(devlink, devlink_port, NULL);
-	return err;
+
+	return genlmsg_reply(msg, info);
 }
 
-static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb,
-					struct genl_info *info)
+static bool
+devlink_rate_is_parent_node(struct devlink_rate *devlink_rate,
+			    struct devlink_rate *parent)
 {
-	struct devlink_port *devlink_port = info->user_ptr[1];
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink *devlink = info->user_ptr[0];
-
-	if (!devlink_port->ops->port_del)
-		return -EOPNOTSUPP;
-
-	return devlink_port->ops->port_del(devlink, devlink_port, extack);
+	while (parent) {
+		if (parent == devlink_rate)
+			return true;
+		parent = parent->parent;
+	}
+	return false;
 }
 
 static int
@@ -6783,489 +5860,6 @@ void devlink_notify_unregister(struct devlink *devlink)
 	devlink_notify(devlink, DEVLINK_CMD_DEL);
 }
 
-static void devlink_port_type_warn(struct work_struct *work)
-{
-	struct devlink_port *port = container_of(to_delayed_work(work),
-						 struct devlink_port,
-						 type_warn_dw);
-	dev_warn(port->devlink->dev, "Type was not set for devlink port.");
-}
-
-static bool devlink_port_type_should_warn(struct devlink_port *devlink_port)
-{
-	/* Ignore CPU and DSA flavours. */
-	return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU &&
-	       devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA &&
-	       devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED;
-}
-
-#define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600)
-
-static void devlink_port_type_warn_schedule(struct devlink_port *devlink_port)
-{
-	if (!devlink_port_type_should_warn(devlink_port))
-		return;
-	/* Schedule a work to WARN in case driver does not set port
-	 * type within timeout.
-	 */
-	schedule_delayed_work(&devlink_port->type_warn_dw,
-			      DEVLINK_PORT_TYPE_WARN_TIMEOUT);
-}
-
-static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port)
-{
-	if (!devlink_port_type_should_warn(devlink_port))
-		return;
-	cancel_delayed_work_sync(&devlink_port->type_warn_dw);
-}
-
-/**
- * devlink_port_init() - Init devlink port
- *
- * @devlink: devlink
- * @devlink_port: devlink port
- *
- * Initialize essential stuff that is needed for functions
- * that may be called before devlink port registration.
- * Call to this function is optional and not needed
- * in case the driver does not use such functions.
- */
-void devlink_port_init(struct devlink *devlink,
-		       struct devlink_port *devlink_port)
-{
-	if (devlink_port->initialized)
-		return;
-	devlink_port->devlink = devlink;
-	INIT_LIST_HEAD(&devlink_port->region_list);
-	devlink_port->initialized = true;
-}
-EXPORT_SYMBOL_GPL(devlink_port_init);
-
-/**
- * devlink_port_fini() - Deinitialize devlink port
- *
- * @devlink_port: devlink port
- *
- * Deinitialize essential stuff that is in use for functions
- * that may be called after devlink port unregistration.
- * Call to this function is optional and not needed
- * in case the driver does not use such functions.
- */
-void devlink_port_fini(struct devlink_port *devlink_port)
-{
-	WARN_ON(!list_empty(&devlink_port->region_list));
-}
-EXPORT_SYMBOL_GPL(devlink_port_fini);
-
-static const struct devlink_port_ops devlink_port_dummy_ops = {};
-
-/**
- * devl_port_register_with_ops() - Register devlink port
- *
- * @devlink: devlink
- * @devlink_port: devlink port
- * @port_index: driver-specific numerical identifier of the port
- * @ops: port ops
- *
- * Register devlink port with provided port index. User can use
- * any indexing, even hw-related one. devlink_port structure
- * is convenient to be embedded inside user driver private structure.
- * Note that the caller should take care of zeroing the devlink_port
- * structure.
- */
-int devl_port_register_with_ops(struct devlink *devlink,
-				struct devlink_port *devlink_port,
-				unsigned int port_index,
-				const struct devlink_port_ops *ops)
-{
-	int err;
-
-	devl_assert_locked(devlink);
-
-	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
-
-	devlink_port_init(devlink, devlink_port);
-	devlink_port->registered = true;
-	devlink_port->index = port_index;
-	devlink_port->ops = ops ? ops : &devlink_port_dummy_ops;
-	spin_lock_init(&devlink_port->type_lock);
-	INIT_LIST_HEAD(&devlink_port->reporter_list);
-	err = xa_insert(&devlink->ports, port_index, devlink_port, GFP_KERNEL);
-	if (err) {
-		devlink_port->registered = false;
-		return err;
-	}
-
-	INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn);
-	devlink_port_type_warn_schedule(devlink_port);
-	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devl_port_register_with_ops);
-
-/**
- *	devlink_port_register_with_ops - Register devlink port
- *
- *	@devlink: devlink
- *	@devlink_port: devlink port
- *	@port_index: driver-specific numerical identifier of the port
- *	@ops: port ops
- *
- *	Register devlink port with provided port index. User can use
- *	any indexing, even hw-related one. devlink_port structure
- *	is convenient to be embedded inside user driver private structure.
- *	Note that the caller should take care of zeroing the devlink_port
- *	structure.
- *
- *	Context: Takes and release devlink->lock <mutex>.
- */
-int devlink_port_register_with_ops(struct devlink *devlink,
-				   struct devlink_port *devlink_port,
-				   unsigned int port_index,
-				   const struct devlink_port_ops *ops)
-{
-	int err;
-
-	devl_lock(devlink);
-	err = devl_port_register_with_ops(devlink, devlink_port,
-					  port_index, ops);
-	devl_unlock(devlink);
-	return err;
-}
-EXPORT_SYMBOL_GPL(devlink_port_register_with_ops);
-
-/**
- * devl_port_unregister() - Unregister devlink port
- *
- * @devlink_port: devlink port
- */
-void devl_port_unregister(struct devlink_port *devlink_port)
-{
-	lockdep_assert_held(&devlink_port->devlink->lock);
-	WARN_ON(devlink_port->type != DEVLINK_PORT_TYPE_NOTSET);
-
-	devlink_port_type_warn_cancel(devlink_port);
-	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL);
-	xa_erase(&devlink_port->devlink->ports, devlink_port->index);
-	WARN_ON(!list_empty(&devlink_port->reporter_list));
-	devlink_port->registered = false;
-}
-EXPORT_SYMBOL_GPL(devl_port_unregister);
-
-/**
- *	devlink_port_unregister - Unregister devlink port
- *
- *	@devlink_port: devlink port
- *
- *	Context: Takes and release devlink->lock <mutex>.
- */
-void devlink_port_unregister(struct devlink_port *devlink_port)
-{
-	struct devlink *devlink = devlink_port->devlink;
-
-	devl_lock(devlink);
-	devl_port_unregister(devlink_port);
-	devl_unlock(devlink);
-}
-EXPORT_SYMBOL_GPL(devlink_port_unregister);
-
-static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port,
-					    struct net_device *netdev)
-{
-	const struct net_device_ops *ops = netdev->netdev_ops;
-
-	/* If driver registers devlink port, it should set devlink port
-	 * attributes accordingly so the compat functions are called
-	 * and the original ops are not used.
-	 */
-	if (ops->ndo_get_phys_port_name) {
-		/* Some drivers use the same set of ndos for netdevs
-		 * that have devlink_port registered and also for
-		 * those who don't. Make sure that ndo_get_phys_port_name
-		 * returns -EOPNOTSUPP here in case it is defined.
-		 * Warn if not.
-		 */
-		char name[IFNAMSIZ];
-		int err;
-
-		err = ops->ndo_get_phys_port_name(netdev, name, sizeof(name));
-		WARN_ON(err != -EOPNOTSUPP);
-	}
-	if (ops->ndo_get_port_parent_id) {
-		/* Some drivers use the same set of ndos for netdevs
-		 * that have devlink_port registered and also for
-		 * those who don't. Make sure that ndo_get_port_parent_id
-		 * returns -EOPNOTSUPP here in case it is defined.
-		 * Warn if not.
-		 */
-		struct netdev_phys_item_id ppid;
-		int err;
-
-		err = ops->ndo_get_port_parent_id(netdev, &ppid);
-		WARN_ON(err != -EOPNOTSUPP);
-	}
-}
-
-static void __devlink_port_type_set(struct devlink_port *devlink_port,
-				    enum devlink_port_type type,
-				    void *type_dev)
-{
-	struct net_device *netdev = type_dev;
-
-	ASSERT_DEVLINK_PORT_REGISTERED(devlink_port);
-
-	if (type == DEVLINK_PORT_TYPE_NOTSET) {
-		devlink_port_type_warn_schedule(devlink_port);
-	} else {
-		devlink_port_type_warn_cancel(devlink_port);
-		if (type == DEVLINK_PORT_TYPE_ETH && netdev)
-			devlink_port_type_netdev_checks(devlink_port, netdev);
-	}
-
-	spin_lock_bh(&devlink_port->type_lock);
-	devlink_port->type = type;
-	switch (type) {
-	case DEVLINK_PORT_TYPE_ETH:
-		devlink_port->type_eth.netdev = netdev;
-		if (netdev) {
-			ASSERT_RTNL();
-			devlink_port->type_eth.ifindex = netdev->ifindex;
-			BUILD_BUG_ON(sizeof(devlink_port->type_eth.ifname) !=
-				     sizeof(netdev->name));
-			strcpy(devlink_port->type_eth.ifname, netdev->name);
-		}
-		break;
-	case DEVLINK_PORT_TYPE_IB:
-		devlink_port->type_ib.ibdev = type_dev;
-		break;
-	default:
-		break;
-	}
-	spin_unlock_bh(&devlink_port->type_lock);
-	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
-}
-
-/**
- *	devlink_port_type_eth_set - Set port type to Ethernet
- *
- *	@devlink_port: devlink port
- *
- *	If driver is calling this, most likely it is doing something wrong.
- */
-void devlink_port_type_eth_set(struct devlink_port *devlink_port)
-{
-	dev_warn(devlink_port->devlink->dev,
-		 "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n",
-		 devlink_port->index);
-	__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL);
-}
-EXPORT_SYMBOL_GPL(devlink_port_type_eth_set);
-
-/**
- *	devlink_port_type_ib_set - Set port type to InfiniBand
- *
- *	@devlink_port: devlink port
- *	@ibdev: related IB device
- */
-void devlink_port_type_ib_set(struct devlink_port *devlink_port,
-			      struct ib_device *ibdev)
-{
-	__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_IB, ibdev);
-}
-EXPORT_SYMBOL_GPL(devlink_port_type_ib_set);
-
-/**
- *	devlink_port_type_clear - Clear port type
- *
- *	@devlink_port: devlink port
- *
- *	If driver is calling this for clearing Ethernet type, most likely
- *	it is doing something wrong.
- */
-void devlink_port_type_clear(struct devlink_port *devlink_port)
-{
-	if (devlink_port->type == DEVLINK_PORT_TYPE_ETH)
-		dev_warn(devlink_port->devlink->dev,
-			 "devlink port type for port %d cleared without a software interface reference, device type not supported by the kernel?\n",
-			 devlink_port->index);
-	__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL);
-}
-EXPORT_SYMBOL_GPL(devlink_port_type_clear);
-
-int devlink_port_netdevice_event(struct notifier_block *nb,
-				 unsigned long event, void *ptr)
-{
-	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
-	struct devlink_port *devlink_port = netdev->devlink_port;
-	struct devlink *devlink;
-
-	if (!devlink_port)
-		return NOTIFY_OK;
-	devlink = devlink_port->devlink;
-
-	switch (event) {
-	case NETDEV_POST_INIT:
-		/* Set the type but not netdev pointer. It is going to be set
-		 * later on by NETDEV_REGISTER event. Happens once during
-		 * netdevice register
-		 */
-		__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH,
-					NULL);
-		break;
-	case NETDEV_REGISTER:
-	case NETDEV_CHANGENAME:
-		if (devlink_net(devlink) != dev_net(netdev))
-			return NOTIFY_OK;
-		/* Set the netdev on top of previously set type. Note this
-		 * event happens also during net namespace change so here
-		 * we take into account netdev pointer appearing in this
-		 * namespace.
-		 */
-		__devlink_port_type_set(devlink_port, devlink_port->type,
-					netdev);
-		break;
-	case NETDEV_UNREGISTER:
-		if (devlink_net(devlink) != dev_net(netdev))
-			return NOTIFY_OK;
-		/* Clear netdev pointer, but not the type. This event happens
-		 * also during net namespace change so we need to clear
-		 * pointer to netdev that is going to another net namespace.
-		 */
-		__devlink_port_type_set(devlink_port, devlink_port->type,
-					NULL);
-		break;
-	case NETDEV_PRE_UNINIT:
-		/* Clear the type and the netdev pointer. Happens one during
-		 * netdevice unregister.
-		 */
-		__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET,
-					NULL);
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static int __devlink_port_attrs_set(struct devlink_port *devlink_port,
-				    enum devlink_port_flavour flavour)
-{
-	struct devlink_port_attrs *attrs = &devlink_port->attrs;
-
-	devlink_port->attrs_set = true;
-	attrs->flavour = flavour;
-	if (attrs->switch_id.id_len) {
-		devlink_port->switch_port = true;
-		if (WARN_ON(attrs->switch_id.id_len > MAX_PHYS_ITEM_ID_LEN))
-			attrs->switch_id.id_len = MAX_PHYS_ITEM_ID_LEN;
-	} else {
-		devlink_port->switch_port = false;
-	}
-	return 0;
-}
-
-/**
- *	devlink_port_attrs_set - Set port attributes
- *
- *	@devlink_port: devlink port
- *	@attrs: devlink port attrs
- */
-void devlink_port_attrs_set(struct devlink_port *devlink_port,
-			    struct devlink_port_attrs *attrs)
-{
-	int ret;
-
-	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
-
-	devlink_port->attrs = *attrs;
-	ret = __devlink_port_attrs_set(devlink_port, attrs->flavour);
-	if (ret)
-		return;
-	WARN_ON(attrs->splittable && attrs->split);
-}
-EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
-
-/**
- *	devlink_port_attrs_pci_pf_set - Set PCI PF port attributes
- *
- *	@devlink_port: devlink port
- *	@controller: associated controller number for the devlink port instance
- *	@pf: associated PF for the devlink port instance
- *	@external: indicates if the port is for an external controller
- */
-void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller,
-				   u16 pf, bool external)
-{
-	struct devlink_port_attrs *attrs = &devlink_port->attrs;
-	int ret;
-
-	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
-
-	ret = __devlink_port_attrs_set(devlink_port,
-				       DEVLINK_PORT_FLAVOUR_PCI_PF);
-	if (ret)
-		return;
-	attrs->pci_pf.controller = controller;
-	attrs->pci_pf.pf = pf;
-	attrs->pci_pf.external = external;
-}
-EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set);
-
-/**
- *	devlink_port_attrs_pci_vf_set - Set PCI VF port attributes
- *
- *	@devlink_port: devlink port
- *	@controller: associated controller number for the devlink port instance
- *	@pf: associated PF for the devlink port instance
- *	@vf: associated VF of a PF for the devlink port instance
- *	@external: indicates if the port is for an external controller
- */
-void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller,
-				   u16 pf, u16 vf, bool external)
-{
-	struct devlink_port_attrs *attrs = &devlink_port->attrs;
-	int ret;
-
-	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
-
-	ret = __devlink_port_attrs_set(devlink_port,
-				       DEVLINK_PORT_FLAVOUR_PCI_VF);
-	if (ret)
-		return;
-	attrs->pci_vf.controller = controller;
-	attrs->pci_vf.pf = pf;
-	attrs->pci_vf.vf = vf;
-	attrs->pci_vf.external = external;
-}
-EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set);
-
-/**
- *	devlink_port_attrs_pci_sf_set - Set PCI SF port attributes
- *
- *	@devlink_port: devlink port
- *	@controller: associated controller number for the devlink port instance
- *	@pf: associated PF for the devlink port instance
- *	@sf: associated SF of a PF for the devlink port instance
- *	@external: indicates if the port is for an external controller
- */
-void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller,
-				   u16 pf, u32 sf, bool external)
-{
-	struct devlink_port_attrs *attrs = &devlink_port->attrs;
-	int ret;
-
-	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
-
-	ret = __devlink_port_attrs_set(devlink_port,
-				       DEVLINK_PORT_FLAVOUR_PCI_SF);
-	if (ret)
-		return;
-	attrs->pci_sf.controller = controller;
-	attrs->pci_sf.pf = pf;
-	attrs->pci_sf.sf = sf;
-	attrs->pci_sf.external = external;
-}
-EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set);
-
 /**
  * devl_rate_node_create - create devlink rate node
  * @devlink: devlink instance
@@ -7412,92 +6006,6 @@ void devl_rate_nodes_destroy(struct devlink *devlink)
 }
 EXPORT_SYMBOL_GPL(devl_rate_nodes_destroy);
 
-/**
- *	devlink_port_linecard_set - Link port with a linecard
- *
- *	@devlink_port: devlink port
- *	@linecard: devlink linecard
- */
-void devlink_port_linecard_set(struct devlink_port *devlink_port,
-			       struct devlink_linecard *linecard)
-{
-	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
-
-	devlink_port->linecard = linecard;
-}
-EXPORT_SYMBOL_GPL(devlink_port_linecard_set);
-
-static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
-					     char *name, size_t len)
-{
-	struct devlink_port_attrs *attrs = &devlink_port->attrs;
-	int n = 0;
-
-	if (!devlink_port->attrs_set)
-		return -EOPNOTSUPP;
-
-	switch (attrs->flavour) {
-	case DEVLINK_PORT_FLAVOUR_PHYSICAL:
-		if (devlink_port->linecard)
-			n = snprintf(name, len, "l%u",
-				     devlink_port->linecard->index);
-		if (n < len)
-			n += snprintf(name + n, len - n, "p%u",
-				      attrs->phys.port_number);
-		if (n < len && attrs->split)
-			n += snprintf(name + n, len - n, "s%u",
-				      attrs->phys.split_subport_number);
-		break;
-	case DEVLINK_PORT_FLAVOUR_CPU:
-	case DEVLINK_PORT_FLAVOUR_DSA:
-	case DEVLINK_PORT_FLAVOUR_UNUSED:
-		/* As CPU and DSA ports do not have a netdevice associated
-		 * case should not ever happen.
-		 */
-		WARN_ON(1);
-		return -EINVAL;
-	case DEVLINK_PORT_FLAVOUR_PCI_PF:
-		if (attrs->pci_pf.external) {
-			n = snprintf(name, len, "c%u", attrs->pci_pf.controller);
-			if (n >= len)
-				return -EINVAL;
-			len -= n;
-			name += n;
-		}
-		n = snprintf(name, len, "pf%u", attrs->pci_pf.pf);
-		break;
-	case DEVLINK_PORT_FLAVOUR_PCI_VF:
-		if (attrs->pci_vf.external) {
-			n = snprintf(name, len, "c%u", attrs->pci_vf.controller);
-			if (n >= len)
-				return -EINVAL;
-			len -= n;
-			name += n;
-		}
-		n = snprintf(name, len, "pf%uvf%u",
-			     attrs->pci_vf.pf, attrs->pci_vf.vf);
-		break;
-	case DEVLINK_PORT_FLAVOUR_PCI_SF:
-		if (attrs->pci_sf.external) {
-			n = snprintf(name, len, "c%u", attrs->pci_sf.controller);
-			if (n >= len)
-				return -EINVAL;
-			len -= n;
-			name += n;
-		}
-		n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf,
-			     attrs->pci_sf.sf);
-		break;
-	case DEVLINK_PORT_FLAVOUR_VIRTUAL:
-		return -EOPNOTSUPP;
-	}
-
-	if (n >= len)
-		return -EINVAL;
-
-	return 0;
-}
-
 static int devlink_linecard_types_init(struct devlink_linecard *linecard)
 {
 	struct devlink_linecard_type *linecard_type;
@@ -9572,39 +8080,3 @@ devl_trap_policers_unregister(struct devlink *devlink,
 		devlink_trap_policer_unregister(devlink, &policers[i]);
 }
 EXPORT_SYMBOL_GPL(devl_trap_policers_unregister);
-
-int devlink_compat_phys_port_name_get(struct net_device *dev,
-				      char *name, size_t len)
-{
-	struct devlink_port *devlink_port;
-
-	/* RTNL mutex is held here which ensures that devlink_port
-	 * instance cannot disappear in the middle. No need to take
-	 * any devlink lock as only permanent values are accessed.
-	 */
-	ASSERT_RTNL();
-
-	devlink_port = dev->devlink_port;
-	if (!devlink_port)
-		return -EOPNOTSUPP;
-
-	return __devlink_port_phys_port_name_get(devlink_port, name, len);
-}
-
-int devlink_compat_switch_id_get(struct net_device *dev,
-				 struct netdev_phys_item_id *ppid)
-{
-	struct devlink_port *devlink_port;
-
-	/* Caller must hold RTNL mutex or reference to dev, which ensures that
-	 * devlink_port instance cannot disappear in the middle. No need to take
-	 * any devlink lock as only permanent values are accessed.
-	 */
-	devlink_port = dev->devlink_port;
-	if (!devlink_port || !devlink_port->switch_port)
-		return -EOPNOTSUPP;
-
-	memcpy(ppid, &devlink_port->attrs.switch_id, sizeof(*ppid));
-
-	return 0;
-}
diff --git a/net/devlink/port.c b/net/devlink/port.c
new file mode 100644
index 0000000000000..4763b42885fbd
--- /dev/null
+++ b/net/devlink/port.c
@@ -0,0 +1,1515 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include "devl_internal.h"
+
+#define DEVLINK_PORT_FN_CAPS_VALID_MASK \
+	(_BITUL(__DEVLINK_PORT_FN_ATTR_CAPS_MAX) - 1)
+
+static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = {
+	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY },
+	[DEVLINK_PORT_FN_ATTR_STATE] =
+		NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE,
+				 DEVLINK_PORT_FN_STATE_ACTIVE),
+	[DEVLINK_PORT_FN_ATTR_CAPS] =
+		NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK),
+};
+
+#define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port)				\
+	WARN_ON_ONCE(!(devlink_port)->registered)
+#define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port)			\
+	WARN_ON_ONCE((devlink_port)->registered)
+
+struct devlink_port *devlink_port_get_by_index(struct devlink *devlink,
+					       unsigned int port_index)
+{
+	return xa_load(&devlink->ports, port_index);
+}
+
+struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink,
+						 struct nlattr **attrs)
+{
+	if (attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]);
+		struct devlink_port *devlink_port;
+
+		devlink_port = devlink_port_get_by_index(devlink, port_index);
+		if (!devlink_port)
+			return ERR_PTR(-ENODEV);
+		return devlink_port;
+	}
+	return ERR_PTR(-EINVAL);
+}
+
+struct devlink_port *devlink_port_get_from_info(struct devlink *devlink,
+						struct genl_info *info)
+{
+	return devlink_port_get_from_attrs(devlink, info->attrs);
+}
+
+static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps,
+				     u32 cap, bool is_enable)
+{
+	caps->selector |= cap;
+	if (is_enable)
+		caps->value |= cap;
+}
+
+static int devlink_port_fn_roce_fill(struct devlink_port *devlink_port,
+				     struct nla_bitfield32 *caps,
+				     struct netlink_ext_ack *extack)
+{
+	bool is_enable;
+	int err;
+
+	if (!devlink_port->ops->port_fn_roce_get)
+		return 0;
+
+	err = devlink_port->ops->port_fn_roce_get(devlink_port, &is_enable,
+						  extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_ROCE, is_enable);
+	return 0;
+}
+
+static int devlink_port_fn_migratable_fill(struct devlink_port *devlink_port,
+					   struct nla_bitfield32 *caps,
+					   struct netlink_ext_ack *extack)
+{
+	bool is_enable;
+	int err;
+
+	if (!devlink_port->ops->port_fn_migratable_get ||
+	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF)
+		return 0;
+
+	err = devlink_port->ops->port_fn_migratable_get(devlink_port,
+							&is_enable, extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_MIGRATABLE, is_enable);
+	return 0;
+}
+
+static int devlink_port_fn_ipsec_crypto_fill(struct devlink_port *devlink_port,
+					     struct nla_bitfield32 *caps,
+					     struct netlink_ext_ack *extack)
+{
+	bool is_enable;
+	int err;
+
+	if (!devlink_port->ops->port_fn_ipsec_crypto_get ||
+	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF)
+		return 0;
+
+	err = devlink_port->ops->port_fn_ipsec_crypto_get(devlink_port, &is_enable, extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, is_enable);
+	return 0;
+}
+
+static int devlink_port_fn_ipsec_packet_fill(struct devlink_port *devlink_port,
+					     struct nla_bitfield32 *caps,
+					     struct netlink_ext_ack *extack)
+{
+	bool is_enable;
+	int err;
+
+	if (!devlink_port->ops->port_fn_ipsec_packet_get ||
+	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF)
+		return 0;
+
+	err = devlink_port->ops->port_fn_ipsec_packet_get(devlink_port, &is_enable, extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_PACKET, is_enable);
+	return 0;
+}
+
+static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port,
+				     struct sk_buff *msg,
+				     struct netlink_ext_ack *extack,
+				     bool *msg_updated)
+{
+	struct nla_bitfield32 caps = {};
+	int err;
+
+	err = devlink_port_fn_roce_fill(devlink_port, &caps, extack);
+	if (err)
+		return err;
+
+	err = devlink_port_fn_migratable_fill(devlink_port, &caps, extack);
+	if (err)
+		return err;
+
+	err = devlink_port_fn_ipsec_crypto_fill(devlink_port, &caps, extack);
+	if (err)
+		return err;
+
+	err = devlink_port_fn_ipsec_packet_fill(devlink_port, &caps, extack);
+	if (err)
+		return err;
+
+	if (!caps.selector)
+		return 0;
+	err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value,
+				 caps.selector);
+	if (err)
+		return err;
+
+	*msg_updated = true;
+	return 0;
+}
+
+int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port)
+{
+	if (devlink_nl_put_handle(msg, devlink_port->devlink))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
+		return -EMSGSIZE;
+	return 0;
+}
+
+size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port)
+{
+	struct devlink *devlink = devlink_port->devlink;
+
+	return nla_total_size(strlen(devlink->dev->bus->name) + 1) /* DEVLINK_ATTR_BUS_NAME */
+	     + nla_total_size(strlen(dev_name(devlink->dev)) + 1) /* DEVLINK_ATTR_DEV_NAME */
+	     + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */
+}
+
+static int devlink_nl_port_attrs_put(struct sk_buff *msg,
+				     struct devlink_port *devlink_port)
+{
+	struct devlink_port_attrs *attrs = &devlink_port->attrs;
+
+	if (!devlink_port->attrs_set)
+		return 0;
+	if (attrs->lanes) {
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_LANES, attrs->lanes))
+			return -EMSGSIZE;
+	}
+	if (nla_put_u8(msg, DEVLINK_ATTR_PORT_SPLITTABLE, attrs->splittable))
+		return -EMSGSIZE;
+	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour))
+		return -EMSGSIZE;
+	switch (devlink_port->attrs.flavour) {
+	case DEVLINK_PORT_FLAVOUR_PCI_PF:
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
+				attrs->pci_pf.controller) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf))
+			return -EMSGSIZE;
+		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external))
+			return -EMSGSIZE;
+		break;
+	case DEVLINK_PORT_FLAVOUR_PCI_VF:
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
+				attrs->pci_vf.controller) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf))
+			return -EMSGSIZE;
+		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external))
+			return -EMSGSIZE;
+		break;
+	case DEVLINK_PORT_FLAVOUR_PCI_SF:
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
+				attrs->pci_sf.controller) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
+				attrs->pci_sf.pf) ||
+		    nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER,
+				attrs->pci_sf.sf))
+			return -EMSGSIZE;
+		break;
+	case DEVLINK_PORT_FLAVOUR_PHYSICAL:
+	case DEVLINK_PORT_FLAVOUR_CPU:
+	case DEVLINK_PORT_FLAVOUR_DSA:
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER,
+				attrs->phys.port_number))
+			return -EMSGSIZE;
+		if (!attrs->split)
+			return 0;
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP,
+				attrs->phys.port_number))
+			return -EMSGSIZE;
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER,
+				attrs->phys.split_subport_number))
+			return -EMSGSIZE;
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int devlink_port_fn_hw_addr_fill(struct devlink_port *port,
+					struct sk_buff *msg,
+					struct netlink_ext_ack *extack,
+					bool *msg_updated)
+{
+	u8 hw_addr[MAX_ADDR_LEN];
+	int hw_addr_len;
+	int err;
+
+	if (!port->ops->port_fn_hw_addr_get)
+		return 0;
+
+	err = port->ops->port_fn_hw_addr_get(port, hw_addr, &hw_addr_len,
+					     extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+	err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr);
+	if (err)
+		return err;
+	*msg_updated = true;
+	return 0;
+}
+
+static bool
+devlink_port_fn_state_valid(enum devlink_port_fn_state state)
+{
+	return state == DEVLINK_PORT_FN_STATE_INACTIVE ||
+	       state == DEVLINK_PORT_FN_STATE_ACTIVE;
+}
+
+static bool
+devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate)
+{
+	return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED ||
+	       opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED;
+}
+
+static int devlink_port_fn_state_fill(struct devlink_port *port,
+				      struct sk_buff *msg,
+				      struct netlink_ext_ack *extack,
+				      bool *msg_updated)
+{
+	enum devlink_port_fn_opstate opstate;
+	enum devlink_port_fn_state state;
+	int err;
+
+	if (!port->ops->port_fn_state_get)
+		return 0;
+
+	err = port->ops->port_fn_state_get(port, &state, &opstate, extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+	if (!devlink_port_fn_state_valid(state)) {
+		WARN_ON_ONCE(1);
+		NL_SET_ERR_MSG(extack, "Invalid state read from driver");
+		return -EINVAL;
+	}
+	if (!devlink_port_fn_opstate_valid(opstate)) {
+		WARN_ON_ONCE(1);
+		NL_SET_ERR_MSG(extack, "Invalid operational state read from driver");
+		return -EINVAL;
+	}
+	if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) ||
+	    nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate))
+		return -EMSGSIZE;
+	*msg_updated = true;
+	return 0;
+}
+
+static int
+devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable,
+			struct netlink_ext_ack *extack)
+{
+	return devlink_port->ops->port_fn_migratable_set(devlink_port, enable,
+							 extack);
+}
+
+static int
+devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable,
+			 struct netlink_ext_ack *extack)
+{
+	return devlink_port->ops->port_fn_roce_set(devlink_port, enable,
+						   extack);
+}
+
+static int
+devlink_port_fn_ipsec_crypto_set(struct devlink_port *devlink_port, bool enable,
+				 struct netlink_ext_ack *extack)
+{
+	return devlink_port->ops->port_fn_ipsec_crypto_set(devlink_port, enable, extack);
+}
+
+static int
+devlink_port_fn_ipsec_packet_set(struct devlink_port *devlink_port, bool enable,
+				 struct netlink_ext_ack *extack)
+{
+	return devlink_port->ops->port_fn_ipsec_packet_set(devlink_port, enable, extack);
+}
+
+static int devlink_port_fn_caps_set(struct devlink_port *devlink_port,
+				    const struct nlattr *attr,
+				    struct netlink_ext_ack *extack)
+{
+	struct nla_bitfield32 caps;
+	u32 caps_value;
+	int err;
+
+	caps = nla_get_bitfield32(attr);
+	caps_value = caps.value & caps.selector;
+	if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE) {
+		err = devlink_port_fn_roce_set(devlink_port,
+					       caps_value & DEVLINK_PORT_FN_CAP_ROCE,
+					       extack);
+		if (err)
+			return err;
+	}
+	if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) {
+		err = devlink_port_fn_mig_set(devlink_port, caps_value &
+					      DEVLINK_PORT_FN_CAP_MIGRATABLE,
+					      extack);
+		if (err)
+			return err;
+	}
+	if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) {
+		err = devlink_port_fn_ipsec_crypto_set(devlink_port, caps_value &
+						       DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO,
+						       extack);
+		if (err)
+			return err;
+	}
+	if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) {
+		err = devlink_port_fn_ipsec_packet_set(devlink_port, caps_value &
+						       DEVLINK_PORT_FN_CAP_IPSEC_PACKET,
+						       extack);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int
+devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port,
+				   struct netlink_ext_ack *extack)
+{
+	struct nlattr *function_attr;
+	bool msg_updated = false;
+	int err;
+
+	function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION);
+	if (!function_attr)
+		return -EMSGSIZE;
+
+	err = devlink_port_fn_hw_addr_fill(port, msg, extack, &msg_updated);
+	if (err)
+		goto out;
+	err = devlink_port_fn_caps_fill(port, msg, extack, &msg_updated);
+	if (err)
+		goto out;
+	err = devlink_port_fn_state_fill(port, msg, extack, &msg_updated);
+out:
+	if (err || !msg_updated)
+		nla_nest_cancel(msg, function_attr);
+	else
+		nla_nest_end(msg, function_attr);
+	return err;
+}
+
+static int devlink_nl_port_fill(struct sk_buff *msg,
+				struct devlink_port *devlink_port,
+				enum devlink_command cmd, u32 portid, u32 seq,
+				int flags, struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = devlink_port->devlink;
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
+		goto nla_put_failure;
+
+	spin_lock_bh(&devlink_port->type_lock);
+	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))
+		goto nla_put_failure_type_locked;
+	if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET &&
+	    nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE,
+			devlink_port->desired_type))
+		goto nla_put_failure_type_locked;
+	if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
+		if (devlink_port->type_eth.netdev &&
+		    (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
+				 devlink_port->type_eth.ifindex) ||
+		     nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,
+				    devlink_port->type_eth.ifname)))
+			goto nla_put_failure_type_locked;
+	}
+	if (devlink_port->type == DEVLINK_PORT_TYPE_IB) {
+		struct ib_device *ibdev = devlink_port->type_ib.ibdev;
+
+		if (ibdev &&
+		    nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME,
+				   ibdev->name))
+			goto nla_put_failure_type_locked;
+	}
+	spin_unlock_bh(&devlink_port->type_lock);
+	if (devlink_nl_port_attrs_put(msg, devlink_port))
+		goto nla_put_failure;
+	if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack))
+		goto nla_put_failure;
+	if (devlink_port->linecard &&
+	    nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX,
+			devlink_port->linecard->index))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure_type_locked:
+	spin_unlock_bh(&devlink_port->type_lock);
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static void devlink_port_notify(struct devlink_port *devlink_port,
+				enum devlink_command cmd)
+{
+	struct devlink *devlink = devlink_port->devlink;
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL);
+
+	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+		return;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_port_fill(msg, devlink_port, cmd, 0, 0, 0, NULL);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
+				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static void devlink_ports_notify(struct devlink *devlink,
+				 enum devlink_command cmd)
+{
+	struct devlink_port *devlink_port;
+	unsigned long port_index;
+
+	xa_for_each(&devlink->ports, port_index, devlink_port)
+		devlink_port_notify(devlink_port, cmd);
+}
+
+void devlink_ports_notify_register(struct devlink *devlink)
+{
+	devlink_ports_notify(devlink, DEVLINK_CMD_PORT_NEW);
+}
+
+void devlink_ports_notify_unregister(struct devlink *devlink)
+{
+	devlink_ports_notify(devlink, DEVLINK_CMD_PORT_DEL);
+}
+
+int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	struct sk_buff *msg;
+	int err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW,
+				   info->snd_portid, info->snd_seq, 0,
+				   info->extack);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int
+devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+			     struct netlink_callback *cb, int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_port *devlink_port;
+	unsigned long port_index;
+	int err = 0;
+
+	xa_for_each_start(&devlink->ports, port_index, devlink_port, state->idx) {
+		err = devlink_nl_port_fill(msg, devlink_port,
+					   DEVLINK_CMD_NEW,
+					   NETLINK_CB(cb->skb).portid,
+					   cb->nlh->nlmsg_seq, flags,
+					   cb->extack);
+		if (err) {
+			state->idx = port_index;
+			break;
+		}
+	}
+
+	return err;
+}
+
+int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_port_get_dump_one);
+}
+
+static int devlink_port_type_set(struct devlink_port *devlink_port,
+				 enum devlink_port_type port_type)
+
+{
+	int err;
+
+	if (!devlink_port->ops->port_type_set)
+		return -EOPNOTSUPP;
+
+	if (port_type == devlink_port->type)
+		return 0;
+
+	err = devlink_port->ops->port_type_set(devlink_port, port_type);
+	if (err)
+		return err;
+
+	devlink_port->desired_type = port_type;
+	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
+	return 0;
+}
+
+static int devlink_port_function_hw_addr_set(struct devlink_port *port,
+					     const struct nlattr *attr,
+					     struct netlink_ext_ack *extack)
+{
+	const u8 *hw_addr;
+	int hw_addr_len;
+
+	hw_addr = nla_data(attr);
+	hw_addr_len = nla_len(attr);
+	if (hw_addr_len > MAX_ADDR_LEN) {
+		NL_SET_ERR_MSG(extack, "Port function hardware address too long");
+		return -EINVAL;
+	}
+	if (port->type == DEVLINK_PORT_TYPE_ETH) {
+		if (hw_addr_len != ETH_ALEN) {
+			NL_SET_ERR_MSG(extack, "Address must be 6 bytes for Ethernet device");
+			return -EINVAL;
+		}
+		if (!is_unicast_ether_addr(hw_addr)) {
+			NL_SET_ERR_MSG(extack, "Non-unicast hardware address unsupported");
+			return -EINVAL;
+		}
+	}
+
+	return port->ops->port_fn_hw_addr_set(port, hw_addr, hw_addr_len,
+					      extack);
+}
+
+static int devlink_port_fn_state_set(struct devlink_port *port,
+				     const struct nlattr *attr,
+				     struct netlink_ext_ack *extack)
+{
+	enum devlink_port_fn_state state;
+
+	state = nla_get_u8(attr);
+	return port->ops->port_fn_state_set(port, state, extack);
+}
+
+static int devlink_port_function_validate(struct devlink_port *devlink_port,
+					  struct nlattr **tb,
+					  struct netlink_ext_ack *extack)
+{
+	const struct devlink_port_ops *ops = devlink_port->ops;
+	struct nlattr *attr;
+
+	if (tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] &&
+	    !ops->port_fn_hw_addr_set) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR],
+				    "Port doesn't support function attributes");
+		return -EOPNOTSUPP;
+	}
+	if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR],
+				    "Function does not support state setting");
+		return -EOPNOTSUPP;
+	}
+	attr = tb[DEVLINK_PORT_FN_ATTR_CAPS];
+	if (attr) {
+		struct nla_bitfield32 caps;
+
+		caps = nla_get_bitfield32(attr);
+		if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE &&
+		    !ops->port_fn_roce_set) {
+			NL_SET_ERR_MSG_ATTR(extack, attr,
+					    "Port doesn't support RoCE function attribute");
+			return -EOPNOTSUPP;
+		}
+		if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) {
+			if (!ops->port_fn_migratable_set) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "Port doesn't support migratable function attribute");
+				return -EOPNOTSUPP;
+			}
+			if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "migratable function attribute supported for VFs only");
+				return -EOPNOTSUPP;
+			}
+		}
+		if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) {
+			if (!ops->port_fn_ipsec_crypto_set) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "Port doesn't support ipsec_crypto function attribute");
+				return -EOPNOTSUPP;
+			}
+			if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "ipsec_crypto function attribute supported for VFs only");
+				return -EOPNOTSUPP;
+			}
+		}
+		if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) {
+			if (!ops->port_fn_ipsec_packet_set) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "Port doesn't support ipsec_packet function attribute");
+				return -EOPNOTSUPP;
+			}
+			if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "ipsec_packet function attribute supported for VFs only");
+				return -EOPNOTSUPP;
+			}
+		}
+	}
+	return 0;
+}
+
+static int devlink_port_function_set(struct devlink_port *port,
+				     const struct nlattr *attr,
+				     struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, DEVLINK_PORT_FUNCTION_ATTR_MAX, attr,
+			       devlink_function_nl_policy, extack);
+	if (err < 0) {
+		NL_SET_ERR_MSG(extack, "Fail to parse port function attributes");
+		return err;
+	}
+
+	err = devlink_port_function_validate(port, tb, extack);
+	if (err)
+		return err;
+
+	attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR];
+	if (attr) {
+		err = devlink_port_function_hw_addr_set(port, attr, extack);
+		if (err)
+			return err;
+	}
+
+	attr = tb[DEVLINK_PORT_FN_ATTR_CAPS];
+	if (attr) {
+		err = devlink_port_fn_caps_set(port, attr, extack);
+		if (err)
+			return err;
+	}
+
+	/* Keep this as the last function attribute set, so that when
+	 * multiple port function attributes are set along with state,
+	 * Those can be applied first before activating the state.
+	 */
+	attr = tb[DEVLINK_PORT_FN_ATTR_STATE];
+	if (attr)
+		err = devlink_port_fn_state_set(port, attr, extack);
+
+	if (!err)
+		devlink_port_notify(port, DEVLINK_CMD_PORT_NEW);
+	return err;
+}
+
+int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	int err;
+
+	if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) {
+		enum devlink_port_type port_type;
+
+		port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]);
+		err = devlink_port_type_set(devlink_port, port_type);
+		if (err)
+			return err;
+	}
+
+	if (info->attrs[DEVLINK_ATTR_PORT_FUNCTION]) {
+		struct nlattr *attr = info->attrs[DEVLINK_ATTR_PORT_FUNCTION];
+		struct netlink_ext_ack *extack = info->extack;
+
+		err = devlink_port_function_set(devlink_port, attr, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	struct devlink *devlink = info->user_ptr[0];
+	u32 count;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_SPLIT_COUNT))
+		return -EINVAL;
+	if (!devlink_port->ops->port_split)
+		return -EOPNOTSUPP;
+
+	count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]);
+
+	if (!devlink_port->attrs.splittable) {
+		/* Split ports cannot be split. */
+		if (devlink_port->attrs.split)
+			NL_SET_ERR_MSG(info->extack, "Port cannot be split further");
+		else
+			NL_SET_ERR_MSG(info->extack, "Port cannot be split");
+		return -EINVAL;
+	}
+
+	if (count < 2 || !is_power_of_2(count) || count > devlink_port->attrs.lanes) {
+		NL_SET_ERR_MSG(info->extack, "Invalid split count");
+		return -EINVAL;
+	}
+
+	return devlink_port->ops->port_split(devlink, devlink_port, count,
+					     info->extack);
+}
+
+int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	struct devlink *devlink = info->user_ptr[0];
+
+	if (!devlink_port->ops->port_unsplit)
+		return -EOPNOTSUPP;
+	return devlink_port->ops->port_unsplit(devlink, devlink_port, info->extack);
+}
+
+int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink_port_new_attrs new_attrs = {};
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_port *devlink_port;
+	struct sk_buff *msg;
+	int err;
+
+	if (!devlink->ops->port_new)
+		return -EOPNOTSUPP;
+
+	if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] ||
+	    !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) {
+		NL_SET_ERR_MSG(extack, "Port flavour or PCI PF are not specified");
+		return -EINVAL;
+	}
+	new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]);
+	new_attrs.pfnum =
+		nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]);
+
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		/* Port index of the new port being created by driver. */
+		new_attrs.port_index =
+			nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+		new_attrs.port_index_valid = true;
+	}
+	if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) {
+		new_attrs.controller =
+			nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]);
+		new_attrs.controller_valid = true;
+	}
+	if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF &&
+	    info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) {
+		new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]);
+		new_attrs.sfnum_valid = true;
+	}
+
+	err = devlink->ops->port_new(devlink, &new_attrs,
+				     extack, &devlink_port);
+	if (err)
+		return err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg) {
+		err = -ENOMEM;
+		goto err_out_port_del;
+	}
+	err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW,
+				   info->snd_portid, info->snd_seq, 0, NULL);
+	if (WARN_ON_ONCE(err))
+		goto err_out_msg_free;
+	err = genlmsg_reply(msg, info);
+	if (err)
+		goto err_out_port_del;
+	return 0;
+
+err_out_msg_free:
+	nlmsg_free(msg);
+err_out_port_del:
+	devlink_port->ops->port_del(devlink, devlink_port, NULL);
+	return err;
+}
+
+int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+
+	if (!devlink_port->ops->port_del)
+		return -EOPNOTSUPP;
+
+	return devlink_port->ops->port_del(devlink, devlink_port, extack);
+}
+
+static void devlink_port_type_warn(struct work_struct *work)
+{
+	struct devlink_port *port = container_of(to_delayed_work(work),
+						 struct devlink_port,
+						 type_warn_dw);
+	dev_warn(port->devlink->dev, "Type was not set for devlink port.");
+}
+
+static bool devlink_port_type_should_warn(struct devlink_port *devlink_port)
+{
+	/* Ignore CPU and DSA flavours. */
+	return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU &&
+	       devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA &&
+	       devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED;
+}
+
+#define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600)
+
+static void devlink_port_type_warn_schedule(struct devlink_port *devlink_port)
+{
+	if (!devlink_port_type_should_warn(devlink_port))
+		return;
+	/* Schedule a work to WARN in case driver does not set port
+	 * type within timeout.
+	 */
+	schedule_delayed_work(&devlink_port->type_warn_dw,
+			      DEVLINK_PORT_TYPE_WARN_TIMEOUT);
+}
+
+static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port)
+{
+	if (!devlink_port_type_should_warn(devlink_port))
+		return;
+	cancel_delayed_work_sync(&devlink_port->type_warn_dw);
+}
+
+/**
+ * devlink_port_init() - Init devlink port
+ *
+ * @devlink: devlink
+ * @devlink_port: devlink port
+ *
+ * Initialize essential stuff that is needed for functions
+ * that may be called before devlink port registration.
+ * Call to this function is optional and not needed
+ * in case the driver does not use such functions.
+ */
+void devlink_port_init(struct devlink *devlink,
+		       struct devlink_port *devlink_port)
+{
+	if (devlink_port->initialized)
+		return;
+	devlink_port->devlink = devlink;
+	INIT_LIST_HEAD(&devlink_port->region_list);
+	devlink_port->initialized = true;
+}
+EXPORT_SYMBOL_GPL(devlink_port_init);
+
+/**
+ * devlink_port_fini() - Deinitialize devlink port
+ *
+ * @devlink_port: devlink port
+ *
+ * Deinitialize essential stuff that is in use for functions
+ * that may be called after devlink port unregistration.
+ * Call to this function is optional and not needed
+ * in case the driver does not use such functions.
+ */
+void devlink_port_fini(struct devlink_port *devlink_port)
+{
+	WARN_ON(!list_empty(&devlink_port->region_list));
+}
+EXPORT_SYMBOL_GPL(devlink_port_fini);
+
+static const struct devlink_port_ops devlink_port_dummy_ops = {};
+
+/**
+ * devl_port_register_with_ops() - Register devlink port
+ *
+ * @devlink: devlink
+ * @devlink_port: devlink port
+ * @port_index: driver-specific numerical identifier of the port
+ * @ops: port ops
+ *
+ * Register devlink port with provided port index. User can use
+ * any indexing, even hw-related one. devlink_port structure
+ * is convenient to be embedded inside user driver private structure.
+ * Note that the caller should take care of zeroing the devlink_port
+ * structure.
+ */
+int devl_port_register_with_ops(struct devlink *devlink,
+				struct devlink_port *devlink_port,
+				unsigned int port_index,
+				const struct devlink_port_ops *ops)
+{
+	int err;
+
+	devl_assert_locked(devlink);
+
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
+	devlink_port_init(devlink, devlink_port);
+	devlink_port->registered = true;
+	devlink_port->index = port_index;
+	devlink_port->ops = ops ? ops : &devlink_port_dummy_ops;
+	spin_lock_init(&devlink_port->type_lock);
+	INIT_LIST_HEAD(&devlink_port->reporter_list);
+	err = xa_insert(&devlink->ports, port_index, devlink_port, GFP_KERNEL);
+	if (err) {
+		devlink_port->registered = false;
+		return err;
+	}
+
+	INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn);
+	devlink_port_type_warn_schedule(devlink_port);
+	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devl_port_register_with_ops);
+
+/**
+ *	devlink_port_register_with_ops - Register devlink port
+ *
+ *	@devlink: devlink
+ *	@devlink_port: devlink port
+ *	@port_index: driver-specific numerical identifier of the port
+ *	@ops: port ops
+ *
+ *	Register devlink port with provided port index. User can use
+ *	any indexing, even hw-related one. devlink_port structure
+ *	is convenient to be embedded inside user driver private structure.
+ *	Note that the caller should take care of zeroing the devlink_port
+ *	structure.
+ *
+ *	Context: Takes and release devlink->lock <mutex>.
+ */
+int devlink_port_register_with_ops(struct devlink *devlink,
+				   struct devlink_port *devlink_port,
+				   unsigned int port_index,
+				   const struct devlink_port_ops *ops)
+{
+	int err;
+
+	devl_lock(devlink);
+	err = devl_port_register_with_ops(devlink, devlink_port,
+					  port_index, ops);
+	devl_unlock(devlink);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devlink_port_register_with_ops);
+
+/**
+ * devl_port_unregister() - Unregister devlink port
+ *
+ * @devlink_port: devlink port
+ */
+void devl_port_unregister(struct devlink_port *devlink_port)
+{
+	lockdep_assert_held(&devlink_port->devlink->lock);
+	WARN_ON(devlink_port->type != DEVLINK_PORT_TYPE_NOTSET);
+
+	devlink_port_type_warn_cancel(devlink_port);
+	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL);
+	xa_erase(&devlink_port->devlink->ports, devlink_port->index);
+	WARN_ON(!list_empty(&devlink_port->reporter_list));
+	devlink_port->registered = false;
+}
+EXPORT_SYMBOL_GPL(devl_port_unregister);
+
+/**
+ *	devlink_port_unregister - Unregister devlink port
+ *
+ *	@devlink_port: devlink port
+ *
+ *	Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_port_unregister(struct devlink_port *devlink_port)
+{
+	struct devlink *devlink = devlink_port->devlink;
+
+	devl_lock(devlink);
+	devl_port_unregister(devlink_port);
+	devl_unlock(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_port_unregister);
+
+static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port,
+					    struct net_device *netdev)
+{
+	const struct net_device_ops *ops = netdev->netdev_ops;
+
+	/* If driver registers devlink port, it should set devlink port
+	 * attributes accordingly so the compat functions are called
+	 * and the original ops are not used.
+	 */
+	if (ops->ndo_get_phys_port_name) {
+		/* Some drivers use the same set of ndos for netdevs
+		 * that have devlink_port registered and also for
+		 * those who don't. Make sure that ndo_get_phys_port_name
+		 * returns -EOPNOTSUPP here in case it is defined.
+		 * Warn if not.
+		 */
+		char name[IFNAMSIZ];
+		int err;
+
+		err = ops->ndo_get_phys_port_name(netdev, name, sizeof(name));
+		WARN_ON(err != -EOPNOTSUPP);
+	}
+	if (ops->ndo_get_port_parent_id) {
+		/* Some drivers use the same set of ndos for netdevs
+		 * that have devlink_port registered and also for
+		 * those who don't. Make sure that ndo_get_port_parent_id
+		 * returns -EOPNOTSUPP here in case it is defined.
+		 * Warn if not.
+		 */
+		struct netdev_phys_item_id ppid;
+		int err;
+
+		err = ops->ndo_get_port_parent_id(netdev, &ppid);
+		WARN_ON(err != -EOPNOTSUPP);
+	}
+}
+
+static void __devlink_port_type_set(struct devlink_port *devlink_port,
+				    enum devlink_port_type type,
+				    void *type_dev)
+{
+	struct net_device *netdev = type_dev;
+
+	ASSERT_DEVLINK_PORT_REGISTERED(devlink_port);
+
+	if (type == DEVLINK_PORT_TYPE_NOTSET) {
+		devlink_port_type_warn_schedule(devlink_port);
+	} else {
+		devlink_port_type_warn_cancel(devlink_port);
+		if (type == DEVLINK_PORT_TYPE_ETH && netdev)
+			devlink_port_type_netdev_checks(devlink_port, netdev);
+	}
+
+	spin_lock_bh(&devlink_port->type_lock);
+	devlink_port->type = type;
+	switch (type) {
+	case DEVLINK_PORT_TYPE_ETH:
+		devlink_port->type_eth.netdev = netdev;
+		if (netdev) {
+			ASSERT_RTNL();
+			devlink_port->type_eth.ifindex = netdev->ifindex;
+			BUILD_BUG_ON(sizeof(devlink_port->type_eth.ifname) !=
+				     sizeof(netdev->name));
+			strcpy(devlink_port->type_eth.ifname, netdev->name);
+		}
+		break;
+	case DEVLINK_PORT_TYPE_IB:
+		devlink_port->type_ib.ibdev = type_dev;
+		break;
+	default:
+		break;
+	}
+	spin_unlock_bh(&devlink_port->type_lock);
+	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
+}
+
+/**
+ *	devlink_port_type_eth_set - Set port type to Ethernet
+ *
+ *	@devlink_port: devlink port
+ *
+ *	If driver is calling this, most likely it is doing something wrong.
+ */
+void devlink_port_type_eth_set(struct devlink_port *devlink_port)
+{
+	dev_warn(devlink_port->devlink->dev,
+		 "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n",
+		 devlink_port->index);
+	__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL);
+}
+EXPORT_SYMBOL_GPL(devlink_port_type_eth_set);
+
+/**
+ *	devlink_port_type_ib_set - Set port type to InfiniBand
+ *
+ *	@devlink_port: devlink port
+ *	@ibdev: related IB device
+ */
+void devlink_port_type_ib_set(struct devlink_port *devlink_port,
+			      struct ib_device *ibdev)
+{
+	__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_IB, ibdev);
+}
+EXPORT_SYMBOL_GPL(devlink_port_type_ib_set);
+
+/**
+ *	devlink_port_type_clear - Clear port type
+ *
+ *	@devlink_port: devlink port
+ *
+ *	If driver is calling this for clearing Ethernet type, most likely
+ *	it is doing something wrong.
+ */
+void devlink_port_type_clear(struct devlink_port *devlink_port)
+{
+	if (devlink_port->type == DEVLINK_PORT_TYPE_ETH)
+		dev_warn(devlink_port->devlink->dev,
+			 "devlink port type for port %d cleared without a software interface reference, device type not supported by the kernel?\n",
+			 devlink_port->index);
+	__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL);
+}
+EXPORT_SYMBOL_GPL(devlink_port_type_clear);
+
+int devlink_port_netdevice_event(struct notifier_block *nb,
+				 unsigned long event, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct devlink_port *devlink_port = netdev->devlink_port;
+	struct devlink *devlink;
+
+	if (!devlink_port)
+		return NOTIFY_OK;
+	devlink = devlink_port->devlink;
+
+	switch (event) {
+	case NETDEV_POST_INIT:
+		/* Set the type but not netdev pointer. It is going to be set
+		 * later on by NETDEV_REGISTER event. Happens once during
+		 * netdevice register
+		 */
+		__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH,
+					NULL);
+		break;
+	case NETDEV_REGISTER:
+	case NETDEV_CHANGENAME:
+		if (devlink_net(devlink) != dev_net(netdev))
+			return NOTIFY_OK;
+		/* Set the netdev on top of previously set type. Note this
+		 * event happens also during net namespace change so here
+		 * we take into account netdev pointer appearing in this
+		 * namespace.
+		 */
+		__devlink_port_type_set(devlink_port, devlink_port->type,
+					netdev);
+		break;
+	case NETDEV_UNREGISTER:
+		if (devlink_net(devlink) != dev_net(netdev))
+			return NOTIFY_OK;
+		/* Clear netdev pointer, but not the type. This event happens
+		 * also during net namespace change so we need to clear
+		 * pointer to netdev that is going to another net namespace.
+		 */
+		__devlink_port_type_set(devlink_port, devlink_port->type,
+					NULL);
+		break;
+	case NETDEV_PRE_UNINIT:
+		/* Clear the type and the netdev pointer. Happens one during
+		 * netdevice unregister.
+		 */
+		__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET,
+					NULL);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int __devlink_port_attrs_set(struct devlink_port *devlink_port,
+				    enum devlink_port_flavour flavour)
+{
+	struct devlink_port_attrs *attrs = &devlink_port->attrs;
+
+	devlink_port->attrs_set = true;
+	attrs->flavour = flavour;
+	if (attrs->switch_id.id_len) {
+		devlink_port->switch_port = true;
+		if (WARN_ON(attrs->switch_id.id_len > MAX_PHYS_ITEM_ID_LEN))
+			attrs->switch_id.id_len = MAX_PHYS_ITEM_ID_LEN;
+	} else {
+		devlink_port->switch_port = false;
+	}
+	return 0;
+}
+
+/**
+ *	devlink_port_attrs_set - Set port attributes
+ *
+ *	@devlink_port: devlink port
+ *	@attrs: devlink port attrs
+ */
+void devlink_port_attrs_set(struct devlink_port *devlink_port,
+			    struct devlink_port_attrs *attrs)
+{
+	int ret;
+
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
+	devlink_port->attrs = *attrs;
+	ret = __devlink_port_attrs_set(devlink_port, attrs->flavour);
+	if (ret)
+		return;
+	WARN_ON(attrs->splittable && attrs->split);
+}
+EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
+
+/**
+ *	devlink_port_attrs_pci_pf_set - Set PCI PF port attributes
+ *
+ *	@devlink_port: devlink port
+ *	@controller: associated controller number for the devlink port instance
+ *	@pf: associated PF for the devlink port instance
+ *	@external: indicates if the port is for an external controller
+ */
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller,
+				   u16 pf, bool external)
+{
+	struct devlink_port_attrs *attrs = &devlink_port->attrs;
+	int ret;
+
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
+	ret = __devlink_port_attrs_set(devlink_port,
+				       DEVLINK_PORT_FLAVOUR_PCI_PF);
+	if (ret)
+		return;
+	attrs->pci_pf.controller = controller;
+	attrs->pci_pf.pf = pf;
+	attrs->pci_pf.external = external;
+}
+EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set);
+
+/**
+ *	devlink_port_attrs_pci_vf_set - Set PCI VF port attributes
+ *
+ *	@devlink_port: devlink port
+ *	@controller: associated controller number for the devlink port instance
+ *	@pf: associated PF for the devlink port instance
+ *	@vf: associated VF of a PF for the devlink port instance
+ *	@external: indicates if the port is for an external controller
+ */
+void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller,
+				   u16 pf, u16 vf, bool external)
+{
+	struct devlink_port_attrs *attrs = &devlink_port->attrs;
+	int ret;
+
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
+	ret = __devlink_port_attrs_set(devlink_port,
+				       DEVLINK_PORT_FLAVOUR_PCI_VF);
+	if (ret)
+		return;
+	attrs->pci_vf.controller = controller;
+	attrs->pci_vf.pf = pf;
+	attrs->pci_vf.vf = vf;
+	attrs->pci_vf.external = external;
+}
+EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set);
+
+/**
+ *	devlink_port_attrs_pci_sf_set - Set PCI SF port attributes
+ *
+ *	@devlink_port: devlink port
+ *	@controller: associated controller number for the devlink port instance
+ *	@pf: associated PF for the devlink port instance
+ *	@sf: associated SF of a PF for the devlink port instance
+ *	@external: indicates if the port is for an external controller
+ */
+void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller,
+				   u16 pf, u32 sf, bool external)
+{
+	struct devlink_port_attrs *attrs = &devlink_port->attrs;
+	int ret;
+
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
+	ret = __devlink_port_attrs_set(devlink_port,
+				       DEVLINK_PORT_FLAVOUR_PCI_SF);
+	if (ret)
+		return;
+	attrs->pci_sf.controller = controller;
+	attrs->pci_sf.pf = pf;
+	attrs->pci_sf.sf = sf;
+	attrs->pci_sf.external = external;
+}
+EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set);
+
+/**
+ *	devlink_port_linecard_set - Link port with a linecard
+ *
+ *	@devlink_port: devlink port
+ *	@linecard: devlink linecard
+ */
+void devlink_port_linecard_set(struct devlink_port *devlink_port,
+			       struct devlink_linecard *linecard)
+{
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
+	devlink_port->linecard = linecard;
+}
+EXPORT_SYMBOL_GPL(devlink_port_linecard_set);
+
+static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
+					     char *name, size_t len)
+{
+	struct devlink_port_attrs *attrs = &devlink_port->attrs;
+	int n = 0;
+
+	if (!devlink_port->attrs_set)
+		return -EOPNOTSUPP;
+
+	switch (attrs->flavour) {
+	case DEVLINK_PORT_FLAVOUR_PHYSICAL:
+		if (devlink_port->linecard)
+			n = snprintf(name, len, "l%u",
+				     devlink_port->linecard->index);
+		if (n < len)
+			n += snprintf(name + n, len - n, "p%u",
+				      attrs->phys.port_number);
+		if (n < len && attrs->split)
+			n += snprintf(name + n, len - n, "s%u",
+				      attrs->phys.split_subport_number);
+		break;
+	case DEVLINK_PORT_FLAVOUR_CPU:
+	case DEVLINK_PORT_FLAVOUR_DSA:
+	case DEVLINK_PORT_FLAVOUR_UNUSED:
+		/* As CPU and DSA ports do not have a netdevice associated
+		 * case should not ever happen.
+		 */
+		WARN_ON(1);
+		return -EINVAL;
+	case DEVLINK_PORT_FLAVOUR_PCI_PF:
+		if (attrs->pci_pf.external) {
+			n = snprintf(name, len, "c%u", attrs->pci_pf.controller);
+			if (n >= len)
+				return -EINVAL;
+			len -= n;
+			name += n;
+		}
+		n = snprintf(name, len, "pf%u", attrs->pci_pf.pf);
+		break;
+	case DEVLINK_PORT_FLAVOUR_PCI_VF:
+		if (attrs->pci_vf.external) {
+			n = snprintf(name, len, "c%u", attrs->pci_vf.controller);
+			if (n >= len)
+				return -EINVAL;
+			len -= n;
+			name += n;
+		}
+		n = snprintf(name, len, "pf%uvf%u",
+			     attrs->pci_vf.pf, attrs->pci_vf.vf);
+		break;
+	case DEVLINK_PORT_FLAVOUR_PCI_SF:
+		if (attrs->pci_sf.external) {
+			n = snprintf(name, len, "c%u", attrs->pci_sf.controller);
+			if (n >= len)
+				return -EINVAL;
+			len -= n;
+			name += n;
+		}
+		n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf,
+			     attrs->pci_sf.sf);
+		break;
+	case DEVLINK_PORT_FLAVOUR_VIRTUAL:
+		return -EOPNOTSUPP;
+	}
+
+	if (n >= len)
+		return -EINVAL;
+
+	return 0;
+}
+
+int devlink_compat_phys_port_name_get(struct net_device *dev,
+				      char *name, size_t len)
+{
+	struct devlink_port *devlink_port;
+
+	/* RTNL mutex is held here which ensures that devlink_port
+	 * instance cannot disappear in the middle. No need to take
+	 * any devlink lock as only permanent values are accessed.
+	 */
+	ASSERT_RTNL();
+
+	devlink_port = dev->devlink_port;
+	if (!devlink_port)
+		return -EOPNOTSUPP;
+
+	return __devlink_port_phys_port_name_get(devlink_port, name, len);
+}
+
+int devlink_compat_switch_id_get(struct net_device *dev,
+				 struct netdev_phys_item_id *ppid)
+{
+	struct devlink_port *devlink_port;
+
+	/* Caller must hold RTNL mutex or reference to dev, which ensures that
+	 * devlink_port instance cannot disappear in the middle. No need to take
+	 * any devlink lock as only permanent values are accessed.
+	 */
+	devlink_port = dev->devlink_port;
+	if (!devlink_port || !devlink_port->switch_port)
+		return -EOPNOTSUPP;
+
+	memcpy(ppid, &devlink_port->attrs.switch_id, sizeof(*ppid));
+
+	return 0;
+}
-- 
GitLab


From 2b4d8bb0888930b4a26cd46ec067753228877488 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:45 +0200
Subject: [PATCH 1790/1806] devlink: push shared buffer related code into
 separate file

Cut out another chunk from leftover.c and put sb related code
into a separate file.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-4-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/Makefile        |    2 +-
 net/devlink/devl_internal.h |    9 +
 net/devlink/leftover.c      | 1338 +++++------------------------------
 net/devlink/sb.c            |  996 ++++++++++++++++++++++++++
 4 files changed, 1180 insertions(+), 1165 deletions(-)
 create mode 100644 net/devlink/sb.c

diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index 456bfb336540a..dcc508af48a9f 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o health.o
+obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o sb.o health.o \
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 7d01e2060702d..e1a6b7a763b8b 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -220,6 +220,15 @@ int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb,
 				     struct genl_info *info);
 int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb,
+					 struct genl_info *info);
+int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb,
+					    struct genl_info *info);
+int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb,
+					 struct genl_info *info);
 int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 					    struct genl_info *info);
 int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index d14b40fb8fdf2..795bfdd41103a 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -231,164 +231,6 @@ devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info)
 	return devlink_linecard_get_from_attrs(devlink, info->attrs);
 }
 
-struct devlink_sb {
-	struct list_head list;
-	unsigned int index;
-	u32 size;
-	u16 ingress_pools_count;
-	u16 egress_pools_count;
-	u16 ingress_tc_count;
-	u16 egress_tc_count;
-};
-
-static u16 devlink_sb_pool_count(struct devlink_sb *devlink_sb)
-{
-	return devlink_sb->ingress_pools_count + devlink_sb->egress_pools_count;
-}
-
-static struct devlink_sb *devlink_sb_get_by_index(struct devlink *devlink,
-						  unsigned int sb_index)
-{
-	struct devlink_sb *devlink_sb;
-
-	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
-		if (devlink_sb->index == sb_index)
-			return devlink_sb;
-	}
-	return NULL;
-}
-
-static bool devlink_sb_index_exists(struct devlink *devlink,
-				    unsigned int sb_index)
-{
-	return devlink_sb_get_by_index(devlink, sb_index);
-}
-
-static struct devlink_sb *devlink_sb_get_from_attrs(struct devlink *devlink,
-						    struct nlattr **attrs)
-{
-	if (attrs[DEVLINK_ATTR_SB_INDEX]) {
-		u32 sb_index = nla_get_u32(attrs[DEVLINK_ATTR_SB_INDEX]);
-		struct devlink_sb *devlink_sb;
-
-		devlink_sb = devlink_sb_get_by_index(devlink, sb_index);
-		if (!devlink_sb)
-			return ERR_PTR(-ENODEV);
-		return devlink_sb;
-	}
-	return ERR_PTR(-EINVAL);
-}
-
-static struct devlink_sb *devlink_sb_get_from_info(struct devlink *devlink,
-						   struct genl_info *info)
-{
-	return devlink_sb_get_from_attrs(devlink, info->attrs);
-}
-
-static int devlink_sb_pool_index_get_from_attrs(struct devlink_sb *devlink_sb,
-						struct nlattr **attrs,
-						u16 *p_pool_index)
-{
-	u16 val;
-
-	if (!attrs[DEVLINK_ATTR_SB_POOL_INDEX])
-		return -EINVAL;
-
-	val = nla_get_u16(attrs[DEVLINK_ATTR_SB_POOL_INDEX]);
-	if (val >= devlink_sb_pool_count(devlink_sb))
-		return -EINVAL;
-	*p_pool_index = val;
-	return 0;
-}
-
-static int devlink_sb_pool_index_get_from_info(struct devlink_sb *devlink_sb,
-					       struct genl_info *info,
-					       u16 *p_pool_index)
-{
-	return devlink_sb_pool_index_get_from_attrs(devlink_sb, info->attrs,
-						    p_pool_index);
-}
-
-static int
-devlink_sb_pool_type_get_from_attrs(struct nlattr **attrs,
-				    enum devlink_sb_pool_type *p_pool_type)
-{
-	u8 val;
-
-	if (!attrs[DEVLINK_ATTR_SB_POOL_TYPE])
-		return -EINVAL;
-
-	val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_TYPE]);
-	if (val != DEVLINK_SB_POOL_TYPE_INGRESS &&
-	    val != DEVLINK_SB_POOL_TYPE_EGRESS)
-		return -EINVAL;
-	*p_pool_type = val;
-	return 0;
-}
-
-static int
-devlink_sb_pool_type_get_from_info(struct genl_info *info,
-				   enum devlink_sb_pool_type *p_pool_type)
-{
-	return devlink_sb_pool_type_get_from_attrs(info->attrs, p_pool_type);
-}
-
-static int
-devlink_sb_th_type_get_from_attrs(struct nlattr **attrs,
-				  enum devlink_sb_threshold_type *p_th_type)
-{
-	u8 val;
-
-	if (!attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE])
-		return -EINVAL;
-
-	val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]);
-	if (val != DEVLINK_SB_THRESHOLD_TYPE_STATIC &&
-	    val != DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC)
-		return -EINVAL;
-	*p_th_type = val;
-	return 0;
-}
-
-static int
-devlink_sb_th_type_get_from_info(struct genl_info *info,
-				 enum devlink_sb_threshold_type *p_th_type)
-{
-	return devlink_sb_th_type_get_from_attrs(info->attrs, p_th_type);
-}
-
-static int
-devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb,
-				   struct nlattr **attrs,
-				   enum devlink_sb_pool_type pool_type,
-				   u16 *p_tc_index)
-{
-	u16 val;
-
-	if (!attrs[DEVLINK_ATTR_SB_TC_INDEX])
-		return -EINVAL;
-
-	val = nla_get_u16(attrs[DEVLINK_ATTR_SB_TC_INDEX]);
-	if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS &&
-	    val >= devlink_sb->ingress_tc_count)
-		return -EINVAL;
-	if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS &&
-	    val >= devlink_sb->egress_tc_count)
-		return -EINVAL;
-	*p_tc_index = val;
-	return 0;
-}
-
-static int
-devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,
-				  struct genl_info *info,
-				  enum devlink_sb_pool_type pool_type,
-				  u16 *p_tc_index)
-{
-	return devlink_sb_tc_index_get_from_attrs(devlink_sb, info->attrs,
-						  pool_type, p_tc_index);
-}
-
 struct devlink_region {
 	struct devlink *devlink;
 	struct devlink_port *port;
@@ -1053,825 +895,31 @@ static void devlink_linecards_notify_unregister(struct devlink *devlink)
 {
 	struct devlink_linecard *linecard;
 
-	list_for_each_entry_reverse(linecard, &devlink->linecard_list, list)
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
-}
-
-int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_linecard *linecard;
-	struct sk_buff *msg;
-	int err;
-
-	linecard = devlink_linecard_get_from_info(devlink, info);
-	if (IS_ERR(linecard))
-		return PTR_ERR(linecard);
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	mutex_lock(&linecard->state_lock);
-	err = devlink_nl_linecard_fill(msg, devlink, linecard,
-				       DEVLINK_CMD_LINECARD_NEW,
-				       info->snd_portid, info->snd_seq, 0,
-				       info->extack);
-	mutex_unlock(&linecard->state_lock);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
-
-	return genlmsg_reply(msg, info);
-}
-
-static int devlink_nl_linecard_get_dump_one(struct sk_buff *msg,
-					    struct devlink *devlink,
-					    struct netlink_callback *cb,
-					    int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_linecard *linecard;
-	int idx = 0;
-	int err = 0;
-
-	list_for_each_entry(linecard, &devlink->linecard_list, list) {
-		if (idx < state->idx) {
-			idx++;
-			continue;
-		}
-		mutex_lock(&linecard->state_lock);
-		err = devlink_nl_linecard_fill(msg, devlink, linecard,
-					       DEVLINK_CMD_LINECARD_NEW,
-					       NETLINK_CB(cb->skb).portid,
-					       cb->nlh->nlmsg_seq, flags,
-					       cb->extack);
-		mutex_unlock(&linecard->state_lock);
-		if (err) {
-			state->idx = idx;
-			break;
-		}
-		idx++;
-	}
-
-	return err;
-}
-
-int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
-				   struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_linecard_get_dump_one);
-}
-
-static struct devlink_linecard_type *
-devlink_linecard_type_lookup(struct devlink_linecard *linecard,
-			     const char *type)
-{
-	struct devlink_linecard_type *linecard_type;
-	int i;
-
-	for (i = 0; i < linecard->types_count; i++) {
-		linecard_type = &linecard->types[i];
-		if (!strcmp(type, linecard_type->type))
-			return linecard_type;
-	}
-	return NULL;
-}
-
-static int devlink_linecard_type_set(struct devlink_linecard *linecard,
-				     const char *type,
-				     struct netlink_ext_ack *extack)
-{
-	const struct devlink_linecard_ops *ops = linecard->ops;
-	struct devlink_linecard_type *linecard_type;
-	int err;
-
-	mutex_lock(&linecard->state_lock);
-	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
-		err = -EBUSY;
-		goto out;
-	}
-	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
-		err = -EBUSY;
-		goto out;
-	}
-
-	linecard_type = devlink_linecard_type_lookup(linecard, type);
-	if (!linecard_type) {
-		NL_SET_ERR_MSG(extack, "Unsupported line card type provided");
-		err = -EINVAL;
-		goto out;
-	}
-
-	if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED &&
-	    linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
-		NL_SET_ERR_MSG(extack, "Line card already provisioned");
-		err = -EBUSY;
-		/* Check if the line card is provisioned in the same
-		 * way the user asks. In case it is, make the operation
-		 * to return success.
-		 */
-		if (ops->same_provision &&
-		    ops->same_provision(linecard, linecard->priv,
-					linecard_type->type,
-					linecard_type->priv))
-			err = 0;
-		goto out;
-	}
-
-	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING;
-	linecard->type = linecard_type->type;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-	err = ops->provision(linecard, linecard->priv, linecard_type->type,
-			     linecard_type->priv, extack);
-	if (err) {
-		/* Provisioning failed. Assume the linecard is unprovisioned
-		 * for future operations.
-		 */
-		mutex_lock(&linecard->state_lock);
-		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-		linecard->type = NULL;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		mutex_unlock(&linecard->state_lock);
-	}
-	return err;
-
-out:
-	mutex_unlock(&linecard->state_lock);
-	return err;
-}
-
-static int devlink_linecard_type_unset(struct devlink_linecard *linecard,
-				       struct netlink_ext_ack *extack)
-{
-	int err;
-
-	mutex_lock(&linecard->state_lock);
-	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
-		err = -EBUSY;
-		goto out;
-	}
-	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
-		err = -EBUSY;
-		goto out;
-	}
-	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
-		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-		linecard->type = NULL;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		err = 0;
-		goto out;
-	}
-
-	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) {
-		NL_SET_ERR_MSG(extack, "Line card is not provisioned");
-		err = 0;
-		goto out;
-	}
-	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-	err = linecard->ops->unprovision(linecard, linecard->priv,
-					 extack);
-	if (err) {
-		/* Unprovisioning failed. Assume the linecard is unprovisioned
-		 * for future operations.
-		 */
-		mutex_lock(&linecard->state_lock);
-		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-		linecard->type = NULL;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		mutex_unlock(&linecard->state_lock);
-	}
-	return err;
-
-out:
-	mutex_unlock(&linecard->state_lock);
-	return err;
-}
-
-static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb,
-					    struct genl_info *info)
-{
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_linecard *linecard;
-	int err;
-
-	linecard = devlink_linecard_get_from_info(devlink, info);
-	if (IS_ERR(linecard))
-		return PTR_ERR(linecard);
-
-	if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) {
-		const char *type;
-
-		type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]);
-		if (strcmp(type, "")) {
-			err = devlink_linecard_type_set(linecard, type, extack);
-			if (err)
-				return err;
-		} else {
-			err = devlink_linecard_type_unset(linecard, extack);
-			if (err)
-				return err;
-		}
-	}
-
-	return 0;
-}
-
-static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink,
-			      struct devlink_sb *devlink_sb,
-			      enum devlink_command cmd, u32 portid,
-			      u32 seq, int flags)
-{
-	void *hdr;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_SB_SIZE, devlink_sb->size))
-		goto nla_put_failure;
-	if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_POOL_COUNT,
-			devlink_sb->ingress_pools_count))
-		goto nla_put_failure;
-	if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_POOL_COUNT,
-			devlink_sb->egress_pools_count))
-		goto nla_put_failure;
-	if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_TC_COUNT,
-			devlink_sb->ingress_tc_count))
-		goto nla_put_failure;
-	if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_TC_COUNT,
-			devlink_sb->egress_tc_count))
-		goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-	return 0;
-
-nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
-}
-
-int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_sb *devlink_sb;
-	struct sk_buff *msg;
-	int err;
-
-	devlink_sb = devlink_sb_get_from_info(devlink, info);
-	if (IS_ERR(devlink_sb))
-		return PTR_ERR(devlink_sb);
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	err = devlink_nl_sb_fill(msg, devlink, devlink_sb,
-				 DEVLINK_CMD_SB_NEW,
-				 info->snd_portid, info->snd_seq, 0);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
-
-	return genlmsg_reply(msg, info);
-}
-
-static int
-devlink_nl_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-			   struct netlink_callback *cb, int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_sb *devlink_sb;
-	int idx = 0;
-	int err = 0;
-
-	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
-		if (idx < state->idx) {
-			idx++;
-			continue;
-		}
-		err = devlink_nl_sb_fill(msg, devlink, devlink_sb,
-					 DEVLINK_CMD_SB_NEW,
-					 NETLINK_CB(cb->skb).portid,
-					 cb->nlh->nlmsg_seq, flags);
-		if (err) {
-			state->idx = idx;
-			break;
-		}
-		idx++;
-	}
-
-	return err;
-}
-
-int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_get_dump_one);
-}
-
-static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink,
-				   struct devlink_sb *devlink_sb,
-				   u16 pool_index, enum devlink_command cmd,
-				   u32 portid, u32 seq, int flags)
-{
-	struct devlink_sb_pool_info pool_info;
-	void *hdr;
-	int err;
-
-	err = devlink->ops->sb_pool_get(devlink, devlink_sb->index,
-					pool_index, &pool_info);
-	if (err)
-		return err;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
-		goto nla_put_failure;
-	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
-		goto nla_put_failure;
-	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_info.pool_type))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_SIZE, pool_info.size))
-		goto nla_put_failure;
-	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE,
-		       pool_info.threshold_type))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE,
-			pool_info.cell_size))
-		goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-	return 0;
-
-nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
-}
-
-int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_sb *devlink_sb;
-	struct sk_buff *msg;
-	u16 pool_index;
-	int err;
-
-	devlink_sb = devlink_sb_get_from_info(devlink, info);
-	if (IS_ERR(devlink_sb))
-		return PTR_ERR(devlink_sb);
-
-	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
-						  &pool_index);
-	if (err)
-		return err;
-
-	if (!devlink->ops->sb_pool_get)
-		return -EOPNOTSUPP;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	err = devlink_nl_sb_pool_fill(msg, devlink, devlink_sb, pool_index,
-				      DEVLINK_CMD_SB_POOL_NEW,
-				      info->snd_portid, info->snd_seq, 0);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
-
-	return genlmsg_reply(msg, info);
-}
-
-static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
-				struct devlink *devlink,
-				struct devlink_sb *devlink_sb,
-				u32 portid, u32 seq, int flags)
-{
-	u16 pool_count = devlink_sb_pool_count(devlink_sb);
-	u16 pool_index;
-	int err;
-
-	for (pool_index = 0; pool_index < pool_count; pool_index++) {
-		if (*p_idx < start) {
-			(*p_idx)++;
-			continue;
-		}
-		err = devlink_nl_sb_pool_fill(msg, devlink,
-					      devlink_sb,
-					      pool_index,
-					      DEVLINK_CMD_SB_POOL_NEW,
-					      portid, seq, flags);
-		if (err)
-			return err;
-		(*p_idx)++;
-	}
-	return 0;
-}
-
-static int
-devlink_nl_sb_pool_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-				struct netlink_callback *cb, int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_sb *devlink_sb;
-	int err = 0;
-	int idx = 0;
-
-	if (!devlink->ops->sb_pool_get)
-		return 0;
-
-	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
-		err = __sb_pool_get_dumpit(msg, state->idx, &idx,
-					   devlink, devlink_sb,
-					   NETLINK_CB(cb->skb).portid,
-					   cb->nlh->nlmsg_seq, flags);
-		if (err == -EOPNOTSUPP) {
-			err = 0;
-		} else if (err) {
-			state->idx = idx;
-			break;
-		}
-	}
-
-	return err;
-}
-
-int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb,
-				  struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_pool_get_dump_one);
-}
-
-static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index,
-			       u16 pool_index, u32 size,
-			       enum devlink_sb_threshold_type threshold_type,
-			       struct netlink_ext_ack *extack)
-
-{
-	const struct devlink_ops *ops = devlink->ops;
-
-	if (ops->sb_pool_set)
-		return ops->sb_pool_set(devlink, sb_index, pool_index,
-					size, threshold_type, extack);
-	return -EOPNOTSUPP;
-}
-
-static int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb,
-					   struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	enum devlink_sb_threshold_type threshold_type;
-	struct devlink_sb *devlink_sb;
-	u16 pool_index;
-	u32 size;
-	int err;
-
-	devlink_sb = devlink_sb_get_from_info(devlink, info);
-	if (IS_ERR(devlink_sb))
-		return PTR_ERR(devlink_sb);
-
-	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
-						  &pool_index);
-	if (err)
-		return err;
-
-	err = devlink_sb_th_type_get_from_info(info, &threshold_type);
-	if (err)
-		return err;
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_POOL_SIZE))
-		return -EINVAL;
-
-	size = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_POOL_SIZE]);
-	return devlink_sb_pool_set(devlink, devlink_sb->index,
-				   pool_index, size, threshold_type,
-				   info->extack);
-}
-
-static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg,
-					struct devlink *devlink,
-					struct devlink_port *devlink_port,
-					struct devlink_sb *devlink_sb,
-					u16 pool_index,
-					enum devlink_command cmd,
-					u32 portid, u32 seq, int flags)
-{
-	const struct devlink_ops *ops = devlink->ops;
-	u32 threshold;
-	void *hdr;
-	int err;
-
-	err = ops->sb_port_pool_get(devlink_port, devlink_sb->index,
-				    pool_index, &threshold);
-	if (err)
-		return err;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
-		goto nla_put_failure;
-	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold))
-		goto nla_put_failure;
-
-	if (ops->sb_occ_port_pool_get) {
-		u32 cur;
-		u32 max;
-
-		err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index,
-						pool_index, &cur, &max);
-		if (err && err != -EOPNOTSUPP)
-			goto sb_occ_get_failure;
-		if (!err) {
-			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
-				goto nla_put_failure;
-			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max))
-				goto nla_put_failure;
-		}
-	}
-
-	genlmsg_end(msg, hdr);
-	return 0;
-
-nla_put_failure:
-	err = -EMSGSIZE;
-sb_occ_get_failure:
-	genlmsg_cancel(msg, hdr);
-	return err;
-}
-
-int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
-				     struct genl_info *info)
-{
-	struct devlink_port *devlink_port = info->user_ptr[1];
-	struct devlink *devlink = devlink_port->devlink;
-	struct devlink_sb *devlink_sb;
-	struct sk_buff *msg;
-	u16 pool_index;
-	int err;
-
-	devlink_sb = devlink_sb_get_from_info(devlink, info);
-	if (IS_ERR(devlink_sb))
-		return PTR_ERR(devlink_sb);
-
-	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
-						  &pool_index);
-	if (err)
-		return err;
-
-	if (!devlink->ops->sb_port_pool_get)
-		return -EOPNOTSUPP;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	err = devlink_nl_sb_port_pool_fill(msg, devlink, devlink_port,
-					   devlink_sb, pool_index,
-					   DEVLINK_CMD_SB_PORT_POOL_NEW,
-					   info->snd_portid, info->snd_seq, 0);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
-
-	return genlmsg_reply(msg, info);
-}
-
-static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
-				     struct devlink *devlink,
-				     struct devlink_sb *devlink_sb,
-				     u32 portid, u32 seq, int flags)
-{
-	struct devlink_port *devlink_port;
-	u16 pool_count = devlink_sb_pool_count(devlink_sb);
-	unsigned long port_index;
-	u16 pool_index;
-	int err;
-
-	xa_for_each(&devlink->ports, port_index, devlink_port) {
-		for (pool_index = 0; pool_index < pool_count; pool_index++) {
-			if (*p_idx < start) {
-				(*p_idx)++;
-				continue;
-			}
-			err = devlink_nl_sb_port_pool_fill(msg, devlink,
-							   devlink_port,
-							   devlink_sb,
-							   pool_index,
-							   DEVLINK_CMD_SB_PORT_POOL_NEW,
-							   portid, seq, flags);
-			if (err)
-				return err;
-			(*p_idx)++;
-		}
-	}
-	return 0;
-}
-
-static int
-devlink_nl_sb_port_pool_get_dump_one(struct sk_buff *msg,
-				     struct devlink *devlink,
-				     struct netlink_callback *cb, int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_sb *devlink_sb;
-	int idx = 0;
-	int err = 0;
-
-	if (!devlink->ops->sb_port_pool_get)
-		return 0;
-
-	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
-		err = __sb_port_pool_get_dumpit(msg, state->idx, &idx,
-						devlink, devlink_sb,
-						NETLINK_CB(cb->skb).portid,
-						cb->nlh->nlmsg_seq, flags);
-		if (err == -EOPNOTSUPP) {
-			err = 0;
-		} else if (err) {
-			state->idx = idx;
-			break;
-		}
-	}
-
-	return err;
-}
-
-int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb,
-				       struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_port_pool_get_dump_one);
-}
-
-static int devlink_sb_port_pool_set(struct devlink_port *devlink_port,
-				    unsigned int sb_index, u16 pool_index,
-				    u32 threshold,
-				    struct netlink_ext_ack *extack)
-
-{
-	const struct devlink_ops *ops = devlink_port->devlink->ops;
-
-	if (ops->sb_port_pool_set)
-		return ops->sb_port_pool_set(devlink_port, sb_index,
-					     pool_index, threshold, extack);
-	return -EOPNOTSUPP;
-}
-
-static int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb,
-						struct genl_info *info)
-{
-	struct devlink_port *devlink_port = info->user_ptr[1];
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_sb *devlink_sb;
-	u16 pool_index;
-	u32 threshold;
-	int err;
-
-	devlink_sb = devlink_sb_get_from_info(devlink, info);
-	if (IS_ERR(devlink_sb))
-		return PTR_ERR(devlink_sb);
-
-	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
-						  &pool_index);
-	if (err)
-		return err;
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD))
-		return -EINVAL;
-
-	threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]);
-	return devlink_sb_port_pool_set(devlink_port, devlink_sb->index,
-					pool_index, threshold, info->extack);
-}
-
-static int
-devlink_nl_sb_tc_pool_bind_fill(struct sk_buff *msg, struct devlink *devlink,
-				struct devlink_port *devlink_port,
-				struct devlink_sb *devlink_sb, u16 tc_index,
-				enum devlink_sb_pool_type pool_type,
-				enum devlink_command cmd,
-				u32 portid, u32 seq, int flags)
-{
-	const struct devlink_ops *ops = devlink->ops;
-	u16 pool_index;
-	u32 threshold;
-	void *hdr;
-	int err;
-
-	err = ops->sb_tc_pool_bind_get(devlink_port, devlink_sb->index,
-				       tc_index, pool_type,
-				       &pool_index, &threshold);
-	if (err)
-		return err;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
-		goto nla_put_failure;
-	if (nla_put_u16(msg, DEVLINK_ATTR_SB_TC_INDEX, tc_index))
-		goto nla_put_failure;
-	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_type))
-		goto nla_put_failure;
-	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold))
-		goto nla_put_failure;
-
-	if (ops->sb_occ_tc_port_bind_get) {
-		u32 cur;
-		u32 max;
-
-		err = ops->sb_occ_tc_port_bind_get(devlink_port,
-						   devlink_sb->index,
-						   tc_index, pool_type,
-						   &cur, &max);
-		if (err && err != -EOPNOTSUPP)
-			return err;
-		if (!err) {
-			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
-				goto nla_put_failure;
-			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max))
-				goto nla_put_failure;
-		}
-	}
-
-	genlmsg_end(msg, hdr);
-	return 0;
-
-nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
+	list_for_each_entry_reverse(linecard, &devlink->linecard_list, list)
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
 }
 
-int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
-					struct genl_info *info)
+int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	struct devlink_port *devlink_port = info->user_ptr[1];
-	struct devlink *devlink = devlink_port->devlink;
-	struct devlink_sb *devlink_sb;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_linecard *linecard;
 	struct sk_buff *msg;
-	enum devlink_sb_pool_type pool_type;
-	u16 tc_index;
 	int err;
 
-	devlink_sb = devlink_sb_get_from_info(devlink, info);
-	if (IS_ERR(devlink_sb))
-		return PTR_ERR(devlink_sb);
-
-	err = devlink_sb_pool_type_get_from_info(info, &pool_type);
-	if (err)
-		return err;
-
-	err = devlink_sb_tc_index_get_from_info(devlink_sb, info,
-						pool_type, &tc_index);
-	if (err)
-		return err;
-
-	if (!devlink->ops->sb_tc_pool_bind_get)
-		return -EOPNOTSUPP;
+	linecard = devlink_linecard_get_from_info(devlink, info);
+	if (IS_ERR(linecard))
+		return PTR_ERR(linecard);
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
 
-	err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port,
-					      devlink_sb, tc_index, pool_type,
-					      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
-					      info->snd_portid,
-					      info->snd_seq, 0);
+	mutex_lock(&linecard->state_lock);
+	err = devlink_nl_linecard_fill(msg, devlink, linecard,
+				       DEVLINK_CMD_LINECARD_NEW,
+				       info->snd_portid, info->snd_seq, 0,
+				       info->extack);
+	mutex_unlock(&linecard->state_lock);
 	if (err) {
 		nlmsg_free(msg);
 		return err;
@@ -1880,179 +928,204 @@ int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
 	return genlmsg_reply(msg, info);
 }
 
-static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
-					int start, int *p_idx,
-					struct devlink *devlink,
-					struct devlink_sb *devlink_sb,
-					u32 portid, u32 seq, int flags)
-{
-	struct devlink_port *devlink_port;
-	unsigned long port_index;
-	u16 tc_index;
-	int err;
-
-	xa_for_each(&devlink->ports, port_index, devlink_port) {
-		for (tc_index = 0;
-		     tc_index < devlink_sb->ingress_tc_count; tc_index++) {
-			if (*p_idx < start) {
-				(*p_idx)++;
-				continue;
-			}
-			err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink,
-							      devlink_port,
-							      devlink_sb,
-							      tc_index,
-							      DEVLINK_SB_POOL_TYPE_INGRESS,
-							      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
-							      portid, seq,
-							      flags);
-			if (err)
-				return err;
-			(*p_idx)++;
-		}
-		for (tc_index = 0;
-		     tc_index < devlink_sb->egress_tc_count; tc_index++) {
-			if (*p_idx < start) {
-				(*p_idx)++;
-				continue;
-			}
-			err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink,
-							      devlink_port,
-							      devlink_sb,
-							      tc_index,
-							      DEVLINK_SB_POOL_TYPE_EGRESS,
-							      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
-							      portid, seq,
-							      flags);
-			if (err)
-				return err;
-			(*p_idx)++;
-		}
-	}
-	return 0;
-}
-
-static int devlink_nl_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg,
-						   struct devlink *devlink,
-						   struct netlink_callback *cb,
-						   int flags)
+static int devlink_nl_linecard_get_dump_one(struct sk_buff *msg,
+					    struct devlink *devlink,
+					    struct netlink_callback *cb,
+					    int flags)
 {
 	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_sb *devlink_sb;
+	struct devlink_linecard *linecard;
 	int idx = 0;
 	int err = 0;
 
-	if (!devlink->ops->sb_tc_pool_bind_get)
-		return 0;
-
-	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
-		err = __sb_tc_pool_bind_get_dumpit(msg, state->idx, &idx,
-						   devlink, devlink_sb,
-						   NETLINK_CB(cb->skb).portid,
-						   cb->nlh->nlmsg_seq, flags);
-		if (err == -EOPNOTSUPP) {
-			err = 0;
-		} else if (err) {
+	list_for_each_entry(linecard, &devlink->linecard_list, list) {
+		if (idx < state->idx) {
+			idx++;
+			continue;
+		}
+		mutex_lock(&linecard->state_lock);
+		err = devlink_nl_linecard_fill(msg, devlink, linecard,
+					       DEVLINK_CMD_LINECARD_NEW,
+					       NETLINK_CB(cb->skb).portid,
+					       cb->nlh->nlmsg_seq, flags,
+					       cb->extack);
+		mutex_unlock(&linecard->state_lock);
+		if (err) {
 			state->idx = idx;
 			break;
 		}
+		idx++;
 	}
 
 	return err;
 }
 
-int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb,
-					  struct netlink_callback *cb)
+int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb)
 {
-	return devlink_nl_dumpit(skb, cb,
-				 devlink_nl_sb_tc_pool_bind_get_dump_one);
+	return devlink_nl_dumpit(skb, cb, devlink_nl_linecard_get_dump_one);
 }
 
-static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
-				       unsigned int sb_index, u16 tc_index,
-				       enum devlink_sb_pool_type pool_type,
-				       u16 pool_index, u32 threshold,
-				       struct netlink_ext_ack *extack)
-
+static struct devlink_linecard_type *
+devlink_linecard_type_lookup(struct devlink_linecard *linecard,
+			     const char *type)
 {
-	const struct devlink_ops *ops = devlink_port->devlink->ops;
+	struct devlink_linecard_type *linecard_type;
+	int i;
 
-	if (ops->sb_tc_pool_bind_set)
-		return ops->sb_tc_pool_bind_set(devlink_port, sb_index,
-						tc_index, pool_type,
-						pool_index, threshold, extack);
-	return -EOPNOTSUPP;
+	for (i = 0; i < linecard->types_count; i++) {
+		linecard_type = &linecard->types[i];
+		if (!strcmp(type, linecard_type->type))
+			return linecard_type;
+	}
+	return NULL;
 }
 
-static int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb,
-						   struct genl_info *info)
+static int devlink_linecard_type_set(struct devlink_linecard *linecard,
+				     const char *type,
+				     struct netlink_ext_ack *extack)
 {
-	struct devlink_port *devlink_port = info->user_ptr[1];
-	struct devlink *devlink = info->user_ptr[0];
-	enum devlink_sb_pool_type pool_type;
-	struct devlink_sb *devlink_sb;
-	u16 tc_index;
-	u16 pool_index;
-	u32 threshold;
+	const struct devlink_linecard_ops *ops = linecard->ops;
+	struct devlink_linecard_type *linecard_type;
 	int err;
 
-	devlink_sb = devlink_sb_get_from_info(devlink, info);
-	if (IS_ERR(devlink_sb))
-		return PTR_ERR(devlink_sb);
-
-	err = devlink_sb_pool_type_get_from_info(info, &pool_type);
-	if (err)
-		return err;
+	mutex_lock(&linecard->state_lock);
+	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
+		err = -EBUSY;
+		goto out;
+	}
+	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
+		err = -EBUSY;
+		goto out;
+	}
 
-	err = devlink_sb_tc_index_get_from_info(devlink_sb, info,
-						pool_type, &tc_index);
-	if (err)
-		return err;
+	linecard_type = devlink_linecard_type_lookup(linecard, type);
+	if (!linecard_type) {
+		NL_SET_ERR_MSG(extack, "Unsupported line card type provided");
+		err = -EINVAL;
+		goto out;
+	}
 
-	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
-						  &pool_index);
-	if (err)
-		return err;
+	if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED &&
+	    linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
+		NL_SET_ERR_MSG(extack, "Line card already provisioned");
+		err = -EBUSY;
+		/* Check if the line card is provisioned in the same
+		 * way the user asks. In case it is, make the operation
+		 * to return success.
+		 */
+		if (ops->same_provision &&
+		    ops->same_provision(linecard, linecard->priv,
+					linecard_type->type,
+					linecard_type->priv))
+			err = 0;
+		goto out;
+	}
 
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD))
-		return -EINVAL;
+	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING;
+	linecard->type = linecard_type->type;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+	err = ops->provision(linecard, linecard->priv, linecard_type->type,
+			     linecard_type->priv, extack);
+	if (err) {
+		/* Provisioning failed. Assume the linecard is unprovisioned
+		 * for future operations.
+		 */
+		mutex_lock(&linecard->state_lock);
+		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+		linecard->type = NULL;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+		mutex_unlock(&linecard->state_lock);
+	}
+	return err;
 
-	threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]);
-	return devlink_sb_tc_pool_bind_set(devlink_port, devlink_sb->index,
-					   tc_index, pool_type,
-					   pool_index, threshold, info->extack);
+out:
+	mutex_unlock(&linecard->state_lock);
+	return err;
 }
 
-static int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb,
-					       struct genl_info *info)
+static int devlink_linecard_type_unset(struct devlink_linecard *linecard,
+				       struct netlink_ext_ack *extack)
 {
-	struct devlink *devlink = info->user_ptr[0];
-	const struct devlink_ops *ops = devlink->ops;
-	struct devlink_sb *devlink_sb;
+	int err;
+
+	mutex_lock(&linecard->state_lock);
+	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
+		err = -EBUSY;
+		goto out;
+	}
+	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
+		err = -EBUSY;
+		goto out;
+	}
+	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
+		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+		linecard->type = NULL;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+		err = 0;
+		goto out;
+	}
 
-	devlink_sb = devlink_sb_get_from_info(devlink, info);
-	if (IS_ERR(devlink_sb))
-		return PTR_ERR(devlink_sb);
+	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) {
+		NL_SET_ERR_MSG(extack, "Line card is not provisioned");
+		err = 0;
+		goto out;
+	}
+	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+	err = linecard->ops->unprovision(linecard, linecard->priv,
+					 extack);
+	if (err) {
+		/* Unprovisioning failed. Assume the linecard is unprovisioned
+		 * for future operations.
+		 */
+		mutex_lock(&linecard->state_lock);
+		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+		linecard->type = NULL;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+		mutex_unlock(&linecard->state_lock);
+	}
+	return err;
 
-	if (ops->sb_occ_snapshot)
-		return ops->sb_occ_snapshot(devlink, devlink_sb->index);
-	return -EOPNOTSUPP;
+out:
+	mutex_unlock(&linecard->state_lock);
+	return err;
 }
 
-static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb,
-						struct genl_info *info)
+static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb,
+					    struct genl_info *info)
 {
+	struct netlink_ext_ack *extack = info->extack;
 	struct devlink *devlink = info->user_ptr[0];
-	const struct devlink_ops *ops = devlink->ops;
-	struct devlink_sb *devlink_sb;
+	struct devlink_linecard *linecard;
+	int err;
 
-	devlink_sb = devlink_sb_get_from_info(devlink, info);
-	if (IS_ERR(devlink_sb))
-		return PTR_ERR(devlink_sb);
+	linecard = devlink_linecard_get_from_info(devlink, info);
+	if (IS_ERR(linecard))
+		return PTR_ERR(linecard);
+
+	if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) {
+		const char *type;
+
+		type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]);
+		if (strcmp(type, "")) {
+			err = devlink_linecard_type_set(linecard, type, extack);
+			if (err)
+				return err;
+		} else {
+			err = devlink_linecard_type_unset(linecard, extack);
+			if (err)
+				return err;
+		}
+	}
 
-	if (ops->sb_occ_max_clear)
-		return ops->sb_occ_max_clear(devlink, devlink_sb->index);
-	return -EOPNOTSUPP;
+	return 0;
 }
 
 int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
@@ -6215,69 +5288,6 @@ void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard,
 }
 EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set);
 
-int devl_sb_register(struct devlink *devlink, unsigned int sb_index,
-		     u32 size, u16 ingress_pools_count,
-		     u16 egress_pools_count, u16 ingress_tc_count,
-		     u16 egress_tc_count)
-{
-	struct devlink_sb *devlink_sb;
-
-	lockdep_assert_held(&devlink->lock);
-
-	if (devlink_sb_index_exists(devlink, sb_index))
-		return -EEXIST;
-
-	devlink_sb = kzalloc(sizeof(*devlink_sb), GFP_KERNEL);
-	if (!devlink_sb)
-		return -ENOMEM;
-	devlink_sb->index = sb_index;
-	devlink_sb->size = size;
-	devlink_sb->ingress_pools_count = ingress_pools_count;
-	devlink_sb->egress_pools_count = egress_pools_count;
-	devlink_sb->ingress_tc_count = ingress_tc_count;
-	devlink_sb->egress_tc_count = egress_tc_count;
-	list_add_tail(&devlink_sb->list, &devlink->sb_list);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devl_sb_register);
-
-int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
-			u32 size, u16 ingress_pools_count,
-			u16 egress_pools_count, u16 ingress_tc_count,
-			u16 egress_tc_count)
-{
-	int err;
-
-	devl_lock(devlink);
-	err = devl_sb_register(devlink, sb_index, size, ingress_pools_count,
-			       egress_pools_count, ingress_tc_count,
-			       egress_tc_count);
-	devl_unlock(devlink);
-	return err;
-}
-EXPORT_SYMBOL_GPL(devlink_sb_register);
-
-void devl_sb_unregister(struct devlink *devlink, unsigned int sb_index)
-{
-	struct devlink_sb *devlink_sb;
-
-	lockdep_assert_held(&devlink->lock);
-
-	devlink_sb = devlink_sb_get_by_index(devlink, sb_index);
-	WARN_ON(!devlink_sb);
-	list_del(&devlink_sb->list);
-	kfree(devlink_sb);
-}
-EXPORT_SYMBOL_GPL(devl_sb_unregister);
-
-void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index)
-{
-	devl_lock(devlink);
-	devl_sb_unregister(devlink, sb_index);
-	devl_unlock(devlink);
-}
-EXPORT_SYMBOL_GPL(devlink_sb_unregister);
-
 /**
  * devl_dpipe_headers_register - register dpipe headers
  *
diff --git a/net/devlink/sb.c b/net/devlink/sb.c
new file mode 100644
index 0000000000000..bd677fff5ec8f
--- /dev/null
+++ b/net/devlink/sb.c
@@ -0,0 +1,996 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include "devl_internal.h"
+
+struct devlink_sb {
+	struct list_head list;
+	unsigned int index;
+	u32 size;
+	u16 ingress_pools_count;
+	u16 egress_pools_count;
+	u16 ingress_tc_count;
+	u16 egress_tc_count;
+};
+
+static u16 devlink_sb_pool_count(struct devlink_sb *devlink_sb)
+{
+	return devlink_sb->ingress_pools_count + devlink_sb->egress_pools_count;
+}
+
+static struct devlink_sb *devlink_sb_get_by_index(struct devlink *devlink,
+						  unsigned int sb_index)
+{
+	struct devlink_sb *devlink_sb;
+
+	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
+		if (devlink_sb->index == sb_index)
+			return devlink_sb;
+	}
+	return NULL;
+}
+
+static bool devlink_sb_index_exists(struct devlink *devlink,
+				    unsigned int sb_index)
+{
+	return devlink_sb_get_by_index(devlink, sb_index);
+}
+
+static struct devlink_sb *devlink_sb_get_from_attrs(struct devlink *devlink,
+						    struct nlattr **attrs)
+{
+	if (attrs[DEVLINK_ATTR_SB_INDEX]) {
+		u32 sb_index = nla_get_u32(attrs[DEVLINK_ATTR_SB_INDEX]);
+		struct devlink_sb *devlink_sb;
+
+		devlink_sb = devlink_sb_get_by_index(devlink, sb_index);
+		if (!devlink_sb)
+			return ERR_PTR(-ENODEV);
+		return devlink_sb;
+	}
+	return ERR_PTR(-EINVAL);
+}
+
+static struct devlink_sb *devlink_sb_get_from_info(struct devlink *devlink,
+						   struct genl_info *info)
+{
+	return devlink_sb_get_from_attrs(devlink, info->attrs);
+}
+
+static int devlink_sb_pool_index_get_from_attrs(struct devlink_sb *devlink_sb,
+						struct nlattr **attrs,
+						u16 *p_pool_index)
+{
+	u16 val;
+
+	if (!attrs[DEVLINK_ATTR_SB_POOL_INDEX])
+		return -EINVAL;
+
+	val = nla_get_u16(attrs[DEVLINK_ATTR_SB_POOL_INDEX]);
+	if (val >= devlink_sb_pool_count(devlink_sb))
+		return -EINVAL;
+	*p_pool_index = val;
+	return 0;
+}
+
+static int devlink_sb_pool_index_get_from_info(struct devlink_sb *devlink_sb,
+					       struct genl_info *info,
+					       u16 *p_pool_index)
+{
+	return devlink_sb_pool_index_get_from_attrs(devlink_sb, info->attrs,
+						    p_pool_index);
+}
+
+static int
+devlink_sb_pool_type_get_from_attrs(struct nlattr **attrs,
+				    enum devlink_sb_pool_type *p_pool_type)
+{
+	u8 val;
+
+	if (!attrs[DEVLINK_ATTR_SB_POOL_TYPE])
+		return -EINVAL;
+
+	val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_TYPE]);
+	if (val != DEVLINK_SB_POOL_TYPE_INGRESS &&
+	    val != DEVLINK_SB_POOL_TYPE_EGRESS)
+		return -EINVAL;
+	*p_pool_type = val;
+	return 0;
+}
+
+static int
+devlink_sb_pool_type_get_from_info(struct genl_info *info,
+				   enum devlink_sb_pool_type *p_pool_type)
+{
+	return devlink_sb_pool_type_get_from_attrs(info->attrs, p_pool_type);
+}
+
+static int
+devlink_sb_th_type_get_from_attrs(struct nlattr **attrs,
+				  enum devlink_sb_threshold_type *p_th_type)
+{
+	u8 val;
+
+	if (!attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE])
+		return -EINVAL;
+
+	val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]);
+	if (val != DEVLINK_SB_THRESHOLD_TYPE_STATIC &&
+	    val != DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC)
+		return -EINVAL;
+	*p_th_type = val;
+	return 0;
+}
+
+static int
+devlink_sb_th_type_get_from_info(struct genl_info *info,
+				 enum devlink_sb_threshold_type *p_th_type)
+{
+	return devlink_sb_th_type_get_from_attrs(info->attrs, p_th_type);
+}
+
+static int
+devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb,
+				   struct nlattr **attrs,
+				   enum devlink_sb_pool_type pool_type,
+				   u16 *p_tc_index)
+{
+	u16 val;
+
+	if (!attrs[DEVLINK_ATTR_SB_TC_INDEX])
+		return -EINVAL;
+
+	val = nla_get_u16(attrs[DEVLINK_ATTR_SB_TC_INDEX]);
+	if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS &&
+	    val >= devlink_sb->ingress_tc_count)
+		return -EINVAL;
+	if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS &&
+	    val >= devlink_sb->egress_tc_count)
+		return -EINVAL;
+	*p_tc_index = val;
+	return 0;
+}
+
+static int
+devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,
+				  struct genl_info *info,
+				  enum devlink_sb_pool_type pool_type,
+				  u16 *p_tc_index)
+{
+	return devlink_sb_tc_index_get_from_attrs(devlink_sb, info->attrs,
+						  pool_type, p_tc_index);
+}
+
+static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink,
+			      struct devlink_sb *devlink_sb,
+			      enum devlink_command cmd, u32 portid,
+			      u32 seq, int flags)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_SIZE, devlink_sb->size))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_POOL_COUNT,
+			devlink_sb->ingress_pools_count))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_POOL_COUNT,
+			devlink_sb->egress_pools_count))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_TC_COUNT,
+			devlink_sb->ingress_tc_count))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_TC_COUNT,
+			devlink_sb->egress_tc_count))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_sb *devlink_sb;
+	struct sk_buff *msg;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_sb_fill(msg, devlink, devlink_sb,
+				 DEVLINK_CMD_SB_NEW,
+				 info->snd_portid, info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int
+devlink_nl_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+			   struct netlink_callback *cb, int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_sb *devlink_sb;
+	int idx = 0;
+	int err = 0;
+
+	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
+		if (idx < state->idx) {
+			idx++;
+			continue;
+		}
+		err = devlink_nl_sb_fill(msg, devlink, devlink_sb,
+					 DEVLINK_CMD_SB_NEW,
+					 NETLINK_CB(cb->skb).portid,
+					 cb->nlh->nlmsg_seq, flags);
+		if (err) {
+			state->idx = idx;
+			break;
+		}
+		idx++;
+	}
+
+	return err;
+}
+
+int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_get_dump_one);
+}
+
+static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink,
+				   struct devlink_sb *devlink_sb,
+				   u16 pool_index, enum devlink_command cmd,
+				   u32 portid, u32 seq, int flags)
+{
+	struct devlink_sb_pool_info pool_info;
+	void *hdr;
+	int err;
+
+	err = devlink->ops->sb_pool_get(devlink, devlink_sb->index,
+					pool_index, &pool_info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
+		goto nla_put_failure;
+	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_info.pool_type))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_SIZE, pool_info.size))
+		goto nla_put_failure;
+	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE,
+		       pool_info.threshold_type))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE,
+			pool_info.cell_size))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_sb *devlink_sb;
+	struct sk_buff *msg;
+	u16 pool_index;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
+						  &pool_index);
+	if (err)
+		return err;
+
+	if (!devlink->ops->sb_pool_get)
+		return -EOPNOTSUPP;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_sb_pool_fill(msg, devlink, devlink_sb, pool_index,
+				      DEVLINK_CMD_SB_POOL_NEW,
+				      info->snd_portid, info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
+				struct devlink *devlink,
+				struct devlink_sb *devlink_sb,
+				u32 portid, u32 seq, int flags)
+{
+	u16 pool_count = devlink_sb_pool_count(devlink_sb);
+	u16 pool_index;
+	int err;
+
+	for (pool_index = 0; pool_index < pool_count; pool_index++) {
+		if (*p_idx < start) {
+			(*p_idx)++;
+			continue;
+		}
+		err = devlink_nl_sb_pool_fill(msg, devlink,
+					      devlink_sb,
+					      pool_index,
+					      DEVLINK_CMD_SB_POOL_NEW,
+					      portid, seq, flags);
+		if (err)
+			return err;
+		(*p_idx)++;
+	}
+	return 0;
+}
+
+static int
+devlink_nl_sb_pool_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+				struct netlink_callback *cb, int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_sb *devlink_sb;
+	int err = 0;
+	int idx = 0;
+
+	if (!devlink->ops->sb_pool_get)
+		return 0;
+
+	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
+		err = __sb_pool_get_dumpit(msg, state->idx, &idx,
+					   devlink, devlink_sb,
+					   NETLINK_CB(cb->skb).portid,
+					   cb->nlh->nlmsg_seq, flags);
+		if (err == -EOPNOTSUPP) {
+			err = 0;
+		} else if (err) {
+			state->idx = idx;
+			break;
+		}
+	}
+
+	return err;
+}
+
+int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_pool_get_dump_one);
+}
+
+static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index,
+			       u16 pool_index, u32 size,
+			       enum devlink_sb_threshold_type threshold_type,
+			       struct netlink_ext_ack *extack)
+
+{
+	const struct devlink_ops *ops = devlink->ops;
+
+	if (ops->sb_pool_set)
+		return ops->sb_pool_set(devlink, sb_index, pool_index,
+					size, threshold_type, extack);
+	return -EOPNOTSUPP;
+}
+
+int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	enum devlink_sb_threshold_type threshold_type;
+	struct devlink_sb *devlink_sb;
+	u16 pool_index;
+	u32 size;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
+						  &pool_index);
+	if (err)
+		return err;
+
+	err = devlink_sb_th_type_get_from_info(info, &threshold_type);
+	if (err)
+		return err;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_POOL_SIZE))
+		return -EINVAL;
+
+	size = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_POOL_SIZE]);
+	return devlink_sb_pool_set(devlink, devlink_sb->index,
+				   pool_index, size, threshold_type,
+				   info->extack);
+}
+
+static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg,
+					struct devlink *devlink,
+					struct devlink_port *devlink_port,
+					struct devlink_sb *devlink_sb,
+					u16 pool_index,
+					enum devlink_command cmd,
+					u32 portid, u32 seq, int flags)
+{
+	const struct devlink_ops *ops = devlink->ops;
+	u32 threshold;
+	void *hdr;
+	int err;
+
+	err = ops->sb_port_pool_get(devlink_port, devlink_sb->index,
+				    pool_index, &threshold);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold))
+		goto nla_put_failure;
+
+	if (ops->sb_occ_port_pool_get) {
+		u32 cur;
+		u32 max;
+
+		err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index,
+						pool_index, &cur, &max);
+		if (err && err != -EOPNOTSUPP)
+			goto sb_occ_get_failure;
+		if (!err) {
+			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
+				goto nla_put_failure;
+			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max))
+				goto nla_put_failure;
+		}
+	}
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	err = -EMSGSIZE;
+sb_occ_get_failure:
+	genlmsg_cancel(msg, hdr);
+	return err;
+}
+
+int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_sb *devlink_sb;
+	struct sk_buff *msg;
+	u16 pool_index;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
+						  &pool_index);
+	if (err)
+		return err;
+
+	if (!devlink->ops->sb_port_pool_get)
+		return -EOPNOTSUPP;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_sb_port_pool_fill(msg, devlink, devlink_port,
+					   devlink_sb, pool_index,
+					   DEVLINK_CMD_SB_PORT_POOL_NEW,
+					   info->snd_portid, info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
+				     struct devlink *devlink,
+				     struct devlink_sb *devlink_sb,
+				     u32 portid, u32 seq, int flags)
+{
+	struct devlink_port *devlink_port;
+	u16 pool_count = devlink_sb_pool_count(devlink_sb);
+	unsigned long port_index;
+	u16 pool_index;
+	int err;
+
+	xa_for_each(&devlink->ports, port_index, devlink_port) {
+		for (pool_index = 0; pool_index < pool_count; pool_index++) {
+			if (*p_idx < start) {
+				(*p_idx)++;
+				continue;
+			}
+			err = devlink_nl_sb_port_pool_fill(msg, devlink,
+							   devlink_port,
+							   devlink_sb,
+							   pool_index,
+							   DEVLINK_CMD_SB_PORT_POOL_NEW,
+							   portid, seq, flags);
+			if (err)
+				return err;
+			(*p_idx)++;
+		}
+	}
+	return 0;
+}
+
+static int
+devlink_nl_sb_port_pool_get_dump_one(struct sk_buff *msg,
+				     struct devlink *devlink,
+				     struct netlink_callback *cb, int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_sb *devlink_sb;
+	int idx = 0;
+	int err = 0;
+
+	if (!devlink->ops->sb_port_pool_get)
+		return 0;
+
+	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
+		err = __sb_port_pool_get_dumpit(msg, state->idx, &idx,
+						devlink, devlink_sb,
+						NETLINK_CB(cb->skb).portid,
+						cb->nlh->nlmsg_seq, flags);
+		if (err == -EOPNOTSUPP) {
+			err = 0;
+		} else if (err) {
+			state->idx = idx;
+			break;
+		}
+	}
+
+	return err;
+}
+
+int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_port_pool_get_dump_one);
+}
+
+static int devlink_sb_port_pool_set(struct devlink_port *devlink_port,
+				    unsigned int sb_index, u16 pool_index,
+				    u32 threshold,
+				    struct netlink_ext_ack *extack)
+
+{
+	const struct devlink_ops *ops = devlink_port->devlink->ops;
+
+	if (ops->sb_port_pool_set)
+		return ops->sb_port_pool_set(devlink_port, sb_index,
+					     pool_index, threshold, extack);
+	return -EOPNOTSUPP;
+}
+
+int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb,
+					 struct genl_info *info)
+{
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_sb *devlink_sb;
+	u16 pool_index;
+	u32 threshold;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
+						  &pool_index);
+	if (err)
+		return err;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD))
+		return -EINVAL;
+
+	threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]);
+	return devlink_sb_port_pool_set(devlink_port, devlink_sb->index,
+					pool_index, threshold, info->extack);
+}
+
+static int
+devlink_nl_sb_tc_pool_bind_fill(struct sk_buff *msg, struct devlink *devlink,
+				struct devlink_port *devlink_port,
+				struct devlink_sb *devlink_sb, u16 tc_index,
+				enum devlink_sb_pool_type pool_type,
+				enum devlink_command cmd,
+				u32 portid, u32 seq, int flags)
+{
+	const struct devlink_ops *ops = devlink->ops;
+	u16 pool_index;
+	u32 threshold;
+	void *hdr;
+	int err;
+
+	err = ops->sb_tc_pool_bind_get(devlink_port, devlink_sb->index,
+				       tc_index, pool_type,
+				       &pool_index, &threshold);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_TC_INDEX, tc_index))
+		goto nla_put_failure;
+	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_type))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold))
+		goto nla_put_failure;
+
+	if (ops->sb_occ_tc_port_bind_get) {
+		u32 cur;
+		u32 max;
+
+		err = ops->sb_occ_tc_port_bind_get(devlink_port,
+						   devlink_sb->index,
+						   tc_index, pool_type,
+						   &cur, &max);
+		if (err && err != -EOPNOTSUPP)
+			return err;
+		if (!err) {
+			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
+				goto nla_put_failure;
+			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max))
+				goto nla_put_failure;
+		}
+	}
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_sb *devlink_sb;
+	struct sk_buff *msg;
+	enum devlink_sb_pool_type pool_type;
+	u16 tc_index;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_type_get_from_info(info, &pool_type);
+	if (err)
+		return err;
+
+	err = devlink_sb_tc_index_get_from_info(devlink_sb, info,
+						pool_type, &tc_index);
+	if (err)
+		return err;
+
+	if (!devlink->ops->sb_tc_pool_bind_get)
+		return -EOPNOTSUPP;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port,
+					      devlink_sb, tc_index, pool_type,
+					      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
+					      info->snd_portid,
+					      info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
+					int start, int *p_idx,
+					struct devlink *devlink,
+					struct devlink_sb *devlink_sb,
+					u32 portid, u32 seq, int flags)
+{
+	struct devlink_port *devlink_port;
+	unsigned long port_index;
+	u16 tc_index;
+	int err;
+
+	xa_for_each(&devlink->ports, port_index, devlink_port) {
+		for (tc_index = 0;
+		     tc_index < devlink_sb->ingress_tc_count; tc_index++) {
+			if (*p_idx < start) {
+				(*p_idx)++;
+				continue;
+			}
+			err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink,
+							      devlink_port,
+							      devlink_sb,
+							      tc_index,
+							      DEVLINK_SB_POOL_TYPE_INGRESS,
+							      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
+							      portid, seq,
+							      flags);
+			if (err)
+				return err;
+			(*p_idx)++;
+		}
+		for (tc_index = 0;
+		     tc_index < devlink_sb->egress_tc_count; tc_index++) {
+			if (*p_idx < start) {
+				(*p_idx)++;
+				continue;
+			}
+			err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink,
+							      devlink_port,
+							      devlink_sb,
+							      tc_index,
+							      DEVLINK_SB_POOL_TYPE_EGRESS,
+							      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
+							      portid, seq,
+							      flags);
+			if (err)
+				return err;
+			(*p_idx)++;
+		}
+	}
+	return 0;
+}
+
+static int devlink_nl_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg,
+						   struct devlink *devlink,
+						   struct netlink_callback *cb,
+						   int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_sb *devlink_sb;
+	int idx = 0;
+	int err = 0;
+
+	if (!devlink->ops->sb_tc_pool_bind_get)
+		return 0;
+
+	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
+		err = __sb_tc_pool_bind_get_dumpit(msg, state->idx, &idx,
+						   devlink, devlink_sb,
+						   NETLINK_CB(cb->skb).portid,
+						   cb->nlh->nlmsg_seq, flags);
+		if (err == -EOPNOTSUPP) {
+			err = 0;
+		} else if (err) {
+			state->idx = idx;
+			break;
+		}
+	}
+
+	return err;
+}
+
+int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb,
+				 devlink_nl_sb_tc_pool_bind_get_dump_one);
+}
+
+static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
+				       unsigned int sb_index, u16 tc_index,
+				       enum devlink_sb_pool_type pool_type,
+				       u16 pool_index, u32 threshold,
+				       struct netlink_ext_ack *extack)
+
+{
+	const struct devlink_ops *ops = devlink_port->devlink->ops;
+
+	if (ops->sb_tc_pool_bind_set)
+		return ops->sb_tc_pool_bind_set(devlink_port, sb_index,
+						tc_index, pool_type,
+						pool_index, threshold, extack);
+	return -EOPNOTSUPP;
+}
+
+int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	struct devlink *devlink = info->user_ptr[0];
+	enum devlink_sb_pool_type pool_type;
+	struct devlink_sb *devlink_sb;
+	u16 tc_index;
+	u16 pool_index;
+	u32 threshold;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_type_get_from_info(info, &pool_type);
+	if (err)
+		return err;
+
+	err = devlink_sb_tc_index_get_from_info(devlink_sb, info,
+						pool_type, &tc_index);
+	if (err)
+		return err;
+
+	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
+						  &pool_index);
+	if (err)
+		return err;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD))
+		return -EINVAL;
+
+	threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]);
+	return devlink_sb_tc_pool_bind_set(devlink_port, devlink_sb->index,
+					   tc_index, pool_type,
+					   pool_index, threshold, info->extack);
+}
+
+int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const struct devlink_ops *ops = devlink->ops;
+	struct devlink_sb *devlink_sb;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	if (ops->sb_occ_snapshot)
+		return ops->sb_occ_snapshot(devlink, devlink_sb->index);
+	return -EOPNOTSUPP;
+}
+
+int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb,
+					 struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const struct devlink_ops *ops = devlink->ops;
+	struct devlink_sb *devlink_sb;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	if (ops->sb_occ_max_clear)
+		return ops->sb_occ_max_clear(devlink, devlink_sb->index);
+	return -EOPNOTSUPP;
+}
+
+int devl_sb_register(struct devlink *devlink, unsigned int sb_index,
+		     u32 size, u16 ingress_pools_count,
+		     u16 egress_pools_count, u16 ingress_tc_count,
+		     u16 egress_tc_count)
+{
+	struct devlink_sb *devlink_sb;
+
+	lockdep_assert_held(&devlink->lock);
+
+	if (devlink_sb_index_exists(devlink, sb_index))
+		return -EEXIST;
+
+	devlink_sb = kzalloc(sizeof(*devlink_sb), GFP_KERNEL);
+	if (!devlink_sb)
+		return -ENOMEM;
+	devlink_sb->index = sb_index;
+	devlink_sb->size = size;
+	devlink_sb->ingress_pools_count = ingress_pools_count;
+	devlink_sb->egress_pools_count = egress_pools_count;
+	devlink_sb->ingress_tc_count = ingress_tc_count;
+	devlink_sb->egress_tc_count = egress_tc_count;
+	list_add_tail(&devlink_sb->list, &devlink->sb_list);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devl_sb_register);
+
+int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
+			u32 size, u16 ingress_pools_count,
+			u16 egress_pools_count, u16 ingress_tc_count,
+			u16 egress_tc_count)
+{
+	int err;
+
+	devl_lock(devlink);
+	err = devl_sb_register(devlink, sb_index, size, ingress_pools_count,
+			       egress_pools_count, ingress_tc_count,
+			       egress_tc_count);
+	devl_unlock(devlink);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devlink_sb_register);
+
+void devl_sb_unregister(struct devlink *devlink, unsigned int sb_index)
+{
+	struct devlink_sb *devlink_sb;
+
+	lockdep_assert_held(&devlink->lock);
+
+	devlink_sb = devlink_sb_get_by_index(devlink, sb_index);
+	WARN_ON(!devlink_sb);
+	list_del(&devlink_sb->list);
+	kfree(devlink_sb);
+}
+EXPORT_SYMBOL_GPL(devl_sb_unregister);
+
+void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index)
+{
+	devl_lock(devlink);
+	devl_sb_unregister(devlink, sb_index);
+	devl_unlock(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_sb_unregister);
-- 
GitLab


From 2475ed158c478c624d8fbc8d639d344a960c1ad8 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:46 +0200
Subject: [PATCH 1791/1806] devlink: move and rename
 devlink_dpipe_send_and_alloc_skb() helper

Since both dpipe and resource code is using this helper, in preparation
for code split to separate files, move
devlink_dpipe_send_and_alloc_skb() helper into netlink.c. Rename it on
the way.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-5-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h |  2 ++
 net/devlink/leftover.c      | 34 +++++++++-------------------------
 net/devlink/netlink.c       | 15 +++++++++++++++
 3 files changed, 26 insertions(+), 25 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index e1a6b7a763b8b..66c94957e96c9 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -150,6 +150,8 @@ devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
 	return 0;
 }
 
+int devlink_nl_msg_reply_and_new(struct sk_buff **msg, struct genl_info *info);
+
 /* Notify */
 void devlink_notify(struct devlink *devlink, enum devlink_command cmd);
 void devlink_ports_notify_register(struct devlink *devlink);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 795bfdd41103a..1bcd4192099e1 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -1277,22 +1277,6 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb,
-					    struct genl_info *info)
-{
-	int err;
-
-	if (*pskb) {
-		err = genlmsg_reply(*pskb, info);
-		if (err)
-			return err;
-	}
-	*pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!*pskb)
-		return -ENOMEM;
-	return 0;
-}
-
 static int devlink_dpipe_tables_fill(struct genl_info *info,
 				     enum devlink_command cmd, int flags,
 				     struct list_head *dpipe_tables,
@@ -1311,7 +1295,7 @@ static int devlink_dpipe_tables_fill(struct genl_info *info,
 	table = list_first_entry(dpipe_tables,
 				 struct devlink_dpipe_table, list);
 start_again:
-	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	err = devlink_nl_msg_reply_and_new(&skb, info);
 	if (err)
 		return err;
 
@@ -1358,7 +1342,7 @@ send_done:
 	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
 			NLMSG_DONE, 0, flags | NLM_F_MULTI);
 	if (!nlh) {
-		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		err = devlink_nl_msg_reply_and_new(&skb, info);
 		if (err)
 			return err;
 		goto send_done;
@@ -1551,8 +1535,8 @@ int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
 	struct devlink *devlink;
 	int err;
 
-	err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb,
-					       dump_ctx->info);
+	err = devlink_nl_msg_reply_and_new(&dump_ctx->skb,
+					   dump_ctx->info);
 	if (err)
 		return err;
 
@@ -1638,7 +1622,7 @@ send_done:
 	nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq,
 			NLMSG_DONE, 0, flags | NLM_F_MULTI);
 	if (!nlh) {
-		err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info);
+		err = devlink_nl_msg_reply_and_new(&dump_ctx.skb, info);
 		if (err)
 			return err;
 		goto send_done;
@@ -1746,7 +1730,7 @@ static int devlink_dpipe_headers_fill(struct genl_info *info,
 
 	i = 0;
 start_again:
-	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	err = devlink_nl_msg_reply_and_new(&skb, info);
 	if (err)
 		return err;
 
@@ -1782,7 +1766,7 @@ send_done:
 	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
 			NLMSG_DONE, 0, flags | NLM_F_MULTI);
 	if (!nlh) {
-		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		err = devlink_nl_msg_reply_and_new(&skb, info);
 		if (err)
 			return err;
 		goto send_done;
@@ -2047,7 +2031,7 @@ static int devlink_resource_fill(struct genl_info *info,
 	resource = list_first_entry(&devlink->resource_list,
 				    struct devlink_resource, list);
 start_again:
-	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	err = devlink_nl_msg_reply_and_new(&skb, info);
 	if (err)
 		return err;
 
@@ -2086,7 +2070,7 @@ send_done:
 	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
 			NLMSG_DONE, 0, flags | NLM_F_MULTI);
 	if (!nlh) {
-		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		err = devlink_nl_msg_reply_and_new(&skb, info);
 		if (err)
 			return err;
 		goto send_done;
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 72a5005a64cd7..5f57afd31dea5 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -82,6 +82,21 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG },
 };
 
+int devlink_nl_msg_reply_and_new(struct sk_buff **msg, struct genl_info *info)
+{
+	int err;
+
+	if (*msg) {
+		err = genlmsg_reply(*msg, info);
+		if (err)
+			return err;
+	}
+	*msg = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!*msg)
+		return -ENOMEM;
+	return 0;
+}
+
 struct devlink *
 devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs)
 {
-- 
GitLab


From a9fd44b15fc5625ee0a38661e773444f6bf31b3d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:47 +0200
Subject: [PATCH 1792/1806] devlink: push dpipe related code into separate file

Cut out another chunk from leftover.c and put dpipe related code
into a separate file.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-6-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/Makefile        |   3 +-
 net/devlink/devl_internal.h |   7 +
 net/devlink/dpipe.c         | 917 ++++++++++++++++++++++++++++++++++++
 net/devlink/leftover.c      | 894 -----------------------------------
 4 files changed, 926 insertions(+), 895 deletions(-)
 create mode 100644 net/devlink/dpipe.c

diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index dcc508af48a9f..122de1d565d22 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o sb.o health.o \
+obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o sb.o dpipe.o \
+	 health.o
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 66c94957e96c9..72653e1dae801 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -231,6 +231,13 @@ int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb,
 					struct genl_info *info);
 int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb,
 					 struct genl_info *info);
+int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb,
+					    struct genl_info *info);
 int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 					    struct genl_info *info);
 int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
diff --git a/net/devlink/dpipe.c b/net/devlink/dpipe.c
new file mode 100644
index 0000000000000..431227c412e5e
--- /dev/null
+++ b/net/devlink/dpipe.c
@@ -0,0 +1,917 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include "devl_internal.h"
+
+static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = {
+	{
+		.name = "destination mac",
+		.id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC,
+		.bitwidth = 48,
+	},
+};
+
+struct devlink_dpipe_header devlink_dpipe_header_ethernet = {
+	.name = "ethernet",
+	.id = DEVLINK_DPIPE_HEADER_ETHERNET,
+	.fields = devlink_dpipe_fields_ethernet,
+	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ethernet),
+	.global = true,
+};
+EXPORT_SYMBOL_GPL(devlink_dpipe_header_ethernet);
+
+static struct devlink_dpipe_field devlink_dpipe_fields_ipv4[] = {
+	{
+		.name = "destination ip",
+		.id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP,
+		.bitwidth = 32,
+	},
+};
+
+struct devlink_dpipe_header devlink_dpipe_header_ipv4 = {
+	.name = "ipv4",
+	.id = DEVLINK_DPIPE_HEADER_IPV4,
+	.fields = devlink_dpipe_fields_ipv4,
+	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv4),
+	.global = true,
+};
+EXPORT_SYMBOL_GPL(devlink_dpipe_header_ipv4);
+
+static struct devlink_dpipe_field devlink_dpipe_fields_ipv6[] = {
+	{
+		.name = "destination ip",
+		.id = DEVLINK_DPIPE_FIELD_IPV6_DST_IP,
+		.bitwidth = 128,
+	},
+};
+
+struct devlink_dpipe_header devlink_dpipe_header_ipv6 = {
+	.name = "ipv6",
+	.id = DEVLINK_DPIPE_HEADER_IPV6,
+	.fields = devlink_dpipe_fields_ipv6,
+	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv6),
+	.global = true,
+};
+EXPORT_SYMBOL_GPL(devlink_dpipe_header_ipv6);
+
+int devlink_dpipe_match_put(struct sk_buff *skb,
+			    struct devlink_dpipe_match *match)
+{
+	struct devlink_dpipe_header *header = match->header;
+	struct devlink_dpipe_field *field = &header->fields[match->field_id];
+	struct nlattr *match_attr;
+
+	match_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_MATCH);
+	if (!match_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, match_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, match_attr);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_match_put);
+
+static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table,
+				     struct sk_buff *skb)
+{
+	struct nlattr *matches_attr;
+
+	matches_attr = nla_nest_start_noflag(skb,
+					     DEVLINK_ATTR_DPIPE_TABLE_MATCHES);
+	if (!matches_attr)
+		return -EMSGSIZE;
+
+	if (table->table_ops->matches_dump(table->priv, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, matches_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, matches_attr);
+	return -EMSGSIZE;
+}
+
+int devlink_dpipe_action_put(struct sk_buff *skb,
+			     struct devlink_dpipe_action *action)
+{
+	struct devlink_dpipe_header *header = action->header;
+	struct devlink_dpipe_field *field = &header->fields[action->field_id];
+	struct nlattr *action_attr;
+
+	action_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ACTION);
+	if (!action_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, action_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, action_attr);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_action_put);
+
+static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table,
+				     struct sk_buff *skb)
+{
+	struct nlattr *actions_attr;
+
+	actions_attr = nla_nest_start_noflag(skb,
+					     DEVLINK_ATTR_DPIPE_TABLE_ACTIONS);
+	if (!actions_attr)
+		return -EMSGSIZE;
+
+	if (table->table_ops->actions_dump(table->priv, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, actions_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, actions_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_table_put(struct sk_buff *skb,
+				   struct devlink_dpipe_table *table)
+{
+	struct nlattr *table_attr;
+	u64 table_size;
+
+	table_size = table->table_ops->size_get(table->priv);
+	table_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLE);
+	if (!table_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) ||
+	    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table_size,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,
+		       table->counters_enabled))
+		goto nla_put_failure;
+
+	if (table->resource_valid) {
+		if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID,
+				      table->resource_id, DEVLINK_ATTR_PAD) ||
+		    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS,
+				      table->resource_units, DEVLINK_ATTR_PAD))
+			goto nla_put_failure;
+	}
+	if (devlink_dpipe_matches_put(table, skb))
+		goto nla_put_failure;
+
+	if (devlink_dpipe_actions_put(table, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, table_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, table_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb,
+					    struct genl_info *info)
+{
+	int err;
+
+	if (*pskb) {
+		err = genlmsg_reply(*pskb, info);
+		if (err)
+			return err;
+	}
+	*pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!*pskb)
+		return -ENOMEM;
+	return 0;
+}
+
+static int devlink_dpipe_tables_fill(struct genl_info *info,
+				     enum devlink_command cmd, int flags,
+				     struct list_head *dpipe_tables,
+				     const char *table_name)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_dpipe_table *table;
+	struct nlattr *tables_attr;
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	bool incomplete;
+	void *hdr;
+	int i;
+	int err;
+
+	table = list_first_entry(dpipe_tables,
+				 struct devlink_dpipe_table, list);
+start_again:
+	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+			  &devlink_nl_family, NLM_F_MULTI, cmd);
+	if (!hdr) {
+		nlmsg_free(skb);
+		return -EMSGSIZE;
+	}
+
+	if (devlink_nl_put_handle(skb, devlink))
+		goto nla_put_failure;
+	tables_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLES);
+	if (!tables_attr)
+		goto nla_put_failure;
+
+	i = 0;
+	incomplete = false;
+	list_for_each_entry_from(table, dpipe_tables, list) {
+		if (!table_name) {
+			err = devlink_dpipe_table_put(skb, table);
+			if (err) {
+				if (!i)
+					goto err_table_put;
+				incomplete = true;
+				break;
+			}
+		} else {
+			if (!strcmp(table->name, table_name)) {
+				err = devlink_dpipe_table_put(skb, table);
+				if (err)
+					break;
+			}
+		}
+		i++;
+	}
+
+	nla_nest_end(skb, tables_attr);
+	genlmsg_end(skb, hdr);
+	if (incomplete)
+		goto start_again;
+
+send_done:
+	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		if (err)
+			return err;
+		goto send_done;
+	}
+
+	return genlmsg_reply(skb, info);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_table_put:
+	nlmsg_free(skb);
+	return err;
+}
+
+int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const char *table_name =  NULL;
+
+	if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME])
+		table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+
+	return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0,
+					 &devlink->dpipe_table_list,
+					 table_name);
+}
+
+static int devlink_dpipe_value_put(struct sk_buff *skb,
+				   struct devlink_dpipe_value *value)
+{
+	if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE,
+		    value->value_size, value->value))
+		return -EMSGSIZE;
+	if (value->mask)
+		if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK,
+			    value->value_size, value->mask))
+			return -EMSGSIZE;
+	if (value->mapping_valid)
+		if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING,
+				value->mapping_value))
+			return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_action_value_put(struct sk_buff *skb,
+					  struct devlink_dpipe_value *value)
+{
+	if (!value->action)
+		return -EINVAL;
+	if (devlink_dpipe_action_put(skb, value->action))
+		return -EMSGSIZE;
+	if (devlink_dpipe_value_put(skb, value))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_action_values_put(struct sk_buff *skb,
+					   struct devlink_dpipe_value *values,
+					   unsigned int values_count)
+{
+	struct nlattr *action_attr;
+	int i;
+	int err;
+
+	for (i = 0; i < values_count; i++) {
+		action_attr = nla_nest_start_noflag(skb,
+						    DEVLINK_ATTR_DPIPE_ACTION_VALUE);
+		if (!action_attr)
+			return -EMSGSIZE;
+		err = devlink_dpipe_action_value_put(skb, &values[i]);
+		if (err)
+			goto err_action_value_put;
+		nla_nest_end(skb, action_attr);
+	}
+	return 0;
+
+err_action_value_put:
+	nla_nest_cancel(skb, action_attr);
+	return err;
+}
+
+static int devlink_dpipe_match_value_put(struct sk_buff *skb,
+					 struct devlink_dpipe_value *value)
+{
+	if (!value->match)
+		return -EINVAL;
+	if (devlink_dpipe_match_put(skb, value->match))
+		return -EMSGSIZE;
+	if (devlink_dpipe_value_put(skb, value))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_match_values_put(struct sk_buff *skb,
+					  struct devlink_dpipe_value *values,
+					  unsigned int values_count)
+{
+	struct nlattr *match_attr;
+	int i;
+	int err;
+
+	for (i = 0; i < values_count; i++) {
+		match_attr = nla_nest_start_noflag(skb,
+						   DEVLINK_ATTR_DPIPE_MATCH_VALUE);
+		if (!match_attr)
+			return -EMSGSIZE;
+		err = devlink_dpipe_match_value_put(skb, &values[i]);
+		if (err)
+			goto err_match_value_put;
+		nla_nest_end(skb, match_attr);
+	}
+	return 0;
+
+err_match_value_put:
+	nla_nest_cancel(skb, match_attr);
+	return err;
+}
+
+static int devlink_dpipe_entry_put(struct sk_buff *skb,
+				   struct devlink_dpipe_entry *entry)
+{
+	struct nlattr *entry_attr, *matches_attr, *actions_attr;
+	int err;
+
+	entry_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ENTRY);
+	if (!entry_attr)
+		return  -EMSGSIZE;
+
+	if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (entry->counter_valid)
+		if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER,
+				      entry->counter, DEVLINK_ATTR_PAD))
+			goto nla_put_failure;
+
+	matches_attr = nla_nest_start_noflag(skb,
+					     DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES);
+	if (!matches_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_match_values_put(skb, entry->match_values,
+					     entry->match_values_count);
+	if (err) {
+		nla_nest_cancel(skb, matches_attr);
+		goto err_match_values_put;
+	}
+	nla_nest_end(skb, matches_attr);
+
+	actions_attr = nla_nest_start_noflag(skb,
+					     DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES);
+	if (!actions_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_action_values_put(skb, entry->action_values,
+					      entry->action_values_count);
+	if (err) {
+		nla_nest_cancel(skb, actions_attr);
+		goto err_action_values_put;
+	}
+	nla_nest_end(skb, actions_attr);
+
+	nla_nest_end(skb, entry_attr);
+	return 0;
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_match_values_put:
+err_action_values_put:
+	nla_nest_cancel(skb, entry_attr);
+	return err;
+}
+
+static struct devlink_dpipe_table *
+devlink_dpipe_table_find(struct list_head *dpipe_tables,
+			 const char *table_name, struct devlink *devlink)
+{
+	struct devlink_dpipe_table *table;
+
+	list_for_each_entry_rcu(table, dpipe_tables, list,
+				lockdep_is_held(&devlink->lock)) {
+		if (!strcmp(table->name, table_name))
+			return table;
+	}
+	return NULL;
+}
+
+int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	struct devlink *devlink;
+	int err;
+
+	err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb,
+					       dump_ctx->info);
+	if (err)
+		return err;
+
+	dump_ctx->hdr = genlmsg_put(dump_ctx->skb,
+				    dump_ctx->info->snd_portid,
+				    dump_ctx->info->snd_seq,
+				    &devlink_nl_family, NLM_F_MULTI,
+				    dump_ctx->cmd);
+	if (!dump_ctx->hdr)
+		goto nla_put_failure;
+
+	devlink = dump_ctx->info->user_ptr[0];
+	if (devlink_nl_put_handle(dump_ctx->skb, devlink))
+		goto nla_put_failure;
+	dump_ctx->nest = nla_nest_start_noflag(dump_ctx->skb,
+					       DEVLINK_ATTR_DPIPE_ENTRIES);
+	if (!dump_ctx->nest)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	nlmsg_free(dump_ctx->skb);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare);
+
+int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+				   struct devlink_dpipe_entry *entry)
+{
+	return devlink_dpipe_entry_put(dump_ctx->skb, entry);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append);
+
+int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	nla_nest_end(dump_ctx->skb, dump_ctx->nest);
+	genlmsg_end(dump_ctx->skb, dump_ctx->hdr);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close);
+
+void devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry)
+
+{
+	unsigned int value_count, value_index;
+	struct devlink_dpipe_value *value;
+
+	value = entry->action_values;
+	value_count = entry->action_values_count;
+	for (value_index = 0; value_index < value_count; value_index++) {
+		kfree(value[value_index].value);
+		kfree(value[value_index].mask);
+	}
+
+	value = entry->match_values;
+	value_count = entry->match_values_count;
+	for (value_index = 0; value_index < value_count; value_index++) {
+		kfree(value[value_index].value);
+		kfree(value[value_index].mask);
+	}
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_clear);
+
+static int devlink_dpipe_entries_fill(struct genl_info *info,
+				      enum devlink_command cmd, int flags,
+				      struct devlink_dpipe_table *table)
+{
+	struct devlink_dpipe_dump_ctx dump_ctx;
+	struct nlmsghdr *nlh;
+	int err;
+
+	dump_ctx.skb = NULL;
+	dump_ctx.cmd = cmd;
+	dump_ctx.info = info;
+
+	err = table->table_ops->entries_dump(table->priv,
+					     table->counters_enabled,
+					     &dump_ctx);
+	if (err)
+		return err;
+
+send_done:
+	nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info);
+		if (err)
+			return err;
+		goto send_done;
+	}
+	return genlmsg_reply(dump_ctx.skb, info);
+}
+
+int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_dpipe_table *table;
+	const char *table_name;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_NAME))
+		return -EINVAL;
+
+	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name, devlink);
+	if (!table)
+		return -EINVAL;
+
+	if (!table->table_ops->entries_dump)
+		return -EINVAL;
+
+	return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET,
+					  0, table);
+}
+
+static int devlink_dpipe_fields_put(struct sk_buff *skb,
+				    const struct devlink_dpipe_header *header)
+{
+	struct devlink_dpipe_field *field;
+	struct nlattr *field_attr;
+	int i;
+
+	for (i = 0; i < header->fields_count; i++) {
+		field = &header->fields[i];
+		field_attr = nla_nest_start_noflag(skb,
+						   DEVLINK_ATTR_DPIPE_FIELD);
+		if (!field_attr)
+			return -EMSGSIZE;
+		if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type))
+			goto nla_put_failure;
+		nla_nest_end(skb, field_attr);
+	}
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, field_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_header_put(struct sk_buff *skb,
+				    struct devlink_dpipe_header *header)
+{
+	struct nlattr *fields_attr, *header_attr;
+	int err;
+
+	header_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADER);
+	if (!header_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	fields_attr = nla_nest_start_noflag(skb,
+					    DEVLINK_ATTR_DPIPE_HEADER_FIELDS);
+	if (!fields_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_fields_put(skb, header);
+	if (err) {
+		nla_nest_cancel(skb, fields_attr);
+		goto nla_put_failure;
+	}
+	nla_nest_end(skb, fields_attr);
+	nla_nest_end(skb, header_attr);
+	return 0;
+
+nla_put_failure:
+	err = -EMSGSIZE;
+	nla_nest_cancel(skb, header_attr);
+	return err;
+}
+
+static int devlink_dpipe_headers_fill(struct genl_info *info,
+				      enum devlink_command cmd, int flags,
+				      struct devlink_dpipe_headers *
+				      dpipe_headers)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct nlattr *headers_attr;
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	void *hdr;
+	int i, j;
+	int err;
+
+	i = 0;
+start_again:
+	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+			  &devlink_nl_family, NLM_F_MULTI, cmd);
+	if (!hdr) {
+		nlmsg_free(skb);
+		return -EMSGSIZE;
+	}
+
+	if (devlink_nl_put_handle(skb, devlink))
+		goto nla_put_failure;
+	headers_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADERS);
+	if (!headers_attr)
+		goto nla_put_failure;
+
+	j = 0;
+	for (; i < dpipe_headers->headers_count; i++) {
+		err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]);
+		if (err) {
+			if (!j)
+				goto err_table_put;
+			break;
+		}
+		j++;
+	}
+	nla_nest_end(skb, headers_attr);
+	genlmsg_end(skb, hdr);
+	if (i != dpipe_headers->headers_count)
+		goto start_again;
+
+send_done:
+	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		if (err)
+			return err;
+		goto send_done;
+	}
+	return genlmsg_reply(skb, info);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_table_put:
+	nlmsg_free(skb);
+	return err;
+}
+
+int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+
+	if (!devlink->dpipe_headers)
+		return -EOPNOTSUPP;
+	return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET,
+					  0, devlink->dpipe_headers);
+}
+
+static int devlink_dpipe_table_counters_set(struct devlink *devlink,
+					    const char *table_name,
+					    bool enable)
+{
+	struct devlink_dpipe_table *table;
+
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name, devlink);
+	if (!table)
+		return -EINVAL;
+
+	if (table->counter_control_extern)
+		return -EOPNOTSUPP;
+
+	if (!(table->counters_enabled ^ enable))
+		return 0;
+
+	table->counters_enabled = enable;
+	if (table->table_ops->counters_set_update)
+		table->table_ops->counters_set_update(table->priv, enable);
+	return 0;
+}
+
+int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const char *table_name;
+	bool counters_enable;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_NAME) ||
+	    GENL_REQ_ATTR_CHECK(info,
+				DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED))
+		return -EINVAL;
+
+	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+	counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]);
+
+	return devlink_dpipe_table_counters_set(devlink, table_name,
+						counters_enable);
+}
+
+/**
+ * devl_dpipe_headers_register - register dpipe headers
+ *
+ * @devlink: devlink
+ * @dpipe_headers: dpipe header array
+ *
+ * Register the headers supported by hardware.
+ */
+void devl_dpipe_headers_register(struct devlink *devlink,
+				 struct devlink_dpipe_headers *dpipe_headers)
+{
+	lockdep_assert_held(&devlink->lock);
+
+	devlink->dpipe_headers = dpipe_headers;
+}
+EXPORT_SYMBOL_GPL(devl_dpipe_headers_register);
+
+/**
+ * devl_dpipe_headers_unregister - unregister dpipe headers
+ *
+ * @devlink: devlink
+ *
+ * Unregister the headers supported by hardware.
+ */
+void devl_dpipe_headers_unregister(struct devlink *devlink)
+{
+	lockdep_assert_held(&devlink->lock);
+
+	devlink->dpipe_headers = NULL;
+}
+EXPORT_SYMBOL_GPL(devl_dpipe_headers_unregister);
+
+/**
+ *	devlink_dpipe_table_counter_enabled - check if counter allocation
+ *					      required
+ *	@devlink: devlink
+ *	@table_name: tables name
+ *
+ *	Used by driver to check if counter allocation is required.
+ *	After counter allocation is turned on the table entries
+ *	are updated to include counter statistics.
+ *
+ *	After that point on the driver must respect the counter
+ *	state so that each entry added to the table is added
+ *	with a counter.
+ */
+bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+					 const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+	bool enabled;
+
+	rcu_read_lock();
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name, devlink);
+	enabled = false;
+	if (table)
+		enabled = table->counters_enabled;
+	rcu_read_unlock();
+	return enabled;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled);
+
+/**
+ * devl_dpipe_table_register - register dpipe table
+ *
+ * @devlink: devlink
+ * @table_name: table name
+ * @table_ops: table ops
+ * @priv: priv
+ * @counter_control_extern: external control for counters
+ */
+int devl_dpipe_table_register(struct devlink *devlink,
+			      const char *table_name,
+			      struct devlink_dpipe_table_ops *table_ops,
+			      void *priv, bool counter_control_extern)
+{
+	struct devlink_dpipe_table *table;
+
+	lockdep_assert_held(&devlink->lock);
+
+	if (WARN_ON(!table_ops->size_get))
+		return -EINVAL;
+
+	if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name,
+				     devlink))
+		return -EEXIST;
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	table->name = table_name;
+	table->table_ops = table_ops;
+	table->priv = priv;
+	table->counter_control_extern = counter_control_extern;
+
+	list_add_tail_rcu(&table->list, &devlink->dpipe_table_list);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devl_dpipe_table_register);
+
+/**
+ * devl_dpipe_table_unregister - unregister dpipe table
+ *
+ * @devlink: devlink
+ * @table_name: table name
+ */
+void devl_dpipe_table_unregister(struct devlink *devlink,
+				 const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+
+	lockdep_assert_held(&devlink->lock);
+
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name, devlink);
+	if (!table)
+		return;
+	list_del_rcu(&table->list);
+	kfree_rcu(table, rcu);
+}
+EXPORT_SYMBOL_GPL(devl_dpipe_table_unregister);
+
+/**
+ * devl_dpipe_table_resource_set - set the resource id
+ *
+ * @devlink: devlink
+ * @table_name: table name
+ * @resource_id: resource id
+ * @resource_units: number of resource's units consumed per table's entry
+ */
+int devl_dpipe_table_resource_set(struct devlink *devlink,
+				  const char *table_name, u64 resource_id,
+				  u64 resource_units)
+{
+	struct devlink_dpipe_table *table;
+
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name, devlink);
+	if (!table)
+		return -EINVAL;
+
+	table->resource_id = resource_id;
+	table->resource_units = resource_units;
+	table->resource_valid = true;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devl_dpipe_table_resource_set);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 1bcd4192099e1..f71201e6b5e16 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -62,57 +62,6 @@ struct devlink_resource {
 	void *occ_get_priv;
 };
 
-static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = {
-	{
-		.name = "destination mac",
-		.id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC,
-		.bitwidth = 48,
-	},
-};
-
-struct devlink_dpipe_header devlink_dpipe_header_ethernet = {
-	.name = "ethernet",
-	.id = DEVLINK_DPIPE_HEADER_ETHERNET,
-	.fields = devlink_dpipe_fields_ethernet,
-	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ethernet),
-	.global = true,
-};
-EXPORT_SYMBOL_GPL(devlink_dpipe_header_ethernet);
-
-static struct devlink_dpipe_field devlink_dpipe_fields_ipv4[] = {
-	{
-		.name = "destination ip",
-		.id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP,
-		.bitwidth = 32,
-	},
-};
-
-struct devlink_dpipe_header devlink_dpipe_header_ipv4 = {
-	.name = "ipv4",
-	.id = DEVLINK_DPIPE_HEADER_IPV4,
-	.fields = devlink_dpipe_fields_ipv4,
-	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv4),
-	.global = true,
-};
-EXPORT_SYMBOL_GPL(devlink_dpipe_header_ipv4);
-
-static struct devlink_dpipe_field devlink_dpipe_fields_ipv6[] = {
-	{
-		.name = "destination ip",
-		.id = DEVLINK_DPIPE_FIELD_IPV6_DST_IP,
-		.bitwidth = 128,
-	},
-};
-
-struct devlink_dpipe_header devlink_dpipe_header_ipv6 = {
-	.name = "ipv6",
-	.id = DEVLINK_DPIPE_HEADER_IPV6,
-	.fields = devlink_dpipe_fields_ipv6,
-	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv6),
-	.global = true,
-};
-EXPORT_SYMBOL_GPL(devlink_dpipe_header_ipv6);
-
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
@@ -1141,698 +1090,6 @@ int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
 	return 0;
 }
 
-int devlink_dpipe_match_put(struct sk_buff *skb,
-			    struct devlink_dpipe_match *match)
-{
-	struct devlink_dpipe_header *header = match->header;
-	struct devlink_dpipe_field *field = &header->fields[match->field_id];
-	struct nlattr *match_attr;
-
-	match_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_MATCH);
-	if (!match_attr)
-		return -EMSGSIZE;
-
-	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) ||
-	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) ||
-	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
-	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
-	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
-		goto nla_put_failure;
-
-	nla_nest_end(skb, match_attr);
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(skb, match_attr);
-	return -EMSGSIZE;
-}
-EXPORT_SYMBOL_GPL(devlink_dpipe_match_put);
-
-static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table,
-				     struct sk_buff *skb)
-{
-	struct nlattr *matches_attr;
-
-	matches_attr = nla_nest_start_noflag(skb,
-					     DEVLINK_ATTR_DPIPE_TABLE_MATCHES);
-	if (!matches_attr)
-		return -EMSGSIZE;
-
-	if (table->table_ops->matches_dump(table->priv, skb))
-		goto nla_put_failure;
-
-	nla_nest_end(skb, matches_attr);
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(skb, matches_attr);
-	return -EMSGSIZE;
-}
-
-int devlink_dpipe_action_put(struct sk_buff *skb,
-			     struct devlink_dpipe_action *action)
-{
-	struct devlink_dpipe_header *header = action->header;
-	struct devlink_dpipe_field *field = &header->fields[action->field_id];
-	struct nlattr *action_attr;
-
-	action_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ACTION);
-	if (!action_attr)
-		return -EMSGSIZE;
-
-	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) ||
-	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) ||
-	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
-	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
-	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
-		goto nla_put_failure;
-
-	nla_nest_end(skb, action_attr);
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(skb, action_attr);
-	return -EMSGSIZE;
-}
-EXPORT_SYMBOL_GPL(devlink_dpipe_action_put);
-
-static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table,
-				     struct sk_buff *skb)
-{
-	struct nlattr *actions_attr;
-
-	actions_attr = nla_nest_start_noflag(skb,
-					     DEVLINK_ATTR_DPIPE_TABLE_ACTIONS);
-	if (!actions_attr)
-		return -EMSGSIZE;
-
-	if (table->table_ops->actions_dump(table->priv, skb))
-		goto nla_put_failure;
-
-	nla_nest_end(skb, actions_attr);
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(skb, actions_attr);
-	return -EMSGSIZE;
-}
-
-static int devlink_dpipe_table_put(struct sk_buff *skb,
-				   struct devlink_dpipe_table *table)
-{
-	struct nlattr *table_attr;
-	u64 table_size;
-
-	table_size = table->table_ops->size_get(table->priv);
-	table_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLE);
-	if (!table_attr)
-		return -EMSGSIZE;
-
-	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) ||
-	    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table_size,
-			      DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-	if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,
-		       table->counters_enabled))
-		goto nla_put_failure;
-
-	if (table->resource_valid) {
-		if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID,
-				      table->resource_id, DEVLINK_ATTR_PAD) ||
-		    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS,
-				      table->resource_units, DEVLINK_ATTR_PAD))
-			goto nla_put_failure;
-	}
-	if (devlink_dpipe_matches_put(table, skb))
-		goto nla_put_failure;
-
-	if (devlink_dpipe_actions_put(table, skb))
-		goto nla_put_failure;
-
-	nla_nest_end(skb, table_attr);
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(skb, table_attr);
-	return -EMSGSIZE;
-}
-
-static int devlink_dpipe_tables_fill(struct genl_info *info,
-				     enum devlink_command cmd, int flags,
-				     struct list_head *dpipe_tables,
-				     const char *table_name)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_dpipe_table *table;
-	struct nlattr *tables_attr;
-	struct sk_buff *skb = NULL;
-	struct nlmsghdr *nlh;
-	bool incomplete;
-	void *hdr;
-	int i;
-	int err;
-
-	table = list_first_entry(dpipe_tables,
-				 struct devlink_dpipe_table, list);
-start_again:
-	err = devlink_nl_msg_reply_and_new(&skb, info);
-	if (err)
-		return err;
-
-	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
-			  &devlink_nl_family, NLM_F_MULTI, cmd);
-	if (!hdr) {
-		nlmsg_free(skb);
-		return -EMSGSIZE;
-	}
-
-	if (devlink_nl_put_handle(skb, devlink))
-		goto nla_put_failure;
-	tables_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLES);
-	if (!tables_attr)
-		goto nla_put_failure;
-
-	i = 0;
-	incomplete = false;
-	list_for_each_entry_from(table, dpipe_tables, list) {
-		if (!table_name) {
-			err = devlink_dpipe_table_put(skb, table);
-			if (err) {
-				if (!i)
-					goto err_table_put;
-				incomplete = true;
-				break;
-			}
-		} else {
-			if (!strcmp(table->name, table_name)) {
-				err = devlink_dpipe_table_put(skb, table);
-				if (err)
-					break;
-			}
-		}
-		i++;
-	}
-
-	nla_nest_end(skb, tables_attr);
-	genlmsg_end(skb, hdr);
-	if (incomplete)
-		goto start_again;
-
-send_done:
-	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
-			NLMSG_DONE, 0, flags | NLM_F_MULTI);
-	if (!nlh) {
-		err = devlink_nl_msg_reply_and_new(&skb, info);
-		if (err)
-			return err;
-		goto send_done;
-	}
-
-	return genlmsg_reply(skb, info);
-
-nla_put_failure:
-	err = -EMSGSIZE;
-err_table_put:
-	nlmsg_free(skb);
-	return err;
-}
-
-static int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb,
-					  struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	const char *table_name =  NULL;
-
-	if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME])
-		table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
-
-	return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0,
-					 &devlink->dpipe_table_list,
-					 table_name);
-}
-
-static int devlink_dpipe_value_put(struct sk_buff *skb,
-				   struct devlink_dpipe_value *value)
-{
-	if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE,
-		    value->value_size, value->value))
-		return -EMSGSIZE;
-	if (value->mask)
-		if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK,
-			    value->value_size, value->mask))
-			return -EMSGSIZE;
-	if (value->mapping_valid)
-		if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING,
-				value->mapping_value))
-			return -EMSGSIZE;
-	return 0;
-}
-
-static int devlink_dpipe_action_value_put(struct sk_buff *skb,
-					  struct devlink_dpipe_value *value)
-{
-	if (!value->action)
-		return -EINVAL;
-	if (devlink_dpipe_action_put(skb, value->action))
-		return -EMSGSIZE;
-	if (devlink_dpipe_value_put(skb, value))
-		return -EMSGSIZE;
-	return 0;
-}
-
-static int devlink_dpipe_action_values_put(struct sk_buff *skb,
-					   struct devlink_dpipe_value *values,
-					   unsigned int values_count)
-{
-	struct nlattr *action_attr;
-	int i;
-	int err;
-
-	for (i = 0; i < values_count; i++) {
-		action_attr = nla_nest_start_noflag(skb,
-						    DEVLINK_ATTR_DPIPE_ACTION_VALUE);
-		if (!action_attr)
-			return -EMSGSIZE;
-		err = devlink_dpipe_action_value_put(skb, &values[i]);
-		if (err)
-			goto err_action_value_put;
-		nla_nest_end(skb, action_attr);
-	}
-	return 0;
-
-err_action_value_put:
-	nla_nest_cancel(skb, action_attr);
-	return err;
-}
-
-static int devlink_dpipe_match_value_put(struct sk_buff *skb,
-					 struct devlink_dpipe_value *value)
-{
-	if (!value->match)
-		return -EINVAL;
-	if (devlink_dpipe_match_put(skb, value->match))
-		return -EMSGSIZE;
-	if (devlink_dpipe_value_put(skb, value))
-		return -EMSGSIZE;
-	return 0;
-}
-
-static int devlink_dpipe_match_values_put(struct sk_buff *skb,
-					  struct devlink_dpipe_value *values,
-					  unsigned int values_count)
-{
-	struct nlattr *match_attr;
-	int i;
-	int err;
-
-	for (i = 0; i < values_count; i++) {
-		match_attr = nla_nest_start_noflag(skb,
-						   DEVLINK_ATTR_DPIPE_MATCH_VALUE);
-		if (!match_attr)
-			return -EMSGSIZE;
-		err = devlink_dpipe_match_value_put(skb, &values[i]);
-		if (err)
-			goto err_match_value_put;
-		nla_nest_end(skb, match_attr);
-	}
-	return 0;
-
-err_match_value_put:
-	nla_nest_cancel(skb, match_attr);
-	return err;
-}
-
-static int devlink_dpipe_entry_put(struct sk_buff *skb,
-				   struct devlink_dpipe_entry *entry)
-{
-	struct nlattr *entry_attr, *matches_attr, *actions_attr;
-	int err;
-
-	entry_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ENTRY);
-	if (!entry_attr)
-		return  -EMSGSIZE;
-
-	if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index,
-			      DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-	if (entry->counter_valid)
-		if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER,
-				      entry->counter, DEVLINK_ATTR_PAD))
-			goto nla_put_failure;
-
-	matches_attr = nla_nest_start_noflag(skb,
-					     DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES);
-	if (!matches_attr)
-		goto nla_put_failure;
-
-	err = devlink_dpipe_match_values_put(skb, entry->match_values,
-					     entry->match_values_count);
-	if (err) {
-		nla_nest_cancel(skb, matches_attr);
-		goto err_match_values_put;
-	}
-	nla_nest_end(skb, matches_attr);
-
-	actions_attr = nla_nest_start_noflag(skb,
-					     DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES);
-	if (!actions_attr)
-		goto nla_put_failure;
-
-	err = devlink_dpipe_action_values_put(skb, entry->action_values,
-					      entry->action_values_count);
-	if (err) {
-		nla_nest_cancel(skb, actions_attr);
-		goto err_action_values_put;
-	}
-	nla_nest_end(skb, actions_attr);
-
-	nla_nest_end(skb, entry_attr);
-	return 0;
-
-nla_put_failure:
-	err = -EMSGSIZE;
-err_match_values_put:
-err_action_values_put:
-	nla_nest_cancel(skb, entry_attr);
-	return err;
-}
-
-static struct devlink_dpipe_table *
-devlink_dpipe_table_find(struct list_head *dpipe_tables,
-			 const char *table_name, struct devlink *devlink)
-{
-	struct devlink_dpipe_table *table;
-	list_for_each_entry_rcu(table, dpipe_tables, list,
-				lockdep_is_held(&devlink->lock)) {
-		if (!strcmp(table->name, table_name))
-			return table;
-	}
-	return NULL;
-}
-
-int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
-{
-	struct devlink *devlink;
-	int err;
-
-	err = devlink_nl_msg_reply_and_new(&dump_ctx->skb,
-					   dump_ctx->info);
-	if (err)
-		return err;
-
-	dump_ctx->hdr = genlmsg_put(dump_ctx->skb,
-				    dump_ctx->info->snd_portid,
-				    dump_ctx->info->snd_seq,
-				    &devlink_nl_family, NLM_F_MULTI,
-				    dump_ctx->cmd);
-	if (!dump_ctx->hdr)
-		goto nla_put_failure;
-
-	devlink = dump_ctx->info->user_ptr[0];
-	if (devlink_nl_put_handle(dump_ctx->skb, devlink))
-		goto nla_put_failure;
-	dump_ctx->nest = nla_nest_start_noflag(dump_ctx->skb,
-					       DEVLINK_ATTR_DPIPE_ENTRIES);
-	if (!dump_ctx->nest)
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	nlmsg_free(dump_ctx->skb);
-	return -EMSGSIZE;
-}
-EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare);
-
-int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
-				   struct devlink_dpipe_entry *entry)
-{
-	return devlink_dpipe_entry_put(dump_ctx->skb, entry);
-}
-EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append);
-
-int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
-{
-	nla_nest_end(dump_ctx->skb, dump_ctx->nest);
-	genlmsg_end(dump_ctx->skb, dump_ctx->hdr);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close);
-
-void devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry)
-
-{
-	unsigned int value_count, value_index;
-	struct devlink_dpipe_value *value;
-
-	value = entry->action_values;
-	value_count = entry->action_values_count;
-	for (value_index = 0; value_index < value_count; value_index++) {
-		kfree(value[value_index].value);
-		kfree(value[value_index].mask);
-	}
-
-	value = entry->match_values;
-	value_count = entry->match_values_count;
-	for (value_index = 0; value_index < value_count; value_index++) {
-		kfree(value[value_index].value);
-		kfree(value[value_index].mask);
-	}
-}
-EXPORT_SYMBOL_GPL(devlink_dpipe_entry_clear);
-
-static int devlink_dpipe_entries_fill(struct genl_info *info,
-				      enum devlink_command cmd, int flags,
-				      struct devlink_dpipe_table *table)
-{
-	struct devlink_dpipe_dump_ctx dump_ctx;
-	struct nlmsghdr *nlh;
-	int err;
-
-	dump_ctx.skb = NULL;
-	dump_ctx.cmd = cmd;
-	dump_ctx.info = info;
-
-	err = table->table_ops->entries_dump(table->priv,
-					     table->counters_enabled,
-					     &dump_ctx);
-	if (err)
-		return err;
-
-send_done:
-	nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq,
-			NLMSG_DONE, 0, flags | NLM_F_MULTI);
-	if (!nlh) {
-		err = devlink_nl_msg_reply_and_new(&dump_ctx.skb, info);
-		if (err)
-			return err;
-		goto send_done;
-	}
-	return genlmsg_reply(dump_ctx.skb, info);
-}
-
-static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb,
-					    struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_dpipe_table *table;
-	const char *table_name;
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_NAME))
-		return -EINVAL;
-
-	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
-	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
-					 table_name, devlink);
-	if (!table)
-		return -EINVAL;
-
-	if (!table->table_ops->entries_dump)
-		return -EINVAL;
-
-	return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET,
-					  0, table);
-}
-
-static int devlink_dpipe_fields_put(struct sk_buff *skb,
-				    const struct devlink_dpipe_header *header)
-{
-	struct devlink_dpipe_field *field;
-	struct nlattr *field_attr;
-	int i;
-
-	for (i = 0; i < header->fields_count; i++) {
-		field = &header->fields[i];
-		field_attr = nla_nest_start_noflag(skb,
-						   DEVLINK_ATTR_DPIPE_FIELD);
-		if (!field_attr)
-			return -EMSGSIZE;
-		if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) ||
-		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
-		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) ||
-		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type))
-			goto nla_put_failure;
-		nla_nest_end(skb, field_attr);
-	}
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(skb, field_attr);
-	return -EMSGSIZE;
-}
-
-static int devlink_dpipe_header_put(struct sk_buff *skb,
-				    struct devlink_dpipe_header *header)
-{
-	struct nlattr *fields_attr, *header_attr;
-	int err;
-
-	header_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADER);
-	if (!header_attr)
-		return -EMSGSIZE;
-
-	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) ||
-	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
-	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
-		goto nla_put_failure;
-
-	fields_attr = nla_nest_start_noflag(skb,
-					    DEVLINK_ATTR_DPIPE_HEADER_FIELDS);
-	if (!fields_attr)
-		goto nla_put_failure;
-
-	err = devlink_dpipe_fields_put(skb, header);
-	if (err) {
-		nla_nest_cancel(skb, fields_attr);
-		goto nla_put_failure;
-	}
-	nla_nest_end(skb, fields_attr);
-	nla_nest_end(skb, header_attr);
-	return 0;
-
-nla_put_failure:
-	err = -EMSGSIZE;
-	nla_nest_cancel(skb, header_attr);
-	return err;
-}
-
-static int devlink_dpipe_headers_fill(struct genl_info *info,
-				      enum devlink_command cmd, int flags,
-				      struct devlink_dpipe_headers *
-				      dpipe_headers)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct nlattr *headers_attr;
-	struct sk_buff *skb = NULL;
-	struct nlmsghdr *nlh;
-	void *hdr;
-	int i, j;
-	int err;
-
-	i = 0;
-start_again:
-	err = devlink_nl_msg_reply_and_new(&skb, info);
-	if (err)
-		return err;
-
-	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
-			  &devlink_nl_family, NLM_F_MULTI, cmd);
-	if (!hdr) {
-		nlmsg_free(skb);
-		return -EMSGSIZE;
-	}
-
-	if (devlink_nl_put_handle(skb, devlink))
-		goto nla_put_failure;
-	headers_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADERS);
-	if (!headers_attr)
-		goto nla_put_failure;
-
-	j = 0;
-	for (; i < dpipe_headers->headers_count; i++) {
-		err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]);
-		if (err) {
-			if (!j)
-				goto err_table_put;
-			break;
-		}
-		j++;
-	}
-	nla_nest_end(skb, headers_attr);
-	genlmsg_end(skb, hdr);
-	if (i != dpipe_headers->headers_count)
-		goto start_again;
-
-send_done:
-	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
-			NLMSG_DONE, 0, flags | NLM_F_MULTI);
-	if (!nlh) {
-		err = devlink_nl_msg_reply_and_new(&skb, info);
-		if (err)
-			return err;
-		goto send_done;
-	}
-	return genlmsg_reply(skb, info);
-
-nla_put_failure:
-	err = -EMSGSIZE;
-err_table_put:
-	nlmsg_free(skb);
-	return err;
-}
-
-static int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb,
-					    struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-
-	if (!devlink->dpipe_headers)
-		return -EOPNOTSUPP;
-	return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET,
-					  0, devlink->dpipe_headers);
-}
-
-static int devlink_dpipe_table_counters_set(struct devlink *devlink,
-					    const char *table_name,
-					    bool enable)
-{
-	struct devlink_dpipe_table *table;
-
-	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
-					 table_name, devlink);
-	if (!table)
-		return -EINVAL;
-
-	if (table->counter_control_extern)
-		return -EOPNOTSUPP;
-
-	if (!(table->counters_enabled ^ enable))
-		return 0;
-
-	table->counters_enabled = enable;
-	if (table->table_ops->counters_set_update)
-		table->table_ops->counters_set_update(table->priv, enable);
-	return 0;
-}
-
-static int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb,
-						   struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	const char *table_name;
-	bool counters_enable;
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_NAME) ||
-	    GENL_REQ_ATTR_CHECK(info,
-				DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED))
-		return -EINVAL;
-
-	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
-	counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]);
-
-	return devlink_dpipe_table_counters_set(devlink, table_name,
-						counters_enable);
-}
-
 static struct devlink_resource *
 devlink_resource_find(struct devlink *devlink,
 		      struct devlink_resource *resource, u64 resource_id)
@@ -5272,131 +4529,6 @@ void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard,
 }
 EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set);
 
-/**
- * devl_dpipe_headers_register - register dpipe headers
- *
- * @devlink: devlink
- * @dpipe_headers: dpipe header array
- *
- * Register the headers supported by hardware.
- */
-void devl_dpipe_headers_register(struct devlink *devlink,
-				 struct devlink_dpipe_headers *dpipe_headers)
-{
-	lockdep_assert_held(&devlink->lock);
-
-	devlink->dpipe_headers = dpipe_headers;
-}
-EXPORT_SYMBOL_GPL(devl_dpipe_headers_register);
-
-/**
- * devl_dpipe_headers_unregister - unregister dpipe headers
- *
- * @devlink: devlink
- *
- * Unregister the headers supported by hardware.
- */
-void devl_dpipe_headers_unregister(struct devlink *devlink)
-{
-	lockdep_assert_held(&devlink->lock);
-
-	devlink->dpipe_headers = NULL;
-}
-EXPORT_SYMBOL_GPL(devl_dpipe_headers_unregister);
-
-/**
- *	devlink_dpipe_table_counter_enabled - check if counter allocation
- *					      required
- *	@devlink: devlink
- *	@table_name: tables name
- *
- *	Used by driver to check if counter allocation is required.
- *	After counter allocation is turned on the table entries
- *	are updated to include counter statistics.
- *
- *	After that point on the driver must respect the counter
- *	state so that each entry added to the table is added
- *	with a counter.
- */
-bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
-					 const char *table_name)
-{
-	struct devlink_dpipe_table *table;
-	bool enabled;
-
-	rcu_read_lock();
-	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
-					 table_name, devlink);
-	enabled = false;
-	if (table)
-		enabled = table->counters_enabled;
-	rcu_read_unlock();
-	return enabled;
-}
-EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled);
-
-/**
- * devl_dpipe_table_register - register dpipe table
- *
- * @devlink: devlink
- * @table_name: table name
- * @table_ops: table ops
- * @priv: priv
- * @counter_control_extern: external control for counters
- */
-int devl_dpipe_table_register(struct devlink *devlink,
-			      const char *table_name,
-			      struct devlink_dpipe_table_ops *table_ops,
-			      void *priv, bool counter_control_extern)
-{
-	struct devlink_dpipe_table *table;
-
-	lockdep_assert_held(&devlink->lock);
-
-	if (WARN_ON(!table_ops->size_get))
-		return -EINVAL;
-
-	if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name,
-				     devlink))
-		return -EEXIST;
-
-	table = kzalloc(sizeof(*table), GFP_KERNEL);
-	if (!table)
-		return -ENOMEM;
-
-	table->name = table_name;
-	table->table_ops = table_ops;
-	table->priv = priv;
-	table->counter_control_extern = counter_control_extern;
-
-	list_add_tail_rcu(&table->list, &devlink->dpipe_table_list);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devl_dpipe_table_register);
-
-/**
- * devl_dpipe_table_unregister - unregister dpipe table
- *
- * @devlink: devlink
- * @table_name: table name
- */
-void devl_dpipe_table_unregister(struct devlink *devlink,
-				 const char *table_name)
-{
-	struct devlink_dpipe_table *table;
-
-	lockdep_assert_held(&devlink->lock);
-
-	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
-					 table_name, devlink);
-	if (!table)
-		return;
-	list_del_rcu(&table->list);
-	kfree_rcu(table, rcu);
-}
-EXPORT_SYMBOL_GPL(devl_dpipe_table_unregister);
-
 /**
  * devl_resource_register - devlink resource register
  *
@@ -5569,32 +4701,6 @@ int devl_resource_size_get(struct devlink *devlink,
 }
 EXPORT_SYMBOL_GPL(devl_resource_size_get);
 
-/**
- * devl_dpipe_table_resource_set - set the resource id
- *
- * @devlink: devlink
- * @table_name: table name
- * @resource_id: resource id
- * @resource_units: number of resource's units consumed per table's entry
- */
-int devl_dpipe_table_resource_set(struct devlink *devlink,
-				  const char *table_name, u64 resource_id,
-				  u64 resource_units)
-{
-	struct devlink_dpipe_table *table;
-
-	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
-					 table_name, devlink);
-	if (!table)
-		return -EINVAL;
-
-	table->resource_id = resource_id;
-	table->resource_units = resource_units;
-	table->resource_valid = true;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devl_dpipe_table_resource_set);
-
 /**
  * devl_resource_occ_get_register - register occupancy getter
  *
-- 
GitLab


From a9f960074ecd9db292744db2491a0cbbd354e24b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:48 +0200
Subject: [PATCH 1793/1806] devlink: push resource related code into separate
 file

Cut out another chunk from leftover.c and put resource related code
into a separate file.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-7-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/Makefile        |   2 +-
 net/devlink/devl_internal.h |   2 +
 net/devlink/leftover.c      | 574 -----------------------------------
 net/devlink/resource.c      | 579 ++++++++++++++++++++++++++++++++++++
 4 files changed, 582 insertions(+), 575 deletions(-)
 create mode 100644 net/devlink/resource.c

diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index 122de1d565d22..8864cd933acbf 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o sb.o dpipe.o \
-	 health.o
+	 resource.o health.o
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 72653e1dae801..e5c0acf7a7583 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -238,6 +238,8 @@ int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb,
 				     struct genl_info *info);
 int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb,
 					    struct genl_info *info);
+int devlink_nl_cmd_resource_set(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_resource_dump(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 					    struct genl_info *info);
 int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index f71201e6b5e16..1c65449f22523 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -33,35 +33,6 @@
 
 #include "devl_internal.h"
 
-/**
- * struct devlink_resource - devlink resource
- * @name: name of the resource
- * @id: id, per devlink instance
- * @size: size of the resource
- * @size_new: updated size of the resource, reload is needed
- * @size_valid: valid in case the total size of the resource is valid
- *              including its children
- * @parent: parent resource
- * @size_params: size parameters
- * @list: parent list
- * @resource_list: list of child resources
- * @occ_get: occupancy getter callback
- * @occ_get_priv: occupancy getter callback priv
- */
-struct devlink_resource {
-	const char *name;
-	u64 id;
-	u64 size;
-	u64 size_new;
-	bool size_valid;
-	struct devlink_resource *parent;
-	struct devlink_resource_size_params size_params;
-	struct list_head list;
-	struct list_head resource_list;
-	devlink_resource_occ_get_t *occ_get;
-	void *occ_get_priv;
-};
-
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
@@ -1090,290 +1061,6 @@ int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
 	return 0;
 }
 
-static struct devlink_resource *
-devlink_resource_find(struct devlink *devlink,
-		      struct devlink_resource *resource, u64 resource_id)
-{
-	struct list_head *resource_list;
-
-	if (resource)
-		resource_list = &resource->resource_list;
-	else
-		resource_list = &devlink->resource_list;
-
-	list_for_each_entry(resource, resource_list, list) {
-		struct devlink_resource *child_resource;
-
-		if (resource->id == resource_id)
-			return resource;
-
-		child_resource = devlink_resource_find(devlink, resource,
-						       resource_id);
-		if (child_resource)
-			return child_resource;
-	}
-	return NULL;
-}
-
-static void
-devlink_resource_validate_children(struct devlink_resource *resource)
-{
-	struct devlink_resource *child_resource;
-	bool size_valid = true;
-	u64 parts_size = 0;
-
-	if (list_empty(&resource->resource_list))
-		goto out;
-
-	list_for_each_entry(child_resource, &resource->resource_list, list)
-		parts_size += child_resource->size_new;
-
-	if (parts_size > resource->size_new)
-		size_valid = false;
-out:
-	resource->size_valid = size_valid;
-}
-
-static int
-devlink_resource_validate_size(struct devlink_resource *resource, u64 size,
-			       struct netlink_ext_ack *extack)
-{
-	u64 reminder;
-	int err = 0;
-
-	if (size > resource->size_params.size_max) {
-		NL_SET_ERR_MSG(extack, "Size larger than maximum");
-		err = -EINVAL;
-	}
-
-	if (size < resource->size_params.size_min) {
-		NL_SET_ERR_MSG(extack, "Size smaller than minimum");
-		err = -EINVAL;
-	}
-
-	div64_u64_rem(size, resource->size_params.size_granularity, &reminder);
-	if (reminder) {
-		NL_SET_ERR_MSG(extack, "Wrong granularity");
-		err = -EINVAL;
-	}
-
-	return err;
-}
-
-static int devlink_nl_cmd_resource_set(struct sk_buff *skb,
-				       struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_resource *resource;
-	u64 resource_id;
-	u64 size;
-	int err;
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_RESOURCE_ID) ||
-	    GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_RESOURCE_SIZE))
-		return -EINVAL;
-	resource_id = nla_get_u64(info->attrs[DEVLINK_ATTR_RESOURCE_ID]);
-
-	resource = devlink_resource_find(devlink, NULL, resource_id);
-	if (!resource)
-		return -EINVAL;
-
-	size = nla_get_u64(info->attrs[DEVLINK_ATTR_RESOURCE_SIZE]);
-	err = devlink_resource_validate_size(resource, size, info->extack);
-	if (err)
-		return err;
-
-	resource->size_new = size;
-	devlink_resource_validate_children(resource);
-	if (resource->parent)
-		devlink_resource_validate_children(resource->parent);
-	return 0;
-}
-
-static int
-devlink_resource_size_params_put(struct devlink_resource *resource,
-				 struct sk_buff *skb)
-{
-	struct devlink_resource_size_params *size_params;
-
-	size_params = &resource->size_params;
-	if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN,
-			      size_params->size_granularity, DEVLINK_ATTR_PAD) ||
-	    nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX,
-			      size_params->size_max, DEVLINK_ATTR_PAD) ||
-	    nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN,
-			      size_params->size_min, DEVLINK_ATTR_PAD) ||
-	    nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit))
-		return -EMSGSIZE;
-	return 0;
-}
-
-static int devlink_resource_occ_put(struct devlink_resource *resource,
-				    struct sk_buff *skb)
-{
-	if (!resource->occ_get)
-		return 0;
-	return nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC,
-				 resource->occ_get(resource->occ_get_priv),
-				 DEVLINK_ATTR_PAD);
-}
-
-static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb,
-				struct devlink_resource *resource)
-{
-	struct devlink_resource *child_resource;
-	struct nlattr *child_resource_attr;
-	struct nlattr *resource_attr;
-
-	resource_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_RESOURCE);
-	if (!resource_attr)
-		return -EMSGSIZE;
-
-	if (nla_put_string(skb, DEVLINK_ATTR_RESOURCE_NAME, resource->name) ||
-	    nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE, resource->size,
-			      DEVLINK_ATTR_PAD) ||
-	    nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_ID, resource->id,
-			      DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-	if (resource->size != resource->size_new &&
-	    nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_NEW,
-			      resource->size_new, DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-	if (devlink_resource_occ_put(resource, skb))
-		goto nla_put_failure;
-	if (devlink_resource_size_params_put(resource, skb))
-		goto nla_put_failure;
-	if (list_empty(&resource->resource_list))
-		goto out;
-
-	if (nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_SIZE_VALID,
-		       resource->size_valid))
-		goto nla_put_failure;
-
-	child_resource_attr = nla_nest_start_noflag(skb,
-						    DEVLINK_ATTR_RESOURCE_LIST);
-	if (!child_resource_attr)
-		goto nla_put_failure;
-
-	list_for_each_entry(child_resource, &resource->resource_list, list) {
-		if (devlink_resource_put(devlink, skb, child_resource))
-			goto resource_put_failure;
-	}
-
-	nla_nest_end(skb, child_resource_attr);
-out:
-	nla_nest_end(skb, resource_attr);
-	return 0;
-
-resource_put_failure:
-	nla_nest_cancel(skb, child_resource_attr);
-nla_put_failure:
-	nla_nest_cancel(skb, resource_attr);
-	return -EMSGSIZE;
-}
-
-static int devlink_resource_fill(struct genl_info *info,
-				 enum devlink_command cmd, int flags)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_resource *resource;
-	struct nlattr *resources_attr;
-	struct sk_buff *skb = NULL;
-	struct nlmsghdr *nlh;
-	bool incomplete;
-	void *hdr;
-	int i;
-	int err;
-
-	resource = list_first_entry(&devlink->resource_list,
-				    struct devlink_resource, list);
-start_again:
-	err = devlink_nl_msg_reply_and_new(&skb, info);
-	if (err)
-		return err;
-
-	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
-			  &devlink_nl_family, NLM_F_MULTI, cmd);
-	if (!hdr) {
-		nlmsg_free(skb);
-		return -EMSGSIZE;
-	}
-
-	if (devlink_nl_put_handle(skb, devlink))
-		goto nla_put_failure;
-
-	resources_attr = nla_nest_start_noflag(skb,
-					       DEVLINK_ATTR_RESOURCE_LIST);
-	if (!resources_attr)
-		goto nla_put_failure;
-
-	incomplete = false;
-	i = 0;
-	list_for_each_entry_from(resource, &devlink->resource_list, list) {
-		err = devlink_resource_put(devlink, skb, resource);
-		if (err) {
-			if (!i)
-				goto err_resource_put;
-			incomplete = true;
-			break;
-		}
-		i++;
-	}
-	nla_nest_end(skb, resources_attr);
-	genlmsg_end(skb, hdr);
-	if (incomplete)
-		goto start_again;
-send_done:
-	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
-			NLMSG_DONE, 0, flags | NLM_F_MULTI);
-	if (!nlh) {
-		err = devlink_nl_msg_reply_and_new(&skb, info);
-		if (err)
-			return err;
-		goto send_done;
-	}
-	return genlmsg_reply(skb, info);
-
-nla_put_failure:
-	err = -EMSGSIZE;
-err_resource_put:
-	nlmsg_free(skb);
-	return err;
-}
-
-static int devlink_nl_cmd_resource_dump(struct sk_buff *skb,
-					struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-
-	if (list_empty(&devlink->resource_list))
-		return -EOPNOTSUPP;
-
-	return devlink_resource_fill(info, DEVLINK_CMD_RESOURCE_DUMP, 0);
-}
-
-int devlink_resources_validate(struct devlink *devlink,
-			       struct devlink_resource *resource,
-			       struct genl_info *info)
-{
-	struct list_head *resource_list;
-	int err = 0;
-
-	if (resource)
-		resource_list = &resource->resource_list;
-	else
-		resource_list = &devlink->resource_list;
-
-	list_for_each_entry(resource, resource_list, list) {
-		if (!resource->size_valid)
-			return -EINVAL;
-		err = devlink_resources_validate(devlink, resource, info);
-		if (err)
-			return err;
-	}
-	return err;
-}
-
 static const struct devlink_param devlink_param_generic[] = {
 	{
 		.id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
@@ -4529,267 +4216,6 @@ void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard,
 }
 EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set);
 
-/**
- * devl_resource_register - devlink resource register
- *
- * @devlink: devlink
- * @resource_name: resource's name
- * @resource_size: resource's size
- * @resource_id: resource's id
- * @parent_resource_id: resource's parent id
- * @size_params: size parameters
- *
- * Generic resources should reuse the same names across drivers.
- * Please see the generic resources list at:
- * Documentation/networking/devlink/devlink-resource.rst
- */
-int devl_resource_register(struct devlink *devlink,
-			   const char *resource_name,
-			   u64 resource_size,
-			   u64 resource_id,
-			   u64 parent_resource_id,
-			   const struct devlink_resource_size_params *size_params)
-{
-	struct devlink_resource *resource;
-	struct list_head *resource_list;
-	bool top_hierarchy;
-
-	lockdep_assert_held(&devlink->lock);
-
-	top_hierarchy = parent_resource_id == DEVLINK_RESOURCE_ID_PARENT_TOP;
-
-	resource = devlink_resource_find(devlink, NULL, resource_id);
-	if (resource)
-		return -EINVAL;
-
-	resource = kzalloc(sizeof(*resource), GFP_KERNEL);
-	if (!resource)
-		return -ENOMEM;
-
-	if (top_hierarchy) {
-		resource_list = &devlink->resource_list;
-	} else {
-		struct devlink_resource *parent_resource;
-
-		parent_resource = devlink_resource_find(devlink, NULL,
-							parent_resource_id);
-		if (parent_resource) {
-			resource_list = &parent_resource->resource_list;
-			resource->parent = parent_resource;
-		} else {
-			kfree(resource);
-			return -EINVAL;
-		}
-	}
-
-	resource->name = resource_name;
-	resource->size = resource_size;
-	resource->size_new = resource_size;
-	resource->id = resource_id;
-	resource->size_valid = true;
-	memcpy(&resource->size_params, size_params,
-	       sizeof(resource->size_params));
-	INIT_LIST_HEAD(&resource->resource_list);
-	list_add_tail(&resource->list, resource_list);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devl_resource_register);
-
-/**
- *	devlink_resource_register - devlink resource register
- *
- *	@devlink: devlink
- *	@resource_name: resource's name
- *	@resource_size: resource's size
- *	@resource_id: resource's id
- *	@parent_resource_id: resource's parent id
- *	@size_params: size parameters
- *
- *	Generic resources should reuse the same names across drivers.
- *	Please see the generic resources list at:
- *	Documentation/networking/devlink/devlink-resource.rst
- *
- *	Context: Takes and release devlink->lock <mutex>.
- */
-int devlink_resource_register(struct devlink *devlink,
-			      const char *resource_name,
-			      u64 resource_size,
-			      u64 resource_id,
-			      u64 parent_resource_id,
-			      const struct devlink_resource_size_params *size_params)
-{
-	int err;
-
-	devl_lock(devlink);
-	err = devl_resource_register(devlink, resource_name, resource_size,
-				     resource_id, parent_resource_id, size_params);
-	devl_unlock(devlink);
-	return err;
-}
-EXPORT_SYMBOL_GPL(devlink_resource_register);
-
-static void devlink_resource_unregister(struct devlink *devlink,
-					struct devlink_resource *resource)
-{
-	struct devlink_resource *tmp, *child_resource;
-
-	list_for_each_entry_safe(child_resource, tmp, &resource->resource_list,
-				 list) {
-		devlink_resource_unregister(devlink, child_resource);
-		list_del(&child_resource->list);
-		kfree(child_resource);
-	}
-}
-
-/**
- * devl_resources_unregister - free all resources
- *
- * @devlink: devlink
- */
-void devl_resources_unregister(struct devlink *devlink)
-{
-	struct devlink_resource *tmp, *child_resource;
-
-	lockdep_assert_held(&devlink->lock);
-
-	list_for_each_entry_safe(child_resource, tmp, &devlink->resource_list,
-				 list) {
-		devlink_resource_unregister(devlink, child_resource);
-		list_del(&child_resource->list);
-		kfree(child_resource);
-	}
-}
-EXPORT_SYMBOL_GPL(devl_resources_unregister);
-
-/**
- *	devlink_resources_unregister - free all resources
- *
- *	@devlink: devlink
- *
- *	Context: Takes and release devlink->lock <mutex>.
- */
-void devlink_resources_unregister(struct devlink *devlink)
-{
-	devl_lock(devlink);
-	devl_resources_unregister(devlink);
-	devl_unlock(devlink);
-}
-EXPORT_SYMBOL_GPL(devlink_resources_unregister);
-
-/**
- * devl_resource_size_get - get and update size
- *
- * @devlink: devlink
- * @resource_id: the requested resource id
- * @p_resource_size: ptr to update
- */
-int devl_resource_size_get(struct devlink *devlink,
-			   u64 resource_id,
-			   u64 *p_resource_size)
-{
-	struct devlink_resource *resource;
-
-	lockdep_assert_held(&devlink->lock);
-
-	resource = devlink_resource_find(devlink, NULL, resource_id);
-	if (!resource)
-		return -EINVAL;
-	*p_resource_size = resource->size_new;
-	resource->size = resource->size_new;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devl_resource_size_get);
-
-/**
- * devl_resource_occ_get_register - register occupancy getter
- *
- * @devlink: devlink
- * @resource_id: resource id
- * @occ_get: occupancy getter callback
- * @occ_get_priv: occupancy getter callback priv
- */
-void devl_resource_occ_get_register(struct devlink *devlink,
-				    u64 resource_id,
-				    devlink_resource_occ_get_t *occ_get,
-				    void *occ_get_priv)
-{
-	struct devlink_resource *resource;
-
-	lockdep_assert_held(&devlink->lock);
-
-	resource = devlink_resource_find(devlink, NULL, resource_id);
-	if (WARN_ON(!resource))
-		return;
-	WARN_ON(resource->occ_get);
-
-	resource->occ_get = occ_get;
-	resource->occ_get_priv = occ_get_priv;
-}
-EXPORT_SYMBOL_GPL(devl_resource_occ_get_register);
-
-/**
- *	devlink_resource_occ_get_register - register occupancy getter
- *
- *	@devlink: devlink
- *	@resource_id: resource id
- *	@occ_get: occupancy getter callback
- *	@occ_get_priv: occupancy getter callback priv
- *
- *	Context: Takes and release devlink->lock <mutex>.
- */
-void devlink_resource_occ_get_register(struct devlink *devlink,
-				       u64 resource_id,
-				       devlink_resource_occ_get_t *occ_get,
-				       void *occ_get_priv)
-{
-	devl_lock(devlink);
-	devl_resource_occ_get_register(devlink, resource_id,
-				       occ_get, occ_get_priv);
-	devl_unlock(devlink);
-}
-EXPORT_SYMBOL_GPL(devlink_resource_occ_get_register);
-
-/**
- * devl_resource_occ_get_unregister - unregister occupancy getter
- *
- * @devlink: devlink
- * @resource_id: resource id
- */
-void devl_resource_occ_get_unregister(struct devlink *devlink,
-				      u64 resource_id)
-{
-	struct devlink_resource *resource;
-
-	lockdep_assert_held(&devlink->lock);
-
-	resource = devlink_resource_find(devlink, NULL, resource_id);
-	if (WARN_ON(!resource))
-		return;
-	WARN_ON(!resource->occ_get);
-
-	resource->occ_get = NULL;
-	resource->occ_get_priv = NULL;
-}
-EXPORT_SYMBOL_GPL(devl_resource_occ_get_unregister);
-
-/**
- *	devlink_resource_occ_get_unregister - unregister occupancy getter
- *
- *	@devlink: devlink
- *	@resource_id: resource id
- *
- *	Context: Takes and release devlink->lock <mutex>.
- */
-void devlink_resource_occ_get_unregister(struct devlink *devlink,
-					 u64 resource_id)
-{
-	devl_lock(devlink);
-	devl_resource_occ_get_unregister(devlink, resource_id);
-	devl_unlock(devlink);
-}
-EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister);
-
 static int devlink_param_verify(const struct devlink_param *param)
 {
 	if (!param || !param->name || !param->supported_cmodes)
diff --git a/net/devlink/resource.c b/net/devlink/resource.c
new file mode 100644
index 0000000000000..c8b615e4c3850
--- /dev/null
+++ b/net/devlink/resource.c
@@ -0,0 +1,579 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include "devl_internal.h"
+
+/**
+ * struct devlink_resource - devlink resource
+ * @name: name of the resource
+ * @id: id, per devlink instance
+ * @size: size of the resource
+ * @size_new: updated size of the resource, reload is needed
+ * @size_valid: valid in case the total size of the resource is valid
+ *              including its children
+ * @parent: parent resource
+ * @size_params: size parameters
+ * @list: parent list
+ * @resource_list: list of child resources
+ * @occ_get: occupancy getter callback
+ * @occ_get_priv: occupancy getter callback priv
+ */
+struct devlink_resource {
+	const char *name;
+	u64 id;
+	u64 size;
+	u64 size_new;
+	bool size_valid;
+	struct devlink_resource *parent;
+	struct devlink_resource_size_params size_params;
+	struct list_head list;
+	struct list_head resource_list;
+	devlink_resource_occ_get_t *occ_get;
+	void *occ_get_priv;
+};
+
+static struct devlink_resource *
+devlink_resource_find(struct devlink *devlink,
+		      struct devlink_resource *resource, u64 resource_id)
+{
+	struct list_head *resource_list;
+
+	if (resource)
+		resource_list = &resource->resource_list;
+	else
+		resource_list = &devlink->resource_list;
+
+	list_for_each_entry(resource, resource_list, list) {
+		struct devlink_resource *child_resource;
+
+		if (resource->id == resource_id)
+			return resource;
+
+		child_resource = devlink_resource_find(devlink, resource,
+						       resource_id);
+		if (child_resource)
+			return child_resource;
+	}
+	return NULL;
+}
+
+static void
+devlink_resource_validate_children(struct devlink_resource *resource)
+{
+	struct devlink_resource *child_resource;
+	bool size_valid = true;
+	u64 parts_size = 0;
+
+	if (list_empty(&resource->resource_list))
+		goto out;
+
+	list_for_each_entry(child_resource, &resource->resource_list, list)
+		parts_size += child_resource->size_new;
+
+	if (parts_size > resource->size_new)
+		size_valid = false;
+out:
+	resource->size_valid = size_valid;
+}
+
+static int
+devlink_resource_validate_size(struct devlink_resource *resource, u64 size,
+			       struct netlink_ext_ack *extack)
+{
+	u64 reminder;
+	int err = 0;
+
+	if (size > resource->size_params.size_max) {
+		NL_SET_ERR_MSG(extack, "Size larger than maximum");
+		err = -EINVAL;
+	}
+
+	if (size < resource->size_params.size_min) {
+		NL_SET_ERR_MSG(extack, "Size smaller than minimum");
+		err = -EINVAL;
+	}
+
+	div64_u64_rem(size, resource->size_params.size_granularity, &reminder);
+	if (reminder) {
+		NL_SET_ERR_MSG(extack, "Wrong granularity");
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+int devlink_nl_cmd_resource_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_resource *resource;
+	u64 resource_id;
+	u64 size;
+	int err;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_RESOURCE_ID) ||
+	    GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_RESOURCE_SIZE))
+		return -EINVAL;
+	resource_id = nla_get_u64(info->attrs[DEVLINK_ATTR_RESOURCE_ID]);
+
+	resource = devlink_resource_find(devlink, NULL, resource_id);
+	if (!resource)
+		return -EINVAL;
+
+	size = nla_get_u64(info->attrs[DEVLINK_ATTR_RESOURCE_SIZE]);
+	err = devlink_resource_validate_size(resource, size, info->extack);
+	if (err)
+		return err;
+
+	resource->size_new = size;
+	devlink_resource_validate_children(resource);
+	if (resource->parent)
+		devlink_resource_validate_children(resource->parent);
+	return 0;
+}
+
+static int
+devlink_resource_size_params_put(struct devlink_resource *resource,
+				 struct sk_buff *skb)
+{
+	struct devlink_resource_size_params *size_params;
+
+	size_params = &resource->size_params;
+	if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN,
+			      size_params->size_granularity, DEVLINK_ATTR_PAD) ||
+	    nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX,
+			      size_params->size_max, DEVLINK_ATTR_PAD) ||
+	    nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN,
+			      size_params->size_min, DEVLINK_ATTR_PAD) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_resource_occ_put(struct devlink_resource *resource,
+				    struct sk_buff *skb)
+{
+	if (!resource->occ_get)
+		return 0;
+	return nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC,
+				 resource->occ_get(resource->occ_get_priv),
+				 DEVLINK_ATTR_PAD);
+}
+
+static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb,
+				struct devlink_resource *resource)
+{
+	struct devlink_resource *child_resource;
+	struct nlattr *child_resource_attr;
+	struct nlattr *resource_attr;
+
+	resource_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_RESOURCE);
+	if (!resource_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, DEVLINK_ATTR_RESOURCE_NAME, resource->name) ||
+	    nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE, resource->size,
+			      DEVLINK_ATTR_PAD) ||
+	    nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_ID, resource->id,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (resource->size != resource->size_new &&
+	    nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_NEW,
+			      resource->size_new, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (devlink_resource_occ_put(resource, skb))
+		goto nla_put_failure;
+	if (devlink_resource_size_params_put(resource, skb))
+		goto nla_put_failure;
+	if (list_empty(&resource->resource_list))
+		goto out;
+
+	if (nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_SIZE_VALID,
+		       resource->size_valid))
+		goto nla_put_failure;
+
+	child_resource_attr = nla_nest_start_noflag(skb,
+						    DEVLINK_ATTR_RESOURCE_LIST);
+	if (!child_resource_attr)
+		goto nla_put_failure;
+
+	list_for_each_entry(child_resource, &resource->resource_list, list) {
+		if (devlink_resource_put(devlink, skb, child_resource))
+			goto resource_put_failure;
+	}
+
+	nla_nest_end(skb, child_resource_attr);
+out:
+	nla_nest_end(skb, resource_attr);
+	return 0;
+
+resource_put_failure:
+	nla_nest_cancel(skb, child_resource_attr);
+nla_put_failure:
+	nla_nest_cancel(skb, resource_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_resource_fill(struct genl_info *info,
+				 enum devlink_command cmd, int flags)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_resource *resource;
+	struct nlattr *resources_attr;
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	bool incomplete;
+	void *hdr;
+	int i;
+	int err;
+
+	resource = list_first_entry(&devlink->resource_list,
+				    struct devlink_resource, list);
+start_again:
+	err = devlink_nl_msg_reply_and_new(&skb, info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+			  &devlink_nl_family, NLM_F_MULTI, cmd);
+	if (!hdr) {
+		nlmsg_free(skb);
+		return -EMSGSIZE;
+	}
+
+	if (devlink_nl_put_handle(skb, devlink))
+		goto nla_put_failure;
+
+	resources_attr = nla_nest_start_noflag(skb,
+					       DEVLINK_ATTR_RESOURCE_LIST);
+	if (!resources_attr)
+		goto nla_put_failure;
+
+	incomplete = false;
+	i = 0;
+	list_for_each_entry_from(resource, &devlink->resource_list, list) {
+		err = devlink_resource_put(devlink, skb, resource);
+		if (err) {
+			if (!i)
+				goto err_resource_put;
+			incomplete = true;
+			break;
+		}
+		i++;
+	}
+	nla_nest_end(skb, resources_attr);
+	genlmsg_end(skb, hdr);
+	if (incomplete)
+		goto start_again;
+send_done:
+	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_nl_msg_reply_and_new(&skb, info);
+		if (err)
+			return err;
+		goto send_done;
+	}
+	return genlmsg_reply(skb, info);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_resource_put:
+	nlmsg_free(skb);
+	return err;
+}
+
+int devlink_nl_cmd_resource_dump(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+
+	if (list_empty(&devlink->resource_list))
+		return -EOPNOTSUPP;
+
+	return devlink_resource_fill(info, DEVLINK_CMD_RESOURCE_DUMP, 0);
+}
+
+int devlink_resources_validate(struct devlink *devlink,
+			       struct devlink_resource *resource,
+			       struct genl_info *info)
+{
+	struct list_head *resource_list;
+	int err = 0;
+
+	if (resource)
+		resource_list = &resource->resource_list;
+	else
+		resource_list = &devlink->resource_list;
+
+	list_for_each_entry(resource, resource_list, list) {
+		if (!resource->size_valid)
+			return -EINVAL;
+		err = devlink_resources_validate(devlink, resource, info);
+		if (err)
+			return err;
+	}
+	return err;
+}
+
+/**
+ * devl_resource_register - devlink resource register
+ *
+ * @devlink: devlink
+ * @resource_name: resource's name
+ * @resource_size: resource's size
+ * @resource_id: resource's id
+ * @parent_resource_id: resource's parent id
+ * @size_params: size parameters
+ *
+ * Generic resources should reuse the same names across drivers.
+ * Please see the generic resources list at:
+ * Documentation/networking/devlink/devlink-resource.rst
+ */
+int devl_resource_register(struct devlink *devlink,
+			   const char *resource_name,
+			   u64 resource_size,
+			   u64 resource_id,
+			   u64 parent_resource_id,
+			   const struct devlink_resource_size_params *size_params)
+{
+	struct devlink_resource *resource;
+	struct list_head *resource_list;
+	bool top_hierarchy;
+
+	lockdep_assert_held(&devlink->lock);
+
+	top_hierarchy = parent_resource_id == DEVLINK_RESOURCE_ID_PARENT_TOP;
+
+	resource = devlink_resource_find(devlink, NULL, resource_id);
+	if (resource)
+		return -EINVAL;
+
+	resource = kzalloc(sizeof(*resource), GFP_KERNEL);
+	if (!resource)
+		return -ENOMEM;
+
+	if (top_hierarchy) {
+		resource_list = &devlink->resource_list;
+	} else {
+		struct devlink_resource *parent_resource;
+
+		parent_resource = devlink_resource_find(devlink, NULL,
+							parent_resource_id);
+		if (parent_resource) {
+			resource_list = &parent_resource->resource_list;
+			resource->parent = parent_resource;
+		} else {
+			kfree(resource);
+			return -EINVAL;
+		}
+	}
+
+	resource->name = resource_name;
+	resource->size = resource_size;
+	resource->size_new = resource_size;
+	resource->id = resource_id;
+	resource->size_valid = true;
+	memcpy(&resource->size_params, size_params,
+	       sizeof(resource->size_params));
+	INIT_LIST_HEAD(&resource->resource_list);
+	list_add_tail(&resource->list, resource_list);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devl_resource_register);
+
+/**
+ *	devlink_resource_register - devlink resource register
+ *
+ *	@devlink: devlink
+ *	@resource_name: resource's name
+ *	@resource_size: resource's size
+ *	@resource_id: resource's id
+ *	@parent_resource_id: resource's parent id
+ *	@size_params: size parameters
+ *
+ *	Generic resources should reuse the same names across drivers.
+ *	Please see the generic resources list at:
+ *	Documentation/networking/devlink/devlink-resource.rst
+ *
+ *	Context: Takes and release devlink->lock <mutex>.
+ */
+int devlink_resource_register(struct devlink *devlink,
+			      const char *resource_name,
+			      u64 resource_size,
+			      u64 resource_id,
+			      u64 parent_resource_id,
+			      const struct devlink_resource_size_params *size_params)
+{
+	int err;
+
+	devl_lock(devlink);
+	err = devl_resource_register(devlink, resource_name, resource_size,
+				     resource_id, parent_resource_id, size_params);
+	devl_unlock(devlink);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devlink_resource_register);
+
+static void devlink_resource_unregister(struct devlink *devlink,
+					struct devlink_resource *resource)
+{
+	struct devlink_resource *tmp, *child_resource;
+
+	list_for_each_entry_safe(child_resource, tmp, &resource->resource_list,
+				 list) {
+		devlink_resource_unregister(devlink, child_resource);
+		list_del(&child_resource->list);
+		kfree(child_resource);
+	}
+}
+
+/**
+ * devl_resources_unregister - free all resources
+ *
+ * @devlink: devlink
+ */
+void devl_resources_unregister(struct devlink *devlink)
+{
+	struct devlink_resource *tmp, *child_resource;
+
+	lockdep_assert_held(&devlink->lock);
+
+	list_for_each_entry_safe(child_resource, tmp, &devlink->resource_list,
+				 list) {
+		devlink_resource_unregister(devlink, child_resource);
+		list_del(&child_resource->list);
+		kfree(child_resource);
+	}
+}
+EXPORT_SYMBOL_GPL(devl_resources_unregister);
+
+/**
+ *	devlink_resources_unregister - free all resources
+ *
+ *	@devlink: devlink
+ *
+ *	Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_resources_unregister(struct devlink *devlink)
+{
+	devl_lock(devlink);
+	devl_resources_unregister(devlink);
+	devl_unlock(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_resources_unregister);
+
+/**
+ * devl_resource_size_get - get and update size
+ *
+ * @devlink: devlink
+ * @resource_id: the requested resource id
+ * @p_resource_size: ptr to update
+ */
+int devl_resource_size_get(struct devlink *devlink,
+			   u64 resource_id,
+			   u64 *p_resource_size)
+{
+	struct devlink_resource *resource;
+
+	lockdep_assert_held(&devlink->lock);
+
+	resource = devlink_resource_find(devlink, NULL, resource_id);
+	if (!resource)
+		return -EINVAL;
+	*p_resource_size = resource->size_new;
+	resource->size = resource->size_new;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devl_resource_size_get);
+
+/**
+ * devl_resource_occ_get_register - register occupancy getter
+ *
+ * @devlink: devlink
+ * @resource_id: resource id
+ * @occ_get: occupancy getter callback
+ * @occ_get_priv: occupancy getter callback priv
+ */
+void devl_resource_occ_get_register(struct devlink *devlink,
+				    u64 resource_id,
+				    devlink_resource_occ_get_t *occ_get,
+				    void *occ_get_priv)
+{
+	struct devlink_resource *resource;
+
+	lockdep_assert_held(&devlink->lock);
+
+	resource = devlink_resource_find(devlink, NULL, resource_id);
+	if (WARN_ON(!resource))
+		return;
+	WARN_ON(resource->occ_get);
+
+	resource->occ_get = occ_get;
+	resource->occ_get_priv = occ_get_priv;
+}
+EXPORT_SYMBOL_GPL(devl_resource_occ_get_register);
+
+/**
+ *	devlink_resource_occ_get_register - register occupancy getter
+ *
+ *	@devlink: devlink
+ *	@resource_id: resource id
+ *	@occ_get: occupancy getter callback
+ *	@occ_get_priv: occupancy getter callback priv
+ *
+ *	Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_resource_occ_get_register(struct devlink *devlink,
+				       u64 resource_id,
+				       devlink_resource_occ_get_t *occ_get,
+				       void *occ_get_priv)
+{
+	devl_lock(devlink);
+	devl_resource_occ_get_register(devlink, resource_id,
+				       occ_get, occ_get_priv);
+	devl_unlock(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_resource_occ_get_register);
+
+/**
+ * devl_resource_occ_get_unregister - unregister occupancy getter
+ *
+ * @devlink: devlink
+ * @resource_id: resource id
+ */
+void devl_resource_occ_get_unregister(struct devlink *devlink,
+				      u64 resource_id)
+{
+	struct devlink_resource *resource;
+
+	lockdep_assert_held(&devlink->lock);
+
+	resource = devlink_resource_find(devlink, NULL, resource_id);
+	if (WARN_ON(!resource))
+		return;
+	WARN_ON(!resource->occ_get);
+
+	resource->occ_get = NULL;
+	resource->occ_get_priv = NULL;
+}
+EXPORT_SYMBOL_GPL(devl_resource_occ_get_unregister);
+
+/**
+ *	devlink_resource_occ_get_unregister - unregister occupancy getter
+ *
+ *	@devlink: devlink
+ *	@resource_id: resource id
+ *
+ *	Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_resource_occ_get_unregister(struct devlink *devlink,
+					 u64 resource_id)
+{
+	devl_lock(devlink);
+	devl_resource_occ_get_unregister(devlink, resource_id);
+	devl_unlock(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister);
-- 
GitLab


From 830c41e1e987d9745a01b06c5f86434df8bd5f58 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:49 +0200
Subject: [PATCH 1794/1806] devlink: push param related code into separate file

Cut out another chunk from leftover.c and put param related code
into a separate file.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-8-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/Makefile        |   2 +-
 net/devlink/devl_internal.h |   9 +
 net/devlink/leftover.c      | 859 -----------------------------------
 net/devlink/param.c         | 865 ++++++++++++++++++++++++++++++++++++
 4 files changed, 875 insertions(+), 860 deletions(-)
 create mode 100644 net/devlink/param.c

diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index 8864cd933acbf..c4b29f603a1f2 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o sb.o dpipe.o \
-	 resource.o health.o
+	 resource.o param.o health.o
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index e5c0acf7a7583..e0304d6079786 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -156,6 +156,8 @@ int devlink_nl_msg_reply_and_new(struct sk_buff **msg, struct genl_info *info);
 void devlink_notify(struct devlink *devlink, enum devlink_command cmd);
 void devlink_ports_notify_register(struct devlink *devlink);
 void devlink_ports_notify_unregister(struct devlink *devlink);
+void devlink_params_notify_register(struct devlink *devlink);
+void devlink_params_notify_unregister(struct devlink *devlink);
 
 /* Ports */
 #define ASSERT_DEVLINK_PORT_INITIALIZED(devlink_port)				\
@@ -240,6 +242,13 @@ int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb,
 					    struct genl_info *info);
 int devlink_nl_cmd_resource_set(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_resource_dump(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg,
+					 struct netlink_callback *cb);
+int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb,
+				       struct genl_info *info);
+int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb,
+				       struct genl_info *info);
 int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 					    struct genl_info *info);
 int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 1c65449f22523..2f1dfd27d1c87 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -1061,611 +1061,6 @@ int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
 	return 0;
 }
 
-static const struct devlink_param devlink_param_generic[] = {
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
-		.name = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME,
-		.type = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
-		.name = DEVLINK_PARAM_GENERIC_MAX_MACS_NAME,
-		.type = DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV,
-		.name = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME,
-		.type = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
-		.name = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME,
-		.type = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI,
-		.name = DEVLINK_PARAM_GENERIC_IGNORE_ARI_NAME,
-		.type = DEVLINK_PARAM_GENERIC_IGNORE_ARI_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
-		.name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_NAME,
-		.type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
-		.name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME,
-		.type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
-		.name = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME,
-		.type = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE,
-		.name = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_NAME,
-		.type = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
-		.name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME,
-		.type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET,
-		.name = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME,
-		.type = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH,
-		.name = DEVLINK_PARAM_GENERIC_ENABLE_ETH_NAME,
-		.type = DEVLINK_PARAM_GENERIC_ENABLE_ETH_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
-		.name = DEVLINK_PARAM_GENERIC_ENABLE_RDMA_NAME,
-		.type = DEVLINK_PARAM_GENERIC_ENABLE_RDMA_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET,
-		.name = DEVLINK_PARAM_GENERIC_ENABLE_VNET_NAME,
-		.type = DEVLINK_PARAM_GENERIC_ENABLE_VNET_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP,
-		.name = DEVLINK_PARAM_GENERIC_ENABLE_IWARP_NAME,
-		.type = DEVLINK_PARAM_GENERIC_ENABLE_IWARP_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE,
-		.name = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_NAME,
-		.type = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_TYPE,
-	},
-	{
-		.id = DEVLINK_PARAM_GENERIC_ID_EVENT_EQ_SIZE,
-		.name = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_NAME,
-		.type = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_TYPE,
-	},
-};
-
-static int devlink_param_generic_verify(const struct devlink_param *param)
-{
-	/* verify it match generic parameter by id and name */
-	if (param->id > DEVLINK_PARAM_GENERIC_ID_MAX)
-		return -EINVAL;
-	if (strcmp(param->name, devlink_param_generic[param->id].name))
-		return -ENOENT;
-
-	WARN_ON(param->type != devlink_param_generic[param->id].type);
-
-	return 0;
-}
-
-static int devlink_param_driver_verify(const struct devlink_param *param)
-{
-	int i;
-
-	if (param->id <= DEVLINK_PARAM_GENERIC_ID_MAX)
-		return -EINVAL;
-	/* verify no such name in generic params */
-	for (i = 0; i <= DEVLINK_PARAM_GENERIC_ID_MAX; i++)
-		if (!strcmp(param->name, devlink_param_generic[i].name))
-			return -EEXIST;
-
-	return 0;
-}
-
-static struct devlink_param_item *
-devlink_param_find_by_name(struct xarray *params, const char *param_name)
-{
-	struct devlink_param_item *param_item;
-	unsigned long param_id;
-
-	xa_for_each(params, param_id, param_item) {
-		if (!strcmp(param_item->param->name, param_name))
-			return param_item;
-	}
-	return NULL;
-}
-
-static struct devlink_param_item *
-devlink_param_find_by_id(struct xarray *params, u32 param_id)
-{
-	return xa_load(params, param_id);
-}
-
-static bool
-devlink_param_cmode_is_supported(const struct devlink_param *param,
-				 enum devlink_param_cmode cmode)
-{
-	return test_bit(cmode, &param->supported_cmodes);
-}
-
-static int devlink_param_get(struct devlink *devlink,
-			     const struct devlink_param *param,
-			     struct devlink_param_gset_ctx *ctx)
-{
-	if (!param->get)
-		return -EOPNOTSUPP;
-	return param->get(devlink, param->id, ctx);
-}
-
-static int devlink_param_set(struct devlink *devlink,
-			     const struct devlink_param *param,
-			     struct devlink_param_gset_ctx *ctx)
-{
-	if (!param->set)
-		return -EOPNOTSUPP;
-	return param->set(devlink, param->id, ctx);
-}
-
-static int
-devlink_param_type_to_nla_type(enum devlink_param_type param_type)
-{
-	switch (param_type) {
-	case DEVLINK_PARAM_TYPE_U8:
-		return NLA_U8;
-	case DEVLINK_PARAM_TYPE_U16:
-		return NLA_U16;
-	case DEVLINK_PARAM_TYPE_U32:
-		return NLA_U32;
-	case DEVLINK_PARAM_TYPE_STRING:
-		return NLA_STRING;
-	case DEVLINK_PARAM_TYPE_BOOL:
-		return NLA_FLAG;
-	default:
-		return -EINVAL;
-	}
-}
-
-static int
-devlink_nl_param_value_fill_one(struct sk_buff *msg,
-				enum devlink_param_type type,
-				enum devlink_param_cmode cmode,
-				union devlink_param_value val)
-{
-	struct nlattr *param_value_attr;
-
-	param_value_attr = nla_nest_start_noflag(msg,
-						 DEVLINK_ATTR_PARAM_VALUE);
-	if (!param_value_attr)
-		goto nla_put_failure;
-
-	if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_CMODE, cmode))
-		goto value_nest_cancel;
-
-	switch (type) {
-	case DEVLINK_PARAM_TYPE_U8:
-		if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu8))
-			goto value_nest_cancel;
-		break;
-	case DEVLINK_PARAM_TYPE_U16:
-		if (nla_put_u16(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu16))
-			goto value_nest_cancel;
-		break;
-	case DEVLINK_PARAM_TYPE_U32:
-		if (nla_put_u32(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu32))
-			goto value_nest_cancel;
-		break;
-	case DEVLINK_PARAM_TYPE_STRING:
-		if (nla_put_string(msg, DEVLINK_ATTR_PARAM_VALUE_DATA,
-				   val.vstr))
-			goto value_nest_cancel;
-		break;
-	case DEVLINK_PARAM_TYPE_BOOL:
-		if (val.vbool &&
-		    nla_put_flag(msg, DEVLINK_ATTR_PARAM_VALUE_DATA))
-			goto value_nest_cancel;
-		break;
-	}
-
-	nla_nest_end(msg, param_value_attr);
-	return 0;
-
-value_nest_cancel:
-	nla_nest_cancel(msg, param_value_attr);
-nla_put_failure:
-	return -EMSGSIZE;
-}
-
-static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
-				 unsigned int port_index,
-				 struct devlink_param_item *param_item,
-				 enum devlink_command cmd,
-				 u32 portid, u32 seq, int flags)
-{
-	union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1];
-	bool param_value_set[DEVLINK_PARAM_CMODE_MAX + 1] = {};
-	const struct devlink_param *param = param_item->param;
-	struct devlink_param_gset_ctx ctx;
-	struct nlattr *param_values_list;
-	struct nlattr *param_attr;
-	int nla_type;
-	void *hdr;
-	int err;
-	int i;
-
-	/* Get value from driver part to driverinit configuration mode */
-	for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) {
-		if (!devlink_param_cmode_is_supported(param, i))
-			continue;
-		if (i == DEVLINK_PARAM_CMODE_DRIVERINIT) {
-			if (param_item->driverinit_value_new_valid)
-				param_value[i] = param_item->driverinit_value_new;
-			else if (param_item->driverinit_value_valid)
-				param_value[i] = param_item->driverinit_value;
-			else
-				return -EOPNOTSUPP;
-		} else {
-			ctx.cmode = i;
-			err = devlink_param_get(devlink, param, &ctx);
-			if (err)
-				return err;
-			param_value[i] = ctx.val;
-		}
-		param_value_set[i] = true;
-	}
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto genlmsg_cancel;
-
-	if (cmd == DEVLINK_CMD_PORT_PARAM_GET ||
-	    cmd == DEVLINK_CMD_PORT_PARAM_NEW ||
-	    cmd == DEVLINK_CMD_PORT_PARAM_DEL)
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index))
-			goto genlmsg_cancel;
-
-	param_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PARAM);
-	if (!param_attr)
-		goto genlmsg_cancel;
-	if (nla_put_string(msg, DEVLINK_ATTR_PARAM_NAME, param->name))
-		goto param_nest_cancel;
-	if (param->generic && nla_put_flag(msg, DEVLINK_ATTR_PARAM_GENERIC))
-		goto param_nest_cancel;
-
-	nla_type = devlink_param_type_to_nla_type(param->type);
-	if (nla_type < 0)
-		goto param_nest_cancel;
-	if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type))
-		goto param_nest_cancel;
-
-	param_values_list = nla_nest_start_noflag(msg,
-						  DEVLINK_ATTR_PARAM_VALUES_LIST);
-	if (!param_values_list)
-		goto param_nest_cancel;
-
-	for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) {
-		if (!param_value_set[i])
-			continue;
-		err = devlink_nl_param_value_fill_one(msg, param->type,
-						      i, param_value[i]);
-		if (err)
-			goto values_list_nest_cancel;
-	}
-
-	nla_nest_end(msg, param_values_list);
-	nla_nest_end(msg, param_attr);
-	genlmsg_end(msg, hdr);
-	return 0;
-
-values_list_nest_cancel:
-	nla_nest_end(msg, param_values_list);
-param_nest_cancel:
-	nla_nest_cancel(msg, param_attr);
-genlmsg_cancel:
-	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
-}
-
-static void devlink_param_notify(struct devlink *devlink,
-				 unsigned int port_index,
-				 struct devlink_param_item *param_item,
-				 enum devlink_command cmd)
-{
-	struct sk_buff *msg;
-	int err;
-
-	WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL &&
-		cmd != DEVLINK_CMD_PORT_PARAM_NEW &&
-		cmd != DEVLINK_CMD_PORT_PARAM_DEL);
-
-	/* devlink_notify_register() / devlink_notify_unregister()
-	 * will replay the notifications if the params are added/removed
-	 * outside of the lifetime of the instance.
-	 */
-	if (!devl_is_registered(devlink))
-		return;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return;
-	err = devlink_nl_param_fill(msg, devlink, port_index, param_item, cmd,
-				    0, 0, 0);
-	if (err) {
-		nlmsg_free(msg);
-		return;
-	}
-
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
-}
-
-static void devlink_params_notify(struct devlink *devlink,
-				  enum devlink_command cmd)
-{
-	struct devlink_param_item *param_item;
-	unsigned long param_id;
-
-	xa_for_each(&devlink->params, param_id, param_item)
-		devlink_param_notify(devlink, 0, param_item, cmd);
-}
-
-static void devlink_params_notify_register(struct devlink *devlink)
-{
-	devlink_params_notify(devlink, DEVLINK_CMD_PARAM_NEW);
-}
-
-static void devlink_params_notify_unregister(struct devlink *devlink)
-{
-	devlink_params_notify(devlink, DEVLINK_CMD_PARAM_DEL);
-}
-
-static int devlink_nl_param_get_dump_one(struct sk_buff *msg,
-					 struct devlink *devlink,
-					 struct netlink_callback *cb,
-					 int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_param_item *param_item;
-	unsigned long param_id;
-	int err = 0;
-
-	xa_for_each_start(&devlink->params, param_id, param_item, state->idx) {
-		err = devlink_nl_param_fill(msg, devlink, 0, param_item,
-					    DEVLINK_CMD_PARAM_GET,
-					    NETLINK_CB(cb->skb).portid,
-					    cb->nlh->nlmsg_seq, flags);
-		if (err == -EOPNOTSUPP) {
-			err = 0;
-		} else if (err) {
-			state->idx = param_id;
-			break;
-		}
-	}
-
-	return err;
-}
-
-int devlink_nl_param_get_dumpit(struct sk_buff *skb,
-				struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_param_get_dump_one);
-}
-
-static int
-devlink_param_type_get_from_info(struct genl_info *info,
-				 enum devlink_param_type *param_type)
-{
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_TYPE))
-		return -EINVAL;
-
-	switch (nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_TYPE])) {
-	case NLA_U8:
-		*param_type = DEVLINK_PARAM_TYPE_U8;
-		break;
-	case NLA_U16:
-		*param_type = DEVLINK_PARAM_TYPE_U16;
-		break;
-	case NLA_U32:
-		*param_type = DEVLINK_PARAM_TYPE_U32;
-		break;
-	case NLA_STRING:
-		*param_type = DEVLINK_PARAM_TYPE_STRING;
-		break;
-	case NLA_FLAG:
-		*param_type = DEVLINK_PARAM_TYPE_BOOL;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int
-devlink_param_value_get_from_info(const struct devlink_param *param,
-				  struct genl_info *info,
-				  union devlink_param_value *value)
-{
-	struct nlattr *param_data;
-	int len;
-
-	param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA];
-
-	if (param->type != DEVLINK_PARAM_TYPE_BOOL && !param_data)
-		return -EINVAL;
-
-	switch (param->type) {
-	case DEVLINK_PARAM_TYPE_U8:
-		if (nla_len(param_data) != sizeof(u8))
-			return -EINVAL;
-		value->vu8 = nla_get_u8(param_data);
-		break;
-	case DEVLINK_PARAM_TYPE_U16:
-		if (nla_len(param_data) != sizeof(u16))
-			return -EINVAL;
-		value->vu16 = nla_get_u16(param_data);
-		break;
-	case DEVLINK_PARAM_TYPE_U32:
-		if (nla_len(param_data) != sizeof(u32))
-			return -EINVAL;
-		value->vu32 = nla_get_u32(param_data);
-		break;
-	case DEVLINK_PARAM_TYPE_STRING:
-		len = strnlen(nla_data(param_data), nla_len(param_data));
-		if (len == nla_len(param_data) ||
-		    len >= __DEVLINK_PARAM_MAX_STRING_VALUE)
-			return -EINVAL;
-		strcpy(value->vstr, nla_data(param_data));
-		break;
-	case DEVLINK_PARAM_TYPE_BOOL:
-		if (param_data && nla_len(param_data))
-			return -EINVAL;
-		value->vbool = nla_get_flag(param_data);
-		break;
-	}
-	return 0;
-}
-
-static struct devlink_param_item *
-devlink_param_get_from_info(struct xarray *params, struct genl_info *info)
-{
-	char *param_name;
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_NAME))
-		return NULL;
-
-	param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]);
-	return devlink_param_find_by_name(params, param_name);
-}
-
-int devlink_nl_param_get_doit(struct sk_buff *skb,
-			      struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_param_item *param_item;
-	struct sk_buff *msg;
-	int err;
-
-	param_item = devlink_param_get_from_info(&devlink->params, info);
-	if (!param_item)
-		return -EINVAL;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	err = devlink_nl_param_fill(msg, devlink, 0, param_item,
-				    DEVLINK_CMD_PARAM_GET,
-				    info->snd_portid, info->snd_seq, 0);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
-
-	return genlmsg_reply(msg, info);
-}
-
-static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink,
-					   unsigned int port_index,
-					   struct xarray *params,
-					   struct genl_info *info,
-					   enum devlink_command cmd)
-{
-	enum devlink_param_type param_type;
-	struct devlink_param_gset_ctx ctx;
-	enum devlink_param_cmode cmode;
-	struct devlink_param_item *param_item;
-	const struct devlink_param *param;
-	union devlink_param_value value;
-	int err = 0;
-
-	param_item = devlink_param_get_from_info(params, info);
-	if (!param_item)
-		return -EINVAL;
-	param = param_item->param;
-	err = devlink_param_type_get_from_info(info, &param_type);
-	if (err)
-		return err;
-	if (param_type != param->type)
-		return -EINVAL;
-	err = devlink_param_value_get_from_info(param, info, &value);
-	if (err)
-		return err;
-	if (param->validate) {
-		err = param->validate(devlink, param->id, value, info->extack);
-		if (err)
-			return err;
-	}
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_VALUE_CMODE))
-		return -EINVAL;
-	cmode = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_CMODE]);
-	if (!devlink_param_cmode_is_supported(param, cmode))
-		return -EOPNOTSUPP;
-
-	if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) {
-		param_item->driverinit_value_new = value;
-		param_item->driverinit_value_new_valid = true;
-	} else {
-		if (!param->set)
-			return -EOPNOTSUPP;
-		ctx.val = value;
-		ctx.cmode = cmode;
-		err = devlink_param_set(devlink, param, &ctx);
-		if (err)
-			return err;
-	}
-
-	devlink_param_notify(devlink, port_index, param_item, cmd);
-	return 0;
-}
-
-static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb,
-					 struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-
-	return __devlink_nl_cmd_param_set_doit(devlink, 0, &devlink->params,
-					       info, DEVLINK_CMD_PARAM_NEW);
-}
-
-static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg,
-						struct netlink_callback *cb)
-{
-	NL_SET_ERR_MSG(cb->extack, "Port params are not supported");
-	return msg->len;
-}
-
-static int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb,
-					      struct genl_info *info)
-{
-	NL_SET_ERR_MSG(info->extack, "Port params are not supported");
-	return -EINVAL;
-}
-
-static int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb,
-					      struct genl_info *info)
-{
-	NL_SET_ERR_MSG(info->extack, "Port params are not supported");
-	return -EINVAL;
-}
-
 static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg,
 					     struct devlink *devlink,
 					     struct devlink_snapshot *snapshot)
@@ -4216,260 +3611,6 @@ void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard,
 }
 EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set);
 
-static int devlink_param_verify(const struct devlink_param *param)
-{
-	if (!param || !param->name || !param->supported_cmodes)
-		return -EINVAL;
-	if (param->generic)
-		return devlink_param_generic_verify(param);
-	else
-		return devlink_param_driver_verify(param);
-}
-
-static int devlink_param_register(struct devlink *devlink,
-				  const struct devlink_param *param)
-{
-	struct devlink_param_item *param_item;
-	int err;
-
-	WARN_ON(devlink_param_verify(param));
-	WARN_ON(devlink_param_find_by_name(&devlink->params, param->name));
-
-	if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT))
-		WARN_ON(param->get || param->set);
-	else
-		WARN_ON(!param->get || !param->set);
-
-	param_item = kzalloc(sizeof(*param_item), GFP_KERNEL);
-	if (!param_item)
-		return -ENOMEM;
-
-	param_item->param = param;
-
-	err = xa_insert(&devlink->params, param->id, param_item, GFP_KERNEL);
-	if (err)
-		goto err_xa_insert;
-
-	devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW);
-	return 0;
-
-err_xa_insert:
-	kfree(param_item);
-	return err;
-}
-
-static void devlink_param_unregister(struct devlink *devlink,
-				     const struct devlink_param *param)
-{
-	struct devlink_param_item *param_item;
-
-	param_item = devlink_param_find_by_id(&devlink->params, param->id);
-	if (WARN_ON(!param_item))
-		return;
-	devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_DEL);
-	xa_erase(&devlink->params, param->id);
-	kfree(param_item);
-}
-
-/**
- *	devl_params_register - register configuration parameters
- *
- *	@devlink: devlink
- *	@params: configuration parameters array
- *	@params_count: number of parameters provided
- *
- *	Register the configuration parameters supported by the driver.
- */
-int devl_params_register(struct devlink *devlink,
-			 const struct devlink_param *params,
-			 size_t params_count)
-{
-	const struct devlink_param *param = params;
-	int i, err;
-
-	lockdep_assert_held(&devlink->lock);
-
-	for (i = 0; i < params_count; i++, param++) {
-		err = devlink_param_register(devlink, param);
-		if (err)
-			goto rollback;
-	}
-	return 0;
-
-rollback:
-	if (!i)
-		return err;
-
-	for (param--; i > 0; i--, param--)
-		devlink_param_unregister(devlink, param);
-	return err;
-}
-EXPORT_SYMBOL_GPL(devl_params_register);
-
-int devlink_params_register(struct devlink *devlink,
-			    const struct devlink_param *params,
-			    size_t params_count)
-{
-	int err;
-
-	devl_lock(devlink);
-	err = devl_params_register(devlink, params, params_count);
-	devl_unlock(devlink);
-	return err;
-}
-EXPORT_SYMBOL_GPL(devlink_params_register);
-
-/**
- *	devl_params_unregister - unregister configuration parameters
- *	@devlink: devlink
- *	@params: configuration parameters to unregister
- *	@params_count: number of parameters provided
- */
-void devl_params_unregister(struct devlink *devlink,
-			    const struct devlink_param *params,
-			    size_t params_count)
-{
-	const struct devlink_param *param = params;
-	int i;
-
-	lockdep_assert_held(&devlink->lock);
-
-	for (i = 0; i < params_count; i++, param++)
-		devlink_param_unregister(devlink, param);
-}
-EXPORT_SYMBOL_GPL(devl_params_unregister);
-
-void devlink_params_unregister(struct devlink *devlink,
-			       const struct devlink_param *params,
-			       size_t params_count)
-{
-	devl_lock(devlink);
-	devl_params_unregister(devlink, params, params_count);
-	devl_unlock(devlink);
-}
-EXPORT_SYMBOL_GPL(devlink_params_unregister);
-
-/**
- *	devl_param_driverinit_value_get - get configuration parameter
- *					  value for driver initializing
- *
- *	@devlink: devlink
- *	@param_id: parameter ID
- *	@val: pointer to store the value of parameter in driverinit
- *	      configuration mode
- *
- *	This function should be used by the driver to get driverinit
- *	configuration for initialization after reload command.
- *
- *	Note that lockless call of this function relies on the
- *	driver to maintain following basic sane behavior:
- *	1) Driver ensures a call to this function cannot race with
- *	   registering/unregistering the parameter with the same parameter ID.
- *	2) Driver ensures a call to this function cannot race with
- *	   devl_param_driverinit_value_set() call with the same parameter ID.
- *	3) Driver ensures a call to this function cannot race with
- *	   reload operation.
- *	If the driver is not able to comply, it has to take the devlink->lock
- *	while calling this.
- */
-int devl_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
-				    union devlink_param_value *val)
-{
-	struct devlink_param_item *param_item;
-
-	if (WARN_ON(!devlink_reload_supported(devlink->ops)))
-		return -EOPNOTSUPP;
-
-	param_item = devlink_param_find_by_id(&devlink->params, param_id);
-	if (!param_item)
-		return -EINVAL;
-
-	if (!param_item->driverinit_value_valid)
-		return -EOPNOTSUPP;
-
-	if (WARN_ON(!devlink_param_cmode_is_supported(param_item->param,
-						      DEVLINK_PARAM_CMODE_DRIVERINIT)))
-		return -EOPNOTSUPP;
-
-	*val = param_item->driverinit_value;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devl_param_driverinit_value_get);
-
-/**
- *	devl_param_driverinit_value_set - set value of configuration
- *					  parameter for driverinit
- *					  configuration mode
- *
- *	@devlink: devlink
- *	@param_id: parameter ID
- *	@init_val: value of parameter to set for driverinit configuration mode
- *
- *	This function should be used by the driver to set driverinit
- *	configuration mode default value.
- */
-void devl_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
-				     union devlink_param_value init_val)
-{
-	struct devlink_param_item *param_item;
-
-	devl_assert_locked(devlink);
-
-	param_item = devlink_param_find_by_id(&devlink->params, param_id);
-	if (WARN_ON(!param_item))
-		return;
-
-	if (WARN_ON(!devlink_param_cmode_is_supported(param_item->param,
-						      DEVLINK_PARAM_CMODE_DRIVERINIT)))
-		return;
-
-	param_item->driverinit_value = init_val;
-	param_item->driverinit_value_valid = true;
-
-	devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW);
-}
-EXPORT_SYMBOL_GPL(devl_param_driverinit_value_set);
-
-void devlink_params_driverinit_load_new(struct devlink *devlink)
-{
-	struct devlink_param_item *param_item;
-	unsigned long param_id;
-
-	xa_for_each(&devlink->params, param_id, param_item) {
-		if (!devlink_param_cmode_is_supported(param_item->param,
-						      DEVLINK_PARAM_CMODE_DRIVERINIT) ||
-		    !param_item->driverinit_value_new_valid)
-			continue;
-		param_item->driverinit_value = param_item->driverinit_value_new;
-		param_item->driverinit_value_valid = true;
-		param_item->driverinit_value_new_valid = false;
-	}
-}
-
-/**
- *	devl_param_value_changed - notify devlink on a parameter's value
- *				   change. Should be called by the driver
- *				   right after the change.
- *
- *	@devlink: devlink
- *	@param_id: parameter ID
- *
- *	This function should be used by the driver to notify devlink on value
- *	change, excluding driverinit configuration mode.
- *	For driverinit configuration mode driver should use the function
- */
-void devl_param_value_changed(struct devlink *devlink, u32 param_id)
-{
-	struct devlink_param_item *param_item;
-
-	param_item = devlink_param_find_by_id(&devlink->params, param_id);
-	WARN_ON(!param_item);
-
-	devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW);
-}
-EXPORT_SYMBOL_GPL(devl_param_value_changed);
-
 /**
  * devl_region_create - create a new address region
  *
diff --git a/net/devlink/param.c b/net/devlink/param.c
new file mode 100644
index 0000000000000..31275f9d4cb73
--- /dev/null
+++ b/net/devlink/param.c
@@ -0,0 +1,865 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include "devl_internal.h"
+
+static const struct devlink_param devlink_param_generic[] = {
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+		.name = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME,
+		.type = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+		.name = DEVLINK_PARAM_GENERIC_MAX_MACS_NAME,
+		.type = DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+		.name = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME,
+		.type = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI,
+		.name = DEVLINK_PARAM_GENERIC_IGNORE_ARI_NAME,
+		.type = DEVLINK_PARAM_GENERIC_IGNORE_ARI_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
+		.name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_NAME,
+		.type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+		.name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME,
+		.type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
+		.name = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME,
+		.type = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE,
+		.name = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_NAME,
+		.type = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_ETH_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_ETH_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_RDMA_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_RDMA_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_VNET_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_VNET_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_IWARP_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_IWARP_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE,
+		.name = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_NAME,
+		.type = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_EVENT_EQ_SIZE,
+		.name = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_NAME,
+		.type = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_TYPE,
+	},
+};
+
+static int devlink_param_generic_verify(const struct devlink_param *param)
+{
+	/* verify it match generic parameter by id and name */
+	if (param->id > DEVLINK_PARAM_GENERIC_ID_MAX)
+		return -EINVAL;
+	if (strcmp(param->name, devlink_param_generic[param->id].name))
+		return -ENOENT;
+
+	WARN_ON(param->type != devlink_param_generic[param->id].type);
+
+	return 0;
+}
+
+static int devlink_param_driver_verify(const struct devlink_param *param)
+{
+	int i;
+
+	if (param->id <= DEVLINK_PARAM_GENERIC_ID_MAX)
+		return -EINVAL;
+	/* verify no such name in generic params */
+	for (i = 0; i <= DEVLINK_PARAM_GENERIC_ID_MAX; i++)
+		if (!strcmp(param->name, devlink_param_generic[i].name))
+			return -EEXIST;
+
+	return 0;
+}
+
+static struct devlink_param_item *
+devlink_param_find_by_name(struct xarray *params, const char *param_name)
+{
+	struct devlink_param_item *param_item;
+	unsigned long param_id;
+
+	xa_for_each(params, param_id, param_item) {
+		if (!strcmp(param_item->param->name, param_name))
+			return param_item;
+	}
+	return NULL;
+}
+
+static struct devlink_param_item *
+devlink_param_find_by_id(struct xarray *params, u32 param_id)
+{
+	return xa_load(params, param_id);
+}
+
+static bool
+devlink_param_cmode_is_supported(const struct devlink_param *param,
+				 enum devlink_param_cmode cmode)
+{
+	return test_bit(cmode, &param->supported_cmodes);
+}
+
+static int devlink_param_get(struct devlink *devlink,
+			     const struct devlink_param *param,
+			     struct devlink_param_gset_ctx *ctx)
+{
+	if (!param->get)
+		return -EOPNOTSUPP;
+	return param->get(devlink, param->id, ctx);
+}
+
+static int devlink_param_set(struct devlink *devlink,
+			     const struct devlink_param *param,
+			     struct devlink_param_gset_ctx *ctx)
+{
+	if (!param->set)
+		return -EOPNOTSUPP;
+	return param->set(devlink, param->id, ctx);
+}
+
+static int
+devlink_param_type_to_nla_type(enum devlink_param_type param_type)
+{
+	switch (param_type) {
+	case DEVLINK_PARAM_TYPE_U8:
+		return NLA_U8;
+	case DEVLINK_PARAM_TYPE_U16:
+		return NLA_U16;
+	case DEVLINK_PARAM_TYPE_U32:
+		return NLA_U32;
+	case DEVLINK_PARAM_TYPE_STRING:
+		return NLA_STRING;
+	case DEVLINK_PARAM_TYPE_BOOL:
+		return NLA_FLAG;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int
+devlink_nl_param_value_fill_one(struct sk_buff *msg,
+				enum devlink_param_type type,
+				enum devlink_param_cmode cmode,
+				union devlink_param_value val)
+{
+	struct nlattr *param_value_attr;
+
+	param_value_attr = nla_nest_start_noflag(msg,
+						 DEVLINK_ATTR_PARAM_VALUE);
+	if (!param_value_attr)
+		goto nla_put_failure;
+
+	if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_CMODE, cmode))
+		goto value_nest_cancel;
+
+	switch (type) {
+	case DEVLINK_PARAM_TYPE_U8:
+		if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu8))
+			goto value_nest_cancel;
+		break;
+	case DEVLINK_PARAM_TYPE_U16:
+		if (nla_put_u16(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu16))
+			goto value_nest_cancel;
+		break;
+	case DEVLINK_PARAM_TYPE_U32:
+		if (nla_put_u32(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu32))
+			goto value_nest_cancel;
+		break;
+	case DEVLINK_PARAM_TYPE_STRING:
+		if (nla_put_string(msg, DEVLINK_ATTR_PARAM_VALUE_DATA,
+				   val.vstr))
+			goto value_nest_cancel;
+		break;
+	case DEVLINK_PARAM_TYPE_BOOL:
+		if (val.vbool &&
+		    nla_put_flag(msg, DEVLINK_ATTR_PARAM_VALUE_DATA))
+			goto value_nest_cancel;
+		break;
+	}
+
+	nla_nest_end(msg, param_value_attr);
+	return 0;
+
+value_nest_cancel:
+	nla_nest_cancel(msg, param_value_attr);
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
+				 unsigned int port_index,
+				 struct devlink_param_item *param_item,
+				 enum devlink_command cmd,
+				 u32 portid, u32 seq, int flags)
+{
+	union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1];
+	bool param_value_set[DEVLINK_PARAM_CMODE_MAX + 1] = {};
+	const struct devlink_param *param = param_item->param;
+	struct devlink_param_gset_ctx ctx;
+	struct nlattr *param_values_list;
+	struct nlattr *param_attr;
+	int nla_type;
+	void *hdr;
+	int err;
+	int i;
+
+	/* Get value from driver part to driverinit configuration mode */
+	for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) {
+		if (!devlink_param_cmode_is_supported(param, i))
+			continue;
+		if (i == DEVLINK_PARAM_CMODE_DRIVERINIT) {
+			if (param_item->driverinit_value_new_valid)
+				param_value[i] = param_item->driverinit_value_new;
+			else if (param_item->driverinit_value_valid)
+				param_value[i] = param_item->driverinit_value;
+			else
+				return -EOPNOTSUPP;
+		} else {
+			ctx.cmode = i;
+			err = devlink_param_get(devlink, param, &ctx);
+			if (err)
+				return err;
+			param_value[i] = ctx.val;
+		}
+		param_value_set[i] = true;
+	}
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto genlmsg_cancel;
+
+	if (cmd == DEVLINK_CMD_PORT_PARAM_GET ||
+	    cmd == DEVLINK_CMD_PORT_PARAM_NEW ||
+	    cmd == DEVLINK_CMD_PORT_PARAM_DEL)
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index))
+			goto genlmsg_cancel;
+
+	param_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PARAM);
+	if (!param_attr)
+		goto genlmsg_cancel;
+	if (nla_put_string(msg, DEVLINK_ATTR_PARAM_NAME, param->name))
+		goto param_nest_cancel;
+	if (param->generic && nla_put_flag(msg, DEVLINK_ATTR_PARAM_GENERIC))
+		goto param_nest_cancel;
+
+	nla_type = devlink_param_type_to_nla_type(param->type);
+	if (nla_type < 0)
+		goto param_nest_cancel;
+	if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type))
+		goto param_nest_cancel;
+
+	param_values_list = nla_nest_start_noflag(msg,
+						  DEVLINK_ATTR_PARAM_VALUES_LIST);
+	if (!param_values_list)
+		goto param_nest_cancel;
+
+	for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) {
+		if (!param_value_set[i])
+			continue;
+		err = devlink_nl_param_value_fill_one(msg, param->type,
+						      i, param_value[i]);
+		if (err)
+			goto values_list_nest_cancel;
+	}
+
+	nla_nest_end(msg, param_values_list);
+	nla_nest_end(msg, param_attr);
+	genlmsg_end(msg, hdr);
+	return 0;
+
+values_list_nest_cancel:
+	nla_nest_end(msg, param_values_list);
+param_nest_cancel:
+	nla_nest_cancel(msg, param_attr);
+genlmsg_cancel:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static void devlink_param_notify(struct devlink *devlink,
+				 unsigned int port_index,
+				 struct devlink_param_item *param_item,
+				 enum devlink_command cmd)
+{
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL &&
+		cmd != DEVLINK_CMD_PORT_PARAM_NEW &&
+		cmd != DEVLINK_CMD_PORT_PARAM_DEL);
+
+	/* devlink_notify_register() / devlink_notify_unregister()
+	 * will replay the notifications if the params are added/removed
+	 * outside of the lifetime of the instance.
+	 */
+	if (!devl_is_registered(devlink))
+		return;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+	err = devlink_nl_param_fill(msg, devlink, port_index, param_item, cmd,
+				    0, 0, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static void devlink_params_notify(struct devlink *devlink,
+				  enum devlink_command cmd)
+{
+	struct devlink_param_item *param_item;
+	unsigned long param_id;
+
+	xa_for_each(&devlink->params, param_id, param_item)
+		devlink_param_notify(devlink, 0, param_item, cmd);
+}
+
+void devlink_params_notify_register(struct devlink *devlink)
+{
+	devlink_params_notify(devlink, DEVLINK_CMD_PARAM_NEW);
+}
+
+void devlink_params_notify_unregister(struct devlink *devlink)
+{
+	devlink_params_notify(devlink, DEVLINK_CMD_PARAM_DEL);
+}
+
+static int devlink_nl_param_get_dump_one(struct sk_buff *msg,
+					 struct devlink *devlink,
+					 struct netlink_callback *cb,
+					 int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_param_item *param_item;
+	unsigned long param_id;
+	int err = 0;
+
+	xa_for_each_start(&devlink->params, param_id, param_item, state->idx) {
+		err = devlink_nl_param_fill(msg, devlink, 0, param_item,
+					    DEVLINK_CMD_PARAM_GET,
+					    NETLINK_CB(cb->skb).portid,
+					    cb->nlh->nlmsg_seq, flags);
+		if (err == -EOPNOTSUPP) {
+			err = 0;
+		} else if (err) {
+			state->idx = param_id;
+			break;
+		}
+	}
+
+	return err;
+}
+
+int devlink_nl_param_get_dumpit(struct sk_buff *skb,
+				struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_param_get_dump_one);
+}
+
+static int
+devlink_param_type_get_from_info(struct genl_info *info,
+				 enum devlink_param_type *param_type)
+{
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_TYPE))
+		return -EINVAL;
+
+	switch (nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_TYPE])) {
+	case NLA_U8:
+		*param_type = DEVLINK_PARAM_TYPE_U8;
+		break;
+	case NLA_U16:
+		*param_type = DEVLINK_PARAM_TYPE_U16;
+		break;
+	case NLA_U32:
+		*param_type = DEVLINK_PARAM_TYPE_U32;
+		break;
+	case NLA_STRING:
+		*param_type = DEVLINK_PARAM_TYPE_STRING;
+		break;
+	case NLA_FLAG:
+		*param_type = DEVLINK_PARAM_TYPE_BOOL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+devlink_param_value_get_from_info(const struct devlink_param *param,
+				  struct genl_info *info,
+				  union devlink_param_value *value)
+{
+	struct nlattr *param_data;
+	int len;
+
+	param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA];
+
+	if (param->type != DEVLINK_PARAM_TYPE_BOOL && !param_data)
+		return -EINVAL;
+
+	switch (param->type) {
+	case DEVLINK_PARAM_TYPE_U8:
+		if (nla_len(param_data) != sizeof(u8))
+			return -EINVAL;
+		value->vu8 = nla_get_u8(param_data);
+		break;
+	case DEVLINK_PARAM_TYPE_U16:
+		if (nla_len(param_data) != sizeof(u16))
+			return -EINVAL;
+		value->vu16 = nla_get_u16(param_data);
+		break;
+	case DEVLINK_PARAM_TYPE_U32:
+		if (nla_len(param_data) != sizeof(u32))
+			return -EINVAL;
+		value->vu32 = nla_get_u32(param_data);
+		break;
+	case DEVLINK_PARAM_TYPE_STRING:
+		len = strnlen(nla_data(param_data), nla_len(param_data));
+		if (len == nla_len(param_data) ||
+		    len >= __DEVLINK_PARAM_MAX_STRING_VALUE)
+			return -EINVAL;
+		strcpy(value->vstr, nla_data(param_data));
+		break;
+	case DEVLINK_PARAM_TYPE_BOOL:
+		if (param_data && nla_len(param_data))
+			return -EINVAL;
+		value->vbool = nla_get_flag(param_data);
+		break;
+	}
+	return 0;
+}
+
+static struct devlink_param_item *
+devlink_param_get_from_info(struct xarray *params, struct genl_info *info)
+{
+	char *param_name;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_NAME))
+		return NULL;
+
+	param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]);
+	return devlink_param_find_by_name(params, param_name);
+}
+
+int devlink_nl_param_get_doit(struct sk_buff *skb,
+			      struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_param_item *param_item;
+	struct sk_buff *msg;
+	int err;
+
+	param_item = devlink_param_get_from_info(&devlink->params, info);
+	if (!param_item)
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_param_fill(msg, devlink, 0, param_item,
+				    DEVLINK_CMD_PARAM_GET,
+				    info->snd_portid, info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink,
+					   unsigned int port_index,
+					   struct xarray *params,
+					   struct genl_info *info,
+					   enum devlink_command cmd)
+{
+	enum devlink_param_type param_type;
+	struct devlink_param_gset_ctx ctx;
+	enum devlink_param_cmode cmode;
+	struct devlink_param_item *param_item;
+	const struct devlink_param *param;
+	union devlink_param_value value;
+	int err = 0;
+
+	param_item = devlink_param_get_from_info(params, info);
+	if (!param_item)
+		return -EINVAL;
+	param = param_item->param;
+	err = devlink_param_type_get_from_info(info, &param_type);
+	if (err)
+		return err;
+	if (param_type != param->type)
+		return -EINVAL;
+	err = devlink_param_value_get_from_info(param, info, &value);
+	if (err)
+		return err;
+	if (param->validate) {
+		err = param->validate(devlink, param->id, value, info->extack);
+		if (err)
+			return err;
+	}
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_VALUE_CMODE))
+		return -EINVAL;
+	cmode = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_CMODE]);
+	if (!devlink_param_cmode_is_supported(param, cmode))
+		return -EOPNOTSUPP;
+
+	if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) {
+		param_item->driverinit_value_new = value;
+		param_item->driverinit_value_new_valid = true;
+	} else {
+		if (!param->set)
+			return -EOPNOTSUPP;
+		ctx.val = value;
+		ctx.cmode = cmode;
+		err = devlink_param_set(devlink, param, &ctx);
+		if (err)
+			return err;
+	}
+
+	devlink_param_notify(devlink, port_index, param_item, cmd);
+	return 0;
+}
+
+int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+
+	return __devlink_nl_cmd_param_set_doit(devlink, 0, &devlink->params,
+					       info, DEVLINK_CMD_PARAM_NEW);
+}
+
+int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg,
+					 struct netlink_callback *cb)
+{
+	NL_SET_ERR_MSG(cb->extack, "Port params are not supported");
+	return msg->len;
+}
+
+int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb,
+				       struct genl_info *info)
+{
+	NL_SET_ERR_MSG(info->extack, "Port params are not supported");
+	return -EINVAL;
+}
+
+int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb,
+				       struct genl_info *info)
+{
+	NL_SET_ERR_MSG(info->extack, "Port params are not supported");
+	return -EINVAL;
+}
+
+static int devlink_param_verify(const struct devlink_param *param)
+{
+	if (!param || !param->name || !param->supported_cmodes)
+		return -EINVAL;
+	if (param->generic)
+		return devlink_param_generic_verify(param);
+	else
+		return devlink_param_driver_verify(param);
+}
+
+static int devlink_param_register(struct devlink *devlink,
+				  const struct devlink_param *param)
+{
+	struct devlink_param_item *param_item;
+	int err;
+
+	WARN_ON(devlink_param_verify(param));
+	WARN_ON(devlink_param_find_by_name(&devlink->params, param->name));
+
+	if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT))
+		WARN_ON(param->get || param->set);
+	else
+		WARN_ON(!param->get || !param->set);
+
+	param_item = kzalloc(sizeof(*param_item), GFP_KERNEL);
+	if (!param_item)
+		return -ENOMEM;
+
+	param_item->param = param;
+
+	err = xa_insert(&devlink->params, param->id, param_item, GFP_KERNEL);
+	if (err)
+		goto err_xa_insert;
+
+	devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW);
+	return 0;
+
+err_xa_insert:
+	kfree(param_item);
+	return err;
+}
+
+static void devlink_param_unregister(struct devlink *devlink,
+				     const struct devlink_param *param)
+{
+	struct devlink_param_item *param_item;
+
+	param_item = devlink_param_find_by_id(&devlink->params, param->id);
+	if (WARN_ON(!param_item))
+		return;
+	devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_DEL);
+	xa_erase(&devlink->params, param->id);
+	kfree(param_item);
+}
+
+/**
+ *	devl_params_register - register configuration parameters
+ *
+ *	@devlink: devlink
+ *	@params: configuration parameters array
+ *	@params_count: number of parameters provided
+ *
+ *	Register the configuration parameters supported by the driver.
+ */
+int devl_params_register(struct devlink *devlink,
+			 const struct devlink_param *params,
+			 size_t params_count)
+{
+	const struct devlink_param *param = params;
+	int i, err;
+
+	lockdep_assert_held(&devlink->lock);
+
+	for (i = 0; i < params_count; i++, param++) {
+		err = devlink_param_register(devlink, param);
+		if (err)
+			goto rollback;
+	}
+	return 0;
+
+rollback:
+	if (!i)
+		return err;
+
+	for (param--; i > 0; i--, param--)
+		devlink_param_unregister(devlink, param);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devl_params_register);
+
+int devlink_params_register(struct devlink *devlink,
+			    const struct devlink_param *params,
+			    size_t params_count)
+{
+	int err;
+
+	devl_lock(devlink);
+	err = devl_params_register(devlink, params, params_count);
+	devl_unlock(devlink);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devlink_params_register);
+
+/**
+ *	devl_params_unregister - unregister configuration parameters
+ *	@devlink: devlink
+ *	@params: configuration parameters to unregister
+ *	@params_count: number of parameters provided
+ */
+void devl_params_unregister(struct devlink *devlink,
+			    const struct devlink_param *params,
+			    size_t params_count)
+{
+	const struct devlink_param *param = params;
+	int i;
+
+	lockdep_assert_held(&devlink->lock);
+
+	for (i = 0; i < params_count; i++, param++)
+		devlink_param_unregister(devlink, param);
+}
+EXPORT_SYMBOL_GPL(devl_params_unregister);
+
+void devlink_params_unregister(struct devlink *devlink,
+			       const struct devlink_param *params,
+			       size_t params_count)
+{
+	devl_lock(devlink);
+	devl_params_unregister(devlink, params, params_count);
+	devl_unlock(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_params_unregister);
+
+/**
+ *	devl_param_driverinit_value_get - get configuration parameter
+ *					  value for driver initializing
+ *
+ *	@devlink: devlink
+ *	@param_id: parameter ID
+ *	@val: pointer to store the value of parameter in driverinit
+ *	      configuration mode
+ *
+ *	This function should be used by the driver to get driverinit
+ *	configuration for initialization after reload command.
+ *
+ *	Note that lockless call of this function relies on the
+ *	driver to maintain following basic sane behavior:
+ *	1) Driver ensures a call to this function cannot race with
+ *	   registering/unregistering the parameter with the same parameter ID.
+ *	2) Driver ensures a call to this function cannot race with
+ *	   devl_param_driverinit_value_set() call with the same parameter ID.
+ *	3) Driver ensures a call to this function cannot race with
+ *	   reload operation.
+ *	If the driver is not able to comply, it has to take the devlink->lock
+ *	while calling this.
+ */
+int devl_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
+				    union devlink_param_value *val)
+{
+	struct devlink_param_item *param_item;
+
+	if (WARN_ON(!devlink_reload_supported(devlink->ops)))
+		return -EOPNOTSUPP;
+
+	param_item = devlink_param_find_by_id(&devlink->params, param_id);
+	if (!param_item)
+		return -EINVAL;
+
+	if (!param_item->driverinit_value_valid)
+		return -EOPNOTSUPP;
+
+	if (WARN_ON(!devlink_param_cmode_is_supported(param_item->param,
+						      DEVLINK_PARAM_CMODE_DRIVERINIT)))
+		return -EOPNOTSUPP;
+
+	*val = param_item->driverinit_value;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devl_param_driverinit_value_get);
+
+/**
+ *	devl_param_driverinit_value_set - set value of configuration
+ *					  parameter for driverinit
+ *					  configuration mode
+ *
+ *	@devlink: devlink
+ *	@param_id: parameter ID
+ *	@init_val: value of parameter to set for driverinit configuration mode
+ *
+ *	This function should be used by the driver to set driverinit
+ *	configuration mode default value.
+ */
+void devl_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
+				     union devlink_param_value init_val)
+{
+	struct devlink_param_item *param_item;
+
+	devl_assert_locked(devlink);
+
+	param_item = devlink_param_find_by_id(&devlink->params, param_id);
+	if (WARN_ON(!param_item))
+		return;
+
+	if (WARN_ON(!devlink_param_cmode_is_supported(param_item->param,
+						      DEVLINK_PARAM_CMODE_DRIVERINIT)))
+		return;
+
+	param_item->driverinit_value = init_val;
+	param_item->driverinit_value_valid = true;
+
+	devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW);
+}
+EXPORT_SYMBOL_GPL(devl_param_driverinit_value_set);
+
+void devlink_params_driverinit_load_new(struct devlink *devlink)
+{
+	struct devlink_param_item *param_item;
+	unsigned long param_id;
+
+	xa_for_each(&devlink->params, param_id, param_item) {
+		if (!devlink_param_cmode_is_supported(param_item->param,
+						      DEVLINK_PARAM_CMODE_DRIVERINIT) ||
+		    !param_item->driverinit_value_new_valid)
+			continue;
+		param_item->driverinit_value = param_item->driverinit_value_new;
+		param_item->driverinit_value_valid = true;
+		param_item->driverinit_value_new_valid = false;
+	}
+}
+
+/**
+ *	devl_param_value_changed - notify devlink on a parameter's value
+ *				   change. Should be called by the driver
+ *				   right after the change.
+ *
+ *	@devlink: devlink
+ *	@param_id: parameter ID
+ *
+ *	This function should be used by the driver to notify devlink on value
+ *	change, excluding driverinit configuration mode.
+ *	For driverinit configuration mode driver should use the function
+ */
+void devl_param_value_changed(struct devlink *devlink, u32 param_id)
+{
+	struct devlink_param_item *param_item;
+
+	param_item = devlink_param_find_by_id(&devlink->params, param_id);
+	WARN_ON(!param_item);
+
+	devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW);
+}
+EXPORT_SYMBOL_GPL(devl_param_value_changed);
-- 
GitLab


From 1aa47ca1f52ee4ef5f553e7ee8fb6749b6c96b9f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:50 +0200
Subject: [PATCH 1795/1806] devlink: push region related code into separate
 file

Cut out another chunk from leftover.c and put region related code
into a separate file.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-9-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/Makefile        |    2 +-
 net/devlink/devl_internal.h |    6 +
 net/devlink/leftover.c      | 1506 +++--------------------------------
 net/devlink/region.c        | 1260 +++++++++++++++++++++++++++++
 4 files changed, 1392 insertions(+), 1382 deletions(-)
 create mode 100644 net/devlink/region.c

diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index c4b29f603a1f2..744f64e467b74 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o sb.o dpipe.o \
-	 resource.o param.o health.o
+	 resource.o param.o region.o health.o
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index e0304d6079786..32b66233240fe 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -158,6 +158,8 @@ void devlink_ports_notify_register(struct devlink *devlink);
 void devlink_ports_notify_unregister(struct devlink *devlink);
 void devlink_params_notify_register(struct devlink *devlink);
 void devlink_params_notify_unregister(struct devlink *devlink);
+void devlink_regions_notify_register(struct devlink *devlink);
+void devlink_regions_notify_unregister(struct devlink *devlink);
 
 /* Ports */
 #define ASSERT_DEVLINK_PORT_INITIALIZED(devlink_port)				\
@@ -249,6 +251,10 @@ int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb,
 				       struct genl_info *info);
 int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb,
 				       struct genl_info *info);
+int devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_region_del(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
+				      struct netlink_callback *cb);
 int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 					    struct genl_info *info);
 int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 2f1dfd27d1c87..6d31aaee8ce8c 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -151,68 +151,6 @@ devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info)
 	return devlink_linecard_get_from_attrs(devlink, info->attrs);
 }
 
-struct devlink_region {
-	struct devlink *devlink;
-	struct devlink_port *port;
-	struct list_head list;
-	union {
-		const struct devlink_region_ops *ops;
-		const struct devlink_port_region_ops *port_ops;
-	};
-	struct mutex snapshot_lock; /* protects snapshot_list,
-				     * max_snapshots and cur_snapshots
-				     * consistency.
-				     */
-	struct list_head snapshot_list;
-	u32 max_snapshots;
-	u32 cur_snapshots;
-	u64 size;
-};
-
-struct devlink_snapshot {
-	struct list_head list;
-	struct devlink_region *region;
-	u8 *data;
-	u32 id;
-};
-
-static struct devlink_region *
-devlink_region_get_by_name(struct devlink *devlink, const char *region_name)
-{
-	struct devlink_region *region;
-
-	list_for_each_entry(region, &devlink->region_list, list)
-		if (!strcmp(region->ops->name, region_name))
-			return region;
-
-	return NULL;
-}
-
-static struct devlink_region *
-devlink_port_region_get_by_name(struct devlink_port *port,
-				const char *region_name)
-{
-	struct devlink_region *region;
-
-	list_for_each_entry(region, &port->region_list, list)
-		if (!strcmp(region->ops->name, region_name))
-			return region;
-
-	return NULL;
-}
-
-static struct devlink_snapshot *
-devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
-{
-	struct devlink_snapshot *snapshot;
-
-	list_for_each_entry(snapshot, &region->snapshot_list, list)
-		if (snapshot->id == id)
-			return snapshot;
-
-	return NULL;
-}
-
 static int devlink_nl_put_nested_handle(struct sk_buff *msg, struct devlink *devlink)
 {
 	struct nlattr *nested_attr;
@@ -909,1125 +847,156 @@ static int devlink_linecard_type_set(struct devlink_linecard *linecard,
 	struct devlink_linecard_type *linecard_type;
 	int err;
 
-	mutex_lock(&linecard->state_lock);
-	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
-		err = -EBUSY;
-		goto out;
-	}
-	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
-		err = -EBUSY;
-		goto out;
-	}
-
-	linecard_type = devlink_linecard_type_lookup(linecard, type);
-	if (!linecard_type) {
-		NL_SET_ERR_MSG(extack, "Unsupported line card type provided");
-		err = -EINVAL;
-		goto out;
-	}
-
-	if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED &&
-	    linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
-		NL_SET_ERR_MSG(extack, "Line card already provisioned");
-		err = -EBUSY;
-		/* Check if the line card is provisioned in the same
-		 * way the user asks. In case it is, make the operation
-		 * to return success.
-		 */
-		if (ops->same_provision &&
-		    ops->same_provision(linecard, linecard->priv,
-					linecard_type->type,
-					linecard_type->priv))
-			err = 0;
-		goto out;
-	}
-
-	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING;
-	linecard->type = linecard_type->type;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-	err = ops->provision(linecard, linecard->priv, linecard_type->type,
-			     linecard_type->priv, extack);
-	if (err) {
-		/* Provisioning failed. Assume the linecard is unprovisioned
-		 * for future operations.
-		 */
-		mutex_lock(&linecard->state_lock);
-		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-		linecard->type = NULL;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		mutex_unlock(&linecard->state_lock);
-	}
-	return err;
-
-out:
-	mutex_unlock(&linecard->state_lock);
-	return err;
-}
-
-static int devlink_linecard_type_unset(struct devlink_linecard *linecard,
-				       struct netlink_ext_ack *extack)
-{
-	int err;
-
-	mutex_lock(&linecard->state_lock);
-	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
-		err = -EBUSY;
-		goto out;
-	}
-	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
-		err = -EBUSY;
-		goto out;
-	}
-	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
-		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-		linecard->type = NULL;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		err = 0;
-		goto out;
-	}
-
-	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) {
-		NL_SET_ERR_MSG(extack, "Line card is not provisioned");
-		err = 0;
-		goto out;
-	}
-	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-	err = linecard->ops->unprovision(linecard, linecard->priv,
-					 extack);
-	if (err) {
-		/* Unprovisioning failed. Assume the linecard is unprovisioned
-		 * for future operations.
-		 */
-		mutex_lock(&linecard->state_lock);
-		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-		linecard->type = NULL;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		mutex_unlock(&linecard->state_lock);
-	}
-	return err;
-
-out:
-	mutex_unlock(&linecard->state_lock);
-	return err;
-}
-
-static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb,
-					    struct genl_info *info)
-{
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_linecard *linecard;
-	int err;
-
-	linecard = devlink_linecard_get_from_info(devlink, info);
-	if (IS_ERR(linecard))
-		return PTR_ERR(linecard);
-
-	if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) {
-		const char *type;
-
-		type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]);
-		if (strcmp(type, "")) {
-			err = devlink_linecard_type_set(linecard, type, extack);
-			if (err)
-				return err;
-		} else {
-			err = devlink_linecard_type_unset(linecard, extack);
-			if (err)
-				return err;
-		}
-	}
-
-	return 0;
-}
-
-int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
-			     struct netlink_ext_ack *extack)
-{
-	struct devlink_rate *devlink_rate;
-
-	list_for_each_entry(devlink_rate, &devlink->rate_list, list)
-		if (devlink_rate_is_node(devlink_rate)) {
-			NL_SET_ERR_MSG(extack, "Rate node(s) exists.");
-			return -EBUSY;
-		}
-	return 0;
-}
-
-static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg,
-					     struct devlink *devlink,
-					     struct devlink_snapshot *snapshot)
-{
-	struct nlattr *snap_attr;
-	int err;
-
-	snap_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOT);
-	if (!snap_attr)
-		return -EINVAL;
-
-	err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id);
-	if (err)
-		goto nla_put_failure;
-
-	nla_nest_end(msg, snap_attr);
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(msg, snap_attr);
-	return err;
-}
-
-static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg,
-					      struct devlink *devlink,
-					      struct devlink_region *region)
-{
-	struct devlink_snapshot *snapshot;
-	struct nlattr *snapshots_attr;
-	int err;
-
-	snapshots_attr = nla_nest_start_noflag(msg,
-					       DEVLINK_ATTR_REGION_SNAPSHOTS);
-	if (!snapshots_attr)
-		return -EINVAL;
-
-	list_for_each_entry(snapshot, &region->snapshot_list, list) {
-		err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot);
-		if (err)
-			goto nla_put_failure;
-	}
-
-	nla_nest_end(msg, snapshots_attr);
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(msg, snapshots_attr);
-	return err;
-}
-
-static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
-				  enum devlink_command cmd, u32 portid,
-				  u32 seq, int flags,
-				  struct devlink_region *region)
-{
-	void *hdr;
-	int err;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	err = devlink_nl_put_handle(msg, devlink);
-	if (err)
-		goto nla_put_failure;
-
-	if (region->port) {
-		err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
-				  region->port->index);
-		if (err)
-			goto nla_put_failure;
-	}
-
-	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name);
-	if (err)
-		goto nla_put_failure;
-
-	err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE,
-				region->size,
-				DEVLINK_ATTR_PAD);
-	if (err)
-		goto nla_put_failure;
-
-	err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS,
-			  region->max_snapshots);
-	if (err)
-		goto nla_put_failure;
-
-	err = devlink_nl_region_snapshots_id_put(msg, devlink, region);
-	if (err)
-		goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-	return 0;
-
-nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	return err;
-}
-
-static struct sk_buff *
-devlink_nl_region_notify_build(struct devlink_region *region,
-			       struct devlink_snapshot *snapshot,
-			       enum devlink_command cmd, u32 portid, u32 seq)
-{
-	struct devlink *devlink = region->devlink;
-	struct sk_buff *msg;
-	void *hdr;
-	int err;
-
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return ERR_PTR(-ENOMEM);
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, 0, cmd);
-	if (!hdr) {
-		err = -EMSGSIZE;
-		goto out_free_msg;
-	}
-
-	err = devlink_nl_put_handle(msg, devlink);
-	if (err)
-		goto out_cancel_msg;
-
-	if (region->port) {
-		err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
-				  region->port->index);
-		if (err)
-			goto out_cancel_msg;
-	}
-
-	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME,
-			     region->ops->name);
-	if (err)
-		goto out_cancel_msg;
-
-	if (snapshot) {
-		err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID,
-				  snapshot->id);
-		if (err)
-			goto out_cancel_msg;
-	} else {
-		err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE,
-					region->size, DEVLINK_ATTR_PAD);
-		if (err)
-			goto out_cancel_msg;
-	}
-	genlmsg_end(msg, hdr);
-
-	return msg;
-
-out_cancel_msg:
-	genlmsg_cancel(msg, hdr);
-out_free_msg:
-	nlmsg_free(msg);
-	return ERR_PTR(err);
-}
-
-static void devlink_nl_region_notify(struct devlink_region *region,
-				     struct devlink_snapshot *snapshot,
-				     enum devlink_command cmd)
-{
-	struct devlink *devlink = region->devlink;
-	struct sk_buff *msg;
-
-	WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
-		return;
-
-	msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0);
-	if (IS_ERR(msg))
-		return;
-
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
-}
-
-static void devlink_regions_notify_register(struct devlink *devlink)
-{
-	struct devlink_region *region;
-
-	list_for_each_entry(region, &devlink->region_list, list)
-		devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
-}
-
-static void devlink_regions_notify_unregister(struct devlink *devlink)
-{
-	struct devlink_region *region;
-
-	list_for_each_entry_reverse(region, &devlink->region_list, list)
-		devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL);
-}
-
-/**
- * __devlink_snapshot_id_increment - Increment number of snapshots using an id
- *	@devlink: devlink instance
- *	@id: the snapshot id
- *
- *	Track when a new snapshot begins using an id. Load the count for the
- *	given id from the snapshot xarray, increment it, and store it back.
- *
- *	Called when a new snapshot is created with the given id.
- *
- *	The id *must* have been previously allocated by
- *	devlink_region_snapshot_id_get().
- *
- *	Returns 0 on success, or an error on failure.
- */
-static int __devlink_snapshot_id_increment(struct devlink *devlink, u32 id)
-{
-	unsigned long count;
-	void *p;
-	int err;
-
-	xa_lock(&devlink->snapshot_ids);
-	p = xa_load(&devlink->snapshot_ids, id);
-	if (WARN_ON(!p)) {
-		err = -EINVAL;
-		goto unlock;
-	}
-
-	if (WARN_ON(!xa_is_value(p))) {
-		err = -EINVAL;
-		goto unlock;
-	}
-
-	count = xa_to_value(p);
-	count++;
-
-	err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(count),
-				GFP_ATOMIC));
-unlock:
-	xa_unlock(&devlink->snapshot_ids);
-	return err;
-}
-
-/**
- * __devlink_snapshot_id_decrement - Decrease number of snapshots using an id
- *	@devlink: devlink instance
- *	@id: the snapshot id
- *
- *	Track when a snapshot is deleted and stops using an id. Load the count
- *	for the given id from the snapshot xarray, decrement it, and store it
- *	back.
- *
- *	If the count reaches zero, erase this id from the xarray, freeing it
- *	up for future re-use by devlink_region_snapshot_id_get().
- *
- *	Called when a snapshot using the given id is deleted, and when the
- *	initial allocator of the id is finished using it.
- */
-static void __devlink_snapshot_id_decrement(struct devlink *devlink, u32 id)
-{
-	unsigned long count;
-	void *p;
-
-	xa_lock(&devlink->snapshot_ids);
-	p = xa_load(&devlink->snapshot_ids, id);
-	if (WARN_ON(!p))
-		goto unlock;
-
-	if (WARN_ON(!xa_is_value(p)))
-		goto unlock;
-
-	count = xa_to_value(p);
-
-	if (count > 1) {
-		count--;
-		__xa_store(&devlink->snapshot_ids, id, xa_mk_value(count),
-			   GFP_ATOMIC);
-	} else {
-		/* If this was the last user, we can erase this id */
-		__xa_erase(&devlink->snapshot_ids, id);
-	}
-unlock:
-	xa_unlock(&devlink->snapshot_ids);
-}
-
-/**
- *	__devlink_snapshot_id_insert - Insert a specific snapshot ID
- *	@devlink: devlink instance
- *	@id: the snapshot id
- *
- *	Mark the given snapshot id as used by inserting a zero value into the
- *	snapshot xarray.
- *
- *	This must be called while holding the devlink instance lock. Unlike
- *	devlink_snapshot_id_get, the initial reference count is zero, not one.
- *	It is expected that the id will immediately be used before
- *	releasing the devlink instance lock.
- *
- *	Returns zero on success, or an error code if the snapshot id could not
- *	be inserted.
- */
-static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id)
-{
-	int err;
-
-	xa_lock(&devlink->snapshot_ids);
-	if (xa_load(&devlink->snapshot_ids, id)) {
-		xa_unlock(&devlink->snapshot_ids);
-		return -EEXIST;
-	}
-	err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(0),
-				GFP_ATOMIC));
-	xa_unlock(&devlink->snapshot_ids);
-	return err;
-}
-
-/**
- *	__devlink_region_snapshot_id_get - get snapshot ID
- *	@devlink: devlink instance
- *	@id: storage to return snapshot id
- *
- *	Allocates a new snapshot id. Returns zero on success, or a negative
- *	error on failure. Must be called while holding the devlink instance
- *	lock.
- *
- *	Snapshot IDs are tracked using an xarray which stores the number of
- *	users of the snapshot id.
- *
- *	Note that the caller of this function counts as a 'user', in order to
- *	avoid race conditions. The caller must release its hold on the
- *	snapshot by using devlink_region_snapshot_id_put.
- */
-static int __devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id)
-{
-	return xa_alloc(&devlink->snapshot_ids, id, xa_mk_value(1),
-			xa_limit_32b, GFP_KERNEL);
-}
-
-/**
- *	__devlink_region_snapshot_create - create a new snapshot
- *	This will add a new snapshot of a region. The snapshot
- *	will be stored on the region struct and can be accessed
- *	from devlink. This is useful for future analyses of snapshots.
- *	Multiple snapshots can be created on a region.
- *	The @snapshot_id should be obtained using the getter function.
- *
- *	Must be called only while holding the region snapshot lock.
- *
- *	@region: devlink region of the snapshot
- *	@data: snapshot data
- *	@snapshot_id: snapshot id to be created
- */
-static int
-__devlink_region_snapshot_create(struct devlink_region *region,
-				 u8 *data, u32 snapshot_id)
-{
-	struct devlink *devlink = region->devlink;
-	struct devlink_snapshot *snapshot;
-	int err;
-
-	lockdep_assert_held(&region->snapshot_lock);
-
-	/* check if region can hold one more snapshot */
-	if (region->cur_snapshots == region->max_snapshots)
-		return -ENOSPC;
-
-	if (devlink_region_snapshot_get_by_id(region, snapshot_id))
-		return -EEXIST;
-
-	snapshot = kzalloc(sizeof(*snapshot), GFP_KERNEL);
-	if (!snapshot)
-		return -ENOMEM;
-
-	err = __devlink_snapshot_id_increment(devlink, snapshot_id);
-	if (err)
-		goto err_snapshot_id_increment;
-
-	snapshot->id = snapshot_id;
-	snapshot->region = region;
-	snapshot->data = data;
-
-	list_add_tail(&snapshot->list, &region->snapshot_list);
-
-	region->cur_snapshots++;
-
-	devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW);
-	return 0;
-
-err_snapshot_id_increment:
-	kfree(snapshot);
-	return err;
-}
-
-static void devlink_region_snapshot_del(struct devlink_region *region,
-					struct devlink_snapshot *snapshot)
-{
-	struct devlink *devlink = region->devlink;
-
-	lockdep_assert_held(&region->snapshot_lock);
-
-	devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL);
-	region->cur_snapshots--;
-	list_del(&snapshot->list);
-	region->ops->destructor(snapshot->data);
-	__devlink_snapshot_id_decrement(devlink, snapshot->id);
-	kfree(snapshot);
-}
-
-int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_port *port = NULL;
-	struct devlink_region *region;
-	const char *region_name;
-	struct sk_buff *msg;
-	unsigned int index;
-	int err;
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME))
-		return -EINVAL;
-
-	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
-		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
-
-		port = devlink_port_get_by_index(devlink, index);
-		if (!port)
-			return -ENODEV;
-	}
-
-	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
-	if (port)
-		region = devlink_port_region_get_by_name(port, region_name);
-	else
-		region = devlink_region_get_by_name(devlink, region_name);
-
-	if (!region)
-		return -EINVAL;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET,
-				     info->snd_portid, info->snd_seq, 0,
-				     region);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
-
-	return genlmsg_reply(msg, info);
-}
-
-static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg,
-						 struct netlink_callback *cb,
-						 struct devlink_port *port,
-						 int *idx, int start, int flags)
-{
-	struct devlink_region *region;
-	int err = 0;
-
-	list_for_each_entry(region, &port->region_list, list) {
-		if (*idx < start) {
-			(*idx)++;
-			continue;
-		}
-		err = devlink_nl_region_fill(msg, port->devlink,
-					     DEVLINK_CMD_REGION_GET,
-					     NETLINK_CB(cb->skb).portid,
-					     cb->nlh->nlmsg_seq,
-					     flags, region);
-		if (err)
-			goto out;
-		(*idx)++;
-	}
-
-out:
-	return err;
-}
-
-static int devlink_nl_region_get_dump_one(struct sk_buff *msg,
-					  struct devlink *devlink,
-					  struct netlink_callback *cb,
-					  int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_region *region;
-	struct devlink_port *port;
-	unsigned long port_index;
-	int idx = 0;
-	int err;
-
-	list_for_each_entry(region, &devlink->region_list, list) {
-		if (idx < state->idx) {
-			idx++;
-			continue;
-		}
-		err = devlink_nl_region_fill(msg, devlink,
-					     DEVLINK_CMD_REGION_GET,
-					     NETLINK_CB(cb->skb).portid,
-					     cb->nlh->nlmsg_seq, flags,
-					     region);
-		if (err) {
-			state->idx = idx;
-			return err;
-		}
-		idx++;
-	}
-
-	xa_for_each(&devlink->ports, port_index, port) {
-		err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, &idx,
-							    state->idx, flags);
-		if (err) {
-			state->idx = idx;
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-int devlink_nl_region_get_dumpit(struct sk_buff *skb,
-				 struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_region_get_dump_one);
-}
-
-static int devlink_nl_cmd_region_del(struct sk_buff *skb,
-				     struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_snapshot *snapshot;
-	struct devlink_port *port = NULL;
-	struct devlink_region *region;
-	const char *region_name;
-	unsigned int index;
-	u32 snapshot_id;
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME) ||
-	    GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_SNAPSHOT_ID))
-		return -EINVAL;
-
-	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
-	snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
-
-	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
-		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
-
-		port = devlink_port_get_by_index(devlink, index);
-		if (!port)
-			return -ENODEV;
-	}
-
-	if (port)
-		region = devlink_port_region_get_by_name(port, region_name);
-	else
-		region = devlink_region_get_by_name(devlink, region_name);
-
-	if (!region)
-		return -EINVAL;
-
-	mutex_lock(&region->snapshot_lock);
-	snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id);
-	if (!snapshot) {
-		mutex_unlock(&region->snapshot_lock);
-		return -EINVAL;
-	}
-
-	devlink_region_snapshot_del(region, snapshot);
-	mutex_unlock(&region->snapshot_lock);
-	return 0;
-}
-
-static int
-devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_snapshot *snapshot;
-	struct devlink_port *port = NULL;
-	struct nlattr *snapshot_id_attr;
-	struct devlink_region *region;
-	const char *region_name;
-	unsigned int index;
-	u32 snapshot_id;
-	u8 *data;
-	int err;
-
-	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) {
-		NL_SET_ERR_MSG(info->extack, "No region name provided");
-		return -EINVAL;
-	}
-
-	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
-
-	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
-		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
-
-		port = devlink_port_get_by_index(devlink, index);
-		if (!port)
-			return -ENODEV;
-	}
-
-	if (port)
-		region = devlink_port_region_get_by_name(port, region_name);
-	else
-		region = devlink_region_get_by_name(devlink, region_name);
-
-	if (!region) {
-		NL_SET_ERR_MSG(info->extack, "The requested region does not exist");
-		return -EINVAL;
-	}
-
-	if (!region->ops->snapshot) {
-		NL_SET_ERR_MSG(info->extack, "The requested region does not support taking an immediate snapshot");
-		return -EOPNOTSUPP;
-	}
-
-	mutex_lock(&region->snapshot_lock);
-
-	if (region->cur_snapshots == region->max_snapshots) {
-		NL_SET_ERR_MSG(info->extack, "The region has reached the maximum number of stored snapshots");
-		err = -ENOSPC;
-		goto unlock;
-	}
-
-	snapshot_id_attr = info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID];
-	if (snapshot_id_attr) {
-		snapshot_id = nla_get_u32(snapshot_id_attr);
-
-		if (devlink_region_snapshot_get_by_id(region, snapshot_id)) {
-			NL_SET_ERR_MSG(info->extack, "The requested snapshot id is already in use");
-			err = -EEXIST;
-			goto unlock;
-		}
-
-		err = __devlink_snapshot_id_insert(devlink, snapshot_id);
-		if (err)
-			goto unlock;
-	} else {
-		err = __devlink_region_snapshot_id_get(devlink, &snapshot_id);
-		if (err) {
-			NL_SET_ERR_MSG(info->extack, "Failed to allocate a new snapshot id");
-			goto unlock;
-		}
-	}
-
-	if (port)
-		err = region->port_ops->snapshot(port, region->port_ops,
-						 info->extack, &data);
-	else
-		err = region->ops->snapshot(devlink, region->ops,
-					    info->extack, &data);
-	if (err)
-		goto err_snapshot_capture;
-
-	err = __devlink_region_snapshot_create(region, data, snapshot_id);
-	if (err)
-		goto err_snapshot_create;
-
-	if (!snapshot_id_attr) {
-		struct sk_buff *msg;
-
-		snapshot = devlink_region_snapshot_get_by_id(region,
-							     snapshot_id);
-		if (WARN_ON(!snapshot)) {
-			err = -EINVAL;
-			goto unlock;
-		}
-
-		msg = devlink_nl_region_notify_build(region, snapshot,
-						     DEVLINK_CMD_REGION_NEW,
-						     info->snd_portid,
-						     info->snd_seq);
-		err = PTR_ERR_OR_ZERO(msg);
-		if (err)
-			goto err_notify;
-
-		err = genlmsg_reply(msg, info);
-		if (err)
-			goto err_notify;
-	}
-
-	mutex_unlock(&region->snapshot_lock);
-	return 0;
-
-err_snapshot_create:
-	region->ops->destructor(data);
-err_snapshot_capture:
-	__devlink_snapshot_id_decrement(devlink, snapshot_id);
-	mutex_unlock(&region->snapshot_lock);
-	return err;
-
-err_notify:
-	devlink_region_snapshot_del(region, snapshot);
-unlock:
-	mutex_unlock(&region->snapshot_lock);
-	return err;
-}
-
-static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg,
-						 u8 *chunk, u32 chunk_size,
-						 u64 addr)
-{
-	struct nlattr *chunk_attr;
-	int err;
-
-	chunk_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_CHUNK);
-	if (!chunk_attr)
-		return -EINVAL;
-
-	err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk);
-	if (err)
-		goto nla_put_failure;
-
-	err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr,
-				DEVLINK_ATTR_PAD);
-	if (err)
-		goto nla_put_failure;
-
-	nla_nest_end(msg, chunk_attr);
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(msg, chunk_attr);
-	return err;
-}
-
-#define DEVLINK_REGION_READ_CHUNK_SIZE 256
-
-typedef int devlink_chunk_fill_t(void *cb_priv, u8 *chunk, u32 chunk_size,
-				 u64 curr_offset,
-				 struct netlink_ext_ack *extack);
-
-static int
-devlink_nl_region_read_fill(struct sk_buff *skb, devlink_chunk_fill_t *cb,
-			    void *cb_priv, u64 start_offset, u64 end_offset,
-			    u64 *new_offset, struct netlink_ext_ack *extack)
-{
-	u64 curr_offset = start_offset;
-	int err = 0;
-	u8 *data;
-
-	/* Allocate and re-use a single buffer */
-	data = kmalloc(DEVLINK_REGION_READ_CHUNK_SIZE, GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	*new_offset = start_offset;
-
-	while (curr_offset < end_offset) {
-		u32 data_size;
-
-		data_size = min_t(u32, end_offset - curr_offset,
-				  DEVLINK_REGION_READ_CHUNK_SIZE);
-
-		err = cb(cb_priv, data, data_size, curr_offset, extack);
-		if (err)
-			break;
-
-		err = devlink_nl_cmd_region_read_chunk_fill(skb, data, data_size, curr_offset);
-		if (err)
-			break;
-
-		curr_offset += data_size;
-	}
-	*new_offset = curr_offset;
-
-	kfree(data);
-
-	return err;
-}
-
-static int
-devlink_region_snapshot_fill(void *cb_priv, u8 *chunk, u32 chunk_size,
-			     u64 curr_offset,
-			     struct netlink_ext_ack __always_unused *extack)
-{
-	struct devlink_snapshot *snapshot = cb_priv;
-
-	memcpy(chunk, &snapshot->data[curr_offset], chunk_size);
-
-	return 0;
-}
-
-static int
-devlink_region_port_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size,
-				u64 curr_offset, struct netlink_ext_ack *extack)
-{
-	struct devlink_region *region = cb_priv;
-
-	return region->port_ops->read(region->port, region->port_ops, extack,
-				      curr_offset, chunk_size, chunk);
-}
-
-static int
-devlink_region_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size,
-			   u64 curr_offset, struct netlink_ext_ack *extack)
-{
-	struct devlink_region *region = cb_priv;
-
-	return region->ops->read(region->devlink, region->ops, extack,
-				 curr_offset, chunk_size, chunk);
-}
-
-static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
-					     struct netlink_callback *cb)
-{
-	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct nlattr *chunks_attr, *region_attr, *snapshot_attr;
-	u64 ret_offset, start_offset, end_offset = U64_MAX;
-	struct nlattr **attrs = info->info.attrs;
-	struct devlink_port *port = NULL;
-	devlink_chunk_fill_t *region_cb;
-	struct devlink_region *region;
-	const char *region_name;
-	struct devlink *devlink;
-	unsigned int index;
-	void *region_cb_priv;
-	void *hdr;
-	int err;
-
-	start_offset = state->start_offset;
-
-	devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs);
-	if (IS_ERR(devlink))
-		return PTR_ERR(devlink);
-
-	if (!attrs[DEVLINK_ATTR_REGION_NAME]) {
-		NL_SET_ERR_MSG(cb->extack, "No region name provided");
-		err = -EINVAL;
-		goto out_unlock;
-	}
-
-	if (attrs[DEVLINK_ATTR_PORT_INDEX]) {
-		index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]);
-
-		port = devlink_port_get_by_index(devlink, index);
-		if (!port) {
-			err = -ENODEV;
-			goto out_unlock;
-		}
+	mutex_lock(&linecard->state_lock);
+	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
+		err = -EBUSY;
+		goto out;
+	}
+	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
+		err = -EBUSY;
+		goto out;
 	}
 
-	region_attr = attrs[DEVLINK_ATTR_REGION_NAME];
-	region_name = nla_data(region_attr);
-
-	if (port)
-		region = devlink_port_region_get_by_name(port, region_name);
-	else
-		region = devlink_region_get_by_name(devlink, region_name);
-
-	if (!region) {
-		NL_SET_ERR_MSG_ATTR(cb->extack, region_attr, "Requested region does not exist");
+	linecard_type = devlink_linecard_type_lookup(linecard, type);
+	if (!linecard_type) {
+		NL_SET_ERR_MSG(extack, "Unsupported line card type provided");
 		err = -EINVAL;
-		goto out_unlock;
+		goto out;
 	}
 
-	snapshot_attr = attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID];
-	if (!snapshot_attr) {
-		if (!nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) {
-			NL_SET_ERR_MSG(cb->extack, "No snapshot id provided");
-			err = -EINVAL;
-			goto out_unlock;
-		}
+	if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED &&
+	    linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
+		NL_SET_ERR_MSG(extack, "Line card already provisioned");
+		err = -EBUSY;
+		/* Check if the line card is provisioned in the same
+		 * way the user asks. In case it is, make the operation
+		 * to return success.
+		 */
+		if (ops->same_provision &&
+		    ops->same_provision(linecard, linecard->priv,
+					linecard_type->type,
+					linecard_type->priv))
+			err = 0;
+		goto out;
+	}
 
-		if (!region->ops->read) {
-			NL_SET_ERR_MSG(cb->extack, "Requested region does not support direct read");
-			err = -EOPNOTSUPP;
-			goto out_unlock;
-		}
+	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING;
+	linecard->type = linecard_type->type;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+	err = ops->provision(linecard, linecard->priv, linecard_type->type,
+			     linecard_type->priv, extack);
+	if (err) {
+		/* Provisioning failed. Assume the linecard is unprovisioned
+		 * for future operations.
+		 */
+		mutex_lock(&linecard->state_lock);
+		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+		linecard->type = NULL;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+		mutex_unlock(&linecard->state_lock);
+	}
+	return err;
 
-		if (port)
-			region_cb = &devlink_region_port_direct_fill;
-		else
-			region_cb = &devlink_region_direct_fill;
-		region_cb_priv = region;
-	} else {
-		struct devlink_snapshot *snapshot;
-		u32 snapshot_id;
+out:
+	mutex_unlock(&linecard->state_lock);
+	return err;
+}
 
-		if (nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) {
-			NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Direct region read does not use snapshot");
-			err = -EINVAL;
-			goto out_unlock;
-		}
+static int devlink_linecard_type_unset(struct devlink_linecard *linecard,
+				       struct netlink_ext_ack *extack)
+{
+	int err;
 
-		snapshot_id = nla_get_u32(snapshot_attr);
-		snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id);
-		if (!snapshot) {
-			NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Requested snapshot does not exist");
-			err = -EINVAL;
-			goto out_unlock;
-		}
-		region_cb = &devlink_region_snapshot_fill;
-		region_cb_priv = snapshot;
+	mutex_lock(&linecard->state_lock);
+	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
+		err = -EBUSY;
+		goto out;
 	}
-
-	if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] &&
-	    attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) {
-		if (!start_offset)
-			start_offset =
-				nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
-
-		end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
-		end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
+	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
+		err = -EBUSY;
+		goto out;
 	}
-
-	if (end_offset > region->size)
-		end_offset = region->size;
-
-	/* return 0 if there is no further data to read */
-	if (start_offset == end_offset) {
+	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
+		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+		linecard->type = NULL;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
 		err = 0;
-		goto out_unlock;
+		goto out;
 	}
 
-	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
-			  &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI,
-			  DEVLINK_CMD_REGION_READ);
-	if (!hdr) {
-		err = -EMSGSIZE;
-		goto out_unlock;
+	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) {
+		NL_SET_ERR_MSG(extack, "Line card is not provisioned");
+		err = 0;
+		goto out;
 	}
-
-	err = devlink_nl_put_handle(skb, devlink);
-	if (err)
-		goto nla_put_failure;
-
-	if (region->port) {
-		err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX,
-				  region->port->index);
-		if (err)
-			goto nla_put_failure;
+	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+	err = linecard->ops->unprovision(linecard, linecard->priv,
+					 extack);
+	if (err) {
+		/* Unprovisioning failed. Assume the linecard is unprovisioned
+		 * for future operations.
+		 */
+		mutex_lock(&linecard->state_lock);
+		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+		linecard->type = NULL;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+		mutex_unlock(&linecard->state_lock);
 	}
+	return err;
 
-	err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name);
-	if (err)
-		goto nla_put_failure;
+out:
+	mutex_unlock(&linecard->state_lock);
+	return err;
+}
 
-	chunks_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_REGION_CHUNKS);
-	if (!chunks_attr) {
-		err = -EMSGSIZE;
-		goto nla_put_failure;
-	}
+static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_linecard *linecard;
+	int err;
 
-	err = devlink_nl_region_read_fill(skb, region_cb, region_cb_priv,
-					  start_offset, end_offset, &ret_offset,
-					  cb->extack);
+	linecard = devlink_linecard_get_from_info(devlink, info);
+	if (IS_ERR(linecard))
+		return PTR_ERR(linecard);
 
-	if (err && err != -EMSGSIZE)
-		goto nla_put_failure;
+	if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) {
+		const char *type;
 
-	/* Check if there was any progress done to prevent infinite loop */
-	if (ret_offset == start_offset) {
-		err = -EINVAL;
-		goto nla_put_failure;
+		type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]);
+		if (strcmp(type, "")) {
+			err = devlink_linecard_type_set(linecard, type, extack);
+			if (err)
+				return err;
+		} else {
+			err = devlink_linecard_type_unset(linecard, extack);
+			if (err)
+				return err;
+		}
 	}
 
-	state->start_offset = ret_offset;
+	return 0;
+}
 
-	nla_nest_end(skb, chunks_attr);
-	genlmsg_end(skb, hdr);
-	devl_unlock(devlink);
-	devlink_put(devlink);
-	return skb->len;
+int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
+			     struct netlink_ext_ack *extack)
+{
+	struct devlink_rate *devlink_rate;
 
-nla_put_failure:
-	genlmsg_cancel(skb, hdr);
-out_unlock:
-	devl_unlock(devlink);
-	devlink_put(devlink);
-	return err;
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list)
+		if (devlink_rate_is_node(devlink_rate)) {
+			NL_SET_ERR_MSG(extack, "Rate node(s) exists.");
+			return -EBUSY;
+		}
+	return 0;
 }
 
 struct devlink_stats {
@@ -3611,231 +2580,6 @@ void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard,
 }
 EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set);
 
-/**
- * devl_region_create - create a new address region
- *
- * @devlink: devlink
- * @ops: region operations and name
- * @region_max_snapshots: Maximum supported number of snapshots for region
- * @region_size: size of region
- */
-struct devlink_region *devl_region_create(struct devlink *devlink,
-					  const struct devlink_region_ops *ops,
-					  u32 region_max_snapshots,
-					  u64 region_size)
-{
-	struct devlink_region *region;
-
-	devl_assert_locked(devlink);
-
-	if (WARN_ON(!ops) || WARN_ON(!ops->destructor))
-		return ERR_PTR(-EINVAL);
-
-	if (devlink_region_get_by_name(devlink, ops->name))
-		return ERR_PTR(-EEXIST);
-
-	region = kzalloc(sizeof(*region), GFP_KERNEL);
-	if (!region)
-		return ERR_PTR(-ENOMEM);
-
-	region->devlink = devlink;
-	region->max_snapshots = region_max_snapshots;
-	region->ops = ops;
-	region->size = region_size;
-	INIT_LIST_HEAD(&region->snapshot_list);
-	mutex_init(&region->snapshot_lock);
-	list_add_tail(&region->list, &devlink->region_list);
-	devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
-
-	return region;
-}
-EXPORT_SYMBOL_GPL(devl_region_create);
-
-/**
- *	devlink_region_create - create a new address region
- *
- *	@devlink: devlink
- *	@ops: region operations and name
- *	@region_max_snapshots: Maximum supported number of snapshots for region
- *	@region_size: size of region
- *
- *	Context: Takes and release devlink->lock <mutex>.
- */
-struct devlink_region *
-devlink_region_create(struct devlink *devlink,
-		      const struct devlink_region_ops *ops,
-		      u32 region_max_snapshots, u64 region_size)
-{
-	struct devlink_region *region;
-
-	devl_lock(devlink);
-	region = devl_region_create(devlink, ops, region_max_snapshots,
-				    region_size);
-	devl_unlock(devlink);
-	return region;
-}
-EXPORT_SYMBOL_GPL(devlink_region_create);
-
-/**
- *	devlink_port_region_create - create a new address region for a port
- *
- *	@port: devlink port
- *	@ops: region operations and name
- *	@region_max_snapshots: Maximum supported number of snapshots for region
- *	@region_size: size of region
- *
- *	Context: Takes and release devlink->lock <mutex>.
- */
-struct devlink_region *
-devlink_port_region_create(struct devlink_port *port,
-			   const struct devlink_port_region_ops *ops,
-			   u32 region_max_snapshots, u64 region_size)
-{
-	struct devlink *devlink = port->devlink;
-	struct devlink_region *region;
-	int err = 0;
-
-	ASSERT_DEVLINK_PORT_INITIALIZED(port);
-
-	if (WARN_ON(!ops) || WARN_ON(!ops->destructor))
-		return ERR_PTR(-EINVAL);
-
-	devl_lock(devlink);
-
-	if (devlink_port_region_get_by_name(port, ops->name)) {
-		err = -EEXIST;
-		goto unlock;
-	}
-
-	region = kzalloc(sizeof(*region), GFP_KERNEL);
-	if (!region) {
-		err = -ENOMEM;
-		goto unlock;
-	}
-
-	region->devlink = devlink;
-	region->port = port;
-	region->max_snapshots = region_max_snapshots;
-	region->port_ops = ops;
-	region->size = region_size;
-	INIT_LIST_HEAD(&region->snapshot_list);
-	mutex_init(&region->snapshot_lock);
-	list_add_tail(&region->list, &port->region_list);
-	devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
-
-	devl_unlock(devlink);
-	return region;
-
-unlock:
-	devl_unlock(devlink);
-	return ERR_PTR(err);
-}
-EXPORT_SYMBOL_GPL(devlink_port_region_create);
-
-/**
- * devl_region_destroy - destroy address region
- *
- * @region: devlink region to destroy
- */
-void devl_region_destroy(struct devlink_region *region)
-{
-	struct devlink *devlink = region->devlink;
-	struct devlink_snapshot *snapshot, *ts;
-
-	devl_assert_locked(devlink);
-
-	/* Free all snapshots of region */
-	mutex_lock(&region->snapshot_lock);
-	list_for_each_entry_safe(snapshot, ts, &region->snapshot_list, list)
-		devlink_region_snapshot_del(region, snapshot);
-	mutex_unlock(&region->snapshot_lock);
-
-	list_del(&region->list);
-	mutex_destroy(&region->snapshot_lock);
-
-	devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL);
-	kfree(region);
-}
-EXPORT_SYMBOL_GPL(devl_region_destroy);
-
-/**
- *	devlink_region_destroy - destroy address region
- *
- *	@region: devlink region to destroy
- *
- *	Context: Takes and release devlink->lock <mutex>.
- */
-void devlink_region_destroy(struct devlink_region *region)
-{
-	struct devlink *devlink = region->devlink;
-
-	devl_lock(devlink);
-	devl_region_destroy(region);
-	devl_unlock(devlink);
-}
-EXPORT_SYMBOL_GPL(devlink_region_destroy);
-
-/**
- *	devlink_region_snapshot_id_get - get snapshot ID
- *
- *	This callback should be called when adding a new snapshot,
- *	Driver should use the same id for multiple snapshots taken
- *	on multiple regions at the same time/by the same trigger.
- *
- *	The caller of this function must use devlink_region_snapshot_id_put
- *	when finished creating regions using this id.
- *
- *	Returns zero on success, or a negative error code on failure.
- *
- *	@devlink: devlink
- *	@id: storage to return id
- */
-int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id)
-{
-	return __devlink_region_snapshot_id_get(devlink, id);
-}
-EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get);
-
-/**
- *	devlink_region_snapshot_id_put - put snapshot ID reference
- *
- *	This should be called by a driver after finishing creating snapshots
- *	with an id. Doing so ensures that the ID can later be released in the
- *	event that all snapshots using it have been destroyed.
- *
- *	@devlink: devlink
- *	@id: id to release reference on
- */
-void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id)
-{
-	__devlink_snapshot_id_decrement(devlink, id);
-}
-EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_put);
-
-/**
- *	devlink_region_snapshot_create - create a new snapshot
- *	This will add a new snapshot of a region. The snapshot
- *	will be stored on the region struct and can be accessed
- *	from devlink. This is useful for future analyses of snapshots.
- *	Multiple snapshots can be created on a region.
- *	The @snapshot_id should be obtained using the getter function.
- *
- *	@region: devlink region of the snapshot
- *	@data: snapshot data
- *	@snapshot_id: snapshot id to be created
- */
-int devlink_region_snapshot_create(struct devlink_region *region,
-				   u8 *data, u32 snapshot_id)
-{
-	int err;
-
-	mutex_lock(&region->snapshot_lock);
-	err = __devlink_region_snapshot_create(region, data, snapshot_id);
-	mutex_unlock(&region->snapshot_lock);
-	return err;
-}
-EXPORT_SYMBOL_GPL(devlink_region_snapshot_create);
-
 #define DEVLINK_TRAP(_id, _type)					      \
 	{								      \
 		.type = DEVLINK_TRAP_TYPE_##_type,			      \
diff --git a/net/devlink/region.c b/net/devlink/region.c
new file mode 100644
index 0000000000000..d197cdb662dbd
--- /dev/null
+++ b/net/devlink/region.c
@@ -0,0 +1,1260 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include "devl_internal.h"
+
+struct devlink_region {
+	struct devlink *devlink;
+	struct devlink_port *port;
+	struct list_head list;
+	union {
+		const struct devlink_region_ops *ops;
+		const struct devlink_port_region_ops *port_ops;
+	};
+	struct mutex snapshot_lock; /* protects snapshot_list,
+				     * max_snapshots and cur_snapshots
+				     * consistency.
+				     */
+	struct list_head snapshot_list;
+	u32 max_snapshots;
+	u32 cur_snapshots;
+	u64 size;
+};
+
+struct devlink_snapshot {
+	struct list_head list;
+	struct devlink_region *region;
+	u8 *data;
+	u32 id;
+};
+
+static struct devlink_region *
+devlink_region_get_by_name(struct devlink *devlink, const char *region_name)
+{
+	struct devlink_region *region;
+
+	list_for_each_entry(region, &devlink->region_list, list)
+		if (!strcmp(region->ops->name, region_name))
+			return region;
+
+	return NULL;
+}
+
+static struct devlink_region *
+devlink_port_region_get_by_name(struct devlink_port *port,
+				const char *region_name)
+{
+	struct devlink_region *region;
+
+	list_for_each_entry(region, &port->region_list, list)
+		if (!strcmp(region->ops->name, region_name))
+			return region;
+
+	return NULL;
+}
+
+static struct devlink_snapshot *
+devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
+{
+	struct devlink_snapshot *snapshot;
+
+	list_for_each_entry(snapshot, &region->snapshot_list, list)
+		if (snapshot->id == id)
+			return snapshot;
+
+	return NULL;
+}
+
+static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg,
+					     struct devlink *devlink,
+					     struct devlink_snapshot *snapshot)
+{
+	struct nlattr *snap_attr;
+	int err;
+
+	snap_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOT);
+	if (!snap_attr)
+		return -EINVAL;
+
+	err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id);
+	if (err)
+		goto nla_put_failure;
+
+	nla_nest_end(msg, snap_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, snap_attr);
+	return err;
+}
+
+static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg,
+					      struct devlink *devlink,
+					      struct devlink_region *region)
+{
+	struct devlink_snapshot *snapshot;
+	struct nlattr *snapshots_attr;
+	int err;
+
+	snapshots_attr = nla_nest_start_noflag(msg,
+					       DEVLINK_ATTR_REGION_SNAPSHOTS);
+	if (!snapshots_attr)
+		return -EINVAL;
+
+	list_for_each_entry(snapshot, &region->snapshot_list, list) {
+		err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot);
+		if (err)
+			goto nla_put_failure;
+	}
+
+	nla_nest_end(msg, snapshots_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, snapshots_attr);
+	return err;
+}
+
+static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
+				  enum devlink_command cmd, u32 portid,
+				  u32 seq, int flags,
+				  struct devlink_region *region)
+{
+	void *hdr;
+	int err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	err = devlink_nl_put_handle(msg, devlink);
+	if (err)
+		goto nla_put_failure;
+
+	if (region->port) {
+		err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				  region->port->index);
+		if (err)
+			goto nla_put_failure;
+	}
+
+	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name);
+	if (err)
+		goto nla_put_failure;
+
+	err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE,
+				region->size,
+				DEVLINK_ATTR_PAD);
+	if (err)
+		goto nla_put_failure;
+
+	err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS,
+			  region->max_snapshots);
+	if (err)
+		goto nla_put_failure;
+
+	err = devlink_nl_region_snapshots_id_put(msg, devlink, region);
+	if (err)
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return err;
+}
+
+static struct sk_buff *
+devlink_nl_region_notify_build(struct devlink_region *region,
+			       struct devlink_snapshot *snapshot,
+			       enum devlink_command cmd, u32 portid, u32 seq)
+{
+	struct devlink *devlink = region->devlink;
+	struct sk_buff *msg;
+	void *hdr;
+	int err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return ERR_PTR(-ENOMEM);
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, 0, cmd);
+	if (!hdr) {
+		err = -EMSGSIZE;
+		goto out_free_msg;
+	}
+
+	err = devlink_nl_put_handle(msg, devlink);
+	if (err)
+		goto out_cancel_msg;
+
+	if (region->port) {
+		err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				  region->port->index);
+		if (err)
+			goto out_cancel_msg;
+	}
+
+	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME,
+			     region->ops->name);
+	if (err)
+		goto out_cancel_msg;
+
+	if (snapshot) {
+		err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID,
+				  snapshot->id);
+		if (err)
+			goto out_cancel_msg;
+	} else {
+		err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE,
+					region->size, DEVLINK_ATTR_PAD);
+		if (err)
+			goto out_cancel_msg;
+	}
+	genlmsg_end(msg, hdr);
+
+	return msg;
+
+out_cancel_msg:
+	genlmsg_cancel(msg, hdr);
+out_free_msg:
+	nlmsg_free(msg);
+	return ERR_PTR(err);
+}
+
+static void devlink_nl_region_notify(struct devlink_region *region,
+				     struct devlink_snapshot *snapshot,
+				     enum devlink_command cmd)
+{
+	struct devlink *devlink = region->devlink;
+	struct sk_buff *msg;
+
+	WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL);
+	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+		return;
+
+	msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0);
+	if (IS_ERR(msg))
+		return;
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
+				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+void devlink_regions_notify_register(struct devlink *devlink)
+{
+	struct devlink_region *region;
+
+	list_for_each_entry(region, &devlink->region_list, list)
+		devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
+}
+
+void devlink_regions_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_region *region;
+
+	list_for_each_entry_reverse(region, &devlink->region_list, list)
+		devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL);
+}
+
+/**
+ * __devlink_snapshot_id_increment - Increment number of snapshots using an id
+ *	@devlink: devlink instance
+ *	@id: the snapshot id
+ *
+ *	Track when a new snapshot begins using an id. Load the count for the
+ *	given id from the snapshot xarray, increment it, and store it back.
+ *
+ *	Called when a new snapshot is created with the given id.
+ *
+ *	The id *must* have been previously allocated by
+ *	devlink_region_snapshot_id_get().
+ *
+ *	Returns 0 on success, or an error on failure.
+ */
+static int __devlink_snapshot_id_increment(struct devlink *devlink, u32 id)
+{
+	unsigned long count;
+	void *p;
+	int err;
+
+	xa_lock(&devlink->snapshot_ids);
+	p = xa_load(&devlink->snapshot_ids, id);
+	if (WARN_ON(!p)) {
+		err = -EINVAL;
+		goto unlock;
+	}
+
+	if (WARN_ON(!xa_is_value(p))) {
+		err = -EINVAL;
+		goto unlock;
+	}
+
+	count = xa_to_value(p);
+	count++;
+
+	err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(count),
+				GFP_ATOMIC));
+unlock:
+	xa_unlock(&devlink->snapshot_ids);
+	return err;
+}
+
+/**
+ * __devlink_snapshot_id_decrement - Decrease number of snapshots using an id
+ *	@devlink: devlink instance
+ *	@id: the snapshot id
+ *
+ *	Track when a snapshot is deleted and stops using an id. Load the count
+ *	for the given id from the snapshot xarray, decrement it, and store it
+ *	back.
+ *
+ *	If the count reaches zero, erase this id from the xarray, freeing it
+ *	up for future re-use by devlink_region_snapshot_id_get().
+ *
+ *	Called when a snapshot using the given id is deleted, and when the
+ *	initial allocator of the id is finished using it.
+ */
+static void __devlink_snapshot_id_decrement(struct devlink *devlink, u32 id)
+{
+	unsigned long count;
+	void *p;
+
+	xa_lock(&devlink->snapshot_ids);
+	p = xa_load(&devlink->snapshot_ids, id);
+	if (WARN_ON(!p))
+		goto unlock;
+
+	if (WARN_ON(!xa_is_value(p)))
+		goto unlock;
+
+	count = xa_to_value(p);
+
+	if (count > 1) {
+		count--;
+		__xa_store(&devlink->snapshot_ids, id, xa_mk_value(count),
+			   GFP_ATOMIC);
+	} else {
+		/* If this was the last user, we can erase this id */
+		__xa_erase(&devlink->snapshot_ids, id);
+	}
+unlock:
+	xa_unlock(&devlink->snapshot_ids);
+}
+
+/**
+ *	__devlink_snapshot_id_insert - Insert a specific snapshot ID
+ *	@devlink: devlink instance
+ *	@id: the snapshot id
+ *
+ *	Mark the given snapshot id as used by inserting a zero value into the
+ *	snapshot xarray.
+ *
+ *	This must be called while holding the devlink instance lock. Unlike
+ *	devlink_snapshot_id_get, the initial reference count is zero, not one.
+ *	It is expected that the id will immediately be used before
+ *	releasing the devlink instance lock.
+ *
+ *	Returns zero on success, or an error code if the snapshot id could not
+ *	be inserted.
+ */
+static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id)
+{
+	int err;
+
+	xa_lock(&devlink->snapshot_ids);
+	if (xa_load(&devlink->snapshot_ids, id)) {
+		xa_unlock(&devlink->snapshot_ids);
+		return -EEXIST;
+	}
+	err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(0),
+				GFP_ATOMIC));
+	xa_unlock(&devlink->snapshot_ids);
+	return err;
+}
+
+/**
+ *	__devlink_region_snapshot_id_get - get snapshot ID
+ *	@devlink: devlink instance
+ *	@id: storage to return snapshot id
+ *
+ *	Allocates a new snapshot id. Returns zero on success, or a negative
+ *	error on failure. Must be called while holding the devlink instance
+ *	lock.
+ *
+ *	Snapshot IDs are tracked using an xarray which stores the number of
+ *	users of the snapshot id.
+ *
+ *	Note that the caller of this function counts as a 'user', in order to
+ *	avoid race conditions. The caller must release its hold on the
+ *	snapshot by using devlink_region_snapshot_id_put.
+ */
+static int __devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id)
+{
+	return xa_alloc(&devlink->snapshot_ids, id, xa_mk_value(1),
+			xa_limit_32b, GFP_KERNEL);
+}
+
+/**
+ *	__devlink_region_snapshot_create - create a new snapshot
+ *	This will add a new snapshot of a region. The snapshot
+ *	will be stored on the region struct and can be accessed
+ *	from devlink. This is useful for future analyses of snapshots.
+ *	Multiple snapshots can be created on a region.
+ *	The @snapshot_id should be obtained using the getter function.
+ *
+ *	Must be called only while holding the region snapshot lock.
+ *
+ *	@region: devlink region of the snapshot
+ *	@data: snapshot data
+ *	@snapshot_id: snapshot id to be created
+ */
+static int
+__devlink_region_snapshot_create(struct devlink_region *region,
+				 u8 *data, u32 snapshot_id)
+{
+	struct devlink *devlink = region->devlink;
+	struct devlink_snapshot *snapshot;
+	int err;
+
+	lockdep_assert_held(&region->snapshot_lock);
+
+	/* check if region can hold one more snapshot */
+	if (region->cur_snapshots == region->max_snapshots)
+		return -ENOSPC;
+
+	if (devlink_region_snapshot_get_by_id(region, snapshot_id))
+		return -EEXIST;
+
+	snapshot = kzalloc(sizeof(*snapshot), GFP_KERNEL);
+	if (!snapshot)
+		return -ENOMEM;
+
+	err = __devlink_snapshot_id_increment(devlink, snapshot_id);
+	if (err)
+		goto err_snapshot_id_increment;
+
+	snapshot->id = snapshot_id;
+	snapshot->region = region;
+	snapshot->data = data;
+
+	list_add_tail(&snapshot->list, &region->snapshot_list);
+
+	region->cur_snapshots++;
+
+	devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW);
+	return 0;
+
+err_snapshot_id_increment:
+	kfree(snapshot);
+	return err;
+}
+
+static void devlink_region_snapshot_del(struct devlink_region *region,
+					struct devlink_snapshot *snapshot)
+{
+	struct devlink *devlink = region->devlink;
+
+	lockdep_assert_held(&region->snapshot_lock);
+
+	devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL);
+	region->cur_snapshots--;
+	list_del(&snapshot->list);
+	region->ops->destructor(snapshot->data);
+	__devlink_snapshot_id_decrement(devlink, snapshot->id);
+	kfree(snapshot);
+}
+
+int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_port *port = NULL;
+	struct devlink_region *region;
+	const char *region_name;
+	struct sk_buff *msg;
+	unsigned int index;
+	int err;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME))
+		return -EINVAL;
+
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port)
+			return -ENODEV;
+	}
+
+	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
+	if (!region)
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET,
+				     info->snd_portid, info->snd_seq, 0,
+				     region);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg,
+						 struct netlink_callback *cb,
+						 struct devlink_port *port,
+						 int *idx, int start, int flags)
+{
+	struct devlink_region *region;
+	int err = 0;
+
+	list_for_each_entry(region, &port->region_list, list) {
+		if (*idx < start) {
+			(*idx)++;
+			continue;
+		}
+		err = devlink_nl_region_fill(msg, port->devlink,
+					     DEVLINK_CMD_REGION_GET,
+					     NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq,
+					     flags, region);
+		if (err)
+			goto out;
+		(*idx)++;
+	}
+
+out:
+	return err;
+}
+
+static int devlink_nl_region_get_dump_one(struct sk_buff *msg,
+					  struct devlink *devlink,
+					  struct netlink_callback *cb,
+					  int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_region *region;
+	struct devlink_port *port;
+	unsigned long port_index;
+	int idx = 0;
+	int err;
+
+	list_for_each_entry(region, &devlink->region_list, list) {
+		if (idx < state->idx) {
+			idx++;
+			continue;
+		}
+		err = devlink_nl_region_fill(msg, devlink,
+					     DEVLINK_CMD_REGION_GET,
+					     NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq, flags,
+					     region);
+		if (err) {
+			state->idx = idx;
+			return err;
+		}
+		idx++;
+	}
+
+	xa_for_each(&devlink->ports, port_index, port) {
+		err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, &idx,
+							    state->idx, flags);
+		if (err) {
+			state->idx = idx;
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+int devlink_nl_region_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_region_get_dump_one);
+}
+
+int devlink_nl_cmd_region_del(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_snapshot *snapshot;
+	struct devlink_port *port = NULL;
+	struct devlink_region *region;
+	const char *region_name;
+	unsigned int index;
+	u32 snapshot_id;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME) ||
+	    GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_SNAPSHOT_ID))
+		return -EINVAL;
+
+	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
+	snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
+
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port)
+			return -ENODEV;
+	}
+
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
+	if (!region)
+		return -EINVAL;
+
+	mutex_lock(&region->snapshot_lock);
+	snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id);
+	if (!snapshot) {
+		mutex_unlock(&region->snapshot_lock);
+		return -EINVAL;
+	}
+
+	devlink_region_snapshot_del(region, snapshot);
+	mutex_unlock(&region->snapshot_lock);
+	return 0;
+}
+
+int devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_snapshot *snapshot;
+	struct devlink_port *port = NULL;
+	struct nlattr *snapshot_id_attr;
+	struct devlink_region *region;
+	const char *region_name;
+	unsigned int index;
+	u32 snapshot_id;
+	u8 *data;
+	int err;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) {
+		NL_SET_ERR_MSG(info->extack, "No region name provided");
+		return -EINVAL;
+	}
+
+	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
+
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port)
+			return -ENODEV;
+	}
+
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
+	if (!region) {
+		NL_SET_ERR_MSG(info->extack, "The requested region does not exist");
+		return -EINVAL;
+	}
+
+	if (!region->ops->snapshot) {
+		NL_SET_ERR_MSG(info->extack, "The requested region does not support taking an immediate snapshot");
+		return -EOPNOTSUPP;
+	}
+
+	mutex_lock(&region->snapshot_lock);
+
+	if (region->cur_snapshots == region->max_snapshots) {
+		NL_SET_ERR_MSG(info->extack, "The region has reached the maximum number of stored snapshots");
+		err = -ENOSPC;
+		goto unlock;
+	}
+
+	snapshot_id_attr = info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID];
+	if (snapshot_id_attr) {
+		snapshot_id = nla_get_u32(snapshot_id_attr);
+
+		if (devlink_region_snapshot_get_by_id(region, snapshot_id)) {
+			NL_SET_ERR_MSG(info->extack, "The requested snapshot id is already in use");
+			err = -EEXIST;
+			goto unlock;
+		}
+
+		err = __devlink_snapshot_id_insert(devlink, snapshot_id);
+		if (err)
+			goto unlock;
+	} else {
+		err = __devlink_region_snapshot_id_get(devlink, &snapshot_id);
+		if (err) {
+			NL_SET_ERR_MSG(info->extack, "Failed to allocate a new snapshot id");
+			goto unlock;
+		}
+	}
+
+	if (port)
+		err = region->port_ops->snapshot(port, region->port_ops,
+						 info->extack, &data);
+	else
+		err = region->ops->snapshot(devlink, region->ops,
+					    info->extack, &data);
+	if (err)
+		goto err_snapshot_capture;
+
+	err = __devlink_region_snapshot_create(region, data, snapshot_id);
+	if (err)
+		goto err_snapshot_create;
+
+	if (!snapshot_id_attr) {
+		struct sk_buff *msg;
+
+		snapshot = devlink_region_snapshot_get_by_id(region,
+							     snapshot_id);
+		if (WARN_ON(!snapshot)) {
+			err = -EINVAL;
+			goto unlock;
+		}
+
+		msg = devlink_nl_region_notify_build(region, snapshot,
+						     DEVLINK_CMD_REGION_NEW,
+						     info->snd_portid,
+						     info->snd_seq);
+		err = PTR_ERR_OR_ZERO(msg);
+		if (err)
+			goto err_notify;
+
+		err = genlmsg_reply(msg, info);
+		if (err)
+			goto err_notify;
+	}
+
+	mutex_unlock(&region->snapshot_lock);
+	return 0;
+
+err_snapshot_create:
+	region->ops->destructor(data);
+err_snapshot_capture:
+	__devlink_snapshot_id_decrement(devlink, snapshot_id);
+	mutex_unlock(&region->snapshot_lock);
+	return err;
+
+err_notify:
+	devlink_region_snapshot_del(region, snapshot);
+unlock:
+	mutex_unlock(&region->snapshot_lock);
+	return err;
+}
+
+static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg,
+						 u8 *chunk, u32 chunk_size,
+						 u64 addr)
+{
+	struct nlattr *chunk_attr;
+	int err;
+
+	chunk_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_CHUNK);
+	if (!chunk_attr)
+		return -EINVAL;
+
+	err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk);
+	if (err)
+		goto nla_put_failure;
+
+	err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr,
+				DEVLINK_ATTR_PAD);
+	if (err)
+		goto nla_put_failure;
+
+	nla_nest_end(msg, chunk_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, chunk_attr);
+	return err;
+}
+
+#define DEVLINK_REGION_READ_CHUNK_SIZE 256
+
+typedef int devlink_chunk_fill_t(void *cb_priv, u8 *chunk, u32 chunk_size,
+				 u64 curr_offset,
+				 struct netlink_ext_ack *extack);
+
+static int
+devlink_nl_region_read_fill(struct sk_buff *skb, devlink_chunk_fill_t *cb,
+			    void *cb_priv, u64 start_offset, u64 end_offset,
+			    u64 *new_offset, struct netlink_ext_ack *extack)
+{
+	u64 curr_offset = start_offset;
+	int err = 0;
+	u8 *data;
+
+	/* Allocate and re-use a single buffer */
+	data = kmalloc(DEVLINK_REGION_READ_CHUNK_SIZE, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	*new_offset = start_offset;
+
+	while (curr_offset < end_offset) {
+		u32 data_size;
+
+		data_size = min_t(u32, end_offset - curr_offset,
+				  DEVLINK_REGION_READ_CHUNK_SIZE);
+
+		err = cb(cb_priv, data, data_size, curr_offset, extack);
+		if (err)
+			break;
+
+		err = devlink_nl_cmd_region_read_chunk_fill(skb, data, data_size, curr_offset);
+		if (err)
+			break;
+
+		curr_offset += data_size;
+	}
+	*new_offset = curr_offset;
+
+	kfree(data);
+
+	return err;
+}
+
+static int
+devlink_region_snapshot_fill(void *cb_priv, u8 *chunk, u32 chunk_size,
+			     u64 curr_offset,
+			     struct netlink_ext_ack __always_unused *extack)
+{
+	struct devlink_snapshot *snapshot = cb_priv;
+
+	memcpy(chunk, &snapshot->data[curr_offset], chunk_size);
+
+	return 0;
+}
+
+static int
+devlink_region_port_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size,
+				u64 curr_offset, struct netlink_ext_ack *extack)
+{
+	struct devlink_region *region = cb_priv;
+
+	return region->port_ops->read(region->port, region->port_ops, extack,
+				      curr_offset, chunk_size, chunk);
+}
+
+static int
+devlink_region_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size,
+			   u64 curr_offset, struct netlink_ext_ack *extack)
+{
+	struct devlink_region *region = cb_priv;
+
+	return region->ops->read(region->devlink, region->ops, extack,
+				 curr_offset, chunk_size, chunk);
+}
+
+int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
+				      struct netlink_callback *cb)
+{
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct nlattr *chunks_attr, *region_attr, *snapshot_attr;
+	u64 ret_offset, start_offset, end_offset = U64_MAX;
+	struct nlattr **attrs = info->info.attrs;
+	struct devlink_port *port = NULL;
+	devlink_chunk_fill_t *region_cb;
+	struct devlink_region *region;
+	const char *region_name;
+	struct devlink *devlink;
+	unsigned int index;
+	void *region_cb_priv;
+	void *hdr;
+	int err;
+
+	start_offset = state->start_offset;
+
+	devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs);
+	if (IS_ERR(devlink))
+		return PTR_ERR(devlink);
+
+	if (!attrs[DEVLINK_ATTR_REGION_NAME]) {
+		NL_SET_ERR_MSG(cb->extack, "No region name provided");
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port) {
+			err = -ENODEV;
+			goto out_unlock;
+		}
+	}
+
+	region_attr = attrs[DEVLINK_ATTR_REGION_NAME];
+	region_name = nla_data(region_attr);
+
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
+	if (!region) {
+		NL_SET_ERR_MSG_ATTR(cb->extack, region_attr, "Requested region does not exist");
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
+	snapshot_attr = attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID];
+	if (!snapshot_attr) {
+		if (!nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) {
+			NL_SET_ERR_MSG(cb->extack, "No snapshot id provided");
+			err = -EINVAL;
+			goto out_unlock;
+		}
+
+		if (!region->ops->read) {
+			NL_SET_ERR_MSG(cb->extack, "Requested region does not support direct read");
+			err = -EOPNOTSUPP;
+			goto out_unlock;
+		}
+
+		if (port)
+			region_cb = &devlink_region_port_direct_fill;
+		else
+			region_cb = &devlink_region_direct_fill;
+		region_cb_priv = region;
+	} else {
+		struct devlink_snapshot *snapshot;
+		u32 snapshot_id;
+
+		if (nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) {
+			NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Direct region read does not use snapshot");
+			err = -EINVAL;
+			goto out_unlock;
+		}
+
+		snapshot_id = nla_get_u32(snapshot_attr);
+		snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id);
+		if (!snapshot) {
+			NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Requested snapshot does not exist");
+			err = -EINVAL;
+			goto out_unlock;
+		}
+		region_cb = &devlink_region_snapshot_fill;
+		region_cb_priv = snapshot;
+	}
+
+	if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] &&
+	    attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) {
+		if (!start_offset)
+			start_offset =
+				nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
+
+		end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
+		end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
+	}
+
+	if (end_offset > region->size)
+		end_offset = region->size;
+
+	/* return 0 if there is no further data to read */
+	if (start_offset == end_offset) {
+		err = 0;
+		goto out_unlock;
+	}
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI,
+			  DEVLINK_CMD_REGION_READ);
+	if (!hdr) {
+		err = -EMSGSIZE;
+		goto out_unlock;
+	}
+
+	err = devlink_nl_put_handle(skb, devlink);
+	if (err)
+		goto nla_put_failure;
+
+	if (region->port) {
+		err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX,
+				  region->port->index);
+		if (err)
+			goto nla_put_failure;
+	}
+
+	err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name);
+	if (err)
+		goto nla_put_failure;
+
+	chunks_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_REGION_CHUNKS);
+	if (!chunks_attr) {
+		err = -EMSGSIZE;
+		goto nla_put_failure;
+	}
+
+	err = devlink_nl_region_read_fill(skb, region_cb, region_cb_priv,
+					  start_offset, end_offset, &ret_offset,
+					  cb->extack);
+
+	if (err && err != -EMSGSIZE)
+		goto nla_put_failure;
+
+	/* Check if there was any progress done to prevent infinite loop */
+	if (ret_offset == start_offset) {
+		err = -EINVAL;
+		goto nla_put_failure;
+	}
+
+	state->start_offset = ret_offset;
+
+	nla_nest_end(skb, chunks_attr);
+	genlmsg_end(skb, hdr);
+	devl_unlock(devlink);
+	devlink_put(devlink);
+	return skb->len;
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+out_unlock:
+	devl_unlock(devlink);
+	devlink_put(devlink);
+	return err;
+}
+
+/**
+ * devl_region_create - create a new address region
+ *
+ * @devlink: devlink
+ * @ops: region operations and name
+ * @region_max_snapshots: Maximum supported number of snapshots for region
+ * @region_size: size of region
+ */
+struct devlink_region *devl_region_create(struct devlink *devlink,
+					  const struct devlink_region_ops *ops,
+					  u32 region_max_snapshots,
+					  u64 region_size)
+{
+	struct devlink_region *region;
+
+	devl_assert_locked(devlink);
+
+	if (WARN_ON(!ops) || WARN_ON(!ops->destructor))
+		return ERR_PTR(-EINVAL);
+
+	if (devlink_region_get_by_name(devlink, ops->name))
+		return ERR_PTR(-EEXIST);
+
+	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	if (!region)
+		return ERR_PTR(-ENOMEM);
+
+	region->devlink = devlink;
+	region->max_snapshots = region_max_snapshots;
+	region->ops = ops;
+	region->size = region_size;
+	INIT_LIST_HEAD(&region->snapshot_list);
+	mutex_init(&region->snapshot_lock);
+	list_add_tail(&region->list, &devlink->region_list);
+	devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
+
+	return region;
+}
+EXPORT_SYMBOL_GPL(devl_region_create);
+
+/**
+ *	devlink_region_create - create a new address region
+ *
+ *	@devlink: devlink
+ *	@ops: region operations and name
+ *	@region_max_snapshots: Maximum supported number of snapshots for region
+ *	@region_size: size of region
+ *
+ *	Context: Takes and release devlink->lock <mutex>.
+ */
+struct devlink_region *
+devlink_region_create(struct devlink *devlink,
+		      const struct devlink_region_ops *ops,
+		      u32 region_max_snapshots, u64 region_size)
+{
+	struct devlink_region *region;
+
+	devl_lock(devlink);
+	region = devl_region_create(devlink, ops, region_max_snapshots,
+				    region_size);
+	devl_unlock(devlink);
+	return region;
+}
+EXPORT_SYMBOL_GPL(devlink_region_create);
+
+/**
+ *	devlink_port_region_create - create a new address region for a port
+ *
+ *	@port: devlink port
+ *	@ops: region operations and name
+ *	@region_max_snapshots: Maximum supported number of snapshots for region
+ *	@region_size: size of region
+ *
+ *	Context: Takes and release devlink->lock <mutex>.
+ */
+struct devlink_region *
+devlink_port_region_create(struct devlink_port *port,
+			   const struct devlink_port_region_ops *ops,
+			   u32 region_max_snapshots, u64 region_size)
+{
+	struct devlink *devlink = port->devlink;
+	struct devlink_region *region;
+	int err = 0;
+
+	ASSERT_DEVLINK_PORT_INITIALIZED(port);
+
+	if (WARN_ON(!ops) || WARN_ON(!ops->destructor))
+		return ERR_PTR(-EINVAL);
+
+	devl_lock(devlink);
+
+	if (devlink_port_region_get_by_name(port, ops->name)) {
+		err = -EEXIST;
+		goto unlock;
+	}
+
+	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	if (!region) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	region->devlink = devlink;
+	region->port = port;
+	region->max_snapshots = region_max_snapshots;
+	region->port_ops = ops;
+	region->size = region_size;
+	INIT_LIST_HEAD(&region->snapshot_list);
+	mutex_init(&region->snapshot_lock);
+	list_add_tail(&region->list, &port->region_list);
+	devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
+
+	devl_unlock(devlink);
+	return region;
+
+unlock:
+	devl_unlock(devlink);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(devlink_port_region_create);
+
+/**
+ * devl_region_destroy - destroy address region
+ *
+ * @region: devlink region to destroy
+ */
+void devl_region_destroy(struct devlink_region *region)
+{
+	struct devlink *devlink = region->devlink;
+	struct devlink_snapshot *snapshot, *ts;
+
+	devl_assert_locked(devlink);
+
+	/* Free all snapshots of region */
+	mutex_lock(&region->snapshot_lock);
+	list_for_each_entry_safe(snapshot, ts, &region->snapshot_list, list)
+		devlink_region_snapshot_del(region, snapshot);
+	mutex_unlock(&region->snapshot_lock);
+
+	list_del(&region->list);
+	mutex_destroy(&region->snapshot_lock);
+
+	devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL);
+	kfree(region);
+}
+EXPORT_SYMBOL_GPL(devl_region_destroy);
+
+/**
+ *	devlink_region_destroy - destroy address region
+ *
+ *	@region: devlink region to destroy
+ *
+ *	Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_region_destroy(struct devlink_region *region)
+{
+	struct devlink *devlink = region->devlink;
+
+	devl_lock(devlink);
+	devl_region_destroy(region);
+	devl_unlock(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_region_destroy);
+
+/**
+ *	devlink_region_snapshot_id_get - get snapshot ID
+ *
+ *	This callback should be called when adding a new snapshot,
+ *	Driver should use the same id for multiple snapshots taken
+ *	on multiple regions at the same time/by the same trigger.
+ *
+ *	The caller of this function must use devlink_region_snapshot_id_put
+ *	when finished creating regions using this id.
+ *
+ *	Returns zero on success, or a negative error code on failure.
+ *
+ *	@devlink: devlink
+ *	@id: storage to return id
+ */
+int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id)
+{
+	return __devlink_region_snapshot_id_get(devlink, id);
+}
+EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get);
+
+/**
+ *	devlink_region_snapshot_id_put - put snapshot ID reference
+ *
+ *	This should be called by a driver after finishing creating snapshots
+ *	with an id. Doing so ensures that the ID can later be released in the
+ *	event that all snapshots using it have been destroyed.
+ *
+ *	@devlink: devlink
+ *	@id: id to release reference on
+ */
+void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id)
+{
+	__devlink_snapshot_id_decrement(devlink, id);
+}
+EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_put);
+
+/**
+ *	devlink_region_snapshot_create - create a new snapshot
+ *	This will add a new snapshot of a region. The snapshot
+ *	will be stored on the region struct and can be accessed
+ *	from devlink. This is useful for future analyses of snapshots.
+ *	Multiple snapshots can be created on a region.
+ *	The @snapshot_id should be obtained using the getter function.
+ *
+ *	@region: devlink region of the snapshot
+ *	@data: snapshot data
+ *	@snapshot_id: snapshot id to be created
+ */
+int devlink_region_snapshot_create(struct devlink_region *region,
+				   u8 *data, u32 snapshot_id)
+{
+	int err;
+
+	mutex_lock(&region->snapshot_lock);
+	err = __devlink_region_snapshot_create(region, data, snapshot_id);
+	mutex_unlock(&region->snapshot_lock);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devlink_region_snapshot_create);
-- 
GitLab


From 85facf94fd804ef557d5d844b5253859adef10d5 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:51 +0200
Subject: [PATCH 1796/1806] devlink: use tracepoint_enabled() helper

In preparation for the trap code move, use tracepoint_enabled() helper
instead of trace_devlink_trap_report_enabled() which would not be
defined in that scope.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-10-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/leftover.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 6d31aaee8ce8c..1db3a7928465b 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -3131,7 +3131,7 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
 	devlink_trap_stats_update(trap_item->stats, skb->len);
 	devlink_trap_stats_update(trap_item->group_item->stats, skb->len);
 
-	if (trace_devlink_trap_report_enabled()) {
+	if (tracepoint_enabled(devlink_trap_report)) {
 		struct devlink_trap_metadata metadata = {};
 
 		devlink_trap_report_metadata_set(&metadata, trap_item,
-- 
GitLab


From 4bbdec80ff270a69b6b61644c597ad6657f2a58b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:52 +0200
Subject: [PATCH 1797/1806] devlink: push trap related code into separate file

Cut out another chunk from leftover.c and put trap related code
into a separate file.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-11-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/Makefile        |    2 +-
 net/devlink/devl_internal.h |   11 +
 net/devlink/leftover.c      | 2915 +++++++----------------------------
 net/devlink/trap.c          | 1861 ++++++++++++++++++++++
 4 files changed, 2400 insertions(+), 2389 deletions(-)
 create mode 100644 net/devlink/trap.c

diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index 744f64e467b74..523efffe522c9 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o sb.o dpipe.o \
-	 resource.o param.o region.o health.o
+	 resource.o param.o region.o health.o trap.o
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 32b66233240fe..148525aa2847e 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -160,6 +160,12 @@ void devlink_params_notify_register(struct devlink *devlink);
 void devlink_params_notify_unregister(struct devlink *devlink);
 void devlink_regions_notify_register(struct devlink *devlink);
 void devlink_regions_notify_unregister(struct devlink *devlink);
+void devlink_trap_policers_notify_register(struct devlink *devlink);
+void devlink_trap_policers_notify_unregister(struct devlink *devlink);
+void devlink_trap_groups_notify_register(struct devlink *devlink);
+void devlink_trap_groups_notify_unregister(struct devlink *devlink);
+void devlink_traps_notify_register(struct devlink *devlink);
+void devlink_traps_notify_unregister(struct devlink *devlink);
 
 /* Ports */
 #define ASSERT_DEVLINK_PORT_INITIALIZED(devlink_port)				\
@@ -267,3 +273,8 @@ int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb,
 						   struct genl_info *info);
 int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb,
 					     struct genl_info *info);
+int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb,
+				       struct genl_info *info);
+int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
+					 struct genl_info *info);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 1db3a7928465b..5b153ce097ab6 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -999,2495 +999,634 @@ int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
 	return 0;
 }
 
-struct devlink_stats {
-	u64_stats_t rx_bytes;
-	u64_stats_t rx_packets;
-	struct u64_stats_sync syncp;
-};
-
-/**
- * struct devlink_trap_policer_item - Packet trap policer attributes.
- * @policer: Immutable packet trap policer attributes.
- * @rate: Rate in packets / sec.
- * @burst: Burst size in packets.
- * @list: trap_policer_list member.
- *
- * Describes packet trap policer attributes. Created by devlink during trap
- * policer registration.
- */
-struct devlink_trap_policer_item {
-	const struct devlink_trap_policer *policer;
-	u64 rate;
-	u64 burst;
-	struct list_head list;
-};
-
-/**
- * struct devlink_trap_group_item - Packet trap group attributes.
- * @group: Immutable packet trap group attributes.
- * @policer_item: Associated policer item. Can be NULL.
- * @list: trap_group_list member.
- * @stats: Trap group statistics.
- *
- * Describes packet trap group attributes. Created by devlink during trap
- * group registration.
- */
-struct devlink_trap_group_item {
-	const struct devlink_trap_group *group;
-	struct devlink_trap_policer_item *policer_item;
-	struct list_head list;
-	struct devlink_stats __percpu *stats;
-};
-
-/**
- * struct devlink_trap_item - Packet trap attributes.
- * @trap: Immutable packet trap attributes.
- * @group_item: Associated group item.
- * @list: trap_list member.
- * @action: Trap action.
- * @stats: Trap statistics.
- * @priv: Driver private information.
- *
- * Describes both mutable and immutable packet trap attributes. Created by
- * devlink during trap registration and used for all trap related operations.
- */
-struct devlink_trap_item {
-	const struct devlink_trap *trap;
-	struct devlink_trap_group_item *group_item;
-	struct list_head list;
-	enum devlink_trap_action action;
-	struct devlink_stats __percpu *stats;
-	void *priv;
-};
-
-static struct devlink_trap_policer_item *
-devlink_trap_policer_item_lookup(struct devlink *devlink, u32 id)
-{
-	struct devlink_trap_policer_item *policer_item;
-
-	list_for_each_entry(policer_item, &devlink->trap_policer_list, list) {
-		if (policer_item->policer->id == id)
-			return policer_item;
-	}
-
-	return NULL;
-}
-
-static struct devlink_trap_item *
-devlink_trap_item_lookup(struct devlink *devlink, const char *name)
-{
-	struct devlink_trap_item *trap_item;
-
-	list_for_each_entry(trap_item, &devlink->trap_list, list) {
-		if (!strcmp(trap_item->trap->name, name))
-			return trap_item;
-	}
-
-	return NULL;
-}
-
-static struct devlink_trap_item *
-devlink_trap_item_get_from_info(struct devlink *devlink,
-				struct genl_info *info)
-{
-	struct nlattr *attr;
-
-	if (!info->attrs[DEVLINK_ATTR_TRAP_NAME])
-		return NULL;
-	attr = info->attrs[DEVLINK_ATTR_TRAP_NAME];
-
-	return devlink_trap_item_lookup(devlink, nla_data(attr));
-}
-
-static int
-devlink_trap_action_get_from_info(struct genl_info *info,
-				  enum devlink_trap_action *p_trap_action)
-{
-	u8 val;
-
-	val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]);
-	switch (val) {
-	case DEVLINK_TRAP_ACTION_DROP:
-	case DEVLINK_TRAP_ACTION_TRAP:
-	case DEVLINK_TRAP_ACTION_MIRROR:
-		*p_trap_action = val;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int devlink_trap_metadata_put(struct sk_buff *msg,
-				     const struct devlink_trap *trap)
-{
-	struct nlattr *attr;
-
-	attr = nla_nest_start(msg, DEVLINK_ATTR_TRAP_METADATA);
-	if (!attr)
-		return -EMSGSIZE;
-
-	if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) &&
-	    nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT))
-		goto nla_put_failure;
-	if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE) &&
-	    nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE))
-		goto nla_put_failure;
-
-	nla_nest_end(msg, attr);
-
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(msg, attr);
-	return -EMSGSIZE;
-}
-
-static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats,
-				    struct devlink_stats *stats)
-{
-	int i;
-
-	memset(stats, 0, sizeof(*stats));
-	for_each_possible_cpu(i) {
-		struct devlink_stats *cpu_stats;
-		u64 rx_packets, rx_bytes;
-		unsigned int start;
-
-		cpu_stats = per_cpu_ptr(trap_stats, i);
-		do {
-			start = u64_stats_fetch_begin(&cpu_stats->syncp);
-			rx_packets = u64_stats_read(&cpu_stats->rx_packets);
-			rx_bytes = u64_stats_read(&cpu_stats->rx_bytes);
-		} while (u64_stats_fetch_retry(&cpu_stats->syncp, start));
-
-		u64_stats_add(&stats->rx_packets, rx_packets);
-		u64_stats_add(&stats->rx_bytes, rx_bytes);
-	}
-}
-
-static int
-devlink_trap_group_stats_put(struct sk_buff *msg,
-			     struct devlink_stats __percpu *trap_stats)
-{
-	struct devlink_stats stats;
-	struct nlattr *attr;
-
-	devlink_trap_stats_read(trap_stats, &stats);
-
-	attr = nla_nest_start(msg, DEVLINK_ATTR_STATS);
-	if (!attr)
-		return -EMSGSIZE;
-
-	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS,
-			      u64_stats_read(&stats.rx_packets),
-			      DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-
-	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES,
-			      u64_stats_read(&stats.rx_bytes),
-			      DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-
-	nla_nest_end(msg, attr);
-
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(msg, attr);
-	return -EMSGSIZE;
-}
-
-static int devlink_trap_stats_put(struct sk_buff *msg, struct devlink *devlink,
-				  const struct devlink_trap_item *trap_item)
-{
-	struct devlink_stats stats;
-	struct nlattr *attr;
-	u64 drops = 0;
-	int err;
-
-	if (devlink->ops->trap_drop_counter_get) {
-		err = devlink->ops->trap_drop_counter_get(devlink,
-							  trap_item->trap,
-							  &drops);
-		if (err)
-			return err;
-	}
-
-	devlink_trap_stats_read(trap_item->stats, &stats);
-
-	attr = nla_nest_start(msg, DEVLINK_ATTR_STATS);
-	if (!attr)
-		return -EMSGSIZE;
-
-	if (devlink->ops->trap_drop_counter_get &&
-	    nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops,
-			      DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-
-	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS,
-			      u64_stats_read(&stats.rx_packets),
-			      DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-
-	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES,
-			      u64_stats_read(&stats.rx_bytes),
-			      DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-
-	nla_nest_end(msg, attr);
-
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(msg, attr);
-	return -EMSGSIZE;
-}
-
-static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink,
-				const struct devlink_trap_item *trap_item,
-				enum devlink_command cmd, u32 portid, u32 seq,
-				int flags)
-{
-	struct devlink_trap_group_item *group_item = trap_item->group_item;
-	void *hdr;
-	int err;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-
-	if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME,
-			   group_item->group->name))
-		goto nla_put_failure;
-
-	if (nla_put_string(msg, DEVLINK_ATTR_TRAP_NAME, trap_item->trap->name))
-		goto nla_put_failure;
-
-	if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_TYPE, trap_item->trap->type))
-		goto nla_put_failure;
-
-	if (trap_item->trap->generic &&
-	    nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC))
-		goto nla_put_failure;
-
-	if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_ACTION, trap_item->action))
-		goto nla_put_failure;
-
-	err = devlink_trap_metadata_put(msg, trap_item->trap);
-	if (err)
-		goto nla_put_failure;
-
-	err = devlink_trap_stats_put(msg, devlink, trap_item);
-	if (err)
-		goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-
-	return 0;
-
-nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
-}
-
-int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_trap_item *trap_item;
-	struct sk_buff *msg;
-	int err;
-
-	if (list_empty(&devlink->trap_list))
-		return -EOPNOTSUPP;
-
-	trap_item = devlink_trap_item_get_from_info(devlink, info);
-	if (!trap_item) {
-		NL_SET_ERR_MSG(extack, "Device did not register this trap");
-		return -ENOENT;
-	}
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	err = devlink_nl_trap_fill(msg, devlink, trap_item,
-				   DEVLINK_CMD_TRAP_NEW, info->snd_portid,
-				   info->snd_seq, 0);
-	if (err)
-		goto err_trap_fill;
-
-	return genlmsg_reply(msg, info);
-
-err_trap_fill:
-	nlmsg_free(msg);
-	return err;
-}
-
-static int devlink_nl_trap_get_dump_one(struct sk_buff *msg,
-					struct devlink *devlink,
-					struct netlink_callback *cb, int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_trap_item *trap_item;
-	int idx = 0;
-	int err = 0;
-
-	list_for_each_entry(trap_item, &devlink->trap_list, list) {
-		if (idx < state->idx) {
-			idx++;
-			continue;
-		}
-		err = devlink_nl_trap_fill(msg, devlink, trap_item,
-					   DEVLINK_CMD_TRAP_NEW,
-					   NETLINK_CB(cb->skb).portid,
-					   cb->nlh->nlmsg_seq, flags);
-		if (err) {
-			state->idx = idx;
-			break;
-		}
-		idx++;
-	}
-
-	return err;
-}
-
-int devlink_nl_trap_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_trap_get_dump_one);
-}
-
-static int __devlink_trap_action_set(struct devlink *devlink,
-				     struct devlink_trap_item *trap_item,
-				     enum devlink_trap_action trap_action,
-				     struct netlink_ext_ack *extack)
-{
-	int err;
-
-	if (trap_item->action != trap_action &&
-	    trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) {
-		NL_SET_ERR_MSG(extack, "Cannot change action of non-drop traps. Skipping");
-		return 0;
-	}
-
-	err = devlink->ops->trap_action_set(devlink, trap_item->trap,
-					    trap_action, extack);
-	if (err)
-		return err;
-
-	trap_item->action = trap_action;
-
-	return 0;
-}
-
-static int devlink_trap_action_set(struct devlink *devlink,
-				   struct devlink_trap_item *trap_item,
-				   struct genl_info *info)
-{
-	enum devlink_trap_action trap_action;
-	int err;
-
-	if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION])
-		return 0;
-
-	err = devlink_trap_action_get_from_info(info, &trap_action);
-	if (err) {
-		NL_SET_ERR_MSG(info->extack, "Invalid trap action");
-		return -EINVAL;
-	}
-
-	return __devlink_trap_action_set(devlink, trap_item, trap_action,
-					 info->extack);
-}
-
-static int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb,
-					struct genl_info *info)
-{
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_trap_item *trap_item;
-
-	if (list_empty(&devlink->trap_list))
-		return -EOPNOTSUPP;
-
-	trap_item = devlink_trap_item_get_from_info(devlink, info);
-	if (!trap_item) {
-		NL_SET_ERR_MSG(extack, "Device did not register this trap");
-		return -ENOENT;
-	}
-
-	return devlink_trap_action_set(devlink, trap_item, info);
-}
-
-static struct devlink_trap_group_item *
-devlink_trap_group_item_lookup(struct devlink *devlink, const char *name)
-{
-	struct devlink_trap_group_item *group_item;
-
-	list_for_each_entry(group_item, &devlink->trap_group_list, list) {
-		if (!strcmp(group_item->group->name, name))
-			return group_item;
-	}
-
-	return NULL;
-}
-
-static struct devlink_trap_group_item *
-devlink_trap_group_item_lookup_by_id(struct devlink *devlink, u16 id)
-{
-	struct devlink_trap_group_item *group_item;
-
-	list_for_each_entry(group_item, &devlink->trap_group_list, list) {
-		if (group_item->group->id == id)
-			return group_item;
-	}
-
-	return NULL;
-}
-
-static struct devlink_trap_group_item *
-devlink_trap_group_item_get_from_info(struct devlink *devlink,
-				      struct genl_info *info)
-{
-	char *name;
-
-	if (!info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME])
-		return NULL;
-	name = nla_data(info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]);
-
-	return devlink_trap_group_item_lookup(devlink, name);
-}
-
-static int
-devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink,
-			   const struct devlink_trap_group_item *group_item,
-			   enum devlink_command cmd, u32 portid, u32 seq,
-			   int flags)
-{
-	void *hdr;
-	int err;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-
-	if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME,
-			   group_item->group->name))
-		goto nla_put_failure;
-
-	if (group_item->group->generic &&
-	    nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC))
-		goto nla_put_failure;
-
-	if (group_item->policer_item &&
-	    nla_put_u32(msg, DEVLINK_ATTR_TRAP_POLICER_ID,
-			group_item->policer_item->policer->id))
-		goto nla_put_failure;
-
-	err = devlink_trap_group_stats_put(msg, group_item->stats);
-	if (err)
-		goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-
-	return 0;
-
-nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
-}
-
-int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_trap_group_item *group_item;
-	struct sk_buff *msg;
-	int err;
-
-	if (list_empty(&devlink->trap_group_list))
-		return -EOPNOTSUPP;
-
-	group_item = devlink_trap_group_item_get_from_info(devlink, info);
-	if (!group_item) {
-		NL_SET_ERR_MSG(extack, "Device did not register this trap group");
-		return -ENOENT;
-	}
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	err = devlink_nl_trap_group_fill(msg, devlink, group_item,
-					 DEVLINK_CMD_TRAP_GROUP_NEW,
-					 info->snd_portid, info->snd_seq, 0);
-	if (err)
-		goto err_trap_group_fill;
-
-	return genlmsg_reply(msg, info);
-
-err_trap_group_fill:
-	nlmsg_free(msg);
-	return err;
-}
-
-static int devlink_nl_trap_group_get_dump_one(struct sk_buff *msg,
-					      struct devlink *devlink,
-					      struct netlink_callback *cb,
-					      int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_trap_group_item *group_item;
-	int idx = 0;
-	int err = 0;
-
-
-	list_for_each_entry(group_item, &devlink->trap_group_list, list) {
-		if (idx < state->idx) {
-			idx++;
-			continue;
-		}
-		err = devlink_nl_trap_group_fill(msg, devlink, group_item,
-						 DEVLINK_CMD_TRAP_GROUP_NEW,
-						 NETLINK_CB(cb->skb).portid,
-						 cb->nlh->nlmsg_seq, flags);
-		if (err) {
-			state->idx = idx;
-			break;
-		}
-		idx++;
-	}
-
-	return err;
-}
-
-int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb,
-				     struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_trap_group_get_dump_one);
-}
-
-static int
-__devlink_trap_group_action_set(struct devlink *devlink,
-				struct devlink_trap_group_item *group_item,
-				enum devlink_trap_action trap_action,
-				struct netlink_ext_ack *extack)
-{
-	const char *group_name = group_item->group->name;
-	struct devlink_trap_item *trap_item;
-	int err;
-
-	if (devlink->ops->trap_group_action_set) {
-		err = devlink->ops->trap_group_action_set(devlink, group_item->group,
-							  trap_action, extack);
-		if (err)
-			return err;
-
-		list_for_each_entry(trap_item, &devlink->trap_list, list) {
-			if (strcmp(trap_item->group_item->group->name, group_name))
-				continue;
-			if (trap_item->action != trap_action &&
-			    trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP)
-				continue;
-			trap_item->action = trap_action;
-		}
-
-		return 0;
-	}
-
-	list_for_each_entry(trap_item, &devlink->trap_list, list) {
-		if (strcmp(trap_item->group_item->group->name, group_name))
-			continue;
-		err = __devlink_trap_action_set(devlink, trap_item,
-						trap_action, extack);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int
-devlink_trap_group_action_set(struct devlink *devlink,
-			      struct devlink_trap_group_item *group_item,
-			      struct genl_info *info, bool *p_modified)
-{
-	enum devlink_trap_action trap_action;
-	int err;
-
-	if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION])
-		return 0;
-
-	err = devlink_trap_action_get_from_info(info, &trap_action);
-	if (err) {
-		NL_SET_ERR_MSG(info->extack, "Invalid trap action");
-		return -EINVAL;
-	}
-
-	err = __devlink_trap_group_action_set(devlink, group_item, trap_action,
-					      info->extack);
-	if (err)
-		return err;
-
-	*p_modified = true;
-
-	return 0;
-}
-
-static int devlink_trap_group_set(struct devlink *devlink,
-				  struct devlink_trap_group_item *group_item,
-				  struct genl_info *info)
-{
-	struct devlink_trap_policer_item *policer_item;
-	struct netlink_ext_ack *extack = info->extack;
-	const struct devlink_trap_policer *policer;
-	struct nlattr **attrs = info->attrs;
-	u32 policer_id;
-	int err;
-
-	if (!attrs[DEVLINK_ATTR_TRAP_POLICER_ID])
-		return 0;
-
-	if (!devlink->ops->trap_group_set)
-		return -EOPNOTSUPP;
-
-	policer_id = nla_get_u32(attrs[DEVLINK_ATTR_TRAP_POLICER_ID]);
-	policer_item = devlink_trap_policer_item_lookup(devlink, policer_id);
-	if (policer_id && !policer_item) {
-		NL_SET_ERR_MSG(extack, "Device did not register this trap policer");
-		return -ENOENT;
-	}
-	policer = policer_item ? policer_item->policer : NULL;
-
-	err = devlink->ops->trap_group_set(devlink, group_item->group, policer,
-					   extack);
-	if (err)
-		return err;
-
-	group_item->policer_item = policer_item;
-
-	return 0;
-}
-
-static int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb,
-					      struct genl_info *info)
-{
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_trap_group_item *group_item;
-	bool modified = false;
-	int err;
-
-	if (list_empty(&devlink->trap_group_list))
-		return -EOPNOTSUPP;
-
-	group_item = devlink_trap_group_item_get_from_info(devlink, info);
-	if (!group_item) {
-		NL_SET_ERR_MSG(extack, "Device did not register this trap group");
-		return -ENOENT;
-	}
-
-	err = devlink_trap_group_action_set(devlink, group_item, info,
-					    &modified);
-	if (err)
-		return err;
-
-	err = devlink_trap_group_set(devlink, group_item, info);
-	if (err)
-		goto err_trap_group_set;
-
-	return 0;
-
-err_trap_group_set:
-	if (modified)
-		NL_SET_ERR_MSG(extack, "Trap group set failed, but some changes were committed already");
-	return err;
-}
-
-static struct devlink_trap_policer_item *
-devlink_trap_policer_item_get_from_info(struct devlink *devlink,
-					struct genl_info *info)
-{
-	u32 id;
-
-	if (!info->attrs[DEVLINK_ATTR_TRAP_POLICER_ID])
-		return NULL;
-	id = nla_get_u32(info->attrs[DEVLINK_ATTR_TRAP_POLICER_ID]);
-
-	return devlink_trap_policer_item_lookup(devlink, id);
-}
-
-static int
-devlink_trap_policer_stats_put(struct sk_buff *msg, struct devlink *devlink,
-			       const struct devlink_trap_policer *policer)
-{
-	struct nlattr *attr;
-	u64 drops;
-	int err;
-
-	if (!devlink->ops->trap_policer_counter_get)
-		return 0;
-
-	err = devlink->ops->trap_policer_counter_get(devlink, policer, &drops);
-	if (err)
-		return err;
-
-	attr = nla_nest_start(msg, DEVLINK_ATTR_STATS);
-	if (!attr)
-		return -EMSGSIZE;
-
-	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops,
-			      DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-
-	nla_nest_end(msg, attr);
-
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(msg, attr);
-	return -EMSGSIZE;
-}
-
-static int
-devlink_nl_trap_policer_fill(struct sk_buff *msg, struct devlink *devlink,
-			     const struct devlink_trap_policer_item *policer_item,
-			     enum devlink_command cmd, u32 portid, u32 seq,
-			     int flags)
-{
-	void *hdr;
-	int err;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-
-	if (nla_put_u32(msg, DEVLINK_ATTR_TRAP_POLICER_ID,
-			policer_item->policer->id))
-		goto nla_put_failure;
-
-	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_TRAP_POLICER_RATE,
-			      policer_item->rate, DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-
-	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_TRAP_POLICER_BURST,
-			      policer_item->burst, DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-
-	err = devlink_trap_policer_stats_put(msg, devlink,
-					     policer_item->policer);
-	if (err)
-		goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-
-	return 0;
-
-nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
-}
-
-int devlink_nl_trap_policer_get_doit(struct sk_buff *skb,
-				     struct genl_info *info)
-{
-	struct devlink_trap_policer_item *policer_item;
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink *devlink = info->user_ptr[0];
-	struct sk_buff *msg;
-	int err;
-
-	if (list_empty(&devlink->trap_policer_list))
-		return -EOPNOTSUPP;
-
-	policer_item = devlink_trap_policer_item_get_from_info(devlink, info);
-	if (!policer_item) {
-		NL_SET_ERR_MSG(extack, "Device did not register this trap policer");
-		return -ENOENT;
-	}
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	err = devlink_nl_trap_policer_fill(msg, devlink, policer_item,
-					   DEVLINK_CMD_TRAP_POLICER_NEW,
-					   info->snd_portid, info->snd_seq, 0);
-	if (err)
-		goto err_trap_policer_fill;
-
-	return genlmsg_reply(msg, info);
-
-err_trap_policer_fill:
-	nlmsg_free(msg);
-	return err;
-}
-
-static int devlink_nl_trap_policer_get_dump_one(struct sk_buff *msg,
-						struct devlink *devlink,
-						struct netlink_callback *cb,
-						int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_trap_policer_item *policer_item;
-	int idx = 0;
-	int err = 0;
-
-	list_for_each_entry(policer_item, &devlink->trap_policer_list, list) {
-		if (idx < state->idx) {
-			idx++;
-			continue;
-		}
-		err = devlink_nl_trap_policer_fill(msg, devlink, policer_item,
-						   DEVLINK_CMD_TRAP_POLICER_NEW,
-						   NETLINK_CB(cb->skb).portid,
-						   cb->nlh->nlmsg_seq, flags);
-		if (err) {
-			state->idx = idx;
-			break;
-		}
-		idx++;
-	}
-
-	return err;
-}
-
-int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb,
-				       struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_trap_policer_get_dump_one);
-}
-
-static int
-devlink_trap_policer_set(struct devlink *devlink,
-			 struct devlink_trap_policer_item *policer_item,
-			 struct genl_info *info)
-{
-	struct netlink_ext_ack *extack = info->extack;
-	struct nlattr **attrs = info->attrs;
-	u64 rate, burst;
-	int err;
-
-	rate = policer_item->rate;
-	burst = policer_item->burst;
-
-	if (attrs[DEVLINK_ATTR_TRAP_POLICER_RATE])
-		rate = nla_get_u64(attrs[DEVLINK_ATTR_TRAP_POLICER_RATE]);
-
-	if (attrs[DEVLINK_ATTR_TRAP_POLICER_BURST])
-		burst = nla_get_u64(attrs[DEVLINK_ATTR_TRAP_POLICER_BURST]);
-
-	if (rate < policer_item->policer->min_rate) {
-		NL_SET_ERR_MSG(extack, "Policer rate lower than limit");
-		return -EINVAL;
-	}
-
-	if (rate > policer_item->policer->max_rate) {
-		NL_SET_ERR_MSG(extack, "Policer rate higher than limit");
-		return -EINVAL;
-	}
-
-	if (burst < policer_item->policer->min_burst) {
-		NL_SET_ERR_MSG(extack, "Policer burst size lower than limit");
-		return -EINVAL;
-	}
-
-	if (burst > policer_item->policer->max_burst) {
-		NL_SET_ERR_MSG(extack, "Policer burst size higher than limit");
-		return -EINVAL;
-	}
-
-	err = devlink->ops->trap_policer_set(devlink, policer_item->policer,
-					     rate, burst, info->extack);
-	if (err)
-		return err;
-
-	policer_item->rate = rate;
-	policer_item->burst = burst;
-
-	return 0;
-}
-
-static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
-						struct genl_info *info)
-{
-	struct devlink_trap_policer_item *policer_item;
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink *devlink = info->user_ptr[0];
-
-	if (list_empty(&devlink->trap_policer_list))
-		return -EOPNOTSUPP;
-
-	if (!devlink->ops->trap_policer_set)
-		return -EOPNOTSUPP;
-
-	policer_item = devlink_trap_policer_item_get_from_info(devlink, info);
-	if (!policer_item) {
-		NL_SET_ERR_MSG(extack, "Device did not register this trap policer");
-		return -ENOENT;
-	}
-
-	return devlink_trap_policer_set(devlink, policer_item, info);
-}
-
-const struct genl_small_ops devlink_nl_small_ops[40] = {
-	{
-		.cmd = DEVLINK_CMD_PORT_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_set_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_RATE_SET,
-		.doit = devlink_nl_cmd_rate_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_RATE_NEW,
-		.doit = devlink_nl_cmd_rate_new_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_RATE_DEL,
-		.doit = devlink_nl_cmd_rate_del_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_SPLIT,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_split_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_UNSPLIT,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_unsplit_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_NEW,
-		.doit = devlink_nl_cmd_port_new_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_DEL,
-		.doit = devlink_nl_cmd_port_del_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-
-	{
-		.cmd = DEVLINK_CMD_LINECARD_SET,
-		.doit = devlink_nl_cmd_linecard_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_POOL_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_pool_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_PORT_POOL_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_port_pool_set_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_occ_snapshot_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_occ_max_clear_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_ESWITCH_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_eswitch_get_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_ESWITCH_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_eswitch_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_dpipe_table_get,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_dpipe_entries_get,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_dpipe_headers_get,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_dpipe_table_counters_set,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_RESOURCE_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_resource_set,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_RESOURCE_DUMP,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_resource_dump,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_RELOAD,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_reload,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_PARAM_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_param_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_PARAM_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_param_get_doit,
-		.dumpit = devlink_nl_cmd_port_param_get_dumpit,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_PARAM_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_param_set_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_REGION_NEW,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_region_new,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_REGION_DEL,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_region_del,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_REGION_READ,
-		.validate = GENL_DONT_VALIDATE_STRICT |
-			    GENL_DONT_VALIDATE_DUMP_STRICT,
-		.dumpit = devlink_nl_cmd_region_read_dumpit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_set_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_recover_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_diagnose_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT |
-			    GENL_DONT_VALIDATE_DUMP_STRICT,
-		.dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_dump_clear_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_test_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_FLASH_UPDATE,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_flash_update,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_TRAP_SET,
-		.doit = devlink_nl_cmd_trap_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_TRAP_GROUP_SET,
-		.doit = devlink_nl_cmd_trap_group_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_TRAP_POLICER_SET,
-		.doit = devlink_nl_cmd_trap_policer_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_SELFTESTS_RUN,
-		.doit = devlink_nl_cmd_selftests_run,
-		.flags = GENL_ADMIN_PERM,
-	},
-	/* -- No new ops here! Use split ops going forward! -- */
-};
-
-static void devlink_trap_policers_notify_register(struct devlink *devlink);
-static void devlink_trap_policers_notify_unregister(struct devlink *devlink);
-static void devlink_trap_groups_notify_register(struct devlink *devlink);
-static void devlink_trap_groups_notify_unregister(struct devlink *devlink);
-static void devlink_traps_notify_register(struct devlink *devlink);
-static void devlink_traps_notify_unregister(struct devlink *devlink);
-
-void devlink_notify_register(struct devlink *devlink)
-{
-	devlink_notify(devlink, DEVLINK_CMD_NEW);
-	devlink_linecards_notify_register(devlink);
-	devlink_ports_notify_register(devlink);
-	devlink_trap_policers_notify_register(devlink);
-	devlink_trap_groups_notify_register(devlink);
-	devlink_traps_notify_register(devlink);
-	devlink_rates_notify_register(devlink);
-	devlink_regions_notify_register(devlink);
-	devlink_params_notify_register(devlink);
-}
-
-void devlink_notify_unregister(struct devlink *devlink)
-{
-	devlink_params_notify_unregister(devlink);
-	devlink_regions_notify_unregister(devlink);
-	devlink_rates_notify_unregister(devlink);
-	devlink_traps_notify_unregister(devlink);
-	devlink_trap_groups_notify_unregister(devlink);
-	devlink_trap_policers_notify_unregister(devlink);
-	devlink_ports_notify_unregister(devlink);
-	devlink_linecards_notify_unregister(devlink);
-	devlink_notify(devlink, DEVLINK_CMD_DEL);
-}
-
-/**
- * devl_rate_node_create - create devlink rate node
- * @devlink: devlink instance
- * @priv: driver private data
- * @node_name: name of the resulting node
- * @parent: parent devlink_rate struct
- *
- * Create devlink rate object of type node
- */
-struct devlink_rate *
-devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,
-		      struct devlink_rate *parent)
-{
-	struct devlink_rate *rate_node;
-
-	rate_node = devlink_rate_node_get_by_name(devlink, node_name);
-	if (!IS_ERR(rate_node))
-		return ERR_PTR(-EEXIST);
-
-	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
-	if (!rate_node)
-		return ERR_PTR(-ENOMEM);
-
-	if (parent) {
-		rate_node->parent = parent;
-		refcount_inc(&rate_node->parent->refcnt);
-	}
-
-	rate_node->type = DEVLINK_RATE_TYPE_NODE;
-	rate_node->devlink = devlink;
-	rate_node->priv = priv;
-
-	rate_node->name = kstrdup(node_name, GFP_KERNEL);
-	if (!rate_node->name) {
-		kfree(rate_node);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	refcount_set(&rate_node->refcnt, 1);
-	list_add(&rate_node->list, &devlink->rate_list);
-	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
-	return rate_node;
-}
-EXPORT_SYMBOL_GPL(devl_rate_node_create);
-
-/**
- * devl_rate_leaf_create - create devlink rate leaf
- * @devlink_port: devlink port object to create rate object on
- * @priv: driver private data
- * @parent: parent devlink_rate struct
- *
- * Create devlink rate object of type leaf on provided @devlink_port.
- */
-int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv,
-			  struct devlink_rate *parent)
-{
-	struct devlink *devlink = devlink_port->devlink;
-	struct devlink_rate *devlink_rate;
-
-	devl_assert_locked(devlink_port->devlink);
-
-	if (WARN_ON(devlink_port->devlink_rate))
-		return -EBUSY;
-
-	devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL);
-	if (!devlink_rate)
-		return -ENOMEM;
-
-	if (parent) {
-		devlink_rate->parent = parent;
-		refcount_inc(&devlink_rate->parent->refcnt);
-	}
-
-	devlink_rate->type = DEVLINK_RATE_TYPE_LEAF;
-	devlink_rate->devlink = devlink;
-	devlink_rate->devlink_port = devlink_port;
-	devlink_rate->priv = priv;
-	list_add_tail(&devlink_rate->list, &devlink->rate_list);
-	devlink_port->devlink_rate = devlink_rate;
-	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devl_rate_leaf_create);
-
-/**
- * devl_rate_leaf_destroy - destroy devlink rate leaf
- *
- * @devlink_port: devlink port linked to the rate object
- *
- * Destroy the devlink rate object of type leaf on provided @devlink_port.
- */
-void devl_rate_leaf_destroy(struct devlink_port *devlink_port)
-{
-	struct devlink_rate *devlink_rate = devlink_port->devlink_rate;
-
-	devl_assert_locked(devlink_port->devlink);
-	if (!devlink_rate)
-		return;
-
-	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL);
-	if (devlink_rate->parent)
-		refcount_dec(&devlink_rate->parent->refcnt);
-	list_del(&devlink_rate->list);
-	devlink_port->devlink_rate = NULL;
-	kfree(devlink_rate);
-}
-EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy);
-
-/**
- * devl_rate_nodes_destroy - destroy all devlink rate nodes on device
- * @devlink: devlink instance
- *
- * Unset parent for all rate objects and destroy all rate nodes
- * on specified device.
- */
-void devl_rate_nodes_destroy(struct devlink *devlink)
-{
-	static struct devlink_rate *devlink_rate, *tmp;
-	const struct devlink_ops *ops = devlink->ops;
-
-	devl_assert_locked(devlink);
-
-	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
-		if (!devlink_rate->parent)
-			continue;
-
-		refcount_dec(&devlink_rate->parent->refcnt);
-		if (devlink_rate_is_leaf(devlink_rate))
-			ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv,
-						  NULL, NULL);
-		else if (devlink_rate_is_node(devlink_rate))
-			ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv,
-						  NULL, NULL);
-	}
-	list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) {
-		if (devlink_rate_is_node(devlink_rate)) {
-			ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL);
-			list_del(&devlink_rate->list);
-			kfree(devlink_rate->name);
-			kfree(devlink_rate);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(devl_rate_nodes_destroy);
-
-static int devlink_linecard_types_init(struct devlink_linecard *linecard)
-{
-	struct devlink_linecard_type *linecard_type;
-	unsigned int count;
-	int i;
-
-	count = linecard->ops->types_count(linecard, linecard->priv);
-	linecard->types = kmalloc_array(count, sizeof(*linecard_type),
-					GFP_KERNEL);
-	if (!linecard->types)
-		return -ENOMEM;
-	linecard->types_count = count;
-
-	for (i = 0; i < count; i++) {
-		linecard_type = &linecard->types[i];
-		linecard->ops->types_get(linecard, linecard->priv, i,
-					 &linecard_type->type,
-					 &linecard_type->priv);
-	}
-	return 0;
-}
-
-static void devlink_linecard_types_fini(struct devlink_linecard *linecard)
-{
-	kfree(linecard->types);
-}
-
-/**
- *	devl_linecard_create - Create devlink linecard
- *
- *	@devlink: devlink
- *	@linecard_index: driver-specific numerical identifier of the linecard
- *	@ops: linecards ops
- *	@priv: user priv pointer
- *
- *	Create devlink linecard instance with provided linecard index.
- *	Caller can use any indexing, even hw-related one.
- *
- *	Return: Line card structure or an ERR_PTR() encoded error code.
- */
-struct devlink_linecard *
-devl_linecard_create(struct devlink *devlink, unsigned int linecard_index,
-		     const struct devlink_linecard_ops *ops, void *priv)
-{
-	struct devlink_linecard *linecard;
-	int err;
-
-	if (WARN_ON(!ops || !ops->provision || !ops->unprovision ||
-		    !ops->types_count || !ops->types_get))
-		return ERR_PTR(-EINVAL);
-
-	if (devlink_linecard_index_exists(devlink, linecard_index))
-		return ERR_PTR(-EEXIST);
-
-	linecard = kzalloc(sizeof(*linecard), GFP_KERNEL);
-	if (!linecard)
-		return ERR_PTR(-ENOMEM);
-
-	linecard->devlink = devlink;
-	linecard->index = linecard_index;
-	linecard->ops = ops;
-	linecard->priv = priv;
-	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-	mutex_init(&linecard->state_lock);
-
-	err = devlink_linecard_types_init(linecard);
-	if (err) {
-		mutex_destroy(&linecard->state_lock);
-		kfree(linecard);
-		return ERR_PTR(err);
-	}
-
-	list_add_tail(&linecard->list, &devlink->linecard_list);
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	return linecard;
-}
-EXPORT_SYMBOL_GPL(devl_linecard_create);
-
-/**
- *	devl_linecard_destroy - Destroy devlink linecard
- *
- *	@linecard: devlink linecard
- */
-void devl_linecard_destroy(struct devlink_linecard *linecard)
-{
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
-	list_del(&linecard->list);
-	devlink_linecard_types_fini(linecard);
-	mutex_destroy(&linecard->state_lock);
-	kfree(linecard);
-}
-EXPORT_SYMBOL_GPL(devl_linecard_destroy);
-
-/**
- *	devlink_linecard_provision_set - Set provisioning on linecard
- *
- *	@linecard: devlink linecard
- *	@type: linecard type
- *
- *	This is either called directly from the provision() op call or
- *	as a result of the provision() op call asynchronously.
- */
-void devlink_linecard_provision_set(struct devlink_linecard *linecard,
-				    const char *type)
-{
-	mutex_lock(&linecard->state_lock);
-	WARN_ON(linecard->type && strcmp(linecard->type, type));
-	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED;
-	linecard->type = type;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_provision_set);
-
-/**
- *	devlink_linecard_provision_clear - Clear provisioning on linecard
- *
- *	@linecard: devlink linecard
- *
- *	This is either called directly from the unprovision() op call or
- *	as a result of the unprovision() op call asynchronously.
- */
-void devlink_linecard_provision_clear(struct devlink_linecard *linecard)
-{
-	mutex_lock(&linecard->state_lock);
-	WARN_ON(linecard->nested_devlink);
-	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-	linecard->type = NULL;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_provision_clear);
-
-/**
- *	devlink_linecard_provision_fail - Fail provisioning on linecard
- *
- *	@linecard: devlink linecard
- *
- *	This is either called directly from the provision() op call or
- *	as a result of the provision() op call asynchronously.
- */
-void devlink_linecard_provision_fail(struct devlink_linecard *linecard)
-{
-	mutex_lock(&linecard->state_lock);
-	WARN_ON(linecard->nested_devlink);
-	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING_FAILED;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_provision_fail);
-
-/**
- *	devlink_linecard_activate - Set linecard active
- *
- *	@linecard: devlink linecard
- */
-void devlink_linecard_activate(struct devlink_linecard *linecard)
-{
-	mutex_lock(&linecard->state_lock);
-	WARN_ON(linecard->state != DEVLINK_LINECARD_STATE_PROVISIONED);
-	linecard->state = DEVLINK_LINECARD_STATE_ACTIVE;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_activate);
-
-/**
- *	devlink_linecard_deactivate - Set linecard inactive
- *
- *	@linecard: devlink linecard
- */
-void devlink_linecard_deactivate(struct devlink_linecard *linecard)
-{
-	mutex_lock(&linecard->state_lock);
-	switch (linecard->state) {
-	case DEVLINK_LINECARD_STATE_ACTIVE:
-		linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		break;
-	case DEVLINK_LINECARD_STATE_UNPROVISIONING:
-		/* Line card is being deactivated as part
-		 * of unprovisioning flow.
-		 */
-		break;
-	default:
-		WARN_ON(1);
-		break;
-	}
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_deactivate);
-
-/**
- *	devlink_linecard_nested_dl_set - Attach/detach nested devlink
- *					 instance to linecard.
- *
- *	@linecard: devlink linecard
- *	@nested_devlink: devlink instance to attach or NULL to detach
- */
-void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard,
-				    struct devlink *nested_devlink)
-{
-	mutex_lock(&linecard->state_lock);
-	linecard->nested_devlink = nested_devlink;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set);
-
-#define DEVLINK_TRAP(_id, _type)					      \
-	{								      \
-		.type = DEVLINK_TRAP_TYPE_##_type,			      \
-		.id = DEVLINK_TRAP_GENERIC_ID_##_id,			      \
-		.name = DEVLINK_TRAP_GENERIC_NAME_##_id,		      \
-	}
-
-static const struct devlink_trap devlink_trap_generic[] = {
-	DEVLINK_TRAP(SMAC_MC, DROP),
-	DEVLINK_TRAP(VLAN_TAG_MISMATCH, DROP),
-	DEVLINK_TRAP(INGRESS_VLAN_FILTER, DROP),
-	DEVLINK_TRAP(INGRESS_STP_FILTER, DROP),
-	DEVLINK_TRAP(EMPTY_TX_LIST, DROP),
-	DEVLINK_TRAP(PORT_LOOPBACK_FILTER, DROP),
-	DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP),
-	DEVLINK_TRAP(TTL_ERROR, EXCEPTION),
-	DEVLINK_TRAP(TAIL_DROP, DROP),
-	DEVLINK_TRAP(NON_IP_PACKET, DROP),
-	DEVLINK_TRAP(UC_DIP_MC_DMAC, DROP),
-	DEVLINK_TRAP(DIP_LB, DROP),
-	DEVLINK_TRAP(SIP_MC, DROP),
-	DEVLINK_TRAP(SIP_LB, DROP),
-	DEVLINK_TRAP(CORRUPTED_IP_HDR, DROP),
-	DEVLINK_TRAP(IPV4_SIP_BC, DROP),
-	DEVLINK_TRAP(IPV6_MC_DIP_RESERVED_SCOPE, DROP),
-	DEVLINK_TRAP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, DROP),
-	DEVLINK_TRAP(MTU_ERROR, EXCEPTION),
-	DEVLINK_TRAP(UNRESOLVED_NEIGH, EXCEPTION),
-	DEVLINK_TRAP(RPF, EXCEPTION),
-	DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION),
-	DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION),
-	DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION),
-	DEVLINK_TRAP(NON_ROUTABLE, DROP),
-	DEVLINK_TRAP(DECAP_ERROR, EXCEPTION),
-	DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP),
-	DEVLINK_TRAP(INGRESS_FLOW_ACTION_DROP, DROP),
-	DEVLINK_TRAP(EGRESS_FLOW_ACTION_DROP, DROP),
-	DEVLINK_TRAP(STP, CONTROL),
-	DEVLINK_TRAP(LACP, CONTROL),
-	DEVLINK_TRAP(LLDP, CONTROL),
-	DEVLINK_TRAP(IGMP_QUERY, CONTROL),
-	DEVLINK_TRAP(IGMP_V1_REPORT, CONTROL),
-	DEVLINK_TRAP(IGMP_V2_REPORT, CONTROL),
-	DEVLINK_TRAP(IGMP_V3_REPORT, CONTROL),
-	DEVLINK_TRAP(IGMP_V2_LEAVE, CONTROL),
-	DEVLINK_TRAP(MLD_QUERY, CONTROL),
-	DEVLINK_TRAP(MLD_V1_REPORT, CONTROL),
-	DEVLINK_TRAP(MLD_V2_REPORT, CONTROL),
-	DEVLINK_TRAP(MLD_V1_DONE, CONTROL),
-	DEVLINK_TRAP(IPV4_DHCP, CONTROL),
-	DEVLINK_TRAP(IPV6_DHCP, CONTROL),
-	DEVLINK_TRAP(ARP_REQUEST, CONTROL),
-	DEVLINK_TRAP(ARP_RESPONSE, CONTROL),
-	DEVLINK_TRAP(ARP_OVERLAY, CONTROL),
-	DEVLINK_TRAP(IPV6_NEIGH_SOLICIT, CONTROL),
-	DEVLINK_TRAP(IPV6_NEIGH_ADVERT, CONTROL),
-	DEVLINK_TRAP(IPV4_BFD, CONTROL),
-	DEVLINK_TRAP(IPV6_BFD, CONTROL),
-	DEVLINK_TRAP(IPV4_OSPF, CONTROL),
-	DEVLINK_TRAP(IPV6_OSPF, CONTROL),
-	DEVLINK_TRAP(IPV4_BGP, CONTROL),
-	DEVLINK_TRAP(IPV6_BGP, CONTROL),
-	DEVLINK_TRAP(IPV4_VRRP, CONTROL),
-	DEVLINK_TRAP(IPV6_VRRP, CONTROL),
-	DEVLINK_TRAP(IPV4_PIM, CONTROL),
-	DEVLINK_TRAP(IPV6_PIM, CONTROL),
-	DEVLINK_TRAP(UC_LB, CONTROL),
-	DEVLINK_TRAP(LOCAL_ROUTE, CONTROL),
-	DEVLINK_TRAP(EXTERNAL_ROUTE, CONTROL),
-	DEVLINK_TRAP(IPV6_UC_DIP_LINK_LOCAL_SCOPE, CONTROL),
-	DEVLINK_TRAP(IPV6_DIP_ALL_NODES, CONTROL),
-	DEVLINK_TRAP(IPV6_DIP_ALL_ROUTERS, CONTROL),
-	DEVLINK_TRAP(IPV6_ROUTER_SOLICIT, CONTROL),
-	DEVLINK_TRAP(IPV6_ROUTER_ADVERT, CONTROL),
-	DEVLINK_TRAP(IPV6_REDIRECT, CONTROL),
-	DEVLINK_TRAP(IPV4_ROUTER_ALERT, CONTROL),
-	DEVLINK_TRAP(IPV6_ROUTER_ALERT, CONTROL),
-	DEVLINK_TRAP(PTP_EVENT, CONTROL),
-	DEVLINK_TRAP(PTP_GENERAL, CONTROL),
-	DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL),
-	DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL),
-	DEVLINK_TRAP(EARLY_DROP, DROP),
-	DEVLINK_TRAP(VXLAN_PARSING, DROP),
-	DEVLINK_TRAP(LLC_SNAP_PARSING, DROP),
-	DEVLINK_TRAP(VLAN_PARSING, DROP),
-	DEVLINK_TRAP(PPPOE_PPP_PARSING, DROP),
-	DEVLINK_TRAP(MPLS_PARSING, DROP),
-	DEVLINK_TRAP(ARP_PARSING, DROP),
-	DEVLINK_TRAP(IP_1_PARSING, DROP),
-	DEVLINK_TRAP(IP_N_PARSING, DROP),
-	DEVLINK_TRAP(GRE_PARSING, DROP),
-	DEVLINK_TRAP(UDP_PARSING, DROP),
-	DEVLINK_TRAP(TCP_PARSING, DROP),
-	DEVLINK_TRAP(IPSEC_PARSING, DROP),
-	DEVLINK_TRAP(SCTP_PARSING, DROP),
-	DEVLINK_TRAP(DCCP_PARSING, DROP),
-	DEVLINK_TRAP(GTP_PARSING, DROP),
-	DEVLINK_TRAP(ESP_PARSING, DROP),
-	DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP),
-	DEVLINK_TRAP(DMAC_FILTER, DROP),
-	DEVLINK_TRAP(EAPOL, CONTROL),
-	DEVLINK_TRAP(LOCKED_PORT, DROP),
-};
-
-#define DEVLINK_TRAP_GROUP(_id)						      \
-	{								      \
-		.id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id,		      \
-		.name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id,		      \
-	}
-
-static const struct devlink_trap_group devlink_trap_group_generic[] = {
-	DEVLINK_TRAP_GROUP(L2_DROPS),
-	DEVLINK_TRAP_GROUP(L3_DROPS),
-	DEVLINK_TRAP_GROUP(L3_EXCEPTIONS),
-	DEVLINK_TRAP_GROUP(BUFFER_DROPS),
-	DEVLINK_TRAP_GROUP(TUNNEL_DROPS),
-	DEVLINK_TRAP_GROUP(ACL_DROPS),
-	DEVLINK_TRAP_GROUP(STP),
-	DEVLINK_TRAP_GROUP(LACP),
-	DEVLINK_TRAP_GROUP(LLDP),
-	DEVLINK_TRAP_GROUP(MC_SNOOPING),
-	DEVLINK_TRAP_GROUP(DHCP),
-	DEVLINK_TRAP_GROUP(NEIGH_DISCOVERY),
-	DEVLINK_TRAP_GROUP(BFD),
-	DEVLINK_TRAP_GROUP(OSPF),
-	DEVLINK_TRAP_GROUP(BGP),
-	DEVLINK_TRAP_GROUP(VRRP),
-	DEVLINK_TRAP_GROUP(PIM),
-	DEVLINK_TRAP_GROUP(UC_LB),
-	DEVLINK_TRAP_GROUP(LOCAL_DELIVERY),
-	DEVLINK_TRAP_GROUP(EXTERNAL_DELIVERY),
-	DEVLINK_TRAP_GROUP(IPV6),
-	DEVLINK_TRAP_GROUP(PTP_EVENT),
-	DEVLINK_TRAP_GROUP(PTP_GENERAL),
-	DEVLINK_TRAP_GROUP(ACL_SAMPLE),
-	DEVLINK_TRAP_GROUP(ACL_TRAP),
-	DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS),
-	DEVLINK_TRAP_GROUP(EAPOL),
-};
-
-static int devlink_trap_generic_verify(const struct devlink_trap *trap)
-{
-	if (trap->id > DEVLINK_TRAP_GENERIC_ID_MAX)
-		return -EINVAL;
-
-	if (strcmp(trap->name, devlink_trap_generic[trap->id].name))
-		return -EINVAL;
-
-	if (trap->type != devlink_trap_generic[trap->id].type)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int devlink_trap_driver_verify(const struct devlink_trap *trap)
-{
-	int i;
-
-	if (trap->id <= DEVLINK_TRAP_GENERIC_ID_MAX)
-		return -EINVAL;
-
-	for (i = 0; i < ARRAY_SIZE(devlink_trap_generic); i++) {
-		if (!strcmp(trap->name, devlink_trap_generic[i].name))
-			return -EEXIST;
-	}
-
-	return 0;
-}
-
-static int devlink_trap_verify(const struct devlink_trap *trap)
-{
-	if (!trap || !trap->name)
-		return -EINVAL;
-
-	if (trap->generic)
-		return devlink_trap_generic_verify(trap);
-	else
-		return devlink_trap_driver_verify(trap);
-}
-
-static int
-devlink_trap_group_generic_verify(const struct devlink_trap_group *group)
-{
-	if (group->id > DEVLINK_TRAP_GROUP_GENERIC_ID_MAX)
-		return -EINVAL;
-
-	if (strcmp(group->name, devlink_trap_group_generic[group->id].name))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int
-devlink_trap_group_driver_verify(const struct devlink_trap_group *group)
-{
-	int i;
-
-	if (group->id <= DEVLINK_TRAP_GROUP_GENERIC_ID_MAX)
-		return -EINVAL;
-
-	for (i = 0; i < ARRAY_SIZE(devlink_trap_group_generic); i++) {
-		if (!strcmp(group->name, devlink_trap_group_generic[i].name))
-			return -EEXIST;
-	}
-
-	return 0;
-}
-
-static int devlink_trap_group_verify(const struct devlink_trap_group *group)
-{
-	if (group->generic)
-		return devlink_trap_group_generic_verify(group);
-	else
-		return devlink_trap_group_driver_verify(group);
-}
-
-static void
-devlink_trap_group_notify(struct devlink *devlink,
-			  const struct devlink_trap_group_item *group_item,
-			  enum devlink_command cmd)
-{
-	struct sk_buff *msg;
-	int err;
-
-	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW &&
-		     cmd != DEVLINK_CMD_TRAP_GROUP_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
-		return;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return;
-
-	err = devlink_nl_trap_group_fill(msg, devlink, group_item, cmd, 0, 0,
-					 0);
-	if (err) {
-		nlmsg_free(msg);
-		return;
-	}
-
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
-}
-
-static void devlink_trap_groups_notify_register(struct devlink *devlink)
-{
-	struct devlink_trap_group_item *group_item;
+const struct genl_small_ops devlink_nl_small_ops[40] = {
+	{
+		.cmd = DEVLINK_CMD_PORT_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_port_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_SET,
+		.doit = devlink_nl_cmd_rate_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_NEW,
+		.doit = devlink_nl_cmd_rate_new_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_DEL,
+		.doit = devlink_nl_cmd_rate_del_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_SPLIT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_port_split_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_UNSPLIT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_port_unsplit_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_NEW,
+		.doit = devlink_nl_cmd_port_new_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_DEL,
+		.doit = devlink_nl_cmd_port_del_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
 
-	list_for_each_entry(group_item, &devlink->trap_group_list, list)
-		devlink_trap_group_notify(devlink, group_item,
-					  DEVLINK_CMD_TRAP_GROUP_NEW);
-}
+	{
+		.cmd = DEVLINK_CMD_LINECARD_SET,
+		.doit = devlink_nl_cmd_linecard_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_SB_POOL_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_sb_pool_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_SB_PORT_POOL_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_sb_port_pool_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_sb_occ_snapshot_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_sb_occ_max_clear_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_ESWITCH_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_eswitch_get_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_ESWITCH_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_eswitch_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_dpipe_table_get,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_dpipe_entries_get,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_dpipe_headers_get,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_dpipe_table_counters_set,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_RESOURCE_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_resource_set,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_RESOURCE_DUMP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_resource_dump,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_RELOAD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_reload,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_PARAM_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_param_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_PARAM_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_port_param_get_doit,
+		.dumpit = devlink_nl_cmd_port_param_get_dumpit,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_PARAM_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_port_param_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_REGION_NEW,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_region_new,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_REGION_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_region_del,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_REGION_READ,
+		.validate = GENL_DONT_VALIDATE_STRICT |
+			    GENL_DONT_VALIDATE_DUMP_STRICT,
+		.dumpit = devlink_nl_cmd_region_read_dumpit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_recover_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_diagnose_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT |
+			    GENL_DONT_VALIDATE_DUMP_STRICT,
+		.dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_dump_clear_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_test_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_FLASH_UPDATE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_flash_update,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_TRAP_SET,
+		.doit = devlink_nl_cmd_trap_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_TRAP_GROUP_SET,
+		.doit = devlink_nl_cmd_trap_group_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_TRAP_POLICER_SET,
+		.doit = devlink_nl_cmd_trap_policer_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_SELFTESTS_RUN,
+		.doit = devlink_nl_cmd_selftests_run,
+		.flags = GENL_ADMIN_PERM,
+	},
+	/* -- No new ops here! Use split ops going forward! -- */
+};
 
-static void devlink_trap_groups_notify_unregister(struct devlink *devlink)
+void devlink_notify_register(struct devlink *devlink)
 {
-	struct devlink_trap_group_item *group_item;
-
-	list_for_each_entry_reverse(group_item, &devlink->trap_group_list, list)
-		devlink_trap_group_notify(devlink, group_item,
-					  DEVLINK_CMD_TRAP_GROUP_DEL);
+	devlink_notify(devlink, DEVLINK_CMD_NEW);
+	devlink_linecards_notify_register(devlink);
+	devlink_ports_notify_register(devlink);
+	devlink_trap_policers_notify_register(devlink);
+	devlink_trap_groups_notify_register(devlink);
+	devlink_traps_notify_register(devlink);
+	devlink_rates_notify_register(devlink);
+	devlink_regions_notify_register(devlink);
+	devlink_params_notify_register(devlink);
 }
 
-static int
-devlink_trap_item_group_link(struct devlink *devlink,
-			     struct devlink_trap_item *trap_item)
+void devlink_notify_unregister(struct devlink *devlink)
 {
-	u16 group_id = trap_item->trap->init_group_id;
-	struct devlink_trap_group_item *group_item;
-
-	group_item = devlink_trap_group_item_lookup_by_id(devlink, group_id);
-	if (WARN_ON_ONCE(!group_item))
-		return -EINVAL;
-
-	trap_item->group_item = group_item;
-
-	return 0;
+	devlink_params_notify_unregister(devlink);
+	devlink_regions_notify_unregister(devlink);
+	devlink_rates_notify_unregister(devlink);
+	devlink_traps_notify_unregister(devlink);
+	devlink_trap_groups_notify_unregister(devlink);
+	devlink_trap_policers_notify_unregister(devlink);
+	devlink_ports_notify_unregister(devlink);
+	devlink_linecards_notify_unregister(devlink);
+	devlink_notify(devlink, DEVLINK_CMD_DEL);
 }
 
-static void devlink_trap_notify(struct devlink *devlink,
-				const struct devlink_trap_item *trap_item,
-				enum devlink_command cmd)
+/**
+ * devl_rate_node_create - create devlink rate node
+ * @devlink: devlink instance
+ * @priv: driver private data
+ * @node_name: name of the resulting node
+ * @parent: parent devlink_rate struct
+ *
+ * Create devlink rate object of type node
+ */
+struct devlink_rate *
+devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,
+		      struct devlink_rate *parent)
 {
-	struct sk_buff *msg;
-	int err;
+	struct devlink_rate *rate_node;
 
-	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW &&
-		     cmd != DEVLINK_CMD_TRAP_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
-		return;
+	rate_node = devlink_rate_node_get_by_name(devlink, node_name);
+	if (!IS_ERR(rate_node))
+		return ERR_PTR(-EEXIST);
 
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return;
+	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
+	if (!rate_node)
+		return ERR_PTR(-ENOMEM);
 
-	err = devlink_nl_trap_fill(msg, devlink, trap_item, cmd, 0, 0, 0);
-	if (err) {
-		nlmsg_free(msg);
-		return;
+	if (parent) {
+		rate_node->parent = parent;
+		refcount_inc(&rate_node->parent->refcnt);
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
-}
-
-static void devlink_traps_notify_register(struct devlink *devlink)
-{
-	struct devlink_trap_item *trap_item;
-
-	list_for_each_entry(trap_item, &devlink->trap_list, list)
-		devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW);
-}
-
-static void devlink_traps_notify_unregister(struct devlink *devlink)
-{
-	struct devlink_trap_item *trap_item;
-
-	list_for_each_entry_reverse(trap_item, &devlink->trap_list, list)
-		devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL);
-}
-
-static int
-devlink_trap_register(struct devlink *devlink,
-		      const struct devlink_trap *trap, void *priv)
-{
-	struct devlink_trap_item *trap_item;
-	int err;
-
-	if (devlink_trap_item_lookup(devlink, trap->name))
-		return -EEXIST;
-
-	trap_item = kzalloc(sizeof(*trap_item), GFP_KERNEL);
-	if (!trap_item)
-		return -ENOMEM;
+	rate_node->type = DEVLINK_RATE_TYPE_NODE;
+	rate_node->devlink = devlink;
+	rate_node->priv = priv;
 
-	trap_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats);
-	if (!trap_item->stats) {
-		err = -ENOMEM;
-		goto err_stats_alloc;
+	rate_node->name = kstrdup(node_name, GFP_KERNEL);
+	if (!rate_node->name) {
+		kfree(rate_node);
+		return ERR_PTR(-ENOMEM);
 	}
 
-	trap_item->trap = trap;
-	trap_item->action = trap->init_action;
-	trap_item->priv = priv;
-
-	err = devlink_trap_item_group_link(devlink, trap_item);
-	if (err)
-		goto err_group_link;
-
-	err = devlink->ops->trap_init(devlink, trap, trap_item);
-	if (err)
-		goto err_trap_init;
-
-	list_add_tail(&trap_item->list, &devlink->trap_list);
-	devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW);
-
-	return 0;
-
-err_trap_init:
-err_group_link:
-	free_percpu(trap_item->stats);
-err_stats_alloc:
-	kfree(trap_item);
-	return err;
-}
-
-static void devlink_trap_unregister(struct devlink *devlink,
-				    const struct devlink_trap *trap)
-{
-	struct devlink_trap_item *trap_item;
-
-	trap_item = devlink_trap_item_lookup(devlink, trap->name);
-	if (WARN_ON_ONCE(!trap_item))
-		return;
-
-	devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL);
-	list_del(&trap_item->list);
-	if (devlink->ops->trap_fini)
-		devlink->ops->trap_fini(devlink, trap, trap_item);
-	free_percpu(trap_item->stats);
-	kfree(trap_item);
-}
-
-static void devlink_trap_disable(struct devlink *devlink,
-				 const struct devlink_trap *trap)
-{
-	struct devlink_trap_item *trap_item;
-
-	trap_item = devlink_trap_item_lookup(devlink, trap->name);
-	if (WARN_ON_ONCE(!trap_item))
-		return;
-
-	devlink->ops->trap_action_set(devlink, trap, DEVLINK_TRAP_ACTION_DROP,
-				      NULL);
-	trap_item->action = DEVLINK_TRAP_ACTION_DROP;
+	refcount_set(&rate_node->refcnt, 1);
+	list_add(&rate_node->list, &devlink->rate_list);
+	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+	return rate_node;
 }
+EXPORT_SYMBOL_GPL(devl_rate_node_create);
 
 /**
- * devl_traps_register - Register packet traps with devlink.
- * @devlink: devlink.
- * @traps: Packet traps.
- * @traps_count: Count of provided packet traps.
- * @priv: Driver private information.
+ * devl_rate_leaf_create - create devlink rate leaf
+ * @devlink_port: devlink port object to create rate object on
+ * @priv: driver private data
+ * @parent: parent devlink_rate struct
  *
- * Return: Non-zero value on failure.
+ * Create devlink rate object of type leaf on provided @devlink_port.
  */
-int devl_traps_register(struct devlink *devlink,
-			const struct devlink_trap *traps,
-			size_t traps_count, void *priv)
+int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv,
+			  struct devlink_rate *parent)
 {
-	int i, err;
+	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_rate *devlink_rate;
 
-	if (!devlink->ops->trap_init || !devlink->ops->trap_action_set)
-		return -EINVAL;
+	devl_assert_locked(devlink_port->devlink);
 
-	devl_assert_locked(devlink);
-	for (i = 0; i < traps_count; i++) {
-		const struct devlink_trap *trap = &traps[i];
+	if (WARN_ON(devlink_port->devlink_rate))
+		return -EBUSY;
 
-		err = devlink_trap_verify(trap);
-		if (err)
-			goto err_trap_verify;
+	devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL);
+	if (!devlink_rate)
+		return -ENOMEM;
 
-		err = devlink_trap_register(devlink, trap, priv);
-		if (err)
-			goto err_trap_register;
+	if (parent) {
+		devlink_rate->parent = parent;
+		refcount_inc(&devlink_rate->parent->refcnt);
 	}
 
-	return 0;
+	devlink_rate->type = DEVLINK_RATE_TYPE_LEAF;
+	devlink_rate->devlink = devlink;
+	devlink_rate->devlink_port = devlink_port;
+	devlink_rate->priv = priv;
+	list_add_tail(&devlink_rate->list, &devlink->rate_list);
+	devlink_port->devlink_rate = devlink_rate;
+	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
 
-err_trap_register:
-err_trap_verify:
-	for (i--; i >= 0; i--)
-		devlink_trap_unregister(devlink, &traps[i]);
-	return err;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(devl_traps_register);
+EXPORT_SYMBOL_GPL(devl_rate_leaf_create);
 
 /**
- * devlink_traps_register - Register packet traps with devlink.
- * @devlink: devlink.
- * @traps: Packet traps.
- * @traps_count: Count of provided packet traps.
- * @priv: Driver private information.
- *
- * Context: Takes and release devlink->lock <mutex>.
+ * devl_rate_leaf_destroy - destroy devlink rate leaf
  *
- * Return: Non-zero value on failure.
- */
-int devlink_traps_register(struct devlink *devlink,
-			   const struct devlink_trap *traps,
-			   size_t traps_count, void *priv)
-{
-	int err;
-
-	devl_lock(devlink);
-	err = devl_traps_register(devlink, traps, traps_count, priv);
-	devl_unlock(devlink);
-	return err;
-}
-EXPORT_SYMBOL_GPL(devlink_traps_register);
-
-/**
- * devl_traps_unregister - Unregister packet traps from devlink.
- * @devlink: devlink.
- * @traps: Packet traps.
- * @traps_count: Count of provided packet traps.
- */
-void devl_traps_unregister(struct devlink *devlink,
-			   const struct devlink_trap *traps,
-			   size_t traps_count)
-{
-	int i;
-
-	devl_assert_locked(devlink);
-	/* Make sure we do not have any packets in-flight while unregistering
-	 * traps by disabling all of them and waiting for a grace period.
-	 */
-	for (i = traps_count - 1; i >= 0; i--)
-		devlink_trap_disable(devlink, &traps[i]);
-	synchronize_rcu();
-	for (i = traps_count - 1; i >= 0; i--)
-		devlink_trap_unregister(devlink, &traps[i]);
-}
-EXPORT_SYMBOL_GPL(devl_traps_unregister);
-
-/**
- * devlink_traps_unregister - Unregister packet traps from devlink.
- * @devlink: devlink.
- * @traps: Packet traps.
- * @traps_count: Count of provided packet traps.
+ * @devlink_port: devlink port linked to the rate object
  *
- * Context: Takes and release devlink->lock <mutex>.
- */
-void devlink_traps_unregister(struct devlink *devlink,
-			      const struct devlink_trap *traps,
-			      size_t traps_count)
-{
-	devl_lock(devlink);
-	devl_traps_unregister(devlink, traps, traps_count);
-	devl_unlock(devlink);
-}
-EXPORT_SYMBOL_GPL(devlink_traps_unregister);
-
-static void
-devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats,
-			  size_t skb_len)
-{
-	struct devlink_stats *stats;
-
-	stats = this_cpu_ptr(trap_stats);
-	u64_stats_update_begin(&stats->syncp);
-	u64_stats_add(&stats->rx_bytes, skb_len);
-	u64_stats_inc(&stats->rx_packets);
-	u64_stats_update_end(&stats->syncp);
-}
-
-static void
-devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata,
-				 const struct devlink_trap_item *trap_item,
-				 struct devlink_port *in_devlink_port,
-				 const struct flow_action_cookie *fa_cookie)
-{
-	metadata->trap_name = trap_item->trap->name;
-	metadata->trap_group_name = trap_item->group_item->group->name;
-	metadata->fa_cookie = fa_cookie;
-	metadata->trap_type = trap_item->trap->type;
-
-	spin_lock(&in_devlink_port->type_lock);
-	if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH)
-		metadata->input_dev = in_devlink_port->type_eth.netdev;
-	spin_unlock(&in_devlink_port->type_lock);
-}
-
-/**
- * devlink_trap_report - Report trapped packet to drop monitor.
- * @devlink: devlink.
- * @skb: Trapped packet.
- * @trap_ctx: Trap context.
- * @in_devlink_port: Input devlink port.
- * @fa_cookie: Flow action cookie. Could be NULL.
+ * Destroy the devlink rate object of type leaf on provided @devlink_port.
  */
-void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
-			 void *trap_ctx, struct devlink_port *in_devlink_port,
-			 const struct flow_action_cookie *fa_cookie)
-
+void devl_rate_leaf_destroy(struct devlink_port *devlink_port)
 {
-	struct devlink_trap_item *trap_item = trap_ctx;
-
-	devlink_trap_stats_update(trap_item->stats, skb->len);
-	devlink_trap_stats_update(trap_item->group_item->stats, skb->len);
+	struct devlink_rate *devlink_rate = devlink_port->devlink_rate;
 
-	if (tracepoint_enabled(devlink_trap_report)) {
-		struct devlink_trap_metadata metadata = {};
+	devl_assert_locked(devlink_port->devlink);
+	if (!devlink_rate)
+		return;
 
-		devlink_trap_report_metadata_set(&metadata, trap_item,
-						 in_devlink_port, fa_cookie);
-		trace_devlink_trap_report(devlink, skb, &metadata);
-	}
+	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL);
+	if (devlink_rate->parent)
+		refcount_dec(&devlink_rate->parent->refcnt);
+	list_del(&devlink_rate->list);
+	devlink_port->devlink_rate = NULL;
+	kfree(devlink_rate);
 }
-EXPORT_SYMBOL_GPL(devlink_trap_report);
+EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy);
 
 /**
- * devlink_trap_ctx_priv - Trap context to driver private information.
- * @trap_ctx: Trap context.
+ * devl_rate_nodes_destroy - destroy all devlink rate nodes on device
+ * @devlink: devlink instance
  *
- * Return: Driver private information passed during registration.
+ * Unset parent for all rate objects and destroy all rate nodes
+ * on specified device.
  */
-void *devlink_trap_ctx_priv(void *trap_ctx)
-{
-	struct devlink_trap_item *trap_item = trap_ctx;
-
-	return trap_item->priv;
-}
-EXPORT_SYMBOL_GPL(devlink_trap_ctx_priv);
-
-static int
-devlink_trap_group_item_policer_link(struct devlink *devlink,
-				     struct devlink_trap_group_item *group_item)
-{
-	u32 policer_id = group_item->group->init_policer_id;
-	struct devlink_trap_policer_item *policer_item;
-
-	if (policer_id == 0)
-		return 0;
-
-	policer_item = devlink_trap_policer_item_lookup(devlink, policer_id);
-	if (WARN_ON_ONCE(!policer_item))
-		return -EINVAL;
-
-	group_item->policer_item = policer_item;
-
-	return 0;
-}
-
-static int
-devlink_trap_group_register(struct devlink *devlink,
-			    const struct devlink_trap_group *group)
+void devl_rate_nodes_destroy(struct devlink *devlink)
 {
-	struct devlink_trap_group_item *group_item;
-	int err;
+	static struct devlink_rate *devlink_rate, *tmp;
+	const struct devlink_ops *ops = devlink->ops;
 
-	if (devlink_trap_group_item_lookup(devlink, group->name))
-		return -EEXIST;
+	devl_assert_locked(devlink);
 
-	group_item = kzalloc(sizeof(*group_item), GFP_KERNEL);
-	if (!group_item)
-		return -ENOMEM;
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+		if (!devlink_rate->parent)
+			continue;
 
-	group_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats);
-	if (!group_item->stats) {
-		err = -ENOMEM;
-		goto err_stats_alloc;
+		refcount_dec(&devlink_rate->parent->refcnt);
+		if (devlink_rate_is_leaf(devlink_rate))
+			ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv,
+						  NULL, NULL);
+		else if (devlink_rate_is_node(devlink_rate))
+			ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv,
+						  NULL, NULL);
+	}
+	list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) {
+		if (devlink_rate_is_node(devlink_rate)) {
+			ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL);
+			list_del(&devlink_rate->list);
+			kfree(devlink_rate->name);
+			kfree(devlink_rate);
+		}
 	}
+}
+EXPORT_SYMBOL_GPL(devl_rate_nodes_destroy);
 
-	group_item->group = group;
+static int devlink_linecard_types_init(struct devlink_linecard *linecard)
+{
+	struct devlink_linecard_type *linecard_type;
+	unsigned int count;
+	int i;
 
-	err = devlink_trap_group_item_policer_link(devlink, group_item);
-	if (err)
-		goto err_policer_link;
+	count = linecard->ops->types_count(linecard, linecard->priv);
+	linecard->types = kmalloc_array(count, sizeof(*linecard_type),
+					GFP_KERNEL);
+	if (!linecard->types)
+		return -ENOMEM;
+	linecard->types_count = count;
 
-	if (devlink->ops->trap_group_init) {
-		err = devlink->ops->trap_group_init(devlink, group);
-		if (err)
-			goto err_group_init;
+	for (i = 0; i < count; i++) {
+		linecard_type = &linecard->types[i];
+		linecard->ops->types_get(linecard, linecard->priv, i,
+					 &linecard_type->type,
+					 &linecard_type->priv);
 	}
-
-	list_add_tail(&group_item->list, &devlink->trap_group_list);
-	devlink_trap_group_notify(devlink, group_item,
-				  DEVLINK_CMD_TRAP_GROUP_NEW);
-
 	return 0;
-
-err_group_init:
-err_policer_link:
-	free_percpu(group_item->stats);
-err_stats_alloc:
-	kfree(group_item);
-	return err;
 }
 
-static void
-devlink_trap_group_unregister(struct devlink *devlink,
-			      const struct devlink_trap_group *group)
+static void devlink_linecard_types_fini(struct devlink_linecard *linecard)
 {
-	struct devlink_trap_group_item *group_item;
-
-	group_item = devlink_trap_group_item_lookup(devlink, group->name);
-	if (WARN_ON_ONCE(!group_item))
-		return;
-
-	devlink_trap_group_notify(devlink, group_item,
-				  DEVLINK_CMD_TRAP_GROUP_DEL);
-	list_del(&group_item->list);
-	free_percpu(group_item->stats);
-	kfree(group_item);
+	kfree(linecard->types);
 }
 
 /**
- * devl_trap_groups_register - Register packet trap groups with devlink.
- * @devlink: devlink.
- * @groups: Packet trap groups.
- * @groups_count: Count of provided packet trap groups.
+ *	devl_linecard_create - Create devlink linecard
+ *
+ *	@devlink: devlink
+ *	@linecard_index: driver-specific numerical identifier of the linecard
+ *	@ops: linecards ops
+ *	@priv: user priv pointer
  *
- * Return: Non-zero value on failure.
+ *	Create devlink linecard instance with provided linecard index.
+ *	Caller can use any indexing, even hw-related one.
+ *
+ *	Return: Line card structure or an ERR_PTR() encoded error code.
  */
-int devl_trap_groups_register(struct devlink *devlink,
-			      const struct devlink_trap_group *groups,
-			      size_t groups_count)
+struct devlink_linecard *
+devl_linecard_create(struct devlink *devlink, unsigned int linecard_index,
+		     const struct devlink_linecard_ops *ops, void *priv)
 {
-	int i, err;
+	struct devlink_linecard *linecard;
+	int err;
 
-	devl_assert_locked(devlink);
-	for (i = 0; i < groups_count; i++) {
-		const struct devlink_trap_group *group = &groups[i];
+	if (WARN_ON(!ops || !ops->provision || !ops->unprovision ||
+		    !ops->types_count || !ops->types_get))
+		return ERR_PTR(-EINVAL);
 
-		err = devlink_trap_group_verify(group);
-		if (err)
-			goto err_trap_group_verify;
+	if (devlink_linecard_index_exists(devlink, linecard_index))
+		return ERR_PTR(-EEXIST);
 
-		err = devlink_trap_group_register(devlink, group);
-		if (err)
-			goto err_trap_group_register;
-	}
+	linecard = kzalloc(sizeof(*linecard), GFP_KERNEL);
+	if (!linecard)
+		return ERR_PTR(-ENOMEM);
 
-	return 0;
+	linecard->devlink = devlink;
+	linecard->index = linecard_index;
+	linecard->ops = ops;
+	linecard->priv = priv;
+	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+	mutex_init(&linecard->state_lock);
 
-err_trap_group_register:
-err_trap_group_verify:
-	for (i--; i >= 0; i--)
-		devlink_trap_group_unregister(devlink, &groups[i]);
-	return err;
+	err = devlink_linecard_types_init(linecard);
+	if (err) {
+		mutex_destroy(&linecard->state_lock);
+		kfree(linecard);
+		return ERR_PTR(err);
+	}
+
+	list_add_tail(&linecard->list, &devlink->linecard_list);
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	return linecard;
 }
-EXPORT_SYMBOL_GPL(devl_trap_groups_register);
+EXPORT_SYMBOL_GPL(devl_linecard_create);
 
 /**
- * devlink_trap_groups_register - Register packet trap groups with devlink.
- * @devlink: devlink.
- * @groups: Packet trap groups.
- * @groups_count: Count of provided packet trap groups.
- *
- * Context: Takes and release devlink->lock <mutex>.
+ *	devl_linecard_destroy - Destroy devlink linecard
  *
- * Return: Non-zero value on failure.
+ *	@linecard: devlink linecard
  */
-int devlink_trap_groups_register(struct devlink *devlink,
-				 const struct devlink_trap_group *groups,
-				 size_t groups_count)
+void devl_linecard_destroy(struct devlink_linecard *linecard)
 {
-	int err;
-
-	devl_lock(devlink);
-	err = devl_trap_groups_register(devlink, groups, groups_count);
-	devl_unlock(devlink);
-	return err;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
+	list_del(&linecard->list);
+	devlink_linecard_types_fini(linecard);
+	mutex_destroy(&linecard->state_lock);
+	kfree(linecard);
 }
-EXPORT_SYMBOL_GPL(devlink_trap_groups_register);
+EXPORT_SYMBOL_GPL(devl_linecard_destroy);
 
 /**
- * devl_trap_groups_unregister - Unregister packet trap groups from devlink.
- * @devlink: devlink.
- * @groups: Packet trap groups.
- * @groups_count: Count of provided packet trap groups.
+ *	devlink_linecard_provision_set - Set provisioning on linecard
+ *
+ *	@linecard: devlink linecard
+ *	@type: linecard type
+ *
+ *	This is either called directly from the provision() op call or
+ *	as a result of the provision() op call asynchronously.
  */
-void devl_trap_groups_unregister(struct devlink *devlink,
-				 const struct devlink_trap_group *groups,
-				 size_t groups_count)
+void devlink_linecard_provision_set(struct devlink_linecard *linecard,
+				    const char *type)
 {
-	int i;
-
-	devl_assert_locked(devlink);
-	for (i = groups_count - 1; i >= 0; i--)
-		devlink_trap_group_unregister(devlink, &groups[i]);
+	mutex_lock(&linecard->state_lock);
+	WARN_ON(linecard->type && strcmp(linecard->type, type));
+	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED;
+	linecard->type = type;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
 }
-EXPORT_SYMBOL_GPL(devl_trap_groups_unregister);
+EXPORT_SYMBOL_GPL(devlink_linecard_provision_set);
 
 /**
- * devlink_trap_groups_unregister - Unregister packet trap groups from devlink.
- * @devlink: devlink.
- * @groups: Packet trap groups.
- * @groups_count: Count of provided packet trap groups.
+ *	devlink_linecard_provision_clear - Clear provisioning on linecard
+ *
+ *	@linecard: devlink linecard
  *
- * Context: Takes and release devlink->lock <mutex>.
+ *	This is either called directly from the unprovision() op call or
+ *	as a result of the unprovision() op call asynchronously.
  */
-void devlink_trap_groups_unregister(struct devlink *devlink,
-				    const struct devlink_trap_group *groups,
-				    size_t groups_count)
-{
-	devl_lock(devlink);
-	devl_trap_groups_unregister(devlink, groups, groups_count);
-	devl_unlock(devlink);
-}
-EXPORT_SYMBOL_GPL(devlink_trap_groups_unregister);
-
-static void
-devlink_trap_policer_notify(struct devlink *devlink,
-			    const struct devlink_trap_policer_item *policer_item,
-			    enum devlink_command cmd)
-{
-	struct sk_buff *msg;
-	int err;
-
-	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_POLICER_NEW &&
-		     cmd != DEVLINK_CMD_TRAP_POLICER_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
-		return;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return;
-
-	err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, cmd, 0,
-					   0, 0);
-	if (err) {
-		nlmsg_free(msg);
-		return;
-	}
-
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
-}
-
-static void devlink_trap_policers_notify_register(struct devlink *devlink)
-{
-	struct devlink_trap_policer_item *policer_item;
-
-	list_for_each_entry(policer_item, &devlink->trap_policer_list, list)
-		devlink_trap_policer_notify(devlink, policer_item,
-					    DEVLINK_CMD_TRAP_POLICER_NEW);
-}
-
-static void devlink_trap_policers_notify_unregister(struct devlink *devlink)
+void devlink_linecard_provision_clear(struct devlink_linecard *linecard)
 {
-	struct devlink_trap_policer_item *policer_item;
-
-	list_for_each_entry_reverse(policer_item, &devlink->trap_policer_list,
-				    list)
-		devlink_trap_policer_notify(devlink, policer_item,
-					    DEVLINK_CMD_TRAP_POLICER_DEL);
+	mutex_lock(&linecard->state_lock);
+	WARN_ON(linecard->nested_devlink);
+	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+	linecard->type = NULL;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
 }
+EXPORT_SYMBOL_GPL(devlink_linecard_provision_clear);
 
-static int
-devlink_trap_policer_register(struct devlink *devlink,
-			      const struct devlink_trap_policer *policer)
+/**
+ *	devlink_linecard_provision_fail - Fail provisioning on linecard
+ *
+ *	@linecard: devlink linecard
+ *
+ *	This is either called directly from the provision() op call or
+ *	as a result of the provision() op call asynchronously.
+ */
+void devlink_linecard_provision_fail(struct devlink_linecard *linecard)
 {
-	struct devlink_trap_policer_item *policer_item;
-	int err;
-
-	if (devlink_trap_policer_item_lookup(devlink, policer->id))
-		return -EEXIST;
-
-	policer_item = kzalloc(sizeof(*policer_item), GFP_KERNEL);
-	if (!policer_item)
-		return -ENOMEM;
-
-	policer_item->policer = policer;
-	policer_item->rate = policer->init_rate;
-	policer_item->burst = policer->init_burst;
-
-	if (devlink->ops->trap_policer_init) {
-		err = devlink->ops->trap_policer_init(devlink, policer);
-		if (err)
-			goto err_policer_init;
-	}
-
-	list_add_tail(&policer_item->list, &devlink->trap_policer_list);
-	devlink_trap_policer_notify(devlink, policer_item,
-				    DEVLINK_CMD_TRAP_POLICER_NEW);
-
-	return 0;
-
-err_policer_init:
-	kfree(policer_item);
-	return err;
+	mutex_lock(&linecard->state_lock);
+	WARN_ON(linecard->nested_devlink);
+	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING_FAILED;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
 }
+EXPORT_SYMBOL_GPL(devlink_linecard_provision_fail);
 
-static void
-devlink_trap_policer_unregister(struct devlink *devlink,
-				const struct devlink_trap_policer *policer)
+/**
+ *	devlink_linecard_activate - Set linecard active
+ *
+ *	@linecard: devlink linecard
+ */
+void devlink_linecard_activate(struct devlink_linecard *linecard)
 {
-	struct devlink_trap_policer_item *policer_item;
-
-	policer_item = devlink_trap_policer_item_lookup(devlink, policer->id);
-	if (WARN_ON_ONCE(!policer_item))
-		return;
-
-	devlink_trap_policer_notify(devlink, policer_item,
-				    DEVLINK_CMD_TRAP_POLICER_DEL);
-	list_del(&policer_item->list);
-	if (devlink->ops->trap_policer_fini)
-		devlink->ops->trap_policer_fini(devlink, policer);
-	kfree(policer_item);
+	mutex_lock(&linecard->state_lock);
+	WARN_ON(linecard->state != DEVLINK_LINECARD_STATE_PROVISIONED);
+	linecard->state = DEVLINK_LINECARD_STATE_ACTIVE;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
 }
+EXPORT_SYMBOL_GPL(devlink_linecard_activate);
 
 /**
- * devl_trap_policers_register - Register packet trap policers with devlink.
- * @devlink: devlink.
- * @policers: Packet trap policers.
- * @policers_count: Count of provided packet trap policers.
+ *	devlink_linecard_deactivate - Set linecard inactive
  *
- * Return: Non-zero value on failure.
+ *	@linecard: devlink linecard
  */
-int
-devl_trap_policers_register(struct devlink *devlink,
-			    const struct devlink_trap_policer *policers,
-			    size_t policers_count)
+void devlink_linecard_deactivate(struct devlink_linecard *linecard)
 {
-	int i, err;
-
-	devl_assert_locked(devlink);
-	for (i = 0; i < policers_count; i++) {
-		const struct devlink_trap_policer *policer = &policers[i];
-
-		if (WARN_ON(policer->id == 0 ||
-			    policer->max_rate < policer->min_rate ||
-			    policer->max_burst < policer->min_burst)) {
-			err = -EINVAL;
-			goto err_trap_policer_verify;
-		}
-
-		err = devlink_trap_policer_register(devlink, policer);
-		if (err)
-			goto err_trap_policer_register;
+	mutex_lock(&linecard->state_lock);
+	switch (linecard->state) {
+	case DEVLINK_LINECARD_STATE_ACTIVE:
+		linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+		break;
+	case DEVLINK_LINECARD_STATE_UNPROVISIONING:
+		/* Line card is being deactivated as part
+		 * of unprovisioning flow.
+		 */
+		break;
+	default:
+		WARN_ON(1);
+		break;
 	}
-	return 0;
-
-err_trap_policer_register:
-err_trap_policer_verify:
-	for (i--; i >= 0; i--)
-		devlink_trap_policer_unregister(devlink, &policers[i]);
-	return err;
+	mutex_unlock(&linecard->state_lock);
 }
-EXPORT_SYMBOL_GPL(devl_trap_policers_register);
+EXPORT_SYMBOL_GPL(devlink_linecard_deactivate);
 
 /**
- * devl_trap_policers_unregister - Unregister packet trap policers from devlink.
- * @devlink: devlink.
- * @policers: Packet trap policers.
- * @policers_count: Count of provided packet trap policers.
+ *	devlink_linecard_nested_dl_set - Attach/detach nested devlink
+ *					 instance to linecard.
+ *
+ *	@linecard: devlink linecard
+ *	@nested_devlink: devlink instance to attach or NULL to detach
  */
-void
-devl_trap_policers_unregister(struct devlink *devlink,
-			      const struct devlink_trap_policer *policers,
-			      size_t policers_count)
+void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard,
+				    struct devlink *nested_devlink)
 {
-	int i;
-
-	devl_assert_locked(devlink);
-	for (i = policers_count - 1; i >= 0; i--)
-		devlink_trap_policer_unregister(devlink, &policers[i]);
+	mutex_lock(&linecard->state_lock);
+	linecard->nested_devlink = nested_devlink;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
 }
-EXPORT_SYMBOL_GPL(devl_trap_policers_unregister);
+EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set);
diff --git a/net/devlink/trap.c b/net/devlink/trap.c
new file mode 100644
index 0000000000000..c26bf9b29bca2
--- /dev/null
+++ b/net/devlink/trap.c
@@ -0,0 +1,1861 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include <trace/events/devlink.h>
+
+#include "devl_internal.h"
+
+struct devlink_stats {
+	u64_stats_t rx_bytes;
+	u64_stats_t rx_packets;
+	struct u64_stats_sync syncp;
+};
+
+/**
+ * struct devlink_trap_policer_item - Packet trap policer attributes.
+ * @policer: Immutable packet trap policer attributes.
+ * @rate: Rate in packets / sec.
+ * @burst: Burst size in packets.
+ * @list: trap_policer_list member.
+ *
+ * Describes packet trap policer attributes. Created by devlink during trap
+ * policer registration.
+ */
+struct devlink_trap_policer_item {
+	const struct devlink_trap_policer *policer;
+	u64 rate;
+	u64 burst;
+	struct list_head list;
+};
+
+/**
+ * struct devlink_trap_group_item - Packet trap group attributes.
+ * @group: Immutable packet trap group attributes.
+ * @policer_item: Associated policer item. Can be NULL.
+ * @list: trap_group_list member.
+ * @stats: Trap group statistics.
+ *
+ * Describes packet trap group attributes. Created by devlink during trap
+ * group registration.
+ */
+struct devlink_trap_group_item {
+	const struct devlink_trap_group *group;
+	struct devlink_trap_policer_item *policer_item;
+	struct list_head list;
+	struct devlink_stats __percpu *stats;
+};
+
+/**
+ * struct devlink_trap_item - Packet trap attributes.
+ * @trap: Immutable packet trap attributes.
+ * @group_item: Associated group item.
+ * @list: trap_list member.
+ * @action: Trap action.
+ * @stats: Trap statistics.
+ * @priv: Driver private information.
+ *
+ * Describes both mutable and immutable packet trap attributes. Created by
+ * devlink during trap registration and used for all trap related operations.
+ */
+struct devlink_trap_item {
+	const struct devlink_trap *trap;
+	struct devlink_trap_group_item *group_item;
+	struct list_head list;
+	enum devlink_trap_action action;
+	struct devlink_stats __percpu *stats;
+	void *priv;
+};
+
+static struct devlink_trap_policer_item *
+devlink_trap_policer_item_lookup(struct devlink *devlink, u32 id)
+{
+	struct devlink_trap_policer_item *policer_item;
+
+	list_for_each_entry(policer_item, &devlink->trap_policer_list, list) {
+		if (policer_item->policer->id == id)
+			return policer_item;
+	}
+
+	return NULL;
+}
+
+static struct devlink_trap_item *
+devlink_trap_item_lookup(struct devlink *devlink, const char *name)
+{
+	struct devlink_trap_item *trap_item;
+
+	list_for_each_entry(trap_item, &devlink->trap_list, list) {
+		if (!strcmp(trap_item->trap->name, name))
+			return trap_item;
+	}
+
+	return NULL;
+}
+
+static struct devlink_trap_item *
+devlink_trap_item_get_from_info(struct devlink *devlink,
+				struct genl_info *info)
+{
+	struct nlattr *attr;
+
+	if (!info->attrs[DEVLINK_ATTR_TRAP_NAME])
+		return NULL;
+	attr = info->attrs[DEVLINK_ATTR_TRAP_NAME];
+
+	return devlink_trap_item_lookup(devlink, nla_data(attr));
+}
+
+static int
+devlink_trap_action_get_from_info(struct genl_info *info,
+				  enum devlink_trap_action *p_trap_action)
+{
+	u8 val;
+
+	val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]);
+	switch (val) {
+	case DEVLINK_TRAP_ACTION_DROP:
+	case DEVLINK_TRAP_ACTION_TRAP:
+	case DEVLINK_TRAP_ACTION_MIRROR:
+		*p_trap_action = val;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int devlink_trap_metadata_put(struct sk_buff *msg,
+				     const struct devlink_trap *trap)
+{
+	struct nlattr *attr;
+
+	attr = nla_nest_start(msg, DEVLINK_ATTR_TRAP_METADATA);
+	if (!attr)
+		return -EMSGSIZE;
+
+	if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) &&
+	    nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT))
+		goto nla_put_failure;
+	if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE) &&
+	    nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE))
+		goto nla_put_failure;
+
+	nla_nest_end(msg, attr);
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, attr);
+	return -EMSGSIZE;
+}
+
+static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats,
+				    struct devlink_stats *stats)
+{
+	int i;
+
+	memset(stats, 0, sizeof(*stats));
+	for_each_possible_cpu(i) {
+		struct devlink_stats *cpu_stats;
+		u64 rx_packets, rx_bytes;
+		unsigned int start;
+
+		cpu_stats = per_cpu_ptr(trap_stats, i);
+		do {
+			start = u64_stats_fetch_begin(&cpu_stats->syncp);
+			rx_packets = u64_stats_read(&cpu_stats->rx_packets);
+			rx_bytes = u64_stats_read(&cpu_stats->rx_bytes);
+		} while (u64_stats_fetch_retry(&cpu_stats->syncp, start));
+
+		u64_stats_add(&stats->rx_packets, rx_packets);
+		u64_stats_add(&stats->rx_bytes, rx_bytes);
+	}
+}
+
+static int
+devlink_trap_group_stats_put(struct sk_buff *msg,
+			     struct devlink_stats __percpu *trap_stats)
+{
+	struct devlink_stats stats;
+	struct nlattr *attr;
+
+	devlink_trap_stats_read(trap_stats, &stats);
+
+	attr = nla_nest_start(msg, DEVLINK_ATTR_STATS);
+	if (!attr)
+		return -EMSGSIZE;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS,
+			      u64_stats_read(&stats.rx_packets),
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES,
+			      u64_stats_read(&stats.rx_bytes),
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	nla_nest_end(msg, attr);
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_trap_stats_put(struct sk_buff *msg, struct devlink *devlink,
+				  const struct devlink_trap_item *trap_item)
+{
+	struct devlink_stats stats;
+	struct nlattr *attr;
+	u64 drops = 0;
+	int err;
+
+	if (devlink->ops->trap_drop_counter_get) {
+		err = devlink->ops->trap_drop_counter_get(devlink,
+							  trap_item->trap,
+							  &drops);
+		if (err)
+			return err;
+	}
+
+	devlink_trap_stats_read(trap_item->stats, &stats);
+
+	attr = nla_nest_start(msg, DEVLINK_ATTR_STATS);
+	if (!attr)
+		return -EMSGSIZE;
+
+	if (devlink->ops->trap_drop_counter_get &&
+	    nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS,
+			      u64_stats_read(&stats.rx_packets),
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES,
+			      u64_stats_read(&stats.rx_bytes),
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	nla_nest_end(msg, attr);
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink,
+				const struct devlink_trap_item *trap_item,
+				enum devlink_command cmd, u32 portid, u32 seq,
+				int flags)
+{
+	struct devlink_trap_group_item *group_item = trap_item->group_item;
+	void *hdr;
+	int err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME,
+			   group_item->group->name))
+		goto nla_put_failure;
+
+	if (nla_put_string(msg, DEVLINK_ATTR_TRAP_NAME, trap_item->trap->name))
+		goto nla_put_failure;
+
+	if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_TYPE, trap_item->trap->type))
+		goto nla_put_failure;
+
+	if (trap_item->trap->generic &&
+	    nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC))
+		goto nla_put_failure;
+
+	if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_ACTION, trap_item->action))
+		goto nla_put_failure;
+
+	err = devlink_trap_metadata_put(msg, trap_item->trap);
+	if (err)
+		goto nla_put_failure;
+
+	err = devlink_trap_stats_put(msg, devlink, trap_item);
+	if (err)
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_trap_item *trap_item;
+	struct sk_buff *msg;
+	int err;
+
+	if (list_empty(&devlink->trap_list))
+		return -EOPNOTSUPP;
+
+	trap_item = devlink_trap_item_get_from_info(devlink, info);
+	if (!trap_item) {
+		NL_SET_ERR_MSG(extack, "Device did not register this trap");
+		return -ENOENT;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_trap_fill(msg, devlink, trap_item,
+				   DEVLINK_CMD_TRAP_NEW, info->snd_portid,
+				   info->snd_seq, 0);
+	if (err)
+		goto err_trap_fill;
+
+	return genlmsg_reply(msg, info);
+
+err_trap_fill:
+	nlmsg_free(msg);
+	return err;
+}
+
+static int devlink_nl_trap_get_dump_one(struct sk_buff *msg,
+					struct devlink *devlink,
+					struct netlink_callback *cb, int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_trap_item *trap_item;
+	int idx = 0;
+	int err = 0;
+
+	list_for_each_entry(trap_item, &devlink->trap_list, list) {
+		if (idx < state->idx) {
+			idx++;
+			continue;
+		}
+		err = devlink_nl_trap_fill(msg, devlink, trap_item,
+					   DEVLINK_CMD_TRAP_NEW,
+					   NETLINK_CB(cb->skb).portid,
+					   cb->nlh->nlmsg_seq, flags);
+		if (err) {
+			state->idx = idx;
+			break;
+		}
+		idx++;
+	}
+
+	return err;
+}
+
+int devlink_nl_trap_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_trap_get_dump_one);
+}
+
+static int __devlink_trap_action_set(struct devlink *devlink,
+				     struct devlink_trap_item *trap_item,
+				     enum devlink_trap_action trap_action,
+				     struct netlink_ext_ack *extack)
+{
+	int err;
+
+	if (trap_item->action != trap_action &&
+	    trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) {
+		NL_SET_ERR_MSG(extack, "Cannot change action of non-drop traps. Skipping");
+		return 0;
+	}
+
+	err = devlink->ops->trap_action_set(devlink, trap_item->trap,
+					    trap_action, extack);
+	if (err)
+		return err;
+
+	trap_item->action = trap_action;
+
+	return 0;
+}
+
+static int devlink_trap_action_set(struct devlink *devlink,
+				   struct devlink_trap_item *trap_item,
+				   struct genl_info *info)
+{
+	enum devlink_trap_action trap_action;
+	int err;
+
+	if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION])
+		return 0;
+
+	err = devlink_trap_action_get_from_info(info, &trap_action);
+	if (err) {
+		NL_SET_ERR_MSG(info->extack, "Invalid trap action");
+		return -EINVAL;
+	}
+
+	return __devlink_trap_action_set(devlink, trap_item, trap_action,
+					 info->extack);
+}
+
+int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_trap_item *trap_item;
+
+	if (list_empty(&devlink->trap_list))
+		return -EOPNOTSUPP;
+
+	trap_item = devlink_trap_item_get_from_info(devlink, info);
+	if (!trap_item) {
+		NL_SET_ERR_MSG(extack, "Device did not register this trap");
+		return -ENOENT;
+	}
+
+	return devlink_trap_action_set(devlink, trap_item, info);
+}
+
+static struct devlink_trap_group_item *
+devlink_trap_group_item_lookup(struct devlink *devlink, const char *name)
+{
+	struct devlink_trap_group_item *group_item;
+
+	list_for_each_entry(group_item, &devlink->trap_group_list, list) {
+		if (!strcmp(group_item->group->name, name))
+			return group_item;
+	}
+
+	return NULL;
+}
+
+static struct devlink_trap_group_item *
+devlink_trap_group_item_lookup_by_id(struct devlink *devlink, u16 id)
+{
+	struct devlink_trap_group_item *group_item;
+
+	list_for_each_entry(group_item, &devlink->trap_group_list, list) {
+		if (group_item->group->id == id)
+			return group_item;
+	}
+
+	return NULL;
+}
+
+static struct devlink_trap_group_item *
+devlink_trap_group_item_get_from_info(struct devlink *devlink,
+				      struct genl_info *info)
+{
+	char *name;
+
+	if (!info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME])
+		return NULL;
+	name = nla_data(info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]);
+
+	return devlink_trap_group_item_lookup(devlink, name);
+}
+
+static int
+devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink,
+			   const struct devlink_trap_group_item *group_item,
+			   enum devlink_command cmd, u32 portid, u32 seq,
+			   int flags)
+{
+	void *hdr;
+	int err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME,
+			   group_item->group->name))
+		goto nla_put_failure;
+
+	if (group_item->group->generic &&
+	    nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC))
+		goto nla_put_failure;
+
+	if (group_item->policer_item &&
+	    nla_put_u32(msg, DEVLINK_ATTR_TRAP_POLICER_ID,
+			group_item->policer_item->policer->id))
+		goto nla_put_failure;
+
+	err = devlink_trap_group_stats_put(msg, group_item->stats);
+	if (err)
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_trap_group_item *group_item;
+	struct sk_buff *msg;
+	int err;
+
+	if (list_empty(&devlink->trap_group_list))
+		return -EOPNOTSUPP;
+
+	group_item = devlink_trap_group_item_get_from_info(devlink, info);
+	if (!group_item) {
+		NL_SET_ERR_MSG(extack, "Device did not register this trap group");
+		return -ENOENT;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_trap_group_fill(msg, devlink, group_item,
+					 DEVLINK_CMD_TRAP_GROUP_NEW,
+					 info->snd_portid, info->snd_seq, 0);
+	if (err)
+		goto err_trap_group_fill;
+
+	return genlmsg_reply(msg, info);
+
+err_trap_group_fill:
+	nlmsg_free(msg);
+	return err;
+}
+
+static int devlink_nl_trap_group_get_dump_one(struct sk_buff *msg,
+					      struct devlink *devlink,
+					      struct netlink_callback *cb,
+					      int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_trap_group_item *group_item;
+	int idx = 0;
+	int err = 0;
+
+	list_for_each_entry(group_item, &devlink->trap_group_list, list) {
+		if (idx < state->idx) {
+			idx++;
+			continue;
+		}
+		err = devlink_nl_trap_group_fill(msg, devlink, group_item,
+						 DEVLINK_CMD_TRAP_GROUP_NEW,
+						 NETLINK_CB(cb->skb).portid,
+						 cb->nlh->nlmsg_seq, flags);
+		if (err) {
+			state->idx = idx;
+			break;
+		}
+		idx++;
+	}
+
+	return err;
+}
+
+int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_trap_group_get_dump_one);
+}
+
+static int
+__devlink_trap_group_action_set(struct devlink *devlink,
+				struct devlink_trap_group_item *group_item,
+				enum devlink_trap_action trap_action,
+				struct netlink_ext_ack *extack)
+{
+	const char *group_name = group_item->group->name;
+	struct devlink_trap_item *trap_item;
+	int err;
+
+	if (devlink->ops->trap_group_action_set) {
+		err = devlink->ops->trap_group_action_set(devlink, group_item->group,
+							  trap_action, extack);
+		if (err)
+			return err;
+
+		list_for_each_entry(trap_item, &devlink->trap_list, list) {
+			if (strcmp(trap_item->group_item->group->name, group_name))
+				continue;
+			if (trap_item->action != trap_action &&
+			    trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP)
+				continue;
+			trap_item->action = trap_action;
+		}
+
+		return 0;
+	}
+
+	list_for_each_entry(trap_item, &devlink->trap_list, list) {
+		if (strcmp(trap_item->group_item->group->name, group_name))
+			continue;
+		err = __devlink_trap_action_set(devlink, trap_item,
+						trap_action, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int
+devlink_trap_group_action_set(struct devlink *devlink,
+			      struct devlink_trap_group_item *group_item,
+			      struct genl_info *info, bool *p_modified)
+{
+	enum devlink_trap_action trap_action;
+	int err;
+
+	if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION])
+		return 0;
+
+	err = devlink_trap_action_get_from_info(info, &trap_action);
+	if (err) {
+		NL_SET_ERR_MSG(info->extack, "Invalid trap action");
+		return -EINVAL;
+	}
+
+	err = __devlink_trap_group_action_set(devlink, group_item, trap_action,
+					      info->extack);
+	if (err)
+		return err;
+
+	*p_modified = true;
+
+	return 0;
+}
+
+static int devlink_trap_group_set(struct devlink *devlink,
+				  struct devlink_trap_group_item *group_item,
+				  struct genl_info *info)
+{
+	struct devlink_trap_policer_item *policer_item;
+	struct netlink_ext_ack *extack = info->extack;
+	const struct devlink_trap_policer *policer;
+	struct nlattr **attrs = info->attrs;
+	u32 policer_id;
+	int err;
+
+	if (!attrs[DEVLINK_ATTR_TRAP_POLICER_ID])
+		return 0;
+
+	if (!devlink->ops->trap_group_set)
+		return -EOPNOTSUPP;
+
+	policer_id = nla_get_u32(attrs[DEVLINK_ATTR_TRAP_POLICER_ID]);
+	policer_item = devlink_trap_policer_item_lookup(devlink, policer_id);
+	if (policer_id && !policer_item) {
+		NL_SET_ERR_MSG(extack, "Device did not register this trap policer");
+		return -ENOENT;
+	}
+	policer = policer_item ? policer_item->policer : NULL;
+
+	err = devlink->ops->trap_group_set(devlink, group_item->group, policer,
+					   extack);
+	if (err)
+		return err;
+
+	group_item->policer_item = policer_item;
+
+	return 0;
+}
+
+int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb,
+				       struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_trap_group_item *group_item;
+	bool modified = false;
+	int err;
+
+	if (list_empty(&devlink->trap_group_list))
+		return -EOPNOTSUPP;
+
+	group_item = devlink_trap_group_item_get_from_info(devlink, info);
+	if (!group_item) {
+		NL_SET_ERR_MSG(extack, "Device did not register this trap group");
+		return -ENOENT;
+	}
+
+	err = devlink_trap_group_action_set(devlink, group_item, info,
+					    &modified);
+	if (err)
+		return err;
+
+	err = devlink_trap_group_set(devlink, group_item, info);
+	if (err)
+		goto err_trap_group_set;
+
+	return 0;
+
+err_trap_group_set:
+	if (modified)
+		NL_SET_ERR_MSG(extack, "Trap group set failed, but some changes were committed already");
+	return err;
+}
+
+static struct devlink_trap_policer_item *
+devlink_trap_policer_item_get_from_info(struct devlink *devlink,
+					struct genl_info *info)
+{
+	u32 id;
+
+	if (!info->attrs[DEVLINK_ATTR_TRAP_POLICER_ID])
+		return NULL;
+	id = nla_get_u32(info->attrs[DEVLINK_ATTR_TRAP_POLICER_ID]);
+
+	return devlink_trap_policer_item_lookup(devlink, id);
+}
+
+static int
+devlink_trap_policer_stats_put(struct sk_buff *msg, struct devlink *devlink,
+			       const struct devlink_trap_policer *policer)
+{
+	struct nlattr *attr;
+	u64 drops;
+	int err;
+
+	if (!devlink->ops->trap_policer_counter_get)
+		return 0;
+
+	err = devlink->ops->trap_policer_counter_get(devlink, policer, &drops);
+	if (err)
+		return err;
+
+	attr = nla_nest_start(msg, DEVLINK_ATTR_STATS);
+	if (!attr)
+		return -EMSGSIZE;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	nla_nest_end(msg, attr);
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, attr);
+	return -EMSGSIZE;
+}
+
+static int
+devlink_nl_trap_policer_fill(struct sk_buff *msg, struct devlink *devlink,
+			     const struct devlink_trap_policer_item *policer_item,
+			     enum devlink_command cmd, u32 portid, u32 seq,
+			     int flags)
+{
+	void *hdr;
+	int err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, DEVLINK_ATTR_TRAP_POLICER_ID,
+			policer_item->policer->id))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_TRAP_POLICER_RATE,
+			      policer_item->rate, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_TRAP_POLICER_BURST,
+			      policer_item->burst, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	err = devlink_trap_policer_stats_put(msg, devlink,
+					     policer_item->policer);
+	if (err)
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+int devlink_nl_trap_policer_get_doit(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct devlink_trap_policer_item *policer_item;
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+	struct sk_buff *msg;
+	int err;
+
+	if (list_empty(&devlink->trap_policer_list))
+		return -EOPNOTSUPP;
+
+	policer_item = devlink_trap_policer_item_get_from_info(devlink, info);
+	if (!policer_item) {
+		NL_SET_ERR_MSG(extack, "Device did not register this trap policer");
+		return -ENOENT;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_trap_policer_fill(msg, devlink, policer_item,
+					   DEVLINK_CMD_TRAP_POLICER_NEW,
+					   info->snd_portid, info->snd_seq, 0);
+	if (err)
+		goto err_trap_policer_fill;
+
+	return genlmsg_reply(msg, info);
+
+err_trap_policer_fill:
+	nlmsg_free(msg);
+	return err;
+}
+
+static int devlink_nl_trap_policer_get_dump_one(struct sk_buff *msg,
+						struct devlink *devlink,
+						struct netlink_callback *cb,
+						int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_trap_policer_item *policer_item;
+	int idx = 0;
+	int err = 0;
+
+	list_for_each_entry(policer_item, &devlink->trap_policer_list, list) {
+		if (idx < state->idx) {
+			idx++;
+			continue;
+		}
+		err = devlink_nl_trap_policer_fill(msg, devlink, policer_item,
+						   DEVLINK_CMD_TRAP_POLICER_NEW,
+						   NETLINK_CB(cb->skb).portid,
+						   cb->nlh->nlmsg_seq, flags);
+		if (err) {
+			state->idx = idx;
+			break;
+		}
+		idx++;
+	}
+
+	return err;
+}
+
+int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_trap_policer_get_dump_one);
+}
+
+static int
+devlink_trap_policer_set(struct devlink *devlink,
+			 struct devlink_trap_policer_item *policer_item,
+			 struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct nlattr **attrs = info->attrs;
+	u64 rate, burst;
+	int err;
+
+	rate = policer_item->rate;
+	burst = policer_item->burst;
+
+	if (attrs[DEVLINK_ATTR_TRAP_POLICER_RATE])
+		rate = nla_get_u64(attrs[DEVLINK_ATTR_TRAP_POLICER_RATE]);
+
+	if (attrs[DEVLINK_ATTR_TRAP_POLICER_BURST])
+		burst = nla_get_u64(attrs[DEVLINK_ATTR_TRAP_POLICER_BURST]);
+
+	if (rate < policer_item->policer->min_rate) {
+		NL_SET_ERR_MSG(extack, "Policer rate lower than limit");
+		return -EINVAL;
+	}
+
+	if (rate > policer_item->policer->max_rate) {
+		NL_SET_ERR_MSG(extack, "Policer rate higher than limit");
+		return -EINVAL;
+	}
+
+	if (burst < policer_item->policer->min_burst) {
+		NL_SET_ERR_MSG(extack, "Policer burst size lower than limit");
+		return -EINVAL;
+	}
+
+	if (burst > policer_item->policer->max_burst) {
+		NL_SET_ERR_MSG(extack, "Policer burst size higher than limit");
+		return -EINVAL;
+	}
+
+	err = devlink->ops->trap_policer_set(devlink, policer_item->policer,
+					     rate, burst, info->extack);
+	if (err)
+		return err;
+
+	policer_item->rate = rate;
+	policer_item->burst = burst;
+
+	return 0;
+}
+
+int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
+					 struct genl_info *info)
+{
+	struct devlink_trap_policer_item *policer_item;
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+
+	if (list_empty(&devlink->trap_policer_list))
+		return -EOPNOTSUPP;
+
+	if (!devlink->ops->trap_policer_set)
+		return -EOPNOTSUPP;
+
+	policer_item = devlink_trap_policer_item_get_from_info(devlink, info);
+	if (!policer_item) {
+		NL_SET_ERR_MSG(extack, "Device did not register this trap policer");
+		return -ENOENT;
+	}
+
+	return devlink_trap_policer_set(devlink, policer_item, info);
+}
+
+#define DEVLINK_TRAP(_id, _type)					      \
+	{								      \
+		.type = DEVLINK_TRAP_TYPE_##_type,			      \
+		.id = DEVLINK_TRAP_GENERIC_ID_##_id,			      \
+		.name = DEVLINK_TRAP_GENERIC_NAME_##_id,		      \
+	}
+
+static const struct devlink_trap devlink_trap_generic[] = {
+	DEVLINK_TRAP(SMAC_MC, DROP),
+	DEVLINK_TRAP(VLAN_TAG_MISMATCH, DROP),
+	DEVLINK_TRAP(INGRESS_VLAN_FILTER, DROP),
+	DEVLINK_TRAP(INGRESS_STP_FILTER, DROP),
+	DEVLINK_TRAP(EMPTY_TX_LIST, DROP),
+	DEVLINK_TRAP(PORT_LOOPBACK_FILTER, DROP),
+	DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP),
+	DEVLINK_TRAP(TTL_ERROR, EXCEPTION),
+	DEVLINK_TRAP(TAIL_DROP, DROP),
+	DEVLINK_TRAP(NON_IP_PACKET, DROP),
+	DEVLINK_TRAP(UC_DIP_MC_DMAC, DROP),
+	DEVLINK_TRAP(DIP_LB, DROP),
+	DEVLINK_TRAP(SIP_MC, DROP),
+	DEVLINK_TRAP(SIP_LB, DROP),
+	DEVLINK_TRAP(CORRUPTED_IP_HDR, DROP),
+	DEVLINK_TRAP(IPV4_SIP_BC, DROP),
+	DEVLINK_TRAP(IPV6_MC_DIP_RESERVED_SCOPE, DROP),
+	DEVLINK_TRAP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, DROP),
+	DEVLINK_TRAP(MTU_ERROR, EXCEPTION),
+	DEVLINK_TRAP(UNRESOLVED_NEIGH, EXCEPTION),
+	DEVLINK_TRAP(RPF, EXCEPTION),
+	DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION),
+	DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION),
+	DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION),
+	DEVLINK_TRAP(NON_ROUTABLE, DROP),
+	DEVLINK_TRAP(DECAP_ERROR, EXCEPTION),
+	DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP),
+	DEVLINK_TRAP(INGRESS_FLOW_ACTION_DROP, DROP),
+	DEVLINK_TRAP(EGRESS_FLOW_ACTION_DROP, DROP),
+	DEVLINK_TRAP(STP, CONTROL),
+	DEVLINK_TRAP(LACP, CONTROL),
+	DEVLINK_TRAP(LLDP, CONTROL),
+	DEVLINK_TRAP(IGMP_QUERY, CONTROL),
+	DEVLINK_TRAP(IGMP_V1_REPORT, CONTROL),
+	DEVLINK_TRAP(IGMP_V2_REPORT, CONTROL),
+	DEVLINK_TRAP(IGMP_V3_REPORT, CONTROL),
+	DEVLINK_TRAP(IGMP_V2_LEAVE, CONTROL),
+	DEVLINK_TRAP(MLD_QUERY, CONTROL),
+	DEVLINK_TRAP(MLD_V1_REPORT, CONTROL),
+	DEVLINK_TRAP(MLD_V2_REPORT, CONTROL),
+	DEVLINK_TRAP(MLD_V1_DONE, CONTROL),
+	DEVLINK_TRAP(IPV4_DHCP, CONTROL),
+	DEVLINK_TRAP(IPV6_DHCP, CONTROL),
+	DEVLINK_TRAP(ARP_REQUEST, CONTROL),
+	DEVLINK_TRAP(ARP_RESPONSE, CONTROL),
+	DEVLINK_TRAP(ARP_OVERLAY, CONTROL),
+	DEVLINK_TRAP(IPV6_NEIGH_SOLICIT, CONTROL),
+	DEVLINK_TRAP(IPV6_NEIGH_ADVERT, CONTROL),
+	DEVLINK_TRAP(IPV4_BFD, CONTROL),
+	DEVLINK_TRAP(IPV6_BFD, CONTROL),
+	DEVLINK_TRAP(IPV4_OSPF, CONTROL),
+	DEVLINK_TRAP(IPV6_OSPF, CONTROL),
+	DEVLINK_TRAP(IPV4_BGP, CONTROL),
+	DEVLINK_TRAP(IPV6_BGP, CONTROL),
+	DEVLINK_TRAP(IPV4_VRRP, CONTROL),
+	DEVLINK_TRAP(IPV6_VRRP, CONTROL),
+	DEVLINK_TRAP(IPV4_PIM, CONTROL),
+	DEVLINK_TRAP(IPV6_PIM, CONTROL),
+	DEVLINK_TRAP(UC_LB, CONTROL),
+	DEVLINK_TRAP(LOCAL_ROUTE, CONTROL),
+	DEVLINK_TRAP(EXTERNAL_ROUTE, CONTROL),
+	DEVLINK_TRAP(IPV6_UC_DIP_LINK_LOCAL_SCOPE, CONTROL),
+	DEVLINK_TRAP(IPV6_DIP_ALL_NODES, CONTROL),
+	DEVLINK_TRAP(IPV6_DIP_ALL_ROUTERS, CONTROL),
+	DEVLINK_TRAP(IPV6_ROUTER_SOLICIT, CONTROL),
+	DEVLINK_TRAP(IPV6_ROUTER_ADVERT, CONTROL),
+	DEVLINK_TRAP(IPV6_REDIRECT, CONTROL),
+	DEVLINK_TRAP(IPV4_ROUTER_ALERT, CONTROL),
+	DEVLINK_TRAP(IPV6_ROUTER_ALERT, CONTROL),
+	DEVLINK_TRAP(PTP_EVENT, CONTROL),
+	DEVLINK_TRAP(PTP_GENERAL, CONTROL),
+	DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL),
+	DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL),
+	DEVLINK_TRAP(EARLY_DROP, DROP),
+	DEVLINK_TRAP(VXLAN_PARSING, DROP),
+	DEVLINK_TRAP(LLC_SNAP_PARSING, DROP),
+	DEVLINK_TRAP(VLAN_PARSING, DROP),
+	DEVLINK_TRAP(PPPOE_PPP_PARSING, DROP),
+	DEVLINK_TRAP(MPLS_PARSING, DROP),
+	DEVLINK_TRAP(ARP_PARSING, DROP),
+	DEVLINK_TRAP(IP_1_PARSING, DROP),
+	DEVLINK_TRAP(IP_N_PARSING, DROP),
+	DEVLINK_TRAP(GRE_PARSING, DROP),
+	DEVLINK_TRAP(UDP_PARSING, DROP),
+	DEVLINK_TRAP(TCP_PARSING, DROP),
+	DEVLINK_TRAP(IPSEC_PARSING, DROP),
+	DEVLINK_TRAP(SCTP_PARSING, DROP),
+	DEVLINK_TRAP(DCCP_PARSING, DROP),
+	DEVLINK_TRAP(GTP_PARSING, DROP),
+	DEVLINK_TRAP(ESP_PARSING, DROP),
+	DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP),
+	DEVLINK_TRAP(DMAC_FILTER, DROP),
+	DEVLINK_TRAP(EAPOL, CONTROL),
+	DEVLINK_TRAP(LOCKED_PORT, DROP),
+};
+
+#define DEVLINK_TRAP_GROUP(_id)						      \
+	{								      \
+		.id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id,		      \
+		.name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id,		      \
+	}
+
+static const struct devlink_trap_group devlink_trap_group_generic[] = {
+	DEVLINK_TRAP_GROUP(L2_DROPS),
+	DEVLINK_TRAP_GROUP(L3_DROPS),
+	DEVLINK_TRAP_GROUP(L3_EXCEPTIONS),
+	DEVLINK_TRAP_GROUP(BUFFER_DROPS),
+	DEVLINK_TRAP_GROUP(TUNNEL_DROPS),
+	DEVLINK_TRAP_GROUP(ACL_DROPS),
+	DEVLINK_TRAP_GROUP(STP),
+	DEVLINK_TRAP_GROUP(LACP),
+	DEVLINK_TRAP_GROUP(LLDP),
+	DEVLINK_TRAP_GROUP(MC_SNOOPING),
+	DEVLINK_TRAP_GROUP(DHCP),
+	DEVLINK_TRAP_GROUP(NEIGH_DISCOVERY),
+	DEVLINK_TRAP_GROUP(BFD),
+	DEVLINK_TRAP_GROUP(OSPF),
+	DEVLINK_TRAP_GROUP(BGP),
+	DEVLINK_TRAP_GROUP(VRRP),
+	DEVLINK_TRAP_GROUP(PIM),
+	DEVLINK_TRAP_GROUP(UC_LB),
+	DEVLINK_TRAP_GROUP(LOCAL_DELIVERY),
+	DEVLINK_TRAP_GROUP(EXTERNAL_DELIVERY),
+	DEVLINK_TRAP_GROUP(IPV6),
+	DEVLINK_TRAP_GROUP(PTP_EVENT),
+	DEVLINK_TRAP_GROUP(PTP_GENERAL),
+	DEVLINK_TRAP_GROUP(ACL_SAMPLE),
+	DEVLINK_TRAP_GROUP(ACL_TRAP),
+	DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS),
+	DEVLINK_TRAP_GROUP(EAPOL),
+};
+
+static int devlink_trap_generic_verify(const struct devlink_trap *trap)
+{
+	if (trap->id > DEVLINK_TRAP_GENERIC_ID_MAX)
+		return -EINVAL;
+
+	if (strcmp(trap->name, devlink_trap_generic[trap->id].name))
+		return -EINVAL;
+
+	if (trap->type != devlink_trap_generic[trap->id].type)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int devlink_trap_driver_verify(const struct devlink_trap *trap)
+{
+	int i;
+
+	if (trap->id <= DEVLINK_TRAP_GENERIC_ID_MAX)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(devlink_trap_generic); i++) {
+		if (!strcmp(trap->name, devlink_trap_generic[i].name))
+			return -EEXIST;
+	}
+
+	return 0;
+}
+
+static int devlink_trap_verify(const struct devlink_trap *trap)
+{
+	if (!trap || !trap->name)
+		return -EINVAL;
+
+	if (trap->generic)
+		return devlink_trap_generic_verify(trap);
+	else
+		return devlink_trap_driver_verify(trap);
+}
+
+static int
+devlink_trap_group_generic_verify(const struct devlink_trap_group *group)
+{
+	if (group->id > DEVLINK_TRAP_GROUP_GENERIC_ID_MAX)
+		return -EINVAL;
+
+	if (strcmp(group->name, devlink_trap_group_generic[group->id].name))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int
+devlink_trap_group_driver_verify(const struct devlink_trap_group *group)
+{
+	int i;
+
+	if (group->id <= DEVLINK_TRAP_GROUP_GENERIC_ID_MAX)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(devlink_trap_group_generic); i++) {
+		if (!strcmp(group->name, devlink_trap_group_generic[i].name))
+			return -EEXIST;
+	}
+
+	return 0;
+}
+
+static int devlink_trap_group_verify(const struct devlink_trap_group *group)
+{
+	if (group->generic)
+		return devlink_trap_group_generic_verify(group);
+	else
+		return devlink_trap_group_driver_verify(group);
+}
+
+static void
+devlink_trap_group_notify(struct devlink *devlink,
+			  const struct devlink_trap_group_item *group_item,
+			  enum devlink_command cmd)
+{
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW &&
+		     cmd != DEVLINK_CMD_TRAP_GROUP_DEL);
+	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+		return;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_trap_group_fill(msg, devlink, group_item, cmd, 0, 0,
+					 0);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+void devlink_trap_groups_notify_register(struct devlink *devlink)
+{
+	struct devlink_trap_group_item *group_item;
+
+	list_for_each_entry(group_item, &devlink->trap_group_list, list)
+		devlink_trap_group_notify(devlink, group_item,
+					  DEVLINK_CMD_TRAP_GROUP_NEW);
+}
+
+void devlink_trap_groups_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_trap_group_item *group_item;
+
+	list_for_each_entry_reverse(group_item, &devlink->trap_group_list, list)
+		devlink_trap_group_notify(devlink, group_item,
+					  DEVLINK_CMD_TRAP_GROUP_DEL);
+}
+
+static int
+devlink_trap_item_group_link(struct devlink *devlink,
+			     struct devlink_trap_item *trap_item)
+{
+	u16 group_id = trap_item->trap->init_group_id;
+	struct devlink_trap_group_item *group_item;
+
+	group_item = devlink_trap_group_item_lookup_by_id(devlink, group_id);
+	if (WARN_ON_ONCE(!group_item))
+		return -EINVAL;
+
+	trap_item->group_item = group_item;
+
+	return 0;
+}
+
+static void devlink_trap_notify(struct devlink *devlink,
+				const struct devlink_trap_item *trap_item,
+				enum devlink_command cmd)
+{
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW &&
+		     cmd != DEVLINK_CMD_TRAP_DEL);
+	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+		return;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_trap_fill(msg, devlink, trap_item, cmd, 0, 0, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+void devlink_traps_notify_register(struct devlink *devlink)
+{
+	struct devlink_trap_item *trap_item;
+
+	list_for_each_entry(trap_item, &devlink->trap_list, list)
+		devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW);
+}
+
+void devlink_traps_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_trap_item *trap_item;
+
+	list_for_each_entry_reverse(trap_item, &devlink->trap_list, list)
+		devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL);
+}
+
+static int
+devlink_trap_register(struct devlink *devlink,
+		      const struct devlink_trap *trap, void *priv)
+{
+	struct devlink_trap_item *trap_item;
+	int err;
+
+	if (devlink_trap_item_lookup(devlink, trap->name))
+		return -EEXIST;
+
+	trap_item = kzalloc(sizeof(*trap_item), GFP_KERNEL);
+	if (!trap_item)
+		return -ENOMEM;
+
+	trap_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats);
+	if (!trap_item->stats) {
+		err = -ENOMEM;
+		goto err_stats_alloc;
+	}
+
+	trap_item->trap = trap;
+	trap_item->action = trap->init_action;
+	trap_item->priv = priv;
+
+	err = devlink_trap_item_group_link(devlink, trap_item);
+	if (err)
+		goto err_group_link;
+
+	err = devlink->ops->trap_init(devlink, trap, trap_item);
+	if (err)
+		goto err_trap_init;
+
+	list_add_tail(&trap_item->list, &devlink->trap_list);
+	devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW);
+
+	return 0;
+
+err_trap_init:
+err_group_link:
+	free_percpu(trap_item->stats);
+err_stats_alloc:
+	kfree(trap_item);
+	return err;
+}
+
+static void devlink_trap_unregister(struct devlink *devlink,
+				    const struct devlink_trap *trap)
+{
+	struct devlink_trap_item *trap_item;
+
+	trap_item = devlink_trap_item_lookup(devlink, trap->name);
+	if (WARN_ON_ONCE(!trap_item))
+		return;
+
+	devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL);
+	list_del(&trap_item->list);
+	if (devlink->ops->trap_fini)
+		devlink->ops->trap_fini(devlink, trap, trap_item);
+	free_percpu(trap_item->stats);
+	kfree(trap_item);
+}
+
+static void devlink_trap_disable(struct devlink *devlink,
+				 const struct devlink_trap *trap)
+{
+	struct devlink_trap_item *trap_item;
+
+	trap_item = devlink_trap_item_lookup(devlink, trap->name);
+	if (WARN_ON_ONCE(!trap_item))
+		return;
+
+	devlink->ops->trap_action_set(devlink, trap, DEVLINK_TRAP_ACTION_DROP,
+				      NULL);
+	trap_item->action = DEVLINK_TRAP_ACTION_DROP;
+}
+
+/**
+ * devl_traps_register - Register packet traps with devlink.
+ * @devlink: devlink.
+ * @traps: Packet traps.
+ * @traps_count: Count of provided packet traps.
+ * @priv: Driver private information.
+ *
+ * Return: Non-zero value on failure.
+ */
+int devl_traps_register(struct devlink *devlink,
+			const struct devlink_trap *traps,
+			size_t traps_count, void *priv)
+{
+	int i, err;
+
+	if (!devlink->ops->trap_init || !devlink->ops->trap_action_set)
+		return -EINVAL;
+
+	devl_assert_locked(devlink);
+	for (i = 0; i < traps_count; i++) {
+		const struct devlink_trap *trap = &traps[i];
+
+		err = devlink_trap_verify(trap);
+		if (err)
+			goto err_trap_verify;
+
+		err = devlink_trap_register(devlink, trap, priv);
+		if (err)
+			goto err_trap_register;
+	}
+
+	return 0;
+
+err_trap_register:
+err_trap_verify:
+	for (i--; i >= 0; i--)
+		devlink_trap_unregister(devlink, &traps[i]);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devl_traps_register);
+
+/**
+ * devlink_traps_register - Register packet traps with devlink.
+ * @devlink: devlink.
+ * @traps: Packet traps.
+ * @traps_count: Count of provided packet traps.
+ * @priv: Driver private information.
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ *
+ * Return: Non-zero value on failure.
+ */
+int devlink_traps_register(struct devlink *devlink,
+			   const struct devlink_trap *traps,
+			   size_t traps_count, void *priv)
+{
+	int err;
+
+	devl_lock(devlink);
+	err = devl_traps_register(devlink, traps, traps_count, priv);
+	devl_unlock(devlink);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devlink_traps_register);
+
+/**
+ * devl_traps_unregister - Unregister packet traps from devlink.
+ * @devlink: devlink.
+ * @traps: Packet traps.
+ * @traps_count: Count of provided packet traps.
+ */
+void devl_traps_unregister(struct devlink *devlink,
+			   const struct devlink_trap *traps,
+			   size_t traps_count)
+{
+	int i;
+
+	devl_assert_locked(devlink);
+	/* Make sure we do not have any packets in-flight while unregistering
+	 * traps by disabling all of them and waiting for a grace period.
+	 */
+	for (i = traps_count - 1; i >= 0; i--)
+		devlink_trap_disable(devlink, &traps[i]);
+	synchronize_rcu();
+	for (i = traps_count - 1; i >= 0; i--)
+		devlink_trap_unregister(devlink, &traps[i]);
+}
+EXPORT_SYMBOL_GPL(devl_traps_unregister);
+
+/**
+ * devlink_traps_unregister - Unregister packet traps from devlink.
+ * @devlink: devlink.
+ * @traps: Packet traps.
+ * @traps_count: Count of provided packet traps.
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_traps_unregister(struct devlink *devlink,
+			      const struct devlink_trap *traps,
+			      size_t traps_count)
+{
+	devl_lock(devlink);
+	devl_traps_unregister(devlink, traps, traps_count);
+	devl_unlock(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_traps_unregister);
+
+static void
+devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats,
+			  size_t skb_len)
+{
+	struct devlink_stats *stats;
+
+	stats = this_cpu_ptr(trap_stats);
+	u64_stats_update_begin(&stats->syncp);
+	u64_stats_add(&stats->rx_bytes, skb_len);
+	u64_stats_inc(&stats->rx_packets);
+	u64_stats_update_end(&stats->syncp);
+}
+
+static void
+devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata,
+				 const struct devlink_trap_item *trap_item,
+				 struct devlink_port *in_devlink_port,
+				 const struct flow_action_cookie *fa_cookie)
+{
+	metadata->trap_name = trap_item->trap->name;
+	metadata->trap_group_name = trap_item->group_item->group->name;
+	metadata->fa_cookie = fa_cookie;
+	metadata->trap_type = trap_item->trap->type;
+
+	spin_lock(&in_devlink_port->type_lock);
+	if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH)
+		metadata->input_dev = in_devlink_port->type_eth.netdev;
+	spin_unlock(&in_devlink_port->type_lock);
+}
+
+/**
+ * devlink_trap_report - Report trapped packet to drop monitor.
+ * @devlink: devlink.
+ * @skb: Trapped packet.
+ * @trap_ctx: Trap context.
+ * @in_devlink_port: Input devlink port.
+ * @fa_cookie: Flow action cookie. Could be NULL.
+ */
+void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
+			 void *trap_ctx, struct devlink_port *in_devlink_port,
+			 const struct flow_action_cookie *fa_cookie)
+
+{
+	struct devlink_trap_item *trap_item = trap_ctx;
+
+	devlink_trap_stats_update(trap_item->stats, skb->len);
+	devlink_trap_stats_update(trap_item->group_item->stats, skb->len);
+
+	if (tracepoint_enabled(devlink_trap_report)) {
+		struct devlink_trap_metadata metadata = {};
+
+		devlink_trap_report_metadata_set(&metadata, trap_item,
+						 in_devlink_port, fa_cookie);
+		trace_devlink_trap_report(devlink, skb, &metadata);
+	}
+}
+EXPORT_SYMBOL_GPL(devlink_trap_report);
+
+/**
+ * devlink_trap_ctx_priv - Trap context to driver private information.
+ * @trap_ctx: Trap context.
+ *
+ * Return: Driver private information passed during registration.
+ */
+void *devlink_trap_ctx_priv(void *trap_ctx)
+{
+	struct devlink_trap_item *trap_item = trap_ctx;
+
+	return trap_item->priv;
+}
+EXPORT_SYMBOL_GPL(devlink_trap_ctx_priv);
+
+static int
+devlink_trap_group_item_policer_link(struct devlink *devlink,
+				     struct devlink_trap_group_item *group_item)
+{
+	u32 policer_id = group_item->group->init_policer_id;
+	struct devlink_trap_policer_item *policer_item;
+
+	if (policer_id == 0)
+		return 0;
+
+	policer_item = devlink_trap_policer_item_lookup(devlink, policer_id);
+	if (WARN_ON_ONCE(!policer_item))
+		return -EINVAL;
+
+	group_item->policer_item = policer_item;
+
+	return 0;
+}
+
+static int
+devlink_trap_group_register(struct devlink *devlink,
+			    const struct devlink_trap_group *group)
+{
+	struct devlink_trap_group_item *group_item;
+	int err;
+
+	if (devlink_trap_group_item_lookup(devlink, group->name))
+		return -EEXIST;
+
+	group_item = kzalloc(sizeof(*group_item), GFP_KERNEL);
+	if (!group_item)
+		return -ENOMEM;
+
+	group_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats);
+	if (!group_item->stats) {
+		err = -ENOMEM;
+		goto err_stats_alloc;
+	}
+
+	group_item->group = group;
+
+	err = devlink_trap_group_item_policer_link(devlink, group_item);
+	if (err)
+		goto err_policer_link;
+
+	if (devlink->ops->trap_group_init) {
+		err = devlink->ops->trap_group_init(devlink, group);
+		if (err)
+			goto err_group_init;
+	}
+
+	list_add_tail(&group_item->list, &devlink->trap_group_list);
+	devlink_trap_group_notify(devlink, group_item,
+				  DEVLINK_CMD_TRAP_GROUP_NEW);
+
+	return 0;
+
+err_group_init:
+err_policer_link:
+	free_percpu(group_item->stats);
+err_stats_alloc:
+	kfree(group_item);
+	return err;
+}
+
+static void
+devlink_trap_group_unregister(struct devlink *devlink,
+			      const struct devlink_trap_group *group)
+{
+	struct devlink_trap_group_item *group_item;
+
+	group_item = devlink_trap_group_item_lookup(devlink, group->name);
+	if (WARN_ON_ONCE(!group_item))
+		return;
+
+	devlink_trap_group_notify(devlink, group_item,
+				  DEVLINK_CMD_TRAP_GROUP_DEL);
+	list_del(&group_item->list);
+	free_percpu(group_item->stats);
+	kfree(group_item);
+}
+
+/**
+ * devl_trap_groups_register - Register packet trap groups with devlink.
+ * @devlink: devlink.
+ * @groups: Packet trap groups.
+ * @groups_count: Count of provided packet trap groups.
+ *
+ * Return: Non-zero value on failure.
+ */
+int devl_trap_groups_register(struct devlink *devlink,
+			      const struct devlink_trap_group *groups,
+			      size_t groups_count)
+{
+	int i, err;
+
+	devl_assert_locked(devlink);
+	for (i = 0; i < groups_count; i++) {
+		const struct devlink_trap_group *group = &groups[i];
+
+		err = devlink_trap_group_verify(group);
+		if (err)
+			goto err_trap_group_verify;
+
+		err = devlink_trap_group_register(devlink, group);
+		if (err)
+			goto err_trap_group_register;
+	}
+
+	return 0;
+
+err_trap_group_register:
+err_trap_group_verify:
+	for (i--; i >= 0; i--)
+		devlink_trap_group_unregister(devlink, &groups[i]);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devl_trap_groups_register);
+
+/**
+ * devlink_trap_groups_register - Register packet trap groups with devlink.
+ * @devlink: devlink.
+ * @groups: Packet trap groups.
+ * @groups_count: Count of provided packet trap groups.
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ *
+ * Return: Non-zero value on failure.
+ */
+int devlink_trap_groups_register(struct devlink *devlink,
+				 const struct devlink_trap_group *groups,
+				 size_t groups_count)
+{
+	int err;
+
+	devl_lock(devlink);
+	err = devl_trap_groups_register(devlink, groups, groups_count);
+	devl_unlock(devlink);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devlink_trap_groups_register);
+
+/**
+ * devl_trap_groups_unregister - Unregister packet trap groups from devlink.
+ * @devlink: devlink.
+ * @groups: Packet trap groups.
+ * @groups_count: Count of provided packet trap groups.
+ */
+void devl_trap_groups_unregister(struct devlink *devlink,
+				 const struct devlink_trap_group *groups,
+				 size_t groups_count)
+{
+	int i;
+
+	devl_assert_locked(devlink);
+	for (i = groups_count - 1; i >= 0; i--)
+		devlink_trap_group_unregister(devlink, &groups[i]);
+}
+EXPORT_SYMBOL_GPL(devl_trap_groups_unregister);
+
+/**
+ * devlink_trap_groups_unregister - Unregister packet trap groups from devlink.
+ * @devlink: devlink.
+ * @groups: Packet trap groups.
+ * @groups_count: Count of provided packet trap groups.
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_trap_groups_unregister(struct devlink *devlink,
+				    const struct devlink_trap_group *groups,
+				    size_t groups_count)
+{
+	devl_lock(devlink);
+	devl_trap_groups_unregister(devlink, groups, groups_count);
+	devl_unlock(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_trap_groups_unregister);
+
+static void
+devlink_trap_policer_notify(struct devlink *devlink,
+			    const struct devlink_trap_policer_item *policer_item,
+			    enum devlink_command cmd)
+{
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_POLICER_NEW &&
+		     cmd != DEVLINK_CMD_TRAP_POLICER_DEL);
+	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+		return;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, cmd, 0,
+					   0, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+void devlink_trap_policers_notify_register(struct devlink *devlink)
+{
+	struct devlink_trap_policer_item *policer_item;
+
+	list_for_each_entry(policer_item, &devlink->trap_policer_list, list)
+		devlink_trap_policer_notify(devlink, policer_item,
+					    DEVLINK_CMD_TRAP_POLICER_NEW);
+}
+
+void devlink_trap_policers_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_trap_policer_item *policer_item;
+
+	list_for_each_entry_reverse(policer_item, &devlink->trap_policer_list,
+				    list)
+		devlink_trap_policer_notify(devlink, policer_item,
+					    DEVLINK_CMD_TRAP_POLICER_DEL);
+}
+
+static int
+devlink_trap_policer_register(struct devlink *devlink,
+			      const struct devlink_trap_policer *policer)
+{
+	struct devlink_trap_policer_item *policer_item;
+	int err;
+
+	if (devlink_trap_policer_item_lookup(devlink, policer->id))
+		return -EEXIST;
+
+	policer_item = kzalloc(sizeof(*policer_item), GFP_KERNEL);
+	if (!policer_item)
+		return -ENOMEM;
+
+	policer_item->policer = policer;
+	policer_item->rate = policer->init_rate;
+	policer_item->burst = policer->init_burst;
+
+	if (devlink->ops->trap_policer_init) {
+		err = devlink->ops->trap_policer_init(devlink, policer);
+		if (err)
+			goto err_policer_init;
+	}
+
+	list_add_tail(&policer_item->list, &devlink->trap_policer_list);
+	devlink_trap_policer_notify(devlink, policer_item,
+				    DEVLINK_CMD_TRAP_POLICER_NEW);
+
+	return 0;
+
+err_policer_init:
+	kfree(policer_item);
+	return err;
+}
+
+static void
+devlink_trap_policer_unregister(struct devlink *devlink,
+				const struct devlink_trap_policer *policer)
+{
+	struct devlink_trap_policer_item *policer_item;
+
+	policer_item = devlink_trap_policer_item_lookup(devlink, policer->id);
+	if (WARN_ON_ONCE(!policer_item))
+		return;
+
+	devlink_trap_policer_notify(devlink, policer_item,
+				    DEVLINK_CMD_TRAP_POLICER_DEL);
+	list_del(&policer_item->list);
+	if (devlink->ops->trap_policer_fini)
+		devlink->ops->trap_policer_fini(devlink, policer);
+	kfree(policer_item);
+}
+
+/**
+ * devl_trap_policers_register - Register packet trap policers with devlink.
+ * @devlink: devlink.
+ * @policers: Packet trap policers.
+ * @policers_count: Count of provided packet trap policers.
+ *
+ * Return: Non-zero value on failure.
+ */
+int
+devl_trap_policers_register(struct devlink *devlink,
+			    const struct devlink_trap_policer *policers,
+			    size_t policers_count)
+{
+	int i, err;
+
+	devl_assert_locked(devlink);
+	for (i = 0; i < policers_count; i++) {
+		const struct devlink_trap_policer *policer = &policers[i];
+
+		if (WARN_ON(policer->id == 0 ||
+			    policer->max_rate < policer->min_rate ||
+			    policer->max_burst < policer->min_burst)) {
+			err = -EINVAL;
+			goto err_trap_policer_verify;
+		}
+
+		err = devlink_trap_policer_register(devlink, policer);
+		if (err)
+			goto err_trap_policer_register;
+	}
+	return 0;
+
+err_trap_policer_register:
+err_trap_policer_verify:
+	for (i--; i >= 0; i--)
+		devlink_trap_policer_unregister(devlink, &policers[i]);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devl_trap_policers_register);
+
+/**
+ * devl_trap_policers_unregister - Unregister packet trap policers from devlink.
+ * @devlink: devlink.
+ * @policers: Packet trap policers.
+ * @policers_count: Count of provided packet trap policers.
+ */
+void
+devl_trap_policers_unregister(struct devlink *devlink,
+			      const struct devlink_trap_policer *policers,
+			      size_t policers_count)
+{
+	int i;
+
+	devl_assert_locked(devlink);
+	for (i = policers_count - 1; i >= 0; i--)
+		devlink_trap_policer_unregister(devlink, &policers[i]);
+}
+EXPORT_SYMBOL_GPL(devl_trap_policers_unregister);
-- 
GitLab


From 7cc7194e85ca01185f9d123e68189ef0a40f0c6a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:53 +0200
Subject: [PATCH 1798/1806] devlink: push rate related code into separate file

Cut out another chunk from leftover.c and put rate related code
into a separate file.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-12-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/Makefile        |   2 +-
 net/devlink/devl_internal.h |   5 +
 net/devlink/leftover.c      | 718 -----------------------------------
 net/devlink/rate.c          | 722 ++++++++++++++++++++++++++++++++++++
 4 files changed, 728 insertions(+), 719 deletions(-)
 create mode 100644 net/devlink/rate.c

diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index 523efffe522c9..f61aa97688f52 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o sb.o dpipe.o \
-	 resource.o param.o region.o health.o trap.o
+	 resource.o param.o region.o health.o trap.o rate.o
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 148525aa2847e..8b530f15c4392 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -166,6 +166,8 @@ void devlink_trap_groups_notify_register(struct devlink *devlink);
 void devlink_trap_groups_notify_unregister(struct devlink *devlink);
 void devlink_traps_notify_register(struct devlink *devlink);
 void devlink_traps_notify_unregister(struct devlink *devlink);
+void devlink_rates_notify_register(struct devlink *devlink);
+void devlink_rates_notify_unregister(struct devlink *devlink);
 
 /* Ports */
 #define ASSERT_DEVLINK_PORT_INITIALIZED(devlink_port)				\
@@ -278,3 +280,6 @@ int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb,
 				       struct genl_info *info);
 int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
 					 struct genl_info *info);
+int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 5b153ce097ab6..13958c3da59ac 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -37,80 +37,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
-static inline bool
-devlink_rate_is_leaf(struct devlink_rate *devlink_rate)
-{
-	return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF;
-}
-
-static inline bool
-devlink_rate_is_node(struct devlink_rate *devlink_rate)
-{
-	return devlink_rate->type == DEVLINK_RATE_TYPE_NODE;
-}
-
-static struct devlink_rate *
-devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info)
-{
-	struct devlink_rate *devlink_rate;
-	struct devlink_port *devlink_port;
-
-	devlink_port = devlink_port_get_from_attrs(devlink, info->attrs);
-	if (IS_ERR(devlink_port))
-		return ERR_CAST(devlink_port);
-	devlink_rate = devlink_port->devlink_rate;
-	return devlink_rate ?: ERR_PTR(-ENODEV);
-}
-
-static struct devlink_rate *
-devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name)
-{
-	static struct devlink_rate *devlink_rate;
-
-	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
-		if (devlink_rate_is_node(devlink_rate) &&
-		    !strcmp(node_name, devlink_rate->name))
-			return devlink_rate;
-	}
-	return ERR_PTR(-ENODEV);
-}
-
-static struct devlink_rate *
-devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
-{
-	const char *rate_node_name;
-	size_t len;
-
-	if (!attrs[DEVLINK_ATTR_RATE_NODE_NAME])
-		return ERR_PTR(-EINVAL);
-	rate_node_name = nla_data(attrs[DEVLINK_ATTR_RATE_NODE_NAME]);
-	len = strlen(rate_node_name);
-	/* Name cannot be empty or decimal number */
-	if (!len || strspn(rate_node_name, "0123456789") == len)
-		return ERR_PTR(-EINVAL);
-
-	return devlink_rate_node_get_by_name(devlink, rate_node_name);
-}
-
-static struct devlink_rate *
-devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info)
-{
-	return devlink_rate_node_get_from_attrs(devlink, info->attrs);
-}
-
-static struct devlink_rate *
-devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info)
-{
-	struct nlattr **attrs = info->attrs;
-
-	if (attrs[DEVLINK_ATTR_PORT_INDEX])
-		return devlink_rate_leaf_get_from_info(devlink, info);
-	else if (attrs[DEVLINK_ATTR_RATE_NODE_NAME])
-		return devlink_rate_node_get_from_info(devlink, info);
-	else
-		return ERR_PTR(-EINVAL);
-}
-
 static struct devlink_linecard *
 devlink_linecard_get_by_index(struct devlink *devlink,
 			      unsigned int linecard_index)
@@ -169,491 +95,6 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int devlink_nl_rate_fill(struct sk_buff *msg,
-				struct devlink_rate *devlink_rate,
-				enum devlink_command cmd, u32 portid, u32 seq,
-				int flags, struct netlink_ext_ack *extack)
-{
-	struct devlink *devlink = devlink_rate->devlink;
-	void *hdr;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-
-	if (nla_put_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type))
-		goto nla_put_failure;
-
-	if (devlink_rate_is_leaf(devlink_rate)) {
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
-				devlink_rate->devlink_port->index))
-			goto nla_put_failure;
-	} else if (devlink_rate_is_node(devlink_rate)) {
-		if (nla_put_string(msg, DEVLINK_ATTR_RATE_NODE_NAME,
-				   devlink_rate->name))
-			goto nla_put_failure;
-	}
-
-	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE,
-			      devlink_rate->tx_share, DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-
-	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_MAX,
-			      devlink_rate->tx_max, DEVLINK_ATTR_PAD))
-		goto nla_put_failure;
-
-	if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_PRIORITY,
-			devlink_rate->tx_priority))
-		goto nla_put_failure;
-
-	if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_WEIGHT,
-			devlink_rate->tx_weight))
-		goto nla_put_failure;
-
-	if (devlink_rate->parent)
-		if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME,
-				   devlink_rate->parent->name))
-			goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-	return 0;
-
-nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
-}
-
-static void devlink_rate_notify(struct devlink_rate *devlink_rate,
-				enum devlink_command cmd)
-{
-	struct devlink *devlink = devlink_rate->devlink;
-	struct sk_buff *msg;
-	int err;
-
-	WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && cmd != DEVLINK_CMD_RATE_DEL);
-
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
-		return;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return;
-
-	err = devlink_nl_rate_fill(msg, devlink_rate, cmd, 0, 0, 0, NULL);
-	if (err) {
-		nlmsg_free(msg);
-		return;
-	}
-
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
-}
-
-static void devlink_rates_notify_register(struct devlink *devlink)
-{
-	struct devlink_rate *rate_node;
-
-	list_for_each_entry(rate_node, &devlink->rate_list, list)
-		devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
-}
-
-static void devlink_rates_notify_unregister(struct devlink *devlink)
-{
-	struct devlink_rate *rate_node;
-
-	list_for_each_entry_reverse(rate_node, &devlink->rate_list, list)
-		devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
-}
-
-static int
-devlink_nl_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
-			     struct netlink_callback *cb, int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_rate *devlink_rate;
-	int idx = 0;
-	int err = 0;
-
-	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
-		enum devlink_command cmd = DEVLINK_CMD_RATE_NEW;
-		u32 id = NETLINK_CB(cb->skb).portid;
-
-		if (idx < state->idx) {
-			idx++;
-			continue;
-		}
-		err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id,
-					   cb->nlh->nlmsg_seq, flags, NULL);
-		if (err) {
-			state->idx = idx;
-			break;
-		}
-		idx++;
-	}
-
-	return err;
-}
-
-int devlink_nl_rate_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_rate_get_dump_one);
-}
-
-int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_rate *devlink_rate;
-	struct sk_buff *msg;
-	int err;
-
-	devlink_rate = devlink_rate_get_from_info(devlink, info);
-	if (IS_ERR(devlink_rate))
-		return PTR_ERR(devlink_rate);
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	err = devlink_nl_rate_fill(msg, devlink_rate, DEVLINK_CMD_RATE_NEW,
-				   info->snd_portid, info->snd_seq, 0,
-				   info->extack);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
-
-	return genlmsg_reply(msg, info);
-}
-
-static bool
-devlink_rate_is_parent_node(struct devlink_rate *devlink_rate,
-			    struct devlink_rate *parent)
-{
-	while (parent) {
-		if (parent == devlink_rate)
-			return true;
-		parent = parent->parent;
-	}
-	return false;
-}
-
-static int
-devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate,
-				struct genl_info *info,
-				struct nlattr *nla_parent)
-{
-	struct devlink *devlink = devlink_rate->devlink;
-	const char *parent_name = nla_data(nla_parent);
-	const struct devlink_ops *ops = devlink->ops;
-	size_t len = strlen(parent_name);
-	struct devlink_rate *parent;
-	int err = -EOPNOTSUPP;
-
-	parent = devlink_rate->parent;
-
-	if (parent && !len) {
-		if (devlink_rate_is_leaf(devlink_rate))
-			err = ops->rate_leaf_parent_set(devlink_rate, NULL,
-							devlink_rate->priv, NULL,
-							info->extack);
-		else if (devlink_rate_is_node(devlink_rate))
-			err = ops->rate_node_parent_set(devlink_rate, NULL,
-							devlink_rate->priv, NULL,
-							info->extack);
-		if (err)
-			return err;
-
-		refcount_dec(&parent->refcnt);
-		devlink_rate->parent = NULL;
-	} else if (len) {
-		parent = devlink_rate_node_get_by_name(devlink, parent_name);
-		if (IS_ERR(parent))
-			return -ENODEV;
-
-		if (parent == devlink_rate) {
-			NL_SET_ERR_MSG(info->extack, "Parent to self is not allowed");
-			return -EINVAL;
-		}
-
-		if (devlink_rate_is_node(devlink_rate) &&
-		    devlink_rate_is_parent_node(devlink_rate, parent->parent)) {
-			NL_SET_ERR_MSG(info->extack, "Node is already a parent of parent node.");
-			return -EEXIST;
-		}
-
-		if (devlink_rate_is_leaf(devlink_rate))
-			err = ops->rate_leaf_parent_set(devlink_rate, parent,
-							devlink_rate->priv, parent->priv,
-							info->extack);
-		else if (devlink_rate_is_node(devlink_rate))
-			err = ops->rate_node_parent_set(devlink_rate, parent,
-							devlink_rate->priv, parent->priv,
-							info->extack);
-		if (err)
-			return err;
-
-		if (devlink_rate->parent)
-			/* we're reassigning to other parent in this case */
-			refcount_dec(&devlink_rate->parent->refcnt);
-
-		refcount_inc(&parent->refcnt);
-		devlink_rate->parent = parent;
-	}
-
-	return 0;
-}
-
-static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
-			       const struct devlink_ops *ops,
-			       struct genl_info *info)
-{
-	struct nlattr *nla_parent, **attrs = info->attrs;
-	int err = -EOPNOTSUPP;
-	u32 priority;
-	u32 weight;
-	u64 rate;
-
-	if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) {
-		rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]);
-		if (devlink_rate_is_leaf(devlink_rate))
-			err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv,
-							  rate, info->extack);
-		else if (devlink_rate_is_node(devlink_rate))
-			err = ops->rate_node_tx_share_set(devlink_rate, devlink_rate->priv,
-							  rate, info->extack);
-		if (err)
-			return err;
-		devlink_rate->tx_share = rate;
-	}
-
-	if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) {
-		rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]);
-		if (devlink_rate_is_leaf(devlink_rate))
-			err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv,
-							rate, info->extack);
-		else if (devlink_rate_is_node(devlink_rate))
-			err = ops->rate_node_tx_max_set(devlink_rate, devlink_rate->priv,
-							rate, info->extack);
-		if (err)
-			return err;
-		devlink_rate->tx_max = rate;
-	}
-
-	if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY]) {
-		priority = nla_get_u32(attrs[DEVLINK_ATTR_RATE_TX_PRIORITY]);
-		if (devlink_rate_is_leaf(devlink_rate))
-			err = ops->rate_leaf_tx_priority_set(devlink_rate, devlink_rate->priv,
-							     priority, info->extack);
-		else if (devlink_rate_is_node(devlink_rate))
-			err = ops->rate_node_tx_priority_set(devlink_rate, devlink_rate->priv,
-							     priority, info->extack);
-
-		if (err)
-			return err;
-		devlink_rate->tx_priority = priority;
-	}
-
-	if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT]) {
-		weight = nla_get_u32(attrs[DEVLINK_ATTR_RATE_TX_WEIGHT]);
-		if (devlink_rate_is_leaf(devlink_rate))
-			err = ops->rate_leaf_tx_weight_set(devlink_rate, devlink_rate->priv,
-							   weight, info->extack);
-		else if (devlink_rate_is_node(devlink_rate))
-			err = ops->rate_node_tx_weight_set(devlink_rate, devlink_rate->priv,
-							   weight, info->extack);
-
-		if (err)
-			return err;
-		devlink_rate->tx_weight = weight;
-	}
-
-	nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME];
-	if (nla_parent) {
-		err = devlink_nl_rate_parent_node_set(devlink_rate, info,
-						      nla_parent);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops,
-					   struct genl_info *info,
-					   enum devlink_rate_type type)
-{
-	struct nlattr **attrs = info->attrs;
-
-	if (type == DEVLINK_RATE_TYPE_LEAF) {
-		if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_leaf_tx_share_set) {
-			NL_SET_ERR_MSG(info->extack, "TX share set isn't supported for the leafs");
-			return false;
-		}
-		if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_leaf_tx_max_set) {
-			NL_SET_ERR_MSG(info->extack, "TX max set isn't supported for the leafs");
-			return false;
-		}
-		if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
-		    !ops->rate_leaf_parent_set) {
-			NL_SET_ERR_MSG(info->extack, "Parent set isn't supported for the leafs");
-			return false;
-		}
-		if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY] && !ops->rate_leaf_tx_priority_set) {
-			NL_SET_ERR_MSG_ATTR(info->extack,
-					    attrs[DEVLINK_ATTR_RATE_TX_PRIORITY],
-					    "TX priority set isn't supported for the leafs");
-			return false;
-		}
-		if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT] && !ops->rate_leaf_tx_weight_set) {
-			NL_SET_ERR_MSG_ATTR(info->extack,
-					    attrs[DEVLINK_ATTR_RATE_TX_WEIGHT],
-					    "TX weight set isn't supported for the leafs");
-			return false;
-		}
-	} else if (type == DEVLINK_RATE_TYPE_NODE) {
-		if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) {
-			NL_SET_ERR_MSG(info->extack, "TX share set isn't supported for the nodes");
-			return false;
-		}
-		if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_node_tx_max_set) {
-			NL_SET_ERR_MSG(info->extack, "TX max set isn't supported for the nodes");
-			return false;
-		}
-		if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
-		    !ops->rate_node_parent_set) {
-			NL_SET_ERR_MSG(info->extack, "Parent set isn't supported for the nodes");
-			return false;
-		}
-		if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY] && !ops->rate_node_tx_priority_set) {
-			NL_SET_ERR_MSG_ATTR(info->extack,
-					    attrs[DEVLINK_ATTR_RATE_TX_PRIORITY],
-					    "TX priority set isn't supported for the nodes");
-			return false;
-		}
-		if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT] && !ops->rate_node_tx_weight_set) {
-			NL_SET_ERR_MSG_ATTR(info->extack,
-					    attrs[DEVLINK_ATTR_RATE_TX_WEIGHT],
-					    "TX weight set isn't supported for the nodes");
-			return false;
-		}
-	} else {
-		WARN(1, "Unknown type of rate object");
-		return false;
-	}
-
-	return true;
-}
-
-static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb,
-					struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_rate *devlink_rate;
-	const struct devlink_ops *ops;
-	int err;
-
-	devlink_rate = devlink_rate_get_from_info(devlink, info);
-	if (IS_ERR(devlink_rate))
-		return PTR_ERR(devlink_rate);
-
-	ops = devlink->ops;
-	if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type))
-		return -EOPNOTSUPP;
-
-	err = devlink_nl_rate_set(devlink_rate, ops, info);
-
-	if (!err)
-		devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
-	return err;
-}
-
-static int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb,
-					struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_rate *rate_node;
-	const struct devlink_ops *ops;
-	int err;
-
-	ops = devlink->ops;
-	if (!ops || !ops->rate_node_new || !ops->rate_node_del) {
-		NL_SET_ERR_MSG(info->extack, "Rate nodes aren't supported");
-		return -EOPNOTSUPP;
-	}
-
-	if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE))
-		return -EOPNOTSUPP;
-
-	rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs);
-	if (!IS_ERR(rate_node))
-		return -EEXIST;
-	else if (rate_node == ERR_PTR(-EINVAL))
-		return -EINVAL;
-
-	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
-	if (!rate_node)
-		return -ENOMEM;
-
-	rate_node->devlink = devlink;
-	rate_node->type = DEVLINK_RATE_TYPE_NODE;
-	rate_node->name = nla_strdup(info->attrs[DEVLINK_ATTR_RATE_NODE_NAME], GFP_KERNEL);
-	if (!rate_node->name) {
-		err = -ENOMEM;
-		goto err_strdup;
-	}
-
-	err = ops->rate_node_new(rate_node, &rate_node->priv, info->extack);
-	if (err)
-		goto err_node_new;
-
-	err = devlink_nl_rate_set(rate_node, ops, info);
-	if (err)
-		goto err_rate_set;
-
-	refcount_set(&rate_node->refcnt, 1);
-	list_add(&rate_node->list, &devlink->rate_list);
-	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
-	return 0;
-
-err_rate_set:
-	ops->rate_node_del(rate_node, rate_node->priv, info->extack);
-err_node_new:
-	kfree(rate_node->name);
-err_strdup:
-	kfree(rate_node);
-	return err;
-}
-
-static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb,
-					struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_rate *rate_node;
-	int err;
-
-	rate_node = devlink_rate_node_get_from_info(devlink, info);
-	if (IS_ERR(rate_node))
-		return PTR_ERR(rate_node);
-
-	if (refcount_read(&rate_node->refcnt) > 1) {
-		NL_SET_ERR_MSG(info->extack, "Node has children. Cannot delete node.");
-		return -EBUSY;
-	}
-
-	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
-	err = devlink->ops->rate_node_del(rate_node, rate_node->priv,
-					  info->extack);
-	if (rate_node->parent)
-		refcount_dec(&rate_node->parent->refcnt);
-	list_del(&rate_node->list);
-	kfree(rate_node->name);
-	kfree(rate_node);
-	return err;
-}
-
 struct devlink_linecard_type {
 	const char *type;
 	const void *priv;
@@ -986,19 +427,6 @@ static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb,
 	return 0;
 }
 
-int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
-			     struct netlink_ext_ack *extack)
-{
-	struct devlink_rate *devlink_rate;
-
-	list_for_each_entry(devlink_rate, &devlink->rate_list, list)
-		if (devlink_rate_is_node(devlink_rate)) {
-			NL_SET_ERR_MSG(extack, "Rate node(s) exists.");
-			return -EBUSY;
-		}
-	return 0;
-}
-
 const struct genl_small_ops devlink_nl_small_ops[40] = {
 	{
 		.cmd = DEVLINK_CMD_PORT_SET,
@@ -1276,152 +704,6 @@ void devlink_notify_unregister(struct devlink *devlink)
 	devlink_notify(devlink, DEVLINK_CMD_DEL);
 }
 
-/**
- * devl_rate_node_create - create devlink rate node
- * @devlink: devlink instance
- * @priv: driver private data
- * @node_name: name of the resulting node
- * @parent: parent devlink_rate struct
- *
- * Create devlink rate object of type node
- */
-struct devlink_rate *
-devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,
-		      struct devlink_rate *parent)
-{
-	struct devlink_rate *rate_node;
-
-	rate_node = devlink_rate_node_get_by_name(devlink, node_name);
-	if (!IS_ERR(rate_node))
-		return ERR_PTR(-EEXIST);
-
-	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
-	if (!rate_node)
-		return ERR_PTR(-ENOMEM);
-
-	if (parent) {
-		rate_node->parent = parent;
-		refcount_inc(&rate_node->parent->refcnt);
-	}
-
-	rate_node->type = DEVLINK_RATE_TYPE_NODE;
-	rate_node->devlink = devlink;
-	rate_node->priv = priv;
-
-	rate_node->name = kstrdup(node_name, GFP_KERNEL);
-	if (!rate_node->name) {
-		kfree(rate_node);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	refcount_set(&rate_node->refcnt, 1);
-	list_add(&rate_node->list, &devlink->rate_list);
-	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
-	return rate_node;
-}
-EXPORT_SYMBOL_GPL(devl_rate_node_create);
-
-/**
- * devl_rate_leaf_create - create devlink rate leaf
- * @devlink_port: devlink port object to create rate object on
- * @priv: driver private data
- * @parent: parent devlink_rate struct
- *
- * Create devlink rate object of type leaf on provided @devlink_port.
- */
-int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv,
-			  struct devlink_rate *parent)
-{
-	struct devlink *devlink = devlink_port->devlink;
-	struct devlink_rate *devlink_rate;
-
-	devl_assert_locked(devlink_port->devlink);
-
-	if (WARN_ON(devlink_port->devlink_rate))
-		return -EBUSY;
-
-	devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL);
-	if (!devlink_rate)
-		return -ENOMEM;
-
-	if (parent) {
-		devlink_rate->parent = parent;
-		refcount_inc(&devlink_rate->parent->refcnt);
-	}
-
-	devlink_rate->type = DEVLINK_RATE_TYPE_LEAF;
-	devlink_rate->devlink = devlink;
-	devlink_rate->devlink_port = devlink_port;
-	devlink_rate->priv = priv;
-	list_add_tail(&devlink_rate->list, &devlink->rate_list);
-	devlink_port->devlink_rate = devlink_rate;
-	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devl_rate_leaf_create);
-
-/**
- * devl_rate_leaf_destroy - destroy devlink rate leaf
- *
- * @devlink_port: devlink port linked to the rate object
- *
- * Destroy the devlink rate object of type leaf on provided @devlink_port.
- */
-void devl_rate_leaf_destroy(struct devlink_port *devlink_port)
-{
-	struct devlink_rate *devlink_rate = devlink_port->devlink_rate;
-
-	devl_assert_locked(devlink_port->devlink);
-	if (!devlink_rate)
-		return;
-
-	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL);
-	if (devlink_rate->parent)
-		refcount_dec(&devlink_rate->parent->refcnt);
-	list_del(&devlink_rate->list);
-	devlink_port->devlink_rate = NULL;
-	kfree(devlink_rate);
-}
-EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy);
-
-/**
- * devl_rate_nodes_destroy - destroy all devlink rate nodes on device
- * @devlink: devlink instance
- *
- * Unset parent for all rate objects and destroy all rate nodes
- * on specified device.
- */
-void devl_rate_nodes_destroy(struct devlink *devlink)
-{
-	static struct devlink_rate *devlink_rate, *tmp;
-	const struct devlink_ops *ops = devlink->ops;
-
-	devl_assert_locked(devlink);
-
-	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
-		if (!devlink_rate->parent)
-			continue;
-
-		refcount_dec(&devlink_rate->parent->refcnt);
-		if (devlink_rate_is_leaf(devlink_rate))
-			ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv,
-						  NULL, NULL);
-		else if (devlink_rate_is_node(devlink_rate))
-			ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv,
-						  NULL, NULL);
-	}
-	list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) {
-		if (devlink_rate_is_node(devlink_rate)) {
-			ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL);
-			list_del(&devlink_rate->list);
-			kfree(devlink_rate->name);
-			kfree(devlink_rate);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(devl_rate_nodes_destroy);
-
 static int devlink_linecard_types_init(struct devlink_linecard *linecard)
 {
 	struct devlink_linecard_type *linecard_type;
diff --git a/net/devlink/rate.c b/net/devlink/rate.c
new file mode 100644
index 0000000000000..dff1593b8406a
--- /dev/null
+++ b/net/devlink/rate.c
@@ -0,0 +1,722 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include "devl_internal.h"
+
+static inline bool
+devlink_rate_is_leaf(struct devlink_rate *devlink_rate)
+{
+	return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF;
+}
+
+static inline bool
+devlink_rate_is_node(struct devlink_rate *devlink_rate)
+{
+	return devlink_rate->type == DEVLINK_RATE_TYPE_NODE;
+}
+
+static struct devlink_rate *
+devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	struct devlink_rate *devlink_rate;
+	struct devlink_port *devlink_port;
+
+	devlink_port = devlink_port_get_from_attrs(devlink, info->attrs);
+	if (IS_ERR(devlink_port))
+		return ERR_CAST(devlink_port);
+	devlink_rate = devlink_port->devlink_rate;
+	return devlink_rate ?: ERR_PTR(-ENODEV);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name)
+{
+	static struct devlink_rate *devlink_rate;
+
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+		if (devlink_rate_is_node(devlink_rate) &&
+		    !strcmp(node_name, devlink_rate->name))
+			return devlink_rate;
+	}
+	return ERR_PTR(-ENODEV);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
+{
+	const char *rate_node_name;
+	size_t len;
+
+	if (!attrs[DEVLINK_ATTR_RATE_NODE_NAME])
+		return ERR_PTR(-EINVAL);
+	rate_node_name = nla_data(attrs[DEVLINK_ATTR_RATE_NODE_NAME]);
+	len = strlen(rate_node_name);
+	/* Name cannot be empty or decimal number */
+	if (!len || strspn(rate_node_name, "0123456789") == len)
+		return ERR_PTR(-EINVAL);
+
+	return devlink_rate_node_get_by_name(devlink, rate_node_name);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	return devlink_rate_node_get_from_attrs(devlink, info->attrs);
+}
+
+static struct devlink_rate *
+devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	struct nlattr **attrs = info->attrs;
+
+	if (attrs[DEVLINK_ATTR_PORT_INDEX])
+		return devlink_rate_leaf_get_from_info(devlink, info);
+	else if (attrs[DEVLINK_ATTR_RATE_NODE_NAME])
+		return devlink_rate_node_get_from_info(devlink, info);
+	else
+		return ERR_PTR(-EINVAL);
+}
+
+static int devlink_nl_rate_fill(struct sk_buff *msg,
+				struct devlink_rate *devlink_rate,
+				enum devlink_command cmd, u32 portid, u32 seq,
+				int flags, struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = devlink_rate->devlink;
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type))
+		goto nla_put_failure;
+
+	if (devlink_rate_is_leaf(devlink_rate)) {
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				devlink_rate->devlink_port->index))
+			goto nla_put_failure;
+	} else if (devlink_rate_is_node(devlink_rate)) {
+		if (nla_put_string(msg, DEVLINK_ATTR_RATE_NODE_NAME,
+				   devlink_rate->name))
+			goto nla_put_failure;
+	}
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE,
+			      devlink_rate->tx_share, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_MAX,
+			      devlink_rate->tx_max, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_PRIORITY,
+			devlink_rate->tx_priority))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_WEIGHT,
+			devlink_rate->tx_weight))
+		goto nla_put_failure;
+
+	if (devlink_rate->parent)
+		if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME,
+				   devlink_rate->parent->name))
+			goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static void devlink_rate_notify(struct devlink_rate *devlink_rate,
+				enum devlink_command cmd)
+{
+	struct devlink *devlink = devlink_rate->devlink;
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && cmd != DEVLINK_CMD_RATE_DEL);
+
+	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+		return;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_rate_fill(msg, devlink_rate, cmd, 0, 0, 0, NULL);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
+				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+void devlink_rates_notify_register(struct devlink *devlink)
+{
+	struct devlink_rate *rate_node;
+
+	list_for_each_entry(rate_node, &devlink->rate_list, list)
+		devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+}
+
+void devlink_rates_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_rate *rate_node;
+
+	list_for_each_entry_reverse(rate_node, &devlink->rate_list, list)
+		devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
+}
+
+static int
+devlink_nl_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+			     struct netlink_callback *cb, int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_rate *devlink_rate;
+	int idx = 0;
+	int err = 0;
+
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+		enum devlink_command cmd = DEVLINK_CMD_RATE_NEW;
+		u32 id = NETLINK_CB(cb->skb).portid;
+
+		if (idx < state->idx) {
+			idx++;
+			continue;
+		}
+		err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id,
+					   cb->nlh->nlmsg_seq, flags, NULL);
+		if (err) {
+			state->idx = idx;
+			break;
+		}
+		idx++;
+	}
+
+	return err;
+}
+
+int devlink_nl_rate_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_rate_get_dump_one);
+}
+
+int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_rate *devlink_rate;
+	struct sk_buff *msg;
+	int err;
+
+	devlink_rate = devlink_rate_get_from_info(devlink, info);
+	if (IS_ERR(devlink_rate))
+		return PTR_ERR(devlink_rate);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_rate_fill(msg, devlink_rate, DEVLINK_CMD_RATE_NEW,
+				   info->snd_portid, info->snd_seq, 0,
+				   info->extack);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static bool
+devlink_rate_is_parent_node(struct devlink_rate *devlink_rate,
+			    struct devlink_rate *parent)
+{
+	while (parent) {
+		if (parent == devlink_rate)
+			return true;
+		parent = parent->parent;
+	}
+	return false;
+}
+
+static int
+devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate,
+				struct genl_info *info,
+				struct nlattr *nla_parent)
+{
+	struct devlink *devlink = devlink_rate->devlink;
+	const char *parent_name = nla_data(nla_parent);
+	const struct devlink_ops *ops = devlink->ops;
+	size_t len = strlen(parent_name);
+	struct devlink_rate *parent;
+	int err = -EOPNOTSUPP;
+
+	parent = devlink_rate->parent;
+
+	if (parent && !len) {
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_parent_set(devlink_rate, NULL,
+							devlink_rate->priv, NULL,
+							info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_parent_set(devlink_rate, NULL,
+							devlink_rate->priv, NULL,
+							info->extack);
+		if (err)
+			return err;
+
+		refcount_dec(&parent->refcnt);
+		devlink_rate->parent = NULL;
+	} else if (len) {
+		parent = devlink_rate_node_get_by_name(devlink, parent_name);
+		if (IS_ERR(parent))
+			return -ENODEV;
+
+		if (parent == devlink_rate) {
+			NL_SET_ERR_MSG(info->extack, "Parent to self is not allowed");
+			return -EINVAL;
+		}
+
+		if (devlink_rate_is_node(devlink_rate) &&
+		    devlink_rate_is_parent_node(devlink_rate, parent->parent)) {
+			NL_SET_ERR_MSG(info->extack, "Node is already a parent of parent node.");
+			return -EEXIST;
+		}
+
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_parent_set(devlink_rate, parent,
+							devlink_rate->priv, parent->priv,
+							info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_parent_set(devlink_rate, parent,
+							devlink_rate->priv, parent->priv,
+							info->extack);
+		if (err)
+			return err;
+
+		if (devlink_rate->parent)
+			/* we're reassigning to other parent in this case */
+			refcount_dec(&devlink_rate->parent->refcnt);
+
+		refcount_inc(&parent->refcnt);
+		devlink_rate->parent = parent;
+	}
+
+	return 0;
+}
+
+static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
+			       const struct devlink_ops *ops,
+			       struct genl_info *info)
+{
+	struct nlattr *nla_parent, **attrs = info->attrs;
+	int err = -EOPNOTSUPP;
+	u32 priority;
+	u32 weight;
+	u64 rate;
+
+	if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) {
+		rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]);
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv,
+							  rate, info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_tx_share_set(devlink_rate, devlink_rate->priv,
+							  rate, info->extack);
+		if (err)
+			return err;
+		devlink_rate->tx_share = rate;
+	}
+
+	if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) {
+		rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]);
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv,
+							rate, info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_tx_max_set(devlink_rate, devlink_rate->priv,
+							rate, info->extack);
+		if (err)
+			return err;
+		devlink_rate->tx_max = rate;
+	}
+
+	if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY]) {
+		priority = nla_get_u32(attrs[DEVLINK_ATTR_RATE_TX_PRIORITY]);
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_tx_priority_set(devlink_rate, devlink_rate->priv,
+							     priority, info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_tx_priority_set(devlink_rate, devlink_rate->priv,
+							     priority, info->extack);
+
+		if (err)
+			return err;
+		devlink_rate->tx_priority = priority;
+	}
+
+	if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT]) {
+		weight = nla_get_u32(attrs[DEVLINK_ATTR_RATE_TX_WEIGHT]);
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_tx_weight_set(devlink_rate, devlink_rate->priv,
+							   weight, info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_tx_weight_set(devlink_rate, devlink_rate->priv,
+							   weight, info->extack);
+
+		if (err)
+			return err;
+		devlink_rate->tx_weight = weight;
+	}
+
+	nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME];
+	if (nla_parent) {
+		err = devlink_nl_rate_parent_node_set(devlink_rate, info,
+						      nla_parent);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops,
+					   struct genl_info *info,
+					   enum devlink_rate_type type)
+{
+	struct nlattr **attrs = info->attrs;
+
+	if (type == DEVLINK_RATE_TYPE_LEAF) {
+		if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_leaf_tx_share_set) {
+			NL_SET_ERR_MSG(info->extack, "TX share set isn't supported for the leafs");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_leaf_tx_max_set) {
+			NL_SET_ERR_MSG(info->extack, "TX max set isn't supported for the leafs");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
+		    !ops->rate_leaf_parent_set) {
+			NL_SET_ERR_MSG(info->extack, "Parent set isn't supported for the leafs");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY] && !ops->rate_leaf_tx_priority_set) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    attrs[DEVLINK_ATTR_RATE_TX_PRIORITY],
+					    "TX priority set isn't supported for the leafs");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT] && !ops->rate_leaf_tx_weight_set) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    attrs[DEVLINK_ATTR_RATE_TX_WEIGHT],
+					    "TX weight set isn't supported for the leafs");
+			return false;
+		}
+	} else if (type == DEVLINK_RATE_TYPE_NODE) {
+		if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) {
+			NL_SET_ERR_MSG(info->extack, "TX share set isn't supported for the nodes");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_node_tx_max_set) {
+			NL_SET_ERR_MSG(info->extack, "TX max set isn't supported for the nodes");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
+		    !ops->rate_node_parent_set) {
+			NL_SET_ERR_MSG(info->extack, "Parent set isn't supported for the nodes");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY] && !ops->rate_node_tx_priority_set) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    attrs[DEVLINK_ATTR_RATE_TX_PRIORITY],
+					    "TX priority set isn't supported for the nodes");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT] && !ops->rate_node_tx_weight_set) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    attrs[DEVLINK_ATTR_RATE_TX_WEIGHT],
+					    "TX weight set isn't supported for the nodes");
+			return false;
+		}
+	} else {
+		WARN(1, "Unknown type of rate object");
+		return false;
+	}
+
+	return true;
+}
+
+int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_rate *devlink_rate;
+	const struct devlink_ops *ops;
+	int err;
+
+	devlink_rate = devlink_rate_get_from_info(devlink, info);
+	if (IS_ERR(devlink_rate))
+		return PTR_ERR(devlink_rate);
+
+	ops = devlink->ops;
+	if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type))
+		return -EOPNOTSUPP;
+
+	err = devlink_nl_rate_set(devlink_rate, ops, info);
+
+	if (!err)
+		devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+	return err;
+}
+
+int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_rate *rate_node;
+	const struct devlink_ops *ops;
+	int err;
+
+	ops = devlink->ops;
+	if (!ops || !ops->rate_node_new || !ops->rate_node_del) {
+		NL_SET_ERR_MSG(info->extack, "Rate nodes aren't supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE))
+		return -EOPNOTSUPP;
+
+	rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs);
+	if (!IS_ERR(rate_node))
+		return -EEXIST;
+	else if (rate_node == ERR_PTR(-EINVAL))
+		return -EINVAL;
+
+	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
+	if (!rate_node)
+		return -ENOMEM;
+
+	rate_node->devlink = devlink;
+	rate_node->type = DEVLINK_RATE_TYPE_NODE;
+	rate_node->name = nla_strdup(info->attrs[DEVLINK_ATTR_RATE_NODE_NAME], GFP_KERNEL);
+	if (!rate_node->name) {
+		err = -ENOMEM;
+		goto err_strdup;
+	}
+
+	err = ops->rate_node_new(rate_node, &rate_node->priv, info->extack);
+	if (err)
+		goto err_node_new;
+
+	err = devlink_nl_rate_set(rate_node, ops, info);
+	if (err)
+		goto err_rate_set;
+
+	refcount_set(&rate_node->refcnt, 1);
+	list_add(&rate_node->list, &devlink->rate_list);
+	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+	return 0;
+
+err_rate_set:
+	ops->rate_node_del(rate_node, rate_node->priv, info->extack);
+err_node_new:
+	kfree(rate_node->name);
+err_strdup:
+	kfree(rate_node);
+	return err;
+}
+
+int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_rate *rate_node;
+	int err;
+
+	rate_node = devlink_rate_node_get_from_info(devlink, info);
+	if (IS_ERR(rate_node))
+		return PTR_ERR(rate_node);
+
+	if (refcount_read(&rate_node->refcnt) > 1) {
+		NL_SET_ERR_MSG(info->extack, "Node has children. Cannot delete node.");
+		return -EBUSY;
+	}
+
+	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
+	err = devlink->ops->rate_node_del(rate_node, rate_node->priv,
+					  info->extack);
+	if (rate_node->parent)
+		refcount_dec(&rate_node->parent->refcnt);
+	list_del(&rate_node->list);
+	kfree(rate_node->name);
+	kfree(rate_node);
+	return err;
+}
+
+int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
+			     struct netlink_ext_ack *extack)
+{
+	struct devlink_rate *devlink_rate;
+
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list)
+		if (devlink_rate_is_node(devlink_rate)) {
+			NL_SET_ERR_MSG(extack, "Rate node(s) exists.");
+			return -EBUSY;
+		}
+	return 0;
+}
+
+/**
+ * devl_rate_node_create - create devlink rate node
+ * @devlink: devlink instance
+ * @priv: driver private data
+ * @node_name: name of the resulting node
+ * @parent: parent devlink_rate struct
+ *
+ * Create devlink rate object of type node
+ */
+struct devlink_rate *
+devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,
+		      struct devlink_rate *parent)
+{
+	struct devlink_rate *rate_node;
+
+	rate_node = devlink_rate_node_get_by_name(devlink, node_name);
+	if (!IS_ERR(rate_node))
+		return ERR_PTR(-EEXIST);
+
+	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
+	if (!rate_node)
+		return ERR_PTR(-ENOMEM);
+
+	if (parent) {
+		rate_node->parent = parent;
+		refcount_inc(&rate_node->parent->refcnt);
+	}
+
+	rate_node->type = DEVLINK_RATE_TYPE_NODE;
+	rate_node->devlink = devlink;
+	rate_node->priv = priv;
+
+	rate_node->name = kstrdup(node_name, GFP_KERNEL);
+	if (!rate_node->name) {
+		kfree(rate_node);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	refcount_set(&rate_node->refcnt, 1);
+	list_add(&rate_node->list, &devlink->rate_list);
+	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+	return rate_node;
+}
+EXPORT_SYMBOL_GPL(devl_rate_node_create);
+
+/**
+ * devl_rate_leaf_create - create devlink rate leaf
+ * @devlink_port: devlink port object to create rate object on
+ * @priv: driver private data
+ * @parent: parent devlink_rate struct
+ *
+ * Create devlink rate object of type leaf on provided @devlink_port.
+ */
+int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv,
+			  struct devlink_rate *parent)
+{
+	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_rate *devlink_rate;
+
+	devl_assert_locked(devlink_port->devlink);
+
+	if (WARN_ON(devlink_port->devlink_rate))
+		return -EBUSY;
+
+	devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL);
+	if (!devlink_rate)
+		return -ENOMEM;
+
+	if (parent) {
+		devlink_rate->parent = parent;
+		refcount_inc(&devlink_rate->parent->refcnt);
+	}
+
+	devlink_rate->type = DEVLINK_RATE_TYPE_LEAF;
+	devlink_rate->devlink = devlink;
+	devlink_rate->devlink_port = devlink_port;
+	devlink_rate->priv = priv;
+	list_add_tail(&devlink_rate->list, &devlink->rate_list);
+	devlink_port->devlink_rate = devlink_rate;
+	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devl_rate_leaf_create);
+
+/**
+ * devl_rate_leaf_destroy - destroy devlink rate leaf
+ *
+ * @devlink_port: devlink port linked to the rate object
+ *
+ * Destroy the devlink rate object of type leaf on provided @devlink_port.
+ */
+void devl_rate_leaf_destroy(struct devlink_port *devlink_port)
+{
+	struct devlink_rate *devlink_rate = devlink_port->devlink_rate;
+
+	devl_assert_locked(devlink_port->devlink);
+	if (!devlink_rate)
+		return;
+
+	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL);
+	if (devlink_rate->parent)
+		refcount_dec(&devlink_rate->parent->refcnt);
+	list_del(&devlink_rate->list);
+	devlink_port->devlink_rate = NULL;
+	kfree(devlink_rate);
+}
+EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy);
+
+/**
+ * devl_rate_nodes_destroy - destroy all devlink rate nodes on device
+ * @devlink: devlink instance
+ *
+ * Unset parent for all rate objects and destroy all rate nodes
+ * on specified device.
+ */
+void devl_rate_nodes_destroy(struct devlink *devlink)
+{
+	static struct devlink_rate *devlink_rate, *tmp;
+	const struct devlink_ops *ops = devlink->ops;
+
+	devl_assert_locked(devlink);
+
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+		if (!devlink_rate->parent)
+			continue;
+
+		refcount_dec(&devlink_rate->parent->refcnt);
+		if (devlink_rate_is_leaf(devlink_rate))
+			ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv,
+						  NULL, NULL);
+		else if (devlink_rate_is_node(devlink_rate))
+			ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv,
+						  NULL, NULL);
+	}
+	list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) {
+		if (devlink_rate_is_node(devlink_rate)) {
+			ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL);
+			list_del(&devlink_rate->list);
+			kfree(devlink_rate->name);
+			kfree(devlink_rate);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(devl_rate_nodes_destroy);
-- 
GitLab


From 9edbe6f36c5f86776cc1c6ba0f546a4aefe2767f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:54 +0200
Subject: [PATCH 1799/1806] devlink: push linecard related code into separate
 file

Cut out another chunk from leftover.c and put linecard related code
into a separate file.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-13-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/Makefile        |   2 +-
 net/devlink/devl_internal.h |  34 +-
 net/devlink/leftover.c      | 599 -----------------------------------
 net/devlink/linecard.c      | 606 ++++++++++++++++++++++++++++++++++++
 4 files changed, 626 insertions(+), 615 deletions(-)
 create mode 100644 net/devlink/linecard.c

diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index f61aa97688f52..71f490d301d7c 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o sb.o dpipe.o \
-	 resource.o param.o region.o health.o trap.o rate.o
+	 resource.o param.o region.o health.o trap.o rate.o linecard.o
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 8b530f15c4392..8c81f731a4c74 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -168,6 +168,8 @@ void devlink_traps_notify_register(struct devlink *devlink);
 void devlink_traps_notify_unregister(struct devlink *devlink);
 void devlink_rates_notify_register(struct devlink *devlink);
 void devlink_rates_notify_unregister(struct devlink *devlink);
+void devlink_linecards_notify_register(struct devlink *devlink);
+void devlink_linecards_notify_unregister(struct devlink *devlink);
 
 /* Ports */
 #define ASSERT_DEVLINK_PORT_INITIALIZED(devlink_port)				\
@@ -182,21 +184,6 @@ devlink_port_get_from_info(struct devlink *devlink, struct genl_info *info);
 struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink,
 						 struct nlattr **attrs);
 
-/* Linecards */
-struct devlink_linecard {
-	struct list_head list;
-	struct devlink *devlink;
-	unsigned int index;
-	const struct devlink_linecard_ops *ops;
-	void *priv;
-	enum devlink_linecard_state state;
-	struct mutex state_lock; /* Protects state */
-	const char *type;
-	struct devlink_linecard_type *types;
-	unsigned int types_count;
-	struct devlink *nested_devlink;
-};
-
 /* Reload */
 bool devlink_reload_actions_valid(const struct devlink_ops *ops);
 int devlink_reload(struct devlink *devlink, struct net *dest_net,
@@ -222,6 +209,21 @@ int devlink_resources_validate(struct devlink *devlink,
 int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
 			     struct netlink_ext_ack *extack);
 
+/* Linecards */
+struct devlink_linecard {
+	struct list_head list;
+	struct devlink *devlink;
+	unsigned int index;
+	const struct devlink_linecard_ops *ops;
+	void *priv;
+	enum devlink_linecard_state state;
+	struct mutex state_lock; /* Protects state */
+	const char *type;
+	struct devlink_linecard_type *types;
+	unsigned int types_count;
+	struct devlink *nested_devlink;
+};
+
 /* Devlink nl cmds */
 int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
@@ -283,3 +285,5 @@ int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
 int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb,
+				     struct genl_info *info);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 13958c3da59ac..98ccb3a8393d8 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -37,396 +37,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
-static struct devlink_linecard *
-devlink_linecard_get_by_index(struct devlink *devlink,
-			      unsigned int linecard_index)
-{
-	struct devlink_linecard *devlink_linecard;
-
-	list_for_each_entry(devlink_linecard, &devlink->linecard_list, list) {
-		if (devlink_linecard->index == linecard_index)
-			return devlink_linecard;
-	}
-	return NULL;
-}
-
-static bool devlink_linecard_index_exists(struct devlink *devlink,
-					  unsigned int linecard_index)
-{
-	return devlink_linecard_get_by_index(devlink, linecard_index);
-}
-
-static struct devlink_linecard *
-devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
-{
-	if (attrs[DEVLINK_ATTR_LINECARD_INDEX]) {
-		u32 linecard_index = nla_get_u32(attrs[DEVLINK_ATTR_LINECARD_INDEX]);
-		struct devlink_linecard *linecard;
-
-		linecard = devlink_linecard_get_by_index(devlink, linecard_index);
-		if (!linecard)
-			return ERR_PTR(-ENODEV);
-		return linecard;
-	}
-	return ERR_PTR(-EINVAL);
-}
-
-static struct devlink_linecard *
-devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info)
-{
-	return devlink_linecard_get_from_attrs(devlink, info->attrs);
-}
-
-static int devlink_nl_put_nested_handle(struct sk_buff *msg, struct devlink *devlink)
-{
-	struct nlattr *nested_attr;
-
-	nested_attr = nla_nest_start(msg, DEVLINK_ATTR_NESTED_DEVLINK);
-	if (!nested_attr)
-		return -EMSGSIZE;
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-
-	nla_nest_end(msg, nested_attr);
-	return 0;
-
-nla_put_failure:
-	nla_nest_cancel(msg, nested_attr);
-	return -EMSGSIZE;
-}
-
-struct devlink_linecard_type {
-	const char *type;
-	const void *priv;
-};
-
-static int devlink_nl_linecard_fill(struct sk_buff *msg,
-				    struct devlink *devlink,
-				    struct devlink_linecard *linecard,
-				    enum devlink_command cmd, u32 portid,
-				    u32 seq, int flags,
-				    struct netlink_ext_ack *extack)
-{
-	struct devlink_linecard_type *linecard_type;
-	struct nlattr *attr;
-	void *hdr;
-	int i;
-
-	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
-	if (!hdr)
-		return -EMSGSIZE;
-
-	if (devlink_nl_put_handle(msg, devlink))
-		goto nla_put_failure;
-	if (nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, linecard->index))
-		goto nla_put_failure;
-	if (nla_put_u8(msg, DEVLINK_ATTR_LINECARD_STATE, linecard->state))
-		goto nla_put_failure;
-	if (linecard->type &&
-	    nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, linecard->type))
-		goto nla_put_failure;
-
-	if (linecard->types_count) {
-		attr = nla_nest_start(msg,
-				      DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES);
-		if (!attr)
-			goto nla_put_failure;
-		for (i = 0; i < linecard->types_count; i++) {
-			linecard_type = &linecard->types[i];
-			if (nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE,
-					   linecard_type->type)) {
-				nla_nest_cancel(msg, attr);
-				goto nla_put_failure;
-			}
-		}
-		nla_nest_end(msg, attr);
-	}
-
-	if (linecard->nested_devlink &&
-	    devlink_nl_put_nested_handle(msg, linecard->nested_devlink))
-		goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-	return 0;
-
-nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
-}
-
-static void devlink_linecard_notify(struct devlink_linecard *linecard,
-				    enum devlink_command cmd)
-{
-	struct devlink *devlink = linecard->devlink;
-	struct sk_buff *msg;
-	int err;
-
-	WARN_ON(cmd != DEVLINK_CMD_LINECARD_NEW &&
-		cmd != DEVLINK_CMD_LINECARD_DEL);
-
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
-		return;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return;
-
-	err = devlink_nl_linecard_fill(msg, devlink, linecard, cmd, 0, 0, 0,
-				       NULL);
-	if (err) {
-		nlmsg_free(msg);
-		return;
-	}
-
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
-}
-
-static void devlink_linecards_notify_register(struct devlink *devlink)
-{
-	struct devlink_linecard *linecard;
-
-	list_for_each_entry(linecard, &devlink->linecard_list, list)
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-}
-
-static void devlink_linecards_notify_unregister(struct devlink *devlink)
-{
-	struct devlink_linecard *linecard;
-
-	list_for_each_entry_reverse(linecard, &devlink->linecard_list, list)
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
-}
-
-int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_linecard *linecard;
-	struct sk_buff *msg;
-	int err;
-
-	linecard = devlink_linecard_get_from_info(devlink, info);
-	if (IS_ERR(linecard))
-		return PTR_ERR(linecard);
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	mutex_lock(&linecard->state_lock);
-	err = devlink_nl_linecard_fill(msg, devlink, linecard,
-				       DEVLINK_CMD_LINECARD_NEW,
-				       info->snd_portid, info->snd_seq, 0,
-				       info->extack);
-	mutex_unlock(&linecard->state_lock);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
-
-	return genlmsg_reply(msg, info);
-}
-
-static int devlink_nl_linecard_get_dump_one(struct sk_buff *msg,
-					    struct devlink *devlink,
-					    struct netlink_callback *cb,
-					    int flags)
-{
-	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
-	struct devlink_linecard *linecard;
-	int idx = 0;
-	int err = 0;
-
-	list_for_each_entry(linecard, &devlink->linecard_list, list) {
-		if (idx < state->idx) {
-			idx++;
-			continue;
-		}
-		mutex_lock(&linecard->state_lock);
-		err = devlink_nl_linecard_fill(msg, devlink, linecard,
-					       DEVLINK_CMD_LINECARD_NEW,
-					       NETLINK_CB(cb->skb).portid,
-					       cb->nlh->nlmsg_seq, flags,
-					       cb->extack);
-		mutex_unlock(&linecard->state_lock);
-		if (err) {
-			state->idx = idx;
-			break;
-		}
-		idx++;
-	}
-
-	return err;
-}
-
-int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
-				   struct netlink_callback *cb)
-{
-	return devlink_nl_dumpit(skb, cb, devlink_nl_linecard_get_dump_one);
-}
-
-static struct devlink_linecard_type *
-devlink_linecard_type_lookup(struct devlink_linecard *linecard,
-			     const char *type)
-{
-	struct devlink_linecard_type *linecard_type;
-	int i;
-
-	for (i = 0; i < linecard->types_count; i++) {
-		linecard_type = &linecard->types[i];
-		if (!strcmp(type, linecard_type->type))
-			return linecard_type;
-	}
-	return NULL;
-}
-
-static int devlink_linecard_type_set(struct devlink_linecard *linecard,
-				     const char *type,
-				     struct netlink_ext_ack *extack)
-{
-	const struct devlink_linecard_ops *ops = linecard->ops;
-	struct devlink_linecard_type *linecard_type;
-	int err;
-
-	mutex_lock(&linecard->state_lock);
-	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
-		err = -EBUSY;
-		goto out;
-	}
-	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
-		err = -EBUSY;
-		goto out;
-	}
-
-	linecard_type = devlink_linecard_type_lookup(linecard, type);
-	if (!linecard_type) {
-		NL_SET_ERR_MSG(extack, "Unsupported line card type provided");
-		err = -EINVAL;
-		goto out;
-	}
-
-	if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED &&
-	    linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
-		NL_SET_ERR_MSG(extack, "Line card already provisioned");
-		err = -EBUSY;
-		/* Check if the line card is provisioned in the same
-		 * way the user asks. In case it is, make the operation
-		 * to return success.
-		 */
-		if (ops->same_provision &&
-		    ops->same_provision(linecard, linecard->priv,
-					linecard_type->type,
-					linecard_type->priv))
-			err = 0;
-		goto out;
-	}
-
-	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING;
-	linecard->type = linecard_type->type;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-	err = ops->provision(linecard, linecard->priv, linecard_type->type,
-			     linecard_type->priv, extack);
-	if (err) {
-		/* Provisioning failed. Assume the linecard is unprovisioned
-		 * for future operations.
-		 */
-		mutex_lock(&linecard->state_lock);
-		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-		linecard->type = NULL;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		mutex_unlock(&linecard->state_lock);
-	}
-	return err;
-
-out:
-	mutex_unlock(&linecard->state_lock);
-	return err;
-}
-
-static int devlink_linecard_type_unset(struct devlink_linecard *linecard,
-				       struct netlink_ext_ack *extack)
-{
-	int err;
-
-	mutex_lock(&linecard->state_lock);
-	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
-		err = -EBUSY;
-		goto out;
-	}
-	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
-		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
-		err = -EBUSY;
-		goto out;
-	}
-	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
-		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-		linecard->type = NULL;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		err = 0;
-		goto out;
-	}
-
-	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) {
-		NL_SET_ERR_MSG(extack, "Line card is not provisioned");
-		err = 0;
-		goto out;
-	}
-	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-	err = linecard->ops->unprovision(linecard, linecard->priv,
-					 extack);
-	if (err) {
-		/* Unprovisioning failed. Assume the linecard is unprovisioned
-		 * for future operations.
-		 */
-		mutex_lock(&linecard->state_lock);
-		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-		linecard->type = NULL;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		mutex_unlock(&linecard->state_lock);
-	}
-	return err;
-
-out:
-	mutex_unlock(&linecard->state_lock);
-	return err;
-}
-
-static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb,
-					    struct genl_info *info)
-{
-	struct netlink_ext_ack *extack = info->extack;
-	struct devlink *devlink = info->user_ptr[0];
-	struct devlink_linecard *linecard;
-	int err;
-
-	linecard = devlink_linecard_get_from_info(devlink, info);
-	if (IS_ERR(linecard))
-		return PTR_ERR(linecard);
-
-	if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) {
-		const char *type;
-
-		type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]);
-		if (strcmp(type, "")) {
-			err = devlink_linecard_type_set(linecard, type, extack);
-			if (err)
-				return err;
-		} else {
-			err = devlink_linecard_type_unset(linecard, extack);
-			if (err)
-				return err;
-		}
-	}
-
-	return 0;
-}
-
 const struct genl_small_ops devlink_nl_small_ops[40] = {
 	{
 		.cmd = DEVLINK_CMD_PORT_SET,
@@ -703,212 +313,3 @@ void devlink_notify_unregister(struct devlink *devlink)
 	devlink_linecards_notify_unregister(devlink);
 	devlink_notify(devlink, DEVLINK_CMD_DEL);
 }
-
-static int devlink_linecard_types_init(struct devlink_linecard *linecard)
-{
-	struct devlink_linecard_type *linecard_type;
-	unsigned int count;
-	int i;
-
-	count = linecard->ops->types_count(linecard, linecard->priv);
-	linecard->types = kmalloc_array(count, sizeof(*linecard_type),
-					GFP_KERNEL);
-	if (!linecard->types)
-		return -ENOMEM;
-	linecard->types_count = count;
-
-	for (i = 0; i < count; i++) {
-		linecard_type = &linecard->types[i];
-		linecard->ops->types_get(linecard, linecard->priv, i,
-					 &linecard_type->type,
-					 &linecard_type->priv);
-	}
-	return 0;
-}
-
-static void devlink_linecard_types_fini(struct devlink_linecard *linecard)
-{
-	kfree(linecard->types);
-}
-
-/**
- *	devl_linecard_create - Create devlink linecard
- *
- *	@devlink: devlink
- *	@linecard_index: driver-specific numerical identifier of the linecard
- *	@ops: linecards ops
- *	@priv: user priv pointer
- *
- *	Create devlink linecard instance with provided linecard index.
- *	Caller can use any indexing, even hw-related one.
- *
- *	Return: Line card structure or an ERR_PTR() encoded error code.
- */
-struct devlink_linecard *
-devl_linecard_create(struct devlink *devlink, unsigned int linecard_index,
-		     const struct devlink_linecard_ops *ops, void *priv)
-{
-	struct devlink_linecard *linecard;
-	int err;
-
-	if (WARN_ON(!ops || !ops->provision || !ops->unprovision ||
-		    !ops->types_count || !ops->types_get))
-		return ERR_PTR(-EINVAL);
-
-	if (devlink_linecard_index_exists(devlink, linecard_index))
-		return ERR_PTR(-EEXIST);
-
-	linecard = kzalloc(sizeof(*linecard), GFP_KERNEL);
-	if (!linecard)
-		return ERR_PTR(-ENOMEM);
-
-	linecard->devlink = devlink;
-	linecard->index = linecard_index;
-	linecard->ops = ops;
-	linecard->priv = priv;
-	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-	mutex_init(&linecard->state_lock);
-
-	err = devlink_linecard_types_init(linecard);
-	if (err) {
-		mutex_destroy(&linecard->state_lock);
-		kfree(linecard);
-		return ERR_PTR(err);
-	}
-
-	list_add_tail(&linecard->list, &devlink->linecard_list);
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	return linecard;
-}
-EXPORT_SYMBOL_GPL(devl_linecard_create);
-
-/**
- *	devl_linecard_destroy - Destroy devlink linecard
- *
- *	@linecard: devlink linecard
- */
-void devl_linecard_destroy(struct devlink_linecard *linecard)
-{
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
-	list_del(&linecard->list);
-	devlink_linecard_types_fini(linecard);
-	mutex_destroy(&linecard->state_lock);
-	kfree(linecard);
-}
-EXPORT_SYMBOL_GPL(devl_linecard_destroy);
-
-/**
- *	devlink_linecard_provision_set - Set provisioning on linecard
- *
- *	@linecard: devlink linecard
- *	@type: linecard type
- *
- *	This is either called directly from the provision() op call or
- *	as a result of the provision() op call asynchronously.
- */
-void devlink_linecard_provision_set(struct devlink_linecard *linecard,
-				    const char *type)
-{
-	mutex_lock(&linecard->state_lock);
-	WARN_ON(linecard->type && strcmp(linecard->type, type));
-	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED;
-	linecard->type = type;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_provision_set);
-
-/**
- *	devlink_linecard_provision_clear - Clear provisioning on linecard
- *
- *	@linecard: devlink linecard
- *
- *	This is either called directly from the unprovision() op call or
- *	as a result of the unprovision() op call asynchronously.
- */
-void devlink_linecard_provision_clear(struct devlink_linecard *linecard)
-{
-	mutex_lock(&linecard->state_lock);
-	WARN_ON(linecard->nested_devlink);
-	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
-	linecard->type = NULL;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_provision_clear);
-
-/**
- *	devlink_linecard_provision_fail - Fail provisioning on linecard
- *
- *	@linecard: devlink linecard
- *
- *	This is either called directly from the provision() op call or
- *	as a result of the provision() op call asynchronously.
- */
-void devlink_linecard_provision_fail(struct devlink_linecard *linecard)
-{
-	mutex_lock(&linecard->state_lock);
-	WARN_ON(linecard->nested_devlink);
-	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING_FAILED;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_provision_fail);
-
-/**
- *	devlink_linecard_activate - Set linecard active
- *
- *	@linecard: devlink linecard
- */
-void devlink_linecard_activate(struct devlink_linecard *linecard)
-{
-	mutex_lock(&linecard->state_lock);
-	WARN_ON(linecard->state != DEVLINK_LINECARD_STATE_PROVISIONED);
-	linecard->state = DEVLINK_LINECARD_STATE_ACTIVE;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_activate);
-
-/**
- *	devlink_linecard_deactivate - Set linecard inactive
- *
- *	@linecard: devlink linecard
- */
-void devlink_linecard_deactivate(struct devlink_linecard *linecard)
-{
-	mutex_lock(&linecard->state_lock);
-	switch (linecard->state) {
-	case DEVLINK_LINECARD_STATE_ACTIVE:
-		linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED;
-		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-		break;
-	case DEVLINK_LINECARD_STATE_UNPROVISIONING:
-		/* Line card is being deactivated as part
-		 * of unprovisioning flow.
-		 */
-		break;
-	default:
-		WARN_ON(1);
-		break;
-	}
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_deactivate);
-
-/**
- *	devlink_linecard_nested_dl_set - Attach/detach nested devlink
- *					 instance to linecard.
- *
- *	@linecard: devlink linecard
- *	@nested_devlink: devlink instance to attach or NULL to detach
- */
-void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard,
-				    struct devlink *nested_devlink)
-{
-	mutex_lock(&linecard->state_lock);
-	linecard->nested_devlink = nested_devlink;
-	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
-	mutex_unlock(&linecard->state_lock);
-}
-EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set);
diff --git a/net/devlink/linecard.c b/net/devlink/linecard.c
new file mode 100644
index 0000000000000..85c32c314b0f9
--- /dev/null
+++ b/net/devlink/linecard.c
@@ -0,0 +1,606 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include "devl_internal.h"
+
+static struct devlink_linecard *
+devlink_linecard_get_by_index(struct devlink *devlink,
+			      unsigned int linecard_index)
+{
+	struct devlink_linecard *devlink_linecard;
+
+	list_for_each_entry(devlink_linecard, &devlink->linecard_list, list) {
+		if (devlink_linecard->index == linecard_index)
+			return devlink_linecard;
+	}
+	return NULL;
+}
+
+static bool devlink_linecard_index_exists(struct devlink *devlink,
+					  unsigned int linecard_index)
+{
+	return devlink_linecard_get_by_index(devlink, linecard_index);
+}
+
+static struct devlink_linecard *
+devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
+{
+	if (attrs[DEVLINK_ATTR_LINECARD_INDEX]) {
+		u32 linecard_index = nla_get_u32(attrs[DEVLINK_ATTR_LINECARD_INDEX]);
+		struct devlink_linecard *linecard;
+
+		linecard = devlink_linecard_get_by_index(devlink, linecard_index);
+		if (!linecard)
+			return ERR_PTR(-ENODEV);
+		return linecard;
+	}
+	return ERR_PTR(-EINVAL);
+}
+
+static struct devlink_linecard *
+devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	return devlink_linecard_get_from_attrs(devlink, info->attrs);
+}
+
+static int devlink_nl_put_nested_handle(struct sk_buff *msg, struct devlink *devlink)
+{
+	struct nlattr *nested_attr;
+
+	nested_attr = nla_nest_start(msg, DEVLINK_ATTR_NESTED_DEVLINK);
+	if (!nested_attr)
+		return -EMSGSIZE;
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	nla_nest_end(msg, nested_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, nested_attr);
+	return -EMSGSIZE;
+}
+
+struct devlink_linecard_type {
+	const char *type;
+	const void *priv;
+};
+
+static int devlink_nl_linecard_fill(struct sk_buff *msg,
+				    struct devlink *devlink,
+				    struct devlink_linecard *linecard,
+				    enum devlink_command cmd, u32 portid,
+				    u32 seq, int flags,
+				    struct netlink_ext_ack *extack)
+{
+	struct devlink_linecard_type *linecard_type;
+	struct nlattr *attr;
+	void *hdr;
+	int i;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, linecard->index))
+		goto nla_put_failure;
+	if (nla_put_u8(msg, DEVLINK_ATTR_LINECARD_STATE, linecard->state))
+		goto nla_put_failure;
+	if (linecard->type &&
+	    nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, linecard->type))
+		goto nla_put_failure;
+
+	if (linecard->types_count) {
+		attr = nla_nest_start(msg,
+				      DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES);
+		if (!attr)
+			goto nla_put_failure;
+		for (i = 0; i < linecard->types_count; i++) {
+			linecard_type = &linecard->types[i];
+			if (nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE,
+					   linecard_type->type)) {
+				nla_nest_cancel(msg, attr);
+				goto nla_put_failure;
+			}
+		}
+		nla_nest_end(msg, attr);
+	}
+
+	if (linecard->nested_devlink &&
+	    devlink_nl_put_nested_handle(msg, linecard->nested_devlink))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static void devlink_linecard_notify(struct devlink_linecard *linecard,
+				    enum devlink_command cmd)
+{
+	struct devlink *devlink = linecard->devlink;
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON(cmd != DEVLINK_CMD_LINECARD_NEW &&
+		cmd != DEVLINK_CMD_LINECARD_DEL);
+
+	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+		return;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_linecard_fill(msg, devlink, linecard, cmd, 0, 0, 0,
+				       NULL);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+void devlink_linecards_notify_register(struct devlink *devlink)
+{
+	struct devlink_linecard *linecard;
+
+	list_for_each_entry(linecard, &devlink->linecard_list, list)
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+}
+
+void devlink_linecards_notify_unregister(struct devlink *devlink)
+{
+	struct devlink_linecard *linecard;
+
+	list_for_each_entry_reverse(linecard, &devlink->linecard_list, list)
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
+}
+
+int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_linecard *linecard;
+	struct sk_buff *msg;
+	int err;
+
+	linecard = devlink_linecard_get_from_info(devlink, info);
+	if (IS_ERR(linecard))
+		return PTR_ERR(linecard);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	mutex_lock(&linecard->state_lock);
+	err = devlink_nl_linecard_fill(msg, devlink, linecard,
+				       DEVLINK_CMD_LINECARD_NEW,
+				       info->snd_portid, info->snd_seq, 0,
+				       info->extack);
+	mutex_unlock(&linecard->state_lock);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_linecard_get_dump_one(struct sk_buff *msg,
+					    struct devlink *devlink,
+					    struct netlink_callback *cb,
+					    int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_linecard *linecard;
+	int idx = 0;
+	int err = 0;
+
+	list_for_each_entry(linecard, &devlink->linecard_list, list) {
+		if (idx < state->idx) {
+			idx++;
+			continue;
+		}
+		mutex_lock(&linecard->state_lock);
+		err = devlink_nl_linecard_fill(msg, devlink, linecard,
+					       DEVLINK_CMD_LINECARD_NEW,
+					       NETLINK_CB(cb->skb).portid,
+					       cb->nlh->nlmsg_seq, flags,
+					       cb->extack);
+		mutex_unlock(&linecard->state_lock);
+		if (err) {
+			state->idx = idx;
+			break;
+		}
+		idx++;
+	}
+
+	return err;
+}
+
+int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_linecard_get_dump_one);
+}
+
+static struct devlink_linecard_type *
+devlink_linecard_type_lookup(struct devlink_linecard *linecard,
+			     const char *type)
+{
+	struct devlink_linecard_type *linecard_type;
+	int i;
+
+	for (i = 0; i < linecard->types_count; i++) {
+		linecard_type = &linecard->types[i];
+		if (!strcmp(type, linecard_type->type))
+			return linecard_type;
+	}
+	return NULL;
+}
+
+static int devlink_linecard_type_set(struct devlink_linecard *linecard,
+				     const char *type,
+				     struct netlink_ext_ack *extack)
+{
+	const struct devlink_linecard_ops *ops = linecard->ops;
+	struct devlink_linecard_type *linecard_type;
+	int err;
+
+	mutex_lock(&linecard->state_lock);
+	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
+		err = -EBUSY;
+		goto out;
+	}
+	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
+		err = -EBUSY;
+		goto out;
+	}
+
+	linecard_type = devlink_linecard_type_lookup(linecard, type);
+	if (!linecard_type) {
+		NL_SET_ERR_MSG(extack, "Unsupported line card type provided");
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED &&
+	    linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
+		NL_SET_ERR_MSG(extack, "Line card already provisioned");
+		err = -EBUSY;
+		/* Check if the line card is provisioned in the same
+		 * way the user asks. In case it is, make the operation
+		 * to return success.
+		 */
+		if (ops->same_provision &&
+		    ops->same_provision(linecard, linecard->priv,
+					linecard_type->type,
+					linecard_type->priv))
+			err = 0;
+		goto out;
+	}
+
+	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING;
+	linecard->type = linecard_type->type;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+	err = ops->provision(linecard, linecard->priv, linecard_type->type,
+			     linecard_type->priv, extack);
+	if (err) {
+		/* Provisioning failed. Assume the linecard is unprovisioned
+		 * for future operations.
+		 */
+		mutex_lock(&linecard->state_lock);
+		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+		linecard->type = NULL;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+		mutex_unlock(&linecard->state_lock);
+	}
+	return err;
+
+out:
+	mutex_unlock(&linecard->state_lock);
+	return err;
+}
+
+static int devlink_linecard_type_unset(struct devlink_linecard *linecard,
+				       struct netlink_ext_ack *extack)
+{
+	int err;
+
+	mutex_lock(&linecard->state_lock);
+	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being provisioned");
+		err = -EBUSY;
+		goto out;
+	}
+	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
+		NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned");
+		err = -EBUSY;
+		goto out;
+	}
+	if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
+		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+		linecard->type = NULL;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+		err = 0;
+		goto out;
+	}
+
+	if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) {
+		NL_SET_ERR_MSG(extack, "Line card is not provisioned");
+		err = 0;
+		goto out;
+	}
+	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+	err = linecard->ops->unprovision(linecard, linecard->priv,
+					 extack);
+	if (err) {
+		/* Unprovisioning failed. Assume the linecard is unprovisioned
+		 * for future operations.
+		 */
+		mutex_lock(&linecard->state_lock);
+		linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+		linecard->type = NULL;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+		mutex_unlock(&linecard->state_lock);
+	}
+	return err;
+
+out:
+	mutex_unlock(&linecard->state_lock);
+	return err;
+}
+
+int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_linecard *linecard;
+	int err;
+
+	linecard = devlink_linecard_get_from_info(devlink, info);
+	if (IS_ERR(linecard))
+		return PTR_ERR(linecard);
+
+	if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) {
+		const char *type;
+
+		type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]);
+		if (strcmp(type, "")) {
+			err = devlink_linecard_type_set(linecard, type, extack);
+			if (err)
+				return err;
+		} else {
+			err = devlink_linecard_type_unset(linecard, extack);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int devlink_linecard_types_init(struct devlink_linecard *linecard)
+{
+	struct devlink_linecard_type *linecard_type;
+	unsigned int count;
+	int i;
+
+	count = linecard->ops->types_count(linecard, linecard->priv);
+	linecard->types = kmalloc_array(count, sizeof(*linecard_type),
+					GFP_KERNEL);
+	if (!linecard->types)
+		return -ENOMEM;
+	linecard->types_count = count;
+
+	for (i = 0; i < count; i++) {
+		linecard_type = &linecard->types[i];
+		linecard->ops->types_get(linecard, linecard->priv, i,
+					 &linecard_type->type,
+					 &linecard_type->priv);
+	}
+	return 0;
+}
+
+static void devlink_linecard_types_fini(struct devlink_linecard *linecard)
+{
+	kfree(linecard->types);
+}
+
+/**
+ *	devl_linecard_create - Create devlink linecard
+ *
+ *	@devlink: devlink
+ *	@linecard_index: driver-specific numerical identifier of the linecard
+ *	@ops: linecards ops
+ *	@priv: user priv pointer
+ *
+ *	Create devlink linecard instance with provided linecard index.
+ *	Caller can use any indexing, even hw-related one.
+ *
+ *	Return: Line card structure or an ERR_PTR() encoded error code.
+ */
+struct devlink_linecard *
+devl_linecard_create(struct devlink *devlink, unsigned int linecard_index,
+		     const struct devlink_linecard_ops *ops, void *priv)
+{
+	struct devlink_linecard *linecard;
+	int err;
+
+	if (WARN_ON(!ops || !ops->provision || !ops->unprovision ||
+		    !ops->types_count || !ops->types_get))
+		return ERR_PTR(-EINVAL);
+
+	if (devlink_linecard_index_exists(devlink, linecard_index))
+		return ERR_PTR(-EEXIST);
+
+	linecard = kzalloc(sizeof(*linecard), GFP_KERNEL);
+	if (!linecard)
+		return ERR_PTR(-ENOMEM);
+
+	linecard->devlink = devlink;
+	linecard->index = linecard_index;
+	linecard->ops = ops;
+	linecard->priv = priv;
+	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+	mutex_init(&linecard->state_lock);
+
+	err = devlink_linecard_types_init(linecard);
+	if (err) {
+		mutex_destroy(&linecard->state_lock);
+		kfree(linecard);
+		return ERR_PTR(err);
+	}
+
+	list_add_tail(&linecard->list, &devlink->linecard_list);
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	return linecard;
+}
+EXPORT_SYMBOL_GPL(devl_linecard_create);
+
+/**
+ *	devl_linecard_destroy - Destroy devlink linecard
+ *
+ *	@linecard: devlink linecard
+ */
+void devl_linecard_destroy(struct devlink_linecard *linecard)
+{
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
+	list_del(&linecard->list);
+	devlink_linecard_types_fini(linecard);
+	mutex_destroy(&linecard->state_lock);
+	kfree(linecard);
+}
+EXPORT_SYMBOL_GPL(devl_linecard_destroy);
+
+/**
+ *	devlink_linecard_provision_set - Set provisioning on linecard
+ *
+ *	@linecard: devlink linecard
+ *	@type: linecard type
+ *
+ *	This is either called directly from the provision() op call or
+ *	as a result of the provision() op call asynchronously.
+ */
+void devlink_linecard_provision_set(struct devlink_linecard *linecard,
+				    const char *type)
+{
+	mutex_lock(&linecard->state_lock);
+	WARN_ON(linecard->type && strcmp(linecard->type, type));
+	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED;
+	linecard->type = type;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_provision_set);
+
+/**
+ *	devlink_linecard_provision_clear - Clear provisioning on linecard
+ *
+ *	@linecard: devlink linecard
+ *
+ *	This is either called directly from the unprovision() op call or
+ *	as a result of the unprovision() op call asynchronously.
+ */
+void devlink_linecard_provision_clear(struct devlink_linecard *linecard)
+{
+	mutex_lock(&linecard->state_lock);
+	WARN_ON(linecard->nested_devlink);
+	linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+	linecard->type = NULL;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_provision_clear);
+
+/**
+ *	devlink_linecard_provision_fail - Fail provisioning on linecard
+ *
+ *	@linecard: devlink linecard
+ *
+ *	This is either called directly from the provision() op call or
+ *	as a result of the provision() op call asynchronously.
+ */
+void devlink_linecard_provision_fail(struct devlink_linecard *linecard)
+{
+	mutex_lock(&linecard->state_lock);
+	WARN_ON(linecard->nested_devlink);
+	linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING_FAILED;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_provision_fail);
+
+/**
+ *	devlink_linecard_activate - Set linecard active
+ *
+ *	@linecard: devlink linecard
+ */
+void devlink_linecard_activate(struct devlink_linecard *linecard)
+{
+	mutex_lock(&linecard->state_lock);
+	WARN_ON(linecard->state != DEVLINK_LINECARD_STATE_PROVISIONED);
+	linecard->state = DEVLINK_LINECARD_STATE_ACTIVE;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_activate);
+
+/**
+ *	devlink_linecard_deactivate - Set linecard inactive
+ *
+ *	@linecard: devlink linecard
+ */
+void devlink_linecard_deactivate(struct devlink_linecard *linecard)
+{
+	mutex_lock(&linecard->state_lock);
+	switch (linecard->state) {
+	case DEVLINK_LINECARD_STATE_ACTIVE:
+		linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED;
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+		break;
+	case DEVLINK_LINECARD_STATE_UNPROVISIONING:
+		/* Line card is being deactivated as part
+		 * of unprovisioning flow.
+		 */
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+	mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_deactivate);
+
+/**
+ *	devlink_linecard_nested_dl_set - Attach/detach nested devlink
+ *					 instance to linecard.
+ *
+ *	@linecard: devlink linecard
+ *	@nested_devlink: devlink instance to attach or NULL to detach
+ */
+void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard,
+				    struct devlink *nested_devlink)
+{
+	mutex_lock(&linecard->state_lock);
+	linecard->nested_devlink = nested_devlink;
+	devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+	mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set);
-- 
GitLab


From 890c556674377c0abba4ab91ff6f1962175d578c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:55 +0200
Subject: [PATCH 1800/1806] devlink: move tracepoint definitions into core.c

Move remaining tracepoint definitions to most suitable file core.c.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-14-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/core.c     | 6 ++++++
 net/devlink/leftover.c | 6 ------
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/devlink/core.c b/net/devlink/core.c
index c23ebabadc526..6cec4afb01fbd 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -5,9 +5,15 @@
  */
 
 #include <net/genetlink.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/devlink.h>
 
 #include "devl_internal.h"
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
+EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
+EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
+
 DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC);
 
 void *devlink_priv(struct devlink *devlink)
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index 98ccb3a8393d8..a477cdbab940a 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -28,15 +28,9 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/devlink.h>
-#define CREATE_TRACE_POINTS
-#include <trace/events/devlink.h>
 
 #include "devl_internal.h"
 
-EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
-EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
-EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
-
 const struct genl_small_ops devlink_nl_small_ops[40] = {
 	{
 		.cmd = DEVLINK_CMD_PORT_SET,
-- 
GitLab


From 29a390d17748d93f9e6bc6fb0e09d89571aa25f6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:56 +0200
Subject: [PATCH 1801/1806] devlink: move small_ops definition into netlink.c

Move the generic netlink small_ops definition where they are consumed,
into netlink.c

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-15-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/devl_internal.h |   2 -
 net/devlink/leftover.c      | 251 ------------------------------------
 net/devlink/netlink.c       | 251 ++++++++++++++++++++++++++++++++++++
 3 files changed, 251 insertions(+), 253 deletions(-)

diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 8c81f731a4c74..efca6abf7af77 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -121,8 +121,6 @@ typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg,
 				       struct netlink_callback *cb,
 				       int flags);
 
-extern const struct genl_small_ops devlink_nl_small_ops[40];
-
 struct devlink *
 devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs);
 
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index a477cdbab940a..05e056d6d5ea9 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -31,257 +31,6 @@
 
 #include "devl_internal.h"
 
-const struct genl_small_ops devlink_nl_small_ops[40] = {
-	{
-		.cmd = DEVLINK_CMD_PORT_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_set_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_RATE_SET,
-		.doit = devlink_nl_cmd_rate_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_RATE_NEW,
-		.doit = devlink_nl_cmd_rate_new_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_RATE_DEL,
-		.doit = devlink_nl_cmd_rate_del_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_SPLIT,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_split_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_UNSPLIT,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_unsplit_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_NEW,
-		.doit = devlink_nl_cmd_port_new_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_DEL,
-		.doit = devlink_nl_cmd_port_del_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-
-	{
-		.cmd = DEVLINK_CMD_LINECARD_SET,
-		.doit = devlink_nl_cmd_linecard_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_POOL_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_pool_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_PORT_POOL_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_port_pool_set_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_occ_snapshot_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_sb_occ_max_clear_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_ESWITCH_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_eswitch_get_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_ESWITCH_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_eswitch_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_dpipe_table_get,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_dpipe_entries_get,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_dpipe_headers_get,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_dpipe_table_counters_set,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_RESOURCE_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_resource_set,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_RESOURCE_DUMP,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_resource_dump,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_RELOAD,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_reload,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_PARAM_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_param_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_PARAM_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_param_get_doit,
-		.dumpit = devlink_nl_cmd_port_param_get_dumpit,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-		/* can be retrieved by unprivileged users */
-	},
-	{
-		.cmd = DEVLINK_CMD_PORT_PARAM_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_port_param_set_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_REGION_NEW,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_region_new,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_REGION_DEL,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_region_del,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_REGION_READ,
-		.validate = GENL_DONT_VALIDATE_STRICT |
-			    GENL_DONT_VALIDATE_DUMP_STRICT,
-		.dumpit = devlink_nl_cmd_region_read_dumpit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_SET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_set_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_recover_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_diagnose_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT |
-			    GENL_DONT_VALIDATE_DUMP_STRICT,
-		.dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_dump_clear_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_health_reporter_test_doit,
-		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
-	},
-	{
-		.cmd = DEVLINK_CMD_FLASH_UPDATE,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = devlink_nl_cmd_flash_update,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_TRAP_SET,
-		.doit = devlink_nl_cmd_trap_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_TRAP_GROUP_SET,
-		.doit = devlink_nl_cmd_trap_group_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_TRAP_POLICER_SET,
-		.doit = devlink_nl_cmd_trap_policer_set_doit,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = DEVLINK_CMD_SELFTESTS_RUN,
-		.doit = devlink_nl_cmd_selftests_run,
-		.flags = GENL_ADMIN_PERM,
-	},
-	/* -- No new ops here! Use split ops going forward! -- */
-};
-
 void devlink_notify_register(struct devlink *devlink)
 {
 	devlink_notify(devlink, DEVLINK_CMD_NEW);
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 5f57afd31dea5..fc3e7c029a3be 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -255,6 +255,257 @@ int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 		return devlink_nl_inst_iter_dumpit(msg, cb, flags, dump_one);
 }
 
+static const struct genl_small_ops devlink_nl_small_ops[40] = {
+	{
+		.cmd = DEVLINK_CMD_PORT_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_port_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_SET,
+		.doit = devlink_nl_cmd_rate_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_NEW,
+		.doit = devlink_nl_cmd_rate_new_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_DEL,
+		.doit = devlink_nl_cmd_rate_del_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_SPLIT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_port_split_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_UNSPLIT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_port_unsplit_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_NEW,
+		.doit = devlink_nl_cmd_port_new_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_DEL,
+		.doit = devlink_nl_cmd_port_del_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+
+	{
+		.cmd = DEVLINK_CMD_LINECARD_SET,
+		.doit = devlink_nl_cmd_linecard_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_SB_POOL_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_sb_pool_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_SB_PORT_POOL_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_sb_port_pool_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_sb_occ_snapshot_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_sb_occ_max_clear_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_ESWITCH_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_eswitch_get_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_ESWITCH_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_eswitch_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_dpipe_table_get,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_dpipe_entries_get,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_dpipe_headers_get,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_dpipe_table_counters_set,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_RESOURCE_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_resource_set,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_RESOURCE_DUMP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_resource_dump,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_RELOAD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_reload,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_PARAM_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_param_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_PARAM_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_port_param_get_doit,
+		.dumpit = devlink_nl_cmd_port_param_get_dumpit,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_PARAM_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_port_param_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_REGION_NEW,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_region_new,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_REGION_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_region_del,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_REGION_READ,
+		.validate = GENL_DONT_VALIDATE_STRICT |
+			    GENL_DONT_VALIDATE_DUMP_STRICT,
+		.dumpit = devlink_nl_cmd_region_read_dumpit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_recover_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_diagnose_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT |
+			    GENL_DONT_VALIDATE_DUMP_STRICT,
+		.dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_dump_clear_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_test_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_FLASH_UPDATE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_flash_update,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_TRAP_SET,
+		.doit = devlink_nl_cmd_trap_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_TRAP_GROUP_SET,
+		.doit = devlink_nl_cmd_trap_group_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_TRAP_POLICER_SET,
+		.doit = devlink_nl_cmd_trap_policer_set_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_SELFTESTS_RUN,
+		.doit = devlink_nl_cmd_selftests_run,
+		.flags = GENL_ADMIN_PERM,
+	},
+	/* -- No new ops here! Use split ops going forward! -- */
+};
+
 struct genl_family devlink_nl_family __ro_after_init = {
 	.name		= DEVLINK_GENL_NAME,
 	.version	= DEVLINK_GENL_VERSION,
-- 
GitLab


From 71179ac5c21185171556bc438d5f22d566948d7f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 28 Aug 2023 08:16:57 +0200
Subject: [PATCH 1802/1806] devlink: move devlink_notify_register/unregister()
 to dev.c

At last, move the last bits out of leftover.c,
the devlink_notify_register/unregister() functions to dev.c

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230828061657.300667-16-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/Makefile        |  2 +-
 net/devlink/dev.c           | 28 +++++++++++++++++-
 net/devlink/devl_internal.h |  6 ++--
 net/devlink/leftover.c      | 58 -------------------------------------
 4 files changed, 30 insertions(+), 64 deletions(-)
 delete mode 100644 net/devlink/leftover.c

diff --git a/net/devlink/Makefile b/net/devlink/Makefile
index 71f490d301d7c..000da622116a3 100644
--- a/net/devlink/Makefile
+++ b/net/devlink/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-y := leftover.o core.o netlink.o netlink_gen.o dev.o port.o sb.o dpipe.o \
+obj-y := core.o netlink.o netlink_gen.o dev.o port.o sb.o dpipe.o \
 	 resource.o param.o region.o health.o trap.o rate.o linecard.o
diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index abf3393a7a175..bba4ace7d22ba 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -174,7 +174,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-void devlink_notify(struct devlink *devlink, enum devlink_command cmd)
+static void devlink_notify(struct devlink *devlink, enum devlink_command cmd)
 {
 	struct sk_buff *msg;
 	int err;
@@ -230,6 +230,32 @@ int devlink_nl_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb)
 	return devlink_nl_dumpit(msg, cb, devlink_nl_get_dump_one);
 }
 
+void devlink_notify_register(struct devlink *devlink)
+{
+	devlink_notify(devlink, DEVLINK_CMD_NEW);
+	devlink_linecards_notify_register(devlink);
+	devlink_ports_notify_register(devlink);
+	devlink_trap_policers_notify_register(devlink);
+	devlink_trap_groups_notify_register(devlink);
+	devlink_traps_notify_register(devlink);
+	devlink_rates_notify_register(devlink);
+	devlink_regions_notify_register(devlink);
+	devlink_params_notify_register(devlink);
+}
+
+void devlink_notify_unregister(struct devlink *devlink)
+{
+	devlink_params_notify_unregister(devlink);
+	devlink_regions_notify_unregister(devlink);
+	devlink_rates_notify_unregister(devlink);
+	devlink_traps_notify_unregister(devlink);
+	devlink_trap_groups_notify_unregister(devlink);
+	devlink_trap_policers_notify_unregister(devlink);
+	devlink_ports_notify_unregister(devlink);
+	devlink_linecards_notify_unregister(devlink);
+	devlink_notify(devlink, DEVLINK_CMD_DEL);
+}
+
 static void devlink_reload_failed_set(struct devlink *devlink,
 				      bool reload_failed)
 {
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index efca6abf7af77..f6b5fea2e13cd 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -124,9 +124,6 @@ typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg,
 struct devlink *
 devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs);
 
-void devlink_notify_unregister(struct devlink *devlink);
-void devlink_notify_register(struct devlink *devlink);
-
 int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 		      devlink_nl_dump_one_func_t *dump_one);
 
@@ -151,7 +148,8 @@ devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
 int devlink_nl_msg_reply_and_new(struct sk_buff **msg, struct genl_info *info);
 
 /* Notify */
-void devlink_notify(struct devlink *devlink, enum devlink_command cmd);
+void devlink_notify_register(struct devlink *devlink);
+void devlink_notify_unregister(struct devlink *devlink);
 void devlink_ports_notify_register(struct devlink *devlink);
 void devlink_ports_notify_unregister(struct devlink *devlink);
 void devlink_params_notify_register(struct devlink *devlink);
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
deleted file mode 100644
index 05e056d6d5ea9..0000000000000
--- a/net/devlink/leftover.c
+++ /dev/null
@@ -1,58 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * net/core/devlink.c - Network physical/parent device Netlink interface
- *
- * Heavily inspired by net/wireless/
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
- */
-
-#include <linux/etherdevice.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/gfp.h>
-#include <linux/device.h>
-#include <linux/list.h>
-#include <linux/netdevice.h>
-#include <linux/spinlock.h>
-#include <linux/refcount.h>
-#include <linux/workqueue.h>
-#include <linux/u64_stats_sync.h>
-#include <linux/timekeeping.h>
-#include <rdma/ib_verbs.h>
-#include <net/netlink.h>
-#include <net/genetlink.h>
-#include <net/rtnetlink.h>
-#include <net/net_namespace.h>
-#include <net/sock.h>
-#include <net/devlink.h>
-
-#include "devl_internal.h"
-
-void devlink_notify_register(struct devlink *devlink)
-{
-	devlink_notify(devlink, DEVLINK_CMD_NEW);
-	devlink_linecards_notify_register(devlink);
-	devlink_ports_notify_register(devlink);
-	devlink_trap_policers_notify_register(devlink);
-	devlink_trap_groups_notify_register(devlink);
-	devlink_traps_notify_register(devlink);
-	devlink_rates_notify_register(devlink);
-	devlink_regions_notify_register(devlink);
-	devlink_params_notify_register(devlink);
-}
-
-void devlink_notify_unregister(struct devlink *devlink)
-{
-	devlink_params_notify_unregister(devlink);
-	devlink_regions_notify_unregister(devlink);
-	devlink_rates_notify_unregister(devlink);
-	devlink_traps_notify_unregister(devlink);
-	devlink_trap_groups_notify_unregister(devlink);
-	devlink_trap_policers_notify_unregister(devlink);
-	devlink_ports_notify_unregister(devlink);
-	devlink_linecards_notify_unregister(devlink);
-	devlink_notify(devlink, DEVLINK_CMD_DEL);
-}
-- 
GitLab


From 72f93a3136ee18fd59fa6579f84c07e93424681e Mon Sep 17 00:00:00 2001
From: Antonio Napolitano <anton@polit.no>
Date: Sat, 26 Aug 2023 01:05:50 +0200
Subject: [PATCH 1803/1806] r8152: add vendor/device ID pair for D-Link
 DUB-E250

The D-Link DUB-E250 is an RTL8156 based 2.5G Ethernet controller.

Add the vendor and product ID values to the driver. This makes Ethernet
work with the adapter.

Signed-off-by: Antonio Napolitano <anton@polit.no>
Link: https://lore.kernel.org/r/CV200KJEEUPC.WPKAHXCQJ05I@mercurius
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c   | 1 +
 include/linux/usb/r8152.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index bb234cf0cea0f..332c853ca99b3 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -9832,6 +9832,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041) },
 	{ USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff) },
 	{ USB_DEVICE(VENDOR_ID_TPLINK,  0x0601) },
+	{ USB_DEVICE(VENDOR_ID_DLINK,   0xb301) },
 	{}
 };
 
diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h
index 20d88b1defc30..287e9d83fb8bc 100644
--- a/include/linux/usb/r8152.h
+++ b/include/linux/usb/r8152.h
@@ -29,6 +29,7 @@
 #define VENDOR_ID_LINKSYS		0x13b1
 #define VENDOR_ID_NVIDIA		0x0955
 #define VENDOR_ID_TPLINK		0x2357
+#define VENDOR_ID_DLINK			0x2001
 
 #if IS_REACHABLE(CONFIG_USB_RTL8152)
 extern u8 rtl8152_get_version(struct usb_interface *intf);
-- 
GitLab


From a014c35556b9045ece8426df2b38eb3c5e1c1aa0 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sat, 26 Aug 2023 11:02:51 +0100
Subject: [PATCH 1804/1806] net: stmmac: clarify difference between "interface"
 and "phy_interface"

Clarify the difference between "interface" and "phy_interface" in
struct plat_stmmacenet_data, both by adding a comment, and also
renaming "interface" to be "mac_interface". The difference between
these are:

 MAC ----- optional PCS ----- SerDes ----- optional PHY ----- Media
       ^                               ^
 mac_interface                   phy_interface

Note that phylink currently only deals with phy_interface.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qZq83-005tts-6K@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwmac-imx.c   | 14 ++++++-------
 .../ethernet/stmicro/stmmac/dwmac-ingenic.c   | 20 +++++++++----------
 .../ethernet/stmicro/stmmac/dwmac-loongson.c  |  2 +-
 .../ethernet/stmicro/stmmac/dwmac-lpc18xx.c   |  4 ++--
 .../ethernet/stmicro/stmmac/dwmac-mediatek.c  |  2 +-
 .../ethernet/stmicro/stmmac/dwmac-socfpga.c   |  2 +-
 .../ethernet/stmicro/stmmac/dwmac-starfive.c  |  4 ++--
 .../net/ethernet/stmicro/stmmac/dwmac-stm32.c |  8 ++++----
 .../net/ethernet/stmicro/stmmac/dwmac-sun8i.c |  6 +++---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c |  6 ++++--
 .../ethernet/stmicro/stmmac/stmmac_platform.c |  6 +++---
 include/linux/stmmac.h                        | 15 +++++++++++++-
 12 files changed, 52 insertions(+), 37 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 535856fffaea9..df34e34cc14fd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -70,7 +70,7 @@ static int imx8mp_set_intf_mode(struct plat_stmmacenet_data *plat_dat)
 	struct imx_priv_data *dwmac = plat_dat->bsp_priv;
 	int val;
 
-	switch (plat_dat->interface) {
+	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_MII:
 		val = GPR_ENET_QOS_INTF_SEL_MII;
 		break;
@@ -87,7 +87,7 @@ static int imx8mp_set_intf_mode(struct plat_stmmacenet_data *plat_dat)
 		break;
 	default:
 		pr_debug("imx dwmac doesn't support %d interface\n",
-			 plat_dat->interface);
+			 plat_dat->mac_interface);
 		return -EINVAL;
 	}
 
@@ -110,7 +110,7 @@ static int imx93_set_intf_mode(struct plat_stmmacenet_data *plat_dat)
 	struct imx_priv_data *dwmac = plat_dat->bsp_priv;
 	int val;
 
-	switch (plat_dat->interface) {
+	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_MII:
 		val = MX93_GPR_ENET_QOS_INTF_SEL_MII;
 		break;
@@ -125,7 +125,7 @@ static int imx93_set_intf_mode(struct plat_stmmacenet_data *plat_dat)
 		break;
 	default:
 		dev_dbg(dwmac->dev, "imx dwmac doesn't support %d interface\n",
-			 plat_dat->interface);
+			 plat_dat->mac_interface);
 		return -EINVAL;
 	}
 
@@ -192,8 +192,8 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod
 	plat_dat = dwmac->plat_dat;
 
 	if (dwmac->ops->mac_rgmii_txclk_auto_adj ||
-	    (plat_dat->interface == PHY_INTERFACE_MODE_RMII) ||
-	    (plat_dat->interface == PHY_INTERFACE_MODE_MII))
+	    (plat_dat->mac_interface == PHY_INTERFACE_MODE_RMII) ||
+	    (plat_dat->mac_interface == PHY_INTERFACE_MODE_MII))
 		return;
 
 	switch (speed) {
@@ -260,7 +260,7 @@ static int imx_dwmac_mx93_reset(void *priv, void __iomem *ioaddr)
 	value |= DMA_BUS_MODE_SFT_RESET;
 	writel(value, ioaddr + DMA_BUS_MODE);
 
-	if (plat_dat->interface == PHY_INTERFACE_MODE_RMII) {
+	if (plat_dat->mac_interface == PHY_INTERFACE_MODE_RMII) {
 		usleep_range(100, 200);
 		writel(RMII_RESET_SPEED, ioaddr + MAC_CTRL_REG);
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
index e22ef0d6bc73d..0a20c3d24722c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
@@ -89,7 +89,7 @@ static int jz4775_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
 	struct ingenic_mac *mac = plat_dat->bsp_priv;
 	unsigned int val;
 
-	switch (plat_dat->interface) {
+	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_MII:
 		val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) |
 			  FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_MII);
@@ -118,7 +118,7 @@ static int jz4775_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
 		break;
 
 	default:
-		dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface);
+		dev_err(mac->dev, "Unsupported interface %d", plat_dat->mac_interface);
 		return -EINVAL;
 	}
 
@@ -130,13 +130,13 @@ static int x1000_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
 {
 	struct ingenic_mac *mac = plat_dat->bsp_priv;
 
-	switch (plat_dat->interface) {
+	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_RMII:
 		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n");
 		break;
 
 	default:
-		dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface);
+		dev_err(mac->dev, "Unsupported interface %d", plat_dat->mac_interface);
 		return -EINVAL;
 	}
 
@@ -149,14 +149,14 @@ static int x1600_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
 	struct ingenic_mac *mac = plat_dat->bsp_priv;
 	unsigned int val;
 
-	switch (plat_dat->interface) {
+	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_RMII:
 		val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII);
 		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n");
 		break;
 
 	default:
-		dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface);
+		dev_err(mac->dev, "Unsupported interface %d", plat_dat->mac_interface);
 		return -EINVAL;
 	}
 
@@ -169,7 +169,7 @@ static int x1830_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
 	struct ingenic_mac *mac = plat_dat->bsp_priv;
 	unsigned int val;
 
-	switch (plat_dat->interface) {
+	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_RMII:
 		val = FIELD_PREP(MACPHYC_MODE_SEL_MASK, MACPHYC_MODE_SEL_RMII) |
 			  FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII);
@@ -177,7 +177,7 @@ static int x1830_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
 		break;
 
 	default:
-		dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface);
+		dev_err(mac->dev, "Unsupported interface %d", plat_dat->mac_interface);
 		return -EINVAL;
 	}
 
@@ -190,7 +190,7 @@ static int x2000_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
 	struct ingenic_mac *mac = plat_dat->bsp_priv;
 	unsigned int val;
 
-	switch (plat_dat->interface) {
+	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_RMII:
 		val = FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_ORIGIN) |
 			  FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_ORIGIN) |
@@ -220,7 +220,7 @@ static int x2000_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
 		break;
 
 	default:
-		dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface);
+		dev_err(mac->dev, "Unsupported interface %d", plat_dat->mac_interface);
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index a25c187d31853..2cd6fce5c9934 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -117,7 +117,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	}
 
 	plat->phy_interface = phy_mode;
-	plat->interface = PHY_INTERFACE_MODE_GMII;
+	plat->mac_interface = PHY_INTERFACE_MODE_GMII;
 
 	pci_set_master(pdev);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c
index 18e84ba693a65..d0aa674ce7053 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c
@@ -50,9 +50,9 @@ static int lpc18xx_dwmac_probe(struct platform_device *pdev)
 		goto err_remove_config_dt;
 	}
 
-	if (plat_dat->interface == PHY_INTERFACE_MODE_MII) {
+	if (plat_dat->mac_interface == PHY_INTERFACE_MODE_MII) {
 		ethmode = LPC18XX_CREG_CREG6_ETHMODE_MII;
-	} else if (plat_dat->interface == PHY_INTERFACE_MODE_RMII) {
+	} else if (plat_dat->mac_interface == PHY_INTERFACE_MODE_RMII) {
 		ethmode = LPC18XX_CREG_CREG6_ETHMODE_RMII;
 	} else {
 		dev_err(&pdev->dev, "Only MII and RMII mode supported\n");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index 7580077383c0a..cd796ec04132d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -587,7 +587,7 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev,
 {
 	int i;
 
-	plat->interface = priv_plat->phy_mode;
+	plat->mac_interface = priv_plat->phy_mode;
 	if (priv_plat->mac_wol)
 		plat->flags |= STMMAC_FLAG_USE_PHY_WOL;
 	else
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 7db176e8691f8..9bf102bbc6a00 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -236,7 +236,7 @@ static int socfpga_get_plat_phymode(struct socfpga_dwmac *dwmac)
 	struct net_device *ndev = dev_get_drvdata(dwmac->dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
 
-	return priv->plat->interface;
+	return priv->plat->mac_interface;
 }
 
 static void socfpga_sgmii_config(struct socfpga_dwmac *dwmac, bool enable)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
index 8926125646945..9289bb87c3e3a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
@@ -60,7 +60,7 @@ static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat)
 	unsigned int mode;
 	int err;
 
-	switch (plat_dat->interface) {
+	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_RMII:
 		mode = STARFIVE_DWMAC_PHY_INFT_RMII;
 		break;
@@ -72,7 +72,7 @@ static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat)
 
 	default:
 		dev_err(dwmac->dev, "unsupported interface %d\n",
-			plat_dat->interface);
+			plat_dat->mac_interface);
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
index 3a09085819dc5..26ea8c687881c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
@@ -171,7 +171,7 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat)
 
 	clk_rate = clk_get_rate(dwmac->clk_eth_ck);
 	dwmac->enable_eth_ck = false;
-	switch (plat_dat->interface) {
+	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_MII:
 		if (clk_rate == ETH_CK_F_25M && dwmac->ext_phyclk)
 			dwmac->enable_eth_ck = true;
@@ -210,7 +210,7 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat)
 		break;
 	default:
 		pr_debug("SYSCFG init :  Do not manage %d interface\n",
-			 plat_dat->interface);
+			 plat_dat->mac_interface);
 		/* Do not manage others interfaces */
 		return -EINVAL;
 	}
@@ -230,7 +230,7 @@ static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat)
 	u32 reg = dwmac->mode_reg;
 	int val;
 
-	switch (plat_dat->interface) {
+	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_MII:
 		val = SYSCFG_MCU_ETH_SEL_MII;
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_MII\n");
@@ -241,7 +241,7 @@ static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat)
 		break;
 	default:
 		pr_debug("SYSCFG init :  Do not manage %d interface\n",
-			 plat_dat->interface);
+			 plat_dat->mac_interface);
 		/* Do not manage others interfaces */
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index c23420863a8d3..01e77368eef1c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -1016,7 +1016,7 @@ static int sun8i_dwmac_set_syscon(struct device *dev,
 	if (gmac->variant->support_rmii)
 		reg &= ~SYSCON_RMII_EN;
 
-	switch (plat->interface) {
+	switch (plat->mac_interface) {
 	case PHY_INTERFACE_MODE_MII:
 		/* default */
 		break;
@@ -1031,7 +1031,7 @@ static int sun8i_dwmac_set_syscon(struct device *dev,
 		break;
 	default:
 		dev_err(dev, "Unsupported interface mode: %s",
-			phy_modes(plat->interface));
+			phy_modes(plat->mac_interface));
 		return -EINVAL;
 	}
 
@@ -1231,7 +1231,7 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	/* platform data specifying hardware features and callbacks.
 	 * hardware features were copied from Allwinner drivers.
 	 */
-	plat_dat->interface = interface;
+	plat_dat->mac_interface = interface;
 	plat_dat->rx_coe = STMMAC_RX_COE_TYPE2;
 	plat_dat->tx_coe = 1;
 	plat_dat->flags |= STMMAC_FLAG_HAS_SUN8I;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 33ca5c50bdcd8..9a3182b9e767c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1119,7 +1119,7 @@ static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
  */
 static void stmmac_check_pcs_mode(struct stmmac_priv *priv)
 {
-	int interface = priv->plat->interface;
+	int interface = priv->plat->mac_interface;
 
 	if (priv->dma_cap.pcs) {
 		if ((interface == PHY_INTERFACE_MODE_RGMII) ||
@@ -1214,7 +1214,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 		priv->phylink_config.ovr_an_inband =
 			mdio_bus_data->xpcs_an_inband;
 
-	/* Set the platform/firmware specified interface mode */
+	/* Set the platform/firmware specified interface mode. Note, phylink
+	 * deals with the PHY interface mode, not the MAC interface mode.
+	 */
 	__set_bit(mode, priv->phylink_config.supported_interfaces);
 
 	/* If we have an xpcs, it defines which PHY interfaces are supported. */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index ff330423ee661..35f4b1484029b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -419,9 +419,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 		return ERR_PTR(phy_mode);
 
 	plat->phy_interface = phy_mode;
-	plat->interface = stmmac_of_get_mac_mode(np);
-	if (plat->interface < 0)
-		plat->interface = plat->phy_interface;
+	plat->mac_interface = stmmac_of_get_mac_mode(np);
+	if (plat->mac_interface < 0)
+		plat->mac_interface = plat->phy_interface;
 
 	/* Some wrapper drivers still rely on phy_node. Let's save it while
 	 * they are not converted to phylink. */
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index b2ccd827bb801..ce89cc3e49135 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -223,7 +223,20 @@ struct dwmac4_addrs {
 struct plat_stmmacenet_data {
 	int bus_id;
 	int phy_addr;
-	int interface;
+	/* MAC ----- optional PCS ----- SerDes ----- optional PHY ----- Media
+	 *       ^                               ^
+	 * mac_interface                   phy_interface
+	 *
+	 * mac_interface is the MAC-side interface, which may be the same
+	 * as phy_interface if there is no intervening PCS. If there is a
+	 * PCS, then mac_interface describes the interface mode between the
+	 * MAC and PCS, and phy_interface describes the interface mode
+	 * between the PCS and PHY.
+	 */
+	phy_interface_t mac_interface;
+	/* phy_interface is the PHY-side interface - the interface used by
+	 * an attached PHY.
+	 */
 	phy_interface_t phy_interface;
 	struct stmmac_mdio_bus_data *mdio_bus_data;
 	struct device_node *phy_node;
-- 
GitLab


From 042bf24ac98702e0b240034f6a8b219104095b06 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sun, 27 Aug 2023 19:31:41 +0200
Subject: [PATCH 1805/1806] net: ethernet: mtk_wed: add some more info in
 wed_txinfo_show handler

Add some new info in Wireless Ethernet Dispatcher wed_txinfo_show
debugfs handler useful during debugging.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/3390292655d568180b73d2a25576f61aa63310e5.1693157377.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_wed_debugfs.c | 11 ++++++++++-
 drivers/net/ethernet/mediatek/mtk_wed_regs.h    |  2 ++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c b/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c
index b244c02c5b511..5446d3be1c3a9 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c
@@ -127,8 +127,17 @@ wed_txinfo_show(struct seq_file *s, void *data)
 		DUMP_WDMA_RING(WDMA_RING_RX(0)),
 		DUMP_WDMA_RING(WDMA_RING_RX(1)),
 
-		DUMP_STR("TX FREE"),
+		DUMP_STR("WED TX FREE"),
 		DUMP_WED(WED_RX_MIB(0)),
+		DUMP_WED_RING(WED_RING_RX(0)),
+		DUMP_WED(WED_WPDMA_RX_COHERENT_MIB(0)),
+		DUMP_WED(WED_RX_MIB(1)),
+		DUMP_WED_RING(WED_RING_RX(1)),
+		DUMP_WED(WED_WPDMA_RX_COHERENT_MIB(1)),
+
+		DUMP_STR("WED WPDMA TX FREE"),
+		DUMP_WED_RING(WED_WPDMA_RING_RX(0)),
+		DUMP_WED_RING(WED_WPDMA_RING_RX(1)),
 	};
 	struct mtk_wed_hw *hw = s->private;
 	struct mtk_wed_device *dev = hw->wed_dev;
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_regs.h b/drivers/net/ethernet/mediatek/mtk_wed_regs.h
index 0a50bb98c5ea4..47ea69feb3b24 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_regs.h
+++ b/drivers/net/ethernet/mediatek/mtk_wed_regs.h
@@ -266,6 +266,8 @@ struct mtk_wdma_desc {
 
 #define MTK_WED_WPDMA_TX_MIB(_n)			(0x5a0 + (_n) * 4)
 #define MTK_WED_WPDMA_TX_COHERENT_MIB(_n)		(0x5d0 + (_n) * 4)
+#define MTK_WED_WPDMA_RX_MIB(_n)			(0x5e0 + (_n) * 4)
+#define MTK_WED_WPDMA_RX_COHERENT_MIB(_n)		(0x5f0 + (_n) * 4)
 
 #define MTK_WED_WPDMA_RING_TX(_n)			(0x600 + (_n) * 0x10)
 #define MTK_WED_WPDMA_RING_RX(_n)			(0x700 + (_n) * 0x10)
-- 
GitLab


From 6c9cfb853063f317b2953c5e852b6bac1eb0cade Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sun, 27 Aug 2023 19:33:47 +0200
Subject: [PATCH 1806/1806] net: ethernet: mtk_wed: minor change in
 wed_{tx,rx}info_show

No functional changes, just cosmetic ones.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/71e046c72a978745f0435af265dda610aa9bfbcf.1693157578.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_wed_debugfs.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c b/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c
index 5446d3be1c3a9..e24afeaea0da8 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c
@@ -84,7 +84,6 @@ dump_wed_regs(struct seq_file *s, struct mtk_wed_device *dev,
 	}
 }
 
-
 static int
 wed_txinfo_show(struct seq_file *s, void *data)
 {
@@ -142,10 +141,8 @@ wed_txinfo_show(struct seq_file *s, void *data)
 	struct mtk_wed_hw *hw = s->private;
 	struct mtk_wed_device *dev = hw->wed_dev;
 
-	if (!dev)
-		return 0;
-
-	dump_wed_regs(s, dev, regs, ARRAY_SIZE(regs));
+	if (dev)
+		dump_wed_regs(s, dev, regs, ARRAY_SIZE(regs));
 
 	return 0;
 }
@@ -217,10 +214,8 @@ wed_rxinfo_show(struct seq_file *s, void *data)
 	struct mtk_wed_hw *hw = s->private;
 	struct mtk_wed_device *dev = hw->wed_dev;
 
-	if (!dev)
-		return 0;
-
-	dump_wed_regs(s, dev, regs, ARRAY_SIZE(regs));
+	if (dev)
+		dump_wed_regs(s, dev, regs, ARRAY_SIZE(regs));
 
 	return 0;
 }
-- 
GitLab